[Qemu-devel] [PATCH] vfio-pci: Add support for MSI affinity

[Alex Williamson]

When MSI is accelerated through KVM the vectors are only programmed
when the guest first enables MSI support.  Subsequent writes to the
vector address or data fields are ignored.  Unfortunately that means
we're ignore updates done to adjust SMP affinity of the vectors.
MSI SMP affinity already works in non-KVM mode because the address
and data fields are read from their backing store on each interrupt.

This patch stores the MSIMessage programmed into KVM so that we can
determine when changes are made and update the routes.

Signed-off-by: Alex Williamson <address@hidden>
---

For qemu-1.6

 hw/misc/vfio.c |   47 ++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 40 insertions(+), 7 deletions(-)

diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c
index 693a9ff..67a1580 100644
--- a/hw/misc/vfio.c
+++ b/hw/misc/vfio.c
@@ -102,6 +102,7 @@ typedef struct VFIOINTx {
 typedef struct VFIOMSIVector {
     EventNotifier interrupt; /* eventfd triggered on interrupt */
     struct VFIODevice *vdev; /* back pointer to device */
+    MSIMessage msg; /* cache the MSI message so we know when it changes */
     int virq; /* KVM irqchip route for QEMU bypass */
     bool use;
 } VFIOMSIVector;
@@ -776,7 +777,6 @@ retry:
     vdev->msi_vectors = g_malloc0(vdev->nr_vectors * sizeof(VFIOMSIVector));
 
     for (i = 0; i < vdev->nr_vectors; i++) {
-        MSIMessage msg;
         VFIOMSIVector *vector = &vdev->msi_vectors[i];
 
         vector->vdev = vdev;
@@ -786,13 +786,13 @@ retry:
             error_report("vfio: Error: event_notifier_init failed");
         }
 
-        msg = msi_get_message(&vdev->pdev, i);
+        vector->msg = msi_get_message(&vdev->pdev, i);
 
         /*
          * Attempt to enable route through KVM irqchip,
          * default to userspace handling if unavailable.
          */
-        vector->virq = kvm_irqchip_add_msi_route(kvm_state, msg);
+        vector->virq = kvm_irqchip_add_msi_route(kvm_state, vector->msg);
         if (vector->virq < 0 ||
             kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
                                            vector->virq) < 0) {
@@ -898,6 +898,33 @@ static void vfio_disable_msi(VFIODevice *vdev)
             vdev->host.bus, vdev->host.slot, vdev->host.function);
 }
 
+static void vfio_update_msi(VFIODevice *vdev)
+{
+    int i;
+
+    for (i = 0; i < vdev->nr_vectors; i++) {
+        VFIOMSIVector *vector = &vdev->msi_vectors[i];
+        MSIMessage msg;
+
+        if (!vector->use || vector->virq < 0) {
+            continue;
+        }
+
+        msg = msi_get_message(&vdev->pdev, i);
+
+        if (msg.address != vector->msg.address ||
+            msg.data != vector->msg.data) {
+
+            DPRINTF("%s(%04x:%02x:%02x.%x) MSI vector %d changed\n",
+                    __func__, vdev->host.domain, vdev->host.bus,
+                    vdev->host.slot, vdev->host.function, i);
+
+            kvm_irqchip_update_msi_route(kvm_state, vector->virq, msg);
+            vector->msg = msg;
+        }
+    }
+}
+
 /*
  * IO Port/MMIO - Beware of the endians, VFIO is always little endian
  */
@@ -1850,10 +1877,16 @@ static void vfio_pci_write_config(PCIDevice *pdev, 
uint32_t addr,
 
         is_enabled = msi_enabled(pdev);
 
-        if (!was_enabled && is_enabled) {
-            vfio_enable_msi(vdev);
-        } else if (was_enabled && !is_enabled) {
-            vfio_disable_msi(vdev);
+        if (!was_enabled) {
+            if (is_enabled) {
+                vfio_enable_msi(vdev);
+            }
+        } else {
+            if (!is_enabled) {
+                vfio_disable_msi(vdev);
+            } else {
+                vfio_update_msi(vdev);
+            }
         }
     } else if (pdev->cap_present & QEMU_PCI_CAP_MSIX &&
         ranges_overlap(addr, len, pdev->msix_cap, MSIX_CAP_LENGTH)) {