Update version for v2.4.0-rc2 release

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

VERSION

@@ -1 +1 @@
-2.3.90
+2.3.92

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

@@ -184,6 +184,8 @@ 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 +202,9 @@ 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;
@@ -254,24 +259,22 @@ 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);
     }
 }
 
@@ -286,6 +289,10 @@ static void aio_rfifolock_cb(void *opaque)
     aio_notify(opaque);
 }
 
+static void event_notifier_dummy_cb(EventNotifier *e)
+{
+}
+
 AioContext *aio_context_new(Error **errp)
 {
     int ret;
@@ -300,7 +307,7 @@ 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);

block/mirror.c

@@ -388,7 +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
@@ -442,7 +442,6 @@ 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);
@@ -450,7 +449,9 @@ static void coroutine_fn mirror_run(void *opaque)
         /* 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;
+            /* 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) {
@@ -462,8 +463,7 @@ static void coroutine_fn mirror_run(void *opaque)
                 goto immediate_exit;
             }
 
-            ret = bdrv_is_allocated_above(bs, base,
-                                          sector_num, next - sector_num, &n);
+            ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n);
 
             if (ret < 0) {
                 goto immediate_exit;
@@ -472,10 +472,8 @@ 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;
         }
     }
 

configure

@@ -2183,6 +2183,7 @@ 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 +4491,7 @@ 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      $curl"
@@ -4858,6 +4859,7 @@ if test "$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

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;

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_;
 };
 

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
 -------------
 

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
     }

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/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/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/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/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/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);
@@ -1142,7 +1150,8 @@ 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");
@@ -1150,13 +1159,25 @@ 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
@@ -1186,7 +1207,7 @@ 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);
 
@@ -1306,9 +1327,86 @@ 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);
 }
@@ -1583,21 +1681,7 @@ 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);
@@ -1651,7 +1735,7 @@ 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);
@@ -1666,18 +1750,9 @@ 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);

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/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/timer/mc146818rtc.c

@@ -56,7 +56,7 @@
 
 #define RTC_REINJECT_ON_ACK_COUNT 20
 #define RTC_CLOCK_RATE            32768
-#define UIP_HOLD_LENGTH           (8 * NSEC_PER_SEC / 32768)
+#define UIP_HOLD_LENGTH           (8 * NANOSECONDS_PER_SECOND / 32768)
 
 #define MC146818_RTC(obj) OBJECT_CHECK(RTCState, (obj), TYPE_MC146818_RTC)
 
@@ -105,7 +105,7 @@ static uint64_t get_guest_rtc_ns(RTCState *s)
     uint64_t guest_rtc;
     uint64_t guest_clock = qemu_clock_get_ns(rtc_clock);
 
-    guest_rtc = s->base_rtc * NSEC_PER_SEC
+    guest_rtc = s->base_rtc * NANOSECONDS_PER_SECOND
                  + guest_clock - s->last_update + s->offset;
     return guest_rtc;
 }
@@ -231,16 +231,17 @@ static void check_update_timer(RTCState *s)
         return;
     }
 
-    guest_nsec = get_guest_rtc_ns(s) % NSEC_PER_SEC;
+    guest_nsec = get_guest_rtc_ns(s) % NANOSECONDS_PER_SECOND;
     /* if UF is clear, reprogram to next second */
     next_update_time = qemu_clock_get_ns(rtc_clock)
-        + NSEC_PER_SEC - guest_nsec;
+        + NANOSECONDS_PER_SECOND - guest_nsec;
 
     /* Compute time of next alarm.  One second is already accounted
      * for in next_update_time.
      */
     next_alarm_sec = get_next_alarm(s);
-    s->next_alarm_time = next_update_time + (next_alarm_sec - 1) * NSEC_PER_SEC;
+    s->next_alarm_time = next_update_time +
+                         (next_alarm_sec - 1) * NANOSECONDS_PER_SECOND;
 
     if (s->cmos_data[RTC_REG_C] & REG_C_UF) {
         /* UF is set, but AF is clear.  Program the timer to target
@@ -456,7 +457,7 @@ static void cmos_ioport_write(void *opaque, hwaddr addr,
                 /* if disabling set mode, update the time */
                 if ((s->cmos_data[RTC_REG_B] & REG_B_SET) &&
                     (s->cmos_data[RTC_REG_A] & 0x70) <= 0x20) {
-                    s->offset = get_guest_rtc_ns(s) % NSEC_PER_SEC;
+                    s->offset = get_guest_rtc_ns(s) % NANOSECONDS_PER_SECOND;
                     rtc_set_time(s);
                 }
             }
@@ -580,7 +581,7 @@ static void rtc_update_time(RTCState *s)
     int64_t guest_nsec;
 
     guest_nsec = get_guest_rtc_ns(s);
-    guest_sec = guest_nsec / NSEC_PER_SEC;
+    guest_sec = guest_nsec / NANOSECONDS_PER_SECOND;
     gmtime_r(&guest_sec, &ret);
 
     /* Is SET flag of Register B disabled? */
@@ -608,7 +609,8 @@ static int update_in_progress(RTCState *s)
 
     guest_nsec = get_guest_rtc_ns(s);
     /* UIP bit will be set at last 244us of every second. */
-    if ((guest_nsec % NSEC_PER_SEC) >= (NSEC_PER_SEC - UIP_HOLD_LENGTH)) {
+    if ((guest_nsec % NANOSECONDS_PER_SECOND) >=
+        (NANOSECONDS_PER_SECOND - UIP_HOLD_LENGTH)) {
         return 1;
     }
     return 0;

hw/usb/dev-smartcard-reader.c

@@ -283,6 +283,7 @@ typedef struct CCIDBus {
 typedef struct USBCCIDState {
     USBDevice dev;
     USBEndpoint *intr;
+    USBEndpoint *bulk;
     CCIDBus bus;
     CCIDCardState *card;
     BulkIn bulk_in_pending[BULK_IN_PENDING_NUM]; /* circular */
@@ -769,6 +770,7 @@ static void ccid_write_slot_status(USBCCIDState *s, CCID_Header *recv)
     h->b.bError = s->bError;
     h->bClockStatus = CLOCK_STATUS_RUNNING;
     ccid_reset_error_status(s);
+    usb_wakeup(s->bulk, 0);
 }
 
 static void ccid_write_parameters(USBCCIDState *s, CCID_Header *recv)
@@ -789,6 +791,7 @@ static void ccid_write_parameters(USBCCIDState *s, CCID_Header *recv)
     h->bProtocolNum = s->bProtocolNum;
     h->abProtocolDataStructure = s->abProtocolDataStructure;
     ccid_reset_error_status(s);
+    usb_wakeup(s->bulk, 0);
 }
 
 static void ccid_write_data_block(USBCCIDState *s, uint8_t slot, uint8_t seq,
@@ -810,6 +813,7 @@ static void ccid_write_data_block(USBCCIDState *s, uint8_t slot, uint8_t seq,
     }
     memcpy(p->abData, data, len);
     ccid_reset_error_status(s);
+    usb_wakeup(s->bulk, 0);
 }
 
 static void ccid_report_error_failed(USBCCIDState *s, uint8_t error)
@@ -1184,7 +1188,7 @@ void ccid_card_send_apdu_to_guest(CCIDCardState *card,
                                   uint8_t *apdu, uint32_t len)
 {
     DeviceState *qdev = DEVICE(card);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
     Answer *answer;
 
@@ -1207,7 +1211,7 @@ void ccid_card_send_apdu_to_guest(CCIDCardState *card,
 void ccid_card_card_removed(CCIDCardState *card)
 {
     DeviceState *qdev = DEVICE(card);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
 
     ccid_on_slot_change(s, false);
@@ -1218,7 +1222,7 @@ void ccid_card_card_removed(CCIDCardState *card)
 int ccid_card_ccid_attach(CCIDCardState *card)
 {
     DeviceState *qdev = DEVICE(card);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
 
     DPRINTF(s, 1, "CCID Attach\n");
@@ -1231,7 +1235,7 @@ int ccid_card_ccid_attach(CCIDCardState *card)
 void ccid_card_ccid_detach(CCIDCardState *card)
 {
     DeviceState *qdev = DEVICE(card);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
 
     DPRINTF(s, 1, "CCID Detach\n");
@@ -1244,7 +1248,7 @@ void ccid_card_ccid_detach(CCIDCardState *card)
 void ccid_card_card_error(CCIDCardState *card, uint64_t error)
 {
     DeviceState *qdev = DEVICE(card);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
 
     s->bmCommandStatus = COMMAND_STATUS_FAILED;
@@ -1263,7 +1267,7 @@ void ccid_card_card_error(CCIDCardState *card, uint64_t error)
 void ccid_card_card_inserted(CCIDCardState *card)
 {
     DeviceState *qdev = DEVICE(card);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
 
     s->bmCommandStatus = COMMAND_STATUS_NO_ERROR;
@@ -1275,7 +1279,7 @@ static int ccid_card_exit(DeviceState *qdev)
 {
     int ret = 0;
     CCIDCardState *card = CCID_CARD(qdev);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
 
     if (ccid_card_inserted(s)) {
@@ -1289,7 +1293,7 @@ static int ccid_card_exit(DeviceState *qdev)
 static int ccid_card_init(DeviceState *qdev)
 {
     CCIDCardState *card = CCID_CARD(qdev);
-    USBDevice *dev = USB_DEVICE(qdev);
+    USBDevice *dev = USB_DEVICE(qdev->parent_bus->parent);
     USBCCIDState *s = USB_CCID_DEV(dev);
     int ret = 0;
 
@@ -1319,6 +1323,7 @@ static void ccid_realize(USBDevice *dev, Error **errp)
                         NULL);
     qbus_set_hotplug_handler(BUS(&s->bus), DEVICE(dev), &error_abort);
     s->intr = usb_ep_get(dev, USB_TOKEN_IN, CCID_INT_IN_EP);
+    s->bulk = usb_ep_get(dev, USB_TOKEN_IN, CCID_BULK_IN_EP);
     s->card = NULL;
     s->migration_state = MIGRATION_NONE;
     s->migration_target_ip = 0;

hw/usb/hcd-ehci.c

@@ -32,7 +32,7 @@
 #include "trace.h"
 
 #define FRAME_TIMER_FREQ 1000
-#define FRAME_TIMER_NS   (NSEC_PER_SEC / FRAME_TIMER_FREQ)
+#define FRAME_TIMER_NS   (NANOSECONDS_PER_SECOND / FRAME_TIMER_FREQ)
 #define UFRAME_TIMER_NS  (FRAME_TIMER_NS / 8)
 
 #define NB_MAXINTRATE    8        // Max rate at which controller issues ints

hw/usb/hcd-xhci.c

@@ -2222,8 +2222,6 @@ static void xhci_kick_ep(XHCIState *xhci, unsigned int slotid,
         if (xfer->running_retry) {
             DPRINTF("xhci: xfer nacked, stopping schedule\n");
             epctx->retry = xfer;
-            timer_mod(epctx->kick_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                      epctx->interval * 125000);
             break;
         }
     }

hw/usb/host-libusb.c

@@ -889,6 +889,9 @@ static int usb_host_open(USBHostDevice *s, libusb_device *dev)
 fail:
     trace_usb_host_open_failure(bus_num, addr);
     if (s->dh != NULL) {
+        usb_host_release_interfaces(s);
+        libusb_reset_device(s->dh);
+        usb_host_attach_kernel(s);
         libusb_close(s->dh);
         s->dh = NULL;
         s->dev = NULL;

hw/virtio/vhost-user.c

@@ -210,12 +210,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
         break;
 
     case VHOST_SET_OWNER:
-        break;
-
     case VHOST_RESET_OWNER:
-        memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
-        msg.state.index += dev->vq_index;
-        msg.size = sizeof(m.state);
         break;
 
     case VHOST_SET_MEM_TABLE:
@@ -258,20 +253,17 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
     case VHOST_SET_VRING_NUM:
     case VHOST_SET_VRING_BASE:
         memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
-        msg.state.index += dev->vq_index;
         msg.size = sizeof(m.state);
         break;
 
     case VHOST_GET_VRING_BASE:
         memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
-        msg.state.index += dev->vq_index;
         msg.size = sizeof(m.state);
         need_reply = 1;
         break;
 
     case VHOST_SET_VRING_ADDR:
         memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr));
-        msg.addr.index += dev->vq_index;
         msg.size = sizeof(m.addr);
         break;
 
@@ -279,7 +271,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
     case VHOST_SET_VRING_CALL:
     case VHOST_SET_VRING_ERR:
         file = arg;
-        msg.u64 = (file->index + dev->vq_index) & VHOST_USER_VRING_IDX_MASK;
+        msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
         msg.size = sizeof(m.u64);
         if (ioeventfd_enabled() && file->fd > 0) {
             fds[fd_num++] = file->fd;
@@ -321,7 +313,6 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
                 error_report("Received bad msg size.");
                 return -1;
             }
-            msg.state.index -= dev->vq_index;
             memcpy(arg, &msg.state, sizeof(struct vhost_vring_state));
             break;
         default:

hw/virtio/virtio-rng.c

@@ -77,6 +77,12 @@ static void virtio_rng_process(VirtIORNG *vrng)
         return;
     }
 
+    if (vrng->activate_timer) {
+        timer_mod(vrng->rate_limit_timer,
+                  qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vrng->conf.period_ms);
+        vrng->activate_timer = false;
+    }
+
     if (vrng->quota_remaining < 0) {
         quota = 0;
     } else {
@@ -138,8 +144,7 @@ static void check_rate_limit(void *opaque)
 
     vrng->quota_remaining = vrng->conf.max_bytes;
     virtio_rng_process(vrng);
-    timer_mod(vrng->rate_limit_timer,
-                   qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vrng->conf.period_ms);
+    vrng->activate_timer = true;
 }
 
 static void virtio_rng_device_realize(DeviceState *dev, Error **errp)
@@ -195,13 +200,9 @@ static void virtio_rng_device_realize(DeviceState *dev, Error **errp)
 
     vrng->vq = virtio_add_queue(vdev, 8, handle_input);
     vrng->quota_remaining = vrng->conf.max_bytes;
-
     vrng->rate_limit_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
                                                check_rate_limit, vrng);
-
-    timer_mod(vrng->rate_limit_timer,
-                   qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vrng->conf.period_ms);
-
+    vrng->activate_timer = true;
     register_savevm(dev, "virtio-rng", -1, 1, virtio_rng_save,
                     virtio_rng_load, vrng);
 }

include/block/aio.h

@@ -63,10 +63,30 @@ struct AioContext {
      */
     int walking_handlers;
 
-    /* Used to avoid unnecessary event_notifier_set calls in aio_notify.
-     * Writes protected by lock or BQL, reads are lockless.
+    /* Used to avoid unnecessary event_notifier_set calls in aio_notify;
+     * accessed with atomic primitives.  If this field is 0, everything
+     * (file descriptors, bottom halves, timers) will be re-evaluated
+     * before the next blocking poll(), thus the event_notifier_set call
+     * can be skipped.  If it is non-zero, you may need to wake up a
+     * concurrent aio_poll or the glib main event loop, making
+     * event_notifier_set necessary.
+     *
+     * Bit 0 is reserved for GSource usage of the AioContext, and is 1
+     * between a call to aio_ctx_check and the next call to aio_ctx_dispatch.
+     * Bits 1-31 simply count the number of active calls to aio_poll
+     * that are in the prepare or poll phase.
+     *
+     * The GSource and aio_poll must use a different mechanism because
+     * there is no certainty that a call to GSource's prepare callback
+     * (via g_main_context_prepare) is indeed followed by check and
+     * dispatch.  It's not clear whether this would be a bug, but let's
+     * play safe and allow it---it will just cause extra calls to
+     * event_notifier_set until the next call to dispatch.
+     *
+     * Instead, the aio_poll calls include both the prepare and the
+     * dispatch phase, hence a simple counter is enough for them.
      */
-    bool dispatching;
+    uint32_t notify_me;
 
     /* lock to protect between bh's adders and deleter */
     QemuMutex bh_lock;
@@ -79,7 +99,19 @@ struct AioContext {
      */
     int walking_bh;
 
-    /* Used for aio_notify.  */
+    /* Used by aio_notify.
+     *
+     * "notified" is used to avoid expensive event_notifier_test_and_clear
+     * calls.  When it is clear, the EventNotifier is clear, or one thread
+     * is going to clear "notified" before processing more events.  False
+     * positives are possible, i.e. "notified" could be set even though the
+     * EventNotifier is clear.
+     *
+     * Note that event_notifier_set *cannot* be optimized the same way.  For
+     * more information on the problem that would result, see "#ifdef BUG2"
+     * in the docs/aio_notify_accept.promela formal model.
+     */
+    bool notified;
     EventNotifier notifier;
 
     /* Thread pool for performing work and receiving completion callbacks */
@@ -89,9 +121,6 @@ struct AioContext {
     QEMUTimerListGroup tlg;
 };
 
-/* Used internally to synchronize aio_poll against qemu_bh_schedule.  */
-void aio_set_dispatching(AioContext *ctx, bool dispatching);
-
 /**
  * aio_context_new: Allocate a new AioContext.
  *
@@ -156,6 +185,24 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
  */
 void aio_notify(AioContext *ctx);
 
+/**
+ * aio_notify_accept: Acknowledge receiving an aio_notify.
+ *
+ * aio_notify() uses an EventNotifier in order to wake up a sleeping
+ * aio_poll() or g_main_context_iteration().  Calls to aio_notify() are
+ * usually rare, but the AioContext has to clear the EventNotifier on
+ * every aio_poll() or g_main_context_iteration() in order to avoid
+ * busy waiting.  This event_notifier_test_and_clear() cannot be done
+ * using the usual aio_context_set_event_notifier(), because it must
+ * be done before processing all events (file descriptors, bottom halves,
+ * timers).
+ *
+ * aio_notify_accept() is an optimized event_notifier_test_and_clear()
+ * that is specific to an AioContext's notifier; it is used internally
+ * to clear the EventNotifier only if aio_notify() had been called.
+ */
+void aio_notify_accept(AioContext *ctx);
+
 /**
  * aio_bh_poll: Poll bottom halves for an AioContext.
  *

include/hw/virtio/virtio-access.h

@@ -143,6 +143,15 @@ static inline uint64_t virtio_ldq_p(VirtIODevice *vdev, const void *ptr)
     }
 }
 
+static inline bool virtio_needs_swap(VirtIODevice *vdev)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+    return virtio_access_is_big_endian(vdev) ? false : true;
+#else
+    return virtio_access_is_big_endian(vdev) ? true : false;
+#endif
+}
+
 static inline uint16_t virtio_tswap16(VirtIODevice *vdev, uint16_t s)
 {
 #ifdef HOST_WORDS_BIGENDIAN

include/hw/virtio/virtio-rng.h

@@ -44,6 +44,7 @@ typedef struct VirtIORNG {
      */
     QEMUTimer *rate_limit_timer;
     int64_t quota_remaining;
+    bool activate_timer;
 } VirtIORNG;
 
 #endif

include/qemu/timer.h

@@ -5,7 +5,7 @@
 #include "qemu-common.h"
 #include "qemu/notify.h"
 
-#define NSEC_PER_SEC 1000000000LL
+#define NANOSECONDS_PER_SECOND 1000000000LL
 
 /* timers */
 

memory.c

@@ -1887,23 +1887,16 @@ static FlatRange *flatview_lookup(FlatView *view, AddrRange addr)
                    sizeof(FlatRange), cmp_flatrange_addr);
 }
 
-bool memory_region_present(MemoryRegion *container, hwaddr addr)
-{
-    MemoryRegion *mr = memory_region_find(container, addr, 1).mr;
-    if (!mr || (mr == container)) {
-        return false;
-    }
-    memory_region_unref(mr);
-    return true;
-}
-
 bool memory_region_is_mapped(MemoryRegion *mr)
 {
     return mr->container ? true : false;
 }
 
-MemoryRegionSection memory_region_find(MemoryRegion *mr,
-                                       hwaddr addr, uint64_t size)
+/* Same as memory_region_find, but it does not add a reference to the
+ * returned region.  It must be called from an RCU critical section.
+ */
+static MemoryRegionSection memory_region_find_rcu(MemoryRegion *mr,
+                                                  hwaddr addr, uint64_t size)
 {
     MemoryRegionSection ret = { .mr = NULL };
     MemoryRegion *root;
@@ -1924,11 +1917,10 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr,
     }
     range = addrrange_make(int128_make64(addr), int128_make64(size));
 
-    rcu_read_lock();
     view = atomic_rcu_read(&as->current_map);
     fr = flatview_lookup(view, range);
     if (!fr) {
-        goto out;
+        return ret;
     }
 
     while (fr > view->ranges && addrrange_intersects(fr[-1].addr, range)) {
@@ -1944,12 +1936,32 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr,
     ret.size = range.size;
     ret.offset_within_address_space = int128_get64(range.start);
     ret.readonly = fr->readonly;
-    memory_region_ref(ret.mr);
-out:
+    return ret;
+}
+
+MemoryRegionSection memory_region_find(MemoryRegion *mr,
+                                       hwaddr addr, uint64_t size)
+{
+    MemoryRegionSection ret;
+    rcu_read_lock();
+    ret = memory_region_find_rcu(mr, addr, size);
+    if (ret.mr) {
+        memory_region_ref(ret.mr);
+    }
     rcu_read_unlock();
     return ret;
 }
 
+bool memory_region_present(MemoryRegion *container, hwaddr addr)
+{
+    MemoryRegion *mr;
+
+    rcu_read_lock();
+    mr = memory_region_find_rcu(container, addr, 1).mr;
+    rcu_read_unlock();
+    return mr && mr != container;
+}
+
 void address_space_sync_dirty_bitmap(AddressSpace *as)
 {
     FlatView *view;

migration/rdma.c

@@ -2997,7 +2997,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque)
                              (unsigned int)comp->block_idx,
                              rdma->local_ram_blocks.nb_blocks);
                 ret = -EIO;
-                break;
+                goto out;
             }
             block = &(rdma->local_ram_blocks.block[comp->block_idx]);
 
@@ -3092,7 +3092,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque)
                                  (unsigned int)reg->current_index,
                                  rdma->local_ram_blocks.nb_blocks);
                     ret = -ENOENT;
-                    break;
+                    goto out;
                 }
                 block = &(rdma->local_ram_blocks.block[reg->current_index]);
                 if (block->is_ram_block) {
@@ -3102,7 +3102,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque)
                             block->block_name, block->offset,
                             reg->key.current_addr);
                         ret = -ERANGE;
-                        break;
+                        goto out;
                     }
                     host_addr = (block->local_host_addr +
                                 (reg->key.current_addr - block->offset));
@@ -3118,7 +3118,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque)
                             " chunk: %" PRIx64,
                             block->block_name, reg->key.chunk);
                         ret = -ERANGE;
-                        break;
+                        goto out;
                     }
                 }
                 chunk_start = ram_chunk_start(block, chunk);

net/net.c

@@ -1257,14 +1257,19 @@ void qmp_set_link(const char *name, bool up, Error **errp)
 static void net_vm_change_state_handler(void *opaque, int running,
                                         RunState state)
 {
-    /* Complete all queued packets, to guarantee we don't modify
-     * state later when VM is not running.
-     */
-    if (!running) {
-        NetClientState *nc;
-        NetClientState *tmp;
+    NetClientState *nc;
+    NetClientState *tmp;
 
-        QTAILQ_FOREACH_SAFE(nc, &net_clients, next, tmp) {
+    QTAILQ_FOREACH_SAFE(nc, &net_clients, next, tmp) {
+        if (running) {
+            /* Flush queued packets and wake up backends. */
+            if (nc->peer && qemu_can_send_packet(nc)) {
+                qemu_flush_queued_packets(nc->peer);
+            }
+        } else {
+            /* Complete all queued packets, to guarantee we don't modify
+             * state later when VM is not running.
+             */
             qemu_flush_or_purge_queued_packets(nc, true);
         }
     }

net/socket.c

@@ -213,7 +213,7 @@ static void net_socket_send(void *opaque)
             if (s->index >= s->packet_len) {
                 s->index = 0;
                 s->state = 0;
-                if (qemu_send_packet_async(&s->nc, s->buf, size,
+                if (qemu_send_packet_async(&s->nc, s->buf, s->packet_len,
                                            net_socket_send_completed) == 0) {
                     net_socket_read_poll(s, false);
                     break;

net/vhost-user.c

@@ -120,39 +120,35 @@ static void net_vhost_user_event(void *opaque, int event)
     case CHR_EVENT_OPENED:
         vhost_user_start(s);
         net_vhost_link_down(s, false);
-        error_report("chardev \"%s\" went up", s->nc.info_str);
+        error_report("chardev \"%s\" went up", s->chr->label);
         break;
     case CHR_EVENT_CLOSED:
         net_vhost_link_down(s, true);
         vhost_user_stop(s);
-        error_report("chardev \"%s\" went down", s->nc.info_str);
+        error_report("chardev \"%s\" went down", s->chr->label);
         break;
     }
 }
 
 static int net_vhost_user_init(NetClientState *peer, const char *device,
-                               const char *name, CharDriverState *chr,
-                               uint32_t queues)
+                               const char *name, CharDriverState *chr)
 {
     NetClientState *nc;
     VhostUserState *s;
-    int i;
 
-    for (i = 0; i < queues; i++) {
-        nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
+    nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
 
-        snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s",
-                 i, chr->label);
+    snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user to %s",
+             chr->label);
 
-        s = DO_UPCAST(VhostUserState, nc, nc);
+    s = DO_UPCAST(VhostUserState, nc, nc);
 
-        /* We don't provide a receive callback */
-        s->nc.receive_disabled = 1;
-        s->chr = chr;
-        s->nc.queue_index = i;
+    /* We don't provide a receive callback */
+    s->nc.receive_disabled = 1;
+    s->chr = chr;
+
+    qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s);
 
-        qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s);
-    }
     return 0;
 }
 
@@ -230,7 +226,6 @@ static int net_vhost_check_net(void *opaque, QemuOpts *opts, Error **errp)
 int net_init_vhost_user(const NetClientOptions *opts, const char *name,
                         NetClientState *peer, Error **errp)
 {
-    uint32_t queues;
     const NetdevVhostUserOptions *vhost_user_opts;
     CharDriverState *chr;
 
@@ -248,12 +243,6 @@ int net_init_vhost_user(const NetClientOptions *opts, const char *name,
         return -1;
     }
 
-    /* number of queues for multiqueue */
-    if (vhost_user_opts->has_queues) {
-        queues = vhost_user_opts->queues;
-    } else {
-        queues = 1;
-    }
 
-    return net_vhost_user_init(peer, "vhost_user", name, chr, queues);
+    return net_vhost_user_init(peer, "vhost_user", name, chr);
 }

qapi-schema.json

@@ -2466,16 +2466,12 @@
 #
 # @vhostforce: #optional vhost on for non-MSIX virtio guests (default: false).
 #
-# @queues: #optional number of queues to be created for multiqueue vhost-user
-#          (default: 1) (Since 2.4)
-#
 # Since 2.1
 ##
 { 'struct': 'NetdevVhostUserOptions',
   'data': {
     'chardev':        'str',
-    '*vhostforce':    'bool',
-    '*queues':        'uint32' } }
+    '*vhostforce':    'bool' } }
 
 ##
 # @NetClientOptions

qemu-options.hx

@@ -1963,14 +1963,13 @@ The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single
 netdev.  @code{-net} and @code{-device} with parameter @option{vlan} create the
 required hub automatically.
 
-@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n]
+@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off]
 
 Establish a vhost-user netdev, backed by a chardev @var{id}. The chardev should
 be a unix domain socket backed one. The vhost-user uses a specifically defined
 protocol to pass vhost ioctl replacement messages to an application on the other
 end of the socket. On non-MSIX guests, the feature can be forced with
-@var{vhostforce}. Use 'queues=@var{n}' to specify the number of queues to
-be created for multiqueue vhost-user.
+@var{vhostforce}.
 
 Example:
 @example

qemu-timer.c

@@ -99,7 +99,7 @@ QEMUTimerList *timerlist_new(QEMUClockType type,
     QEMUClock *clock = qemu_clock_ptr(type);
 
     timer_list = g_malloc0(sizeof(QEMUTimerList));
-    qemu_event_init(&timer_list->timers_done_ev, false);
+    qemu_event_init(&timer_list->timers_done_ev, true);
     timer_list->clock = clock;
     timer_list->notify_cb = cb;
     timer_list->notify_opaque = opaque;

qga/qapi-schema.json

@@ -714,7 +714,7 @@
 # @virtual: Win virtual bus type
 # @file-backed virtual: Win file-backed bus type
 #
-# Since: 2.2
+# Since: 2.2; 'Unknown' and all entries below since 2.4
 ##
 { 'enum': 'GuestDiskBusType',
   'data': [ 'ide', 'fdc', 'scsi', 'virtio', 'xen', 'usb', 'uml', 'sata',

target-arm/kvm-stub.c

@@ -17,7 +17,7 @@ bool write_kvmstate_to_list(ARMCPU *cpu)
     abort();
 }
 
-bool write_list_to_kvmstate(ARMCPU *cpu)
+bool write_list_to_kvmstate(ARMCPU *cpu, int level)
 {
     abort();
 }

target-arm/kvm.c

@@ -409,7 +409,7 @@ bool write_kvmstate_to_list(ARMCPU *cpu)
     return ok;
 }
 
-bool write_list_to_kvmstate(ARMCPU *cpu)
+bool write_list_to_kvmstate(ARMCPU *cpu, int level)
 {
     CPUState *cs = CPU(cpu);
     int i;
@@ -421,6 +421,10 @@ bool write_list_to_kvmstate(ARMCPU *cpu)
         uint32_t v32;
         int ret;
 
+        if (kvm_arm_cpreg_level(regidx) > level) {
+            continue;
+        }
+
         r.id = regidx;
         switch (regidx & KVM_REG_SIZE_MASK) {
         case KVM_REG_SIZE_U32:

target-arm/kvm32.c

@@ -153,6 +153,34 @@ bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx)
     }
 }
 
+typedef struct CPRegStateLevel {
+    uint64_t regidx;
+    int level;
+} CPRegStateLevel;
+
+/* All coprocessor registers not listed in the following table are assumed to
+ * be of the level KVM_PUT_RUNTIME_STATE. If a register should be written less
+ * often, you must add it to this table with a state of either
+ * KVM_PUT_RESET_STATE or KVM_PUT_FULL_STATE.
+ */
+static const CPRegStateLevel non_runtime_cpregs[] = {
+    { KVM_REG_ARM_TIMER_CNT, KVM_PUT_FULL_STATE },
+};
+
+int kvm_arm_cpreg_level(uint64_t regidx)
+{
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(non_runtime_cpregs); i++) {
+        const CPRegStateLevel *l = &non_runtime_cpregs[i];
+        if (l->regidx == regidx) {
+            return l->level;
+        }
+    }
+
+    return KVM_PUT_RUNTIME_STATE;
+}
+
 #define ARM_MPIDR_HWID_BITMASK 0xFFFFFF
 #define ARM_CPU_ID_MPIDR       0, 0, 0, 5
 
@@ -367,7 +395,7 @@ int kvm_arch_put_registers(CPUState *cs, int level)
      * managed to update the CPUARMState with, and only allowing those
      * to be written back up into the kernel).
      */
-    if (!write_list_to_kvmstate(cpu)) {
+    if (!write_list_to_kvmstate(cpu, level)) {
         return EINVAL;
     }
 

target-arm/kvm64.c

@@ -139,6 +139,34 @@ bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx)
     }
 }
 
+typedef struct CPRegStateLevel {
+    uint64_t regidx;
+    int level;
+} CPRegStateLevel;
+
+/* All system registers not listed in the following table are assumed to be
+ * of the level KVM_PUT_RUNTIME_STATE. If a register should be written less
+ * often, you must add it to this table with a state of either
+ * KVM_PUT_RESET_STATE or KVM_PUT_FULL_STATE.
+ */
+static const CPRegStateLevel non_runtime_cpregs[] = {
+    { KVM_REG_ARM_TIMER_CNT, KVM_PUT_FULL_STATE },
+};
+
+int kvm_arm_cpreg_level(uint64_t regidx)
+{
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(non_runtime_cpregs); i++) {
+        const CPRegStateLevel *l = &non_runtime_cpregs[i];
+        if (l->regidx == regidx) {
+            return l->level;
+        }
+    }
+
+    return KVM_PUT_RUNTIME_STATE;
+}
+
 #define AARCH64_CORE_REG(x)   (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
                  KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
 
@@ -280,7 +308,7 @@ int kvm_arch_put_registers(CPUState *cs, int level)
         return ret;
     }
 
-    if (!write_list_to_kvmstate(cpu)) {
+    if (!write_list_to_kvmstate(cpu, level)) {
         return EINVAL;
     }
 

target-arm/kvm_arm.h

@@ -68,9 +68,19 @@ int kvm_arm_init_cpreg_list(ARMCPU *cpu);
  */
 bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx);
 
+/**
+ * kvm_arm_cpreg_level
+ * regidx: KVM register index
+ *
+ * Return the level of this coprocessor/system register.  Return value is
+ * either KVM_PUT_RUNTIME_STATE, KVM_PUT_RESET_STATE, or KVM_PUT_FULL_STATE.
+ */
+int kvm_arm_cpreg_level(uint64_t regidx);
+
 /**
  * write_list_to_kvmstate:
  * @cpu: ARMCPU
+ * @level: the state level to sync
  *
  * For each register listed in the ARMCPU cpreg_indexes list, write
  * its value from the cpreg_values list into the kernel (via ioctl).
@@ -83,7 +93,7 @@ bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx);
  * Note that we do not stop early on failure -- we will attempt
  * writing all registers in the list.
  */
-bool write_list_to_kvmstate(ARMCPU *cpu);
+bool write_list_to_kvmstate(ARMCPU *cpu, int level);
 
 /**
  * write_kvmstate_to_list:

target-arm/machine.c

@@ -251,7 +251,7 @@ static int cpu_post_load(void *opaque, int version_id)
     }
 
     if (kvm_enabled()) {
-        if (!write_list_to_kvmstate(cpu)) {
+        if (!write_list_to_kvmstate(cpu, KVM_PUT_FULL_STATE)) {
             return -1;
         }
         /* Note that it's OK for the TCG side not to know about

target-mips/kvm.c

@@ -235,10 +235,9 @@ int kvm_mips_set_ipi_interrupt(MIPSCPU *cpu, int irq, int level)
 static inline int kvm_mips_put_one_reg(CPUState *cs, uint64_t reg_id,
                                        int32_t *addr)
 {
-    uint64_t val64 = *addr;
     struct kvm_one_reg cp0reg = {
         .id = reg_id,
-        .addr = (uintptr_t)&val64
+        .addr = (uintptr_t)addr
     };
 
     return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &cp0reg);
@@ -270,18 +269,12 @@ static inline int kvm_mips_put_one_reg64(CPUState *cs, uint64_t reg_id,
 static inline int kvm_mips_get_one_reg(CPUState *cs, uint64_t reg_id,
                                        int32_t *addr)
 {
-    int ret;
-    uint64_t val64 = 0;
     struct kvm_one_reg cp0reg = {
         .id = reg_id,
-        .addr = (uintptr_t)&val64
+        .addr = (uintptr_t)addr
     };
 
-    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &cp0reg);
-    if (ret >= 0) {
-        *addr = val64;
-    }
-    return ret;
+    return kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &cp0reg);
 }
 
 static inline int kvm_mips_get_one_ulreg(CPUState *cs, uint64 reg_id,
@@ -635,12 +628,12 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 
     /* Set the registers based on QEMU's view of things */
     for (i = 0; i < 32; i++) {
-        regs.gpr[i] = env->active_tc.gpr[i];
+        regs.gpr[i] = (int64_t)(target_long)env->active_tc.gpr[i];
     }
 
-    regs.hi = env->active_tc.HI[0];
-    regs.lo = env->active_tc.LO[0];
-    regs.pc = env->active_tc.PC;
+    regs.hi = (int64_t)(target_long)env->active_tc.HI[0];
+    regs.lo = (int64_t)(target_long)env->active_tc.LO[0];
+    regs.pc = (int64_t)(target_long)env->active_tc.PC;
 
     ret = kvm_vcpu_ioctl(cs, KVM_SET_REGS, &regs);
 

tests/Makefile

@@ -478,6 +478,7 @@ $(patsubst %, check-%, $(check-unit-y)): check-%: %
 
 $(patsubst %, check-report-qtest-%.xml, $(QTEST_TARGETS)): check-report-qtest-%.xml: $(check-qtest-y)
 	$(call quiet-command,QTEST_QEMU_BINARY=$*-softmmu/qemu-system-$* \
+		QTEST_QEMU_IMG=qemu-img$(EXESUF) \
 	  gtester -q $(GTESTER_OPTIONS) -o $@ -m=$(SPEED) $(check-qtest-$*-y),"GTESTER $@")
 
 check-report-unit.xml: $(check-unit-y)

tests/ide-test.c

@@ -339,6 +339,31 @@ static void test_bmdma_short_prdt(void)
     assert_bit_clear(inb(IDE_BASE + reg_status), DF | ERR);
 }
 
+static void test_bmdma_one_sector_short_prdt(void)
+{
+    uint8_t status;
+
+    /* Read 2 sectors but only give 1 sector in PRDT */
+    PrdtEntry prdt[] = {
+        {
+            .addr = 0,
+            .size = cpu_to_le32(0x200 | PRDT_EOT),
+        },
+    };
+
+    /* Normal request */
+    status = send_dma_request(CMD_READ_DMA, 0, 2,
+                              prdt, ARRAY_SIZE(prdt));
+    g_assert_cmphex(status, ==, 0);
+    assert_bit_clear(inb(IDE_BASE + reg_status), DF | ERR);
+
+    /* Abort the request before it completes */
+    status = send_dma_request(CMD_READ_DMA | CMDF_ABORT, 0, 2,
+                              prdt, ARRAY_SIZE(prdt));
+    g_assert_cmphex(status, ==, 0);
+    assert_bit_clear(inb(IDE_BASE + reg_status), DF | ERR);
+}
+
 static void test_bmdma_long_prdt(void)
 {
     uint8_t status;
@@ -592,6 +617,8 @@ int main(int argc, char **argv)
     qtest_add_func("/ide/bmdma/setup", test_bmdma_setup);
     qtest_add_func("/ide/bmdma/simple_rw", test_bmdma_simple_rw);
     qtest_add_func("/ide/bmdma/short_prdt", test_bmdma_short_prdt);
+    qtest_add_func("/ide/bmdma/one_sector_short_prdt",
+                   test_bmdma_one_sector_short_prdt);
     qtest_add_func("/ide/bmdma/long_prdt", test_bmdma_long_prdt);
     qtest_add_func("/ide/bmdma/no_busmaster", test_bmdma_no_busmaster);
     qtest_add_func("/ide/bmdma/teardown", test_bmdma_teardown);

tests/rtl8139-test.c

@@ -86,7 +86,7 @@ static void test_timer(void)
         fatal("time too big %u\n", curr);
     }
     for (cnt = 0; ; ) {
-        clock_step(1 * NSEC_PER_SEC);
+        clock_step(1 * NANOSECONDS_PER_SECOND);
         prev = curr;
         curr = in_Timer();
 
@@ -125,7 +125,7 @@ static void test_timer(void)
     out_IntrStatus(0x4000);
     curr = in_Timer();
     out_TimerInt(curr + 0.5 * CLK);
-    clock_step(1 * NSEC_PER_SEC);
+    clock_step(1 * NANOSECONDS_PER_SECOND);
     out_Timer(0);
     if ((in_IntrStatus() & 0x4000) == 0) {
         fatal("we should have an interrupt here!\n");
@@ -137,7 +137,7 @@ static void test_timer(void)
     out_IntrStatus(0x4000);
     curr = in_Timer();
     out_TimerInt(curr + 0.5 * CLK);
-    clock_step(1 * NSEC_PER_SEC);
+    clock_step(1 * NANOSECONDS_PER_SECOND);
     out_TimerInt(0);
     if ((in_IntrStatus() & 0x4000) == 0) {
         fatal("we should have an interrupt here!\n");
@@ -148,7 +148,7 @@ static void test_timer(void)
     next = curr + 5.0 * CLK;
     out_TimerInt(next);
     for (cnt = 0; ; ) {
-        clock_step(1 * NSEC_PER_SEC);
+        clock_step(1 * NANOSECONDS_PER_SECOND);
         prev = curr;
         curr = in_Timer();
         diff = (curr-prev) & 0xffffffffu;

tests/test-aio.c

@@ -97,14 +97,6 @@ static void event_ready_cb(EventNotifier *e)
 
 /* Tests using aio_*.  */
 
-static void test_notify(void)
-{
-    g_assert(!aio_poll(ctx, false));
-    aio_notify(ctx);
-    g_assert(!aio_poll(ctx, true));
-    g_assert(!aio_poll(ctx, false));
-}
-
 typedef struct {
     QemuMutex start_lock;
     bool thread_acquired;
@@ -331,7 +323,7 @@ static void test_wait_event_notifier(void)
     EventNotifierTestData data = { .n = 0, .active = 1 };
     event_notifier_init(&data.e, false);
     aio_set_event_notifier(ctx, &data.e, event_ready_cb);
-    g_assert(!aio_poll(ctx, false));
+    while (aio_poll(ctx, false));
     g_assert_cmpint(data.n, ==, 0);
     g_assert_cmpint(data.active, ==, 1);
 
@@ -356,7 +348,7 @@ static void test_flush_event_notifier(void)
     EventNotifierTestData data = { .n = 0, .active = 10, .auto_set = true };
     event_notifier_init(&data.e, false);
     aio_set_event_notifier(ctx, &data.e, event_ready_cb);
-    g_assert(!aio_poll(ctx, false));
+    while (aio_poll(ctx, false));
     g_assert_cmpint(data.n, ==, 0);
     g_assert_cmpint(data.active, ==, 10);
 
@@ -494,14 +486,6 @@ static void test_timer_schedule(void)
  *   works well, and that's what I am using.
  */
 
-static void test_source_notify(void)
-{
-    while (g_main_context_iteration(NULL, false));
-    aio_notify(ctx);
-    g_assert(g_main_context_iteration(NULL, true));
-    g_assert(!g_main_context_iteration(NULL, false));
-}
-
 static void test_source_flush(void)
 {
     g_assert(!g_main_context_iteration(NULL, false));
@@ -669,7 +653,7 @@ static void test_source_wait_event_notifier(void)
     EventNotifierTestData data = { .n = 0, .active = 1 };
     event_notifier_init(&data.e, false);
     aio_set_event_notifier(ctx, &data.e, event_ready_cb);
-    g_assert(g_main_context_iteration(NULL, false));
+    while (g_main_context_iteration(NULL, false));
     g_assert_cmpint(data.n, ==, 0);
     g_assert_cmpint(data.active, ==, 1);
 
@@ -694,7 +678,7 @@ static void test_source_flush_event_notifier(void)
     EventNotifierTestData data = { .n = 0, .active = 10, .auto_set = true };
     event_notifier_init(&data.e, false);
     aio_set_event_notifier(ctx, &data.e, event_ready_cb);
-    g_assert(g_main_context_iteration(NULL, false));
+    while (g_main_context_iteration(NULL, false));
     g_assert_cmpint(data.n, ==, 0);
     g_assert_cmpint(data.active, ==, 10);
 
@@ -830,7 +814,6 @@ int main(int argc, char **argv)
     while (g_main_context_iteration(NULL, false));
 
     g_test_init(&argc, &argv, NULL);
-    g_test_add_func("/aio/notify",                  test_notify);
     g_test_add_func("/aio/acquire",                 test_acquire);
     g_test_add_func("/aio/bh/schedule",             test_bh_schedule);
     g_test_add_func("/aio/bh/schedule10",           test_bh_schedule10);
@@ -845,7 +828,6 @@ int main(int argc, char **argv)
     g_test_add_func("/aio/event/flush",             test_flush_event_notifier);
     g_test_add_func("/aio/timer/schedule",          test_timer_schedule);
 
-    g_test_add_func("/aio-gsource/notify",                  test_source_notify);
     g_test_add_func("/aio-gsource/flush",                   test_source_flush);
     g_test_add_func("/aio-gsource/bh/schedule",             test_source_bh_schedule);
     g_test_add_func("/aio-gsource/bh/schedule10",           test_source_bh_schedule10);

tests/test-throttle.c

@@ -40,19 +40,19 @@ static void test_leak_bucket(void)
     bkt.level = 1.5;
 
     /* leak an op work of time */
-    throttle_leak_bucket(&bkt, NSEC_PER_SEC / 150);
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 150);
     g_assert(bkt.avg == 150);
     g_assert(bkt.max == 15);
     g_assert(double_cmp(bkt.level, 0.5));
 
     /* leak again emptying the bucket */
-    throttle_leak_bucket(&bkt, NSEC_PER_SEC / 150);
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 150);
     g_assert(bkt.avg == 150);
     g_assert(bkt.max == 15);
     g_assert(double_cmp(bkt.level, 0));
 
     /* check that the bucket level won't go lower */
-    throttle_leak_bucket(&bkt, NSEC_PER_SEC / 150);
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 150);
     g_assert(bkt.avg == 150);
     g_assert(bkt.max == 15);
     g_assert(double_cmp(bkt.level, 0));
@@ -90,7 +90,7 @@ static void test_compute_wait(void)
     bkt.level = 15.5;
     wait = throttle_compute_wait(&bkt);
     /* time required to do half an operation */
-    result = (int64_t)  NSEC_PER_SEC / 150 / 2;
+    result = (int64_t)  NANOSECONDS_PER_SECOND / 150 / 2;
     g_assert(wait == result);
 }
 

tests/wdt_ib700-test.c

@@ -40,29 +40,29 @@ static QDict *qmp_get_event(const char *name)
 
 static QDict *ib700_program_and_wait(QTestState *s)
 {
-    clock_step(NSEC_PER_SEC * 40);
+    clock_step(NANOSECONDS_PER_SECOND * 40);
     qmp_check_no_event();
 
     /* 2 second limit */
     outb(0x443, 14);
 
     /* Ping */
-    clock_step(NSEC_PER_SEC);
+    clock_step(NANOSECONDS_PER_SECOND);
     qmp_check_no_event();
     outb(0x443, 14);
 
     /* Disable */
-    clock_step(NSEC_PER_SEC);
+    clock_step(NANOSECONDS_PER_SECOND);
     qmp_check_no_event();
     outb(0x441, 1);
-    clock_step(3 * NSEC_PER_SEC);
+    clock_step(3 * NANOSECONDS_PER_SECOND);
     qmp_check_no_event();
 
     /* Enable and let it fire */
     outb(0x443, 13);
-    clock_step(3 * NSEC_PER_SEC);
+    clock_step(3 * NANOSECONDS_PER_SECOND);
     qmp_check_no_event();
-    clock_step(2 * NSEC_PER_SEC);
+    clock_step(2 * NANOSECONDS_PER_SECOND);
     return qmp_get_event("WATCHDOG");
 }
 

util/throttle.c

@@ -36,7 +36,7 @@ void throttle_leak_bucket(LeakyBucket *bkt, int64_t delta_ns)
     double leak;
 
     /* compute how much to leak */
-    leak = (bkt->avg * (double) delta_ns) / NSEC_PER_SEC;
+    leak = (bkt->avg * (double) delta_ns) / NANOSECONDS_PER_SECOND;
 
     /* make the bucket leak */
     bkt->level = MAX(bkt->level - leak, 0);
@@ -72,7 +72,7 @@ static void throttle_do_leak(ThrottleState *ts, int64_t now)
  */
 static int64_t throttle_do_compute_wait(double limit, double extra)
 {
-    double wait = extra * NSEC_PER_SEC;
+    double wait = extra * NANOSECONDS_PER_SECOND;
     wait /= limit;
     return wait;
 }