From f2abba0e6f1d885e67b5c90a328666ab852a0788 Mon Sep 17 00:00:00 2001 From: Juan Quintela Date: Tue, 28 Jul 2015 15:46:48 +0200 Subject: [PATCH 03/28] migration: move savevm.c inside migration/ Message-id: <1438098431-30847-4-git-send-email-quintela@redhat.com> Patchwork-id: 67173 O-Subject: [RHEL-7 qemu-kvm PATCH 03/26] migration: move savevm.c inside migration/ Bugzilla: 580006 RH-Acked-by: Alex Williamson RH-Acked-by: Amit Shah RH-Acked-by: Dr. David Alan Gilbert Now, everything is in place. Signed-off-by: Juan Quintela Reviewed-by: Eric Blake (cherry picked from commit c3049a56d69f1ee7e85b5100ba5d0e3dc69a14f1) Signed-off-by: Miroslav Rezanina Conflicts: Makefile.target trace-events virtio-gpu traces Signed-off-by: Juan Quintela --- MAINTAINERS | 1 - Makefile.target | 4 +- migration/savevm.c | 1523 ++++++++++++++++++++++++++++++++++++++++++++++++++++ savevm.c | 1523 ---------------------------------------------------- trace-events | 2 +- 5 files changed, 1526 insertions(+), 1527 deletions(-) create mode 100644 migration/savevm.c delete mode 100644 savevm.c diff --git a/MAINTAINERS b/MAINTAINERS index ec1d6af..806bad5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -984,7 +984,6 @@ M: Amit Shah S: Maintained F: include/migration/ F: migration/ -F: savevm.c F: scripts/vmstate-static-checker.py F: tests/vmstate-static-checker-data/ diff --git a/Makefile.target b/Makefile.target index 729ac57..ab83aff 100644 --- a/Makefile.target +++ b/Makefile.target @@ -131,10 +131,10 @@ obj-y += qtest.o bootdevice.o obj-y += hw/ obj-$(CONFIG_FDT) += device_tree.o obj-$(CONFIG_KVM) += kvm-all.o -obj-y += memory.o savevm.o cputlb.o +obj-y += memory.o cputlb.o obj-y += memory_mapping.o obj-y += dump.o -obj-y += migration/ram.o +obj-y += migration/ram.o migration/savevm.o LIBS+=$(libs_softmmu) # xen support diff --git a/migration/savevm.c b/migration/savevm.c new file mode 100644 index 0000000..416bd3e --- /dev/null +++ b/migration/savevm.c @@ -0,0 +1,1523 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "config-host.h" +#include "qemu-common.h" +#include "hw/boards.h" +#include "hw/hw.h" +#include "hw/qdev.h" +#include "net/net.h" +#include "monitor/monitor.h" +#include "sysemu/sysemu.h" +#include "qemu/timer.h" +#include "audio/audio.h" +#include "migration/migration.h" +#include "qemu/sockets.h" +#include "qemu/queue.h" +#include "qemu/rcu_queue.h" +#include "sysemu/cpus.h" +#include "exec/memory.h" +#include "qmp-commands.h" +#include "trace.h" +#include "qemu/iov.h" +#include "block/snapshot.h" +#include "block/qapi.h" + + +#ifndef ETH_P_RARP +#define ETH_P_RARP 0x8035 +#endif +#define ARP_HTYPE_ETH 0x0001 +#define ARP_PTYPE_IP 0x0800 +#define ARP_OP_REQUEST_REV 0x3 + +bool shadow_bios_after_incoming; + +static int announce_self_create(uint8_t *buf, + uint8_t *mac_addr) +{ + /* Ethernet header. */ + memset(buf, 0xff, 6); /* destination MAC addr */ + memcpy(buf + 6, mac_addr, 6); /* source MAC addr */ + *(uint16_t *)(buf + 12) = htons(ETH_P_RARP); /* ethertype */ + + /* RARP header. */ + *(uint16_t *)(buf + 14) = htons(ARP_HTYPE_ETH); /* hardware addr space */ + *(uint16_t *)(buf + 16) = htons(ARP_PTYPE_IP); /* protocol addr space */ + *(buf + 18) = 6; /* hardware addr length (ethernet) */ + *(buf + 19) = 4; /* protocol addr length (IPv4) */ + *(uint16_t *)(buf + 20) = htons(ARP_OP_REQUEST_REV); /* opcode */ + memcpy(buf + 22, mac_addr, 6); /* source hw addr */ + memset(buf + 28, 0x00, 4); /* source protocol addr */ + memcpy(buf + 32, mac_addr, 6); /* target hw addr */ + memset(buf + 38, 0x00, 4); /* target protocol addr */ + + /* Padding to get up to 60 bytes (ethernet min packet size, minus FCS). */ + memset(buf + 42, 0x00, 18); + + return 60; /* len (FCS will be added by hardware) */ +} + +static void qemu_announce_self_iter(NICState *nic, void *opaque) +{ + uint8_t buf[60]; + int len; + + trace_qemu_announce_self_iter(qemu_ether_ntoa(&nic->conf->macaddr)); + len = announce_self_create(buf, nic->conf->macaddr.a); + + qemu_send_packet_raw(qemu_get_queue(nic), buf, len); +} + + +static void qemu_announce_self_once(void *opaque) +{ + static int count = SELF_ANNOUNCE_ROUNDS; + QEMUTimer *timer = *(QEMUTimer **)opaque; + + qemu_foreach_nic(qemu_announce_self_iter, NULL); + + if (--count) { + /* delay 50ms, 150ms, 250ms, ... */ + timer_mod(timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + + self_announce_delay(count)); + } else { + timer_del(timer); + timer_free(timer); + } +} + +void qemu_announce_self(void) +{ + static QEMUTimer *timer; + timer = timer_new_ms(QEMU_CLOCK_REALTIME, qemu_announce_self_once, &timer); + qemu_announce_self_once(&timer); +} + +/***********************************************************/ +/* savevm/loadvm support */ + +static ssize_t block_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) +{ + int ret; + QEMUIOVector qiov; + + qemu_iovec_init_external(&qiov, iov, iovcnt); + ret = bdrv_writev_vmstate(opaque, &qiov, pos); + if (ret < 0) { + return ret; + } + + return qiov.size; +} + +static int block_put_buffer(void *opaque, const uint8_t *buf, + int64_t pos, int size) +{ + bdrv_save_vmstate(opaque, buf, pos, size); + return size; +} + +static int block_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size) +{ + return bdrv_load_vmstate(opaque, buf, pos, size); +} + +static int bdrv_fclose(void *opaque) +{ + return bdrv_flush(opaque); +} + +static const QEMUFileOps bdrv_read_ops = { + .get_buffer = block_get_buffer, + .close = bdrv_fclose +}; + +static const QEMUFileOps bdrv_write_ops = { + .put_buffer = block_put_buffer, + .writev_buffer = block_writev_buffer, + .close = bdrv_fclose +}; + +static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable) +{ + if (is_writable) { + return qemu_fopen_ops(bs, &bdrv_write_ops); + } + return qemu_fopen_ops(bs, &bdrv_read_ops); +} + + +/* QEMUFile timer support. + * Not in qemu-file.c to not add qemu-timer.c as dependency to qemu-file.c + */ + +void timer_put(QEMUFile *f, QEMUTimer *ts) +{ + uint64_t expire_time; + + expire_time = timer_expire_time_ns(ts); + qemu_put_be64(f, expire_time); +} + +void timer_get(QEMUFile *f, QEMUTimer *ts) +{ + uint64_t expire_time; + + expire_time = qemu_get_be64(f); + if (expire_time != -1) { + timer_mod_ns(ts, expire_time); + } else { + timer_del(ts); + } +} + + +/* VMState timer support. + * Not in vmstate.c to not add qemu-timer.c as dependency to vmstate.c + */ + +static int get_timer(QEMUFile *f, void *pv, size_t size) +{ + QEMUTimer *v = pv; + timer_get(f, v); + return 0; +} + +static void put_timer(QEMUFile *f, void *pv, size_t size) +{ + QEMUTimer *v = pv; + timer_put(f, v); +} + +const VMStateInfo vmstate_info_timer = { + .name = "timer", + .get = get_timer, + .put = put_timer, +}; + + +typedef struct CompatEntry { + char idstr[256]; + int instance_id; +} CompatEntry; + +typedef struct SaveStateEntry { + QTAILQ_ENTRY(SaveStateEntry) entry; + char idstr[256]; + int instance_id; + int alias_id; + int version_id; + int section_id; + SaveVMHandlers *ops; + const VMStateDescription *vmsd; + void *opaque; + CompatEntry *compat; + int is_ram; +} SaveStateEntry; + + +static QTAILQ_HEAD(savevm_handlers, SaveStateEntry) savevm_handlers = + QTAILQ_HEAD_INITIALIZER(savevm_handlers); +static int global_section_id; + +static void dump_vmstate_vmsd(FILE *out_file, + const VMStateDescription *vmsd, int indent, + bool is_subsection); + +static void dump_vmstate_vmsf(FILE *out_file, const VMStateField *field, + int indent) +{ + fprintf(out_file, "%*s{\n", indent, ""); + indent += 2; + fprintf(out_file, "%*s\"field\": \"%s\",\n", indent, "", field->name); + fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", + field->version_id); + fprintf(out_file, "%*s\"field_exists\": %s,\n", indent, "", + field->field_exists ? "true" : "false"); + fprintf(out_file, "%*s\"size\": %zu", indent, "", field->size); + if (field->vmsd != NULL) { + fprintf(out_file, ",\n"); + dump_vmstate_vmsd(out_file, field->vmsd, indent, false); + } + fprintf(out_file, "\n%*s}", indent - 2, ""); +} + +static void dump_vmstate_vmss(FILE *out_file, + const VMStateSubsection *subsection, + int indent) +{ + if (subsection->vmsd != NULL) { + dump_vmstate_vmsd(out_file, subsection->vmsd, indent, true); + } +} + +static void dump_vmstate_vmsd(FILE *out_file, + const VMStateDescription *vmsd, int indent, + bool is_subsection) +{ + if (is_subsection) { + fprintf(out_file, "%*s{\n", indent, ""); + } else { + fprintf(out_file, "%*s\"%s\": {\n", indent, "", "Description"); + } + indent += 2; + fprintf(out_file, "%*s\"name\": \"%s\",\n", indent, "", vmsd->name); + fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", + vmsd->version_id); + fprintf(out_file, "%*s\"minimum_version_id\": %d", indent, "", + vmsd->minimum_version_id); + if (vmsd->fields != NULL) { + const VMStateField *field = vmsd->fields; + bool first; + + fprintf(out_file, ",\n%*s\"Fields\": [\n", indent, ""); + first = true; + while (field->name != NULL) { + if (field->flags & VMS_MUST_EXIST) { + /* Ignore VMSTATE_VALIDATE bits; these don't get migrated */ + field++; + continue; + } + if (!first) { + fprintf(out_file, ",\n"); + } + dump_vmstate_vmsf(out_file, field, indent + 2); + field++; + first = false; + } + fprintf(out_file, "\n%*s]", indent, ""); + } + if (vmsd->subsections != NULL) { + const VMStateSubsection *subsection = vmsd->subsections; + bool first; + + fprintf(out_file, ",\n%*s\"Subsections\": [\n", indent, ""); + first = true; + while (subsection->vmsd != NULL) { + if (!first) { + fprintf(out_file, ",\n"); + } + dump_vmstate_vmss(out_file, subsection, indent + 2); + subsection++; + first = false; + } + fprintf(out_file, "\n%*s]", indent, ""); + } + fprintf(out_file, "\n%*s}", indent - 2, ""); +} + +static void dump_machine_type(FILE *out_file) +{ + MachineClass *mc; + + mc = MACHINE_GET_CLASS(current_machine); + + fprintf(out_file, " \"vmschkmachine\": {\n"); + fprintf(out_file, " \"Name\": \"%s\"\n", mc->name); + fprintf(out_file, " },\n"); +} + +void dump_vmstate_json_to_file(FILE *out_file) +{ + GSList *list, *elt; + bool first; + + fprintf(out_file, "{\n"); + dump_machine_type(out_file); + + first = true; + list = object_class_get_list(TYPE_DEVICE, true); + for (elt = list; elt; elt = elt->next) { + DeviceClass *dc = OBJECT_CLASS_CHECK(DeviceClass, elt->data, + TYPE_DEVICE); + const char *name; + int indent = 2; + + if (!dc->vmsd) { + continue; + } + + if (!first) { + fprintf(out_file, ",\n"); + } + name = object_class_get_name(OBJECT_CLASS(dc)); + fprintf(out_file, "%*s\"%s\": {\n", indent, "", name); + indent += 2; + fprintf(out_file, "%*s\"Name\": \"%s\",\n", indent, "", name); + fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", + dc->vmsd->version_id); + fprintf(out_file, "%*s\"minimum_version_id\": %d,\n", indent, "", + dc->vmsd->minimum_version_id); + + dump_vmstate_vmsd(out_file, dc->vmsd, indent, false); + + fprintf(out_file, "\n%*s}", indent - 2, ""); + first = false; + } + fprintf(out_file, "\n}\n"); + fclose(out_file); +} + +static int calculate_new_instance_id(const char *idstr) +{ + SaveStateEntry *se; + int instance_id = 0; + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (strcmp(idstr, se->idstr) == 0 + && instance_id <= se->instance_id) { + instance_id = se->instance_id + 1; + } + } + return instance_id; +} + +static int calculate_compat_instance_id(const char *idstr) +{ + SaveStateEntry *se; + int instance_id = 0; + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (!se->compat) { + continue; + } + + if (strcmp(idstr, se->compat->idstr) == 0 + && instance_id <= se->compat->instance_id) { + instance_id = se->compat->instance_id + 1; + } + } + return instance_id; +} + +/* TODO: Individual devices generally have very little idea about the rest + of the system, so instance_id should be removed/replaced. + Meanwhile pass -1 as instance_id if you do not already have a clearly + distinguishing id for all instances of your device class. */ +int register_savevm_live(DeviceState *dev, + const char *idstr, + int instance_id, + int version_id, + SaveVMHandlers *ops, + void *opaque) +{ + SaveStateEntry *se; + + se = g_malloc0(sizeof(SaveStateEntry)); + se->version_id = version_id; + se->section_id = global_section_id++; + se->ops = ops; + se->opaque = opaque; + se->vmsd = NULL; + /* if this is a live_savem then set is_ram */ + if (ops->save_live_setup != NULL) { + se->is_ram = 1; + } + + if (dev) { + char *id = qdev_get_dev_path(dev); + if (id) { + pstrcpy(se->idstr, sizeof(se->idstr), id); + pstrcat(se->idstr, sizeof(se->idstr), "/"); + g_free(id); + + se->compat = g_malloc0(sizeof(CompatEntry)); + pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), idstr); + se->compat->instance_id = instance_id == -1 ? + calculate_compat_instance_id(idstr) : instance_id; + instance_id = -1; + } + } + pstrcat(se->idstr, sizeof(se->idstr), idstr); + + if (instance_id == -1) { + se->instance_id = calculate_new_instance_id(se->idstr); + } else { + se->instance_id = instance_id; + } + assert(!se->compat || se->instance_id == 0); + /* add at the end of list */ + QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry); + return 0; +} + +int register_savevm(DeviceState *dev, + const char *idstr, + int instance_id, + int version_id, + SaveStateHandler *save_state, + LoadStateHandler *load_state, + void *opaque) +{ + SaveVMHandlers *ops = g_malloc0(sizeof(SaveVMHandlers)); + ops->save_state = save_state; + ops->load_state = load_state; + return register_savevm_live(dev, idstr, instance_id, version_id, + ops, opaque); +} + +void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque) +{ + SaveStateEntry *se, *new_se; + char id[256] = ""; + + if (dev) { + char *path = qdev_get_dev_path(dev); + if (path) { + pstrcpy(id, sizeof(id), path); + pstrcat(id, sizeof(id), "/"); + g_free(path); + } + } + pstrcat(id, sizeof(id), idstr); + + QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) { + if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) { + QTAILQ_REMOVE(&savevm_handlers, se, entry); + if (se->compat) { + g_free(se->compat); + } + g_free(se->ops); + g_free(se); + } + } +} + +int vmstate_register_with_alias_id(DeviceState *dev, int instance_id, + const VMStateDescription *vmsd, + void *opaque, int alias_id, + int required_for_version) +{ + SaveStateEntry *se; + + /* If this triggers, alias support can be dropped for the vmsd. */ + assert(alias_id == -1 || required_for_version >= vmsd->minimum_version_id); + + se = g_malloc0(sizeof(SaveStateEntry)); + se->version_id = vmsd->version_id; + se->section_id = global_section_id++; + se->opaque = opaque; + se->vmsd = vmsd; + se->alias_id = alias_id; + + if (dev) { + char *id = qdev_get_dev_path(dev); + if (id) { + pstrcpy(se->idstr, sizeof(se->idstr), id); + pstrcat(se->idstr, sizeof(se->idstr), "/"); + g_free(id); + + se->compat = g_malloc0(sizeof(CompatEntry)); + pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), vmsd->name); + se->compat->instance_id = instance_id == -1 ? + calculate_compat_instance_id(vmsd->name) : instance_id; + instance_id = -1; + } + } + pstrcat(se->idstr, sizeof(se->idstr), vmsd->name); + + if (instance_id == -1) { + se->instance_id = calculate_new_instance_id(se->idstr); + } else { + se->instance_id = instance_id; + } + assert(!se->compat || se->instance_id == 0); + /* add at the end of list */ + QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry); + return 0; +} + +void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd, + void *opaque) +{ + SaveStateEntry *se, *new_se; + + QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) { + if (se->vmsd == vmsd && se->opaque == opaque) { + QTAILQ_REMOVE(&savevm_handlers, se, entry); + if (se->compat) { + g_free(se->compat); + } + g_free(se); + } + } +} + +static int vmstate_load(QEMUFile *f, SaveStateEntry *se, int version_id) +{ + trace_vmstate_load(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); + if (!se->vmsd) { /* Old style */ + return se->ops->load_state(f, se->opaque, version_id); + } + return vmstate_load_state(f, se->vmsd, se->opaque, version_id); +} + +static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se, QJSON *vmdesc) +{ + int64_t old_offset, size; + + old_offset = qemu_ftell_fast(f); + se->ops->save_state(f, se->opaque); + size = qemu_ftell_fast(f) - old_offset; + + if (vmdesc) { + json_prop_int(vmdesc, "size", size); + json_start_array(vmdesc, "fields"); + json_start_object(vmdesc, NULL); + json_prop_str(vmdesc, "name", "data"); + json_prop_int(vmdesc, "size", size); + json_prop_str(vmdesc, "type", "buffer"); + json_end_object(vmdesc); + json_end_array(vmdesc); + } +} + +static void vmstate_save(QEMUFile *f, SaveStateEntry *se, QJSON *vmdesc) +{ + trace_vmstate_save(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); + if (!se->vmsd) { + vmstate_save_old_style(f, se, vmdesc); + return; + } + vmstate_save_state(f, se->vmsd, se->opaque, vmdesc); +} + +bool qemu_savevm_state_blocked(Error **errp) +{ + SaveStateEntry *se; + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (se->vmsd && se->vmsd->unmigratable) { + error_setg(errp, "State blocked by non-migratable device '%s'", + se->idstr); + return true; + } + } + return false; +} + +void qemu_savevm_state_begin(QEMUFile *f, + const MigrationParams *params) +{ + SaveStateEntry *se; + int ret; + + trace_savevm_state_begin(); + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (!se->ops || !se->ops->set_params) { + continue; + } + se->ops->set_params(params, se->opaque); + } + + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); + qemu_put_be32(f, QEMU_VM_FILE_VERSION); + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + int len; + + if (!se->ops || !se->ops->save_live_setup) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_START); + qemu_put_be32(f, se->section_id); + + /* ID string */ + len = strlen(se->idstr); + qemu_put_byte(f, len); + qemu_put_buffer(f, (uint8_t *)se->idstr, len); + + qemu_put_be32(f, se->instance_id); + qemu_put_be32(f, se->version_id); + + ret = se->ops->save_live_setup(f, se->opaque); + if (ret < 0) { + qemu_file_set_error(f, ret); + break; + } + } +} + +/* + * this function has three return values: + * negative: there was one error, and we have -errno. + * 0 : We haven't finished, caller have to go again + * 1 : We have finished, we can go to complete phase + */ +int qemu_savevm_state_iterate(QEMUFile *f) +{ + SaveStateEntry *se; + int ret = 1; + + trace_savevm_state_iterate(); + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (!se->ops || !se->ops->save_live_iterate) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + if (qemu_file_rate_limit(f)) { + return 0; + } + trace_savevm_section_start(se->idstr, se->section_id); + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_PART); + qemu_put_be32(f, se->section_id); + + ret = se->ops->save_live_iterate(f, se->opaque); + trace_savevm_section_end(se->idstr, se->section_id, ret); + + if (ret < 0) { + qemu_file_set_error(f, ret); + } + if (ret <= 0) { + /* Do not proceed to the next vmstate before this one reported + completion of the current stage. This serializes the migration + and reduces the probability that a faster changing state is + synchronized over and over again. */ + break; + } + } + return ret; +} + +static bool should_send_vmdesc(void) +{ + MachineState *machine = MACHINE(qdev_get_machine()); + return !machine->suppress_vmdesc; +} + +void qemu_savevm_state_complete(QEMUFile *f) +{ + QJSON *vmdesc; + int vmdesc_len; + SaveStateEntry *se; + int ret; + + trace_savevm_state_complete(); + + cpu_synchronize_all_states(); + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (!se->ops || !se->ops->save_live_complete) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + trace_savevm_section_start(se->idstr, se->section_id); + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_END); + qemu_put_be32(f, se->section_id); + + ret = se->ops->save_live_complete(f, se->opaque); + trace_savevm_section_end(se->idstr, se->section_id, ret); + if (ret < 0) { + qemu_file_set_error(f, ret); + return; + } + } + + vmdesc = qjson_new(); + json_prop_int(vmdesc, "page_size", TARGET_PAGE_SIZE); + json_start_array(vmdesc, "devices"); + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + int len; + + if ((!se->ops || !se->ops->save_state) && !se->vmsd) { + continue; + } + trace_savevm_section_start(se->idstr, se->section_id); + + json_start_object(vmdesc, NULL); + json_prop_str(vmdesc, "name", se->idstr); + json_prop_int(vmdesc, "instance_id", se->instance_id); + + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_FULL); + qemu_put_be32(f, se->section_id); + + /* ID string */ + len = strlen(se->idstr); + qemu_put_byte(f, len); + qemu_put_buffer(f, (uint8_t *)se->idstr, len); + + qemu_put_be32(f, se->instance_id); + qemu_put_be32(f, se->version_id); + + vmstate_save(f, se, vmdesc); + + json_end_object(vmdesc); + trace_savevm_section_end(se->idstr, se->section_id, 0); + } + + qemu_put_byte(f, QEMU_VM_EOF); + + json_end_array(vmdesc); + qjson_finish(vmdesc); + vmdesc_len = strlen(qjson_get_str(vmdesc)); + + if (should_send_vmdesc()) { + qemu_put_byte(f, QEMU_VM_VMDESCRIPTION); + qemu_put_be32(f, vmdesc_len); + qemu_put_buffer(f, (uint8_t *)qjson_get_str(vmdesc), vmdesc_len); + } + object_unref(OBJECT(vmdesc)); + + qemu_fflush(f); +} + +uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size) +{ + SaveStateEntry *se; + uint64_t ret = 0; + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (!se->ops || !se->ops->save_live_pending) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + ret += se->ops->save_live_pending(f, se->opaque, max_size); + } + return ret; +} + +void qemu_savevm_state_cancel(void) +{ + SaveStateEntry *se; + + trace_savevm_state_cancel(); + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (se->ops && se->ops->cancel) { + se->ops->cancel(se->opaque); + } + } +} + +static int qemu_savevm_state(QEMUFile *f, Error **errp) +{ + int ret; + MigrationParams params = { + .blk = 0, + .shared = 0 + }; + + if (qemu_savevm_state_blocked(errp)) { + return -EINVAL; + } + + qemu_mutex_unlock_iothread(); + qemu_savevm_state_begin(f, ¶ms); + qemu_mutex_lock_iothread(); + + while (qemu_file_get_error(f) == 0) { + if (qemu_savevm_state_iterate(f) > 0) { + break; + } + } + + ret = qemu_file_get_error(f); + if (ret == 0) { + qemu_savevm_state_complete(f); + ret = qemu_file_get_error(f); + } + if (ret != 0) { + qemu_savevm_state_cancel(); + error_setg_errno(errp, -ret, "Error while writing VM state"); + } + return ret; +} + +static int qemu_save_device_state(QEMUFile *f) +{ + SaveStateEntry *se; + + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); + qemu_put_be32(f, QEMU_VM_FILE_VERSION); + + cpu_synchronize_all_states(); + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + int len; + + if (se->is_ram) { + continue; + } + if ((!se->ops || !se->ops->save_state) && !se->vmsd) { + continue; + } + + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_FULL); + qemu_put_be32(f, se->section_id); + + /* ID string */ + len = strlen(se->idstr); + qemu_put_byte(f, len); + qemu_put_buffer(f, (uint8_t *)se->idstr, len); + + qemu_put_be32(f, se->instance_id); + qemu_put_be32(f, se->version_id); + + vmstate_save(f, se, NULL); + } + + qemu_put_byte(f, QEMU_VM_EOF); + + return qemu_file_get_error(f); +} + +static SaveStateEntry *find_se(const char *idstr, int instance_id) +{ + SaveStateEntry *se; + + QTAILQ_FOREACH(se, &savevm_handlers, entry) { + if (!strcmp(se->idstr, idstr) && + (instance_id == se->instance_id || + instance_id == se->alias_id)) + return se; + /* Migrating from an older version? */ + if (strstr(se->idstr, idstr) && se->compat) { + if (!strcmp(se->compat->idstr, idstr) && + (instance_id == se->compat->instance_id || + instance_id == se->alias_id)) + return se; + } + } + return NULL; +} + +typedef struct LoadStateEntry { + QLIST_ENTRY(LoadStateEntry) entry; + SaveStateEntry *se; + int section_id; + int version_id; +} LoadStateEntry; + +static void shadow_bios(void) +{ + RAMBlock *block, *ram, *oprom, *bios; + size_t one_meg, oprom_size, bios_size; + uint8_t *cd_seg_host, *ef_seg_host; + + ram = NULL; + oprom = NULL; + bios = NULL; + rcu_read_lock(); + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + if (strcmp("pc.ram", block->idstr) == 0) { + assert(ram == NULL); + ram = block; + } else if (strcmp("pc.rom", block->idstr) == 0) { + assert(oprom == NULL); + oprom = block; + } else if (strcmp("pc.bios", block->idstr) == 0) { + assert(bios == NULL); + bios = block; + } + } + assert(ram != NULL); + assert(oprom != NULL); + assert(bios != NULL); + assert(memory_region_is_ram(ram->mr)); + assert(memory_region_is_ram(oprom->mr)); + assert(memory_region_is_ram(bios->mr)); + assert(int128_eq(ram->mr->size, int128_make64(ram->used_length))); + assert(int128_eq(oprom->mr->size, int128_make64(oprom->used_length))); + assert(int128_eq(bios->mr->size, int128_make64(bios->used_length))); + + one_meg = 1024 * 1024; + oprom_size = 128 * 1024; + bios_size = 128 * 1024; + assert(ram->used_length >= one_meg); + assert(oprom->used_length == oprom_size); + assert(bios->used_length == bios_size); + + ef_seg_host = memory_region_get_ram_ptr(ram->mr) + (one_meg - bios_size); + cd_seg_host = ef_seg_host - oprom_size; + + /* This is a crude hack, but we must distinguish a rhel6.x.0 machtype guest + * coming in from a RHEL-6 emulator (where shadowing has had no effect on + * "pc.ram") from a similar guest coming in from a RHEL-7 emulator (where + * shadowing has worked). In the latter case we must not trample the live + * SeaBIOS variables in "pc.ram". + */ + if (buffer_is_zero(ef_seg_host, bios_size)) { + fprintf(stderr, "copying E and F segments from pc.bios to pc.ram\n"); + memcpy(ef_seg_host, memory_region_get_ram_ptr(bios->mr), bios_size); + } + if (buffer_is_zero(cd_seg_host, oprom_size)) { + fprintf(stderr, "copying C and D segments from pc.rom to pc.ram\n"); + memcpy(cd_seg_host, memory_region_get_ram_ptr(oprom->mr), oprom_size); + } + rcu_read_unlock(); +} + +int qemu_loadvm_state(QEMUFile *f) +{ + QLIST_HEAD(, LoadStateEntry) loadvm_handlers = + QLIST_HEAD_INITIALIZER(loadvm_handlers); + LoadStateEntry *le, *new_le; + Error *local_err = NULL; + uint8_t section_type; + unsigned int v; + int ret; + int file_error_after_eof = -1; + + if (qemu_savevm_state_blocked(&local_err)) { + error_report_err(local_err); + return -EINVAL; + } + + v = qemu_get_be32(f); + if (v != QEMU_VM_FILE_MAGIC) { + error_report("Not a migration stream"); + return -EINVAL; + } + + v = qemu_get_be32(f); + if (v == QEMU_VM_FILE_VERSION_COMPAT) { + error_report("SaveVM v2 format is obsolete and don't work anymore"); + return -ENOTSUP; + } + if (v != QEMU_VM_FILE_VERSION) { + error_report("Unsupported migration stream version"); + return -ENOTSUP; + } + + while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) { + uint32_t instance_id, version_id, section_id; + SaveStateEntry *se; + char idstr[257]; + int len; + + trace_qemu_loadvm_state_section(section_type); + switch (section_type) { + case QEMU_VM_SECTION_START: + case QEMU_VM_SECTION_FULL: + /* Read section start */ + section_id = qemu_get_be32(f); + len = qemu_get_byte(f); + qemu_get_buffer(f, (uint8_t *)idstr, len); + idstr[len] = 0; + instance_id = qemu_get_be32(f); + version_id = qemu_get_be32(f); + + trace_qemu_loadvm_state_section_startfull(section_id, idstr, + instance_id, version_id); + /* Find savevm section */ + se = find_se(idstr, instance_id); + if (se == NULL) { + error_report("Unknown savevm section or instance '%s' %d", + idstr, instance_id); + ret = -EINVAL; + goto out; + } + + /* Validate version */ + if (version_id > se->version_id) { + error_report("savevm: unsupported version %d for '%s' v%d", + version_id, idstr, se->version_id); + ret = -EINVAL; + goto out; + } + + /* Add entry */ + le = g_malloc0(sizeof(*le)); + + le->se = se; + le->section_id = section_id; + le->version_id = version_id; + QLIST_INSERT_HEAD(&loadvm_handlers, le, entry); + + ret = vmstate_load(f, le->se, le->version_id); + if (ret < 0) { + error_report("error while loading state for instance 0x%x of" + " device '%s'", instance_id, idstr); + goto out; + } + break; + case QEMU_VM_SECTION_PART: + case QEMU_VM_SECTION_END: + section_id = qemu_get_be32(f); + + trace_qemu_loadvm_state_section_partend(section_id); + QLIST_FOREACH(le, &loadvm_handlers, entry) { + if (le->section_id == section_id) { + break; + } + } + if (le == NULL) { + error_report("Unknown savevm section %d", section_id); + ret = -EINVAL; + goto out; + } + + ret = vmstate_load(f, le->se, le->version_id); + if (ret < 0) { + error_report("error while loading state section id %d(%s)", + section_id, le->se->idstr); + goto out; + } + break; + default: + error_report("Unknown savevm section type %d", section_type); + ret = -EINVAL; + goto out; + } + } + + file_error_after_eof = qemu_file_get_error(f); + + /* + * Try to read in the VMDESC section as well, so that dumping tools that + * intercept our migration stream have the chance to see it. + */ + + /* We've got to be careful; if we don't read the data and just shut the fd + * then the sender can error if we close while it's still sending. + * We also mustn't read data that isn't there; some transports (RDMA) + * will stall waiting for that data when the source has already closed. + */ + if (should_send_vmdesc()) { + uint8_t *buf; + uint32_t size; + section_type = qemu_get_byte(f); + + if (section_type != QEMU_VM_VMDESCRIPTION) { + error_report("Expected vmdescription section, but got %d", + section_type); + /* + * It doesn't seem worth failing at this point since + * we apparently have an otherwise valid VM state + */ + } else { + buf = g_malloc(0x1000); + size = qemu_get_be32(f); + + while (size > 0) { + uint32_t read_chunk = MIN(size, 0x1000); + qemu_get_buffer(f, buf, read_chunk); + size -= read_chunk; + } + g_free(buf); + } + } + + /* Supplement SeaBIOS's shadowing now, because it was useless when the + * incoming VM started on the RHEL-6 emulator. + */ + if (shadow_bios_after_incoming) { + shadow_bios(); + } + + cpu_synchronize_all_post_init(); + + ret = 0; + +out: + QLIST_FOREACH_SAFE(le, &loadvm_handlers, entry, new_le) { + QLIST_REMOVE(le, entry); + g_free(le); + } + + if (ret == 0) { + /* We may not have a VMDESC section, so ignore relative errors */ + ret = file_error_after_eof; + } + + return ret; +} + +static BlockDriverState *find_vmstate_bs(void) +{ + BlockDriverState *bs = NULL; + while ((bs = bdrv_next(bs))) { + if (bdrv_can_snapshot(bs)) { + return bs; + } + } + return NULL; +} + +/* + * Deletes snapshots of a given name in all opened images. + */ +static int del_existing_snapshots(Monitor *mon, const char *name) +{ + BlockDriverState *bs; + QEMUSnapshotInfo sn1, *snapshot = &sn1; + Error *err = NULL; + + bs = NULL; + while ((bs = bdrv_next(bs))) { + if (bdrv_can_snapshot(bs) && + bdrv_snapshot_find(bs, snapshot, name) >= 0) { + bdrv_snapshot_delete_by_id_or_name(bs, name, &err); + if (err) { + monitor_printf(mon, + "Error while deleting snapshot on device '%s':" + " %s\n", + bdrv_get_device_name(bs), + error_get_pretty(err)); + error_free(err); + return -1; + } + } + } + + return 0; +} + +void hmp_savevm(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs, *bs1; + QEMUSnapshotInfo sn1, *sn = &sn1, old_sn1, *old_sn = &old_sn1; + int ret; + QEMUFile *f; + int saved_vm_running; + uint64_t vm_state_size; + qemu_timeval tv; + struct tm tm; + const char *name = qdict_get_try_str(qdict, "name"); + Error *local_err = NULL; + + /* Verify if there is a device that doesn't support snapshots and is writable */ + bs = NULL; + while ((bs = bdrv_next(bs))) { + + if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) { + continue; + } + + if (!bdrv_can_snapshot(bs)) { + monitor_printf(mon, "Device '%s' is writable but does not support snapshots.\n", + bdrv_get_device_name(bs)); + return; + } + } + + bs = find_vmstate_bs(); + if (!bs) { + monitor_printf(mon, "No block device can accept snapshots\n"); + return; + } + + saved_vm_running = runstate_is_running(); + vm_stop(RUN_STATE_SAVE_VM); + + memset(sn, 0, sizeof(*sn)); + + /* fill auxiliary fields */ + qemu_gettimeofday(&tv); + sn->date_sec = tv.tv_sec; + sn->date_nsec = tv.tv_usec * 1000; + sn->vm_clock_nsec = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + if (name) { + ret = bdrv_snapshot_find(bs, old_sn, name); + if (ret >= 0) { + pstrcpy(sn->name, sizeof(sn->name), old_sn->name); + pstrcpy(sn->id_str, sizeof(sn->id_str), old_sn->id_str); + } else { + pstrcpy(sn->name, sizeof(sn->name), name); + } + } else { + /* cast below needed for OpenBSD where tv_sec is still 'long' */ + localtime_r((const time_t *)&tv.tv_sec, &tm); + strftime(sn->name, sizeof(sn->name), "vm-%Y%m%d%H%M%S", &tm); + } + + /* Delete old snapshots of the same name */ + if (name && del_existing_snapshots(mon, name) < 0) { + goto the_end; + } + + /* save the VM state */ + f = qemu_fopen_bdrv(bs, 1); + if (!f) { + monitor_printf(mon, "Could not open VM state file\n"); + goto the_end; + } + ret = qemu_savevm_state(f, &local_err); + vm_state_size = qemu_ftell(f); + qemu_fclose(f); + if (ret < 0) { + monitor_printf(mon, "%s\n", error_get_pretty(local_err)); + error_free(local_err); + goto the_end; + } + + /* create the snapshots */ + + bs1 = NULL; + while ((bs1 = bdrv_next(bs1))) { + if (bdrv_can_snapshot(bs1)) { + /* Write VM state size only to the image that contains the state */ + sn->vm_state_size = (bs == bs1 ? vm_state_size : 0); + ret = bdrv_snapshot_create(bs1, sn); + if (ret < 0) { + monitor_printf(mon, "Error while creating snapshot on '%s'\n", + bdrv_get_device_name(bs1)); + } + } + } + + the_end: + if (saved_vm_running) { + vm_start(); + } +} + +void qmp_xen_save_devices_state(const char *filename, Error **errp) +{ + QEMUFile *f; + int saved_vm_running; + int ret; + + saved_vm_running = runstate_is_running(); + vm_stop(RUN_STATE_SAVE_VM); + + f = qemu_fopen(filename, "wb"); + if (!f) { + error_setg_file_open(errp, errno, filename); + goto the_end; + } + ret = qemu_save_device_state(f); + qemu_fclose(f); + if (ret < 0) { + error_set(errp, QERR_IO_ERROR); + } + + the_end: + if (saved_vm_running) { + vm_start(); + } +} + +int load_vmstate(const char *name) +{ + BlockDriverState *bs, *bs_vm_state; + QEMUSnapshotInfo sn; + QEMUFile *f; + int ret; + + bs_vm_state = find_vmstate_bs(); + if (!bs_vm_state) { + error_report("No block device supports snapshots"); + return -ENOTSUP; + } + + /* Don't even try to load empty VM states */ + ret = bdrv_snapshot_find(bs_vm_state, &sn, name); + if (ret < 0) { + return ret; + } else if (sn.vm_state_size == 0) { + error_report("This is a disk-only snapshot. Revert to it offline " + "using qemu-img."); + return -EINVAL; + } + + /* Verify if there is any device that doesn't support snapshots and is + writable and check if the requested snapshot is available too. */ + bs = NULL; + while ((bs = bdrv_next(bs))) { + + if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) { + continue; + } + + if (!bdrv_can_snapshot(bs)) { + error_report("Device '%s' is writable but does not support snapshots.", + bdrv_get_device_name(bs)); + return -ENOTSUP; + } + + ret = bdrv_snapshot_find(bs, &sn, name); + if (ret < 0) { + error_report("Device '%s' does not have the requested snapshot '%s'", + bdrv_get_device_name(bs), name); + return ret; + } + } + + /* Flush all IO requests so they don't interfere with the new state. */ + bdrv_drain_all(); + + bs = NULL; + while ((bs = bdrv_next(bs))) { + if (bdrv_can_snapshot(bs)) { + ret = bdrv_snapshot_goto(bs, name); + if (ret < 0) { + error_report("Error %d while activating snapshot '%s' on '%s'", + ret, name, bdrv_get_device_name(bs)); + return ret; + } + } + } + + /* restore the VM state */ + f = qemu_fopen_bdrv(bs_vm_state, 0); + if (!f) { + error_report("Could not open VM state file"); + return -EINVAL; + } + + qemu_system_reset(VMRESET_SILENT); + ret = qemu_loadvm_state(f); + + qemu_fclose(f); + if (ret < 0) { + error_report("Error %d while loading VM state", ret); + return ret; + } + + return 0; +} + +void hmp_delvm(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs; + Error *err; + const char *name = qdict_get_str(qdict, "name"); + + if (!find_vmstate_bs()) { + monitor_printf(mon, "No block device supports snapshots\n"); + return; + } + + bs = NULL; + while ((bs = bdrv_next(bs))) { + if (bdrv_can_snapshot(bs)) { + err = NULL; + bdrv_snapshot_delete_by_id_or_name(bs, name, &err); + if (err) { + monitor_printf(mon, + "Error while deleting snapshot on device '%s':" + " %s\n", + bdrv_get_device_name(bs), + error_get_pretty(err)); + error_free(err); + } + } + } +} + +void hmp_info_snapshots(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs, *bs1; + QEMUSnapshotInfo *sn_tab, *sn, s, *sn_info = &s; + int nb_sns, i, ret, available; + int total; + int *available_snapshots; + + bs = find_vmstate_bs(); + if (!bs) { + monitor_printf(mon, "No available block device supports snapshots\n"); + return; + } + + nb_sns = bdrv_snapshot_list(bs, &sn_tab); + if (nb_sns < 0) { + monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns); + return; + } + + if (nb_sns == 0) { + monitor_printf(mon, "There is no snapshot available.\n"); + return; + } + + available_snapshots = g_malloc0(sizeof(int) * nb_sns); + total = 0; + for (i = 0; i < nb_sns; i++) { + sn = &sn_tab[i]; + available = 1; + bs1 = NULL; + + while ((bs1 = bdrv_next(bs1))) { + if (bdrv_can_snapshot(bs1) && bs1 != bs) { + ret = bdrv_snapshot_find(bs1, sn_info, sn->id_str); + if (ret < 0) { + available = 0; + break; + } + } + } + + if (available) { + available_snapshots[total] = i; + total++; + } + } + + if (total > 0) { + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); + monitor_printf(mon, "\n"); + for (i = 0; i < total; i++) { + sn = &sn_tab[available_snapshots[i]]; + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, sn); + monitor_printf(mon, "\n"); + } + } else { + monitor_printf(mon, "There is no suitable snapshot available\n"); + } + + g_free(sn_tab); + g_free(available_snapshots); + +} + +void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev) +{ + qemu_ram_set_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK, + memory_region_name(mr), dev); +} + +void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev) +{ + qemu_ram_unset_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK); +} + +void vmstate_register_ram_global(MemoryRegion *mr) +{ + vmstate_register_ram(mr, NULL); +} diff --git a/savevm.c b/savevm.c deleted file mode 100644 index 416bd3e..0000000 --- a/savevm.c +++ /dev/null @@ -1,1523 +0,0 @@ -/* - * QEMU System Emulator - * - * Copyright (c) 2003-2008 Fabrice Bellard - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ - -#include "config-host.h" -#include "qemu-common.h" -#include "hw/boards.h" -#include "hw/hw.h" -#include "hw/qdev.h" -#include "net/net.h" -#include "monitor/monitor.h" -#include "sysemu/sysemu.h" -#include "qemu/timer.h" -#include "audio/audio.h" -#include "migration/migration.h" -#include "qemu/sockets.h" -#include "qemu/queue.h" -#include "qemu/rcu_queue.h" -#include "sysemu/cpus.h" -#include "exec/memory.h" -#include "qmp-commands.h" -#include "trace.h" -#include "qemu/iov.h" -#include "block/snapshot.h" -#include "block/qapi.h" - - -#ifndef ETH_P_RARP -#define ETH_P_RARP 0x8035 -#endif -#define ARP_HTYPE_ETH 0x0001 -#define ARP_PTYPE_IP 0x0800 -#define ARP_OP_REQUEST_REV 0x3 - -bool shadow_bios_after_incoming; - -static int announce_self_create(uint8_t *buf, - uint8_t *mac_addr) -{ - /* Ethernet header. */ - memset(buf, 0xff, 6); /* destination MAC addr */ - memcpy(buf + 6, mac_addr, 6); /* source MAC addr */ - *(uint16_t *)(buf + 12) = htons(ETH_P_RARP); /* ethertype */ - - /* RARP header. */ - *(uint16_t *)(buf + 14) = htons(ARP_HTYPE_ETH); /* hardware addr space */ - *(uint16_t *)(buf + 16) = htons(ARP_PTYPE_IP); /* protocol addr space */ - *(buf + 18) = 6; /* hardware addr length (ethernet) */ - *(buf + 19) = 4; /* protocol addr length (IPv4) */ - *(uint16_t *)(buf + 20) = htons(ARP_OP_REQUEST_REV); /* opcode */ - memcpy(buf + 22, mac_addr, 6); /* source hw addr */ - memset(buf + 28, 0x00, 4); /* source protocol addr */ - memcpy(buf + 32, mac_addr, 6); /* target hw addr */ - memset(buf + 38, 0x00, 4); /* target protocol addr */ - - /* Padding to get up to 60 bytes (ethernet min packet size, minus FCS). */ - memset(buf + 42, 0x00, 18); - - return 60; /* len (FCS will be added by hardware) */ -} - -static void qemu_announce_self_iter(NICState *nic, void *opaque) -{ - uint8_t buf[60]; - int len; - - trace_qemu_announce_self_iter(qemu_ether_ntoa(&nic->conf->macaddr)); - len = announce_self_create(buf, nic->conf->macaddr.a); - - qemu_send_packet_raw(qemu_get_queue(nic), buf, len); -} - - -static void qemu_announce_self_once(void *opaque) -{ - static int count = SELF_ANNOUNCE_ROUNDS; - QEMUTimer *timer = *(QEMUTimer **)opaque; - - qemu_foreach_nic(qemu_announce_self_iter, NULL); - - if (--count) { - /* delay 50ms, 150ms, 250ms, ... */ - timer_mod(timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + - self_announce_delay(count)); - } else { - timer_del(timer); - timer_free(timer); - } -} - -void qemu_announce_self(void) -{ - static QEMUTimer *timer; - timer = timer_new_ms(QEMU_CLOCK_REALTIME, qemu_announce_self_once, &timer); - qemu_announce_self_once(&timer); -} - -/***********************************************************/ -/* savevm/loadvm support */ - -static ssize_t block_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, - int64_t pos) -{ - int ret; - QEMUIOVector qiov; - - qemu_iovec_init_external(&qiov, iov, iovcnt); - ret = bdrv_writev_vmstate(opaque, &qiov, pos); - if (ret < 0) { - return ret; - } - - return qiov.size; -} - -static int block_put_buffer(void *opaque, const uint8_t *buf, - int64_t pos, int size) -{ - bdrv_save_vmstate(opaque, buf, pos, size); - return size; -} - -static int block_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size) -{ - return bdrv_load_vmstate(opaque, buf, pos, size); -} - -static int bdrv_fclose(void *opaque) -{ - return bdrv_flush(opaque); -} - -static const QEMUFileOps bdrv_read_ops = { - .get_buffer = block_get_buffer, - .close = bdrv_fclose -}; - -static const QEMUFileOps bdrv_write_ops = { - .put_buffer = block_put_buffer, - .writev_buffer = block_writev_buffer, - .close = bdrv_fclose -}; - -static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable) -{ - if (is_writable) { - return qemu_fopen_ops(bs, &bdrv_write_ops); - } - return qemu_fopen_ops(bs, &bdrv_read_ops); -} - - -/* QEMUFile timer support. - * Not in qemu-file.c to not add qemu-timer.c as dependency to qemu-file.c - */ - -void timer_put(QEMUFile *f, QEMUTimer *ts) -{ - uint64_t expire_time; - - expire_time = timer_expire_time_ns(ts); - qemu_put_be64(f, expire_time); -} - -void timer_get(QEMUFile *f, QEMUTimer *ts) -{ - uint64_t expire_time; - - expire_time = qemu_get_be64(f); - if (expire_time != -1) { - timer_mod_ns(ts, expire_time); - } else { - timer_del(ts); - } -} - - -/* VMState timer support. - * Not in vmstate.c to not add qemu-timer.c as dependency to vmstate.c - */ - -static int get_timer(QEMUFile *f, void *pv, size_t size) -{ - QEMUTimer *v = pv; - timer_get(f, v); - return 0; -} - -static void put_timer(QEMUFile *f, void *pv, size_t size) -{ - QEMUTimer *v = pv; - timer_put(f, v); -} - -const VMStateInfo vmstate_info_timer = { - .name = "timer", - .get = get_timer, - .put = put_timer, -}; - - -typedef struct CompatEntry { - char idstr[256]; - int instance_id; -} CompatEntry; - -typedef struct SaveStateEntry { - QTAILQ_ENTRY(SaveStateEntry) entry; - char idstr[256]; - int instance_id; - int alias_id; - int version_id; - int section_id; - SaveVMHandlers *ops; - const VMStateDescription *vmsd; - void *opaque; - CompatEntry *compat; - int is_ram; -} SaveStateEntry; - - -static QTAILQ_HEAD(savevm_handlers, SaveStateEntry) savevm_handlers = - QTAILQ_HEAD_INITIALIZER(savevm_handlers); -static int global_section_id; - -static void dump_vmstate_vmsd(FILE *out_file, - const VMStateDescription *vmsd, int indent, - bool is_subsection); - -static void dump_vmstate_vmsf(FILE *out_file, const VMStateField *field, - int indent) -{ - fprintf(out_file, "%*s{\n", indent, ""); - indent += 2; - fprintf(out_file, "%*s\"field\": \"%s\",\n", indent, "", field->name); - fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", - field->version_id); - fprintf(out_file, "%*s\"field_exists\": %s,\n", indent, "", - field->field_exists ? "true" : "false"); - fprintf(out_file, "%*s\"size\": %zu", indent, "", field->size); - if (field->vmsd != NULL) { - fprintf(out_file, ",\n"); - dump_vmstate_vmsd(out_file, field->vmsd, indent, false); - } - fprintf(out_file, "\n%*s}", indent - 2, ""); -} - -static void dump_vmstate_vmss(FILE *out_file, - const VMStateSubsection *subsection, - int indent) -{ - if (subsection->vmsd != NULL) { - dump_vmstate_vmsd(out_file, subsection->vmsd, indent, true); - } -} - -static void dump_vmstate_vmsd(FILE *out_file, - const VMStateDescription *vmsd, int indent, - bool is_subsection) -{ - if (is_subsection) { - fprintf(out_file, "%*s{\n", indent, ""); - } else { - fprintf(out_file, "%*s\"%s\": {\n", indent, "", "Description"); - } - indent += 2; - fprintf(out_file, "%*s\"name\": \"%s\",\n", indent, "", vmsd->name); - fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", - vmsd->version_id); - fprintf(out_file, "%*s\"minimum_version_id\": %d", indent, "", - vmsd->minimum_version_id); - if (vmsd->fields != NULL) { - const VMStateField *field = vmsd->fields; - bool first; - - fprintf(out_file, ",\n%*s\"Fields\": [\n", indent, ""); - first = true; - while (field->name != NULL) { - if (field->flags & VMS_MUST_EXIST) { - /* Ignore VMSTATE_VALIDATE bits; these don't get migrated */ - field++; - continue; - } - if (!first) { - fprintf(out_file, ",\n"); - } - dump_vmstate_vmsf(out_file, field, indent + 2); - field++; - first = false; - } - fprintf(out_file, "\n%*s]", indent, ""); - } - if (vmsd->subsections != NULL) { - const VMStateSubsection *subsection = vmsd->subsections; - bool first; - - fprintf(out_file, ",\n%*s\"Subsections\": [\n", indent, ""); - first = true; - while (subsection->vmsd != NULL) { - if (!first) { - fprintf(out_file, ",\n"); - } - dump_vmstate_vmss(out_file, subsection, indent + 2); - subsection++; - first = false; - } - fprintf(out_file, "\n%*s]", indent, ""); - } - fprintf(out_file, "\n%*s}", indent - 2, ""); -} - -static void dump_machine_type(FILE *out_file) -{ - MachineClass *mc; - - mc = MACHINE_GET_CLASS(current_machine); - - fprintf(out_file, " \"vmschkmachine\": {\n"); - fprintf(out_file, " \"Name\": \"%s\"\n", mc->name); - fprintf(out_file, " },\n"); -} - -void dump_vmstate_json_to_file(FILE *out_file) -{ - GSList *list, *elt; - bool first; - - fprintf(out_file, "{\n"); - dump_machine_type(out_file); - - first = true; - list = object_class_get_list(TYPE_DEVICE, true); - for (elt = list; elt; elt = elt->next) { - DeviceClass *dc = OBJECT_CLASS_CHECK(DeviceClass, elt->data, - TYPE_DEVICE); - const char *name; - int indent = 2; - - if (!dc->vmsd) { - continue; - } - - if (!first) { - fprintf(out_file, ",\n"); - } - name = object_class_get_name(OBJECT_CLASS(dc)); - fprintf(out_file, "%*s\"%s\": {\n", indent, "", name); - indent += 2; - fprintf(out_file, "%*s\"Name\": \"%s\",\n", indent, "", name); - fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", - dc->vmsd->version_id); - fprintf(out_file, "%*s\"minimum_version_id\": %d,\n", indent, "", - dc->vmsd->minimum_version_id); - - dump_vmstate_vmsd(out_file, dc->vmsd, indent, false); - - fprintf(out_file, "\n%*s}", indent - 2, ""); - first = false; - } - fprintf(out_file, "\n}\n"); - fclose(out_file); -} - -static int calculate_new_instance_id(const char *idstr) -{ - SaveStateEntry *se; - int instance_id = 0; - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (strcmp(idstr, se->idstr) == 0 - && instance_id <= se->instance_id) { - instance_id = se->instance_id + 1; - } - } - return instance_id; -} - -static int calculate_compat_instance_id(const char *idstr) -{ - SaveStateEntry *se; - int instance_id = 0; - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (!se->compat) { - continue; - } - - if (strcmp(idstr, se->compat->idstr) == 0 - && instance_id <= se->compat->instance_id) { - instance_id = se->compat->instance_id + 1; - } - } - return instance_id; -} - -/* TODO: Individual devices generally have very little idea about the rest - of the system, so instance_id should be removed/replaced. - Meanwhile pass -1 as instance_id if you do not already have a clearly - distinguishing id for all instances of your device class. */ -int register_savevm_live(DeviceState *dev, - const char *idstr, - int instance_id, - int version_id, - SaveVMHandlers *ops, - void *opaque) -{ - SaveStateEntry *se; - - se = g_malloc0(sizeof(SaveStateEntry)); - se->version_id = version_id; - se->section_id = global_section_id++; - se->ops = ops; - se->opaque = opaque; - se->vmsd = NULL; - /* if this is a live_savem then set is_ram */ - if (ops->save_live_setup != NULL) { - se->is_ram = 1; - } - - if (dev) { - char *id = qdev_get_dev_path(dev); - if (id) { - pstrcpy(se->idstr, sizeof(se->idstr), id); - pstrcat(se->idstr, sizeof(se->idstr), "/"); - g_free(id); - - se->compat = g_malloc0(sizeof(CompatEntry)); - pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), idstr); - se->compat->instance_id = instance_id == -1 ? - calculate_compat_instance_id(idstr) : instance_id; - instance_id = -1; - } - } - pstrcat(se->idstr, sizeof(se->idstr), idstr); - - if (instance_id == -1) { - se->instance_id = calculate_new_instance_id(se->idstr); - } else { - se->instance_id = instance_id; - } - assert(!se->compat || se->instance_id == 0); - /* add at the end of list */ - QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry); - return 0; -} - -int register_savevm(DeviceState *dev, - const char *idstr, - int instance_id, - int version_id, - SaveStateHandler *save_state, - LoadStateHandler *load_state, - void *opaque) -{ - SaveVMHandlers *ops = g_malloc0(sizeof(SaveVMHandlers)); - ops->save_state = save_state; - ops->load_state = load_state; - return register_savevm_live(dev, idstr, instance_id, version_id, - ops, opaque); -} - -void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque) -{ - SaveStateEntry *se, *new_se; - char id[256] = ""; - - if (dev) { - char *path = qdev_get_dev_path(dev); - if (path) { - pstrcpy(id, sizeof(id), path); - pstrcat(id, sizeof(id), "/"); - g_free(path); - } - } - pstrcat(id, sizeof(id), idstr); - - QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) { - if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) { - QTAILQ_REMOVE(&savevm_handlers, se, entry); - if (se->compat) { - g_free(se->compat); - } - g_free(se->ops); - g_free(se); - } - } -} - -int vmstate_register_with_alias_id(DeviceState *dev, int instance_id, - const VMStateDescription *vmsd, - void *opaque, int alias_id, - int required_for_version) -{ - SaveStateEntry *se; - - /* If this triggers, alias support can be dropped for the vmsd. */ - assert(alias_id == -1 || required_for_version >= vmsd->minimum_version_id); - - se = g_malloc0(sizeof(SaveStateEntry)); - se->version_id = vmsd->version_id; - se->section_id = global_section_id++; - se->opaque = opaque; - se->vmsd = vmsd; - se->alias_id = alias_id; - - if (dev) { - char *id = qdev_get_dev_path(dev); - if (id) { - pstrcpy(se->idstr, sizeof(se->idstr), id); - pstrcat(se->idstr, sizeof(se->idstr), "/"); - g_free(id); - - se->compat = g_malloc0(sizeof(CompatEntry)); - pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), vmsd->name); - se->compat->instance_id = instance_id == -1 ? - calculate_compat_instance_id(vmsd->name) : instance_id; - instance_id = -1; - } - } - pstrcat(se->idstr, sizeof(se->idstr), vmsd->name); - - if (instance_id == -1) { - se->instance_id = calculate_new_instance_id(se->idstr); - } else { - se->instance_id = instance_id; - } - assert(!se->compat || se->instance_id == 0); - /* add at the end of list */ - QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry); - return 0; -} - -void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd, - void *opaque) -{ - SaveStateEntry *se, *new_se; - - QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) { - if (se->vmsd == vmsd && se->opaque == opaque) { - QTAILQ_REMOVE(&savevm_handlers, se, entry); - if (se->compat) { - g_free(se->compat); - } - g_free(se); - } - } -} - -static int vmstate_load(QEMUFile *f, SaveStateEntry *se, int version_id) -{ - trace_vmstate_load(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); - if (!se->vmsd) { /* Old style */ - return se->ops->load_state(f, se->opaque, version_id); - } - return vmstate_load_state(f, se->vmsd, se->opaque, version_id); -} - -static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se, QJSON *vmdesc) -{ - int64_t old_offset, size; - - old_offset = qemu_ftell_fast(f); - se->ops->save_state(f, se->opaque); - size = qemu_ftell_fast(f) - old_offset; - - if (vmdesc) { - json_prop_int(vmdesc, "size", size); - json_start_array(vmdesc, "fields"); - json_start_object(vmdesc, NULL); - json_prop_str(vmdesc, "name", "data"); - json_prop_int(vmdesc, "size", size); - json_prop_str(vmdesc, "type", "buffer"); - json_end_object(vmdesc); - json_end_array(vmdesc); - } -} - -static void vmstate_save(QEMUFile *f, SaveStateEntry *se, QJSON *vmdesc) -{ - trace_vmstate_save(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); - if (!se->vmsd) { - vmstate_save_old_style(f, se, vmdesc); - return; - } - vmstate_save_state(f, se->vmsd, se->opaque, vmdesc); -} - -bool qemu_savevm_state_blocked(Error **errp) -{ - SaveStateEntry *se; - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (se->vmsd && se->vmsd->unmigratable) { - error_setg(errp, "State blocked by non-migratable device '%s'", - se->idstr); - return true; - } - } - return false; -} - -void qemu_savevm_state_begin(QEMUFile *f, - const MigrationParams *params) -{ - SaveStateEntry *se; - int ret; - - trace_savevm_state_begin(); - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (!se->ops || !se->ops->set_params) { - continue; - } - se->ops->set_params(params, se->opaque); - } - - qemu_put_be32(f, QEMU_VM_FILE_MAGIC); - qemu_put_be32(f, QEMU_VM_FILE_VERSION); - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - int len; - - if (!se->ops || !se->ops->save_live_setup) { - continue; - } - if (se->ops && se->ops->is_active) { - if (!se->ops->is_active(se->opaque)) { - continue; - } - } - /* Section type */ - qemu_put_byte(f, QEMU_VM_SECTION_START); - qemu_put_be32(f, se->section_id); - - /* ID string */ - len = strlen(se->idstr); - qemu_put_byte(f, len); - qemu_put_buffer(f, (uint8_t *)se->idstr, len); - - qemu_put_be32(f, se->instance_id); - qemu_put_be32(f, se->version_id); - - ret = se->ops->save_live_setup(f, se->opaque); - if (ret < 0) { - qemu_file_set_error(f, ret); - break; - } - } -} - -/* - * this function has three return values: - * negative: there was one error, and we have -errno. - * 0 : We haven't finished, caller have to go again - * 1 : We have finished, we can go to complete phase - */ -int qemu_savevm_state_iterate(QEMUFile *f) -{ - SaveStateEntry *se; - int ret = 1; - - trace_savevm_state_iterate(); - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (!se->ops || !se->ops->save_live_iterate) { - continue; - } - if (se->ops && se->ops->is_active) { - if (!se->ops->is_active(se->opaque)) { - continue; - } - } - if (qemu_file_rate_limit(f)) { - return 0; - } - trace_savevm_section_start(se->idstr, se->section_id); - /* Section type */ - qemu_put_byte(f, QEMU_VM_SECTION_PART); - qemu_put_be32(f, se->section_id); - - ret = se->ops->save_live_iterate(f, se->opaque); - trace_savevm_section_end(se->idstr, se->section_id, ret); - - if (ret < 0) { - qemu_file_set_error(f, ret); - } - if (ret <= 0) { - /* Do not proceed to the next vmstate before this one reported - completion of the current stage. This serializes the migration - and reduces the probability that a faster changing state is - synchronized over and over again. */ - break; - } - } - return ret; -} - -static bool should_send_vmdesc(void) -{ - MachineState *machine = MACHINE(qdev_get_machine()); - return !machine->suppress_vmdesc; -} - -void qemu_savevm_state_complete(QEMUFile *f) -{ - QJSON *vmdesc; - int vmdesc_len; - SaveStateEntry *se; - int ret; - - trace_savevm_state_complete(); - - cpu_synchronize_all_states(); - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (!se->ops || !se->ops->save_live_complete) { - continue; - } - if (se->ops && se->ops->is_active) { - if (!se->ops->is_active(se->opaque)) { - continue; - } - } - trace_savevm_section_start(se->idstr, se->section_id); - /* Section type */ - qemu_put_byte(f, QEMU_VM_SECTION_END); - qemu_put_be32(f, se->section_id); - - ret = se->ops->save_live_complete(f, se->opaque); - trace_savevm_section_end(se->idstr, se->section_id, ret); - if (ret < 0) { - qemu_file_set_error(f, ret); - return; - } - } - - vmdesc = qjson_new(); - json_prop_int(vmdesc, "page_size", TARGET_PAGE_SIZE); - json_start_array(vmdesc, "devices"); - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - int len; - - if ((!se->ops || !se->ops->save_state) && !se->vmsd) { - continue; - } - trace_savevm_section_start(se->idstr, se->section_id); - - json_start_object(vmdesc, NULL); - json_prop_str(vmdesc, "name", se->idstr); - json_prop_int(vmdesc, "instance_id", se->instance_id); - - /* Section type */ - qemu_put_byte(f, QEMU_VM_SECTION_FULL); - qemu_put_be32(f, se->section_id); - - /* ID string */ - len = strlen(se->idstr); - qemu_put_byte(f, len); - qemu_put_buffer(f, (uint8_t *)se->idstr, len); - - qemu_put_be32(f, se->instance_id); - qemu_put_be32(f, se->version_id); - - vmstate_save(f, se, vmdesc); - - json_end_object(vmdesc); - trace_savevm_section_end(se->idstr, se->section_id, 0); - } - - qemu_put_byte(f, QEMU_VM_EOF); - - json_end_array(vmdesc); - qjson_finish(vmdesc); - vmdesc_len = strlen(qjson_get_str(vmdesc)); - - if (should_send_vmdesc()) { - qemu_put_byte(f, QEMU_VM_VMDESCRIPTION); - qemu_put_be32(f, vmdesc_len); - qemu_put_buffer(f, (uint8_t *)qjson_get_str(vmdesc), vmdesc_len); - } - object_unref(OBJECT(vmdesc)); - - qemu_fflush(f); -} - -uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size) -{ - SaveStateEntry *se; - uint64_t ret = 0; - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (!se->ops || !se->ops->save_live_pending) { - continue; - } - if (se->ops && se->ops->is_active) { - if (!se->ops->is_active(se->opaque)) { - continue; - } - } - ret += se->ops->save_live_pending(f, se->opaque, max_size); - } - return ret; -} - -void qemu_savevm_state_cancel(void) -{ - SaveStateEntry *se; - - trace_savevm_state_cancel(); - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (se->ops && se->ops->cancel) { - se->ops->cancel(se->opaque); - } - } -} - -static int qemu_savevm_state(QEMUFile *f, Error **errp) -{ - int ret; - MigrationParams params = { - .blk = 0, - .shared = 0 - }; - - if (qemu_savevm_state_blocked(errp)) { - return -EINVAL; - } - - qemu_mutex_unlock_iothread(); - qemu_savevm_state_begin(f, ¶ms); - qemu_mutex_lock_iothread(); - - while (qemu_file_get_error(f) == 0) { - if (qemu_savevm_state_iterate(f) > 0) { - break; - } - } - - ret = qemu_file_get_error(f); - if (ret == 0) { - qemu_savevm_state_complete(f); - ret = qemu_file_get_error(f); - } - if (ret != 0) { - qemu_savevm_state_cancel(); - error_setg_errno(errp, -ret, "Error while writing VM state"); - } - return ret; -} - -static int qemu_save_device_state(QEMUFile *f) -{ - SaveStateEntry *se; - - qemu_put_be32(f, QEMU_VM_FILE_MAGIC); - qemu_put_be32(f, QEMU_VM_FILE_VERSION); - - cpu_synchronize_all_states(); - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - int len; - - if (se->is_ram) { - continue; - } - if ((!se->ops || !se->ops->save_state) && !se->vmsd) { - continue; - } - - /* Section type */ - qemu_put_byte(f, QEMU_VM_SECTION_FULL); - qemu_put_be32(f, se->section_id); - - /* ID string */ - len = strlen(se->idstr); - qemu_put_byte(f, len); - qemu_put_buffer(f, (uint8_t *)se->idstr, len); - - qemu_put_be32(f, se->instance_id); - qemu_put_be32(f, se->version_id); - - vmstate_save(f, se, NULL); - } - - qemu_put_byte(f, QEMU_VM_EOF); - - return qemu_file_get_error(f); -} - -static SaveStateEntry *find_se(const char *idstr, int instance_id) -{ - SaveStateEntry *se; - - QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if (!strcmp(se->idstr, idstr) && - (instance_id == se->instance_id || - instance_id == se->alias_id)) - return se; - /* Migrating from an older version? */ - if (strstr(se->idstr, idstr) && se->compat) { - if (!strcmp(se->compat->idstr, idstr) && - (instance_id == se->compat->instance_id || - instance_id == se->alias_id)) - return se; - } - } - return NULL; -} - -typedef struct LoadStateEntry { - QLIST_ENTRY(LoadStateEntry) entry; - SaveStateEntry *se; - int section_id; - int version_id; -} LoadStateEntry; - -static void shadow_bios(void) -{ - RAMBlock *block, *ram, *oprom, *bios; - size_t one_meg, oprom_size, bios_size; - uint8_t *cd_seg_host, *ef_seg_host; - - ram = NULL; - oprom = NULL; - bios = NULL; - rcu_read_lock(); - QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { - if (strcmp("pc.ram", block->idstr) == 0) { - assert(ram == NULL); - ram = block; - } else if (strcmp("pc.rom", block->idstr) == 0) { - assert(oprom == NULL); - oprom = block; - } else if (strcmp("pc.bios", block->idstr) == 0) { - assert(bios == NULL); - bios = block; - } - } - assert(ram != NULL); - assert(oprom != NULL); - assert(bios != NULL); - assert(memory_region_is_ram(ram->mr)); - assert(memory_region_is_ram(oprom->mr)); - assert(memory_region_is_ram(bios->mr)); - assert(int128_eq(ram->mr->size, int128_make64(ram->used_length))); - assert(int128_eq(oprom->mr->size, int128_make64(oprom->used_length))); - assert(int128_eq(bios->mr->size, int128_make64(bios->used_length))); - - one_meg = 1024 * 1024; - oprom_size = 128 * 1024; - bios_size = 128 * 1024; - assert(ram->used_length >= one_meg); - assert(oprom->used_length == oprom_size); - assert(bios->used_length == bios_size); - - ef_seg_host = memory_region_get_ram_ptr(ram->mr) + (one_meg - bios_size); - cd_seg_host = ef_seg_host - oprom_size; - - /* This is a crude hack, but we must distinguish a rhel6.x.0 machtype guest - * coming in from a RHEL-6 emulator (where shadowing has had no effect on - * "pc.ram") from a similar guest coming in from a RHEL-7 emulator (where - * shadowing has worked). In the latter case we must not trample the live - * SeaBIOS variables in "pc.ram". - */ - if (buffer_is_zero(ef_seg_host, bios_size)) { - fprintf(stderr, "copying E and F segments from pc.bios to pc.ram\n"); - memcpy(ef_seg_host, memory_region_get_ram_ptr(bios->mr), bios_size); - } - if (buffer_is_zero(cd_seg_host, oprom_size)) { - fprintf(stderr, "copying C and D segments from pc.rom to pc.ram\n"); - memcpy(cd_seg_host, memory_region_get_ram_ptr(oprom->mr), oprom_size); - } - rcu_read_unlock(); -} - -int qemu_loadvm_state(QEMUFile *f) -{ - QLIST_HEAD(, LoadStateEntry) loadvm_handlers = - QLIST_HEAD_INITIALIZER(loadvm_handlers); - LoadStateEntry *le, *new_le; - Error *local_err = NULL; - uint8_t section_type; - unsigned int v; - int ret; - int file_error_after_eof = -1; - - if (qemu_savevm_state_blocked(&local_err)) { - error_report_err(local_err); - return -EINVAL; - } - - v = qemu_get_be32(f); - if (v != QEMU_VM_FILE_MAGIC) { - error_report("Not a migration stream"); - return -EINVAL; - } - - v = qemu_get_be32(f); - if (v == QEMU_VM_FILE_VERSION_COMPAT) { - error_report("SaveVM v2 format is obsolete and don't work anymore"); - return -ENOTSUP; - } - if (v != QEMU_VM_FILE_VERSION) { - error_report("Unsupported migration stream version"); - return -ENOTSUP; - } - - while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) { - uint32_t instance_id, version_id, section_id; - SaveStateEntry *se; - char idstr[257]; - int len; - - trace_qemu_loadvm_state_section(section_type); - switch (section_type) { - case QEMU_VM_SECTION_START: - case QEMU_VM_SECTION_FULL: - /* Read section start */ - section_id = qemu_get_be32(f); - len = qemu_get_byte(f); - qemu_get_buffer(f, (uint8_t *)idstr, len); - idstr[len] = 0; - instance_id = qemu_get_be32(f); - version_id = qemu_get_be32(f); - - trace_qemu_loadvm_state_section_startfull(section_id, idstr, - instance_id, version_id); - /* Find savevm section */ - se = find_se(idstr, instance_id); - if (se == NULL) { - error_report("Unknown savevm section or instance '%s' %d", - idstr, instance_id); - ret = -EINVAL; - goto out; - } - - /* Validate version */ - if (version_id > se->version_id) { - error_report("savevm: unsupported version %d for '%s' v%d", - version_id, idstr, se->version_id); - ret = -EINVAL; - goto out; - } - - /* Add entry */ - le = g_malloc0(sizeof(*le)); - - le->se = se; - le->section_id = section_id; - le->version_id = version_id; - QLIST_INSERT_HEAD(&loadvm_handlers, le, entry); - - ret = vmstate_load(f, le->se, le->version_id); - if (ret < 0) { - error_report("error while loading state for instance 0x%x of" - " device '%s'", instance_id, idstr); - goto out; - } - break; - case QEMU_VM_SECTION_PART: - case QEMU_VM_SECTION_END: - section_id = qemu_get_be32(f); - - trace_qemu_loadvm_state_section_partend(section_id); - QLIST_FOREACH(le, &loadvm_handlers, entry) { - if (le->section_id == section_id) { - break; - } - } - if (le == NULL) { - error_report("Unknown savevm section %d", section_id); - ret = -EINVAL; - goto out; - } - - ret = vmstate_load(f, le->se, le->version_id); - if (ret < 0) { - error_report("error while loading state section id %d(%s)", - section_id, le->se->idstr); - goto out; - } - break; - default: - error_report("Unknown savevm section type %d", section_type); - ret = -EINVAL; - goto out; - } - } - - file_error_after_eof = qemu_file_get_error(f); - - /* - * Try to read in the VMDESC section as well, so that dumping tools that - * intercept our migration stream have the chance to see it. - */ - - /* We've got to be careful; if we don't read the data and just shut the fd - * then the sender can error if we close while it's still sending. - * We also mustn't read data that isn't there; some transports (RDMA) - * will stall waiting for that data when the source has already closed. - */ - if (should_send_vmdesc()) { - uint8_t *buf; - uint32_t size; - section_type = qemu_get_byte(f); - - if (section_type != QEMU_VM_VMDESCRIPTION) { - error_report("Expected vmdescription section, but got %d", - section_type); - /* - * It doesn't seem worth failing at this point since - * we apparently have an otherwise valid VM state - */ - } else { - buf = g_malloc(0x1000); - size = qemu_get_be32(f); - - while (size > 0) { - uint32_t read_chunk = MIN(size, 0x1000); - qemu_get_buffer(f, buf, read_chunk); - size -= read_chunk; - } - g_free(buf); - } - } - - /* Supplement SeaBIOS's shadowing now, because it was useless when the - * incoming VM started on the RHEL-6 emulator. - */ - if (shadow_bios_after_incoming) { - shadow_bios(); - } - - cpu_synchronize_all_post_init(); - - ret = 0; - -out: - QLIST_FOREACH_SAFE(le, &loadvm_handlers, entry, new_le) { - QLIST_REMOVE(le, entry); - g_free(le); - } - - if (ret == 0) { - /* We may not have a VMDESC section, so ignore relative errors */ - ret = file_error_after_eof; - } - - return ret; -} - -static BlockDriverState *find_vmstate_bs(void) -{ - BlockDriverState *bs = NULL; - while ((bs = bdrv_next(bs))) { - if (bdrv_can_snapshot(bs)) { - return bs; - } - } - return NULL; -} - -/* - * Deletes snapshots of a given name in all opened images. - */ -static int del_existing_snapshots(Monitor *mon, const char *name) -{ - BlockDriverState *bs; - QEMUSnapshotInfo sn1, *snapshot = &sn1; - Error *err = NULL; - - bs = NULL; - while ((bs = bdrv_next(bs))) { - if (bdrv_can_snapshot(bs) && - bdrv_snapshot_find(bs, snapshot, name) >= 0) { - bdrv_snapshot_delete_by_id_or_name(bs, name, &err); - if (err) { - monitor_printf(mon, - "Error while deleting snapshot on device '%s':" - " %s\n", - bdrv_get_device_name(bs), - error_get_pretty(err)); - error_free(err); - return -1; - } - } - } - - return 0; -} - -void hmp_savevm(Monitor *mon, const QDict *qdict) -{ - BlockDriverState *bs, *bs1; - QEMUSnapshotInfo sn1, *sn = &sn1, old_sn1, *old_sn = &old_sn1; - int ret; - QEMUFile *f; - int saved_vm_running; - uint64_t vm_state_size; - qemu_timeval tv; - struct tm tm; - const char *name = qdict_get_try_str(qdict, "name"); - Error *local_err = NULL; - - /* Verify if there is a device that doesn't support snapshots and is writable */ - bs = NULL; - while ((bs = bdrv_next(bs))) { - - if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) { - continue; - } - - if (!bdrv_can_snapshot(bs)) { - monitor_printf(mon, "Device '%s' is writable but does not support snapshots.\n", - bdrv_get_device_name(bs)); - return; - } - } - - bs = find_vmstate_bs(); - if (!bs) { - monitor_printf(mon, "No block device can accept snapshots\n"); - return; - } - - saved_vm_running = runstate_is_running(); - vm_stop(RUN_STATE_SAVE_VM); - - memset(sn, 0, sizeof(*sn)); - - /* fill auxiliary fields */ - qemu_gettimeofday(&tv); - sn->date_sec = tv.tv_sec; - sn->date_nsec = tv.tv_usec * 1000; - sn->vm_clock_nsec = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - if (name) { - ret = bdrv_snapshot_find(bs, old_sn, name); - if (ret >= 0) { - pstrcpy(sn->name, sizeof(sn->name), old_sn->name); - pstrcpy(sn->id_str, sizeof(sn->id_str), old_sn->id_str); - } else { - pstrcpy(sn->name, sizeof(sn->name), name); - } - } else { - /* cast below needed for OpenBSD where tv_sec is still 'long' */ - localtime_r((const time_t *)&tv.tv_sec, &tm); - strftime(sn->name, sizeof(sn->name), "vm-%Y%m%d%H%M%S", &tm); - } - - /* Delete old snapshots of the same name */ - if (name && del_existing_snapshots(mon, name) < 0) { - goto the_end; - } - - /* save the VM state */ - f = qemu_fopen_bdrv(bs, 1); - if (!f) { - monitor_printf(mon, "Could not open VM state file\n"); - goto the_end; - } - ret = qemu_savevm_state(f, &local_err); - vm_state_size = qemu_ftell(f); - qemu_fclose(f); - if (ret < 0) { - monitor_printf(mon, "%s\n", error_get_pretty(local_err)); - error_free(local_err); - goto the_end; - } - - /* create the snapshots */ - - bs1 = NULL; - while ((bs1 = bdrv_next(bs1))) { - if (bdrv_can_snapshot(bs1)) { - /* Write VM state size only to the image that contains the state */ - sn->vm_state_size = (bs == bs1 ? vm_state_size : 0); - ret = bdrv_snapshot_create(bs1, sn); - if (ret < 0) { - monitor_printf(mon, "Error while creating snapshot on '%s'\n", - bdrv_get_device_name(bs1)); - } - } - } - - the_end: - if (saved_vm_running) { - vm_start(); - } -} - -void qmp_xen_save_devices_state(const char *filename, Error **errp) -{ - QEMUFile *f; - int saved_vm_running; - int ret; - - saved_vm_running = runstate_is_running(); - vm_stop(RUN_STATE_SAVE_VM); - - f = qemu_fopen(filename, "wb"); - if (!f) { - error_setg_file_open(errp, errno, filename); - goto the_end; - } - ret = qemu_save_device_state(f); - qemu_fclose(f); - if (ret < 0) { - error_set(errp, QERR_IO_ERROR); - } - - the_end: - if (saved_vm_running) { - vm_start(); - } -} - -int load_vmstate(const char *name) -{ - BlockDriverState *bs, *bs_vm_state; - QEMUSnapshotInfo sn; - QEMUFile *f; - int ret; - - bs_vm_state = find_vmstate_bs(); - if (!bs_vm_state) { - error_report("No block device supports snapshots"); - return -ENOTSUP; - } - - /* Don't even try to load empty VM states */ - ret = bdrv_snapshot_find(bs_vm_state, &sn, name); - if (ret < 0) { - return ret; - } else if (sn.vm_state_size == 0) { - error_report("This is a disk-only snapshot. Revert to it offline " - "using qemu-img."); - return -EINVAL; - } - - /* Verify if there is any device that doesn't support snapshots and is - writable and check if the requested snapshot is available too. */ - bs = NULL; - while ((bs = bdrv_next(bs))) { - - if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) { - continue; - } - - if (!bdrv_can_snapshot(bs)) { - error_report("Device '%s' is writable but does not support snapshots.", - bdrv_get_device_name(bs)); - return -ENOTSUP; - } - - ret = bdrv_snapshot_find(bs, &sn, name); - if (ret < 0) { - error_report("Device '%s' does not have the requested snapshot '%s'", - bdrv_get_device_name(bs), name); - return ret; - } - } - - /* Flush all IO requests so they don't interfere with the new state. */ - bdrv_drain_all(); - - bs = NULL; - while ((bs = bdrv_next(bs))) { - if (bdrv_can_snapshot(bs)) { - ret = bdrv_snapshot_goto(bs, name); - if (ret < 0) { - error_report("Error %d while activating snapshot '%s' on '%s'", - ret, name, bdrv_get_device_name(bs)); - return ret; - } - } - } - - /* restore the VM state */ - f = qemu_fopen_bdrv(bs_vm_state, 0); - if (!f) { - error_report("Could not open VM state file"); - return -EINVAL; - } - - qemu_system_reset(VMRESET_SILENT); - ret = qemu_loadvm_state(f); - - qemu_fclose(f); - if (ret < 0) { - error_report("Error %d while loading VM state", ret); - return ret; - } - - return 0; -} - -void hmp_delvm(Monitor *mon, const QDict *qdict) -{ - BlockDriverState *bs; - Error *err; - const char *name = qdict_get_str(qdict, "name"); - - if (!find_vmstate_bs()) { - monitor_printf(mon, "No block device supports snapshots\n"); - return; - } - - bs = NULL; - while ((bs = bdrv_next(bs))) { - if (bdrv_can_snapshot(bs)) { - err = NULL; - bdrv_snapshot_delete_by_id_or_name(bs, name, &err); - if (err) { - monitor_printf(mon, - "Error while deleting snapshot on device '%s':" - " %s\n", - bdrv_get_device_name(bs), - error_get_pretty(err)); - error_free(err); - } - } - } -} - -void hmp_info_snapshots(Monitor *mon, const QDict *qdict) -{ - BlockDriverState *bs, *bs1; - QEMUSnapshotInfo *sn_tab, *sn, s, *sn_info = &s; - int nb_sns, i, ret, available; - int total; - int *available_snapshots; - - bs = find_vmstate_bs(); - if (!bs) { - monitor_printf(mon, "No available block device supports snapshots\n"); - return; - } - - nb_sns = bdrv_snapshot_list(bs, &sn_tab); - if (nb_sns < 0) { - monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns); - return; - } - - if (nb_sns == 0) { - monitor_printf(mon, "There is no snapshot available.\n"); - return; - } - - available_snapshots = g_malloc0(sizeof(int) * nb_sns); - total = 0; - for (i = 0; i < nb_sns; i++) { - sn = &sn_tab[i]; - available = 1; - bs1 = NULL; - - while ((bs1 = bdrv_next(bs1))) { - if (bdrv_can_snapshot(bs1) && bs1 != bs) { - ret = bdrv_snapshot_find(bs1, sn_info, sn->id_str); - if (ret < 0) { - available = 0; - break; - } - } - } - - if (available) { - available_snapshots[total] = i; - total++; - } - } - - if (total > 0) { - bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); - monitor_printf(mon, "\n"); - for (i = 0; i < total; i++) { - sn = &sn_tab[available_snapshots[i]]; - bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, sn); - monitor_printf(mon, "\n"); - } - } else { - monitor_printf(mon, "There is no suitable snapshot available\n"); - } - - g_free(sn_tab); - g_free(available_snapshots); - -} - -void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev) -{ - qemu_ram_set_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK, - memory_region_name(mr), dev); -} - -void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev) -{ - qemu_ram_unset_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK); -} - -void vmstate_register_ram_global(MemoryRegion *mr) -{ - vmstate_register_ram(mr, NULL); -} diff --git a/trace-events b/trace-events index 450022d..6c9e33f 100644 --- a/trace-events +++ b/trace-events @@ -1167,7 +1167,7 @@ vmware_scratch_read(uint32_t index, uint32_t value) "index %d, value 0x%x" vmware_scratch_write(uint32_t index, uint32_t value) "index %d, value 0x%x" vmware_setmode(uint32_t w, uint32_t h, uint32_t bpp) "%dx%d @ %d bpp" -# savevm.c +# migration/savevm.c qemu_loadvm_state_section(unsigned int section_type) "%d" qemu_loadvm_state_section_partend(uint32_t section_id) "%u" qemu_loadvm_state_section_startfull(uint32_t section_id, const char *idstr, uint32_t instance_id, uint32_t version_id) "%u(%s) %u %u" -- 1.8.3.1