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

# gpg: Signature made Tue 27 Mar 2018 15:41:11 BST
# gpg:                using RSA key 9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  MAINTAINERS: add include/block/aio-wait.h
  coroutine: add test-aio coroutine queue chaining test case
  coroutine: avoid co_queue_wakeup recursion
  queue: add QSIMPLEQ_PREPEND()

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

7 files changed, 112 insertions, 92 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 6fa36c7a2d..24b70169bc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1351,6 +1351,7 @@ F: util/aio-*.c
 F: block/io.c
 F: migration/block*
 F: include/block/aio.h
+F: include/block/aio-wait.h
 F: scripts/qemugdb/aio.py
 T: git git://github.com/stefanha/qemu.git block
 
diff --git a/block/io.c b/block/io.c
index 2b09c656d0..bd9a19a9c4 100644
--- a/block/io.c
+++ b/block/io.c
@@ -249,8 +249,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
     BdrvCoDrainData data;
 
     /* Calling bdrv_drain() from a BH ensures the current coroutine yields and
-     * other coroutines run if they were queued from
-     * qemu_co_queue_run_restart(). */
+     * other coroutines run if they were queued by aio_co_enter(). */
 
     assert(qemu_in_coroutine());
     data = (BdrvCoDrainData) {
diff --git a/include/qemu/coroutine_int.h b/include/qemu/coroutine_int.h
index 59e8406398..bd6b0468e1 100644
--- a/include/qemu/coroutine_int.h
+++ b/include/qemu/coroutine_int.h
@@ -68,6 +68,5 @@ Coroutine *qemu_coroutine_new(void);
 void qemu_coroutine_delete(Coroutine *co);
 CoroutineAction qemu_coroutine_switch(Coroutine *from, Coroutine *to,
                                       CoroutineAction action);
-void coroutine_fn qemu_co_queue_run_restart(Coroutine *co);
 
 #endif
diff --git a/include/qemu/queue.h b/include/qemu/queue.h
index aa270d2b38..59fd1203a1 100644
--- a/include/qemu/queue.h
+++ b/include/qemu/queue.h
@@ -324,6 +324,14 @@ struct {                                                                \
     }                                                                   \
 } while (/*CONSTCOND*/0)
 
+#define QSIMPLEQ_PREPEND(head1, head2) do {                             \
+    if (!QSIMPLEQ_EMPTY((head2))) {                                     \
+        *(head2)->sqh_last = (head1)->sqh_first;                        \
+        (head1)->sqh_first = (head2)->sqh_first;                          \
+        QSIMPLEQ_INIT((head2));                                         \
+    }                                                                   \
+} while (/*CONSTCOND*/0)
+
 #define QSIMPLEQ_LAST(head, type, field)                                \
     (QSIMPLEQ_EMPTY((head)) ?                                           \
         NULL :                                                          \
diff --git a/tests/test-aio.c b/tests/test-aio.c
index 54e20d6ab1..86fb73b3d5 100644
--- a/tests/test-aio.c
+++ b/tests/test-aio.c
@@ -16,6 +16,8 @@
 #include "qemu/timer.h"
 #include "qemu/sockets.h"
 #include "qemu/error-report.h"
+#include "qemu/coroutine.h"
+#include "qemu/main-loop.h"
 
 static AioContext *ctx;
 
@@ -827,24 +829,59 @@ static void test_source_timer_schedule(void)
     timer_del(&data.timer);
 }
 
+/*
+ * Check that aio_co_enter() can chain many times
+ *
+ * Two coroutines should be able to invoke each other via aio_co_enter() many
+ * times without hitting a limit like stack exhaustion.  In other words, the
+ * calls should be chained instead of nested.
+ */
 
-/* End of tests.  */
+typedef struct {
+    Coroutine *other;
+    unsigned i;
+    unsigned max;
+} ChainData;
 
-int main(int argc, char **argv)
+static void coroutine_fn chain(void *opaque)
 {
-    Error *local_error = NULL;
-    GSource *src;
+    ChainData *data = opaque;
 
-    init_clocks(NULL);
+    for (data->i = 0; data->i < data->max; data->i++) {
+        /* Queue up the other coroutine... */
+        aio_co_enter(ctx, data->other);
 
-    ctx = aio_context_new(&local_error);
-    if (!ctx) {
-        error_reportf_err(local_error, "Failed to create AIO Context: ");
-        exit(1);
+        /* ...and give control to it */
+        qemu_coroutine_yield();
     }
-    src = aio_get_g_source(ctx);
-    g_source_attach(src, NULL);
-    g_source_unref(src);
+}
+
+static void test_queue_chaining(void)
+{
+    /* This number of iterations hit stack exhaustion in the past: */
+    ChainData data_a = { .max = 25000 };
+    ChainData data_b = { .max = 25000 };
+
+    data_b.other = qemu_coroutine_create(chain, &data_a);
+    data_a.other = qemu_coroutine_create(chain, &data_b);
+
+    qemu_coroutine_enter(data_b.other);
+
+    g_assert_cmpint(data_a.i, ==, data_a.max);
+    g_assert_cmpint(data_b.i, ==, data_b.max - 1);
+
+    /* Allow the second coroutine to terminate */
+    qemu_coroutine_enter(data_a.other);
+
+    g_assert_cmpint(data_b.i, ==, data_b.max);
+}
+
+/* End of tests.  */
+
+int main(int argc, char **argv)
+{
+    qemu_init_main_loop(&error_fatal);
+    ctx = qemu_get_aio_context();
 
     while (g_main_context_iteration(NULL, false));
 
@@ -864,6 +901,8 @@ int main(int argc, char **argv)
     g_test_add_func("/aio/external-client",         test_aio_external_client);
     g_test_add_func("/aio/timer/schedule",          test_timer_schedule);
 
+    g_test_add_func("/aio/coroutine/queue-chaining", test_queue_chaining);
+
     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);
diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c
index 5a80c10690..27438a1858 100644
--- a/util/qemu-coroutine-lock.c
+++ b/util/qemu-coroutine-lock.c
@@ -68,40 +68,6 @@ void coroutine_fn qemu_co_queue_wait_impl(CoQueue *queue, QemuLockable *lock)
     }
 }
 
-/**
- * qemu_co_queue_run_restart:
- *
- * Enter each coroutine that was previously marked for restart by
- * qemu_co_queue_next() or qemu_co_queue_restart_all().  This function is
- * invoked by the core coroutine code when the current coroutine yields or
- * terminates.
- */
-void qemu_co_queue_run_restart(Coroutine *co)
-{
-    Coroutine *next;
-    QSIMPLEQ_HEAD(, Coroutine) tmp_queue_wakeup =
-        QSIMPLEQ_HEAD_INITIALIZER(tmp_queue_wakeup);
-
-    trace_qemu_co_queue_run_restart(co);
-
-    /* Because "co" has yielded, any coroutine that we wakeup can resume it.
-     * If this happens and "co" terminates, co->co_queue_wakeup becomes
-     * invalid memory.  Therefore, use a temporary queue and do not touch
-     * the "co" coroutine as soon as you enter another one.
-     *
-     * In its turn resumed "co" can populate "co_queue_wakeup" queue with
-     * new coroutines to be woken up.  The caller, who has resumed "co",
-     * will be responsible for traversing the same queue, which may cause
-     * a different wakeup order but not any missing wakeups.
-     */
-    QSIMPLEQ_CONCAT(&tmp_queue_wakeup, &co->co_queue_wakeup);
-
-    while ((next = QSIMPLEQ_FIRST(&tmp_queue_wakeup))) {
-        QSIMPLEQ_REMOVE_HEAD(&tmp_queue_wakeup, co_queue_next);
-        qemu_coroutine_enter(next);
-    }
-}
-
 static bool qemu_co_queue_do_restart(CoQueue *queue, bool single)
 {
     Coroutine *next;
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 9eff7fd450..1ba4191b84 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -104,57 +104,65 @@ static void coroutine_delete(Coroutine *co)
 
 void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
 {
-    Coroutine *self = qemu_coroutine_self();
-    CoroutineAction ret;
-
-    /* Cannot rely on the read barrier for co in aio_co_wake(), as there are
-     * callers outside of aio_co_wake() */
-    const char *scheduled = atomic_mb_read(&co->scheduled);
+    QSIMPLEQ_HEAD(, Coroutine) pending = QSIMPLEQ_HEAD_INITIALIZER(pending);
+    Coroutine *from = qemu_coroutine_self();
 
-    trace_qemu_aio_coroutine_enter(ctx, self, co, co->entry_arg);
+    QSIMPLEQ_INSERT_TAIL(&pending, co, co_queue_next);
 
-    /* if the Coroutine has already been scheduled, entering it again will
-     * cause us to enter it twice, potentially even after the coroutine has
-     * been deleted */
-    if (scheduled) {
-        fprintf(stderr,
-                "%s: Co-routine was already scheduled in '%s'\n",
-                __func__, scheduled);
-        abort();
-    }
+    /* Run co and any queued coroutines */
+    while (!QSIMPLEQ_EMPTY(&pending)) {
+        Coroutine *to = QSIMPLEQ_FIRST(&pending);
+        CoroutineAction ret;
 
-    if (co->caller) {
-        fprintf(stderr, "Co-routine re-entered recursively\n");
-        abort();
-    }
+        /* Cannot rely on the read barrier for to in aio_co_wake(), as there are
+         * callers outside of aio_co_wake() */
+        const char *scheduled = atomic_mb_read(&to->scheduled);
 
-    co->caller = self;
-    co->ctx = ctx;
+        QSIMPLEQ_REMOVE_HEAD(&pending, co_queue_next);
 
-    /* Store co->ctx before anything that stores co.  Matches
-     * barrier in aio_co_wake and qemu_co_mutex_wake.
-     */
-    smp_wmb();
+        trace_qemu_aio_coroutine_enter(ctx, from, to, to->entry_arg);
 
-    ret = qemu_coroutine_switch(self, co, COROUTINE_ENTER);
-
-    qemu_co_queue_run_restart(co);
+        /* if the Coroutine has already been scheduled, entering it again will
+         * cause us to enter it twice, potentially even after the coroutine has
+         * been deleted */
+        if (scheduled) {
+            fprintf(stderr,
+                    "%s: Co-routine was already scheduled in '%s'\n",
+                    __func__, scheduled);
+            abort();
+        }
 
-    /* Beware, if ret == COROUTINE_YIELD and qemu_co_queue_run_restart()
-     * has started any other coroutine, "co" might have been reentered
-     * and even freed by now!  So be careful and do not touch it.
-     */
+        if (to->caller) {
+            fprintf(stderr, "Co-routine re-entered recursively\n");
+            abort();
+        }
 
-    switch (ret) {
-    case COROUTINE_YIELD:
-        return;
-    case COROUTINE_TERMINATE:
-        assert(!co->locks_held);
-        trace_qemu_coroutine_terminate(co);
-        coroutine_delete(co);
-        return;
-    default:
-        abort();
+        to->caller = from;
+        to->ctx = ctx;
+
+        /* Store to->ctx before anything that stores to.  Matches
+         * barrier in aio_co_wake and qemu_co_mutex_wake.
+         */
+        smp_wmb();
+
+        ret = qemu_coroutine_switch(from, to, COROUTINE_ENTER);
+
+        /* Queued coroutines are run depth-first; previously pending coroutines
+         * run after those queued more recently.
+         */
+        QSIMPLEQ_PREPEND(&pending, &to->co_queue_wakeup);
+
+        switch (ret) {
+        case COROUTINE_YIELD:
+            break;
+        case COROUTINE_TERMINATE:
+            assert(!to->locks_held);
+            trace_qemu_coroutine_terminate(to);
+            coroutine_delete(to);
+            break;
+        default:
+            abort();
+        }
     }
 }