sdl2/opengl: add opengl context and scanout support

This allows virtio-gpu to render in 3d mode.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>

MAINTAINERS

@@ -941,6 +941,13 @@ M: Jiri Pirko <jiri@resnulli.us>
 S: Maintained
 F: hw/net/rocker/
 
+NVDIMM
+M: Xiao Guangrong <guangrong.xiao@linux.intel.com>
+S: Maintained
+F: hw/acpi/nvdimm.c
+F: hw/mem/nvdimm.c
+F: include/hw/mem/nvdimm.h
+
 Subsystems
 ----------
 Audio
@@ -1243,6 +1250,13 @@ S: Odd fixes
 F: util/buffer.c
 F: include/qemu/buffer.h
 
+I/O Channels
+M: Daniel P. Berrange <berrange@redhat.com>
+S: Maintained
+F: io/
+F: include/io/
+F: tests/test-io-*
+
 Usermode Emulation
 ------------------
 Overall
@@ -1483,6 +1497,7 @@ M: Denis V. Lunev <den@openvz.org>
 L: qemu-block@nongnu.org
 S: Supported
 F: block/parallels.c
+F: docs/specs/parallels.txt
 
 qed
 M: Stefan Hajnoczi <stefanha@redhat.com>

Makefile

@@ -159,6 +159,7 @@ dummy := $(call unnest-vars,, \
                 crypto-obj-y \
                 crypto-aes-obj-y \
                 qom-obj-y \
+                io-obj-y \
                 common-obj-y \
                 common-obj-m)
 
@@ -178,6 +179,7 @@ SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))
 
 $(SOFTMMU_SUBDIR_RULES): $(block-obj-y)
 $(SOFTMMU_SUBDIR_RULES): $(crypto-obj-y)
+$(SOFTMMU_SUBDIR_RULES): $(io-obj-y)
 $(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
 
 subdir-%:
@@ -269,7 +271,8 @@ $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 
 qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
                $(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
-               $(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json
+               $(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json \
+               $(SRC_PATH)/qapi/crypto.json
 
 qapi-types.c qapi-types.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)

Makefile.objs

@@ -28,6 +28,11 @@ crypto-aes-obj-y = crypto/
 
 qom-obj-y = qom/
 
+#######################################################################
+# io-obj-y is code used by both qemu system emulation and qemu-img
+
+io-obj-y = io/
+
 ######################################################################
 # Target independent part of system emulation. The long term path is to
 # suppress *all* target specific code in case of system emulation, i.e. a

Makefile.target

@@ -176,6 +176,7 @@ dummy := $(call unnest-vars,.., \
                crypto-obj-y \
                crypto-aes-obj-y \
                qom-obj-y \
+               io-obj-y \
                common-obj-y \
                common-obj-m)
 target-obj-y := $(target-obj-y-save)
@@ -185,6 +186,7 @@ all-obj-y += $(qom-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
 all-obj-$(CONFIG_USER_ONLY) += $(crypto-aes-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(crypto-obj-y)
+all-obj-$(CONFIG_SOFTMMU) += $(io-obj-y)
 
 $(QEMU_PROG_BUILD): config-devices.mak
 

VERSION

@@ -1 +1 @@
-2.5.0
+2.5.50

audio/coreaudio.c

@@ -32,6 +32,10 @@
 #define AUDIO_CAP "coreaudio"
 #include "audio_int.h"
 
+#ifndef MAC_OS_X_VERSION_10_6
+#define MAC_OS_X_VERSION_10_6 1060
+#endif
+
 static int isAtexit;
 
 typedef struct {
@@ -45,11 +49,233 @@ typedef struct coreaudioVoiceOut {
     AudioDeviceID outputDeviceID;
     UInt32 audioDevicePropertyBufferFrameSize;
     AudioStreamBasicDescription outputStreamBasicDescription;
+    AudioDeviceIOProcID ioprocid;
     int live;
     int decr;
     int rpos;
 } coreaudioVoiceOut;
 
+#if MAC_OS_X_VERSION_MAX_ALLOWED >= MAC_OS_X_VERSION_10_6
+/* The APIs used here only become available from 10.6 */
+
+static OSStatus coreaudio_get_voice(AudioDeviceID *id)
+{
+    UInt32 size = sizeof(*id);
+    AudioObjectPropertyAddress addr = {
+        kAudioHardwarePropertyDefaultOutputDevice,
+        kAudioObjectPropertyScopeGlobal,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectGetPropertyData(kAudioObjectSystemObject,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      &size,
+                                      id);
+}
+
+static OSStatus coreaudio_get_framesizerange(AudioDeviceID id,
+                                             AudioValueRange *framerange)
+{
+    UInt32 size = sizeof(*framerange);
+    AudioObjectPropertyAddress addr = {
+        kAudioDevicePropertyBufferFrameSizeRange,
+        kAudioDevicePropertyScopeOutput,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectGetPropertyData(id,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      &size,
+                                      framerange);
+}
+
+static OSStatus coreaudio_get_framesize(AudioDeviceID id, UInt32 *framesize)
+{
+    UInt32 size = sizeof(*framesize);
+    AudioObjectPropertyAddress addr = {
+        kAudioDevicePropertyBufferFrameSize,
+        kAudioDevicePropertyScopeOutput,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectGetPropertyData(id,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      &size,
+                                      framesize);
+}
+
+static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize)
+{
+    UInt32 size = sizeof(*framesize);
+    AudioObjectPropertyAddress addr = {
+        kAudioDevicePropertyBufferFrameSize,
+        kAudioDevicePropertyScopeOutput,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectSetPropertyData(id,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      size,
+                                      framesize);
+}
+
+static OSStatus coreaudio_get_streamformat(AudioDeviceID id,
+                                           AudioStreamBasicDescription *d)
+{
+    UInt32 size = sizeof(*d);
+    AudioObjectPropertyAddress addr = {
+        kAudioDevicePropertyStreamFormat,
+        kAudioDevicePropertyScopeOutput,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectGetPropertyData(id,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      &size,
+                                      d);
+}
+
+static OSStatus coreaudio_set_streamformat(AudioDeviceID id,
+                                           AudioStreamBasicDescription *d)
+{
+    UInt32 size = sizeof(*d);
+    AudioObjectPropertyAddress addr = {
+        kAudioDevicePropertyStreamFormat,
+        kAudioDevicePropertyScopeOutput,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectSetPropertyData(id,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      size,
+                                      d);
+}
+
+static OSStatus coreaudio_get_isrunning(AudioDeviceID id, UInt32 *result)
+{
+    UInt32 size = sizeof(*result);
+    AudioObjectPropertyAddress addr = {
+        kAudioDevicePropertyDeviceIsRunning,
+        kAudioDevicePropertyScopeOutput,
+        kAudioObjectPropertyElementMaster
+    };
+
+    return AudioObjectGetPropertyData(id,
+                                      &addr,
+                                      0,
+                                      NULL,
+                                      &size,
+                                      result);
+}
+#else
+/* Legacy versions of functions using deprecated APIs */
+
+static OSStatus coreaudio_get_voice(AudioDeviceID *id)
+{
+    UInt32 size = sizeof(*id);
+
+    return AudioHardwareGetProperty(
+        kAudioHardwarePropertyDefaultOutputDevice,
+        &size,
+        id);
+}
+
+static OSStatus coreaudio_get_framesizerange(AudioDeviceID id,
+                                             AudioValueRange *framerange)
+{
+    UInt32 size = sizeof(*framerange);
+
+    return AudioDeviceGetProperty(
+        id,
+        0,
+        0,
+        kAudioDevicePropertyBufferFrameSizeRange,
+        &size,
+        framerange);
+}
+
+static OSStatus coreaudio_get_framesize(AudioDeviceID id, UInt32 *framesize)
+{
+    UInt32 size = sizeof(*framesize);
+
+    return AudioDeviceGetProperty(
+        id,
+        0,
+        false,
+        kAudioDevicePropertyBufferFrameSize,
+        &size,
+        framesize);
+}
+
+static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize)
+{
+    UInt32 size = sizeof(*framesize);
+
+    return AudioDeviceSetProperty(
+        id,
+        NULL,
+        0,
+        false,
+        kAudioDevicePropertyBufferFrameSize,
+        size,
+        framesize);
+}
+
+static OSStatus coreaudio_get_streamformat(AudioDeviceID id,
+                                           AudioStreamBasicDescription *d)
+{
+    UInt32 size = sizeof(*d);
+
+    return AudioDeviceGetProperty(
+        id,
+        0,
+        false,
+        kAudioDevicePropertyStreamFormat,
+        &size,
+        d);
+}
+
+static OSStatus coreaudio_set_streamformat(AudioDeviceID id,
+                                           AudioStreamBasicDescription *d)
+{
+    UInt32 size = sizeof(*d);
+
+    return AudioDeviceSetProperty(
+        id,
+        0,
+        0,
+        0,
+        kAudioDevicePropertyStreamFormat,
+        size,
+        d);
+}
+
+static OSStatus coreaudio_get_isrunning(AudioDeviceID id, UInt32 *result)
+{
+    UInt32 size = sizeof(*result);
+
+    return AudioDeviceGetProperty(
+        id,
+        0,
+        0,
+        kAudioDevicePropertyDeviceIsRunning,
+        &size,
+        result);
+}
+#endif
+
 static void coreaudio_logstatus (OSStatus status)
 {
     const char *str = "BUG";
@@ -144,10 +370,7 @@ static inline UInt32 isPlaying (AudioDeviceID outputDeviceID)
 {
     OSStatus status;
     UInt32 result = 0;
-    UInt32 propertySize = sizeof(outputDeviceID);
-    status = AudioDeviceGetProperty(
-        outputDeviceID, 0, 0,
-        kAudioDevicePropertyDeviceIsRunning, &propertySize, &result);
+    status = coreaudio_get_isrunning(outputDeviceID, &result);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr(status,
                          "Could not determine whether Device is playing\n");
@@ -288,7 +511,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 {
     OSStatus status;
     coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
-    UInt32 propertySize;
     int err;
     const char *typ = "playback";
     AudioValueRange frameRange;
@@ -303,12 +525,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 
     audio_pcm_init_info (&hw->info, as);
 
-    /* open default output device */
-    propertySize = sizeof(core->outputDeviceID);
-    status = AudioHardwareGetProperty(
-        kAudioHardwarePropertyDefaultOutputDevice,
-        &propertySize,
-        &core->outputDeviceID);
+    status = coreaudio_get_voice(&core->outputDeviceID);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
                            "Could not get default output Device\n");
@@ -320,13 +537,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* get minimum and maximum buffer frame sizes */
-    propertySize = sizeof(frameRange);
-    status = AudioDeviceGetProperty(
-        core->outputDeviceID,
-        0,
-        0,
-        kAudioDevicePropertyBufferFrameSizeRange,
-        &propertySize,
+    status = coreaudio_get_framesizerange(core->outputDeviceID,
                                           &frameRange);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
@@ -347,14 +558,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* set Buffer Frame Size */
-    propertySize = sizeof(core->audioDevicePropertyBufferFrameSize);
-    status = AudioDeviceSetProperty(
-        core->outputDeviceID,
-        NULL,
-        0,
-        false,
-        kAudioDevicePropertyBufferFrameSize,
-        propertySize,
+    status = coreaudio_set_framesize(core->outputDeviceID,
                                      &core->audioDevicePropertyBufferFrameSize);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
@@ -364,13 +568,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* get Buffer Frame Size */
-    propertySize = sizeof(core->audioDevicePropertyBufferFrameSize);
-    status = AudioDeviceGetProperty(
-        core->outputDeviceID,
-        0,
-        false,
-        kAudioDevicePropertyBufferFrameSize,
-        &propertySize,
+    status = coreaudio_get_framesize(core->outputDeviceID,
                                      &core->audioDevicePropertyBufferFrameSize);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
@@ -380,13 +578,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     hw->samples = conf->nbuffers * core->audioDevicePropertyBufferFrameSize;
 
     /* get StreamFormat */
-    propertySize = sizeof(core->outputStreamBasicDescription);
-    status = AudioDeviceGetProperty(
-        core->outputDeviceID,
-        0,
-        false,
-        kAudioDevicePropertyStreamFormat,
-        &propertySize,
+    status = coreaudio_get_streamformat(core->outputDeviceID,
                                         &core->outputStreamBasicDescription);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
@@ -397,14 +589,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 
     /* set Samplerate */
     core->outputStreamBasicDescription.mSampleRate = (Float64) as->freq;
-    propertySize = sizeof(core->outputStreamBasicDescription);
-    status = AudioDeviceSetProperty(
-        core->outputDeviceID,
-        0,
-        0,
-        0,
-        kAudioDevicePropertyStreamFormat,
-        propertySize,
+    status = coreaudio_set_streamformat(core->outputDeviceID,
                                         &core->outputStreamBasicDescription);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ, "Could not set samplerate %d\n",
@@ -414,8 +599,12 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* set Callback */
-    status = AudioDeviceAddIOProc(core->outputDeviceID, audioDeviceIOProc, hw);
-    if (status != kAudioHardwareNoError) {
+    core->ioprocid = NULL;
+    status = AudioDeviceCreateIOProcID(core->outputDeviceID,
+                                       audioDeviceIOProc,
+                                       hw,
+                                       &core->ioprocid);
+    if (status != kAudioHardwareNoError || core->ioprocid == NULL) {
         coreaudio_logerr2 (status, typ, "Could not set IOProc\n");
         core->outputDeviceID = kAudioDeviceUnknown;
         return -1;
@@ -423,10 +612,10 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 
     /* start Playback */
     if (!isPlaying(core->outputDeviceID)) {
-        status = AudioDeviceStart(core->outputDeviceID, audioDeviceIOProc);
+        status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
         if (status != kAudioHardwareNoError) {
             coreaudio_logerr2 (status, typ, "Could not start playback\n");
-            AudioDeviceRemoveIOProc(core->outputDeviceID, audioDeviceIOProc);
+            AudioDeviceDestroyIOProcID(core->outputDeviceID, core->ioprocid);
             core->outputDeviceID = kAudioDeviceUnknown;
             return -1;
         }
@@ -444,15 +633,15 @@ static void coreaudio_fini_out (HWVoiceOut *hw)
     if (!isAtexit) {
         /* stop playback */
         if (isPlaying(core->outputDeviceID)) {
-            status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
+            status = AudioDeviceStop(core->outputDeviceID, core->ioprocid);
             if (status != kAudioHardwareNoError) {
                 coreaudio_logerr (status, "Could not stop playback\n");
             }
         }
 
         /* remove callback */
-        status = AudioDeviceRemoveIOProc(core->outputDeviceID,
-                                         audioDeviceIOProc);
+        status = AudioDeviceDestroyIOProcID(core->outputDeviceID,
+                                            core->ioprocid);
         if (status != kAudioHardwareNoError) {
             coreaudio_logerr (status, "Could not remove IOProc\n");
         }
@@ -475,7 +664,7 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
     case VOICE_ENABLE:
         /* start playback */
         if (!isPlaying(core->outputDeviceID)) {
-            status = AudioDeviceStart(core->outputDeviceID, audioDeviceIOProc);
+            status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
             if (status != kAudioHardwareNoError) {
                 coreaudio_logerr (status, "Could not resume playback\n");
             }
@@ -486,7 +675,8 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
         /* stop playback */
         if (!isAtexit) {
             if (isPlaying(core->outputDeviceID)) {
-                status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
+                status = AudioDeviceStop(core->outputDeviceID,
+                                         core->ioprocid);
                 if (status != kAudioHardwareNoError) {
                     coreaudio_logerr (status, "Could not pause playback\n");
                 }

block.c

@@ -29,6 +29,7 @@
 #include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qjson.h"
 #include "sysemu/block-backend.h"
 #include "sysemu/sysemu.h"
@@ -623,6 +624,20 @@ static int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
     return 0;
 }
 
+/**
+ * Combines a QDict of new block driver @options with any missing options taken
+ * from @old_options, so that leaving out an option defaults to its old value.
+ */
+static void bdrv_join_options(BlockDriverState *bs, QDict *options,
+                              QDict *old_options)
+{
+    if (bs->drv && bs->drv->bdrv_join_options) {
+        bs->drv->bdrv_join_options(options, old_options);
+    } else {
+        qdict_join(options, old_options, false);
+    }
+}
+
 /**
  * Set open flags for a given discard mode
  *
@@ -681,60 +696,81 @@ static int bdrv_temp_snapshot_flags(int flags)
 }
 
 /*
- * Returns the flags that bs->file should get if a protocol driver is expected,
- * based on the given flags for the parent BDS
+ * Returns the options and flags that bs->file should get if a protocol driver
+ * is expected, based on the given options and flags for the parent BDS
  */
-static int bdrv_inherited_flags(int flags)
+static void bdrv_inherited_options(int *child_flags, QDict *child_options,
+                                   int parent_flags, QDict *parent_options)
 {
+    int flags = parent_flags;
+
     /* Enable protocol handling, disable format probing for bs->file */
     flags |= BDRV_O_PROTOCOL;
 
+    /* If the cache mode isn't explicitly set, inherit direct and no-flush from
+     * the parent. */
+    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_DIRECT);
+    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_NO_FLUSH);
+
     /* Our block drivers take care to send flushes and respect unmap policy,
-     * so we can enable both unconditionally on lower layers. */
-    flags |= BDRV_O_CACHE_WB | BDRV_O_UNMAP;
+     * so we can default to enable both on lower layers regardless of the
+     * corresponding parent options. */
+    qdict_set_default_str(child_options, BDRV_OPT_CACHE_WB, "on");
+    flags |= BDRV_O_UNMAP;
 
     /* Clear flags that only apply to the top layer */
     flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ);
 
-    return flags;
+    *child_flags = flags;
 }
 
 const BdrvChildRole child_file = {
-    .inherit_flags = bdrv_inherited_flags,
+    .inherit_options = bdrv_inherited_options,
 };
 
 /*
- * Returns the flags that bs->file should get if the use of formats (and not
- * only protocols) is permitted for it, based on the given flags for the parent
- * BDS
+ * Returns the options and flags that bs->file should get if the use of formats
+ * (and not only protocols) is permitted for it, based on the given options and
+ * flags for the parent BDS
  */
-static int bdrv_inherited_fmt_flags(int parent_flags)
+static void bdrv_inherited_fmt_options(int *child_flags, QDict *child_options,
+                                       int parent_flags, QDict *parent_options)
 {
-    int flags = child_file.inherit_flags(parent_flags);
-    return flags & ~BDRV_O_PROTOCOL;
+    child_file.inherit_options(child_flags, child_options,
+                               parent_flags, parent_options);
+
+    *child_flags &= ~BDRV_O_PROTOCOL;
 }
 
 const BdrvChildRole child_format = {
-    .inherit_flags = bdrv_inherited_fmt_flags,
+    .inherit_options = bdrv_inherited_fmt_options,
 };
 
 /*
- * Returns the flags that bs->backing should get, based on the given flags
- * for the parent BDS
+ * Returns the options and flags that bs->backing should get, based on the
+ * given options and flags for the parent BDS
  */
-static int bdrv_backing_flags(int flags)
+static void bdrv_backing_options(int *child_flags, QDict *child_options,
+                                 int parent_flags, QDict *parent_options)
 {
+    int flags = parent_flags;
+
+    /* The cache mode is inherited unmodified for backing files */
+    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_WB);
+    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_DIRECT);
+    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_NO_FLUSH);
+
     /* backing files always opened read-only */
     flags &= ~(BDRV_O_RDWR | BDRV_O_COPY_ON_READ);
 
     /* snapshot=on is handled on the top layer */
     flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_TEMPORARY);
 
-    return flags;
+    *child_flags = flags;
 }
 
 static const BdrvChildRole child_backing = {
-    .inherit_flags = bdrv_backing_flags,
+    .inherit_options = bdrv_backing_options,
 };
 
 static int bdrv_open_flags(BlockDriverState *bs, int flags)
@@ -757,6 +793,42 @@ static int bdrv_open_flags(BlockDriverState *bs, int flags)
     return open_flags;
 }
 
+static void update_flags_from_options(int *flags, QemuOpts *opts)
+{
+    *flags &= ~BDRV_O_CACHE_MASK;
+
+    assert(qemu_opt_find(opts, BDRV_OPT_CACHE_WB));
+    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, false)) {
+        *flags |= BDRV_O_CACHE_WB;
+    }
+
+    assert(qemu_opt_find(opts, BDRV_OPT_CACHE_NO_FLUSH));
+    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
+        *flags |= BDRV_O_NO_FLUSH;
+    }
+
+    assert(qemu_opt_find(opts, BDRV_OPT_CACHE_DIRECT));
+    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_DIRECT, false)) {
+        *flags |= BDRV_O_NOCACHE;
+    }
+}
+
+static void update_options_from_flags(QDict *options, int flags)
+{
+    if (!qdict_haskey(options, BDRV_OPT_CACHE_WB)) {
+        qdict_put(options, BDRV_OPT_CACHE_WB,
+                  qbool_from_bool(flags & BDRV_O_CACHE_WB));
+    }
+    if (!qdict_haskey(options, BDRV_OPT_CACHE_DIRECT)) {
+        qdict_put(options, BDRV_OPT_CACHE_DIRECT,
+                  qbool_from_bool(flags & BDRV_O_NOCACHE));
+    }
+    if (!qdict_haskey(options, BDRV_OPT_CACHE_NO_FLUSH)) {
+        qdict_put(options, BDRV_OPT_CACHE_NO_FLUSH,
+                  qbool_from_bool(flags & BDRV_O_NO_FLUSH));
+    }
+}
+
 static void bdrv_assign_node_name(BlockDriverState *bs,
                                   const char *node_name,
                                   Error **errp)
@@ -803,6 +875,26 @@ static QemuOptsList bdrv_runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "Node name of the block device node",
         },
+        {
+            .name = "driver",
+            .type = QEMU_OPT_STRING,
+            .help = "Block driver to use for the node",
+        },
+        {
+            .name = BDRV_OPT_CACHE_WB,
+            .type = QEMU_OPT_BOOL,
+            .help = "Enable writeback mode",
+        },
+        {
+            .name = BDRV_OPT_CACHE_DIRECT,
+            .type = QEMU_OPT_BOOL,
+            .help = "Bypass software writeback cache on the host",
+        },
+        {
+            .name = BDRV_OPT_CACHE_NO_FLUSH,
+            .type = QEMU_OPT_BOOL,
+            .help = "Ignore flush requests",
+        },
         { /* end of list */ }
     },
 };
@@ -813,18 +905,31 @@ static QemuOptsList bdrv_runtime_opts = {
  * Removes all processed options from *options.
  */
 static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
-    QDict *options, int flags, BlockDriver *drv, Error **errp)
+                            QDict *options, int flags, Error **errp)
 {
     int ret, open_flags;
     const char *filename;
+    const char *driver_name = NULL;
     const char *node_name = NULL;
     QemuOpts *opts;
+    BlockDriver *drv;
     Error *local_err = NULL;
 
-    assert(drv != NULL);
     assert(bs->file == NULL);
     assert(options != NULL && bs->options != options);
 
+    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fail_opts;
+    }
+
+    driver_name = qemu_opt_get(opts, "driver");
+    drv = bdrv_find_format(driver_name);
+    assert(drv != NULL);
+
     if (file != NULL) {
         filename = file->bs->filename;
     } else {
@@ -834,19 +939,12 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
     if (drv->bdrv_needs_filename && !filename) {
         error_setg(errp, "The '%s' block driver requires a file name",
                    drv->format_name);
-        return -EINVAL;
-    }
-
-    trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
-
-    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
         ret = -EINVAL;
         goto fail_opts;
     }
 
+    trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
+
     node_name = qemu_opt_get(opts, "node-name");
     bdrv_assign_node_name(bs, node_name, &local_err);
     if (local_err) {
@@ -891,7 +989,9 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
     bs->drv = drv;
     bs->opaque = g_malloc0(drv->instance_size);
 
-    bs->enable_write_cache = !!(flags & BDRV_O_CACHE_WB);
+    /* Apply cache mode options */
+    update_flags_from_options(&bs->open_flags, opts);
+    bdrv_set_enable_write_cache(bs, bs->open_flags & BDRV_O_CACHE_WB);
 
     /* Open the image, either directly or using a protocol */
     if (drv->bdrv_file_open) {
@@ -984,37 +1084,45 @@ static QDict *parse_json_filename(const char *filename, Error **errp)
     return options;
 }
 
+static void parse_json_protocol(QDict *options, const char **pfilename,
+                                Error **errp)
+{
+    QDict *json_options;
+    Error *local_err = NULL;
+
+    /* Parse json: pseudo-protocol */
+    if (!*pfilename || !g_str_has_prefix(*pfilename, "json:")) {
+        return;
+    }
+
+    json_options = parse_json_filename(*pfilename, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    /* Options given in the filename have lower priority than options
+     * specified directly */
+    qdict_join(options, json_options, false);
+    QDECREF(json_options);
+    *pfilename = NULL;
+}
+
 /*
  * Fills in default options for opening images and converts the legacy
  * filename/flags pair to option QDict entries.
  * The BDRV_O_PROTOCOL flag in *flags will be set or cleared accordingly if a
  * block driver has been specified explicitly.
  */
-static int bdrv_fill_options(QDict **options, const char **pfilename,
+static int bdrv_fill_options(QDict **options, const char *filename,
                              int *flags, Error **errp)
 {
-    const char *filename = *pfilename;
     const char *drvname;
     bool protocol = *flags & BDRV_O_PROTOCOL;
     bool parse_filename = false;
     BlockDriver *drv = NULL;
     Error *local_err = NULL;
 
-    /* Parse json: pseudo-protocol */
-    if (filename && g_str_has_prefix(filename, "json:")) {
-        QDict *json_options = parse_json_filename(filename, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return -EINVAL;
-        }
-
-        /* Options given in the filename have lower priority than options
-         * specified directly */
-        qdict_join(*options, json_options, false);
-        QDECREF(json_options);
-        *pfilename = filename = NULL;
-    }
-
     drvname = qdict_get_try_str(*options, "driver");
     if (drvname) {
         drv = bdrv_find_format(drvname);
@@ -1033,6 +1141,9 @@ static int bdrv_fill_options(QDict **options, const char **pfilename,
         *flags &= ~BDRV_O_PROTOCOL;
     }
 
+    /* Translate cache options from flags into options */
+    update_options_from_flags(*options, *flags);
+
     /* Fetch the file name from the options QDict if necessary */
     if (protocol && filename) {
         if (!qdict_haskey(*options, "filename")) {
@@ -1087,11 +1198,13 @@ static int bdrv_fill_options(QDict **options, const char **pfilename,
 
 static BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
                                     BlockDriverState *child_bs,
+                                    const char *child_name,
                                     const BdrvChildRole *child_role)
 {
     BdrvChild *child = g_new(BdrvChild, 1);
     *child = (BdrvChild) {
         .bs     = child_bs,
+        .name   = g_strdup(child_name),
         .role   = child_role,
     };
 
@@ -1105,6 +1218,7 @@ static void bdrv_detach_child(BdrvChild *child)
 {
     QLIST_REMOVE(child, next);
     QLIST_REMOVE(child, next_parent);
+    g_free(child->name);
     g_free(child);
 }
 
@@ -1151,7 +1265,7 @@ void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
         bs->backing = NULL;
         goto out;
     }
-    bs->backing = bdrv_attach_child(bs, backing_hd, &child_backing);
+    bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_backing);
     bs->open_flags &= ~BDRV_O_NO_BACKING;
     pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_hd->filename);
     pstrcpy(bs->backing_format, sizeof(bs->backing_format),
@@ -1168,30 +1282,43 @@ out:
 /*
  * Opens the backing file for a BlockDriverState if not yet open
  *
- * options is a QDict of options to pass to the block drivers, or NULL for an
- * empty set of options. The reference to the QDict is transferred to this
- * function (even on failure), so if the caller intends to reuse the dictionary,
- * it needs to use QINCREF() before calling bdrv_file_open.
+ * bdref_key specifies the key for the image's BlockdevRef in the options QDict.
+ * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
+ * itself, all options starting with "${bdref_key}." are considered part of the
+ * BlockdevRef.
+ *
+ * TODO Can this be unified with bdrv_open_image()?
  */
-int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
+int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
+                           const char *bdref_key, Error **errp)
 {
     char *backing_filename = g_malloc0(PATH_MAX);
+    char *bdref_key_dot;
+    const char *reference = NULL;
     int ret = 0;
     BlockDriverState *backing_hd;
+    QDict *options;
+    QDict *tmp_parent_options = NULL;
     Error *local_err = NULL;
 
     if (bs->backing != NULL) {
-        QDECREF(options);
         goto free_exit;
     }
 
     /* NULL means an empty set of options */
-    if (options == NULL) {
-        options = qdict_new();
+    if (parent_options == NULL) {
+        tmp_parent_options = qdict_new();
+        parent_options = tmp_parent_options;
     }
 
     bs->open_flags &= ~BDRV_O_NO_BACKING;
-    if (qdict_haskey(options, "file.filename")) {
+
+    bdref_key_dot = g_strdup_printf("%s.", bdref_key);
+    qdict_extract_subqdict(parent_options, &options, bdref_key_dot);
+    g_free(bdref_key_dot);
+
+    reference = qdict_get_try_str(parent_options, bdref_key);
+    if (reference || qdict_haskey(options, "file.filename")) {
         backing_filename[0] = '\0';
     } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
         QDECREF(options);
@@ -1214,19 +1341,16 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
         goto free_exit;
     }
 
-    backing_hd = bdrv_new();
-
     if (bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) {
         qdict_put(options, "driver", qstring_from_str(bs->backing_format));
     }
 
-    assert(bs->backing == NULL);
+    backing_hd = NULL;
     ret = bdrv_open_inherit(&backing_hd,
                             *backing_filename ? backing_filename : NULL,
-                            NULL, options, 0, bs, &child_backing, &local_err);
+                            reference, options, 0, bs, &child_backing,
+                            &local_err);
     if (ret < 0) {
-        bdrv_unref(backing_hd);
-        backing_hd = NULL;
         bs->open_flags |= BDRV_O_NO_BACKING;
         error_setg(errp, "Could not open backing file: %s",
                    error_get_pretty(local_err));
@@ -1239,8 +1363,11 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
     bdrv_set_backing_hd(bs, backing_hd);
     bdrv_unref(backing_hd);
 
+    qdict_del(parent_options, bdref_key);
+
 free_exit:
     g_free(backing_filename);
+    QDECREF(tmp_parent_options);
     return ret;
 }
 
@@ -1294,7 +1421,7 @@ BdrvChild *bdrv_open_child(const char *filename,
         goto done;
     }
 
-    c = bdrv_attach_child(parent, bs, child_role);
+    c = bdrv_attach_child(parent, bs, bdref_key, child_role);
 
 done:
     qdict_del(options, bdref_key);
@@ -1437,21 +1564,34 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
         options = qdict_new();
     }
 
-    if (child_role) {
-        bs->inherits_from = parent;
-        flags = child_role->inherit_flags(parent->open_flags);
+    /* json: syntax counts as explicit options, as if in the QDict */
+    parse_json_protocol(options, &filename, &local_err);
+    if (local_err) {
+        ret = -EINVAL;
+        goto fail;
     }
 
-    ret = bdrv_fill_options(&options, &filename, &flags, &local_err);
+    bs->explicit_options = qdict_clone_shallow(options);
+
+    if (child_role) {
+        bs->inherits_from = parent;
+        child_role->inherit_options(&flags, options,
+                                    parent->open_flags, parent->options);
+    }
+
+    ret = bdrv_fill_options(&options, filename, &flags, &local_err);
     if (local_err) {
         goto fail;
     }
 
+    bs->open_flags = flags;
+    bs->options = options;
+    options = qdict_clone_shallow(options);
+
     /* Find the right image format driver */
     drvname = qdict_get_try_str(options, "driver");
     if (drvname) {
         drv = bdrv_find_format(drvname);
-        qdict_del(options, "driver");
         if (!drv) {
             error_setg(errp, "Unknown driver: '%s'", drvname);
             ret = -EINVAL;
@@ -1467,10 +1607,6 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
         qdict_del(options, "backing");
     }
 
-    bs->open_flags = flags;
-    bs->options = options;
-    options = qdict_clone_shallow(options);
-
     /* Open image file without format layer */
     if ((flags & BDRV_O_PROTOCOL) == 0) {
         if (flags & BDRV_O_RDWR) {
@@ -1478,7 +1614,7 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
         }
         if (flags & BDRV_O_SNAPSHOT) {
             snapshot_flags = bdrv_temp_snapshot_flags(flags);
-            flags = bdrv_backing_flags(flags);
+            bdrv_backing_options(&flags, options, flags, options);
         }
 
         bs->open_flags = flags;
@@ -1498,6 +1634,19 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
         if (ret < 0) {
             goto fail;
         }
+        /*
+         * This option update would logically belong in bdrv_fill_options(),
+         * but we first need to open bs->file for the probing to work, while
+         * opening bs->file already requires the (mostly) final set of options
+         * so that cache mode etc. can be inherited.
+         *
+         * Adding the driver later is somewhat ugly, but it's not an option
+         * that would ever be inherited, so it's correct. We just need to make
+         * sure to update both bs->options (which has the full effective
+         * options for bs) and options (which has file.* already removed).
+         */
+        qdict_put(bs->options, "driver", qstring_from_str(drv->format_name));
+        qdict_put(options, "driver", qstring_from_str(drv->format_name));
     } else if (!drv) {
         error_setg(errp, "Must specify either driver or file");
         ret = -EINVAL;
@@ -1511,7 +1660,7 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
     assert(!(flags & BDRV_O_PROTOCOL) || !file);
 
     /* Open the image */
-    ret = bdrv_open_common(bs, file, options, flags, drv, &local_err);
+    ret = bdrv_open_common(bs, file, options, flags, &local_err);
     if (ret < 0) {
         goto fail;
     }
@@ -1523,10 +1672,7 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
 
     /* If there is a backing file, use it */
     if ((flags & BDRV_O_NO_BACKING) == 0) {
-        QDict *backing_options;
-
-        qdict_extract_subqdict(options, &backing_options, "backing.");
-        ret = bdrv_open_backing_file(bs, backing_options, &local_err);
+        ret = bdrv_open_backing_file(bs, options, "backing", &local_err);
         if (ret < 0) {
             goto close_and_fail;
         }
@@ -1581,6 +1727,7 @@ fail:
     if (file != NULL) {
         bdrv_unref_child(bs, file);
     }
+    QDECREF(bs->explicit_options);
     QDECREF(bs->options);
     QDECREF(options);
     bs->options = NULL;
@@ -1643,15 +1790,19 @@ typedef struct BlockReopenQueueEntry {
  * bs_queue, or the existing bs_queue being used.
  *
  */
-BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
+static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
                                                  BlockDriverState *bs,
-                                    QDict *options, int flags)
+                                                 QDict *options,
+                                                 int flags,
+                                                 const BdrvChildRole *role,
+                                                 QDict *parent_options,
+                                                 int parent_flags)
 {
     assert(bs != NULL);
 
     BlockReopenQueueEntry *bs_entry;
     BdrvChild *child;
-    QDict *old_options;
+    QDict *old_options, *explicit_options;
 
     if (bs_queue == NULL) {
         bs_queue = g_new0(BlockReopenQueue, 1);
@@ -1662,23 +1813,63 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
         options = qdict_new();
     }
 
+    /*
+     * Precedence of options:
+     * 1. Explicitly passed in options (highest)
+     * 2. Set in flags (only for top level)
+     * 3. Retained from explicitly set options of bs
+     * 4. Inherited from parent node
+     * 5. Retained from effective options of bs
+     */
+
+    if (!parent_options) {
+        /*
+         * Any setting represented by flags is always updated. If the
+         * corresponding QDict option is set, it takes precedence. Otherwise
+         * the flag is translated into a QDict option. The old setting of bs is
+         * not considered.
+         */
+        update_options_from_flags(options, flags);
+    }
+
+    /* Old explicitly set values (don't overwrite by inherited value) */
+    old_options = qdict_clone_shallow(bs->explicit_options);
+    bdrv_join_options(bs, options, old_options);
+    QDECREF(old_options);
+
+    explicit_options = qdict_clone_shallow(options);
+
+    /* Inherit from parent node */
+    if (parent_options) {
+        assert(!flags);
+        role->inherit_options(&flags, options, parent_flags, parent_options);
+    }
+
+    /* Old values are used for options that aren't set yet */
     old_options = qdict_clone_shallow(bs->options);
-    qdict_join(options, old_options, false);
+    bdrv_join_options(bs, options, old_options);
     QDECREF(old_options);
 
     /* bdrv_open() masks this flag out */
     flags &= ~BDRV_O_PROTOCOL;
 
     QLIST_FOREACH(child, &bs->children, next) {
-        int child_flags;
+        QDict *new_child_options;
+        char *child_key_dot;
 
+        /* reopen can only change the options of block devices that were
+         * implicitly created and inherited options. For other (referenced)
+         * block devices, a syntax like "backing.foo" results in an error. */
         if (child->bs->inherits_from != bs) {
             continue;
         }
 
-        child_flags = child->role->inherit_flags(flags);
-        /* TODO Pass down child flags (backing.*, extents.*, ...) */
-        bdrv_reopen_queue(bs_queue, child->bs, NULL, child_flags);
+        child_key_dot = g_strdup_printf("%s.", child->name);
+        qdict_extract_subqdict(options, &new_child_options, child_key_dot);
+        g_free(child_key_dot);
+
+        bdrv_reopen_queue_child(bs_queue, child->bs, new_child_options, 0,
+                                child->role, options, flags);
     }
 
     bs_entry = g_new0(BlockReopenQueueEntry, 1);
@@ -1686,11 +1877,20 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
 
     bs_entry->state.bs = bs;
     bs_entry->state.options = options;
+    bs_entry->state.explicit_options = explicit_options;
     bs_entry->state.flags = flags;
 
     return bs_queue;
 }
 
+BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
+                                    BlockDriverState *bs,
+                                    QDict *options, int flags)
+{
+    return bdrv_reopen_queue_child(bs_queue, bs, options, flags,
+                                   NULL, NULL, 0);
+}
+
 /*
  * Reopen multiple BlockDriverStates atomically & transactionally.
  *
@@ -1737,6 +1937,8 @@ cleanup:
     QSIMPLEQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
         if (ret && bs_entry->prepared) {
             bdrv_reopen_abort(&bs_entry->state);
+        } else if (ret) {
+            QDECREF(bs_entry->state.explicit_options);
         }
         QDECREF(bs_entry->state.options);
         g_free(bs_entry);
@@ -1784,11 +1986,47 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
     int ret = -1;
     Error *local_err = NULL;
     BlockDriver *drv;
+    QemuOpts *opts;
+    const char *value;
 
     assert(reopen_state != NULL);
     assert(reopen_state->bs->drv != NULL);
     drv = reopen_state->bs->drv;
 
+    /* Process generic block layer options */
+    opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, reopen_state->options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto error;
+    }
+
+    update_flags_from_options(&reopen_state->flags, opts);
+
+    /* If a guest device is attached, it owns WCE */
+    if (reopen_state->bs->blk && blk_get_attached_dev(reopen_state->bs->blk)) {
+        bool old_wce = bdrv_enable_write_cache(reopen_state->bs);
+        bool new_wce = (reopen_state->flags & BDRV_O_CACHE_WB);
+        if (old_wce != new_wce) {
+            error_setg(errp, "Cannot change cache.writeback: Device attached");
+            ret = -EINVAL;
+            goto error;
+        }
+    }
+
+    /* node-name and driver must be unchanged. Put them back into the QDict, so
+     * that they are checked at the end of this function. */
+    value = qemu_opt_get(opts, "node-name");
+    if (value) {
+        qdict_put(reopen_state->options, "node-name", qstring_from_str(value));
+    }
+
+    value = qemu_opt_get(opts, "driver");
+    if (value) {
+        qdict_put(reopen_state->options, "driver", qstring_from_str(value));
+    }
+
     /* if we are to stay read-only, do not allow permission change
      * to r/w */
     if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
@@ -1849,6 +2087,7 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
     ret = 0;
 
 error:
+    qemu_opts_del(opts);
     return ret;
 }
 
@@ -1871,6 +2110,9 @@ void bdrv_reopen_commit(BDRVReopenState *reopen_state)
     }
 
     /* set BDS specific flags now */
+    QDECREF(reopen_state->bs->explicit_options);
+
+    reopen_state->bs->explicit_options   = reopen_state->explicit_options;
     reopen_state->bs->open_flags         = reopen_state->flags;
     reopen_state->bs->enable_write_cache = !!(reopen_state->flags &
                                               BDRV_O_CACHE_WB);
@@ -1894,6 +2136,8 @@ void bdrv_reopen_abort(BDRVReopenState *reopen_state)
     if (drv->bdrv_reopen_abort) {
         drv->bdrv_reopen_abort(reopen_state);
     }
+
+    QDECREF(reopen_state->explicit_options);
 }
 
 
@@ -1952,6 +2196,7 @@ void bdrv_close(BlockDriverState *bs)
         bs->sg = 0;
         bs->zero_beyond_eof = false;
         QDECREF(bs->options);
+        QDECREF(bs->explicit_options);
         bs->options = NULL;
         QDECREF(bs->full_open_options);
         bs->full_open_options = NULL;
@@ -2851,7 +3096,7 @@ ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs)
     return NULL;
 }
 
-void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event)
+void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event)
 {
     if (!bs || !bs->drv || !bs->drv->bdrv_debug_event) {
         return;
@@ -3823,12 +4068,12 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
 }
 
 int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
-                       BlockDriverAmendStatusCB *status_cb)
+                       BlockDriverAmendStatusCB *status_cb, void *cb_opaque)
 {
     if (!bs->drv->bdrv_amend_options) {
         return -ENOTSUP;
     }
-    return bs->drv->bdrv_amend_options(bs, opts, status_cb);
+    return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque);
 }
 
 /* This function will be called by the bdrv_recurse_is_first_non_filter method
@@ -3926,21 +4171,40 @@ out:
 static bool append_open_options(QDict *d, BlockDriverState *bs)
 {
     const QDictEntry *entry;
+    QemuOptDesc *desc;
+    BdrvChild *child;
     bool found_any = false;
+    const char *p;
 
     for (entry = qdict_first(bs->options); entry;
          entry = qdict_next(bs->options, entry))
     {
-        /* Only take options for this level and exclude all non-driver-specific
-         * options */
-        if (!strchr(qdict_entry_key(entry), '.') &&
-            strcmp(qdict_entry_key(entry), "node-name"))
+        /* Exclude options for children */
+        QLIST_FOREACH(child, &bs->children, next) {
+            if (strstart(qdict_entry_key(entry), child->name, &p)
+                && (!*p || *p == '.'))
             {
+                break;
+            }
+        }
+        if (child) {
+            continue;
+        }
+
+        /* And exclude all non-driver-specific options */
+        for (desc = bdrv_runtime_opts.desc; desc->name; desc++) {
+            if (!strcmp(qdict_entry_key(entry), desc->name)) {
+                break;
+            }
+        }
+        if (desc->name) {
+            continue;
+        }
+
         qobject_incref(qdict_entry_value(entry));
         qdict_put_obj(d, qdict_entry_key(entry), qdict_entry_value(entry));
         found_any = true;
     }
-    }
 
     return found_any;
 }
@@ -3981,7 +4245,10 @@ void bdrv_refresh_filename(BlockDriverState *bs)
             bs->full_open_options = NULL;
         }
 
-        drv->bdrv_refresh_filename(bs);
+        opts = qdict_new();
+        append_open_options(opts, bs);
+        drv->bdrv_refresh_filename(bs, opts);
+        QDECREF(opts);
     } else if (bs->file) {
         /* Try to reconstruct valid information from the underlying file */
         bool has_open_options;

block/blkdebug.c

@@ -36,7 +36,7 @@ typedef struct BDRVBlkdebugState {
     int state;
     int new_state;
 
-    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
+    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG__MAX];
     QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
     QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
 } BDRVBlkdebugState;
@@ -64,7 +64,7 @@ enum {
 };
 
 typedef struct BlkdebugRule {
-    BlkDebugEvent event;
+    BlkdebugEvent event;
     int action;
     int state;
     union {
@@ -143,69 +143,12 @@ static QemuOptsList *config_groups[] = {
     NULL
 };
 
-static const char *event_names[BLKDBG_EVENT_MAX] = {
-    [BLKDBG_L1_UPDATE]                      = "l1_update",
-    [BLKDBG_L1_GROW_ALLOC_TABLE]            = "l1_grow.alloc_table",
-    [BLKDBG_L1_GROW_WRITE_TABLE]            = "l1_grow.write_table",
-    [BLKDBG_L1_GROW_ACTIVATE_TABLE]         = "l1_grow.activate_table",
-
-    [BLKDBG_L2_LOAD]                        = "l2_load",
-    [BLKDBG_L2_UPDATE]                      = "l2_update",
-    [BLKDBG_L2_UPDATE_COMPRESSED]           = "l2_update_compressed",
-    [BLKDBG_L2_ALLOC_COW_READ]              = "l2_alloc.cow_read",
-    [BLKDBG_L2_ALLOC_WRITE]                 = "l2_alloc.write",
-
-    [BLKDBG_READ_AIO]                       = "read_aio",
-    [BLKDBG_READ_BACKING_AIO]               = "read_backing_aio",
-    [BLKDBG_READ_COMPRESSED]                = "read_compressed",
-
-    [BLKDBG_WRITE_AIO]                      = "write_aio",
-    [BLKDBG_WRITE_COMPRESSED]               = "write_compressed",
-
-    [BLKDBG_VMSTATE_LOAD]                   = "vmstate_load",
-    [BLKDBG_VMSTATE_SAVE]                   = "vmstate_save",
-
-    [BLKDBG_COW_READ]                       = "cow_read",
-    [BLKDBG_COW_WRITE]                      = "cow_write",
-
-    [BLKDBG_REFTABLE_LOAD]                  = "reftable_load",
-    [BLKDBG_REFTABLE_GROW]                  = "reftable_grow",
-    [BLKDBG_REFTABLE_UPDATE]                = "reftable_update",
-
-    [BLKDBG_REFBLOCK_LOAD]                  = "refblock_load",
-    [BLKDBG_REFBLOCK_UPDATE]                = "refblock_update",
-    [BLKDBG_REFBLOCK_UPDATE_PART]           = "refblock_update_part",
-    [BLKDBG_REFBLOCK_ALLOC]                 = "refblock_alloc",
-    [BLKDBG_REFBLOCK_ALLOC_HOOKUP]          = "refblock_alloc.hookup",
-    [BLKDBG_REFBLOCK_ALLOC_WRITE]           = "refblock_alloc.write",
-    [BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS]    = "refblock_alloc.write_blocks",
-    [BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE]     = "refblock_alloc.write_table",
-    [BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE]    = "refblock_alloc.switch_table",
-
-    [BLKDBG_CLUSTER_ALLOC]                  = "cluster_alloc",
-    [BLKDBG_CLUSTER_ALLOC_BYTES]            = "cluster_alloc_bytes",
-    [BLKDBG_CLUSTER_FREE]                   = "cluster_free",
-
-    [BLKDBG_FLUSH_TO_OS]                    = "flush_to_os",
-    [BLKDBG_FLUSH_TO_DISK]                  = "flush_to_disk",
-
-    [BLKDBG_PWRITEV_RMW_HEAD]               = "pwritev_rmw.head",
-    [BLKDBG_PWRITEV_RMW_AFTER_HEAD]         = "pwritev_rmw.after_head",
-    [BLKDBG_PWRITEV_RMW_TAIL]               = "pwritev_rmw.tail",
-    [BLKDBG_PWRITEV_RMW_AFTER_TAIL]         = "pwritev_rmw.after_tail",
-    [BLKDBG_PWRITEV]                        = "pwritev",
-    [BLKDBG_PWRITEV_ZERO]                   = "pwritev_zero",
-    [BLKDBG_PWRITEV_DONE]                   = "pwritev_done",
-
-    [BLKDBG_EMPTY_IMAGE_PREPARE]            = "empty_image_prepare",
-};
-
-static int get_event_by_name(const char *name, BlkDebugEvent *event)
+static int get_event_by_name(const char *name, BlkdebugEvent *event)
 {
     int i;
 
-    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
-        if (!strcmp(event_names[i], name)) {
+    for (i = 0; i < BLKDBG__MAX; i++) {
+        if (!strcmp(BlkdebugEvent_lookup[i], name)) {
             *event = i;
             return 0;
         }
@@ -224,7 +167,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
     struct add_rule_data *d = opaque;
     BDRVBlkdebugState *s = d->s;
     const char* event_name;
-    BlkDebugEvent event;
+    BlkdebugEvent event;
     struct BlkdebugRule *rule;
 
     /* Find the right event for the rule */
@@ -564,7 +507,7 @@ static void blkdebug_close(BlockDriverState *bs)
     BlkdebugRule *rule, *next;
     int i;
 
-    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
+    for (i = 0; i < BLKDBG__MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
             remove_rule(rule);
         }
@@ -627,13 +570,13 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
     return injected;
 }
 
-static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
+static void blkdebug_debug_event(BlockDriverState *bs, BlkdebugEvent event)
 {
     BDRVBlkdebugState *s = bs->opaque;
     struct BlkdebugRule *rule, *next;
     bool injected;
 
-    assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
+    assert((int)event >= 0 && event < BLKDBG__MAX);
 
     injected = false;
     s->new_state = s->state;
@@ -648,7 +591,7 @@ static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
 {
     BDRVBlkdebugState *s = bs->opaque;
     struct BlkdebugRule *rule;
-    BlkDebugEvent blkdebug_event;
+    BlkdebugEvent blkdebug_event;
 
     if (get_event_by_name(event, &blkdebug_event) < 0) {
         return -ENOENT;
@@ -690,7 +633,7 @@ static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs,
     BlkdebugRule *rule, *next;
     int i, ret = -ENOENT;
 
-    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
+    for (i = 0; i < BLKDBG__MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
             if (rule->action == ACTION_SUSPEND &&
                 !strcmp(rule->options.suspend.tag, tag)) {
@@ -731,17 +674,15 @@ static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
     return bdrv_truncate(bs->file->bs, offset);
 }
 
-static void blkdebug_refresh_filename(BlockDriverState *bs)
+static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
 {
     QDict *opts;
     const QDictEntry *e;
     bool force_json = false;
 
-    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
+    for (e = qdict_first(options); e; e = qdict_next(options, e)) {
         if (strcmp(qdict_entry_key(e), "config") &&
-            strcmp(qdict_entry_key(e), "x-image") &&
-            strcmp(qdict_entry_key(e), "image") &&
-            strncmp(qdict_entry_key(e), "image.", strlen("image.")))
+            strcmp(qdict_entry_key(e), "x-image"))
         {
             force_json = true;
             break;
@@ -757,7 +698,7 @@ static void blkdebug_refresh_filename(BlockDriverState *bs)
     if (!force_json && bs->file->bs->exact_filename[0]) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
                  "blkdebug:%s:%s",
-                 qdict_get_try_str(bs->options, "config") ?: "",
+                 qdict_get_try_str(options, "config") ?: "",
                  bs->file->bs->exact_filename);
     }
 
@@ -767,11 +708,8 @@ static void blkdebug_refresh_filename(BlockDriverState *bs)
     QINCREF(bs->file->bs->full_open_options);
     qdict_put_obj(opts, "image", QOBJECT(bs->file->bs->full_open_options));
 
-    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
-        if (strcmp(qdict_entry_key(e), "x-image") &&
-            strcmp(qdict_entry_key(e), "image") &&
-            strncmp(qdict_entry_key(e), "image.", strlen("image.")))
-        {
+    for (e = qdict_first(options); e; e = qdict_next(options, e)) {
+        if (strcmp(qdict_entry_key(e), "x-image")) {
             qobject_incref(qdict_entry_value(e));
             qdict_put_obj(opts, qdict_entry_key(e), qdict_entry_value(e));
         }
@@ -780,6 +718,12 @@ static void blkdebug_refresh_filename(BlockDriverState *bs)
     bs->full_open_options = opts;
 }
 
+static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state,
+                                   BlockReopenQueue *queue, Error **errp)
+{
+    return 0;
+}
+
 static BlockDriver bdrv_blkdebug = {
     .format_name            = "blkdebug",
     .protocol_name          = "blkdebug",
@@ -788,6 +732,7 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_parse_filename    = blkdebug_parse_filename,
     .bdrv_file_open         = blkdebug_open,
     .bdrv_close             = blkdebug_close,
+    .bdrv_reopen_prepare    = blkdebug_reopen_prepare,
     .bdrv_getlength         = blkdebug_getlength,
     .bdrv_truncate          = blkdebug_truncate,
     .bdrv_refresh_filename  = blkdebug_refresh_filename,

block/blkverify.c

@@ -307,7 +307,7 @@ static void blkverify_attach_aio_context(BlockDriverState *bs,
     bdrv_attach_aio_context(s->test_file->bs, new_context);
 }
 
-static void blkverify_refresh_filename(BlockDriverState *bs)
+static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
 {
     BDRVBlkverifyState *s = bs->opaque;
 

block/block-backend.c

@@ -1023,6 +1023,11 @@ int blk_get_max_transfer_length(BlockBackend *blk)
     }
 }
 
+int blk_get_max_iov(BlockBackend *blk)
+{
+    return blk->bs->bl.max_iov;
+}
+
 void blk_set_guest_block_size(BlockBackend *blk, int align)
 {
     blk->guest_block_size = align;

block/io.c

@@ -166,9 +166,13 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
         bs->bl.max_transfer_length = bs->file->bs->bl.max_transfer_length;
         bs->bl.min_mem_alignment = bs->file->bs->bl.min_mem_alignment;
         bs->bl.opt_mem_alignment = bs->file->bs->bl.opt_mem_alignment;
+        bs->bl.max_iov = bs->file->bs->bl.max_iov;
     } else {
         bs->bl.min_mem_alignment = 512;
         bs->bl.opt_mem_alignment = getpagesize();
+
+        /* Safe default since most protocols use readv()/writev()/etc */
+        bs->bl.max_iov = IOV_MAX;
     }
 
     if (bs->backing) {
@@ -189,6 +193,9 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
         bs->bl.min_mem_alignment =
             MAX(bs->bl.min_mem_alignment,
                 bs->backing->bs->bl.min_mem_alignment);
+        bs->bl.max_iov =
+            MIN(bs->bl.max_iov,
+                bs->backing->bs->bl.max_iov);
     }
 
     /* Then let the driver override it */
@@ -1882,7 +1889,8 @@ static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
             merge = 1;
         }
 
-        if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 > IOV_MAX) {
+        if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 >
+            bs->bl.max_iov) {
             merge = 0;
         }
 
@@ -2614,11 +2622,12 @@ int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
         bdrv_co_ioctl_entry(&data);
     } else {
         Coroutine *co = qemu_coroutine_create(bdrv_co_ioctl_entry);
+
         qemu_coroutine_enter(co, &data);
-    }
         while (data.ret == -EINPROGRESS) {
             aio_poll(bdrv_get_aio_context(bs), true);
         }
+    }
     return data.ret;
 }
 

block/mirror.c

@@ -18,6 +18,7 @@
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "qemu/bitmap.h"
+#include "qemu/error-report.h"
 
 #define SLICE_TIME    100000000ULL /* ns */
 #define MAX_IN_FLIGHT 16
@@ -160,13 +161,15 @@ static void mirror_read_complete(void *opaque, int ret)
 static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
     BlockDriverState *source = s->common.bs;
-    int nb_sectors, sectors_per_chunk, nb_chunks;
+    int nb_sectors, sectors_per_chunk, nb_chunks, max_iov;
     int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
     uint64_t delay_ns = 0;
     MirrorOp *op;
     int pnum;
     int64_t ret;
 
+    max_iov = MIN(source->bl.max_iov, s->target->bl.max_iov);
+
     s->sector_num = hbitmap_iter_next(&s->hbi);
     if (s->sector_num < 0) {
         bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
@@ -247,7 +250,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
             trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
             break;
         }
-        if (IOV_MAX < nb_chunks + added_chunks) {
+        if (max_iov < nb_chunks + added_chunks) {
             trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
             break;
         }
@@ -370,11 +373,22 @@ static void mirror_exit(BlockJob *job, void *opaque)
         if (s->to_replace) {
             to_replace = s->to_replace;
         }
+
+        /* This was checked in mirror_start_job(), but meanwhile one of the
+         * nodes could have been newly attached to a BlockBackend. */
+        if (to_replace->blk && s->target->blk) {
+            error_report("block job: Can't create node with two BlockBackends");
+            data->ret = -EINVAL;
+            goto out;
+        }
+
         if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
             bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
         }
         bdrv_replace_in_backing_chain(to_replace, s->target);
     }
+
+out:
     if (s->to_replace) {
         bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
         error_free(s->replace_blocker);
@@ -640,7 +654,7 @@ static void mirror_complete(BlockJob *job, Error **errp)
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_open_backing_file(s->target, NULL, &local_err);
+    ret = bdrv_open_backing_file(s->target, NULL, "backing", &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         return;
@@ -705,6 +719,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
                              bool is_none_mode, BlockDriverState *base)
 {
     MirrorBlockJob *s;
+    BlockDriverState *replaced_bs;
 
     if (granularity == 0) {
         granularity = bdrv_get_default_bitmap_granularity(target);
@@ -728,6 +743,21 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
         buf_size = DEFAULT_MIRROR_BUF_SIZE;
     }
 
+    /* We can't support this case as long as the block layer can't handle
+     * multiple BlockBackends per BlockDriverState. */
+    if (replaces) {
+        replaced_bs = bdrv_lookup_bs(replaces, replaces, errp);
+        if (replaced_bs == NULL) {
+            return;
+        }
+    } else {
+        replaced_bs = bs;
+    }
+    if (replaced_bs->blk && target->blk) {
+        error_setg(errp, "Can't create node with two BlockBackends");
+        return;
+    }
+
     s = block_job_create(driver, bs, speed, cb, opaque, errp);
     if (!s) {
         return;

block/nbd.c

@@ -342,13 +342,13 @@ static void nbd_attach_aio_context(BlockDriverState *bs,
     nbd_client_attach_aio_context(bs, new_context);
 }
 
-static void nbd_refresh_filename(BlockDriverState *bs)
+static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
 {
     QDict *opts = qdict_new();
-    const char *path   = qdict_get_try_str(bs->options, "path");
-    const char *host   = qdict_get_try_str(bs->options, "host");
-    const char *port   = qdict_get_try_str(bs->options, "port");
-    const char *export = qdict_get_try_str(bs->options, "export");
+    const char *path   = qdict_get_try_str(options, "path");
+    const char *host   = qdict_get_try_str(options, "host");
+    const char *port   = qdict_get_try_str(options, "port");
+    const char *export = qdict_get_try_str(options, "export");
 
     qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("nbd")));
 

block/parallels.c

@@ -61,7 +61,7 @@ typedef struct ParallelsHeader {
 typedef enum ParallelsPreallocMode {
     PRL_PREALLOC_MODE_FALLOCATE = 0,
     PRL_PREALLOC_MODE_TRUNCATE = 1,
-    PRL_PREALLOC_MODE_MAX = 2,
+    PRL_PREALLOC_MODE__MAX = 2,
 } ParallelsPreallocMode;
 
 static const char *prealloc_mode_lookup[] = {
@@ -660,7 +660,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     s->prealloc_size = MAX(s->tracks, s->prealloc_size >> BDRV_SECTOR_BITS);
     buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
     s->prealloc_mode = qapi_enum_parse(prealloc_mode_lookup, buf,
-            PRL_PREALLOC_MODE_MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
+            PRL_PREALLOC_MODE__MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
     g_free(buf);
     if (local_err != NULL) {
         goto fail_options;

block/qapi.c

@@ -245,15 +245,17 @@ void bdrv_query_image_info(BlockDriverState *bs,
         info->has_backing_filename = true;
         bdrv_get_full_backing_filename(bs, backing_filename2, PATH_MAX, &err);
         if (err) {
-            error_propagate(errp, err);
-            qapi_free_ImageInfo(info);
+            /* Can't reconstruct the full backing filename, so we must omit
+             * this field and apply a Best Effort to this query. */
             g_free(backing_filename2);
-            return;
+            backing_filename2 = NULL;
+            error_free(err);
         }
 
-        if (strcmp(backing_filename, backing_filename2) != 0) {
-            info->full_backing_filename =
-                        g_strdup(backing_filename2);
+        /* Always report the full_backing_filename if present, even if it's the
+         * same as backing_filename. That they are same is useful info. */
+        if (backing_filename2) {
+            info->full_backing_filename = g_strdup(backing_filename2);
             info->has_full_backing_filename = true;
         }
 
@@ -588,7 +590,7 @@ static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
     int i = 0;
 
     for (entry = qlist_first(list); entry; entry = qlist_next(entry), i++) {
-        qtype_code type = qobject_type(entry->value);
+        QType type = qobject_type(entry->value);
         bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
         const char *format = composite ? "%*s[%i]:\n" : "%*s[%i]: ";
 
@@ -606,7 +608,7 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
     const QDictEntry *entry;
 
     for (entry = qdict_first(dict); entry; entry = qdict_next(dict, entry)) {
-        qtype_code type = qobject_type(entry->value);
+        QType type = qobject_type(entry->value);
         bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
         const char *format = composite ? "%*s%s:\n" : "%*s%s: ";
         char key[strlen(entry->key) + 1];
@@ -676,7 +678,10 @@ void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
 
     if (info->has_backing_filename) {
         func_fprintf(f, "backing file: %s", info->backing_filename);
-        if (info->has_full_backing_filename) {
+        if (!info->has_full_backing_filename) {
+            func_fprintf(f, " (cannot determine actual path)");
+        } else if (strcmp(info->backing_filename,
+                          info->full_backing_filename) != 0) {
             func_fprintf(f, " (actual path: %s)", info->full_backing_filename);
         }
         func_fprintf(f, "\n");

block/qcow2-cluster.c

@@ -1641,7 +1641,8 @@ fail:
 static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                                       int l1_size, int64_t *visited_l1_entries,
                                       int64_t l1_entries,
-                                      BlockDriverAmendStatusCB *status_cb)
+                                      BlockDriverAmendStatusCB *status_cb,
+                                      void *cb_opaque)
 {
     BDRVQcow2State *s = bs->opaque;
     bool is_active_l1 = (l1_table == s->l1_table);
@@ -1667,7 +1668,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
             /* unallocated */
             (*visited_l1_entries)++;
             if (status_cb) {
-                status_cb(bs, *visited_l1_entries, l1_entries);
+                status_cb(bs, *visited_l1_entries, l1_entries, cb_opaque);
             }
             continue;
         }
@@ -1804,7 +1805,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
 
         (*visited_l1_entries)++;
         if (status_cb) {
-            status_cb(bs, *visited_l1_entries, l1_entries);
+            status_cb(bs, *visited_l1_entries, l1_entries, cb_opaque);
         }
     }
 
@@ -1828,7 +1829,8 @@ fail:
  * qcow2 version which doesn't yet support metadata zero clusters.
  */
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
-                               BlockDriverAmendStatusCB *status_cb)
+                               BlockDriverAmendStatusCB *status_cb,
+                               void *cb_opaque)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t *l1_table = NULL;
@@ -1845,7 +1847,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
 
     ret = expand_zero_clusters_in_l1(bs, s->l1_table, s->l1_size,
                                      &visited_l1_entries, l1_entries,
-                                     status_cb);
+                                     status_cb, cb_opaque);
     if (ret < 0) {
         goto fail;
     }
@@ -1881,7 +1883,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
 
         ret = expand_zero_clusters_in_l1(bs, l1_table, s->snapshots[i].l1_size,
                                          &visited_l1_entries, l1_entries,
-                                         status_cb);
+                                         status_cb, cb_opaque);
         if (ret < 0) {
             goto fail;
         }

block/qcow2-refcount.c

@@ -1345,6 +1345,9 @@ static int inc_refcounts(BlockDriverState *bs,
         if (refcount == s->refcount_max) {
             fprintf(stderr, "ERROR: overflow cluster offset=0x%" PRIx64
                     "\n", cluster_offset);
+            fprintf(stderr, "Use qemu-img amend to increase the refcount entry "
+                    "width or qemu-img convert to create a clean copy if the "
+                    "image cannot be opened for writing\n");
             res->corruptions++;
             continue;
         }
@@ -2467,3 +2470,450 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
 
     return 0;
 }
+
+/* A pointer to a function of this type is given to walk_over_reftable(). That
+ * function will create refblocks and pass them to a RefblockFinishOp once they
+ * are completed (@refblock). @refblock_empty is set if the refblock is
+ * completely empty.
+ *
+ * Along with the refblock, a corresponding reftable entry is passed, in the
+ * reftable @reftable (which may be reallocated) at @reftable_index.
+ *
+ * @allocated should be set to true if a new cluster has been allocated.
+ */
+typedef int (RefblockFinishOp)(BlockDriverState *bs, uint64_t **reftable,
+                               uint64_t reftable_index, uint64_t *reftable_size,
+                               void *refblock, bool refblock_empty,
+                               bool *allocated, Error **errp);
+
+/**
+ * This "operation" for walk_over_reftable() allocates the refblock on disk (if
+ * it is not empty) and inserts its offset into the new reftable. The size of
+ * this new reftable is increased as required.
+ */
+static int alloc_refblock(BlockDriverState *bs, uint64_t **reftable,
+                          uint64_t reftable_index, uint64_t *reftable_size,
+                          void *refblock, bool refblock_empty, bool *allocated,
+                          Error **errp)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int64_t offset;
+
+    if (!refblock_empty && reftable_index >= *reftable_size) {
+        uint64_t *new_reftable;
+        uint64_t new_reftable_size;
+
+        new_reftable_size = ROUND_UP(reftable_index + 1,
+                                     s->cluster_size / sizeof(uint64_t));
+        if (new_reftable_size > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
+            error_setg(errp,
+                       "This operation would make the refcount table grow "
+                       "beyond the maximum size supported by QEMU, aborting");
+            return -ENOTSUP;
+        }
+
+        new_reftable = g_try_realloc(*reftable, new_reftable_size *
+                                                sizeof(uint64_t));
+        if (!new_reftable) {
+            error_setg(errp, "Failed to increase reftable buffer size");
+            return -ENOMEM;
+        }
+
+        memset(new_reftable + *reftable_size, 0,
+               (new_reftable_size - *reftable_size) * sizeof(uint64_t));
+
+        *reftable      = new_reftable;
+        *reftable_size = new_reftable_size;
+    }
+
+    if (!refblock_empty && !(*reftable)[reftable_index]) {
+        offset = qcow2_alloc_clusters(bs, s->cluster_size);
+        if (offset < 0) {
+            error_setg_errno(errp, -offset, "Failed to allocate refblock");
+            return offset;
+        }
+        (*reftable)[reftable_index] = offset;
+        *allocated = true;
+    }
+
+    return 0;
+}
+
+/**
+ * This "operation" for walk_over_reftable() writes the refblock to disk at the
+ * offset specified by the new reftable's entry. It does not modify the new
+ * reftable or change any refcounts.
+ */
+static int flush_refblock(BlockDriverState *bs, uint64_t **reftable,
+                          uint64_t reftable_index, uint64_t *reftable_size,
+                          void *refblock, bool refblock_empty, bool *allocated,
+                          Error **errp)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int64_t offset;
+    int ret;
+
+    if (reftable_index < *reftable_size && (*reftable)[reftable_index]) {
+        offset = (*reftable)[reftable_index];
+
+        ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret, "Overlap check failed");
+            return ret;
+        }
+
+        ret = bdrv_pwrite(bs->file->bs, offset, refblock, s->cluster_size);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret, "Failed to write refblock");
+            return ret;
+        }
+    } else {
+        assert(refblock_empty);
+    }
+
+    return 0;
+}
+
+/**
+ * This function walks over the existing reftable and every referenced refblock;
+ * if @new_set_refcount is non-NULL, it is called for every refcount entry to
+ * create an equal new entry in the passed @new_refblock. Once that
+ * @new_refblock is completely filled, @operation will be called.
+ *
+ * @status_cb and @cb_opaque are used for the amend operation's status callback.
+ * @index is the index of the walk_over_reftable() calls and @total is the total
+ * number of walk_over_reftable() calls per amend operation. Both are used for
+ * calculating the parameters for the status callback.
+ *
+ * @allocated is set to true if a new cluster has been allocated.
+ */
+static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable,
+                              uint64_t *new_reftable_index,
+                              uint64_t *new_reftable_size,
+                              void *new_refblock, int new_refblock_size,
+                              int new_refcount_bits,
+                              RefblockFinishOp *operation, bool *allocated,
+                              Qcow2SetRefcountFunc *new_set_refcount,
+                              BlockDriverAmendStatusCB *status_cb,
+                              void *cb_opaque, int index, int total,
+                              Error **errp)
+{
+    BDRVQcow2State *s = bs->opaque;
+    uint64_t reftable_index;
+    bool new_refblock_empty = true;
+    int refblock_index;
+    int new_refblock_index = 0;
+    int ret;
+
+    for (reftable_index = 0; reftable_index < s->refcount_table_size;
+         reftable_index++)
+    {
+        uint64_t refblock_offset = s->refcount_table[reftable_index]
+                                 & REFT_OFFSET_MASK;
+
+        status_cb(bs, (uint64_t)index * s->refcount_table_size + reftable_index,
+                  (uint64_t)total * s->refcount_table_size, cb_opaque);
+
+        if (refblock_offset) {
+            void *refblock;
+
+            if (offset_into_cluster(s, refblock_offset)) {
+                qcow2_signal_corruption(bs, true, -1, -1, "Refblock offset %#"
+                                        PRIx64 " unaligned (reftable index: %#"
+                                        PRIx64 ")", refblock_offset,
+                                        reftable_index);
+                error_setg(errp,
+                           "Image is corrupt (unaligned refblock offset)");
+                return -EIO;
+            }
+
+            ret = qcow2_cache_get(bs, s->refcount_block_cache, refblock_offset,
+                                  &refblock);
+            if (ret < 0) {
+                error_setg_errno(errp, -ret, "Failed to retrieve refblock");
+                return ret;
+            }
+
+            for (refblock_index = 0; refblock_index < s->refcount_block_size;
+                 refblock_index++)
+            {
+                uint64_t refcount;
+
+                if (new_refblock_index >= new_refblock_size) {
+                    /* new_refblock is now complete */
+                    ret = operation(bs, new_reftable, *new_reftable_index,
+                                    new_reftable_size, new_refblock,
+                                    new_refblock_empty, allocated, errp);
+                    if (ret < 0) {
+                        qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
+                        return ret;
+                    }
+
+                    (*new_reftable_index)++;
+                    new_refblock_index = 0;
+                    new_refblock_empty = true;
+                }
+
+                refcount = s->get_refcount(refblock, refblock_index);
+                if (new_refcount_bits < 64 && refcount >> new_refcount_bits) {
+                    uint64_t offset;
+
+                    qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
+
+                    offset = ((reftable_index << s->refcount_block_bits)
+                              + refblock_index) << s->cluster_bits;
+
+                    error_setg(errp, "Cannot decrease refcount entry width to "
+                               "%i bits: Cluster at offset %#" PRIx64 " has a "
+                               "refcount of %" PRIu64, new_refcount_bits,
+                               offset, refcount);
+                    return -EINVAL;
+                }
+
+                if (new_set_refcount) {
+                    new_set_refcount(new_refblock, new_refblock_index++,
+                                     refcount);
+                } else {
+                    new_refblock_index++;
+                }
+                new_refblock_empty = new_refblock_empty && refcount == 0;
+            }
+
+            qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
+        } else {
+            /* No refblock means every refcount is 0 */
+            for (refblock_index = 0; refblock_index < s->refcount_block_size;
+                 refblock_index++)
+            {
+                if (new_refblock_index >= new_refblock_size) {
+                    /* new_refblock is now complete */
+                    ret = operation(bs, new_reftable, *new_reftable_index,
+                                    new_reftable_size, new_refblock,
+                                    new_refblock_empty, allocated, errp);
+                    if (ret < 0) {
+                        return ret;
+                    }
+
+                    (*new_reftable_index)++;
+                    new_refblock_index = 0;
+                    new_refblock_empty = true;
+                }
+
+                if (new_set_refcount) {
+                    new_set_refcount(new_refblock, new_refblock_index++, 0);
+                } else {
+                    new_refblock_index++;
+                }
+            }
+        }
+    }
+
+    if (new_refblock_index > 0) {
+        /* Complete the potentially existing partially filled final refblock */
+        if (new_set_refcount) {
+            for (; new_refblock_index < new_refblock_size;
+                 new_refblock_index++)
+            {
+                new_set_refcount(new_refblock, new_refblock_index, 0);
+            }
+        }
+
+        ret = operation(bs, new_reftable, *new_reftable_index,
+                        new_reftable_size, new_refblock, new_refblock_empty,
+                        allocated, errp);
+        if (ret < 0) {
+            return ret;
+        }
+
+        (*new_reftable_index)++;
+    }
+
+    status_cb(bs, (uint64_t)(index + 1) * s->refcount_table_size,
+              (uint64_t)total * s->refcount_table_size, cb_opaque);
+
+    return 0;
+}
+
+int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
+                                BlockDriverAmendStatusCB *status_cb,
+                                void *cb_opaque, Error **errp)
+{
+    BDRVQcow2State *s = bs->opaque;
+    Qcow2GetRefcountFunc *new_get_refcount;
+    Qcow2SetRefcountFunc *new_set_refcount;
+    void *new_refblock = qemu_blockalign(bs->file->bs, s->cluster_size);
+    uint64_t *new_reftable = NULL, new_reftable_size = 0;
+    uint64_t *old_reftable, old_reftable_size, old_reftable_offset;
+    uint64_t new_reftable_index = 0;
+    uint64_t i;
+    int64_t new_reftable_offset = 0, allocated_reftable_size = 0;
+    int new_refblock_size, new_refcount_bits = 1 << refcount_order;
+    int old_refcount_order;
+    int walk_index = 0;
+    int ret;
+    bool new_allocation;
+
+    assert(s->qcow_version >= 3);
+    assert(refcount_order >= 0 && refcount_order <= 6);
+
+    /* see qcow2_open() */
+    new_refblock_size = 1 << (s->cluster_bits - (refcount_order - 3));
+
+    new_get_refcount = get_refcount_funcs[refcount_order];
+    new_set_refcount = set_refcount_funcs[refcount_order];
+
+
+    do {
+        int total_walks;
+
+        new_allocation = false;
+
+        /* At least we have to do this walk and the one which writes the
+         * refblocks; also, at least we have to do this loop here at least
+         * twice (normally), first to do the allocations, and second to
+         * determine that everything is correctly allocated, this then makes
+         * three walks in total */
+        total_walks = MAX(walk_index + 2, 3);
+
+        /* First, allocate the structures so they are present in the refcount
+         * structures */
+        ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
+                                 &new_reftable_size, NULL, new_refblock_size,
+                                 new_refcount_bits, &alloc_refblock,
+                                 &new_allocation, NULL, status_cb, cb_opaque,
+                                 walk_index++, total_walks, errp);
+        if (ret < 0) {
+            goto done;
+        }
+
+        new_reftable_index = 0;
+
+        if (new_allocation) {
+            if (new_reftable_offset) {
+                qcow2_free_clusters(bs, new_reftable_offset,
+                                    allocated_reftable_size * sizeof(uint64_t),
+                                    QCOW2_DISCARD_NEVER);
+            }
+
+            new_reftable_offset = qcow2_alloc_clusters(bs, new_reftable_size *
+                                                           sizeof(uint64_t));
+            if (new_reftable_offset < 0) {
+                error_setg_errno(errp, -new_reftable_offset,
+                                 "Failed to allocate the new reftable");
+                ret = new_reftable_offset;
+                goto done;
+            }
+            allocated_reftable_size = new_reftable_size;
+        }
+    } while (new_allocation);
+
+    /* Second, write the new refblocks */
+    ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
+                             &new_reftable_size, new_refblock,
+                             new_refblock_size, new_refcount_bits,
+                             &flush_refblock, &new_allocation, new_set_refcount,
+                             status_cb, cb_opaque, walk_index, walk_index + 1,
+                             errp);
+    if (ret < 0) {
+        goto done;
+    }
+    assert(!new_allocation);
+
+
+    /* Write the new reftable */
+    ret = qcow2_pre_write_overlap_check(bs, 0, new_reftable_offset,
+                                        new_reftable_size * sizeof(uint64_t));
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Overlap check failed");
+        goto done;
+    }
+
+    for (i = 0; i < new_reftable_size; i++) {
+        cpu_to_be64s(&new_reftable[i]);
+    }
+
+    ret = bdrv_pwrite(bs->file->bs, new_reftable_offset, new_reftable,
+                      new_reftable_size * sizeof(uint64_t));
+
+    for (i = 0; i < new_reftable_size; i++) {
+        be64_to_cpus(&new_reftable[i]);
+    }
+
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to write the new reftable");
+        goto done;
+    }
+
+
+    /* Empty the refcount cache */
+    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to flush the refblock cache");
+        goto done;
+    }
+
+    /* Update the image header to point to the new reftable; this only updates
+     * the fields which are relevant to qcow2_update_header(); other fields
+     * such as s->refcount_table or s->refcount_bits stay stale for now
+     * (because we have to restore everything if qcow2_update_header() fails) */
+    old_refcount_order  = s->refcount_order;
+    old_reftable_size   = s->refcount_table_size;
+    old_reftable_offset = s->refcount_table_offset;
+
+    s->refcount_order        = refcount_order;
+    s->refcount_table_size   = new_reftable_size;
+    s->refcount_table_offset = new_reftable_offset;
+
+    ret = qcow2_update_header(bs);
+    if (ret < 0) {
+        s->refcount_order        = old_refcount_order;
+        s->refcount_table_size   = old_reftable_size;
+        s->refcount_table_offset = old_reftable_offset;
+        error_setg_errno(errp, -ret, "Failed to update the qcow2 header");
+        goto done;
+    }
+
+    /* Now update the rest of the in-memory information */
+    old_reftable = s->refcount_table;
+    s->refcount_table = new_reftable;
+
+    s->refcount_bits = 1 << refcount_order;
+    s->refcount_max = UINT64_C(1) << (s->refcount_bits - 1);
+    s->refcount_max += s->refcount_max - 1;
+
+    s->refcount_block_bits = s->cluster_bits - (refcount_order - 3);
+    s->refcount_block_size = 1 << s->refcount_block_bits;
+
+    s->get_refcount = new_get_refcount;
+    s->set_refcount = new_set_refcount;
+
+    /* For cleaning up all old refblocks and the old reftable below the "done"
+     * label */
+    new_reftable        = old_reftable;
+    new_reftable_size   = old_reftable_size;
+    new_reftable_offset = old_reftable_offset;
+
+done:
+    if (new_reftable) {
+        /* On success, new_reftable actually points to the old reftable (and
+         * new_reftable_size is the old reftable's size); but that is just
+         * fine */
+        for (i = 0; i < new_reftable_size; i++) {
+            uint64_t offset = new_reftable[i] & REFT_OFFSET_MASK;
+            if (offset) {
+                qcow2_free_clusters(bs, offset, s->cluster_size,
+                                    QCOW2_DISCARD_OTHER);
+            }
+        }
+        g_free(new_reftable);
+
+        if (new_reftable_offset > 0) {
+            qcow2_free_clusters(bs, new_reftable_offset,
+                                new_reftable_size * sizeof(uint64_t),
+                                QCOW2_DISCARD_OTHER);
+        }
+    }
+
+    qemu_vfree(new_refblock);
+    return ret;
+}

block/qcow2.c

@@ -1282,6 +1282,52 @@ static void qcow2_reopen_abort(BDRVReopenState *state)
     g_free(state->opaque);
 }
 
+static void qcow2_join_options(QDict *options, QDict *old_options)
+{
+    bool has_new_overlap_template =
+        qdict_haskey(options, QCOW2_OPT_OVERLAP) ||
+        qdict_haskey(options, QCOW2_OPT_OVERLAP_TEMPLATE);
+    bool has_new_total_cache_size =
+        qdict_haskey(options, QCOW2_OPT_CACHE_SIZE);
+    bool has_all_cache_options;
+
+    /* New overlap template overrides all old overlap options */
+    if (has_new_overlap_template) {
+        qdict_del(old_options, QCOW2_OPT_OVERLAP);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_TEMPLATE);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_MAIN_HEADER);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_ACTIVE_L1);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_ACTIVE_L2);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_REFCOUNT_TABLE);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_REFCOUNT_BLOCK);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_INACTIVE_L1);
+        qdict_del(old_options, QCOW2_OPT_OVERLAP_INACTIVE_L2);
+    }
+
+    /* New total cache size overrides all old options */
+    if (qdict_haskey(options, QCOW2_OPT_CACHE_SIZE)) {
+        qdict_del(old_options, QCOW2_OPT_L2_CACHE_SIZE);
+        qdict_del(old_options, QCOW2_OPT_REFCOUNT_CACHE_SIZE);
+    }
+
+    qdict_join(options, old_options, false);
+
+    /*
+     * If after merging all cache size options are set, an old total size is
+     * overwritten. Do keep all options, however, if all three are new. The
+     * resulting error message is what we want to happen.
+     */
+    has_all_cache_options =
+        qdict_haskey(options, QCOW2_OPT_CACHE_SIZE) ||
+        qdict_haskey(options, QCOW2_OPT_L2_CACHE_SIZE) ||
+        qdict_haskey(options, QCOW2_OPT_REFCOUNT_CACHE_SIZE);
+
+    if (has_all_cache_options && !has_new_total_cache_size) {
+        qdict_del(options, QCOW2_OPT_CACHE_SIZE);
+    }
+}
+
 static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -2269,7 +2315,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
                                          DEFAULT_CLUSTER_SIZE);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
-                               PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+                               PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
                                &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -2757,6 +2803,10 @@ static ImageInfoSpecific *qcow2_get_specific_info(BlockDriverState *bs)
             .has_corrupt        = true,
             .refcount_bits      = s->refcount_bits,
         };
+    } else {
+        /* if this assertion fails, this probably means a new version was
+         * added without having it covered here */
+        assert(false);
     }
 
     return spec_info;
@@ -2824,7 +2874,7 @@ static int qcow2_load_vmstate(BlockDriverState *bs, uint8_t *buf,
  * have to be removed.
  */
 static int qcow2_downgrade(BlockDriverState *bs, int target_version,
-                           BlockDriverAmendStatusCB *status_cb)
+                           BlockDriverAmendStatusCB *status_cb, void *cb_opaque)
 {
     BDRVQcow2State *s = bs->opaque;
     int current_version = s->qcow_version;
@@ -2839,13 +2889,7 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version,
     }
 
     if (s->refcount_order != 4) {
-        /* we would have to convert the image to a refcount_order == 4 image
-         * here; however, since qemu (at the time of writing this) does not
-         * support anything different than 4 anyway, there is no point in doing
-         * so right now; however, we should error out (if qemu supports this in
-         * the future and this code has not been adapted) */
-        error_report("qcow2_downgrade: Image refcount orders other than 4 are "
-                     "currently not supported.");
+        error_report("compat=0.10 requires refcount_bits=16");
         return -ENOTSUP;
     }
 
@@ -2873,7 +2917,7 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version,
     /* clearing autoclear features is trivial */
     s->autoclear_features = 0;
 
-    ret = qcow2_expand_zero_clusters(bs, status_cb);
+    ret = qcow2_expand_zero_clusters(bs, status_cb, cb_opaque);
     if (ret < 0) {
         return ret;
     }
@@ -2887,8 +2931,79 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version,
     return 0;
 }
 
+typedef enum Qcow2AmendOperation {
+    /* This is the value Qcow2AmendHelperCBInfo::last_operation will be
+     * statically initialized to so that the helper CB can discern the first
+     * invocation from an operation change */
+    QCOW2_NO_OPERATION = 0,
+
+    QCOW2_CHANGING_REFCOUNT_ORDER,
+    QCOW2_DOWNGRADING,
+} Qcow2AmendOperation;
+
+typedef struct Qcow2AmendHelperCBInfo {
+    /* The code coordinating the amend operations should only modify
+     * these four fields; the rest will be managed by the CB */
+    BlockDriverAmendStatusCB *original_status_cb;
+    void *original_cb_opaque;
+
+    Qcow2AmendOperation current_operation;
+
+    /* Total number of operations to perform (only set once) */
+    int total_operations;
+
+    /* The following fields are managed by the CB */
+
+    /* Number of operations completed */
+    int operations_completed;
+
+    /* Cumulative offset of all completed operations */
+    int64_t offset_completed;
+
+    Qcow2AmendOperation last_operation;
+    int64_t last_work_size;
+} Qcow2AmendHelperCBInfo;
+
+static void qcow2_amend_helper_cb(BlockDriverState *bs,
+                                  int64_t operation_offset,
+                                  int64_t operation_work_size, void *opaque)
+{
+    Qcow2AmendHelperCBInfo *info = opaque;
+    int64_t current_work_size;
+    int64_t projected_work_size;
+
+    if (info->current_operation != info->last_operation) {
+        if (info->last_operation != QCOW2_NO_OPERATION) {
+            info->offset_completed += info->last_work_size;
+            info->operations_completed++;
+        }
+
+        info->last_operation = info->current_operation;
+    }
+
+    assert(info->total_operations > 0);
+    assert(info->operations_completed < info->total_operations);
+
+    info->last_work_size = operation_work_size;
+
+    current_work_size = info->offset_completed + operation_work_size;
+
+    /* current_work_size is the total work size for (operations_completed + 1)
+     * operations (which includes this one), so multiply it by the number of
+     * operations not covered and divide it by the number of operations
+     * covered to get a projection for the operations not covered */
+    projected_work_size = current_work_size * (info->total_operations -
+                                               info->operations_completed - 1)
+                                            / (info->operations_completed + 1);
+
+    info->original_status_cb(bs, info->offset_completed + operation_offset,
+                             current_work_size + projected_work_size,
+                             info->original_cb_opaque);
+}
+
 static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
-                               BlockDriverAmendStatusCB *status_cb)
+                               BlockDriverAmendStatusCB *status_cb,
+                               void *cb_opaque)
 {
     BDRVQcow2State *s = bs->opaque;
     int old_version = s->qcow_version, new_version = old_version;
@@ -2898,8 +3013,10 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     const char *compat = NULL;
     uint64_t cluster_size = s->cluster_size;
     bool encrypt;
+    int refcount_bits = s->refcount_bits;
     int ret;
     QemuOptDesc *desc = opts->list->desc;
+    Qcow2AmendHelperCBInfo helper_cb_info;
 
     while (desc && desc->name) {
         if (!qemu_opt_find(opts, desc->name)) {
@@ -2917,11 +3034,11 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
             } else if (!strcmp(compat, "1.1")) {
                 new_version = 3;
             } else {
-                fprintf(stderr, "Unknown compatibility level %s.\n", compat);
+                error_report("Unknown compatibility level %s", compat);
                 return -EINVAL;
             }
         } else if (!strcmp(desc->name, BLOCK_OPT_PREALLOC)) {
-            fprintf(stderr, "Cannot change preallocation mode.\n");
+            error_report("Cannot change preallocation mode");
             return -ENOTSUP;
         } else if (!strcmp(desc->name, BLOCK_OPT_SIZE)) {
             new_size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0);
@@ -2934,47 +3051,74 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
                                         !!s->cipher);
 
             if (encrypt != !!s->cipher) {
-                fprintf(stderr, "Changing the encryption flag is not "
-                        "supported.\n");
+                error_report("Changing the encryption flag is not supported");
                 return -ENOTSUP;
             }
         } else if (!strcmp(desc->name, BLOCK_OPT_CLUSTER_SIZE)) {
             cluster_size = qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE,
                                              cluster_size);
             if (cluster_size != s->cluster_size) {
-                fprintf(stderr, "Changing the cluster size is not "
-                        "supported.\n");
+                error_report("Changing the cluster size is not supported");
                 return -ENOTSUP;
             }
         } else if (!strcmp(desc->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
             lazy_refcounts = qemu_opt_get_bool(opts, BLOCK_OPT_LAZY_REFCOUNTS,
                                                lazy_refcounts);
         } else if (!strcmp(desc->name, BLOCK_OPT_REFCOUNT_BITS)) {
-            error_report("Cannot change refcount entry width");
-            return -ENOTSUP;
+            refcount_bits = qemu_opt_get_number(opts, BLOCK_OPT_REFCOUNT_BITS,
+                                                refcount_bits);
+
+            if (refcount_bits <= 0 || refcount_bits > 64 ||
+                !is_power_of_2(refcount_bits))
+            {
+                error_report("Refcount width must be a power of two and may "
+                             "not exceed 64 bits");
+                return -EINVAL;
+            }
         } else {
-            /* if this assertion fails, this probably means a new option was
+            /* if this point is reached, this probably means a new option was
              * added without having it covered here */
-            assert(false);
+            abort();
         }
 
         desc++;
     }
 
-    if (new_version != old_version) {
+    helper_cb_info = (Qcow2AmendHelperCBInfo){
+        .original_status_cb = status_cb,
+        .original_cb_opaque = cb_opaque,
+        .total_operations = (new_version < old_version)
+                          + (s->refcount_bits != refcount_bits)
+    };
+
+    /* Upgrade first (some features may require compat=1.1) */
     if (new_version > old_version) {
-            /* Upgrade */
         s->qcow_version = new_version;
         ret = qcow2_update_header(bs);
         if (ret < 0) {
             s->qcow_version = old_version;
             return ret;
         }
-        } else {
-            ret = qcow2_downgrade(bs, new_version, status_cb);
-            if (ret < 0) {
-                return ret;
     }
+
+    if (s->refcount_bits != refcount_bits) {
+        int refcount_order = ctz32(refcount_bits);
+        Error *local_error = NULL;
+
+        if (new_version < 3 && refcount_bits != 16) {
+            error_report("Different refcount widths than 16 bits require "
+                         "compatibility level 1.1 or above (use compat=1.1 or "
+                         "greater)");
+            return -EINVAL;
+        }
+
+        helper_cb_info.current_operation = QCOW2_CHANGING_REFCOUNT_ORDER;
+        ret = qcow2_change_refcount_order(bs, refcount_order,
+                                          &qcow2_amend_helper_cb,
+                                          &helper_cb_info, &local_error);
+        if (ret < 0) {
+            error_report_err(local_error);
+            return ret;
         }
     }
 
@@ -2989,9 +3133,9 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
 
     if (s->use_lazy_refcounts != lazy_refcounts) {
         if (lazy_refcounts) {
-            if (s->qcow_version < 3) {
-                fprintf(stderr, "Lazy refcounts only supported with compatibility "
-                        "level 1.1 and above (use compat=1.1 or greater)\n");
+            if (new_version < 3) {
+                error_report("Lazy refcounts only supported with compatibility "
+                             "level 1.1 and above (use compat=1.1 or greater)");
                 return -EINVAL;
             }
             s->compatible_features |= QCOW2_COMPAT_LAZY_REFCOUNTS;
@@ -3025,6 +3169,16 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
         }
     }
 
+    /* Downgrade last (so unsupported features can be removed before) */
+    if (new_version < old_version) {
+        helper_cb_info.current_operation = QCOW2_DOWNGRADING;
+        ret = qcow2_downgrade(bs, new_version, &qcow2_amend_helper_cb,
+                              &helper_cb_info);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     return 0;
 }
 
@@ -3145,6 +3299,7 @@ BlockDriver bdrv_qcow2 = {
     .bdrv_reopen_prepare  = qcow2_reopen_prepare,
     .bdrv_reopen_commit   = qcow2_reopen_commit,
     .bdrv_reopen_abort    = qcow2_reopen_abort,
+    .bdrv_join_options    = qcow2_join_options,
     .bdrv_create        = qcow2_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = qcow2_co_get_block_status,

block/qcow2.h

@@ -529,6 +529,10 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
 int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
                                   int64_t size);
 
+int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
+                                BlockDriverAmendStatusCB *status_cb,
+                                void *cb_opaque, Error **errp);
+
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
                         bool exact_size);
@@ -553,7 +557,8 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
 
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
-                               BlockDriverAmendStatusCB *status_cb);
+                               BlockDriverAmendStatusCB *status_cb,
+                               void *cb_opaque);
 
 /* qcow2-snapshot.c functions */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);

block/quorum.c

@@ -847,7 +847,7 @@ static int parse_read_pattern(const char *opt)
         return QUORUM_READ_PATTERN_QUORUM;
     }
 
-    for (i = 0; i < QUORUM_READ_PATTERN_MAX; i++) {
+    for (i = 0; i < QUORUM_READ_PATTERN__MAX; i++) {
         if (!strcmp(opt, QuorumReadPattern_lookup[i])) {
             return i;
         }
@@ -997,7 +997,7 @@ static void quorum_attach_aio_context(BlockDriverState *bs,
     }
 }
 
-static void quorum_refresh_filename(BlockDriverState *bs)
+static void quorum_refresh_filename(BlockDriverState *bs, QDict *options)
 {
     BDRVQuorumState *s = bs->opaque;
     QDict *opts;

block/raw-posix.c

@@ -500,21 +500,17 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
         goto fail;
     }
     if (!s->use_aio && (bdrv_flags & BDRV_O_NATIVE_AIO)) {
-        error_printf("WARNING: aio=native was specified for '%s', but "
-                     "it requires cache.direct=on, which was not "
-                     "specified. Falling back to aio=threads.\n"
-                     "         This will become an error condition in "
-                     "future QEMU versions.\n",
-                     bs->filename);
+        error_setg(errp, "aio=native was specified, but it requires "
+                         "cache.direct=on, which was not specified.");
+        ret = -EINVAL;
+        goto fail;
     }
 #else
     if (bdrv_flags & BDRV_O_NATIVE_AIO) {
-        error_printf("WARNING: aio=native was specified for '%s', but "
-                     "is not supported in this build. Falling back to "
-                     "aio=threads.\n"
-                     "         This will become an error condition in "
-                     "future QEMU versions.\n",
-                     bs->filename);
+        error_setg(errp, "aio=native was specified, but is not supported "
+                         "in this build.");
+        ret = -EINVAL;
+        goto fail;
     }
 #endif /* !defined(CONFIG_LINUX_AIO) */
 
@@ -1636,7 +1632,7 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
     nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
-                               PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+                               PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
                                &local_err);
     g_free(buf);
     if (local_err) {

block/snapshot.c

@@ -229,6 +229,8 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
                          Error **errp)
 {
     BlockDriver *drv = bs->drv;
+    int ret;
+
     if (!drv) {
         error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
         return -ENOMEDIUM;
@@ -239,18 +241,21 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
     }
 
     /* drain all pending i/o before deleting snapshot */
-    bdrv_drain(bs);
+    bdrv_drained_begin(bs);
 
     if (drv->bdrv_snapshot_delete) {
-        return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
-    }
-    if (bs->file) {
-        return bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
-    }
+        ret = drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
+    } else if (bs->file) {
+        ret = bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
+    } else {
         error_setg(errp, "Block format '%s' used by device '%s' "
                    "does not support internal snapshot deletion",
                    drv->format_name, bdrv_get_device_name(bs));
-    return -ENOTSUP;
+        ret = -ENOTSUP;
+    }
+
+    bdrv_drained_end(bs);
+    return ret;
 }
 
 int bdrv_snapshot_delete_by_id_or_name(BlockDriverState *bs,

blockdev.c

@@ -387,16 +387,6 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
             }
         }
 
-        if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, true)) {
-            *bdrv_flags |= BDRV_O_CACHE_WB;
-        }
-        if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_DIRECT, false)) {
-            *bdrv_flags |= BDRV_O_NOCACHE;
-        }
-        if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
-            *bdrv_flags |= BDRV_O_NO_FLUSH;
-        }
-
         if ((aio = qemu_opt_get(opts, "aio")) != NULL) {
             if (!strcmp(aio, "native")) {
                 *bdrv_flags |= BDRV_O_NATIVE_AIO;
@@ -454,7 +444,7 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
         *detect_zeroes =
             qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
                             qemu_opt_get(opts, "detect-zeroes"),
-                            BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
+                            BLOCKDEV_DETECT_ZEROES_OPTIONS__MAX,
                             BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
                             &local_error);
         if (local_error) {
@@ -490,7 +480,6 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     QDict *interval_dict = NULL;
     QList *interval_list = NULL;
     const char *id;
-    bool has_driver_specific_opts;
     BlockdevDetectZeroesOptions detect_zeroes =
         BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
     const char *throttling_group = NULL;
@@ -514,8 +503,6 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
         qdict_del(bs_opts, "id");
     }
 
-    has_driver_specific_opts = !!qdict_size(bs_opts);
-
     /* extract parameters */
     snapshot = qemu_opt_get_bool(opts, "snapshot", 0);
 
@@ -572,13 +559,11 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     }
 
     if (snapshot) {
-        /* always use cache=unsafe with snapshot */
-        bdrv_flags &= ~BDRV_O_CACHE_MASK;
-        bdrv_flags |= (BDRV_O_SNAPSHOT|BDRV_O_CACHE_WB|BDRV_O_NO_FLUSH);
+        bdrv_flags |= BDRV_O_SNAPSHOT;
     }
 
     /* init */
-    if ((!file || !*file) && !has_driver_specific_opts) {
+    if ((!file || !*file) && !qdict_size(bs_opts)) {
         BlockBackendRootState *blk_rs;
 
         blk = blk_new(qemu_opts_id(opts), errp);
@@ -606,6 +591,20 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
             file = NULL;
         }
 
+        /* bdrv_open() defaults to the values in bdrv_flags (for compatibility
+         * with other callers) rather than what we want as the real defaults.
+         * Apply the defaults here instead. */
+        qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_WB, "on");
+        qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_DIRECT, "off");
+        qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, "off");
+
+        if (snapshot) {
+            /* always use cache=unsafe with snapshot */
+            qdict_put(bs_opts, BDRV_OPT_CACHE_WB, qstring_from_str("on"));
+            qdict_put(bs_opts, BDRV_OPT_CACHE_DIRECT, qstring_from_str("off"));
+            qdict_put(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, qstring_from_str("on"));
+        }
+
         blk = blk_new_open(qemu_opts_id(opts), file, NULL, bs_opts, bdrv_flags,
                            errp);
         if (!blk) {
@@ -3872,18 +3871,6 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "discard",
             .type = QEMU_OPT_STRING,
             .help = "discard operation (ignore/off, unmap/on)",
-        },{
-            .name = BDRV_OPT_CACHE_WB,
-            .type = QEMU_OPT_BOOL,
-            .help = "enables writeback mode for any caches",
-        },{
-            .name = BDRV_OPT_CACHE_DIRECT,
-            .type = QEMU_OPT_BOOL,
-            .help = "enables use of O_DIRECT (bypass the host page cache)",
-        },{
-            .name = BDRV_OPT_CACHE_NO_FLUSH,
-            .type = QEMU_OPT_BOOL,
-            .help = "ignore any flush requests for the device",
         },{
             .name = "aio",
             .type = QEMU_OPT_STRING,
@@ -3991,18 +3978,6 @@ static QemuOptsList qemu_root_bds_opts = {
             .name = "discard",
             .type = QEMU_OPT_STRING,
             .help = "discard operation (ignore/off, unmap/on)",
-        },{
-            .name = "cache.writeback",
-            .type = QEMU_OPT_BOOL,
-            .help = "enables writeback mode for any caches",
-        },{
-            .name = "cache.direct",
-            .type = QEMU_OPT_BOOL,
-            .help = "enables use of O_DIRECT (bypass the host page cache)",
-        },{
-            .name = "cache.no-flush",
-            .type = QEMU_OPT_BOOL,
-            .help = "ignore any flush requests for the device",
         },{
             .name = "aio",
             .type = QEMU_OPT_STRING,

bsd-user/main.c

@@ -938,7 +938,7 @@ int main(int argc, char **argv)
             unsigned long tmp;
             if (fscanf(fp, "%lu", &tmp) == 1) {
                 mmap_min_addr = tmp;
-                qemu_log("host mmap_min_addr=0x%lx\n", mmap_min_addr);
+                qemu_log_mask(CPU_LOG_PAGE, "host mmap_min_addr=0x%lx\n", mmap_min_addr);
             }
             fclose(fp);
         }
@@ -955,7 +955,7 @@ int main(int argc, char **argv)
 
     free(target_environ);
 
-    if (qemu_log_enabled()) {
+    if (qemu_loglevel_mask(CPU_LOG_PAGE)) {
         qemu_log("guest_base  0x%lx\n", guest_base);
         log_page_dump();
 

bsd-user/signal.c

@@ -26,8 +26,6 @@
 #include "qemu.h"
 #include "target_signal.h"
 
-//#define DEBUG_SIGNAL
-
 void signal_init(void)
 {
 }

configure

@@ -2426,6 +2426,14 @@ else
 fi
 
 
+##########################################
+# getifaddrs (for tests/test-io-channel-socket )
+
+have_ifaddrs_h=yes
+if ! check_include "ifaddrs.h" ; then
+  have_ifaddrs_h=no
+fi
+
 ##########################################
 # VTE probe
 
@@ -4758,7 +4766,11 @@ echo "GTK GL support    $gtk_gl"
 echo "GNUTLS support    $gnutls"
 echo "GNUTLS hash       $gnutls_hash"
 echo "libgcrypt         $gcrypt"
-echo "nettle            $nettle ${nettle+($nettle_version)}"
+if test "$nettle" = "yes"; then
+    echo "nettle            $nettle ($nettle_version)"
+else
+    echo "nettle            $nettle"
+fi
 echo "libtasn1          $tasn1"
 echo "VTE support       $vte"
 echo "curses support    $curses"
@@ -5137,6 +5149,9 @@ fi
 if test "$tasn1" = "yes" ; then
   echo "CONFIG_TASN1=y" >> $config_host_mak
 fi
+if test "$have_ifaddrs_h" = "yes" ; then
+    echo "HAVE_IFADDRS_H=y" >> $config_host_mak
+fi
 if test "$vte" = "yes" ; then
   echo "CONFIG_VTE=y" >> $config_host_mak
   echo "VTE_CFLAGS=$vte_cflags" >> $config_host_mak

cpus.c

@@ -1558,22 +1558,29 @@ CpuInfoList *qmp_query_cpus(Error **errp)
         info->value->qom_path = object_get_canonical_path(OBJECT(cpu));
         info->value->thread_id = cpu->thread_id;
 #if defined(TARGET_I386)
-        info->value->has_pc = true;
-        info->value->pc = env->eip + env->segs[R_CS].base;
+        info->value->arch = CPU_INFO_ARCH_X86;
+        info->value->u.x86 = g_new0(CpuInfoX86, 1);
+        info->value->u.x86->pc = env->eip + env->segs[R_CS].base;
 #elif defined(TARGET_PPC)
-        info->value->has_nip = true;
-        info->value->nip = env->nip;
+        info->value->arch = CPU_INFO_ARCH_PPC;
+        info->value->u.ppc = g_new0(CpuInfoPPC, 1);
+        info->value->u.ppc->nip = env->nip;
 #elif defined(TARGET_SPARC)
-        info->value->has_pc = true;
-        info->value->pc = env->pc;
-        info->value->has_npc = true;
-        info->value->npc = env->npc;
+        info->value->arch = CPU_INFO_ARCH_SPARC;
+        info->value->u.sparc = g_new0(CpuInfoSPARC, 1);
+        info->value->u.sparc->pc = env->pc;
+        info->value->u.sparc->npc = env->npc;
 #elif defined(TARGET_MIPS)
-        info->value->has_PC = true;
-        info->value->PC = env->active_tc.PC;
+        info->value->arch = CPU_INFO_ARCH_MIPS;
+        info->value->u.mips = g_new0(CpuInfoMIPS, 1);
+        info->value->u.mips->PC = env->active_tc.PC;
 #elif defined(TARGET_TRICORE)
-        info->value->has_PC = true;
-        info->value->PC = env->PC;
+        info->value->arch = CPU_INFO_ARCH_TRICORE;
+        info->value->u.tricore = g_new0(CpuInfoTricore, 1);
+        info->value->u.tricore->PC = env->PC;
+#else
+        info->value->arch = CPU_INFO_ARCH_OTHER;
+        info->value->u.other = g_new0(CpuInfoOther, 1);
 #endif
 
         /* XXX: waiting for the qapi to support GSList */

crypto/Makefile.objs

@@ -7,6 +7,7 @@ crypto-obj-y += tlscreds.o
 crypto-obj-y += tlscredsanon.o
 crypto-obj-y += tlscredsx509.o
 crypto-obj-y += tlssession.o
+crypto-obj-y += secret.o
 
 # Let the userspace emulators avoid linking gnutls/etc
 crypto-aes-obj-y = aes.o

crypto/cipher.c

@@ -21,19 +21,67 @@
 #include "crypto/cipher.h"
 
 
-static size_t alg_key_len[QCRYPTO_CIPHER_ALG_LAST] = {
+static size_t alg_key_len[QCRYPTO_CIPHER_ALG__MAX] = {
     [QCRYPTO_CIPHER_ALG_AES_128] = 16,
     [QCRYPTO_CIPHER_ALG_AES_192] = 24,
     [QCRYPTO_CIPHER_ALG_AES_256] = 32,
     [QCRYPTO_CIPHER_ALG_DES_RFB] = 8,
 };
 
+static size_t alg_block_len[QCRYPTO_CIPHER_ALG__MAX] = {
+    [QCRYPTO_CIPHER_ALG_AES_128] = 16,
+    [QCRYPTO_CIPHER_ALG_AES_192] = 16,
+    [QCRYPTO_CIPHER_ALG_AES_256] = 16,
+    [QCRYPTO_CIPHER_ALG_DES_RFB] = 8,
+};
+
+static bool mode_need_iv[QCRYPTO_CIPHER_MODE__MAX] = {
+    [QCRYPTO_CIPHER_MODE_ECB] = false,
+    [QCRYPTO_CIPHER_MODE_CBC] = true,
+};
+
+
+size_t qcrypto_cipher_get_block_len(QCryptoCipherAlgorithm alg)
+{
+    if (alg >= G_N_ELEMENTS(alg_key_len)) {
+        return 0;
+    }
+    return alg_block_len[alg];
+}
+
+
+size_t qcrypto_cipher_get_key_len(QCryptoCipherAlgorithm alg)
+{
+    if (alg >= G_N_ELEMENTS(alg_key_len)) {
+        return 0;
+    }
+    return alg_key_len[alg];
+}
+
+
+size_t qcrypto_cipher_get_iv_len(QCryptoCipherAlgorithm alg,
+                                 QCryptoCipherMode mode)
+{
+    if (alg >= G_N_ELEMENTS(alg_block_len)) {
+        return 0;
+    }
+    if (mode >= G_N_ELEMENTS(mode_need_iv)) {
+        return 0;
+    }
+
+    if (mode_need_iv[mode]) {
+        return alg_block_len[alg];
+    }
+    return 0;
+}
+
+
 static bool
 qcrypto_cipher_validate_key_length(QCryptoCipherAlgorithm alg,
                                    size_t nkey,
                                    Error **errp)
 {
-    if ((unsigned)alg >= QCRYPTO_CIPHER_ALG_LAST) {
+    if ((unsigned)alg >= QCRYPTO_CIPHER_ALG__MAX) {
         error_setg(errp, "Cipher algorithm %d out of range",
                    alg);
         return false;
@@ -41,7 +89,7 @@ qcrypto_cipher_validate_key_length(QCryptoCipherAlgorithm alg,
 
     if (alg_key_len[alg] != nkey) {
         error_setg(errp, "Cipher key length %zu should be %zu",
-                   alg_key_len[alg], nkey);
+                   nkey, alg_key_len[alg]);
         return false;
     }
     return true;

crypto/hash.c

@@ -24,12 +24,18 @@
 #include <gnutls/gnutls.h>
 #include <gnutls/crypto.h>
 
-static int qcrypto_hash_alg_map[QCRYPTO_HASH_ALG_LAST] = {
+static int qcrypto_hash_alg_map[QCRYPTO_HASH_ALG__MAX] = {
     [QCRYPTO_HASH_ALG_MD5] = GNUTLS_DIG_MD5,
     [QCRYPTO_HASH_ALG_SHA1] = GNUTLS_DIG_SHA1,
     [QCRYPTO_HASH_ALG_SHA256] = GNUTLS_DIG_SHA256,
 };
 
+static size_t qcrypto_hash_alg_size[QCRYPTO_HASH_ALG__MAX] = {
+    [QCRYPTO_HASH_ALG_MD5] = 16,
+    [QCRYPTO_HASH_ALG_SHA1] = 20,
+    [QCRYPTO_HASH_ALG_SHA256] = 32,
+};
+
 gboolean qcrypto_hash_supports(QCryptoHashAlgorithm alg)
 {
     if (alg < G_N_ELEMENTS(qcrypto_hash_alg_map)) {
@@ -38,6 +44,15 @@ gboolean qcrypto_hash_supports(QCryptoHashAlgorithm alg)
     return false;
 }
 
+size_t qcrypto_hash_digest_len(QCryptoHashAlgorithm alg)
+{
+    if (alg >= G_N_ELEMENTS(qcrypto_hash_alg_size)) {
+        return 0;
+    }
+    return qcrypto_hash_alg_size[alg];
+}
+
+
 int qcrypto_hash_bytesv(QCryptoHashAlgorithm alg,
                         const struct iovec *iov,
                         size_t niov,

crypto/secret.c

@@ -0,0 +1,513 @@
+/*
+ * QEMU crypto secret support
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include "crypto/secret.h"
+#include "crypto/cipher.h"
+#include "qom/object_interfaces.h"
+#include "qemu/base64.h"
+#include "trace.h"
+
+
+static void
+qcrypto_secret_load_data(QCryptoSecret *secret,
+                         uint8_t **output,
+                         size_t *outputlen,
+                         Error **errp)
+{
+    char *data = NULL;
+    size_t length = 0;
+    GError *gerr = NULL;
+
+    *output = NULL;
+    *outputlen = 0;
+
+    if (secret->file) {
+        if (secret->data) {
+            error_setg(errp,
+                       "'file' and 'data' are mutually exclusive");
+            return;
+        }
+        if (!g_file_get_contents(secret->file, &data, &length, &gerr)) {
+            error_setg(errp,
+                       "Unable to read %s: %s",
+                       secret->file, gerr->message);
+            g_error_free(gerr);
+            return;
+        }
+        *output = (uint8_t *)data;
+        *outputlen = length;
+    } else if (secret->data) {
+        *outputlen = strlen(secret->data);
+        *output = (uint8_t *)g_strdup(secret->data);
+    } else {
+        error_setg(errp, "Either 'file' or 'data' must be provided");
+    }
+}
+
+
+static void qcrypto_secret_decrypt(QCryptoSecret *secret,
+                                   const uint8_t *input,
+                                   size_t inputlen,
+                                   uint8_t **output,
+                                   size_t *outputlen,
+                                   Error **errp)
+{
+    uint8_t *key = NULL, *ciphertext = NULL, *iv = NULL;
+    size_t keylen, ciphertextlen, ivlen;
+    QCryptoCipher *aes = NULL;
+    uint8_t *plaintext = NULL;
+
+    *output = NULL;
+    *outputlen = 0;
+
+    if (qcrypto_secret_lookup(secret->keyid,
+                              &key, &keylen,
+                              errp) < 0) {
+        goto cleanup;
+    }
+
+    if (keylen != 32) {
+        error_setg(errp, "Key should be 32 bytes in length");
+        goto cleanup;
+    }
+
+    if (!secret->iv) {
+        error_setg(errp, "IV is required to decrypt secret");
+        goto cleanup;
+    }
+
+    iv = qbase64_decode(secret->iv, -1, &ivlen, errp);
+    if (!iv) {
+        goto cleanup;
+    }
+    if (ivlen != 16) {
+        error_setg(errp, "IV should be 16 bytes in length not %zu",
+                   ivlen);
+        goto cleanup;
+    }
+
+    aes = qcrypto_cipher_new(QCRYPTO_CIPHER_ALG_AES_256,
+                             QCRYPTO_CIPHER_MODE_CBC,
+                             key, keylen,
+                             errp);
+    if (!aes) {
+        goto cleanup;
+    }
+
+    if (qcrypto_cipher_setiv(aes, iv, ivlen, errp) < 0) {
+        goto cleanup;
+    }
+
+    if (secret->format == QCRYPTO_SECRET_FORMAT_BASE64) {
+        ciphertext = qbase64_decode((const gchar*)input,
+                                    inputlen,
+                                    &ciphertextlen,
+                                    errp);
+        if (!ciphertext) {
+            goto cleanup;
+        }
+        plaintext = g_new0(uint8_t, ciphertextlen + 1);
+    } else {
+        ciphertextlen = inputlen;
+        plaintext = g_new0(uint8_t, inputlen + 1);
+    }
+    if (qcrypto_cipher_decrypt(aes,
+                               ciphertext ? ciphertext : input,
+                               plaintext,
+                               ciphertextlen,
+                               errp) < 0) {
+        plaintext = NULL;
+        goto cleanup;
+    }
+
+    if (plaintext[ciphertextlen - 1] > 16 ||
+        plaintext[ciphertextlen - 1] > ciphertextlen) {
+        error_setg(errp, "Incorrect number of padding bytes (%d) "
+                   "found on decrypted data",
+                   (int)plaintext[ciphertextlen - 1]);
+        g_free(plaintext);
+        plaintext = NULL;
+        goto cleanup;
+    }
+
+    /* Even though plaintext may contain arbitrary NUL
+     * ensure it is explicitly NUL terminated.
+     */
+    ciphertextlen -= plaintext[ciphertextlen - 1];
+    plaintext[ciphertextlen] = '\0';
+
+    *output = plaintext;
+    *outputlen = ciphertextlen;
+
+ cleanup:
+    g_free(ciphertext);
+    g_free(iv);
+    g_free(key);
+    qcrypto_cipher_free(aes);
+}
+
+
+static void qcrypto_secret_decode(const uint8_t *input,
+                                  size_t inputlen,
+                                  uint8_t **output,
+                                  size_t *outputlen,
+                                  Error **errp)
+{
+    *output = qbase64_decode((const gchar*)input,
+                             inputlen,
+                             outputlen,
+                             errp);
+}
+
+
+static void
+qcrypto_secret_prop_set_loaded(Object *obj,
+                               bool value,
+                               Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+
+    if (value) {
+        Error *local_err = NULL;
+        uint8_t *input = NULL;
+        size_t inputlen = 0;
+        uint8_t *output = NULL;
+        size_t outputlen = 0;
+
+        qcrypto_secret_load_data(secret, &input, &inputlen, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+        }
+
+        if (secret->keyid) {
+            qcrypto_secret_decrypt(secret, input, inputlen,
+                                   &output, &outputlen, &local_err);
+            g_free(input);
+            if (local_err) {
+                error_propagate(errp, local_err);
+                return;
+            }
+            input = output;
+            inputlen = outputlen;
+        } else {
+            if (secret->format != QCRYPTO_SECRET_FORMAT_RAW) {
+                qcrypto_secret_decode(input, inputlen,
+                                      &output, &outputlen, &local_err);
+                g_free(input);
+                if (local_err) {
+                    error_propagate(errp, local_err);
+                    return;
+                }
+                input = output;
+                inputlen = outputlen;
+            }
+        }
+
+        secret->rawdata = input;
+        secret->rawlen = inputlen;
+    } else {
+        g_free(secret->rawdata);
+        secret->rawlen = 0;
+    }
+}
+
+
+static bool
+qcrypto_secret_prop_get_loaded(Object *obj,
+                               Error **errp G_GNUC_UNUSED)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+    return secret->data != NULL;
+}
+
+
+static void
+qcrypto_secret_prop_set_format(Object *obj,
+                               int value,
+                               Error **errp G_GNUC_UNUSED)
+{
+    QCryptoSecret *creds = QCRYPTO_SECRET(obj);
+
+    creds->format = value;
+}
+
+
+static int
+qcrypto_secret_prop_get_format(Object *obj,
+                               Error **errp G_GNUC_UNUSED)
+{
+    QCryptoSecret *creds = QCRYPTO_SECRET(obj);
+
+    return creds->format;
+}
+
+
+static void
+qcrypto_secret_prop_set_data(Object *obj,
+                             const char *value,
+                             Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+
+    g_free(secret->data);
+    secret->data = g_strdup(value);
+}
+
+
+static char *
+qcrypto_secret_prop_get_data(Object *obj,
+                             Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+    return g_strdup(secret->data);
+}
+
+
+static void
+qcrypto_secret_prop_set_file(Object *obj,
+                             const char *value,
+                             Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+
+    g_free(secret->file);
+    secret->file = g_strdup(value);
+}
+
+
+static char *
+qcrypto_secret_prop_get_file(Object *obj,
+                             Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+    return g_strdup(secret->file);
+}
+
+
+static void
+qcrypto_secret_prop_set_iv(Object *obj,
+                           const char *value,
+                           Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+
+    g_free(secret->iv);
+    secret->iv = g_strdup(value);
+}
+
+
+static char *
+qcrypto_secret_prop_get_iv(Object *obj,
+                           Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+    return g_strdup(secret->iv);
+}
+
+
+static void
+qcrypto_secret_prop_set_keyid(Object *obj,
+                              const char *value,
+                              Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+
+    g_free(secret->keyid);
+    secret->keyid = g_strdup(value);
+}
+
+
+static char *
+qcrypto_secret_prop_get_keyid(Object *obj,
+                              Error **errp)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+    return g_strdup(secret->keyid);
+}
+
+
+static void
+qcrypto_secret_complete(UserCreatable *uc, Error **errp)
+{
+    object_property_set_bool(OBJECT(uc), true, "loaded", errp);
+}
+
+
+static void
+qcrypto_secret_init(Object *obj)
+{
+    object_property_add_bool(obj, "loaded",
+                             qcrypto_secret_prop_get_loaded,
+                             qcrypto_secret_prop_set_loaded,
+                             NULL);
+    object_property_add_enum(obj, "format",
+                             "QCryptoSecretFormat",
+                             QCryptoSecretFormat_lookup,
+                             qcrypto_secret_prop_get_format,
+                             qcrypto_secret_prop_set_format,
+                             NULL);
+    object_property_add_str(obj, "data",
+                            qcrypto_secret_prop_get_data,
+                            qcrypto_secret_prop_set_data,
+                            NULL);
+    object_property_add_str(obj, "file",
+                            qcrypto_secret_prop_get_file,
+                            qcrypto_secret_prop_set_file,
+                            NULL);
+    object_property_add_str(obj, "keyid",
+                            qcrypto_secret_prop_get_keyid,
+                            qcrypto_secret_prop_set_keyid,
+                            NULL);
+    object_property_add_str(obj, "iv",
+                            qcrypto_secret_prop_get_iv,
+                            qcrypto_secret_prop_set_iv,
+                            NULL);
+}
+
+
+static void
+qcrypto_secret_finalize(Object *obj)
+{
+    QCryptoSecret *secret = QCRYPTO_SECRET(obj);
+
+    g_free(secret->iv);
+    g_free(secret->file);
+    g_free(secret->keyid);
+    g_free(secret->rawdata);
+    g_free(secret->data);
+}
+
+static void
+qcrypto_secret_class_init(ObjectClass *oc, void *data)
+{
+    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
+
+    ucc->complete = qcrypto_secret_complete;
+}
+
+
+int qcrypto_secret_lookup(const char *secretid,
+                          uint8_t **data,
+                          size_t *datalen,
+                          Error **errp)
+{
+    Object *obj;
+    QCryptoSecret *secret;
+
+    obj = object_resolve_path_component(
+        object_get_objects_root(), secretid);
+    if (!obj) {
+        error_setg(errp, "No secret with id '%s'", secretid);
+        return -1;
+    }
+
+    secret = (QCryptoSecret *)
+        object_dynamic_cast(obj,
+                            TYPE_QCRYPTO_SECRET);
+    if (!secret) {
+        error_setg(errp, "Object with id '%s' is not a secret",
+                   secretid);
+        return -1;
+    }
+
+    if (!secret->rawdata) {
+        error_setg(errp, "Secret with id '%s' has no data",
+                   secretid);
+        return -1;
+    }
+
+    *data = g_new0(uint8, secret->rawlen + 1);
+    memcpy(*data, secret->rawdata, secret->rawlen);
+    (*data)[secret->rawlen] = '\0';
+    *datalen = secret->rawlen;
+
+    return 0;
+}
+
+
+char *qcrypto_secret_lookup_as_utf8(const char *secretid,
+                                    Error **errp)
+{
+    uint8_t *data;
+    size_t datalen;
+
+    if (qcrypto_secret_lookup(secretid,
+                              &data,
+                              &datalen,
+                              errp) < 0) {
+        return NULL;
+    }
+
+    if (!g_utf8_validate((const gchar*)data, datalen, NULL)) {
+        error_setg(errp,
+                   "Data from secret %s is not valid UTF-8",
+                   secretid);
+        g_free(data);
+        return NULL;
+    }
+
+    return (char *)data;
+}
+
+
+char *qcrypto_secret_lookup_as_base64(const char *secretid,
+                                      Error **errp)
+{
+    uint8_t *data;
+    size_t datalen;
+    char *ret;
+
+    if (qcrypto_secret_lookup(secretid,
+                              &data,
+                              &datalen,
+                              errp) < 0) {
+        return NULL;
+    }
+
+    ret = g_base64_encode(data, datalen);
+    g_free(data);
+    return ret;
+}
+
+
+static const TypeInfo qcrypto_secret_info = {
+    .parent = TYPE_OBJECT,
+    .name = TYPE_QCRYPTO_SECRET,
+    .instance_size = sizeof(QCryptoSecret),
+    .instance_init = qcrypto_secret_init,
+    .instance_finalize = qcrypto_secret_finalize,
+    .class_size = sizeof(QCryptoSecretClass),
+    .class_init = qcrypto_secret_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_USER_CREATABLE },
+        { }
+    }
+};
+
+
+static void
+qcrypto_secret_register_types(void)
+{
+    type_register_static(&qcrypto_secret_info);
+}
+
+
+type_init(qcrypto_secret_register_types);

crypto/tlscredsx509.c

@@ -20,6 +20,7 @@
 
 #include "crypto/tlscredsx509.h"
 #include "crypto/tlscredspriv.h"
+#include "crypto/secret.h"
 #include "qom/object_interfaces.h"
 #include "trace.h"
 
@@ -607,9 +608,30 @@ qcrypto_tls_creds_x509_load(QCryptoTLSCredsX509 *creds,
     }
 
     if (cert != NULL && key != NULL) {
+#if GNUTLS_VERSION_NUMBER >= 0x030111
+        char *password = NULL;
+        if (creds->passwordid) {
+            password = qcrypto_secret_lookup_as_utf8(creds->passwordid,
+                                                     errp);
+            if (!password) {
+                goto cleanup;
+            }
+        }
+        ret = gnutls_certificate_set_x509_key_file2(creds->data,
+                                                    cert, key,
+                                                    GNUTLS_X509_FMT_PEM,
+                                                    password,
+                                                    0);
+        g_free(password);
+#else /* GNUTLS_VERSION_NUMBER < 0x030111 */
+        if (creds->passwordid) {
+            error_setg(errp, "PKCS8 decryption requires GNUTLS >= 3.1.11");
+            goto cleanup;
+        }
         ret = gnutls_certificate_set_x509_key_file(creds->data,
                                                    cert, key,
                                                    GNUTLS_X509_FMT_PEM);
+#endif /* GNUTLS_VERSION_NUMBER < 0x030111 */
         if (ret < 0) {
             error_setg(errp, "Cannot load certificate '%s' & key '%s': %s",
                        cert, key, gnutls_strerror(ret));
@@ -737,6 +759,27 @@ qcrypto_tls_creds_x509_prop_set_sanity(Object *obj,
 }
 
 
+static void
+qcrypto_tls_creds_x509_prop_set_passwordid(Object *obj,
+                                           const char *value,
+                                           Error **errp G_GNUC_UNUSED)
+{
+    QCryptoTLSCredsX509 *creds = QCRYPTO_TLS_CREDS_X509(obj);
+
+    creds->passwordid = g_strdup(value);
+}
+
+
+static char *
+qcrypto_tls_creds_x509_prop_get_passwordid(Object *obj,
+                                           Error **errp G_GNUC_UNUSED)
+{
+    QCryptoTLSCredsX509 *creds = QCRYPTO_TLS_CREDS_X509(obj);
+
+    return g_strdup(creds->passwordid);
+}
+
+
 static bool
 qcrypto_tls_creds_x509_prop_get_sanity(Object *obj,
                                        Error **errp G_GNUC_UNUSED)
@@ -769,6 +812,10 @@ qcrypto_tls_creds_x509_init(Object *obj)
                              qcrypto_tls_creds_x509_prop_get_sanity,
                              qcrypto_tls_creds_x509_prop_set_sanity,
                              NULL);
+    object_property_add_str(obj, "passwordid",
+                            qcrypto_tls_creds_x509_prop_get_passwordid,
+                            qcrypto_tls_creds_x509_prop_set_passwordid,
+                            NULL);
 }
 
 
@@ -777,6 +824,7 @@ qcrypto_tls_creds_x509_finalize(Object *obj)
 {
     QCryptoTLSCredsX509 *creds = QCRYPTO_TLS_CREDS_X509(obj);
 
+    g_free(creds->passwordid);
     qcrypto_tls_creds_x509_unload(creds);
 }
 

default-configs/i386-softmmu.mak

@@ -9,6 +9,11 @@ CONFIG_VGA_CIRRUS=y
 CONFIG_VMWARE_VGA=y
 CONFIG_VIRTIO_VGA=y
 CONFIG_VMMOUSE=y
+CONFIG_IPMI=y
+CONFIG_IPMI_LOCAL=y
+CONFIG_IPMI_EXTERN=y
+CONFIG_ISA_IPMI_KCS=y
+CONFIG_ISA_IPMI_BT=y
 CONFIG_SERIAL=y
 CONFIG_PARALLEL=y
 CONFIG_I8254=y
@@ -46,7 +51,10 @@ CONFIG_APIC=y
 CONFIG_IOAPIC=y
 CONFIG_PVPANIC=y
 CONFIG_MEM_HOTPLUG=y
+CONFIG_NVDIMM=y
+CONFIG_ACPI_NVDIMM=y
 CONFIG_XIO3130=y
 CONFIG_IOH3420=y
 CONFIG_I82801B11=y
 CONFIG_SMBIOS=y
+CONFIG_HYPERV_TESTDEV=$(CONFIG_KVM)

default-configs/x86_64-softmmu.mak

@@ -9,6 +9,11 @@ CONFIG_VGA_CIRRUS=y
 CONFIG_VMWARE_VGA=y
 CONFIG_VIRTIO_VGA=y
 CONFIG_VMMOUSE=y
+CONFIG_IPMI=y
+CONFIG_IPMI_LOCAL=y
+CONFIG_IPMI_EXTERN=y
+CONFIG_ISA_IPMI_KCS=y
+CONFIG_ISA_IPMI_BT=y
 CONFIG_SERIAL=y
 CONFIG_PARALLEL=y
 CONFIG_I8254=y
@@ -46,7 +51,10 @@ CONFIG_APIC=y
 CONFIG_IOAPIC=y
 CONFIG_PVPANIC=y
 CONFIG_MEM_HOTPLUG=y
+CONFIG_NVDIMM=y
+CONFIG_ACPI_NVDIMM=y
 CONFIG_XIO3130=y
 CONFIG_IOH3420=y
 CONFIG_I82801B11=y
 CONFIG_SMBIOS=y
+CONFIG_HYPERV_TESTDEV=$(CONFIG_KVM)

docs/blkdebug.txt

@@ -1,6 +1,6 @@
 Block I/O error injection using blkdebug
 ----------------------------------------
-Copyright (C) 2014 Red Hat Inc
+Copyright (C) 2014-2015 Red Hat Inc
 
 This work is licensed under the terms of the GNU GPL, version 2 or later.  See
 the COPYING file in the top-level directory.
@@ -92,8 +92,9 @@ The core events are:
 
   flush_to_disk - flush the host block device's disk cache
 
-See block/blkdebug.c:event_names[] for the full list of events.  You may need
-to grep block driver source code to understand the meaning of specific events.
+See qapi/block-core.json:BlkdebugEvent for the full list of events.
+You may need to grep block driver source code to understand the
+meaning of specific events.
 
 State transitions
 -----------------

docs/pci_expander_bridge.txt

@@ -23,9 +23,9 @@ A detailed command line would be:
 -m 2G
 -object memory-backend-ram,size=1024M,policy=bind,host-nodes=0,id=ram-node0 -numa node,nodeid=0,cpus=0,memdev=ram-node0
 -object memory-backend-ram,size=1024M,policy=bind,host-nodes=1,id=ram-node1 -numa node,nodeid=1,cpus=1,memdev=ram-node1
--device pxb,id=bridge1,bus=pci.0,numa_node=1,bus_nr=4 -netdev user,id=nd-device e1000,bus=bridge1,addr=0x4,netdev=nd
--device pxb,id=bridge2,bus=pci.0,numa_node=0,bus_nr=8,bus=pci.0 -device e1000,bus=bridge2,addr=0x3
--device pxb,id=bridge3,bus=pci.0,bus_nr=40,bus=pci.0 -drive if=none,id=drive0,file=[img] -device virtio-blk-pci,drive=drive0,scsi=off,bus=bridge3,addr=1
+-device pxb,id=bridge1,bus=pci.0,numa_node=1,bus_nr=4 -netdev user,id=nd -device e1000,bus=bridge1,addr=0x4,netdev=nd
+-device pxb,id=bridge2,bus=pci.0,numa_node=0,bus_nr=8, -device e1000,bus=bridge2,addr=0x3
+-device pxb,id=bridge3,bus=pci.0,bus_nr=40, -drive if=none,id=drive0,file=[img] -device virtio-blk-pci,drive=drive0,scsi=off,bus=bridge3,addr=1
 
 Here you have:
  - 2 NUMA nodes for the guest, 0 and 1. (both mapped to the same NUMA node in host, but you can and should put it in different host NUMA nodes)

docs/qapi-code-gen.txt

@@ -118,17 +118,17 @@ tracking optional fields.
 
 Any name (command, event, type, field, or enum value) beginning with
 "x-" is marked experimental, and may be withdrawn or changed
-incompatibly in a future release.  Downstream vendors may add
-extensions; such extensions should begin with a prefix matching
-"__RFQDN_" (for the reverse-fully-qualified-domain-name of the
-vendor), even if the rest of the name uses dash (example:
-__com.redhat_drive-mirror).  Other than downstream extensions (with
-leading underscore and the use of dots), all names should begin with a
-letter, and contain only ASCII letters, digits, dash, and underscore.
-Names beginning with 'q_' are reserved for the generator: QMP names
-that resemble C keywords or other problematic strings will be munged
-in C to use this prefix.  For example, a field named "default" in
-qapi becomes "q_default" in the generated C code.
+incompatibly in a future release.  All names must begin with a letter,
+and contain only ASCII letters, digits, dash, and underscore.  There
+are two exceptions: enum values may start with a digit, and any
+extensions added by downstream vendors should start with a prefix
+matching "__RFQDN_" (for the reverse-fully-qualified-domain-name of
+the vendor), even if the rest of the name uses dash (example:
+__com.redhat_drive-mirror).  Names beginning with 'q_' are reserved
+for the generator: QMP names that resemble C keywords or other
+problematic strings will be munged in C to use this prefix.  For
+example, a field named "default" in qapi becomes "q_default" in the
+generated C code.
 
 In the rest of this document, usage lines are given for each
 expression type, with literal strings written in lower case and
@@ -160,6 +160,7 @@ The following types are predefined, and map to C as follows:
                        accepts size suffixes
   bool      bool       JSON true or false
   any       QObject *  any JSON value
+  QType     QType      JSON string matching enum QType values
 
 
 === Includes ===
@@ -383,9 +384,6 @@ where each branch of the union names a QAPI type.  For example:
    'data': { 'definition': 'BlockdevOptions',
              'reference': 'str' } }
 
-Just like for a simple union, an implicit C enum 'NameKind' is created
-to enumerate the branches for the alternate 'Name'.
-
 Unlike a union, the discriminator string is never passed on the wire
 for the Client JSON Protocol.  Instead, the value's JSON type serves
 as an implicit discriminator, which in turn means that an alternate
@@ -1053,7 +1051,7 @@ Example:
 
     const char *const example_QAPIEvent_lookup[] = {
         [EXAMPLE_QAPI_EVENT_MY_EVENT] = "MY_EVENT",
-        [EXAMPLE_QAPI_EVENT_MAX] = NULL,
+        [EXAMPLE_QAPI_EVENT__MAX] = NULL,
     };
     $ cat qapi-generated/example-qapi-event.h
 [Uninteresting stuff omitted...]
@@ -1070,7 +1068,7 @@ Example:
 
     typedef enum example_QAPIEvent {
         EXAMPLE_QAPI_EVENT_MY_EVENT = 0,
-        EXAMPLE_QAPI_EVENT_MAX = 1,
+        EXAMPLE_QAPI_EVENT__MAX = 1,
     } example_QAPIEvent;
 
     extern const char *const example_QAPIEvent_lookup[];

docs/specs/fw_cfg.txt

@@ -192,90 +192,7 @@ To check the result, read the "control" field:
                             today due to implementation not being async,
                             but may in the future).
 
-= Host-side API =
-
-The following functions are available to the QEMU programmer for adding
-data to a fw_cfg device during guest initialization (see fw_cfg.h for
-each function's complete prototype):
-
-== fw_cfg_add_bytes() ==
-
-Given a selector key value, starting pointer, and size, create an item
-as a raw "blob" of the given size, available by selecting the given key.
-The data referenced by the starting pointer is only linked, NOT copied,
-into the data structure of the fw_cfg device.
-
-== fw_cfg_add_string() ==
-
-Instead of a starting pointer and size, this function accepts a pointer
-to a NUL-terminated ascii string, and inserts a newly allocated copy of
-the string (including the NUL terminator) into the fw_cfg device data
-structure.
-
-== fw_cfg_add_iXX() ==
-
-Insert an XX-bit item, where XX may be 16, 32, or 64. These functions
-will convert a 16-, 32-, or 64-bit integer to little-endian, then add
-a dynamically allocated copy of the appropriately sized item to fw_cfg
-under the given selector key value.
-
-== fw_cfg_modify_iXX() ==
-
-Modify the value of an XX-bit item (where XX may be 16, 32, or 64).
-Similarly to the corresponding fw_cfg_add_iXX() function set, convert
-a 16-, 32-, or 64-bit integer to little endian, create a dynamically
-allocated copy of the required size, and replace the existing item at
-the given selector key value with the newly allocated one. The previous
-item, assumed to have been allocated during an earlier call to
-fw_cfg_add_iXX() or fw_cfg_modify_iXX() (of the same width XX), is freed
-before the function returns.
-
-== fw_cfg_add_file() ==
-
-Given a filename (i.e., fw_cfg item name), starting pointer, and size,
-create an item as a raw "blob" of the given size. Unlike fw_cfg_add_bytes()
-above, the next available selector key (above 0x0020, FW_CFG_FILE_FIRST)
-will be used, and a new entry will be added to the file directory structure
-(at key 0x0019), containing the item name, blob size, and automatically
-assigned selector key value. The data referenced by the starting pointer
-is only linked, NOT copied, into the fw_cfg data structure.
-
-== fw_cfg_add_file_callback() ==
-
-Like fw_cfg_add_file(), but additionally sets pointers to a callback
-function (and opaque argument), which will be executed host-side by
-QEMU each time a byte is read by the guest from this particular item.
-
-NOTE: The callback function is given the opaque argument set by
-fw_cfg_add_file_callback(), but also the current data offset,
-allowing it the option of only acting upon specific offset values
-(e.g., 0, before the first data byte of the selected item is
-returned to the guest).
-
-== fw_cfg_modify_file() ==
-
-Given a filename (i.e., fw_cfg item name), starting pointer, and size,
-completely replace the configuration item referenced by the given item
-name with the new given blob. If an existing blob is found, its
-callback information is removed, and a pointer to the old data is
-returned to allow the caller to free it, helping avoid memory leaks.
-If a configuration item does not already exist under the given item
-name, a new item will be created as with fw_cfg_add_file(), and NULL
-is returned to the caller. In any case, the data referenced by the
-starting pointer is only linked, NOT copied, into the fw_cfg data
-structure.
-
-== fw_cfg_add_callback() ==
-
-Like fw_cfg_add_bytes(), but additionally sets pointers to a callback
-function (and opaque argument), which will be executed host-side by
-QEMU each time a guest-side write operation to this particular item
-completes fully overwriting the item's data.
-
-NOTE: This function is deprecated, and will be completely removed
-starting with QEMU v2.4.
-
-== Externally Provided Items ==
+= Externally Provided Items =
 
 As of v2.4, "file" fw_cfg items (i.e., items with selector keys above
 FW_CFG_FILE_FIRST, and with a corresponding entry in the fw_cfg file

docs/specs/parallels.txt

@@ -0,0 +1,228 @@
+= License =
+
+Copyright (c) 2015 Denis Lunev
+Copyright (c) 2015 Vladimir Sementsov-Ogievskiy
+
+This work is licensed under the terms of the GNU GPL, version 2 or later.
+See the COPYING file in the top-level directory.
+
+= Parallels Expandable Image File Format =
+
+A Parallels expandable image file consists of three consecutive parts:
+    * header
+    * BAT
+    * data area
+
+All numbers in a Parallels expandable image are stored in little-endian byte
+order.
+
+
+== Definitions ==
+
+    Sector    A 512-byte data chunk.
+
+    Cluster   A data chunk of the size specified in the image header.
+              Currently, the default size is 1MiB (2048 sectors). In previous
+              versions, cluster sizes of 63 sectors, 256 and 252 kilobytes were
+              used.
+
+    BAT       Block Allocation Table, an entity that contains information for
+              guest-to-host I/O data address translation.
+
+
+== Header ==
+
+The header is placed at the start of an image and contains the following
+fields:
+
+Bytes:
+   0 - 15:    magic
+              Must contain "WithoutFreeSpace" or "WithouFreSpacExt".
+
+  16 - 19:    version
+              Must be 2.
+
+  20 - 23:    heads
+              Disk geometry parameter for guest.
+
+  24 - 27:    cylinders
+              Disk geometry parameter for guest.
+
+  28 - 31:    tracks
+              Cluster size, in sectors.
+
+  32 - 35:    nb_bat_entries
+              Disk size, in clusters (BAT size).
+
+  36 - 43:    nb_sectors
+              Disk size, in sectors.
+
+              For "WithoutFreeSpace" images:
+              Only the lowest 4 bytes are used. The highest 4 bytes must be
+              cleared in this case.
+
+              For "WithouFreSpacExt" images, there are no such
+              restrictions.
+
+  44 - 47:    in_use
+              Set to 0x746F6E59 when the image is opened by software in R/W
+              mode; set to 0x312e3276 when the image is closed.
+
+              A zero in this field means that the image was opened by an old
+              version of the software that doesn't support Format Extension
+              (see below).
+
+              Other values are not allowed.
+
+  48 - 51:    data_off
+              An offset, in sectors, from the start of the file to the start of
+              the data area.
+
+              For "WithoutFreeSpace" images:
+              - If data_off is zero, the offset is calculated as the end of BAT
+                table plus some padding to ensure sector size alignment.
+              - If data_off is non-zero, the offset should be aligned to sector
+                size. However it is recommended to align it to cluster size for
+                newly created images.
+
+              For "WithouFreSpacExt" images:
+              data_off must be non-zero and aligned to cluster size.
+
+  52 - 55:    flags
+              Miscellaneous flags.
+
+              Bit 0: Empty Image bit. If set, the image should be
+                     considered clear.
+
+              Bits 2-31: Unused.
+
+  56 - 63:    ext_off
+              Format Extension offset, an offset, in sectors, from the start of
+              the file to the start of the Format Extension Cluster.
+
+              ext_off must meet the same requirements as cluster offsets
+              defined by BAT entries (see below).
+
+
+== BAT ==
+
+BAT is placed immediately after the image header. In the file, BAT is a
+contiguous array of 32-bit unsigned little-endian integers with
+(bat_entries * 4) bytes size.
+
+Each BAT entry contains an offset from the start of the file to the
+corresponding cluster. The offset set in clusters for "WithouFreSpacExt" images
+and in sectors for "WithoutFreeSpace" images.
+
+If a BAT entry is zero, the corresponding cluster is not allocated and should
+be considered as filled with zeroes.
+
+Cluster offsets specified by BAT entries must meet the following requirements:
+    - the value must not be lower than data offset (provided by header.data_off
+      or calculated as specified above),
+    - the value must be lower than the desired file size,
+    - the value must be unique among all BAT entries,
+    - the result of (cluster offset - data offset) must be aligned to cluster
+      size.
+
+
+== Data Area ==
+
+The data area is an area from the data offset (provided by header.data_off or
+calculated as specified above) to the end of the file. It represents a
+contiguous array of clusters. Most of them are allocated by the BAT, some may
+be allocated by the ext_off field in the header while other may be allocated by
+extensions. All clusters allocated by ext_off and extensions should meet the
+same requirements as clusters specified by BAT entries.
+
+
+== Format Extension ==
+
+The Format Extension is an area 1 cluster in size that provides additional
+format features. This cluster is addressed by the ext_off field in the header.
+The format of the Format Extension area is the following:
+
+   0 -  7:    magic
+              Must be 0xAB234CEF23DCEA87
+
+   8 - 23:    m_CheckSum
+              The MD5 checksum of the entire Header Extension cluster except
+              the first 24 bytes.
+
+    The above are followed by feature sections or "extensions". The last
+    extension must be "End of features" (see below).
+
+Each feature section has the following format:
+
+   0 -  7:    magic
+              The identifier of the feature:
+              0x0000000000000000 - End of features
+              0x20385FAE252CB34A - Dirty bitmap
+
+   8 - 15:    flags
+              External flags for extension:
+
+              Bit 0: NECESSARY
+                     If the software cannot load the extension (due to an
+                     unknown magic number or error), the file should not be
+                     changed. If this flag is unset and there is an error on
+                     loading the extension, said extension should be dropped.
+
+              Bit 1: TRANSIT
+                     If there is an unknown extension with this flag set,
+                     said extension should be left as is.
+
+              If neither NECESSARY nor TRANSIT are set, the extension should be
+              dropped.
+
+  16 - 19:    data_size
+              The size of the following feature data, in bytes.
+
+  20 - 23:    unused32
+              Align header to 8 bytes boundary.
+
+  variable:   data (data_size bytes)
+
+    The above is followed by padding to the next 8 bytes boundary, then the
+    next extension starts.
+
+    The last extension must be "End of features" with all the fields set to 0.
+
+
+=== Dirty bitmaps feature ===
+
+This feature provides a way of storing dirty bitmaps in the image. The fields
+of its data area are:
+
+   0 -  7:    size
+              The bitmap size, should be equal to disk size in sectors.
+
+   8 - 23:    id
+              An identifier for backup consistency checking.
+
+  24 - 27:    granularity
+              Bitmap granularity, in sectors. I.e., the number of sectors
+              corresponding to one bit of the bitmap. Granularity must be
+              a power of 2.
+
+  28 - 31:    l1_size
+              The number of entries in the L1 table of the bitmap.
+
+  variable:   l1 (64 * l1_size bytes)
+              L1 offset table (in bytes)
+
+A dirty bitmap is stored using a one-level structure for the mapping to host
+clusters - an L1 table.
+
+Given an offset in bytes into the bitmap data, the offset in bytes into the
+image file can be obtained as follows:
+
+    offset = l1_table[offset / cluster_size] + (offset % cluster_size)
+
+If an L1 table entry is 0, the corresponding cluster of the bitmap is assumed
+to be zero.
+
+If an L1 table entry is 1, the corresponding cluster of the bitmap is assumed
+to have all bits set.
+
+If an L1 table entry is not 0 or 1, it allocates a cluster from the data area.

exec.c

@@ -88,9 +88,6 @@ static MemoryRegion io_mem_unassigned;
  */
 #define RAM_RESIZEABLE (1 << 2)
 
-/* RAM is backed by an mmapped file.
- */
-#define RAM_FILE (1 << 3)
 #endif
 
 struct CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus);
@@ -393,18 +390,6 @@ address_space_translate_internal(AddressSpaceDispatch *d, hwaddr addr, hwaddr *x
     return section;
 }
 
-static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
-{
-    if (memory_region_is_ram(mr)) {
-        return !(is_write && mr->readonly);
-    }
-    if (memory_region_is_romd(mr)) {
-        return !is_write;
-    }
-
-    return false;
-}
-
 /* Called from RCU critical section */
 MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,
                                       hwaddr *xlat, hwaddr *plen,
@@ -873,7 +858,7 @@ void cpu_abort(CPUState *cpu, const char *fmt, ...)
     vfprintf(stderr, fmt, ap);
     fprintf(stderr, "\n");
     cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_FPU | CPU_DUMP_CCOP);
-    if (qemu_log_enabled()) {
+    if (qemu_log_separate()) {
         qemu_log("qemu: fatal: ");
         qemu_log_vprintf(fmt, ap2);
         qemu_log("\n");
@@ -1601,7 +1586,6 @@ ram_addr_t qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
     new_block->used_length = size;
     new_block->max_length = size;
     new_block->flags = share ? RAM_SHARED : 0;
-    new_block->flags |= RAM_FILE;
     new_block->host = file_ram_alloc(new_block, size,
                                      mem_path, errp);
     if (!new_block->host) {
@@ -1676,25 +1660,6 @@ ram_addr_t qemu_ram_alloc_resizeable(ram_addr_t size, ram_addr_t maxsz,
     return qemu_ram_alloc_internal(size, maxsz, resized, NULL, true, mr, errp);
 }
 
-void qemu_ram_free_from_ptr(ram_addr_t addr)
-{
-    RAMBlock *block;
-
-    qemu_mutex_lock_ramlist();
-    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-        if (addr == block->offset) {
-            QLIST_REMOVE_RCU(block, next);
-            ram_list.mru_block = NULL;
-            /* Write list before version */
-            smp_wmb();
-            ram_list.version++;
-            g_free_rcu(block, rcu);
-            break;
-        }
-    }
-    qemu_mutex_unlock_ramlist();
-}
-
 static void reclaim_ramblock(RAMBlock *block)
 {
     if (block->flags & RAM_PREALLOC) {
@@ -1703,11 +1668,7 @@ static void reclaim_ramblock(RAMBlock *block)
         xen_invalidate_map_cache_entry(block->host);
 #ifndef _WIN32
     } else if (block->fd >= 0) {
-        if (block->flags & RAM_FILE) {
         qemu_ram_munmap(block->host, block->max_length);
-        } else {
-            munmap(block->host, block->max_length);
-        }
         close(block->fd);
 #endif
     } else {
@@ -1813,19 +1774,11 @@ void *qemu_get_ram_block_host_ptr(ram_addr_t addr)
  * or address_space_rw instead. For local memory (e.g. video ram) that the
  * device owns, use memory_region_get_ram_ptr.
  *
- * By the time this function returns, the returned pointer is not protected
- * by RCU anymore.  If the caller is not within an RCU critical section and
- * does not hold the iothread lock, it must have other means of protecting the
- * pointer, such as a reference to the region that includes the incoming
- * ram_addr_t.
+ * Called within RCU critical section.
  */
 void *qemu_get_ram_ptr(ram_addr_t addr)
 {
-    RAMBlock *block;
-    void *ptr;
-
-    rcu_read_lock();
-    block = qemu_get_ram_block(addr);
+    RAMBlock *block = qemu_get_ram_block(addr);
 
     if (xen_enabled() && block->host == NULL) {
         /* We need to check if the requested address is in the RAM
@@ -1833,52 +1786,44 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
          * In that case just map until the end of the page.
          */
         if (block->offset == 0) {
-            ptr = xen_map_cache(addr, 0, 0);
-            goto unlock;
+            return xen_map_cache(addr, 0, 0);
         }
 
         block->host = xen_map_cache(block->offset, block->max_length, 1);
     }
-    ptr = ramblock_ptr(block, addr - block->offset);
-
-unlock:
-    rcu_read_unlock();
-    return ptr;
+    return ramblock_ptr(block, addr - block->offset);
 }
 
 /* Return a host pointer to guest's ram. Similar to qemu_get_ram_ptr
  * but takes a size argument.
  *
- * By the time this function returns, the returned pointer is not protected
- * by RCU anymore.  If the caller is not within an RCU critical section and
- * does not hold the iothread lock, it must have other means of protecting the
- * pointer, such as a reference to the region that includes the incoming
- * ram_addr_t.
+ * Called within RCU critical section.
  */
 static void *qemu_ram_ptr_length(ram_addr_t addr, hwaddr *size)
 {
-    void *ptr;
+    RAMBlock *block;
+    ram_addr_t offset_inside_block;
     if (*size == 0) {
         return NULL;
     }
-    if (xen_enabled()) {
+
+    block = qemu_get_ram_block(addr);
+    offset_inside_block = addr - block->offset;
+    *size = MIN(*size, block->max_length - offset_inside_block);
+
+    if (xen_enabled() && block->host == NULL) {
+        /* We need to check if the requested address is in the RAM
+         * because we don't want to map the entire memory in QEMU.
+         * In that case just map the requested area.
+         */
+        if (block->offset == 0) {
             return xen_map_cache(addr, *size, 1);
-    } else {
-        RAMBlock *block;
-        rcu_read_lock();
-        QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-            if (addr - block->offset < block->max_length) {
-                if (addr - block->offset + *size > block->max_length)
-                    *size = block->max_length - addr + block->offset;
-                ptr = ramblock_ptr(block, addr - block->offset);
-                rcu_read_unlock();
-                return ptr;
-            }
         }
 
-        fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
-        abort();
+        block->host = xen_map_cache(block->offset, block->max_length, 1);
     }
+
+    return ramblock_ptr(block, offset_inside_block);
 }
 
 /*
@@ -1981,6 +1926,7 @@ MemoryRegion *qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr)
     return block->mr;
 }
 
+/* Called within RCU critical section.  */
 static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
                                uint64_t val, unsigned size)
 {
@@ -2511,24 +2457,20 @@ static bool prepare_mmio_access(MemoryRegion *mr)
     return release_lock;
 }
 
-MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
-                             uint8_t *buf, int len, bool is_write)
+/* Called within RCU critical section.  */
+static MemTxResult address_space_write_continue(AddressSpace *as, hwaddr addr,
+                                                MemTxAttrs attrs,
+                                                const uint8_t *buf,
+                                                int len, hwaddr addr1,
+                                                hwaddr l, MemoryRegion *mr)
 {
-    hwaddr l;
     uint8_t *ptr;
     uint64_t val;
-    hwaddr addr1;
-    MemoryRegion *mr;
     MemTxResult result = MEMTX_OK;
     bool release_lock = false;
 
-    rcu_read_lock();
-    while (len > 0) {
-        l = len;
-        mr = address_space_translate(as, addr, &addr1, &l, is_write);
-
-        if (is_write) {
-            if (!memory_access_is_direct(mr, is_write)) {
+    for (;;) {
+        if (!memory_access_is_direct(mr, true)) {
             release_lock |= prepare_mmio_access(mr);
             l = memory_access_size(mr, l, addr1);
             /* XXX: could force current_cpu to NULL to avoid
@@ -2568,8 +2510,60 @@ MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
             memcpy(ptr, buf, l);
             invalidate_and_set_dirty(mr, addr1, l);
         }
-        } else {
-            if (!memory_access_is_direct(mr, is_write)) {
+
+        if (release_lock) {
+            qemu_mutex_unlock_iothread();
+            release_lock = false;
+        }
+
+        len -= l;
+        buf += l;
+        addr += l;
+
+        if (!len) {
+            break;
+        }
+
+        l = len;
+        mr = address_space_translate(as, addr, &addr1, &l, true);
+    }
+
+    return result;
+}
+
+MemTxResult address_space_write(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
+                                const uint8_t *buf, int len)
+{
+    hwaddr l;
+    hwaddr addr1;
+    MemoryRegion *mr;
+    MemTxResult result = MEMTX_OK;
+
+    if (len > 0) {
+        rcu_read_lock();
+        l = len;
+        mr = address_space_translate(as, addr, &addr1, &l, true);
+        result = address_space_write_continue(as, addr, attrs, buf, len,
+                                              addr1, l, mr);
+        rcu_read_unlock();
+    }
+
+    return result;
+}
+
+/* Called within RCU critical section.  */
+MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
+                                        MemTxAttrs attrs, uint8_t *buf,
+                                        int len, hwaddr addr1, hwaddr l,
+                                        MemoryRegion *mr)
+{
+    uint8_t *ptr;
+    uint64_t val;
+    MemTxResult result = MEMTX_OK;
+    bool release_lock = false;
+
+    for (;;) {
+        if (!memory_access_is_direct(mr, false)) {
             /* I/O case */
             release_lock |= prepare_mmio_access(mr);
             l = memory_access_size(mr, l, addr1);
@@ -2606,7 +2600,6 @@ MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
             ptr = qemu_get_ram_ptr(mr->ram_addr + addr1);
             memcpy(buf, ptr, l);
         }
-        }
 
         if (release_lock) {
             qemu_mutex_unlock_iothread();
@@ -2616,25 +2609,48 @@ MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
         len -= l;
         buf += l;
         addr += l;
+
+        if (!len) {
+            break;
+        }
+
+        l = len;
+        mr = address_space_translate(as, addr, &addr1, &l, false);
     }
-    rcu_read_unlock();
 
     return result;
 }
 
-MemTxResult address_space_write(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
-                                const uint8_t *buf, int len)
+MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
+                                    MemTxAttrs attrs, uint8_t *buf, int len)
 {
-    return address_space_rw(as, addr, attrs, (uint8_t *)buf, len, true);
+    hwaddr l;
+    hwaddr addr1;
+    MemoryRegion *mr;
+    MemTxResult result = MEMTX_OK;
+
+    if (len > 0) {
+        rcu_read_lock();
+        l = len;
+        mr = address_space_translate(as, addr, &addr1, &l, false);
+        result = address_space_read_continue(as, addr, attrs, buf, len,
+                                             addr1, l, mr);
+        rcu_read_unlock();
+    }
+
+    return result;
 }
 
-MemTxResult address_space_read(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
-                               uint8_t *buf, int len)
+MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
+                             uint8_t *buf, int len, bool is_write)
 {
-    return address_space_rw(as, addr, attrs, buf, len, false);
+    if (is_write) {
+        return address_space_write(as, addr, attrs, (uint8_t *)buf, len);
+    } else {
+        return address_space_read(as, addr, attrs, (uint8_t *)buf, len);
+    }
 }
 
-
 void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf,
                             int len, int is_write)
 {
@@ -2825,6 +2841,7 @@ void *address_space_map(AddressSpace *as,
     hwaddr l, xlat, base;
     MemoryRegion *mr, *this_mr;
     ram_addr_t raddr;
+    void *ptr;
 
     if (len == 0) {
         return NULL;
@@ -2876,9 +2893,11 @@ void *address_space_map(AddressSpace *as,
     }
 
     memory_region_ref(mr);
-    rcu_read_unlock();
     *plen = done;
-    return qemu_ram_ptr_length(raddr + base, plen);
+    ptr = qemu_ram_ptr_length(raddr + base, plen);
+    rcu_read_unlock();
+
+    return ptr;
 }
 
 /* Unmaps a memory region previously mapped by address_space_map().

hmp.c

@@ -311,17 +311,25 @@ void hmp_info_cpus(Monitor *mon, const QDict *qdict)
 
         monitor_printf(mon, "%c CPU #%" PRId64 ":", active, cpu->value->CPU);
 
-        if (cpu->value->has_pc) {
-            monitor_printf(mon, " pc=0x%016" PRIx64, cpu->value->pc);
-        }
-        if (cpu->value->has_nip) {
-            monitor_printf(mon, " nip=0x%016" PRIx64, cpu->value->nip);
-        }
-        if (cpu->value->has_npc) {
-            monitor_printf(mon, " npc=0x%016" PRIx64, cpu->value->npc);
-        }
-        if (cpu->value->has_PC) {
-            monitor_printf(mon, " PC=0x%016" PRIx64, cpu->value->PC);
+        switch (cpu->value->arch) {
+        case CPU_INFO_ARCH_X86:
+            monitor_printf(mon, " pc=0x%016" PRIx64, cpu->value->u.x86->pc);
+            break;
+        case CPU_INFO_ARCH_PPC:
+            monitor_printf(mon, " nip=0x%016" PRIx64, cpu->value->u.ppc->nip);
+            break;
+        case CPU_INFO_ARCH_SPARC:
+            monitor_printf(mon, " pc=0x%016" PRIx64, cpu->value->u.sparc->pc);
+            monitor_printf(mon, " npc=0x%016" PRIx64, cpu->value->u.sparc->npc);
+            break;
+        case CPU_INFO_ARCH_MIPS:
+            monitor_printf(mon, " PC=0x%016" PRIx64, cpu->value->u.mips->PC);
+            break;
+        case CPU_INFO_ARCH_TRICORE:
+            monitor_printf(mon, " PC=0x%016" PRIx64, cpu->value->u.tricore->PC);
+            break;
+        default:
+            break;
         }
 
         if (cpu->value->halted) {
@@ -855,7 +863,7 @@ void hmp_info_tpm(Monitor *mon, const QDict *qdict)
                            tpo->has_cancel_path ? ",cancel-path=" : "",
                            tpo->has_cancel_path ? tpo->cancel_path : "");
             break;
-        case TPM_TYPE_OPTIONS_KIND_MAX:
+        case TPM_TYPE_OPTIONS_KIND__MAX:
             break;
         }
         monitor_printf(mon, "\n");
@@ -1203,7 +1211,7 @@ void hmp_migrate_set_capability(Monitor *mon, const QDict *qdict)
     MigrationCapabilityStatusList *caps = g_malloc0(sizeof(*caps));
     int i;
 
-    for (i = 0; i < MIGRATION_CAPABILITY_MAX; i++) {
+    for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
         if (strcmp(cap, MigrationCapability_lookup[i]) == 0) {
             caps->value = g_malloc0(sizeof(*caps->value));
             caps->value->capability = i;
@@ -1214,7 +1222,7 @@ void hmp_migrate_set_capability(Monitor *mon, const QDict *qdict)
         }
     }
 
-    if (i == MIGRATION_CAPABILITY_MAX) {
+    if (i == MIGRATION_CAPABILITY__MAX) {
         error_setg(&err, QERR_INVALID_PARAMETER, cap);
     }
 
@@ -1239,7 +1247,7 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
     bool has_x_cpu_throttle_increment = false;
     int i;
 
-    for (i = 0; i < MIGRATION_PARAMETER_MAX; i++) {
+    for (i = 0; i < MIGRATION_PARAMETER__MAX; i++) {
         if (strcmp(param, MigrationParameter_lookup[i]) == 0) {
             switch (i) {
             case MIGRATION_PARAMETER_COMPRESS_LEVEL:
@@ -1268,7 +1276,7 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
         }
     }
 
-    if (i == MIGRATION_PARAMETER_MAX) {
+    if (i == MIGRATION_PARAMETER__MAX) {
         error_setg(&err, QERR_INVALID_PARAMETER, param);
     }
 
@@ -1368,7 +1376,7 @@ void hmp_change(Monitor *mon, const QDict *qdict)
         if (read_only) {
             read_only_mode =
                 qapi_enum_parse(BlockdevChangeReadOnlyMode_lookup,
-                                read_only, BLOCKDEV_CHANGE_READ_ONLY_MODE_MAX,
+                                read_only, BLOCKDEV_CHANGE_READ_ONLY_MODE__MAX,
                                 BLOCKDEV_CHANGE_READ_ONLY_MODE_RETAIN, &err);
             if (err) {
                 hmp_handle_error(mon, &err);
@@ -1771,7 +1779,7 @@ void hmp_sendkey(Monitor *mon, const QDict *qdict)
             keylist->value->u.number = value;
         } else {
             int idx = index_from_key(keyname_buf);
-            if (idx == Q_KEY_CODE_MAX) {
+            if (idx == Q_KEY_CODE__MAX) {
                 goto err_out;
             }
             keylist->value->type = KEY_VALUE_KIND_QCODE;

hw/9pfs/virtio-9p-coth.c

@@ -36,6 +36,6 @@ static int coroutine_enter_func(void *arg)
 void co_run_in_worker_bh(void *opaque)
 {
     Coroutine *co = opaque;
-    thread_pool_submit_aio(qemu_get_aio_context()->thread_pool,
+    thread_pool_submit_aio(aio_get_thread_pool(qemu_get_aio_context()),
                            coroutine_enter_func, co, coroutine_enter_cb, co);
 }

hw/Makefile.objs

@@ -13,6 +13,7 @@ devices-dirs-$(CONFIG_SOFTMMU) += ide/
 devices-dirs-$(CONFIG_SOFTMMU) += input/
 devices-dirs-$(CONFIG_SOFTMMU) += intc/
 devices-dirs-$(CONFIG_IPACK) += ipack/
+devices-dirs-$(CONFIG_IPMI) += ipmi/
 devices-dirs-$(CONFIG_SOFTMMU) += isa/
 devices-dirs-$(CONFIG_SOFTMMU) += misc/
 devices-dirs-$(CONFIG_SOFTMMU) += net/

hw/acpi/Makefile.objs

@@ -2,6 +2,7 @@ common-obj-$(CONFIG_ACPI_X86) += core.o piix4.o pcihp.o
 common-obj-$(CONFIG_ACPI_X86_ICH) += ich9.o tco.o
 common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu_hotplug.o
 common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o
+common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o
 common-obj-$(CONFIG_ACPI) += acpi_interface.o
 common-obj-$(CONFIG_ACPI) += bios-linker-loader.o
 common-obj-$(CONFIG_ACPI) += aml-build.o

hw/acpi/aml-build.c

@@ -427,6 +427,41 @@ Aml *aml_arg(int pos)
     return var;
 }
 
+/* ACPI 2.0a: 17.2.4.4 Type 2 Opcodes Encoding: DefToInteger */
+Aml *aml_to_integer(Aml *arg)
+{
+    Aml *var = aml_opcode(0x99 /* ToIntegerOp */);
+    aml_append(var, arg);
+    build_append_byte(var->buf, 0x00 /* NullNameOp */);
+    return var;
+}
+
+/* ACPI 2.0a: 17.2.4.4 Type 2 Opcodes Encoding: DefToHexString */
+Aml *aml_to_hexstring(Aml *src, Aml *dst)
+{
+    Aml *var = aml_opcode(0x98 /* ToHexStringOp */);
+    aml_append(var, src);
+    if (dst) {
+        aml_append(var, dst);
+    } else {
+        build_append_byte(var->buf, 0x00 /* NullNameOp */);
+    }
+    return var;
+}
+
+/* ACPI 2.0a: 17.2.4.4 Type 2 Opcodes Encoding: DefToBuffer */
+Aml *aml_to_buffer(Aml *src, Aml *dst)
+{
+    Aml *var = aml_opcode(0x96 /* ToBufferOp */);
+    aml_append(var, src);
+    if (dst) {
+        aml_append(var, dst);
+    } else {
+        build_append_byte(var->buf, 0x00 /* NullNameOp */);
+    }
+    return var;
+}
+
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefStore */
 Aml *aml_store(Aml *val, Aml *target)
 {
@@ -436,44 +471,64 @@ Aml *aml_store(Aml *val, Aml *target)
     return var;
 }
 
-/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefAnd */
-Aml *aml_and(Aml *arg1, Aml *arg2)
+/**
+ * build_opcode_2arg_dst:
+ * @op: 1-byte opcode
+ * @arg1: 1st operand
+ * @arg2: 2nd operand
+ * @dst: optional target to store to, set to NULL if it's not required
+ *
+ * An internal helper to compose AML terms that have
+ *   "Op Operand Operand Target"
+ * pattern.
+ *
+ * Returns: The newly allocated and composed according to patter Aml object.
+ */
+static Aml *
+build_opcode_2arg_dst(uint8_t op, Aml *arg1, Aml *arg2, Aml *dst)
 {
-    Aml *var = aml_opcode(0x7B /* AndOp */);
+    Aml *var = aml_opcode(op);
     aml_append(var, arg1);
     aml_append(var, arg2);
+    if (dst) {
+        aml_append(var, dst);
+    } else {
         build_append_byte(var->buf, 0x00 /* NullNameOp */);
+    }
     return var;
 }
 
-/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefOr */
-Aml *aml_or(Aml *arg1, Aml *arg2)
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefAnd */
+Aml *aml_and(Aml *arg1, Aml *arg2, Aml *dst)
 {
-    Aml *var = aml_opcode(0x7D /* OrOp */);
+    return build_opcode_2arg_dst(0x7B /* AndOp */, arg1, arg2, dst);
+}
+
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefOr */
+Aml *aml_or(Aml *arg1, Aml *arg2, Aml *dst)
+{
+    return build_opcode_2arg_dst(0x7D /* OrOp */, arg1, arg2, dst);
+}
+
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefLOr */
+Aml *aml_lor(Aml *arg1, Aml *arg2)
+{
+    Aml *var = aml_opcode(0x91 /* LOrOp */);
     aml_append(var, arg1);
     aml_append(var, arg2);
-    build_append_byte(var->buf, 0x00 /* NullNameOp */);
     return var;
 }
 
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefShiftLeft */
 Aml *aml_shiftleft(Aml *arg1, Aml *count)
 {
-    Aml *var = aml_opcode(0x79 /* ShiftLeftOp */);
-    aml_append(var, arg1);
-    aml_append(var, count);
-    build_append_byte(var->buf, 0x00); /* NullNameOp */
-    return var;
+    return build_opcode_2arg_dst(0x79 /* ShiftLeftOp */, arg1, count, NULL);
 }
 
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefShiftRight */
-Aml *aml_shiftright(Aml *arg1, Aml *count)
+Aml *aml_shiftright(Aml *arg1, Aml *count, Aml *dst)
 {
-    Aml *var = aml_opcode(0x7A /* ShiftRightOp */);
-    aml_append(var, arg1);
-    aml_append(var, count);
-    build_append_byte(var->buf, 0x00); /* NullNameOp */
-    return var;
+    return build_opcode_2arg_dst(0x7A /* ShiftRightOp */, arg1, count, dst);
 }
 
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefLLess */
@@ -486,13 +541,15 @@ Aml *aml_lless(Aml *arg1, Aml *arg2)
 }
 
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefAdd */
-Aml *aml_add(Aml *arg1, Aml *arg2)
+Aml *aml_add(Aml *arg1, Aml *arg2, Aml *dst)
 {
-    Aml *var = aml_opcode(0x72 /* AddOp */);
-    aml_append(var, arg1);
-    aml_append(var, arg2);
-    build_append_byte(var->buf, 0x00 /* NullNameOp */);
-    return var;
+    return build_opcode_2arg_dst(0x72 /* AddOp */, arg1, arg2, dst);
+}
+
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefSubtract */
+Aml *aml_subtract(Aml *arg1, Aml *arg2, Aml *dst)
+{
+    return build_opcode_2arg_dst(0x74 /* SubtractOp */, arg1, arg2, dst);
 }
 
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefIncrement */
@@ -503,14 +560,18 @@ Aml *aml_increment(Aml *arg)
     return var;
 }
 
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefDecrement */
+Aml *aml_decrement(Aml *arg)
+{
+    Aml *var = aml_opcode(0x76 /* DecrementOp */);
+    aml_append(var, arg);
+    return var;
+}
+
 /* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefIndex */
 Aml *aml_index(Aml *arg1, Aml *idx)
 {
-    Aml *var = aml_opcode(0x88 /* IndexOp */);
-    aml_append(var, arg1);
-    aml_append(var, idx);
-    build_append_byte(var->buf, 0x00 /* NullNameOp */);
-    return var;
+    return build_opcode_2arg_dst(0x88 /* IndexOp */, arg1, idx, NULL);
 }
 
 /* ACPI 1.0b: 16.2.5.3 Type 1 Opcodes Encoding: DefNotify */
@@ -522,6 +583,14 @@ Aml *aml_notify(Aml *arg1, Aml *arg2)
     return var;
 }
 
+/* helper to call method with 1 argument */
+Aml *aml_call0(const char *method)
+{
+    Aml *var = aml_alloc();
+    build_append_namestring(var->buf, "%s", method);
+    return var;
+}
+
 /* helper to call method with 1 argument */
 Aml *aml_call1(const char *method, Aml *arg1)
 {
@@ -564,6 +633,94 @@ Aml *aml_call4(const char *method, Aml *arg1, Aml *arg2, Aml *arg3, Aml *arg4)
     return var;
 }
 
+/*
+ * ACPI 5.0: 6.4.3.8.1 GPIO Connection Descriptor
+ * Type 1, Large Item Name 0xC
+ */
+
+static Aml *aml_gpio_connection(AmlGpioConnectionType type,
+                                AmlConsumerAndProducer con_and_pro,
+                                uint8_t flags, AmlPinConfig pin_config,
+                                uint16_t output_drive,
+                                uint16_t debounce_timeout,
+                                const uint32_t pin_list[], uint32_t pin_count,
+                                const char *resource_source_name,
+                                const uint8_t *vendor_data,
+                                uint16_t vendor_data_len)
+{
+    Aml *var = aml_alloc();
+    const uint16_t min_desc_len = 0x16;
+    uint16_t resource_source_name_len, length;
+    uint16_t pin_table_offset, resource_source_name_offset, vendor_data_offset;
+    uint32_t i;
+
+    assert(resource_source_name);
+    resource_source_name_len = strlen(resource_source_name) + 1;
+    length = min_desc_len + resource_source_name_len + vendor_data_len;
+    pin_table_offset = min_desc_len + 1;
+    resource_source_name_offset = pin_table_offset + pin_count * 2;
+    vendor_data_offset = resource_source_name_offset + resource_source_name_len;
+
+    build_append_byte(var->buf, 0x8C);  /* GPIO Connection Descriptor */
+    build_append_int_noprefix(var->buf, length, 2); /* Length */
+    build_append_byte(var->buf, 1);     /* Revision ID */
+    build_append_byte(var->buf, type);  /* GPIO Connection Type */
+    /* General Flags (2 bytes) */
+    build_append_int_noprefix(var->buf, con_and_pro, 2);
+    /* Interrupt and IO Flags (2 bytes) */
+    build_append_int_noprefix(var->buf, flags, 2);
+    /* Pin Configuration 0 = Default 1 = Pull-up 2 = Pull-down 3 = No Pull */
+    build_append_byte(var->buf, pin_config);
+    /* Output Drive Strength (2 bytes) */
+    build_append_int_noprefix(var->buf, output_drive, 2);
+    /* Debounce Timeout (2 bytes) */
+    build_append_int_noprefix(var->buf, debounce_timeout, 2);
+    /* Pin Table Offset (2 bytes) */
+    build_append_int_noprefix(var->buf, pin_table_offset, 2);
+    build_append_byte(var->buf, 0);     /* Resource Source Index */
+    /* Resource Source Name Offset (2 bytes) */
+    build_append_int_noprefix(var->buf, resource_source_name_offset, 2);
+    /* Vendor Data Offset (2 bytes) */
+    build_append_int_noprefix(var->buf, vendor_data_offset, 2);
+    /* Vendor Data Length (2 bytes) */
+    build_append_int_noprefix(var->buf, vendor_data_len, 2);
+    /* Pin Number (2n bytes)*/
+    for (i = 0; i < pin_count; i++) {
+        build_append_int_noprefix(var->buf, pin_list[i], 2);
+    }
+
+    /* Resource Source Name */
+    build_append_namestring(var->buf, "%s", resource_source_name);
+    build_append_byte(var->buf, '\0');
+
+    /* Vendor-defined Data */
+    if (vendor_data != NULL) {
+        g_array_append_vals(var->buf, vendor_data, vendor_data_len);
+    }
+
+    return var;
+}
+
+/*
+ * ACPI 5.0: 19.5.53
+ * GpioInt(GPIO Interrupt Connection Resource Descriptor Macro)
+ */
+Aml *aml_gpio_int(AmlConsumerAndProducer con_and_pro,
+                  AmlLevelAndEdge edge_level,
+                  AmlActiveHighAndLow active_level, AmlShared shared,
+                  AmlPinConfig pin_config, uint16_t debounce_timeout,
+                  const uint32_t pin_list[], uint32_t pin_count,
+                  const char *resource_source_name,
+                  const uint8_t *vendor_data, uint16_t vendor_data_len)
+{
+    uint8_t flags = edge_level | (active_level << 1) | (shared << 3);
+
+    return aml_gpio_connection(AML_INTERRUPT_CONNECTION, con_and_pro, flags,
+                               pin_config, 0, debounce_timeout, pin_list,
+                               pin_count, resource_source_name, vendor_data,
+                               vendor_data_len);
+}
+
 /*
  * ACPI 1.0b: 6.4.3.4 32-Bit Fixed Location Memory Range Descriptor
  * (Type 1, Large Item Name 0x6)
@@ -598,23 +755,27 @@ Aml *aml_memory32_fixed(uint32_t addr, uint32_t size,
 Aml *aml_interrupt(AmlConsumerAndProducer con_and_pro,
                    AmlLevelAndEdge level_and_edge,
                    AmlActiveHighAndLow high_and_low, AmlShared shared,
-                   uint32_t irq)
+                   uint32_t *irq_list, uint8_t irq_count)
 {
+    int i;
     Aml *var = aml_alloc();
     uint8_t irq_flags = con_and_pro | (level_and_edge << 1)
                         | (high_and_low << 2) | (shared << 3);
+    const int header_bytes_in_len = 2;
+    uint16_t len = header_bytes_in_len + irq_count * sizeof(uint32_t);
+
+    assert(irq_count > 0);
 
     build_append_byte(var->buf, 0x89); /* Extended irq descriptor */
-    build_append_byte(var->buf, 6); /* Length, bits[7:0] minimum value = 6 */
-    build_append_byte(var->buf, 0); /* Length, bits[15:8] minimum value = 0 */
+    build_append_byte(var->buf, len & 0xFF); /* Length, bits[7:0] */
+    build_append_byte(var->buf, len >> 8); /* Length, bits[15:8] */
     build_append_byte(var->buf, irq_flags); /* Interrupt Vector Information. */
-    build_append_byte(var->buf, 0x01);      /* Interrupt table length = 1 */
+    build_append_byte(var->buf, irq_count);   /* Interrupt table length */
 
-    /* Interrupt Number */
-    build_append_byte(var->buf, extract32(irq, 0, 8));  /* bits[7:0] */
-    build_append_byte(var->buf, extract32(irq, 8, 8));  /* bits[15:8] */
-    build_append_byte(var->buf, extract32(irq, 16, 8)); /* bits[23:16] */
-    build_append_byte(var->buf, extract32(irq, 24, 8)); /* bits[31:24] */
+    /* Interrupt Number List */
+    for (i = 0; i < irq_count; i++) {
+        build_append_int_noprefix(var->buf, irq_list[i], 4);
+    }
     return var;
 }
 
@@ -672,6 +833,26 @@ Aml *aml_equal(Aml *arg1, Aml *arg2)
     return var;
 }
 
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefLGreater */
+Aml *aml_lgreater(Aml *arg1, Aml *arg2)
+{
+    Aml *var = aml_opcode(0x94 /* LGreaterOp */);
+    aml_append(var, arg1);
+    aml_append(var, arg2);
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefLGreaterEqual */
+Aml *aml_lgreater_equal(Aml *arg1, Aml *arg2)
+{
+    /* LGreaterEqualOp := LNotOp LLessOp */
+    Aml *var = aml_opcode(0x92 /* LNotOp */);
+    build_append_byte(var->buf, 0x95 /* LLessOp */);
+    aml_append(var, arg1);
+    aml_append(var, arg2);
+    return var;
+}
+
 /* ACPI 1.0b: 16.2.5.3 Type 1 Opcodes Encoding: DefIfElse */
 Aml *aml_if(Aml *predicate)
 {
@@ -696,11 +877,24 @@ Aml *aml_while(Aml *predicate)
 }
 
 /* ACPI 1.0b: 16.2.5.2 Named Objects Encoding: DefMethod */
-Aml *aml_method(const char *name, int arg_count)
+Aml *aml_method(const char *name, int arg_count, AmlSerializeFlag sflag)
 {
     Aml *var = aml_bundle(0x14 /* MethodOp */, AML_PACKAGE);
+    int methodflags;
+
+    /*
+     * MethodFlags:
+     *   bit 0-2: ArgCount (0-7)
+     *   bit 3: SerializeFlag
+     *     0: NotSerialized
+     *     1: Serialized
+     *   bit 4-7: reserved (must be 0)
+     */
+    assert(arg_count < 8);
+    methodflags = arg_count | (sflag << 3);
+
     build_append_namestring(var->buf, "%s", name);
-    build_append_byte(var->buf, arg_count); /* MethodFlags: ArgCount */
+    build_append_byte(var->buf, methodflags); /* MethodFlags: ArgCount */
     return var;
 }
 
@@ -784,27 +978,43 @@ Aml *aml_reserved_field(unsigned length)
 }
 
 /* ACPI 1.0b: 16.2.5.2 Named Objects Encoding: DefField */
-Aml *aml_field(const char *name, AmlAccessType type, AmlUpdateRule rule)
+Aml *aml_field(const char *name, AmlAccessType type, AmlLockRule lock,
+               AmlUpdateRule rule)
 {
     Aml *var = aml_bundle(0x81 /* FieldOp */, AML_EXT_PACKAGE);
     uint8_t flags = rule << 5 | type;
 
+    flags |= lock << 4; /* LockRule at 4 bit offset */
+
     build_append_namestring(var->buf, "%s", name);
     build_append_byte(var->buf, flags);
     return var;
 }
 
-/* ACPI 1.0b: 16.2.5.2 Named Objects Encoding: DefCreateDWordField */
-Aml *aml_create_dword_field(Aml *srcbuf, Aml *index, const char *name)
+static
+Aml *create_field_common(int opcode, Aml *srcbuf, Aml *index, const char *name)
 {
-    Aml *var = aml_alloc();
-    build_append_byte(var->buf, 0x8A); /* CreateDWordFieldOp */
+    Aml *var = aml_opcode(opcode);
     aml_append(var, srcbuf);
     aml_append(var, index);
     build_append_namestring(var->buf, "%s", name);
     return var;
 }
 
+/* ACPI 1.0b: 16.2.5.2 Named Objects Encoding: DefCreateDWordField */
+Aml *aml_create_dword_field(Aml *srcbuf, Aml *index, const char *name)
+{
+    return create_field_common(0x8A /* CreateDWordFieldOp */,
+                               srcbuf, index, name);
+}
+
+/* ACPI 2.0a: 17.2.4.2 Named Objects Encoding: DefCreateQWordField */
+Aml *aml_create_qword_field(Aml *srcbuf, Aml *index, const char *name)
+{
+    return create_field_common(0x8F /* CreateQWordFieldOp */,
+                               srcbuf, index, name);
+}
+
 /* ACPI 1.0b: 16.2.3 Data Objects Encoding: String */
 Aml *aml_string(const char *name_format, ...)
 {
@@ -1065,6 +1275,30 @@ Aml *aml_qword_memory(AmlDecode dec, AmlMinFixed min_fixed,
                              addr_trans, len, flags);
 }
 
+/* ACPI 1.0b: 6.4.2.2 DMA Format/6.4.2.2.1 ASL Macro for DMA Descriptor */
+Aml *aml_dma(AmlDmaType typ, AmlDmaBusMaster bm, AmlTransferSize sz,
+             uint8_t channel)
+{
+    Aml *var = aml_alloc();
+    uint8_t flags = sz | bm << 2 | typ << 5;
+
+    assert(channel < 8);
+    build_append_byte(var->buf, 0x2A);    /* Byte 0: DMA Descriptor */
+    build_append_byte(var->buf, 1U << channel); /* Byte 1: _DMA - DmaChannel */
+    build_append_byte(var->buf, flags);   /* Byte 2 */
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.3 Type 1 Opcodes Encoding: DefSleep */
+Aml *aml_sleep(uint64_t msec)
+{
+    Aml *var = aml_alloc();
+    build_append_byte(var->buf, 0x5B); /* ExtOpPrefix */
+    build_append_byte(var->buf, 0x22); /* SleepOp */
+    aml_append(var, aml_int(msec));
+    return var;
+}
+
 static uint8_t Hex2Byte(const char *src)
 {
     int hi, lo;
@@ -1135,16 +1369,81 @@ Aml *aml_unicode(const char *str)
     return var;
 }
 
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefDerefOf */
+Aml *aml_derefof(Aml *arg)
+{
+    Aml *var = aml_opcode(0x83 /* DerefOfOp */);
+    aml_append(var, arg);
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefSizeOf */
+Aml *aml_sizeof(Aml *arg)
+{
+    Aml *var = aml_opcode(0x87 /* SizeOfOp */);
+    aml_append(var, arg);
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.2 Named Objects Encoding: DefMutex */
+Aml *aml_mutex(const char *name, uint8_t sync_level)
+{
+    Aml *var = aml_alloc();
+    build_append_byte(var->buf, 0x5B); /* ExtOpPrefix */
+    build_append_byte(var->buf, 0x01); /* MutexOp */
+    build_append_namestring(var->buf, "%s", name);
+    assert(!(sync_level & 0xF0));
+    build_append_byte(var->buf, sync_level);
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefAcquire */
+Aml *aml_acquire(Aml *mutex, uint16_t timeout)
+{
+    Aml *var = aml_alloc();
+    build_append_byte(var->buf, 0x5B); /* ExtOpPrefix */
+    build_append_byte(var->buf, 0x23); /* AcquireOp */
+    aml_append(var, mutex);
+    build_append_int_noprefix(var->buf, timeout, sizeof(timeout));
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.3 Type 1 Opcodes Encoding: DefRelease */
+Aml *aml_release(Aml *mutex)
+{
+    Aml *var = aml_alloc();
+    build_append_byte(var->buf, 0x5B); /* ExtOpPrefix */
+    build_append_byte(var->buf, 0x27); /* ReleaseOp */
+    aml_append(var, mutex);
+    return var;
+}
+
+/* ACPI 1.0b: 16.2.5.1 Name Space Modifier Objects Encoding: DefAlias */
+Aml *aml_alias(const char *source_object, const char *alias_object)
+{
+    Aml *var = aml_opcode(0x06 /* AliasOp */);
+    aml_append(var, aml_name("%s", source_object));
+    aml_append(var, aml_name("%s", alias_object));
+    return var;
+}
+
 void
 build_header(GArray *linker, GArray *table_data,
-             AcpiTableHeader *h, const char *sig, int len, uint8_t rev)
+             AcpiTableHeader *h, const char *sig, int len, uint8_t rev,
+             const char *oem_table_id)
 {
     memcpy(&h->signature, sig, 4);
     h->length = cpu_to_le32(len);
     h->revision = rev;
     memcpy(h->oem_id, ACPI_BUILD_APPNAME6, 6);
+
+    if (oem_table_id) {
+        strncpy((char *)h->oem_table_id, oem_table_id, sizeof(h->oem_table_id));
+    } else {
         memcpy(h->oem_table_id, ACPI_BUILD_APPNAME4, 4);
         memcpy(h->oem_table_id + 4, sig, 4);
+    }
+
     h->oem_revision = cpu_to_le32(1);
     memcpy(h->asl_compiler_id, ACPI_BUILD_APPNAME4, 4);
     h->asl_compiler_revision = cpu_to_le32(1);
@@ -1211,5 +1510,5 @@ build_rsdt(GArray *table_data, GArray *linker, GArray *table_offsets)
                                        sizeof(uint32_t));
     }
     build_header(linker, table_data,
-                 (void *)rsdt, "RSDT", rsdt_len, 1);
+                 (void *)rsdt, "RSDT", rsdt_len, 1, NULL);
 }

hw/acpi/memory_hotplug.c

@@ -231,6 +231,11 @@ void acpi_memory_plug_cb(ACPIREGS *ar, qemu_irq irq, MemHotplugState *mem_st,
                          DeviceState *dev, Error **errp)
 {
     MemStatus *mdev;
+    DeviceClass *dc = DEVICE_GET_CLASS(dev);
+
+    if (!dc->hotpluggable) {
+        return;
+    }
 
     mdev = acpi_memory_slot_status(mem_st, dev, errp);
     if (!mdev) {

hw/acpi/nvdimm.c

@@ -0,0 +1,488 @@
+/*
+ * NVDIMM ACPI Implementation
+ *
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Author:
+ *  Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *
+ * NFIT is defined in ACPI 6.0: 5.2.25 NVDIMM Firmware Interface Table (NFIT)
+ * and the DSM specification can be found at:
+ *       http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf
+ *
+ * Currently, it only supports PMEM Virtualization.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>
+ */
+
+#include "hw/acpi/acpi.h"
+#include "hw/acpi/aml-build.h"
+#include "hw/mem/nvdimm.h"
+
+static int nvdimm_plugged_device_list(Object *obj, void *opaque)
+{
+    GSList **list = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_NVDIMM)) {
+        DeviceState *dev = DEVICE(obj);
+
+        if (dev->realized) { /* only realized NVDIMMs matter */
+            *list = g_slist_append(*list, DEVICE(obj));
+        }
+    }
+
+    object_child_foreach(obj, nvdimm_plugged_device_list, opaque);
+    return 0;
+}
+
+/*
+ * inquire plugged NVDIMM devices and link them into the list which is
+ * returned to the caller.
+ *
+ * Note: it is the caller's responsibility to free the list to avoid
+ * memory leak.
+ */
+static GSList *nvdimm_get_plugged_device_list(void)
+{
+    GSList *list = NULL;
+
+    object_child_foreach(qdev_get_machine(), nvdimm_plugged_device_list,
+                         &list);
+    return list;
+}
+
+#define NVDIMM_UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7)             \
+   { (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \
+     (b) & 0xff, ((b) >> 8) & 0xff, (c) & 0xff, ((c) >> 8) & 0xff,          \
+     (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }
+
+/*
+ * define Byte Addressable Persistent Memory (PM) Region according to
+ * ACPI 6.0: 5.2.25.1 System Physical Address Range Structure.
+ */
+static const uint8_t nvdimm_nfit_spa_uuid[] =
+      NVDIMM_UUID_LE(0x66f0d379, 0xb4f3, 0x4074, 0xac, 0x43, 0x0d, 0x33,
+                     0x18, 0xb7, 0x8c, 0xdb);
+
+/*
+ * NVDIMM Firmware Interface Table
+ * @signature: "NFIT"
+ *
+ * It provides information that allows OSPM to enumerate NVDIMM present in
+ * the platform and associate system physical address ranges created by the
+ * NVDIMMs.
+ *
+ * It is defined in ACPI 6.0: 5.2.25 NVDIMM Firmware Interface Table (NFIT)
+ */
+struct NvdimmNfitHeader {
+    ACPI_TABLE_HEADER_DEF
+    uint32_t reserved;
+} QEMU_PACKED;
+typedef struct NvdimmNfitHeader NvdimmNfitHeader;
+
+/*
+ * define NFIT structures according to ACPI 6.0: 5.2.25 NVDIMM Firmware
+ * Interface Table (NFIT).
+ */
+
+/*
+ * System Physical Address Range Structure
+ *
+ * It describes the system physical address ranges occupied by NVDIMMs and
+ * the types of the regions.
+ */
+struct NvdimmNfitSpa {
+    uint16_t type;
+    uint16_t length;
+    uint16_t spa_index;
+    uint16_t flags;
+    uint32_t reserved;
+    uint32_t proximity_domain;
+    uint8_t type_guid[16];
+    uint64_t spa_base;
+    uint64_t spa_length;
+    uint64_t mem_attr;
+} QEMU_PACKED;
+typedef struct NvdimmNfitSpa NvdimmNfitSpa;
+
+/*
+ * Memory Device to System Physical Address Range Mapping Structure
+ *
+ * It enables identifying each NVDIMM region and the corresponding SPA
+ * describing the memory interleave
+ */
+struct NvdimmNfitMemDev {
+    uint16_t type;
+    uint16_t length;
+    uint32_t nfit_handle;
+    uint16_t phys_id;
+    uint16_t region_id;
+    uint16_t spa_index;
+    uint16_t dcr_index;
+    uint64_t region_len;
+    uint64_t region_offset;
+    uint64_t region_dpa;
+    uint16_t interleave_index;
+    uint16_t interleave_ways;
+    uint16_t flags;
+    uint16_t reserved;
+} QEMU_PACKED;
+typedef struct NvdimmNfitMemDev NvdimmNfitMemDev;
+
+/*
+ * NVDIMM Control Region Structure
+ *
+ * It describes the NVDIMM and if applicable, Block Control Window.
+ */
+struct NvdimmNfitControlRegion {
+    uint16_t type;
+    uint16_t length;
+    uint16_t dcr_index;
+    uint16_t vendor_id;
+    uint16_t device_id;
+    uint16_t revision_id;
+    uint16_t sub_vendor_id;
+    uint16_t sub_device_id;
+    uint16_t sub_revision_id;
+    uint8_t reserved[6];
+    uint32_t serial_number;
+    uint16_t fic;
+    uint16_t num_bcw;
+    uint64_t bcw_size;
+    uint64_t cmd_offset;
+    uint64_t cmd_size;
+    uint64_t status_offset;
+    uint64_t status_size;
+    uint16_t flags;
+    uint8_t reserved2[6];
+} QEMU_PACKED;
+typedef struct NvdimmNfitControlRegion NvdimmNfitControlRegion;
+
+/*
+ * Module serial number is a unique number for each device. We use the
+ * slot id of NVDIMM device to generate this number so that each device
+ * associates with a different number.
+ *
+ * 0x123456 is a magic number we arbitrarily chose.
+ */
+static uint32_t nvdimm_slot_to_sn(int slot)
+{
+    return 0x123456 + slot;
+}
+
+/*
+ * handle is used to uniquely associate nfit_memdev structure with NVDIMM
+ * ACPI device - nfit_memdev.nfit_handle matches with the value returned
+ * by ACPI device _ADR method.
+ *
+ * We generate the handle with the slot id of NVDIMM device and reserve
+ * 0 for NVDIMM root device.
+ */
+static uint32_t nvdimm_slot_to_handle(int slot)
+{
+    return slot + 1;
+}
+
+/*
+ * index uniquely identifies the structure, 0 is reserved which indicates
+ * that the structure is not valid or the associated structure is not
+ * present.
+ *
+ * Each NVDIMM device needs two indexes, one for nfit_spa and another for
+ * nfit_dc which are generated by the slot id of NVDIMM device.
+ */
+static uint16_t nvdimm_slot_to_spa_index(int slot)
+{
+    return (slot + 1) << 1;
+}
+
+/* See the comments of nvdimm_slot_to_spa_index(). */
+static uint32_t nvdimm_slot_to_dcr_index(int slot)
+{
+    return nvdimm_slot_to_spa_index(slot) + 1;
+}
+
+/* ACPI 6.0: 5.2.25.1 System Physical Address Range Structure */
+static void
+nvdimm_build_structure_spa(GArray *structures, DeviceState *dev)
+{
+    NvdimmNfitSpa *nfit_spa;
+    uint64_t addr = object_property_get_int(OBJECT(dev), PC_DIMM_ADDR_PROP,
+                                            NULL);
+    uint64_t size = object_property_get_int(OBJECT(dev), PC_DIMM_SIZE_PROP,
+                                            NULL);
+    uint32_t node = object_property_get_int(OBJECT(dev), PC_DIMM_NODE_PROP,
+                                            NULL);
+    int slot = object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP,
+                                            NULL);
+
+    nfit_spa = acpi_data_push(structures, sizeof(*nfit_spa));
+
+    nfit_spa->type = cpu_to_le16(0 /* System Physical Address Range
+                                      Structure */);
+    nfit_spa->length = cpu_to_le16(sizeof(*nfit_spa));
+    nfit_spa->spa_index = cpu_to_le16(nvdimm_slot_to_spa_index(slot));
+
+    /*
+     * Control region is strict as all the device info, such as SN, index,
+     * is associated with slot id.
+     */
+    nfit_spa->flags = cpu_to_le16(1 /* Control region is strictly for
+                                       management during hot add/online
+                                       operation */ |
+                                  2 /* Data in Proximity Domain field is
+                                       valid*/);
+
+    /* NUMA node. */
+    nfit_spa->proximity_domain = cpu_to_le32(node);
+    /* the region reported as PMEM. */
+    memcpy(nfit_spa->type_guid, nvdimm_nfit_spa_uuid,
+           sizeof(nvdimm_nfit_spa_uuid));
+
+    nfit_spa->spa_base = cpu_to_le64(addr);
+    nfit_spa->spa_length = cpu_to_le64(size);
+
+    /* It is the PMEM and can be cached as writeback. */
+    nfit_spa->mem_attr = cpu_to_le64(0x8ULL /* EFI_MEMORY_WB */ |
+                                     0x8000ULL /* EFI_MEMORY_NV */);
+}
+
+/*
+ * ACPI 6.0: 5.2.25.2 Memory Device to System Physical Address Range Mapping
+ * Structure
+ */
+static void
+nvdimm_build_structure_memdev(GArray *structures, DeviceState *dev)
+{
+    NvdimmNfitMemDev *nfit_memdev;
+    uint64_t addr = object_property_get_int(OBJECT(dev), PC_DIMM_ADDR_PROP,
+                                            NULL);
+    uint64_t size = object_property_get_int(OBJECT(dev), PC_DIMM_SIZE_PROP,
+                                            NULL);
+    int slot = object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP,
+                                            NULL);
+    uint32_t handle = nvdimm_slot_to_handle(slot);
+
+    nfit_memdev = acpi_data_push(structures, sizeof(*nfit_memdev));
+
+    nfit_memdev->type = cpu_to_le16(1 /* Memory Device to System Address
+                                         Range Map Structure*/);
+    nfit_memdev->length = cpu_to_le16(sizeof(*nfit_memdev));
+    nfit_memdev->nfit_handle = cpu_to_le32(handle);
+
+    /*
+     * associate memory device with System Physical Address Range
+     * Structure.
+     */
+    nfit_memdev->spa_index = cpu_to_le16(nvdimm_slot_to_spa_index(slot));
+    /* associate memory device with Control Region Structure. */
+    nfit_memdev->dcr_index = cpu_to_le16(nvdimm_slot_to_dcr_index(slot));
+
+    /* The memory region on the device. */
+    nfit_memdev->region_len = cpu_to_le64(size);
+    nfit_memdev->region_dpa = cpu_to_le64(addr);
+
+    /* Only one interleave for PMEM. */
+    nfit_memdev->interleave_ways = cpu_to_le16(1);
+}
+
+/*
+ * ACPI 6.0: 5.2.25.5 NVDIMM Control Region Structure.
+ */
+static void nvdimm_build_structure_dcr(GArray *structures, DeviceState *dev)
+{
+    NvdimmNfitControlRegion *nfit_dcr;
+    int slot = object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP,
+                                       NULL);
+    uint32_t sn = nvdimm_slot_to_sn(slot);
+
+    nfit_dcr = acpi_data_push(structures, sizeof(*nfit_dcr));
+
+    nfit_dcr->type = cpu_to_le16(4 /* NVDIMM Control Region Structure */);
+    nfit_dcr->length = cpu_to_le16(sizeof(*nfit_dcr));
+    nfit_dcr->dcr_index = cpu_to_le16(nvdimm_slot_to_dcr_index(slot));
+
+    /* vendor: Intel. */
+    nfit_dcr->vendor_id = cpu_to_le16(0x8086);
+    nfit_dcr->device_id = cpu_to_le16(1);
+
+    /* The _DSM method is following Intel's DSM specification. */
+    nfit_dcr->revision_id = cpu_to_le16(1 /* Current Revision supported
+                                             in ACPI 6.0 is 1. */);
+    nfit_dcr->serial_number = cpu_to_le32(sn);
+    nfit_dcr->fic = cpu_to_le16(0x201 /* Format Interface Code. See Chapter
+                                         2: NVDIMM Device Specific Method
+                                         (DSM) in DSM Spec Rev1.*/);
+}
+
+static GArray *nvdimm_build_device_structure(GSList *device_list)
+{
+    GArray *structures = g_array_new(false, true /* clear */, 1);
+
+    for (; device_list; device_list = device_list->next) {
+        DeviceState *dev = device_list->data;
+
+        /* build System Physical Address Range Structure. */
+        nvdimm_build_structure_spa(structures, dev);
+
+        /*
+         * build Memory Device to System Physical Address Range Mapping
+         * Structure.
+         */
+        nvdimm_build_structure_memdev(structures, dev);
+
+        /* build NVDIMM Control Region Structure. */
+        nvdimm_build_structure_dcr(structures, dev);
+    }
+
+    return structures;
+}
+
+static void nvdimm_build_nfit(GSList *device_list, GArray *table_offsets,
+                              GArray *table_data, GArray *linker)
+{
+    GArray *structures = nvdimm_build_device_structure(device_list);
+    void *header;
+
+    acpi_add_table(table_offsets, table_data);
+
+    /* NFIT header. */
+    header = acpi_data_push(table_data, sizeof(NvdimmNfitHeader));
+    /* NVDIMM device structures. */
+    g_array_append_vals(table_data, structures->data, structures->len);
+
+    build_header(linker, table_data, header, "NFIT",
+                 sizeof(NvdimmNfitHeader) + structures->len, 1, NULL);
+    g_array_free(structures, true);
+}
+
+#define NVDIMM_COMMON_DSM      "NCAL"
+
+static void nvdimm_build_common_dsm(Aml *dev)
+{
+    Aml *method, *ifctx, *function;
+    uint8_t byte_list[1];
+
+    method = aml_method(NVDIMM_COMMON_DSM, 4, AML_NOTSERIALIZED);
+    function = aml_arg(2);
+
+    /*
+     * function 0 is called to inquire what functions are supported by
+     * OSPM
+     */
+    ifctx = aml_if(aml_equal(function, aml_int(0)));
+    byte_list[0] = 0 /* No function Supported */;
+    aml_append(ifctx, aml_return(aml_buffer(1, byte_list)));
+    aml_append(method, ifctx);
+
+    /* No function is supported yet. */
+    byte_list[0] = 1 /* Not Supported */;
+    aml_append(method, aml_return(aml_buffer(1, byte_list)));
+
+    aml_append(dev, method);
+}
+
+static void nvdimm_build_device_dsm(Aml *dev)
+{
+    Aml *method;
+
+    method = aml_method("_DSM", 4, AML_NOTSERIALIZED);
+    aml_append(method, aml_return(aml_call4(NVDIMM_COMMON_DSM, aml_arg(0),
+                                  aml_arg(1), aml_arg(2), aml_arg(3))));
+    aml_append(dev, method);
+}
+
+static void nvdimm_build_nvdimm_devices(GSList *device_list, Aml *root_dev)
+{
+    for (; device_list; device_list = device_list->next) {
+        DeviceState *dev = device_list->data;
+        int slot = object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP,
+                                           NULL);
+        uint32_t handle = nvdimm_slot_to_handle(slot);
+        Aml *nvdimm_dev;
+
+        nvdimm_dev = aml_device("NV%02X", slot);
+
+        /*
+         * ACPI 6.0: 9.20 NVDIMM Devices:
+         *
+         * _ADR object that is used to supply OSPM with unique address
+         * of the NVDIMM device. This is done by returning the NFIT Device
+         * handle that is used to identify the associated entries in ACPI
+         * table NFIT or _FIT.
+         */
+        aml_append(nvdimm_dev, aml_name_decl("_ADR", aml_int(handle)));
+
+        nvdimm_build_device_dsm(nvdimm_dev);
+        aml_append(root_dev, nvdimm_dev);
+    }
+}
+
+static void nvdimm_build_ssdt(GSList *device_list, GArray *table_offsets,
+                              GArray *table_data, GArray *linker)
+{
+    Aml *ssdt, *sb_scope, *dev;
+
+    acpi_add_table(table_offsets, table_data);
+
+    ssdt = init_aml_allocator();
+    acpi_data_push(ssdt->buf, sizeof(AcpiTableHeader));
+
+    sb_scope = aml_scope("\\_SB");
+
+    dev = aml_device("NVDR");
+
+    /*
+     * ACPI 6.0: 9.20 NVDIMM Devices:
+     *
+     * The ACPI Name Space device uses _HID of ACPI0012 to identify the root
+     * NVDIMM interface device. Platform firmware is required to contain one
+     * such device in _SB scope if NVDIMMs support is exposed by platform to
+     * OSPM.
+     * For each NVDIMM present or intended to be supported by platform,
+     * platform firmware also exposes an ACPI Namespace Device under the
+     * root device.
+     */
+    aml_append(dev, aml_name_decl("_HID", aml_string("ACPI0012")));
+
+    nvdimm_build_common_dsm(dev);
+    nvdimm_build_device_dsm(dev);
+
+    nvdimm_build_nvdimm_devices(device_list, dev);
+
+    aml_append(sb_scope, dev);
+
+    aml_append(ssdt, sb_scope);
+    /* copy AML table into ACPI tables blob and patch header there */
+    g_array_append_vals(table_data, ssdt->buf->data, ssdt->buf->len);
+    build_header(linker, table_data,
+        (void *)(table_data->data + table_data->len - ssdt->buf->len),
+        "SSDT", ssdt->buf->len, 1, "NVDIMM");
+    free_aml_allocator();
+}
+
+void nvdimm_build_acpi(GArray *table_offsets, GArray *table_data,
+                       GArray *linker)
+{
+    GSList *device_list;
+
+    /* no NVDIMM device is plugged. */
+    device_list = nvdimm_get_plugged_device_list();
+    if (!device_list) {
+        return;
+    }
+    nvdimm_build_nfit(device_list, table_offsets, table_data, linker);
+    nvdimm_build_ssdt(device_list, table_offsets, table_data, linker);
+    g_slist_free(device_list);
+}

hw/alpha/pci.c

@@ -10,6 +10,7 @@
 #include "alpha_sys.h"
 #include "qemu/log.h"
 #include "sysemu/sysemu.h"
+#include "trace.h"
 
 
 /* Fallback for unassigned PCI I/O operations.  Avoids MCHK.  */
@@ -73,7 +74,7 @@ static uint64_t iack_read(void *opaque, hwaddr addr, unsigned size)
 static void special_write(void *opaque, hwaddr addr,
                           uint64_t val, unsigned size)
 {
-    qemu_log("pci: special write cycle");
+    trace_alpha_pci_iack_write();
 }
 
 const MemoryRegionOps alpha_pci_iack_ops = {

hw/arm/fsl-imx25.c

@@ -38,7 +38,7 @@ static void fsl_imx25_init(Object *obj)
     object_initialize(&s->avic, sizeof(s->avic), TYPE_IMX_AVIC);
     qdev_set_parent_bus(DEVICE(&s->avic), sysbus_get_default());
 
-    object_initialize(&s->ccm, sizeof(s->ccm), TYPE_IMX_CCM);
+    object_initialize(&s->ccm, sizeof(s->ccm), TYPE_IMX25_CCM);
     qdev_set_parent_bus(DEVICE(&s->ccm), sysbus_get_default());
 
     for (i = 0; i < FSL_IMX25_NUM_UARTS; i++) {
@@ -150,7 +150,7 @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp)
             { FSL_IMX25_GPT4_ADDR, FSL_IMX25_GPT4_IRQ }
         };
 
-        s->gpt[i].ccm = DEVICE(&s->ccm);
+        s->gpt[i].ccm = IMX_CCM(&s->ccm);
 
         object_property_set_bool(OBJECT(&s->gpt[i]), true, "realized", &err);
         if (err) {
@@ -173,7 +173,7 @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp)
             { FSL_IMX25_EPIT2_ADDR, FSL_IMX25_EPIT2_IRQ }
         };
 
-        s->epit[i].ccm = DEVICE(&s->ccm);
+        s->epit[i].ccm = IMX_CCM(&s->ccm);
 
         object_property_set_bool(OBJECT(&s->epit[i]), true, "realized", &err);
         if (err) {

hw/arm/fsl-imx31.c

@@ -35,7 +35,7 @@ static void fsl_imx31_init(Object *obj)
     object_initialize(&s->avic, sizeof(s->avic), TYPE_IMX_AVIC);
     qdev_set_parent_bus(DEVICE(&s->avic), sysbus_get_default());
 
-    object_initialize(&s->ccm, sizeof(s->ccm), TYPE_IMX_CCM);
+    object_initialize(&s->ccm, sizeof(s->ccm), TYPE_IMX31_CCM);
     qdev_set_parent_bus(DEVICE(&s->ccm), sysbus_get_default());
 
     for (i = 0; i < FSL_IMX31_NUM_UARTS; i++) {
@@ -128,7 +128,7 @@ static void fsl_imx31_realize(DeviceState *dev, Error **errp)
                                             serial_table[i].irq));
     }
 
-    s->gpt.ccm = DEVICE(&s->ccm);
+    s->gpt.ccm = IMX_CCM(&s->ccm);
 
     object_property_set_bool(OBJECT(&s->gpt), true, "realized", &err);
     if (err) {
@@ -150,7 +150,7 @@ static void fsl_imx31_realize(DeviceState *dev, Error **errp)
             { FSL_IMX31_EPIT2_ADDR, FSL_IMX31_EPIT2_IRQ },
         };
 
-        s->epit[i].ccm = DEVICE(&s->ccm);
+        s->epit[i].ccm = IMX_CCM(&s->ccm);
 
         object_property_set_bool(OBJECT(&s->epit[i]), true, "realized", &err);
         if (err) {

hw/arm/virt-acpi-build.c

@@ -43,6 +43,7 @@
 #include "hw/pci/pci.h"
 
 #define ARM_SPI_BASE 32
+#define ACPI_POWER_BUTTON_DEVICE "PWRB"
 
 typedef struct VirtAcpiCpuInfo {
     DECLARE_BITMAP(found_cpus, VIRT_ACPI_CPU_ID_LIMIT);
@@ -71,7 +72,7 @@ static void acpi_dsdt_add_cpus(Aml *scope, int smp_cpus)
 }
 
 static void acpi_dsdt_add_uart(Aml *scope, const MemMapEntry *uart_memmap,
-                                           int uart_irq)
+                                           uint32_t uart_irq)
 {
     Aml *dev = aml_device("COM0");
     aml_append(dev, aml_name_decl("_HID", aml_string("ARMH0011")));
@@ -82,7 +83,7 @@ static void acpi_dsdt_add_uart(Aml *scope, const MemMapEntry *uart_memmap,
                                        uart_memmap->size, AML_READ_WRITE));
     aml_append(crs,
                aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
-                             AML_EXCLUSIVE, uart_irq));
+                             AML_EXCLUSIVE, &uart_irq, 1));
     aml_append(dev, aml_name_decl("_CRS", crs));
 
     /* The _ADR entry is used to link this device to the UART described
@@ -94,7 +95,7 @@ static void acpi_dsdt_add_uart(Aml *scope, const MemMapEntry *uart_memmap,
 }
 
 static void acpi_dsdt_add_rtc(Aml *scope, const MemMapEntry *rtc_memmap,
-                                          int rtc_irq)
+                                          uint32_t rtc_irq)
 {
     Aml *dev = aml_device("RTC0");
     aml_append(dev, aml_name_decl("_HID", aml_string("LNRO0013")));
@@ -105,7 +106,7 @@ static void acpi_dsdt_add_rtc(Aml *scope, const MemMapEntry *rtc_memmap,
                                        rtc_memmap->size, AML_READ_WRITE));
     aml_append(crs,
                aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
-                             AML_EXCLUSIVE, rtc_irq));
+                             AML_EXCLUSIVE, &rtc_irq, 1));
     aml_append(dev, aml_name_decl("_CRS", crs));
     aml_append(scope, dev);
 }
@@ -136,14 +137,14 @@ static void acpi_dsdt_add_flash(Aml *scope, const MemMapEntry *flash_memmap)
 
 static void acpi_dsdt_add_virtio(Aml *scope,
                                  const MemMapEntry *virtio_mmio_memmap,
-                                 int mmio_irq, int num)
+                                 uint32_t mmio_irq, int num)
 {
     hwaddr base = virtio_mmio_memmap->base;
     hwaddr size = virtio_mmio_memmap->size;
-    int irq = mmio_irq;
     int i;
 
     for (i = 0; i < num; i++) {
+        uint32_t irq = mmio_irq + i;
         Aml *dev = aml_device("VR%02u", i);
         aml_append(dev, aml_name_decl("_HID", aml_string("LNRO0005")));
         aml_append(dev, aml_name_decl("_UID", aml_int(i)));
@@ -152,15 +153,15 @@ static void acpi_dsdt_add_virtio(Aml *scope,
         aml_append(crs, aml_memory32_fixed(base, size, AML_READ_WRITE));
         aml_append(crs,
                    aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
-                                 AML_EXCLUSIVE, irq + i));
+                                 AML_EXCLUSIVE, &irq, 1));
         aml_append(dev, aml_name_decl("_CRS", crs));
         aml_append(scope, dev);
         base += size;
     }
 }
 
-static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, int irq,
-                              bool use_highmem)
+static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
+                              uint32_t irq, bool use_highmem)
 {
     Aml *method, *crs, *ifctx, *UUID, *ifctx1, *elsectx, *buf;
     int i, bus_no;
@@ -199,29 +200,30 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, int irq,
 
     /* Create GSI link device */
     for (i = 0; i < PCI_NUM_PINS; i++) {
+        uint32_t irqs =  irq + i;
         Aml *dev_gsi = aml_device("GSI%d", i);
         aml_append(dev_gsi, aml_name_decl("_HID", aml_string("PNP0C0F")));
         aml_append(dev_gsi, aml_name_decl("_UID", aml_int(0)));
         crs = aml_resource_template();
         aml_append(crs,
                    aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
-                                 AML_EXCLUSIVE, irq + i));
+                                 AML_EXCLUSIVE, &irqs, 1));
         aml_append(dev_gsi, aml_name_decl("_PRS", crs));
         crs = aml_resource_template();
         aml_append(crs,
                    aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
-                                 AML_EXCLUSIVE, irq + i));
+                                 AML_EXCLUSIVE, &irqs, 1));
         aml_append(dev_gsi, aml_name_decl("_CRS", crs));
-        method = aml_method("_SRS", 1);
+        method = aml_method("_SRS", 1, AML_NOTSERIALIZED);
         aml_append(dev_gsi, method);
         aml_append(dev, dev_gsi);
     }
 
-    method = aml_method("_CBA", 0);
+    method = aml_method("_CBA", 0, AML_NOTSERIALIZED);
     aml_append(method, aml_return(aml_int(base_ecam)));
     aml_append(dev, method);
 
-    method = aml_method("_CRS", 0);
+    method = aml_method("_CRS", 0, AML_NOTSERIALIZED);
     Aml *rbuf = aml_resource_template();
     aml_append(rbuf,
         aml_word_bus_number(AML_MIN_FIXED, AML_MAX_FIXED, AML_POS_DECODE,
@@ -254,7 +256,7 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, int irq,
     /* Declare an _OSC (OS Control Handoff) method */
     aml_append(dev, aml_name_decl("SUPP", aml_int(0)));
     aml_append(dev, aml_name_decl("CTRL", aml_int(0)));
-    method = aml_method("_OSC", 4);
+    method = aml_method("_OSC", 4, AML_NOTSERIALIZED);
     aml_append(method,
         aml_create_dword_field(aml_arg(3), aml_int(0), "CDW1"));
 
@@ -272,16 +274,16 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, int irq,
         aml_create_dword_field(aml_arg(3), aml_int(8), "CDW3"));
     aml_append(ifctx, aml_store(aml_name("CDW2"), aml_name("SUPP")));
     aml_append(ifctx, aml_store(aml_name("CDW3"), aml_name("CTRL")));
-    aml_append(ifctx, aml_store(aml_and(aml_name("CTRL"), aml_int(0x1D)),
+    aml_append(ifctx, aml_store(aml_and(aml_name("CTRL"), aml_int(0x1D), NULL),
                                 aml_name("CTRL")));
 
     ifctx1 = aml_if(aml_lnot(aml_equal(aml_arg(1), aml_int(0x1))));
-    aml_append(ifctx1, aml_store(aml_or(aml_name("CDW1"), aml_int(0x08)),
+    aml_append(ifctx1, aml_store(aml_or(aml_name("CDW1"), aml_int(0x08), NULL),
                                  aml_name("CDW1")));
     aml_append(ifctx, ifctx1);
 
     ifctx1 = aml_if(aml_lnot(aml_equal(aml_name("CDW3"), aml_name("CTRL"))));
-    aml_append(ifctx1, aml_store(aml_or(aml_name("CDW1"), aml_int(0x10)),
+    aml_append(ifctx1, aml_store(aml_or(aml_name("CDW1"), aml_int(0x10), NULL),
                                  aml_name("CDW1")));
     aml_append(ifctx, ifctx1);
 
@@ -290,13 +292,13 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, int irq,
     aml_append(method, ifctx);
 
     elsectx = aml_else();
-    aml_append(elsectx, aml_store(aml_or(aml_name("CDW1"), aml_int(4)),
+    aml_append(elsectx, aml_store(aml_or(aml_name("CDW1"), aml_int(4), NULL),
                                   aml_name("CDW1")));
     aml_append(elsectx, aml_return(aml_arg(3)));
     aml_append(method, elsectx);
     aml_append(dev, method);
 
-    method = aml_method("_DSM", 4);
+    method = aml_method("_DSM", 4, AML_NOTSERIALIZED);
 
     /* PCI Firmware Specification 3.0
      * 4.6.1. _DSM for PCI Express Slot Information
@@ -323,6 +325,46 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, int irq,
     aml_append(scope, dev);
 }
 
+static void acpi_dsdt_add_gpio(Aml *scope, const MemMapEntry *gpio_memmap,
+                                           uint32_t gpio_irq)
+{
+    Aml *dev = aml_device("GPO0");
+    aml_append(dev, aml_name_decl("_HID", aml_string("ARMH0061")));
+    aml_append(dev, aml_name_decl("_ADR", aml_int(0)));
+    aml_append(dev, aml_name_decl("_UID", aml_int(0)));
+
+    Aml *crs = aml_resource_template();
+    aml_append(crs, aml_memory32_fixed(gpio_memmap->base, gpio_memmap->size,
+                                       AML_READ_WRITE));
+    aml_append(crs, aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
+                                  AML_EXCLUSIVE, &gpio_irq, 1));
+    aml_append(dev, aml_name_decl("_CRS", crs));
+
+    Aml *aei = aml_resource_template();
+    /* Pin 3 for power button */
+    const uint32_t pin_list[1] = {3};
+    aml_append(aei, aml_gpio_int(AML_CONSUMER, AML_EDGE, AML_ACTIVE_HIGH,
+                                 AML_EXCLUSIVE, AML_PULL_UP, 0, pin_list, 1,
+                                 "GPO0", NULL, 0));
+    aml_append(dev, aml_name_decl("_AEI", aei));
+
+    /* _E03 is handle for power button */
+    Aml *method = aml_method("_E03", 0, AML_NOTSERIALIZED);
+    aml_append(method, aml_notify(aml_name(ACPI_POWER_BUTTON_DEVICE),
+                                  aml_int(0x80)));
+    aml_append(dev, method);
+    aml_append(scope, dev);
+}
+
+static void acpi_dsdt_add_power_button(Aml *scope)
+{
+    Aml *dev = aml_device(ACPI_POWER_BUTTON_DEVICE);
+    aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C0C")));
+    aml_append(dev, aml_name_decl("_ADR", aml_int(0)));
+    aml_append(dev, aml_name_decl("_UID", aml_int(0)));
+    aml_append(scope, dev);
+}
+
 /* RSDP */
 static GArray *
 build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt)
@@ -381,7 +423,8 @@ build_spcr(GArray *table_data, GArray *linker, VirtGuestInfo *guest_info)
     spcr->pci_device_id = 0xffff;  /* PCI Device ID: not a PCI device */
     spcr->pci_vendor_id = 0xffff;  /* PCI Vendor ID: not a PCI device */
 
-    build_header(linker, table_data, (void *)spcr, "SPCR", sizeof(*spcr), 2);
+    build_header(linker, table_data, (void *)spcr, "SPCR", sizeof(*spcr), 2,
+                 NULL);
 }
 
 static void
@@ -400,7 +443,7 @@ build_mcfg(GArray *table_data, GArray *linker, VirtGuestInfo *guest_info)
     mcfg->allocation[0].end_bus_number = (memmap[VIRT_PCIE_ECAM].size
                                           / PCIE_MMCFG_SIZE_MIN) - 1;
 
-    build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1);
+    build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1, NULL);
 }
 
 /* GTDT */
@@ -426,7 +469,7 @@ build_gtdt(GArray *table_data, GArray *linker)
 
     build_header(linker, table_data,
                  (void *)(table_data->data + gtdt_start), "GTDT",
-                 table_data->len - gtdt_start, 2);
+                 table_data->len - gtdt_start, 2, NULL);
 }
 
 /* MADT */
@@ -488,7 +531,7 @@ build_madt(GArray *table_data, GArray *linker, VirtGuestInfo *guest_info,
 
     build_header(linker, table_data,
                  (void *)(table_data->data + madt_start), "APIC",
-                 table_data->len - madt_start, 3);
+                 table_data->len - madt_start, 3, NULL);
 }
 
 /* FADT */
@@ -513,7 +556,7 @@ build_fadt(GArray *table_data, GArray *linker, unsigned dsdt)
                                    sizeof fadt->dsdt);
 
     build_header(linker, table_data,
-                 (void *)fadt, "FACP", sizeof(*fadt), 5);
+                 (void *)fadt, "FACP", sizeof(*fadt), 5, NULL);
 }
 
 /* DSDT */
@@ -539,6 +582,9 @@ build_dsdt(GArray *table_data, GArray *linker, VirtGuestInfo *guest_info)
                     (irqmap[VIRT_MMIO] + ARM_SPI_BASE), NUM_VIRTIO_TRANSPORTS);
     acpi_dsdt_add_pci(scope, memmap, (irqmap[VIRT_PCIE] + ARM_SPI_BASE),
                       guest_info->use_highmem);
+    acpi_dsdt_add_gpio(scope, &memmap[VIRT_GPIO],
+                       (irqmap[VIRT_GPIO] + ARM_SPI_BASE));
+    acpi_dsdt_add_power_button(scope);
 
     aml_append(dsdt, scope);
 
@@ -546,7 +592,7 @@ build_dsdt(GArray *table_data, GArray *linker, VirtGuestInfo *guest_info)
     g_array_append_vals(table_data, dsdt->buf->data, dsdt->buf->len);
     build_header(linker, table_data,
         (void *)(table_data->data + table_data->len - dsdt->buf->len),
-        "DSDT", dsdt->buf->len, 2);
+        "DSDT", dsdt->buf->len, 2, NULL);
     free_aml_allocator();
 }
 
@@ -631,7 +677,7 @@ static void acpi_ram_update(MemoryRegion *mr, GArray *data)
     memory_region_set_dirty(mr, 0, size);
 }
 
-static void virt_acpi_build_update(void *build_opaque, uint32_t offset)
+static void virt_acpi_build_update(void *build_opaque)
 {
     AcpiBuildState *build_state = build_opaque;
     AcpiBuildTables tables;

hw/arm/virt.c

@@ -52,6 +52,7 @@
 #include "kvm_arm.h"
 #include "hw/smbios/smbios.h"
 #include "qapi/visitor.h"
+#include "standard-headers/linux/input.h"
 
 /* Number of external interrupt lines to configure the GIC with */
 #define NUM_IRQS 256
@@ -120,6 +121,7 @@ static const MemMapEntry a15memmap[] = {
     [VIRT_UART] =               { 0x09000000, 0x00001000 },
     [VIRT_RTC] =                { 0x09010000, 0x00001000 },
     [VIRT_FW_CFG] =             { 0x09020000, 0x00000018 },
+    [VIRT_GPIO] =               { 0x09030000, 0x00001000 },
     [VIRT_MMIO] =               { 0x0a000000, 0x00000200 },
     /* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */
     [VIRT_PLATFORM_BUS] =       { 0x0c000000, 0x02000000 },
@@ -135,6 +137,7 @@ static const int a15irqmap[] = {
     [VIRT_UART] = 1,
     [VIRT_RTC] = 2,
     [VIRT_PCIE] = 3, /* ... to 6 */
+    [VIRT_GPIO] = 7,
     [VIRT_MMIO] = 16, /* ...to 16 + NUM_VIRTIO_TRANSPORTS - 1 */
     [VIRT_GIC_V2M] = 48, /* ...to 48 + NUM_GICV2M_SPIS - 1 */
     [VIRT_PLATFORM_BUS] = 112, /* ...to 112 + PLATFORM_BUS_NUM_IRQS -1 */
@@ -538,6 +541,61 @@ static void create_rtc(const VirtBoardInfo *vbi, qemu_irq *pic)
     g_free(nodename);
 }
 
+static DeviceState *pl061_dev;
+static void virt_powerdown_req(Notifier *n, void *opaque)
+{
+    /* use gpio Pin 3 for power button event */
+    qemu_set_irq(qdev_get_gpio_in(pl061_dev, 3), 1);
+}
+
+static Notifier virt_system_powerdown_notifier = {
+    .notify = virt_powerdown_req
+};
+
+static void create_gpio(const VirtBoardInfo *vbi, qemu_irq *pic)
+{
+    char *nodename;
+    hwaddr base = vbi->memmap[VIRT_GPIO].base;
+    hwaddr size = vbi->memmap[VIRT_GPIO].size;
+    int irq = vbi->irqmap[VIRT_GPIO];
+    const char compat[] = "arm,pl061\0arm,primecell";
+
+    pl061_dev = sysbus_create_simple("pl061", base, pic[irq]);
+
+    uint32_t phandle = qemu_fdt_alloc_phandle(vbi->fdt);
+    nodename = g_strdup_printf("/pl061@%" PRIx64, base);
+    qemu_fdt_add_subnode(vbi->fdt, nodename);
+    qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+                                 2, base, 2, size);
+    qemu_fdt_setprop(vbi->fdt, nodename, "compatible", compat, sizeof(compat));
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "#gpio-cells", 2);
+    qemu_fdt_setprop(vbi->fdt, nodename, "gpio-controller", NULL, 0);
+    qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts",
+                           GIC_FDT_IRQ_TYPE_SPI, irq,
+                           GIC_FDT_IRQ_FLAGS_LEVEL_HI);
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "clocks", vbi->clock_phandle);
+    qemu_fdt_setprop_string(vbi->fdt, nodename, "clock-names", "apb_pclk");
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "phandle", phandle);
+
+    qemu_fdt_add_subnode(vbi->fdt, "/gpio-keys");
+    qemu_fdt_setprop_string(vbi->fdt, "/gpio-keys", "compatible", "gpio-keys");
+    qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys", "#size-cells", 0);
+    qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys", "#address-cells", 1);
+
+    qemu_fdt_add_subnode(vbi->fdt, "/gpio-keys/poweroff");
+    qemu_fdt_setprop_string(vbi->fdt, "/gpio-keys/poweroff",
+                            "label", "GPIO Key Poweroff");
+    qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys/poweroff", "linux,code",
+                          KEY_POWER);
+    qemu_fdt_setprop_cells(vbi->fdt, "/gpio-keys/poweroff",
+                           "gpios", phandle, 3, 0);
+
+    /* connect powerdown request */
+    qemu_register_powerdown_notifier(&virt_system_powerdown_notifier);
+
+    g_free(nodename);
+}
+
 static void create_virtio_devices(const VirtBoardInfo *vbi, qemu_irq *pic)
 {
     int i;
@@ -1041,6 +1099,8 @@ static void machvirt_init(MachineState *machine)
 
     create_pcie(vbi, pic, vms->highmem);
 
+    create_gpio(vbi, pic);
+
     /* Create mmio transports, so the user can create virtio backends
      * (which will be automatically plugged in to the transports). If
      * no backend is created the transport will just sit harmlessly idle.

hw/block/virtio-blk.c

@@ -407,24 +407,16 @@ void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
     for (i = 0; i < mrb->num_reqs; i++) {
         VirtIOBlockReq *req = mrb->reqs[i];
         if (num_reqs > 0) {
-            bool merge = true;
-
-            /* merge would exceed maximum number of IOVs */
-            if (niov + req->qiov.niov > IOV_MAX) {
-                merge = false;
-            }
-
-            /* merge would exceed maximum transfer length of backend device */
-            if (req->qiov.size / BDRV_SECTOR_SIZE + nb_sectors > max_xfer_len) {
-                merge = false;
-            }
-
-            /* requests are not sequential */
-            if (sector_num + nb_sectors != req->sector_num) {
-                merge = false;
-            }
-
-            if (!merge) {
+            /*
+             * NOTE: We cannot merge the requests in below situations:
+             * 1. requests are not sequential
+             * 2. merge would exceed maximum number of IOVs
+             * 3. merge would exceed maximum transfer length of backend device
+             */
+            if (sector_num + nb_sectors != req->sector_num ||
+                niov > blk_get_max_iov(blk) - req->qiov.niov ||
+                req->qiov.size / BDRV_SECTOR_SIZE > max_xfer_len ||
+                nb_sectors > max_xfer_len - req->qiov.size / BDRV_SECTOR_SIZE) {
                 submit_requests(blk, mrb, start, num_reqs, niov);
                 num_reqs = 0;
             }

hw/block/xen_blkif.h

@@ -85,8 +85,10 @@ static inline void blkif_get_x86_32_req(blkif_request_t *dst, blkif_x86_32_reque
 		d->nr_sectors = s->nr_sectors;
 		return;
 	}
-	if (n > src->nr_segments)
-		n = src->nr_segments;
+	/* prevent the compiler from optimizing the code and using src->nr_segments instead */
+	barrier();
+	if (n > dst->nr_segments)
+		n = dst->nr_segments;
 	for (i = 0; i < n; i++)
 		dst->seg[i] = src->seg[i];
 }
@@ -106,8 +108,10 @@ static inline void blkif_get_x86_64_req(blkif_request_t *dst, blkif_x86_64_reque
 		d->nr_sectors = s->nr_sectors;
 		return;
 	}
-	if (n > src->nr_segments)
-		n = src->nr_segments;
+	/* prevent the compiler from optimizing the code and using src->nr_segments instead */
+	barrier();
+	if (n > dst->nr_segments)
+		n = dst->nr_segments;
 	for (i = 0; i < n; i++)
 		dst->seg[i] = src->seg[i];
 }

hw/block/xen_disk.c

@@ -825,6 +825,9 @@ static int blk_init(struct XenDevice *xendev)
     if (!strcmp("aio", blkdev->fileproto)) {
         blkdev->fileproto = "raw";
     }
+    if (!strcmp("vhd", blkdev->fileproto)) {
+        blkdev->fileproto = "vpc";
+    }
     if (blkdev->mode == NULL) {
         blkdev->mode = xenstore_read_be_str(&blkdev->xendev, "mode");
     }

hw/char/escc.c

@@ -714,7 +714,7 @@ MemoryRegion *escc_init(hwaddr base, qemu_irq irqA, qemu_irq irqB,
     return &d->mmio;
 }
 
-static const uint8_t qcode_to_keycode[Q_KEY_CODE_MAX] = {
+static const uint8_t qcode_to_keycode[Q_KEY_CODE__MAX] = {
     [Q_KEY_CODE_SHIFT]         = 99,
     [Q_KEY_CODE_SHIFT_R]       = 110,
     [Q_KEY_CODE_ALT]           = 19,

hw/char/etraxfs_ser.c

@@ -165,7 +165,7 @@ static void serial_receive(void *opaque, const uint8_t *buf, int size)
 
     /* Got a byte.  */
     if (s->rx_fifo_len >= 16) {
-        qemu_log("WARNING: UART dropped char.\n");
+        D(qemu_log("WARNING: UART dropped char.\n"));
         return;
     }
 

hw/core/loader.c

@@ -51,12 +51,10 @@
 #include "hw/nvram/fw_cfg.h"
 #include "exec/memory.h"
 #include "exec/address-spaces.h"
+#include "hw/boards.h"
 
 #include <zlib.h>
 
-bool option_rom_has_mr = false;
-bool rom_file_has_mr = true;
-
 static int roms_loaded;
 
 /* return the size or -1 if error */
@@ -754,6 +752,7 @@ int rom_add_file(const char *file, const char *fw_dir,
                  hwaddr addr, int32_t bootindex,
                  bool option_rom)
 {
+    MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
     Rom *rom;
     int rc, fd = -1;
     char devpath[100];
@@ -810,7 +809,7 @@ int rom_add_file(const char *file, const char *fw_dir,
                  basename);
         snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name);
 
-        if ((!option_rom || option_rom_has_mr) && rom_file_has_mr) {
+        if ((!option_rom || mc->option_rom_has_mr) && mc->rom_file_has_mr) {
             data = rom_set_mr(rom, OBJECT(fw_cfg), devpath);
         } else {
             data = rom->data;
@@ -838,6 +837,7 @@ MemoryRegion *rom_add_blob(const char *name, const void *blob, size_t len,
                    size_t max_len, hwaddr addr, const char *fw_file_name,
                    FWCfgReadCallback fw_callback, void *callback_opaque)
 {
+    MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
     Rom *rom;
     MemoryRegion *mr = NULL;
 
@@ -855,7 +855,7 @@ MemoryRegion *rom_add_blob(const char *name, const void *blob, size_t len,
 
         snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name);
 
-        if (rom_file_has_mr) {
+        if (mc->rom_file_has_mr) {
             data = rom_set_mr(rom, OBJECT(fw_cfg), devpath);
             mr = rom->mr;
         } else {

hw/core/machine.c

@@ -11,6 +11,7 @@
  */
 
 #include "hw/boards.h"
+#include "qapi-visit.h"
 #include "qapi/visitor.h"
 #include "hw/sysbus.h"
 #include "sysemu/sysemu.h"
@@ -31,12 +32,39 @@ static void machine_set_accel(Object *obj, const char *value, Error **errp)
     ms->accel = g_strdup(value);
 }
 
-static void machine_set_kernel_irqchip(Object *obj, bool value, Error **errp)
+static void machine_set_kernel_irqchip(Object *obj, Visitor *v,
+                                       void *opaque, const char *name,
+                                       Error **errp)
 {
+    Error *err = NULL;
     MachineState *ms = MACHINE(obj);
+    OnOffSplit mode;
 
-    ms->kernel_irqchip_allowed = value;
-    ms->kernel_irqchip_required = value;
+    visit_type_OnOffSplit(v, &mode, name, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    } else {
+        switch (mode) {
+        case ON_OFF_SPLIT_ON:
+            ms->kernel_irqchip_allowed = true;
+            ms->kernel_irqchip_required = true;
+            ms->kernel_irqchip_split = false;
+            break;
+        case ON_OFF_SPLIT_OFF:
+            ms->kernel_irqchip_allowed = false;
+            ms->kernel_irqchip_required = false;
+            ms->kernel_irqchip_split = false;
+            break;
+        case ON_OFF_SPLIT_SPLIT:
+            ms->kernel_irqchip_allowed = true;
+            ms->kernel_irqchip_required = true;
+            ms->kernel_irqchip_split = true;
+            break;
+        default:
+            abort();
+        }
+    }
 }
 
 static void machine_get_kvm_shadow_mem(Object *obj, Visitor *v,
@@ -314,6 +342,7 @@ static void machine_class_init(ObjectClass *oc, void *data)
 
     /* Default 128 MB as guest ram size */
     mc->default_ram_size = 128 * M_BYTE;
+    mc->rom_file_has_mr = true;
 }
 
 static void machine_class_base_init(ObjectClass *oc, void *data)
@@ -341,12 +370,12 @@ static void machine_initfn(Object *obj)
     object_property_set_description(obj, "accel",
                                     "Accelerator list",
                                     NULL);
-    object_property_add_bool(obj, "kernel-irqchip",
+    object_property_add(obj, "kernel-irqchip", "OnOffSplit",
                         NULL,
                         machine_set_kernel_irqchip,
-                             NULL);
+                        NULL, NULL, NULL);
     object_property_set_description(obj, "kernel-irqchip",
-                                    "Use KVM in-kernel irqchip",
+                                    "Configure KVM in-kernel irqchip",
                                     NULL);
     object_property_add(obj, "kvm-shadow-mem", "int",
                         machine_get_kvm_shadow_mem,
@@ -472,6 +501,11 @@ bool machine_kernel_irqchip_required(MachineState *machine)
     return machine->kernel_irqchip_required;
 }
 
+bool machine_kernel_irqchip_split(MachineState *machine)
+{
+    return machine->kernel_irqchip_split;
+}
+
 int machine_kvm_shadow_mem(MachineState *machine)
 {
     return machine->kvm_shadow_mem;

hw/display/jazz_led.c

@@ -233,8 +233,10 @@ static void jazz_led_text_update(void *opaque, console_ch_t *chardata)
 
     /* TODO: draw the segments */
     snprintf(buf, 2, "%02hhx\n", s->segments);
-    console_write_ch(chardata++, 0x00200100 | buf[0]);
-    console_write_ch(chardata++, 0x00200100 | buf[1]);
+    console_write_ch(chardata++, ATTR2CHTYPE(buf[0], QEMU_COLOR_BLUE,
+                                             QEMU_COLOR_BLACK, 1));
+    console_write_ch(chardata++, ATTR2CHTYPE(buf[1], QEMU_COLOR_BLUE,
+                                             QEMU_COLOR_BLACK, 1));
 
     dpy_text_update(s->con, 0, 0, 2, 1);
 }

hw/display/omap_lcd_template.h

@@ -136,7 +136,7 @@ static void glue(draw_line12_, DEPTH)(void *opaque,
     uint8_t r, g, b;
 
     do {
-        v = lduw_p((void *) s);
+        v = lduw_le_p((void *) s);
         r = (v >> 4) & 0xf0;
         g = v & 0xf0;
         b = (v << 4) & 0xf0;
@@ -159,7 +159,7 @@ static void glue(draw_line16_, DEPTH)(void *opaque,
     uint8_t r, g, b;
 
     do {
-        v = lduw_p((void *) s);
+        v = lduw_le_p((void *) s);
         r = (v >> 8) & 0xf8;
         g = (v >> 3) & 0xfc;
         b = (v << 3) & 0xf8;

hw/display/pxa2xx_lcd.c

@@ -309,10 +309,10 @@ static void pxa2xx_descriptor_load(PXA2xxLCDState *s)
         }
 
         cpu_physical_memory_read(descptr, &desc, sizeof(desc));
-        s->dma_ch[i].descriptor = tswap32(desc.fdaddr);
-        s->dma_ch[i].source = tswap32(desc.fsaddr);
-        s->dma_ch[i].id = tswap32(desc.fidr);
-        s->dma_ch[i].command = tswap32(desc.ldcmd);
+        s->dma_ch[i].descriptor = le32_to_cpu(desc.fdaddr);
+        s->dma_ch[i].source = le32_to_cpu(desc.fsaddr);
+        s->dma_ch[i].id = le32_to_cpu(desc.fidr);
+        s->dma_ch[i].command = le32_to_cpu(desc.ldcmd);
     }
 }
 

hw/display/vga.c

@@ -1979,7 +1979,8 @@ static void vga_update_text(void *opaque, console_ch_t *chardata)
     width = (s->last_width - size) / 2;
     dst = chardata + s->last_width + width;
     for (i = 0; i < size; i ++)
-        console_write_ch(dst ++, 0x00200100 | msg_buffer[i]);
+        console_write_ch(dst ++, ATTR2CHTYPE(msg_buffer[i], QEMU_COLOR_BLUE,
+                                             QEMU_COLOR_BLACK, 1));
 
     dpy_text_update(s->con, 0, 0, s->last_width, height);
 }

hw/display/virtio-gpu.c

@@ -146,14 +146,14 @@ static uint64_t virtio_gpu_get_features(VirtIODevice *vdev, uint64_t features,
     VirtIOGPU *g = VIRTIO_GPU(vdev);
 
     if (virtio_gpu_virgl_enabled(g->conf)) {
-        features |= (1 << VIRTIO_GPU_FEATURE_VIRGL);
+        features |= (1 << VIRTIO_GPU_F_VIRGL);
     }
     return features;
 }
 
 static void virtio_gpu_set_features(VirtIODevice *vdev, uint64_t features)
 {
-    static const uint32_t virgl = (1 << VIRTIO_GPU_FEATURE_VIRGL);
+    static const uint32_t virgl = (1 << VIRTIO_GPU_F_VIRGL);
     VirtIOGPU *g = VIRTIO_GPU(vdev);
 
     g->use_virgl_renderer = ((features & virgl) == virgl);

hw/display/xenfb.c

@@ -784,18 +784,20 @@ static void xenfb_invalidate(void *opaque)
 
 static void xenfb_handle_events(struct XenFB *xenfb)
 {
-    uint32_t prod, cons;
+    uint32_t prod, cons, out_cons;
     struct xenfb_page *page = xenfb->c.page;
 
     prod = page->out_prod;
-    if (prod == page->out_cons)
+    out_cons = page->out_cons;
+    if (prod == out_cons)
 	return;
     xen_rmb();		/* ensure we see ring contents up to prod */
-    for (cons = page->out_cons; cons != prod; cons++) {
+    for (cons = out_cons; cons != prod; cons++) {
 	union xenfb_out_event *event = &XENFB_OUT_RING_REF(page, cons);
+        uint8_t type = event->type;
 	int x, y, w, h;
 
-	switch (event->type) {
+	switch (type) {
 	case XENFB_TYPE_UPDATE:
 	    if (xenfb->up_count == UP_QUEUE)
 		xenfb->up_fullscreen = 1;

hw/dma/soc_dma.c

@@ -269,11 +269,10 @@ void soc_dma_port_add_fifo(struct soc_dma_s *soc, hwaddr virt_base,
         if (entry->type == soc_dma_port_mem) {
             if (entry->addr <= virt_base &&
                             entry->addr + entry->u.mem.size > virt_base) {
-                fprintf(stderr, "%s: FIFO at " TARGET_FMT_lx
-                                " collides with RAM region at " TARGET_FMT_lx
-                                "-" TARGET_FMT_lx "\n", __FUNCTION__,
-                                (target_ulong) virt_base,
-                                (target_ulong) entry->addr, (target_ulong)
+                fprintf(stderr, "%s: FIFO at %"PRIx64
+                                " collides with RAM region at %"PRIx64
+                                "-%"PRIx64 "\n", __func__,
+                                virt_base, entry->addr,
                                 (entry->addr + entry->u.mem.size));
                 exit(-1);
             }
@@ -284,10 +283,9 @@ void soc_dma_port_add_fifo(struct soc_dma_s *soc, hwaddr virt_base,
             while (entry < dma->memmap + dma->memmap_size &&
                             entry->addr <= virt_base) {
                 if (entry->addr == virt_base && entry->u.fifo.out == out) {
-                    fprintf(stderr, "%s: FIFO at " TARGET_FMT_lx
-                                    " collides FIFO at " TARGET_FMT_lx "\n",
-                                    __FUNCTION__, (target_ulong) virt_base,
-                                    (target_ulong) entry->addr);
+                    fprintf(stderr, "%s: FIFO at %"PRIx64
+                                    " collides FIFO at %"PRIx64 "\n",
+                                    __func__, virt_base, entry->addr);
                     exit(-1);
                 }
 
@@ -322,13 +320,11 @@ void soc_dma_port_add_mem(struct soc_dma_s *soc, uint8_t *phys_base,
             if ((entry->addr >= virt_base && entry->addr < virt_base + size) ||
                             (entry->addr <= virt_base &&
                              entry->addr + entry->u.mem.size > virt_base)) {
-                fprintf(stderr, "%s: RAM at " TARGET_FMT_lx "-" TARGET_FMT_lx
-                                " collides with RAM region at " TARGET_FMT_lx
-                                "-" TARGET_FMT_lx "\n", __FUNCTION__,
-                                (target_ulong) virt_base,
-                                (target_ulong) (virt_base + size),
-                                (target_ulong) entry->addr, (target_ulong)
-                                (entry->addr + entry->u.mem.size));
+                fprintf(stderr, "%s: RAM at %"PRIx64 "-%"PRIx64
+                                " collides with RAM region at %"PRIx64
+                                "-%"PRIx64 "\n", __func__,
+                                virt_base, virt_base + size,
+                                entry->addr, entry->addr + entry->u.mem.size);
                 exit(-1);
             }
 
@@ -337,12 +333,11 @@ void soc_dma_port_add_mem(struct soc_dma_s *soc, uint8_t *phys_base,
         } else {
             if (entry->addr >= virt_base &&
                             entry->addr < virt_base + size) {
-                fprintf(stderr, "%s: RAM at " TARGET_FMT_lx "-" TARGET_FMT_lx
-                                " collides with FIFO at " TARGET_FMT_lx
-                                "\n", __FUNCTION__,
-                                (target_ulong) virt_base,
-                                (target_ulong) (virt_base + size),
-                                (target_ulong) entry->addr);
+                fprintf(stderr, "%s: RAM at %"PRIx64 "-%"PRIx64
+                                " collides with FIFO at %"PRIx64
+                                "\n", __func__,
+                                virt_base, virt_base + size,
+                                entry->addr);
                 exit(-1);
             }
 

hw/gpio/imx_gpio.c

@@ -62,7 +62,12 @@ static const char *imx_gpio_reg_name(uint32_t reg)
 
 static void imx_gpio_update_int(IMXGPIOState *s)
 {
-    qemu_set_irq(s->irq, (s->isr & s->imr) ? 1 : 0);
+    if (s->has_upper_pin_irq) {
+        qemu_set_irq(s->irq[0], (s->isr & s->imr & 0x0000FFFF) ? 1 : 0);
+        qemu_set_irq(s->irq[1], (s->isr & s->imr & 0xFFFF0000) ? 1 : 0);
+    } else {
+        qemu_set_irq(s->irq[0], (s->isr & s->imr) ? 1 : 0);
+    }
 }
 
 static void imx_gpio_set_int_line(IMXGPIOState *s, int line, IMXGPIOLevel level)
@@ -282,6 +287,8 @@ static const VMStateDescription vmstate_imx_gpio = {
 
 static Property imx_gpio_properties[] = {
     DEFINE_PROP_BOOL("has-edge-sel", IMXGPIOState, has_edge_sel, true),
+    DEFINE_PROP_BOOL("has-upper-pin-irq", IMXGPIOState, has_upper_pin_irq,
+                     false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -311,7 +318,8 @@ static void imx_gpio_realize(DeviceState *dev, Error **errp)
     qdev_init_gpio_in(DEVICE(s), imx_gpio_set, IMX_GPIO_PIN_COUNT);
     qdev_init_gpio_out(DEVICE(s), s->output, IMX_GPIO_PIN_COUNT);
 
-    sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq);
+    sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq[0]);
+    sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq[1]);
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem);
 }
 

hw/i386/acpi-build.c

@@ -39,6 +39,7 @@
 #include "hw/loader.h"
 #include "hw/isa/isa.h"
 #include "hw/acpi/memory_hotplug.h"
+#include "hw/mem/nvdimm.h"
 #include "sysemu/tpm.h"
 #include "hw/acpi/tpm.h"
 #include "sysemu/tpm_backend.h"
@@ -361,7 +362,7 @@ build_fadt(GArray *table_data, GArray *linker, AcpiPmInfo *pm,
     fadt_setup(fadt, pm);
 
     build_header(linker, table_data,
-                 (void *)fadt, "FACP", sizeof(*fadt), 1);
+                 (void *)fadt, "FACP", sizeof(*fadt), 1, NULL);
 }
 
 static void
@@ -431,7 +432,7 @@ build_madt(GArray *table_data, GArray *linker, AcpiCpuInfo *cpu,
 
     build_header(linker, table_data,
                  (void *)(table_data->data + madt_start), "APIC",
-                 table_data->len - madt_start, 1);
+                 table_data->len - madt_start, 1, NULL);
 }
 
 /* Assign BSEL property to all buses.  In the future, this can be changed
@@ -469,7 +470,7 @@ static void build_append_pcihp_notify_entry(Aml *method, int slot)
     Aml *if_ctx;
     int32_t devfn = PCI_DEVFN(slot, 0);
 
-    if_ctx = aml_if(aml_and(aml_arg(0), aml_int(0x1U << slot)));
+    if_ctx = aml_if(aml_and(aml_arg(0), aml_int(0x1U << slot), NULL));
     aml_append(if_ctx, aml_notify(aml_name("S%.02X", devfn), aml_arg(1)));
     aml_append(method, if_ctx);
 }
@@ -487,7 +488,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus,
         int64_t bsel_val = qint_get_int(qobject_to_qint(bsel));
 
         aml_append(parent_scope, aml_name_decl("BSEL", aml_int(bsel_val)));
-        notify_method = aml_method("DVNT", 2);
+        notify_method = aml_method("DVNT", 2, AML_NOTSERIALIZED);
     }
 
     for (i = 0; i < ARRAY_SIZE(bus->devices); i += PCI_FUNC_MAX) {
@@ -503,7 +504,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus,
                 dev = aml_device("S%.02X", PCI_DEVFN(slot, 0));
                 aml_append(dev, aml_name_decl("_SUN", aml_int(slot)));
                 aml_append(dev, aml_name_decl("_ADR", aml_int(slot << 16)));
-                method = aml_method("_EJ0", 1);
+                method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
                 aml_append(method,
                     aml_call2("PCEJ", aml_name("BSEL"), aml_name("_SUN"))
                 );
@@ -546,22 +547,22 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus,
                 s3d = 0;
             }
 
-            method = aml_method("_S1D", 0);
+            method = aml_method("_S1D", 0, AML_NOTSERIALIZED);
             aml_append(method, aml_return(aml_int(0)));
             aml_append(dev, method);
 
-            method = aml_method("_S2D", 0);
+            method = aml_method("_S2D", 0, AML_NOTSERIALIZED);
             aml_append(method, aml_return(aml_int(0)));
             aml_append(dev, method);
 
-            method = aml_method("_S3D", 0);
+            method = aml_method("_S3D", 0, AML_NOTSERIALIZED);
             aml_append(method, aml_return(aml_int(s3d)));
             aml_append(dev, method);
         } else if (hotplug_enabled_dev) {
             /* add _SUN/_EJ0 to make slot hotpluggable  */
             aml_append(dev, aml_name_decl("_SUN", aml_int(slot)));
 
-            method = aml_method("_EJ0", 1);
+            method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
             aml_append(method,
                 aml_call2("PCEJ", aml_name("BSEL"), aml_name("_SUN"))
             );
@@ -590,7 +591,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus,
     /* Append PCNT method to notify about events on local and child buses.
      * Add unconditionally for root since DSDT expects it.
      */
-    method = aml_method("PCNT", 0);
+    method = aml_method("PCNT", 0, AML_NOTSERIALIZED);
 
     /* If bus supports hotplug select it and notify about local events */
     if (bsel) {
@@ -651,7 +652,7 @@ static Aml *build_prt(void)
 {
     Aml *method, *while_ctx, *pin, *res;
 
-    method = aml_method("_PRT", 0);
+    method = aml_method("_PRT", 0, AML_NOTSERIALIZED);
     res = aml_local(0);
     pin = aml_local(1);
     aml_append(method, aml_store(aml_package(128), res));
@@ -666,10 +667,11 @@ static Aml *build_prt(void)
 
         /* slot = pin >> 2 */
         aml_append(while_ctx,
-                   aml_store(aml_shiftright(pin, aml_int(2)), slot));
+                   aml_store(aml_shiftright(pin, aml_int(2), NULL), slot));
         /* lnk_idx = (slot + pin) & 3 */
         aml_append(while_ctx,
-                   aml_store(aml_and(aml_add(pin, slot), aml_int(3)), lnk_idx));
+            aml_store(aml_and(aml_add(pin, slot, NULL), aml_int(3), NULL),
+                      lnk_idx));
 
         /* route[2] = "LNK[D|A|B|C]", selection based on pin % 3  */
         aml_append(while_ctx, initialize_route(route, "LNKD", lnk_idx, 0));
@@ -679,11 +681,13 @@ static Aml *build_prt(void)
 
         /* route[0] = 0x[slot]FFFF */
         aml_append(while_ctx,
-            aml_store(aml_or(aml_shiftleft(slot, aml_int(16)), aml_int(0xFFFF)),
+            aml_store(aml_or(aml_shiftleft(slot, aml_int(16)), aml_int(0xFFFF),
+                             NULL),
                       aml_index(route, aml_int(0))));
         /* route[1] = pin & 3 */
         aml_append(while_ctx,
-            aml_store(aml_and(pin, aml_int(3)), aml_index(route, aml_int(1))));
+            aml_store(aml_and(pin, aml_int(3), NULL),
+                      aml_index(route, aml_int(1))));
         /* res[pin] = route */
         aml_append(while_ctx, aml_store(route, aml_index(res, pin)));
         /* pin++ */
@@ -762,16 +766,59 @@ static void crs_replace_with_free_ranges(GPtrArray *ranges,
     g_ptr_array_free(free_ranges, false);
 }
 
+/*
+ * crs_range_merge - merges adjacent ranges in the given array.
+ * Array elements are deleted and replaced with the merged ranges.
+ */
+static void crs_range_merge(GPtrArray *range)
+{
+    GPtrArray *tmp =  g_ptr_array_new_with_free_func(crs_range_free);
+    CrsRangeEntry *entry;
+    uint64_t range_base, range_limit;
+    int i;
+
+    if (!range->len) {
+        return;
+    }
+
+    g_ptr_array_sort(range, crs_range_compare);
+
+    entry = g_ptr_array_index(range, 0);
+    range_base = entry->base;
+    range_limit = entry->limit;
+    for (i = 1; i < range->len; i++) {
+        entry = g_ptr_array_index(range, i);
+        if (entry->base - 1 == range_limit) {
+            range_limit = entry->limit;
+        } else {
+            crs_range_insert(tmp, range_base, range_limit);
+            range_base = entry->base;
+            range_limit = entry->limit;
+        }
+    }
+    crs_range_insert(tmp, range_base, range_limit);
+
+    g_ptr_array_set_size(range, 0);
+    for (i = 0; i < tmp->len; i++) {
+        entry = g_ptr_array_index(tmp, i);
+        crs_range_insert(range, entry->base, entry->limit);
+    }
+    g_ptr_array_free(tmp, true);
+}
+
 static Aml *build_crs(PCIHostState *host,
                       GPtrArray *io_ranges, GPtrArray *mem_ranges)
 {
     Aml *crs = aml_resource_template();
+    GPtrArray *host_io_ranges = g_ptr_array_new_with_free_func(crs_range_free);
+    GPtrArray *host_mem_ranges = g_ptr_array_new_with_free_func(crs_range_free);
+    CrsRangeEntry *entry;
     uint8_t max_bus = pci_bus_num(host->bus);
     uint8_t type;
     int devfn;
+    int i;
 
     for (devfn = 0; devfn < ARRAY_SIZE(host->bus->devices); devfn++) {
-        int i;
         uint64_t range_base, range_limit;
         PCIDevice *dev = host->bus->devices[devfn];
 
@@ -794,26 +841,9 @@ static Aml *build_crs(PCIHostState *host,
             }
 
             if (r->type & PCI_BASE_ADDRESS_SPACE_IO) {
-                aml_append(crs,
-                    aml_word_io(AML_MIN_FIXED, AML_MAX_FIXED,
-                                AML_POS_DECODE, AML_ENTIRE_RANGE,
-                                0,
-                                range_base,
-                                range_limit,
-                                0,
-                                range_limit - range_base + 1));
-                crs_range_insert(io_ranges, range_base, range_limit);
+                crs_range_insert(host_io_ranges, range_base, range_limit);
             } else { /* "memory" */
-                aml_append(crs,
-                    aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED,
-                                     AML_MAX_FIXED, AML_NON_CACHEABLE,
-                                     AML_READ_WRITE,
-                                     0,
-                                     range_base,
-                                     range_limit,
-                                     0,
-                                     range_limit - range_base + 1));
-                crs_range_insert(mem_ranges, range_base, range_limit);
+                crs_range_insert(host_mem_ranges, range_base, range_limit);
             }
         }
 
@@ -832,15 +862,7 @@ static Aml *build_crs(PCIHostState *host,
              * that do not support multiple root buses
              */
             if (range_base && range_base <= range_limit) {
-                aml_append(crs,
-                           aml_word_io(AML_MIN_FIXED, AML_MAX_FIXED,
-                                       AML_POS_DECODE, AML_ENTIRE_RANGE,
-                                       0,
-                                       range_base,
-                                       range_limit,
-                                       0,
-                                       range_limit - range_base + 1));
-                crs_range_insert(io_ranges, range_base, range_limit);
+                crs_range_insert(host_io_ranges, range_base, range_limit);
             }
 
             range_base =
@@ -853,16 +875,7 @@ static Aml *build_crs(PCIHostState *host,
              * that do not support multiple root buses
              */
             if (range_base && range_base <= range_limit) {
-                aml_append(crs,
-                           aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED,
-                                            AML_MAX_FIXED, AML_NON_CACHEABLE,
-                                            AML_READ_WRITE,
-                                            0,
-                                            range_base,
-                                            range_limit,
-                                            0,
-                                            range_limit - range_base + 1));
-                crs_range_insert(mem_ranges, range_base, range_limit);
+                crs_range_insert(host_mem_ranges, range_base, range_limit);
             }
 
             range_base =
@@ -875,19 +888,35 @@ static Aml *build_crs(PCIHostState *host,
              * that do not support multiple root buses
              */
             if (range_base && range_base <= range_limit) {
+                crs_range_insert(host_mem_ranges, range_base, range_limit);
+            }
+        }
+    }
+
+    crs_range_merge(host_io_ranges);
+    for (i = 0; i < host_io_ranges->len; i++) {
+        entry = g_ptr_array_index(host_io_ranges, i);
+        aml_append(crs,
+                   aml_word_io(AML_MIN_FIXED, AML_MAX_FIXED,
+                               AML_POS_DECODE, AML_ENTIRE_RANGE,
+                               0, entry->base, entry->limit, 0,
+                               entry->limit - entry->base + 1));
+        crs_range_insert(io_ranges, entry->base, entry->limit);
+    }
+    g_ptr_array_free(host_io_ranges, true);
+
+    crs_range_merge(host_mem_ranges);
+    for (i = 0; i < host_mem_ranges->len; i++) {
+        entry = g_ptr_array_index(host_mem_ranges, i);
         aml_append(crs,
                    aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED,
                                     AML_MAX_FIXED, AML_NON_CACHEABLE,
                                     AML_READ_WRITE,
-                                            0,
-                                            range_base,
-                                            range_limit,
-                                            0,
-                                            range_limit - range_base + 1));
-                crs_range_insert(mem_ranges, range_base, range_limit);
-            }
-        }
+                                    0, entry->base, entry->limit, 0,
+                                    entry->limit - entry->base + 1));
+        crs_range_insert(mem_ranges, entry->base, entry->limit);
     }
+    g_ptr_array_free(host_mem_ranges, true);
 
     aml_append(crs,
         aml_word_bus_number(AML_MIN_FIXED, AML_MAX_FIXED, AML_POS_DECODE,
@@ -925,8 +954,7 @@ build_ssdt(GArray *table_data, GArray *linker,
     /* Reserve space for header */
     acpi_data_push(ssdt->buf, sizeof(AcpiTableHeader));
 
-    /* Extra PCI root buses are implemented  only for i440fx */
-    bus = find_i440fx();
+    bus = PC_MACHINE(machine)->bus;
     if (bus) {
         QLIST_FOREACH(bus, &bus->child, sibling) {
             uint8_t bus_num = pci_bus_num(bus);
@@ -1105,19 +1133,19 @@ build_ssdt(GArray *table_data, GArray *linker,
 
         aml_append(dev, aml_operation_region("PEOR", AML_SYSTEM_IO,
                                               misc->pvpanic_port, 1));
-        field = aml_field("PEOR", AML_BYTE_ACC, AML_PRESERVE);
+        field = aml_field("PEOR", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE);
         aml_append(field, aml_named_field("PEPT", 8));
         aml_append(dev, field);
 
         /* device present, functioning, decoding, shown in UI */
         aml_append(dev, aml_name_decl("_STA", aml_int(0xF)));
 
-        method = aml_method("RDPT", 0);
+        method = aml_method("RDPT", 0, AML_NOTSERIALIZED);
         aml_append(method, aml_store(aml_name("PEPT"), aml_local(0)));
         aml_append(method, aml_return(aml_local(0)));
         aml_append(dev, method);
 
-        method = aml_method("WRPT", 1);
+        method = aml_method("WRPT", 1, AML_NOTSERIALIZED);
         aml_append(method, aml_store(aml_arg(0), aml_name("PEPT")));
         aml_append(dev, method);
 
@@ -1145,7 +1173,7 @@ build_ssdt(GArray *table_data, GArray *linker,
         /* declare CPU hotplug MMIO region and PRS field to access it */
         aml_append(sb_scope, aml_operation_region(
             "PRST", AML_SYSTEM_IO, pm->cpu_hp_io_base, pm->cpu_hp_io_len));
-        field = aml_field("PRST", AML_BYTE_ACC, AML_PRESERVE);
+        field = aml_field("PRST", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE);
         aml_append(field, aml_named_field("PRS", 256));
         aml_append(sb_scope, field);
 
@@ -1153,15 +1181,15 @@ build_ssdt(GArray *table_data, GArray *linker,
         for (i = 0; i < acpi_cpus; i++) {
             dev = aml_processor(i, 0, 0, "CP%.02X", i);
 
-            method = aml_method("_MAT", 0);
+            method = aml_method("_MAT", 0, AML_NOTSERIALIZED);
             aml_append(method, aml_return(aml_call1("CPMA", aml_int(i))));
             aml_append(dev, method);
 
-            method = aml_method("_STA", 0);
+            method = aml_method("_STA", 0, AML_NOTSERIALIZED);
             aml_append(method, aml_return(aml_call1("CPST", aml_int(i))));
             aml_append(dev, method);
 
-            method = aml_method("_EJ0", 1);
+            method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
             aml_append(method,
                 aml_return(aml_call2("CPEJ", aml_int(i), aml_arg(0)))
             );
@@ -1174,7 +1202,7 @@ build_ssdt(GArray *table_data, GArray *linker,
          *   Method(NTFY, 2) {If (LEqual(Arg0, 0x00)) {Notify(CP00, Arg1)} ...}
          */
         /* Arg0 = Processor ID = APIC ID */
-        method = aml_method("NTFY", 2);
+        method = aml_method("NTFY", 2, AML_NOTSERIALIZED);
         for (i = 0; i < acpi_cpus; i++) {
             ifctx = aml_if(aml_equal(aml_arg(0), aml_int(i)));
             aml_append(ifctx,
@@ -1220,7 +1248,7 @@ build_ssdt(GArray *table_data, GArray *linker,
         );
 
         field = aml_field(stringify(MEMORY_HOTPLUG_IO_REGION), AML_DWORD_ACC,
-                          AML_PRESERVE);
+                          AML_NOLOCK, AML_PRESERVE);
         aml_append(field, /* read only */
             aml_named_field(stringify(MEMORY_SLOT_ADDR_LOW), 32));
         aml_append(field, /* read only */
@@ -1234,7 +1262,7 @@ build_ssdt(GArray *table_data, GArray *linker,
         aml_append(scope, field);
 
         field = aml_field(stringify(MEMORY_HOTPLUG_IO_REGION), AML_BYTE_ACC,
-                          AML_WRITE_AS_ZEROS);
+                          AML_NOLOCK, AML_WRITE_AS_ZEROS);
         aml_append(field, aml_reserved_field(160 /* bits, Offset(20) */));
         aml_append(field, /* 1 if enabled, read only */
             aml_named_field(stringify(MEMORY_SLOT_ENABLED), 1));
@@ -1250,7 +1278,7 @@ build_ssdt(GArray *table_data, GArray *linker,
         aml_append(scope, field);
 
         field = aml_field(stringify(MEMORY_HOTPLUG_IO_REGION), AML_DWORD_ACC,
-                          AML_PRESERVE);
+                          AML_NOLOCK, AML_PRESERVE);
         aml_append(field, /* DIMM selector, write only */
             aml_named_field(stringify(MEMORY_SLOT_SLECTOR), 32));
         aml_append(field, /* _OST event code, write only */
@@ -1269,29 +1297,29 @@ build_ssdt(GArray *table_data, GArray *linker,
             aml_append(dev, aml_name_decl("_UID", aml_string("0x%02X", i)));
             aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C80")));
 
-            method = aml_method("_CRS", 0);
+            method = aml_method("_CRS", 0, AML_NOTSERIALIZED);
             s = BASEPATH stringify(MEMORY_SLOT_CRS_METHOD);
             aml_append(method, aml_return(aml_call1(s, aml_name("_UID"))));
             aml_append(dev, method);
 
-            method = aml_method("_STA", 0);
+            method = aml_method("_STA", 0, AML_NOTSERIALIZED);
             s = BASEPATH stringify(MEMORY_SLOT_STATUS_METHOD);
             aml_append(method, aml_return(aml_call1(s, aml_name("_UID"))));
             aml_append(dev, method);
 
-            method = aml_method("_PXM", 0);
+            method = aml_method("_PXM", 0, AML_NOTSERIALIZED);
             s = BASEPATH stringify(MEMORY_SLOT_PROXIMITY_METHOD);
             aml_append(method, aml_return(aml_call1(s, aml_name("_UID"))));
             aml_append(dev, method);
 
-            method = aml_method("_OST", 3);
+            method = aml_method("_OST", 3, AML_NOTSERIALIZED);
             s = BASEPATH stringify(MEMORY_SLOT_OST_METHOD);
             aml_append(method, aml_return(aml_call4(
                 s, aml_name("_UID"), aml_arg(0), aml_arg(1), aml_arg(2)
             )));
             aml_append(dev, method);
 
-            method = aml_method("_EJ0", 1);
+            method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
             s = BASEPATH stringify(MEMORY_SLOT_EJECT_METHOD);
             aml_append(method, aml_return(aml_call2(
                        s, aml_name("_UID"), aml_arg(0))));
@@ -1303,7 +1331,8 @@ build_ssdt(GArray *table_data, GArray *linker,
         /* build Method(MEMORY_SLOT_NOTIFY_METHOD, 2) {
          *     If (LEqual(Arg0, 0x00)) {Notify(MP00, Arg1)} ... }
          */
-        method = aml_method(stringify(MEMORY_SLOT_NOTIFY_METHOD), 2);
+        method = aml_method(stringify(MEMORY_SLOT_NOTIFY_METHOD), 2,
+                            AML_NOTSERIALIZED);
         for (i = 0; i < nr_mem; i++) {
             ifctx = aml_if(aml_equal(aml_arg(0), aml_int(i)));
             aml_append(ifctx,
@@ -1349,7 +1378,7 @@ build_ssdt(GArray *table_data, GArray *linker,
     g_array_append_vals(table_data, ssdt->buf->data, ssdt->buf->len);
     build_header(linker, table_data,
         (void *)(table_data->data + table_data->len - ssdt->buf->len),
-        "SSDT", ssdt->buf->len, 1);
+        "SSDT", ssdt->buf->len, 1, NULL);
     free_aml_allocator();
 }
 
@@ -1365,7 +1394,7 @@ build_hpet(GArray *table_data, GArray *linker)
     hpet->timer_block_id = cpu_to_le32(0x8086a201);
     hpet->addr.address = cpu_to_le64(HPET_BASE);
     build_header(linker, table_data,
-                 (void *)hpet, "HPET", sizeof(*hpet), 1);
+                 (void *)hpet, "HPET", sizeof(*hpet), 1, NULL);
 }
 
 static void
@@ -1388,7 +1417,7 @@ build_tpm_tcpa(GArray *table_data, GArray *linker, GArray *tcpalog)
                                    sizeof(tcpa->log_area_start_address));
 
     build_header(linker, table_data,
-                 (void *)tcpa, "TCPA", sizeof(*tcpa), 2);
+                 (void *)tcpa, "TCPA", sizeof(*tcpa), 2, NULL);
 
     acpi_data_push(tcpalog, TPM_LOG_AREA_MINIMUM_SIZE);
 }
@@ -1405,7 +1434,7 @@ build_tpm2(GArray *table_data, GArray *linker)
     tpm2_ptr->start_method = cpu_to_le32(TPM2_START_METHOD_MMIO);
 
     build_header(linker, table_data,
-                 (void *)tpm2_ptr, "TPM2", sizeof(*tpm2_ptr), 4);
+                 (void *)tpm2_ptr, "TPM2", sizeof(*tpm2_ptr), 4, NULL);
 }
 
 typedef enum {
@@ -1519,7 +1548,7 @@ build_srat(GArray *table_data, GArray *linker, PcGuestInfo *guest_info)
     build_header(linker, table_data,
                  (void *)(table_data->data + srat_start),
                  "SRAT",
-                 table_data->len - srat_start, 1);
+                 table_data->len - srat_start, 1, NULL);
 }
 
 static void
@@ -1548,7 +1577,7 @@ build_mcfg_q35(GArray *table_data, GArray *linker, AcpiMcfgInfo *info)
     } else {
         sig = "MCFG";
     }
-    build_header(linker, table_data, (void *)mcfg, sig, len, 1);
+    build_header(linker, table_data, (void *)mcfg, sig, len, 1, NULL);
 }
 
 static void
@@ -1572,7 +1601,7 @@ build_dmar_q35(GArray *table_data, GArray *linker)
     drhd->address = cpu_to_le64(Q35_HOST_BRIDGE_IOMMU_ADDR);
 
     build_header(linker, table_data, (void *)(table_data->data + dmar_start),
-                 "DMAR", table_data->len - dmar_start, 1);
+                 "DMAR", table_data->len - dmar_start, 1, NULL);
 }
 
 static void
@@ -1587,7 +1616,7 @@ build_dsdt(GArray *table_data, GArray *linker, AcpiMiscInfo *misc)
 
     memset(dsdt, 0, sizeof *dsdt);
     build_header(linker, table_data, dsdt, "DSDT",
-                 misc->dsdt_size, 1);
+                 misc->dsdt_size, 1, NULL);
 }
 
 static GArray *
@@ -1658,6 +1687,13 @@ static bool acpi_has_iommu(void)
     return intel_iommu && !ambiguous;
 }
 
+static bool acpi_has_nvdimm(void)
+{
+    PCMachineState *pcms = PC_MACHINE(qdev_get_machine());
+
+    return pcms->nvdimm;
+}
+
 static
 void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
 {
@@ -1742,6 +1778,10 @@ void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
         build_dmar_q35(tables_blob, tables->linker);
     }
 
+    if (acpi_has_nvdimm()) {
+        nvdimm_build_acpi(table_offsets, tables_blob, tables->linker);
+    }
+
     /* Add tables supplied by user (if any) */
     for (u = acpi_table_first(); u; u = acpi_table_next(u)) {
         unsigned len = acpi_table_len(u);
@@ -1818,7 +1858,7 @@ static void acpi_ram_update(MemoryRegion *mr, GArray *data)
     memory_region_set_dirty(mr, 0, size);
 }
 
-static void acpi_build_update(void *build_opaque, uint32_t offset)
+static void acpi_build_update(void *build_opaque)
 {
     AcpiBuildState *build_state = build_opaque;
     AcpiBuildTables tables;

hw/i386/pc.c

@@ -65,6 +65,7 @@
 #include "hw/mem/pc-dimm.h"
 #include "qapi/visitor.h"
 #include "qapi-visit.h"
+#include "qom/cpu.h"
 
 /* debug PC/ISA interrupts */
 //#define DEBUG_IRQ
@@ -76,15 +77,6 @@
 #define DPRINTF(fmt, ...)
 #endif
 
-/* Leave a chunk of memory at the top of RAM for the BIOS ACPI tables
- * (128K) and other BIOS datastructures (less than 4K reported to be used at
- * the moment, 32K should be enough for a while).  */
-static unsigned acpi_data_size = 0x20000 + 0x8000;
-void pc_set_legacy_acpi_data_size(void)
-{
-    acpi_data_size = 0x10000;
-}
-
 #define BIOS_CFG_IOPORT 0x510
 #define FW_CFG_ACPI_TABLES (FW_CFG_ARCH_LOCAL + 0)
 #define FW_CFG_SMBIOS_ENTRIES (FW_CFG_ARCH_LOCAL + 1)
@@ -840,6 +832,7 @@ static void load_linux(PCMachineState *pcms,
     FILE *f;
     char *vmode;
     MachineState *machine = MACHINE(pcms);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
     const char *kernel_filename = machine->kernel_filename;
     const char *initrd_filename = machine->initrd_filename;
     const char *kernel_cmdline = machine->kernel_cmdline;
@@ -907,8 +900,8 @@ static void load_linux(PCMachineState *pcms,
         initrd_max = 0x37ffffff;
     }
 
-    if (initrd_max >= pcms->below_4g_mem_size - acpi_data_size) {
-        initrd_max = pcms->below_4g_mem_size - acpi_data_size - 1;
+    if (initrd_max >= pcms->below_4g_mem_size - pcmc->acpi_data_size) {
+        initrd_max = pcms->below_4g_mem_size - pcmc->acpi_data_size - 1;
     }
 
     fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr);
@@ -1174,7 +1167,7 @@ void pc_guest_info_machine_done(Notifier *notifier, void *data)
     PcGuestInfoState *guest_info_state = container_of(notifier,
                                                       PcGuestInfoState,
                                                       machine_done);
-    PCIBus *bus = find_i440fx();
+    PCIBus *bus = PC_MACHINE(qdev_get_machine())->bus;
 
     if (bus) {
         int extra_hosts = 0;
@@ -1302,6 +1295,7 @@ FWCfgState *pc_memory_init(PCMachineState *pcms,
     MemoryRegion *ram_below_4g, *ram_above_4g;
     FWCfgState *fw_cfg;
     MachineState *machine = MACHINE(pcms);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
 
     assert(machine->ram_size == pcms->below_4g_mem_size +
                                 pcms->above_4g_mem_size);
@@ -1363,7 +1357,7 @@ FWCfgState *pc_memory_init(PCMachineState *pcms,
         pcms->hotplug_memory.base =
             ROUND_UP(0x100000000ULL + pcms->above_4g_mem_size, 1ULL << 30);
 
-        if (pcms->enforce_aligned_dimm) {
+        if (pcmc->enforce_aligned_dimm) {
             /* size hotplug region assuming 1G page max alignment per slot */
             hotplug_mem_size += (1ULL << 30) * machine->ram_slots;
         }
@@ -1517,7 +1511,7 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,
     qemu_register_boot_set(pc_boot_set, *rtc_state);
 
     if (!xen_enabled()) {
-        if (kvm_irqchip_in_kernel()) {
+        if (kvm_pit_in_kernel()) {
             pit = kvm_pit_init(isa_bus, 0x40);
         } else {
             pit = pit_init(isa_bus, 0x40, pit_isa_irq, pit_alt_irq);
@@ -1592,7 +1586,7 @@ void ioapic_init_gsi(GSIState *gsi_state, const char *parent_name)
     SysBusDevice *d;
     unsigned int i;
 
-    if (kvm_irqchip_in_kernel()) {
+    if (kvm_ioapic_in_kernel()) {
         dev = qdev_create(NULL, "kvm-ioapic");
     } else {
         dev = qdev_create(NULL, "ioapic");
@@ -1616,12 +1610,13 @@ static void pc_dimm_plug(HotplugHandler *hotplug_dev,
     HotplugHandlerClass *hhc;
     Error *local_err = NULL;
     PCMachineState *pcms = PC_MACHINE(hotplug_dev);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
     PCDIMMDevice *dimm = PC_DIMM(dev);
     PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
     MemoryRegion *mr = ddc->get_memory_region(dimm);
     uint64_t align = TARGET_PAGE_SIZE;
 
-    if (memory_region_get_alignment(mr) && pcms->enforce_aligned_dimm) {
+    if (memory_region_get_alignment(mr) && pcmc->enforce_aligned_dimm) {
         align = memory_region_get_alignment(mr);
     }
 
@@ -1870,11 +1865,18 @@ static void pc_machine_set_smm(Object *obj, Visitor *v, void *opaque,
     visit_type_OnOffAuto(v, &pcms->smm, name, errp);
 }
 
-static bool pc_machine_get_aligned_dimm(Object *obj, Error **errp)
+static bool pc_machine_get_nvdimm(Object *obj, Error **errp)
 {
     PCMachineState *pcms = PC_MACHINE(obj);
 
-    return pcms->enforce_aligned_dimm;
+    return pcms->nvdimm;
+}
+
+static void pc_machine_set_nvdimm(Object *obj, bool value, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    pcms->nvdimm = value;
 }
 
 static void pc_machine_initfn(Object *obj)
@@ -1912,10 +1914,10 @@ static void pc_machine_initfn(Object *obj)
                                     "Enable vmport (pc & q35)",
                                     &error_abort);
 
-    pcms->enforce_aligned_dimm = true;
-    object_property_add_bool(obj, PC_MACHINE_ENFORCE_ALIGNED_DIMM,
-                             pc_machine_get_aligned_dimm,
-                             NULL, &error_abort);
+    /* nvdimm is disabled on default. */
+    pcms->nvdimm = false;
+    object_property_add_bool(obj, PC_MACHINE_NVDIMM, pc_machine_get_nvdimm,
+                             pc_machine_set_nvdimm, &error_abort);
 }
 
 static void pc_machine_reset(void)
@@ -1952,6 +1954,18 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
 
     pcmc->get_hotplug_handler = mc->get_hotplug_handler;
+    pcmc->pci_enabled = true;
+    pcmc->has_acpi_build = true;
+    pcmc->rsdp_in_ram = true;
+    pcmc->smbios_defaults = true;
+    pcmc->smbios_uuid_encoded = true;
+    pcmc->gigabyte_align = true;
+    pcmc->has_reserved_memory = true;
+    pcmc->kvmclock_enabled = true;
+    pcmc->enforce_aligned_dimm = true;
+    /* BIOS ACPI tables: 128K. Other BIOS datastructures: less than 4K reported
+     * to be used at the moment, 32K should be enough for a while.  */
+    pcmc->acpi_data_size = 0x20000 + 0x8000;
     mc->get_hotplug_handler = pc_get_hotpug_handler;
     mc->cpu_index_to_socket_id = pc_cpu_index_to_socket_id;
     mc->default_boot_order = "cad";

hw/i386/pc_piix.c

@@ -53,6 +53,7 @@
 #include "hw/xen/xen_pt.h"
 #endif
 #include "migration/migration.h"
+#include "kvm_i386.h"
 
 #define MAX_IDE_BUS 2
 
@@ -60,26 +61,12 @@ static const int ide_iobase[MAX_IDE_BUS] = { 0x1f0, 0x170 };
 static const int ide_iobase2[MAX_IDE_BUS] = { 0x3f6, 0x376 };
 static const int ide_irq[MAX_IDE_BUS] = { 14, 15 };
 
-static bool pci_enabled = true;
-static bool has_acpi_build = true;
-static bool rsdp_in_ram = true;
-static int legacy_acpi_table_size;
-static bool smbios_defaults = true;
-static bool smbios_legacy_mode;
-static bool smbios_uuid_encoded = true;
-/* Make sure that guest addresses aligned at 1Gbyte boundaries get mapped to
- * host addresses aligned at 1Gbyte boundaries.  This way we can use 1GByte
- * pages in the host.
- */
-static bool gigabyte_align = true;
-static bool has_reserved_memory = true;
-static bool kvmclock_enabled = true;
-
 /* PC hardware initialisation */
 static void pc_init1(MachineState *machine,
                      const char *host_type, const char *pci_type)
 {
     PCMachineState *pcms = PC_MACHINE(machine);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
     MemoryRegion *system_memory = get_system_memory();
     MemoryRegion *system_io = get_system_io();
     int i;
@@ -108,7 +95,7 @@ static void pc_init1(MachineState *machine,
      * breaking migration.
      */
     if (machine->ram_size >= 0xe0000000) {
-        lowmem = gigabyte_align ? 0xc0000000 : 0xe0000000;
+        lowmem = pcmc->gigabyte_align ? 0xc0000000 : 0xe0000000;
     } else {
         lowmem = 0xe0000000;
     }
@@ -141,11 +128,11 @@ static void pc_init1(MachineState *machine,
 
     pc_cpus_init(pcms);
 
-    if (kvm_enabled() && kvmclock_enabled) {
+    if (kvm_enabled() && pcmc->kvmclock_enabled) {
         kvmclock_create();
     }
 
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         pci_memory = g_new(MemoryRegion, 1);
         memory_region_init(pci_memory, NULL, "pci", UINT64_MAX);
         rom_memory = pci_memory;
@@ -156,18 +143,19 @@ static void pc_init1(MachineState *machine,
 
     guest_info = pc_guest_info_init(pcms);
 
-    guest_info->has_acpi_build = has_acpi_build;
-    guest_info->legacy_acpi_table_size = legacy_acpi_table_size;
+    guest_info->has_acpi_build = pcmc->has_acpi_build;
+    guest_info->legacy_acpi_table_size = pcmc->legacy_acpi_table_size;
 
-    guest_info->isapc_ram_fw = !pci_enabled;
-    guest_info->has_reserved_memory = has_reserved_memory;
-    guest_info->rsdp_in_ram = rsdp_in_ram;
+    guest_info->isapc_ram_fw = !pcmc->pci_enabled;
+    guest_info->has_reserved_memory = pcmc->has_reserved_memory;
+    guest_info->rsdp_in_ram = pcmc->rsdp_in_ram;
 
-    if (smbios_defaults) {
+    if (pcmc->smbios_defaults) {
         MachineClass *mc = MACHINE_GET_CLASS(machine);
         /* These values are guest ABI, do not change */
         smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)",
-                            mc->name, smbios_legacy_mode, smbios_uuid_encoded,
+                            mc->name, pcmc->smbios_legacy_mode,
+                            pcmc->smbios_uuid_encoded,
                             SMBIOS_ENTRY_POINT_21);
     }
 
@@ -181,15 +169,15 @@ static void pc_init1(MachineState *machine,
     }
 
     gsi_state = g_malloc0(sizeof(*gsi_state));
-    if (kvm_irqchip_in_kernel()) {
-        kvm_pc_setup_irq_routing(pci_enabled);
+    if (kvm_ioapic_in_kernel()) {
+        kvm_pc_setup_irq_routing(pcmc->pci_enabled);
         gsi = qemu_allocate_irqs(kvm_pc_gsi_handler, gsi_state,
                                  GSI_NUM_PINS);
     } else {
         gsi = qemu_allocate_irqs(gsi_handler, gsi_state, GSI_NUM_PINS);
     }
 
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         pci_bus = i440fx_init(host_type,
                               pci_type,
                               &i440fx_state, &piix3_devfn, &isa_bus, gsi,
@@ -197,6 +185,7 @@ static void pc_init1(MachineState *machine,
                               pcms->below_4g_mem_size,
                               pcms->above_4g_mem_size,
                               pci_memory, ram_memory);
+        pcms->bus = pci_bus;
     } else {
         pci_bus = NULL;
         i440fx_state = NULL;
@@ -205,7 +194,7 @@ static void pc_init1(MachineState *machine,
     }
     isa_bus_irqs(isa_bus, gsi);
 
-    if (kvm_irqchip_in_kernel()) {
+    if (kvm_pic_in_kernel()) {
         i8259 = kvm_i8259_init(isa_bus);
     } else if (xen_enabled()) {
         i8259 = xen_interrupt_controller_init();
@@ -217,15 +206,15 @@ static void pc_init1(MachineState *machine,
         gsi_state->i8259_irq[i] = i8259[i];
     }
     g_free(i8259);
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         ioapic_init_gsi(gsi_state, "i440fx");
     }
 
     pc_register_ferr_irq(gsi[13]);
 
-    pc_vga_init(isa_bus, pci_enabled ? pci_bus : NULL);
+    pc_vga_init(isa_bus, pcmc->pci_enabled ? pci_bus : NULL);
 
-    assert(pcms->vmport != ON_OFF_AUTO_MAX);
+    assert(pcms->vmport != ON_OFF_AUTO__MAX);
     if (pcms->vmport == ON_OFF_AUTO_AUTO) {
         pcms->vmport = xen_enabled() ? ON_OFF_AUTO_OFF : ON_OFF_AUTO_ON;
     }
@@ -237,7 +226,7 @@ static void pc_init1(MachineState *machine,
     pc_nic_init(isa_bus, pci_bus);
 
     ide_drive_get(hd, ARRAY_SIZE(hd));
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         PCIDevice *dev;
         if (xen_enabled()) {
             dev = pci_piix3_xen_ide_init(pci_bus, hd, piix3_devfn + 1);
@@ -264,11 +253,11 @@ static void pc_init1(MachineState *machine,
 
     pc_cmos_init(pcms, idebus[0], idebus[1], rtc_state);
 
-    if (pci_enabled && usb_enabled()) {
+    if (pcmc->pci_enabled && usb_enabled()) {
         pci_create_simple(pci_bus, piix3_devfn + 2, "piix3-usb-uhci");
     }
 
-    if (pci_enabled && acpi_enabled) {
+    if (pcmc->pci_enabled && acpi_enabled) {
         DeviceState *piix4_pm;
         I2CBus *smbus;
 
@@ -289,7 +278,7 @@ static void pc_init1(MachineState *machine,
                                  PC_MACHINE_ACPI_DEVICE_PROP, &error_abort);
     }
 
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         pc_pci_device_init(pci_bus);
     }
 }
@@ -315,60 +304,29 @@ static void pc_compat_2_3(MachineState *machine)
 static void pc_compat_2_2(MachineState *machine)
 {
     pc_compat_2_3(machine);
-    rsdp_in_ram = false;
     machine->suppress_vmdesc = true;
 }
 
 static void pc_compat_2_1(MachineState *machine)
 {
-    PCMachineState *pcms = PC_MACHINE(machine);
-
     pc_compat_2_2(machine);
-    smbios_uuid_encoded = false;
     x86_cpu_change_kvm_default("svm", NULL);
-    pcms->enforce_aligned_dimm = false;
 }
 
 static void pc_compat_2_0(MachineState *machine)
 {
     pc_compat_2_1(machine);
-    /* This value depends on the actual DSDT and SSDT compiled into
-     * the source QEMU; unfortunately it depends on the binary and
-     * not on the machine type, so we cannot make pc-i440fx-1.7 work on
-     * both QEMU 1.7 and QEMU 2.0.
-     *
-     * Large variations cause migration to fail for more than one
-     * consecutive value of the "-smp" maxcpus option.
-     *
-     * For small variations of the kind caused by different iasl versions,
-     * the 4k rounding usually leaves slack.  However, there could be still
-     * one or two values that break.  For QEMU 1.7 and QEMU 2.0 the
-     * slack is only ~10 bytes before one "-smp maxcpus" value breaks!
-     *
-     * 6652 is valid for QEMU 2.0, the right value for pc-i440fx-1.7 on
-     * QEMU 1.7 it is 6414.  For RHEL/CentOS 7.0 it is 6418.
-     */
-    legacy_acpi_table_size = 6652;
-    smbios_legacy_mode = true;
-    has_reserved_memory = false;
-    pc_set_legacy_acpi_data_size();
 }
 
 static void pc_compat_1_7(MachineState *machine)
 {
     pc_compat_2_0(machine);
-    smbios_defaults = false;
-    gigabyte_align = false;
-    option_rom_has_mr = true;
-    legacy_acpi_table_size = 6414;
     x86_cpu_change_kvm_default("x2apic", NULL);
 }
 
 static void pc_compat_1_6(MachineState *machine)
 {
     pc_compat_1_7(machine);
-    rom_file_has_mr = false;
-    has_acpi_build = false;
 }
 
 static void pc_compat_1_5(MachineState *machine)
@@ -398,19 +356,10 @@ static void pc_compat_1_2(MachineState *machine)
 static void pc_compat_0_13(MachineState *machine)
 {
     pc_compat_1_2(machine);
-    kvmclock_enabled = false;
 }
 
 static void pc_init_isa(MachineState *machine)
 {
-    pci_enabled = false;
-    has_acpi_build = false;
-    smbios_defaults = false;
-    gigabyte_align = false;
-    smbios_legacy_mode = true;
-    has_reserved_memory = false;
-    option_rom_has_mr = true;
-    rom_file_has_mr = false;
     if (!machine->cpu_model) {
         machine->cpu_model = "486";
     }
@@ -469,13 +418,25 @@ static void pc_i440fx_machine_options(MachineClass *m)
     m->default_display = "std";
 }
 
-static void pc_i440fx_2_5_machine_options(MachineClass *m)
+static void pc_i440fx_2_6_machine_options(MachineClass *m)
 {
     pc_i440fx_machine_options(m);
     m->alias = "pc";
     m->is_default = 1;
 }
 
+DEFINE_I440FX_MACHINE(v2_6, "pc-i440fx-2.6", NULL,
+                      pc_i440fx_2_6_machine_options);
+
+
+static void pc_i440fx_2_5_machine_options(MachineClass *m)
+{
+    pc_i440fx_2_6_machine_options(m);
+    m->alias = NULL;
+    m->is_default = 0;
+    SET_MACHINE_COMPAT(m, PC_COMPAT_2_5);
+}
+
 DEFINE_I440FX_MACHINE(v2_5, "pc-i440fx-2.5", NULL,
                       pc_i440fx_2_5_machine_options);
 
@@ -485,8 +446,6 @@ static void pc_i440fx_2_4_machine_options(MachineClass *m)
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_2_5_machine_options(m);
     m->hw_version = "2.4.0";
-    m->alias = NULL;
-    m->is_default = 0;
     pcmc->broken_reserved_end = true;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_4);
 }
@@ -499,8 +458,6 @@ static void pc_i440fx_2_3_machine_options(MachineClass *m)
 {
     pc_i440fx_2_4_machine_options(m);
     m->hw_version = "2.3.0";
-    m->alias = NULL;
-    m->is_default = 0;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_3);
 }
 
@@ -510,9 +467,11 @@ DEFINE_I440FX_MACHINE(v2_3, "pc-i440fx-2.3", pc_compat_2_3,
 
 static void pc_i440fx_2_2_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_2_3_machine_options(m);
     m->hw_version = "2.2.0";
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_2);
+    pcmc->rsdp_in_ram = false;
 }
 
 DEFINE_I440FX_MACHINE(v2_2, "pc-i440fx-2.2", pc_compat_2_2,
@@ -521,10 +480,13 @@ DEFINE_I440FX_MACHINE(v2_2, "pc-i440fx-2.2", pc_compat_2_2,
 
 static void pc_i440fx_2_1_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_2_2_machine_options(m);
     m->hw_version = "2.1.0";
     m->default_display = NULL;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_1);
+    pcmc->smbios_uuid_encoded = false;
+    pcmc->enforce_aligned_dimm = false;
 }
 
 DEFINE_I440FX_MACHINE(v2_1, "pc-i440fx-2.1", pc_compat_2_1,
@@ -534,9 +496,30 @@ DEFINE_I440FX_MACHINE(v2_1, "pc-i440fx-2.1", pc_compat_2_1,
 
 static void pc_i440fx_2_0_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_2_1_machine_options(m);
     m->hw_version = "2.0.0";
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_0);
+    pcmc->smbios_legacy_mode = true;
+    pcmc->has_reserved_memory = false;
+    /* This value depends on the actual DSDT and SSDT compiled into
+     * the source QEMU; unfortunately it depends on the binary and
+     * not on the machine type, so we cannot make pc-i440fx-1.7 work on
+     * both QEMU 1.7 and QEMU 2.0.
+     *
+     * Large variations cause migration to fail for more than one
+     * consecutive value of the "-smp" maxcpus option.
+     *
+     * For small variations of the kind caused by different iasl versions,
+     * the 4k rounding usually leaves slack.  However, there could be still
+     * one or two values that break.  For QEMU 1.7 and QEMU 2.0 the
+     * slack is only ~10 bytes before one "-smp maxcpus" value breaks!
+     *
+     * 6652 is valid for QEMU 2.0, the right value for pc-i440fx-1.7 on
+     * QEMU 1.7 it is 6414.  For RHEL/CentOS 7.0 it is 6418.
+     */
+    pcmc->legacy_acpi_table_size = 6652;
+    pcmc->acpi_data_size = 0x10000;
 }
 
 DEFINE_I440FX_MACHINE(v2_0, "pc-i440fx-2.0", pc_compat_2_0,
@@ -545,10 +528,15 @@ DEFINE_I440FX_MACHINE(v2_0, "pc-i440fx-2.0", pc_compat_2_0,
 
 static void pc_i440fx_1_7_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_2_0_machine_options(m);
     m->hw_version = "1.7.0";
     m->default_machine_opts = NULL;
+    m->option_rom_has_mr = true;
     SET_MACHINE_COMPAT(m, PC_COMPAT_1_7);
+    pcmc->smbios_defaults = false;
+    pcmc->gigabyte_align = false;
+    pcmc->legacy_acpi_table_size = 6414;
 }
 
 DEFINE_I440FX_MACHINE(v1_7, "pc-i440fx-1.7", pc_compat_1_7,
@@ -557,9 +545,12 @@ DEFINE_I440FX_MACHINE(v1_7, "pc-i440fx-1.7", pc_compat_1_7,
 
 static void pc_i440fx_1_6_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_1_7_machine_options(m);
     m->hw_version = "1.6.0";
+    m->rom_file_has_mr = false;
     SET_MACHINE_COMPAT(m, PC_COMPAT_1_6);
+    pcmc->has_acpi_build = false;
 }
 
 DEFINE_I440FX_MACHINE(v1_6, "pc-i440fx-1.6", pc_compat_1_6,
@@ -813,9 +804,11 @@ DEFINE_I440FX_MACHINE(v0_14, "pc-0.14", pc_compat_1_2,
 
 static void pc_i440fx_0_13_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_0_14_machine_options(m);
     m->hw_version = "0.13";
     SET_MACHINE_COMPAT(m, PC_COMPAT_0_13);
+    pcmc->kvmclock_enabled = false;
 }
 
 DEFINE_I440FX_MACHINE(v0_13, "pc-0.13", pc_compat_0_13,
@@ -1037,8 +1030,17 @@ void igd_passthrough_isa_bridge_create(PCIBus *bus, uint16_t gpu_dev_id)
 
 static void isapc_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     m->desc = "ISA-only PC";
     m->max_cpus = 1;
+    m->option_rom_has_mr = true;
+    m->rom_file_has_mr = false;
+    pcmc->pci_enabled = false;
+    pcmc->has_acpi_build = false;
+    pcmc->smbios_defaults = false;
+    pcmc->gigabyte_align = false;
+    pcmc->smbios_legacy_mode = true;
+    pcmc->has_reserved_memory = false;
 }
 
 DEFINE_PC_MACHINE(isapc, "isapc", pc_init_isa,

hw/i386/pc_q35.c

@@ -49,22 +49,11 @@
 /* ICH9 AHCI has 6 ports */
 #define MAX_SATA_PORTS     6
 
-static bool has_acpi_build = true;
-static bool rsdp_in_ram = true;
-static bool smbios_defaults = true;
-static bool smbios_legacy_mode;
-static bool smbios_uuid_encoded = true;
-/* Make sure that guest addresses aligned at 1Gbyte boundaries get mapped to
- * host addresses aligned at 1Gbyte boundaries.  This way we can use 1GByte
- * pages in the host.
- */
-static bool gigabyte_align = true;
-static bool has_reserved_memory = true;
-
 /* PC hardware initialisation */
 static void pc_q35_init(MachineState *machine)
 {
     PCMachineState *pcms = PC_MACHINE(machine);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
     Q35PCIHost *q35_host;
     PCIHostState *phb;
     PCIBus *host_bus;
@@ -76,7 +65,6 @@ static void pc_q35_init(MachineState *machine)
     MemoryRegion *ram_memory;
     GSIState *gsi_state;
     ISABus *isa_bus;
-    int pci_enabled = 1;
     qemu_irq *gsi;
     qemu_irq *i8259;
     int i;
@@ -97,7 +85,7 @@ static void pc_q35_init(MachineState *machine)
      * breaking migration.
      */
     if (machine->ram_size >= 0xb0000000) {
-        lowmem = gigabyte_align ? 0x80000000 : 0xb0000000;
+        lowmem = pcmc->gigabyte_align ? 0x80000000 : 0xb0000000;
     } else {
         lowmem = 0xb0000000;
     }
@@ -129,12 +117,15 @@ static void pc_q35_init(MachineState *machine)
     }
 
     pc_cpus_init(pcms);
+    if (!pcmc->has_acpi_build) {
+        /* only machine types 1.7 & older need this */
         pc_acpi_init("q35-acpi-dsdt.aml");
+    }
 
     kvmclock_create();
 
     /* pci enabled */
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         pci_memory = g_new(MemoryRegion, 1);
         memory_region_init(pci_memory, NULL, "pci", UINT64_MAX);
         rom_memory = pci_memory;
@@ -145,19 +136,20 @@ static void pc_q35_init(MachineState *machine)
 
     guest_info = pc_guest_info_init(pcms);
     guest_info->isapc_ram_fw = false;
-    guest_info->has_acpi_build = has_acpi_build;
-    guest_info->has_reserved_memory = has_reserved_memory;
-    guest_info->rsdp_in_ram = rsdp_in_ram;
+    guest_info->has_acpi_build = pcmc->has_acpi_build;
+    guest_info->has_reserved_memory = pcmc->has_reserved_memory;
+    guest_info->rsdp_in_ram = pcmc->rsdp_in_ram;
 
     /* Migration was not supported in 2.0 for Q35, so do not bother
      * with this hack (see hw/i386/acpi-build.c).
      */
     guest_info->legacy_acpi_table_size = 0;
 
-    if (smbios_defaults) {
+    if (pcmc->smbios_defaults) {
         /* These values are guest ABI, do not change */
         smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)",
-                            mc->name, smbios_legacy_mode, smbios_uuid_encoded,
+                            mc->name, pcmc->smbios_legacy_mode,
+                            pcmc->smbios_uuid_encoded,
                             SMBIOS_ENTRY_POINT_21);
     }
 
@@ -170,7 +162,7 @@ static void pc_q35_init(MachineState *machine)
     /* irq lines */
     gsi_state = g_malloc0(sizeof(*gsi_state));
     if (kvm_irqchip_in_kernel()) {
-        kvm_pc_setup_irq_routing(pci_enabled);
+        kvm_pc_setup_irq_routing(pcmc->pci_enabled);
         gsi = qemu_allocate_irqs(kvm_pc_gsi_handler, gsi_state,
                                  GSI_NUM_PINS);
     } else {
@@ -187,11 +179,11 @@ static void pc_q35_init(MachineState *machine)
     q35_host->mch.address_space_io = get_system_io();
     q35_host->mch.below_4g_mem_size = pcms->below_4g_mem_size;
     q35_host->mch.above_4g_mem_size = pcms->above_4g_mem_size;
-    q35_host->mch.guest_info = guest_info;
     /* pci */
     qdev_init_nofail(DEVICE(q35_host));
     phb = PCI_HOST_BRIDGE(q35_host);
     host_bus = phb->bus;
+    pcms->bus = phb->bus;
     /* create ISA bus */
     lpc = pci_create_simple_multifunction(host_bus, PCI_DEVFN(ICH9_LPC_DEV,
                                           ICH9_LPC_FUNC), true,
@@ -227,13 +219,13 @@ static void pc_q35_init(MachineState *machine)
     for (i = 0; i < ISA_NUM_IRQS; i++) {
         gsi_state->i8259_irq[i] = i8259[i];
     }
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         ioapic_init_gsi(gsi_state, "q35");
     }
 
     pc_register_ferr_irq(gsi[13]);
 
-    assert(pcms->vmport != ON_OFF_AUTO_MAX);
+    assert(pcms->vmport != ON_OFF_AUTO__MAX);
     if (pcms->vmport == ON_OFF_AUTO_AUTO) {
         pcms->vmport = xen_enabled() ? ON_OFF_AUTO_OFF : ON_OFF_AUTO_ON;
     }
@@ -272,7 +264,7 @@ static void pc_q35_init(MachineState *machine)
     /* the rest devices to which pci devfn is automatically assigned */
     pc_vga_init(isa_bus, host_bus);
     pc_nic_init(isa_bus, host_bus);
-    if (pci_enabled) {
+    if (pcmc->pci_enabled) {
         pc_pci_device_init(host_bus);
     }
 }
@@ -298,42 +290,29 @@ static void pc_compat_2_3(MachineState *machine)
 static void pc_compat_2_2(MachineState *machine)
 {
     pc_compat_2_3(machine);
-    rsdp_in_ram = false;
     machine->suppress_vmdesc = true;
 }
 
 static void pc_compat_2_1(MachineState *machine)
 {
-    PCMachineState *pcms = PC_MACHINE(machine);
-
     pc_compat_2_2(machine);
-    pcms->enforce_aligned_dimm = false;
-    smbios_uuid_encoded = false;
     x86_cpu_change_kvm_default("svm", NULL);
 }
 
 static void pc_compat_2_0(MachineState *machine)
 {
     pc_compat_2_1(machine);
-    smbios_legacy_mode = true;
-    has_reserved_memory = false;
-    pc_set_legacy_acpi_data_size();
 }
 
 static void pc_compat_1_7(MachineState *machine)
 {
     pc_compat_2_0(machine);
-    smbios_defaults = false;
-    gigabyte_align = false;
-    option_rom_has_mr = true;
     x86_cpu_change_kvm_default("x2apic", NULL);
 }
 
 static void pc_compat_1_6(MachineState *machine)
 {
     pc_compat_1_7(machine);
-    rom_file_has_mr = false;
-    has_acpi_build = false;
 }
 
 static void pc_compat_1_5(MachineState *machine)
@@ -370,12 +349,22 @@ static void pc_q35_machine_options(MachineClass *m)
     m->no_tco = 0;
 }
 
-static void pc_q35_2_5_machine_options(MachineClass *m)
+static void pc_q35_2_6_machine_options(MachineClass *m)
 {
     pc_q35_machine_options(m);
     m->alias = "q35";
 }
 
+DEFINE_Q35_MACHINE(v2_6, "pc-q35-2.6", NULL,
+                   pc_q35_2_6_machine_options);
+
+static void pc_q35_2_5_machine_options(MachineClass *m)
+{
+    pc_q35_2_6_machine_options(m);
+    m->alias = NULL;
+    SET_MACHINE_COMPAT(m, PC_COMPAT_2_5);
+}
+
 DEFINE_Q35_MACHINE(v2_5, "pc-q35-2.5", NULL,
                    pc_q35_2_5_machine_options);
 
@@ -384,7 +373,6 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_2_5_machine_options(m);
     m->hw_version = "2.4.0";
-    m->alias = NULL;
     pcmc->broken_reserved_end = true;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_4);
 }
@@ -399,7 +387,6 @@ static void pc_q35_2_3_machine_options(MachineClass *m)
     m->hw_version = "2.3.0";
     m->no_floppy = 0;
     m->no_tco = 1;
-    m->alias = NULL;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_3);
 }
 
@@ -409,9 +396,11 @@ DEFINE_Q35_MACHINE(v2_3, "pc-q35-2.3", pc_compat_2_3,
 
 static void pc_q35_2_2_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_2_3_machine_options(m);
     m->hw_version = "2.2.0";
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_2);
+    pcmc->rsdp_in_ram = false;
 }
 
 DEFINE_Q35_MACHINE(v2_2, "pc-q35-2.2", pc_compat_2_2,
@@ -420,10 +409,13 @@ DEFINE_Q35_MACHINE(v2_2, "pc-q35-2.2", pc_compat_2_2,
 
 static void pc_q35_2_1_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_2_2_machine_options(m);
     m->hw_version = "2.1.0";
     m->default_display = NULL;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_1);
+    pcmc->smbios_uuid_encoded = false;
+    pcmc->enforce_aligned_dimm = false;
 }
 
 DEFINE_Q35_MACHINE(v2_1, "pc-q35-2.1", pc_compat_2_1,
@@ -432,9 +424,13 @@ DEFINE_Q35_MACHINE(v2_1, "pc-q35-2.1", pc_compat_2_1,
 
 static void pc_q35_2_0_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_2_1_machine_options(m);
     m->hw_version = "2.0.0";
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_0);
+    pcmc->has_reserved_memory = false;
+    pcmc->smbios_legacy_mode = true;
+    pcmc->acpi_data_size = 0x10000;
 }
 
 DEFINE_Q35_MACHINE(v2_0, "pc-q35-2.0", pc_compat_2_0,
@@ -443,10 +439,14 @@ DEFINE_Q35_MACHINE(v2_0, "pc-q35-2.0", pc_compat_2_0,
 
 static void pc_q35_1_7_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_2_0_machine_options(m);
     m->hw_version = "1.7.0";
     m->default_machine_opts = NULL;
+    m->option_rom_has_mr = true;
     SET_MACHINE_COMPAT(m, PC_COMPAT_1_7);
+    pcmc->smbios_defaults = false;
+    pcmc->gigabyte_align = false;
 }
 
 DEFINE_Q35_MACHINE(v1_7, "pc-q35-1.7", pc_compat_1_7,
@@ -455,9 +455,12 @@ DEFINE_Q35_MACHINE(v1_7, "pc-q35-1.7", pc_compat_1_7,
 
 static void pc_q35_1_6_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_machine_options(m);
     m->hw_version = "1.6.0";
+    m->rom_file_has_mr = false;
     SET_MACHINE_COMPAT(m, PC_COMPAT_1_6);
+    pcmc->has_acpi_build = false;
 }
 
 DEFINE_Q35_MACHINE(v1_6, "pc-q35-1.6", pc_compat_1_6,

hw/input/hid.c

@@ -108,7 +108,7 @@ void hid_set_next_idle(HIDState *hs)
 static void hid_pointer_event(DeviceState *dev, QemuConsole *src,
                               InputEvent *evt)
 {
-    static const int bmap[INPUT_BUTTON_MAX] = {
+    static const int bmap[INPUT_BUTTON__MAX] = {
         [INPUT_BUTTON_LEFT]   = 0x01,
         [INPUT_BUTTON_RIGHT]  = 0x02,
         [INPUT_BUTTON_MIDDLE] = 0x04,
@@ -139,9 +139,9 @@ static void hid_pointer_event(DeviceState *dev, QemuConsole *src,
     case INPUT_EVENT_KIND_BTN:
         if (evt->u.btn->down) {
             e->buttons_state |= bmap[evt->u.btn->button];
-            if (evt->u.btn->button == INPUT_BUTTON_WHEEL_UP) {
+            if (evt->u.btn->button == INPUT_BUTTON_WHEELUP) {
                 e->dz--;
-            } else if (evt->u.btn->button == INPUT_BUTTON_WHEEL_DOWN) {
+            } else if (evt->u.btn->button == INPUT_BUTTON_WHEELDOWN) {
                 e->dz++;
             }
         } else {

hw/input/ps2.c

@@ -382,7 +382,7 @@ static void ps2_mouse_send_packet(PS2MouseState *s)
 static void ps2_mouse_event(DeviceState *dev, QemuConsole *src,
                             InputEvent *evt)
 {
-    static const int bmap[INPUT_BUTTON_MAX] = {
+    static const int bmap[INPUT_BUTTON__MAX] = {
         [INPUT_BUTTON_LEFT]   = MOUSE_EVENT_LBUTTON,
         [INPUT_BUTTON_MIDDLE] = MOUSE_EVENT_MBUTTON,
         [INPUT_BUTTON_RIGHT]  = MOUSE_EVENT_RBUTTON,
@@ -405,9 +405,9 @@ static void ps2_mouse_event(DeviceState *dev, QemuConsole *src,
     case INPUT_EVENT_KIND_BTN:
         if (evt->u.btn->down) {
             s->mouse_buttons |= bmap[evt->u.btn->button];
-            if (evt->u.btn->button == INPUT_BUTTON_WHEEL_UP) {
+            if (evt->u.btn->button == INPUT_BUTTON_WHEELUP) {
                 s->mouse_dz--;
-            } else if (evt->u.btn->button == INPUT_BUTTON_WHEEL_DOWN) {
+            } else if (evt->u.btn->button == INPUT_BUTTON_WHEELDOWN) {
                 s->mouse_dz++;
             }
         } else {

hw/input/virtio-input-hid.c

@@ -21,7 +21,7 @@
 
 /* ----------------------------------------------------------------- */
 
-static const unsigned int keymap_qcode[Q_KEY_CODE_MAX] = {
+static const unsigned int keymap_qcode[Q_KEY_CODE__MAX] = {
     [Q_KEY_CODE_ESC]                 = KEY_ESC,
     [Q_KEY_CODE_1]                   = KEY_1,
     [Q_KEY_CODE_2]                   = KEY_2,
@@ -138,20 +138,20 @@ static const unsigned int keymap_qcode[Q_KEY_CODE_MAX] = {
     [Q_KEY_CODE_MENU]                = KEY_MENU,
 };
 
-static const unsigned int keymap_button[INPUT_BUTTON_MAX] = {
+static const unsigned int keymap_button[INPUT_BUTTON__MAX] = {
     [INPUT_BUTTON_LEFT]              = BTN_LEFT,
     [INPUT_BUTTON_RIGHT]             = BTN_RIGHT,
     [INPUT_BUTTON_MIDDLE]            = BTN_MIDDLE,
-    [INPUT_BUTTON_WHEEL_UP]          = BTN_GEAR_UP,
-    [INPUT_BUTTON_WHEEL_DOWN]        = BTN_GEAR_DOWN,
+    [INPUT_BUTTON_WHEELUP]           = BTN_GEAR_UP,
+    [INPUT_BUTTON_WHEELDOWN]         = BTN_GEAR_DOWN,
 };
 
-static const unsigned int axismap_rel[INPUT_AXIS_MAX] = {
+static const unsigned int axismap_rel[INPUT_AXIS__MAX] = {
     [INPUT_AXIS_X]                   = REL_X,
     [INPUT_AXIS_Y]                   = REL_Y,
 };
 
-static const unsigned int axismap_abs[INPUT_AXIS_MAX] = {
+static const unsigned int axismap_abs[INPUT_AXIS__MAX] = {
     [INPUT_AXIS_X]                   = ABS_X,
     [INPUT_AXIS_Y]                   = ABS_Y,
 };

hw/intc/ioapic.c

@@ -25,6 +25,8 @@
 #include "hw/i386/pc.h"
 #include "hw/i386/ioapic.h"
 #include "hw/i386/ioapic_internal.h"
+#include "include/hw/pci/msi.h"
+#include "sysemu/kvm.h"
 
 //#define DEBUG_IOAPIC
 
@@ -35,6 +37,10 @@
 #define DPRINTF(fmt, ...)
 #endif
 
+#define APIC_DELIVERY_MODE_SHIFT 8
+#define APIC_POLARITY_SHIFT 14
+#define APIC_TRIG_MODE_SHIFT 15
+
 static IOAPICCommonState *ioapics[MAX_IOAPICS];
 
 /* global variable from ioapic_common.c */
@@ -54,6 +60,8 @@ static void ioapic_service(IOAPICCommonState *s)
     for (i = 0; i < IOAPIC_NUM_PINS; i++) {
         mask = 1 << i;
         if (s->irr & mask) {
+            int coalesce = 0;
+
             entry = s->ioredtbl[i];
             if (!(entry & IOAPIC_LVT_MASKED)) {
                 trig_mode = ((entry >> IOAPIC_LVT_TRIGGER_MODE_SHIFT) & 1);
@@ -64,6 +72,7 @@ static void ioapic_service(IOAPICCommonState *s)
                 if (trig_mode == IOAPIC_TRIGGER_EDGE) {
                     s->irr &= ~mask;
                 } else {
+                    coalesce = s->ioredtbl[i] & IOAPIC_LVT_REMOTE_IRR;
                     s->ioredtbl[i] |= IOAPIC_LVT_REMOTE_IRR;
                 }
                 if (delivery_mode == IOAPIC_DM_EXTINT) {
@@ -71,8 +80,23 @@ static void ioapic_service(IOAPICCommonState *s)
                 } else {
                     vector = entry & IOAPIC_VECTOR_MASK;
                 }
-                apic_deliver_irq(dest, dest_mode, delivery_mode,
-                                 vector, trig_mode);
+#ifdef CONFIG_KVM
+                if (kvm_irqchip_is_split()) {
+                    if (trig_mode == IOAPIC_TRIGGER_EDGE) {
+                        kvm_set_irq(kvm_state, i, 1);
+                        kvm_set_irq(kvm_state, i, 0);
+                    } else {
+                        if (!coalesce) {
+                            kvm_set_irq(kvm_state, i, 1);
+                        }
+                    }
+                    continue;
+                }
+#else
+                (void)coalesce;
+#endif
+                apic_deliver_irq(dest, dest_mode, delivery_mode, vector,
+                                 trig_mode);
             }
         }
     }
@@ -116,6 +140,44 @@ static void ioapic_set_irq(void *opaque, int vector, int level)
     }
 }
 
+static void ioapic_update_kvm_routes(IOAPICCommonState *s)
+{
+#ifdef CONFIG_KVM
+    int i;
+
+    if (kvm_irqchip_is_split()) {
+        for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+            uint64_t entry = s->ioredtbl[i];
+            uint8_t trig_mode;
+            uint8_t delivery_mode;
+            uint8_t dest;
+            uint8_t dest_mode;
+            uint64_t pin_polarity;
+            MSIMessage msg;
+
+            trig_mode = ((entry >> IOAPIC_LVT_TRIGGER_MODE_SHIFT) & 1);
+            dest = entry >> IOAPIC_LVT_DEST_SHIFT;
+            dest_mode = (entry >> IOAPIC_LVT_DEST_MODE_SHIFT) & 1;
+            pin_polarity = (entry >> IOAPIC_LVT_TRIGGER_MODE_SHIFT) & 1;
+            delivery_mode =
+                (entry >> IOAPIC_LVT_DELIV_MODE_SHIFT) & IOAPIC_DM_MASK;
+
+            msg.address = APIC_DEFAULT_ADDRESS;
+            msg.address |= dest_mode << 2;
+            msg.address |= dest << 12;
+
+            msg.data = entry & IOAPIC_VECTOR_MASK;
+            msg.data |= delivery_mode << APIC_DELIVERY_MODE_SHIFT;
+            msg.data |= pin_polarity << APIC_POLARITY_SHIFT;
+            msg.data |= trig_mode << APIC_TRIG_MODE_SHIFT;
+
+            kvm_irqchip_update_msi_route(kvm_state, i, msg, NULL);
+        }
+        kvm_irqchip_commit_routes(kvm_state);
+    }
+#endif
+}
+
 void ioapic_eoi_broadcast(int vector)
 {
     IOAPICCommonState *s;
@@ -229,6 +291,8 @@ ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val,
         }
         break;
     }
+
+    ioapic_update_kvm_routes(s);
 }
 
 static const MemoryRegionOps ioapic_io_ops = {

hw/ipmi/Makefile.objs

@@ -0,0 +1,5 @@
+common-obj-$(CONFIG_IPMI) += ipmi.o
+common-obj-$(CONFIG_IPMI_LOCAL) += ipmi_bmc_sim.o
+common-obj-$(CONFIG_IPMI_LOCAL) += ipmi_bmc_extern.o
+common-obj-$(CONFIG_ISA_IPMI_KCS) += isa_ipmi_kcs.o
+common-obj-$(CONFIG_ISA_IPMI_BT) += isa_ipmi_bt.o

hw/ipmi/ipmi.c

@@ -0,0 +1,152 @@
+/*
+ * QEMU IPMI emulation
+ *
+ * Copyright (c) 2015 Corey Minyard, MontaVista Software, LLC
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "hw/hw.h"
+#include "hw/ipmi/ipmi.h"
+#include "sysemu/sysemu.h"
+#include "qmp-commands.h"
+#include "qom/object_interfaces.h"
+#include "qapi/visitor.h"
+
+static int ipmi_do_hw_op(IPMIInterface *s, enum ipmi_op op, int checkonly)
+{
+    switch (op) {
+    case IPMI_RESET_CHASSIS:
+        if (checkonly) {
+            return 0;
+        }
+        qemu_system_reset_request();
+        return 0;
+
+    case IPMI_POWEROFF_CHASSIS:
+        if (checkonly) {
+            return 0;
+        }
+        qemu_system_powerdown_request();
+        return 0;
+
+    case IPMI_SEND_NMI:
+        if (checkonly) {
+            return 0;
+        }
+        qemu_mutex_lock_iothread();
+        qmp_inject_nmi(NULL);
+        qemu_mutex_unlock_iothread();
+        return 0;
+
+    case IPMI_POWERCYCLE_CHASSIS:
+    case IPMI_PULSE_DIAG_IRQ:
+    case IPMI_SHUTDOWN_VIA_ACPI_OVERTEMP:
+    case IPMI_POWERON_CHASSIS:
+    default:
+        return IPMI_CC_COMMAND_NOT_SUPPORTED;
+    }
+}
+
+static void ipmi_interface_class_init(ObjectClass *class, void *data)
+{
+    IPMIInterfaceClass *ik = IPMI_INTERFACE_CLASS(class);
+
+    ik->do_hw_op = ipmi_do_hw_op;
+}
+
+static TypeInfo ipmi_interface_type_info = {
+    .name = TYPE_IPMI_INTERFACE,
+    .parent = TYPE_INTERFACE,
+    .class_size = sizeof(IPMIInterfaceClass),
+    .class_init = ipmi_interface_class_init,
+};
+
+static void isa_ipmi_bmc_check(Object *obj, const char *name,
+                               Object *val, Error **errp)
+{
+    IPMIBmc *bmc = IPMI_BMC(val);
+
+    if (bmc->intf)
+        error_setg(errp, "BMC object is already in use");
+}
+
+void ipmi_bmc_find_and_link(Object *obj, Object **bmc)
+{
+    object_property_add_link(obj, "bmc", TYPE_IPMI_BMC, bmc,
+                             isa_ipmi_bmc_check,
+                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             &error_abort);
+}
+
+static Property ipmi_bmc_properties[] = {
+    DEFINE_PROP_UINT8("slave_addr",  IPMIBmc, slave_addr, 0x20),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void bmc_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    dc->props = ipmi_bmc_properties;
+}
+
+static TypeInfo ipmi_bmc_type_info = {
+    .name = TYPE_IPMI_BMC,
+    .parent = TYPE_DEVICE,
+    .instance_size = sizeof(IPMIBmc),
+    .abstract = true,
+    .class_size = sizeof(IPMIBmcClass),
+    .class_init = bmc_class_init,
+};
+
+static void ipmi_register_types(void)
+{
+    type_register_static(&ipmi_interface_type_info);
+    type_register_static(&ipmi_bmc_type_info);
+}
+
+type_init(ipmi_register_types)
+
+static IPMIFwInfo *ipmi_fw_info;
+static unsigned int ipmi_fw_info_len;
+
+static uint32_t current_uuid = 1;
+
+void ipmi_add_fwinfo(IPMIFwInfo *info, Error **errp)
+{
+    info->uuid = current_uuid++;
+    ipmi_fw_info = g_realloc(ipmi_fw_info,
+                             sizeof(*ipmi_fw_info) * (ipmi_fw_info_len + 1));
+    ipmi_fw_info[ipmi_fw_info_len] = *info;
+}
+
+IPMIFwInfo *ipmi_first_fwinfo(void)
+{
+    return ipmi_fw_info;
+}
+
+IPMIFwInfo *ipmi_next_fwinfo(IPMIFwInfo *current)
+{
+    current++;
+    if (current >= &ipmi_fw_info[ipmi_fw_info_len]) {
+        return NULL;
+    }
+    return current;
+}

hw/ipmi/ipmi_bmc_extern.c

@@ -0,0 +1,518 @@
+/*
+ * IPMI BMC external connection
+ *
+ * Copyright (c) 2015 Corey Minyard, MontaVista Software, LLC
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/*
+ * This is designed to connect with OpenIPMI's lanserv serial interface
+ * using the "VM" connection type.  See that for details.
+ */
+
+#include <stdint.h>
+#include "qemu/timer.h"
+#include "sysemu/char.h"
+#include "sysemu/sysemu.h"
+#include "hw/ipmi/ipmi.h"
+
+#define VM_MSG_CHAR        0xA0 /* Marks end of message */
+#define VM_CMD_CHAR        0xA1 /* Marks end of a command */
+#define VM_ESCAPE_CHAR     0xAA /* Set bit 4 from the next byte to 0 */
+
+#define VM_PROTOCOL_VERSION        1
+#define VM_CMD_VERSION             0xff /* A version number byte follows */
+#define VM_CMD_NOATTN              0x00
+#define VM_CMD_ATTN                0x01
+#define VM_CMD_ATTN_IRQ            0x02
+#define VM_CMD_POWEROFF            0x03
+#define VM_CMD_RESET               0x04
+#define VM_CMD_ENABLE_IRQ          0x05 /* Enable/disable the messaging irq */
+#define VM_CMD_DISABLE_IRQ         0x06
+#define VM_CMD_SEND_NMI            0x07
+#define VM_CMD_CAPABILITIES        0x08
+#define   VM_CAPABILITIES_POWER    0x01
+#define   VM_CAPABILITIES_RESET    0x02
+#define   VM_CAPABILITIES_IRQ      0x04
+#define   VM_CAPABILITIES_NMI      0x08
+#define   VM_CAPABILITIES_ATTN     0x10
+#define VM_CMD_FORCEOFF            0x09
+
+#define TYPE_IPMI_BMC_EXTERN "ipmi-bmc-extern"
+#define IPMI_BMC_EXTERN(obj) OBJECT_CHECK(IPMIBmcExtern, (obj), \
+                                        TYPE_IPMI_BMC_EXTERN)
+typedef struct IPMIBmcExtern {
+    IPMIBmc parent;
+
+    CharDriverState *chr;
+
+    bool connected;
+
+    unsigned char inbuf[MAX_IPMI_MSG_SIZE + 2];
+    unsigned int inpos;
+    bool in_escape;
+    bool in_too_many;
+    bool waiting_rsp;
+    bool sending_cmd;
+
+    unsigned char outbuf[(MAX_IPMI_MSG_SIZE + 2) * 2 + 1];
+    unsigned int outpos;
+    unsigned int outlen;
+
+    struct QEMUTimer *extern_timer;
+
+    /* A reset event is pending to be sent upstream. */
+    bool send_reset;
+} IPMIBmcExtern;
+
+static int can_receive(void *opaque);
+static void receive(void *opaque, const uint8_t *buf, int size);
+static void chr_event(void *opaque, int event);
+
+static unsigned char
+ipmb_checksum(const unsigned char *data, int size, unsigned char start)
+{
+        unsigned char csum = start;
+
+        for (; size > 0; size--, data++) {
+                csum += *data;
+        }
+        return csum;
+}
+
+static void continue_send(IPMIBmcExtern *ibe)
+{
+    if (ibe->outlen == 0) {
+        goto check_reset;
+    }
+ send:
+    ibe->outpos += qemu_chr_fe_write(ibe->chr, ibe->outbuf + ibe->outpos,
+                                     ibe->outlen - ibe->outpos);
+    if (ibe->outpos < ibe->outlen) {
+        /* Not fully transmitted, try again in a 10ms */
+        timer_mod_ns(ibe->extern_timer,
+                     qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 10000000);
+    } else {
+        /* Sent */
+        ibe->outlen = 0;
+        ibe->outpos = 0;
+        if (!ibe->sending_cmd) {
+            ibe->waiting_rsp = true;
+        } else {
+            ibe->sending_cmd = false;
+        }
+    check_reset:
+        if (ibe->connected && ibe->send_reset) {
+            /* Send the reset */
+            ibe->outbuf[0] = VM_CMD_RESET;
+            ibe->outbuf[1] = VM_CMD_CHAR;
+            ibe->outlen = 2;
+            ibe->outpos = 0;
+            ibe->send_reset = false;
+            ibe->sending_cmd = true;
+            goto send;
+        }
+
+        if (ibe->waiting_rsp) {
+            /* Make sure we get a response within 4 seconds. */
+            timer_mod_ns(ibe->extern_timer,
+                         qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 4000000000ULL);
+        }
+    }
+    return;
+}
+
+static void extern_timeout(void *opaque)
+{
+    IPMIBmcExtern *ibe = opaque;
+    IPMIInterface *s = ibe->parent.intf;
+
+    if (ibe->connected) {
+        if (ibe->waiting_rsp && (ibe->outlen == 0)) {
+            IPMIInterfaceClass *k = IPMI_INTERFACE_GET_CLASS(s);
+            /* The message response timed out, return an error. */
+            ibe->waiting_rsp = false;
+            ibe->inbuf[1] = ibe->outbuf[1] | 0x04;
+            ibe->inbuf[2] = ibe->outbuf[2];
+            ibe->inbuf[3] = IPMI_CC_TIMEOUT;
+            k->handle_rsp(s, ibe->outbuf[0], ibe->inbuf + 1, 3);
+        } else {
+            continue_send(ibe);
+        }
+    }
+}
+
+static void addchar(IPMIBmcExtern *ibe, unsigned char ch)
+{
+    switch (ch) {
+    case VM_MSG_CHAR:
+    case VM_CMD_CHAR:
+    case VM_ESCAPE_CHAR:
+        ibe->outbuf[ibe->outlen] = VM_ESCAPE_CHAR;
+        ibe->outlen++;
+        ch |= 0x10;
+        /* No break */
+
+    default:
+        ibe->outbuf[ibe->outlen] = ch;
+        ibe->outlen++;
+    }
+}
+
+static void ipmi_bmc_extern_handle_command(IPMIBmc *b,
+                                       uint8_t *cmd, unsigned int cmd_len,
+                                       unsigned int max_cmd_len,
+                                       uint8_t msg_id)
+{
+    IPMIBmcExtern *ibe = IPMI_BMC_EXTERN(b);
+    IPMIInterface *s = ibe->parent.intf;
+    uint8_t err = 0, csum;
+    unsigned int i;
+
+    if (ibe->outlen) {
+        /* We already have a command queued.  Shouldn't ever happen. */
+        fprintf(stderr, "IPMI KCS: Got command when not finished with the"
+                " previous commmand\n");
+        abort();
+    }
+
+    /* If it's too short or it was truncated, return an error. */
+    if (cmd_len < 2) {
+        err = IPMI_CC_REQUEST_DATA_LENGTH_INVALID;
+    } else if ((cmd_len > max_cmd_len) || (cmd_len > MAX_IPMI_MSG_SIZE)) {
+        err = IPMI_CC_REQUEST_DATA_TRUNCATED;
+    } else if (!ibe->connected) {
+        err = IPMI_CC_BMC_INIT_IN_PROGRESS;
+    }
+    if (err) {
+        IPMIInterfaceClass *k = IPMI_INTERFACE_GET_CLASS(s);
+        unsigned char rsp[3];
+        rsp[0] = cmd[0] | 0x04;
+        rsp[1] = cmd[1];
+        rsp[2] = err;
+        ibe->waiting_rsp = false;
+        k->handle_rsp(s, msg_id, rsp, 3);
+        goto out;
+    }
+
+    addchar(ibe, msg_id);
+    for (i = 0; i < cmd_len; i++) {
+        addchar(ibe, cmd[i]);
+    }
+    csum = ipmb_checksum(&msg_id, 1, 0);
+    addchar(ibe, -ipmb_checksum(cmd, cmd_len, csum));
+
+    ibe->outbuf[ibe->outlen] = VM_MSG_CHAR;
+    ibe->outlen++;
+
+    /* Start the transmit */
+    continue_send(ibe);
+
+ out:
+    return;
+}
+
+static void handle_hw_op(IPMIBmcExtern *ibe, unsigned char hw_op)
+{
+    IPMIInterface *s = ibe->parent.intf;
+    IPMIInterfaceClass *k = IPMI_INTERFACE_GET_CLASS(s);
+
+    switch (hw_op) {
+    case VM_CMD_VERSION:
+        /* We only support one version at this time. */
+        break;
+
+    case VM_CMD_NOATTN:
+        k->set_atn(s, 0, 0);
+        break;
+
+    case VM_CMD_ATTN:
+        k->set_atn(s, 1, 0);
+        break;
+
+    case VM_CMD_ATTN_IRQ:
+        k->set_atn(s, 1, 1);
+        break;
+
+    case VM_CMD_POWEROFF:
+        k->do_hw_op(s, IPMI_POWEROFF_CHASSIS, 0);
+        break;
+
+    case VM_CMD_RESET:
+        k->do_hw_op(s, IPMI_RESET_CHASSIS, 0);
+        break;
+
+    case VM_CMD_ENABLE_IRQ:
+        k->set_irq_enable(s, 1);
+        break;
+
+    case VM_CMD_DISABLE_IRQ:
+        k->set_irq_enable(s, 0);
+        break;
+
+    case VM_CMD_SEND_NMI:
+        k->do_hw_op(s, IPMI_SEND_NMI, 0);
+        break;
+
+    case VM_CMD_FORCEOFF:
+        qemu_system_shutdown_request();
+        break;
+    }
+}
+
+static void handle_msg(IPMIBmcExtern *ibe)
+{
+    IPMIInterfaceClass *k = IPMI_INTERFACE_GET_CLASS(ibe->parent.intf);
+
+    if (ibe->in_escape) {
+        ipmi_debug("msg escape not ended\n");
+        return;
+    }
+    if (ibe->inpos < 5) {
+        ipmi_debug("msg too short\n");
+        return;
+    }
+    if (ibe->in_too_many) {
+        ibe->inbuf[3] = IPMI_CC_REQUEST_DATA_TRUNCATED;
+        ibe->inpos = 4;
+    } else if (ipmb_checksum(ibe->inbuf, ibe->inpos, 0) != 0) {
+        ipmi_debug("msg checksum failure\n");
+        return;
+    } else {
+        ibe->inpos--; /* Remove checkum */
+    }
+
+    timer_del(ibe->extern_timer);
+    ibe->waiting_rsp = false;
+    k->handle_rsp(ibe->parent.intf, ibe->inbuf[0], ibe->inbuf + 1, ibe->inpos - 1);
+}
+
+static int can_receive(void *opaque)
+{
+    return 1;
+}
+
+static void receive(void *opaque, const uint8_t *buf, int size)
+{
+    IPMIBmcExtern *ibe = opaque;
+    int i;
+    unsigned char hw_op;
+
+    for (i = 0; i < size; i++) {
+        unsigned char ch = buf[i];
+
+        switch (ch) {
+        case VM_MSG_CHAR:
+            handle_msg(ibe);
+            ibe->in_too_many = false;
+            ibe->inpos = 0;
+            break;
+
+        case VM_CMD_CHAR:
+            if (ibe->in_too_many) {
+                ipmi_debug("cmd in too many\n");
+                ibe->in_too_many = false;
+                ibe->inpos = 0;
+                break;
+            }
+            if (ibe->in_escape) {
+                ipmi_debug("cmd in escape\n");
+                ibe->in_too_many = false;
+                ibe->inpos = 0;
+                ibe->in_escape = false;
+                break;
+            }
+            ibe->in_too_many = false;
+            if (ibe->inpos < 1) {
+                break;
+            }
+            hw_op = ibe->inbuf[0];
+            ibe->inpos = 0;
+            goto out_hw_op;
+            break;
+
+        case VM_ESCAPE_CHAR:
+            ibe->in_escape = true;
+            break;
+
+        default:
+            if (ibe->in_escape) {
+                ch &= ~0x10;
+                ibe->in_escape = false;
+            }
+            if (ibe->in_too_many) {
+                break;
+            }
+            if (ibe->inpos >= sizeof(ibe->inbuf)) {
+                ibe->in_too_many = true;
+                break;
+            }
+            ibe->inbuf[ibe->inpos] = ch;
+            ibe->inpos++;
+            break;
+        }
+    }
+    return;
+
+ out_hw_op:
+    handle_hw_op(ibe, hw_op);
+}
+
+static void chr_event(void *opaque, int event)
+{
+    IPMIBmcExtern *ibe = opaque;
+    IPMIInterface *s = ibe->parent.intf;
+    IPMIInterfaceClass *k = IPMI_INTERFACE_GET_CLASS(s);
+    unsigned char v;
+
+    switch (event) {
+    case CHR_EVENT_OPENED:
+        ibe->connected = true;
+        ibe->outpos = 0;
+        ibe->outlen = 0;
+        addchar(ibe, VM_CMD_VERSION);
+        addchar(ibe, VM_PROTOCOL_VERSION);
+        ibe->outbuf[ibe->outlen] = VM_CMD_CHAR;
+        ibe->outlen++;
+        addchar(ibe, VM_CMD_CAPABILITIES);
+        v = VM_CAPABILITIES_IRQ | VM_CAPABILITIES_ATTN;
+        if (k->do_hw_op(ibe->parent.intf, IPMI_POWEROFF_CHASSIS, 1) == 0) {
+            v |= VM_CAPABILITIES_POWER;
+        }
+        if (k->do_hw_op(ibe->parent.intf, IPMI_RESET_CHASSIS, 1) == 0) {
+            v |= VM_CAPABILITIES_RESET;
+        }
+        if (k->do_hw_op(ibe->parent.intf, IPMI_SEND_NMI, 1) == 0) {
+            v |= VM_CAPABILITIES_NMI;
+        }
+        addchar(ibe, v);
+        ibe->outbuf[ibe->outlen] = VM_CMD_CHAR;
+        ibe->outlen++;
+        ibe->sending_cmd = false;
+        continue_send(ibe);
+        break;
+
+    case CHR_EVENT_CLOSED:
+        if (!ibe->connected) {
+            return;
+        }
+        ibe->connected = false;
+        if (ibe->waiting_rsp) {
+            ibe->waiting_rsp = false;
+            ibe->inbuf[1] = ibe->outbuf[1] | 0x04;
+            ibe->inbuf[2] = ibe->outbuf[2];
+            ibe->inbuf[3] = IPMI_CC_BMC_INIT_IN_PROGRESS;
+            k->handle_rsp(s, ibe->outbuf[0], ibe->inbuf + 1, 3);
+        }
+        break;
+    }
+}
+
+static void ipmi_bmc_extern_handle_reset(IPMIBmc *b)
+{
+    IPMIBmcExtern *ibe = IPMI_BMC_EXTERN(b);
+
+    ibe->send_reset = true;
+    continue_send(ibe);
+}
+
+static void ipmi_bmc_extern_realize(DeviceState *dev, Error **errp)
+{
+    IPMIBmcExtern *ibe = IPMI_BMC_EXTERN(dev);
+
+    if (!ibe->chr) {
+        error_setg(errp, "IPMI external bmc requires chardev attribute");
+        return;
+    }
+
+    qemu_chr_add_handlers(ibe->chr, can_receive, receive, chr_event, ibe);
+}
+
+static int ipmi_bmc_extern_post_migrate(void *opaque, int version_id)
+{
+    IPMIBmcExtern *ibe = opaque;
+
+    /*
+     * We don't directly restore waiting_rsp, Instead, we return an
+     * error on the interface if a response was being waited for.
+     */
+    if (ibe->waiting_rsp) {
+        IPMIInterface *ii = ibe->parent.intf;
+        IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+
+        ibe->waiting_rsp = false;
+        ibe->inbuf[1] = ibe->outbuf[1] | 0x04;
+        ibe->inbuf[2] = ibe->outbuf[2];
+        ibe->inbuf[3] = IPMI_CC_BMC_INIT_IN_PROGRESS;
+        iic->handle_rsp(ii, ibe->outbuf[0], ibe->inbuf + 1, 3);
+    }
+    return 0;
+}
+
+static const VMStateDescription vmstate_ipmi_bmc_extern = {
+    .name = TYPE_IPMI_BMC_EXTERN,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .post_load = ipmi_bmc_extern_post_migrate,
+    .fields      = (VMStateField[]) {
+        VMSTATE_BOOL(send_reset, IPMIBmcExtern),
+        VMSTATE_BOOL(waiting_rsp, IPMIBmcExtern),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void ipmi_bmc_extern_init(Object *obj)
+{
+    IPMIBmcExtern *ibe = IPMI_BMC_EXTERN(obj);
+
+    ibe->extern_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, extern_timeout, ibe);
+    vmstate_register(NULL, 0, &vmstate_ipmi_bmc_extern, ibe);
+}
+
+static Property ipmi_bmc_extern_properties[] = {
+    DEFINE_PROP_CHR("chardev", IPMIBmcExtern, chr),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void ipmi_bmc_extern_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+    IPMIBmcClass *bk = IPMI_BMC_CLASS(oc);
+
+    bk->handle_command = ipmi_bmc_extern_handle_command;
+    bk->handle_reset = ipmi_bmc_extern_handle_reset;
+    dc->realize = ipmi_bmc_extern_realize;
+    dc->props = ipmi_bmc_extern_properties;
+}
+
+static const TypeInfo ipmi_bmc_extern_type = {
+    .name          = TYPE_IPMI_BMC_EXTERN,
+    .parent        = TYPE_IPMI_BMC,
+    .instance_size = sizeof(IPMIBmcExtern),
+    .instance_init = ipmi_bmc_extern_init,
+    .class_init    = ipmi_bmc_extern_class_init,
+ };
+
+static void ipmi_bmc_extern_register_types(void)
+{
+    type_register_static(&ipmi_bmc_extern_type);
+}
+
+type_init(ipmi_bmc_extern_register_types)

hw/ipmi/isa_ipmi_bt.c

@@ -0,0 +1,528 @@
+/*
+ * QEMU ISA IPMI BT emulation
+ *
+ * Copyright (c) 2015 Corey Minyard, MontaVista Software, LLC
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "hw/hw.h"
+#include "hw/ipmi/ipmi.h"
+#include "hw/isa/isa.h"
+#include "hw/i386/pc.h"
+
+/* Control register */
+#define IPMI_BT_CLR_WR_BIT         0
+#define IPMI_BT_CLR_RD_BIT         1
+#define IPMI_BT_H2B_ATN_BIT        2
+#define IPMI_BT_B2H_ATN_BIT        3
+#define IPMI_BT_SMS_ATN_BIT        4
+#define IPMI_BT_HBUSY_BIT          6
+#define IPMI_BT_BBUSY_BIT          7
+
+#define IPMI_BT_CLR_WR_MASK        (1 << IPMI_BT_CLR_WR_BIT)
+#define IPMI_BT_GET_CLR_WR(d)      (((d) >> IPMI_BT_CLR_WR_BIT) & 0x1)
+#define IPMI_BT_SET_CLR_WR(d, v)   (d) = (((d) & ~IPMI_BT_CLR_WR_MASK) | \
+                                       (((v & 1) << IPMI_BT_CLR_WR_BIT)))
+
+#define IPMI_BT_CLR_RD_MASK        (1 << IPMI_BT_CLR_RD_BIT)
+#define IPMI_BT_GET_CLR_RD(d)      (((d) >> IPMI_BT_CLR_RD_BIT) & 0x1)
+#define IPMI_BT_SET_CLR_RD(d, v)   (d) = (((d) & ~IPMI_BT_CLR_RD_MASK) | \
+                                       (((v & 1) << IPMI_BT_CLR_RD_BIT)))
+
+#define IPMI_BT_H2B_ATN_MASK       (1 << IPMI_BT_H2B_ATN_BIT)
+#define IPMI_BT_GET_H2B_ATN(d)     (((d) >> IPMI_BT_H2B_ATN_BIT) & 0x1)
+#define IPMI_BT_SET_H2B_ATN(d, v)  (d) = (((d) & ~IPMI_BT_H2B_ATN_MASK) | \
+                                        (((v & 1) << IPMI_BT_H2B_ATN_BIT)))
+
+#define IPMI_BT_B2H_ATN_MASK       (1 << IPMI_BT_B2H_ATN_BIT)
+#define IPMI_BT_GET_B2H_ATN(d)     (((d) >> IPMI_BT_B2H_ATN_BIT) & 0x1)
+#define IPMI_BT_SET_B2H_ATN(d, v)  (d) = (((d) & ~IPMI_BT_B2H_ATN_MASK) | \
+                                        (((v & 1) << IPMI_BT_B2H_ATN_BIT)))
+
+#define IPMI_BT_SMS_ATN_MASK       (1 << IPMI_BT_SMS_ATN_BIT)
+#define IPMI_BT_GET_SMS_ATN(d)     (((d) >> IPMI_BT_SMS_ATN_BIT) & 0x1)
+#define IPMI_BT_SET_SMS_ATN(d, v)  (d) = (((d) & ~IPMI_BT_SMS_ATN_MASK) | \
+                                        (((v & 1) << IPMI_BT_SMS_ATN_BIT)))
+
+#define IPMI_BT_HBUSY_MASK         (1 << IPMI_BT_HBUSY_BIT)
+#define IPMI_BT_GET_HBUSY(d)       (((d) >> IPMI_BT_HBUSY_BIT) & 0x1)
+#define IPMI_BT_SET_HBUSY(d, v)    (d) = (((d) & ~IPMI_BT_HBUSY_MASK) | \
+                                       (((v & 1) << IPMI_BT_HBUSY_BIT)))
+
+#define IPMI_BT_BBUSY_MASK         (1 << IPMI_BT_BBUSY_BIT)
+#define IPMI_BT_GET_BBUSY(d)       (((d) >> IPMI_BT_BBUSY_BIT) & 0x1)
+#define IPMI_BT_SET_BBUSY(d, v)    (d) = (((d) & ~IPMI_BT_BBUSY_MASK) | \
+                                       (((v & 1) << IPMI_BT_BBUSY_BIT)))
+
+
+/* Mask register */
+#define IPMI_BT_B2H_IRQ_EN_BIT     0
+#define IPMI_BT_B2H_IRQ_BIT        1
+
+#define IPMI_BT_B2H_IRQ_EN_MASK      (1 << IPMI_BT_B2H_IRQ_EN_BIT)
+#define IPMI_BT_GET_B2H_IRQ_EN(d)    (((d) >> IPMI_BT_B2H_IRQ_EN_BIT) & 0x1)
+#define IPMI_BT_SET_B2H_IRQ_EN(d, v) (d) = (((d) & ~IPMI_BT_B2H_IRQ_EN_MASK) | \
+                                        (((v & 1) << IPMI_BT_B2H_IRQ_EN_BIT)))
+
+#define IPMI_BT_B2H_IRQ_MASK         (1 << IPMI_BT_B2H_IRQ_BIT)
+#define IPMI_BT_GET_B2H_IRQ(d)       (((d) >> IPMI_BT_B2H_IRQ_BIT) & 0x1)
+#define IPMI_BT_SET_B2H_IRQ(d, v)    (d) = (((d) & ~IPMI_BT_B2H_IRQ_MASK) | \
+                                        (((v & 1) << IPMI_BT_B2H_IRQ_BIT)))
+
+typedef struct IPMIBT {
+    IPMIBmc *bmc;
+
+    bool do_wake;
+
+    qemu_irq irq;
+
+    uint32_t io_base;
+    unsigned long io_length;
+    MemoryRegion io;
+
+    bool obf_irq_set;
+    bool atn_irq_set;
+    bool use_irq;
+    bool irqs_enabled;
+
+    uint8_t outmsg[MAX_IPMI_MSG_SIZE];
+    uint32_t outpos;
+    uint32_t outlen;
+
+    uint8_t inmsg[MAX_IPMI_MSG_SIZE];
+    uint32_t inlen;
+
+    uint8_t control_reg;
+    uint8_t mask_reg;
+
+    /*
+     * This is a response number that we send with the command to make
+     * sure that the response matches the command.
+     */
+    uint8_t waiting_rsp;
+    uint8_t waiting_seq;
+} IPMIBT;
+
+#define IPMI_CMD_GET_BT_INTF_CAP        0x36
+
+static void ipmi_bt_handle_event(IPMIInterface *ii)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    if (ib->inlen < 4) {
+        goto out;
+    }
+    /* Note that overruns are handled by handle_command */
+    if (ib->inmsg[0] != (ib->inlen - 1)) {
+        /* Length mismatch, just ignore. */
+        IPMI_BT_SET_BBUSY(ib->control_reg, 1);
+        ib->inlen = 0;
+        goto out;
+    }
+    if ((ib->inmsg[1] == (IPMI_NETFN_APP << 2)) &&
+                        (ib->inmsg[3] == IPMI_CMD_GET_BT_INTF_CAP)) {
+        /* We handle this one ourselves. */
+        ib->outmsg[0] = 9;
+        ib->outmsg[1] = ib->inmsg[1] | 0x04;
+        ib->outmsg[2] = ib->inmsg[2];
+        ib->outmsg[3] = ib->inmsg[3];
+        ib->outmsg[4] = 0;
+        ib->outmsg[5] = 1; /* Only support 1 outstanding request. */
+        if (sizeof(ib->inmsg) > 0xff) { /* Input buffer size */
+            ib->outmsg[6] = 0xff;
+        } else {
+            ib->outmsg[6] = (unsigned char) sizeof(ib->inmsg);
+        }
+        if (sizeof(ib->outmsg) > 0xff) { /* Output buffer size */
+            ib->outmsg[7] = 0xff;
+        } else {
+            ib->outmsg[7] = (unsigned char) sizeof(ib->outmsg);
+        }
+        ib->outmsg[8] = 10; /* Max request to response time */
+        ib->outmsg[9] = 0; /* Don't recommend retries */
+        ib->outlen = 10;
+        IPMI_BT_SET_BBUSY(ib->control_reg, 0);
+        IPMI_BT_SET_B2H_ATN(ib->control_reg, 1);
+        if (ib->use_irq && ib->irqs_enabled &&
+                !IPMI_BT_GET_B2H_IRQ(ib->mask_reg) &&
+                IPMI_BT_GET_B2H_IRQ_EN(ib->mask_reg)) {
+            IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 1);
+            qemu_irq_raise(ib->irq);
+        }
+        goto out;
+    }
+    ib->waiting_seq = ib->inmsg[2];
+    ib->inmsg[2] = ib->inmsg[1];
+    {
+        IPMIBmcClass *bk = IPMI_BMC_GET_CLASS(ib->bmc);
+        bk->handle_command(ib->bmc, ib->inmsg + 2, ib->inlen - 2,
+                           sizeof(ib->inmsg), ib->waiting_rsp);
+    }
+ out:
+    return;
+}
+
+static void ipmi_bt_handle_rsp(IPMIInterface *ii, uint8_t msg_id,
+                                unsigned char *rsp, unsigned int rsp_len)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    if (ib->waiting_rsp == msg_id) {
+        ib->waiting_rsp++;
+        if (rsp_len > (sizeof(ib->outmsg) - 2)) {
+            ib->outmsg[0] = 4;
+            ib->outmsg[1] = rsp[0];
+            ib->outmsg[2] = ib->waiting_seq;
+            ib->outmsg[3] = rsp[1];
+            ib->outmsg[4] = IPMI_CC_CANNOT_RETURN_REQ_NUM_BYTES;
+            ib->outlen = 5;
+        } else {
+            ib->outmsg[0] = rsp_len + 1;
+            ib->outmsg[1] = rsp[0];
+            ib->outmsg[2] = ib->waiting_seq;
+            memcpy(ib->outmsg + 3, rsp + 1, rsp_len - 1);
+            ib->outlen = rsp_len + 2;
+        }
+        IPMI_BT_SET_BBUSY(ib->control_reg, 0);
+        IPMI_BT_SET_B2H_ATN(ib->control_reg, 1);
+        if (ib->use_irq && ib->irqs_enabled &&
+                !IPMI_BT_GET_B2H_IRQ(ib->mask_reg) &&
+                IPMI_BT_GET_B2H_IRQ_EN(ib->mask_reg)) {
+            IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 1);
+            qemu_irq_raise(ib->irq);
+        }
+    }
+}
+
+
+static uint64_t ipmi_bt_ioport_read(void *opaque, hwaddr addr, unsigned size)
+{
+    IPMIInterface *ii = opaque;
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+    uint32_t ret = 0xff;
+
+    switch (addr & 3) {
+    case 0:
+        ret = ib->control_reg;
+        break;
+    case 1:
+        if (ib->outpos < ib->outlen) {
+            ret = ib->outmsg[ib->outpos];
+            ib->outpos++;
+            if (ib->outpos == ib->outlen) {
+                ib->outpos = 0;
+                ib->outlen = 0;
+            }
+        } else {
+            ret = 0xff;
+        }
+        break;
+    case 2:
+        ret = ib->mask_reg;
+        break;
+    }
+    return ret;
+}
+
+static void ipmi_bt_signal(IPMIBT *ib, IPMIInterface *ii)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+
+    ib->do_wake = 1;
+    while (ib->do_wake) {
+        ib->do_wake = 0;
+        iic->handle_if_event(ii);
+    }
+}
+
+static void ipmi_bt_ioport_write(void *opaque, hwaddr addr, uint64_t val,
+                                 unsigned size)
+{
+    IPMIInterface *ii = opaque;
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    switch (addr & 3) {
+    case 0:
+        if (IPMI_BT_GET_CLR_WR(val)) {
+            ib->inlen = 0;
+        }
+        if (IPMI_BT_GET_CLR_RD(val)) {
+            ib->outpos = 0;
+        }
+        if (IPMI_BT_GET_B2H_ATN(val)) {
+            IPMI_BT_SET_B2H_ATN(ib->control_reg, 0);
+        }
+        if (IPMI_BT_GET_SMS_ATN(val)) {
+            IPMI_BT_SET_SMS_ATN(ib->control_reg, 0);
+        }
+        if (IPMI_BT_GET_HBUSY(val)) {
+            /* Toggle */
+            IPMI_BT_SET_HBUSY(ib->control_reg,
+                              !IPMI_BT_GET_HBUSY(ib->control_reg));
+        }
+        if (IPMI_BT_GET_H2B_ATN(val)) {
+            IPMI_BT_SET_BBUSY(ib->control_reg, 1);
+            ipmi_bt_signal(ib, ii);
+        }
+        break;
+
+    case 1:
+        if (ib->inlen < sizeof(ib->inmsg)) {
+            ib->inmsg[ib->inlen] = val;
+        }
+        ib->inlen++;
+        break;
+
+    case 2:
+        if (IPMI_BT_GET_B2H_IRQ_EN(val) !=
+                        IPMI_BT_GET_B2H_IRQ_EN(ib->mask_reg)) {
+            if (IPMI_BT_GET_B2H_IRQ_EN(val)) {
+                if (IPMI_BT_GET_B2H_ATN(ib->control_reg) ||
+                        IPMI_BT_GET_SMS_ATN(ib->control_reg)) {
+                    IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 1);
+                    qemu_irq_raise(ib->irq);
+                }
+                IPMI_BT_SET_B2H_IRQ_EN(ib->mask_reg, 1);
+            } else {
+                if (IPMI_BT_GET_B2H_IRQ(ib->mask_reg)) {
+                    IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 0);
+                    qemu_irq_lower(ib->irq);
+                }
+                IPMI_BT_SET_B2H_IRQ_EN(ib->mask_reg, 0);
+            }
+        }
+        if (IPMI_BT_GET_B2H_IRQ(val) && IPMI_BT_GET_B2H_IRQ(ib->mask_reg)) {
+            IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 0);
+            qemu_irq_lower(ib->irq);
+        }
+        break;
+    }
+}
+
+static const MemoryRegionOps ipmi_bt_io_ops = {
+    .read = ipmi_bt_ioport_read,
+    .write = ipmi_bt_ioport_write,
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 1,
+    },
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+static void ipmi_bt_set_atn(IPMIInterface *ii, int val, int irq)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    if (!!val == IPMI_BT_GET_SMS_ATN(ib->control_reg)) {
+        return;
+    }
+
+    IPMI_BT_SET_SMS_ATN(ib->control_reg, val);
+    if (val) {
+        if (irq && ib->use_irq && ib->irqs_enabled &&
+                !IPMI_BT_GET_B2H_ATN(ib->control_reg) &&
+                IPMI_BT_GET_B2H_IRQ_EN(ib->mask_reg)) {
+            IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 1);
+            qemu_irq_raise(ib->irq);
+        }
+    } else {
+        if (!IPMI_BT_GET_B2H_ATN(ib->control_reg) &&
+                IPMI_BT_GET_B2H_IRQ(ib->mask_reg)) {
+            IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 0);
+            qemu_irq_lower(ib->irq);
+        }
+    }
+}
+
+static void ipmi_bt_handle_reset(IPMIInterface *ii, bool is_cold)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    if (is_cold) {
+        /* Disable the BT interrupt on reset */
+        if (IPMI_BT_GET_B2H_IRQ(ib->mask_reg)) {
+            IPMI_BT_SET_B2H_IRQ(ib->mask_reg, 0);
+            qemu_irq_lower(ib->irq);
+        }
+        IPMI_BT_SET_B2H_IRQ_EN(ib->mask_reg, 0);
+    }
+}
+
+static void ipmi_bt_set_irq_enable(IPMIInterface *ii, int val)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    ib->irqs_enabled = val;
+}
+
+static void ipmi_bt_init(IPMIInterface *ii, Error **errp)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIBT *ib = iic->get_backend_data(ii);
+
+    ib->io_length = 3;
+
+    memory_region_init_io(&ib->io, NULL, &ipmi_bt_io_ops, ii, "ipmi-bt", 3);
+}
+
+static void ipmi_bt_class_init(IPMIInterfaceClass *iic)
+{
+    iic->init = ipmi_bt_init;
+    iic->set_atn = ipmi_bt_set_atn;
+    iic->handle_rsp = ipmi_bt_handle_rsp;
+    iic->handle_if_event = ipmi_bt_handle_event;
+    iic->set_irq_enable = ipmi_bt_set_irq_enable;
+    iic->reset = ipmi_bt_handle_reset;
+}
+
+
+#define TYPE_ISA_IPMI_BT "isa-ipmi-bt"
+#define ISA_IPMI_BT(obj) OBJECT_CHECK(ISAIPMIBTDevice, (obj), \
+                                       TYPE_ISA_IPMI_BT)
+
+typedef struct ISAIPMIBTDevice {
+    ISADevice dev;
+    int32 isairq;
+    IPMIBT bt;
+    IPMIFwInfo fwinfo;
+} ISAIPMIBTDevice;
+
+static void isa_ipmi_bt_realize(DeviceState *dev, Error **errp)
+{
+    ISADevice *isadev = ISA_DEVICE(dev);
+    ISAIPMIBTDevice *iib = ISA_IPMI_BT(dev);
+    IPMIInterface *ii = IPMI_INTERFACE(dev);
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+
+    if (!iib->bt.bmc) {
+        error_setg(errp, "IPMI device requires a bmc attribute to be set");
+        return;
+    }
+
+    iib->bt.bmc->intf = ii;
+
+    iic->init(ii, errp);
+    if (*errp)
+        return;
+
+    if (iib->isairq > 0) {
+        isa_init_irq(isadev, &iib->bt.irq, iib->isairq);
+        iib->bt.use_irq = 1;
+    }
+
+    qdev_set_legacy_instance_id(dev, iib->bt.io_base, iib->bt.io_length);
+
+    isa_register_ioport(isadev, &iib->bt.io, iib->bt.io_base);
+
+    iib->fwinfo.interface_name = "bt";
+    iib->fwinfo.interface_type = IPMI_SMBIOS_BT;
+    iib->fwinfo.ipmi_spec_major_revision = 2;
+    iib->fwinfo.ipmi_spec_minor_revision = 0;
+    iib->fwinfo.base_address = iib->bt.io_base;
+    iib->fwinfo.register_length = iib->bt.io_length;
+    iib->fwinfo.register_spacing = 1;
+    iib->fwinfo.memspace = IPMI_MEMSPACE_IO;
+    iib->fwinfo.irq_type = IPMI_LEVEL_IRQ;
+    iib->fwinfo.interrupt_number = iib->isairq;
+    iib->fwinfo.acpi_parent = "\\_SB.PCI0.ISA";
+    iib->fwinfo.i2c_slave_address = iib->bt.bmc->slave_addr;
+    ipmi_add_fwinfo(&iib->fwinfo, errp);
+}
+
+static const VMStateDescription vmstate_ISAIPMIBTDevice = {
+    .name = TYPE_IPMI_INTERFACE,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields      = (VMStateField[]) {
+        VMSTATE_BOOL(bt.obf_irq_set, ISAIPMIBTDevice),
+        VMSTATE_BOOL(bt.atn_irq_set, ISAIPMIBTDevice),
+        VMSTATE_BOOL(bt.use_irq, ISAIPMIBTDevice),
+        VMSTATE_BOOL(bt.irqs_enabled, ISAIPMIBTDevice),
+        VMSTATE_UINT32(bt.outpos, ISAIPMIBTDevice),
+        VMSTATE_VBUFFER_UINT32(bt.outmsg, ISAIPMIBTDevice, 1, NULL, 0,
+                               bt.outlen),
+        VMSTATE_VBUFFER_UINT32(bt.inmsg, ISAIPMIBTDevice, 1, NULL, 0,
+                               bt.inlen),
+        VMSTATE_UINT8(bt.control_reg, ISAIPMIBTDevice),
+        VMSTATE_UINT8(bt.mask_reg, ISAIPMIBTDevice),
+        VMSTATE_UINT8(bt.waiting_rsp, ISAIPMIBTDevice),
+        VMSTATE_UINT8(bt.waiting_seq, ISAIPMIBTDevice),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void isa_ipmi_bt_init(Object *obj)
+{
+    ISAIPMIBTDevice *iib = ISA_IPMI_BT(obj);
+
+    ipmi_bmc_find_and_link(obj, (Object **) &iib->bt.bmc);
+
+    vmstate_register(NULL, 0, &vmstate_ISAIPMIBTDevice, iib);
+}
+
+static void *isa_ipmi_bt_get_backend_data(IPMIInterface *ii)
+{
+    ISAIPMIBTDevice *iib = ISA_IPMI_BT(ii);
+
+    return &iib->bt;
+}
+
+static Property ipmi_isa_properties[] = {
+    DEFINE_PROP_UINT32("ioport", ISAIPMIBTDevice, bt.io_base,  0xe4),
+    DEFINE_PROP_INT32("irq",   ISAIPMIBTDevice, isairq,  5),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void isa_ipmi_bt_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_CLASS(oc);
+
+    dc->realize = isa_ipmi_bt_realize;
+    dc->props = ipmi_isa_properties;
+
+    iic->get_backend_data = isa_ipmi_bt_get_backend_data;
+    ipmi_bt_class_init(iic);
+}
+
+static const TypeInfo isa_ipmi_bt_info = {
+    .name          = TYPE_ISA_IPMI_BT,
+    .parent        = TYPE_ISA_DEVICE,
+    .instance_size = sizeof(ISAIPMIBTDevice),
+    .instance_init = isa_ipmi_bt_init,
+    .class_init    = isa_ipmi_bt_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_IPMI_INTERFACE },
+        { }
+    }
+};
+
+static void ipmi_register_types(void)
+{
+    type_register_static(&isa_ipmi_bt_info);
+}
+
+type_init(ipmi_register_types)

hw/ipmi/isa_ipmi_kcs.c

@@ -0,0 +1,493 @@
+/*
+ * QEMU ISA IPMI KCS emulation
+ *
+ * Copyright (c) 2015 Corey Minyard, MontaVista Software, LLC
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "hw/hw.h"
+#include "hw/ipmi/ipmi.h"
+#include "hw/isa/isa.h"
+#include "hw/i386/pc.h"
+
+#define IPMI_KCS_OBF_BIT        0
+#define IPMI_KCS_IBF_BIT        1
+#define IPMI_KCS_SMS_ATN_BIT    2
+#define IPMI_KCS_CD_BIT         3
+
+#define IPMI_KCS_OBF_MASK          (1 << IPMI_KCS_OBF_BIT)
+#define IPMI_KCS_GET_OBF(d)        (((d) >> IPMI_KCS_OBF_BIT) & 0x1)
+#define IPMI_KCS_SET_OBF(d, v)     (d) = (((d) & ~IPMI_KCS_OBF_MASK) | \
+                                       (((v) & 1) << IPMI_KCS_OBF_BIT))
+#define IPMI_KCS_IBF_MASK          (1 << IPMI_KCS_IBF_BIT)
+#define IPMI_KCS_GET_IBF(d)        (((d) >> IPMI_KCS_IBF_BIT) & 0x1)
+#define IPMI_KCS_SET_IBF(d, v)     (d) = (((d) & ~IPMI_KCS_IBF_MASK) | \
+                                       (((v) & 1) << IPMI_KCS_IBF_BIT))
+#define IPMI_KCS_SMS_ATN_MASK      (1 << IPMI_KCS_SMS_ATN_BIT)
+#define IPMI_KCS_GET_SMS_ATN(d)    (((d) >> IPMI_KCS_SMS_ATN_BIT) & 0x1)
+#define IPMI_KCS_SET_SMS_ATN(d, v) (d) = (((d) & ~IPMI_KCS_SMS_ATN_MASK) | \
+                                       (((v) & 1) << IPMI_KCS_SMS_ATN_BIT))
+#define IPMI_KCS_CD_MASK           (1 << IPMI_KCS_CD_BIT)
+#define IPMI_KCS_GET_CD(d)         (((d) >> IPMI_KCS_CD_BIT) & 0x1)
+#define IPMI_KCS_SET_CD(d, v)      (d) = (((d) & ~IPMI_KCS_CD_MASK) | \
+                                       (((v) & 1) << IPMI_KCS_CD_BIT))
+
+#define IPMI_KCS_IDLE_STATE        0
+#define IPMI_KCS_READ_STATE        1
+#define IPMI_KCS_WRITE_STATE       2
+#define IPMI_KCS_ERROR_STATE       3
+
+#define IPMI_KCS_GET_STATE(d)    (((d) >> 6) & 0x3)
+#define IPMI_KCS_SET_STATE(d, v) ((d) = ((d) & ~0xc0) | (((v) & 0x3) << 6))
+
+#define IPMI_KCS_ABORT_STATUS_CMD       0x60
+#define IPMI_KCS_WRITE_START_CMD        0x61
+#define IPMI_KCS_WRITE_END_CMD          0x62
+#define IPMI_KCS_READ_CMD               0x68
+
+#define IPMI_KCS_STATUS_NO_ERR          0x00
+#define IPMI_KCS_STATUS_ABORTED_ERR     0x01
+#define IPMI_KCS_STATUS_BAD_CC_ERR      0x02
+#define IPMI_KCS_STATUS_LENGTH_ERR      0x06
+
+typedef struct IPMIKCS {
+    IPMIBmc *bmc;
+
+    bool do_wake;
+
+    qemu_irq irq;
+
+    uint32_t io_base;
+    unsigned long io_length;
+    MemoryRegion io;
+
+    bool obf_irq_set;
+    bool atn_irq_set;
+    bool use_irq;
+    bool irqs_enabled;
+
+    uint8_t outmsg[MAX_IPMI_MSG_SIZE];
+    uint32_t outpos;
+    uint32_t outlen;
+
+    uint8_t inmsg[MAX_IPMI_MSG_SIZE];
+    uint32_t inlen;
+    bool write_end;
+
+    uint8_t status_reg;
+    uint8_t data_out_reg;
+
+    int16_t data_in_reg; /* -1 means not written */
+    int16_t cmd_reg;
+
+    /*
+     * This is a response number that we send with the command to make
+     * sure that the response matches the command.
+     */
+    uint8_t waiting_rsp;
+} IPMIKCS;
+
+#define SET_OBF() \
+    do {                                                                      \
+        IPMI_KCS_SET_OBF(ik->status_reg, 1);                                  \
+        if (ik->use_irq && ik->irqs_enabled && !ik->obf_irq_set) {            \
+            ik->obf_irq_set = 1;                                              \
+            if (!ik->atn_irq_set) {                                           \
+                qemu_irq_raise(ik->irq);                                      \
+            }                                                                 \
+        }                                                                     \
+    } while (0)
+
+static void ipmi_kcs_signal(IPMIKCS *ik, IPMIInterface *ii)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+
+    ik->do_wake = 1;
+    while (ik->do_wake) {
+        ik->do_wake = 0;
+        iic->handle_if_event(ii);
+    }
+}
+
+static void ipmi_kcs_handle_event(IPMIInterface *ii)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+
+    if (ik->cmd_reg == IPMI_KCS_ABORT_STATUS_CMD) {
+        if (IPMI_KCS_GET_STATE(ik->status_reg) != IPMI_KCS_ERROR_STATE) {
+            ik->waiting_rsp++; /* Invalidate the message */
+            ik->outmsg[0] = IPMI_KCS_STATUS_ABORTED_ERR;
+            ik->outlen = 1;
+            ik->outpos = 0;
+            IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_ERROR_STATE);
+            SET_OBF();
+        }
+        goto out;
+    }
+
+    switch (IPMI_KCS_GET_STATE(ik->status_reg)) {
+    case IPMI_KCS_IDLE_STATE:
+        if (ik->cmd_reg == IPMI_KCS_WRITE_START_CMD) {
+            IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_WRITE_STATE);
+            ik->cmd_reg = -1;
+            ik->write_end = 0;
+            ik->inlen = 0;
+            SET_OBF();
+        }
+        break;
+
+    case IPMI_KCS_READ_STATE:
+    handle_read:
+        if (ik->outpos >= ik->outlen) {
+            IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_IDLE_STATE);
+            SET_OBF();
+        } else if (ik->data_in_reg == IPMI_KCS_READ_CMD) {
+            ik->data_out_reg = ik->outmsg[ik->outpos];
+            ik->outpos++;
+            SET_OBF();
+        } else {
+            ik->outmsg[0] = IPMI_KCS_STATUS_BAD_CC_ERR;
+            ik->outlen = 1;
+            ik->outpos = 0;
+            IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_ERROR_STATE);
+            SET_OBF();
+            goto out;
+        }
+        break;
+
+    case IPMI_KCS_WRITE_STATE:
+        if (ik->data_in_reg != -1) {
+            /*
+             * Don't worry about input overrun here, that will be
+             * handled in the BMC.
+             */
+            if (ik->inlen < sizeof(ik->inmsg)) {
+                ik->inmsg[ik->inlen] = ik->data_in_reg;
+            }
+            ik->inlen++;
+        }
+        if (ik->write_end) {
+            IPMIBmcClass *bk = IPMI_BMC_GET_CLASS(ik->bmc);
+            ik->outlen = 0;
+            ik->write_end = 0;
+            ik->outpos = 0;
+            bk->handle_command(ik->bmc, ik->inmsg, ik->inlen, sizeof(ik->inmsg),
+                               ik->waiting_rsp);
+            goto out_noibf;
+        } else if (ik->cmd_reg == IPMI_KCS_WRITE_END_CMD) {
+            ik->cmd_reg = -1;
+            ik->write_end = 1;
+        }
+        SET_OBF();
+        break;
+
+    case IPMI_KCS_ERROR_STATE:
+        if (ik->data_in_reg != -1) {
+            IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_READ_STATE);
+            ik->data_in_reg = IPMI_KCS_READ_CMD;
+            goto handle_read;
+        }
+        break;
+    }
+
+    if (ik->cmd_reg != -1) {
+        /* Got an invalid command */
+        ik->outmsg[0] = IPMI_KCS_STATUS_BAD_CC_ERR;
+        ik->outlen = 1;
+        ik->outpos = 0;
+        IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_ERROR_STATE);
+    }
+
+ out:
+    ik->cmd_reg = -1;
+    ik->data_in_reg = -1;
+    IPMI_KCS_SET_IBF(ik->status_reg, 0);
+ out_noibf:
+    return;
+}
+
+static void ipmi_kcs_handle_rsp(IPMIInterface *ii, uint8_t msg_id,
+                                unsigned char *rsp, unsigned int rsp_len)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+
+    if (ik->waiting_rsp == msg_id) {
+        ik->waiting_rsp++;
+        if (rsp_len > sizeof(ik->outmsg)) {
+            ik->outmsg[0] = rsp[0];
+            ik->outmsg[1] = rsp[1];
+            ik->outmsg[2] = IPMI_CC_CANNOT_RETURN_REQ_NUM_BYTES;
+            ik->outlen = 3;
+        } else {
+            memcpy(ik->outmsg, rsp, rsp_len);
+            ik->outlen = rsp_len;
+        }
+        IPMI_KCS_SET_STATE(ik->status_reg, IPMI_KCS_READ_STATE);
+        ik->data_in_reg = IPMI_KCS_READ_CMD;
+        ipmi_kcs_signal(ik, ii);
+    }
+}
+
+
+static uint64_t ipmi_kcs_ioport_read(void *opaque, hwaddr addr, unsigned size)
+{
+    IPMIInterface *ii = opaque;
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+    uint32_t ret;
+
+    switch (addr & 1) {
+    case 0:
+        ret = ik->data_out_reg;
+        IPMI_KCS_SET_OBF(ik->status_reg, 0);
+        if (ik->obf_irq_set) {
+            ik->obf_irq_set = 0;
+            if (!ik->atn_irq_set) {
+                qemu_irq_lower(ik->irq);
+            }
+        }
+        break;
+    case 1:
+        ret = ik->status_reg;
+        if (ik->atn_irq_set) {
+            ik->atn_irq_set = 0;
+            if (!ik->obf_irq_set) {
+                qemu_irq_lower(ik->irq);
+            }
+        }
+        break;
+    }
+    return ret;
+}
+
+static void ipmi_kcs_ioport_write(void *opaque, hwaddr addr, uint64_t val,
+                                  unsigned size)
+{
+    IPMIInterface *ii = opaque;
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+
+    if (IPMI_KCS_GET_IBF(ik->status_reg)) {
+        return;
+    }
+
+    switch (addr & 1) {
+    case 0:
+        ik->data_in_reg = val;
+        break;
+
+    case 1:
+        ik->cmd_reg = val;
+        break;
+    }
+    IPMI_KCS_SET_IBF(ik->status_reg, 1);
+    ipmi_kcs_signal(ik, ii);
+}
+
+const MemoryRegionOps ipmi_kcs_io_ops = {
+    .read = ipmi_kcs_ioport_read,
+    .write = ipmi_kcs_ioport_write,
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 1,
+    },
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+static void ipmi_kcs_set_atn(IPMIInterface *ii, int val, int irq)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+
+    IPMI_KCS_SET_SMS_ATN(ik->status_reg, val);
+    if (val) {
+        if (irq && !ik->atn_irq_set && ik->use_irq && ik->irqs_enabled) {
+            ik->atn_irq_set = 1;
+            if (!ik->obf_irq_set) {
+                qemu_irq_raise(ik->irq);
+            }
+        }
+    } else {
+        if (ik->atn_irq_set) {
+            ik->atn_irq_set = 0;
+            if (!ik->obf_irq_set) {
+                qemu_irq_lower(ik->irq);
+            }
+        }
+    }
+}
+
+static void ipmi_kcs_set_irq_enable(IPMIInterface *ii, int val)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+
+    ik->irqs_enabled = val;
+}
+
+static void ipmi_kcs_init(IPMIInterface *ii, Error **errp)
+{
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+    IPMIKCS *ik = iic->get_backend_data(ii);
+
+    ik->io_length = 2;
+    memory_region_init_io(&ik->io, NULL, &ipmi_kcs_io_ops, ii, "ipmi-kcs", 2);
+}
+
+static void ipmi_kcs_class_init(IPMIInterfaceClass *iic)
+{
+    iic->init = ipmi_kcs_init;
+    iic->set_atn = ipmi_kcs_set_atn;
+    iic->handle_rsp = ipmi_kcs_handle_rsp;
+    iic->handle_if_event = ipmi_kcs_handle_event;
+    iic->set_irq_enable = ipmi_kcs_set_irq_enable;
+}
+
+
+#define TYPE_ISA_IPMI_KCS "isa-ipmi-kcs"
+#define ISA_IPMI_KCS(obj) OBJECT_CHECK(ISAIPMIKCSDevice, (obj), \
+                                       TYPE_ISA_IPMI_KCS)
+
+typedef struct ISAIPMIKCSDevice {
+    ISADevice dev;
+    int32 isairq;
+    IPMIKCS kcs;
+    IPMIFwInfo fwinfo;
+} ISAIPMIKCSDevice;
+
+static void ipmi_isa_realize(DeviceState *dev, Error **errp)
+{
+    ISADevice *isadev = ISA_DEVICE(dev);
+    ISAIPMIKCSDevice *iik = ISA_IPMI_KCS(dev);
+    IPMIInterface *ii = IPMI_INTERFACE(dev);
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_GET_CLASS(ii);
+
+    if (!iik->kcs.bmc) {
+        error_setg(errp, "IPMI device requires a bmc attribute to be set");
+        return;
+    }
+
+    iik->kcs.bmc->intf = ii;
+
+    iic->init(ii, errp);
+    if (*errp)
+        return;
+
+    if (iik->isairq > 0) {
+        isa_init_irq(isadev, &iik->kcs.irq, iik->isairq);
+        iik->kcs.use_irq = 1;
+    }
+
+    qdev_set_legacy_instance_id(dev, iik->kcs.io_base, iik->kcs.io_length);
+
+    isa_register_ioport(isadev, &iik->kcs.io, iik->kcs.io_base);
+
+    iik->fwinfo.interface_name = "kcs";
+    iik->fwinfo.interface_type = IPMI_SMBIOS_KCS;
+    iik->fwinfo.ipmi_spec_major_revision = 2;
+    iik->fwinfo.ipmi_spec_minor_revision = 0;
+    iik->fwinfo.base_address = iik->kcs.io_base;
+    iik->fwinfo.i2c_slave_address = iik->kcs.bmc->slave_addr;
+    iik->fwinfo.register_length = iik->kcs.io_length;
+    iik->fwinfo.register_spacing = 1;
+    iik->fwinfo.memspace = IPMI_MEMSPACE_IO;
+    iik->fwinfo.irq_type = IPMI_LEVEL_IRQ;
+    iik->fwinfo.interrupt_number = iik->isairq;
+    iik->fwinfo.acpi_parent = "\\_SB.PCI0.ISA";
+    ipmi_add_fwinfo(&iik->fwinfo, errp);
+}
+
+const VMStateDescription vmstate_ISAIPMIKCSDevice = {
+    .name = TYPE_IPMI_INTERFACE,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields      = (VMStateField[]) {
+        VMSTATE_BOOL(kcs.obf_irq_set, ISAIPMIKCSDevice),
+        VMSTATE_BOOL(kcs.atn_irq_set, ISAIPMIKCSDevice),
+        VMSTATE_BOOL(kcs.use_irq, ISAIPMIKCSDevice),
+        VMSTATE_BOOL(kcs.irqs_enabled, ISAIPMIKCSDevice),
+        VMSTATE_UINT32(kcs.outpos, ISAIPMIKCSDevice),
+        VMSTATE_VBUFFER_UINT32(kcs.outmsg, ISAIPMIKCSDevice, 1, NULL, 0,
+                               kcs.outlen),
+        VMSTATE_VBUFFER_UINT32(kcs.inmsg, ISAIPMIKCSDevice, 1, NULL, 0,
+                               kcs.inlen),
+        VMSTATE_BOOL(kcs.write_end, ISAIPMIKCSDevice),
+        VMSTATE_UINT8(kcs.status_reg, ISAIPMIKCSDevice),
+        VMSTATE_UINT8(kcs.data_out_reg, ISAIPMIKCSDevice),
+        VMSTATE_INT16(kcs.data_in_reg, ISAIPMIKCSDevice),
+        VMSTATE_INT16(kcs.cmd_reg, ISAIPMIKCSDevice),
+        VMSTATE_UINT8(kcs.waiting_rsp, ISAIPMIKCSDevice),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void isa_ipmi_kcs_init(Object *obj)
+{
+    ISAIPMIKCSDevice *iik = ISA_IPMI_KCS(obj);
+
+    ipmi_bmc_find_and_link(obj, (Object **) &iik->kcs.bmc);
+
+    vmstate_register(NULL, 0, &vmstate_ISAIPMIKCSDevice, iik);
+}
+
+static void *isa_ipmi_kcs_get_backend_data(IPMIInterface *ii)
+{
+    ISAIPMIKCSDevice *iik = ISA_IPMI_KCS(ii);
+
+    return &iik->kcs;
+}
+
+static Property ipmi_isa_properties[] = {
+    DEFINE_PROP_UINT32("ioport", ISAIPMIKCSDevice, kcs.io_base,  0xca2),
+    DEFINE_PROP_INT32("irq",   ISAIPMIKCSDevice, isairq,  5),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void isa_ipmi_kcs_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+    IPMIInterfaceClass *iic = IPMI_INTERFACE_CLASS(oc);
+
+    dc->realize = ipmi_isa_realize;
+    dc->props = ipmi_isa_properties;
+
+    iic->get_backend_data = isa_ipmi_kcs_get_backend_data;
+    ipmi_kcs_class_init(iic);
+}
+
+static const TypeInfo isa_ipmi_kcs_info = {
+    .name          = TYPE_ISA_IPMI_KCS,
+    .parent        = TYPE_ISA_DEVICE,
+    .instance_size = sizeof(ISAIPMIKCSDevice),
+    .instance_init = isa_ipmi_kcs_init,
+    .class_init    = isa_ipmi_kcs_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_IPMI_INTERFACE },
+        { }
+    }
+};
+
+static void ipmi_register_types(void)
+{
+    type_register_static(&isa_ipmi_kcs_info);
+}
+
+type_init(ipmi_register_types)

hw/mem/Makefile.objs

@@ -1 +1,2 @@
 common-obj-$(CONFIG_MEM_HOTPLUG) += pc-dimm.o
+common-obj-$(CONFIG_NVDIMM) += nvdimm.o

hw/mem/nvdimm.c

@@ -0,0 +1,46 @@
+/*
+ * Non-Volatile Dual In-line Memory Module Virtualization Implementation
+ *
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Author:
+ *  Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *
+ * Currently, it only supports PMEM Virtualization.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>
+ */
+
+#include "hw/mem/nvdimm.h"
+
+static void nvdimm_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    /* nvdimm hotplug has not been supported yet. */
+    dc->hotpluggable = false;
+}
+
+static TypeInfo nvdimm_info = {
+    .name          = TYPE_NVDIMM,
+    .parent        = TYPE_PC_DIMM,
+    .class_init    = nvdimm_class_init,
+};
+
+static void nvdimm_register_types(void)
+{
+    type_register_static(&nvdimm_info);
+}
+
+type_init(nvdimm_register_types)

hw/microblaze/petalogix_ml605_mmu.c

@@ -81,6 +81,7 @@ petalogix_ml605_init(MachineState *machine)
 
     /* init CPUs */
     cpu = MICROBLAZE_CPU(object_new(TYPE_MICROBLAZE_CPU));
+    object_property_set_str(OBJECT(cpu), "8.10.a", "version", &error_abort);
     /* Use FPU but don't use floating point conversion and square
      * root instructions
      */

hw/microblaze/petalogix_s3adsp1800_mmu.c

@@ -66,6 +66,7 @@ petalogix_s3adsp1800_init(MachineState *machine)
     MemoryRegion *sysmem = get_system_memory();
 
     cpu = MICROBLAZE_CPU(object_new(TYPE_MICROBLAZE_CPU));
+    object_property_set_str(OBJECT(cpu), "7.10.d", "version", &error_abort);
     object_property_set_bool(OBJECT(cpu), true, "realized", &error_abort);
 
     /* Attach emulated BRAM through the LMB.  */

hw/misc/Makefile.objs

@@ -26,6 +26,8 @@ obj-$(CONFIG_NSERIES) += cbus.o
 obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o
 obj-$(CONFIG_EXYNOS4) += exynos4210_pmu.o
 obj-$(CONFIG_IMX) += imx_ccm.o
+obj-$(CONFIG_IMX) += imx31_ccm.o
+obj-$(CONFIG_IMX) += imx25_ccm.o
 obj-$(CONFIG_MILKYMIST) += milkymist-hpdmc.o
 obj-$(CONFIG_MILKYMIST) += milkymist-pfpu.o
 obj-$(CONFIG_MAINSTONE) += mst_fpga.o
@@ -41,3 +43,4 @@ obj-$(CONFIG_STM32F2XX_SYSCFG) += stm32f2xx_syscfg.o
 
 obj-$(CONFIG_PVPANIC) += pvpanic.o
 obj-$(CONFIG_EDU) += edu.o
+obj-$(CONFIG_HYPERV_TESTDEV) += hyperv_testdev.o

hw/misc/hyperv_testdev.c

@@ -0,0 +1,167 @@
+/*
+ * QEMU KVM Hyper-V test device to support Hyper-V kvm-unit-tests
+ *
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ *  Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "hw/hw.h"
+#include "hw/qdev.h"
+#include "hw/isa/isa.h"
+#include "sysemu/kvm.h"
+#include "linux/kvm.h"
+#include "target-i386/hyperv.h"
+#include "kvm_i386.h"
+
+#define HV_TEST_DEV_MAX_SINT_ROUTES 64
+
+struct HypervTestDev {
+    ISADevice parent_obj;
+    MemoryRegion sint_control;
+    HvSintRoute *sint_route[HV_TEST_DEV_MAX_SINT_ROUTES];
+};
+typedef struct HypervTestDev HypervTestDev;
+
+#define TYPE_HYPERV_TEST_DEV "hyperv-testdev"
+#define HYPERV_TEST_DEV(obj) \
+        OBJECT_CHECK(HypervTestDev, (obj), TYPE_HYPERV_TEST_DEV)
+
+enum {
+    HV_TEST_DEV_SINT_ROUTE_CREATE = 1,
+    HV_TEST_DEV_SINT_ROUTE_DESTROY,
+    HV_TEST_DEV_SINT_ROUTE_SET_SINT
+};
+
+static int alloc_sint_route_index(HypervTestDev *dev)
+{
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(dev->sint_route); i++) {
+        if (dev->sint_route[i] == NULL) {
+            return i;
+        }
+    }
+    return -1;
+}
+
+static void free_sint_route_index(HypervTestDev *dev, int i)
+{
+    assert(i >= 0 && i < ARRAY_SIZE(dev->sint_route));
+    dev->sint_route[i] = NULL;
+}
+
+static int find_sint_route_index(HypervTestDev *dev, uint32_t vcpu_id,
+                                 uint32_t sint)
+{
+    HvSintRoute *sint_route;
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(dev->sint_route); i++) {
+        sint_route = dev->sint_route[i];
+        if (sint_route && sint_route->vcpu_id == vcpu_id &&
+            sint_route->sint == sint) {
+            return i;
+        }
+    }
+    return -1;
+}
+
+static void hv_synic_test_dev_control(HypervTestDev *dev, uint32_t ctl,
+                                      uint32_t vcpu_id, uint32_t sint)
+{
+    int i;
+    HvSintRoute *sint_route;
+
+    switch (ctl) {
+    case HV_TEST_DEV_SINT_ROUTE_CREATE:
+        i = alloc_sint_route_index(dev);
+        assert(i >= 0);
+        sint_route = kvm_hv_sint_route_create(vcpu_id, sint, NULL);
+        assert(sint_route);
+        dev->sint_route[i] = sint_route;
+        break;
+    case HV_TEST_DEV_SINT_ROUTE_DESTROY:
+        i = find_sint_route_index(dev, vcpu_id, sint);
+        assert(i >= 0);
+        sint_route = dev->sint_route[i];
+        kvm_hv_sint_route_destroy(sint_route);
+        free_sint_route_index(dev, i);
+        break;
+    case HV_TEST_DEV_SINT_ROUTE_SET_SINT:
+        i = find_sint_route_index(dev, vcpu_id, sint);
+        assert(i >= 0);
+        sint_route = dev->sint_route[i];
+        kvm_hv_sint_route_set_sint(sint_route);
+        break;
+    default:
+        break;
+    }
+}
+
+static void hv_test_dev_control(void *opaque, hwaddr addr, uint64_t data,
+                                uint32_t len)
+{
+    HypervTestDev *dev = HYPERV_TEST_DEV(opaque);
+    uint8_t ctl;
+
+    ctl = (data >> 16ULL) & 0xFF;
+    switch (ctl) {
+    case HV_TEST_DEV_SINT_ROUTE_CREATE:
+    case HV_TEST_DEV_SINT_ROUTE_DESTROY:
+    case HV_TEST_DEV_SINT_ROUTE_SET_SINT: {
+        uint8_t sint = data & 0xFF;
+        uint8_t vcpu_id = (data >> 8ULL) & 0xFF;
+        hv_synic_test_dev_control(dev, ctl, vcpu_id, sint);
+        break;
+    }
+    default:
+        break;
+    }
+}
+
+static const MemoryRegionOps synic_test_sint_ops = {
+    .write = hv_test_dev_control,
+    .valid.min_access_size = 4,
+    .valid.max_access_size = 4,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+static void hv_test_dev_realizefn(DeviceState *d, Error **errp)
+{
+    ISADevice *isa = ISA_DEVICE(d);
+    HypervTestDev *dev = HYPERV_TEST_DEV(d);
+    MemoryRegion *io = isa_address_space_io(isa);
+
+    memset(dev->sint_route, 0, sizeof(dev->sint_route));
+    memory_region_init_io(&dev->sint_control, OBJECT(dev),
+                          &synic_test_sint_ops, dev,
+                          "hyperv-testdev-ctl", 4);
+    memory_region_add_subregion(io, 0x3000, &dev->sint_control);
+}
+
+static void hv_test_dev_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    dc->realize = hv_test_dev_realizefn;
+}
+
+static const TypeInfo hv_test_dev_info = {
+    .name           = TYPE_HYPERV_TEST_DEV,
+    .parent         = TYPE_ISA_DEVICE,
+    .instance_size  = sizeof(HypervTestDev),
+    .class_init     = hv_test_dev_class_init,
+};
+
+static void hv_test_dev_register_types(void)
+{
+    type_register_static(&hv_test_dev_info);
+}
+type_init(hv_test_dev_register_types);

hw/misc/imx25_ccm.c

@@ -0,0 +1,341 @@
+/*
+ * IMX25 Clock Control Module
+ *
+ * Copyright (C) 2012 NICTA
+ * Updated by Jean-Christophe Dubois <jcd@tribudubois.net>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ * To get the timer frequencies right, we need to emulate at least part of
+ * the CCM.
+ */
+
+#include "hw/misc/imx25_ccm.h"
+
+#ifndef DEBUG_IMX25_CCM
+#define DEBUG_IMX25_CCM 0
+#endif
+
+#define DPRINTF(fmt, args...) \
+    do { \
+        if (DEBUG_IMX25_CCM) { \
+            fprintf(stderr, "[%s]%s: " fmt , TYPE_IMX25_CCM, \
+                                             __func__, ##args); \
+        } \
+    } while (0)
+
+static char const *imx25_ccm_reg_name(uint32_t reg)
+{
+    static char unknown[20];
+
+    switch (reg) {
+    case IMX25_CCM_MPCTL_REG:
+        return "mpctl";
+    case IMX25_CCM_UPCTL_REG:
+        return "upctl";
+    case IMX25_CCM_CCTL_REG:
+        return "cctl";
+    case IMX25_CCM_CGCR0_REG:
+        return "cgcr0";
+    case IMX25_CCM_CGCR1_REG:
+        return "cgcr1";
+    case IMX25_CCM_CGCR2_REG:
+        return "cgcr2";
+    case IMX25_CCM_PCDR0_REG:
+        return "pcdr0";
+    case IMX25_CCM_PCDR1_REG:
+        return "pcdr1";
+    case IMX25_CCM_PCDR2_REG:
+        return "pcdr2";
+    case IMX25_CCM_PCDR3_REG:
+        return "pcdr3";
+    case IMX25_CCM_RCSR_REG:
+        return "rcsr";
+    case IMX25_CCM_CRDR_REG:
+        return "crdr";
+    case IMX25_CCM_DCVR0_REG:
+        return "dcvr0";
+    case IMX25_CCM_DCVR1_REG:
+        return "dcvr1";
+    case IMX25_CCM_DCVR2_REG:
+        return "dcvr2";
+    case IMX25_CCM_DCVR3_REG:
+        return "dcvr3";
+    case IMX25_CCM_LTR0_REG:
+        return "ltr0";
+    case IMX25_CCM_LTR1_REG:
+        return "ltr1";
+    case IMX25_CCM_LTR2_REG:
+        return "ltr2";
+    case IMX25_CCM_LTR3_REG:
+        return "ltr3";
+    case IMX25_CCM_LTBR0_REG:
+        return "ltbr0";
+    case IMX25_CCM_LTBR1_REG:
+        return "ltbr1";
+    case IMX25_CCM_PMCR0_REG:
+        return "pmcr0";
+    case IMX25_CCM_PMCR1_REG:
+        return "pmcr1";
+    case IMX25_CCM_PMCR2_REG:
+        return "pmcr2";
+    case IMX25_CCM_MCR_REG:
+        return "mcr";
+    case IMX25_CCM_LPIMR0_REG:
+        return "lpimr0";
+    case IMX25_CCM_LPIMR1_REG:
+        return "lpimr1";
+    default:
+        sprintf(unknown, "[%d ?]", reg);
+        return unknown;
+    }
+}
+#define CKIH_FREQ 24000000 /* 24MHz crystal input */
+
+static const VMStateDescription vmstate_imx25_ccm = {
+    .name = TYPE_IMX25_CCM,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32_ARRAY(reg, IMX25CCMState, IMX25_CCM_MAX_REG),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static uint32_t imx25_ccm_get_mpll_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX25CCMState *s = IMX25_CCM(dev);
+
+    if (EXTRACT(s->reg[IMX25_CCM_CCTL_REG], MPLL_BYPASS)) {
+        freq = CKIH_FREQ;
+    } else {
+        freq = imx_ccm_calc_pll(s->reg[IMX25_CCM_MPCTL_REG], CKIH_FREQ);
+    }
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx25_ccm_get_upll_clk(IMXCCMState *dev)
+{
+    uint32_t freq = 0;
+    IMX25CCMState *s = IMX25_CCM(dev);
+
+    if (!EXTRACT(s->reg[IMX25_CCM_CCTL_REG], UPLL_DIS)) {
+        freq = imx_ccm_calc_pll(s->reg[IMX25_CCM_UPCTL_REG], CKIH_FREQ);
+    }
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx25_ccm_get_mcu_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX25CCMState *s = IMX25_CCM(dev);
+
+    freq = imx25_ccm_get_mpll_clk(dev);
+
+    if (EXTRACT(s->reg[IMX25_CCM_CCTL_REG], ARM_SRC)) {
+        freq = (freq * 3 / 4);
+    }
+
+    freq = freq / (1 + EXTRACT(s->reg[IMX25_CCM_CCTL_REG], ARM_CLK_DIV));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx25_ccm_get_ahb_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX25CCMState *s = IMX25_CCM(dev);
+
+    freq = imx25_ccm_get_mcu_clk(dev)
+           / (1 + EXTRACT(s->reg[IMX25_CCM_CCTL_REG], AHB_CLK_DIV));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx25_ccm_get_ipg_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+
+    freq = imx25_ccm_get_ahb_clk(dev) / 2;
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx25_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock)
+{
+    uint32_t freq = 0;
+    DPRINTF("Clock = %d)\n", clock);
+
+    switch (clock) {
+    case NOCLK:
+        break;
+    case CLK_MPLL:
+        freq = imx25_ccm_get_mpll_clk(dev);
+        break;
+    case CLK_UPLL:
+        freq = imx25_ccm_get_upll_clk(dev);
+        break;
+    case CLK_MCU:
+        freq = imx25_ccm_get_mcu_clk(dev);
+        break;
+    case CLK_AHB:
+        freq = imx25_ccm_get_ahb_clk(dev);
+        break;
+    case CLK_IPG:
+        freq = imx25_ccm_get_ipg_clk(dev);
+        break;
+    case CLK_32k:
+        freq = CKIL_FREQ;
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: unsupported clock %d\n",
+                      TYPE_IMX25_CCM, __func__, clock);
+        break;
+    }
+
+    DPRINTF("Clock = %d) = %d\n", clock, freq);
+
+    return freq;
+}
+
+static void imx25_ccm_reset(DeviceState *dev)
+{
+    IMX25CCMState *s = IMX25_CCM(dev);
+
+    DPRINTF("\n");
+
+    memset(s->reg, 0, IMX25_CCM_MAX_REG * sizeof(uint32_t));
+    s->reg[IMX25_CCM_MPCTL_REG] = 0x800b2c01;
+    s->reg[IMX25_CCM_UPCTL_REG] = 0x84042800;
+    /* 
+     * The value below gives:
+     * CPU = 133 MHz, AHB = 66,5 MHz, IPG = 33 MHz. 
+     */
+    s->reg[IMX25_CCM_CCTL_REG]  = 0xd0030000;
+    s->reg[IMX25_CCM_CGCR0_REG] = 0x028A0100;
+    s->reg[IMX25_CCM_CGCR1_REG] = 0x04008100;
+    s->reg[IMX25_CCM_CGCR2_REG] = 0x00000438;
+    s->reg[IMX25_CCM_PCDR0_REG] = 0x01010101;
+    s->reg[IMX25_CCM_PCDR1_REG] = 0x01010101;
+    s->reg[IMX25_CCM_PCDR2_REG] = 0x01010101;
+    s->reg[IMX25_CCM_PCDR3_REG] = 0x01010101;
+    s->reg[IMX25_CCM_PMCR0_REG] = 0x00A00000;
+    s->reg[IMX25_CCM_PMCR1_REG] = 0x0000A030;
+    s->reg[IMX25_CCM_PMCR2_REG] = 0x0000A030;
+    s->reg[IMX25_CCM_MCR_REG]   = 0x43000000;
+
+    /*
+     * default boot will change the reset values to allow:
+     * CPU = 399 MHz, AHB = 133 MHz, IPG = 66,5 MHz. 
+     * For some reason, this doesn't work. With the value below, linux
+     * detects a 88 MHz IPG CLK instead of 66,5 MHz.
+    s->reg[IMX25_CCM_CCTL_REG]  = 0x20032000;
+     */
+}
+
+static uint64_t imx25_ccm_read(void *opaque, hwaddr offset, unsigned size)
+{
+    uint32 value = 0;
+    IMX25CCMState *s = (IMX25CCMState *)opaque;
+
+    if (offset < 0x70) {
+        value = s->reg[offset >> 2];
+    } else {
+        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%"
+                      HWADDR_PRIx "\n", TYPE_IMX25_CCM, __func__, offset);
+    }
+
+    DPRINTF("reg[%s] => 0x%" PRIx32 "\n", imx25_ccm_reg_name(offset >> 2),
+            value);
+
+    return value;
+}
+
+static void imx25_ccm_write(void *opaque, hwaddr offset, uint64_t value,
+                            unsigned size)
+{
+    IMX25CCMState *s = (IMX25CCMState *)opaque;
+
+    DPRINTF("reg[%s] <= 0x%" PRIx32 "\n", imx25_ccm_reg_name(offset >> 2),
+            (uint32_t)value);
+
+    if (offset < 0x70) {
+        /*
+         * We will do a better implementation later. In particular some bits
+         * cannot be written to.
+         */
+        s->reg[offset >> 2] = value;
+    } else {
+        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%"
+                      HWADDR_PRIx "\n", TYPE_IMX25_CCM, __func__, offset);
+    }
+}
+
+static const struct MemoryRegionOps imx25_ccm_ops = {
+    .read = imx25_ccm_read,
+    .write = imx25_ccm_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        /*
+         * Our device would not work correctly if the guest was doing
+         * unaligned access. This might not be a limitation on the real
+         * device but in practice there is no reason for a guest to access
+         * this device unaligned.
+         */
+        .min_access_size = 4,
+        .max_access_size = 4,
+        .unaligned = false,
+    },
+};
+
+static void imx25_ccm_init(Object *obj)
+{
+    DeviceState *dev = DEVICE(obj);
+    SysBusDevice *sd = SYS_BUS_DEVICE(obj);
+    IMX25CCMState *s = IMX25_CCM(obj);
+
+    memory_region_init_io(&s->iomem, OBJECT(dev), &imx25_ccm_ops, s,
+                          TYPE_IMX25_CCM, 0x1000);
+    sysbus_init_mmio(sd, &s->iomem);
+}
+
+static void imx25_ccm_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
+
+    dc->reset = imx25_ccm_reset;
+    dc->vmsd = &vmstate_imx25_ccm;
+    dc->desc = "i.MX25 Clock Control Module";
+
+    ccm->get_clock_frequency = imx25_ccm_get_clock_frequency;
+}
+
+static const TypeInfo imx25_ccm_info = {
+    .name          = TYPE_IMX25_CCM,
+    .parent        = TYPE_IMX_CCM,
+    .instance_size = sizeof(IMX25CCMState),
+    .instance_init = imx25_ccm_init,
+    .class_init    = imx25_ccm_class_init,
+};
+
+static void imx25_ccm_register_types(void)
+{
+    type_register_static(&imx25_ccm_info);
+}
+
+type_init(imx25_ccm_register_types)

hw/misc/imx31_ccm.c

@@ -0,0 +1,392 @@
+/*
+ * IMX31 Clock Control Module
+ *
+ * Copyright (C) 2012 NICTA
+ * Updated by Jean-Christophe Dubois <jcd@tribudubois.net>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ * To get the timer frequencies right, we need to emulate at least part of
+ * the i.MX31 CCM.
+ */
+
+#include "hw/misc/imx31_ccm.h"
+
+#define CKIH_FREQ 26000000 /* 26MHz crystal input */
+
+#ifndef DEBUG_IMX31_CCM
+#define DEBUG_IMX31_CCM 0
+#endif
+
+#define DPRINTF(fmt, args...) \
+    do { \
+        if (DEBUG_IMX31_CCM) { \
+            fprintf(stderr, "[%s]%s: " fmt , TYPE_IMX31_CCM, \
+                                             __func__, ##args); \
+        } \
+    } while (0)
+
+static char const *imx31_ccm_reg_name(uint32_t reg)
+{
+    switch (reg) {
+    case 0:
+        return "CCMR";
+    case 1:
+        return "PDR0";
+    case 2:
+        return "PDR1";
+    case 3:
+        return "RCSR";
+    case 4:
+        return "MPCTL";
+    case 5:
+        return "UPCTL";
+    case 6:
+        return "SPCTL";
+    case 7:
+        return "COSR";
+    case 8:
+        return "CGR0";
+    case 9:
+        return "CGR1";
+    case 10:
+        return "CGR2";
+    case 11:
+        return "WIMR";
+    case 12:
+        return "LDC";
+    case 13:
+        return "DCVR0";
+    case 14:
+        return "DCVR1";
+    case 15:
+        return "DCVR2";
+    case 16:
+        return "DCVR3";
+    case 17:
+        return "LTR0";
+    case 18:
+        return "LTR1";
+    case 19:
+        return "LTR2";
+    case 20:
+        return "LTR3";
+    case 21:
+        return "LTBR0";
+    case 22:
+        return "LTBR1";
+    case 23:
+        return "PMCR0";
+    case 24:
+        return "PMCR1";
+    case 25:
+        return "PDR2";
+    default:
+        return "???";
+    }
+}
+
+static const VMStateDescription vmstate_imx31_ccm = {
+    .name = TYPE_IMX31_CCM,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(ccmr, IMX31CCMState),
+        VMSTATE_UINT32(pdr0, IMX31CCMState),
+        VMSTATE_UINT32(pdr1, IMX31CCMState),
+        VMSTATE_UINT32(mpctl, IMX31CCMState),
+        VMSTATE_UINT32(spctl, IMX31CCMState),
+        VMSTATE_UINT32_ARRAY(cgr, IMX31CCMState, 3),
+        VMSTATE_UINT32(pmcr0, IMX31CCMState),
+        VMSTATE_UINT32(pmcr1, IMX31CCMState),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static uint32_t imx31_ccm_get_pll_ref_clk(IMXCCMState *dev)
+{
+    uint32_t freq = 0;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    if ((s->ccmr & CCMR_PRCS) == 2) {
+        if (s->ccmr & CCMR_FPME) {
+            freq = CKIL_FREQ;
+            if (s->ccmr & CCMR_FPMF) {
+                freq *= 1024;
+            }
+        } 
+    } else {
+        freq = CKIH_FREQ;
+    }
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_mpll_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    freq = imx_ccm_calc_pll(s->mpctl, imx31_ccm_get_pll_ref_clk(dev));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_mcu_main_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    if ((s->ccmr & CCMR_MDS) || !(s->ccmr & CCMR_MPE)) {
+        freq = imx31_ccm_get_pll_ref_clk(dev);
+    } else {
+        freq = imx31_ccm_get_mpll_clk(dev);
+    }
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_mcu_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    freq = imx31_ccm_get_mcu_main_clk(dev) / (1 + EXTRACT(s->pdr0, MCU));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_hsp_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    freq = imx31_ccm_get_mcu_main_clk(dev) / (1 + EXTRACT(s->pdr0, HSP));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_hclk_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    freq = imx31_ccm_get_mcu_main_clk(dev) / (1 + EXTRACT(s->pdr0, MAX));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_ipg_clk(IMXCCMState *dev)
+{
+    uint32_t freq;
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    freq = imx31_ccm_get_hclk_clk(dev) / (1 + EXTRACT(s->pdr0, IPG));
+
+    DPRINTF("freq = %d\n", freq);
+
+    return freq;
+}
+
+static uint32_t imx31_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock)
+{
+    uint32_t freq = 0;
+
+    switch (clock) {
+    case NOCLK:
+        break;
+    case CLK_MCU:
+        freq = imx31_ccm_get_mcu_clk(dev);
+        break;
+    case CLK_HSP:
+        freq = imx31_ccm_get_hsp_clk(dev);
+        break;
+    case CLK_IPG:
+        freq = imx31_ccm_get_ipg_clk(dev);
+        break;
+    case CLK_32k:
+        freq = CKIL_FREQ;
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: unsupported clock %d\n",
+                      TYPE_IMX31_CCM, __func__, clock);
+        break;
+    }
+
+    DPRINTF("Clock = %d) = %d\n", clock, freq);
+
+    return freq;
+}
+
+static void imx31_ccm_reset(DeviceState *dev)
+{
+    IMX31CCMState *s = IMX31_CCM(dev);
+
+    DPRINTF("()\n");
+
+    s->ccmr   = 0x074b0b7d;
+    s->pdr0   = 0xff870b48;
+    s->pdr1   = 0x49fcfe7f;
+    s->mpctl  = 0x04001800;
+    s->cgr[0] = s->cgr[1] = s->cgr[2] = 0xffffffff;
+    s->spctl  = 0x04043001;
+    s->pmcr0  = 0x80209828;
+    s->pmcr1  = 0x00aa0000;
+}
+
+static uint64_t imx31_ccm_read(void *opaque, hwaddr offset, unsigned size)
+{
+    uint32 value = 0;
+    IMX31CCMState *s = (IMX31CCMState *)opaque;
+
+    switch (offset >> 2) {
+    case 0: /* CCMR */
+        value = s->ccmr;
+        break;
+    case 1:
+        value = s->pdr0;
+        break;
+    case 2:
+        value = s->pdr1;
+        break;
+    case 4:
+        value = s->mpctl;
+        break;
+    case 6:
+        value = s->spctl;
+        break;
+    case 8:
+        value = s->cgr[0];
+        break;
+    case 9:
+        value = s->cgr[1];
+        break;
+    case 10:
+        value = s->cgr[2];
+        break;
+    case 18: /* LTR1 */
+        value = 0x00004040;
+        break;
+    case 23:
+        value = s->pmcr0;
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%"
+                      HWADDR_PRIx "\n", TYPE_IMX31_CCM, __func__, offset);
+        break;
+    }
+
+    DPRINTF("reg[%s] => 0x%" PRIx32 "\n", imx31_ccm_reg_name(offset >> 2),
+            value);
+
+    return (uint64_t)value;
+}
+
+static void imx31_ccm_write(void *opaque, hwaddr offset, uint64_t value,
+                            unsigned size)
+{
+    IMX31CCMState *s = (IMX31CCMState *)opaque;
+
+    DPRINTF("reg[%s] <= 0x%" PRIx32 "\n", imx31_ccm_reg_name(offset >> 2),
+            (uint32_t)value);
+
+    switch (offset >> 2) {
+    case 0:
+        s->ccmr = CCMR_FPMF | (value & 0x3b6fdfff);
+        break;
+    case 1:
+        s->pdr0 = value & 0xff9f3fff;
+        break;
+    case 2:
+        s->pdr1 = value;
+        break;
+    case 4:
+        s->mpctl = value & 0xbfff3fff;
+        break;
+    case 6:
+        s->spctl = value & 0xbfff3fff;
+        break;
+    case 8:
+        s->cgr[0] = value;
+        break;
+    case 9:
+        s->cgr[1] = value;
+        break;
+    case 10:
+        s->cgr[2] = value;
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%"
+                      HWADDR_PRIx "\n", TYPE_IMX31_CCM, __func__, offset);
+        break;
+    }
+}
+
+static const struct MemoryRegionOps imx31_ccm_ops = {
+    .read = imx31_ccm_read,
+    .write = imx31_ccm_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        /*
+         * Our device would not work correctly if the guest was doing
+         * unaligned access. This might not be a limitation on the real
+         * device but in practice there is no reason for a guest to access
+         * this device unaligned.
+         */
+        .min_access_size = 4,
+        .max_access_size = 4,
+        .unaligned = false,
+    },
+
+};
+
+static void imx31_ccm_init(Object *obj)
+{
+    DeviceState *dev = DEVICE(obj);
+    SysBusDevice *sd = SYS_BUS_DEVICE(obj);
+    IMX31CCMState *s = IMX31_CCM(obj);
+
+    memory_region_init_io(&s->iomem, OBJECT(dev), &imx31_ccm_ops, s,
+                          TYPE_IMX31_CCM, 0x1000);
+    sysbus_init_mmio(sd, &s->iomem);
+}
+
+static void imx31_ccm_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc  = DEVICE_CLASS(klass);
+    IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
+
+    dc->reset = imx31_ccm_reset;
+    dc->vmsd  = &vmstate_imx31_ccm;
+    dc->desc  = "i.MX31 Clock Control Module";
+
+    ccm->get_clock_frequency = imx31_ccm_get_clock_frequency;
+}
+
+static const TypeInfo imx31_ccm_info = {
+    .name          = TYPE_IMX31_CCM,
+    .parent        = TYPE_IMX_CCM,
+    .instance_size = sizeof(IMX31CCMState),
+    .instance_init = imx31_ccm_init,
+    .class_init    = imx31_ccm_class_init,
+};
+
+static void imx31_ccm_register_types(void)
+{
+    type_register_static(&imx31_ccm_info);
+}
+
+type_init(imx31_ccm_register_types)

hw/misc/imx_ccm.c

@@ -7,15 +7,12 @@
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
  *
- * To get the timer frequencies right, we need to emulate at least part of
- * the CCM.
+ * This is an abstract base class used to get a common interface to
+ * retrieve the CCM frequencies from the various i.MX SOC.
  */
 
 #include "hw/misc/imx_ccm.h"
 
-#define CKIH_FREQ 26000000 /* 26MHz crystal input */
-#define CKIL_FREQ    32768 /* nominal 32khz clock */
-
 #ifndef DEBUG_IMX_CCM
 #define DEBUG_IMX_CCM 0
 #endif
@@ -28,51 +25,27 @@
         } \
     } while (0)
 
-static int imx_ccm_post_load(void *opaque, int version_id);
 
-static const VMStateDescription vmstate_imx_ccm = {
-    .name = TYPE_IMX_CCM,
-    .version_id = 1,
-    .minimum_version_id = 1,
-    .fields = (VMStateField[]) {
-        VMSTATE_UINT32(ccmr, IMXCCMState),
-        VMSTATE_UINT32(pdr0, IMXCCMState),
-        VMSTATE_UINT32(pdr1, IMXCCMState),
-        VMSTATE_UINT32(mpctl, IMXCCMState),
-        VMSTATE_UINT32(spctl, IMXCCMState),
-        VMSTATE_UINT32_ARRAY(cgr, IMXCCMState, 3),
-        VMSTATE_UINT32(pmcr0, IMXCCMState),
-        VMSTATE_UINT32(pmcr1, IMXCCMState),
-        VMSTATE_UINT32(pll_refclk_freq, IMXCCMState),
-        VMSTATE_END_OF_LIST()
-    },
-    .post_load = imx_ccm_post_load,
-};
-
-uint32_t imx_clock_frequency(DeviceState *dev, IMXClk clock)
+uint32_t imx_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock)
 {
-    IMXCCMState *s = IMX_CCM(dev);
+    uint32_t freq = 0;
+    IMXCCMClass *klass = IMX_GET_CLASS(dev);
 
-    switch (clock) {
-    case NOCLK:
-        return 0;
-    case MCU:
-        return s->mcu_clk_freq;
-    case HSP:
-        return s->hsp_clk_freq;
-    case IPG:
-        return s->ipg_clk_freq;
-    case CLK_32k:
-        return CKIL_FREQ;
+    if (klass->get_clock_frequency) {
+        freq = klass->get_clock_frequency(dev, clock);
     }
-    return 0;
+
+    DPRINTF("(clock = %d) = %d\n", clock, freq);
+
+    return freq;
 }
 
 /*
  * Calculate PLL output frequency
  */
-static uint32_t calc_pll(uint32_t pllreg, uint32_t base_freq)
+uint32_t imx_ccm_calc_pll(uint32_t pllreg, uint32_t base_freq)
 {
+    int32_t freq;
     int32_t mfn = MFN(pllreg);  /* Numerator */
     uint32_t mfi = MFI(pllreg); /* Integer part */
     uint32_t mfd = 1 + MFD(pllreg); /* Denominator */
@@ -81,186 +54,26 @@ static uint32_t calc_pll(uint32_t pllreg, uint32_t base_freq)
     if (mfi < 5) {
         mfi = 5;
     }
+
     /* mfn is 10-bit signed twos-complement */
     mfn <<= 32 - 10;
     mfn >>= 32 - 10;
 
-    return ((2 * (base_freq >> 10) * (mfi * mfd + mfn)) /
+    freq = ((2 * (base_freq >> 10) * (mfi * mfd + mfn)) /
             (mfd * pd)) << 10;
-}
 
-static void update_clocks(IMXCCMState *s)
-{
-    /*
-     * If we ever emulate more clocks, this should switch to a data-driven
-     * approach
-     */
+    DPRINTF("(pllreg = 0x%08x, base_freq = %d) = %d\n", pllreg, base_freq,
+            freq);
 
-    if ((s->ccmr & CCMR_PRCS) == 2) {
-        s->pll_refclk_freq = CKIL_FREQ * 1024;
-    } else {
-        s->pll_refclk_freq = CKIH_FREQ;
-    }
-
-    /* ipg_clk_arm aka MCU clock */
-    if ((s->ccmr & CCMR_MDS) || !(s->ccmr & CCMR_MPE)) {
-        s->mcu_clk_freq = s->pll_refclk_freq;
-    } else {
-        s->mcu_clk_freq = calc_pll(s->mpctl, s->pll_refclk_freq);
-    }
-
-    /* High-speed clock */
-    s->hsp_clk_freq = s->mcu_clk_freq / (1 + EXTRACT(s->pdr0, HSP));
-    s->ipg_clk_freq = s->hsp_clk_freq / (1 + EXTRACT(s->pdr0, IPG));
-
-    DPRINTF("mcu %uMHz, HSP %uMHz, IPG %uHz\n",
-            s->mcu_clk_freq / 1000000,
-            s->hsp_clk_freq / 1000000,
-            s->ipg_clk_freq);
-}
-
-static void imx_ccm_reset(DeviceState *dev)
-{
-    IMXCCMState *s = IMX_CCM(dev);
-
-    s->ccmr = 0x074b0b7b;
-    s->pdr0 = 0xff870b48;
-    s->pdr1 = 0x49fcfe7f;
-    s->mpctl = PLL_PD(1) | PLL_MFD(0) | PLL_MFI(6) | PLL_MFN(0);
-    s->cgr[0] = s->cgr[1] = s->cgr[2] = 0xffffffff;
-    s->spctl = PLL_PD(1) | PLL_MFD(4) | PLL_MFI(0xc) | PLL_MFN(1);
-    s->pmcr0 = 0x80209828;
-
-    update_clocks(s);
-}
-
-static uint64_t imx_ccm_read(void *opaque, hwaddr offset,
-                                unsigned size)
-{
-    IMXCCMState *s = (IMXCCMState *)opaque;
-
-    DPRINTF("(offset=0x%" HWADDR_PRIx ")\n", offset);
-
-    switch (offset >> 2) {
-    case 0: /* CCMR */
-        DPRINTF(" ccmr = 0x%x\n", s->ccmr);
-        return s->ccmr;
-    case 1:
-        DPRINTF(" pdr0 = 0x%x\n", s->pdr0);
-        return s->pdr0;
-    case 2:
-        DPRINTF(" pdr1 = 0x%x\n", s->pdr1);
-        return s->pdr1;
-    case 4:
-        DPRINTF(" mpctl = 0x%x\n", s->mpctl);
-        return s->mpctl;
-    case 6:
-        DPRINTF(" spctl = 0x%x\n", s->spctl);
-        return s->spctl;
-    case 8:
-        DPRINTF(" cgr0 = 0x%x\n", s->cgr[0]);
-        return s->cgr[0];
-    case 9:
-        DPRINTF(" cgr1 = 0x%x\n", s->cgr[1]);
-        return s->cgr[1];
-    case 10:
-        DPRINTF(" cgr2 = 0x%x\n", s->cgr[2]);
-        return s->cgr[2];
-    case 18: /* LTR1 */
-        return 0x00004040;
-    case 23:
-        DPRINTF(" pcmr0 = 0x%x\n", s->pmcr0);
-        return s->pmcr0;
-    default:
-        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%"
-                      HWADDR_PRIx "\n", TYPE_IMX_CCM, __func__, offset);
-        return 0;
-    }
-}
-
-static void imx_ccm_write(void *opaque, hwaddr offset,
-                          uint64_t value, unsigned size)
-{
-    IMXCCMState *s = (IMXCCMState *)opaque;
-
-    DPRINTF("(offset=0x%" HWADDR_PRIx ", value = 0x%x)\n",
-            offset, (unsigned int)value);
-
-    switch (offset >> 2) {
-    case 0:
-        s->ccmr = CCMR_FPMF | (value & 0x3b6fdfff);
-        break;
-    case 1:
-        s->pdr0 = value & 0xff9f3fff;
-        break;
-    case 2:
-        s->pdr1 = value;
-        break;
-    case 4:
-        s->mpctl = value & 0xbfff3fff;
-        break;
-    case 6:
-        s->spctl = value & 0xbfff3fff;
-        break;
-    case 8:
-        s->cgr[0] = value;
-        return;
-    case 9:
-        s->cgr[1] = value;
-        return;
-    case 10:
-        s->cgr[2] = value;
-        return;
-
-    default:
-        qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%"
-                      HWADDR_PRIx "\n", TYPE_IMX_CCM, __func__, offset);
-        return;
-    }
-    update_clocks(s);
-}
-
-static const struct MemoryRegionOps imx_ccm_ops = {
-    .read = imx_ccm_read,
-    .write = imx_ccm_write,
-    .endianness = DEVICE_NATIVE_ENDIAN,
-};
-
-static int imx_ccm_init(SysBusDevice *dev)
-{
-    IMXCCMState *s = IMX_CCM(dev);
-
-    memory_region_init_io(&s->iomem, OBJECT(dev), &imx_ccm_ops, s,
-                          TYPE_IMX_CCM, 0x1000);
-    sysbus_init_mmio(dev, &s->iomem);
-
-    return 0;
-}
-
-static int imx_ccm_post_load(void *opaque, int version_id)
-{
-    IMXCCMState *s = (IMXCCMState *)opaque;
-
-    update_clocks(s);
-    return 0;
-}
-
-static void imx_ccm_class_init(ObjectClass *klass, void *data)
-{
-    DeviceClass *dc = DEVICE_CLASS(klass);
-    SysBusDeviceClass *sbc = SYS_BUS_DEVICE_CLASS(klass);
-
-    sbc->init = imx_ccm_init;
-    dc->reset = imx_ccm_reset;
-    dc->vmsd = &vmstate_imx_ccm;
-    dc->desc = "i.MX Clock Control Module";
+    return freq;
 }
 
 static const TypeInfo imx_ccm_info = {
     .name          = TYPE_IMX_CCM,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(IMXCCMState),
-    .class_init = imx_ccm_class_init,
+    .class_size    = sizeof(IMXCCMClass),
+    .abstract      = true,
 };
 
 static void imx_ccm_register_types(void)

hw/nvram/fw_cfg.c

@@ -252,7 +252,8 @@ static void fw_cfg_write(FWCfgState *s, uint8_t value)
 
 static int fw_cfg_select(FWCfgState *s, uint16_t key)
 {
-    int ret;
+    int arch, ret;
+    FWCfgEntry *e;
 
     s->cur_offset = 0;
     if ((key & FW_CFG_ENTRY_MASK) >= FW_CFG_MAX_ENTRY) {
@@ -261,41 +262,45 @@ static int fw_cfg_select(FWCfgState *s, uint16_t key)
     } else {
         s->cur_entry = key;
         ret = 1;
+        /* entry successfully selected, now run callback if present */
+        arch = !!(key & FW_CFG_ARCH_LOCAL);
+        e = &s->entries[arch][key & FW_CFG_ENTRY_MASK];
+        if (e->read_callback) {
+            e->read_callback(e->callback_opaque);
+        }
     }
 
     trace_fw_cfg_select(s, key, ret);
     return ret;
 }
 
-static uint8_t fw_cfg_read(FWCfgState *s)
-{
-    int arch = !!(s->cur_entry & FW_CFG_ARCH_LOCAL);
-    FWCfgEntry *e = &s->entries[arch][s->cur_entry & FW_CFG_ENTRY_MASK];
-    uint8_t ret;
-
-    if (s->cur_entry == FW_CFG_INVALID || !e->data || s->cur_offset >= e->len)
-        ret = 0;
-    else {
-        if (e->read_callback) {
-            e->read_callback(e->callback_opaque, s->cur_offset);
-        }
-        ret = e->data[s->cur_offset++];
-    }
-
-    trace_fw_cfg_read(s, ret);
-    return ret;
-}
-
-static uint64_t fw_cfg_data_mem_read(void *opaque, hwaddr addr,
-                                     unsigned size)
+static uint64_t fw_cfg_data_read(void *opaque, hwaddr addr, unsigned size)
 {
     FWCfgState *s = opaque;
+    int arch = !!(s->cur_entry & FW_CFG_ARCH_LOCAL);
+    FWCfgEntry *e = (s->cur_entry == FW_CFG_INVALID) ? NULL :
+                    &s->entries[arch][s->cur_entry & FW_CFG_ENTRY_MASK];
     uint64_t value = 0;
-    unsigned i;
 
-    for (i = 0; i < size; ++i) {
-        value = (value << 8) | fw_cfg_read(s);
+    assert(size > 0 && size <= sizeof(value));
+    if (s->cur_entry != FW_CFG_INVALID && e->data && s->cur_offset < e->len) {
+        /* The least significant 'size' bytes of the return value are
+         * expected to contain a string preserving portion of the item
+         * data, padded with zeros on the right in case we run out early.
+         * In technical terms, we're composing the host-endian representation
+         * of the big endian interpretation of the fw_cfg string.
+         */
+        do {
+            value = (value << 8) | e->data[s->cur_offset++];
+        } while (--size && s->cur_offset < e->len);
+        /* If size is still not zero, we *did* run out early, so continue
+         * left-shifting, to add the appropriate number of padding zeros
+         * on the right.
+         */
+        value <<= 8 * size;
     }
+
+    trace_fw_cfg_read(s, value);
     return value;
 }
 
@@ -338,7 +343,8 @@ static void fw_cfg_dma_transfer(FWCfgState *s)
     }
 
     arch = !!(s->cur_entry & FW_CFG_ARCH_LOCAL);
-    e = &s->entries[arch][s->cur_entry & FW_CFG_ENTRY_MASK];
+    e = (s->cur_entry == FW_CFG_INVALID) ? NULL :
+        &s->entries[arch][s->cur_entry & FW_CFG_ENTRY_MASK];
 
     if (dma.control & FW_CFG_DMA_CTL_READ) {
         read = 1;
@@ -371,10 +377,6 @@ static void fw_cfg_dma_transfer(FWCfgState *s)
                 len = (e->len - s->cur_offset);
             }
 
-            if (e->read_callback) {
-                e->read_callback(e->callback_opaque, s->cur_offset);
-            }
-
             /* If the access is not a read access, it will be a skip access,
              * tested before.
              */
@@ -451,12 +453,6 @@ static bool fw_cfg_ctl_mem_valid(void *opaque, hwaddr addr,
     return is_write && size == 2;
 }
 
-static uint64_t fw_cfg_comb_read(void *opaque, hwaddr addr,
-                                 unsigned size)
-{
-    return fw_cfg_read(opaque);
-}
-
 static void fw_cfg_comb_write(void *opaque, hwaddr addr,
                               uint64_t value, unsigned size)
 {
@@ -483,7 +479,7 @@ static const MemoryRegionOps fw_cfg_ctl_mem_ops = {
 };
 
 static const MemoryRegionOps fw_cfg_data_mem_ops = {
-    .read = fw_cfg_data_mem_read,
+    .read = fw_cfg_data_read,
     .write = fw_cfg_data_mem_write,
     .endianness = DEVICE_BIG_ENDIAN,
     .valid = {
@@ -494,7 +490,7 @@ static const MemoryRegionOps fw_cfg_data_mem_ops = {
 };
 
 static const MemoryRegionOps fw_cfg_comb_mem_ops = {
-    .read = fw_cfg_comb_read,
+    .read = fw_cfg_data_read,
     .write = fw_cfg_comb_write,
     .endianness = DEVICE_LITTLE_ENDIAN,
     .valid.accepts = fw_cfg_comb_valid,
@@ -513,7 +509,8 @@ static void fw_cfg_reset(DeviceState *d)
 {
     FWCfgState *s = FW_CFG(d);
 
-    fw_cfg_select(s, 0);
+    /* we never register a read callback for FW_CFG_SIGNATURE */
+    fw_cfg_select(s, FW_CFG_SIGNATURE);
 }
 
 /* Save restore 32 bit int as uint16_t

hw/pci-bridge/pci_expander_bridge.c

@@ -23,6 +23,9 @@
 #define TYPE_PXB_BUS "pxb-bus"
 #define PXB_BUS(obj) OBJECT_CHECK(PXBBus, (obj), TYPE_PXB_BUS)
 
+#define TYPE_PXB_PCIE_BUS "pxb-pcie-bus"
+#define PXB_PCIE_BUS(obj) OBJECT_CHECK(PXBBus, (obj), TYPE_PXB_PCIE_BUS)
+
 typedef struct PXBBus {
     /*< private >*/
     PCIBus parent_obj;
@@ -34,6 +37,9 @@ typedef struct PXBBus {
 #define TYPE_PXB_DEVICE "pxb"
 #define PXB_DEV(obj) OBJECT_CHECK(PXBDev, (obj), TYPE_PXB_DEVICE)
 
+#define TYPE_PXB_PCIE_DEVICE "pxb-pcie"
+#define PXB_PCIE_DEV(obj) OBJECT_CHECK(PXBDev, (obj), TYPE_PXB_PCIE_DEVICE)
+
 typedef struct PXBDev {
     /*< private >*/
     PCIDevice parent_obj;
@@ -43,13 +49,18 @@ typedef struct PXBDev {
     uint16_t numa_node;
 } PXBDev;
 
+static PXBDev *convert_to_pxb(PCIDevice *dev)
+{
+    return pci_bus_is_express(dev->bus) ? PXB_PCIE_DEV(dev) : PXB_DEV(dev);
+}
+
 static GList *pxb_dev_list;
 
 #define TYPE_PXB_HOST "pxb-host"
 
 static int pxb_bus_num(PCIBus *bus)
 {
-    PXBDev *pxb = PXB_DEV(bus->parent_dev);
+    PXBDev *pxb = convert_to_pxb(bus->parent_dev);
 
     return pxb->bus_nr;
 }
@@ -61,7 +72,7 @@ static bool pxb_is_root(PCIBus *bus)
 
 static uint16_t pxb_bus_numa_node(PCIBus *bus)
 {
-    PXBDev *pxb = PXB_DEV(bus->parent_dev);
+    PXBDev *pxb = convert_to_pxb(bus->parent_dev);
 
     return pxb->numa_node;
 }
@@ -82,10 +93,18 @@ static const TypeInfo pxb_bus_info = {
     .class_init    = pxb_bus_class_init,
 };
 
+static const TypeInfo pxb_pcie_bus_info = {
+    .name          = TYPE_PXB_PCIE_BUS,
+    .parent        = TYPE_PCIE_BUS,
+    .instance_size = sizeof(PXBBus),
+    .class_init    = pxb_bus_class_init,
+};
+
 static const char *pxb_host_root_bus_path(PCIHostState *host_bridge,
                                           PCIBus *rootbus)
 {
-    PXBBus *bus = PXB_BUS(rootbus);
+    PXBBus *bus = pci_bus_is_express(rootbus) ?
+                  PXB_PCIE_BUS(rootbus) : PXB_BUS(rootbus);
 
     snprintf(bus->bus_path, 8, "0000:%02x", pxb_bus_num(rootbus));
     return bus->bus_path;
@@ -103,7 +122,7 @@ static char *pxb_host_ofw_unit_address(const SysBusDevice *dev)
 
     pxb_host = PCI_HOST_BRIDGE(dev);
     pxb_bus = pxb_host->bus;
-    pxb_dev = PXB_DEV(pxb_bus->parent_dev);
+    pxb_dev = convert_to_pxb(pxb_bus->parent_dev);
     position = g_list_index(pxb_dev_list, pxb_dev);
     assert(position >= 0);
 
@@ -193,10 +212,10 @@ static gint pxb_compare(gconstpointer a, gconstpointer b)
            0;
 }
 
-static int pxb_dev_initfn(PCIDevice *dev)
+static int pxb_dev_init_common(PCIDevice *dev, bool pcie)
 {
-    PXBDev *pxb = PXB_DEV(dev);
-    DeviceState *ds, *bds;
+    PXBDev *pxb = convert_to_pxb(dev);
+    DeviceState *ds, *bds = NULL;
     PCIBus *bus;
     const char *dev_name = NULL;
 
@@ -211,18 +230,21 @@ static int pxb_dev_initfn(PCIDevice *dev)
     }
 
     ds = qdev_create(NULL, TYPE_PXB_HOST);
+    if (pcie) {
+        bus = pci_bus_new(ds, dev_name, NULL, NULL, 0, TYPE_PXB_PCIE_BUS);
+    } else {
         bus = pci_bus_new(ds, "pxb-internal", NULL, NULL, 0, TYPE_PXB_BUS);
+        bds = qdev_create(BUS(bus), "pci-bridge");
+        bds->id = dev_name;
+        qdev_prop_set_uint8(bds, PCI_BRIDGE_DEV_PROP_CHASSIS_NR, pxb->bus_nr);
+        qdev_prop_set_bit(bds, PCI_BRIDGE_DEV_PROP_SHPC, false);
+    }
 
     bus->parent_dev = dev;
     bus->address_space_mem = dev->bus->address_space_mem;
     bus->address_space_io = dev->bus->address_space_io;
     bus->map_irq = pxb_map_irq_fn;
 
-    bds = qdev_create(BUS(bus), "pci-bridge");
-    bds->id = dev_name;
-    qdev_prop_set_uint8(bds, PCI_BRIDGE_DEV_PROP_CHASSIS_NR, pxb->bus_nr);
-    qdev_prop_set_bit(bds, PCI_BRIDGE_DEV_PROP_SHPC, false);
-
     PCI_HOST_BRIDGE(ds)->bus = bus;
 
     if (pxb_register_bus(dev, bus)) {
@@ -230,7 +252,9 @@ static int pxb_dev_initfn(PCIDevice *dev)
     }
 
     qdev_init_nofail(ds);
+    if (bds) {
         qdev_init_nofail(bds);
+    }
 
     pci_word_test_and_set_mask(dev->config + PCI_STATUS,
                                PCI_STATUS_66MHZ | PCI_STATUS_FAST_BACK);
@@ -240,9 +264,19 @@ static int pxb_dev_initfn(PCIDevice *dev)
     return 0;
 }
 
+static int pxb_dev_initfn(PCIDevice *dev)
+{
+    if (pci_bus_is_express(dev->bus)) {
+        error_report("pxb devices cannot reside on a PCIe bus!");
+        return -EINVAL;
+    }
+
+    return pxb_dev_init_common(dev, false);
+}
+
 static void pxb_dev_exitfn(PCIDevice *pci_dev)
 {
-    PXBDev *pxb = PXB_DEV(pci_dev);
+    PXBDev *pxb = convert_to_pxb(pci_dev);
 
     pxb_dev_list = g_list_remove(pxb_dev_list, pxb);
 }
@@ -276,11 +310,45 @@ static const TypeInfo pxb_dev_info = {
     .class_init    = pxb_dev_class_init,
 };
 
+static int pxb_pcie_dev_initfn(PCIDevice *dev)
+{
+    if (!pci_bus_is_express(dev->bus)) {
+        error_report("pxb-pcie devices cannot reside on a PCI bus!");
+        return -EINVAL;
+    }
+
+    return pxb_dev_init_common(dev, true);
+}
+
+static void pxb_pcie_dev_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->init = pxb_pcie_dev_initfn;
+    k->exit = pxb_dev_exitfn;
+    k->vendor_id = PCI_VENDOR_ID_REDHAT;
+    k->device_id = PCI_DEVICE_ID_REDHAT_PXB_PCIE;
+    k->class_id = PCI_CLASS_BRIDGE_HOST;
+
+    dc->desc = "PCI Express Expander Bridge";
+    dc->props = pxb_dev_properties;
+}
+
+static const TypeInfo pxb_pcie_dev_info = {
+    .name          = TYPE_PXB_PCIE_DEVICE,
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PXBDev),
+    .class_init    = pxb_pcie_dev_class_init,
+};
+
 static void pxb_register_types(void)
 {
     type_register_static(&pxb_bus_info);
+    type_register_static(&pxb_pcie_bus_info);
     type_register_static(&pxb_host_info);
     type_register_static(&pxb_dev_info);
+    type_register_static(&pxb_pcie_dev_info);
 }
 
 type_init(pxb_register_types)

hw/scsi/scsi-bus.c

@@ -1759,9 +1759,6 @@ void scsi_req_cancel_async(SCSIRequest *req, Notifier *notifier)
     if (notifier) {
         notifier_list_add(&req->cancel_notifiers, notifier);
     }
-    if (req->io_canceled) {
-        return;
-    }
     scsi_req_ref(req);
     scsi_req_dequeue(req);
     req->io_canceled = true;
@@ -1841,11 +1838,13 @@ void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense)
 {
     SCSIRequest *req;
 
+    aio_context_acquire(blk_get_aio_context(sdev->conf.blk));
     while (!QTAILQ_EMPTY(&sdev->requests)) {
         req = QTAILQ_FIRST(&sdev->requests);
-        scsi_req_cancel(req);
+        scsi_req_cancel_async(req, NULL);
     }
-
+    blk_drain(sdev->conf.blk);
+    aio_context_release(blk_get_aio_context(sdev->conf.blk));
     scsi_device_set_ua(sdev, sense);
 }
 

hw/scsi/vmw_pvscsi.c

@@ -32,7 +32,6 @@
 #include "trace.h"
 
 
-#define PVSCSI_MSI_OFFSET        (0x50)
 #define PVSCSI_USE_64BIT         (true)
 #define PVSCSI_PER_VECTOR_MASK   (false)
 
@@ -49,9 +48,33 @@
     (stl_le_pci_dma(&container_of(m, PVSCSIState, rings)->parent_obj, \
                  (m)->rs_pa + offsetof(struct PVSCSIRingsState, field), val))
 
+typedef struct PVSCSIClass {
+    PCIDeviceClass parent_class;
+    DeviceRealize parent_dc_realize;
+} PVSCSIClass;
+
 #define TYPE_PVSCSI "pvscsi"
 #define PVSCSI(obj) OBJECT_CHECK(PVSCSIState, (obj), TYPE_PVSCSI)
 
+#define PVSCSI_DEVICE_CLASS(klass) \
+    OBJECT_CLASS_CHECK(PVSCSIClass, (klass), TYPE_PVSCSI)
+#define PVSCSI_DEVICE_GET_CLASS(obj) \
+    OBJECT_GET_CLASS(PVSCSIClass, (obj), TYPE_PVSCSI)
+
+/* Compatability flags for migration */
+#define PVSCSI_COMPAT_OLD_PCI_CONFIGURATION_BIT 0
+#define PVSCSI_COMPAT_OLD_PCI_CONFIGURATION \
+    (1 << PVSCSI_COMPAT_OLD_PCI_CONFIGURATION_BIT)
+#define PVSCSI_COMPAT_DISABLE_PCIE_BIT 1
+#define PVSCSI_COMPAT_DISABLE_PCIE \
+    (1 << PVSCSI_COMPAT_DISABLE_PCIE_BIT)
+
+#define PVSCSI_USE_OLD_PCI_CONFIGURATION(s) \
+    ((s)->compat_flags & PVSCSI_COMPAT_OLD_PCI_CONFIGURATION)
+#define PVSCSI_MSI_OFFSET(s) \
+    (PVSCSI_USE_OLD_PCI_CONFIGURATION(s) ? 0x50 : 0x7c)
+#define PVSCSI_EXP_EP_OFFSET (0x40)
+
 typedef struct PVSCSIRingInfo {
     uint64_t            rs_pa;
     uint32_t            txr_len_mask;
@@ -100,6 +123,8 @@ typedef struct {
 
     PVSCSIRingInfo rings;                /* Data transfer rings manager      */
     uint32_t resetting;                  /* Reset in progress                */
+
+    uint32_t compat_flags;
 } PVSCSIState;
 
 typedef struct PVSCSIRequest {
@@ -1019,7 +1044,7 @@ pvscsi_init_msi(PVSCSIState *s)
     int res;
     PCIDevice *d = PCI_DEVICE(s);
 
-    res = msi_init(d, PVSCSI_MSI_OFFSET, PVSCSI_MSIX_NUM_VECTORS,
+    res = msi_init(d, PVSCSI_MSI_OFFSET(s), PVSCSI_MSIX_NUM_VECTORS,
                    PVSCSI_USE_64BIT, PVSCSI_PER_VECTOR_MASK);
     if (res < 0) {
         trace_pvscsi_init_msi_fail(res);
@@ -1069,9 +1094,16 @@ pvscsi_init(PCIDevice *pci_dev)
 
     trace_pvscsi_state("init");
 
-    /* PCI subsystem ID */
-    pci_dev->config[PCI_SUBSYSTEM_ID] = 0x00;
-    pci_dev->config[PCI_SUBSYSTEM_ID + 1] = 0x10;
+    /* PCI subsystem ID, subsystem vendor ID, revision */
+    if (PVSCSI_USE_OLD_PCI_CONFIGURATION(s)) {
+        pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID, 0x1000);
+    } else {
+        pci_set_word(pci_dev->config + PCI_SUBSYSTEM_VENDOR_ID,
+                     PCI_VENDOR_ID_VMWARE);
+        pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID,
+                     PCI_DEVICE_ID_VMWARE_PVSCSI);
+        pci_config_set_revision(pci_dev->config, 0x2);
+    }
 
     /* PCI latency timer = 255 */
     pci_dev->config[PCI_LATENCY_TIMER] = 0xff;
@@ -1085,6 +1117,10 @@ pvscsi_init(PCIDevice *pci_dev)
 
     pvscsi_init_msi(s);
 
+    if (pci_is_express(pci_dev) && pci_bus_is_express(pci_dev->bus)) {
+        pcie_endpoint_cap_init(pci_dev, PVSCSI_EXP_EP_OFFSET);
+    }
+
     s->completion_worker = qemu_bh_new(pvscsi_process_completion_queue, s);
     if (!s->completion_worker) {
         pvscsi_cleanup_msi(s);
@@ -1139,6 +1175,27 @@ pvscsi_post_load(void *opaque, int version_id)
     return 0;
 }
 
+static bool pvscsi_vmstate_need_pcie_device(void *opaque)
+{
+    PVSCSIState *s = PVSCSI(opaque);
+
+    return !(s->compat_flags & PVSCSI_COMPAT_DISABLE_PCIE);
+}
+
+static bool pvscsi_vmstate_test_pci_device(void *opaque, int version_id)
+{
+    return !pvscsi_vmstate_need_pcie_device(opaque);
+}
+
+static const VMStateDescription vmstate_pvscsi_pcie_device = {
+    .name = "pvscsi/pcie",
+    .needed = pvscsi_vmstate_need_pcie_device,
+    .fields = (VMStateField[]) {
+        VMSTATE_PCIE_DEVICE(parent_obj, PVSCSIState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_pvscsi = {
     .name = "pvscsi",
     .version_id = 0,
@@ -1146,7 +1203,9 @@ static const VMStateDescription vmstate_pvscsi = {
     .pre_save = pvscsi_pre_save,
     .post_load = pvscsi_post_load,
     .fields = (VMStateField[]) {
-        VMSTATE_PCI_DEVICE(parent_obj, PVSCSIState),
+        VMSTATE_STRUCT_TEST(parent_obj, PVSCSIState,
+                            pvscsi_vmstate_test_pci_device, 0,
+                            vmstate_pci_device, PCIDevice),
         VMSTATE_UINT8(msi_used, PVSCSIState),
         VMSTATE_UINT32(resetting, PVSCSIState),
         VMSTATE_UINT64(reg_interrupt_status, PVSCSIState),
@@ -1171,18 +1230,40 @@ static const VMStateDescription vmstate_pvscsi = {
         VMSTATE_UINT64(rings.filled_cmp_ptr, PVSCSIState),
 
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription*[]) {
+        &vmstate_pvscsi_pcie_device,
+        NULL
     }
 };
 
 static Property pvscsi_properties[] = {
     DEFINE_PROP_UINT8("use_msg", PVSCSIState, use_msg, 1),
+    DEFINE_PROP_BIT("x-old-pci-configuration", PVSCSIState, compat_flags,
+                    PVSCSI_COMPAT_OLD_PCI_CONFIGURATION_BIT, false),
+    DEFINE_PROP_BIT("x-disable-pcie", PVSCSIState, compat_flags,
+                    PVSCSI_COMPAT_DISABLE_PCIE_BIT, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
+static void pvscsi_realize(DeviceState *qdev, Error **errp)
+{
+    PVSCSIClass *pvs_c = PVSCSI_DEVICE_GET_CLASS(qdev);
+    PCIDevice *pci_dev = PCI_DEVICE(qdev);
+    PVSCSIState *s = PVSCSI(qdev);
+
+    if (!(s->compat_flags & PVSCSI_COMPAT_DISABLE_PCIE)) {
+        pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
+    }
+
+    pvs_c->parent_dc_realize(qdev, errp);
+}
+
 static void pvscsi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+    PVSCSIClass *pvs_k = PVSCSI_DEVICE_CLASS(klass);
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
 
     k->init = pvscsi_init;
@@ -1191,6 +1272,8 @@ static void pvscsi_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_VMWARE_PVSCSI;
     k->class_id = PCI_CLASS_STORAGE_SCSI;
     k->subsystem_id = 0x1000;
+    pvs_k->parent_dc_realize = dc->realize;
+    dc->realize = pvscsi_realize;
     dc->reset = pvscsi_reset;
     dc->vmsd = &vmstate_pvscsi;
     dc->props = pvscsi_properties;
@@ -1202,6 +1285,7 @@ static void pvscsi_class_init(ObjectClass *klass, void *data)
 static const TypeInfo pvscsi_info = {
     .name          = TYPE_PVSCSI,
     .parent        = TYPE_PCI_DEVICE,
+    .class_size    = sizeof(PVSCSIClass),
     .instance_size = sizeof(PVSCSIState),
     .class_init    = pvscsi_class_init,
     .interfaces = (InterfaceInfo[]) {

hw/sd/sdhci.c

@@ -193,7 +193,9 @@ static void sdhci_reset(SDHCIState *s)
      * initialization */
     memset(&s->sdmasysad, 0, (uintptr_t)&s->capareg - (uintptr_t)&s->sdmasysad);
 
+    if (!s->noeject_quirk) {
         sd_set_cb(s->card, s->ro_cb, s->eject_cb);
+    }
     s->data_count = 0;
     s->stopped_state = sdhc_not_stopped;
 }
@@ -243,9 +245,6 @@ static void sdhci_send_command(SDHCIState *s)
             (s->cmdreg & SDHC_CMD_RESPONSE) == SDHC_CMD_RSP_WITH_BUSY) {
             s->norintsts |= SDHC_NIS_TRSCMP;
         }
-    } else if (rlen != 0 && (s->errintstsen & SDHC_EISEN_CMDIDX)) {
-        s->errintsts |= SDHC_EIS_CMDIDX;
-        s->norintsts |= SDHC_NIS_ERR;
     }
 
     if (s->norintstsen & SDHC_NISEN_CMDCMP) {
@@ -831,7 +830,7 @@ static void sdhci_data_transfer(void *opaque)
 
 static bool sdhci_can_issue_command(SDHCIState *s)
 {
-    if (!SDHC_CLOCK_IS_ON(s->clkcon) || !(s->pwrcon & SDHC_POWER_ON) ||
+    if (!SDHC_CLOCK_IS_ON(s->clkcon) ||
         (((s->prnsts & SDHC_DATA_INHIBIT) || s->stopped_state) &&
         ((s->cmdreg & SDHC_CMD_DATA_PRESENT) ||
         ((s->cmdreg & SDHC_CMD_RESPONSE) == SDHC_CMD_RSP_WITH_BUSY &&
@@ -1279,6 +1278,7 @@ static Property sdhci_sysbus_properties[] = {
     DEFINE_PROP_UINT32("capareg", SDHCIState, capareg,
             SDHC_CAPAB_REG_DEFAULT),
     DEFINE_PROP_UINT32("maxcurr", SDHCIState, maxcurr, 0),
+    DEFINE_PROP_BOOL("noeject-quirk", SDHCIState, noeject_quirk, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/sparc64/sun4u.c

@@ -363,6 +363,8 @@ void cpu_put_timer(QEMUFile *f, CPUTimer *s)
     qemu_put_be32s(f, &s->frequency);
     qemu_put_be32s(f, &s->disabled);
     qemu_put_be64s(f, &s->disabled_mask);
+    qemu_put_be32s(f, &s->npt);
+    qemu_put_be64s(f, &s->npt_mask);
     qemu_put_sbe64s(f, &s->clock_offset);
 
     timer_put(f, s->qtimer);
@@ -373,6 +375,8 @@ void cpu_get_timer(QEMUFile *f, CPUTimer *s)
     qemu_get_be32s(f, &s->frequency);
     qemu_get_be32s(f, &s->disabled);
     qemu_get_be64s(f, &s->disabled_mask);
+    qemu_get_be32s(f, &s->npt);
+    qemu_get_be64s(f, &s->npt_mask);
     qemu_get_sbe64s(f, &s->clock_offset);
 
     timer_get(f, s->qtimer);
@@ -380,15 +384,17 @@ void cpu_get_timer(QEMUFile *f, CPUTimer *s)
 
 static CPUTimer *cpu_timer_create(const char *name, SPARCCPU *cpu,
                                   QEMUBHFunc *cb, uint32_t frequency,
-                                  uint64_t disabled_mask)
+                                  uint64_t disabled_mask, uint64_t npt_mask)
 {
     CPUTimer *timer = g_malloc0(sizeof (CPUTimer));
 
     timer->name = name;
     timer->frequency = frequency;
     timer->disabled_mask = disabled_mask;
+    timer->npt_mask = npt_mask;
 
     timer->disabled = 1;
+    timer->npt = 1;
     timer->clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
 
     timer->qtimer = timer_new_ns(QEMU_CLOCK_VIRTUAL, cb, cpu);
@@ -494,17 +500,17 @@ static uint64_t timer_to_cpu_ticks(int64_t timer_ticks, uint32_t frequency)
 
 void cpu_tick_set_count(CPUTimer *timer, uint64_t count)
 {
-    uint64_t real_count = count & ~timer->disabled_mask;
-    uint64_t disabled_bit = count & timer->disabled_mask;
+    uint64_t real_count = count & ~timer->npt_mask;
+    uint64_t npt_bit = count & timer->npt_mask;
 
     int64_t vm_clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) -
                     cpu_to_timer_ticks(real_count, timer->frequency);
 
-    TIMER_DPRINTF("%s set_count count=0x%016lx (%s) p=%p\n",
+    TIMER_DPRINTF("%s set_count count=0x%016lx (npt %s) p=%p\n",
                   timer->name, real_count,
-                  timer->disabled?"disabled":"enabled", timer);
+                  timer->npt ? "disabled" : "enabled", timer);
 
-    timer->disabled = disabled_bit ? 1 : 0;
+    timer->npt = npt_bit ? 1 : 0;
     timer->clock_offset = vm_clock_offset;
 }
 
@@ -514,12 +520,13 @@ uint64_t cpu_tick_get_count(CPUTimer *timer)
                     qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - timer->clock_offset,
                     timer->frequency);
 
-    TIMER_DPRINTF("%s get_count count=0x%016lx (%s) p=%p\n",
+    TIMER_DPRINTF("%s get_count count=0x%016lx (npt %s) p=%p\n",
            timer->name, real_count,
-           timer->disabled?"disabled":"enabled", timer);
+           timer->npt ? "disabled" : "enabled", timer);
 
-    if (timer->disabled)
-        real_count |= timer->disabled_mask;
+    if (timer->npt) {
+        real_count |= timer->npt_mask;
+    }
 
     return real_count;
 }
@@ -799,13 +806,16 @@ static SPARCCPU *cpu_devinit(const char *cpu_model, const struct hwdef *hwdef)
     env = &cpu->env;
 
     env->tick = cpu_timer_create("tick", cpu, tick_irq,
-                                  tick_frequency, TICK_NPT_MASK);
+                                  tick_frequency, TICK_INT_DIS,
+                                  TICK_NPT_MASK);
 
     env->stick = cpu_timer_create("stick", cpu, stick_irq,
-                                   stick_frequency, TICK_INT_DIS);
+                                   stick_frequency, TICK_INT_DIS,
+                                   TICK_NPT_MASK);
 
     env->hstick = cpu_timer_create("hstick", cpu, hstick_irq,
-                                    hstick_frequency, TICK_INT_DIS);
+                                    hstick_frequency, TICK_INT_DIS,
+                                    TICK_NPT_MASK);
 
     reset_info = g_malloc0(sizeof(ResetData));
     reset_info->cpu = cpu;

hw/timer/imx_epit.c

@@ -51,9 +51,9 @@ static char const *imx_epit_reg_name(uint32_t reg)
  * These are typical.
  */
 static const IMXClk imx_epit_clocks[] =  {
-    0,        /* 00 disabled */
-    IPG,      /* 01 ipg_clk, ~532MHz */
-    IPG,      /* 10 ipg_clk_highfreq */
+    NOCLK,    /* 00 disabled */
+    CLK_IPG,  /* 01 ipg_clk, ~532MHz */
+    CLK_IPG,  /* 10 ipg_clk_highfreq */
     CLK_32k,  /* 11 ipg_clk_32k -- ~32kHz */
 };
 
@@ -73,20 +73,18 @@ static void imx_epit_set_freq(IMXEPITState *s)
 {
     uint32_t clksrc;
     uint32_t prescaler;
-    uint32_t freq;
 
     clksrc = extract32(s->cr, CR_CLKSRC_SHIFT, 2);
     prescaler = 1 + extract32(s->cr, CR_PRESCALE_SHIFT, 12);
 
-    freq = imx_clock_frequency(s->ccm, imx_epit_clocks[clksrc]) / prescaler;
+    s->freq = imx_ccm_get_clock_frequency(s->ccm,
+                                imx_epit_clocks[clksrc]) / prescaler;
 
-    s->freq = freq;
+    DPRINTF("Setting ptimer frequency to %u\n", s->freq);
 
-    DPRINTF("Setting ptimer frequency to %u\n", freq);
-
-    if (freq) {
-        ptimer_set_freq(s->timer_reload, freq);
-        ptimer_set_freq(s->timer_cmp, freq);
+    if (s->freq) {
+        ptimer_set_freq(s->timer_reload, s->freq);
+        ptimer_set_freq(s->timer_cmp, s->freq);
     }
 }
 

hw/timer/imx_gpt.c

@@ -81,8 +81,8 @@ static const VMStateDescription vmstate_imx_timer_gpt = {
 
 static const IMXClk imx_gpt_clocks[] = {
     NOCLK,    /* 000 No clock source */
-    IPG,      /* 001 ipg_clk, 532MHz*/
-    IPG,      /* 010 ipg_clk_highfreq */
+    CLK_IPG,  /* 001 ipg_clk, 532MHz*/
+    CLK_IPG,  /* 010 ipg_clk_highfreq */
     NOCLK,    /* 011 not defined */
     CLK_32k,  /* 100 ipg_clk_32k */
     NOCLK,    /* 101 not defined */
@@ -93,14 +93,14 @@ static const IMXClk imx_gpt_clocks[] = {
 static void imx_gpt_set_freq(IMXGPTState *s)
 {
     uint32_t clksrc = extract32(s->cr, GPT_CR_CLKSRC_SHIFT, 3);
-    uint32_t freq = imx_clock_frequency(s->ccm, imx_gpt_clocks[clksrc])
-                    / (1 + s->pr);
-    s->freq = freq;
 
-    DPRINTF("Setting clksrc %d to frequency %d\n", clksrc, freq);
+    s->freq = imx_ccm_get_clock_frequency(s->ccm,
+                                imx_gpt_clocks[clksrc]) / (1 + s->pr);
 
-    if (freq) {
-        ptimer_set_freq(s->timer, freq);
+    DPRINTF("Setting clksrc %d to frequency %d\n", clksrc, s->freq);
+
+    if (s->freq) {
+        ptimer_set_freq(s->timer, s->freq);
     }
 }
 

hw/usb/dev-mtp.c

@@ -15,6 +15,10 @@
 
 #include <sys/stat.h>
 #include <sys/statvfs.h>
+#ifdef __linux__
+#include <sys/inotify.h>
+#include "qemu/main-loop.h"
+#endif
 
 #include "qemu-common.h"
 #include "qemu/iov.h"
@@ -62,6 +66,11 @@ enum mtp_code {
     /* format codes */
     FMT_UNDEFINED_OBJECT           = 0x3000,
     FMT_ASSOCIATION                = 0x3001,
+
+    /* event codes */
+    EVT_OBJ_ADDED                  = 0x4002,
+    EVT_OBJ_REMOVED                = 0x4003,
+    EVT_OBJ_INFO_CHANGED           = 0x4007,
 };
 
 typedef struct {
@@ -84,6 +93,17 @@ enum {
     EP_EVENT,
 };
 
+#ifdef __linux__
+typedef struct MTPMonEntry MTPMonEntry;
+
+struct MTPMonEntry {
+    uint32_t event;
+    uint32_t handle;
+
+    QTAILQ_ENTRY(MTPMonEntry) next;
+};
+#endif
+
 struct MTPControl {
     uint16_t     code;
     uint32_t     trans;
@@ -108,9 +128,14 @@ struct MTPObject {
     char         *name;
     char         *path;
     struct stat  stat;
+#ifdef __linux__
+    /* inotify watch cookie */
+    int          watchfd;
+#endif
     MTPObject    *parent;
-    MTPObject    **children;
     uint32_t     nchildren;
+    QLIST_HEAD(, MTPObject) children;
+    QLIST_ENTRY(MTPObject) list;
     bool         have_children;
     QTAILQ_ENTRY(MTPObject) next;
 };
@@ -128,6 +153,11 @@ struct MTPState {
     uint32_t     next_handle;
 
     QTAILQ_HEAD(, MTPObject) objects;
+#ifdef __linux__
+    /* inotify descriptor */
+    int          inotifyfd;
+    QTAILQ_HEAD(events, MTPMonEntry) events;
+#endif
 };
 
 #define TYPE_USB_MTP "usb-mtp"
@@ -183,7 +213,7 @@ static const USBDescIface desc_iface_full = {
         },{
             .bEndpointAddress      = USB_DIR_IN | EP_EVENT,
             .bmAttributes          = USB_ENDPOINT_XFER_INT,
-            .wMaxPacketSize        = 8,
+            .wMaxPacketSize        = 64,
             .bInterval             = 0x0a,
         },
     }
@@ -225,7 +255,7 @@ static const USBDescIface desc_iface_high = {
         },{
             .bEndpointAddress      = USB_DIR_IN | EP_EVENT,
             .bmAttributes          = USB_ENDPOINT_XFER_INT,
-            .wMaxPacketSize        = 8,
+            .wMaxPacketSize        = 64,
             .bInterval             = 0x0a,
         },
     }
@@ -317,15 +347,24 @@ ignore:
 
 static void usb_mtp_object_free(MTPState *s, MTPObject *o)
 {
-    int i;
+    MTPObject *iter;
+
+    if (!o) {
+        return;
+    }
 
     trace_usb_mtp_object_free(s->dev.addr, o->handle, o->path);
 
     QTAILQ_REMOVE(&s->objects, o, next);
-    for (i = 0; i < o->nchildren; i++) {
-        usb_mtp_object_free(s, o->children[i]);
+    if (o->parent) {
+        QLIST_REMOVE(o, list);
+        o->parent->nchildren--;
+    }
+
+    while (!QLIST_EMPTY(&o->children)) {
+        iter = QLIST_FIRST(&o->children);
+        usb_mtp_object_free(s, iter);
     }
-    g_free(o->children);
     g_free(o->name);
     g_free(o->path);
     g_free(o);
@@ -343,6 +382,204 @@ static MTPObject *usb_mtp_object_lookup(MTPState *s, uint32_t handle)
     return NULL;
 }
 
+static MTPObject *usb_mtp_add_child(MTPState *s, MTPObject *o,
+                                    char *name)
+{
+    MTPObject *child =
+        usb_mtp_object_alloc(s, s->next_handle++, o, name);
+
+    if (child) {
+        trace_usb_mtp_add_child(s->dev.addr, child->handle, child->path);
+        QLIST_INSERT_HEAD(&o->children, child, list);
+        o->nchildren++;
+
+        if (child->format == FMT_ASSOCIATION) {
+            QLIST_INIT(&child->children);
+        }
+    }
+
+    return child;
+}
+
+#ifdef __linux__
+static MTPObject *usb_mtp_object_lookup_name(MTPObject *parent,
+                                             char *name, int len)
+{
+    MTPObject *iter;
+
+    QLIST_FOREACH(iter, &parent->children, list) {
+        if (strncmp(iter->name, name, len) == 0) {
+            return iter;
+        }
+    }
+
+    return NULL;
+}
+
+static MTPObject *usb_mtp_object_lookup_wd(MTPState *s, int wd)
+{
+    MTPObject *iter;
+
+    QTAILQ_FOREACH(iter, &s->objects, next) {
+        if (iter->watchfd == wd) {
+            return iter;
+        }
+    }
+
+    return NULL;
+}
+
+static void inotify_watchfn(void *arg)
+{
+    MTPState *s = arg;
+    ssize_t bytes;
+    /* From the man page: atleast one event can be read */
+    int len = sizeof(struct inotify_event) + NAME_MAX + 1;
+    int pos;
+    char buf[len];
+
+    for (;;) {
+        bytes = read(s->inotifyfd, buf, len);
+        pos = 0;
+
+        if (bytes <= 0) {
+            /* Better luck next time */
+            return;
+        }
+
+        /*
+         * TODO: Ignore initiator initiated events.
+         * For now we are good because the store is RO
+         */
+        while (bytes > 0) {
+            char *p = buf + pos;
+            struct inotify_event *event = (struct inotify_event *)p;
+            int watchfd = 0;
+            uint32_t mask = event->mask & (IN_CREATE | IN_DELETE |
+                                           IN_MODIFY | IN_IGNORED);
+            MTPObject *parent = usb_mtp_object_lookup_wd(s, event->wd);
+            MTPMonEntry *entry = NULL;
+            MTPObject *o;
+
+            pos = pos + sizeof(struct inotify_event) + event->len;
+            bytes = bytes - pos;
+
+            if (!parent) {
+                continue;
+            }
+
+            switch (mask) {
+            case IN_CREATE:
+                if (usb_mtp_object_lookup_name
+                    (parent, event->name, event->len)) {
+                    /* Duplicate create event */
+                    continue;
+                }
+                entry = g_new0(MTPMonEntry, 1);
+                entry->handle = s->next_handle;
+                entry->event = EVT_OBJ_ADDED;
+                o = usb_mtp_add_child(s, parent, event->name);
+                if (!o) {
+                    g_free(entry);
+                    continue;
+                }
+                o->watchfd = watchfd;
+                trace_usb_mtp_inotify_event(s->dev.addr, event->name,
+                                            event->mask, "Obj Added");
+                break;
+
+            case IN_DELETE:
+                /*
+                 * The kernel issues a IN_IGNORED event
+                 * when a dir containing a watchpoint is
+                 * deleted, so we don't have to delete the
+                 * watchpoint
+                 */
+                o = usb_mtp_object_lookup_name(parent, event->name, event->len);
+                if (!o) {
+                    continue;
+                }
+                entry = g_new0(MTPMonEntry, 1);
+                entry->handle = o->handle;
+                entry->event = EVT_OBJ_REMOVED;
+                usb_mtp_object_free(s, o);
+                trace_usb_mtp_inotify_event(s->dev.addr, o->path,
+                                      event->mask, "Obj Deleted");
+                break;
+
+            case IN_MODIFY:
+                o = usb_mtp_object_lookup_name(parent, event->name, event->len);
+                if (!o) {
+                    continue;
+                }
+                entry = g_new0(MTPMonEntry, 1);
+                entry->handle = o->handle;
+                entry->event = EVT_OBJ_INFO_CHANGED;
+                trace_usb_mtp_inotify_event(s->dev.addr, o->path,
+                                      event->mask, "Obj Modified");
+                break;
+
+            case IN_IGNORED:
+                o = usb_mtp_object_lookup_name(parent, event->name, event->len);
+                trace_usb_mtp_inotify_event(s->dev.addr, o->path,
+                                      event->mask, "Obj ignored");
+                break;
+
+            default:
+                fprintf(stderr, "usb-mtp: failed to parse inotify event\n");
+                continue;
+            }
+
+            if (entry) {
+                QTAILQ_INSERT_HEAD(&s->events, entry, next);
+            }
+        }
+    }
+}
+
+static int usb_mtp_inotify_init(MTPState *s)
+{
+    int fd;
+
+    fd = inotify_init1(IN_NONBLOCK);
+    if (fd == -1) {
+        return 1;
+    }
+
+    QTAILQ_INIT(&s->events);
+    s->inotifyfd = fd;
+
+    qemu_set_fd_handler(fd, inotify_watchfn, NULL, s);
+
+    return 0;
+}
+
+static void usb_mtp_inotify_cleanup(MTPState *s)
+{
+    MTPMonEntry *e;
+
+    if (!s->inotifyfd) {
+        return;
+    }
+
+    qemu_set_fd_handler(s->inotifyfd, NULL, NULL, s);
+    close(s->inotifyfd);
+
+    QTAILQ_FOREACH(e, &s->events, next) {
+        QTAILQ_REMOVE(&s->events, e, next);
+        g_free(e);
+    }
+}
+
+static int usb_mtp_add_watch(int inotifyfd, char *path)
+{
+    uint32_t mask = IN_CREATE | IN_DELETE | IN_MODIFY |
+        IN_ISDIR;
+
+    return inotify_add_watch(inotifyfd, path, mask);
+}
+#endif
+
 static void usb_mtp_object_readdir(MTPState *s, MTPObject *o)
 {
     struct dirent *entry;
@@ -357,15 +594,18 @@ static void usb_mtp_object_readdir(MTPState *s, MTPObject *o)
     if (!dir) {
         return;
     }
+#ifdef __linux__
+    int watchfd = usb_mtp_add_watch(s->inotifyfd, o->path);
+    if (watchfd == -1) {
+        fprintf(stderr, "usb-mtp: failed to add watch for %s\n", o->path);
+    } else {
+        trace_usb_mtp_inotify_event(s->dev.addr, o->path,
+                                    0, "Watch Added");
+        o->watchfd = watchfd;
+    }
+#endif
     while ((entry = readdir(dir)) != NULL) {
-        if ((o->nchildren % 32) == 0) {
-            o->children = g_renew(MTPObject *, o->children, o->nchildren + 32);
-        }
-        o->children[o->nchildren] =
-            usb_mtp_object_alloc(s, s->next_handle++, o, entry->d_name);
-        if (o->children[o->nchildren] != NULL) {
-            o->nchildren++;
-        }
+        usb_mtp_add_child(s, o, entry->d_name);
     }
     closedir(dir);
 }
@@ -617,13 +857,15 @@ static MTPData *usb_mtp_get_object_handles(MTPState *s, MTPControl *c,
                                            MTPObject *o)
 {
     MTPData *d = usb_mtp_data_alloc(c);
-    uint32_t i, handles[o->nchildren];
+    uint32_t i = 0, handles[o->nchildren];
+    MTPObject *iter;
 
     trace_usb_mtp_op_get_object_handles(s->dev.addr, o->handle, o->path);
 
-    for (i = 0; i < o->nchildren; i++) {
-        handles[i] = o->children[i]->handle;
+    QLIST_FOREACH(iter, &o->children, list) {
+        handles[i++] = iter->handle;
     }
+    assert(i == o->nchildren);
     usb_mtp_add_u32_array(d, o->nchildren, handles);
 
     return d;
@@ -754,11 +996,19 @@ static void usb_mtp_command(MTPState *s, MTPControl *c)
         trace_usb_mtp_op_open_session(s->dev.addr);
         s->session = c->argv[0];
         usb_mtp_object_alloc(s, s->next_handle++, NULL, s->root);
+#ifdef __linux__
+        if (usb_mtp_inotify_init(s)) {
+            fprintf(stderr, "usb-mtp: file monitoring init failed\n");
+        }
+#endif
         break;
     case CMD_CLOSE_SESSION:
         trace_usb_mtp_op_close_session(s->dev.addr);
         s->session = 0;
         s->next_handle = 0;
+#ifdef __linux__
+        usb_mtp_inotify_cleanup(s);
+#endif
         usb_mtp_object_free(s, QTAILQ_FIRST(&s->objects));
         assert(QTAILQ_EMPTY(&s->objects));
         break;
@@ -884,6 +1134,10 @@ static void usb_mtp_handle_reset(USBDevice *dev)
 
     trace_usb_mtp_reset(s->dev.addr);
 
+#ifdef __linux__
+    usb_mtp_inotify_cleanup(s);
+#endif
+    usb_mtp_object_free(s, QTAILQ_FIRST(&s->objects));
     s->session = 0;
     usb_mtp_data_free(s->data_in);
     s->data_in = NULL;
@@ -1043,6 +1297,31 @@ static void usb_mtp_handle_data(USBDevice *dev, USBPacket *p)
         }
         break;
     case EP_EVENT:
+#ifdef __linux__
+        if (!QTAILQ_EMPTY(&s->events)) {
+            struct MTPMonEntry *e = QTAILQ_LAST(&s->events, events);
+            uint32_t handle;
+            int len = sizeof(container) + sizeof(uint32_t);
+
+            if (p->iov.size < len) {
+                trace_usb_mtp_stall(s->dev.addr,
+                                    "packet too small to send event");
+                p->status = USB_RET_STALL;
+                return;
+            }
+
+            QTAILQ_REMOVE(&s->events, e, next);
+            container.length = cpu_to_le32(len);
+            container.type = cpu_to_le32(TYPE_EVENT);
+            container.code = cpu_to_le16(e->event);
+            container.trans = 0; /* no trans specific events */
+            handle = cpu_to_le32(e->handle);
+            usb_packet_copy(p, &container, sizeof(container));
+            usb_packet_copy(p, &handle, sizeof(uint32_t));
+            g_free(e);
+            return;
+        }
+#endif
         p->status = USB_RET_NAK;
         return;
     default:

hw/usb/hcd-ehci.c

@@ -1389,7 +1389,7 @@ static int ehci_process_itd(EHCIState *ehci,
 {
     USBDevice *dev;
     USBEndpoint *ep;
-    uint32_t i, len, pid, dir, devaddr, endp;
+    uint32_t i, len, pid, dir, devaddr, endp, xfers = 0;
     uint32_t pg, off, ptr1, ptr2, max, mult;
 
     ehci->periodic_sched_active = PERIODIC_ACTIVE;
@@ -1479,9 +1479,10 @@ static int ehci_process_itd(EHCIState *ehci,
                 ehci_raise_irq(ehci, USBSTS_INT);
             }
             itd->transact[i] &= ~ITD_XACT_ACTIVE;
+            xfers++;
         }
     }
-    return 0;
+    return xfers ? 0 : -1;
 }