summary refs log tree commit diff stats
path: root/hw
diff options
context:
space:
mode:
Diffstat (limited to 'hw')
-rw-r--r--hw/fw_cfg.c1
-rw-r--r--hw/ide/ahci.c98
-rw-r--r--hw/ide/ahci.h20
-rw-r--r--hw/ide/core.c33
-rw-r--r--hw/ide/ich.c14
-rw-r--r--hw/pc.c40
-rw-r--r--hw/pc_piix.c26
-rw-r--r--hw/ppc/mac_newworld.c1
-rw-r--r--hw/ppc/mac_oldworld.c1
-rw-r--r--hw/sun4m.c3
-rw-r--r--hw/sun4u.c1
-rw-r--r--hw/virtio-balloon.c175
12 files changed, 346 insertions, 67 deletions
diff --git a/hw/fw_cfg.c b/hw/fw_cfg.c
index bdcd836986..02618f2480 100644
--- a/hw/fw_cfg.c
+++ b/hw/fw_cfg.c
@@ -504,7 +504,6 @@ FWCfgState *fw_cfg_init(uint32_t ctl_port, uint32_t data_port,
     fw_cfg_add_bytes(s, FW_CFG_UUID, qemu_uuid, 16);
     fw_cfg_add_i16(s, FW_CFG_NOGRAPHIC, (uint16_t)(display_type == DT_NOGRAPHIC));
     fw_cfg_add_i16(s, FW_CFG_NB_CPUS, (uint16_t)smp_cpus);
-    fw_cfg_add_i16(s, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i16(s, FW_CFG_BOOT_MENU, (uint16_t)boot_menu);
     fw_cfg_bootsplash(s);
     fw_cfg_reboot(s);
diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index 21f50ea5be..ad0094f532 100644
--- a/hw/ide/ahci.c
+++ b/hw/ide/ahci.c
@@ -241,7 +241,7 @@ static void  ahci_port_write(AHCIState *s, int port, int offset, uint32_t val)
             if ((pr->cmd & PORT_CMD_FIS_ON) &&
                 !s->dev[port].init_d2h_sent) {
                 ahci_init_d2h(&s->dev[port]);
-                s->dev[port].init_d2h_sent = 1;
+                s->dev[port].init_d2h_sent = true;
             }
 
             check_cmd(s, port);
@@ -494,7 +494,7 @@ static void ahci_reset_port(AHCIState *s, int port)
     pr->scr_err = 0;
     pr->scr_act = 0;
     d->busy_slot = -1;
-    d->init_d2h_sent = 0;
+    d->init_d2h_sent = false;
 
     ide_state = &s->dev[port].port.ifs[0];
     if (!ide_state->bs) {
@@ -946,7 +946,7 @@ static int handle_cmd(AHCIState *s, int port, int slot)
             ide_state->hcyl = 0xeb;
             debug_print_fis(ide_state->io_buffer, 0x10);
             ide_state->feature = IDE_FEATURE_DMA;
-            s->dev[port].done_atapi_packet = 0;
+            s->dev[port].done_atapi_packet = false;
             /* XXX send PIO setup FIS */
         }
 
@@ -991,7 +991,7 @@ static int ahci_start_transfer(IDEDMA *dma)
 
     if (is_atapi && !ad->done_atapi_packet) {
         /* already prepopulated iobuffer */
-        ad->done_atapi_packet = 1;
+        ad->done_atapi_packet = true;
         goto out;
     }
 
@@ -1035,11 +1035,10 @@ out:
 static void ahci_start_dma(IDEDMA *dma, IDEState *s,
                            BlockDriverCompletionFunc *dma_cb)
 {
+#ifdef DEBUG_AHCI
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
-
+#endif
     DPRINTF(ad->port_no, "\n");
-    ad->dma_cb = dma_cb;
-    ad->dma_status |= BM_STATUS_DMAING;
     s->io_buffer_offset = 0;
     dma_cb(s, 0);
 }
@@ -1095,7 +1094,6 @@ static int ahci_dma_set_unit(IDEDMA *dma, int unit)
 static int ahci_dma_add_status(IDEDMA *dma, int status)
 {
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
-    ad->dma_status |= status;
     DPRINTF(ad->port_no, "set status: %x\n", status);
 
     if (status & BM_STATUS_INT) {
@@ -1114,8 +1112,6 @@ static int ahci_dma_set_inactive(IDEDMA *dma)
     /* update d2h status */
     ahci_write_fis_d2h(ad, NULL);
 
-    ad->dma_cb = NULL;
-
     if (!ad->check_bh) {
         /* maybe we still have something to process, check later */
         ad->check_bh = qemu_bh_new(ahci_check_cmd_bh, ad);
@@ -1203,6 +1199,82 @@ void ahci_reset(AHCIState *s)
     }
 }
 
+static const VMStateDescription vmstate_ahci_device = {
+    .name = "ahci port",
+    .version_id = 1,
+    .fields = (VMStateField []) {
+        VMSTATE_IDE_BUS(port, AHCIDevice),
+        VMSTATE_UINT32(port_state, AHCIDevice),
+        VMSTATE_UINT32(finished, AHCIDevice),
+        VMSTATE_UINT32(port_regs.lst_addr, AHCIDevice),
+        VMSTATE_UINT32(port_regs.lst_addr_hi, AHCIDevice),
+        VMSTATE_UINT32(port_regs.fis_addr, AHCIDevice),
+        VMSTATE_UINT32(port_regs.fis_addr_hi, AHCIDevice),
+        VMSTATE_UINT32(port_regs.irq_stat, AHCIDevice),
+        VMSTATE_UINT32(port_regs.irq_mask, AHCIDevice),
+        VMSTATE_UINT32(port_regs.cmd, AHCIDevice),
+        VMSTATE_UINT32(port_regs.tfdata, AHCIDevice),
+        VMSTATE_UINT32(port_regs.sig, AHCIDevice),
+        VMSTATE_UINT32(port_regs.scr_stat, AHCIDevice),
+        VMSTATE_UINT32(port_regs.scr_ctl, AHCIDevice),
+        VMSTATE_UINT32(port_regs.scr_err, AHCIDevice),
+        VMSTATE_UINT32(port_regs.scr_act, AHCIDevice),
+        VMSTATE_UINT32(port_regs.cmd_issue, AHCIDevice),
+        VMSTATE_BOOL(done_atapi_packet, AHCIDevice),
+        VMSTATE_INT32(busy_slot, AHCIDevice),
+        VMSTATE_BOOL(init_d2h_sent, AHCIDevice),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static int ahci_state_post_load(void *opaque, int version_id)
+{
+    int i;
+    struct AHCIDevice *ad;
+    AHCIState *s = opaque;
+
+    for (i = 0; i < s->ports; i++) {
+        ad = &s->dev[i];
+        AHCIPortRegs *pr = &ad->port_regs;
+
+        map_page(&ad->lst,
+                 ((uint64_t)pr->lst_addr_hi << 32) | pr->lst_addr, 1024);
+        map_page(&ad->res_fis,
+                 ((uint64_t)pr->fis_addr_hi << 32) | pr->fis_addr, 256);
+        /*
+         * All pending i/o should be flushed out on a migrate. However,
+         * we might not have cleared the busy_slot since this is done
+         * in a bh. Also, issue i/o against any slots that are pending.
+         */
+        if ((ad->busy_slot != -1) &&
+            !(ad->port.ifs[0].status & (BUSY_STAT|DRQ_STAT))) {
+            pr->cmd_issue &= ~(1 << ad->busy_slot);
+            ad->busy_slot = -1;
+        }
+        check_cmd(s, i);
+    }
+
+    return 0;
+}
+
+const VMStateDescription vmstate_ahci = {
+    .name = "ahci",
+    .version_id = 1,
+    .post_load = ahci_state_post_load,
+    .fields = (VMStateField []) {
+        VMSTATE_STRUCT_VARRAY_POINTER_INT32(dev, AHCIState, ports,
+                                     vmstate_ahci_device, AHCIDevice),
+        VMSTATE_UINT32(control_regs.cap, AHCIState),
+        VMSTATE_UINT32(control_regs.ghc, AHCIState),
+        VMSTATE_UINT32(control_regs.irqstatus, AHCIState),
+        VMSTATE_UINT32(control_regs.impl, AHCIState),
+        VMSTATE_UINT32(control_regs.version, AHCIState),
+        VMSTATE_UINT32(idp_index, AHCIState),
+        VMSTATE_INT32(ports, AHCIState),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 typedef struct SysbusAHCIState {
     SysBusDevice busdev;
     AHCIState ahci;
@@ -1211,7 +1283,11 @@ typedef struct SysbusAHCIState {
 
 static const VMStateDescription vmstate_sysbus_ahci = {
     .name = "sysbus-ahci",
-    .unmigratable = 1,
+    .unmigratable = 1, /* Still buggy under I/O load */
+    .fields = (VMStateField []) {
+        VMSTATE_AHCI(ahci, AHCIPCIState),
+        VMSTATE_END_OF_LIST()
+    },
 };
 
 static void sysbus_ahci_reset(DeviceState *dev)
diff --git a/hw/ide/ahci.h b/hw/ide/ahci.h
index 1200a56ada..85f37fe99d 100644
--- a/hw/ide/ahci.h
+++ b/hw/ide/ahci.h
@@ -281,11 +281,9 @@ struct AHCIDevice {
     QEMUBH *check_bh;
     uint8_t *lst;
     uint8_t *res_fis;
-    int dma_status;
-    int done_atapi_packet;
-    int busy_slot;
-    int init_d2h_sent;
-    BlockDriverCompletionFunc *dma_cb;
+    bool done_atapi_packet;
+    int32_t busy_slot;
+    bool init_d2h_sent;
     AHCICmdHdr *cur_cmd;
     NCQTransferState ncq_tfs[AHCI_MAX_CMDS];
 };
@@ -297,7 +295,7 @@ typedef struct AHCIState {
     MemoryRegion idp;       /* Index-Data Pair I/O port space */
     unsigned idp_offset;    /* Offset of index in I/O port space */
     uint32_t idp_index;     /* Current IDP index */
-    int ports;
+    int32_t ports;
     qemu_irq irq;
     DMAContext *dma;
 } AHCIState;
@@ -307,6 +305,16 @@ typedef struct AHCIPCIState {
     AHCIState ahci;
 } AHCIPCIState;
 
+extern const VMStateDescription vmstate_ahci;
+
+#define VMSTATE_AHCI(_field, _state) {                               \
+    .name       = (stringify(_field)),                               \
+    .size       = sizeof(AHCIState),                                 \
+    .vmsd       = &vmstate_ahci,                                     \
+    .flags      = VMS_STRUCT,                                        \
+    .offset     = vmstate_offset_value(_state, _field, AHCIState),   \
+}
+
 typedef struct NCQFrame {
     uint8_t fis_type;
     uint8_t c;
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 14ad0799c3..3743dc3b55 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -1149,8 +1149,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         }
         ide_set_irq(s->bus);
         break;
+
     case WIN_VERIFY_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_VERIFY:
     case WIN_VERIFY_ONCE:
         /* do sector number check ? */
@@ -1158,8 +1160,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         s->status = READY_STAT | SEEK_STAT;
         ide_set_irq(s->bus);
         break;
+
     case WIN_READ_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_READ:
     case WIN_READ_ONCE:
         if (s->drive_kind == IDE_CD) {
@@ -1173,8 +1177,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         s->req_nb_sectors = 1;
         ide_sector_read(s);
         break;
+
     case WIN_WRITE_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_WRITE:
     case WIN_WRITE_ONCE:
     case CFA_WRITE_SECT_WO_ERASE:
@@ -1189,8 +1195,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         ide_transfer_start(s, s->io_buffer, 512, ide_sector_write);
         s->media_changed = 1;
         break;
+
     case WIN_MULTREAD_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_MULTREAD:
         if (!s->bs) {
             goto abort_cmd;
@@ -1202,8 +1210,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         s->req_nb_sectors = s->mult_sectors;
         ide_sector_read(s);
         break;
+
     case WIN_MULTWRITE_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_MULTWRITE:
     case CFA_WRITE_MULTI_WO_ERASE:
         if (!s->bs) {
@@ -1222,8 +1232,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         ide_transfer_start(s, s->io_buffer, 512 * n, ide_sector_write);
         s->media_changed = 1;
         break;
+
     case WIN_READDMA_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_READDMA:
     case WIN_READDMA_ONCE:
         if (!s->bs) {
@@ -1232,8 +1244,10 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
 	ide_cmd_lba48_transform(s, lba48);
         ide_sector_start_dma(s, IDE_DMA_READ);
         break;
+
     case WIN_WRITEDMA_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_WRITEDMA:
     case WIN_WRITEDMA_ONCE:
         if (!s->bs) {
@@ -1243,14 +1257,17 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         ide_sector_start_dma(s, IDE_DMA_WRITE);
         s->media_changed = 1;
         break;
+
     case WIN_READ_NATIVE_MAX_EXT:
-	lba48 = 1;
+        lba48 = 1;
+        /* fall through */
     case WIN_READ_NATIVE_MAX:
 	ide_cmd_lba48_transform(s, lba48);
         ide_set_sector(s, s->nb_sectors - 1);
         s->status = READY_STAT | SEEK_STAT;
         ide_set_irq(s->bus);
         break;
+
     case WIN_CHECKPOWERMODE1:
     case WIN_CHECKPOWERMODE2:
         s->error = 0;
diff --git a/hw/ide/ich.c b/hw/ide/ich.c
index 1fb803d340..cc30adc701 100644
--- a/hw/ide/ich.c
+++ b/hw/ide/ich.c
@@ -79,9 +79,15 @@
 #define ICH9_IDP_INDEX          0x10
 #define ICH9_IDP_INDEX_LOG2     0x04
 
-static const VMStateDescription vmstate_ahci = {
-    .name = "ahci",
-    .unmigratable = 1,
+static const VMStateDescription vmstate_ich9_ahci = {
+    .name = "ich9_ahci",
+    .unmigratable = 1, /* Still buggy under I/O load */
+    .version_id = 1,
+    .fields = (VMStateField []) {
+        VMSTATE_PCI_DEVICE(card, AHCIPCIState),
+        VMSTATE_AHCI(ahci, AHCIPCIState),
+        VMSTATE_END_OF_LIST()
+    },
 };
 
 static void pci_ich9_reset(DeviceState *dev)
@@ -152,7 +158,7 @@ static void ich_ahci_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_INTEL_82801IR;
     k->revision = 0x02;
     k->class_id = PCI_CLASS_STORAGE_SATA;
-    dc->vmsd = &vmstate_ahci;
+    dc->vmsd = &vmstate_ich9_ahci;
     dc->reset = pci_ich9_reset;
 }
 
diff --git a/hw/pc.c b/hw/pc.c
index 780b1e4743..34b6dff686 100644
--- a/hw/pc.c
+++ b/hw/pc.c
@@ -551,6 +551,18 @@ int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
     return index;
 }
 
+/* Calculates the limit to CPU APIC ID values
+ *
+ * This function returns the limit for the APIC ID value, so that all
+ * CPU APIC IDs are < pc_apic_id_limit().
+ *
+ * This is used for FW_CFG_MAX_CPUS. See comments on bochs_bios_init().
+ */
+static unsigned int pc_apic_id_limit(unsigned int max_cpus)
+{
+    return x86_cpu_apic_id_from_index(max_cpus - 1) + 1;
+}
+
 static void *bochs_bios_init(void)
 {
     void *fw_cfg;
@@ -558,9 +570,24 @@ static void *bochs_bios_init(void)
     size_t smbios_len;
     uint64_t *numa_fw_cfg;
     int i, j;
+    unsigned int apic_id_limit = pc_apic_id_limit(max_cpus);
 
     fw_cfg = fw_cfg_init(BIOS_CFG_IOPORT, BIOS_CFG_IOPORT + 1, 0, 0);
-
+    /* FW_CFG_MAX_CPUS is a bit confusing/problematic on x86:
+     *
+     * SeaBIOS needs FW_CFG_MAX_CPUS for CPU hotplug, but the CPU hotplug
+     * QEMU<->SeaBIOS interface is not based on the "CPU index", but on the APIC
+     * ID of hotplugged CPUs[1]. This means that FW_CFG_MAX_CPUS is not the
+     * "maximum number of CPUs", but the "limit to the APIC ID values SeaBIOS
+     * may see".
+     *
+     * So, this means we must not use max_cpus, here, but the maximum possible
+     * APIC ID value, plus one.
+     *
+     * [1] The only kind of "CPU identifier" used between SeaBIOS and QEMU is
+     *     the APIC ID, not the "CPU index"
+     */
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)apic_id_limit);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_bytes(fw_cfg, FW_CFG_ACPI_TABLES,
@@ -579,21 +606,24 @@ static void *bochs_bios_init(void)
      * of nodes, one word for each VCPU->node and one word for each node to
      * hold the amount of memory.
      */
-    numa_fw_cfg = g_new0(uint64_t, 1 + max_cpus + nb_numa_nodes);
+    numa_fw_cfg = g_new0(uint64_t, 1 + apic_id_limit + nb_numa_nodes);
     numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
     for (i = 0; i < max_cpus; i++) {
+        unsigned int apic_id = x86_cpu_apic_id_from_index(i);
+        assert(apic_id < apic_id_limit);
         for (j = 0; j < nb_numa_nodes; j++) {
             if (test_bit(i, node_cpumask[j])) {
-                numa_fw_cfg[i + 1] = cpu_to_le64(j);
+                numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);
                 break;
             }
         }
     }
     for (i = 0; i < nb_numa_nodes; i++) {
-        numa_fw_cfg[max_cpus + 1 + i] = cpu_to_le64(node_mem[i]);
+        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(node_mem[i]);
     }
     fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,
-                     (1 + max_cpus + nb_numa_nodes) * sizeof(*numa_fw_cfg));
+                     (1 + apic_id_limit + nb_numa_nodes) *
+                     sizeof(*numa_fw_cfg));
 
     return fw_cfg;
 }
diff --git a/hw/pc_piix.c b/hw/pc_piix.c
index 0a6923dcef..b9a9b2efe1 100644
--- a/hw/pc_piix.c
+++ b/hw/pc_piix.c
@@ -235,10 +235,18 @@ static void pc_init_pci(QEMUMachineInitArgs *args)
 
 static void pc_init_pci_1_3(QEMUMachineInitArgs *args)
 {
-    enable_kvm_pv_eoi();
+    enable_compat_apic_id_mode();
     pc_init_pci(args);
 }
 
+/* PC machine init function for pc-0.14 to pc-1.2 */
+static void pc_init_pci_1_2(QEMUMachineInitArgs *args)
+{
+    disable_kvm_pv_eoi();
+    pc_init_pci_1_3(args);
+}
+
+/* PC init function for pc-0.10 to pc-0.13, and reused by xenfv */
 static void pc_init_pci_no_kvmclock(QEMUMachineInitArgs *args)
 {
     ram_addr_t ram_size = args->ram_size;
@@ -247,6 +255,8 @@ static void pc_init_pci_no_kvmclock(QEMUMachineInitArgs *args)
     const char *kernel_cmdline = args->kernel_cmdline;
     const char *initrd_filename = args->initrd_filename;
     const char *boot_device = args->boot_device;
+    disable_kvm_pv_eoi();
+    enable_compat_apic_id_mode();
     pc_init1(get_system_memory(),
              get_system_io(),
              ram_size, boot_device,
@@ -264,6 +274,8 @@ static void pc_init_isa(QEMUMachineInitArgs *args)
     const char *boot_device = args->boot_device;
     if (cpu_model == NULL)
         cpu_model = "486";
+    disable_kvm_pv_eoi();
+    enable_compat_apic_id_mode();
     pc_init1(get_system_memory(),
              get_system_io(),
              ram_size, boot_device,
@@ -286,7 +298,7 @@ static QEMUMachine pc_i440fx_machine_v1_4 = {
     .name = "pc-i440fx-1.4",
     .alias = "pc",
     .desc = "Standard PC (i440FX + PIIX, 1996)",
-    .init = pc_init_pci_1_3,
+    .init = pc_init_pci,
     .max_cpus = 255,
     .is_default = 1,
     DEFAULT_MACHINE_OPTIONS,
@@ -342,7 +354,7 @@ static QEMUMachine pc_machine_v1_3 = {
 static QEMUMachine pc_machine_v1_2 = {
     .name = "pc-1.2",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_1_2,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_2,
@@ -386,7 +398,7 @@ static QEMUMachine pc_machine_v1_2 = {
 static QEMUMachine pc_machine_v1_1 = {
     .name = "pc-1.1",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_1_2,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_1,
@@ -422,7 +434,7 @@ static QEMUMachine pc_machine_v1_1 = {
 static QEMUMachine pc_machine_v1_0 = {
     .name = "pc-1.0",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_1_2,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_0,
@@ -438,7 +450,7 @@ static QEMUMachine pc_machine_v1_0 = {
 static QEMUMachine pc_machine_v0_15 = {
     .name = "pc-0.15",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_1_2,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_15,
@@ -471,7 +483,7 @@ static QEMUMachine pc_machine_v0_15 = {
 static QEMUMachine pc_machine_v0_14 = {
     .name = "pc-0.14",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_1_2,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_14, 
diff --git a/hw/ppc/mac_newworld.c b/hw/ppc/mac_newworld.c
index 6de810bde1..065ea871b3 100644
--- a/hw/ppc/mac_newworld.c
+++ b/hw/ppc/mac_newworld.c
@@ -413,6 +413,7 @@ static void ppc_core99_init(QEMUMachineInitArgs *args)
     /* No PCI init: the BIOS will do it */
 
     fw_cfg = fw_cfg_init(0, 0, CFG_ADDR, CFG_ADDR + 2);
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_i16(fw_cfg, FW_CFG_MACHINE_ID, machine_arch);
diff --git a/hw/ppc/mac_oldworld.c b/hw/ppc/mac_oldworld.c
index 9ed303a5e5..2778e45879 100644
--- a/hw/ppc/mac_oldworld.c
+++ b/hw/ppc/mac_oldworld.c
@@ -299,6 +299,7 @@ static void ppc_heathrow_init(QEMUMachineInitArgs *args)
     /* No PCI init: the BIOS will do it */
 
     fw_cfg = fw_cfg_init(0, 0, CFG_ADDR, CFG_ADDR + 2);
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_i16(fw_cfg, FW_CFG_MACHINE_ID, ARCH_HEATHROW);
diff --git a/hw/sun4m.c b/hw/sun4m.c
index 035a011768..9903f443cb 100644
--- a/hw/sun4m.c
+++ b/hw/sun4m.c
@@ -1021,6 +1021,7 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, ram_addr_t RAM_size,
                  hwdef->ecc_version);
 
     fw_cfg = fw_cfg_init(0, 0, CFG_ADDR, CFG_ADDR + 2);
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_i16(fw_cfg, FW_CFG_MACHINE_ID, hwdef->machine_id);
@@ -1665,6 +1666,7 @@ static void sun4d_hw_init(const struct sun4d_hwdef *hwdef, ram_addr_t RAM_size,
                "Sun4d");
 
     fw_cfg = fw_cfg_init(0, 0, CFG_ADDR, CFG_ADDR + 2);
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_i16(fw_cfg, FW_CFG_MACHINE_ID, hwdef->machine_id);
@@ -1865,6 +1867,7 @@ static void sun4c_hw_init(const struct sun4c_hwdef *hwdef, ram_addr_t RAM_size,
                "Sun4c");
 
     fw_cfg = fw_cfg_init(0, 0, CFG_ADDR, CFG_ADDR + 2);
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_i16(fw_cfg, FW_CFG_MACHINE_ID, hwdef->machine_id);
diff --git a/hw/sun4u.c b/hw/sun4u.c
index b891b84c9c..9fbda29ac4 100644
--- a/hw/sun4u.c
+++ b/hw/sun4u.c
@@ -878,6 +878,7 @@ static void sun4uv_init(MemoryRegion *address_space_mem,
                            (uint8_t *)&nd_table[0].macaddr);
 
     fw_cfg = fw_cfg_init(BIOS_CFG_IOPORT, BIOS_CFG_IOPORT + 1, 0, 0);
+    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)max_cpus);
     fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
     fw_cfg_add_i16(fw_cfg, FW_CFG_MACHINE_ID, hwdef->machine_id);
diff --git a/hw/virtio-balloon.c b/hw/virtio-balloon.c
index 3040bc63ab..c0a790264c 100644
--- a/hw/virtio-balloon.c
+++ b/hw/virtio-balloon.c
@@ -14,6 +14,7 @@
  */
 
 #include "qemu/iov.h"
+#include "qemu/timer.h"
 #include "qemu-common.h"
 #include "virtio.h"
 #include "pc.h"
@@ -22,6 +23,7 @@
 #include "virtio-balloon.h"
 #include "sysemu/kvm.h"
 #include "exec/address-spaces.h"
+#include "qapi/visitor.h"
 
 #if defined(__linux__)
 #include <sys/mman.h>
@@ -36,6 +38,9 @@ typedef struct VirtIOBalloon
     uint64_t stats[VIRTIO_BALLOON_S_NR];
     VirtQueueElement stats_vq_elem;
     size_t stats_vq_offset;
+    QEMUTimer *stats_timer;
+    int64_t stats_last_update;
+    int64_t stats_poll_interval;
     DeviceState *qdev;
 } VirtIOBalloon;
 
@@ -53,6 +58,16 @@ static void balloon_page(void *addr, int deflate)
 #endif
 }
 
+static const char *balloon_stat_names[] = {
+   [VIRTIO_BALLOON_S_SWAP_IN] = "stat-swap-in",
+   [VIRTIO_BALLOON_S_SWAP_OUT] = "stat-swap-out",
+   [VIRTIO_BALLOON_S_MAJFLT] = "stat-major-faults",
+   [VIRTIO_BALLOON_S_MINFLT] = "stat-minor-faults",
+   [VIRTIO_BALLOON_S_MEMFREE] = "stat-free-memory",
+   [VIRTIO_BALLOON_S_MEMTOT] = "stat-total-memory",
+   [VIRTIO_BALLOON_S_NR] = NULL
+};
+
 /*
  * reset_stats - Mark all items in the stats array as unset
  *
@@ -67,6 +82,118 @@ static inline void reset_stats(VirtIOBalloon *dev)
     for (i = 0; i < VIRTIO_BALLOON_S_NR; dev->stats[i++] = -1);
 }
 
+static bool balloon_stats_supported(const VirtIOBalloon *s)
+{
+    return s->vdev.guest_features & (1 << VIRTIO_BALLOON_F_STATS_VQ);
+}
+
+static bool balloon_stats_enabled(const VirtIOBalloon *s)
+{
+    return s->stats_poll_interval > 0;
+}
+
+static void balloon_stats_destroy_timer(VirtIOBalloon *s)
+{
+    if (balloon_stats_enabled(s)) {
+        qemu_del_timer(s->stats_timer);
+        qemu_free_timer(s->stats_timer);
+        s->stats_timer = NULL;
+        s->stats_poll_interval = 0;
+    }
+}
+
+static void balloon_stats_change_timer(VirtIOBalloon *s, int secs)
+{
+    qemu_mod_timer(s->stats_timer, qemu_get_clock_ms(vm_clock) + secs * 1000);
+}
+
+static void balloon_stats_poll_cb(void *opaque)
+{
+    VirtIOBalloon *s = opaque;
+
+    if (!balloon_stats_supported(s)) {
+        /* re-schedule */
+        balloon_stats_change_timer(s, s->stats_poll_interval);
+        return;
+    }
+
+    virtqueue_push(s->svq, &s->stats_vq_elem, s->stats_vq_offset);
+    virtio_notify(&s->vdev, s->svq);
+}
+
+static void balloon_stats_get_all(Object *obj, struct Visitor *v,
+                                  void *opaque, const char *name, Error **errp)
+{
+    VirtIOBalloon *s = opaque;
+    int i;
+
+    if (!s->stats_last_update) {
+        error_setg(errp, "guest hasn't updated any stats yet");
+        return;
+    }
+
+    visit_start_struct(v, NULL, "guest-stats", name, 0, errp);
+    visit_type_int(v, &s->stats_last_update, "last-update", errp);
+
+    visit_start_struct(v, NULL, NULL, "stats", 0, errp);
+    for (i = 0; i < VIRTIO_BALLOON_S_NR; i++) {
+        visit_type_int64(v, (int64_t *) &s->stats[i], balloon_stat_names[i],
+                         errp);
+    }
+    visit_end_struct(v, errp);
+
+    visit_end_struct(v, errp);
+}
+
+static void balloon_stats_get_poll_interval(Object *obj, struct Visitor *v,
+                                            void *opaque, const char *name,
+                                            Error **errp)
+{
+    VirtIOBalloon *s = opaque;
+    visit_type_int(v, &s->stats_poll_interval, name, errp);
+}
+
+static void balloon_stats_set_poll_interval(Object *obj, struct Visitor *v,
+                                            void *opaque, const char *name,
+                                            Error **errp)
+{
+    VirtIOBalloon *s = opaque;
+    int64_t value;
+
+    visit_type_int(v, &value, name, errp);
+    if (error_is_set(errp)) {
+        return;
+    }
+
+    if (value < 0) {
+        error_setg(errp, "timer value must be greater than zero");
+        return;
+    }
+
+    if (value == s->stats_poll_interval) {
+        return;
+    }
+
+    if (value == 0) {
+        /* timer=0 disables the timer */
+        balloon_stats_destroy_timer(s);
+        return;
+    }
+
+    if (balloon_stats_enabled(s)) {
+        /* timer interval change */
+        s->stats_poll_interval = value;
+        balloon_stats_change_timer(s, value);
+        return;
+    }
+
+    /* create a new timer */
+    g_assert(s->stats_timer == NULL);
+    s->stats_timer = qemu_new_timer_ms(vm_clock, balloon_stats_poll_cb, s);
+    s->stats_poll_interval = value;
+    balloon_stats_change_timer(s, 0);
+}
+
 static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOBalloon *s = to_virtio_balloon(vdev);
@@ -107,9 +234,10 @@ static void virtio_balloon_receive_stats(VirtIODevice *vdev, VirtQueue *vq)
     VirtQueueElement *elem = &s->stats_vq_elem;
     VirtIOBalloonStat stat;
     size_t offset = 0;
+    qemu_timeval tv;
 
     if (!virtqueue_pop(vq, elem)) {
-        return;
+        goto out;
     }
 
     /* Initialize the stats to get rid of any stale values.  This is only
@@ -128,6 +256,18 @@ static void virtio_balloon_receive_stats(VirtIODevice *vdev, VirtQueue *vq)
             s->stats[tag] = val;
     }
     s->stats_vq_offset = offset;
+
+    if (qemu_gettimeofday(&tv) < 0) {
+        fprintf(stderr, "warning: %s: failed to get time of day\n", __func__);
+        goto out;
+    }
+
+    s->stats_last_update = tv.tv_sec;
+
+out:
+    if (balloon_stats_enabled(s)) {
+        balloon_stats_change_timer(s, s->stats_poll_interval);
+    }
 }
 
 static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
@@ -164,28 +304,6 @@ static uint32_t virtio_balloon_get_features(VirtIODevice *vdev, uint32_t f)
 static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
 {
     VirtIOBalloon *dev = opaque;
-
-#if 0
-    /* Disable guest-provided stats for now. For more details please check:
-     * https://bugzilla.redhat.com/show_bug.cgi?id=623903
-     *
-     * If you do enable it (which is probably not going to happen as we
-     * need a new command for it), remember that you also need to fill the
-     * appropriate members of the BalloonInfo structure so that the stats
-     * are returned to the client.
-     */
-    if (dev->vdev.guest_features & (1 << VIRTIO_BALLOON_F_STATS_VQ)) {
-        virtqueue_push(dev->svq, &dev->stats_vq_elem, dev->stats_vq_offset);
-        virtio_notify(&dev->vdev, dev->svq);
-        return;
-    }
-#endif
-
-    /* Stats are not supported.  Clear out any stale values that might
-     * have been set by a more featureful guest kernel.
-     */
-    reset_stats(dev);
-
     info->actual = ram_size - ((uint64_t) dev->actual <<
                                VIRTIO_BALLOON_PFN_SHIFT);
 }
@@ -255,12 +373,18 @@ VirtIODevice *virtio_balloon_init(DeviceState *dev)
     s->dvq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
     s->svq = virtio_add_queue(&s->vdev, 128, virtio_balloon_receive_stats);
 
-    reset_stats(s);
-
     s->qdev = dev;
     register_savevm(dev, "virtio-balloon", -1, 1,
                     virtio_balloon_save, virtio_balloon_load, s);
 
+    object_property_add(OBJECT(dev), "guest-stats", "guest statistics",
+                        balloon_stats_get_all, NULL, NULL, s, NULL);
+
+    object_property_add(OBJECT(dev), "guest-stats-polling-interval", "int",
+                        balloon_stats_get_poll_interval,
+                        balloon_stats_set_poll_interval,
+                        NULL, s, NULL);
+
     return &s->vdev;
 }
 
@@ -268,6 +392,7 @@ void virtio_balloon_exit(VirtIODevice *vdev)
 {
     VirtIOBalloon *s = DO_UPCAST(VirtIOBalloon, vdev, vdev);
 
+    balloon_stats_destroy_timer(s);
     qemu_remove_balloon_handler(s);
     unregister_savevm(s->qdev, "virtio-balloon", s);
     virtio_cleanup(vdev);