Series comparison

The following changes since commit f17783e706ab9c7b3a2b69cf48e4f0ba40664f54:

Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20191220' into staging (2020-01-03 18:50:33 +0000)

are available in the Git repository at:

https://github.com/XanClic/qemu.git tags/pull-block-2020-01-06

for you to fetch changes up to 503ca1262bab2c11c533a4816d1ff4297d4f58a6:

backup-top: Begin drain earlier (2020-01-06 14:26:23 +0100)

----------------------------------------------------------------
Block patches:
- Minor fixes and tests from the freeze period (too minor to be included
  in 4.2)
- Allow many bash iotests to test qcow2's external data file feature
- Add compress filter driver
- Fix Python iotests after 6f6e1698a6
- Fix for the backup job

----------------------------------------------------------------
Andrey Shinkevich (3):
  block: introduce compress filter driver
  qcow2: Allow writing compressed data of multiple clusters
  tests/qemu-iotests: add case to write compressed data of multiple
    clusters

Max Reitz (28):
  block: Add bdrv_qapi_perm_to_blk_perm()
  block: Use bdrv_qapi_perm_to_blk_perm()
  blkdebug: Allow taking/unsharing permissions
  iotests: Add @error to wait_until_completed
  iotests: Add test for failing mirror complete
  iotests: s/qocw2/qcow2/
  iotests/qcow2.py: Add dump-header-exts
  iotests/qcow2.py: Split feature fields into bits
  iotests: Add _filter_json_filename
  iotests: Filter refcount_order in 036
  iotests: Replace IMGOPTS by _unsupported_imgopts
  iotests: Drop compat=1.1 in 050
  iotests: Let _make_test_img parse its parameters
  iotests: Add -o and --no-opts to _make_test_img
  iotests: Inject space into -ocompat=0.10 in 051
  iotests: Replace IMGOPTS= by -o
  iotests: Replace IMGOPTS='' by --no-opts
  iotests: Drop IMGOPTS use in 267
  iotests: Avoid qemu-img create
  iotests: Use _rm_test_img for deleting test images
  iotests: Avoid cp/mv of test images
  iotests: Make 091 work with data_file
  iotests: Make 110 work with data_file
  iotests: Make 137 work with data_file
  iotests: Make 198 work with data_file
  iotests: Disable data_file where it cannot be used
  iotests: Allow check -o data_file
  backup-top: Begin drain earlier

PanNengyuan (1):
  throttle-groups: fix memory leak in throttle_group_set_limit:

Philippe Mathieu-Daudé (1):
  tests/qemu-iotests: Update tests to recent desugarized -accel option

Vladimir Sementsov-Ogievskiy (1):
  qcow2-bitmaps: fix qcow2_can_store_new_dirty_bitmap

-- 
2.24.1

We need some way to correlate QAPI BlockPermission values with
BLK_PERM_* flags.  We could:

(1) have the same order in the QAPI definition as the the BLK_PERM_*
    flags are in LSb-first order.  However, then there is no guarantee
    that they actually match (e.g. when someone modifies the QAPI schema
    without thinking of the BLK_PERM_* definitions).
    We could add static assertions, but these would break what’s good
    about this solution, namely its simplicity.

(2) define the BLK_PERM_* flags based on the BlockPermission values.
    But this way whenever someone were to modify the QAPI order
    (perfectly sensible in theory), the BLK_PERM_* values would change.
    Because these values are used for file locking, this might break
    file locking between different qemu versions.

Therefore, go the slightly more cumbersome way: Add a function to
translate from the QAPI constants to the BLK_PERM_* flags.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20191108123455.39445-2-mreitz@redhat.com
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c               | 18 ++++++++++++++++++
 include/block/block.h |  1 +
 2 files changed, 19 insertions(+)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
     *nshared = shared;
 }
 
+uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm)
+{
+    static const uint64_t permissions[] = {
+        [BLOCK_PERMISSION_CONSISTENT_READ]  = BLK_PERM_CONSISTENT_READ,
+        [BLOCK_PERMISSION_WRITE]            = BLK_PERM_WRITE,
+        [BLOCK_PERMISSION_WRITE_UNCHANGED]  = BLK_PERM_WRITE_UNCHANGED,
+        [BLOCK_PERMISSION_RESIZE]           = BLK_PERM_RESIZE,
+        [BLOCK_PERMISSION_GRAPH_MOD]        = BLK_PERM_GRAPH_MOD,
+    };
+
+    QEMU_BUILD_BUG_ON(ARRAY_SIZE(permissions) != BLOCK_PERMISSION__MAX);
+    QEMU_BUILD_BUG_ON(1UL << ARRAY_SIZE(permissions) != BLK_PERM_ALL + 1);
+
+    assert(qapi_perm < BLOCK_PERMISSION__MAX);
+
+    return permissions[qapi_perm];
+}
+
 static void bdrv_replace_child_noperm(BdrvChild *child,
                                       BlockDriverState *new_bs)
 {
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 @@ enum {
 };
 
 char *bdrv_perm_names(uint64_t perm);
+uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm);
 
 /* disk I/O throttling */
 void bdrv_init(void);
-- 
2.24.1

We can save some LoC in xdbg_graph_add_edge() by using
bdrv_qapi_perm_to_blk_perm().

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20191108123455.39445-3-mreitz@redhat.com
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block.c | 29 ++++++++---------------------
 1 file changed, 8 insertions(+), 21 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 xdbg_graph_add_node(XDbgBlockGraphConstructor *gr, void *node,
 static void xdbg_graph_add_edge(XDbgBlockGraphConstructor *gr, void *parent,
                                 const BdrvChild *child)
 {
-    typedef struct {
-        unsigned int flag;
-        BlockPermission num;
-    } PermissionMap;
-
-    static const PermissionMap permissions[] = {
-        { BLK_PERM_CONSISTENT_READ, BLOCK_PERMISSION_CONSISTENT_READ },
-        { BLK_PERM_WRITE,           BLOCK_PERMISSION_WRITE },
-        { BLK_PERM_WRITE_UNCHANGED, BLOCK_PERMISSION_WRITE_UNCHANGED },
-        { BLK_PERM_RESIZE,          BLOCK_PERMISSION_RESIZE },
-        { BLK_PERM_GRAPH_MOD,       BLOCK_PERMISSION_GRAPH_MOD },
-        { 0, 0 }
-    };
-    const PermissionMap *p;
+    BlockPermission qapi_perm;
     XDbgBlockGraphEdge *edge;
 
-    QEMU_BUILD_BUG_ON(1UL << (ARRAY_SIZE(permissions) - 1) != BLK_PERM_ALL + 1);
-
     edge = g_new0(XDbgBlockGraphEdge, 1);
 
     edge->parent = xdbg_graph_node_num(gr, parent);
     edge->child = xdbg_graph_node_num(gr, child->bs);
     edge->name = g_strdup(child->name);
 
-    for (p = permissions; p->flag; p++) {
-        if (p->flag & child->perm) {
-            QAPI_LIST_ADD(edge->perm, p->num);
+    for (qapi_perm = 0; qapi_perm < BLOCK_PERMISSION__MAX; qapi_perm++) {
+        uint64_t flag = bdrv_qapi_perm_to_blk_perm(qapi_perm);
+
+        if (flag & child->perm) {
+            QAPI_LIST_ADD(edge->perm, qapi_perm);
         }
-        if (p->flag & child->shared_perm) {
-            QAPI_LIST_ADD(edge->shared_perm, p->num);
+        if (flag & child->shared_perm) {
+            QAPI_LIST_ADD(edge->shared_perm, qapi_perm);
         }
     }
 
-- 
2.24.1

Sometimes it is useful to be able to add a node to the block graph that
takes or unshare a certain set of permissions for debugging purposes.
This patch adds this capability to blkdebug.

(Note that you cannot make blkdebug release or share permissions that it
needs to take or cannot share, because this might result in assertion
failures in the block layer.  But if the blkdebug node has no parents,
it will not take any permissions and share everything by default, so you
can then freely choose what permissions to take and share.)

Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20191108123455.39445-4-mreitz@redhat.com
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/blkdebug.c     | 93 +++++++++++++++++++++++++++++++++++++++++++-
 qapi/block-core.json | 14 ++++++-
 2 files changed, 105 insertions(+), 2 deletions(-)

diff --git a/block/blkdebug.c b/block/blkdebug.c
index XXXXXXX..XXXXXXX 100644
--- a/block/blkdebug.c
+++ b/block/blkdebug.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/cutils.h"
 #include "qemu/config-file.h"
 #include "block/block_int.h"
+#include "block/qdict.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
+#include "qapi/qapi-visit-block-core.h"
 #include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qlist.h"
 #include "qapi/qmp/qstring.h"
+#include "qapi/qobject-input-visitor.h"
 #include "sysemu/qtest.h"
 
 typedef struct BDRVBlkdebugState {
@@ -XXX,XX +XXX,XX @@ typedef struct BDRVBlkdebugState {
     uint64_t opt_discard;
     uint64_t max_discard;
 
+    uint64_t take_child_perms;
+    uint64_t unshare_child_perms;
+
     /* For blkdebug_refresh_filename() */
     char *config_file;
 
@@ -XXX,XX +XXX,XX @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
     qdict_put_str(options, "x-image", filename);
 }
 
+static int blkdebug_parse_perm_list(uint64_t *dest, QDict *options,
+                                    const char *prefix, Error **errp)
+{
+    int ret = 0;
+    QDict *subqdict = NULL;
+    QObject *crumpled_subqdict = NULL;
+    Visitor *v = NULL;
+    BlockPermissionList *perm_list = NULL, *element;
+    Error *local_err = NULL;
+
+    *dest = 0;
+
+    qdict_extract_subqdict(options, &subqdict, prefix);
+    if (!qdict_size(subqdict)) {
+        goto out;
+    }
+
+    crumpled_subqdict = qdict_crumple(subqdict, errp);
+    if (!crumpled_subqdict) {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    v = qobject_input_visitor_new(crumpled_subqdict);
+    visit_type_BlockPermissionList(v, NULL, &perm_list, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto out;
+    }
+
+    for (element = perm_list; element; element = element->next) {
+        *dest |= bdrv_qapi_perm_to_blk_perm(element->value);
+    }
+
+out:
+    qapi_free_BlockPermissionList(perm_list);
+    visit_free(v);
+    qobject_unref(subqdict);
+    qobject_unref(crumpled_subqdict);
+    return ret;
+}
+
+static int blkdebug_parse_perms(BDRVBlkdebugState *s, QDict *options,
+                                Error **errp)
+{
+    int ret;
+
+    ret = blkdebug_parse_perm_list(&s->take_child_perms, options,
+                                   "take-child-perms.", errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    ret = blkdebug_parse_perm_list(&s->unshare_child_perms, options,
+                                   "unshare-child-perms.", errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return 0;
+}
+
 static QemuOptsList runtime_opts = {
     .name = "blkdebug",
     .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
@@ -XXX,XX +XXX,XX @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     /* Set initial state */
     s->state = 1;
 
+    /* Parse permissions modifiers before opening the image file */
+    ret = blkdebug_parse_perms(s, options, errp);
+    if (ret < 0) {
+        goto out;
+    }
+
     /* Open the image file */
     bs->file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options, "image",
                                bs, &child_file, false, &local_err);
@@ -XXX,XX +XXX,XX @@ static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state,
     return 0;
 }
 
+static void blkdebug_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                const BdrvChildRole *role,
+                                BlockReopenQueue *reopen_queue,
+                                uint64_t perm, uint64_t shared,
+                                uint64_t *nperm, uint64_t *nshared)
+{
+    BDRVBlkdebugState *s = bs->opaque;
+
+    bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared,
+                              nperm, nshared);
+
+    *nperm |= s->take_child_perms;
+    *nshared &= ~s->unshare_child_perms;
+}
+
 static const char *const blkdebug_strong_runtime_opts[] = {
     "config",
     "inject-error.",
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_file_open         = blkdebug_open,
     .bdrv_close             = blkdebug_close,
     .bdrv_reopen_prepare    = blkdebug_reopen_prepare,
-    .bdrv_child_perm        = bdrv_filter_default_perms,
+    .bdrv_child_perm        = blkdebug_child_perm,
 
     .bdrv_getlength         = blkdebug_getlength,
     .bdrv_refresh_filename  = blkdebug_refresh_filename,
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 @@
 #
 # @set-state:       array of state-change descriptions
 #
+# @take-child-perms: Permissions to take on @image in addition to what
+#                    is necessary anyway (which depends on how the
+#                    blkdebug node is used).  Defaults to none.
+#                    (since 5.0)
+#
+# @unshare-child-perms: Permissions not to share on @image in addition
+#                       to what cannot be shared anyway (which depends
+#                       on how the blkdebug node is used).  Defaults
+#                       to none.  (since 5.0)
+#
 # Since: 2.9
 ##
 { 'struct': 'BlockdevOptionsBlkdebug',
@@ -XXX,XX +XXX,XX @@
             '*opt-write-zero': 'int32', '*max-write-zero': 'int32',
             '*opt-discard': 'int32', '*max-discard': 'int32',
             '*inject-error': ['BlkdebugInjectErrorOptions'],
-            '*set-state': ['BlkdebugSetStateOptions'] } }
+            '*set-state': ['BlkdebugSetStateOptions'],
+            '*take-child-perms': ['BlockPermission'],
+            '*unshare-child-perms': ['BlockPermission'] } }
 
 ##
 # @BlockdevOptionsBlklogwrites:
-- 
2.24.1

Callers can use this new parameter to expect failure during the
completion process.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-id: 20191108123455.39445-5-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/iotests.py | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

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 @@ class QMPTestCase(unittest.TestCase):
         self.assert_no_active_block_jobs()
         return result
 
-    def wait_until_completed(self, drive='drive0', check_offset=True, wait=60.0):
+    def wait_until_completed(self, drive='drive0', check_offset=True, wait=60.0,
+                             error=None):
         '''Wait for a block job to finish, returning the event'''
         while True:
             for event in self.vm.get_qmp_events(wait=wait):
                 if event['event'] == 'BLOCK_JOB_COMPLETED':
                     self.assert_qmp(event, 'data/device', drive)
-                    self.assert_qmp_absent(event, 'data/error')
-                    if check_offset:
-                        self.assert_qmp(event, 'data/offset', event['data']['len'])
+                    if error is None:
+                        self.assert_qmp_absent(event, 'data/error')
+                        if check_offset:
+                            self.assert_qmp(event, 'data/offset',
+                                            event['data']['len'])
+                    else:
+                        self.assert_qmp(event, 'data/error', error)
                     self.assert_no_active_block_jobs()
                     return event
                 elif event['event'] == 'JOB_STATUS_CHANGE':
@@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase):
         self.assert_qmp(event, 'data/type', 'mirror')
         self.assert_qmp(event, 'data/offset', event['data']['len'])
 
-    def complete_and_wait(self, drive='drive0', wait_ready=True):
+    def complete_and_wait(self, drive='drive0', wait_ready=True,
+                          completion_error=None):
         '''Complete a block job and wait for it to finish'''
         if wait_ready:
             self.wait_ready(drive=drive)
@@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase):
         result = self.vm.qmp('block-job-complete', device=drive)
         self.assert_qmp(result, 'return', {})
 
-        event = self.wait_until_completed(drive=drive)
+        event = self.wait_until_completed(drive=drive, error=completion_error)
         self.assert_qmp(event, 'data/type', 'mirror')
 
     def pause_wait(self, job_id='job0'):
-- 
2.24.1

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Tested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: 20191108123455.39445-6-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/041     | 44 ++++++++++++++++++++++++++++++++++++++
 tests/qemu-iotests/041.out |  4 ++--
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/041
+++ b/tests/qemu-iotests/041
@@ -XXX,XX +XXX,XX @@ class TestOrphanedSource(iotests.QMPTestCase):
                              target='dest-ro')
         self.assert_qmp(result, 'error/class', 'GenericError')
 
+    def test_failing_permission_in_complete(self):
+        self.assert_no_active_block_jobs()
+
+        # Unshare consistent-read on the target
+        # (The mirror job does not care)
+        result = self.vm.qmp('blockdev-add',
+                             driver='blkdebug',
+                             node_name='dest-perm',
+                             image='dest',
+                             unshare_child_perms=['consistent-read'])
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('blockdev-mirror', job_id='job', device='src',
+                             sync='full', target='dest',
+                             filter_node_name='mirror-filter')
+        self.assert_qmp(result, 'return', {})
+
+        # Require consistent-read on the source
+        # (We can only add this node once the job has started, or it
+        # will complain that it does not want to run on non-root nodes)
+        result = self.vm.qmp('blockdev-add',
+                             driver='blkdebug',
+                             node_name='src-perm',
+                             image='src',
+                             take_child_perms=['consistent-read'])
+        self.assert_qmp(result, 'return', {})
+
+        # While completing, mirror will attempt to replace src by
+        # dest, which must fail because src-perm requires
+        # consistent-read but dest-perm does not share it; thus
+        # aborting the job when it is supposed to complete
+        self.complete_and_wait('job',
+                               completion_error='Operation not permitted')
+
+        # Assert that all of our nodes are still there (except for the
+        # mirror filter, which should be gone despite the failure)
+        nodes = self.vm.qmp('query-named-block-nodes')['return']
+        nodes = [node['node-name'] for node in nodes]
+
+        for expect in ('src', 'src-perm', 'dest', 'dest-perm'):
+            self.assertTrue(expect in nodes, '%s disappeared' % expect)
+        self.assertFalse('mirror-filter' in nodes,
+                         'Mirror filter node did not disappear')
+
 if __name__ == '__main__':
     iotests.main(supported_fmts=['qcow2', 'qed'],
                  supported_protocols=['file'])
diff --git a/tests/qemu-iotests/041.out b/tests/qemu-iotests/041.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/041.out
+++ b/tests/qemu-iotests/041.out
@@ -XXX,XX +XXX,XX @@
-..........................................................................................
+...........................................................................................
 ----------------------------------------------------------------------
-Ran 90 tests
+Ran 91 tests
 
 OK
-- 
2.24.1

From: PanNengyuan <pannengyuan@huawei.com>

This avoid a memory leak when qom-set is called to set throttle_group
limits, here is an easy way to reproduce:

1. run qemu-iotests as follow and check the result with asan:
       ./check -qcow2 184

Following is the asan output backtrack:
Direct leak of 912 byte(s) in 3 object(s) allocated from:
    #0 0xffff8d7ab3c3 in __interceptor_calloc   (/lib64/libasan.so.4+0xd33c3)
    #1 0xffff8d4c31cb in g_malloc0   (/lib64/libglib-2.0.so.0+0x571cb)
    #2 0x190c857 in qobject_input_start_struct  /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qapi/qobject-input-visitor.c:295
    #3 0x19070df in visit_start_struct   /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qapi/qapi-visit-core.c:49
    #4 0x1948b87 in visit_type_ThrottleLimits   qapi/qapi-visit-block-core.c:3759
    #5 0x17e4aa3 in throttle_group_set_limits   /mnt/sdc/qemu-master/qemu-4.2.0-rc0/block/throttle-groups.c:900
    #6 0x1650eff in object_property_set     /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qom/object.c:1272
    #7 0x1658517 in object_property_set_qobject   /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qom/qom-qobject.c:26
    #8 0x15880bb in qmp_qom_set  /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qom/qom-qmp-cmds.c:74
    #9 0x157e3e3 in qmp_marshal_qom_set  qapi/qapi-commands-qom.c:154

Reported-by: Euler Robot <euler.robot@huawei.com>
Signed-off-by: PanNengyuan <pannengyuan@huawei.com>
Message-id: 1574835614-42028-1-git-send-email-pannengyuan@huawei.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/throttle-groups.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/throttle-groups.c b/block/throttle-groups.c
index XXXXXXX..XXXXXXX 100644
--- a/block/throttle-groups.c
+++ b/block/throttle-groups.c
@@ -XXX,XX +XXX,XX @@ static void throttle_group_set_limits(Object *obj, Visitor *v,
 {
     ThrottleGroup *tg = THROTTLE_GROUP(obj);
     ThrottleConfig cfg;
-    ThrottleLimits arg = { 0 };
-    ThrottleLimits *argp = &arg;
+    ThrottleLimits *argp;
     Error *local_err = NULL;
 
     visit_type_ThrottleLimits(v, name, &argp, &local_err);
@@ -XXX,XX +XXX,XX @@ static void throttle_group_set_limits(Object *obj, Visitor *v,
 unlock:
     qemu_mutex_unlock(&tg->lock);
 ret:
+    qapi_free_ThrottleLimits(argp);
     error_propagate(errp, local_err);
     return;
 }
-- 
2.24.1

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

qcow2_can_store_new_dirty_bitmap works wrong, as it considers only
bitmaps already stored in the qcow2 image and ignores persistent
BdrvDirtyBitmap objects.

So, let's instead count persistent BdrvDirtyBitmaps. We load all qcow2
bitmaps on open, so there should not be any bitmap in the image for
which we don't have BdrvDirtyBitmaps version. If it is - it's a kind of
corruption, and no reason to check for corruptions here (open() and
close() are better places for it).

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-id: 20191014115126.15360-2-vsementsov@virtuozzo.com
Reviewed-by: Max Reitz <mreitz@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/qcow2-bitmap.c | 41 ++++++++++++++++++-----------------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2-bitmap.c
+++ b/block/qcow2-bitmap.c
@@ -XXX,XX +XXX,XX @@ bool coroutine_fn qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs,
                                                       Error **errp)
 {
     BDRVQcow2State *s = bs->opaque;
-    bool found;
-    Qcow2BitmapList *bm_list;
+    BdrvDirtyBitmap *bitmap;
+    uint64_t bitmap_directory_size = 0;
+    uint32_t nb_bitmaps = 0;
+
+    if (bdrv_find_dirty_bitmap(bs, name)) {
+        error_setg(errp, "Bitmap already exists: %s", name);
+        return false;
+    }
 
     if (s->qcow_version < 3) {
         /* Without autoclear_features, we would always have to assume
@@ -XXX,XX +XXX,XX @@ bool coroutine_fn qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs,
         goto fail;
     }
 
-    if (s->nb_bitmaps == 0) {
-        return true;
+    FOR_EACH_DIRTY_BITMAP(bs, bitmap) {
+        if (bdrv_dirty_bitmap_get_persistence(bitmap)) {
+            nb_bitmaps++;
+            bitmap_directory_size +=
+                calc_dir_entry_size(strlen(bdrv_dirty_bitmap_name(bitmap)), 0);
+        }
     }
+    nb_bitmaps++;
+    bitmap_directory_size += calc_dir_entry_size(strlen(name), 0);
 
-    if (s->nb_bitmaps >= QCOW2_MAX_BITMAPS) {
+    if (nb_bitmaps > QCOW2_MAX_BITMAPS) {
         error_setg(errp,
                    "Maximum number of persistent bitmaps is already reached");
         goto fail;
     }
 
-    if (s->bitmap_directory_size + calc_dir_entry_size(strlen(name), 0) >
-        QCOW2_MAX_BITMAP_DIRECTORY_SIZE)
-    {
+    if (bitmap_directory_size > QCOW2_MAX_BITMAP_DIRECTORY_SIZE) {
         error_setg(errp, "Not enough space in the bitmap directory");
         goto fail;
     }
 
-    qemu_co_mutex_lock(&s->lock);
-    bm_list = bitmap_list_load(bs, s->bitmap_directory_offset,
-                               s->bitmap_directory_size, errp);
-    qemu_co_mutex_unlock(&s->lock);
-    if (bm_list == NULL) {
-        goto fail;
-    }
-
-    found = find_bitmap_by_name(bm_list, name);
-    bitmap_list_free(bm_list);
-    if (found) {
-        error_setg(errp, "Bitmap with the same name is already stored");
-        goto fail;
-    }
-
     return true;
 
 fail:
-- 
2.24.1

Probably due to blind copy-pasting, we have several instances of "qocw2"
in our iotests.  Fix them.

Reported-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20191107163708.833192-2-mreitz@redhat.com
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/060 | 2 +-
 tests/qemu-iotests/061 | 2 +-
 tests/qemu-iotests/062 | 2 +-
 tests/qemu-iotests/066 | 2 +-
 tests/qemu-iotests/068 | 2 +-
 tests/qemu-iotests/108 | 2 +-
 tests/qemu-iotests/138 | 2 +-
 tests/qemu-iotests/261 | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/060
+++ b/tests/qemu-iotests/060
@@ -XXX,XX +XXX,XX @@ _filter_io_error()
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/061
+++ b/tests/qemu-iotests/061
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
diff --git a/tests/qemu-iotests/062 b/tests/qemu-iotests/062
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/062
+++ b/tests/qemu-iotests/062
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
 
diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/066
+++ b/tests/qemu-iotests/066
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
 
diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/068
+++ b/tests/qemu-iotests/068
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
 
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
diff --git a/tests/qemu-iotests/138 b/tests/qemu-iotests/138
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/138
+++ b/tests/qemu-iotests/138
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
diff --git a/tests/qemu-iotests/261 b/tests/qemu-iotests/261
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/261
+++ b/tests/qemu-iotests/261
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 . ./common.rc
 . ./common.filter
 
-# This tests qocw2-specific low-level functionality
+# This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-- 
2.24.1

This is useful for tests that want to whitelist fields from dump-header
(with grep) but still print all header extensions.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-3-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/qcow2.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tests/qemu-iotests/qcow2.py b/tests/qemu-iotests/qcow2.py
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/qcow2.py
+++ b/tests/qemu-iotests/qcow2.py
@@ -XXX,XX +XXX,XX @@ def cmd_dump_header(fd):
     h.dump()
     h.dump_extensions()
 
+def cmd_dump_header_exts(fd):
+    h = QcowHeader(fd)
+    h.dump_extensions()
+
 def cmd_set_header(fd, name, value):
     try:
         value = int(value, 0)
@@ -XXX,XX +XXX,XX @@ def cmd_set_feature_bit(fd, group, bit):
 
 cmds = [
     [ 'dump-header',          cmd_dump_header,          0, 'Dump image header and header extensions' ],
+    [ 'dump-header-exts',     cmd_dump_header_exts,     0, 'Dump image header extensions' ],
     [ 'set-header',           cmd_set_header,           2, 'Set a field in the header'],
     [ 'add-header-ext',       cmd_add_header_ext,       2, 'Add a header extension' ],
     [ 'add-header-ext-stdio', cmd_add_header_ext_stdio, 1, 'Add a header extension, data from stdin' ],
-- 
2.24.1

Print the feature fields as a set of bits so that filtering is easier.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-4-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/031.out  | 36 +++++++++----------
 tests/qemu-iotests/036.out  | 18 +++++-----
 tests/qemu-iotests/039.out  | 22 ++++++------
 tests/qemu-iotests/060.out  | 20 +++++------
 tests/qemu-iotests/061.out  | 72 ++++++++++++++++++-------------------
 tests/qemu-iotests/137.out  |  2 +-
 tests/qemu-iotests/qcow2.py | 18 +++++++---
 7 files changed, 99 insertions(+), 89 deletions(-)

diff --git a/tests/qemu-iotests/031.out b/tests/qemu-iotests/031.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/031.out
+++ b/tests/qemu-iotests/031.out
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             104
 
diff --git a/tests/qemu-iotests/036.out b/tests/qemu-iotests/036.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/036.out
+++ b/tests/qemu-iotests/036.out
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x8000000000000000
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     [63]
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x8000000000000000
+incompatible_features     []
+compatible_features       []
+autoclear_features        [63]
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             104
 
diff --git a/tests/qemu-iotests/039.out b/tests/qemu-iotests/039.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/039.out
+++ b/tests/qemu-iotests/039.out
@@ -XXX,XX +XXX,XX @@ QA output created by 039
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-incompatible_features     0x0
+incompatible_features     []
 No errors were found on the image.
 
 == Creating a dirty image file ==
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     0x1
+incompatible_features     [0]
 ERROR cluster 5 refcount=0 reference=1
 ERROR OFLAG_COPIED data cluster: l2_entry=8000000000050000 refcount=0
 
@@ -XXX,XX +XXX,XX @@ Data may be corrupted, or further writes to the image may corrupt it.
 == Read-only access must still work ==
 read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-incompatible_features     0x1
+incompatible_features     [0]
 
 == Repairing the image file must succeed ==
 ERROR cluster 5 refcount=0 reference=1
@@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired:
 
 Double checking the fixed image now...
 No errors were found on the image.
-incompatible_features     0x0
+incompatible_features     []
 
 == Data should still be accessible after repair ==
 read 512/512 bytes at offset 0
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     0x1
+incompatible_features     [0]
 ERROR cluster 5 refcount=0 reference=1
 Rebuilding refcount structure
 Repairing cluster 1 refcount=1 reference=0
 Repairing cluster 2 refcount=1 reference=0
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-incompatible_features     0x0
+incompatible_features     []
 
 == Creating an image file with lazy_refcounts=off ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     0x0
+incompatible_features     []
 No errors were found on the image.
 
 == Committing to a backing file with lazy_refcounts=on ==
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 Image committed.
-incompatible_features     0x0
-incompatible_features     0x0
+incompatible_features     []
+incompatible_features     []
 No errors were found on the image.
 No errors were found on the image.
 
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     0x1
+incompatible_features     [0]
 ERROR cluster 5 refcount=0 reference=1
 ERROR OFLAG_COPIED data cluster: l2_entry=8000000000050000 refcount=0
 
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     0x0
+incompatible_features     []
 No errors were found on the image.
 *** done
diff --git a/tests/qemu-iotests/060.out b/tests/qemu-iotests/060.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/060.out
+++ b/tests/qemu-iotests/060.out
@@ -XXX,XX +XXX,XX @@ ERROR cluster 3 refcount=1 reference=3
 
 1 errors were found on the image.
 Data may be corrupted, or further writes to the image may corrupt it.
-incompatible_features     0x0
+incompatible_features     []
 qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with active L1 table); further corruption events will be suppressed
 write failed: Input/output error
-incompatible_features     0x2
+incompatible_features     [1]
 image: TEST_DIR/t.IMGFMT
 file format: IMGFMT
 virtual size: 64 MiB (67108864 bytes)
@@ -XXX,XX +XXX,XX @@ ERROR cluster 2 refcount=1 reference=2
 
 2 errors were found on the image.
 Data may be corrupted, or further writes to the image may corrupt it.
-incompatible_features     0x0
+incompatible_features     []
 qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with refcount block); further corruption events will be suppressed
 write failed: Input/output error
-incompatible_features     0x2
+incompatible_features     [1]
 ERROR refcount block 0 refcount=2
 ERROR cluster 2 refcount=1 reference=2
 Rebuilding refcount structure
@@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired:
 
 Double checking the fixed image now...
 No errors were found on the image.
-incompatible_features     0x0
+incompatible_features     []
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-incompatible_features     0x0
+incompatible_features     []
 
 === Testing cluster data reference into inactive L2 table ===
 
@@ -XXX,XX +XXX,XX @@ Data may be corrupted, or further writes to the image may corrupt it.
 
 1 leaked clusters were found on the image.
 This means waste of disk space, but no harm to data.
-incompatible_features     0x0
+incompatible_features     []
 qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with inactive L2 table); further corruption events will be suppressed
 write failed: Input/output error
-incompatible_features     0x2
+incompatible_features     [1]
 ERROR cluster 4 refcount=1 reference=2
 Leaked cluster 9 refcount=1 reference=0
 Repairing cluster 4 refcount=1 reference=2
@@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired:
 
 Double checking the fixed image now...
 No errors were found on the image.
-incompatible_features     0x0
+incompatible_features     []
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-incompatible_features     0x0
+incompatible_features     []
 read 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 No errors were found on the image.
diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/061.out
+++ b/tests/qemu-iotests/061.out
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x1
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       [0]
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x1
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       [0]
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x1
-compatible_features       0x1
-autoclear_features        0x0
+incompatible_features     [0]
+compatible_features       [0]
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x80000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x40000000000
-autoclear_features        0x40000000000
+incompatible_features     []
+compatible_features       [42]
+autoclear_features        [42]
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             72
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x1
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       [0]
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x10000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x1
-compatible_features       0x1
-autoclear_features        0x0
+incompatible_features     [0]
+compatible_features       [0]
+autoclear_features        []
 refcount_order            4
 header_length             104
 
@@ -XXX,XX +XXX,XX @@ refcount_table_offset     0x80000
 refcount_table_clusters   1
 nb_snapshots              0
 snapshot_offset           0x0
-incompatible_features     0x0
-compatible_features       0x0
-autoclear_features        0x0
+incompatible_features     []
+compatible_features       []
+autoclear_features        []
 refcount_order            4
 header_length             104
 
diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/137.out
+++ b/tests/qemu-iotests/137.out
@@ -XXX,XX +XXX,XX @@ qemu-io: Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     0x0
+incompatible_features     []
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
 wrote 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
diff --git a/tests/qemu-iotests/qcow2.py b/tests/qemu-iotests/qcow2.py
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/qcow2.py
+++ b/tests/qemu-iotests/qcow2.py
@@ -XXX,XX +XXX,XX @@ class QcowHeader:
         [ uint64_t, '%#x',  'snapshot_offset' ],
 
         # Version 3 header fields
-        [ uint64_t, '%#x',  'incompatible_features' ],
-        [ uint64_t, '%#x',  'compatible_features' ],
-        [ uint64_t, '%#x',  'autoclear_features' ],
+        [ uint64_t, 'mask', 'incompatible_features' ],
+        [ uint64_t, 'mask', 'compatible_features' ],
+        [ uint64_t, 'mask', 'autoclear_features' ],
         [ uint32_t, '%d',   'refcount_order' ],
         [ uint32_t, '%d',   'header_length' ],
     ];
@@ -XXX,XX +XXX,XX @@ class QcowHeader:
 
     def dump(self):
         for f in QcowHeader.fields:
-            print("%-25s" % f[2], f[1] % self.__dict__[f[2]])
+            value = self.__dict__[f[2]]
+            if f[1] == 'mask':
+                bits = []
+                for bit in range(64):
+                    if value & (1 << bit):
+                        bits.append(bit)
+                value_str = str(bits)
+            else:
+                value_str = f[1] % value
+
+            print("%-25s" % f[2], value_str)
         print("")
 
     def dump_extensions(self):
-- 
2.24.1

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-5-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/common.filter | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -XXX,XX +XXX,XX @@ _filter_qmp_empty_return()
     grep -v '{"return": {}}'
 }
 
+_filter_json_filename()
+{
+    $PYTHON -c 'import sys
+result, *fnames = sys.stdin.read().split("json:{")
+depth = 0
+for fname in fnames:
+    depth += 1 # For the opening brace in the split separator
+    for chr_i, chr in enumerate(fname):
+        if chr == "{":
+            depth += 1
+        elif chr == "}":
+            depth -= 1
+            if depth == 0:
+                break
+
+    # json:{} filenames may be nested; filter out everything from
+    # inside the outermost one
+    if depth == 0:
+        chr_i += 1 # First character past the filename
+        result += "json:{ /* filtered */ }" + fname[chr_i:]
+
+sys.stdout.write(result)'
+}
+
 # make sure this script returns success
 true
-- 
2.24.1

This test can run just fine with other values for refcount_bits, so we
should filter the value from qcow2.py's dump-header.  In fact, we can
filter everything but the feature bits and header extensions, because
that is what the test is about.

(036 currently ignores user-specified image options, but that will be
fixed in the next patch.)

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-6-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/036     |  9 ++++---
 tests/qemu-iotests/036.out | 48 --------------------------------------
 2 files changed, 6 insertions(+), 51 deletions(-)

diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/036
+++ b/tests/qemu-iotests/036
@@ -XXX,XX +XXX,XX @@ $PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 63
 
 # Without feature table
 $PYTHON qcow2.py "$TEST_IMG" del-header-ext 0x6803f857
-$PYTHON qcow2.py "$TEST_IMG" dump-header
+$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features
+$PYTHON qcow2.py "$TEST_IMG" dump-header-exts
 _img_info
 
 # With feature table containing bit 63
@@ -XXX,XX +XXX,XX @@ echo === Create image with unknown autoclear feature bit ===
 echo
 _make_test_img 64M
 $PYTHON qcow2.py "$TEST_IMG" set-feature-bit autoclear 63
-$PYTHON qcow2.py "$TEST_IMG" dump-header
+$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features
+$PYTHON qcow2.py "$TEST_IMG" dump-header-exts
 
 echo
 echo === Repair image ===
 echo
 _check_test_img -r all
 
-$PYTHON qcow2.py "$TEST_IMG" dump-header
+$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features
+$PYTHON qcow2.py "$TEST_IMG" dump-header-exts
 
 # success, all done
 echo "*** done"
diff --git a/tests/qemu-iotests/036.out b/tests/qemu-iotests/036.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/036.out
+++ b/tests/qemu-iotests/036.out
@@ -XXX,XX +XXX,XX @@ QA output created by 036
 === Image with unknown incompatible feature bit ===
 
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
-magic                     0x514649fb
-version                   3
-backing_file_offset       0x0
-backing_file_size         0x0
-cluster_bits              16
-size                      67108864
-crypt_method              0
-l1_size                   1
-l1_table_offset           0x30000
-refcount_table_offset     0x10000
-refcount_table_clusters   1
-nb_snapshots              0
-snapshot_offset           0x0
 incompatible_features     [63]
 compatible_features       []
 autoclear_features        []
-refcount_order            4
-header_length             104
-
 qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Unsupported IMGFMT feature(s): Unknown incompatible feature: 8000000000000000
 qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Unsupported IMGFMT feature(s): Test feature
 
@@ -XXX,XX +XXX,XX @@ qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Unsupported IMGFMT feature(s): tes
 === Create image with unknown autoclear feature bit ===
 
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
-magic                     0x514649fb
-version                   3
-backing_file_offset       0x0
-backing_file_size         0x0
-cluster_bits              16
-size                      67108864
-crypt_method              0
-l1_size                   1
-l1_table_offset           0x30000
-refcount_table_offset     0x10000
-refcount_table_clusters   1
-nb_snapshots              0
-snapshot_offset           0x0
 incompatible_features     []
 compatible_features       []
 autoclear_features        [63]
-refcount_order            4
-header_length             104
-
 Header extension:
 magic                     0x6803f857
 length                    192
@@ -XXX,XX +XXX,XX @@ data                      <binary>
 === Repair image ===
 
 No errors were found on the image.
-magic                     0x514649fb
-version                   3
-backing_file_offset       0x0
-backing_file_size         0x0
-cluster_bits              16
-size                      67108864
-crypt_method              0
-l1_size                   1
-l1_table_offset           0x30000
-refcount_table_offset     0x10000
-refcount_table_clusters   1
-nb_snapshots              0
-snapshot_offset           0x0
 incompatible_features     []
 compatible_features       []
 autoclear_features        []
-refcount_order            4
-header_length             104
-
 Header extension:
 magic                     0x6803f857
 length                    192
-- 
2.24.1

Some tests require compat=1.1 and thus set IMGOPTS='compat=1.1'
globally.  That is not how it should be done; instead, they should
simply set _unsupported_imgopts to compat=0.10 (compat=1.1 is the
default anyway).

This makes the tests heed user-specified $IMGOPTS.  Some do not work
with all image options, though, so we need to disable them accordingly.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsky@redhat.com>
Message-id: 20191107163708.833192-7-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/036 | 3 +--
 tests/qemu-iotests/060 | 4 ++--
 tests/qemu-iotests/062 | 3 ++-
 tests/qemu-iotests/066 | 3 ++-
 tests/qemu-iotests/068 | 3 ++-
 tests/qemu-iotests/098 | 4 ++--
 6 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/036
+++ b/tests/qemu-iotests/036
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
-
 # Only qcow2v3 and later supports feature bits
-IMGOPTS="compat=1.1"
+_unsupported_imgopts 'compat=0.10'
 
 echo
 echo === Image with unknown incompatible feature bit ===
diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/060
+++ b/tests/qemu-iotests/060
@@ -XXX,XX +XXX,XX @@ _filter_io_error()
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# These tests only work for compat=1.1 images with refcount_bits=16
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
 
 # The repair process will create a large file - so check for availability first
 _require_large_file 64G
@@ -XXX,XX +XXX,XX @@ l1_offset=196608 # 0x30000 (XXX: just an assumption)
 l2_offset=262144 # 0x40000 (XXX: just an assumption)
 l2_offset_after_snapshot=524288 # 0x80000 (XXX: just an assumption)
 
-IMGOPTS="compat=1.1"
-
 OPEN_RW="open -o overlap-check=all $TEST_IMG"
 # Overlap checks are done before write operations only, therefore opening an
 # image read-only makes the overlap-check option irrelevant
diff --git a/tests/qemu-iotests/062 b/tests/qemu-iotests/062
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/062
+++ b/tests/qemu-iotests/062
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
+# We need zero clusters and snapshots
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]'
 
-IMGOPTS="compat=1.1"
 IMG_SIZE=64M
 
 echo
diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/066
+++ b/tests/qemu-iotests/066
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
+# We need zero clusters and snapshots
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]'
 
 # Intentionally create an unaligned image
-IMGOPTS="compat=1.1"
 IMG_SIZE=$((64 * 1024 * 1024 + 512))
 
 echo
diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/068
+++ b/tests/qemu-iotests/068
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
+# Internal snapshots are (currently) impossible with refcount_bits=1
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]'
 
-IMGOPTS="compat=1.1"
 IMG_SIZE=128K
 
 case "$QEMU_DEFAULT_MACHINE" in
diff --git a/tests/qemu-iotests/098 b/tests/qemu-iotests/098
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/098
+++ b/tests/qemu-iotests/098
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto file
-
-IMGOPTS="compat=1.1"
+# The code path we want to test here only works for compat=1.1 images
+_unsupported_imgopts 'compat=0.10'
 
 for event in l1_update empty_image_prepare reftable_update refblock_alloc; do
 
-- 
2.24.1

This will allow us to add more options than just -b.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-9-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/common.rc | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -XXX,XX +XXX,XX @@ _make_test_img()
     # extra qemu-img options can be added by tests
     # at least one argument (the image size) needs to be added
     local extra_img_options=""
-    local image_size=$*
     local optstr=""
     local img_name=""
     local use_backing=0
     local backing_file=""
     local object_options=""
+    local misc_params=()
 
     if [ -n "$TEST_IMG_FILE" ]; then
         img_name=$TEST_IMG_FILE
@@ -XXX,XX +XXX,XX @@ _make_test_img()
         optstr=$(_optstr_add "$optstr" "key-secret=keysec0")
     fi
 
-    if [ "$1" = "-b" ]; then
-        use_backing=1
-        backing_file=$2
-        image_size=$3
-    fi
+    for param; do
+        if [ "$use_backing" = "1" -a -z "$backing_file" ]; then
+            backing_file=$param
+            continue
+        fi
+
+        case "$param" in
+            -b)
+                use_backing=1
+                ;;
+
+            *)
+                misc_params=("${misc_params[@]}" "$param")
+                ;;
+        esac
+    done
+
     if [ $ "$IMGFMT" = "qcow2" -o "$IMGFMT" = "qed" $ -a -n "$CLUSTER_SIZE" ]; then
         optstr=$(_optstr_add "$optstr" "cluster_size=$CLUSTER_SIZE")
     fi
@@ -XXX,XX +XXX,XX @@ _make_test_img()
     # XXX(hch): have global image options?
     (
      if [ $use_backing = 1 ]; then
-        $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options -b "$backing_file" "$img_name" $image_size 2>&1
+        $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options -b "$backing_file" "$img_name" "${misc_params[@]}" 2>&1
      else
-        $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options "$img_name" $image_size 2>&1
+        $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options "$img_name" "${misc_params[@]}" 2>&1
      fi
     ) | _filter_img_create
 
-- 
2.24.1

Blindly overriding IMGOPTS is suboptimal as this discards user-specified
options.  Whatever options the test needs should simply be appended.

Some tests do this (with IMGOPTS=$(_optstr_add "$IMGOPTS" "...")), but
that is cumbersome.  It’s simpler to just give _make_test_img an -o
parameter with which tests can add options.

Some tests actually must override the user-specified options, though,
for example when creating an image in a different format than the test
$IMGFMT.  For such cases, --no-opts allows clearing the current option
list.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-10-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/common.rc | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -XXX,XX +XXX,XX @@ _make_test_img()
     local use_backing=0
     local backing_file=""
     local object_options=""
+    local opts_param=false
     local misc_params=()
 
     if [ -n "$TEST_IMG_FILE" ]; then
@@ -XXX,XX +XXX,XX @@ _make_test_img()
         if [ "$use_backing" = "1" -a -z "$backing_file" ]; then
             backing_file=$param
             continue
+        elif $opts_param; then
+            optstr=$(_optstr_add "$optstr" "$param")
+            opts_param=false
+            continue
         fi
 
         case "$param" in
@@ -XXX,XX +XXX,XX @@ _make_test_img()
                 use_backing=1
                 ;;
 
+            -o)
+                opts_param=true
+                ;;
+
+            --no-opts)
+                optstr=""
+                ;;
+
             *)
                 misc_params=("${misc_params[@]}" "$param")
                 ;;
-- 
2.24.1

Tests should not overwrite all user-supplied image options, but only add
to it (which will effectively overwrite conflicting values).  Accomplish
this by passing options to _make_test_img via -o instead of $IMGOPTS.

For some tests, there is no functional change because they already only
appended options to IMGOPTS.  For these, this patch is just a
simplification.

For others, this is a change, so they now heed user-specified $IMGOPTS.
Some of those tests do not work with all image options, though, so we
need to disable them accordingly.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-12-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/031 |  9 ++++---
 tests/qemu-iotests/039 | 24 ++++++------------
 tests/qemu-iotests/059 | 18 ++++++-------
 tests/qemu-iotests/060 |  6 ++---
 tests/qemu-iotests/061 | 57 ++++++++++++++++++++++--------------------
 tests/qemu-iotests/079 |  3 +--
 tests/qemu-iotests/106 |  2 +-
 tests/qemu-iotests/108 |  2 +-
 tests/qemu-iotests/112 | 32 ++++++++++++------------
 tests/qemu-iotests/115 |  3 +--
 tests/qemu-iotests/121 |  6 ++---
 tests/qemu-iotests/125 |  2 +-
 tests/qemu-iotests/137 |  2 +-
 tests/qemu-iotests/138 |  3 +--
 tests/qemu-iotests/175 |  2 +-
 tests/qemu-iotests/190 |  2 +-
 tests/qemu-iotests/191 |  3 +--
 tests/qemu-iotests/220 |  4 ++-
 tests/qemu-iotests/243 |  6 +++--
 tests/qemu-iotests/244 | 10 +++++---
 tests/qemu-iotests/250 |  3 +--
 tests/qemu-iotests/265 |  2 +-
 22 files changed, 100 insertions(+), 101 deletions(-)

diff --git a/tests/qemu-iotests/031 b/tests/qemu-iotests/031
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/031
+++ b/tests/qemu-iotests/031
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
+# We want to test compat=0.10, which does not support refcount widths
+# other than 16
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
 
 CLUSTER_SIZE=65536
 
 # qcow2.py output depends on the exact options used, so override the command
 # line here as an exception
-for IMGOPTS in "compat=0.10" "compat=1.1"; do
+for compat in "compat=0.10" "compat=1.1"; do
 
     echo
-    echo ===== Testing with -o $IMGOPTS =====
+    echo ===== Testing with -o $compat =====
     echo
     echo === Create image with unknown header extension ===
     echo
-    _make_test_img 64M
+    _make_test_img -o $compat 64M
     $PYTHON qcow2.py "$TEST_IMG" add-header-ext 0x12345678 "This is a test header extension"
     $PYTHON qcow2.py "$TEST_IMG" dump-header
     _check_test_img
diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/039
+++ b/tests/qemu-iotests/039
@@ -XXX,XX +XXX,XX @@ size=128M
 echo
 echo "== Checking that image is clean on shutdown =="
 
-IMGOPTS="compat=1.1,lazy_refcounts=on"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=on" $size
 
 $QEMU_IO -c "write -P 0x5a 0 512" "$TEST_IMG" | _filter_qemu_io
 
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "== Creating a dirty image file =="
 
-IMGOPTS="compat=1.1,lazy_refcounts=on"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=on" $size
 
 _NO_VALGRIND \
 $QEMU_IO -c "write -P 0x5a 0 512" \
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0x5a 0 512" "$TEST_IMG" | _filter_qemu_io
 echo
 echo "== Opening a dirty image read/write should repair it =="
 
-IMGOPTS="compat=1.1,lazy_refcounts=on"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=on" $size
 
 _NO_VALGRIND \
 $QEMU_IO -c "write -P 0x5a 0 512" \
@@ -XXX,XX +XXX,XX @@ $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features
 echo
 echo "== Creating an image file with lazy_refcounts=off =="
 
-IMGOPTS="compat=1.1,lazy_refcounts=off"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=off" $size
 
 _NO_VALGRIND \
 $QEMU_IO -c "write -P 0x5a 0 512" \
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "== Committing to a backing file with lazy_refcounts=on =="
 
-IMGOPTS="compat=1.1,lazy_refcounts=on"
-TEST_IMG="$TEST_IMG".base _make_test_img $size
+TEST_IMG="$TEST_IMG".base _make_test_img -o "compat=1.1,lazy_refcounts=on" $size
 
-IMGOPTS="compat=1.1,lazy_refcounts=on,backing_file=$TEST_IMG.base"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=on,backing_file=$TEST_IMG.base" $size
 
 $QEMU_IO -c "write 0 512" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG commit "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ TEST_IMG="$TEST_IMG".base _check_test_img
 echo
 echo "== Changing lazy_refcounts setting at runtime =="
 
-IMGOPTS="compat=1.1,lazy_refcounts=off"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=off" $size
 
 _NO_VALGRIND \
 $QEMU_IO -c "reopen -o lazy-refcounts=on" \
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "reopen -o lazy-refcounts=on" \
 $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features
 _check_test_img
 
-IMGOPTS="compat=1.1,lazy_refcounts=on"
-_make_test_img $size
+_make_test_img -o "compat=1.1,lazy_refcounts=on" $size
 
 _NO_VALGRIND \
 $QEMU_IO -c "reopen -o lazy-refcounts=off" \
diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/059
+++ b/tests/qemu-iotests/059
@@ -XXX,XX +XXX,XX @@ poke_file "$TEST_IMG" "$grain_table_size_offset" "\x01\x00\x00\x00"
 
 echo
 echo "=== Testing monolithicFlat creation and opening ==="
-IMGOPTS="subformat=monolithicFlat" _make_test_img 2G
+_make_test_img -o "subformat=monolithicFlat" 2G
 _img_info
 _cleanup_test_img
 
 echo
 echo "=== Testing monolithicFlat with zeroed_grain ==="
-IMGOPTS="subformat=monolithicFlat,zeroed_grain=on" _make_test_img 2G
+_make_test_img -o "subformat=monolithicFlat,zeroed_grain=on" 2G
 _cleanup_test_img
 
 echo
 echo "=== Testing big twoGbMaxExtentFlat ==="
-IMGOPTS="subformat=twoGbMaxExtentFlat" _make_test_img 1000G
+_make_test_img -o "subformat=twoGbMaxExtentFlat" 1000G
 $QEMU_IMG info $TEST_IMG | _filter_testdir | sed -e 's/cid: [0-9]*/cid: XXXXXXXX/'
 _cleanup_test_img
 
@@ -XXX,XX +XXX,XX @@ _img_info
 
 echo
 echo "=== Testing truncated sparse ==="
-IMGOPTS="subformat=monolithicSparse" _make_test_img 100G
+_make_test_img -o "subformat=monolithicSparse" 100G
 truncate -s 10M $TEST_IMG
 _img_info
 
 echo
 echo "=== Converting to streamOptimized from image with small cluster size==="
-TEST_IMG="$TEST_IMG.qcow2" IMGFMT=qcow2 IMGOPTS="cluster_size=4096" _make_test_img 1G
+TEST_IMG="$TEST_IMG.qcow2" IMGFMT=qcow2 _make_test_img -o "cluster_size=4096" 1G
 $QEMU_IO -f qcow2 -c "write -P 0xa 0 512" "$TEST_IMG.qcow2" | _filter_qemu_io
 $QEMU_IO -f qcow2 -c "write -P 0xb 10240 512" "$TEST_IMG.qcow2" | _filter_qemu_io
 $QEMU_IMG convert -f qcow2 -O vmdk -o subformat=streamOptimized "$TEST_IMG.qcow2" "$TEST_IMG" 2>&1
@@ -XXX,XX +XXX,XX @@ echo "=== Testing monolithicFlat with internally generated JSON file name ==="
 
 echo '--- blkdebug ---'
 # Should work, because bdrv_dirname() works fine with blkdebug
-IMGOPTS="subformat=monolithicFlat" _make_test_img 64M
+_make_test_img -o "subformat=monolithicFlat" 64M
 $QEMU_IO -c "open -o driver=$IMGFMT,file.driver=blkdebug,file.image.filename=$TEST_IMG,file.inject-error.0.event=read_aio" \
          -c info \
     2>&1 \
@@ -XXX,XX +XXX,XX @@ _cleanup_test_img
 
 echo '--- quorum ---'
 # Should not work, because bdrv_dirname() does not work with quorum
-IMGOPTS="subformat=monolithicFlat" _make_test_img 64M
+_make_test_img -o "subformat=monolithicFlat" 64M
 cp "$TEST_IMG" "$TEST_IMG.orig"
 
 filename="json:{
@@ -XXX,XX +XXX,XX @@ _cleanup_test_img
 
 echo
 echo "=== Testing 4TB monolithicFlat creation and IO ==="
-IMGOPTS="subformat=monolithicFlat" _make_test_img 4T
+_make_test_img -o "subformat=monolithicFlat" 4T
 _img_info
 $QEMU_IO -c "write -P 0xa 900G 512" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IO -c "read -v 900G 1024" "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ _cleanup_test_img
 echo
 echo "=== Testing qemu-img map on extents ==="
 for fmt in monolithicSparse twoGbMaxExtentSparse; do
-    IMGOPTS="subformat=$fmt" _make_test_img 31G
+    _make_test_img -o "subformat=$fmt" 31G
     $QEMU_IO -c "write 65024 1k" "$TEST_IMG" | _filter_qemu_io
     $QEMU_IO -c "write 2147483136 1k" "$TEST_IMG" | _filter_qemu_io
     $QEMU_IO -c "write 5G 1k" "$TEST_IMG" | _filter_qemu_io
diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/060
+++ b/tests/qemu-iotests/060
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'write 0k 64k' "$BACKING_IMG" | _filter_qemu_io
 # compat=0.10 is required in order to make the following discard actually
 # unallocate the sector rather than make it a zero sector - we want COW, after
 # all.
-IMGOPTS='compat=0.10' _make_test_img -b "$BACKING_IMG" 1G
+_make_test_img -o 'compat=0.10' -b "$BACKING_IMG" 1G
 # Write two clusters, the second one enforces creation of an L2 table after
 # the first data cluster.
 $QEMU_IO -c 'write 0k 64k' -c 'write 512M 64k' "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== Discarding a non-covered in-bounds refblock ==="
 echo
 
-IMGOPTS='refcount_bits=1' _make_test_img 64M
+_make_test_img -o 'refcount_bits=1' 64M
 
 # Pretend there's a refblock somewhere where there is no refblock to
 # cover it (but the covering refblock has a valid index in the
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== Discarding a refblock covered by an unaligned refblock ==="
 echo
 
-IMGOPTS='refcount_bits=1' _make_test_img 64M
+_make_test_img -o 'refcount_bits=1' 64M
 
 # Same as above
 poke_file "$TEST_IMG" "$(($rt_offset+8))" "\x00\x00\x00\x10\x00\x00\x00\x00"
diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/061
+++ b/tests/qemu-iotests/061
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# Conversion between different compat versions can only really work
+# with refcount_bits=16
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
 
 echo
 echo "=== Testing version downgrade with zero expansion ==="
 echo
-IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M
+_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M
 $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io
 $PYTHON qcow2.py "$TEST_IMG" dump-header
 $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing version downgrade with zero expansion and 4K cache entries ==="
 echo
-IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M
+_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M
 $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IO -c "write -z 32M 128k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IO -c map "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing dirty version downgrade ==="
 echo
-IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M
+_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M
 _NO_VALGRIND \
 $QEMU_IO -c "write -P 0x2a 0 128k" -c flush \
          -c "sigraise $(kill -l KILL)" "$TEST_IMG" 2>&1 | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing version downgrade with unknown compat/autoclear flags ==="
 echo
-IMGOPTS="compat=1.1" _make_test_img 64M
+_make_test_img -o "compat=1.1" 64M
 $PYTHON qcow2.py "$TEST_IMG" set-feature-bit compatible 42
 $PYTHON qcow2.py "$TEST_IMG" set-feature-bit autoclear 42
 $PYTHON qcow2.py "$TEST_IMG" dump-header
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing version upgrade and resize ==="
 echo
-IMGOPTS="compat=0.10" _make_test_img 64M
+_make_test_img -o "compat=0.10" 64M
 $QEMU_IO -c "write -P 0x2a 42M 64k" "$TEST_IMG" | _filter_qemu_io
 $PYTHON qcow2.py "$TEST_IMG" dump-header
 $QEMU_IMG amend -o "compat=1.1,lazy_refcounts=on,size=128M" "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing dirty lazy_refcounts=off ==="
 echo
-IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M
+_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M
 _NO_VALGRIND \
 $QEMU_IO -c "write -P 0x2a 0 128k" -c flush \
          -c "sigraise $(kill -l KILL)" "$TEST_IMG" 2>&1 | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing backing file ==="
 echo
-IMGOPTS="compat=1.1" _make_test_img 64M
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+_make_test_img -o "compat=1.1" 64M
+TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io
 $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG amend -o "backing_file=$TEST_IMG.base,backing_fmt=qcow2" "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing invalid configurations ==="
 echo
-IMGOPTS="compat=0.10" _make_test_img 64M
+_make_test_img -o "compat=0.10" 64M
 $QEMU_IMG amend -o "lazy_refcounts=on" "$TEST_IMG"
 $QEMU_IMG amend -o "compat=1.1" "$TEST_IMG" # actually valid
 $QEMU_IMG amend -o "compat=0.10,lazy_refcounts=on" "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ $QEMU_IMG amend -o "preallocation=on" "$TEST_IMG"
 echo
 echo "=== Testing correct handling of unset value ==="
 echo
-IMGOPTS="compat=1.1,cluster_size=1k" _make_test_img 64M
+_make_test_img -o "compat=1.1,cluster_size=1k" 64M
 echo "Should work:"
 $QEMU_IMG amend -o "lazy_refcounts=on" "$TEST_IMG"
 echo "Should not work:" # Just to know which of these tests actually fails
@@ -XXX,XX +XXX,XX @@ $QEMU_IMG amend -o "cluster_size=64k" "$TEST_IMG"
 echo
 echo "=== Testing zero expansion on inactive clusters ==="
 echo
-IMGOPTS="compat=1.1" _make_test_img 64M
+_make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG snapshot -c foo "$TEST_IMG"
 $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io
 echo
 echo "=== Testing zero expansion on shared L2 table ==="
 echo
-IMGOPTS="compat=1.1" _make_test_img 64M
+_make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG snapshot -c foo "$TEST_IMG"
 $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io
 echo
 echo "=== Testing zero expansion on backed image ==="
 echo
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io
-IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 64M
+_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 64M
 $QEMU_IO -c "read -P 0x2a 0 128k" -c "write -z 0 64k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG"
 _check_test_img
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 64k" -c "read -P 0x2a 64k 64k" "$TEST_IMG" | _filter_qe
 echo
 echo "=== Testing zero expansion on backed inactive clusters ==="
 echo
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io
-IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 64M
+_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 64M
 $QEMU_IO -c "write -z 0 64k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG snapshot -c foo "$TEST_IMG"
 $QEMU_IO -c "write -P 0x42 0 128k" "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 64k" -c "read -P 0x2a 64k 64k" "$TEST_IMG" | _filter_qe
 echo
 echo "=== Testing zero expansion on backed image with shared L2 table ==="
 echo
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io
-IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 64M
+_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 64M
 $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io
 $QEMU_IMG snapshot -c foo "$TEST_IMG"
 $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG"
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io
 echo
 echo "=== Testing preallocated zero expansion on full image ==="
 echo
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG" _make_test_img 64M
+TEST_IMG="$TEST_IMG" _make_test_img -o "compat=1.1" 64M
 $QEMU_IO -c "write -P 0x2a 0 64M" "$TEST_IMG" -c "write -z 0 64M" | _filter_qemu_io
 $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG"
 _check_test_img
@@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 64M" "$TEST_IMG" | _filter_qemu_io
 echo
 echo "=== Testing progress report without snapshot ==="
 echo
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 4G
-IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 4G
+TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 4G
+_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 4G
 $QEMU_IO -c "write -z 0  64k" \
          -c "write -z 1G 64k" \
          -c "write -z 2G 64k" \
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing progress report with snapshot ==="
 echo
-IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 4G
-IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 4G
+TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 4G
+_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 4G
 $QEMU_IO -c "write -z 0  64k" \
          -c "write -z 1G 64k" \
          -c "write -z 2G 64k" \
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Testing version downgrade with external data file ==="
 echo
-IMGOPTS="compat=1.1,data_file=$TEST_IMG.data" _make_test_img 64M
+_make_test_img -o "compat=1.1,data_file=$TEST_IMG.data" 64M
 $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG"
 _img_info --format-specific
 _check_test_img
@@ -XXX,XX +XXX,XX @@ _check_test_img
 echo
 echo "=== Try changing the external data file ==="
 echo
-IMGOPTS="compat=1.1" _make_test_img 64M
+_make_test_img -o "compat=1.1" 64M
 $QEMU_IMG amend -o "data_file=foo" "$TEST_IMG"
 
 echo
-IMGOPTS="compat=1.1,data_file=$TEST_IMG.data" _make_test_img 64M
+_make_test_img -o "compat=1.1,data_file=$TEST_IMG.data" 64M
 $QEMU_IMG amend -o "data_file=foo" "$TEST_IMG"
 _img_info --format-specific
 TEST_IMG="data-file.filename=$TEST_IMG.data,file.filename=$TEST_IMG" _img_info --format-specific --image-opts
@@ -XXX,XX +XXX,XX @@ TEST_IMG="data-file.filename=$TEST_IMG.data,file.filename=$TEST_IMG" _img_info -
 echo
 echo "=== Clearing and setting data-file-raw ==="
 echo
-IMGOPTS="compat=1.1,data_file=$TEST_IMG.data,data_file_raw=on" _make_test_img 64M
+_make_test_img -o "compat=1.1,data_file=$TEST_IMG.data,data_file_raw=on" 64M
 $QEMU_IMG amend -o "data_file_raw=on" "$TEST_IMG"
 _img_info --format-specific
 _check_test_img
diff --git a/tests/qemu-iotests/079 b/tests/qemu-iotests/079
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/079
+++ b/tests/qemu-iotests/079
@@ -XXX,XX +XXX,XX @@ echo
 cluster_sizes="16384 32768 65536 131072 262144 524288 1048576 2097152 4194304"
 
 for s in $cluster_sizes; do
-    IMGOPTS=$(_optstr_add "$IMGOPTS" "preallocation=metadata,cluster_size=$s") \
-        _make_test_img 4G
+    _make_test_img -o "preallocation=metadata,cluster_size=$s" 4G
 done
 
 # success, all done
diff --git a/tests/qemu-iotests/106 b/tests/qemu-iotests/106
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/106
+++ b/tests/qemu-iotests/106
@@ -XXX,XX +XXX,XX @@ for create_mode in off falloc full; do
         echo
         echo "--- create_mode=$create_mode growth_mode=$growth_mode ---"
 
-        IMGOPTS="preallocation=$create_mode" _make_test_img ${CREATION_SIZE}K
+        _make_test_img -o "preallocation=$create_mode" ${CREATION_SIZE}K
         $QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K
 
         expected_size=0
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Repairing unreferenced data cluster in new refblock area ==='
 echo
 
-IMGOPTS='cluster_size=512' _make_test_img 64M
+_make_test_img -o 'cluster_size=512' 64M
 # Allocate the first 128 kB in the image (first refblock)
 $QEMU_IO -c 'write 0 0x1b200' "$TEST_IMG" | _filter_qemu_io
 # should be 131072 == 0x20000
diff --git a/tests/qemu-iotests/112 b/tests/qemu-iotests/112
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/112
+++ b/tests/qemu-iotests/112
@@ -XXX,XX +XXX,XX @@ echo '=== refcount_bits limits ==='
 echo
 
 # Must be positive (non-zero)
-IMGOPTS="$IMGOPTS,refcount_bits=0" _make_test_img 64M
+_make_test_img -o "refcount_bits=0" 64M
 # Must be positive (non-negative)
-IMGOPTS="$IMGOPTS,refcount_bits=-1" _make_test_img 64M
+_make_test_img -o "refcount_bits=-1" 64M
 # May not exceed 64
-IMGOPTS="$IMGOPTS,refcount_bits=128" _make_test_img 64M
+_make_test_img -o "refcount_bits=128" 64M
 # Must be a power of two
-IMGOPTS="$IMGOPTS,refcount_bits=42" _make_test_img 64M
+_make_test_img -o "refcount_bits=42" 64M
 
 # 1 is the minimum
-IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M
+_make_test_img -o "refcount_bits=1" 64M
 print_refcount_bits
 
 # 64 is the maximum
-IMGOPTS="$IMGOPTS,refcount_bits=64" _make_test_img 64M
+_make_test_img -o "refcount_bits=64" 64M
 print_refcount_bits
 
 # 16 is the default
@@ -XXX,XX +XXX,XX @@ echo '=== refcount_bits and compat=0.10 ==='
 echo
 
 # Should work
-IMGOPTS="$IMGOPTS,compat=0.10,refcount_bits=16" _make_test_img 64M
+_make_test_img -o "compat=0.10,refcount_bits=16" 64M
 print_refcount_bits
 
 # Should not work
-IMGOPTS="$IMGOPTS,compat=0.10,refcount_bits=1" _make_test_img 64M
-IMGOPTS="$IMGOPTS,compat=0.10,refcount_bits=64" _make_test_img 64M
+_make_test_img -o "compat=0.10,refcount_bits=1" 64M
+_make_test_img -o "compat=0.10,refcount_bits=64" 64M
 
 
 echo
 echo '=== Snapshot limit on refcount_bits=1 ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M
+_make_test_img -o "refcount_bits=1" 64M
 print_refcount_bits
 
 $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Snapshot limit on refcount_bits=2 ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=2" _make_test_img 64M
+_make_test_img -o "refcount_bits=2" 64M
 print_refcount_bits
 
 $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Compressed clusters with refcount_bits=1 ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M
+_make_test_img -o "refcount_bits=1" 64M
 print_refcount_bits
 
 # Both should fit into a single host cluster; instead of failing to increase the
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== MSb set in 64 bit refcount ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=64" _make_test_img 64M
+_make_test_img -o "refcount_bits=64" 64M
 print_refcount_bits
 
 $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Snapshot on maximum 64 bit refcount value ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=64" _make_test_img 64M
+_make_test_img -o "refcount_bits=64" 64M
 print_refcount_bits
 
 $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Testing too many references for check ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M
+_make_test_img -o "refcount_bits=1" 64M
 print_refcount_bits
 
 # This cluster should be created at 0x50000
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Multiple walks necessary during amend ==='
 echo
 
-IMGOPTS="$IMGOPTS,refcount_bits=1,cluster_size=512" _make_test_img 64k
+_make_test_img -o "refcount_bits=1,cluster_size=512" 64k
 
 # Cluster 0 is the image header, clusters 1 to 4 are used by the L1 table, a
 # single L2 table, the reftable and a single refblock. This creates 58 data
diff --git a/tests/qemu-iotests/115 b/tests/qemu-iotests/115
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/115
+++ b/tests/qemu-iotests/115
@@ -XXX,XX +XXX,XX @@ echo
 # least 256 MB. We can achieve that by using preallocation=metadata for an image
 # which has a guest disk size of 256 MB.
 
-IMGOPTS="$IMGOPTS,refcount_bits=64,cluster_size=512,preallocation=metadata" \
-    _make_test_img 256M
+_make_test_img -o "refcount_bits=64,cluster_size=512,preallocation=metadata" 256M
 
 # We know for sure that the L1 and refcount tables do not overlap with any other
 # structure because the metadata overlap checks would have caught that case.
diff --git a/tests/qemu-iotests/121 b/tests/qemu-iotests/121
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/121
+++ b/tests/qemu-iotests/121
@@ -XXX,XX +XXX,XX @@ echo
 # Preallocation speeds up the write operation, but preallocating everything will
 # destroy the purpose of the write; so preallocate one KB less than what would
 # cause a reftable growth...
-IMGOPTS='preallocation=metadata,cluster_size=1k' _make_test_img 64512K
+_make_test_img -o 'preallocation=metadata,cluster_size=1k' 64512K
 # ...and make the image the desired size afterwards.
 $QEMU_IMG resize "$TEST_IMG" 65M
 
@@ -XXX,XX +XXX,XX @@ echo
 echo '--- Test 2 ---'
 echo
 
-IMGOPTS='preallocation=metadata,cluster_size=1k' _make_test_img 64513K
+_make_test_img -o 'preallocation=metadata,cluster_size=1k' 64513K
 # This results in an L1 table growth which in turn results in some clusters at
 # the start of the image becoming free
 $QEMU_IMG resize "$TEST_IMG" 65M
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Allocating a new refcount block must not leave holes in the image ==='
 echo
 
-IMGOPTS='cluster_size=512,refcount_bits=16' _make_test_img 1M
+_make_test_img -o 'cluster_size=512,refcount_bits=16' 1M
 
 # This results in an image with 256 used clusters: the qcow2 header,
 # the refcount table, one refcount block, the L1 table, four L2 tables
diff --git a/tests/qemu-iotests/125 b/tests/qemu-iotests/125
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/125
+++ b/tests/qemu-iotests/125
@@ -XXX,XX +XXX,XX @@ for GROWTH_SIZE in 16 48 80; do
         for growth_mode in off metadata falloc full; do
             echo "--- cluster_size=$cluster_size growth_size=$GROWTH_SIZE create_mode=$create_mode growth_mode=$growth_mode ---"
 
-            IMGOPTS="preallocation=$create_mode,cluster_size=$cluster_size" _make_test_img ${CREATION_SIZE}
+            _make_test_img -o "preallocation=$create_mode,cluster_size=$cluster_size" ${CREATION_SIZE}
             $QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K
 
             host_size_0=$(get_image_size_on_host)
diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/137
+++ b/tests/qemu-iotests/137
@@ -XXX,XX +XXX,XX @@ $QEMU_IO \
     -c "reopen -o cache-clean-interval=-1" \
     "$TEST_IMG" | _filter_qemu_io
 
-IMGOPTS="cluster_size=256k" _make_test_img 32P
+_make_test_img -o "cluster_size=256k" 32P
 $QEMU_IO \
     -c "reopen -o l2-cache-entry-size=512,l2-cache-size=1T" \
     "$TEST_IMG" | _filter_qemu_io
diff --git a/tests/qemu-iotests/138 b/tests/qemu-iotests/138
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/138
+++ b/tests/qemu-iotests/138
@@ -XXX,XX +XXX,XX @@ echo
 echo '=== Check on an image with a multiple of 2^32 clusters ==='
 echo
 
-IMGOPTS=$(_optstr_add "$IMGOPTS" "cluster_size=512") \
-    _make_test_img 512
+_make_test_img -o "cluster_size=512" 512
 
 # Allocate L2 table
 $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io
diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/175
+++ b/tests/qemu-iotests/175
@@ -XXX,XX +XXX,XX @@ stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_block
 for mode in off full falloc; do
     echo
     echo "== creating image with preallocation $mode =="
-    IMGOPTS=preallocation=$mode _make_test_img $size | _filter_imgfmt
+    _make_test_img -o preallocation=$mode $size | _filter_imgfmt
     stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size
 done
 
diff --git a/tests/qemu-iotests/190 b/tests/qemu-iotests/190
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/190
+++ b/tests/qemu-iotests/190
@@ -XXX,XX +XXX,XX @@ _supported_proto file
 echo "== Huge file =="
 echo
 
-IMGOPTS='cluster_size=2M' _make_test_img 2T
+_make_test_img -o 'cluster_size=2M' 2T
 
 $QEMU_IMG measure -O raw -f qcow2 "$TEST_IMG"
 $QEMU_IMG measure -O qcow2 -o cluster_size=64k -f qcow2 "$TEST_IMG"
diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/191
+++ b/tests/qemu-iotests/191
@@ -XXX,XX +XXX,XX @@ echo === Preparing and starting VM ===
 echo
 
 TEST_IMG="${TEST_IMG}.base" _make_test_img $size
-IMGOPTS=$(_optstr_add "$IMGOPTS" "backing_fmt=$IMGFMT") \
-    TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base"
+TEST_IMG="${TEST_IMG}.mid" _make_test_img -o "backing_fmt=$IMGFMT" -b "${TEST_IMG}.base"
 _make_test_img -b "${TEST_IMG}.mid"
 TEST_IMG="${TEST_IMG}.ovl2" _make_test_img -b "${TEST_IMG}.mid"
 
diff --git a/tests/qemu-iotests/220 b/tests/qemu-iotests/220
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/220
+++ b/tests/qemu-iotests/220
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# To use a different refcount width but 16 bits we need compat=1.1
+_unsupported_imgopts 'compat=0.10'
 
 echo "== Creating huge file =="
 
@@ -XXX,XX +XXX,XX @@ echo "== Creating huge file =="
 # of a HUGE (but very sparse) file.  tmpfs works, ext4 does not.
 _require_large_file 513T
 
-IMGOPTS='cluster_size=2M,refcount_bits=1' _make_test_img 513T
+_make_test_img -o 'cluster_size=2M,refcount_bits=1' 513T
 
 echo "== Populating refcounts =="
 # We want an image with 256M refcounts * 2M clusters = 512T referenced.
diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/243
+++ b/tests/qemu-iotests/243
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# External data files do not work with compat=0.10
+_unsupported_imgopts 'compat=0.10'
 
 for mode in off metadata falloc full; do
 
@@ -XXX,XX +XXX,XX @@ for mode in off metadata falloc full; do
     echo "=== preallocation=$mode ==="
     echo
 
-    IMGOPTS="preallocation=$mode" _make_test_img 64M
+    _make_test_img -o "preallocation=$mode" 64M
 
     printf "File size: "
     du -b $TEST_IMG | cut -f1
@@ -XXX,XX +XXX,XX @@ for mode in off metadata falloc full; do
     echo "=== External data file: preallocation=$mode ==="
     echo
 
-    IMGOPTS="data_file=$TEST_IMG.data,preallocation=$mode" _make_test_img 64M
+    _make_test_img -o "data_file=$TEST_IMG.data,preallocation=$mode" 64M
 
     echo -n "qcow2 file size: "
     du -b $TEST_IMG | cut -f1
diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/244
+++ b/tests/qemu-iotests/244
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# External data files do not work with compat=0.10
+_unsupported_imgopts 'compat=0.10'
 
 echo
 echo "=== Create and open image with external data file ==="
 echo
 
 echo "With data file name in the image:"
-IMGOPTS="data_file=$TEST_IMG.data" _make_test_img 64M
+_make_test_img -o "data_file=$TEST_IMG.data" 64M
 _check_test_img
 
 $QEMU_IO -c "open $TEST_IMG" -c "read -P 0 0 64k" 2>&1 | _filter_qemu_io | _filter_testdir
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== Standalone image with external data file (efficient) ==="
 echo
 
-IMGOPTS="data_file=$TEST_IMG.data" _make_test_img 64M
+_make_test_img -o "data_file=$TEST_IMG.data" 64M
 
 echo -n "qcow2 file size before I/O: "
 du -b $TEST_IMG | cut -f1
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== Standalone image with external data file (valid raw) ==="
 echo
 
-IMGOPTS="data_file=$TEST_IMG.data,data_file_raw=on" _make_test_img 64M
+_make_test_img -o "data_file=$TEST_IMG.data,data_file_raw=on" 64M
 
 echo -n "qcow2 file size before I/O: "
 du -b $TEST_IMG | cut -f1
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== bdrv_co_block_status test for file and offset=0 ==="
 echo
 
-IMGOPTS="data_file=$TEST_IMG.data" _make_test_img 64M
+_make_test_img -o "data_file=$TEST_IMG.data" 64M
 
 $QEMU_IO -c 'write -P 0x11 0 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io
 $QEMU_IO -c 'read -P 0x11 0 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io
diff --git a/tests/qemu-iotests/250 b/tests/qemu-iotests/250
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/250
+++ b/tests/qemu-iotests/250
@@ -XXX,XX +XXX,XX @@ disk_usage()
 }
 
 size=2100M
-IMGOPTS="cluster_size=1M,preallocation=metadata"
 
-_make_test_img $size
+_make_test_img -o "cluster_size=1M,preallocation=metadata" $size
 $QEMU_IO -c 'discard 0 10M' -c 'discard 2090M 10M' \
          -c 'write 2090M 10M' -c 'write 0 10M' "$TEST_IMG" | _filter_qemu_io
 
diff --git a/tests/qemu-iotests/265 b/tests/qemu-iotests/265
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/265
+++ b/tests/qemu-iotests/265
@@ -XXX,XX +XXX,XX @@ _supported_os Linux
 echo '--- Writing to the image ---'
 
 # Reduce cluster size so we get more and quicker I/O
-IMGOPTS='cluster_size=4096' _make_test_img 1M
+_make_test_img -o 'cluster_size=4096' 1M
 (for ((kb = 1024 - 4; kb >= 0; kb -= 4)); do \
      echo "aio_write -P 42 $((kb + 1))k 2k"; \
  done) \
-- 
2.24.1

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-13-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/071 | 4 ++--
 tests/qemu-iotests/174 | 2 +-
 tests/qemu-iotests/178 | 4 ++--
 tests/qemu-iotests/197 | 4 ++--
 tests/qemu-iotests/215 | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tests/qemu-iotests/071 b/tests/qemu-iotests/071
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/071
+++ b/tests/qemu-iotests/071
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== Testing blkverify through filename ==="
 echo
 
-TEST_IMG="$TEST_IMG.base" IMGOPTS="" IMGFMT="raw" _make_test_img $IMG_SIZE |\
+TEST_IMG="$TEST_IMG.base" IMGFMT="raw" _make_test_img --no-opts $IMG_SIZE |\
     _filter_imgfmt
 _make_test_img $IMG_SIZE
 $QEMU_IO -c "open -o driver=raw,file.driver=blkverify,file.raw.filename=$TEST_IMG.base $TEST_IMG" \
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== Testing blkverify through file blockref ==="
 echo
 
-TEST_IMG="$TEST_IMG.base" IMGOPTS="" IMGFMT="raw" _make_test_img $IMG_SIZE |\
+TEST_IMG="$TEST_IMG.base" IMGFMT="raw" _make_test_img --no-opts $IMG_SIZE |\
     _filter_imgfmt
 _make_test_img $IMG_SIZE
 $QEMU_IO -c "open -o driver=raw,file.driver=blkverify,file.raw.filename=$TEST_IMG.base,file.test.driver=$IMGFMT,file.test.file.filename=$TEST_IMG" \
diff --git a/tests/qemu-iotests/174 b/tests/qemu-iotests/174
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/174
+++ b/tests/qemu-iotests/174
@@ -XXX,XX +XXX,XX @@ _unsupported_fmt raw
 
 
 size=256K
-IMGFMT=raw IMGKEYSECRET= IMGOPTS= _make_test_img $size | _filter_imgfmt
+IMGFMT=raw IMGKEYSECRET= _make_test_img --no-opts $size | _filter_imgfmt
 
 echo
 echo "== reading wrong format should fail =="
diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/178
+++ b/tests/qemu-iotests/178
@@ -XXX,XX +XXX,XX @@ $QEMU_IMG measure -O foo "$TEST_IMG" # unknown image file format
 
 make_test_img_with_fmt() {
     # Shadow global variables within this function
-    local IMGFMT="$1" IMGOPTS=""
-    _make_test_img "$2"
+    local IMGFMT="$1"
+    _make_test_img --no-opts "$2"
 }
 
 qemu_io_with_fmt() {
diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/197
+++ b/tests/qemu-iotests/197
@@ -XXX,XX +XXX,XX @@ if [ "$IMGFMT" = "vpc" ]; then
 fi
 _make_test_img 4G
 $QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io
-IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \
-    _make_test_img -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create
+IMGPROTO=file IMGFMT=qcow2 TEST_IMG_FILE="$TEST_WRAP" \
+    _make_test_img --no-opts -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create
 $QEMU_IO -f qcow2 -c "write -z -u 1M 64k" "$TEST_WRAP" | _filter_qemu_io
 
 # Ensure that a read of two clusters, but where one is already allocated,
diff --git a/tests/qemu-iotests/215 b/tests/qemu-iotests/215
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/215
+++ b/tests/qemu-iotests/215
@@ -XXX,XX +XXX,XX @@ if [ "$IMGFMT" = "vpc" ]; then
 fi
 _make_test_img 4G
 $QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io
-IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \
-    _make_test_img -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create
+IMGPROTO=file IMGFMT=qcow2 TEST_IMG_FILE="$TEST_WRAP" \
+    _make_test_img --no-opts -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create
 $QEMU_IO -f qcow2 -c "write -z -u 1M 64k" "$TEST_WRAP" | _filter_qemu_io
 
 # Ensure that a read of two clusters, but where one is already allocated,
-- 
2.24.1

Overwriting IMGOPTS means ignoring all user-supplied options, which is
not what we want.  Replace the current IMGOPTS use by a new BACKING_FILE
variable.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-14-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/267 | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/tests/qemu-iotests/267 b/tests/qemu-iotests/267
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/267
+++ b/tests/qemu-iotests/267
@@ -XXX,XX +XXX,XX @@ size=128M
 
 run_test()
 {
-    _make_test_img $size
+    if [ -n "$BACKING_FILE" ]; then
+        _make_test_img -b "$BACKING_FILE" $size
+    else
+        _make_test_img $size
+    fi
     printf "savevm snap0\ninfo snapshots\nloadvm snap0\n" | run_qemu "$@" | _filter_date
 }
 
@@ -XXX,XX +XXX,XX @@ echo
 
 TEST_IMG="$TEST_IMG.base" _make_test_img $size
 
-IMGOPTS="backing_file=$TEST_IMG.base" \
+BACKING_FILE="$TEST_IMG.base" \
 run_test -blockdev driver=file,filename="$TEST_IMG.base",node-name=backing-file \
          -blockdev driver=file,filename="$TEST_IMG",node-name=file \
          -blockdev driver=$IMGFMT,file=file,backing=backing-file,node-name=fmt
 
-IMGOPTS="backing_file=$TEST_IMG.base" \
+BACKING_FILE="$TEST_IMG.base" \
 run_test -blockdev driver=file,filename="$TEST_IMG.base",node-name=backing-file \
          -blockdev driver=$IMGFMT,file=backing-file,node-name=backing-fmt \
          -blockdev driver=file,filename="$TEST_IMG",node-name=file \
@@ -XXX,XX +XXX,XX @@ echo
 echo "=== -blockdev with NBD server on the backing file ==="
 echo
 
-IMGOPTS="backing_file=$TEST_IMG.base" _make_test_img $size
+_make_test_img -b "$TEST_IMG.base" $size
 cat <<EOF |
 nbd_server_start unix:$SOCK_DIR/nbd
 nbd_server_add -w backing-fmt
-- 
2.24.1

Use _make_test_img whenever possible.  This way, we will not ignore
user-specified image options.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-15-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/094 | 2 +-
 tests/qemu-iotests/111 | 3 +--
 tests/qemu-iotests/123 | 2 +-
 tests/qemu-iotests/153 | 2 +-
 tests/qemu-iotests/200 | 4 ++--
 5 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/tests/qemu-iotests/094 b/tests/qemu-iotests/094
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/094
+++ b/tests/qemu-iotests/094
@@ -XXX,XX +XXX,XX @@ _supported_proto nbd
 _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat"
 
 _make_test_img 64M
-$QEMU_IMG create -f $IMGFMT "$TEST_DIR/source.$IMGFMT" 64M | _filter_img_create
+TEST_IMG_FILE="$TEST_DIR/source.$IMGFMT" IMGPROTO=file _make_test_img 64M
 
 _launch_qemu -drive if=none,id=src,file="$TEST_DIR/source.$IMGFMT",format=raw \
              -nodefaults
diff --git a/tests/qemu-iotests/111 b/tests/qemu-iotests/111
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/111
+++ b/tests/qemu-iotests/111
@@ -XXX,XX +XXX,XX @@ _supported_fmt qed qcow qcow2 vmdk
 _supported_proto file
 _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat"
 
-$QEMU_IMG create -f $IMGFMT -b "$TEST_IMG.inexistent" "$TEST_IMG" 2>&1 \
-    | _filter_testdir | _filter_imgfmt
+_make_test_img -b "$TEST_IMG.inexistent"
 
 # success, all done
 echo '*** done'
diff --git a/tests/qemu-iotests/123 b/tests/qemu-iotests/123
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/123
+++ b/tests/qemu-iotests/123
@@ -XXX,XX +XXX,XX @@ _supported_os Linux
 SRC_IMG="$TEST_DIR/source.$IMGFMT"
 
 _make_test_img 1M
-$QEMU_IMG create -f $IMGFMT "$SRC_IMG" 1M | _filter_img_create
+TEST_IMG_FILE=$SRC_IMG IMGPROTO=file _make_test_img 1M
 
 $QEMU_IO -c 'write -P 42 0 1M' "$SRC_IMG" | _filter_qemu_io
 
diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/153
+++ b/tests/qemu-iotests/153
@@ -XXX,XX +XXX,XX @@ for opts1 in "" "read-only=on" "read-only=on,force-share=on"; do
 
     echo
     echo "== Creating test image =="
-    $QEMU_IMG create -f $IMGFMT "${TEST_IMG}" -b ${TEST_IMG}.base | _filter_img_create
+    _make_test_img -b "${TEST_IMG}.base"
 
     echo
     echo "== Launching QEMU, opts: '$opts1' =="
diff --git a/tests/qemu-iotests/200 b/tests/qemu-iotests/200
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/200
+++ b/tests/qemu-iotests/200
@@ -XXX,XX +XXX,XX @@ _supported_proto file
 BACKING_IMG="${TEST_DIR}/backing.img"
 TEST_IMG="${TEST_DIR}/test.img"
 
-${QEMU_IMG} create -f $IMGFMT "${BACKING_IMG}" 512M | _filter_img_create
-${QEMU_IMG} create -f $IMGFMT -F $IMGFMT "${TEST_IMG}" -b "${BACKING_IMG}" 512M | _filter_img_create
+TEST_IMG="$BACKING_IMG" _make_test_img 512M
+_make_test_img -F $IMGFMT -b "$BACKING_IMG" 512M
 
 ${QEMU_IO} -c "write -P 0xa5 512 300M" "${BACKING_IMG}" | _filter_qemu_io
 
-- 
2.24.1

Just rm will not delete external data files.  Use _rm_test_img every
time we delete a test image.

(In the process, clean up the indentation of every _cleanup() this patch
touches.)

((Also, use quotes consistently.  I am happy to see unquoted instances
like "rm -rf $TEST_DIR/..." go.))

diff --git a/tests/qemu-iotests/019 b/tests/qemu-iotests/019
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/019
+++ b/tests/qemu-iotests/019
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
-    rm -f "$TEST_IMG.base"
-    rm -f "$TEST_IMG.orig"
+    _cleanup_test_img
+    _rm_test_img "$TEST_IMG.base"
+    _rm_test_img "$TEST_IMG.orig"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/020 b/tests/qemu-iotests/020
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/020
+++ b/tests/qemu-iotests/020
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
-    rm -f "$TEST_IMG.base"
-    rm -f "$TEST_IMG.orig"
+    _cleanup_test_img
+    _rm_test_img "$TEST_IMG.base"
+    _rm_test_img "$TEST_IMG.orig"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/024 b/tests/qemu-iotests/024
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/024
+++ b/tests/qemu-iotests/024
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_DIR/t.$IMGFMT.base_old"
-    rm -f "$TEST_DIR/t.$IMGFMT.base_new"
+    _rm_test_img "$TEST_DIR/t.$IMGFMT.base_old"
+    _rm_test_img "$TEST_DIR/t.$IMGFMT.base_new"
 
-    rm -f "$TEST_DIR/subdir/t.$IMGFMT"
-    rm -f "$TEST_DIR/subdir/t.$IMGFMT.base_old"
-    rm -f "$TEST_DIR/subdir/t.$IMGFMT.base_new"
+    _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT"
+    _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT.base_old"
+    _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT.base_new"
     rmdir "$TEST_DIR/subdir" 2> /dev/null
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/028 b/tests/qemu-iotests/028
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/028
+++ b/tests/qemu-iotests/028
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_qemu
-    rm -f "${TEST_IMG}.copy"
+    _rm_test_img "${TEST_IMG}.copy"
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/029
+++ b/tests/qemu-iotests/029
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-    rm -f $TEST_IMG.snap
+    _rm_test_img "$TEST_IMG.snap"
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/043 b/tests/qemu-iotests/043
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/043
+++ b/tests/qemu-iotests/043
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG".[123].base
+    for img in "$TEST_IMG".[123].base; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/048 b/tests/qemu-iotests/048
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/048
+++ b/tests/qemu-iotests/048
@@ -XXX,XX +XXX,XX @@ _cleanup()
 {
     echo "Cleanup"
     _cleanup_test_img
-    rm "${TEST_IMG_FILE2}"
+    _rm_test_img "${TEST_IMG_FILE2}"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/050 b/tests/qemu-iotests/050
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/050
+++ b/tests/qemu-iotests/050
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.old"
-    rm -f "$TEST_IMG.new"
+    _rm_test_img "$TEST_IMG.old"
+    _rm_test_img "$TEST_IMG.new"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/053 b/tests/qemu-iotests/053
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/053
+++ b/tests/qemu-iotests/053
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	rm -f "$TEST_IMG.orig"
-	_cleanup_test_img
+    _rm_test_img "$TEST_IMG.orig"
+    _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/058 b/tests/qemu-iotests/058
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/058
+++ b/tests/qemu-iotests/058
@@ -XXX,XX +XXX,XX @@ _cleanup()
 {
     nbd_server_stop
     _cleanup_test_img
-    rm -f "$converted_image"
+    _rm_test_img "$converted_image"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/059
+++ b/tests/qemu-iotests/059
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.qcow2"
+    IMGFMT=qcow2 _rm_test_img "$TEST_IMG.qcow2"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/061
+++ b/tests/qemu-iotests/061
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f $TEST_IMG.data
+    _rm_test_img "$TEST_IMG.data"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/063 b/tests/qemu-iotests/063
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/063
+++ b/tests/qemu-iotests/063
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
-	rm -f "$TEST_IMG.orig" "$TEST_IMG.raw1" "$TEST_IMG.raw2"
+    _cleanup_test_img
+    for img in "$TEST_IMG".{orig,raw1,raw2,target}; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/069 b/tests/qemu-iotests/069
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/069
+++ b/tests/qemu-iotests/069
@@ -XXX,XX +XXX,XX @@ echo "=== Creating an image with a backing file and deleting that file ==="
 echo
 TEST_IMG="$TEST_IMG.base" _make_test_img $IMG_SIZE
 _make_test_img -b "$TEST_IMG.base" $IMG_SIZE
-rm -f "$TEST_IMG.base"
+_rm_test_img "$TEST_IMG.base"
 # Just open the image and close it right again (this should print an error message)
 $QEMU_IO -c quit "$TEST_IMG" 2>&1 | _filter_testdir | _filter_imgfmt
 
diff --git a/tests/qemu-iotests/074 b/tests/qemu-iotests/074
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/074
+++ b/tests/qemu-iotests/074
@@ -XXX,XX +XXX,XX @@ _cleanup()
 {
     echo "Cleanup"
     _cleanup_test_img
-    rm "${TEST_IMG2}"
+    _rm_test_img "${TEST_IMG2}"
     rm -f "$TEST_DIR/blkdebug.conf"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/080 b/tests/qemu-iotests/080
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/080
+++ b/tests/qemu-iotests/080
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-    rm -f $TEST_IMG.snap
+    _rm_test_img "$TEST_IMG.snap"
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/081 b/tests/qemu-iotests/081
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/081
+++ b/tests/qemu-iotests/081
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-    rm -rf $TEST_DIR/1.raw
-    rm -rf $TEST_DIR/2.raw
-    rm -rf $TEST_DIR/3.raw
+    _rm_test_img "$TEST_DIR/1.raw"
+    _rm_test_img "$TEST_DIR/2.raw"
+    _rm_test_img "$TEST_DIR/3.raw"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/085 b/tests/qemu-iotests/085
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/085
+++ b/tests/qemu-iotests/085
@@ -XXX,XX +XXX,XX @@ _cleanup()
     _cleanup_qemu
     for i in $(seq 1 ${SNAPSHOTS})
     do
-        rm -f "${TEST_DIR}/${i}-${snapshot_virt0}"
-        rm -f "${TEST_DIR}/${i}-${snapshot_virt1}"
+        _rm_test_img "${TEST_DIR}/${i}-${snapshot_virt0}"
+        _rm_test_img "${TEST_DIR}/${i}-${snapshot_virt1}"
+    done
+    for img in "${TEST_IMG}".{1,2,base}
+    do
+        _rm_test_img "$img"
     done
-    rm -f "${TEST_IMG}" "${TEST_IMG}.1" "${TEST_IMG}.2" "${TEST_IMG}.base"
 
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/088 b/tests/qemu-iotests/088
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/088
+++ b/tests/qemu-iotests/088
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-    rm -f $TEST_IMG.snap
+    _rm_test_img "$TEST_IMG.snap"
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/092 b/tests/qemu-iotests/092
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/092
+++ b/tests/qemu-iotests/092
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-    rm -f $TEST_IMG.snap
+    _rm_test_img "$TEST_IMG.snap"
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/094 b/tests/qemu-iotests/094
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/094
+++ b/tests/qemu-iotests/094
@@ -XXX,XX +XXX,XX @@ _cleanup()
 {
     _cleanup_qemu
     _cleanup_test_img
-    rm -f "$TEST_DIR/source.$IMGFMT"
+    _rm_test_img "$TEST_DIR/source.$IMGFMT"
 }
 
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/095 b/tests/qemu-iotests/095
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/095
+++ b/tests/qemu-iotests/095
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_qemu
-    rm  -f "${TEST_IMG}.base" "${TEST_IMG}.snp1"
-	_cleanup_test_img
+    _rm_test_img "${TEST_IMG}.base"
+    _rm_test_img "${TEST_IMG}.snp1"
+    _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/099 b/tests/qemu-iotests/099
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/099
+++ b/tests/qemu-iotests/099
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
+    _cleanup_test_img
+    _rm_test_img "$TEST_IMG.compare"
+    rm -f "$TEST_DIR/blkdebug.conf"
+
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
@@ -XXX,XX +XXX,XX @@ echo
 test_qemu "file.driver=blkdebug,file.image.filename=$TEST_IMG"
 
 
-rm -f "$TEST_IMG.compare" "$TEST_DIR/blkdebug.conf"
-
 # success, all done
 echo "*** done"
 rm -f $seq.full
diff --git a/tests/qemu-iotests/109 b/tests/qemu-iotests/109
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/109
+++ b/tests/qemu-iotests/109
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_qemu
-    rm -f $TEST_IMG.src
-	_cleanup_test_img
+    _rm_test_img "$TEST_IMG.src"
+    _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/110 b/tests/qemu-iotests/110
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/110
+++ b/tests/qemu-iotests/110
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
-        rm -f "$TEST_IMG.copy"
+    _cleanup_test_img
+    _rm_test_img "$TEST_IMG.copy"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/122 b/tests/qemu-iotests/122
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/122
+++ b/tests/qemu-iotests/122
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-    rm -f "$TEST_IMG".[123]
-	_cleanup_test_img
+    for img in "$TEST_IMG".[123]; do
+        _rm_test_img "$img"
+    done
+    _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/123 b/tests/qemu-iotests/123
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/123
+++ b/tests/qemu-iotests/123
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$SRC_IMG"
+    _rm_test_img "$SRC_IMG"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/141
+++ b/tests/qemu-iotests/141
@@ -XXX,XX +XXX,XX @@ _cleanup()
 {
     _cleanup_qemu
     _cleanup_test_img
-    rm -f "$TEST_DIR"/{b,m,o}.$IMGFMT
+    for img in "$TEST_DIR"/{b,m,o}.$IMGFMT; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/142 b/tests/qemu-iotests/142
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/142
+++ b/tests/qemu-iotests/142
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f $TEST_IMG.snap
+    _rm_test_img "$TEST_IMG.snap"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/144 b/tests/qemu-iotests/144
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/144
+++ b/tests/qemu-iotests/144
@@ -XXX,XX +XXX,XX @@ TMP_SNAP2=${TEST_DIR}/tmp2.qcow2
 _cleanup()
 {
     _cleanup_qemu
-    rm -f "${TEST_IMG}" "${TMP_SNAP1}" "${TMP_SNAP2}"
+    for img in "${TEST_IMG}" "${TMP_SNAP1}" "${TMP_SNAP2}"; do
+        _rm_test_img "$img"
+    done
 }
 
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/153
+++ b/tests/qemu-iotests/153
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "${TEST_IMG}.base"
-    rm -f "${TEST_IMG}.overlay"
-    rm -f "${TEST_IMG}.convert"
-    rm -f "${TEST_IMG}.a"
-    rm -f "${TEST_IMG}.b"
-    rm -f "${TEST_IMG}.c"
-    rm -f "${TEST_IMG}.lnk"
+    for img in "${TEST_IMG}".{base,overlay,convert,a,b,c,lnk}; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/156
+++ b/tests/qemu-iotests/156
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_qemu
-    rm -f "$TEST_IMG"{,.target}{,.backing,.overlay}
+    for img in "$TEST_IMG"{,.target}{,.backing,.overlay}; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $QEMU_HANDLE \
     '"status": "null"'
 
 # Remove the source images
-rm -f "$TEST_IMG{,.backing,.overlay}"
+for img in "$TEST_IMG{,.backing,.overlay}"; do
+    _rm_test_img "$img"
+done
 
 echo
 
diff --git a/tests/qemu-iotests/159 b/tests/qemu-iotests/159
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/159
+++ b/tests/qemu-iotests/159
@@ -XXX,XX +XXX,XX @@ status=1
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.out"
+    _rm_test_img "$TEST_IMG.out"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/160 b/tests/qemu-iotests/160
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/160
+++ b/tests/qemu-iotests/160
@@ -XXX,XX +XXX,XX @@ status=1
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.out" "$TEST_IMG.out.dd"
+    _rm_test_img "$TEST_IMG.out"
+    _rm_test_img "$TEST_IMG.out.dd"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/161 b/tests/qemu-iotests/161
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/161
+++ b/tests/qemu-iotests/161
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.base"
-    rm -f "$TEST_IMG.int"
+    _rm_test_img "$TEST_IMG.base"
+    _rm_test_img "$TEST_IMG.int"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/170 b/tests/qemu-iotests/170
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/170
+++ b/tests/qemu-iotests/170
@@ -XXX,XX +XXX,XX @@ status=1
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.out"
+    _rm_test_img  "$TEST_IMG.out"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/172 b/tests/qemu-iotests/172
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/172
+++ b/tests/qemu-iotests/172
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
-    rm -f "$TEST_IMG.2"
-    rm -f "$TEST_IMG.3"
+    _cleanup_test_img
+    _rm_test_img "$TEST_IMG.2"
+    _rm_test_img "$TEST_IMG.3"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/173 b/tests/qemu-iotests/173
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/173
+++ b/tests/qemu-iotests/173
@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
 _cleanup()
 {
     _cleanup_qemu
-    rm  -f "${QEMU_TEST_DIR}/image.base" "${QEMU_TEST_DIR}/image.snp1"
+    _rm_test_img "${TEST_DIR}/image.base"
+    _rm_test_img "${TEST_DIR}/image.snp1"
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/178
+++ b/tests/qemu-iotests/178
@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.converted"
+    _rm_test_img "$TEST_IMG.converted"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/182 b/tests/qemu-iotests/182
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/182
+++ b/tests/qemu-iotests/182
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.overlay"
+    _rm_test_img "$TEST_IMG.overlay"
     rm -f "$SOCK_DIR/nbd.socket"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/183 b/tests/qemu-iotests/183
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/183
+++ b/tests/qemu-iotests/183
@@ -XXX,XX +XXX,XX @@ MIG_SOCKET="${SOCK_DIR}/migrate"
 _cleanup()
 {
     rm -f "${MIG_SOCKET}"
-    rm -f "${TEST_IMG}.dest"
+    _rm_test_img "${TEST_IMG}.dest"
     _cleanup_test_img
     _cleanup_qemu
 }
diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/185
+++ b/tests/qemu-iotests/185
@@ -XXX,XX +XXX,XX @@ status=1 # failure is the default!
 
 _cleanup()
 {
-    rm -f "${TEST_IMG}.mid"
-    rm -f "${TEST_IMG}.copy"
+    _rm_test_img "${TEST_IMG}.mid"
+    _rm_test_img "${TEST_IMG}.copy"
     _cleanup_test_img
     _cleanup_qemu
 }
diff --git a/tests/qemu-iotests/187 b/tests/qemu-iotests/187
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/187
+++ b/tests/qemu-iotests/187
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
-    rm -f "$TEST_IMG.2"
-    rm -f "$TEST_IMG.3"
+    _cleanup_test_img
+    _rm_test_img "$TEST_IMG.2"
+    _rm_test_img "$TEST_IMG.3"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/190 b/tests/qemu-iotests/190
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/190
+++ b/tests/qemu-iotests/190
@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.converted"
+    _rm_test_img "$TEST_IMG.converted"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/191
+++ b/tests/qemu-iotests/191
@@ -XXX,XX +XXX,XX @@ status=1 # failure is the default!
 
 _cleanup()
 {
-    rm -f "${TEST_IMG}.mid"
-    rm -f "${TEST_IMG}.ovl2"
-    rm -f "${TEST_IMG}.ovl3"
+    _rm_test_img "${TEST_IMG}.mid"
+    _rm_test_img "${TEST_IMG}.ovl2"
+    _rm_test_img "${TEST_IMG}.ovl3"
     _cleanup_test_img
     _cleanup_qemu
 }
diff --git a/tests/qemu-iotests/195 b/tests/qemu-iotests/195
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/195
+++ b/tests/qemu-iotests/195
@@ -XXX,XX +XXX,XX @@ status=1 # failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.mid"
+    _rm_test_img "$TEST_IMG.mid"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/197
+++ b/tests/qemu-iotests/197
@@ -XXX,XX +XXX,XX @@ esac
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_WRAP"
+    _rm_test_img "$TEST_WRAP"
     rm -f "$BLKDBG_CONF"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/200 b/tests/qemu-iotests/200
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/200
+++ b/tests/qemu-iotests/200
@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
 _cleanup()
 {
     _cleanup_qemu
-    rm -f "${TEST_IMG}" "${BACKING_IMG}"
+    _rm_test_img "${TEST_IMG}"
+    _rm_test_img "${BACKING_IMG}"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/215 b/tests/qemu-iotests/215
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/215
+++ b/tests/qemu-iotests/215
@@ -XXX,XX +XXX,XX @@ esac
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_WRAP"
+    _rm_test_img "$TEST_WRAP"
     rm -f "$BLKDBG_CONF"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/225 b/tests/qemu-iotests/225
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/225
+++ b/tests/qemu-iotests/225
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.not_base"
+    _rm_test_img "$TEST_IMG.not_base"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/229 b/tests/qemu-iotests/229
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/229
+++ b/tests/qemu-iotests/229
@@ -XXX,XX +XXX,XX @@ _cleanup()
 {
     _cleanup_qemu
     _cleanup_test_img
-    rm -f "$TEST_IMG" "$DEST_IMG"
+    _rm_test_img "$TEST_IMG"
+    _rm_test_img "$DEST_IMG"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/232 b/tests/qemu-iotests/232
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/232
+++ b/tests/qemu-iotests/232
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f $TEST_IMG.[01234]
+    for img in "$TEST_IMG".[01234]; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/243
+++ b/tests/qemu-iotests/243
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f $TEST_IMG.data
+    _rm_test_img "$TEST_IMG.data"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/244
+++ b/tests/qemu-iotests/244
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f $TEST_IMG.data
-    rm -f $TEST_IMG.src
+    _rm_test_img "$TEST_IMG.data"
+    _rm_test_img "$TEST_IMG.src"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/247 b/tests/qemu-iotests/247
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/247
+++ b/tests/qemu-iotests/247
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f $TEST_IMG.[01234]
+    for img in "$TEST_IMG".[01234]; do
+        _rm_test_img "$img"
+    done
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/249 b/tests/qemu-iotests/249
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/249
+++ b/tests/qemu-iotests/249
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.base"
-    rm -f "$TEST_IMG.int"
+    _rm_test_img "$TEST_IMG.base"
+    _rm_test_img "$TEST_IMG.int"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/252 b/tests/qemu-iotests/252
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/252
+++ b/tests/qemu-iotests/252
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 _cleanup()
 {
     _cleanup_test_img
-    rm -f "$TEST_IMG.base_new"
+    _rm_test_img "$TEST_IMG.base_new"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
-- 
2.24.1

This will not work with external data files, so try to get tests working
without it as far as possible.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-17-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/063     | 12 ++++--------
 tests/qemu-iotests/063.out |  3 ++-
 tests/qemu-iotests/085     |  9 +++------
 tests/qemu-iotests/085.out |  8 ++++----
 4 files changed, 13 insertions(+), 19 deletions(-)

diff --git a/tests/qemu-iotests/063 b/tests/qemu-iotests/063
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/063
+++ b/tests/qemu-iotests/063
@@ -XXX,XX +XXX,XX @@ _unsupported_imgopts "subformat=monolithicFlat" \
 _make_test_img 4M
 
 echo "== Testing conversion with -n fails with no target file =="
-# check .orig file does not exist
-rm -f "$TEST_IMG.orig"
 if $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG.orig" >/dev/null 2>&1; then
     exit 1
 fi
 
 echo "== Testing conversion with -n succeeds with a target file =="
-rm -f "$TEST_IMG.orig"
-cp "$TEST_IMG" "$TEST_IMG.orig"
+_rm_test_img "$TEST_IMG.orig"
+TEST_IMG="$TEST_IMG.orig" _make_test_img 4M
 if ! $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG.orig" ; then
     exit 1
 fi
@@ -XXX,XX +XXX,XX @@ fi
 _check_test_img
 
 echo "== Testing conversion to a smaller file fails =="
-rm -f "$TEST_IMG.orig"
-mv "$TEST_IMG" "$TEST_IMG.orig"
-_make_test_img 2M
-if $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG.orig" "$TEST_IMG" >/dev/null 2>&1; then
+TEST_IMG="$TEST_IMG.target" _make_test_img 2M
+if $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG.target" >/dev/null 2>&1; then
     exit 1
 fi
 
diff --git a/tests/qemu-iotests/063.out b/tests/qemu-iotests/063.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/063.out
+++ b/tests/qemu-iotests/063.out
@@ -XXX,XX +XXX,XX @@ QA output created by 063
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=4194304
 == Testing conversion with -n fails with no target file ==
 == Testing conversion with -n succeeds with a target file ==
+Formatting 'TEST_DIR/t.IMGFMT.orig', fmt=IMGFMT size=4194304
 == Testing conversion to raw is the same after conversion with -n ==
 == Testing conversion back to original format ==
 No errors were found on the image.
 == Testing conversion to a smaller file fails ==
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2097152
+Formatting 'TEST_DIR/t.IMGFMT.target', fmt=IMGFMT size=2097152
 == Regression testing for copy offloading bug ==
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
 Formatting 'TEST_DIR/t.IMGFMT.target', fmt=IMGFMT size=1048576
diff --git a/tests/qemu-iotests/085 b/tests/qemu-iotests/085
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/085
+++ b/tests/qemu-iotests/085
@@ -XXX,XX +XXX,XX @@ add_snapshot_image()
 {
     base_image="${TEST_DIR}/$((${1}-1))-${snapshot_virt0}"
     snapshot_file="${TEST_DIR}/${1}-${snapshot_virt0}"
-    _make_test_img -u -b "${base_image}" "$size"
-    mv "${TEST_IMG}" "${snapshot_file}"
+    TEST_IMG=$snapshot_file _make_test_img -u -b "${base_image}" "$size"
     do_blockdev_add "$1" "'backing': null, " "${snapshot_file}"
 }
 
@@ -XXX,XX +XXX,XX @@ blockdev_snapshot()
 
 size=128M
 
-_make_test_img $size
-mv "${TEST_IMG}" "${TEST_IMG}.1"
-_make_test_img $size
-mv "${TEST_IMG}" "${TEST_IMG}.2"
+TEST_IMG="$TEST_IMG.1" _make_test_img $size
+TEST_IMG="$TEST_IMG.2" _make_test_img $size
 
 echo
 echo === Running QEMU ===
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 @@
 QA output created by 085
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
+Formatting 'TEST_DIR/t.IMGFMT.1', fmt=IMGFMT size=134217728
+Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=134217728
 
 === Running QEMU ===
 
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_fil
 
 === Create a couple of snapshots using blockdev-snapshot ===
 
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/10-snapshot-v0.IMGFMT
+Formatting 'TEST_DIR/11-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/10-snapshot-v0.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' } } }
 {"return": {}}
 { 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_11' } }
 {"return": {}}
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/11-snapshot-v0.IMGFMT
+Formatting 'TEST_DIR/12-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/11-snapshot-v0.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' } } }
 {"return": {}}
 { 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_12' } }
-- 
2.24.1

The image end offset as reported by qemu-img check is different when
using an external data file; we do not care about its value here, so we
can just filter it.  Incidentally, common.rc already has _check_test_img
for us which does exactly that.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-18-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/091     | 2 +-
 tests/qemu-iotests/091.out | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/tests/qemu-iotests/091 b/tests/qemu-iotests/091
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/091
+++ b/tests/qemu-iotests/091
@@ -XXX,XX +XXX,XX @@ echo "Check image pattern"
 ${QEMU_IO} -c "read -P 0x22 0 4M" "${TEST_IMG}" | _filter_testdir | _filter_qemu_io
 
 echo "Running 'qemu-img check -r all \$TEST_IMG'"
-"${QEMU_IMG}" check -r all "${TEST_IMG}" 2>&1 | _filter_testdir | _filter_qemu
+_check_test_img -r all
 
 echo "*** done"
 rm -f $seq.full
diff --git a/tests/qemu-iotests/091.out b/tests/qemu-iotests/091.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/091.out
+++ b/tests/qemu-iotests/091.out
@@ -XXX,XX +XXX,XX @@ read 4194304/4194304 bytes at offset 0
 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 Running 'qemu-img check -r all $TEST_IMG'
 No errors were found on the image.
-80/16384 = 0.49% allocated, 0.00% fragmented, 0.00% compressed clusters
-Image end offset: 5570560
 *** done
-- 
2.24.1

The only difference is that the json:{} filename of the image looks
different.  We actually do not care about that filename in this test, we
are only interested in (1) that there is a json:{} filename, and (2)
whether the backing filename can be constructed.

So just filter out the json:{} data, thus making this test pass both
with and without data_file.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-19-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/110     | 7 +++++--
 tests/qemu-iotests/110.out | 4 ++--
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/tests/qemu-iotests/110 b/tests/qemu-iotests/110
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/110
+++ b/tests/qemu-iotests/110
@@ -XXX,XX +XXX,XX @@ echo
 # Across blkdebug without a config file, you cannot reconstruct filenames, so
 # qemu is incapable of knowing the directory of the top image from the filename
 # alone. However, using bdrv_dirname(), it should still work.
+# (Filter out the json:{} filename so this test works with external data files)
 TEST_IMG="json:{
     'driver': '$IMGFMT',
     'file': {
@@ -XXX,XX +XXX,XX @@ TEST_IMG="json:{
             }
         ]
     }
-}" _img_info | _filter_img_info | grep -v 'backing file format'
+}" _img_info | _filter_img_info | grep -v 'backing file format' \
+    | _filter_json_filename
 
 echo
 echo '=== Backing name is always relative to the backed image ==='
@@ -XXX,XX +XXX,XX @@ TEST_IMG="json:{
             }
         ]
     }
-}" _img_info | _filter_img_info | grep -v 'backing file format'
+}" _img_info | _filter_img_info | grep -v 'backing file format' \
+    | _filter_json_filename
 
 
 # success, all done
diff --git a/tests/qemu-iotests/110.out b/tests/qemu-iotests/110.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/110.out
+++ b/tests/qemu-iotests/110.out
@@ -XXX,XX +XXX,XX @@ backing file: t.IMGFMT.base (actual path: TEST_DIR/t.IMGFMT.base)
 
 === Non-reconstructable filename ===
 
-image: json:{"driver": "IMGFMT", "file": {"set-state.0.event": "read_aio", "image": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "driver": "blkdebug", "set-state.0.new_state": 42}}
+image: json:{ /* filtered */ }
 file format: IMGFMT
 virtual size: 64 MiB (67108864 bytes)
 backing file: t.IMGFMT.base (actual path: TEST_DIR/t.IMGFMT.base)
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file=t.IMGFMT.b
 
 === Nodes without a common directory ===
 
-image: json:{"driver": "IMGFMT", "file": {"children": [{"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, {"driver": "file", "filename": "TEST_DIR/t.IMGFMT.copy"}], "driver": "quorum", "vote-threshold": 1}}
+image: json:{ /* filtered */ }
 file format: IMGFMT
 virtual size: 64 MiB (67108864 bytes)
 backing file: t.IMGFMT.base (cannot determine actual path)
-- 
2.24.1

When using an external data file, there are no refcounts for data
clusters.  We thus have to adjust the corruption test in this patch to
not be based around a data cluster allocation, but the L2 table
allocation (L2 tables are still refcounted with external data files).

Furthermore, we should not print qcow2.py's list of incompatible
features because it differs depending on whether there is an external
data file or not.

With those two changes, the test will work both with and without
external data files (once that options works with the iotests at all).

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-20-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/137     | 15 +++++++++++----
 tests/qemu-iotests/137.out |  6 ++----
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/137
+++ b/tests/qemu-iotests/137
@@ -XXX,XX +XXX,XX @@ $QEMU_IO \
     "$TEST_IMG" 2>&1 | _filter_qemu_io
 
 # The dirty bit must not be set
-$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features
+# (Filter the external data file bit)
+if $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features \
+    | grep -q '\<0\>'
+then
+    echo 'ERROR: Dirty bit set'
+else
+    echo 'OK: Dirty bit not set'
+fi
 
 # Similarly we can test whether corruption detection has been enabled:
-# Create L1/L2, overwrite first entry in refcount block, allocate something.
+# Create L1, overwrite refcounts, force allocation of L2 by writing
+# data.
 # Disabling the checks should fail, so the corruption must be detected.
 _make_test_img 64M
-$QEMU_IO -c "write 0 64k" "$TEST_IMG" | _filter_qemu_io
-poke_file "$TEST_IMG" "$((0x20000))" "\x00\x00"
+poke_file "$TEST_IMG" "$((0x20000))" "\x00\x00\x00\x00\x00\x00\x00\x00"
 $QEMU_IO \
     -c "reopen -o overlap-check=none,lazy-refcounts=42" \
     -c "write 64k 64k" \
diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/137.out
+++ b/tests/qemu-iotests/137.out
@@ -XXX,XX +XXX,XX @@ qemu-io: Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are
 wrote 512/512 bytes at offset 0
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 ./common.rc: Killed                  ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" )
-incompatible_features     []
+OK: Dirty bit not set
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
-wrote 65536/65536 bytes at offset 0
-64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 qemu-io: Parameter 'lazy-refcounts' expects 'on' or 'off'
-qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with qcow2_header); further corruption events will be suppressed
+qcow2: Marking image as corrupt: Preventing invalid allocation of L2 table at offset 0; further corruption events will be suppressed
 write failed: Input/output error
 *** done
-- 
2.24.1

We do not care about the json:{} filenames here, so we can just filter
them out and thus make the test work both with and without external data
files.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-21-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/198     | 6 ++++--
 tests/qemu-iotests/198.out | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/tests/qemu-iotests/198 b/tests/qemu-iotests/198
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/198
+++ b/tests/qemu-iotests/198
@@ -XXX,XX +XXX,XX @@ echo
 echo "== checking image base =="
 $QEMU_IMG info --image-opts $IMGSPECBASE | _filter_img_info --format-specific \
     | sed -e "/^disk size:/ D" -e '/refcount bits:/ D' -e '/compat:/ D' \
-          -e '/lazy refcounts:/ D' -e '/corrupt:/ D'
+          -e '/lazy refcounts:/ D' -e '/corrupt:/ D' -e '/^\s*data file/ D' \
+    | _filter_json_filename
 
 echo
 echo "== checking image layer =="
 $QEMU_IMG info --image-opts $IMGSPECLAYER | _filter_img_info --format-specific \
     | sed -e "/^disk size:/ D" -e '/refcount bits:/ D' -e '/compat:/ D' \
-          -e '/lazy refcounts:/ D' -e '/corrupt:/ D'
+          -e '/lazy refcounts:/ D' -e '/corrupt:/ D' -e '/^\s*data file/ D' \
+    | _filter_json_filename
 
 
 # success, all done
diff --git a/tests/qemu-iotests/198.out b/tests/qemu-iotests/198.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/198.out
+++ b/tests/qemu-iotests/198.out
@@ -XXX,XX +XXX,XX @@ read 16777216/16777216 bytes at offset 0
 16 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 == checking image base ==
-image: json:{"encrypt.key-secret": "sec0", "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT.base"}}
+image: json:{ /* filtered */ }
 file format: IMGFMT
 virtual size: 16 MiB (16777216 bytes)
 Format specific information:
@@ -XXX,XX +XXX,XX @@ Format specific information:
         master key iters: 1024
 
 == checking image layer ==
-image: json:{"encrypt.key-secret": "sec1", "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}}
+image: json:{ /* filtered */ }
 file format: IMGFMT
 virtual size: 16 MiB (16777216 bytes)
 backing file: TEST_DIR/t.IMGFMT.base
-- 
2.24.1

diff --git a/tests/qemu-iotests/007 b/tests/qemu-iotests/007
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/007
+++ b/tests/qemu-iotests/007
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 # refcount_bits must be at least 4 so we can create ten internal snapshots
-# (1 bit supports none, 2 bits support two, 4 bits support 14)
-_unsupported_imgopts 'refcount_bits=$1\|2$[^0-9]'
+# (1 bit supports none, 2 bits support two, 4 bits support 14);
+# snapshot are generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=$1\|2$[^0-9]' data_file
 
 echo
 echo "creating image"
diff --git a/tests/qemu-iotests/014 b/tests/qemu-iotests/014
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/014
+++ b/tests/qemu-iotests/014
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# Compression and snapshots do not work with external data files
+_unsupported_imgopts data_file
 
 TEST_OFFSETS="0 4294967296"
 TEST_OPS="writev read write readv"
diff --git a/tests/qemu-iotests/015 b/tests/qemu-iotests/015
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/015
+++ b/tests/qemu-iotests/015
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # actually any format that supports snapshots
 _supported_fmt qcow2
 _supported_proto generic
-# Internal snapshots are (currently) impossible with refcount_bits=1
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 echo
 echo "creating image"
diff --git a/tests/qemu-iotests/026 b/tests/qemu-iotests/026
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/026
+++ b/tests/qemu-iotests/026
@@ -XXX,XX +XXX,XX @@ _supported_cache_modes writethrough none
 # 32 and 64 bits do not work either, however, due to different leaked cluster
 # count on error.
 # Thus, the only remaining option is refcount_bits=16.
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+#
+# As for data_file, none of the refcount tests can work for it.
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)' \
+    data_file
 
 echo "Errors while writing 128 kB"
 echo
diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/029
+++ b/tests/qemu-iotests/029
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _unsupported_proto vxhs
-# Internal snapshots are (currently) impossible with refcount_bits=1
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 offset_size=24
 offset_l1_size=36
diff --git a/tests/qemu-iotests/031 b/tests/qemu-iotests/031
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/031
+++ b/tests/qemu-iotests/031
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
-# We want to test compat=0.10, which does not support refcount widths
-# other than 16
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# We want to test compat=0.10, which does not support external data
+# files or refcount widths other than 16
+_unsupported_imgopts data_file 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
 
 CLUSTER_SIZE=65536
 
diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/036
+++ b/tests/qemu-iotests/036
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto file
-# Only qcow2v3 and later supports feature bits
-_unsupported_imgopts 'compat=0.10'
+# Only qcow2v3 and later supports feature bits;
+# qcow2.py does not support external data files
+_unsupported_imgopts 'compat=0.10' data_file
 
 echo
 echo === Image with unknown incompatible feature bit ===
diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/039
+++ b/tests/qemu-iotests/039
@@ -XXX,XX +XXX,XX @@ _supported_proto file
 _supported_os Linux
 _default_cache_mode writethrough
 _supported_cache_modes writethrough
+# Some of these test cases expect no external data file so that all
+# clusters are part of the qcow2 image and refcounted
+_unsupported_imgopts data_file
 
 size=128M
 
diff --git a/tests/qemu-iotests/046 b/tests/qemu-iotests/046
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/046
+++ b/tests/qemu-iotests/046
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto file
+# data_file does not support compressed clusters
+_unsupported_imgopts data_file
 
 CLUSTER_SIZE=64k
 size=128M
diff --git a/tests/qemu-iotests/048 b/tests/qemu-iotests/048
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/048
+++ b/tests/qemu-iotests/048
@@ -XXX,XX +XXX,XX @@ _compare()
 _supported_fmt raw qcow2 qed luks
 _supported_proto file
 _supported_os Linux
+# Using 'cp' is incompatible with external data files
+_unsupported_imgopts data_file
 
 # Remove once all tests are fixed to use TEST_IMG_FILE
 # correctly and common.rc sets it unconditionally
diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/051
+++ b/tests/qemu-iotests/051
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 # A compat=0.10 image is created in this test which does not support anything
-# other than refcount_bits=16
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# other than refcount_bits=16;
+# it also will not support an external data file
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)' data_file
 _require_drivers nbd
 
 do_run_qemu()
diff --git a/tests/qemu-iotests/058 b/tests/qemu-iotests/058
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/058
+++ b/tests/qemu-iotests/058
@@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
 _require_command QEMU_NBD
-# Internal snapshots are (currently) impossible with refcount_bits=1
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 nbd_snapshot_img="nbd:unix:$nbd_unix_socket"
 
diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/060
+++ b/tests/qemu-iotests/060
@@ -XXX,XX +XXX,XX @@ _filter_io_error()
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# These tests only work for compat=1.1 images with refcount_bits=16
-_unsupported_imgopts 'compat=0.10' 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# These tests only work for compat=1.1 images without an external
+# data file with refcount_bits=16
+_unsupported_imgopts 'compat=0.10' data_file \
+    'refcount_bits=$[^1]\|.\([^6]\|$$\)'
 
 # The repair process will create a large file - so check for availability first
 _require_large_file 64G
diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/061
+++ b/tests/qemu-iotests/061
@@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
 # Conversion between different compat versions can only really work
-# with refcount_bits=16
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# with refcount_bits=16;
+# we have explicit tests for data_file here, but the whole test does
+# not work with it
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)' data_file
 
 echo
 echo "=== Testing version downgrade with zero expansion ==="
diff --git a/tests/qemu-iotests/062 b/tests/qemu-iotests/062
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/062
+++ b/tests/qemu-iotests/062
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 # We need zero clusters and snapshots
-_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]'
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file
 
 IMG_SIZE=64M
 
diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/066
+++ b/tests/qemu-iotests/066
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 # We need zero clusters and snapshots
-_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]'
+# (TODO: Consider splitting the snapshot part into a separate test
+#        file, so this one runs with refcount_bits=1 and data_file)
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file
 
 # Intentionally create an unaligned image
 IMG_SIZE=$((64 * 1024 * 1024 + 512))
diff --git a/tests/qemu-iotests/067 b/tests/qemu-iotests/067
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/067
+++ b/tests/qemu-iotests/067
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _supported_fmt qcow2
 _supported_proto file
-# Because anything other than 16 would change the output of query-block
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# Because anything other than 16 would change the output of query-block,
+# and external data files would change the output of
+# query-named-block-nodes
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)' data_file
 
 do_run_qemu()
 {
diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/068
+++ b/tests/qemu-iotests/068
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # This tests qcow2-specific low-level functionality
 _supported_fmt qcow2
 _supported_proto generic
-# Internal snapshots are (currently) impossible with refcount_bits=1
-_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file
 
 IMG_SIZE=128K
 
diff --git a/tests/qemu-iotests/071 b/tests/qemu-iotests/071
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/071
+++ b/tests/qemu-iotests/071
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _require_drivers blkdebug blkverify
+# blkdebug can only inject errors on bs->file, not on the data_file,
+# so thie test does not work with external data files
+_unsupported_imgopts data_file
 
 do_run_qemu()
 {
diff --git a/tests/qemu-iotests/073 b/tests/qemu-iotests/073
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/073
+++ b/tests/qemu-iotests/073
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _unsupported_proto vxhs
+# External data files do not support compressed clusters
+# (TODO: Consider writing a version for external data files that does
+#        not test compressed clusters)
+_unsupported_imgopts data_file
 
 CLUSTER_SIZE=64k
 size=128M
diff --git a/tests/qemu-iotests/074 b/tests/qemu-iotests/074
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/074
+++ b/tests/qemu-iotests/074
@@ -XXX,XX +XXX,XX @@ _compare()
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# blkdebug can only inject errors on bs->file
+_unsupported_imgopts data_file
 
 # Setup test basic parameters
 TEST_IMG2=$TEST_IMG.2
diff --git a/tests/qemu-iotests/080 b/tests/qemu-iotests/080
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/080
+++ b/tests/qemu-iotests/080
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# - Internal snapshots are (currently) impossible with refcount_bits=1
+# - Internal snapshots are (currently) impossible with refcount_bits=1,
+#   and generally impossible with external data files
 # - This is generally a test for compat=1.1 images
-_unsupported_imgopts 'refcount_bits=1[^0-9]' 'compat=0.10'
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file 'compat=0.10'
 
 header_size=104
 
diff --git a/tests/qemu-iotests/090 b/tests/qemu-iotests/090
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/090
+++ b/tests/qemu-iotests/090
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto file nfs
+# External data files do not support compressed clusters
+_unsupported_imgopts data_file
 
 IMG_SIZE=128K
 
diff --git a/tests/qemu-iotests/098 b/tests/qemu-iotests/098
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/098
+++ b/tests/qemu-iotests/098
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto file
-# The code path we want to test here only works for compat=1.1 images
-_unsupported_imgopts 'compat=0.10'
+# The code path we want to test here only works for compat=1.1 images;
+# blkdebug can only inject errors on bs->file, so external data files
+# do not work with this test
+_unsupported_imgopts 'compat=0.10' data_file
 
 for event in l1_update empty_image_prepare reftable_update refblock_alloc; do
 
diff --git a/tests/qemu-iotests/099 b/tests/qemu-iotests/099
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/099
+++ b/tests/qemu-iotests/099
@@ -XXX,XX +XXX,XX @@ _supported_fmt qcow qcow2 qed vdi vhdx vmdk vpc
 _supported_proto file
 _supported_os Linux
 _require_drivers blkdebug blkverify
+# data_file would change the json:{} filenames
 _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" \
-    "subformat=twoGbMaxExtentSparse"
+    "subformat=twoGbMaxExtentSparse" data_file
 
 do_run_qemu()
 {
diff --git a/tests/qemu-iotests/103 b/tests/qemu-iotests/103
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/103
+++ b/tests/qemu-iotests/103
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto file nfs
-# Internal snapshots are (currently) impossible with refcount_bits=1
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 IMG_SIZE=64K
 
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# This test directly modifies a refblock so it relies on refcount_bits being 16
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# This test directly modifies a refblock so it relies on refcount_bits being 16;
+# and the low-level modification it performs are not tuned for external data
+# files
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)' data_file
 
 echo
 echo '=== Repairing an image without any refcount table ==='
diff --git a/tests/qemu-iotests/112 b/tests/qemu-iotests/112
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/112
+++ b/tests/qemu-iotests/112
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 # This test will set refcount_bits on its own which would conflict with the
-# manual setting; compat will be overridden as well
-_unsupported_imgopts refcount_bits 'compat=0.10'
+# manual setting; compat will be overridden as well;
+# and external data files do not work well with our refcount testing
+_unsupported_imgopts refcount_bits 'compat=0.10' data_file
 
 print_refcount_bits()
 {
diff --git a/tests/qemu-iotests/114 b/tests/qemu-iotests/114
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/114
+++ b/tests/qemu-iotests/114
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto generic
 _unsupported_proto vxhs
+# qcow2.py does not work too well with external data files
+_unsupported_imgopts data_file
 
 
 TEST_IMG="$TEST_IMG.base" _make_test_img 64M
diff --git a/tests/qemu-iotests/121 b/tests/qemu-iotests/121
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/121
+++ b/tests/qemu-iotests/121
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# Refcount structures are used much differently with external data
+# files
+_unsupported_imgopts data_file
 
 echo
 echo '=== New refcount structures may not conflict with existing structures ==='
diff --git a/tests/qemu-iotests/138 b/tests/qemu-iotests/138
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/138
+++ b/tests/qemu-iotests/138
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# With an external data file, data clusters are not refcounted
+# (and so qemu-img check does not check their refcount)
+_unsupported_imgopts data_file
 
 echo
 echo '=== Check on an image with a multiple of 2^32 clusters ==='
diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/156
+++ b/tests/qemu-iotests/156
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2 qed
 _supported_proto generic
 _unsupported_proto vxhs
+# Copying files around with cp does not work with external data files
+_unsupported_imgopts data_file
 
 # Create source disk
 TEST_IMG="$TEST_IMG.backing" _make_test_img 1M
diff --git a/tests/qemu-iotests/176 b/tests/qemu-iotests/176
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/176
+++ b/tests/qemu-iotests/176
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# Persistent dirty bitmaps require compat=1.1
-_unsupported_imgopts 'compat=0.10'
+# Persistent dirty bitmaps require compat=1.1;
+# Internal snapshots forbid using an external data file
+# (they work with refcount_bits=1 here, though, because there actually
+# is no data when creating the snapshot)
+_unsupported_imgopts 'compat=0.10' data_file
 
 run_qemu()
 {
diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/191
+++ b/tests/qemu-iotests/191
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto file
+# An external data file would change the query-named-block-nodes output
+_unsupported_imgopts data_file
 
 size=64M
 
diff --git a/tests/qemu-iotests/201 b/tests/qemu-iotests/201
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/201
+++ b/tests/qemu-iotests/201
@@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2
 _supported_proto generic
 _supported_os Linux
 
-# Internal snapshots are (currently) impossible with refcount_bits=1
-# This was taken from test 080
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 size=64M
 _make_test_img $size
diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/214
+++ b/tests/qemu-iotests/214
@@ -XXX,XX +XXX,XX @@ _supported_proto file
 
 # Repairing the corrupted image requires qemu-img check to store a
 # refcount up to 3, which requires at least two refcount bits.
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# External data files do not support compressed clusters.
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 
 echo
diff --git a/tests/qemu-iotests/217 b/tests/qemu-iotests/217
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/217
+++ b/tests/qemu-iotests/217
@@ -XXX,XX +XXX,XX @@ _supported_proto file
 
 # This test needs clusters with at least a refcount of 2 so that
 # OFLAG_COPIED is not set.  refcount_bits=1 is therefore unsupported.
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# (As are external data files.)
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 echo
 echo '=== Simulating an I/O error during snapshot deletion ==='
diff --git a/tests/qemu-iotests/220 b/tests/qemu-iotests/220
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/220
+++ b/tests/qemu-iotests/220
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# To use a different refcount width but 16 bits we need compat=1.1
-_unsupported_imgopts 'compat=0.10'
+# To use a different refcount width but 16 bits we need compat=1.1,
+# and external data files do not support compressed clusters.
+_unsupported_imgopts 'compat=0.10' data_file
 
 echo "== Creating huge file =="
 
diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/243
+++ b/tests/qemu-iotests/243
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# External data files do not work with compat=0.10
-_unsupported_imgopts 'compat=0.10'
+# External data files do not work with compat=0.10, and because there
+# is an explicit case for external data files here, we cannot allow
+# the user to specify whether to use one
+_unsupported_imgopts 'compat=0.10' data_file
 
 for mode in off metadata falloc full; do
 
diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/244
+++ b/tests/qemu-iotests/244
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
-# External data files do not work with compat=0.10
-_unsupported_imgopts 'compat=0.10'
+# External data files do not work with compat=0.10, and because we use
+# our own external data file, we cannot let the user specify one
+_unsupported_imgopts 'compat=0.10' data_file
 
 echo
 echo "=== Create and open image with external data file ==="
diff --git a/tests/qemu-iotests/250 b/tests/qemu-iotests/250
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/250
+++ b/tests/qemu-iotests/250
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# This test does not make much sense with external data files
+_unsupported_imgopts data_file
 
 # This test checks that qcow2_process_discards does not truncate a discard
 # request > 2G.
diff --git a/tests/qemu-iotests/261 b/tests/qemu-iotests/261
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/261
+++ b/tests/qemu-iotests/261
@@ -XXX,XX +XXX,XX @@ _supported_os Linux
 # (1) We create a v2 image that supports nothing but refcount_bits=16
 # (2) We do some refcount management on our own which expects
 #     refcount_bits=16
-_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)'
+# As for data files, they do not support snapshots at all.
+_unsupported_imgopts 'refcount_bits=$[^1]\|.\([^6]\|$$\)' data_file
 
 # Parameters:
 #   $1: image filename
diff --git a/tests/qemu-iotests/267 b/tests/qemu-iotests/267
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/267
+++ b/tests/qemu-iotests/267
@@ -XXX,XX +XXX,XX @@ _supported_proto file
 _supported_os Linux
 _require_drivers copy-on-read
 
-# Internal snapshots are (currently) impossible with refcount_bits=1
-_unsupported_imgopts 'refcount_bits=1[^0-9]'
+# Internal snapshots are (currently) impossible with refcount_bits=1,
+# and generally impossible with external data files
+_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file
 
 do_run_qemu()
 {
diff --git a/tests/qemu-iotests/273 b/tests/qemu-iotests/273
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/273
+++ b/tests/qemu-iotests/273
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt qcow2
 _supported_proto file
 _supported_os Linux
+# External data files would add nodes to the block graph, so it would
+# not match the reference output
+_unsupported_imgopts data_file
 
 do_run_qemu()
 {
-- 
2.24.1

The problem with allowing the data_file option is that you want to use a
different data file per image used in the test.  Therefore, we need to
allow patterns like -o data_file='$TEST_IMG.data_file'.

Then, we need to filter it out from qemu-img map, qemu-img create, and
remove the data file in _rm_test_img.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-id: 20191107163708.833192-23-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/common.filter | 23 +++++++++++++++++++++--
 tests/qemu-iotests/common.rc     | 22 +++++++++++++++++++++-
 2 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -XXX,XX +XXX,XX @@ _filter_actual_image_size()
 # replace driver-specific options in the "Formatting..." line
 _filter_img_create()
 {
-    $SED -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \
+    data_file_filter=()
+    if data_file=$(_get_data_file "$TEST_IMG"); then
+        data_file_filter=(-e "s# data_file=$data_file##")
+    fi
+
+    $SED "${data_file_filter[@]}" \
+        -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \
         -e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \
         -e "s#$TEST_DIR#TEST_DIR#g" \
         -e "s#$SOCK_DIR#SOCK_DIR#g" \
@@ -XXX,XX +XXX,XX @@ _filter_img_info()
 # human and json output
 _filter_qemu_img_map()
 {
+    # Assuming the data_file value in $IMGOPTS contains a '$TEST_IMG',
+    # create a filter that replaces the data file name by $TEST_IMG.
+    # Example:
+    #   In $IMGOPTS: 'data_file=$TEST_IMG.data_file'
+    #   Then data_file_pattern == '$.*$.data_file'
+    #   And  data_file_filter  == -e 's#$.*$.data_file#\1#
+    data_file_filter=()
+    if data_file_pattern=$(_get_data_file '\$.*\$'); then
+        data_file_filter=(-e "s#$data_file_pattern#\\1#")
+    fi
+
     $SED -e 's/$[0-9a-fx]* *[0-9a-fx]* *$[0-9a-fx]* */\1/g' \
         -e 's/"offset": [0-9]\+/"offset": OFFSET/g' \
-        -e 's/Mapped to *//' | _filter_testdir | _filter_imgfmt
+        -e 's/Mapped to *//' \
+        "${data_file_filter[@]}" \
+        | _filter_testdir | _filter_imgfmt
 }
 
 _filter_nbd()
diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -XXX,XX +XXX,XX @@ _stop_nbd_server()
     fi
 }
 
+# Gets the data_file value from IMGOPTS and replaces the '$TEST_IMG'
+# pattern by '$1'
+# Caution: The replacement is done with sed, so $1 must be escaped
+#          properly.  (The delimiter is '#'.)
+_get_data_file()
+{
+    if ! echo "$IMGOPTS" | grep -q 'data_file='; then
+        return 1
+    fi
+
+    echo "$IMGOPTS" | sed -e 's/.*data_file=$[^,]*$.*/\1/' \
+                    | sed -e "s#\\\$TEST_IMG#$1#"
+}
+
 _make_test_img()
 {
     # extra qemu-img options can be added by tests
@@ -XXX,XX +XXX,XX @@ _make_test_img()
     fi
 
     if [ -n "$IMGOPTS" ]; then
-        optstr=$(_optstr_add "$optstr" "$IMGOPTS")
+        imgopts_expanded=$(echo "$IMGOPTS" | sed -e "s#\\\$TEST_IMG#$img_name#")
+        optstr=$(_optstr_add "$optstr" "$imgopts_expanded")
     fi
     if [ -n "$IMGKEYSECRET" ]; then
         object_options="--object secret,id=keysec0,data=$IMGKEYSECRET"
@@ -XXX,XX +XXX,XX @@ _rm_test_img()
         # Remove all the extents for vmdk
         "$QEMU_IMG" info "$img" 2>/dev/null | grep 'filename:' | cut -f 2 -d: \
             | xargs -I {} rm -f "{}"
+    elif [ "$IMGFMT" = "qcow2" ]; then
+        # Remove external data file
+        if data_file=$(_get_data_file "$img"); then
+            rm -f "$data_file"
+        fi
     fi
     rm -f "$img"
 }
-- 
2.24.1

From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>

Allow writing all the data compressed through the filter driver.
The written data will be aligned by the cluster size.
Based on the QEMU current implementation, that data can be written to
unallocated clusters only. May be used for a backup job.

Suggested-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-id: 1575288906-551879-2-git-send-email-andrey.shinkevich@virtuozzo.com
[mreitz: Replace NULL bdrv_get_format_name() by "(no format)"]
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/Makefile.objs     |   1 +
 block/filter-compress.c | 168 ++++++++++++++++++++++++++++++++++++++++
 qapi/block-core.json    |  10 ++-
 3 files changed, 175 insertions(+), 4 deletions(-)
 create mode 100644 block/filter-compress.c

diff --git a/block/Makefile.objs b/block/Makefile.objs
index XXXXXXX..XXXXXXX 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -XXX,XX +XXX,XX @@ block-obj-y += crypto.o
 
 block-obj-y += aio_task.o
 block-obj-y += backup-top.o
+block-obj-y += filter-compress.o
 
 common-obj-y += stream.o
 
diff --git a/block/filter-compress.c b/block/filter-compress.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/block/filter-compress.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * Compress filter block driver
+ *
+ * Copyright (c) 2019 Virtuozzo International GmbH
+ *
+ * Author:
+ *   Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
+ *   (based on block/copy-on-read.c by Max Reitz)
+ *
+ * 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 or
+ * (at your option) any later version of the License.
+ *
+ * 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 "block/block_int.h"
+#include "qemu/module.h"
+#include "qapi/error.h"
+
+
+static int compress_open(BlockDriverState *bs, QDict *options, int flags,
+                         Error **errp)
+{
+    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false,
+                               errp);
+    if (!bs->file) {
+        return -EINVAL;
+    }
+
+    if (!bs->file->bs->drv || !block_driver_can_compress(bs->file->bs->drv)) {
+        error_setg(errp,
+                   "Compression is not supported for underlying format: %s",
+                   bdrv_get_format_name(bs->file->bs) ?: "(no format)");
+
+        return -ENOTSUP;
+    }
+
+    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 int64_t compress_getlength(BlockDriverState *bs)
+{
+    return bdrv_getlength(bs->file->bs);
+}
+
+
+static int coroutine_fn compress_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 compress_co_pwritev_part(BlockDriverState *bs,
+                                                 uint64_t offset,
+                                                 uint64_t bytes,
+                                                 QEMUIOVector *qiov,
+                                                 size_t qiov_offset, int flags)
+{
+    return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset,
+                                flags | BDRV_REQ_WRITE_COMPRESSED);
+}
+
+
+static int coroutine_fn compress_co_pwrite_zeroes(BlockDriverState *bs,
+                                                  int64_t offset, int bytes,
+                                                  BdrvRequestFlags flags)
+{
+    return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
+}
+
+
+static int coroutine_fn compress_co_pdiscard(BlockDriverState *bs,
+                                             int64_t offset, int bytes)
+{
+    return bdrv_co_pdiscard(bs->file, offset, bytes);
+}
+
+
+static void compress_refresh_limits(BlockDriverState *bs, Error **errp)
+{
+    BlockDriverInfo bdi;
+    int ret;
+
+    if (!bs->file) {
+        return;
+    }
+
+    ret = bdrv_get_info(bs->file->bs, &bdi);
+    if (ret < 0 || bdi.cluster_size == 0) {
+        return;
+    }
+
+    bs->bl.request_alignment = bdi.cluster_size;
+}
+
+
+static void compress_eject(BlockDriverState *bs, bool eject_flag)
+{
+    bdrv_eject(bs->file->bs, eject_flag);
+}
+
+
+static void compress_lock_medium(BlockDriverState *bs, bool locked)
+{
+    bdrv_lock_medium(bs->file->bs, locked);
+}
+
+
+static bool compress_recurse_is_first_non_filter(BlockDriverState *bs,
+                                                 BlockDriverState *candidate)
+{
+    return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
+}
+
+
+static BlockDriver bdrv_compress = {
+    .format_name                        = "compress",
+
+    .bdrv_open                          = compress_open,
+    .bdrv_child_perm                    = bdrv_filter_default_perms,
+
+    .bdrv_getlength                     = compress_getlength,
+
+    .bdrv_co_preadv_part                = compress_co_preadv_part,
+    .bdrv_co_pwritev_part               = compress_co_pwritev_part,
+    .bdrv_co_pwrite_zeroes              = compress_co_pwrite_zeroes,
+    .bdrv_co_pdiscard                   = compress_co_pdiscard,
+    .bdrv_refresh_limits                = compress_refresh_limits,
+
+    .bdrv_eject                         = compress_eject,
+    .bdrv_lock_medium                   = compress_lock_medium,
+
+    .bdrv_co_block_status               = bdrv_co_block_status_from_file,
+
+    .bdrv_recurse_is_first_non_filter   = compress_recurse_is_first_non_filter,
+
+    .has_variable_length                = true,
+    .is_filter                          = true,
+};
+
+static void bdrv_compress_init(void)
+{
+    bdrv_register(&bdrv_compress);
+}
+
+block_init(bdrv_compress_init);
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 @@
 # @copy-on-read: Since 3.0
 # @blklogwrites: Since 3.0
 # @blkreplay: Since 4.2
+# @compress: Since 5.0
 #
 # Since: 2.9
 ##
 { 'enum': 'BlockdevDriver',
   'data': [ 'blkdebug', 'blklogwrites', 'blkreplay', 'blkverify', 'bochs',
-            'cloop', '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',
+            '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',
             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
             'sheepdog',
             'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
@@ -XXX,XX +XXX,XX @@
       'blkreplay':  'BlockdevOptionsBlkreplay',
       'bochs':      'BlockdevOptionsGenericFormat',
       'cloop':      'BlockdevOptionsGenericFormat',
+      'compress':   'BlockdevOptionsGenericFormat',
       'copy-on-read':'BlockdevOptionsGenericFormat',
       'dmg':        'BlockdevOptionsGenericFormat',
       'file':       'BlockdevOptionsFile',
-- 
2.24.1

From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>

QEMU currently supports writing compressed data of the size equal to
one cluster. This patch allows writing QCOW2 compressed data that
exceed one cluster. Now, we split buffered data into separate clusters
and write them compressed using the block/aio_task API.

Suggested-by: Pavel Butsykin <pbutsykin@virtuozzo.com>
Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-id: 1575288906-551879-3-git-send-email-andrey.shinkevich@virtuozzo.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/qcow2.c | 102 +++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 75 insertions(+), 27 deletions(-)

diff --git a/block/qcow2.c b/block/qcow2.c
index XXXXXXX..XXXXXXX 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -XXX,XX +XXX,XX @@ fail:
     return ret;
 }
 
-/* XXX: put compressed sectors first, then all the cluster aligned
-   tables to avoid losing bytes in alignment */
 static coroutine_fn int
-qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
+qcow2_co_pwritev_compressed_task(BlockDriverState *bs,
                                  uint64_t offset, uint64_t bytes,
                                  QEMUIOVector *qiov, size_t qiov_offset)
 {
@@ -XXX,XX +XXX,XX @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
     uint8_t *buf, *out_buf;
     uint64_t cluster_offset;
 
-    if (has_data_file(bs)) {
-        return -ENOTSUP;
-    }
-
-    if (bytes == 0) {
-        /* align end of file to a sector boundary to ease reading with
-           sector based I/Os */
-        int64_t len = bdrv_getlength(bs->file->bs);
-        if (len < 0) {
-            return len;
-        }
-        return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL);
-    }
-
-    if (offset_into_cluster(s, offset)) {
-        return -EINVAL;
-    }
+    assert(bytes == s->cluster_size || (bytes < s->cluster_size &&
+           (offset + bytes == bs->total_sectors << BDRV_SECTOR_BITS)));
 
     buf = qemu_blockalign(bs, s->cluster_size);
-    if (bytes != s->cluster_size) {
-        if (bytes > s->cluster_size ||
-            offset + bytes != bs->total_sectors << BDRV_SECTOR_BITS)
-        {
-            qemu_vfree(buf);
-            return -EINVAL;
-        }
+    if (bytes < s->cluster_size) {
         /* Zero-pad last write if image size is not cluster aligned */
         memset(buf + bytes, 0, s->cluster_size - bytes);
     }
@@ -XXX,XX +XXX,XX @@ fail:
     return ret;
 }
 
+static coroutine_fn int qcow2_co_pwritev_compressed_task_entry(AioTask *task)
+{
+    Qcow2AioTask *t = container_of(task, Qcow2AioTask, task);
+
+    assert(!t->cluster_type && !t->l2meta);
+
+    return qcow2_co_pwritev_compressed_task(t->bs, t->offset, t->bytes, t->qiov,
+                                            t->qiov_offset);
+}
+
+/*
+ * XXX: put compressed sectors first, then all the cluster aligned
+ * tables to avoid losing bytes in alignment
+ */
+static coroutine_fn int
+qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
+                                 uint64_t offset, uint64_t bytes,
+                                 QEMUIOVector *qiov, size_t qiov_offset)
+{
+    BDRVQcow2State *s = bs->opaque;
+    AioTaskPool *aio = NULL;
+    int ret = 0;
+
+    if (has_data_file(bs)) {
+        return -ENOTSUP;
+    }
+
+    if (bytes == 0) {
+        /*
+         * align end of file to a sector boundary to ease reading with
+         * sector based I/Os
+         */
+        int64_t len = bdrv_getlength(bs->file->bs);
+        if (len < 0) {
+            return len;
+        }
+        return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL);
+    }
+
+    if (offset_into_cluster(s, offset)) {
+        return -EINVAL;
+    }
+
+    while (bytes && aio_task_pool_status(aio) == 0) {
+        uint64_t chunk_size = MIN(bytes, s->cluster_size);
+
+        if (!aio && chunk_size != bytes) {
+            aio = aio_task_pool_new(QCOW2_MAX_WORKERS);
+        }
+
+        ret = qcow2_add_task(bs, aio, qcow2_co_pwritev_compressed_task_entry,
+                             0, 0, offset, chunk_size, qiov, qiov_offset, NULL);
+        if (ret < 0) {
+            break;
+        }
+        qiov_offset += chunk_size;
+        offset += chunk_size;
+        bytes -= chunk_size;
+    }
+
+    if (aio) {
+        aio_task_pool_wait_all(aio);
+        if (ret == 0) {
+            ret = aio_task_pool_status(aio);
+        }
+        g_free(aio);
+    }
+
+    return ret;
+}
+
 static int coroutine_fn
 qcow2_co_preadv_compressed(BlockDriverState *bs,
                            uint64_t file_cluster_offset,
-- 
2.24.1

From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>

Add the case to the iotest #214 that checks possibility of writing
compressed data of more than one cluster size. The test case involves
the compress filter driver showing a sample usage of that.

Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-id: 1575288906-551879-4-git-send-email-andrey.shinkevich@virtuozzo.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/214     | 43 ++++++++++++++++++++++++++++++++++++++
 tests/qemu-iotests/214.out | 14 +++++++++++++
 2 files changed, 57 insertions(+)

diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/214
+++ b/tests/qemu-iotests/214
@@ -XXX,XX +XXX,XX @@ _check_test_img -r all
 $QEMU_IO -c "read  -P 0x11  0 4M" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir
 $QEMU_IO -c "read  -P 0x22 4M 4M" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir
 
+echo
+echo "=== Write compressed data of multiple clusters ==="
+echo
+cluster_size=0x10000
+_make_test_img 2M -o cluster_size=$cluster_size
+
+echo "Write uncompressed data:"
+let data_size="8 * $cluster_size"
+$QEMU_IO -c "write -P 0xaa 0 $data_size" "$TEST_IMG" \
+         2>&1 | _filter_qemu_io | _filter_testdir
+sizeA=$($QEMU_IMG info --output=json "$TEST_IMG" |
+        sed -n '/"actual-size":/ s/[^0-9]//gp')
+
+_make_test_img 2M -o cluster_size=$cluster_size
+echo "Write compressed data:"
+let data_size="3 * $cluster_size + $cluster_size / 2"
+# Set compress on. That will align the written data
+# by the cluster size and will write them compressed.
+QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT \
+$QEMU_IO -c "write -P 0xbb 0 $data_size" --image-opts \
+         "driver=compress,file.driver=$IMGFMT,file.file.driver=file,file.file.filename=$TEST_IMG" \
+         2>&1 | _filter_qemu_io | _filter_testdir
+
+let offset="4 * $cluster_size + $cluster_size / 4"
+QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT \
+$QEMU_IO -c "write -P 0xcc $offset $data_size" "json:{\
+    'driver': 'compress',
+    'file': {'driver': '$IMGFMT',
+             'file': {'driver': 'file',
+                      'filename': '$TEST_IMG'}}}" | \
+                          _filter_qemu_io | _filter_testdir
+
+sizeB=$($QEMU_IMG info --output=json "$TEST_IMG" |
+        sed -n '/"actual-size":/ s/[^0-9]//gp')
+
+if [ $sizeA -le $sizeB ]
+then
+    echo "Compression ERROR"
+fi
+
+$QEMU_IMG check --output=json "$TEST_IMG" |
+          sed -n 's/,$//; /"compressed-clusters":/ s/^ *//p'
+
 # success, all done
 echo '*** done'
 rm -f $seq.full
diff --git a/tests/qemu-iotests/214.out b/tests/qemu-iotests/214.out
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/214.out
+++ b/tests/qemu-iotests/214.out
@@ -XXX,XX +XXX,XX @@ read 4194304/4194304 bytes at offset 0
 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 read 4194304/4194304 bytes at offset 4194304
 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+=== Write compressed data of multiple clusters ===
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2097152
+Write uncompressed data:
+wrote 524288/524288 bytes at offset 0
+512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2097152
+Write compressed data:
+wrote 229376/229376 bytes at offset 0
+224 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 229376/229376 bytes at offset 278528
+224 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+"compressed-clusters": 8
 *** done
-- 
2.24.1

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

Commit 6f6e1698a6 desugarized "-machine accel=" to a list
of "-accel" options. Since now "-machine accel" and "-accel"
became incompatible, update the iotests to the new format.

Error reported here:
https://gitlab.com/qemu-project/qemu/-/jobs/385801004#L3400

Reported-by: GitLab CI
Fixes: 6f6e1698a6 (vl: configure accelerators from -accel options)
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200106130951.29873-1-philmd@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 tests/qemu-iotests/235   | 2 +-
 tests/qemu-iotests/check | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tests/qemu-iotests/235 b/tests/qemu-iotests/235
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/235
+++ b/tests/qemu-iotests/235
@@ -XXX,XX +XXX,XX @@ qemu_img_create('-f', iotests.imgfmt, '-o', 'preallocation=metadata', disk,
                 str(size))
 
 vm = QEMUMachine(iotests.qemu_prog)
-vm.add_args('-machine', 'accel=kvm:tcg')
+vm.add_args('-accel', 'kvm', '-accel', 'tcg')
 if iotests.qemu_default_machine == 's390-ccw-virtio':
         vm.add_args('-no-shutdown')
 vm.add_args('-drive', 'id=src,file=' + disk)
diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/check
+++ b/tests/qemu-iotests/check
@@ -XXX,XX +XXX,XX @@ export QEMU_PROG="$(type -p "$QEMU_PROG")"
 
 case "$QEMU_PROG" in
     *qemu-system-arm|*qemu-system-aarch64)
-        export QEMU_OPTIONS="-nodefaults -display none -machine virt,accel=qtest"
+        export QEMU_OPTIONS="-nodefaults -display none -machine virt -accel qtest"
         ;;
     *qemu-system-tricore)
-        export QEMU_OPTIONS="-nodefaults -display none -machine tricore_testboard,accel=qtest"
+        export QEMU_OPTIONS="-nodefaults -display none -machine tricore_testboard -accel qtest"
         ;;
     *)
-        export QEMU_OPTIONS="-nodefaults -display none -machine accel=qtest"
+        export QEMU_OPTIONS="-nodefaults -display none -accel qtest"
         ;;
 esac
 
-- 
2.24.1

When dropping backup-top, we need to drain the node before freeing the
BlockCopyState.  Otherwise, requests may still be in flight and then the
assertion in shres_destroy() will fail.

(This becomes visible in intermittent failure of 056.)

Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20191219182638.104621-1-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
---
 block/backup-top.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/backup-top.c b/block/backup-top.c
index XXXXXXX..XXXXXXX 100644
--- a/block/backup-top.c
+++ b/block/backup-top.c
@@ -XXX,XX +XXX,XX @@ void bdrv_backup_top_drop(BlockDriverState *bs)
     BDRVBackupTopState *s = bs->opaque;
     AioContext *aio_context = bdrv_get_aio_context(bs);
 
-    block_copy_state_free(s->bcs);
-
     aio_context_acquire(aio_context);
 
     bdrv_drained_begin(bs);
 
+    block_copy_state_free(s->bcs);
+
     s->active = false;
     bdrv_child_refresh_perms(bs, bs->backing, &error_abort);
     bdrv_replace_node(bs, backing_bs(bs), &error_abort);
-- 
2.24.1

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