[Qemu-devel] [PATCH 1/2] vfio-pci: Make host MSI-X enable track guest

[Alex Williamson <alex.williamson@redhat.com>]

Guests typically enable MSI-X with all of the vectors in the MSI-X
vector table masked.  Only when the vector is enabled does the vector
get unmasked, resulting in a vector_use callback.  These two points,
enable and unmask, correspond to pci_enable_msix() and request_irq()
for Linux guests.  Some drivers rely on VF/PF or PF/fw communication
channels that expect the physical state of the device to match the
guest visible state of the device.  They don't appreciate lazily
enabling MSI-X on the physical device.

To solve this, enable MSI-X with a single vector when the MSI-X
capability is enabled and immediate disable the vector.  This leaves
the physical device in exactly the same state between host and guest.
Furthermore, the brief gap where we enable vector 0, it fires into
userspace, not KVM, so the guest doesn't get spurious interrupts.
Ideally we could call VFIO_DEVICE_SET_IRQS with the right parameters
to enable MSI-X with zero vectors, but this will currently return an
error as the Linux MSI-X interfaces do not allow it.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Cc: qemu-stable@nongnu.org
---
 hw/vfio_pci.c |   30 ++++++++++++++++++++++++++----
 1 file changed, 26 insertions(+), 4 deletions(-)

diff --git a/hw/vfio_pci.c b/hw/vfio_pci.c
index 28c8303..8ec1faf 100644
--- a/hw/vfio_pci.c
+++ b/hw/vfio_pci.c
@@ -562,8 +562,8 @@ static int vfio_enable_vectors(VFIODevice *vdev, bool msix)
     return ret;
 }
 
-static int vfio_msix_vector_use(PCIDevice *pdev,
-                                unsigned int nr, MSIMessage msg)
+static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
+                                   MSIMessage *msg, IOHandler *handler)
 {
     VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
     VFIOMSIVector *vector;
@@ -587,7 +587,7 @@ static int vfio_msix_vector_use(PCIDevice *pdev,
      * 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 = msg ? kvm_irqchip_add_msi_route(kvm_state, *msg) : -1;
     if (vector->virq < 0 ||
         kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
                                        vector->virq) < 0) {
@@ -596,7 +596,7 @@ static int vfio_msix_vector_use(PCIDevice *pdev,
             vector->virq = -1;
         }
         qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
-                            vfio_msi_interrupt, NULL, vector);
+                            handler, NULL, vector);
     }
 
     /*
@@ -639,6 +639,12 @@ static int vfio_msix_vector_use(PCIDevice *pdev,
     return 0;
 }
 
+static int vfio_msix_vector_use(PCIDevice *pdev,
+                                unsigned int nr, MSIMessage msg)
+{
+    return vfio_msix_vector_do_use(pdev, nr, &msg, vfio_msi_interrupt);
+}
+
 static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
 {
     VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
@@ -697,6 +703,22 @@ static void vfio_enable_msix(VFIODevice *vdev)
 
     vdev->interrupt = VFIO_INT_MSIX;
 
+    /*
+     * Some communication channels between VF & PF or PF & fw rely on the
+     * physical state of the device and expect that enabling MSI-X from the
+     * guest enables the same on the host.  When our guest is Linux, the
+     * guest driver call to pci_enable_msix() sets the enabling bit in the
+     * MSI-X capability, but leaves the vector table masked.  We therefore
+     * can't rely on a vector_use callback (from request_irq() in the guest)
+     * to switch the physical device into MSI-X mode because that may come a
+     * long time after pci_enable_msix().  This code enables vector 0 with
+     * triggering to userspace, then immediately release the vector, leaving
+     * the physical device with no vectors enabled, but MSI-X enabled, just
+     * like the guest view.
+     */
+    vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL);
+    vfio_msix_vector_release(&vdev->pdev, 0);
+
     if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
                                   vfio_msix_vector_release, NULL)) {
         error_report("vfio: msix_set_vector_notifiers failed\n");