diff options
Diffstat (limited to 'drivers/net/xen-netback')
| -rw-r--r-- | drivers/net/xen-netback/common.h | 107 | ||||
| -rw-r--r-- | drivers/net/xen-netback/interface.c | 130 | ||||
| -rw-r--r-- | drivers/net/xen-netback/netback.c | 766 |
3 files changed, 709 insertions, 294 deletions
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index ae413a2cbee7..89b2d429c440 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -48,37 +48,19 @@ typedef unsigned int pending_ring_idx_t; #define INVALID_PENDING_RING_IDX (~0U) -/* For the head field in pending_tx_info: it is used to indicate - * whether this tx info is the head of one or more coalesced requests. - * - * When head != INVALID_PENDING_RING_IDX, it means the start of a new - * tx requests queue and the end of previous queue. - * - * An example sequence of head fields (I = INVALID_PENDING_RING_IDX): - * - * ...|0 I I I|5 I|9 I I I|... - * -->|<-INUSE---------------- - * - * After consuming the first slot(s) we have: - * - * ...|V V V V|5 I|9 I I I|... - * -----FREE->|<-INUSE-------- - * - * where V stands for "valid pending ring index". Any number other - * than INVALID_PENDING_RING_IDX is OK. These entries are considered - * free and can contain any number other than - * INVALID_PENDING_RING_IDX. In practice we use 0. - * - * The in use non-INVALID_PENDING_RING_IDX (say 0, 5 and 9 in the - * above example) number is the index into pending_tx_info and - * mmap_pages arrays. - */ struct pending_tx_info { - struct xen_netif_tx_request req; /* coalesced tx request */ - pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX - * if it is head of one or more tx - * reqs - */ + struct xen_netif_tx_request req; /* tx request */ + /* Callback data for released SKBs. The callback is always + * xenvif_zerocopy_callback, desc contains the pending_idx, which is + * also an index in pending_tx_info array. It is initialized in + * xenvif_alloc and it never changes. + * skb_shinfo(skb)->destructor_arg points to the first mapped slot's + * callback_struct in this array of struct pending_tx_info's, then ctx + * to the next, or NULL if there is no more slot for this skb. + * ubuf_to_vif is a helper which finds the struct xenvif from a pointer + * to this field. + */ + struct ubuf_info callback_struct; }; #define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE) @@ -99,7 +81,7 @@ struct xenvif_rx_meta { #define MAX_BUFFER_OFFSET PAGE_SIZE -#define MAX_PENDING_REQS 256 +#define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE /* 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 @@ -108,6 +90,15 @@ struct xenvif_rx_meta { */ #define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE) +#define NETBACK_INVALID_HANDLE -1 + +/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating + * the maximum slots a valid packet can use. Now this value is defined + * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by + * all backend. + */ +#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN + struct xenvif { /* Unique identifier for this interface. */ domid_t domid; @@ -126,13 +117,26 @@ struct xenvif { pending_ring_idx_t pending_cons; u16 pending_ring[MAX_PENDING_REQS]; struct pending_tx_info pending_tx_info[MAX_PENDING_REQS]; - - /* Coalescing tx requests before copying makes number of grant - * copy ops greater or equal to number of slots required. In - * worst case a tx request consumes 2 gnttab_copy. + grant_handle_t grant_tx_handle[MAX_PENDING_REQS]; + + struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS]; + struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS]; + /* passed to gnttab_[un]map_refs with pages under (un)mapping */ + struct page *pages_to_map[MAX_PENDING_REQS]; + struct page *pages_to_unmap[MAX_PENDING_REQS]; + + /* This prevents zerocopy callbacks to race over dealloc_ring */ + spinlock_t callback_lock; + /* This prevents dealloc thread and NAPI instance to race over response + * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err + * it only protect response creation */ - struct gnttab_copy tx_copy_ops[2*MAX_PENDING_REQS]; - + spinlock_t response_lock; + pending_ring_idx_t dealloc_prod; + pending_ring_idx_t dealloc_cons; + u16 dealloc_ring[MAX_PENDING_REQS]; + struct task_struct *dealloc_task; + wait_queue_head_t dealloc_wq; /* Use kthread for guest RX */ struct task_struct *task; @@ -144,6 +148,9 @@ struct xenvif { struct xen_netif_rx_back_ring rx; struct sk_buff_head rx_queue; RING_IDX rx_last_skb_slots; + bool rx_queue_purge; + + struct timer_list wake_queue; /* This array is allocated seperately as it is large */ struct gnttab_copy *grant_copy_op; @@ -175,6 +182,10 @@ struct xenvif { /* Statistics */ unsigned long rx_gso_checksum_fixup; + unsigned long tx_zerocopy_sent; + unsigned long tx_zerocopy_success; + unsigned long tx_zerocopy_fail; + unsigned long tx_frag_overflow; /* Miscellaneous private stuff. */ struct net_device *dev; @@ -216,9 +227,11 @@ void xenvif_carrier_off(struct xenvif *vif); int xenvif_tx_action(struct xenvif *vif, int budget); -int xenvif_kthread(void *data); +int xenvif_kthread_guest_rx(void *data); void xenvif_kick_thread(struct xenvif *vif); +int xenvif_dealloc_kthread(void *data); + /* Determine whether the needed number of slots (req) are available, * and set req_event if not. */ @@ -226,6 +239,24 @@ bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed); void xenvif_stop_queue(struct xenvif *vif); +/* Callback from stack when TX packet can be released */ +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); + +/* Unmap a pending page and release it back to the guest */ +void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx); + +static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif) +{ + return MAX_PENDING_REQS - + vif->pending_prod + vif->pending_cons; +} + +/* Callback from stack when TX packet can be released */ +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); + extern bool separate_tx_rx_irq; +extern unsigned int rx_drain_timeout_msecs; +extern unsigned int rx_drain_timeout_jiffies; + #endif /* __XEN_NETBACK__COMMON_H__ */ diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 301cc037fda8..cdc298e3b747 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -38,6 +38,7 @@ #include <xen/events.h> #include <asm/xen/hypercall.h> +#include <xen/balloon.h> #define XENVIF_QUEUE_LENGTH 32 #define XENVIF_NAPI_WEIGHT 64 @@ -113,6 +114,18 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static void xenvif_wake_queue(unsigned long data) +{ + struct xenvif *vif = (struct xenvif *)data; + + if (netif_queue_stopped(vif->dev)) { + netdev_err(vif->dev, "draining TX queue\n"); + vif->rx_queue_purge = true; + xenvif_kick_thread(vif); + netif_wake_queue(vif->dev); + } +} + static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); @@ -121,7 +134,9 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) BUG_ON(skb->dev != dev); /* Drop the packet if vif is not ready */ - if (vif->task == NULL || !xenvif_schedulable(vif)) + if (vif->task == NULL || + vif->dealloc_task == NULL || + !xenvif_schedulable(vif)) goto drop; /* At best we'll need one slot for the header and one for each @@ -139,8 +154,13 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) * then turn off the queue to give the ring a chance to * drain. */ - if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) + if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) { + vif->wake_queue.function = xenvif_wake_queue; + vif->wake_queue.data = (unsigned long)vif; xenvif_stop_queue(vif); + mod_timer(&vif->wake_queue, + jiffies + rx_drain_timeout_jiffies); + } skb_queue_tail(&vif->rx_queue, skb); xenvif_kick_thread(vif); @@ -233,6 +253,28 @@ static const struct xenvif_stat { "rx_gso_checksum_fixup", offsetof(struct xenvif, rx_gso_checksum_fixup) }, + /* If (sent != success + fail), there are probably packets never + * freed up properly! + */ + { + "tx_zerocopy_sent", + offsetof(struct xenvif, tx_zerocopy_sent), + }, + { + "tx_zerocopy_success", + offsetof(struct xenvif, tx_zerocopy_success), + }, + { + "tx_zerocopy_fail", + offsetof(struct xenvif, 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, tx_frag_overflow) + }, }; static int xenvif_get_sset_count(struct net_device *dev, int string_set) @@ -326,6 +368,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, init_timer(&vif->credit_timeout); vif->credit_window_start = get_jiffies_64(); + init_timer(&vif->wake_queue); + dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -342,8 +386,26 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, 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; + spin_lock_init(&vif->callback_lock); + spin_lock_init(&vif->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 = alloc_xenballooned_pages(MAX_PENDING_REQS, + vif->mmap_pages, + false); + if (err) { + netdev_err(dev, "Could not reserve mmap_pages\n"); + return ERR_PTR(-ENOMEM); + } + for (i = 0; i < MAX_PENDING_REQS; i++) { + vif->pending_tx_info[i].callback_struct = (struct ubuf_info) + { .callback = xenvif_zerocopy_callback, + .ctx = NULL, + .desc = i }; + vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; + } /* * Initialise a dummy MAC address. We choose the numerically @@ -381,12 +443,14 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, BUG_ON(vif->tx_irq); BUG_ON(vif->task); + BUG_ON(vif->dealloc_task); err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); if (err < 0) goto err; init_waitqueue_head(&vif->wq); + init_waitqueue_head(&vif->dealloc_wq); if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ @@ -420,8 +484,8 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, disable_irq(vif->rx_irq); } - task = kthread_create(xenvif_kthread, - (void *)vif, "%s", vif->dev->name); + task = kthread_create(xenvif_kthread_guest_rx, + (void *)vif, "%s-guest-rx", vif->dev->name); if (IS_ERR(task)) { pr_warn("Could not allocate kthread for %s\n", vif->dev->name); err = PTR_ERR(task); @@ -430,6 +494,16 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, vif->task = task; + task = kthread_create(xenvif_dealloc_kthread, + (void *)vif, "%s-dealloc", vif->dev->name); + if (IS_ERR(task)) { + pr_warn("Could not allocate kthread for %s\n", vif->dev->name); + err = PTR_ERR(task); + goto err_rx_unbind; + } + + vif->dealloc_task = task; + rtnl_lock(); if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) dev_set_mtu(vif->dev, ETH_DATA_LEN); @@ -440,6 +514,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, rtnl_unlock(); wake_up_process(vif->task); + wake_up_process(vif->dealloc_task); return 0; @@ -473,10 +548,16 @@ void xenvif_disconnect(struct xenvif *vif) xenvif_carrier_off(vif); if (vif->task) { + del_timer_sync(&vif->wake_queue); kthread_stop(vif->task); vif->task = NULL; } + if (vif->dealloc_task) { + kthread_stop(vif->dealloc_task); + vif->dealloc_task = NULL; + } + if (vif->tx_irq) { if (vif->tx_irq == vif->rx_irq) unbind_from_irqhandler(vif->tx_irq, vif); @@ -492,6 +573,43 @@ void xenvif_disconnect(struct xenvif *vif) void xenvif_free(struct xenvif *vif) { + int i, unmap_timeout = 0; + /* Here we want to avoid timeout messages if an skb can be legitimately + * stuck somewhere else. Realistically this could be an another vif's + * internal or QDisc queue. That another vif also has this + * rx_drain_timeout_msecs timeout, but the timer only ditches the + * internal queue. After that, the QDisc queue can put in worst case + * XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS skbs into that another vif's + * internal queue, so we need several rounds of such timeouts until we + * can be sure that no another vif should have skb's from us. We are + * not sending more skb's, so newly stuck packets are not interesting + * for us here. + */ + unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000) * + DIV_ROUND_UP(XENVIF_QUEUE_LENGTH, (XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS)); + + for (i = 0; i < MAX_PENDING_REQS; ++i) { + if (vif->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) { + unmap_timeout++; + schedule_timeout(msecs_to_jiffies(1000)); + if (unmap_timeout > worst_case_skb_lifetime && + net_ratelimit()) + netdev_err(vif->dev, + "Page still granted! Index: %x\n", + i); + /* If there are still unmapped pages, reset the loop to + * start checking again. We shouldn't exit here until + * dealloc thread and NAPI instance release all the + * pages. If a kernel bug causes the skbs to stall + * somewhere, the interface cannot be brought down + * properly. + */ + i = -1; + } + } + + free_xenballooned_pages(MAX_PENDING_REQS, vif->mmap_pages); + netif_napi_del(&vif->napi); unregister_netdev(vif->dev); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index cd0bd95ccc14..ae34f5fc7fbc 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -37,6 +37,7 @@ #include <linux/kthread.h> #include <linux/if_vlan.h> #include <linux/udp.h> +#include <linux/highmem.h> #include <net/tcp.h> @@ -54,6 +55,13 @@ bool separate_tx_rx_irq = 1; module_param(separate_tx_rx_irq, bool, 0644); +/* When guest ring is filled up, qdisc queues the packets for us, but we have + * to timeout them, otherwise other guests' packets can get stuck there + */ +unsigned int rx_drain_timeout_msecs = 10000; +module_param(rx_drain_timeout_msecs, uint, 0444); +unsigned int rx_drain_timeout_jiffies; + /* * This is the maximum slots a skb can have. If a guest sends a skb * which exceeds this limit it is considered malicious. @@ -62,24 +70,6 @@ module_param(separate_tx_rx_irq, bool, 0644); static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT; module_param(fatal_skb_slots, uint, 0444); -/* - * To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating - * the maximum slots a valid packet can use. Now this value is defined - * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by - * all backend. - */ -#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN - -/* - * If head != INVALID_PENDING_RING_IDX, it means this tx request is head of - * one or more merged tx requests, otherwise it is the continuation of - * previous tx request. - */ -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 xenvif_idx_release(struct xenvif *vif, u16 pending_idx, u8 status); @@ -109,6 +99,21 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif, return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx)); } +#define callback_param(vif, pending_idx) \ + (vif->pending_tx_info[pending_idx].callback_struct) + +/* Find the containing VIF's structure from a pointer in pending_tx_info array + */ +static inline struct xenvif* ubuf_to_vif(struct ubuf_info *ubuf) +{ + u16 pending_idx = ubuf->desc; + struct pending_tx_info *temp = + container_of(ubuf, struct pending_tx_info, callback_struct); + return container_of(temp - pending_idx, + struct xenvif, + pending_tx_info[0]); +} + /* This is a miniumum size for the linear area to avoid lots of * calls to __pskb_pull_tail() as we set up checksum offsets. The * value 128 was chosen as it covers all IPv4 and most likely @@ -131,12 +136,6 @@ static inline pending_ring_idx_t pending_index(unsigned i) return i & (MAX_PENDING_REQS-1); } -static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif) -{ - return MAX_PENDING_REQS - - vif->pending_prod + vif->pending_cons; -} - bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed) { RING_IDX prod, cons; @@ -235,7 +234,9 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif, 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) + unsigned long offset, int *head, + struct xenvif *foreign_vif, + grant_ref_t foreign_gref) { struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; @@ -277,8 +278,15 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, copy_gop->flags = GNTCOPY_dest_gref; copy_gop->len = bytes; - copy_gop->source.domid = DOMID_SELF; - copy_gop->source.u.gmfn = virt_to_mfn(page_address(page)); + if (foreign_vif) { + copy_gop->source.domid = foreign_vif->domid; + copy_gop->source.u.ref = foreign_gref; + copy_gop->flags |= GNTCOPY_source_gref; + } else { + copy_gop->source.domid = DOMID_SELF; + copy_gop->source.u.gmfn = + virt_to_mfn(page_address(page)); + } copy_gop->source.offset = offset; copy_gop->dest.domid = vif->domid; @@ -338,6 +346,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, int head = 1; int old_meta_prod; int gso_type; + struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg; + grant_ref_t foreign_grefs[MAX_SKB_FRAGS]; + struct xenvif *foreign_vif = NULL; old_meta_prod = npo->meta_prod; @@ -375,6 +386,19 @@ static int xenvif_gop_skb(struct sk_buff *skb, npo->copy_off = 0; npo->copy_gref = req->gref; + if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) && + (ubuf->callback == &xenvif_zerocopy_callback)) { + int i = 0; + foreign_vif = ubuf_to_vif(ubuf); + + do { + u16 pending_idx = ubuf->desc; + foreign_grefs[i++] = + foreign_vif->pending_tx_info[pending_idx].req.gref; + ubuf = (struct ubuf_info *) ubuf->ctx; + } while (ubuf); + } + data = skb->data; while (data < skb_tail_pointer(skb)) { unsigned int offset = offset_in_page(data); @@ -384,7 +408,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, len = skb_tail_pointer(skb) - data; xenvif_gop_frag_copy(vif, skb, npo, - virt_to_page(data), len, offset, &head); + virt_to_page(data), len, offset, &head, + NULL, + 0); data += len; } @@ -393,7 +419,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, skb_frag_page(&skb_shinfo(skb)->frags[i]), skb_frag_size(&skb_shinfo(skb)->frags[i]), skb_shinfo(skb)->frags[i].page_offset, - &head); + &head, + foreign_vif, + foreign_grefs[i]); } return npo->meta_prod - old_meta_prod; @@ -451,10 +479,12 @@ static void xenvif_add_frag_responses(struct xenvif *vif, int status, } } -struct skb_cb_overlay { +struct xenvif_rx_cb { int meta_slots_used; }; +#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) + void xenvif_kick_thread(struct xenvif *vif) { wake_up(&vif->wq); @@ -470,7 +500,6 @@ static void xenvif_rx_action(struct xenvif *vif) LIST_HEAD(notify); int ret; unsigned long offset; - struct skb_cb_overlay *sco; bool need_to_notify = false; struct netrx_pending_operations npo = { @@ -531,10 +560,8 @@ static void xenvif_rx_action(struct xenvif *vif) } else vif->rx_last_skb_slots = 0; - sco = (struct skb_cb_overlay *)skb->cb; - old_req_cons = vif->rx.req_cons; - sco->meta_slots_used = xenvif_gop_skb(skb, &npo); + XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo); ring_slots_used = vif->rx.req_cons - old_req_cons; BUG_ON(ring_slots_used > max_slots_needed); @@ -551,7 +578,6 @@ static void xenvif_rx_action(struct xenvif *vif) gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod); while ((skb = __skb_dequeue(&rxq)) != NULL) { - sco = (struct skb_cb_overlay *)skb->cb; if ((1 << vif->meta[npo.meta_cons].gso_type) & vif->gso_prefix_mask) { @@ -562,19 +588,21 @@ static void xenvif_rx_action(struct xenvif *vif) resp->offset = vif->meta[npo.meta_cons].gso_size; resp->id = vif->meta[npo.meta_cons].id; - resp->status = sco->meta_slots_used; + resp->status = XENVIF_RX_CB(skb)->meta_slots_used; npo.meta_cons++; - sco->meta_slots_used--; + XENVIF_RX_CB(skb)->meta_slots_used--; } vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - status = xenvif_check_gop(vif, sco->meta_slots_used, &npo); + status = xenvif_check_gop(vif, + XENVIF_RX_CB(skb)->meta_slots_used, + &npo); - if (sco->meta_slots_used == 1) + if (XENVIF_RX_CB(skb)->meta_slots_used == 1) flags = 0; else flags = XEN_NETRXF_more_data; @@ -611,13 +639,13 @@ static void xenvif_rx_action(struct xenvif *vif) xenvif_add_frag_responses(vif, status, vif->meta + npo.meta_cons + 1, - sco->meta_slots_used); + XENVIF_RX_CB(skb)->meta_slots_used); RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret); need_to_notify |= !!ret; - npo.meta_cons += sco->meta_slots_used; + npo.meta_cons += XENVIF_RX_CB(skb)->meta_slots_used; dev_kfree_skb(skb); } @@ -667,9 +695,12 @@ static void xenvif_tx_err(struct xenvif *vif, struct xen_netif_tx_request *txp, RING_IDX end) { RING_IDX cons = vif->tx.req_cons; + unsigned long flags; do { + spin_lock_irqsave(&vif->response_lock, flags); make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); + spin_unlock_irqrestore(&vif->response_lock, flags); if (cons == end) break; txp = RING_GET_REQUEST(&vif->tx, cons++); @@ -781,180 +812,168 @@ static int xenvif_count_requests(struct xenvif *vif, return slots; } -static struct page *xenvif_alloc_page(struct xenvif *vif, - u16 pending_idx) + +struct xenvif_tx_cb { + u16 pending_idx; +}; + +#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) + +static inline void xenvif_tx_create_gop(struct xenvif *vif, + u16 pending_idx, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *gop) { - struct page *page; + vif->pages_to_map[gop-vif->tx_map_ops] = vif->mmap_pages[pending_idx]; + gnttab_set_map_op(gop, idx_to_kaddr(vif, pending_idx), + GNTMAP_host_map | GNTMAP_readonly, + txp->gref, vif->domid); - page = alloc_page(GFP_ATOMIC|__GFP_COLD); - if (!page) + memcpy(&vif->pending_tx_info[pending_idx].req, txp, + sizeof(*txp)); +} + +static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) +{ + struct sk_buff *skb = + alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(skb == NULL)) return NULL; - vif->mmap_pages[pending_idx] = page; - return page; + /* Packets passed to netif_rx() must have some headroom. */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + + /* Initialize it here to avoid later surprises */ + skb_shinfo(skb)->destructor_arg = NULL; + + return skb; } -static struct gnttab_copy *xenvif_get_requests(struct xenvif *vif, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_copy *gop) +static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, + struct sk_buff *skb, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *gop) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; - u16 pending_idx = *((u16 *)skb->data); - u16 head_idx = 0; - int slot, start; - struct page *page; - pending_ring_idx_t index, start_idx = 0; - uint16_t dst_offset; - unsigned int nr_slots; - struct pending_tx_info *first = NULL; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + int start; + pending_ring_idx_t index; + unsigned int nr_slots, frag_overflow = 0; /* At this point shinfo->nr_frags is in fact the number of * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. */ + if (shinfo->nr_frags > MAX_SKB_FRAGS) { + frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS; + BUG_ON(frag_overflow > MAX_SKB_FRAGS); + shinfo->nr_frags = MAX_SKB_FRAGS; + } nr_slots = shinfo->nr_frags; /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); - /* Coalesce tx requests, at this point the packet passed in - * should be <= 64K. Any packets larger than 64K have been - * handled in xenvif_count_requests(). - */ - for (shinfo->nr_frags = slot = start; slot < nr_slots; - shinfo->nr_frags++) { - struct pending_tx_info *pending_tx_info = - vif->pending_tx_info; + for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(vif->pending_cons++); + pending_idx = vif->pending_ring[index]; + xenvif_tx_create_gop(vif, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + } - page = alloc_page(GFP_ATOMIC|__GFP_COLD); - if (!page) - goto err; - - dst_offset = 0; - first = NULL; - while (dst_offset < PAGE_SIZE && slot < nr_slots) { - gop->flags = GNTCOPY_source_gref; - - gop->source.u.ref = txp->gref; - gop->source.domid = vif->domid; - gop->source.offset = txp->offset; - - gop->dest.domid = DOMID_SELF; - - gop->dest.offset = dst_offset; - gop->dest.u.gmfn = virt_to_mfn(page_address(page)); - - if (dst_offset + txp->size > PAGE_SIZE) { - /* This page can only merge a portion - * of tx request. Do not increment any - * pointer / counter here. The txp - * will be dealt with in future - * rounds, eventually hitting the - * `else` branch. - */ - gop->len = PAGE_SIZE - dst_offset; - txp->offset += gop->len; - txp->size -= gop->len; - dst_offset += gop->len; /* quit loop */ - } else { - /* This tx request can be merged in the page */ - gop->len = txp->size; - dst_offset += gop->len; - - index = pending_index(vif->pending_cons++); - - pending_idx = vif->pending_ring[index]; - - memcpy(&pending_tx_info[pending_idx].req, txp, - sizeof(*txp)); - - /* Poison these fields, corresponding - * fields for head tx req will be set - * to correct values after the loop. - */ - vif->mmap_pages[pending_idx] = (void *)(~0UL); - pending_tx_info[pending_idx].head = - INVALID_PENDING_RING_IDX; - - if (!first) { - first = &pending_tx_info[pending_idx]; - start_idx = index; - head_idx = pending_idx; - } - - txp++; - slot++; - } + if (frag_overflow) { + struct sk_buff *nskb = xenvif_alloc_skb(0); + if (unlikely(nskb == NULL)) { + if (net_ratelimit()) + netdev_err(vif->dev, + "Can't allocate the frag_list skb.\n"); + return NULL; + } - gop++; + shinfo = skb_shinfo(nskb); + frags = shinfo->frags; + + for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(vif->pending_cons++); + pending_idx = vif->pending_ring[index]; + xenvif_tx_create_gop(vif, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], + pending_idx); } - first->req.offset = 0; - first->req.size = dst_offset; - first->head = start_idx; - vif->mmap_pages[head_idx] = page; - frag_set_pending_idx(&frags[shinfo->nr_frags], head_idx); + skb_shinfo(skb)->frag_list = nskb; } - BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS); - return gop; -err: - /* Unwind, freeing all pages and sending error responses. */ - while (shinfo->nr_frags-- > start) { - xenvif_idx_release(vif, - frag_get_pending_idx(&frags[shinfo->nr_frags]), - XEN_NETIF_RSP_ERROR); +} + +static inline void xenvif_grant_handle_set(struct xenvif *vif, + u16 pending_idx, + grant_handle_t handle) +{ + if (unlikely(vif->grant_tx_handle[pending_idx] != + NETBACK_INVALID_HANDLE)) { + netdev_err(vif->dev, + "Trying to overwrite active handle! pending_idx: %x\n", + pending_idx); + BUG(); } - /* The head too, if necessary. */ - if (start) - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + vif->grant_tx_handle[pending_idx] = handle; +} - return NULL; +static inline void xenvif_grant_handle_reset(struct xenvif *vif, + u16 pending_idx) +{ + if (unlikely(vif->grant_tx_handle[pending_idx] == + NETBACK_INVALID_HANDLE)) { + netdev_err(vif->dev, + "Trying to unmap invalid handle! pending_idx: %x\n", + pending_idx); + BUG(); + } + vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE; } static int xenvif_tx_check_gop(struct xenvif *vif, struct sk_buff *skb, - struct gnttab_copy **gopp) + struct gnttab_map_grant_ref **gopp) { - struct gnttab_copy *gop = *gopp; - u16 pending_idx = *((u16 *)skb->data); + struct gnttab_map_grant_ref *gop = *gopp; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; struct skb_shared_info *shinfo = skb_shinfo(skb); struct pending_tx_info *tx_info; int nr_frags = shinfo->nr_frags; int i, err, start; - u16 peek; /* peek into next tx request */ + struct sk_buff *first_skb = NULL; /* Check status of header. */ err = gop->status; if (unlikely(err)) xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + else + xenvif_grant_handle_set(vif, pending_idx , gop->handle); /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); +check_frags: for (i = start; i < nr_frags; i++) { int j, newerr; - pending_ring_idx_t head; pending_idx = frag_get_pending_idx(&shinfo->frags[i]); tx_info = &vif->pending_tx_info[pending_idx]; - head = tx_info->head; /* Check error status: if okay then remember grant handle. */ - do { - newerr = (++gop)->status; - if (newerr) - break; - peek = vif->pending_ring[pending_index(++head)]; - } while (!pending_tx_is_head(vif, peek)); + newerr = (++gop)->status; if (likely(!newerr)) { + xenvif_grant_handle_set(vif, pending_idx , gop->handle); /* Had a previous error? Invalidate this fragment. */ if (unlikely(err)) - xenvif_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_unmap(vif, pending_idx); continue; } @@ -964,20 +983,45 @@ static int xenvif_tx_check_gop(struct xenvif *vif, /* Not the first error? Preceding frags already invalidated. */ if (err) continue; - /* First error: invalidate header and preceding fragments. */ - pending_idx = *((u16 *)skb->data); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); + if (!first_skb) + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + else + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + xenvif_idx_unmap(vif, pending_idx); for (j = start; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xenvif_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_unmap(vif, pending_idx); } /* Remember the error: invalidate all subsequent fragments. */ err = newerr; } + if (skb_has_frag_list(skb)) { + first_skb = skb; + skb = shinfo->frag_list; + shinfo = skb_shinfo(skb); + nr_frags = shinfo->nr_frags; + start = 0; + + goto check_frags; + } + + /* There was a mapping error in the frag_list skb. We have to unmap + * the first skb's frags + */ + if (first_skb && err) { + int j; + shinfo = skb_shinfo(first_skb); + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + for (j = start; j < shinfo->nr_frags; j++) { + pending_idx = frag_get_pending_idx(&shinfo->frags[j]); + xenvif_idx_unmap(vif, pending_idx); + } + } + *gopp = gop + 1; return err; } @@ -987,6 +1031,10 @@ 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; int i; + u16 prev_pending_idx = INVALID_PENDING_IDX; + + if (skb_shinfo(skb)->destructor_arg) + prev_pending_idx = XENVIF_TX_CB(skb)->pending_idx; for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = shinfo->frags + i; @@ -996,6 +1044,17 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) pending_idx = frag_get_pending_idx(frag); + /* If this is not the first frag, chain it to the previous*/ + if (unlikely(prev_pending_idx == INVALID_PENDING_IDX)) + skb_shinfo(skb)->destructor_arg = + &callback_param(vif, pending_idx); + else if (likely(pending_idx != prev_pending_idx)) + callback_param(vif, prev_pending_idx).ctx = + &callback_param(vif, pending_idx); + + callback_param(vif, pending_idx).ctx = NULL; + prev_pending_idx = pending_idx; + txp = &vif->pending_tx_info[pending_idx].req; page = virt_to_page(idx_to_kaddr(vif, pending_idx)); __skb_fill_page_desc(skb, i, page, txp->offset, txp->size); @@ -1003,10 +1062,15 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) skb->data_len += txp->size; skb->truesize += txp->size; - /* Take an extra reference to offset xenvif_idx_release */ + /* Take an extra reference to offset network stack's put_page */ get_page(vif->mmap_pages[pending_idx]); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); } + /* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc + * overlaps with "index", and "mapping" is not set. I think mapping + * should be set. If delivered to local stack, it would drop this + * skb in sk_filter unless the socket has the right to use it. + */ + skb->pfmemalloc = false; } static int xenvif_get_extras(struct xenvif *vif, @@ -1126,16 +1190,13 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) { - struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop; + struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop; struct sk_buff *skb; int ret; - while ((nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX - < MAX_PENDING_REQS) && - (skb_queue_len(&vif->tx_queue) < budget)) { + while (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; struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1]; u16 pending_idx; RING_IDX idx; @@ -1211,8 +1272,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? PKT_PROT_LEN : txreq.size; - skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN, - GFP_ATOMIC | __GFP_NOWARN); + skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { netdev_dbg(vif->dev, "Can't allocate a skb in start_xmit.\n"); @@ -1220,9 +1280,6 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) break; } - /* Packets passed to netif_rx() must have some headroom. */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) { struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; @@ -1234,31 +1291,11 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) } } - /* XXX could copy straight to head */ - page = xenvif_alloc_page(vif, pending_idx); - if (!page) { - kfree_skb(skb); - xenvif_tx_err(vif, &txreq, idx); - break; - } - - gop->source.u.ref = txreq.gref; - gop->source.domid = vif->domid; - gop->source.offset = txreq.offset; - - gop->dest.u.gmfn = virt_to_mfn(page_address(page)); - gop->dest.domid = DOMID_SELF; - gop->dest.offset = txreq.offset; - - gop->len = txreq.size; - gop->flags = GNTCOPY_source_gref; + xenvif_tx_create_gop(vif, pending_idx, &txreq, gop); gop++; - memcpy(&vif->pending_tx_info[pending_idx].req, - &txreq, sizeof(txreq)); - vif->pending_tx_info[pending_idx].head = index; - *((u16 *)skb->data) = pending_idx; + XENVIF_TX_CB(skb)->pending_idx = pending_idx; __skb_put(skb, data_len); @@ -1286,17 +1323,82 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) vif->tx.req_cons = idx; - if ((gop-vif->tx_copy_ops) >= ARRAY_SIZE(vif->tx_copy_ops)) + if ((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops)) break; } - return gop - vif->tx_copy_ops; + return gop - vif->tx_map_ops; } +/* Consolidate skb with a frag_list into a brand new one with local pages on + * frags. Returns 0 or -ENOMEM if can't allocate new pages. + */ +static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb) +{ + unsigned int offset = skb_headlen(skb); + skb_frag_t frags[MAX_SKB_FRAGS]; + int i; + struct ubuf_info *uarg; + struct sk_buff *nskb = skb_shinfo(skb)->frag_list; + + vif->tx_zerocopy_sent += 2; + vif->tx_frag_overflow++; + + xenvif_fill_frags(vif, nskb); + /* Subtract frags size, we will correct it later */ + skb->truesize -= skb->data_len; + skb->len += nskb->len; + skb->data_len += nskb->len; + + /* create a brand new frags array and coalesce there */ + for (i = 0; offset < skb->len; i++) { + struct page *page; + unsigned int len; + + BUG_ON(i >= MAX_SKB_FRAGS); + page = alloc_page(GFP_ATOMIC|__GFP_COLD); + if (!page) { + int j; + skb->truesize += skb->data_len; + for (j = 0; j < i; j++) + put_page(frags[j].page.p); + return -ENOMEM; + } + + if (offset + PAGE_SIZE < skb->len) + len = PAGE_SIZE; + else + len = skb->len - offset; + if (skb_copy_bits(skb, offset, page_address(page), len)) + BUG(); + + offset += len; + frags[i].page.p = page; + frags[i].page_offset = 0; + skb_frag_size_set(&frags[i], len); + } + /* swap out with old one */ + memcpy(skb_shinfo(skb)->frags, + frags, + i * sizeof(skb_frag_t)); + skb_shinfo(skb)->nr_frags = i; + skb->truesize += i * PAGE_SIZE; + + /* remove traces of mapped pages and frag_list */ + skb_frag_list_init(skb); + uarg = skb_shinfo(skb)->destructor_arg; + uarg->callback(uarg, true); + skb_shinfo(skb)->destructor_arg = NULL; + + skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + kfree_skb(nskb); + + return 0; +} static int xenvif_tx_submit(struct xenvif *vif) { - struct gnttab_copy *gop = vif->tx_copy_ops; + struct gnttab_map_grant_ref *gop = vif->tx_map_ops; struct sk_buff *skb; int work_done = 0; @@ -1305,7 +1407,7 @@ static int xenvif_tx_submit(struct xenvif *vif) u16 pending_idx; unsigned data_len; - pending_idx = *((u16 *)skb->data); + pending_idx = XENVIF_TX_CB(skb)->pending_idx; txp = &vif->pending_tx_info[pending_idx].req; /* Check the remap error code. */ @@ -1320,14 +1422,16 @@ static int xenvif_tx_submit(struct xenvif *vif) memcpy(skb->data, (void *)(idx_to_kaddr(vif, pending_idx)|txp->offset), data_len); + callback_param(vif, pending_idx).ctx = NULL; if (data_len < txp->size) { /* Append the packet payload as a fragment. */ txp->offset += data_len; txp->size -= data_len; + skb_shinfo(skb)->destructor_arg = + &callback_param(vif, pending_idx); } else { /* Schedule a response immediately. */ - xenvif_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_unmap(vif, pending_idx); } if (txp->flags & XEN_NETTXF_csum_blank) @@ -1337,6 +1441,17 @@ static int xenvif_tx_submit(struct xenvif *vif) xenvif_fill_frags(vif, skb); + if (unlikely(skb_has_frag_list(skb))) { + if (xenvif_handle_frag_list(vif, skb)) { + if (net_ratelimit()) + netdev_err(vif->dev, + "Not enough memory to consolidate frag_list!\n"); + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + kfree_skb(skb); + continue; + } + } + if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) { int target = min_t(int, skb->len, PKT_PROT_LEN); __pskb_pull_tail(skb, target - skb_headlen(skb)); @@ -1349,6 +1464,9 @@ static int xenvif_tx_submit(struct xenvif *vif) if (checksum_setup(vif, skb)) { netdev_dbg(vif->dev, "Can't setup checksum in net_tx_action\n"); + /* We have to set this flag to trigger the callback */ + if (skb_shinfo(skb)->destructor_arg) + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; kfree_skb(skb); continue; } @@ -1374,17 +1492,126 @@ static int xenvif_tx_submit(struct xenvif *vif) work_done++; + /* Set this flag right before netif_receive_skb, otherwise + * someone might think this packet already left netback, and + * do a skb_copy_ubufs while we are still in control of the + * skb. E.g. the __pskb_pull_tail earlier can do such thing. + */ + if (skb_shinfo(skb)->destructor_arg) { + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + vif->tx_zerocopy_sent++; + } + netif_receive_skb(skb); } return work_done; } +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success) +{ + unsigned long flags; + pending_ring_idx_t index; + struct xenvif *vif = ubuf_to_vif(ubuf); + + /* This is the only place where we grab this lock, to protect callbacks + * from each other. + */ + spin_lock_irqsave(&vif->callback_lock, flags); + do { + u16 pending_idx = ubuf->desc; + ubuf = (struct ubuf_info *) ubuf->ctx; + BUG_ON(vif->dealloc_prod - vif->dealloc_cons >= + MAX_PENDING_REQS); + index = pending_index(vif->dealloc_prod); + vif->dealloc_ring[index] = pending_idx; + /* Sync with xenvif_tx_dealloc_action: + * insert idx then incr producer. + */ + smp_wmb(); + vif->dealloc_prod++; + } while (ubuf); + wake_up(&vif->dealloc_wq); + spin_unlock_irqrestore(&vif->callback_lock, flags); + + if (likely(zerocopy_success)) + vif->tx_zerocopy_success++; + else + vif->tx_zerocopy_fail++; +} + +static inline void xenvif_tx_dealloc_action(struct xenvif *vif) +{ + struct gnttab_unmap_grant_ref *gop; + pending_ring_idx_t dc, dp; + u16 pending_idx, pending_idx_release[MAX_PENDING_REQS]; + unsigned int i = 0; + + dc = vif->dealloc_cons; + gop = vif->tx_unmap_ops; + + /* Free up any grants we have finished using */ + do { + dp = vif->dealloc_prod; + + /* Ensure we see all indices enqueued by all + * xenvif_zerocopy_callback(). + */ + smp_rmb(); + + while (dc != dp) { + BUG_ON(gop - vif->tx_unmap_ops > MAX_PENDING_REQS); + pending_idx = + vif->dealloc_ring[pending_index(dc++)]; + + pending_idx_release[gop-vif->tx_unmap_ops] = + pending_idx; + vif->pages_to_unmap[gop-vif->tx_unmap_ops] = + vif->mmap_pages[pending_idx]; + gnttab_set_unmap_op(gop, + idx_to_kaddr(vif, pending_idx), + GNTMAP_host_map, + vif->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(vif, pending_idx); + ++gop; + } + + } while (dp != vif->dealloc_prod); + + vif->dealloc_cons = dc; + + if (gop - vif->tx_unmap_ops > 0) { + int ret; + ret = gnttab_unmap_refs(vif->tx_unmap_ops, + NULL, + vif->pages_to_unmap, + gop - vif->tx_unmap_ops); + if (ret) { + netdev_err(vif->dev, "Unmap fail: nr_ops %tx ret %d\n", + gop - vif->tx_unmap_ops, ret); + for (i = 0; i < gop - vif->tx_unmap_ops; ++i) { + if (gop[i].status != GNTST_okay) + netdev_err(vif->dev, + " host_addr: %llx handle: %x status: %d\n", + gop[i].host_addr, + gop[i].handle, + gop[i].status); + } + BUG(); + } + } + + for (i = 0; i < gop - vif->tx_unmap_ops; ++i) + xenvif_idx_release(vif, pending_idx_release[i], + XEN_NETIF_RSP_OKAY); +} + + /* Called after netfront has transmitted */ int xenvif_tx_action(struct xenvif *vif, int budget) { unsigned nr_gops; - int work_done; + int work_done, ret; if (unlikely(!tx_work_todo(vif))) return 0; @@ -1394,7 +1621,11 @@ int xenvif_tx_action(struct xenvif *vif, int budget) if (nr_gops == 0) return 0; - gnttab_batch_copy(vif->tx_copy_ops, nr_gops); + ret = gnttab_map_refs(vif->tx_map_ops, + NULL, + vif->pages_to_map, + nr_gops); + BUG_ON(ret); work_done = xenvif_tx_submit(vif); @@ -1405,45 +1636,18 @@ 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; - u16 peek; /* peek into next tx request */ - - BUG_ON(vif->mmap_pages[pending_idx] == (void *)(~0UL)); - - /* Already complete? */ - if (vif->mmap_pages[pending_idx] == NULL) - return; + pending_ring_idx_t index; + unsigned long flags; pending_tx_info = &vif->pending_tx_info[pending_idx]; - - head = pending_tx_info->head; - - BUG_ON(!pending_tx_is_head(vif, head)); - BUG_ON(vif->pending_ring[pending_index(head)] != pending_idx); - - do { - pending_ring_idx_t index; - pending_ring_idx_t idx = pending_index(head); - u16 info_idx = vif->pending_ring[idx]; - - pending_tx_info = &vif->pending_tx_info[info_idx]; - make_tx_response(vif, &pending_tx_info->req, status); - - /* Setting any number other than - * INVALID_PENDING_RING_IDX indicates this slot is - * starting a new packet / ending a previous packet. - */ - pending_tx_info->head = 0; - - index = pending_index(vif->pending_prod++); - vif->pending_ring[index] = vif->pending_ring[info_idx]; - - peek = vif->pending_ring[pending_index(++head)]; - - } while (!pending_tx_is_head(vif, peek)); - - put_page(vif->mmap_pages[pending_idx]); - vif->mmap_pages[pending_idx] = NULL; + spin_lock_irqsave(&vif->response_lock, flags); + make_tx_response(vif, &pending_tx_info->req, status); + index = pending_index(vif->pending_prod); + vif->pending_ring[index] = pending_idx; + /* TX shouldn't use the index before we give it back here */ + mb(); + vif->pending_prod++; + spin_unlock_irqrestore(&vif->response_lock, flags); } @@ -1491,23 +1695,54 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, return resp; } +void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx) +{ + int ret; + struct gnttab_unmap_grant_ref tx_unmap_op; + + gnttab_set_unmap_op(&tx_unmap_op, + idx_to_kaddr(vif, pending_idx), + GNTMAP_host_map, + vif->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(vif, pending_idx); + + ret = gnttab_unmap_refs(&tx_unmap_op, NULL, + &vif->mmap_pages[pending_idx], 1); + if (ret) { + netdev_err(vif->dev, + "Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n", + ret, + pending_idx, + tx_unmap_op.host_addr, + tx_unmap_op.handle, + tx_unmap_op.status); + BUG(); + } + + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); +} + static inline int rx_work_todo(struct xenvif *vif) { - return !skb_queue_empty(&vif->rx_queue) && - xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots); + return (!skb_queue_empty(&vif->rx_queue) && + xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots)) || + vif->rx_queue_purge; } static inline int tx_work_todo(struct xenvif *vif) { - if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)) && - (nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX - < MAX_PENDING_REQS)) + if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))) return 1; return 0; } +static inline bool tx_dealloc_work_todo(struct xenvif *vif) +{ + return vif->dealloc_cons != vif->dealloc_prod; +} + void xenvif_unmap_frontend_rings(struct xenvif *vif) { if (vif->tx.sring) @@ -1565,7 +1800,7 @@ static void xenvif_start_queue(struct xenvif *vif) netif_wake_queue(vif->dev); } -int xenvif_kthread(void *data) +int xenvif_kthread_guest_rx(void *data) { struct xenvif *vif = data; struct sk_buff *skb; @@ -1577,12 +1812,19 @@ int xenvif_kthread(void *data) if (kthread_should_stop()) break; + if (vif->rx_queue_purge) { + skb_queue_purge(&vif->rx_queue); + vif->rx_queue_purge = false; + } + if (!skb_queue_empty(&vif->rx_queue)) xenvif_rx_action(vif); if (skb_queue_empty(&vif->rx_queue) && - netif_queue_stopped(vif->dev)) + netif_queue_stopped(vif->dev)) { + del_timer_sync(&vif->wake_queue); xenvif_start_queue(vif); + } cond_resched(); } @@ -1594,6 +1836,28 @@ int xenvif_kthread(void *data) return 0; } +int xenvif_dealloc_kthread(void *data) +{ + struct xenvif *vif = data; + + while (!kthread_should_stop()) { + wait_event_interruptible(vif->dealloc_wq, + tx_dealloc_work_todo(vif) || + kthread_should_stop()); + if (kthread_should_stop()) + break; + + xenvif_tx_dealloc_action(vif); + cond_resched(); + } + + /* Unmap anything remaining*/ + if (tx_dealloc_work_todo(vif)) + xenvif_tx_dealloc_action(vif); + + return 0; +} + static int __init netback_init(void) { int rc = 0; @@ -1611,6 +1875,8 @@ static int __init netback_init(void) if (rc) goto failed_init; + rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs); + return 0; failed_init: |