From: Liu Yi L <yi.l....@intel.com>

VFIO exposes IOMMU nesting translation (a.k.a dual stage translation)
capability to userspace. Thus applications like QEMU could support
vIOMMU with hardware's nesting translation capability for pass-through
devices. Before setting up nesting translation for pass-through devices,
QEMU and other applications need to learn the supported 1st-lvl/stage-1
translation structure format like page table format.

Take vSVA (virtual Shared Virtual Addressing) as an example, to support
vSVA for pass-through devices, QEMU setup nesting translation for pass-
through devices. The guest page table are configured to host as 1st-lvl/
stage-1 page table. Therefore, guest format should be compatible with
host side.

This patch reports the supported 1st-lvl/stage-1 page table format on the
current platform to userspace. QEMU and other alike applications should
use this format info when trying to setup IOMMU nesting translation on
host IOMMU.

Cc: Kevin Tian <kevin.t...@intel.com>
CC: Jacob Pan <jacob.jun....@linux.intel.com>
Cc: Alex Williamson <alex.william...@redhat.com>
Cc: Eric Auger <eric.au...@redhat.com>
Cc: Jean-Philippe Brucker <jean-philippe.bruc...@arm.com>
Signed-off-by: Liu Yi L <yi.l....@intel.com>
---
 drivers/vfio/vfio_iommu_type1.c | 79 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/vfio.h       |  7 ++++
 2 files changed, 86 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 1cf75f5..e0bbcfb 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2243,6 +2243,81 @@ static int vfio_iommu_type1_pasid_free(struct vfio_iommu 
*iommu,
        return ret;
 }
 
+static int vfio_iommu_get_pasid_format(struct vfio_iommu *iommu,
+                                       u32 *pasid_format)
+{
+       struct vfio_domain *domain;
+       u32 format = 0, tmp_format = 0;
+       int ret;
+
+       mutex_lock(&iommu->lock);
+       if (list_empty(&iommu->domain_list)) {
+               mutex_unlock(&iommu->lock);
+               return -EINVAL;
+       }
+
+       list_for_each_entry(domain, &iommu->domain_list, next) {
+               if (iommu_domain_get_attr(domain->domain,
+                       DOMAIN_ATTR_PASID_FORMAT, &format)) {
+                       ret = -EINVAL;
+                       format = 0;
+                       goto out_unlock;
+               }
+               /*
+                * format is always non-zero (the first format is
+                * IOMMU_PASID_FORMAT_INTEL_VTD which is 1). For
+                * the reason of potential different backed IOMMU
+                * formats, here we expect to have identical formats
+                * in the domain list, no miexed formats support.
+                * return -EINVAL to fail the attempt of setup
+                * VFIO_TYPE1_NESTING_IOMMU if non-identical formats
+                * are detected.
+                */
+               if (tmp_format && tmp_format != format) {
+                       ret = -EINVAL;
+                       format = 0;
+                       goto out_unlock;
+               }
+
+               tmp_format = format;
+       }
+       ret = 0;
+
+out_unlock:
+       if (format)
+               *pasid_format = format;
+       mutex_unlock(&iommu->lock);
+       return ret;
+}
+
+static int vfio_iommu_info_add_nesting_cap(struct vfio_iommu *iommu,
+                                        struct vfio_info_cap *caps)
+{
+       struct vfio_info_cap_header *header;
+       struct vfio_iommu_type1_info_cap_nesting *nesting_cap;
+       u32 format = 0;
+       int ret;
+
+       ret = vfio_iommu_get_pasid_format(iommu, &format);
+       if (ret) {
+               pr_warn("Failed to get domain format\n");
+               return ret;
+       }
+
+       header = vfio_info_cap_add(caps, sizeof(*nesting_cap) + sizeof(format),
+                                  VFIO_IOMMU_TYPE1_INFO_CAP_NESTING, 1);
+       if (IS_ERR(header))
+               return PTR_ERR(header);
+
+       nesting_cap = container_of(header,
+                               struct vfio_iommu_type1_info_cap_nesting,
+                               header);
+
+       nesting_cap->pasid_format = format;
+
+       return 0;
+}
+
 static int vfio_iommu_type1_set_pasid_quota(struct vfio_iommu *iommu,
                                            u32 quota)
 {
@@ -2313,6 +2388,10 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
                if (ret)
                        return ret;
 
+               ret = vfio_iommu_info_add_nesting_cap(iommu, &caps);
+               if (ret)
+                       return ret;
+
                if (caps.size) {
                        info.flags |= VFIO_IOMMU_INFO_CAPS;
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 62113be..633c07f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -748,6 +748,13 @@ struct vfio_iommu_type1_info_cap_iova_range {
        struct  vfio_iova_range iova_ranges[];
 };
 
+#define VFIO_IOMMU_TYPE1_INFO_CAP_NESTING  2
+
+struct vfio_iommu_type1_info_cap_nesting {
+       struct  vfio_info_cap_header header;
+       __u32   pasid_format;
+};
+
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
 
 /**
-- 
2.7.4

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Reply via email to