Merge branch 'ppc-next' of git://repo.or.cz/qemu/agraf

* 'ppc-next' of git://repo.or.cz/qemu/agraf:
  PPC: Add description for the Freescale e500mc core.
  pseries: Check for duplicate addresses on the spapr-vio bus
  pseries: Populate "/chosen/linux,stdout-path" in the FDT
  pseries: Add a routine to find a stable "default" vty and use it
  pseries: Emit device tree nodes in reg order
  pseries: FDT NUMA extensions to support multi-node guests
  pseries: Remove hcalls callback
  kvm-ppc: halt secondary cpus when guest reset
  console: Fix segfault on screendump without VGA adapter
  PPC: monitor: add ability to dump SLB entries

7 files changed, 265 insertions, 57 deletions

diff --git a/hw/ppce500_spin.c b/hw/ppce500_spin.c
index df74953874..e7b1453855 100644
--- a/hw/ppce500_spin.c
+++ b/hw/ppce500_spin.c
@@ -112,6 +112,7 @@ static void spin_kick(void *data)
 
     env->halted = 0;
     env->exception_index = -1;
+    env->stopped = 0;
     qemu_cpu_kick(env);
 }
 
diff --git a/hw/spapr.c b/hw/spapr.c
index 161b5858ae..0e1f80dfdc 100644
--- a/hw/spapr.c
+++ b/hw/spapr.c
@@ -97,6 +97,44 @@ qemu_irq spapr_allocate_irq(uint32_t hint, uint32_t *irq_num)
     return qirq;
 }
 
+static int spapr_set_associativity(void *fdt, sPAPREnvironment *spapr)
+{
+    int ret = 0, offset;
+    CPUState *env;
+    char cpu_model[32];
+    int smt = kvmppc_smt_threads();
+
+    assert(spapr->cpu_model);
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        uint32_t associativity[] = {cpu_to_be32(0x5),
+                                    cpu_to_be32(0x0),
+                                    cpu_to_be32(0x0),
+                                    cpu_to_be32(0x0),
+                                    cpu_to_be32(env->numa_node),
+                                    cpu_to_be32(env->cpu_index)};
+
+        if ((env->cpu_index % smt) != 0) {
+            continue;
+        }
+
+        snprintf(cpu_model, 32, "/cpus/%s@%x", spapr->cpu_model,
+                 env->cpu_index);
+
+        offset = fdt_path_offset(fdt, cpu_model);
+        if (offset < 0) {
+            return offset;
+        }
+
+        ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity,
+                          sizeof(associativity));
+        if (ret < 0) {
+            return ret;
+        }
+    }
+    return ret;
+}
+
 static void *spapr_create_fdt_skel(const char *cpu_model,
                                    target_phys_addr_t rma_size,
                                    target_phys_addr_t initrd_base,
@@ -107,9 +145,7 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
 {
     void *fdt;
     CPUState *env;
-    uint64_t mem_reg_property_rma[] = { 0, cpu_to_be64(rma_size) };
-    uint64_t mem_reg_property_nonrma[] = { cpu_to_be64(rma_size),
-                                           cpu_to_be64(ram_size - rma_size) };
+    uint64_t mem_reg_property[2];
     uint32_t start_prop = cpu_to_be32(initrd_base);
     uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
     uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
@@ -119,6 +155,13 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
     int i;
     char *modelname;
     int smt = kvmppc_smt_threads();
+    unsigned char vec5[] = {0x0, 0x0, 0x0, 0x0, 0x0, 0x80};
+    uint32_t refpoints[] = {cpu_to_be32(0x4), cpu_to_be32(0x4)};
+    uint32_t associativity[] = {cpu_to_be32(0x4), cpu_to_be32(0x0),
+                                cpu_to_be32(0x0), cpu_to_be32(0x0),
+                                cpu_to_be32(0x0)};
+    char mem_name[32];
+    target_phys_addr_t node0_size, mem_start;
 
 #define _FDT(exp) \
     do { \
@@ -146,6 +189,9 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
     /* /chosen */
     _FDT((fdt_begin_node(fdt, "chosen")));
 
+    /* Set Form1_affinity */
+    _FDT((fdt_property(fdt, "ibm,architecture-vec-5", vec5, sizeof(vec5))));
+
     _FDT((fdt_property_string(fdt, "bootargs", kernel_cmdline)));
     _FDT((fdt_property(fdt, "linux,initrd-start",
                        &start_prop, sizeof(start_prop))));
@@ -164,24 +210,54 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
     _FDT((fdt_end_node(fdt)));
 
     /* memory node(s) */
-    _FDT((fdt_begin_node(fdt, "memory@0")));
+    node0_size = (nb_numa_nodes > 1) ? node_mem[0] : ram_size;
+    if (rma_size > node0_size) {
+        rma_size = node0_size;
+    }
 
+    /* RMA */
+    mem_reg_property[0] = 0;
+    mem_reg_property[1] = cpu_to_be64(rma_size);
+    _FDT((fdt_begin_node(fdt, "memory@0")));
     _FDT((fdt_property_string(fdt, "device_type", "memory")));
-    _FDT((fdt_property(fdt, "reg", mem_reg_property_rma,
-                       sizeof(mem_reg_property_rma))));
+    _FDT((fdt_property(fdt, "reg", mem_reg_property,
+        sizeof(mem_reg_property))));
+    _FDT((fdt_property(fdt, "ibm,associativity", associativity,
+        sizeof(associativity))));
     _FDT((fdt_end_node(fdt)));
 
-    if (ram_size > rma_size) {
-        char mem_name[32];
+    /* RAM: Node 0 */
+    if (node0_size > rma_size) {
+        mem_reg_property[0] = cpu_to_be64(rma_size);
+        mem_reg_property[1] = cpu_to_be64(node0_size - rma_size);
 
-        sprintf(mem_name, "memory@%" PRIx64, (uint64_t)rma_size);
+        sprintf(mem_name, "memory@" TARGET_FMT_lx, rma_size);
         _FDT((fdt_begin_node(fdt, mem_name)));
         _FDT((fdt_property_string(fdt, "device_type", "memory")));
-        _FDT((fdt_property(fdt, "reg", mem_reg_property_nonrma,
-                           sizeof(mem_reg_property_nonrma))));
+        _FDT((fdt_property(fdt, "reg", mem_reg_property,
+                           sizeof(mem_reg_property))));
+        _FDT((fdt_property(fdt, "ibm,associativity", associativity,
+                           sizeof(associativity))));
         _FDT((fdt_end_node(fdt)));
     }
 
+    /* RAM: Node 1 and beyond */
+    mem_start = node0_size;
+    for (i = 1; i < nb_numa_nodes; i++) {
+        mem_reg_property[0] = cpu_to_be64(mem_start);
+        mem_reg_property[1] = cpu_to_be64(node_mem[i]);
+        associativity[3] = associativity[4] = cpu_to_be32(i);
+        sprintf(mem_name, "memory@" TARGET_FMT_lx, mem_start);
+        _FDT((fdt_begin_node(fdt, mem_name)));
+        _FDT((fdt_property_string(fdt, "device_type", "memory")));
+        _FDT((fdt_property(fdt, "reg", mem_reg_property,
+            sizeof(mem_reg_property))));
+        _FDT((fdt_property(fdt, "ibm,associativity", associativity,
+            sizeof(associativity))));
+        _FDT((fdt_end_node(fdt)));
+        mem_start += node_mem[i];
+    }
+
     /* cpus */
     _FDT((fdt_begin_node(fdt, "cpus")));
 
@@ -194,6 +270,9 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
         modelname[i] = toupper(modelname[i]);
     }
 
+    /* This is needed during FDT finalization */
+    spapr->cpu_model = g_strdup(modelname);
+
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
         int index = env->cpu_index;
         uint32_t servers_prop[smp_threads];
@@ -280,6 +359,9 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
     _FDT((fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop,
                        sizeof(hypertas_prop))));
 
+    _FDT((fdt_property(fdt, "ibm,associativity-reference-points",
+        refpoints, sizeof(refpoints))));
+
     _FDT((fdt_end_node(fdt)));
 
     /* interrupt controller */
@@ -351,6 +433,16 @@ static void spapr_finalize_fdt(sPAPREnvironment *spapr,
         fprintf(stderr, "Couldn't set up RTAS device tree properties\n");
     }
 
+    /* Advertise NUMA via ibm,associativity */
+    if (nb_numa_nodes > 1) {
+        ret = spapr_set_associativity(fdt, spapr);
+        if (ret < 0) {
+            fprintf(stderr, "Couldn't set up NUMA device tree properties\n");
+        }
+    }
+
+    spapr_populate_chosen_stdout(fdt, spapr->vio_bus);
+
     _FDT((fdt_pack(fdt)));
 
     cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
diff --git a/hw/spapr.h b/hw/spapr.h
index d624841362..e946a3433e 100644
--- a/hw/spapr.h
+++ b/hw/spapr.h
@@ -21,6 +21,7 @@ typedef struct sPAPREnvironment {
     target_ulong entry_point;
     int next_irq;
     int rtc_offset;
+    char *cpu_model;
 } sPAPREnvironment;
 
 #define H_SUCCESS         0
diff --git a/hw/spapr_llan.c b/hw/spapr_llan.c
index abe12973e6..45674c4cb9 100644
--- a/hw/spapr_llan.c
+++ b/hw/spapr_llan.c
@@ -474,16 +474,6 @@ static target_ulong h_multicast_ctrl(CPUState *env, sPAPREnvironment *spapr,
     return H_SUCCESS;
 }
 
-static void vlan_hcalls(VIOsPAPRBus *bus)
-{
-    spapr_register_hypercall(H_REGISTER_LOGICAL_LAN, h_register_logical_lan);
-    spapr_register_hypercall(H_FREE_LOGICAL_LAN, h_free_logical_lan);
-    spapr_register_hypercall(H_SEND_LOGICAL_LAN, h_send_logical_lan);
-    spapr_register_hypercall(H_ADD_LOGICAL_LAN_BUFFER,
-                             h_add_logical_lan_buffer);
-    spapr_register_hypercall(H_MULTICAST_CTRL, h_multicast_ctrl);
-}
-
 static VIOsPAPRDeviceInfo spapr_vlan = {
     .init = spapr_vlan_init,
     .devnode = spapr_vlan_devnode,
@@ -491,7 +481,6 @@ static VIOsPAPRDeviceInfo spapr_vlan = {
     .dt_type = "network",
     .dt_compatible = "IBM,l-lan",
     .signal_mask = 0x1,
-    .hcalls = vlan_hcalls,
     .qdev.name = "spapr-vlan",
     .qdev.size = sizeof(VIOsPAPRVLANDevice),
     .qdev.props = (Property[]) {
@@ -504,5 +493,11 @@ static VIOsPAPRDeviceInfo spapr_vlan = {
 static void spapr_vlan_register(void)
 {
     spapr_vio_bus_register_withprop(&spapr_vlan);
+    spapr_register_hypercall(H_REGISTER_LOGICAL_LAN, h_register_logical_lan);
+    spapr_register_hypercall(H_FREE_LOGICAL_LAN, h_free_logical_lan);
+    spapr_register_hypercall(H_SEND_LOGICAL_LAN, h_send_logical_lan);
+    spapr_register_hypercall(H_ADD_LOGICAL_LAN_BUFFER,
+                             h_add_logical_lan_buffer);
+    spapr_register_hypercall(H_MULTICAST_CTRL, h_multicast_ctrl);
 }
 device_init(spapr_vlan_register);
diff --git a/hw/spapr_vio.c b/hw/spapr_vio.c
index 2dcc0361ed..7a86dc8d2c 100644
--- a/hw/spapr_vio.c
+++ b/hw/spapr_vio.c
@@ -621,11 +621,43 @@ static void rtas_quiesce(sPAPREnvironment *spapr, uint32_t token,
     rtas_st(rets, 0, 0);
 }
 
+static int spapr_vio_check_reg(VIOsPAPRDevice *sdev, VIOsPAPRDeviceInfo *info)
+{
+    VIOsPAPRDevice *other_sdev;
+    DeviceState *qdev;
+    VIOsPAPRBus *sbus;
+
+    sbus = DO_UPCAST(VIOsPAPRBus, bus, sdev->qdev.parent_bus);
+
+    /*
+     * Check two device aren't given clashing addresses by the user (or some
+     * other mechanism). We have to open code this because we have to check
+     * for matches with devices other than us.
+     */
+    QTAILQ_FOREACH(qdev, &sbus->bus.children, sibling) {
+        other_sdev = DO_UPCAST(VIOsPAPRDevice, qdev, qdev);
+
+        if (other_sdev != sdev && other_sdev->reg == sdev->reg) {
+            fprintf(stderr, "vio: %s and %s devices conflict at address %#x\n",
+                    info->qdev.name, other_sdev->qdev.info->name, sdev->reg);
+            return -EEXIST;
+        }
+    }
+
+    return 0;
+}
+
 static int spapr_vio_busdev_init(DeviceState *qdev, DeviceInfo *qinfo)
 {
     VIOsPAPRDeviceInfo *info = (VIOsPAPRDeviceInfo *)qinfo;
     VIOsPAPRDevice *dev = (VIOsPAPRDevice *)qdev;
     char *id;
+    int ret;
+
+    ret = spapr_vio_check_reg(dev, info);
+    if (ret) {
+        return ret;
+    }
 
     /* Don't overwrite ids assigned on the command line */
     if (!dev->qdev.id) {
@@ -684,7 +716,6 @@ VIOsPAPRBus *spapr_vio_bus_init(void)
     VIOsPAPRBus *bus;
     BusState *qbus;
     DeviceState *dev;
-    DeviceInfo *qinfo;
 
     /* Create bridge device */
     dev = qdev_create(NULL, "spapr-vio-bridge");
@@ -711,18 +742,6 @@ VIOsPAPRBus *spapr_vio_bus_init(void)
     spapr_rtas_register("ibm,set-tce-bypass", rtas_set_tce_bypass);
     spapr_rtas_register("quiesce", rtas_quiesce);
 
-    for (qinfo = device_info_list; qinfo; qinfo = qinfo->next) {
-        VIOsPAPRDeviceInfo *info = (VIOsPAPRDeviceInfo *)qinfo;
-
-        if (qinfo->bus_info != &spapr_vio_bus_info) {
-            continue;
-        }
-
-        if (info->hcalls) {
-            info->hcalls(bus);
-        }
-    }
-
     return bus;
 }
 
@@ -749,21 +768,95 @@ static void spapr_vio_register_devices(void)
 device_init(spapr_vio_register_devices)
 
 #ifdef CONFIG_FDT
+static int compare_reg(const void *p1, const void *p2)
+{
+    VIOsPAPRDevice const *dev1, *dev2;
+
+    dev1 = (VIOsPAPRDevice *)*(DeviceState **)p1;
+    dev2 = (VIOsPAPRDevice *)*(DeviceState **)p2;
+
+    if (dev1->reg < dev2->reg) {
+        return -1;
+    }
+    if (dev1->reg == dev2->reg) {
+        return 0;
+    }
+
+    /* dev1->reg > dev2->reg */
+    return 1;
+}
+
 int spapr_populate_vdevice(VIOsPAPRBus *bus, void *fdt)
 {
-    DeviceState *qdev;
-    int ret = 0;
+    DeviceState *qdev, **qdevs;
+    int i, num, ret = 0;
 
+    /* Count qdevs on the bus list */
+    num = 0;
     QTAILQ_FOREACH(qdev, &bus->bus.children, sibling) {
-        VIOsPAPRDevice *dev = (VIOsPAPRDevice *)qdev;
+        num++;
+    }
+
+    /* Copy out into an array of pointers */
+    qdevs = g_malloc(sizeof(qdev) * num);
+    num = 0;
+    QTAILQ_FOREACH(qdev, &bus->bus.children, sibling) {
+        qdevs[num++] = qdev;
+    }
+
+    /* Sort the array */
+    qsort(qdevs, num, sizeof(qdev), compare_reg);
+
+    /* Hack alert. Give the devices to libfdt in reverse order, we happen
+     * to know that will mean they are in forward order in the tree. */
+    for (i = num - 1; i >= 0; i--) {
+        VIOsPAPRDevice *dev = (VIOsPAPRDevice *)(qdevs[i]);
 
         ret = vio_make_devnode(dev, fdt);
 
         if (ret < 0) {
-            return ret;
+            goto out;
         }
     }
 
-    return 0;
+    ret = 0;
+out:
+    free(qdevs);
+
+    return ret;
+}
+
+int spapr_populate_chosen_stdout(void *fdt, VIOsPAPRBus *bus)
+{
+    VIOsPAPRDevice *dev;
+    char *name, *path;
+    int ret, offset;
+
+    dev = spapr_vty_get_default(bus);
+    if (!dev)
+        return 0;
+
+    offset = fdt_path_offset(fdt, "/chosen");
+    if (offset < 0) {
+        return offset;
+    }
+
+    name = vio_format_dev_name(dev);
+    if (!name) {
+        return -ENOMEM;
+    }
+
+    if (asprintf(&path, "/vdevice/%s", name) < 0) {
+        path = NULL;
+        ret = -ENOMEM;
+        goto out;
+    }
+
+    ret = fdt_setprop_string(fdt, offset, "linux,stdout-path", path);
+out:
+    free(name);
+    free(path);
+
+    return ret;
 }
 #endif /* CONFIG_FDT */
diff --git a/hw/spapr_vio.h b/hw/spapr_vio.h
index a325a5f4b3..0984d559db 100644
--- a/hw/spapr_vio.h
+++ b/hw/spapr_vio.h
@@ -75,7 +75,6 @@ typedef struct {
     const char *dt_name, *dt_type, *dt_compatible;
     target_ulong signal_mask;
     int (*init)(VIOsPAPRDevice *dev);
-    void (*hcalls)(VIOsPAPRBus *bus);
     int (*devnode)(VIOsPAPRDevice *dev, void *fdt, int node_off);
 } VIOsPAPRDeviceInfo;
 
@@ -83,6 +82,7 @@ extern VIOsPAPRBus *spapr_vio_bus_init(void);
 extern VIOsPAPRDevice *spapr_vio_find_by_reg(VIOsPAPRBus *bus, uint32_t reg);
 extern void spapr_vio_bus_register_withprop(VIOsPAPRDeviceInfo *info);
 extern int spapr_populate_vdevice(VIOsPAPRBus *bus, void *fdt);
+extern int spapr_populate_chosen_stdout(void *fdt, VIOsPAPRBus *bus);
 
 extern int spapr_vio_signal(VIOsPAPRDevice *dev, target_ulong mode);
 
@@ -108,6 +108,8 @@ void spapr_vty_create(VIOsPAPRBus *bus, uint32_t reg, CharDriverState *chardev);
 void spapr_vlan_create(VIOsPAPRBus *bus, uint32_t reg, NICInfo *nd);
 void spapr_vscsi_create(VIOsPAPRBus *bus, uint32_t reg);
 
+VIOsPAPRDevice *spapr_vty_get_default(VIOsPAPRBus *bus);
+
 int spapr_tce_set_bypass(uint32_t unit, uint32_t enable);
 void spapr_vio_quiesce(void);
 
diff --git a/hw/spapr_vty.c b/hw/spapr_vty.c
index f23cc36231..c5fb0968ed 100644
--- a/hw/spapr_vty.c
+++ b/hw/spapr_vty.c
@@ -135,18 +135,11 @@ void spapr_vty_create(VIOsPAPRBus *bus, uint32_t reg, CharDriverState *chardev)
     qdev_init_nofail(dev);
 }
 
-static void vty_hcalls(VIOsPAPRBus *bus)
-{
-    spapr_register_hypercall(H_PUT_TERM_CHAR, h_put_term_char);
-    spapr_register_hypercall(H_GET_TERM_CHAR, h_get_term_char);
-}
-
 static VIOsPAPRDeviceInfo spapr_vty = {
     .init = spapr_vty_init,
     .dt_name = "vty",
     .dt_type = "serial",
     .dt_compatible = "hvterm1",
-    .hcalls = vty_hcalls,
     .qdev.name = "spapr-vty",
     .qdev.size = sizeof(VIOsPAPRVTYDevice),
     .qdev.props = (Property[]) {
@@ -156,24 +149,53 @@ static VIOsPAPRDeviceInfo spapr_vty = {
     },
 };
 
+VIOsPAPRDevice *spapr_vty_get_default(VIOsPAPRBus *bus)
+{
+    VIOsPAPRDevice *sdev, *selected;
+    DeviceState *iter;
+
+    /*
+     * To avoid the console bouncing around we want one VTY to be
+     * the "default". We haven't really got anything to go on, so
+     * arbitrarily choose the one with the lowest reg value.
+     */
+
+    selected = NULL;
+    QTAILQ_FOREACH(iter, &bus->bus.children, sibling) {
+        /* Only look at VTY devices */
+        if (iter->info != &spapr_vty.qdev) {
+            continue;
+        }
+
+        sdev = DO_UPCAST(VIOsPAPRDevice, qdev, iter);
+
+        /* First VTY we've found, so it is selected for now */
+        if (!selected) {
+            selected = sdev;
+            continue;
+        }
+
+        /* Choose VTY with lowest reg value */
+        if (sdev->reg < selected->reg) {
+            selected = sdev;
+        }
+    }
+
+    return selected;
+}
+
 static VIOsPAPRDevice *vty_lookup(sPAPREnvironment *spapr, target_ulong reg)
 {
     VIOsPAPRDevice *sdev;
 
     sdev = spapr_vio_find_by_reg(spapr->vio_bus, reg);
     if (!sdev && reg == 0) {
-        DeviceState *qdev;
-
         /* Hack for kernel early debug, which always specifies reg==0.
-         * We search all VIO devices, and grab the first available vty
-         * device.  This attempts to mimic existing PowerVM behaviour
+         * We search all VIO devices, and grab the vty with the lowest
+         * reg.  This attempts to mimic existing PowerVM behaviour
          * (early debug does work there, despite having no vty with
          * reg==0. */
-        QTAILQ_FOREACH(qdev, &spapr->vio_bus->bus.children, sibling) {
-            if (qdev->info == &spapr_vty.qdev) {
-                return DO_UPCAST(VIOsPAPRDevice, qdev, qdev);
-            }
-        }
+        return spapr_vty_get_default(spapr->vio_bus);
     }
 
     return sdev;
@@ -182,5 +204,7 @@ static VIOsPAPRDevice *vty_lookup(sPAPREnvironment *spapr, target_ulong reg)
 static void spapr_vty_register(void)
 {
     spapr_vio_bus_register_withprop(&spapr_vty);
+    spapr_register_hypercall(H_PUT_TERM_CHAR, h_put_term_char);
+    spapr_register_hypercall(H_GET_TERM_CHAR, h_get_term_char);
 }
 device_init(spapr_vty_register);