spapr_iommu: Introduce "enabled" state for TCE table

Currently TCE tables are created once at start and their sizes never
change. We are going to change that by introducing a Dynamic DMA windows
support where DMA configuration may change during the guest execution.

This changes spapr_tce_new_table() to create an empty zero-size IOMMU
memory region (IOMMU MR). Only LIOBN is assigned by the time of creation.
It still will be called once at the owner object (VIO or PHB) creation.

This introduces an "enabled" state for TCE table objects, some
helper functions are added:
- spapr_tce_table_enable() receives TCE table parameters, stores in
sPAPRTCETable and allocates a guest view of the TCE table
(in the user space or KVM) and sets the correct size on the IOMMU MR;
- spapr_tce_table_disable() disposes the table and resets the IOMMU MR
size; it is made public as the following DDW code will be using it.

This changes the PHB reset handler to do the default DMA initialization
instead of spapr_phb_realize(). This does not make differenct now but
later with more than just one DMA window, we will have to remove them all
and create the default one on a system reset.

No visible change in behaviour is expected except the actual table
will be reallocated every reset. We might optimize this later.

The other way to implement this would be dynamically create/remove
the TCE table QOM objects but this would make migration impossible
as the migration code expects all QOM objects to exist at the receiver
so we have to have TCE table objects created when migration begins.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

4 files changed, 56 insertions, 37 deletions

diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index 96bb0181a7..de63467ef7 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -17,6 +17,7 @@
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "qemu/osdep.h"
+#include "qemu/error-report.h"
 #include "hw/hw.h"
 #include "qemu/log.h"
 #include "sysemu/kvm.h"
@@ -175,15 +176,9 @@ static int spapr_tce_table_realize(DeviceState *dev)
     sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
 
     tcet->fd = -1;
-    tcet->table = spapr_tce_alloc_table(tcet->liobn,
-                                        tcet->page_shift,
-                                        tcet->nb_table,
-                                        &tcet->fd,
-                                        tcet->need_vfio);
-
+    tcet->need_vfio = false;
     memory_region_init_iommu(&tcet->iommu, OBJECT(dev), &spapr_iommu_ops,
-                             "iommu-spapr",
-                             (uint64_t)tcet->nb_table << tcet->page_shift);
+                             "iommu-spapr", 0);
 
     QLIST_INSERT_HEAD(&spapr_tce_tables, tcet, list);
 
@@ -225,14 +220,10 @@ void spapr_tce_set_need_vfio(sPAPRTCETable *tcet, bool need_vfio)
     tcet->table = newtable;
 }
 
-sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
-                                   uint64_t bus_offset,
-                                   uint32_t page_shift,
-                                   uint32_t nb_table,
-                                   bool need_vfio)
+sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn)
 {
     sPAPRTCETable *tcet;
-    char tmp[64];
+    char tmp[32];
 
     if (spapr_tce_find_by_liobn(liobn)) {
         fprintf(stderr, "Attempted to create TCE table with duplicate"
@@ -240,16 +231,8 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
         return NULL;
     }
 
-    if (!nb_table) {
-        return NULL;
-    }
-
     tcet = SPAPR_TCE_TABLE(object_new(TYPE_SPAPR_TCE_TABLE));
     tcet->liobn = liobn;
-    tcet->bus_offset = bus_offset;
-    tcet->page_shift = page_shift;
-    tcet->nb_table = nb_table;
-    tcet->need_vfio = need_vfio;
 
     snprintf(tmp, sizeof(tmp), "tce-table-%x", liobn);
     object_property_add_child(OBJECT(owner), tmp, OBJECT(tcet), NULL);
@@ -259,14 +242,51 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
     return tcet;
 }
 
+void spapr_tce_table_enable(sPAPRTCETable *tcet,
+                            uint32_t page_shift, uint64_t bus_offset,
+                            uint32_t nb_table)
+{
+    if (tcet->nb_table) {
+        error_report("Warning: trying to enable already enabled TCE table");
+        return;
+    }
+
+    tcet->bus_offset = bus_offset;
+    tcet->page_shift = page_shift;
+    tcet->nb_table = nb_table;
+    tcet->table = spapr_tce_alloc_table(tcet->liobn,
+                                        tcet->page_shift,
+                                        tcet->nb_table,
+                                        &tcet->fd,
+                                        tcet->need_vfio);
+
+    memory_region_set_size(&tcet->iommu,
+                           (uint64_t)tcet->nb_table << tcet->page_shift);
+}
+
+static void spapr_tce_table_disable(sPAPRTCETable *tcet)
+{
+    if (!tcet->nb_table) {
+        return;
+    }
+
+    memory_region_set_size(&tcet->iommu, 0);
+
+    spapr_tce_free_table(tcet->table, tcet->fd, tcet->nb_table);
+    tcet->fd = -1;
+    tcet->table = NULL;
+    tcet->bus_offset = 0;
+    tcet->page_shift = 0;
+    tcet->nb_table = 0;
+}
+
 static void spapr_tce_table_unrealize(DeviceState *dev, Error **errp)
 {
     sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
 
     QLIST_REMOVE(tcet, list);
 
-    spapr_tce_free_table(tcet->table, tcet->fd, tcet->nb_table);
-    tcet->fd = -1;
+    spapr_tce_table_disable(tcet);
 }
 
 MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet)
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index 856aec7f51..7688ae073a 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -1463,8 +1463,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
     }
 
     nb_table = sphb->dma_win_size >> SPAPR_TCE_PAGE_SHIFT;
-    tcet = spapr_tce_new_table(DEVICE(sphb), sphb->dma_liobn,
-                               0, SPAPR_TCE_PAGE_SHIFT, nb_table, false);
+    tcet = spapr_tce_new_table(DEVICE(sphb), sphb->dma_liobn);
     if (!tcet) {
         error_setg(errp, "Unable to create TCE table for %s",
                    sphb->dtbusname);
@@ -1472,7 +1471,10 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
     }
 
     /* Register default 32bit DMA window */
-    memory_region_add_subregion(&sphb->iommu_root, sphb->dma_win_addr,
+    spapr_tce_table_enable(tcet, SPAPR_TCE_PAGE_SHIFT, sphb->dma_win_addr,
+                           nb_table);
+
+    memory_region_add_subregion(&sphb->iommu_root, tcet->bus_offset,
                                 spapr_tce_get_iommu(tcet));
 
     sphb->msi = g_hash_table_new_full(g_int_hash, g_int_equal, g_free, g_free);
diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c
index d084aedadf..3d9b9c60f4 100644
--- a/hw/ppc/spapr_vio.c
+++ b/hw/ppc/spapr_vio.c
@@ -483,11 +483,9 @@ static void spapr_vio_busdev_realize(DeviceState *qdev, Error **errp)
         memory_region_add_subregion_overlap(&dev->mrroot, 0, &dev->mrbypass, 1);
         address_space_init(&dev->as, &dev->mrroot, qdev->id);
 
-        dev->tcet = spapr_tce_new_table(qdev, liobn,
-                                        0,
-                                        SPAPR_TCE_PAGE_SHIFT,
-                                        pc->rtce_window_size >>
-                                        SPAPR_TCE_PAGE_SHIFT, false);
+        dev->tcet = spapr_tce_new_table(qdev, liobn);
+        spapr_tce_table_enable(dev->tcet, SPAPR_TCE_PAGE_SHIFT, 0,
+                               pc->rtce_window_size >> SPAPR_TCE_PAGE_SHIFT);
         dev->tcet->vdev = dev;
         memory_region_add_subregion_overlap(&dev->mrroot, 0,
                                             spapr_tce_get_iommu(dev->tcet), 2);
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 815d5eec45..26c327d74d 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -561,11 +561,10 @@ void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq);
 int spapr_h_cas_compose_response(sPAPRMachineState *sm,
                                  target_ulong addr, target_ulong size,
                                  bool cpu_update, bool memory_update);
-sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
-                                   uint64_t bus_offset,
-                                   uint32_t page_shift,
-                                   uint32_t nb_table,
-                                   bool need_vfio);
+sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn);
+void spapr_tce_table_enable(sPAPRTCETable *tcet,
+                            uint32_t page_shift, uint64_t bus_offset,
+                            uint32_t nb_table);
 void spapr_tce_set_need_vfio(sPAPRTCETable *tcet, bool need_vfio);
 
 MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet);