Update version for v2.4.0 release

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

.gitignore

@@ -17,6 +17,8 @@
 /trace/generated-tcg-tracers.h
 /trace/generated-ust-provider.h
 /trace/generated-ust.c
+/ui/shader/texture-blit-frag.h
+/ui/shader/texture-blit-vert.h
 /libcacard/trace/generated-tracers.c
 *-timestamp
 /*-softmmu

MAINTAINERS

@@ -1169,7 +1169,7 @@ S: Supported
 F: block/vmdk.c
 
 RBD
-M: Josh Durgin <josh.durgin@inktank.com>
+M: Josh Durgin <jdurgin@redhat.com>
 M: Jeff Cody <jcody@redhat.com>
 L: qemu-block@nongnu.org
 S: Supported

Makefile

@@ -135,7 +135,7 @@ endif
 	 else \
 	  mv $@.tmp $@; \
 	  cp -p $@ $@.old; \
-	 fi, "  GEN  $@");
+	 fi, "  GEN   $@");
 
 defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)

VERSION

@@ -1 +1 @@
-2.3.90
+2.4.0

aio-posix.c

@@ -233,26 +233,23 @@ static void add_pollfd(AioHandler *node)
 bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
-    bool was_dispatching;
     int i, ret;
     bool progress;
     int64_t timeout;
 
     aio_context_acquire(ctx);
-    was_dispatching = ctx->dispatching;
     progress = false;
 
     /* aio_notify can avoid the expensive event_notifier_set if
      * everything (file descriptors, bottom halves, timers) will
      * be re-evaluated before the next blocking poll().  This is
      * already true when aio_poll is called with blocking == false;
-     * if blocking == true, it is only true after poll() returns.
-     *
-     * If we're in a nested event loop, ctx->dispatching might be true.
-     * In that case we can restore it just before returning, but we
-     * have to clear it now.
+     * if blocking == true, it is only true after poll() returns,
+     * so disable the optimization now.
      */
-    aio_set_dispatching(ctx, !blocking);
+    if (blocking) {
+        atomic_add(&ctx->notify_me, 2);
+    }
 
     ctx->walking_handlers++;
 
@@ -272,10 +269,15 @@ bool aio_poll(AioContext *ctx, bool blocking)
         aio_context_release(ctx);
     }
     ret = qemu_poll_ns((GPollFD *)pollfds, npfd, timeout);
+    if (blocking) {
+        atomic_sub(&ctx->notify_me, 2);
+    }
     if (timeout) {
         aio_context_acquire(ctx);
     }
 
+    aio_notify_accept(ctx);
+
     /* if we have any readable fds, dispatch event */
     if (ret > 0) {
         for (i = 0; i < npfd; i++) {
@@ -287,12 +289,10 @@ bool aio_poll(AioContext *ctx, bool blocking)
     ctx->walking_handlers--;
 
     /* Run dispatch even if there were no readable fds to run timers */
-    aio_set_dispatching(ctx, true);
     if (aio_dispatch(ctx)) {
         progress = true;
     }
 
-    aio_set_dispatching(ctx, was_dispatching);
     aio_context_release(ctx);
 
     return progress;

aio-win32.c

@@ -279,30 +279,25 @@ bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
     HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool was_dispatching, progress, have_select_revents, first;
+    bool progress, have_select_revents, first;
     int count;
     int timeout;
 
     aio_context_acquire(ctx);
-    have_select_revents = aio_prepare(ctx);
-    if (have_select_revents) {
-        blocking = false;
-    }
-
-    was_dispatching = ctx->dispatching;
     progress = false;
 
     /* aio_notify can avoid the expensive event_notifier_set if
      * everything (file descriptors, bottom halves, timers) will
      * be re-evaluated before the next blocking poll().  This is
      * already true when aio_poll is called with blocking == false;
-     * if blocking == true, it is only true after poll() returns.
-     *
-     * If we're in a nested event loop, ctx->dispatching might be true.
-     * In that case we can restore it just before returning, but we
-     * have to clear it now.
+     * if blocking == true, it is only true after poll() returns,
+     * so disable the optimization now.
      */
-    aio_set_dispatching(ctx, !blocking);
+    if (blocking) {
+        atomic_add(&ctx->notify_me, 2);
+    }
+
+    have_select_revents = aio_prepare(ctx);
 
     ctx->walking_handlers++;
 
@@ -317,26 +312,36 @@ bool aio_poll(AioContext *ctx, bool blocking)
     ctx->walking_handlers--;
     first = true;
 
-    /* wait until next event */
-    while (count > 0) {
+    /* ctx->notifier is always registered.  */
+    assert(count > 0);
+
+    /* Multiple iterations, all of them non-blocking except the first,
+     * may be necessary to process all pending events.  After the first
+     * WaitForMultipleObjects call ctx->notify_me will be decremented.
+     */
+    do {
         HANDLE event;
         int ret;
 
-        timeout = blocking
+        timeout = blocking && !have_select_revents
             ? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0;
         if (timeout) {
             aio_context_release(ctx);
         }
         ret = WaitForMultipleObjects(count, events, FALSE, timeout);
+        if (blocking) {
+            assert(first);
+            atomic_sub(&ctx->notify_me, 2);
+        }
         if (timeout) {
             aio_context_acquire(ctx);
         }
-        aio_set_dispatching(ctx, true);
 
-        if (first && aio_bh_poll(ctx)) {
-            progress = true;
+        if (first) {
+            aio_notify_accept(ctx);
+            progress |= aio_bh_poll(ctx);
+            first = false;
         }
-        first = false;
 
         /* if we have any signaled events, dispatch event */
         event = NULL;
@@ -351,11 +356,10 @@ bool aio_poll(AioContext *ctx, bool blocking)
         blocking = false;
 
         progress |= aio_dispatch_handlers(ctx, event);
-    }
+    } while (count > 0);
 
     progress |= timerlistgroup_run_timers(&ctx->tlg);
 
-    aio_set_dispatching(ctx, was_dispatching);
     aio_context_release(ctx);
     return progress;
 }

async.c

@@ -79,8 +79,10 @@ int aio_bh_poll(AioContext *ctx)
          * aio_notify again if necessary.
          */
         if (!bh->deleted && atomic_xchg(&bh->scheduled, 0)) {
-            if (!bh->idle)
+            /* Idle BHs and the notify BH don't count as progress */
+            if (!bh->idle && bh != ctx->notify_dummy_bh) {
                 ret = 1;
+            }
             bh->idle = 0;
             bh->cb(bh->opaque);
         }
@@ -184,6 +186,8 @@ aio_ctx_prepare(GSource *source, gint    *timeout)
 {
     AioContext *ctx = (AioContext *) source;
 
+    atomic_or(&ctx->notify_me, 1);
+
     /* We assume there is no timeout already supplied */
     *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
 
@@ -200,6 +204,9 @@ aio_ctx_check(GSource *source)
     AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
 
+    atomic_and(&ctx->notify_me, ~1);
+    aio_notify_accept(ctx);
+
     for (bh = ctx->first_bh; bh; bh = bh->next) {
         if (!bh->deleted && bh->scheduled) {
             return true;
@@ -225,7 +232,21 @@ aio_ctx_finalize(GSource     *source)
 {
     AioContext *ctx = (AioContext *) source;
 
+    qemu_bh_delete(ctx->notify_dummy_bh);
     thread_pool_free(ctx->thread_pool);
+
+    qemu_mutex_lock(&ctx->bh_lock);
+    while (ctx->first_bh) {
+        QEMUBH *next = ctx->first_bh->next;
+
+        /* qemu_bh_delete() must have been called on BHs in this AioContext */
+        assert(ctx->first_bh->deleted);
+
+        g_free(ctx->first_bh);
+        ctx->first_bh = next;
+    }
+    qemu_mutex_unlock(&ctx->bh_lock);
+
     aio_set_event_notifier(ctx, &ctx->notifier, NULL);
     event_notifier_cleanup(&ctx->notifier);
     rfifolock_destroy(&ctx->lock);
@@ -254,24 +275,22 @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)
     return ctx->thread_pool;
 }
 
-void aio_set_dispatching(AioContext *ctx, bool dispatching)
+void aio_notify(AioContext *ctx)
 {
-    ctx->dispatching = dispatching;
-    if (!dispatching) {
-        /* Write ctx->dispatching before reading e.g. bh->scheduled.
-         * Optimization: this is only needed when we're entering the "unsafe"
-         * phase where other threads must call event_notifier_set.
-         */
-        smp_mb();
+    /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
+     * with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
+     */
+    smp_mb();
+    if (ctx->notify_me) {
+        event_notifier_set(&ctx->notifier);
+        atomic_mb_set(&ctx->notified, true);
     }
 }
 
-void aio_notify(AioContext *ctx)
+void aio_notify_accept(AioContext *ctx)
 {
-    /* Write e.g. bh->scheduled before reading ctx->dispatching.  */
-    smp_mb();
-    if (!ctx->dispatching) {
-        event_notifier_set(&ctx->notifier);
+    if (atomic_xchg(&ctx->notified, false)) {
+        event_notifier_test_and_clear(&ctx->notifier);
     }
 }
 
@@ -282,8 +301,19 @@ static void aio_timerlist_notify(void *opaque)
 
 static void aio_rfifolock_cb(void *opaque)
 {
+    AioContext *ctx = opaque;
+
     /* Kick owner thread in case they are blocked in aio_poll() */
-    aio_notify(opaque);
+    qemu_bh_schedule(ctx->notify_dummy_bh);
+}
+
+static void notify_dummy_bh(void *opaque)
+{
+    /* Do nothing, we were invoked just to force the event loop to iterate */
+}
+
+static void event_notifier_dummy_cb(EventNotifier *e)
+{
 }
 
 AioContext *aio_context_new(Error **errp)
@@ -300,12 +330,14 @@ AioContext *aio_context_new(Error **errp)
     g_source_set_can_recurse(&ctx->source, true);
     aio_set_event_notifier(ctx, &ctx->notifier,
                            (EventNotifierHandler *)
-                           event_notifier_test_and_clear);
+                           event_notifier_dummy_cb);
     ctx->thread_pool = NULL;
     qemu_mutex_init(&ctx->bh_lock);
     rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
     timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
 
+    ctx->notify_dummy_bh = aio_bh_new(ctx, notify_dummy_bh, NULL);
+
     return ctx;
 }
 

backends/hostmem.c

@@ -10,6 +10,7 @@
  * See the COPYING file in the top-level directory.
  */
 #include "sysemu/hostmem.h"
+#include "hw/boards.h"
 #include "qapi/visitor.h"
 #include "qapi-types.h"
 #include "qapi-visit.h"
@@ -222,11 +223,10 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
 static void host_memory_backend_init(Object *obj)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    MachineState *machine = MACHINE(qdev_get_machine());
 
-    backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                       "mem-merge", true);
-    backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                      "dump-guest-core", true);
+    backend->merge = machine_mem_merge(machine);
+    backend->dump = machine_dump_guest_core(machine);
     backend->prealloc = mem_prealloc;
 
     object_property_add_bool(obj, "merge",

block.c

@@ -1102,12 +1102,46 @@ static int bdrv_fill_options(QDict **options, const char **pfilename,
     return 0;
 }
 
+static BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
+                                    BlockDriverState *child_bs,
+                                    const BdrvChildRole *child_role)
+{
+    BdrvChild *child = g_new(BdrvChild, 1);
+    *child = (BdrvChild) {
+        .bs     = child_bs,
+        .role   = child_role,
+    };
+
+    QLIST_INSERT_HEAD(&parent_bs->children, child, next);
+
+    return child;
+}
+
+static void bdrv_detach_child(BdrvChild *child)
+{
+    QLIST_REMOVE(child, next);
+    g_free(child);
+}
+
+void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
+{
+    BlockDriverState *child_bs = child->bs;
+
+    if (child->bs->inherits_from == parent) {
+        child->bs->inherits_from = NULL;
+    }
+
+    bdrv_detach_child(child);
+    bdrv_unref(child_bs);
+}
+
 void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
 {
 
     if (bs->backing_hd) {
         assert(bs->backing_blocker);
         bdrv_op_unblock_all(bs->backing_hd, bs->backing_blocker);
+        bdrv_detach_child(bs->backing_child);
     } else if (backing_hd) {
         error_setg(&bs->backing_blocker,
                    "node is used as backing hd of '%s'",
@@ -1118,8 +1152,10 @@ void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
     if (!backing_hd) {
         error_free(bs->backing_blocker);
         bs->backing_blocker = NULL;
+        bs->backing_child = NULL;
         goto out;
     }
+    bs->backing_child = bdrv_attach_child(bs, backing_hd, &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),
@@ -1202,6 +1238,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
         error_free(local_err);
         goto free_exit;
     }
+
     bdrv_set_backing_hd(bs, backing_hd);
 
 free_exit:
@@ -1214,7 +1251,7 @@ free_exit:
  * device's options.
  *
  * If allow_none is true, no image will be opened if filename is false and no
- * BlockdevRef is given. *pbs will remain unchanged and 0 will be returned.
+ * BlockdevRef is given. NULL will be returned, but errp remains unset.
  *
  * bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
  * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
@@ -1222,6 +1259,56 @@ free_exit:
  * BlockdevRef.
  *
  * The BlockdevRef will be removed from the options QDict.
+ */
+BdrvChild *bdrv_open_child(const char *filename,
+                           QDict *options, const char *bdref_key,
+                           BlockDriverState* parent,
+                           const BdrvChildRole *child_role,
+                           bool allow_none, Error **errp)
+{
+    BdrvChild *c = NULL;
+    BlockDriverState *bs;
+    QDict *image_options;
+    int ret;
+    char *bdref_key_dot;
+    const char *reference;
+
+    assert(child_role != NULL);
+
+    bdref_key_dot = g_strdup_printf("%s.", bdref_key);
+    qdict_extract_subqdict(options, &image_options, bdref_key_dot);
+    g_free(bdref_key_dot);
+
+    reference = qdict_get_try_str(options, bdref_key);
+    if (!filename && !reference && !qdict_size(image_options)) {
+        if (!allow_none) {
+            error_setg(errp, "A block device must be specified for \"%s\"",
+                       bdref_key);
+        }
+        QDECREF(image_options);
+        goto done;
+    }
+
+    bs = NULL;
+    ret = bdrv_open_inherit(&bs, filename, reference, image_options, 0,
+                            parent, child_role, NULL, errp);
+    if (ret < 0) {
+        goto done;
+    }
+
+    c = bdrv_attach_child(parent, bs, child_role);
+
+done:
+    qdict_del(options, bdref_key);
+    return c;
+}
+
+/*
+ * This is a version of bdrv_open_child() that returns 0/-EINVAL instead of
+ * a BdrvChild object.
+ *
+ * If allow_none is true, no image will be opened if filename is false and no
+ * BlockdevRef is given. *pbs will remain unchanged and 0 will be returned.
  *
  * To conform with the behavior of bdrv_open(), *pbs has to be NULL.
  */
@@ -1230,37 +1317,24 @@ int bdrv_open_image(BlockDriverState **pbs, const char *filename,
                     BlockDriverState* parent, const BdrvChildRole *child_role,
                     bool allow_none, Error **errp)
 {
-    QDict *image_options;
-    int ret;
-    char *bdref_key_dot;
-    const char *reference;
+    Error *local_err = NULL;
+    BdrvChild *c;
 
     assert(pbs);
     assert(*pbs == NULL);
 
-    bdref_key_dot = g_strdup_printf("%s.", bdref_key);
-    qdict_extract_subqdict(options, &image_options, bdref_key_dot);
-    g_free(bdref_key_dot);
-
-    reference = qdict_get_try_str(options, bdref_key);
-    if (!filename && !reference && !qdict_size(image_options)) {
-        if (allow_none) {
-            ret = 0;
-        } else {
-            error_setg(errp, "A block device must be specified for \"%s\"",
-                       bdref_key);
-            ret = -EINVAL;
-        }
-        QDECREF(image_options);
-        goto done;
+    c = bdrv_open_child(filename, options, bdref_key, parent, child_role,
+                        allow_none, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return -EINVAL;
     }
 
-    ret = bdrv_open_inherit(pbs, filename, reference, image_options, 0,
-                            parent, child_role, NULL, errp);
+    if (c != NULL) {
+        *pbs = c->bs;
+    }
 
-done:
-    qdict_del(options, bdref_key);
-    return ret;
+    return 0;
 }
 
 int bdrv_append_temp_snapshot(BlockDriverState *bs, int flags, Error **errp)
@@ -1328,19 +1402,6 @@ out:
     return ret;
 }
 
-static void bdrv_attach_child(BlockDriverState *parent_bs,
-                              BlockDriverState *child_bs,
-                              const BdrvChildRole *child_role)
-{
-    BdrvChild *child = g_new(BdrvChild, 1);
-    *child = (BdrvChild) {
-        .bs     = child_bs,
-        .role   = child_role,
-    };
-
-    QLIST_INSERT_HEAD(&parent_bs->children, child, next);
-}
-
 /*
  * Opens a disk image (raw, qcow2, vmdk, ...)
  *
@@ -1393,9 +1454,6 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
             return -ENODEV;
         }
         bdrv_ref(bs);
-        if (child_role) {
-            bdrv_attach_child(parent, bs, child_role);
-        }
         *pbs = bs;
         return 0;
     }
@@ -1540,10 +1598,6 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
         goto close_and_fail;
     }
 
-    if (child_role) {
-        bdrv_attach_child(parent, bs, child_role);
-    }
-
     QDECREF(options);
     *pbs = bs;
     return 0;
@@ -1849,20 +1903,23 @@ void bdrv_close(BlockDriverState *bs)
     if (bs->drv) {
         BdrvChild *child, *next;
 
-        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
-            if (child->bs->inherits_from == bs) {
-                child->bs->inherits_from = NULL;
-            }
-            QLIST_REMOVE(child, next);
-            g_free(child);
-        }
+        bs->drv->bdrv_close(bs);
 
         if (bs->backing_hd) {
             BlockDriverState *backing_hd = bs->backing_hd;
             bdrv_set_backing_hd(bs, NULL);
             bdrv_unref(backing_hd);
         }
-        bs->drv->bdrv_close(bs);
+
+        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
+            /* TODO Remove bdrv_unref() from drivers' close function and use
+             * bdrv_unref_child() here */
+            if (child->bs->inherits_from == bs) {
+                child->bs->inherits_from = NULL;
+            }
+            bdrv_detach_child(child);
+        }
+
         g_free(bs->opaque);
         bs->opaque = NULL;
         bs->drv = NULL;
@@ -2116,7 +2173,6 @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
     /* The contents of 'tmp' will become bs_top, as we are
      * swapping bs_new and bs_top contents. */
     bdrv_set_backing_hd(bs_top, bs_new);
-    bdrv_attach_child(bs_top, bs_new, &child_backing);
 }
 
 static void bdrv_delete(BlockDriverState *bs)

block/backup.c

@@ -431,7 +431,7 @@ static void coroutine_fn backup_run(void *opaque)
 
     if (job->sync_bitmap) {
         BdrvDirtyBitmap *bm;
-        if (ret < 0) {
+        if (ret < 0 || block_job_is_cancelled(&job->common)) {
             /* Merge the successor back into the parent, delete nothing. */
             bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL);
             assert(bm);

block/curl.c

@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
+#include "qemu/error-report.h"
 #include "block/block_int.h"
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qstring.h"
@@ -298,6 +299,18 @@ static void curl_multi_check_completion(BDRVCURLState *s)
             /* ACBs for successful messages get completed in curl_read_cb */
             if (msg->data.result != CURLE_OK) {
                 int i;
+                static int errcount = 100;
+
+                /* Don't lose the original error message from curl, since
+                 * it contains extra data.
+                 */
+                if (errcount > 0) {
+                    error_report("curl: %s", state->errmsg);
+                    if (--errcount == 0) {
+                        error_report("curl: further errors suppressed");
+                    }
+                }
+
                 for (i = 0; i < CURL_NUM_ACB; i++) {
                     CURLAIOCB *acb = state->acb[i];
 
@@ -305,7 +318,7 @@ static void curl_multi_check_completion(BDRVCURLState *s)
                         continue;
                     }
 
-                    acb->common.cb(acb->common.opaque, -EIO);
+                    acb->common.cb(acb->common.opaque, -EPROTO);
                     qemu_aio_unref(acb);
                     state->acb[i] = NULL;
                 }

block/mirror.c

@@ -20,6 +20,7 @@
 
 #define SLICE_TIME    100000000ULL /* ns */
 #define MAX_IN_FLIGHT 16
+#define DEFAULT_MIRROR_BUF_SIZE   (10 << 20)
 
 /* The mirroring buffer is a list of granularity-sized chunks.
  * Free chunks are organized in a list.
@@ -387,7 +388,7 @@ static void coroutine_fn mirror_run(void *opaque)
     MirrorBlockJob *s = opaque;
     MirrorExitData *data;
     BlockDriverState *bs = s->common.bs;
-    int64_t sector_num, end, sectors_per_chunk, length;
+    int64_t sector_num, end, length;
     uint64_t last_pause_ns;
     BlockDriverInfo bdi;
     char backing_filename[2]; /* we only need 2 characters because we are only
@@ -441,16 +442,28 @@ static void coroutine_fn mirror_run(void *opaque)
         goto immediate_exit;
     }
 
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
     mirror_free_init(s);
 
+    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     if (!s->is_none_mode) {
         /* First part, loop on the sectors and initialize the dirty bitmap.  */
         BlockDriverState *base = s->base;
         for (sector_num = 0; sector_num < end; ) {
-            int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
-            ret = bdrv_is_allocated_above(bs, base,
-                                          sector_num, next - sector_num, &n);
+            /* Just to make sure we are not exceeding int limit. */
+            int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS,
+                                 end - sector_num);
+            int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+
+            if (now - last_pause_ns > SLICE_TIME) {
+                last_pause_ns = now;
+                block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0);
+            }
+
+            if (block_job_is_cancelled(&s->common)) {
+                goto immediate_exit;
+            }
+
+            ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n);
 
             if (ret < 0) {
                 goto immediate_exit;
@@ -459,15 +472,12 @@ static void coroutine_fn mirror_run(void *opaque)
             assert(n > 0);
             if (ret == 1) {
                 bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n);
-                sector_num = next;
-            } else {
-                sector_num += n;
             }
+            sector_num += n;
         }
     }
 
     bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
-    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     for (;;) {
         uint64_t delay_ns = 0;
         int64_t cnt;
@@ -690,6 +700,14 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
         return;
     }
 
+    if (buf_size < 0) {
+        error_setg(errp, "Invalid parameter 'buf-size'");
+        return;
+    }
+
+    if (buf_size == 0) {
+        buf_size = DEFAULT_MIRROR_BUF_SIZE;
+    }
 
     s = block_job_create(driver, bs, speed, cb, opaque, errp);
     if (!s) {
@@ -703,7 +721,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
     s->is_none_mode = is_none_mode;
     s->base = base;
     s->granularity = granularity;
-    s->buf_size = MAX(buf_size, granularity);
+    s->buf_size = ROUND_UP(buf_size, granularity);
     s->unmap = unmap;
 
     s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);

block/quorum.c

@@ -865,12 +865,6 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     int i;
     int ret = 0;
 
-    if (!qcrypto_hash_supports(QCRYPTO_HASH_ALG_SHA256)) {
-        error_setg(errp,
-                   "SHA256 hash support is required for quorum device");
-        return -EINVAL;
-    }
-
     qdict_flatten(options);
 
     /* count how many different children are present */
@@ -1061,6 +1055,10 @@ static BlockDriver bdrv_quorum = {
 
 static void bdrv_quorum_init(void)
 {
+    if (!qcrypto_hash_supports(QCRYPTO_HASH_ALG_SHA256)) {
+        /* SHA256 hash support is required for quorum device */
+        return;
+    }
     bdrv_register(&bdrv_quorum);
 }
 

block/rbd.c

@@ -74,25 +74,18 @@ typedef struct RBDAIOCB {
     QEMUIOVector *qiov;
     char *bounce;
     RBDAIOCmd cmd;
-    int64_t sector_num;
     int error;
     struct BDRVRBDState *s;
-    int status;
 } RBDAIOCB;
 
 typedef struct RADOSCB {
-    int rcbid;
     RBDAIOCB *acb;
     struct BDRVRBDState *s;
-    int done;
     int64_t size;
     char *buf;
     int64_t ret;
 } RADOSCB;
 
-#define RBD_FD_READ 0
-#define RBD_FD_WRITE 1
-
 typedef struct BDRVRBDState {
     rados_t cluster;
     rados_ioctx_t io_ctx;
@@ -235,7 +228,9 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
     return NULL;
 }
 
-static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
+static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
+                             bool only_read_conf_file,
+                             Error **errp)
 {
     char *p, *buf;
     char name[RBD_MAX_CONF_NAME_SIZE];
@@ -267,14 +262,18 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
         qemu_rbd_unescape(value);
 
         if (strcmp(name, "conf") == 0) {
-            ret = rados_conf_read_file(cluster, value);
-            if (ret < 0) {
-                error_setg(errp, "error reading conf file %s", value);
-                break;
+            /* read the conf file alone, so it doesn't override more
+               specific settings for a particular device */
+            if (only_read_conf_file) {
+                ret = rados_conf_read_file(cluster, value);
+                if (ret < 0) {
+                    error_setg(errp, "error reading conf file %s", value);
+                    break;
+                }
             }
         } else if (strcmp(name, "id") == 0) {
             /* ignore, this is parsed by qemu_rbd_parse_clientname() */
-        } else {
+        } else if (!only_read_conf_file) {
             ret = rados_conf_set(cluster, name, value);
             if (ret < 0) {
                 error_setg(errp, "invalid conf option %s", name);
@@ -337,10 +336,15 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
     if (strstr(conf, "conf=") == NULL) {
         /* try default location, but ignore failure */
         rados_conf_read_file(cluster, NULL);
+    } else if (conf[0] != '\0' &&
+               qemu_rbd_set_conf(cluster, conf, true, &local_err) < 0) {
+        rados_shutdown(cluster);
+        error_propagate(errp, local_err);
+        return -EIO;
     }
 
     if (conf[0] != '\0' &&
-        qemu_rbd_set_conf(cluster, conf, &local_err) < 0) {
+        qemu_rbd_set_conf(cluster, conf, false, &local_err) < 0) {
         rados_shutdown(cluster);
         error_propagate(errp, local_err);
         return -EIO;
@@ -405,7 +409,6 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     }
     qemu_vfree(acb->bounce);
     acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
-    acb->status = 0;
 
     qemu_aio_unref(acb);
 }
@@ -468,6 +471,23 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
         s->snap = g_strdup(snap_buf);
     }
 
+    if (strstr(conf, "conf=") == NULL) {
+        /* try default location, but ignore failure */
+        rados_conf_read_file(s->cluster, NULL);
+    } else if (conf[0] != '\0') {
+        r = qemu_rbd_set_conf(s->cluster, conf, true, errp);
+        if (r < 0) {
+            goto failed_shutdown;
+        }
+    }
+
+    if (conf[0] != '\0') {
+        r = qemu_rbd_set_conf(s->cluster, conf, false, errp);
+        if (r < 0) {
+            goto failed_shutdown;
+        }
+    }
+
     /*
      * Fallback to more conservative semantics if setting cache
      * options fails. Ignore errors from setting rbd_cache because the
@@ -481,18 +501,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
         rados_conf_set(s->cluster, "rbd_cache", "true");
     }
 
-    if (strstr(conf, "conf=") == NULL) {
-        /* try default location, but ignore failure */
-        rados_conf_read_file(s->cluster, NULL);
-    }
-
-    if (conf[0] != '\0') {
-        r = qemu_rbd_set_conf(s->cluster, conf, errp);
-        if (r < 0) {
-            goto failed_shutdown;
-        }
-    }
-
     r = rados_connect(s->cluster);
     if (r < 0) {
         error_setg(errp, "error connecting");
@@ -621,7 +629,6 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
     acb->error = 0;
     acb->s = s;
     acb->bh = NULL;
-    acb->status = -EINPROGRESS;
 
     if (cmd == RBD_AIO_WRITE) {
         qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
@@ -633,7 +640,6 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
     size = nb_sectors * BDRV_SECTOR_SIZE;
 
     rcb = g_new(RADOSCB, 1);
-    rcb->done = 0;
     rcb->acb = acb;
     rcb->buf = buf;
     rcb->s = acb->s;

block/sheepdog.c

@@ -318,6 +318,10 @@ enum AIOCBState {
     AIOCB_DISCARD_OBJ,
 };
 
+#define AIOCBOverwrapping(x, y)                                 \
+    (!(x->max_affect_data_idx < y->min_affect_data_idx          \
+       || y->max_affect_data_idx < x->min_affect_data_idx))
+
 struct SheepdogAIOCB {
     BlockAIOCB common;
 
@@ -334,6 +338,11 @@ struct SheepdogAIOCB {
 
     bool cancelable;
     int nr_pending;
+
+    uint32_t min_affect_data_idx;
+    uint32_t max_affect_data_idx;
+
+    QLIST_ENTRY(SheepdogAIOCB) aiocb_siblings;
 };
 
 typedef struct BDRVSheepdogState {
@@ -362,8 +371,10 @@ typedef struct BDRVSheepdogState {
 
     /* Every aio request must be linked to either of these queues. */
     QLIST_HEAD(inflight_aio_head, AIOReq) inflight_aio_head;
-    QLIST_HEAD(pending_aio_head, AIOReq) pending_aio_head;
     QLIST_HEAD(failed_aio_head, AIOReq) failed_aio_head;
+
+    CoQueue overwrapping_queue;
+    QLIST_HEAD(inflight_aiocb_head, SheepdogAIOCB) inflight_aiocb_head;
 } BDRVSheepdogState;
 
 static const char * sd_strerror(int err)
@@ -498,13 +509,7 @@ static void sd_aio_cancel(BlockAIOCB *blockacb)
     AIOReq *aioreq, *next;
 
     if (sd_acb_cancelable(acb)) {
-        /* Remove outstanding requests from pending and failed queues.  */
-        QLIST_FOREACH_SAFE(aioreq, &s->pending_aio_head, aio_siblings,
-                           next) {
-            if (aioreq->aiocb == acb) {
-                free_aio_req(s, aioreq);
-            }
-        }
+        /* Remove outstanding requests from failed queue.  */
         QLIST_FOREACH_SAFE(aioreq, &s->failed_aio_head, aio_siblings,
                            next) {
             if (aioreq->aiocb == acb) {
@@ -529,6 +534,10 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
                                    int64_t sector_num, int nb_sectors)
 {
     SheepdogAIOCB *acb;
+    uint32_t object_size;
+    BDRVSheepdogState *s = bs->opaque;
+
+    object_size = (UINT32_C(1) << s->inode.block_size_shift);
 
     acb = qemu_aio_get(&sd_aiocb_info, bs, NULL, NULL);
 
@@ -542,6 +551,11 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
     acb->coroutine = qemu_coroutine_self();
     acb->ret = 0;
     acb->nr_pending = 0;
+
+    acb->min_affect_data_idx = acb->sector_num * BDRV_SECTOR_SIZE / object_size;
+    acb->max_affect_data_idx = (acb->sector_num * BDRV_SECTOR_SIZE +
+                              acb->nb_sectors * BDRV_SECTOR_SIZE) / object_size;
+
     return acb;
 }
 
@@ -703,38 +717,6 @@ static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag);
 static int get_sheep_fd(BDRVSheepdogState *s, Error **errp);
 static void co_write_request(void *opaque);
 
-static AIOReq *find_pending_req(BDRVSheepdogState *s, uint64_t oid)
-{
-    AIOReq *aio_req;
-
-    QLIST_FOREACH(aio_req, &s->pending_aio_head, aio_siblings) {
-        if (aio_req->oid == oid) {
-            return aio_req;
-        }
-    }
-
-    return NULL;
-}
-
-/*
- * This function searchs pending requests to the object `oid', and
- * sends them.
- */
-static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid)
-{
-    AIOReq *aio_req;
-    SheepdogAIOCB *acb;
-
-    while ((aio_req = find_pending_req(s, oid)) != NULL) {
-        acb = aio_req->aiocb;
-        /* move aio_req from pending list to inflight one */
-        QLIST_REMOVE(aio_req, aio_siblings);
-        QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
-                        acb->aiocb_type);
-    }
-}
-
 static coroutine_fn void reconnect_to_sdog(void *opaque)
 {
     BDRVSheepdogState *s = opaque;
@@ -840,12 +822,6 @@ static void coroutine_fn aio_read_response(void *opaque)
                 s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
                 s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
             }
-            /*
-             * Some requests may be blocked because simultaneous
-             * create requests are not allowed, so we search the
-             * pending requests here.
-             */
-            send_pending_req(s, aio_req->oid);
         }
         break;
     case AIOCB_READ_UDATA:
@@ -1341,30 +1317,6 @@ out:
     return ret;
 }
 
-/* Return true if the specified request is linked to the pending list. */
-static bool check_simultaneous_create(BDRVSheepdogState *s, AIOReq *aio_req)
-{
-    AIOReq *areq;
-    QLIST_FOREACH(areq, &s->inflight_aio_head, aio_siblings) {
-        if (areq != aio_req && areq->oid == aio_req->oid) {
-            /*
-             * Sheepdog cannot handle simultaneous create requests to the same
-             * object, so we cannot send the request until the previous request
-             * finishes.
-             */
-            DPRINTF("simultaneous create to %" PRIx64 "\n", aio_req->oid);
-            aio_req->flags = 0;
-            aio_req->base_oid = 0;
-            aio_req->create = false;
-            QLIST_REMOVE(aio_req, aio_siblings);
-            QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req, aio_siblings);
-            return true;
-        }
-    }
-
-    return false;
-}
-
 static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
 {
     SheepdogAIOCB *acb = aio_req->aiocb;
@@ -1379,10 +1331,6 @@ static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
             goto out;
         }
 
-        if (check_simultaneous_create(s, aio_req)) {
-            return;
-        }
-
         if (s->inode.data_vdi_id[idx]) {
             aio_req->base_oid = vid_to_data_oid(s->inode.data_vdi_id[idx], idx);
             aio_req->flags |= SD_FLAG_CMD_COW;
@@ -1458,8 +1406,8 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     filename = qemu_opt_get(opts, "filename");
 
     QLIST_INIT(&s->inflight_aio_head);
-    QLIST_INIT(&s->pending_aio_head);
     QLIST_INIT(&s->failed_aio_head);
+    QLIST_INIT(&s->inflight_aiocb_head);
     s->fd = -1;
 
     memset(vdi, 0, sizeof(vdi));
@@ -1524,6 +1472,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     bs->total_sectors = s->inode.vdi_size / BDRV_SECTOR_SIZE;
     pstrcpy(s->name, sizeof(s->name), vdi);
     qemu_co_mutex_init(&s->lock);
+    qemu_co_queue_init(&s->overwrapping_queue);
     qemu_opts_del(opts);
     g_free(buf);
     return 0;
@@ -2195,12 +2144,6 @@ static int coroutine_fn sd_co_rw_vector(void *p)
                                 old_oid, done);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
 
-        if (create) {
-            if (check_simultaneous_create(s, aio_req)) {
-                goto done;
-            }
-        }
-
         add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                         acb->aiocb_type);
     done:
@@ -2215,6 +2158,20 @@ out:
     return 1;
 }
 
+static bool check_overwrapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *aiocb)
+{
+    SheepdogAIOCB *cb;
+
+    QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) {
+        if (AIOCBOverwrapping(aiocb, cb)) {
+            return true;
+        }
+    }
+
+    QLIST_INSERT_HEAD(&s->inflight_aiocb_head, aiocb, aiocb_siblings);
+    return false;
+}
+
 static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
@@ -2234,14 +2191,25 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
     acb->aio_done_func = sd_write_done;
     acb->aiocb_type = AIOCB_WRITE_UDATA;
 
+retry:
+    if (check_overwrapping_aiocb(s, acb)) {
+        qemu_co_queue_wait(&s->overwrapping_queue);
+        goto retry;
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
+        QLIST_REMOVE(acb, aiocb_siblings);
+        qemu_co_queue_restart_all(&s->overwrapping_queue);
         qemu_aio_unref(acb);
         return ret;
     }
 
     qemu_coroutine_yield();
 
+    QLIST_REMOVE(acb, aiocb_siblings);
+    qemu_co_queue_restart_all(&s->overwrapping_queue);
+
     return acb->ret;
 }
 
@@ -2250,19 +2218,30 @@ static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
 {
     SheepdogAIOCB *acb;
     int ret;
+    BDRVSheepdogState *s = bs->opaque;
 
     acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
     acb->aiocb_type = AIOCB_READ_UDATA;
     acb->aio_done_func = sd_finish_aiocb;
 
+retry:
+    if (check_overwrapping_aiocb(s, acb)) {
+        qemu_co_queue_wait(&s->overwrapping_queue);
+        goto retry;
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
+        QLIST_REMOVE(acb, aiocb_siblings);
+        qemu_co_queue_restart_all(&s->overwrapping_queue);
         qemu_aio_unref(acb);
         return ret;
     }
 
     qemu_coroutine_yield();
 
+    QLIST_REMOVE(acb, aiocb_siblings);
+    qemu_co_queue_restart_all(&s->overwrapping_queue);
     return acb->ret;
 }
 
@@ -2610,14 +2589,25 @@ static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num,
     acb->aiocb_type = AIOCB_DISCARD_OBJ;
     acb->aio_done_func = sd_finish_aiocb;
 
+retry:
+    if (check_overwrapping_aiocb(s, acb)) {
+        qemu_co_queue_wait(&s->overwrapping_queue);
+        goto retry;
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
+        QLIST_REMOVE(acb, aiocb_siblings);
+        qemu_co_queue_restart_all(&s->overwrapping_queue);
         qemu_aio_unref(acb);
         return ret;
     }
 
     qemu_coroutine_yield();
 
+    QLIST_REMOVE(acb, aiocb_siblings);
+    qemu_co_queue_restart_all(&s->overwrapping_queue);
+
     return acb->ret;
 }
 

block/ssh.c

@@ -563,7 +563,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     /* Open the socket and connect. */
     s->sock = inet_connect(s->hostport, errp);
     if (s->sock < 0) {
-        ret = -errno;
+        ret = -EIO;
         goto err;
     }
 

block/vpc.c

@@ -168,6 +168,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
     uint64_t computed_size;
+    uint64_t pagetable_size;
     int disk_type = VHD_DYNAMIC;
     int ret;
 
@@ -269,7 +270,17 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
 
-        s->pagetable = qemu_try_blockalign(bs->file, s->max_table_entries * 4);
+        if (s->max_table_entries > SIZE_MAX / 4 ||
+            s->max_table_entries > (int) INT_MAX / 4) {
+            error_setg(errp, "Max Table Entries too large (%" PRId32 ")",
+                        s->max_table_entries);
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        pagetable_size = (uint64_t) s->max_table_entries * 4;
+
+        s->pagetable = qemu_try_blockalign(bs->file, pagetable_size);
         if (s->pagetable == NULL) {
             ret = -ENOMEM;
             goto fail;
@@ -277,14 +288,13 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
 
         s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
 
-        ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable,
-                         s->max_table_entries * 4);
+        ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable, pagetable_size);
         if (ret < 0) {
             goto fail;
         }
 
         s->free_data_block_offset =
-            (s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
+            ROUND_UP(s->bat_offset + pagetable_size, 512);
 
         for (i = 0; i < s->max_table_entries; i++) {
             be32_to_cpus(&s->pagetable[i]);

blockdev.c

@@ -2380,9 +2380,6 @@ void qmp_block_commit(const char *device,
     aio_context = bdrv_get_aio_context(bs);
     aio_context_acquire(aio_context);
 
-    /* drain all i/o before commits */
-    bdrv_drain_all();
-
     if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, errp)) {
         goto out;
     }
@@ -2642,8 +2639,6 @@ out:
     aio_context_release(aio_context);
 }
 
-#define DEFAULT_MIRROR_BUF_SIZE   (10 << 20)
-
 void qmp_drive_mirror(const char *device, const char *target,
                       bool has_format, const char *format,
                       bool has_node_name, const char *node_name,
@@ -2685,7 +2680,7 @@ void qmp_drive_mirror(const char *device, const char *target,
         granularity = 0;
     }
     if (!has_buf_size) {
-        buf_size = DEFAULT_MIRROR_BUF_SIZE;
+        buf_size = 0;
     }
     if (!has_unmap) {
         unmap = true;

bsd-user/main.c

@@ -173,7 +173,7 @@ void cpu_loop(CPUX86State *env)
     //target_siginfo_t info;
 
     for(;;) {
-        trapnr = cpu_x86_exec(env);
+        trapnr = cpu_x86_exec(cs);
         switch(trapnr) {
         case 0x80:
             /* syscall from int $0x80 */

configure

@@ -1337,7 +1337,6 @@ disabled with --disable-FEATURE, default is enabled if available:
   vnc-sasl        SASL encryption for VNC server
   vnc-jpeg        JPEG lossy compression for VNC server
   vnc-png         PNG compression for VNC server
-  vnc-ws          Websockets support for VNC server
   cocoa           Cocoa UI (Mac OS X only)
   virtfs          VirtFS
   xen             xen backend driver support
@@ -2116,10 +2115,26 @@ fi
 ##########################################
 # GNUTLS probe
 
+gnutls_works() {
+    # Unfortunately some distros have bad pkg-config information for gnutls
+    # such that it claims to exist but you get a compiler error if you try
+    # to use the options returned by --libs. Specifically, Ubuntu for --static
+    # builds doesn't work:
+    # https://bugs.launchpad.net/ubuntu/+source/gnutls26/+bug/1478035
+    #
+    # So sanity check the cflags/libs before assuming gnutls can be used.
+    if ! $pkg_config --exists "gnutls"; then
+        return 1
+    fi
+
+    write_c_skeleton
+    compile_prog "$($pkg_config --cflags gnutls)" "$($pkg_config --libs gnutls)"
+}
+
 gnutls_gcrypt=no
 gnutls_nettle=no
 if test "$gnutls" != "no"; then
-    if $pkg_config --exists "gnutls"; then
+    if gnutls_works; then
         gnutls_cflags=`$pkg_config --cflags gnutls`
         gnutls_libs=`$pkg_config --libs gnutls`
         libs_softmmu="$gnutls_libs $libs_softmmu"
@@ -2183,6 +2198,7 @@ if test "$gnutls_nettle" != "no"; then
     if $pkg_config --exists "nettle"; then
         nettle_cflags=`$pkg_config --cflags nettle`
         nettle_libs=`$pkg_config --libs nettle`
+        nettle_version=`$pkg_config --modversion nettle`
         libs_softmmu="$nettle_libs $libs_softmmu"
         libs_tools="$nettle_libs $libs_tools"
         QEMU_CFLAGS="$QEMU_CFLAGS $nettle_cflags"
@@ -4490,7 +4506,7 @@ echo "GTK support       $gtk"
 echo "GNUTLS support    $gnutls"
 echo "GNUTLS hash       $gnutls_hash"
 echo "GNUTLS gcrypt     $gnutls_gcrypt"
-echo "GNUTLS nettle     $gnutls_nettle"
+echo "GNUTLS nettle     $gnutls_nettle ${gnutls_nettle+($nettle_version)}"
 echo "VTE support       $vte"
 echo "curses support    $curses"
 echo "curl support      $curl"
@@ -4858,6 +4874,7 @@ if test "$gnutls_gcrypt" = "yes" ; then
 fi
 if test "$gnutls_nettle" = "yes" ; then
   echo "CONFIG_GNUTLS_NETTLE=y" >> $config_host_mak
+  echo "CONFIG_NETTLE_VERSION_MAJOR=${nettle_version%%.*}" >> $config_host_mak
 fi
 if test "$vte" = "yes" ; then
   echo "CONFIG_VTE=y" >> $config_host_mak

cpus.c

@@ -954,6 +954,8 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
     CPUState *cpu = arg;
     int r;
 
+    rcu_register_thread();
+
     qemu_mutex_lock_iothread();
     qemu_thread_get_self(cpu->thread);
     cpu->thread_id = qemu_get_thread_id();
@@ -995,6 +997,8 @@ static void *qemu_dummy_cpu_thread_fn(void *arg)
     sigset_t waitset;
     int r;
 
+    rcu_register_thread();
+
     qemu_mutex_lock_iothread();
     qemu_thread_get_self(cpu->thread);
     cpu->thread_id = qemu_get_thread_id();
@@ -1034,6 +1038,8 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
 {
     CPUState *cpu = arg;
 
+    rcu_register_thread();
+
     qemu_mutex_lock_iothread();
     qemu_tcg_init_cpu_signals();
     qemu_thread_get_self(cpu->thread);

crypto/cipher-builtin.c

@@ -117,7 +117,7 @@ static int qcrypto_cipher_decrypt_aes(QCryptoCipher *cipher,
         uint8_t *outptr = out;
         while (len) {
             if (len > AES_BLOCK_SIZE) {
-                AES_decrypt(inptr, outptr, &ctxt->state.aes.encrypt_key);
+                AES_decrypt(inptr, outptr, &ctxt->state.aes.decrypt_key);
                 inptr += AES_BLOCK_SIZE;
                 outptr += AES_BLOCK_SIZE;
                 len -= AES_BLOCK_SIZE;
@@ -126,15 +126,15 @@ static int qcrypto_cipher_decrypt_aes(QCryptoCipher *cipher,
                 memcpy(tmp1, inptr, len);
                 /* Fill with 0 to avoid valgrind uninitialized reads */
                 memset(tmp1 + len, 0, sizeof(tmp1) - len);
-                AES_decrypt(tmp1, tmp2, &ctxt->state.aes.encrypt_key);
+                AES_decrypt(tmp1, tmp2, &ctxt->state.aes.decrypt_key);
                 memcpy(outptr, tmp2, len);
                 len = 0;
             }
         }
     } else {
         AES_cbc_encrypt(in, out, len,
-                        &ctxt->state.aes.encrypt_key,
-                        ctxt->state.aes.iv, 1);
+                        &ctxt->state.aes.decrypt_key,
+                        ctxt->state.aes.iv, 0);
     }
 
     return 0;

crypto/cipher-nettle.c

@@ -23,12 +23,51 @@
 #include <nettle/des.h>
 #include <nettle/cbc.h>
 
+#if CONFIG_NETTLE_VERSION_MAJOR < 3
+typedef nettle_crypt_func nettle_cipher_func;
+
+typedef void *       cipher_ctx_t;
+typedef unsigned     cipher_length_t;
+#else
+typedef const void * cipher_ctx_t;
+typedef size_t       cipher_length_t;
+#endif
+
+static nettle_cipher_func aes_encrypt_wrapper;
+static nettle_cipher_func aes_decrypt_wrapper;
+static nettle_cipher_func des_encrypt_wrapper;
+static nettle_cipher_func des_decrypt_wrapper;
+
+static void aes_encrypt_wrapper(cipher_ctx_t ctx, cipher_length_t length,
+                                uint8_t *dst, const uint8_t *src)
+{
+    aes_encrypt(ctx, length, dst, src);
+}
+
+static void aes_decrypt_wrapper(cipher_ctx_t ctx, cipher_length_t length,
+                                uint8_t *dst, const uint8_t *src)
+{
+    aes_decrypt(ctx, length, dst, src);
+}
+
+static void des_encrypt_wrapper(cipher_ctx_t ctx, cipher_length_t length,
+                                uint8_t *dst, const uint8_t *src)
+{
+    des_encrypt(ctx, length, dst, src);
+}
+
+static void des_decrypt_wrapper(cipher_ctx_t ctx, cipher_length_t length,
+                                uint8_t *dst, const uint8_t *src)
+{
+    des_decrypt(ctx, length, dst, src);
+}
+
 typedef struct QCryptoCipherNettle QCryptoCipherNettle;
 struct QCryptoCipherNettle {
     void *ctx_encrypt;
     void *ctx_decrypt;
-    nettle_crypt_func *alg_encrypt;
-    nettle_crypt_func *alg_decrypt;
+    nettle_cipher_func *alg_encrypt;
+    nettle_cipher_func *alg_decrypt;
     uint8_t *iv;
     size_t niv;
 };
@@ -83,8 +122,8 @@ QCryptoCipher *qcrypto_cipher_new(QCryptoCipherAlgorithm alg,
         des_set_key(ctx->ctx_encrypt, rfbkey);
         g_free(rfbkey);
 
-        ctx->alg_encrypt = (nettle_crypt_func *)des_encrypt;
-        ctx->alg_decrypt = (nettle_crypt_func *)des_decrypt;
+        ctx->alg_encrypt = des_encrypt_wrapper;
+        ctx->alg_decrypt = des_decrypt_wrapper;
 
         ctx->niv = DES_BLOCK_SIZE;
         break;
@@ -98,8 +137,8 @@ QCryptoCipher *qcrypto_cipher_new(QCryptoCipherAlgorithm alg,
         aes_set_encrypt_key(ctx->ctx_encrypt, nkey, key);
         aes_set_decrypt_key(ctx->ctx_decrypt, nkey, key);
 
-        ctx->alg_encrypt = (nettle_crypt_func *)aes_encrypt;
-        ctx->alg_decrypt = (nettle_crypt_func *)aes_decrypt;
+        ctx->alg_encrypt = aes_encrypt_wrapper;
+        ctx->alg_decrypt = aes_decrypt_wrapper;
 
         ctx->niv = AES_BLOCK_SIZE;
         break;

device_tree.c

@@ -241,7 +241,7 @@ uint32_t qemu_fdt_alloc_phandle(void *fdt)
 
     /*
      * We need to find out if the user gave us special instruction at
-     * which phandle id to start allocting phandles.
+     * which phandle id to start allocating phandles.
      */
     if (!phandle) {
         phandle = machine_phandle_start(current_machine);

disas/arm-a64.cc

@@ -42,7 +42,7 @@ public:
         stream_ = stream;
     }
 
-    void SetPrintf(int (*printf_fn)(FILE *, const char *, ...)) {
+    void SetPrintf(fprintf_function printf_fn) {
         printf_ = printf_fn;
     }
 
@@ -53,7 +53,7 @@ protected:
     }
 
 private:
-    int (*printf_)(FILE *, const char *, ...);
+    fprintf_function printf_;
     FILE *stream_;
 };
 

disas/mips.c

@@ -1296,12 +1296,12 @@ const struct mips_opcode mips_builtin_opcodes[] =
 {"dmod",    "d,s,t",    0x000000de, 0xfc0007ff, WR_d|RD_s|RD_t,       0, I64R6},
 {"ddivu",   "d,s,t",    0x0000009f, 0xfc0007ff, WR_d|RD_s|RD_t,       0, I64R6},
 {"dmodu",   "d,s,t",    0x000000df, 0xfc0007ff, WR_d|RD_s|RD_t,       0, I64R6},
-{"ll",      "t,o(b)",   0x7c000036, 0xfc00007f, LDD|RD_b|WR_t,        0, I32R6},
-{"sc",      "t,o(b)",   0x7c000026, 0xfc00007f, LDD|RD_b|WR_t,        0, I32R6},
-{"lld",     "t,o(b)",   0x7c000037, 0xfc00007f, LDD|RD_b|WR_t,        0, I64R6},
-{"scd",     "t,o(b)",   0x7c000027, 0xfc00007f, LDD|RD_b|WR_t,        0, I64R6},
-{"pref",    "h,o(b)",   0x7c000035, 0xfc00007f, RD_b,                 0, I32R6},
-{"cache",   "k,o(b)",   0x7c000025, 0xfc00007f, RD_b,                 0, I32R6},
+{"ll",      "t,+o(b)",  0x7c000036, 0xfc00007f, LDD|RD_b|WR_t,        0, I32R6},
+{"sc",      "t,+o(b)",  0x7c000026, 0xfc00007f, LDD|RD_b|WR_t,        0, I32R6},
+{"lld",     "t,+o(b)",  0x7c000037, 0xfc00007f, LDD|RD_b|WR_t,        0, I64R6},
+{"scd",     "t,+o(b)",  0x7c000027, 0xfc00007f, LDD|RD_b|WR_t,        0, I64R6},
+{"pref",    "h,+o(b)",  0x7c000035, 0xfc00007f, RD_b,                 0, I32R6},
+{"cache",   "k,+o(b)",  0x7c000025, 0xfc00007f, RD_b,                 0, I32R6},
 {"seleqz",  "d,v,t",    0x00000035, 0xfc0007ff, WR_d|RD_s|RD_t,       0, I32R6},
 {"selnez",  "d,v,t",    0x00000037, 0xfc0007ff, WR_d|RD_s|RD_t,       0, I32R6},
 {"maddf.s", "D,S,T",    0x46000018, 0xffe0003f, WR_D|RD_S|RD_T|FP_S,  0, I32R6},

docs/aio_notify.promela

@@ -1,5 +1,5 @@
 /*
- * This model describes the interaction between aio_set_dispatching()
+ * This model describes the interaction between ctx->notify_me
  * and aio_notify().
  *
  * Author: Paolo Bonzini <pbonzini@redhat.com>
@@ -14,57 +14,53 @@
  *     spin -a docs/aio_notify.promela
  *     gcc -O2 pan.c
  *     ./a.out -a
+ *
+ * To verify it (with a bug planted in the model):
+ *     spin -a -DBUG docs/aio_notify.promela
+ *     gcc -O2 pan.c
+ *     ./a.out -a
  */
 
 #define MAX   4
 #define LAST  (1 << (MAX - 1))
 #define FINAL ((LAST << 1) - 1)
 
-bool dispatching;
+bool notify_me;
 bool event;
 
-int req, done;
+int req;
+int done;
 
 active proctype waiter()
 {
-     int fetch, blocking;
+    int fetch;
 
-     do
-        :: done != FINAL -> {
-            // Computing "blocking" is separate from execution of the
-            // "bottom half"
-            blocking = (req == 0);
+    do
+        :: true -> {
+            notify_me++;
+
+            if
+#ifndef BUG
+                :: (req > 0) -> skip;
+#endif
+                :: else ->
+                    // Wait for a nudge from the other side
+                    do
+                        :: event == 1 -> { event = 0; break; }
+                    od;
+            fi;
+
+            notify_me--;
 
-            // This is our "bottom half"
             atomic { fetch = req; req = 0; }
             done = done | fetch;
-
-            // Wait for a nudge from the other side
-            do
-                :: event == 1 -> { event = 0; break; }
-                :: !blocking  -> break;
-            od;
-
-            dispatching = 1;
-
-            // If you are simulating this model, you may want to add
-            // something like this here:
-            //
-            //      int foo; foo++; foo++; foo++;
-            //
-            // This only wastes some time and makes it more likely
-            // that the notifier process hits the "fast path".
-
-            dispatching = 0;
         }
-        :: else -> break;
     od
 }
 
 active proctype notifier()
 {
     int next = 1;
-    int sets = 0;
 
     do
         :: next <= LAST -> {
@@ -74,8 +70,8 @@ active proctype notifier()
 
             // aio_notify
             if
-                :: dispatching == 0 -> sets++; event = 1;
-                :: else             -> skip;
+                :: notify_me == 1 -> event = 1;
+                :: else           -> printf("Skipped event_notifier_set\n"); skip;
             fi;
 
             // Test both synchronous and asynchronous delivery
@@ -86,19 +82,12 @@ active proctype notifier()
                 :: 1 -> skip;
             fi;
         }
-        :: else -> break;
     od;
-    printf("Skipped %d event_notifier_set\n", MAX - sets);
 }
 
-#define p (done == FINAL)
-
-never  {
-    do
-        :: 1                      // after an arbitrarily long prefix
-        :: p -> break             // p becomes true
-    od;
-    do
-        :: !p -> accept: break    // it then must remains true forever after
-    od
+never { /* [] done < FINAL */
+accept_init:
+        do
+        :: done < FINAL -> skip;
+        od;
 }

docs/aio_notify_accept.promela

@@ -0,0 +1,152 @@
+/*
+ * This model describes the interaction between ctx->notified
+ * and ctx->notifier.
+ *
+ * Author: Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This file is in the public domain.  If you really want a license,
+ * the WTFPL will do.
+ *
+ * To verify the buggy version:
+ *     spin -a -DBUG1 docs/aio_notify_bug.promela
+ *     gcc -O2 pan.c
+ *     ./a.out -a -f
+ * (or -DBUG2)
+ *
+ * To verify the fixed version:
+ *     spin -a docs/aio_notify_bug.promela
+ *     gcc -O2 pan.c
+ *     ./a.out -a -f
+ *
+ * Add -DCHECK_REQ to test an alternative invariant and the
+ * "notify_me" optimization.
+ */
+
+int notify_me;
+bool notified;
+bool event;
+bool req;
+bool notifier_done;
+
+#ifdef CHECK_REQ
+#define USE_NOTIFY_ME 1
+#else
+#define USE_NOTIFY_ME 0
+#endif
+
+#ifdef BUG
+#error Please define BUG1 or BUG2 instead.
+#endif
+
+active proctype notifier()
+{
+    do
+        :: true -> {
+            req = 1;
+            if
+               :: !USE_NOTIFY_ME || notify_me ->
+#if defined BUG1
+                   /* CHECK_REQ does not detect this bug! */
+                   notified = 1;
+                   event = 1;
+#elif defined BUG2
+                   if
+                      :: !notified -> event = 1;
+                      :: else -> skip;
+                   fi;
+                   notified = 1;
+#else
+                   event = 1;
+                   notified = 1;
+#endif
+               :: else -> skip;
+            fi
+        }
+        :: true -> break;
+    od;
+    notifier_done = 1;
+}
+
+#define AIO_POLL                                                    \
+    notify_me++;                                                    \
+    if                                                              \
+        :: !req -> {                                                \
+            if                                                      \
+                :: event -> skip;                                   \
+            fi;                                                     \
+        }                                                           \
+        :: else -> skip;                                            \
+    fi;                                                             \
+    notify_me--;                                                    \
+                                                                    \
+    atomic { old = notified; notified = 0; }                        \
+    if                                                              \
+       :: old -> event = 0;                                         \
+       :: else -> skip;                                             \
+    fi;                                                             \
+                                                                    \
+    req = 0;
+
+active proctype waiter()
+{
+    bool old;
+
+    do
+       :: true -> AIO_POLL;
+    od;
+}
+
+/* Same as waiter(), but disappears after a while.  */
+active proctype temporary_waiter()
+{
+    bool old;
+
+    do
+       :: true -> AIO_POLL;
+       :: true -> break;
+    od;
+}
+
+#ifdef CHECK_REQ
+never {
+    do
+        :: req -> goto accept_if_req_not_eventually_false;
+        :: true -> skip;
+    od;
+
+accept_if_req_not_eventually_false:
+    if
+        :: req -> goto accept_if_req_not_eventually_false;
+    fi;
+    assert(0);
+}
+
+#else
+/* There must be infinitely many transitions of event as long
+ * as the notifier does not exit.
+ *
+ * If event stayed always true, the waiters would be busy looping.
+ * If event stayed always false, the waiters would be sleeping
+ * forever.
+ */
+never {
+    do
+        :: !event    -> goto accept_if_event_not_eventually_true;
+        :: event     -> goto accept_if_event_not_eventually_false;
+        :: true      -> skip;
+    od;
+
+accept_if_event_not_eventually_true:
+    if
+        :: !event && notifier_done  -> do :: true -> skip; od;
+        :: !event && !notifier_done -> goto accept_if_event_not_eventually_true;
+    fi;
+    assert(0);
+
+accept_if_event_not_eventually_false:
+    if
+        :: event     -> goto accept_if_event_not_eventually_false;
+    fi;
+    assert(0);
+}
+#endif

docs/aio_notify_bug.promela

@@ -0,0 +1,140 @@
+/*
+ * This model describes a bug in aio_notify.  If ctx->notifier is
+ * cleared too late, a wakeup could be lost.
+ *
+ * Author: Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This file is in the public domain.  If you really want a license,
+ * the WTFPL will do.
+ *
+ * To verify the buggy version:
+ *     spin -a -DBUG docs/aio_notify_bug.promela
+ *     gcc -O2 pan.c
+ *     ./a.out -a -f
+ *
+ * To verify the fixed version:
+ *     spin -a docs/aio_notify_bug.promela
+ *     gcc -O2 pan.c
+ *     ./a.out -a -f
+ *
+ * Add -DCHECK_REQ to test an alternative invariant and the
+ * "notify_me" optimization.
+ */
+
+int notify_me;
+bool event;
+bool req;
+bool notifier_done;
+
+#ifdef CHECK_REQ
+#define USE_NOTIFY_ME 1
+#else
+#define USE_NOTIFY_ME 0
+#endif
+
+active proctype notifier()
+{
+    do
+        :: true -> {
+            req = 1;
+            if
+               :: !USE_NOTIFY_ME || notify_me -> event = 1;
+               :: else -> skip;
+            fi
+        }
+        :: true -> break;
+    od;
+    notifier_done = 1;
+}
+
+#ifdef BUG
+#define AIO_POLL                                                    \
+    notify_me++;                                                    \
+    if                                                              \
+        :: !req -> {                                                \
+            if                                                      \
+                :: event -> skip;                                   \
+            fi;                                                     \
+        }                                                           \
+        :: else -> skip;                                            \
+    fi;                                                             \
+    notify_me--;                                                    \
+                                                                    \
+    req = 0;                                                        \
+    event = 0;
+#else
+#define AIO_POLL                                                    \
+    notify_me++;                                                    \
+    if                                                              \
+        :: !req -> {                                                \
+            if                                                      \
+                :: event -> skip;                                   \
+            fi;                                                     \
+        }                                                           \
+        :: else -> skip;                                            \
+    fi;                                                             \
+    notify_me--;                                                    \
+                                                                    \
+    event = 0;                                                      \
+    req = 0;
+#endif
+
+active proctype waiter()
+{
+    do
+       :: true -> AIO_POLL;
+    od;
+}
+
+/* Same as waiter(), but disappears after a while.  */
+active proctype temporary_waiter()
+{
+    do
+       :: true -> AIO_POLL;
+       :: true -> break;
+    od;
+}
+
+#ifdef CHECK_REQ
+never {
+    do
+        :: req -> goto accept_if_req_not_eventually_false;
+        :: true -> skip;
+    od;
+
+accept_if_req_not_eventually_false:
+    if
+        :: req -> goto accept_if_req_not_eventually_false;
+    fi;
+    assert(0);
+}
+
+#else
+/* There must be infinitely many transitions of event as long
+ * as the notifier does not exit.
+ *
+ * If event stayed always true, the waiters would be busy looping.
+ * If event stayed always false, the waiters would be sleeping
+ * forever.
+ */
+never {
+    do
+        :: !event    -> goto accept_if_event_not_eventually_true;
+        :: event     -> goto accept_if_event_not_eventually_false;
+        :: true      -> skip;
+    od;
+
+accept_if_event_not_eventually_true:
+    if
+        :: !event && notifier_done  -> do :: true -> skip; od;
+        :: !event && !notifier_done -> goto accept_if_event_not_eventually_true;
+    fi;
+    assert(0);
+
+accept_if_event_not_eventually_false:
+    if
+        :: event     -> goto accept_if_event_not_eventually_false;
+    fi;
+    assert(0);
+}
+#endif

docs/specs/vhost-user.txt

@@ -127,11 +127,6 @@ in the ancillary data:
 If Master is unable to send the full message or receives a wrong reply it will
 close the connection. An optional reconnection mechanism can be implemented.
 
-Multi queue support
--------------------
-The protocol supports multiple queues by setting all index fields in the sent
-messages to a properly calculated value.
-
 Message types
 -------------
 

exec.c

@@ -954,7 +954,10 @@ hwaddr memory_region_section_get_iotlb(CPUState *cpu,
             iotlb |= PHYS_SECTION_ROM;
         }
     } else {
-        iotlb = section - section->address_space->dispatch->map.sections;
+        AddressSpaceDispatch *d;
+
+        d = atomic_rcu_read(&section->address_space->dispatch);
+        iotlb = section - d->map.sections;
         iotlb += xlat;
     }
 

gdbstub.c

@@ -1285,6 +1285,7 @@ static void gdb_vm_state_change(void *opaque, int running, RunState state)
         ret = GDB_SIGNAL_UNKNOWN;
         break;
     }
+    gdb_set_stop_cpu(cpu);
     snprintf(buf, sizeof(buf), "T%02xthread:%02x;", ret, cpu_index(cpu));
 
 send_packet:

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

@@ -21,7 +21,8 @@
 #include "virtio-9p-coth.h"
 #include "hw/virtio/virtio-access.h"
 
-static uint64_t virtio_9p_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_9p_get_features(VirtIODevice *vdev, uint64_t features,
+                                       Error **errp)
 {
     virtio_add_feature(&features, VIRTIO_9P_MOUNT_TAG);
     return features;

hw/9pfs/virtio-9p.c

@@ -14,6 +14,7 @@
 #include "hw/virtio/virtio.h"
 #include "hw/i386/pc.h"
 #include "qemu/error-report.h"
+#include "qemu/iov.h"
 #include "qemu/sockets.h"
 #include "virtio-9p.h"
 #include "fsdev/qemu-fsdev.h"
@@ -3261,16 +3262,26 @@ void handle_9p_output(VirtIODevice *vdev, VirtQueue *vq)
 
     while ((pdu = alloc_pdu(s)) &&
             (len = virtqueue_pop(vq, &pdu->elem)) != 0) {
-        uint8_t *ptr;
+        struct {
+            uint32_t size_le;
+            uint8_t id;
+            uint16_t tag_le;
+        } QEMU_PACKED out;
+        int len;
+
         pdu->s = s;
         BUG_ON(pdu->elem.out_num == 0 || pdu->elem.in_num == 0);
-        BUG_ON(pdu->elem.out_sg[0].iov_len < 7);
+        QEMU_BUILD_BUG_ON(sizeof out != 7);
 
-        ptr = pdu->elem.out_sg[0].iov_base;
+        len = iov_to_buf(pdu->elem.out_sg, pdu->elem.out_num, 0,
+                         &out, sizeof out);
+        BUG_ON(len != sizeof out);
+
+        pdu->size = le32_to_cpu(out.size_le);
+
+        pdu->id = out.id;
+        pdu->tag = le16_to_cpu(out.tag_le);
 
-        pdu->size = le32_to_cpu(*(uint32_t *)ptr);
-        pdu->id = ptr[4];
-        pdu->tag = le16_to_cpu(*(uint16_t *)(ptr + 5));
         qemu_co_queue_init(&pdu->complete);
         submit_pdu(s, pdu);
     }

hw/acpi/ich9.c

@@ -206,9 +206,6 @@ const VMStateDescription vmstate_ich9_pm = {
     },
     .subsections = (const VMStateDescription*[]) {
         &vmstate_memhp_state,
-        NULL
-    },
-    .subsections = (const VMStateDescription*[]) {
         &vmstate_tco_io_state,
         NULL
     }
@@ -224,9 +221,9 @@ static void pm_reset(void *opaque)
     acpi_pm_tmr_reset(&pm->acpi_regs);
     acpi_gpe_reset(&pm->acpi_regs);
 
+    pm->smi_en = 0;
     if (!pm->smm_enabled) {
-        /* Mark SMM as already inited to prevent SMM from running. KVM does not
-         * support SMM mode. */
+        /* Mark SMM as already inited to prevent SMM from running. */
         pm->smi_en |= ICH9_PMIO_SMI_EN_APMC_EN;
     }
     pm->smi_en_wmask = ~0;

hw/arm/boot.c

@@ -735,12 +735,28 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
          * we point to the kernel args.
          */
         if (have_dtb(info)) {
-            /* Place the DTB after the initrd in memory. Note that some
-             * kernels will trash anything in the 4K page the initrd
-             * ends in, so make sure the DTB isn't caught up in that.
-             */
-            hwaddr dtb_start = QEMU_ALIGN_UP(info->initrd_start + initrd_size,
-                                             4096);
+            hwaddr align;
+            hwaddr dtb_start;
+
+            if (elf_machine == EM_AARCH64) {
+                /*
+                 * Some AArch64 kernels on early bootup map the fdt region as
+                 *
+                 *   [ ALIGN_DOWN(fdt, 2MB) ... ALIGN_DOWN(fdt, 2MB) + 2MB ]
+                 *
+                 * Let's play safe and prealign it to 2MB to give us some space.
+                 */
+                align = 2 * 1024 * 1024;
+            } else {
+                /*
+                 * Some 32bit kernels will trash anything in the 4K page the
+                 * initrd ends in, so make sure the DTB isn't caught up in that.
+                 */
+                align = 4096;
+            }
+
+            /* Place the DTB after the initrd in memory with alignment. */
+            dtb_start = QEMU_ALIGN_UP(info->initrd_start + initrd_size, align);
             if (load_dtb(dtb_start, info, 0) < 0) {
                 exit(1);
             }

hw/arm/musicpal.c

@@ -187,11 +187,6 @@ static void eth_rx_desc_get(uint32_t addr, mv88w8618_rx_desc *desc)
     le32_to_cpus(&desc->next);
 }
 
-static int eth_can_receive(NetClientState *nc)
-{
-    return 1;
-}
-
 static ssize_t eth_receive(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     mv88w8618_eth_state *s = qemu_get_nic_opaque(nc);
@@ -381,7 +376,6 @@ static void eth_cleanup(NetClientState *nc)
 static NetClientInfo net_mv88w8618_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = eth_can_receive,
     .receive = eth_receive,
     .cleanup = eth_cleanup,
 };

hw/arm/xlnx-zynqmp.c

@@ -144,6 +144,7 @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp)
         } else {
             s->boot_cpu_ptr = &s->apu_cpu[i];
         }
+        g_free(name);
 
         object_property_set_int(OBJECT(&s->apu_cpu[i]), GIC_BASE_ADDR,
                                 "reset-cbar", &err);
@@ -181,6 +182,7 @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp)
         } else {
             s->boot_cpu_ptr = &s->rpu_cpu[i];
         }
+        g_free(name);
 
         object_property_set_bool(OBJECT(&s->rpu_cpu[i]), true, "reset-hivecs",
                                  &err);

hw/block/dataplane/virtio-blk.c

@@ -223,8 +223,8 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
     virtio_blk_data_plane_stop(s);
     blk_op_unblock_all(s->conf->conf.blk, s->blocker);
     error_free(s->blocker);
-    object_unref(OBJECT(s->iothread));
     qemu_bh_delete(s->bh);
+    object_unref(OBJECT(s->iothread));
     g_free(s);
 }
 

hw/block/nvme.c

@@ -207,11 +207,23 @@ static void nvme_rw_cb(void *opaque, int ret)
     } else {
         req->status = NVME_INTERNAL_DEV_ERROR;
     }
-
-    qemu_sglist_destroy(&req->qsg);
+    if (req->has_sg) {
+        qemu_sglist_destroy(&req->qsg);
+    }
     nvme_enqueue_req_completion(cq, req);
 }
 
+static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
+    NvmeRequest *req)
+{
+    req->has_sg = false;
+    block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
+         BLOCK_ACCT_FLUSH);
+    req->aiocb = blk_aio_flush(n->conf.blk, nvme_rw_cb, req);
+
+    return NVME_NO_COMPLETE;
+}
+
 static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     NvmeRequest *req)
 {
@@ -235,6 +247,7 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     }
     assert((nlb << data_shift) == req->qsg.size);
 
+    req->has_sg = true;
     dma_acct_start(n->conf.blk, &req->acct, &req->qsg,
                    is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
     req->aiocb = is_write ?
@@ -256,7 +269,7 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     ns = &n->namespaces[nsid - 1];
     switch (cmd->opcode) {
     case NVME_CMD_FLUSH:
-        return NVME_SUCCESS;
+        return nvme_flush(n, ns, cmd, req);
     case NVME_CMD_WRITE:
     case NVME_CMD_READ:
         return nvme_rw(n, ns, cmd, req);
@@ -474,26 +487,32 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
 static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     uint32_t dw10 = le32_to_cpu(cmd->cdw10);
+    uint32_t result;
 
     switch (dw10) {
-    case NVME_NUMBER_OF_QUEUES:
-        req->cqe.result =
-            cpu_to_le32((n->num_queues - 1) | ((n->num_queues - 1) << 16));
-        break;
     case NVME_VOLATILE_WRITE_CACHE:
-        req->cqe.result = cpu_to_le32(1);
+        result = blk_enable_write_cache(n->conf.blk);
+        break;
+    case NVME_NUMBER_OF_QUEUES:
+        result = cpu_to_le32((n->num_queues - 1) | ((n->num_queues - 1) << 16));
         break;
     default:
         return NVME_INVALID_FIELD | NVME_DNR;
     }
+
+    req->cqe.result = result;
     return NVME_SUCCESS;
 }
 
 static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     uint32_t dw10 = le32_to_cpu(cmd->cdw10);
+    uint32_t dw11 = le32_to_cpu(cmd->cdw11);
 
     switch (dw10) {
+    case NVME_VOLATILE_WRITE_CACHE:
+        blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
+        break;
     case NVME_NUMBER_OF_QUEUES:
         req->cqe.result =
             cpu_to_le32((n->num_queues - 1) | ((n->num_queues - 1) << 16));
@@ -818,6 +837,9 @@ static int nvme_init(PCIDevice *pci_dev)
     id->psd[0].mp = cpu_to_le16(0x9c4);
     id->psd[0].enlat = cpu_to_le32(0x10);
     id->psd[0].exlat = cpu_to_le32(0x4);
+    if (blk_enable_write_cache(n->conf.blk)) {
+        id->vwc = 1;
+    }
 
     n->bar.cap = 0;
     NVME_CAP_SET_MQES(n->bar.cap, 0x7ff);

hw/block/nvme.h

@@ -638,6 +638,7 @@ typedef struct NvmeRequest {
     struct NvmeSQueue       *sq;
     BlockAIOCB              *aiocb;
     uint16_t                status;
+    bool                    has_sg;
     NvmeCqe                 cqe;
     BlockAcctCookie         acct;
     QEMUSGList              qsg;

hw/block/virtio-blk.c

@@ -722,7 +722,8 @@ static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
     aio_context_release(blk_get_aio_context(s->blk));
 }
 
-static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
+                                        Error **errp)
 {
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 
@@ -730,7 +731,15 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features)
     virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
     virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
     virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
-    virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
+    if (__virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
+        if (s->conf.scsi) {
+            error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
+            return 0;
+        }
+    } else {
+        virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT);
+        virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
+    }
 
     if (s->conf.config_wce) {
         virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE);

hw/char/virtio-serial-bus.c

@@ -195,7 +195,8 @@ static size_t send_control_msg(VirtIOSerial *vser, void *buf, size_t len)
         return 0;
     }
 
-    memcpy(elem.in_sg[0].iov_base, buf, len);
+    /* TODO: detect a buffer that's too short, set NEEDS_RESET */
+    iov_from_buf(elem.in_sg, elem.in_num, 0, buf, len);
 
     virtqueue_push(vq, &elem, len);
     virtio_notify(VIRTIO_DEVICE(vser), vq);
@@ -499,7 +500,8 @@ static void handle_input(VirtIODevice *vdev, VirtQueue *vq)
     }
 }
 
-static uint64_t get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t get_features(VirtIODevice *vdev, uint64_t features,
+                             Error **errp)
 {
     VirtIOSerial *vser;
 

hw/core/qdev-properties.c

@@ -130,7 +130,7 @@ PropertyInfo qdev_prop_bit = {
 
 static uint64_t qdev_get_prop_mask64(Property *prop)
 {
-    assert(prop->info == &qdev_prop_bit);
+    assert(prop->info == &qdev_prop_bit64);
     return 0x1ull << prop->bitnr;
 }
 

hw/display/framebuffer.c

@@ -21,12 +21,40 @@
 #include "ui/console.h"
 #include "framebuffer.h"
 
+void framebuffer_update_memory_section(
+    MemoryRegionSection *mem_section,
+    MemoryRegion *root,
+    hwaddr base,
+    unsigned rows,
+    unsigned src_width)
+{
+    hwaddr src_len = (hwaddr)rows * src_width;
+
+    if (mem_section->mr) {
+        memory_region_set_log(mem_section->mr, false, DIRTY_MEMORY_VGA);
+        memory_region_unref(mem_section->mr);
+        mem_section->mr = NULL;
+    }
+
+    *mem_section = memory_region_find(root, base, src_len);
+    if (!mem_section->mr) {
+        return;
+    }
+
+    if (int128_get64(mem_section->size) < src_len ||
+            !memory_region_is_ram(mem_section->mr)) {
+        memory_region_unref(mem_section->mr);
+        mem_section->mr = NULL;
+        return;
+    }
+
+    memory_region_set_log(mem_section->mr, true, DIRTY_MEMORY_VGA);
+}
+
 /* Render an image from a shared memory framebuffer.  */
-   
 void framebuffer_update_display(
     DisplaySurface *ds,
-    MemoryRegion *address_space,
-    hwaddr base,
+    MemoryRegionSection *mem_section,
     int cols, /* Width in pixels.  */
     int rows, /* Height in pixels.  */
     int src_width, /* Length of source line, in bytes.  */
@@ -41,51 +69,33 @@ void framebuffer_update_display(
     hwaddr src_len;
     uint8_t *dest;
     uint8_t *src;
-    uint8_t *src_base;
     int first, last = 0;
     int dirty;
     int i;
     ram_addr_t addr;
-    MemoryRegionSection mem_section;
     MemoryRegion *mem;
 
     i = *first_row;
     *first_row = -1;
     src_len = src_width * rows;
 
-    mem_section = memory_region_find(address_space, base, src_len);
-    mem = mem_section.mr;
-    if (int128_get64(mem_section.size) != src_len ||
-            !memory_region_is_ram(mem_section.mr)) {
-        goto out;
+    mem = mem_section->mr;
+    if (!mem) {
+        return;
     }
-    assert(mem);
-    assert(mem_section.offset_within_address_space == base);
-
     memory_region_sync_dirty_bitmap(mem);
-    if (!memory_region_is_logging(mem, DIRTY_MEMORY_VGA)) {
-        invalidate = true;
-    }
 
-    src_base = cpu_physical_memory_map(base, &src_len, 0);
-    /* If we can't map the framebuffer then bail.  We could try harder,
-       but it's not really worth it as dirty flag tracking will probably
-       already have failed above.  */
-    if (!src_base)
-        goto out;
-    if (src_len != src_width * rows) {
-        cpu_physical_memory_unmap(src_base, src_len, 0, 0);
-        goto out;
-    }
-    src = src_base;
+    addr = mem_section->offset_within_region;
+    src = memory_region_get_ram_ptr(mem) + addr;
+
     dest = surface_data(ds);
-    if (dest_col_pitch < 0)
+    if (dest_col_pitch < 0) {
         dest -= dest_col_pitch * (cols - 1);
+    }
     if (dest_row_pitch < 0) {
         dest -= dest_row_pitch * (rows - 1);
     }
     first = -1;
-    addr = mem_section.offset_within_region;
 
     addr += i * src_width;
     src += i * src_width;
@@ -104,14 +114,11 @@ void framebuffer_update_display(
         src += src_width;
         dest += dest_row_pitch;
     }
-    cpu_physical_memory_unmap(src_base, src_len, 0, 0);
     if (first < 0) {
-        goto out;
+        return;
     }
-    memory_region_reset_dirty(mem, mem_section.offset_within_region, src_len,
+    memory_region_reset_dirty(mem, mem_section->offset_within_region, src_len,
                               DIRTY_MEMORY_VGA);
     *first_row = first;
     *last_row = last;
-out:
-    memory_region_unref(mem);
 }

hw/display/framebuffer.h

@@ -7,10 +7,50 @@
 
 typedef void (*drawfn)(void *, uint8_t *, const uint8_t *, int, int);
 
+/* framebuffer_update_memory_section: Update framebuffer
+ * #MemoryRegionSection, for example if the framebuffer is switched to
+ * a different memory area.
+ *
+ * @mem_section: Output #MemoryRegionSection, to be passed to
+ * framebuffer_update_display().
+ * @root: #MemoryRegion within which the framebuffer lies
+ * @base: Base address of the framebuffer within @root.
+ * @rows: Height of the screen.
+ * @src_width: Number of bytes in framebuffer memory between two rows.
+ */
+void framebuffer_update_memory_section(
+    MemoryRegionSection *mem_section,
+    MemoryRegion *root,
+    hwaddr base,
+    unsigned rows,
+    unsigned src_width);
+
+/* framebuffer_update_display: Draw the framebuffer on a surface.
+ *
+ * @ds: #DisplaySurface to draw to.
+ * @mem_section: #MemoryRegionSection provided by
+ * framebuffer_update_memory_section().
+ * @cols: Width the screen.
+ * @rows: Height of the screen.
+ * @src_width: Number of bytes in framebuffer memory between two rows.
+ * @dest_row_pitch: Number of bytes in the surface data between two rows.
+ * Negative if the framebuffer is stored in the opposite order (e.g.
+ * bottom-to-top) compared to the framebuffer.
+ * @dest_col_pitch: Number of bytes in the surface data between two pixels.
+ * Negative if the framebuffer is stored in the opposite order (e.g.
+ * right-to-left) compared to the framebuffer.
+ * @invalidate: True if the function should redraw the whole screen
+ * without checking the DIRTY_MEMORY_VGA dirty bitmap.
+ * @fn: Drawing function to be called for each row that has to be drawn.
+ * @opaque: Opaque pointer passed to @fn.
+ * @first_row: Pointer to an integer, receives the number of the first row
+ * that was drawn (either the first dirty row, or 0 if @invalidate is true).
+ * @last_row: Pointer to an integer, receives the number of the last row that
+ * was drawn (either the last dirty row, or @rows-1 if @invalidate is true).
+ */
 void framebuffer_update_display(
     DisplaySurface *ds,
-    MemoryRegion *address_space,
-    hwaddr base,
+    MemoryRegionSection *mem_section,
     int cols,
     int rows,
     int src_width,

hw/display/milkymist-vgafb.c

@@ -71,6 +71,7 @@ struct MilkymistVgafbState {
     SysBusDevice parent_obj;
 
     MemoryRegion regs_region;
+    MemoryRegionSection fbsection;
     QemuConsole *con;
 
     int invalidate;
@@ -91,6 +92,7 @@ static void vgafb_update_display(void *opaque)
     MilkymistVgafbState *s = opaque;
     SysBusDevice *sbd;
     DisplaySurface *surface = qemu_console_surface(s->con);
+    int src_width;
     int first = 0;
     int last = 0;
     drawfn fn;
@@ -129,11 +131,18 @@ static void vgafb_update_display(void *opaque)
         break;
     }
 
-    framebuffer_update_display(surface, sysbus_address_space(sbd),
-                               s->regs[R_BASEADDRESS] + s->fb_offset,
+    src_width = s->regs[R_HRES] * 2;
+    if (s->invalidate) {
+        framebuffer_update_memory_section(&s->fbsection,
+                                          sysbus_address_space(sbd),
+                                          s->regs[R_BASEADDRESS] + s->fb_offset,
+                                          s->regs[R_VRES], src_width);
+    }
+
+    framebuffer_update_display(surface, &s->fbsection,
                                s->regs[R_HRES],
                                s->regs[R_VRES],
-                               s->regs[R_HRES] * 2,
+                               src_width,
                                dest_width,
                                0,
                                s->invalidate,

hw/display/omap_lcdc.c

@@ -25,6 +25,7 @@
 struct omap_lcd_panel_s {
     MemoryRegion *sysmem;
     MemoryRegion iomem;
+    MemoryRegionSection fbsection;
     qemu_irq irq;
     QemuConsole *con;
 
@@ -215,12 +216,19 @@ static void omap_update_display(void *opaque)
 
     step = width * bpp >> 3;
     linesize = surface_stride(surface);
-    framebuffer_update_display(surface, omap_lcd->sysmem,
-                               frame_base, width, height,
+    if (omap_lcd->invalidate) {
+        framebuffer_update_memory_section(&omap_lcd->fbsection,
+                                          omap_lcd->sysmem, frame_base,
+                                          height, step);
+    }
+
+    framebuffer_update_display(surface, &omap_lcd->fbsection,
+                               width, height,
                                step, linesize, 0,
                                omap_lcd->invalidate,
                                draw_line, omap_lcd->palette,
                                &first, &last);
+
     if (first >= 0) {
         dpy_gfx_update(omap_lcd->con, 0, first, width, last - first + 1);
     }

hw/display/pl110.c

@@ -46,6 +46,7 @@ typedef struct PL110State {
     SysBusDevice parent_obj;
 
     MemoryRegion iomem;
+    MemoryRegionSection fbsection;
     QemuConsole *con;
 
     int version;
@@ -238,12 +239,20 @@ static void pl110_update_display(void *opaque)
     }
     dest_width *= s->cols;
     first = 0;
-    framebuffer_update_display(surface, sysbus_address_space(sbd),
-                               s->upbase, s->cols, s->rows,
+    if (s->invalidate) {
+        framebuffer_update_memory_section(&s->fbsection,
+                                          sysbus_address_space(sbd),
+                                          s->upbase,
+                                          s->rows, src_width);
+    }
+
+    framebuffer_update_display(surface, &s->fbsection,
+                               s->cols, s->rows,
                                src_width, dest_width, 0,
                                s->invalidate,
                                fn, s->palette,
                                &first, &last);
+
     if (first >= 0) {
         dpy_gfx_update(s->con, 0, first, s->cols, last - first + 1);
     }

hw/display/pxa2xx_lcd.c

@@ -35,6 +35,7 @@ struct DMAChannel {
 struct PXA2xxLCDState {
     MemoryRegion *sysmem;
     MemoryRegion iomem;
+    MemoryRegionSection fbsection;
     qemu_irq irq;
     int irqlevel;
 
@@ -687,8 +688,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot0(PXA2xxLCDState *s,
 
     dest_width = s->xres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, dest_width, s->dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette, miny, maxy);
@@ -715,8 +719,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot90(PXA2xxLCDState *s,
 
     dest_width = s->yres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, s->dest_width, -dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette,
@@ -747,8 +754,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot180(PXA2xxLCDState *s,
 
     dest_width = s->xres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, -dest_width, -s->dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette, miny, maxy);
@@ -778,8 +788,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot270(PXA2xxLCDState *s,
 
     dest_width = s->yres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, -s->dest_width, dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette,

hw/display/qxl.c

@@ -271,6 +271,11 @@ static void qxl_spice_monitors_config_async(PCIQXLDevice *qxl, int replay)
                     QXL_COOKIE_TYPE_POST_LOAD_MONITORS_CONFIG,
                     0));
     } else {
+#if SPICE_SERVER_VERSION >= 0x000c06 /* release 0.12.6 */
+        if (qxl->max_outputs) {
+            spice_qxl_set_max_monitors(&qxl->ssd.qxl, qxl->max_outputs);
+        }
+#endif
         qxl->guest_monitors_config = qxl->ram->monitors_config;
         spice_qxl_monitors_config_async(&qxl->ssd.qxl,
                 qxl->ram->monitors_config,
@@ -991,6 +996,7 @@ static int interface_client_monitors_config(QXLInstance *sin,
     PCIQXLDevice *qxl = container_of(sin, PCIQXLDevice, ssd.qxl);
     QXLRom *rom = memory_region_get_ram_ptr(&qxl->rom_bar);
     int i;
+    unsigned max_outputs = ARRAY_SIZE(rom->client_monitors_config.heads);
 
     if (qxl->revision < 4) {
         trace_qxl_client_monitors_config_unsupported_by_device(qxl->id,
@@ -1013,17 +1019,23 @@ static int interface_client_monitors_config(QXLInstance *sin,
     if (!monitors_config) {
         return 1;
     }
+
+#if SPICE_SERVER_VERSION >= 0x000c06 /* release 0.12.6 */
+    /* limit number of outputs based on setting limit */
+    if (qxl->max_outputs && qxl->max_outputs <= max_outputs) {
+        max_outputs = qxl->max_outputs;
+    }
+#endif
+
     memset(&rom->client_monitors_config, 0,
            sizeof(rom->client_monitors_config));
     rom->client_monitors_config.count = monitors_config->num_of_monitors;
     /* monitors_config->flags ignored */
-    if (rom->client_monitors_config.count >=
-            ARRAY_SIZE(rom->client_monitors_config.heads)) {
+    if (rom->client_monitors_config.count >= max_outputs) {
         trace_qxl_client_monitors_config_capped(qxl->id,
                                 monitors_config->num_of_monitors,
-                                ARRAY_SIZE(rom->client_monitors_config.heads));
-        rom->client_monitors_config.count =
-            ARRAY_SIZE(rom->client_monitors_config.heads);
+                                max_outputs);
+        rom->client_monitors_config.count = max_outputs;
     }
     for (i = 0 ; i < rom->client_monitors_config.count ; ++i) {
         VDAgentMonConfig *monitor = &monitors_config->monitors[i];
@@ -2274,6 +2286,9 @@ static Property qxl_properties[] = {
         DEFINE_PROP_UINT32("vram64_size_mb", PCIQXLDevice, vram_size_mb, -1),
         DEFINE_PROP_UINT32("vgamem_mb", PCIQXLDevice, vgamem_size_mb, 16),
         DEFINE_PROP_INT32("surfaces", PCIQXLDevice, ssd.num_surfaces, 1024),
+#if SPICE_SERVER_VERSION >= 0x000c06 /* release 0.12.6 */
+        DEFINE_PROP_UINT16("max_outputs", PCIQXLDevice, max_outputs, 0),
+#endif
         DEFINE_PROP_END_OF_LIST(),
 };
 

hw/display/qxl.h

@@ -99,6 +99,9 @@ typedef struct PCIQXLDevice {
     QXLModes           *modes;
     uint32_t           rom_size;
     MemoryRegion       rom_bar;
+#if SPICE_SERVER_VERSION >= 0x000c06 /* release 0.12.6 */
+    uint16_t           max_outputs;
+#endif
 
     /* vram pci bar */
     uint32_t           vram_size;

hw/display/virtio-gpu.c

@@ -89,7 +89,8 @@ static void virtio_gpu_set_config(VirtIODevice *vdev, const uint8_t *config)
     }
 }
 
-static uint64_t virtio_gpu_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_gpu_get_features(VirtIODevice *vdev, uint64_t features,
+                                        Error **errp)
 {
     return features;
 }

hw/i386/acpi-build.c

@@ -1108,8 +1108,8 @@ build_ssdt(GArray *table_data, GArray *linker,
         aml_append(field, aml_named_field("PEPT", 8));
         aml_append(dev, field);
 
-        /* device present, functioning, decoding, not shown in UI */
-        aml_append(dev, aml_name_decl("_STA", aml_int(0xB)));
+        /* device present, functioning, decoding, shown in UI */
+        aml_append(dev, aml_name_decl("_STA", aml_int(0xF)));
 
         method = aml_method("RDPT", 0);
         aml_append(method, aml_store(aml_name("PEPT"), aml_local(0)));

hw/i386/pc_piix.c

@@ -492,7 +492,7 @@ DEFINE_I440FX_MACHINE(v2_4, "pc-i440fx-2.4", NULL,
 
 static void pc_i440fx_2_3_machine_options(MachineClass *m)
 {
-    pc_i440fx_machine_options(m);
+    pc_i440fx_2_4_machine_options(m);
     m->alias = NULL;
     m->is_default = 0;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_3);

hw/ide/ahci.c

@@ -279,8 +279,13 @@ static void  ahci_port_write(AHCIState *s, int port, int offset, uint32_t val)
             break;
         case PORT_CMD:
             /* Block any Read-only fields from being set;
-             * including LIST_ON and FIS_ON. */
-            pr->cmd = (pr->cmd & PORT_CMD_RO_MASK) | (val & ~PORT_CMD_RO_MASK);
+             * including LIST_ON and FIS_ON.
+             * The spec requires to set ICC bits to zero after the ICC change
+             * is done. We don't support ICC state changes, therefore always
+             * force the ICC bits to zero.
+             */
+            pr->cmd = (pr->cmd & PORT_CMD_RO_MASK) |
+                      (val & ~(PORT_CMD_RO_MASK|PORT_CMD_ICC_MASK));
 
             /* Check FIS RX and CLB engines, allow transition to false: */
             ahci_cond_start_engines(&s->dev[port], true);

hw/ide/ahci.h

@@ -127,7 +127,7 @@
 #define PORT_CMD_SPIN_UP          (1 << 1) /* Spin up device */
 #define PORT_CMD_START            (1 << 0) /* Enable port DMA engine */
 
-#define PORT_CMD_ICC_MASK         (0xf << 28) /* i/f ICC state mask */
+#define PORT_CMD_ICC_MASK        (0xfU << 28) /* i/f ICC state mask */
 #define PORT_CMD_ICC_ACTIVE       (0x1 << 28) /* Put i/f in active state */
 #define PORT_CMD_ICC_PARTIAL      (0x2 << 28) /* Put i/f in partial state */
 #define PORT_CMD_ICC_SLUMBER      (0x6 << 28) /* Put i/f in slumber state */

hw/ide/atapi.c

@@ -983,6 +983,7 @@ static void cmd_start_stop_unit(IDEState *s, uint8_t* buf)
 
     if (pwrcnd) {
         /* eject/load only happens for power condition == 0 */
+        ide_atapi_cmd_ok(s);
         return;
     }
 

hw/ide/core.c

@@ -2021,11 +2021,17 @@ void ide_data_writew(void *opaque, uint32_t addr, uint32_t val)
     }
 
     p = s->data_ptr;
+    if (p + 2 > s->data_end) {
+        return;
+    }
+
     *(uint16_t *)p = le16_to_cpu(val);
     p += 2;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
 }
 
 uint32_t ide_data_readw(void *opaque, uint32_t addr)
@@ -2042,11 +2048,17 @@ uint32_t ide_data_readw(void *opaque, uint32_t addr)
     }
 
     p = s->data_ptr;
+    if (p + 2 > s->data_end) {
+        return 0;
+    }
+
     ret = cpu_to_le16(*(uint16_t *)p);
     p += 2;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
     return ret;
 }
 
@@ -2063,11 +2075,17 @@ void ide_data_writel(void *opaque, uint32_t addr, uint32_t val)
     }
 
     p = s->data_ptr;
+    if (p + 4 > s->data_end) {
+        return;
+    }
+
     *(uint32_t *)p = le32_to_cpu(val);
     p += 4;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
 }
 
 uint32_t ide_data_readl(void *opaque, uint32_t addr)
@@ -2084,11 +2102,17 @@ uint32_t ide_data_readl(void *opaque, uint32_t addr)
     }
 
     p = s->data_ptr;
+    if (p + 4 > s->data_end) {
+        return 0;
+    }
+
     ret = cpu_to_le32(*(uint32_t *)p);
     p += 4;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
     return ret;
 }
 

hw/ide/macio.c

@@ -208,6 +208,33 @@ static void pmac_dma_write(BlockBackend *blk,
                               cb, io);
 }
 
+static void pmac_dma_trim(BlockBackend *blk,
+                        int64_t offset, int bytes,
+                        void (*cb)(void *opaque, int ret), void *opaque)
+{
+    DBDMA_io *io = opaque;
+    MACIOIDEState *m = io->opaque;
+    IDEState *s = idebus_active_if(&m->bus);
+    dma_addr_t dma_addr, dma_len;
+    void *mem;
+
+    qemu_iovec_destroy(&io->iov);
+    qemu_iovec_init(&io->iov, io->len / MACIO_PAGE_SIZE + 1);
+
+    dma_addr = io->addr;
+    dma_len = io->len;
+    mem = dma_memory_map(&address_space_memory, dma_addr, &dma_len,
+                         DMA_DIRECTION_TO_DEVICE);
+
+    qemu_iovec_add(&io->iov, mem, io->len);
+    s->io_buffer_size -= io->len;
+    s->io_buffer_index += io->len;
+    io->len = 0;
+
+    m->aiocb = ide_issue_trim(blk, (offset >> 9), &io->iov, (bytes >> 9),
+                              cb, io);
+}
+
 static void pmac_ide_atapi_transfer_cb(void *opaque, int ret)
 {
     DBDMA_io *io = opaque;
@@ -313,6 +340,7 @@ static void pmac_ide_transfer_cb(void *opaque, int ret)
         pmac_dma_write(s->blk, offset, io->len, pmac_ide_transfer_cb, io);
         break;
     case IDE_DMA_TRIM:
+        pmac_dma_trim(s->blk, offset, io->len, pmac_ide_transfer_cb, io);
         break;
     }
 

hw/ide/piix.c

@@ -169,6 +169,7 @@ int pci_piix3_xen_ide_unplug(DeviceState *dev)
     PCIIDEState *pci_ide;
     DriveInfo *di;
     int i;
+    IDEDevice *idedev;
 
     pci_ide = PCI_IDE(dev);
 
@@ -181,6 +182,12 @@ int pci_piix3_xen_ide_unplug(DeviceState *dev)
                 blk_detach_dev(blk, ds);
             }
             pci_ide->bus[di->bus].ifs[di->unit].blk = NULL;
+            if (!(i % 2)) {
+                idedev = pci_ide->bus[di->bus].master;
+            } else {
+                idedev = pci_ide->bus[di->bus].slave;
+            }
+            idedev->conf.blk = NULL;
             blk_unref(blk);
         }
     }

hw/input/hid.c

@@ -239,7 +239,7 @@ static void hid_keyboard_event(DeviceState *dev, QemuConsole *src,
 
 static void hid_keyboard_process_keycode(HIDState *hs)
 {
-    uint8_t hid_code, key;
+    uint8_t hid_code, index, key;
     int i, keycode, slot;
 
     if (hs->n == 0) {
@@ -249,7 +249,8 @@ static void hid_keyboard_process_keycode(HIDState *hs)
     keycode = hs->kbd.keycodes[slot];
 
     key = keycode & 0x7f;
-    hid_code = hid_usage_keys[key | ((hs->kbd.modifiers >> 1) & (1 << 7))];
+    index = key | ((hs->kbd.modifiers & (1 << 8)) >> 1);
+    hid_code = hid_usage_keys[index];
     hs->kbd.modifiers &= ~(1 << 8);
 
     switch (hid_code) {
@@ -257,18 +258,41 @@ static void hid_keyboard_process_keycode(HIDState *hs)
         return;
 
     case 0xe0:
+        assert(key == 0x1d);
         if (hs->kbd.modifiers & (1 << 9)) {
-            hs->kbd.modifiers ^= 3 << 8;
+            /* The hid_codes for the 0xe1/0x1d scancode sequence are 0xe9/0xe0.
+             * Here we're processing the second hid_code.  By dropping bit 9
+             * and setting bit 8, the scancode after 0x1d will access the
+             * second half of the table.
+             */
+            hs->kbd.modifiers ^= (1 << 8) | (1 << 9);
             return;
         }
+        /* fall through to process Ctrl_L */
     case 0xe1 ... 0xe7:
+        /* Ctrl_L/Ctrl_R, Shift_L/Shift_R, Alt_L/Alt_R, Win_L/Win_R.
+         * Handle releases here, or fall through to process presses.
+         */
         if (keycode & (1 << 7)) {
             hs->kbd.modifiers &= ~(1 << (hid_code & 0x0f));
             return;
         }
-    case 0xe8 ... 0xef:
+        /* fall through */
+    case 0xe8 ... 0xe9:
+        /* USB modifiers are just 1 byte long.  Bits 8 and 9 of
+         * hs->kbd.modifiers implement a state machine that detects the
+         * 0xe0 and 0xe1/0x1d sequences.  These bits do not follow the
+         * usual rules where bit 7 marks released keys; they are cleared
+         * elsewhere in the function as the state machine dictates.
+         */
         hs->kbd.modifiers |= 1 << (hid_code & 0x0f);
         return;
+
+    case 0xea ... 0xef:
+        abort();
+
+    default:
+        break;
     }
 
     if (keycode & (1 << 7)) {

hw/input/virtio-input-hid.c

@@ -308,6 +308,7 @@ static void virtio_input_hid_handle_status(VirtIOInput *vinput,
 static Property virtio_input_hid_properties[] = {
     DEFINE_PROP_STRING("display", VirtIOInputHID, display),
     DEFINE_PROP_UINT32("head", VirtIOInputHID, head, 0),
+    DEFINE_PROP_END_OF_LIST(),
 };
 
 static void virtio_input_hid_class_init(ObjectClass *klass, void *data)

hw/input/virtio-input-host.c

@@ -11,6 +11,7 @@
 #include "hw/virtio/virtio.h"
 #include "hw/virtio/virtio-input.h"
 
+#include <sys/ioctl.h>
 #include "standard-headers/linux/input.h"
 
 /* ----------------------------------------------------------------- */

hw/input/virtio-input.c

@@ -166,7 +166,8 @@ static void virtio_input_set_config(VirtIODevice *vdev,
     virtio_notify_config(vdev);
 }
 
-static uint64_t virtio_input_get_features(VirtIODevice *vdev, uint64_t f)
+static uint64_t virtio_input_get_features(VirtIODevice *vdev, uint64_t f,
+                                          Error **errp)
 {
     return f;
 }

hw/net/dp8393x.c

@@ -327,9 +327,14 @@ static void dp8393x_do_stop_timer(dp8393xState *s)
     dp8393x_update_wt_regs(s);
 }
 
+static int dp8393x_can_receive(NetClientState *nc);
+
 static void dp8393x_do_receiver_enable(dp8393xState *s)
 {
     s->regs[SONIC_CR] &= ~SONIC_CR_RXDIS;
+    if (dp8393x_can_receive(s->nic->ncs)) {
+        qemu_flush_queued_packets(qemu_get_queue(s->nic));
+    }
 }
 
 static void dp8393x_do_receiver_disable(dp8393xState *s)
@@ -569,6 +574,9 @@ static void dp8393x_write(void *opaque, hwaddr addr, uint64_t data,
                 dp8393x_do_read_rra(s);
             }
             dp8393x_update_irq(s);
+            if (dp8393x_can_receive(s->nic->ncs)) {
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
             break;
         /* Ignore least significant bit */
         case SONIC_RSA:
@@ -635,11 +643,6 @@ static int dp8393x_receive_filter(dp8393xState *s, const uint8_t * buf,
     static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
     int i;
 
-    /* Check for runt packet (remember that checksum is not there) */
-    if (size < 64 - 4) {
-        return (s->regs[SONIC_RCR] & SONIC_RCR_RNT) ? 0 : -1;
-    }
-
     /* Check promiscuous mode */
     if ((s->regs[SONIC_RCR] & SONIC_RCR_PRO) && (buf[0] & 1) == 0) {
         return 0;
@@ -828,6 +831,7 @@ static void dp8393x_realize(DeviceState *dev, Error **errp)
     dp8393xState *s = DP8393X(dev);
     int i, checksum;
     uint8_t *prom;
+    Error *local_err = NULL;
 
     address_space_init(&s->as, s->dma_mr, "dp8393x");
     memory_region_init_io(&s->mmio, OBJECT(dev), &dp8393x_ops, s,
@@ -840,8 +844,13 @@ static void dp8393x_realize(DeviceState *dev, Error **errp)
     s->watchdog = timer_new_ns(QEMU_CLOCK_VIRTUAL, dp8393x_watchdog, s);
     s->regs[SONIC_SR] = 0x0004; /* only revision recognized by Linux */
 
-    memory_region_init_rom_device(&s->prom, OBJECT(dev), NULL, NULL,
-                                  "dp8393x-prom", SONIC_PROM_SIZE, NULL);
+    memory_region_init_ram(&s->prom, OBJECT(dev),
+                           "dp8393x-prom", SONIC_PROM_SIZE, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+    memory_region_set_readonly(&s->prom, true);
     prom = memory_region_get_ram_ptr(&s->prom);
     checksum = 0;
     for (i = 0; i < 6; i++) {
@@ -881,6 +890,8 @@ static void dp8393x_class_init(ObjectClass *klass, void *data)
     dc->reset = dp8393x_reset;
     dc->vmsd = &vmstate_dp8393x;
     dc->props = dp8393x_properties;
+    /* Reason: dma_mr property can't be set */
+    dc->cannot_instantiate_with_device_add_yet = true;
 }
 
 static const TypeInfo dp8393x_info = {

hw/net/eepro100.c

@@ -1617,16 +1617,6 @@ static const MemoryRegionOps eepro100_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static int nic_can_receive(NetClientState *nc)
-{
-    EEPRO100State *s = qemu_get_nic_opaque(nc);
-    TRACE(RXTX, logout("%p\n", s));
-    return get_ru_state(s) == ru_ready;
-#if 0
-    return !eepro100_buffer_full(s);
-#endif
-}
-
 static ssize_t nic_receive(NetClientState *nc, const uint8_t * buf, size_t size)
 {
     /* TODO:
@@ -1844,7 +1834,6 @@ static void pci_nic_uninit(PCIDevice *pci_dev)
 static NetClientInfo net_eepro100_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = nic_can_receive,
     .receive = nic_receive,
 };
 

hw/net/etraxfs_eth.c

@@ -520,11 +520,6 @@ static int eth_match_groupaddr(ETRAXFSEthState *eth, const unsigned char *sa)
     return match;
 }
 
-static int eth_can_receive(NetClientState *nc)
-{
-    return 1;
-}
-
 static ssize_t eth_receive(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     unsigned char sa_bcast[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
@@ -584,7 +579,6 @@ static const MemoryRegionOps eth_ops = {
 static NetClientInfo net_etraxfs_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = eth_can_receive,
     .receive = eth_receive,
     .link_status_changed = eth_set_link,
 };

hw/net/fsl_etsec/etsec.c

@@ -338,25 +338,26 @@ static void etsec_reset(DeviceState *d)
         MII_SR_100X_FD_CAPS     | MII_SR_100T4_CAPS;
 }
 
-static int etsec_can_receive(NetClientState *nc)
-{
-    eTSEC *etsec = qemu_get_nic_opaque(nc);
-
-    return etsec->rx_buffer_len == 0;
-}
-
 static ssize_t etsec_receive(NetClientState *nc,
                              const uint8_t  *buf,
                              size_t          size)
 {
+    ssize_t ret;
     eTSEC *etsec = qemu_get_nic_opaque(nc);
 
 #if defined(HEX_DUMP)
     fprintf(stderr, "%s receive size:%d\n", etsec->nic->nc.name, size);
     qemu_hexdump(buf, stderr, "", size);
 #endif
-    etsec_rx_ring_write(etsec, buf, size);
-    return size;
+    /* Flush is unnecessary as are already in receiving path */
+    etsec->need_flush = false;
+    ret = etsec_rx_ring_write(etsec, buf, size);
+    if (ret == 0) {
+        /* The packet will be queued, let's flush it when buffer is avilable
+         * again. */
+        etsec->need_flush = true;
+    }
+    return ret;
 }
 
 
@@ -370,7 +371,6 @@ static void etsec_set_link_status(NetClientState *nc)
 static NetClientInfo net_etsec_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = etsec_can_receive,
     .receive = etsec_receive,
     .link_status_changed = etsec_set_link_status,
 };

hw/net/fsl_etsec/etsec.h

@@ -144,6 +144,8 @@ typedef struct eTSEC {
     QEMUBH *bh;
     struct ptimer_state *ptimer;
 
+    /* Whether we should flush the rx queue when buffer becomes available. */
+    bool need_flush;
 } eTSEC;
 
 #define TYPE_ETSEC_COMMON "eTSEC"
@@ -162,7 +164,7 @@ DeviceState *etsec_create(hwaddr        base,
 
 void etsec_walk_tx_ring(eTSEC *etsec, int ring_nbr);
 void etsec_walk_rx_ring(eTSEC *etsec, int ring_nbr);
-void etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size);
+ssize_t etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size);
 
 void etsec_write_miim(eTSEC          *etsec,
                       eTSEC_Register *reg,

hw/net/fsl_etsec/rings.c

@@ -481,40 +481,42 @@ static void rx_init_frame(eTSEC *etsec, const uint8_t *buf, size_t size)
                etsec->rx_buffer_len, etsec->rx_padding);
 }
 
-void etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size)
+ssize_t etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size)
 {
     int ring_nbr = 0;           /* Always use ring0 (no filer) */
 
     if (etsec->rx_buffer_len != 0) {
         RING_DEBUG("%s: We can't receive now,"
                    " a buffer is already in the pipe\n", __func__);
-        return;
+        return 0;
     }
 
     if (etsec->regs[RSTAT].value & 1 << (23 - ring_nbr)) {
         RING_DEBUG("%s: The ring is halted\n", __func__);
-        return;
+        return -1;
     }
 
     if (etsec->regs[DMACTRL].value & DMACTRL_GRS) {
         RING_DEBUG("%s: Graceful receive stop\n", __func__);
-        return;
+        return -1;
     }
 
     if (!(etsec->regs[MACCFG1].value & MACCFG1_RX_EN)) {
         RING_DEBUG("%s: MAC Receive not enabled\n", __func__);
-        return;
+        return -1;
     }
 
     if ((etsec->regs[RCTRL].value & RCTRL_RSF) && (size < 60)) {
         /* CRC is not in the packet yet, so short frame is below 60 bytes */
         RING_DEBUG("%s: Drop short frame\n", __func__);
-        return;
+        return -1;
     }
 
     rx_init_frame(etsec, buf, size);
 
     etsec_walk_rx_ring(etsec, ring_nbr);
+
+    return size;
 }
 
 void etsec_walk_rx_ring(eTSEC *etsec, int ring_nbr)
@@ -644,6 +646,9 @@ void etsec_walk_rx_ring(eTSEC *etsec, int ring_nbr)
     } else {
         etsec->rx_buffer_len = 0;
         etsec->rx_buffer     = NULL;
+        if (etsec->need_flush) {
+            qemu_flush_queued_packets(qemu_get_queue(etsec->nic));
+        }
     }
 
     RING_DEBUG("eTSEC End of ring_write: remaining_data:%zu\n", remaining_data);

hw/net/lan9118.c

@@ -461,11 +461,6 @@ static void lan9118_reset(DeviceState *d)
     lan9118_reload_eeprom(s);
 }
 
-static int lan9118_can_receive(NetClientState *nc)
-{
-    return 1;
-}
-
 static void rx_fifo_push(lan9118_state *s, uint32_t val)
 {
     int fifo_pos;
@@ -1312,7 +1307,6 @@ static const MemoryRegionOps lan9118_16bit_mem_ops = {
 static NetClientInfo net_lan9118_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = lan9118_can_receive,
     .receive = lan9118_receive,
     .link_status_changed = lan9118_set_link,
 };

hw/net/lance.c

@@ -94,7 +94,6 @@ static const MemoryRegionOps lance_mem_ops = {
 static NetClientInfo net_lance_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = pcnet_can_receive,
     .receive = pcnet_receive,
     .link_status_changed = pcnet_set_link_status,
 };

hw/net/mcf_fec.c

@@ -8,6 +8,7 @@
 #include "hw/hw.h"
 #include "net/net.h"
 #include "hw/m68k/mcf.h"
+#include "hw/net/mii.h"
 /* For crc32 */
 #include <zlib.h>
 #include "exec/address-spaces.h"
@@ -195,12 +196,14 @@ static void mcf_fec_do_tx(mcf_fec_state *s)
 
 static void mcf_fec_enable_rx(mcf_fec_state *s)
 {
+    NetClientState *nc = qemu_get_queue(s->nic);
     mcf_fec_bd bd;
 
     mcf_fec_read_bd(&bd, s->rx_descriptor);
     s->rx_enabled = ((bd.flags & FEC_BD_E) != 0);
-    if (!s->rx_enabled)
-        DPRINTF("RX buffer full\n");
+    if (s->rx_enabled) {
+        qemu_flush_queued_packets(nc);
+    }
 }
 
 static void mcf_fec_reset(mcf_fec_state *s)
@@ -216,6 +219,51 @@ static void mcf_fec_reset(mcf_fec_state *s)
     s->rfsr = 0x500;
 }
 
+#define MMFR_WRITE_OP	(1 << 28)
+#define MMFR_READ_OP	(2 << 28)
+#define MMFR_PHYADDR(v)	(((v) >> 23) & 0x1f)
+#define MMFR_REGNUM(v)	(((v) >> 18) & 0x1f)
+
+static uint64_t mcf_fec_read_mdio(mcf_fec_state *s)
+{
+    uint64_t v;
+
+    if (s->mmfr & MMFR_WRITE_OP)
+        return s->mmfr;
+    if (MMFR_PHYADDR(s->mmfr) != 1)
+        return s->mmfr |= 0xffff;
+
+    switch (MMFR_REGNUM(s->mmfr)) {
+    case MII_BMCR:
+        v = MII_BMCR_SPEED | MII_BMCR_AUTOEN | MII_BMCR_FD;
+        break;
+    case MII_BMSR:
+        v = MII_BMSR_100TX_FD | MII_BMSR_100TX_HD | MII_BMSR_10T_FD |
+            MII_BMSR_10T_HD | MII_BMSR_MFPS | MII_BMSR_AN_COMP |
+            MII_BMSR_AUTONEG | MII_BMSR_LINK_ST;
+        break;
+    case MII_PHYID1:
+        v = DP83848_PHYID1;
+        break;
+    case MII_PHYID2:
+        v = DP83848_PHYID2;
+        break;
+    case MII_ANAR:
+        v = MII_ANAR_TXFD | MII_ANAR_TX | MII_ANAR_10FD |
+            MII_ANAR_10 | MII_ANAR_CSMACD;
+        break;
+    case MII_ANLPAR:
+        v = MII_ANLPAR_ACK | MII_ANLPAR_TXFD | MII_ANLPAR_TX |
+            MII_ANLPAR_10FD | MII_ANLPAR_10 | MII_ANLPAR_CSMACD;
+        break;
+    default:
+        v = 0xffff;
+        break;
+    }
+    s->mmfr = (s->mmfr & ~0xffff) | v;
+    return s->mmfr;
+}
+
 static uint64_t mcf_fec_read(void *opaque, hwaddr addr,
                              unsigned size)
 {
@@ -226,7 +274,7 @@ static uint64_t mcf_fec_read(void *opaque, hwaddr addr,
     case 0x010: return s->rx_enabled ? (1 << 24) : 0; /* RDAR */
     case 0x014: return 0; /* TDAR */
     case 0x024: return s->ecr;
-    case 0x040: return s->mmfr;
+    case 0x040: return mcf_fec_read_mdio(s);
     case 0x044: return s->mscr;
     case 0x064: return 0; /* MIBC */
     case 0x084: return s->rcr;
@@ -287,8 +335,8 @@ static void mcf_fec_write(void *opaque, hwaddr addr,
         }
         break;
     case 0x040:
-        /* TODO: Implement MII.  */
         s->mmfr = value;
+        s->eir |= FEC_INT_MII;
         break;
     case 0x044:
         s->mscr = value & 0xfe;
@@ -351,10 +399,30 @@ static void mcf_fec_write(void *opaque, hwaddr addr,
     mcf_fec_update(s);
 }
 
-static int mcf_fec_can_receive(NetClientState *nc)
+static int mcf_fec_have_receive_space(mcf_fec_state *s, size_t want)
 {
-    mcf_fec_state *s = qemu_get_nic_opaque(nc);
-    return s->rx_enabled;
+    mcf_fec_bd bd;
+    uint32_t addr;
+
+    /* Walk descriptor list to determine if we have enough buffer */
+    addr = s->rx_descriptor;
+    while (want > 0) {
+        mcf_fec_read_bd(&bd, addr);
+        if ((bd.flags & FEC_BD_E) == 0) {
+            return 0;
+        }
+        if (want < s->emrbr) {
+            return 1;
+        }
+        want -= s->emrbr;
+        /* Advance to the next descriptor.  */
+        if ((bd.flags & FEC_BD_W) != 0) {
+            addr = s->erdsr;
+        } else {
+            addr += 8;
+        }
+    }
+    return 0;
 }
 
 static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t size)
@@ -367,10 +435,11 @@ static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t si
     uint32_t buf_addr;
     uint8_t *crc_ptr;
     unsigned int buf_len;
+    size_t retsize;
 
     DPRINTF("do_rx len %d\n", size);
     if (!s->rx_enabled) {
-        fprintf(stderr, "mcf_fec_receive: Unexpected packet\n");
+        return -1;
     }
     /* 4 bytes for the CRC.  */
     size += 4;
@@ -385,17 +454,14 @@ static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t si
     if (size > (s->rcr >> 16)) {
         flags |= FEC_BD_LG;
     }
+    /* Check if we have enough space in current descriptors */
+    if (!mcf_fec_have_receive_space(s, size)) {
+        return 0;
+    }
     addr = s->rx_descriptor;
+    retsize = size;
     while (size > 0) {
         mcf_fec_read_bd(&bd, addr);
-        if ((bd.flags & FEC_BD_E) == 0) {
-            /* No descriptors available.  Bail out.  */
-            /* FIXME: This is wrong.  We should probably either save the
-               remainder for when more RX buffers are available, or
-               flag an error.  */
-            fprintf(stderr, "mcf_fec: Lost end of frame\n");
-            break;
-        }
         buf_len = (size <= s->emrbr) ? size: s->emrbr;
         bd.length = buf_len;
         size -= buf_len;
@@ -430,7 +496,7 @@ static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t si
     s->rx_descriptor = addr;
     mcf_fec_enable_rx(s);
     mcf_fec_update(s);
-    return size;
+    return retsize;
 }
 
 static const MemoryRegionOps mcf_fec_ops = {
@@ -442,7 +508,6 @@ static const MemoryRegionOps mcf_fec_ops = {
 static NetClientInfo net_mcf_fec_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = mcf_fec_can_receive,
     .receive = mcf_fec_receive,
 };
 

hw/net/milkymist-minimac2.c

@@ -303,8 +303,7 @@ static ssize_t minimac2_rx(NetClientState *nc, const uint8_t *buf, size_t size)
         r_state = R_STATE1;
         rx_buf = s->rx1_buf;
     } else {
-        trace_milkymist_minimac2_drop_rx_frame(buf);
-        return size;
+        return 0;
     }
 
     /* assemble frame */
@@ -354,6 +353,18 @@ minimac2_read(void *opaque, hwaddr addr, unsigned size)
     return r;
 }
 
+static int minimac2_can_rx(MilkymistMinimac2State *s)
+{
+    if (s->regs[R_STATE0] == STATE_LOADED) {
+        return 1;
+    }
+    if (s->regs[R_STATE1] == STATE_LOADED) {
+        return 1;
+    }
+
+    return 0;
+}
+
 static void
 minimac2_write(void *opaque, hwaddr addr, uint64_t value,
                unsigned size)
@@ -387,6 +398,9 @@ minimac2_write(void *opaque, hwaddr addr, uint64_t value,
     case R_STATE1:
         s->regs[addr] = value;
         update_rx_interrupt(s);
+        if (minimac2_can_rx(s)) {
+            qemu_flush_queued_packets(qemu_get_queue(s->nic));
+        }
         break;
     case R_SETUP:
     case R_COUNT0:
@@ -411,20 +425,6 @@ static const MemoryRegionOps minimac2_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
-static int minimac2_can_rx(NetClientState *nc)
-{
-    MilkymistMinimac2State *s = qemu_get_nic_opaque(nc);
-
-    if (s->regs[R_STATE0] == STATE_LOADED) {
-        return 1;
-    }
-    if (s->regs[R_STATE1] == STATE_LOADED) {
-        return 1;
-    }
-
-    return 0;
-}
-
 static void milkymist_minimac2_reset(DeviceState *d)
 {
     MilkymistMinimac2State *s = MILKYMIST_MINIMAC2(d);
@@ -445,7 +445,6 @@ static void milkymist_minimac2_reset(DeviceState *d)
 static NetClientInfo net_milkymist_minimac2_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = minimac2_can_rx,
     .receive = minimac2_rx,
 };
 

hw/net/mipsnet.c

@@ -80,7 +80,7 @@ static ssize_t mipsnet_receive(NetClientState *nc, const uint8_t *buf, size_t si
 
     trace_mipsnet_receive(size);
     if (!mipsnet_can_receive(nc))
-        return -1;
+        return 0;
 
     s->busy = 1;
 
@@ -134,6 +134,9 @@ static uint64_t mipsnet_ioport_read(void *opaque, hwaddr addr,
         if (s->rx_count) {
             s->rx_count--;
             ret = s->rx_buffer[s->rx_read++];
+            if (mipsnet_can_receive(s->nic->ncs)) {
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
         }
         break;
     /* Reads as zero. */
@@ -170,6 +173,9 @@ static void mipsnet_ioport_write(void *opaque, hwaddr addr,
         }
         s->busy = !!s->intctl;
         mipsnet_update_irq(s);
+        if (mipsnet_can_receive(s->nic->ncs)) {
+            qemu_flush_queued_packets(qemu_get_queue(s->nic));
+        }
         break;
     case MIPSNET_TX_DATA_BUFFER:
         s->tx_buffer[s->tx_written++] = val;
@@ -214,7 +220,6 @@ static const VMStateDescription vmstate_mipsnet = {
 static NetClientInfo net_mipsnet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = mipsnet_can_receive,
     .receive = mipsnet_receive,
 };
 

hw/net/pcnet-pci.c

@@ -273,7 +273,6 @@ static void pci_pcnet_uninit(PCIDevice *dev)
 static NetClientInfo net_pci_pcnet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = pcnet_can_receive,
     .receive = pcnet_receive,
     .link_status_changed = pcnet_set_link_status,
 };

hw/net/pcnet.c

@@ -995,15 +995,6 @@ static int pcnet_tdte_poll(PCNetState *s)
     return !!(CSR_CXST(s) & 0x8000);
 }
 
-int pcnet_can_receive(NetClientState *nc)
-{
-    PCNetState *s = qemu_get_nic_opaque(nc);
-    if (CSR_STOP(s) || CSR_SPND(s))
-        return 0;
-
-    return sizeof(s->buffer)-16;
-}
-
 #define MIN_BUF_SIZE 60
 
 ssize_t pcnet_receive(NetClientState *nc, const uint8_t *buf, size_t size_)

hw/net/pcnet.h

@@ -60,7 +60,6 @@ uint32_t pcnet_ioport_readw(void *opaque, uint32_t addr);
 void pcnet_ioport_writel(void *opaque, uint32_t addr, uint32_t val);
 uint32_t pcnet_ioport_readl(void *opaque, uint32_t addr);
 uint32_t pcnet_bcr_readw(PCNetState *s, uint32_t rap);
-int pcnet_can_receive(NetClientState *nc);
 ssize_t pcnet_receive(NetClientState *nc, const uint8_t *buf, size_t size_);
 void pcnet_set_link_status(NetClientState *nc);
 void pcnet_common_init(DeviceState *dev, PCNetState *s, NetClientInfo *info);

hw/net/rtl8139.c

@@ -2150,6 +2150,11 @@ static int rtl8139_cplus_transmit_one(RTL8139State *s)
         {
             DPRINTF("+++ C+ mode offloaded task checksum\n");
 
+            /* Large enough for Ethernet and IP headers? */
+            if (saved_size < ETH_HLEN + sizeof(ip_header)) {
+                goto skip_offload;
+            }
+
             /* ip packet header */
             ip_header *ip = NULL;
             int hlen = 0;
@@ -2160,223 +2165,235 @@ static int rtl8139_cplus_transmit_one(RTL8139State *s)
             size_t   eth_payload_len  = 0;
 
             int proto = be16_to_cpu(*(uint16_t *)(saved_buffer + 12));
-            if (proto == ETH_P_IP)
+            if (proto != ETH_P_IP)
             {
-                DPRINTF("+++ C+ mode has IP packet\n");
-
-                /* not aligned */
-                eth_payload_data = saved_buffer + ETH_HLEN;
-                eth_payload_len  = saved_size   - ETH_HLEN;
-
-                ip = (ip_header*)eth_payload_data;
-
-                if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
-                    DPRINTF("+++ C+ mode packet has bad IP version %d "
-                        "expected %d\n", IP_HEADER_VERSION(ip),
-                        IP_HEADER_VERSION_4);
-                    ip = NULL;
-                } else {
-                    hlen = IP_HEADER_LENGTH(ip);
-                    ip_protocol = ip->ip_p;
-                    ip_data_len = be16_to_cpu(ip->ip_len) - hlen;
-                }
+                goto skip_offload;
             }
 
-            if (ip)
+            DPRINTF("+++ C+ mode has IP packet\n");
+
+            /* not aligned */
+            eth_payload_data = saved_buffer + ETH_HLEN;
+            eth_payload_len  = saved_size   - ETH_HLEN;
+
+            ip = (ip_header*)eth_payload_data;
+
+            if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
+                DPRINTF("+++ C+ mode packet has bad IP version %d "
+                    "expected %d\n", IP_HEADER_VERSION(ip),
+                    IP_HEADER_VERSION_4);
+                goto skip_offload;
+            }
+
+            hlen = IP_HEADER_LENGTH(ip);
+            if (hlen < sizeof(ip_header) || hlen > eth_payload_len) {
+                goto skip_offload;
+            }
+
+            ip_protocol = ip->ip_p;
+
+            ip_data_len = be16_to_cpu(ip->ip_len);
+            if (ip_data_len < hlen || ip_data_len > eth_payload_len) {
+                goto skip_offload;
+            }
+            ip_data_len -= hlen;
+
+            if (txdw0 & CP_TX_IPCS)
             {
-                if (txdw0 & CP_TX_IPCS)
-                {
-                    DPRINTF("+++ C+ mode need IP checksum\n");
+                DPRINTF("+++ C+ mode need IP checksum\n");
 
-                    if (hlen<sizeof(ip_header) || hlen>eth_payload_len) {/* min header length */
-                        /* bad packet header len */
-                        /* or packet too short */
-                    }
-                    else
-                    {
-                        ip->ip_sum = 0;
-                        ip->ip_sum = ip_checksum(ip, hlen);
-                        DPRINTF("+++ C+ mode IP header len=%d checksum=%04x\n",
-                            hlen, ip->ip_sum);
-                    }
+                ip->ip_sum = 0;
+                ip->ip_sum = ip_checksum(ip, hlen);
+                DPRINTF("+++ C+ mode IP header len=%d checksum=%04x\n",
+                    hlen, ip->ip_sum);
+            }
+
+            if ((txdw0 & CP_TX_LGSEN) && ip_protocol == IP_PROTO_TCP)
+            {
+                /* Large enough for the TCP header? */
+                if (ip_data_len < sizeof(tcp_header)) {
+                    goto skip_offload;
                 }
 
-                if ((txdw0 & CP_TX_LGSEN) && ip_protocol == IP_PROTO_TCP)
+                int large_send_mss = (txdw0 >> 16) & CP_TC_LGSEN_MSS_MASK;
+
+                DPRINTF("+++ C+ mode offloaded task TSO MTU=%d IP data %d "
+                    "frame data %d specified MSS=%d\n", ETH_MTU,
+                    ip_data_len, saved_size - ETH_HLEN, large_send_mss);
+
+                int tcp_send_offset = 0;
+                int send_count = 0;
+
+                /* maximum IP header length is 60 bytes */
+                uint8_t saved_ip_header[60];
+
+                /* save IP header template; data area is used in tcp checksum calculation */
+                memcpy(saved_ip_header, eth_payload_data, hlen);
+
+                /* a placeholder for checksum calculation routine in tcp case */
+                uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
+                //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
+
+                /* pointer to TCP header */
+                tcp_header *p_tcp_hdr = (tcp_header*)(eth_payload_data + hlen);
+
+                int tcp_hlen = TCP_HEADER_DATA_OFFSET(p_tcp_hdr);
+
+                /* Invalid TCP data offset? */
+                if (tcp_hlen < sizeof(tcp_header) || tcp_hlen > ip_data_len) {
+                    goto skip_offload;
+                }
+
+                /* ETH_MTU = ip header len + tcp header len + payload */
+                int tcp_data_len = ip_data_len - tcp_hlen;
+                int tcp_chunk_size = ETH_MTU - hlen - tcp_hlen;
+
+                DPRINTF("+++ C+ mode TSO IP data len %d TCP hlen %d TCP "
+                    "data len %d TCP chunk size %d\n", ip_data_len,
+                    tcp_hlen, tcp_data_len, tcp_chunk_size);
+
+                /* note the cycle below overwrites IP header data,
+                   but restores it from saved_ip_header before sending packet */
+
+                int is_last_frame = 0;
+
+                for (tcp_send_offset = 0; tcp_send_offset < tcp_data_len; tcp_send_offset += tcp_chunk_size)
                 {
-                    int large_send_mss = (txdw0 >> 16) & CP_TC_LGSEN_MSS_MASK;
+                    uint16_t chunk_size = tcp_chunk_size;
 
-                    DPRINTF("+++ C+ mode offloaded task TSO MTU=%d IP data %d "
-                        "frame data %d specified MSS=%d\n", ETH_MTU,
-                        ip_data_len, saved_size - ETH_HLEN, large_send_mss);
-
-                    int tcp_send_offset = 0;
-                    int send_count = 0;
-
-                    /* maximum IP header length is 60 bytes */
-                    uint8_t saved_ip_header[60];
-
-                    /* save IP header template; data area is used in tcp checksum calculation */
-                    memcpy(saved_ip_header, eth_payload_data, hlen);
-
-                    /* a placeholder for checksum calculation routine in tcp case */
-                    uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
-                    //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
-
-                    /* pointer to TCP header */
-                    tcp_header *p_tcp_hdr = (tcp_header*)(eth_payload_data + hlen);
-
-                    int tcp_hlen = TCP_HEADER_DATA_OFFSET(p_tcp_hdr);
-
-                    /* ETH_MTU = ip header len + tcp header len + payload */
-                    int tcp_data_len = ip_data_len - tcp_hlen;
-                    int tcp_chunk_size = ETH_MTU - hlen - tcp_hlen;
-
-                    DPRINTF("+++ C+ mode TSO IP data len %d TCP hlen %d TCP "
-                        "data len %d TCP chunk size %d\n", ip_data_len,
-                        tcp_hlen, tcp_data_len, tcp_chunk_size);
-
-                    /* note the cycle below overwrites IP header data,
-                       but restores it from saved_ip_header before sending packet */
-
-                    int is_last_frame = 0;
-
-                    for (tcp_send_offset = 0; tcp_send_offset < tcp_data_len; tcp_send_offset += tcp_chunk_size)
+                    /* check if this is the last frame */
+                    if (tcp_send_offset + tcp_chunk_size >= tcp_data_len)
                     {
-                        uint16_t chunk_size = tcp_chunk_size;
-
-                        /* check if this is the last frame */
-                        if (tcp_send_offset + tcp_chunk_size >= tcp_data_len)
-                        {
-                            is_last_frame = 1;
-                            chunk_size = tcp_data_len - tcp_send_offset;
-                        }
-
-                        DPRINTF("+++ C+ mode TSO TCP seqno %08x\n",
-                            be32_to_cpu(p_tcp_hdr->th_seq));
-
-                        /* add 4 TCP pseudoheader fields */
-                        /* copy IP source and destination fields */
-                        memcpy(data_to_checksum, saved_ip_header + 12, 8);
-
-                        DPRINTF("+++ C+ mode TSO calculating TCP checksum for "
-                            "packet with %d bytes data\n", tcp_hlen +
-                            chunk_size);
-
-                        if (tcp_send_offset)
-                        {
-                            memcpy((uint8_t*)p_tcp_hdr + tcp_hlen, (uint8_t*)p_tcp_hdr + tcp_hlen + tcp_send_offset, chunk_size);
-                        }
-
-                        /* keep PUSH and FIN flags only for the last frame */
-                        if (!is_last_frame)
-                        {
-                            TCP_HEADER_CLEAR_FLAGS(p_tcp_hdr, TCP_FLAG_PUSH|TCP_FLAG_FIN);
-                        }
-
-                        /* recalculate TCP checksum */
-                        ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
-                        p_tcpip_hdr->zeros      = 0;
-                        p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
-                        p_tcpip_hdr->ip_payload = cpu_to_be16(tcp_hlen + chunk_size);
-
-                        p_tcp_hdr->th_sum = 0;
-
-                        int tcp_checksum = ip_checksum(data_to_checksum, tcp_hlen + chunk_size + 12);
-                        DPRINTF("+++ C+ mode TSO TCP checksum %04x\n",
-                            tcp_checksum);
-
-                        p_tcp_hdr->th_sum = tcp_checksum;
-
-                        /* restore IP header */
-                        memcpy(eth_payload_data, saved_ip_header, hlen);
-
-                        /* set IP data length and recalculate IP checksum */
-                        ip->ip_len = cpu_to_be16(hlen + tcp_hlen + chunk_size);
-
-                        /* increment IP id for subsequent frames */
-                        ip->ip_id = cpu_to_be16(tcp_send_offset/tcp_chunk_size + be16_to_cpu(ip->ip_id));
-
-                        ip->ip_sum = 0;
-                        ip->ip_sum = ip_checksum(eth_payload_data, hlen);
-                        DPRINTF("+++ C+ mode TSO IP header len=%d "
-                            "checksum=%04x\n", hlen, ip->ip_sum);
-
-                        int tso_send_size = ETH_HLEN + hlen + tcp_hlen + chunk_size;
-                        DPRINTF("+++ C+ mode TSO transferring packet size "
-                            "%d\n", tso_send_size);
-                        rtl8139_transfer_frame(s, saved_buffer, tso_send_size,
-                            0, (uint8_t *) dot1q_buffer);
-
-                        /* add transferred count to TCP sequence number */
-                        p_tcp_hdr->th_seq = cpu_to_be32(chunk_size + be32_to_cpu(p_tcp_hdr->th_seq));
-                        ++send_count;
+                        is_last_frame = 1;
+                        chunk_size = tcp_data_len - tcp_send_offset;
                     }
 
-                    /* Stop sending this frame */
-                    saved_size = 0;
-                }
-                else if (txdw0 & (CP_TX_TCPCS|CP_TX_UDPCS))
-                {
-                    DPRINTF("+++ C+ mode need TCP or UDP checksum\n");
-
-                    /* maximum IP header length is 60 bytes */
-                    uint8_t saved_ip_header[60];
-                    memcpy(saved_ip_header, eth_payload_data, hlen);
-
-                    uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
-                    //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
+                    DPRINTF("+++ C+ mode TSO TCP seqno %08x\n",
+                        be32_to_cpu(p_tcp_hdr->th_seq));
 
                     /* add 4 TCP pseudoheader fields */
                     /* copy IP source and destination fields */
                     memcpy(data_to_checksum, saved_ip_header + 12, 8);
 
-                    if ((txdw0 & CP_TX_TCPCS) && ip_protocol == IP_PROTO_TCP)
+                    DPRINTF("+++ C+ mode TSO calculating TCP checksum for "
+                        "packet with %d bytes data\n", tcp_hlen +
+                        chunk_size);
+
+                    if (tcp_send_offset)
                     {
-                        DPRINTF("+++ C+ mode calculating TCP checksum for "
-                            "packet with %d bytes data\n", ip_data_len);
-
-                        ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
-                        p_tcpip_hdr->zeros      = 0;
-                        p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
-                        p_tcpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
-
-                        tcp_header* p_tcp_hdr = (tcp_header *) (data_to_checksum+12);
-
-                        p_tcp_hdr->th_sum = 0;
-
-                        int tcp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
-                        DPRINTF("+++ C+ mode TCP checksum %04x\n",
-                            tcp_checksum);
-
-                        p_tcp_hdr->th_sum = tcp_checksum;
+                        memcpy((uint8_t*)p_tcp_hdr + tcp_hlen, (uint8_t*)p_tcp_hdr + tcp_hlen + tcp_send_offset, chunk_size);
                     }
-                    else if ((txdw0 & CP_TX_UDPCS) && ip_protocol == IP_PROTO_UDP)
+
+                    /* keep PUSH and FIN flags only for the last frame */
+                    if (!is_last_frame)
                     {
-                        DPRINTF("+++ C+ mode calculating UDP checksum for "
-                            "packet with %d bytes data\n", ip_data_len);
-
-                        ip_pseudo_header *p_udpip_hdr = (ip_pseudo_header *)data_to_checksum;
-                        p_udpip_hdr->zeros      = 0;
-                        p_udpip_hdr->ip_proto   = IP_PROTO_UDP;
-                        p_udpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
-
-                        udp_header *p_udp_hdr = (udp_header *) (data_to_checksum+12);
-
-                        p_udp_hdr->uh_sum = 0;
-
-                        int udp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
-                        DPRINTF("+++ C+ mode UDP checksum %04x\n",
-                            udp_checksum);
-
-                        p_udp_hdr->uh_sum = udp_checksum;
+                        TCP_HEADER_CLEAR_FLAGS(p_tcp_hdr, TCP_FLAG_PUSH|TCP_FLAG_FIN);
                     }
 
+                    /* recalculate TCP checksum */
+                    ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
+                    p_tcpip_hdr->zeros      = 0;
+                    p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
+                    p_tcpip_hdr->ip_payload = cpu_to_be16(tcp_hlen + chunk_size);
+
+                    p_tcp_hdr->th_sum = 0;
+
+                    int tcp_checksum = ip_checksum(data_to_checksum, tcp_hlen + chunk_size + 12);
+                    DPRINTF("+++ C+ mode TSO TCP checksum %04x\n",
+                        tcp_checksum);
+
+                    p_tcp_hdr->th_sum = tcp_checksum;
+
                     /* restore IP header */
                     memcpy(eth_payload_data, saved_ip_header, hlen);
+
+                    /* set IP data length and recalculate IP checksum */
+                    ip->ip_len = cpu_to_be16(hlen + tcp_hlen + chunk_size);
+
+                    /* increment IP id for subsequent frames */
+                    ip->ip_id = cpu_to_be16(tcp_send_offset/tcp_chunk_size + be16_to_cpu(ip->ip_id));
+
+                    ip->ip_sum = 0;
+                    ip->ip_sum = ip_checksum(eth_payload_data, hlen);
+                    DPRINTF("+++ C+ mode TSO IP header len=%d "
+                        "checksum=%04x\n", hlen, ip->ip_sum);
+
+                    int tso_send_size = ETH_HLEN + hlen + tcp_hlen + chunk_size;
+                    DPRINTF("+++ C+ mode TSO transferring packet size "
+                        "%d\n", tso_send_size);
+                    rtl8139_transfer_frame(s, saved_buffer, tso_send_size,
+                        0, (uint8_t *) dot1q_buffer);
+
+                    /* add transferred count to TCP sequence number */
+                    p_tcp_hdr->th_seq = cpu_to_be32(chunk_size + be32_to_cpu(p_tcp_hdr->th_seq));
+                    ++send_count;
                 }
+
+                /* Stop sending this frame */
+                saved_size = 0;
+            }
+            else if (txdw0 & (CP_TX_TCPCS|CP_TX_UDPCS))
+            {
+                DPRINTF("+++ C+ mode need TCP or UDP checksum\n");
+
+                /* maximum IP header length is 60 bytes */
+                uint8_t saved_ip_header[60];
+                memcpy(saved_ip_header, eth_payload_data, hlen);
+
+                uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
+                //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
+
+                /* add 4 TCP pseudoheader fields */
+                /* copy IP source and destination fields */
+                memcpy(data_to_checksum, saved_ip_header + 12, 8);
+
+                if ((txdw0 & CP_TX_TCPCS) && ip_protocol == IP_PROTO_TCP)
+                {
+                    DPRINTF("+++ C+ mode calculating TCP checksum for "
+                        "packet with %d bytes data\n", ip_data_len);
+
+                    ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
+                    p_tcpip_hdr->zeros      = 0;
+                    p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
+                    p_tcpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
+
+                    tcp_header* p_tcp_hdr = (tcp_header *) (data_to_checksum+12);
+
+                    p_tcp_hdr->th_sum = 0;
+
+                    int tcp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
+                    DPRINTF("+++ C+ mode TCP checksum %04x\n",
+                        tcp_checksum);
+
+                    p_tcp_hdr->th_sum = tcp_checksum;
+                }
+                else if ((txdw0 & CP_TX_UDPCS) && ip_protocol == IP_PROTO_UDP)
+                {
+                    DPRINTF("+++ C+ mode calculating UDP checksum for "
+                        "packet with %d bytes data\n", ip_data_len);
+
+                    ip_pseudo_header *p_udpip_hdr = (ip_pseudo_header *)data_to_checksum;
+                    p_udpip_hdr->zeros      = 0;
+                    p_udpip_hdr->ip_proto   = IP_PROTO_UDP;
+                    p_udpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
+
+                    udp_header *p_udp_hdr = (udp_header *) (data_to_checksum+12);
+
+                    p_udp_hdr->uh_sum = 0;
+
+                    int udp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
+                    DPRINTF("+++ C+ mode UDP checksum %04x\n",
+                        udp_checksum);
+
+                    p_udp_hdr->uh_sum = udp_checksum;
+                }
+
+                /* restore IP header */
+                memcpy(eth_payload_data, saved_ip_header, hlen);
             }
         }
 
+skip_offload:
         /* update tally counter */
         ++s->tally_counters.TxOk;
 

hw/net/stellaris_enet.c

@@ -228,8 +228,7 @@ static ssize_t stellaris_enet_receive(NetClientState *nc, const uint8_t *buf, si
     if ((s->rctl & SE_RCTL_RXEN) == 0)
         return -1;
     if (s->np >= 31) {
-        DPRINTF("Packet dropped\n");
-        return -1;
+        return 0;
     }
 
     DPRINTF("Received packet len=%zu\n", size);
@@ -260,13 +259,8 @@ static ssize_t stellaris_enet_receive(NetClientState *nc, const uint8_t *buf, si
     return size;
 }
 
-static int stellaris_enet_can_receive(NetClientState *nc)
+static int stellaris_enet_can_receive(stellaris_enet_state *s)
 {
-    stellaris_enet_state *s = qemu_get_nic_opaque(nc);
-
-    if ((s->rctl & SE_RCTL_RXEN) == 0)
-        return 1;
-
     return (s->np < 31);
 }
 
@@ -307,6 +301,9 @@ static uint64_t stellaris_enet_read(void *opaque, hwaddr offset,
                 s->next_packet = 0;
             s->np--;
             DPRINTF("RX done np=%d\n", s->np);
+            if (!s->np && stellaris_enet_can_receive(s)) {
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
         }
         return val;
     }
@@ -454,7 +451,6 @@ static void stellaris_enet_reset(stellaris_enet_state *s)
 static NetClientInfo net_stellaris_enet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = stellaris_enet_can_receive,
     .receive = stellaris_enet_receive,
 };
 

hw/net/vhost_net.c

@@ -160,7 +160,6 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options)
 
     net->dev.nvqs = 2;
     net->dev.vqs = net->vqs;
-    net->dev.vq_index = net->nc->queue_index;
 
     r = vhost_dev_init(&net->dev, options->opaque,
                        options->backend_type);
@@ -287,7 +286,7 @@ static void vhost_net_stop_one(struct vhost_net *net,
         for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
             const VhostOps *vhost_ops = net->dev.vhost_ops;
             int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_OWNER,
-                                          &file);
+                                          NULL);
             assert(r >= 0);
         }
     }

hw/net/virtio-net.c

@@ -162,6 +162,8 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
     virtio_net_vhost_status(n, status);
 
     for (i = 0; i < n->max_queues; i++) {
+        NetClientState *ncs = qemu_get_subqueue(n->nic, i);
+        bool queue_started;
         q = &n->vqs[i];
 
         if ((!n->multiqueue && i != 0) || i >= n->curr_queues) {
@@ -169,12 +171,18 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
         } else {
             queue_status = status;
         }
+        queue_started =
+            virtio_net_started(n, queue_status) && !n->vhost_started;
+
+        if (queue_started) {
+            qemu_flush_queued_packets(ncs);
+        }
 
         if (!q->tx_waiting) {
             continue;
         }
 
-        if (virtio_net_started(n, queue_status) && !n->vhost_started) {
+        if (queue_started) {
             if (q->tx_timer) {
                 timer_mod(q->tx_timer,
                                qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout);
@@ -438,7 +446,8 @@ static void virtio_net_set_queues(VirtIONet *n)
 
 static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue);
 
-static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features,
+                                        Error **errp)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
     NetClientState *nc = qemu_get_queue(n->nic);
@@ -466,7 +475,6 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features)
     }
 
     if (!get_vhost_net(nc->peer)) {
-        virtio_add_feature(&features, VIRTIO_F_VERSION_1);
         return features;
     }
     return vhost_net_get_features(get_vhost_net(nc->peer), features);
@@ -1143,7 +1151,8 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         ssize_t ret, len;
         unsigned int out_num = elem.out_num;
         struct iovec *out_sg = &elem.out_sg[0];
-        struct iovec sg[VIRTQUEUE_MAX_SIZE];
+        struct iovec sg[VIRTQUEUE_MAX_SIZE], sg2[VIRTQUEUE_MAX_SIZE + 1];
+        struct virtio_net_hdr_mrg_rxbuf mhdr;
 
         if (out_num < 1) {
             error_report("virtio-net header not in first element");
@@ -1151,13 +1160,25 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         }
 
         if (n->has_vnet_hdr) {
-            if (out_sg[0].iov_len < n->guest_hdr_len) {
+            if (iov_to_buf(out_sg, out_num, 0, &mhdr, n->guest_hdr_len) <
+                n->guest_hdr_len) {
                 error_report("virtio-net header incorrect");
                 exit(1);
             }
-            virtio_net_hdr_swap(vdev, (void *) out_sg[0].iov_base);
+            if (virtio_needs_swap(vdev)) {
+                virtio_net_hdr_swap(vdev, (void *) &mhdr);
+                sg2[0].iov_base = &mhdr;
+                sg2[0].iov_len = n->guest_hdr_len;
+                out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1,
+                                   out_sg, out_num,
+                                   n->guest_hdr_len, -1);
+                if (out_num == VIRTQUEUE_MAX_SIZE) {
+                    goto drop;
+		}
+                out_num += 1;
+                out_sg = sg2;
+	    }
         }
-
         /*
          * If host wants to see the guest header as is, we can
          * pass it on unchanged. Otherwise, copy just the parts
@@ -1187,7 +1208,7 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         }
 
         len += ret;
-
+drop:
         virtqueue_push(q->tx_vq, &elem, 0);
         virtio_notify(vdev, q->tx_vq);
 
@@ -1307,9 +1328,86 @@ static void virtio_net_tx_bh(void *opaque)
     }
 }
 
+static void virtio_net_add_queue(VirtIONet *n, int index)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+
+    n->vqs[index].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
+    if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
+        n->vqs[index].tx_vq =
+            virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
+        n->vqs[index].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                              virtio_net_tx_timer,
+                                              &n->vqs[index]);
+    } else {
+        n->vqs[index].tx_vq =
+            virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
+        n->vqs[index].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[index]);
+    }
+
+    n->vqs[index].tx_waiting = 0;
+    n->vqs[index].n = n;
+}
+
+static void virtio_net_del_queue(VirtIONet *n, int index)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+    VirtIONetQueue *q = &n->vqs[index];
+    NetClientState *nc = qemu_get_subqueue(n->nic, index);
+
+    qemu_purge_queued_packets(nc);
+
+    virtio_del_queue(vdev, index * 2);
+    if (q->tx_timer) {
+        timer_del(q->tx_timer);
+        timer_free(q->tx_timer);
+    } else {
+        qemu_bh_delete(q->tx_bh);
+    }
+    virtio_del_queue(vdev, index * 2 + 1);
+}
+
+static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+    int old_num_queues = virtio_get_num_queues(vdev);
+    int new_num_queues = new_max_queues * 2 + 1;
+    int i;
+
+    assert(old_num_queues >= 3);
+    assert(old_num_queues % 2 == 1);
+
+    if (old_num_queues == new_num_queues) {
+        return;
+    }
+
+    /*
+     * We always need to remove and add ctrl vq if
+     * old_num_queues != new_num_queues. Remove ctrl_vq first,
+     * and then we only enter one of the following too loops.
+     */
+    virtio_del_queue(vdev, old_num_queues - 1);
+
+    for (i = new_num_queues - 1; i < old_num_queues - 1; i += 2) {
+        /* new_num_queues < old_num_queues */
+        virtio_net_del_queue(n, i / 2);
+    }
+
+    for (i = old_num_queues - 1; i < new_num_queues - 1; i += 2) {
+        /* new_num_queues > old_num_queues */
+        virtio_net_add_queue(n, i / 2);
+    }
+
+    /* add ctrl_vq last */
+    n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
+}
+
 static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue)
 {
+    int max = multiqueue ? n->max_queues : 1;
+
     n->multiqueue = multiqueue;
+    virtio_net_change_num_queues(n, max);
 
     virtio_net_set_queues(n);
 }
@@ -1584,21 +1682,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     }
 
     for (i = 0; i < n->max_queues; i++) {
-        n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
-        if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
-            n->vqs[i].tx_vq =
-                virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
-            n->vqs[i].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                                              virtio_net_tx_timer,
-                                              &n->vqs[i]);
-        } else {
-            n->vqs[i].tx_vq =
-                virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
-            n->vqs[i].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[i]);
-        }
-
-        n->vqs[i].tx_waiting = 0;
-        n->vqs[i].n = n;
+        virtio_net_add_queue(n, i);
     }
 
     n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
@@ -1652,7 +1736,7 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIONet *n = VIRTIO_NET(dev);
-    int i;
+    int i, max_queues;
 
     /* This will stop vhost backend if appropriate. */
     virtio_net_set_status(vdev, 0);
@@ -1667,18 +1751,9 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
     g_free(n->mac_table.macs);
     g_free(n->vlans);
 
-    for (i = 0; i < n->max_queues; i++) {
-        VirtIONetQueue *q = &n->vqs[i];
-        NetClientState *nc = qemu_get_subqueue(n->nic, i);
-
-        qemu_purge_queued_packets(nc);
-
-        if (q->tx_timer) {
-            timer_del(q->tx_timer);
-            timer_free(q->tx_timer);
-        } else if (q->tx_bh) {
-            qemu_bh_delete(q->tx_bh);
-        }
+    max_queues = n->multiqueue ? n->max_queues : 1;
+    for (i = 0; i < max_queues; i++) {
+        virtio_net_del_queue(n, i);
     }
 
     timer_del(n->announce_timer);
@@ -1703,8 +1778,6 @@ static void virtio_net_instance_init(Object *obj)
 }
 
 static Property virtio_net_properties[] = {
-    DEFINE_PROP_BIT("any_layout", VirtIONet, host_features,
-                    VIRTIO_F_ANY_LAYOUT, true),
     DEFINE_PROP_BIT("csum", VirtIONet, host_features, VIRTIO_NET_F_CSUM, true),
     DEFINE_PROP_BIT("guest_csum", VirtIONet, host_features,
                     VIRTIO_NET_F_GUEST_CSUM, true),

hw/net/vmxnet3.c

@@ -885,6 +885,63 @@ vmxnet3_get_next_rx_descr(VMXNET3State *s, bool is_head,
     }
 }
 
+/* In case packet was csum offloaded (either NEEDS_CSUM or DATA_VALID),
+ * the implementation always passes an RxCompDesc with a "Checksum
+ * calculated and found correct" to the OS (cnc=0 and tuc=1, see
+ * vmxnet3_rx_update_descr). This emulates the observed ESXi behavior.
+ *
+ * Therefore, if packet has the NEEDS_CSUM set, we must calculate
+ * and place a fully computed checksum into the tcp/udp header.
+ * Otherwise, the OS driver will receive a checksum-correct indication
+ * (CHECKSUM_UNNECESSARY), but with the actual tcp/udp checksum field
+ * having just the pseudo header csum value.
+ *
+ * While this is not a problem if packet is destined for local delivery,
+ * in the case the host OS performs forwarding, it will forward an
+ * incorrectly checksummed packet.
+ */
+static void vmxnet3_rx_need_csum_calculate(struct VmxnetRxPkt *pkt,
+                                           const void *pkt_data,
+                                           size_t pkt_len)
+{
+    struct virtio_net_hdr *vhdr;
+    bool isip4, isip6, istcp, isudp;
+    uint8_t *data;
+    int len;
+
+    if (!vmxnet_rx_pkt_has_virt_hdr(pkt)) {
+        return;
+    }
+
+    vhdr = vmxnet_rx_pkt_get_vhdr(pkt);
+    if (!VMXNET_FLAG_IS_SET(vhdr->flags, VIRTIO_NET_HDR_F_NEEDS_CSUM)) {
+        return;
+    }
+
+    vmxnet_rx_pkt_get_protocols(pkt, &isip4, &isip6, &isudp, &istcp);
+    if (!(isip4 || isip6) || !(istcp || isudp)) {
+        return;
+    }
+
+    vmxnet3_dump_virt_hdr(vhdr);
+
+    /* Validate packet len: csum_start + scum_offset + length of csum field */
+    if (pkt_len < (vhdr->csum_start + vhdr->csum_offset + 2)) {
+        VMW_PKPRN("packet len:%d < csum_start(%d) + csum_offset(%d) + 2, "
+                  "cannot calculate checksum",
+                  len, vhdr->csum_start, vhdr->csum_offset);
+        return;
+    }
+
+    data = (uint8_t *)pkt_data + vhdr->csum_start;
+    len = pkt_len - vhdr->csum_start;
+    /* Put the checksum obtained into the packet */
+    stw_be_p(data + vhdr->csum_offset, net_raw_checksum(data, len));
+
+    vhdr->flags &= ~VIRTIO_NET_HDR_F_NEEDS_CSUM;
+    vhdr->flags |= VIRTIO_NET_HDR_F_DATA_VALID;
+}
+
 static void vmxnet3_rx_update_descr(struct VmxnetRxPkt *pkt,
     struct Vmxnet3_RxCompDesc *rxcd)
 {
@@ -1897,6 +1954,8 @@ vmxnet3_receive(NetClientState *nc, const uint8_t *buf, size_t size)
         get_eth_packet_type(PKT_GET_ETH_HDR(buf)));
 
     if (vmxnet3_rx_filter_may_indicate(s, buf, size)) {
+        vmxnet_rx_pkt_set_protocols(s->rx_pkt, buf, size);
+        vmxnet3_rx_need_csum_calculate(s->rx_pkt, buf, size);
         vmxnet_rx_pkt_attach_data(s->rx_pkt, buf, size, s->rx_vlan_stripping);
         bytes_indicated = vmxnet3_indicate_packet(s) ? size : -1;
         if (bytes_indicated < size) {

hw/net/vmxnet_rx_pkt.c

@@ -92,9 +92,6 @@ void vmxnet_rx_pkt_attach_data(struct VmxnetRxPkt *pkt, const void *data,
     }
 
     pkt->tci = tci;
-
-    eth_get_protocols(data, len, &pkt->isip4, &pkt->isip6,
-        &pkt->isudp, &pkt->istcp);
 }
 
 void vmxnet_rx_pkt_dump(struct VmxnetRxPkt *pkt)
@@ -131,6 +128,15 @@ size_t vmxnet_rx_pkt_get_total_len(struct VmxnetRxPkt *pkt)
     return pkt->tot_len;
 }
 
+void vmxnet_rx_pkt_set_protocols(struct VmxnetRxPkt *pkt, const void *data,
+                                 size_t len)
+{
+    assert(pkt);
+
+    eth_get_protocols(data, len, &pkt->isip4, &pkt->isip6,
+        &pkt->isudp, &pkt->istcp);
+}
+
 void vmxnet_rx_pkt_get_protocols(struct VmxnetRxPkt *pkt,
                                  bool *isip4, bool *isip6,
                                  bool *isudp, bool *istcp)

hw/net/vmxnet_rx_pkt.h

@@ -54,6 +54,17 @@ void vmxnet_rx_pkt_init(struct VmxnetRxPkt **pkt, bool has_virt_hdr);
  */
 size_t vmxnet_rx_pkt_get_total_len(struct VmxnetRxPkt *pkt);
 
+/**
+ * parse and set packet analysis results
+ *
+ * @pkt:            packet
+ * @data:           pointer to the data buffer to be parsed
+ * @len:            data length
+ *
+ */
+void vmxnet_rx_pkt_set_protocols(struct VmxnetRxPkt *pkt, const void *data,
+                                 size_t len);
+
 /**
  * fetches packet analysis results
  *

hw/net/xen_nic.c

@@ -234,27 +234,6 @@ static void net_rx_response(struct XenNetDev *netdev,
 
 #define NET_IP_ALIGN 2
 
-static int net_rx_ok(NetClientState *nc)
-{
-    struct XenNetDev *netdev = qemu_get_nic_opaque(nc);
-    RING_IDX rc, rp;
-
-    if (netdev->xendev.be_state != XenbusStateConnected) {
-        return 0;
-    }
-
-    rc = netdev->rx_ring.req_cons;
-    rp = netdev->rx_ring.sring->req_prod;
-    xen_rmb();
-
-    if (rc == rp || RING_REQUEST_CONS_OVERFLOW(&netdev->rx_ring, rc)) {
-        xen_be_printf(&netdev->xendev, 2, "%s: no rx buffers (%d/%d)\n",
-                      __FUNCTION__, rc, rp);
-        return 0;
-    }
-    return 1;
-}
-
 static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     struct XenNetDev *netdev = qemu_get_nic_opaque(nc);
@@ -271,8 +250,7 @@ static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size
     xen_rmb(); /* Ensure we see queued requests up to 'rp'. */
 
     if (rc == rp || RING_REQUEST_CONS_OVERFLOW(&netdev->rx_ring, rc)) {
-        xen_be_printf(&netdev->xendev, 2, "no buffer, drop packet\n");
-        return -1;
+        return 0;
     }
     if (size > XC_PAGE_SIZE - NET_IP_ALIGN) {
         xen_be_printf(&netdev->xendev, 0, "packet too big (%lu > %ld)",
@@ -304,7 +282,6 @@ static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size
 static NetClientInfo net_xen_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = net_rx_ok,
     .receive = net_rx_packet,
 };
 

hw/net/xgmac.c

@@ -312,10 +312,8 @@ static const MemoryRegionOps enet_mem_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static int eth_can_rx(NetClientState *nc)
+static int eth_can_rx(XgmacState *s)
 {
-    XgmacState *s = qemu_get_nic_opaque(nc);
-
     /* RX enabled?  */
     return s->regs[DMA_CONTROL] & DMA_CONTROL_SR;
 }
@@ -329,6 +327,9 @@ static ssize_t eth_rx(NetClientState *nc, const uint8_t *buf, size_t size)
     struct desc bd;
     ssize_t ret;
 
+    if (!eth_can_rx(s)) {
+        return -1;
+    }
     unicast = ~buf[0] & 0x1;
     broadcast = memcmp(buf, sa_bcast, 6) == 0;
     multicast = !unicast && !broadcast;
@@ -371,7 +372,6 @@ out:
 static NetClientInfo net_xgmac_enet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = eth_can_rx,
     .receive = eth_rx,
 };
 

hw/net/xilinx_axienet.c

@@ -401,6 +401,9 @@ struct XilinxAXIEnet {
 
     uint8_t rxapp[CONTROL_PAYLOAD_SIZE];
     uint32_t rxappsize;
+
+    /* Whether axienet_eth_rx_notify should flush incoming queue. */
+    bool need_flush;
 };
 
 static void axienet_rx_reset(XilinxAXIEnet *s)
@@ -658,10 +661,8 @@ static const MemoryRegionOps enet_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static int eth_can_rx(NetClientState *nc)
+static int eth_can_rx(XilinxAXIEnet *s)
 {
-    XilinxAXIEnet *s = qemu_get_nic_opaque(nc);
-
     /* RX enabled?  */
     return !s->rxsize && !axienet_rx_resetting(s) && axienet_rx_enabled(s);
 }
@@ -701,6 +702,10 @@ static void axienet_eth_rx_notify(void *opaque)
         s->rxpos += ret;
         if (!s->rxsize) {
             s->regs[R_IS] |= IS_RX_COMPLETE;
+            if (s->need_flush) {
+                s->need_flush = false;
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
         }
     }
     enet_update_irq(s);
@@ -721,6 +726,11 @@ static ssize_t eth_rx(NetClientState *nc, const uint8_t *buf, size_t size)
 
     DENET(qemu_log("%s: %zd bytes\n", __func__, size));
 
+    if (!eth_can_rx(s)) {
+        s->need_flush = true;
+        return 0;
+    }
+
     unicast = ~buf[0] & 0x1;
     broadcast = memcmp(buf, sa_bcast, 6) == 0;
     multicast = !unicast && !broadcast;
@@ -925,7 +935,6 @@ xilinx_axienet_data_stream_push(StreamSlave *obj, uint8_t *buf, size_t size)
 static NetClientInfo net_xilinx_enet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = eth_can_rx,
     .receive = eth_rx,
 };
 

hw/pci/pci.c

@@ -2101,12 +2101,10 @@ static void pci_del_option_rom(PCIDevice *pdev)
 }
 
 /*
- * if !offset
- * Reserve space and add capability to the linked list in pci config space
- *
  * if offset = 0,
  * Find and reserve space and add capability to the linked list
- * in pci config space */
+ * in pci config space
+ */
 int pci_add_capability(PCIDevice *pdev, uint8_t cap_id,
                        uint8_t offset, uint8_t size)
 {

hw/ppc/ppc.c

@@ -873,8 +873,9 @@ static int timebase_post_load(void *opaque, int version_id)
      */
     host_ns = qemu_clock_get_ns(QEMU_CLOCK_HOST);
     ns_diff = MAX(0, host_ns - tb_remote->time_of_the_day_ns);
-    migration_duration_ns = MIN(NSEC_PER_SEC, ns_diff);
-    migration_duration_tb = muldiv64(migration_duration_ns, freq, NSEC_PER_SEC);
+    migration_duration_ns = MIN(NANOSECONDS_PER_SECOND, ns_diff);
+    migration_duration_tb = muldiv64(migration_duration_ns, freq,
+                                     NANOSECONDS_PER_SECOND);
     guest_tb = tb_remote->guest_timebase + MIN(0, migration_duration_tb);
 
     tb_off_adj = guest_tb - cpu_get_real_ticks();

hw/ppc/spapr_drc.c

@@ -422,6 +422,7 @@ static void realize(DeviceState *d, Error **errp)
         error_free(err);
         object_unref(OBJECT(drc));
     }
+    g_free(child_name);
     DPRINTFN("drc realize complete");
 }
 

hw/ppc/spapr_rtc.c

@@ -51,7 +51,7 @@ void spapr_rtc_read(DeviceState *dev, struct tm *tm, uint32_t *ns)
     assert(rtc);
 
     guest_ns = host_ns + rtc->ns_offset;
-    guest_s = guest_ns / NSEC_PER_SEC;
+    guest_s = guest_ns / NANOSECONDS_PER_SECOND;
 
     if (tm) {
         gmtime_r(&guest_s, tm);
@@ -71,7 +71,7 @@ int spapr_rtc_import_offset(DeviceState *dev, int64_t legacy_offset)
 
     rtc = SPAPR_RTC(dev);
 
-    rtc->ns_offset = legacy_offset * NSEC_PER_SEC;
+    rtc->ns_offset = legacy_offset * NANOSECONDS_PER_SECOND;
 
     return 0;
 }
@@ -146,7 +146,7 @@ static void rtas_set_time_of_day(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 
     host_ns = qemu_clock_get_ns(rtc_clock);
 
-    rtc->ns_offset = (new_s * NSEC_PER_SEC) - host_ns;
+    rtc->ns_offset = (new_s * NANOSECONDS_PER_SECOND) - host_ns;
 
     rtas_st(rets, 0, RTAS_OUT_SUCCESS);
 }
@@ -168,7 +168,7 @@ static void spapr_rtc_realize(DeviceState *dev, Error **errp)
     qemu_get_timedate(&tm, 0);
     host_s = mktimegm(&tm);
     rtc_ns = qemu_clock_get_ns(rtc_clock);
-    rtc->ns_offset = host_s * NSEC_PER_SEC - rtc_ns;
+    rtc->ns_offset = host_s * NANOSECONDS_PER_SECOND - rtc_ns;
 
     object_property_add_tm(OBJECT(rtc), "date", spapr_rtc_qom_date, NULL);
 }

hw/s390x/s390-virtio-ccw.c

@@ -36,7 +36,7 @@ typedef struct S390CcwMachineState {
 
 void io_subsystem_reset(void)
 {
-    DeviceState *css, *sclp, *flic;
+    DeviceState *css, *sclp, *flic, *diag288;
 
     css = DEVICE(object_resolve_path_type("", "virtual-css-bridge", NULL));
     if (css) {
@@ -51,6 +51,10 @@ void io_subsystem_reset(void)
     if (flic) {
         qdev_reset_all(flic);
     }
+    diag288 = DEVICE(object_resolve_path_type("", "diag288", NULL));
+    if (diag288) {
+        qdev_reset_all(diag288);
+    }
 }
 
 static int virtio_ccw_hcall_notify(const uint64_t *args)

hw/s390x/virtio-ccw.c

@@ -1508,12 +1508,12 @@ static int virtio_ccw_load_config(DeviceState *d, QEMUFile *f)
     qemu_get_be16s(f, &vdev->config_vector);
     dev->routes.adapter.ind_offset = qemu_get_be64(f);
     dev->thinint_isc = qemu_get_byte(f);
+    dev->revision = qemu_get_be32(f);
     if (s->thinint_active) {
         return css_register_io_adapter(CSS_IO_ADAPTER_VIRTIO,
                                        dev->thinint_isc, true, false,
                                        &dev->routes.adapter.adapter_id);
     }
-    dev->revision = qemu_get_be32(f);
 
     return 0;
 }

hw/scsi/megasas.c

@@ -2202,8 +2202,15 @@ static uint64_t megasas_queue_read(void *opaque, hwaddr addr,
     return 0;
 }
 
+static void megasas_queue_write(void *opaque, hwaddr addr,
+                               uint64_t val, unsigned size)
+{
+    return;
+}
+
 static const MemoryRegionOps megasas_queue_ops = {
     .read = megasas_queue_read,
+    .write = megasas_queue_write,
     .endianness = DEVICE_LITTLE_ENDIAN,
     .impl = {
         .min_access_size = 8,

hw/scsi/scsi-bus.c

@@ -1239,10 +1239,15 @@ int scsi_cdb_length(uint8_t *buf) {
 int scsi_req_parse_cdb(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf)
 {
     int rc;
+    int len;
 
     cmd->lba = -1;
-    cmd->len = scsi_cdb_length(buf);
+    len = scsi_cdb_length(buf);
+    if (len < 0) {
+        return -1;
+    }
 
+    cmd->len = len;
     switch (dev->type) {
     case TYPE_TAPE:
         rc = scsi_req_stream_xfer(cmd, dev, buf);

hw/scsi/scsi-disk.c

@@ -765,6 +765,9 @@ static inline bool media_is_dvd(SCSIDiskState *s)
     if (!blk_is_inserted(s->qdev.conf.blk)) {
         return false;
     }
+    if (s->tray_open) {
+        return false;
+    }
     blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
     return nb_sectors > CD_MAX_SECTORS;
 }
@@ -778,6 +781,9 @@ static inline bool media_is_cd(SCSIDiskState *s)
     if (!blk_is_inserted(s->qdev.conf.blk)) {
         return false;
     }
+    if (s->tray_open) {
+        return false;
+    }
     blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
     return nb_sectors <= CD_MAX_SECTORS;
 }
@@ -975,7 +981,15 @@ static int scsi_get_configuration(SCSIDiskState *s, uint8_t *outbuf)
     if (s->qdev.type != TYPE_ROM) {
         return -1;
     }
-    current = media_is_dvd(s) ? MMC_PROFILE_DVD_ROM : MMC_PROFILE_CD_ROM;
+
+    if (media_is_dvd(s)) {
+        current = MMC_PROFILE_DVD_ROM;
+    } else if (media_is_cd(s)) {
+        current = MMC_PROFILE_CD_ROM;
+    } else {
+        current = MMC_PROFILE_NONE;
+    }
+
     memset(outbuf, 0, 40);
     stl_be_p(&outbuf[0], 36); /* Bytes after the data length field */
     stw_be_p(&outbuf[6], current);

hw/scsi/vhost-scsi.c

@@ -153,7 +153,8 @@ static void vhost_scsi_stop(VHostSCSI *s)
 }
 
 static uint64_t vhost_scsi_get_features(VirtIODevice *vdev,
-                                        uint64_t features)
+                                        uint64_t features,
+                                        Error **errp)
 {
     VHostSCSI *s = VHOST_SCSI(vdev);
 

hw/scsi/virtio-scsi.c

@@ -629,7 +629,8 @@ static void virtio_scsi_set_config(VirtIODevice *vdev,
 }
 
 static uint64_t virtio_scsi_get_features(VirtIODevice *vdev,
-                                         uint64_t requested_features)
+                                         uint64_t requested_features,
+                                         Error **errp)
 {
     VirtIOSCSI *s = VIRTIO_SCSI(vdev);
 
@@ -953,8 +954,6 @@ static Property virtio_scsi_properties[] = {
                                                   0xFFFF),
     DEFINE_PROP_UINT32("cmd_per_lun", VirtIOSCSI, parent_obj.conf.cmd_per_lun,
                                                   128),
-    DEFINE_PROP_BIT("any_layout", VirtIOSCSI, host_features,
-                                              VIRTIO_F_ANY_LAYOUT, true),
     DEFINE_PROP_BIT("hotplug", VirtIOSCSI, host_features,
                                            VIRTIO_SCSI_F_HOTPLUG, true),
     DEFINE_PROP_BIT("param_change", VirtIOSCSI, host_features,