block/io: wait for serialising requests when a request becomes serialising

Marking without waiting would not result in actual serialising behavior.
Thus, make a call bdrv_mark_request_serialising sufficient for
serialisation to happen.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1578495356-46219-3-git-send-email-pbonzini@redhat.com
Message-Id: <1578495356-46219-3-git-send-email-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

block/file-posix.c

@@ -2753,7 +2753,6 @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
         req->overlap_bytes = req->bytes;
 
         bdrv_mark_request_serialising(req, bs->bl.request_alignment);
-        bdrv_wait_serialising_requests(req);
     }
 #endif
 

block/io.c

@@ -41,6 +41,7 @@
 #define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS)
 
 static void bdrv_parent_cb_resize(BlockDriverState *bs);
+static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self);
 static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
     int64_t offset, int bytes, BdrvRequestFlags flags);
 
@@ -715,7 +716,7 @@ static void tracked_request_begin(BdrvTrackedRequest *req,
     qemu_co_mutex_unlock(&bs->reqs_lock);
 }
 
-void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
+bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
 {
     int64_t overlap_offset = req->offset & ~(align - 1);
     uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
@@ -728,18 +729,7 @@ void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
 
     req->overlap_offset = MIN(req->overlap_offset, overlap_offset);
     req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
-}
+    return bdrv_wait_serialising_requests(req);
-
-static bool is_request_serialising_and_aligned(BdrvTrackedRequest *req)
-{
-    /*
-     * If the request is serialising, overlap_offset and overlap_bytes are set,
-     * so we can check if the request is aligned. Otherwise, don't care and
-     * return false.
-     */
-
-    return req->serialising && (req->offset == req->overlap_offset) &&
-           (req->bytes == req->overlap_bytes);
 }
 
 /**
@@ -823,7 +813,7 @@ void bdrv_dec_in_flight(BlockDriverState *bs)
     bdrv_wakeup(bs);
 }
 
-bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self)
+static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self)
 {
     BlockDriverState *bs = self->bs;
     BdrvTrackedRequest *req;
@@ -1455,10 +1445,10 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
          * it ensures that the CoR read and write operations are atomic and
          * guest writes cannot interleave between them. */
         bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
+    } else {
+        bdrv_wait_serialising_requests(req);
     }
 
-    bdrv_wait_serialising_requests(req);
-
     if (flags & BDRV_REQ_COPY_ON_READ) {
         int64_t pnum;
 
@@ -1851,13 +1841,19 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
     assert(!(flags & ~BDRV_REQ_MASK));
 
     if (flags & BDRV_REQ_SERIALISING) {
-        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
+        waited = bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
+        /*
+         * For a misaligned request we should have already waited earlier,
+         * because we come after bdrv_padding_rmw_read which must be called
+         * with the request already marked as serialising.
+         */
+        assert(!waited ||
+               (req->offset == req->overlap_offset &&
+                req->bytes == req->overlap_bytes));
+    } else {
+        bdrv_wait_serialising_requests(req);
     }
 
-    waited = bdrv_wait_serialising_requests(req);
-
-    assert(!waited || !req->serialising ||
-           is_request_serialising_and_aligned(req));
     assert(req->overlap_offset <= offset);
     assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
     assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
@@ -2019,7 +2015,6 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
     padding = bdrv_init_padding(bs, offset, bytes, &pad);
     if (padding) {
         bdrv_mark_request_serialising(req, align);
-        bdrv_wait_serialising_requests(req);
 
         bdrv_padding_rmw_read(child, req, &pad, true);
 
@@ -2122,7 +2117,6 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
 
     if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) {
         bdrv_mark_request_serialising(&req, align);
-        bdrv_wait_serialising_requests(&req);
         bdrv_padding_rmw_read(child, &req, &pad, false);
     }
 

include/block/block_int.h

@@ -999,8 +999,7 @@ extern unsigned int bdrv_drain_all_count;
 void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
 void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
 
-bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self);
+bool coroutine_fn bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align);
-void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align);
 BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs);
 
 int get_tmp_filename(char *filename, int size);