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, 70 insertions, 10 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 7c8a531..f3c0522 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -265,6 +265,21 @@ static void vfio_host_win_add(VFIOContainer *container,
     QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next);
 }
 
+static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova,
+                             hwaddr max_iova)
+{
+    VFIOHostDMAWindow *hostwin;
+
+    QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
+        if (hostwin->min_iova == min_iova && hostwin->max_iova == max_iova) {
+            QLIST_REMOVE(hostwin, hostwin_next);
+            return 0;
+        }
+    }
+
+    return -1;
+}
+
 static bool vfio_listener_skipped_section(MemoryRegionSection *section)
 {
     return (!memory_region_is_ram(section->mr) &&
@@ -380,6 +395,31 @@ static void vfio_listener_region_add(MemoryListener *listener,
     }
     end = int128_get64(int128_sub(llend, int128_one()));
 
+    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+        VFIOHostDMAWindow *hostwin;
+        hwaddr pgsize = 0;
+
+        /* For now intersections are not allowed, we may relax this later */
+        QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
+            if (ranges_overlap(hostwin->min_iova,
+                               hostwin->max_iova - hostwin->min_iova + 1,
+                               section->offset_within_address_space,
+                               int128_get64(section->size))) {
+                ret = -1;
+                goto fail;
+            }
+        }
+
+        ret = vfio_spapr_create_window(container, section, &pgsize);
+        if (ret) {
+            goto fail;
+        }
+
+        vfio_host_win_add(container, section->offset_within_address_space,
+                          section->offset_within_address_space +
+                          int128_get64(section->size) - 1, pgsize);
+    }
+
     hostwin_found = false;
     QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
         if (hostwin->min_iova <= iova && end <= hostwin->max_iova) {
@@ -523,6 +563,18 @@ static void vfio_listener_region_del(MemoryListener *listener,
                      "0x%"HWADDR_PRIx") = %d (%m)",
                      container, iova, int128_get64(llsize), ret);
     }
+
+    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+        vfio_spapr_remove_window(container,
+                                 section->offset_within_address_space);
+        if (vfio_host_win_del(container,
+                              section->offset_within_address_space,
+                              section->offset_within_address_space +
+                              int128_get64(section->size) - 1) < 0) {
+            hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx,
+                     __func__, section->offset_within_address_space);
+        }
+    }
 }
 
 static const MemoryListener vfio_memory_listener = {
@@ -961,11 +1013,6 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
             }
         }
 
-        /*
-         * This only considers the host IOMMU's 32-bit window.  At
-         * some point we need to add support for the optional 64-bit
-         * window and dynamic windows
-         */
         info.argsz = sizeof(info);
         ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
         if (ret) {
@@ -977,11 +1024,24 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
             goto free_container_exit;
         }
 
-        /* The default table uses 4K pages */
-        vfio_host_win_add(container, info.dma32_window_start,
-                          info.dma32_window_start +
-                          info.dma32_window_size - 1,
-                          0x1000);
+        if (v2) {
+            /*
+             * There is a default window in just created container.
+             * To make region_add/del simpler, we better remove this
+             * window now and let those iommu_listener callbacks
+             * create/remove them when needed.
+             */
+            ret = vfio_spapr_remove_window(container, info.dma32_window_start);
+            if (ret) {
+                goto free_container_exit;
+            }
+        } else {
+            /* The default table uses 4K pages */
+            vfio_host_win_add(container, info.dma32_window_start,
+                              info.dma32_window_start +
+                              info.dma32_window_size - 1,
+                              0x1000);
+        }
     } else {
         error_report("vfio: No available IOMMU models");
         ret = -EINVAL;