xen: fix MSI setup and teardown for PV on HVM guests

When remapping MSIs into pirqs for PV on HVM guests, qemu is responsible
for doing the actual mapping and unmapping.
We only give qemu the desired pirq number when we ask to do the mapping
the first time, after that we should be reading back the pirq number
from qemu every time we want to re-enable the MSI.

This fixes a bug in xen_hvm_setup_msi_irqs that manifests itself when
trying to enable the same MSI for the second time: the old MSI to pirq
mapping is still valid at this point but xen_hvm_setup_msi_irqs would
try to assign a new pirq anyway.
A simple way to reproduce this bug is to assign an MSI capable network
card to a PV on HVM guest, if the user brings down the corresponding
ethernet interface and up again, Linux would fail to enable MSIs on the
device.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>

1 files changed, 20 insertions, 7 deletions

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index d7b5109f7a9c..25cd4a07d09f 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -70,6 +70,9 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
 struct xen_pci_frontend_ops *xen_pci_frontend;
 EXPORT_SYMBOL_GPL(xen_pci_frontend);
 
+#define XEN_PIRQ_MSI_DATA  (MSI_DATA_TRIGGER_EDGE | \
+		MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0))
+
 static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		struct msi_msg *msg)
 {
@@ -83,12 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		MSI_ADDR_REDIRECTION_CPU |
 		MSI_ADDR_DEST_ID(pirq);
 
-	msg->data =
-		MSI_DATA_TRIGGER_EDGE |
-		MSI_DATA_LEVEL_ASSERT |
-		/* delivery mode reserved */
-		(3 << 8) |
-		MSI_DATA_VECTOR(0);
+	msg->data = XEN_PIRQ_MSI_DATA;
 }
 
 static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -98,8 +96,23 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	struct msi_msg msg;
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
+		__read_msi_msg(msidesc, &msg);
+		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
+			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
+		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
+			xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
+					"msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ);
+			if (irq < 0)
+				goto error;
+			ret = set_irq_msi(irq, msidesc);
+			if (ret < 0)
+				goto error_while;
+			printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d"
+					" pirq=%d\n", irq, pirq);
+			return 0;
+		}
 		xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-				"msi-x" : "msi", &irq, &pirq);
+				"msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ));
 		if (irq < 0 || pirq < 0)
 			goto error;
 		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);