pc,pci,vhost,net fixes, enhancements

Don's patches to limit below-4g ram for pc
 Marcel's pcie hotplug rewrite
 Gabriel's changes to e1000 auto-negotiation
 qemu char bugfixes by Stefan
 misc bugfixes
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJTqEbfAAoJECgfDbjSjVRpFkoIAKj/JZvwQfOkDON12iIou8Fm
 qFhn9t6Tf/HHvwhsrLrPH3wnmTiwJpnSrU2/X9SjSBqugiG4NdS2BrzGS1T5mNET
 Q8q2CdYhrWzriCnNMotoug8oXIJGSfORITsU2c3zH7mLJHi5V6m78PZzLiiyTgJW
 VS0Zb/F2YFn9vDA6vzSX3dUCH/1MGVwTf3pSaGBs3k1DwPT9OpV7ejdhqJ0SB03t
 ih//P3E5t2+kkoUEUEqHVhRepvn0nrDq9fxL97scUbhx5Lz3hBteoewNjlqDsrCv
 kbX+PswfSRWTEbjQ3yeGSyyzITIe/6W7rLb2gYAl2Efn/WDGIw2JXff2XPiro1I=
 =qjXy
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pc,pci,vhost,net fixes, enhancements

Don's patches to limit below-4g ram for pc
Marcel's pcie hotplug rewrite
Gabriel's changes to e1000 auto-negotiation
qemu char bugfixes by Stefan
misc bugfixes

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Mon 23 Jun 2014 16:25:19 BST using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"

* remotes/mst/tags/for_upstream: (23 commits)
  xen-hvm: Handle machine opt max-ram-below-4g
  pc & q35: Add new machine opt max-ram-below-4g
  xen-hvm: Fix xen_hvm_init() to adjust pc memory layout
  pcie: coding style tweak
  hw/pcie: better hotplug/hotunplug support
  hw/pcie: implement power controller functionality
  hw/pcie: correct debug message
  q35: Use PC_Q35_COMPAT_1_4 on pc-q35-1.4 compat_props
  virtio-pci: Report an error when msix vectors init fails
  qemu-char: avoid leaking unused fds in tcp_get_msgfds()
  qemu-char: fix qemu_chr_fe_get_msgfd()
  qapi/string-output-visitor: fix human output
  e1000: factor out checking for auto-negotiation availability
  e1000: move e1000_autoneg_timer() to after set_ics()
  e1000: signal guest on successful link auto-negotiation
  e1000: improve auto-negotiation reporting via mii-tool
  e1000: emulate auto-negotiation during external link status change
  qtest: fix vhost-user-test unbalanced mutex locks
  qtest: fix qtest for vhost-user
  libqemustub: add more stubs for qemu-char
  ...

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

hmp.c

@@ -1692,7 +1692,7 @@ void hmp_info_memdev(Monitor *mon, const QDict *qdict)
         ov = string_output_visitor_new(false);
         visit_type_uint16List(string_output_get_visitor(ov),
                               &m->value->host_nodes, NULL, NULL);
-        monitor_printf(mon, "memory device %d\n", i);
+        monitor_printf(mon, "memory backend: %d\n", i);
         monitor_printf(mon, "  size:  %" PRId64 "\n", m->value->size);
         monitor_printf(mon, "  merge: %s\n",
                        m->value->merge ? "true" : "false");

hw/i386/pc.c

@@ -1643,11 +1643,58 @@ pc_machine_get_hotplug_memory_region_size(Object *obj, Visitor *v, void *opaque,
     visit_type_int(v, &value, name, errp);
 }
 
+static void pc_machine_get_max_ram_below_4g(Object *obj, Visitor *v,
+                                         void *opaque, const char *name,
+                                         Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+    uint64_t value = pcms->max_ram_below_4g;
+
+    visit_type_size(v, &value, name, errp);
+}
+
+static void pc_machine_set_max_ram_below_4g(Object *obj, Visitor *v,
+                                         void *opaque, const char *name,
+                                         Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+    Error *error = NULL;
+    uint64_t value;
+
+    visit_type_size(v, &value, name, &error);
+    if (error) {
+        error_propagate(errp, error);
+        return;
+    }
+    if (value > (1ULL << 32)) {
+        error_set(&error, ERROR_CLASS_GENERIC_ERROR,
+                  "Machine option 'max-ram-below-4g=%"PRIu64
+                  "' expects size less than or equal to 4G", value);
+        error_propagate(errp, error);
+        return;
+    }
+
+    if (value < (1ULL << 20)) {
+        error_report("Warning: small max_ram_below_4g(%"PRIu64
+                     ") less than 1M.  BIOS may not work..",
+                     value);
+    }
+
+    pcms->max_ram_below_4g = value;
+}
+
 static void pc_machine_initfn(Object *obj)
 {
+    PCMachineState *pcms = PC_MACHINE(obj);
+
     object_property_add(obj, PC_MACHINE_MEMHP_REGION_SIZE, "int",
                         pc_machine_get_hotplug_memory_region_size,
                         NULL, NULL, NULL, NULL);
+    pcms->max_ram_below_4g = 1ULL << 32; /* 4G */
+    object_property_add(obj, PC_MACHINE_MAX_RAM_BELOW_4G, "size",
+                        pc_machine_get_max_ram_below_4g,
+                        pc_machine_set_max_ram_below_4g,
+                        NULL, NULL, NULL);
 }
 
 static void pc_machine_class_init(ObjectClass *oc, void *data)

hw/i386/pc_piix.c

@@ -48,6 +48,7 @@
 #include "exec/address-spaces.h"
 #include "hw/acpi/acpi.h"
 #include "cpu.h"
+#include "qemu/error-report.h"
 #ifdef CONFIG_XEN
 #  include <xen/hvm/hvm_info_table.h>
 #endif
@@ -98,8 +99,44 @@ static void pc_init1(MachineState *machine,
     DeviceState *icc_bridge;
     FWCfgState *fw_cfg = NULL;
     PcGuestInfo *guest_info;
+    ram_addr_t lowmem;
 
-    if (xen_enabled() && xen_hvm_init(&ram_memory) != 0) {
+    /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory).
+     * If it doesn't, we need to split it in chunks below and above 4G.
+     * In any case, try to make sure that guest addresses aligned at
+     * 1G boundaries get mapped to host addresses aligned at 1G boundaries.
+     * For old machine types, use whatever split we used historically to avoid
+     * breaking migration.
+     */
+    if (machine->ram_size >= 0xe0000000) {
+        lowmem = gigabyte_align ? 0xc0000000 : 0xe0000000;
+    } else {
+        lowmem = 0xe0000000;
+    }
+
+    /* Handle the machine opt max-ram-below-4g.  It is basicly doing
+     * min(qemu limit, user limit).
+     */
+    if (lowmem > pc_machine->max_ram_below_4g) {
+        lowmem = pc_machine->max_ram_below_4g;
+        if (machine->ram_size - lowmem > lowmem &&
+            lowmem & ((1ULL << 30) - 1)) {
+            error_report("Warning: Large machine and max_ram_below_4g(%"PRIu64
+                         ") not a multiple of 1G; possible bad performance.",
+                         pc_machine->max_ram_below_4g);
+        }
+    }
+
+    if (machine->ram_size >= lowmem) {
+        above_4g_mem_size = machine->ram_size - lowmem;
+        below_4g_mem_size = lowmem;
+    } else {
+        above_4g_mem_size = 0;
+        below_4g_mem_size = machine->ram_size;
+    }
+
+    if (xen_enabled() && xen_hvm_init(&below_4g_mem_size, &above_4g_mem_size,
+                                      &ram_memory) != 0) {
         fprintf(stderr, "xen hardware virtual machine initialisation failed\n");
         exit(1);
     }
@@ -114,22 +151,6 @@ static void pc_init1(MachineState *machine,
         kvmclock_create();
     }
 
-    /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory).
-     * If it doesn't, we need to split it in chunks below and above 4G.
-     * In any case, try to make sure that guest addresses aligned at
-     * 1G boundaries get mapped to host addresses aligned at 1G boundaries.
-     * For old machine types, use whatever split we used historically to avoid
-     * breaking migration.
-     */
-    if (machine->ram_size >= 0xe0000000) {
-        ram_addr_t lowmem = gigabyte_align ? 0xc0000000 : 0xe0000000;
-        above_4g_mem_size = machine->ram_size - lowmem;
-        below_4g_mem_size = lowmem;
-    } else {
-        above_4g_mem_size = 0;
-        below_4g_mem_size = machine->ram_size;
-    }
-
     if (pci_enabled) {
         pci_memory = g_new(MemoryRegion, 1);
         memory_region_init(pci_memory, NULL, "pci", UINT64_MAX);

hw/i386/pc_q35.c

@@ -44,6 +44,7 @@
 #include "hw/ide/ahci.h"
 #include "hw/usb.h"
 #include "hw/cpu/icc_bus.h"
+#include "qemu/error-report.h"
 
 /* ICH9 AHCI has 6 ports */
 #define MAX_SATA_PORTS     6
@@ -85,8 +86,46 @@ static void pc_q35_init(MachineState *machine)
     PCIDevice *ahci;
     DeviceState *icc_bridge;
     PcGuestInfo *guest_info;
+    ram_addr_t lowmem;
 
-    if (xen_enabled() && xen_hvm_init(&ram_memory) != 0) {
+    /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory
+     * and 256 Mbytes for PCI Express Enhanced Configuration Access Mapping
+     * also known as MMCFG).
+     * If it doesn't, we need to split it in chunks below and above 4G.
+     * In any case, try to make sure that guest addresses aligned at
+     * 1G boundaries get mapped to host addresses aligned at 1G boundaries.
+     * For old machine types, use whatever split we used historically to avoid
+     * breaking migration.
+     */
+    if (machine->ram_size >= 0xb0000000) {
+        lowmem = gigabyte_align ? 0x80000000 : 0xb0000000;
+    } else {
+        lowmem = 0xb0000000;
+    }
+
+    /* Handle the machine opt max-ram-below-4g.  It is basicly doing
+     * min(qemu limit, user limit).
+     */
+    if (lowmem > pc_machine->max_ram_below_4g) {
+        lowmem = pc_machine->max_ram_below_4g;
+        if (machine->ram_size - lowmem > lowmem &&
+            lowmem & ((1ULL << 30) - 1)) {
+            error_report("Warning: Large machine and max_ram_below_4g(%"PRIu64
+                         ") not a multiple of 1G; possible bad performance.",
+                         pc_machine->max_ram_below_4g);
+        }
+    }
+
+    if (machine->ram_size >= lowmem) {
+        above_4g_mem_size = machine->ram_size - lowmem;
+        below_4g_mem_size = lowmem;
+    } else {
+        above_4g_mem_size = 0;
+        below_4g_mem_size = machine->ram_size;
+    }
+
+    if (xen_enabled() && xen_hvm_init(&below_4g_mem_size, &above_4g_mem_size,
+                                      &ram_memory) != 0) {
         fprintf(stderr, "xen hardware virtual machine initialisation failed\n");
         exit(1);
     }
@@ -100,24 +139,6 @@ static void pc_q35_init(MachineState *machine)
 
     kvmclock_create();
 
-    /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory
-     * and 256 Mbytes for PCI Express Enhanced Configuration Access Mapping
-     * also known as MMCFG).
-     * If it doesn't, we need to split it in chunks below and above 4G.
-     * In any case, try to make sure that guest addresses aligned at
-     * 1G boundaries get mapped to host addresses aligned at 1G boundaries.
-     * For old machine types, use whatever split we used historically to avoid
-     * breaking migration.
-     */
-    if (machine->ram_size >= 0xb0000000) {
-        ram_addr_t lowmem = gigabyte_align ? 0x80000000 : 0xb0000000;
-        above_4g_mem_size = machine->ram_size - lowmem;
-        below_4g_mem_size = lowmem;
-    } else {
-        above_4g_mem_size = 0;
-        below_4g_mem_size = machine->ram_size;
-    }
-
     /* pci enabled */
     if (pci_enabled) {
         pci_memory = g_new(MemoryRegion, 1);
@@ -388,7 +409,7 @@ static QEMUMachine pc_q35_machine_v1_4 = {
     .name = "pc-q35-1.4",
     .init = pc_q35_init_1_4,
     .compat_props = (GlobalProperty[]) {
-        PC_COMPAT_1_4,
+        PC_Q35_COMPAT_1_4,
         { /* end of list */ }
     },
 };

hw/net/e1000.c

@@ -175,6 +175,8 @@ e1000_link_down(E1000State *s)
 {
     s->mac_reg[STATUS] &= ~E1000_STATUS_LU;
     s->phy_reg[PHY_STATUS] &= ~MII_SR_LINK_STATUS;
+    s->phy_reg[PHY_STATUS] &= ~MII_SR_AUTONEG_COMPLETE;
+    s->phy_reg[PHY_LP_ABILITY] &= ~MII_LPAR_LPACK;
 }
 
 static void
@@ -197,23 +199,11 @@ set_phy_ctrl(E1000State *s, int index, uint16_t val)
     }
     if ((val & MII_CR_AUTO_NEG_EN) && (val & MII_CR_RESTART_AUTO_NEG)) {
         e1000_link_down(s);
-        s->phy_reg[PHY_STATUS] &= ~MII_SR_AUTONEG_COMPLETE;
         DBGOUT(PHY, "Start link auto negotiation\n");
         timer_mod(s->autoneg_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + 500);
     }
 }
 
-static void
-e1000_autoneg_timer(void *opaque)
-{
-    E1000State *s = opaque;
-    if (!qemu_get_queue(s->nic)->link_down) {
-        e1000_link_up(s);
-    }
-    s->phy_reg[PHY_STATUS] |= MII_SR_AUTONEG_COMPLETE;
-    DBGOUT(PHY, "Auto negotiation is completed\n");
-}
-
 static void (*phyreg_writeops[])(E1000State *, int, uint16_t) = {
     [PHY_CTRL] = set_phy_ctrl,
 };
@@ -227,7 +217,8 @@ static const char phy_regcap[0x20] = {
     [PHY_CTRL] = PHY_RW,	[PHY_1000T_CTRL] = PHY_RW,
     [PHY_LP_ABILITY] = PHY_R,	[PHY_1000T_STATUS] = PHY_R,
     [PHY_AUTONEG_ADV] = PHY_RW,	[M88E1000_RX_ERR_CNTR] = PHY_R,
-    [PHY_ID2] = PHY_R,		[M88E1000_PHY_SPEC_STATUS] = PHY_R
+    [PHY_ID2] = PHY_R,		[M88E1000_PHY_SPEC_STATUS] = PHY_R,
+    [PHY_AUTONEG_EXP] = PHY_R,
 };
 
 /* PHY_ID2 documented in 8254x_GBe_SDM.pdf, pp. 250 */
@@ -344,6 +335,19 @@ set_ics(E1000State *s, int index, uint32_t val)
     set_interrupt_cause(s, 0, val | s->mac_reg[ICR]);
 }
 
+static void
+e1000_autoneg_timer(void *opaque)
+{
+    E1000State *s = opaque;
+    if (!qemu_get_queue(s->nic)->link_down) {
+        e1000_link_up(s);
+        s->phy_reg[PHY_LP_ABILITY] |= MII_LPAR_LPACK;
+        s->phy_reg[PHY_STATUS] |= MII_SR_AUTONEG_COMPLETE;
+        DBGOUT(PHY, "Auto negotiation is completed\n");
+        set_ics(s, 0, E1000_ICS_LSC); /* signal link status change to guest */
+    }
+}
+
 static int
 rxbufsize(uint32_t v)
 {
@@ -844,6 +848,14 @@ receive_filter(E1000State *s, const uint8_t *buf, int size)
     return 0;
 }
 
+static bool
+have_autoneg(E1000State *s)
+{
+    return (s->compat_flags & E1000_FLAG_AUTONEG) &&
+           (s->phy_reg[PHY_CTRL] & MII_CR_AUTO_NEG_EN) &&
+           (s->phy_reg[PHY_CTRL] & MII_CR_RESTART_AUTO_NEG);
+}
+
 static void
 e1000_set_link_status(NetClientState *nc)
 {
@@ -853,7 +865,14 @@ e1000_set_link_status(NetClientState *nc)
     if (nc->link_down) {
         e1000_link_down(s);
     } else {
-        e1000_link_up(s);
+        if (have_autoneg(s) &&
+            !(s->phy_reg[PHY_STATUS] & MII_SR_AUTONEG_COMPLETE)) {
+            /* emulate auto-negotiation if supported */
+            timer_mod(s->autoneg_timer,
+                      qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + 500);
+        } else {
+            e1000_link_up(s);
+        }
     }
 
     if (s->mac_reg[STATUS] != old_status)
@@ -1279,19 +1298,13 @@ static void e1000_pre_save(void *opaque)
         e1000_mit_timer(s);
     }
 
-    if (!(s->compat_flags & E1000_FLAG_AUTONEG)) {
-        return;
-    }
-
     /*
-     * If link is down and auto-negotiation is ongoing, complete
+     * If link is down and auto-negotiation is supported and ongoing,
-     * auto-negotiation immediately.  This allows is to look at
+     * complete auto-negotiation immediately. This allows us to look
-     * MII_SR_AUTONEG_COMPLETE to infer link status on load.
+     * at MII_SR_AUTONEG_COMPLETE to infer link status on load.
      */
-    if (nc->link_down &&
+    if (nc->link_down && have_autoneg(s)) {
-        s->phy_reg[PHY_CTRL] & MII_CR_AUTO_NEG_EN &&
+        s->phy_reg[PHY_STATUS] |= MII_SR_AUTONEG_COMPLETE;
-        s->phy_reg[PHY_CTRL] & MII_CR_RESTART_AUTO_NEG) {
-         s->phy_reg[PHY_STATUS] |= MII_SR_AUTONEG_COMPLETE;
     }
 }
 
@@ -1313,15 +1326,11 @@ static int e1000_post_load(void *opaque, int version_id)
      * Alternatively, restart link negotiation if it was in progress. */
     nc->link_down = (s->mac_reg[STATUS] & E1000_STATUS_LU) == 0;
 
-    if (!(s->compat_flags & E1000_FLAG_AUTONEG)) {
+    if (have_autoneg(s) &&
-        return 0;
-    }
-
-    if (s->phy_reg[PHY_CTRL] & MII_CR_AUTO_NEG_EN &&
-        s->phy_reg[PHY_CTRL] & MII_CR_RESTART_AUTO_NEG &&
         !(s->phy_reg[PHY_STATUS] & MII_SR_AUTONEG_COMPLETE)) {
         nc->link_down = false;
-        timer_mod(s->autoneg_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + 500);
+        timer_mod(s->autoneg_timer,
+                  qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + 500);
     }
 
     return 0;

hw/net/e1000_regs.h

@@ -384,6 +384,9 @@
 #define MII_SR_100X_FD_CAPS      0x4000	/* 100X  Full Duplex Capable */
 #define MII_SR_100T4_CAPS        0x8000	/* 100T4 Capable */
 
+/* PHY Link Partner Ability Register */
+#define MII_LPAR_LPACK           0x4000 /* Acked by link partner */
+
 /* Interrupt Cause Read */
 #define E1000_ICR_TXDW          0x00000001 /* Transmit desc written back */
 #define E1000_ICR_TXQE          0x00000002 /* Transmit Queue empty */

hw/pci-bridge/ioh3420.c

@@ -180,6 +180,12 @@ PCIESlot *ioh3420_init(PCIBus *bus, int devfn, bool multifunction,
     return PCIE_SLOT(d);
 }
 
+static Property ioh3420_props[] = {
+    DEFINE_PROP_BIT(COMPAT_PROP_PCP, PCIDevice, cap_present,
+                    QEMU_PCIE_SLTCAP_PCP_BITNR, true),
+    DEFINE_PROP_END_OF_LIST()
+};
+
 static const VMStateDescription vmstate_ioh3420 = {
     .name = "ioh-3240-express-root-port",
     .version_id = 1,
@@ -210,6 +216,7 @@ static void ioh3420_class_init(ObjectClass *klass, void *data)
     dc->desc = "Intel IOH device id 3420 PCIE Root Port";
     dc->reset = ioh3420_reset;
     dc->vmsd = &vmstate_ioh3420;
+    dc->props = ioh3420_props;
 }
 
 static const TypeInfo ioh3420_info = {

hw/pci-bridge/xio3130_downstream.c

@@ -147,6 +147,12 @@ PCIESlot *xio3130_downstream_init(PCIBus *bus, int devfn, bool multifunction,
     return PCIE_SLOT(d);
 }
 
+static Property xio3130_downstream_props[] = {
+    DEFINE_PROP_BIT(COMPAT_PROP_PCP, PCIDevice, cap_present,
+                    QEMU_PCIE_SLTCAP_PCP_BITNR, true),
+    DEFINE_PROP_END_OF_LIST()
+};
+
 static const VMStateDescription vmstate_xio3130_downstream = {
     .name = "xio3130-express-downstream-port",
     .version_id = 1,
@@ -177,6 +183,7 @@ static void xio3130_downstream_class_init(ObjectClass *klass, void *data)
     dc->desc = "TI X3130 Downstream Port of PCI Express Switch";
     dc->reset = xio3130_downstream_reset;
     dc->vmsd = &vmstate_xio3130_downstream;
+    dc->props = xio3130_downstream_props;
 }
 
 static const TypeInfo xio3130_downstream_info = {

hw/pci/pcie.c

@@ -224,7 +224,7 @@ static void pcie_cap_slot_hotplug_common(PCIDevice *hotplug_dev,
     *exp_cap = hotplug_dev->config + hotplug_dev->exp.exp_cap;
     uint16_t sltsta = pci_get_word(*exp_cap + PCI_EXP_SLTSTA);
 
-    PCIE_DEV_PRINTF(PCI_DEVICE(dev), "hotplug state: %d\n", state);
+    PCIE_DEV_PRINTF(PCI_DEVICE(dev), "hotplug state: 0x%x\n", sltsta);
     if (sltsta & PCI_EXP_SLTSTA_EIS) {
         /* the slot is electromechanically locked.
          * This error is propagated up to qdev and then to HMP/QMP.
@@ -258,7 +258,8 @@ void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
 
     pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
                                PCI_EXP_SLTSTA_PDS);
-    pcie_cap_slot_event(PCI_DEVICE(hotplug_dev), PCI_EXP_HP_EV_PDC);
+    pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
+                        PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
 }
 
 void pcie_cap_slot_hot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
@@ -268,10 +269,7 @@ void pcie_cap_slot_hot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
 
     pcie_cap_slot_hotplug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
 
-    object_unparent(OBJECT(dev));
+    pcie_cap_slot_push_attention_button(PCI_DEVICE(hotplug_dev));
-    pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
-                                 PCI_EXP_SLTSTA_PDS);
-    pcie_cap_slot_event(PCI_DEVICE(hotplug_dev), PCI_EXP_HP_EV_PDC);
 }
 
 /* pci express slot for pci express root/downstream port
@@ -294,6 +292,15 @@ void pcie_cap_slot_init(PCIDevice *dev, uint16_t slot)
                                PCI_EXP_SLTCAP_AIP |
                                PCI_EXP_SLTCAP_ABP);
 
+    if (dev->cap_present & QEMU_PCIE_SLTCAP_PCP) {
+        pci_long_test_and_set_mask(dev->config + pos + PCI_EXP_SLTCAP,
+                                   PCI_EXP_SLTCAP_PCP);
+        pci_word_test_and_clear_mask(dev->config + pos + PCI_EXP_SLTCTL,
+                                     PCI_EXP_SLTCTL_PCC);
+        pci_word_test_and_set_mask(dev->wmask + pos + PCI_EXP_SLTCTL,
+                                   PCI_EXP_SLTCTL_PCC);
+    }
+
     pci_word_test_and_clear_mask(dev->config + pos + PCI_EXP_SLTCTL,
                                  PCI_EXP_SLTCTL_PIC |
                                  PCI_EXP_SLTCTL_AIC);
@@ -327,6 +334,10 @@ void pcie_cap_slot_init(PCIDevice *dev, uint16_t slot)
 void pcie_cap_slot_reset(PCIDevice *dev)
 {
     uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+    uint8_t port_type = pcie_cap_get_type(dev);
+
+    assert(port_type == PCI_EXP_TYPE_DOWNSTREAM ||
+           port_type == PCI_EXP_TYPE_ROOT_PORT);
 
     PCIE_DEV_PRINTF(dev, "reset\n");
 
@@ -339,9 +350,25 @@ void pcie_cap_slot_reset(PCIDevice *dev)
                                  PCI_EXP_SLTCTL_PDCE |
                                  PCI_EXP_SLTCTL_ABPE);
     pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTCTL,
-                               PCI_EXP_SLTCTL_PIC_OFF |
                                PCI_EXP_SLTCTL_AIC_OFF);
 
+    if (dev->cap_present & QEMU_PCIE_SLTCAP_PCP) {
+        /* Downstream ports enforce device number 0. */
+        bool populated = pci_bridge_get_sec_bus(PCI_BRIDGE(dev))->devices[0];
+        uint16_t pic;
+
+        if (populated) {
+            pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTCTL,
+                                         PCI_EXP_SLTCTL_PCC);
+        } else {
+            pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTCTL,
+                                       PCI_EXP_SLTCTL_PCC);
+        }
+
+        pic = populated ? PCI_EXP_SLTCTL_PIC_ON : PCI_EXP_SLTCTL_PIC_OFF;
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTCTL, pic);
+    }
+
     pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
                                  PCI_EXP_SLTSTA_EIS |/* on reset,
                                                         the lock is released */
@@ -352,6 +379,11 @@ void pcie_cap_slot_reset(PCIDevice *dev)
     hotplug_event_update_event_status(dev);
 }
 
+static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
+{
+    object_unparent(OBJECT(dev));
+}
+
 void pcie_cap_slot_write_config(PCIDevice *dev,
                                 uint32_t addr, uint32_t val, int len)
 {
@@ -376,6 +408,22 @@ void pcie_cap_slot_write_config(PCIDevice *dev,
                         sltsta);
     }
 
+    /*
+     * If the slot is polulated, power indicator is off and power
+     * controller is off, it is safe to detach the devices.
+     */
+    if ((sltsta & PCI_EXP_SLTSTA_PDS) && (val & PCI_EXP_SLTCTL_PCC) &&
+        ((val & PCI_EXP_SLTCTL_PIC_OFF) == PCI_EXP_SLTCTL_PIC_OFF)) {
+            PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev));
+            pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
+                                pcie_unplug_device, NULL);
+
+            pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
+                                         PCI_EXP_SLTSTA_PDS);
+            pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+                                       PCI_EXP_SLTSTA_PDC);
+    }
+
     hotplug_event_notify(dev);
 
     /* 

hw/virtio/vhost.c

@@ -20,6 +20,7 @@
 #include <linux/vhost.h>
 #include "exec/address-spaces.h"
 #include "hw/virtio/virtio-bus.h"
+#include "migration/migration.h"
 
 static void vhost_dev_sync_region(struct vhost_dev *dev,
                                   MemoryRegionSection *section,
@@ -304,7 +305,9 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev,
                                       uint64_t size)
 {
     int i;
-    for (i = 0; i < dev->nvqs; ++i) {
+    int r = 0;
+
+    for (i = 0; !r && i < dev->nvqs; ++i) {
         struct vhost_virtqueue *vq = dev->vqs + i;
         hwaddr l;
         void *p;
@@ -316,15 +319,15 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev,
         p = cpu_physical_memory_map(vq->ring_phys, &l, 1);
         if (!p || l != vq->ring_size) {
             fprintf(stderr, "Unable to map ring buffer for ring %d\n", i);
-            return -ENOMEM;
+            r = -ENOMEM;
         }
         if (p != vq->ring) {
             fprintf(stderr, "Ring buffer relocated for ring %d\n", i);
-            return -EBUSY;
+            r = -EBUSY;
         }
         cpu_physical_memory_unmap(p, l, 0, 0);
     }
-    return 0;
+    return r;
 }
 
 static struct vhost_memory_region *vhost_dev_find_reg(struct vhost_dev *dev,
@@ -854,6 +857,12 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
         .eventfd_del = vhost_eventfd_del,
         .priority = 10
     };
+    hdev->migration_blocker = NULL;
+    if (!(hdev->features & (0x1 << VHOST_F_LOG_ALL))) {
+        error_setg(&hdev->migration_blocker,
+                   "Migration disabled: vhost lacks VHOST_F_LOG_ALL feature.");
+        migrate_add_blocker(hdev->migration_blocker);
+    }
     hdev->mem = g_malloc0(offsetof(struct vhost_memory, regions));
     hdev->n_mem_sections = 0;
     hdev->mem_sections = NULL;
@@ -882,6 +891,10 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
         vhost_virtqueue_cleanup(hdev->vqs + i);
     }
     memory_listener_unregister(&hdev->memory_listener);
+    if (hdev->migration_blocker) {
+        migrate_del_blocker(hdev->migration_blocker);
+        error_free(hdev->migration_blocker);
+    }
     g_free(hdev->mem);
     g_free(hdev->mem_sections);
     hdev->vhost_ops->vhost_backend_cleanup(hdev);

hw/virtio/virtio-pci.c

@@ -976,6 +976,8 @@ static void virtio_pci_device_plugged(DeviceState *d)
 
     if (proxy->nvectors &&
         msix_init_exclusive_bar(&proxy->pci_dev, proxy->nvectors, 1)) {
+        error_report("unable to init msix vectors to %" PRIu32,
+                     proxy->nvectors);
         proxy->nvectors = 0;
     }
 

include/hw/i386/pc.h

@@ -33,10 +33,13 @@ struct PCMachineState {
     MemoryRegion hotplug_memory;
 
     HotplugHandler *acpi_dev;
+
+    uint64_t max_ram_below_4g;
 };
 
 #define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device"
 #define PC_MACHINE_MEMHP_REGION_SIZE "hotplug-memory-region-size"
+#define PC_MACHINE_MAX_RAM_BELOW_4G "max-ram-below-4g"
 
 /**
  * PCMachineClass:
@@ -297,8 +300,16 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);
             .driver   = "ICH9-LPC",\
             .property = "memory-hotplug-support",\
             .value    = "off",\
+        },{\
+            .driver   = "xio3130-downstream",\
+            .property = COMPAT_PROP_PCP,\
+            .value    = "off",\
+        },{\
+            .driver   = "ioh3420",\
+            .property = COMPAT_PROP_PCP,\
+            .value    = "off",\
         }
-
+ 
 #define PC_Q35_COMPAT_1_7 \
         PC_COMPAT_1_7, \
         PC_Q35_COMPAT_2_0, \

include/hw/pci/pci.h

@@ -158,6 +158,9 @@ enum {
     QEMU_PCI_CAP_SHPC = (1 << QEMU_PCI_SHPC_BITNR),
 #define QEMU_PCI_SLOTID_BITNR 6
     QEMU_PCI_CAP_SLOTID = (1 << QEMU_PCI_SLOTID_BITNR),
+    /* PCI Express capability - Power Controller Present */
+#define QEMU_PCIE_SLTCAP_PCP_BITNR 7
+    QEMU_PCIE_SLTCAP_PCP = (1 << QEMU_PCIE_SLTCAP_PCP_BITNR),
 };
 
 #define TYPE_PCI_DEVICE "pci-device"

include/hw/pci/pcie.h

@@ -76,6 +76,8 @@ struct PCIExpressDevice {
     PCIEAERLog aer_log;
 };
 
+#define COMPAT_PROP_PCP "power_controller_present"
+
 /* PCI express capability helper functions */
 int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type, uint8_t port);
 int pcie_endpoint_cap_init(PCIDevice *dev, uint8_t offset);

include/hw/pci/pcie_regs.h

@@ -57,6 +57,8 @@
 #define PCI_EXP_SLTCTL_PIC_SHIFT        (ffs(PCI_EXP_SLTCTL_PIC) - 1)
 #define PCI_EXP_SLTCTL_PIC_OFF                          \
     (PCI_EXP_SLTCTL_IND_OFF << PCI_EXP_SLTCTL_PIC_SHIFT)
+#define PCI_EXP_SLTCTL_PIC_ON                          \
+    (PCI_EXP_SLTCTL_IND_ON << PCI_EXP_SLTCTL_PIC_SHIFT)
 
 #define PCI_EXP_SLTCTL_SUPPORTED        \
             (PCI_EXP_SLTCTL_ABPE |      \

include/hw/virtio/vhost.h

@@ -45,6 +45,7 @@ struct vhost_dev {
     bool log_enabled;
     vhost_log_chunk_t *log;
     unsigned long long log_size;
+    Error *migration_blocker;
     bool force;
     bool memory_changed;
     hwaddr mem_changed_start_addr;

include/hw/xen/xen.h

@@ -37,10 +37,11 @@ void xen_cmos_set_s3_resume(void *opaque, int irq, int level);
 qemu_irq *xen_interrupt_controller_init(void);
 
 int xen_init(MachineClass *mc);
-int xen_hvm_init(MemoryRegion **ram_memory);
 void xenstore_store_pv_console_info(int i, struct CharDriverState *chr);
 
 #if defined(NEED_CPU_H) && !defined(CONFIG_USER_ONLY)
+int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size,
+                 MemoryRegion **ram_memory);
 void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size,
                    struct MemoryRegion *mr);
 void xen_modified_memory(ram_addr_t start, ram_addr_t length);

monitor.c

@@ -2968,7 +2968,7 @@ static mon_cmd_t info_cmds[] = {
         .name       = "memdev",
         .args_type  = "",
         .params     = "",
-        .help       = "show the memory device",
+        .help       = "show memory backends",
         .mhandler.cmd = hmp_info_memdev,
     },
     {

qapi-schema.json

@@ -3158,19 +3158,19 @@
 ##
 # @Memdev:
 #
-# Information of memory device
+# Information about memory backend
 #
-# @size: memory device size
+# @size: memory backend size
 #
 # @merge: enables or disables memory merge support
 #
-# @dump: includes memory device's memory in a core dump or not
+# @dump: includes memory backend's memory in a core dump or not
 #
 # @prealloc: enables or disables memory preallocation
 #
 # @host-nodes: host nodes for its memory policy
 #
-# @policy: memory policy of memory device
+# @policy: memory policy of memory backend
 #
 # Since: 2.1
 ##
@@ -3187,13 +3187,15 @@
 ##
 # @query-memdev:
 #
-# Returns information for all memory devices.
+# Returns information for all memory backends.
 #
 # Returns: a list of @Memdev.
 #
 # Since: 2.1
 ##
 { 'command': 'query-memdev', 'returns': ['Memdev'] }
+
+##
 # @PCDIMMDeviceInfo:
 #
 # PCDIMMDevice state information

qapi/string-output-visitor.c

@@ -98,7 +98,7 @@ static void format_string(StringOutputVisitor *sov, Range *r, bool next,
 {
     if (r->end - r->begin > 1) {
         if (human) {
-            g_string_append_printf(sov->string, "0x%" PRIx64 "-%" PRIx64,
+            g_string_append_printf(sov->string, "0x%" PRIx64 "-0x%" PRIx64,
                                    r->begin, r->end - 1);
 
         } else {

qemu-char.c

@@ -204,7 +204,7 @@ void qemu_chr_be_write(CharDriverState *s, uint8_t *buf, int len)
 int qemu_chr_fe_get_msgfd(CharDriverState *s)
 {
     int fd;
-    return (qemu_chr_fe_get_msgfds(s, &fd, 1) >= 0) ? fd : -1;
+    return (qemu_chr_fe_get_msgfds(s, &fd, 1) == 1) ? fd : -1;
 }
 
 int qemu_chr_fe_get_msgfds(CharDriverState *s, int *fds, int len)
@@ -2481,8 +2481,15 @@ static int tcp_get_msgfds(CharDriverState *chr, int *fds, int num)
     int to_copy = (s->read_msgfds_num < num) ? s->read_msgfds_num : num;
 
     if (to_copy) {
+        int i;
+
         memcpy(fds, s->read_msgfds, to_copy * sizeof(int));
 
+        /* Close unused fds */
+        for (i = to_copy; i < s->read_msgfds_num; i++) {
+            close(s->read_msgfds[i]);
+        }
+
         g_free(s->read_msgfds);
         s->read_msgfds = 0;
         s->read_msgfds_num = 0;

stubs/Makefile.objs

@@ -1,5 +1,6 @@
 stub-obj-y += arch-query-cpu-def.o
 stub-obj-y += bdrv-commit-all.o
+stub-obj-y += chr-baum-init.o
 stub-obj-y += chr-msmouse.o
 stub-obj-y += clock-warp.o
 stub-obj-y += cpu-get-clock.o
@@ -24,6 +25,7 @@ stub-obj-y += mon-set-error.o
 stub-obj-y += monitor-init.o
 stub-obj-y += notify-event.o
 stub-obj-y += pci-drive-hot-add.o
+stub-obj-$(CONFIG_SPICE) += qemu-chr-open-spice.o
 stub-obj-y += qtest.o
 stub-obj-y += reset.o
 stub-obj-y += runstate-check.o

stubs/chr-baum-init.c

@@ -0,0 +1,7 @@
+#include "qemu-common.h"
+#include "sysemu/char.h"
+
+CharDriverState *chr_baum_init(void)
+{
+    return NULL;
+}

stubs/qemu-chr-open-spice.c

@@ -0,0 +1,14 @@
+#include "qemu-common.h"
+#include "ui/qemu-spice.h"
+
+CharDriverState *qemu_chr_open_spice_vmc(const char *type)
+{
+    return NULL;
+}
+
+#if SPICE_SERVER_VERSION >= 0x000c02
+CharDriverState *qemu_chr_open_spice_port(const char *name)
+{
+    return NULL;
+}
+#endif

tests/vhost-user-test.c

@@ -8,17 +8,30 @@
  *
  */
 
+#define QEMU_GLIB_COMPAT_H
+#include <glib.h>
+
 #include "libqtest.h"
 #include "qemu/option.h"
 #include "sysemu/char.h"
 #include "sysemu/sysemu.h"
 
-#include <glib.h>
 #include <linux/vhost.h>
 #include <sys/mman.h>
 #include <sys/vfs.h>
 #include <qemu/sockets.h>
 
+/* GLIB version compatibility flags */
+#if GLIB_CHECK_VERSION(2, 28, 0)
+#define HAVE_MONOTONIC_TIME
+#endif
+
+#if GLIB_CHECK_VERSION(2, 32, 0)
+#define HAVE_MUTEX_INIT
+#define HAVE_COND_INIT
+#define HAVE_THREAD_NEW
+#endif
+
 #define QEMU_CMD_ACCEL  " -machine accel=tcg"
 #define QEMU_CMD_MEM    " -m 512 -object memory-backend-file,id=mem,size=512M,"\
                         "mem-path=%s,share=on -numa node,memdev=mem"
@@ -95,8 +108,93 @@ static VhostUserMsg m __attribute__ ((unused));
 
 int fds_num = 0, fds[VHOST_MEMORY_MAX_NREGIONS];
 static VhostUserMemory memory;
-static GMutex data_mutex;
+static GMutex *data_mutex;
-static GCond data_cond;
+static GCond *data_cond;
+
+static gint64 _get_time(void)
+{
+#ifdef HAVE_MONOTONIC_TIME
+    return g_get_monotonic_time();
+#else
+    GTimeVal time;
+    g_get_current_time(&time);
+
+    return time.tv_sec * G_TIME_SPAN_SECOND + time.tv_usec;
+#endif
+}
+
+static GMutex *_mutex_new(void)
+{
+    GMutex *mutex;
+
+#ifdef HAVE_MUTEX_INIT
+    mutex = g_new(GMutex, 1);
+    g_mutex_init(mutex);
+#else
+    mutex = g_mutex_new();
+#endif
+
+    return mutex;
+}
+
+static void _mutex_free(GMutex *mutex)
+{
+#ifdef HAVE_MUTEX_INIT
+    g_mutex_clear(mutex);
+    g_free(mutex);
+#else
+    g_mutex_free(mutex);
+#endif
+}
+
+static GCond *_cond_new(void)
+{
+    GCond *cond;
+
+#ifdef HAVE_COND_INIT
+    cond = g_new(GCond, 1);
+    g_cond_init(cond);
+#else
+    cond = g_cond_new();
+#endif
+
+    return cond;
+}
+
+static gboolean _cond_wait_until(GCond *cond, GMutex *mutex, gint64 end_time)
+{
+    gboolean ret = FALSE;
+#ifdef HAVE_COND_INIT
+    ret = g_cond_wait_until(cond, mutex, end_time);
+#else
+    GTimeVal time = { end_time / G_TIME_SPAN_SECOND,
+                      end_time % G_TIME_SPAN_SECOND };
+    ret = g_cond_timed_wait(cond, mutex, &time);
+#endif
+    return ret;
+}
+
+static void _cond_free(GCond *cond)
+{
+#ifdef HAVE_COND_INIT
+    g_cond_clear(cond);
+    g_free(cond);
+#else
+    g_cond_free(cond);
+#endif
+}
+
+static GThread *_thread_new(const gchar *name, GThreadFunc func, gpointer data)
+{
+    GThread *thread = NULL;
+    GError *error = NULL;
+#ifdef HAVE_THREAD_NEW
+    thread = g_thread_try_new(name, func, data, &error);
+#else
+    thread = g_thread_create(func, data, TRUE, &error);
+#endif
+    return thread;
+}
 
 static void read_guest_mem(void)
 {
@@ -104,11 +202,11 @@ static void read_guest_mem(void)
     gint64 end_time;
     int i, j;
 
-    g_mutex_lock(&data_mutex);
+    g_mutex_lock(data_mutex);
 
-    end_time = g_get_monotonic_time() + 5 * G_TIME_SPAN_SECOND;
+    end_time = _get_time() + 5 * G_TIME_SPAN_SECOND;
     while (!fds_num) {
-        if (!g_cond_wait_until(&data_cond, &data_mutex, end_time)) {
+        if (!_cond_wait_until(data_cond, data_mutex, end_time)) {
             /* timeout has passed */
             g_assert(fds_num);
             break;
@@ -143,7 +241,7 @@ static void read_guest_mem(void)
     }
 
     g_assert_cmpint(1, ==, 1);
-    g_mutex_unlock(&data_mutex);
+    g_mutex_unlock(data_mutex);
 }
 
 static void *thread_function(void *data)
@@ -171,6 +269,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
         return;
     }
 
+    g_mutex_lock(data_mutex);
     memcpy(p, buf, VHOST_USER_HDR_SIZE);
 
     if (msg.size) {
@@ -203,8 +302,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
         fds_num = qemu_chr_fe_get_msgfds(chr, fds, sizeof(fds) / sizeof(int));
 
         /* signal the test that it can continue */
-        g_cond_signal(&data_cond);
+        g_cond_signal(data_cond);
-        g_mutex_unlock(&data_mutex);
         break;
 
     case VHOST_USER_SET_VRING_KICK:
@@ -221,6 +319,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
     default:
         break;
     }
+    g_mutex_unlock(data_mutex);
 }
 
 static const char *init_hugepagefs(void)
@@ -285,10 +384,9 @@ int main(int argc, char **argv)
     qemu_chr_add_handlers(chr, chr_can_read, chr_read, NULL, chr);
 
     /* run the main loop thread so the chardev may operate */
-    g_mutex_init(&data_mutex);
+    data_mutex = _mutex_new();
-    g_cond_init(&data_cond);
+    data_cond = _cond_new();
-    g_mutex_lock(&data_mutex);
+    _thread_new(NULL, thread_function, NULL);
-    g_thread_new(NULL, thread_function, NULL);
 
     qemu_cmd = g_strdup_printf(QEMU_CMD, hugefs, socket_path);
     s = qtest_start(qemu_cmd);
@@ -305,8 +403,8 @@ int main(int argc, char **argv)
     /* cleanup */
     unlink(socket_path);
     g_free(socket_path);
-    g_cond_clear(&data_cond);
+    _cond_free(data_cond);
-    g_mutex_clear(&data_mutex);
+    _mutex_free(data_mutex);
 
     return ret;
 }

vl.c

@@ -380,6 +380,10 @@ static QemuOptsList qemu_machine_opts = {
             .name = "kvm-type",
             .type = QEMU_OPT_STRING,
             .help = "Specifies the KVM virtualization mode (HV, PR)",
+        },{
+            .name = PC_MACHINE_MAX_RAM_BELOW_4G,
+            .type = QEMU_OPT_SIZE,
+            .help = "maximum ram below the 4G boundary (32bit boundary)",
         },
         { /* End of list */ }
     },

xen-hvm-stub.c

@@ -51,7 +51,8 @@ void xen_modified_memory(ram_addr_t start, ram_addr_t length)
 {
 }
 
-int xen_hvm_init(MemoryRegion **ram_memory)
+int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size,
+                 MemoryRegion **ram_memory)
 {
     return 0;
 }

xen-hvm.c

@@ -155,30 +155,43 @@ qemu_irq *xen_interrupt_controller_init(void)
 
 /* Memory Ops */
 
-static void xen_ram_init(ram_addr_t ram_size, MemoryRegion **ram_memory_p)
+static void xen_ram_init(ram_addr_t *below_4g_mem_size,
+                         ram_addr_t *above_4g_mem_size,
+                         ram_addr_t ram_size, MemoryRegion **ram_memory_p)
 {
     MemoryRegion *sysmem = get_system_memory();
-    ram_addr_t below_4g_mem_size, above_4g_mem_size = 0;
     ram_addr_t block_len;
+    uint64_t user_lowmem = object_property_get_int(qdev_get_machine(),
+                                                   PC_MACHINE_MAX_RAM_BELOW_4G,
+                                                   &error_abort);
 
-    block_len = ram_size;
+    /* Handle the machine opt max-ram-below-4g.  It is basicly doing
-    if (ram_size >= HVM_BELOW_4G_RAM_END) {
+     * min(xen limit, user limit).
-        /* Xen does not allocate the memory continuously, and keep a hole at
+     */
-         * HVM_BELOW_4G_MMIO_START of HVM_BELOW_4G_MMIO_LENGTH
+    if (HVM_BELOW_4G_RAM_END <= user_lowmem) {
+        user_lowmem = HVM_BELOW_4G_RAM_END;
+    }
+
+    if (ram_size >= user_lowmem) {
+        *above_4g_mem_size = ram_size - user_lowmem;
+        *below_4g_mem_size = user_lowmem;
+    } else {
+        *above_4g_mem_size = 0;
+        *below_4g_mem_size = ram_size;
+    }
+    if (!*above_4g_mem_size) {
+        block_len = ram_size;
+    } else {
+        /*
+         * Xen does not allocate the memory continuously, it keeps a
+         * hole of the size computed above or passed in.
          */
-        block_len += HVM_BELOW_4G_MMIO_LENGTH;
+        block_len = (1ULL << 32) + *above_4g_mem_size;
     }
     memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len);
     *ram_memory_p = &ram_memory;
     vmstate_register_ram_global(&ram_memory);
 
-    if (ram_size >= HVM_BELOW_4G_RAM_END) {
-        above_4g_mem_size = ram_size - HVM_BELOW_4G_RAM_END;
-        below_4g_mem_size = HVM_BELOW_4G_RAM_END;
-    } else {
-        below_4g_mem_size = ram_size;
-    }
-
     memory_region_init_alias(&ram_640k, NULL, "xen.ram.640k",
                              &ram_memory, 0, 0xa0000);
     memory_region_add_subregion(sysmem, 0, &ram_640k);
@@ -189,12 +202,13 @@ static void xen_ram_init(ram_addr_t ram_size, MemoryRegion **ram_memory_p)
      * the Options ROM, so it is registered here as RAM.
      */
     memory_region_init_alias(&ram_lo, NULL, "xen.ram.lo",
-                             &ram_memory, 0xc0000, below_4g_mem_size - 0xc0000);
+                             &ram_memory, 0xc0000,
+                             *below_4g_mem_size - 0xc0000);
     memory_region_add_subregion(sysmem, 0xc0000, &ram_lo);
-    if (above_4g_mem_size > 0) {
+    if (*above_4g_mem_size > 0) {
         memory_region_init_alias(&ram_hi, NULL, "xen.ram.hi",
                                  &ram_memory, 0x100000000ULL,
-                                 above_4g_mem_size);
+                                 *above_4g_mem_size);
         memory_region_add_subregion(sysmem, 0x100000000ULL, &ram_hi);
     }
 }
@@ -958,7 +972,8 @@ static void xen_wakeup_notifier(Notifier *notifier, void *data)
     xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0);
 }
 
-int xen_hvm_init(MemoryRegion **ram_memory)
+int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size,
+                 MemoryRegion **ram_memory)
 {
     int i, rc;
     unsigned long ioreq_pfn;
@@ -1036,7 +1051,7 @@ int xen_hvm_init(MemoryRegion **ram_memory)
 
     /* Init RAM management */
     xen_map_cache_init(xen_phys_offset_to_gaddr, state);
-    xen_ram_init(ram_size, ram_memory);
+    xen_ram_init(below_4g_mem_size, above_4g_mem_size, ram_size, ram_memory);
 
     qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state);