1 files changed, 126 insertions, 77 deletions

diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index ef64bf1..c46f6f9 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -15,20 +15,20 @@
 #include "qemu/cutils.h"
 #include "qemu/error-report.h"
 #include "qemu/units.h"
-#include "sysemu/numa.h"
-#include "sysemu/sysemu.h"
-#include "sysemu/reset.h"
-#include "sysemu/runstate.h"
+#include "system/numa.h"
+#include "system/system.h"
+#include "system/reset.h"
+#include "system/runstate.h"
 #include "hw/virtio/virtio.h"
 #include "hw/virtio/virtio-bus.h"
 #include "hw/virtio/virtio-mem.h"
 #include "qapi/error.h"
 #include "qapi/visitor.h"
-#include "exec/ram_addr.h"
+#include "system/ram_addr.h"
 #include "migration/misc.h"
 #include "hw/boards.h"
 #include "hw/qdev-properties.h"
-#include CONFIG_DEVICES
+#include "hw/acpi/acpi.h"
 #include "trace.h"
 
 static const VMStateDescription vmstate_virtio_mem_device_early;
@@ -61,6 +61,8 @@ static uint32_t virtio_mem_default_thp_size(void)
     } else if (qemu_real_host_page_size() == 64 * KiB) {
         default_thp_size = 512 * MiB;
     }
+#elif defined(__s390x__)
+    default_thp_size = 1 * MiB;
 #endif
 
     return default_thp_size;
@@ -88,6 +90,7 @@ static uint32_t virtio_mem_default_thp_size(void)
 static uint32_t thp_size;
 
 #define HPAGE_PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size"
+#define HPAGE_PATH "/sys/kernel/mm/transparent_hugepage/"
 static uint32_t virtio_mem_thp_size(void)
 {
     gchar *content = NULL;
@@ -98,6 +101,12 @@ static uint32_t virtio_mem_thp_size(void)
         return thp_size;
     }
 
+    /* No THP -> no restrictions. */
+    if (!g_file_test(HPAGE_PATH, G_FILE_TEST_EXISTS)) {
+        thp_size = VIRTIO_MEM_MIN_BLOCK_SIZE;
+        return thp_size;
+    }
+
     /*
      * Try to probe the actual THP size, fallback to (sane but eventually
      * incorrect) default sizes.
@@ -161,7 +170,7 @@ static bool virtio_mem_has_shared_zeropage(RAMBlock *rb)
  * necessary (as the section size can change). But it's more likely that the
  * section size will rather get smaller and not bigger over time.
  */
-#if defined(TARGET_X86_64) || defined(TARGET_I386)
+#if defined(TARGET_X86_64) || defined(TARGET_I386) || defined(TARGET_S390X)
 #define VIRTIO_MEM_USABLE_EXTENT (2 * (128 * MiB))
 #elif defined(TARGET_ARM)
 #define VIRTIO_MEM_USABLE_EXTENT (2 * (512 * MiB))
@@ -181,7 +190,7 @@ static bool virtio_mem_is_busy(void)
      * after plugging them) until we're running on the destination (as we didn't
      * migrate these blocks when they were unplugged).
      */
-    return migration_in_incoming_postcopy() || !migration_is_idle();
+    return migration_in_incoming_postcopy() || migration_is_running();
 }
 
 typedef int (*virtio_mem_range_cb)(VirtIOMEM *vmem, void *arg,
@@ -235,28 +244,6 @@ static int virtio_mem_for_each_plugged_range(VirtIOMEM *vmem, void *arg,
     return ret;
 }
 
-/*
- * Adjust the memory section to cover the intersection with the given range.
- *
- * Returns false if the intersection is empty, otherwise returns true.
- */
-static bool virtio_mem_intersect_memory_section(MemoryRegionSection *s,
-                                                uint64_t offset, uint64_t size)
-{
-    uint64_t start = MAX(s->offset_within_region, offset);
-    uint64_t end = MIN(s->offset_within_region + int128_get64(s->size),
-                       offset + size);
-
-    if (end <= start) {
-        return false;
-    }
-
-    s->offset_within_address_space += start - s->offset_within_region;
-    s->offset_within_region = start;
-    s->size = int128_make64(end - start);
-    return true;
-}
-
 typedef int (*virtio_mem_section_cb)(MemoryRegionSection *s, void *arg);
 
 static int virtio_mem_for_each_plugged_section(const VirtIOMEM *vmem,
@@ -278,7 +265,7 @@ static int virtio_mem_for_each_plugged_section(const VirtIOMEM *vmem,
                                       first_bit + 1) - 1;
         size = (last_bit - first_bit + 1) * vmem->block_size;
 
-        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!memory_region_section_intersect_range(&tmp, offset, size)) {
             break;
         }
         ret = cb(&tmp, arg);
@@ -310,7 +297,7 @@ static int virtio_mem_for_each_unplugged_section(const VirtIOMEM *vmem,
                                  first_bit + 1) - 1;
         size = (last_bit - first_bit + 1) * vmem->block_size;
 
-        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!memory_region_section_intersect_range(&tmp, offset, size)) {
             break;
         }
         ret = cb(&tmp, arg);
@@ -346,7 +333,7 @@ static void virtio_mem_notify_unplug(VirtIOMEM *vmem, uint64_t offset,
     QLIST_FOREACH(rdl, &vmem->rdl_list, next) {
         MemoryRegionSection tmp = *rdl->section;
 
-        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!memory_region_section_intersect_range(&tmp, offset, size)) {
             continue;
         }
         rdl->notify_discard(rdl, &tmp);
@@ -362,7 +349,7 @@ static int virtio_mem_notify_plug(VirtIOMEM *vmem, uint64_t offset,
     QLIST_FOREACH(rdl, &vmem->rdl_list, next) {
         MemoryRegionSection tmp = *rdl->section;
 
-        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!memory_region_section_intersect_range(&tmp, offset, size)) {
             continue;
         }
         ret = rdl->notify_populate(rdl, &tmp);
@@ -379,7 +366,7 @@ static int virtio_mem_notify_plug(VirtIOMEM *vmem, uint64_t offset,
             if (rdl2 == rdl) {
                 break;
             }
-            if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
+            if (!memory_region_section_intersect_range(&tmp, offset, size)) {
                 continue;
             }
             rdl2->notify_discard(rdl2, &tmp);
@@ -874,15 +861,16 @@ static uint64_t virtio_mem_get_features(VirtIODevice *vdev, uint64_t features,
     MachineState *ms = MACHINE(qdev_get_machine());
     VirtIOMEM *vmem = VIRTIO_MEM(vdev);
 
-    if (ms->numa_state) {
-#if defined(CONFIG_ACPI)
+    if (ms->numa_state && acpi_builtin()) {
         virtio_add_feature(&features, VIRTIO_MEM_F_ACPI_PXM);
-#endif
     }
     assert(vmem->unplugged_inaccessible != ON_OFF_AUTO_AUTO);
     if (vmem->unplugged_inaccessible == ON_OFF_AUTO_ON) {
         virtio_add_feature(&features, VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE);
     }
+    if (qemu_wakeup_suspend_enabled()) {
+        virtio_add_feature(&features, VIRTIO_MEM_F_PERSISTENT_SUSPEND);
+    }
     return features;
 }
 
@@ -895,18 +883,6 @@ static int virtio_mem_validate_features(VirtIODevice *vdev)
     return 0;
 }
 
-static void virtio_mem_system_reset(void *opaque)
-{
-    VirtIOMEM *vmem = VIRTIO_MEM(opaque);
-
-    /*
-     * During usual resets, we will unplug all memory and shrink the usable
-     * region size. This is, however, not possible in all scenarios. Then,
-     * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL).
-     */
-    virtio_mem_unplug_all(vmem);
-}
-
 static void virtio_mem_prepare_mr(VirtIOMEM *vmem)
 {
     const uint64_t region_size = memory_region_size(&vmem->memdev->mr);
@@ -958,6 +934,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
     VirtIOMEM *vmem = VIRTIO_MEM(dev);
     uint64_t page_size;
     RAMBlock *rb;
+    Object *obj;
     int ret;
 
     if (!vmem->memdev) {
@@ -990,7 +967,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
         return;
     }
 
-    if (enable_mlock) {
+    if (should_mlock(mlock_state)) {
         error_setg(errp, "Incompatible with mlock");
         return;
     }
@@ -1071,6 +1048,17 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
     }
 
     /*
+     * Set ourselves as RamDiscardManager before the plug handler maps the
+     * memory region and exposes it via an address space.
+     */
+    if (memory_region_set_ram_discard_manager(&vmem->memdev->mr,
+                                              RAM_DISCARD_MANAGER(vmem))) {
+        error_setg(errp, "Failed to set RamDiscardManager");
+        ram_block_coordinated_discard_require(false);
+        return;
+    }
+
+    /*
      * We don't know at this point whether shared RAM is migrated using
      * QEMU or migrated using the file content. "x-ignore-shared" will be
      * configured after realizing the device. So in case we have an
@@ -1084,6 +1072,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
         ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb));
         if (ret) {
             error_setg_errno(errp, -ret, "Unexpected error discarding RAM");
+            memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL);
             ram_block_coordinated_discard_require(false);
             return;
         }
@@ -1123,14 +1112,28 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
         vmstate_register_any(VMSTATE_IF(vmem),
                              &vmstate_virtio_mem_device_early, vmem);
     }
-    qemu_register_reset(virtio_mem_system_reset, vmem);
 
     /*
-     * Set ourselves as RamDiscardManager before the plug handler maps the
-     * memory region and exposes it via an address space.
+     * We only want to unplug all memory to start with a clean slate when
+     * it is safe for the guest -- during system resets that call
+     * qemu_devices_reset().
+     *
+     * We'll filter out selected qemu_devices_reset() calls used for other
+     * purposes, like resetting all devices during wakeup from suspend on
+     * x86 based on the reset type passed to qemu_devices_reset().
+     *
+     * Unplugging all memory during simple device resets can result in the VM
+     * unexpectedly losing RAM, corrupting VM state.
+     *
+     * Simple device resets (or resets triggered by getting a parent device
+     * reset) must not change the state of plugged memory blocks. Therefore,
+     * we need a dedicated reset object that only gets called during
+     * qemu_devices_reset().
      */
-    memory_region_set_ram_discard_manager(&vmem->memdev->mr,
-                                          RAM_DISCARD_MANAGER(vmem));
+    obj = object_new(TYPE_VIRTIO_MEM_SYSTEM_RESET);
+    vmem->system_reset = VIRTIO_MEM_SYSTEM_RESET(obj);
+    vmem->system_reset->vmem = vmem;
+    qemu_register_resettable(obj);
 }
 
 static void virtio_mem_device_unrealize(DeviceState *dev)
@@ -1138,12 +1141,9 @@ static void virtio_mem_device_unrealize(DeviceState *dev)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOMEM *vmem = VIRTIO_MEM(dev);
 
-    /*
-     * The unplug handler unmapped the memory region, it cannot be
-     * found via an address space anymore. Unset ourselves.
-     */
-    memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL);
-    qemu_unregister_reset(virtio_mem_system_reset, vmem);
+    qemu_unregister_resettable(OBJECT(vmem->system_reset));
+    object_unref(OBJECT(vmem->system_reset));
+
     if (vmem->early_migration) {
         vmstate_unregister(VMSTATE_IF(vmem), &vmstate_virtio_mem_device_early,
                            vmem);
@@ -1153,6 +1153,11 @@ static void virtio_mem_device_unrealize(DeviceState *dev)
     virtio_del_queue(vdev, 0);
     virtio_cleanup(vdev);
     g_free(vmem->bitmap);
+    /*
+     * The unplug handler unmapped the memory region, it cannot be
+     * found via an address space anymore. Unset ourselves.
+     */
+    memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL);
     ram_block_coordinated_discard_require(false);
 }
 
@@ -1682,7 +1687,7 @@ static void virtio_mem_instance_finalize(Object *obj)
     vmem->mr = NULL;
 }
 
-static Property virtio_mem_properties[] = {
+static const Property virtio_mem_properties[] = {
     DEFINE_PROP_UINT64(VIRTIO_MEM_ADDR_PROP, VirtIOMEM, addr, 0),
     DEFINE_PROP_UINT32(VIRTIO_MEM_NODE_PROP, VirtIOMEM, node, 0),
     DEFINE_PROP_BOOL(VIRTIO_MEM_PREALLOC_PROP, VirtIOMEM, prealloc, false),
@@ -1696,7 +1701,6 @@ static Property virtio_mem_properties[] = {
                      early_migration, true),
     DEFINE_PROP_BOOL(VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, VirtIOMEM,
                      dynamic_memslots, false),
-    DEFINE_PROP_END_OF_LIST(),
 };
 
 static uint64_t virtio_mem_rdm_get_min_granularity(const RamDiscardManager *rdm,
@@ -1728,7 +1732,7 @@ static bool virtio_mem_rdm_is_populated(const RamDiscardManager *rdm,
 }
 
 struct VirtIOMEMReplayData {
-    void *fn;
+    ReplayRamDiscardState fn;
     void *opaque;
 };
 
@@ -1736,12 +1740,12 @@ static int virtio_mem_rdm_replay_populated_cb(MemoryRegionSection *s, void *arg)
 {
     struct VirtIOMEMReplayData *data = arg;
 
-    return ((ReplayRamPopulate)data->fn)(s, data->opaque);
+    return data->fn(s, data->opaque);
 }
 
 static int virtio_mem_rdm_replay_populated(const RamDiscardManager *rdm,
                                            MemoryRegionSection *s,
-                                           ReplayRamPopulate replay_fn,
+                                           ReplayRamDiscardState replay_fn,
                                            void *opaque)
 {
     const VirtIOMEM *vmem = VIRTIO_MEM(rdm);
@@ -1760,14 +1764,13 @@ static int virtio_mem_rdm_replay_discarded_cb(MemoryRegionSection *s,
 {
     struct VirtIOMEMReplayData *data = arg;
 
-    ((ReplayRamDiscard)data->fn)(s, data->opaque);
-    return 0;
+    return data->fn(s, data->opaque);
 }
 
-static void virtio_mem_rdm_replay_discarded(const RamDiscardManager *rdm,
-                                            MemoryRegionSection *s,
-                                            ReplayRamDiscard replay_fn,
-                                            void *opaque)
+static int virtio_mem_rdm_replay_discarded(const RamDiscardManager *rdm,
+                                           MemoryRegionSection *s,
+                                           ReplayRamDiscardState replay_fn,
+                                           void *opaque)
 {
     const VirtIOMEM *vmem = VIRTIO_MEM(rdm);
     struct VirtIOMEMReplayData data = {
@@ -1776,8 +1779,8 @@ static void virtio_mem_rdm_replay_discarded(const RamDiscardManager *rdm,
     };
 
     g_assert(s->mr == &vmem->memdev->mr);
-    virtio_mem_for_each_unplugged_section(vmem, s, &data,
-                                          virtio_mem_rdm_replay_discarded_cb);
+    return virtio_mem_for_each_unplugged_section(vmem, s, &data,
+                                                 virtio_mem_rdm_replay_discarded_cb);
 }
 
 static void virtio_mem_rdm_register_listener(RamDiscardManager *rdm,
@@ -1843,7 +1846,7 @@ static void virtio_mem_unplug_request_check(VirtIOMEM *vmem, Error **errp)
     }
 }
 
-static void virtio_mem_class_init(ObjectClass *klass, void *data)
+static void virtio_mem_class_init(ObjectClass *klass, const void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
@@ -1885,7 +1888,7 @@ static const TypeInfo virtio_mem_info = {
     .instance_finalize = virtio_mem_instance_finalize,
     .class_init = virtio_mem_class_init,
     .class_size = sizeof(VirtIOMEMClass),
-    .interfaces = (InterfaceInfo[]) {
+    .interfaces = (const InterfaceInfo[]) {
         { TYPE_RAM_DISCARD_MANAGER },
         { }
     },
@@ -1897,3 +1900,49 @@ static void virtio_register_types(void)
 }
 
 type_init(virtio_register_types)
+
+OBJECT_DEFINE_SIMPLE_TYPE_WITH_INTERFACES(VirtioMemSystemReset, virtio_mem_system_reset, VIRTIO_MEM_SYSTEM_RESET, OBJECT, { TYPE_RESETTABLE_INTERFACE }, { })
+
+static void virtio_mem_system_reset_init(Object *obj)
+{
+}
+
+static void virtio_mem_system_reset_finalize(Object *obj)
+{
+}
+
+static ResettableState *virtio_mem_system_reset_get_state(Object *obj)
+{
+    VirtioMemSystemReset *vmem_reset = VIRTIO_MEM_SYSTEM_RESET(obj);
+
+    return &vmem_reset->reset_state;
+}
+
+static void virtio_mem_system_reset_hold(Object *obj, ResetType type)
+{
+    VirtioMemSystemReset *vmem_reset = VIRTIO_MEM_SYSTEM_RESET(obj);
+    VirtIOMEM *vmem = vmem_reset->vmem;
+
+    /*
+     * When waking up from standby/suspend-to-ram, do not unplug any memory.
+     */
+    if (type == RESET_TYPE_WAKEUP) {
+        return;
+    }
+
+    /*
+     * During usual resets, we will unplug all memory and shrink the usable
+     * region size. This is, however, not possible in all scenarios. Then,
+     * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL).
+     */
+    virtio_mem_unplug_all(vmem);
+}
+
+static void virtio_mem_system_reset_class_init(ObjectClass *klass,
+                                               const void *data)
+{
+    ResettableClass *rc = RESETTABLE_CLASS(klass);
+
+    rc->get_state = virtio_mem_system_reset_get_state;
+    rc->phases.hold = virtio_mem_system_reset_hold;
+}