Blob Blame Raw
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 13 Aug 2015 10:41:50 +0200
Subject: [PATCH] mirror: Fix coroutine reentrance

This fixes a regression introduced by commit dcfb3beb ("mirror: Do zero
write on target if sectors not allocated"), which was reported to cause
aborts with the message "Co-routine re-entered recursively".

The cause for this bug is the following code in mirror_iteration_done():

    if (s->common.busy) {
        qemu_coroutine_enter(s->common.co, NULL);
    }

This has always been ugly because - unlike most places that reenter - it
doesn't have a specific yield that it pairs with, but is more
uncontrolled.  What we really mean here is "reenter the coroutine if
it's in one of the four explicit yields in mirror.c".

This used to be equivalent with s->common.busy because neither
mirror_run() nor mirror_iteration() call any function that could yield.
However since commit dcfb3beb this doesn't hold true any more:
bdrv_get_block_status_above() can yield.

So what happens is that bdrv_get_block_status_above() wants to take a
lock that is already held, so it adds itself to the queue of waiting
coroutines and yields. Instead of being woken up by the unlock function,
however, it gets woken up by mirror_iteration_done(), which is obviously
wrong.

In most cases the code actually happens to cope fairly well with such
cases, but in this specific case, the unlock must already have scheduled
the coroutine for wakeup when mirror_iteration_done() reentered it. And
then the coroutine happened to process the scheduled restarts and tried
to reenter itself recursively.

This patch fixes the problem by pairing the reenter in
mirror_iteration_done() with specific yields instead of abusing
s->common.busy.

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jeff Cody <jcody@redhat.com>
Message-id: 1439455310-11263-1-git-send-email-kwolf@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit e424aff5f307227b1c2512bbb8ece891bb895cef)
---
 block/mirror.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/block/mirror.c b/block/mirror.c
index 6f1bc3c..d06a0be 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -58,6 +58,7 @@ typedef struct MirrorBlockJob {
     int sectors_in_flight;
     int ret;
     bool unmap;
+    bool waiting_for_io;
 } MirrorBlockJob;
 
 typedef struct MirrorOp {
@@ -112,11 +113,7 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
     qemu_iovec_destroy(&op->qiov);
     g_slice_free(MirrorOp, op);
 
-    /* Enter coroutine when it is not sleeping.  The coroutine sleeps to
-     * rate-limit itself.  The coroutine will eventually resume since there is
-     * a sleep timeout so don't wake it early.
-     */
-    if (s->common.busy) {
+    if (s->waiting_for_io) {
         qemu_coroutine_enter(s->common.co, NULL);
     }
 }
@@ -206,7 +203,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
     /* Wait for I/O to this cluster (from a previous iteration) to be done.  */
     while (test_bit(next_chunk, s->in_flight_bitmap)) {
         trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
+        s->waiting_for_io = true;
         qemu_coroutine_yield();
+        s->waiting_for_io = false;
     }
 
     do {
@@ -242,7 +241,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
          */
         while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
             trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
+            s->waiting_for_io = true;
             qemu_coroutine_yield();
+            s->waiting_for_io = false;
         }
         if (s->buf_free_count < nb_chunks + added_chunks) {
             trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
@@ -341,7 +342,9 @@ static void mirror_free_init(MirrorBlockJob *s)
 static void mirror_drain(MirrorBlockJob *s)
 {
     while (s->in_flight > 0) {
+        s->waiting_for_io = true;
         qemu_coroutine_yield();
+        s->waiting_for_io = false;
     }
 }
 
@@ -516,7 +519,9 @@ static void coroutine_fn mirror_run(void *opaque)
             if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
                 (cnt == 0 && s->in_flight > 0)) {
                 trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
+                s->waiting_for_io = true;
                 qemu_coroutine_yield();
+                s->waiting_for_io = false;
                 continue;
             } else if (cnt != 0) {
                 delay_ns = mirror_iteration(s);