Block patches:

- Parallelized request handling for qcow2
 - Backup job refactoring to use a filter node instead of before-write
   notifiers
 - Add discard accounting information to file-posix nodes
 - Allow trivial reopening of nbd nodes
 - Some iotest fixes
 -----BEGIN PGP SIGNATURE-----
 
 iQFGBAABCAAwFiEEkb62CjDbPohX0Rgp9AfbAGHVz0AFAl2fGLISHG1yZWl0ekBy
 ZWRoYXQuY29tAAoJEPQH2wBh1c9A5JEH/2Hluzk0kfpYK+Ju3Mpf6syE2XdtYL7q
 zJNQgx4aIQOnBkCnUhQckNnRLWbiv9DxcJQ9iueRyst5nQhOpGisNw5LS4vYUbKV
 rHA3oITdV9Ozsr2d8SL+ncvY91I5zpzFySDsYIwMD6Y7H42NVcs7yvUjilHW2SmN
 9bPFp0mocMLeH/2keQE3H5mJGb+tAogM9FW/jQ/fjD5eql05gb9McDjjPD6jHLk6
 AEzWxWh6M56krEgke390gxy/N7r9u5+HHRAfFldEGoI+jw0iTt3L1MXcz0zytxfx
 Gdh+gyihauQVTIfTvyAAHHYaOuXUwSWJOjlbILleLEhnTYd/cFGRYzM=
 =u0I2
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/maxreitz/tags/pull-block-2019-10-10' into staging

Block patches:
- Parallelized request handling for qcow2
- Backup job refactoring to use a filter node instead of before-write
  notifiers
- Add discard accounting information to file-posix nodes
- Allow trivial reopening of nbd nodes
- Some iotest fixes

# gpg: Signature made Thu 10 Oct 2019 12:40:34 BST
# gpg:                using RSA key 91BEB60A30DB3E8857D11829F407DB0061D5CF40
# gpg:                issuer "mreitz@redhat.com"
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>" [full]
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/maxreitz/tags/pull-block-2019-10-10: (36 commits)
  iotests/162: Fix for newer Linux 5.3+
  tests: fix I/O test for hosts defaulting to LUKSv2
  nbd: add empty .bdrv_reopen_prepare
  block/backup: use backup-top instead of write notifiers
  block: introduce backup-top filter driver
  block/block-copy: split block_copy_set_callbacks function
  block/backup: move write_flags calculation inside backup_job_create
  block/backup: move in-flight requests handling from backup to block-copy
  iotests: Use stat -c %b in 125
  iotests: Disable 125 on broken XFS versions
  iotests: Fix 125 for growth_mode = metadata
  qapi: query-blockstat: add driver specific file-posix stats
  file-posix: account discard operations
  scsi: account unmap operations
  scsi: move unmap error checking to the complete callback
  scsi: store unmap offset and nb_sectors in request struct
  ide: account UNMAP (TRIM) operations
  block: add empty account cookie type
  qapi: add unmap to BlockDeviceStats
  qapi: group BlockDeviceStats fields
  ...

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

block.c

@@ -5155,6 +5155,15 @@ ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs,
     return NULL;
 }
 
+BlockStatsSpecific *bdrv_get_specific_stats(BlockDriverState *bs)
+{
+    BlockDriver *drv = bs->drv;
+    if (!drv || !drv->bdrv_get_specific_stats) {
+        return NULL;
+    }
+    return drv->bdrv_get_specific_stats(bs);
+}
+
 void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event)
 {
     if (!bs || !bs->drv || !bs->drv->bdrv_debug_event) {
@@ -5164,14 +5173,35 @@ void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event)
     bs->drv->bdrv_debug_event(bs, event);
 }
 
-int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
-                          const char *tag)
+static BlockDriverState *bdrv_find_debug_node(BlockDriverState *bs)
 {
     while (bs && bs->drv && !bs->drv->bdrv_debug_breakpoint) {
-        bs = bs->file ? bs->file->bs : NULL;
+        if (bs->file) {
+            bs = bs->file->bs;
+            continue;
+        }
+
+        if (bs->drv->is_filter && bs->backing) {
+            bs = bs->backing->bs;
+            continue;
+        }
+
+        break;
     }
 
     if (bs && bs->drv && bs->drv->bdrv_debug_breakpoint) {
+        assert(bs->drv->bdrv_debug_remove_breakpoint);
+        return bs;
+    }
+
+    return NULL;
+}
+
+int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
+                          const char *tag)
+{
+    bs = bdrv_find_debug_node(bs);
+    if (bs) {
         return bs->drv->bdrv_debug_breakpoint(bs, event, tag);
     }
 
@@ -5180,11 +5210,8 @@ int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
 
 int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag)
 {
-    while (bs && bs->drv && !bs->drv->bdrv_debug_remove_breakpoint) {
-        bs = bs->file ? bs->file->bs : NULL;
-    }
-
-    if (bs && bs->drv && bs->drv->bdrv_debug_remove_breakpoint) {
+    bs = bdrv_find_debug_node(bs);
+    if (bs) {
         return bs->drv->bdrv_debug_remove_breakpoint(bs, tag);
     }
 

block/Makefile.objs

@@ -37,9 +37,13 @@ block-obj-y += write-threshold.o
 block-obj-y += backup.o
 block-obj-$(CONFIG_REPLICATION) += replication.o
 block-obj-y += throttle.o copy-on-read.o
+block-obj-y += block-copy.o
 
 block-obj-y += crypto.o
 
+block-obj-y += aio_task.o
+block-obj-y += backup-top.o
+
 common-obj-y += stream.o
 
 nfs.o-libs         := $(LIBNFS_LIBS)

block/accounting.c

@@ -195,6 +195,10 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
 
     assert(cookie->type < BLOCK_MAX_IOTYPE);
 
+    if (cookie->type == BLOCK_ACCT_NONE) {
+        return;
+    }
+
     qemu_mutex_lock(&stats->lock);
 
     if (failed) {
@@ -217,6 +221,8 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
     }
 
     qemu_mutex_unlock(&stats->lock);
+
+    cookie->type = BLOCK_ACCT_NONE;
 }
 
 void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)

block/aio_task.c

@@ -0,0 +1,124 @@
+/*
+ * Aio tasks loops
+ *
+ * Copyright (c) 2019 Virtuozzo International GmbH.
+ *
+ * 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 "qemu/osdep.h"
+#include "block/aio.h"
+#include "block/aio_task.h"
+
+struct AioTaskPool {
+    Coroutine *main_co;
+    int status;
+    int max_busy_tasks;
+    int busy_tasks;
+    bool waiting;
+};
+
+static void coroutine_fn aio_task_co(void *opaque)
+{
+    AioTask *task = opaque;
+    AioTaskPool *pool = task->pool;
+
+    assert(pool->busy_tasks < pool->max_busy_tasks);
+    pool->busy_tasks++;
+
+    task->ret = task->func(task);
+
+    pool->busy_tasks--;
+
+    if (task->ret < 0 && pool->status == 0) {
+        pool->status = task->ret;
+    }
+
+    g_free(task);
+
+    if (pool->waiting) {
+        pool->waiting = false;
+        aio_co_wake(pool->main_co);
+    }
+}
+
+void coroutine_fn aio_task_pool_wait_one(AioTaskPool *pool)
+{
+    assert(pool->busy_tasks > 0);
+    assert(qemu_coroutine_self() == pool->main_co);
+
+    pool->waiting = true;
+    qemu_coroutine_yield();
+
+    assert(!pool->waiting);
+    assert(pool->busy_tasks < pool->max_busy_tasks);
+}
+
+void coroutine_fn aio_task_pool_wait_slot(AioTaskPool *pool)
+{
+    if (pool->busy_tasks < pool->max_busy_tasks) {
+        return;
+    }
+
+    aio_task_pool_wait_one(pool);
+}
+
+void coroutine_fn aio_task_pool_wait_all(AioTaskPool *pool)
+{
+    while (pool->busy_tasks > 0) {
+        aio_task_pool_wait_one(pool);
+    }
+}
+
+void coroutine_fn aio_task_pool_start_task(AioTaskPool *pool, AioTask *task)
+{
+    aio_task_pool_wait_slot(pool);
+
+    task->pool = pool;
+    qemu_coroutine_enter(qemu_coroutine_create(aio_task_co, task));
+}
+
+AioTaskPool *coroutine_fn aio_task_pool_new(int max_busy_tasks)
+{
+    AioTaskPool *pool = g_new0(AioTaskPool, 1);
+
+    pool->main_co = qemu_coroutine_self();
+    pool->max_busy_tasks = max_busy_tasks;
+
+    return pool;
+}
+
+void aio_task_pool_free(AioTaskPool *pool)
+{
+    g_free(pool);
+}
+
+int aio_task_pool_status(AioTaskPool *pool)
+{
+    if (!pool) {
+        return 0; /* Sugar for lazy allocation of aio pool */
+    }
+
+    return pool->status;
+}
+
+bool aio_task_pool_empty(AioTaskPool *pool)
+{
+    return pool->busy_tasks == 0;
+}

block/backup-top.c

@@ -0,0 +1,276 @@
+/*
+ * backup-top filter driver
+ *
+ * The driver performs Copy-Before-Write (CBW) operation: it is injected above
+ * some node, and before each write it copies _old_ data to the target node.
+ *
+ * Copyright (c) 2018-2019 Virtuozzo International GmbH.
+ *
+ * Author:
+ *  Sementsov-Ogievskiy Vladimir <vsementsov@virtuozzo.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+
+#include "sysemu/block-backend.h"
+#include "qemu/cutils.h"
+#include "qapi/error.h"
+#include "block/block_int.h"
+#include "block/qdict.h"
+#include "block/block-copy.h"
+
+#include "block/backup-top.h"
+
+typedef struct BDRVBackupTopState {
+    BlockCopyState *bcs;
+    BdrvChild *target;
+    bool active;
+} BDRVBackupTopState;
+
+static coroutine_fn int backup_top_co_preadv(
+        BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+        QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset,
+                                       uint64_t bytes)
+{
+    BDRVBackupTopState *s = bs->opaque;
+    uint64_t end = QEMU_ALIGN_UP(offset + bytes, s->bcs->cluster_size);
+    uint64_t off = QEMU_ALIGN_DOWN(offset, s->bcs->cluster_size);
+
+    return block_copy(s->bcs, off, end - off, NULL);
+}
+
+static int coroutine_fn backup_top_co_pdiscard(BlockDriverState *bs,
+                                               int64_t offset, int bytes)
+{
+    int ret = backup_top_cbw(bs, offset, bytes);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return bdrv_co_pdiscard(bs->backing, offset, bytes);
+}
+
+static int coroutine_fn backup_top_co_pwrite_zeroes(BlockDriverState *bs,
+        int64_t offset, int bytes, BdrvRequestFlags flags)
+{
+    int ret = backup_top_cbw(bs, offset, bytes);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return bdrv_co_pwrite_zeroes(bs->backing, offset, bytes, flags);
+}
+
+static coroutine_fn int backup_top_co_pwritev(BlockDriverState *bs,
+                                              uint64_t offset,
+                                              uint64_t bytes,
+                                              QEMUIOVector *qiov, int flags)
+{
+    if (!(flags & BDRV_REQ_WRITE_UNCHANGED)) {
+        int ret = backup_top_cbw(bs, offset, bytes);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    return bdrv_co_pwritev(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn backup_top_co_flush(BlockDriverState *bs)
+{
+    if (!bs->backing) {
+        return 0;
+    }
+
+    return bdrv_co_flush(bs->backing->bs);
+}
+
+static void backup_top_refresh_filename(BlockDriverState *bs)
+{
+    if (bs->backing == NULL) {
+        /*
+         * we can be here after failed bdrv_attach_child in
+         * bdrv_set_backing_hd
+         */
+        return;
+    }
+    pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
+            bs->backing->bs->filename);
+}
+
+static void backup_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                  const BdrvChildRole *role,
+                                  BlockReopenQueue *reopen_queue,
+                                  uint64_t perm, uint64_t shared,
+                                  uint64_t *nperm, uint64_t *nshared)
+{
+    BDRVBackupTopState *s = bs->opaque;
+
+    if (!s->active) {
+        /*
+         * The filter node may be in process of bdrv_append(), which firstly do
+         * bdrv_set_backing_hd() and then bdrv_replace_node(). This means that
+         * we can't unshare BLK_PERM_WRITE during bdrv_append() operation. So,
+         * let's require nothing during bdrv_append() and refresh permissions
+         * after it (see bdrv_backup_top_append()).
+         */
+        *nperm = 0;
+        *nshared = BLK_PERM_ALL;
+        return;
+    }
+
+    if (role == &child_file) {
+        /*
+         * Target child
+         *
+         * Share write to target (child_file), to not interfere
+         * with guest writes to its disk which may be in target backing chain.
+         */
+        *nshared = BLK_PERM_ALL;
+        *nperm = BLK_PERM_WRITE;
+    } else {
+        /* Source child */
+        bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared,
+                                  nperm, nshared);
+
+        if (perm & BLK_PERM_WRITE) {
+            *nperm = *nperm | BLK_PERM_CONSISTENT_READ;
+        }
+        *nshared &= ~BLK_PERM_WRITE;
+    }
+}
+
+BlockDriver bdrv_backup_top_filter = {
+    .format_name = "backup-top",
+    .instance_size = sizeof(BDRVBackupTopState),
+
+    .bdrv_co_preadv             = backup_top_co_preadv,
+    .bdrv_co_pwritev            = backup_top_co_pwritev,
+    .bdrv_co_pwrite_zeroes      = backup_top_co_pwrite_zeroes,
+    .bdrv_co_pdiscard           = backup_top_co_pdiscard,
+    .bdrv_co_flush              = backup_top_co_flush,
+
+    .bdrv_co_block_status       = bdrv_co_block_status_from_backing,
+
+    .bdrv_refresh_filename      = backup_top_refresh_filename,
+
+    .bdrv_child_perm            = backup_top_child_perm,
+
+    .is_filter = true,
+};
+
+BlockDriverState *bdrv_backup_top_append(BlockDriverState *source,
+                                         BlockDriverState *target,
+                                         const char *filter_node_name,
+                                         uint64_t cluster_size,
+                                         BdrvRequestFlags write_flags,
+                                         BlockCopyState **bcs,
+                                         Error **errp)
+{
+    Error *local_err = NULL;
+    BDRVBackupTopState *state;
+    BlockDriverState *top = bdrv_new_open_driver(&bdrv_backup_top_filter,
+                                                 filter_node_name,
+                                                 BDRV_O_RDWR, errp);
+
+    if (!top) {
+        return NULL;
+    }
+
+    top->total_sectors = source->total_sectors;
+    top->opaque = state = g_new0(BDRVBackupTopState, 1);
+
+    bdrv_ref(target);
+    state->target = bdrv_attach_child(top, target, "target", &child_file, errp);
+    if (!state->target) {
+        bdrv_unref(target);
+        bdrv_unref(top);
+        return NULL;
+    }
+
+    bdrv_drained_begin(source);
+
+    bdrv_ref(top);
+    bdrv_append(top, source, &local_err);
+    if (local_err) {
+        error_prepend(&local_err, "Cannot append backup-top filter: ");
+        goto append_failed;
+    }
+
+    /*
+     * bdrv_append() finished successfully, now we can require permissions
+     * we want.
+     */
+    state->active = true;
+    bdrv_child_refresh_perms(top, top->backing, &local_err);
+    if (local_err) {
+        error_prepend(&local_err,
+                      "Cannot set permissions for backup-top filter: ");
+        goto failed_after_append;
+    }
+
+    state->bcs = block_copy_state_new(top->backing, state->target,
+                                      cluster_size, write_flags, &local_err);
+    if (local_err) {
+        error_prepend(&local_err, "Cannot create block-copy-state: ");
+        goto failed_after_append;
+    }
+    *bcs = state->bcs;
+
+    bdrv_drained_end(source);
+
+    return top;
+
+failed_after_append:
+    state->active = false;
+    bdrv_backup_top_drop(top);
+
+append_failed:
+    bdrv_drained_end(source);
+    bdrv_unref_child(top, state->target);
+    bdrv_unref(top);
+    error_propagate(errp, local_err);
+
+    return NULL;
+}
+
+void bdrv_backup_top_drop(BlockDriverState *bs)
+{
+    BDRVBackupTopState *s = bs->opaque;
+    AioContext *aio_context = bdrv_get_aio_context(bs);
+
+    block_copy_state_free(s->bcs);
+
+    aio_context_acquire(aio_context);
+
+    bdrv_drained_begin(bs);
+
+    s->active = false;
+    bdrv_child_refresh_perms(bs, bs->backing, &error_abort);
+    bdrv_replace_node(bs, backing_bs(bs), &error_abort);
+    bdrv_set_backing_hd(bs, NULL, &error_abort);
+
+    bdrv_drained_end(bs);
+
+    bdrv_unref(bs);
+
+    aio_context_release(aio_context);
+}

block/backup-top.h

@@ -0,0 +1,41 @@
+/*
+ * backup-top filter driver
+ *
+ * The driver performs Copy-Before-Write (CBW) operation: it is injected above
+ * some node, and before each write it copies _old_ data to the target node.
+ *
+ * Copyright (c) 2018-2019 Virtuozzo International GmbH.
+ *
+ * Author:
+ *  Sementsov-Ogievskiy Vladimir <vsementsov@virtuozzo.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef BACKUP_TOP_H
+#define BACKUP_TOP_H
+
+#include "block/block_int.h"
+#include "block/block-copy.h"
+
+BlockDriverState *bdrv_backup_top_append(BlockDriverState *source,
+                                         BlockDriverState *target,
+                                         const char *filter_node_name,
+                                         uint64_t cluster_size,
+                                         BdrvRequestFlags write_flags,
+                                         BlockCopyState **bcs,
+                                         Error **errp);
+void bdrv_backup_top_drop(BlockDriverState *bs);
+
+#endif /* BACKUP_TOP_H */

block/backup.c

@@ -2,6 +2,7 @@
  * QEMU backup
  *
  * Copyright (C) 2013 Proxmox Server Solutions
+ * Copyright (c) 2019 Virtuozzo International GmbH.
  *
  * Authors:
  *  Dietmar Maurer (dietmar@proxmox.com)
@@ -18,6 +19,7 @@
 #include "block/block_int.h"
 #include "block/blockjob_int.h"
 #include "block/block_backup.h"
+#include "block/block-copy.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
@@ -26,333 +28,68 @@
 #include "qemu/bitmap.h"
 #include "qemu/error-report.h"
 
-#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
+#include "block/backup-top.h"
 
-typedef struct CowRequest {
-    int64_t start_byte;
-    int64_t end_byte;
-    QLIST_ENTRY(CowRequest) list;
-    CoQueue wait_queue; /* coroutines blocked on this request */
-} CowRequest;
+#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
 
 typedef struct BackupBlockJob {
     BlockJob common;
-    BlockBackend *target;
+    BlockDriverState *backup_top;
+    BlockDriverState *source_bs;
 
     BdrvDirtyBitmap *sync_bitmap;
-    BdrvDirtyBitmap *copy_bitmap;
 
     MirrorSyncMode sync_mode;
     BitmapSyncMode bitmap_mode;
     BlockdevOnError on_source_error;
     BlockdevOnError on_target_error;
-    CoRwlock flush_rwlock;
     uint64_t len;
     uint64_t bytes_read;
     int64_t cluster_size;
-    NotifierWithReturn before_write;
-    QLIST_HEAD(, CowRequest) inflight_reqs;
 
-    bool use_copy_range;
-    int64_t copy_range_size;
-
-    BdrvRequestFlags write_flags;
-    bool initializing_bitmap;
+    BlockCopyState *bcs;
 } BackupBlockJob;
 
 static const BlockJobDriver backup_job_driver;
 
-/* See if in-flight requests overlap and wait for them to complete */
-static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
-                                                       int64_t start,
-                                                       int64_t end)
+static void backup_progress_bytes_callback(int64_t bytes, void *opaque)
 {
-    CowRequest *req;
-    bool retry;
+    BackupBlockJob *s = opaque;
 
-    do {
-        retry = false;
-        QLIST_FOREACH(req, &job->inflight_reqs, list) {
-            if (end > req->start_byte && start < req->end_byte) {
-                qemu_co_queue_wait(&req->wait_queue, NULL);
-                retry = true;
-                break;
-            }
-        }
-    } while (retry);
+    s->bytes_read += bytes;
+    job_progress_update(&s->common.job, bytes);
 }
 
-/* Keep track of an in-flight request */
-static void cow_request_begin(CowRequest *req, BackupBlockJob *job,
-                              int64_t start, int64_t end)
+static void backup_progress_reset_callback(void *opaque)
 {
-    req->start_byte = start;
-    req->end_byte = end;
-    qemu_co_queue_init(&req->wait_queue);
-    QLIST_INSERT_HEAD(&job->inflight_reqs, req, list);
-}
+    BackupBlockJob *s = opaque;
+    uint64_t estimate = bdrv_get_dirty_count(s->bcs->copy_bitmap);
 
-/* Forget about a completed request */
-static void cow_request_end(CowRequest *req)
-{
-    QLIST_REMOVE(req, list);
-    qemu_co_queue_restart_all(&req->wait_queue);
-}
-
-/* Copy range to target with a bounce buffer and return the bytes copied. If
- * error occurred, return a negative error number */
-static int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job,
-                                                      int64_t start,
-                                                      int64_t end,
-                                                      bool is_write_notifier,
-                                                      bool *error_is_read,
-                                                      void **bounce_buffer)
-{
-    int ret;
-    BlockBackend *blk = job->common.blk;
-    int nbytes;
-    int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0;
-
-    assert(QEMU_IS_ALIGNED(start, job->cluster_size));
-    bdrv_reset_dirty_bitmap(job->copy_bitmap, start, job->cluster_size);
-    nbytes = MIN(job->cluster_size, job->len - start);
-    if (!*bounce_buffer) {
-        *bounce_buffer = blk_blockalign(blk, job->cluster_size);
-    }
-
-    ret = blk_co_pread(blk, start, nbytes, *bounce_buffer, read_flags);
-    if (ret < 0) {
-        trace_backup_do_cow_read_fail(job, start, ret);
-        if (error_is_read) {
-            *error_is_read = true;
-        }
-        goto fail;
-    }
-
-    ret = blk_co_pwrite(job->target, start, nbytes, *bounce_buffer,
-                        job->write_flags);
-    if (ret < 0) {
-        trace_backup_do_cow_write_fail(job, start, ret);
-        if (error_is_read) {
-            *error_is_read = false;
-        }
-        goto fail;
-    }
-
-    return nbytes;
-fail:
-    bdrv_set_dirty_bitmap(job->copy_bitmap, start, job->cluster_size);
-    return ret;
-
-}
-
-/* Copy range to target and return the bytes copied. If error occurred, return a
- * negative error number. */
-static int coroutine_fn backup_cow_with_offload(BackupBlockJob *job,
-                                                int64_t start,
-                                                int64_t end,
-                                                bool is_write_notifier)
-{
-    int ret;
-    int nr_clusters;
-    BlockBackend *blk = job->common.blk;
-    int nbytes;
-    int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0;
-
-    assert(QEMU_IS_ALIGNED(job->copy_range_size, job->cluster_size));
-    assert(QEMU_IS_ALIGNED(start, job->cluster_size));
-    nbytes = MIN(job->copy_range_size, end - start);
-    nr_clusters = DIV_ROUND_UP(nbytes, job->cluster_size);
-    bdrv_reset_dirty_bitmap(job->copy_bitmap, start,
-                            job->cluster_size * nr_clusters);
-    ret = blk_co_copy_range(blk, start, job->target, start, nbytes,
-                            read_flags, job->write_flags);
-    if (ret < 0) {
-        trace_backup_do_cow_copy_range_fail(job, start, ret);
-        bdrv_set_dirty_bitmap(job->copy_bitmap, start,
-                              job->cluster_size * nr_clusters);
-        return ret;
-    }
-
-    return nbytes;
-}
-
-/*
- * Check if the cluster starting at offset is allocated or not.
- * return via pnum the number of contiguous clusters sharing this allocation.
- */
-static int backup_is_cluster_allocated(BackupBlockJob *s, int64_t offset,
-                                       int64_t *pnum)
-{
-    BlockDriverState *bs = blk_bs(s->common.blk);
-    int64_t count, total_count = 0;
-    int64_t bytes = s->len - offset;
-    int ret;
-
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-
-    while (true) {
-        ret = bdrv_is_allocated(bs, offset, bytes, &count);
-        if (ret < 0) {
-            return ret;
-        }
-
-        total_count += count;
-
-        if (ret || count == 0) {
-            /*
-             * ret: partial segment(s) are considered allocated.
-             * otherwise: unallocated tail is treated as an entire segment.
-             */
-            *pnum = DIV_ROUND_UP(total_count, s->cluster_size);
-            return ret;
-        }
-
-        /* Unallocated segment(s) with uncertain following segment(s) */
-        if (total_count >= s->cluster_size) {
-            *pnum = total_count / s->cluster_size;
-            return 0;
-        }
-
-        offset += count;
-        bytes -= count;
-    }
-}
-
-/**
- * Reset bits in copy_bitmap starting at offset if they represent unallocated
- * data in the image. May reset subsequent contiguous bits.
- * @return 0 when the cluster at @offset was unallocated,
- *         1 otherwise, and -ret on error.
- */
-static int64_t backup_bitmap_reset_unallocated(BackupBlockJob *s,
-                                               int64_t offset, int64_t *count)
-{
-    int ret;
-    int64_t clusters, bytes, estimate;
-
-    ret = backup_is_cluster_allocated(s, offset, &clusters);
-    if (ret < 0) {
-        return ret;
-    }
-
-    bytes = clusters * s->cluster_size;
-
-    if (!ret) {
-        bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
-        estimate = bdrv_get_dirty_count(s->copy_bitmap);
-        job_progress_set_remaining(&s->common.job, estimate);
-    }
-
-    *count = bytes;
-    return ret;
+    job_progress_set_remaining(&s->common.job, estimate);
 }
 
 static int coroutine_fn backup_do_cow(BackupBlockJob *job,
                                       int64_t offset, uint64_t bytes,
-                                      bool *error_is_read,
-                                      bool is_write_notifier)
+                                      bool *error_is_read)
 {
-    CowRequest cow_request;
     int ret = 0;
     int64_t start, end; /* bytes */
-    void *bounce_buffer = NULL;
-    int64_t status_bytes;
-
-    qemu_co_rwlock_rdlock(&job->flush_rwlock);
 
     start = QEMU_ALIGN_DOWN(offset, job->cluster_size);
     end = QEMU_ALIGN_UP(bytes + offset, job->cluster_size);
 
     trace_backup_do_cow_enter(job, start, offset, bytes);
 
-    wait_for_overlapping_requests(job, start, end);
-    cow_request_begin(&cow_request, job, start, end);
-
-    while (start < end) {
-        int64_t dirty_end;
-
-        if (!bdrv_dirty_bitmap_get(job->copy_bitmap, start)) {
-            trace_backup_do_cow_skip(job, start);
-            start += job->cluster_size;
-            continue; /* already copied */
-        }
-
-        dirty_end = bdrv_dirty_bitmap_next_zero(job->copy_bitmap, start,
-                                                (end - start));
-        if (dirty_end < 0) {
-            dirty_end = end;
-        }
-
-        if (job->initializing_bitmap) {
-            ret = backup_bitmap_reset_unallocated(job, start, &status_bytes);
-            if (ret == 0) {
-                trace_backup_do_cow_skip_range(job, start, status_bytes);
-                start += status_bytes;
-                continue;
-            }
-            /* Clamp to known allocated region */
-            dirty_end = MIN(dirty_end, start + status_bytes);
-        }
-
-        trace_backup_do_cow_process(job, start);
-
-        if (job->use_copy_range) {
-            ret = backup_cow_with_offload(job, start, dirty_end,
-                                          is_write_notifier);
-            if (ret < 0) {
-                job->use_copy_range = false;
-            }
-        }
-        if (!job->use_copy_range) {
-            ret = backup_cow_with_bounce_buffer(job, start, dirty_end,
-                                                is_write_notifier,
-                                                error_is_read, &bounce_buffer);
-        }
-        if (ret < 0) {
-            break;
-        }
-
-        /* Publish progress, guest I/O counts as progress too.  Note that the
-         * offset field is an opaque progress value, it is not a disk offset.
-         */
-        start += ret;
-        job->bytes_read += ret;
-        job_progress_update(&job->common.job, ret);
-        ret = 0;
-    }
-
-    if (bounce_buffer) {
-        qemu_vfree(bounce_buffer);
-    }
-
-    cow_request_end(&cow_request);
+    ret = block_copy(job->bcs, start, end - start, error_is_read);
 
     trace_backup_do_cow_return(job, offset, bytes, ret);
 
-    qemu_co_rwlock_unlock(&job->flush_rwlock);
-
     return ret;
 }
 
-static int coroutine_fn backup_before_write_notify(
-        NotifierWithReturn *notifier,
-        void *opaque)
-{
-    BackupBlockJob *job = container_of(notifier, BackupBlockJob, before_write);
-    BdrvTrackedRequest *req = opaque;
-
-    assert(req->bs == blk_bs(job->common.blk));
-    assert(QEMU_IS_ALIGNED(req->offset, BDRV_SECTOR_SIZE));
-    assert(QEMU_IS_ALIGNED(req->bytes, BDRV_SECTOR_SIZE));
-
-    return backup_do_cow(job, req->offset, req->bytes, NULL, true);
-}
-
 static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
 {
     BdrvDirtyBitmap *bm;
-    BlockDriverState *bs = blk_bs(job->common.blk);
     bool sync = (((ret == 0) || (job->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS)) \
                  && (job->bitmap_mode != BITMAP_SYNC_MODE_NEVER));
 
@@ -361,20 +98,20 @@ static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
          * We succeeded, or we always intended to sync the bitmap.
          * Delete this bitmap and install the child.
          */
-        bm = bdrv_dirty_bitmap_abdicate(bs, job->sync_bitmap, NULL);
+        bm = bdrv_dirty_bitmap_abdicate(job->source_bs, job->sync_bitmap, NULL);
     } else {
         /*
          * We failed, or we never intended to sync the bitmap anyway.
          * Merge the successor back into the parent, keeping all data.
          */
-        bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL);
+        bm = bdrv_reclaim_dirty_bitmap(job->source_bs, job->sync_bitmap, NULL);
     }
 
     assert(bm);
 
     if (ret < 0 && job->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS) {
         /* If we failed and synced, merge in the bits we didn't copy: */
-        bdrv_dirty_bitmap_merge_internal(bm, job->copy_bitmap,
+        bdrv_dirty_bitmap_merge_internal(bm, job->bcs->copy_bitmap,
                                          NULL, true);
     }
 }
@@ -398,16 +135,8 @@ static void backup_abort(Job *job)
 static void backup_clean(Job *job)
 {
     BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
-    BlockDriverState *bs = blk_bs(s->common.blk);
 
-    if (s->copy_bitmap) {
-        bdrv_release_dirty_bitmap(bs, s->copy_bitmap);
-        s->copy_bitmap = NULL;
-    }
-
-    assert(s->target);
-    blk_unref(s->target);
-    s->target = NULL;
+    bdrv_backup_top_drop(s->backup_top);
 }
 
 void backup_do_checkpoint(BlockJob *job, Error **errp)
@@ -422,7 +151,7 @@ void backup_do_checkpoint(BlockJob *job, Error **errp)
         return;
     }
 
-    bdrv_set_dirty_bitmap(backup_job->copy_bitmap, 0, backup_job->len);
+    bdrv_set_dirty_bitmap(backup_job->bcs->copy_bitmap, 0, backup_job->len);
 }
 
 static BlockErrorAction backup_error_action(BackupBlockJob *job,
@@ -445,8 +174,10 @@ static bool coroutine_fn yield_and_check(BackupBlockJob *job)
         return true;
     }
 
-    /* We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
-     * return. Without a yield, the VM would not reboot. */
+    /*
+     * We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
+     * return. Without a yield, the VM would not reboot.
+     */
     delay_ns = block_job_ratelimit_get_delay(&job->common, job->bytes_read);
     job->bytes_read = 0;
     job_sleep_ns(&job->common.job, delay_ns);
@@ -465,14 +196,13 @@ static int coroutine_fn backup_loop(BackupBlockJob *job)
     BdrvDirtyBitmapIter *bdbi;
     int ret = 0;
 
-    bdbi = bdrv_dirty_iter_new(job->copy_bitmap);
+    bdbi = bdrv_dirty_iter_new(job->bcs->copy_bitmap);
     while ((offset = bdrv_dirty_iter_next(bdbi)) != -1) {
         do {
             if (yield_and_check(job)) {
                 goto out;
             }
-            ret = backup_do_cow(job, offset,
-                                job->cluster_size, &error_is_read, false);
+            ret = backup_do_cow(job, offset, job->cluster_size, &error_is_read);
             if (ret < 0 && backup_error_action(job, error_is_read, -ret) ==
                            BLOCK_ERROR_ACTION_REPORT)
             {
@@ -492,7 +222,7 @@ static void backup_init_copy_bitmap(BackupBlockJob *job)
     uint64_t estimate;
 
     if (job->sync_mode == MIRROR_SYNC_MODE_BITMAP) {
-        ret = bdrv_dirty_bitmap_merge_internal(job->copy_bitmap,
+        ret = bdrv_dirty_bitmap_merge_internal(job->bcs->copy_bitmap,
                                                job->sync_bitmap,
                                                NULL, true);
         assert(ret);
@@ -502,29 +232,22 @@ static void backup_init_copy_bitmap(BackupBlockJob *job)
              * We can't hog the coroutine to initialize this thoroughly.
              * Set a flag and resume work when we are able to yield safely.
              */
-            job->initializing_bitmap = true;
+            job->bcs->skip_unallocated = true;
         }
-        bdrv_set_dirty_bitmap(job->copy_bitmap, 0, job->len);
+        bdrv_set_dirty_bitmap(job->bcs->copy_bitmap, 0, job->len);
     }
 
-    estimate = bdrv_get_dirty_count(job->copy_bitmap);
+    estimate = bdrv_get_dirty_count(job->bcs->copy_bitmap);
     job_progress_set_remaining(&job->common.job, estimate);
 }
 
 static int coroutine_fn backup_run(Job *job, Error **errp)
 {
     BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
-    BlockDriverState *bs = blk_bs(s->common.blk);
     int ret = 0;
 
-    QLIST_INIT(&s->inflight_reqs);
-    qemu_co_rwlock_init(&s->flush_rwlock);
-
     backup_init_copy_bitmap(s);
 
-    s->before_write.notify = backup_before_write_notify;
-    bdrv_add_before_write_notifier(bs, &s->before_write);
-
     if (s->sync_mode == MIRROR_SYNC_MODE_TOP) {
         int64_t offset = 0;
         int64_t count;
@@ -535,22 +258,26 @@ static int coroutine_fn backup_run(Job *job, Error **errp)
                 goto out;
             }
 
-            ret = backup_bitmap_reset_unallocated(s, offset, &count);
+            ret = block_copy_reset_unallocated(s->bcs, offset, &count);
             if (ret < 0) {
                 goto out;
             }
 
             offset += count;
         }
-        s->initializing_bitmap = false;
+        s->bcs->skip_unallocated = false;
     }
 
     if (s->sync_mode == MIRROR_SYNC_MODE_NONE) {
-        /* All bits are set in copy_bitmap to allow any cluster to be copied.
-         * This does not actually require them to be copied. */
+        /*
+         * All bits are set in copy_bitmap to allow any cluster to be copied.
+         * This does not actually require them to be copied.
+         */
         while (!job_is_cancelled(job)) {
-            /* Yield until the job is cancelled.  We just let our before_write
-             * notify callback service CoW requests. */
+            /*
+             * Yield until the job is cancelled.  We just let our before_write
+             * notify callback service CoW requests.
+             */
             job_yield(job);
         }
     } else {
@@ -558,12 +285,6 @@ static int coroutine_fn backup_run(Job *job, Error **errp)
     }
 
  out:
-    notifier_with_return_remove(&s->before_write);
-
-    /* wait until pending backup_do_cow() calls have completed */
-    qemu_co_rwlock_wrlock(&s->flush_rwlock);
-    qemu_co_rwlock_unlock(&s->flush_rwlock);
-
     return ret;
 }
 
@@ -621,6 +342,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
                   MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
                   BitmapSyncMode bitmap_mode,
                   bool compress,
+                  const char *filter_node_name,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
                   int creation_flags,
@@ -629,9 +351,10 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
 {
     int64_t len;
     BackupBlockJob *job = NULL;
-    int ret;
     int64_t cluster_size;
-    BdrvDirtyBitmap *copy_bitmap = NULL;
+    BdrvRequestFlags write_flags;
+    BlockDriverState *backup_top = NULL;
+    BlockCopyState *bcs = NULL;
 
     assert(bs);
     assert(target);
@@ -696,76 +419,66 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         goto error;
     }
 
-    copy_bitmap = bdrv_create_dirty_bitmap(bs, cluster_size, NULL, errp);
-    if (!copy_bitmap) {
+    /*
+     * If source is in backing chain of target assume that target is going to be
+     * used for "image fleecing", i.e. it should represent a kind of snapshot of
+     * source at backup-start point in time. And target is going to be read by
+     * somebody (for example, used as NBD export) during backup job.
+     *
+     * In this case, we need to add BDRV_REQ_SERIALISING write flag to avoid
+     * intersection of backup writes and third party reads from target,
+     * otherwise reading from target we may occasionally read already updated by
+     * guest data.
+     *
+     * For more information see commit f8d59dfb40bb and test
+     * tests/qemu-iotests/222
+     */
+    write_flags = (bdrv_chain_contains(target, bs) ? BDRV_REQ_SERIALISING : 0) |
+                  (compress ? BDRV_REQ_WRITE_COMPRESSED : 0),
+
+    backup_top = bdrv_backup_top_append(bs, target, filter_node_name,
+                                        cluster_size, write_flags, &bcs, errp);
+    if (!backup_top) {
         goto error;
     }
-    bdrv_disable_dirty_bitmap(copy_bitmap);
 
     /* job->len is fixed, so we can't allow resize */
-    job = block_job_create(job_id, &backup_job_driver, txn, bs,
-                           BLK_PERM_CONSISTENT_READ,
-                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
-                           BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD,
+    job = block_job_create(job_id, &backup_job_driver, txn, backup_top,
+                           0, BLK_PERM_ALL,
                            speed, creation_flags, cb, opaque, errp);
     if (!job) {
         goto error;
     }
 
-    /* The target must match the source in size, so no resize here either */
-    job->target = blk_new(job->common.job.aio_context,
-                          BLK_PERM_WRITE,
-                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
-                          BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD);
-    ret = blk_insert_bs(job->target, target, errp);
-    if (ret < 0) {
-        goto error;
-    }
-    blk_set_disable_request_queuing(job->target, true);
-
+    job->backup_top = backup_top;
+    job->source_bs = bs;
     job->on_source_error = on_source_error;
     job->on_target_error = on_target_error;
     job->sync_mode = sync_mode;
     job->sync_bitmap = sync_bitmap;
     job->bitmap_mode = bitmap_mode;
-
-    /*
-     * Set write flags:
-     * 1. Detect image-fleecing (and similar) schemes
-     * 2. Handle compression
-     */
-    job->write_flags =
-        (bdrv_chain_contains(target, bs) ? BDRV_REQ_SERIALISING : 0) |
-        (compress ? BDRV_REQ_WRITE_COMPRESSED : 0);
-
+    job->bcs = bcs;
     job->cluster_size = cluster_size;
-    job->copy_bitmap = copy_bitmap;
-    copy_bitmap = NULL;
-    job->use_copy_range = !compress; /* compression isn't supported for it */
-    job->copy_range_size = MIN_NON_ZERO(blk_get_max_transfer(job->common.blk),
-                                        blk_get_max_transfer(job->target));
-    job->copy_range_size = MAX(job->cluster_size,
-                               QEMU_ALIGN_UP(job->copy_range_size,
-                                             job->cluster_size));
+    job->len = len;
 
-    /* Required permissions are already taken with target's blk_new() */
+    block_copy_set_callbacks(bcs, backup_progress_bytes_callback,
+                             backup_progress_reset_callback, job);
+
+    /* Required permissions are already taken by backup-top target */
     block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
                        &error_abort);
-    job->len = len;
 
     return &job->common;
 
  error:
-    if (copy_bitmap) {
-        assert(!job || !job->copy_bitmap);
-        bdrv_release_dirty_bitmap(bs, copy_bitmap);
-    }
     if (sync_bitmap) {
         bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
     }
     if (job) {
         backup_clean(&job->common.job);
         job_early_fail(&job->common.job);
+    } else if (backup_top) {
+        bdrv_backup_top_drop(backup_top);
     }
 
     return NULL;

block/block-copy.c

@@ -0,0 +1,345 @@
+/*
+ * block_copy API
+ *
+ * Copyright (C) 2013 Proxmox Server Solutions
+ * Copyright (c) 2019 Virtuozzo International GmbH.
+ *
+ * Authors:
+ *  Dietmar Maurer (dietmar@proxmox.com)
+ *  Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+
+#include "trace.h"
+#include "qapi/error.h"
+#include "block/block-copy.h"
+#include "sysemu/block-backend.h"
+
+static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s,
+                                                       int64_t start,
+                                                       int64_t end)
+{
+    BlockCopyInFlightReq *req;
+    bool waited;
+
+    do {
+        waited = false;
+        QLIST_FOREACH(req, &s->inflight_reqs, list) {
+            if (end > req->start_byte && start < req->end_byte) {
+                qemu_co_queue_wait(&req->wait_queue, NULL);
+                waited = true;
+                break;
+            }
+        }
+    } while (waited);
+}
+
+static void block_copy_inflight_req_begin(BlockCopyState *s,
+                                          BlockCopyInFlightReq *req,
+                                          int64_t start, int64_t end)
+{
+    req->start_byte = start;
+    req->end_byte = end;
+    qemu_co_queue_init(&req->wait_queue);
+    QLIST_INSERT_HEAD(&s->inflight_reqs, req, list);
+}
+
+static void coroutine_fn block_copy_inflight_req_end(BlockCopyInFlightReq *req)
+{
+    QLIST_REMOVE(req, list);
+    qemu_co_queue_restart_all(&req->wait_queue);
+}
+
+void block_copy_state_free(BlockCopyState *s)
+{
+    if (!s) {
+        return;
+    }
+
+    bdrv_release_dirty_bitmap(s->source->bs, s->copy_bitmap);
+    g_free(s);
+}
+
+BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                     int64_t cluster_size,
+                                     BdrvRequestFlags write_flags, Error **errp)
+{
+    BlockCopyState *s;
+    BdrvDirtyBitmap *copy_bitmap;
+    uint32_t max_transfer =
+            MIN_NON_ZERO(INT_MAX, MIN_NON_ZERO(source->bs->bl.max_transfer,
+                                               target->bs->bl.max_transfer));
+
+    copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL,
+                                           errp);
+    if (!copy_bitmap) {
+        return NULL;
+    }
+    bdrv_disable_dirty_bitmap(copy_bitmap);
+
+    s = g_new(BlockCopyState, 1);
+    *s = (BlockCopyState) {
+        .source = source,
+        .target = target,
+        .copy_bitmap = copy_bitmap,
+        .cluster_size = cluster_size,
+        .len = bdrv_dirty_bitmap_size(copy_bitmap),
+        .write_flags = write_flags,
+    };
+
+    s->copy_range_size = QEMU_ALIGN_DOWN(max_transfer, cluster_size),
+    /*
+     * Set use_copy_range, consider the following:
+     * 1. Compression is not supported for copy_range.
+     * 2. copy_range does not respect max_transfer (it's a TODO), so we factor
+     *    that in here. If max_transfer is smaller than the job->cluster_size,
+     *    we do not use copy_range (in that case it's zero after aligning down
+     *    above).
+     */
+    s->use_copy_range =
+        !(write_flags & BDRV_REQ_WRITE_COMPRESSED) && s->copy_range_size > 0;
+
+    QLIST_INIT(&s->inflight_reqs);
+
+    return s;
+}
+
+void block_copy_set_callbacks(
+        BlockCopyState *s,
+        ProgressBytesCallbackFunc progress_bytes_callback,
+        ProgressResetCallbackFunc progress_reset_callback,
+        void *progress_opaque)
+{
+    s->progress_bytes_callback = progress_bytes_callback;
+    s->progress_reset_callback = progress_reset_callback;
+    s->progress_opaque = progress_opaque;
+}
+
+/*
+ * Copy range to target with a bounce buffer and return the bytes copied. If
+ * error occurred, return a negative error number
+ */
+static int coroutine_fn block_copy_with_bounce_buffer(BlockCopyState *s,
+                                                      int64_t start,
+                                                      int64_t end,
+                                                      bool *error_is_read,
+                                                      void **bounce_buffer)
+{
+    int ret;
+    int nbytes;
+
+    assert(QEMU_IS_ALIGNED(start, s->cluster_size));
+    bdrv_reset_dirty_bitmap(s->copy_bitmap, start, s->cluster_size);
+    nbytes = MIN(s->cluster_size, s->len - start);
+    if (!*bounce_buffer) {
+        *bounce_buffer = qemu_blockalign(s->source->bs, s->cluster_size);
+    }
+
+    ret = bdrv_co_pread(s->source, start, nbytes, *bounce_buffer, 0);
+    if (ret < 0) {
+        trace_block_copy_with_bounce_buffer_read_fail(s, start, ret);
+        if (error_is_read) {
+            *error_is_read = true;
+        }
+        goto fail;
+    }
+
+    ret = bdrv_co_pwrite(s->target, start, nbytes, *bounce_buffer,
+                         s->write_flags);
+    if (ret < 0) {
+        trace_block_copy_with_bounce_buffer_write_fail(s, start, ret);
+        if (error_is_read) {
+            *error_is_read = false;
+        }
+        goto fail;
+    }
+
+    return nbytes;
+fail:
+    bdrv_set_dirty_bitmap(s->copy_bitmap, start, s->cluster_size);
+    return ret;
+
+}
+
+/*
+ * Copy range to target and return the bytes copied. If error occurred, return a
+ * negative error number.
+ */
+static int coroutine_fn block_copy_with_offload(BlockCopyState *s,
+                                                int64_t start,
+                                                int64_t end)
+{
+    int ret;
+    int nr_clusters;
+    int nbytes;
+
+    assert(QEMU_IS_ALIGNED(s->copy_range_size, s->cluster_size));
+    assert(QEMU_IS_ALIGNED(start, s->cluster_size));
+    nbytes = MIN(s->copy_range_size, MIN(end, s->len) - start);
+    nr_clusters = DIV_ROUND_UP(nbytes, s->cluster_size);
+    bdrv_reset_dirty_bitmap(s->copy_bitmap, start,
+                            s->cluster_size * nr_clusters);
+    ret = bdrv_co_copy_range(s->source, start, s->target, start, nbytes,
+                             0, s->write_flags);
+    if (ret < 0) {
+        trace_block_copy_with_offload_fail(s, start, ret);
+        bdrv_set_dirty_bitmap(s->copy_bitmap, start,
+                              s->cluster_size * nr_clusters);
+        return ret;
+    }
+
+    return nbytes;
+}
+
+/*
+ * Check if the cluster starting at offset is allocated or not.
+ * return via pnum the number of contiguous clusters sharing this allocation.
+ */
+static int block_copy_is_cluster_allocated(BlockCopyState *s, int64_t offset,
+                                           int64_t *pnum)
+{
+    BlockDriverState *bs = s->source->bs;
+    int64_t count, total_count = 0;
+    int64_t bytes = s->len - offset;
+    int ret;
+
+    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
+
+    while (true) {
+        ret = bdrv_is_allocated(bs, offset, bytes, &count);
+        if (ret < 0) {
+            return ret;
+        }
+
+        total_count += count;
+
+        if (ret || count == 0) {
+            /*
+             * ret: partial segment(s) are considered allocated.
+             * otherwise: unallocated tail is treated as an entire segment.
+             */
+            *pnum = DIV_ROUND_UP(total_count, s->cluster_size);
+            return ret;
+        }
+
+        /* Unallocated segment(s) with uncertain following segment(s) */
+        if (total_count >= s->cluster_size) {
+            *pnum = total_count / s->cluster_size;
+            return 0;
+        }
+
+        offset += count;
+        bytes -= count;
+    }
+}
+
+/*
+ * Reset bits in copy_bitmap starting at offset if they represent unallocated
+ * data in the image. May reset subsequent contiguous bits.
+ * @return 0 when the cluster at @offset was unallocated,
+ *         1 otherwise, and -ret on error.
+ */
+int64_t block_copy_reset_unallocated(BlockCopyState *s,
+                                     int64_t offset, int64_t *count)
+{
+    int ret;
+    int64_t clusters, bytes;
+
+    ret = block_copy_is_cluster_allocated(s, offset, &clusters);
+    if (ret < 0) {
+        return ret;
+    }
+
+    bytes = clusters * s->cluster_size;
+
+    if (!ret) {
+        bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
+        s->progress_reset_callback(s->progress_opaque);
+    }
+
+    *count = bytes;
+    return ret;
+}
+
+int coroutine_fn block_copy(BlockCopyState *s,
+                            int64_t start, uint64_t bytes,
+                            bool *error_is_read)
+{
+    int ret = 0;
+    int64_t end = bytes + start; /* bytes */
+    void *bounce_buffer = NULL;
+    int64_t status_bytes;
+    BlockCopyInFlightReq req;
+
+    /*
+     * block_copy() user is responsible for keeping source and target in same
+     * aio context
+     */
+    assert(bdrv_get_aio_context(s->source->bs) ==
+           bdrv_get_aio_context(s->target->bs));
+
+    assert(QEMU_IS_ALIGNED(start, s->cluster_size));
+    assert(QEMU_IS_ALIGNED(end, s->cluster_size));
+
+    block_copy_wait_inflight_reqs(s, start, bytes);
+    block_copy_inflight_req_begin(s, &req, start, end);
+
+    while (start < end) {
+        int64_t dirty_end;
+
+        if (!bdrv_dirty_bitmap_get(s->copy_bitmap, start)) {
+            trace_block_copy_skip(s, start);
+            start += s->cluster_size;
+            continue; /* already copied */
+        }
+
+        dirty_end = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, start,
+                                                (end - start));
+        if (dirty_end < 0) {
+            dirty_end = end;
+        }
+
+        if (s->skip_unallocated) {
+            ret = block_copy_reset_unallocated(s, start, &status_bytes);
+            if (ret == 0) {
+                trace_block_copy_skip_range(s, start, status_bytes);
+                start += status_bytes;
+                continue;
+            }
+            /* Clamp to known allocated region */
+            dirty_end = MIN(dirty_end, start + status_bytes);
+        }
+
+        trace_block_copy_process(s, start);
+
+        if (s->use_copy_range) {
+            ret = block_copy_with_offload(s, start, dirty_end);
+            if (ret < 0) {
+                s->use_copy_range = false;
+            }
+        }
+        if (!s->use_copy_range) {
+            ret = block_copy_with_bounce_buffer(s, start, dirty_end,
+                                                error_is_read, &bounce_buffer);
+        }
+        if (ret < 0) {
+            break;
+        }
+
+        start += ret;
+        s->progress_bytes_callback(ret, s->progress_opaque);
+        ret = 0;
+    }
+
+    if (bounce_buffer) {
+        qemu_vfree(bounce_buffer);
+    }
+
+    block_copy_inflight_req_end(&req);
+
+    return ret;
+}

block/file-posix.c

@@ -161,6 +161,11 @@ typedef struct BDRVRawState {
     bool needs_alignment;
     bool drop_cache;
     bool check_cache_dropped;
+    struct {
+        uint64_t discard_nb_ok;
+        uint64_t discard_nb_failed;
+        uint64_t discard_bytes_ok;
+    } stats;
 
     PRManager *pr_mgr;
 } BDRVRawState;
@@ -2660,11 +2665,22 @@ static void coroutine_fn raw_co_invalidate_cache(BlockDriverState *bs,
 #endif /* !__linux__ */
 }
 
+static void raw_account_discard(BDRVRawState *s, uint64_t nbytes, int ret)
+{
+    if (ret) {
+        s->stats.discard_nb_failed++;
+    } else {
+        s->stats.discard_nb_ok++;
+        s->stats.discard_bytes_ok += nbytes;
+    }
+}
+
 static coroutine_fn int
 raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int bytes, bool blkdev)
 {
     BDRVRawState *s = bs->opaque;
     RawPosixAIOData acb;
+    int ret;
 
     acb = (RawPosixAIOData) {
         .bs             = bs,
@@ -2678,7 +2694,9 @@ raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int bytes, bool blkdev)
         acb.aio_type |= QEMU_AIO_BLKDEV;
     }
 
-    return raw_thread_pool_submit(bs, handle_aiocb_discard, &acb);
+    ret = raw_thread_pool_submit(bs, handle_aiocb_discard, &acb);
+    raw_account_discard(s, bytes, ret);
+    return ret;
 }
 
 static coroutine_fn int
@@ -2735,6 +2753,36 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
+static BlockStatsSpecificFile get_blockstats_specific_file(BlockDriverState *bs)
+{
+    BDRVRawState *s = bs->opaque;
+    return (BlockStatsSpecificFile) {
+        .discard_nb_ok = s->stats.discard_nb_ok,
+        .discard_nb_failed = s->stats.discard_nb_failed,
+        .discard_bytes_ok = s->stats.discard_bytes_ok,
+    };
+}
+
+static BlockStatsSpecific *raw_get_specific_stats(BlockDriverState *bs)
+{
+    BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1);
+
+    stats->driver = BLOCKDEV_DRIVER_FILE;
+    stats->u.file = get_blockstats_specific_file(bs);
+
+    return stats;
+}
+
+static BlockStatsSpecific *hdev_get_specific_stats(BlockDriverState *bs)
+{
+    BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1);
+
+    stats->driver = BLOCKDEV_DRIVER_HOST_DEVICE;
+    stats->u.host_device = get_blockstats_specific_file(bs);
+
+    return stats;
+}
+
 static QemuOptsList raw_create_opts = {
     .name = "raw-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
@@ -2942,6 +2990,7 @@ BlockDriver bdrv_file = {
     .bdrv_get_info = raw_get_info,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
+    .bdrv_get_specific_stats = raw_get_specific_stats,
     .bdrv_check_perm = raw_check_perm,
     .bdrv_set_perm   = raw_set_perm,
     .bdrv_abort_perm_update = raw_abort_perm_update,
@@ -3301,10 +3350,12 @@ static int fd_open(BlockDriverState *bs)
 static coroutine_fn int
 hdev_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
 {
+    BDRVRawState *s = bs->opaque;
     int ret;
 
     ret = fd_open(bs);
     if (ret < 0) {
+        raw_account_discard(s, bytes, ret);
         return ret;
     }
     return raw_do_pdiscard(bs, offset, bytes, true);
@@ -3418,6 +3469,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_get_info = raw_get_info,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
+    .bdrv_get_specific_stats = hdev_get_specific_stats,
     .bdrv_check_perm = raw_check_perm,
     .bdrv_set_perm   = raw_set_perm,
     .bdrv_abort_perm_update = raw_abort_perm_update,

block/nbd.c

@@ -1158,6 +1158,18 @@ static int coroutine_fn nbd_client_co_block_status(
         BDRV_BLOCK_OFFSET_VALID;
 }
 
+static int nbd_client_reopen_prepare(BDRVReopenState *state,
+                                     BlockReopenQueue *queue, Error **errp)
+{
+    BDRVNBDState *s = (BDRVNBDState *)state->bs->opaque;
+
+    if ((state->flags & BDRV_O_RDWR) && (s->info.flags & NBD_FLAG_READ_ONLY)) {
+        error_setg(errp, "Can't reopen read-only NBD mount as read/write");
+        return -EACCES;
+    }
+    return 0;
+}
+
 static void nbd_client_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
@@ -1798,6 +1810,7 @@ static BlockDriver bdrv_nbd = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
+    .bdrv_reopen_prepare        = nbd_client_reopen_prepare,
     .bdrv_co_preadv             = nbd_client_co_preadv,
     .bdrv_co_pwritev            = nbd_client_co_pwritev,
     .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
@@ -1820,6 +1833,7 @@ static BlockDriver bdrv_nbd_tcp = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
+    .bdrv_reopen_prepare        = nbd_client_reopen_prepare,
     .bdrv_co_preadv             = nbd_client_co_preadv,
     .bdrv_co_pwritev            = nbd_client_co_pwritev,
     .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
@@ -1842,6 +1856,7 @@ static BlockDriver bdrv_nbd_unix = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
+    .bdrv_reopen_prepare        = nbd_client_reopen_prepare,
     .bdrv_co_preadv             = nbd_client_co_preadv,
     .bdrv_co_pwritev            = nbd_client_co_pwritev,
     .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,

block/qapi.c

@@ -440,24 +440,30 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
 
     ds->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
     ds->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
+    ds->unmap_bytes = stats->nr_bytes[BLOCK_ACCT_UNMAP];
     ds->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
     ds->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
+    ds->unmap_operations = stats->nr_ops[BLOCK_ACCT_UNMAP];
 
     ds->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
     ds->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
     ds->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
+    ds->failed_unmap_operations = stats->failed_ops[BLOCK_ACCT_UNMAP];
 
     ds->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
     ds->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
     ds->invalid_flush_operations =
         stats->invalid_ops[BLOCK_ACCT_FLUSH];
+    ds->invalid_unmap_operations = stats->invalid_ops[BLOCK_ACCT_UNMAP];
 
     ds->rd_merged = stats->merged[BLOCK_ACCT_READ];
     ds->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
+    ds->unmap_merged = stats->merged[BLOCK_ACCT_UNMAP];
     ds->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
     ds->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
     ds->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
     ds->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
+    ds->unmap_total_time_ns = stats->total_time_ns[BLOCK_ACCT_UNMAP];
 
     ds->has_idle_time_ns = stats->last_access_time_ns > 0;
     if (ds->has_idle_time_ns) {
@@ -537,6 +543,11 @@ static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
 
     s->stats->wr_highest_offset = stat64_get(&bs->wr_highest_offset);
 
+    s->driver_specific = bdrv_get_specific_stats(bs);
+    if (s->driver_specific) {
+        s->has_driver_specific = true;
+    }
+
     if (bs->file) {
         s->has_parent = true;
         s->parent = bdrv_query_bds_stats(bs->file->bs, blk_level);

block/qcow2.c

@@ -41,6 +41,7 @@
 #include "qapi/qobject-input-visitor.h"
 #include "qapi/qapi-visit-block-core.h"
 #include "crypto.h"
+#include "block/aio_task.h"
 
 /*
   Differences with QCOW:
@@ -1972,20 +1973,184 @@ out:
     return ret;
 }
 
+static coroutine_fn int
+qcow2_co_preadv_encrypted(BlockDriverState *bs,
+                           uint64_t file_cluster_offset,
+                           uint64_t offset,
+                           uint64_t bytes,
+                           QEMUIOVector *qiov,
+                           uint64_t qiov_offset)
+{
+    int ret;
+    BDRVQcow2State *s = bs->opaque;
+    uint8_t *buf;
+
+    assert(bs->encrypted && s->crypto);
+    assert(bytes <= QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
+
+    /*
+     * For encrypted images, read everything into a temporary
+     * contiguous buffer on which the AES functions can work.
+     * Also, decryption in a separate buffer is better as it
+     * prevents the guest from learning information about the
+     * encrypted nature of the virtual disk.
+     */
+
+    buf = qemu_try_blockalign(s->data_file->bs, bytes);
+    if (buf == NULL) {
+        return -ENOMEM;
+    }
+
+    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
+    ret = bdrv_co_pread(s->data_file,
+                        file_cluster_offset + offset_into_cluster(s, offset),
+                        bytes, buf, 0);
+    if (ret < 0) {
+        goto fail;
+    }
+
+    assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
+    assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));
+    if (qcow2_co_decrypt(bs,
+                         file_cluster_offset + offset_into_cluster(s, offset),
+                         offset, buf, bytes) < 0)
+    {
+        ret = -EIO;
+        goto fail;
+    }
+    qemu_iovec_from_buf(qiov, qiov_offset, buf, bytes);
+
+fail:
+    qemu_vfree(buf);
+
+    return ret;
+}
+
+typedef struct Qcow2AioTask {
+    AioTask task;
+
+    BlockDriverState *bs;
+    QCow2ClusterType cluster_type; /* only for read */
+    uint64_t file_cluster_offset;
+    uint64_t offset;
+    uint64_t bytes;
+    QEMUIOVector *qiov;
+    uint64_t qiov_offset;
+    QCowL2Meta *l2meta; /* only for write */
+} Qcow2AioTask;
+
+static coroutine_fn int qcow2_co_preadv_task_entry(AioTask *task);
+static coroutine_fn int qcow2_add_task(BlockDriverState *bs,
+                                       AioTaskPool *pool,
+                                       AioTaskFunc func,
+                                       QCow2ClusterType cluster_type,
+                                       uint64_t file_cluster_offset,
+                                       uint64_t offset,
+                                       uint64_t bytes,
+                                       QEMUIOVector *qiov,
+                                       size_t qiov_offset,
+                                       QCowL2Meta *l2meta)
+{
+    Qcow2AioTask local_task;
+    Qcow2AioTask *task = pool ? g_new(Qcow2AioTask, 1) : &local_task;
+
+    *task = (Qcow2AioTask) {
+        .task.func = func,
+        .bs = bs,
+        .cluster_type = cluster_type,
+        .qiov = qiov,
+        .file_cluster_offset = file_cluster_offset,
+        .offset = offset,
+        .bytes = bytes,
+        .qiov_offset = qiov_offset,
+        .l2meta = l2meta,
+    };
+
+    trace_qcow2_add_task(qemu_coroutine_self(), bs, pool,
+                         func == qcow2_co_preadv_task_entry ? "read" : "write",
+                         cluster_type, file_cluster_offset, offset, bytes,
+                         qiov, qiov_offset);
+
+    if (!pool) {
+        return func(&task->task);
+    }
+
+    aio_task_pool_start_task(pool, &task->task);
+
+    return 0;
+}
+
+static coroutine_fn int qcow2_co_preadv_task(BlockDriverState *bs,
+                                             QCow2ClusterType cluster_type,
+                                             uint64_t file_cluster_offset,
+                                             uint64_t offset, uint64_t bytes,
+                                             QEMUIOVector *qiov,
+                                             size_t qiov_offset)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int offset_in_cluster = offset_into_cluster(s, offset);
+
+    switch (cluster_type) {
+    case QCOW2_CLUSTER_ZERO_PLAIN:
+    case QCOW2_CLUSTER_ZERO_ALLOC:
+        /* Both zero types are handled in qcow2_co_preadv_part */
+        g_assert_not_reached();
+
+    case QCOW2_CLUSTER_UNALLOCATED:
+        assert(bs->backing); /* otherwise handled in qcow2_co_preadv_part */
+
+        BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
+        return bdrv_co_preadv_part(bs->backing, offset, bytes,
+                                   qiov, qiov_offset, 0);
+
+    case QCOW2_CLUSTER_COMPRESSED:
+        return qcow2_co_preadv_compressed(bs, file_cluster_offset,
+                                          offset, bytes, qiov, qiov_offset);
+
+    case QCOW2_CLUSTER_NORMAL:
+        if ((file_cluster_offset & 511) != 0) {
+            return -EIO;
+        }
+
+        if (bs->encrypted) {
+            return qcow2_co_preadv_encrypted(bs, file_cluster_offset,
+                                             offset, bytes, qiov, qiov_offset);
+        }
+
+        BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
+        return bdrv_co_preadv_part(s->data_file,
+                                   file_cluster_offset + offset_in_cluster,
+                                   bytes, qiov, qiov_offset, 0);
+
+    default:
+        g_assert_not_reached();
+    }
+
+    g_assert_not_reached();
+}
+
+static coroutine_fn int qcow2_co_preadv_task_entry(AioTask *task)
+{
+    Qcow2AioTask *t = container_of(task, Qcow2AioTask, task);
+
+    assert(!t->l2meta);
+
+    return qcow2_co_preadv_task(t->bs, t->cluster_type, t->file_cluster_offset,
+                                t->offset, t->bytes, t->qiov, t->qiov_offset);
+}
+
 static coroutine_fn int qcow2_co_preadv_part(BlockDriverState *bs,
                                              uint64_t offset, uint64_t bytes,
                                              QEMUIOVector *qiov,
                                              size_t qiov_offset, int flags)
 {
     BDRVQcow2State *s = bs->opaque;
-    int offset_in_cluster;
-    int ret;
+    int ret = 0;
     unsigned int cur_bytes; /* number of bytes in current iteration */
     uint64_t cluster_offset = 0;
-    uint8_t *cluster_data = NULL;
-
-    while (bytes != 0) {
+    AioTaskPool *aio = NULL;
 
+    while (bytes != 0 && aio_task_pool_status(aio) == 0) {
         /* prepare next request */
         cur_bytes = MIN(bytes, INT_MAX);
         if (s->crypto) {
@@ -1997,110 +2162,39 @@ static coroutine_fn int qcow2_co_preadv_part(BlockDriverState *bs,
         ret = qcow2_get_cluster_offset(bs, offset, &cur_bytes, &cluster_offset);
         qemu_co_mutex_unlock(&s->lock);
         if (ret < 0) {
-            goto fail;
+            goto out;
         }
 
-        offset_in_cluster = offset_into_cluster(s, offset);
-
-        switch (ret) {
-        case QCOW2_CLUSTER_UNALLOCATED:
-
-            if (bs->backing) {
-                BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
-                ret = bdrv_co_preadv_part(bs->backing, offset, cur_bytes,
-                                          qiov, qiov_offset, 0);
-                if (ret < 0) {
-                    goto fail;
-                }
-            } else {
-                /* Note: in this case, no need to wait */
-                qemu_iovec_memset(qiov, qiov_offset, 0, cur_bytes);
-            }
-            break;
-
-        case QCOW2_CLUSTER_ZERO_PLAIN:
-        case QCOW2_CLUSTER_ZERO_ALLOC:
+        if (ret == QCOW2_CLUSTER_ZERO_PLAIN ||
+            ret == QCOW2_CLUSTER_ZERO_ALLOC ||
+            (ret == QCOW2_CLUSTER_UNALLOCATED && !bs->backing))
+        {
             qemu_iovec_memset(qiov, qiov_offset, 0, cur_bytes);
-            break;
-
-        case QCOW2_CLUSTER_COMPRESSED:
-            ret = qcow2_co_preadv_compressed(bs, cluster_offset,
-                                             offset, cur_bytes,
-                                             qiov, qiov_offset);
+        } else {
+            if (!aio && cur_bytes != bytes) {
+                aio = aio_task_pool_new(QCOW2_MAX_WORKERS);
+            }
+            ret = qcow2_add_task(bs, aio, qcow2_co_preadv_task_entry, ret,
+                                 cluster_offset, offset, cur_bytes,
+                                 qiov, qiov_offset, NULL);
             if (ret < 0) {
-                goto fail;
+                goto out;
             }
-
-            break;
-
-        case QCOW2_CLUSTER_NORMAL:
-            if ((cluster_offset & 511) != 0) {
-                ret = -EIO;
-                goto fail;
-            }
-
-            if (bs->encrypted) {
-                assert(s->crypto);
-
-                /*
-                 * For encrypted images, read everything into a temporary
-                 * contiguous buffer on which the AES functions can work.
-                 */
-                if (!cluster_data) {
-                    cluster_data =
-                        qemu_try_blockalign(s->data_file->bs,
-                                            QCOW_MAX_CRYPT_CLUSTERS
-                                            * s->cluster_size);
-                    if (cluster_data == NULL) {
-                        ret = -ENOMEM;
-                        goto fail;
-                    }
-                }
-
-                assert(cur_bytes <= QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
-
-                BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-                ret = bdrv_co_pread(s->data_file,
-                                    cluster_offset + offset_in_cluster,
-                                    cur_bytes, cluster_data, 0);
-                if (ret < 0) {
-                    goto fail;
-                }
-
-                assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
-                assert(QEMU_IS_ALIGNED(cur_bytes, BDRV_SECTOR_SIZE));
-                if (qcow2_co_decrypt(bs, cluster_offset + offset_in_cluster,
-                                     offset,
-                                     cluster_data, cur_bytes) < 0) {
-                    ret = -EIO;
-                    goto fail;
-                }
-                qemu_iovec_from_buf(qiov, qiov_offset, cluster_data, cur_bytes);
-            } else {
-                BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-                ret = bdrv_co_preadv_part(s->data_file,
-                                          cluster_offset + offset_in_cluster,
-                                          cur_bytes, qiov, qiov_offset, 0);
-                if (ret < 0) {
-                    goto fail;
-                }
-            }
-            break;
-
-        default:
-            g_assert_not_reached();
-            ret = -EIO;
-            goto fail;
         }
 
         bytes -= cur_bytes;
         offset += cur_bytes;
         qiov_offset += cur_bytes;
     }
-    ret = 0;
 
-fail:
-    qemu_vfree(cluster_data);
+out:
+    if (aio) {
+        aio_task_pool_wait_all(aio);
+        if (ret == 0) {
+            ret = aio_task_pool_status(aio);
+        }
+        g_free(aio);
+    }
 
     return ret;
 }
@@ -2225,6 +2319,99 @@ static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta)
     return 0;
 }
 
+/*
+ * qcow2_co_pwritev_task
+ * Called with s->lock unlocked
+ * l2meta  - if not NULL, qcow2_co_pwritev_task() will consume it. Caller must
+ *           not use it somehow after qcow2_co_pwritev_task() call
+ */
+static coroutine_fn int qcow2_co_pwritev_task(BlockDriverState *bs,
+                                              uint64_t file_cluster_offset,
+                                              uint64_t offset, uint64_t bytes,
+                                              QEMUIOVector *qiov,
+                                              uint64_t qiov_offset,
+                                              QCowL2Meta *l2meta)
+{
+    int ret;
+    BDRVQcow2State *s = bs->opaque;
+    void *crypt_buf = NULL;
+    int offset_in_cluster = offset_into_cluster(s, offset);
+    QEMUIOVector encrypted_qiov;
+
+    if (bs->encrypted) {
+        assert(s->crypto);
+        assert(bytes <= QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
+        crypt_buf = qemu_try_blockalign(bs->file->bs, bytes);
+        if (crypt_buf == NULL) {
+            ret = -ENOMEM;
+            goto out_unlocked;
+        }
+        qemu_iovec_to_buf(qiov, qiov_offset, crypt_buf, bytes);
+
+        if (qcow2_co_encrypt(bs, file_cluster_offset + offset_in_cluster,
+                             offset, crypt_buf, bytes) < 0)
+        {
+            ret = -EIO;
+            goto out_unlocked;
+        }
+
+        qemu_iovec_init_buf(&encrypted_qiov, crypt_buf, bytes);
+        qiov = &encrypted_qiov;
+        qiov_offset = 0;
+    }
+
+    /* Try to efficiently initialize the physical space with zeroes */
+    ret = handle_alloc_space(bs, l2meta);
+    if (ret < 0) {
+        goto out_unlocked;
+    }
+
+    /*
+     * If we need to do COW, check if it's possible to merge the
+     * writing of the guest data together with that of the COW regions.
+     * If it's not possible (or not necessary) then write the
+     * guest data now.
+     */
+    if (!merge_cow(offset, bytes, qiov, qiov_offset, l2meta)) {
+        BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+        trace_qcow2_writev_data(qemu_coroutine_self(),
+                                file_cluster_offset + offset_in_cluster);
+        ret = bdrv_co_pwritev_part(s->data_file,
+                                   file_cluster_offset + offset_in_cluster,
+                                   bytes, qiov, qiov_offset, 0);
+        if (ret < 0) {
+            goto out_unlocked;
+        }
+    }
+
+    qemu_co_mutex_lock(&s->lock);
+
+    ret = qcow2_handle_l2meta(bs, &l2meta, true);
+    goto out_locked;
+
+out_unlocked:
+    qemu_co_mutex_lock(&s->lock);
+
+out_locked:
+    qcow2_handle_l2meta(bs, &l2meta, false);
+    qemu_co_mutex_unlock(&s->lock);
+
+    qemu_vfree(crypt_buf);
+
+    return ret;
+}
+
+static coroutine_fn int qcow2_co_pwritev_task_entry(AioTask *task)
+{
+    Qcow2AioTask *t = container_of(task, Qcow2AioTask, task);
+
+    assert(!t->cluster_type);
+
+    return qcow2_co_pwritev_task(t->bs, t->file_cluster_offset,
+                                 t->offset, t->bytes, t->qiov, t->qiov_offset,
+                                 t->l2meta);
+}
+
 static coroutine_fn int qcow2_co_pwritev_part(
         BlockDriverState *bs, uint64_t offset, uint64_t bytes,
         QEMUIOVector *qiov, size_t qiov_offset, int flags)
@@ -2234,16 +2421,12 @@ static coroutine_fn int qcow2_co_pwritev_part(
     int ret;
     unsigned int cur_bytes; /* number of sectors in current iteration */
     uint64_t cluster_offset;
-    QEMUIOVector encrypted_qiov;
-    uint64_t bytes_done = 0;
-    uint8_t *cluster_data = NULL;
     QCowL2Meta *l2meta = NULL;
+    AioTaskPool *aio = NULL;
 
     trace_qcow2_writev_start_req(qemu_coroutine_self(), offset, bytes);
 
-    qemu_co_mutex_lock(&s->lock);
-
-    while (bytes != 0) {
+    while (bytes != 0 && aio_task_pool_status(aio) == 0) {
 
         l2meta = NULL;
 
@@ -2256,6 +2439,8 @@ static coroutine_fn int qcow2_co_pwritev_part(
                             - offset_in_cluster);
         }
 
+        qemu_co_mutex_lock(&s->lock);
+
         ret = qcow2_alloc_cluster_offset(bs, offset, &cur_bytes,
                                          &cluster_offset, &l2meta);
         if (ret < 0) {
@@ -2273,73 +2458,24 @@ static coroutine_fn int qcow2_co_pwritev_part(
 
         qemu_co_mutex_unlock(&s->lock);
 
-        if (bs->encrypted) {
-            assert(s->crypto);
-            if (!cluster_data) {
-                cluster_data = qemu_try_blockalign(bs->file->bs,
-                                                   QCOW_MAX_CRYPT_CLUSTERS
-                                                   * s->cluster_size);
-                if (cluster_data == NULL) {
-                    ret = -ENOMEM;
-                    goto out_unlocked;
-                }
-            }
-
-            assert(cur_bytes <= QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
-            qemu_iovec_to_buf(qiov, qiov_offset + bytes_done,
-                              cluster_data, cur_bytes);
-
-            if (qcow2_co_encrypt(bs, cluster_offset + offset_in_cluster, offset,
-                                 cluster_data, cur_bytes) < 0) {
-                ret = -EIO;
-                goto out_unlocked;
-            }
-
-            qemu_iovec_init_buf(&encrypted_qiov, cluster_data, cur_bytes);
+        if (!aio && cur_bytes != bytes) {
+            aio = aio_task_pool_new(QCOW2_MAX_WORKERS);
         }
-
-        /* Try to efficiently initialize the physical space with zeroes */
-        ret = handle_alloc_space(bs, l2meta);
+        ret = qcow2_add_task(bs, aio, qcow2_co_pwritev_task_entry, 0,
+                             cluster_offset, offset, cur_bytes,
+                             qiov, qiov_offset, l2meta);
+        l2meta = NULL; /* l2meta is consumed by qcow2_co_pwritev_task() */
         if (ret < 0) {
-            goto out_unlocked;
-        }
-
-        /* If we need to do COW, check if it's possible to merge the
-         * writing of the guest data together with that of the COW regions.
-         * If it's not possible (or not necessary) then write the
-         * guest data now. */
-        if (!merge_cow(offset, cur_bytes,
-                       bs->encrypted ? &encrypted_qiov : qiov,
-                       bs->encrypted ? 0 : qiov_offset + bytes_done, l2meta))
-        {
-            BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
-            trace_qcow2_writev_data(qemu_coroutine_self(),
-                                    cluster_offset + offset_in_cluster);
-            ret = bdrv_co_pwritev_part(
-                    s->data_file, cluster_offset + offset_in_cluster, cur_bytes,
-                    bs->encrypted ? &encrypted_qiov : qiov,
-                    bs->encrypted ? 0 : qiov_offset + bytes_done, 0);
-            if (ret < 0) {
-                goto out_unlocked;
-            }
-        }
-
-        qemu_co_mutex_lock(&s->lock);
-
-        ret = qcow2_handle_l2meta(bs, &l2meta, true);
-        if (ret) {
-            goto out_locked;
+            goto fail_nometa;
         }
 
         bytes -= cur_bytes;
         offset += cur_bytes;
-        bytes_done += cur_bytes;
+        qiov_offset += cur_bytes;
         trace_qcow2_writev_done_part(qemu_coroutine_self(), cur_bytes);
     }
     ret = 0;
-    goto out_locked;
 
-out_unlocked:
     qemu_co_mutex_lock(&s->lock);
 
 out_locked:
@@ -2347,7 +2483,15 @@ out_locked:
 
     qemu_co_mutex_unlock(&s->lock);
 
-    qemu_vfree(cluster_data);
+fail_nometa:
+    if (aio) {
+        aio_task_pool_wait_all(aio);
+        if (ret == 0) {
+            ret = aio_task_pool_status(aio);
+        }
+        g_free(aio);
+    }
+
     trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
 
     return ret;

block/qcow2.h

@@ -65,6 +65,9 @@
 #define QCOW2_MAX_BITMAPS 65535
 #define QCOW2_MAX_BITMAP_DIRECTORY_SIZE (1024 * QCOW2_MAX_BITMAPS)
 
+/* Maximum of parallel sub-request per guest request */
+#define QCOW2_MAX_WORKERS 8
+
 /* indicate that the refcount of the referenced cluster is exactly one. */
 #define QCOW_OFLAG_COPIED     (1ULL << 63)
 /* indicate that the cluster is compressed (they never have the copied flag) */

block/replication.c

@@ -543,7 +543,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode,
 
         s->backup_job = backup_job_create(
                                 NULL, s->secondary_disk->bs, s->hidden_disk->bs,
-                                0, MIRROR_SYNC_MODE_NONE, NULL, 0, false,
+                                0, MIRROR_SYNC_MODE_NONE, NULL, 0, false, NULL,
                                 BLOCKDEV_ON_ERROR_REPORT,
                                 BLOCKDEV_ON_ERROR_REPORT, JOB_INTERNAL,
                                 backup_job_completed, bs, NULL, &local_err);

block/trace-events

@@ -40,12 +40,14 @@ mirror_yield_in_flight(void *s, int64_t offset, int in_flight) "s %p offset %" P
 # backup.c
 backup_do_cow_enter(void *job, int64_t start, int64_t offset, uint64_t bytes) "job %p start %" PRId64 " offset %" PRId64 " bytes %" PRIu64
 backup_do_cow_return(void *job, int64_t offset, uint64_t bytes, int ret) "job %p offset %" PRId64 " bytes %" PRIu64 " ret %d"
-backup_do_cow_skip(void *job, int64_t start) "job %p start %"PRId64
-backup_do_cow_skip_range(void *job, int64_t start, uint64_t bytes) "job %p start %"PRId64" bytes %"PRId64
-backup_do_cow_process(void *job, int64_t start) "job %p start %"PRId64
-backup_do_cow_read_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
-backup_do_cow_write_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
-backup_do_cow_copy_range_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
+
+# block-copy.c
+block_copy_skip(void *bcs, int64_t start) "bcs %p start %"PRId64
+block_copy_skip_range(void *bcs, int64_t start, uint64_t bytes) "bcs %p start %"PRId64" bytes %"PRId64
+block_copy_process(void *bcs, int64_t start) "bcs %p start %"PRId64
+block_copy_with_bounce_buffer_read_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d"
+block_copy_with_bounce_buffer_write_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d"
+block_copy_with_offload_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d"
 
 # ../blockdev.c
 qmp_block_job_cancel(void *job) "job %p"
@@ -62,6 +64,7 @@ file_paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "
 file_copy_file_range(void *bs, int src, int64_t src_off, int dst, int64_t dst_off, int64_t bytes, int flags, int64_t ret) "bs %p src_fd %d offset %"PRIu64" dst_fd %d offset %"PRIu64" bytes %"PRIu64" flags %d ret %"PRId64
 
 # qcow2.c
+qcow2_add_task(void *co, void *bs, void *pool, const char *action, int cluster_type, uint64_t file_cluster_offset, uint64_t offset, uint64_t bytes, void *qiov, size_t qiov_offset) "co %p bs %p pool %p: %s: cluster_type %d file_cluster_offset %" PRIu64 " offset %" PRIu64 " bytes %" PRIu64 " qiov %p qiov_offset %zu"
 qcow2_writev_start_req(void *co, int64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"
 qcow2_writev_done_req(void *co, int ret) "co %p ret %d"
 qcow2_writev_start_part(void *co) "co %p"

blockdev.c

@@ -3601,6 +3601,7 @@ static BlockJob *do_backup_common(BackupCommon *backup,
     job = backup_job_create(backup->job_id, bs, target_bs, backup->speed,
                             backup->sync, bmap, backup->bitmap_mode,
                             backup->compress,
+                            backup->filter_node_name,
                             backup->on_source_error,
                             backup->on_target_error,
                             job_flags, NULL, NULL, txn, errp);

hw/ide/core.c

@@ -442,6 +442,14 @@ static void ide_issue_trim_cb(void *opaque, int ret)
     TrimAIOCB *iocb = opaque;
     IDEState *s = iocb->s;
 
+    if (iocb->i >= 0) {
+        if (ret >= 0) {
+            block_acct_done(blk_get_stats(s->blk), &s->acct);
+        } else {
+            block_acct_failed(blk_get_stats(s->blk), &s->acct);
+        }
+    }
+
     if (ret >= 0) {
         while (iocb->j < iocb->qiov->niov) {
             int j = iocb->j;
@@ -459,10 +467,14 @@ static void ide_issue_trim_cb(void *opaque, int ret)
                 }
 
                 if (!ide_sect_range_ok(s, sector, count)) {
+                    block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_UNMAP);
                     iocb->ret = -EINVAL;
                     goto done;
                 }
 
+                block_acct_start(blk_get_stats(s->blk), &s->acct,
+                                 count << BDRV_SECTOR_BITS, BLOCK_ACCT_UNMAP);
+
                 /* Got an entry! Submit and exit.  */
                 iocb->aiocb = blk_aio_pdiscard(s->blk,
                                                sector << BDRV_SECTOR_BITS,

hw/scsi/scsi-disk.c

@@ -1608,25 +1608,28 @@ static void scsi_unmap_complete_noio(UnmapCBData *data, int ret)
 {
     SCSIDiskReq *r = data->r;
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
-    uint64_t sector_num;
-    uint32_t nb_sectors;
 
     assert(r->req.aiocb == NULL);
-    if (scsi_disk_req_check_error(r, ret, false)) {
-        goto done;
-    }
 
     if (data->count > 0) {
-        sector_num = ldq_be_p(&data->inbuf[0]);
-        nb_sectors = ldl_be_p(&data->inbuf[8]) & 0xffffffffULL;
-        if (!check_lba_range(s, sector_num, nb_sectors)) {
+        r->sector = ldq_be_p(&data->inbuf[0])
+            * (s->qdev.blocksize / BDRV_SECTOR_SIZE);
+        r->sector_count = (ldl_be_p(&data->inbuf[8]) & 0xffffffffULL)
+            * (s->qdev.blocksize / BDRV_SECTOR_SIZE);
+        if (!check_lba_range(s, r->sector, r->sector_count)) {
+            block_acct_invalid(blk_get_stats(s->qdev.conf.blk),
+                               BLOCK_ACCT_UNMAP);
             scsi_check_condition(r, SENSE_CODE(LBA_OUT_OF_RANGE));
             goto done;
         }
 
+        block_acct_start(blk_get_stats(s->qdev.conf.blk), &r->acct,
+                         r->sector_count * BDRV_SECTOR_SIZE,
+                         BLOCK_ACCT_UNMAP);
+
         r->req.aiocb = blk_aio_pdiscard(s->qdev.conf.blk,
-                                        sector_num * s->qdev.blocksize,
-                                        nb_sectors * s->qdev.blocksize,
+                                        r->sector * BDRV_SECTOR_SIZE,
+                                        r->sector_count * BDRV_SECTOR_SIZE,
                                         scsi_unmap_complete, data);
         data->count--;
         data->inbuf += 16;
@@ -1650,7 +1653,13 @@ static void scsi_unmap_complete(void *opaque, int ret)
     r->req.aiocb = NULL;
 
     aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
-    scsi_unmap_complete_noio(data, ret);
+    if (scsi_disk_req_check_error(r, ret, true)) {
+        scsi_req_unref(&r->req);
+        g_free(data);
+    } else {
+        block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+        scsi_unmap_complete_noio(data, ret);
+    }
     aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
 }
 
@@ -1680,6 +1689,7 @@ static void scsi_disk_emulate_unmap(SCSIDiskReq *r, uint8_t *inbuf)
     }
 
     if (blk_is_read_only(s->qdev.conf.blk)) {
+        block_acct_invalid(blk_get_stats(s->qdev.conf.blk), BLOCK_ACCT_UNMAP);
         scsi_check_condition(r, SENSE_CODE(WRITE_PROTECTED));
         return;
     }
@@ -1695,10 +1705,12 @@ static void scsi_disk_emulate_unmap(SCSIDiskReq *r, uint8_t *inbuf)
     return;
 
 invalid_param_len:
+    block_acct_invalid(blk_get_stats(s->qdev.conf.blk), BLOCK_ACCT_UNMAP);
     scsi_check_condition(r, SENSE_CODE(INVALID_PARAM_LEN));
     return;
 
 invalid_field:
+    block_acct_invalid(blk_get_stats(s->qdev.conf.blk), BLOCK_ACCT_UNMAP);
     scsi_check_condition(r, SENSE_CODE(INVALID_FIELD));
 }
 

include/block/accounting.h

@@ -33,9 +33,11 @@ typedef struct BlockAcctTimedStats BlockAcctTimedStats;
 typedef struct BlockAcctStats BlockAcctStats;
 
 enum BlockAcctType {
+    BLOCK_ACCT_NONE = 0,
     BLOCK_ACCT_READ,
     BLOCK_ACCT_WRITE,
     BLOCK_ACCT_FLUSH,
+    BLOCK_ACCT_UNMAP,
     BLOCK_MAX_IOTYPE,
 };
 

include/block/aio_task.h

@@ -0,0 +1,54 @@
+/*
+ * Aio tasks loops
+ *
+ * Copyright (c) 2019 Virtuozzo International GmbH.
+ *
+ * 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.
+ */
+
+#ifndef BLOCK_AIO_TASK_H
+#define BLOCK_AIO_TASK_H
+
+#include "qemu/coroutine.h"
+
+typedef struct AioTaskPool AioTaskPool;
+typedef struct AioTask AioTask;
+typedef int coroutine_fn (*AioTaskFunc)(AioTask *task);
+struct AioTask {
+    AioTaskPool *pool;
+    AioTaskFunc func;
+    int ret;
+};
+
+AioTaskPool *coroutine_fn aio_task_pool_new(int max_busy_tasks);
+void aio_task_pool_free(AioTaskPool *);
+
+/* error code of failed task or 0 if all is OK */
+int aio_task_pool_status(AioTaskPool *pool);
+
+bool aio_task_pool_empty(AioTaskPool *pool);
+
+/* User provides filled @task, however task->pool will be set automatically */
+void coroutine_fn aio_task_pool_start_task(AioTaskPool *pool, AioTask *task);
+
+void coroutine_fn aio_task_pool_wait_slot(AioTaskPool *pool);
+void coroutine_fn aio_task_pool_wait_one(AioTaskPool *pool);
+void coroutine_fn aio_task_pool_wait_all(AioTaskPool *pool);
+
+#endif /* BLOCK_AIO_TASK_H */

include/block/block-copy.h

@@ -0,0 +1,93 @@
+/*
+ * block_copy API
+ *
+ * Copyright (C) 2013 Proxmox Server Solutions
+ * Copyright (c) 2019 Virtuozzo International GmbH.
+ *
+ * Authors:
+ *  Dietmar Maurer (dietmar@proxmox.com)
+ *  Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef BLOCK_COPY_H
+#define BLOCK_COPY_H
+
+#include "block/block.h"
+
+typedef struct BlockCopyInFlightReq {
+    int64_t start_byte;
+    int64_t end_byte;
+    QLIST_ENTRY(BlockCopyInFlightReq) list;
+    CoQueue wait_queue; /* coroutines blocked on this request */
+} BlockCopyInFlightReq;
+
+typedef void (*ProgressBytesCallbackFunc)(int64_t bytes, void *opaque);
+typedef void (*ProgressResetCallbackFunc)(void *opaque);
+typedef struct BlockCopyState {
+    /*
+     * BdrvChild objects are not owned or managed by block-copy. They are
+     * provided by block-copy user and user is responsible for appropriate
+     * permissions on these children.
+     */
+    BdrvChild *source;
+    BdrvChild *target;
+    BdrvDirtyBitmap *copy_bitmap;
+    int64_t cluster_size;
+    bool use_copy_range;
+    int64_t copy_range_size;
+    uint64_t len;
+    QLIST_HEAD(, BlockCopyInFlightReq) inflight_reqs;
+
+    BdrvRequestFlags write_flags;
+
+    /*
+     * skip_unallocated:
+     *
+     * Used by sync=top jobs, which first scan the source node for unallocated
+     * areas and clear them in the copy_bitmap.  During this process, the bitmap
+     * is thus not fully initialized: It may still have bits set for areas that
+     * are unallocated and should actually not be copied.
+     *
+     * This is indicated by skip_unallocated.
+     *
+     * In this case, block_copy() will query the source’s allocation status,
+     * skip unallocated regions, clear them in the copy_bitmap, and invoke
+     * block_copy_reset_unallocated() every time it does.
+     */
+    bool skip_unallocated;
+
+    /* progress_bytes_callback: called when some copying progress is done. */
+    ProgressBytesCallbackFunc progress_bytes_callback;
+
+    /*
+     * progress_reset_callback: called when some bytes reset from copy_bitmap
+     * (see @skip_unallocated above). The callee is assumed to recalculate how
+     * many bytes remain based on the dirty bit count of copy_bitmap.
+     */
+    ProgressResetCallbackFunc progress_reset_callback;
+    void *progress_opaque;
+} BlockCopyState;
+
+BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
+                                     int64_t cluster_size,
+                                     BdrvRequestFlags write_flags,
+                                     Error **errp);
+
+void block_copy_set_callbacks(
+        BlockCopyState *s,
+        ProgressBytesCallbackFunc progress_bytes_callback,
+        ProgressResetCallbackFunc progress_reset_callback,
+        void *progress_opaque);
+
+void block_copy_state_free(BlockCopyState *s);
+
+int64_t block_copy_reset_unallocated(BlockCopyState *s,
+                                     int64_t offset, int64_t *count);
+
+int coroutine_fn block_copy(BlockCopyState *s, int64_t start, uint64_t bytes,
+                            bool *error_is_read);
+
+#endif /* BLOCK_COPY_H */

include/block/block.h

@@ -501,6 +501,7 @@ int bdrv_get_flags(BlockDriverState *bs);
 int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
 ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs,
                                           Error **errp);
+BlockStatsSpecific *bdrv_get_specific_stats(BlockDriverState *bs);
 void bdrv_round_to_clusters(BlockDriverState *bs,
                             int64_t offset, int64_t bytes,
                             int64_t *cluster_offset,

include/block/block_int.h

@@ -366,6 +366,7 @@ struct BlockDriver {
     int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
     ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs,
                                                  Error **errp);
+    BlockStatsSpecific *(*bdrv_get_specific_stats)(BlockDriverState *bs);
 
     int coroutine_fn (*bdrv_save_vmstate)(BlockDriverState *bs,
                                           QEMUIOVector *qiov,
@@ -1196,6 +1197,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
                             BdrvDirtyBitmap *sync_bitmap,
                             BitmapSyncMode bitmap_mode,
                             bool compress,
+                            const char *filter_node_name,
                             BlockdevOnError on_source_error,
                             BlockdevOnError on_target_error,
                             int creation_flags,

qapi/block-core.json

@@ -860,6 +860,8 @@
 #
 # @wr_bytes:      The number of bytes written by the device.
 #
+# @unmap_bytes: The number of bytes unmapped by the device (Since 4.2)
+#
 # @rd_operations: The number of read operations performed by the device.
 #
 # @wr_operations: The number of write operations performed by the device.
@@ -867,12 +869,18 @@
 # @flush_operations: The number of cache flush operations performed by the
 #                    device (since 0.15.0)
 #
-# @flush_total_time_ns: Total time spend on cache flushes in nano-seconds
+# @unmap_operations: The number of unmap operations performed by the device
+#                    (Since 4.2)
+#
+# @rd_total_time_ns: Total time spent on reads in nanoseconds (since 0.15.0).
+#
+# @wr_total_time_ns: Total time spent on writes in nanoseconds (since 0.15.0).
+#
+# @flush_total_time_ns: Total time spent on cache flushes in nanoseconds
 #                       (since 0.15.0).
 #
-# @wr_total_time_ns: Total time spend on writes in nano-seconds (since 0.15.0).
-#
-# @rd_total_time_ns: Total_time_spend on reads in nano-seconds (since 0.15.0).
+# @unmap_total_time_ns: Total time spent on unmap operations in nanoseconds
+#                       (Since 4.2)
 #
 # @wr_highest_offset: The offset after the greatest byte written to the
 #                     device.  The intended use of this information is for
@@ -885,6 +893,9 @@
 # @wr_merged: Number of write requests that have been merged into another
 #             request (Since 2.3).
 #
+# @unmap_merged: Number of unmap requests that have been merged into another
+#                request (Since 4.2)
+#
 # @idle_time_ns: Time since the last I/O operation, in
 #                nanoseconds. If the field is absent it means that
 #                there haven't been any operations yet (Since 2.5).
@@ -898,6 +909,9 @@
 # @failed_flush_operations: The number of failed flush operations
 #                           performed by the device (Since 2.5)
 #
+# @failed_unmap_operations: The number of failed unmap operations performed
+#                           by the device (Since 4.2)
+#
 # @invalid_rd_operations: The number of invalid read operations
 #                          performed by the device (Since 2.5)
 #
@@ -907,6 +921,9 @@
 # @invalid_flush_operations: The number of invalid flush operations
 #                            performed by the device (Since 2.5)
 #
+# @invalid_unmap_operations: The number of invalid unmap operations performed
+#                            by the device (Since 4.2)
+#
 # @account_invalid: Whether invalid operations are included in the
 #                   last access statistics (Since 2.5)
 #
@@ -925,20 +942,59 @@
 # Since: 0.14.0
 ##
 { 'struct': 'BlockDeviceStats',
-  'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'rd_operations': 'int',
-           'wr_operations': 'int', 'flush_operations': 'int',
-           'flush_total_time_ns': 'int', 'wr_total_time_ns': 'int',
-           'rd_total_time_ns': 'int', 'wr_highest_offset': 'int',
-           'rd_merged': 'int', 'wr_merged': 'int', '*idle_time_ns': 'int',
+  'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'unmap_bytes' : 'int',
+           'rd_operations': 'int', 'wr_operations': 'int',
+           'flush_operations': 'int', 'unmap_operations': 'int',
+           'rd_total_time_ns': 'int', 'wr_total_time_ns': 'int',
+           'flush_total_time_ns': 'int', 'unmap_total_time_ns': 'int',
+           'wr_highest_offset': 'int',
+           'rd_merged': 'int', 'wr_merged': 'int', 'unmap_merged': 'int',
+           '*idle_time_ns': 'int',
            'failed_rd_operations': 'int', 'failed_wr_operations': 'int',
-           'failed_flush_operations': 'int', 'invalid_rd_operations': 'int',
-           'invalid_wr_operations': 'int', 'invalid_flush_operations': 'int',
+           'failed_flush_operations': 'int', 'failed_unmap_operations': 'int',
+           'invalid_rd_operations': 'int', 'invalid_wr_operations': 'int',
+           'invalid_flush_operations': 'int', 'invalid_unmap_operations': 'int',
            'account_invalid': 'bool', 'account_failed': 'bool',
            'timed_stats': ['BlockDeviceTimedStats'],
            '*rd_latency_histogram': 'BlockLatencyHistogramInfo',
            '*wr_latency_histogram': 'BlockLatencyHistogramInfo',
            '*flush_latency_histogram': 'BlockLatencyHistogramInfo' } }
 
+##
+# @BlockStatsSpecificFile:
+#
+# File driver statistics
+#
+# @discard-nb-ok: The number of successful discard operations performed by
+#                 the driver.
+#
+# @discard-nb-failed: The number of failed discard operations performed by
+#                     the driver.
+#
+# @discard-bytes-ok: The number of bytes discarded by the driver.
+#
+# Since: 4.2
+##
+{ 'struct': 'BlockStatsSpecificFile',
+  'data': {
+      'discard-nb-ok': 'uint64',
+      'discard-nb-failed': 'uint64',
+      'discard-bytes-ok': 'uint64' } }
+
+##
+# @BlockStatsSpecific:
+#
+# Block driver specific statistics
+#
+# Since: 4.2
+##
+{ 'union': 'BlockStatsSpecific',
+  'base': { 'driver': 'BlockdevDriver' },
+  'discriminator': 'driver',
+  'data': {
+      'file': 'BlockStatsSpecificFile',
+      'host_device': 'BlockStatsSpecificFile' } }
+
 ##
 # @BlockStats:
 #
@@ -954,6 +1010,8 @@
 #
 # @stats:  A @BlockDeviceStats for the device.
 #
+# @driver-specific: Optional driver-specific stats. (Since 4.2)
+#
 # @parent: This describes the file block device if it has one.
 #          Contains recursively the statistics of the underlying
 #          protocol (e.g. the host file for a qcow2 image). If there is
@@ -967,6 +1025,7 @@
 { 'struct': 'BlockStats',
   'data': {'*device': 'str', '*qdev': 'str', '*node-name': 'str',
            'stats': 'BlockDeviceStats',
+           '*driver-specific': 'BlockStatsSpecific',
            '*parent': 'BlockStats',
            '*backing': 'BlockStats'} }
 
@@ -1391,6 +1450,11 @@
 #                list without user intervention.
 #                Defaults to true. (Since 2.12)
 #
+# @filter-node-name: the node name that should be assigned to the
+#                    filter driver that the backup job inserts into the graph
+#                    above node specified by @drive. If this option is not given,
+#                    a node name is autogenerated. (Since: 4.2)
+#
 # Note: @on-source-error and @on-target-error only affect background
 # I/O.  If an error occurs during a guest write request, the device's
 # rerror/werror actions will be used.
@@ -1404,7 +1468,8 @@
             '*compress': 'bool',
             '*on-source-error': 'BlockdevOnError',
             '*on-target-error': 'BlockdevOnError',
-            '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } }
+            '*auto-finalize': 'bool', '*auto-dismiss': 'bool',
+            '*filter-node-name': 'str' } }
 
 ##
 # @DriveBackup:

tests/qemu-iotests/026

@@ -107,7 +107,7 @@ if [ "$event" == "l2_load" ]; then
     $QEMU_IO -c "read $vmstate 0 128k " "$BLKDBG_TEST_IMG" | _filter_qemu_io
 fi
 
-_check_test_img 2>&1 | grep -v "refcount=1 reference=0"
+_check_test_img_ignore_leaks 2>&1 | grep -v "refcount=1 reference=0"
 
 done
 done
@@ -152,7 +152,7 @@ echo
 echo "Event: $event; errno: $errno; imm: $imm; once: $once; write $vmstate"
 $QEMU_IO -c "write $vmstate 0 64M" "$BLKDBG_TEST_IMG" | _filter_qemu_io
 
-_check_test_img 2>&1 | grep -v "refcount=1 reference=0"
+_check_test_img_ignore_leaks 2>&1 | grep -v "refcount=1 reference=0"
 
 done
 done
@@ -191,7 +191,7 @@ echo
 echo "Event: $event; errno: $errno; imm: $imm; once: $once"
 $QEMU_IO -c "write -b 0 64k" "$BLKDBG_TEST_IMG" | _filter_qemu_io
 
-_check_test_img 2>&1 | grep -v "refcount=1 reference=0"
+_check_test_img_ignore_leaks 2>&1 | grep -v "refcount=1 reference=0"
 
 done
 done

tests/qemu-iotests/026.out

@@ -17,18 +17,14 @@ Event: l1_update; errno: 5; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l1_update; errno: 5; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l1_update; errno: 28; imm: off; once: on; write
@@ -45,18 +41,14 @@ Event: l1_update; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l1_update; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l2_load; errno: 5; imm: off; once: on; write
@@ -137,18 +129,14 @@ Event: l2_update; errno: 5; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l2_update; errno: 5; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l2_update; errno: 28; imm: off; once: on; write
@@ -165,18 +153,14 @@ Event: l2_update; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l2_update; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l2_alloc_write; errno: 5; imm: off; once: on; write
@@ -200,9 +184,7 @@ Event: l2_alloc_write; errno: 5; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l2_alloc_write; errno: 28; imm: off; once: on; write
@@ -226,9 +208,7 @@ Event: l2_alloc_write; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: write_aio; errno: 5; imm: off; once: on; write
@@ -480,18 +460,14 @@ Event: refblock_alloc_hookup; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-55 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_hookup; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-251 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_write; errno: 28; imm: off; once: on; write
@@ -532,18 +508,14 @@ Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-10 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-23 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_write_table; errno: 28; imm: off; once: on; write
@@ -560,18 +532,14 @@ Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-10 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-23 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_switch_table; errno: 28; imm: off; once: on; write
@@ -588,18 +556,14 @@ Event: refblock_alloc_switch_table; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-10 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: refblock_alloc_switch_table; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-23 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 
 === L1 growth tests ===
 
@@ -658,9 +622,7 @@ Event: l1_grow_activate_table; errno: 5; imm: off; once: off
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-96 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
 
 Event: l1_grow_activate_table; errno: 28; imm: off; once: on
@@ -672,9 +634,7 @@ Event: l1_grow_activate_table; errno: 28; imm: off; once: off
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-96 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 
 === Avoid cluster leaks after temporary failure ===
 

tests/qemu-iotests/026.out.nocache

@@ -17,18 +17,14 @@ Event: l1_update; errno: 5; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l1_update; errno: 5; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l1_update; errno: 28; imm: off; once: on; write 
@@ -45,18 +41,14 @@ Event: l1_update; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l1_update; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l2_load; errno: 5; imm: off; once: on; write 
@@ -140,9 +132,7 @@ qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 wrote 131072/131072 bytes at offset 0
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l2_update; errno: 5; imm: off; once: off; write -b
@@ -150,9 +140,7 @@ qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 wrote 131072/131072 bytes at offset 0
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l2_update; errno: 28; imm: off; once: on; write 
@@ -172,9 +160,7 @@ qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 wrote 131072/131072 bytes at offset 0
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l2_update; errno: 28; imm: off; once: off; write -b
@@ -182,9 +168,7 @@ qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 wrote 131072/131072 bytes at offset 0
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-127 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l2_alloc_write; errno: 5; imm: off; once: on; write 
@@ -208,9 +192,7 @@ Event: l2_alloc_write; errno: 5; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l2_alloc_write; errno: 28; imm: off; once: on; write 
@@ -234,9 +216,7 @@ Event: l2_alloc_write; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-1 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: write_aio; errno: 5; imm: off; once: on; write 
@@ -488,18 +468,14 @@ Event: refblock_alloc_hookup; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-55 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_hookup; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-251 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_write; errno: 28; imm: off; once: on; write 
@@ -540,18 +516,14 @@ Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-10 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-23 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_write_table; errno: 28; imm: off; once: on; write 
@@ -568,18 +540,14 @@ Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-10 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-23 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_switch_table; errno: 28; imm: off; once: on; write 
@@ -596,18 +564,14 @@ Event: refblock_alloc_switch_table; errno: 28; imm: off; once: off; write
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-10 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: refblock_alloc_switch_table; errno: 28; imm: off; once: off; write -b
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-23 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 
 === L1 growth tests ===
 
@@ -666,9 +630,7 @@ Event: l1_grow_activate_table; errno: 5; imm: off; once: off
 qemu-io: Failed to flush the L2 table cache: Input/output error
 qemu-io: Failed to flush the refcount block cache: Input/output error
 write failed: Input/output error
-
-96 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 
 
 Event: l1_grow_activate_table; errno: 28; imm: off; once: on
@@ -680,9 +642,7 @@ Event: l1_grow_activate_table; errno: 28; imm: off; once: off
 qemu-io: Failed to flush the L2 table cache: No space left on device
 qemu-io: Failed to flush the refcount block cache: No space left on device
 write failed: No space left on device
-
-96 leaked clusters were found on the image.
-This means waste of disk space, but no harm to data.
+No errors were found on the image.
 
 === Avoid cluster leaks after temporary failure ===
 

tests/qemu-iotests/056

@@ -133,6 +133,7 @@ class BackupTest(iotests.QMPTestCase):
         self.vm = iotests.VM()
         self.test_img = img_create('test')
         self.dest_img = img_create('dest')
+        self.dest_img2 = img_create('dest2')
         self.ref_img = img_create('ref')
         self.vm.add_drive(self.test_img)
         self.vm.launch()
@@ -141,6 +142,7 @@ class BackupTest(iotests.QMPTestCase):
         self.vm.shutdown()
         try_remove(self.test_img)
         try_remove(self.dest_img)
+        try_remove(self.dest_img2)
         try_remove(self.ref_img)
 
     def hmp_io_writes(self, drive, patterns):
@@ -253,9 +255,9 @@ class BackupTest(iotests.QMPTestCase):
         res = self.vm.qmp('query-block-jobs')
         self.assert_qmp(res, 'return[0]/status', 'concluded')
         # Leave zombie job un-dismissed, observe a failure:
-        res = self.qmp_backup_and_wait(serror="Node 'drive0' is busy: block device is in use by block job: backup",
+        res = self.qmp_backup_and_wait(serror="Job ID 'drive0' already in use",
                                        device='drive0', format=iotests.imgfmt,
-                                       sync='full', target=self.dest_img,
+                                       sync='full', target=self.dest_img2,
                                        auto_dismiss=False)
         self.assertEqual(res, False)
         # OK, dismiss the zombie.
@@ -265,7 +267,7 @@ class BackupTest(iotests.QMPTestCase):
         self.assert_qmp(res, 'return', [])
         # Ensure it's really gone.
         self.qmp_backup_and_wait(device='drive0', format=iotests.imgfmt,
-                                 sync='full', target=self.dest_img,
+                                 sync='full', target=self.dest_img2,
                                  auto_dismiss=False)
 
     def dismissal_failure(self, dismissal_opt):

tests/qemu-iotests/124

@@ -105,7 +105,7 @@ class TestIncrementalBackupBase(iotests.QMPTestCase):
         # Create a base image with a distinctive patterning
         drive0 = self.add_node('drive0')
         self.img_create(drive0['file'], drive0['fmt'])
-        self.vm.add_drive(drive0['file'])
+        self.vm.add_drive(drive0['file'], opts='node-name=node0')
         self.write_default_pattern(drive0['file'])
         self.vm.launch()
 
@@ -348,12 +348,14 @@ class TestIncrementalBackup(TestIncrementalBackupBase):
                             ('0xfe', '16M', '256k'),
                             ('0x64', '32736k', '64k')))
         # Check the dirty bitmap stats
-        result = self.vm.qmp('query-block')
-        self.assert_qmp(result, 'return[0]/dirty-bitmaps[0]/name', 'bitmap0')
-        self.assert_qmp(result, 'return[0]/dirty-bitmaps[0]/count', 458752)
-        self.assert_qmp(result, 'return[0]/dirty-bitmaps[0]/granularity', 65536)
-        self.assert_qmp(result, 'return[0]/dirty-bitmaps[0]/status', 'active')
-        self.assert_qmp(result, 'return[0]/dirty-bitmaps[0]/persistent', False)
+        self.assertTrue(self.vm.check_bitmap_status(
+            'node0', bitmap0.name, {
+                'name': 'bitmap0',
+                'count': 458752,
+                'granularity': 65536,
+                'status': 'active',
+                'persistent': False
+            }))
 
         # Prepare a cluster_size=128k backup target without a backing file.
         (target, _) = bitmap0.new_target()
@@ -670,9 +672,8 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase):
         """
 
         drive0 = self.drives[0]
-        # NB: The blkdebug script here looks for a "flush, read, read" pattern.
-        # The flush occurs in hmp_io_writes, the first read in device_add, and
-        # the last read during the block job.
+        # NB: The blkdebug script here looks for a "flush, read" pattern.
+        # The flush occurs in hmp_io_writes, and the read during the block job.
         result = self.vm.qmp('blockdev-add',
                              node_name=drive0['id'],
                              driver=drive0['fmt'],
@@ -686,15 +687,11 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase):
                                      'event': 'flush_to_disk',
                                      'state': 1,
                                      'new_state': 2
-                                 },{
-                                     'event': 'read_aio',
-                                     'state': 2,
-                                     'new_state': 3
                                  }],
                                  'inject-error': [{
                                      'event': 'read_aio',
                                      'errno': 5,
-                                     'state': 3,
+                                     'state': 2,
                                      'immediately': False,
                                      'once': True
                                  }],
@@ -708,23 +705,15 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase):
                                           ('0xfe', '16M', '256k'),
                                           ('0x64', '32736k', '64k')))
 
-        # For the purposes of query-block visibility of bitmaps, add a drive
-        # frontend after we've written data; otherwise we can't use hmp-io
-        result = self.vm.qmp("device_add",
-                             id="device0",
-                             drive=drive0['id'],
-                             driver="virtio-blk")
-        self.assert_qmp(result, 'return', {})
-
         # Bitmap Status Check
-        query = self.vm.qmp('query-block')
-        ret = [bmap for bmap in query['return'][0]['dirty-bitmaps']
-               if bmap.get('name') == bitmap.name][0]
-        self.assert_qmp(ret, 'count', 458752)
-        self.assert_qmp(ret, 'granularity', 65536)
-        self.assert_qmp(ret, 'status', 'active')
-        self.assert_qmp(ret, 'busy', False)
-        self.assert_qmp(ret, 'recording', True)
+        self.assertTrue(self.vm.check_bitmap_status(
+            drive0['id'], bitmap.name, {
+                'count': 458752,
+                'granularity': 65536,
+                'status': 'active',
+                'busy': False,
+                'recording': True
+            }))
 
         # Start backup
         parent, _ = bitmap.last_target()
@@ -748,14 +737,14 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase):
                                         'operation': 'read'})
 
         # Bitmap Status Check
-        query = self.vm.qmp('query-block')
-        ret = [bmap for bmap in query['return'][0]['dirty-bitmaps']
-               if bmap.get('name') == bitmap.name][0]
-        self.assert_qmp(ret, 'count', 458752)
-        self.assert_qmp(ret, 'granularity', 65536)
-        self.assert_qmp(ret, 'status', 'frozen')
-        self.assert_qmp(ret, 'busy', True)
-        self.assert_qmp(ret, 'recording', True)
+        self.assertTrue(self.vm.check_bitmap_status(
+            drive0['id'], bitmap.name, {
+                'count': 458752,
+                'granularity': 65536,
+                'status': 'frozen',
+                'busy': True,
+                'recording': True
+            }))
 
         # Resume and check incremental backup for consistency
         res = self.vm.qmp('block-job-resume', device=bitmap.drive['id'])
@@ -763,14 +752,14 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase):
         self.wait_qmp_backup(bitmap.drive['id'])
 
         # Bitmap Status Check
-        query = self.vm.qmp('query-block')
-        ret = [bmap for bmap in query['return'][0]['dirty-bitmaps']
-               if bmap.get('name') == bitmap.name][0]
-        self.assert_qmp(ret, 'count', 0)
-        self.assert_qmp(ret, 'granularity', 65536)
-        self.assert_qmp(ret, 'status', 'active')
-        self.assert_qmp(ret, 'busy', False)
-        self.assert_qmp(ret, 'recording', True)
+        self.assertTrue(self.vm.check_bitmap_status(
+            drive0['id'], bitmap.name, {
+                'count': 0,
+                'granularity': 65536,
+                'status': 'active',
+                'busy': False,
+                'recording': True
+            }))
 
         # Finalize / Cleanup
         self.make_reference_backup(bitmap)

tests/qemu-iotests/125

@@ -34,8 +34,7 @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 get_image_size_on_host()
 {
-    $QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep "disk size" \
-        | sed -e 's/^[^0-9]*\([0-9]\+\).*$/\1/'
+    echo $(($(stat -c '%b * %B' "$TEST_IMG_FILE")))
 }
 
 # get standard environment and filters
@@ -49,6 +48,46 @@ if [ -z "$TEST_IMG_FILE" ]; then
     TEST_IMG_FILE=$TEST_IMG
 fi
 
+# Test whether we are running on a broken XFS version.  There is this
+# bug:
+
+# $ rm -f foo
+# $ touch foo
+# $ block_size=4096 # Your FS's block size
+# $ fallocate -o $((block_size / 2)) -l $block_size foo
+# $ LANG=C xfs_bmap foo | grep hole
+#         1: [8..15]: hole
+#
+# The problem is that the XFS driver rounds down the offset and
+# rounds up the length to the block size, but independently.  As
+# such, it only allocates the first block in the example above,
+# even though it should allocate the first two blocks (because our
+# request is to fallocate something that touches both the first
+# two blocks).
+#
+# This means that when you then write to the beginning of the
+# second block, the disk usage of the first two blocks grows.
+#
+# That is precisely what fallocate() promises, though: That when you
+# write to an area that you have fallocated, no new blocks will have
+# to be allocated.
+
+touch "$TEST_IMG_FILE"
+# Assuming there is no FS with a block size greater than 64k
+fallocate -o 65535 -l 2 "$TEST_IMG_FILE"
+len0=$(get_image_size_on_host)
+
+# Write to something that in theory we have just fallocated
+# (Thus, the on-disk size should not increase)
+poke_file "$TEST_IMG_FILE" 65536 42
+len1=$(get_image_size_on_host)
+
+if [ $len1 -gt $len0 ]; then
+    _notrun "the test filesystem's fallocate() is broken"
+fi
+
+rm -f "$TEST_IMG_FILE"
+
 # Generally, we create some image with or without existing preallocation and
 # then resize it. Then we write some data into the image and verify that its
 # size does not change if we have used preallocation.
@@ -111,7 +150,7 @@ for GROWTH_SIZE in 16 48 80; do
                 if [ $file_length_2 -gt $file_length_1 ]; then
                     echo "ERROR (grow): Image length has grown from $file_length_1 to $file_length_2"
                 fi
-                if [ $create_mode != metadata ]; then
+                if [ $growth_mode != metadata ]; then
                     # The host size should not have grown either
                     if [ $host_size_2 -gt $host_size_1 ]; then
                         echo "ERROR (grow): Host size has grown from $host_size_1 to $host_size_2"

tests/qemu-iotests/141.out

@@ -10,7 +10,7 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/m.
 Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{"error": {"class": "GenericError", "desc": "Node drv0 is in use"}}
+{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 0, "speed": 0, "type": "backup"}}

tests/qemu-iotests/149

@@ -153,7 +153,7 @@ def cryptsetup_format(config):
 
     (password, slot) = config.first_password()
 
-    args = ["luksFormat"]
+    args = ["luksFormat", "--type", "luks1"]
     cipher = config.cipher + "-" + config.mode + "-" + config.ivgen
     if config.ivgen_hash is not None:
         cipher = cipher + ":" + config.ivgen_hash

tests/qemu-iotests/149.out

@@ -2,7 +2,7 @@
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha1.img qiotest-145-aes-256-xts-plain64-sha1
 # Write test pattern 0xa7
@@ -122,7 +122,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha1.img
 # Create image
 truncate TEST_DIR/luks-twofish-256-xts-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher twofish-xts-plain64 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-twofish-256-xts-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher twofish-xts-plain64 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-twofish-256-xts-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-twofish-256-xts-plain64-sha1.img qiotest-145-twofish-256-xts-plain64-sha1
 # Write test pattern 0xa7
@@ -242,7 +242,7 @@ unlink TEST_DIR/luks-twofish-256-xts-plain64-sha1.img
 # Create image
 truncate TEST_DIR/luks-serpent-256-xts-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher serpent-xts-plain64 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-serpent-256-xts-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher serpent-xts-plain64 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-serpent-256-xts-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-serpent-256-xts-plain64-sha1.img qiotest-145-serpent-256-xts-plain64-sha1
 # Write test pattern 0xa7
@@ -362,7 +362,7 @@ unlink TEST_DIR/luks-serpent-256-xts-plain64-sha1.img
 # Create image
 truncate TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher cast5-cbc-plain64 --key-size 128 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher cast5-cbc-plain64 --key-size 128 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-cast5-128-cbc-plain64-sha1.img qiotest-145-cast5-128-cbc-plain64-sha1
 # Write test pattern 0xa7
@@ -483,7 +483,7 @@ Skipping cast6-256-xts-plain64-sha1 in blacklist
 # Create image
 truncate TEST_DIR/luks-aes-256-cbc-plain-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-cbc-plain --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-plain-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-cbc-plain --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-plain-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-plain-sha1.img qiotest-145-aes-256-cbc-plain-sha1
 # Write test pattern 0xa7
@@ -603,7 +603,7 @@ unlink TEST_DIR/luks-aes-256-cbc-plain-sha1.img
 # Create image
 truncate TEST_DIR/luks-aes-256-cbc-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-cbc-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-cbc-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-plain64-sha1.img qiotest-145-aes-256-cbc-plain64-sha1
 # Write test pattern 0xa7
@@ -723,7 +723,7 @@ unlink TEST_DIR/luks-aes-256-cbc-plain64-sha1.img
 # Create image
 truncate TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-cbc-essiv:sha256 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-cbc-essiv:sha256 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img qiotest-145-aes-256-cbc-essiv-sha256-sha1
 # Write test pattern 0xa7
@@ -843,7 +843,7 @@ unlink TEST_DIR/luks-aes-256-cbc-essiv-sha256-sha1.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-essiv:sha256 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-essiv:sha256 --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img qiotest-145-aes-256-xts-essiv-sha256-sha1
 # Write test pattern 0xa7
@@ -963,7 +963,7 @@ unlink TEST_DIR/luks-aes-256-xts-essiv-sha256-sha1.img
 # Create image
 truncate TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img qiotest-145-aes-128-xts-plain64-sha256-sha1
 # Write test pattern 0xa7
@@ -1083,7 +1083,7 @@ unlink TEST_DIR/luks-aes-128-xts-plain64-sha256-sha1.img
 # Create image
 truncate TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 384 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 384 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img qiotest-145-aes-192-xts-plain64-sha256-sha1
 # Write test pattern 0xa7
@@ -1203,7 +1203,7 @@ unlink TEST_DIR/luks-aes-192-xts-plain64-sha256-sha1.img
 # Create image
 truncate TEST_DIR/luks-twofish-128-xts-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher twofish-xts-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-twofish-128-xts-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher twofish-xts-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-twofish-128-xts-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-twofish-128-xts-plain64-sha1.img qiotest-145-twofish-128-xts-plain64-sha1
 # Write test pattern 0xa7
@@ -1324,7 +1324,7 @@ Skipping twofish-192-xts-plain64-sha1 in blacklist
 # Create image
 truncate TEST_DIR/luks-serpent-128-xts-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher serpent-xts-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-serpent-128-xts-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher serpent-xts-plain64 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-serpent-128-xts-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-serpent-128-xts-plain64-sha1.img qiotest-145-serpent-128-xts-plain64-sha1
 # Write test pattern 0xa7
@@ -1444,7 +1444,7 @@ unlink TEST_DIR/luks-serpent-128-xts-plain64-sha1.img
 # Create image
 truncate TEST_DIR/luks-serpent-192-xts-plain64-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher serpent-xts-plain64 --key-size 384 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-serpent-192-xts-plain64-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher serpent-xts-plain64 --key-size 384 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-serpent-192-xts-plain64-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-serpent-192-xts-plain64-sha1.img qiotest-145-serpent-192-xts-plain64-sha1
 # Write test pattern 0xa7
@@ -1566,7 +1566,7 @@ Skipping cast6-192-xts-plain64-sha1 in blacklist
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain64-sha224.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 512 --hash sha224 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha224.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 512 --hash sha224 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha224.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha224.img qiotest-145-aes-256-xts-plain64-sha224
 # Write test pattern 0xa7
@@ -1686,7 +1686,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha224.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain64-sha256.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 512 --hash sha256 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha256.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 512 --hash sha256 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha256.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha256.img qiotest-145-aes-256-xts-plain64-sha256
 # Write test pattern 0xa7
@@ -1806,7 +1806,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha256.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain64-sha384.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 512 --hash sha384 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha384.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 512 --hash sha384 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha384.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha384.img qiotest-145-aes-256-xts-plain64-sha384
 # Write test pattern 0xa7
@@ -1926,7 +1926,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha384.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain64-sha512.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 512 --hash sha512 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha512.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 512 --hash sha512 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-sha512.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-sha512.img qiotest-145-aes-256-xts-plain64-sha512
 # Write test pattern 0xa7
@@ -2046,7 +2046,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain64-sha512.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain64 --key-size 512 --hash ripemd160 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain64 --key-size 512 --hash ripemd160 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img qiotest-145-aes-256-xts-plain64-ripemd160
 # Write test pattern 0xa7
@@ -2166,7 +2166,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain64-ripemd160.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain-sha1-pwslot3.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain --key-size 512 --hash sha1 --key-slot 3 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain-sha1-pwslot3.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain --key-size 512 --hash sha1 --key-slot 3 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain-sha1-pwslot3.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-xts-plain-sha1-pwslot3.img qiotest-145-aes-256-xts-plain-sha1-pwslot3
 # Write test pattern 0xa7
@@ -2226,7 +2226,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain-sha1-pwslot3.img
 # Create image
 truncate TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-xts-plain --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-xts-plain --key-size 512 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img
 # Add password slot 1
 sudo cryptsetup -q -v luksAddKey TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img --key-slot 1 --key-file - --iter-time 10 TEST_DIR/passwd.txt
 # Add password slot 2
@@ -2360,7 +2360,7 @@ unlink TEST_DIR/luks-aes-256-xts-plain-sha1-pwallslots.img
 # Create image
 truncate TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-cbc-essiv:sha256 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-cbc-essiv:sha256 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img qiotest-145-aes-256-cbc-essiv-auto-sha1
 # Write test pattern 0xa7
@@ -2480,7 +2480,7 @@ unlink TEST_DIR/luks-aes-256-cbc-essiv-auto-sha1.img
 # Create image
 truncate TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img --size 4194304MB
 # Format image
-sudo cryptsetup -q -v luksFormat --cipher aes-cbc-plain64:sha256 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img
+sudo cryptsetup -q -v luksFormat --type luks1 --cipher aes-cbc-plain64:sha256 --key-size 256 --hash sha1 --key-slot 0 --key-file - --iter-time 10 TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img
 # Open dev
 sudo cryptsetup -q -v luksOpen TEST_DIR/luks-aes-256-cbc-plain64-sha256-sha1.img qiotest-145-aes-256-cbc-plain64-sha256-sha1
 # Write test pattern 0xa7

tests/qemu-iotests/162

@@ -46,7 +46,7 @@ echo '=== NBD ==='
 # NBD expects all of its arguments to be strings
 
 # So this should not crash
-$QEMU_IMG info 'json:{"driver": "nbd", "host": 42}'
+$QEMU_IMG info 'json:{"driver": "nbd", "host": -1}'
 
 # And this should not treat @port as if it had not been specified
 # (We need to set up a server here, because the error message for "Connection

tests/qemu-iotests/162.out

@@ -1,7 +1,7 @@
 QA output created by 162
 
 === NBD ===
-qemu-img: Could not open 'json:{"driver": "nbd", "host": 42}': Failed to connect socket: Invalid argument
+qemu-img: Could not open 'json:{"driver": "nbd", "host": -1}': address resolution failed for -1:10809: Name or service not known
 image: nbd://localhost:PORT
 image: nbd+unix://?socket=42
 

tests/qemu-iotests/227.out

@@ -15,6 +15,8 @@ Testing: -drive driver=null-co,read-zeroes=on,if=virtio
         {
             "device": "virtio0",
             "stats": {
+                "unmap_operations": 0,
+                "unmap_merged": 0,
                 "flush_total_time_ns": 0,
                 "wr_highest_offset": 0,
                 "wr_total_time_ns": 0,
@@ -24,13 +26,17 @@ Testing: -drive driver=null-co,read-zeroes=on,if=virtio
                 "wr_bytes": 0,
                 "timed_stats": [
                 ],
+                "failed_unmap_operations": 0,
                 "failed_flush_operations": 0,
                 "account_invalid": true,
                 "rd_total_time_ns": 0,
+                "invalid_unmap_operations": 0,
                 "flush_operations": 0,
                 "wr_operations": 0,
+                "unmap_bytes": 0,
                 "rd_merged": 0,
                 "rd_bytes": 0,
+                "unmap_total_time_ns": 0,
                 "invalid_flush_operations": 0,
                 "account_failed": true,
                 "rd_operations": 0,
@@ -74,6 +80,8 @@ Testing: -drive driver=null-co,if=none
         {
             "device": "none0",
             "stats": {
+                "unmap_operations": 0,
+                "unmap_merged": 0,
                 "flush_total_time_ns": 0,
                 "wr_highest_offset": 0,
                 "wr_total_time_ns": 0,
@@ -83,13 +91,17 @@ Testing: -drive driver=null-co,if=none
                 "wr_bytes": 0,
                 "timed_stats": [
                 ],
+                "failed_unmap_operations": 0,
                 "failed_flush_operations": 0,
                 "account_invalid": true,
                 "rd_total_time_ns": 0,
+                "invalid_unmap_operations": 0,
                 "flush_operations": 0,
                 "wr_operations": 0,
+                "unmap_bytes": 0,
                 "rd_merged": 0,
                 "rd_bytes": 0,
+                "unmap_total_time_ns": 0,
                 "invalid_flush_operations": 0,
                 "account_failed": true,
                 "rd_operations": 0,
@@ -163,6 +175,8 @@ Testing: -blockdev driver=null-co,read-zeroes=on,node-name=null -device virtio-b
         {
             "device": "",
             "stats": {
+                "unmap_operations": 0,
+                "unmap_merged": 0,
                 "flush_total_time_ns": 0,
                 "wr_highest_offset": 0,
                 "wr_total_time_ns": 0,
@@ -172,13 +186,17 @@ Testing: -blockdev driver=null-co,read-zeroes=on,node-name=null -device virtio-b
                 "wr_bytes": 0,
                 "timed_stats": [
                 ],
+                "failed_unmap_operations": 0,
                 "failed_flush_operations": 0,
                 "account_invalid": false,
                 "rd_total_time_ns": 0,
+                "invalid_unmap_operations": 0,
                 "flush_operations": 0,
                 "wr_operations": 0,
+                "unmap_bytes": 0,
                 "rd_merged": 0,
                 "rd_bytes": 0,
+                "unmap_total_time_ns": 0,
                 "invalid_flush_operations": 0,
                 "account_failed": false,
                 "rd_operations": 0,

tests/qemu-iotests/257

@@ -148,11 +148,6 @@ class Drive:
         self.fmt = None
         self.size = None
         self.node = None
-        self.device = None
-
-    @property
-    def name(self):
-        return self.node or self.device
 
     def img_create(self, fmt, size):
         self.fmt = fmt
@@ -188,25 +183,6 @@ class Drive:
         self.size = size
         self.node = name
 
-def query_bitmaps(vm):
-    res = vm.qmp("query-block")
-    return {"bitmaps": {device['device'] or device['qdev']:
-                        device.get('dirty-bitmaps', []) for
-                        device in res['return']}}
-
-def get_bitmap(bitmaps, drivename, name, recording=None):
-    """
-    get a specific bitmap from the object returned by query_bitmaps.
-    :param recording: If specified, filter results by the specified value.
-    """
-    for bitmap in bitmaps['bitmaps'][drivename]:
-        if bitmap.get('name', '') == name:
-            if recording is None:
-                return bitmap
-            elif bitmap.get('recording') == recording:
-                return bitmap
-    return None
-
 def blockdev_backup(vm, device, target, sync, **kwargs):
     # Strip any arguments explicitly nulled by the caller:
     kwargs = {key: val for key, val in kwargs.items() if val is not None}
@@ -214,13 +190,14 @@ def blockdev_backup(vm, device, target, sync, **kwargs):
                         device=device,
                         target=target,
                         sync=sync,
+                        filter_node_name='backup-top',
                         **kwargs)
     return result
 
 def blockdev_backup_mktarget(drive, target_id, filepath, sync, **kwargs):
     target_drive = Drive(filepath, vm=drive.vm)
     target_drive.create_target(target_id, drive.fmt, drive.size)
-    blockdev_backup(drive.vm, drive.name, target_id, sync, **kwargs)
+    blockdev_backup(drive.vm, drive.node, target_id, sync, **kwargs)
 
 def reference_backup(drive, n, filepath):
     log("--- Reference Backup #{:d} ---\n".format(n))
@@ -240,7 +217,7 @@ def backup(drive, n, filepath, sync, **kwargs):
                              job_id=job_id, **kwargs)
     return job_id
 
-def perform_writes(drive, n):
+def perform_writes(drive, n, filter_node_name=None):
     log("--- Write #{:d} ---\n".format(n))
     for pattern in GROUPS[n].patterns:
         cmd = "write -P{:s} 0x{:07x} 0x{:x}".format(
@@ -248,9 +225,9 @@ def perform_writes(drive, n):
             pattern.offset,
             pattern.size)
         log(cmd)
-        log(drive.vm.hmp_qemu_io(drive.name, cmd))
-    bitmaps = query_bitmaps(drive.vm)
-    log(bitmaps, indent=2)
+        log(drive.vm.hmp_qemu_io(filter_node_name or drive.node, cmd))
+    bitmaps = drive.vm.query_bitmaps()
+    log({'bitmaps': bitmaps}, indent=2)
     log('')
     return bitmaps
 
@@ -343,26 +320,19 @@ def test_bitmap_sync(bsync_mode, msync_mode='bitmap', failure=None):
                 }]
             }
 
+        drive0.node = 'drive0'
         vm.qmp_log('blockdev-add',
                    filters=[iotests.filter_qmp_testfiles],
-                   node_name="drive0",
+                   node_name=drive0.node,
                    driver=drive0.fmt,
                    file=file_config)
-        drive0.node = 'drive0'
-        drive0.device = 'device0'
-        # Use share-rw to allow writes directly to the node;
-        # The anonymous block-backend for this configuration prevents us
-        # from using HMP's qemu-io commands to address the device.
-        vm.qmp_log("device_add", id=drive0.device,
-                   drive=drive0.name, driver="scsi-hd",
-                   share_rw=True)
         log('')
 
         # 0 - Writes and Reference Backup
         perform_writes(drive0, 0)
         reference_backup(drive0, 0, fbackup0)
         log('--- Add Bitmap ---\n')
-        vm.qmp_log("block-dirty-bitmap-add", node=drive0.name,
+        vm.qmp_log("block-dirty-bitmap-add", node=drive0.node,
                    name="bitmap0", granularity=GRANULARITY)
         log('')
         ebitmap = EmulatedBitmap()
@@ -370,14 +340,14 @@ def test_bitmap_sync(bsync_mode, msync_mode='bitmap', failure=None):
         # 1 - Writes and Reference Backup
         bitmaps = perform_writes(drive0, 1)
         ebitmap.dirty_group(1)
-        bitmap = get_bitmap(bitmaps, drive0.device, 'bitmap0')
+        bitmap = vm.get_bitmap(drive0.node, 'bitmap0', bitmaps=bitmaps)
         ebitmap.compare(bitmap)
         reference_backup(drive0, 1, fbackup1)
 
         # 1 - Test Backup (w/ Optional induced failure)
         if failure == 'intermediate':
             # Activate blkdebug induced failure for second-to-next read
-            log(vm.hmp_qemu_io(drive0.name, 'flush'))
+            log(vm.hmp_qemu_io(drive0.node, 'flush'))
             log('')
         job = backup(drive0, 1, bsync1, msync_mode,
                      bitmap="bitmap0", bitmap_mode=bsync_mode)
@@ -386,14 +356,15 @@ def test_bitmap_sync(bsync_mode, msync_mode='bitmap', failure=None):
             """Issue writes while the job is open to test bitmap divergence."""
             # Note: when `failure` is 'intermediate', this isn't called.
             log('')
-            bitmaps = perform_writes(drive0, 2)
+            bitmaps = perform_writes(drive0, 2, filter_node_name='backup-top')
             # Named bitmap (static, should be unchanged)
-            ebitmap.compare(get_bitmap(bitmaps, drive0.device, 'bitmap0'))
+            ebitmap.compare(vm.get_bitmap(drive0.node, 'bitmap0',
+                                          bitmaps=bitmaps))
             # Anonymous bitmap (dynamic, shows new writes)
             anonymous = EmulatedBitmap()
             anonymous.dirty_group(2)
-            anonymous.compare(get_bitmap(bitmaps, drive0.device, '',
-                                         recording=True))
+            anonymous.compare(vm.get_bitmap(drive0.node, '', recording=True,
+                                            bitmaps=bitmaps))
 
             # Simulate the order in which this will happen:
             # group 1 gets cleared first, then group two gets written.
@@ -405,8 +376,8 @@ def test_bitmap_sync(bsync_mode, msync_mode='bitmap', failure=None):
         vm.run_job(job, auto_dismiss=True, auto_finalize=False,
                    pre_finalize=_callback,
                    cancel=(failure == 'simulated'))
-        bitmaps = query_bitmaps(vm)
-        log(bitmaps, indent=2)
+        bitmaps = vm.query_bitmaps()
+        log({'bitmaps': bitmaps}, indent=2)
         log('')
 
         if bsync_mode == 'always' and failure == 'intermediate':
@@ -423,29 +394,30 @@ def test_bitmap_sync(bsync_mode, msync_mode='bitmap', failure=None):
                 ebitmap.clear()
                 ebitmap.dirty_bits(range(fail_bit, SIZE // GRANULARITY))
 
-        ebitmap.compare(get_bitmap(bitmaps, drive0.device, 'bitmap0'))
+        ebitmap.compare(vm.get_bitmap(drive0.node, 'bitmap0', bitmaps=bitmaps))
 
         # 2 - Writes and Reference Backup
         bitmaps = perform_writes(drive0, 3)
         ebitmap.dirty_group(3)
-        ebitmap.compare(get_bitmap(bitmaps, drive0.device, 'bitmap0'))
+        ebitmap.compare(vm.get_bitmap(drive0.node, 'bitmap0', bitmaps=bitmaps))
         reference_backup(drive0, 2, fbackup2)
 
         # 2 - Bitmap Backup (In failure modes, this is a recovery.)
         job = backup(drive0, 2, bsync2, "bitmap",
                      bitmap="bitmap0", bitmap_mode=bsync_mode)
         vm.run_job(job, auto_dismiss=True, auto_finalize=False)
-        bitmaps = query_bitmaps(vm)
-        log(bitmaps, indent=2)
+        bitmaps = vm.query_bitmaps()
+        log({'bitmaps': bitmaps}, indent=2)
         log('')
         if bsync_mode != 'never':
             ebitmap.clear()
-        ebitmap.compare(get_bitmap(bitmaps, drive0.device, 'bitmap0'))
+        ebitmap.compare(vm.get_bitmap(drive0.node, 'bitmap0', bitmaps=bitmaps))
 
         log('--- Cleanup ---\n')
         vm.qmp_log("block-dirty-bitmap-remove",
-                   node=drive0.name, name="bitmap0")
-        log(query_bitmaps(vm), indent=2)
+                   node=drive0.node, name="bitmap0")
+        bitmaps = vm.query_bitmaps()
+        log({'bitmaps': bitmaps}, indent=2)
         vm.shutdown()
         log('')
 
@@ -484,22 +456,19 @@ def test_backup_api():
             'filename': drive0.path
         }
 
+        drive0.node = 'drive0'
         vm.qmp_log('blockdev-add',
                    filters=[iotests.filter_qmp_testfiles],
-                   node_name="drive0",
+                   node_name=drive0.node,
                    driver=drive0.fmt,
                    file=file_config)
-        drive0.node = 'drive0'
-        drive0.device = 'device0'
-        vm.qmp_log("device_add", id=drive0.device,
-                   drive=drive0.name, driver="scsi-hd")
         log('')
 
         target0 = Drive(backup_path, vm=vm)
         target0.create_target("backup_target", drive0.fmt, drive0.size)
         log('')
 
-        vm.qmp_log("block-dirty-bitmap-add", node=drive0.name,
+        vm.qmp_log("block-dirty-bitmap-add", node=drive0.node,
                    name="bitmap0", granularity=GRANULARITY)
         log('')
 
@@ -538,7 +507,7 @@ def test_backup_api():
             log("-- Sync mode {:s} tests --\n".format(sync_mode))
             for bitmap in (None, 'bitmap404', 'bitmap0'):
                 for policy in error_cases[sync_mode][bitmap]:
-                    blockdev_backup(drive0.vm, drive0.name, "backup_target",
+                    blockdev_backup(drive0.vm, drive0.node, "backup_target",
                                     sync_mode, job_id='api_job',
                                     bitmap=bitmap, bitmap_mode=policy)
                     log('')

tests/qemu-iotests/common.rc

@@ -405,6 +405,23 @@ _check_test_img()
             $QEMU_IMG check "$@" -f $IMGFMT "$TEST_IMG" 2>&1
         fi
     ) | _filter_testdir | _filter_qemu_img_check
+
+    # return real qemu_img check status, to analyze in
+    # _check_test_img_ignore_leaks
+    return ${PIPESTATUS[0]}
+}
+
+_check_test_img_ignore_leaks()
+{
+    out=$(_check_test_img "$@")
+    status=$?
+    if [ $status = 3 ]; then
+        # This must correspond to success output in dump_human_image_check()
+        echo "No errors were found on the image."
+        return 0
+    fi
+    echo "$out"
+    return $status
 }
 
 _img_info()

tests/qemu-iotests/iotests.py

@@ -641,6 +641,33 @@ class VM(qtest.QEMUQtestMachine):
                 return x
         return None
 
+    def query_bitmaps(self):
+        res = self.qmp("query-named-block-nodes")
+        return {device['node-name']: device['dirty-bitmaps']
+                for device in res['return'] if 'dirty-bitmaps' in device}
+
+    def get_bitmap(self, node_name, bitmap_name, recording=None, bitmaps=None):
+        """
+        get a specific bitmap from the object returned by query_bitmaps.
+        :param recording: If specified, filter results by the specified value.
+        :param bitmaps: If specified, use it instead of call query_bitmaps()
+        """
+        if bitmaps is None:
+            bitmaps = self.query_bitmaps()
+
+        for bitmap in bitmaps[node_name]:
+            if bitmap.get('name', '') == bitmap_name:
+                if recording is None:
+                    return bitmap
+                elif bitmap.get('recording') == recording:
+                    return bitmap
+        return None
+
+    def check_bitmap_status(self, node_name, bitmap_name, fields):
+        ret = self.get_bitmap(node_name, bitmap_name)
+
+        return fields.items() <= ret.items()
+
 
 index_re = re.compile(r'([^\[]+)\[([^\]]+)\]')