vfio/spapr: Create DMA window dynamically (SPAPR IOMMU v2)

New VFIO_SPAPR_TCE_v2_IOMMU type supports dynamic DMA window management.
This adds ability to VFIO common code to dynamically allocate/remove
DMA windows in the host kernel when new VFIO container is added/removed.

This adds a helper to vfio_listener_region_add which makes
VFIO_IOMMU_SPAPR_TCE_CREATE ioctl and adds just created IOMMU into
the host IOMMU list; the opposite action is taken in
vfio_listener_region_del.

When creating a new window, this uses heuristic to decide on the TCE table
levels number.

This should cause no guest visible change in behavior.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
[dwg: Added some casts to prevent printf() warnings on certain targets
 where the kernel headers' __u64 doesn't match uint64_t or PRIx64]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

1 files changed, 71 insertions, 0 deletions

diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
index 7d64443b7f..0af342332c 100644
--- a/hw/vfio/spapr.c
+++ b/hw/vfio/spapr.c
@@ -137,3 +137,74 @@ const MemoryListener vfio_prereg_listener = {
     .region_add = vfio_prereg_listener_region_add,
     .region_del = vfio_prereg_listener_region_del,
 };
+
+int vfio_spapr_create_window(VFIOContainer *container,
+                             MemoryRegionSection *section,
+                             hwaddr *pgsize)
+{
+    int ret;
+    unsigned pagesize = memory_region_iommu_get_min_page_size(section->mr);
+    unsigned entries, pages;
+    struct vfio_iommu_spapr_tce_create create = { .argsz = sizeof(create) };
+
+    /*
+     * FIXME: For VFIO iommu types which have KVM acceleration to
+     * avoid bouncing all map/unmaps through qemu this way, this
+     * would be the right place to wire that up (tell the KVM
+     * device emulation the VFIO iommu handles to use).
+     */
+    create.window_size = int128_get64(section->size);
+    create.page_shift = ctz64(pagesize);
+    /*
+     * SPAPR host supports multilevel TCE tables, there is some
+     * heuristic to decide how many levels we want for our table:
+     * 0..64 = 1; 65..4096 = 2; 4097..262144 = 3; 262145.. = 4
+     */
+    entries = create.window_size >> create.page_shift;
+    pages = MAX((entries * sizeof(uint64_t)) / getpagesize(), 1);
+    pages = MAX(pow2ceil(pages) - 1, 1); /* Round up */
+    create.levels = ctz64(pages) / 6 + 1;
+
+    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
+    if (ret) {
+        error_report("Failed to create a window, ret = %d (%m)", ret);
+        return -errno;
+    }
+
+    if (create.start_addr != section->offset_within_address_space) {
+        vfio_spapr_remove_window(container, create.start_addr);
+
+        error_report("Host doesn't support DMA window at %"HWADDR_PRIx", must be %"PRIx64,
+                     section->offset_within_address_space,
+                     (uint64_t)create.start_addr);
+        ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
+        return -EINVAL;
+    }
+    trace_vfio_spapr_create_window(create.page_shift,
+                                   create.window_size,
+                                   create.start_addr);
+    *pgsize = pagesize;
+
+    return 0;
+}
+
+int vfio_spapr_remove_window(VFIOContainer *container,
+                             hwaddr offset_within_address_space)
+{
+    struct vfio_iommu_spapr_tce_remove remove = {
+        .argsz = sizeof(remove),
+        .start_addr = offset_within_address_space,
+    };
+    int ret;
+
+    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
+    if (ret) {
+        error_report("Failed to remove window at %"PRIx64,
+                     (uint64_t)remove.start_addr);
+        return -errno;
+    }
+
+    trace_vfio_spapr_remove_window(offset_within_address_space);
+
+    return 0;
+}