Merge remote-tracking branch 'sstabellini/saverestore-8' into staging

* sstabellini/saverestore-8:
  xen: do not allocate RAM during INMIGRATE runstate
  xen mapcache: check if memory region has moved.
  xen: record physmap changes to xenstore
  Set runstate to INMIGRATE earlier
  Introduce "xen-save-devices-state"
  cirrus_vga: do not reset videoram

Conflicts:
	qapi-schema.json

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

docs/xen-save-devices-state.txt

@@ -0,0 +1,34 @@
+= Save Devices =
+
+QEMU has code to load/save the state of the guest that it is running.
+These are two complementary operations.  Saving the state just does
+that, saves the state for each device that the guest is running.
+
+These operations are normally used with migration (see migration.txt),
+however it is also possible to save the state of all devices to file,
+without saving the RAM or the block devices of the VM.
+
+This operation is called "xen-save-devices-state" (see
+QMP/qmp-commands.txt)
+
+
+The binary format used in the file is the following:
+
+
+-------------------------------------------
+
+32 bit big endian: QEMU_VM_FILE_MAGIC
+32 bit big endian: QEMU_VM_FILE_VERSION
+
+for_each_device
+{
+    8 bit:              QEMU_VM_SECTION_FULL
+    32 bit big endian:  section_id
+    8 bit:              idstr (ID string) length
+    string:             idstr (ID string)
+    32 bit big endian:  instance_id
+    32 bit big endian:  version_id
+    buffer:             device specific data
+}
+
+8 bit: QEMU_VM_EOF

hw/cirrus_vga.c

@@ -2767,10 +2767,6 @@ static void cirrus_reset(void *opaque)
     }
     s->vga.cr[0x27] = s->device_id;
 
-    /* Win2K seems to assume that the pattern buffer is at 0xff
-       initially ! */
-    memset(s->vga.vram_ptr, 0xff, s->real_vram_size);
-
     s->cirrus_hidden_dac_lockindex = 5;
     s->cirrus_hidden_dac_data = 0;
 }

qapi-schema.json

@@ -1684,3 +1684,20 @@
 ##
 { 'command': 'migrate',
   'data': {'uri': 'str', '*blk': 'bool', '*inc': 'bool', '*detach': 'bool' } }
+
+# @xen-save-devices-state:
+#
+# Save the state of all devices to file. The RAM and the block devices
+# of the VM are not saved by this command.
+#
+# @filename: the file to save the state of the devices to as binary
+# data. See xen-save-devices-state.txt for a description of the binary
+# format.
+#
+# Returns: Nothing on success
+#          If @filename cannot be opened, OpenFileFailed
+#          If an I/O error occurs while writing the file, IOError
+#
+# Since: 1.1
+##
+{ 'command': 'xen-save-devices-state', 'data': {'filename': 'str'} }

qmp-commands.hx

@@ -441,6 +441,33 @@ Example:
 Note: inject-nmi is only supported for x86 guest currently, it will
       returns "Unsupported" error for non-x86 guest.
 
+EQMP
+
+    {
+        .name       = "xen-save-devices-state",
+        .args_type  = "filename:F",
+    .mhandler.cmd_new = qmp_marshal_input_xen_save_devices_state,
+    },
+
+SQMP
+xen-save-devices-state
+-------
+
+Save the state of all devices to file. The RAM and the block devices
+of the VM are not saved by this command.
+
+Arguments:
+
+- "filename": the file to save the state of the devices to as binary
+data. See xen-save-devices-state.txt for a description of the binary
+format.
+
+Example:
+
+-> { "execute": "xen-save-devices-state",
+     "arguments": { "filename": "/tmp/save" } }
+<- { "return": {} }
+
 EQMP
 
     {

savevm.c

@@ -84,6 +84,7 @@
 #include "qemu-timer.h"
 #include "cpus.h"
 #include "memory.h"
+#include "qmp-commands.h"
 
 #define SELF_ANNOUNCE_ROUNDS 5
 
@@ -1177,6 +1178,7 @@ typedef struct SaveStateEntry {
     void *opaque;
     CompatEntry *compat;
     int no_migrate;
+    int is_ram;
 } SaveStateEntry;
 
 
@@ -1241,6 +1243,10 @@ int register_savevm_live(DeviceState *dev,
     se->opaque = opaque;
     se->vmsd = NULL;
     se->no_migrate = 0;
+    /* if this is a live_savem then set is_ram */
+    if (save_live_state != NULL) {
+        se->is_ram = 1;
+    }
 
     if (dev && dev->parent_bus && dev->parent_bus->info->get_dev_path) {
         char *id = dev->parent_bus->info->get_dev_path(dev);
@@ -1728,6 +1734,45 @@ out:
     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->save_state == NULL && se->vmsd == NULL) {
+            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);
+    }
+
+    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;
@@ -2109,6 +2154,32 @@ void do_savevm(Monitor *mon, const QDict *qdict)
         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_set(errp, QERR_OPEN_FILE_FAILED, 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();
+    return;
+}
+
 int load_vmstate(const char *name)
 {
     BlockDriverState *bs, *bs_vm_state;

vl.c

@@ -3099,6 +3099,7 @@ int main(int argc, char **argv, char **envp)
                 break;
             case QEMU_OPTION_incoming:
                 incoming = optarg;
+                runstate_set(RUN_STATE_INMIGRATE);
                 break;
             case QEMU_OPTION_nodefaults:
                 default_serial = 0;
@@ -3616,7 +3617,6 @@ int main(int argc, char **argv, char **envp)
     }
 
     if (incoming) {
-        runstate_set(RUN_STATE_INMIGRATE);
         int ret = qemu_start_incoming_migration(incoming);
         if (ret < 0) {
             fprintf(stderr, "Migration failed. Exit code %s(%d), exiting.\n",

xen-all.c

@@ -65,7 +65,7 @@ static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu)
 typedef struct XenPhysmap {
     target_phys_addr_t start_addr;
     ram_addr_t size;
-    MemoryRegion *mr;
+    char *name;
     target_phys_addr_t phys_offset;
 
     QLIST_ENTRY(XenPhysmap) list;
@@ -190,6 +190,14 @@ void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr)
     xen_pfn_t *pfn_list;
     int i;
 
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        /* RAM already populated in Xen */
+        fprintf(stderr, "%s: do not alloc "RAM_ADDR_FMT
+                " bytes of ram at "RAM_ADDR_FMT" when runstate is INMIGRATE\n",
+                __func__, size, ram_addr); 
+        return;
+    }
+
     if (mr == &ram_memory) {
         return;
     }
@@ -225,6 +233,22 @@ static XenPhysmap *get_physmapping(XenIOState *state,
     return NULL;
 }
 
+static target_phys_addr_t xen_phys_offset_to_gaddr(target_phys_addr_t start_addr,
+                                                   ram_addr_t size, void *opaque)
+{
+    target_phys_addr_t addr = start_addr & TARGET_PAGE_MASK;
+    XenIOState *xen_io_state = opaque;
+    XenPhysmap *physmap = NULL;
+
+    QLIST_FOREACH(physmap, &xen_io_state->physmap, list) {
+        if (range_covers_byte(physmap->phys_offset, physmap->size, addr)) {
+            return physmap->start_addr;
+        }
+    }
+
+    return start_addr;
+}
+
 #if CONFIG_XEN_CTRL_INTERFACE_VERSION >= 340
 static int xen_add_to_physmap(XenIOState *state,
                               target_phys_addr_t start_addr,
@@ -237,6 +261,7 @@ static int xen_add_to_physmap(XenIOState *state,
     XenPhysmap *physmap = NULL;
     target_phys_addr_t pfn, start_gpfn;
     target_phys_addr_t phys_offset = memory_region_get_ram_addr(mr);
+    char path[80], value[17];
 
     if (get_physmapping(state, start_addr, size)) {
         return 0;
@@ -275,6 +300,7 @@ go_physmap:
 
     physmap->start_addr = start_addr;
     physmap->size = size;
+    physmap->name = (char *)mr->name;
     physmap->phys_offset = phys_offset;
 
     QLIST_INSERT_HEAD(&state->physmap, physmap, list);
@@ -283,6 +309,30 @@ go_physmap:
                                    start_addr >> TARGET_PAGE_BITS,
                                    (start_addr + size) >> TARGET_PAGE_BITS,
                                    XEN_DOMCTL_MEM_CACHEATTR_WB);
+
+    snprintf(path, sizeof(path),
+            "/local/domain/0/device-model/%d/physmap/%"PRIx64"/start_addr",
+            xen_domid, (uint64_t)phys_offset);
+    snprintf(value, sizeof(value), "%"PRIx64, (uint64_t)start_addr);
+    if (!xs_write(state->xenstore, 0, path, value, strlen(value))) {
+        return -1;
+    }
+    snprintf(path, sizeof(path),
+            "/local/domain/0/device-model/%d/physmap/%"PRIx64"/size",
+            xen_domid, (uint64_t)phys_offset);
+    snprintf(value, sizeof(value), "%"PRIx64, (uint64_t)size);
+    if (!xs_write(state->xenstore, 0, path, value, strlen(value))) {
+        return -1;
+    }
+    if (mr->name) {
+        snprintf(path, sizeof(path),
+                "/local/domain/0/device-model/%d/physmap/%"PRIx64"/name",
+                xen_domid, (uint64_t)phys_offset);
+        if (!xs_write(state->xenstore, 0, path, mr->name, strlen(mr->name))) {
+            return -1;
+        }
+    }
+
     return 0;
 }
 
@@ -942,6 +992,55 @@ int xen_init(void)
     return 0;
 }
 
+static void xen_read_physmap(XenIOState *state)
+{
+    XenPhysmap *physmap = NULL;
+    unsigned int len, num, i;
+    char path[80], *value = NULL;
+    char **entries = NULL;
+
+    snprintf(path, sizeof(path),
+            "/local/domain/0/device-model/%d/physmap", xen_domid);
+    entries = xs_directory(state->xenstore, 0, path, &num);
+    if (entries == NULL)
+        return;
+
+    for (i = 0; i < num; i++) {
+        physmap = g_malloc(sizeof (XenPhysmap));
+        physmap->phys_offset = strtoull(entries[i], NULL, 16);
+        snprintf(path, sizeof(path),
+                "/local/domain/0/device-model/%d/physmap/%s/start_addr",
+                xen_domid, entries[i]);
+        value = xs_read(state->xenstore, 0, path, &len);
+        if (value == NULL) {
+            free(physmap);
+            continue;
+        }
+        physmap->start_addr = strtoull(value, NULL, 16);
+        free(value);
+
+        snprintf(path, sizeof(path),
+                "/local/domain/0/device-model/%d/physmap/%s/size",
+                xen_domid, entries[i]);
+        value = xs_read(state->xenstore, 0, path, &len);
+        if (value == NULL) {
+            free(physmap);
+            continue;
+        }
+        physmap->size = strtoull(value, NULL, 16);
+        free(value);
+
+        snprintf(path, sizeof(path),
+                "/local/domain/0/device-model/%d/physmap/%s/name",
+                xen_domid, entries[i]);
+        physmap->name = xs_read(state->xenstore, 0, path, &len);
+
+        QLIST_INSERT_HEAD(&state->physmap, physmap, list);
+    }
+    free(entries);
+    return;
+}
+
 int xen_hvm_init(void)
 {
     int i, rc;
@@ -999,7 +1098,7 @@ int xen_hvm_init(void)
     }
 
     /* Init RAM management */
-    xen_map_cache_init();
+    xen_map_cache_init(xen_phys_offset_to_gaddr, state);
     xen_ram_init(ram_size);
 
     qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state);
@@ -1017,6 +1116,7 @@ int xen_hvm_init(void)
     xen_be_register("console", &xen_console_ops);
     xen_be_register("vkbd", &xen_kbdmouse_ops);
     xen_be_register("qdisk", &xen_blkdev_ops);
+    xen_read_physmap(state);
 
     return 0;
 }

xen-mapcache.c

@@ -78,6 +78,9 @@ typedef struct MapCache {
     uint8_t *last_address_vaddr;
     unsigned long max_mcache_size;
     unsigned int mcache_bucket_shift;
+
+    phys_offset_to_gaddr_t phys_offset_to_gaddr;
+    void *opaque;
 } MapCache;
 
 static MapCache *mapcache;
@@ -91,13 +94,16 @@ static inline int test_bits(int nr, int size, const unsigned long *addr)
         return 0;
 }
 
-void xen_map_cache_init(void)
+void xen_map_cache_init(phys_offset_to_gaddr_t f, void *opaque)
 {
     unsigned long size;
     struct rlimit rlimit_as;
 
     mapcache = g_malloc0(sizeof (MapCache));
 
+    mapcache->phys_offset_to_gaddr = f;
+    mapcache->opaque = opaque;
+
     QTAILQ_INIT(&mapcache->locked_entries);
     mapcache->last_address_index = -1;
 
@@ -193,9 +199,14 @@ uint8_t *xen_map_cache(target_phys_addr_t phys_addr, target_phys_addr_t size,
                        uint8_t lock)
 {
     MapCacheEntry *entry, *pentry = NULL;
-    target_phys_addr_t address_index  = phys_addr >> MCACHE_BUCKET_SHIFT;
+    target_phys_addr_t address_index;
-    target_phys_addr_t address_offset = phys_addr & (MCACHE_BUCKET_SIZE - 1);
+    target_phys_addr_t address_offset;
     target_phys_addr_t __size = size;
+    bool translated = false;
+
+tryagain:
+    address_index  = phys_addr >> MCACHE_BUCKET_SHIFT;
+    address_offset = phys_addr & (MCACHE_BUCKET_SIZE - 1);
 
     trace_xen_map_cache(phys_addr);
 
@@ -237,6 +248,11 @@ uint8_t *xen_map_cache(target_phys_addr_t phys_addr, target_phys_addr_t size,
     if(!test_bits(address_offset >> XC_PAGE_SHIFT, size >> XC_PAGE_SHIFT,
                 entry->valid_mapping)) {
         mapcache->last_address_index = -1;
+        if (!translated && mapcache->phys_offset_to_gaddr) {
+            phys_addr = mapcache->phys_offset_to_gaddr(phys_addr, size, mapcache->opaque);
+            translated = true;
+            goto tryagain;
+        }
         trace_xen_map_cache_return(NULL);
         return NULL;
     }

xen-mapcache.h

@@ -11,9 +11,13 @@
 
 #include <stdlib.h>
 
+typedef target_phys_addr_t (*phys_offset_to_gaddr_t)(target_phys_addr_t start_addr,
+                                                     ram_addr_t size,
+                                                     void *opaque);
 #ifdef CONFIG_XEN
 
-void xen_map_cache_init(void);
+void xen_map_cache_init(phys_offset_to_gaddr_t f,
+                        void *opaque);
 uint8_t *xen_map_cache(target_phys_addr_t phys_addr, target_phys_addr_t size,
                        uint8_t lock);
 ram_addr_t xen_ram_addr_from_mapcache(void *ptr);
@@ -22,7 +26,8 @@ void xen_invalidate_map_cache(void);
 
 #else
 
-static inline void xen_map_cache_init(void)
+static inline void xen_map_cache_init(phys_offset_to_gaddr_t f,
+                                      void *opaque)
 {
 }