[PATCH v11 8/8] vfio/type1: return MSI geometry through VFIO_IOMMU_GET_INFO capability chains

[Eric Auger]

This patch allows the user-space to retrieve the MSI geometry. The
implementation is based on capability chains, now also added to
VFIO_IOMMU_GET_INFO.

The returned info comprise:
- whether the MSI IOVA are constrained to a reserved range (x86 case) and
  in the positive, the start/end of the aperture,
- or whether the IOVA aperture need to be set by the userspace. In that
  case, the size and alignment of the IOVA window to be provided are
  returned.

In case the userspace must provide the IOVA aperture, we currently report
a size/alignment based on all the doorbells registered by the host kernel.
This may exceed the actual needs.

Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>

---
v9 -> v10:
- move cap_offset after iova_pgsizes
- replace __u64 alignment by __u32 order
- introduce __u32 flags in vfio_iommu_type1_info_cap_msi_geometry and
  fix alignment
- call msi-doorbell API to compute the size/alignment

v8 -> v9:
- use iommu_msi_supported flag instead of programmable
- replace IOMMU_INFO_REQUIRE_MSI_MAP flag by a more sophisticated
  capability chain, reporting the MSI geometry

v7 -> v8:
- use iommu_domain_msi_geometry

v6 -> v7:
- remove the computation of the number of IOVA pages to be provisionned.
  This number depends on the domain/group/device topology which can
  dynamically change. Let's rely instead rely on an arbitrary max depending
  on the system

v4 -> v5:
- move msi_info and ret declaration within the conditional code

v3 -> v4:
- replace former vfio_domains_require_msi_mapping by
  more complex computation of MSI mapping requirements, especially the
  number of pages to be provided by the user-space.
- reword patch title

RFC v1 -> v1:
- derived from
  [RFC PATCH 3/6] vfio: Extend iommu-info to return MSIs automap state
- renamed allow_msi_reconfig into require_msi_mapping
- fixed VFIO_IOMMU_GET_INFO
---
 drivers/vfio/vfio_iommu_type1.c | 78 ++++++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/vfio.h       | 32 ++++++++++++++++-
 2 files changed, 108 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 7daab53..7e38207 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -38,6 +38,8 @@
 #include <linux/workqueue.h>
 #include <linux/msi-iommu.h>
 #include <linux/msi-doorbell.h>
+#include <linux/irqdomain.h>
+#include <linux/msi.h>
 
 #define DRIVER_VERSION  "0.2"
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@xxxxxxxxxx>"
@@ -1103,6 +1105,55 @@ static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
 	return ret;
 }
 
+static int compute_msi_geometry_caps(struct vfio_iommu *iommu,
+				     struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_cap_msi_geometry *vfio_msi_geometry;
+	unsigned long order = __ffs(vfio_pgsize_bitmap(iommu));
+	struct iommu_domain_msi_geometry msi_geometry;
+	struct vfio_info_cap_header *header;
+	struct vfio_domain *d;
+	bool reserved;
+	size_t size;
+
+	mutex_lock(&iommu->lock);
+	/* All domains have same require_msi_map property, pick first */
+	d = list_first_entry(&iommu->domain_list, struct vfio_domain, next);
+	iommu_domain_get_attr(d->domain, DOMAIN_ATTR_MSI_GEOMETRY,
+			      &msi_geometry);
+	reserved = !msi_geometry.iommu_msi_supported;
+
+	mutex_unlock(&iommu->lock);
+
+	size = sizeof(*vfio_msi_geometry);
+	header = vfio_info_cap_add(caps, size,
+				   VFIO_IOMMU_TYPE1_INFO_CAP_MSI_GEOMETRY, 1);
+
+	if (IS_ERR(header))
+		return PTR_ERR(header);
+
+	vfio_msi_geometry = container_of(header,
+				struct vfio_iommu_type1_info_cap_msi_geometry,
+				header);
+
+	vfio_msi_geometry->flags = reserved;
+	if (reserved) {
+		vfio_msi_geometry->aperture_start = msi_geometry.aperture_start;
+		vfio_msi_geometry->aperture_end = msi_geometry.aperture_end;
+		return 0;
+	}
+
+	vfio_msi_geometry->order = order;
+	/*
+	 * we compute a system-wide requirement based on all the registered
+	 * doorbells
+	 */
+	vfio_msi_geometry->size =
+		msi_doorbell_pages(order) * ((uint64_t) 1 << order);
+
+	return 0;
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -1124,8 +1175,10 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		}
 	} else if (cmd == VFIO_IOMMU_GET_INFO) {
 		struct vfio_iommu_type1_info info;
+		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+		int ret;
 
-		minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
+		minsz = offsetofend(struct vfio_iommu_type1_info, cap_offset);
 
 		if (copy_from_user(&info, (void __user *)arg, minsz))
 			return -EFAULT;
@@ -1137,6 +1190,29 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 
 		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
 
+		ret = compute_msi_geometry_caps(iommu, &caps);
+		if (ret)
+			return ret;
+
+		if (caps.size) {
+			info.flags |= VFIO_IOMMU_INFO_CAPS;
+			if (info.argsz < sizeof(info) + caps.size) {
+				info.argsz = sizeof(info) + caps.size;
+				info.cap_offset = 0;
+			} else {
+				vfio_info_cap_shift(&caps, sizeof(info));
+				if (copy_to_user((void __user *)arg +
+						sizeof(info), caps.buf,
+						caps.size)) {
+					kfree(caps.buf);
+					return -EFAULT;
+				}
+				info.cap_offset = sizeof(info);
+			}
+
+			kfree(caps.buf);
+		}
+
 		return copy_to_user((void __user *)arg, &info, minsz) ?
 			-EFAULT : 0;
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 4a9dbc2..8dae013 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -488,7 +488,35 @@ struct vfio_iommu_type1_info {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_IOMMU_INFO_PGSIZES (1 << 0)	/* supported page sizes info */
-	__u64	iova_pgsizes;		/* Bitmap of supported page sizes */
+#define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */
+	__u64	iova_pgsizes;	/* Bitmap of supported page sizes */
+	__u32	__resv;
+	__u32   cap_offset;	/* Offset within info struct of first cap */
+};
+
+#define VFIO_IOMMU_TYPE1_INFO_CAP_MSI_GEOMETRY	1
+
+/*
+ * The MSI geometry capability allows to report the MSI IOVA geometry:
+ * - either the MSI IOVAs are constrained within a reserved IOVA aperture
+ *   whose boundaries are given by [@aperture_start, @aperture_end].
+ *   this is typically the case on x86 host. The userspace is not allowed
+ *   to map userspace memory at IOVAs intersecting this range using
+ *   VFIO_IOMMU_MAP_DMA.
+ * - or the MSI IOVAs are not requested to belong to any reserved range;
+ *   in that case the userspace must provide an IOVA window characterized by
+ *   @size and @alignment using VFIO_IOMMU_MAP_DMA with RESERVED_MSI_IOVA flag.
+ */
+struct vfio_iommu_type1_info_cap_msi_geometry {
+	struct vfio_info_cap_header header;
+	__u32 flags;
+#define VFIO_IOMMU_MSI_GEOMETRY_RESERVED (1 << 0) /* reserved geometry */
+	/* not reserved */
+	__u32 order; /* iommu page order used for aperture alignment*/
+	__u64 size; /* IOVA aperture size (bytes) the userspace must provide */
+	/* reserved */
+	__u64 aperture_start;
+	__u64 aperture_end;
 };
 
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
@@ -503,6 +531,8 @@ struct vfio_iommu_type1_info {
  * IOVA region that will be used on some platforms to map the host MSI frames.
  * In that specific case, vaddr is ignored. Once registered, an MSI reserved
  * IOVA region stays until the container is closed.
+ * The requirement for provisioning such reserved IOVA range can be checked by
+ * checking the VFIO_IOMMU_TYPE1_INFO_CAP_MSI_GEOMETRY capability.
  */
 struct vfio_iommu_type1_dma_map {
 	__u32	argsz;
-- 
1.9.1