1 files changed, 330 insertions, 30 deletions

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 7a206cffb062..580517d857bf 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;
@@ -34,13 +36,183 @@ 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,
 			      enum xenbus_state state);
 
+#ifdef CONFIG_DEBUG_FS
+struct dentry *xen_netback_dbg_root = NULL;
+
+static int xenvif_read_io_ring(struct seq_file *m, void *v)
+{
+	struct xenvif_queue *queue = m->private;
+	struct xen_netif_tx_back_ring *tx_ring = &queue->tx;
+	struct xen_netif_rx_back_ring *rx_ring = &queue->rx;
+
+	if (tx_ring->sring) {
+		struct xen_netif_tx_sring *sring = tx_ring->sring;
+
+		seq_printf(m, "Queue %d\nTX: nr_ents %u\n", queue->id,
+			   tx_ring->nr_ents);
+		seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n",
+			   sring->req_prod,
+			   sring->req_prod - sring->rsp_prod,
+			   tx_ring->req_cons,
+			   tx_ring->req_cons - sring->rsp_prod,
+			   sring->req_event,
+			   sring->req_event - sring->rsp_prod);
+		seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n",
+			   sring->rsp_prod,
+			   tx_ring->rsp_prod_pvt,
+			   tx_ring->rsp_prod_pvt - sring->rsp_prod,
+			   sring->rsp_event,
+			   sring->rsp_event - sring->rsp_prod);
+		seq_printf(m, "pending prod %u pending cons %u nr_pending_reqs %u\n",
+			   queue->pending_prod,
+			   queue->pending_cons,
+			   nr_pending_reqs(queue));
+		seq_printf(m, "dealloc prod %u dealloc cons %u dealloc_queue %u\n\n",
+			   queue->dealloc_prod,
+			   queue->dealloc_cons,
+			   queue->dealloc_prod - queue->dealloc_cons);
+	}
+
+	if (rx_ring->sring) {
+		struct xen_netif_rx_sring *sring = rx_ring->sring;
+
+		seq_printf(m, "RX: nr_ents %u\n", rx_ring->nr_ents);
+		seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n",
+			   sring->req_prod,
+			   sring->req_prod - sring->rsp_prod,
+			   rx_ring->req_cons,
+			   rx_ring->req_cons - sring->rsp_prod,
+			   sring->req_event,
+			   sring->req_event - sring->rsp_prod);
+		seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n\n",
+			   sring->rsp_prod,
+			   rx_ring->rsp_prod_pvt,
+			   rx_ring->rsp_prod_pvt - sring->rsp_prod,
+			   sring->rsp_event,
+			   sring->rsp_event - sring->rsp_prod);
+	}
+
+	seq_printf(m, "NAPI state: %lx NAPI weight: %d TX queue len %u\n"
+		   "Credit timer_pending: %d, credit: %lu, usec: %lu\n"
+		   "remaining: %lu, expires: %lu, now: %lu\n",
+		   queue->napi.state, queue->napi.weight,
+		   skb_queue_len(&queue->tx_queue),
+		   timer_pending(&queue->credit_timeout),
+		   queue->credit_bytes,
+		   queue->credit_usec,
+		   queue->remaining_credit,
+		   queue->credit_timeout.expires,
+		   jiffies);
+
+	return 0;
+}
+
+#define XENVIF_KICK_STR "kick"
+
+static ssize_t
+xenvif_write_io_ring(struct file *filp, const char __user *buf, size_t count,
+		     loff_t *ppos)
+{
+	struct xenvif_queue *queue =
+		((struct seq_file *)filp->private_data)->private;
+	int len;
+	char write[sizeof(XENVIF_KICK_STR)];
+
+	/* don't allow partial writes and check the length */
+	if (*ppos != 0)
+		return 0;
+	if (count < sizeof(XENVIF_KICK_STR) - 1)
+		return -ENOSPC;
+
+	len = simple_write_to_buffer(write,
+				     sizeof(write),
+				     ppos,
+				     buf,
+				     count);
+	if (len < 0)
+		return len;
+
+	if (!strncmp(write, XENVIF_KICK_STR, sizeof(XENVIF_KICK_STR) - 1))
+		xenvif_interrupt(0, (void *)queue);
+	else {
+		pr_warn("Unknown command to io_ring_q%d. Available: kick\n",
+			queue->id);
+		count = -EINVAL;
+	}
+	return count;
+}
+
+static int xenvif_dump_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+	void *queue = NULL;
+
+	if (inode->i_private)
+		queue = inode->i_private;
+	ret = single_open(filp, xenvif_read_io_ring, queue);
+	filp->f_mode |= FMODE_PWRITE;
+	return ret;
+}
+
+static const struct file_operations xenvif_dbg_io_ring_ops_fops = {
+	.owner = THIS_MODULE,
+	.open = xenvif_dump_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+	.write = xenvif_write_io_ring,
+};
+
+static void xenvif_debugfs_addif(struct xenvif_queue *queue)
+{
+	struct dentry *pfile;
+	struct xenvif *vif = queue->vif;
+	int i;
+
+	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
+		return;
+
+	vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name,
+						  xen_netback_dbg_root);
+	if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) {
+		for (i = 0; i < vif->num_queues; ++i) {
+			char filename[sizeof("io_ring_q") + 4];
+
+			snprintf(filename, sizeof(filename), "io_ring_q%d", i);
+			pfile = debugfs_create_file(filename,
+						    S_IRUSR | S_IWUSR,
+						    vif->xenvif_dbg_root,
+						    &vif->queues[i],
+						    &xenvif_dbg_io_ring_ops_fops);
+			if (IS_ERR_OR_NULL(pfile))
+				pr_warn("Creation of io_ring file returned %ld!\n",
+					PTR_ERR(pfile));
+		}
+	} else
+		netdev_warn(vif->dev,
+			    "Creation of vif debugfs dir returned %ld!\n",
+			    PTR_ERR(vif->xenvif_dbg_root));
+}
+
+static void xenvif_debugfs_delif(struct xenvif *vif)
+{
+	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
+		return;
+
+	if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root))
+		debugfs_remove_recursive(vif->xenvif_dbg_root);
+	vif->xenvif_dbg_root = NULL;
+}
+#endif /* CONFIG_DEBUG_FS */
+
 static int netback_remove(struct xenbus_device *dev)
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -157,6 +329,12 @@ 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;
@@ -237,8 +415,12 @@ static void backend_create_xenvif(struct backend_info *be)
 
 static void backend_disconnect(struct backend_info *be)
 {
-	if (be->vif)
+	if (be->vif) {
+#ifdef CONFIG_DEBUG_FS
+		xenvif_debugfs_delif(be->vif);
+#endif /* CONFIG_DEBUG_FS */
 		xenvif_disconnect(be->vif);
+	}
 }
 
 static void backend_connect(struct backend_info *be)
@@ -485,10 +667,26 @@ 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 +694,59 @@ 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));
+	be->vif->num_queues = requested_num_queues;
+
+	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.
+			 */
+			be->vif->num_queues = queue_index;
+			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);
+			be->vif->num_queues = queue_index;
+			goto err;
+		}
+#ifdef CONFIG_DEBUG_FS
+		xenvif_debugfs_addif(queue);
+#endif /* CONFIG_DEBUG_FS */
+	}
+
+	/* Initialisation completed, tell core driver the number of
+	 * active queues.
+	 */
+	rtnl_lock();
+	netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues);
+	netif_set_real_num_rx_queues(be->vif->dev, requested_num_queues);
+	rtnl_unlock();
+
+	xenvif_carrier_on(be->vif);
 
 	unregister_hotplug_status_watch(be);
 	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
@@ -507,45 +755,107 @@ 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->num_queues > 0)
+		xenvif_disconnect(be->vif); /* Clean up existing queues */
+	vfree(be->vif->queues);
+	be->vif->queues = NULL;
+	be->vif->num_queues = 0;
+	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->num_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 +931,6 @@ 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;
 }