[PATCH v7 4/7] vfio: allow reserved iova registration
From: Eric Auger
Date: Tue Apr 19 2016 - 13:25:17 EST
The user is allowed to [un]register a reserved IOVA range by using the
DMA MAP API and setting the new flag: VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA.
It provides the base address and the size. This region is stored in the
vfio_dma rb tree. At that point the iova range is not mapped to any target
address yet. The host kernel will use those iova when needed, typically
when the VFIO-PCI driver allocates its MSIs.
Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@xxxxxxxxxxxxx>
---
v6 -> v7:
- use iommu_free_reserved_iova_domain
- convey prot attributes downto dma-reserved-iommu iova domain creation
- reserved bindings teardown now performed on iommu domain destruction
- rename VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA into
VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA
- change title
- pass the protection attribute to dma-reserved-iommu API
v3 -> v4:
- use iommu_alloc/free_reserved_iova_domain exported by dma-reserved-iommu
- protect vfio_register_reserved_iova_range implementation with
CONFIG_IOMMU_DMA_RESERVED
- handle unregistration by user-space and on vfio_iommu_type1 release
v1 -> v2:
- set returned value according to alloc_reserved_iova_domain result
- free the iova domains in case any error occurs
RFC v1 -> v1:
- takes into account Alex comments, based on
[RFC PATCH 1/6] vfio: Add interface for add/del reserved iova region:
- use the existing dma map/unmap ioctl interface with a flag to register
a reserved IOVA range. A single reserved iova region is allowed.
---
drivers/vfio/vfio_iommu_type1.c | 138 +++++++++++++++++++++++++++++++++++++++-
include/uapi/linux/vfio.h | 9 ++-
2 files changed, 145 insertions(+), 2 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 93c17d9..fa6b8b1 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -454,6 +454,27 @@ static void vfio_destroy_reserved(struct vfio_iommu *iommu)
iommu_free_reserved_iova_domain(d->domain);
}
+static int vfio_create_reserved(struct vfio_iommu *iommu,
+ dma_addr_t iova, size_t size,
+ int prot, unsigned long order)
+{
+ struct vfio_domain *d;
+ int ret = 0;
+
+ list_for_each_entry(d, &iommu->domain_list, next) {
+ ret = iommu_alloc_reserved_iova_domain(d->domain, iova,
+ size, prot, order);
+ if (ret)
+ break;
+ }
+
+ if (ret) {
+ list_for_each_entry(d, &iommu->domain_list, next)
+ iommu_free_reserved_iova_domain(d->domain);
+ }
+ return ret;
+}
+
static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
{
if (likely(dma->type == VFIO_IOVA_USER))
@@ -705,6 +726,110 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
return ret;
}
+static int vfio_register_reserved_iova_range(struct vfio_iommu *iommu,
+ struct vfio_iommu_type1_dma_map *map)
+{
+ dma_addr_t iova = map->iova;
+ size_t size = map->size;
+ int ret = 0, prot = 0;
+ struct vfio_dma *dma;
+ unsigned long order;
+ uint64_t mask;
+
+ /* Verify that none of our __u64 fields overflow */
+ if (map->size != size || map->iova != iova)
+ return -EINVAL;
+
+ order = __ffs(vfio_pgsize_bitmap(iommu));
+ mask = ((uint64_t)1 << order) - 1;
+
+ WARN_ON(mask & PAGE_MASK);
+
+ if (!size || (size | iova) & mask)
+ return -EINVAL;
+
+ /* Don't allow IOVA address wrap */
+ if (iova + size - 1 < iova)
+ return -EINVAL;
+
+ mutex_lock(&iommu->lock);
+
+ if (vfio_find_dma(iommu, iova, size, VFIO_IOVA_ANY)) {
+ ret = -EEXIST;
+ goto unlock;
+ }
+
+ dma = kzalloc(sizeof(*dma), GFP_KERNEL);
+ if (!dma) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
+
+ dma->iova = iova;
+ dma->size = size;
+ dma->type = VFIO_IOVA_RESERVED;
+
+ if (map->flags & VFIO_DMA_MAP_FLAG_READ)
+ prot = IOMMU_READ;
+ if (map->flags & VFIO_DMA_MAP_FLAG_WRITE)
+ prot |= IOMMU_WRITE;
+
+ ret = vfio_create_reserved(iommu, iova, size, prot, order);
+ if (ret)
+ goto free_unlock;
+
+ vfio_link_dma(iommu, dma);
+ goto unlock;
+
+free_unlock:
+ kfree(dma);
+unlock:
+ mutex_unlock(&iommu->lock);
+ return ret;
+}
+
+static int vfio_unregister_reserved_iova_range(struct vfio_iommu *iommu,
+ struct vfio_iommu_type1_dma_unmap *unmap)
+{
+ dma_addr_t iova = unmap->iova;
+ struct vfio_dma *dma;
+ size_t size = unmap->size;
+ uint64_t mask;
+ unsigned long order;
+ int ret = -EINVAL;
+
+ /* Verify that none of our __u64 fields overflow */
+ if (unmap->size != size || unmap->iova != iova)
+ return ret;
+
+ order = __ffs(vfio_pgsize_bitmap(iommu));
+ mask = ((uint64_t)1 << order) - 1;
+
+ WARN_ON(mask & PAGE_MASK);
+
+ if (!size || (size | iova) & mask)
+ return ret;
+
+ /* Don't allow IOVA address wrap */
+ if (iova + size - 1 < iova)
+ return ret;
+
+ mutex_lock(&iommu->lock);
+
+ dma = vfio_find_dma(iommu, iova, size, VFIO_IOVA_RESERVED);
+
+ if (dma && (dma->iova == iova) && (dma->size == size)) {
+ unmap->size = dma->size;
+ vfio_remove_dma(iommu, dma);
+ ret = 0;
+ goto unlock;
+ }
+ unmap->size = 0;
+unlock:
+ mutex_unlock(&iommu->lock);
+ return ret;
+}
+
static int vfio_bus_type(struct device *dev, void *data)
{
struct bus_type **bus = data;
@@ -1074,7 +1199,8 @@ 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_RESERVED_MSI_IOVA;
minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
@@ -1084,6 +1210,9 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
if (map.argsz < minsz || map.flags & ~mask)
return -EINVAL;
+ if (map.flags & VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA)
+ return vfio_register_reserved_iova_range(iommu, &map);
+
return vfio_dma_do_map(iommu, &map);
} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
@@ -1098,6 +1227,13 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
if (unmap.argsz < minsz || unmap.flags)
return -EINVAL;
+ if (unmap.flags & VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA) {
+ ret = vfio_unregister_reserved_iova_range(iommu,
+ &unmap);
+ if (ret)
+ return ret;
+ }
+
ret = vfio_dma_do_unmap(iommu, &unmap);
if (ret)
return ret;
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 255a211..0637f35 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -498,12 +498,18 @@ 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.
+ *
+ * In case RESERVED_MSI_IOVA flag is set, the API only aims at registering an
+ * IOVA region that will be used on some platforms to map the host MSI frames.
+ * In that specific case, vaddr is ignored.
*/
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 */
+/* reserved iova for MSI vectors*/
+#define VFIO_DMA_MAP_FLAG_RESERVED_MSI_IOVA (1 << 2)
__u64 vaddr; /* Process virtual address */
__u64 iova; /* IO virtual address */
__u64 size; /* Size of mapping (bytes) */
@@ -519,7 +525,8 @@ struct vfio_iommu_type1_dma_map {
* Caller sets argsz. The actual unmapped size is returned in the size
* field. No guarantee is made to the user that arbitrary unmaps of iova
* or size different from those used in the original mapping call will
- * succeed.
+ * succeed. A Reserved DMA region must be unmapped with RESERVED_MSI_IOVA
+ * flag set.
*/
struct vfio_iommu_type1_dma_unmap {
__u32 argsz;
--
1.9.1