Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.6-20160316' into staging

ppc patch queue for 2016-03-16

Accumulated patches for target-ppc, pseries machine type and related
devices.  As we are now in soft freeze, these are mostly fixes.
   * Fix KVM migration for several SPRs that qemu didn't handle
   * Clean up handling of SDR1, which allows a fix to the gdbstub
   * Fix a race in spapr_rng
   * Fix a bug with multifunction hotplug

The exception is the 7 patches to allow EEH on spapr-pci-host-bridge
devices (rather than the special and poorly designed
spapr-vfio-pci-host-bridge device).  I believe these are low risk of
breaking non-EEH cases, and EEH cases were little used in practice
previously (since libvirt did not support the special device amongst
other things).  It did have a draft posted before the soft freeze,
removes a very ugly VFIO interface, and removes device we'd like to
deprecate sooner rather than later.  So, I'm hoping we can squeeze
these in during the soft freeze.

This includes two patches to the VFIO code, which Alex Williamson has
indicated he's ok with coming through my tree.

# gpg: Signature made Wed 16 Mar 2016 05:04:52 GMT using RSA key ID 20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-2.6-20160316:
  vfio: Eliminate vfio_container_ioctl()
  spapr_pci: Remove finish_realize hook
  spapr_pci: (Mostly) remove spapr-pci-vfio-host-bridge
  spapr_pci: Allow EEH on spapr-pci-host-bridge
  spapr_pci: Eliminate class callbacks
  spapr_pci: Switch to vfio_eeh_as_op() interface
  vfio: Start improving VFIO/EEH interface
  spapr_rng: fix race with main loop
  target-ppc: Eliminate kvmppc_kern_htab global
  target-ppc: Add helpers for updating a CPU's SDR1 and external HPT
  target-ppc: Split out SREGS get/put functions
  spapr_pci: fix multifunction hotplug
  target-ppc: Add PVR for POWER8NVL processor
  ppc: Add a few more P8 PMU SPRs
  ppc: Fix migration of the TAR SPR
  ppc: Define the PSPB register on POWER8

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 241 insertions, 188 deletions

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 298171a205..79a70a9c0f 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1091,7 +1091,7 @@ static void spapr_reallocate_hpt(sPAPRMachineState *spapr, int shift,
         }
 
         spapr->htab_shift = shift;
-        kvmppc_kern_htab = true;
+        spapr->htab = NULL;
     } else {
         /* kernel-side HPT not needed, allocate in userspace instead */
         size_t size = 1ULL << shift;
@@ -1106,7 +1106,6 @@ static void spapr_reallocate_hpt(sPAPRMachineState *spapr, int shift,
 
         memset(spapr->htab, 0, size);
         spapr->htab_shift = shift;
-        kvmppc_kern_htab = false;
 
         for (i = 0; i < size / HASH_PTE_SIZE_64; i++) {
             DIRTY_HPTE(HPTE(spapr->htab, i));
@@ -1196,17 +1195,8 @@ static void spapr_cpu_reset(void *opaque)
 
     env->spr[SPR_HIOR] = 0;
 
-    env->external_htab = (uint8_t *)spapr->htab;
-    env->htab_base = -1;
-    /*
-     * htab_mask is the mask used to normalize hash value to PTEG index.
-     * htab_shift is log2 of hash table size.
-     * We have 8 hpte per group, and each hpte is 16 bytes.
-     * ie have 128 bytes per hpte entry.
-     */
-    env->htab_mask = (1ULL << (spapr->htab_shift - 7)) - 1;
-    env->spr[SPR_SDR1] = (target_ulong)(uintptr_t)spapr->htab |
-        (spapr->htab_shift - 18);
+    ppc_hash64_set_external_hpt(cpu, spapr->htab, spapr->htab_shift,
+                                &error_fatal);
 }
 
 static void spapr_create_nvram(sPAPRMachineState *spapr)
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 1733482de6..b2b1b93cfd 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -122,17 +122,17 @@ static target_ulong h_enter(PowerPCCPU *cpu, sPAPRMachineState *spapr,
                 break;
             }
         }
-        ppc_hash64_stop_access(token);
+        ppc_hash64_stop_access(cpu, token);
         if (index == 8) {
             return H_PTEG_FULL;
         }
     } else {
         token = ppc_hash64_start_access(cpu, pte_index);
         if (ppc_hash64_load_hpte0(cpu, token, 0) & HPTE64_V_VALID) {
-            ppc_hash64_stop_access(token);
+            ppc_hash64_stop_access(cpu, token);
             return H_PTEG_FULL;
         }
-        ppc_hash64_stop_access(token);
+        ppc_hash64_stop_access(cpu, token);
     }
 
     ppc_hash64_store_hpte(cpu, pte_index + index,
@@ -165,7 +165,7 @@ static RemoveResult remove_hpte(PowerPCCPU *cpu, target_ulong ptex,
     token = ppc_hash64_start_access(cpu, ptex);
     v = ppc_hash64_load_hpte0(cpu, token, 0);
     r = ppc_hash64_load_hpte1(cpu, token, 0);
-    ppc_hash64_stop_access(token);
+    ppc_hash64_stop_access(cpu, token);
 
     if ((v & HPTE64_V_VALID) == 0 ||
         ((flags & H_AVPN) && (v & ~0x7fULL) != avpn) ||
@@ -288,7 +288,7 @@ static target_ulong h_protect(PowerPCCPU *cpu, sPAPRMachineState *spapr,
     token = ppc_hash64_start_access(cpu, pte_index);
     v = ppc_hash64_load_hpte0(cpu, token, 0);
     r = ppc_hash64_load_hpte1(cpu, token, 0);
-    ppc_hash64_stop_access(token);
+    ppc_hash64_stop_access(cpu, token);
 
     if ((v & HPTE64_V_VALID) == 0 ||
         ((flags & H_AVPN) && (v & ~0x7fULL) != avpn)) {
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index 3fc78955ec..79baa7b177 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -42,6 +42,8 @@
 #include "hw/ppc/spapr_drc.h"
 #include "sysemu/device_tree.h"
 
+#include "hw/vfio/vfio.h"
+
 /* Copied from the kernel arch/powerpc/platforms/pseries/msi.c */
 #define RTAS_QUERY_FN           0
 #define RTAS_CHANGE_FN          1
@@ -440,7 +442,6 @@ static void rtas_ibm_set_eeh_option(PowerPCCPU *cpu,
                                     target_ulong rets)
 {
     sPAPRPHBState *sphb;
-    sPAPRPHBClass *spc;
     uint32_t addr, option;
     uint64_t buid;
     int ret;
@@ -458,12 +459,11 @@ static void rtas_ibm_set_eeh_option(PowerPCCPU *cpu,
         goto param_error_exit;
     }
 
-    spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
-    if (!spc->eeh_set_option) {
+    if (!spapr_phb_eeh_available(sphb)) {
         goto param_error_exit;
     }
 
-    ret = spc->eeh_set_option(sphb, addr, option);
+    ret = spapr_phb_vfio_eeh_set_option(sphb, addr, option);
     rtas_st(rets, 0, ret);
     return;
 
@@ -478,7 +478,6 @@ static void rtas_ibm_get_config_addr_info2(PowerPCCPU *cpu,
                                            target_ulong rets)
 {
     sPAPRPHBState *sphb;
-    sPAPRPHBClass *spc;
     PCIDevice *pdev;
     uint32_t addr, option;
     uint64_t buid;
@@ -493,8 +492,7 @@ static void rtas_ibm_get_config_addr_info2(PowerPCCPU *cpu,
         goto param_error_exit;
     }
 
-    spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
-    if (!spc->eeh_set_option) {
+    if (!spapr_phb_eeh_available(sphb)) {
         goto param_error_exit;
     }
 
@@ -534,7 +532,6 @@ static void rtas_ibm_read_slot_reset_state2(PowerPCCPU *cpu,
                                             target_ulong rets)
 {
     sPAPRPHBState *sphb;
-    sPAPRPHBClass *spc;
     uint64_t buid;
     int state, ret;
 
@@ -548,12 +545,11 @@ static void rtas_ibm_read_slot_reset_state2(PowerPCCPU *cpu,
         goto param_error_exit;
     }
 
-    spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
-    if (!spc->eeh_get_state) {
+    if (!spapr_phb_eeh_available(sphb)) {
         goto param_error_exit;
     }
 
-    ret = spc->eeh_get_state(sphb, &state);
+    ret = spapr_phb_vfio_eeh_get_state(sphb, &state);
     rtas_st(rets, 0, ret);
     if (ret != RTAS_OUT_SUCCESS) {
         return;
@@ -578,7 +574,6 @@ static void rtas_ibm_set_slot_reset(PowerPCCPU *cpu,
                                     target_ulong rets)
 {
     sPAPRPHBState *sphb;
-    sPAPRPHBClass *spc;
     uint32_t option;
     uint64_t buid;
     int ret;
@@ -594,12 +589,11 @@ static void rtas_ibm_set_slot_reset(PowerPCCPU *cpu,
         goto param_error_exit;
     }
 
-    spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
-    if (!spc->eeh_reset) {
+    if (!spapr_phb_eeh_available(sphb)) {
         goto param_error_exit;
     }
 
-    ret = spc->eeh_reset(sphb, option);
+    ret = spapr_phb_vfio_eeh_reset(sphb, option);
     rtas_st(rets, 0, ret);
     return;
 
@@ -614,7 +608,6 @@ static void rtas_ibm_configure_pe(PowerPCCPU *cpu,
                                   target_ulong rets)
 {
     sPAPRPHBState *sphb;
-    sPAPRPHBClass *spc;
     uint64_t buid;
     int ret;
 
@@ -628,12 +621,11 @@ static void rtas_ibm_configure_pe(PowerPCCPU *cpu,
         goto param_error_exit;
     }
 
-    spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
-    if (!spc->eeh_configure) {
+    if (!spapr_phb_eeh_available(sphb)) {
         goto param_error_exit;
     }
 
-    ret = spc->eeh_configure(sphb);
+    ret = spapr_phb_vfio_eeh_configure(sphb);
     rtas_st(rets, 0, ret);
     return;
 
@@ -649,7 +641,6 @@ static void rtas_ibm_slot_error_detail(PowerPCCPU *cpu,
                                        target_ulong rets)
 {
     sPAPRPHBState *sphb;
-    sPAPRPHBClass *spc;
     int option;
     uint64_t buid;
 
@@ -663,8 +654,7 @@ static void rtas_ibm_slot_error_detail(PowerPCCPU *cpu,
         goto param_error_exit;
     }
 
-    spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
-    if (!spc->eeh_set_option) {
+    if (!spapr_phb_eeh_available(sphb)) {
         goto param_error_exit;
     }
 
@@ -1142,14 +1132,21 @@ static void spapr_phb_remove_pci_device(sPAPRDRConnector *drc,
     drck->detach(drc, DEVICE(pdev), spapr_phb_remove_pci_device_cb, phb, errp);
 }
 
-static sPAPRDRConnector *spapr_phb_get_pci_drc(sPAPRPHBState *phb,
-                                               PCIDevice *pdev)
+static sPAPRDRConnector *spapr_phb_get_pci_func_drc(sPAPRPHBState *phb,
+                                                    uint32_t busnr,
+                                                    int32_t devfn)
 {
-    uint32_t busnr = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))));
     return spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_PCI,
                                     (phb->index << 16) |
                                     (busnr << 8) |
-                                    pdev->devfn);
+                                    devfn);
+}
+
+static sPAPRDRConnector *spapr_phb_get_pci_drc(sPAPRPHBState *phb,
+                                               PCIDevice *pdev)
+{
+    uint32_t busnr = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))));
+    return spapr_phb_get_pci_func_drc(phb, busnr, pdev->devfn);
 }
 
 static uint32_t spapr_phb_get_pci_drc_index(sPAPRPHBState *phb,
@@ -1173,6 +1170,8 @@ static void spapr_phb_hot_plug_child(HotplugHandler *plug_handler,
     PCIDevice *pdev = PCI_DEVICE(plugged_dev);
     sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev);
     Error *local_err = NULL;
+    PCIBus *bus = PCI_BUS(qdev_get_parent_bus(DEVICE(pdev)));
+    uint32_t slotnr = PCI_SLOT(pdev->devfn);
 
     /* if DR is disabled we don't need to do anything in the case of
      * hotplug or coldplug callbacks
@@ -1190,13 +1189,44 @@ static void spapr_phb_hot_plug_child(HotplugHandler *plug_handler,
 
     g_assert(drc);
 
+    /* Following the QEMU convention used for PCIe multifunction
+     * hotplug, we do not allow functions to be hotplugged to a
+     * slot that already has function 0 present
+     */
+    if (plugged_dev->hotplugged && bus->devices[PCI_DEVFN(slotnr, 0)] &&
+        PCI_FUNC(pdev->devfn) != 0) {
+        error_setg(errp, "PCI: slot %d function 0 already ocuppied by %s,"
+                   " additional functions can no longer be exposed to guest.",
+                   slotnr, bus->devices[PCI_DEVFN(slotnr, 0)]->name);
+        return;
+    }
+
     spapr_phb_add_pci_device(drc, phb, pdev, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         return;
     }
-    if (plugged_dev->hotplugged) {
-        spapr_hotplug_req_add_by_index(drc);
+
+    /* If this is function 0, signal hotplug for all the device functions.
+     * Otherwise defer sending the hotplug event.
+     */
+    if (plugged_dev->hotplugged && PCI_FUNC(pdev->devfn) == 0) {
+        int i;
+
+        for (i = 0; i < 8; i++) {
+            sPAPRDRConnector *func_drc;
+            sPAPRDRConnectorClass *func_drck;
+            sPAPRDREntitySense state;
+
+            func_drc = spapr_phb_get_pci_func_drc(phb, pci_bus_num(bus),
+                                                  PCI_DEVFN(slotnr, i));
+            func_drck = SPAPR_DR_CONNECTOR_GET_CLASS(func_drc);
+            func_drck->entity_sense(func_drc, &state);
+
+            if (state == SPAPR_DR_ENTITY_SENSE_PRESENT) {
+                spapr_hotplug_req_add_by_index(func_drc);
+            }
+        }
     }
 }
 
@@ -1219,12 +1249,51 @@ static void spapr_phb_hot_unplug_child(HotplugHandler *plug_handler,
 
     drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
     if (!drck->release_pending(drc)) {
+        PCIBus *bus = PCI_BUS(qdev_get_parent_bus(DEVICE(pdev)));
+        uint32_t slotnr = PCI_SLOT(pdev->devfn);
+        sPAPRDRConnector *func_drc;
+        sPAPRDRConnectorClass *func_drck;
+        sPAPRDREntitySense state;
+        int i;
+
+        /* ensure any other present functions are pending unplug */
+        if (PCI_FUNC(pdev->devfn) == 0) {
+            for (i = 1; i < 8; i++) {
+                func_drc = spapr_phb_get_pci_func_drc(phb, pci_bus_num(bus),
+                                                      PCI_DEVFN(slotnr, i));
+                func_drck = SPAPR_DR_CONNECTOR_GET_CLASS(func_drc);
+                func_drck->entity_sense(func_drc, &state);
+                if (state == SPAPR_DR_ENTITY_SENSE_PRESENT
+                    && !func_drck->release_pending(func_drc)) {
+                    error_setg(errp,
+                               "PCI: slot %d, function %d still present. "
+                               "Must unplug all non-0 functions first.",
+                               slotnr, i);
+                    return;
+                }
+            }
+        }
+
         spapr_phb_remove_pci_device(drc, phb, pdev, &local_err);
         if (local_err) {
             error_propagate(errp, local_err);
             return;
         }
-        spapr_hotplug_req_remove_by_index(drc);
+
+        /* if this isn't func 0, defer unplug event. otherwise signal removal
+         * for all present functions
+         */
+        if (PCI_FUNC(pdev->devfn) == 0) {
+            for (i = 7; i >= 0; i--) {
+                func_drc = spapr_phb_get_pci_func_drc(phb, pci_bus_num(bus),
+                                                      PCI_DEVFN(slotnr, i));
+                func_drck = SPAPR_DR_CONNECTOR_GET_CLASS(func_drc);
+                func_drck->entity_sense(func_drc, &state);
+                if (state == SPAPR_DR_ENTITY_SENSE_PRESENT) {
+                    spapr_hotplug_req_remove_by_index(func_drc);
+                }
+            }
+        }
     }
 }
 
@@ -1234,11 +1303,12 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
     SysBusDevice *s = SYS_BUS_DEVICE(dev);
     sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(s);
     PCIHostState *phb = PCI_HOST_BRIDGE(s);
-    sPAPRPHBClass *info = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(s);
     char *namebuf;
     int i;
     PCIBus *bus;
     uint64_t msi_window_size = 4096;
+    sPAPRTCETable *tcet;
+    uint32_t nb_table;
 
     if (sphb->index != (uint32_t)-1) {
         hwaddr windows_base;
@@ -1390,33 +1460,20 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
         }
     }
 
-    if (!info->finish_realize) {
-        error_setg(errp, "finish_realize not defined");
-        return;
-    }
-
-    info->finish_realize(sphb, errp);
-
-    sphb->msi = g_hash_table_new_full(g_int_hash, g_int_equal, g_free, g_free);
-}
-
-static void spapr_phb_finish_realize(sPAPRPHBState *sphb, Error **errp)
-{
-    sPAPRTCETable *tcet;
-    uint32_t nb_table;
-
     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);
     if (!tcet) {
         error_setg(errp, "Unable to create TCE table for %s",
                    sphb->dtbusname);
-        return ;
+        return;
     }
 
     /* Register default 32bit DMA window */
     memory_region_add_subregion(&sphb->iommu_root, sphb->dma_win_addr,
                                 spapr_tce_get_iommu(tcet));
+
+    sphb->msi = g_hash_table_new_full(g_int_hash, g_int_equal, g_free, g_free);
 }
 
 static int spapr_phb_children_reset(Object *child, void *opaque)
@@ -1434,6 +1491,10 @@ static void spapr_phb_reset(DeviceState *qdev)
 {
     /* Reset the IOMMU state */
     object_child_foreach(OBJECT(qdev), spapr_phb_children_reset, NULL);
+
+    if (spapr_phb_eeh_available(SPAPR_PCI_HOST_BRIDGE(qdev))) {
+        spapr_phb_vfio_reset(qdev);
+    }
 }
 
 static Property spapr_phb_properties[] = {
@@ -1553,7 +1614,6 @@ static void spapr_phb_class_init(ObjectClass *klass, void *data)
 {
     PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
-    sPAPRPHBClass *spc = SPAPR_PCI_HOST_BRIDGE_CLASS(klass);
     HotplugHandlerClass *hp = HOTPLUG_HANDLER_CLASS(klass);
 
     hc->root_bus_path = spapr_phb_root_bus_path;
@@ -1563,7 +1623,6 @@ static void spapr_phb_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_spapr_pci;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->cannot_instantiate_with_device_add_yet = false;
-    spc->finish_realize = spapr_phb_finish_realize;
     hp->plug = spapr_phb_hot_plug_child;
     hp->unplug = spapr_phb_hot_unplug_child;
 }
@@ -1573,7 +1632,6 @@ static const TypeInfo spapr_phb_info = {
     .parent        = TYPE_PCI_HOST_BRIDGE,
     .instance_size = sizeof(sPAPRPHBState),
     .class_init    = spapr_phb_class_init,
-    .class_size    = sizeof(sPAPRPHBClass),
     .interfaces    = (InterfaceInfo[]) {
         { TYPE_HOTPLUG_HANDLER },
         { }
diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c
index 2f3752ea18..9e15924f50 100644
--- a/hw/ppc/spapr_pci_vfio.c
+++ b/hw/ppc/spapr_pci_vfio.c
@@ -23,68 +23,42 @@
 #include "hw/pci/msix.h"
 #include "linux/vfio.h"
 #include "hw/vfio/vfio.h"
+#include "qemu/error-report.h"
 
-static Property spapr_phb_vfio_properties[] = {
-    DEFINE_PROP_INT32("iommu", sPAPRPHBVFIOState, iommugroupid, -1),
-    DEFINE_PROP_END_OF_LIST(),
-};
+#define TYPE_SPAPR_PCI_VFIO_HOST_BRIDGE "spapr-pci-vfio-host-bridge"
 
-static void spapr_phb_vfio_finish_realize(sPAPRPHBState *sphb, Error **errp)
-{
-    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
-    struct vfio_iommu_spapr_tce_info info = { .argsz = sizeof(info) };
-    int ret;
-    sPAPRTCETable *tcet;
-    uint32_t liobn = svphb->phb.dma_liobn;
+#define SPAPR_PCI_VFIO_HOST_BRIDGE(obj) \
+    OBJECT_CHECK(sPAPRPHBVFIOState, (obj), TYPE_SPAPR_PCI_VFIO_HOST_BRIDGE)
 
-    if (svphb->iommugroupid == -1) {
-        error_setg(errp, "Wrong IOMMU group ID %d", svphb->iommugroupid);
-        return;
-    }
+typedef struct sPAPRPHBVFIOState sPAPRPHBVFIOState;
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
-                               VFIO_CHECK_EXTENSION,
-                               (void *) VFIO_SPAPR_TCE_IOMMU);
-    if (ret != 1) {
-        error_setg_errno(errp, -ret,
-                         "spapr-vfio: SPAPR extension is not supported");
-        return;
-    }
+struct sPAPRPHBVFIOState {
+    sPAPRPHBState phb;
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
-                               VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
-    if (ret) {
-        error_setg_errno(errp, -ret,
-                         "spapr-vfio: get info from container failed");
-        return;
-    }
+    int32_t iommugroupid;
+};
 
-    tcet = spapr_tce_new_table(DEVICE(sphb), liobn, info.dma32_window_start,
-                               SPAPR_TCE_PAGE_SHIFT,
-                               info.dma32_window_size >> SPAPR_TCE_PAGE_SHIFT,
-                               true);
-    if (!tcet) {
-        error_setg(errp, "spapr-vfio: failed to create VFIO TCE table");
-        return;
-    }
+static Property spapr_phb_vfio_properties[] = {
+    DEFINE_PROP_INT32("iommu", sPAPRPHBVFIOState, iommugroupid, -1),
+    DEFINE_PROP_END_OF_LIST(),
+};
 
-    /* Register default 32bit DMA window */
-    memory_region_add_subregion(&sphb->iommu_root, tcet->bus_offset,
-                                spapr_tce_get_iommu(tcet));
+static void spapr_phb_vfio_instance_init(Object *obj)
+{
+    error_report("spapr-pci-vfio-host-bridge is deprecated");
 }
 
-static void spapr_phb_vfio_eeh_reenable(sPAPRPHBVFIOState *svphb)
+bool spapr_phb_eeh_available(sPAPRPHBState *sphb)
 {
-    struct vfio_eeh_pe_op op = {
-        .argsz = sizeof(op),
-        .op    = VFIO_EEH_PE_ENABLE
-    };
+    return vfio_eeh_as_ok(&sphb->iommu_as);
+}
 
-    vfio_container_ioctl(&svphb->phb.iommu_as,
-                         svphb->iommugroupid, VFIO_EEH_PE_OP, &op);
+static void spapr_phb_vfio_eeh_reenable(sPAPRPHBState *sphb)
+{
+    vfio_eeh_as_op(&sphb->iommu_as, VFIO_EEH_PE_ENABLE);
 }
 
-static void spapr_phb_vfio_reset(DeviceState *qdev)
+void spapr_phb_vfio_reset(DeviceState *qdev)
 {
     /*
      * The PE might be in frozen state. To reenable the EEH
@@ -92,19 +66,18 @@ static void spapr_phb_vfio_reset(DeviceState *qdev)
      * ensures that the contained PCI devices will work properly
      * after reboot.
      */
-    spapr_phb_vfio_eeh_reenable(SPAPR_PCI_VFIO_HOST_BRIDGE(qdev));
+    spapr_phb_vfio_eeh_reenable(SPAPR_PCI_HOST_BRIDGE(qdev));
 }
 
-static int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
-                                         unsigned int addr, int option)
+int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
+                                  unsigned int addr, int option)
 {
-    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
-    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
+    uint32_t op;
     int ret;
 
     switch (option) {
     case RTAS_EEH_DISABLE:
-        op.op = VFIO_EEH_PE_DISABLE;
+        op = VFIO_EEH_PE_DISABLE;
         break;
     case RTAS_EEH_ENABLE: {
         PCIHostState *phb;
@@ -122,21 +95,20 @@ static int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
             return RTAS_OUT_PARAM_ERROR;
         }
 
-        op.op = VFIO_EEH_PE_ENABLE;
+        op = VFIO_EEH_PE_ENABLE;
         break;
     }
     case RTAS_EEH_THAW_IO:
-        op.op = VFIO_EEH_PE_UNFREEZE_IO;
+        op = VFIO_EEH_PE_UNFREEZE_IO;
         break;
     case RTAS_EEH_THAW_DMA:
-        op.op = VFIO_EEH_PE_UNFREEZE_DMA;
+        op = VFIO_EEH_PE_UNFREEZE_DMA;
         break;
     default:
         return RTAS_OUT_PARAM_ERROR;
     }
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
-                               VFIO_EEH_PE_OP, &op);
+    ret = vfio_eeh_as_op(&sphb->iommu_as, op);
     if (ret < 0) {
         return RTAS_OUT_HW_ERROR;
     }
@@ -144,15 +116,11 @@ static int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
     return RTAS_OUT_SUCCESS;
 }
 
-static int spapr_phb_vfio_eeh_get_state(sPAPRPHBState *sphb, int *state)
+int spapr_phb_vfio_eeh_get_state(sPAPRPHBState *sphb, int *state)
 {
-    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
-    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
     int ret;
 
-    op.op = VFIO_EEH_PE_GET_STATE;
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
-                               VFIO_EEH_PE_OP, &op);
+    ret = vfio_eeh_as_op(&sphb->iommu_as, VFIO_EEH_PE_GET_STATE);
     if (ret < 0) {
         return RTAS_OUT_PARAM_ERROR;
     }
@@ -204,30 +172,28 @@ static void spapr_phb_vfio_eeh_pre_reset(sPAPRPHBState *sphb)
        pci_for_each_bus(phb->bus, spapr_phb_vfio_eeh_clear_bus_msix, NULL);
 }
 
-static int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option)
+int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option)
 {
-    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
-    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
+    uint32_t op;
     int ret;
 
     switch (option) {
     case RTAS_SLOT_RESET_DEACTIVATE:
-        op.op = VFIO_EEH_PE_RESET_DEACTIVATE;
+        op = VFIO_EEH_PE_RESET_DEACTIVATE;
         break;
     case RTAS_SLOT_RESET_HOT:
         spapr_phb_vfio_eeh_pre_reset(sphb);
-        op.op = VFIO_EEH_PE_RESET_HOT;
+        op = VFIO_EEH_PE_RESET_HOT;
         break;
     case RTAS_SLOT_RESET_FUNDAMENTAL:
         spapr_phb_vfio_eeh_pre_reset(sphb);
-        op.op = VFIO_EEH_PE_RESET_FUNDAMENTAL;
+        op = VFIO_EEH_PE_RESET_FUNDAMENTAL;
         break;
     default:
         return RTAS_OUT_PARAM_ERROR;
     }
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
-                               VFIO_EEH_PE_OP, &op);
+    ret = vfio_eeh_as_op(&sphb->iommu_as, op);
     if (ret < 0) {
         return RTAS_OUT_HW_ERROR;
     }
@@ -235,15 +201,11 @@ static int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option)
     return RTAS_OUT_SUCCESS;
 }
 
-static int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb)
+int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb)
 {
-    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
-    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
     int ret;
 
-    op.op = VFIO_EEH_PE_CONFIGURE;
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
-                               VFIO_EEH_PE_OP, &op);
+    ret = vfio_eeh_as_op(&sphb->iommu_as, VFIO_EEH_PE_CONFIGURE);
     if (ret < 0) {
         return RTAS_OUT_PARAM_ERROR;
     }
@@ -254,23 +216,16 @@ static int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb)
 static void spapr_phb_vfio_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
-    sPAPRPHBClass *spc = SPAPR_PCI_HOST_BRIDGE_CLASS(klass);
 
     dc->props = spapr_phb_vfio_properties;
-    dc->reset = spapr_phb_vfio_reset;
-    spc->finish_realize = spapr_phb_vfio_finish_realize;
-    spc->eeh_set_option = spapr_phb_vfio_eeh_set_option;
-    spc->eeh_get_state = spapr_phb_vfio_eeh_get_state;
-    spc->eeh_reset = spapr_phb_vfio_eeh_reset;
-    spc->eeh_configure = spapr_phb_vfio_eeh_configure;
 }
 
 static const TypeInfo spapr_phb_vfio_info = {
     .name          = TYPE_SPAPR_PCI_VFIO_HOST_BRIDGE,
     .parent        = TYPE_SPAPR_PCI_HOST_BRIDGE,
     .instance_size = sizeof(sPAPRPHBVFIOState),
+    .instance_init = spapr_phb_vfio_instance_init,
     .class_init    = spapr_phb_vfio_class_init,
-    .class_size    = sizeof(sPAPRPHBClass),
 };
 
 static void spapr_pci_vfio_register_types(void)
diff --git a/hw/ppc/spapr_rng.c b/hw/ppc/spapr_rng.c
index a39d472b66..02d6be49f5 100644
--- a/hw/ppc/spapr_rng.c
+++ b/hw/ppc/spapr_rng.c
@@ -77,13 +77,13 @@ static target_ulong h_random(PowerPCCPU *cpu, sPAPRMachineState *spapr,
     hrdata.val.v64 = 0;
     hrdata.received = 0;
 
-    qemu_mutex_unlock_iothread();
     while (hrdata.received < 8) {
         rng_backend_request_entropy(rngstate->backend, 8 - hrdata.received,
                                     random_recv, &hrdata);
+        qemu_mutex_unlock_iothread();
         qemu_sem_wait(&hrdata.sem);
+        qemu_mutex_lock_iothread();
     }
-    qemu_mutex_lock_iothread();
 
     qemu_sem_destroy(&hrdata.sem);
     args[0] = hrdata.val.v64;
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 96ccb797fe..fb588d8d8e 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1093,47 +1093,97 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
     return 0;
 }
 
-static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid,
-                                   int req, void *param)
+/*
+ * Interfaces for IBM EEH (Enhanced Error Handling)
+ */
+static bool vfio_eeh_container_ok(VFIOContainer *container)
 {
-    VFIOGroup *group;
-    VFIOContainer *container;
-    int ret = -1;
+    /*
+     * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO
+     * implementation is broken if there are multiple groups in a
+     * container.  The hardware works in units of Partitionable
+     * Endpoints (== IOMMU groups) and the EEH operations naively
+     * iterate across all groups in the container, without any logic
+     * to make sure the groups have their state synchronized.  For
+     * certain operations (ENABLE) that might be ok, until an error
+     * occurs, but for others (GET_STATE) it's clearly broken.
+     */
 
-    group = vfio_get_group(groupid, as);
-    if (!group) {
-        error_report("vfio: group %d not registered", groupid);
-        return ret;
+    /*
+     * XXX Once fixed kernels exist, test for them here
+     */
+
+    if (QLIST_EMPTY(&container->group_list)) {
+        return false;
     }
 
-    container = group->container;
-    if (group->container) {
-        ret = ioctl(container->fd, req, param);
-        if (ret < 0) {
-            error_report("vfio: failed to ioctl %d to container: ret=%d, %s",
-                         _IOC_NR(req) - VFIO_BASE, ret, strerror(errno));
-        }
+    if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) {
+        return false;
     }
 
-    vfio_put_group(group);
+    return true;
+}
 
-    return ret;
+static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op)
+{
+    struct vfio_eeh_pe_op pe_op = {
+        .argsz = sizeof(pe_op),
+        .op = op,
+    };
+    int ret;
+
+    if (!vfio_eeh_container_ok(container)) {
+        error_report("vfio/eeh: EEH_PE_OP 0x%x: "
+                     "kernel requires a container with exactly one group", op);
+        return -EPERM;
+    }
+
+    ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op);
+    if (ret < 0) {
+        error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op);
+        return -errno;
+    }
+
+    return 0;
 }
 
-int vfio_container_ioctl(AddressSpace *as, int32_t groupid,
-                         int req, void *param)
+static VFIOContainer *vfio_eeh_as_container(AddressSpace *as)
 {
-    /* We allow only certain ioctls to the container */
-    switch (req) {
-    case VFIO_CHECK_EXTENSION:
-    case VFIO_IOMMU_SPAPR_TCE_GET_INFO:
-    case VFIO_EEH_PE_OP:
-        break;
-    default:
-        /* Return an error on unknown requests */
-        error_report("vfio: unsupported ioctl %X", req);
-        return -1;
+    VFIOAddressSpace *space = vfio_get_address_space(as);
+    VFIOContainer *container = NULL;
+
+    if (QLIST_EMPTY(&space->containers)) {
+        /* No containers to act on */
+        goto out;
+    }
+
+    container = QLIST_FIRST(&space->containers);
+
+    if (QLIST_NEXT(container, next)) {
+        /* We don't yet have logic to synchronize EEH state across
+         * multiple containers */
+        container = NULL;
+        goto out;
     }
 
-    return vfio_container_do_ioctl(as, groupid, req, param);
+out:
+    vfio_put_address_space(space);
+    return container;
+}
+
+bool vfio_eeh_as_ok(AddressSpace *as)
+{
+    VFIOContainer *container = vfio_eeh_as_container(as);
+
+    return (container != NULL) && vfio_eeh_container_ok(container);
+}
+
+int vfio_eeh_as_op(AddressSpace *as, uint32_t op)
+{
+    VFIOContainer *container = vfio_eeh_as_container(as);
+
+    if (!container) {
+        return -ENODEV;
+    }
+    return vfio_eeh_container_op(container, op);
 }