quorum: Convert to BdrvChild

[qemu.git] / block / io.c

diff --git a/block/io.c b/block/io.c
index ccf79c33c5e2966bbdefb05d7e4828dbbc5c5104..17293c3dd3a930370e7935fcbc7b906e9e023abd 100644 (file)
--- a/block/io.c
+++ b/block/io.c
@@ -236,12 +236,12 @@ static bool bdrv_requests_pending(BlockDriverState *bs)
 /*
  * Wait for pending requests to complete on a single BlockDriverState subtree
  *
- * See the warning in bdrv_drain_all().  This function can only be called if
- * you are sure nothing can generate I/O because you have op blockers
- * installed.
- *
  * Note that unlike bdrv_drain_all(), the caller must hold the BlockDriverState
  * AioContext.
+ *
+ * Only this BlockDriverState's AioContext is run, so in-flight requests must
+ * not depend on events in other AioContexts.  In that case, use
+ * bdrv_drain_all() instead.
  */
 void bdrv_drain(BlockDriverState *bs)
 {
@@ -260,12 +260,6 @@ void bdrv_drain(BlockDriverState *bs)
  *
  * This function does not flush data to disk, use bdrv_flush_all() for that
  * after calling this function.
- *
- * Note that completion of an asynchronous I/O operation can trigger any
- * number of other I/O operations on other devices---for example a coroutine
- * can be arbitrarily complex and a constant flow of I/O can come until the
- * coroutine is complete.  Because of this, it is not possible to have a
- * function to drain a single device's I/O queue.
  */
 void bdrv_drain_all(void)
 {
@@ -283,11 +277,17 @@ void bdrv_drain_all(void)
         }
         aio_context_release(aio_context);
 
-        if (!aio_ctxs || !g_slist_find(aio_ctxs, aio_context)) {
+        if (!g_slist_find(aio_ctxs, aio_context)) {
             aio_ctxs = g_slist_prepend(aio_ctxs, aio_context);
         }
     }
 
+    /* Note that completion of an asynchronous I/O operation can trigger any
+     * number of other I/O operations on other devices---for example a
+     * coroutine can submit an I/O request to another device in response to
+     * request completion.  Therefore we must keep looping until there was no
+     * more activity rather than simply draining each device independently.
+     */
     while (busy) {
         busy = false;
 
@@ -932,7 +932,8 @@ static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
         return ret;
     }
 
-    if (bs->copy_on_read) {
+    /* Don't do copy-on-read if we read data before write operation */
+    if (bs->copy_on_read && !(flags & BDRV_REQ_NO_COPY_ON_READ)) {
         flags |= BDRV_REQ_COPY_ON_READ;
     }
 
@@ -1001,6 +1002,15 @@ int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
     return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov, 0);
 }
 
+int coroutine_fn bdrv_co_no_copy_on_readv(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    trace_bdrv_co_no_copy_on_readv(bs, sector_num, nb_sectors);
+
+    return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov,
+                            BDRV_REQ_NO_COPY_ON_READ);
+}
+
 int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
 {
@@ -2208,7 +2218,7 @@ void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs,
 {
     BlockAIOCB *acb;
 
-    acb = g_slice_alloc(aiocb_info->aiocb_size);
+    acb = g_malloc(aiocb_info->aiocb_size);
     acb->aiocb_info = aiocb_info;
     acb->bs = bs;
     acb->cb = cb;
@@ -2228,7 +2238,7 @@ void qemu_aio_unref(void *p)
     BlockAIOCB *acb = p;
     assert(acb->refcnt > 0);
     if (--acb->refcnt == 0) {
-        g_slice_free1(acb->aiocb_info->aiocb_size, acb);
+        g_free(acb);
     }
 }
 
@@ -2412,8 +2422,6 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
         return -EPERM;
     }
 
-    bdrv_reset_dirty(bs, sector_num, nb_sectors);
-
     /* Do nothing if disabled.  */
     if (!(bs->open_flags & BDRV_O_UNMAP)) {
         return 0;
@@ -2423,6 +2431,8 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
         return 0;
     }
 
+    bdrv_set_dirty(bs, sector_num, nb_sectors);
+
     max_discard = MIN_NON_ZERO(bs->bl.max_discard, BDRV_REQUEST_MAX_SECTORS);
     while (nb_sectors > 0) {
         int ret;