[Qemu-devel] [PATCH qemu v18 1/5] memory: Add reporting of supported page sizes

[Alexey Kardashevskiy]

Every IOMMU has some granularity which MemoryRegionIOMMUOps::translate
uses when translating, however this information is not available outside
the translate context for various checks.

This adds a get_min_page_size callback to MemoryRegionIOMMUOps and
a wrapper for it so IOMMU users (such as VFIO) can know the minimum
actual page size supported by an IOMMU.

As IOMMU MR represents a guest IOMMU, this uses TARGET_PAGE_SIZE
as fallback.

This removes vfio_container_granularity() and uses new helper in
memory_region_iommu_replay() when replaying IOMMU mappings on added
IOMMU memory region.

Signed-off-by: Alexey Kardashevskiy <address@hidden>
Reviewed-by: David Gibson <address@hidden>
Acked-by: Alex Williamson <address@hidden>
---
Changes:
v18:
* fixed unnecessary line wrap
* s/get_page_sizes/get_min_page_size/

v16:
* used memory_region_iommu_get_page_sizes() instead of
mr->iommu_ops->get_page_sizes() in memory_region_iommu_replay()

v15:
* s/qemu_real_host_page_size/TARGET_PAGE_SIZE/ in 
memory_region_iommu_get_page_sizes

v14:
* removed vfio_container_granularity(), changed memory_region_iommu_replay()

v4:
* s/1<<TARGET_PAGE_BITS/qemu_real_host_page_size/
---
 hw/ppc/spapr_iommu.c  |  8 ++++++++
 hw/vfio/common.c      |  9 +--------
 include/exec/memory.h | 19 +++++++++++++++----
 memory.c              | 16 +++++++++++++---
 4 files changed, 37 insertions(+), 15 deletions(-)

diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index a3cc572..e230bac 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -149,6 +149,13 @@ static void spapr_tce_table_pre_save(void *opaque)
                                tcet->bus_offset, tcet->page_shift);
 }
 
+static uint64_t spapr_tce_get_min_page_size(MemoryRegion *iommu)
+{
+    sPAPRTCETable *tcet = container_of(iommu, sPAPRTCETable, iommu);
+
+    return 1ULL << tcet->page_shift;
+}
+
 static int spapr_tce_table_post_load(void *opaque, int version_id)
 {
     sPAPRTCETable *tcet = SPAPR_TCE_TABLE(opaque);
@@ -228,6 +235,7 @@ static const VMStateDescription vmstate_spapr_tce_table = {
 
 static MemoryRegionIOMMUOps spapr_iommu_ops = {
     .translate = spapr_tce_translate_iommu,
+    .get_min_page_size = spapr_tce_get_min_page_size,
 };
 
 static int spapr_tce_table_realize(DeviceState *dev)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 1898f1f..27cc159 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -321,11 +321,6 @@ out:
     rcu_read_unlock();
 }
 
-static hwaddr vfio_container_granularity(VFIOContainer *container)
-{
-    return (hwaddr)1 << ctz64(container->iova_pgsizes);
-}
-
 static void vfio_listener_region_add(MemoryListener *listener,
                                      MemoryRegionSection *section)
 {
@@ -392,9 +387,7 @@ static void vfio_listener_region_add(MemoryListener 
*listener,
         QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
 
         memory_region_register_iommu_notifier(giommu->iommu, &giommu->n);
-        memory_region_iommu_replay(giommu->iommu, &giommu->n,
-                                   vfio_container_granularity(container),
-                                   false);
+        memory_region_iommu_replay(giommu->iommu, &giommu->n, false);
 
         return;
     }
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 4ab6800..e3829f7 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -151,6 +151,8 @@ typedef struct MemoryRegionIOMMUOps MemoryRegionIOMMUOps;
 struct MemoryRegionIOMMUOps {
     /* Return a TLB entry that contains a given address. */
     IOMMUTLBEntry (*translate)(MemoryRegion *iommu, hwaddr addr, bool 
is_write);
+    /* Returns minimum supported page size */
+    uint64_t (*get_min_page_size)(MemoryRegion *iommu);
 };
 
 typedef struct CoalescedMemoryRange CoalescedMemoryRange;
@@ -573,6 +575,16 @@ static inline bool memory_region_is_iommu(MemoryRegion *mr)
 
 
 /**
+ * memory_region_iommu_get_min_page_size: get minimum supported page size
+ * for an iommu
+ *
+ * Returns minimum supported page size for an iommu.
+ *
+ * @mr: the memory region being queried
+ */
+uint64_t memory_region_iommu_get_min_page_size(MemoryRegion *mr);
+
+/**
  * memory_region_notify_iommu: notify a change in an IOMMU translation entry.
  *
  * @mr: the memory region that was changed
@@ -596,16 +608,15 @@ void memory_region_register_iommu_notifier(MemoryRegion 
*mr, Notifier *n);
 
 /**
  * memory_region_iommu_replay: replay existing IOMMU translations to
- * a notifier
+ * a notifier with the minimum page granularity returned by
+ * mr->iommu_ops->get_page_size().
  *
  * @mr: the memory region to observe
  * @n: the notifier to which to replay iommu mappings
- * @granularity: Minimum page granularity to replay notifications for
  * @is_write: Whether to treat the replay as a translate "write"
  *     through the iommu
  */
-void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n,
-                                hwaddr granularity, bool is_write);
+void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n, bool is_write);
 
 /**
  * memory_region_unregister_iommu_notifier: unregister a notifier for
diff --git a/memory.c b/memory.c
index 8ba496d..fe44e29 100644
--- a/memory.c
+++ b/memory.c
@@ -1502,12 +1502,22 @@ void memory_region_register_iommu_notifier(MemoryRegion 
*mr, Notifier *n)
     notifier_list_add(&mr->iommu_notify, n);
 }
 
-void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n,
-                                hwaddr granularity, bool is_write)
+uint64_t memory_region_iommu_get_min_page_size(MemoryRegion *mr)
 {
-    hwaddr addr;
+    assert(memory_region_is_iommu(mr));
+    if (mr->iommu_ops && mr->iommu_ops->get_min_page_size) {
+        return mr->iommu_ops->get_min_page_size(mr);
+    }
+    return TARGET_PAGE_SIZE;
+}
+
+void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n, bool is_write)
+{
+    hwaddr addr, granularity;
     IOMMUTLBEntry iotlb;
 
+    granularity = (hwaddr)1 << 
ctz64(memory_region_iommu_get_min_page_size(mr));
+
     for (addr = 0; addr < memory_region_size(mr); addr += granularity) {
         iotlb = mr->iommu_ops->translate(mr, addr, is_write);
         if (iotlb.perm != IOMMU_NONE) {
-- 
2.5.0.rc3