memory: allow memory_region_register_iommu_notifier() to fail

Currently, when a notifier is attempted to be registered and its
flags are not supported (especially the MAP one) by the IOMMU MR,
we generally abruptly exit in the IOMMU code. The failure could be
handled more nicely in the caller and especially in the VFIO code.

So let's allow memory_region_register_iommu_notifier() to fail as
well as notify_flag_changed() callback.

All sites implementing the callback are updated. This patch does
not yet remove the exit(1) in the amd_iommu code.

in SMMUv3 we turn the warning message into an error message saying
that the assigned device would not work properly.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/exec.c b/exec.c
index 1d6e4d8608408c4b22adea2ac37fc5b0db09d6bd..bdcfcdff3f976d4a8c7dadd0830af7ca2e976ab2 100644 (file)
--- a/exec.c
+++ b/exec.c
@@ -660,7 +660,8 @@ static void tcg_register_iommu_notifier(CPUState *cpu,
      */
     MemoryRegion *mr = MEMORY_REGION(iommu_mr);
     TCGIOMMUNotifier *notifier;
-    int i;
+    Error *err = NULL;
+    int i, ret;
 
     for (i = 0; i < cpu->iommu_notifiers->len; i++) {
         notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i);
@@ -689,7 +690,12 @@ static void tcg_register_iommu_notifier(CPUState *cpu,
                             0,
                             HWADDR_MAX,
                             iommu_idx);
-        memory_region_register_iommu_notifier(notifier->mr, &notifier->n);
+        ret = memory_region_register_iommu_notifier(notifier->mr, &notifier->n,
+                                                    &err);
+        if (ret) {
+            error_report_err(err);
+            exit(1);
+        }
     }
 
     if (!notifier->active) {

diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
index db051dcac87d249687419dadbaa27f077afbcd8d..e2fbb8357ea521cd4ca6185b3c7aad2e4af3460a 100644 (file)
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -1469,20 +1469,21 @@ static void smmuv3_class_init(ObjectClass *klass, void *data)
     dc->realize = smmu_realize;
 }
 
-static void smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,
-                                       IOMMUNotifierFlag old,
-                                       IOMMUNotifierFlag new)
+static int smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,
+                                      IOMMUNotifierFlag old,
+                                      IOMMUNotifierFlag new,
+                                      Error **errp)
 {
     SMMUDevice *sdev = container_of(iommu, SMMUDevice, iommu);
     SMMUv3State *s3 = sdev->smmu;
     SMMUState *s = &(s3->smmu_state);
 
     if (new & IOMMU_NOTIFIER_MAP) {
-        int bus_num = pci_bus_num(sdev->bus);
-        PCIDevice *pcidev = pci_find_device(sdev->bus, bus_num, sdev->devfn);
-
-        warn_report("SMMUv3 does not support notification on MAP: "
-                     "device %s will not function properly", pcidev->name);
+        error_setg(errp,
+                   "device %02x.%02x.%x requires iommu MAP notifier which is "
+                   "not currently supported", pci_bus_num(sdev->bus),
+                   PCI_SLOT(sdev->devfn), PCI_FUNC(sdev->devfn));
+        return -EINVAL;
     }
 
     if (old == IOMMU_NOTIFIER_NONE) {
@@ -1492,6 +1493,7 @@ static void smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,
         trace_smmuv3_notify_flag_del(iommu->parent_obj.name);
         QLIST_REMOVE(sdev, next);
     }
+    return 0;
 }
 
 static void smmuv3_iommu_memory_region_class_init(ObjectClass *klass,

diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c
index 08884523e2ca94dc7cceae24da0126597b1c98d5..d3726361dda0579845aed9695c01088ab7464dc1 100644 (file)
--- a/hw/i386/amd_iommu.c
+++ b/hw/i386/amd_iommu.c
@@ -1466,18 +1466,21 @@ static const MemoryRegionOps mmio_mem_ops = {
     }
 };
 
-static void amdvi_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
-                                            IOMMUNotifierFlag old,
-                                            IOMMUNotifierFlag new)
+static int amdvi_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
+                                           IOMMUNotifierFlag old,
+                                           IOMMUNotifierFlag new,
+                                           Error **errp)
 {
     AMDVIAddressSpace *as = container_of(iommu, AMDVIAddressSpace, iommu);
 
     if (new & IOMMU_NOTIFIER_MAP) {
-        error_report("device %02x.%02x.%x requires iommu notifier which is not "
-                     "currently supported", as->bus_num, PCI_SLOT(as->devfn),
-                     PCI_FUNC(as->devfn));
-        exit(1);
+        error_setg(errp,
+                   "device %02x.%02x.%x requires iommu notifier which is not "
+                   "currently supported", as->bus_num, PCI_SLOT(as->devfn),
+                   PCI_FUNC(as->devfn));
+        return -EINVAL;
     }
+    return 0;
 }
 
 static void amdvi_init(AMDVIState *s)

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index f1de8fdb7598c57d3482a37d87dd1ee85c20f9bb..771bed25c9031f7738a1b7094374da6b02d8490a 100644 (file)
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -2929,9 +2929,10 @@ static IOMMUTLBEntry vtd_iommu_translate(IOMMUMemoryRegion *iommu, hwaddr addr,
     return iotlb;
 }
 
-static void vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
-                                          IOMMUNotifierFlag old,
-                                          IOMMUNotifierFlag new)
+static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
+                                         IOMMUNotifierFlag old,
+                                         IOMMUNotifierFlag new,
+                                         Error **errp)
 {
     VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
     IntelIOMMUState *s = vtd_as->iommu_state;
@@ -2944,6 +2945,7 @@ static void vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
     } else if (new == IOMMU_NOTIFIER_NONE) {
         QLIST_REMOVE(vtd_as, next);
     }
+    return 0;
 }
 
 static int vtd_post_load(void *opaque, int version_id)

diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index e87b3d50f7e561f47e46ffcc2f318b1f7b334ffd..3d3bcc86496a5277d62f7855fbb09c013c015f27 100644 (file)
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -205,9 +205,10 @@ static int spapr_tce_get_attr(IOMMUMemoryRegion *iommu,
     return -EINVAL;
 }
 
-static void spapr_tce_notify_flag_changed(IOMMUMemoryRegion *iommu,
-                                          IOMMUNotifierFlag old,
-                                          IOMMUNotifierFlag new)
+static int spapr_tce_notify_flag_changed(IOMMUMemoryRegion *iommu,
+                                         IOMMUNotifierFlag old,
+                                         IOMMUNotifierFlag new,
+                                         Error **errp)
 {
     struct SpaprTceTable *tbl = container_of(iommu, SpaprTceTable, iommu);
 
@@ -216,6 +217,7 @@ static void spapr_tce_notify_flag_changed(IOMMUMemoryRegion *iommu,
     } else if (old != IOMMU_NOTIFIER_NONE && new == IOMMU_NOTIFIER_NONE) {
         spapr_tce_set_need_vfio(tbl, false);
     }
+    return 0;
 }
 
 static int spapr_tce_table_post_load(void *opaque, int version_id)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index cebbb1c28a5dbf3443b6b72e8235b7f09ee6ec8e..5ca11488d67635c09088b3f5b789b68dc815a512 100644 (file)
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -636,9 +636,14 @@ static void vfio_listener_region_add(MemoryListener *listener,
                             section->offset_within_region,
                             int128_get64(llend),
                             iommu_idx);
-        QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
 
-        memory_region_register_iommu_notifier(section->mr, &giommu->n);
+        ret = memory_region_register_iommu_notifier(section->mr, &giommu->n,
+                                                    &err);
+        if (ret) {
+            g_free(giommu);
+            goto fail;
+        }
+        QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
         memory_region_iommu_replay(giommu->iommu, &giommu->n);
 
         return;

diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 2386b511f311223c1938aea5c2db5dbcdafa4080..99de5f196fc723f04e768f7428872083c043bd3b 100644 (file)
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -677,8 +677,9 @@ static void vhost_iommu_region_add(MemoryListener *listener,
                                          iommu_listener);
     struct vhost_iommu *iommu;
     Int128 end;
-    int iommu_idx;
+    int iommu_idx, ret;
     IOMMUMemoryRegion *iommu_mr;
+    Error *err = NULL;
 
     if (!memory_region_is_iommu(section->mr)) {
         return;
@@ -701,7 +702,11 @@ static void vhost_iommu_region_add(MemoryListener *listener,
     iommu->iommu_offset = section->offset_within_address_space -
                           section->offset_within_region;
     iommu->hdev = dev;
-    memory_region_register_iommu_notifier(section->mr, &iommu->n);
+    ret = memory_region_register_iommu_notifier(section->mr, &iommu->n, &err);
+    if (ret) {
+        error_report_err(err);
+        exit(1);
+    }
     QLIST_INSERT_HEAD(&dev->iommu_list, iommu, iommu_next);
     /* TODO: can replay help performance here? */
 }

diff --git a/include/exec/memory.h b/include/exec/memory.h
index 6e67043ee03b1a11a8a7bd62263e2e4fe69333f0..e499dc215b3021a11e981ff6d9828abcf3d7d319 100644 (file)
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -288,10 +288,16 @@ typedef struct IOMMUMemoryRegionClass {
      * @iommu: the IOMMUMemoryRegion
      * @old_flags: events which previously needed to be notified
      * @new_flags: events which now need to be notified
+     *
+     * Returns 0 on success, or a negative errno; in particular
+     * returns -EINVAL if the new flag bitmap is not supported by the
+     * IOMMU memory region. In case of failure, the error object
+     * must be created
      */
-    void (*notify_flag_changed)(IOMMUMemoryRegion *iommu,
-                                IOMMUNotifierFlag old_flags,
-                                IOMMUNotifierFlag new_flags);
+    int (*notify_flag_changed)(IOMMUMemoryRegion *iommu,
+                               IOMMUNotifierFlag old_flags,
+                               IOMMUNotifierFlag new_flags,
+                               Error **errp);
     /* Called to handle memory_region_iommu_replay().
      *
      * The default implementation of memory_region_iommu_replay() is to
@@ -1079,13 +1085,18 @@ void memory_region_notify_one(IOMMUNotifier *notifier,
  * memory_region_register_iommu_notifier: register a notifier for changes to
  * IOMMU translation entries.
  *
+ * Returns 0 on success, or a negative errno otherwise. In particular,
+ * -EINVAL indicates that at least one of the attributes of the notifier
+ * is not supported (flag/range) by the IOMMU memory region. In case of error
+ * the error object must be created.
+ *
  * @mr: the memory region to observe
  * @n: the IOMMUNotifier to be added; the notify callback receives a
  *     pointer to an #IOMMUTLBEntry as the opaque value; the pointer
  *     ceases to be valid on exit from the notifier.
  */
-void memory_region_register_iommu_notifier(MemoryRegion *mr,
-                                           IOMMUNotifier *n);
+int memory_region_register_iommu_notifier(MemoryRegion *mr,
+                                          IOMMUNotifier *n, Error **errp);
 
 /**
  * memory_region_iommu_replay: replay existing IOMMU translations to

diff --git a/memory.c b/memory.c
index a99b8c076778f2b7ddffea3f8dd133609f308287..978da3d3df65aab2fb6b6f7f6d99beb9e7812cbf 100644 (file)
--- a/memory.c
+++ b/memory.c
@@ -1817,33 +1817,38 @@ bool memory_region_is_logging(MemoryRegion *mr, uint8_t client)
     return memory_region_get_dirty_log_mask(mr) & (1 << client);
 }
 
-static void memory_region_update_iommu_notify_flags(IOMMUMemoryRegion *iommu_mr)
+static int memory_region_update_iommu_notify_flags(IOMMUMemoryRegion *iommu_mr,
+                                                   Error **errp)
 {
     IOMMUNotifierFlag flags = IOMMU_NOTIFIER_NONE;
     IOMMUNotifier *iommu_notifier;
     IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_GET_CLASS(iommu_mr);
+    int ret = 0;
 
     IOMMU_NOTIFIER_FOREACH(iommu_notifier, iommu_mr) {
         flags |= iommu_notifier->notifier_flags;
     }
 
     if (flags != iommu_mr->iommu_notify_flags && imrc->notify_flag_changed) {
-        imrc->notify_flag_changed(iommu_mr,
-                                  iommu_mr->iommu_notify_flags,
-                                  flags);
+        ret = imrc->notify_flag_changed(iommu_mr,
+                                        iommu_mr->iommu_notify_flags,
+                                        flags, errp);
     }
 
-    iommu_mr->iommu_notify_flags = flags;
+    if (!ret) {
+        iommu_mr->iommu_notify_flags = flags;
+    }
+    return ret;
 }
 
-void memory_region_register_iommu_notifier(MemoryRegion *mr,
-                                           IOMMUNotifier *n)
+int memory_region_register_iommu_notifier(MemoryRegion *mr,
+                                          IOMMUNotifier *n, Error **errp)
 {
     IOMMUMemoryRegion *iommu_mr;
+    int ret;
 
     if (mr->alias) {
-        memory_region_register_iommu_notifier(mr->alias, n);
-        return;
+        return memory_region_register_iommu_notifier(mr->alias, n, errp);
     }
 
     /* We need to register for at least one bitfield */
@@ -1854,7 +1859,11 @@ void memory_region_register_iommu_notifier(MemoryRegion *mr,
            n->iommu_idx < memory_region_iommu_num_indexes(iommu_mr));
 
     QLIST_INSERT_HEAD(&iommu_mr->iommu_notify, n, node);
-    memory_region_update_iommu_notify_flags(iommu_mr);
+    ret = memory_region_update_iommu_notify_flags(iommu_mr, errp);
+    if (ret) {
+        QLIST_REMOVE(n, node);
+    }
+    return ret;
 }
 
 uint64_t memory_region_iommu_get_min_page_size(IOMMUMemoryRegion *iommu_mr)
@@ -1907,7 +1916,7 @@ void memory_region_unregister_iommu_notifier(MemoryRegion *mr,
     }
     QLIST_REMOVE(n, node);
     iommu_mr = IOMMU_MEMORY_REGION(mr);
-    memory_region_update_iommu_notify_flags(iommu_mr);
+    memory_region_update_iommu_notify_flags(iommu_mr, NULL);
 }
 
 void memory_region_notify_one(IOMMUNotifier *notifier,