Update dtc submodule to v1.4.3

Since the last submodule update (which was v1.4.2) dtc and libfdt have
gained some features which would be useful in qemu.  There's now a v1.4.3
upstream release, so update our submodule to point to it.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

.shippable.yml

@@ -5,6 +5,8 @@ env:
       TARGET_LIST=arm-softmmu,arm-linux-user
     - IMAGE=debian-arm64-cross
       TARGET_LIST=aarch64-softmmu,aarch64-linux-user
+    - IMAGE=debian-s390x-cross
+      TARGET_LIST=s390x-softmmu,s390x-linux-user
 build:
   pre_ci:
     - make docker-image-${IMAGE}

CODING_STYLE

@@ -116,3 +116,10 @@ if (a == 1) {
 Rationale: Yoda conditions (as in 'if (1 == a)') are awkward to read.
 Besides, good compilers already warn users when '==' is mis-typed as '=',
 even when the constant is on the right.
+
+7. Comment style
+
+We use traditional C-style /* */ comments and avoid // comments.
+
+Rationale: The // form is valid in C99, so this is purely a matter of
+consistency of style. The checkpatch script will warn you about this.

audio/audio.c

@@ -28,6 +28,7 @@
 #include "qemu/timer.h"
 #include "sysemu/sysemu.h"
 #include "qemu/cutils.h"
+#include "sysemu/replay.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -1112,7 +1113,7 @@ static int audio_is_timer_needed (void)
 static void audio_reset_timer (AudioState *s)
 {
     if (audio_is_timer_needed ()) {
-        timer_mod (s->ts,
+        timer_mod_anticipate_ns(s->ts,
             qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + conf.period.ticks);
     }
     else {
@@ -1387,6 +1388,7 @@ static void audio_run_out (AudioState *s)
 
         prev_rpos = hw->rpos;
         played = hw->pcm_ops->run_out (hw, live);
+        replay_audio_out(&played);
         if (audio_bug (AUDIO_FUNC, hw->rpos >= hw->samples)) {
             dolog ("hw->rpos=%d hw->samples=%d played=%d\n",
                    hw->rpos, hw->samples, played);
@@ -1450,9 +1452,12 @@ static void audio_run_in (AudioState *s)
 
     while ((hw = audio_pcm_hw_find_any_enabled_in (hw))) {
         SWVoiceIn *sw;
-        int captured, min;
+        int captured = 0, min;
 
-        captured = hw->pcm_ops->run_in (hw);
+        if (replay_mode != REPLAY_MODE_PLAY) {
+            captured = hw->pcm_ops->run_in(hw);
+        }
+        replay_audio_in(&captured, hw->conv_buf, &hw->wpos, hw->samples);
 
         min = audio_pcm_hw_find_min_in (hw);
         hw->total_samples_captured += captured - min;

audio/audio.h

@@ -166,4 +166,9 @@ int wav_start_capture (CaptureState *s, const char *path, int freq,
 bool audio_is_cleaning_up(void);
 void audio_cleanup(void);
 
+void audio_sample_to_uint64(void *samples, int pos,
+                            uint64_t *left, uint64_t *right);
+void audio_sample_from_uint64(void *samples, int pos,
+                            uint64_t left, uint64_t right);
+
 #endif /* QEMU_AUDIO_H */

audio/mixeng.c

@@ -25,6 +25,7 @@
 #include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "qemu/bswap.h"
+#include "qemu/error-report.h"
 #include "audio.h"
 
 #define AUDIO_CAP "mixeng"
@@ -267,6 +268,37 @@ f_sample *mixeng_clip[2][2][2][3] = {
     }
 };
 
+
+void audio_sample_to_uint64(void *samples, int pos,
+                            uint64_t *left, uint64_t *right)
+{
+    struct st_sample *sample = samples;
+    sample += pos;
+#ifdef FLOAT_MIXENG
+    error_report(
+        "Coreaudio and floating point samples are not supported by replay yet");
+    abort();
+#else
+    *left = sample->l;
+    *right = sample->r;
+#endif
+}
+
+void audio_sample_from_uint64(void *samples, int pos,
+                            uint64_t left, uint64_t right)
+{
+    struct st_sample *sample = samples;
+    sample += pos;
+#ifdef FLOAT_MIXENG
+    error_report(
+        "Coreaudio and floating point samples are not supported by replay yet");
+    abort();
+#else
+    sample->l = left;
+    sample->r = right;
+#endif
+}
+
 /*
  * August 21, 1998
  * Copyright 1998 Fabrice Bellard.

audio/sdlaudio.c

@@ -38,10 +38,14 @@
 #define AUDIO_CAP "sdl"
 #include "audio_int.h"
 
+#define USE_SEMAPHORE (SDL_MAJOR_VERSION < 2)
+
 typedef struct SDLVoiceOut {
     HWVoiceOut hw;
     int live;
+#if USE_SEMAPHORE
     int rpos;
+#endif
     int decr;
 } SDLVoiceOut;
 
@@ -53,8 +57,10 @@ static struct {
 
 static struct SDLAudioState {
     int exit;
+#if USE_SEMAPHORE
     SDL_mutex *mutex;
     SDL_sem *sem;
+#endif
     int initialized;
     bool driver_created;
 } glob_sdl;
@@ -73,31 +79,45 @@ static void GCC_FMT_ATTR (1, 2) sdl_logerr (const char *fmt, ...)
 
 static int sdl_lock (SDLAudioState *s, const char *forfn)
 {
+#if USE_SEMAPHORE
     if (SDL_LockMutex (s->mutex)) {
         sdl_logerr ("SDL_LockMutex for %s failed\n", forfn);
         return -1;
     }
+#else
+    SDL_LockAudio();
+#endif
+
     return 0;
 }
 
 static int sdl_unlock (SDLAudioState *s, const char *forfn)
 {
+#if USE_SEMAPHORE
     if (SDL_UnlockMutex (s->mutex)) {
         sdl_logerr ("SDL_UnlockMutex for %s failed\n", forfn);
         return -1;
     }
+#else
+    SDL_UnlockAudio();
+#endif
+
     return 0;
 }
 
 static int sdl_post (SDLAudioState *s, const char *forfn)
 {
+#if USE_SEMAPHORE
     if (SDL_SemPost (s->sem)) {
         sdl_logerr ("SDL_SemPost for %s failed\n", forfn);
         return -1;
     }
+#endif
+
     return 0;
 }
 
+#if USE_SEMAPHORE
 static int sdl_wait (SDLAudioState *s, const char *forfn)
 {
     if (SDL_SemWait (s->sem)) {
@@ -106,6 +126,7 @@ static int sdl_wait (SDLAudioState *s, const char *forfn)
     }
     return 0;
 }
+#endif
 
 static int sdl_unlock_and_post (SDLAudioState *s, const char *forfn)
 {
@@ -246,6 +267,7 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
         int to_mix, decr;
 
         /* dolog ("in callback samples=%d\n", samples); */
+#if USE_SEMAPHORE
         sdl_wait (s, "sdl_callback");
         if (s->exit) {
             return;
@@ -264,6 +286,11 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
         if (!sdl->live) {
             goto again;
         }
+#else
+        if (s->exit || !sdl->live) {
+            break;
+        }
+#endif
 
         /* dolog ("in callback live=%d\n", live); */
         to_mix = audio_MIN (samples, sdl->live);
@@ -274,7 +301,11 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
 
             /* dolog ("in callback to_mix %d, chunk %d\n", to_mix, chunk); */
             hw->clip (buf, src, chunk);
+#if USE_SEMAPHORE
             sdl->rpos = (sdl->rpos + chunk) % hw->samples;
+#else
+            hw->rpos = (hw->rpos + chunk) % hw->samples;
+#endif
             to_mix -= chunk;
             buf += chunk << hw->info.shift;
         }
@@ -282,12 +313,21 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
         sdl->live -= decr;
         sdl->decr += decr;
 
+#if USE_SEMAPHORE
     again:
         if (sdl_unlock (s, "sdl_callback")) {
             return;
         }
+#endif
     }
     /* dolog ("done len=%d\n", len); */
+
+#if (SDL_MAJOR_VERSION >= 2)
+    /* SDL2 does not clear the remaining buffer for us, so do it on our own */
+    if (samples) {
+        memset(buf, 0, samples << hw->info.shift);
+    }
+#endif
 }
 
 static int sdl_write_out (SWVoiceOut *sw, void *buf, int len)
@@ -315,8 +355,12 @@ static int sdl_run_out (HWVoiceOut *hw, int live)
     decr = audio_MIN (sdl->decr, live);
     sdl->decr -= decr;
 
+#if USE_SEMAPHORE
     sdl->live = live - decr;
     hw->rpos = sdl->rpos;
+#else
+    sdl->live = live;
+#endif
 
     if (sdl->live > 0) {
         sdl_unlock_and_post (s, "sdl_run_out");
@@ -405,6 +449,7 @@ static void *sdl_audio_init (void)
         return NULL;
     }
 
+#if USE_SEMAPHORE
     s->mutex = SDL_CreateMutex ();
     if (!s->mutex) {
         sdl_logerr ("Failed to create SDL mutex\n");
@@ -419,6 +464,7 @@ static void *sdl_audio_init (void)
         SDL_QuitSubSystem (SDL_INIT_AUDIO);
         return NULL;
     }
+#endif
 
     s->driver_created = true;
     return s;
@@ -428,8 +474,10 @@ static void sdl_audio_fini (void *opaque)
 {
     SDLAudioState *s = opaque;
     sdl_close (s);
+#if USE_SEMAPHORE
     SDL_DestroySemaphore (s->sem);
     SDL_DestroyMutex (s->mutex);
+#endif
     SDL_QuitSubSystem (SDL_INIT_AUDIO);
     s->driver_created = false;
 }

block.c

@@ -707,6 +707,12 @@ int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough)
     return 0;
 }
 
+static char *bdrv_child_get_parent_desc(BdrvChild *c)
+{
+    BlockDriverState *parent = c->opaque;
+    return g_strdup(bdrv_get_device_or_node_name(parent));
+}
+
 static void bdrv_child_cb_drained_begin(BdrvChild *child)
 {
     BlockDriverState *bs = child->opaque;
@@ -774,6 +780,7 @@ static void bdrv_inherited_options(int *child_flags, QDict *child_options,
 }
 
 const BdrvChildRole child_file = {
+    .get_parent_desc = bdrv_child_get_parent_desc,
     .inherit_options = bdrv_inherited_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
@@ -794,11 +801,63 @@ static void bdrv_inherited_fmt_options(int *child_flags, QDict *child_options,
 }
 
 const BdrvChildRole child_format = {
+    .get_parent_desc = bdrv_child_get_parent_desc,
     .inherit_options = bdrv_inherited_fmt_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
 };
 
+static void bdrv_backing_attach(BdrvChild *c)
+{
+    BlockDriverState *parent = c->opaque;
+    BlockDriverState *backing_hd = c->bs;
+
+    assert(!parent->backing_blocker);
+    error_setg(&parent->backing_blocker,
+               "node is used as backing hd of '%s'",
+               bdrv_get_device_or_node_name(parent));
+
+    parent->open_flags &= ~BDRV_O_NO_BACKING;
+    pstrcpy(parent->backing_file, sizeof(parent->backing_file),
+            backing_hd->filename);
+    pstrcpy(parent->backing_format, sizeof(parent->backing_format),
+            backing_hd->drv ? backing_hd->drv->format_name : "");
+
+    bdrv_op_block_all(backing_hd, parent->backing_blocker);
+    /* Otherwise we won't be able to commit or stream */
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
+                    parent->backing_blocker);
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
+                    parent->backing_blocker);
+    /*
+     * We do backup in 3 ways:
+     * 1. drive backup
+     *    The target bs is new opened, and the source is top BDS
+     * 2. blockdev backup
+     *    Both the source and the target are top BDSes.
+     * 3. internal backup(used for block replication)
+     *    Both the source and the target are backing file
+     *
+     * In case 1 and 2, neither the source nor the target is the backing file.
+     * In case 3, we will block the top BDS, so there is only one block job
+     * for the top BDS and its backing chain.
+     */
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_SOURCE,
+                    parent->backing_blocker);
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
+                    parent->backing_blocker);
+}
+
+static void bdrv_backing_detach(BdrvChild *c)
+{
+    BlockDriverState *parent = c->opaque;
+
+    assert(parent->backing_blocker);
+    bdrv_op_unblock_all(c->bs, parent->backing_blocker);
+    error_free(parent->backing_blocker);
+    parent->backing_blocker = NULL;
+}
+
 /*
  * Returns the options and flags that bs->backing should get, based on the
  * given options and flags for the parent BDS
@@ -823,7 +882,10 @@ static void bdrv_backing_options(int *child_flags, QDict *child_options,
     *child_flags = flags;
 }
 
-static const BdrvChildRole child_backing = {
+const BdrvChildRole child_backing = {
+    .get_parent_desc = bdrv_child_get_parent_desc,
+    .attach          = bdrv_backing_attach,
+    .detach          = bdrv_backing_detach,
     .inherit_options = bdrv_backing_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
@@ -1326,15 +1388,352 @@ static int bdrv_fill_options(QDict **options, const char *filename,
     return 0;
 }
 
-static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
+/*
+ * Check whether permissions on this node can be changed in a way that
+ * @cumulative_perms and @cumulative_shared_perms are the new cumulative
+ * permissions of all its parents. This involves checking whether all necessary
+ * permission changes to child nodes can be performed.
+ *
+ * A call to this function must always be followed by a call to bdrv_set_perm()
+ * or bdrv_abort_perm_update().
+ */
+static int bdrv_check_perm(BlockDriverState *bs, uint64_t cumulative_perms,
+                           uint64_t cumulative_shared_perms, Error **errp)
+{
+    BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+    int ret;
+
+    /* Write permissions never work with read-only images */
+    if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) &&
+        bdrv_is_read_only(bs))
+    {
+        error_setg(errp, "Block node is read-only");
+        return -EPERM;
+    }
+
+    /* Check this node */
+    if (!drv) {
+        return 0;
+    }
+
+    if (drv->bdrv_check_perm) {
+        return drv->bdrv_check_perm(bs, cumulative_perms,
+                                    cumulative_shared_perms, errp);
+    }
+
+    /* Drivers that never have children can omit .bdrv_child_perm() */
+    if (!drv->bdrv_child_perm) {
+        assert(QLIST_EMPTY(&bs->children));
+        return 0;
+    }
+
+    /* Check all children */
+    QLIST_FOREACH(c, &bs->children, next) {
+        uint64_t cur_perm, cur_shared;
+        drv->bdrv_child_perm(bs, c, c->role,
+                             cumulative_perms, cumulative_shared_perms,
+                             &cur_perm, &cur_shared);
+        ret = bdrv_child_check_perm(c, cur_perm, cur_shared, errp);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * Notifies drivers that after a previous bdrv_check_perm() call, the
+ * permission update is not performed and any preparations made for it (e.g.
+ * taken file locks) need to be undone.
+ *
+ * This function recursively notifies all child nodes.
+ */
+static void bdrv_abort_perm_update(BlockDriverState *bs)
+{
+    BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+
+    if (!drv) {
+        return;
+    }
+
+    if (drv->bdrv_abort_perm_update) {
+        drv->bdrv_abort_perm_update(bs);
+    }
+
+    QLIST_FOREACH(c, &bs->children, next) {
+        bdrv_child_abort_perm_update(c);
+    }
+}
+
+static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms,
+                          uint64_t cumulative_shared_perms)
+{
+    BlockDriver *drv = bs->drv;
+    BdrvChild *c;
+
+    if (!drv) {
+        return;
+    }
+
+    /* Update this node */
+    if (drv->bdrv_set_perm) {
+        drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms);
+    }
+
+    /* Drivers that never have children can omit .bdrv_child_perm() */
+    if (!drv->bdrv_child_perm) {
+        assert(QLIST_EMPTY(&bs->children));
+        return;
+    }
+
+    /* Update all children */
+    QLIST_FOREACH(c, &bs->children, next) {
+        uint64_t cur_perm, cur_shared;
+        drv->bdrv_child_perm(bs, c, c->role,
+                             cumulative_perms, cumulative_shared_perms,
+                             &cur_perm, &cur_shared);
+        bdrv_child_set_perm(c, cur_perm, cur_shared);
+    }
+}
+
+static void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
+                                     uint64_t *shared_perm)
+{
+    BdrvChild *c;
+    uint64_t cumulative_perms = 0;
+    uint64_t cumulative_shared_perms = BLK_PERM_ALL;
+
+    QLIST_FOREACH(c, &bs->parents, next_parent) {
+        cumulative_perms |= c->perm;
+        cumulative_shared_perms &= c->shared_perm;
+    }
+
+    *perm = cumulative_perms;
+    *shared_perm = cumulative_shared_perms;
+}
+
+static char *bdrv_child_user_desc(BdrvChild *c)
+{
+    if (c->role->get_parent_desc) {
+        return c->role->get_parent_desc(c);
+    }
+
+    return g_strdup("another user");
+}
+
+static char *bdrv_perm_names(uint64_t perm)
+{
+    struct perm_name {
+        uint64_t perm;
+        const char *name;
+    } permissions[] = {
+        { BLK_PERM_CONSISTENT_READ, "consistent read" },
+        { BLK_PERM_WRITE,           "write" },
+        { BLK_PERM_WRITE_UNCHANGED, "write unchanged" },
+        { BLK_PERM_RESIZE,          "resize" },
+        { BLK_PERM_GRAPH_MOD,       "change children" },
+        { 0, NULL }
+    };
+
+    char *result = g_strdup("");
+    struct perm_name *p;
+
+    for (p = permissions; p->name; p++) {
+        if (perm & p->perm) {
+            char *old = result;
+            result = g_strdup_printf("%s%s%s", old, *old ? ", " : "", p->name);
+            g_free(old);
+        }
+    }
+
+    return result;
+}
+
+/*
+ * Checks whether a new reference to @bs can be added if the new user requires
+ * @new_used_perm/@new_shared_perm as its permissions. If @ignore_child is set,
+ * this old reference is ignored in the calculations; this allows checking
+ * permission updates for an existing reference.
+ *
+ * Needs to be followed by a call to either bdrv_set_perm() or
+ * bdrv_abort_perm_update(). */
+static int bdrv_check_update_perm(BlockDriverState *bs, uint64_t new_used_perm,
+                                  uint64_t new_shared_perm,
+                                  BdrvChild *ignore_child, Error **errp)
+{
+    BdrvChild *c;
+    uint64_t cumulative_perms = new_used_perm;
+    uint64_t cumulative_shared_perms = new_shared_perm;
+
+    /* There is no reason why anyone couldn't tolerate write_unchanged */
+    assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED);
+
+    QLIST_FOREACH(c, &bs->parents, next_parent) {
+        if (c == ignore_child) {
+            continue;
+        }
+
+        if ((new_used_perm & c->shared_perm) != new_used_perm) {
+            char *user = bdrv_child_user_desc(c);
+            char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm);
+            error_setg(errp, "Conflicts with use by %s as '%s', which does not "
+                             "allow '%s' on %s",
+                       user, c->name, perm_names, bdrv_get_node_name(c->bs));
+            g_free(user);
+            g_free(perm_names);
+            return -EPERM;
+        }
+
+        if ((c->perm & new_shared_perm) != c->perm) {
+            char *user = bdrv_child_user_desc(c);
+            char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm);
+            error_setg(errp, "Conflicts with use by %s as '%s', which uses "
+                             "'%s' on %s",
+                       user, c->name, perm_names, bdrv_get_node_name(c->bs));
+            g_free(user);
+            g_free(perm_names);
+            return -EPERM;
+        }
+
+        cumulative_perms |= c->perm;
+        cumulative_shared_perms &= c->shared_perm;
+    }
+
+    return bdrv_check_perm(bs, cumulative_perms, cumulative_shared_perms, errp);
+}
+
+/* Needs to be followed by a call to either bdrv_child_set_perm() or
+ * bdrv_child_abort_perm_update(). */
+int bdrv_child_check_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                          Error **errp)
+{
+    return bdrv_check_update_perm(c->bs, perm, shared, c, errp);
+}
+
+void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared)
+{
+    uint64_t cumulative_perms, cumulative_shared_perms;
+
+    c->perm = perm;
+    c->shared_perm = shared;
+
+    bdrv_get_cumulative_perm(c->bs, &cumulative_perms,
+                             &cumulative_shared_perms);
+    bdrv_set_perm(c->bs, cumulative_perms, cumulative_shared_perms);
+}
+
+void bdrv_child_abort_perm_update(BdrvChild *c)
+{
+    bdrv_abort_perm_update(c->bs);
+}
+
+int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                            Error **errp)
+{
+    int ret;
+
+    ret = bdrv_child_check_perm(c, perm, shared, errp);
+    if (ret < 0) {
+        bdrv_child_abort_perm_update(c);
+        return ret;
+    }
+
+    bdrv_child_set_perm(c, perm, shared);
+
+    return 0;
+}
+
+#define DEFAULT_PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
+                                 | BLK_PERM_WRITE \
+                                 | BLK_PERM_WRITE_UNCHANGED \
+                                 | BLK_PERM_RESIZE)
+#define DEFAULT_PERM_UNCHANGED (BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH)
+
+void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared)
+{
+    if (c == NULL) {
+        *nperm = perm & DEFAULT_PERM_PASSTHROUGH;
+        *nshared = (shared & DEFAULT_PERM_PASSTHROUGH) | DEFAULT_PERM_UNCHANGED;
+        return;
+    }
+
+    *nperm = (perm & DEFAULT_PERM_PASSTHROUGH) |
+             (c->perm & DEFAULT_PERM_UNCHANGED);
+    *nshared = (shared & DEFAULT_PERM_PASSTHROUGH) |
+               (c->shared_perm & DEFAULT_PERM_UNCHANGED);
+}
+
+void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared)
+{
+    bool backing = (role == &child_backing);
+    assert(role == &child_backing || role == &child_file);
+
+    if (!backing) {
+        /* Apart from the modifications below, the same permissions are
+         * forwarded and left alone as for filters */
+        bdrv_filter_default_perms(bs, c, role, perm, shared, &perm, &shared);
+
+        /* Format drivers may touch metadata even if the guest doesn't write */
+        if (!bdrv_is_read_only(bs)) {
+            perm |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
+        }
+
+        /* bs->file always needs to be consistent because of the metadata. We
+         * can never allow other users to resize or write to it. */
+        perm |= BLK_PERM_CONSISTENT_READ;
+        shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
+    } else {
+        /* We want consistent read from backing files if the parent needs it.
+         * No other operations are performed on backing files. */
+        perm &= BLK_PERM_CONSISTENT_READ;
+
+        /* If the parent can deal with changing data, we're okay with a
+         * writable and resizable backing file. */
+        /* TODO Require !(perm & BLK_PERM_CONSISTENT_READ), too? */
+        if (shared & BLK_PERM_WRITE) {
+            shared = BLK_PERM_WRITE | BLK_PERM_RESIZE;
+        } else {
+            shared = 0;
+        }
+
+        shared |= BLK_PERM_CONSISTENT_READ | BLK_PERM_GRAPH_MOD |
+                  BLK_PERM_WRITE_UNCHANGED;
+    }
+
+    *nperm = perm;
+    *nshared = shared;
+}
+
+static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs,
+                               bool check_new_perm)
 {
     BlockDriverState *old_bs = child->bs;
+    uint64_t perm, shared_perm;
 
     if (old_bs) {
         if (old_bs->quiesce_counter && child->role->drained_end) {
             child->role->drained_end(child);
         }
+        if (child->role->detach) {
+            child->role->detach(child);
+        }
         QLIST_REMOVE(child, next_parent);
+
+        /* Update permissions for old node. This is guaranteed to succeed
+         * because we're just taking a parent away, so we're loosening
+         * restrictions. */
+        bdrv_get_cumulative_perm(old_bs, &perm, &shared_perm);
+        bdrv_check_perm(old_bs, perm, shared_perm, &error_abort);
+        bdrv_set_perm(old_bs, perm, shared_perm);
     }
 
     child->bs = new_bs;
@@ -1344,23 +1743,46 @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
         if (new_bs->quiesce_counter && child->role->drained_begin) {
             child->role->drained_begin(child);
         }
+
+        bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm);
+        if (check_new_perm) {
+            bdrv_check_perm(new_bs, perm, shared_perm, &error_abort);
+        }
+        bdrv_set_perm(new_bs, perm, shared_perm);
+
+        if (child->role->attach) {
+            child->role->attach(child);
+        }
     }
 }
 
 BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
                                   const char *child_name,
                                   const BdrvChildRole *child_role,
-                                  void *opaque)
+                                  uint64_t perm, uint64_t shared_perm,
+                                  void *opaque, Error **errp)
 {
-    BdrvChild *child = g_new(BdrvChild, 1);
+    BdrvChild *child;
+    int ret;
+
+    ret = bdrv_check_update_perm(child_bs, perm, shared_perm, NULL, errp);
+    if (ret < 0) {
+        bdrv_abort_perm_update(child_bs);
+        return NULL;
+    }
+
+    child = g_new(BdrvChild, 1);
     *child = (BdrvChild) {
-        .bs     = NULL,
-        .name   = g_strdup(child_name),
-        .role   = child_role,
-        .opaque = opaque,
+        .bs             = NULL,
+        .name           = g_strdup(child_name),
+        .role           = child_role,
+        .perm           = perm,
+        .shared_perm    = shared_perm,
+        .opaque         = opaque,
     };
 
-    bdrv_replace_child(child, child_bs);
+    /* This performs the matching bdrv_set_perm() for the above check. */
+    bdrv_replace_child(child, child_bs, false);
 
     return child;
 }
@@ -1368,10 +1790,24 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
 BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
                              BlockDriverState *child_bs,
                              const char *child_name,
-                             const BdrvChildRole *child_role)
+                             const BdrvChildRole *child_role,
+                             Error **errp)
 {
-    BdrvChild *child = bdrv_root_attach_child(child_bs, child_name, child_role,
-                                              parent_bs);
+    BdrvChild *child;
+    uint64_t perm, shared_perm;
+
+    bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm);
+
+    assert(parent_bs->drv);
+    parent_bs->drv->bdrv_child_perm(parent_bs, NULL, child_role,
+                                    perm, shared_perm, &perm, &shared_perm);
+
+    child = bdrv_root_attach_child(child_bs, child_name, child_role,
+                                   perm, shared_perm, parent_bs, errp);
+    if (child == NULL) {
+        return NULL;
+    }
+
     QLIST_INSERT_HEAD(&parent_bs->children, child, next);
     return child;
 }
@@ -1383,7 +1819,7 @@ static void bdrv_detach_child(BdrvChild *child)
         child->next.le_prev = NULL;
     }
 
-    bdrv_replace_child(child, NULL);
+    bdrv_replace_child(child, NULL, false);
 
     g_free(child->name);
     g_free(child);
@@ -1447,57 +1883,28 @@ static void bdrv_parent_cb_resize(BlockDriverState *bs)
  * Sets the backing file link of a BDS. A new reference is created; callers
  * which don't need their own reference any more must call bdrv_unref().
  */
-void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
+void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
+                         Error **errp)
 {
     if (backing_hd) {
         bdrv_ref(backing_hd);
     }
 
     if (bs->backing) {
-        assert(bs->backing_blocker);
-        bdrv_op_unblock_all(bs->backing->bs, bs->backing_blocker);
         bdrv_unref_child(bs, bs->backing);
-    } else if (backing_hd) {
-        error_setg(&bs->backing_blocker,
-                   "node is used as backing hd of '%s'",
-                   bdrv_get_device_or_node_name(bs));
     }
 
     if (!backing_hd) {
-        error_free(bs->backing_blocker);
-        bs->backing_blocker = NULL;
         bs->backing = NULL;
         goto out;
     }
-    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),
-            backing_hd->drv ? backing_hd->drv->format_name : "");
 
-    bdrv_op_block_all(backing_hd, bs->backing_blocker);
-    /* Otherwise we won't be able to commit or stream */
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
-                    bs->backing_blocker);
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
-                    bs->backing_blocker);
-    /*
-     * We do backup in 3 ways:
-     * 1. drive backup
-     *    The target bs is new opened, and the source is top BDS
-     * 2. blockdev backup
-     *    Both the source and the target are top BDSes.
-     * 3. internal backup(used for block replication)
-     *    Both the source and the target are backing file
-     *
-     * In case 1 and 2, neither the source nor the target is the backing file.
-     * In case 3, we will block the top BDS, so there is only one block job
-     * for the top BDS and its backing chain.
-     */
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_SOURCE,
-                    bs->backing_blocker);
-    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
-                    bs->backing_blocker);
+    bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_backing,
+                                    errp);
+    if (!bs->backing) {
+        bdrv_unref(backing_hd);
+    }
+
 out:
     bdrv_refresh_limits(bs, NULL);
 }
@@ -1580,8 +1987,12 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
 
     /* Hook up the backing file link; drop our reference, bs owns the
      * backing_hd reference now */
-    bdrv_set_backing_hd(bs, backing_hd);
+    bdrv_set_backing_hd(bs, backing_hd, &local_err);
     bdrv_unref(backing_hd);
+    if (local_err) {
+        ret = -EINVAL;
+        goto free_exit;
+    }
 
     qdict_del(parent_options, bdref_key);
 
@@ -1648,6 +2059,7 @@ BdrvChild *bdrv_open_child(const char *filename,
                            const BdrvChildRole *child_role,
                            bool allow_none, Error **errp)
 {
+    BdrvChild *c;
     BlockDriverState *bs;
 
     bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role,
@@ -1656,7 +2068,13 @@ BdrvChild *bdrv_open_child(const char *filename,
         return NULL;
     }
 
-    return bdrv_attach_child(parent, bs, bdref_key, child_role);
+    c = bdrv_attach_child(parent, bs, bdref_key, child_role, errp);
+    if (!c) {
+        bdrv_unref(bs);
+        return NULL;
+    }
+
+    return c;
 }
 
 static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
@@ -1669,6 +2087,7 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
     int64_t total_size;
     QemuOpts *opts = NULL;
     BlockDriverState *bs_snapshot;
+    Error *local_err = NULL;
     int ret;
 
     /* if snapshot, we create a temporary backing file and open it
@@ -1718,7 +2137,12 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
      * call bdrv_unref() on it), so in order to be able to return one, we have
      * to increase bs_snapshot's refcount here */
     bdrv_ref(bs_snapshot);
-    bdrv_append(bs_snapshot, bs);
+    bdrv_append(bs_snapshot, bs, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto out;
+    }
 
     g_free(tmp_filename);
     return bs_snapshot;
@@ -1862,9 +2286,12 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
             goto fail;
         }
         if (file_bs != NULL) {
-            file = blk_new();
-            blk_insert_bs(file, file_bs);
+            file = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
+            blk_insert_bs(file, file_bs, &local_err);
             bdrv_unref(file_bs);
+            if (local_err) {
+                goto fail;
+            }
 
             qdict_put(options, "file",
                       qstring_from_str(bdrv_get_node_name(file_bs)));
@@ -2405,7 +2832,7 @@ static void bdrv_close(BlockDriverState *bs)
         bs->drv->bdrv_close(bs);
         bs->drv = NULL;
 
-        bdrv_set_backing_hd(bs, NULL);
+        bdrv_set_backing_hd(bs, NULL, &error_abort);
 
         if (bs->file != NULL) {
             bdrv_unref_child(bs, bs->file);
@@ -2465,10 +2892,13 @@ static void change_parent_backing_link(BlockDriverState *from,
     BdrvChild *c, *next, *to_c;
 
     QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
+        if (c->role->stay_at_node) {
+            continue;
+        }
         if (c->role == &child_backing) {
-            /* @from is generally not allowed to be a backing file, except for
-             * when @to is the overlay. In that case, @from may not be replaced
-             * by @to as @to's backing node. */
+            /* If @from is a backing file of @to, ignore the child to avoid
+             * creating a loop. We only want to change the pointer of other
+             * parents. */
             QLIST_FOREACH(to_c, &to->children, next) {
                 if (to_c == c) {
                     break;
@@ -2479,9 +2909,10 @@ static void change_parent_backing_link(BlockDriverState *from,
             }
         }
 
-        assert(c->role != &child_backing);
         bdrv_ref(to);
-        bdrv_replace_child(c, to);
+        /* FIXME Are we sure that bdrv_replace_child() can't run into
+         * &error_abort because of permissions? */
+        bdrv_replace_child(c, to, true);
         bdrv_unref(from);
     }
 }
@@ -2502,19 +2933,25 @@ static void change_parent_backing_link(BlockDriverState *from,
  * parents of bs_top after bdrv_append() returns. If the caller needs to keep a
  * reference of its own, it must call bdrv_ref().
  */
-void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
+                 Error **errp)
 {
-    assert(!bdrv_requests_pending(bs_top));
-    assert(!bdrv_requests_pending(bs_new));
+    Error *local_err = NULL;
 
-    bdrv_ref(bs_top);
+    assert(!atomic_read(&bs_top->in_flight));
+    assert(!atomic_read(&bs_new->in_flight));
+
+    bdrv_set_backing_hd(bs_new, bs_top, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        goto out;
+    }
 
     change_parent_backing_link(bs_top, bs_new);
-    bdrv_set_backing_hd(bs_new, bs_top);
-    bdrv_unref(bs_top);
 
     /* bs_new is now referenced by its new parents, we don't need the
      * additional reference any more. */
+out:
     bdrv_unref(bs_new);
 }
 
@@ -2658,6 +3095,7 @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
                            BlockDriverState *base, const char *backing_file_str)
 {
     BlockDriverState *new_top_bs = NULL;
+    Error *local_err = NULL;
     int ret = -EIO;
 
     if (!top->drv || !base->drv) {
@@ -2690,7 +3128,13 @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
     if (ret) {
         goto exit;
     }
-    bdrv_set_backing_hd(new_top_bs, base);
+
+    bdrv_set_backing_hd(new_top_bs, base, &local_err);
+    if (local_err) {
+        ret = -EPERM;
+        error_report_err(local_err);
+        goto exit;
+    }
 
     ret = 0;
 exit:
@@ -2705,6 +3149,9 @@ int bdrv_truncate(BdrvChild *child, int64_t offset)
     BlockDriverState *bs = child->bs;
     BlockDriver *drv = bs->drv;
     int ret;
+
+    assert(child->perm & BLK_PERM_RESIZE);
+
     if (!drv)
         return -ENOMEDIUM;
     if (!drv->bdrv_truncate)

block/backup.c

@@ -618,14 +618,24 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         goto error;
     }
 
-    job = block_job_create(job_id, &backup_job_driver, bs, speed,
-                           creation_flags, cb, opaque, errp);
+    /* job->common.len is fixed, so we can't allow resize */
+    job = block_job_create(job_id, &backup_job_driver, bs,
+                           BLK_PERM_CONSISTENT_READ,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
+                           BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD,
+                           speed, creation_flags, cb, opaque, errp);
     if (!job) {
         goto error;
     }
 
-    job->target = blk_new();
-    blk_insert_bs(job->target, target);
+    /* The target must match the source in size, so no resize here either */
+    job->target = blk_new(BLK_PERM_WRITE,
+                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
+                          BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD);
+    ret = blk_insert_bs(job->target, target, errp);
+    if (ret < 0) {
+        goto error;
+    }
 
     job->on_source_error = on_source_error;
     job->on_target_error = on_target_error;
@@ -652,7 +662,9 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
     }
 
-    block_job_add_bdrv(&job->common, target);
+    /* Required permissions are already taken with target's blk_new() */
+    block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
+                       &error_abort);
     job->common.len = len;
     block_job_txn_add_job(txn, &job->common);
 

block/blkdebug.c

@@ -734,6 +734,8 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_file_open         = blkdebug_open,
     .bdrv_close             = blkdebug_close,
     .bdrv_reopen_prepare    = blkdebug_reopen_prepare,
+    .bdrv_child_perm        = bdrv_filter_default_perms,
+
     .bdrv_getlength         = blkdebug_getlength,
     .bdrv_truncate          = blkdebug_truncate,
     .bdrv_refresh_filename  = blkdebug_refresh_filename,

block/blkreplay.c

@@ -137,6 +137,7 @@ static BlockDriver bdrv_blkreplay = {
 
     .bdrv_file_open         = blkreplay_open,
     .bdrv_close             = blkreplay_close,
+    .bdrv_child_perm        = bdrv_filter_default_perms,
     .bdrv_getlength         = blkreplay_getlength,
 
     .bdrv_co_preadv         = blkreplay_co_preadv,

block/blkverify.c

@@ -320,6 +320,7 @@ static BlockDriver bdrv_blkverify = {
     .bdrv_parse_filename              = blkverify_parse_filename,
     .bdrv_file_open                   = blkverify_open,
     .bdrv_close                       = blkverify_close,
+    .bdrv_child_perm                  = bdrv_filter_default_perms,
     .bdrv_getlength                   = blkverify_getlength,
     .bdrv_refresh_filename            = blkverify_refresh_filename,
 

block/block-backend.c

@@ -59,6 +59,9 @@ struct BlockBackend {
     bool iostatus_enabled;
     BlockDeviceIoStatus iostatus;
 
+    uint64_t perm;
+    uint64_t shared_perm;
+
     bool allow_write_beyond_eof;
 
     NotifierList remove_bs_notifiers, insert_bs_notifiers;
@@ -77,6 +80,7 @@ static const AIOCBInfo block_backend_aiocb_info = {
 
 static void drive_info_del(DriveInfo *dinfo);
 static BlockBackend *bdrv_first_blk(BlockDriverState *bs);
+static char *blk_get_attached_dev_id(BlockBackend *blk);
 
 /* All BlockBackends */
 static QTAILQ_HEAD(, BlockBackend) block_backends =
@@ -99,6 +103,25 @@ static void blk_root_drained_end(BdrvChild *child);
 static void blk_root_change_media(BdrvChild *child, bool load);
 static void blk_root_resize(BdrvChild *child);
 
+static char *blk_root_get_parent_desc(BdrvChild *child)
+{
+    BlockBackend *blk = child->opaque;
+    char *dev_id;
+
+    if (blk->name) {
+        return g_strdup(blk->name);
+    }
+
+    dev_id = blk_get_attached_dev_id(blk);
+    if (*dev_id) {
+        return dev_id;
+    } else {
+        /* TODO Callback into the BB owner for something more detailed */
+        g_free(dev_id);
+        return g_strdup("a block device");
+    }
+}
+
 static const char *blk_root_get_name(BdrvChild *child)
 {
     return blk_name(child->opaque);
@@ -110,6 +133,7 @@ static const BdrvChildRole child_root = {
     .change_media       = blk_root_change_media,
     .resize             = blk_root_resize,
     .get_name           = blk_root_get_name,
+    .get_parent_desc    = blk_root_get_parent_desc,
 
     .drained_begin      = blk_root_drained_begin,
     .drained_end        = blk_root_drained_end,
@@ -117,15 +141,23 @@ static const BdrvChildRole child_root = {
 
 /*
  * Create a new BlockBackend with a reference count of one.
- * Store an error through @errp on failure, unless it's null.
+ *
+ * @perm is a bitmasks of BLK_PERM_* constants which describes the permissions
+ * to request for a block driver node that is attached to this BlockBackend.
+ * @shared_perm is a bitmask which describes which permissions may be granted
+ * to other users of the attached node.
+ * Both sets of permissions can be changed later using blk_set_perm().
+ *
  * Return the new BlockBackend on success, null on failure.
  */
-BlockBackend *blk_new(void)
+BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm)
 {
     BlockBackend *blk;
 
     blk = g_new0(BlockBackend, 1);
     blk->refcnt = 1;
+    blk->perm = perm;
+    blk->shared_perm = shared_perm;
     blk_set_enable_write_cache(blk, true);
 
     qemu_co_queue_init(&blk->public.throttled_reqs[0]);
@@ -155,15 +187,33 @@ BlockBackend *blk_new_open(const char *filename, const char *reference,
 {
     BlockBackend *blk;
     BlockDriverState *bs;
+    uint64_t perm;
 
-    blk = blk_new();
+    /* blk_new_open() is mainly used in .bdrv_create implementations and the
+     * tools where sharing isn't a concern because the BDS stays private, so we
+     * just request permission according to the flags.
+     *
+     * The exceptions are xen_disk and blockdev_init(); in these cases, the
+     * caller of blk_new_open() doesn't make use of the permissions, but they
+     * shouldn't hurt either. We can still share everything here because the
+     * guest devices will add their own blockers if they can't share. */
+    perm = BLK_PERM_CONSISTENT_READ;
+    if (flags & BDRV_O_RDWR) {
+        perm |= BLK_PERM_WRITE;
+    }
+    if (flags & BDRV_O_RESIZE) {
+        perm |= BLK_PERM_RESIZE;
+    }
+
+    blk = blk_new(perm, BLK_PERM_ALL);
     bs = bdrv_open(filename, reference, options, flags, errp);
     if (!bs) {
         blk_unref(blk);
         return NULL;
     }
 
-    blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk);
+    blk->root = bdrv_root_attach_child(bs, "root", &child_root,
+                                       perm, BLK_PERM_ALL, blk, &error_abort);
 
     return blk;
 }
@@ -495,16 +545,49 @@ void blk_remove_bs(BlockBackend *blk)
 /*
  * Associates a new BlockDriverState with @blk.
  */
-void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs)
+int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
 {
+    blk->root = bdrv_root_attach_child(bs, "root", &child_root,
+                                       blk->perm, blk->shared_perm, blk, errp);
+    if (blk->root == NULL) {
+        return -EPERM;
+    }
     bdrv_ref(bs);
-    blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk);
 
     notifier_list_notify(&blk->insert_bs_notifiers, blk);
     if (blk->public.throttle_state) {
         throttle_timers_attach_aio_context(
             &blk->public.throttle_timers, bdrv_get_aio_context(bs));
     }
+
+    return 0;
+}
+
+/*
+ * Sets the permission bitmasks that the user of the BlockBackend needs.
+ */
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+                 Error **errp)
+{
+    int ret;
+
+    if (blk->root) {
+        ret = bdrv_child_try_set_perm(blk->root, perm, shared_perm, errp);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    blk->perm = perm;
+    blk->shared_perm = shared_perm;
+
+    return 0;
+}
+
+void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
+{
+    *perm = blk->perm;
+    *shared_perm = blk->shared_perm;
 }
 
 static int blk_do_attach_dev(BlockBackend *blk, void *dev)
@@ -553,6 +636,7 @@ void blk_detach_dev(BlockBackend *blk, void *dev)
     blk->dev_ops = NULL;
     blk->dev_opaque = NULL;
     blk->guest_block_size = 512;
+    blk_set_perm(blk, 0, BLK_PERM_ALL, &error_abort);
     blk_unref(blk);
 }
 
@@ -620,19 +704,29 @@ void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
 
 /*
  * Notify @blk's attached device model of media change.
- * If @load is true, notify of media load.
- * Else, notify of media eject.
+ *
+ * If @load is true, notify of media load. This action can fail, meaning that
+ * the medium cannot be loaded. @errp is set then.
+ *
+ * If @load is false, notify of media eject. This can never fail.
+ *
  * Also send DEVICE_TRAY_MOVED events as appropriate.
  */
-void blk_dev_change_media_cb(BlockBackend *blk, bool load)
+void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp)
 {
     if (blk->dev_ops && blk->dev_ops->change_media_cb) {
         bool tray_was_open, tray_is_open;
+        Error *local_err = NULL;
 
         assert(!blk->legacy_dev);
 
         tray_was_open = blk_dev_is_tray_open(blk);
-        blk->dev_ops->change_media_cb(blk->dev_opaque, load);
+        blk->dev_ops->change_media_cb(blk->dev_opaque, load, &local_err);
+        if (local_err) {
+            assert(load == true);
+            error_propagate(errp, local_err);
+            return;
+        }
         tray_is_open = blk_dev_is_tray_open(blk);
 
         if (tray_was_open != tray_is_open) {
@@ -646,7 +740,7 @@ void blk_dev_change_media_cb(BlockBackend *blk, bool load)
 
 static void blk_root_change_media(BdrvChild *child, bool load)
 {
-    blk_dev_change_media_cb(child->opaque, load);
+    blk_dev_change_media_cb(child->opaque, load, NULL);
 }
 
 /*

block/bochs.c

@@ -293,6 +293,7 @@ static BlockDriver bdrv_bochs = {
     .instance_size	= sizeof(BDRVBochsState),
     .bdrv_probe		= bochs_probe,
     .bdrv_open		= bochs_open,
+    .bdrv_child_perm     = bdrv_format_default_perms,
     .bdrv_refresh_limits = bochs_refresh_limits,
     .bdrv_co_preadv = bochs_co_preadv,
     .bdrv_close		= bochs_close,

block/cloop.c

@@ -290,6 +290,7 @@ static BlockDriver bdrv_cloop = {
     .instance_size  = sizeof(BDRVCloopState),
     .bdrv_probe     = cloop_probe,
     .bdrv_open      = cloop_open,
+    .bdrv_child_perm     = bdrv_format_default_perms,
     .bdrv_refresh_limits = cloop_refresh_limits,
     .bdrv_co_preadv = cloop_co_preadv,
     .bdrv_close     = cloop_close,

block/commit.c

@@ -36,6 +36,7 @@ typedef struct CommitBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *active;
+    BlockDriverState *commit_top_bs;
     BlockBackend *top;
     BlockBackend *base;
     BlockdevOnError on_error;
@@ -83,12 +84,23 @@ static void commit_complete(BlockJob *job, void *opaque)
     BlockDriverState *active = s->active;
     BlockDriverState *top = blk_bs(s->top);
     BlockDriverState *base = blk_bs(s->base);
-    BlockDriverState *overlay_bs = bdrv_find_overlay(active, top);
+    BlockDriverState *overlay_bs = bdrv_find_overlay(active, s->commit_top_bs);
     int ret = data->ret;
+    bool remove_commit_top_bs = false;
+
+    /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
+     * the normal backing chain can be restored. */
+    blk_unref(s->base);
 
     if (!block_job_is_cancelled(&s->common) && ret == 0) {
         /* success */
-        ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
+        ret = bdrv_drop_intermediate(active, s->commit_top_bs, base,
+                                     s->backing_file_str);
+    } else if (overlay_bs) {
+        /* XXX Can (or should) we somehow keep 'consistent read' blocked even
+         * after the failed/cancelled commit job is gone? If we already wrote
+         * something to base, the intermediate images aren't valid any more. */
+        remove_commit_top_bs = true;
     }
 
     /* restore base open flags here if appropriate (e.g., change the base back
@@ -102,9 +114,15 @@ static void commit_complete(BlockJob *job, void *opaque)
     }
     g_free(s->backing_file_str);
     blk_unref(s->top);
-    blk_unref(s->base);
     block_job_completed(&s->common, ret);
     g_free(data);
+
+    /* If bdrv_drop_intermediate() didn't already do that, remove the commit
+     * filter driver from the backing chain. Do this as the final step so that
+     * the 'consistent read' permission can be granted.  */
+    if (remove_commit_top_bs) {
+        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+    }
 }
 
 static void coroutine_fn commit_run(void *opaque)
@@ -208,10 +226,38 @@ static const BlockJobDriver commit_job_driver = {
     .start         = commit_run,
 };
 
+static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static void bdrv_commit_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                       const BdrvChildRole *role,
+                                       uint64_t perm, uint64_t shared,
+                                       uint64_t *nperm, uint64_t *nshared)
+{
+    *nperm = 0;
+    *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_commit_top = {
+    .format_name        = "commit_top",
+    .bdrv_co_preadv     = bdrv_commit_top_preadv,
+    .bdrv_close         = bdrv_commit_top_close,
+    .bdrv_child_perm    = bdrv_commit_top_child_perm,
+};
+
 void commit_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *base, BlockDriverState *top, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
-                  Error **errp)
+                  const char *filter_node_name, Error **errp)
 {
     CommitBlockJob *s;
     BlockReopenQueue *reopen_queue = NULL;
@@ -219,7 +265,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     int orig_base_flags;
     BlockDriverState *iter;
     BlockDriverState *overlay_bs;
+    BlockDriverState *commit_top_bs = NULL;
     Error *local_err = NULL;
+    int ret;
 
     assert(top != bs);
     if (top == base) {
@@ -234,8 +282,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    s = block_job_create(job_id, &commit_job_driver, bs, speed,
-                         BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+    s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL,
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
     if (!s) {
         return;
     }
@@ -256,30 +304,70 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err);
         if (local_err != NULL) {
             error_propagate(errp, local_err);
-            block_job_unref(&s->common);
-            return;
+            goto fail;
         }
     }
 
+    /* Insert commit_top block node above top, so we can block consistent read
+     * on the backing chain below it */
+    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
+                                         errp);
+    if (commit_top_bs == NULL) {
+        goto fail;
+    }
+
+    bdrv_set_backing_hd(commit_top_bs, top, &error_abort);
+    bdrv_set_backing_hd(overlay_bs, commit_top_bs, &error_abort);
+
+    s->commit_top_bs = commit_top_bs;
+    bdrv_unref(commit_top_bs);
 
     /* Block all nodes between top and base, because they will
      * disappear from the chain after this operation. */
     assert(bdrv_chain_contains(top, base));
-    for (iter = top; iter != backing_bs(base); iter = backing_bs(iter)) {
-        block_job_add_bdrv(&s->common, iter);
+    for (iter = top; iter != base; iter = backing_bs(iter)) {
+        /* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
+         * at s->base (if writes are blocked for a node, they are also blocked
+         * for its backing file). The other options would be a second filter
+         * driver above s->base. */
+        ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                                 BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                 errp);
+        if (ret < 0) {
+            goto fail;
+        }
     }
+
+    ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
+    if (ret < 0) {
+        goto fail;
+    }
+
     /* overlay_bs must be blocked because it needs to be modified to
-     * update the backing image string, but if it's the root node then
-     * don't block it again */
-    if (bs != overlay_bs) {
-        block_job_add_bdrv(&s->common, overlay_bs);
+     * update the backing image string. */
+    ret = block_job_add_bdrv(&s->common, "overlay of top", overlay_bs,
+                             BLK_PERM_GRAPH_MOD, BLK_PERM_ALL, errp);
+    if (ret < 0) {
+        goto fail;
     }
 
-    s->base = blk_new();
-    blk_insert_bs(s->base, base);
+    s->base = blk_new(BLK_PERM_CONSISTENT_READ
+                      | BLK_PERM_WRITE
+                      | BLK_PERM_RESIZE,
+                      BLK_PERM_CONSISTENT_READ
+                      | BLK_PERM_GRAPH_MOD
+                      | BLK_PERM_WRITE_UNCHANGED);
+    ret = blk_insert_bs(s->base, base, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
-    s->top = blk_new();
-    blk_insert_bs(s->top, top);
+    /* Required permissions are already taken with block_job_add_bdrv() */
+    s->top = blk_new(0, BLK_PERM_ALL);
+    blk_insert_bs(s->top, top, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
     s->active = bs;
 
@@ -292,6 +380,19 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 
     trace_commit_start(bs, base, top, s);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (s->base) {
+        blk_unref(s->base);
+    }
+    if (s->top) {
+        blk_unref(s->top);
+    }
+    if (commit_top_bs) {
+        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+    }
+    block_job_unref(&s->common);
 }
 
 
@@ -301,11 +402,14 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 int bdrv_commit(BlockDriverState *bs)
 {
     BlockBackend *src, *backing;
+    BlockDriverState *backing_file_bs = NULL;
+    BlockDriverState *commit_top_bs = NULL;
     BlockDriver *drv = bs->drv;
     int64_t sector, total_sectors, length, backing_length;
     int n, ro, open_flags;
     int ret = 0;
     uint8_t *buf = NULL;
+    Error *local_err = NULL;
 
     if (!drv)
         return -ENOMEDIUM;
@@ -328,11 +432,33 @@ int bdrv_commit(BlockDriverState *bs)
         }
     }
 
-    src = blk_new();
-    blk_insert_bs(src, bs);
+    src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
+    backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
 
-    backing = blk_new();
-    blk_insert_bs(backing, bs->backing->bs);
+    ret = blk_insert_bs(src, bs, &local_err);
+    if (ret < 0) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
+
+    /* Insert commit_top block node above backing, so we can write to it */
+    backing_file_bs = backing_bs(bs);
+
+    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
+                                         &local_err);
+    if (commit_top_bs == NULL) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
+
+    bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
+    bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
+
+    ret = blk_insert_bs(backing, backing_file_bs, &local_err);
+    if (ret < 0) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
 
     length = blk_getlength(src);
     if (length < 0) {
@@ -404,8 +530,12 @@ int bdrv_commit(BlockDriverState *bs)
 ro_cleanup:
     qemu_vfree(buf);
 
-    blk_unref(src);
     blk_unref(backing);
+    if (backing_file_bs) {
+        bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
+    }
+    bdrv_unref(commit_top_bs);
+    blk_unref(src);
 
     if (ro) {
         /* ignoring error return here */

block/crypto.c

@@ -628,6 +628,7 @@ BlockDriver bdrv_crypto_luks = {
     .bdrv_probe         = block_crypto_probe_luks,
     .bdrv_open          = block_crypto_open_luks,
     .bdrv_close         = block_crypto_close,
+    .bdrv_child_perm    = bdrv_format_default_perms,
     .bdrv_create        = block_crypto_create_luks,
     .bdrv_truncate      = block_crypto_truncate,
     .create_opts        = &block_crypto_create_opts_luks,

block/curl.c

@@ -135,6 +135,7 @@ typedef struct BDRVCURLState {
     char *cookie;
     bool accept_range;
     AioContext *aio_context;
+    QemuMutex mutex;
     char *username;
     char *password;
     char *proxyusername;
@@ -333,6 +334,7 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
     return FIND_RET_NONE;
 }
 
+/* Called with s->mutex held.  */
 static void curl_multi_check_completion(BDRVCURLState *s)
 {
     int msgs_in_queue;
@@ -374,7 +376,9 @@ static void curl_multi_check_completion(BDRVCURLState *s)
                         continue;
                     }
 
+                    qemu_mutex_unlock(&s->mutex);
                     acb->common.cb(acb->common.opaque, -EPROTO);
+                    qemu_mutex_lock(&s->mutex);
                     qemu_aio_unref(acb);
                     state->acb[i] = NULL;
                 }
@@ -386,6 +390,7 @@ static void curl_multi_check_completion(BDRVCURLState *s)
     }
 }
 
+/* Called with s->mutex held.  */
 static void curl_multi_do_locked(CURLState *s)
 {
     CURLSocket *socket, *next_socket;
@@ -409,19 +414,19 @@ static void curl_multi_do(void *arg)
 {
     CURLState *s = (CURLState *)arg;
 
-    aio_context_acquire(s->s->aio_context);
+    qemu_mutex_lock(&s->s->mutex);
     curl_multi_do_locked(s);
-    aio_context_release(s->s->aio_context);
+    qemu_mutex_unlock(&s->s->mutex);
 }
 
 static void curl_multi_read(void *arg)
 {
     CURLState *s = (CURLState *)arg;
 
-    aio_context_acquire(s->s->aio_context);
+    qemu_mutex_lock(&s->s->mutex);
     curl_multi_do_locked(s);
     curl_multi_check_completion(s->s);
-    aio_context_release(s->s->aio_context);
+    qemu_mutex_unlock(&s->s->mutex);
 }
 
 static void curl_multi_timeout_do(void *arg)
@@ -434,11 +439,11 @@ static void curl_multi_timeout_do(void *arg)
         return;
     }
 
-    aio_context_acquire(s->aio_context);
+    qemu_mutex_lock(&s->mutex);
     curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 
     curl_multi_check_completion(s);
-    aio_context_release(s->aio_context);
+    qemu_mutex_unlock(&s->mutex);
 #else
     abort();
 #endif
@@ -771,6 +776,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
+    qemu_mutex_init(&s->mutex);
     curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
 
     qemu_opts_del(opts);
@@ -801,12 +807,11 @@ static void curl_readv_bh_cb(void *p)
     CURLAIOCB *acb = p;
     BlockDriverState *bs = acb->common.bs;
     BDRVCURLState *s = bs->opaque;
-    AioContext *ctx = bdrv_get_aio_context(bs);
 
     size_t start = acb->sector_num * BDRV_SECTOR_SIZE;
     size_t end;
 
-    aio_context_acquire(ctx);
+    qemu_mutex_lock(&s->mutex);
 
     // In case we have the requested data already (e.g. read-ahead),
     // we can just call the callback and be done.
@@ -854,7 +859,7 @@ static void curl_readv_bh_cb(void *p)
     curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 
 out:
-    aio_context_release(ctx);
+    qemu_mutex_unlock(&s->mutex);
     if (ret != -EINPROGRESS) {
         acb->common.cb(acb->common.opaque, ret);
         qemu_aio_unref(acb);
@@ -883,6 +888,7 @@ static void curl_close(BlockDriverState *bs)
 
     DPRINTF("CURL: Close\n");
     curl_detach_aio_context(bs);
+    qemu_mutex_destroy(&s->mutex);
 
     g_free(s->cookie);
     g_free(s->url);

block/dmg.c

@@ -697,6 +697,7 @@ static BlockDriver bdrv_dmg = {
     .bdrv_probe     = dmg_probe,
     .bdrv_open      = dmg_open,
     .bdrv_refresh_limits = dmg_refresh_limits,
+    .bdrv_child_perm     = bdrv_format_default_perms,
     .bdrv_co_preadv = dmg_co_preadv,
     .bdrv_close     = dmg_close,
 };

block/io.c

@@ -925,9 +925,11 @@ bdrv_driver_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
     return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov);
 }
 
-static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
+static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
         int64_t offset, unsigned int bytes, QEMUIOVector *qiov)
 {
+    BlockDriverState *bs = child->bs;
+
     /* Perform I/O through a temporary buffer so that users who scribble over
      * their read buffer while the operation is in progress do not end up
      * modifying the image file.  This is critical for zero-copy guest I/O
@@ -943,6 +945,8 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
     size_t skip_bytes;
     int ret;
 
+    assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
+
     /* Cover entire cluster so no additional backing file I/O is required when
      * allocating cluster in the image file.
      */
@@ -1001,10 +1005,11 @@ err:
  * handles copy on read, zeroing after EOF, and fragmentation of large
  * reads; any other features must be implemented by the caller.
  */
-static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
+static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
     BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
     int64_t align, QEMUIOVector *qiov, int flags)
 {
+    BlockDriverState *bs = child->bs;
     int64_t total_bytes, max_bytes;
     int ret = 0;
     uint64_t bytes_remaining = bytes;
@@ -1050,7 +1055,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
         }
 
         if (!ret || pnum != nb_sectors) {
-            ret = bdrv_co_do_copy_on_readv(bs, offset, bytes, qiov);
+            ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov);
             goto out;
         }
     }
@@ -1158,7 +1163,7 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child,
     }
 
     tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ);
-    ret = bdrv_aligned_preadv(bs, &req, offset, bytes, align,
+    ret = bdrv_aligned_preadv(child, &req, offset, bytes, align,
                               use_local_qiov ? &local_qiov : qiov,
                               flags);
     tracked_request_end(&req);
@@ -1306,10 +1311,11 @@ fail:
  * Forwards an already correctly aligned write request to the BlockDriver,
  * after possibly fragmenting it.
  */
-static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
+static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
     BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
     int64_t align, QEMUIOVector *qiov, int flags)
 {
+    BlockDriverState *bs = child->bs;
     BlockDriver *drv = bs->drv;
     bool waited;
     int ret;
@@ -1332,6 +1338,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     assert(!waited || !req->serialising);
     assert(req->overlap_offset <= offset);
     assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
+    assert(child->perm & BLK_PERM_WRITE);
+    assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
 
     ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
 
@@ -1397,12 +1405,13 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     return ret;
 }
 
-static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
+static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
                                                 int64_t offset,
                                                 unsigned int bytes,
                                                 BdrvRequestFlags flags,
                                                 BdrvTrackedRequest *req)
 {
+    BlockDriverState *bs = child->bs;
     uint8_t *buf = NULL;
     QEMUIOVector local_qiov;
     struct iovec iov;
@@ -1430,7 +1439,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         mark_request_serialising(req, align);
         wait_serialising_requests(req);
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
-        ret = bdrv_aligned_preadv(bs, req, offset & ~(align - 1), align,
+        ret = bdrv_aligned_preadv(child, req, offset & ~(align - 1), align,
                                   align, &local_qiov, 0);
         if (ret < 0) {
             goto fail;
@@ -1438,7 +1447,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
 
         memset(buf + head_padding_bytes, 0, zero_bytes);
-        ret = bdrv_aligned_pwritev(bs, req, offset & ~(align - 1), align,
+        ret = bdrv_aligned_pwritev(child, req, offset & ~(align - 1), align,
                                    align, &local_qiov,
                                    flags & ~BDRV_REQ_ZERO_WRITE);
         if (ret < 0) {
@@ -1452,7 +1461,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
     if (bytes >= align) {
         /* Write the aligned part in the middle. */
         uint64_t aligned_bytes = bytes & ~(align - 1);
-        ret = bdrv_aligned_pwritev(bs, req, offset, aligned_bytes, align,
+        ret = bdrv_aligned_pwritev(child, req, offset, aligned_bytes, align,
                                    NULL, flags);
         if (ret < 0) {
             goto fail;
@@ -1468,7 +1477,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         mark_request_serialising(req, align);
         wait_serialising_requests(req);
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
-        ret = bdrv_aligned_preadv(bs, req, offset, align,
+        ret = bdrv_aligned_preadv(child, req, offset, align,
                                   align, &local_qiov, 0);
         if (ret < 0) {
             goto fail;
@@ -1476,7 +1485,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
 
         memset(buf, 0, bytes);
-        ret = bdrv_aligned_pwritev(bs, req, offset, align, align,
+        ret = bdrv_aligned_pwritev(child, req, offset, align, align,
                                    &local_qiov, flags & ~BDRV_REQ_ZERO_WRITE);
     }
 fail:
@@ -1523,7 +1532,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
     tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_WRITE);
 
     if (!qiov) {
-        ret = bdrv_co_do_zero_pwritev(bs, offset, bytes, flags, &req);
+        ret = bdrv_co_do_zero_pwritev(child, offset, bytes, flags, &req);
         goto out;
     }
 
@@ -1542,7 +1551,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
         qemu_iovec_init_external(&head_qiov, &head_iov, 1);
 
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
-        ret = bdrv_aligned_preadv(bs, &req, offset & ~(align - 1), align,
+        ret = bdrv_aligned_preadv(child, &req, offset & ~(align - 1), align,
                                   align, &head_qiov, 0);
         if (ret < 0) {
             goto fail;
@@ -1584,8 +1593,8 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
         qemu_iovec_init_external(&tail_qiov, &tail_iov, 1);
 
         bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
-        ret = bdrv_aligned_preadv(bs, &req, (offset + bytes) & ~(align - 1), align,
-                                  align, &tail_qiov, 0);
+        ret = bdrv_aligned_preadv(child, &req, (offset + bytes) & ~(align - 1),
+                                  align, align, &tail_qiov, 0);
         if (ret < 0) {
             goto fail;
         }
@@ -1603,7 +1612,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
         bytes = ROUND_UP(bytes, align);
     }
 
-    ret = bdrv_aligned_pwritev(bs, &req, offset, bytes, align,
+    ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align,
                                use_local_qiov ? &local_qiov : qiov,
                                flags);
 

block/iscsi.c

@@ -58,6 +58,7 @@ typedef struct IscsiLun {
     int events;
     QEMUTimer *nop_timer;
     QEMUTimer *event_timer;
+    QemuMutex mutex;
     struct scsi_inquiry_logical_block_provisioning lbp;
     struct scsi_inquiry_block_limits bl;
     unsigned char *zeroblock;
@@ -252,6 +253,7 @@ static int iscsi_translate_sense(struct scsi_sense *sense)
     return ret;
 }
 
+/* Called (via iscsi_service) with QemuMutex held.  */
 static void
 iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                         void *command_data, void *opaque)
@@ -352,6 +354,7 @@ static const AIOCBInfo iscsi_aiocb_info = {
 static void iscsi_process_read(void *arg);
 static void iscsi_process_write(void *arg);
 
+/* Called with QemuMutex held.  */
 static void
 iscsi_set_events(IscsiLun *iscsilun)
 {
@@ -395,10 +398,10 @@ iscsi_process_read(void *arg)
     IscsiLun *iscsilun = arg;
     struct iscsi_context *iscsi = iscsilun->iscsi;
 
-    aio_context_acquire(iscsilun->aio_context);
+    qemu_mutex_lock(&iscsilun->mutex);
     iscsi_service(iscsi, POLLIN);
     iscsi_set_events(iscsilun);
-    aio_context_release(iscsilun->aio_context);
+    qemu_mutex_unlock(&iscsilun->mutex);
 }
 
 static void
@@ -407,10 +410,10 @@ iscsi_process_write(void *arg)
     IscsiLun *iscsilun = arg;
     struct iscsi_context *iscsi = iscsilun->iscsi;
 
-    aio_context_acquire(iscsilun->aio_context);
+    qemu_mutex_lock(&iscsilun->mutex);
     iscsi_service(iscsi, POLLOUT);
     iscsi_set_events(iscsilun);
-    aio_context_release(iscsilun->aio_context);
+    qemu_mutex_unlock(&iscsilun->mutex);
 }
 
 static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun)
@@ -589,6 +592,7 @@ iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
     uint64_t lba;
     uint32_t num_sectors;
     bool fua = flags & BDRV_REQ_FUA;
+    int r = 0;
 
     if (fua) {
         assert(iscsilun->dpofua);
@@ -604,6 +608,7 @@ iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
     lba = sector_qemu2lun(sector_num, iscsilun);
     num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
     iscsi_co_init_iscsitask(iscsilun, &iTask);
+    qemu_mutex_lock(&iscsilun->mutex);
 retry:
     if (iscsilun->use_16_for_rw) {
 #if LIBISCSI_API_VERSION >= (20160603)
@@ -640,7 +645,9 @@ retry:
 #endif
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
         qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
     }
 
     if (iTask.task != NULL) {
@@ -655,12 +662,15 @@ retry:
 
     if (iTask.status != SCSI_STATUS_GOOD) {
         iscsi_allocmap_set_invalid(iscsilun, sector_num, nb_sectors);
-        return iTask.err_code;
+        r = iTask.err_code;
+        goto out_unlock;
     }
 
     iscsi_allocmap_set_allocated(iscsilun, sector_num, nb_sectors);
 
-    return 0;
+out_unlock:
+    qemu_mutex_unlock(&iscsilun->mutex);
+    return r;
 }
 
 
@@ -693,18 +703,21 @@ static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
         goto out;
     }
 
+    qemu_mutex_lock(&iscsilun->mutex);
 retry:
     if (iscsi_get_lba_status_task(iscsilun->iscsi, iscsilun->lun,
                                   sector_qemu2lun(sector_num, iscsilun),
                                   8 + 16, iscsi_co_generic_cb,
                                   &iTask) == NULL) {
         ret = -ENOMEM;
-        goto out;
+        goto out_unlock;
     }
 
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
         qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
     }
 
     if (iTask.do_retry) {
@@ -721,20 +734,20 @@ retry:
          * because the device is busy or the cmd is not
          * supported) we pretend all blocks are allocated
          * for backwards compatibility */
-        goto out;
+        goto out_unlock;
     }
 
     lbas = scsi_datain_unmarshall(iTask.task);
     if (lbas == NULL) {
         ret = -EIO;
-        goto out;
+        goto out_unlock;
     }
 
     lbasd = &lbas->descriptors[0];
 
     if (sector_qemu2lun(sector_num, iscsilun) != lbasd->lba) {
         ret = -EIO;
-        goto out;
+        goto out_unlock;
     }
 
     *pnum = sector_lun2qemu(lbasd->num_blocks, iscsilun);
@@ -756,6 +769,8 @@ retry:
     if (*pnum > nb_sectors) {
         *pnum = nb_sectors;
     }
+out_unlock:
+    qemu_mutex_unlock(&iscsilun->mutex);
 out:
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -818,6 +833,7 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
     num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
+    qemu_mutex_lock(&iscsilun->mutex);
 retry:
     if (iscsilun->use_16_for_rw) {
 #if LIBISCSI_API_VERSION >= (20160603)
@@ -855,7 +871,9 @@ retry:
 #endif
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
         qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
     }
 
     if (iTask.task != NULL) {
@@ -867,6 +885,7 @@ retry:
         iTask.complete = 0;
         goto retry;
     }
+    qemu_mutex_unlock(&iscsilun->mutex);
 
     if (iTask.status != SCSI_STATUS_GOOD) {
         return iTask.err_code;
@@ -881,6 +900,7 @@ static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
     struct IscsiTask iTask;
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
+    qemu_mutex_lock(&iscsilun->mutex);
 retry:
     if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
                                       0, iscsi_co_generic_cb, &iTask) == NULL) {
@@ -889,7 +909,9 @@ retry:
 
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
         qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
     }
 
     if (iTask.task != NULL) {
@@ -901,6 +923,7 @@ retry:
         iTask.complete = 0;
         goto retry;
     }
+    qemu_mutex_unlock(&iscsilun->mutex);
 
     if (iTask.status != SCSI_STATUS_GOOD) {
         return iTask.err_code;
@@ -910,6 +933,7 @@ retry:
 }
 
 #ifdef __linux__
+/* Called (via iscsi_service) with QemuMutex held.  */
 static void
 iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
                      void *command_data, void *opaque)
@@ -1034,6 +1058,7 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
     acb->task->expxferlen = acb->ioh->dxfer_len;
 
     data.size = 0;
+    qemu_mutex_lock(&iscsilun->mutex);
     if (acb->task->xfer_dir == SCSI_XFER_WRITE) {
         if (acb->ioh->iovec_count == 0) {
             data.data = acb->ioh->dxferp;
@@ -1049,6 +1074,7 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
                                  iscsi_aio_ioctl_cb,
                                  (data.size > 0) ? &data : NULL,
                                  acb) != 0) {
+        qemu_mutex_unlock(&iscsilun->mutex);
         scsi_free_scsi_task(acb->task);
         qemu_aio_unref(acb);
         return NULL;
@@ -1068,6 +1094,7 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
     }
 
     iscsi_set_events(iscsilun);
+    qemu_mutex_unlock(&iscsilun->mutex);
 
     return &acb->common;
 }
@@ -1092,6 +1119,7 @@ coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
     IscsiLun *iscsilun = bs->opaque;
     struct IscsiTask iTask;
     struct unmap_list list;
+    int r = 0;
 
     if (!is_byte_request_lun_aligned(offset, count, iscsilun)) {
         return -ENOTSUP;
@@ -1106,15 +1134,19 @@ coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
     list.num = count / iscsilun->block_size;
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
+    qemu_mutex_lock(&iscsilun->mutex);
 retry:
     if (iscsi_unmap_task(iscsilun->iscsi, iscsilun->lun, 0, 0, &list, 1,
                          iscsi_co_generic_cb, &iTask) == NULL) {
-        return -ENOMEM;
+        r = -ENOMEM;
+        goto out_unlock;
     }
 
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
         qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
     }
 
     if (iTask.task != NULL) {
@@ -1131,17 +1163,20 @@ retry:
         /* the target might fail with a check condition if it
            is not happy with the alignment of the UNMAP request
            we silently fail in this case */
-        return 0;
+        goto out_unlock;
     }
 
     if (iTask.status != SCSI_STATUS_GOOD) {
-        return iTask.err_code;
+        r = iTask.err_code;
+        goto out_unlock;
     }
 
     iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
                                count >> BDRV_SECTOR_BITS);
 
-    return 0;
+out_unlock:
+    qemu_mutex_unlock(&iscsilun->mutex);
+    return r;
 }
 
 static int
@@ -1153,6 +1188,7 @@ coroutine_fn iscsi_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
     uint64_t lba;
     uint32_t nb_blocks;
     bool use_16_for_ws = iscsilun->use_16_for_rw;
+    int r = 0;
 
     if (!is_byte_request_lun_aligned(offset, count, iscsilun)) {
         return -ENOTSUP;
@@ -1186,6 +1222,7 @@ coroutine_fn iscsi_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
         }
     }
 
+    qemu_mutex_lock(&iscsilun->mutex);
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
     if (use_16_for_ws) {
@@ -1205,7 +1242,9 @@ retry:
 
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
         qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
     }
 
     if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
@@ -1215,7 +1254,8 @@ retry:
         /* WRITE SAME is not supported by the target */
         iscsilun->has_write_same = false;
         scsi_free_scsi_task(iTask.task);
-        return -ENOTSUP;
+        r = -ENOTSUP;
+        goto out_unlock;
     }
 
     if (iTask.task != NULL) {
@@ -1231,7 +1271,8 @@ retry:
     if (iTask.status != SCSI_STATUS_GOOD) {
         iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
                                    count >> BDRV_SECTOR_BITS);
-        return iTask.err_code;
+        r = iTask.err_code;
+        goto out_unlock;
     }
 
     if (flags & BDRV_REQ_MAY_UNMAP) {
@@ -1242,7 +1283,9 @@ retry:
                                      count >> BDRV_SECTOR_BITS);
     }
 
-    return 0;
+out_unlock:
+    qemu_mutex_unlock(&iscsilun->mutex);
+    return r;
 }
 
 static void apply_chap(struct iscsi_context *iscsi, QemuOpts *opts,
@@ -1331,7 +1374,7 @@ static void iscsi_nop_timed_event(void *opaque)
 {
     IscsiLun *iscsilun = opaque;
 
-    aio_context_acquire(iscsilun->aio_context);
+    qemu_mutex_lock(&iscsilun->mutex);
     if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) {
         error_report("iSCSI: NOP timeout. Reconnecting...");
         iscsilun->request_timed_out = true;
@@ -1344,7 +1387,7 @@ static void iscsi_nop_timed_event(void *opaque)
     iscsi_set_events(iscsilun);
 
 out:
-    aio_context_release(iscsilun->aio_context);
+    qemu_mutex_unlock(&iscsilun->mutex);
 }
 
 static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
@@ -1890,6 +1933,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     scsi_free_scsi_task(task);
     task = NULL;
 
+    qemu_mutex_init(&iscsilun->mutex);
     iscsi_attach_aio_context(bs, iscsilun->aio_context);
 
     /* Guess the internal cluster (page) size of the iscsi target by the means
@@ -1935,6 +1979,7 @@ static void iscsi_close(BlockDriverState *bs)
     iscsi_destroy_context(iscsi);
     g_free(iscsilun->zeroblock);
     iscsi_allocmap_free(iscsilun);
+    qemu_mutex_destroy(&iscsilun->mutex);
     memset(iscsilun, 0, sizeof(IscsiLun));
 }
 

block/mirror.c

@@ -38,7 +38,10 @@ typedef struct MirrorBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockBackend *target;
+    BlockDriverState *mirror_top_bs;
+    BlockDriverState *source;
     BlockDriverState *base;
+
     /* The name of the graph node to replace */
     char *replaces;
     /* The BDS to replace */
@@ -327,7 +330,7 @@ static void mirror_do_zero_or_discard(MirrorBlockJob *s,
 
 static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
-    BlockDriverState *source = blk_bs(s->common.blk);
+    BlockDriverState *source = s->source;
     int64_t sector_num, first_chunk;
     uint64_t delay_ns = 0;
     /* At least the first dirty chunk is mirrored in one iteration. */
@@ -386,7 +389,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
                             nb_chunks * sectors_per_chunk);
     bitmap_set(s->in_flight_bitmap, sector_num / sectors_per_chunk, nb_chunks);
     while (nb_chunks > 0 && sector_num < end) {
-        int ret;
+        int64_t ret;
         int io_sectors, io_sectors_acct;
         BlockDriverState *file;
         enum MirrorMethod {
@@ -497,12 +500,30 @@ static void mirror_exit(BlockJob *job, void *opaque)
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
     MirrorExitData *data = opaque;
     AioContext *replace_aio_context = NULL;
-    BlockDriverState *src = blk_bs(s->common.blk);
+    BlockDriverState *src = s->source;
     BlockDriverState *target_bs = blk_bs(s->target);
+    BlockDriverState *mirror_top_bs = s->mirror_top_bs;
+    Error *local_err = NULL;
 
     /* Make sure that the source BDS doesn't go away before we called
      * block_job_completed(). */
     bdrv_ref(src);
+    bdrv_ref(mirror_top_bs);
+
+    /* We don't access the source any more. Dropping any WRITE/RESIZE is
+     * required before it could become a backing file of target_bs. */
+    bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
+                            &error_abort);
+    if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
+        BlockDriverState *backing = s->is_none_mode ? src : s->base;
+        if (backing_bs(target_bs) != backing) {
+            bdrv_set_backing_hd(target_bs, backing, &local_err);
+            if (local_err) {
+                error_report_err(local_err);
+                data->ret = -EPERM;
+            }
+        }
+    }
 
     if (s->to_replace) {
         replace_aio_context = bdrv_get_aio_context(s->to_replace);
@@ -524,10 +545,6 @@ static void mirror_exit(BlockJob *job, void *opaque)
         bdrv_drained_begin(target_bs);
         bdrv_replace_in_backing_chain(to_replace, target_bs);
         bdrv_drained_end(target_bs);
-
-        /* We just changed the BDS the job BB refers to */
-        blk_remove_bs(job->blk);
-        blk_insert_bs(job->blk, src);
     }
     if (s->to_replace) {
         bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
@@ -540,9 +557,26 @@ static void mirror_exit(BlockJob *job, void *opaque)
     g_free(s->replaces);
     blk_unref(s->target);
     s->target = NULL;
+
+    /* Remove the mirror filter driver from the graph. Before this, get rid of
+     * the blockers on the intermediate nodes so that the resulting state is
+     * valid. */
+    block_job_remove_all_bdrv(job);
+    bdrv_replace_in_backing_chain(mirror_top_bs, backing_bs(mirror_top_bs));
+
+    /* We just changed the BDS the job BB refers to (with either or both of the
+     * bdrv_replace_in_backing_chain() calls), so switch the BB back so the
+     * cleanup does the right thing. We don't need any permissions any more
+     * now. */
+    blk_remove_bs(job->blk);
+    blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
+    blk_insert_bs(job->blk, mirror_top_bs, &error_abort);
+
     block_job_completed(&s->common, data->ret);
+
     g_free(data);
     bdrv_drained_end(src);
+    bdrv_unref(mirror_top_bs);
     bdrv_unref(src);
 }
 
@@ -562,7 +596,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
 {
     int64_t sector_num, end;
     BlockDriverState *base = s->base;
-    BlockDriverState *bs = blk_bs(s->common.blk);
+    BlockDriverState *bs = s->source;
     BlockDriverState *target_bs = blk_bs(s->target);
     int ret, n;
 
@@ -644,7 +678,7 @@ static void coroutine_fn mirror_run(void *opaque)
 {
     MirrorBlockJob *s = opaque;
     MirrorExitData *data;
-    BlockDriverState *bs = blk_bs(s->common.blk);
+    BlockDriverState *bs = s->source;
     BlockDriverState *target_bs = blk_bs(s->target);
     bool need_drain = true;
     int64_t length;
@@ -876,9 +910,8 @@ static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
 static void mirror_complete(BlockJob *job, Error **errp)
 {
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-    BlockDriverState *src, *target;
+    BlockDriverState *target;
 
-    src = blk_bs(job->blk);
     target = blk_bs(s->target);
 
     if (!s->synced) {
@@ -910,6 +943,10 @@ static void mirror_complete(BlockJob *job, Error **errp)
         replace_aio_context = bdrv_get_aio_context(s->to_replace);
         aio_context_acquire(replace_aio_context);
 
+        /* TODO Translate this into permission system. Current definition of
+         * GRAPH_MOD would require to request it for the parents; they might
+         * not even be BlockDriverStates, however, so a BdrvChild can't address
+         * them. May need redefinition of GRAPH_MOD. */
         error_setg(&s->replace_blocker,
                    "block device is in use by block-job-complete");
         bdrv_op_block_all(s->to_replace, s->replace_blocker);
@@ -918,13 +955,6 @@ static void mirror_complete(BlockJob *job, Error **errp)
         aio_context_release(replace_aio_context);
     }
 
-    if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
-        BlockDriverState *backing = s->is_none_mode ? src : s->base;
-        if (backing_bs(target) != backing) {
-            bdrv_set_backing_hd(target, backing);
-        }
-    }
-
     s->should_complete = true;
     block_job_enter(&s->common);
 }
@@ -980,6 +1010,77 @@ static const BlockJobDriver commit_active_job_driver = {
     .drain                  = mirror_drain,
 };
 
+static int coroutine_fn bdrv_mirror_top_preadv(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_pwritev(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_pwritev(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_flush(BlockDriverState *bs)
+{
+    return bdrv_co_flush(bs->backing->bs);
+}
+
+static int64_t coroutine_fn bdrv_mirror_top_get_block_status(
+    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
+    BlockDriverState **file)
+{
+    *pnum = nb_sectors;
+    *file = bs->backing->bs;
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
+           (sector_num << BDRV_SECTOR_BITS);
+}
+
+static int coroutine_fn bdrv_mirror_top_pwrite_zeroes(BlockDriverState *bs,
+    int64_t offset, int count, BdrvRequestFlags flags)
+{
+    return bdrv_co_pwrite_zeroes(bs->backing, offset, count, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_pdiscard(BlockDriverState *bs,
+    int64_t offset, int count)
+{
+    return bdrv_co_pdiscard(bs->backing->bs, offset, count);
+}
+
+static void bdrv_mirror_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_mirror_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                       const BdrvChildRole *role,
+                                       uint64_t perm, uint64_t shared,
+                                       uint64_t *nperm, uint64_t *nshared)
+{
+    /* Must be able to forward guest writes to the real image */
+    *nperm = 0;
+    if (perm & BLK_PERM_WRITE) {
+        *nperm |= BLK_PERM_WRITE;
+    }
+
+    *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_mirror_top = {
+    .format_name                = "mirror_top",
+    .bdrv_co_preadv             = bdrv_mirror_top_preadv,
+    .bdrv_co_pwritev            = bdrv_mirror_top_pwritev,
+    .bdrv_co_pwrite_zeroes      = bdrv_mirror_top_pwrite_zeroes,
+    .bdrv_co_pdiscard           = bdrv_mirror_top_pdiscard,
+    .bdrv_co_flush              = bdrv_mirror_top_flush,
+    .bdrv_co_get_block_status   = bdrv_mirror_top_get_block_status,
+    .bdrv_close                 = bdrv_mirror_top_close,
+    .bdrv_child_perm            = bdrv_mirror_top_child_perm,
+};
+
 static void mirror_start_job(const char *job_id, BlockDriverState *bs,
                              int creation_flags, BlockDriverState *target,
                              const char *replaces, int64_t speed,
@@ -992,9 +1093,14 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
                              void *opaque, Error **errp,
                              const BlockJobDriver *driver,
                              bool is_none_mode, BlockDriverState *base,
-                             bool auto_complete)
+                             bool auto_complete, const char *filter_node_name)
 {
     MirrorBlockJob *s;
+    BlockDriverState *mirror_top_bs;
+    bool target_graph_mod;
+    bool target_is_backing;
+    Error *local_err = NULL;
+    int ret;
 
     if (granularity == 0) {
         granularity = bdrv_get_default_bitmap_granularity(target);
@@ -1011,14 +1117,62 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
         buf_size = DEFAULT_MIRROR_BUF_SIZE;
     }
 
-    s = block_job_create(job_id, driver, bs, speed, creation_flags,
-                         cb, opaque, errp);
-    if (!s) {
+    /* In the case of active commit, add dummy driver to provide consistent
+     * reads on the top, while disabling it in the intermediate nodes, and make
+     * the backing chain writable. */
+    mirror_top_bs = bdrv_new_open_driver(&bdrv_mirror_top, filter_node_name,
+                                         BDRV_O_RDWR, errp);
+    if (mirror_top_bs == NULL) {
+        return;
+    }
+    mirror_top_bs->total_sectors = bs->total_sectors;
+
+    /* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
+     * it alive until block_job_create() even if bs has no parent. */
+    bdrv_ref(mirror_top_bs);
+    bdrv_drained_begin(bs);
+    bdrv_append(mirror_top_bs, bs, &local_err);
+    bdrv_drained_end(bs);
+
+    if (local_err) {
+        bdrv_unref(mirror_top_bs);
+        error_propagate(errp, local_err);
         return;
     }
 
-    s->target = blk_new();
-    blk_insert_bs(s->target, target);
+    /* Make sure that the source is not resized while the job is running */
+    s = block_job_create(job_id, driver, mirror_top_bs,
+                         BLK_PERM_CONSISTENT_READ,
+                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                         BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed,
+                         creation_flags, cb, opaque, errp);
+    bdrv_unref(mirror_top_bs);
+    if (!s) {
+        goto fail;
+    }
+    s->source = bs;
+    s->mirror_top_bs = mirror_top_bs;
+
+    /* No resize for the target either; while the mirror is still running, a
+     * consistent read isn't necessarily possible. We could possibly allow
+     * writes and graph modifications, though it would likely defeat the
+     * purpose of a mirror, so leave them blocked for now.
+     *
+     * In the case of active commit, things look a bit different, though,
+     * because the target is an already populated backing file in active use.
+     * We can allow anything except resize there.*/
+    target_is_backing = bdrv_chain_contains(bs, target);
+    target_graph_mod = (backing_mode != MIRROR_LEAVE_BACKING_CHAIN);
+    s->target = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE |
+                        (target_graph_mod ? BLK_PERM_GRAPH_MOD : 0),
+                        BLK_PERM_WRITE_UNCHANGED |
+                        (target_is_backing ? BLK_PERM_CONSISTENT_READ |
+                                             BLK_PERM_WRITE |
+                                             BLK_PERM_GRAPH_MOD : 0));
+    ret = blk_insert_bs(s->target, target, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
     s->replaces = g_strdup(replaces);
     s->on_source_error = on_source_error;
@@ -1041,18 +1195,40 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    block_job_add_bdrv(&s->common, target);
+    /* Required permissions are already taken with blk_new() */
+    block_job_add_bdrv(&s->common, "target", target, 0, BLK_PERM_ALL,
+                       &error_abort);
+
     /* In commit_active_start() all intermediate nodes disappear, so
      * any jobs in them must be blocked */
-    if (bdrv_chain_contains(bs, target)) {
+    if (target_is_backing) {
         BlockDriverState *iter;
         for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
-            block_job_add_bdrv(&s->common, iter);
+            /* XXX BLK_PERM_WRITE needs to be allowed so we don't block
+             * ourselves at s->base (if writes are blocked for a node, they are
+             * also blocked for its backing file). The other options would be a
+             * second filter driver above s->base (== target). */
+            ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                                     BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                     errp);
+            if (ret < 0) {
+                goto fail;
+            }
         }
     }
 
     trace_mirror_start(bs, s, opaque);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (s) {
+        g_free(s->replaces);
+        blk_unref(s->target);
+        block_job_unref(&s->common);
+    }
+
+    bdrv_replace_in_backing_chain(mirror_top_bs, backing_bs(mirror_top_bs));
 }
 
 void mirror_start(const char *job_id, BlockDriverState *bs,
@@ -1061,7 +1237,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                   MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
-                  bool unmap, Error **errp)
+                  bool unmap, const char *filter_node_name, Error **errp)
 {
     bool is_none_mode;
     BlockDriverState *base;
@@ -1075,12 +1251,14 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
     mirror_start_job(job_id, bs, BLOCK_JOB_DEFAULT, target, replaces,
                      speed, granularity, buf_size, backing_mode,
                      on_source_error, on_target_error, unmap, NULL, NULL, errp,
-                     &mirror_job_driver, is_none_mode, base, false);
+                     &mirror_job_driver, is_none_mode, base, false,
+                     filter_node_name);
 }
 
 void commit_active_start(const char *job_id, BlockDriverState *bs,
                          BlockDriverState *base, int creation_flags,
                          int64_t speed, BlockdevOnError on_error,
+                         const char *filter_node_name,
                          BlockCompletionFunc *cb, void *opaque, Error **errp,
                          bool auto_complete)
 {
@@ -1096,7 +1274,8 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
     mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0,
                      MIRROR_LEAVE_BACKING_CHAIN,
                      on_error, on_error, true, cb, opaque, &local_err,
-                     &commit_active_job_driver, false, base, auto_complete);
+                     &commit_active_job_driver, false, base, auto_complete,
+                     filter_node_name);
     if (local_err) {
         error_propagate(errp, local_err);
         goto error_restore_flags;

block/nfs.c

@@ -54,6 +54,7 @@ typedef struct NFSClient {
     int events;
     bool has_zero_init;
     AioContext *aio_context;
+    QemuMutex mutex;
     blkcnt_t st_blocks;
     bool cache_used;
     NFSServer *server;
@@ -191,6 +192,7 @@ static void nfs_parse_filename(const char *filename, QDict *options,
 static void nfs_process_read(void *arg);
 static void nfs_process_write(void *arg);
 
+/* Called with QemuMutex held.  */
 static void nfs_set_events(NFSClient *client)
 {
     int ev = nfs_which_events(client->context);
@@ -209,20 +211,20 @@ static void nfs_process_read(void *arg)
 {
     NFSClient *client = arg;
 
-    aio_context_acquire(client->aio_context);
+    qemu_mutex_lock(&client->mutex);
     nfs_service(client->context, POLLIN);
     nfs_set_events(client);
-    aio_context_release(client->aio_context);
+    qemu_mutex_unlock(&client->mutex);
 }
 
 static void nfs_process_write(void *arg)
 {
     NFSClient *client = arg;
 
-    aio_context_acquire(client->aio_context);
+    qemu_mutex_lock(&client->mutex);
     nfs_service(client->context, POLLOUT);
     nfs_set_events(client);
-    aio_context_release(client->aio_context);
+    qemu_mutex_unlock(&client->mutex);
 }
 
 static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
@@ -242,6 +244,7 @@ static void nfs_co_generic_bh_cb(void *opaque)
     aio_co_wake(task->co);
 }
 
+/* Called (via nfs_service) with QemuMutex held.  */
 static void
 nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
                   void *private_data)
@@ -273,12 +276,15 @@ static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
     nfs_co_init_task(bs, &task);
     task.iov = iov;
 
+    qemu_mutex_lock(&client->mutex);
     if (nfs_pread_async(client->context, client->fh,
                         offset, bytes, nfs_co_generic_cb, &task) != 0) {
+        qemu_mutex_unlock(&client->mutex);
         return -ENOMEM;
     }
 
     nfs_set_events(client);
+    qemu_mutex_unlock(&client->mutex);
     while (!task.complete) {
         qemu_coroutine_yield();
     }
@@ -317,9 +323,11 @@ static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
         buf = iov->iov[0].iov_base;
     }
 
+    qemu_mutex_lock(&client->mutex);
     if (nfs_pwrite_async(client->context, client->fh,
                          offset, bytes, buf,
                          nfs_co_generic_cb, &task) != 0) {
+        qemu_mutex_unlock(&client->mutex);
         if (my_buffer) {
             g_free(buf);
         }
@@ -327,6 +335,7 @@ static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
     }
 
     nfs_set_events(client);
+    qemu_mutex_unlock(&client->mutex);
     while (!task.complete) {
         qemu_coroutine_yield();
     }
@@ -349,12 +358,15 @@ static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
 
     nfs_co_init_task(bs, &task);
 
+    qemu_mutex_lock(&client->mutex);
     if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
                         &task) != 0) {
+        qemu_mutex_unlock(&client->mutex);
         return -ENOMEM;
     }
 
     nfs_set_events(client);
+    qemu_mutex_unlock(&client->mutex);
     while (!task.complete) {
         qemu_coroutine_yield();
     }
@@ -440,6 +452,7 @@ static void nfs_file_close(BlockDriverState *bs)
 {
     NFSClient *client = bs->opaque;
     nfs_client_close(client);
+    qemu_mutex_destroy(&client->mutex);
 }
 
 static NFSServer *nfs_config(QDict *options, Error **errp)
@@ -647,6 +660,7 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
     if (ret < 0) {
         return ret;
     }
+    qemu_mutex_init(&client->mutex);
     bs->total_sectors = ret;
     ret = 0;
     return ret;
@@ -702,6 +716,7 @@ static int nfs_has_zero_init(BlockDriverState *bs)
     return client->has_zero_init;
 }
 
+/* Called (via nfs_service) with QemuMutex held.  */
 static void
 nfs_get_allocated_file_size_cb(int ret, struct nfs_context *nfs, void *data,
                                void *private_data)

block/parallels.c

@@ -488,7 +488,8 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     file = blk_new_open(filename, NULL, NULL,
-                        BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                        BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                        &local_err);
     if (file == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -762,6 +763,7 @@ static BlockDriver bdrv_parallels = {
     .bdrv_probe		= parallels_probe,
     .bdrv_open		= parallels_open,
     .bdrv_close		= parallels_close,
+    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_co_get_block_status = parallels_co_get_block_status,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_flush_to_os      = parallels_co_flush_to_os,

block/qcow.c

@@ -823,7 +823,8 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     qcow_blk = blk_new_open(filename, NULL, NULL,
-                            BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                            BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                            &local_err);
     if (qcow_blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1052,6 +1053,7 @@ static BlockDriver bdrv_qcow = {
     .bdrv_probe		= qcow_probe,
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
+    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_reopen_prepare    = qcow_reopen_prepare,
     .bdrv_create            = qcow_create,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,

block/qcow2.c

@@ -2202,7 +2202,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -2266,7 +2267,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     options = qdict_new();
     qdict_put(options, "driver", qstring_from_str("qcow2"));
     blk = blk_new_open(filename, NULL, options,
-                       BDRV_O_RDWR | BDRV_O_NO_FLUSH, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_NO_FLUSH,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -3113,6 +3115,7 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     uint64_t cluster_size = s->cluster_size;
     bool encrypt;
     int refcount_bits = s->refcount_bits;
+    Error *local_err = NULL;
     int ret;
     QemuOptDesc *desc = opts->list->desc;
     Qcow2AmendHelperCBInfo helper_cb_info;
@@ -3262,11 +3265,16 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     }
 
     if (new_size) {
-        BlockBackend *blk = blk_new();
-        blk_insert_bs(blk, bs);
+        BlockBackend *blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL);
+        ret = blk_insert_bs(blk, bs, &local_err);
+        if (ret < 0) {
+            error_report_err(local_err);
+            blk_unref(blk);
+            return ret;
+        }
+
         ret = blk_truncate(blk, new_size);
         blk_unref(blk);
-
         if (ret < 0) {
             return ret;
         }
@@ -3403,6 +3411,7 @@ BlockDriver bdrv_qcow2 = {
     .bdrv_reopen_commit   = qcow2_reopen_commit,
     .bdrv_reopen_abort    = qcow2_reopen_abort,
     .bdrv_join_options    = qcow2_join_options,
+    .bdrv_child_perm      = bdrv_format_default_perms,
     .bdrv_create        = qcow2_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = qcow2_co_get_block_status,

block/qed.c

@@ -625,7 +625,8 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -1704,6 +1705,7 @@ static BlockDriver bdrv_qed = {
     .bdrv_open                = bdrv_qed_open,
     .bdrv_close               = bdrv_qed_close,
     .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
+    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_create              = bdrv_qed_create,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = bdrv_qed_co_get_block_status,

block/quorum.c

@@ -1032,10 +1032,17 @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs,
 
     /* We can safely add the child now */
     bdrv_ref(child_bs);
-    child = bdrv_attach_child(bs, child_bs, indexstr, &child_format);
+
+    child = bdrv_attach_child(bs, child_bs, indexstr, &child_format, errp);
+    if (child == NULL) {
+        s->next_child_index--;
+        bdrv_unref(child_bs);
+        goto out;
+    }
     s->children = g_renew(BdrvChild *, s->children, s->num_children + 1);
     s->children[s->num_children++] = child;
 
+out:
     bdrv_drained_end(bs);
 }
 
@@ -1126,6 +1133,8 @@ static BlockDriver bdrv_quorum = {
     .bdrv_add_child                     = quorum_add_child,
     .bdrv_del_child                     = quorum_del_child,
 
+    .bdrv_child_perm                    = bdrv_filter_default_perms,
+
     .is_filter                          = true,
     .bdrv_recurse_is_first_non_filter   = quorum_recurse_is_first_non_filter,
 };

block/raw-format.c

@@ -467,6 +467,7 @@ BlockDriver bdrv_raw = {
     .bdrv_reopen_abort    = &raw_reopen_abort,
     .bdrv_open            = &raw_open,
     .bdrv_close           = &raw_close,
+    .bdrv_child_perm      = bdrv_filter_default_perms,
     .bdrv_create          = &raw_create,
     .bdrv_co_preadv       = &raw_co_preadv,
     .bdrv_co_pwritev      = &raw_co_pwritev,

block/replication.c

@@ -644,7 +644,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
         s->replication_state = BLOCK_REPLICATION_FAILOVER;
         commit_active_start(NULL, s->active_disk->bs, s->secondary_disk->bs,
                             BLOCK_JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT,
-                            replication_done, bs, errp, true);
+                            NULL, replication_done, bs, errp, true);
         break;
     default:
         aio_context_release(aio_context);
@@ -660,6 +660,7 @@ BlockDriver bdrv_replication = {
 
     .bdrv_open                  = replication_open,
     .bdrv_close                 = replication_close,
+    .bdrv_child_perm            = bdrv_filter_default_perms,
 
     .bdrv_getlength             = replication_getlength,
     .bdrv_co_readv              = replication_co_readv,

block/sheepdog.c

@@ -1609,7 +1609,7 @@ static int sd_prealloc(const char *filename, Error **errp)
     int ret;
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, errp);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
     if (blk == NULL) {
         ret = -EIO;
         goto out_with_err_set;

block/stream.c

@@ -68,6 +68,7 @@ static void stream_complete(BlockJob *job, void *opaque)
     StreamCompleteData *data = opaque;
     BlockDriverState *bs = blk_bs(job->blk);
     BlockDriverState *base = s->base;
+    Error *local_err = NULL;
 
     if (!block_job_is_cancelled(&s->common) && data->reached_end &&
         data->ret == 0) {
@@ -79,11 +80,19 @@ static void stream_complete(BlockJob *job, void *opaque)
             }
         }
         data->ret = bdrv_change_backing_file(bs, base_id, base_fmt);
-        bdrv_set_backing_hd(bs, base);
+        bdrv_set_backing_hd(bs, base, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            data->ret = -EPERM;
+            goto out;
+        }
     }
 
+out:
     /* Reopen the image back in read-only mode if necessary */
     if (s->bs_flags != bdrv_get_flags(bs)) {
+        /* Give up write permissions before making it read-only */
+        blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
         bdrv_reopen(bs, s->bs_flags, NULL);
     }
 
@@ -229,25 +238,35 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     BlockDriverState *iter;
     int orig_bs_flags;
 
-    s = block_job_create(job_id, &stream_job_driver, bs, speed,
-                         BLOCK_JOB_DEFAULT, NULL, NULL, errp);
-    if (!s) {
-        return;
-    }
-
     /* Make sure that the image is opened in read-write mode */
     orig_bs_flags = bdrv_get_flags(bs);
     if (!(orig_bs_flags & BDRV_O_RDWR)) {
         if (bdrv_reopen(bs, orig_bs_flags | BDRV_O_RDWR, errp) != 0) {
-            block_job_unref(&s->common);
             return;
         }
     }
 
-    /* Block all intermediate nodes between bs and base, because they
-     * will disappear from the chain after this operation */
+    /* Prevent concurrent jobs trying to modify the graph structure here, we
+     * already have our own plans. Also don't allow resize as the image size is
+     * queried only at the job start and then cached. */
+    s = block_job_create(job_id, &stream_job_driver, bs,
+                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                         BLK_PERM_GRAPH_MOD,
+                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                         BLK_PERM_WRITE,
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+    if (!s) {
+        goto fail;
+    }
+
+    /* Block all intermediate nodes between bs and base, because they will
+     * disappear from the chain after this operation. The streaming job reads
+     * every block only once, assuming that it doesn't change, so block writes
+     * and resizes. */
     for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
-        block_job_add_bdrv(&s->common, iter);
+        block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
+                           &error_abort);
     }
 
     s->base = base;
@@ -257,4 +276,10 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     s->on_error = on_error;
     trace_stream_start(bs, base, s);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (orig_bs_flags != bdrv_get_flags(bs)) {
+        bdrv_reopen(bs, s->bs_flags, NULL);
+    }
 }

block/vdi.c

@@ -763,7 +763,8 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -891,6 +892,7 @@ static BlockDriver bdrv_vdi = {
     .bdrv_open = vdi_open,
     .bdrv_close = vdi_close,
     .bdrv_reopen_prepare = vdi_reopen_prepare,
+    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_create = vdi_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = vdi_co_get_block_status,

block/vhdx.c

@@ -1859,7 +1859,8 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1983,6 +1984,7 @@ static BlockDriver bdrv_vhdx = {
     .bdrv_open              = vhdx_open,
     .bdrv_close             = vhdx_close,
     .bdrv_reopen_prepare    = vhdx_reopen_prepare,
+    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_co_readv          = vhdx_co_readv,
     .bdrv_co_writev         = vhdx_co_writev,
     .bdrv_create            = vhdx_create,

block/vmdk.c

@@ -1703,7 +1703,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -2071,7 +2072,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     new_blk = blk_new_open(filename, NULL, NULL,
-                           BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                           BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                           &local_err);
     if (new_blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -2359,6 +2361,7 @@ static BlockDriver bdrv_vmdk = {
     .bdrv_open                    = vmdk_open,
     .bdrv_check                   = vmdk_check,
     .bdrv_reopen_prepare          = vmdk_reopen_prepare,
+    .bdrv_child_perm              = bdrv_format_default_perms,
     .bdrv_co_preadv               = vmdk_co_preadv,
     .bdrv_co_pwritev              = vmdk_co_pwritev,
     .bdrv_co_pwritev_compressed   = vmdk_co_pwritev_compressed,

block/vpc.c

@@ -915,7 +915,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1067,6 +1068,7 @@ static BlockDriver bdrv_vpc = {
     .bdrv_open              = vpc_open,
     .bdrv_close             = vpc_close,
     .bdrv_reopen_prepare    = vpc_reopen_prepare,
+    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_create            = vpc_create,
 
     .bdrv_co_preadv             = vpc_co_preadv,

block/vvfat.c

@@ -3041,7 +3041,7 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
                                    &error_abort);
     *(void**) backing->opaque = s;
 
-    bdrv_set_backing_hd(s->bs, backing);
+    bdrv_set_backing_hd(s->bs, backing, &error_abort);
     bdrv_unref(backing);
 
     return 0;
@@ -3052,6 +3052,27 @@ err:
     return ret;
 }
 
+static void vvfat_child_perm(BlockDriverState *bs, BdrvChild *c,
+                             const BdrvChildRole *role,
+                             uint64_t perm, uint64_t shared,
+                             uint64_t *nperm, uint64_t *nshared)
+{
+    BDRVVVFATState *s = bs->opaque;
+
+    assert(c == s->qcow || role == &child_backing);
+
+    if (c == s->qcow) {
+        /* This is a private node, nobody should try to attach to it */
+        *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE;
+        *nshared = BLK_PERM_WRITE_UNCHANGED;
+    } else {
+        /* The backing file is there so 'commit' can use it. vvfat doesn't
+         * access it in any way. */
+        *nperm = 0;
+        *nshared = BLK_PERM_ALL;
+    }
+}
+
 static void vvfat_close(BlockDriverState *bs)
 {
     BDRVVVFATState *s = bs->opaque;
@@ -3077,6 +3098,7 @@ static BlockDriver bdrv_vvfat = {
     .bdrv_file_open         = vvfat_open,
     .bdrv_refresh_limits    = vvfat_refresh_limits,
     .bdrv_close             = vvfat_close,
+    .bdrv_child_perm        = vvfat_child_perm,
 
     .bdrv_co_preadv         = vvfat_co_preadv,
     .bdrv_co_pwritev        = vvfat_co_pwritev,

blockdev.c

@@ -52,6 +52,7 @@
 #include "sysemu/arch_init.h"
 #include "qemu/cutils.h"
 #include "qemu/help_option.h"
+#include "qemu/throttle-options.h"
 
 static QTAILQ_HEAD(, BlockDriverState) monitor_bdrv_states =
     QTAILQ_HEAD_INITIALIZER(monitor_bdrv_states);
@@ -557,7 +558,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     if ((!file || !*file) && !qdict_size(bs_opts)) {
         BlockBackendRootState *blk_rs;
 
-        blk = blk_new();
+        blk = blk_new(0, BLK_PERM_ALL);
         blk_rs = blk_get_root_state(blk);
         blk_rs->open_flags    = bdrv_flags;
         blk_rs->read_only     = read_only;
@@ -1767,6 +1768,17 @@ static void external_snapshot_prepare(BlkActionState *common,
 
     if (!state->new_bs->drv->supports_backing) {
         error_setg(errp, "The snapshot does not support backing images");
+        return;
+    }
+
+    /* This removes our old bs and adds the new bs. This is an operation that
+     * can fail, so we need to do it in .prepare; undoing it for abort is
+     * always possible. */
+    bdrv_ref(state->new_bs);
+    bdrv_append(state->new_bs, state->old_bs, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
     }
 }
 
@@ -1777,8 +1789,6 @@ static void external_snapshot_commit(BlkActionState *common)
 
     bdrv_set_aio_context(state->new_bs, state->aio_context);
 
-    /* This removes our old bs and adds the new bs */
-    bdrv_append(state->new_bs, state->old_bs);
     /* We don't need (or want) to use the transactional
      * bdrv_reopen_multiple() across all the entries at once, because we
      * don't want to abort all of them if one of them fails the reopen */
@@ -1793,7 +1803,9 @@ static void external_snapshot_abort(BlkActionState *common)
     ExternalSnapshotState *state =
                              DO_UPCAST(ExternalSnapshotState, common, common);
     if (state->new_bs) {
-        bdrv_unref(state->new_bs);
+        if (state->new_bs->backing) {
+            bdrv_replace_in_backing_chain(state->new_bs, state->old_bs);
+        }
     }
 }
 
@@ -1804,6 +1816,7 @@ static void external_snapshot_clean(BlkActionState *common)
     if (state->aio_context) {
         bdrv_drained_end(state->old_bs);
         aio_context_release(state->aio_context);
+        bdrv_unref(state->new_bs);
     }
 }
 
@@ -2310,7 +2323,7 @@ static int do_open_tray(const char *blk_name, const char *qdev_id,
     }
 
     if (!locked || force) {
-        blk_dev_change_media_cb(blk, false);
+        blk_dev_change_media_cb(blk, false, &error_abort);
     }
 
     if (locked && !force) {
@@ -2348,6 +2361,7 @@ void qmp_blockdev_close_tray(bool has_device, const char *device,
                              Error **errp)
 {
     BlockBackend *blk;
+    Error *local_err = NULL;
 
     device = has_device ? device : NULL;
     id = has_id ? id : NULL;
@@ -2371,7 +2385,11 @@ void qmp_blockdev_close_tray(bool has_device, const char *device,
         return;
     }
 
-    blk_dev_change_media_cb(blk, true);
+    blk_dev_change_media_cb(blk, true, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
 }
 
 void qmp_x_blockdev_remove_medium(bool has_device, const char *device,
@@ -2424,7 +2442,7 @@ void qmp_x_blockdev_remove_medium(bool has_device, const char *device,
          * called at all); therefore, the medium needs to be ejected here.
          * Do it after blk_remove_bs() so blk_is_inserted(blk) returns the @load
          * value passed here (i.e. false). */
-        blk_dev_change_media_cb(blk, false);
+        blk_dev_change_media_cb(blk, false, &error_abort);
     }
 
 out:
@@ -2434,7 +2452,9 @@ out:
 static void qmp_blockdev_insert_anon_medium(BlockBackend *blk,
                                             BlockDriverState *bs, Error **errp)
 {
+    Error *local_err = NULL;
     bool has_device;
+    int ret;
 
     /* For BBs without a device, we can exchange the BDS tree at will */
     has_device = blk_get_attached_dev(blk);
@@ -2454,7 +2474,10 @@ static void qmp_blockdev_insert_anon_medium(BlockBackend *blk,
         return;
     }
 
-    blk_insert_bs(blk, bs);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        return;
+    }
 
     if (!blk_dev_has_tray(blk)) {
         /* For tray-less devices, blockdev-close-tray is a no-op (or may not be
@@ -2462,7 +2485,12 @@ static void qmp_blockdev_insert_anon_medium(BlockBackend *blk,
          * slot here.
          * Do it after blk_insert_bs() so blk_is_inserted(blk) returns the @load
          * value passed here (i.e. true). */
-        blk_dev_change_media_cb(blk, true);
+        blk_dev_change_media_cb(blk, true, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            blk_remove_bs(blk);
+            return;
+        }
     }
 }
 
@@ -2889,8 +2917,11 @@ void qmp_block_resize(bool has_device, const char *device,
         goto out;
     }
 
-    blk = blk_new();
-    blk_insert_bs(blk, bs);
+    blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        goto out;
+    }
 
     /* complete all in-flight operations before resizing the device */
     bdrv_drain_all();
@@ -3013,6 +3044,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
                       bool has_top, const char *top,
                       bool has_backing_file, const char *backing_file,
                       bool has_speed, int64_t speed,
+                      bool has_filter_node_name, const char *filter_node_name,
                       Error **errp)
 {
     BlockDriverState *bs;
@@ -3028,6 +3060,9 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
     if (!has_speed) {
         speed = 0;
     }
+    if (!has_filter_node_name) {
+        filter_node_name = NULL;
+    }
 
     /* Important Note:
      *  libvirt relies on the DeviceNotFound error class in order to probe for
@@ -3102,8 +3137,8 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
             goto out;
         }
         commit_active_start(has_job_id ? job_id : NULL, bs, base_bs,
-                            BLOCK_JOB_DEFAULT, speed, on_error, NULL, NULL,
-                            &local_err, false);
+                            BLOCK_JOB_DEFAULT, speed, on_error,
+                            filter_node_name, NULL, NULL, &local_err, false);
     } else {
         BlockDriverState *overlay_bs = bdrv_find_overlay(bs, top_bs);
         if (bdrv_op_is_blocked(overlay_bs, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
@@ -3111,7 +3146,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
         }
         commit_start(has_job_id ? job_id : NULL, bs, base_bs, top_bs, speed,
                      on_error, has_backing_file ? backing_file : NULL,
-                     &local_err);
+                     filter_node_name, &local_err);
     }
     if (local_err != NULL) {
         error_propagate(errp, local_err);
@@ -3347,6 +3382,8 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
                                    bool has_on_target_error,
                                    BlockdevOnError on_target_error,
                                    bool has_unmap, bool unmap,
+                                   bool has_filter_node_name,
+                                   const char *filter_node_name,
                                    Error **errp)
 {
 
@@ -3368,6 +3405,9 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
     if (!has_unmap) {
         unmap = true;
     }
+    if (!has_filter_node_name) {
+        filter_node_name = NULL;
+    }
 
     if (granularity != 0 && (granularity < 512 || granularity > 1048576 * 64)) {
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "granularity",
@@ -3397,7 +3437,8 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
     mirror_start(job_id, bs, target,
                  has_replaces ? replaces : NULL,
                  speed, granularity, buf_size, sync, backing_mode,
-                 on_source_error, on_target_error, unmap, errp);
+                 on_source_error, on_target_error, unmap, filter_node_name,
+                 errp);
 }
 
 void qmp_drive_mirror(DriveMirror *arg, Error **errp)
@@ -3535,6 +3576,7 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
                            arg->has_on_source_error, arg->on_source_error,
                            arg->has_on_target_error, arg->on_target_error,
                            arg->has_unmap, arg->unmap,
+                           false, NULL,
                            &local_err);
     bdrv_unref(target_bs);
     error_propagate(errp, local_err);
@@ -3553,6 +3595,8 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
                          BlockdevOnError on_source_error,
                          bool has_on_target_error,
                          BlockdevOnError on_target_error,
+                         bool has_filter_node_name,
+                         const char *filter_node_name,
                          Error **errp)
 {
     BlockDriverState *bs;
@@ -3584,6 +3628,7 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
                            has_on_source_error, on_source_error,
                            has_on_target_error, on_target_error,
                            true, true,
+                           has_filter_node_name, filter_node_name,
                            &local_err);
     error_propagate(errp, local_err);
 
@@ -4007,83 +4052,11 @@ QemuOptsList qemu_common_drive_opts = {
             .name = BDRV_OPT_READ_ONLY,
             .type = QEMU_OPT_BOOL,
             .help = "open drive file as read-only",
-        },{
-            .name = "throttling.iops-total",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit total I/O operations per second",
-        },{
-            .name = "throttling.iops-read",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit read operations per second",
-        },{
-            .name = "throttling.iops-write",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit write operations per second",
-        },{
-            .name = "throttling.bps-total",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit total bytes per second",
-        },{
-            .name = "throttling.bps-read",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit read bytes per second",
-        },{
-            .name = "throttling.bps-write",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit write bytes per second",
-        },{
-            .name = "throttling.iops-total-max",
-            .type = QEMU_OPT_NUMBER,
-            .help = "I/O operations burst",
-        },{
-            .name = "throttling.iops-read-max",
-            .type = QEMU_OPT_NUMBER,
-            .help = "I/O operations read burst",
-        },{
-            .name = "throttling.iops-write-max",
-            .type = QEMU_OPT_NUMBER,
-            .help = "I/O operations write burst",
-        },{
-            .name = "throttling.bps-total-max",
-            .type = QEMU_OPT_NUMBER,
-            .help = "total bytes burst",
-        },{
-            .name = "throttling.bps-read-max",
-            .type = QEMU_OPT_NUMBER,
-            .help = "total bytes read burst",
-        },{
-            .name = "throttling.bps-write-max",
-            .type = QEMU_OPT_NUMBER,
-            .help = "total bytes write burst",
-        },{
-            .name = "throttling.iops-total-max-length",
-            .type = QEMU_OPT_NUMBER,
-            .help = "length of the iops-total-max burst period, in seconds",
-        },{
-            .name = "throttling.iops-read-max-length",
-            .type = QEMU_OPT_NUMBER,
-            .help = "length of the iops-read-max burst period, in seconds",
-        },{
-            .name = "throttling.iops-write-max-length",
-            .type = QEMU_OPT_NUMBER,
-            .help = "length of the iops-write-max burst period, in seconds",
-        },{
-            .name = "throttling.bps-total-max-length",
-            .type = QEMU_OPT_NUMBER,
-            .help = "length of the bps-total-max burst period, in seconds",
-        },{
-            .name = "throttling.bps-read-max-length",
-            .type = QEMU_OPT_NUMBER,
-            .help = "length of the bps-read-max burst period, in seconds",
-        },{
-            .name = "throttling.bps-write-max-length",
-            .type = QEMU_OPT_NUMBER,
-            .help = "length of the bps-write-max burst period, in seconds",
-        },{
-            .name = "throttling.iops-size",
-            .type = QEMU_OPT_NUMBER,
-            .help = "when limiting by iops max size of an I/O in bytes",
-        },{
+        },
+
+        THROTTLE_OPTS,
+
+        {
             .name = "throttling.group",
             .type = QEMU_OPT_STRING,
             .help = "name of the block throttling group",

blockjob.c

@@ -55,6 +55,19 @@ struct BlockJobTxn {
 
 static QLIST_HEAD(, BlockJob) block_jobs = QLIST_HEAD_INITIALIZER(block_jobs);
 
+static char *child_job_get_parent_desc(BdrvChild *c)
+{
+    BlockJob *job = c->opaque;
+    return g_strdup_printf("%s job '%s'",
+                           BlockJobType_lookup[job->driver->job_type],
+                           job->id);
+}
+
+static const BdrvChildRole child_job = {
+    .get_parent_desc    = child_job_get_parent_desc,
+    .stay_at_node       = true,
+};
+
 BlockJob *block_job_next(BlockJob *job)
 {
     if (!job) {
@@ -115,19 +128,44 @@ static void block_job_detach_aio_context(void *opaque)
     block_job_unref(job);
 }
 
-void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs)
+void block_job_remove_all_bdrv(BlockJob *job)
 {
-    job->nodes = g_slist_prepend(job->nodes, bs);
+    GSList *l;
+    for (l = job->nodes; l; l = l->next) {
+        BdrvChild *c = l->data;
+        bdrv_op_unblock_all(c->bs, job->blocker);
+        bdrv_root_unref_child(c);
+    }
+    g_slist_free(job->nodes);
+    job->nodes = NULL;
+}
+
+int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
+                       uint64_t perm, uint64_t shared_perm, Error **errp)
+{
+    BdrvChild *c;
+
+    c = bdrv_root_attach_child(bs, name, &child_job, perm, shared_perm,
+                               job, errp);
+    if (c == NULL) {
+        return -EPERM;
+    }
+
+    job->nodes = g_slist_prepend(job->nodes, c);
     bdrv_ref(bs);
     bdrv_op_block_all(bs, job->blocker);
+
+    return 0;
 }
 
 void *block_job_create(const char *job_id, const BlockJobDriver *driver,
-                       BlockDriverState *bs, int64_t speed, int flags,
+                       BlockDriverState *bs, uint64_t perm,
+                       uint64_t shared_perm, int64_t speed, int flags,
                        BlockCompletionFunc *cb, void *opaque, Error **errp)
 {
     BlockBackend *blk;
     BlockJob *job;
+    int ret;
 
     if (bs->job) {
         error_setg(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
@@ -159,13 +197,17 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
         }
     }
 
-    blk = blk_new();
-    blk_insert_bs(blk, bs);
+    blk = blk_new(perm, shared_perm);
+    ret = blk_insert_bs(blk, bs, errp);
+    if (ret < 0) {
+        blk_unref(blk);
+        return NULL;
+    }
 
     job = g_malloc0(driver->instance_size);
     error_setg(&job->blocker, "block device is in use by block job: %s",
                BlockJobType_lookup[driver->job_type]);
-    block_job_add_bdrv(job, bs);
+    block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort);
     bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
 
     job->driver        = driver;
@@ -228,15 +270,9 @@ void block_job_ref(BlockJob *job)
 void block_job_unref(BlockJob *job)
 {
     if (--job->refcnt == 0) {
-        GSList *l;
         BlockDriverState *bs = blk_bs(job->blk);
         bs->job = NULL;
-        for (l = job->nodes; l; l = l->next) {
-            bs = l->data;
-            bdrv_op_unblock_all(bs, job->blocker);
-            bdrv_unref(bs);
-        }
-        g_slist_free(job->nodes);
+        block_job_remove_all_bdrv(job);
         blk_remove_aio_context_notifier(job->blk,
                                         block_job_attached_aio_context,
                                         block_job_detach_aio_context, job);

configure

@@ -5894,6 +5894,7 @@ case "$target_name" in
     TARGET_BASE_ARCH=i386
   ;;
   alpha)
+    mttcg="yes"
   ;;
   arm|armeb)
     TARGET_ARCH=arm

cputlb.c

@@ -769,14 +769,13 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
     pd = iotlbentry->addr & ~TARGET_PAGE_MASK;
     mr = iotlb_to_region(cpu, pd, iotlbentry->attrs);
     if (memory_region_is_unassigned(mr)) {
-        CPUClass *cc = CPU_GET_CLASS(cpu);
-
-        if (cc->do_unassigned_access) {
-            cc->do_unassigned_access(cpu, addr, false, true, 0, 4);
-        } else {
-            report_bad_exec(cpu, addr);
-            exit(1);
-        }
+        cpu_unassigned_access(cpu, addr, false, true, 0, 4);
+        /* The CPU's unassigned access hook might have longjumped out
+         * with an exception. If it didn't (or there was no hook) then
+         * we can't proceed further.
+         */
+        report_bad_exec(cpu, addr);
+        exit(1);
     }
     p = (void *)((uintptr_t)addr + env1->tlb_table[mmu_idx][page_index].addend);
     return qemu_ram_addr_from_host_nofail(p);

crypto/cipher.c

@@ -63,18 +63,14 @@ static bool mode_need_iv[QCRYPTO_CIPHER_MODE__MAX] = {
 
 size_t qcrypto_cipher_get_block_len(QCryptoCipherAlgorithm alg)
 {
-    if (alg >= G_N_ELEMENTS(alg_key_len)) {
-        return 0;
-    }
+    assert(alg < G_N_ELEMENTS(alg_key_len));
     return alg_block_len[alg];
 }
 
 
 size_t qcrypto_cipher_get_key_len(QCryptoCipherAlgorithm alg)
 {
-    if (alg >= G_N_ELEMENTS(alg_key_len)) {
-        return 0;
-    }
+    assert(alg < G_N_ELEMENTS(alg_key_len));
     return alg_key_len[alg];
 }
 

crypto/ivgen-essiv.c

@@ -48,6 +48,7 @@ static int qcrypto_ivgen_essiv_init(QCryptoIVGen *ivgen,
                            &salt, &nhash,
                            errp) < 0) {
         g_free(essiv);
+        g_free(salt);
         return -1;
     }
 

default-configs/arm-softmmu.mak

@@ -42,6 +42,8 @@ CONFIG_ARM11MPCORE=y
 CONFIG_A9MPCORE=y
 CONFIG_A15MPCORE=y
 
+CONFIG_ARM_V7M=y
+
 CONFIG_ARM_GIC=y
 CONFIG_ARM_GIC_KVM=$(CONFIG_KVM)
 CONFIG_ARM_TIMER=y

docs/mach-virt-graphical.cfg

@@ -0,0 +1,281 @@
+# mach-virt - VirtIO guest (graphical console)
+# =========================================================
+#
+# Usage:
+#
+#   $ qemu-system-aarch64 \
+#     -nodefaults \
+#     -readconfig mach-virt-graphical.cfg \
+#     -cpu host
+#
+# You will probably need to tweak the lines marked as
+# CHANGE ME before being able to use this configuration!
+#
+# The guest will have a selection of VirtIO devices
+# tailored towards optimal performance with modern guests,
+# and will be accessed through a graphical console.
+#
+# ---------------------------------------------------------
+#
+# Using -nodefaults is required to have full control over
+# the virtual hardware: when it's specified, QEMU will
+# populate the board with only the builtin peripherals,
+# such as the PL011 UART, plus a PCI Express Root Bus; the
+# user will then have to explicitly add further devices.
+#
+# The PCI Express Root Bus shows up in the guest as:
+#
+#   00:00.0 Host bridge
+#
+# This configuration file adds a number of other useful
+# devices, more specifically:
+#
+#   00:01.0 Display controller
+#   00.1c.* PCI bridge (PCI Express Root Ports)
+#   01:00.0 SCSI storage controller
+#   02:00.0 Ethernet controller
+#   03:00.0 USB controller
+#
+# More information about these devices is available below.
+
+
+# Machine options
+# =========================================================
+#
+# We use the virt machine type and enable KVM acceleration
+# for better performance.
+#
+# Using less than 1 GiB of memory is probably not going to
+# yield good performance in the guest, and might even lead
+# to obscure boot issues in some cases.
+#
+# Unfortunately, there is no way to configure the CPU model
+# in this file, so it will have to be provided on the
+# command line, but we can configure the guest to use the
+# same GIC version as the host.
+
+[machine]
+  type = "virt"
+  accel = "kvm"
+  gic-version = "host"
+
+[memory]
+  size = "1024"
+
+
+# Firmware configuration
+# =========================================================
+#
+# There are two parts to the firmware: a read-only image
+# containing the executable code, which is shared between
+# guests, and a read/write variable store that is owned
+# by one specific guest, exclusively, and is used to
+# record information such as the UEFI boot order.
+#
+# For any new guest, its permanent, private variable store
+# should initially be copied from the template file
+# provided along with the firmware binary.
+#
+# Depending on the OS distribution you're using on the
+# host, the name of the package containing the firmware
+# binary and variable store template, as well as the paths
+# to the files themselves, will be different. For example:
+#
+# Fedora
+#   edk2-aarch64                                      (pkg)
+#   /usr/share/edk2/aarch64/QEMU_EFI-pflash.raw       (bin)
+#   /usr/share/edk2/aarch64/vars-template-pflash.raw  (var)
+#
+# RHEL
+#   AAVMF                                             (pkg)
+#   /usr/share/AAVMF/AAVMF_CODE.fd                    (bin)
+#   /usr/share/AAVMF/AAVMF_VARS.fd                    (var)
+#
+# Debian/Ubuntu
+#   qemu-efi                                          (pkg)
+#   /usr/share/AAVMF/AAVMF_CODE.fd                    (bin)
+#   /usr/share/AAVMF/AAVMF_VARS.fd                    (var)
+
+[drive "uefi-binary"]
+  file = "/usr/share/AAVMF/AAVMF_CODE.fd"       # CHANGE ME
+  format = "raw"
+  if = "pflash"
+  unit = "0"
+  readonly = "on"
+
+[drive "uefi-varstore"]
+  file = "guest_VARS.fd"                        # CHANGE ME
+  format = "raw"
+  if = "pflash"
+  unit = "1"
+
+
+# PCI bridge (PCI Express Root Ports)
+# =========================================================
+#
+# We create eight PCI Express Root Ports, and we plug them
+# all into separate functions of the same slot. Some of
+# them will be used by devices, the rest will remain
+# available for hotplug.
+
+[device "pcie.1"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.0"
+  port = "1"
+  chassis = "1"
+  multifunction = "on"
+
+[device "pcie.2"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.1"
+  port = "2"
+  chassis = "2"
+
+[device "pcie.3"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.2"
+  port = "3"
+  chassis = "3"
+
+[device "pcie.4"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.3"
+  port = "4"
+  chassis = "4"
+
+[device "pcie.5"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.4"
+  port = "5"
+  chassis = "5"
+
+[device "pcie.6"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.5"
+  port = "6"
+  chassis = "6"
+
+[device "pcie.7"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.6"
+  port = "7"
+  chassis = "7"
+
+[device "pcie.8"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.7"
+  port = "8"
+  chassis = "8"
+
+
+# SCSI storage controller (and storage)
+# =========================================================
+#
+# We use virtio-scsi here so that we can (hot)plug a large
+# number of disks without running into issues; a SCSI disk,
+# backed by a qcow2 disk image on the host's filesystem, is
+# attached to it.
+#
+# We also create an optical disk, mostly for installation
+# purposes: once the guest OS has been succesfully
+# installed, the guest will no longer boot from optical
+# media. If you don't want, or no longer want, to have an
+# optical disk in the guest you can safely comment out
+# all relevant sections below.
+
+[device "scsi"]
+  driver = "virtio-scsi-pci"
+  bus = "pcie.1"
+  addr = "00.0"
+
+[device "scsi-disk"]
+  driver = "scsi-hd"
+  bus = "scsi.0"
+  drive = "disk"
+  bootindex = "1"
+
+[drive "disk"]
+  file = "guest.qcow2"                          # CHANGE ME
+  format = "qcow2"
+  if = "none"
+
+[device "scsi-optical-disk"]
+  driver = "scsi-cd"
+  bus = "scsi.0"
+  drive = "optical-disk"
+  bootindex = "2"
+
+[drive "optical-disk"]
+  file = "install.iso"                          # CHANGE ME
+  format = "raw"
+  if = "none"
+
+
+# Ethernet controller
+# =========================================================
+#
+# We use virtio-net for improved performance over emulated
+# hardware; on the host side, we take advantage of user
+# networking so that the QEMU process doesn't require any
+# additional privileges.
+
+[netdev "hostnet"]
+  type = "user"
+
+[device "net"]
+  driver = "virtio-net-pci"
+  netdev = "hostnet"
+  bus = "pcie.2"
+  addr = "00.0"
+
+
+# USB controller (and input devices)
+# =========================================================
+#
+# We add a virtualization-friendly USB 3.0 controller and
+# a USB keyboard / USB tablet combo so that graphical
+# guests can be controlled appropriately.
+
+[device "usb"]
+  driver = "nec-usb-xhci"
+  bus = "pcie.3"
+  addr = "00.0"
+
+[device "keyboard"]
+  driver = "usb-kbd"
+  bus = "usb.0"
+
+[device "tablet"]
+  driver = "usb-tablet"
+  bus = "usb.0"
+
+
+# Display controller
+# =========================================================
+#
+# We use virtio-gpu because the legacy VGA framebuffer is
+# very troublesome on aarch64, and virtio-gpu is the only
+# video device that doesn't implement it.
+#
+# If you're running the guest on a remote, potentially
+# headless host, you will probably want to append something
+# like
+#
+#   -display vnc=127.0.0.1:0
+#
+# to the command line in order to prevent QEMU from
+# creating a graphical display window on the host and
+# enable remote access instead.
+
+[device "video"]
+  driver = "virtio-gpu"
+  bus = "pcie.0"
+  addr = "01.0"

docs/mach-virt-serial.cfg

@@ -0,0 +1,243 @@
+# mach-virt - VirtIO guest (serial console)
+# =========================================================
+#
+# Usage:
+#
+#   $ qemu-system-aarch64 \
+#     -nodefaults \
+#     -readconfig mach-virt-serial.cfg \
+#     -display none -serial mon:stdio \
+#     -cpu host
+#
+# You will probably need to tweak the lines marked as
+# CHANGE ME before being able to use this configuration!
+#
+# The guest will have a selection of VirtIO devices
+# tailored towards optimal performance with modern guests,
+# and will be accessed through the serial console.
+#
+# ---------------------------------------------------------
+#
+# Using -nodefaults is required to have full control over
+# the virtual hardware: when it's specified, QEMU will
+# populate the board with only the builtin peripherals,
+# such as the PL011 UART, plus a PCI Express Root Bus; the
+# user will then have to explicitly add further devices.
+#
+# The PCI Express Root Bus shows up in the guest as:
+#
+#   00:00.0 Host bridge
+#
+# This configuration file adds a number of other useful
+# devices, more specifically:
+#
+#   00.1c.* PCI bridge (PCI Express Root Ports)
+#   01:00.0 SCSI storage controller
+#   02:00.0 Ethernet controller
+#
+# More information about these devices is available below.
+#
+# We use '-display none' to prevent QEMU from creating a
+# graphical display window, which would serve no use in
+# this specific configuration, and '-serial mon:stdio' to
+# multiplex the guest's serial console and the QEMU monitor
+# to the host's stdio; use 'Ctrl+A h' to learn how to
+# switch between the two and more.
+
+
+# Machine options
+# =========================================================
+#
+# We use the virt machine type and enable KVM acceleration
+# for better performance.
+#
+# Using less than 1 GiB of memory is probably not going to
+# yield good performance in the guest, and might even lead
+# to obscure boot issues in some cases.
+#
+# Unfortunately, there is no way to configure the CPU model
+# in this file, so it will have to be provided on the
+# command line, but we can configure the guest to use the
+# same GIC version as the host.
+
+[machine]
+  type = "virt"
+  accel = "kvm"
+  gic-version = "host"
+
+[memory]
+  size = "1024"
+
+
+# Firmware configuration
+# =========================================================
+#
+# There are two parts to the firmware: a read-only image
+# containing the executable code, which is shared between
+# guests, and a read/write variable store that is owned
+# by one specific guest, exclusively, and is used to
+# record information such as the UEFI boot order.
+#
+# For any new guest, its permanent, private variable store
+# should initially be copied from the template file
+# provided along with the firmware binary.
+#
+# Depending on the OS distribution you're using on the
+# host, the name of the package containing the firmware
+# binary and variable store template, as well as the paths
+# to the files themselves, will be different. For example:
+#
+# Fedora
+#   edk2-aarch64                                      (pkg)
+#   /usr/share/edk2/aarch64/QEMU_EFI-pflash.raw       (bin)
+#   /usr/share/edk2/aarch64/vars-template-pflash.raw  (var)
+#
+# RHEL
+#   AAVMF                                             (pkg)
+#   /usr/share/AAVMF/AAVMF_CODE.fd                    (bin)
+#   /usr/share/AAVMF/AAVMF_VARS.fd                    (var)
+#
+# Debian/Ubuntu
+#   qemu-efi                                          (pkg)
+#   /usr/share/AAVMF/AAVMF_CODE.fd                    (bin)
+#   /usr/share/AAVMF/AAVMF_VARS.fd                    (var)
+
+[drive "uefi-binary"]
+  file = "/usr/share/AAVMF/AAVMF_CODE.fd"       # CHANGE ME
+  format = "raw"
+  if = "pflash"
+  unit = "0"
+  readonly = "on"
+
+[drive "uefi-varstore"]
+  file = "guest_VARS.fd"                        # CHANGE ME
+  format = "raw"
+  if = "pflash"
+  unit = "1"
+
+
+# PCI bridge (PCI Express Root Ports)
+# =========================================================
+#
+# We create eight PCI Express Root Ports, and we plug them
+# all into separate functions of the same slot. Some of
+# them will be used by devices, the rest will remain
+# available for hotplug.
+
+[device "pcie.1"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.0"
+  port = "1"
+  chassis = "1"
+  multifunction = "on"
+
+[device "pcie.2"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.1"
+  port = "2"
+  chassis = "2"
+
+[device "pcie.3"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.2"
+  port = "3"
+  chassis = "3"
+
+[device "pcie.4"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.3"
+  port = "4"
+  chassis = "4"
+
+[device "pcie.5"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.4"
+  port = "5"
+  chassis = "5"
+
+[device "pcie.6"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.5"
+  port = "6"
+  chassis = "6"
+
+[device "pcie.7"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.6"
+  port = "7"
+  chassis = "7"
+
+[device "pcie.8"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.7"
+  port = "8"
+  chassis = "8"
+
+
+# SCSI storage controller (and storage)
+# =========================================================
+#
+# We use virtio-scsi here so that we can (hot)plug a large
+# number of disks without running into issues; a SCSI disk,
+# backed by a qcow2 disk image on the host's filesystem, is
+# attached to it.
+#
+# We also create an optical disk, mostly for installation
+# purposes: once the guest OS has been succesfully
+# installed, the guest will no longer boot from optical
+# media. If you don't want, or no longer want, to have an
+# optical disk in the guest you can safely comment out
+# all relevant sections below.
+
+[device "scsi"]
+  driver = "virtio-scsi-pci"
+  bus = "pcie.1"
+  addr = "00.0"
+
+[device "scsi-disk"]
+  driver = "scsi-hd"
+  bus = "scsi.0"
+  drive = "disk"
+  bootindex = "1"
+
+[drive "disk"]
+  file = "guest.qcow2"                          # CHANGE ME
+  format = "qcow2"
+  if = "none"
+
+[device "scsi-optical-disk"]
+  driver = "scsi-cd"
+  bus = "scsi.0"
+  drive = "optical-disk"
+  bootindex = "2"
+
+[drive "optical-disk"]
+  file = "install.iso"                          # CHANGE ME
+  format = "raw"
+  if = "none"
+
+
+# Ethernet controller
+# =========================================================
+#
+# We use virtio-net for improved performance over emulated
+# hardware; on the host side, we take advantage of user
+# networking so that the QEMU process doesn't require any
+# additional privileges.
+
+[netdev "hostnet"]
+  type = "user"
+
+[device "net"]
+  driver = "virtio-net-pci"
+  netdev = "hostnet"
+  bus = "pcie.2"
+  addr = "00.0"

docs/migration.txt

@@ -161,6 +161,11 @@ include/hw/hw.h.
 
 === More about versions ===
 
+Version numbers are intended for major incompatible changes to the
+migration of a device, and using them breaks backwards-migration
+compatibility; in general most changes can be made by adding Subsections
+(see below) or _TEST macros (see below) which won't break compatibility.
+
 You can see that there are several version fields:
 
 - version_id: the maximum version_id supported by VMState for that device.
@@ -175,6 +180,9 @@ version_id.  And the function load_state_old() (if present) is able to
 load state from minimum_version_id_old to minimum_version_id.  This
 function is deprecated and will be removed when no more users are left.
 
+Saving state will always create a section with the 'version_id' value
+and thus can't be loaded by any older QEMU.
+
 ===  Massaging functions ===
 
 Sometimes, it is not enough to be able to save the state directly
@@ -292,6 +300,56 @@ save/send this state when we are in the middle of a pio operation
 not enabled, the values on that fields are garbage and don't need to
 be sent.
 
+Using a condition function that checks a 'property' to determine whether
+to send a subsection allows backwards migration compatibility when
+new subsections are added.
+
+For example;
+   a) Add a new property using DEFINE_PROP_BOOL - e.g. support-foo and
+      default it to true.
+   b) Add an entry to the HW_COMPAT_ for the previous version
+      that sets the property to false.
+   c) Add a static bool  support_foo function that tests the property.
+   d) Add a subsection with a .needed set to the support_foo function
+   e) (potentially) Add a pre_load that sets up a default value for 'foo'
+      to be used if the subsection isn't loaded.
+
+Now that subsection will not be generated when using an older
+machine type and the migration stream will be accepted by older
+QEMU versions. pre-load functions can be used to initialise state
+on the newer version so that they default to suitable values
+when loading streams created by older QEMU versions that do not
+generate the subsection.
+
+In some cases subsections are added for data that had been accidentally
+omitted by earlier versions; if the missing data causes the migration
+process to succeed but the guest to behave badly then it may be better
+to send the subsection and cause the migration to explicitly fail
+with the unknown subsection error.   If the bad behaviour only happens
+with certain data values, making the subsection conditional on
+the data value (rather than the machine type) allows migrations to succeed
+in most cases.  In general the preference is to tie the subsection to
+the machine type, and allow reliable migrations, unless the behaviour
+from omission of the subsection is really bad.
+
+= Not sending existing elements =
+
+Sometimes members of the VMState are no longer needed;
+  removing them will break migration compatibility
+  making them version dependent and bumping the version will break backwards
+   migration compatibility.
+
+The best way is to:
+  a) Add a new property/compatibility/function in the same way for subsections
+    above.
+  b) replace the VMSTATE macro with the _TEST version of the macro, e.g.:
+     VMSTATE_UINT32(foo, barstruct)
+   becomes
+     VMSTATE_UINT32_TEST(foo, barstruct, pre_version_baz)
+
+  Sometime in the future when we no longer care about the ancient
+versions these can be killed off.
+
 = Return path =
 
 In most migration scenarios there is only a single data path that runs
@@ -482,3 +540,16 @@ request for a page that has already been sent is ignored.  Duplicate requests
 such as this can happen as a page is sent at about the same time the
 destination accesses it.
 
+=== Postcopy with hugepages ===
+
+Postcopy now works with hugetlbfs backed memory:
+  a) The linux kernel on the destination must support userfault on hugepages.
+  b) The huge-page configuration on the source and destination VMs must be
+     identical; i.e. RAMBlocks on both sides must use the same page size.
+  c) Note that -mem-path /dev/hugepages  will fall back to allocating normal
+     RAM if it doesn't have enough hugepages, triggering (b) to fail.
+     Using -mem-prealloc enforces the allocation using hugepages.
+  d) Care should be taken with the size of hugepage used; postcopy with 2MB
+     hugepages works well, however 1GB hugepages are likely to be problematic
+     since it takes ~1 second to transfer a 1GB hugepage across a 10Gbps link,
+     and until the full page is transferred the destination thread is blocked.

docs/q35-chipset.cfg

@@ -1,152 +0,0 @@
-################################################################
-#
-# qemu -M q35 creates a bare machine with just the very essential
-# chipset devices being present:
-#
-#     00.0 - Host bridge
-#     1f.0 - ISA bridge / LPC
-#     1f.2 - SATA (AHCI) controller
-#     1f.3 - SMBus controller
-#
-# This config file documents the other devices and how they are
-# created.  You can simply use "-readconfig $thisfile" to create
-# them all.  Here is a overview:
-#
-#     19.0 - Ethernet controller (not created, our e1000 emulation
-#                                 doesn't emulate the ich9 device).
-#     1a.* - USB Controller #2 (ehci + uhci companions)
-#     1b.0 - HD Audio Controller
-#     1c.* - PCI Express Ports
-#     1d.* - USB Controller #1 (ehci + uhci companions,
-#                               "qemu -M q35 -usb" creates these too)
-#     1e.0 - PCI Bridge
-#
-
-[device "ich9-ehci-2"]
-  driver = "ich9-usb-ehci2"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1a.7"
-
-[device "ich9-uhci-4"]
-  driver = "ich9-usb-uhci4"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1a.0"
-  masterbus = "ich9-ehci-2.0"
-  firstport = "0"
-
-[device "ich9-uhci-5"]
-  driver = "ich9-usb-uhci5"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1a.1"
-  masterbus = "ich9-ehci-2.0"
-  firstport = "2"
-
-[device "ich9-uhci-6"]
-  driver = "ich9-usb-uhci6"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1a.2"
-  masterbus = "ich9-ehci-2.0"
-  firstport = "4"
-
-
-[device "ich9-hda-audio"]
-  driver = "ich9-intel-hda"
-  bus = "pcie.0"
-  addr = "1b.0"
-
-
-[device "ich9-pcie-port-1"]
-  driver = "ioh3420"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1c.0"
-  port = "1"
-  chassis = "1"
-
-[device "ich9-pcie-port-2"]
-  driver = "ioh3420"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1c.1"
-  port = "2"
-  chassis = "2"
-
-[device "ich9-pcie-port-3"]
-  driver = "ioh3420"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1c.2"
-  port = "3"
-  chassis = "3"
-
-[device "ich9-pcie-port-4"]
-  driver = "ioh3420"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1c.3"
-  port = "4"
-  chassis = "4"
-
-##
-# Example PCIe switch with two downstream ports
-#
-#[device "pcie-switch-upstream-port-1"]
-#  driver = "x3130-upstream"
-#  bus = "ich9-pcie-port-4"
-#  addr = "00.0"
-#
-#[device "pcie-switch-downstream-port-1-1"]
-#  driver = "xio3130-downstream"
-#  multifunction = "on"
-#  bus = "pcie-switch-upstream-port-1"
-#  addr = "00.0"
-#  port = "1"
-#  chassis = "5"
-#
-#[device "pcie-switch-downstream-port-1-2"]
-#  driver = "xio3130-downstream"
-#  multifunction = "on"
-#  bus = "pcie-switch-upstream-port-1"
-#  addr = "00.1"
-#  port = "1"
-#  chassis = "6"
-
-[device "ich9-ehci-1"]
-  driver = "ich9-usb-ehci1"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1d.7"
-
-[device "ich9-uhci-1"]
-  driver = "ich9-usb-uhci1"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1d.0"
-  masterbus = "ich9-ehci-1.0"
-  firstport = "0"
-
-[device "ich9-uhci-2"]
-  driver = "ich9-usb-uhci2"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1d.1"
-  masterbus = "ich9-ehci-1.0"
-  firstport = "2"
-
-[device "ich9-uhci-3"]
-  driver = "ich9-usb-uhci3"
-  multifunction = "on"
-  bus = "pcie.0"
-  addr = "1d.2"
-  masterbus = "ich9-ehci-1.0"
-  firstport = "4"
-
-
-[device "ich9-pci-bridge"]
-  driver = "i82801b11-bridge"
-  bus = "pcie.0"
-  addr = "1e.0"

docs/q35-emulated.cfg

@@ -0,0 +1,288 @@
+# q35 - Emulated guest (graphical console)
+# =========================================================
+#
+# Usage:
+#
+#   $ qemu-system-x86_64 \
+#     -nodefaults \
+#     -readconfig q35-emulated.cfg
+#
+# You will probably need to tweak the lines marked as
+# CHANGE ME before being able to use this configuration!
+#
+# The guest will have a selection of emulated devices that
+# closely resembles that of a physical machine, and will be
+# accessed through a graphical console.
+#
+# ---------------------------------------------------------
+#
+# Using -nodefaults is required to have full control over
+# the virtual hardware: when it's specified, QEMU will
+# populate the board with only the builtin peripherals
+# plus a small selection of core PCI devices and
+# controllers; the user will then have to explicitly add
+# further devices.
+#
+# The core PCI devices show up in the guest as:
+#
+#   00:00.0 Host bridge
+#   00:1f.0 ISA bridge / LPC
+#   00:1f.2 SATA (AHCI) controller
+#   00:1f.3 SMBus controller
+#
+# This configuration file adds a number of devices that
+# are pretty much guaranteed to be present in every single
+# physical machine based on q35, more specifically:
+#
+#   00:01.0 VGA compatible controller
+#   00:19.0 Ethernet controller
+#   00:1a.* USB controller (#2)
+#   00:1b.0 Audio device
+#   00:1c.* PCI bridge (PCI Express Root Ports)
+#   00:1d.* USB Controller (#1)
+#   00:1e.0 PCI bridge (legacy PCI bridge)
+#
+# More information about these devices is available below.
+
+
+# Machine options
+# =========================================================
+#
+# We use the q35 machine type and enable KVM acceleration
+# for better performance.
+#
+# Using less than 1 GiB of memory is probably not going to
+# yield good performance in the guest, and might even lead
+# to obscure boot issues in some cases.
+#
+# Unfortunately, there is no way to configure the CPU model
+# in this file, so it will have to be provided on the
+# command line.
+
+[machine]
+  type = "q35"
+  accel = "kvm"
+
+[memory]
+  size = "1024"
+
+
+# PCI bridge (PCI Express Root Ports)
+# =========================================================
+#
+# We add four PCI Express Root Ports, all sharing the same
+# slot on the PCI Express  Root Bus. These ports support
+# hotplug.
+
+[device "ich9-pcie-port-1"]
+  driver = "ioh3420"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1c.0"
+  port = "1"
+  chassis = "1"
+
+[device "ich9-pcie-port-2"]
+  driver = "ioh3420"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1c.1"
+  port = "2"
+  chassis = "2"
+
+[device "ich9-pcie-port-3"]
+  driver = "ioh3420"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1c.2"
+  port = "3"
+  chassis = "3"
+
+[device "ich9-pcie-port-4"]
+  driver = "ioh3420"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1c.3"
+  port = "4"
+  chassis = "4"
+
+
+# PCI bridge (legacy PCI bridge)
+# =========================================================
+#
+# This bridge can be used to build an independent topology
+# for legacy PCI devices. PCI Express devices should be
+# plugged into PCI Express slots instead, so ideally there
+# will be no devices connected to this bridge.
+
+[device "ich9-pci-bridge"]
+  driver = "i82801b11-bridge"
+  bus = "pcie.0"
+  addr = "1e.0"
+
+
+# SATA storage
+# =========================================================
+#
+# An implicit SATA controller is created automatically for
+# every single q35 guest; here we create a disk, backed by
+# a qcow2 disk image on the host's filesystem, and attach
+# it to that controller so that the guest can use it.
+#
+# We also create an optical disk, mostly for installation
+# purposes: once the guest OS has been succesfully
+# installed, the guest will no longer boot from optical
+# media. If you don't want, or no longer want, to have an
+# optical disk in the guest you can safely comment out
+# all relevant sections below.
+
+[device "sata-disk"]
+  driver = "ide-hd"
+  bus = "ide.0"
+  drive = "disk"
+  bootindex = "1"
+
+[drive "disk"]
+  file = "guest.qcow2"                          # CHANGE ME
+  format = "qcow2"
+  if = "none"
+
+[device "sata-optical-disk"]
+  driver = "ide-cd"
+  bus = "ide.1"
+  drive = "optical-disk"
+  bootindex = "2"
+
+[drive "optical-disk"]
+  file = "install.iso"                          # CHANGE ME
+  format = "raw"
+  if = "none"
+
+
+# USB controller (#1)
+# =========================================================
+#
+# EHCI controller + UHCI companion controllers.
+
+[device "ich9-ehci-1"]
+  driver = "ich9-usb-ehci1"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1d.7"
+
+[device "ich9-uhci-1"]
+  driver = "ich9-usb-uhci1"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1d.0"
+  masterbus = "ich9-ehci-1.0"
+  firstport = "0"
+
+[device "ich9-uhci-2"]
+  driver = "ich9-usb-uhci2"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1d.1"
+  masterbus = "ich9-ehci-1.0"
+  firstport = "2"
+
+[device "ich9-uhci-3"]
+  driver = "ich9-usb-uhci3"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1d.2"
+  masterbus = "ich9-ehci-1.0"
+  firstport = "4"
+
+
+# USB controller (#2)
+# =========================================================
+#
+# EHCI controller + UHCI companion controllers.
+
+[device "ich9-ehci-2"]
+  driver = "ich9-usb-ehci2"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1a.7"
+
+[device "ich9-uhci-4"]
+  driver = "ich9-usb-uhci4"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1a.0"
+  masterbus = "ich9-ehci-2.0"
+  firstport = "0"
+
+[device "ich9-uhci-5"]
+  driver = "ich9-usb-uhci5"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1a.1"
+  masterbus = "ich9-ehci-2.0"
+  firstport = "2"
+
+[device "ich9-uhci-6"]
+  driver = "ich9-usb-uhci6"
+  multifunction = "on"
+  bus = "pcie.0"
+  addr = "1a.2"
+  masterbus = "ich9-ehci-2.0"
+  firstport = "4"
+
+
+# Ethernet controller
+# =========================================================
+#
+# We add a Gigabit Ethernet interface to the guest; on the
+# host side, we take advantage of user networking so that
+# the QEMU process doesn't require any additional
+# privileges.
+
+[netdev "hostnet"]
+  type = "user"
+
+[device "net"]
+  driver = "e1000"
+  netdev = "hostnet"
+  bus = "pcie.0"
+  addr = "19.0"
+
+
+# VGA compatible controller
+# =========================================================
+#
+# We use stdvga instead of Cirrus as it supports more video
+# modes and is closer to what actual hardware looks like.
+#
+# If you're running the guest on a remote, potentially
+# headless host, you will probably want to append something
+# like
+#
+#   -display vnc=127.0.0.1:0
+#
+# to the command line in order to prevent QEMU from
+# creating a graphical display window on the host and
+# enable remote access instead.
+
+[device "video"]
+  driver = "VGA"
+  bus = "pcie.0"
+  addr = "01.0"
+
+
+# Audio device
+# =========================================================
+#
+# The sound card is a legacy PCI device that is plugged
+# directly into the PCI Express Root Bus.
+
+[device "ich9-hda-audio"]
+  driver = "ich9-intel-hda"
+  bus = "pcie.0"
+  addr = "1b.0"
+
+[device "ich9-hda-duplex"]
+  driver = "hda-duplex"
+  bus = "ich9-hda-audio.0"
+  cad = "0"

docs/q35-virtio-graphical.cfg

@@ -0,0 +1,248 @@
+# q35 - VirtIO guest (graphical console)
+# =========================================================
+#
+# Usage:
+#
+#   $ qemu-system-x86_64 \
+#     -nodefaults \
+#     -readconfig q35-virtio-graphical.cfg
+#
+# You will probably need to tweak the lines marked as
+# CHANGE ME before being able to use this configuration!
+#
+# The guest will have a selection of VirtIO devices
+# tailored towards optimal performance with modern guests,
+# and will be accessed through a graphical console.
+#
+# ---------------------------------------------------------
+#
+# Using -nodefaults is required to have full control over
+# the virtual hardware: when it's specified, QEMU will
+# populate the board with only the builtin peripherals
+# plus a small selection of core PCI devices and
+# controllers; the user will then have to explicitly add
+# further devices.
+#
+# The core PCI devices show up in the guest as:
+#
+#   00:00.0 Host bridge
+#   00:1f.0 ISA bridge / LPC
+#   00:1f.2 SATA (AHCI) controller
+#   00:1f.3 SMBus controller
+#
+# This configuration file adds a number of other useful
+# devices, more specifically:
+#
+#   00:01.0 VGA compatible controller
+#   00:1b.0 Audio device
+#   00.1c.* PCI bridge (PCI Express Root Ports)
+#   01:00.0 SCSI storage controller
+#   02:00.0 Ethernet controller
+#   03:00.0 USB controller
+#
+# More information about these devices is available below.
+
+
+# Machine options
+# =========================================================
+#
+# We use the q35 machine type and enable KVM acceleration
+# for better performance.
+#
+# Using less than 1 GiB of memory is probably not going to
+# yield good performance in the guest, and might even lead
+# to obscure boot issues in some cases.
+
+[machine]
+  type = "q35"
+  accel = "kvm"
+
+[memory]
+  size = "1024"
+
+
+# PCI bridge (PCI Express Root Ports)
+# =========================================================
+#
+# We create eight PCI Express Root Ports, and we plug them
+# all into separate functions of the same slot. Some of
+# them will be used by devices, the rest will remain
+# available for hotplug.
+
+[device "pcie.1"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.0"
+  port = "1"
+  chassis = "1"
+  multifunction = "on"
+
+[device "pcie.2"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.1"
+  port = "2"
+  chassis = "2"
+
+[device "pcie.3"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.2"
+  port = "3"
+  chassis = "3"
+
+[device "pcie.4"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.3"
+  port = "4"
+  chassis = "4"
+
+[device "pcie.5"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.4"
+  port = "5"
+  chassis = "5"
+
+[device "pcie.6"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.5"
+  port = "6"
+  chassis = "6"
+
+[device "pcie.7"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.6"
+  port = "7"
+  chassis = "7"
+
+[device "pcie.8"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.7"
+  port = "8"
+  chassis = "8"
+
+
+# SCSI storage controller (and storage)
+# =========================================================
+#
+# We use virtio-scsi here so that we can (hot)plug a large
+# number of disks without running into issues; a SCSI disk,
+# backed by a qcow2 disk image on the host's filesystem, is
+# attached to it.
+#
+# We also create an optical disk, mostly for installation
+# purposes: once the guest OS has been succesfully
+# installed, the guest will no longer boot from optical
+# media. If you don't want, or no longer want, to have an
+# optical disk in the guest you can safely comment out
+# all relevant sections below.
+
+[device "scsi"]
+  driver = "virtio-scsi-pci"
+  bus = "pcie.1"
+  addr = "00.0"
+
+[device "scsi-disk"]
+  driver = "scsi-hd"
+  bus = "scsi.0"
+  drive = "disk"
+  bootindex = "1"
+
+[drive "disk"]
+  file = "guest.qcow2"                          # CHANGE ME
+  format = "qcow2"
+  if = "none"
+
+[device "scsi-optical-disk"]
+  driver = "scsi-cd"
+  bus = "scsi.0"
+  drive = "optical-disk"
+  bootindex = "2"
+
+[drive "optical-disk"]
+  file = "install.iso"                          # CHANGE ME
+  format = "raw"
+  if = "none"
+
+
+# Ethernet controller
+# =========================================================
+#
+# We use virtio-net for improved performance over emulated
+# hardware; on the host side, we take advantage of user
+# networking so that the QEMU process doesn't require any
+# additional privileges.
+
+[netdev "hostnet"]
+  type = "user"
+
+[device "net"]
+  driver = "virtio-net-pci"
+  netdev = "hostnet"
+  bus = "pcie.2"
+  addr = "00.0"
+
+
+# USB controller (and input devices)
+# =========================================================
+#
+# We add a virtualization-friendly USB 3.0 controller and
+# a USB tablet so that graphical guests can be controlled
+# appropriately. A USB keyboard is not needed, as q35
+# guests get a PS/2 one added automatically.
+
+[device "usb"]
+  driver = "nec-usb-xhci"
+  bus = "pcie.3"
+  addr = "00.0"
+
+[device "tablet"]
+  driver = "usb-tablet"
+  bus = "usb.0"
+
+
+# VGA compatible controller
+# =========================================================
+#
+# We plug the QXL video card directly into the PCI Express
+# Root Bus as it is a legacy PCI device; this way, we can
+# reduce the number of PCI Express controllers in the
+# guest.
+#
+# If you're running the guest on a remote, potentially
+# headless host, you will probably want to append something
+# like
+#
+#   -display vnc=127.0.0.1:0
+#
+# to the command line in order to prevent QEMU from
+# creating a graphical display window on the host and
+# enable remote access instead.
+
+[device "video"]
+  driver = "qxl-vga"
+  bus = "pcie.0"
+  addr = "01.0"
+
+
+# Audio device
+# =========================================================
+#
+# Like the video card, the sound card is a legacy PCI
+# device and as such can be plugged directly into the PCI
+# Express Root Bus.
+
+[device "sound"]
+  driver = "ich9-intel-hda"
+  bus = "pcie.0"
+  addr = "1b.0"
+
+[device "duplex"]
+  driver = "hda-duplex"
+  bus = "sound.0"
+  cad = "0"

docs/q35-virtio-serial.cfg

@@ -0,0 +1,193 @@
+# q35 - VirtIO guest (serial console)
+# =========================================================
+#
+# Usage:
+#
+#   $ qemu-system-x86_64 \
+#     -nodefaults \
+#     -readconfig q35-virtio-serial.cfg \
+#     -display none -serial mon:stdio
+#
+# You will probably need to tweak the lines marked as
+# CHANGE ME before being able to use this configuration!
+#
+# The guest will have a selection of VirtIO devices
+# tailored towards optimal performance with modern guests,
+# and will be accessed through the serial console.
+#
+# ---------------------------------------------------------
+#
+# Using -nodefaults is required to have full control over
+# the virtual hardware: when it's specified, QEMU will
+# populate the board with only the builtin peripherals
+# plus a small selection of core PCI devices and
+# controllers; the user will then have to explicitly add
+# further devices.
+#
+# The core PCI devices show up in the guest as:
+#
+#   00:00.0 Host bridge
+#   00:1f.0 ISA bridge / LPC
+#   00:1f.2 SATA (AHCI) controller
+#   00:1f.3 SMBus controller
+#
+# This configuration file adds a number of other useful
+# devices, more specifically:
+#
+#   00.1c.* PCI bridge (PCI Express Root Ports)
+#   01:00.0 SCSI storage controller
+#   02:00.0 Ethernet controller
+#
+# More information about these devices is available below.
+#
+# We use '-display none' to prevent QEMU from creating a
+# graphical display window, which would serve no use in
+# this specific configuration, and '-serial mon:stdio' to
+# multiplex the guest's serial console and the QEMU monitor
+# to the host's stdio; use 'Ctrl+A h' to learn how to
+# switch between the two and more.
+
+
+# Machine options
+# =========================================================
+#
+# We use the q35 machine type and enable KVM acceleration
+# for better performance.
+#
+# Using less than 1 GiB of memory is probably not going to
+# yield good performance in the guest, and might even lead
+# to obscure boot issues in some cases.
+
+[machine]
+  type = "q35"
+  accel = "kvm"
+
+[memory]
+  size = "1024"
+
+
+# PCI bridge (PCI Express Root Ports)
+# =========================================================
+#
+# We create eight PCI Express Root Ports, and we plug them
+# all into separate functions of the same slot. Some of
+# them will be used by devices, the rest will remain
+# available for hotplug.
+
+[device "pcie.1"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.0"
+  port = "1"
+  chassis = "1"
+  multifunction = "on"
+
+[device "pcie.2"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.1"
+  port = "2"
+  chassis = "2"
+
+[device "pcie.3"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.2"
+  port = "3"
+  chassis = "3"
+
+[device "pcie.4"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.3"
+  port = "4"
+  chassis = "4"
+
+[device "pcie.5"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.4"
+  port = "5"
+  chassis = "5"
+
+[device "pcie.6"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.5"
+  port = "6"
+  chassis = "6"
+
+[device "pcie.7"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.6"
+  port = "7"
+  chassis = "7"
+
+[device "pcie.8"]
+  driver = "pcie-root-port"
+  bus = "pcie.0"
+  addr = "1c.7"
+  port = "8"
+  chassis = "8"
+
+
+# SCSI storage controller (and storage)
+# =========================================================
+#
+# We use virtio-scsi here so that we can (hot)plug a large
+# number of disks without running into issues; a SCSI disk,
+# backed by a qcow2 disk image on the host's filesystem, is
+# attached to it.
+#
+# We also create an optical disk, mostly for installation
+# purposes: once the guest OS has been succesfully
+# installed, the guest will no longer boot from optical
+# media. If you don't want, or no longer want, to have an
+# optical disk in the guest you can safely comment out
+# all relevant sections below.
+
+[device "scsi"]
+  driver = "virtio-scsi-pci"
+  bus = "pcie.1"
+  addr = "00.0"
+
+[device "scsi-disk"]
+  driver = "scsi-hd"
+  bus = "scsi.0"
+  drive = "disk"
+  bootindex = "1"
+
+[drive "disk"]
+  file = "guest.qcow2"                          # CHANGE ME
+  format = "qcow2"
+  if = "none"
+
+[device "scsi-optical-disk"]
+  driver = "scsi-cd"
+  bus = "scsi.0"
+  drive = "optical-disk"
+  bootindex = "2"
+
+[drive "optical-disk"]
+  file = "install.iso"                          # CHANGE ME
+  format = "raw"
+  if = "none"
+
+
+# Ethernet controller
+# =========================================================
+#
+# We use virtio-net for improved performance over emulated
+# hardware; on the host side, we take advantage of user
+# networking so that the QEMU process doesn't require any
+# additional privileges.
+
+[netdev "hostnet"]
+  type = "user"
+
+[device "net"]
+  driver = "virtio-net-pci"
+  netdev = "hostnet"
+  bus = "pcie.2"
+  addr = "00.0"

docs/replay.txt

@@ -225,3 +225,10 @@ recording the virtual machine this filter puts all packets coming from
 the outer world into the log. In replay mode packets from the log are
 injected into the network device. All interactions with network backend
 in replay mode are disabled.
+
+Audio devices
+-------------
+
+Audio data is recorded and replay automatically. The command line for recording
+and replaying must contain identical specifications of audio hardware, e.g.:
+ -soundhw ac97

exec.c

@@ -45,6 +45,12 @@
 #include "exec/address-spaces.h"
 #include "sysemu/xen-mapcache.h"
 #include "trace-root.h"
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+#include <fcntl.h>
+#include <linux/falloc.h>
+#endif
+
 #endif
 #include "exec/cpu-all.h"
 #include "qemu/rcu_queue.h"
@@ -1518,6 +1524,19 @@ size_t qemu_ram_pagesize(RAMBlock *rb)
     return rb->page_size;
 }
 
+/* Returns the largest size of page in use */
+size_t qemu_ram_pagesize_largest(void)
+{
+    RAMBlock *block;
+    size_t largest = 0;
+
+    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        largest = MAX(largest, qemu_ram_pagesize(block));
+    }
+
+    return largest;
+}
+
 static int memory_try_enable_merging(void *addr, size_t len)
 {
     if (!machine_mem_merge(current_machine)) {
@@ -3294,4 +3313,68 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
     rcu_read_unlock();
     return ret;
 }
+
+/*
+ * Unmap pages of memory from start to start+length such that
+ * they a) read as 0, b) Trigger whatever fault mechanism
+ * the OS provides for postcopy.
+ * The pages must be unmapped by the end of the function.
+ * Returns: 0 on success, none-0 on failure
+ *
+ */
+int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
+{
+    int ret = -1;
+
+    uint8_t *host_startaddr = rb->host + start;
+
+    if ((uintptr_t)host_startaddr & (rb->page_size - 1)) {
+        error_report("ram_block_discard_range: Unaligned start address: %p",
+                     host_startaddr);
+        goto err;
+    }
+
+    if ((start + length) <= rb->used_length) {
+        uint8_t *host_endaddr = host_startaddr + length;
+        if ((uintptr_t)host_endaddr & (rb->page_size - 1)) {
+            error_report("ram_block_discard_range: Unaligned end address: %p",
+                         host_endaddr);
+            goto err;
+        }
+
+        errno = ENOTSUP; /* If we are missing MADVISE etc */
+
+        if (rb->page_size == qemu_host_page_size) {
+#if defined(CONFIG_MADVISE)
+            /* Note: We need the madvise MADV_DONTNEED behaviour of definitely
+             * freeing the page.
+             */
+            ret = madvise(host_startaddr, length, MADV_DONTNEED);
+#endif
+        } else {
+            /* Huge page case  - unfortunately it can't do DONTNEED, but
+             * it can do the equivalent by FALLOC_FL_PUNCH_HOLE in the
+             * huge page file.
+             */
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+            ret = fallocate(rb->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                            start, length);
+#endif
+        }
+        if (ret) {
+            ret = -errno;
+            error_report("ram_block_discard_range: Failed to discard range "
+                         "%s:%" PRIx64 " +%zx (%d)",
+                         rb->idstr, start, length, ret);
+        }
+    } else {
+        error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
+                     "/%zx/" RAM_ADDR_FMT")",
+                     rb->idstr, start, length, rb->used_length);
+    }
+
+err:
+    return ret;
+}
+
 #endif

fpu/softfloat.c

@@ -7492,7 +7492,7 @@ uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *status)
 {
     signed char current_rounding_mode = status->float_rounding_mode;
     set_float_rounding_mode(float_round_to_zero, status);
-    int64_t v = float64_to_uint64(a, status);
+    uint64_t v = float64_to_uint64(a, status);
     set_float_rounding_mode(current_rounding_mode, status);
     return v;
 }

fsdev/Makefile.objs

@@ -5,7 +5,7 @@ common-obj-y = qemu-fsdev.o 9p-marshal.o 9p-iov-marshal.o
 else
 common-obj-y = qemu-fsdev-dummy.o
 endif
-common-obj-y += qemu-fsdev-opts.o
+common-obj-y += qemu-fsdev-opts.o qemu-fsdev-throttle.o
 
 # Toplevel always builds this; targets without virtio will put it in
 # common-obj-y

fsdev/file-op-9p.h

@@ -17,6 +17,7 @@
 #include <dirent.h>
 #include <utime.h>
 #include <sys/vfs.h>
+#include "qemu-fsdev-throttle.h"
 
 #define SM_LOCAL_MODE_BITS    0600
 #define SM_LOCAL_DIR_MODE_BITS    0700
@@ -74,6 +75,7 @@ typedef struct FsDriverEntry {
     char *path;
     int export_flags;
     FileOperations *ops;
+    FsThrottle fst;
 } FsDriverEntry;
 
 typedef struct FsContext
@@ -83,6 +85,7 @@ typedef struct FsContext
     int export_flags;
     struct xattr_operations **xops;
     struct extended_ops exops;
+    FsThrottle *fst;
     /* fs driver specific data */
     void *private;
 } FsContext;

fsdev/qemu-fsdev-opts.c

@@ -9,6 +9,7 @@
 #include "qemu/config-file.h"
 #include "qemu/option.h"
 #include "qemu/module.h"
+#include "qemu/throttle-options.h"
 
 static QemuOptsList qemu_fsdev_opts = {
     .name = "fsdev",
@@ -39,6 +40,8 @@ static QemuOptsList qemu_fsdev_opts = {
             .type = QEMU_OPT_NUMBER,
         },
 
+        THROTTLE_OPTS,
+
         { /*End of list */ }
     },
 };

fsdev/qemu-fsdev-throttle.c

@@ -0,0 +1,118 @@
+/*
+ * Fsdev Throttle
+ *
+ * Copyright (C) 2016 Huawei Technologies Duesseldorf GmbH
+ *
+ * Author: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/error-report.h"
+#include "qemu-fsdev-throttle.h"
+#include "qemu/iov.h"
+
+static void fsdev_throttle_read_timer_cb(void *opaque)
+{
+    FsThrottle *fst = opaque;
+    qemu_co_enter_next(&fst->throttled_reqs[false]);
+}
+
+static void fsdev_throttle_write_timer_cb(void *opaque)
+{
+    FsThrottle *fst = opaque;
+    qemu_co_enter_next(&fst->throttled_reqs[true]);
+}
+
+void fsdev_throttle_parse_opts(QemuOpts *opts, FsThrottle *fst, Error **errp)
+{
+    throttle_config_init(&fst->cfg);
+    fst->cfg.buckets[THROTTLE_BPS_TOTAL].avg =
+        qemu_opt_get_number(opts, "throttling.bps-total", 0);
+    fst->cfg.buckets[THROTTLE_BPS_READ].avg  =
+        qemu_opt_get_number(opts, "throttling.bps-read", 0);
+    fst->cfg.buckets[THROTTLE_BPS_WRITE].avg =
+        qemu_opt_get_number(opts, "throttling.bps-write", 0);
+    fst->cfg.buckets[THROTTLE_OPS_TOTAL].avg =
+        qemu_opt_get_number(opts, "throttling.iops-total", 0);
+    fst->cfg.buckets[THROTTLE_OPS_READ].avg =
+        qemu_opt_get_number(opts, "throttling.iops-read", 0);
+    fst->cfg.buckets[THROTTLE_OPS_WRITE].avg =
+        qemu_opt_get_number(opts, "throttling.iops-write", 0);
+
+    fst->cfg.buckets[THROTTLE_BPS_TOTAL].max =
+        qemu_opt_get_number(opts, "throttling.bps-total-max", 0);
+    fst->cfg.buckets[THROTTLE_BPS_READ].max  =
+        qemu_opt_get_number(opts, "throttling.bps-read-max", 0);
+    fst->cfg.buckets[THROTTLE_BPS_WRITE].max =
+        qemu_opt_get_number(opts, "throttling.bps-write-max", 0);
+    fst->cfg.buckets[THROTTLE_OPS_TOTAL].max =
+        qemu_opt_get_number(opts, "throttling.iops-total-max", 0);
+    fst->cfg.buckets[THROTTLE_OPS_READ].max =
+        qemu_opt_get_number(opts, "throttling.iops-read-max", 0);
+    fst->cfg.buckets[THROTTLE_OPS_WRITE].max =
+        qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
+
+    fst->cfg.buckets[THROTTLE_BPS_TOTAL].burst_length =
+        qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
+    fst->cfg.buckets[THROTTLE_BPS_READ].burst_length  =
+        qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
+    fst->cfg.buckets[THROTTLE_BPS_WRITE].burst_length =
+        qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
+    fst->cfg.buckets[THROTTLE_OPS_TOTAL].burst_length =
+        qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
+    fst->cfg.buckets[THROTTLE_OPS_READ].burst_length =
+        qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
+    fst->cfg.buckets[THROTTLE_OPS_WRITE].burst_length =
+        qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
+    fst->cfg.op_size =
+        qemu_opt_get_number(opts, "throttling.iops-size", 0);
+
+    throttle_is_valid(&fst->cfg, errp);
+}
+
+void fsdev_throttle_init(FsThrottle *fst)
+{
+    if (throttle_enabled(&fst->cfg)) {
+        throttle_init(&fst->ts);
+        throttle_timers_init(&fst->tt,
+                             qemu_get_aio_context(),
+                             QEMU_CLOCK_REALTIME,
+                             fsdev_throttle_read_timer_cb,
+                             fsdev_throttle_write_timer_cb,
+                             fst);
+        throttle_config(&fst->ts, &fst->tt, &fst->cfg);
+        qemu_co_queue_init(&fst->throttled_reqs[0]);
+        qemu_co_queue_init(&fst->throttled_reqs[1]);
+    }
+}
+
+void coroutine_fn fsdev_co_throttle_request(FsThrottle *fst, bool is_write,
+                                            struct iovec *iov, int iovcnt)
+{
+    if (throttle_enabled(&fst->cfg)) {
+        if (throttle_schedule_timer(&fst->ts, &fst->tt, is_write) ||
+            !qemu_co_queue_empty(&fst->throttled_reqs[is_write])) {
+            qemu_co_queue_wait(&fst->throttled_reqs[is_write], NULL);
+        }
+
+        throttle_account(&fst->ts, is_write, iov_size(iov, iovcnt));
+
+        if (!qemu_co_queue_empty(&fst->throttled_reqs[is_write]) &&
+            !throttle_schedule_timer(&fst->ts, &fst->tt, is_write)) {
+            qemu_co_queue_next(&fst->throttled_reqs[is_write]);
+        }
+    }
+}
+
+void fsdev_throttle_cleanup(FsThrottle *fst)
+{
+    if (throttle_enabled(&fst->cfg)) {
+        throttle_timers_destroy(&fst->tt);
+    }
+}

fsdev/qemu-fsdev-throttle.h

@@ -0,0 +1,39 @@
+/*
+ * Fsdev Throttle
+ *
+ * Copyright (C) 2016 Huawei Technologies Duesseldorf GmbH
+ *
+ * Author: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ *
+ */
+
+#ifndef _FSDEV_THROTTLE_H
+#define _FSDEV_THROTTLE_H
+
+#include "block/aio.h"
+#include "qemu/main-loop.h"
+#include "qemu/coroutine.h"
+#include "qapi/error.h"
+#include "qemu/throttle.h"
+
+typedef struct FsThrottle {
+    ThrottleState ts;
+    ThrottleTimers tt;
+    ThrottleConfig cfg;
+    CoQueue      throttled_reqs[2];
+} FsThrottle;
+
+void fsdev_throttle_parse_opts(QemuOpts *, FsThrottle *, Error **);
+
+void fsdev_throttle_init(FsThrottle *);
+
+void coroutine_fn fsdev_co_throttle_request(FsThrottle *, bool ,
+                                            struct iovec *, int);
+
+void fsdev_throttle_cleanup(FsThrottle *);
+#endif /* _FSDEV_THROTTLE_H */

hmp.c

@@ -2045,13 +2045,17 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
     const char* device = qdict_get_str(qdict, "device");
     const char* command = qdict_get_str(qdict, "command");
     Error *err = NULL;
+    int ret;
 
     blk = blk_by_name(device);
     if (!blk) {
         BlockDriverState *bs = bdrv_lookup_bs(NULL, device, &err);
         if (bs) {
-            blk = local_blk = blk_new();
-            blk_insert_bs(blk, bs);
+            blk = local_blk = blk_new(0, BLK_PERM_ALL);
+            ret = blk_insert_bs(blk, bs, &err);
+            if (ret < 0) {
+                goto fail;
+            }
         } else {
             goto fail;
         }
@@ -2060,6 +2064,31 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
     aio_context = blk_get_aio_context(blk);
     aio_context_acquire(aio_context);
 
+    /*
+     * Notably absent: Proper permission management. This is sad, but it seems
+     * almost impossible to achieve without changing the semantics and thereby
+     * limiting the use cases of the qemu-io HMP command.
+     *
+     * In an ideal world we would unconditionally create a new BlockBackend for
+     * qemuio_command(), but we have commands like 'reopen' and want them to
+     * take effect on the exact BlockBackend whose name the user passed instead
+     * of just on a temporary copy of it.
+     *
+     * Another problem is that deleting the temporary BlockBackend involves
+     * draining all requests on it first, but some qemu-iotests cases want to
+     * issue multiple aio_read/write requests and expect them to complete in
+     * the background while the monitor has already returned.
+     *
+     * This is also what prevents us from saving the original permissions and
+     * restoring them later: We can't revoke permissions until all requests
+     * have completed, and we don't know when that is nor can we really let
+     * anything else run before we have revoken them to avoid race conditions.
+     *
+     * What happens now is that command() in qemu-io-cmds.c can extend the
+     * permissions if necessary for the qemu-io command. And they simply stay
+     * extended, possibly resulting in a read-only guest device keeping write
+     * permissions. Ugly, but it appears to be the lesser evil.
+     */
     qemuio_command(blk, command);
 
     aio_context_release(aio_context);

hw/9pfs/9p-local.h

@@ -0,0 +1,20 @@
+/*
+ * 9p local backend utilities
+ *
+ * Copyright IBM, Corp. 2017
+ *
+ * Authors:
+ *  Greg Kurz <groug@kaod.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_9P_LOCAL_H
+#define QEMU_9P_LOCAL_H
+
+int local_open_nofollow(FsContext *fs_ctx, const char *path, int flags,
+                        mode_t mode);
+int local_opendir_nofollow(FsContext *fs_ctx, const char *path);
+
+#endif

hw/9pfs/9p-posix-acl.c

@@ -25,13 +25,7 @@
 static ssize_t mp_pacl_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char *buffer;
-    ssize_t ret;
-
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, MAP_ACL_ACCESS, value, size);
-    g_free(buffer);
-    return ret;
+    return local_getxattr_nofollow(ctx, path, MAP_ACL_ACCESS, value, size);
 }
 
 static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path,
@@ -56,23 +50,16 @@ static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path,
 static int mp_pacl_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, MAP_ACL_ACCESS, value, size, flags);
-    g_free(buffer);
-    return ret;
+    return local_setxattr_nofollow(ctx, path, MAP_ACL_ACCESS, value, size,
+                                   flags);
 }
 
 static int mp_pacl_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
     int ret;
-    char *buffer;
 
-    buffer = rpath(ctx, path);
-    ret  = lremovexattr(buffer, MAP_ACL_ACCESS);
+    ret = local_removexattr_nofollow(ctx, path, MAP_ACL_ACCESS);
     if (ret == -1 && errno == ENODATA) {
         /*
          * We don't get ENODATA error when trying to remove a
@@ -82,20 +69,13 @@ static int mp_pacl_removexattr(FsContext *ctx,
         errno = 0;
         ret = 0;
     }
-    g_free(buffer);
     return ret;
 }
 
 static ssize_t mp_dacl_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char *buffer;
-    ssize_t ret;
-
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, MAP_ACL_DEFAULT, value, size);
-    g_free(buffer);
-    return ret;
+    return local_getxattr_nofollow(ctx, path, MAP_ACL_DEFAULT, value, size);
 }
 
 static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path,
@@ -120,23 +100,16 @@ static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path,
 static int mp_dacl_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, MAP_ACL_DEFAULT, value, size, flags);
-    g_free(buffer);
-    return ret;
+    return local_setxattr_nofollow(ctx, path, MAP_ACL_DEFAULT, value, size,
+                                   flags);
 }
 
 static int mp_dacl_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
     int ret;
-    char *buffer;
 
-    buffer = rpath(ctx, path);
-    ret  = lremovexattr(buffer, MAP_ACL_DEFAULT);
+    ret = local_removexattr_nofollow(ctx, path, MAP_ACL_DEFAULT);
     if (ret == -1 && errno == ENODATA) {
         /*
          * We don't get ENODATA error when trying to remove a
@@ -146,7 +119,6 @@ static int mp_dacl_removexattr(FsContext *ctx,
         errno = 0;
         ret = 0;
     }
-    g_free(buffer);
     return ret;
 }
 

hw/9pfs/9p-util.c

@@ -0,0 +1,69 @@
+/*
+ * 9p utilities
+ *
+ * Copyright IBM, Corp. 2017
+ *
+ * Authors:
+ *  Greg Kurz <groug@kaod.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/xattr.h"
+#include "9p-util.h"
+
+int relative_openat_nofollow(int dirfd, const char *path, int flags,
+                             mode_t mode)
+{
+    int fd;
+
+    fd = dup(dirfd);
+    if (fd == -1) {
+        return -1;
+    }
+
+    while (*path) {
+        const char *c;
+        int next_fd;
+        char *head;
+
+        /* Only relative paths without consecutive slashes */
+        assert(path[0] != '/');
+
+        head = g_strdup(path);
+        c = strchr(path, '/');
+        if (c) {
+            head[c - path] = 0;
+            next_fd = openat_dir(fd, head);
+        } else {
+            next_fd = openat_file(fd, head, flags, mode);
+        }
+        g_free(head);
+        if (next_fd == -1) {
+            close_preserve_errno(fd);
+            return -1;
+        }
+        close(fd);
+        fd = next_fd;
+
+        if (!c) {
+            break;
+        }
+        path = c + 1;
+    }
+
+    return fd;
+}
+
+ssize_t fgetxattrat_nofollow(int dirfd, const char *filename, const char *name,
+                             void *value, size_t size)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = lgetxattr(proc_path, name, value, size);
+    g_free(proc_path);
+    return ret;
+}

hw/9pfs/9p-util.h

@@ -0,0 +1,54 @@
+/*
+ * 9p utilities
+ *
+ * Copyright IBM, Corp. 2017
+ *
+ * Authors:
+ *  Greg Kurz <groug@kaod.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_9P_UTIL_H
+#define QEMU_9P_UTIL_H
+
+static inline void close_preserve_errno(int fd)
+{
+    int serrno = errno;
+    close(fd);
+    errno = serrno;
+}
+
+static inline int openat_dir(int dirfd, const char *name)
+{
+    return openat(dirfd, name, O_DIRECTORY | O_RDONLY | O_PATH);
+}
+
+static inline int openat_file(int dirfd, const char *name, int flags,
+                              mode_t mode)
+{
+    int fd, serrno, ret;
+
+    fd = openat(dirfd, name, flags | O_NOFOLLOW | O_NOCTTY | O_NONBLOCK,
+                mode);
+    if (fd == -1) {
+        return -1;
+    }
+
+    serrno = errno;
+    /* O_NONBLOCK was only needed to open the file. Let's drop it. */
+    ret = fcntl(fd, F_SETFL, flags);
+    assert(!ret);
+    errno = serrno;
+    return fd;
+}
+
+int relative_openat_nofollow(int dirfd, const char *path, int flags,
+                             mode_t mode);
+ssize_t fgetxattrat_nofollow(int dirfd, const char *path, const char *name,
+                             void *value, size_t size);
+int fsetxattrat_nofollow(int dirfd, const char *path, const char *name,
+                         void *value, size_t size, int flags);
+
+#endif

hw/9pfs/9p-xattr-user.c

@@ -20,9 +20,6 @@
 static ssize_t mp_user_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char *buffer;
-    ssize_t ret;
-
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -31,10 +28,7 @@ static ssize_t mp_user_getxattr(FsContext *ctx, const char *path,
         errno = ENOATTR;
         return -1;
     }
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, name, value, size);
-    g_free(buffer);
-    return ret;
+    return local_getxattr_nofollow(ctx, path, name, value, size);
 }
 
 static ssize_t mp_user_listxattr(FsContext *ctx, const char *path,
@@ -73,9 +67,6 @@ static ssize_t mp_user_listxattr(FsContext *ctx, const char *path,
 static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char *buffer;
-    int ret;
-
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -84,18 +75,12 @@ static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name,
         errno = EACCES;
         return -1;
     }
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, name, value, size, flags);
-    g_free(buffer);
-    return ret;
+    return local_setxattr_nofollow(ctx, path, name, value, size, flags);
 }
 
 static int mp_user_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
-    char *buffer;
-    int ret;
-
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -104,10 +89,7 @@ static int mp_user_removexattr(FsContext *ctx,
         errno = EACCES;
         return -1;
     }
-    buffer = rpath(ctx, path);
-    ret = lremovexattr(buffer, name);
-    g_free(buffer);
-    return ret;
+    return local_removexattr_nofollow(ctx, path, name);
 }
 
 XattrOperations mapped_user_xattr = {

hw/9pfs/9p-xattr.c

@@ -15,6 +15,8 @@
 #include "9p.h"
 #include "fsdev/file-op-9p.h"
 #include "9p-xattr.h"
+#include "9p-util.h"
+#include "9p-local.h"
 
 
 static XattrOperations *get_xattr_operations(XattrOperations **h,
@@ -58,6 +60,16 @@ ssize_t pt_listxattr(FsContext *ctx, const char *path,
     return name_size;
 }
 
+static ssize_t flistxattrat_nofollow(int dirfd, const char *filename,
+                                     char *list, size_t size)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = llistxattr(proc_path, list, size);
+    g_free(proc_path);
+    return ret;
+}
 
 /*
  * Get the list and pass to each layer to find out whether
@@ -67,24 +79,37 @@ ssize_t v9fs_list_xattr(FsContext *ctx, const char *path,
                         void *value, size_t vsize)
 {
     ssize_t size = 0;
-    char *buffer;
     void *ovalue = value;
     XattrOperations *xops;
     char *orig_value, *orig_value_start;
     ssize_t xattr_len, parsed_len = 0, attr_len;
+    char *dirpath, *name;
+    int dirfd;
 
     /* Get the actual len */
-    buffer = rpath(ctx, path);
-    xattr_len = llistxattr(buffer, value, 0);
+    dirpath = g_path_get_dirname(path);
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    g_free(dirpath);
+    if (dirfd == -1) {
+        return -1;
+    }
+
+    name = g_path_get_basename(path);
+    xattr_len = flistxattrat_nofollow(dirfd, name, value, 0);
     if (xattr_len <= 0) {
-        g_free(buffer);
+        g_free(name);
+        close_preserve_errno(dirfd);
         return xattr_len;
     }
 
     /* Now fetch the xattr and find the actual size */
     orig_value = g_malloc(xattr_len);
-    xattr_len = llistxattr(buffer, orig_value, xattr_len);
-    g_free(buffer);
+    xattr_len = flistxattrat_nofollow(dirfd, name, orig_value, xattr_len);
+    g_free(name);
+    close_preserve_errno(dirfd);
+    if (xattr_len < 0) {
+        return -1;
+    }
 
     /* store the orig pointer */
     orig_value_start = orig_value;
@@ -143,6 +168,135 @@ int v9fs_remove_xattr(FsContext *ctx,
 
 }
 
+ssize_t local_getxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size)
+{
+    char *dirpath = g_path_get_dirname(path);
+    char *filename = g_path_get_basename(path);
+    int dirfd;
+    ssize_t ret = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    ret = fgetxattrat_nofollow(dirfd, filename, name, value, size);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(filename);
+    return ret;
+}
+
+ssize_t pt_getxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size)
+{
+    return local_getxattr_nofollow(ctx, path, name, value, size);
+}
+
+int fsetxattrat_nofollow(int dirfd, const char *filename, const char *name,
+                         void *value, size_t size, int flags)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = lsetxattr(proc_path, name, value, size, flags);
+    g_free(proc_path);
+    return ret;
+}
+
+ssize_t local_setxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size,
+                                int flags)
+{
+    char *dirpath = g_path_get_dirname(path);
+    char *filename = g_path_get_basename(path);
+    int dirfd;
+    ssize_t ret = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    ret = fsetxattrat_nofollow(dirfd, filename, name, value, size, flags);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(filename);
+    return ret;
+}
+
+int pt_setxattr(FsContext *ctx, const char *path, const char *name, void *value,
+                size_t size, int flags)
+{
+    return local_setxattr_nofollow(ctx, path, name, value, size, flags);
+}
+
+static ssize_t fremovexattrat_nofollow(int dirfd, const char *filename,
+                                       const char *name)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = lremovexattr(proc_path, name);
+    g_free(proc_path);
+    return ret;
+}
+
+ssize_t local_removexattr_nofollow(FsContext *ctx, const char *path,
+                                   const char *name)
+{
+    char *dirpath = g_path_get_dirname(path);
+    char *filename = g_path_get_basename(path);
+    int dirfd;
+    ssize_t ret = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    ret = fremovexattrat_nofollow(dirfd, filename, name);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(filename);
+    return ret;
+}
+
+int pt_removexattr(FsContext *ctx, const char *path, const char *name)
+{
+    return local_removexattr_nofollow(ctx, path, name);
+}
+
+ssize_t notsup_getxattr(FsContext *ctx, const char *path, const char *name,
+                        void *value, size_t size)
+{
+    errno = ENOTSUP;
+    return -1;
+}
+
+int notsup_setxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size, int flags)
+{
+    errno = ENOTSUP;
+    return -1;
+}
+
+ssize_t notsup_listxattr(FsContext *ctx, const char *path, char *name,
+                         void *value, size_t size)
+{
+    return 0;
+}
+
+int notsup_removexattr(FsContext *ctx, const char *path, const char *name)
+{
+    errno = ENOTSUP;
+    return -1;
+}
+
 XattrOperations *mapped_xattr_ops[] = {
     &mapped_user_xattr,
     &mapped_pacl_xattr,

hw/9pfs/9p-xattr.h

@@ -29,6 +29,13 @@ typedef struct xattr_operations
                        const char *path, const char *name);
 } XattrOperations;
 
+ssize_t local_getxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size);
+ssize_t local_setxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size,
+                                int flags);
+ssize_t local_removexattr_nofollow(FsContext *ctx, const char *path,
+                                   const char *name);
 
 extern XattrOperations mapped_user_xattr;
 extern XattrOperations passthrough_user_xattr;
@@ -49,73 +56,21 @@ ssize_t v9fs_list_xattr(FsContext *ctx, const char *path, void *value,
 int v9fs_set_xattr(FsContext *ctx, const char *path, const char *name,
                           void *value, size_t size, int flags);
 int v9fs_remove_xattr(FsContext *ctx, const char *path, const char *name);
+
 ssize_t pt_listxattr(FsContext *ctx, const char *path, char *name, void *value,
                      size_t size);
+ssize_t pt_getxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size);
+int pt_setxattr(FsContext *ctx, const char *path, const char *name, void *value,
+                size_t size, int flags);
+int pt_removexattr(FsContext *ctx, const char *path, const char *name);
 
-static inline ssize_t pt_getxattr(FsContext *ctx, const char *path,
-                                  const char *name, void *value, size_t size)
-{
-    char *buffer;
-    ssize_t ret;
-
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, name, value, size);
-    g_free(buffer);
-    return ret;
-}
-
-static inline int pt_setxattr(FsContext *ctx, const char *path,
-                              const char *name, void *value,
-                              size_t size, int flags)
-{
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, name, value, size, flags);
-    g_free(buffer);
-    return ret;
-}
-
-static inline int pt_removexattr(FsContext *ctx,
-                                 const char *path, const char *name)
-{
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lremovexattr(path, name);
-    g_free(buffer);
-    return ret;
-}
-
-static inline ssize_t notsup_getxattr(FsContext *ctx, const char *path,
-                                      const char *name, void *value,
-                                      size_t size)
-{
-    errno = ENOTSUP;
-    return -1;
-}
-
-static inline int notsup_setxattr(FsContext *ctx, const char *path,
-                                  const char *name, void *value,
-                                  size_t size, int flags)
-{
-    errno = ENOTSUP;
-    return -1;
-}
-
-static inline ssize_t notsup_listxattr(FsContext *ctx, const char *path,
-                                       char *name, void *value, size_t size)
-{
-    return 0;
-}
-
-static inline int notsup_removexattr(FsContext *ctx,
-                                     const char *path, const char *name)
-{
-    errno = ENOTSUP;
-    return -1;
-}
+ssize_t notsup_getxattr(FsContext *ctx, const char *path, const char *name,
+                        void *value, size_t size);
+int notsup_setxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size, int flags);
+ssize_t notsup_listxattr(FsContext *ctx, const char *path, char *name,
+                         void *value, size_t size);
+int notsup_removexattr(FsContext *ctx, const char *path, const char *name);
 
 #endif

hw/9pfs/9p.c

@@ -3010,7 +3010,6 @@ out_nofid:
  */
 static void coroutine_fn v9fs_lock(void *opaque)
 {
-    int8_t status;
     V9fsFlock flock;
     size_t offset = 7;
     struct stat stbuf;
@@ -3018,7 +3017,6 @@ static void coroutine_fn v9fs_lock(void *opaque)
     int32_t fid, err = 0;
     V9fsPDU *pdu = opaque;
 
-    status = P9_LOCK_ERROR;
     v9fs_string_init(&flock.client_id);
     err = pdu_unmarshal(pdu, offset, "dbdqqds", &fid, &flock.type,
                         &flock.flags, &flock.start, &flock.length,
@@ -3044,15 +3042,15 @@ static void coroutine_fn v9fs_lock(void *opaque)
     if (err < 0) {
         goto out;
     }
-    status = P9_LOCK_SUCCESS;
+    err = pdu_marshal(pdu, offset, "b", P9_LOCK_SUCCESS);
+    if (err < 0) {
+        goto out;
+    }
+    err += offset;
+    trace_v9fs_lock_return(pdu->tag, pdu->id, P9_LOCK_SUCCESS);
 out:
     put_fid(pdu, fidp);
 out_nofid:
-    err = pdu_marshal(pdu, offset, "b", status);
-    if (err > 0) {
-        err += offset;
-    }
-    trace_v9fs_lock_return(pdu->tag, pdu->id, status);
     pdu_complete(pdu, err);
     v9fs_string_free(&flock.client_id);
 }
@@ -3531,6 +3529,10 @@ int v9fs_device_realize_common(V9fsState *s, Error **errp)
         error_setg(errp, "share path %s is not a directory", fse->path);
         goto out;
     }
+
+    s->ctx.fst = &fse->fst;
+    fsdev_throttle_init(s->ctx.fst);
+
     v9fs_path_free(&path);
 
     rc = 0;
@@ -3551,6 +3553,7 @@ void v9fs_device_unrealize_common(V9fsState *s, Error **errp)
     if (s->ops->cleanup) {
         s->ops->cleanup(&s->ctx);
     }
+    fsdev_throttle_cleanup(s->ctx.fst);
     g_free(s->tag);
     g_free(s->ctx.fs_root);
 }

hw/9pfs/Makefile.objs

@@ -1,4 +1,4 @@
-common-obj-y  = 9p.o
+common-obj-y  = 9p.o 9p-util.o
 common-obj-y += 9p-local.o 9p-xattr.o
 common-obj-y += 9p-xattr-user.o 9p-posix-acl.o
 common-obj-y += coth.o cofs.o codir.o cofile.o

hw/9pfs/cofile.c

@@ -247,6 +247,7 @@ int coroutine_fn v9fs_co_pwritev(V9fsPDU *pdu, V9fsFidState *fidp,
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
+    fsdev_co_throttle_request(s->ctx.fst, true, iov, iovcnt);
     v9fs_co_run_in_worker(
         {
             err = s->ops->pwritev(&s->ctx, &fidp->fs, iov, iovcnt, offset);
@@ -266,6 +267,7 @@ int coroutine_fn v9fs_co_preadv(V9fsPDU *pdu, V9fsFidState *fidp,
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
+    fsdev_co_throttle_request(s->ctx.fst, false, iov, iovcnt);
     v9fs_co_run_in_worker(
         {
             err = s->ops->preadv(&s->ctx, &fidp->fs, iov, iovcnt, offset);

hw/acpi/pcihp.c

@@ -49,7 +49,6 @@
 
 #define ACPI_PCIHP_ADDR 0xae00
 #define ACPI_PCIHP_SIZE 0x0014
-#define ACPI_PCIHP_LEGACY_SIZE 0x000f
 #define PCI_UP_BASE 0x0000
 #define PCI_DOWN_BASE 0x0004
 #define PCI_EJ_BASE 0x0008
@@ -302,16 +301,6 @@ void acpi_pcihp_init(Object *owner, AcpiPciHpState *s, PCIBus *root_bus,
     s->root= root_bus;
     s->legacy_piix = !bridges_enabled;
 
-    if (s->legacy_piix) {
-        unsigned *bus_bsel = g_malloc(sizeof *bus_bsel);
-
-        s->io_len = ACPI_PCIHP_LEGACY_SIZE;
-
-        *bus_bsel = ACPI_PCIHP_BSEL_DEFAULT;
-        object_property_add_uint32_ptr(OBJECT(root_bus), ACPI_PCIHP_PROP_BSEL,
-                                       bus_bsel, NULL);
-    }
-
     memory_region_init_io(&s->io, owner, &acpi_pcihp_io_ops, s,
                           "acpi-pci-hotplug", s->io_len);
     memory_region_add_subregion(address_space_io, s->io_base, &s->io);

hw/acpi/piix4.c

@@ -440,6 +440,8 @@ static void piix4_update_bus_hotplug(PCIBus *pci_bus, void *opaque)
 {
     PIIX4PMState *s = opaque;
 
+    /* pci_bus cannot outlive PIIX4PMState, because /machine keeps it alive
+     * and it's not hot-unpluggable */
     qbus_set_hotplug_handler(BUS(pci_bus), DEVICE(s), &error_abort);
 }
 

hw/acpi/tco.c

@@ -49,6 +49,7 @@ static inline void tco_timer_reload(TCOIORegs *tr)
 static inline void tco_timer_stop(TCOIORegs *tr)
 {
     tr->expire_time = -1;
+    timer_del(tr->tco_timer);
 }
 
 static void tco_timer_expired(void *opaque)

hw/arm/armv7m.c

@@ -8,6 +8,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "hw/arm/armv7m.h"
 #include "qapi/error.h"
 #include "qemu-common.h"
 #include "cpu.h"
@@ -17,148 +18,261 @@
 #include "elf.h"
 #include "sysemu/qtest.h"
 #include "qemu/error-report.h"
+#include "exec/address-spaces.h"
 
 /* Bitbanded IO.  Each word corresponds to a single bit.  */
 
 /* Get the byte address of the real memory for a bitband access.  */
-static inline uint32_t bitband_addr(void * opaque, uint32_t addr)
+static inline hwaddr bitband_addr(BitBandState *s, hwaddr offset)
 {
-    uint32_t res;
-
-    res = *(uint32_t *)opaque;
-    res |= (addr & 0x1ffffff) >> 5;
-    return res;
-
+    return s->base | (offset & 0x1ffffff) >> 5;
 }
 
-static uint32_t bitband_readb(void *opaque, hwaddr offset)
+static MemTxResult bitband_read(void *opaque, hwaddr offset,
+                                uint64_t *data, unsigned size, MemTxAttrs attrs)
 {
-    uint8_t v;
-    cpu_physical_memory_read(bitband_addr(opaque, offset), &v, 1);
-    return (v & (1 << ((offset >> 2) & 7))) != 0;
+    BitBandState *s = opaque;
+    uint8_t buf[4];
+    MemTxResult res;
+    int bitpos, bit;
+    hwaddr addr;
+
+    assert(size <= 4);
+
+    /* Find address in underlying memory and round down to multiple of size */
+    addr = bitband_addr(s, offset) & (-size);
+    res = address_space_read(s->source_as, addr, attrs, buf, size);
+    if (res) {
+        return res;
+    }
+    /* Bit position in the N bytes read... */
+    bitpos = (offset >> 2) & ((size * 8) - 1);
+    /* ...converted to byte in buffer and bit in byte */
+    bit = (buf[bitpos >> 3] >> (bitpos & 7)) & 1;
+    *data = bit;
+    return MEMTX_OK;
 }
 
-static void bitband_writeb(void *opaque, hwaddr offset,
-                           uint32_t value)
+static MemTxResult bitband_write(void *opaque, hwaddr offset, uint64_t value,
+                                 unsigned size, MemTxAttrs attrs)
 {
-    uint32_t addr;
-    uint8_t mask;
-    uint8_t v;
-    addr = bitband_addr(opaque, offset);
-    mask = (1 << ((offset >> 2) & 7));
-    cpu_physical_memory_read(addr, &v, 1);
-    if (value & 1)
-        v |= mask;
-    else
-        v &= ~mask;
-    cpu_physical_memory_write(addr, &v, 1);
-}
+    BitBandState *s = opaque;
+    uint8_t buf[4];
+    MemTxResult res;
+    int bitpos, bit;
+    hwaddr addr;
 
-static uint32_t bitband_readw(void *opaque, hwaddr offset)
-{
-    uint32_t addr;
-    uint16_t mask;
-    uint16_t v;
-    addr = bitband_addr(opaque, offset) & ~1;
-    mask = (1 << ((offset >> 2) & 15));
-    mask = tswap16(mask);
-    cpu_physical_memory_read(addr, &v, 2);
-    return (v & mask) != 0;
-}
+    assert(size <= 4);
 
-static void bitband_writew(void *opaque, hwaddr offset,
-                           uint32_t value)
-{
-    uint32_t addr;
-    uint16_t mask;
-    uint16_t v;
-    addr = bitband_addr(opaque, offset) & ~1;
-    mask = (1 << ((offset >> 2) & 15));
-    mask = tswap16(mask);
-    cpu_physical_memory_read(addr, &v, 2);
-    if (value & 1)
-        v |= mask;
-    else
-        v &= ~mask;
-    cpu_physical_memory_write(addr, &v, 2);
-}
-
-static uint32_t bitband_readl(void *opaque, hwaddr offset)
-{
-    uint32_t addr;
-    uint32_t mask;
-    uint32_t v;
-    addr = bitband_addr(opaque, offset) & ~3;
-    mask = (1 << ((offset >> 2) & 31));
-    mask = tswap32(mask);
-    cpu_physical_memory_read(addr, &v, 4);
-    return (v & mask) != 0;
-}
-
-static void bitband_writel(void *opaque, hwaddr offset,
-                           uint32_t value)
-{
-    uint32_t addr;
-    uint32_t mask;
-    uint32_t v;
-    addr = bitband_addr(opaque, offset) & ~3;
-    mask = (1 << ((offset >> 2) & 31));
-    mask = tswap32(mask);
-    cpu_physical_memory_read(addr, &v, 4);
-    if (value & 1)
-        v |= mask;
-    else
-        v &= ~mask;
-    cpu_physical_memory_write(addr, &v, 4);
+    /* Find address in underlying memory and round down to multiple of size */
+    addr = bitband_addr(s, offset) & (-size);
+    res = address_space_read(s->source_as, addr, attrs, buf, size);
+    if (res) {
+        return res;
+    }
+    /* Bit position in the N bytes read... */
+    bitpos = (offset >> 2) & ((size * 8) - 1);
+    /* ...converted to byte in buffer and bit in byte */
+    bit = 1 << (bitpos & 7);
+    if (value & 1) {
+        buf[bitpos >> 3] |= bit;
+    } else {
+        buf[bitpos >> 3] &= ~bit;
+    }
+    return address_space_write(s->source_as, addr, attrs, buf, size);
 }
 
 static const MemoryRegionOps bitband_ops = {
-    .old_mmio = {
-        .read = { bitband_readb, bitband_readw, bitband_readl, },
-        .write = { bitband_writeb, bitband_writew, bitband_writel, },
-    },
+    .read_with_attrs = bitband_read,
+    .write_with_attrs = bitband_write,
     .endianness = DEVICE_NATIVE_ENDIAN,
+    .impl.min_access_size = 1,
+    .impl.max_access_size = 4,
+    .valid.min_access_size = 1,
+    .valid.max_access_size = 4,
 };
 
-#define TYPE_BITBAND "ARM,bitband-memory"
-#define BITBAND(obj) OBJECT_CHECK(BitBandState, (obj), TYPE_BITBAND)
-
-typedef struct {
-    /*< private >*/
-    SysBusDevice parent_obj;
-    /*< public >*/
-
-    MemoryRegion iomem;
-    uint32_t base;
-} BitBandState;
-
 static void bitband_init(Object *obj)
 {
     BitBandState *s = BITBAND(obj);
     SysBusDevice *dev = SYS_BUS_DEVICE(obj);
 
-    memory_region_init_io(&s->iomem, obj, &bitband_ops, &s->base,
+    object_property_add_link(obj, "source-memory",
+                             TYPE_MEMORY_REGION,
+                             (Object **)&s->source_memory,
+                             qdev_prop_allow_set_link_before_realize,
+                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             &error_abort);
+    memory_region_init_io(&s->iomem, obj, &bitband_ops, s,
                           "bitband", 0x02000000);
     sysbus_init_mmio(dev, &s->iomem);
 }
 
-static void armv7m_bitband_init(void)
+static void bitband_realize(DeviceState *dev, Error **errp)
 {
-    DeviceState *dev;
+    BitBandState *s = BITBAND(dev);
 
-    dev = qdev_create(NULL, TYPE_BITBAND);
-    qdev_prop_set_uint32(dev, "base", 0x20000000);
-    qdev_init_nofail(dev);
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0x22000000);
+    if (!s->source_memory) {
+        error_setg(errp, "source-memory property not set");
+        return;
+    }
 
-    dev = qdev_create(NULL, TYPE_BITBAND);
-    qdev_prop_set_uint32(dev, "base", 0x40000000);
-    qdev_init_nofail(dev);
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0x42000000);
+    s->source_as = address_space_init_shareable(s->source_memory,
+                                                "bitband-source");
 }
 
 /* Board init.  */
 
+static const hwaddr bitband_input_addr[ARMV7M_NUM_BITBANDS] = {
+    0x20000000, 0x40000000
+};
+
+static const hwaddr bitband_output_addr[ARMV7M_NUM_BITBANDS] = {
+    0x22000000, 0x42000000
+};
+
+static void armv7m_instance_init(Object *obj)
+{
+    ARMv7MState *s = ARMV7M(obj);
+    int i;
+
+    /* Can't init the cpu here, we don't yet know which model to use */
+
+    object_property_add_link(obj, "memory",
+                             TYPE_MEMORY_REGION,
+                             (Object **)&s->board_memory,
+                             qdev_prop_allow_set_link_before_realize,
+                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             &error_abort);
+    memory_region_init(&s->container, obj, "armv7m-container", UINT64_MAX);
+
+    object_initialize(&s->nvic, sizeof(s->nvic), "armv7m_nvic");
+    qdev_set_parent_bus(DEVICE(&s->nvic), sysbus_get_default());
+    object_property_add_alias(obj, "num-irq",
+                              OBJECT(&s->nvic), "num-irq", &error_abort);
+
+    for (i = 0; i < ARRAY_SIZE(s->bitband); i++) {
+        object_initialize(&s->bitband[i], sizeof(s->bitband[i]), TYPE_BITBAND);
+        qdev_set_parent_bus(DEVICE(&s->bitband[i]), sysbus_get_default());
+    }
+}
+
+static void armv7m_realize(DeviceState *dev, Error **errp)
+{
+    ARMv7MState *s = ARMV7M(dev);
+    SysBusDevice *sbd;
+    Error *err = NULL;
+    int i;
+    char **cpustr;
+    ObjectClass *oc;
+    const char *typename;
+    CPUClass *cc;
+
+    if (!s->board_memory) {
+        error_setg(errp, "memory property was not set");
+        return;
+    }
+
+    memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1);
+
+    cpustr = g_strsplit(s->cpu_model, ",", 2);
+
+    oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]);
+    if (!oc) {
+        error_setg(errp, "Unknown CPU model %s", cpustr[0]);
+        g_strfreev(cpustr);
+        return;
+    }
+
+    cc = CPU_CLASS(oc);
+    typename = object_class_get_name(oc);
+    cc->parse_features(typename, cpustr[1], &err);
+    g_strfreev(cpustr);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    s->cpu = ARM_CPU(object_new(typename));
+    if (!s->cpu) {
+        error_setg(errp, "Unknown CPU model %s", s->cpu_model);
+        return;
+    }
+
+    object_property_set_link(OBJECT(s->cpu), OBJECT(&s->container), "memory",
+                             &error_abort);
+    object_property_set_bool(OBJECT(s->cpu), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    /* Note that we must realize the NVIC after the CPU */
+    object_property_set_bool(OBJECT(&s->nvic), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    /* Alias the NVIC's input and output GPIOs as our own so the board
+     * code can wire them up. (We do this in realize because the
+     * NVIC doesn't create the input GPIO array until realize.)
+     */
+    qdev_pass_gpios(DEVICE(&s->nvic), dev, NULL);
+    qdev_pass_gpios(DEVICE(&s->nvic), dev, "SYSRESETREQ");
+
+    /* Wire the NVIC up to the CPU */
+    sbd = SYS_BUS_DEVICE(&s->nvic);
+    sysbus_connect_irq(sbd, 0,
+                       qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ));
+    s->cpu->env.nvic = &s->nvic;
+
+    memory_region_add_subregion(&s->container, 0xe000e000,
+                                sysbus_mmio_get_region(sbd, 0));
+
+    for (i = 0; i < ARRAY_SIZE(s->bitband); i++) {
+        Object *obj = OBJECT(&s->bitband[i]);
+        SysBusDevice *sbd = SYS_BUS_DEVICE(&s->bitband[i]);
+
+        object_property_set_int(obj, bitband_input_addr[i], "base", &err);
+        if (err != NULL) {
+            error_propagate(errp, err);
+            return;
+        }
+        object_property_set_link(obj, OBJECT(s->board_memory),
+                                 "source-memory", &error_abort);
+        object_property_set_bool(obj, true, "realized", &err);
+        if (err != NULL) {
+            error_propagate(errp, err);
+            return;
+        }
+
+        memory_region_add_subregion(&s->container, bitband_output_addr[i],
+                                    sysbus_mmio_get_region(sbd, 0));
+    }
+}
+
+static Property armv7m_properties[] = {
+    DEFINE_PROP_STRING("cpu-model", ARMv7MState, cpu_model),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void armv7m_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->realize = armv7m_realize;
+    dc->props = armv7m_properties;
+}
+
+static const TypeInfo armv7m_info = {
+    .name = TYPE_ARMV7M,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(ARMv7MState),
+    .instance_init = armv7m_instance_init,
+    .class_init = armv7m_class_init,
+};
+
 static void armv7m_reset(void *opaque)
 {
     ARMCPU *cpu = opaque;
@@ -168,38 +282,36 @@ static void armv7m_reset(void *opaque)
 
 /* Init CPU and memory for a v7-M based board.
    mem_size is in bytes.
-   Returns the NVIC array.  */
+   Returns the ARMv7M device.  */
 
 DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq,
                       const char *kernel_filename, const char *cpu_model)
 {
-    ARMCPU *cpu;
-    CPUARMState *env;
-    DeviceState *nvic;
+    DeviceState *armv7m;
+
+    if (cpu_model == NULL) {
+        cpu_model = "cortex-m3";
+    }
+
+    armv7m = qdev_create(NULL, "armv7m");
+    qdev_prop_set_uint32(armv7m, "num-irq", num_irq);
+    qdev_prop_set_string(armv7m, "cpu-model", cpu_model);
+    object_property_set_link(OBJECT(armv7m), OBJECT(get_system_memory()),
+                                     "memory", &error_abort);
+    /* This will exit with an error if the user passed us a bad cpu_model */
+    qdev_init_nofail(armv7m);
+
+    armv7m_load_kernel(ARM_CPU(first_cpu), kernel_filename, mem_size);
+    return armv7m;
+}
+
+void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size)
+{
     int image_size;
     uint64_t entry;
     uint64_t lowaddr;
     int big_endian;
 
-    if (cpu_model == NULL) {
-	cpu_model = "cortex-m3";
-    }
-    cpu = cpu_arm_init(cpu_model);
-    if (cpu == NULL) {
-        fprintf(stderr, "Unable to find CPU definition\n");
-        exit(1);
-    }
-    env = &cpu->env;
-
-    armv7m_bitband_init();
-
-    nvic = qdev_create(NULL, "armv7m_nvic");
-    qdev_prop_set_uint32(nvic, "num-irq", num_irq);
-    env->nvic = nvic;
-    qdev_init_nofail(nvic);
-    sysbus_connect_irq(SYS_BUS_DEVICE(nvic), 0,
-                       qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));
-
 #ifdef TARGET_WORDS_BIGENDIAN
     big_endian = 1;
 #else
@@ -224,8 +336,15 @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq,
         }
     }
 
+    /* CPU objects (unlike devices) are not automatically reset on system
+     * reset, so we must always register a handler to do so. Unlike
+     * A-profile CPUs, we don't need to do anything special in the
+     * handler to arrange that it starts correctly.
+     * This is arguably the wrong place to do this, but it matches the
+     * way A-profile does it. Note that this means that every M profile
+     * board must call this function!
+     */
     qemu_register_reset(armv7m_reset, cpu);
-    return nvic;
 }
 
 static Property bitband_properties[] = {
@@ -237,6 +356,7 @@ static void bitband_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
+    dc->realize = bitband_realize;
     dc->props = bitband_properties;
 }
 
@@ -251,6 +371,7 @@ static const TypeInfo bitband_info = {
 static void armv7m_register_types(void)
 {
     type_register_static(&bitband_info);
+    type_register_static(&armv7m_info);
 }
 
 type_init(armv7m_register_types)

hw/arm/bcm2835_peripherals.c

@@ -86,11 +86,21 @@ static void bcm2835_peripherals_init(Object *obj)
     object_property_add_const_link(OBJECT(&s->property), "dma-mr",
                                    OBJECT(&s->gpu_bus_mr), &error_abort);
 
+    /* Random Number Generator */
+    object_initialize(&s->rng, sizeof(s->rng), TYPE_BCM2835_RNG);
+    object_property_add_child(obj, "rng", OBJECT(&s->rng), NULL);
+    qdev_set_parent_bus(DEVICE(&s->rng), sysbus_get_default());
+
     /* Extended Mass Media Controller */
     object_initialize(&s->sdhci, sizeof(s->sdhci), TYPE_SYSBUS_SDHCI);
     object_property_add_child(obj, "sdhci", OBJECT(&s->sdhci), NULL);
     qdev_set_parent_bus(DEVICE(&s->sdhci), sysbus_get_default());
 
+    /* SDHOST */
+    object_initialize(&s->sdhost, sizeof(s->sdhost), TYPE_BCM2835_SDHOST);
+    object_property_add_child(obj, "sdhost", OBJECT(&s->sdhost), NULL);
+    qdev_set_parent_bus(DEVICE(&s->sdhost), sysbus_get_default());
+
     /* DMA Channels */
     object_initialize(&s->dma, sizeof(s->dma), TYPE_BCM2835_DMA);
     object_property_add_child(obj, "dma", OBJECT(&s->dma), NULL);
@@ -98,6 +108,16 @@ static void bcm2835_peripherals_init(Object *obj)
 
     object_property_add_const_link(OBJECT(&s->dma), "dma-mr",
                                    OBJECT(&s->gpu_bus_mr), &error_abort);
+
+    /* GPIO */
+    object_initialize(&s->gpio, sizeof(s->gpio), TYPE_BCM2835_GPIO);
+    object_property_add_child(obj, "gpio", OBJECT(&s->gpio), NULL);
+    qdev_set_parent_bus(DEVICE(&s->gpio), sysbus_get_default());
+
+    object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhci",
+                                   OBJECT(&s->sdhci.sdbus), &error_abort);
+    object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhost",
+                                   OBJECT(&s->sdhost.sdbus), &error_abort);
 }
 
 static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
@@ -226,6 +246,16 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->property), 0,
                       qdev_get_gpio_in(DEVICE(&s->mboxes), MBOX_CHAN_PROPERTY));
 
+    /* Random Number Generator */
+    object_property_set_bool(OBJECT(&s->rng), true, "realized", &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    memory_region_add_subregion(&s->peri_mr, RNG_OFFSET,
+                sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->rng), 0));
+
     /* Extended Mass Media Controller */
     object_property_set_int(OBJECT(&s->sdhci), BCM2835_SDHC_CAPAREG, "capareg",
                             &err);
@@ -252,13 +282,20 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhci), 0,
         qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
                                INTERRUPT_ARASANSDIO));
-    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->sdhci), "sd-bus",
-                              &err);
+
+    /* SDHOST */
+    object_property_set_bool(OBJECT(&s->sdhost), true, "realized", &err);
     if (err) {
         error_propagate(errp, err);
         return;
     }
 
+    memory_region_add_subregion(&s->peri_mr, MMCI0_OFFSET,
+                sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->sdhost), 0));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhost), 0,
+        qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
+                               INTERRUPT_SDIO));
+
     /* DMA Channels */
     object_property_set_bool(OBJECT(&s->dma), true, "realized", &err);
     if (err) {
@@ -277,6 +314,23 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
                                                   BCM2835_IC_GPU_IRQ,
                                                   INTERRUPT_DMA0 + n));
     }
+
+    /* GPIO */
+    object_property_set_bool(OBJECT(&s->gpio), true, "realized", &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    memory_region_add_subregion(&s->peri_mr, GPIO_OFFSET,
+                sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->gpio), 0));
+
+    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->gpio), "sd-bus",
+                              &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 }
 
 static void bcm2835_peripherals_class_init(ObjectClass *oc, void *data)

hw/arm/exynos4210.c

@@ -24,6 +24,7 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "qemu-common.h"
+#include "qemu/log.h"
 #include "cpu.h"
 #include "hw/boards.h"
 #include "sysemu/sysemu.h"
@@ -74,6 +75,9 @@
 /* PMU SFR base address */
 #define EXYNOS4210_PMU_BASE_ADDR            0x10020000
 
+/* Clock controller SFR base address */
+#define EXYNOS4210_CLK_BASE_ADDR            0x10030000
+
 /* Display controllers (FIMD) */
 #define EXYNOS4210_FIMD0_BASE_ADDR          0x11C00000
 
@@ -138,6 +142,16 @@ void exynos4210_write_secondary(ARMCPU *cpu,
                        info->smp_loader_start);
 }
 
+static uint64_t exynos4210_calc_affinity(int cpu)
+{
+    uint64_t mp_affinity;
+
+    /* Exynos4210 has 0x9 as cluster ID */
+    mp_affinity = (0x9 << ARM_AFF1_SHIFT) | cpu;
+
+    return mp_affinity;
+}
+
 Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
         unsigned long ram_size)
 {
@@ -163,6 +177,8 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
         }
 
         s->cpu[n] = ARM_CPU(cpuobj);
+        object_property_set_int(cpuobj, exynos4210_calc_affinity(n),
+                                "mp-affinity", &error_abort);
         object_property_set_int(cpuobj, EXYNOS4210_SMP_PRIVATE_BASE_ADDR,
                                 "reset-cbar", &error_abort);
         object_property_set_bool(cpuobj, true, "realized", &error_fatal);
@@ -297,6 +313,8 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
     */
     sysbus_create_simple("exynos4210.pmu", EXYNOS4210_PMU_BASE_ADDR, NULL);
 
+    sysbus_create_simple("exynos4210.clk", EXYNOS4210_CLK_BASE_ADDR, NULL);
+
     /* PWM */
     sysbus_create_varargs("exynos4210.pwm", EXYNOS4210_PWM_BASE_ADDR,
                           s->irq_table[exynos4210_get_irq(22, 0)],

hw/arm/netduino2.c

@@ -27,17 +27,18 @@
 #include "hw/boards.h"
 #include "qemu/error-report.h"
 #include "hw/arm/stm32f205_soc.h"
+#include "hw/arm/arm.h"
 
 static void netduino2_init(MachineState *machine)
 {
     DeviceState *dev;
 
     dev = qdev_create(NULL, TYPE_STM32F205_SOC);
-    if (machine->kernel_filename) {
-        qdev_prop_set_string(dev, "kernel-filename", machine->kernel_filename);
-    }
     qdev_prop_set_string(dev, "cpu-model", "cortex-m3");
     object_property_set_bool(OBJECT(dev), true, "realized", &error_fatal);
+
+    armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename,
+                       FLASH_SIZE);
 }
 
 static void netduino2_machine_init(MachineClass *mc)

hw/arm/stm32f205_soc.c

@@ -49,6 +49,9 @@ static void stm32f205_soc_initfn(Object *obj)
     STM32F205State *s = STM32F205_SOC(obj);
     int i;
 
+    object_initialize(&s->armv7m, sizeof(s->armv7m), TYPE_ARMV7M);
+    qdev_set_parent_bus(DEVICE(&s->armv7m), sysbus_get_default());
+
     object_initialize(&s->syscfg, sizeof(s->syscfg), TYPE_STM32F2XX_SYSCFG);
     qdev_set_parent_bus(DEVICE(&s->syscfg), sysbus_get_default());
 
@@ -82,7 +85,7 @@ static void stm32f205_soc_initfn(Object *obj)
 static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
 {
     STM32F205State *s = STM32F205_SOC(dev_soc);
-    DeviceState *dev, *nvic;
+    DeviceState *dev, *armv7m;
     SysBusDevice *busdev;
     Error *err = NULL;
     int i;
@@ -110,8 +113,16 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
     vmstate_register_ram_global(sram);
     memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram);
 
-    nvic = armv7m_init(get_system_memory(), FLASH_SIZE, 96,
-                       s->kernel_filename, s->cpu_model);
+    armv7m = DEVICE(&s->armv7m);
+    qdev_prop_set_uint32(armv7m, "num-irq", 96);
+    qdev_prop_set_string(armv7m, "cpu-model", s->cpu_model);
+    object_property_set_link(OBJECT(&s->armv7m), OBJECT(get_system_memory()),
+                                     "memory", &error_abort);
+    object_property_set_bool(OBJECT(&s->armv7m), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
 
     /* System configuration controller */
     dev = DEVICE(&s->syscfg);
@@ -122,7 +133,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
     }
     busdev = SYS_BUS_DEVICE(dev);
     sysbus_mmio_map(busdev, 0, 0x40013800);
-    sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, 71));
+    sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, 71));
 
     /* Attach UART (uses USART registers) and USART controllers */
     for (i = 0; i < STM_NUM_USARTS; i++) {
@@ -136,7 +147,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         }
         busdev = SYS_BUS_DEVICE(dev);
         sysbus_mmio_map(busdev, 0, usart_addr[i]);
-        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, usart_irq[i]));
+        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, usart_irq[i]));
     }
 
     /* Timer 2 to 5 */
@@ -150,7 +161,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         }
         busdev = SYS_BUS_DEVICE(dev);
         sysbus_mmio_map(busdev, 0, timer_addr[i]);
-        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, timer_irq[i]));
+        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, timer_irq[i]));
     }
 
     /* ADC 1 to 3 */
@@ -162,7 +173,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         return;
     }
     qdev_connect_gpio_out(DEVICE(s->adc_irqs), 0,
-                          qdev_get_gpio_in(nvic, ADC_IRQ));
+                          qdev_get_gpio_in(armv7m, ADC_IRQ));
 
     for (i = 0; i < STM_NUM_ADCS; i++) {
         dev = DEVICE(&(s->adc[i]));
@@ -187,12 +198,11 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         }
         busdev = SYS_BUS_DEVICE(dev);
         sysbus_mmio_map(busdev, 0, spi_addr[i]);
-        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, spi_irq[i]));
+        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, spi_irq[i]));
     }
 }
 
 static Property stm32f205_soc_properties[] = {
-    DEFINE_PROP_STRING("kernel-filename", STM32F205State, kernel_filename),
     DEFINE_PROP_STRING("cpu-model", STM32F205State, cpu_model),
     DEFINE_PROP_END_OF_LIST(),
 };

hw/arm/virt.c

@@ -535,7 +535,6 @@ static void create_v2m(VirtMachineState *vms, qemu_irq *pic)
 static void create_gic(VirtMachineState *vms, qemu_irq *pic)
 {
     /* We create a standalone GIC */
-    VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
     DeviceState *gicdev;
     SysBusDevice *gicbusdev;
     const char *gictype;
@@ -605,7 +604,7 @@ static void create_gic(VirtMachineState *vms, qemu_irq *pic)
 
     fdt_add_gic_node(vms);
 
-    if (type == 3 && !vmc->no_its) {
+    if (type == 3 && vms->its) {
         create_its(vms, gicdev);
     } else if (type == 2) {
         create_v2m(vms, pic);
@@ -1378,6 +1377,7 @@ static void machvirt_init(MachineState *machine)
         }
 
         object_property_set_bool(cpuobj, true, "realized", NULL);
+        object_unref(cpuobj);
     }
     fdt_add_timer_nodes(vms);
     fdt_add_cpu_nodes(vms);
@@ -1480,6 +1480,20 @@ static void virt_set_highmem(Object *obj, bool value, Error **errp)
     vms->highmem = value;
 }
 
+static bool virt_get_its(Object *obj, Error **errp)
+{
+    VirtMachineState *vms = VIRT_MACHINE(obj);
+
+    return vms->its;
+}
+
+static void virt_set_its(Object *obj, bool value, Error **errp)
+{
+    VirtMachineState *vms = VIRT_MACHINE(obj);
+
+    vms->its = value;
+}
+
 static char *virt_get_gic_version(Object *obj, Error **errp)
 {
     VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -1540,6 +1554,7 @@ type_init(machvirt_machine_init);
 static void virt_2_9_instance_init(Object *obj)
 {
     VirtMachineState *vms = VIRT_MACHINE(obj);
+    VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
 
     /* EL3 is disabled by default on virt: this makes us consistent
      * between KVM and TCG for this board, and it also allows us to
@@ -1579,6 +1594,19 @@ static void virt_2_9_instance_init(Object *obj)
                                     "Set GIC version. "
                                     "Valid values are 2, 3 and host", NULL);
 
+    if (vmc->no_its) {
+        vms->its = false;
+    } else {
+        /* Default allows ITS instantiation */
+        vms->its = true;
+        object_property_add_bool(obj, "its", virt_get_its,
+                                 virt_set_its, NULL);
+        object_property_set_description(obj, "its",
+                                        "Set on/off to enable/disable "
+                                        "ITS instantiation",
+                                        NULL);
+    }
+
     vms->memmap = a15memmap;
     vms->irqmap = a15irqmap;
 }

hw/block/block.c

@@ -51,11 +51,33 @@ void blkconf_blocksizes(BlockConf *conf)
     }
 }
 
-void blkconf_apply_backend_options(BlockConf *conf)
+void blkconf_apply_backend_options(BlockConf *conf, bool readonly,
+                                   bool resizable, Error **errp)
 {
     BlockBackend *blk = conf->blk;
     BlockdevOnError rerror, werror;
+    uint64_t perm, shared_perm;
     bool wce;
+    int ret;
+
+    perm = BLK_PERM_CONSISTENT_READ;
+    if (!readonly) {
+        perm |= BLK_PERM_WRITE;
+    }
+
+    shared_perm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                  BLK_PERM_GRAPH_MOD;
+    if (resizable) {
+        shared_perm |= BLK_PERM_RESIZE;
+    }
+    if (conf->share_rw) {
+        shared_perm |= BLK_PERM_WRITE;
+    }
+
+    ret = blk_set_perm(blk, perm, shared_perm, errp);
+    if (ret < 0) {
+        return;
+    }
 
     switch (conf->wce) {
     case ON_OFF_AUTO_ON:    wce = true; break;

hw/block/fdc.c

@@ -186,6 +186,7 @@ typedef enum FDiskFlags {
 struct FDrive {
     FDCtrl *fdctrl;
     BlockBackend *blk;
+    BlockConf *conf;
     /* Drive status */
     FloppyDriveType drive;    /* CMOS drive type        */
     uint8_t perpendicular;    /* 2.88 MB access mode    */
@@ -469,9 +470,22 @@ static void fd_revalidate(FDrive *drv)
     }
 }
 
-static void fd_change_cb(void *opaque, bool load)
+static void fd_change_cb(void *opaque, bool load, Error **errp)
 {
     FDrive *drive = opaque;
+    Error *local_err = NULL;
+
+    if (!load) {
+        blk_set_perm(drive->blk, 0, BLK_PERM_ALL, &error_abort);
+    } else {
+        blkconf_apply_backend_options(drive->conf,
+                                      blk_is_read_only(drive->blk), false,
+                                      &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+        }
+    }
 
     drive->media_changed = 1;
     drive->media_validated = false;
@@ -508,6 +522,7 @@ static int floppy_drive_init(DeviceState *qdev)
     FloppyDrive *dev = FLOPPY_DRIVE(qdev);
     FloppyBus *bus = FLOPPY_BUS(qdev->parent_bus);
     FDrive *drive;
+    Error *local_err = NULL;
     int ret;
 
     if (dev->unit == -1) {
@@ -533,7 +548,7 @@ static int floppy_drive_init(DeviceState *qdev)
 
     if (!dev->conf.blk) {
         /* Anonymous BlockBackend for an empty drive */
-        dev->conf.blk = blk_new();
+        dev->conf.blk = blk_new(0, BLK_PERM_ALL);
         ret = blk_attach_dev(dev->conf.blk, qdev);
         assert(ret == 0);
     }
@@ -551,7 +566,13 @@ static int floppy_drive_init(DeviceState *qdev)
      * blkconf_apply_backend_options(). */
     dev->conf.rerror = BLOCKDEV_ON_ERROR_AUTO;
     dev->conf.werror = BLOCKDEV_ON_ERROR_AUTO;
-    blkconf_apply_backend_options(&dev->conf);
+
+    blkconf_apply_backend_options(&dev->conf, blk_is_read_only(dev->conf.blk),
+                                  false, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
 
     /* 'enospc' is the default for -drive, 'report' is what blk_new() gives us
      * for empty drives. */
@@ -565,6 +586,7 @@ static int floppy_drive_init(DeviceState *qdev)
         return -1;
     }
 
+    drive->conf = &dev->conf;
     drive->blk = dev->conf.blk;
     drive->fdctrl = bus->fdc;
 

hw/block/m25p80.c

@@ -1215,6 +1215,7 @@ static void m25p80_realize(SSISlave *ss, Error **errp)
 {
     Flash *s = M25P80(ss);
     M25P80Class *mc = M25P80_GET_CLASS(s);
+    int ret;
 
     s->pi = mc->pi;
 
@@ -1222,6 +1223,13 @@ static void m25p80_realize(SSISlave *ss, Error **errp)
     s->dirty_page = -1;
 
     if (s->blk) {
+        uint64_t perm = BLK_PERM_CONSISTENT_READ |
+                        (blk_is_read_only(s->blk) ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(s->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+
         DB_PRINT_L(0, "Binding to IF_MTD drive\n");
         s->storage = blk_blockalign(s->blk, s->size);
 

hw/block/nand.c

@@ -373,6 +373,8 @@ static void nand_realize(DeviceState *dev, Error **errp)
 {
     int pagesize;
     NANDFlashState *s = NAND(dev);
+    int ret;
+
 
     s->buswidth = nand_flash_ids[s->chip_id].width >> 3;
     s->size = nand_flash_ids[s->chip_id].size << 20;
@@ -407,6 +409,11 @@ static void nand_realize(DeviceState *dev, Error **errp)
             error_setg(errp, "Can't use a read-only drive");
             return;
         }
+        ret = blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
         if (blk_getlength(s->blk) >=
                 (s->pages << s->page_shift) + (s->pages << s->oob_shift)) {
             pagesize = 0;

hw/block/nvme.c

@@ -835,6 +835,7 @@ static int nvme_init(PCIDevice *pci_dev)
     int i;
     int64_t bs_size;
     uint8_t *pci_conf;
+    Error *local_err = NULL;
 
     if (!n->conf.blk) {
         return -1;
@@ -850,7 +851,12 @@ static int nvme_init(PCIDevice *pci_dev)
         return -1;
     }
     blkconf_blocksizes(&n->conf);
-    blkconf_apply_backend_options(&n->conf);
+    blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                  false, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
 
     pci_conf = pci_dev->config;
     pci_conf[PCI_INTERRUPT_PIN] = 1;

hw/block/onenand.c

@@ -778,6 +778,7 @@ static int onenand_initfn(SysBusDevice *sbd)
     OneNANDState *s = ONE_NAND(dev);
     uint32_t size = 1 << (24 + ((s->id.dev >> 4) & 7));
     void *ram;
+    Error *local_err = NULL;
 
     s->base = (hwaddr)-1;
     s->rdy = NULL;
@@ -796,6 +797,12 @@ static int onenand_initfn(SysBusDevice *sbd)
             error_report("Can't use a read-only drive");
             return -1;
         }
+        blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                     BLK_PERM_ALL, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
         s->blk_cur = s->blk;
     }
     s->otp = memset(g_malloc((64 + 2) << PAGE_SHIFT),

hw/block/pflash_cfi01.c

@@ -757,6 +757,18 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
     pfl->storage = memory_region_get_ram_ptr(&pfl->mem);
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
 
+    if (pfl->blk) {
+        uint64_t perm;
+        pfl->ro = blk_is_read_only(pfl->blk);
+        perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+    } else {
+        pfl->ro = 0;
+    }
+
     if (pfl->blk) {
         /* read the initial flash content */
         ret = blk_pread(pfl->blk, 0, pfl->storage, total_len);
@@ -768,12 +780,6 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
         }
     }
 
-    if (pfl->blk) {
-        pfl->ro = blk_is_read_only(pfl->blk);
-    } else {
-        pfl->ro = 0;
-    }
-
     /* Default to devices being used at their maximum device width. This was
      * assumed before the device_width support was added.
      */

hw/block/pflash_cfi02.c

@@ -632,6 +632,19 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     vmstate_register_ram(&pfl->orig_mem, DEVICE(pfl));
     pfl->storage = memory_region_get_ram_ptr(&pfl->orig_mem);
     pfl->chip_len = chip_len;
+
+    if (pfl->blk) {
+        uint64_t perm;
+        pfl->ro = blk_is_read_only(pfl->blk);
+        perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+    } else {
+        pfl->ro = 0;
+    }
+
     if (pfl->blk) {
         /* read the initial flash content */
         ret = blk_pread(pfl->blk, 0, pfl->storage, chip_len);
@@ -646,12 +659,6 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     pfl->rom_mode = 1;
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
 
-    if (pfl->blk) {
-        pfl->ro = blk_is_read_only(pfl->blk);
-    } else {
-        pfl->ro = 0;
-    }
-
     pfl->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pflash_timer, pfl);
     pfl->wcycle = 0;
     pfl->cmd = 0;

hw/block/virtio-blk.c

@@ -928,7 +928,13 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     }
 
     blkconf_serial(&conf->conf, &conf->serial);
-    blkconf_apply_backend_options(&conf->conf);
+    blkconf_apply_backend_options(&conf->conf,
+                                  blk_is_read_only(conf->conf.blk), true,
+                                  &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
     s->original_wce = blk_enable_write_cache(conf->conf.blk);
     blkconf_geometry(&conf->conf, NULL, 65535, 255, 255, &err);
     if (err) {

hw/core/bus.c

@@ -197,7 +197,7 @@ static void qbus_initfn(Object *obj)
                              TYPE_HOTPLUG_HANDLER,
                              (Object **)&bus->hotplug_handler,
                              object_property_allow_set_link,
-                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             0,
                              NULL);
     object_property_add_bool(obj, "realized",
                              bus_get_realized, bus_set_realized, NULL);

hw/core/loader.c

@@ -434,6 +434,19 @@ int load_elf_as(const char *filename,
                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
                 uint64_t *highaddr, int big_endian, int elf_machine,
                 int clear_lsb, int data_swab, AddressSpace *as)
+{
+    return load_elf_ram(filename, translate_fn, translate_opaque,
+                        pentry, lowaddr, highaddr, big_endian, elf_machine,
+                        clear_lsb, data_swab, as, true);
+}
+
+/* return < 0 if error, otherwise the number of bytes loaded in memory */
+int load_elf_ram(const char *filename,
+                 uint64_t (*translate_fn)(void *, uint64_t),
+                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
+                 uint64_t *highaddr, int big_endian, int elf_machine,
+                 int clear_lsb, int data_swab, AddressSpace *as,
+                 bool load_rom)
 {
     int fd, data_order, target_data_order, must_swab, ret = ELF_LOAD_FAILED;
     uint8_t e_ident[EI_NIDENT];
@@ -473,11 +486,11 @@ int load_elf_as(const char *filename,
     if (e_ident[EI_CLASS] == ELFCLASS64) {
         ret = load_elf64(filename, fd, translate_fn, translate_opaque, must_swab,
                          pentry, lowaddr, highaddr, elf_machine, clear_lsb,
-                         data_swab, as);
+                         data_swab, as, load_rom);
     } else {
         ret = load_elf32(filename, fd, translate_fn, translate_opaque, must_swab,
                          pentry, lowaddr, highaddr, elf_machine, clear_lsb,
-                         data_swab, as);
+                         data_swab, as, load_rom);
     }
 
  fail:

hw/core/or-irq.c

@@ -89,6 +89,9 @@ static void or_irq_class_init(ObjectClass *klass, void *data)
     dc->props = or_irq_properties;
     dc->realize = or_irq_realize;
     dc->vmsd = &vmstate_or_irq;
+
+    /* Reason: Needs to be wired up to work, e.g. see stm32f205_soc.c */
+    dc->cannot_instantiate_with_device_add_yet = true;
 }
 
 static const TypeInfo or_irq_type_info = {

hw/core/ptimer.c

@@ -12,6 +12,7 @@
 #include "qemu/host-utils.h"
 #include "sysemu/replay.h"
 #include "sysemu/qtest.h"
+#include "block/aio.h"
 
 #define DELTA_ADJUST     1
 #define DELTA_NO_ADJUST -1
@@ -353,3 +354,10 @@ ptimer_state *ptimer_init(QEMUBH *bh, uint8_t policy_mask)
     s->policy_mask = policy_mask;
     return s;
 }
+
+void ptimer_free(ptimer_state *s)
+{
+    qemu_bh_delete(s->bh);
+    timer_free(s->timer);
+    g_free(s);
+}

hw/core/qdev-properties-system.c

@@ -73,14 +73,19 @@ static void parse_drive(DeviceState *dev, const char *str, void **ptr,
 {
     BlockBackend *blk;
     bool blk_created = false;
+    int ret;
 
     blk = blk_by_name(str);
     if (!blk) {
         BlockDriverState *bs = bdrv_lookup_bs(NULL, str, NULL);
         if (bs) {
-            blk = blk_new();
-            blk_insert_bs(blk, bs);
+            blk = blk_new(0, BLK_PERM_ALL);
             blk_created = true;
+
+            ret = blk_insert_bs(blk, bs, errp);
+            if (ret < 0) {
+                goto fail;
+            }
         }
     }
     if (!blk) {

hw/core/qdev.c

@@ -37,6 +37,7 @@
 #include "hw/boards.h"
 #include "hw/sysbus.h"
 #include "qapi-event.h"
+#include "migration/migration.h"
 
 int qdev_hotplug = 0;
 static bool qdev_hot_added = false;
@@ -102,9 +103,23 @@ static void bus_add_child(BusState *bus, DeviceState *child)
 
 void qdev_set_parent_bus(DeviceState *dev, BusState *bus)
 {
+    bool replugging = dev->parent_bus != NULL;
+
+    if (replugging) {
+        /* Keep a reference to the device while it's not plugged into
+         * any bus, to avoid it potentially evaporating when it is
+         * dereffed in bus_remove_child().
+         */
+        object_ref(OBJECT(dev));
+        bus_remove_child(dev->parent_bus, dev);
+        object_unref(OBJECT(dev->parent_bus));
+    }
     dev->parent_bus = bus;
     object_ref(OBJECT(bus));
     bus_add_child(bus, dev);
+    if (replugging) {
+        object_unref(OBJECT(dev));
+    }
 }
 
 /* Create a new device.  This only initializes the device state
@@ -889,6 +904,7 @@ static void device_set_realized(Object *obj, bool value, Error **errp)
     Error *local_err = NULL;
     bool unattached_parent = false;
     static int unattached_count;
+    int ret;
 
     if (dev->hotplugged && !dc->hotpluggable) {
         error_setg(errp, QERR_DEVICE_NO_HOTPLUG, object_get_typename(obj));
@@ -896,6 +912,11 @@ static void device_set_realized(Object *obj, bool value, Error **errp)
     }
 
     if (value && !dev->realized) {
+        ret = check_migratable(obj, &local_err);
+        if (ret < 0) {
+            goto fail;
+        }
+
         if (!obj->parent) {
             gchar *name = g_strdup_printf("device[%d]", unattached_count++);
 

hw/core/register.c

@@ -59,6 +59,15 @@ static inline uint64_t register_read_val(RegisterInfo *reg)
     return 0; /* unreachable */
 }
 
+static inline uint64_t register_enabled_mask(int data_size, unsigned size)
+{
+    if (data_size < size) {
+        size = data_size;
+    }
+
+    return MAKE_64BIT_MASK(0, size * 8);
+}
+
 void register_write(RegisterInfo *reg, uint64_t val, uint64_t we,
                     const char *prefix, bool debug)
 {
@@ -192,11 +201,7 @@ void register_write_memory(void *opaque, hwaddr addr,
     }
 
     /* Generate appropriate write enable mask */
-    if (reg->data_size < size) {
-        we = MAKE_64BIT_MASK(0, reg->data_size * 8);
-    } else {
-        we = MAKE_64BIT_MASK(0, size * 8);
-    }
+    we = register_enabled_mask(reg->data_size, size);
 
     register_write(reg, value, we, reg_array->prefix,
                    reg_array->debug);
@@ -208,6 +213,7 @@ uint64_t register_read_memory(void *opaque, hwaddr addr,
     RegisterInfoArray *reg_array = opaque;
     RegisterInfo *reg = NULL;
     uint64_t read_val;
+    uint64_t re;
     int i;
 
     for (i = 0; i < reg_array->num_elements; i++) {
@@ -223,7 +229,10 @@ uint64_t register_read_memory(void *opaque, hwaddr addr,
         return 0;
     }
 
-    read_val = register_read(reg, size * 8, reg_array->prefix,
+    /* Generate appropriate read enable mask */
+    re = register_enabled_mask(reg->data_size, size);
+
+    read_val = register_read(reg, re, reg_array->prefix,
                              reg_array->debug);
 
     return extract64(read_val, 0, size * 8);
@@ -274,9 +283,18 @@ void register_finalize_block(RegisterInfoArray *r_array)
     g_free(r_array);
 }
 
+static void register_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    /* Reason: needs to be wired up to work */
+    dc->cannot_instantiate_with_device_add_yet = true;
+}
+
 static const TypeInfo register_info = {
     .name  = TYPE_REGISTER,
     .parent = TYPE_DEVICE,
+    .class_init = register_class_init,
 };
 
 static void register_register_types(void)

hw/display/milkymist-tmu2.c

@@ -293,7 +293,7 @@ static void tmu2_start(MilkymistTMU2State *s)
     cpu_physical_memory_unmap(mesh, mesh_len, 0, mesh_len);
 
     /* Write back the OpenGL framebuffer to the QEMU framebuffer */
-    fb_len = 2 * s->regs[R_DSTHRES] * s->regs[R_DSTVRES];
+    fb_len = 2ULL * s->regs[R_DSTHRES] * s->regs[R_DSTVRES];
     fb = cpu_physical_memory_map(s->regs[R_DSTFBUF], &fb_len, 1);
     if (fb == NULL) {
         glDeleteTextures(1, &texture);

hw/gpio/Makefile.objs

@@ -7,3 +7,4 @@ common-obj-$(CONFIG_GPIO_KEY) += gpio_key.o
 
 obj-$(CONFIG_OMAP) += omap_gpio.o
 obj-$(CONFIG_IMX) += imx_gpio.o
+obj-$(CONFIG_RASPI) += bcm2835_gpio.o

hw/gpio/bcm2835_gpio.c

@@ -0,0 +1,353 @@
+/*
+ * Raspberry Pi (BCM2835) GPIO Controller
+ *
+ * Copyright (c) 2017 Antfield SAS
+ *
+ * Authors:
+ *  Clement Deschamps <clement.deschamps@antfield.fr>
+ *  Luc Michel <luc.michel@antfield.fr>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/log.h"
+#include "qemu/timer.h"
+#include "qapi/error.h"
+#include "hw/sysbus.h"
+#include "hw/sd/sd.h"
+#include "hw/gpio/bcm2835_gpio.h"
+
+#define GPFSEL0   0x00
+#define GPFSEL1   0x04
+#define GPFSEL2   0x08
+#define GPFSEL3   0x0C
+#define GPFSEL4   0x10
+#define GPFSEL5   0x14
+#define GPSET0    0x1C
+#define GPSET1    0x20
+#define GPCLR0    0x28
+#define GPCLR1    0x2C
+#define GPLEV0    0x34
+#define GPLEV1    0x38
+#define GPEDS0    0x40
+#define GPEDS1    0x44
+#define GPREN0    0x4C
+#define GPREN1    0x50
+#define GPFEN0    0x58
+#define GPFEN1    0x5C
+#define GPHEN0    0x64
+#define GPHEN1    0x68
+#define GPLEN0    0x70
+#define GPLEN1    0x74
+#define GPAREN0   0x7C
+#define GPAREN1   0x80
+#define GPAFEN0   0x88
+#define GPAFEN1   0x8C
+#define GPPUD     0x94
+#define GPPUDCLK0 0x98
+#define GPPUDCLK1 0x9C
+
+static uint32_t gpfsel_get(BCM2835GpioState *s, uint8_t reg)
+{
+    int i;
+    uint32_t value = 0;
+    for (i = 0; i < 10; i++) {
+        uint32_t index = 10 * reg + i;
+        if (index < sizeof(s->fsel)) {
+            value |= (s->fsel[index] & 0x7) << (3 * i);
+        }
+    }
+    return value;
+}
+
+static void gpfsel_set(BCM2835GpioState *s, uint8_t reg, uint32_t value)
+{
+    int i;
+    for (i = 0; i < 10; i++) {
+        uint32_t index = 10 * reg + i;
+        if (index < sizeof(s->fsel)) {
+            int fsel = (value >> (3 * i)) & 0x7;
+            s->fsel[index] = fsel;
+        }
+    }
+
+    /* SD controller selection (48-53) */
+    if (s->sd_fsel != 0
+            && (s->fsel[48] == 0) /* SD_CLK_R */
+            && (s->fsel[49] == 0) /* SD_CMD_R */
+            && (s->fsel[50] == 0) /* SD_DATA0_R */
+            && (s->fsel[51] == 0) /* SD_DATA1_R */
+            && (s->fsel[52] == 0) /* SD_DATA2_R */
+            && (s->fsel[53] == 0) /* SD_DATA3_R */
+            ) {
+        /* SDHCI controller selected */
+        sdbus_reparent_card(s->sdbus_sdhost, s->sdbus_sdhci);
+        s->sd_fsel = 0;
+    } else if (s->sd_fsel != 4
+            && (s->fsel[48] == 4) /* SD_CLK_R */
+            && (s->fsel[49] == 4) /* SD_CMD_R */
+            && (s->fsel[50] == 4) /* SD_DATA0_R */
+            && (s->fsel[51] == 4) /* SD_DATA1_R */
+            && (s->fsel[52] == 4) /* SD_DATA2_R */
+            && (s->fsel[53] == 4) /* SD_DATA3_R */
+            ) {
+        /* SDHost controller selected */
+        sdbus_reparent_card(s->sdbus_sdhci, s->sdbus_sdhost);
+        s->sd_fsel = 4;
+    }
+}
+
+static int gpfsel_is_out(BCM2835GpioState *s, int index)
+{
+    if (index >= 0 && index < 54) {
+        return s->fsel[index] == 1;
+    }
+    return 0;
+}
+
+static void gpset(BCM2835GpioState *s,
+        uint32_t val, uint8_t start, uint8_t count, uint32_t *lev)
+{
+    uint32_t changes = val & ~*lev;
+    uint32_t cur = 1;
+
+    int i;
+    for (i = 0; i < count; i++) {
+        if ((changes & cur) && (gpfsel_is_out(s, start + i))) {
+            qemu_set_irq(s->out[start + i], 1);
+        }
+        cur <<= 1;
+    }
+
+    *lev |= val;
+}
+
+static void gpclr(BCM2835GpioState *s,
+        uint32_t val, uint8_t start, uint8_t count, uint32_t *lev)
+{
+    uint32_t changes = val & *lev;
+    uint32_t cur = 1;
+
+    int i;
+    for (i = 0; i < count; i++) {
+        if ((changes & cur) && (gpfsel_is_out(s, start + i))) {
+            qemu_set_irq(s->out[start + i], 0);
+        }
+        cur <<= 1;
+    }
+
+    *lev &= ~val;
+}
+
+static uint64_t bcm2835_gpio_read(void *opaque, hwaddr offset,
+        unsigned size)
+{
+    BCM2835GpioState *s = (BCM2835GpioState *)opaque;
+
+    switch (offset) {
+    case GPFSEL0:
+    case GPFSEL1:
+    case GPFSEL2:
+    case GPFSEL3:
+    case GPFSEL4:
+    case GPFSEL5:
+        return gpfsel_get(s, offset / 4);
+    case GPSET0:
+    case GPSET1:
+        /* Write Only */
+        return 0;
+    case GPCLR0:
+    case GPCLR1:
+        /* Write Only */
+        return 0;
+    case GPLEV0:
+        return s->lev0;
+    case GPLEV1:
+        return s->lev1;
+    case GPEDS0:
+    case GPEDS1:
+    case GPREN0:
+    case GPREN1:
+    case GPFEN0:
+    case GPFEN1:
+    case GPHEN0:
+    case GPHEN1:
+    case GPLEN0:
+    case GPLEN1:
+    case GPAREN0:
+    case GPAREN1:
+    case GPAFEN0:
+    case GPAFEN1:
+    case GPPUD:
+    case GPPUDCLK0:
+    case GPPUDCLK1:
+        /* Not implemented */
+        return 0;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n",
+                __func__, offset);
+        break;
+    }
+
+    return 0;
+}
+
+static void bcm2835_gpio_write(void *opaque, hwaddr offset,
+        uint64_t value, unsigned size)
+{
+    BCM2835GpioState *s = (BCM2835GpioState *)opaque;
+
+    switch (offset) {
+    case GPFSEL0:
+    case GPFSEL1:
+    case GPFSEL2:
+    case GPFSEL3:
+    case GPFSEL4:
+    case GPFSEL5:
+        gpfsel_set(s, offset / 4, value);
+        break;
+    case GPSET0:
+        gpset(s, value, 0, 32, &s->lev0);
+        break;
+    case GPSET1:
+        gpset(s, value, 32, 22, &s->lev1);
+        break;
+    case GPCLR0:
+        gpclr(s, value, 0, 32, &s->lev0);
+        break;
+    case GPCLR1:
+        gpclr(s, value, 32, 22, &s->lev1);
+        break;
+    case GPLEV0:
+    case GPLEV1:
+        /* Read Only */
+        break;
+    case GPEDS0:
+    case GPEDS1:
+    case GPREN0:
+    case GPREN1:
+    case GPFEN0:
+    case GPFEN1:
+    case GPHEN0:
+    case GPHEN1:
+    case GPLEN0:
+    case GPLEN1:
+    case GPAREN0:
+    case GPAREN1:
+    case GPAFEN0:
+    case GPAFEN1:
+    case GPPUD:
+    case GPPUDCLK0:
+    case GPPUDCLK1:
+        /* Not implemented */
+        break;
+    default:
+        goto err_out;
+    }
+    return;
+
+err_out:
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n",
+            __func__, offset);
+}
+
+static void bcm2835_gpio_reset(DeviceState *dev)
+{
+    BCM2835GpioState *s = BCM2835_GPIO(dev);
+
+    int i;
+    for (i = 0; i < 6; i++) {
+        gpfsel_set(s, i, 0);
+    }
+
+    s->sd_fsel = 0;
+
+    /* SDHCI is selected by default */
+    sdbus_reparent_card(&s->sdbus, s->sdbus_sdhci);
+
+    s->lev0 = 0;
+    s->lev1 = 0;
+}
+
+static const MemoryRegionOps bcm2835_gpio_ops = {
+    .read = bcm2835_gpio_read,
+    .write = bcm2835_gpio_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static const VMStateDescription vmstate_bcm2835_gpio = {
+    .name = "bcm2835_gpio",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT8_ARRAY(fsel, BCM2835GpioState, 54),
+        VMSTATE_UINT32(lev0, BCM2835GpioState),
+        VMSTATE_UINT32(lev1, BCM2835GpioState),
+        VMSTATE_UINT8(sd_fsel, BCM2835GpioState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void bcm2835_gpio_init(Object *obj)
+{
+    BCM2835GpioState *s = BCM2835_GPIO(obj);
+    DeviceState *dev = DEVICE(obj);
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+
+    qbus_create_inplace(&s->sdbus, sizeof(s->sdbus),
+                        TYPE_SD_BUS, DEVICE(s), "sd-bus");
+
+    memory_region_init_io(&s->iomem, obj,
+            &bcm2835_gpio_ops, s, "bcm2835_gpio", 0x1000);
+    sysbus_init_mmio(sbd, &s->iomem);
+    qdev_init_gpio_out(dev, s->out, 54);
+}
+
+static void bcm2835_gpio_realize(DeviceState *dev, Error **errp)
+{
+    BCM2835GpioState *s = BCM2835_GPIO(dev);
+    Object *obj;
+    Error *err = NULL;
+
+    obj = object_property_get_link(OBJECT(dev), "sdbus-sdhci", &err);
+    if (obj == NULL) {
+        error_setg(errp, "%s: required sdhci link not found: %s",
+                __func__, error_get_pretty(err));
+        return;
+    }
+    s->sdbus_sdhci = SD_BUS(obj);
+
+    obj = object_property_get_link(OBJECT(dev), "sdbus-sdhost", &err);
+    if (obj == NULL) {
+        error_setg(errp, "%s: required sdhost link not found: %s",
+                __func__, error_get_pretty(err));
+        return;
+    }
+    s->sdbus_sdhost = SD_BUS(obj);
+}
+
+static void bcm2835_gpio_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->vmsd = &vmstate_bcm2835_gpio;
+    dc->realize = &bcm2835_gpio_realize;
+    dc->reset = &bcm2835_gpio_reset;
+}
+
+static const TypeInfo bcm2835_gpio_info = {
+    .name          = TYPE_BCM2835_GPIO,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(BCM2835GpioState),
+    .instance_init = bcm2835_gpio_init,
+    .class_init    = bcm2835_gpio_class_init,
+};
+
+static void bcm2835_gpio_register_types(void)
+{
+    type_register_static(&bcm2835_gpio_info);
+}
+
+type_init(bcm2835_gpio_register_types)

hw/i386/acpi-build.c

@@ -462,7 +462,7 @@ static void *acpi_set_bsel(PCIBus *bus, void *opaque)
 
         *bus_bsel = (*bsel_alloc)++;
         object_property_add_uint32_ptr(OBJECT(bus), ACPI_PCIHP_PROP_BSEL,
-                                       bus_bsel, NULL);
+                                       bus_bsel, &error_abort);
     }
 
     return bsel_alloc;
@@ -471,7 +471,7 @@ static void *acpi_set_bsel(PCIBus *bus, void *opaque)
 static void acpi_set_pci_info(void)
 {
     PCIBus *bus = find_i440fx(); /* TODO: Q35 support */
-    unsigned bsel_alloc = 0;
+    unsigned bsel_alloc = ACPI_PCIHP_BSEL_DEFAULT;
 
     if (bus) {
         /* Scan all PCI buses. Set property to enable acpi based hotplug. */