6 files changed, 149 insertions, 17 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 05847eb91a1b..8ee24e351bdc 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -140,6 +140,20 @@ struct xenvif_queue { /* Per-queue data for xenvif */
 	char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
 	struct xenvif *vif; /* Parent VIF */
 
+	/*
+	 * TX/RX common EOI handling.
+	 * When feature-split-event-channels = 0, interrupt handler sets
+	 * NETBK_COMMON_EOI, otherwise NETBK_RX_EOI and NETBK_TX_EOI are set
+	 * by the RX and TX interrupt handlers.
+	 * RX and TX handler threads will issue an EOI when either
+	 * NETBK_COMMON_EOI or their specific bits (NETBK_RX_EOI or
+	 * NETBK_TX_EOI) are set and they will reset those bits.
+	 */
+	atomic_t eoi_pending;
+#define NETBK_RX_EOI		0x01
+#define NETBK_TX_EOI		0x02
+#define NETBK_COMMON_EOI	0x04
+
 	/* Use NAPI for guest TX */
 	struct napi_struct napi;
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
@@ -281,6 +295,9 @@ struct xenvif {
 	u8 ipv6_csum:1;
 	u8 multicast_control:1;
 
+	/* headroom requested by xen-netfront */
+	u16 xdp_headroom;
+
 	/* Is this interface disabled? True when backend discovers
 	 * frontend is rogue.
 	 */
@@ -375,6 +392,7 @@ int xenvif_dealloc_kthread(void *data);
 
 irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data);
 
+bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread);
 void xenvif_rx_action(struct xenvif_queue *queue);
 void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb);
 
@@ -395,6 +413,7 @@ static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
 irqreturn_t xenvif_interrupt(int irq, void *dev_id);
 
 extern bool separate_tx_rx_irq;
+extern bool provides_xdp_headroom;
 
 extern unsigned int rx_drain_timeout_msecs;
 extern unsigned int rx_stall_timeout_msecs;
diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index 6b7532f7c936..ff96f22648ef 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -393,7 +393,7 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m)
 
 	case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE:
 		seq_puts(m, "Hash Algorithm: NONE\n");
-		/* FALLTHRU */
+		fallthrough;
 	default:
 		return;
 	}
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 0c8a02a1ead7..acb786d8b1d8 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -77,12 +77,28 @@ int xenvif_schedulable(struct xenvif *vif)
 		!vif->disabled;
 }
 
+static bool xenvif_handle_tx_interrupt(struct xenvif_queue *queue)
+{
+	bool rc;
+
+	rc = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx);
+	if (rc)
+		napi_schedule(&queue->napi);
+	return rc;
+}
+
 static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
 {
 	struct xenvif_queue *queue = dev_id;
+	int old;
 
-	if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))
-		napi_schedule(&queue->napi);
+	old = atomic_fetch_or(NETBK_TX_EOI, &queue->eoi_pending);
+	WARN(old & NETBK_TX_EOI, "Interrupt while EOI pending\n");
+
+	if (!xenvif_handle_tx_interrupt(queue)) {
+		atomic_andnot(NETBK_TX_EOI, &queue->eoi_pending);
+		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
+	}
 
 	return IRQ_HANDLED;
 }
@@ -116,19 +132,46 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
+static bool xenvif_handle_rx_interrupt(struct xenvif_queue *queue)
+{
+	bool rc;
+
+	rc = xenvif_have_rx_work(queue, false);
+	if (rc)
+		xenvif_kick_thread(queue);
+	return rc;
+}
+
 static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
 {
 	struct xenvif_queue *queue = dev_id;
+	int old;
 
-	xenvif_kick_thread(queue);
+	old = atomic_fetch_or(NETBK_RX_EOI, &queue->eoi_pending);
+	WARN(old & NETBK_RX_EOI, "Interrupt while EOI pending\n");
+
+	if (!xenvif_handle_rx_interrupt(queue)) {
+		atomic_andnot(NETBK_RX_EOI, &queue->eoi_pending);
+		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
+	}
 
 	return IRQ_HANDLED;
 }
 
 irqreturn_t xenvif_interrupt(int irq, void *dev_id)
 {
-	xenvif_tx_interrupt(irq, dev_id);
-	xenvif_rx_interrupt(irq, dev_id);
+	struct xenvif_queue *queue = dev_id;
+	int old;
+
+	old = atomic_fetch_or(NETBK_COMMON_EOI, &queue->eoi_pending);
+	WARN(old, "Interrupt while EOI pending\n");
+
+	/* Use bitwise or as we need to call both functions. */
+	if ((!xenvif_handle_tx_interrupt(queue) |
+	     !xenvif_handle_rx_interrupt(queue))) {
+		atomic_andnot(NETBK_COMMON_EOI, &queue->eoi_pending);
+		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
+	}
 
 	return IRQ_HANDLED;
 }
@@ -483,6 +526,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->queues = NULL;
 	vif->num_queues = 0;
 
+	vif->xdp_headroom = 0;
+
 	spin_lock_init(&vif->lock);
 	INIT_LIST_HEAD(&vif->fe_mcast_addr);
 
@@ -603,7 +648,7 @@ int xenvif_connect_ctrl(struct xenvif *vif, grant_ref_t ring_ref,
 	if (req_prod - rsp_prod > RING_SIZE(&vif->ctrl))
 		goto err_unmap;
 
-	err = bind_interdomain_evtchn_to_irq(vif->domid, evtchn);
+	err = bind_interdomain_evtchn_to_irq_lateeoi(vif->domid, evtchn);
 	if (err < 0)
 		goto err_unmap;
 
@@ -707,7 +752,7 @@ int xenvif_connect_data(struct xenvif_queue *queue,
 
 	if (tx_evtchn == rx_evtchn) {
 		/* feature-split-event-channels == 0 */
-		err = bind_interdomain_evtchn_to_irqhandler(
+		err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
 			queue->vif->domid, tx_evtchn, xenvif_interrupt, 0,
 			queue->name, queue);
 		if (err < 0)
@@ -718,7 +763,7 @@ int xenvif_connect_data(struct xenvif_queue *queue,
 		/* feature-split-event-channels == 1 */
 		snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
 			 "%s-tx", queue->name);
-		err = bind_interdomain_evtchn_to_irqhandler(
+		err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
 			queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
 			queue->tx_irq_name, queue);
 		if (err < 0)
@@ -728,7 +773,7 @@ int xenvif_connect_data(struct xenvif_queue *queue,
 
 		snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
 			 "%s-rx", queue->name);
-		err = bind_interdomain_evtchn_to_irqhandler(
+		err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
 			queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
 			queue->rx_irq_name, queue);
 		if (err < 0)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 315dfc6ea297..bc3421d14576 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -96,6 +96,13 @@ unsigned int xenvif_hash_cache_size = XENVIF_HASH_CACHE_SIZE_DEFAULT;
 module_param_named(hash_cache_size, xenvif_hash_cache_size, uint, 0644);
 MODULE_PARM_DESC(hash_cache_size, "Number of flows in the hash cache");
 
+/* The module parameter tells that we have to put data
+ * for xen-netfront with the XDP_PACKET_HEADROOM offset
+ * needed for XDP processing
+ */
+bool provides_xdp_headroom = true;
+module_param(provides_xdp_headroom, bool, 0644);
+
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 			       u8 status);
 
@@ -162,6 +169,10 @@ void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue)
 
 	if (more_to_do)
 		napi_schedule(&queue->napi);
+	else if (atomic_fetch_andnot(NETBK_TX_EOI | NETBK_COMMON_EOI,
+				     &queue->eoi_pending) &
+		 (NETBK_TX_EOI | NETBK_COMMON_EOI))
+		xen_irq_lateeoi(queue->tx_irq, 0);
 }
 
 static void tx_add_credit(struct xenvif_queue *queue)
@@ -1636,9 +1647,14 @@ static bool xenvif_ctrl_work_todo(struct xenvif *vif)
 irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data)
 {
 	struct xenvif *vif = data;
+	unsigned int eoi_flag = XEN_EOI_FLAG_SPURIOUS;
 
-	while (xenvif_ctrl_work_todo(vif))
+	while (xenvif_ctrl_work_todo(vif)) {
 		xenvif_ctrl_action(vif);
+		eoi_flag = 0;
+	}
+
+	xen_irq_lateeoi(irq, eoi_flag);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
index ef5887037b22..b8febe1d1bfd 100644
--- a/drivers/net/xen-netback/rx.c
+++ b/drivers/net/xen-netback/rx.c
@@ -258,6 +258,19 @@ static void xenvif_rx_next_skb(struct xenvif_queue *queue,
 		pkt->extra_count++;
 	}
 
+	if (queue->vif->xdp_headroom) {
+		struct xen_netif_extra_info *extra;
+
+		extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_XDP - 1];
+
+		memset(extra, 0, sizeof(struct xen_netif_extra_info));
+		extra->u.xdp.headroom = queue->vif->xdp_headroom;
+		extra->type = XEN_NETIF_EXTRA_TYPE_XDP;
+		extra->flags = 0;
+
+		pkt->extra_count++;
+	}
+
 	if (skb->sw_hash) {
 		struct xen_netif_extra_info *extra;
 
@@ -356,7 +369,7 @@ static void xenvif_rx_data_slot(struct xenvif_queue *queue,
 				struct xen_netif_rx_request *req,
 				struct xen_netif_rx_response *rsp)
 {
-	unsigned int offset = 0;
+	unsigned int offset = queue->vif->xdp_headroom;
 	unsigned int flags;
 
 	do {
@@ -490,13 +503,13 @@ static bool xenvif_rx_queue_ready(struct xenvif_queue *queue)
 	return queue->stalled && prod - cons >= 1;
 }
 
-static bool xenvif_have_rx_work(struct xenvif_queue *queue)
+bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread)
 {
 	return xenvif_rx_ring_slots_available(queue) ||
 		(queue->vif->stall_timeout &&
 		 (xenvif_rx_queue_stalled(queue) ||
 		  xenvif_rx_queue_ready(queue))) ||
-		kthread_should_stop() ||
+		(test_kthread && kthread_should_stop()) ||
 		queue->vif->disabled;
 }
 
@@ -527,15 +540,20 @@ static void xenvif_wait_for_rx_work(struct xenvif_queue *queue)
 {
 	DEFINE_WAIT(wait);
 
-	if (xenvif_have_rx_work(queue))
+	if (xenvif_have_rx_work(queue, true))
 		return;
 
 	for (;;) {
 		long ret;
 
 		prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE);
-		if (xenvif_have_rx_work(queue))
+		if (xenvif_have_rx_work(queue, true))
 			break;
+		if (atomic_fetch_andnot(NETBK_RX_EOI | NETBK_COMMON_EOI,
+					&queue->eoi_pending) &
+		    (NETBK_RX_EOI | NETBK_COMMON_EOI))
+			xen_irq_lateeoi(queue->rx_irq, 0);
+
 		ret = schedule_timeout(xenvif_rx_queue_timeout(queue));
 		if (!ret)
 			break;
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 286054b60d47..f1c1624cec8f 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -393,6 +393,24 @@ static void set_backend_state(struct backend_info *be,
 	}
 }
 
+static void read_xenbus_frontend_xdp(struct backend_info *be,
+				      struct xenbus_device *dev)
+{
+	struct xenvif *vif = be->vif;
+	u16 headroom;
+	int err;
+
+	err = xenbus_scanf(XBT_NIL, dev->otherend,
+			   "xdp-headroom", "%hu", &headroom);
+	if (err != 1) {
+		vif->xdp_headroom = 0;
+		return;
+	}
+	if (headroom > XEN_NETIF_MAX_XDP_HEADROOM)
+		headroom = XEN_NETIF_MAX_XDP_HEADROOM;
+	vif->xdp_headroom = headroom;
+}
+
 /**
  * Callback received when the frontend's state changes.
  */
@@ -417,6 +435,11 @@ static void frontend_changed(struct xenbus_device *dev,
 		set_backend_state(be, XenbusStateConnected);
 		break;
 
+	case XenbusStateReconfiguring:
+		read_xenbus_frontend_xdp(be, dev);
+		xenbus_switch_state(dev, XenbusStateReconfigured);
+		break;
+
 	case XenbusStateClosing:
 		set_backend_state(be, XenbusStateClosing);
 		break;
@@ -425,7 +448,7 @@ static void frontend_changed(struct xenbus_device *dev,
 		set_backend_state(be, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
-		/* fall through - if not online */
+		fallthrough;	/* if not online */
 	case XenbusStateUnknown:
 		set_backend_state(be, XenbusStateClosed);
 		device_unregister(&dev->dev);
@@ -947,6 +970,8 @@ static int read_xenbus_vif_flags(struct backend_info *be)
 	vif->ipv6_csum = !!xenbus_read_unsigned(dev->otherend,
 						"feature-ipv6-csum-offload", 0);
 
+	read_xenbus_frontend_xdp(be, dev);
+
 	return 0;
 }
 
@@ -1036,6 +1061,15 @@ static int netback_probe(struct xenbus_device *dev,
 			goto abort_transaction;
 		}
 
+		/* we can adjust a headroom for netfront XDP processing */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-xdp-headroom", "%d",
+				    provides_xdp_headroom);
+		if (err) {
+			message = "writing feature-xdp-headroom";
+			goto abort_transaction;
+		}
+
 		/* We don't support rx-flip path (except old guests who
 		 * don't grok this feature flag).
 		 */