Merge remote-tracking branch 'remotes/stefanha/tags/tracing-pull-request' into staging

# gpg: Signature made Tue 01 Mar 2016 15:48:04 GMT using RSA key ID 81AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"

* remotes/stefanha/tags/tracing-pull-request:
  trace: Add a proper API to manage auto-generated events from the 'tcg' property
  trace: Add 'vcpu' event property to trace guest vCPU
  typedefs: Add CPUState
  trace: Add helper function to cast event arguments
  tcg: Move definition of type TCGv
  tcg: Add type for vCPU pointers
  trace: Remove unnecessary intermediate event copies
  trace: Extend API to manage event arguments
  vl: fix tracing initialization
  trace: use addresses instead of offsets in memory tracepoints
  trace: split subpage MMIOs into their own trace events.
  trace: docs: "simple" backend does support strings
  trace: drop trailing empty strings

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

39 files changed, 339 insertions, 113 deletions

diff --git a/docs/tracing.txt b/docs/tracing.txt
index 3853a6a..3182ee8 100644
--- a/docs/tracing.txt
+++ b/docs/tracing.txt
@@ -172,9 +172,6 @@ source tree.  It may not be as powerful as platform-specific or third-party
 trace backends but it is portable.  This is the recommended trace backend
 unless you have specific needs for more advanced backends.
 
-The "simple" backend currently does not capture string arguments, it simply
-records the char* pointer value instead of the string that is pointed to.
-
 === Ftrace ===
 
 The "ftrace" backend writes trace data to ftrace marker. This effectively
@@ -347,3 +344,44 @@ This will immediately call:
 and will generate the TCG code to call:
 
     void trace_foo(uint8_t a1, uint32_t a2);
+
+=== "vcpu" ===
+
+Identifies events that trace vCPU-specific information. It implicitly adds a
+"CPUState*" argument, and extends the tracing print format to show the vCPU
+information. If used together with the "tcg" property, it adds a second
+"TCGv_env" argument that must point to the per-target global TCG register that
+points to the vCPU when guest code is executed (usually the "cpu_env" variable).
+
+The following example events:
+
+    foo(uint32_t a) "a=%x"
+    vcpu bar(uint32_t a) "a=%x"
+    tcg vcpu baz(uint32_t a) "a=%x", "a=%x"
+
+Can be used as:
+
+    #include "trace-tcg.h"
+    
+    CPUArchState *env;
+    TCGv_ptr cpu_env;
+    
+    void some_disassembly_func(...)
+    {
+        /* trace emitted at this point */
+        trace_foo(0xd1);
+        /* trace emitted at this point */
+        trace_bar(ENV_GET_CPU(env), 0xd2);
+        /* trace emitted at this point (env) and when guest code is executed (cpu_env) */
+        trace_baz_tcg(ENV_GET_CPU(env), cpu_env, 0xd3);
+    }
+
+If the translating vCPU has address 0xc1 and code is later executed by vCPU
+0xc2, this would be an example output:
+
+    // at guest code translation
+    foo a=0xd1
+    bar cpu=0xc1 a=0xd2
+    baz_trans cpu=0xc1 a=0xd3
+    // at guest code execution
+    baz_exec cpu=0xc2 a=0xd3
diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h
index 6ed91b4..9a5ead6 100644
--- a/include/qemu/typedefs.h
+++ b/include/qemu/typedefs.h
@@ -18,6 +18,7 @@ typedef struct BusState BusState;
 typedef struct CharDriverState CharDriverState;
 typedef struct CompatProperty CompatProperty;
 typedef struct CPUAddressSpace CPUAddressSpace;
+typedef struct CPUState CPUState;
 typedef struct DeviceListener DeviceListener;
 typedef struct DeviceState DeviceState;
 typedef struct DisplayChangeListener DisplayChangeListener;
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index 1df7cb4..7052eee 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -62,7 +62,6 @@ typedef uint64_t vaddr;
 #define CPU_CLASS(class) OBJECT_CLASS_CHECK(CPUClass, (class), TYPE_CPU)
 #define CPU_GET_CLASS(obj) OBJECT_GET_CLASS(CPUClass, (obj), TYPE_CPU)
 
-typedef struct CPUState CPUState;
 typedef struct CPUWatchpoint CPUWatchpoint;
 
 typedef void (*CPUUnassignedAccess)(CPUState *cpu, hwaddr addr,
diff --git a/memory.c b/memory.c
index 0dd9695..013c2ed 100644
--- a/memory.c
+++ b/memory.c
@@ -372,6 +372,20 @@ static void adjust_endianness(MemoryRegion *mr, uint64_t *data, unsigned size)
     }
 }
 
+static hwaddr memory_region_to_absolute_addr(MemoryRegion *mr, hwaddr offset)
+{
+    MemoryRegion *root;
+    hwaddr abs_addr = offset;
+
+    abs_addr += mr->addr;
+    for (root = mr; root->container; ) {
+        root = root->container;
+        abs_addr += root->addr;
+    }
+
+    return abs_addr;
+}
+
 static MemTxResult memory_region_oldmmio_read_accessor(MemoryRegion *mr,
                                                        hwaddr addr,
                                                        uint64_t *value,
@@ -383,7 +397,12 @@ static MemTxResult memory_region_oldmmio_read_accessor(MemoryRegion *mr,
     uint64_t tmp;
 
     tmp = mr->ops->old_mmio.read[ctz32(size)](mr->opaque, addr);
-    trace_memory_region_ops_read(mr, addr, tmp, size);
+    if (mr->subpage) {
+        trace_memory_region_subpage_read(mr, addr, tmp, size);
+    } else if (TRACE_MEMORY_REGION_OPS_READ_ENABLED) {
+        hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
+        trace_memory_region_ops_read(mr, abs_addr, tmp, size);
+    }
     *value |= (tmp & mask) << shift;
     return MEMTX_OK;
 }
@@ -399,7 +418,12 @@ static MemTxResult  memory_region_read_accessor(MemoryRegion *mr,
     uint64_t tmp;
 
     tmp = mr->ops->read(mr->opaque, addr, size);
-    trace_memory_region_ops_read(mr, addr, tmp, size);
+    if (mr->subpage) {
+        trace_memory_region_subpage_read(mr, addr, tmp, size);
+    } else if (TRACE_MEMORY_REGION_OPS_READ_ENABLED) {
+        hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
+        trace_memory_region_ops_read(mr, abs_addr, tmp, size);
+    }
     *value |= (tmp & mask) << shift;
     return MEMTX_OK;
 }
@@ -416,7 +440,12 @@ static MemTxResult memory_region_read_with_attrs_accessor(MemoryRegion *mr,
     MemTxResult r;
 
     r = mr->ops->read_with_attrs(mr->opaque, addr, &tmp, size, attrs);
-    trace_memory_region_ops_read(mr, addr, tmp, size);
+    if (mr->subpage) {
+        trace_memory_region_subpage_read(mr, addr, tmp, size);
+    } else if (TRACE_MEMORY_REGION_OPS_READ_ENABLED) {
+        hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
+        trace_memory_region_ops_read(mr, abs_addr, tmp, size);
+    }
     *value |= (tmp & mask) << shift;
     return r;
 }
@@ -432,7 +461,12 @@ static MemTxResult memory_region_oldmmio_write_accessor(MemoryRegion *mr,
     uint64_t tmp;
 
     tmp = (*value >> shift) & mask;
-    trace_memory_region_ops_write(mr, addr, tmp, size);
+    if (mr->subpage) {
+        trace_memory_region_subpage_write(mr, addr, tmp, size);
+    } else if (TRACE_MEMORY_REGION_OPS_WRITE_ENABLED) {
+        hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
+        trace_memory_region_ops_write(mr, abs_addr, tmp, size);
+    }
     mr->ops->old_mmio.write[ctz32(size)](mr->opaque, addr, tmp);
     return MEMTX_OK;
 }
@@ -448,7 +482,12 @@ static MemTxResult memory_region_write_accessor(MemoryRegion *mr,
     uint64_t tmp;
 
     tmp = (*value >> shift) & mask;
-    trace_memory_region_ops_write(mr, addr, tmp, size);
+    if (mr->subpage) {
+        trace_memory_region_subpage_write(mr, addr, tmp, size);
+    } else if (TRACE_MEMORY_REGION_OPS_WRITE_ENABLED) {
+        hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
+        trace_memory_region_ops_write(mr, abs_addr, tmp, size);
+    }
     mr->ops->write(mr->opaque, addr, tmp, size);
     return MEMTX_OK;
 }
@@ -464,7 +503,12 @@ static MemTxResult memory_region_write_with_attrs_accessor(MemoryRegion *mr,
     uint64_t tmp;
 
     tmp = (*value >> shift) & mask;
-    trace_memory_region_ops_write(mr, addr, tmp, size);
+    if (mr->subpage) {
+        trace_memory_region_subpage_write(mr, addr, tmp, size);
+    } else if (TRACE_MEMORY_REGION_OPS_WRITE_ENABLED) {
+        hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
+        trace_memory_region_ops_write(mr, abs_addr, tmp, size);
+    }
     return mr->ops->write_with_attrs(mr->opaque, addr, tmp, size, attrs);
 }
 
diff --git a/scripts/tracetool/__init__.py b/scripts/tracetool/__init__.py
index 181675f..be24039 100644
--- a/scripts/tracetool/__init__.py
+++ b/scripts/tracetool/__init__.py
@@ -6,7 +6,7 @@ Machinery for generating tracing-related intermediate files.
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
@@ -50,9 +50,14 @@ class Arguments:
         Parameters
         ----------
         args :
-            List of (type, name) tuples.
+            List of (type, name) tuples or Arguments objects.
         """
-        self._args = args
+        self._args = []
+        for arg in args:
+            if isinstance(arg, Arguments):
+                self._args.extend(arg._args)
+            else:
+                self._args.append(arg)
 
     def copy(self):
         """Create a new copy."""
@@ -83,6 +88,12 @@ class Arguments:
             res.append((arg_type, identifier))
         return Arguments(res)
 
+    def __getitem__(self, index):
+        if isinstance(index, slice):
+            return Arguments(self._args[index])
+        else:
+            return self._args[index]
+
     def __iter__(self):
         """Iterate over the (type, name) pairs."""
         return iter(self._args)
@@ -110,6 +121,10 @@ class Arguments:
         """List of argument types."""
         return [ type_ for type_, _ in self._args ]
 
+    def casted(self):
+        """List of argument names casted to their type."""
+        return ["(%s)%s" % (type_, name) for type_, name in self._args]
+
     def transform(self, *trans):
         """Return a new Arguments instance with transformed types.
 
@@ -146,9 +161,10 @@ class Event(object):
                       "(?:(?:(?P<fmt_trans>\".+),)?\s*(?P<fmt>\".+))?"
                       "\s*")
 
-    _VALID_PROPS = set(["disable", "tcg", "tcg-trans", "tcg-exec"])
+    _VALID_PROPS = set(["disable", "tcg", "tcg-trans", "tcg-exec", "vcpu"])
 
-    def __init__(self, name, props, fmt, args, orig=None):
+    def __init__(self, name, props, fmt, args, orig=None,
+                 event_trans=None, event_exec=None):
         """
         Parameters
         ----------
@@ -161,13 +177,19 @@ class Event(object):
         args : Arguments
             Event arguments.
         orig : Event or None
-            Original Event before transformation.
+            Original Event before transformation/generation.
+        event_trans : Event or None
+            Generated translation-time event ("tcg" property).
+        event_exec : Event or None
+            Generated execution-time event ("tcg" property).
 
         """
         self.name = name
         self.properties = props
         self.fmt = fmt
         self.args = args
+        self.event_trans = event_trans
+        self.event_exec = event_exec
 
         if orig is None:
             self.original = weakref.ref(self)
@@ -183,7 +205,7 @@ class Event(object):
     def copy(self):
         """Create a new copy."""
         return Event(self.name, list(self.properties), self.fmt,
-                     self.args.copy(), self)
+                     self.args.copy(), self, self.event_trans, self.event_exec)
 
     @staticmethod
     def build(line_str):
@@ -215,7 +237,13 @@ class Event(object):
         if "tcg" in props and isinstance(fmt, str):
             raise ValueError("Events with 'tcg' property must have two formats")
 
-        return Event(name, props, fmt, args)
+        event = Event(name, props, fmt, args)
+
+        # add implicit arguments when using the 'vcpu' property
+        import tracetool.vcpu
+        event = tracetool.vcpu.transform_event(event)
+
+        return event
 
     def __repr__(self):
         """Evaluable string representation for this object."""
@@ -270,6 +298,7 @@ def _read_events(fobj):
             event_trans.name += "_trans"
             event_trans.properties += ["tcg-trans"]
             event_trans.fmt = event.fmt[0]
+            # ignore TCG arguments
             args_trans = []
             for atrans, aorig in zip(
                     event_trans.transform(tracetool.transform.TCG_2_HOST).args,
@@ -277,13 +306,12 @@ def _read_events(fobj):
                 if atrans == aorig:
                     args_trans.append(atrans)
             event_trans.args = Arguments(args_trans)
-            event_trans = event_trans.copy()
 
             event_exec = event.copy()
             event_exec.name += "_exec"
             event_exec.properties += ["tcg-exec"]
             event_exec.fmt = event.fmt[1]
-            event_exec = event_exec.transform(tracetool.transform.TCG_2_HOST)
+            event_exec.args = event_exec.args.transform(tracetool.transform.TCG_2_HOST)
 
             new_event = [event_trans, event_exec]
             event.event_trans, event.event_exec = new_event
diff --git a/scripts/tracetool/format/events_h.py b/scripts/tracetool/format/events_h.py
index 9f114a3..bbfaa5b 100644
--- a/scripts/tracetool/format/events_h.py
+++ b/scripts/tracetool/format/events_h.py
@@ -6,7 +6,7 @@ trace/generated-events.h
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
@@ -43,7 +43,7 @@ def generate(events, backend):
         if "tcg-trans" in e.properties:
             # a single define for the two "sub-events"
             out('#define TRACE_%(name)s_ENABLED %(enabled)d',
-                name=e.original.original.name.upper(),
+                name=e.original.name.upper(),
                 enabled=enabled)
         out('#define TRACE_%s_ENABLED %d' % (e.name.upper(), enabled))
 
diff --git a/scripts/tracetool/format/h.py b/scripts/tracetool/format/h.py
index 9b39430..2bd68a2 100644
--- a/scripts/tracetool/format/h.py
+++ b/scripts/tracetool/format/h.py
@@ -6,7 +6,7 @@ trace/generated-tracers.h
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
@@ -23,6 +23,7 @@ def generate(events, backend):
         '#define TRACE__GENERATED_TRACERS_H',
         '',
         '#include "qemu-common.h"',
+        '#include "qemu/typedefs.h"',
         '')
 
     backend.generate_begin(events)
diff --git a/scripts/tracetool/format/tcg_h.py b/scripts/tracetool/format/tcg_h.py
index f676b66..006eaa8 100644
--- a/scripts/tracetool/format/tcg_h.py
+++ b/scripts/tracetool/format/tcg_h.py
@@ -6,14 +6,25 @@ Generate .h file for TCG code generation.
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
 __email__      = "stefanha@linux.vnet.ibm.com"
 
 
-from tracetool import out
+from tracetool import out, Arguments
+import tracetool.vcpu
+
+
+def vcpu_transform_args(args):
+    assert len(args) == 1
+    return Arguments([
+        args,
+        # NOTE: this name must be kept in sync with the one in "tcg_h"
+        # NOTE: Current helper code uses TCGv_env (CPUArchState*)
+        ("TCGv_env", "__tcg_" + args.names()[0]),
+    ])
 
 
 def generate(events, backend):
@@ -35,21 +46,21 @@ def generate(events, backend):
         if "tcg-trans" not in e.properties:
             continue
 
-        # get the original event definition
-        e = e.original.original
-
         out('static inline void %(name_tcg)s(%(args)s)',
             '{',
-            name_tcg=e.api(e.QEMU_TRACE_TCG),
-            args=e.args)
+            name_tcg=e.original.api(e.QEMU_TRACE_TCG),
+            args=tracetool.vcpu.transform_args("tcg_h", e.original))
 
         if "disable" not in e.properties:
+            args_trans = e.original.event_trans.args
+            args_exec = tracetool.vcpu.transform_args(
+                "tcg_helper_c", e.original.event_exec, "wrapper")
             out('    %(name_trans)s(%(argnames_trans)s);',
                 '    gen_helper_%(name_exec)s(%(argnames_exec)s);',
-                name_trans=e.event_trans.api(e.QEMU_TRACE),
-                name_exec=e.event_exec.api(e.QEMU_TRACE),
-                argnames_trans=", ".join(e.event_trans.args.names()),
-                argnames_exec=", ".join(e.event_exec.args.names()))
+                name_trans=e.original.event_trans.api(e.QEMU_TRACE),
+                name_exec=e.original.event_exec.api(e.QEMU_TRACE),
+                argnames_trans=", ".join(args_trans.names()),
+                argnames_exec=", ".join(args_exec.names()))
 
         out('}')
 
diff --git a/scripts/tracetool/format/tcg_helper_c.py b/scripts/tracetool/format/tcg_helper_c.py
index afd6e98..a089b0b 100644
--- a/scripts/tracetool/format/tcg_helper_c.py
+++ b/scripts/tracetool/format/tcg_helper_c.py
@@ -6,15 +6,38 @@ Generate trace/generated-helpers.c.
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
 __email__      = "stefanha@linux.vnet.ibm.com"
 
 
-from tracetool import out
+from tracetool import Arguments, out
 from tracetool.transform import *
+import tracetool.vcpu
+
+
+def vcpu_transform_args(args, mode):
+    assert len(args) == 1
+    # NOTE: this name must be kept in sync with the one in "tcg_h"
+    args = Arguments([(args.types()[0], "__tcg_" + args.names()[0])])
+    if mode == "code":
+        return Arguments([
+            # Does cast from helper requirements to tracing types
+            ("CPUState *", "ENV_GET_CPU(%s)" % args.names()[0]),
+        ])
+    else:
+        args = Arguments([
+            # NOTE: Current helper code uses TCGv_env (CPUArchState*)
+            ("CPUArchState *", args.names()[0]),
+        ])
+        if mode == "header":
+            return args
+        elif mode == "wrapper":
+            return args.transform(HOST_2_TCG)
+        else:
+            assert False
 
 
 def generate(events, backend):
@@ -34,18 +57,18 @@ def generate(events, backend):
         if "tcg-exec" not in e.properties:
             continue
 
-        # tracetool.generate always transforms types to host
-        e_args = e.original.args
-
-        values = ["(%s)%s" % (t, n)
-                  for t, n in e.args.transform(TCG_2_TCG_HELPER_DEF)]
+        e_args_api = tracetool.vcpu.transform_args(
+            "tcg_helper_c", e.original, "header").transform(
+                HOST_2_TCG_COMPAT, TCG_2_TCG_HELPER_DEF)
+        e_args_call = tracetool.vcpu.transform_args(
+            "tcg_helper_c", e, "code")
 
-        out('void %(name_tcg)s(%(args)s)',
+        out('void %(name_tcg)s(%(args_api)s)',
             '{',
-            '    %(name)s(%(values)s);',
+            '    %(name)s(%(args_call)s);',
             '}',
             name_tcg="helper_%s_proxy" % e.api(),
             name=e.api(),
-            args=e_args.transform(HOST_2_TCG_COMPAT, TCG_2_TCG_HELPER_DEF),
-            values=", ".join(values),
+            args_api=e_args_api,
+            args_call=", ".join(e_args_call.casted()),
             )
diff --git a/scripts/tracetool/format/tcg_helper_h.py b/scripts/tracetool/format/tcg_helper_h.py
index a8ba7ba..dc76c15 100644
--- a/scripts/tracetool/format/tcg_helper_h.py
+++ b/scripts/tracetool/format/tcg_helper_h.py
@@ -6,7 +6,7 @@ Generate trace/generated-helpers.h.
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
@@ -15,6 +15,7 @@ __email__      = "stefanha@linux.vnet.ibm.com"
 
 from tracetool import out
 from tracetool.transform import *
+import tracetool.vcpu
 
 
 def generate(events, backend):
@@ -29,11 +30,9 @@ def generate(events, backend):
         if "tcg-exec" not in e.properties:
             continue
 
-        # tracetool.generate always transforms types to host
-        e_args = e.original.args
-
         # TCG helper proxy declaration
         fmt = "DEF_HELPER_FLAGS_%(argc)d(%(name)s, %(flags)svoid%(types)s)"
+        e_args = tracetool.vcpu.transform_args("tcg_helper_c", e.original, "header")
         args = e_args.transform(HOST_2_TCG_COMPAT, HOST_2_TCG,
                                 TCG_2_TCG_HELPER_DECL)
         types = ", ".join(args.types())
diff --git a/scripts/tracetool/format/tcg_helper_wrapper_h.py b/scripts/tracetool/format/tcg_helper_wrapper_h.py
index cac5a87..020f442 100644
--- a/scripts/tracetool/format/tcg_helper_wrapper_h.py
+++ b/scripts/tracetool/format/tcg_helper_wrapper_h.py
@@ -6,7 +6,7 @@ Generate trace/generated-helpers-wrappers.h.
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
@@ -15,6 +15,7 @@ __email__      = "stefanha@linux.vnet.ibm.com"
 
 from tracetool import out
 from tracetool.transform import *
+import tracetool.vcpu
 
 
 def generate(events, backend):
@@ -33,7 +34,7 @@ def generate(events, backend):
             continue
 
         # tracetool.generate always transforms types to host
-        e_args = e.original.args
+        e_args = tracetool.vcpu.transform_args("tcg_helper_c", e.original, "wrapper")
 
         # mixed-type to TCG helper bridge
         args_tcg_compat = e_args.transform(HOST_2_TCG_COMPAT)
diff --git a/scripts/tracetool/format/ust_events_c.py b/scripts/tracetool/format/ust_events_c.py
index 9967c7a..bf0b334 100644
--- a/scripts/tracetool/format/ust_events_c.py
+++ b/scripts/tracetool/format/ust_events_c.py
@@ -32,4 +32,5 @@ def generate(events, backend):
         ' */',
         '#pragma GCC diagnostic ignored "-Wredundant-decls"',
         '',
+        '#include "qemu/typedefs.h"',
         '#include "generated-ust-provider.h"')
diff --git a/scripts/tracetool/transform.py b/scripts/tracetool/transform.py
index fc5e679..e18b053 100644
--- a/scripts/tracetool/transform.py
+++ b/scripts/tracetool/transform.py
@@ -6,7 +6,7 @@ Type-transformation rules.
 """
 
 __author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
-__copyright__  = "Copyright 2012-2014, Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2012-2016, Lluís Vilanova <vilanova@ac.upc.edu>"
 __license__    = "GPL version 2 or (at your option) any later version"
 
 __maintainer__ = "Stefan Hajnoczi"
@@ -98,6 +98,7 @@ HOST_2_TCG = {
     "uint32_t": "TCGv_i32",
     "uint64_t": "TCGv_i64",
     "void *"  : "TCGv_ptr",
+    "CPUArchState *": "TCGv_env",
     None: _host_2_tcg,
     }
 
@@ -130,6 +131,7 @@ TCG_2_TCG_HELPER_DECL = {
     "TCGv_ptr": "ptr",
     "TCGv_i32": "i32",
     "TCGv_i64": "i64",
+    "TCGv_env": "env",
     None: _tcg_2_tcg_helper_decl_error,
     }
 
diff --git a/scripts/tracetool/vcpu.py b/scripts/tracetool/vcpu.py
new file mode 100644
index 0000000..452c7f5
--- /dev/null
+++ b/scripts/tracetool/vcpu.py
@@ -0,0 +1,70 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+Generic management for the 'vcpu' property.
+
+"""
+
+__author__     = "Lluís Vilanova <vilanova@ac.upc.edu>"
+__copyright__  = "Copyright 2016, Lluís Vilanova <vilanova@ac.upc.edu>"
+__license__    = "GPL version 2 or (at your option) any later version"
+
+__maintainer__ = "Stefan Hajnoczi"
+__email__      = "stefanha@linux.vnet.ibm.com"
+
+
+from tracetool import Arguments, try_import
+
+
+def transform_event(event):
+    """Transform event to comply with the 'vcpu' property (if present)."""
+    if "vcpu" in event.properties:
+        # events with 'tcg-trans' and 'tcg-exec' are auto-generated from
+        # already-patched events
+        assert "tcg-trans" not in event.properties
+        assert "tcg-exec" not in event.properties
+
+        event.args = Arguments([("CPUState *", "__cpu"), event.args])
+        if "tcg" in event.properties:
+            fmt = "\"cpu=%p \""
+            event.fmt = [fmt + event.fmt[0],
+                         fmt + event.fmt[1]]
+        else:
+            fmt = "\"cpu=%p \""
+            event.fmt = fmt + event.fmt
+    return event
+
+
+def transform_args(format, event, *args, **kwargs):
+    """Transforms the arguments to suit the specified format.
+
+    The format module must implement function 'vcpu_args', which receives the
+    implicit arguments added by the 'vcpu' property, and must return suitable
+    arguments for the given format.
+
+    The function is only called for events with the 'vcpu' property.
+
+    Parameters
+    ==========
+    format : str
+        Format module name.
+    event : Event
+    args, kwargs
+        Passed to 'vcpu_transform_args'.
+
+    Returns
+    =======
+    Arguments
+        The transformed arguments, including the non-implicit ones.
+
+    """
+    if "vcpu" in event.properties:
+        ok, func = try_import("tracetool.format." + format,
+                              "vcpu_transform_args")
+        assert ok
+        assert func
+        return Arguments([func(event.args[:1], *args, **kwargs),
+                          event.args[1:]])
+    else:
+        return event.args
diff --git a/stubs/target-get-monitor-def.c b/stubs/target-get-monitor-def.c
index 013e657..4d1033d 100644
--- a/stubs/target-get-monitor-def.c
+++ b/stubs/target-get-monitor-def.c
@@ -20,10 +20,9 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/typedefs.h"
 #include "stdint.h"
 
-typedef struct CPUState CPUState;
-
 int target_get_monitor_def(CPUState *cs, const char *name, uint64_t *pval);
 
 int target_get_monitor_def(CPUState *cs, const char *name, uint64_t *pval)
diff --git a/target-alpha/translate.c b/target-alpha/translate.c
index 7b798b0..5b86992 100644
--- a/target-alpha/translate.c
+++ b/target-alpha/translate.c
@@ -93,7 +93,7 @@ typedef enum {
 } ExitStatus;
 
 /* global register indexes */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_std_ir[31];
 static TCGv cpu_fir[31];
 static TCGv cpu_pc;
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 413f7de..c29c47f 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -56,7 +56,7 @@
 #define IS_USER(s) (s->user)
 #endif
 
-TCGv_ptr cpu_env;
+TCGv_env cpu_env;
 /* We reuse the same 64-bit temporaries for efficiency.  */
 static TCGv_i64 cpu_V0, cpu_V1, cpu_M0;
 static TCGv_i32 cpu_R[16];
diff --git a/target-arm/translate.h b/target-arm/translate.h
index 53ef971..82e3f6b 100644
--- a/target-arm/translate.h
+++ b/target-arm/translate.h
@@ -70,7 +70,7 @@ typedef struct DisasCompare {
 } DisasCompare;
 
 /* Share the TCG temporaries common between 32 and 64 bit modes.  */
-extern TCGv_ptr cpu_env;
+extern TCGv_env cpu_env;
 extern TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF;
 extern TCGv_i64 cpu_exclusive_addr;
 extern TCGv_i64 cpu_exclusive_val;
diff --git a/target-cris/translate.c b/target-cris/translate.c
index 2a283e0..a73176c 100644
--- a/target-cris/translate.c
+++ b/target-cris/translate.c
@@ -60,7 +60,7 @@
 #define CC_MASK_NZVC 0xf
 #define CC_MASK_RNZV 0x10e
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_R[16];
 static TCGv cpu_PR[16];
 static TCGv cc_x;
diff --git a/target-i386/translate.c b/target-i386/translate.c
index 9171929..53dee79 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -65,7 +65,7 @@
 //#define MACRO_TEST   1
 
 /* global register indexes */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_A0;
 static TCGv cpu_cc_dst, cpu_cc_src, cpu_cc_src2, cpu_cc_srcT;
 static TCGv_i32 cpu_cc_op;
diff --git a/target-lm32/translate.c b/target-lm32/translate.c
index 3877993..256a51f 100644
--- a/target-lm32/translate.c
+++ b/target-lm32/translate.c
@@ -44,7 +44,7 @@
 
 #define MEM_INDEX 0
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_R[32];
 static TCGv cpu_pc;
 static TCGv cpu_ie;
diff --git a/target-m68k/translate.c b/target-m68k/translate.c
index 085cb6a..7560c3a 100644
--- a/target-m68k/translate.c
+++ b/target-m68k/translate.c
@@ -50,7 +50,7 @@
 static TCGv_i32 cpu_halted;
 static TCGv_i32 cpu_exception_index;
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 
 static char cpu_reg_names[3*8*3 + 5*4];
 static TCGv cpu_dregs[8];
diff --git a/target-microblaze/translate.c b/target-microblaze/translate.c
index 296c4d7..f944965 100644
--- a/target-microblaze/translate.c
+++ b/target-microblaze/translate.c
@@ -46,7 +46,7 @@
             (((src) >> start) & ((1 << (end - start + 1)) - 1))
 
 static TCGv env_debug;
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_R[32];
 static TCGv cpu_SR[18];
 static TCGv env_imm;
diff --git a/target-mips/translate.c b/target-mips/translate.c
index a166569..12ed820 100644
--- a/target-mips/translate.c
+++ b/target-mips/translate.c
@@ -1355,7 +1355,7 @@ enum {
 };
 
 /* global register indices */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_gpr[32], cpu_PC;
 static TCGv cpu_HI[MIPS_DSP_ACC], cpu_LO[MIPS_DSP_ACC];
 static TCGv cpu_dspctrl, btarget, bcond;
diff --git a/target-moxie/translate.c b/target-moxie/translate.c
index bc860a5..a437e2a 100644
--- a/target-moxie/translate.c
+++ b/target-moxie/translate.c
@@ -56,7 +56,7 @@ enum {
 
 static TCGv cpu_pc;
 static TCGv cpu_gregs[16];
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cc_a, cc_b;
 
 #include "exec/gen-icount.h"
diff --git a/target-openrisc/translate.c b/target-openrisc/translate.c
index d25324e..5d0ab44 100644
--- a/target-openrisc/translate.c
+++ b/target-openrisc/translate.c
@@ -53,7 +53,7 @@ typedef struct DisasContext {
     uint32_t delayed_branch;
 } DisasContext;
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_sr;
 static TCGv cpu_R[32];
 static TCGv cpu_pc;
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index ecc85f0..e402ff9 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -49,7 +49,7 @@
 /* Code translation helpers                                                  */
 
 /* global register indexes */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static char cpu_reg_names[10*3 + 22*4 /* GPR */
     + 10*4 + 22*5 /* SPE GPRh */
     + 10*4 + 22*5 /* FPR */
diff --git a/target-s390x/translate.c b/target-s390x/translate.c
index 82e1165..c871ef2 100644
--- a/target-s390x/translate.c
+++ b/target-s390x/translate.c
@@ -37,7 +37,7 @@
 #include "exec/cpu_ldst.h"
 
 /* global register indexes */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 
 #include "exec/gen-icount.h"
 #include "exec/helper-proto.h"
diff --git a/target-sh4/translate.c b/target-sh4/translate.c
index e35d175..7c18968 100644
--- a/target-sh4/translate.c
+++ b/target-sh4/translate.c
@@ -61,7 +61,7 @@ enum {
 };
 
 /* global register indexes */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_gregs[24];
 static TCGv cpu_sr, cpu_sr_m, cpu_sr_q, cpu_sr_t;
 static TCGv cpu_pc, cpu_ssr, cpu_spc, cpu_gbr;
diff --git a/target-sparc/translate.c b/target-sparc/translate.c
index 00d61ee..58572c3 100644
--- a/target-sparc/translate.c
+++ b/target-sparc/translate.c
@@ -39,7 +39,8 @@
                          according to jump_pc[T2] */
 
 /* global register indexes */
-static TCGv_ptr cpu_env, cpu_regwptr;
+static TCGv_env cpu_env;
+static TCGv_ptr cpu_regwptr;
 static TCGv cpu_cc_src, cpu_cc_src2, cpu_cc_dst;
 static TCGv_i32 cpu_cc_op;
 static TCGv_i32 cpu_psr;
@@ -2291,7 +2292,7 @@ static void gen_fmovq(DisasContext *dc, DisasCompare *cmp, int rd, int rs)
 }
 
 #ifndef CONFIG_USER_ONLY
-static inline void gen_load_trap_state_at_tl(TCGv_ptr r_tsptr, TCGv_ptr cpu_env)
+static inline void gen_load_trap_state_at_tl(TCGv_ptr r_tsptr, TCGv_env cpu_env)
 {
     TCGv_i32 r_tl = tcg_temp_new_i32();
 
diff --git a/target-tilegx/translate.c b/target-tilegx/translate.c
index 7073aba..03918eb 100644
--- a/target-tilegx/translate.c
+++ b/target-tilegx/translate.c
@@ -32,7 +32,7 @@
 
 #define FMT64X                          "%016" PRIx64
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv cpu_pc;
 static TCGv cpu_regs[TILEGX_R_COUNT];
 
diff --git a/target-tricore/translate.c b/target-tricore/translate.c
index 6d7f553..d13e5c8 100644
--- a/target-tricore/translate.c
+++ b/target-tricore/translate.c
@@ -47,7 +47,7 @@ static TCGv cpu_PSW_SV;
 static TCGv cpu_PSW_AV;
 static TCGv cpu_PSW_SAV;
 /* CPU env */
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 
 #include "exec/gen-icount.h"
 
diff --git a/target-unicore32/translate.c b/target-unicore32/translate.c
index 1dd086d..39af3af 100644
--- a/target-unicore32/translate.c
+++ b/target-unicore32/translate.c
@@ -48,7 +48,7 @@ typedef struct DisasContext {
    conditional executions state has been updated.  */
 #define DISAS_SYSCALL 5
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv_i32 cpu_R[32];
 
 /* FIXME:  These should be removed.  */
diff --git a/target-xtensa/translate.c b/target-xtensa/translate.c
index fd03603..9894488 100644
--- a/target-xtensa/translate.c
+++ b/target-xtensa/translate.c
@@ -74,7 +74,7 @@ typedef struct DisasContext {
     unsigned cpenable;
 } DisasContext;
 
-static TCGv_ptr cpu_env;
+static TCGv_env cpu_env;
 static TCGv_i32 cpu_pc;
 static TCGv_i32 cpu_R[16];
 static TCGv_i32 cpu_FR[16];
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 4e20dc1..c446d3d 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -756,7 +756,6 @@ static inline void tcg_gen_exit_tb(uintptr_t val)
 void tcg_gen_goto_tb(unsigned idx);
 
 #if TARGET_LONG_BITS == 32
-#define TCGv TCGv_i32
 #define tcg_temp_new() tcg_temp_new_i32()
 #define tcg_global_reg_new tcg_global_reg_new_i32
 #define tcg_global_mem_new tcg_global_mem_new_i32
@@ -768,7 +767,6 @@ void tcg_gen_goto_tb(unsigned idx);
 #define tcg_gen_qemu_ld_tl tcg_gen_qemu_ld_i32
 #define tcg_gen_qemu_st_tl tcg_gen_qemu_st_i32
 #else
-#define TCGv TCGv_i64
 #define tcg_temp_new() tcg_temp_new_i64()
 #define tcg_global_reg_new tcg_global_reg_new_i64
 #define tcg_global_mem_new tcg_global_mem_new_i64
diff --git a/tcg/tcg.h b/tcg/tcg.h
index c45329a..b83f763 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -308,6 +308,14 @@ typedef tcg_target_ulong TCGArg;
 typedef struct TCGv_i32_d *TCGv_i32;
 typedef struct TCGv_i64_d *TCGv_i64;
 typedef struct TCGv_ptr_d *TCGv_ptr;
+typedef TCGv_ptr TCGv_env;
+#if TARGET_LONG_BITS == 32
+#define TCGv TCGv_i32
+#elif TARGET_LONG_BITS == 64
+#define TCGv TCGv_i64
+#else
+#error Unhandled TARGET_LONG_BITS value
+#endif
 
 static inline TCGv_i32 QEMU_ARTIFICIAL MAKE_TCGV_I32(intptr_t i)
 {
diff --git a/trace-events b/trace-events
index deb4d80..6fba6cc 100644
--- a/trace-events
+++ b/trace-events
@@ -143,7 +143,7 @@ cpu_out(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u"
 # balloon.c
 # Since requests are raised via monitor, not many tracepoints are needed.
 balloon_event(void *opaque, unsigned long addr) "opaque %p addr %lu"
-virtio_balloon_handle_output(const char *name, uint64_t gpa) "setion name: %s gpa: %"PRIx64""
+virtio_balloon_handle_output(const char *name, uint64_t gpa) "section name: %s gpa: %"PRIx64
 virtio_balloon_get_config(uint32_t num_pages, uint32_t acutal) "num_pages: %d acutal: %d"
 virtio_balloon_set_config(uint32_t acutal, uint32_t oldacutal) "acutal: %d oldacutal: %d"
 virtio_balloon_to_target(uint64_t target, uint32_t num_pages) "balloon target: %"PRIx64" num_pages: %d"
@@ -683,7 +683,7 @@ grlib_irqmp_writel_unknown(uint64_t addr, uint32_t value) "addr 0x%"PRIx64" valu
 # hw/char/grlib_apbuart.c
 grlib_apbuart_event(int event) "event:%d"
 grlib_apbuart_writel_unknown(uint64_t addr, uint32_t value) "addr 0x%"PRIx64" value 0x%x"
-grlib_apbuart_readl_unknown(uint64_t addr) "addr 0x%"PRIx64""
+grlib_apbuart_readl_unknown(uint64_t addr) "addr 0x%"PRIx64
 
 # hw/sparc/leon3.c
 leon3_set_irq(int intno) "Set CPU IRQ %d"
@@ -748,10 +748,10 @@ mptsas_config_sas_phy(void *dev, int address, int port, int phy_handle, int dev_
 megasas_init_firmware(uint64_t pa) "pa %" PRIx64 " "
 megasas_init_queue(uint64_t queue_pa, int queue_len, uint64_t head, uint64_t tail, uint32_t flags) "queue at %" PRIx64 " len %d head %" PRIx64 " tail %" PRIx64 " flags %x"
 megasas_initq_map_failed(int frame) "scmd %d: failed to map queue"
-megasas_initq_mapped(uint64_t pa) "queue already mapped at %" PRIx64 ""
+megasas_initq_mapped(uint64_t pa) "queue already mapped at %" PRIx64
 megasas_initq_mismatch(int queue_len, int fw_cmds) "queue size %d max fw cmds %d"
 megasas_qf_mapped(unsigned int index) "skip mapped frame %x"
-megasas_qf_new(unsigned int index, uint64_t frame) "frame %x addr %" PRIx64 ""
+megasas_qf_new(unsigned int index, uint64_t frame) "frame %x addr %" PRIx64
 megasas_qf_busy(unsigned long pa) "all frames busy for frame %lx"
 megasas_qf_enqueue(unsigned int index, unsigned int count, uint64_t context, unsigned int head, unsigned int tail, int busy) "frame %x count %d context %" PRIx64 " head %x tail %x busy %d"
 megasas_qf_update(unsigned int head, unsigned int tail, unsigned int busy) "head %x tail %x busy %d"
@@ -805,7 +805,7 @@ megasas_dcmd_pd_list_query(int cmd, int flags) "scmd %d: query flags %x"
 megasas_dcmd_reset_ld(int cmd, int target_id) "scmd %d: dev %d"
 megasas_dcmd_unsupported(int cmd, unsigned long size) "scmd %d: set properties len %ld"
 megasas_abort_frame(int cmd, int abort_cmd) "scmd %d: frame %x"
-megasas_abort_no_cmd(int cmd, uint64_t context) "scmd %d: no active command for frame context %" PRIx64 ""
+megasas_abort_no_cmd(int cmd, uint64_t context) "scmd %d: no active command for frame context %" PRIx64
 megasas_abort_invalid_context(int cmd, uint64_t context, int abort_cmd) "scmd %d: invalid frame context %" PRIx64 " for abort frame %x"
 megasas_reset(int fw_state) "firmware state %x"
 megasas_init(int sges, int cmds, const char *mode) "Using %d sges, %d cmds, %s mode"
@@ -898,7 +898,7 @@ milkymist_vgafb_memory_write(uint32_t addr, uint32_t value) "addr %08x value %08
 mipsnet_send(uint32_t size) "sending len=%u"
 mipsnet_receive(uint32_t size) "receiving len=%u"
 mipsnet_read(uint64_t addr, uint32_t val) "read addr=0x%" PRIx64 " val=0x%x"
-mipsnet_write(uint64_t addr, uint64_t val) "write addr=0x%" PRIx64 " val=0x%" PRIx64 ""
+mipsnet_write(uint64_t addr, uint64_t val) "write addr=0x%" PRIx64 " val=0x%" PRIx64
 mipsnet_irq(uint32_t isr, uint32_t intctl) "set irq to %d (%02x)"
 
 # hw/isa/pc87312.c
@@ -912,8 +912,8 @@ pc87312_info_serial(int n, uint32_t base, uint32_t irq) "id=%d, base 0x%x, irq %
 # hw/scsi/vmw_pvscsi.c
 pvscsi_ring_init_data(uint32_t txr_len_log2, uint32_t rxr_len_log2) "TX/RX rings logarithms set to %d/%d"
 pvscsi_ring_init_msg(uint32_t len_log2) "MSG ring logarithm set to %d"
-pvscsi_ring_flush_cmp(uint64_t filled_cmp_ptr) "new production counter of completion ring is 0x%"PRIx64""
-pvscsi_ring_flush_msg(uint64_t filled_cmp_ptr) "new production counter of message ring is 0x%"PRIx64""
+pvscsi_ring_flush_cmp(uint64_t filled_cmp_ptr) "new production counter of completion ring is 0x%"PRIx64
+pvscsi_ring_flush_msg(uint64_t filled_cmp_ptr) "new production counter of message ring is 0x%"PRIx64
 pvscsi_update_irq_level(bool raise, uint64_t mask, uint64_t status) "interrupt level set to %d (MASK: 0x%"PRIx64", STATUS: 0x%"PRIx64")"
 pvscsi_update_irq_msi(void) "sending MSI notification"
 pvscsi_cmp_ring_put(unsigned long addr) "got completion descriptor 0x%lx"
@@ -925,7 +925,7 @@ pvscsi_command_complete_not_found(uint32_t tag) "can't find request for tag 0x%x
 pvscsi_command_complete_data_run(void) "not all data required for command transferred"
 pvscsi_command_complete_sense_len(int len) "sense information length is %d bytes"
 pvscsi_convert_sglist(uint64_t context, unsigned long addr, uint32_t resid) "element: ctx: 0x%"PRIx64" addr: 0x%lx, len: %ul"
-pvscsi_process_req_descr(uint8_t cmd, uint64_t ctx) "SCSI cmd 0x%x, ctx: 0x%"PRIx64""
+pvscsi_process_req_descr(uint8_t cmd, uint64_t ctx) "SCSI cmd 0x%x, ctx: 0x%"PRIx64
 pvscsi_process_req_descr_unknown_device(void) "command directed to unknown device rejected"
 pvscsi_process_req_descr_invalid_dir(void) "command with invalid transfer direction rejected"
 pvscsi_process_io(unsigned long addr) "got descriptor 0x%lx"
@@ -933,15 +933,15 @@ pvscsi_on_cmd_noimpl(const char* cmd) "unimplemented command %s ignored"
 pvscsi_on_cmd_reset_dev(uint32_t tgt, int lun, void* dev) "PVSCSI_CMD_RESET_DEVICE[target %u lun %d (dev 0x%p)]"
 pvscsi_on_cmd_arrived(const char* cmd) "command %s arrived"
 pvscsi_on_cmd_abort(uint64_t ctx, uint32_t tgt) "command PVSCSI_CMD_ABORT_CMD for ctx 0x%"PRIx64", target %u"
-pvscsi_on_cmd_unknown(uint64_t cmd_id) "unknown command %"PRIx64""
+pvscsi_on_cmd_unknown(uint64_t cmd_id) "unknown command %"PRIx64
 pvscsi_on_cmd_unknown_data(uint32_t data) "data for unknown command 0x:%x"
-pvscsi_io_write(const char* cmd, uint64_t val) "%s write: %"PRIx64""
-pvscsi_io_write_unknown(unsigned long addr, unsigned sz, uint64_t val) "unknown write address: 0x%lx size: %u bytes value: 0x%"PRIx64""
-pvscsi_io_read(const char* cmd, uint64_t status) "%s read: 0x%"PRIx64""
+pvscsi_io_write(const char* cmd, uint64_t val) "%s write: %"PRIx64
+pvscsi_io_write_unknown(unsigned long addr, unsigned sz, uint64_t val) "unknown write address: 0x%lx size: %u bytes value: 0x%"PRIx64
+pvscsi_io_read(const char* cmd, uint64_t status) "%s read: 0x%"PRIx64
 pvscsi_io_read_unknown(unsigned long addr, unsigned sz) "unknown read address: 0x%lx size: %u bytes"
 pvscsi_init_msi_fail(int res) "failed to initialize MSI, error %d"
 pvscsi_state(const char* state) "starting %s ..."
-pvscsi_tx_rings_ppn(const char* label, uint64_t ppn) "%s page: %"PRIx64""
+pvscsi_tx_rings_ppn(const char* label, uint64_t ppn) "%s page: %"PRIx64
 pvscsi_tx_rings_num_pages(const char* label, uint32_t num) "Number of %s pages: %u"
 
 # xen-hvm.c
@@ -1077,10 +1077,10 @@ v9fs_rerror(uint16_t tag, uint8_t id, int err) "tag %d id %d err %d"
 v9fs_version(uint16_t tag, uint8_t id, int32_t msize, char* version) "tag %d id %d msize %d version %s"
 v9fs_version_return(uint16_t tag, uint8_t id, int32_t msize, char* version) "tag %d id %d msize %d version %s"
 v9fs_attach(uint16_t tag, uint8_t id, int32_t fid, int32_t afid, char* uname, char* aname) "tag %u id %u fid %d afid %d uname %s aname %s"
-v9fs_attach_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path) "tag %d id %d type %d version %d path %"PRId64""
+v9fs_attach_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path) "tag %d id %d type %d version %d path %"PRId64
 v9fs_stat(uint16_t tag, uint8_t id, int32_t fid) "tag %d id %d fid %d"
 v9fs_stat_return(uint16_t tag, uint8_t id, int32_t mode, int32_t atime, int32_t mtime, int64_t length) "tag %d id %d stat={mode %d atime %d mtime %d length %"PRId64"}"
-v9fs_getattr(uint16_t tag, uint8_t id, int32_t fid, uint64_t request_mask) "tag %d id %d fid %d request_mask %"PRIu64""
+v9fs_getattr(uint16_t tag, uint8_t id, int32_t fid, uint64_t request_mask) "tag %d id %d fid %d request_mask %"PRIu64
 v9fs_getattr_return(uint16_t tag, uint8_t id, uint64_t result_mask, uint32_t mode, uint32_t uid, uint32_t gid) "tag %d id %d getattr={result_mask %"PRId64" mode %u uid %u gid %u}"
 v9fs_walk(uint16_t tag, uint8_t id, int32_t fid, int32_t newfid, uint16_t nwnames) "tag %d id %d fid %d newfid %d nwnames %d"
 v9fs_walk_return(uint16_t tag, uint8_t id, uint16_t nwnames, void* qids) "tag %d id %d nwnames %d qids %p"
@@ -1106,14 +1106,14 @@ v9fs_remove(uint16_t tag, uint8_t id, int32_t fid) "tag %d id %d fid %d"
 v9fs_wstat(uint16_t tag, uint8_t id, int32_t fid, int32_t mode, int32_t atime, int32_t mtime) "tag %u id %u fid %d stat={mode %d atime %d mtime %d}"
 v9fs_mknod(uint16_t tag, uint8_t id, int32_t fid, int mode, int major, int minor) "tag %d id %d fid %d mode %d major %d minor %d"
 v9fs_mknod_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path) "tag %d id %d qid={type %d version %d path %"PRId64"}"
-v9fs_lock(uint16_t tag, uint8_t id, int32_t fid, uint8_t type, uint64_t start, uint64_t length) "tag %d id %d fid %d type %d start %"PRIu64" length %"PRIu64""
+v9fs_lock(uint16_t tag, uint8_t id, int32_t fid, uint8_t type, uint64_t start, uint64_t length) "tag %d id %d fid %d type %d start %"PRIu64" length %"PRIu64
 v9fs_lock_return(uint16_t tag, uint8_t id, int8_t status) "tag %d id %d status %d"
-v9fs_getlock(uint16_t tag, uint8_t id, int32_t fid, uint8_t type, uint64_t start, uint64_t length)"tag %d id %d fid %d type %d start %"PRIu64" length %"PRIu64""
+v9fs_getlock(uint16_t tag, uint8_t id, int32_t fid, uint8_t type, uint64_t start, uint64_t length)"tag %d id %d fid %d type %d start %"PRIu64" length %"PRIu64
 v9fs_getlock_return(uint16_t tag, uint8_t id, uint8_t type, uint64_t start, uint64_t length, uint32_t proc_id) "tag %d id %d type %d start %"PRIu64" length %"PRIu64" proc_id %u"
 v9fs_mkdir(uint16_t tag, uint8_t id, int32_t fid, char* name, int mode, uint32_t gid) "tag %u id %u fid %d name %s mode %d gid %u"
 v9fs_mkdir_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path, int err) "tag %u id %u qid={type %d version %d path %"PRId64"} err %d"
 v9fs_xattrwalk(uint16_t tag, uint8_t id, int32_t fid, int32_t newfid, char* name) "tag %d id %d fid %d newfid %d name %s"
-v9fs_xattrwalk_return(uint16_t tag, uint8_t id, int64_t size) "tag %d id %d size %"PRId64""
+v9fs_xattrwalk_return(uint16_t tag, uint8_t id, int64_t size) "tag %d id %d size %"PRId64
 v9fs_xattrcreate(uint16_t tag, uint8_t id, int32_t fid, char* name, int64_t size, int flags) "tag %d id %d fid %d name %s size %"PRId64" flags %d"
 v9fs_readlink(uint16_t tag, uint8_t id, int32_t fid) "tag %d id %d fid %d"
 v9fs_readlink_return(uint16_t tag, uint8_t id, char* target) "tag %d id %d name %s"
@@ -1121,12 +1121,12 @@ v9fs_readlink_return(uint16_t tag, uint8_t id, char* target) "tag %d id %d name
 # target-sparc/mmu_helper.c
 mmu_helper_dfault(uint64_t address, uint64_t context, int mmu_idx, uint32_t tl) "DFAULT at %"PRIx64" context %"PRIx64" mmu_idx=%d tl=%d"
 mmu_helper_dprot(uint64_t address, uint64_t context, int mmu_idx, uint32_t tl) "DPROT at %"PRIx64" context %"PRIx64" mmu_idx=%d tl=%d"
-mmu_helper_dmiss(uint64_t address, uint64_t context) "DMISS at %"PRIx64" context %"PRIx64""
-mmu_helper_tfault(uint64_t address, uint64_t context) "TFAULT at %"PRIx64" context %"PRIx64""
-mmu_helper_tmiss(uint64_t address, uint64_t context) "TMISS at %"PRIx64" context %"PRIx64""
-mmu_helper_get_phys_addr_code(uint32_t tl, int mmu_idx, uint64_t prim_context, uint64_t sec_context, uint64_t address) "tl=%d mmu_idx=%d primary context=%"PRIx64" secondary context=%"PRIx64" address=%"PRIx64""
-mmu_helper_get_phys_addr_data(uint32_t tl, int mmu_idx, uint64_t prim_context, uint64_t sec_context, uint64_t address) "tl=%d mmu_idx=%d primary context=%"PRIx64" secondary context=%"PRIx64" address=%"PRIx64""
-mmu_helper_mmu_fault(uint64_t address, uint64_t paddr, int mmu_idx, uint32_t tl, uint64_t prim_context, uint64_t sec_context) "Translate at %"PRIx64" -> %"PRIx64", mmu_idx=%d tl=%d primary context=%"PRIx64" secondary context=%"PRIx64""
+mmu_helper_dmiss(uint64_t address, uint64_t context) "DMISS at %"PRIx64" context %"PRIx64
+mmu_helper_tfault(uint64_t address, uint64_t context) "TFAULT at %"PRIx64" context %"PRIx64
+mmu_helper_tmiss(uint64_t address, uint64_t context) "TMISS at %"PRIx64" context %"PRIx64
+mmu_helper_get_phys_addr_code(uint32_t tl, int mmu_idx, uint64_t prim_context, uint64_t sec_context, uint64_t address) "tl=%d mmu_idx=%d primary context=%"PRIx64" secondary context=%"PRIx64" address=%"PRIx64
+mmu_helper_get_phys_addr_data(uint32_t tl, int mmu_idx, uint64_t prim_context, uint64_t sec_context, uint64_t address) "tl=%d mmu_idx=%d primary context=%"PRIx64" secondary context=%"PRIx64" address=%"PRIx64
+mmu_helper_mmu_fault(uint64_t address, uint64_t paddr, int mmu_idx, uint32_t tl, uint64_t prim_context, uint64_t sec_context) "Translate at %"PRIx64" -> %"PRIx64", mmu_idx=%d tl=%d primary context=%"PRIx64" secondary context=%"PRIx64
 
 # target-sparc/int64_helper.c
 int_helper_set_softint(uint32_t softint) "new %08x"
@@ -1281,7 +1281,7 @@ qemu_file_fclose(void) ""
 get_queued_page(const char *block_name, uint64_t tmp_offset, uint64_t ram_addr) "%s/%" PRIx64 " ram_addr=%" PRIx64
 get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, uint64_t ram_addr, int sent) "%s/%" PRIx64 " ram_addr=%" PRIx64 " (sent=%d)"
 migration_bitmap_sync_start(void) ""
-migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64""
+migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
 migration_throttle(void) ""
 ram_load_postcopy_loop(uint64_t addr, int flags) "@%" PRIx64 " %x"
 ram_postcopy_send_discard_bitmap(void) ""
@@ -1295,7 +1295,7 @@ qxl_create_guest_primary_rest(int qid, int32_t stride, uint32_t type, uint32_t f
 qxl_destroy_primary(int qid) "%d"
 qxl_enter_vga_mode(int qid) "%d"
 qxl_exit_vga_mode(int qid) "%d"
-qxl_hard_reset(int qid, int64_t loadvm) "%d loadvm=%"PRId64""
+qxl_hard_reset(int qid, int64_t loadvm) "%d loadvm=%"PRId64
 qxl_interface_async_complete_io(int qid, uint32_t current_async, void *cookie) "%d current=%d cookie=%p"
 qxl_interface_attach_worker(int qid) "%d"
 qxl_interface_get_init_info(int qid) "%d"
@@ -1622,6 +1622,8 @@ translate_block(void *tb, uintptr_t pc, uint8_t *tb_code) "tb:%p, pc:0x%"PRIxPTR
 # memory.c
 memory_region_ops_read(void *mr, uint64_t addr, uint64_t value, unsigned size) "mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
 memory_region_ops_write(void *mr, uint64_t addr, uint64_t value, unsigned size) "mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
+memory_region_subpage_read(void *mr, uint64_t offset, uint64_t value, unsigned size) "mr %p offset %#"PRIx64" value %#"PRIx64" size %u"
+memory_region_subpage_write(void *mr, uint64_t offset, uint64_t value, unsigned size) "mr %p offset %#"PRIx64" value %#"PRIx64" size %u"
 
 # qom/object.c
 object_dynamic_cast_assert(const char *type, const char *target, const char *file, int line, const char *func) "%s->%s (%s:%d:%s)"
@@ -1819,15 +1821,15 @@ qcrypto_tls_session_new(void *session, void *creds, const char *hostname, const
 vhost_user_event(const char *chr, int event) "chr: %s got event: %d"
 
 # linux-user/signal.c
-user_setup_frame(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64""
-user_setup_rt_frame(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64""
-user_do_rt_sigreturn(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64""
-user_do_sigreturn(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64""
+user_setup_frame(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64
+user_setup_rt_frame(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64
+user_do_rt_sigreturn(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64
+user_do_sigreturn(void *env, uint64_t frame_addr) "env=%p frame_addr=%"PRIx64
 user_force_sig(void *env, int target_sig, int host_sig) "env=%p signal %d (host %d)"
 user_handle_signal(void *env, int target_sig) "env=%p signal %d"
 user_host_signal(void *env, int host_sig, int target_sig) "env=%p signal %d (target %d("
 user_queue_signal(void *env, int target_sig) "env=%p signal %d"
-user_s390x_restore_sigregs(void *env, uint64_t sc_psw_addr, uint64_t env_psw_addr) "env=%p frame psw.addr %"PRIx64 " current psw.addr %"PRIx64""
+user_s390x_restore_sigregs(void *env, uint64_t sc_psw_addr, uint64_t env_psw_addr) "env=%p frame psw.addr %"PRIx64 " current psw.addr %"PRIx64
 
 # io/task.c
 qio_task_new(void *task, void *source, void *func, void *opaque) "Task new task=%p source=%p func=%p opaque=%p"
diff --git a/trace/control.h b/trace/control.h
index d5bc86e..f0fe535 100644
--- a/trace/control.h
+++ b/trace/control.h
@@ -1,7 +1,7 @@
 /*
  * Interface for configuring and controlling the state of tracing events.
  *
- * Copyright (C) 2011-2014 Lluís Vilanova <vilanova@ac.upc.edu>
+ * Copyright (C) 2011-2016 Lluís Vilanova <vilanova@ac.upc.edu>
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
@@ -11,6 +11,7 @@
 #define TRACE__CONTROL_H
 
 #include "qemu-common.h"
+#include "qemu/typedefs.h"
 #include "trace/generated-events.h"
 
 
diff --git a/vl.c b/vl.c
index b87e292..adeddd9 100644
--- a/vl.c
+++ b/vl.c
@@ -4081,6 +4081,9 @@ int main(int argc, char **argv, char **envp)
         exit(0);
     }
 
+    if (!trace_init_backends()) {
+        exit(1);
+    }
     trace_init_file(trace_file);
 
     /* Open the logfile at this point and set the log mask if necessary.
@@ -4101,10 +4104,6 @@ int main(int argc, char **argv, char **envp)
         qemu_set_log(0);
     }
 
-    if (!trace_init_backends()) {
-        exit(1);
-    }
-
     /* If no data_dir is specified then try to find it relative to the
        executable path.  */
     if (data_dir_idx < ARRAY_SIZE(data_dir)) {