Merge branch 'virtio-next' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux

Pull virtio changes from Rusty Russell:
 "New workflow: same git trees pulled by linux-next get sent straight to
  Linus.  Git is awkward at shuffling patches compared with quilt or mq,
  but that doesn't happen often once things get into my -next branch."

* 'virtio-next' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (24 commits)
  lguest: fix occasional crash in example launcher.
  virtio-blk: Disable callback in virtblk_done()
  virtio_mmio: Don't attempt to create empty virtqueues
  virtio_mmio: fix off by one error allocating queue
  drivers/virtio/virtio_pci.c: fix error return code
  virtio: don't crash when device is buggy
  virtio: remove CONFIG_VIRTIO_RING
  virtio: add help to CONFIG_VIRTIO option.
  virtio: support reserved vqs
  virtio: introduce an API to set affinity for a virtqueue
  virtio-ring: move queue_index to vring_virtqueue
  virtio_balloon: not EXPERIMENTAL any more.
  virtio-balloon: dependency fix
  virtio-blk: fix NULL checking in virtblk_alloc_req()
  virtio-blk: Add REQ_FLUSH and REQ_FUA support to bio path
  virtio-blk: Add bio-based IO path for virtio-blk
  virtio: console: fix error handling in init() function
  tools: Fix pthread flag for Makefile of trace-agent used by virtio-trace
  tools: Add guest trace agent as a user tool
  virtio/console: Allocate scatterlist according to the current pipe size
  ...

6 files changed, 98 insertions, 35 deletions

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index f38b17a86c35..8d5bddb56cb1 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -1,11 +1,9 @@
-# Virtio always gets selected by whoever wants it.
 config VIRTIO
 	tristate
-
-# Similarly the virtio ring implementation.
-config VIRTIO_RING
-	tristate
-	depends on VIRTIO
+	---help---
+	  This option is selected by any driver which implements the virtio
+	  bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_LGUEST,
+	  CONFIG_RPMSG or CONFIG_S390_GUEST.
 
 menu "Virtio drivers"
 
@@ -13,7 +11,6 @@ config VIRTIO_PCI
 	tristate "PCI driver for virtio devices (EXPERIMENTAL)"
 	depends on PCI && EXPERIMENTAL
 	select VIRTIO
-	select VIRTIO_RING
 	---help---
 	  This drivers provides support for virtio based paravirtual device
 	  drivers over PCI.  This requires that your VMM has appropriate PCI
@@ -26,9 +23,8 @@ config VIRTIO_PCI
 	  If unsure, say M.
 
 config VIRTIO_BALLOON
-	tristate "Virtio balloon driver (EXPERIMENTAL)"
-	select VIRTIO
-	select VIRTIO_RING
+	tristate "Virtio balloon driver"
+	depends on VIRTIO
 	---help---
 	 This driver supports increasing and decreasing the amount
 	 of memory within a KVM guest.
@@ -39,7 +35,6 @@ config VIRTIO_BALLOON
  	tristate "Platform bus driver for memory mapped virtio devices (EXPERIMENTAL)"
  	depends on HAS_IOMEM && EXPERIMENTAL
  	select VIRTIO
- 	select VIRTIO_RING
  	---help---
  	 This drivers provides support for memory mapped virtio
 	 platform device driver.
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 5a4c63cfd380..9076635697bb 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,4 @@
-obj-$(CONFIG_VIRTIO) += virtio.o
-obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index c3b3f7f0d9d1..1e8659ca27ef 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -159,7 +159,7 @@ static int virtio_dev_remove(struct device *_d)
 	drv->remove(dev);
 
 	/* Driver should have reset device. */
-	BUG_ON(dev->config->get_status(dev));
+	WARN_ON_ONCE(dev->config->get_status(dev));
 
 	/* Acknowledge the device's existence again. */
 	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 453db0c403d8..6b1b7e184939 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -131,9 +131,6 @@ struct virtio_mmio_vq_info {
 	/* the number of entries in the queue */
 	unsigned int num;
 
-	/* the index of the queue */
-	int queue_index;
-
 	/* the virtual address of the ring queue */
 	void *queue;
 
@@ -225,11 +222,10 @@ static void vm_reset(struct virtio_device *vdev)
 static void vm_notify(struct virtqueue *vq)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
-	struct virtio_mmio_vq_info *info = vq->priv;
 
 	/* We write the queue's selector into the notification register to
 	 * signal the other end */
-	writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	writel(virtqueue_get_queue_index(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
 }
 
 /* Notify all virtqueues on an interrupt. */
@@ -270,6 +266,7 @@ static void vm_del_vq(struct virtqueue *vq)
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
 	struct virtio_mmio_vq_info *info = vq->priv;
 	unsigned long flags, size;
+	unsigned int index = virtqueue_get_queue_index(vq);
 
 	spin_lock_irqsave(&vm_dev->lock, flags);
 	list_del(&info->node);
@@ -278,7 +275,7 @@ static void vm_del_vq(struct virtqueue *vq)
 	vring_del_virtqueue(vq);
 
 	/* Select and deactivate the queue */
-	writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
 	writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 
 	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));
@@ -309,6 +306,9 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 	unsigned long flags, size;
 	int err;
 
+	if (!name)
+		return NULL;
+
 	/* Select the queue we're interested in */
 	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
 
@@ -324,7 +324,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 		err = -ENOMEM;
 		goto error_kmalloc;
 	}
-	info->queue_index = index;
 
 	/* Allocate pages for the queue - start with a queue as big as
 	 * possible (limited by maximum size allowed by device), drop down
@@ -332,11 +331,21 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 	 * and two rings (which makes it "alignment_size * 2")
 	 */
 	info->num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+
+	/* If the device reports a 0 entry queue, we won't be able to
+	 * use it to perform I/O, and vring_new_virtqueue() can't create
+	 * empty queues anyway, so don't bother to set up the device.
+	 */
+	if (info->num == 0) {
+		err = -ENOENT;
+		goto error_alloc_pages;
+	}
+
 	while (1) {
 		size = PAGE_ALIGN(vring_size(info->num,
 				VIRTIO_MMIO_VRING_ALIGN));
-		/* Already smallest possible allocation? */
-		if (size <= VIRTIO_MMIO_VRING_ALIGN * 2) {
+		/* Did the last iter shrink the queue below minimum size? */
+		if (size < VIRTIO_MMIO_VRING_ALIGN * 2) {
 			err = -ENOMEM;
 			goto error_alloc_pages;
 		}
@@ -356,7 +365,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 			vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 
 	/* Create the vring */
-	vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
 				 true, info->queue, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 2e03d416b9af..c33aea36598a 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -48,6 +48,7 @@ struct virtio_pci_device
 	int msix_enabled;
 	int intx_enabled;
 	struct msix_entry *msix_entries;
+	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
 	char (*msix_names)[256];
@@ -79,9 +80,6 @@ struct virtio_pci_vq_info
 	/* the number of entries in the queue */
 	int num;
 
-	/* the index of the queue */
-	int queue_index;
-
 	/* the virtual address of the ring queue */
 	void *queue;
 
@@ -202,11 +200,11 @@ static void vp_reset(struct virtio_device *vdev)
 static void vp_notify(struct virtqueue *vq)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
-	struct virtio_pci_vq_info *info = vq->priv;
 
 	/* we write the queue's selector into the notification register to
 	 * signal the other end */
-	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	iowrite16(virtqueue_get_queue_index(vq),
+		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
 }
 
 /* Handle a configuration change: Tell driver if it wants to know. */
@@ -279,6 +277,10 @@ static void vp_free_vectors(struct virtio_device *vdev)
 	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
 		free_irq(vp_dev->msix_entries[i].vector, vp_dev);
 
+	for (i = 0; i < vp_dev->msix_vectors; i++)
+		if (vp_dev->msix_affinity_masks[i])
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
 	if (vp_dev->msix_enabled) {
 		/* Disable the vector used for configuration */
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
@@ -296,6 +298,8 @@ static void vp_free_vectors(struct virtio_device *vdev)
 	vp_dev->msix_names = NULL;
 	kfree(vp_dev->msix_entries);
 	vp_dev->msix_entries = NULL;
+	kfree(vp_dev->msix_affinity_masks);
+	vp_dev->msix_affinity_masks = NULL;
 }
 
 static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
@@ -314,6 +318,15 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 				     GFP_KERNEL);
 	if (!vp_dev->msix_names)
 		goto error;
+	vp_dev->msix_affinity_masks
+		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+			  GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto error;
+	for (i = 0; i < nvectors; ++i)
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+					GFP_KERNEL))
+			goto error;
 
 	for (i = 0; i < nvectors; ++i)
 		vp_dev->msix_entries[i].entry = i;
@@ -402,7 +415,6 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	info->queue_index = index;
 	info->num = num;
 	info->msix_vector = msix_vec;
 
@@ -418,7 +430,7 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
 		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
 	/* create the vring */
-	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
 				 true, info->queue, vp_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
@@ -467,7 +479,8 @@ static void vp_del_vq(struct virtqueue *vq)
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
-	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite16(virtqueue_get_queue_index(vq),
+		vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
 	if (vp_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
@@ -542,7 +555,10 @@ static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	vp_dev->per_vq_vectors = per_vq_vectors;
 	allocated_vectors = vp_dev->msix_used_vectors;
 	for (i = 0; i < nvqs; ++i) {
-		if (!callbacks[i] || !vp_dev->msix_enabled)
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		} else if (!callbacks[i] || !vp_dev->msix_enabled)
 			msix_vec = VIRTIO_MSI_NO_VECTOR;
 		else if (vp_dev->per_vq_vectors)
 			msix_vec = allocated_vectors++;
@@ -609,6 +625,35 @@ static const char *vp_bus_name(struct virtio_device *vdev)
 	return pci_name(vp_dev->pci_dev);
 }
 
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+	struct cpumask *mask;
+	unsigned int irq;
+
+	if (!vq->callback)
+		return -EINVAL;
+
+	if (vp_dev->msix_enabled) {
+		mask = vp_dev->msix_affinity_masks[info->msix_vector];
+		irq = vp_dev->msix_entries[info->msix_vector].vector;
+		if (cpu == -1)
+			irq_set_affinity_hint(irq, NULL);
+		else {
+			cpumask_set_cpu(cpu, mask);
+			irq_set_affinity_hint(irq, mask);
+		}
+	}
+	return 0;
+}
+
 static struct virtio_config_ops virtio_pci_config_ops = {
 	.get		= vp_get,
 	.set		= vp_set,
@@ -620,6 +665,7 @@ static struct virtio_config_ops virtio_pci_config_ops = {
 	.get_features	= vp_get_features,
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
 };
 
 static void virtio_pci_release_dev(struct device *_d)
@@ -673,8 +719,10 @@ static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
 		goto out_enable_device;
 
 	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
-	if (vp_dev->ioaddr == NULL)
+	if (vp_dev->ioaddr == NULL) {
+		err = -ENOMEM;
 		goto out_req_regions;
+	}
 
 	pci_set_drvdata(pci_dev, vp_dev);
 	pci_set_master(pci_dev);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 5aa43c3392a2..e639584b2dbd 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -106,6 +106,9 @@ struct vring_virtqueue
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	void (*notify)(struct virtqueue *vq);
 
+	/* Index of the queue */
+	int queue_index;
+
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;
@@ -171,6 +174,13 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	return head;
 }
 
+int virtqueue_get_queue_index(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	return vq->queue_index;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_queue_index);
+
 /**
  * virtqueue_add_buf - expose buffer to other end
  * @vq: the struct virtqueue we're talking about.
@@ -616,7 +626,8 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 }
 EXPORT_SYMBOL_GPL(vring_interrupt);
 
-struct virtqueue *vring_new_virtqueue(unsigned int num,
+struct virtqueue *vring_new_virtqueue(unsigned int index,
+				      unsigned int num,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,
@@ -647,6 +658,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
+	vq->queue_index = index;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;