Merge remote-tracking branch 'remotes/dgibson/tags/ppc-next-20151111' into staging
ppc patch queue - 2015-11-11
Highlights:
- Updated SLOF version for "pseries machine
- Bugfix / cleanup for KVM hash page table allocation
# gpg: Signature made Wed 11 Nov 2015 02:30:51 GMT using RSA key ID 20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg: aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg: aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg: It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E 87DC 6C38 CACA 20D9 B392
* remotes/dgibson/tags/ppc-next-20151111:
spapr: Handle failure of KVM_PPC_ALLOCATE_HTAB ioctl
ppc: Let kvmppc_reset_htab() return 0 for !CONFIG_KVM
pseries: Update SLOF firmware image to qemu-slof-20151103
ppc: Add/Re-introduce MMU model definitions needed by PR KVM
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c
index c675d1b..30c68a1 100644
--- a/hw/vfio/pci-quirks.c
+++ b/hw/vfio/pci-quirks.c
@@ -284,7 +284,7 @@
}
quirk = g_malloc0(sizeof(*quirk));
- quirk->mem = g_malloc0(sizeof(MemoryRegion));
+ quirk->mem = g_new0(MemoryRegion, 1);
quirk->nr_mem = 1;
memory_region_init_io(quirk->mem, OBJECT(vdev), &vfio_ati_3c3_quirk, vdev,
@@ -319,7 +319,7 @@
}
quirk = g_malloc0(sizeof(*quirk));
- quirk->mem = g_malloc0(sizeof(MemoryRegion) * 2);
+ quirk->mem = g_new0(MemoryRegion, 2);
quirk->nr_mem = 2;
window = quirk->data = g_malloc0(sizeof(*window) +
sizeof(VFIOConfigWindowMatch));
@@ -368,7 +368,7 @@
quirk = g_malloc0(sizeof(*quirk));
mirror = quirk->data = g_malloc0(sizeof(*mirror));
- mirror->mem = quirk->mem = g_malloc0(sizeof(MemoryRegion));
+ mirror->mem = quirk->mem = g_new0(MemoryRegion, 1);
quirk->nr_mem = 1;
mirror->vdev = vdev;
mirror->offset = 0x4000;
@@ -544,7 +544,7 @@
quirk = g_malloc0(sizeof(*quirk));
quirk->data = data = g_malloc0(sizeof(*data));
- quirk->mem = g_malloc0(sizeof(MemoryRegion) * 2);
+ quirk->mem = g_new0(MemoryRegion, 2);
quirk->nr_mem = 2;
data->vdev = vdev;
@@ -661,7 +661,7 @@
}
quirk = g_malloc0(sizeof(*quirk));
- quirk->mem = g_malloc0(sizeof(MemoryRegion) * 4);
+ quirk->mem = g_new0(MemoryRegion, 4);
quirk->nr_mem = 4;
bar5 = quirk->data = g_malloc0(sizeof(*bar5) +
(sizeof(VFIOConfigWindowMatch) * 2));
@@ -756,7 +756,7 @@
quirk = g_malloc0(sizeof(*quirk));
mirror = quirk->data = g_malloc0(sizeof(*mirror));
- mirror->mem = quirk->mem = g_malloc0(sizeof(MemoryRegion));
+ mirror->mem = quirk->mem = g_new0(MemoryRegion, 1);
quirk->nr_mem = 1;
mirror->vdev = vdev;
mirror->offset = 0x88000;
@@ -775,7 +775,7 @@
if (vdev->has_vga) {
quirk = g_malloc0(sizeof(*quirk));
mirror = quirk->data = g_malloc0(sizeof(*mirror));
- mirror->mem = quirk->mem = g_malloc0(sizeof(MemoryRegion));
+ mirror->mem = quirk->mem = g_new0(MemoryRegion, 1);
quirk->nr_mem = 1;
mirror->vdev = vdev;
mirror->offset = 0x1800;
@@ -938,7 +938,7 @@
}
quirk = g_malloc0(sizeof(*quirk));
- quirk->mem = g_malloc0(sizeof(MemoryRegion) * 2);
+ quirk->mem = g_new0(MemoryRegion, 2);
quirk->nr_mem = 2;
quirk->data = rtl = g_malloc0(sizeof(*rtl));
rtl->vdev = vdev;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 8fadbcf..1fb868c 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -28,6 +28,7 @@
#include "config.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
+#include "hw/pci/pci_bridge.h"
#include "qemu/error-report.h"
#include "qemu/range.h"
#include "sysemu/kvm.h"
@@ -586,7 +587,7 @@
{
vfio_disable_interrupts(vdev);
- vdev->msi_vectors = g_malloc0(vdev->msix->entries * sizeof(VFIOMSIVector));
+ vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->msix->entries);
vdev->interrupt = VFIO_INT_MSIX;
@@ -622,7 +623,7 @@
vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev);
retry:
- vdev->msi_vectors = g_malloc0(vdev->nr_vectors * sizeof(VFIOMSIVector));
+ vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->nr_vectors);
for (i = 0; i < vdev->nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[i];
@@ -1524,13 +1525,38 @@
}
if (!pci_bus_is_express(vdev->pdev.bus)) {
+ PCIBus *bus = vdev->pdev.bus;
+ PCIDevice *bridge;
+
/*
- * Use express capability as-is on PCI bus. It doesn't make much
- * sense to even expose, but some drivers (ex. tg3) depend on it
- * and guests don't seem to be particular about it. We'll need
- * to revist this or force express devices to express buses if we
- * ever expose an IOMMU to the guest.
+ * Traditionally PCI device assignment exposes the PCIe capability
+ * as-is on non-express buses. The reason being that some drivers
+ * simply assume that it's there, for example tg3. However when
+ * we're running on a native PCIe machine type, like Q35, we need
+ * to hide the PCIe capability. The reason for this is twofold;
+ * first Windows guests get a Code 10 error when the PCIe capability
+ * is exposed in this configuration. Therefore express devices won't
+ * work at all unless they're attached to express buses in the VM.
+ * Second, a native PCIe machine introduces the possibility of fine
+ * granularity IOMMUs supporting both translation and isolation.
+ * Guest code to discover the IOMMU visibility of a device, such as
+ * IOMMU grouping code on Linux, is very aware of device types and
+ * valid transitions between bus types. An express device on a non-
+ * express bus is not a valid combination on bare metal systems.
+ *
+ * Drivers that require a PCIe capability to make the device
+ * functional are simply going to need to have their devices placed
+ * on a PCIe bus in the VM.
*/
+ while (!pci_bus_is_root(bus)) {
+ bridge = pci_bridge_get_device(bus);
+ bus = bridge->bus;
+ }
+
+ if (pci_bus_is_express(bus)) {
+ return 0;
+ }
+
} else if (pci_bus_is_root(vdev->pdev.bus)) {
/*
* On a Root Complex bus Endpoints become Root Complex Integrated
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
index 5c1156c..289b498 100644
--- a/hw/vfio/platform.c
+++ b/hw/vfio/platform.c
@@ -478,7 +478,7 @@
struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) };
VFIORegion *ptr;
- vdev->regions[i] = g_malloc0(sizeof(VFIORegion));
+ vdev->regions[i] = g_new0(VFIORegion, 1);
ptr = vdev->regions[i];
reg_info.index = i;
ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, ®_info);
