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>

1 files changed, 107 insertions, 49 deletions

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 },
         { }