Merge remote-tracking branch 'remotes/juanquintela/tags/migration/20180604' into staging

migration/next for 20180604

# gpg: Signature made Mon 04 Jun 2018 05:14:24 BST
# gpg:                using RSA key F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>"
# gpg:                 aka "Juan Quintela <quintela@trasno.org>"
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* remotes/juanquintela/tags/migration/20180604:
  migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect
  migration: remove unnecessary variables len in QIOChannelRDMA
  migration: Don't activate block devices if using -S
  migration: discard non-migratable RAMBlocks
  migration: introduce decompress-error-check

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

7 files changed, 90 insertions, 45 deletions

diff --git a/migration/migration.c b/migration/migration.c
index 05aec2c905..1e99ec9b7e 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -202,6 +202,16 @@ static void migrate_generate_event(int new_state)
     }
 }
 
+static bool migrate_late_block_activate(void)
+{
+    MigrationState *s;
+
+    s = migrate_get_current();
+
+    return s->enabled_capabilities[
+        MIGRATION_CAPABILITY_LATE_BLOCK_ACTIVATE];
+}
+
 /*
  * Called on -incoming with a defer: uri.
  * The migration can be started later after any parameters have been
@@ -311,13 +321,23 @@ static void process_incoming_migration_bh(void *opaque)
     Error *local_err = NULL;
     MigrationIncomingState *mis = opaque;
 
-    /* Make sure all file formats flush their mutable metadata.
-     * If we get an error here, just don't restart the VM yet. */
-    bdrv_invalidate_cache_all(&local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        local_err = NULL;
-        autostart = false;
+    /* If capability late_block_activate is set:
+     * Only fire up the block code now if we're going to restart the
+     * VM, else 'cont' will do it.
+     * This causes file locking to happen; so we don't want it to happen
+     * unless we really are starting the VM.
+     */
+    if (!migrate_late_block_activate() ||
+         (autostart && (!global_state_received() ||
+            global_state_get_runstate() == RUN_STATE_RUNNING))) {
+        /* Make sure all file formats flush their mutable metadata.
+         * If we get an error here, just don't restart the VM yet. */
+        bdrv_invalidate_cache_all(&local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            local_err = NULL;
+            autostart = false;
+        }
     }
 
     /*
@@ -2971,6 +2991,8 @@ void migration_global_dump(Monitor *mon)
                    ms->send_configuration ? "on" : "off");
     monitor_printf(mon, "send-section-footer: %s\n",
                    ms->send_section_footer ? "on" : "off");
+    monitor_printf(mon, "decompress-error-check: %s\n",
+                   ms->decompress_error_check ? "on" : "off");
 }
 
 #define DEFINE_PROP_MIG_CAP(name, x)             \
@@ -2984,6 +3006,8 @@ static Property migration_properties[] = {
                      send_configuration, true),
     DEFINE_PROP_BOOL("send-section-footer", MigrationState,
                      send_section_footer, true),
+    DEFINE_PROP_BOOL("decompress-error-check", MigrationState,
+                      decompress_error_check, true),
 
     /* Migration parameters */
     DEFINE_PROP_UINT8("x-compress-level", MigrationState,
diff --git a/migration/migration.h b/migration/migration.h
index 8f0c82159b..5af57d616c 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -212,6 +212,13 @@ struct MigrationState
     /* Needed by postcopy-pause state */
     QemuSemaphore postcopy_pause_sem;
     QemuSemaphore postcopy_pause_rp_sem;
+    /*
+     * Whether we abort the migration if decompression errors are
+     * detected at the destination. It is left at false for qemu
+     * older than 3.0, since only newer qemu sends streams that
+     * do not trigger spurious decompression errors.
+     */
+    bool decompress_error_check;
 };
 
 void migrate_set_state(int *state, int old_state, int new_state);
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 658b750a8e..48e51556a7 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -374,7 +374,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
     }
 
     /* We don't support postcopy with shared RAM yet */
-    if (qemu_ram_foreach_block(test_ramblock_postcopiable, NULL)) {
+    if (qemu_ram_foreach_migratable_block(test_ramblock_postcopiable, NULL)) {
         goto out;
     }
 
@@ -502,7 +502,7 @@ static int cleanup_range(const char *block_name, void *host_addr,
  */
 int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages)
 {
-    if (qemu_ram_foreach_block(init_range, NULL)) {
+    if (qemu_ram_foreach_migratable_block(init_range, NULL)) {
         return -1;
     }
 
@@ -524,7 +524,7 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
             return -1;
         }
 
-        if (qemu_ram_foreach_block(cleanup_range, mis)) {
+        if (qemu_ram_foreach_migratable_block(cleanup_range, mis)) {
             return -1;
         }
         /* Let the fault thread quit */
@@ -593,7 +593,7 @@ static int nhp_range(const char *block_name, void *host_addr,
  */
 int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
 {
-    if (qemu_ram_foreach_block(nhp_range, mis)) {
+    if (qemu_ram_foreach_migratable_block(nhp_range, mis)) {
         return -1;
     }
 
@@ -604,7 +604,7 @@ int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
 
 /*
  * Mark the given area of RAM as requiring notification to unwritten areas
- * Used as a  callback on qemu_ram_foreach_block.
+ * Used as a  callback on qemu_ram_foreach_migratable_block.
  *   host_addr: Base of area to mark
  *   offset: Offset in the whole ram arena
  *   length: Length of the section
@@ -1099,7 +1099,7 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
     mis->have_fault_thread = true;
 
     /* Mark so that we get notified of accesses to unwritten areas */
-    if (qemu_ram_foreach_block(ram_block_enable_notify, mis)) {
+    if (qemu_ram_foreach_migratable_block(ram_block_enable_notify, mis)) {
         return -1;
     }
 
diff --git a/migration/ram.c b/migration/ram.c
index f4e29cadc6..a500015a2f 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -157,11 +157,16 @@ out:
     return ret;
 }
 
+/* Should be holding either ram_list.mutex, or the RCU lock. */
+#define RAMBLOCK_FOREACH_MIGRATABLE(block)             \
+    RAMBLOCK_FOREACH(block)                            \
+        if (!qemu_ram_is_migratable(block)) {} else
+
 static void ramblock_recv_map_init(void)
 {
     RAMBlock *rb;
 
-    RAMBLOCK_FOREACH(rb) {
+    RAMBLOCK_FOREACH_MIGRATABLE(rb) {
         assert(!rb->receivedmap);
         rb->receivedmap = bitmap_new(rb->max_length >> qemu_target_page_bits());
     }
@@ -1078,6 +1083,10 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb,
     unsigned long *bitmap = rb->bmap;
     unsigned long next;
 
+    if (!qemu_ram_is_migratable(rb)) {
+        return size;
+    }
+
     if (rs->ram_bulk_stage && start > 0) {
         next = start + 1;
     } else {
@@ -1123,7 +1132,7 @@ uint64_t ram_pagesize_summary(void)
     RAMBlock *block;
     uint64_t summary = 0;
 
-    RAMBLOCK_FOREACH(block) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         summary |= block->page_size;
     }
 
@@ -1147,7 +1156,7 @@ static void migration_bitmap_sync(RAMState *rs)
 
     qemu_mutex_lock(&rs->bitmap_mutex);
     rcu_read_lock();
-    RAMBLOCK_FOREACH(block) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         migration_bitmap_sync_range(rs, block, 0, block->used_length);
     }
     rcu_read_unlock();
@@ -1786,6 +1795,11 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
     size_t pagesize_bits =
         qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;
 
+    if (!qemu_ram_is_migratable(pss->block)) {
+        error_report("block %s should not be migrated !", pss->block->idstr);
+        return 0;
+    }
+
     do {
         /* Check the pages is dirty and if it is send it */
         if (!migration_bitmap_clear_dirty(rs, pss->block, pss->page)) {
@@ -1884,7 +1898,7 @@ uint64_t ram_bytes_total(void)
     uint64_t total = 0;
 
     rcu_read_lock();
-    RAMBLOCK_FOREACH(block) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         total += block->used_length;
     }
     rcu_read_unlock();
@@ -1939,7 +1953,7 @@ static void ram_save_cleanup(void *opaque)
      */
     memory_global_dirty_log_stop();
 
-    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         g_free(block->bmap);
         block->bmap = NULL;
         g_free(block->unsentmap);
@@ -2002,7 +2016,7 @@ void ram_postcopy_migrated_memory_release(MigrationState *ms)
 {
     struct RAMBlock *block;
 
-    RAMBLOCK_FOREACH(block) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         unsigned long *bitmap = block->bmap;
         unsigned long range = block->used_length >> TARGET_PAGE_BITS;
         unsigned long run_start = find_next_zero_bit(bitmap, range, 0);
@@ -2080,7 +2094,7 @@ static int postcopy_each_ram_send_discard(MigrationState *ms)
     struct RAMBlock *block;
     int ret;
 
-    RAMBLOCK_FOREACH(block) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         PostcopyDiscardState *pds =
             postcopy_discard_send_init(ms, block->idstr);
 
@@ -2288,7 +2302,7 @@ int ram_postcopy_send_discard_bitmap(MigrationState *ms)
     rs->last_sent_block = NULL;
     rs->last_page = 0;
 
-    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         unsigned long pages = block->used_length >> TARGET_PAGE_BITS;
         unsigned long *bitmap = block->bmap;
         unsigned long *unsentmap = block->unsentmap;
@@ -2447,7 +2461,7 @@ static void ram_list_init_bitmaps(void)
 
     /* Skip setting bitmap if there is no RAM */
     if (ram_bytes_total()) {
-        QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        RAMBLOCK_FOREACH_MIGRATABLE(block) {
             pages = block->max_length >> TARGET_PAGE_BITS;
             block->bmap = bitmap_new(pages);
             bitmap_set(block->bmap, 0, pages);
@@ -2563,7 +2577,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
 
     qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
 
-    RAMBLOCK_FOREACH(block) {
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
         qemu_put_byte(f, strlen(block->idstr));
         qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
         qemu_put_be64(f, block->used_length);
@@ -2807,6 +2821,11 @@ static inline RAMBlock *ram_block_from_stream(QEMUFile *f, int flags)
         return NULL;
     }
 
+    if (!qemu_ram_is_migratable(block)) {
+        error_report("block %s should not be migrated !", id);
+        return NULL;
+    }
+
     return block;
 }
 
@@ -2881,7 +2900,7 @@ static void *do_data_decompress(void *opaque)
 
             ret = qemu_uncompress_data(&param->stream, des, pagesize,
                                        param->compbuf, len);
-            if (ret < 0) {
+            if (ret < 0 && migrate_get_current()->decompress_error_check) {
                 error_report("decompress data failed");
                 qemu_file_set_error(decomp_file, ret);
             }
@@ -3049,7 +3068,7 @@ static int ram_load_cleanup(void *opaque)
     xbzrle_load_cleanup();
     compress_threads_load_cleanup();
 
-    RAMBLOCK_FOREACH(rb) {
+    RAMBLOCK_FOREACH_MIGRATABLE(rb) {
         g_free(rb->receivedmap);
         rb->receivedmap = NULL;
     }
@@ -3311,7 +3330,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 length = qemu_get_be64(f);
 
                 block = qemu_ram_block_by_name(id);
-                if (block) {
+                if (block && !qemu_ram_is_migratable(block)) {
+                    error_report("block %s should not be migrated !", id);
+                    ret = -EINVAL;
+                } else if (block) {
                     if (length != block->used_length) {
                         Error *local_err = NULL;
 
diff --git a/migration/rdma.c b/migration/rdma.c
index 7d233b0820..05aee3d591 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -400,7 +400,6 @@ struct QIOChannelRDMA {
     QIOChannel parent;
     RDMAContext *rdma;
     QEMUFile *file;
-    size_t len;
     bool blocking; /* XXX we don't actually honour this yet */
 };
 
@@ -2268,8 +2267,7 @@ static int qemu_rdma_write(QEMUFile *f, RDMAContext *rdma,
 
 static void qemu_rdma_cleanup(RDMAContext *rdma)
 {
-    struct rdma_cm_event *cm_event;
-    int ret, idx;
+    int idx;
 
     if (rdma->cm_id && rdma->connected) {
         if ((rdma->error_state ||
@@ -2283,14 +2281,7 @@ static void qemu_rdma_cleanup(RDMAContext *rdma)
             qemu_rdma_post_send_control(rdma, NULL, &head);
         }
 
-        ret = rdma_disconnect(rdma->cm_id);
-        if (!ret) {
-            trace_qemu_rdma_cleanup_waiting_for_disconnect();
-            ret = rdma_get_cm_event(rdma->channel, &cm_event);
-            if (!ret) {
-                rdma_ack_cm_event(cm_event);
-            }
-        }
+        rdma_disconnect(rdma->cm_id);
         trace_qemu_rdma_cleanup_disconnect();
         rdma->connected = false;
     }
@@ -2608,6 +2599,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc,
     int ret;
     ssize_t done = 0;
     size_t i;
+    size_t len = 0;
 
     CHECK_ERROR_STATE();
 
@@ -2627,10 +2619,10 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc,
         while (remaining) {
             RDMAControlHeader head;
 
-            rioc->len = MIN(remaining, RDMA_SEND_INCREMENT);
-            remaining -= rioc->len;
+            len = MIN(remaining, RDMA_SEND_INCREMENT);
+            remaining -= len;
 
-            head.len = rioc->len;
+            head.len = len;
             head.type = RDMA_CONTROL_QEMU_FILE;
 
             ret = qemu_rdma_exchange_send(rdma, &head, data, NULL, NULL, NULL);
@@ -2640,8 +2632,8 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc,
                 return ret;
             }
 
-            data += rioc->len;
-            done += rioc->len;
+            data += len;
+            done += len;
         }
     }
 
@@ -2736,8 +2728,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc,
             }
         }
     }
-    rioc->len = done;
-    return rioc->len;
+    return done;
 }
 
 /*
diff --git a/migration/savevm.c b/migration/savevm.c
index da724c52f2..c2f34ffc7c 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2689,11 +2689,13 @@ void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev)
 {
     qemu_ram_set_idstr(mr->ram_block,
                        memory_region_name(mr), dev);
+    qemu_ram_set_migratable(mr->ram_block);
 }
 
 void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev)
 {
     qemu_ram_unset_idstr(mr->ram_block);
+    qemu_ram_unset_migratable(mr->ram_block);
 }
 
 void vmstate_register_ram_global(MemoryRegion *mr)
diff --git a/migration/trace-events b/migration/trace-events
index 3c798ddd11..4a768eaaeb 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -146,7 +146,6 @@ qemu_rdma_accept_pin_state(bool pin) "%d"
 qemu_rdma_accept_pin_verbsc(void *verbs) "Verbs context after listen: %p"
 qemu_rdma_block_for_wrid_miss(const char *wcompstr, int wcomp, const char *gcompstr, uint64_t req) "A Wanted wrid %s (%d) but got %s (%" PRIu64 ")"
 qemu_rdma_cleanup_disconnect(void) ""
-qemu_rdma_cleanup_waiting_for_disconnect(void) ""
 qemu_rdma_close(void) ""
 qemu_rdma_connect_pin_all_requested(void) ""
 qemu_rdma_connect_pin_all_outcome(bool pin) "%d"