From 7da624e26a4ef149927fe0ac187148f24306412f Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Jul 2017 10:39:43 -0600 Subject: [PATCH 1/2] vfio: Test realized when using VFIOGroup.device_list iterator VFIOGroup.device_list is effectively our reference tracking mechanism such that we can teardown a group when all of the device references are removed. However, we also use this list from our machine reset handler for processing resets that affect multiple devices. Generally device removals are fully processed (exitfn + finalize) when this reset handler is invoked, however if the removal is triggered via another reset handler (piix4_reset->acpi_pcihp_reset) then the device exitfn may run, but not finalize. In this case we hit asserts when we start trying to access PCI helpers since much of the PCI state of the device is released. To resolve this, add a pointer to the Object DeviceState in our common base-device and skip non-realized devices as we iterate. Signed-off-by: Alex Williamson --- hw/vfio/common.c | 6 ++++-- hw/vfio/pci.c | 7 +++++-- hw/vfio/platform.c | 1 + include/hw/vfio/vfio-common.h | 1 + 4 files changed, 11 insertions(+), 4 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index b9abe77f5a..29923e4990 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -858,13 +858,15 @@ void vfio_reset_handler(void *opaque) QLIST_FOREACH(group, &vfio_group_list, next) { QLIST_FOREACH(vbasedev, &group->device_list, next) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); + if (vbasedev->dev->realized) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); + } } } QLIST_FOREACH(group, &vfio_group_list, next) { QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->needs_reset) { + if (vbasedev->dev->realized && vbasedev->needs_reset) { vbasedev->ops->vfio_hot_reset_multi(vbasedev); } } diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 8de8272e96..ccdb6e1d63 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2116,7 +2116,8 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single) /* Prep dependent devices for reset and clear our marker. */ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) { + if (!vbasedev_iter->dev->realized || + vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) { continue; } tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev); @@ -2197,7 +2198,8 @@ out: } QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) { + if (!vbasedev_iter->dev->realized || + vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) { continue; } tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev); @@ -2647,6 +2649,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) vdev->vbasedev.name = g_strdup(basename(vdev->vbasedev.sysfsdev)); vdev->vbasedev.ops = &vfio_pci_ops; vdev->vbasedev.type = VFIO_DEVICE_TYPE_PCI; + vdev->vbasedev.dev = &vdev->pdev.qdev; tmp = g_strdup_printf("%s/iommu_group", vdev->vbasedev.sysfsdev); len = readlink(tmp, group_path, sizeof(group_path)); diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index a4663c918e..7c09deda61 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -640,6 +640,7 @@ static void vfio_platform_realize(DeviceState *dev, Error **errp) int i, ret; vbasedev->type = VFIO_DEVICE_TYPE_PLATFORM; + vbasedev->dev = dev; vbasedev->ops = &vfio_platform_ops; trace_vfio_platform_realize(vbasedev->sysfsdev ? diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 9521013d52..0b475a3596 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -115,6 +115,7 @@ typedef struct VFIODevice { struct VFIOGroup *group; char *sysfsdev; char *name; + DeviceState *dev; int fd; int type; bool reset_works; From 47985727e383eee191a39cc007541c17cd8680ee Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Jul 2017 10:39:43 -0600 Subject: [PATCH 2/2] vfio/pci: Fixup v0 PCIe capabilities Intel 82599 VFs report a PCIe capability version of 0, which is invalid. The earliest version of the PCIe spec used version 1. This causes Windows to fail startup on the device and it will be disabled with error code 10. Our choices are either to drop the PCIe cap on such devices, which has the side effect of likely preventing the guest from discovering any extended capabilities, or performing a fixup to update the capability to the earliest valid version. This implements the latter. Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index ccdb6e1d63..d4051cb951 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -1743,6 +1743,18 @@ static int vfio_setup_pcie_cap(VFIOPCIDevice *vdev, int pos, uint8_t size, PCI_EXP_LNKCAP_MLW | PCI_EXP_LNKCAP_SLS); } + /* + * Intel 82599 SR-IOV VFs report an invalid PCIe capability version 0 + * (Niantic errate #35) causing Windows to error with a Code 10 for the + * device on Q35. Fixup any such devices to report version 1. If we + * were to remove the capability entirely the guest would lose extended + * config space. + */ + if ((flags & PCI_EXP_FLAGS_VERS) == 0) { + vfio_add_emulated_word(vdev, pos + PCI_CAP_FLAGS, + 1, PCI_EXP_FLAGS_VERS); + } + pos = pci_add_capability(&vdev->pdev, PCI_CAP_ID_EXP, pos, size, errp); if (pos < 0) {