Hello Shameer,
On 1/2/26 16:35, Shameer Kolothum wrote:
Hi Cédric,
-----Original Message-----
From: Cédric Le Goater <[email protected]>
Sent: 15 December 2025 10:55
To: Shameer Kolothum <[email protected]>; qemu-
[email protected]; [email protected]
Cc: [email protected]; [email protected]; Jason Gunthorpe
<[email protected]>; Nicolin Chen <[email protected]>;
[email protected]; [email protected]; Nathan Chen
<[email protected]>; Matt Ochs <[email protected]>;
[email protected]; [email protected];
[email protected]; [email protected];
[email protected]; [email protected]; [email protected];
Krishnakant Jaju <[email protected]>
Subject: Re: [PATCH v6 32/33] vfio: Synthesize vPASID capability to VM
External email: Use caution opening links or attachments
On 11/20/25 14:22, Shameer Kolothum wrote:
From: Yi Liu <[email protected]>
If user wants to expose PASID capability in vIOMMU, then VFIO would also
need to report the PASID cap for this device if the underlying hardware
supports it as well.
As a start, this chooses to put the vPASID cap in the last 8 bytes of the
vconfig space. This is a choice in the good hope of no conflict with any
existing cap or hidden registers. For the devices that has hidden registers,
user should figure out a proper offset for the vPASID cap. This may require
an option for user to config it. Here we leave it as a future extension.
There are more discussions on the mechanism of finding the proper offset.
https://lore.kernel.org/kvm/BN9PR11MB5276318969A212AD0649C7BE8CBE2
@BN9PR11MB5276.namprd11.prod.outlook.com/
Since we add a check to ensure the vIOMMU supports PASID, only devices
under those vIOMMUs can synthesize the vPASID capability. This gives
users control over which devices expose vPASID.
Signed-off-by: Yi Liu <[email protected]>
Tested-by: Zhangfei Gao <[email protected]>
Reviewed-by: Jonathan Cameron <[email protected]>
Signed-off-by: Shameer Kolothum <[email protected]>
---
hw/vfio/pci.c | 38 ++++++++++++++++++++++++++++++++++++++
include/hw/iommu.h | 1 +
2 files changed, 39 insertions(+)
I just noticed another problem with this change. It relies on the
availability of the HostIOMMUDevice which doesn't exist with VFIO
mdev devices, such as vGPU. QEMU simply coredumps :/
We will have to check/protect QEMU in some ways. I need to take
a closer look because mdev handling seems to be spread across
the code and may need to be improved first.
I did attempt a rework on this patch and the previous one(patch #31) to
address the above issue and to avoid the #ifdef CONFIG_IOMMUFD in
vfio. Please find below:
Patch #1:
This adds get_pasid_info to HostIOMMUDeviceClass. One thing I am not
sure, below is to use #ifdef CONFIG_LINUX or not. Please take a look
and let me know if this is the right direction or not.
I don't think CONFIG_LINUX is needed there because the declarations
are not specific to linux. A simple way to try a windows build is with :
--cross-prefix=x86_64-w64-mingw32-
you might need to add :
--disable-sdl
and targets should be aarch64-softmmu,ppc64-softmmu,x86_64-softmmu,s390x-softmmu
You should resend a v7, in whole or in parts, as you wish.
Thanks,
C.
From e1305b0d44b2002778059decc3d6b220414b0589 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <[email protected]>
Date: Fri, 2 Jan 2026 14:50:58 +0000
Subject: [PATCH 1/2] backends/iommufd: Add get_pasid_info
TODO:
Signed-off-by: Shameer Kolothum <[email protected]>
---
backends/iommufd.c | 17 +++++++++++++++++
include/system/host_iommu_device.h | 19 +++++++++++++++++++
2 files changed, 36 insertions(+)
diff --git a/backends/iommufd.c b/backends/iommufd.c
index 2c9ce1a03a..7beff372ba 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -634,11 +634,28 @@ static int hiod_iommufd_get_cap(HostIOMMUDevice *hiod,
int cap, Error **errp)
}
}
+static bool hiod_iommufd_get_pasid_info(HostIOMMUDevice *hiod,
+ HostIOMMUDevicePasidInfo *pasid_info)
+{
+ HostIOMMUDeviceCaps *caps = &hiod->caps;
+
+ if (!caps->max_pasid_log2) {
+ return false;
+ }
+
+ g_assert(pasid_info);
+ pasid_info->exec_perm = (caps->hw_caps & IOMMU_HW_CAP_PCI_PASID_EXEC);
+ pasid_info->priv_mod = (caps->hw_caps & IOMMU_HW_CAP_PCI_PASID_PRIV);
+ pasid_info->max_pasid_log2 = caps->max_pasid_log2;
+ return true;
+}
+
static void hiod_iommufd_class_init(ObjectClass *oc, const void *data)
{
HostIOMMUDeviceClass *hioc = HOST_IOMMU_DEVICE_CLASS(oc);
hioc->get_cap = hiod_iommufd_get_cap;
+ hioc->get_pasid_info = hiod_iommufd_get_pasid_info;
};
static const TypeInfo types[] = {
diff --git a/include/system/host_iommu_device.h
b/include/system/host_iommu_device.h
index bfb2b60478..6e62f643fe 100644
--- a/include/system/host_iommu_device.h
+++ b/include/system/host_iommu_device.h
@@ -22,6 +22,13 @@ typedef union VendorCaps {
struct iommu_hw_info_arm_smmuv3 smmuv3;
} VendorCaps;
+
+typedef struct HostIOMMUDevicePasidInfo {
+ bool exec_perm;
+ bool priv_mod;
+ uint64_t max_pasid_log2;
+} HostIOMMUDevicePasidInfo;
+
/**
* struct HostIOMMUDeviceCaps - Define host IOMMU device capabilities.
*
@@ -116,6 +123,18 @@ struct HostIOMMUDeviceClass {
* @hiod: handle to the host IOMMU device
*/
uint64_t (*get_page_size_mask)(HostIOMMUDevice *hiod);
+#ifdef CONFIG_LINUX
+ /**
+ * @get_pasid_info: Return the PASID information associated with the Host
+ * IOMMU device.
+ *
+ * @pasid_info: If success, returns the PASID related information.
+ *
+ * Returns: true on success, false on failure.
+ */
+ bool (*get_pasid_info)(HostIOMMUDevice *hiod,
+ HostIOMMUDevicePasidInfo *pasid_info);
+#endif
};
/*
--
Patch #2:
This adds a check for mdev to avoid the coredump mentioned above.
Please let me know If you have a nicer/broader solution to address this
for mdev devices.
From bbb54b349fccd61d8dab6b95be11c42510db3f95 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <[email protected]>
Date: Fri, 2 Jan 2026 14:52:26 +0000
Subject: [PATCH 2/2] hw/vfio/pci: Add pasid cap synthesize
TODO:
Signed-off-by: Shameer Kolothum <[email protected]>
---
hw/vfio/pci.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 45 insertions(+)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 8b8bc5a421..5f1a93cfc8 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -24,6 +24,7 @@
#include <sys/ioctl.h>
#include "hw/hw.h"
+#include "hw/iommu.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "hw/pci/pci_bridge.h"
@@ -2498,9 +2499,41 @@ static int vfio_setup_rebar_ecap(VFIOPCIDevice *vdev,
uint16_t pos)
return 0;
}
+/*
+ * Try to retrieve PASID CAP through IOMMUFD APIs. If available, adds the
+ * PASID capability in the end of the PCIe config space.
+ * TODO: Add support for enabling pasid at a safe offset.
+ */
+static void vfio_pci_synthesize_pasid_cap(VFIOPCIDevice *vdev)
+{
+ HostIOMMUDevice *hiod = vdev->vbasedev.hiod;
+ PCIDevice *pdev = PCI_DEVICE(vdev);
+ HostIOMMUDeviceClass *hiodc;
+ HostIOMMUDevicePasidInfo pasid_info;
+
+ if (vdev->vbasedev.mdev) {
+ return;
+ }
+
+ hiodc = HOST_IOMMU_DEVICE_GET_CLASS(hiod);
+ if (!hiodc->get_pasid_info ||
+ !(pci_device_get_viommu_flags(pdev) & VIOMMU_FLAG_PASID_SUPPORTED)) {
+ return;
+ }
+
+ if (hiodc->get_pasid_info(hiod, &pasid_info)) {
+ pcie_pasid_init(pdev, PCIE_CONFIG_SPACE_SIZE -
PCI_EXT_CAP_PASID_SIZEOF,
+ pasid_info.max_pasid_log2, pasid_info.exec_perm,
+ pasid_info.priv_mod);
+ /* PASID capability is fully emulated by QEMU */
+ memset(vdev->emulated_config_bits + pdev->exp.pasid_cap, 0xff, 8);
+ }
+}
+
static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
{
PCIDevice *pdev = PCI_DEVICE(vdev);
+ bool pasid_cap_added = false;
uint32_t header;
uint16_t cap_id, next, size;
uint8_t cap_ver;
@@ -2578,12 +2611,24 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
pcie_add_capability(pdev, cap_id, cap_ver, next, size);
}
break;
+ /*
+ * VFIO kernel does not expose the PASID CAP today. We may synthesize
+ * one later through IOMMUFD APIs. If VFIO ever starts exposing it,
+ * record its presence here so we do not create a duplicate CAP.
+ */
+ case PCI_EXT_CAP_ID_PASID:
+ pasid_cap_added = true;
+ /* fallthrough */
default:
pcie_add_capability(pdev, cap_id, cap_ver, next, size);
}
}
+ if (!pasid_cap_added) {
+ vfio_pci_synthesize_pasid_cap(vdev);
+ }
+
/* Cleanup chain head ID if necessary */
if (pci_get_word(pdev->config + PCI_CONFIG_SPACE_SIZE) == 0xFFFF) {
pci_set_word(pdev->config + PCI_CONFIG_SPACE_SIZE, 0);
--
2.43.0
Please let me know your thoughts.
Thanks,
Shameer
