coroutine-lock: do not touch coroutine after another one has been entered

Submission of requests on linux aio is a bit tricky and can lead to
requests completions on submission path:

44713c9e ("linux-aio: Handle io_submit() failure gracefully")
0ed93d84 ("linux-aio: process completions from ioq_submit()")

That means that any coroutine which has been yielded in order to wait
for completion can be resumed from submission path and be eventually
terminated (freed).

The following use-after-free crash was observed when IO throttling
was enabled:

 Program received signal SIGSEGV, Segmentation fault.
 [Switching to Thread 0x7f5813dff700 (LWP 56417)]
 virtqueue_unmap_sg (elem=0x7f5804009a30, len=1, vq=<optimized out>) at virtio.c:252
 (gdb) bt
 #0  virtqueue_unmap_sg (elem=0x7f5804009a30, len=1, vq=<optimized out>) at virtio.c:252
                              ^^^^^^^^^^^^^^
                              remember the address

 #1  virtqueue_fill (vq=0x5598b20d21b0, elem=0x7f5804009a30, len=1, idx=0) at virtio.c:282
 #2  virtqueue_push (vq=0x5598b20d21b0, elem=elem@entry=0x7f5804009a30, len=<optimized out>) at virtio.c:308
 #3  virtio_blk_req_complete (req=req@entry=0x7f5804009a30, status=status@entry=0 '\000') at virtio-blk.c:61
 #4  virtio_blk_rw_complete (opaque=<optimized out>, ret=0) at virtio-blk.c:126
 #5  blk_aio_complete (acb=0x7f58040068d0) at block-backend.c:923
 #6  coroutine_trampoline (i0=<optimized out>, i1=<optimized out>) at coroutine-ucontext.c:78

 (gdb) p * elem
 $8 = {index = 77, out_num = 2, in_num = 1,
       in_addr = 0x7f5804009ad8, out_addr = 0x7f5804009ae0,
       in_sg = 0x0, out_sg = 0x7f5804009a50}
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       'in_sg' and 'out_sg' are invalid.
       e.g. it is impossible that 'in_sg' is zero,
       instead its value must be equal to:

       (gdb) p/x 0x7f5804009ad8 + sizeof(elem->in_addr[0]) + 2 * sizeof(elem->out_addr[0])
       $26 = 0x7f5804009af0

Seems 'elem' was corrupted.  Meanwhile another thread raised an abort:

 Thread 12 (Thread 0x7f57f2ffd700 (LWP 56426)):
 #0  raise () from /lib/x86_64-linux-gnu/libc.so.6
 #1  abort () from /lib/x86_64-linux-gnu/libc.so.6
 #2  qemu_coroutine_enter (co=0x7f5804009af0) at qemu-coroutine.c:113
 #3  qemu_co_queue_run_restart (co=0x7f5804009a30) at qemu-coroutine-lock.c:60
 #4  qemu_coroutine_enter (co=0x7f5804009a30) at qemu-coroutine.c:119
                           ^^^^^^^^^^^^^^^^^^
                           WTF?? this is equal to elem from crashed thread

 #5  qemu_co_queue_run_restart (co=0x7f57e7f16ae0) at qemu-coroutine-lock.c:60
 #6  qemu_coroutine_enter (co=0x7f57e7f16ae0) at qemu-coroutine.c:119
 #7  qemu_co_queue_run_restart (co=0x7f5807e112a0) at qemu-coroutine-lock.c:60
 #8  qemu_coroutine_enter (co=0x7f5807e112a0) at qemu-coroutine.c:119
 #9  qemu_co_queue_run_restart (co=0x7f5807f17820) at qemu-coroutine-lock.c:60
 #10 qemu_coroutine_enter (co=0x7f5807f17820) at qemu-coroutine.c:119
 #11 qemu_co_queue_run_restart (co=0x7f57e7f18e10) at qemu-coroutine-lock.c:60
 #12 qemu_coroutine_enter (co=0x7f57e7f18e10) at qemu-coroutine.c:119
 #13 qemu_co_enter_next (queue=queue@entry=0x5598b1e742d0) at qemu-coroutine-lock.c:106
 #14 timer_cb (blk=0x5598b1e74280, is_write=<optimized out>) at throttle-groups.c:419

Crash can be explained by access of 'co' object from the loop inside
qemu_co_queue_run_restart():

  while ((next = QSIMPLEQ_FIRST(&co->co_queue_wakeup))) {
      QSIMPLEQ_REMOVE_HEAD(&co->co_queue_wakeup, co_queue_next);
                           ^^^^^^^^^^^^^^^^^^^^
                           on each iteration 'co' is accessed,
                           but 'co' can be already freed

      qemu_coroutine_enter(next);
  }

When 'next' coroutine is resumed (entered) it can in its turn resume
'co', and eventually free it.  That's why we see 'co' (which was freed)
has the same address as 'elem' from the first backtrace.

The fix is obvious: use temporary queue and do not touch coroutine after
first qemu_coroutine_enter() is invoked.

The issue is quite rare and happens every ~12 hours on very high IO
and CPU load (building linux kernel with -j512 inside guest) when IO
throttling is enabled.  With the fix applied guest is running ~35 hours
and is still alive so far.
Signed-off-by: NRoman Pen <roman.penyaev@profitbricks.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Message-id: 20170601160847.23720-1-roman.penyaev@profitbricks.com
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Fam Zheng <famz@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: qemu-devel@nongnu.org
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

util/qemu-coroutine-lock.c

@@ -77,10 +77,25 @@ void coroutine_fn qemu_co_queue_wait(CoQueue *queue, CoMutex *mutex)
 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);
-    while ((next = QSIMPLEQ_FIRST(&co->co_queue_wakeup))) {
-        QSIMPLEQ_REMOVE_HEAD(&co->co_queue_wakeup, co_queue_next);
+
+    /* 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 pupulate "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);
     }
 }

util/qemu-coroutine.c

@@ -126,6 +126,11 @@ void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co)
 
     qemu_co_queue_run_restart(co);
 
+    /* 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.
+     */
+
     switch (ret) {
     case COROUTINE_YIELD:
         return;