Merge tag 'vfio-v6.19-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Move libvfio selftest artifacts in preparation of more tightly
   coupled integration with KVM selftests (David Matlack)

 - Fix comment typo in mtty driver (Chu Guangqing)

 - Support for new hardware revision in the hisi_acc vfio-pci variant
   driver where the migration registers can now be accessed via the PF.
   When enabled for this support, the full BAR can be exposed to the
   user (Longfang Liu)

 - Fix vfio cdev support for VF token passing, using the correct size
   for the kernel structure, thereby actually allowing userspace to
   provide a non-zero UUID token. Also set the match token callback for
   the hisi_acc, fixing VF token support for this this vfio-pci variant
   driver (Raghavendra Rao Ananta)

 - Introduce internal callbacks on vfio devices to simplify and
   consolidate duplicate code for generating VFIO_DEVICE_GET_REGION_INFO
   data, removing various ioctl intercepts with a more structured
   solution (Jason Gunthorpe)

 - Introduce dma-buf support for vfio-pci devices, allowing MMIO regions
   to be exposed through dma-buf objects with lifecycle managed through
   move operations. This enables low-level interactions such as a
   vfio-pci based SPDK drivers interacting directly with dma-buf capable
   RDMA devices to enable peer-to-peer operations. IOMMUFD is also now
   able to build upon this support to fill a long standing feature gap
   versus the legacy vfio type1 IOMMU backend with an implementation of
   P2P support for VM use cases that better manages the lifecycle of the
   P2P mapping (Leon Romanovsky, Jason Gunthorpe, Vivek Kasireddy)

 - Convert eventfd triggering for error and request signals to use RCU
   mechanisms in order to avoid a 3-way lockdep reported deadlock issue
   (Alex Williamson)

 - Fix a 32-bit overflow introduced via dma-buf support manifesting with
   large DMA buffers (Alex Mastro)

 - Convert nvgrace-gpu vfio-pci variant driver to insert mappings on
   fault rather than at mmap time. This conversion serves both to make
   use of huge PFNMAPs but also to both avoid corrected RAS events
   during reset by now being subject to vfio-pci-core's use of
   unmap_mapping_range(), and to enable a device readiness test after
   reset (Ankit Agrawal)

 - Refactoring of vfio selftests to support multi-device tests and split
   code to provide better separation between IOMMU and device objects.
   This work also enables a new test suite addition to measure parallel
   device initialization latency (David Matlack)

* tag 'vfio-v6.19-rc1' of https://github.com/awilliam/linux-vfio: (65 commits)
  vfio: selftests: Add vfio_pci_device_init_perf_test
  vfio: selftests: Eliminate INVALID_IOVA
  vfio: selftests: Split libvfio.h into separate header files
  vfio: selftests: Move vfio_selftests_*() helpers into libvfio.c
  vfio: selftests: Rename vfio_util.h to libvfio.h
  vfio: selftests: Stop passing device for IOMMU operations
  vfio: selftests: Move IOVA allocator into iova_allocator.c
  vfio: selftests: Move IOMMU library code into iommu.c
  vfio: selftests: Rename struct vfio_dma_region to dma_region
  vfio: selftests: Upgrade driver logging to dev_err()
  vfio: selftests: Prefix logs with device BDF where relevant
  vfio: selftests: Eliminate overly chatty logging
  vfio: selftests: Support multiple devices in the same container/iommufd
  vfio: selftests: Introduce struct iommu
  vfio: selftests: Rename struct vfio_iommu_mode to iommu_mode
  vfio: selftests: Allow passing multiple BDFs on the command line
  vfio: selftests: Split run.sh into separate scripts
  vfio: selftests: Move run.sh into scripts directory
  vfio/nvgrace-gpu: wait for the GPU mem to be ready
  vfio/nvgrace-gpu: Inform devmem unmapped after reset
  ...

3 files changed, 38 insertions, 102 deletions

diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c
index 18623ba666e3..64ea19253ee3 100644
--- a/samples/vfio-mdev/mbochs.c
+++ b/samples/vfio-mdev/mbochs.c
@@ -143,11 +143,6 @@ static struct mdev_parent mbochs_parent;
 static atomic_t mbochs_avail_mbytes;
 static const struct vfio_device_ops mbochs_dev_ops;
 
-struct vfio_region_info_ext {
-	struct vfio_region_info          base;
-	struct vfio_region_info_cap_type type;
-};
-
 struct mbochs_mode {
 	u32 drm_format;
 	u32 bytepp;
@@ -1033,10 +1028,12 @@ static int mbochs_dmabuf_export(struct mbochs_dmabuf *dmabuf)
 	return 0;
 }
 
-static int mbochs_get_region_info(struct mdev_state *mdev_state,
-				  struct vfio_region_info_ext *ext)
+static int mbochs_ioctl_get_region_info(struct vfio_device *vdev,
+					struct vfio_region_info *region_info,
+					struct vfio_info_cap *caps)
 {
-	struct vfio_region_info *region_info = &ext->base;
+	struct mdev_state *mdev_state =
+		container_of(vdev, struct mdev_state, vdev);
 
 	if (region_info->index >= MBOCHS_NUM_REGIONS)
 		return -EINVAL;
@@ -1061,20 +1058,23 @@ static int mbochs_get_region_info(struct mdev_state *mdev_state,
 		region_info->flags  = (VFIO_REGION_INFO_FLAG_READ  |
 				       VFIO_REGION_INFO_FLAG_WRITE);
 		break;
-	case MBOCHS_EDID_REGION_INDEX:
-		ext->base.argsz = sizeof(*ext);
-		ext->base.offset = MBOCHS_EDID_OFFSET;
-		ext->base.size = MBOCHS_EDID_SIZE;
-		ext->base.flags = (VFIO_REGION_INFO_FLAG_READ  |
-				   VFIO_REGION_INFO_FLAG_WRITE |
-				   VFIO_REGION_INFO_FLAG_CAPS);
-		ext->base.cap_offset = offsetof(typeof(*ext), type);
-		ext->type.header.id = VFIO_REGION_INFO_CAP_TYPE;
-		ext->type.header.version = 1;
-		ext->type.header.next = 0;
-		ext->type.type = VFIO_REGION_TYPE_GFX;
-		ext->type.subtype = VFIO_REGION_SUBTYPE_GFX_EDID;
-		break;
+	case MBOCHS_EDID_REGION_INDEX: {
+		struct vfio_region_info_cap_type cap_type = {
+			.header.id = VFIO_REGION_INFO_CAP_TYPE,
+			.header.version = 1,
+			.type = VFIO_REGION_TYPE_GFX,
+			.subtype = VFIO_REGION_SUBTYPE_GFX_EDID,
+		};
+
+		region_info->offset = MBOCHS_EDID_OFFSET;
+		region_info->size = MBOCHS_EDID_SIZE;
+		region_info->flags = (VFIO_REGION_INFO_FLAG_READ |
+				      VFIO_REGION_INFO_FLAG_WRITE |
+				      VFIO_REGION_INFO_FLAG_CAPS);
+
+		return vfio_info_add_capability(caps, &cap_type.header,
+						sizeof(cap_type));
+	}
 	default:
 		region_info->size   = 0;
 		region_info->offset = 0;
@@ -1191,7 +1191,7 @@ static long mbochs_ioctl(struct vfio_device *vdev, unsigned int cmd,
 	struct mdev_state *mdev_state =
 		container_of(vdev, struct mdev_state, vdev);
 	int ret = 0;
-	unsigned long minsz, outsz;
+	unsigned long minsz;
 
 	switch (cmd) {
 	case VFIO_DEVICE_GET_INFO:
@@ -1215,30 +1215,6 @@ static long mbochs_ioctl(struct vfio_device *vdev, unsigned int cmd,
 
 		return 0;
 	}
-	case VFIO_DEVICE_GET_REGION_INFO:
-	{
-		struct vfio_region_info_ext info;
-
-		minsz = offsetofend(typeof(info), base.offset);
-
-		if (copy_from_user(&info, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		outsz = info.base.argsz;
-		if (outsz < minsz)
-			return -EINVAL;
-		if (outsz > sizeof(info))
-			return -EINVAL;
-
-		ret = mbochs_get_region_info(mdev_state, &info);
-		if (ret)
-			return ret;
-
-		if (copy_to_user((void __user *)arg, &info, outsz))
-			return -EFAULT;
-
-		return 0;
-	}
 
 	case VFIO_DEVICE_GET_IRQ_INFO:
 	{
@@ -1376,6 +1352,7 @@ static const struct vfio_device_ops mbochs_dev_ops = {
 	.read = mbochs_read,
 	.write = mbochs_write,
 	.ioctl = mbochs_ioctl,
+	.get_region_info_caps = mbochs_ioctl_get_region_info,
 	.mmap = mbochs_mmap,
 	.bind_iommufd	= vfio_iommufd_emulated_bind,
 	.unbind_iommufd	= vfio_iommufd_emulated_unbind,
diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c
index 8104831ae125..0759bd68edca 100644
--- a/samples/vfio-mdev/mdpy.c
+++ b/samples/vfio-mdev/mdpy.c
@@ -435,10 +435,13 @@ static int mdpy_mmap(struct vfio_device *vdev, struct vm_area_struct *vma)
 	return remap_vmalloc_range(vma, mdev_state->memblk, 0);
 }
 
-static int mdpy_get_region_info(struct mdev_state *mdev_state,
-				struct vfio_region_info *region_info,
-				u16 *cap_type_id, void **cap_type)
+static int mdpy_ioctl_get_region_info(struct vfio_device *vdev,
+				      struct vfio_region_info *region_info,
+				      struct vfio_info_cap *caps)
 {
+	struct mdev_state *mdev_state =
+		container_of(vdev, struct mdev_state, vdev);
+
 	if (region_info->index >= VFIO_PCI_NUM_REGIONS &&
 	    region_info->index != MDPY_DISPLAY_REGION)
 		return -EINVAL;
@@ -544,30 +547,6 @@ static long mdpy_ioctl(struct vfio_device *vdev, unsigned int cmd,
 
 		return 0;
 	}
-	case VFIO_DEVICE_GET_REGION_INFO:
-	{
-		struct vfio_region_info info;
-		u16 cap_type_id = 0;
-		void *cap_type = NULL;
-
-		minsz = offsetofend(struct vfio_region_info, offset);
-
-		if (copy_from_user(&info, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (info.argsz < minsz)
-			return -EINVAL;
-
-		ret = mdpy_get_region_info(mdev_state, &info, &cap_type_id,
-					   &cap_type);
-		if (ret)
-			return ret;
-
-		if (copy_to_user((void __user *)arg, &info, minsz))
-			return -EFAULT;
-
-		return 0;
-	}
 
 	case VFIO_DEVICE_GET_IRQ_INFO:
 	{
@@ -665,6 +644,7 @@ static const struct vfio_device_ops mdpy_dev_ops = {
 	.read = mdpy_read,
 	.write = mdpy_write,
 	.ioctl = mdpy_ioctl,
+	.get_region_info_caps = mdpy_ioctl_get_region_info,
 	.mmap = mdpy_mmap,
 	.bind_iommufd	= vfio_iommufd_emulated_bind,
 	.unbind_iommufd	= vfio_iommufd_emulated_unbind,
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 59eefe2fed10..bd92c38379b8 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -624,7 +624,7 @@ static void handle_bar_read(unsigned int index, struct mdev_state *mdev_state,
 		u8 lsr = 0;
 
 		mutex_lock(&mdev_state->rxtx_lock);
-		/* atleast one char in FIFO */
+		/* at least one char in FIFO */
 		if (mdev_state->s[index].rxtx.head !=
 				 mdev_state->s[index].rxtx.tail)
 			lsr |= UART_LSR_DR;
@@ -1717,10 +1717,12 @@ static int mtty_set_irqs(struct mdev_state *mdev_state, uint32_t flags,
 	return ret;
 }
 
-static int mtty_get_region_info(struct mdev_state *mdev_state,
-			 struct vfio_region_info *region_info,
-			 u16 *cap_type_id, void **cap_type)
+static int mtty_ioctl_get_region_info(struct vfio_device *vdev,
+				      struct vfio_region_info *region_info,
+				      struct vfio_info_cap *caps)
 {
+	struct mdev_state *mdev_state =
+		container_of(vdev, struct mdev_state, vdev);
 	unsigned int size = 0;
 	u32 bar_index;
 
@@ -1817,30 +1819,6 @@ static long mtty_ioctl(struct vfio_device *vdev, unsigned int cmd,
 
 		return 0;
 	}
-	case VFIO_DEVICE_GET_REGION_INFO:
-	{
-		struct vfio_region_info info;
-		u16 cap_type_id = 0;
-		void *cap_type = NULL;
-
-		minsz = offsetofend(struct vfio_region_info, offset);
-
-		if (copy_from_user(&info, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (info.argsz < minsz)
-			return -EINVAL;
-
-		ret = mtty_get_region_info(mdev_state, &info, &cap_type_id,
-					   &cap_type);
-		if (ret)
-			return ret;
-
-		if (copy_to_user((void __user *)arg, &info, minsz))
-			return -EFAULT;
-
-		return 0;
-	}
 
 	case VFIO_DEVICE_GET_IRQ_INFO:
 	{
@@ -1949,6 +1927,7 @@ static const struct vfio_device_ops mtty_dev_ops = {
 	.read = mtty_read,
 	.write = mtty_write,
 	.ioctl = mtty_ioctl,
+	.get_region_info_caps = mtty_ioctl_get_region_info,
 	.bind_iommufd	= vfio_iommufd_emulated_bind,
 	.unbind_iommufd	= vfio_iommufd_emulated_unbind,
 	.attach_ioas	= vfio_iommufd_emulated_attach_ioas,