3 files changed, 69 insertions, 16 deletions

diff --git a/kernel/drivers/xen/xen-pciback/pciback.h b/kernel/drivers/xen/xen-pciback/pciback.h
index 58e38d586..4d529f3e4 100644
--- a/kernel/drivers/xen/xen-pciback/pciback.h
+++ b/kernel/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/kernel/drivers/xen/xen-pciback/pciback_ops.c b/kernel/drivers/xen/xen-pciback/pciback_ops.c
index c4a0666de..fb0221434 100644
--- a/kernel/drivers/xen/xen-pciback/pciback_ops.c
+++ b/kernel/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 +212,27 @@ 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.
+	 * But VF devices are unique in which the PF needs to be checked.
+	 */
+	pci_read_config_word(pci_physfn(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 +274,27 @@ 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 +331,14 @@ 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;
+#ifdef CONFIG_PCI_MSI
+	unsigned int nr = 0;
+#endif
 
+	*op = pdev->sh_info->op;
+	barrier();
 	dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn);
 
 	if (dev == NULL)
@@ -326,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 			op->err = xen_pcibk_disable_msi(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_enable_msix:
+			nr = op->value;
 			op->err = xen_pcibk_enable_msix(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_disable_msix:
@@ -342,6 +381,17 @@ 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 < nr; 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/kernel/drivers/xen/xen-pciback/xenbus.c b/kernel/drivers/xen/xen-pciback/xenbus.c
index 98bc345f2..4843741e7 100644
--- a/kernel/drivers/xen/xen-pciback/xenbus.c
+++ b/kernel/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;
 }