coroutine: abort if we try to schedule or enter a pending coroutine

The previous patch fixed a race condition, in which there were
coroutines being executing doubly, or after coroutine deletion.

We can detect common scenarios when this happens, and print an error
message and abort before we corrupt memory / data, or segfault.

This patch will abort if an attempt to enter a coroutine is made while
it is currently pending execution, either in a specific AioContext bh,
or pending execution via a timer.  It will also abort if a coroutine
is scheduled, before a prior scheduled run has occurred.

We cannot rely on the existing co->caller check for recursive re-entry
to catch this, as the coroutine may run and exit with
COROUTINE_TERMINATE before the scheduled coroutine executes.

(This is the scenario that was occurring and fixed in the previous
patch).

This patch also re-orders the Coroutine struct elements in an attempt to
optimize caching.

Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 12 insertions, 0 deletions

diff --git a/util/qemu-coroutine-sleep.c b/util/qemu-coroutine-sleep.c
index 9c5655041b..254349cdbb 100644
--- a/util/qemu-coroutine-sleep.c
+++ b/util/qemu-coroutine-sleep.c
@@ -13,6 +13,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/coroutine.h"
+#include "qemu/coroutine_int.h"
 #include "qemu/timer.h"
 #include "block/aio.h"
 
@@ -25,6 +26,8 @@ static void co_sleep_cb(void *opaque)
 {
     CoSleepCB *sleep_cb = opaque;
 
+    /* Write of schedule protected by barrier write in aio_co_schedule */
+    atomic_set(&sleep_cb->co->scheduled, NULL);
     aio_co_wake(sleep_cb->co);
 }
 
@@ -34,6 +37,15 @@ void coroutine_fn co_aio_sleep_ns(AioContext *ctx, QEMUClockType type,
     CoSleepCB sleep_cb = {
         .co = qemu_coroutine_self(),
     };
+
+    const char *scheduled = atomic_cmpxchg(&sleep_cb.co->scheduled, NULL,
+                                           __func__);
+    if (scheduled) {
+        fprintf(stderr,
+                "%s: Co-routine was already scheduled in '%s'\n",
+                __func__, scheduled);
+        abort();
+    }
     sleep_cb.ts = aio_timer_new(ctx, type, SCALE_NS, co_sleep_cb, &sleep_cb);
     timer_mod(sleep_cb.ts, qemu_clock_get_ns(type) + ns);
     qemu_coroutine_yield();