8 files changed, 194 insertions, 41 deletions

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 849500e..524c221 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -39,6 +39,7 @@
 #include <asm/irq.h>
 #include <asm/idle.h>
 #include <asm/io_apic.h>
+#include <asm/i8259.h>
 #include <asm/xen/pci.h>
 #endif
 #include <asm/sync_bitops.h>
@@ -420,7 +421,7 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 		return xen_allocate_irq_dynamic();
 
 	/* Legacy IRQ descriptors are already allocated by the arch. */
-	if (gsi < NR_IRQS_LEGACY)
+	if (gsi < nr_legacy_irqs())
 		irq = gsi;
 	else
 		irq = irq_alloc_desc_at(gsi, -1);
@@ -446,7 +447,7 @@ static void xen_free_irq(unsigned irq)
 	kfree(info);
 
 	/* Legacy IRQ descriptors are managed by the arch. */
-	if (irq < NR_IRQS_LEGACY)
+	if (irq < nr_legacy_irqs())
 		return;
 
 	irq_free_desc(irq);
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index e3e9e3d..96a1b8d 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -281,7 +281,8 @@ static void handle_irq_for_port(unsigned port)
 
 static void consume_one_event(unsigned cpu,
 			      struct evtchn_fifo_control_block *control_block,
-			      unsigned priority, unsigned long *ready)
+			      unsigned priority, unsigned long *ready,
+			      bool drop)
 {
 	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
 	uint32_t head;
@@ -313,13 +314,17 @@ static void consume_one_event(unsigned cpu,
 	if (head == 0)
 		clear_bit(priority, ready);
 
-	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port))
-		handle_irq_for_port(port);
+	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) {
+		if (unlikely(drop))
+			pr_warn("Dropping pending event for port %u\n", port);
+		else
+			handle_irq_for_port(port);
+	}
 
 	q->head[priority] = head;
 }
 
-static void evtchn_fifo_handle_events(unsigned cpu)
+static void __evtchn_fifo_handle_events(unsigned cpu, bool drop)
 {
 	struct evtchn_fifo_control_block *control_block;
 	unsigned long ready;
@@ -331,11 +336,16 @@ static void evtchn_fifo_handle_events(unsigned cpu)
 
 	while (ready) {
 		q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES);
-		consume_one_event(cpu, control_block, q, &ready);
+		consume_one_event(cpu, control_block, q, &ready, drop);
 		ready |= xchg(&control_block->ready, 0);
 	}
 }
 
+static void evtchn_fifo_handle_events(unsigned cpu)
+{
+	__evtchn_fifo_handle_events(cpu, false);
+}
+
 static void evtchn_fifo_resume(void)
 {
 	unsigned cpu;
@@ -420,6 +430,9 @@ static int evtchn_fifo_cpu_notification(struct notifier_block *self,
 		if (!per_cpu(cpu_control_block, cpu))
 			ret = evtchn_fifo_alloc_control_block(cpu);
 		break;
+	case CPU_DEAD:
+		__evtchn_fifo_handle_events(cpu, true);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 00f40f0..38272ad 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -49,6 +49,8 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -58,10 +60,10 @@
 struct per_user_data {
 	struct mutex bind_mutex; /* serialize bind/unbind operations */
 	struct rb_root evtchns;
+	unsigned int nr_evtchns;
 
 	/* Notification ring, accessed via /dev/xen/evtchn. */
-#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
-#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+	unsigned int ring_size;
 	evtchn_port_t *ring;
 	unsigned int ring_cons, ring_prod, ring_overflow;
 	struct mutex ring_cons_mutex; /* protect against concurrent readers */
@@ -80,10 +82,41 @@ struct user_evtchn {
 	bool enabled;
 };
 
+static evtchn_port_t *evtchn_alloc_ring(unsigned int size)
+{
+	evtchn_port_t *ring;
+	size_t s = size * sizeof(*ring);
+
+	ring = kmalloc(s, GFP_KERNEL);
+	if (!ring)
+		ring = vmalloc(s);
+
+	return ring;
+}
+
+static void evtchn_free_ring(evtchn_port_t *ring)
+{
+	kvfree(ring);
+}
+
+static unsigned int evtchn_ring_offset(struct per_user_data *u,
+				       unsigned int idx)
+{
+	return idx & (u->ring_size - 1);
+}
+
+static evtchn_port_t *evtchn_ring_entry(struct per_user_data *u,
+					unsigned int idx)
+{
+	return u->ring + evtchn_ring_offset(u, idx);
+}
+
 static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
 	struct rb_node **new = &(u->evtchns.rb_node), *parent = NULL;
 
+	u->nr_evtchns++;
+
 	while (*new) {
 		struct user_evtchn *this;
 
@@ -107,6 +140,7 @@ static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 
 static void del_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
+	u->nr_evtchns--;
 	rb_erase(&evtchn->node, &u->evtchns);
 	kfree(evtchn);
 }
@@ -144,8 +178,8 @@ static irqreturn_t evtchn_interrupt(int irq, void *data)
 
 	spin_lock(&u->ring_prod_lock);
 
-	if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
-		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = evtchn->port;
+	if ((u->ring_prod - u->ring_cons) < u->ring_size) {
+		*evtchn_ring_entry(u, u->ring_prod) = evtchn->port;
 		wmb(); /* Ensure ring contents visible */
 		if (u->ring_cons == u->ring_prod++) {
 			wake_up_interruptible(&u->evtchn_wait);
@@ -200,10 +234,10 @@ static ssize_t evtchn_read(struct file *file, char __user *buf,
 	}
 
 	/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
-	if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
-		bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+	if (((c ^ p) & u->ring_size) != 0) {
+		bytes1 = (u->ring_size - evtchn_ring_offset(u, c)) *
 			sizeof(evtchn_port_t);
-		bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+		bytes2 = evtchn_ring_offset(u, p) * sizeof(evtchn_port_t);
 	} else {
 		bytes1 = (p - c) * sizeof(evtchn_port_t);
 		bytes2 = 0;
@@ -219,7 +253,7 @@ static ssize_t evtchn_read(struct file *file, char __user *buf,
 
 	rc = -EFAULT;
 	rmb(); /* Ensure that we see the port before we copy it. */
-	if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+	if (copy_to_user(buf, evtchn_ring_entry(u, c), bytes1) ||
 	    ((bytes2 != 0) &&
 	     copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
 		goto unlock_out;
@@ -278,6 +312,66 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf,
 	return rc;
 }
 
+static int evtchn_resize_ring(struct per_user_data *u)
+{
+	unsigned int new_size;
+	evtchn_port_t *new_ring, *old_ring;
+	unsigned int p, c;
+
+	/*
+	 * Ensure the ring is large enough to capture all possible
+	 * events. i.e., one free slot for each bound event.
+	 */
+	if (u->nr_evtchns <= u->ring_size)
+		return 0;
+
+	if (u->ring_size == 0)
+		new_size = 64;
+	else
+		new_size = 2 * u->ring_size;
+
+	new_ring = evtchn_alloc_ring(new_size);
+	if (!new_ring)
+		return -ENOMEM;
+
+	old_ring = u->ring;
+
+	/*
+	 * Access to the ring contents is serialized by either the
+	 * prod /or/ cons lock so take both when resizing.
+	 */
+	mutex_lock(&u->ring_cons_mutex);
+	spin_lock_irq(&u->ring_prod_lock);
+
+	/*
+	 * Copy the old ring contents to the new ring.
+	 *
+	 * If the ring contents crosses the end of the current ring,
+	 * it needs to be copied in two chunks.
+	 *
+	 * +---------+    +------------------+
+	 * |34567  12| -> |       1234567    |
+	 * +-----p-c-+    +------------------+
+	 */
+	p = evtchn_ring_offset(u, u->ring_prod);
+	c = evtchn_ring_offset(u, u->ring_cons);
+	if (p < c) {
+		memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring));
+		memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring));
+	} else
+		memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring));
+
+	u->ring = new_ring;
+	u->ring_size = new_size;
+
+	spin_unlock_irq(&u->ring_prod_lock);
+	mutex_unlock(&u->ring_cons_mutex);
+
+	evtchn_free_ring(old_ring);
+
+	return 0;
+}
+
 static int evtchn_bind_to_user(struct per_user_data *u, int port)
 {
 	struct user_evtchn *evtchn;
@@ -305,6 +399,10 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port)
 	if (rc < 0)
 		goto err;
 
+	rc = evtchn_resize_ring(u);
+	if (rc < 0)
+		goto err;
+
 	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, 0,
 				       u->name, evtchn);
 	if (rc < 0)
@@ -503,13 +601,6 @@ static int evtchn_open(struct inode *inode, struct file *filp)
 
 	init_waitqueue_head(&u->evtchn_wait);
 
-	u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
-	if (u->ring == NULL) {
-		kfree(u->name);
-		kfree(u);
-		return -ENOMEM;
-	}
-
 	mutex_init(&u->bind_mutex);
 	mutex_init(&u->ring_cons_mutex);
 	spin_lock_init(&u->ring_prod_lock);
@@ -532,7 +623,7 @@ static int evtchn_release(struct inode *inode, struct file *filp)
 		evtchn_unbind_from_user(u, evtchn);
 	}
 
-	free_page((unsigned long)u->ring);
+	evtchn_free_ring(u->ring);
 	kfree(u->name);
 	kfree(u);
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 2ea0b3b..1be5dd0 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -804,7 +804,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 
 	vma->vm_ops = &gntdev_vmops;
 
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
 
 	if (use_ptemod)
 		vma->vm_flags |= VM_DONTCOPY;
diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h
index 58e38d5..4d529f3 100644
--- a/drivers/xen/xen-pciback/pciback.h
+++ b/drivers/xen/xen-pciback/pciback.h
@@ -37,6 +37,7 @@ struct xen_pcibk_device {
 	struct xen_pci_sharedinfo *sh_info;
 	unsigned long flags;
 	struct work_struct op_work;
+	struct xen_pci_op op;
 };
 
 struct xen_pcibk_dev_data {
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index c4a0666..73dafdc 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -70,6 +70,13 @@ static void xen_pcibk_control_isr(struct pci_dev *dev, int reset)
 		enable ? "enable" : "disable");
 
 	if (enable) {
+		/*
+		 * The MSI or MSI-X should not have an IRQ handler. Otherwise
+		 * if the guest terminates we BUG_ON in free_msi_irqs.
+		 */
+		if (dev->msi_enabled || dev->msix_enabled)
+			goto out;
+
 		rc = request_irq(dev_data->irq,
 				xen_pcibk_guest_interrupt, IRQF_SHARED,
 				dev_data->irq_name, dev);
@@ -144,7 +151,12 @@ int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev,
 	if (unlikely(verbose_request))
 		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI\n", pci_name(dev));
 
-	status = pci_enable_msi(dev);
+	if (dev->msi_enabled)
+		status = -EALREADY;
+	else if (dev->msix_enabled)
+		status = -ENXIO;
+	else
+		status = pci_enable_msi(dev);
 
 	if (status) {
 		pr_warn_ratelimited("%s: error enabling MSI for guest %u: err %d\n",
@@ -173,20 +185,23 @@ static
 int xen_pcibk_disable_msi(struct xen_pcibk_device *pdev,
 			  struct pci_dev *dev, struct xen_pci_op *op)
 {
-	struct xen_pcibk_dev_data *dev_data;
-
 	if (unlikely(verbose_request))
 		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI\n",
 		       pci_name(dev));
-	pci_disable_msi(dev);
 
+	if (dev->msi_enabled) {
+		struct xen_pcibk_dev_data *dev_data;
+
+		pci_disable_msi(dev);
+
+		dev_data = pci_get_drvdata(dev);
+		if (dev_data)
+			dev_data->ack_intr = 1;
+	}
 	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
 	if (unlikely(verbose_request))
 		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
 			op->value);
-	dev_data = pci_get_drvdata(dev);
-	if (dev_data)
-		dev_data->ack_intr = 1;
 	return 0;
 }
 
@@ -197,13 +212,26 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
 	struct xen_pcibk_dev_data *dev_data;
 	int i, result;
 	struct msix_entry *entries;
+	u16 cmd;
 
 	if (unlikely(verbose_request))
 		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI-X\n",
 		       pci_name(dev));
+
 	if (op->value > SH_INFO_MAX_VEC)
 		return -EINVAL;
 
+	if (dev->msix_enabled)
+		return -EALREADY;
+
+	/*
+	 * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able
+	 * to access the BARs where the MSI-X entries reside.
+	 */
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY))
+		return -ENXIO;
+
 	entries = kmalloc(op->value * sizeof(*entries), GFP_KERNEL);
 	if (entries == NULL)
 		return -ENOMEM;
@@ -245,23 +273,27 @@ static
 int xen_pcibk_disable_msix(struct xen_pcibk_device *pdev,
 			   struct pci_dev *dev, struct xen_pci_op *op)
 {
-	struct xen_pcibk_dev_data *dev_data;
 	if (unlikely(verbose_request))
 		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI-X\n",
 			pci_name(dev));
-	pci_disable_msix(dev);
 
+	if (dev->msix_enabled) {
+		struct xen_pcibk_dev_data *dev_data;
+
+		pci_disable_msix(dev);
+
+		dev_data = pci_get_drvdata(dev);
+		if (dev_data)
+			dev_data->ack_intr = 1;
+	}
 	/*
 	 * SR-IOV devices (which don't have any legacy IRQ) have
 	 * an undefined IRQ value of zero.
 	 */
 	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
 	if (unlikely(verbose_request))
-		printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n", pci_name(dev),
-			op->value);
-	dev_data = pci_get_drvdata(dev);
-	if (dev_data)
-		dev_data->ack_intr = 1;
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n",
+		       pci_name(dev), op->value);
 	return 0;
 }
 #endif
@@ -298,9 +330,11 @@ void xen_pcibk_do_op(struct work_struct *data)
 		container_of(data, struct xen_pcibk_device, op_work);
 	struct pci_dev *dev;
 	struct xen_pcibk_dev_data *dev_data = NULL;
-	struct xen_pci_op *op = &pdev->sh_info->op;
+	struct xen_pci_op *op = &pdev->op;
 	int test_intx = 0;
 
+	*op = pdev->sh_info->op;
+	barrier();
 	dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn);
 
 	if (dev == NULL)
@@ -342,6 +376,17 @@ void xen_pcibk_do_op(struct work_struct *data)
 		if ((dev_data->enable_intx != test_intx))
 			xen_pcibk_control_isr(dev, 0 /* no reset */);
 	}
+	pdev->sh_info->op.err = op->err;
+	pdev->sh_info->op.value = op->value;
+#ifdef CONFIG_PCI_MSI
+	if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) {
+		unsigned int i;
+
+		for (i = 0; i < op->value; i++)
+			pdev->sh_info->op.msix_entries[i].vector =
+				op->msix_entries[i].vector;
+	}
+#endif
 	/* Tell the driver domain that we're done. */
 	wmb();
 	clear_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index 98bc345..4843741 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -44,7 +44,6 @@ static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev)
 	dev_dbg(&xdev->dev, "allocated pdev @ 0x%p\n", pdev);
 
 	pdev->xdev = xdev;
-	dev_set_drvdata(&xdev->dev, pdev);
 
 	mutex_init(&pdev->dev_lock);
 
@@ -58,6 +57,9 @@ static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev)
 		kfree(pdev);
 		pdev = NULL;
 	}
+
+	dev_set_drvdata(&xdev->dev, pdev);
+
 out:
 	return pdev;
 }
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 43bcae8..ad4eb10 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -726,7 +726,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 		if (!pending_req)
 			return 1;
 
-		ring_req = *RING_GET_REQUEST(ring, rc);
+		RING_COPY_REQUEST(ring, rc, &ring_req);
 		ring->req_cons = ++rc;
 
 		err = prepare_pending_reqs(info, &ring_req, pending_req);