[Qemu-devel] [PATCH v9 07/17] qapi: Start converting to new qapi union layout

[Eric Blake]

We have two issues with our qapi union layout:
1) Even though the QMP wire format spells the tag 'type', the
C code spells it 'kind', requiring some hacks in the generator.
2) The C struct uses an anonymous union, which places all tag
values in the same namespace as all non-variant members. This
leads to spurious collisions if a tag value matches a QMP name.

This patch is the front end for a series that converts to a
saner qapi union layout.  By the end of the series, we will no
longer have the type/kind mismatch, and all tag values will be
under a named union, which requires clients to access
'obj->u.value' instead of 'obj->value'.  But since the
conversion touches a number of files, it is easiest if we
temporarily support BOTH layouts simultaneously.

Given a simple union qapi type:

{ 'union':'Foo', 'data': { 'a':'int', 'b':'bool' } }

we make the following changes in generated qapi-types.h:

| struct Foo {
|-    FooKind kind;
|-    union { /* union tag is @kind */
|+    union {
|+        FooKind kind;
|+        FooKind type;
|+    };
|+    union { /* union tag is @type */
|         void *data;
|         int64_t a;
|         bool b;
|+        union { /* union tag is @type */
|+            void *data;
|+            int64_t a;
|+            bool b;
|+        } u;
|     };
| };

Flat unions do not need the anonymous union for the tag member,
as we already fixed that to use the member name instead of 'kind'
back in commit 0f61af3e.  On the other hand, the duplication
means that we temporarily cannot support 'u' as a branch name.

Later, when the conversions are complete, we will remove the
duplication hacks and restore support for 'u' as a branch name.

Note, however, that we do not rename the generated enum, which
is still 'FooKind'.  A further patch could generate implicit
enums as 'FooType', but that causes more churn to C code, and
gets harder since the generator already reserved the '*Kind'
namespace, but there are already QMP constructs with '*Type'
naming which means we cannot easily reserve it for qapi.

Signed-off-by: Eric Blake <address@hidden>

---
v9: new patch, but incorporates parts of v5 31/46 and Markus' RFC:
http://lists.gnu.org/archive/html/qemu-devel/2015-10/msg02236.html
---
 scripts/qapi-types.py                   | 26 +++++++++++++++++++-------
 scripts/qapi-visit.py                   | 24 +++++++++---------------
 tests/qapi-schema/qapi-schema-test.json |  4 +++-
 tests/qapi-schema/qapi-schema-test.out  |  4 ++--
 4 files changed, 33 insertions(+), 25 deletions(-)

diff --git a/scripts/qapi-types.py b/scripts/qapi-types.py
index bcef39d..0a14451 100644
--- a/scripts/qapi-types.py
+++ b/scripts/qapi-types.py
@@ -136,11 +136,23 @@ struct %(c_name)s {
     if base:
         ret += gen_struct_fields([], base)
     else:
+        # TODO As a hack, we emit both 'kind' and 'type'. Ultimately, we
+        # want to use only 'type', but the conversion is large enough to
+        # require staging over several commits.
         ret += mcgen('''
-    %(c_type)s kind;
+    union {
+        %(c_type)s kind;
+        %(c_type)s type;
+    };
 ''',
                      c_type=c_name(variants.tag_member.type.name))

+    # TODO As a hack, we emit the union twice, once as an anonymous union
+    # and once as a named union.  Ultimately, we want to use only the
+    # named union version (as it avoids conflicts between tag values as
+    # branch names competing with non-variant QMP names), but the conversion
+    # is large enough to require staging over several commits.
+    tmp = ''
     # FIXME: What purpose does data serve, besides preventing a union that
     # has a branch named 'data'? We use it in qapi-visit.py to decide
     # whether to bypass the switch statement if visiting the discriminator
@@ -149,25 +161,25 @@ struct %(c_name)s {
     # should not be any data leaks even without a data pointer.  Or, if
     # 'data' is merely added to guarantee we don't have an empty union,
     # shouldn't we enforce that at .json parse time?
-    ret += mcgen('''
+    tmp += mcgen('''
     union { /* union tag is @%(c_name)s */
         void *data;
 ''',
-                 # TODO ugly special case for simple union
-                 # Use same tag name in C as on the wire to get rid of
-                 # it, then: c_name=c_name(variants.tag_member.name)
-                 c_name=c_name(variants.tag_name or 'kind'))
+                 c_name=c_name(variants.tag_member.name))

     for var in variants.variants:
         # Ugly special case for simple union TODO get rid of it
         typ = var.simple_union_type() or var.type
-        ret += mcgen('''
+        tmp += mcgen('''
         %(c_type)s %(c_name)s;
 ''',
                      c_type=typ.c_type(),
                      c_name=c_name(var.name))

+    ret += tmp
+    ret += '    ' + '\n    '.join(tmp.split('\n'))
     ret += mcgen('''
+    } u;
     };
 };
 ''')
diff --git a/scripts/qapi-visit.py b/scripts/qapi-visit.py
index 91bf350..2afe811 100644
--- a/scripts/qapi-visit.py
+++ b/scripts/qapi-visit.py
@@ -182,18 +182,18 @@ void visit_type_%(c_name)s(Visitor *v, %(c_name)s **obj, 
const char *name, Error
     if (err) {
         goto out;
     }
-    visit_get_next_type(v, (int*) &(*obj)->kind, %(c_name)s_qtypes, name, 
&err);
+    visit_get_next_type(v, (int*) &(*obj)->type, %(c_name)s_qtypes, name, 
&err);
     if (err) {
         goto out_obj;
     }
-    switch ((*obj)->kind) {
+    switch ((*obj)->type) {
 ''',
                 c_name=c_name(name))

     for var in variants.variants:
         ret += mcgen('''
     case %(case)s:
-        visit_type_%(c_type)s(v, &(*obj)->%(c_name)s, name, &err);
+        visit_type_%(c_type)s(v, &(*obj)->u.%(c_name)s, name, &err);
         break;
 ''',
                      case=c_enum_const(variants.tag_member.type.name,
@@ -255,22 +255,16 @@ void visit_type_%(c_name)s(Visitor *v, %(c_name)s **obj, 
const char *name, Error
     visit_type_%(c_type)s(v, &(*obj)->%(c_name)s, "%(name)s", &err);
 ''',
                      c_type=variants.tag_member.type.c_name(),
-                     # TODO ugly special case for simple union
-                     # Use same tag name in C as on the wire to get rid of
-                     # it, then: c_name=c_name(variants.tag_member.name)
-                     c_name='kind',
+                     c_name=c_name(variants.tag_member.name),
                      name=variants.tag_member.name)
     ret += gen_err_check(label='out_obj')
     ret += mcgen('''
-    if (!visit_start_union(v, !!(*obj)->data, &err) || err) {
+    if (!visit_start_union(v, !!(*obj)->u.data, &err) || err) {
         goto out_obj;
     }
     switch ((*obj)->%(c_name)s) {
 ''',
-                 # TODO ugly special case for simple union
-                 # Use same tag name in C as on the wire to get rid of
-                 # it, then: c_name=c_name(variants.tag_member.name)
-                 c_name=c_name(variants.tag_name or 'kind'))
+                 c_name=c_name(variants.tag_member.name))

     for var in variants.variants:
         # TODO ugly special case for simple union
@@ -282,13 +276,13 @@ void visit_type_%(c_name)s(Visitor *v, %(c_name)s **obj, 
const char *name, Error
                                        var.name))
         if simple_union_type:
             ret += mcgen('''
-        visit_type_%(c_type)s(v, &(*obj)->%(c_name)s, "data", &err);
+        visit_type_%(c_type)s(v, &(*obj)->u.%(c_name)s, "data", &err);
 ''',
                          c_type=simple_union_type.c_name(),
                          c_name=c_name(var.name))
         else:
             ret += mcgen('''
-        visit_type_implicit_%(c_type)s(v, &(*obj)->%(c_name)s, &err);
+        visit_type_implicit_%(c_type)s(v, &(*obj)->u.%(c_name)s, &err);
 ''',
                          c_type=var.type.c_name(),
                          c_name=c_name(var.name))
@@ -304,7 +298,7 @@ out_obj:
     error_propagate(errp, err);
     err = NULL;
     if (*obj) {
-        visit_end_union(v, !!(*obj)->data, &err);
+        visit_end_union(v, !!(*obj)->u.data, &err);
     }
     error_propagate(errp, err);
     err = NULL;
diff --git a/tests/qapi-schema/qapi-schema-test.json 
b/tests/qapi-schema/qapi-schema-test.json
index 22e15eb..876ce18 100644
--- a/tests/qapi-schema/qapi-schema-test.json
+++ b/tests/qapi-schema/qapi-schema-test.json
@@ -113,8 +113,10 @@
 # should still be valid as a type or union branch name. And although
 # '*Kind' and '*List' are forbidden as type names, they should not be
 # forbidden as a member or branch name.
+# TODO - we temporarily do not support 'u' as branch name, while converting
+# code to use the new union layout
 { 'struct': 'has_a', 'data': { 'MyKind': 'int', 'MyList': ['int'] } }
-{ 'union': 'u', 'data': { 'u': 'uint8', 'myKind': 'has_a',
+{ 'union': 'u', 'data': { 'u8': 'uint8', 'myKind': 'has_a',
                           'myList': 'has_a' } }

 # testing commands
diff --git a/tests/qapi-schema/qapi-schema-test.out 
b/tests/qapi-schema/qapi-schema-test.out
index feaf20d..cb12435 100644
--- a/tests/qapi-schema/qapi-schema-test.out
+++ b/tests/qapi-schema/qapi-schema-test.out
@@ -202,10 +202,10 @@ object has_a
     member MyKind: int optional=False
     member MyList: intList optional=False
 object u
-    case u: :obj-uint8-wrapper
+    case u8: :obj-uint8-wrapper
     case myKind: :obj-has_a-wrapper
     case myList: :obj-has_a-wrapper
-enum uKind ['u', 'myKind', 'myList']
+enum uKind ['u8', 'myKind', 'myList']
 command user_def_cmd None -> None
    gen=True success_response=True
 command user_def_cmd1 :obj-user_def_cmd1-arg -> None
-- 
2.4.3