diff options
| -rw-r--r-- | drivers/net/xen-netback/common.h | 107 | ||||
| -rw-r--r-- | drivers/net/xen-netback/interface.c | 522 | ||||
| -rw-r--r-- | drivers/net/xen-netback/netback.c | 718 | ||||
| -rw-r--r-- | drivers/net/xen-netback/xenbus.c | 182 | ||||
| -rw-r--r-- | drivers/net/xen-netfront.c | 1121 | ||||
| -rw-r--r-- | include/xen/interface/io/netif.h | 53 |
6 files changed, 1680 insertions, 1023 deletions
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 0d4a285cbd7e..4dd7c4a1923b 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -99,22 +99,43 @@ struct xenvif_rx_meta { */ #define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN -struct xenvif { - /* Unique identifier for this interface. */ - domid_t domid; - unsigned int handle; +/* Queue name is interface name with "-qNNN" appended */ +#define QUEUE_NAME_SIZE (IFNAMSIZ + 5) - /* Is this interface disabled? True when backend discovers - * frontend is rogue. +/* IRQ name is queue name with "-tx" or "-rx" appended */ +#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) + +struct xenvif; + +struct xenvif_stats { + /* Stats fields to be updated per-queue. + * A subset of struct net_device_stats that contains only the + * fields that are updated in netback.c for each queue. */ - bool disabled; + unsigned int rx_bytes; + unsigned int rx_packets; + unsigned int tx_bytes; + unsigned int tx_packets; + + /* Additional stats used by xenvif */ + 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; +}; + +struct xenvif_queue { /* Per-queue data for xenvif */ + unsigned int id; /* Queue ID, 0-based */ + char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */ + struct xenvif *vif; /* Parent VIF */ /* Use NAPI for guest TX */ struct napi_struct napi; /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ unsigned int tx_irq; /* Only used when feature-split-event-channels = 1 */ - char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */ + char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */ struct xen_netif_tx_back_ring tx; struct sk_buff_head tx_queue; struct page *mmap_pages[MAX_PENDING_REQS]; @@ -150,7 +171,7 @@ struct xenvif { /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ unsigned int rx_irq; /* Only used when feature-split-event-channels = 1 */ - char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */ + char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */ struct xen_netif_rx_back_ring rx; struct sk_buff_head rx_queue; RING_IDX rx_last_skb_slots; @@ -158,14 +179,29 @@ struct xenvif { struct timer_list wake_queue; - /* This array is allocated seperately as it is large */ - struct gnttab_copy *grant_copy_op; + struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS]; /* 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]; + /* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */ + unsigned long credit_bytes; + unsigned long credit_usec; + unsigned long remaining_credit; + struct timer_list credit_timeout; + u64 credit_window_start; + + /* Statistics */ + struct xenvif_stats stats; +}; + +struct xenvif { + /* Unique identifier for this interface. */ + domid_t domid; + unsigned int handle; + u8 fe_dev_addr[6]; /* Frontend feature information. */ @@ -179,19 +215,13 @@ struct xenvif { /* Internal feature information. */ u8 can_queue:1; /* can queue packets for receiver? */ - /* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */ - unsigned long credit_bytes; - unsigned long credit_usec; - unsigned long remaining_credit; - struct timer_list credit_timeout; - u64 credit_window_start; + /* Is this interface disabled? True when backend discovers + * frontend is rogue. + */ + bool disabled; - /* 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; + /* Queues */ + struct xenvif_queue *queues; /* Miscellaneous private stuff. */ struct net_device *dev; @@ -206,7 +236,10 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, unsigned int handle); -int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, +int xenvif_init_queue(struct xenvif_queue *queue); +void xenvif_deinit_queue(struct xenvif_queue *queue); + +int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, unsigned long rx_ring_ref, unsigned int tx_evtchn, unsigned int rx_evtchn); void xenvif_disconnect(struct xenvif *vif); @@ -217,44 +250,47 @@ void xenvif_xenbus_fini(void); int xenvif_schedulable(struct xenvif *vif); -int xenvif_must_stop_queue(struct xenvif *vif); +int xenvif_must_stop_queue(struct xenvif_queue *queue); + +int xenvif_queue_stopped(struct xenvif_queue *queue); +void xenvif_wake_queue(struct xenvif_queue *queue); /* (Un)Map communication rings. */ -void xenvif_unmap_frontend_rings(struct xenvif *vif); -int xenvif_map_frontend_rings(struct xenvif *vif, +void xenvif_unmap_frontend_rings(struct xenvif_queue *queue); +int xenvif_map_frontend_rings(struct xenvif_queue *queue, grant_ref_t tx_ring_ref, grant_ref_t rx_ring_ref); /* Check for SKBs from frontend and schedule backend processing */ -void xenvif_napi_schedule_or_enable_events(struct xenvif *vif); +void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue); /* Prevent the device from generating any further traffic. */ void xenvif_carrier_off(struct xenvif *vif); -int xenvif_tx_action(struct xenvif *vif, int budget); +int xenvif_tx_action(struct xenvif_queue *queue, int budget); int xenvif_kthread_guest_rx(void *data); -void xenvif_kick_thread(struct xenvif *vif); +void xenvif_kick_thread(struct xenvif_queue *queue); int xenvif_dealloc_kthread(void *data); /* 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); +bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed); -void xenvif_stop_queue(struct xenvif *vif); +void xenvif_carrier_on(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); +void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); -static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif) +static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue) { return MAX_PENDING_REQS - - vif->pending_prod + vif->pending_cons; + queue->pending_prod + queue->pending_cons; } /* Callback from stack when TX packet can be released */ @@ -264,5 +300,6 @@ extern bool separate_tx_rx_irq; extern unsigned int rx_drain_timeout_msecs; extern unsigned int rx_drain_timeout_jiffies; +extern unsigned int xenvif_max_queues; #endif /* __XEN_NETBACK__COMMON_H__ */ diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 53cdcdf3dfa1..6929bcb61cf0 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -34,7 +34,6 @@ #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> @@ -43,6 +42,16 @@ #define XENVIF_QUEUE_LENGTH 32 #define XENVIF_NAPI_WEIGHT 64 +static inline void xenvif_stop_queue(struct xenvif_queue *queue) +{ + struct net_device *dev = queue->vif->dev; + + if (!queue->vif->can_queue) + return; + + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); +} + int xenvif_schedulable(struct xenvif *vif) { return netif_running(vif->dev) && netif_carrier_ok(vif->dev); @@ -50,33 +59,34 @@ int xenvif_schedulable(struct xenvif *vif) static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) { - struct xenvif *vif = dev_id; + struct xenvif_queue *queue = dev_id; - if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)) - napi_schedule(&vif->napi); + if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)) + napi_schedule(&queue->napi); return IRQ_HANDLED; } -static int xenvif_poll(struct napi_struct *napi, int budget) +int xenvif_poll(struct napi_struct *napi, int budget) { - struct xenvif *vif = container_of(napi, struct xenvif, napi); + struct xenvif_queue *queue = + container_of(napi, struct xenvif_queue, napi); int work_done; /* This vif is rogue, we pretend we've there is nothing to do * for this vif to deschedule it from NAPI. But this interface * will be turned off in thread context later. */ - if (unlikely(vif->disabled)) { + if (unlikely(queue->vif->disabled)) { napi_complete(napi); return 0; } - work_done = xenvif_tx_action(vif, budget); + work_done = xenvif_tx_action(queue, budget); if (work_done < budget) { napi_complete(napi); - xenvif_napi_schedule_or_enable_events(vif); + xenvif_napi_schedule_or_enable_events(queue); } return work_done; @@ -84,9 +94,9 @@ static int xenvif_poll(struct napi_struct *napi, int budget) static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { - struct xenvif *vif = dev_id; + struct xenvif_queue *queue = dev_id; - xenvif_kick_thread(vif); + xenvif_kick_thread(queue); return IRQ_HANDLED; } @@ -99,28 +109,80 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static void xenvif_wake_queue(unsigned long data) +int xenvif_queue_stopped(struct xenvif_queue *queue) { - struct xenvif *vif = (struct xenvif *)data; + struct net_device *dev = queue->vif->dev; + unsigned int id = queue->id; + return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id)); +} - 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); +void xenvif_wake_queue(struct xenvif_queue *queue) +{ + struct net_device *dev = queue->vif->dev; + unsigned int id = queue->id; + netif_tx_wake_queue(netdev_get_tx_queue(dev, id)); +} + +/* Callback to wake the queue and drain it on timeout */ +static void xenvif_wake_queue_callback(unsigned long data) +{ + struct xenvif_queue *queue = (struct xenvif_queue *)data; + + if (xenvif_queue_stopped(queue)) { + netdev_err(queue->vif->dev, "draining TX queue\n"); + queue->rx_queue_purge = true; + xenvif_kick_thread(queue); + xenvif_wake_queue(queue); } } +static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + unsigned int num_queues = dev->real_num_tx_queues; + u32 hash; + u16 queue_index; + + /* First, check if there is only one queue to optimise the + * single-queue or old frontend scenario. + */ + if (num_queues == 1) { + queue_index = 0; + } else { + /* Use skb_get_hash to obtain an L4 hash if available */ + hash = skb_get_hash(skb); + queue_index = hash % num_queues; + } + + return queue_index; +} + static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = dev->real_num_tx_queues; + u16 index; int min_slots_needed; BUG_ON(skb->dev != dev); - /* Drop the packet if vif is not ready */ - if (vif->task == NULL || - vif->dealloc_task == NULL || + /* Drop the packet if queues are not set up */ + if (num_queues < 1) + goto drop; + + /* Obtain the queue to be used to transmit this packet */ + index = skb_get_queue_mapping(skb); + if (index >= num_queues) { + pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n.", + index, vif->dev->name); + index %= num_queues; + } + queue = &vif->queues[index]; + + /* Drop the packet if queue is not ready */ + if (queue->task == NULL || + queue->dealloc_task == NULL || !xenvif_schedulable(vif)) goto drop; @@ -139,16 +201,16 @@ 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)) { - vif->wake_queue.function = xenvif_wake_queue; - vif->wake_queue.data = (unsigned long)vif; - xenvif_stop_queue(vif); - mod_timer(&vif->wake_queue, + if (!xenvif_rx_ring_slots_available(queue, min_slots_needed)) { + queue->wake_queue.function = xenvif_wake_queue_callback; + queue->wake_queue.data = (unsigned long)queue; + xenvif_stop_queue(queue); + mod_timer(&queue->wake_queue, jiffies + rx_drain_timeout_jiffies); } - skb_queue_tail(&vif->rx_queue, skb); - xenvif_kick_thread(vif); + skb_queue_tail(&queue->rx_queue, skb); + xenvif_kick_thread(queue); return NETDEV_TX_OK; @@ -161,25 +223,65 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) static struct net_device_stats *xenvif_get_stats(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = dev->real_num_tx_queues; + unsigned long rx_bytes = 0; + unsigned long rx_packets = 0; + unsigned long tx_bytes = 0; + unsigned long tx_packets = 0; + unsigned int index; + + if (vif->queues == NULL) + goto out; + + /* Aggregate tx and rx stats from each queue */ + for (index = 0; index < num_queues; ++index) { + queue = &vif->queues[index]; + rx_bytes += queue->stats.rx_bytes; + rx_packets += queue->stats.rx_packets; + tx_bytes += queue->stats.tx_bytes; + tx_packets += queue->stats.tx_packets; + } + +out: + vif->dev->stats.rx_bytes = rx_bytes; + vif->dev->stats.rx_packets = rx_packets; + vif->dev->stats.tx_bytes = tx_bytes; + vif->dev->stats.tx_packets = tx_packets; + return &vif->dev->stats; } static void xenvif_up(struct xenvif *vif) { - napi_enable(&vif->napi); - enable_irq(vif->tx_irq); - if (vif->tx_irq != vif->rx_irq) - enable_irq(vif->rx_irq); - xenvif_napi_schedule_or_enable_events(vif); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->dev->real_num_tx_queues; + unsigned int queue_index; + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + napi_enable(&queue->napi); + enable_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + enable_irq(queue->rx_irq); + xenvif_napi_schedule_or_enable_events(queue); + } } static void xenvif_down(struct xenvif *vif) { - 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); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->dev->real_num_tx_queues; + unsigned int queue_index; + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + napi_disable(&queue->napi); + disable_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + disable_irq(queue->rx_irq); + del_timer_sync(&queue->credit_timeout); + } } static int xenvif_open(struct net_device *dev) @@ -187,7 +289,7 @@ static int xenvif_open(struct net_device *dev) struct xenvif *vif = netdev_priv(dev); if (netif_carrier_ok(dev)) xenvif_up(vif); - netif_start_queue(dev); + netif_tx_start_all_queues(dev); return 0; } @@ -196,7 +298,7 @@ static int xenvif_close(struct net_device *dev) struct xenvif *vif = netdev_priv(dev); if (netif_carrier_ok(dev)) xenvif_down(vif); - netif_stop_queue(dev); + netif_tx_stop_all_queues(dev); return 0; } @@ -236,29 +338,29 @@ static const struct xenvif_stat { } xenvif_stats[] = { { "rx_gso_checksum_fixup", - offsetof(struct xenvif, rx_gso_checksum_fixup) + offsetof(struct xenvif_stats, rx_gso_checksum_fixup) }, /* If (sent != success + fail), there are probably packets never * freed up properly! */ { "tx_zerocopy_sent", - offsetof(struct xenvif, tx_zerocopy_sent), + offsetof(struct xenvif_stats, tx_zerocopy_sent), }, { "tx_zerocopy_success", - offsetof(struct xenvif, tx_zerocopy_success), + offsetof(struct xenvif_stats, tx_zerocopy_success), }, { "tx_zerocopy_fail", - offsetof(struct xenvif, tx_zerocopy_fail) + offsetof(struct xenvif_stats, tx_zerocopy_fail) }, /* Number of packets exceeding MAX_SKB_FRAG slots. You should use * a guest with the same MAX_SKB_FRAG */ { "tx_frag_overflow", - offsetof(struct xenvif, tx_frag_overflow) + offsetof(struct xenvif_stats, tx_frag_overflow) }, }; @@ -275,11 +377,20 @@ static int xenvif_get_sset_count(struct net_device *dev, int string_set) static void xenvif_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 * data) { - void *vif = netdev_priv(dev); + struct xenvif *vif = netdev_priv(dev); + unsigned int num_queues = dev->real_num_tx_queues; int i; - - for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) - data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset); + unsigned int queue_index; + struct xenvif_stats *vif_stats; + + for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) { + unsigned long accum = 0; + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + vif_stats = &vif->queues[queue_index].stats; + accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset); + } + data[i] = accum; + } } static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data) @@ -312,6 +423,7 @@ static const struct net_device_ops xenvif_netdev_ops = { .ndo_fix_features = xenvif_fix_features, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, + .ndo_select_queue = xenvif_select_queue, }; struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, @@ -321,10 +433,14 @@ 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); + /* Allocate a netdev with the max. supported number of queues. + * When the guest selects the desired number, it will be updated + * via netif_set_real_num_tx_queues(). + */ + dev = alloc_netdev_mq(sizeof(struct xenvif), name, ether_setup, + xenvif_max_queues); if (dev == NULL) { pr_warn("Could not allocate netdev for %s\n", name); return ERR_PTR(-ENOMEM); @@ -334,28 +450,18 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, 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; vif->ip_csum = 1; vif->dev = dev; - vif->disabled = false; - vif->credit_bytes = vif->remaining_credit = ~0UL; - vif->credit_usec = 0UL; - init_timer(&vif->credit_timeout); - vif->credit_window_start = get_jiffies_64(); - - init_timer(&vif->wake_queue); + /* Start out with no queues. The call below does not require + * rtnl_lock() as it happens before register_netdev(). + */ + vif->queues = NULL; + netif_set_real_num_tx_queues(dev, 0); dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | @@ -366,34 +472,6 @@ 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; - 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 * largest non-broadcast address to prevent the address getting @@ -403,8 +481,6 @@ 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); @@ -421,98 +497,147 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, return vif; } -int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, +int xenvif_init_queue(struct xenvif_queue *queue) +{ + int err, i; + + queue->credit_bytes = queue->remaining_credit = ~0UL; + queue->credit_usec = 0UL; + init_timer(&queue->credit_timeout); + queue->credit_window_start = get_jiffies_64(); + + skb_queue_head_init(&queue->rx_queue); + skb_queue_head_init(&queue->tx_queue); + + queue->pending_cons = 0; + queue->pending_prod = MAX_PENDING_REQS; + for (i = 0; i < MAX_PENDING_REQS; ++i) + queue->pending_ring[i] = i; + + spin_lock_init(&queue->callback_lock); + spin_lock_init(&queue->response_lock); + + /* If ballooning is disabled, this will consume real memory, so you + * better enable it. The long term solution would be to use just a + * bunch of valid page descriptors, without dependency on ballooning + */ + err = alloc_xenballooned_pages(MAX_PENDING_REQS, + queue->mmap_pages, + false); + if (err) { + netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n"); + return -ENOMEM; + } + + for (i = 0; i < MAX_PENDING_REQS; i++) { + queue->pending_tx_info[i].callback_struct = (struct ubuf_info) + { .callback = xenvif_zerocopy_callback, + .ctx = NULL, + .desc = i }; + queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; + } + + init_timer(&queue->wake_queue); + + netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll, + XENVIF_NAPI_WEIGHT); + + return 0; +} + +void xenvif_carrier_on(struct xenvif *vif) +{ + rtnl_lock(); + if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) + dev_set_mtu(vif->dev, ETH_DATA_LEN); + netdev_update_features(vif->dev); + netif_carrier_on(vif->dev); + if (netif_running(vif->dev)) + xenvif_up(vif); + rtnl_unlock(); +} + +int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, unsigned long rx_ring_ref, unsigned int tx_evtchn, unsigned int rx_evtchn) { struct task_struct *task; int err = -ENOMEM; - BUG_ON(vif->tx_irq); - BUG_ON(vif->task); - BUG_ON(vif->dealloc_task); + BUG_ON(queue->tx_irq); + BUG_ON(queue->task); + BUG_ON(queue->dealloc_task); - err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); + err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref); if (err < 0) goto err; - init_waitqueue_head(&vif->wq); - init_waitqueue_head(&vif->dealloc_wq); + init_waitqueue_head(&queue->wq); + init_waitqueue_head(&queue->dealloc_wq); if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ err = bind_interdomain_evtchn_to_irqhandler( - vif->domid, tx_evtchn, xenvif_interrupt, 0, - vif->dev->name, vif); + queue->vif->domid, tx_evtchn, xenvif_interrupt, 0, + queue->name, queue); if (err < 0) goto err_unmap; - vif->tx_irq = vif->rx_irq = err; - disable_irq(vif->tx_irq); + queue->tx_irq = queue->rx_irq = err; + disable_irq(queue->tx_irq); } else { /* feature-split-event-channels == 1 */ - snprintf(vif->tx_irq_name, sizeof(vif->tx_irq_name), - "%s-tx", vif->dev->name); + snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), + "%s-tx", queue->name); err = bind_interdomain_evtchn_to_irqhandler( - vif->domid, tx_evtchn, xenvif_tx_interrupt, 0, - vif->tx_irq_name, vif); + queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0, + queue->tx_irq_name, queue); if (err < 0) goto err_unmap; - vif->tx_irq = err; - disable_irq(vif->tx_irq); + queue->tx_irq = err; + disable_irq(queue->tx_irq); - snprintf(vif->rx_irq_name, sizeof(vif->rx_irq_name), - "%s-rx", vif->dev->name); + snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), + "%s-rx", queue->name); err = bind_interdomain_evtchn_to_irqhandler( - vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, - vif->rx_irq_name, vif); + queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, + queue->rx_irq_name, queue); if (err < 0) goto err_tx_unbind; - vif->rx_irq = err; - disable_irq(vif->rx_irq); + queue->rx_irq = err; + disable_irq(queue->rx_irq); } task = kthread_create(xenvif_kthread_guest_rx, - (void *)vif, "%s-guest-rx", vif->dev->name); + (void *)queue, "%s-guest-rx", queue->name); if (IS_ERR(task)) { - pr_warn("Could not allocate kthread for %s\n", vif->dev->name); + pr_warn("Could not allocate kthread for %s\n", queue->name); err = PTR_ERR(task); goto err_rx_unbind; } - - vif->task = task; + queue->task = task; task = kthread_create(xenvif_dealloc_kthread, - (void *)vif, "%s-dealloc", vif->dev->name); + (void *)queue, "%s-dealloc", queue->name); if (IS_ERR(task)) { - pr_warn("Could not allocate kthread for %s\n", vif->dev->name); + pr_warn("Could not allocate kthread for %s\n", queue->name); err = PTR_ERR(task); goto err_rx_unbind; } + queue->dealloc_task = task; - vif->dealloc_task = task; - - rtnl_lock(); - if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) - dev_set_mtu(vif->dev, ETH_DATA_LEN); - netdev_update_features(vif->dev); - netif_carrier_on(vif->dev); - if (netif_running(vif->dev)) - xenvif_up(vif); - rtnl_unlock(); - - wake_up_process(vif->task); - wake_up_process(vif->dealloc_task); + wake_up_process(queue->task); + wake_up_process(queue->dealloc_task); return 0; err_rx_unbind: - unbind_from_irqhandler(vif->rx_irq, vif); - vif->rx_irq = 0; + unbind_from_irqhandler(queue->rx_irq, queue); + queue->rx_irq = 0; err_tx_unbind: - unbind_from_irqhandler(vif->tx_irq, vif); - vif->tx_irq = 0; + unbind_from_irqhandler(queue->tx_irq, queue); + queue->tx_irq = 0; err_unmap: - xenvif_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(queue); err: module_put(THIS_MODULE); return err; @@ -529,38 +654,77 @@ void xenvif_carrier_off(struct xenvif *vif) rtnl_unlock(); } +static void xenvif_wait_unmap_timeout(struct xenvif_queue *queue, + unsigned int worst_case_skb_lifetime) +{ + int i, unmap_timeout = 0; + + for (i = 0; i < MAX_PENDING_REQS; ++i) { + if (queue->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(queue->vif->dev, + "Page still granted! Index: %x\n", + i); + i = -1; + } + } +} + void xenvif_disconnect(struct xenvif *vif) { + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->dev->real_num_tx_queues; + unsigned int queue_index; + if (netif_carrier_ok(vif->dev)) xenvif_carrier_off(vif); - if (vif->task) { - del_timer_sync(&vif->wake_queue); - kthread_stop(vif->task); - vif->task = NULL; - } + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; - if (vif->dealloc_task) { - kthread_stop(vif->dealloc_task); - vif->dealloc_task = NULL; - } + if (queue->task) { + del_timer_sync(&queue->wake_queue); + kthread_stop(queue->task); + queue->task = NULL; + } - if (vif->tx_irq) { - if (vif->tx_irq == vif->rx_irq) - unbind_from_irqhandler(vif->tx_irq, vif); - else { - unbind_from_irqhandler(vif->tx_irq, vif); - unbind_from_irqhandler(vif->rx_irq, vif); + if (queue->dealloc_task) { + kthread_stop(queue->dealloc_task); + queue->dealloc_task = NULL; } - vif->tx_irq = 0; + + if (queue->tx_irq) { + if (queue->tx_irq == queue->rx_irq) + unbind_from_irqhandler(queue->tx_irq, queue); + else { + unbind_from_irqhandler(queue->tx_irq, queue); + unbind_from_irqhandler(queue->rx_irq, queue); + } + queue->tx_irq = 0; + } + + xenvif_unmap_frontend_rings(queue); } +} - xenvif_unmap_frontend_rings(vif); +/* Reverse the relevant parts of xenvif_init_queue(). + * Used for queue teardown from xenvif_free(), and on the + * error handling paths in xenbus.c:connect(). + */ +void xenvif_deinit_queue(struct xenvif_queue *queue) +{ + free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages); + netif_napi_del(&queue->napi); } void xenvif_free(struct xenvif *vif) { - int i, unmap_timeout = 0; + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->dev->real_num_tx_queues; + unsigned int queue_index; /* 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 @@ -575,33 +739,21 @@ void xenvif_free(struct xenvif *vif) 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); + unregister_netdev(vif->dev); - netif_napi_del(&vif->napi); + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + xenvif_wait_unmap_timeout(queue, worst_case_skb_lifetime); + xenvif_deinit_queue(queue); + } - unregister_netdev(vif->dev); + /* Free the array of queues. The call below does not require + * rtnl_lock() because it happens after unregister_netdev(). + */ + netif_set_real_num_tx_queues(vif->dev, 0); + vfree(vif->queues); + vif->queues = NULL; - 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 7367208ee8cd..49efff9b99f4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -62,6 +62,11 @@ unsigned int rx_drain_timeout_msecs = 10000; module_param(rx_drain_timeout_msecs, uint, 0444); unsigned int rx_drain_timeout_jiffies; +unsigned int xenvif_max_queues; +module_param_named(max_queues, xenvif_max_queues, uint, 0644); +MODULE_PARM_DESC(max_queues, + "Maximum number of queues per virtual interface"); + /* * This is the maximum slots a skb can have. If a guest sends a skb * which exceeds this limit it is considered malicious. @@ -70,33 +75,33 @@ unsigned int rx_drain_timeout_jiffies; static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT; module_param(fatal_skb_slots, uint, 0444); -static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx, +static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, u8 status); -static void make_tx_response(struct xenvif *vif, +static void make_tx_response(struct xenvif_queue *queue, struct xen_netif_tx_request *txp, s8 st); -static inline int tx_work_todo(struct xenvif *vif); -static inline int rx_work_todo(struct xenvif *vif); +static inline int tx_work_todo(struct xenvif_queue *queue); +static inline int rx_work_todo(struct xenvif_queue *queue); -static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, +static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, u16 id, s8 st, u16 offset, u16 size, u16 flags); -static inline unsigned long idx_to_pfn(struct xenvif *vif, +static inline unsigned long idx_to_pfn(struct xenvif_queue *queue, u16 idx) { - return page_to_pfn(vif->mmap_pages[idx]); + return page_to_pfn(queue->mmap_pages[idx]); } -static inline unsigned long idx_to_kaddr(struct xenvif *vif, +static inline unsigned long idx_to_kaddr(struct xenvif_queue *queue, u16 idx) { - return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx)); + return (unsigned long)pfn_to_kaddr(idx_to_pfn(queue, idx)); } #define callback_param(vif, pending_idx) \ @@ -104,13 +109,13 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif, /* Find the containing VIF's structure from a pointer in pending_tx_info array */ -static inline struct xenvif *ubuf_to_vif(const struct ubuf_info *ubuf) +static inline struct xenvif_queue *ubuf_to_queue(const 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, + struct xenvif_queue, pending_tx_info[0]); } @@ -136,24 +141,24 @@ static inline pending_ring_idx_t pending_index(unsigned i) return i & (MAX_PENDING_REQS-1); } -bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed) +bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed) { RING_IDX prod, cons; do { - prod = vif->rx.sring->req_prod; - cons = vif->rx.req_cons; + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; if (prod - cons >= needed) return true; - vif->rx.sring->req_event = prod + 1; + queue->rx.sring->req_event = prod + 1; /* Make sure event is visible before we check prod * again. */ mb(); - } while (vif->rx.sring->req_prod != prod); + } while (queue->rx.sring->req_prod != prod); return false; } @@ -207,13 +212,13 @@ struct netrx_pending_operations { grant_ref_t copy_gref; }; -static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif, +static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, struct netrx_pending_operations *npo) { struct xenvif_rx_meta *meta; struct xen_netif_rx_request *req; - req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); meta = npo->meta + npo->meta_prod++; meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; @@ -231,11 +236,11 @@ 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 xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, +static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb, struct netrx_pending_operations *npo, struct page *page, unsigned long size, unsigned long offset, int *head, - struct xenvif *foreign_vif, + struct xenvif_queue *foreign_queue, grant_ref_t foreign_gref) { struct gnttab_copy *copy_gop; @@ -268,7 +273,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, */ BUG_ON(*head); - meta = get_next_rx_buffer(vif, npo); + meta = get_next_rx_buffer(queue, npo); } if (npo->copy_off + bytes > MAX_BUFFER_OFFSET) @@ -278,8 +283,8 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, copy_gop->flags = GNTCOPY_dest_gref; copy_gop->len = bytes; - if (foreign_vif) { - copy_gop->source.domid = foreign_vif->domid; + if (foreign_queue) { + copy_gop->source.domid = foreign_queue->vif->domid; copy_gop->source.u.ref = foreign_gref; copy_gop->flags |= GNTCOPY_source_gref; } else { @@ -289,7 +294,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, } copy_gop->source.offset = offset; - copy_gop->dest.domid = vif->domid; + copy_gop->dest.domid = queue->vif->domid; copy_gop->dest.offset = npo->copy_off; copy_gop->dest.u.ref = npo->copy_gref; @@ -314,8 +319,8 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, gso_type = XEN_NETIF_GSO_TYPE_TCPV6; } - if (*head && ((1 << gso_type) & vif->gso_mask)) - vif->rx.req_cons++; + if (*head && ((1 << gso_type) & queue->vif->gso_mask)) + queue->rx.req_cons++; *head = 0; /* There must be something in this buffer now. */ @@ -337,13 +342,13 @@ static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb, const int i, const struct ubuf_info *ubuf) { - struct xenvif *foreign_vif = ubuf_to_vif(ubuf); + struct xenvif_queue *foreign_queue = ubuf_to_queue(ubuf); do { u16 pending_idx = ubuf->desc; if (skb_shinfo(skb)->frags[i].page.p == - foreign_vif->mmap_pages[pending_idx]) + foreign_queue->mmap_pages[pending_idx]) break; ubuf = (struct ubuf_info *) ubuf->ctx; } while (ubuf); @@ -364,7 +369,8 @@ static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb, * frontend-side LRO). */ static int xenvif_gop_skb(struct sk_buff *skb, - struct netrx_pending_operations *npo) + struct netrx_pending_operations *npo, + struct xenvif_queue *queue) { struct xenvif *vif = netdev_priv(skb->dev); int nr_frags = skb_shinfo(skb)->nr_frags; @@ -390,7 +396,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, /* Set up a GSO prefix descriptor, if necessary */ if ((1 << gso_type) & vif->gso_prefix_mask) { - req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); meta = npo->meta + npo->meta_prod++; meta->gso_type = gso_type; meta->gso_size = skb_shinfo(skb)->gso_size; @@ -398,7 +404,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, meta->id = req->id; } - req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); + req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++); meta = npo->meta + npo->meta_prod++; if ((1 << gso_type) & vif->gso_mask) { @@ -422,7 +428,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, if (data + len > skb_tail_pointer(skb)) len = skb_tail_pointer(skb) - data; - xenvif_gop_frag_copy(vif, skb, npo, + xenvif_gop_frag_copy(queue, skb, npo, virt_to_page(data), len, offset, &head, NULL, 0); @@ -433,7 +439,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, /* This variable also signals whether foreign_gref has a real * value or not. */ - struct xenvif *foreign_vif = NULL; + struct xenvif_queue *foreign_queue = NULL; grant_ref_t foreign_gref; if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) && @@ -458,8 +464,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, if (likely(ubuf)) { u16 pending_idx = ubuf->desc; - foreign_vif = ubuf_to_vif(ubuf); - foreign_gref = foreign_vif->pending_tx_info[pending_idx].req.gref; + foreign_queue = ubuf_to_queue(ubuf); + foreign_gref = + foreign_queue->pending_tx_info[pending_idx].req.gref; /* Just a safety measure. If this was the last * element on the list, the for loop will * iterate again if a local page were added to @@ -477,13 +484,13 @@ static int xenvif_gop_skb(struct sk_buff *skb, */ ubuf = head_ubuf; } - xenvif_gop_frag_copy(vif, skb, npo, + xenvif_gop_frag_copy(queue, 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, - foreign_vif, - foreign_vif ? foreign_gref : UINT_MAX); + foreign_queue, + foreign_queue ? foreign_gref : UINT_MAX); } return npo->meta_prod - old_meta_prod; @@ -515,7 +522,7 @@ static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots, return status; } -static void xenvif_add_frag_responses(struct xenvif *vif, int status, +static void xenvif_add_frag_responses(struct xenvif_queue *queue, int status, struct xenvif_rx_meta *meta, int nr_meta_slots) { @@ -536,7 +543,7 @@ static void xenvif_add_frag_responses(struct xenvif *vif, int status, flags = XEN_NETRXF_more_data; offset = 0; - make_rx_response(vif, meta[i].id, status, offset, + make_rx_response(queue, meta[i].id, status, offset, meta[i].size, flags); } } @@ -547,12 +554,12 @@ struct xenvif_rx_cb { #define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) -void xenvif_kick_thread(struct xenvif *vif) +void xenvif_kick_thread(struct xenvif_queue *queue) { - wake_up(&vif->wq); + wake_up(&queue->wq); } -static void xenvif_rx_action(struct xenvif *vif) +static void xenvif_rx_action(struct xenvif_queue *queue) { s8 status; u16 flags; @@ -565,13 +572,13 @@ static void xenvif_rx_action(struct xenvif *vif) bool need_to_notify = false; struct netrx_pending_operations npo = { - .copy = vif->grant_copy_op, - .meta = vif->meta, + .copy = queue->grant_copy_op, + .meta = queue->meta, }; skb_queue_head_init(&rxq); - while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) { + while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) { RING_IDX max_slots_needed; RING_IDX old_req_cons; RING_IDX ring_slots_used; @@ -614,42 +621,42 @@ static void xenvif_rx_action(struct xenvif *vif) 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); + if (!xenvif_rx_ring_slots_available(queue, max_slots_needed)) { + skb_queue_head(&queue->rx_queue, skb); need_to_notify = true; - vif->rx_last_skb_slots = max_slots_needed; + queue->rx_last_skb_slots = max_slots_needed; break; } else - vif->rx_last_skb_slots = 0; + queue->rx_last_skb_slots = 0; - old_req_cons = vif->rx.req_cons; - XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo); - ring_slots_used = vif->rx.req_cons - old_req_cons; + old_req_cons = queue->rx.req_cons; + XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue); + ring_slots_used = queue->rx.req_cons - old_req_cons; BUG_ON(ring_slots_used > max_slots_needed); __skb_queue_tail(&rxq, skb); } - BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta)); + BUG_ON(npo.meta_prod > ARRAY_SIZE(queue->meta)); if (!npo.copy_prod) goto done; BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS); - gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod); + gnttab_batch_copy(queue->grant_copy_op, npo.copy_prod); while ((skb = __skb_dequeue(&rxq)) != NULL) { - if ((1 << vif->meta[npo.meta_cons].gso_type) & - vif->gso_prefix_mask) { - resp = RING_GET_RESPONSE(&vif->rx, - vif->rx.rsp_prod_pvt++); + if ((1 << queue->meta[npo.meta_cons].gso_type) & + queue->vif->gso_prefix_mask) { + resp = RING_GET_RESPONSE(&queue->rx, + queue->rx.rsp_prod_pvt++); resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data; - resp->offset = vif->meta[npo.meta_cons].gso_size; - resp->id = vif->meta[npo.meta_cons].id; + resp->offset = queue->meta[npo.meta_cons].gso_size; + resp->id = queue->meta[npo.meta_cons].id; resp->status = XENVIF_RX_CB(skb)->meta_slots_used; npo.meta_cons++; @@ -657,10 +664,10 @@ static void xenvif_rx_action(struct xenvif *vif) } - vif->dev->stats.tx_bytes += skb->len; - vif->dev->stats.tx_packets++; + queue->stats.tx_bytes += skb->len; + queue->stats.tx_packets++; - status = xenvif_check_gop(vif, + status = xenvif_check_gop(queue->vif, XENVIF_RX_CB(skb)->meta_slots_used, &npo); @@ -676,22 +683,22 @@ static void xenvif_rx_action(struct xenvif *vif) flags |= XEN_NETRXF_data_validated; offset = 0; - resp = make_rx_response(vif, vif->meta[npo.meta_cons].id, + resp = make_rx_response(queue, queue->meta[npo.meta_cons].id, status, offset, - vif->meta[npo.meta_cons].size, + queue->meta[npo.meta_cons].size, flags); - if ((1 << vif->meta[npo.meta_cons].gso_type) & - vif->gso_mask) { + if ((1 << queue->meta[npo.meta_cons].gso_type) & + queue->vif->gso_mask) { struct xen_netif_extra_info *gso = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&vif->rx, - vif->rx.rsp_prod_pvt++); + RING_GET_RESPONSE(&queue->rx, + queue->rx.rsp_prod_pvt++); resp->flags |= XEN_NETRXF_extra_info; - gso->u.gso.type = vif->meta[npo.meta_cons].gso_type; - gso->u.gso.size = vif->meta[npo.meta_cons].gso_size; + gso->u.gso.type = queue->meta[npo.meta_cons].gso_type; + gso->u.gso.size = queue->meta[npo.meta_cons].gso_size; gso->u.gso.pad = 0; gso->u.gso.features = 0; @@ -699,11 +706,11 @@ static void xenvif_rx_action(struct xenvif *vif) gso->flags = 0; } - xenvif_add_frag_responses(vif, status, - vif->meta + npo.meta_cons + 1, + xenvif_add_frag_responses(queue, status, + queue->meta + npo.meta_cons + 1, XENVIF_RX_CB(skb)->meta_slots_used); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret); + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, ret); need_to_notify |= !!ret; @@ -713,20 +720,20 @@ static void xenvif_rx_action(struct xenvif *vif) done: if (need_to_notify) - notify_remote_via_irq(vif->rx_irq); + notify_remote_via_irq(queue->rx_irq); } -void xenvif_napi_schedule_or_enable_events(struct xenvif *vif) +void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue) { int more_to_do; - RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do); + RING_FINAL_CHECK_FOR_REQUESTS(&queue->tx, more_to_do); if (more_to_do) - napi_schedule(&vif->napi); + napi_schedule(&queue->napi); } -static void tx_add_credit(struct xenvif *vif) +static void tx_add_credit(struct xenvif_queue *queue) { unsigned long max_burst, max_credit; @@ -734,55 +741,57 @@ static void tx_add_credit(struct xenvif *vif) * Allow a burst big enough to transmit a jumbo packet of up to 128kB. * Otherwise the interface can seize up due to insufficient credit. */ - max_burst = RING_GET_REQUEST(&vif->tx, vif->tx.req_cons)->size; + max_burst = RING_GET_REQUEST(&queue->tx, queue->tx.req_cons)->size; max_burst = min(max_burst, 131072UL); - max_burst = max(max_burst, vif->credit_bytes); + max_burst = max(max_burst, queue->credit_bytes); /* Take care that adding a new chunk of credit doesn't wrap to zero. */ - max_credit = vif->remaining_credit + vif->credit_bytes; - if (max_credit < vif->remaining_credit) + max_credit = queue->remaining_credit + queue->credit_bytes; + if (max_credit < queue->remaining_credit) max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */ - vif->remaining_credit = min(max_credit, max_burst); + queue->remaining_credit = min(max_credit, max_burst); } static void tx_credit_callback(unsigned long data) { - struct xenvif *vif = (struct xenvif *)data; - tx_add_credit(vif); - xenvif_napi_schedule_or_enable_events(vif); + struct xenvif_queue *queue = (struct xenvif_queue *)data; + tx_add_credit(queue); + xenvif_napi_schedule_or_enable_events(queue); } -static void xenvif_tx_err(struct xenvif *vif, +static void xenvif_tx_err(struct xenvif_queue *queue, struct xen_netif_tx_request *txp, RING_IDX end) { - RING_IDX cons = vif->tx.req_cons; + RING_IDX cons = queue->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); + spin_lock_irqsave(&queue->response_lock, flags); + make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR); + spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; - txp = RING_GET_REQUEST(&vif->tx, cons++); + txp = RING_GET_REQUEST(&queue->tx, cons++); } while (1); - vif->tx.req_cons = cons; + queue->tx.req_cons = cons; } static void xenvif_fatal_tx_err(struct xenvif *vif) { netdev_err(vif->dev, "fatal error; disabling device\n"); vif->disabled = true; - xenvif_kick_thread(vif); + /* Disable the vif from queue 0's kthread */ + if (vif->queues) + xenvif_kick_thread(&vif->queues[0]); } -static int xenvif_count_requests(struct xenvif *vif, +static int xenvif_count_requests(struct xenvif_queue *queue, struct xen_netif_tx_request *first, struct xen_netif_tx_request *txp, int work_to_do) { - RING_IDX cons = vif->tx.req_cons; + RING_IDX cons = queue->tx.req_cons; int slots = 0; int drop_err = 0; int more_data; @@ -794,10 +803,10 @@ static int xenvif_count_requests(struct xenvif *vif, struct xen_netif_tx_request dropped_tx = { 0 }; if (slots >= work_to_do) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Asked for %d slots but exceeds this limit\n", work_to_do); - xenvif_fatal_tx_err(vif); + xenvif_fatal_tx_err(queue->vif); return -ENODATA; } @@ -805,10 +814,10 @@ static int xenvif_count_requests(struct xenvif *vif, * considered malicious. */ if (unlikely(slots >= fatal_skb_slots)) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Malicious frontend using %d slots, threshold %u\n", slots, fatal_skb_slots); - xenvif_fatal_tx_err(vif); + xenvif_fatal_tx_err(queue->vif); return -E2BIG; } @@ -821,7 +830,7 @@ static int xenvif_count_requests(struct xenvif *vif, */ if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) { if (net_ratelimit()) - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Too many slots (%d) exceeding limit (%d), dropping packet\n", slots, XEN_NETBK_LEGACY_SLOTS_MAX); drop_err = -E2BIG; @@ -830,7 +839,7 @@ static int xenvif_count_requests(struct xenvif *vif, if (drop_err) txp = &dropped_tx; - memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + slots), + memcpy(txp, RING_GET_REQUEST(&queue->tx, cons + slots), sizeof(*txp)); /* If the guest submitted a frame >= 64 KiB then @@ -844,7 +853,7 @@ static int xenvif_count_requests(struct xenvif *vif, */ if (!drop_err && txp->size > first->size) { if (net_ratelimit()) - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Invalid tx request, slot size %u > remaining size %u\n", txp->size, first->size); drop_err = -EIO; @@ -854,9 +863,9 @@ static int xenvif_count_requests(struct xenvif *vif, slots++; if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) { - netdev_err(vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n", + netdev_err(queue->vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n", txp->offset, txp->size); - xenvif_fatal_tx_err(vif); + xenvif_fatal_tx_err(queue->vif); return -EINVAL; } @@ -868,7 +877,7 @@ static int xenvif_count_requests(struct xenvif *vif, } while (more_data); if (drop_err) { - xenvif_tx_err(vif, first, cons + slots); + xenvif_tx_err(queue, first, cons + slots); return drop_err; } @@ -882,17 +891,17 @@ struct xenvif_tx_cb { #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) -static inline void xenvif_tx_create_map_op(struct xenvif *vif, +static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue, u16 pending_idx, struct xen_netif_tx_request *txp, struct gnttab_map_grant_ref *mop) { - vif->pages_to_map[mop-vif->tx_map_ops] = vif->mmap_pages[pending_idx]; - gnttab_set_map_op(mop, idx_to_kaddr(vif, pending_idx), + queue->pages_to_map[mop-queue->tx_map_ops] = queue->mmap_pages[pending_idx]; + gnttab_set_map_op(mop, idx_to_kaddr(queue, pending_idx), GNTMAP_host_map | GNTMAP_readonly, - txp->gref, vif->domid); + txp->gref, queue->vif->domid); - memcpy(&vif->pending_tx_info[pending_idx].req, txp, + memcpy(&queue->pending_tx_info[pending_idx].req, txp, sizeof(*txp)); } @@ -913,7 +922,7 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) return skb; } -static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, +static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, struct sk_buff *skb, struct xen_netif_tx_request *txp, struct gnttab_map_grant_ref *gop) @@ -940,9 +949,9 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, 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_map_op(vif, pending_idx, txp, gop); + index = pending_index(queue->pending_cons++); + pending_idx = queue->pending_ring[index]; + xenvif_tx_create_map_op(queue, pending_idx, txp, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); } @@ -950,7 +959,7 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, struct sk_buff *nskb = xenvif_alloc_skb(0); if (unlikely(nskb == NULL)) { if (net_ratelimit()) - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Can't allocate the frag_list skb.\n"); return NULL; } @@ -960,9 +969,9 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, 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_map_op(vif, pending_idx, txp, gop); + index = pending_index(queue->pending_cons++); + pending_idx = queue->pending_ring[index]; + xenvif_tx_create_map_op(queue, pending_idx, txp, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); } @@ -973,34 +982,34 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, return gop; } -static inline void xenvif_grant_handle_set(struct xenvif *vif, +static inline void xenvif_grant_handle_set(struct xenvif_queue *queue, u16 pending_idx, grant_handle_t handle) { - if (unlikely(vif->grant_tx_handle[pending_idx] != + if (unlikely(queue->grant_tx_handle[pending_idx] != NETBACK_INVALID_HANDLE)) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Trying to overwrite active handle! pending_idx: %x\n", pending_idx); BUG(); } - vif->grant_tx_handle[pending_idx] = handle; + queue->grant_tx_handle[pending_idx] = handle; } -static inline void xenvif_grant_handle_reset(struct xenvif *vif, +static inline void xenvif_grant_handle_reset(struct xenvif_queue *queue, u16 pending_idx) { - if (unlikely(vif->grant_tx_handle[pending_idx] == + if (unlikely(queue->grant_tx_handle[pending_idx] == NETBACK_INVALID_HANDLE)) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Trying to unmap invalid handle! pending_idx: %x\n", pending_idx); BUG(); } - vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE; + queue->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE; } -static int xenvif_tx_check_gop(struct xenvif *vif, +static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct sk_buff *skb, struct gnttab_map_grant_ref **gopp_map, struct gnttab_copy **gopp_copy) @@ -1017,12 +1026,12 @@ static int xenvif_tx_check_gop(struct xenvif *vif, (*gopp_copy)++; if (unlikely(err)) { if (net_ratelimit()) - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", (*gopp_copy)->status, pending_idx, (*gopp_copy)->source.u.ref); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); } check_frags: @@ -1035,24 +1044,24 @@ check_frags: newerr = gop_map->status; if (likely(!newerr)) { - xenvif_grant_handle_set(vif, + xenvif_grant_handle_set(queue, pending_idx, gop_map->handle); /* Had a previous error? Invalidate this fragment. */ if (unlikely(err)) - xenvif_idx_unmap(vif, pending_idx); + xenvif_idx_unmap(queue, pending_idx); continue; } /* Error on this fragment: respond to client with an error. */ if (net_ratelimit()) - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Grant map of %d. frag failed! status: %d pending_idx: %u ref: %u\n", i, gop_map->status, pending_idx, gop_map->ref); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); /* Not the first error? Preceding frags already invalidated. */ if (err) @@ -1060,7 +1069,7 @@ check_frags: /* First error: invalidate preceding fragments. */ for (j = 0; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xenvif_idx_unmap(vif, pending_idx); + xenvif_idx_unmap(queue, pending_idx); } /* Remember the error: invalidate all subsequent fragments. */ @@ -1084,7 +1093,7 @@ check_frags: shinfo = skb_shinfo(first_skb); for (j = 0; j < shinfo->nr_frags; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xenvif_idx_unmap(vif, pending_idx); + xenvif_idx_unmap(queue, pending_idx); } } @@ -1092,7 +1101,7 @@ check_frags: return err; } -static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) +static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); int nr_frags = shinfo->nr_frags; @@ -1110,23 +1119,23 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) /* If this is not the first frag, chain it to the previous*/ if (prev_pending_idx == INVALID_PENDING_IDX) skb_shinfo(skb)->destructor_arg = - &callback_param(vif, pending_idx); + &callback_param(queue, pending_idx); else - callback_param(vif, prev_pending_idx).ctx = - &callback_param(vif, pending_idx); + callback_param(queue, prev_pending_idx).ctx = + &callback_param(queue, pending_idx); - callback_param(vif, pending_idx).ctx = NULL; + callback_param(queue, 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)); + txp = &queue->pending_tx_info[pending_idx].req; + page = virt_to_page(idx_to_kaddr(queue, pending_idx)); __skb_fill_page_desc(skb, i, page, txp->offset, txp->size); skb->len += txp->size; skb->data_len += txp->size; skb->truesize += txp->size; /* Take an extra reference to offset network stack's put_page */ - get_page(vif->mmap_pages[pending_idx]); + get_page(queue->mmap_pages[pending_idx]); } /* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc * overlaps with "index", and "mapping" is not set. I think mapping @@ -1136,33 +1145,33 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) skb->pfmemalloc = false; } -static int xenvif_get_extras(struct xenvif *vif, +static int xenvif_get_extras(struct xenvif_queue *queue, struct xen_netif_extra_info *extras, int work_to_do) { struct xen_netif_extra_info extra; - RING_IDX cons = vif->tx.req_cons; + RING_IDX cons = queue->tx.req_cons; do { if (unlikely(work_to_do-- <= 0)) { - netdev_err(vif->dev, "Missing extra info\n"); - xenvif_fatal_tx_err(vif); + netdev_err(queue->vif->dev, "Missing extra info\n"); + xenvif_fatal_tx_err(queue->vif); return -EBADR; } - memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons), + memcpy(&extra, RING_GET_REQUEST(&queue->tx, cons), sizeof(extra)); if (unlikely(!extra.type || extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { - vif->tx.req_cons = ++cons; - netdev_err(vif->dev, + queue->tx.req_cons = ++cons; + netdev_err(queue->vif->dev, "Invalid extra type: %d\n", extra.type); - xenvif_fatal_tx_err(vif); + xenvif_fatal_tx_err(queue->vif); return -EINVAL; } memcpy(&extras[extra.type - 1], &extra, sizeof(extra)); - vif->tx.req_cons = ++cons; + queue->tx.req_cons = ++cons; } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE); return work_to_do; @@ -1197,7 +1206,7 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return 0; } -static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) +static int checksum_setup(struct xenvif_queue *queue, struct sk_buff *skb) { bool recalculate_partial_csum = false; @@ -1207,7 +1216,7 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) * recalculate the partial checksum. */ if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { - vif->rx_gso_checksum_fixup++; + queue->stats.rx_gso_checksum_fixup++; skb->ip_summed = CHECKSUM_PARTIAL; recalculate_partial_csum = true; } @@ -1219,31 +1228,31 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) return skb_checksum_setup(skb, recalculate_partial_csum); } -static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) +static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) { u64 now = get_jiffies_64(); - u64 next_credit = vif->credit_window_start + - msecs_to_jiffies(vif->credit_usec / 1000); + u64 next_credit = queue->credit_window_start + + msecs_to_jiffies(queue->credit_usec / 1000); /* Timer could already be pending in rare cases. */ - if (timer_pending(&vif->credit_timeout)) + if (timer_pending(&queue->credit_timeout)) return true; /* Passed the point where we can replenish credit? */ if (time_after_eq64(now, next_credit)) { - vif->credit_window_start = now; - tx_add_credit(vif); + queue->credit_window_start = now; + tx_add_credit(queue); } /* Still too big to send right now? Set a callback. */ - if (size > vif->remaining_credit) { - vif->credit_timeout.data = - (unsigned long)vif; - vif->credit_timeout.function = + if (size > queue->remaining_credit) { + queue->credit_timeout.data = + (unsigned long)queue; + queue->credit_timeout.function = tx_credit_callback; - mod_timer(&vif->credit_timeout, + mod_timer(&queue->credit_timeout, next_credit); - vif->credit_window_start = next_credit; + queue->credit_window_start = next_credit; return true; } @@ -1251,16 +1260,16 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return false; } -static void xenvif_tx_build_gops(struct xenvif *vif, +static void xenvif_tx_build_gops(struct xenvif_queue *queue, int budget, unsigned *copy_ops, unsigned *map_ops) { - struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop; + struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop; struct sk_buff *skb; int ret; - while (skb_queue_len(&vif->tx_queue) < budget) { + while (skb_queue_len(&queue->tx_queue) < budget) { struct xen_netif_tx_request txreq; struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1]; @@ -1270,69 +1279,69 @@ static void xenvif_tx_build_gops(struct xenvif *vif, unsigned int data_len; pending_ring_idx_t index; - if (vif->tx.sring->req_prod - vif->tx.req_cons > + if (queue->tx.sring->req_prod - queue->tx.req_cons > XEN_NETIF_TX_RING_SIZE) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Impossible number of requests. " "req_prod %d, req_cons %d, size %ld\n", - vif->tx.sring->req_prod, vif->tx.req_cons, + queue->tx.sring->req_prod, queue->tx.req_cons, XEN_NETIF_TX_RING_SIZE); - xenvif_fatal_tx_err(vif); + xenvif_fatal_tx_err(queue->vif); break; } - work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx); + work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx); if (!work_to_do) break; - idx = vif->tx.req_cons; + idx = queue->tx.req_cons; rmb(); /* Ensure that we see the request before we copy it. */ - memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq)); + memcpy(&txreq, RING_GET_REQUEST(&queue->tx, idx), sizeof(txreq)); /* Credit-based scheduling. */ - if (txreq.size > vif->remaining_credit && - tx_credit_exceeded(vif, txreq.size)) + if (txreq.size > queue->remaining_credit && + tx_credit_exceeded(queue, txreq.size)) break; - vif->remaining_credit -= txreq.size; + queue->remaining_credit -= txreq.size; work_to_do--; - vif->tx.req_cons = ++idx; + queue->tx.req_cons = ++idx; memset(extras, 0, sizeof(extras)); if (txreq.flags & XEN_NETTXF_extra_info) { - work_to_do = xenvif_get_extras(vif, extras, + work_to_do = xenvif_get_extras(queue, extras, work_to_do); - idx = vif->tx.req_cons; + idx = queue->tx.req_cons; if (unlikely(work_to_do < 0)) break; } - ret = xenvif_count_requests(vif, &txreq, txfrags, work_to_do); + ret = xenvif_count_requests(queue, &txreq, txfrags, work_to_do); if (unlikely(ret < 0)) break; idx += ret; if (unlikely(txreq.size < ETH_HLEN)) { - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Bad packet size: %d\n", txreq.size); - xenvif_tx_err(vif, &txreq, idx); + xenvif_tx_err(queue, &txreq, idx); break; } /* No crossing a page as the payload mustn't fragment. */ if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "txreq.offset: %x, size: %u, end: %lu\n", txreq.offset, txreq.size, (txreq.offset&~PAGE_MASK) + txreq.size); - xenvif_fatal_tx_err(vif); + xenvif_fatal_tx_err(queue->vif); break; } - index = pending_index(vif->pending_cons); - pending_idx = vif->pending_ring[index]; + index = pending_index(queue->pending_cons); + pending_idx = queue->pending_ring[index]; data_len = (txreq.size > PKT_PROT_LEN && ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? @@ -1340,9 +1349,9 @@ static void xenvif_tx_build_gops(struct xenvif *vif, skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { - netdev_dbg(vif->dev, + netdev_dbg(queue->vif->dev, "Can't allocate a skb in start_xmit.\n"); - xenvif_tx_err(vif, &txreq, idx); + xenvif_tx_err(queue, &txreq, idx); break; } @@ -1350,7 +1359,7 @@ static void xenvif_tx_build_gops(struct xenvif *vif, struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; - if (xenvif_set_skb_gso(vif, skb, gso)) { + if (xenvif_set_skb_gso(queue->vif, skb, gso)) { /* Failure in xenvif_set_skb_gso is fatal. */ kfree_skb(skb); break; @@ -1360,18 +1369,18 @@ static void xenvif_tx_build_gops(struct xenvif *vif, XENVIF_TX_CB(skb)->pending_idx = pending_idx; __skb_put(skb, data_len); - vif->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; - vif->tx_copy_ops[*copy_ops].source.domid = vif->domid; - vif->tx_copy_ops[*copy_ops].source.offset = txreq.offset; + queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; + queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid; + queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset; - vif->tx_copy_ops[*copy_ops].dest.u.gmfn = + queue->tx_copy_ops[*copy_ops].dest.u.gmfn = virt_to_mfn(skb->data); - vif->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; - vif->tx_copy_ops[*copy_ops].dest.offset = + queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; + queue->tx_copy_ops[*copy_ops].dest.offset = offset_in_page(skb->data); - vif->tx_copy_ops[*copy_ops].len = data_len; - vif->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; + queue->tx_copy_ops[*copy_ops].len = data_len; + queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; (*copy_ops)++; @@ -1380,42 +1389,42 @@ static void xenvif_tx_build_gops(struct xenvif *vif, skb_shinfo(skb)->nr_frags++; frag_set_pending_idx(&skb_shinfo(skb)->frags[0], pending_idx); - xenvif_tx_create_map_op(vif, pending_idx, &txreq, gop); + xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop); gop++; } else { frag_set_pending_idx(&skb_shinfo(skb)->frags[0], INVALID_PENDING_IDX); - memcpy(&vif->pending_tx_info[pending_idx].req, &txreq, + memcpy(&queue->pending_tx_info[pending_idx].req, &txreq, sizeof(txreq)); } - vif->pending_cons++; + queue->pending_cons++; - request_gop = xenvif_get_requests(vif, skb, txfrags, gop); + request_gop = xenvif_get_requests(queue, skb, txfrags, gop); if (request_gop == NULL) { kfree_skb(skb); - xenvif_tx_err(vif, &txreq, idx); + xenvif_tx_err(queue, &txreq, idx); break; } gop = request_gop; - __skb_queue_tail(&vif->tx_queue, skb); + __skb_queue_tail(&queue->tx_queue, skb); - vif->tx.req_cons = idx; + queue->tx.req_cons = idx; - if (((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops)) || - (*copy_ops >= ARRAY_SIZE(vif->tx_copy_ops))) + if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) || + (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops))) break; } - (*map_ops) = gop - vif->tx_map_ops; + (*map_ops) = gop - queue->tx_map_ops; return; } /* 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) +static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *skb) { unsigned int offset = skb_headlen(skb); skb_frag_t frags[MAX_SKB_FRAGS]; @@ -1423,10 +1432,10 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb) struct ubuf_info *uarg; struct sk_buff *nskb = skb_shinfo(skb)->frag_list; - vif->tx_zerocopy_sent += 2; - vif->tx_frag_overflow++; + queue->stats.tx_zerocopy_sent += 2; + queue->stats.tx_frag_overflow++; - xenvif_fill_frags(vif, nskb); + xenvif_fill_frags(queue, nskb); /* Subtract frags size, we will correct it later */ skb->truesize -= skb->data_len; skb->len += nskb->len; @@ -1478,37 +1487,37 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb) return 0; } -static int xenvif_tx_submit(struct xenvif *vif) +static int xenvif_tx_submit(struct xenvif_queue *queue) { - struct gnttab_map_grant_ref *gop_map = vif->tx_map_ops; - struct gnttab_copy *gop_copy = vif->tx_copy_ops; + struct gnttab_map_grant_ref *gop_map = queue->tx_map_ops; + struct gnttab_copy *gop_copy = queue->tx_copy_ops; struct sk_buff *skb; int work_done = 0; - while ((skb = __skb_dequeue(&vif->tx_queue)) != NULL) { + while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; u16 pending_idx; unsigned data_len; pending_idx = XENVIF_TX_CB(skb)->pending_idx; - txp = &vif->pending_tx_info[pending_idx].req; + txp = &queue->pending_tx_info[pending_idx].req; /* Check the remap error code. */ - if (unlikely(xenvif_tx_check_gop(vif, skb, &gop_map, &gop_copy))) { + if (unlikely(xenvif_tx_check_gop(queue, skb, &gop_map, &gop_copy))) { skb_shinfo(skb)->nr_frags = 0; kfree_skb(skb); continue; } data_len = skb->len; - callback_param(vif, pending_idx).ctx = NULL; + callback_param(queue, pending_idx).ctx = NULL; if (data_len < txp->size) { /* Append the packet payload as a fragment. */ txp->offset += data_len; txp->size -= data_len; } else { /* Schedule a response immediately. */ - xenvif_idx_release(vif, pending_idx, + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_OKAY); } @@ -1517,12 +1526,12 @@ static int xenvif_tx_submit(struct xenvif *vif) else if (txp->flags & XEN_NETTXF_data_validated) skb->ip_summed = CHECKSUM_UNNECESSARY; - xenvif_fill_frags(vif, skb); + xenvif_fill_frags(queue, skb); if (unlikely(skb_has_frag_list(skb))) { - if (xenvif_handle_frag_list(vif, skb)) { + if (xenvif_handle_frag_list(queue, skb)) { if (net_ratelimit()) - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Not enough memory to consolidate frag_list!\n"); skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; kfree_skb(skb); @@ -1535,12 +1544,12 @@ static int xenvif_tx_submit(struct xenvif *vif) __pskb_pull_tail(skb, target - skb_headlen(skb)); } - skb->dev = vif->dev; + skb->dev = queue->vif->dev; skb->protocol = eth_type_trans(skb, skb->dev); skb_reset_network_header(skb); - if (checksum_setup(vif, skb)) { - netdev_dbg(vif->dev, + if (checksum_setup(queue, skb)) { + netdev_dbg(queue->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) @@ -1565,8 +1574,8 @@ static int xenvif_tx_submit(struct xenvif *vif) DIV_ROUND_UP(skb->len - hdrlen, mss); } - vif->dev->stats.rx_bytes += skb->len; - vif->dev->stats.rx_packets++; + queue->stats.rx_bytes += skb->len; + queue->stats.rx_packets++; work_done++; @@ -1577,7 +1586,7 @@ static int xenvif_tx_submit(struct xenvif *vif) */ if (skb_shinfo(skb)->destructor_arg) { skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; - vif->tx_zerocopy_sent++; + queue->stats.tx_zerocopy_sent++; } netif_receive_skb(skb); @@ -1590,47 +1599,47 @@ 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); + struct xenvif_queue *queue = ubuf_to_queue(ubuf); /* This is the only place where we grab this lock, to protect callbacks * from each other. */ - spin_lock_irqsave(&vif->callback_lock, flags); + spin_lock_irqsave(&queue->callback_lock, flags); do { u16 pending_idx = ubuf->desc; ubuf = (struct ubuf_info *) ubuf->ctx; - BUG_ON(vif->dealloc_prod - vif->dealloc_cons >= + BUG_ON(queue->dealloc_prod - queue->dealloc_cons >= MAX_PENDING_REQS); - index = pending_index(vif->dealloc_prod); - vif->dealloc_ring[index] = pending_idx; + index = pending_index(queue->dealloc_prod); + queue->dealloc_ring[index] = pending_idx; /* Sync with xenvif_tx_dealloc_action: * insert idx then incr producer. */ smp_wmb(); - vif->dealloc_prod++; + queue->dealloc_prod++; } while (ubuf); - wake_up(&vif->dealloc_wq); - spin_unlock_irqrestore(&vif->callback_lock, flags); + wake_up(&queue->dealloc_wq); + spin_unlock_irqrestore(&queue->callback_lock, flags); if (likely(zerocopy_success)) - vif->tx_zerocopy_success++; + queue->stats.tx_zerocopy_success++; else - vif->tx_zerocopy_fail++; + queue->stats.tx_zerocopy_fail++; } -static inline void xenvif_tx_dealloc_action(struct xenvif *vif) +static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) { 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; + dc = queue->dealloc_cons; + gop = queue->tx_unmap_ops; /* Free up any grants we have finished using */ do { - dp = vif->dealloc_prod; + dp = queue->dealloc_prod; /* Ensure we see all indices enqueued by all * xenvif_zerocopy_callback(). @@ -1638,38 +1647,38 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif) smp_rmb(); while (dc != dp) { - BUG_ON(gop - vif->tx_unmap_ops > MAX_PENDING_REQS); + BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS); pending_idx = - vif->dealloc_ring[pending_index(dc++)]; + queue->dealloc_ring[pending_index(dc++)]; - pending_idx_release[gop-vif->tx_unmap_ops] = + pending_idx_release[gop-queue->tx_unmap_ops] = pending_idx; - vif->pages_to_unmap[gop-vif->tx_unmap_ops] = - vif->mmap_pages[pending_idx]; + queue->pages_to_unmap[gop-queue->tx_unmap_ops] = + queue->mmap_pages[pending_idx]; gnttab_set_unmap_op(gop, - idx_to_kaddr(vif, pending_idx), + idx_to_kaddr(queue, pending_idx), GNTMAP_host_map, - vif->grant_tx_handle[pending_idx]); - xenvif_grant_handle_reset(vif, pending_idx); + queue->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(queue, pending_idx); ++gop; } - } while (dp != vif->dealloc_prod); + } while (dp != queue->dealloc_prod); - vif->dealloc_cons = dc; + queue->dealloc_cons = dc; - if (gop - vif->tx_unmap_ops > 0) { + if (gop - queue->tx_unmap_ops > 0) { int ret; - ret = gnttab_unmap_refs(vif->tx_unmap_ops, + ret = gnttab_unmap_refs(queue->tx_unmap_ops, NULL, - vif->pages_to_unmap, - gop - vif->tx_unmap_ops); + queue->pages_to_unmap, + gop - queue->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) { + netdev_err(queue->vif->dev, "Unmap fail: nr_ops %tx ret %d\n", + gop - queue->tx_unmap_ops, ret); + for (i = 0; i < gop - queue->tx_unmap_ops; ++i) { if (gop[i].status != GNTST_okay) - netdev_err(vif->dev, + netdev_err(queue->vif->dev, " host_addr: %llx handle: %x status: %d\n", gop[i].host_addr, gop[i].handle, @@ -1679,91 +1688,91 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif) } } - for (i = 0; i < gop - vif->tx_unmap_ops; ++i) - xenvif_idx_release(vif, pending_idx_release[i], + for (i = 0; i < gop - queue->tx_unmap_ops; ++i) + xenvif_idx_release(queue, pending_idx_release[i], XEN_NETIF_RSP_OKAY); } /* Called after netfront has transmitted */ -int xenvif_tx_action(struct xenvif *vif, int budget) +int xenvif_tx_action(struct xenvif_queue *queue, int budget) { unsigned nr_mops, nr_cops = 0; int work_done, ret; - if (unlikely(!tx_work_todo(vif))) + if (unlikely(!tx_work_todo(queue))) return 0; - xenvif_tx_build_gops(vif, budget, &nr_cops, &nr_mops); + xenvif_tx_build_gops(queue, budget, &nr_cops, &nr_mops); if (nr_cops == 0) return 0; - gnttab_batch_copy(vif->tx_copy_ops, nr_cops); + gnttab_batch_copy(queue->tx_copy_ops, nr_cops); if (nr_mops != 0) { - ret = gnttab_map_refs(vif->tx_map_ops, + ret = gnttab_map_refs(queue->tx_map_ops, NULL, - vif->pages_to_map, + queue->pages_to_map, nr_mops); BUG_ON(ret); } - work_done = xenvif_tx_submit(vif); + work_done = xenvif_tx_submit(queue); return work_done; } -static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx, +static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, u8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; unsigned long flags; - pending_tx_info = &vif->pending_tx_info[pending_idx]; - 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; + pending_tx_info = &queue->pending_tx_info[pending_idx]; + spin_lock_irqsave(&queue->response_lock, flags); + make_tx_response(queue, &pending_tx_info->req, status); + index = pending_index(queue->pending_prod); + queue->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); + queue->pending_prod++; + spin_unlock_irqrestore(&queue->response_lock, flags); } -static void make_tx_response(struct xenvif *vif, +static void make_tx_response(struct xenvif_queue *queue, struct xen_netif_tx_request *txp, s8 st) { - RING_IDX i = vif->tx.rsp_prod_pvt; + RING_IDX i = queue->tx.rsp_prod_pvt; struct xen_netif_tx_response *resp; int notify; - resp = RING_GET_RESPONSE(&vif->tx, i); + resp = RING_GET_RESPONSE(&queue->tx, i); resp->id = txp->id; resp->status = st; if (txp->flags & XEN_NETTXF_extra_info) - RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL; + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; - vif->tx.rsp_prod_pvt = ++i; - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify); + queue->tx.rsp_prod_pvt = ++i; + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); if (notify) - notify_remote_via_irq(vif->tx_irq); + notify_remote_via_irq(queue->tx_irq); } -static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, +static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, u16 id, s8 st, u16 offset, u16 size, u16 flags) { - RING_IDX i = vif->rx.rsp_prod_pvt; + RING_IDX i = queue->rx.rsp_prod_pvt; struct xen_netif_rx_response *resp; - resp = RING_GET_RESPONSE(&vif->rx, i); + resp = RING_GET_RESPONSE(&queue->rx, i); resp->offset = offset; resp->flags = flags; resp->id = id; @@ -1771,26 +1780,26 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, if (st < 0) resp->status = (s16)st; - vif->rx.rsp_prod_pvt = ++i; + queue->rx.rsp_prod_pvt = ++i; return resp; } -void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx) +void xenvif_idx_unmap(struct xenvif_queue *queue, 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), + idx_to_kaddr(queue, pending_idx), GNTMAP_host_map, - vif->grant_tx_handle[pending_idx]); - xenvif_grant_handle_reset(vif, pending_idx); + queue->grant_tx_handle[pending_idx]); + xenvif_grant_handle_reset(queue, pending_idx); ret = gnttab_unmap_refs(&tx_unmap_op, NULL, - &vif->mmap_pages[pending_idx], 1); + &queue->mmap_pages[pending_idx], 1); if (ret) { - netdev_err(vif->dev, + netdev_err(queue->vif->dev, "Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n", ret, pending_idx, @@ -1800,41 +1809,40 @@ void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx) BUG(); } - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); + xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_OKAY); } -static inline int rx_work_todo(struct xenvif *vif) +static inline int rx_work_todo(struct xenvif_queue *queue) { - return (!skb_queue_empty(&vif->rx_queue) && - xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots)) || - vif->rx_queue_purge; + return (!skb_queue_empty(&queue->rx_queue) && + xenvif_rx_ring_slots_available(queue, queue->rx_last_skb_slots)) || + queue->rx_queue_purge; } -static inline int tx_work_todo(struct xenvif *vif) +static inline int tx_work_todo(struct xenvif_queue *queue) { - - if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))) + if (likely(RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))) return 1; return 0; } -static inline bool tx_dealloc_work_todo(struct xenvif *vif) +static inline bool tx_dealloc_work_todo(struct xenvif_queue *queue) { - return vif->dealloc_cons != vif->dealloc_prod; + return queue->dealloc_cons != queue->dealloc_prod; } -void xenvif_unmap_frontend_rings(struct xenvif *vif) +void xenvif_unmap_frontend_rings(struct xenvif_queue *queue) { - if (vif->tx.sring) - xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif), - vif->tx.sring); - if (vif->rx.sring) - xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif), - vif->rx.sring); + if (queue->tx.sring) + xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif), + queue->tx.sring); + if (queue->rx.sring) + xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif), + queue->rx.sring); } -int xenvif_map_frontend_rings(struct xenvif *vif, +int xenvif_map_frontend_rings(struct xenvif_queue *queue, grant_ref_t tx_ring_ref, grant_ref_t rx_ring_ref) { @@ -1844,85 +1852,78 @@ int xenvif_map_frontend_rings(struct xenvif *vif, int err = -ENOMEM; - err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif), + err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), tx_ring_ref, &addr); if (err) goto err; txs = (struct xen_netif_tx_sring *)addr; - BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE); + BACK_RING_INIT(&queue->tx, txs, PAGE_SIZE); - err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif), + err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), rx_ring_ref, &addr); if (err) goto err; rxs = (struct xen_netif_rx_sring *)addr; - BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE); + BACK_RING_INIT(&queue->rx, rxs, PAGE_SIZE); return 0; err: - xenvif_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(queue); return err; } -void xenvif_stop_queue(struct xenvif *vif) +static void xenvif_start_queue(struct xenvif_queue *queue) { - 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); + if (xenvif_schedulable(queue->vif)) + xenvif_wake_queue(queue); } int xenvif_kthread_guest_rx(void *data) { - struct xenvif *vif = data; + struct xenvif_queue *queue = data; struct sk_buff *skb; while (!kthread_should_stop()) { - wait_event_interruptible(vif->wq, - rx_work_todo(vif) || - vif->disabled || + wait_event_interruptible(queue->wq, + rx_work_todo(queue) || + queue->vif->disabled || kthread_should_stop()); /* This frontend is found to be rogue, disable it in * kthread context. Currently this is only set when * netback finds out frontend sends malformed packet, * but we cannot disable the interface in softirq - * context so we defer it here. + * context so we defer it here, if this thread is + * associated with queue 0. */ - if (unlikely(vif->disabled && netif_carrier_ok(vif->dev))) - xenvif_carrier_off(vif); + if (unlikely(queue->vif->disabled && netif_carrier_ok(queue->vif->dev) && queue->id == 0)) + xenvif_carrier_off(queue->vif); if (kthread_should_stop()) break; - if (vif->rx_queue_purge) { - skb_queue_purge(&vif->rx_queue); - vif->rx_queue_purge = false; + if (queue->rx_queue_purge) { + skb_queue_purge(&queue->rx_queue); + queue->rx_queue_purge = false; } - if (!skb_queue_empty(&vif->rx_queue)) - xenvif_rx_action(vif); + if (!skb_queue_empty(&queue->rx_queue)) + xenvif_rx_action(queue); - if (skb_queue_empty(&vif->rx_queue) && - netif_queue_stopped(vif->dev)) { - del_timer_sync(&vif->wake_queue); - xenvif_start_queue(vif); + if (skb_queue_empty(&queue->rx_queue) && + xenvif_queue_stopped(queue)) { + del_timer_sync(&queue->wake_queue); + xenvif_start_queue(queue); } cond_resched(); } /* Bin any remaining skbs */ - while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) + while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) dev_kfree_skb(skb); return 0; @@ -1930,22 +1931,22 @@ int xenvif_kthread_guest_rx(void *data) int xenvif_dealloc_kthread(void *data) { - struct xenvif *vif = data; + struct xenvif_queue *queue = data; while (!kthread_should_stop()) { - wait_event_interruptible(vif->dealloc_wq, - tx_dealloc_work_todo(vif) || + wait_event_interruptible(queue->dealloc_wq, + tx_dealloc_work_todo(queue) || kthread_should_stop()); if (kthread_should_stop()) break; - xenvif_tx_dealloc_action(vif); + xenvif_tx_dealloc_action(queue); cond_resched(); } /* Unmap anything remaining*/ - if (tx_dealloc_work_todo(vif)) - xenvif_tx_dealloc_action(vif); + if (tx_dealloc_work_todo(queue)) + xenvif_tx_dealloc_action(queue); return 0; } @@ -1957,6 +1958,9 @@ static int __init netback_init(void) if (!xen_domain()) return -ENODEV; + /* Allow as many queues as there are CPUs, by default */ + xenvif_max_queues = num_online_cpus(); + if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) { pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n", fatal_skb_slots, XEN_NETBK_LEGACY_SLOTS_MAX); diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 7a206cffb062..96c63dc2509e 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -19,6 +19,8 @@ */ #include "common.h" +#include <linux/vmalloc.h> +#include <linux/rtnetlink.h> struct backend_info { struct xenbus_device *dev; @@ -34,8 +36,9 @@ struct backend_info { u8 have_hotplug_status_watch:1; }; -static int connect_rings(struct backend_info *); -static void connect(struct backend_info *); +static int connect_rings(struct backend_info *be, struct xenvif_queue *queue); +static void connect(struct backend_info *be); +static int read_xenbus_vif_flags(struct backend_info *be); static void backend_create_xenvif(struct backend_info *be); static void unregister_hotplug_status_watch(struct backend_info *be); static void set_backend_state(struct backend_info *be, @@ -157,6 +160,12 @@ static int netback_probe(struct xenbus_device *dev, if (err) pr_debug("Error writing feature-split-event-channels\n"); + /* Multi-queue support: This is an optional feature. */ + err = xenbus_printf(XBT_NIL, dev->nodename, + "multi-queue-max-queues", "%u", xenvif_max_queues); + if (err) + pr_debug("Error writing multi-queue-max-queues\n"); + err = xenbus_switch_state(dev, XenbusStateInitWait); if (err) goto fail; @@ -485,10 +494,26 @@ static void connect(struct backend_info *be) { int err; struct xenbus_device *dev = be->dev; + unsigned long credit_bytes, credit_usec; + unsigned int queue_index; + unsigned int requested_num_queues; + struct xenvif_queue *queue; - err = connect_rings(be); - if (err) + /* Check whether the frontend requested multiple queues + * and read the number requested. + */ + err = xenbus_scanf(XBT_NIL, dev->otherend, + "multi-queue-num-queues", + "%u", &requested_num_queues); + if (err < 0) { + requested_num_queues = 1; /* Fall back to single queue */ + } else if (requested_num_queues > xenvif_max_queues) { + /* buggy or malicious guest */ + xenbus_dev_fatal(dev, err, + "guest requested %u queues, exceeding the maximum of %u.", + requested_num_queues, xenvif_max_queues); return; + } err = xen_net_read_mac(dev, be->vif->fe_dev_addr); if (err) { @@ -496,9 +521,54 @@ static void connect(struct backend_info *be) return; } - xen_net_read_rate(dev, &be->vif->credit_bytes, - &be->vif->credit_usec); - be->vif->remaining_credit = be->vif->credit_bytes; + xen_net_read_rate(dev, &credit_bytes, &credit_usec); + read_xenbus_vif_flags(be); + + /* Use the number of queues requested by the frontend */ + be->vif->queues = vzalloc(requested_num_queues * + sizeof(struct xenvif_queue)); + rtnl_lock(); + netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues); + rtnl_unlock(); + + for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) { + queue = &be->vif->queues[queue_index]; + queue->vif = be->vif; + queue->id = queue_index; + snprintf(queue->name, sizeof(queue->name), "%s-q%u", + be->vif->dev->name, queue->id); + + err = xenvif_init_queue(queue); + if (err) { + /* xenvif_init_queue() cleans up after itself on + * failure, but we need to clean up any previously + * initialised queues. Set num_queues to i so that + * earlier queues can be destroyed using the regular + * disconnect logic. + */ + rtnl_lock(); + netif_set_real_num_tx_queues(be->vif->dev, queue_index); + rtnl_unlock(); + goto err; + } + + queue->remaining_credit = credit_bytes; + + err = connect_rings(be, queue); + if (err) { + /* connect_rings() cleans up after itself on failure, + * but we need to clean up after xenvif_init_queue() here, + * and also clean up any previously initialised queues. + */ + xenvif_deinit_queue(queue); + rtnl_lock(); + netif_set_real_num_tx_queues(be->vif->dev, queue_index); + rtnl_unlock(); + goto err; + } + } + + xenvif_carrier_on(be->vif); unregister_hotplug_status_watch(be); err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, @@ -507,45 +577,109 @@ static void connect(struct backend_info *be) if (!err) be->have_hotplug_status_watch = 1; - netif_wake_queue(be->vif->dev); + netif_tx_wake_all_queues(be->vif->dev); + + return; + +err: + if (be->vif->dev->real_num_tx_queues > 0) + xenvif_disconnect(be->vif); /* Clean up existing queues */ + vfree(be->vif->queues); + be->vif->queues = NULL; + rtnl_lock(); + netif_set_real_num_tx_queues(be->vif->dev, 0); + rtnl_unlock(); + return; } -static int connect_rings(struct backend_info *be) +static int connect_rings(struct backend_info *be, struct xenvif_queue *queue) { - struct xenvif *vif = be->vif; struct xenbus_device *dev = be->dev; + unsigned int num_queues = queue->vif->dev->real_num_tx_queues; unsigned long tx_ring_ref, rx_ring_ref; - unsigned int tx_evtchn, rx_evtchn, rx_copy; + unsigned int tx_evtchn, rx_evtchn; int err; - int val; + char *xspath; + size_t xspathsize; + const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */ + + /* If the frontend requested 1 queue, or we have fallen back + * to single queue due to lack of frontend support for multi- + * queue, expect the remaining XenStore keys in the toplevel + * directory. Otherwise, expect them in a subdirectory called + * queue-N. + */ + if (num_queues == 1) { + xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL); + if (!xspath) { + xenbus_dev_fatal(dev, -ENOMEM, + "reading ring references"); + return -ENOMEM; + } + strcpy(xspath, dev->otherend); + } else { + xspathsize = strlen(dev->otherend) + xenstore_path_ext_size; + xspath = kzalloc(xspathsize, GFP_KERNEL); + if (!xspath) { + xenbus_dev_fatal(dev, -ENOMEM, + "reading ring references"); + return -ENOMEM; + } + snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend, + queue->id); + } - err = xenbus_gather(XBT_NIL, dev->otherend, + err = xenbus_gather(XBT_NIL, xspath, "tx-ring-ref", "%lu", &tx_ring_ref, "rx-ring-ref", "%lu", &rx_ring_ref, NULL); if (err) { xenbus_dev_fatal(dev, err, "reading %s/ring-ref", - dev->otherend); - return err; + xspath); + goto err; } /* Try split event channels first, then single event channel. */ - err = xenbus_gather(XBT_NIL, dev->otherend, + err = xenbus_gather(XBT_NIL, xspath, "event-channel-tx", "%u", &tx_evtchn, "event-channel-rx", "%u", &rx_evtchn, NULL); if (err < 0) { - err = xenbus_scanf(XBT_NIL, dev->otherend, + err = xenbus_scanf(XBT_NIL, xspath, "event-channel", "%u", &tx_evtchn); if (err < 0) { xenbus_dev_fatal(dev, err, "reading %s/event-channel(-tx/rx)", - dev->otherend); - return err; + xspath); + goto err; } rx_evtchn = tx_evtchn; } + /* Map the shared frame, irq etc. */ + err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref, + tx_evtchn, rx_evtchn); + if (err) { + xenbus_dev_fatal(dev, err, + "mapping shared-frames %lu/%lu port tx %u rx %u", + tx_ring_ref, rx_ring_ref, + tx_evtchn, rx_evtchn); + goto err; + } + + err = 0; +err: /* Regular return falls through with err == 0 */ + kfree(xspath); + return err; +} + +static int read_xenbus_vif_flags(struct backend_info *be) +{ + struct xenvif *vif = be->vif; + struct xenbus_device *dev = be->dev; + unsigned int rx_copy; + int err, val; + err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u", &rx_copy); if (err == -ENOENT) { @@ -621,16 +755,6 @@ static int connect_rings(struct backend_info *be) val = 0; vif->ipv6_csum = !!val; - /* Map the shared frame, irq etc. */ - err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref, - tx_evtchn, rx_evtchn); - if (err) { - xenbus_dev_fatal(dev, err, - "mapping shared-frames %lu/%lu port tx %u rx %u", - tx_ring_ref, rx_ring_ref, - tx_evtchn, rx_evtchn); - return err; - } return 0; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 895355de8ac4..5a7872ac3566 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -57,6 +57,12 @@ #include <xen/interface/memory.h> #include <xen/interface/grant_table.h> +/* Module parameters */ +static unsigned int xennet_max_queues; +module_param_named(max_queues, xennet_max_queues, uint, 0644); +MODULE_PARM_DESC(max_queues, + "Maximum number of queues per virtual interface"); + static const struct ethtool_ops xennet_ethtool_ops; struct netfront_cb { @@ -73,6 +79,12 @@ struct netfront_cb { #define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE) #define TX_MAX_TARGET min_t(int, NET_TX_RING_SIZE, 256) +/* Queue name is interface name with "-qNNN" appended */ +#define QUEUE_NAME_SIZE (IFNAMSIZ + 6) + +/* IRQ name is queue name with "-tx" or "-rx" appended */ +#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) + struct netfront_stats { u64 rx_packets; u64 tx_packets; @@ -81,9 +93,12 @@ struct netfront_stats { struct u64_stats_sync syncp; }; -struct netfront_info { - struct list_head list; - struct net_device *netdev; +struct netfront_info; + +struct netfront_queue { + unsigned int id; /* Queue ID, 0-based */ + char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */ + struct netfront_info *info; struct napi_struct napi; @@ -93,10 +108,8 @@ struct netfront_info { unsigned int tx_evtchn, rx_evtchn; unsigned int tx_irq, rx_irq; /* Only used when split event channels support is enabled */ - char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */ - char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */ - - struct xenbus_device *xbdev; + char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */ + char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */ spinlock_t tx_lock; struct xen_netif_tx_front_ring tx; @@ -140,11 +153,21 @@ struct netfront_info { unsigned long rx_pfn_array[NET_RX_RING_SIZE]; struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1]; struct mmu_update rx_mmu[NET_RX_RING_SIZE]; +}; + +struct netfront_info { + struct list_head list; + struct net_device *netdev; + + struct xenbus_device *xbdev; + + /* Multi-queue support */ + struct netfront_queue *queues; /* Statistics */ struct netfront_stats __percpu *stats; - unsigned long rx_gso_checksum_fixup; + atomic_t rx_gso_checksum_fixup; }; struct netfront_rx_info { @@ -187,21 +210,21 @@ static int xennet_rxidx(RING_IDX idx) return idx & (NET_RX_RING_SIZE - 1); } -static struct sk_buff *xennet_get_rx_skb(struct netfront_info *np, +static struct sk_buff *xennet_get_rx_skb(struct netfront_queue *queue, RING_IDX ri) { int i = xennet_rxidx(ri); - struct sk_buff *skb = np->rx_skbs[i]; - np->rx_skbs[i] = NULL; + struct sk_buff *skb = queue->rx_skbs[i]; + queue->rx_skbs[i] = NULL; return skb; } -static grant_ref_t xennet_get_rx_ref(struct netfront_info *np, +static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue, RING_IDX ri) { int i = xennet_rxidx(ri); - grant_ref_t ref = np->grant_rx_ref[i]; - np->grant_rx_ref[i] = GRANT_INVALID_REF; + grant_ref_t ref = queue->grant_rx_ref[i]; + queue->grant_rx_ref[i] = GRANT_INVALID_REF; return ref; } @@ -221,41 +244,40 @@ static bool xennet_can_sg(struct net_device *dev) static void rx_refill_timeout(unsigned long data) { - struct net_device *dev = (struct net_device *)data; - struct netfront_info *np = netdev_priv(dev); - napi_schedule(&np->napi); + struct netfront_queue *queue = (struct netfront_queue *)data; + napi_schedule(&queue->napi); } -static int netfront_tx_slot_available(struct netfront_info *np) +static int netfront_tx_slot_available(struct netfront_queue *queue) { - return (np->tx.req_prod_pvt - np->tx.rsp_cons) < + return (queue->tx.req_prod_pvt - queue->tx.rsp_cons) < (TX_MAX_TARGET - MAX_SKB_FRAGS - 2); } -static void xennet_maybe_wake_tx(struct net_device *dev) +static void xennet_maybe_wake_tx(struct netfront_queue *queue) { - struct netfront_info *np = netdev_priv(dev); + struct net_device *dev = queue->info->netdev; + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, queue->id); - if (unlikely(netif_queue_stopped(dev)) && - netfront_tx_slot_available(np) && + if (unlikely(netif_tx_queue_stopped(dev_queue)) && + netfront_tx_slot_available(queue) && likely(netif_running(dev))) - netif_wake_queue(dev); + netif_tx_wake_queue(netdev_get_tx_queue(dev, queue->id)); } -static void xennet_alloc_rx_buffers(struct net_device *dev) +static void xennet_alloc_rx_buffers(struct netfront_queue *queue) { unsigned short id; - struct netfront_info *np = netdev_priv(dev); struct sk_buff *skb; struct page *page; int i, batch_target, notify; - RING_IDX req_prod = np->rx.req_prod_pvt; + RING_IDX req_prod = queue->rx.req_prod_pvt; grant_ref_t ref; unsigned long pfn; void *vaddr; struct xen_netif_rx_request *req; - if (unlikely(!netif_carrier_ok(dev))) + if (unlikely(!netif_carrier_ok(queue->info->netdev))) return; /* @@ -264,9 +286,10 @@ static void xennet_alloc_rx_buffers(struct net_device *dev) * allocator, so should reduce the chance of failed allocation requests * both for ourself and for other kernel subsystems. */ - batch_target = np->rx_target - (req_prod - np->rx.rsp_cons); - for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) { - skb = __netdev_alloc_skb(dev, RX_COPY_THRESHOLD + NET_IP_ALIGN, + batch_target = queue->rx_target - (req_prod - queue->rx.rsp_cons); + for (i = skb_queue_len(&queue->rx_batch); i < batch_target; i++) { + skb = __netdev_alloc_skb(queue->info->netdev, + RX_COPY_THRESHOLD + NET_IP_ALIGN, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) goto no_skb; @@ -279,7 +302,7 @@ static void xennet_alloc_rx_buffers(struct net_device *dev) kfree_skb(skb); no_skb: /* Could not allocate any skbuffs. Try again later. */ - mod_timer(&np->rx_refill_timer, + mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10)); /* Any skbuffs queued for refill? Force them out. */ @@ -289,44 +312,44 @@ no_skb: } skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE); - __skb_queue_tail(&np->rx_batch, skb); + __skb_queue_tail(&queue->rx_batch, skb); } /* Is the batch large enough to be worthwhile? */ - if (i < (np->rx_target/2)) { - if (req_prod > np->rx.sring->req_prod) + if (i < (queue->rx_target/2)) { + if (req_prod > queue->rx.sring->req_prod) goto push; return; } /* Adjust our fill target if we risked running out of buffers. */ - if (((req_prod - np->rx.sring->rsp_prod) < (np->rx_target / 4)) && - ((np->rx_target *= 2) > np->rx_max_target)) - np->rx_target = np->rx_max_target; + if (((req_prod - queue->rx.sring->rsp_prod) < (queue->rx_target / 4)) && + ((queue->rx_target *= 2) > queue->rx_max_target)) + queue->rx_target = queue->rx_max_target; refill: for (i = 0; ; i++) { - skb = __skb_dequeue(&np->rx_batch); + skb = __skb_dequeue(&queue->rx_batch); if (skb == NULL) break; - skb->dev = dev; + skb->dev = queue->info->netdev; id = xennet_rxidx(req_prod + i); - BUG_ON(np->rx_skbs[id]); - np->rx_skbs[id] = skb; + BUG_ON(queue->rx_skbs[id]); + queue->rx_skbs[id] = skb; - ref = gnttab_claim_grant_reference(&np->gref_rx_head); + ref = gnttab_claim_grant_reference(&queue->gref_rx_head); BUG_ON((signed short)ref < 0); - np->grant_rx_ref[id] = ref; + queue->grant_rx_ref[id] = ref; pfn = page_to_pfn(skb_frag_page(&skb_shinfo(skb)->frags[0])); vaddr = page_address(skb_frag_page(&skb_shinfo(skb)->frags[0])); - req = RING_GET_REQUEST(&np->rx, req_prod + i); + req = RING_GET_REQUEST(&queue->rx, req_prod + i); gnttab_grant_foreign_access_ref(ref, - np->xbdev->otherend_id, + queue->info->xbdev->otherend_id, pfn_to_mfn(pfn), 0); @@ -337,72 +360,77 @@ no_skb: wmb(); /* barrier so backend seens requests */ /* Above is a suitable barrier to ensure backend will see requests. */ - np->rx.req_prod_pvt = req_prod + i; + queue->rx.req_prod_pvt = req_prod + i; push: - RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->rx, notify); + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->rx, notify); if (notify) - notify_remote_via_irq(np->rx_irq); + notify_remote_via_irq(queue->rx_irq); } static int xennet_open(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - - napi_enable(&np->napi); - - spin_lock_bh(&np->rx_lock); - if (netif_carrier_ok(dev)) { - xennet_alloc_rx_buffers(dev); - np->rx.sring->rsp_event = np->rx.rsp_cons + 1; - if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx)) - napi_schedule(&np->napi); + unsigned int num_queues = dev->real_num_tx_queues; + unsigned int i = 0; + struct netfront_queue *queue = NULL; + + for (i = 0; i < num_queues; ++i) { + queue = &np->queues[i]; + napi_enable(&queue->napi); + + spin_lock_bh(&queue->rx_lock); + if (netif_carrier_ok(dev)) { + xennet_alloc_rx_buffers(queue); + queue->rx.sring->rsp_event = queue->rx.rsp_cons + 1; + if (RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)) + napi_schedule(&queue->napi); + } + spin_unlock_bh(&queue->rx_lock); } - spin_unlock_bh(&np->rx_lock); - netif_start_queue(dev); + netif_tx_start_all_queues(dev); return 0; } -static void xennet_tx_buf_gc(struct net_device *dev) +static void xennet_tx_buf_gc(struct netfront_queue *queue) { RING_IDX cons, prod; unsigned short id; - struct netfront_info *np = netdev_priv(dev); struct sk_buff *skb; - BUG_ON(!netif_carrier_ok(dev)); + BUG_ON(!netif_carrier_ok(queue->info->netdev)); do { - prod = np->tx.sring->rsp_prod; + prod = queue->tx.sring->rsp_prod; rmb(); /* Ensure we see responses up to 'rp'. */ - for (cons = np->tx.rsp_cons; cons != prod; cons++) { + for (cons = queue->tx.rsp_cons; cons != prod; cons++) { struct xen_netif_tx_response *txrsp; - txrsp = RING_GET_RESPONSE(&np->tx, cons); + txrsp = RING_GET_RESPONSE(&queue->tx, cons); if (txrsp->status == XEN_NETIF_RSP_NULL) continue; id = txrsp->id; - skb = np->tx_skbs[id].skb; + skb = queue->tx_skbs[id].skb; if (unlikely(gnttab_query_foreign_access( - np->grant_tx_ref[id]) != 0)) { + queue->grant_tx_ref[id]) != 0)) { pr_alert("%s: warning -- grant still in use by backend domain\n", __func__); BUG(); } gnttab_end_foreign_access_ref( - np->grant_tx_ref[id], GNTMAP_readonly); + queue->grant_tx_ref[id], GNTMAP_readonly); gnttab_release_grant_reference( - &np->gref_tx_head, np->grant_tx_ref[id]); - np->grant_tx_ref[id] = GRANT_INVALID_REF; - np->grant_tx_page[id] = NULL; - add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, id); + &queue->gref_tx_head, queue->grant_tx_ref[id]); + queue->grant_tx_ref[id] = GRANT_INVALID_REF; + queue->grant_tx_page[id] = NULL; + add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id); dev_kfree_skb_irq(skb); } - np->tx.rsp_cons = prod; + queue->tx.rsp_cons = prod; /* * Set a new event, then check for race with update of tx_cons. @@ -412,21 +440,20 @@ static void xennet_tx_buf_gc(struct net_device *dev) * data is outstanding: in such cases notification from Xen is * likely to be the only kick that we'll get. */ - np->tx.sring->rsp_event = - prod + ((np->tx.sring->req_prod - prod) >> 1) + 1; + queue->tx.sring->rsp_event = + prod + ((queue->tx.sring->req_prod - prod) >> 1) + 1; mb(); /* update shared area */ - } while ((cons == prod) && (prod != np->tx.sring->rsp_prod)); + } while ((cons == prod) && (prod != queue->tx.sring->rsp_prod)); - xennet_maybe_wake_tx(dev); + xennet_maybe_wake_tx(queue); } -static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, +static void xennet_make_frags(struct sk_buff *skb, struct netfront_queue *queue, struct xen_netif_tx_request *tx) { - struct netfront_info *np = netdev_priv(dev); char *data = skb->data; unsigned long mfn; - RING_IDX prod = np->tx.req_prod_pvt; + RING_IDX prod = queue->tx.req_prod_pvt; int frags = skb_shinfo(skb)->nr_frags; unsigned int offset = offset_in_page(data); unsigned int len = skb_headlen(skb); @@ -443,19 +470,19 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, data += tx->size; offset = 0; - id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs); - np->tx_skbs[id].skb = skb_get(skb); - tx = RING_GET_REQUEST(&np->tx, prod++); + id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); + queue->tx_skbs[id].skb = skb_get(skb); + tx = RING_GET_REQUEST(&queue->tx, prod++); tx->id = id; - ref = gnttab_claim_grant_reference(&np->gref_tx_head); + ref = gnttab_claim_grant_reference(&queue->gref_tx_head); BUG_ON((signed short)ref < 0); mfn = virt_to_mfn(data); - gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id, + gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id, mfn, GNTMAP_readonly); - np->grant_tx_page[id] = virt_to_page(data); - tx->gref = np->grant_tx_ref[id] = ref; + queue->grant_tx_page[id] = virt_to_page(data); + tx->gref = queue->grant_tx_ref[id] = ref; tx->offset = offset; tx->size = len; tx->flags = 0; @@ -487,21 +514,21 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, tx->flags |= XEN_NETTXF_more_data; - id = get_id_from_freelist(&np->tx_skb_freelist, - np->tx_skbs); - np->tx_skbs[id].skb = skb_get(skb); - tx = RING_GET_REQUEST(&np->tx, prod++); + id = get_id_from_freelist(&queue->tx_skb_freelist, + queue->tx_skbs); + queue->tx_skbs[id].skb = skb_get(skb); + tx = RING_GET_REQUEST(&queue->tx, prod++); tx->id = id; - ref = gnttab_claim_grant_reference(&np->gref_tx_head); + ref = gnttab_claim_grant_reference(&queue->gref_tx_head); BUG_ON((signed short)ref < 0); mfn = pfn_to_mfn(page_to_pfn(page)); gnttab_grant_foreign_access_ref(ref, - np->xbdev->otherend_id, + queue->info->xbdev->otherend_id, mfn, GNTMAP_readonly); - np->grant_tx_page[id] = page; - tx->gref = np->grant_tx_ref[id] = ref; + queue->grant_tx_page[id] = page; + tx->gref = queue->grant_tx_ref[id] = ref; tx->offset = offset; tx->size = bytes; tx->flags = 0; @@ -518,7 +545,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, } } - np->tx.req_prod_pvt = prod; + queue->tx.req_prod_pvt = prod; } /* @@ -544,6 +571,24 @@ static int xennet_count_skb_frag_slots(struct sk_buff *skb) return pages; } +static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + unsigned int num_queues = dev->real_num_tx_queues; + u32 hash; + u16 queue_idx; + + /* First, check if there is only one queue */ + if (num_queues == 1) { + queue_idx = 0; + } else { + hash = skb_get_hash(skb); + queue_idx = hash % num_queues; + } + + return queue_idx; +} + static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned short id; @@ -559,6 +604,16 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int offset = offset_in_page(data); unsigned int len = skb_headlen(skb); unsigned long flags; + struct netfront_queue *queue = NULL; + unsigned int num_queues = dev->real_num_tx_queues; + u16 queue_index; + + /* Drop the packet if no queues are set up */ + if (num_queues < 1) + goto drop; + /* Determine which queue to transmit this SKB on */ + queue_index = skb_get_queue_mapping(skb); + queue = &np->queues[queue_index]; /* If skb->len is too big for wire format, drop skb and alert * user about misconfiguration. @@ -578,30 +633,30 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) goto drop; } - spin_lock_irqsave(&np->tx_lock, flags); + spin_lock_irqsave(&queue->tx_lock, flags); if (unlikely(!netif_carrier_ok(dev) || (slots > 1 && !xennet_can_sg(dev)) || netif_needs_gso(skb, netif_skb_features(skb)))) { - spin_unlock_irqrestore(&np->tx_lock, flags); + spin_unlock_irqrestore(&queue->tx_lock, flags); goto drop; } - i = np->tx.req_prod_pvt; + i = queue->tx.req_prod_pvt; - id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs); - np->tx_skbs[id].skb = skb; + id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); + queue->tx_skbs[id].skb = skb; - tx = RING_GET_REQUEST(&np->tx, i); + tx = RING_GET_REQUEST(&queue->tx, i); tx->id = id; - ref = gnttab_claim_grant_reference(&np->gref_tx_head); + ref = gnttab_claim_grant_reference(&queue->gref_tx_head); BUG_ON((signed short)ref < 0); mfn = virt_to_mfn(data); gnttab_grant_foreign_access_ref( - ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly); - np->grant_tx_page[id] = virt_to_page(data); - tx->gref = np->grant_tx_ref[id] = ref; + ref, queue->info->xbdev->otherend_id, mfn, GNTMAP_readonly); + queue->grant_tx_page[id] = virt_to_page(data); + tx->gref = queue->grant_tx_ref[id] = ref; tx->offset = offset; tx->size = len; @@ -617,7 +672,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) struct xen_netif_extra_info *gso; gso = (struct xen_netif_extra_info *) - RING_GET_REQUEST(&np->tx, ++i); + RING_GET_REQUEST(&queue->tx, ++i); tx->flags |= XEN_NETTXF_extra_info; @@ -632,14 +687,14 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) gso->flags = 0; } - np->tx.req_prod_pvt = i + 1; + queue->tx.req_prod_pvt = i + 1; - xennet_make_frags(skb, dev, tx); + xennet_make_frags(skb, queue, tx); tx->size = skb->len; - RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->tx, notify); + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify); if (notify) - notify_remote_via_irq(np->tx_irq); + notify_remote_via_irq(queue->tx_irq); u64_stats_update_begin(&stats->syncp); stats->tx_bytes += skb->len; @@ -647,12 +702,12 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) u64_stats_update_end(&stats->syncp); /* Note: It is not safe to access skb after xennet_tx_buf_gc()! */ - xennet_tx_buf_gc(dev); + xennet_tx_buf_gc(queue); - if (!netfront_tx_slot_available(np)) - netif_stop_queue(dev); + if (!netfront_tx_slot_available(queue)) + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); - spin_unlock_irqrestore(&np->tx_lock, flags); + spin_unlock_irqrestore(&queue->tx_lock, flags); return NETDEV_TX_OK; @@ -665,32 +720,38 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - netif_stop_queue(np->netdev); - napi_disable(&np->napi); + unsigned int num_queues = dev->real_num_tx_queues; + unsigned int i; + struct netfront_queue *queue; + netif_tx_stop_all_queues(np->netdev); + for (i = 0; i < num_queues; ++i) { + queue = &np->queues[i]; + napi_disable(&queue->napi); + } return 0; } -static void xennet_move_rx_slot(struct netfront_info *np, struct sk_buff *skb, +static void xennet_move_rx_slot(struct netfront_queue *queue, struct sk_buff *skb, grant_ref_t ref) { - int new = xennet_rxidx(np->rx.req_prod_pvt); - - BUG_ON(np->rx_skbs[new]); - np->rx_skbs[new] = skb; - np->grant_rx_ref[new] = ref; - RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->id = new; - RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->gref = ref; - np->rx.req_prod_pvt++; + int new = xennet_rxidx(queue->rx.req_prod_pvt); + + BUG_ON(queue->rx_skbs[new]); + queue->rx_skbs[new] = skb; + queue->grant_rx_ref[new] = ref; + RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->id = new; + RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->gref = ref; + queue->rx.req_prod_pvt++; } -static int xennet_get_extras(struct netfront_info *np, +static int xennet_get_extras(struct netfront_queue *queue, struct xen_netif_extra_info *extras, RING_IDX rp) { struct xen_netif_extra_info *extra; - struct device *dev = &np->netdev->dev; - RING_IDX cons = np->rx.rsp_cons; + struct device *dev = &queue->info->netdev->dev; + RING_IDX cons = queue->rx.rsp_cons; int err = 0; do { @@ -705,7 +766,7 @@ static int xennet_get_extras(struct netfront_info *np, } extra = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&np->rx, ++cons); + RING_GET_RESPONSE(&queue->rx, ++cons); if (unlikely(!extra->type || extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) { @@ -718,33 +779,33 @@ static int xennet_get_extras(struct netfront_info *np, sizeof(*extra)); } - skb = xennet_get_rx_skb(np, cons); - ref = xennet_get_rx_ref(np, cons); - xennet_move_rx_slot(np, skb, ref); + skb = xennet_get_rx_skb(queue, cons); + ref = xennet_get_rx_ref(queue, cons); + xennet_move_rx_slot(queue, skb, ref); } while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE); - np->rx.rsp_cons = cons; + queue->rx.rsp_cons = cons; return err; } -static int xennet_get_responses(struct netfront_info *np, +static int xennet_get_responses(struct netfront_queue *queue, struct netfront_rx_info *rinfo, RING_IDX rp, struct sk_buff_head *list) { struct xen_netif_rx_response *rx = &rinfo->rx; struct xen_netif_extra_info *extras = rinfo->extras; - struct device *dev = &np->netdev->dev; - RING_IDX cons = np->rx.rsp_cons; - struct sk_buff *skb = xennet_get_rx_skb(np, cons); - grant_ref_t ref = xennet_get_rx_ref(np, cons); + struct device *dev = &queue->info->netdev->dev; + RING_IDX cons = queue->rx.rsp_cons; + struct sk_buff *skb = xennet_get_rx_skb(queue, cons); + grant_ref_t ref = xennet_get_rx_ref(queue, cons); int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD); int slots = 1; int err = 0; unsigned long ret; if (rx->flags & XEN_NETRXF_extra_info) { - err = xennet_get_extras(np, extras, rp); - cons = np->rx.rsp_cons; + err = xennet_get_extras(queue, extras, rp); + cons = queue->rx.rsp_cons; } for (;;) { @@ -753,7 +814,7 @@ static int xennet_get_responses(struct netfront_info *np, if (net_ratelimit()) dev_warn(dev, "rx->offset: %x, size: %u\n", rx->offset, rx->status); - xennet_move_rx_slot(np, skb, ref); + xennet_move_rx_slot(queue, skb, ref); err = -EINVAL; goto next; } @@ -774,7 +835,7 @@ static int xennet_get_responses(struct netfront_info *np, ret = gnttab_end_foreign_access_ref(ref, 0); BUG_ON(!ret); - gnttab_release_grant_reference(&np->gref_rx_head, ref); + gnttab_release_grant_reference(&queue->gref_rx_head, ref); __skb_queue_tail(list, skb); @@ -789,9 +850,9 @@ next: break; } - rx = RING_GET_RESPONSE(&np->rx, cons + slots); - skb = xennet_get_rx_skb(np, cons + slots); - ref = xennet_get_rx_ref(np, cons + slots); + rx = RING_GET_RESPONSE(&queue->rx, cons + slots); + skb = xennet_get_rx_skb(queue, cons + slots); + ref = xennet_get_rx_ref(queue, cons + slots); slots++; } @@ -802,7 +863,7 @@ next: } if (unlikely(err)) - np->rx.rsp_cons = cons + slots; + queue->rx.rsp_cons = cons + slots; return err; } @@ -836,17 +897,17 @@ static int xennet_set_skb_gso(struct sk_buff *skb, return 0; } -static RING_IDX xennet_fill_frags(struct netfront_info *np, +static RING_IDX xennet_fill_frags(struct netfront_queue *queue, struct sk_buff *skb, struct sk_buff_head *list) { struct skb_shared_info *shinfo = skb_shinfo(skb); - RING_IDX cons = np->rx.rsp_cons; + RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb; while ((nskb = __skb_dequeue(list))) { struct xen_netif_rx_response *rx = - RING_GET_RESPONSE(&np->rx, ++cons); + RING_GET_RESPONSE(&queue->rx, ++cons); skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0]; if (shinfo->nr_frags == MAX_SKB_FRAGS) { @@ -879,7 +940,7 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb) */ if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { struct netfront_info *np = netdev_priv(dev); - np->rx_gso_checksum_fixup++; + atomic_inc(&np->rx_gso_checksum_fixup); skb->ip_summed = CHECKSUM_PARTIAL; recalculate_partial_csum = true; } @@ -891,11 +952,10 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb) return skb_checksum_setup(skb, recalculate_partial_csum); } -static int handle_incoming_queue(struct net_device *dev, +static int handle_incoming_queue(struct netfront_queue *queue, struct sk_buff_head *rxq) { - struct netfront_info *np = netdev_priv(dev); - struct netfront_stats *stats = this_cpu_ptr(np->stats); + struct netfront_stats *stats = this_cpu_ptr(queue->info->stats); int packets_dropped = 0; struct sk_buff *skb; @@ -906,13 +966,13 @@ static int handle_incoming_queue(struct net_device *dev, __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); /* Ethernet work: Delayed to here as it peeks the header. */ - skb->protocol = eth_type_trans(skb, dev); + skb->protocol = eth_type_trans(skb, queue->info->netdev); skb_reset_network_header(skb); - if (checksum_setup(dev, skb)) { + if (checksum_setup(queue->info->netdev, skb)) { kfree_skb(skb); packets_dropped++; - dev->stats.rx_errors++; + queue->info->netdev->stats.rx_errors++; continue; } @@ -922,7 +982,7 @@ static int handle_incoming_queue(struct net_device *dev, u64_stats_update_end(&stats->syncp); /* Pass it up. */ - napi_gro_receive(&np->napi, skb); + napi_gro_receive(&queue->napi, skb); } return packets_dropped; @@ -930,8 +990,8 @@ static int handle_incoming_queue(struct net_device *dev, static int xennet_poll(struct napi_struct *napi, int budget) { - struct netfront_info *np = container_of(napi, struct netfront_info, napi); - struct net_device *dev = np->netdev; + struct netfront_queue *queue = container_of(napi, struct netfront_queue, napi); + struct net_device *dev = queue->info->netdev; struct sk_buff *skb; struct netfront_rx_info rinfo; struct xen_netif_rx_response *rx = &rinfo.rx; @@ -944,29 +1004,29 @@ static int xennet_poll(struct napi_struct *napi, int budget) unsigned long flags; int err; - spin_lock(&np->rx_lock); + spin_lock(&queue->rx_lock); skb_queue_head_init(&rxq); skb_queue_head_init(&errq); skb_queue_head_init(&tmpq); - rp = np->rx.sring->rsp_prod; + rp = queue->rx.sring->rsp_prod; rmb(); /* Ensure we see queued responses up to 'rp'. */ - i = np->rx.rsp_cons; + i = queue->rx.rsp_cons; work_done = 0; while ((i != rp) && (work_done < budget)) { - memcpy(rx, RING_GET_RESPONSE(&np->rx, i), sizeof(*rx)); + memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx)); memset(extras, 0, sizeof(rinfo.extras)); - err = xennet_get_responses(np, &rinfo, rp, &tmpq); + err = xennet_get_responses(queue, &rinfo, rp, &tmpq); if (unlikely(err)) { err: while ((skb = __skb_dequeue(&tmpq))) __skb_queue_tail(&errq, skb); dev->stats.rx_errors++; - i = np->rx.rsp_cons; + i = queue->rx.rsp_cons; continue; } @@ -978,7 +1038,7 @@ err: if (unlikely(xennet_set_skb_gso(skb, gso))) { __skb_queue_head(&tmpq, skb); - np->rx.rsp_cons += skb_queue_len(&tmpq); + queue->rx.rsp_cons += skb_queue_len(&tmpq); goto err; } } @@ -992,7 +1052,7 @@ err: skb->data_len = rx->status; skb->len += rx->status; - i = xennet_fill_frags(np, skb, &tmpq); + i = xennet_fill_frags(queue, skb, &tmpq); if (rx->flags & XEN_NETRXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; @@ -1001,22 +1061,22 @@ err: __skb_queue_tail(&rxq, skb); - np->rx.rsp_cons = ++i; + queue->rx.rsp_cons = ++i; work_done++; } __skb_queue_purge(&errq); - work_done -= handle_incoming_queue(dev, &rxq); + work_done -= handle_incoming_queue(queue, &rxq); /* If we get a callback with very few responses, reduce fill target. */ /* NB. Note exponential increase, linear decrease. */ - if (((np->rx.req_prod_pvt - np->rx.sring->rsp_prod) > - ((3*np->rx_target) / 4)) && - (--np->rx_target < np->rx_min_target)) - np->rx_target = np->rx_min_target; + if (((queue->rx.req_prod_pvt - queue->rx.sring->rsp_prod) > + ((3*queue->rx_target) / 4)) && + (--queue->rx_target < queue->rx_min_target)) + queue->rx_target = queue->rx_min_target; - xennet_alloc_rx_buffers(dev); + xennet_alloc_rx_buffers(queue); if (work_done < budget) { int more_to_do = 0; @@ -1025,14 +1085,14 @@ err: local_irq_save(flags); - RING_FINAL_CHECK_FOR_RESPONSES(&np->rx, more_to_do); + RING_FINAL_CHECK_FOR_RESPONSES(&queue->rx, more_to_do); if (!more_to_do) __napi_complete(napi); local_irq_restore(flags); } - spin_unlock(&np->rx_lock); + spin_unlock(&queue->rx_lock); return work_done; } @@ -1080,43 +1140,43 @@ static struct rtnl_link_stats64 *xennet_get_stats64(struct net_device *dev, return tot; } -static void xennet_release_tx_bufs(struct netfront_info *np) +static void xennet_release_tx_bufs(struct netfront_queue *queue) { struct sk_buff *skb; int i; for (i = 0; i < NET_TX_RING_SIZE; i++) { /* Skip over entries which are actually freelist references */ - if (skb_entry_is_link(&np->tx_skbs[i])) + if (skb_entry_is_link(&queue->tx_skbs[i])) continue; - skb = np->tx_skbs[i].skb; - get_page(np->grant_tx_page[i]); - gnttab_end_foreign_access(np->grant_tx_ref[i], + skb = queue->tx_skbs[i].skb; + get_page(queue->grant_tx_page[i]); + gnttab_end_foreign_access(queue->grant_tx_ref[i], GNTMAP_readonly, - (unsigned long)page_address(np->grant_tx_page[i])); - np->grant_tx_page[i] = NULL; - np->grant_tx_ref[i] = GRANT_INVALID_REF; - add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i); + (unsigned long)page_address(queue->grant_tx_page[i])); + queue->grant_tx_page[i] = NULL; + queue->grant_tx_ref[i] = GRANT_INVALID_REF; + add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i); dev_kfree_skb_irq(skb); } } -static void xennet_release_rx_bufs(struct netfront_info *np) +static void xennet_release_rx_bufs(struct netfront_queue *queue) { int id, ref; - spin_lock_bh(&np->rx_lock); + spin_lock_bh(&queue->rx_lock); for (id = 0; id < NET_RX_RING_SIZE; id++) { struct sk_buff *skb; struct page *page; - skb = np->rx_skbs[id]; + skb = queue->rx_skbs[id]; if (!skb) continue; - ref = np->grant_rx_ref[id]; + ref = queue->grant_rx_ref[id]; if (ref == GRANT_INVALID_REF) continue; @@ -1128,21 +1188,28 @@ static void xennet_release_rx_bufs(struct netfront_info *np) get_page(page); gnttab_end_foreign_access(ref, 0, (unsigned long)page_address(page)); - np->grant_rx_ref[id] = GRANT_INVALID_REF; + queue->grant_rx_ref[id] = GRANT_INVALID_REF; kfree_skb(skb); } - spin_unlock_bh(&np->rx_lock); + spin_unlock_bh(&queue->rx_lock); } static void xennet_uninit(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - xennet_release_tx_bufs(np); - xennet_release_rx_bufs(np); - gnttab_free_grant_references(np->gref_tx_head); - gnttab_free_grant_references(np->gref_rx_head); + unsigned int num_queues = dev->real_num_tx_queues; + struct netfront_queue *queue; + unsigned int i; + + for (i = 0; i < num_queues; ++i) { + queue = &np->queues[i]; + xennet_release_tx_bufs(queue); + xennet_release_rx_bufs(queue); + gnttab_free_grant_references(queue->gref_tx_head); + gnttab_free_grant_references(queue->gref_rx_head); + } } static netdev_features_t xennet_fix_features(struct net_device *dev, @@ -1203,25 +1270,24 @@ static int xennet_set_features(struct net_device *dev, static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id) { - struct netfront_info *np = dev_id; - struct net_device *dev = np->netdev; + struct netfront_queue *queue = dev_id; unsigned long flags; - spin_lock_irqsave(&np->tx_lock, flags); - xennet_tx_buf_gc(dev); - spin_unlock_irqrestore(&np->tx_lock, flags); + spin_lock_irqsave(&queue->tx_lock, flags); + xennet_tx_buf_gc(queue); + spin_unlock_irqrestore(&queue->tx_lock, flags); return IRQ_HANDLED; } static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id) { - struct netfront_info *np = dev_id; - struct net_device *dev = np->netdev; + struct netfront_queue *queue = dev_id; + struct net_device *dev = queue->info->netdev; if (likely(netif_carrier_ok(dev) && - RING_HAS_UNCONSUMED_RESPONSES(&np->rx))) - napi_schedule(&np->napi); + RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))) + napi_schedule(&queue->napi); return IRQ_HANDLED; } @@ -1236,7 +1302,12 @@ static irqreturn_t xennet_interrupt(int irq, void *dev_id) #ifdef CONFIG_NET_POLL_CONTROLLER static void xennet_poll_controller(struct net_device *dev) { - xennet_interrupt(0, dev); + /* Poll each queue */ + struct netfront_info *info = netdev_priv(dev); + unsigned int num_queues = dev->real_num_tx_queues; + unsigned int i; + for (i = 0; i < num_queues; ++i) + xennet_interrupt(0, &info->queues[i]); } #endif @@ -1251,6 +1322,7 @@ static const struct net_device_ops xennet_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_fix_features = xennet_fix_features, .ndo_set_features = xennet_set_features, + .ndo_select_queue = xennet_select_queue, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = xennet_poll_controller, #endif @@ -1258,66 +1330,30 @@ static const struct net_device_ops xennet_netdev_ops = { static struct net_device *xennet_create_dev(struct xenbus_device *dev) { - int i, err; + int err; struct net_device *netdev; struct netfront_info *np; - netdev = alloc_etherdev(sizeof(struct netfront_info)); + netdev = alloc_etherdev_mq(sizeof(struct netfront_info), xennet_max_queues); if (!netdev) return ERR_PTR(-ENOMEM); np = netdev_priv(netdev); np->xbdev = dev; - spin_lock_init(&np->tx_lock); - spin_lock_init(&np->rx_lock); - - skb_queue_head_init(&np->rx_batch); - np->rx_target = RX_DFL_MIN_TARGET; - np->rx_min_target = RX_DFL_MIN_TARGET; - np->rx_max_target = RX_MAX_TARGET; - - init_timer(&np->rx_refill_timer); - np->rx_refill_timer.data = (unsigned long)netdev; - np->rx_refill_timer.function = rx_refill_timeout; + /* No need to use rtnl_lock() before the call below as it + * happens before register_netdev(). + */ + netif_set_real_num_tx_queues(netdev, 0); + np->queues = NULL; err = -ENOMEM; np->stats = netdev_alloc_pcpu_stats(struct netfront_stats); if (np->stats == NULL) goto exit; - /* Initialise tx_skbs as a free chain containing every entry. */ - np->tx_skb_freelist = 0; - for (i = 0; i < NET_TX_RING_SIZE; i++) { - skb_entry_set_link(&np->tx_skbs[i], i+1); - np->grant_tx_ref[i] = GRANT_INVALID_REF; - np->grant_tx_page[i] = NULL; - } - - /* Clear out rx_skbs */ - for (i = 0; i < NET_RX_RING_SIZE; i++) { - np->rx_skbs[i] = NULL; - np->grant_rx_ref[i] = GRANT_INVALID_REF; - } - - /* A grant for every tx ring slot */ - if (gnttab_alloc_grant_references(TX_MAX_TARGET, - &np->gref_tx_head) < 0) { - pr_alert("can't alloc tx grant refs\n"); - err = -ENOMEM; - goto exit_free_stats; - } - /* A grant for every rx ring slot */ - if (gnttab_alloc_grant_references(RX_MAX_TARGET, - &np->gref_rx_head) < 0) { - pr_alert("can't alloc rx grant refs\n"); - err = -ENOMEM; - goto exit_free_tx; - } - netdev->netdev_ops = &xennet_netdev_ops; - netif_napi_add(netdev, &np->napi, xennet_poll, 64); netdev->features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_GSO_ROBUST; netdev->hw_features = NETIF_F_SG | @@ -1343,10 +1379,6 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) return netdev; - exit_free_tx: - gnttab_free_grant_references(np->gref_tx_head); - exit_free_stats: - free_percpu(np->stats); exit: free_netdev(netdev); return ERR_PTR(err); @@ -1404,30 +1436,36 @@ static void xennet_end_access(int ref, void *page) static void xennet_disconnect_backend(struct netfront_info *info) { - /* Stop old i/f to prevent errors whilst we rebuild the state. */ - spin_lock_bh(&info->rx_lock); - spin_lock_irq(&info->tx_lock); - netif_carrier_off(info->netdev); - spin_unlock_irq(&info->tx_lock); - spin_unlock_bh(&info->rx_lock); - - if (info->tx_irq && (info->tx_irq == info->rx_irq)) - unbind_from_irqhandler(info->tx_irq, info); - if (info->tx_irq && (info->tx_irq != info->rx_irq)) { - unbind_from_irqhandler(info->tx_irq, info); - unbind_from_irqhandler(info->rx_irq, info); - } - info->tx_evtchn = info->rx_evtchn = 0; - info->tx_irq = info->rx_irq = 0; + unsigned int i = 0; + struct netfront_queue *queue = NULL; + unsigned int num_queues = info->netdev->real_num_tx_queues; + + for (i = 0; i < num_queues; ++i) { + /* Stop old i/f to prevent errors whilst we rebuild the state. */ + spin_lock_bh(&queue->rx_lock); + spin_lock_irq(&queue->tx_lock); + netif_carrier_off(queue->info->netdev); + spin_unlock_irq(&queue->tx_lock); + spin_unlock_bh(&queue->rx_lock); + + if (queue->tx_irq && (queue->tx_irq == queue->rx_irq)) + unbind_from_irqhandler(queue->tx_irq, queue); + if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) { + unbind_from_irqhandler(queue->tx_irq, queue); + unbind_from_irqhandler(queue->rx_irq, queue); + } + queue->tx_evtchn = queue->rx_evtchn = 0; + queue->tx_irq = queue->rx_irq = 0; - /* End access and free the pages */ - xennet_end_access(info->tx_ring_ref, info->tx.sring); - xennet_end_access(info->rx_ring_ref, info->rx.sring); + /* End access and free the pages */ + xennet_end_access(queue->tx_ring_ref, queue->tx.sring); + xennet_end_access(queue->rx_ring_ref, queue->rx.sring); - info->tx_ring_ref = GRANT_INVALID_REF; - info->rx_ring_ref = GRANT_INVALID_REF; - info->tx.sring = NULL; - info->rx.sring = NULL; + queue->tx_ring_ref = GRANT_INVALID_REF; + queue->rx_ring_ref = GRANT_INVALID_REF; + queue->tx.sring = NULL; + queue->rx.sring = NULL; + } } /** @@ -1468,100 +1506,86 @@ static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[]) return 0; } -static int setup_netfront_single(struct netfront_info *info) +static int setup_netfront_single(struct netfront_queue *queue) { int err; - err = xenbus_alloc_evtchn(info->xbdev, &info->tx_evtchn); + err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->tx_evtchn); if (err < 0) goto fail; - err = bind_evtchn_to_irqhandler(info->tx_evtchn, + err = bind_evtchn_to_irqhandler(queue->tx_evtchn, xennet_interrupt, - 0, info->netdev->name, info); + 0, queue->info->netdev->name, queue); if (err < 0) goto bind_fail; - info->rx_evtchn = info->tx_evtchn; - info->rx_irq = info->tx_irq = err; + queue->rx_evtchn = queue->tx_evtchn; + queue->rx_irq = queue->tx_irq = err; return 0; bind_fail: - xenbus_free_evtchn(info->xbdev, info->tx_evtchn); - info->tx_evtchn = 0; + xenbus_free_evtchn(queue->info->xbdev, queue->tx_evtchn); + queue->tx_evtchn = 0; fail: return err; } -static int setup_netfront_split(struct netfront_info *info) +static int setup_netfront_split(struct netfront_queue *queue) { int err; - err = xenbus_alloc_evtchn(info->xbdev, &info->tx_evtchn); + err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->tx_evtchn); if (err < 0) goto fail; - err = xenbus_alloc_evtchn(info->xbdev, &info->rx_evtchn); + err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->rx_evtchn); if (err < 0) goto alloc_rx_evtchn_fail; - snprintf(info->tx_irq_name, sizeof(info->tx_irq_name), - "%s-tx", info->netdev->name); - err = bind_evtchn_to_irqhandler(info->tx_evtchn, + snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), + "%s-tx", queue->name); + err = bind_evtchn_to_irqhandler(queue->tx_evtchn, xennet_tx_interrupt, - 0, info->tx_irq_name, info); + 0, queue->tx_irq_name, queue); if (err < 0) goto bind_tx_fail; - info->tx_irq = err; + queue->tx_irq = err; - snprintf(info->rx_irq_name, sizeof(info->rx_irq_name), - "%s-rx", info->netdev->name); - err = bind_evtchn_to_irqhandler(info->rx_evtchn, + snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), + "%s-rx", queue->name); + err = bind_evtchn_to_irqhandler(queue->rx_evtchn, xennet_rx_interrupt, - 0, info->rx_irq_name, info); + 0, queue->rx_irq_name, queue); if (err < 0) goto bind_rx_fail; - info->rx_irq = err; + queue->rx_irq = err; return 0; bind_rx_fail: - unbind_from_irqhandler(info->tx_irq, info); - info->tx_irq = 0; + unbind_from_irqhandler(queue->tx_irq, queue); + queue->tx_irq = 0; bind_tx_fail: - xenbus_free_evtchn(info->xbdev, info->rx_evtchn); - info->rx_evtchn = 0; + xenbus_free_evtchn(queue->info->xbdev, queue->rx_evtchn); + queue->rx_evtchn = 0; alloc_rx_evtchn_fail: - xenbus_free_evtchn(info->xbdev, info->tx_evtchn); - info->tx_evtchn = 0; + xenbus_free_evtchn(queue->info->xbdev, queue->tx_evtchn); + queue->tx_evtchn = 0; fail: return err; } -static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info) +static int setup_netfront(struct xenbus_device *dev, + struct netfront_queue *queue, unsigned int feature_split_evtchn) { struct xen_netif_tx_sring *txs; struct xen_netif_rx_sring *rxs; int err; - struct net_device *netdev = info->netdev; - unsigned int feature_split_evtchn; - info->tx_ring_ref = GRANT_INVALID_REF; - info->rx_ring_ref = GRANT_INVALID_REF; - info->rx.sring = NULL; - info->tx.sring = NULL; - netdev->irq = 0; - - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-split-event-channels", "%u", - &feature_split_evtchn); - if (err < 0) - feature_split_evtchn = 0; - - err = xen_net_read_mac(dev, netdev->dev_addr); - if (err) { - xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename); - goto fail; - } + queue->tx_ring_ref = GRANT_INVALID_REF; + queue->rx_ring_ref = GRANT_INVALID_REF; + queue->rx.sring = NULL; + queue->tx.sring = NULL; txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH); if (!txs) { @@ -1570,13 +1594,13 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info) goto fail; } SHARED_RING_INIT(txs); - FRONT_RING_INIT(&info->tx, txs, PAGE_SIZE); + FRONT_RING_INIT(&queue->tx, txs, PAGE_SIZE); err = xenbus_grant_ring(dev, virt_to_mfn(txs)); if (err < 0) goto grant_tx_ring_fail; + queue->tx_ring_ref = err; - info->tx_ring_ref = err; rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH); if (!rxs) { err = -ENOMEM; @@ -1584,21 +1608,21 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info) goto alloc_rx_ring_fail; } SHARED_RING_INIT(rxs); - FRONT_RING_INIT(&info->rx, rxs, PAGE_SIZE); + FRONT_RING_INIT(&queue->rx, rxs, PAGE_SIZE); err = xenbus_grant_ring(dev, virt_to_mfn(rxs)); if (err < 0) goto grant_rx_ring_fail; - info->rx_ring_ref = err; + queue->rx_ring_ref = err; if (feature_split_evtchn) - err = setup_netfront_split(info); + err = setup_netfront_split(queue); /* setup single event channel if * a) feature-split-event-channels == 0 * b) feature-split-event-channels == 1 but failed to setup */ if (!feature_split_evtchn || (feature_split_evtchn && err)) - err = setup_netfront_single(info); + err = setup_netfront_single(queue); if (err) goto alloc_evtchn_fail; @@ -1609,17 +1633,163 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info) * granted pages because backend is not accessing it at this point. */ alloc_evtchn_fail: - gnttab_end_foreign_access_ref(info->rx_ring_ref, 0); + gnttab_end_foreign_access_ref(queue->rx_ring_ref, 0); grant_rx_ring_fail: free_page((unsigned long)rxs); alloc_rx_ring_fail: - gnttab_end_foreign_access_ref(info->tx_ring_ref, 0); + gnttab_end_foreign_access_ref(queue->tx_ring_ref, 0); grant_tx_ring_fail: free_page((unsigned long)txs); fail: return err; } +/* Queue-specific initialisation + * This used to be done in xennet_create_dev() but must now + * be run per-queue. + */ +static int xennet_init_queue(struct netfront_queue *queue) +{ + unsigned short i; + int err = 0; + + spin_lock_init(&queue->tx_lock); + spin_lock_init(&queue->rx_lock); + + skb_queue_head_init(&queue->rx_batch); + queue->rx_target = RX_DFL_MIN_TARGET; + queue->rx_min_target = RX_DFL_MIN_TARGET; + queue->rx_max_target = RX_MAX_TARGET; + + init_timer(&queue->rx_refill_timer); + queue->rx_refill_timer.data = (unsigned long)queue; + queue->rx_refill_timer.function = rx_refill_timeout; + + snprintf(queue->name, sizeof(queue->name), "%s-q%u", + queue->info->netdev->name, queue->id); + + /* Initialise tx_skbs as a free chain containing every entry. */ + queue->tx_skb_freelist = 0; + for (i = 0; i < NET_TX_RING_SIZE; i++) { + skb_entry_set_link(&queue->tx_skbs[i], i+1); + queue->grant_tx_ref[i] = GRANT_INVALID_REF; + queue->grant_tx_page[i] = NULL; + } + + /* Clear out rx_skbs */ + for (i = 0; i < NET_RX_RING_SIZE; i++) { + queue->rx_skbs[i] = NULL; + queue->grant_rx_ref[i] = GRANT_INVALID_REF; + } + + /* A grant for every tx ring slot */ + if (gnttab_alloc_grant_references(TX_MAX_TARGET, + &queue->gref_tx_head) < 0) { + pr_alert("can't alloc tx grant refs\n"); + err = -ENOMEM; + goto exit; + } + + /* A grant for every rx ring slot */ + if (gnttab_alloc_grant_references(RX_MAX_TARGET, + &queue->gref_rx_head) < 0) { + pr_alert("can't alloc rx grant refs\n"); + err = -ENOMEM; + goto exit_free_tx; + } + + netif_napi_add(queue->info->netdev, &queue->napi, xennet_poll, 64); + + return 0; + + exit_free_tx: + gnttab_free_grant_references(queue->gref_tx_head); + exit: + return err; +} + +static int write_queue_xenstore_keys(struct netfront_queue *queue, + struct xenbus_transaction *xbt, int write_hierarchical) +{ + /* Write the queue-specific keys into XenStore in the traditional + * way for a single queue, or in a queue subkeys for multiple + * queues. + */ + struct xenbus_device *dev = queue->info->xbdev; + int err; + const char *message; + char *path; + size_t pathsize; + + /* Choose the correct place to write the keys */ + if (write_hierarchical) { + pathsize = strlen(dev->nodename) + 10; + path = kzalloc(pathsize, GFP_KERNEL); + if (!path) { + err = -ENOMEM; + message = "out of memory while writing ring references"; + goto error; + } + snprintf(path, pathsize, "%s/queue-%u", + dev->nodename, queue->id); + } else { + path = (char *)dev->nodename; + } + + /* Write ring references */ + err = xenbus_printf(*xbt, path, "tx-ring-ref", "%u", + queue->tx_ring_ref); + if (err) { + message = "writing tx-ring-ref"; + goto error; + } + + err = xenbus_printf(*xbt, path, "rx-ring-ref", "%u", + queue->rx_ring_ref); + if (err) { + message = "writing rx-ring-ref"; + goto error; + } + + /* Write event channels; taking into account both shared + * and split event channel scenarios. + */ + if (queue->tx_evtchn == queue->rx_evtchn) { + /* Shared event channel */ + err = xenbus_printf(*xbt, path, + "event-channel", "%u", queue->tx_evtchn); + if (err) { + message = "writing event-channel"; + goto error; + } + } else { + /* Split event channels */ + err = xenbus_printf(*xbt, path, + "event-channel-tx", "%u", queue->tx_evtchn); + if (err) { + message = "writing event-channel-tx"; + goto error; + } + + err = xenbus_printf(*xbt, path, + "event-channel-rx", "%u", queue->rx_evtchn); + if (err) { + message = "writing event-channel-rx"; + goto error; + } + } + + if (write_hierarchical) + kfree(path); + return 0; + +error: + if (write_hierarchical) + kfree(path); + xenbus_dev_fatal(dev, err, "%s", message); + return err; +} + /* Common code used when first setting up, and when resuming. */ static int talk_to_netback(struct xenbus_device *dev, struct netfront_info *info) @@ -1627,11 +1797,83 @@ static int talk_to_netback(struct xenbus_device *dev, const char *message; struct xenbus_transaction xbt; int err; + unsigned int feature_split_evtchn; + unsigned int i = 0; + unsigned int max_queues = 0; + struct netfront_queue *queue = NULL; + unsigned int num_queues = 1; - /* Create shared ring, alloc event channel. */ - err = setup_netfront(dev, info); - if (err) + info->netdev->irq = 0; + + /* Check if backend supports multiple queues */ + err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, + "multi-queue-max-queues", "%u", &max_queues); + if (err < 0) + max_queues = 1; + num_queues = min(max_queues, xennet_max_queues); + + /* Check feature-split-event-channels */ + err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, + "feature-split-event-channels", "%u", + &feature_split_evtchn); + if (err < 0) + feature_split_evtchn = 0; + + /* Read mac addr. */ + err = xen_net_read_mac(dev, info->netdev->dev_addr); + if (err) { + xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename); + goto out; + } + + /* Allocate array of queues */ + info->queues = kcalloc(num_queues, sizeof(struct netfront_queue), GFP_KERNEL); + if (!info->queues) { + err = -ENOMEM; goto out; + } + rtnl_lock(); + netif_set_real_num_tx_queues(info->netdev, num_queues); + rtnl_unlock(); + + /* Create shared ring, alloc event channel -- for each queue */ + for (i = 0; i < num_queues; ++i) { + queue = &info->queues[i]; + queue->id = i; + queue->info = info; + err = xennet_init_queue(queue); + if (err) { + /* xennet_init_queue() cleans up after itself on failure, + * but we still have to clean up any previously initialised + * queues. If i > 0, set num_queues to i, then goto + * destroy_ring, which calls xennet_disconnect_backend() + * to tidy up. + */ + if (i > 0) { + rtnl_lock(); + netif_set_real_num_tx_queues(info->netdev, i); + rtnl_unlock(); + goto destroy_ring; + } else { + goto out; + } + } + err = setup_netfront(dev, queue, feature_split_evtchn); + if (err) { + /* As for xennet_init_queue(), setup_netfront() will tidy + * up the current queue on error, but we need to clean up + * those already allocated. + */ + if (i > 0) { + rtnl_lock(); + netif_set_real_num_tx_queues(info->netdev, i); + rtnl_unlock(); + goto destroy_ring; + } else { + goto out; + } + } + } again: err = xenbus_transaction_start(&xbt); @@ -1640,41 +1882,29 @@ again: goto destroy_ring; } - err = xenbus_printf(xbt, dev->nodename, "tx-ring-ref", "%u", - info->tx_ring_ref); - if (err) { - message = "writing tx ring-ref"; - goto abort_transaction; - } - err = xenbus_printf(xbt, dev->nodename, "rx-ring-ref", "%u", - info->rx_ring_ref); - if (err) { - message = "writing rx ring-ref"; - goto abort_transaction; - } - - if (info->tx_evtchn == info->rx_evtchn) { - err = xenbus_printf(xbt, dev->nodename, - "event-channel", "%u", info->tx_evtchn); - if (err) { - message = "writing event-channel"; - goto abort_transaction; - } + if (num_queues == 1) { + err = write_queue_xenstore_keys(&info->queues[0], &xbt, 0); /* flat */ + if (err) + goto abort_transaction_no_dev_fatal; } else { - err = xenbus_printf(xbt, dev->nodename, - "event-channel-tx", "%u", info->tx_evtchn); + /* Write the number of queues */ + err = xenbus_printf(xbt, dev->nodename, "multi-queue-num-queues", + "%u", num_queues); if (err) { - message = "writing event-channel-tx"; - goto abort_transaction; + message = "writing multi-queue-num-queues"; + goto abort_transaction_no_dev_fatal; } - err = xenbus_printf(xbt, dev->nodename, - "event-channel-rx", "%u", info->rx_evtchn); - if (err) { - message = "writing event-channel-rx"; - goto abort_transaction; + + /* Write the keys for each queue */ + for (i = 0; i < num_queues; ++i) { + queue = &info->queues[i]; + err = write_queue_xenstore_keys(queue, &xbt, 1); /* hierarchical */ + if (err) + goto abort_transaction_no_dev_fatal; } } + /* The remaining keys are not queue-specific */ err = xenbus_printf(xbt, dev->nodename, "request-rx-copy", "%u", 1); if (err) { @@ -1724,10 +1954,16 @@ again: return 0; abort_transaction: - xenbus_transaction_end(xbt, 1); xenbus_dev_fatal(dev, err, "%s", message); +abort_transaction_no_dev_fatal: + xenbus_transaction_end(xbt, 1); destroy_ring: xennet_disconnect_backend(info); + kfree(info->queues); + info->queues = NULL; + rtnl_lock(); + netif_set_real_num_tx_queues(info->netdev, 0); + rtnl_lock(); out: return err; } @@ -1735,11 +1971,14 @@ again: static int xennet_connect(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); + unsigned int num_queues = 0; int i, requeue_idx, err; struct sk_buff *skb; grant_ref_t ref; struct xen_netif_rx_request *req; unsigned int feature_rx_copy; + unsigned int j = 0; + struct netfront_queue *queue = NULL; err = xenbus_scanf(XBT_NIL, np->xbdev->otherend, "feature-rx-copy", "%u", &feature_rx_copy); @@ -1756,40 +1995,47 @@ static int xennet_connect(struct net_device *dev) if (err) return err; + /* talk_to_netback() sets the correct number of queues */ + num_queues = dev->real_num_tx_queues; + rtnl_lock(); netdev_update_features(dev); rtnl_unlock(); - spin_lock_bh(&np->rx_lock); - spin_lock_irq(&np->tx_lock); + /* By now, the queue structures have been set up */ + for (j = 0; j < num_queues; ++j) { + queue = &np->queues[j]; + spin_lock_bh(&queue->rx_lock); + spin_lock_irq(&queue->tx_lock); - /* Step 1: Discard all pending TX packet fragments. */ - xennet_release_tx_bufs(np); + /* Step 1: Discard all pending TX packet fragments. */ + xennet_release_tx_bufs(queue); - /* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */ - for (requeue_idx = 0, i = 0; i < NET_RX_RING_SIZE; i++) { - skb_frag_t *frag; - const struct page *page; - if (!np->rx_skbs[i]) - continue; + /* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */ + for (requeue_idx = 0, i = 0; i < NET_RX_RING_SIZE; i++) { + skb_frag_t *frag; + const struct page *page; + if (!queue->rx_skbs[i]) + continue; - skb = np->rx_skbs[requeue_idx] = xennet_get_rx_skb(np, i); - ref = np->grant_rx_ref[requeue_idx] = xennet_get_rx_ref(np, i); - req = RING_GET_REQUEST(&np->rx, requeue_idx); + skb = queue->rx_skbs[requeue_idx] = xennet_get_rx_skb(queue, i); + ref = queue->grant_rx_ref[requeue_idx] = xennet_get_rx_ref(queue, i); + req = RING_GET_REQUEST(&queue->rx, requeue_idx); - frag = &skb_shinfo(skb)->frags[0]; - page = skb_frag_page(frag); - gnttab_grant_foreign_access_ref( - ref, np->xbdev->otherend_id, - pfn_to_mfn(page_to_pfn(page)), - 0); - req->gref = ref; - req->id = requeue_idx; + frag = &skb_shinfo(skb)->frags[0]; + page = skb_frag_page(frag); + gnttab_grant_foreign_access_ref( + ref, queue->info->xbdev->otherend_id, + pfn_to_mfn(page_to_pfn(page)), + 0); + req->gref = ref; + req->id = requeue_idx; - requeue_idx++; - } + requeue_idx++; + } - np->rx.req_prod_pvt = requeue_idx; + queue->rx.req_prod_pvt = requeue_idx; + } /* * Step 3: All public and private state should now be sane. Get @@ -1798,14 +2044,17 @@ static int xennet_connect(struct net_device *dev) * packets. */ netif_carrier_on(np->netdev); - notify_remote_via_irq(np->tx_irq); - if (np->tx_irq != np->rx_irq) - notify_remote_via_irq(np->rx_irq); - xennet_tx_buf_gc(dev); - xennet_alloc_rx_buffers(dev); - - spin_unlock_irq(&np->tx_lock); - spin_unlock_bh(&np->rx_lock); + for (j = 0; j < num_queues; ++j) { + queue = &np->queues[j]; + notify_remote_via_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + notify_remote_via_irq(queue->rx_irq); + xennet_tx_buf_gc(queue); + xennet_alloc_rx_buffers(queue); + + spin_unlock_irq(&queue->tx_lock); + spin_unlock_bh(&queue->rx_lock); + } return 0; } @@ -1878,7 +2127,7 @@ static void xennet_get_ethtool_stats(struct net_device *dev, int i; for (i = 0; i < ARRAY_SIZE(xennet_stats); i++) - data[i] = *(unsigned long *)(np + xennet_stats[i].offset); + data[i] = atomic_read((atomic_t *)(np + xennet_stats[i].offset)); } static void xennet_get_strings(struct net_device *dev, u32 stringset, u8 * data) @@ -1909,8 +2158,12 @@ static ssize_t show_rxbuf_min(struct device *dev, { struct net_device *netdev = to_net_dev(dev); struct netfront_info *info = netdev_priv(netdev); + unsigned int num_queues = netdev->real_num_tx_queues; - return sprintf(buf, "%u\n", info->rx_min_target); + if (num_queues) + return sprintf(buf, "%u\n", info->queues[0].rx_min_target); + else + return sprintf(buf, "%u\n", RX_MIN_TARGET); } static ssize_t store_rxbuf_min(struct device *dev, @@ -1919,8 +2172,11 @@ static ssize_t store_rxbuf_min(struct device *dev, { struct net_device *netdev = to_net_dev(dev); struct netfront_info *np = netdev_priv(netdev); + unsigned int num_queues = netdev->real_num_tx_queues; char *endp; unsigned long target; + unsigned int i; + struct netfront_queue *queue; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1934,16 +2190,19 @@ static ssize_t store_rxbuf_min(struct device *dev, if (target > RX_MAX_TARGET) target = RX_MAX_TARGET; - spin_lock_bh(&np->rx_lock); - if (target > np->rx_max_target) - np->rx_max_target = target; - np->rx_min_target = target; - if (target > np->rx_target) - np->rx_target = target; + for (i = 0; i < num_queues; ++i) { + queue = &np->queues[i]; + spin_lock_bh(&queue->rx_lock); + if (target > queue->rx_max_target) + queue->rx_max_target = target; + queue->rx_min_target = target; + if (target > queue->rx_target) + queue->rx_target = target; - xennet_alloc_rx_buffers(netdev); + xennet_alloc_rx_buffers(queue); - spin_unlock_bh(&np->rx_lock); + spin_unlock_bh(&queue->rx_lock); + } return len; } @@ -1952,8 +2211,12 @@ static ssize_t show_rxbuf_max(struct device *dev, { struct net_device *netdev = to_net_dev(dev); struct netfront_info *info = netdev_priv(netdev); + unsigned int num_queues = netdev->real_num_tx_queues; - return sprintf(buf, "%u\n", info->rx_max_target); + if (num_queues) + return sprintf(buf, "%u\n", info->queues[0].rx_max_target); + else + return sprintf(buf, "%u\n", RX_MAX_TARGET); } static ssize_t store_rxbuf_max(struct device *dev, @@ -1962,8 +2225,11 @@ static ssize_t store_rxbuf_max(struct device *dev, { struct net_device *netdev = to_net_dev(dev); struct netfront_info *np = netdev_priv(netdev); + unsigned int num_queues = netdev->real_num_tx_queues; char *endp; unsigned long target; + unsigned int i = 0; + struct netfront_queue *queue = NULL; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1977,16 +2243,19 @@ static ssize_t store_rxbuf_max(struct device *dev, if (target > RX_MAX_TARGET) target = RX_MAX_TARGET; - spin_lock_bh(&np->rx_lock); - if (target < np->rx_min_target) - np->rx_min_target = target; - np->rx_max_target = target; - if (target < np->rx_target) - np->rx_target = target; + for (i = 0; i < num_queues; ++i) { + queue = &np->queues[i]; + spin_lock_bh(&queue->rx_lock); + if (target < queue->rx_min_target) + queue->rx_min_target = target; + queue->rx_max_target = target; + if (target < queue->rx_target) + queue->rx_target = target; - xennet_alloc_rx_buffers(netdev); + xennet_alloc_rx_buffers(queue); - spin_unlock_bh(&np->rx_lock); + spin_unlock_bh(&queue->rx_lock); + } return len; } @@ -1995,8 +2264,12 @@ static ssize_t show_rxbuf_cur(struct device *dev, { struct net_device *netdev = to_net_dev(dev); struct netfront_info *info = netdev_priv(netdev); + unsigned int num_queues = netdev->real_num_tx_queues; - return sprintf(buf, "%u\n", info->rx_target); + if (num_queues) + return sprintf(buf, "%u\n", info->queues[0].rx_target); + else + return sprintf(buf, "0\n"); } static struct device_attribute xennet_attrs[] = { @@ -2043,6 +2316,9 @@ static const struct xenbus_device_id netfront_ids[] = { static int xennet_remove(struct xenbus_device *dev) { struct netfront_info *info = dev_get_drvdata(&dev->dev); + unsigned int num_queues = info->netdev->real_num_tx_queues; + struct netfront_queue *queue = NULL; + unsigned int i = 0; dev_dbg(&dev->dev, "%s\n", dev->nodename); @@ -2052,7 +2328,15 @@ static int xennet_remove(struct xenbus_device *dev) unregister_netdev(info->netdev); - del_timer_sync(&info->rx_refill_timer); + for (i = 0; i < num_queues; ++i) { + queue = &info->queues[i]; + del_timer_sync(&queue->rx_refill_timer); + } + + if (num_queues) { + kfree(info->queues); + info->queues = NULL; + } free_percpu(info->stats); @@ -2078,6 +2362,9 @@ static int __init netif_init(void) pr_info("Initialising Xen virtual ethernet driver\n"); + /* Allow as many queues as there are CPUs, by default */ + xennet_max_queues = num_online_cpus(); + return xenbus_register_frontend(&netfront_driver); } module_init(netif_init); diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index c50061db6098..70054cc0708d 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -51,6 +51,59 @@ */ /* + * Multiple transmit and receive queues: + * If supported, the backend will write the key "multi-queue-max-queues" to + * the directory for that vif, and set its value to the maximum supported + * number of queues. + * Frontends that are aware of this feature and wish to use it can write the + * key "multi-queue-num-queues", set to the number they wish to use, which + * must be greater than zero, and no more than the value reported by the backend + * in "multi-queue-max-queues". + * + * Queues replicate the shared rings and event channels. + * "feature-split-event-channels" may optionally be used when using + * multiple queues, but is not mandatory. + * + * Each queue consists of one shared ring pair, i.e. there must be the same + * number of tx and rx rings. + * + * For frontends requesting just one queue, the usual event-channel and + * ring-ref keys are written as before, simplifying the backend processing + * to avoid distinguishing between a frontend that doesn't understand the + * multi-queue feature, and one that does, but requested only one queue. + * + * Frontends requesting two or more queues must not write the toplevel + * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys, + * instead writing those keys under sub-keys having the name "queue-N" where + * N is the integer ID of the queue for which those keys belong. Queues + * are indexed from zero. For example, a frontend with two queues and split + * event channels must write the following set of queue-related keys: + * + * /local/domain/1/device/vif/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vif/0/queue-0 = "" + * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>" + * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>" + * /local/domain/1/device/vif/0/queue-1 = "" + * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>" + * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1" + * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>" + * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>" + * + * If there is any inconsistency in the XenStore data, the backend may + * choose not to connect any queues, instead treating the request as an + * error. This includes scenarios where more (or fewer) queues were + * requested than the frontend provided details for. + * + * Mapping of packets to queues is considered to be a function of the + * transmitting system (backend or frontend) and is not negotiated + * between the two. Guests are free to transmit packets on any queue + * they choose, provided it has been set up correctly. Guests must be + * prepared to receive packets on any queue they have requested be set up. + */ + +/* * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum * offload off or on. If it is missing then the feature is assumed to be on. * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum |