Skip to contentSkip to conversation

Allow memory_region_register_iommu_notifier() to fail

PATCH Superseded Eric Auger 3 participants 11 messages Sep 13, 2019 – Sep 19, 2019

v1 of 4 Superseded Latest is v4 →

lore
Share & tools
lore

Eric Auger

author
#0 lore raw

cover Allow memory_region_register_iommu_notifier() to fail

This series allows the memory_region_register_iommu_notifier() to fail. As of now, when a MAP notifier is attempted to be registered along with SMMUv3, Intel iommu without caching mode or AMD IOMMU, we exit in the IOMMU MR notify_flag_changed() callback. In case of VFIO assigned device hotplug, this could be handled more nicely directly within the VFIO code, simply rejecting the hotplug without exiting. This is what the series achieves by handling the memory_region_register_iommu_notifier() returned value.

Best Regards

Eric

This series can be found at:
https://github.com/eauger/qemu/tree/v4.1.0_register_iommu_notifier_fail_v1

History:

Follow-up of "VFIO/SMMUv3: Fail on VFIO/HW nested paging detection"
https://patchew.org/QEMU/[email protected]/

Eric Auger (6):
memory: allow memory_region_register_iommu_notifier() to fail vfio/common: Handle memory_region_register_iommu_notifier() failure
exec: assert on memory_region_register_iommu_notifier() failure
vhost: assert on memory_region_register_iommu_notifier() failure
intel_iommu: Let vtd_iommu_notify_flag_changed() fail
amd_iommu: Let amdvi_iommu_notify_flag_changed() fail

 exec.c                |  3 ++-
 hw/arm/smmuv3.c       |  8 +++++---
 hw/i386/amd_iommu.c   |  9 +++++----
 hw/i386/intel_iommu.c |  9 +++++----
 hw/ppc/spapr_iommu.c  |  7 ++++---
 hw/vfio/common.c      |  8 ++++++--
 hw/virtio/vhost.c     |  2 +-
 include/exec/memory.h | 18 +++++++++++++-----
 memory.c              | 28 ++++++++++++++++++----------
 9 files changed, 59 insertions(+), 33 deletions(-)
Signature · 1 line
2.20.1
author
#1 lore raw

PATCH 1/6 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 intel_iommu and amd_iommu code.

---
 hw/arm/smmuv3.c       |  8 +++++---
 hw/i386/amd_iommu.c   |  7 ++++---
 hw/i386/intel_iommu.c |  7 ++++---
 hw/ppc/spapr_iommu.c  |  7 ++++---
 include/exec/memory.h | 18 +++++++++++++-----
 memory.c              | 28 ++++++++++++++++++----------
 6 files changed, 48 insertions(+), 27 deletions(-)
hw/arm/smmuv3.c +5 -3
index db051dcac8..d7a86fc505 100644
@@ -1469,9 +1469,9 @@ 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)
 {
     SMMUDevice *sdev = container_of(iommu, SMMUDevice, iommu);
     SMMUv3State *s3 = sdev->smmu;
@@ -1483,6 +1483,7 @@ static void smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,
 
         warn_report("SMMUv3 does not support notification on MAP: "
                      "device %s will not function properly", pcidev->name);
+        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,
hw/i386/amd_iommu.c +4 -3
index 08884523e2..137ba367db 100644
@@ -1466,9 +1466,9 @@ 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)
 {
     AMDVIAddressSpace *as = container_of(iommu, AMDVIAddressSpace, iommu);
 
@@ -1478,6 +1478,7 @@ static void amdvi_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
                      PCI_FUNC(as->devfn));
         exit(1);
     }
+    return 0;
 }
 
 static void amdvi_init(AMDVIState *s)
hw/i386/intel_iommu.c +4 -3
index 75ca6f9c70..7a89ea9ba1 100644
@@ -2921,9 +2921,9 @@ 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)
 {
     VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
     IntelIOMMUState *s = vtd_as->iommu_state;
@@ -2942,6 +2942,7 @@ 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)
hw/ppc/spapr_iommu.c +4 -3
index e87b3d50f7..8d3b38f90b 100644
@@ -205,9 +205,9 @@ 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)
 {
     struct SpaprTceTable *tbl = container_of(iommu, SpaprTceTable, iommu);
 
@@ -216,6 +216,7 @@ 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)
include/exec/memory.h +13 -5
index 2dd810259d..504c19ecd9 100644
@@ -288,10 +288,14 @@ 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.
      */
-    void (*notify_flag_changed)(IOMMUMemoryRegion *iommu,
-                                IOMMUNotifierFlag old_flags,
-                                IOMMUNotifierFlag new_flags);
+    int (*notify_flag_changed)(IOMMUMemoryRegion *iommu,
+                               IOMMUNotifierFlag old_flags,
+                               IOMMUNotifierFlag new_flags);
     /* Called to handle memory_region_iommu_replay().
      *
      * The default implementation of memory_region_iommu_replay() is to
@@ -1067,13 +1071,17 @@ 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.
+ *
  * @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);
 
 /**
  * memory_region_iommu_replay: replay existing IOMMU translations to
memory.c +18 -10
index 61a254c3f9..699a3d61a6 100644
@@ -1837,33 +1837,37 @@ 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)
 {
     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);
     }
 
-    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)
 {
     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);
     }
 
     /* We need to register for at least one bitfield */
@@ -1874,7 +1878,11 @@ 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);
+    if (ret) {
+        QLIST_REMOVE(n, node);
+    }
+    return ret;
 }
 
 uint64_t memory_region_iommu_get_min_page_size(IOMMUMemoryRegion *iommu_mr)
Signature · 1 line
2.20.1
#2 lore raw

Re: [Qemu-arm] [PATCH v1 1/6] memory: allow memory_region_register_iommu_notifier() to fail

Quoted 10 lines · Eric Auger

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 intel_iommu and amd_iommu code.

The idea looks sane to me, though how about using "Error **" instead of returning int (or, both)? Just like the majority of rest of QEMU.

Regards,

Signature · 1 line
Peter Xu
author
#3 lore raw

Re: [Qemu-arm] [PATCH v1 1/6] memory: allow memory_region_register_iommu_notifier() to fail

Hi Peter,

Quoted 6 lines · Peter Xu
Quoted 5 lines · Eric Auger

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.

Quoted 8 lines
Quoted 5 lines

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 intel_iommu and amd_iommu code.

The idea looks sane to me, though how about using "Error **" instead of returning int (or, both)? Just like the majority of rest of QEMU.

None of the memory_region_register_iommu_notifier callsites would really use the Error object and pass it up. I am a bit reluctant to add it if not really used. There are still plenty of functions in the memory API that do not use any Error handle. Anyway I will follow recommendations if there is a consensus.

Thanks

Eric

Quoted 3 lines

Regards,

author
#4 lore raw

PATCH 2/6 vfio/common: Handle memory_region_register_iommu_notifier() failure

In reply to Eric Auger

Now memory_region_register_iommu_notifier() is allowed to fail, let's handle the returned value in vfio_listener_region_add().

This will allow to remove the error handling (exit) in the IOMMUs that implement a notify_flag_changed() that sometimes cannot accept the MAP flag.

---
 hw/vfio/common.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
hw/vfio/common.c +6 -2
index 3e03c495d8..d57d72cfb9 100644
@@ -630,9 +630,13 @@ 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);
+        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;
Signature · 1 line
2.20.1
author
#5 lore raw

PATCH 3/6 exec: assert on memory_region_register_iommu_notifier() failure

In reply to Eric Auger

memory_region_register_iommu_notifier now returns an error in case of failure. Assert in such a case.

---
 exec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
exec.c +2 -1
index 235d6bc883..da30251a2b 100644
@@ -692,7 +692,8 @@ static void tcg_register_iommu_notifier(CPUState *cpu,
                             0,
                             HWADDR_MAX,
                             iommu_idx);
-        memory_region_register_iommu_notifier(notifier->mr, &notifier->n);
+        assert(!memory_region_register_iommu_notifier(notifier->mr,
+                                                      &notifier->n));
     }
 
     if (!notifier->active) {
Signature · 1 line
2.20.1
#6 lore raw

Re: [Qemu-arm] [Qemu-devel] [PATCH v1 3/6] exec: assert on memory_region_register_iommu_notifier() failure

Quoted 13 lines · Eric Auger

memory_region_register_iommu_notifier now returns an error in case of failure. Assert in such a case.

---
 exec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
exec.c +0 -0
index 235d6bc883..da30251a2b 100644

exec.c static void tcg_register_iommu_notifier(CPUState *cpu, · line 696

Quoted 6 lines
exec.c +2 -1
@@ -692,7 +692,8 @@ static void tcg_register_iommu_notifier(CPUState *cpu,
                             0,
                             HWADDR_MAX,
                             iommu_idx);
-        memory_region_register_iommu_notifier(notifier->mr, &notifier->n);
+        assert(!memory_region_register_iommu_notifier(notifier->mr,
+                                                      &notifier->n));

ret = memory_region_register_iommu_notifier(notifier->mr, &notifier->n); assert(!ret);

to avoid functions with side effects being called inside assert()'s, as assert()'s could be compiled as no-ops.

Same comment for next patch.

Thanks,
drew

Quoted 7 lines
exec.c +0 -0
     }
 
     if (!notifier->active) {
Signature · 1 line
2.20.1
author
#7 lore raw

PATCH 4/6 vhost: assert on memory_region_register_iommu_notifier() failure

In reply to Eric Auger

memory_region_register_iommu_notifier now returns an error in case of failure. Assert in such a case.

---
 hw/virtio/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
hw/virtio/vhost.c +1 -1
index 34accdf615..9b5551fc4d 100644
@@ -696,7 +696,7 @@ 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);
+    assert(!memory_region_register_iommu_notifier(section->mr, &iommu->n));
     QLIST_INSERT_HEAD(&dev->iommu_list, iommu, iommu_next);
     /* TODO: can replay help performance here? */
 }
Signature · 1 line
2.20.1
author
#8 lore raw

PATCH 5/6 intel_iommu: Let vtd_iommu_notify_flag_changed() fail

In reply to Eric Auger

In case a MAP notifier is attempted to be registered without caching mode, let's simply return an error. This latter now is handled in the VFIO code.

---
 hw/i386/intel_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
hw/i386/intel_iommu.c +1 -1
index 7a89ea9ba1..2f66d6882c 100644
@@ -2931,7 +2931,7 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
     if (!s->caching_mode && new & IOMMU_NOTIFIER_MAP) {
         error_report("We need to set caching-mode=on for intel-iommu to enable "
                      "device assignment with IOMMU protection.");
-        exit(1);
+        return -EINVAL;
     }
 
     /* Update per-address-space notifier flags */
Signature · 1 line
2.20.1
#9 lore raw

Re: [Qemu-devel] [PATCH v1 5/6] intel_iommu: Let vtd_iommu_notify_flag_changed() fail

Quoted 14 lines · Eric Auger

In case a MAP notifier is attempted to be registered without caching mode, let's simply return an error. This latter now is handled in the VFIO code.

---
 hw/i386/intel_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
hw/i386/intel_iommu.c +0 -0
index 7a89ea9ba1..2f66d6882c 100644

hw/i386/intel_iommu.c static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu, · line 2934

Quoted 5 lines
hw/i386/intel_iommu.c +1 -1
@@ -2931,7 +2931,7 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
     if (!s->caching_mode && new & IOMMU_NOTIFIER_MAP) {
         error_report("We need to set caching-mode=on for intel-iommu to enable "
                      "device assignment with IOMMU protection.");
-        exit(1);
+        return -EINVAL;

This might be conflicting with the other series because that's going to drop these lines:

https://lists.gnu.org/archive/html/qemu-devel/2019-08/msg01968.html

Though current change looks ok to me, and I don't even know which one will reach master earlier after all so let's see. :)

The rest patches besides patch 1 all look sane to me. If we're going to have "Error **" then the rest patches might need trivial touch-ups of course. And, IMHO squashing the whole series into patch 1 could be better, but it's a personal preference only.

Thanks,

Signature · 1 line
Peter Xu
author
#10 lore raw

PATCH 6/6 amd_iommu: Let amdvi_iommu_notify_flag_changed() fail

In reply to Eric Auger

In case a MAP notifier is attempted to be registered, let's simply return an error. This latter now is handled in the VFIO code.

---
 hw/i386/amd_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
hw/i386/amd_iommu.c +1 -1
index 137ba367db..09dee48fac 100644
@@ -1476,7 +1476,7 @@ static int amdvi_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
         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);
+        return -EINVAL;
     }
     return 0;
 }
Signature · 1 line
2.20.1