[PATCH v3 21/22] iommu/amd: Add translation DTE and VFctrl TransDevID helpers
From: Suravee Suthikulpanit
Date: Mon Jun 29 2026 - 11:49:05 EST
The hardware vIOMMU uses a per-VM translate device ID (TransDevID) to
index the host device table when guest IOMMU traffic needs GPA->SPA
translation. The VF Control guest miscellaneous register tells the
IOMMU which TransDevID to use; the corresponding device table entry
(DTE) points at the nested IOMMU v1 page table that performs the walk
from guest physical to system physical addresses.
Add amd_iommu_set_translate_dte() and amd_iommu_clear_translate_dte()
to install or clear that DTE for a given TransDevID slot through
iommu_dev_data and the existing DTE update path, restoring IVRS
persistent bits via amd_iommu_make_clear_dte() on teardown. Add
amd_iommu_update_vfctrl_mmio_translate_devid() to publish the
TransDevID in VFctrl guest-misc MMIO, and
VIOMMU_VFCTRL_GUEST_MISC_CONTROL_OFFSET for the register offset.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
---
drivers/iommu/amd/amd_iommu_types.h | 1 +
drivers/iommu/amd/iommu.c | 78 ++++++++++++++++++++++++++++-
2 files changed, 77 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 91cdb61b5254..cd10e33c1317 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -495,6 +495,7 @@ extern bool amdr_ivrs_remap_support;
/* VIOMMU stuff */
#define VIOMMU_VF_MMIO_ENTRY_SIZE 4096
#define VIOMMU_VFCTRL_MMIO_ENTRY_SIZE 64
+#define VIOMMU_VFCTRL_GUEST_MISC_CONTROL_OFFSET 0x10
/* Host ioremap/request_mem_region sizes for VF / VF_CNTL BARs */
#define VIOMMU_VF_MMIO_MAP_SIZE 0x10000000UL
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index fd25c4c361f3..410c2f91064a 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -213,7 +213,12 @@ void amd_iommu_update_dte(struct amd_iommu *iommu,
struct dev_table_entry *new)
{
update_dte256(iommu, dev_data, new);
- clone_aliases(iommu, dev_data->dev);
+ /*
+ * The dev_data for trans_devid does not have struct dev.
+ * So clone_aliases is not supported for translate-device-id.
+ */
+ if (dev_data->dev)
+ clone_aliases(iommu, dev_data->dev);
device_flush_dte(iommu, dev_data);
amd_iommu_completion_wait(iommu);
}
@@ -1747,7 +1752,11 @@ static int device_flush_dte(struct amd_iommu *iommu, struct iommu_dev_data *dev_
u16 alias;
int ret;
- if (dev_is_pci(dev_data->dev))
+ /*
+ * The dev_data for trans_devid does not have struct dev.
+ * So, it is not considered as a PCI device.
+ */
+ if (dev_data->dev && dev_is_pci(dev_data->dev))
pdev = to_pci_dev(dev_data->dev);
if (pdev)
@@ -3281,6 +3290,71 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
return true;
}
+#if IS_ENABLED(CONFIG_AMD_IOMMU_IOMMUFD)
+
+void amd_iommu_update_vfctrl_mmio_translate_devid(struct amd_iommu *iommu,
+ u16 gid, u32 devid)
+{
+ writeq((devid & 0xFFFFULL) << 16,
+ VIOMMU_VFCTRL_MMIO_BASE(iommu, gid) +
+ VIOMMU_VFCTRL_GUEST_MISC_CONTROL_OFFSET);
+}
+
+int amd_iommu_set_translate_dte(struct amd_iommu *iommu,
+ struct protection_domain *pdom,
+ u16 gid, u32 trans_devid)
+{
+ struct dev_table_entry new = {};
+ struct iommu_dev_data *trans_dev_data;
+ struct pt_iommu_amdv1_hw_info pt_info;
+
+ trans_dev_data = search_dev_data(iommu, trans_devid);
+ if (!trans_dev_data) {
+ trans_dev_data = amd_iommu_alloc_dev_data(iommu, trans_devid);
+ if (!trans_dev_data) {
+ pr_err("%s: Failed to allocate dev_data for translate-device-id %#x\n",
+ __func__, trans_devid);
+ return -ENOMEM;
+ }
+ }
+
+ trans_dev_data->dev = NULL;
+ trans_dev_data->devid = trans_devid;
+ trans_dev_data->domain = pdom;
+ trans_dev_data->gid = gid;
+
+ amd_iommu_make_clear_dte(iommu, trans_devid, &new);
+ /* Setup DTE for v1 page table at the offset specified by trans_devid */
+ pt_iommu_amdv1_hw_info(&pdom->amdv1, &pt_info);
+
+ pr_debug("%s: gid=%#x, iommu_devid=%#x, devid=%#x, host_pt_root=%#llx, mode=%#x\n",
+ __func__, gid, iommu->devid, trans_devid, pt_info.host_pt_root, pt_info.mode);
+
+ amd_iommu_set_dte_v1(trans_dev_data, pdom, pdom->id, &pt_info, &new);
+ amd_iommu_update_dte(iommu, trans_dev_data, &new);
+ return 0;
+}
+
+void amd_iommu_clear_translate_dte(struct amd_iommu *iommu, u32 trans_devid)
+{
+ struct dev_table_entry new = {};
+ struct iommu_dev_data *trans_dev_data;
+
+ pr_debug("%s: iommu_devid=%#x, trans_devid=%#x\n",
+ __func__, iommu->devid, trans_devid);
+
+ trans_dev_data = search_dev_data(iommu, trans_devid);
+ if (!trans_dev_data) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ amd_iommu_make_clear_dte(iommu, trans_devid, &new);
+ amd_iommu_update_dte(iommu, trans_dev_data, &new);
+ amd_iommu_free_dev_data(iommu, trans_dev_data);
+}
+#endif /* CONFIG_AMD_IOMMU_IOMMUFD */
+
const struct iommu_ops amd_iommu_ops = {
.capable = amd_iommu_capable,
.hw_info = amd_iommufd_hw_info,
--
2.34.1