[PATCH v5 1/4] vfio: implement iommu driver capabilities with an enum

[PATCH v5 1/4] vfio: implement iommu driver capabilities with an enum

[Baptiste Reynal]

From: Antonios Motakis <a.motakis@virtualopensystems.com>

Currently a VFIO driver's IOMMU capabilities are encoded as a series of
numerical defines. Replace this with an enum for future maintainability.

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: Baptiste Reynal <b.reynal@virtualopensystems.com>
---
 include/uapi/linux/vfio.h | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 82889c3..5fb3d46 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -19,22 +19,20 @@
 
 /* Kernel & User level defines for VFIO IOCTLs. */
 
-/* Extensions */
-
-#define VFIO_TYPE1_IOMMU		1
-#define VFIO_SPAPR_TCE_IOMMU		2
-#define VFIO_TYPE1v2_IOMMU		3
 /*
- * IOMMU enforces DMA cache coherence (ex. PCIe NoSnoop stripping).  This
- * capability is subject to change as groups are added or removed.
+ * Capabilities exposed by the VFIO IOMMU driver. Some capabilities are subject
+ * to change as groups are added or removed.
  */
-#define VFIO_DMA_CC_IOMMU		4
-
-/* Check if EEH is supported */
-#define VFIO_EEH			5
+enum vfio_iommu_cap {
+	VFIO_TYPE1_IOMMU = 1,
+	VFIO_SPAPR_TCE_IOMMU = 2,
+	VFIO_TYPE1v2_IOMMU = 3,
+	VFIO_DMA_CC_IOMMU = 4,		/* IOMMU enforces DMA cache coherence
+					   (ex. PCIe NoSnoop stripping) */
+	VFIO_EEH = 5,			/* Check if EEH is supported */
+	VFIO_TYPE1_NESTING_IOMMU = 6,	/* Two-stage IOMMU, implies v2  */
+};
 
-/* Two-stage IOMMU */
-#define VFIO_TYPE1_NESTING_IOMMU	6	/* Implies v2 */
 
 /*
  * The IOCTL interface is designed for extensibility by embedding the
-- 
2.3.1

[PATCH v5 2/4] vfio: introduce the VFIO_DMA_MAP_FLAG_NOEXEC flag

[Baptiste Reynal]

From: Antonios Motakis <a.motakis@virtualopensystems.com>

We introduce the VFIO_DMA_MAP_FLAG_NOEXEC flag to the VFIO dma map call,
and expose its availability via the capability VFIO_DMA_NOEXEC_IOMMU.
This way the user can control whether the XN flag will be set on the
requested mappings. The IOMMU_NOEXEC flag needs to be available for all
the IOMMUs of the container used.

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: Baptiste Reynal <b.reynal@virtualopensystems.com>
---
 include/uapi/linux/vfio.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5fb3d46..30801a7 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -31,6 +31,7 @@ enum vfio_iommu_cap {
 					   (ex. PCIe NoSnoop stripping) */
 	VFIO_EEH = 5,			/* Check if EEH is supported */
 	VFIO_TYPE1_NESTING_IOMMU = 6,	/* Two-stage IOMMU, implies v2  */
+	VFIO_DMA_NOEXEC_IOMMU = 7,
 };
 
 
@@ -397,12 +398,17 @@ struct vfio_iommu_type1_info {
  *
  * Map process virtual addresses to IO virtual addresses using the
  * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required.
+ *
+ * To use the VFIO_DMA_MAP_FLAG_NOEXEC flag, the container must support the
+ * VFIO_DMA_NOEXEC_IOMMU capability. If mappings are created using this flag,
+ * any groups subsequently added to the container must support this capability.
  */
 struct vfio_iommu_type1_dma_map {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_DMA_MAP_FLAG_READ (1 << 0)		/* readable from device */
 #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1)	/* writable from device */
+#define VFIO_DMA_MAP_FLAG_NOEXEC (1 << 2)	/* not executable from device */
 	__u64	vaddr;				/* Process virtual address */
 	__u64	iova;				/* IO virtual address */
 	__u64	size;				/* Size of mapping (bytes) */
-- 
2.3.1

[PATCH v5 3/4] vfio: type1: replace vfio_domains_have_iommu_cache with generic function

[Baptiste Reynal]

From: Antonios Motakis <a.motakis@virtualopensystems.com>

Replace the function vfio_domains_have_iommu_cache() with a more generic
function vfio_domains_have_iommu_cap() which allows to check all domains
of an vfio_iommu structure for a given cached capability.

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: Baptiste Reynal <b.reynal@virtualopensystems.com>
---
 drivers/vfio/vfio_iommu_type1.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 57d8c37..a5847e8 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -82,6 +82,23 @@ struct vfio_group {
 	struct list_head	next;
 };
 
+static int vfio_domains_have_iommu_cap(struct vfio_iommu *iommu, int cap)
+{
+	struct vfio_domain *domain;
+	int ret = 1;
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		if (!(domain->domain->ops->capable(cap))) {
+			ret = 0;
+			break;
+		}
+	}
+	mutex_unlock(&iommu->lock);
+
+	return ret;
+}
+
 /*
  * This code handles mapping and unmapping of user data buffers
  * into DMA'ble space using the IOMMU
@@ -935,23 +952,6 @@ static void vfio_iommu_type1_release(void *iommu_data)
 	kfree(iommu);
 }
 
-static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
-{
-	struct vfio_domain *domain;
-	int ret = 1;
-
-	mutex_lock(&iommu->lock);
-	list_for_each_entry(domain, &iommu->domain_list, next) {
-		if (!(domain->prot & IOMMU_CACHE)) {
-			ret = 0;
-			break;
-		}
-	}
-	mutex_unlock(&iommu->lock);
-
-	return ret;
-}
-
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -967,7 +967,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		case VFIO_DMA_CC_IOMMU:
 			if (!iommu)
 				return 0;
-			return vfio_domains_have_iommu_cache(iommu);
+			return vfio_domains_have_iommu_cap(iommu,
+						  IOMMU_CAP_CACHE_COHERENCY);
 		default:
 			return 0;
 		}
-- 
2.3.1

[PATCH v5 4/4] vfio: type1: implement the VFIO_DMA_MAP_FLAG_NOEXEC flag

[Baptiste Reynal]

From: Antonios Motakis <a.motakis@virtualopensystems.com>

Some IOMMU drivers, such as the ARM SMMU driver, make available the
IOMMU_NOEXEC flag to set the page tables for a device as XN (execute never).
This affects devices such as the ARM PL330 DMA Controller, which respects
this flag and will refuse to fetch DMA instructions from memory where the
XN flag has been set.

The flag can be used only if all IOMMU domains behind the container support
the IOMMU_NOEXEC flag. Also, if any mappings are created with the flag, any
new domains with devices will have to support it as well.

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: Baptiste Reynal <b.reynal@virtualopensystems.com>
---
 drivers/vfio/vfio_iommu_type1.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index a5847e8..ec313e5 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -591,6 +591,12 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	if (!prot || !size || (size | iova | vaddr) & mask)
 		return -EINVAL;
 
+	if (map->flags & VFIO_DMA_MAP_FLAG_NOEXEC) {
+		if (!vfio_domains_have_iommu_cap(iommu, IOMMU_CAP_NOEXEC))
+			return -EINVAL;
+		prot |= IOMMU_NOEXEC;
+	}
+
 	/* Don't allow IOVA or virtual address wrap */
 	if (iova + size - 1 < iova || vaddr + size - 1 < vaddr)
 		return -EINVAL;
@@ -672,11 +678,20 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 
 	for (; n; n = rb_next(n)) {
 		struct vfio_dma *dma;
+		const struct iommu_ops *ops = domain->domain->ops;
 		dma_addr_t iova;
 
 		dma = rb_entry(n, struct vfio_dma, node);
 		iova = dma->iova;
 
+		/*
+		 * if any of the mappings to be replayed has the NOEXEC flag
+		 * set, then the new iommu domain must support it
+		 */
+		if ((dma->prot & IOMMU_NOEXEC) &&
+				!(ops->capable(IOMMU_CAP_NOEXEC)))
+			return -EINVAL;
+
 		while (iova < dma->iova + dma->size) {
 			phys_addr_t phys = iommu_iova_to_phys(d->domain, iova);
 			size_t size;
@@ -969,6 +984,11 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 				return 0;
 			return vfio_domains_have_iommu_cap(iommu,
 						  IOMMU_CAP_CACHE_COHERENCY);
+		case VFIO_DMA_NOEXEC_IOMMU:
+			if (!iommu)
+				return 0;
+			return vfio_domains_have_iommu_cap(iommu,
+							   IOMMU_CAP_NOEXEC);
 		default:
 			return 0;
 		}
@@ -992,7 +1012,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 	} else if (cmd == VFIO_IOMMU_MAP_DMA) {
 		struct vfio_iommu_type1_dma_map map;
 		uint32_t mask = VFIO_DMA_MAP_FLAG_READ |
-				VFIO_DMA_MAP_FLAG_WRITE;
+				VFIO_DMA_MAP_FLAG_WRITE |
+				VFIO_DMA_MAP_FLAG_NOEXEC;
 
 		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
 
-- 
2.3.1