1 files changed, 203 insertions, 2 deletions

diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
index 21ec63b..fc5c75d 100644
--- a/hw/virtio/virtio-iommu.c
+++ b/hw/virtio/virtio-iommu.c
@@ -49,6 +49,7 @@ typedef struct VirtIOIOMMUDomain {
 typedef struct VirtIOIOMMUEndpoint {
     uint32_t id;
     VirtIOIOMMUDomain *domain;
+    IOMMUMemoryRegion *iommu_mr;
     QLIST_ENTRY(VirtIOIOMMUEndpoint) next;
 } VirtIOIOMMUEndpoint;
 
@@ -101,7 +102,7 @@ static IOMMUMemoryRegion *virtio_iommu_mr(VirtIOIOMMU *s, uint32_t sid)
     bus_n = PCI_BUS_NUM(sid);
     iommu_pci_bus = iommu_find_iommu_pcibus(s, bus_n);
     if (iommu_pci_bus) {
-        devfn = sid & PCI_DEVFN_MAX;
+        devfn = sid & (PCI_DEVFN_MAX - 1);
         dev = iommu_pci_bus->pbdev[devfn];
         if (dev) {
             return &dev->iommu_mr;
@@ -124,11 +125,84 @@ static gint interval_cmp(gconstpointer a, gconstpointer b, gpointer user_data)
     }
 }
 
+static void virtio_iommu_notify_map(IOMMUMemoryRegion *mr, hwaddr virt_start,
+                                    hwaddr virt_end, hwaddr paddr,
+                                    uint32_t flags)
+{
+    IOMMUTLBEntry entry;
+    IOMMUAccessFlags perm = IOMMU_ACCESS_FLAG(flags & VIRTIO_IOMMU_MAP_F_READ,
+                                              flags & VIRTIO_IOMMU_MAP_F_WRITE);
+
+    if (!(mr->iommu_notify_flags & IOMMU_NOTIFIER_MAP) ||
+        (flags & VIRTIO_IOMMU_MAP_F_MMIO) || !perm) {
+        return;
+    }
+
+    trace_virtio_iommu_notify_map(mr->parent_obj.name, virt_start, virt_end,
+                                  paddr, perm);
+
+    entry.target_as = &address_space_memory;
+    entry.addr_mask = virt_end - virt_start;
+    entry.iova = virt_start;
+    entry.perm = perm;
+    entry.translated_addr = paddr;
+
+    memory_region_notify_iommu(mr, 0, entry);
+}
+
+static void virtio_iommu_notify_unmap(IOMMUMemoryRegion *mr, hwaddr virt_start,
+                                      hwaddr virt_end)
+{
+    IOMMUTLBEntry entry;
+
+    if (!(mr->iommu_notify_flags & IOMMU_NOTIFIER_UNMAP)) {
+        return;
+    }
+
+    trace_virtio_iommu_notify_unmap(mr->parent_obj.name, virt_start, virt_end);
+
+    entry.target_as = &address_space_memory;
+    entry.addr_mask = virt_end - virt_start;
+    entry.iova = virt_start;
+    entry.perm = IOMMU_NONE;
+    entry.translated_addr = 0;
+
+    memory_region_notify_iommu(mr, 0, entry);
+}
+
+static gboolean virtio_iommu_notify_unmap_cb(gpointer key, gpointer value,
+                                             gpointer data)
+{
+    VirtIOIOMMUInterval *interval = (VirtIOIOMMUInterval *) key;
+    IOMMUMemoryRegion *mr = (IOMMUMemoryRegion *) data;
+
+    virtio_iommu_notify_unmap(mr, interval->low, interval->high);
+
+    return false;
+}
+
+static gboolean virtio_iommu_notify_map_cb(gpointer key, gpointer value,
+                                           gpointer data)
+{
+    VirtIOIOMMUMapping *mapping = (VirtIOIOMMUMapping *) value;
+    VirtIOIOMMUInterval *interval = (VirtIOIOMMUInterval *) key;
+    IOMMUMemoryRegion *mr = (IOMMUMemoryRegion *) data;
+
+    virtio_iommu_notify_map(mr, interval->low, interval->high,
+                            mapping->phys_addr, mapping->flags);
+
+    return false;
+}
+
 static void virtio_iommu_detach_endpoint_from_domain(VirtIOIOMMUEndpoint *ep)
 {
+    VirtIOIOMMUDomain *domain = ep->domain;
+
     if (!ep->domain) {
         return;
     }
+    g_tree_foreach(domain->mappings, virtio_iommu_notify_unmap_cb,
+                   ep->iommu_mr);
     QLIST_REMOVE(ep, next);
     ep->domain = NULL;
 }
@@ -137,16 +211,19 @@ static VirtIOIOMMUEndpoint *virtio_iommu_get_endpoint(VirtIOIOMMU *s,
                                                       uint32_t ep_id)
 {
     VirtIOIOMMUEndpoint *ep;
+    IOMMUMemoryRegion *mr;
 
     ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(ep_id));
     if (ep) {
         return ep;
     }
-    if (!virtio_iommu_mr(s, ep_id)) {
+    mr = virtio_iommu_mr(s, ep_id);
+    if (!mr) {
         return NULL;
     }
     ep = g_malloc0(sizeof(*ep));
     ep->id = ep_id;
+    ep->iommu_mr = mr;
     trace_virtio_iommu_get_endpoint(ep_id);
     g_tree_insert(s->endpoints, GUINT_TO_POINTER(ep_id), ep);
     return ep;
@@ -268,6 +345,10 @@ static int virtio_iommu_attach(VirtIOIOMMU *s,
 
     ep->domain = domain;
 
+    /* Replay domain mappings on the associated memory region */
+    g_tree_foreach(domain->mappings, virtio_iommu_notify_map_cb,
+                   ep->iommu_mr);
+
     return VIRTIO_IOMMU_S_OK;
 }
 
@@ -311,6 +392,7 @@ static int virtio_iommu_map(VirtIOIOMMU *s,
     VirtIOIOMMUDomain *domain;
     VirtIOIOMMUInterval *interval;
     VirtIOIOMMUMapping *mapping;
+    VirtIOIOMMUEndpoint *ep;
 
     if (flags & ~VIRTIO_IOMMU_MAP_F_MASK) {
         return VIRTIO_IOMMU_S_INVAL;
@@ -340,6 +422,11 @@ static int virtio_iommu_map(VirtIOIOMMU *s,
 
     g_tree_insert(domain->mappings, interval, mapping);
 
+    QLIST_FOREACH(ep, &domain->endpoint_list, next) {
+        virtio_iommu_notify_map(ep->iommu_mr, virt_start, virt_end, phys_start,
+                                flags);
+    }
+
     return VIRTIO_IOMMU_S_OK;
 }
 
@@ -352,6 +439,7 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s,
     VirtIOIOMMUMapping *iter_val;
     VirtIOIOMMUInterval interval, *iter_key;
     VirtIOIOMMUDomain *domain;
+    VirtIOIOMMUEndpoint *ep;
     int ret = VIRTIO_IOMMU_S_OK;
 
     trace_virtio_iommu_unmap(domain_id, virt_start, virt_end);
@@ -369,6 +457,10 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s,
         uint64_t current_high = iter_key->high;
 
         if (interval.low <= current_low && interval.high >= current_high) {
+            QLIST_FOREACH(ep, &domain->endpoint_list, next) {
+                virtio_iommu_notify_unmap(ep->iommu_mr, current_low,
+                                          current_high);
+            }
             g_tree_remove(domain->mappings, iter_key);
             trace_virtio_iommu_unmap_done(domain_id, current_low, current_high);
         } else {
@@ -755,6 +847,107 @@ static gint int_cmp(gconstpointer a, gconstpointer b, gpointer user_data)
     return (ua > ub) - (ua < ub);
 }
 
+static gboolean virtio_iommu_remap(gpointer key, gpointer value, gpointer data)
+{
+    VirtIOIOMMUMapping *mapping = (VirtIOIOMMUMapping *) value;
+    VirtIOIOMMUInterval *interval = (VirtIOIOMMUInterval *) key;
+    IOMMUMemoryRegion *mr = (IOMMUMemoryRegion *) data;
+
+    trace_virtio_iommu_remap(mr->parent_obj.name, interval->low, interval->high,
+                             mapping->phys_addr);
+    virtio_iommu_notify_map(mr, interval->low, interval->high,
+                            mapping->phys_addr, mapping->flags);
+    return false;
+}
+
+static void virtio_iommu_replay(IOMMUMemoryRegion *mr, IOMMUNotifier *n)
+{
+    IOMMUDevice *sdev = container_of(mr, IOMMUDevice, iommu_mr);
+    VirtIOIOMMU *s = sdev->viommu;
+    uint32_t sid;
+    VirtIOIOMMUEndpoint *ep;
+
+    sid = virtio_iommu_get_bdf(sdev);
+
+    qemu_mutex_lock(&s->mutex);
+
+    if (!s->endpoints) {
+        goto unlock;
+    }
+
+    ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(sid));
+    if (!ep || !ep->domain) {
+        goto unlock;
+    }
+
+    g_tree_foreach(ep->domain->mappings, virtio_iommu_remap, mr);
+
+unlock:
+    qemu_mutex_unlock(&s->mutex);
+}
+
+static int virtio_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu_mr,
+                                            IOMMUNotifierFlag old,
+                                            IOMMUNotifierFlag new,
+                                            Error **errp)
+{
+    if (old == IOMMU_NOTIFIER_NONE) {
+        trace_virtio_iommu_notify_flag_add(iommu_mr->parent_obj.name);
+    } else if (new == IOMMU_NOTIFIER_NONE) {
+        trace_virtio_iommu_notify_flag_del(iommu_mr->parent_obj.name);
+    }
+    return 0;
+}
+
+/*
+ * The default mask (TARGET_PAGE_MASK) is the smallest supported guest granule,
+ * for example 0xfffffffffffff000. When an assigned device has page size
+ * restrictions due to the hardware IOMMU configuration, apply this restriction
+ * to the mask.
+ */
+static int virtio_iommu_set_page_size_mask(IOMMUMemoryRegion *mr,
+                                           uint64_t new_mask,
+                                           Error **errp)
+{
+    IOMMUDevice *sdev = container_of(mr, IOMMUDevice, iommu_mr);
+    VirtIOIOMMU *s = sdev->viommu;
+    uint64_t cur_mask = s->config.page_size_mask;
+
+    trace_virtio_iommu_set_page_size_mask(mr->parent_obj.name, cur_mask,
+                                          new_mask);
+
+    if ((cur_mask & new_mask) == 0) {
+        error_setg(errp, "virtio-iommu page mask 0x%"PRIx64
+                   " is incompatible with mask 0x%"PRIx64, cur_mask, new_mask);
+        return -1;
+    }
+
+    /*
+     * After the machine is finalized, we can't change the mask anymore. If by
+     * chance the hotplugged device supports the same granule, we can still
+     * accept it. Having a different masks is possible but the guest will use
+     * sub-optimal block sizes, so warn about it.
+     */
+    if (qdev_hotplug) {
+        int new_granule = ctz64(new_mask);
+        int cur_granule = ctz64(cur_mask);
+
+        if (new_granule != cur_granule) {
+            error_setg(errp, "virtio-iommu page mask 0x%"PRIx64
+                       " is incompatible with mask 0x%"PRIx64, cur_mask,
+                       new_mask);
+            return -1;
+        } else if (new_mask != cur_mask) {
+            warn_report("virtio-iommu page mask 0x%"PRIx64
+                        " does not match 0x%"PRIx64, cur_mask, new_mask);
+        }
+        return 0;
+    }
+
+    s->config.page_size_mask &= new_mask;
+    return 0;
+}
+
 static void virtio_iommu_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -910,9 +1103,14 @@ static gboolean reconstruct_endpoints(gpointer key, gpointer value,
     VirtIOIOMMU *s = (VirtIOIOMMU *)data;
     VirtIOIOMMUDomain *d = (VirtIOIOMMUDomain *)value;
     VirtIOIOMMUEndpoint *iter;
+    IOMMUMemoryRegion *mr;
 
     QLIST_FOREACH(iter, &d->endpoint_list, next) {
+        mr = virtio_iommu_mr(s, iter->id);
+        assert(mr);
+
         iter->domain = d;
+        iter->iommu_mr = mr;
         g_tree_insert(s->endpoints, GUINT_TO_POINTER(iter->id), iter);
     }
     return false; /* continue the domain traversal */
@@ -979,6 +1177,9 @@ static void virtio_iommu_memory_region_class_init(ObjectClass *klass,
     IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_CLASS(klass);
 
     imrc->translate = virtio_iommu_translate;
+    imrc->replay = virtio_iommu_replay;
+    imrc->notify_flag_changed = virtio_iommu_notify_flag_changed;
+    imrc->iommu_set_page_size_mask = virtio_iommu_set_page_size_mask;
 }
 
 static const TypeInfo virtio_iommu_info = {