Series comparison

The following changes since commit 75ee62ac606bfc9eb59310b9446df3434bf6e8c2:

Merge remote-tracking branch 'remotes/ehabkost-gl/tags/x86-next-pull-request' into staging (2020-12-17 18:53:36 +0000)

are available in the Git repository at:

https://github.com/XanClic/qemu.git tags/pull-block-2020-12-18

for you to fetch changes up to 0e72078128229bf9efb542e396ab44bf91b91340:

iotests: Fix _send_qemu_cmd with bash 5.1 (2020-12-18 12:47:38 +0100)

----------------------------------------------------------------
Block patches:
- New block filter: preallocate (which, on writes beyond an image file's
  end, allocates big chunks of data so that such post-EOF writes will
  occur less frequently)
- write-zeroes and block-status support for Quorum
- Implementation of truncate for the nvme block driver similarly to the
  existing implementations for host block devices and iscsi devices
- Block layer refactoring: Drop the tighten_restrictions concept in the
  block permission functions
- iotest fixes

----------------------------------------------------------------
Alberto Garcia (2):
  quorum: Implement bdrv_co_block_status()
  quorum: Implement bdrv_co_pwrite_zeroes()

Max Reitz (2):
  iotests/102: Pass $QEMU_HANDLE to _send_qemu_cmd
  iotests: Fix _send_qemu_cmd with bash 5.1

Philippe Mathieu-Daudé (1):
  block/nvme: Implement fake truncate() coroutine

Vladimir Sementsov-Ogievskiy (25):
  block: add bdrv_refresh_perms() helper
  block: bdrv_set_perm() drop redundant parameters.
  block: bdrv_child_set_perm() drop redundant parameters.
  block: drop tighten_restrictions
  block: simplify comment to BDRV_REQ_SERIALISING
  block/io.c: drop assertion on double waiting for request serialisation
  block/io: split out bdrv_find_conflicting_request
  block/io: bdrv_wait_serialising_requests_locked: drop extra bs arg
  block: bdrv_mark_request_serialising: split non-waiting function
  block: introduce BDRV_REQ_NO_WAIT flag
  block: bdrv_check_perm(): process children anyway
  block: introduce preallocate filter
  qemu-io: add preallocate mode parameter for truncate command
  iotests: qemu_io_silent: support --image-opts
  iotests.py: execute_setup_common(): add required_fmts argument
  iotests: add 298 to test new preallocate filter driver
  scripts/simplebench: fix grammar: s/successed/succeeded/
  scripts/simplebench: support iops
  scripts/simplebench: use standard deviation for +- error
  simplebench: rename ascii() to results_to_text()
  simplebench: move results_to_text() into separate file
  simplebench/results_to_text: improve view of the table
  simplebench/results_to_text: add difference line to the table
  simplebench/results_to_text: make executable
  scripts/simplebench: add bench_prealloc.py

-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Make separate function for common pattern.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201106124241.16950-5-vsementsov@virtuozzo.com>
[mreitz: Squashed in
https://lists.nongnu.org/archive/html/qemu-block/2020-11/msg00299.html]
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c | 61 +++++++++++++++++++++++++++++----------------------------
 1 file changed, 31 insertions(+), 30 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ static void bdrv_child_abort_perm_update(BdrvChild *c)
     bdrv_abort_perm_update(c->bs);
 }
 
+static int bdrv_refresh_perms(BlockDriverState *bs, bool *tighten_restrictions,
+                              Error **errp)
+{
+    int ret;
+    uint64_t perm, shared_perm;
+
+    bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
+    ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL,
+                          tighten_restrictions, errp);
+    if (ret < 0) {
+        bdrv_abort_perm_update(bs);
+        return ret;
+    }
+    bdrv_set_perm(bs, perm, shared_perm);
+
+    return 0;
+}
+
 int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
                             Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
     }
 
     if (old_bs) {
-        /* Update permissions for old node. This is guaranteed to succeed
-         * because we're just taking a parent away, so we're loosening
-         * restrictions. */
         bool tighten_restrictions;
-        int ret;
 
-        bdrv_get_cumulative_perm(old_bs, &perm, &shared_perm);
-        ret = bdrv_check_perm(old_bs, NULL, perm, shared_perm, NULL,
-                              &tighten_restrictions, NULL);
+        /*
+         * Update permissions for old node. We're just taking a parent away, so
+         * we're loosening restrictions. Errors of permission update are not
+         * fatal in this case, ignore them.
+         */
+        bdrv_refresh_perms(old_bs, &tighten_restrictions, NULL);
         assert(tighten_restrictions == false);
-        if (ret < 0) {
-            /* We only tried to loosen restrictions, so errors are not fatal */
-            bdrv_abort_perm_update(old_bs);
-        } else {
-            bdrv_set_perm(old_bs, perm, shared_perm);
-        }
 
         /* When the parent requiring a non-default AioContext is removed, the
          * node moves back to the main AioContext */
@@ -XXX,XX +XXX,XX @@ void bdrv_init_with_whitelist(void)
 int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp)
 {
     BdrvChild *child, *parent;
-    uint64_t perm, shared_perm;
     Error *local_err = NULL;
     int ret;
     BdrvDirtyBitmap *bm;
@@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp)
      */
     if (bs->open_flags & BDRV_O_INACTIVE) {
         bs->open_flags &= ~BDRV_O_INACTIVE;
-        bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
-        ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, NULL, errp);
+        ret = bdrv_refresh_perms(bs, NULL, errp);
         if (ret < 0) {
-            bdrv_abort_perm_update(bs);
             bs->open_flags |= BDRV_O_INACTIVE;
             return ret;
         }
-        bdrv_set_perm(bs, perm, shared_perm);
 
         if (bs->drv->bdrv_co_invalidate_cache) {
             bs->drv->bdrv_co_invalidate_cache(bs, &local_err);
@@ -XXX,XX +XXX,XX @@ static int bdrv_inactivate_recurse(BlockDriverState *bs)
 {
     BdrvChild *child, *parent;
     bool tighten_restrictions;
-    uint64_t perm, shared_perm;
     int ret;
 
     if (!bs->drv) {
@@ -XXX,XX +XXX,XX @@ static int bdrv_inactivate_recurse(BlockDriverState *bs)
 
     bs->open_flags |= BDRV_O_INACTIVE;
 
-    /* Update permissions, they may differ for inactive nodes */
-    bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
-    ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL,
-                          &tighten_restrictions, NULL);
+    /*
+     * Update permissions, they may differ for inactive nodes.
+     * We only tried to loosen restrictions, so errors are not fatal, ignore
+     * them.
+     */
+    bdrv_refresh_perms(bs, &tighten_restrictions, NULL);
     assert(tighten_restrictions == false);
-    if (ret < 0) {
-        /* We only tried to loosen restrictions, so errors are not fatal */
-        bdrv_abort_perm_update(bs);
-    } else {
-        bdrv_set_perm(bs, perm, shared_perm);
-    }
-
 
     /* Recursively inactivate children */
     QLIST_FOREACH(child, &bs->children, next) {
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

We should never set permissions other than cumulative permissions of
parents. During bdrv_reopen_multiple() we _check_ for synthetic
permissions but when we do _set_ the graph is already updated.
Add an assertion to bdrv_reopen_multiple(), other cases are more
obvious.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201106124241.16950-6-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ static void bdrv_abort_perm_update(BlockDriverState *bs)
     }
 }
 
-static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms,
-                          uint64_t cumulative_shared_perms)
+static void bdrv_set_perm(BlockDriverState *bs)
 {
+    uint64_t cumulative_perms, cumulative_shared_perms;
     BlockDriver *drv = bs->drv;
     BdrvChild *c;
 
@@ -XXX,XX +XXX,XX @@ static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms,
         return;
     }
 
+    bdrv_get_cumulative_perm(bs, &cumulative_perms, &cumulative_shared_perms);
+
     /* Update this node */
     if (drv->bdrv_set_perm) {
         drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms);
@@ -XXX,XX +XXX,XX @@ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
 
 static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared)
 {
-    uint64_t cumulative_perms, cumulative_shared_perms;
-
     c->has_backup_perm = false;
 
     c->perm = perm;
     c->shared_perm = shared;
 
-    bdrv_get_cumulative_perm(c->bs, &cumulative_perms,
-                             &cumulative_shared_perms);
-    bdrv_set_perm(c->bs, cumulative_perms, cumulative_shared_perms);
+    bdrv_set_perm(c->bs);
 }
 
 static void bdrv_child_abort_perm_update(BdrvChild *c)
@@ -XXX,XX +XXX,XX @@ static int bdrv_refresh_perms(BlockDriverState *bs, bool *tighten_restrictions,
         bdrv_abort_perm_update(bs);
         return ret;
     }
-    bdrv_set_perm(bs, perm, shared_perm);
+    bdrv_set_perm(bs);
 
     return 0;
 }
@@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child,
 static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
 {
     BlockDriverState *old_bs = child->bs;
-    uint64_t perm, shared_perm;
 
     /* Asserts that child->frozen == false */
     bdrv_replace_child_noperm(child, new_bs);
@@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
      * restrictions.
      */
     if (new_bs) {
-        bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm);
-        bdrv_set_perm(new_bs, perm, shared_perm);
+        bdrv_set_perm(new_bs);
     }
 
     if (old_bs) {
@@ -XXX,XX +XXX,XX @@ cleanup_perm:
         }
 
         if (ret == 0) {
-            bdrv_set_perm(state->bs, state->perm, state->shared_perm);
+            uint64_t perm, shared;
+
+            bdrv_get_cumulative_perm(state->bs, &perm, &shared);
+            assert(perm == state->perm);
+            assert(shared == state->shared_perm);
+
+            bdrv_set_perm(state->bs);
         } else {
             bdrv_abort_perm_update(state->bs);
             if (state->replace_backing_bs && state->new_backing_bs) {
@@ -XXX,XX +XXX,XX @@ static void bdrv_replace_node_common(BlockDriverState *from,
         bdrv_unref(from);
     }
 
-    bdrv_get_cumulative_perm(to, &perm, &shared);
-    bdrv_set_perm(to, perm, shared);
+    bdrv_set_perm(to);
 
 out:
     g_slist_free(list);
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

We must set the permission used for _check_.  Assert that we have
backup and drop extra arguments.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201106124241.16950-7-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
                                  GSList *ignore_children,
                                  bool *tighten_restrictions, Error **errp);
 static void bdrv_child_abort_perm_update(BdrvChild *c);
-static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared);
+static void bdrv_child_set_perm(BdrvChild *c);
 
 typedef struct BlockReopenQueueEntry {
      bool prepared;
@@ -XXX,XX +XXX,XX @@ static void bdrv_set_perm(BlockDriverState *bs)
 
     /* Update all children */
     QLIST_FOREACH(c, &bs->children, next) {
-        uint64_t cur_perm, cur_shared;
-        bdrv_child_perm(bs, c->bs, c, c->role, NULL,
-                        cumulative_perms, cumulative_shared_perms,
-                        &cur_perm, &cur_shared);
-        bdrv_child_set_perm(c, cur_perm, cur_shared);
+        bdrv_child_set_perm(c);
     }
 }
 
@@ -XXX,XX +XXX,XX @@ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
     return 0;
 }
 
-static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared)
+static void bdrv_child_set_perm(BdrvChild *c)
 {
     c->has_backup_perm = false;
 
-    c->perm = perm;
-    c->shared_perm = shared;
-
     bdrv_set_perm(c->bs);
 }
 
@@ -XXX,XX +XXX,XX @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
         return ret;
     }
 
-    bdrv_child_set_perm(c, perm, shared);
+    bdrv_child_set_perm(c);
 
     return 0;
 }
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

The only users of this thing are:
 1. bdrv_child_try_set_perm, to ignore failures on loosen restrictions
 2. assertion in bdrv_replace_child
 3. assertion in bdrv_inactivate_recurse

Assertions are not enough reason for overcomplication the permission
update system. So, look at bdrv_child_try_set_perm.

We are interested in tighten_restrictions only on failure. But on
failure this field is not reliable: we may fail in the middle of
permission update, some nodes are not touched and we don't know should
their permissions be tighten or not. So, we rely on the fact that if we
loose restrictions on some node (or BdrvChild), we'll not tighten
restriction in the whole subtree as part of this update (assertions 2
and 3 rely on this fact as well). And, if we rely on this fact anyway,
we can just check it on top, and don't pass additional pointer through
the whole recursive infrastructure.

Note also, that further patches will fix real bugs in permission update
system, so now is good time to simplify it, as a help for further
refactorings.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201106124241.16950-8-vsementsov@virtuozzo.com>
[mreitz: Fixed rebase conflict]
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c | 89 +++++++++++----------------------------------------------
 1 file changed, 17 insertions(+), 72 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ static int bdrv_fill_options(QDict **options, const char *filename,
 
 static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
                                  uint64_t perm, uint64_t shared,
-                                 GSList *ignore_children,
-                                 bool *tighten_restrictions, Error **errp);
+                                 GSList *ignore_children, Error **errp);
 static void bdrv_child_abort_perm_update(BdrvChild *c);
 static void bdrv_child_set_perm(BdrvChild *c);
 
@@ -XXX,XX +XXX,XX @@ static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs,
  * permissions of all its parents. This involves checking whether all necessary
  * permission changes to child nodes can be performed.
  *
- * Will set *tighten_restrictions to true if and only if new permissions have to
- * be taken or currently shared permissions are to be unshared.  Otherwise,
- * errors are not fatal as long as the caller accepts that the restrictions
- * remain tighter than they need to be.  The caller still has to abort the
- * transaction.
- * @tighten_restrictions cannot be used together with @q: When reopening, we may
- * encounter fatal errors even though no restrictions are to be tightened.  For
- * example, changing a node from RW to RO will fail if the WRITE permission is
- * to be kept.
- *
  * A call to this function must always be followed by a call to bdrv_set_perm()
  * or bdrv_abort_perm_update().
  */
 static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
                            uint64_t cumulative_perms,
                            uint64_t cumulative_shared_perms,
-                           GSList *ignore_children,
-                           bool *tighten_restrictions, Error **errp)
+                           GSList *ignore_children, Error **errp)
 {
     BlockDriver *drv = bs->drv;
     BdrvChild *c;
     int ret;
 
-    assert(!q || !tighten_restrictions);
-
-    if (tighten_restrictions) {
-        uint64_t current_perms, current_shared;
-        uint64_t added_perms, removed_shared_perms;
-
-        bdrv_get_cumulative_perm(bs, &current_perms, &current_shared);
-
-        added_perms = cumulative_perms & ~current_perms;
-        removed_shared_perms = current_shared & ~cumulative_shared_perms;
-
-        *tighten_restrictions = added_perms || removed_shared_perms;
-    }
-
     /* Write permissions never work with read-only images */
     if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) &&
         !bdrv_is_writable_after_reopen(bs, q))
@@ -XXX,XX +XXX,XX @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
     /* Check all children */
     QLIST_FOREACH(c, &bs->children, next) {
         uint64_t cur_perm, cur_shared;
-        bool child_tighten_restr;
 
         bdrv_child_perm(bs, c->bs, c, c->role, q,
                         cumulative_perms, cumulative_shared_perms,
                         &cur_perm, &cur_shared);
         ret = bdrv_child_check_perm(c, q, cur_perm, cur_shared, ignore_children,
-                                    tighten_restrictions ? &child_tighten_restr
-                                                         : NULL,
                                     errp);
-        if (tighten_restrictions) {
-            *tighten_restrictions |= child_tighten_restr;
-        }
         if (ret < 0) {
             return ret;
         }
@@ -XXX,XX +XXX,XX @@ char *bdrv_perm_names(uint64_t perm)
  * set, the BdrvChild objects in this list are ignored in the calculations;
  * this allows checking permission updates for an existing reference.
  *
- * See bdrv_check_perm() for the semantics of @tighten_restrictions.
- *
  * Needs to be followed by a call to either bdrv_set_perm() or
  * bdrv_abort_perm_update(). */
 static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q,
                                   uint64_t new_used_perm,
                                   uint64_t new_shared_perm,
                                   GSList *ignore_children,
-                                  bool *tighten_restrictions,
                                   Error **errp)
 {
     BdrvChild *c;
     uint64_t cumulative_perms = new_used_perm;
     uint64_t cumulative_shared_perms = new_shared_perm;
 
-    assert(!q || !tighten_restrictions);
 
     /* There is no reason why anyone couldn't tolerate write_unchanged */
     assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED);
@@ -XXX,XX +XXX,XX @@ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q,
             char *user = bdrv_child_user_desc(c);
             char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm);
 
-            if (tighten_restrictions) {
-                *tighten_restrictions = true;
-            }
-
             error_setg(errp, "Conflicts with use by %s as '%s', which does not "
                              "allow '%s' on %s",
                        user, c->name, perm_names, bdrv_get_node_name(c->bs));
@@ -XXX,XX +XXX,XX @@ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q,
             char *user = bdrv_child_user_desc(c);
             char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm);
 
-            if (tighten_restrictions) {
-                *tighten_restrictions = true;
-            }
-
             error_setg(errp, "Conflicts with use by %s as '%s', which uses "
                              "'%s' on %s",
                        user, c->name, perm_names, bdrv_get_node_name(c->bs));
@@ -XXX,XX +XXX,XX @@ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q,
     }
 
     return bdrv_check_perm(bs, q, cumulative_perms, cumulative_shared_perms,
-                           ignore_children, tighten_restrictions, errp);
+                           ignore_children, errp);
 }
 
 /* Needs to be followed by a call to either bdrv_child_set_perm() or
  * bdrv_child_abort_perm_update(). */
 static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
                                  uint64_t perm, uint64_t shared,
-                                 GSList *ignore_children,
-                                 bool *tighten_restrictions, Error **errp)
+                                 GSList *ignore_children, Error **errp)
 {
     int ret;
 
     ignore_children = g_slist_prepend(g_slist_copy(ignore_children), c);
-    ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children,
-                                 tighten_restrictions, errp);
+    ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children, errp);
     g_slist_free(ignore_children);
 
     if (ret < 0) {
@@ -XXX,XX +XXX,XX @@ static void bdrv_child_abort_perm_update(BdrvChild *c)
     bdrv_abort_perm_update(c->bs);
 }
 
-static int bdrv_refresh_perms(BlockDriverState *bs, bool *tighten_restrictions,
-                              Error **errp)
+static int bdrv_refresh_perms(BlockDriverState *bs, Error **errp)
 {
     int ret;
     uint64_t perm, shared_perm;
 
     bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
-    ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL,
-                          tighten_restrictions, errp);
+    ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, errp);
     if (ret < 0) {
         bdrv_abort_perm_update(bs);
         return ret;
@@ -XXX,XX +XXX,XX @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
 {
     Error *local_err = NULL;
     int ret;
-    bool tighten_restrictions;
 
-    ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL,
-                                &tighten_restrictions, &local_err);
+    ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL, &local_err);
     if (ret < 0) {
         bdrv_child_abort_perm_update(c);
-        if (tighten_restrictions) {
+        if ((perm & ~c->perm) || (c->shared_perm & ~shared)) {
+            /* tighten permissions */
             error_propagate(errp, local_err);
         } else {
             /*
@@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
     }
 
     if (old_bs) {
-        bool tighten_restrictions;
-
         /*
          * Update permissions for old node. We're just taking a parent away, so
          * we're loosening restrictions. Errors of permission update are not
          * fatal in this case, ignore them.
          */
-        bdrv_refresh_perms(old_bs, &tighten_restrictions, NULL);
-        assert(tighten_restrictions == false);
+        bdrv_refresh_perms(old_bs, NULL);
 
         /* When the parent requiring a non-default AioContext is removed, the
          * node moves back to the main AioContext */
@@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, NULL,
-                                 errp);
+    ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, errp);
     if (ret < 0) {
         bdrv_abort_perm_update(child_bs);
         bdrv_unref(child_bs);
@@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
     QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
         BDRVReopenState *state = &bs_entry->state;
         ret = bdrv_check_perm(state->bs, bs_queue, state->perm,
-                              state->shared_perm, NULL, NULL, errp);
+                              state->shared_perm, NULL, errp);
         if (ret < 0) {
             goto cleanup_perm;
         }
@@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
                             bs_queue, state->perm, state->shared_perm,
                             &nperm, &nshared);
             ret = bdrv_check_update_perm(state->new_backing_bs, NULL,
-                                         nperm, nshared, NULL, NULL, errp);
+                                         nperm, nshared, NULL, errp);
             if (ret < 0) {
                 goto cleanup_perm;
             }
@@ -XXX,XX +XXX,XX @@ static void bdrv_replace_node_common(BlockDriverState *from,
 
     /* Check whether the required permissions can be granted on @to, ignoring
      * all BdrvChild in @list so that they can't block themselves. */
-    ret = bdrv_check_update_perm(to, NULL, perm, shared, list, NULL, errp);
+    ret = bdrv_check_update_perm(to, NULL, perm, shared, list, errp);
     if (ret < 0) {
         bdrv_abort_perm_update(to);
         goto out;
@@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp)
      */
     if (bs->open_flags & BDRV_O_INACTIVE) {
         bs->open_flags &= ~BDRV_O_INACTIVE;
-        ret = bdrv_refresh_perms(bs, NULL, errp);
+        ret = bdrv_refresh_perms(bs, errp);
         if (ret < 0) {
             bs->open_flags |= BDRV_O_INACTIVE;
             return ret;
@@ -XXX,XX +XXX,XX @@ static bool bdrv_has_bds_parent(BlockDriverState *bs, bool only_active)
 static int bdrv_inactivate_recurse(BlockDriverState *bs)
 {
     BdrvChild *child, *parent;
-    bool tighten_restrictions;
     int ret;
 
     if (!bs->drv) {
@@ -XXX,XX +XXX,XX @@ static int bdrv_inactivate_recurse(BlockDriverState *bs)
      * We only tried to loosen restrictions, so errors are not fatal, ignore
      * them.
      */
-    bdrv_refresh_perms(bs, &tighten_restrictions, NULL);
-    assert(tighten_restrictions == false);
+    bdrv_refresh_perms(bs, NULL);
 
     /* Recursively inactivate children */
     QLIST_FOREACH(child, &bs->children, next) {
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

1. BDRV_REQ_NO_SERIALISING doesn't exist already, don't mention it.

2. We are going to add one more user of BDRV_REQ_SERIALISING, so
   comment about backup becomes a bit confusing here. The use case in
   backup is documented in block/backup.c, so let's just drop
   duplication here.

3. The fact that BDRV_REQ_SERIALISING is only for write requests is
   omitted. Add a note.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Alberto Garcia <berto@igalia.com>
Message-Id: <20201021145859.11201-2-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block.h | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
      * content. */
     BDRV_REQ_WRITE_UNCHANGED    = 0x40,
 
-    /*
-     * BDRV_REQ_SERIALISING forces request serialisation for writes.
-     * It is used to ensure that writes to the backing file of a backup process
-     * target cannot race with a read of the backup target that defers to the
-     * backing file.
-     *
-     * Note, that BDRV_REQ_SERIALISING is _not_ opposite in meaning to
-     * BDRV_REQ_NO_SERIALISING. A more descriptive name for the latter might be
-     * _DO_NOT_WAIT_FOR_SERIALISING, except that is too long.
-     */
+    /* Forces request serialisation. Use only with write requests. */
     BDRV_REQ_SERIALISING        = 0x80,
 
     /* Execute the request only if the operation can be offloaded or otherwise
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

The comments states, that on misaligned request we should have already
been waiting. But for bdrv_padding_rmw_read, we called
bdrv_mark_request_serialising with align = request_alignment, and now
we serialise with align = cluster_size. So we may have to wait again
with larger alignment.

Note, that the only user of BDRV_REQ_SERIALISING is backup which issues
cluster-aligned requests, so seems the assertion should not fire for
now. But it's wrong anyway.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20201021145859.11201-3-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/io.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
                           BdrvTrackedRequest *req, int flags)
 {
     BlockDriverState *bs = child->bs;
-    bool waited;
     int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
 
     if (bs->read_only) {
@@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
     assert(!(flags & ~BDRV_REQ_MASK));
 
     if (flags & BDRV_REQ_SERIALISING) {
-        waited = bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
-        /*
-         * For a misaligned request we should have already waited earlier,
-         * because we come after bdrv_padding_rmw_read which must be called
-         * with the request already marked as serialising.
-         */
-        assert(!waited ||
-               (req->offset == req->overlap_offset &&
-                req->bytes == req->overlap_bytes));
+        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
     } else {
         bdrv_wait_serialising_requests(req);
     }
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

To be reused in separate.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20201021145859.11201-4-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/io.c | 71 +++++++++++++++++++++++++++++++-----------------------
 1 file changed, 41 insertions(+), 30 deletions(-)

diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ static bool tracked_request_overlaps(BdrvTrackedRequest *req,
     return true;
 }
 
+/* Called with self->bs->reqs_lock held */
+static BdrvTrackedRequest *
+bdrv_find_conflicting_request(BdrvTrackedRequest *self)
+{
+    BdrvTrackedRequest *req;
+
+    QLIST_FOREACH(req, &self->bs->tracked_requests, list) {
+        if (req == self || (!req->serialising && !self->serialising)) {
+            continue;
+        }
+        if (tracked_request_overlaps(req, self->overlap_offset,
+                                     self->overlap_bytes))
+        {
+            /*
+             * Hitting this means there was a reentrant request, for
+             * example, a block driver issuing nested requests.  This must
+             * never happen since it means deadlock.
+             */
+            assert(qemu_coroutine_self() != req->co);
+
+            /*
+             * If the request is already (indirectly) waiting for us, or
+             * will wait for us as soon as it wakes up, then just go on
+             * (instead of producing a deadlock in the former case).
+             */
+            if (!req->waiting_for) {
+                return req;
+            }
+        }
+    }
+
+    return NULL;
+}
+
 static bool coroutine_fn
 bdrv_wait_serialising_requests_locked(BlockDriverState *bs,
                                       BdrvTrackedRequest *self)
 {
     BdrvTrackedRequest *req;
-    bool retry;
     bool waited = false;
 
-    do {
-        retry = false;
-        QLIST_FOREACH(req, &bs->tracked_requests, list) {
-            if (req == self || (!req->serialising && !self->serialising)) {
-                continue;
-            }
-            if (tracked_request_overlaps(req, self->overlap_offset,
-                                         self->overlap_bytes))
-            {
-                /* Hitting this means there was a reentrant request, for
-                 * example, a block driver issuing nested requests.  This must
-                 * never happen since it means deadlock.
-                 */
-                assert(qemu_coroutine_self() != req->co);
-
-                /* If the request is already (indirectly) waiting for us, or
-                 * will wait for us as soon as it wakes up, then just go on
-                 * (instead of producing a deadlock in the former case). */
-                if (!req->waiting_for) {
-                    self->waiting_for = req;
-                    qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock);
-                    self->waiting_for = NULL;
-                    retry = true;
-                    waited = true;
-                    break;
-                }
-            }
-        }
-    } while (retry);
+    while ((req = bdrv_find_conflicting_request(self))) {
+        self->waiting_for = req;
+        qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock);
+        self->waiting_for = NULL;
+        waited = true;
+    }
+
     return waited;
 }
 
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

bs is linked in req, so no needs to pass it separately. Most of
tracked-requests API doesn't have bs argument. Actually, after this
patch only tracked_request_begin has it, but it's for purpose.

While being here, also add a comment about what "_locked" is.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20201021145859.11201-5-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/io.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ bdrv_find_conflicting_request(BdrvTrackedRequest *self)
     return NULL;
 }
 
+/* Called with self->bs->reqs_lock held */
 static bool coroutine_fn
-bdrv_wait_serialising_requests_locked(BlockDriverState *bs,
-                                      BdrvTrackedRequest *self)
+bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self)
 {
     BdrvTrackedRequest *req;
     bool waited = false;
 
     while ((req = bdrv_find_conflicting_request(self))) {
         self->waiting_for = req;
-        qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock);
+        qemu_co_queue_wait(&req->wait_queue, &self->bs->reqs_lock);
         self->waiting_for = NULL;
         waited = true;
     }
@@ -XXX,XX +XXX,XX @@ bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
 
     req->overlap_offset = MIN(req->overlap_offset, overlap_offset);
     req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
-    waited = bdrv_wait_serialising_requests_locked(bs, req);
+    waited = bdrv_wait_serialising_requests_locked(req);
     qemu_co_mutex_unlock(&bs->reqs_lock);
     return waited;
 }
@@ -XXX,XX +XXX,XX @@ static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self
     }
 
     qemu_co_mutex_lock(&bs->reqs_lock);
-    waited = bdrv_wait_serialising_requests_locked(bs, self);
+    waited = bdrv_wait_serialising_requests_locked(self);
     qemu_co_mutex_unlock(&bs->reqs_lock);
 
     return waited;
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

We'll need a separate function, which will only "mark" request
serialising with specified align but not wait for conflicting
requests. So, it will be like old bdrv_mark_request_serialising(),
before merging bdrv_wait_serialising_requests_locked() into it.

To reduce the possible mess, let's do the following:

Public function that does both marking and waiting will be called
bdrv_make_request_serialising, and private function which will only
"mark" will be called tracked_request_set_serialising().

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20201021145859.11201-6-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block_int.h |  3 ++-
 block/file-posix.c        |  2 +-
 block/io.c                | 35 +++++++++++++++++++++++------------
 3 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/block/block_int.h b/include/block/block_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -XXX,XX +XXX,XX @@ extern unsigned int bdrv_drain_all_count;
 void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
 void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
 
-bool coroutine_fn bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align);
+bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req,
+                                                uint64_t align);
 BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs);
 
 int get_tmp_filename(char *filename, int size);
diff --git a/block/file-posix.c b/block/file-posix.c
index XXXXXXX..XXXXXXX 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -XXX,XX +XXX,XX @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
 
         assert(bdrv_check_request(req->offset, req->bytes) == 0);
 
-        bdrv_mark_request_serialising(req, bs->bl.request_alignment);
+        bdrv_make_request_serialising(req, bs->bl.request_alignment);
     }
 #endif
 
diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self)
     return waited;
 }
 
-bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
+/* Called with req->bs->reqs_lock held */
+static void tracked_request_set_serialising(BdrvTrackedRequest *req,
+                                            uint64_t align)
 {
-    BlockDriverState *bs = req->bs;
     int64_t overlap_offset = req->offset & ~(align - 1);
     uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
                                - overlap_offset;
-    bool waited;
 
-    qemu_co_mutex_lock(&bs->reqs_lock);
     if (!req->serialising) {
         qatomic_inc(&req->bs->serialising_in_flight);
         req->serialising = true;
@@ -XXX,XX +XXX,XX @@ bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
 
     req->overlap_offset = MIN(req->overlap_offset, overlap_offset);
     req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
-    waited = bdrv_wait_serialising_requests_locked(req);
-    qemu_co_mutex_unlock(&bs->reqs_lock);
-    return waited;
 }
 
 /**
@@ -XXX,XX +XXX,XX @@ static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self
     return waited;
 }
 
+bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req,
+                                                uint64_t align)
+{
+    bool waited;
+
+    qemu_co_mutex_lock(&req->bs->reqs_lock);
+
+    tracked_request_set_serialising(req, align);
+    waited = bdrv_wait_serialising_requests_locked(req);
+
+    qemu_co_mutex_unlock(&req->bs->reqs_lock);
+
+    return waited;
+}
+
 int bdrv_check_request(int64_t offset, int64_t bytes)
 {
     if (offset < 0 || bytes < 0) {
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
          * with each other for the same cluster.  For example, in copy-on-read
          * it ensures that the CoR read and write operations are atomic and
          * guest writes cannot interleave between them. */
-        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
+        bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs));
     } else {
         bdrv_wait_serialising_requests(req);
     }
@@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
     assert(!(flags & ~BDRV_REQ_MASK));
 
     if (flags & BDRV_REQ_SERIALISING) {
-        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
+        bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs));
     } else {
         bdrv_wait_serialising_requests(req);
     }
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
 
     padding = bdrv_init_padding(bs, offset, bytes, &pad);
     if (padding) {
-        bdrv_mark_request_serialising(req, align);
+        bdrv_make_request_serialising(req, align);
 
         bdrv_padding_rmw_read(child, req, &pad, true);
 
@@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
     }
 
     if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) {
-        bdrv_mark_request_serialising(&req, align);
+        bdrv_make_request_serialising(&req, align);
         bdrv_padding_rmw_read(child, &req, &pad, false);
     }
 
@@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
      * new area, we need to make sure that no write requests are made to it
      * concurrently or they might be overwritten by preallocation. */
     if (new_bytes) {
-        bdrv_mark_request_serialising(&req, 1);
+        bdrv_make_request_serialising(&req, 1);
     }
     if (bs->read_only) {
         error_setg(errp, "Image is read-only");
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Add flag to make serialising request no wait: if there are conflicting
requests, just return error immediately. It's will be used in upcoming
preallocate filter.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20201021145859.11201-7-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block.h |  9 ++++++++-
 block/io.c            | 11 ++++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
      * written to qiov parameter which may be NULL.
      */
     BDRV_REQ_PREFETCH  = 0x200,
+
+    /*
+     * If we need to wait for other requests, just fail immediately. Used
+     * only together with BDRV_REQ_SERIALISING.
+     */
+    BDRV_REQ_NO_WAIT = 0x400,
+
     /* Mask of valid flags */
-    BDRV_REQ_MASK               = 0x3ff,
+    BDRV_REQ_MASK               = 0x7ff,
 } BdrvRequestFlags;
 
 typedef struct BlockSizes {
diff --git a/block/io.c b/block/io.c
index XXXXXXX..XXXXXXX 100644
--- a/block/io.c
+++ b/block/io.c
@@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
     assert(!(bs->open_flags & BDRV_O_INACTIVE));
     assert((bs->open_flags & BDRV_O_NO_IO) == 0);
     assert(!(flags & ~BDRV_REQ_MASK));
+    assert(!((flags & BDRV_REQ_NO_WAIT) && !(flags & BDRV_REQ_SERIALISING)));
 
     if (flags & BDRV_REQ_SERIALISING) {
-        bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs));
+        QEMU_LOCK_GUARD(&bs->reqs_lock);
+
+        tracked_request_set_serialising(req, bdrv_get_cluster_size(bs));
+
+        if ((flags & BDRV_REQ_NO_WAIT) && bdrv_find_conflicting_request(req)) {
+            return -EBUSY;
+        }
+
+        bdrv_wait_serialising_requests_locked(req);
     } else {
         bdrv_wait_serialising_requests(req);
     }
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Do generic processing even for drivers which define .bdrv_check_perm
handler. It's needed for further preallocate filter: it will need to do
additional action on bdrv_check_perm, but don't want to reimplement
generic logic.

The patch doesn't change existing behaviour: the only driver that
implements bdrv_check_perm is file-posix, but it never has any
children.

Also, bdrv_set_perm() don't stop processing if driver has
.bdrv_set_perm handler as well.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-8-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
     }
 
     if (drv->bdrv_check_perm) {
-        return drv->bdrv_check_perm(bs, cumulative_perms,
-                                    cumulative_shared_perms, errp);
+        ret = drv->bdrv_check_perm(bs, cumulative_perms,
+                                   cumulative_shared_perms, errp);
+        if (ret < 0) {
+            return ret;
+        }
     }
 
     /* Drivers that never have children can omit .bdrv_child_perm() */
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

It's intended to be inserted between format and protocol nodes to
preallocate additional space (expanding protocol file) on writes
crossing EOF. It improves performance for file-systems with slow
allocation.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-9-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
[mreitz: Two comment fixes, and bumped the version from 5.2 to 6.0]
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 docs/system/qemu-block-drivers.rst.inc |  26 ++
 qapi/block-core.json                   |  20 +-
 block/preallocate.c                    | 559 +++++++++++++++++++++++++
 block/meson.build                      |   1 +
 4 files changed, 605 insertions(+), 1 deletion(-)
 create mode 100644 block/preallocate.c

diff --git a/docs/system/qemu-block-drivers.rst.inc b/docs/system/qemu-block-drivers.rst.inc
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/qemu-block-drivers.rst.inc
+++ b/docs/system/qemu-block-drivers.rst.inc
@@ -XXX,XX +XXX,XX @@ on host and see if there are locks held by the QEMU process on the image file.
 More than one byte could be locked by the QEMU instance, each byte of which
 reflects a particular permission that is acquired or protected by the running
 block driver.
+
+Filter drivers
+~~~~~~~~~~~~~~
+
+QEMU supports several filter drivers, which don't store any data, but perform
+some additional tasks, hooking io requests.
+
+.. program:: filter-drivers
+.. option:: preallocate
+
+  The preallocate filter driver is intended to be inserted between format
+  and protocol nodes and preallocates some additional space
+  (expanding the protocol file) when writing past the file’s end. This can be
+  useful for file-systems with slow allocation.
+
+  Supported options:
+
+  .. program:: preallocate
+  .. option:: prealloc-align
+
+    On preallocation, align the file length to this value (in bytes), default 1M.
+
+  .. program:: preallocate
+  .. option:: prealloc-size
+
+    How much to preallocate (in bytes), default 128M.
diff --git a/qapi/block-core.json b/qapi/block-core.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -XXX,XX +XXX,XX @@
             'cloop', 'compress', 'copy-on-read', 'dmg', 'file', 'ftp', 'ftps',
             'gluster', 'host_cdrom', 'host_device', 'http', 'https', 'iscsi',
             'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
-            'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+            'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
             'sheepdog',
             'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
@@ -XXX,XX +XXX,XX @@
   'data': { 'aes': 'QCryptoBlockOptionsQCow',
             'luks': 'QCryptoBlockOptionsLUKS'} }
 
+##
+# @BlockdevOptionsPreallocate:
+#
+# Filter driver intended to be inserted between format and protocol node
+# and do preallocation in protocol node on write.
+#
+# @prealloc-align: on preallocation, align file length to this number,
+#                  default 1048576 (1M)
+#
+# @prealloc-size: how much to preallocate, default 134217728 (128M)
+#
+# Since: 6.0
+##
+{ 'struct': 'BlockdevOptionsPreallocate',
+  'base': 'BlockdevOptionsGenericFormat',
+  'data': { '*prealloc-align': 'int', '*prealloc-size': 'int' } }
+
 ##
 # @BlockdevOptionsQcow2:
 #
@@ -XXX,XX +XXX,XX @@
       'null-co':    'BlockdevOptionsNull',
       'nvme':       'BlockdevOptionsNVMe',
       'parallels':  'BlockdevOptionsGenericFormat',
+      'preallocate':'BlockdevOptionsPreallocate',
       'qcow2':      'BlockdevOptionsQcow2',
       'qcow':       'BlockdevOptionsQcow',
       'qed':        'BlockdevOptionsGenericCOWFormat',
diff --git a/block/preallocate.c b/block/preallocate.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/block/preallocate.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * preallocate filter driver
+ *
+ * The driver performs preallocate operation: it is injected above
+ * some node, and before each write over EOF it does additional preallocating
+ * write-zeroes request.
+ *
+ * Copyright (c) 2020 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 "qapi/error.h"
+#include "qemu/module.h"
+#include "qemu/option.h"
+#include "qemu/units.h"
+#include "block/block_int.h"
+
+
+typedef struct PreallocateOpts {
+    int64_t prealloc_size;
+    int64_t prealloc_align;
+} PreallocateOpts;
+
+typedef struct BDRVPreallocateState {
+    PreallocateOpts opts;
+
+    /*
+     * Track real data end, to crop preallocation on close. If < 0 the status is
+     * unknown.
+     *
+     * @data_end is a maximum of file size on open (or when we get write/resize
+     * permissions) and all write request ends after it. So it's safe to
+     * truncate to data_end if it is valid.
+     */
+    int64_t data_end;
+
+    /*
+     * Start of trailing preallocated area which reads as zero. May be smaller
+     * than data_end, if user does over-EOF write zero operation. If < 0 the
+     * status is unknown.
+     *
+     * If both @zero_start and @file_end are valid, the region
+     * [@zero_start, @file_end) is known to be preallocated zeroes. If @file_end
+     * is not valid, @zero_start doesn't make much sense.
+     */
+    int64_t zero_start;
+
+    /*
+     * Real end of file. Actually the cache for bdrv_getlength(bs->file->bs),
+     * to avoid extra lseek() calls on each write operation. If < 0 the status
+     * is unknown.
+     */
+    int64_t file_end;
+
+    /*
+     * All three states @data_end, @zero_start and @file_end are guaranteed to
+     * be invalid (< 0) when we don't have both exclusive BLK_PERM_RESIZE and
+     * BLK_PERM_WRITE permissions on file child.
+     */
+} BDRVPreallocateState;
+
+#define PREALLOCATE_OPT_PREALLOC_ALIGN "prealloc-align"
+#define PREALLOCATE_OPT_PREALLOC_SIZE "prealloc-size"
+static QemuOptsList runtime_opts = {
+    .name = "preallocate",
+    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+    .desc = {
+        {
+            .name = PREALLOCATE_OPT_PREALLOC_ALIGN,
+            .type = QEMU_OPT_SIZE,
+            .help = "on preallocation, align file length to this number, "
+                "default 1M",
+        },
+        {
+            .name = PREALLOCATE_OPT_PREALLOC_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "how much to preallocate, default 128M",
+        },
+        { /* end of list */ }
+    },
+};
+
+static bool preallocate_absorb_opts(PreallocateOpts *dest, QDict *options,
+                                    BlockDriverState *child_bs, Error **errp)
+{
+    QemuOpts *opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+
+    if (!qemu_opts_absorb_qdict(opts, options, errp)) {
+        return false;
+    }
+
+    dest->prealloc_align =
+        qemu_opt_get_size(opts, PREALLOCATE_OPT_PREALLOC_ALIGN, 1 * MiB);
+    dest->prealloc_size =
+        qemu_opt_get_size(opts, PREALLOCATE_OPT_PREALLOC_SIZE, 128 * MiB);
+
+    qemu_opts_del(opts);
+
+    if (!QEMU_IS_ALIGNED(dest->prealloc_align, BDRV_SECTOR_SIZE)) {
+        error_setg(errp, "prealloc-align parameter of preallocate filter "
+                   "is not aligned to %llu", BDRV_SECTOR_SIZE);
+        return false;
+    }
+
+    if (!QEMU_IS_ALIGNED(dest->prealloc_align,
+                         child_bs->bl.request_alignment)) {
+        error_setg(errp, "prealloc-align parameter of preallocate filter "
+                   "is not aligned to underlying node request alignment "
+                   "(%" PRIi32 ")", child_bs->bl.request_alignment);
+        return false;
+    }
+
+    return true;
+}
+
+static int preallocate_open(BlockDriverState *bs, QDict *options, int flags,
+                            Error **errp)
+{
+    BDRVPreallocateState *s = bs->opaque;
+
+    /*
+     * s->data_end and friends should be initialized on permission update.
+     * For this to work, mark them invalid.
+     */
+    s->file_end = s->zero_start = s->data_end = -EINVAL;
+
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
+                               BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
+                               false, errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
+    if (!preallocate_absorb_opts(&s->opts, options, bs->file->bs, errp)) {
+        return -EINVAL;
+    }
+
+    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
+        (BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
+
+    bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
+        ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) &
+            bs->file->bs->supported_zero_flags);
+
+    return 0;
+}
+
+static void preallocate_close(BlockDriverState *bs)
+{
+    int ret;
+    BDRVPreallocateState *s = bs->opaque;
+
+    if (s->data_end < 0) {
+        return;
+    }
+
+    if (s->file_end < 0) {
+        s->file_end = bdrv_getlength(bs->file->bs);
+        if (s->file_end < 0) {
+            return;
+        }
+    }
+
+    if (s->data_end < s->file_end) {
+        ret = bdrv_truncate(bs->file, s->data_end, true, PREALLOC_MODE_OFF, 0,
+                            NULL);
+        s->file_end = ret < 0 ? ret : s->data_end;
+    }
+}
+
+
+/*
+ * Handle reopen.
+ *
+ * We must implement reopen handlers, otherwise reopen just don't work. Handle
+ * new options and don't care about preallocation state, as it is handled in
+ * set/check permission handlers.
+ */
+
+static int preallocate_reopen_prepare(BDRVReopenState *reopen_state,
+                                      BlockReopenQueue *queue, Error **errp)
+{
+    PreallocateOpts *opts = g_new0(PreallocateOpts, 1);
+
+    if (!preallocate_absorb_opts(opts, reopen_state->options,
+                                 reopen_state->bs->file->bs, errp)) {
+        g_free(opts);
+        return -EINVAL;
+    }
+
+    reopen_state->opaque = opts;
+
+    return 0;
+}
+
+static void preallocate_reopen_commit(BDRVReopenState *state)
+{
+    BDRVPreallocateState *s = state->bs->opaque;
+
+    s->opts = *(PreallocateOpts *)state->opaque;
+
+    g_free(state->opaque);
+    state->opaque = NULL;
+}
+
+static void preallocate_reopen_abort(BDRVReopenState *state)
+{
+    g_free(state->opaque);
+    state->opaque = NULL;
+}
+
+static coroutine_fn int preallocate_co_preadv_part(
+        BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+        QEMUIOVector *qiov, size_t qiov_offset, int flags)
+{
+    return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset,
+                               flags);
+}
+
+static int coroutine_fn preallocate_co_pdiscard(BlockDriverState *bs,
+                                               int64_t offset, int bytes)
+{
+    return bdrv_co_pdiscard(bs->file, offset, bytes);
+}
+
+static bool can_write_resize(uint64_t perm)
+{
+    return (perm & BLK_PERM_WRITE) && (perm & BLK_PERM_RESIZE);
+}
+
+static bool has_prealloc_perms(BlockDriverState *bs)
+{
+    BDRVPreallocateState *s = bs->opaque;
+
+    if (can_write_resize(bs->file->perm)) {
+        assert(!(bs->file->shared_perm & BLK_PERM_WRITE));
+        assert(!(bs->file->shared_perm & BLK_PERM_RESIZE));
+        return true;
+    }
+
+    assert(s->data_end < 0);
+    assert(s->zero_start < 0);
+    assert(s->file_end < 0);
+    return false;
+}
+
+/*
+ * Call on each write. Returns true if @want_merge_zero is true and the region
+ * [offset, offset + bytes) is zeroed (as a result of this call or earlier
+ * preallocation).
+ *
+ * want_merge_zero is used to merge write-zero request with preallocation in
+ * one bdrv_co_pwrite_zeroes() call.
+ */
+static bool coroutine_fn handle_write(BlockDriverState *bs, int64_t offset,
+                                      int64_t bytes, bool want_merge_zero)
+{
+    BDRVPreallocateState *s = bs->opaque;
+    int64_t end = offset + bytes;
+    int64_t prealloc_start, prealloc_end;
+    int ret;
+
+    if (!has_prealloc_perms(bs)) {
+        /* We don't have state neither should try to recover it */
+        return false;
+    }
+
+    if (s->data_end < 0) {
+        s->data_end = bdrv_getlength(bs->file->bs);
+        if (s->data_end < 0) {
+            return false;
+        }
+
+        if (s->file_end < 0) {
+            s->file_end = s->data_end;
+        }
+    }
+
+    if (end <= s->data_end) {
+        return false;
+    }
+
+    /* We have valid s->data_end, and request writes beyond it. */
+
+    s->data_end = end;
+    if (s->zero_start < 0 || !want_merge_zero) {
+        s->zero_start = end;
+    }
+
+    if (s->file_end < 0) {
+        s->file_end = bdrv_getlength(bs->file->bs);
+        if (s->file_end < 0) {
+            return false;
+        }
+    }
+
+    /* Now s->data_end, s->zero_start and s->file_end are valid. */
+
+    if (end <= s->file_end) {
+        /* No preallocation needed. */
+        return want_merge_zero && offset >= s->zero_start;
+    }
+
+    /* Now we want new preallocation, as request writes beyond s->file_end. */
+
+    prealloc_start = want_merge_zero ? MIN(offset, s->file_end) : s->file_end;
+    prealloc_end = QEMU_ALIGN_UP(end + s->opts.prealloc_size,
+                                 s->opts.prealloc_align);
+
+    ret = bdrv_co_pwrite_zeroes(
+            bs->file, prealloc_start, prealloc_end - prealloc_start,
+            BDRV_REQ_NO_FALLBACK | BDRV_REQ_SERIALISING | BDRV_REQ_NO_WAIT);
+    if (ret < 0) {
+        s->file_end = ret;
+        return false;
+    }
+
+    s->file_end = prealloc_end;
+    return want_merge_zero;
+}
+
+static int coroutine_fn preallocate_co_pwrite_zeroes(BlockDriverState *bs,
+        int64_t offset, int bytes, BdrvRequestFlags flags)
+{
+    bool want_merge_zero =
+        !(flags & ~(BDRV_REQ_ZERO_WRITE | BDRV_REQ_NO_FALLBACK));
+    if (handle_write(bs, offset, bytes, want_merge_zero)) {
+        return 0;
+    }
+
+    return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
+}
+
+static coroutine_fn int preallocate_co_pwritev_part(BlockDriverState *bs,
+                                                    uint64_t offset,
+                                                    uint64_t bytes,
+                                                    QEMUIOVector *qiov,
+                                                    size_t qiov_offset,
+                                                    int flags)
+{
+    handle_write(bs, offset, bytes, false);
+
+    return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset,
+                                flags);
+}
+
+static int coroutine_fn
+preallocate_co_truncate(BlockDriverState *bs, int64_t offset,
+                        bool exact, PreallocMode prealloc,
+                        BdrvRequestFlags flags, Error **errp)
+{
+    ERRP_GUARD();
+    BDRVPreallocateState *s = bs->opaque;
+    int ret;
+
+    if (s->data_end >= 0 && offset > s->data_end) {
+        if (s->file_end < 0) {
+            s->file_end = bdrv_getlength(bs->file->bs);
+            if (s->file_end < 0) {
+                error_setg(errp, "failed to get file length");
+                return s->file_end;
+            }
+        }
+
+        if (prealloc == PREALLOC_MODE_FALLOC) {
+            /*
+             * If offset <= s->file_end, the task is already done, just
+             * update s->data_end, to move part of "filter preallocation"
+             * to "preallocation requested by user".
+             * Otherwise just proceed to preallocate missing part.
+             */
+            if (offset <= s->file_end) {
+                s->data_end = offset;
+                return 0;
+            }
+        } else {
+            /*
+             * We have to drop our preallocation, to
+             * - avoid "Cannot use preallocation for shrinking files" in
+             *   case of offset < file_end
+             * - give PREALLOC_MODE_OFF a chance to keep small disk
+             *   usage
+             * - give PREALLOC_MODE_FULL a chance to actually write the
+             *   whole region as user expects
+             */
+            if (s->file_end > s->data_end) {
+                ret = bdrv_co_truncate(bs->file, s->data_end, true,
+                                       PREALLOC_MODE_OFF, 0, errp);
+                if (ret < 0) {
+                    s->file_end = ret;
+                    error_prepend(errp, "preallocate-filter: failed to drop "
+                                  "write-zero preallocation: ");
+                    return ret;
+                }
+                s->file_end = s->data_end;
+            }
+        }
+
+        s->data_end = offset;
+    }
+
+    ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp);
+    if (ret < 0) {
+        s->file_end = s->zero_start = s->data_end = ret;
+        return ret;
+    }
+
+    if (has_prealloc_perms(bs)) {
+        s->file_end = s->zero_start = s->data_end = offset;
+    }
+    return 0;
+}
+
+static int coroutine_fn preallocate_co_flush(BlockDriverState *bs)
+{
+    return bdrv_co_flush(bs->file->bs);
+}
+
+static int64_t preallocate_getlength(BlockDriverState *bs)
+{
+    int64_t ret;
+    BDRVPreallocateState *s = bs->opaque;
+
+    if (s->data_end >= 0) {
+        return s->data_end;
+    }
+
+    ret = bdrv_getlength(bs->file->bs);
+
+    if (has_prealloc_perms(bs)) {
+        s->file_end = s->zero_start = s->data_end = ret;
+    }
+
+    return ret;
+}
+
+static int preallocate_check_perm(BlockDriverState *bs,
+                                  uint64_t perm, uint64_t shared, Error **errp)
+{
+    BDRVPreallocateState *s = bs->opaque;
+
+    if (s->data_end >= 0 && !can_write_resize(perm)) {
+        /*
+         * Lose permissions.
+         * We should truncate in check_perm, as in set_perm bs->file->perm will
+         * be already changed, and we should not violate it.
+         */
+        if (s->file_end < 0) {
+            s->file_end = bdrv_getlength(bs->file->bs);
+            if (s->file_end < 0) {
+                error_setg(errp, "Failed to get file length");
+                return s->file_end;
+            }
+        }
+
+        if (s->data_end < s->file_end) {
+            int ret = bdrv_truncate(bs->file, s->data_end, true,
+                                    PREALLOC_MODE_OFF, 0, NULL);
+            if (ret < 0) {
+                error_setg(errp, "Failed to drop preallocation");
+                s->file_end = ret;
+                return ret;
+            }
+            s->file_end = s->data_end;
+        }
+    }
+
+    return 0;
+}
+
+static void preallocate_set_perm(BlockDriverState *bs,
+                                 uint64_t perm, uint64_t shared)
+{
+    BDRVPreallocateState *s = bs->opaque;
+
+    if (can_write_resize(perm)) {
+        if (s->data_end < 0) {
+            s->data_end = s->file_end = s->zero_start =
+                bdrv_getlength(bs->file->bs);
+        }
+    } else {
+        /*
+         * We drop our permissions, as well as allow shared
+         * permissions (see preallocate_child_perm), anyone will be able to
+         * change the child, so mark all states invalid. We'll regain control if
+         * get good permissions back.
+         */
+        s->data_end = s->file_end = s->zero_start = -EINVAL;
+    }
+}
+
+static void preallocate_child_perm(BlockDriverState *bs, BdrvChild *c,
+    BdrvChildRole role, BlockReopenQueue *reopen_queue,
+    uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared)
+{
+    bdrv_default_perms(bs, c, role, reopen_queue, perm, shared, nperm, nshared);
+
+    if (can_write_resize(perm)) {
+        /* This should come by default, but let's enforce: */
+        *nperm |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
+
+        /*
+         * Don't share, to keep our states s->file_end, s->data_end and
+         * s->zero_start valid.
+         */
+        *nshared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
+    }
+}
+
+BlockDriver bdrv_preallocate_filter = {
+    .format_name = "preallocate",
+    .instance_size = sizeof(BDRVPreallocateState),
+
+    .bdrv_getlength = preallocate_getlength,
+    .bdrv_open = preallocate_open,
+    .bdrv_close = preallocate_close,
+
+    .bdrv_reopen_prepare  = preallocate_reopen_prepare,
+    .bdrv_reopen_commit   = preallocate_reopen_commit,
+    .bdrv_reopen_abort    = preallocate_reopen_abort,
+
+    .bdrv_co_preadv_part = preallocate_co_preadv_part,
+    .bdrv_co_pwritev_part = preallocate_co_pwritev_part,
+    .bdrv_co_pwrite_zeroes = preallocate_co_pwrite_zeroes,
+    .bdrv_co_pdiscard = preallocate_co_pdiscard,
+    .bdrv_co_flush = preallocate_co_flush,
+    .bdrv_co_truncate = preallocate_co_truncate,
+
+    .bdrv_check_perm = preallocate_check_perm,
+    .bdrv_set_perm = preallocate_set_perm,
+    .bdrv_child_perm = preallocate_child_perm,
+
+    .has_variable_length = true,
+    .is_filter = true,
+};
+
+static void bdrv_preallocate_init(void)
+{
+    bdrv_register(&bdrv_preallocate_filter);
+}
+
+block_init(bdrv_preallocate_init);
diff --git a/block/meson.build b/block/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/block/meson.build
+++ b/block/meson.build
@@ -XXX,XX +XXX,XX @@ block_ss.add(files(
   'block-copy.c',
   'commit.c',
   'copy-on-read.c',
+  'preallocate.c',
   'create.c',
   'crypto.c',
   'dirty-bitmap.c',
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

This will be used in further test.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20201021145859.11201-10-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 qemu-io-cmds.c | 46 ++++++++++++++++++++++++++++++++--------------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index XXXXXXX..XXXXXXX 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -XXX,XX +XXX,XX @@ static const cmdinfo_t flush_cmd = {
     .oneline    = "flush all in-core file state to disk",
 };
 
+static int truncate_f(BlockBackend *blk, int argc, char **argv);
+static const cmdinfo_t truncate_cmd = {
+    .name       = "truncate",
+    .altname    = "t",
+    .cfunc      = truncate_f,
+    .perm       = BLK_PERM_WRITE | BLK_PERM_RESIZE,
+    .argmin     = 1,
+    .argmax     = 3,
+    .args       = "[-m prealloc_mode] off",
+    .oneline    = "truncates the current file at the given offset",
+};
+
 static int truncate_f(BlockBackend *blk, int argc, char **argv)
 {
     Error *local_err = NULL;
     int64_t offset;
-    int ret;
+    int c, ret;
+    PreallocMode prealloc = PREALLOC_MODE_OFF;
 
-    offset = cvtnum(argv[1]);
+    while ((c = getopt(argc, argv, "m:")) != -1) {
+        switch (c) {
+        case 'm':
+            prealloc = qapi_enum_parse(&PreallocMode_lookup, optarg,
+                                       PREALLOC_MODE__MAX, NULL);
+            if (prealloc == PREALLOC_MODE__MAX) {
+                error_report("Invalid preallocation mode '%s'", optarg);
+                return -EINVAL;
+            }
+            break;
+        default:
+            qemuio_command_usage(&truncate_cmd);
+            return -EINVAL;
+        }
+    }
+
+    offset = cvtnum(argv[optind]);
     if (offset < 0) {
         print_cvtnum_err(offset, argv[1]);
         return offset;
@@ -XXX,XX +XXX,XX @@ static int truncate_f(BlockBackend *blk, int argc, char **argv)
      * exact=true.  It is better to err on the "emit more errors" side
      * than to be overly permissive.
      */
-    ret = blk_truncate(blk, offset, false, PREALLOC_MODE_OFF, 0, &local_err);
+    ret = blk_truncate(blk, offset, false, prealloc, 0, &local_err);
     if (ret < 0) {
         error_report_err(local_err);
         return ret;
@@ -XXX,XX +XXX,XX @@ static int truncate_f(BlockBackend *blk, int argc, char **argv)
     return 0;
 }
 
-static const cmdinfo_t truncate_cmd = {
-    .name       = "truncate",
-    .altname    = "t",
-    .cfunc      = truncate_f,
-    .perm       = BLK_PERM_WRITE | BLK_PERM_RESIZE,
-    .argmin     = 1,
-    .argmax     = 1,
-    .args       = "off",
-    .oneline    = "truncates the current file at the given offset",
-};
-
 static int length_f(BlockBackend *blk, int argc, char **argv)
 {
     int64_t size;
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20201021145859.11201-11-vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/iotests.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -XXX,XX +XXX,XX @@ def qemu_io_log(*args):
 
 def qemu_io_silent(*args):
     '''Run qemu-io and return the exit code, suppressing stdout'''
-    args = qemu_io_args + list(args)
+    if '-f' in args or '--image-opts' in args:
+        default_args = qemu_io_args_no_fmt
+    else:
+        default_args = qemu_io_args
+
+    args = default_args + list(args)
     exitcode = subprocess.call(args, stdout=open('/dev/null', 'w'))
     if exitcode < 0:
         sys.stderr.write('qemu-io received signal %i: %s\n' %
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Add a parameter to skip test if some needed additional formats are not
supported (for example filter drivers).

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-12-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/iotests.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -XXX,XX +XXX,XX @@ def _verify_aio_mode(supported_aio_modes: Sequence[str] = ()) -> None:
     if supported_aio_modes and (aiomode not in supported_aio_modes):
         notrun('not suitable for this aio mode: %s' % aiomode)
 
+def _verify_formats(required_formats: Sequence[str] = ()) -> None:
+    usf_list = list(set(required_formats) - set(supported_formats()))
+    if usf_list:
+        notrun(f'formats {usf_list} are not whitelisted')
+
 def supports_quorum():
     return 'quorum' in qemu_img_pipe('--help')
 
@@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (),
                          supported_aio_modes: Sequence[str] = (),
                          unsupported_fmts: Sequence[str] = (),
                          supported_protocols: Sequence[str] = (),
-                         unsupported_protocols: Sequence[str] = ()) -> bool:
+                         unsupported_protocols: Sequence[str] = (),
+                         required_fmts: Sequence[str] = ()) -> bool:
     """
     Perform necessary setup for either script-style or unittest-style tests.
 
@@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (),
     _verify_platform(supported=supported_platforms)
     _verify_cache_mode(supported_cache_modes)
     _verify_aio_mode(supported_aio_modes)
+    _verify_formats(required_fmts)
 
     return debug
 
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-13-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/298     | 186 +++++++++++++++++++++++++++++++++++++
 tests/qemu-iotests/298.out |   5 +
 tests/qemu-iotests/group   |   1 +
 3 files changed, 192 insertions(+)
 create mode 100644 tests/qemu-iotests/298
 create mode 100644 tests/qemu-iotests/298.out

diff --git a/tests/qemu-iotests/298 b/tests/qemu-iotests/298
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/298
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Test for preallocate filter
+#
+# Copyright (c) 2020 Virtuozzo International GmbH.
+#
+# 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/>.
+#
+
+import os
+import iotests
+
+MiB = 1024 * 1024
+disk = os.path.join(iotests.test_dir, 'disk')
+overlay = os.path.join(iotests.test_dir, 'overlay')
+refdisk = os.path.join(iotests.test_dir, 'refdisk')
+drive_opts = f'node-name=disk,driver={iotests.imgfmt},' \
+    f'file.node-name=filter,file.driver=preallocate,' \
+    f'file.file.node-name=file,file.file.filename={disk}'
+
+
+class TestPreallocateBase(iotests.QMPTestCase):
+    def setUp(self):
+        iotests.qemu_img_create('-f', iotests.imgfmt, disk, str(10 * MiB))
+
+    def tearDown(self):
+        try:
+            self.check_small()
+            check = iotests.qemu_img_check(disk)
+            self.assertFalse('leaks' in check)
+            self.assertFalse('corruptions' in check)
+            self.assertEqual(check['check-errors'], 0)
+        finally:
+            os.remove(disk)
+
+    def check_big(self):
+        self.assertTrue(os.path.getsize(disk) > 100 * MiB)
+
+    def check_small(self):
+        self.assertTrue(os.path.getsize(disk) < 10 * MiB)
+
+
+class TestQemuImg(TestPreallocateBase):
+    def test_qemu_img(self):
+        p = iotests.QemuIoInteractive('--image-opts', drive_opts)
+
+        p.cmd('write 0 1M')
+        p.cmd('flush')
+
+        self.check_big()
+
+        p.close()
+
+
+class TestPreallocateFilter(TestPreallocateBase):
+    def setUp(self):
+        super().setUp()
+        self.vm = iotests.VM().add_drive(path=None, opts=drive_opts)
+        self.vm.launch()
+
+    def tearDown(self):
+        self.vm.shutdown()
+        super().tearDown()
+
+    def test_prealloc(self):
+        self.vm.hmp_qemu_io('drive0', 'write 0 1M')
+        self.check_big()
+
+    def test_external_snapshot(self):
+        self.test_prealloc()
+
+        result = self.vm.qmp('blockdev-snapshot-sync', node_name='disk',
+                             snapshot_file=overlay,
+                             snapshot_node_name='overlay')
+        self.assert_qmp(result, 'return', {})
+
+        # on reopen to  r-o base preallocation should be dropped
+        self.check_small()
+
+        self.vm.hmp_qemu_io('drive0', 'write 1M 1M')
+
+        result = self.vm.qmp('block-commit', device='overlay')
+        self.assert_qmp(result, 'return', {})
+        self.complete_and_wait()
+
+        # commit of new megabyte should trigger preallocation
+        self.check_big()
+
+    def test_reopen_opts(self):
+        result = self.vm.qmp('x-blockdev-reopen', **{
+            'node-name': 'disk',
+            'driver': iotests.imgfmt,
+            'file': {
+                'node-name': 'filter',
+                'driver': 'preallocate',
+                'prealloc-size': 20 * MiB,
+                'prealloc-align': 5 * MiB,
+                'file': {
+                    'node-name': 'file',
+                    'driver': 'file',
+                    'filename': disk
+                }
+            }
+        })
+        self.assert_qmp(result, 'return', {})
+
+        self.vm.hmp_qemu_io('drive0', 'write 0 1M')
+        self.assertTrue(os.path.getsize(disk) == 25 * MiB)
+
+
+class TestTruncate(iotests.QMPTestCase):
+    def setUp(self):
+        iotests.qemu_img_create('-f', iotests.imgfmt, disk, str(10 * MiB))
+        iotests.qemu_img_create('-f', iotests.imgfmt, refdisk, str(10 * MiB))
+
+    def tearDown(self):
+        os.remove(disk)
+        os.remove(refdisk)
+
+    def do_test(self, prealloc_mode, new_size):
+        ret = iotests.qemu_io_silent('--image-opts', '-c', 'write 0 10M', '-c',
+                                     f'truncate -m {prealloc_mode} {new_size}',
+                                     drive_opts)
+        self.assertEqual(ret, 0)
+
+        ret = iotests.qemu_io_silent('-f', iotests.imgfmt, '-c', 'write 0 10M',
+                                     '-c',
+                                     f'truncate -m {prealloc_mode} {new_size}',
+                                     refdisk)
+        self.assertEqual(ret, 0)
+
+        stat = os.stat(disk)
+        refstat = os.stat(refdisk)
+
+        # Probably we'll want preallocate filter to keep align to cluster when
+        # shrink preallocation, so, ignore small differece
+        self.assertLess(abs(stat.st_size - refstat.st_size), 64 * 1024)
+
+        # Preallocate filter may leak some internal clusters (for example, if
+        # guest write far over EOF, skipping some clusters - they will remain
+        # fallocated, preallocate filter don't care about such leaks, it drops
+        # only trailing preallocation.
+        self.assertLess(abs(stat.st_blocks - refstat.st_blocks) * 512,
+                        1024 * 1024)
+
+    def test_real_shrink(self):
+        self.do_test('off', '5M')
+
+    def test_truncate_inside_preallocated_area__falloc(self):
+        self.do_test('falloc', '50M')
+
+    def test_truncate_inside_preallocated_area__metadata(self):
+        self.do_test('metadata', '50M')
+
+    def test_truncate_inside_preallocated_area__full(self):
+        self.do_test('full', '50M')
+
+    def test_truncate_inside_preallocated_area__off(self):
+        self.do_test('off', '50M')
+
+    def test_truncate_over_preallocated_area__falloc(self):
+        self.do_test('falloc', '150M')
+
+    def test_truncate_over_preallocated_area__metadata(self):
+        self.do_test('metadata', '150M')
+
+    def test_truncate_over_preallocated_area__full(self):
+        self.do_test('full', '150M')
+
+    def test_truncate_over_preallocated_area__off(self):
+        self.do_test('off', '150M')
+
+
+if __name__ == '__main__':
+    iotests.main(supported_fmts=['qcow2'], required_fmts=['preallocate'])
diff --git a/tests/qemu-iotests/298.out b/tests/qemu-iotests/298.out
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/298.out
@@ -XXX,XX +XXX,XX @@
+.............
+----------------------------------------------------------------------
+Ran 13 tests
+
+OK
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -XXX,XX +XXX,XX @@
 295 rw
 296 rw
 297 meta
+298
 299 auto quick
 300 migration
 301 backing quick
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-14-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/simplebench.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Support benchmarks returning not seconds but iops. We'll use it for
further new test.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-15-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/simplebench.py | 38 ++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py
index XXXXXXX..XXXXXXX 100644
--- a/scripts/simplebench/simplebench.py
+++ b/scripts/simplebench/simplebench.py
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
 
     test_func   -- benchmarking function with prototype
                    test_func(env, case), which takes test_env and test_case
-                   arguments and returns {'seconds': int} (which is benchmark
-                   result) on success and {'error': str} on error. Returned
-                   dict may contain any other additional fields.
+                   arguments and on success returns dict with 'seconds' or
+                   'iops' (or both) fields, specifying the benchmark result.
+                   If both 'iops' and 'seconds' provided, the 'iops' is
+                   considered the main, and 'seconds' is just an additional
+                   info. On failure test_func should return {'error': str}.
+                   Returned dict may contain any other additional fields.
     test_env    -- test environment - opaque first argument for test_func
     test_case   -- test case - opaque second argument for test_func
     count       -- how many times to call test_func, to calculate average
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
 
     Returns dict with the following fields:
         'runs':     list of test_func results
-        'average':  average seconds per run (exists only if at least one run
-                    succeeded)
+        'dimension': dimension of results, may be 'seconds' or 'iops'
+        'average':  average value (iops or seconds) per run (exists only if at
+                    least one run succeeded)
         'delta':    maximum delta between test_func result and the average
                     (exists only if at least one run succeeded)
         'n-failed': number of failed runs (exists only if at least one run
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
 
     result = {'runs': runs}
 
-    succeeded = [r for r in runs if ('seconds' in r)]
+    succeeded = [r for r in runs if ('seconds' in r or 'iops' in r)]
     if succeeded:
-        avg = sum(r['seconds'] for r in succeeded) / len(succeeded)
+        if 'iops' in succeeded[0]:
+            assert all('iops' in r for r in succeeded)
+            dim = 'iops'
+        else:
+            assert all('seconds' in r for r in succeeded)
+            assert all('iops' not in r for r in succeeded)
+            dim = 'seconds'
+        avg = sum(r[dim] for r in succeeded) / len(succeeded)
+        result['dimension'] = dim
         result['average'] = avg
-        result['delta'] = max(abs(r['seconds'] - avg) for r in succeeded)
+        result['delta'] = max(abs(r[dim] - avg) for r in succeeded)
 
     if len(succeeded) < count:
         result['n-failed'] = count - len(succeeded)
@@ -XXX,XX +XXX,XX @@ def ascii(results):
     """Return ASCII representation of bench() returned dict."""
     from tabulate import tabulate
 
+    dim = None
     tab = [[""] + [c['id'] for c in results['envs']]]
     for case in results['cases']:
         row = [case['id']]
         for env in results['envs']:
-            row.append(ascii_one(results['tab'][case['id']][env['id']]))
+            res = results['tab'][case['id']][env['id']]
+            if dim is None:
+                dim = res['dimension']
+            else:
+                assert dim == res['dimension']
+            row.append(ascii_one(res))
         tab.append(row)
 
-    return tabulate(tab)
+    return f'All results are in {dim}\n\n' + tabulate(tab)
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Standard deviation is more usual to see after +- than current maximum
of deviations.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-16-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/simplebench.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py
index XXXXXXX..XXXXXXX 100644
--- a/scripts/simplebench/simplebench.py
+++ b/scripts/simplebench/simplebench.py
@@ -XXX,XX +XXX,XX @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 
+import statistics
+
 
 def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
     """Benchmark one test-case
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
         'dimension': dimension of results, may be 'seconds' or 'iops'
         'average':  average value (iops or seconds) per run (exists only if at
                     least one run succeeded)
-        'delta':    maximum delta between test_func result and the average
+        'stdev':    standard deviation of results
                     (exists only if at least one run succeeded)
         'n-failed': number of failed runs (exists only if at least one run
                     failed)
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
             assert all('seconds' in r for r in succeeded)
             assert all('iops' not in r for r in succeeded)
             dim = 'seconds'
-        avg = sum(r[dim] for r in succeeded) / len(succeeded)
         result['dimension'] = dim
-        result['average'] = avg
-        result['delta'] = max(abs(r[dim] - avg) for r in succeeded)
+        result['average'] = statistics.mean(r[dim] for r in succeeded)
+        result['stdev'] = statistics.stdev(r[dim] for r in succeeded)
 
     if len(succeeded) < count:
         result['n-failed'] = count - len(succeeded)
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
 def ascii_one(result):
     """Return ASCII representation of bench_one() returned dict."""
     if 'average' in result:
-        s = '{:.2f} +- {:.2f}'.format(result['average'], result['delta'])
+        s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev'])
         if 'n-failed' in result:
             s += '\n({} failed)'.format(result['n-failed'])
         return s
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Next patch will use utf8 plus-minus symbol, let's use more generic (and
more readable) name.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-17-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/bench-example.py   |  2 +-
 scripts/simplebench/bench_write_req.py |  2 +-
 scripts/simplebench/simplebench.py     | 10 +++++-----
 3 files changed, 7 insertions(+), 7 deletions(-)

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Let's keep view part in separate: this way it's better to improve it in
the following commits.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-18-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/bench-example.py   |  3 +-
 scripts/simplebench/bench_write_req.py |  3 +-
 scripts/simplebench/results_to_text.py | 48 ++++++++++++++++++++++++++
 scripts/simplebench/simplebench.py     | 31 -----------------
 4 files changed, 52 insertions(+), 33 deletions(-)
 create mode 100644 scripts/simplebench/results_to_text.py

diff --git a/scripts/simplebench/bench-example.py b/scripts/simplebench/bench-example.py
index XXXXXXX..XXXXXXX 100644
--- a/scripts/simplebench/bench-example.py
+++ b/scripts/simplebench/bench-example.py
@@ -XXX,XX +XXX,XX @@
 #
 
 import simplebench
+from results_to_text import results_to_text
 from bench_block_job import bench_block_copy, drv_file, drv_nbd
 
 
@@ -XXX,XX +XXX,XX @@ test_envs = [
 ]
 
 result = simplebench.bench(bench_func, test_envs, test_cases, count=3)
-print(simplebench.results_to_text(result))
+print(results_to_text(result))
diff --git a/scripts/simplebench/bench_write_req.py b/scripts/simplebench/bench_write_req.py
index XXXXXXX..XXXXXXX 100755
--- a/scripts/simplebench/bench_write_req.py
+++ b/scripts/simplebench/bench_write_req.py
@@ -XXX,XX +XXX,XX @@ import sys
 import os
 import subprocess
 import simplebench
+from results_to_text import results_to_text
 
 
 def bench_func(env, case):
@@ -XXX,XX +XXX,XX @@ if __name__ == '__main__':
 
     result = simplebench.bench(bench_func, test_envs, test_cases, count=3,
                                initial_run=False)
-    print(simplebench.results_to_text(result))
+    print(results_to_text(result))
diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/scripts/simplebench/results_to_text.py
@@ -XXX,XX +XXX,XX @@
+# Simple benchmarking framework
+#
+# Copyright (c) 2019 Virtuozzo International GmbH.
+#
+# 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/>.
+#
+
+
+def result_to_text(result):
+    """Return text representation of bench_one() returned dict."""
+    if 'average' in result:
+        s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev'])
+        if 'n-failed' in result:
+            s += '\n({} failed)'.format(result['n-failed'])
+        return s
+    else:
+        return 'FAILED'
+
+
+def results_to_text(results):
+    """Return text representation of bench() returned dict."""
+    from tabulate import tabulate
+
+    dim = None
+    tab = [[""] + [c['id'] for c in results['envs']]]
+    for case in results['cases']:
+        row = [case['id']]
+        for env in results['envs']:
+            res = results['tab'][case['id']][env['id']]
+            if dim is None:
+                dim = res['dimension']
+            else:
+                assert dim == res['dimension']
+            row.append(result_to_text(res))
+        tab.append(row)
+
+    return f'All results are in {dim}\n\n' + tabulate(tab)
diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py
index XXXXXXX..XXXXXXX 100644
--- a/scripts/simplebench/simplebench.py
+++ b/scripts/simplebench/simplebench.py
@@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True):
     return result
 
 
-def result_to_text(result):
-    """Return text representation of bench_one() returned dict."""
-    if 'average' in result:
-        s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev'])
-        if 'n-failed' in result:
-            s += '\n({} failed)'.format(result['n-failed'])
-        return s
-    else:
-        return 'FAILED'
-
-
 def bench(test_func, test_envs, test_cases, *args, **vargs):
     """Fill benchmark table
 
@@ -XXX,XX +XXX,XX @@ def bench(test_func, test_envs, test_cases, *args, **vargs):
 
     print('Done')
     return results
-
-
-def results_to_text(results):
-    """Return text representation of bench() returned dict."""
-    from tabulate import tabulate
-
-    dim = None
-    tab = [[""] + [c['id'] for c in results['envs']]]
-    for case in results['cases']:
-        row = [case['id']]
-        for env in results['envs']:
-            res = results['tab'][case['id']][env['id']]
-            if dim is None:
-                dim = res['dimension']
-            else:
-                assert dim == res['dimension']
-            row.append(result_to_text(res))
-        tab.append(row)
-
-    return f'All results are in {dim}\n\n' + tabulate(tab)
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Move to generic format for floats and percentage for error.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-19-vsementsov@virtuozzo.com>
Acked-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/results_to_text.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Performance improvements / degradations are usually discussed in
percentage. Let's make the script calculate it for us.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-20-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
[mreitz: 'seconds' instead of 'secs']
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/results_to_text.py | 67 +++++++++++++++++++++++---
 1 file changed, 60 insertions(+), 7 deletions(-)

diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py
index XXXXXXX..XXXXXXX 100644
--- a/scripts/simplebench/results_to_text.py
+++ b/scripts/simplebench/results_to_text.py
@@ -XXX,XX +XXX,XX @@
 #
 
 import math
+import tabulate
+
+# We want leading whitespace for difference row cells (see below)
+tabulate.PRESERVE_WHITESPACE = True
 
 
 def format_value(x, stdev):
@@ -XXX,XX +XXX,XX @@ def result_to_text(result):
         return 'FAILED'
 
 
-def results_to_text(results):
-    """Return text representation of bench() returned dict."""
-    from tabulate import tabulate
-
+def results_dimension(results):
     dim = None
-    tab = [[""] + [c['id'] for c in results['envs']]]
     for case in results['cases']:
-        row = [case['id']]
         for env in results['envs']:
             res = results['tab'][case['id']][env['id']]
             if dim is None:
                 dim = res['dimension']
             else:
                 assert dim == res['dimension']
+
+    assert dim in ('iops', 'seconds')
+
+    return dim
+
+
+def results_to_text(results):
+    """Return text representation of bench() returned dict."""
+    n_columns = len(results['envs'])
+    named_columns = n_columns > 2
+    dim = results_dimension(results)
+    tab = []
+
+    if named_columns:
+        # Environment columns are named A, B, ...
+        tab.append([''] + [chr(ord('A') + i) for i in range(n_columns)])
+
+    tab.append([''] + [c['id'] for c in results['envs']])
+
+    for case in results['cases']:
+        row = [case['id']]
+        case_results = results['tab'][case['id']]
+        for env in results['envs']:
+            res = case_results[env['id']]
             row.append(result_to_text(res))
         tab.append(row)
 
-    return f'All results are in {dim}\n\n' + tabulate(tab)
+        # Add row of difference between columns. For each column starting from
+        # B we calculate difference with all previous columns.
+        row = ['', '']  # case name and first column
+        for i in range(1, n_columns):
+            cell = ''
+            env = results['envs'][i]
+            res = case_results[env['id']]
+
+            if 'average' not in res:
+                # Failed result
+                row.append(cell)
+                continue
+
+            for j in range(0, i):
+                env_j = results['envs'][j]
+                res_j = case_results[env_j['id']]
+                cell += ' '
+
+                if 'average' not in res_j:
+                    # Failed result
+                    cell += '--'
+                    continue
+
+                col_j = tab[0][j + 1] if named_columns else ''
+                diff_pr = round((res['average'] - res_j['average']) /
+                                res_j['average'] * 100)
+                cell += f' {col_j}{diff_pr:+}%'
+            row.append(cell)
+        tab.append(row)
+
+    return f'All results are in {dim}\n\n' + tabulate.tabulate(tab)
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Make results_to_text a tool to dump results saved in JSON file.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-21-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/results_to_text.py | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
 mode change 100644 => 100755 scripts/simplebench/results_to_text.py

diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py
old mode 100644
new mode 100755
index XXXXXXX..XXXXXXX
--- a/scripts/simplebench/results_to_text.py
+++ b/scripts/simplebench/results_to_text.py
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
 # Simple benchmarking framework
 #
 # Copyright (c) 2019 Virtuozzo International GmbH.
@@ -XXX,XX +XXX,XX @@ def results_to_text(results):
         tab.append(row)
 
     return f'All results are in {dim}\n\n' + tabulate.tabulate(tab)
+
+
+if __name__ == '__main__':
+    import sys
+    import json
+
+    if len(sys.argv) < 2:
+        print(f'USAGE: {sys.argv[0]} results.json')
+        exit(1)
+
+    with open(sys.argv[1]) as f:
+        print(results_to_text(json.load(f)))
-- 
2.29.2

From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Benchmark for new preallocate filter.

Example usage:
    ./bench_prealloc.py ../../build/qemu-img \
        ssd-ext4:/path/to/mount/point \
        ssd-xfs:/path2 hdd-ext4:/path3 hdd-xfs:/path4

The benchmark shows performance improvement (or degradation) when use
new preallocate filter with qcow2 image.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201021145859.11201-22-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 scripts/simplebench/bench_prealloc.py | 132 ++++++++++++++++++++++++++
 1 file changed, 132 insertions(+)
 create mode 100755 scripts/simplebench/bench_prealloc.py

diff --git a/scripts/simplebench/bench_prealloc.py b/scripts/simplebench/bench_prealloc.py
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/scripts/simplebench/bench_prealloc.py
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Benchmark preallocate filter
+#
+# Copyright (c) 2020 Virtuozzo International GmbH.
+#
+# 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/>.
+#
+
+
+import sys
+import os
+import subprocess
+import re
+import json
+
+import simplebench
+from results_to_text import results_to_text
+
+
+def qemu_img_bench(args):
+    p = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+                       universal_newlines=True)
+
+    if p.returncode == 0:
+        try:
+            m = re.search(r'Run completed in (\d+.\d+) seconds.', p.stdout)
+            return {'seconds': float(m.group(1))}
+        except Exception:
+            return {'error': f'failed to parse qemu-img output: {p.stdout}'}
+    else:
+        return {'error': f'qemu-img failed: {p.returncode}: {p.stdout}'}
+
+
+def bench_func(env, case):
+    fname = f"{case['dir']}/prealloc-test.qcow2"
+    try:
+        os.remove(fname)
+    except OSError:
+        pass
+
+    subprocess.run([env['qemu-img-binary'], 'create', '-f', 'qcow2', fname,
+                   '16G'], stdout=subprocess.DEVNULL,
+                   stderr=subprocess.DEVNULL, check=True)
+
+    args = [env['qemu-img-binary'], 'bench', '-c', str(case['count']),
+            '-d', '64', '-s', case['block-size'], '-t', 'none', '-n', '-w']
+    if env['prealloc']:
+        args += ['--image-opts',
+                 'driver=qcow2,file.driver=preallocate,file.file.driver=file,'
+                 f'file.file.filename={fname}']
+    else:
+        args += ['-f', 'qcow2', fname]
+
+    return qemu_img_bench(args)
+
+
+def auto_count_bench_func(env, case):
+    case['count'] = 100
+    while True:
+        res = bench_func(env, case)
+        if 'error' in res:
+            return res
+
+        if res['seconds'] >= 1:
+            break
+
+        case['count'] *= 10
+
+    if res['seconds'] < 5:
+        case['count'] = round(case['count'] * 5 / res['seconds'])
+        res = bench_func(env, case)
+        if 'error' in res:
+            return res
+
+    res['iops'] = case['count'] / res['seconds']
+    return res
+
+
+if __name__ == '__main__':
+    if len(sys.argv) < 2:
+        print(f'USAGE: {sys.argv[0]} <qemu-img binary> '
+              'DISK_NAME:DIR_PATH ...')
+        exit(1)
+
+    qemu_img = sys.argv[1]
+
+    envs = [
+        {
+            'id': 'no-prealloc',
+            'qemu-img-binary': qemu_img,
+            'prealloc': False
+        },
+        {
+            'id': 'prealloc',
+            'qemu-img-binary': qemu_img,
+            'prealloc': True
+        }
+    ]
+
+    aligned_cases = []
+    unaligned_cases = []
+
+    for disk in sys.argv[2:]:
+        name, path = disk.split(':')
+        aligned_cases.append({
+            'id': f'{name}, aligned sequential 16k',
+            'block-size': '16k',
+            'dir': path
+        })
+        unaligned_cases.append({
+            'id': f'{name}, unaligned sequential 64k',
+            'block-size': '16k',
+            'dir': path
+        })
+
+    result = simplebench.bench(auto_count_bench_func, envs,
+                               aligned_cases + unaligned_cases, count=5)
+    print(results_to_text(result))
+    with open('results.json', 'w') as f:
+        json.dump(result, f, indent=4)
-- 
2.29.2

From: Alberto Garcia <berto@igalia.com>

The quorum driver does not implement bdrv_co_block_status() and
because of that it always reports to contain data even if all its
children are known to be empty.

One consequence of this is that if we for example create a quorum with
a size of 10GB and we mirror it to a new image the operation will
write 10GB of actual zeroes to the destination image wasting a lot of
time and disk space.

Since a quorum has an arbitrary number of children of potentially
different formats there is no way to report all possible allocation
status flags in a way that makes sense, so this implementation only
reports when a given region is known to contain zeroes
(BDRV_BLOCK_ZERO) or not (BDRV_BLOCK_DATA).

If all children agree that a region contains zeroes then we can return
BDRV_BLOCK_ZERO using the smallest size reported by the children
(because all agree that a region of at least that size contains
zeroes).

If at least one child disagrees we have to return BDRV_BLOCK_DATA.
In this case we use the largest of the sizes reported by the children
that didn't return BDRV_BLOCK_ZERO (because we know that there won't
be an agreement for at least that size).

Signed-off-by: Alberto Garcia <berto@igalia.com>
Tested-by: Tao Xu <tao3.xu@intel.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <db83149afcf0f793effc8878089d29af4c46ffe1.1605286097.git.berto@igalia.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/quorum.c             |  52 +++++++++++++
 tests/qemu-iotests/312     | 148 +++++++++++++++++++++++++++++++++++++
 tests/qemu-iotests/312.out |  67 +++++++++++++++++
 tests/qemu-iotests/group   |   1 +
 4 files changed, 268 insertions(+)
 create mode 100755 tests/qemu-iotests/312
 create mode 100644 tests/qemu-iotests/312.out

diff --git a/block/quorum.c b/block/quorum.c
index XXXXXXX..XXXXXXX 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/module.h"
 #include "qemu/option.h"
 #include "block/block_int.h"
+#include "block/coroutines.h"
 #include "block/qdict.h"
 #include "qapi/error.h"
 #include "qapi/qapi-events-block.h"
@@ -XXX,XX +XXX,XX @@ static void quorum_child_perm(BlockDriverState *bs, BdrvChild *c,
              | DEFAULT_PERM_UNCHANGED;
 }
 
+/*
+ * Each one of the children can report different status flags even
+ * when they contain the same data, so what this function does is
+ * return BDRV_BLOCK_ZERO if *all* children agree that a certain
+ * region contains zeroes, and BDRV_BLOCK_DATA otherwise.
+ */
+static int coroutine_fn quorum_co_block_status(BlockDriverState *bs,
+                                               bool want_zero,
+                                               int64_t offset, int64_t count,
+                                               int64_t *pnum, int64_t *map,
+                                               BlockDriverState **file)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i, ret;
+    int64_t pnum_zero = count;
+    int64_t pnum_data = 0;
+
+    for (i = 0; i < s->num_children; i++) {
+        int64_t bytes;
+        ret = bdrv_co_common_block_status_above(s->children[i]->bs, NULL, false,
+                                                want_zero, offset, count,
+                                                &bytes, NULL, NULL, NULL);
+        if (ret < 0) {
+            quorum_report_bad(QUORUM_OP_TYPE_READ, offset, count,
+                              s->children[i]->bs->node_name, ret);
+            pnum_data = count;
+            break;
+        }
+        /*
+         * Even if all children agree about whether there are zeroes
+         * or not at @offset they might disagree on the size, so use
+         * the smallest when reporting BDRV_BLOCK_ZERO and the largest
+         * when reporting BDRV_BLOCK_DATA.
+         */
+        if (ret & BDRV_BLOCK_ZERO) {
+            pnum_zero = MIN(pnum_zero, bytes);
+        } else {
+            pnum_data = MAX(pnum_data, bytes);
+        }
+    }
+
+    if (pnum_data) {
+        *pnum = pnum_data;
+        return BDRV_BLOCK_DATA;
+    } else {
+        *pnum = pnum_zero;
+        return BDRV_BLOCK_ZERO;
+    }
+}
+
 static const char *const quorum_strong_runtime_opts[] = {
     QUORUM_OPT_VOTE_THRESHOLD,
     QUORUM_OPT_BLKVERIFY,
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = {
     .bdrv_close                         = quorum_close,
     .bdrv_gather_child_options          = quorum_gather_child_options,
     .bdrv_dirname                       = quorum_dirname,
+    .bdrv_co_block_status               = quorum_co_block_status,
 
     .bdrv_co_flush_to_disk              = quorum_co_flush,
 
diff --git a/tests/qemu-iotests/312 b/tests/qemu-iotests/312
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/312
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env bash
+#
+# Test drive-mirror with quorum
+#
+# The goal of this test is to check how the quorum driver reports
+# regions that are known to read as zeroes (BDRV_BLOCK_ZERO). The idea
+# is that drive-mirror will try the efficient representation of zeroes
+# in the destination image instead of writing actual zeroes.
+#
+# Copyright (C) 2020 Igalia, S.L.
+# Author: Alberto Garcia <berto@igalia.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/>.
+#
+
+# creator
+owner=berto@igalia.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+status=1	# failure is the default!
+
+_cleanup()
+{
+    _rm_test_img "$TEST_IMG.0"
+    _rm_test_img "$TEST_IMG.1"
+    _rm_test_img "$TEST_IMG.2"
+    _rm_test_img "$TEST_IMG.3"
+    _cleanup_qemu
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+. ./common.qemu
+
+_supported_fmt qcow2
+_supported_proto file
+_supported_os Linux
+_unsupported_imgopts cluster_size data_file
+
+echo
+echo '### Create all images' # three source (quorum), one destination
+echo
+TEST_IMG="$TEST_IMG.0" _make_test_img -o cluster_size=64k 10M
+TEST_IMG="$TEST_IMG.1" _make_test_img -o cluster_size=64k 10M
+TEST_IMG="$TEST_IMG.2" _make_test_img -o cluster_size=64k 10M
+TEST_IMG="$TEST_IMG.3" _make_test_img -o cluster_size=64k 10M
+
+quorum="driver=raw,file.driver=quorum,file.vote-threshold=2"
+quorum="$quorum,file.children.0.file.filename=$TEST_IMG.0"
+quorum="$quorum,file.children.1.file.filename=$TEST_IMG.1"
+quorum="$quorum,file.children.2.file.filename=$TEST_IMG.2"
+quorum="$quorum,file.children.0.driver=$IMGFMT"
+quorum="$quorum,file.children.1.driver=$IMGFMT"
+quorum="$quorum,file.children.2.driver=$IMGFMT"
+
+echo
+echo '### Output of qemu-img map (empty quorum)'
+echo
+$QEMU_IMG map --image-opts $quorum | _filter_qemu_img_map
+
+# Now we write data to the quorum. All three images will read as
+# zeroes in all cases, but with different ways to represent them
+# (unallocated clusters, zero clusters, data clusters with zeroes)
+# that will have an effect on how the data will be mirrored and the
+# output of qemu-img map on the resulting image.
+echo
+echo '### Write data to the quorum'
+echo
+# Test 1: data regions surrounded by unallocated clusters.
+# Three data regions, the largest one (0x30000) will be picked, end result:
+# offset 0x10000, length 0x30000 -> data
+$QEMU_IO -c "write -P 0 $((0x10000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io
+$QEMU_IO -c "write -P 0 $((0x10000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io
+$QEMU_IO -c "write -P 0 $((0x10000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io
+
+# Test 2: zero regions surrounded by data clusters.
+# First we allocate the data clusters.
+$QEMU_IO -c "open -o $quorum" -c "write -P 0 $((0x100000)) $((0x40000))" | _filter_qemu_io
+
+# Three zero regions, the smallest one (0x10000) will be picked, end result:
+# offset 0x100000, length 0x10000 -> data
+# offset 0x110000, length 0x10000 -> zeroes
+# offset 0x120000, length 0x20000 -> data
+$QEMU_IO -c "write -z $((0x110000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io
+$QEMU_IO -c "write -z $((0x110000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io
+$QEMU_IO -c "write -z $((0x110000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io
+
+# Test 3: zero clusters surrounded by unallocated clusters.
+# Everything reads as zeroes, no effect on the end result.
+$QEMU_IO -c "write -z $((0x150000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io
+$QEMU_IO -c "write -z $((0x150000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io
+$QEMU_IO -c "write -z $((0x150000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io
+
+# Test 4: mix of data and zero clusters.
+# The zero region will be ignored in favor of the largest data region
+# (0x20000), end result:
+# offset 0x200000, length 0x20000 -> data
+$QEMU_IO -c "write -P 0 $((0x200000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io
+$QEMU_IO -c "write -z   $((0x200000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io
+$QEMU_IO -c "write -P 0 $((0x200000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io
+
+echo
+echo '### Launch the drive-mirror job'
+echo
+qemu_comm_method="qmp" _launch_qemu -drive if=virtio,"$quorum"
+h=$QEMU_HANDLE
+_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return'
+
+_send_qemu_cmd $h \
+    "{'execute': 'drive-mirror',
+                 'arguments': {'device': 'virtio0',
+                               'format': '$IMGFMT',
+                               'target': '$TEST_IMG.3',
+                               'sync':   'full',
+                               'mode':   'existing' }}"    \
+     "BLOCK_JOB_READY.*virtio0"
+
+_send_qemu_cmd $h \
+    "{ 'execute': 'block-job-complete',
+       'arguments': { 'device': 'virtio0' } }" \
+    'BLOCK_JOB_COMPLETED'
+
+_send_qemu_cmd $h "{ 'execute': 'quit' }" ''
+
+echo
+echo '### Output of qemu-img map (destination image)'
+echo
+$QEMU_IMG map "$TEST_IMG.3" | _filter_qemu_img_map
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/312.out b/tests/qemu-iotests/312.out
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/qemu-iotests/312.out
@@ -XXX,XX +XXX,XX @@
+QA output created by 312
+
+### Create all images
+
+Formatting 'TEST_DIR/t.IMGFMT.0', fmt=IMGFMT size=10485760
+Formatting 'TEST_DIR/t.IMGFMT.1', fmt=IMGFMT size=10485760
+Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=10485760
+Formatting 'TEST_DIR/t.IMGFMT.3', fmt=IMGFMT size=10485760
+
+### Output of qemu-img map (empty quorum)
+
+Offset          Length          File
+
+### Write data to the quorum
+
+wrote 65536/65536 bytes at offset 65536
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 196608/196608 bytes at offset 65536
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 65536
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 262144/262144 bytes at offset 1048576
+256 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 1114112
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 196608/196608 bytes at offset 1114112
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 1114112
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 1376256
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 196608/196608 bytes at offset 1376256
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 1376256
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 2097152
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 196608/196608 bytes at offset 2097152
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 2097152
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+### Launch the drive-mirror job
+
+{ 'execute': 'qmp_capabilities' }
+{"return": {}}
+{'execute': 'drive-mirror', 'arguments': {'device': 'virtio0', 'format': 'IMGFMT', 'target': 'TEST_DIR/t.IMGFMT.3', 'sync': 'full', 'mode': 'existing' }}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}}
+{"return": {}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 10485760, "offset": 10485760, "speed": 0, "type": "mirror"}}
+{ 'execute': 'block-job-complete', 'arguments': { 'device': 'virtio0' } }
+{"return": {}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "virtio0"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "virtio0"}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "virtio0", "len": 10485760, "offset": 10485760, "speed": 0, "type": "mirror"}}
+{ 'execute': 'quit' }
+
+### Output of qemu-img map (destination image)
+
+Offset          Length          File
+0x10000         0x30000         TEST_DIR/t.IMGFMT.3
+0x100000        0x10000         TEST_DIR/t.IMGFMT.3
+0x120000        0x20000         TEST_DIR/t.IMGFMT.3
+0x200000        0x20000         TEST_DIR/t.IMGFMT.3
+*** done
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -XXX,XX +XXX,XX @@
 307 rw quick export
 308 rw
 309 rw auto quick
+312 rw auto quick
-- 
2.29.2

From: Alberto Garcia <berto@igalia.com>

This simply calls bdrv_co_pwrite_zeroes() in all children.

bs->supported_zero_flags is also set to the flags that are supported
by all children.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Message-Id: <2f09c842781fe336b4c2e40036bba577b7430190.1605286097.git.berto@igalia.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/quorum.c             | 36 ++++++++++++++++++++++++++++++++++--
 tests/qemu-iotests/312     | 11 +++++++++++
 tests/qemu-iotests/312.out |  8 ++++++++
 3 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/block/quorum.c b/block/quorum.c
index XXXXXXX..XXXXXXX 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -XXX,XX +XXX,XX @@ static void write_quorum_entry(void *opaque)
     QuorumChildRequest *sacb = &acb->qcrs[i];
 
     sacb->bs = s->children[i]->bs;
-    sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes,
-                                acb->qiov, acb->flags);
+    if (acb->flags & BDRV_REQ_ZERO_WRITE) {
+        sacb->ret = bdrv_co_pwrite_zeroes(s->children[i], acb->offset,
+                                          acb->bytes, acb->flags);
+    } else {
+        sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes,
+                                    acb->qiov, acb->flags);
+    }
     if (sacb->ret == 0) {
         acb->success_count++;
     } else {
@@ -XXX,XX +XXX,XX @@ static int quorum_co_pwritev(BlockDriverState *bs, uint64_t offset,
     return ret;
 }
 
+static int quorum_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
+                                   int bytes, BdrvRequestFlags flags)
+
+{
+    return quorum_co_pwritev(bs, offset, bytes, NULL,
+                             flags | BDRV_REQ_ZERO_WRITE);
+}
+
 static int64_t quorum_getlength(BlockDriverState *bs)
 {
     BDRVQuorumState *s = bs->opaque;
@@ -XXX,XX +XXX,XX @@ static QemuOptsList quorum_runtime_opts = {
     },
 };
 
+static void quorum_refresh_flags(BlockDriverState *bs)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i;
+
+    bs->supported_zero_flags =
+        BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK;
+
+    for (i = 0; i < s->num_children; i++) {
+        bs->supported_zero_flags &= s->children[i]->bs->supported_zero_flags;
+    }
+
+    bs->supported_zero_flags |= BDRV_REQ_WRITE_UNCHANGED;
+}
+
 static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
                        Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     s->next_child_index = s->num_children;
 
     bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
+    quorum_refresh_flags(bs);
 
     g_free(opened);
     goto exit;
@@ -XXX,XX +XXX,XX @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs,
     }
     s->children = g_renew(BdrvChild *, s->children, s->num_children + 1);
     s->children[s->num_children++] = child;
+    quorum_refresh_flags(bs);
 
 out:
     bdrv_drained_end(bs);
@@ -XXX,XX +XXX,XX @@ static void quorum_del_child(BlockDriverState *bs, BdrvChild *child,
     s->children = g_renew(BdrvChild *, s->children, --s->num_children);
     bdrv_unref_child(bs, child);
 
+    quorum_refresh_flags(bs);
     bdrv_drained_end(bs);
 }
 
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = {
 
     .bdrv_co_preadv                     = quorum_co_preadv,
     .bdrv_co_pwritev                    = quorum_co_pwritev,
+    .bdrv_co_pwrite_zeroes              = quorum_co_pwrite_zeroes,
 
     .bdrv_add_child                     = quorum_add_child,
     .bdrv_del_child                     = quorum_del_child,
diff --git a/tests/qemu-iotests/312 b/tests/qemu-iotests/312
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/312
+++ b/tests/qemu-iotests/312
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write -P 0 $((0x200000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu
 $QEMU_IO -c "write -z   $((0x200000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io
 $QEMU_IO -c "write -P 0 $((0x200000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io
 
+# Test 5: write data to a region and then zeroize it, doing it
+# directly on the quorum device instead of the individual images.
+# This has no effect on the end result but proves that the quorum driver
+# supports 'write -z'.
+$QEMU_IO -c "open -o $quorum" -c "write -P 1 $((0x250000)) $((0x10000))" | _filter_qemu_io
+# Verify the data that we just wrote
+$QEMU_IO -c "open -o $quorum" -c "read -P 1 $((0x250000)) $((0x10000))" | _filter_qemu_io
+$QEMU_IO -c "open -o $quorum" -c "write -z $((0x250000)) $((0x10000))" | _filter_qemu_io
+# Now it should read back as zeroes
+$QEMU_IO -c "open -o $quorum" -c "read -P 0 $((0x250000)) $((0x10000))" | _filter_qemu_io
+
 echo
 echo '### Launch the drive-mirror job'
 echo
diff --git a/tests/qemu-iotests/312.out b/tests/qemu-iotests/312.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/312.out
+++ b/tests/qemu-iotests/312.out
@@ -XXX,XX +XXX,XX @@ wrote 196608/196608 bytes at offset 2097152
 192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 wrote 131072/131072 bytes at offset 2097152
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 2424832
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 2424832
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 2424832
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 2424832
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 ### Launch the drive-mirror job
 
-- 
2.29.2

From: Philippe Mathieu-Daudé <philmd@redhat.com>

NVMe drive cannot be shrunk.

Since commit c80d8b06cfa we can use the @exact parameter (set
to false) to return success if the block device is larger than
the requested offset (even if we can not be shrunk).

Use this parameter to implement the NVMe truncate() coroutine,
similarly how it is done for the iscsi and file-posix drivers
(see commit 82325ae5f2f "Evaluate @exact in protocol drivers").

Reported-by: Xueqiang Wei <xuwei@redhat.com>
Suggested-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20201210125202.858656-1-philmd@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/nvme.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/block/nvme.c b/block/nvme.c
index XXXXXXX..XXXXXXX 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -XXX,XX +XXX,XX @@ out:
 
 }
 
+static int coroutine_fn nvme_co_truncate(BlockDriverState *bs, int64_t offset,
+                                         bool exact, PreallocMode prealloc,
+                                         BdrvRequestFlags flags, Error **errp)
+{
+    int64_t cur_length;
+
+    if (prealloc != PREALLOC_MODE_OFF) {
+        error_setg(errp, "Unsupported preallocation mode '%s'",
+                   PreallocMode_str(prealloc));
+        return -ENOTSUP;
+    }
+
+    cur_length = nvme_getlength(bs);
+    if (offset != cur_length && exact) {
+        error_setg(errp, "Cannot resize NVMe devices");
+        return -ENOTSUP;
+    } else if (offset > cur_length) {
+        error_setg(errp, "Cannot grow NVMe devices");
+        return -EINVAL;
+    }
+
+    return 0;
+}
 
 static int nvme_reopen_prepare(BDRVReopenState *reopen_state,
                                BlockReopenQueue *queue, Error **errp)
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = {
     .bdrv_close               = nvme_close,
     .bdrv_getlength           = nvme_getlength,
     .bdrv_probe_blocksizes    = nvme_probe_blocksizes,
+    .bdrv_co_truncate         = nvme_co_truncate,
 
     .bdrv_co_preadv           = nvme_co_preadv,
     .bdrv_co_pwritev          = nvme_co_pwritev,
-- 
2.29.2

The first parameter passed to _send_qemu_cmd is supposed to be the
$QEMU_HANDLE.  102 does not do so here, fix it.

As a result, the output changes: Now we see the prompt this command is
supposedly waiting for before the resize message - as it should be.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20201217153803.101231-2-mreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
---
 tests/qemu-iotests/102     | 2 +-
 tests/qemu-iotests/102.out | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/qemu-iotests/102 b/tests/qemu-iotests/102
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/102
+++ b/tests/qemu-iotests/102
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
 qemu_comm_method=monitor _launch_qemu -drive if=none,file="$TEST_IMG",id=drv0
 
 # Wait for a prompt to appear (so we know qemu has opened the image)
-_send_qemu_cmd '' '(qemu)'
+_send_qemu_cmd $QEMU_HANDLE '' '(qemu)'
 
 $QEMU_IMG resize --shrink --image-opts \
     "driver=raw,file.driver=file,file.filename=$TEST_IMG,file.locking=off" \
diff --git a/tests/qemu-iotests/102.out b/tests/qemu-iotests/102.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/102.out
+++ b/tests/qemu-iotests/102.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536
 wrote 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 QEMU X.Y.Z monitor - type 'help' for more information
-Image resized.
 (qemu)
+Image resized.
 (qemu) qemu-io drv0 map
 64 KiB (0x10000) bytes     allocated at offset 0 bytes (0x0)
 *** done
-- 
2.29.2

With bash 5.1, the output of the following script changes:

a=("double  space")
  a=${a[@]:0:1}
  echo "$a"

from "double space" to "double  space", i.e. all white space is
preserved as-is.  This is probably what we actually want here (judging
from the "...to accommodate pathnames with spaces" comment), but before
5.1, we would have to quote the ${} slice to get the same behavior.

In any case, without quoting, the reference output of many iotests is
different between bash 5.1 and pre-5.1, which is not very good.  The
output of 5.1 is what we want, so whatever we do to get pre-5.1 to the
same result, it means we have to fix the reference output of basically
all tests that invoke _send_qemu_cmd (except the ones that only use
single spaces in the commands they invoke).

Instead of quoting the ${} slice (cmd="${$@: 1:...}"), we can also just
not use array slicing and replace the whole thing with a simple "cmd=$1;
shift", which works because all callers quote the whole $cmd argument
anyway.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20201217153803.101231-3-mreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
---
 tests/qemu-iotests/085.out     | 167 ++++++++++++++++++++++++++++-----
 tests/qemu-iotests/094.out     |  10 +-
 tests/qemu-iotests/095.out     |   4 +-
 tests/qemu-iotests/109.out     |  88 ++++++++++++-----
 tests/qemu-iotests/117.out     |  13 ++-
 tests/qemu-iotests/127.out     |  12 ++-
 tests/qemu-iotests/140.out     |  10 +-
 tests/qemu-iotests/141.out     | 128 +++++++++++++++++++------
 tests/qemu-iotests/143.out     |   4 +-
 tests/qemu-iotests/144.out     |  28 +++++-
 tests/qemu-iotests/153.out     |  18 ++--
 tests/qemu-iotests/156.out     |  39 ++++++--
 tests/qemu-iotests/161.out     |  18 +++-
 tests/qemu-iotests/173.out     |  25 ++++-
 tests/qemu-iotests/182.out     |  42 +++++++--
 tests/qemu-iotests/183.out     |  19 +++-
 tests/qemu-iotests/185.out     |  45 +++++++--
 tests/qemu-iotests/191.out     |  12 ++-
 tests/qemu-iotests/223.out     |  92 ++++++++++++------
 tests/qemu-iotests/229.out     |  13 ++-
 tests/qemu-iotests/249.out     |  16 +++-
 tests/qemu-iotests/308.out     | 103 +++++++++++++++++---
 tests/qemu-iotests/312.out     |  10 +-
 tests/qemu-iotests/common.qemu |  11 +--
 24 files changed, 728 insertions(+), 199 deletions(-)

diff --git a/tests/qemu-iotests/085.out b/tests/qemu-iotests/085.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/085.out
+++ b/tests/qemu-iotests/085.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=134217728
 
 === Create a single snapshot on virtio0 ===
 
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', 'format': 'IMGFMT' } }
+{ 'execute': 'blockdev-snapshot-sync',
+                      'arguments': { 'device': 'virtio0',
+                                     'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT',
+                                     'format': 'IMGFMT' } }
 Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2.1 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Invalid command - missing device and nodename ===
 
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', 'format': 'IMGFMT' } }
+{ 'execute': 'blockdev-snapshot-sync',
+                         'arguments': { 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT',
+                                     'format': 'IMGFMT' } }
 {"error": {"class": "GenericError", "desc": "Cannot find device= nor node_name="}}
 
 === Invalid command - missing snapshot-file ===
 
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'format': 'IMGFMT' } }
+{ 'execute': 'blockdev-snapshot-sync',
+                         'arguments': { 'device': 'virtio0',
+                                     'format': 'IMGFMT' } }
 {"error": {"class": "GenericError", "desc": "Parameter 'snapshot-file' is missing"}}
 
 
 === Create several transactional group snapshots ===
 
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/2-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/2-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/2-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/2-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/2-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/1-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/2-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2.2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/3-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/3-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/3-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/3-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/3-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/2-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/3-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/2-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/4-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/4-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/4-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/4-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/4-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/3-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/4-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/3-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/5-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/5-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/5-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/5-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/5-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/4-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/5-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/4-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/6-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/6-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/6-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/6-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/6-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/5-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/6-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/5-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/7-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/7-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/7-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/7-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/7-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/6-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/7-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/6-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/8-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/8-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/8-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/8-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/8-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/7-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/8-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/7-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/9-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/9-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/9-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/9-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/9-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/8-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/9-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/8-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/10-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/10-snapshot-v1.IMGFMT' } } ] } }
+{ 'execute': 'transaction', 'arguments':
+           {'actions': [
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio0',
+                      'snapshot-file': 'TEST_DIR/10-snapshot-v0.IMGFMT' } },
+               { 'type': 'blockdev-snapshot-sync', 'data' :
+                   { 'device': 'virtio1',
+                       'snapshot-file': 'TEST_DIR/10-snapshot-v1.IMGFMT' } } ]
+             } }
 Formatting 'TEST_DIR/10-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/9-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/9-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extende
 === Create a couple of snapshots using blockdev-snapshot ===
 
 Formatting 'TEST_DIR/11-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/10-snapshot-v0.IMGFMT backing_fmt=IMGFMT
-{ 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_11', 'backing': null, 'file': { 'driver': 'file', 'filename': 'TEST_DIR/11-snapshot-v0.IMGFMT', 'node-name': 'file_11' } } }
+{ 'execute': 'blockdev-add', 'arguments':
+           { 'driver': 'IMGFMT', 'node-name': 'snap_11', 'backing': null,
+             'file':
+             { 'driver': 'file', 'filename': 'TEST_DIR/11-snapshot-v0.IMGFMT',
+               'node-name': 'file_11' } } }
 {"return": {}}
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_11' } }
+{ 'execute': 'blockdev-snapshot',
+                      'arguments': { 'node': 'virtio0',
+                                     'overlay':'snap_11' } }
 {"return": {}}
 Formatting 'TEST_DIR/12-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/11-snapshot-v0.IMGFMT backing_fmt=IMGFMT
-{ 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_12', 'backing': null, 'file': { 'driver': 'file', 'filename': 'TEST_DIR/12-snapshot-v0.IMGFMT', 'node-name': 'file_12' } } }
+{ 'execute': 'blockdev-add', 'arguments':
+           { 'driver': 'IMGFMT', 'node-name': 'snap_12', 'backing': null,
+             'file':
+             { 'driver': 'file', 'filename': 'TEST_DIR/12-snapshot-v0.IMGFMT',
+               'node-name': 'file_12' } } }
 {"return": {}}
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_12' } }
+{ 'execute': 'blockdev-snapshot',
+                      'arguments': { 'node': 'virtio0',
+                                     'overlay':'snap_12' } }
 {"return": {}}
 
 === Invalid command - cannot create a snapshot using a file BDS ===
 
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'virtio0', 'overlay':'file_12' } }
+{ 'execute': 'blockdev-snapshot',
+                     'arguments': { 'node':'virtio0',
+                                    'overlay':'file_12' }
+                   }
 {"error": {"class": "GenericError", "desc": "The overlay is already in use"}}
 
 === Invalid command - snapshot node used as active layer ===
 
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_12' } }
+{ 'execute': 'blockdev-snapshot',
+                      'arguments': { 'node': 'virtio0',
+                                     'overlay':'snap_12' } }
 {"error": {"class": "GenericError", "desc": "The overlay is already in use"}}
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'virtio0', 'overlay':'virtio0' } }
+{ 'execute': 'blockdev-snapshot',
+                     'arguments': { 'node':'virtio0',
+                                    'overlay':'virtio0' }
+                   }
 {"error": {"class": "GenericError", "desc": "The overlay is already in use"}}
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'virtio0', 'overlay':'virtio1' } }
+{ 'execute': 'blockdev-snapshot',
+                     'arguments': { 'node':'virtio0',
+                                    'overlay':'virtio1' }
+                   }
 {"error": {"class": "GenericError", "desc": "The overlay is already in use"}}
 
 === Invalid command - snapshot node used as backing hd ===
 
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_11' } }
+{ 'execute': 'blockdev-snapshot',
+                      'arguments': { 'node': 'virtio0',
+                                     'overlay':'snap_11' } }
 {"error": {"class": "GenericError", "desc": "The overlay is already in use"}}
 
 === Invalid command - snapshot node has a backing image ===
 
 Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=IMGFMT
-{ 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_13', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'node-name': 'file_13' } } }
-{"return": {}}
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_13' } }
+{ 'execute': 'blockdev-add', 'arguments':
+           { 'driver': 'IMGFMT', 'node-name': 'snap_13',
+             'file':
+             { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT',
+               'node-name': 'file_13' } } }
+{"return": {}}
+{ 'execute': 'blockdev-snapshot',
+                      'arguments': { 'node': 'virtio0',
+                                     'overlay':'snap_13' } }
 {"error": {"class": "GenericError", "desc": "The overlay already has a backing image"}}
 
 === Invalid command - The node does not exist ===
 
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_14' } }
+{ 'execute': 'blockdev-snapshot',
+                      'arguments': { 'node': 'virtio0',
+                                     'overlay':'snap_14' } }
 {"error": {"class": "GenericError", "desc": "Cannot find device=snap_14 nor node_name=snap_14"}}
-{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'nodevice', 'overlay':'snap_13' } }
+{ 'execute': 'blockdev-snapshot',
+                     'arguments': { 'node':'nodevice',
+                                    'overlay':'snap_13' }
+                   }
 {"error": {"class": "GenericError", "desc": "Cannot find device=nodevice nor node_name=nodevice"}}
 *** done
diff --git a/tests/qemu-iotests/094.out b/tests/qemu-iotests/094.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/094.out
+++ b/tests/qemu-iotests/094.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/source.IMGFMT', fmt=IMGFMT size=67108864
 {'execute': 'qmp_capabilities'}
 {"return": {}}
-{'execute': 'drive-mirror', 'arguments': {'device': 'src', 'target': 'nbd+unix:///?socket=SOCK_DIR/nbd', 'format': 'nbd', 'sync':'full', 'mode':'existing'}}
+{'execute': 'drive-mirror',
+      'arguments': {'device': 'src',
+                    'target': 'nbd+unix:///?socket=SOCK_DIR/nbd',
+                    'format': 'nbd',
+                    'sync':'full',
+                    'mode':'existing'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 67108864, "offset": 67108864, "speed": 0, "type": "mirror"}}
-{'execute': 'block-job-complete', 'arguments': {'device': 'src'}}
+{'execute': 'block-job-complete',
+      'arguments': {'device': 'src'}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}}
diff --git a/tests/qemu-iotests/095.out b/tests/qemu-iotests/095.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/095.out
+++ b/tests/qemu-iotests/095.out
@@ -XXX,XX +XXX,XX @@ virtual size: 5 MiB (5242880 bytes)
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'block-commit', 'arguments': { 'device': 'test', 'top': 'TEST_DIR/t.IMGFMT.snp1' } }
+{ 'execute': 'block-commit',
+                                 'arguments': { 'device': 'test',
+                                 'top': 'TEST_DIR/t.IMGFMT.snp1' } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "test"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "test"}}
 {"return": {}}
diff --git a/tests/qemu-iotests/109.out b/tests/qemu-iotests/109.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/109.out
+++ b/tests/qemu-iotests/109.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Images are identical.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Images are identical.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Images are identical.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Images are identical.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Images are identical.
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw.
          Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted.
          Specify the 'raw' format explicitly to remove the restrictions.
@@ -XXX,XX +XXX,XX @@ WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed
 Images are identical.
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}}
+{'execute':'drive-mirror', 'arguments':{
+            'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT',
+            'mode': 'existing', 'sync': 'full'}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}}
 {"return": {}}
diff --git a/tests/qemu-iotests/117.out b/tests/qemu-iotests/117.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/117.out
+++ b/tests/qemu-iotests/117.out
@@ -XXX,XX +XXX,XX @@ QA output created by 117
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'blockdev-add', 'arguments': { 'node-name': 'protocol', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' } }
+{ 'execute': 'blockdev-add',
+       'arguments': { 'node-name': 'protocol',
+                      'driver': 'file',
+                      'filename': 'TEST_DIR/t.IMGFMT' } }
 {"return": {}}
-{ 'execute': 'blockdev-add', 'arguments': { 'node-name': 'format', 'driver': 'IMGFMT', 'file': 'protocol' } }
+{ 'execute': 'blockdev-add',
+       'arguments': { 'node-name': 'format',
+                      'driver': 'IMGFMT',
+                      'file': 'protocol' } }
 {"return": {}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io format "write -P 42 0 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line': 'qemu-io format "write -P 42 0 64k"' } }
 wrote 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
diff --git a/tests/qemu-iotests/127.out b/tests/qemu-iotests/127.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/127.out
+++ b/tests/qemu-iotests/127.out
@@ -XXX,XX +XXX,XX @@ wrote 42/42 bytes at offset 0
 42 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'drive-mirror', 'arguments': { 'job-id': 'mirror', 'device': 'source', 'target': 'TEST_DIR/t.IMGFMT.overlay1', 'mode': 'existing', 'sync': 'top' } }
+{ 'execute': 'drive-mirror',
+       'arguments': {
+           'job-id': 'mirror',
+           'device': 'source',
+           'target': 'TEST_DIR/t.IMGFMT.overlay1',
+           'mode':   'existing',
+           'sync':   'top'
+       } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "mirror"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "mirror"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "mirror"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "mirror", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}}
-{ 'execute': 'block-job-complete', 'arguments': { 'device': 'mirror' } }
+{ 'execute': 'block-job-complete',
+       'arguments': { 'device': 'mirror' } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "mirror"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "mirror"}}
diff --git a/tests/qemu-iotests/140.out b/tests/qemu-iotests/140.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/140.out
+++ b/tests/qemu-iotests/140.out
@@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'nbd-server-start', 'arguments': { 'addr': { 'type': 'unix', 'data': { 'path': 'SOCK_DIR/nbd' }}}}
+{ 'execute': 'nbd-server-start',
+       'arguments': { 'addr': { 'type': 'unix',
+                                'data': { 'path': 'SOCK_DIR/nbd' }}}}
 {"return": {}}
-{ 'execute': 'nbd-server-add', 'arguments': { 'device': 'drv' }}
+{ 'execute': 'nbd-server-add',
+       'arguments': { 'device': 'drv' }}
 {"return": {}}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-{ 'execute': 'eject', 'arguments': { 'device': 'drv' }}
+{ 'execute': 'eject',
+       'arguments': { 'device': 'drv' }}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "drv"}}
 qemu-io: can't open device nbd+unix:///drv?socket=SOCK_DIR/nbd: Requested export not available
 server reported: export 'drv' not present
diff --git a/tests/qemu-iotests/141.out b/tests/qemu-iotests/141.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/141.out
+++ b/tests/qemu-iotests/141.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/m.
 
 === Testing drive-backup ===
 
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}}
-{"return": {}}
-{'execute': 'drive-backup', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'target': 'TEST_DIR/o.IMGFMT', 'format': 'IMGFMT', 'sync': 'none'}}
+{'execute': 'blockdev-add',
+          'arguments': {
+              'node-name': 'drv0',
+              'driver': 'IMGFMT',
+              'file': {
+                  'driver': 'file',
+                  'filename': 'TEST_DIR/t.IMGFMT'
+              }}}
+{"return": {}}
+{'execute': 'drive-backup',
+'arguments': {'job-id': 'job0',
+'device': 'drv0',
+'target': 'TEST_DIR/o.IMGFMT',
+'format': 'IMGFMT',
+'sync': 'none'}}
 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"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}}
-{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}}
+{'execute': 'block-job-cancel',
+          'arguments': {'device': 'job0'}}
 {"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"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"return": {}}
 
 === Testing drive-mirror ===
 
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}}
-{"return": {}}
-{'execute': 'drive-mirror', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'target': 'TEST_DIR/o.IMGFMT', 'format': 'IMGFMT', 'sync': 'none'}}
+{'execute': 'blockdev-add',
+          'arguments': {
+              'node-name': 'drv0',
+              'driver': 'IMGFMT',
+              'file': {
+                  'driver': 'file',
+                  'filename': 'TEST_DIR/t.IMGFMT'
+              }}}
+{"return": {}}
+{'execute': 'drive-mirror',
+'arguments': {'job-id': 'job0',
+'device': 'drv0',
+'target': 'TEST_DIR/o.IMGFMT',
+'format': 'IMGFMT',
+'sync': 'none'}}
 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"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: mirror"}}
-{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}}
+{'execute': 'block-job-cancel',
+          'arguments': {'device': 'job0'}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"return": {}}
 
 === Testing active block-commit ===
 
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}}
-{"return": {}}
-{'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'drv0'}}
+{'execute': 'blockdev-add',
+          'arguments': {
+              'node-name': 'drv0',
+              'driver': 'IMGFMT',
+              'file': {
+                  'driver': 'file',
+                  'filename': 'TEST_DIR/t.IMGFMT'
+              }}}
+{"return": {}}
+{'execute': 'block-commit',
+'arguments': {'job-id': 'job0', 'device': 'drv0'}}
 {"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"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: commit"}}
-{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}}
+{'execute': 'block-job-cancel',
+          'arguments': {'device': 'job0'}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"return": {}}
 
 === Testing non-active block-commit ===
 
 wrote 1048576/1048576 bytes at offset 0
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}}
-{"return": {}}
-{'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'top': 'TEST_DIR/m.IMGFMT', 'speed': 1}}
+{'execute': 'blockdev-add',
+          'arguments': {
+              'node-name': 'drv0',
+              'driver': 'IMGFMT',
+              'file': {
+                  'driver': 'file',
+                  'filename': 'TEST_DIR/t.IMGFMT'
+              }}}
+{"return": {}}
+{'execute': 'block-commit',
+'arguments': {'job-id': 'job0',
+'device': 'drv0',
+'top':    'TEST_DIR/m.IMGFMT',
+'speed':  1}}
 {"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"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"error": {"class": "GenericError", "desc": "Node drv0 is in use"}}
-{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}}
+{'execute': 'block-job-cancel',
+          'arguments': {'device': 'job0'}}
 {"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": 524288, "speed": 1, "type": "commit"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"return": {}}
 
 === Testing block-stream ===
 
 wrote 1048576/1048576 bytes at offset 0
 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}}
-{"return": {}}
-{'execute': 'block-stream', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'speed': 1}}
+{'execute': 'blockdev-add',
+          'arguments': {
+              'node-name': 'drv0',
+              'driver': 'IMGFMT',
+              'file': {
+                  'driver': 'file',
+                  'filename': 'TEST_DIR/t.IMGFMT'
+              }}}
+{"return": {}}
+{'execute': 'block-stream',
+'arguments': {'job-id': 'job0',
+'device': 'drv0',
+'speed': 1}}
 {"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"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"error": {"class": "GenericError", "desc": "Node drv0 is in use"}}
-{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}}
+{'execute': 'block-job-cancel',
+          'arguments': {'device': 'job0'}}
 {"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": 524288, "speed": 1, "type": "stream"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
-{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}}
+{'execute': 'blockdev-del',
+          'arguments': {'node-name': 'drv0'}}
 {"return": {}}
 *** done
diff --git a/tests/qemu-iotests/143.out b/tests/qemu-iotests/143.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/143.out
+++ b/tests/qemu-iotests/143.out
@@ -XXX,XX +XXX,XX @@
 QA output created by 143
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'nbd-server-start', 'arguments': { 'addr': { 'type': 'unix', 'data': { 'path': 'SOCK_DIR/nbd' }}}}
+{ 'execute': 'nbd-server-start',
+       'arguments': { 'addr': { 'type': 'unix',
+                                'data': { 'path': 'SOCK_DIR/nbd' }}}}
 {"return": {}}
 qemu-io: can't open device nbd+unix:///no_such_export?socket=SOCK_DIR/nbd: Requested export not available
 server reported: export 'no_such_export' not present
diff --git a/tests/qemu-iotests/144.out b/tests/qemu-iotests/144.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/144.out
+++ b/tests/qemu-iotests/144.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=536870912
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp.IMGFMT', 'format': 'IMGFMT' } }
+{ 'execute': 'blockdev-snapshot-sync',
+                                'arguments': {
+                                             'device': 'virtio0',
+                                             'snapshot-file':'TEST_DIR/tmp.IMGFMT',
+                                             'format': 'IMGFMT'
+                                             }
+                    }
 Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Performing block-commit on active layer ===
 
-{ 'execute': 'block-commit', 'arguments': { 'device': 'virtio0' } }
+{ 'execute': 'block-commit',
+                                'arguments': {
+                                                 'device': 'virtio0'
+                                              }
+                    }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
-{ 'execute': 'block-job-complete', 'arguments': { 'device': 'virtio0' } }
+{ 'execute': 'block-job-complete',
+                                'arguments': {
+                                                'device': 'virtio0'
+                                              }
+                   }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "virtio0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "virtio0"}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off co
 
 === Performing Live Snapshot 2 ===
 
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp2.IMGFMT', 'format': 'IMGFMT' } }
+{ 'execute': 'blockdev-snapshot-sync',
+                                'arguments': {
+                                                'device': 'virtio0',
+                                                'snapshot-file':'TEST_DIR/tmp2.IMGFMT',
+                                                'format': 'IMGFMT'
+                                              }
+                   }
 Formatting 'TEST_DIR/tmp2.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 *** done
diff --git a/tests/qemu-iotests/153.out b/tests/qemu-iotests/153.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/153.out
+++ b/tests/qemu-iotests/153.out
@@ -XXX,XX +XXX,XX @@ _qemu_img_wrapper commit -b TEST_DIR/t.qcow2.b TEST_DIR/t.qcow2.c
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
 Adding drive
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT' } }
 {"return": "OKrn"}
 
 _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512
@@ -XXX,XX +XXX,XX @@ Creating overlay with qemu-img when the guest is running should be allowed
 
 _qemu_img_wrapper create -f qcow2 -b TEST_DIR/t.qcow2 -F qcow2 TEST_DIR/t.qcow2.overlay
 == Closing an image should unlock it ==
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_del d0' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line': 'drive_del d0' } }
 {"return": ""}
 
 _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512
 Adding two and closing one
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT,readonly=on' } }
+{ 'execute': 'human-monitor-command',
+           'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT,readonly=on' } }
 {"return": "OKrn"}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_add 0 if=none,id=d1,file=TEST_DIR/t.IMGFMT,readonly=on' } }
+{ 'execute': 'human-monitor-command',
+           'arguments': { 'command-line': 'drive_add 0 if=none,id=d1,file=TEST_DIR/t.IMGFMT,readonly=on' } }
 {"return": "OKrn"}
 
 _qemu_img_wrapper info TEST_DIR/t.qcow2
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_del d0' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line': 'drive_del d0' } }
 {"return": ""}
 
 _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512
 qemu-io: can't open device TEST_DIR/t.qcow2: Failed to get "write" lock
 Is another process using the image [TEST_DIR/t.qcow2]?
 Closing the other
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_del d1' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line': 'drive_del d1' } }
 {"return": ""}
 
 _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512
diff --git a/tests/qemu-iotests/156.out b/tests/qemu-iotests/156.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/156.out
+++ b/tests/qemu-iotests/156.out
@@ -XXX,XX +XXX,XX @@ wrote 196608/196608 bytes at offset 65536
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
 Formatting 'TEST_DIR/t.IMGFMT.overlay', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'source', 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', 'format': 'IMGFMT', 'mode': 'existing' } }
+{ 'execute': 'blockdev-snapshot-sync',
+       'arguments': { 'device': 'source',
+                      'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay',
+                      'format': 'IMGFMT',
+                      'mode': 'existing' } }
 {"return": {}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "write -P 3 128k 128k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io source "write -P 3 128k 128k"' } }
 wrote 131072/131072 bytes at offset 131072
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
 Formatting 'TEST_DIR/t.IMGFMT.target.overlay', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT.target backing_fmt=IMGFMT
-{ 'execute': 'drive-mirror', 'arguments': { 'device': 'source', 'target': 'TEST_DIR/t.IMGFMT.target.overlay', 'mode': 'existing', 'sync': 'top' } }
+{ 'execute': 'drive-mirror',
+       'arguments': { 'device': 'source',
+                      'target': 'TEST_DIR/t.IMGFMT.target.overlay',
+                      'mode': 'existing',
+                      'sync': 'top' } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "source"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "source"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "source"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "source", "len": 131072, "offset": 131072, "speed": 0, "type": "mirror"}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "write -P 4 192k 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io source "write -P 4 192k 64k"' } }
 wrote 65536/65536 bytes at offset 196608
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'block-job-complete', 'arguments': { 'device': 'source' } }
+{ 'execute': 'block-job-complete',
+       'arguments': { 'device': 'source' } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "source"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "source"}}
@@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 196608
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "source"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "source"}}
 
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 1 0k 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io source "read -P 1 0k 64k"' } }
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 2 64k 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io source "read -P 2 64k 64k"' } }
 read 65536/65536 bytes at offset 65536
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 3 128k 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io source "read -P 3 128k 64k"' } }
 read 65536/65536 bytes at offset 131072
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 4 192k 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io source "read -P 4 192k 64k"' } }
 read 65536/65536 bytes at offset 196608
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
diff --git a/tests/qemu-iotests/161.out b/tests/qemu-iotests/161.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/161.out
+++ b/tests/qemu-iotests/161.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } }
 {"return": ""}
 
 *** Stream and then change an option on the backing file
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'block-stream', 'arguments': { 'device': 'none0', 'base': 'TEST_DIR/t.IMGFMT.base' } }
+{ 'execute': 'block-stream',        'arguments': { 'device': 'none0',
+                      'base': 'TEST_DIR/t.IMGFMT.base' } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "none0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "none0"}}
 {"return": {}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "none0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "none0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "none0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "stream"}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.int', fmt=IMGFMT size=1048576 backing_file=TEST_DI
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT.int backing_fmt=IMGFMT
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'block-commit', 'arguments': { 'device': 'none0', 'top': 'TEST_DIR/t.IMGFMT.int' } }
+{ 'execute': 'block-commit',        'arguments': { 'device': 'none0',
+                      'top': 'TEST_DIR/t.IMGFMT.int' } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "none0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "none0"}}
 {"return": {}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "none0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "none0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "none0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}}
diff --git a/tests/qemu-iotests/173.out b/tests/qemu-iotests/173.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/173.out
+++ b/tests/qemu-iotests/173.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/image.snp1', fmt=IMGFMT size=104857600
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'arguments': { 'device': 'disk2', 'format': 'IMGFMT', 'mode': 'existing', 'snapshot-file': 'TEST_DIR/image.snp1', 'snapshot-node-name': 'snp1' }, 'execute': 'blockdev-snapshot-sync' }
+{ 'arguments': {
+                        'device': 'disk2',
+                        'format': 'IMGFMT',
+                        'mode': 'existing',
+                        'snapshot-file': 'TEST_DIR/image.snp1',
+                        'snapshot-node-name': 'snp1'
+                     },
+                     'execute': 'blockdev-snapshot-sync'
+                   }
 {"return": {}}
-{ 'arguments': { 'backing-file': 'image.base', 'device': 'disk2', 'image-node-name': 'snp1' }, 'execute': 'change-backing-file' }
+{ 'arguments': {
+                        'backing-file': 'image.base',
+                        'device': 'disk2',
+                        'image-node-name': 'snp1'
+                     },
+                     'execute': 'change-backing-file'
+                   }
 {"return": {}}
-{ 'arguments': { 'base': 'TEST_DIR/image.base', 'device': 'disk2' }, 'execute': 'block-stream' }
+{ 'arguments': {
+                        'base': 'TEST_DIR/image.base',
+                        'device': 'disk2'
+                      },
+                      'execute': 'block-stream'
+                   }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk2"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk2"}}
 {"return": {}}
diff --git a/tests/qemu-iotests/182.out b/tests/qemu-iotests/182.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/182.out
+++ b/tests/qemu-iotests/182.out
@@ -XXX,XX +XXX,XX @@ Is another process using the image [TEST_DIR/t.qcow2]?
 
 {'execute': 'qmp_capabilities'}
 {"return": {}}
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'node0', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } }
-{"return": {}}
-{'execute': 'blockdev-snapshot-sync', 'arguments': { 'node-name': 'node0', 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', 'snapshot-node-name': 'node1' } }
+{'execute': 'blockdev-add',
+      'arguments': {
+          'node-name': 'node0',
+          'driver': 'file',
+          'filename': 'TEST_DIR/t.IMGFMT',
+          'locking': 'on'
+          } }
+{"return": {}}
+{'execute': 'blockdev-snapshot-sync',
+      'arguments': {
+          'node-name': 'node0',
+          'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay',
+          'snapshot-node-name': 'node1'
+      } }
 Formatting 'TEST_DIR/t.qcow2.overlay', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=197120 backing_file=TEST_DIR/t.qcow2 backing_fmt=file lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{'execute': 'blockdev-add', 'arguments': { 'node-name': 'node1', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } }
-{"return": {}}
-{'execute': 'nbd-server-start', 'arguments': { 'addr': { 'type': 'unix', 'data': { 'path': 'SOCK_DIR/nbd.socket' } } } }
-{"return": {}}
-{'execute': 'nbd-server-add', 'arguments': { 'device': 'node1' } }
+{'execute': 'blockdev-add',
+      'arguments': {
+          'node-name': 'node1',
+          'driver': 'file',
+          'filename': 'TEST_DIR/t.IMGFMT',
+          'locking': 'on'
+          } }
+{"return": {}}
+{'execute': 'nbd-server-start',
+      'arguments': {
+          'addr': {
+              'type': 'unix',
+              'data': {
+                  'path': 'SOCK_DIR/nbd.socket'
+              } } } }
+{"return": {}}
+{'execute': 'nbd-server-add',
+      'arguments': {
+          'device': 'node1'
+      } }
 {"return": {}}
 
 === Testing failure to loosen restrictions ===
diff --git a/tests/qemu-iotests/183.out b/tests/qemu-iotests/183.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/183.out
+++ b/tests/qemu-iotests/183.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.dest', fmt=IMGFMT size=67108864
 
 === Write something on the source ===
 
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write -P 0x55 0 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io disk "write -P 0x55 0 64k"' } }
 wrote 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "read -P 0x55 0 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io disk "read -P 0x55 0 64k"' } }
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
 
 === Do block migration to destination ===
 
-{ 'execute': 'migrate', 'arguments': { 'uri': 'unix:SOCK_DIR/migrate', 'blk': true } }
+{ 'execute': 'migrate',
+       'arguments': { 'uri': 'unix:SOCK_DIR/migrate', 'blk': true } }
 {"return": {}}
 { 'execute': 'query-status' }
 {"return": {"status": "postmigrate", "singlestep": false, "running": false}}
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0
 { 'execute': 'query-status' }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "RESUME"}
 {"return": {"status": "running", "singlestep": false, "running": true}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "read -P 0x55 0 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io disk "read -P 0x55 0 64k"' } }
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write -P 0x66 1M 64k"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io disk "write -P 0x66 1M 64k"' } }
 wrote 65536/65536 bytes at offset 1048576
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
diff --git a/tests/qemu-iotests/185.out b/tests/qemu-iotests/185.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/185.out
+++ b/tests/qemu-iotests/185.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
 
 === Creating backing chain ===
 
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT.mid', 'format': 'IMGFMT', 'mode': 'absolute-paths' } }
+{ 'execute': 'blockdev-snapshot-sync',
+       'arguments': { 'device': 'disk',
+                      'snapshot-file': 'TEST_DIR/t.IMGFMT.mid',
+                      'format': 'IMGFMT',
+                      'mode': 'absolute-paths' } }
 Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
-{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write 0 4M"' } }
+{ 'execute': 'human-monitor-command',
+       'arguments': { 'command-line':
+                      'qemu-io disk "write 0 4M"' } }
 wrote 4194304/4194304 bytes at offset 0
 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}
-{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'absolute-paths' } }
+{ 'execute': 'blockdev-snapshot-sync',
+       'arguments': { 'device': 'disk',
+                      'snapshot-file': 'TEST_DIR/t.IMGFMT',
+                      'format': 'IMGFMT',
+                      'mode': 'absolute-paths' } }
 Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16
 {"return": {}}
 
 === Start commit job and exit qemu ===
 
-{ 'execute': 'block-commit', 'arguments': { 'device': 'disk', 'base':'TEST_DIR/t.IMGFMT.base', 'top': 'TEST_DIR/t.IMGFMT.mid', 'speed': 65536 } }
+{ 'execute': 'block-commit',
+       'arguments': { 'device': 'disk',
+                      'base':'TEST_DIR/t.IMGFMT.base',
+                      'top': 'TEST_DIR/t.IMGFMT.mid',
+                      'speed': 65536 } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off comp
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'block-commit', 'arguments': { 'device': 'disk', 'base':'TEST_DIR/t.IMGFMT.base', 'speed': 65536 } }
+{ 'execute': 'block-commit',
+       'arguments': { 'device': 'disk',
+                      'base':'TEST_DIR/t.IMGFMT.base',
+                      'speed': 65536 } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off comp
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'drive-mirror', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } }
+{ 'execute': 'drive-mirror',
+       'arguments': { 'device': 'disk',
+                      'target': 'TEST_DIR/t.IMGFMT.copy',
+                      'format': 'IMGFMT',
+                      'sync': 'full',
+                      'speed': 65536 } }
 Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'drive-backup', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } }
+{ 'execute': 'drive-backup',
+       'arguments': { 'device': 'disk',
+                      'target': 'TEST_DIR/t.IMGFMT.copy',
+                      'format': 'IMGFMT',
+                      'sync': 'full',
+                      'speed': 65536 } }
 Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{ 'execute': 'block-stream', 'arguments': { 'device': 'disk', 'speed': 65536 } }
+{ 'execute': 'block-stream',
+       'arguments': { 'device': 'disk',
+                      'speed': 65536 } }
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}}
 {"return": {}}
diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/191.out
+++ b/tests/qemu-iotests/191.out
@@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576
 
 === Perform commit job ===
 
-{ 'execute': 'block-commit', 'arguments': { 'job-id': 'commit0', 'device': 'top', 'base':'TEST_DIR/t.IMGFMT.base', 'top': 'TEST_DIR/t.IMGFMT.mid' } }
+{ 'execute': 'block-commit',
+       'arguments': { 'job-id': 'commit0',
+                      'device': 'top',
+                      'base':'TEST_DIR/t.IMGFMT.base',
+                      'top': 'TEST_DIR/t.IMGFMT.mid' } }
 {
     "timestamp": {
         "seconds":  TIMESTAMP,
@@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576
 
 === Perform commit job ===
 
-{ 'execute': 'block-commit', 'arguments': { 'job-id': 'commit0', 'device': 'top', 'base':'TEST_DIR/t.IMGFMT.base', 'top': 'TEST_DIR/t.IMGFMT.mid' } }
+{ 'execute': 'block-commit',
+       'arguments': { 'job-id': 'commit0',
+                      'device': 'top',
+                      'base':'TEST_DIR/t.IMGFMT.base',
+                      'top': 'TEST_DIR/t.IMGFMT.mid' } }
 {
     "timestamp": {
         "seconds":  TIMESTAMP,
diff --git a/tests/qemu-iotests/223.out b/tests/qemu-iotests/223.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/223.out
+++ b/tests/qemu-iotests/223.out
@@ -XXX,XX +XXX,XX @@ wrote 2097152/2097152 bytes at offset 2097152
 
 {"execute":"qmp_capabilities"}
 {"return": {}}
-{"execute":"blockdev-add", "arguments":{"driver":"IMGFMT", "node-name":"n", "file":{"driver":"file", "filename":"TEST_DIR/t.IMGFMT"}}}
+{"execute":"blockdev-add",
+  "arguments":{"driver":"IMGFMT", "node-name":"n",
+    "file":{"driver":"file", "filename":"TEST_DIR/t.IMGFMT"}}}
 {"return": {}}
-{"execute":"block-dirty-bitmap-disable", "arguments":{"node":"n", "name":"b"}}
+{"execute":"block-dirty-bitmap-disable",
+  "arguments":{"node":"n", "name":"b"}}
 {"return": {}}
 
 === Set up NBD with normal access ===
 
-{"execute":"nbd-server-add", "arguments":{"device":"n"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n"}}
 {"error": {"class": "GenericError", "desc": "NBD server not running"}}
-{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd"}}}}
+{"execute":"nbd-server-start",
+  "arguments":{"addr":{"type":"unix",
+    "data":{"path":"SOCK_DIR/nbd"}}}}
 {"return": {}}
-{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd1"}}}}
+{"execute":"nbd-server-start",
+  "arguments":{"addr":{"type":"unix",
+    "data":{"path":"SOCK_DIR/nbd1"}}}}
 {"error": {"class": "GenericError", "desc": "NBD server already running"}}
 exports available: 0
-{"execute":"nbd-server-add", "arguments":{"device":"n", "bitmap":"b"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "bitmap":"b"}}
 {"return": {}}
-{"execute":"nbd-server-add", "arguments":{"device":"nosuch"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"nosuch"}}
 {"error": {"class": "GenericError", "desc": "Cannot find device=nosuch nor node_name=nosuch"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n"}}
 {"error": {"class": "GenericError", "desc": "Block export id 'n' is already in use"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b2"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "name":"n2",
+  "bitmap":"b2"}}
 {"error": {"class": "GenericError", "desc": "Enabled bitmap 'b2' incompatible with readonly export"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b3"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "name":"n2",
+  "bitmap":"b3"}}
 {"error": {"class": "GenericError", "desc": "Bitmap 'b3' is not found"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "writable":true, "description":"some text", "bitmap":"b2"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "name":"n2", "writable":true,
+  "description":"some text", "bitmap":"b2"}}
 {"return": {}}
 exports available: 2
  export: 'n'
@@ -XXX,XX +XXX,XX @@ read 2097152/2097152 bytes at offset 2097152
 
 === End qemu NBD server ===
 
-{"execute":"nbd-server-remove", "arguments":{"name":"n"}}
+{"execute":"nbd-server-remove",
+  "arguments":{"name":"n"}}
 {"return": {}}
-{"execute":"nbd-server-remove", "arguments":{"name":"n2"}}
+{"execute":"nbd-server-remove",
+  "arguments":{"name":"n2"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n"}}
 {"return": {}}
-{"execute":"nbd-server-remove", "arguments":{"name":"n2"}}
+{"execute":"nbd-server-remove",
+  "arguments":{"name":"n2"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n2"}}
 {"error": {"class": "GenericError", "desc": "Export 'n2' is not found"}}
 {"execute":"nbd-server-stop"}
@@ -XXX,XX +XXX,XX @@ read 2097152/2097152 bytes at offset 2097152
 
 === Set up NBD with iothread access ===
 
-{"execute":"x-blockdev-set-iothread", "arguments":{"node-name":"n", "iothread":"io0"}}
+{"execute":"x-blockdev-set-iothread",
+  "arguments":{"node-name":"n", "iothread":"io0"}}
 {"return": {}}
-{"execute":"nbd-server-add", "arguments":{"device":"n"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n"}}
 {"error": {"class": "GenericError", "desc": "NBD server not running"}}
-{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd"}}}}
+{"execute":"nbd-server-start",
+  "arguments":{"addr":{"type":"unix",
+    "data":{"path":"SOCK_DIR/nbd"}}}}
 {"return": {}}
-{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd1"}}}}
+{"execute":"nbd-server-start",
+  "arguments":{"addr":{"type":"unix",
+    "data":{"path":"SOCK_DIR/nbd1"}}}}
 {"error": {"class": "GenericError", "desc": "NBD server already running"}}
 exports available: 0
-{"execute":"nbd-server-add", "arguments":{"device":"n", "bitmap":"b"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "bitmap":"b"}}
 {"return": {}}
-{"execute":"nbd-server-add", "arguments":{"device":"nosuch"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"nosuch"}}
 {"error": {"class": "GenericError", "desc": "Cannot find device=nosuch nor node_name=nosuch"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n"}}
 {"error": {"class": "GenericError", "desc": "Block export id 'n' is already in use"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b2"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "name":"n2",
+  "bitmap":"b2"}}
 {"error": {"class": "GenericError", "desc": "Enabled bitmap 'b2' incompatible with readonly export"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b3"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "name":"n2",
+  "bitmap":"b3"}}
 {"error": {"class": "GenericError", "desc": "Bitmap 'b3' is not found"}}
-{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "writable":true, "description":"some text", "bitmap":"b2"}}
+{"execute":"nbd-server-add",
+  "arguments":{"device":"n", "name":"n2", "writable":true,
+  "description":"some text", "bitmap":"b2"}}
 {"return": {}}
 exports available: 2
  export: 'n'
@@ -XXX,XX +XXX,XX @@ read 2097152/2097152 bytes at offset 2097152
 
 === End qemu NBD server ===
 
-{"execute":"nbd-server-remove", "arguments":{"name":"n"}}
+{"execute":"nbd-server-remove",
+  "arguments":{"name":"n"}}
 {"return": {}}
-{"execute":"nbd-server-remove", "arguments":{"name":"n2"}}
+{"execute":"nbd-server-remove",
+  "arguments":{"name":"n2"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n"}}
 {"return": {}}
-{"execute":"nbd-server-remove", "arguments":{"name":"n2"}}
+{"execute":"nbd-server-remove",
+  "arguments":{"name":"n2"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n2"}}
 {"error": {"class": "GenericError", "desc": "Export 'n2' is not found"}}
 {"execute":"nbd-server-stop"}
diff --git a/tests/qemu-iotests/229.out b/tests/qemu-iotests/229.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/229.out
+++ b/tests/qemu-iotests/229.out
@@ -XXX,XX +XXX,XX @@ wrote 2097152/2097152 bytes at offset 0
 
 === Starting drive-mirror, causing error & stop  ===
 
-{'execute': 'drive-mirror', 'arguments': {'device': 'testdisk', 'format': 'IMGFMT', 'target': 'blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT.dest', 'sync': 'full', 'mode': 'existing', 'on-source-error': 'stop', 'on-target-error': 'stop' }}
+{'execute': 'drive-mirror',
+                 'arguments': {'device': 'testdisk',
+                               'format': 'IMGFMT',
+                               'target': 'blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT.dest',
+                               'sync':   'full',
+                               'mode':   'existing',
+                               'on-source-error': 'stop',
+                               'on-target-error': 'stop' }}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "testdisk"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "testdisk"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ wrote 2097152/2097152 bytes at offset 0
 
 === Force cancel job paused in error state  ===
 
-{'execute': 'block-job-cancel', 'arguments': { 'device': 'testdisk', 'force': true}}
+{'execute': 'block-job-cancel',
+                 'arguments': { 'device': 'testdisk',
+                                'force': true}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "testdisk"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "testdisk"}}
diff --git a/tests/qemu-iotests/249.out b/tests/qemu-iotests/249.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/249.out
+++ b/tests/qemu-iotests/249.out
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.
 
 === Send a write command to a drive opened in read-only mode (1)
 
-{ 'execute': 'human-monitor-command', 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}}
+{ 'execute': 'human-monitor-command',
+       'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}}
 {"return": "Block node is read-onlyrn"}
 
 === Run block-commit on base using an invalid filter node name
 
-{ 'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int', 'filter-node-name': '1234'}}
+{ 'execute': 'block-commit',
+       'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int',
+                     'filter-node-name': '1234'}}
 {"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": "null", "id": "job0"}}
 {"error": {"class": "GenericError", "desc": "Invalid node name"}}
 
 === Send a write command to a drive opened in read-only mode (2)
 
-{ 'execute': 'human-monitor-command', 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}}
+{ 'execute': 'human-monitor-command',
+       'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}}
 {"return": "Block node is read-onlyrn"}
 
 === Run block-commit on base using the default filter node name
 
-{ 'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int'}}
+{ 'execute': 'block-commit',
+       'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int'}}
 {"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"}}
 {"return": {}}
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.
 
 === Send a write command to a drive opened in read-only mode (3)
 
-{ 'execute': 'human-monitor-command', 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}}
+{ 'execute': 'human-monitor-command',
+       'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}}
 {"return": "Block node is read-onlyrn"}
 *** done
diff --git a/tests/qemu-iotests/308.out b/tests/qemu-iotests/308.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/308.out
+++ b/tests/qemu-iotests/308.out
@@ -XXX,XX +XXX,XX @@ wrote 67108864/67108864 bytes at offset 0
 64 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {'execute': 'qmp_capabilities'}
 {"return": {}}
-{'execute': 'blockdev-add', 'arguments': { 'driver': 'file', 'node-name': 'node-protocol', 'filename': 'TEST_DIR/t.IMGFMT' } }
+{'execute': 'blockdev-add',
+      'arguments': {
+          'driver': 'file',
+          'node-name': 'node-protocol',
+          'filename': 'TEST_DIR/t.IMGFMT'
+      } }
 {"return": {}}
-{'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'node-format', 'file': 'node-protocol' } }
+{'execute': 'blockdev-add',
+      'arguments': {
+          'driver': 'IMGFMT',
+          'node-name': 'node-format',
+          'file': 'node-protocol'
+      } }
 {"return": {}}
 
 === Mountpoint not present ===
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-err', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-err',
+              'node-name': 'node-format',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse'
+          } }
 {"error": {"class": "GenericError", "desc": "Failed to stat 'TEST_DIR/t.IMGFMT.fuse': No such file or directory"}}
 
 === Mountpoint is a directory ===
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-err', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-err',
+              'node-name': 'node-format',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse'
+          } }
 {"error": {"class": "GenericError", "desc": "'TEST_DIR/t.IMGFMT.fuse' is not a regular file"}}
 
 === Mountpoint is a regular file ===
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-mp',
+              'node-name': 'node-format',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse'
+          } }
 {"return": {}}
 Images are identical.
 
 === Mount over existing file ===
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-img', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT' } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-img',
+              'node-name': 'node-format',
+              'mountpoint': 'TEST_DIR/t.IMGFMT'
+          } }
 {"return": {}}
 Images are identical.
 
 === Double export ===
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-err', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-err',
+              'node-name': 'node-format',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse'
+          } }
 {"error": {"class": "GenericError", "desc": "There already is a FUSE export on 'TEST_DIR/t.IMGFMT.fuse'"}}
 
 === Remove export ===
 virtual size: 64 MiB (67108864 bytes)
-{'execute': 'block-export-del', 'arguments': { 'id': 'export-mp' } }
+{'execute': 'block-export-del',
+          'arguments': {
+              'id': 'export-mp'
+          } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-mp"}}
 virtual size: 0 B (0 bytes)
 
 === Writable export ===
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-mp',
+              'node-name': 'node-format',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true
+          } }
 {"return": {}}
 write failed: Permission denied
 wrote 65536/65536 bytes at offset 1048576
@@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 === Resizing exports ===
-{'execute': 'block-export-del', 'arguments': { 'id': 'export-mp' } }
+{'execute': 'block-export-del',
+          'arguments': {
+              'id': 'export-mp'
+          } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-mp"}}
-{'execute': 'block-export-del', 'arguments': { 'id': 'export-img' } }
+{'execute': 'block-export-del',
+          'arguments': {
+              'id': 'export-img'
+          } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-img"}}
-{'execute': 'blockdev-del', 'arguments': { 'node-name': 'node-format' } }
+{'execute': 'blockdev-del',
+      'arguments': {
+          'node-name': 'node-format'
+      } }
 {"return": {}}
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-protocol', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-mp',
+              'node-name': 'node-protocol',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true
+          } }
 {"return": {}}
 
 --- Try growing non-growable export ---
@@ -XXX,XX +XXX,XX @@ OK: Post-truncate image size is as expected
 OK: Disk usage grew with fallocate
 
 --- Try growing growable export ---
-{'execute': 'block-export-del', 'arguments': { 'id': 'export-mp' } }
+{'execute': 'block-export-del',
+          'arguments': {
+              'id': 'export-mp'
+          } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-mp"}}
-{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-protocol', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true, 'growable': true } }
+{'execute': 'block-export-add',
+          'arguments': {
+              'type': 'fuse',
+              'id': 'export-mp',
+              'node-name': 'node-protocol',
+              'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true, 'growable': true
+          } }
 {"return": {}}
 65536+0 records in
 65536+0 records out
diff --git a/tests/qemu-iotests/312.out b/tests/qemu-iotests/312.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/312.out
+++ b/tests/qemu-iotests/312.out
@@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 2424832
 
 { 'execute': 'qmp_capabilities' }
 {"return": {}}
-{'execute': 'drive-mirror', 'arguments': {'device': 'virtio0', 'format': 'IMGFMT', 'target': 'TEST_DIR/t.IMGFMT.3', 'sync': 'full', 'mode': 'existing' }}
+{'execute': 'drive-mirror',
+                 'arguments': {'device': 'virtio0',
+                               'format': 'IMGFMT',
+                               'target': 'TEST_DIR/t.IMGFMT.3',
+                               'sync':   'full',
+                               'mode':   'existing' }}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}}
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 10485760, "offset": 10485760, "speed": 0, "type": "mirror"}}
-{ 'execute': 'block-job-complete', 'arguments': { 'device': 'virtio0' } }
+{ 'execute': 'block-job-complete',
+       'arguments': { 'device': 'virtio0' } }
 {"return": {}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "virtio0"}}
 {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "virtio0"}}
diff --git a/tests/qemu-iotests/common.qemu b/tests/qemu-iotests/common.qemu
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.qemu
+++ b/tests/qemu-iotests/common.qemu
@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd()
         count=${qemu_cmd_repeat}
         use_error="no"
     fi
-    # This array element extraction is done to accommodate pathnames with spaces
-    if [ -z "${success_or_failure}" ]; then
-        cmd=${@: 1:${#@}-1}
-        shift $(($# - 1))
-    else
-        cmd=${@: 1:${#@}-2}
-        shift $(($# - 2))
-    fi
+
+    cmd=$1
+    shift
 
     # Display QMP being sent, but not HMP (since HMP already echoes its
     # input back to output); decide based on leading '{'
-- 
2.29.2

The following changes since commit 1214d55d1c41fbab3a9973a05085b8760647e411:

Merge remote-tracking branch 'remotes/nvme/tags/nvme-next-pull-request' into staging (2021-02-09 13:24:37 +0000)

are available in the Git repository at:

https://gitlab.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to eb847c42296497978942f738cd41dc29a35a49b2:

docs: fix Parallels Image "dirty bitmap" section (2021-02-10 09:23:28 +0000)

----------------------------------------------------------------
Pull request

v4:
 * Add PCI_EXPRESS Kconfig dependency to fix s390x in "multi-process: setup PCI
   host bridge for remote device" [Philippe and Thomas]

----------------------------------------------------------------

Denis V. Lunev (1):
  docs: fix Parallels Image "dirty bitmap" section

Elena Ufimtseva (8):
  multi-process: add configure and usage information
  io: add qio_channel_writev_full_all helper
  io: add qio_channel_readv_full_all_eof & qio_channel_readv_full_all
    helpers
  multi-process: define MPQemuMsg format and transmission functions
  multi-process: introduce proxy object
  multi-process: add proxy communication functions
  multi-process: Forward PCI config space acceses to the remote process
  multi-process: perform device reset in the remote process

Jagannathan Raman (11):
  memory: alloc RAM from file at offset
  multi-process: Add config option for multi-process QEMU
  multi-process: setup PCI host bridge for remote device
  multi-process: setup a machine object for remote device process
  multi-process: Initialize message handler in remote device
  multi-process: Associate fd of a PCIDevice with its object
  multi-process: setup memory manager for remote device
  multi-process: PCI BAR read/write handling for proxy & remote
    endpoints
  multi-process: Synchronize remote memory
  multi-process: create IOHUB object to handle irq
  multi-process: Retrieve PCI info from remote process

John G Johnson (1):
  multi-process: add the concept description to
    docs/devel/qemu-multiprocess

Stefan Hajnoczi (6):
  .github: point Repo Lockdown bot to GitLab repo
  gitmodules: use GitLab repos instead of qemu.org
  gitlab-ci: remove redundant GitLab repo URL command
  docs: update README to use GitLab repo URLs
  pc-bios: update mirror URLs to GitLab
  get_maintainer: update repo URL to GitLab

MAINTAINERS                               |  24 +
 README.rst                                |   4 +-
 docs/devel/index.rst                      |   1 +
 docs/devel/multi-process.rst              | 966 ++++++++++++++++++++++
 docs/system/index.rst                     |   1 +
 docs/system/multi-process.rst             |  64 ++
 docs/interop/parallels.txt                |   2 +-
 configure                                 |  10 +
 meson.build                               |   5 +-
 hw/remote/trace.h                         |   1 +
 include/exec/memory.h                     |   2 +
 include/exec/ram_addr.h                   |   4 +-
 include/hw/pci-host/remote.h              |  30 +
 include/hw/pci/pci_ids.h                  |   3 +
 include/hw/remote/iohub.h                 |  42 +
 include/hw/remote/machine.h               |  38 +
 include/hw/remote/memory.h                |  19 +
 include/hw/remote/mpqemu-link.h           |  99 +++
 include/hw/remote/proxy-memory-listener.h |  28 +
 include/hw/remote/proxy.h                 |  48 ++
 include/io/channel.h                      |  78 ++
 include/qemu/mmap-alloc.h                 |   4 +-
 include/sysemu/iothread.h                 |   6 +
 backends/hostmem-memfd.c                  |   2 +-
 hw/misc/ivshmem.c                         |   3 +-
 hw/pci-host/remote.c                      |  75 ++
 hw/remote/iohub.c                         | 119 +++
 hw/remote/machine.c                       |  80 ++
 hw/remote/memory.c                        |  65 ++
 hw/remote/message.c                       | 230 ++++++
 hw/remote/mpqemu-link.c                   | 267 ++++++
 hw/remote/proxy-memory-listener.c         | 227 +++++
 hw/remote/proxy.c                         | 379 +++++++++
 hw/remote/remote-obj.c                    | 203 +++++
 io/channel.c                              | 116 ++-
 iothread.c                                |   6 +
 softmmu/memory.c                          |   3 +-
 softmmu/physmem.c                         |  12 +-
 util/mmap-alloc.c                         |   8 +-
 util/oslib-posix.c                        |   2 +-
 .github/lockdown.yml                      |   8 +-
 .gitlab-ci.yml                            |   1 -
 .gitmodules                               |  44 +-
 Kconfig.host                              |   4 +
 hw/Kconfig                                |   1 +
 hw/meson.build                            |   1 +
 hw/pci-host/Kconfig                       |   3 +
 hw/pci-host/meson.build                   |   1 +
 hw/remote/Kconfig                         |   4 +
 hw/remote/meson.build                     |  13 +
 hw/remote/trace-events                    |   4 +
 pc-bios/README                            |   4 +-
 scripts/get_maintainer.pl                 |   2 +-
 53 files changed, 3296 insertions(+), 70 deletions(-)
 create mode 100644 docs/devel/multi-process.rst
 create mode 100644 docs/system/multi-process.rst
 create mode 100644 hw/remote/trace.h
 create mode 100644 include/hw/pci-host/remote.h
 create mode 100644 include/hw/remote/iohub.h
 create mode 100644 include/hw/remote/machine.h
 create mode 100644 include/hw/remote/memory.h
 create mode 100644 include/hw/remote/mpqemu-link.h
 create mode 100644 include/hw/remote/proxy-memory-listener.h
 create mode 100644 include/hw/remote/proxy.h
 create mode 100644 hw/pci-host/remote.c
 create mode 100644 hw/remote/iohub.c
 create mode 100644 hw/remote/machine.c
 create mode 100644 hw/remote/memory.c
 create mode 100644 hw/remote/message.c
 create mode 100644 hw/remote/mpqemu-link.c
 create mode 100644 hw/remote/proxy-memory-listener.c
 create mode 100644 hw/remote/proxy.c
 create mode 100644 hw/remote/remote-obj.c
 create mode 100644 hw/remote/Kconfig
 create mode 100644 hw/remote/meson.build
 create mode 100644 hw/remote/trace-events

-- 
2.29.2

Use the GitLab repo URL as the main repo location in order to reduce
load on qemu.org.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-id: 20210111115017.156802-2-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 .github/lockdown.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/lockdown.yml b/.github/lockdown.yml
index XXXXXXX..XXXXXXX 100644
--- a/.github/lockdown.yml
+++ b/.github/lockdown.yml
@@ -XXX,XX +XXX,XX @@ issues:
   comment: |
     Thank you for your interest in the QEMU project.
 
-    This repository is a read-only mirror of the project's master
-    repostories hosted on https://git.qemu.org/git/qemu.git.
+    This repository is a read-only mirror of the project's repostories hosted
+    at https://gitlab.com/qemu-project/qemu.git.
     The project does not process issues filed on GitHub.
 
     The project issues are tracked on Launchpad:
@@ -XXX,XX +XXX,XX @@ pulls:
   comment: |
     Thank you for your interest in the QEMU project.
 
-    This repository is a read-only mirror of the project's master
-    repostories hosted on https://git.qemu.org/git/qemu.git.
+    This repository is a read-only mirror of the project's repostories hosted
+    on https://gitlab.com/qemu-project/qemu.git.
     The project does not process merge requests filed on GitHub.
 
     QEMU welcomes contributions of code (either fixing bugs or adding new
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-3-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 .gitmodules | 44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/.gitmodules b/.gitmodules
index XXXXXXX..XXXXXXX 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -XXX,XX +XXX,XX @@
 [submodule "roms/seabios"]
 	path = roms/seabios
-	url = https://git.qemu.org/git/seabios.git/
+	url = https://gitlab.com/qemu-project/seabios.git/
 [submodule "roms/SLOF"]
 	path = roms/SLOF
-	url = https://git.qemu.org/git/SLOF.git
+	url = https://gitlab.com/qemu-project/SLOF.git
 [submodule "roms/ipxe"]
 	path = roms/ipxe
-	url = https://git.qemu.org/git/ipxe.git
+	url = https://gitlab.com/qemu-project/ipxe.git
 [submodule "roms/openbios"]
 	path = roms/openbios
-	url = https://git.qemu.org/git/openbios.git
+	url = https://gitlab.com/qemu-project/openbios.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
-	url = https://git.qemu.org/git/qemu-palcode.git
+	url = https://gitlab.com/qemu-project/qemu-palcode.git
 [submodule "roms/sgabios"]
 	path = roms/sgabios
-	url = https://git.qemu.org/git/sgabios.git
+	url = https://gitlab.com/qemu-project/sgabios.git
 [submodule "dtc"]
 	path = dtc
-	url = https://git.qemu.org/git/dtc.git
+	url = https://gitlab.com/qemu-project/dtc.git
 [submodule "roms/u-boot"]
 	path = roms/u-boot
-	url = https://git.qemu.org/git/u-boot.git
+	url = https://gitlab.com/qemu-project/u-boot.git
 [submodule "roms/skiboot"]
 	path = roms/skiboot
-	url = https://git.qemu.org/git/skiboot.git
+	url = https://gitlab.com/qemu-project/skiboot.git
 [submodule "roms/QemuMacDrivers"]
 	path = roms/QemuMacDrivers
-	url = https://git.qemu.org/git/QemuMacDrivers.git
+	url = https://gitlab.com/qemu-project/QemuMacDrivers.git
 [submodule "ui/keycodemapdb"]
 	path = ui/keycodemapdb
-	url = https://git.qemu.org/git/keycodemapdb.git
+	url = https://gitlab.com/qemu-project/keycodemapdb.git
 [submodule "capstone"]
 	path = capstone
-	url = https://git.qemu.org/git/capstone.git
+	url = https://gitlab.com/qemu-project/capstone.git
 [submodule "roms/seabios-hppa"]
 	path = roms/seabios-hppa
-	url = https://git.qemu.org/git/seabios-hppa.git
+	url = https://gitlab.com/qemu-project/seabios-hppa.git
 [submodule "roms/u-boot-sam460ex"]
 	path = roms/u-boot-sam460ex
-	url = https://git.qemu.org/git/u-boot-sam460ex.git
+	url = https://gitlab.com/qemu-project/u-boot-sam460ex.git
 [submodule "tests/fp/berkeley-testfloat-3"]
 	path = tests/fp/berkeley-testfloat-3
-	url = https://git.qemu.org/git/berkeley-testfloat-3.git
+	url = https://gitlab.com/qemu-project/berkeley-testfloat-3.git
 [submodule "tests/fp/berkeley-softfloat-3"]
 	path = tests/fp/berkeley-softfloat-3
-	url = https://git.qemu.org/git/berkeley-softfloat-3.git
+	url = https://gitlab.com/qemu-project/berkeley-softfloat-3.git
 [submodule "roms/edk2"]
 	path = roms/edk2
-	url = https://git.qemu.org/git/edk2.git
+	url = https://gitlab.com/qemu-project/edk2.git
 [submodule "slirp"]
 	path = slirp
-	url = https://git.qemu.org/git/libslirp.git
+	url = https://gitlab.com/qemu-project/libslirp.git
 [submodule "roms/opensbi"]
 	path = roms/opensbi
-	url = 	https://git.qemu.org/git/opensbi.git
+	url = 	https://gitlab.com/qemu-project/opensbi.git
 [submodule "roms/qboot"]
 	path = roms/qboot
-	url = https://git.qemu.org/git/qboot.git
+	url = https://gitlab.com/qemu-project/qboot.git
 [submodule "meson"]
 	path = meson
-	url = https://git.qemu.org/git/meson.git
+	url = https://gitlab.com/qemu-project/meson.git
 [submodule "roms/vbootrom"]
 	path = roms/vbootrom
-	url = https://git.qemu.org/git/vbootrom.git
+	url = https://gitlab.com/qemu-project/vbootrom.git
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-5-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 README.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.rst b/README.rst
index XXXXXXX..XXXXXXX 100644
--- a/README.rst
+++ b/README.rst
@@ -XXX,XX +XXX,XX @@ The QEMU source code is maintained under the GIT version control system.
 
 .. code-block:: shell
 
-   git clone https://git.qemu.org/git/qemu.git
+   git clone https://gitlab.com/qemu-project/qemu.git
 
 When submitting patches, one common approach is to use 'git
 format-patch' and/or 'git send-email' to format & send the mail to the
@@ -XXX,XX +XXX,XX @@ The QEMU website is also maintained under source control.
 
 .. code-block:: shell
 
-  git clone https://git.qemu.org/git/qemu-web.git
+  git clone https://gitlab.com/qemu-project/qemu-web.git
 
 * `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_
 
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-6-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 pc-bios/README | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pc-bios/README b/pc-bios/README
index XXXXXXX..XXXXXXX 100644
--- a/pc-bios/README
+++ b/pc-bios/README
@@ -XXX,XX +XXX,XX @@
   legacy x86 software to communicate with an attached serial console as
   if a video card were attached.  The master sources reside in a subversion
   repository at http://sgabios.googlecode.com/svn/trunk.  A git mirror is
-  available at https://git.qemu.org/git/sgabios.git.
+  available at https://gitlab.com/qemu-project/sgabios.git.
 
 - The PXE roms come from the iPXE project. Built with BANNER_TIME 0.
   Sources available at http://ipxe.org.  Vendor:Device ID -> ROM mapping:
@@ -XXX,XX +XXX,XX @@
 
 - The u-boot binary for e500 comes from the upstream denx u-boot project where
   it was compiled using the qemu-ppce500 target.
-  A git mirror is available at: https://git.qemu.org/git/u-boot.git
+  A git mirror is available at: https://gitlab.com/qemu-project/u-boot.git
   The hash used to compile the current version is: 2072e72
 
 - Skiboot (https://github.com/open-power/skiboot/) is an OPAL
-- 
2.29.2

qemu.org is running out of bandwidth and the QEMU project is moving
towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org
(they will become mirrors).

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210111115017.156802-7-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 scripts/get_maintainer.pl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index XXXXXXX..XXXXXXX 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -XXX,XX +XXX,XX @@ sub vcs_exists {
 	warn("$P: No supported VCS found.  Add --nogit to options?\n");
 	warn("Using a git repository produces better results.\n");
 	warn("Try latest git repository using:\n");
-	warn("git clone https://git.qemu.org/git/qemu.git\n");
+	warn("git clone https://gitlab.com/qemu-project/qemu.git\n");
 	$printed_novcs = 1;
     }
     return 0;
-- 
2.29.2

From: John G Johnson <john.g.johnson@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 02a68adef99f5df6a380bf8fd7b90948777e411c.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                  |   7 +
 docs/devel/index.rst         |   1 +
 docs/devel/multi-process.rst | 966 +++++++++++++++++++++++++++++++++++
 3 files changed, 974 insertions(+)
 create mode 100644 docs/devel/multi-process.rst

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ S: Maintained
 F: hw/semihosting/
 F: include/hw/semihosting/
 
+Multi-process QEMU
+M: Elena Ufimtseva <elena.ufimtseva@oracle.com>
+M: Jagannathan Raman <jag.raman@oracle.com>
+M: John G Johnson <john.g.johnson@oracle.com>
+S: Maintained
+F: docs/devel/multi-process.rst
+
 Build and test automation
 -------------------------
 Build and test automation
diff --git a/docs/devel/index.rst b/docs/devel/index.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/devel/index.rst
+++ b/docs/devel/index.rst
@@ -XXX,XX +XXX,XX @@ Contents:
    clocks
    qom
    block-coroutine-wrapper
+   multi-process
diff --git a/docs/devel/multi-process.rst b/docs/devel/multi-process.rst
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/docs/devel/multi-process.rst
@@ -XXX,XX +XXX,XX @@
+This is the design document for multi-process QEMU. It does not
+necessarily reflect the status of the current implementation, which
+may lack features or be considerably different from what is described
+in this document. This document is still useful as a description of
+the goals and general direction of this feature.
+
+Please refer to the following wiki for latest details:
+https://wiki.qemu.org/Features/MultiProcessQEMU
+
+Multi-process QEMU
+===================
+
+QEMU is often used as the hypervisor for virtual machines running in the
+Oracle cloud. Since one of the advantages of cloud computing is the
+ability to run many VMs from different tenants in the same cloud
+infrastructure, a guest that compromised its hypervisor could
+potentially use the hypervisor's access privileges to access data it is
+not authorized for.
+
+QEMU can be susceptible to security attacks because it is a large,
+monolithic program that provides many features to the VMs it services.
+Many of these features can be configured out of QEMU, but even a reduced
+configuration QEMU has a large amount of code a guest can potentially
+attack. Separating QEMU reduces the attack surface by aiding to
+limit each component in the system to only access the resources that
+it needs to perform its job.
+
+QEMU services
+-------------
+
+QEMU can be broadly described as providing three main services. One is a
+VM control point, where VMs can be created, migrated, re-configured, and
+destroyed. A second is to emulate the CPU instructions within the VM,
+often accelerated by HW virtualization features such as Intel's VT
+extensions. Finally, it provides IO services to the VM by emulating HW
+IO devices, such as disk and network devices.
+
+A multi-process QEMU
+~~~~~~~~~~~~~~~~~~~~
+
+A multi-process QEMU involves separating QEMU services into separate
+host processes. Each of these processes can be given only the privileges
+it needs to provide its service, e.g., a disk service could be given
+access only to the disk images it provides, and not be allowed to
+access other files, or any network devices. An attacker who compromised
+this service would not be able to use this exploit to access files or
+devices beyond what the disk service was given access to.
+
+A QEMU control process would remain, but in multi-process mode, will
+have no direct interfaces to the VM. During VM execution, it would still
+provide the user interface to hot-plug devices or live migrate the VM.
+
+A first step in creating a multi-process QEMU is to separate IO services
+from the main QEMU program, which would continue to provide CPU
+emulation. i.e., the control process would also be the CPU emulation
+process. In a later phase, CPU emulation could be separated from the
+control process.
+
+Separating IO services
+----------------------
+
+Separating IO services into individual host processes is a good place to
+begin for a couple of reasons. One is the sheer number of IO devices QEMU
+can emulate provides a large surface of interfaces which could potentially
+be exploited, and, indeed, have been a source of exploits in the past.
+Another is the modular nature of QEMU device emulation code provides
+interface points where the QEMU functions that perform device emulation
+can be separated from the QEMU functions that manage the emulation of
+guest CPU instructions. The devices emulated in the separate process are
+referred to as remote devices.
+
+QEMU device emulation
+~~~~~~~~~~~~~~~~~~~~~
+
+QEMU uses an object oriented SW architecture for device emulation code.
+Configured objects are all compiled into the QEMU binary, then objects
+are instantiated by name when used by the guest VM. For example, the
+code to emulate a device named "foo" is always present in QEMU, but its
+instantiation code is only run when the device is included in the target
+VM. (e.g., via the QEMU command line as *-device foo*)
+
+The object model is hierarchical, so device emulation code names its
+parent object (such as "pci-device" for a PCI device) and QEMU will
+instantiate a parent object before calling the device's instantiation
+code.
+
+Current separation models
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In order to separate the device emulation code from the CPU emulation
+code, the device object code must run in a different process. There are
+a couple of existing QEMU features that can run emulation code
+separately from the main QEMU process. These are examined below.
+
+vhost user model
+^^^^^^^^^^^^^^^^
+
+Virtio guest device drivers can be connected to vhost user applications
+in order to perform their IO operations. This model uses special virtio
+device drivers in the guest and vhost user device objects in QEMU, but
+once the QEMU vhost user code has configured the vhost user application,
+mission-mode IO is performed by the application. The vhost user
+application is a daemon process that can be contacted via a known UNIX
+domain socket.
+
+vhost socket
+''''''''''''
+
+As mentioned above, one of the tasks of the vhost device object within
+QEMU is to contact the vhost application and send it configuration
+information about this device instance. As part of the configuration
+process, the application can also be sent other file descriptors over
+the socket, which then can be used by the vhost user application in
+various ways, some of which are described below.
+
+vhost MMIO store acceleration
+'''''''''''''''''''''''''''''
+
+VMs are often run using HW virtualization features via the KVM kernel
+driver. This driver allows QEMU to accelerate the emulation of guest CPU
+instructions by running the guest in a virtual HW mode. When the guest
+executes instructions that cannot be executed by virtual HW mode,
+execution returns to the KVM driver so it can inform QEMU to emulate the
+instructions in SW.
+
+One of the events that can cause a return to QEMU is when a guest device
+driver accesses an IO location. QEMU then dispatches the memory
+operation to the corresponding QEMU device object. In the case of a
+vhost user device, the memory operation would need to be sent over a
+socket to the vhost application. This path is accelerated by the QEMU
+virtio code by setting up an eventfd file descriptor that the vhost
+application can directly receive MMIO store notifications from the KVM
+driver, instead of needing them to be sent to the QEMU process first.
+
+vhost interrupt acceleration
+''''''''''''''''''''''''''''
+
+Another optimization used by the vhost application is the ability to
+directly inject interrupts into the VM via the KVM driver, again,
+bypassing the need to send the interrupt back to the QEMU process first.
+The QEMU virtio setup code configures the KVM driver with an eventfd
+that triggers the device interrupt in the guest when the eventfd is
+written. This irqfd file descriptor is then passed to the vhost user
+application program.
+
+vhost access to guest memory
+''''''''''''''''''''''''''''
+
+The vhost application is also allowed to directly access guest memory,
+instead of needing to send the data as messages to QEMU. This is also
+done with file descriptors sent to the vhost user application by QEMU.
+These descriptors can be passed to ``mmap()`` by the vhost application
+to map the guest address space into the vhost application.
+
+IOMMUs introduce another level of complexity, since the address given to
+the guest virtio device to DMA to or from is not a guest physical
+address. This case is handled by having vhost code within QEMU register
+as a listener for IOMMU mapping changes. The vhost application maintains
+a cache of IOMMMU translations: sending translation requests back to
+QEMU on cache misses, and in turn receiving flush requests from QEMU
+when mappings are purged.
+
+applicability to device separation
+''''''''''''''''''''''''''''''''''
+
+Much of the vhost model can be re-used by separated device emulation. In
+particular, the ideas of using a socket between QEMU and the device
+emulation application, using a file descriptor to inject interrupts into
+the VM via KVM, and allowing the application to ``mmap()`` the guest
+should be re used.
+
+There are, however, some notable differences between how a vhost
+application works and the needs of separated device emulation. The most
+basic is that vhost uses custom virtio device drivers which always
+trigger IO with MMIO stores. A separated device emulation model must
+work with existing IO device models and guest device drivers. MMIO loads
+break vhost store acceleration since they are synchronous - guest
+progress cannot continue until the load has been emulated. By contrast,
+stores are asynchronous, the guest can continue after the store event
+has been sent to the vhost application.
+
+Another difference is that in the vhost user model, a single daemon can
+support multiple QEMU instances. This is contrary to the security regime
+desired, in which the emulation application should only be allowed to
+access the files or devices the VM it's running on behalf of can access.
+#### qemu-io model
+
+Qemu-io is a test harness used to test changes to the QEMU block backend
+object code. (e.g., the code that implements disk images for disk driver
+emulation) Qemu-io is not a device emulation application per se, but it
+does compile the QEMU block objects into a separate binary from the main
+QEMU one. This could be useful for disk device emulation, since its
+emulation applications will need to include the QEMU block objects.
+
+New separation model based on proxy objects
+-------------------------------------------
+
+A different model based on proxy objects in the QEMU program
+communicating with remote emulation programs could provide separation
+while minimizing the changes needed to the device emulation code. The
+rest of this section is a discussion of how a proxy object model would
+work.
+
+Remote emulation processes
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The remote emulation process will run the QEMU object hierarchy without
+modification. The device emulation objects will be also be based on the
+QEMU code, because for anything but the simplest device, it would not be
+a tractable to re-implement both the object model and the many device
+backends that QEMU has.
+
+The processes will communicate with the QEMU process over UNIX domain
+sockets. The processes can be executed either as standalone processes,
+or be executed by QEMU. In both cases, the host backends the emulation
+processes will provide are specified on its command line, as they would
+be for QEMU. For example:
+
+::
+
+    disk-proc -blockdev driver=file,node-name=file0,filename=disk-file0  \
+    -blockdev driver=qcow2,node-name=drive0,file=file0
+
+would indicate process *disk-proc* uses a qcow2 emulated disk named
+*file0* as its backend.
+
+Emulation processes may emulate more than one guest controller. A common
+configuration might be to put all controllers of the same device class
+(e.g., disk, network, etc.) in a single process, so that all backends of
+the same type can be managed by a single QMP monitor.
+
+communication with QEMU
+^^^^^^^^^^^^^^^^^^^^^^^
+
+The first argument to the remote emulation process will be a Unix domain
+socket that connects with the Proxy object. This is a required argument.
+
+::
+
+    disk-proc <socket number> <backend list>
+
+remote process QMP monitor
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Remote emulation processes can be monitored via QMP, similar to QEMU
+itself. The QMP monitor socket is specified the same as for a QEMU
+process:
+
+::
+
+    disk-proc -qmp unix:/tmp/disk-mon,server
+
+can be monitored over the UNIX socket path */tmp/disk-mon*.
+
+QEMU command line
+~~~~~~~~~~~~~~~~~
+
+Each remote device emulated in a remote process on the host is
+represented as a *-device* of type *pci-proxy-dev*. A socket
+sub-option to this option specifies the Unix socket that connects
+to the remote process. An *id* sub-option is required, and it should
+be the same id as used in the remote process.
+
+::
+
+    qemu-system-x86_64 ... -device pci-proxy-dev,id=lsi0,socket=3
+
+can be used to add a device emulated in a remote process
+
+
+QEMU management of remote processes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+QEMU is not aware of the type of type of the remote PCI device. It is
+a pass through device as far as QEMU is concerned.
+
+communication with emulation process
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+primary channel
+'''''''''''''''
+
+The primary channel (referred to as com in the code) is used to bootstrap
+the remote process. It is also used to pass on device-agnostic commands
+like reset.
+
+per-device channels
+'''''''''''''''''''
+
+Each remote device communicates with QEMU using a dedicated communication
+channel. The proxy object sets up this channel using the primary
+channel during its initialization.
+
+QEMU device proxy objects
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+QEMU has an object model based on sub-classes inherited from the
+"object" super-class. The sub-classes that are of interest here are the
+"device" and "bus" sub-classes whose child sub-classes make up the
+device tree of a QEMU emulated system.
+
+The proxy object model will use device proxy objects to replace the
+device emulation code within the QEMU process. These objects will live
+in the same place in the object and bus hierarchies as the objects they
+replace. i.e., the proxy object for an LSI SCSI controller will be a
+sub-class of the "pci-device" class, and will have the same PCI bus
+parent and the same SCSI bus child objects as the LSI controller object
+it replaces.
+
+It is worth noting that the same proxy object is used to mediate with
+all types of remote PCI devices.
+
+object initialization
+^^^^^^^^^^^^^^^^^^^^^
+
+The Proxy device objects are initialized in the exact same manner in
+which any other QEMU device would be initialized.
+
+In addition, the Proxy objects perform the following two tasks:
+- Parses the "socket" sub option and connects to the remote process
+using this channel
+- Uses the "id" sub-option to connect to the emulated device on the
+separate process
+
+class\_init
+'''''''''''
+
+The ``class_init()`` method of a proxy object will, in general behave
+similarly to the object it replaces, including setting any static
+properties and methods needed by the proxy.
+
+instance\_init / realize
+''''''''''''''''''''''''
+
+The ``instance_init()`` and ``realize()`` functions would only need to
+perform tasks related to being a proxy, such are registering its own
+MMIO handlers, or creating a child bus that other proxy devices can be
+attached to later.
+
+Other tasks will be device-specific. For example, PCI device objects
+will initialize the PCI config space in order to make a valid PCI device
+tree within the QEMU process.
+
+address space registration
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Most devices are driven by guest device driver accesses to IO addresses
+or ports. The QEMU device emulation code uses QEMU's memory region
+function calls (such as ``memory_region_init_io()``) to add callback
+functions that QEMU will invoke when the guest accesses the device's
+areas of the IO address space. When a guest driver does access the
+device, the VM will exit HW virtualization mode and return to QEMU,
+which will then lookup and execute the corresponding callback function.
+
+A proxy object would need to mirror the memory region calls the actual
+device emulator would perform in its initialization code, but with its
+own callbacks. When invoked by QEMU as a result of a guest IO operation,
+they will forward the operation to the device emulation process.
+
+PCI config space
+^^^^^^^^^^^^^^^^
+
+PCI devices also have a configuration space that can be accessed by the
+guest driver. Guest accesses to this space is not handled by the device
+emulation object, but by its PCI parent object. Much of this space is
+read-only, but certain registers (especially BAR and MSI-related ones)
+need to be propagated to the emulation process.
+
+PCI parent proxy
+''''''''''''''''
+
+One way to propagate guest PCI config accesses is to create a
+"pci-device-proxy" class that can serve as the parent of a PCI device
+proxy object. This class's parent would be "pci-device" and it would
+override the PCI parent's ``config_read()`` and ``config_write()``
+methods with ones that forward these operations to the emulation
+program.
+
+interrupt receipt
+^^^^^^^^^^^^^^^^^
+
+A proxy for a device that generates interrupts will need to create a
+socket to receive interrupt indications from the emulation process. An
+incoming interrupt indication would then be sent up to its bus parent to
+be injected into the guest. For example, a PCI device object may use
+``pci_set_irq()``.
+
+live migration
+^^^^^^^^^^^^^^
+
+The proxy will register to save and restore any *vmstate* it needs over
+a live migration event. The device proxy does not need to manage the
+remote device's *vmstate*; that will be handled by the remote process
+proxy (see below).
+
+QEMU remote device operation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Generic device operations, such as DMA, will be performed by the remote
+process proxy by sending messages to the remote process.
+
+DMA operations
+^^^^^^^^^^^^^^
+
+DMA operations would be handled much like vhost applications do. One of
+the initial messages sent to the emulation process is a guest memory
+table. Each entry in this table consists of a file descriptor and size
+that the emulation process can ``mmap()`` to directly access guest
+memory, similar to ``vhost_user_set_mem_table()``. Note guest memory
+must be backed by file descriptors, such as when QEMU is given the
+*-mem-path* command line option.
+
+IOMMU operations
+^^^^^^^^^^^^^^^^
+
+When the emulated system includes an IOMMU, the remote process proxy in
+QEMU will need to create a socket for IOMMU requests from the emulation
+process. It will handle those requests with an
+``address_space_get_iotlb_entry()`` call. In order to handle IOMMU
+unmaps, the remote process proxy will also register as a listener on the
+device's DMA address space. When an IOMMU memory region is created
+within the DMA address space, an IOMMU notifier for unmaps will be added
+to the memory region that will forward unmaps to the emulation process
+over the IOMMU socket.
+
+device hot-plug via QMP
+^^^^^^^^^^^^^^^^^^^^^^^
+
+An QMP "device\_add" command can add a device emulated by a remote
+process. It will also have "rid" option to the command, just as the
+*-device* command line option does. The remote process may either be one
+started at QEMU startup, or be one added by the "add-process" QMP
+command described above. In either case, the remote process proxy will
+forward the new device's JSON description to the corresponding emulation
+process.
+
+live migration
+^^^^^^^^^^^^^^
+
+The remote process proxy will also register for live migration
+notifications with ``vmstate_register()``. When called to save state,
+the proxy will send the remote process a secondary socket file
+descriptor to save the remote process's device *vmstate* over. The
+incoming byte stream length and data will be saved as the proxy's
+*vmstate*. When the proxy is resumed on its new host, this *vmstate*
+will be extracted, and a secondary socket file descriptor will be sent
+to the new remote process through which it receives the *vmstate* in
+order to restore the devices there.
+
+device emulation in remote process
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The parts of QEMU that the emulation program will need include the
+object model; the memory emulation objects; the device emulation objects
+of the targeted device, and any dependent devices; and, the device's
+backends. It will also need code to setup the machine environment,
+handle requests from the QEMU process, and route machine-level requests
+(such as interrupts or IOMMU mappings) back to the QEMU process.
+
+initialization
+^^^^^^^^^^^^^^
+
+The process initialization sequence will follow the same sequence
+followed by QEMU. It will first initialize the backend objects, then
+device emulation objects. The JSON descriptions sent by the QEMU process
+will drive which objects need to be created.
+
+-  address spaces
+
+Before the device objects are created, the initial address spaces and
+memory regions must be configured with ``memory_map_init()``. This
+creates a RAM memory region object (*system\_memory*) and an IO memory
+region object (*system\_io*).
+
+-  RAM
+
+RAM memory region creation will follow how ``pc_memory_init()`` creates
+them, but must use ``memory_region_init_ram_from_fd()`` instead of
+``memory_region_allocate_system_memory()``. The file descriptors needed
+will be supplied by the guest memory table from above. Those RAM regions
+would then be added to the *system\_memory* memory region with
+``memory_region_add_subregion()``.
+
+-  PCI
+
+IO initialization will be driven by the JSON descriptions sent from the
+QEMU process. For a PCI device, a PCI bus will need to be created with
+``pci_root_bus_new()``, and a PCI memory region will need to be created
+and added to the *system\_memory* memory region with
+``memory_region_add_subregion_overlap()``. The overlap version is
+required for architectures where PCI memory overlaps with RAM memory.
+
+MMIO handling
+^^^^^^^^^^^^^
+
+The device emulation objects will use ``memory_region_init_io()`` to
+install their MMIO handlers, and ``pci_register_bar()`` to associate
+those handlers with a PCI BAR, as they do within QEMU currently.
+
+In order to use ``address_space_rw()`` in the emulation process to
+handle MMIO requests from QEMU, the PCI physical addresses must be the
+same in the QEMU process and the device emulation process. In order to
+accomplish that, guest BAR programming must also be forwarded from QEMU
+to the emulation process.
+
+interrupt injection
+^^^^^^^^^^^^^^^^^^^
+
+When device emulation wants to inject an interrupt into the VM, the
+request climbs the device's bus object hierarchy until the point where a
+bus object knows how to signal the interrupt to the guest. The details
+depend on the type of interrupt being raised.
+
+-  PCI pin interrupts
+
+On x86 systems, there is an emulated IOAPIC object attached to the root
+PCI bus object, and the root PCI object forwards interrupt requests to
+it. The IOAPIC object, in turn, calls the KVM driver to inject the
+corresponding interrupt into the VM. The simplest way to handle this in
+an emulation process would be to setup the root PCI bus driver (via
+``pci_bus_irqs()``) to send a interrupt request back to the QEMU
+process, and have the device proxy object reflect it up the PCI tree
+there.
+
+-  PCI MSI/X interrupts
+
+PCI MSI/X interrupts are implemented in HW as DMA writes to a
+CPU-specific PCI address. In QEMU on x86, a KVM APIC object receives
+these DMA writes, then calls into the KVM driver to inject the interrupt
+into the VM. A simple emulation process implementation would be to send
+the MSI DMA address from QEMU as a message at initialization, then
+install an address space handler at that address which forwards the MSI
+message back to QEMU.
+
+DMA operations
+^^^^^^^^^^^^^^
+
+When a emulation object wants to DMA into or out of guest memory, it
+first must use dma\_memory\_map() to convert the DMA address to a local
+virtual address. The emulation process memory region objects setup above
+will be used to translate the DMA address to a local virtual address the
+device emulation code can access.
+
+IOMMU
+^^^^^
+
+When an IOMMU is in use in QEMU, DMA translation uses IOMMU memory
+regions to translate the DMA address to a guest physical address before
+that physical address can be translated to a local virtual address. The
+emulation process will need similar functionality.
+
+-  IOTLB cache
+
+The emulation process will maintain a cache of recent IOMMU translations
+(the IOTLB). When the translate() callback of an IOMMU memory region is
+invoked, the IOTLB cache will be searched for an entry that will map the
+DMA address to a guest PA. On a cache miss, a message will be sent back
+to QEMU requesting the corresponding translation entry, which be both be
+used to return a guest address and be added to the cache.
+
+-  IOTLB purge
+
+The IOMMU emulation will also need to act on unmap requests from QEMU.
+These happen when the guest IOMMU driver purges an entry from the
+guest's translation table.
+
+live migration
+^^^^^^^^^^^^^^
+
+When a remote process receives a live migration indication from QEMU, it
+will set up a channel using the received file descriptor with
+``qio_channel_socket_new_fd()``. This channel will be used to create a
+*QEMUfile* that can be passed to ``qemu_save_device_state()`` to send
+the process's device state back to QEMU. This method will be reversed on
+restore - the channel will be passed to ``qemu_loadvm_state()`` to
+restore the device state.
+
+Accelerating device emulation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The messages that are required to be sent between QEMU and the emulation
+process can add considerable latency to IO operations. The optimizations
+described below attempt to ameliorate this effect by allowing the
+emulation process to communicate directly with the kernel KVM driver.
+The KVM file descriptors created would be passed to the emulation process
+via initialization messages, much like the guest memory table is done.
+#### MMIO acceleration
+
+Vhost user applications can receive guest virtio driver stores directly
+from KVM. The issue with the eventfd mechanism used by vhost user is
+that it does not pass any data with the event indication, so it cannot
+handle guest loads or guest stores that carry store data. This concept
+could, however, be expanded to cover more cases.
+
+The expanded idea would require a new type of KVM device:
+*KVM\_DEV\_TYPE\_USER*. This device has two file descriptors: a master
+descriptor that QEMU can use for configuration, and a slave descriptor
+that the emulation process can use to receive MMIO notifications. QEMU
+would create both descriptors using the KVM driver, and pass the slave
+descriptor to the emulation process via an initialization message.
+
+data structures
+^^^^^^^^^^^^^^^
+
+-  guest physical range
+
+The guest physical range structure describes the address range that a
+device will respond to. It includes the base and length of the range, as
+well as which bus the range resides on (e.g., on an x86machine, it can
+specify whether the range refers to memory or IO addresses).
+
+A device can have multiple physical address ranges it responds to (e.g.,
+a PCI device can have multiple BARs), so the structure will also include
+an enumerated identifier to specify which of the device's ranges is
+being referred to.
+
++--------+----------------------------+
+| Name   | Description                |
++========+============================+
+| addr   | range base address         |
++--------+----------------------------+
+| len    | range length               |
++--------+----------------------------+
+| bus    | addr type (memory or IO)   |
++--------+----------------------------+
+| id     | range ID (e.g., PCI BAR)   |
++--------+----------------------------+
+
+-  MMIO request structure
+
+This structure describes an MMIO operation. It includes which guest
+physical range the MMIO was within, the offset within that range, the
+MMIO type (e.g., load or store), and its length and data. It also
+includes a sequence number that can be used to reply to the MMIO, and
+the CPU that issued the MMIO.
+
++----------+------------------------+
+| Name     | Description            |
++==========+========================+
+| rid      | range MMIO is within   |
++----------+------------------------+
+| offset   | offset withing *rid*   |
++----------+------------------------+
+| type     | e.g., load or store    |
++----------+------------------------+
+| len      | MMIO length            |
++----------+------------------------+
+| data     | store data             |
++----------+------------------------+
+| seq      | sequence ID            |
++----------+------------------------+
+
+-  MMIO request queues
+
+MMIO request queues are FIFO arrays of MMIO request structures. There
+are two queues: pending queue is for MMIOs that haven't been read by the
+emulation program, and the sent queue is for MMIOs that haven't been
+acknowledged. The main use of the second queue is to validate MMIO
+replies from the emulation program.
+
+-  scoreboard
+
+Each CPU in the VM is emulated in QEMU by a separate thread, so multiple
+MMIOs may be waiting to be consumed by an emulation program and multiple
+threads may be waiting for MMIO replies. The scoreboard would contain a
+wait queue and sequence number for the per-CPU threads, allowing them to
+be individually woken when the MMIO reply is received from the emulation
+program. It also tracks the number of posted MMIO stores to the device
+that haven't been replied to, in order to satisfy the PCI constraint
+that a load to a device will not complete until all previous stores to
+that device have been completed.
+
+-  device shadow memory
+
+Some MMIO loads do not have device side-effects. These MMIOs can be
+completed without sending a MMIO request to the emulation program if the
+emulation program shares a shadow image of the device's memory image
+with the KVM driver.
+
+The emulation program will ask the KVM driver to allocate memory for the
+shadow image, and will then use ``mmap()`` to directly access it. The
+emulation program can control KVM access to the shadow image by sending
+KVM an access map telling it which areas of the image have no
+side-effects (and can be completed immediately), and which require a
+MMIO request to the emulation program. The access map can also inform
+the KVM drive which size accesses are allowed to the image.
+
+master descriptor
+^^^^^^^^^^^^^^^^^
+
+The master descriptor is used by QEMU to configure the new KVM device.
+The descriptor would be returned by the KVM driver when QEMU issues a
+*KVM\_CREATE\_DEVICE* ``ioctl()`` with a *KVM\_DEV\_TYPE\_USER* type.
+
+KVM\_DEV\_TYPE\_USER device ops
+
+
+The *KVM\_DEV\_TYPE\_USER* operations vector will be registered by a
+``kvm_register_device_ops()`` call when the KVM system in initialized by
+``kvm_init()``. These device ops are called by the KVM driver when QEMU
+executes certain ``ioctl()`` operations on its KVM file descriptor. They
+include:
+
+-  create
+
+This routine is called when QEMU issues a *KVM\_CREATE\_DEVICE*
+``ioctl()`` on its per-VM file descriptor. It will allocate and
+initialize a KVM user device specific data structure, and assign the
+*kvm\_device* private field to it.
+
+-  ioctl
+
+This routine is invoked when QEMU issues an ``ioctl()`` on the master
+descriptor. The ``ioctl()`` commands supported are defined by the KVM
+device type. *KVM\_DEV\_TYPE\_USER* ones will need several commands:
+
+*KVM\_DEV\_USER\_SLAVE\_FD* creates the slave file descriptor that will
+be passed to the device emulation program. Only one slave can be created
+by each master descriptor. The file operations performed by this
+descriptor are described below.
+
+The *KVM\_DEV\_USER\_PA\_RANGE* command configures a guest physical
+address range that the slave descriptor will receive MMIO notifications
+for. The range is specified by a guest physical range structure
+argument. For buses that assign addresses to devices dynamically, this
+command can be executed while the guest is running, such as the case
+when a guest changes a device's PCI BAR registers.
+
+*KVM\_DEV\_USER\_PA\_RANGE* will use ``kvm_io_bus_register_dev()`` to
+register *kvm\_io\_device\_ops* callbacks to be invoked when the guest
+performs a MMIO operation within the range. When a range is changed,
+``kvm_io_bus_unregister_dev()`` is used to remove the previous
+instantiation.
+
+*KVM\_DEV\_USER\_TIMEOUT* will configure a timeout value that specifies
+how long KVM will wait for the emulation process to respond to a MMIO
+indication.
+
+-  destroy
+
+This routine is called when the VM instance is destroyed. It will need
+to destroy the slave descriptor; and free any memory allocated by the
+driver, as well as the *kvm\_device* structure itself.
+
+slave descriptor
+^^^^^^^^^^^^^^^^
+
+The slave descriptor will have its own file operations vector, which
+responds to system calls on the descriptor performed by the device
+emulation program.
+
+-  read
+
+A read returns any pending MMIO requests from the KVM driver as MMIO
+request structures. Multiple structures can be returned if there are
+multiple MMIO operations pending. The MMIO requests are moved from the
+pending queue to the sent queue, and if there are threads waiting for
+space in the pending to add new MMIO operations, they will be woken
+here.
+
+-  write
+
+A write also consists of a set of MMIO requests. They are compared to
+the MMIO requests in the sent queue. Matches are removed from the sent
+queue, and any threads waiting for the reply are woken. If a store is
+removed, then the number of posted stores in the per-CPU scoreboard is
+decremented. When the number is zero, and a non side-effect load was
+waiting for posted stores to complete, the load is continued.
+
+-  ioctl
+
+There are several ioctl()s that can be performed on the slave
+descriptor.
+
+A *KVM\_DEV\_USER\_SHADOW\_SIZE* ``ioctl()`` causes the KVM driver to
+allocate memory for the shadow image. This memory can later be
+``mmap()``\ ed by the emulation process to share the emulation's view of
+device memory with the KVM driver.
+
+A *KVM\_DEV\_USER\_SHADOW\_CTRL* ``ioctl()`` controls access to the
+shadow image. It will send the KVM driver a shadow control map, which
+specifies which areas of the image can complete guest loads without
+sending the load request to the emulation program. It will also specify
+the size of load operations that are allowed.
+
+-  poll
+
+An emulation program will use the ``poll()`` call with a *POLLIN* flag
+to determine if there are MMIO requests waiting to be read. It will
+return if the pending MMIO request queue is not empty.
+
+-  mmap
+
+This call allows the emulation program to directly access the shadow
+image allocated by the KVM driver. As device emulation updates device
+memory, changes with no side-effects will be reflected in the shadow,
+and the KVM driver can satisfy guest loads from the shadow image without
+needing to wait for the emulation program.
+
+kvm\_io\_device ops
+^^^^^^^^^^^^^^^^^^^
+
+Each KVM per-CPU thread can handle MMIO operation on behalf of the guest
+VM. KVM will use the MMIO's guest physical address to search for a
+matching *kvm\_io\_device* to see if the MMIO can be handled by the KVM
+driver instead of exiting back to QEMU. If a match is found, the
+corresponding callback will be invoked.
+
+-  read
+
+This callback is invoked when the guest performs a load to the device.
+Loads with side-effects must be handled synchronously, with the KVM
+driver putting the QEMU thread to sleep waiting for the emulation
+process reply before re-starting the guest. Loads that do not have
+side-effects may be optimized by satisfying them from the shadow image,
+if there are no outstanding stores to the device by this CPU. PCI memory
+ordering demands that a load cannot complete before all older stores to
+the same device have been completed.
+
+-  write
+
+Stores can be handled asynchronously unless the pending MMIO request
+queue is full. In this case, the QEMU thread must sleep waiting for
+space in the queue. Stores will increment the number of posted stores in
+the per-CPU scoreboard, in order to implement the PCI ordering
+constraint above.
+
+interrupt acceleration
+^^^^^^^^^^^^^^^^^^^^^^
+
+This performance optimization would work much like a vhost user
+application does, where the QEMU process sets up *eventfds* that cause
+the device's corresponding interrupt to be triggered by the KVM driver.
+These irq file descriptors are sent to the emulation process at
+initialization, and are used when the emulation code raises a device
+interrupt.
+
+intx acceleration
+'''''''''''''''''
+
+Traditional PCI pin interrupts are level based, so, in addition to an
+irq file descriptor, a re-sampling file descriptor needs to be sent to
+the emulation program. This second file descriptor allows multiple
+devices sharing an irq to be notified when the interrupt has been
+acknowledged by the guest, so they can re-trigger the interrupt if their
+device has not de-asserted its interrupt.
+
+intx irq descriptor
+
+
+The irq descriptors are created by the proxy object
+``using event_notifier_init()`` to create the irq and re-sampling
+*eventds*, and ``kvm_vm_ioctl(KVM_IRQFD)`` to bind them to an interrupt.
+The interrupt route can be found with
+``pci_device_route_intx_to_irq()``.
+
+intx routing changes
+
+
+Intx routing can be changed when the guest programs the APIC the device
+pin is connected to. The proxy object in QEMU will use
+``pci_device_set_intx_routing_notifier()`` to be informed of any guest
+changes to the route. This handler will broadly follow the VFIO
+interrupt logic to change the route: de-assigning the existing irq
+descriptor from its route, then assigning it the new route. (see
+``vfio_intx_update()``)
+
+MSI/X acceleration
+''''''''''''''''''
+
+MSI/X interrupts are sent as DMA transactions to the host. The interrupt
+data contains a vector that is programmed by the guest, A device may have
+multiple MSI interrupts associated with it, so multiple irq descriptors
+may need to be sent to the emulation program.
+
+MSI/X irq descriptor
+
+
+This case will also follow the VFIO example. For each MSI/X interrupt,
+an *eventfd* is created, a virtual interrupt is allocated by
+``kvm_irqchip_add_msi_route()``, and the virtual interrupt is bound to
+the eventfd with ``kvm_irqchip_add_irqfd_notifier()``.
+
+MSI/X config space changes
+
+
+The guest may dynamically update several MSI-related tables in the
+device's PCI config space. These include per-MSI interrupt enables and
+vector data. Additionally, MSIX tables exist in device memory space, not
+config space. Much like the BAR case above, the proxy object must look
+at guest config space programming to keep the MSI interrupt state
+consistent between QEMU and the emulation program.
+
+--------------
+
+Disaggregated CPU emulation
+---------------------------
+
+After IO services have been disaggregated, a second phase would be to
+separate a process to handle CPU instruction emulation from the main
+QEMU control function. There are no object separation points for this
+code, so the first task would be to create one.
+
+Host access controls
+--------------------
+
+Separating QEMU relies on the host OS's access restriction mechanisms to
+enforce that the differing processes can only access the objects they
+are entitled to. There are a couple types of mechanisms usually provided
+by general purpose OSs.
+
+Discretionary access control
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Discretionary access control allows each user to control who can access
+their files. In Linux, this type of control is usually too coarse for
+QEMU separation, since it only provides three separate access controls:
+one for the same user ID, the second for users IDs with the same group
+ID, and the third for all other user IDs. Each device instance would
+need a separate user ID to provide access control, which is likely to be
+unwieldy for dynamically created VMs.
+
+Mandatory access control
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Mandatory access control allows the OS to add an additional set of
+controls on top of discretionary access for the OS to control. It also
+adds other attributes to processes and files such as types, roles, and
+categories, and can establish rules for how processes and files can
+interact.
+
+Type enforcement
+^^^^^^^^^^^^^^^^
+
+Type enforcement assigns a *type* attribute to processes and files, and
+allows rules to be written on what operations a process with a given
+type can perform on a file with a given type. QEMU separation could take
+advantage of type enforcement by running the emulation processes with
+different types, both from the main QEMU process, and from the emulation
+processes of different classes of devices.
+
+For example, guest disk images and disk emulation processes could have
+types separate from the main QEMU process and non-disk emulation
+processes, and the type rules could prevent processes other than disk
+emulation ones from accessing guest disk images. Similarly, network
+emulation processes can have a type separate from the main QEMU process
+and non-network emulation process, and only that type can access the
+host tun/tap device used to provide guest networking.
+
+Category enforcement
+^^^^^^^^^^^^^^^^^^^^
+
+Category enforcement assigns a set of numbers within a given range to
+the process or file. The process is granted access to the file if the
+process's set is a superset of the file's set. This enforcement can be
+used to separate multiple instances of devices in the same class.
+
+For example, if there are multiple disk devices provides to a guest,
+each device emulation process could be provisioned with a separate
+category. The different device emulation processes would not be able to
+access each other's backing disk images.
+
+Alternatively, categories could be used in lieu of the type enforcement
+scheme described above. In this scenario, different categories would be
+used to prevent device emulation processes in different classes from
+accessing resources assigned to other classes.
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Adds documentation explaining the command-line arguments needed
to use multi-process.

[Move orphan docs/multi-process.rst document into docs/system/ and add
it to index.rst to prevent Sphinx "document isn't included in any
toctree" error.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                   |  1 +
 docs/system/index.rst         |  1 +
 docs/system/multi-process.rst | 64 +++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+)
 create mode 100644 docs/system/multi-process.rst

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ M: Jagannathan Raman <jag.raman@oracle.com>
 M: John G Johnson <john.g.johnson@oracle.com>
 S: Maintained
 F: docs/devel/multi-process.rst
+F: docs/system/multi-process.rst
 
 Build and test automation
 -------------------------
diff --git a/docs/system/index.rst b/docs/system/index.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/index.rst
+++ b/docs/system/index.rst
@@ -XXX,XX +XXX,XX @@ Contents:
    pr-manager
    targets
    security
+   multi-process
    deprecated
    removed-features
    build-platforms
diff --git a/docs/system/multi-process.rst b/docs/system/multi-process.rst
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/docs/system/multi-process.rst
@@ -XXX,XX +XXX,XX @@
+Multi-process QEMU
+==================
+
+This document describes how to configure and use multi-process qemu.
+For the design document refer to docs/devel/qemu-multiprocess.
+
+1) Configuration
+----------------
+
+multi-process is enabled by default for targets that enable KVM
+
+
+2) Usage
+--------
+
+Multi-process QEMU requires an orchestrator to launch.
+
+Following is a description of command-line used to launch mpqemu.
+
+* Orchestrator:
+
+  - The Orchestrator creates a unix socketpair
+
+  - It launches the remote process and passes one of the
+    sockets to it via command-line.
+
+  - It then launches QEMU and specifies the other socket as an option
+    to the Proxy device object
+
+* Remote Process:
+
+  - QEMU can enter remote process mode by using the "remote" machine
+    option.
+
+  - The orchestrator creates a "remote-object" with details about
+    the device and the file descriptor for the device
+
+  - The remaining options are no different from how one launches QEMU with
+    devices.
+
+  - Example command-line for the remote process is as follows:
+
+      /usr/bin/qemu-system-x86_64                                        \
+      -machine x-remote                                                  \
+      -device lsi53c895a,id=lsi0                                         \
+      -drive id=drive_image2,file=/build/ol7-nvme-test-1.qcow2           \
+      -device scsi-hd,id=drive2,drive=drive_image2,bus=lsi0.0,scsi-id=0  \
+      -object x-remote-object,id=robj1,devid=lsi1,fd=4,
+
+* QEMU:
+
+  - Since parts of the RAM are shared between QEMU & remote process, a
+    memory-backend-memfd is required to facilitate this, as follows:
+
+    -object memory-backend-memfd,id=mem,size=2G
+
+  - A "x-pci-proxy-dev" device is created for each of the PCI devices emulated
+    in the remote process. A "socket" sub-option specifies the other end of
+    unix channel created by orchestrator. The "id" sub-option must be specified
+    and should be the same as the "id" specified for the remote PCI device
+
+  - Example commandline for QEMU is as follows:
+
+      -device x-pci-proxy-dev,id=lsi0,socket=3
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Allow RAM MemoryRegion to be created from an offset in a file, instead
of allocating at offset of 0 by default. This is needed to synchronize
RAM between QEMU & remote process.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 609996697ad8617e3b01df38accc5c208c24d74e.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/exec/memory.h     |  2 ++
 include/exec/ram_addr.h   |  4 ++--
 include/qemu/mmap-alloc.h |  4 +++-
 backends/hostmem-memfd.c  |  2 +-
 hw/misc/ivshmem.c         |  3 ++-
 softmmu/memory.c          |  3 ++-
 softmmu/physmem.c         | 12 +++++++-----
 util/mmap-alloc.c         |  8 +++++---
 util/oslib-posix.c        |  2 +-
 9 files changed, 25 insertions(+), 15 deletions(-)

diff --git a/include/exec/memory.h b/include/exec/memory.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
  * @size: size of the region.
  * @share: %true if memory must be mmaped with the MAP_SHARED flag
  * @fd: the fd to mmap.
+ * @offset: offset within the file referenced by fd
  * @errp: pointer to Error*, to store an error if it happens.
  *
  * Note that this function does not do anything to cause the data in the
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
                                     uint64_t size,
                                     bool share,
                                     int fd,
+                                    ram_addr_t offset,
                                     Error **errp);
 #endif
 
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
                                    uint32_t ram_flags, const char *mem_path,
                                    bool readonly, Error **errp);
 RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
-                                 uint32_t ram_flags, int fd, bool readonly,
-                                 Error **errp);
+                                 uint32_t ram_flags, int fd, off_t offset,
+                                 bool readonly, Error **errp);
 
 RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
                                   MemoryRegion *mr, Error **errp);
diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h
index XXXXXXX..XXXXXXX 100644
--- a/include/qemu/mmap-alloc.h
+++ b/include/qemu/mmap-alloc.h
@@ -XXX,XX +XXX,XX @@ size_t qemu_mempath_getpagesize(const char *mem_path);
  *  @readonly: true for a read-only mapping, false for read/write.
  *  @shared: map has RAM_SHARED flag.
  *  @is_pmem: map has RAM_PMEM flag.
+ *  @map_offset: map starts at offset of map_offset from the start of fd
  *
  * Return:
  *  On success, return a pointer to the mapped area.
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
                     size_t align,
                     bool readonly,
                     bool shared,
-                    bool is_pmem);
+                    bool is_pmem,
+                    off_t map_offset);
 
 void qemu_ram_munmap(int fd, void *ptr, size_t size);
 
diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c
index XXXXXXX..XXXXXXX 100644
--- a/backends/hostmem-memfd.c
+++ b/backends/hostmem-memfd.c
@@ -XXX,XX +XXX,XX @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
     name = host_memory_backend_get_name(backend);
     memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend),
                                    name, backend->size,
-                                   backend->share, fd, errp);
+                                   backend->share, fd, 0, errp);
     g_free(name);
 }
 
diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/ivshmem.c
+++ b/hw/misc/ivshmem.c
@@ -XXX,XX +XXX,XX @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp)
 
     /* mmap the region and map into the BAR2 */
     memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s),
-                                   "ivshmem.bar2", size, true, fd, &local_err);
+                                   "ivshmem.bar2", size, true, fd, 0,
+                                   &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         return;
diff --git a/softmmu/memory.c b/softmmu/memory.c
index XXXXXXX..XXXXXXX 100644
--- a/softmmu/memory.c
+++ b/softmmu/memory.c
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
                                     uint64_t size,
                                     bool share,
                                     int fd,
+                                    ram_addr_t offset,
                                     Error **errp)
 {
     Error *err = NULL;
@@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
     mr->destructor = memory_region_destructor_ram;
     mr->ram_block = qemu_ram_alloc_from_fd(size, mr,
                                            share ? RAM_SHARED : 0,
-                                           fd, false, &err);
+                                           fd, offset, false, &err);
     if (err) {
         mr->size = int128_zero();
         object_unparent(OBJECT(mr));
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index XXXXXXX..XXXXXXX 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block,
                             int fd,
                             bool readonly,
                             bool truncate,
+                            off_t offset,
                             Error **errp)
 {
     void *area;
@@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block,
     }
 
     area = qemu_ram_mmap(fd, memory, block->mr->align, readonly,
-                         block->flags & RAM_SHARED, block->flags & RAM_PMEM);
+                         block->flags & RAM_SHARED, block->flags & RAM_PMEM,
+                         offset);
     if (area == MAP_FAILED) {
         error_setg_errno(errp, errno,
                          "unable to map backing store for guest RAM");
@@ -XXX,XX +XXX,XX @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
 
 #ifdef CONFIG_POSIX
 RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
-                                 uint32_t ram_flags, int fd, bool readonly,
-                                 Error **errp)
+                                 uint32_t ram_flags, int fd, off_t offset,
+                                 bool readonly, Error **errp)
 {
     RAMBlock *new_block;
     Error *local_err = NULL;
@@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     new_block->max_length = size;
     new_block->flags = ram_flags;
     new_block->host = file_ram_alloc(new_block, size, fd, readonly,
-                                     !file_size, errp);
+                                     !file_size, offset, errp);
     if (!new_block->host) {
         g_free(new_block);
         return NULL;
@@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
         return NULL;
     }
 
-    block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, readonly, errp);
+    block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, 0, readonly, errp);
     if (!block) {
         if (created) {
             unlink(mem_path);
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index XXXXXXX..XXXXXXX 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
                     size_t align,
                     bool readonly,
                     bool shared,
-                    bool is_pmem)
+                    bool is_pmem,
+                    off_t map_offset)
 {
     int prot;
     int flags;
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
 
     prot = PROT_READ | (readonly ? 0 : PROT_WRITE);
 
-    ptr = mmap(guardptr + offset, size, prot, flags | map_sync_flags, fd, 0);
+    ptr = mmap(guardptr + offset, size, prot,
+               flags | map_sync_flags, fd, map_offset);
 
     if (ptr == MAP_FAILED && map_sync_flags) {
         if (errno == ENOTSUP) {
@@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd,
          * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC,
          * we will remove these flags to handle compatibility.
          */
-        ptr = mmap(guardptr + offset, size, prot, flags, fd, 0);
+        ptr = mmap(guardptr + offset, size, prot, flags, fd, map_offset);
     }
 
     if (ptr == MAP_FAILED) {
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index XXXXXXX..XXXXXXX 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -XXX,XX +XXX,XX @@ void *qemu_memalign(size_t alignment, size_t size)
 void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared)
 {
     size_t align = QEMU_VMALLOC_ALIGN;
-    void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false);
+    void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false, 0);
 
     if (ptr == MAP_FAILED) {
         return NULL;
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Add configuration options to enable or disable multiprocess QEMU code

diff --git a/configure b/configure
index XXXXXXX..XXXXXXX 100755
--- a/configure
+++ b/configure
@@ -XXX,XX +XXX,XX @@ skip_meson=no
 gettext="auto"
 fuse="auto"
 fuse_lseek="auto"
+multiprocess="no"
 
 malloc_trim="auto"
 
@@ -XXX,XX +XXX,XX @@ Linux)
   linux="yes"
   linux_user="yes"
   vhost_user=${default_feature:-yes}
+  multiprocess=${default_feature:-yes}
 ;;
 esac
 
@@ -XXX,XX +XXX,XX @@ for opt do
   ;;
   --disable-fuse-lseek) fuse_lseek="disabled"
   ;;
+  --enable-multiprocess) multiprocess="yes"
+  ;;
+  --disable-multiprocess) multiprocess="no"
+  ;;
   *)
       echo "ERROR: unknown option $opt"
       echo "Try '$0 --help' for more information"
@@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available
   libdaxctl       libdaxctl support
   fuse            FUSE block device export
   fuse-lseek      SEEK_HOLE/SEEK_DATA support for FUSE exports
+  multiprocess    Multiprocess QEMU support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -XXX,XX +XXX,XX @@ fi
 if test "$have_mlockall" = "yes" ; then
   echo "HAVE_MLOCKALL=y" >> $config_host_mak
 fi
+if test "$multiprocess" = "yes" ; then
+  echo "CONFIG_MULTIPROCESS_ALLOWED=y" >> $config_host_mak
+fi
 if test "$fuzzing" = "yes" ; then
   # If LIB_FUZZING_ENGINE is set, assume we are running on OSS-Fuzz, and the
   # needed CFLAGS have already been provided
diff --git a/meson.build b/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/meson.build
+++ b/meson.build
@@ -XXX,XX +XXX,XX @@ host_kconfig = \
   ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \
   (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \
   ('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \
-  ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : [])
+  ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \
+  ('CONFIG_MULTIPROCESS_ALLOWED' in config_host ? ['CONFIG_MULTIPROCESS_ALLOWED=y'] : [])
 
 ignored = [ 'TARGET_XML_FILES', 'TARGET_ABI_DIR', 'TARGET_ARCH' ]
 
@@ -XXX,XX +XXX,XX @@ summary_info += {'libpmem support':   config_host.has_key('CONFIG_LIBPMEM')}
 summary_info += {'libdaxctl support': config_host.has_key('CONFIG_LIBDAXCTL')}
 summary_info += {'libudev':           libudev.found()}
 summary_info += {'FUSE lseek':        fuse_lseek.found()}
+summary_info += {'Multiprocess QEMU': config_host.has_key('CONFIG_MULTIPROCESS_ALLOWED')}
 summary(summary_info, bool_yn: true, section: 'Dependencies')
 
 if not supported_cpus.contains(cpu)
diff --git a/Kconfig.host b/Kconfig.host
index XXXXXXX..XXXXXXX 100644
--- a/Kconfig.host
+++ b/Kconfig.host
@@ -XXX,XX +XXX,XX @@ config VIRTFS
 
 config PVRDMA
     bool
+
+config MULTIPROCESS_ALLOWED
+    bool
+    imply MULTIPROCESS
diff --git a/hw/Kconfig b/hw/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/Kconfig
+++ b/hw/Kconfig
@@ -XXX,XX +XXX,XX @@ source pci-host/Kconfig
 source pcmcia/Kconfig
 source pci/Kconfig
 source rdma/Kconfig
+source remote/Kconfig
 source rtc/Kconfig
 source scsi/Kconfig
 source sd/Kconfig
diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/Kconfig
@@ -XXX,XX +XXX,XX @@
+config MULTIPROCESS
+    bool
+    depends on PCI && KVM
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

PCI host bridge is setup for the remote device process. It is
implemented using remote-pcihost object. It is an extension of the PCI
host bridge setup by QEMU.
Remote-pcihost configures a PCI bus which could be used by the remote
PCI device to latch on to.

[Added PCI_EXPRESS condition in hw/remote/Kconfig since remote-pcihost
needs PCIe. This solves "make check" failure on s390x. Fix suggested by
Philippe Mathieu-Daudé <philmd@redhat.com> and Thomas Huth
<thuth@redhat.com>.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                  |  2 +
 include/hw/pci-host/remote.h | 29 ++++++++++++++
 hw/pci-host/remote.c         | 75 ++++++++++++++++++++++++++++++++++++
 hw/pci-host/Kconfig          |  3 ++
 hw/pci-host/meson.build      |  1 +
 hw/remote/Kconfig            |  3 +-
 6 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 include/hw/pci-host/remote.h
 create mode 100644 hw/pci-host/remote.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ M: John G Johnson <john.g.johnson@oracle.com>
 S: Maintained
 F: docs/devel/multi-process.rst
 F: docs/system/multi-process.rst
+F: hw/pci-host/remote.c
+F: include/hw/pci-host/remote.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/pci-host/remote.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * PCI Host for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 REMOTE_PCIHOST_H
+#define REMOTE_PCIHOST_H
+
+#include "exec/memory.h"
+#include "hw/pci/pcie_host.h"
+
+#define TYPE_REMOTE_PCIHOST "remote-pcihost"
+OBJECT_DECLARE_SIMPLE_TYPE(RemotePCIHost, REMOTE_PCIHOST)
+
+struct RemotePCIHost {
+    /*< private >*/
+    PCIExpressHost parent_obj;
+    /*< public >*/
+
+    MemoryRegion *mr_pci_mem;
+    MemoryRegion *mr_sys_io;
+};
+
+#endif
diff --git a/hw/pci-host/remote.c b/hw/pci-host/remote.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/pci-host/remote.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Remote PCI host device
+ *
+ * Unlike PCI host devices that model physical hardware, the purpose
+ * of this PCI host is to host multi-process QEMU devices.
+ *
+ * Multi-process QEMU extends the PCI host of a QEMU machine into a
+ * remote process. Any PCI device attached to the remote process is
+ * visible in the QEMU guest. This allows existing QEMU device models
+ * to be reused in the remote process.
+ *
+ * This PCI host is purely a container for PCI devices. It's fake in the
+ * sense that the guest never sees this PCI host and has no way of
+ * accessing it. Its job is just to provide the environment that QEMU
+ * PCI device models need when running in a remote process.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_host.h"
+#include "hw/pci/pcie_host.h"
+#include "hw/qdev-properties.h"
+#include "hw/pci-host/remote.h"
+#include "exec/memory.h"
+
+static const char *remote_pcihost_root_bus_path(PCIHostState *host_bridge,
+                                                PCIBus *rootbus)
+{
+    return "0000:00";
+}
+
+static void remote_pcihost_realize(DeviceState *dev, Error **errp)
+{
+    PCIHostState *pci = PCI_HOST_BRIDGE(dev);
+    RemotePCIHost *s = REMOTE_PCIHOST(dev);
+
+    pci->bus = pci_root_bus_new(DEVICE(s), "remote-pci",
+                                s->mr_pci_mem, s->mr_sys_io,
+                                0, TYPE_PCIE_BUS);
+}
+
+static void remote_pcihost_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass);
+
+    hc->root_bus_path = remote_pcihost_root_bus_path;
+    dc->realize = remote_pcihost_realize;
+
+    dc->user_creatable = false;
+    set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+    dc->fw_name = "pci";
+}
+
+static const TypeInfo remote_pcihost_info = {
+    .name = TYPE_REMOTE_PCIHOST,
+    .parent = TYPE_PCIE_HOST_BRIDGE,
+    .instance_size = sizeof(RemotePCIHost),
+    .class_init = remote_pcihost_class_init,
+};
+
+static void remote_pcihost_register(void)
+{
+    type_register_static(&remote_pcihost_info);
+}
+
+type_init(remote_pcihost_register)
diff --git a/hw/pci-host/Kconfig b/hw/pci-host/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/Kconfig
+++ b/hw/pci-host/Kconfig
@@ -XXX,XX +XXX,XX @@ config PCI_POWERNV
     select PCI_EXPRESS
     select MSI_NONBROKEN
     select PCIE_PORT
+
+config REMOTE_PCIHOST
+    bool
diff --git a/hw/pci-host/meson.build b/hw/pci-host/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/meson.build
+++ b/hw/pci-host/meson.build
@@ -XXX,XX +XXX,XX @@ pci_ss.add(when: 'CONFIG_PCI_EXPRESS_XILINX', if_true: files('xilinx-pcie.c'))
 pci_ss.add(when: 'CONFIG_PCI_I440FX', if_true: files('i440fx.c'))
 pci_ss.add(when: 'CONFIG_PCI_SABRE', if_true: files('sabre.c'))
 pci_ss.add(when: 'CONFIG_XEN_IGD_PASSTHROUGH', if_true: files('xen_igd_pt.c'))
+pci_ss.add(when: 'CONFIG_REMOTE_PCIHOST', if_true: files('remote.c'))
 
 # PPC devices
 pci_ss.add(when: 'CONFIG_PREP_PCI', if_true: files('prep.c'))
diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/Kconfig
+++ b/hw/remote/Kconfig
@@ -XXX,XX +XXX,XX @@
 config MULTIPROCESS
     bool
-    depends on PCI && KVM
+    depends on PCI && PCI_EXPRESS && KVM
+    select REMOTE_PCIHOST
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

x-remote-machine object sets up various subsystems of the remote
device process. Instantiate PCI host bridge object and initialize RAM, IO &
PCI memory regions.

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: c537f38d17f90453ca610c6b70cf3480274e0ba1.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                  |  2 ++
 include/hw/pci-host/remote.h |  1 +
 include/hw/remote/machine.h  | 27 ++++++++++++++
 hw/remote/machine.c          | 70 ++++++++++++++++++++++++++++++++++++
 hw/meson.build               |  1 +
 hw/remote/meson.build        |  5 +++
 6 files changed, 106 insertions(+)
 create mode 100644 include/hw/remote/machine.h
 create mode 100644 hw/remote/machine.c
 create mode 100644 hw/remote/meson.build

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: docs/devel/multi-process.rst
 F: docs/system/multi-process.rst
 F: hw/pci-host/remote.c
 F: include/hw/pci-host/remote.h
+F: hw/remote/machine.c
+F: include/hw/remote/machine.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/pci-host/remote.h
+++ b/include/hw/pci-host/remote.h
@@ -XXX,XX +XXX,XX @@ struct RemotePCIHost {
 
     MemoryRegion *mr_pci_mem;
     MemoryRegion *mr_sys_io;
+    MemoryRegion *mr_sys_mem;
 };
 
 #endif
diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/machine.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Remote machine configuration
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 REMOTE_MACHINE_H
+#define REMOTE_MACHINE_H
+
+#include "qom/object.h"
+#include "hw/boards.h"
+#include "hw/pci-host/remote.h"
+
+struct RemoteMachineState {
+    MachineState parent_obj;
+
+    RemotePCIHost *host;
+};
+
+#define TYPE_REMOTE_MACHINE "x-remote-machine"
+OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE)
+
+#endif
diff --git a/hw/remote/machine.c b/hw/remote/machine.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/machine.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Machine for remote device
+ *
+ *  This machine type is used by the remote device process in multi-process
+ *  QEMU. QEMU device models depend on parent busses, interrupt controllers,
+ *  memory regions, etc. The remote machine type offers this environment so
+ *  that QEMU device models can be used as remote devices.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "hw/remote/machine.h"
+#include "exec/address-spaces.h"
+#include "exec/memory.h"
+#include "qapi/error.h"
+
+static void remote_machine_init(MachineState *machine)
+{
+    MemoryRegion *system_memory, *system_io, *pci_memory;
+    RemoteMachineState *s = REMOTE_MACHINE(machine);
+    RemotePCIHost *rem_host;
+
+    system_memory = get_system_memory();
+    system_io = get_system_io();
+
+    pci_memory = g_new(MemoryRegion, 1);
+    memory_region_init(pci_memory, NULL, "pci", UINT64_MAX);
+
+    rem_host = REMOTE_PCIHOST(qdev_new(TYPE_REMOTE_PCIHOST));
+
+    rem_host->mr_pci_mem = pci_memory;
+    rem_host->mr_sys_mem = system_memory;
+    rem_host->mr_sys_io = system_io;
+
+    s->host = rem_host;
+
+    object_property_add_child(OBJECT(s), "remote-pcihost", OBJECT(rem_host));
+    memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1);
+
+    qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal);
+}
+
+static void remote_machine_class_init(ObjectClass *oc, void *data)
+{
+    MachineClass *mc = MACHINE_CLASS(oc);
+
+    mc->init = remote_machine_init;
+    mc->desc = "Experimental remote machine";
+}
+
+static const TypeInfo remote_machine = {
+    .name = TYPE_REMOTE_MACHINE,
+    .parent = TYPE_MACHINE,
+    .instance_size = sizeof(RemoteMachineState),
+    .class_init = remote_machine_class_init,
+};
+
+static void remote_machine_register_types(void)
+{
+    type_register_static(&remote_machine);
+}
+
+type_init(remote_machine_register_types);
diff --git a/hw/meson.build b/hw/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/meson.build
+++ b/hw/meson.build
@@ -XXX,XX +XXX,XX @@ subdir('moxie')
 subdir('nios2')
 subdir('openrisc')
 subdir('ppc')
+subdir('remote')
 subdir('riscv')
 subdir('rx')
 subdir('s390x')
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@
+remote_ss = ss.source_set()
+
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
+
+softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Adds qio_channel_writev_full_all() to transmit both data and FDs.
Refactors existing code to use this helper.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 480fbf1fe4152495d60596c9b665124549b426a5.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/io/channel.h | 25 +++++++++++++++++++++++++
 io/channel.c         | 15 ++++++++++++++-
 2 files changed, 39 insertions(+), 1 deletion(-)

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Adds qio_channel_readv_full_all_eof() and qio_channel_readv_full_all()
to read both data and FDs. Refactors existing code to use these helpers.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: b059c4cc0fb741e794d644c144cc21372cad877d.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/io/channel.h |  53 +++++++++++++++++++++++
 io/channel.c         | 101 ++++++++++++++++++++++++++++++++++---------
 2 files changed, 134 insertions(+), 20 deletions(-)

diff --git a/include/io/channel.h b/include/io/channel.h
index XXXXXXX..XXXXXXX 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -XXX,XX +XXX,XX @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc,
                                     IOHandler *io_write,
                                     void *opaque);
 
+/**
+ * qio_channel_readv_full_all_eof:
+ * @ioc: the channel object
+ * @iov: the array of memory regions to read data to
+ * @niov: the length of the @iov array
+ * @fds: an array of file handles to read
+ * @nfds: number of file handles in @fds
+ * @errp: pointer to a NULL-initialized error object
+ *
+ *
+ * Performs same function as qio_channel_readv_all_eof.
+ * Additionally, attempts to read file descriptors shared
+ * over the channel. The function will wait for all
+ * requested data to be read, yielding from the current
+ * coroutine if required. data refers to both file
+ * descriptors and the iovs.
+ *
+ * Returns: 1 if all bytes were read, 0 if end-of-file
+ *          occurs without data, or -1 on error
+ */
+
+int qio_channel_readv_full_all_eof(QIOChannel *ioc,
+                                   const struct iovec *iov,
+                                   size_t niov,
+                                   int **fds, size_t *nfds,
+                                   Error **errp);
+
+/**
+ * qio_channel_readv_full_all:
+ * @ioc: the channel object
+ * @iov: the array of memory regions to read data to
+ * @niov: the length of the @iov array
+ * @fds: an array of file handles to read
+ * @nfds: number of file handles in @fds
+ * @errp: pointer to a NULL-initialized error object
+ *
+ *
+ * Performs same function as qio_channel_readv_all_eof.
+ * Additionally, attempts to read file descriptors shared
+ * over the channel. The function will wait for all
+ * requested data to be read, yielding from the current
+ * coroutine if required. data refers to both file
+ * descriptors and the iovs.
+ *
+ * Returns: 0 if all bytes were read, or -1 on error
+ */
+
+int qio_channel_readv_full_all(QIOChannel *ioc,
+                               const struct iovec *iov,
+                               size_t niov,
+                               int **fds, size_t *nfds,
+                               Error **errp);
+
 /**
  * qio_channel_writev_full_all:
  * @ioc: the channel object
diff --git a/io/channel.c b/io/channel.c
index XXXXXXX..XXXXXXX 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc,
                               const struct iovec *iov,
                               size_t niov,
                               Error **errp)
+{
+    return qio_channel_readv_full_all_eof(ioc, iov, niov, NULL, NULL, errp);
+}
+
+int qio_channel_readv_all(QIOChannel *ioc,
+                          const struct iovec *iov,
+                          size_t niov,
+                          Error **errp)
+{
+    return qio_channel_readv_full_all(ioc, iov, niov, NULL, NULL, errp);
+}
+
+int qio_channel_readv_full_all_eof(QIOChannel *ioc,
+                                   const struct iovec *iov,
+                                   size_t niov,
+                                   int **fds, size_t *nfds,
+                                   Error **errp)
 {
     int ret = -1;
     struct iovec *local_iov = g_new(struct iovec, niov);
     struct iovec *local_iov_head = local_iov;
     unsigned int nlocal_iov = niov;
+    int **local_fds = fds;
+    size_t *local_nfds = nfds;
     bool partial = false;
 
+    if (nfds) {
+        *nfds = 0;
+    }
+
+    if (fds) {
+        *fds = NULL;
+    }
+
     nlocal_iov = iov_copy(local_iov, nlocal_iov,
                           iov, niov,
                           0, iov_size(iov, niov));
 
-    while (nlocal_iov > 0) {
+    while ((nlocal_iov > 0) || local_fds) {
         ssize_t len;
-        len = qio_channel_readv(ioc, local_iov, nlocal_iov, errp);
+        len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds,
+                                     local_nfds, errp);
         if (len == QIO_CHANNEL_ERR_BLOCK) {
             if (qemu_in_coroutine()) {
                 qio_channel_yield(ioc, G_IO_IN);
@@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc,
                 qio_channel_wait(ioc, G_IO_IN);
             }
             continue;
-        } else if (len < 0) {
-            goto cleanup;
-        } else if (len == 0) {
-            if (partial) {
-                error_setg(errp,
-                           "Unexpected end-of-file before all bytes were read");
-            } else {
+        }
+
+        if (len == 0) {
+            if (local_nfds && *local_nfds) {
+                /*
+                 * Got some FDs, but no data yet. This isn't an EOF
+                 * scenario (yet), so carry on to try to read data
+                 * on next loop iteration
+                 */
+                goto next_iter;
+            } else if (!partial) {
+                /* No fds and no data - EOF before any data read */
                 ret = 0;
+                goto cleanup;
+            } else {
+                len = -1;
+                error_setg(errp,
+                           "Unexpected end-of-file before all data were read");
+                /* Fallthrough into len < 0 handling */
+            }
+        }
+
+        if (len < 0) {
+            /* Close any FDs we previously received */
+            if (nfds && fds) {
+                size_t i;
+                for (i = 0; i < (*nfds); i++) {
+                    close((*fds)[i]);
+                }
+                g_free(*fds);
+                *fds = NULL;
+                *nfds = 0;
             }
             goto cleanup;
         }
 
+        if (nlocal_iov) {
+            iov_discard_front(&local_iov, &nlocal_iov, len);
+        }
+
+next_iter:
         partial = true;
-        iov_discard_front(&local_iov, &nlocal_iov, len);
+        local_fds = NULL;
+        local_nfds = NULL;
     }
 
     ret = 1;
@@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc,
     return ret;
 }
 
-int qio_channel_readv_all(QIOChannel *ioc,
-                          const struct iovec *iov,
-                          size_t niov,
-                          Error **errp)
+int qio_channel_readv_full_all(QIOChannel *ioc,
+                               const struct iovec *iov,
+                               size_t niov,
+                               int **fds, size_t *nfds,
+                               Error **errp)
 {
-    int ret = qio_channel_readv_all_eof(ioc, iov, niov, errp);
+    int ret = qio_channel_readv_full_all_eof(ioc, iov, niov, fds, nfds, errp);
 
     if (ret == 0) {
-        ret = -1;
-        error_setg(errp,
-                   "Unexpected end-of-file before all bytes were read");
-    } else if (ret == 1) {
-        ret = 0;
+        error_prepend(errp,
+                      "Unexpected end-of-file before all data were read.");
+        return -1;
     }
+    if (ret == 1) {
+        return 0;
+    }
+
     return ret;
 }
 
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Defines MPQemuMsg, which is the message that is sent to the remote
process. This message is sent over QIOChannel and is used to
command the remote process to perform various tasks.
Define transmission functions used by proxy and by remote.

[Replace struct iovec send[2] = {0} with {} to make clang happy as
suggested by Peter Maydell <peter.maydell@linaro.org>.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                     |   2 +
 meson.build                     |   1 +
 hw/remote/trace.h               |   1 +
 include/hw/remote/mpqemu-link.h |  63 ++++++++++
 include/sysemu/iothread.h       |   6 +
 hw/remote/mpqemu-link.c         | 205 ++++++++++++++++++++++++++++++++
 iothread.c                      |   6 +
 hw/remote/meson.build           |   1 +
 hw/remote/trace-events          |   4 +
 9 files changed, 289 insertions(+)
 create mode 100644 hw/remote/trace.h
 create mode 100644 include/hw/remote/mpqemu-link.h
 create mode 100644 hw/remote/mpqemu-link.c
 create mode 100644 hw/remote/trace-events

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/pci-host/remote.c
 F: include/hw/pci-host/remote.h
 F: hw/remote/machine.c
 F: include/hw/remote/machine.h
+F: hw/remote/mpqemu-link.c
+F: include/hw/remote/mpqemu-link.h
 
 Build and test automation
 -------------------------
diff --git a/meson.build b/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/meson.build
+++ b/meson.build
@@ -XXX,XX +XXX,XX @@ if have_system
     'net',
     'softmmu',
     'ui',
+    'hw/remote',
   ]
 endif
 if have_system or have_user
diff --git a/hw/remote/trace.h b/hw/remote/trace.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-hw_remote.h"
diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Communication channel between QEMU and remote device process
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 MPQEMU_LINK_H
+#define MPQEMU_LINK_H
+
+#include "qom/object.h"
+#include "qemu/thread.h"
+#include "io/channel.h"
+
+#define REMOTE_MAX_FDS 8
+
+#define MPQEMU_MSG_HDR_SIZE offsetof(MPQemuMsg, data.u64)
+
+/**
+ * MPQemuCmd:
+ *
+ * MPQemuCmd enum type to specify the command to be executed on the remote
+ * device.
+ *
+ * This uses a private protocol between QEMU and the remote process. vfio-user
+ * protocol would supersede this in the future.
+ *
+ */
+typedef enum {
+    MPQEMU_CMD_MAX,
+} MPQemuCmd;
+
+/**
+ * MPQemuMsg:
+ * @cmd: The remote command
+ * @size: Size of the data to be shared
+ * @data: Structured data
+ * @fds: File descriptors to be shared with remote device
+ *
+ * MPQemuMsg Format of the message sent to the remote device from QEMU.
+ *
+ */
+typedef struct {
+    int cmd;
+    size_t size;
+
+    union {
+        uint64_t u64;
+    } data;
+
+    int fds[REMOTE_MAX_FDS];
+    int num_fds;
+} MPQemuMsg;
+
+bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
+bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
+
+bool mpqemu_msg_valid(MPQemuMsg *msg);
+
+#endif
diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/iothread.h
+++ b/include/sysemu/iothread.h
@@ -XXX,XX +XXX,XX @@ IOThread *iothread_create(const char *id, Error **errp);
 void iothread_stop(IOThread *iothread);
 void iothread_destroy(IOThread *iothread);
 
+/*
+ * Returns true if executing withing IOThread context,
+ * false otherwise.
+ */
+bool qemu_in_iothread(void);
+
 #endif /* IOTHREAD_H */
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Communication channel between QEMU and remote device process
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "qemu/module.h"
+#include "hw/remote/mpqemu-link.h"
+#include "qapi/error.h"
+#include "qemu/iov.h"
+#include "qemu/error-report.h"
+#include "qemu/main-loop.h"
+#include "io/channel.h"
+#include "sysemu/iothread.h"
+#include "trace.h"
+
+/*
+ * Send message over the ioc QIOChannel.
+ * This function is safe to call from:
+ * - main loop in co-routine context. Will block the main loop if not in
+ *   co-routine context;
+ * - vCPU thread with no co-routine context and if the channel is not part
+ *   of the main loop handling;
+ * - IOThread within co-routine context, outside of co-routine context
+ *   will block IOThread;
+ * Returns true if no errors were encountered, false otherwise.
+ */
+bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
+{
+    ERRP_GUARD();
+    bool iolock = qemu_mutex_iothread_locked();
+    bool iothread = qemu_in_iothread();
+    struct iovec send[2] = {};
+    int *fds = NULL;
+    size_t nfds = 0;
+    bool ret = false;
+
+    send[0].iov_base = msg;
+    send[0].iov_len = MPQEMU_MSG_HDR_SIZE;
+
+    send[1].iov_base = (void *)&msg->data;
+    send[1].iov_len = msg->size;
+
+    if (msg->num_fds) {
+        nfds = msg->num_fds;
+        fds = msg->fds;
+    }
+
+    /*
+     * Dont use in IOThread out of co-routine context as
+     * it will block IOThread.
+     */
+    assert(qemu_in_coroutine() || !iothread);
+
+    /*
+     * Skip unlocking/locking iothread lock when the IOThread is running
+     * in co-routine context. Co-routine context is asserted above
+     * for IOThread case.
+     * Also skip lock handling while in a co-routine in the main context.
+     */
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        qemu_mutex_unlock_iothread();
+    }
+
+    if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send),
+                                    fds, nfds, errp)) {
+        ret = true;
+    } else {
+        trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds);
+    }
+
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        /* See above comment why skip locking here. */
+        qemu_mutex_lock_iothread();
+    }
+
+    return ret;
+}
+
+/*
+ * Read message from the ioc QIOChannel.
+ * This function is safe to call from:
+ * - From main loop in co-routine context. Will block the main loop if not in
+ *   co-routine context;
+ * - From vCPU thread with no co-routine context and if the channel is not part
+ *   of the main loop handling;
+ * - From IOThread within co-routine context, outside of co-routine context
+ *   will block IOThread;
+ */
+static ssize_t mpqemu_read(QIOChannel *ioc, void *buf, size_t len, int **fds,
+                           size_t *nfds, Error **errp)
+{
+    ERRP_GUARD();
+    struct iovec iov = { .iov_base = buf, .iov_len = len };
+    bool iolock = qemu_mutex_iothread_locked();
+    bool iothread = qemu_in_iothread();
+    int ret = -1;
+
+    /*
+     * Dont use in IOThread out of co-routine context as
+     * it will block IOThread.
+     */
+    assert(qemu_in_coroutine() || !iothread);
+
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        qemu_mutex_unlock_iothread();
+    }
+
+    ret = qio_channel_readv_full_all_eof(ioc, &iov, 1, fds, nfds, errp);
+
+    if (iolock && !iothread && !qemu_in_coroutine()) {
+        qemu_mutex_lock_iothread();
+    }
+
+    return (ret <= 0) ? ret : iov.iov_len;
+}
+
+bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
+{
+    ERRP_GUARD();
+    g_autofree int *fds = NULL;
+    size_t nfds = 0;
+    ssize_t len;
+    bool ret = false;
+
+    len = mpqemu_read(ioc, msg, MPQEMU_MSG_HDR_SIZE, &fds, &nfds, errp);
+    if (len <= 0) {
+        goto fail;
+    } else if (len != MPQEMU_MSG_HDR_SIZE) {
+        error_setg(errp, "Message header corrupted");
+        goto fail;
+    }
+
+    if (msg->size > sizeof(msg->data)) {
+        error_setg(errp, "Invalid size for message");
+        goto fail;
+    }
+
+    if (!msg->size) {
+        goto copy_fds;
+    }
+
+    len = mpqemu_read(ioc, &msg->data, msg->size, NULL, NULL, errp);
+    if (len <= 0) {
+        goto fail;
+    }
+    if (len != msg->size) {
+        error_setg(errp, "Unable to read full message");
+        goto fail;
+    }
+
+copy_fds:
+    msg->num_fds = nfds;
+    if (nfds > G_N_ELEMENTS(msg->fds)) {
+        error_setg(errp,
+                   "Overflow error: received %zu fds, more than max of %d fds",
+                   nfds, REMOTE_MAX_FDS);
+        goto fail;
+    }
+    if (nfds) {
+        memcpy(msg->fds, fds, nfds * sizeof(int));
+    }
+
+    ret = true;
+
+fail:
+    if (*errp) {
+        trace_mpqemu_recv_io_error(msg->cmd, msg->size, nfds);
+    }
+    while (*errp && nfds) {
+        close(fds[nfds - 1]);
+        nfds--;
+    }
+
+    return ret;
+}
+
+bool mpqemu_msg_valid(MPQemuMsg *msg)
+{
+    if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) {
+        return false;
+    }
+
+    /* Verify FDs. */
+    if (msg->num_fds >= REMOTE_MAX_FDS) {
+        return false;
+    }
+
+    if (msg->num_fds > 0) {
+        for (int i = 0; i < msg->num_fds; i++) {
+            if (fcntl(msg->fds[i], F_GETFL) == -1) {
+                return false;
+            }
+        }
+    }
+
+    return true;
+}
diff --git a/iothread.c b/iothread.c
index XXXXXXX..XXXXXXX 100644
--- a/iothread.c
+++ b/iothread.c
@@ -XXX,XX +XXX,XX @@ IOThread *iothread_by_id(const char *id)
 {
     return IOTHREAD(object_resolve_path_type(id, TYPE_IOTHREAD, NULL));
 }
+
+bool qemu_in_iothread(void)
+{
+    return qemu_get_current_aio_context() == qemu_get_aio_context() ?
+                    false : true;
+}
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@
 remote_ss = ss.source_set()
 
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
diff --git a/hw/remote/trace-events b/hw/remote/trace-events
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/trace-events
@@ -XXX,XX +XXX,XX @@
+# multi-process trace events
+
+mpqemu_send_io_error(int cmd, int size, int nfds) "send command %d size %d, %d file descriptors to remote process"
+mpqemu_recv_io_error(int cmd, int size, int nfds) "failed to receive %d size %d, %d file descriptors to remote process"
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Initializes the message handler function in the remote process. It is
called whenever there's an event pending on QIOChannel that registers
this function.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 99d38d8b93753a6409ac2340e858858cda59ab1b.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                 |  1 +
 include/hw/remote/machine.h |  9 ++++++
 hw/remote/message.c         | 57 +++++++++++++++++++++++++++++++++++++
 hw/remote/meson.build       |  1 +
 4 files changed, 68 insertions(+)
 create mode 100644 hw/remote/message.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/machine.c
 F: include/hw/remote/machine.h
 F: hw/remote/mpqemu-link.c
 F: include/hw/remote/mpqemu-link.h
+F: hw/remote/message.c
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/machine.h
+++ b/include/hw/remote/machine.h
@@ -XXX,XX +XXX,XX @@
 #include "qom/object.h"
 #include "hw/boards.h"
 #include "hw/pci-host/remote.h"
+#include "io/channel.h"
 
 struct RemoteMachineState {
     MachineState parent_obj;
@@ -XXX,XX +XXX,XX @@ struct RemoteMachineState {
     RemotePCIHost *host;
 };
 
+/* Used to pass to co-routine device and ioc. */
+typedef struct RemoteCommDev {
+    PCIDevice *dev;
+    QIOChannel *ioc;
+} RemoteCommDev;
+
 #define TYPE_REMOTE_MACHINE "x-remote-machine"
 OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE)
 
+void coroutine_fn mpqemu_remote_msg_loop_co(void *data);
+
 #endif
diff --git a/hw/remote/message.c b/hw/remote/message.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2020, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL-v2, version 2 or later.
+ *
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/remote/machine.h"
+#include "io/channel.h"
+#include "hw/remote/mpqemu-link.h"
+#include "qapi/error.h"
+#include "sysemu/runstate.h"
+
+void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
+{
+    g_autofree RemoteCommDev *com = (RemoteCommDev *)data;
+    PCIDevice *pci_dev = NULL;
+    Error *local_err = NULL;
+
+    assert(com->ioc);
+
+    pci_dev = com->dev;
+    for (; !local_err;) {
+        MPQemuMsg msg = {0};
+
+        if (!mpqemu_msg_recv(&msg, com->ioc, &local_err)) {
+            break;
+        }
+
+        if (!mpqemu_msg_valid(&msg)) {
+            error_setg(&local_err, "Received invalid message from proxy"
+                                   "in remote process pid="FMT_pid"",
+                                   getpid());
+            break;
+        }
+
+        switch (msg.cmd) {
+        default:
+            error_setg(&local_err,
+                       "Unknown command (%d) received for device %s"
+                       " (pid="FMT_pid")",
+                       msg.cmd, DEVICE(pci_dev)->id, getpid());
+        }
+    }
+
+    if (local_err) {
+        error_report_err(local_err);
+        qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR);
+    } else {
+        qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
+    }
+}
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set()
 
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Associate the file descriptor for a PCIDevice in remote process with
DeviceState object.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: f405a2ed5d7518b87bea7c59cfdf334d67e5ee51.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS            |   1 +
 hw/remote/remote-obj.c | 203 +++++++++++++++++++++++++++++++++++++++++
 hw/remote/meson.build  |   1 +
 3 files changed, 205 insertions(+)
 create mode 100644 hw/remote/remote-obj.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: include/hw/remote/machine.h
 F: hw/remote/mpqemu-link.c
 F: include/hw/remote/mpqemu-link.h
 F: hw/remote/message.c
+F: hw/remote/remote-obj.c
 
 Build and test automation
 -------------------------
diff --git a/hw/remote/remote-obj.c b/hw/remote/remote-obj.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/remote-obj.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2020, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL-v2, version 2 or later.
+ *
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "qemu/error-report.h"
+#include "qemu/notify.h"
+#include "qom/object_interfaces.h"
+#include "hw/qdev-core.h"
+#include "io/channel.h"
+#include "hw/qdev-core.h"
+#include "hw/remote/machine.h"
+#include "io/channel-util.h"
+#include "qapi/error.h"
+#include "sysemu/sysemu.h"
+#include "hw/pci/pci.h"
+#include "qemu/sockets.h"
+#include "monitor/monitor.h"
+
+#define TYPE_REMOTE_OBJECT "x-remote-object"
+OBJECT_DECLARE_TYPE(RemoteObject, RemoteObjectClass, REMOTE_OBJECT)
+
+struct RemoteObjectClass {
+    ObjectClass parent_class;
+
+    unsigned int nr_devs;
+    unsigned int max_devs;
+};
+
+struct RemoteObject {
+    /* private */
+    Object parent;
+
+    Notifier machine_done;
+
+    int32_t fd;
+    char *devid;
+
+    QIOChannel *ioc;
+
+    DeviceState *dev;
+    DeviceListener listener;
+};
+
+static void remote_object_set_fd(Object *obj, const char *str, Error **errp)
+{
+    RemoteObject *o = REMOTE_OBJECT(obj);
+    int fd = -1;
+
+    fd = monitor_fd_param(monitor_cur(), str, errp);
+    if (fd == -1) {
+        error_prepend(errp, "Could not parse remote object fd %s:", str);
+        return;
+    }
+
+    if (!fd_is_socket(fd)) {
+        error_setg(errp, "File descriptor '%s' is not a socket", str);
+        close(fd);
+        return;
+    }
+
+    o->fd = fd;
+}
+
+static void remote_object_set_devid(Object *obj, const char *str, Error **errp)
+{
+    RemoteObject *o = REMOTE_OBJECT(obj);
+
+    g_free(o->devid);
+
+    o->devid = g_strdup(str);
+}
+
+static void remote_object_unrealize_listener(DeviceListener *listener,
+                                             DeviceState *dev)
+{
+    RemoteObject *o = container_of(listener, RemoteObject, listener);
+
+    if (o->dev == dev) {
+        object_unref(OBJECT(o));
+    }
+}
+
+static void remote_object_machine_done(Notifier *notifier, void *data)
+{
+    RemoteObject *o = container_of(notifier, RemoteObject, machine_done);
+    DeviceState *dev = NULL;
+    QIOChannel *ioc = NULL;
+    Coroutine *co = NULL;
+    RemoteCommDev *comdev = NULL;
+    Error *err = NULL;
+
+    dev = qdev_find_recursive(sysbus_get_default(), o->devid);
+    if (!dev || !object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
+        error_report("%s is not a PCI device", o->devid);
+        return;
+    }
+
+    ioc = qio_channel_new_fd(o->fd, &err);
+    if (!ioc) {
+        error_report_err(err);
+        return;
+    }
+    qio_channel_set_blocking(ioc, false, NULL);
+
+    o->dev = dev;
+
+    o->listener.unrealize = remote_object_unrealize_listener;
+    device_listener_register(&o->listener);
+
+    /* co-routine should free this. */
+    comdev = g_new0(RemoteCommDev, 1);
+    *comdev = (RemoteCommDev) {
+        .ioc = ioc,
+        .dev = PCI_DEVICE(dev),
+    };
+
+    co = qemu_coroutine_create(mpqemu_remote_msg_loop_co, comdev);
+    qemu_coroutine_enter(co);
+}
+
+static void remote_object_init(Object *obj)
+{
+    RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj);
+    RemoteObject *o = REMOTE_OBJECT(obj);
+
+    if (k->nr_devs >= k->max_devs) {
+        error_report("Reached maximum number of devices: %u", k->max_devs);
+        return;
+    }
+
+    o->ioc = NULL;
+    o->fd = -1;
+    o->devid = NULL;
+
+    k->nr_devs++;
+
+    o->machine_done.notify = remote_object_machine_done;
+    qemu_add_machine_init_done_notifier(&o->machine_done);
+}
+
+static void remote_object_finalize(Object *obj)
+{
+    RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj);
+    RemoteObject *o = REMOTE_OBJECT(obj);
+
+    device_listener_unregister(&o->listener);
+
+    if (o->ioc) {
+        qio_channel_shutdown(o->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+        qio_channel_close(o->ioc, NULL);
+    }
+
+    object_unref(OBJECT(o->ioc));
+
+    k->nr_devs--;
+    g_free(o->devid);
+}
+
+static void remote_object_class_init(ObjectClass *klass, void *data)
+{
+    RemoteObjectClass *k = REMOTE_OBJECT_CLASS(klass);
+
+    /*
+     * Limit number of supported devices to 1. This is done to avoid devices
+     * from one VM accessing the RAM of another VM. This is done until we
+     * start using separate address spaces for individual devices.
+     */
+    k->max_devs = 1;
+    k->nr_devs = 0;
+
+    object_class_property_add_str(klass, "fd", NULL, remote_object_set_fd);
+    object_class_property_add_str(klass, "devid", NULL,
+                                  remote_object_set_devid);
+}
+
+static const TypeInfo remote_object_info = {
+    .name = TYPE_REMOTE_OBJECT,
+    .parent = TYPE_OBJECT,
+    .instance_size = sizeof(RemoteObject),
+    .instance_init = remote_object_init,
+    .instance_finalize = remote_object_finalize,
+    .class_size = sizeof(RemoteObjectClass),
+    .class_init = remote_object_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_USER_CREATABLE },
+        { }
+    }
+};
+
+static void register_types(void)
+{
+    type_register_static(&remote_object_info);
+}
+
+type_init(register_types);
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set()
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

SyncSysMemMsg message format is defined. It is used to send
file descriptors of the RAM regions to remote device.
RAM on the remote device is configured with a set of file descriptors.
Old RAM regions are deleted and new regions, each with an fd, is
added to the RAM.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 7d2d1831d812e85f681e7a8ab99e032cf4704689.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                     |  2 +
 include/hw/remote/memory.h      | 19 ++++++++++
 include/hw/remote/mpqemu-link.h | 10 +++++
 hw/remote/memory.c              | 65 +++++++++++++++++++++++++++++++++
 hw/remote/mpqemu-link.c         | 11 ++++++
 hw/remote/meson.build           |  2 +
 6 files changed, 109 insertions(+)
 create mode 100644 include/hw/remote/memory.h
 create mode 100644 hw/remote/memory.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/mpqemu-link.c
 F: include/hw/remote/mpqemu-link.h
 F: hw/remote/message.c
 F: hw/remote/remote-obj.c
+F: include/hw/remote/memory.h
+F: hw/remote/memory.c
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/memory.h b/include/hw/remote/memory.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/memory.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Memory manager for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 REMOTE_MEMORY_H
+#define REMOTE_MEMORY_H
+
+#include "exec/hwaddr.h"
+#include "hw/remote/mpqemu-link.h"
+
+void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp);
+
+#endif
diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
 #include "qom/object.h"
 #include "qemu/thread.h"
 #include "io/channel.h"
+#include "exec/hwaddr.h"
 
 #define REMOTE_MAX_FDS 8
 
@@ -XXX,XX +XXX,XX @@
  *
  */
 typedef enum {
+    MPQEMU_CMD_SYNC_SYSMEM,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
+typedef struct {
+    hwaddr gpas[REMOTE_MAX_FDS];
+    uint64_t sizes[REMOTE_MAX_FDS];
+    off_t offsets[REMOTE_MAX_FDS];
+} SyncSysmemMsg;
+
 /**
  * MPQemuMsg:
  * @cmd: The remote command
@@ -XXX,XX +XXX,XX @@ typedef enum {
  * MPQemuMsg Format of the message sent to the remote device from QEMU.
  *
  */
+
 typedef struct {
     int cmd;
     size_t size;
 
     union {
         uint64_t u64;
+        SyncSysmemMsg sync_sysmem;
     } data;
 
     int fds[REMOTE_MAX_FDS];
diff --git a/hw/remote/memory.c b/hw/remote/memory.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/memory.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Memory manager for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "hw/remote/memory.h"
+#include "exec/address-spaces.h"
+#include "exec/ram_addr.h"
+#include "qapi/error.h"
+
+static void remote_sysmem_reset(void)
+{
+    MemoryRegion *sysmem, *subregion, *next;
+
+    sysmem = get_system_memory();
+
+    QTAILQ_FOREACH_SAFE(subregion, &sysmem->subregions, subregions_link, next) {
+        if (subregion->ram) {
+            memory_region_del_subregion(sysmem, subregion);
+            object_unparent(OBJECT(subregion));
+        }
+    }
+}
+
+void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    SyncSysmemMsg *sysmem_info = &msg->data.sync_sysmem;
+    MemoryRegion *sysmem, *subregion;
+    static unsigned int suffix;
+    int region;
+
+    sysmem = get_system_memory();
+
+    remote_sysmem_reset();
+
+    for (region = 0; region < msg->num_fds; region++) {
+        g_autofree char *name;
+        subregion = g_new(MemoryRegion, 1);
+        name = g_strdup_printf("remote-mem-%u", suffix++);
+        memory_region_init_ram_from_fd(subregion, NULL,
+                                       name, sysmem_info->sizes[region],
+                                       true, msg->fds[region],
+                                       sysmem_info->offsets[region],
+                                       errp);
+
+        if (*errp) {
+            g_free(subregion);
+            remote_sysmem_reset();
+            return;
+        }
+
+        memory_region_add_subregion(sysmem, sysmem_info->gpas[region],
+                                    subregion);
+
+    }
+}
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
         }
     }
 
+     /* Verify message specific fields. */
+    switch (msg->cmd) {
+    case MPQEMU_CMD_SYNC_SYSMEM:
+        if (msg->num_fds == 0 || msg->size != sizeof(SyncSysmemMsg)) {
+            return false;
+        }
+        break;
+    default:
+        break;
+    }
+
     return true;
 }
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 
+specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
+
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Defines a PCI Device proxy object as a child of TYPE_PCI_DEVICE.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: b5186ebfedf8e557044d09a768846c59230ad3a7.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS               |  2 +
 include/hw/remote/proxy.h | 33 +++++++++++++
 hw/remote/proxy.c         | 99 +++++++++++++++++++++++++++++++++++++++
 hw/remote/meson.build     |  1 +
 4 files changed, 135 insertions(+)
 create mode 100644 include/hw/remote/proxy.h
 create mode 100644 hw/remote/proxy.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/message.c
 F: hw/remote/remote-obj.c
 F: include/hw/remote/memory.h
 F: hw/remote/memory.c
+F: hw/remote/proxy.c
+F: include/hw/remote/proxy.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 PROXY_H
+#define PROXY_H
+
+#include "hw/pci/pci.h"
+#include "io/channel.h"
+
+#define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
+OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
+
+struct PCIProxyDev {
+    PCIDevice parent_dev;
+    char *fd;
+
+    /*
+     * Mutex used to protect the QIOChannel fd from
+     * the concurrent access by the VCPUs since proxy
+     * blocks while awaiting for the replies from the
+     * process remote.
+     */
+    QemuMutex io_mutex;
+    QIOChannel *ioc;
+    Error *migration_blocker;
+};
+
+#endif /* PROXY_H */
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "hw/remote/proxy.h"
+#include "hw/pci/pci.h"
+#include "qapi/error.h"
+#include "io/channel-util.h"
+#include "hw/qdev-properties.h"
+#include "monitor/monitor.h"
+#include "migration/blocker.h"
+#include "qemu/sockets.h"
+
+static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
+{
+    ERRP_GUARD();
+    PCIProxyDev *dev = PCI_PROXY_DEV(device);
+    int fd;
+
+    if (!dev->fd) {
+        error_setg(errp, "fd parameter not specified for %s",
+                   DEVICE(device)->id);
+        return;
+    }
+
+    fd = monitor_fd_param(monitor_cur(), dev->fd, errp);
+    if (fd == -1) {
+        error_prepend(errp, "proxy: unable to parse fd %s: ", dev->fd);
+        return;
+    }
+
+    if (!fd_is_socket(fd)) {
+        error_setg(errp, "proxy: fd %d is not a socket", fd);
+        close(fd);
+        return;
+    }
+
+    dev->ioc = qio_channel_new_fd(fd, errp);
+
+    error_setg(&dev->migration_blocker, "%s does not support migration",
+               TYPE_PCI_PROXY_DEV);
+    migrate_add_blocker(dev->migration_blocker, errp);
+
+    qemu_mutex_init(&dev->io_mutex);
+    qio_channel_set_blocking(dev->ioc, true, NULL);
+}
+
+static void pci_proxy_dev_exit(PCIDevice *pdev)
+{
+    PCIProxyDev *dev = PCI_PROXY_DEV(pdev);
+
+    if (dev->ioc) {
+        qio_channel_close(dev->ioc, NULL);
+    }
+
+    migrate_del_blocker(dev->migration_blocker);
+
+    error_free(dev->migration_blocker);
+}
+
+static Property proxy_properties[] = {
+    DEFINE_PROP_STRING("fd", PCIProxyDev, fd),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->realize = pci_proxy_dev_realize;
+    k->exit = pci_proxy_dev_exit;
+    device_class_set_props(dc, proxy_properties);
+}
+
+static const TypeInfo pci_proxy_dev_type_info = {
+    .name          = TYPE_PCI_PROXY_DEV,
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PCIProxyDev),
+    .class_init    = pci_proxy_dev_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { INTERFACE_CONVENTIONAL_PCI_DEVICE },
+        { },
+    },
+};
+
+static void pci_proxy_dev_register_types(void)
+{
+    type_register_static(&pci_proxy_dev_type_info);
+}
+
+type_init(pci_proxy_dev_register_types)
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
 
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: d54edb4176361eed86b903e8f27058363b6c83b3.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h |  4 ++++
 hw/remote/mpqemu-link.c         | 34 +++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
 #include "qemu/thread.h"
 #include "io/channel.h"
 #include "exec/hwaddr.h"
+#include "io/channel-socket.h"
+#include "hw/remote/proxy.h"
 
 #define REMOTE_MAX_FDS 8
 
@@ -XXX,XX +XXX,XX @@ typedef struct {
 bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
 bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp);
 
+uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
+                                         Error **errp);
 bool mpqemu_msg_valid(MPQemuMsg *msg);
 
 #endif
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ fail:
     return ret;
 }
 
+/*
+ * Send msg and wait for a reply with command code RET_MSG.
+ * Returns the message received of size u64 or UINT64_MAX
+ * on error.
+ * Called from VCPU thread in non-coroutine context.
+ * Used by the Proxy object to communicate to remote processes.
+ */
+uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
+                                         Error **errp)
+{
+    ERRP_GUARD();
+    MPQemuMsg msg_reply = {0};
+    uint64_t ret = UINT64_MAX;
+
+    assert(!qemu_in_coroutine());
+
+    QEMU_LOCK_GUARD(&pdev->io_mutex);
+    if (!mpqemu_msg_send(msg, pdev->ioc, errp)) {
+        return ret;
+    }
+
+    if (!mpqemu_msg_recv(&msg_reply, pdev->ioc, errp)) {
+        return ret;
+    }
+
+    if (!mpqemu_msg_valid(&msg_reply)) {
+        error_setg(errp, "ERROR: Invalid reply received for command %d",
+                         msg->cmd);
+        return ret;
+    }
+
+    return msg_reply.data.u64;
+}
+
 bool mpqemu_msg_valid(MPQemuMsg *msg)
 {
     if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) {
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

The Proxy Object sends the PCI config space accesses as messages
to the remote process over the communication channel

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: d3c94f4618813234655356c60e6f0d0362ff42d6.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h | 10 ++++++
 hw/remote/message.c             | 60 +++++++++++++++++++++++++++++++++
 hw/remote/mpqemu-link.c         |  8 ++++-
 hw/remote/proxy.c               | 55 ++++++++++++++++++++++++++++++
 4 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@
  */
 typedef enum {
     MPQEMU_CMD_SYNC_SYSMEM,
+    MPQEMU_CMD_RET,
+    MPQEMU_CMD_PCI_CFGWRITE,
+    MPQEMU_CMD_PCI_CFGREAD,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
@@ -XXX,XX +XXX,XX @@ typedef struct {
     off_t offsets[REMOTE_MAX_FDS];
 } SyncSysmemMsg;
 
+typedef struct {
+    uint32_t addr;
+    uint32_t val;
+    int len;
+} PciConfDataMsg;
+
 /**
  * MPQemuMsg:
  * @cmd: The remote command
@@ -XXX,XX +XXX,XX @@ typedef struct {
 
     union {
         uint64_t u64;
+        PciConfDataMsg pci_conf_data;
         SyncSysmemMsg sync_sysmem;
     } data;
 
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/remote/mpqemu-link.h"
 #include "qapi/error.h"
 #include "sysemu/runstate.h"
+#include "hw/pci/pci.h"
+
+static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
+                                 MPQemuMsg *msg, Error **errp);
+static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
+                                MPQemuMsg *msg, Error **errp);
 
 void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
 {
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         }
 
         switch (msg.cmd) {
+        case MPQEMU_CMD_PCI_CFGWRITE:
+            process_config_write(com->ioc, pci_dev, &msg, &local_err);
+            break;
+        case MPQEMU_CMD_PCI_CFGREAD:
+            process_config_read(com->ioc, pci_dev, &msg, &local_err);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
     }
 }
+
+static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
+                                 MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data;
+    MPQemuMsg ret = { 0 };
+
+    if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) {
+        error_setg(errp, "Bad address for PCI config write, pid "FMT_pid".",
+                   getpid());
+        ret.data.u64 = UINT64_MAX;
+    } else {
+        pci_default_write_config(dev, conf->addr, conf->val, conf->len);
+    }
+
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
+
+static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
+                                MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data;
+    MPQemuMsg ret = { 0 };
+
+    if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) {
+        error_setg(errp, "Bad address for PCI config read, pid "FMT_pid".",
+                   getpid());
+        ret.data.u64 = UINT64_MAX;
+    } else {
+        ret.data.u64 = pci_default_read_config(dev, conf->addr, conf->len);
+    }
+
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev,
         return ret;
     }
 
-    if (!mpqemu_msg_valid(&msg_reply)) {
+    if (!mpqemu_msg_valid(&msg_reply) || msg_reply.cmd != MPQEMU_CMD_RET) {
         error_setg(errp, "ERROR: Invalid reply received for command %d",
                          msg->cmd);
         return ret;
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_PCI_CFGWRITE:
+    case MPQEMU_CMD_PCI_CFGREAD:
+        if (msg->size != sizeof(PciConfDataMsg)) {
+            return false;
+        }
+        break;
     default:
         break;
     }
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "monitor/monitor.h"
 #include "migration/blocker.h"
 #include "qemu/sockets.h"
+#include "hw/remote/mpqemu-link.h"
+#include "qemu/error-report.h"
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     error_free(dev->migration_blocker);
 }
 
+static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
+                           int len, unsigned int op)
+{
+    MPQemuMsg msg = { 0 };
+    uint64_t ret = -EINVAL;
+    Error *local_err = NULL;
+
+    msg.cmd = op;
+    msg.data.pci_conf_data.addr = addr;
+    msg.data.pci_conf_data.val = (op == MPQEMU_CMD_PCI_CFGWRITE) ? *val : 0;
+    msg.data.pci_conf_data.len = len;
+    msg.size = sizeof(PciConfDataMsg);
+
+    ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+
+    if (ret == UINT64_MAX) {
+        error_report("Failed to perform PCI config %s operation",
+                     (op == MPQEMU_CMD_PCI_CFGREAD) ? "READ" : "WRITE");
+    }
+
+    if (op == MPQEMU_CMD_PCI_CFGREAD) {
+        *val = (uint32_t)ret;
+    }
+}
+
+static uint32_t pci_proxy_read_config(PCIDevice *d, uint32_t addr, int len)
+{
+    uint32_t val;
+
+    config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGREAD);
+
+    return val;
+}
+
+static void pci_proxy_write_config(PCIDevice *d, uint32_t addr, uint32_t val,
+                                   int len)
+{
+    /*
+     * Some of the functions access the copy of remote device's PCI config
+     * space which is cached in the proxy device. Therefore, maintain
+     * it updated.
+     */
+    pci_default_write_config(d, addr, val, len);
+
+    config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGWRITE);
+}
+
 static Property proxy_properties[] = {
     DEFINE_PROP_STRING("fd", PCIProxyDev, fd),
     DEFINE_PROP_END_OF_LIST(),
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
 
     k->realize = pci_proxy_dev_realize;
     k->exit = pci_proxy_dev_exit;
+    k->config_read = pci_proxy_read_config;
+    k->config_write = pci_proxy_write_config;
+
     device_class_set_props(dc, proxy_properties);
 }
 
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Proxy device object implements handler for PCI BAR writes and reads.
The handler uses BAR_WRITE/BAR_READ message to communicate to the
remote process with the BAR address and value to be written/read.
The remote process implements handler for BAR_WRITE/BAR_READ
message.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: a8b76714a9688be5552c4c92d089bc9e8a4707ff.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h | 10 ++++
 include/hw/remote/proxy.h       |  9 ++++
 hw/remote/message.c             | 83 +++++++++++++++++++++++++++++++++
 hw/remote/mpqemu-link.c         |  6 +++
 hw/remote/proxy.c               | 60 ++++++++++++++++++++++++
 5 files changed, 168 insertions(+)

diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     MPQEMU_CMD_RET,
     MPQEMU_CMD_PCI_CFGWRITE,
     MPQEMU_CMD_PCI_CFGREAD,
+    MPQEMU_CMD_BAR_WRITE,
+    MPQEMU_CMD_BAR_READ,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
@@ -XXX,XX +XXX,XX @@ typedef struct {
     int len;
 } PciConfDataMsg;
 
+typedef struct {
+    hwaddr addr;
+    uint64_t val;
+    unsigned size;
+    bool memory;
+} BarAccessMsg;
+
 /**
  * MPQemuMsg:
  * @cmd: The remote command
@@ -XXX,XX +XXX,XX @@ typedef struct {
         uint64_t u64;
         PciConfDataMsg pci_conf_data;
         SyncSysmemMsg sync_sysmem;
+        BarAccessMsg bar_access;
     } data;
 
     int fds[REMOTE_MAX_FDS];
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/proxy.h
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
 
+typedef struct ProxyMemoryRegion {
+    PCIProxyDev *dev;
+    MemoryRegion mr;
+    bool memory;
+    bool present;
+    uint8_t type;
+} ProxyMemoryRegion;
+
 struct PCIProxyDev {
     PCIDevice parent_dev;
     char *fd;
@@ -XXX,XX +XXX,XX @@ struct PCIProxyDev {
     QemuMutex io_mutex;
     QIOChannel *ioc;
     Error *migration_blocker;
+    ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
 #endif /* PROXY_H */
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "qapi/error.h"
 #include "sysemu/runstate.h"
 #include "hw/pci/pci.h"
+#include "exec/memattrs.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
 static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
                                 MPQemuMsg *msg, Error **errp);
+static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp);
+static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp);
 
 void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
 {
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_PCI_CFGREAD:
             process_config_read(com->ioc, pci_dev, &msg, &local_err);
             break;
+        case MPQEMU_CMD_BAR_WRITE:
+            process_bar_write(com->ioc, &msg, &local_err);
+            break;
+        case MPQEMU_CMD_BAR_READ:
+            process_bar_read(com->ioc, &msg, &local_err);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
@@ -XXX,XX +XXX,XX @@ static void process_config_read(QIOChannel *ioc, PCIDevice *dev,
                       getpid());
     }
 }
+
+static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    BarAccessMsg *bar_access = &msg->data.bar_access;
+    AddressSpace *as =
+        bar_access->memory ? &address_space_memory : &address_space_io;
+    MPQemuMsg ret = { 0 };
+    MemTxResult res;
+    uint64_t val;
+
+    if (!is_power_of_2(bar_access->size) ||
+       (bar_access->size > sizeof(uint64_t))) {
+        ret.data.u64 = UINT64_MAX;
+        goto fail;
+    }
+
+    val = cpu_to_le64(bar_access->val);
+
+    res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED,
+                           (void *)&val, bar_access->size, true);
+
+    if (res != MEMTX_OK) {
+        error_setg(errp, "Bad address %"PRIx64" for mem write, pid "FMT_pid".",
+                   bar_access->addr, getpid());
+        ret.data.u64 = -1;
+    }
+
+fail:
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
+
+static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp)
+{
+    ERRP_GUARD();
+    BarAccessMsg *bar_access = &msg->data.bar_access;
+    MPQemuMsg ret = { 0 };
+    AddressSpace *as;
+    MemTxResult res;
+    uint64_t val = 0;
+
+    as = bar_access->memory ? &address_space_memory : &address_space_io;
+
+    if (!is_power_of_2(bar_access->size) ||
+       (bar_access->size > sizeof(uint64_t))) {
+        val = UINT64_MAX;
+        goto fail;
+    }
+
+    res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED,
+                           (void *)&val, bar_access->size, false);
+
+    if (res != MEMTX_OK) {
+        error_setg(errp, "Bad address %"PRIx64" for mem read, pid "FMT_pid".",
+                   bar_access->addr, getpid());
+        val = UINT64_MAX;
+    }
+
+fail:
+    ret.cmd = MPQEMU_CMD_RET;
+    ret.data.u64 = le64_to_cpu(val);
+    ret.size = sizeof(ret.data.u64);
+
+    if (!mpqemu_msg_send(&ret, ioc, NULL)) {
+        error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ",
+                      getpid());
+    }
+}
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_BAR_WRITE:
+    case MPQEMU_CMD_BAR_READ:
+        if ((msg->size != sizeof(BarAccessMsg)) || (msg->num_fds != 0)) {
+            return false;
+        }
+        break;
     default:
         break;
     }
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_register_types(void)
 }
 
 type_init(pci_proxy_dev_register_types)
+
+static void send_bar_access_msg(PCIProxyDev *pdev, MemoryRegion *mr,
+                                bool write, hwaddr addr, uint64_t *val,
+                                unsigned size, bool memory)
+{
+    MPQemuMsg msg = { 0 };
+    long ret = -EINVAL;
+    Error *local_err = NULL;
+
+    msg.size = sizeof(BarAccessMsg);
+    msg.data.bar_access.addr = mr->addr + addr;
+    msg.data.bar_access.size = size;
+    msg.data.bar_access.memory = memory;
+
+    if (write) {
+        msg.cmd = MPQEMU_CMD_BAR_WRITE;
+        msg.data.bar_access.val = *val;
+    } else {
+        msg.cmd = MPQEMU_CMD_BAR_READ;
+    }
+
+    ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+
+    if (!write) {
+        *val = ret;
+    }
+}
+
+static void proxy_bar_write(void *opaque, hwaddr addr, uint64_t val,
+                            unsigned size)
+{
+    ProxyMemoryRegion *pmr = opaque;
+
+    send_bar_access_msg(pmr->dev, &pmr->mr, true, addr, &val, size,
+                        pmr->memory);
+}
+
+static uint64_t proxy_bar_read(void *opaque, hwaddr addr, unsigned size)
+{
+    ProxyMemoryRegion *pmr = opaque;
+    uint64_t val;
+
+    send_bar_access_msg(pmr->dev, &pmr->mr, false, addr, &val, size,
+                        pmr->memory);
+
+    return val;
+}
+
+const MemoryRegionOps proxy_mr_ops = {
+    .read = proxy_bar_read,
+    .write = proxy_bar_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+};
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Add ProxyMemoryListener object which is used to keep the view of the RAM
in sync between QEMU and remote process.
A MemoryListener is registered for system-memory AddressSpace. The
listener sends SYNC_SYSMEM message to the remote process when memory
listener commits the changes to memory, the remote process receives
the message and processes it in the handler for SYNC_SYSMEM message.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 04fe4e6a9ca90d4f11ab6f59be7652f5b086a071.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                               |   2 +
 include/hw/remote/proxy-memory-listener.h |  28 +++
 include/hw/remote/proxy.h                 |   2 +
 hw/remote/message.c                       |   4 +
 hw/remote/proxy-memory-listener.c         | 227 ++++++++++++++++++++++
 hw/remote/proxy.c                         |   6 +
 hw/remote/meson.build                     |   1 +
 7 files changed, 270 insertions(+)
 create mode 100644 include/hw/remote/proxy-memory-listener.h
 create mode 100644 hw/remote/proxy-memory-listener.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: include/hw/remote/memory.h
 F: hw/remote/memory.c
 F: hw/remote/proxy.c
 F: include/hw/remote/proxy.h
+F: hw/remote/proxy-memory-listener.c
+F: include/hw/remote/proxy-memory-listener.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/remote/proxy-memory-listener.h b/include/hw/remote/proxy-memory-listener.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/proxy-memory-listener.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 PROXY_MEMORY_LISTENER_H
+#define PROXY_MEMORY_LISTENER_H
+
+#include "exec/memory.h"
+#include "io/channel.h"
+
+typedef struct ProxyMemoryListener {
+    MemoryListener listener;
+
+    int n_mr_sections;
+    MemoryRegionSection *mr_sections;
+
+    QIOChannel *ioc;
+} ProxyMemoryListener;
+
+void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener,
+                                     QIOChannel *ioc);
+void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener);
+
+#endif
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/proxy.h
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
 
 #include "hw/pci/pci.h"
 #include "io/channel.h"
+#include "hw/remote/proxy-memory-listener.h"
 
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
@@ -XXX,XX +XXX,XX @@ struct PCIProxyDev {
     QemuMutex io_mutex;
     QIOChannel *ioc;
     Error *migration_blocker;
+    ProxyMemoryListener proxy_listener;
     ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/runstate.h"
 #include "hw/pci/pci.h"
 #include "exec/memattrs.h"
+#include "hw/remote/memory.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_BAR_READ:
             process_bar_read(com->ioc, &msg, &local_err);
             break;
+        case MPQEMU_CMD_SYNC_SYSMEM:
+            remote_sysmem_reconfig(&msg, &local_err);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/proxy-memory-listener.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "qemu/compiler.h"
+#include "qemu/int128.h"
+#include "qemu/range.h"
+#include "exec/memory.h"
+#include "exec/cpu-common.h"
+#include "cpu.h"
+#include "exec/ram_addr.h"
+#include "exec/address-spaces.h"
+#include "qapi/error.h"
+#include "hw/remote/mpqemu-link.h"
+#include "hw/remote/proxy-memory-listener.h"
+
+/*
+ * TODO: get_fd_from_hostaddr(), proxy_mrs_can_merge() and
+ * proxy_memory_listener_commit() defined below perform tasks similar to the
+ * functions defined in vhost-user.c. These functions are good candidates
+ * for refactoring.
+ *
+ */
+
+static void proxy_memory_listener_reset(MemoryListener *listener)
+{
+    ProxyMemoryListener *proxy_listener = container_of(listener,
+                                                       ProxyMemoryListener,
+                                                       listener);
+    int mrs;
+
+    for (mrs = 0; mrs < proxy_listener->n_mr_sections; mrs++) {
+        memory_region_unref(proxy_listener->mr_sections[mrs].mr);
+    }
+
+    g_free(proxy_listener->mr_sections);
+    proxy_listener->mr_sections = NULL;
+    proxy_listener->n_mr_sections = 0;
+}
+
+static int get_fd_from_hostaddr(uint64_t host, ram_addr_t *offset)
+{
+    MemoryRegion *mr;
+    ram_addr_t off;
+
+    /**
+     * Assumes that the host address is a valid address as it's
+     * coming from the MemoryListener system. In the case host
+     * address is not valid, the following call would return
+     * the default subregion of "system_memory" region, and
+     * not NULL. So it's not possible to check for NULL here.
+     */
+    mr = memory_region_from_host((void *)(uintptr_t)host, &off);
+
+    if (offset) {
+        *offset = off;
+    }
+
+    return memory_region_get_fd(mr);
+}
+
+static bool proxy_mrs_can_merge(uint64_t host, uint64_t prev_host, size_t size)
+{
+    if (((prev_host + size) != host)) {
+        return false;
+    }
+
+    if (get_fd_from_hostaddr(host, NULL) !=
+            get_fd_from_hostaddr(prev_host, NULL)) {
+        return false;
+    }
+
+    return true;
+}
+
+static bool try_merge(ProxyMemoryListener *proxy_listener,
+                      MemoryRegionSection *section)
+{
+    uint64_t mrs_size, mrs_gpa, mrs_page;
+    MemoryRegionSection *prev_sec;
+    bool merged = false;
+    uintptr_t mrs_host;
+    RAMBlock *mrs_rb;
+
+    if (!proxy_listener->n_mr_sections) {
+        return false;
+    }
+
+    mrs_rb = section->mr->ram_block;
+    mrs_page = (uint64_t)qemu_ram_pagesize(mrs_rb);
+    mrs_size = int128_get64(section->size);
+    mrs_gpa = section->offset_within_address_space;
+    mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
+               section->offset_within_region;
+
+    if (get_fd_from_hostaddr(mrs_host, NULL) < 0) {
+        return true;
+    }
+
+    mrs_host = mrs_host & ~(mrs_page - 1);
+    mrs_gpa = mrs_gpa & ~(mrs_page - 1);
+    mrs_size = ROUND_UP(mrs_size, mrs_page);
+
+    prev_sec = proxy_listener->mr_sections +
+               (proxy_listener->n_mr_sections - 1);
+    uint64_t prev_gpa_start = prev_sec->offset_within_address_space;
+    uint64_t prev_size = int128_get64(prev_sec->size);
+    uint64_t prev_gpa_end   = range_get_last(prev_gpa_start, prev_size);
+    uint64_t prev_host_start =
+        (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) +
+        prev_sec->offset_within_region;
+    uint64_t prev_host_end = range_get_last(prev_host_start, prev_size);
+
+    if (mrs_gpa <= (prev_gpa_end + 1)) {
+        g_assert(mrs_gpa > prev_gpa_start);
+
+        if ((section->mr == prev_sec->mr) &&
+            proxy_mrs_can_merge(mrs_host, prev_host_start,
+                                (mrs_gpa - prev_gpa_start))) {
+            uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size);
+            merged = true;
+            prev_sec->offset_within_address_space =
+                MIN(prev_gpa_start, mrs_gpa);
+            prev_sec->offset_within_region =
+                MIN(prev_host_start, mrs_host) -
+                (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr);
+            prev_sec->size = int128_make64(max_end - MIN(prev_host_start,
+                                                         mrs_host));
+        }
+    }
+
+    return merged;
+}
+
+static void proxy_memory_listener_region_addnop(MemoryListener *listener,
+                                                MemoryRegionSection *section)
+{
+    ProxyMemoryListener *proxy_listener = container_of(listener,
+                                                       ProxyMemoryListener,
+                                                       listener);
+
+    if (!memory_region_is_ram(section->mr) ||
+            memory_region_is_rom(section->mr)) {
+        return;
+    }
+
+    if (try_merge(proxy_listener, section)) {
+        return;
+    }
+
+    ++proxy_listener->n_mr_sections;
+    proxy_listener->mr_sections = g_renew(MemoryRegionSection,
+                                          proxy_listener->mr_sections,
+                                          proxy_listener->n_mr_sections);
+    proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1] = *section;
+    proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1].fv = NULL;
+    memory_region_ref(section->mr);
+}
+
+static void proxy_memory_listener_commit(MemoryListener *listener)
+{
+    ProxyMemoryListener *proxy_listener = container_of(listener,
+                                                       ProxyMemoryListener,
+                                                       listener);
+    MPQemuMsg msg;
+    MemoryRegionSection *section;
+    ram_addr_t offset;
+    uintptr_t host_addr;
+    int region;
+    Error *local_err = NULL;
+
+    memset(&msg, 0, sizeof(MPQemuMsg));
+
+    msg.cmd = MPQEMU_CMD_SYNC_SYSMEM;
+    msg.num_fds = proxy_listener->n_mr_sections;
+    msg.size = sizeof(SyncSysmemMsg);
+    if (msg.num_fds > REMOTE_MAX_FDS) {
+        error_report("Number of fds is more than %d", REMOTE_MAX_FDS);
+        return;
+    }
+
+    for (region = 0; region < proxy_listener->n_mr_sections; region++) {
+        section = &proxy_listener->mr_sections[region];
+        msg.data.sync_sysmem.gpas[region] =
+            section->offset_within_address_space;
+        msg.data.sync_sysmem.sizes[region] = int128_get64(section->size);
+        host_addr = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
+                    section->offset_within_region;
+        msg.fds[region] = get_fd_from_hostaddr(host_addr, &offset);
+        msg.data.sync_sysmem.offsets[region] = offset;
+    }
+    if (!mpqemu_msg_send(&msg, proxy_listener->ioc, &local_err)) {
+        error_report_err(local_err);
+    }
+}
+
+void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener)
+{
+    memory_listener_unregister(&proxy_listener->listener);
+
+    proxy_memory_listener_reset(&proxy_listener->listener);
+}
+
+void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener,
+                                     QIOChannel *ioc)
+{
+    proxy_listener->n_mr_sections = 0;
+    proxy_listener->mr_sections = NULL;
+
+    proxy_listener->ioc = ioc;
+
+    proxy_listener->listener.begin = proxy_memory_listener_reset;
+    proxy_listener->listener.commit = proxy_memory_listener_commit;
+    proxy_listener->listener.region_add = proxy_memory_listener_region_addnop;
+    proxy_listener->listener.region_nop = proxy_memory_listener_region_addnop;
+    proxy_listener->listener.priority = 10;
+
+    memory_listener_register(&proxy_listener->listener,
+                             &address_space_memory);
+}
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/sockets.h"
 #include "hw/remote/mpqemu-link.h"
 #include "qemu/error-report.h"
+#include "hw/remote/proxy-memory-listener.h"
+#include "qom/object.h"
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 
     qemu_mutex_init(&dev->io_mutex);
     qio_channel_set_blocking(dev->ioc, true, NULL);
+
+    proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     migrate_del_blocker(dev->migration_blocker);
 
     error_free(dev->migration_blocker);
+
+    proxy_memory_listener_deconfigure(&dev->proxy_listener);
 }
 
 static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
+specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c'))
 
 softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss)
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

IOHUB object is added to manage PCI IRQs. It uses KVM_IRQFD
ioctl to create irqfd to injecting PCI interrupts to the guest.
IOHUB object forwards the irqfd to the remote process. Remote process
uses this fd to directly send interrupts to the guest, bypassing QEMU.

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 51d5c3d54e28a68b002e3875c59599c9f5a424a1.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 MAINTAINERS                     |   2 +
 include/hw/pci/pci_ids.h        |   3 +
 include/hw/remote/iohub.h       |  42 +++++++++++
 include/hw/remote/machine.h     |   2 +
 include/hw/remote/mpqemu-link.h |   1 +
 include/hw/remote/proxy.h       |   4 ++
 hw/remote/iohub.c               | 119 ++++++++++++++++++++++++++++++++
 hw/remote/machine.c             |  10 +++
 hw/remote/message.c             |   4 ++
 hw/remote/mpqemu-link.c         |   5 ++
 hw/remote/proxy.c               |  56 +++++++++++++++
 hw/remote/meson.build           |   1 +
 12 files changed, 249 insertions(+)
 create mode 100644 include/hw/remote/iohub.h
 create mode 100644 hw/remote/iohub.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/remote/proxy.c
 F: include/hw/remote/proxy.h
 F: hw/remote/proxy-memory-listener.c
 F: include/hw/remote/proxy-memory-listener.h
+F: hw/remote/iohub.c
+F: include/hw/remote/iohub.h
 
 Build and test automation
 -------------------------
diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/pci/pci_ids.h
+++ b/include/hw/pci/pci_ids.h
@@ -XXX,XX +XXX,XX @@
 #define PCI_DEVICE_ID_SUN_SIMBA          0x5000
 #define PCI_DEVICE_ID_SUN_SABRE          0xa000
 
+#define PCI_VENDOR_ID_ORACLE             0x108e
+#define PCI_DEVICE_ID_REMOTE_IOHUB       0xb000
+
 #define PCI_VENDOR_ID_CMD                0x1095
 #define PCI_DEVICE_ID_CMD_646            0x0646
 
diff --git a/include/hw/remote/iohub.h b/include/hw/remote/iohub.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/remote/iohub.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * IO Hub for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 REMOTE_IOHUB_H
+#define REMOTE_IOHUB_H
+
+#include "hw/pci/pci.h"
+#include "qemu/event_notifier.h"
+#include "qemu/thread-posix.h"
+#include "hw/remote/mpqemu-link.h"
+
+#define REMOTE_IOHUB_NB_PIRQS    PCI_DEVFN_MAX
+
+typedef struct ResampleToken {
+    void *iohub;
+    int pirq;
+} ResampleToken;
+
+typedef struct RemoteIOHubState {
+    PCIDevice d;
+    EventNotifier irqfds[REMOTE_IOHUB_NB_PIRQS];
+    EventNotifier resamplefds[REMOTE_IOHUB_NB_PIRQS];
+    unsigned int irq_level[REMOTE_IOHUB_NB_PIRQS];
+    ResampleToken token[REMOTE_IOHUB_NB_PIRQS];
+    QemuMutex irq_level_lock[REMOTE_IOHUB_NB_PIRQS];
+} RemoteIOHubState;
+
+int remote_iohub_map_irq(PCIDevice *pci_dev, int intx);
+void remote_iohub_set_irq(void *opaque, int pirq, int level);
+void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg);
+
+void remote_iohub_init(RemoteIOHubState *iohub);
+void remote_iohub_finalize(RemoteIOHubState *iohub);
+
+#endif
diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/machine.h
+++ b/include/hw/remote/machine.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/boards.h"
 #include "hw/pci-host/remote.h"
 #include "io/channel.h"
+#include "hw/remote/iohub.h"
 
 struct RemoteMachineState {
     MachineState parent_obj;
 
     RemotePCIHost *host;
+    RemoteIOHubState iohub;
 };
 
 /* Used to pass to co-routine device and ioc. */
diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/mpqemu-link.h
+++ b/include/hw/remote/mpqemu-link.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     MPQEMU_CMD_PCI_CFGREAD,
     MPQEMU_CMD_BAR_WRITE,
     MPQEMU_CMD_BAR_READ,
+    MPQEMU_CMD_SET_IRQFD,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 
diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/remote/proxy.h
+++ b/include/hw/remote/proxy.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci/pci.h"
 #include "io/channel.h"
 #include "hw/remote/proxy-memory-listener.h"
+#include "qemu/event_notifier.h"
 
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
@@ -XXX,XX +XXX,XX @@ struct PCIProxyDev {
     QIOChannel *ioc;
     Error *migration_blocker;
     ProxyMemoryListener proxy_listener;
+    int virq;
+    EventNotifier intr;
+    EventNotifier resample;
     ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
diff --git a/hw/remote/iohub.c b/hw/remote/iohub.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/remote/iohub.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Remote IO Hub
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * 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 "qemu-common.h"
+
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_ids.h"
+#include "hw/pci/pci_bus.h"
+#include "qemu/thread.h"
+#include "hw/boards.h"
+#include "hw/remote/machine.h"
+#include "hw/remote/iohub.h"
+#include "qemu/main-loop.h"
+
+void remote_iohub_init(RemoteIOHubState *iohub)
+{
+    int pirq;
+
+    memset(&iohub->irqfds, 0, sizeof(iohub->irqfds));
+    memset(&iohub->resamplefds, 0, sizeof(iohub->resamplefds));
+
+    for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) {
+        qemu_mutex_init(&iohub->irq_level_lock[pirq]);
+        iohub->irq_level[pirq] = 0;
+        event_notifier_init_fd(&iohub->irqfds[pirq], -1);
+        event_notifier_init_fd(&iohub->resamplefds[pirq], -1);
+    }
+}
+
+void remote_iohub_finalize(RemoteIOHubState *iohub)
+{
+    int pirq;
+
+    for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) {
+        qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]),
+                            NULL, NULL, NULL);
+        event_notifier_cleanup(&iohub->irqfds[pirq]);
+        event_notifier_cleanup(&iohub->resamplefds[pirq]);
+        qemu_mutex_destroy(&iohub->irq_level_lock[pirq]);
+    }
+}
+
+int remote_iohub_map_irq(PCIDevice *pci_dev, int intx)
+{
+    return pci_dev->devfn;
+}
+
+void remote_iohub_set_irq(void *opaque, int pirq, int level)
+{
+    RemoteIOHubState *iohub = opaque;
+
+    assert(pirq >= 0);
+    assert(pirq < PCI_DEVFN_MAX);
+
+    QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]);
+
+    if (level) {
+        if (++iohub->irq_level[pirq] == 1) {
+            event_notifier_set(&iohub->irqfds[pirq]);
+        }
+    } else if (iohub->irq_level[pirq] > 0) {
+        iohub->irq_level[pirq]--;
+    }
+}
+
+static void intr_resample_handler(void *opaque)
+{
+    ResampleToken *token = opaque;
+    RemoteIOHubState *iohub = token->iohub;
+    int pirq, s;
+
+    pirq = token->pirq;
+
+    s = event_notifier_test_and_clear(&iohub->resamplefds[pirq]);
+
+    assert(s >= 0);
+
+    QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]);
+
+    if (iohub->irq_level[pirq]) {
+        event_notifier_set(&iohub->irqfds[pirq]);
+    }
+}
+
+void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg)
+{
+    RemoteMachineState *machine = REMOTE_MACHINE(current_machine);
+    RemoteIOHubState *iohub = &machine->iohub;
+    int pirq, intx;
+
+    intx = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+
+    pirq = remote_iohub_map_irq(pci_dev, intx);
+
+    if (event_notifier_get_fd(&iohub->irqfds[pirq]) != -1) {
+        qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]),
+                            NULL, NULL, NULL);
+        event_notifier_cleanup(&iohub->irqfds[pirq]);
+        event_notifier_cleanup(&iohub->resamplefds[pirq]);
+        memset(&iohub->token[pirq], 0, sizeof(ResampleToken));
+    }
+
+    event_notifier_init_fd(&iohub->irqfds[pirq], msg->fds[0]);
+    event_notifier_init_fd(&iohub->resamplefds[pirq], msg->fds[1]);
+
+    iohub->token[pirq].iohub = iohub;
+    iohub->token[pirq].pirq = pirq;
+
+    qemu_set_fd_handler(msg->fds[1], intr_resample_handler, NULL,
+                        &iohub->token[pirq]);
+}
diff --git a/hw/remote/machine.c b/hw/remote/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/machine.c
+++ b/hw/remote/machine.c
@@ -XXX,XX +XXX,XX @@
 #include "exec/address-spaces.h"
 #include "exec/memory.h"
 #include "qapi/error.h"
+#include "hw/pci/pci_host.h"
+#include "hw/remote/iohub.h"
 
 static void remote_machine_init(MachineState *machine)
 {
     MemoryRegion *system_memory, *system_io, *pci_memory;
     RemoteMachineState *s = REMOTE_MACHINE(machine);
     RemotePCIHost *rem_host;
+    PCIHostState *pci_host;
 
     system_memory = get_system_memory();
     system_io = get_system_io();
@@ -XXX,XX +XXX,XX @@ static void remote_machine_init(MachineState *machine)
     memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1);
 
     qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal);
+
+    pci_host = PCI_HOST_BRIDGE(rem_host);
+
+    remote_iohub_init(&s->iohub);
+
+    pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq,
+                 &s->iohub, REMOTE_IOHUB_NB_PIRQS);
 }
 
 static void remote_machine_class_init(ObjectClass *oc, void *data)
diff --git a/hw/remote/message.c b/hw/remote/message.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/message.c
+++ b/hw/remote/message.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci/pci.h"
 #include "exec/memattrs.h"
 #include "hw/remote/memory.h"
+#include "hw/remote/iohub.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
@@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_SYNC_SYSMEM:
             remote_sysmem_reconfig(&msg, &local_err);
             break;
+        case MPQEMU_CMD_SET_IRQFD:
+            process_set_irqfd_msg(pci_dev, &msg);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_SET_IRQFD:
+        if (msg->size || (msg->num_fds != 2)) {
+            return false;
+        }
+        break;
     default:
         break;
     }
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/error-report.h"
 #include "hw/remote/proxy-memory-listener.h"
 #include "qom/object.h"
+#include "qemu/event_notifier.h"
+#include "sysemu/kvm.h"
+#include "util/event_notifier-posix.c"
+
+static void proxy_intx_update(PCIDevice *pci_dev)
+{
+    PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev);
+    PCIINTxRoute route;
+    int pin = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+
+    if (dev->virq != -1) {
+        kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &dev->intr, dev->virq);
+        dev->virq = -1;
+    }
+
+    route = pci_device_route_intx_to_irq(pci_dev, pin);
+
+    dev->virq = route.irq;
+
+    if (dev->virq != -1) {
+        kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &dev->intr,
+                                           &dev->resample, dev->virq);
+    }
+}
+
+static void setup_irqfd(PCIProxyDev *dev)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    MPQemuMsg msg;
+    Error *local_err = NULL;
+
+    event_notifier_init(&dev->intr, 0);
+    event_notifier_init(&dev->resample, 0);
+
+    memset(&msg, 0, sizeof(MPQemuMsg));
+    msg.cmd = MPQEMU_CMD_SET_IRQFD;
+    msg.num_fds = 2;
+    msg.fds[0] = event_notifier_get_fd(&dev->intr);
+    msg.fds[1] = event_notifier_get_fd(&dev->resample);
+    msg.size = 0;
+
+    if (!mpqemu_msg_send(&msg, dev->ioc, &local_err)) {
+        error_report_err(local_err);
+    }
+
+    dev->virq = -1;
+
+    proxy_intx_update(pci_dev);
+
+    pci_device_set_intx_routing_notifier(pci_dev, proxy_intx_update);
+}
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
     qio_channel_set_blocking(dev->ioc, true, NULL);
 
     proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
+
+    setup_irqfd(dev);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     error_free(dev->migration_blocker);
 
     proxy_memory_listener_deconfigure(&dev->proxy_listener);
+
+    event_notifier_cleanup(&dev->intr);
+    event_notifier_cleanup(&dev->resample);
 }
 
 static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c'))
-- 
2.29.2

From: Jagannathan Raman <jag.raman@oracle.com>

Retrieve PCI configuration info about the remote device and
configure the Proxy PCI object based on the returned information

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 85ee367bbb993aa23699b44cfedd83b4ea6d5221.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/remote/proxy.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 84 insertions(+)

diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/kvm.h"
 #include "util/event_notifier-posix.c"
 
+static void probe_pci_info(PCIDevice *dev, Error **errp);
+
 static void proxy_intx_update(PCIDevice *pci_dev)
 {
     PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev);
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
     ERRP_GUARD();
     PCIProxyDev *dev = PCI_PROXY_DEV(device);
+    uint8_t *pci_conf = device->config;
     int fd;
 
     if (!dev->fd) {
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
     qemu_mutex_init(&dev->io_mutex);
     qio_channel_set_blocking(dev->ioc, true, NULL);
 
+    pci_conf[PCI_LATENCY_TIMER] = 0xff;
+    pci_conf[PCI_INTERRUPT_PIN] = 0x01;
+
     proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
 
     setup_irqfd(dev);
+
+    probe_pci_info(PCI_DEVICE(dev), errp);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -XXX,XX +XXX,XX @@ const MemoryRegionOps proxy_mr_ops = {
         .max_access_size = 8,
     },
 };
+
+static void probe_pci_info(PCIDevice *dev, Error **errp)
+{
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
+    uint32_t orig_val, new_val, base_class, val;
+    PCIProxyDev *pdev = PCI_PROXY_DEV(dev);
+    DeviceClass *dc = DEVICE_CLASS(pc);
+    uint8_t type;
+    int i, size;
+
+    config_op_send(pdev, PCI_VENDOR_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->vendor_id = (uint16_t)val;
+
+    config_op_send(pdev, PCI_DEVICE_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->device_id = (uint16_t)val;
+
+    config_op_send(pdev, PCI_CLASS_DEVICE, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->class_id = (uint16_t)val;
+
+    config_op_send(pdev, PCI_SUBSYSTEM_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD);
+    pc->subsystem_id = (uint16_t)val;
+
+    base_class = pc->class_id >> 4;
+    switch (base_class) {
+    case PCI_BASE_CLASS_BRIDGE:
+        set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+        break;
+    case PCI_BASE_CLASS_STORAGE:
+        set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+        break;
+    case PCI_BASE_CLASS_NETWORK:
+        set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
+        break;
+    case PCI_BASE_CLASS_INPUT:
+        set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
+        break;
+    case PCI_BASE_CLASS_DISPLAY:
+        set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
+        break;
+    case PCI_BASE_CLASS_PROCESSOR:
+        set_bit(DEVICE_CATEGORY_CPU, dc->categories);
+        break;
+    default:
+        set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+        break;
+    }
+
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4,
+                       MPQEMU_CMD_PCI_CFGREAD);
+        new_val = 0xffffffff;
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4,
+                       MPQEMU_CMD_PCI_CFGWRITE);
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4,
+                       MPQEMU_CMD_PCI_CFGREAD);
+        size = (~(new_val & 0xFFFFFFF0)) + 1;
+        config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4,
+                       MPQEMU_CMD_PCI_CFGWRITE);
+        type = (new_val & 0x1) ?
+                   PCI_BASE_ADDRESS_SPACE_IO : PCI_BASE_ADDRESS_SPACE_MEMORY;
+
+        if (size) {
+            g_autofree char *name;
+            pdev->region[i].dev = pdev;
+            pdev->region[i].present = true;
+            if (type == PCI_BASE_ADDRESS_SPACE_MEMORY) {
+                pdev->region[i].memory = true;
+            }
+            name = g_strdup_printf("bar-region-%d", i);
+            memory_region_init_io(&pdev->region[i].mr, OBJECT(pdev),
+                                  &proxy_mr_ops, &pdev->region[i],
+                                  name, size);
+            pci_register_bar(dev, i, type, &pdev->region[i].mr);
+        }
+    }
+}
-- 
2.29.2

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Perform device reset in the remote process when QEMU performs
device reset. This is required to reset the internal state
(like registers, etc...) of emulated devices

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 7cb220a51f565dc0817bd76e2f540e89c2d2b850.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/remote/mpqemu-link.h |  1 +
 hw/remote/message.c             | 22 ++++++++++++++++++++++
 hw/remote/proxy.c               | 19 +++++++++++++++++++
 3 files changed, 42 insertions(+)

From: "Denis V. Lunev" <den@openvz.org>

Original specification says that l1 table size if 64 * l1_size, which
is obviously wrong. The size of the l1 entry is 64 _bits_, not bytes.
Thus 64 is to be replaces with 8 as specification says about bytes.

There is also minor tweak, field name is renamed from l1 to l1_table,
which matches with the later text.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-id: 20210128171313.2210947-1-den@openvz.org
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

[Replace the original commit message "docs: fix mistake in dirty bitmap
feature description" as suggested by Eric Blake.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 docs/interop/parallels.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/interop/parallels.txt b/docs/interop/parallels.txt
index XXXXXXX..XXXXXXX 100644
--- a/docs/interop/parallels.txt
+++ b/docs/interop/parallels.txt
@@ -XXX,XX +XXX,XX @@ of its data area are:
   28 - 31:    l1_size
               The number of entries in the L1 table of the bitmap.
 
-  variable:   l1 (64 * l1_size bytes)
+  variable:   l1_table (8 * l1_size bytes)
               L1 offset table (in bytes)
 
 A dirty bitmap is stored using a one-level structure for the mapping to host
-- 
2.29.2