vfio: powerpc/spapr: Support Dynamic DMA windows

This adds create/remove window ioctls to create and remove DMA windows.
sPAPR defines a Dynamic DMA windows capability which allows
para-virtualized guests to create additional DMA windows on a PCI bus.
The existing linux kernels use this new window to map the entire guest
memory and switch to the direct DMA operations saving time on map/unmap
requests which would normally happen in a big amounts.

This adds 2 ioctl handlers - VFIO_IOMMU_SPAPR_TCE_CREATE and
VFIO_IOMMU_SPAPR_TCE_REMOVE - to create and remove windows.
Up to 2 windows are supported now by the hardware and by this driver.

This changes VFIO_IOMMU_SPAPR_TCE_GET_INFO handler to return additional
information such as a number of supported windows and maximum number
levels of TCE tables.

DDW is added as a capability, not as a SPAPR TCE IOMMU v2 unique feature
as we still want to support v2 on platforms which cannot do DDW for
the sake of TCE acceleration in KVM (coming soon).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 58 insertions, 3 deletions

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index fa84391a0d00..9fd7b5d8df2f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -445,6 +445,23 @@ struct vfio_iommu_type1_dma_unmap {
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*
+ * The SPAPR TCE DDW info struct provides the information about
+ * the details of Dynamic DMA window capability.
+ *
+ * @pgsizes contains a page size bitmask, 4K/64K/16M are supported.
+ * @max_dynamic_windows_supported tells the maximum number of windows
+ * which the platform can create.
+ * @levels tells the maximum number of levels in multi-level IOMMU tables;
+ * this allows splitting a table into smaller chunks which reduces
+ * the amount of physically contiguous memory required for the table.
+ */
+struct vfio_iommu_spapr_tce_ddw_info {
+	__u64 pgsizes;			/* Bitmap of supported page sizes */
+	__u32 max_dynamic_windows_supported;
+	__u32 levels;
+};
+
+/*
  * The SPAPR TCE info struct provides the information about the PCI bus
  * address ranges available for DMA, these values are programmed into
  * the hardware so the guest has to know that information.
@@ -454,14 +471,17 @@ struct vfio_iommu_type1_dma_unmap {
  * addresses too so the window works as a filter rather than an offset
  * for IOVA addresses.
  *
- * A flag will need to be added if other page sizes are supported,
- * so as defined here, it is always 4k.
+ * Flags supported:
+ * - VFIO_IOMMU_SPAPR_INFO_DDW: informs the userspace that dynamic DMA windows
+ *   (DDW) support is present. @ddw is only supported when DDW is present.
  */
 struct vfio_iommu_spapr_tce_info {
 	__u32 argsz;
-	__u32 flags;			/* reserved for future use */
+	__u32 flags;
+#define VFIO_IOMMU_SPAPR_INFO_DDW	(1 << 0)	/* DDW supported */
 	__u32 dma32_window_start;	/* 32 bit window start (bytes) */
 	__u32 dma32_window_size;	/* 32 bit window size (bytes) */
+	struct vfio_iommu_spapr_tce_ddw_info ddw;
 };
 
 #define VFIO_IOMMU_SPAPR_TCE_GET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
@@ -534,6 +554,41 @@ struct vfio_iommu_spapr_register_memory {
  */
 #define VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY	_IO(VFIO_TYPE, VFIO_BASE + 18)
 
+/**
+ * VFIO_IOMMU_SPAPR_TCE_CREATE - _IOWR(VFIO_TYPE, VFIO_BASE + 19, struct vfio_iommu_spapr_tce_create)
+ *
+ * Creates an additional TCE table and programs it (sets a new DMA window)
+ * to every IOMMU group in the container. It receives page shift, window
+ * size and number of levels in the TCE table being created.
+ *
+ * It allocates and returns an offset on a PCI bus of the new DMA window.
+ */
+struct vfio_iommu_spapr_tce_create {
+	__u32 argsz;
+	__u32 flags;
+	/* in */
+	__u32 page_shift;
+	__u64 window_size;
+	__u32 levels;
+	/* out */
+	__u64 start_addr;
+};
+#define VFIO_IOMMU_SPAPR_TCE_CREATE	_IO(VFIO_TYPE, VFIO_BASE + 19)
+
+/**
+ * VFIO_IOMMU_SPAPR_TCE_REMOVE - _IOW(VFIO_TYPE, VFIO_BASE + 20, struct vfio_iommu_spapr_tce_remove)
+ *
+ * Unprograms a TCE table from all groups in the container and destroys it.
+ * It receives a PCI bus offset as a window id.
+ */
+struct vfio_iommu_spapr_tce_remove {
+	__u32 argsz;
+	__u32 flags;
+	/* in */
+	__u64 start_addr;
+};
+#define VFIO_IOMMU_SPAPR_TCE_REMOVE	_IO(VFIO_TYPE, VFIO_BASE + 20)
+
 /* ***************************************************************** */
 
 #endif /* _UAPIVFIO_H */