[PATCH v2 03/15] vfio/type1: Report iommu nesting info to userspace

[Liu Yi L <yi.l.liu@intel.com>]

This patch exports iommu nesting capability info to user space through
VFIO. User space is expected to check this info for supported uAPIs (e.g.
PASID alloc/free, bind page table, and cache invalidation) and the vendor
specific format information for first level/stage page table that will be
bound to.

The nesting info is available only after the nesting iommu type is set
for a container. Current implementation imposes one limitation - one
nesting container should include at most one group. The philosophy of
vfio container is having all groups/devices within the container share
the same IOMMU context. When vSVA is enabled, one IOMMU context could
include one 2nd-level address space and multiple 1st-level address spaces.
While the 2nd-leve address space is reasonably sharable by multiple groups
, blindly sharing 1st-level address spaces across all groups within the
container might instead break the guest expectation. In the future sub/
super container concept might be introduced to allow partial address space
sharing within an IOMMU context. But for now let's go with this restriction
by requiring singleton container for using nesting iommu features. Below
link has the related discussion about this decision.

https://lkml.org/lkml/2020/5/15/1028

Cc: Kevin Tian <kevin.tian@intel.com>
CC: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Eric Auger <eric.auger@redhat.com>
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
 drivers/vfio/vfio_iommu_type1.c | 73 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/vfio.h       |  9 +++++
 2 files changed, 82 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 402aad3..22432cf 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -71,6 +71,7 @@ struct vfio_iommu {
 	unsigned int		dma_avail;
 	bool			v2;
 	bool			nesting;
+	struct iommu_nesting_info *nesting_info;
 };
 
 struct vfio_domain {
@@ -125,6 +126,9 @@ struct vfio_regions {
 #define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)	\
 					(!list_empty(&iommu->domain_list))
 
+#define IS_DOMAIN_IN_CONTAINER(iommu)	((iommu->external_domain) || \
+					 (!list_empty(&iommu->domain_list)))
+
 static int put_pfn(unsigned long pfn, int prot);
 
 /*
@@ -1641,6 +1645,12 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 		}
 	}
 
+	/* Nesting type container can include only one group */
+	if (iommu->nesting && IS_DOMAIN_IN_CONTAINER(iommu)) {
+		mutex_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
 	group = kzalloc(sizeof(*group), GFP_KERNEL);
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!group || !domain) {
@@ -1700,6 +1710,36 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_domain;
 
+	/* Nesting cap info is available only after attaching */
+	if (iommu->nesting) {
+		struct iommu_nesting_info tmp;
+		struct iommu_nesting_info *info;
+
+		/* First get the size of vendor specific nesting info */
+		ret = iommu_domain_get_attr(domain->domain,
+					    DOMAIN_ATTR_NESTING_INFO,
+					    &tmp);
+		if (ret)
+			goto out_detach;
+
+		info = kzalloc(tmp.size, GFP_KERNEL);
+		if (!info) {
+			ret = -ENOMEM;
+			goto out_detach;
+		}
+
+		/* Now get the nesting info */
+		info->size = tmp.size;
+		ret = iommu_domain_get_attr(domain->domain,
+					    DOMAIN_ATTR_NESTING_INFO,
+					    info);
+		if (ret) {
+			kfree(info);
+			goto out_detach;
+		}
+		iommu->nesting_info = info;
+	}
+
 	/* Get aperture info */
 	iommu_domain_get_attr(domain->domain, DOMAIN_ATTR_GEOMETRY, &geo);
 
@@ -1801,6 +1841,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	return 0;
 
 out_detach:
+	kfree(iommu->nesting_info);
 	vfio_iommu_detach_group(domain, group);
 out_domain:
 	iommu_domain_free(domain->domain);
@@ -1998,6 +2039,8 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 					vfio_iommu_unmap_unpin_all(iommu);
 				else
 					vfio_iommu_unmap_unpin_reaccount(iommu);
+
+				kfree(iommu->nesting_info);
 			}
 			iommu_domain_free(domain->domain);
 			list_del(&domain->next);
@@ -2190,6 +2233,30 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,
 	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;
+	size_t size;
+
+	size = sizeof(*nesting_cap) + iommu->nesting_info->size;
+
+	header = vfio_info_cap_add(caps, size,
+				   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);
+
+	memcpy(&nesting_cap->info, iommu->nesting_info,
+	       iommu->nesting_info->size);
+
+	return 0;
+}
+
 static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
 				     unsigned long arg)
 {
@@ -2223,6 +2290,12 @@ static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
 	if (ret)
 		return ret;
 
+	if (iommu->nesting_info) {
+		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 015516b..26e3dce 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
+#include <linux/iommu.h>
 
 #define VFIO_API_VERSION	0
 
@@ -785,6 +786,14 @@ 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	flags;
+	__u8	info[];
+};
+
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
 
 /**
-- 
2.7.4