[PULL v2 14/32] vfio: Dirty page tracking when vIOMMU is enabled

[Alex Williamson <alex.williamson@redhat.com>]

From: Kirti Wankhede <kwankhede@nvidia.com>

When vIOMMU is enabled, register MAP notifier from log_sync when all
devices in container are in stop and copy phase of migration. Call replay
and get dirty pages from notifier callback.

Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 hw/vfio/common.c     |   88 +++++++++++++++++++++++++++++++++++++++++++++++---
 hw/vfio/trace-events |    1 +
 2 files changed, 83 insertions(+), 6 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 2b1455e78089..32d536e32507 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -442,8 +442,8 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section)
 }
 
 /* Called with rcu_read_lock held.  */
-static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
-                           bool *read_only)
+static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
+                               ram_addr_t *ram_addr, bool *read_only)
 {
     MemoryRegion *mr;
     hwaddr xlat;
@@ -474,8 +474,17 @@ static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
         return false;
     }
 
-    *vaddr = memory_region_get_ram_ptr(mr) + xlat;
-    *read_only = !writable || mr->readonly;
+    if (vaddr) {
+        *vaddr = memory_region_get_ram_ptr(mr) + xlat;
+    }
+
+    if (ram_addr) {
+        *ram_addr = memory_region_get_ram_addr(mr) + xlat;
+    }
+
+    if (read_only) {
+        *read_only = !writable || mr->readonly;
+    }
 
     return true;
 }
@@ -485,7 +494,6 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
     VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
     VFIOContainer *container = giommu->container;
     hwaddr iova = iotlb->iova + giommu->iommu_offset;
-    bool read_only;
     void *vaddr;
     int ret;
 
@@ -501,7 +509,9 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
     rcu_read_lock();
 
     if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
-        if (!vfio_get_vaddr(iotlb, &vaddr, &read_only)) {
+        bool read_only;
+
+        if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only)) {
             goto out;
         }
         /*
@@ -899,11 +909,77 @@ err_out:
     return ret;
 }
 
+typedef struct {
+    IOMMUNotifier n;
+    VFIOGuestIOMMU *giommu;
+} vfio_giommu_dirty_notifier;
+
+static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+    vfio_giommu_dirty_notifier *gdn = container_of(n,
+                                                vfio_giommu_dirty_notifier, n);
+    VFIOGuestIOMMU *giommu = gdn->giommu;
+    VFIOContainer *container = giommu->container;
+    hwaddr iova = iotlb->iova + giommu->iommu_offset;
+    ram_addr_t translated_addr;
+
+    trace_vfio_iommu_map_dirty_notify(iova, iova + iotlb->addr_mask);
+
+    if (iotlb->target_as != &address_space_memory) {
+        error_report("Wrong target AS \"%s\", only system memory is allowed",
+                     iotlb->target_as->name ? iotlb->target_as->name : "none");
+        return;
+    }
+
+    rcu_read_lock();
+    if (vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL)) {
+        int ret;
+
+        ret = vfio_get_dirty_bitmap(container, iova, iotlb->addr_mask + 1,
+                                    translated_addr);
+        if (ret) {
+            error_report("vfio_iommu_map_dirty_notify(%p, 0x%"HWADDR_PRIx", "
+                         "0x%"HWADDR_PRIx") = %d (%m)",
+                         container, iova,
+                         iotlb->addr_mask + 1, ret);
+        }
+    }
+    rcu_read_unlock();
+}
+
 static int vfio_sync_dirty_bitmap(VFIOContainer *container,
                                   MemoryRegionSection *section)
 {
     ram_addr_t ram_addr;
 
+    if (memory_region_is_iommu(section->mr)) {
+        VFIOGuestIOMMU *giommu;
+
+        QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
+            if (MEMORY_REGION(giommu->iommu) == section->mr &&
+                giommu->n.start == section->offset_within_region) {
+                Int128 llend;
+                vfio_giommu_dirty_notifier gdn = { .giommu = giommu };
+                int idx = memory_region_iommu_attrs_to_index(giommu->iommu,
+                                                       MEMTXATTRS_UNSPECIFIED);
+
+                llend = int128_add(int128_make64(section->offset_within_region),
+                                   section->size);
+                llend = int128_sub(llend, int128_one());
+
+                iommu_notifier_init(&gdn.n,
+                                    vfio_iommu_map_dirty_notify,
+                                    IOMMU_NOTIFIER_MAP,
+                                    section->offset_within_region,
+                                    int128_get64(llend),
+                                    idx);
+                memory_region_iommu_replay(giommu->iommu, &gdn.n);
+                break;
+            }
+        }
+        return 0;
+    }
+
     ram_addr = memory_region_get_ram_addr(section->mr) +
                section->offset_within_region;
 
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index dd991bd8f265..c0e75f24b76d 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -164,3 +164,4 @@ vfio_load_state(const char *name, uint64_t data) " (%s) data 0x%"PRIx64
 vfio_load_state_device_data(const char *name, uint64_t data_offset, uint64_t data_size) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64
 vfio_load_cleanup(const char *name) " (%s)"
 vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start) "container fd=%d, iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64
+vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64