Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.7-20160726' into staging

ppc patch queue 2016-07-26

Here's the current batch of ppc and spapr related patches intended for
qemu-2.7.  Given the late stage in 2.7 development, these are all
bugfixes with one exception:

The "spapr: disintricate core-id from DT semantics" changes the way
ids are assigned in the new core-based hotplug infrastructure.  This
isn't strictly a bugfix, but we've determined that the current way of
assigning core-ids will cause considerable grief with future plans for
cpu hotplug.  Therefore it's better to fix this now, late in 2.7,
before we have a released version with the problematic numbering.

# gpg: Signature made Tue 26 Jul 2016 04:04:57 BST
# gpg:                using RSA key 0x6C38CACA20D9B392
# 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-2.7-20160726:
  spapr: disintricate core-id from DT semantics
  target-ppc: add PPC_MFTB flag to e500mc and e5500
  spapr: fix spapr-nvram migration
  hw/ppc/spapr: Make sure to close the htab_fd when migration is canceled
  ppc: Huge page detection mechanism fixes - Episode III
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

hw/nvram/spapr_nvram.c

@@ -39,6 +39,7 @@ typedef struct sPAPRNVRAM {
     uint32_t size;
     uint8_t *buf;
     BlockBackend *blk;
+    VMChangeStateEntry *vmstate;
 } sPAPRNVRAM;
 
 #define TYPE_VIO_SPAPR_NVRAM "spapr-nvram"
@@ -185,19 +186,25 @@ static int spapr_nvram_pre_load(void *opaque)
     return 0;
 }
 
+static void postload_update_cb(void *opaque, int running, RunState state)
+{
+    sPAPRNVRAM *nvram = opaque;
+
+    /* This is called after bdrv_invalidate_cache_all.  */
+
+    qemu_del_vm_change_state_handler(nvram->vmstate);
+    nvram->vmstate = NULL;
+
+    blk_pwrite(nvram->blk, 0, nvram->buf, nvram->size, 0);
+}
+
 static int spapr_nvram_post_load(void *opaque, int version_id)
 {
     sPAPRNVRAM *nvram = VIO_SPAPR_NVRAM(opaque);
 
     if (nvram->blk) {
-        int alen = blk_pwrite(nvram->blk, 0, nvram->buf, nvram->size, 0);
-
-        if (alen < 0) {
-            return alen;
-        }
-        if (alen != nvram->size) {
-            return -1;
-        }
+        nvram->vmstate = qemu_add_vm_change_state_handler(postload_update_cb,
+                                                          nvram);
     }
 
     return 0;

hw/ppc/spapr.c

@@ -1512,7 +1512,6 @@ static int htab_save_complete(QEMUFile *f, void *opaque)
         if (rc < 0) {
             return rc;
         }
-        close_htab_fd(spapr);
     } else {
         if (spapr->htab_first_pass) {
             htab_save_first_pass(f, spapr, -1);
@@ -1614,10 +1613,18 @@ static int htab_load(QEMUFile *f, void *opaque, int version_id)
     return 0;
 }
 
+static void htab_cleanup(void *opaque)
+{
+    sPAPRMachineState *spapr = opaque;
+
+    close_htab_fd(spapr);
+}
+
 static SaveVMHandlers savevm_htab_handlers = {
     .save_live_setup = htab_save_setup,
     .save_live_iterate = htab_save_iterate,
     .save_live_complete_precopy = htab_save_complete,
+    .cleanup = htab_cleanup,
     .load_state = htab_load,
 };
 
@@ -1808,10 +1815,11 @@ static void ppc_spapr_init(MachineState *machine)
 
         spapr->cores = g_new0(Object *, spapr_max_cores);
         for (i = 0; i < spapr_max_cores; i++) {
-            int core_dt_id = i * smt;
+            int core_id = i * smp_threads;
             sPAPRDRConnector *drc =
                 spapr_dr_connector_new(OBJECT(spapr),
-                                       SPAPR_DR_CONNECTOR_TYPE_CPU, core_dt_id);
+                                       SPAPR_DR_CONNECTOR_TYPE_CPU,
+                                       (core_id / smp_threads) * smt);
 
             qemu_register_reset(spapr_drc_reset, drc);
 
@@ -1827,7 +1835,7 @@ static void ppc_spapr_init(MachineState *machine)
                 core  = object_new(type);
                 object_property_set_int(core, smp_threads, "nr-threads",
                                         &error_fatal);
-                object_property_set_int(core, core_dt_id, CPU_CORE_PROP_CORE_ID,
+                object_property_set_int(core, core_id, CPU_CORE_PROP_CORE_ID,
                                         &error_fatal);
                 object_property_set_bool(core, true, "realized", &error_fatal);
             }
@@ -2369,7 +2377,6 @@ static HotpluggableCPUList *spapr_query_hotpluggable_cpus(MachineState *machine)
     HotpluggableCPUList *head = NULL;
     sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
     int spapr_max_cores = max_cpus / smp_threads;
-    int smt = kvmppc_smt_threads();
 
     for (i = 0; i < spapr_max_cores; i++) {
         HotpluggableCPUList *list_item = g_new0(typeof(*list_item), 1);
@@ -2379,7 +2386,7 @@ static HotpluggableCPUList *spapr_query_hotpluggable_cpus(MachineState *machine)
         cpu_item->type = spapr_get_cpu_core_type(machine->cpu_model);
         cpu_item->vcpus_count = smp_threads;
         cpu_props->has_core_id = true;
-        cpu_props->core_id = i * smt;
+        cpu_props->core_id = i * smp_threads;
         /* TODO: add 'has_node/node' here to describe
            to which node core belongs */
 

hw/ppc/spapr_cpu_core.c

@@ -103,7 +103,6 @@ static void spapr_core_release(DeviceState *dev, void *opaque)
     size_t size = object_type_get_instance_size(typename);
     sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
     CPUCore *cc = CPU_CORE(dev);
-    int smt = kvmppc_smt_threads();
     int i;
 
     for (i = 0; i < cc->nr_threads; i++) {
@@ -117,7 +116,7 @@ static void spapr_core_release(DeviceState *dev, void *opaque)
         object_unparent(obj);
     }
 
-    spapr->cores[cc->core_id / smt] = NULL;
+    spapr->cores[cc->core_id / smp_threads] = NULL;
 
     g_free(sc->threads);
     object_unparent(OBJECT(dev));
@@ -128,18 +127,19 @@ void spapr_core_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
 {
     sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
     CPUCore *cc = CPU_CORE(dev);
+    int smt = kvmppc_smt_threads();
+    int index = cc->core_id / smp_threads;
     sPAPRDRConnector *drc =
-        spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, cc->core_id);
+        spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt);
     sPAPRDRConnectorClass *drck;
     Error *local_err = NULL;
-    int smt = kvmppc_smt_threads();
-    int index = cc->core_id / smt;
     int spapr_max_cores = max_cpus / smp_threads;
     int i;
 
     for (i = spapr_max_cores - 1; i > index; i--) {
         if (spapr->cores[i]) {
-            error_setg(errp, "core-id %d should be removed first", i * smt);
+            error_setg(errp, "core-id %d should be removed first",
+                       i * smp_threads);
             return;
         }
     }
@@ -168,11 +168,10 @@ void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     Error *local_err = NULL;
     void *fdt = NULL;
     int fdt_offset = 0;
-    int index;
+    int index = cc->core_id / smp_threads;
     int smt = kvmppc_smt_threads();
 
-    drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, cc->core_id);
-    index = cc->core_id / smt;
+    drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt);
     spapr->cores[index] = OBJECT(dev);
 
     if (!smc->dr_cpu_enabled) {
@@ -226,7 +225,6 @@ void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
     int spapr_max_cores = max_cpus / smp_threads;
     int index, i;
-    int smt = kvmppc_smt_threads();
     Error *local_err = NULL;
     CPUCore *cc = CPU_CORE(dev);
     char *base_core_type = spapr_get_cpu_core_type(machine->cpu_model);
@@ -247,12 +245,12 @@ void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
         goto out;
     }
 
-    if (cc->core_id % smt) {
+    if (cc->core_id % smp_threads) {
         error_setg(&local_err, "invalid core id %d\n", cc->core_id);
         goto out;
     }
 
-    index = cc->core_id / smt;
+    index = cc->core_id / smp_threads;
     if (index < 0 || index >= spapr_max_cores) {
         error_setg(&local_err, "core id %d out of range", cc->core_id);
         goto out;
@@ -266,7 +264,7 @@ void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     for (i = 0; i < index; i++) {
         if (!spapr->cores[i]) {
             error_setg(&local_err, "core-id %d should be added first",
-                       i * smt);
+                       i * smp_threads);
             goto out;
         }
     }

target-ppc/kvm.c

@@ -366,10 +366,13 @@ static int find_max_supported_pagesize(Object *obj, void *opaque)
 static long getrampagesize(void)
 {
     long hpsize = LONG_MAX;
+    long mainrampagesize;
     Object *memdev_root;
 
     if (mem_path) {
-        return gethugepagesize(mem_path);
+        mainrampagesize = gethugepagesize(mem_path);
+    } else {
+        mainrampagesize = getpagesize();
     }
 
     /* it's possible we have memory-backend objects with
@@ -383,28 +386,26 @@ static long getrampagesize(void)
      * backend isn't backed by hugepages.
      */
     memdev_root = object_resolve_path("/objects", NULL);
-    if (!memdev_root) {
-        return getpagesize();
+    if (memdev_root) {
+        object_child_foreach(memdev_root, find_max_supported_pagesize, &hpsize);
     }
-
-    object_child_foreach(memdev_root, find_max_supported_pagesize, &hpsize);
-
-    if (hpsize == LONG_MAX || hpsize == getpagesize()) {
-        return getpagesize();
+    if (hpsize == LONG_MAX) {
+        /* No additional memory regions found ==> Report main RAM page size */
+        return mainrampagesize;
     }
 
     /* If NUMA is disabled or the NUMA nodes are not backed with a
-     * memory-backend, then there is at least one node using "normal"
-     * RAM. And since normal RAM has not been configured with "-mem-path"
-     * (what we've checked earlier here already), we can not use huge pages!
+     * memory-backend, then there is at least one node using "normal" RAM,
+     * so if its page size is smaller we have got to report that size instead.
      */
-    if (nb_numa_nodes == 0 || numa_info[0].node_memdev == NULL) {
+    if (hpsize > mainrampagesize &&
+        (nb_numa_nodes == 0 || numa_info[0].node_memdev == NULL)) {
         static bool warned;
         if (!warned) {
             error_report("Huge page support disabled (n/a for main memory).");
             warned = true;
         }
-        return getpagesize();
+        return mainrampagesize;
     }
 
     return hpsize;

target-ppc/translate_init.c

@@ -5133,7 +5133,7 @@ POWERPC_FAMILY(e500mc)(ObjectClass *oc, void *data)
     dc->desc = "e500mc core";
     pcc->init_proc = init_proc_e500mc;
     pcc->check_pow = check_pow_none;
-    pcc->insns_flags = PPC_INSNS_BASE | PPC_ISEL |
+    pcc->insns_flags = PPC_INSNS_BASE | PPC_ISEL | PPC_MFTB |
                        PPC_WRTEE | PPC_RFDI | PPC_RFMCI |
                        PPC_CACHE | PPC_CACHE_LOCK | PPC_CACHE_ICBI |
                        PPC_CACHE_DCBZ | PPC_CACHE_DCBA |
@@ -5179,7 +5179,7 @@ POWERPC_FAMILY(e5500)(ObjectClass *oc, void *data)
     dc->desc = "e5500 core";
     pcc->init_proc = init_proc_e5500;
     pcc->check_pow = check_pow_none;
-    pcc->insns_flags = PPC_INSNS_BASE | PPC_ISEL |
+    pcc->insns_flags = PPC_INSNS_BASE | PPC_ISEL | PPC_MFTB |
                        PPC_WRTEE | PPC_RFDI | PPC_RFMCI |
                        PPC_CACHE | PPC_CACHE_LOCK | PPC_CACHE_ICBI |
                        PPC_CACHE_DCBZ | PPC_CACHE_DCBA |