vfio: Support host translation granule size

The cpu_physical_memory_set_dirty_lebitmap() can quickly deal with
the dirty pages of memory by bitmap-traveling, regardless of whether
the bitmap is aligned correctly or not.

cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
host page size. So it'd better to set bitmap_pgsize to host page size
to support more translation granule sizes.

[aw: The Fixes commit below introduced code to restrict migration
support to configurations where the target page size intersects the
host dirty page support.  For example, a 4K guest on a 4K host.
Due to the above flexibility in bitmap handling, this restriction
unnecessarily prevents mixed target/host pages size that could
otherwise be supported.  Use host page size for dirty bitmap.]

Fixes: 87ea529c502 ("vfio: Get migration capability flags for container")
Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com>
Message-Id: <20210304133446.1521-1-jiangkunkun@huawei.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 25 insertions, 23 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 35a41fd052..ad08dfd729 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -378,7 +378,7 @@ static int vfio_dma_unmap_bitmap(VFIOContainer *container,
 {
     struct vfio_iommu_type1_dma_unmap *unmap;
     struct vfio_bitmap *bitmap;
-    uint64_t pages = TARGET_PAGE_ALIGN(size) >> TARGET_PAGE_BITS;
+    uint64_t pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size;
     int ret;
 
     unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap));
@@ -390,12 +390,12 @@ static int vfio_dma_unmap_bitmap(VFIOContainer *container,
     bitmap = (struct vfio_bitmap *)&unmap->data;
 
     /*
-     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
-     * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap_pgsize to
-     * TARGET_PAGE_SIZE.
+     * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
+     * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize
+     * to qemu_real_host_page_size.
      */
 
-    bitmap->pgsize = TARGET_PAGE_SIZE;
+    bitmap->pgsize = qemu_real_host_page_size;
     bitmap->size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
                    BITS_PER_BYTE;
 
@@ -674,16 +674,17 @@ static void vfio_listener_region_add(MemoryListener *listener,
         return;
     }
 
-    if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
-                 (section->offset_within_region & ~TARGET_PAGE_MASK))) {
+    if (unlikely((section->offset_within_address_space &
+                  ~qemu_real_host_page_mask) !=
+                 (section->offset_within_region & ~qemu_real_host_page_mask))) {
         error_report("%s received unaligned region", __func__);
         return;
     }
 
-    iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
+    iova = REAL_HOST_PAGE_ALIGN(section->offset_within_address_space);
     llend = int128_make64(section->offset_within_address_space);
     llend = int128_add(llend, section->size);
-    llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK));
+    llend = int128_and(llend, int128_exts64(qemu_real_host_page_mask));
 
     if (int128_ge(int128_make64(iova), llend)) {
         return;
@@ -892,8 +893,9 @@ static void vfio_listener_region_del(MemoryListener *listener,
         return;
     }
 
-    if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
-                 (section->offset_within_region & ~TARGET_PAGE_MASK))) {
+    if (unlikely((section->offset_within_address_space &
+                  ~qemu_real_host_page_mask) !=
+                 (section->offset_within_region & ~qemu_real_host_page_mask))) {
         error_report("%s received unaligned region", __func__);
         return;
     }
@@ -921,10 +923,10 @@ static void vfio_listener_region_del(MemoryListener *listener,
          */
     }
 
-    iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
+    iova = REAL_HOST_PAGE_ALIGN(section->offset_within_address_space);
     llend = int128_make64(section->offset_within_address_space);
     llend = int128_add(llend, section->size);
-    llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK));
+    llend = int128_and(llend, int128_exts64(qemu_real_host_page_mask));
 
     if (int128_ge(int128_make64(iova), llend)) {
         return;
@@ -1004,13 +1006,13 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
     range->size = size;
 
     /*
-     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
-     * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap's pgsize to
-     * TARGET_PAGE_SIZE.
+     * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
+     * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pgsize
+     * to qemu_real_host_page_size.
      */
-    range->bitmap.pgsize = TARGET_PAGE_SIZE;
+    range->bitmap.pgsize = qemu_real_host_page_size;
 
-    pages = TARGET_PAGE_ALIGN(range->size) >> TARGET_PAGE_BITS;
+    pages = REAL_HOST_PAGE_ALIGN(range->size) / qemu_real_host_page_size;
     range->bitmap.size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
                                          BITS_PER_BYTE;
     range->bitmap.data = g_try_malloc0(range->bitmap.size);
@@ -1114,8 +1116,8 @@ static int vfio_sync_dirty_bitmap(VFIOContainer *container,
                section->offset_within_region;
 
     return vfio_get_dirty_bitmap(container,
-                       TARGET_PAGE_ALIGN(section->offset_within_address_space),
-                       int128_get64(section->size), ram_addr);
+                   REAL_HOST_PAGE_ALIGN(section->offset_within_address_space),
+                   int128_get64(section->size), ram_addr);
 }
 
 static void vfio_listener_log_sync(MemoryListener *listener,
@@ -1655,10 +1657,10 @@ static void vfio_get_iommu_info_migration(VFIOContainer *container,
                             header);
 
     /*
-     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
-     * TARGET_PAGE_SIZE to mark those dirty.
+     * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
+     * qemu_real_host_page_size to mark those dirty.
      */
-    if (cap_mig->pgsize_bitmap & TARGET_PAGE_SIZE) {
+    if (cap_mig->pgsize_bitmap & qemu_real_host_page_size) {
         container->dirty_pages_supported = true;
         container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size;
         container->dirty_pgsizes = cap_mig->pgsize_bitmap;