Merge tag 'migration-20230420-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request (take 2)

Remove the two atomic patches that broke mips32.

Please, apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmRGYTkACgkQ9IfvGFhy
# 1yMD5RAApL8bJTMpmkZ8afxG124/CID7fvg/WMp3vOTG/6923XZHfosUwqrCCvzN
# 8qfSfOl4P5Gtv1dOU+ZBcgoFS3tj00Ud2YhcZiSVUy5LZPJNJEfv4YzIErDTJq3I
# wcv/CgHvK1CKJ5DZ1g9hqnRvw9qYiodDEHS7UxvhGzckFExHps2oWt9nDuEZefKV
# XptOX7YDFYmWE87fp8+rQMYGZEN/6Cc7p4HmSt9I11CgLbeaqTpmKuwTv89PU9qV
# 7/X9kfoHNsKsVKw5WosEdRvEqhVQbvcCCxq+TGpeQz6d5U2mY7RVxQSNJxXNdD3P
# uz7uannx+UhESgzf5GnwOMIcxWD6UMAcDt349IAWFbq5d1QGaXJ9fVVHVJDV1Irl
# XHqxkugNMxRVZ8hQy5gSE6UTpeIjkIpSoZGnGS7E/iLMZHZBgv7s5VK21mYxn/QF
# F9g3Ewo2lF+kpQ/ZEnQ9mFyCYtqOHOAOLAUa7/6WdGnUMuqQ47Fh+jbb+KdEyCLg
# l7yXk2gXAb8SN6957Tlvo9okOB4NzhDPDXgvewAG/1yW4zL9hA+YCMvEvy90N8Be
# rRKO7H9YlsW4wKjA//i2YNAbtaZN5+zeAS39m0exYmXA54AMufjWq/a7Ya/ix5Jo
# 452LEz5hA4ckXXtP715pKQjqafxWXbHSS1qw9LBfMYr5TEEWC6c=
# =JTxg
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 24 Apr 2023 12:00:09 PM BST
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [undefined]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20230420-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: Pass migrate_caps_check() the old and new caps
  migration: rename enabled_capabilities to capabilities
  migration/postcopy: Detect file system on dest host
  vl.c: Create late backends before migration object
  util/mmap-alloc: qemu_fd_getfs()
  migration: Handle block device inactivation failures better
  migration: Rename normal to normal_pages
  migration: Rename duplicate to zero_pages
  migration: Make postcopy_requests atomic
  migration: Make dirty_sync_count atomic
  migration: Make downtime_bytes atomic
  migration: Make precopy_bytes atomic
  migration: Make dirty_sync_missed_zero_copy atomic
  migration: Make multifd_bytes atomic
  migration: Update atomic stats out of the mutex
  migration: Merge ram_counters and ram_atomic_counters
  migration: remove extra whitespace character for code style

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

include/qemu/mmap-alloc.h

@@ -1,8 +1,15 @@
 #ifndef QEMU_MMAP_ALLOC_H
 #define QEMU_MMAP_ALLOC_H
 
+typedef enum {
+    QEMU_FS_TYPE_UNKNOWN = 0,
+    QEMU_FS_TYPE_TMPFS,
+    QEMU_FS_TYPE_HUGETLBFS,
+    QEMU_FS_TYPE_NUM,
+} QemuFsType;
 
 size_t qemu_fd_getpagesize(int fd);
+QemuFsType qemu_fd_getfs(int fd);
 
 /**
  * qemu_ram_mmap: mmap anonymous memory, the specified file or device.

migration/migration.c

@@ -364,8 +364,7 @@ static bool migrate_late_block_activate(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[
-        MIGRATION_CAPABILITY_LATE_BLOCK_ACTIVATE];
+    return s->capabilities[MIGRATION_CAPABILITY_LATE_BLOCK_ACTIVATE];
 }
 
 /*
@@ -944,7 +943,7 @@ MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp)
 #endif
         caps = g_malloc0(sizeof(*caps));
         caps->capability = i;
-        caps->state = s->enabled_capabilities[i];
+        caps->state = s->capabilities[i];
         QAPI_LIST_APPEND(tail, caps);
     }
 
@@ -1140,24 +1139,26 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
     size_t page_size = qemu_target_page_size();
 
     info->ram = g_malloc0(sizeof(*info->ram));
-    info->ram->transferred = stat64_get(&ram_atomic_counters.transferred);
+    info->ram->transferred = stat64_get(&ram_counters.transferred);
     info->ram->total = ram_bytes_total();
-    info->ram->duplicate = stat64_get(&ram_atomic_counters.duplicate);
+    info->ram->duplicate = stat64_get(&ram_counters.zero_pages);
     /* legacy value.  It is not used anymore */
     info->ram->skipped = 0;
-    info->ram->normal = stat64_get(&ram_atomic_counters.normal);
+    info->ram->normal = stat64_get(&ram_counters.normal_pages);
     info->ram->normal_bytes = info->ram->normal * page_size;
     info->ram->mbps = s->mbps;
-    info->ram->dirty_sync_count = ram_counters.dirty_sync_count;
+    info->ram->dirty_sync_count =
+        stat64_get(&ram_counters.dirty_sync_count);
     info->ram->dirty_sync_missed_zero_copy =
-            ram_counters.dirty_sync_missed_zero_copy;
-    info->ram->postcopy_requests = ram_counters.postcopy_requests;
+        stat64_get(&ram_counters.dirty_sync_missed_zero_copy);
+    info->ram->postcopy_requests =
+        stat64_get(&ram_counters.postcopy_requests);
     info->ram->page_size = page_size;
-    info->ram->multifd_bytes = ram_counters.multifd_bytes;
+    info->ram->multifd_bytes = stat64_get(&ram_counters.multifd_bytes);
     info->ram->pages_per_second = s->pages_per_second;
-    info->ram->precopy_bytes = ram_counters.precopy_bytes;
-    info->ram->downtime_bytes = ram_counters.downtime_bytes;
-    info->ram->postcopy_bytes = stat64_get(&ram_atomic_counters.postcopy_bytes);
+    info->ram->precopy_bytes = stat64_get(&ram_counters.precopy_bytes);
+    info->ram->downtime_bytes = stat64_get(&ram_counters.downtime_bytes);
+    info->ram->postcopy_bytes = stat64_get(&ram_counters.postcopy_bytes);
 
     if (migrate_use_xbzrle()) {
         info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache));
@@ -1298,30 +1299,20 @@ WriteTrackingSupport migrate_query_write_tracking(void)
 }
 
 /**
- * @migration_caps_check - check capability validity
+ * @migration_caps_check - check capability compatibility
  *
- * @cap_list: old capability list, array of bool
- * @params: new capabilities to be applied soon
+ * @old_caps: old capability list
+ * @new_caps: new capability list
  * @errp: set *errp if the check failed, with reason
  *
  * Returns true if check passed, otherwise false.
  */
-static bool migrate_caps_check(bool *cap_list,
-                               MigrationCapabilityStatusList *params,
-                               Error **errp)
+static bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
 {
-    MigrationCapabilityStatusList *cap;
-    bool old_postcopy_cap;
     MigrationIncomingState *mis = migration_incoming_get_current();
 
-    old_postcopy_cap = cap_list[MIGRATION_CAPABILITY_POSTCOPY_RAM];
-
-    for (cap = params; cap; cap = cap->next) {
-        cap_list[cap->value->capability] = cap->value->state;
-    }
-
 #ifndef CONFIG_LIVE_BLOCK_MIGRATION
-    if (cap_list[MIGRATION_CAPABILITY_BLOCK]) {
+    if (new_caps[MIGRATION_CAPABILITY_BLOCK]) {
         error_setg(errp, "QEMU compiled without old-style (blk/-b, inc/-i) "
                    "block migration");
         error_append_hint(errp, "Use drive_mirror+NBD instead.\n");
@@ -1330,7 +1321,7 @@ static bool migrate_caps_check(bool *cap_list,
 #endif
 
 #ifndef CONFIG_REPLICATION
-    if (cap_list[MIGRATION_CAPABILITY_X_COLO]) {
+    if (new_caps[MIGRATION_CAPABILITY_X_COLO]) {
         error_setg(errp, "QEMU compiled without replication module"
                    " can't enable COLO");
         error_append_hint(errp, "Please enable replication before COLO.\n");
@@ -1338,12 +1329,13 @@ static bool migrate_caps_check(bool *cap_list,
     }
 #endif
 
-    if (cap_list[MIGRATION_CAPABILITY_POSTCOPY_RAM]) {
+    if (new_caps[MIGRATION_CAPABILITY_POSTCOPY_RAM]) {
         /* This check is reasonably expensive, so only when it's being
          * set the first time, also it's only the destination that needs
          * special support.
          */
-        if (!old_postcopy_cap && runstate_check(RUN_STATE_INMIGRATE) &&
+        if (!old_caps[MIGRATION_CAPABILITY_POSTCOPY_RAM] &&
+            runstate_check(RUN_STATE_INMIGRATE) &&
             !postcopy_ram_supported_by_host(mis)) {
             /* postcopy_ram_supported_by_host will have emitted a more
              * detailed message
@@ -1352,13 +1344,13 @@ static bool migrate_caps_check(bool *cap_list,
             return false;
         }
 
-        if (cap_list[MIGRATION_CAPABILITY_X_IGNORE_SHARED]) {
+        if (new_caps[MIGRATION_CAPABILITY_X_IGNORE_SHARED]) {
             error_setg(errp, "Postcopy is not compatible with ignore-shared");
             return false;
         }
     }
 
-    if (cap_list[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT]) {
+    if (new_caps[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT]) {
         WriteTrackingSupport wt_support;
         int idx;
         /*
@@ -1382,7 +1374,7 @@ static bool migrate_caps_check(bool *cap_list,
          */
         for (idx = 0; idx < check_caps_background_snapshot.size; idx++) {
             int incomp_cap = check_caps_background_snapshot.caps[idx];
-            if (cap_list[incomp_cap]) {
+            if (new_caps[incomp_cap]) {
                 error_setg(errp,
                         "Background-snapshot is not compatible with %s",
                         MigrationCapability_str(incomp_cap));
@@ -1392,10 +1384,10 @@ static bool migrate_caps_check(bool *cap_list,
     }
 
 #ifdef CONFIG_LINUX
-    if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND] &&
-        (!cap_list[MIGRATION_CAPABILITY_MULTIFD] ||
-         cap_list[MIGRATION_CAPABILITY_COMPRESS] ||
-         cap_list[MIGRATION_CAPABILITY_XBZRLE] ||
+    if (new_caps[MIGRATION_CAPABILITY_ZERO_COPY_SEND] &&
+        (!new_caps[MIGRATION_CAPABILITY_MULTIFD] ||
+         new_caps[MIGRATION_CAPABILITY_COMPRESS] ||
+         new_caps[MIGRATION_CAPABILITY_XBZRLE] ||
          migrate_multifd_compression() ||
          migrate_use_tls())) {
         error_setg(errp,
@@ -1403,15 +1395,15 @@ static bool migrate_caps_check(bool *cap_list,
         return false;
     }
 #else
-    if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND]) {
+    if (new_caps[MIGRATION_CAPABILITY_ZERO_COPY_SEND]) {
         error_setg(errp,
                    "Zero copy currently only available on Linux");
         return false;
     }
 #endif
 
-    if (cap_list[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT]) {
-        if (!cap_list[MIGRATION_CAPABILITY_POSTCOPY_RAM]) {
+    if (new_caps[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT]) {
+        if (!new_caps[MIGRATION_CAPABILITY_POSTCOPY_RAM]) {
             error_setg(errp, "Postcopy preempt requires postcopy-ram");
             return false;
         }
@@ -1422,14 +1414,14 @@ static bool migrate_caps_check(bool *cap_list,
          * different compression channels, which is not compatible with the
          * preempt assumptions on channel assignments.
          */
-        if (cap_list[MIGRATION_CAPABILITY_COMPRESS]) {
+        if (new_caps[MIGRATION_CAPABILITY_COMPRESS]) {
             error_setg(errp, "Postcopy preempt not compatible with compress");
             return false;
         }
     }
 
-    if (cap_list[MIGRATION_CAPABILITY_MULTIFD]) {
-        if (cap_list[MIGRATION_CAPABILITY_COMPRESS]) {
+    if (new_caps[MIGRATION_CAPABILITY_MULTIFD]) {
+        if (new_caps[MIGRATION_CAPABILITY_COMPRESS]) {
             error_setg(errp, "Multifd is not compatible with compress");
             return false;
         }
@@ -1485,20 +1477,24 @@ void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
 {
     MigrationState *s = migrate_get_current();
     MigrationCapabilityStatusList *cap;
-    bool cap_list[MIGRATION_CAPABILITY__MAX];
+    bool new_caps[MIGRATION_CAPABILITY__MAX];
 
     if (migration_is_running(s->state)) {
         error_setg(errp, QERR_MIGRATION_ACTIVE);
         return;
     }
 
-    memcpy(cap_list, s->enabled_capabilities, sizeof(cap_list));
-    if (!migrate_caps_check(cap_list, params, errp)) {
+    memcpy(new_caps, s->capabilities, sizeof(new_caps));
+    for (cap = params; cap; cap = cap->next) {
+        new_caps[cap->value->capability] = cap->value->state;
+    }
+
+    if (!migrate_caps_check(s->capabilities, new_caps, errp)) {
         return;
     }
 
     for (cap = params; cap; cap = cap->next) {
-        s->enabled_capabilities[cap->value->capability] = cap->value->state;
+        s->capabilities[cap->value->capability] = cap->value->state;
     }
 }
 
@@ -2567,7 +2563,7 @@ bool migrate_release_ram(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_RELEASE_RAM];
+    return s->capabilities[MIGRATION_CAPABILITY_RELEASE_RAM];
 }
 
 bool migrate_postcopy_ram(void)
@@ -2576,7 +2572,7 @@ bool migrate_postcopy_ram(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_POSTCOPY_RAM];
+    return s->capabilities[MIGRATION_CAPABILITY_POSTCOPY_RAM];
 }
 
 bool migrate_postcopy(void)
@@ -2590,7 +2586,7 @@ bool migrate_auto_converge(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
+    return s->capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
 }
 
 bool migrate_zero_blocks(void)
@@ -2599,7 +2595,7 @@ bool migrate_zero_blocks(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_BLOCKS];
+    return s->capabilities[MIGRATION_CAPABILITY_ZERO_BLOCKS];
 }
 
 bool migrate_postcopy_blocktime(void)
@@ -2608,7 +2604,7 @@ bool migrate_postcopy_blocktime(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_POSTCOPY_BLOCKTIME];
+    return s->capabilities[MIGRATION_CAPABILITY_POSTCOPY_BLOCKTIME];
 }
 
 bool migrate_use_compression(void)
@@ -2617,7 +2613,7 @@ bool migrate_use_compression(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_COMPRESS];
+    return s->capabilities[MIGRATION_CAPABILITY_COMPRESS];
 }
 
 int migrate_compress_level(void)
@@ -2662,7 +2658,7 @@ bool migrate_dirty_bitmaps(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_DIRTY_BITMAPS];
+    return s->capabilities[MIGRATION_CAPABILITY_DIRTY_BITMAPS];
 }
 
 bool migrate_ignore_shared(void)
@@ -2671,7 +2667,7 @@ bool migrate_ignore_shared(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_X_IGNORE_SHARED];
+    return s->capabilities[MIGRATION_CAPABILITY_X_IGNORE_SHARED];
 }
 
 bool migrate_validate_uuid(void)
@@ -2680,7 +2676,7 @@ bool migrate_validate_uuid(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_VALIDATE_UUID];
+    return s->capabilities[MIGRATION_CAPABILITY_VALIDATE_UUID];
 }
 
 bool migrate_use_events(void)
@@ -2689,7 +2685,7 @@ bool migrate_use_events(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_EVENTS];
+    return s->capabilities[MIGRATION_CAPABILITY_EVENTS];
 }
 
 bool migrate_use_multifd(void)
@@ -2698,7 +2694,7 @@ bool migrate_use_multifd(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_MULTIFD];
+    return s->capabilities[MIGRATION_CAPABILITY_MULTIFD];
 }
 
 bool migrate_pause_before_switchover(void)
@@ -2707,8 +2703,7 @@ bool migrate_pause_before_switchover(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[
-        MIGRATION_CAPABILITY_PAUSE_BEFORE_SWITCHOVER];
+    return s->capabilities[MIGRATION_CAPABILITY_PAUSE_BEFORE_SWITCHOVER];
 }
 
 int migrate_multifd_channels(void)
@@ -2755,7 +2750,7 @@ bool migrate_use_zero_copy_send(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_COPY_SEND];
+    return s->capabilities[MIGRATION_CAPABILITY_ZERO_COPY_SEND];
 }
 #endif
 
@@ -2774,7 +2769,7 @@ int migrate_use_xbzrle(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
+    return s->capabilities[MIGRATION_CAPABILITY_XBZRLE];
 }
 
 uint64_t migrate_xbzrle_cache_size(void)
@@ -2801,7 +2796,7 @@ bool migrate_use_block(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_BLOCK];
+    return s->capabilities[MIGRATION_CAPABILITY_BLOCK];
 }
 
 bool migrate_use_return_path(void)
@@ -2810,7 +2805,7 @@ bool migrate_use_return_path(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_RETURN_PATH];
+    return s->capabilities[MIGRATION_CAPABILITY_RETURN_PATH];
 }
 
 bool migrate_use_block_incremental(void)
@@ -2828,7 +2823,7 @@ bool migrate_background_snapshot(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT];
+    return s->capabilities[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT];
 }
 
 bool migrate_postcopy_preempt(void)
@@ -2837,7 +2832,7 @@ bool migrate_postcopy_preempt(void)
 
     s = migrate_get_current();
 
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT];
+    return s->capabilities[MIGRATION_CAPABILITY_POSTCOPY_PREEMPT];
 }
 
 /* migration thread support */
@@ -3444,13 +3439,11 @@ static void migration_completion(MigrationState *s)
                                             MIGRATION_STATUS_DEVICE);
             }
             if (ret >= 0) {
+                s->block_inactive = inactivate;
                 qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
                 ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
                                                          inactivate);
             }
-            if (inactivate && ret >= 0) {
-                s->block_inactive = true;
-            }
         }
         qemu_mutex_unlock_iothread();
 
@@ -3522,6 +3515,7 @@ fail_invalidate:
         bdrv_activate_all(&local_err);
         if (local_err) {
             error_report_err(local_err);
+            s->block_inactive = true;
         } else {
             s->block_inactive = false;
         }
@@ -3580,7 +3574,7 @@ fail:
 bool migrate_colo_enabled(void)
 {
     MigrationState *s = migrate_get_current();
-    return s->enabled_capabilities[MIGRATION_CAPABILITY_X_COLO];
+    return s->capabilities[MIGRATION_CAPABILITY_X_COLO];
 }
 
 typedef enum MigThrError {
@@ -3778,7 +3772,7 @@ static MigThrError migration_detect_error(MigrationState *s)
 static uint64_t migration_total_bytes(MigrationState *s)
 {
     return qemu_file_total_transferred(s->to_dst_file) +
-        ram_counters.multifd_bytes;
+        stat64_get(&ram_counters.multifd_bytes);
 }
 
 static void migration_calculate_complete(MigrationState *s)
@@ -4443,7 +4437,7 @@ void migration_global_dump(Monitor *mon)
 }
 
 #define DEFINE_PROP_MIG_CAP(name, x)             \
-    DEFINE_PROP_BOOL(name, MigrationState, enabled_capabilities[x], false)
+    DEFINE_PROP_BOOL(name, MigrationState, capabilities[x], false)
 
 static Property migration_properties[] = {
     DEFINE_PROP_BOOL("store-global-state", MigrationState,
@@ -4632,27 +4626,14 @@ static void migration_instance_init(Object *obj)
  */
 static bool migration_object_check(MigrationState *ms, Error **errp)
 {
-    MigrationCapabilityStatusList *head = NULL;
     /* Assuming all off */
-    bool cap_list[MIGRATION_CAPABILITY__MAX] = { 0 }, ret;
-    int i;
+    bool old_caps[MIGRATION_CAPABILITY__MAX] = { 0 };
 
     if (!migrate_params_check(&ms->parameters, errp)) {
         return false;
     }
 
-    for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
-        if (ms->enabled_capabilities[i]) {
-            QAPI_LIST_PREPEND(head, migrate_cap_add(i, true));
-        }
-    }
-
-    ret = migrate_caps_check(cap_list, head, errp);
-
-    /* It works with head == NULL */
-    qapi_free_MigrationCapabilityStatusList(head);
-
-    return ret;
+    return migrate_caps_check(old_caps, ms->capabilities, errp);
 }
 
 static const TypeInfo migration_type = {

migration/migration.h

@@ -310,7 +310,7 @@ struct MigrationState {
     int64_t downtime_start;
     int64_t downtime;
     int64_t expected_downtime;
-    bool enabled_capabilities[MIGRATION_CAPABILITY__MAX];
+    bool capabilities[MIGRATION_CAPABILITY__MAX];
     int64_t setup_time;
     /*
      * Whether guest was running when we enter the completion stage.

migration/multifd.c

@@ -432,9 +432,9 @@ static int multifd_send_pages(QEMUFile *f)
     p->pages = pages;
     transferred = ((uint64_t) pages->num) * p->page_size + p->packet_len;
     qemu_file_acct_rate_limit(f, transferred);
-    ram_counters.multifd_bytes += transferred;
-    stat64_add(&ram_atomic_counters.transferred, transferred);
     qemu_mutex_unlock(&p->mutex);
+    stat64_add(&ram_counters.transferred, transferred);
+    stat64_add(&ram_counters.multifd_bytes, transferred);
     qemu_sem_post(&p->sem);
 
     return 1;
@@ -576,7 +576,7 @@ static int multifd_zero_copy_flush(QIOChannel *c)
         return -1;
     }
     if (ret == 1) {
-        dirty_sync_missed_zero_copy();
+        stat64_add(&ram_counters.dirty_sync_missed_zero_copy, 1);
     }
 
     return ret;
@@ -627,9 +627,9 @@ int multifd_send_sync_main(QEMUFile *f)
         p->flags |= MULTIFD_FLAG_SYNC;
         p->pending_job++;
         qemu_file_acct_rate_limit(f, p->packet_len);
-        ram_counters.multifd_bytes += p->packet_len;
-        stat64_add(&ram_atomic_counters.transferred, p->packet_len);
         qemu_mutex_unlock(&p->mutex);
+        stat64_add(&ram_counters.transferred, p->packet_len);
+        stat64_add(&ram_counters.multifd_bytes, p->packet_len);
         qemu_sem_post(&p->sem);
     }
     for (i = 0; i < migrate_multifd_channels(); i++) {

migration/postcopy-ram.c

@@ -36,6 +36,7 @@
 #include "yank_functions.h"
 #include "tls.h"
 #include "qemu/userfaultfd.h"
+#include "qemu/mmap-alloc.h"
 
 /* Arbitrary limit on size of each discard command,
  * keeps them around ~200 bytes
@@ -336,11 +337,12 @@ static bool ufd_check_and_apply(int ufd, MigrationIncomingState *mis)
 
 /* Callback from postcopy_ram_supported_by_host block iterator.
  */
-static int test_ramblock_postcopiable(RAMBlock *rb, void *opaque)
+static int test_ramblock_postcopiable(RAMBlock *rb)
 {
     const char *block_name = qemu_ram_get_idstr(rb);
     ram_addr_t length = qemu_ram_get_used_length(rb);
     size_t pagesize = qemu_ram_pagesize(rb);
+    QemuFsType fs;
 
     if (length % pagesize) {
         error_report("Postcopy requires RAM blocks to be a page size multiple,"
@@ -348,6 +350,15 @@ static int test_ramblock_postcopiable(RAMBlock *rb, void *opaque)
                      "page size of 0x%zx", block_name, length, pagesize);
         return 1;
     }
+
+    if (rb->fd >= 0) {
+        fs = qemu_fd_getfs(rb->fd);
+        if (fs != QEMU_FS_TYPE_TMPFS && fs != QEMU_FS_TYPE_HUGETLBFS) {
+            error_report("Host backend files need to be TMPFS or HUGETLBFS only");
+            return 1;
+        }
+    }
+
     return 0;
 }
 
@@ -366,6 +377,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
     struct uffdio_range range_struct;
     uint64_t feature_mask;
     Error *local_err = NULL;
+    RAMBlock *block;
 
     if (qemu_target_page_size() > pagesize) {
         error_report("Target page size bigger than host page size");
@@ -390,9 +402,23 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
         goto out;
     }
 
-    /* We don't support postcopy with shared RAM yet */
-    if (foreach_not_ignored_block(test_ramblock_postcopiable, NULL)) {
-        goto out;
+    /*
+     * We don't support postcopy with some type of ramblocks.
+     *
+     * NOTE: we explicitly ignored ramblock_is_ignored() instead we checked
+     * all possible ramblocks.  This is because this function can be called
+     * when creating the migration object, during the phase RAM_MIGRATABLE
+     * is not even properly set for all the ramblocks.
+     *
+     * A side effect of this is we'll also check against RAM_SHARED
+     * ramblocks even if migrate_ignore_shared() is set (in which case
+     * we'll never migrate RAM_SHARED at all), but normally this shouldn't
+     * affect in reality, or we can revisit.
+     */
+    RAMBLOCK_FOREACH(block) {
+        if (test_ramblock_postcopiable(block)) {
+            goto out;
+        }
     }
 
     /*

migration/ram.c

@@ -458,30 +458,18 @@ uint64_t ram_bytes_remaining(void)
                        0;
 }
 
-/*
- * NOTE: not all stats in ram_counters are used in reality.  See comments
- * for struct MigrationAtomicStats.  The ultimate result of ram migration
- * counters will be a merged version with both ram_counters and the atomic
- * fields in ram_atomic_counters.
- */
-MigrationStats ram_counters;
-MigrationAtomicStats ram_atomic_counters;
+RAMStats ram_counters;
 
 void ram_transferred_add(uint64_t bytes)
 {
     if (runstate_is_running()) {
-        ram_counters.precopy_bytes += bytes;
+        stat64_add(&ram_counters.precopy_bytes, bytes);
     } else if (migration_in_postcopy()) {
-        stat64_add(&ram_atomic_counters.postcopy_bytes, bytes);
+        stat64_add(&ram_counters.postcopy_bytes, bytes);
     } else {
-        ram_counters.downtime_bytes += bytes;
+        stat64_add(&ram_counters.downtime_bytes, bytes);
     }
-    stat64_add(&ram_atomic_counters.transferred, bytes);
-}
-
-void dirty_sync_missed_zero_copy(void)
-{
-    ram_counters.dirty_sync_missed_zero_copy++;
+    stat64_add(&ram_counters.transferred, bytes);
 }
 
 struct MigrationOps {
@@ -756,7 +744,7 @@ void mig_throttle_counter_reset(void)
 
     rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     rs->num_dirty_pages_period = 0;
-    rs->bytes_xfer_prev = stat64_get(&ram_atomic_counters.transferred);
+    rs->bytes_xfer_prev = stat64_get(&ram_counters.transferred);
 }
 
 /**
@@ -776,7 +764,7 @@ static void xbzrle_cache_zero_page(RAMState *rs, ram_addr_t current_addr)
     /* We don't care if this fails to allocate a new cache page
      * as long as it updated an old one */
     cache_insert(XBZRLE.cache, current_addr, XBZRLE.zero_target_page,
-                 ram_counters.dirty_sync_count);
+                 stat64_get(&ram_counters.dirty_sync_count));
 }
 
 #define ENCODING_FLAG_XBZRLE 0x1
@@ -802,13 +790,13 @@ static int save_xbzrle_page(RAMState *rs, PageSearchStatus *pss,
     int encoded_len = 0, bytes_xbzrle;
     uint8_t *prev_cached_page;
     QEMUFile *file = pss->pss_channel;
+    uint64_t generation = stat64_get(&ram_counters.dirty_sync_count);
 
-    if (!cache_is_cached(XBZRLE.cache, current_addr,
-                         ram_counters.dirty_sync_count)) {
+    if (!cache_is_cached(XBZRLE.cache, current_addr, generation)) {
         xbzrle_counters.cache_miss++;
         if (!rs->last_stage) {
             if (cache_insert(XBZRLE.cache, current_addr, *current_data,
-                             ram_counters.dirty_sync_count) == -1) {
+                             generation) == -1) {
                 return -1;
             } else {
                 /* update *current_data when the page has been
@@ -1130,8 +1118,8 @@ uint64_t ram_pagesize_summary(void)
 
 uint64_t ram_get_total_transferred_pages(void)
 {
-    return  stat64_get(&ram_atomic_counters.normal) +
-        stat64_get(&ram_atomic_counters.duplicate) +
+    return stat64_get(&ram_counters.normal_pages) +
+        stat64_get(&ram_counters.zero_pages) +
         compression_counters.pages + xbzrle_counters.pages;
 }
 
@@ -1192,7 +1180,7 @@ static void migration_trigger_throttle(RAMState *rs)
     MigrationState *s = migrate_get_current();
     uint64_t threshold = s->parameters.throttle_trigger_threshold;
     uint64_t bytes_xfer_period =
-        stat64_get(&ram_atomic_counters.transferred) - rs->bytes_xfer_prev;
+        stat64_get(&ram_counters.transferred) - rs->bytes_xfer_prev;
     uint64_t bytes_dirty_period = rs->num_dirty_pages_period * TARGET_PAGE_SIZE;
     uint64_t bytes_dirty_threshold = bytes_xfer_period * threshold / 100;
 
@@ -1221,7 +1209,7 @@ static void migration_bitmap_sync(RAMState *rs)
     RAMBlock *block;
     int64_t end_time;
 
-    ram_counters.dirty_sync_count++;
+    stat64_add(&ram_counters.dirty_sync_count, 1);
 
     if (!rs->time_last_bitmap_sync) {
         rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
@@ -1255,10 +1243,11 @@ static void migration_bitmap_sync(RAMState *rs)
         /* reset period counters */
         rs->time_last_bitmap_sync = end_time;
         rs->num_dirty_pages_period = 0;
-        rs->bytes_xfer_prev = stat64_get(&ram_atomic_counters.transferred);
+        rs->bytes_xfer_prev = stat64_get(&ram_counters.transferred);
     }
     if (migrate_use_events()) {
-        qapi_event_send_migration_pass(ram_counters.dirty_sync_count);
+        uint64_t generation = stat64_get(&ram_counters.dirty_sync_count);
+        qapi_event_send_migration_pass(generation);
     }
 }
 
@@ -1331,7 +1320,7 @@ static int save_zero_page(PageSearchStatus *pss, QEMUFile *f, RAMBlock *block,
     int len = save_zero_page_to_file(pss, f, block, offset);
 
     if (len) {
-        stat64_add(&ram_atomic_counters.duplicate, 1);
+        stat64_add(&ram_counters.zero_pages, 1);
         ram_transferred_add(len);
         return 1;
     }
@@ -1368,9 +1357,9 @@ static bool control_save_page(PageSearchStatus *pss, RAMBlock *block,
     }
 
     if (bytes_xmit > 0) {
-        stat64_add(&ram_atomic_counters.normal, 1);
+        stat64_add(&ram_counters.normal_pages, 1);
     } else if (bytes_xmit == 0) {
-        stat64_add(&ram_atomic_counters.duplicate, 1);
+        stat64_add(&ram_counters.zero_pages, 1);
     }
 
     return true;
@@ -1402,7 +1391,7 @@ static int save_normal_page(PageSearchStatus *pss, RAMBlock *block,
         qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
     }
     ram_transferred_add(TARGET_PAGE_SIZE);
-    stat64_add(&ram_atomic_counters.normal, 1);
+    stat64_add(&ram_counters.normal_pages, 1);
     return 1;
 }
 
@@ -1458,7 +1447,7 @@ static int ram_save_multifd_page(QEMUFile *file, RAMBlock *block,
     if (multifd_queue_page(file, block, offset) < 0) {
         return -1;
     }
-    stat64_add(&ram_atomic_counters.normal, 1);
+    stat64_add(&ram_counters.normal_pages, 1);
 
     return 1;
 }
@@ -1497,7 +1486,7 @@ update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
     ram_transferred_add(bytes_xmit);
 
     if (param->zero_page) {
-        stat64_add(&ram_atomic_counters.duplicate, 1);
+        stat64_add(&ram_counters.zero_pages, 1);
         return;
     }
 
@@ -2180,7 +2169,7 @@ int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
     RAMBlock *ramblock;
     RAMState *rs = ram_state;
 
-    ram_counters.postcopy_requests++;
+    stat64_add(&ram_counters.postcopy_requests, 1);
     RCU_READ_LOCK_GUARD();
 
     if (!rbname) {
@@ -2632,9 +2621,9 @@ void acct_update_position(QEMUFile *f, size_t size, bool zero)
     uint64_t pages = size / TARGET_PAGE_SIZE;
 
     if (zero) {
-        stat64_add(&ram_atomic_counters.duplicate, pages);
+        stat64_add(&ram_counters.zero_pages, pages);
     } else {
-        stat64_add(&ram_atomic_counters.normal, pages);
+        stat64_add(&ram_counters.normal_pages, pages);
         ram_transferred_add(size);
         qemu_file_credit_transfer(f, size);
     }
@@ -3293,7 +3282,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
 
     migration_ops = g_malloc0(sizeof(MigrationOps));
     migration_ops->ram_save_target_page = ram_save_target_page_legacy;
-    ret =  multifd_send_sync_main(f);
+    ret = multifd_send_sync_main(f);
     if (ret < 0) {
         return ret;
     }

migration/ram.h

@@ -35,25 +35,27 @@
 #include "qemu/stats64.h"
 
 /*
- * These are the migration statistic counters that need to be updated using
- * atomic ops (can be accessed by more than one thread).  Here since we
- * cannot modify MigrationStats directly to use Stat64 as it was defined in
- * the QAPI scheme, we define an internal structure to hold them, and we
- * propagate the real values when QMP queries happen.
- *
- * IOW, the corresponding fields within ram_counters on these specific
- * fields will be always zero and not being used at all; they're just
- * placeholders to make it QAPI-compatible.
+ * These are the ram migration statistic counters.  It is loosely
+ * based on MigrationStats.  We change to Stat64 any counter that
+ * needs to be updated using atomic ops (can be accessed by more than
+ * one thread).
  */
 typedef struct {
-    Stat64 transferred;
-    Stat64 duplicate;
-    Stat64 normal;
+    int64_t dirty_pages_rate;
+    Stat64 dirty_sync_count;
+    Stat64 dirty_sync_missed_zero_copy;
+    Stat64 downtime_bytes;
+    Stat64 zero_pages;
+    Stat64 multifd_bytes;
+    Stat64 normal_pages;
     Stat64 postcopy_bytes;
-} MigrationAtomicStats;
+    Stat64 postcopy_requests;
+    Stat64 precopy_bytes;
+    int64_t remaining;
+    Stat64 transferred;
+} RAMStats;
 
-extern MigrationAtomicStats ram_atomic_counters;
-extern MigrationStats ram_counters;
+extern RAMStats ram_counters;
 extern XBZRLECacheStats xbzrle_counters;
 extern CompressionStats compression_counters;
 
@@ -112,6 +114,4 @@ void ram_write_tracking_prepare(void);
 int ram_write_tracking_start(void);
 void ram_write_tracking_stop(void);
 
-void dirty_sync_missed_zero_copy(void);
-
 #endif

migration/rdma.c

@@ -4179,7 +4179,7 @@ void rdma_start_outgoing_migration(void *opaque,
     }
 
     ret = qemu_rdma_source_init(rdma,
-        s->enabled_capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp);
+        s->capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp);
 
     if (ret) {
         goto err;
@@ -4201,7 +4201,7 @@ void rdma_start_outgoing_migration(void *opaque,
         }
 
         ret = qemu_rdma_source_init(rdma_return_path,
-            s->enabled_capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp);
+            s->capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp);
 
         if (ret) {
             goto return_path_err;

migration/savevm.c

@@ -253,7 +253,7 @@ static uint32_t get_validatable_capabilities_count(void)
     uint32_t result = 0;
     int i;
     for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
-        if (should_validate_capability(i) && s->enabled_capabilities[i]) {
+        if (should_validate_capability(i) && s->capabilities[i]) {
             result++;
         }
     }
@@ -275,7 +275,7 @@ static int configuration_pre_save(void *opaque)
     state->capabilities = g_renew(MigrationCapability, state->capabilities,
                                   state->caps_count);
     for (i = j = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
-        if (should_validate_capability(i) && s->enabled_capabilities[i]) {
+        if (should_validate_capability(i) && s->capabilities[i]) {
             state->capabilities[j++] = i;
         }
     }
@@ -325,7 +325,7 @@ static bool configuration_validate_capabilities(SaveState *state)
             continue;
         }
         source_state = test_bit(i, source_caps_bm);
-        target_state = s->enabled_capabilities[i];
+        target_state = s->capabilities[i];
         if (source_state != target_state) {
             error_report("Capability %s is %s, but received capability is %s",
                          MigrationCapability_str(i),

softmmu/vl.c

@@ -3583,14 +3583,19 @@ void qemu_init(int argc, char **argv)
                      machine_class->name, machine_class->deprecation_reason);
     }
 
+    /*
+     * Create backends before creating migration objects, so that it can
+     * check against compatibilities on the backend memories (e.g. postcopy
+     * over memory-backend-file objects).
+     */
+    qemu_create_late_backends();
+
     /*
      * Note: creates a QOM object, must run only after global and
      * compat properties have been set up.
      */
     migration_object_init();
 
-    qemu_create_late_backends();
-
     /* parse features once if machine provides default cpu_type */
     current_machine->cpu_type = machine_class->default_cpu_type;
     if (cpu_option) {

util/mmap-alloc.c

@@ -27,8 +27,36 @@
 
 #ifdef CONFIG_LINUX
 #include <sys/vfs.h>
+#include <linux/magic.h>
 #endif
 
+QemuFsType qemu_fd_getfs(int fd)
+{
+#ifdef CONFIG_LINUX
+    struct statfs fs;
+    int ret;
+
+    if (fd < 0) {
+        return QEMU_FS_TYPE_UNKNOWN;
+    }
+
+    do {
+        ret = fstatfs(fd, &fs);
+    } while (ret != 0 && errno == EINTR);
+
+    switch (fs.f_type) {
+    case TMPFS_MAGIC:
+        return QEMU_FS_TYPE_TMPFS;
+    case HUGETLBFS_MAGIC:
+        return QEMU_FS_TYPE_HUGETLBFS;
+    default:
+        return QEMU_FS_TYPE_UNKNOWN;
+    }
+#else
+    return QEMU_FS_TYPE_UNKNOWN;
+#endif
+}
+
 size_t qemu_fd_getpagesize(int fd)
 {
 #ifdef CONFIG_LINUX