block, block-backend: write some hot coroutine wrappers by hand

The introduction of the graph lock is causing blk_get_geometry, a hot function
used in the I/O path, to create a coroutine.  However, the only part that really
needs to run in coroutine context is the call to bdrv_co_refresh_total_sectors,
which in turn only happens in the rare case of host CD-ROM devices.

So, write by hand the three wrappers on the path from blk_co_get_geometry to
bdrv_co_refresh_total_sectors, so that the coroutine wrapper is only created
if bdrv_nb_sectors actually calls bdrv_refresh_total_sectors.

Reported-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20230407153303.391121-9-pbonzini@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

block.c

@@ -5859,6 +5859,28 @@ int64_t coroutine_fn bdrv_co_nb_sectors(BlockDriverState *bs)
     return bs->total_sectors;
 }
 
+/*
+ * This wrapper is written by hand because this function is in the hot I/O path,
+ * via blk_get_geometry.
+ */
+int64_t coroutine_mixed_fn bdrv_nb_sectors(BlockDriverState *bs)
+{
+    BlockDriver *drv = bs->drv;
+    IO_CODE();
+
+    if (!drv)
+        return -ENOMEDIUM;
+
+    if (bs->bl.has_variable_length) {
+        int ret = bdrv_refresh_total_sectors(bs, bs->total_sectors);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
+    return bs->total_sectors;
+}
+
 /**
  * Return length in bytes on success, -errno on error.
  * The length is always a multiple of BDRV_SECTOR_SIZE.

block/block-backend.c

@@ -1629,6 +1629,23 @@ int64_t coroutine_fn blk_co_nb_sectors(BlockBackend *blk)
     }
 }
 
+/*
+ * This wrapper is written by hand because this function is in the hot I/O path,
+ * via blk_get_geometry.
+ */
+int64_t coroutine_mixed_fn blk_nb_sectors(BlockBackend *blk)
+{
+    BlockDriverState *bs = blk_bs(blk);
+
+    IO_CODE();
+
+    if (!bs) {
+        return -ENOMEDIUM;
+    } else {
+        return bdrv_nb_sectors(bs);
+    }
+}
+
 /* return 0 as number of sectors if no device present or error */
 void coroutine_fn blk_co_get_geometry(BlockBackend *blk,
                                       uint64_t *nb_sectors_ptr)
@@ -1637,6 +1654,16 @@ void coroutine_fn blk_co_get_geometry(BlockBackend *blk,
     *nb_sectors_ptr = ret < 0 ? 0 : ret;
 }
 
+/*
+ * This wrapper is written by hand because this function is in the hot I/O path.
+ */
+void coroutine_mixed_fn blk_get_geometry(BlockBackend *blk,
+                                         uint64_t *nb_sectors_ptr)
+{
+    int64_t ret = blk_nb_sectors(blk);
+    *nb_sectors_ptr = ret < 0 ? 0 : ret;
+}
+
 BlockAIOCB *blk_aio_preadv(BlockBackend *blk, int64_t offset,
                            QEMUIOVector *qiov, BdrvRequestFlags flags,
                            BlockCompletionFunc *cb, void *opaque)

include/block/block-io.h

@@ -79,7 +79,7 @@ bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
                  PreallocMode prealloc, BdrvRequestFlags flags, Error **errp);
 
 int64_t coroutine_fn GRAPH_RDLOCK bdrv_co_nb_sectors(BlockDriverState *bs);
-int64_t co_wrapper_mixed_bdrv_rdlock bdrv_nb_sectors(BlockDriverState *bs);
+int64_t coroutine_mixed_fn bdrv_nb_sectors(BlockDriverState *bs);
 
 int64_t coroutine_fn GRAPH_RDLOCK bdrv_co_getlength(BlockDriverState *bs);
 int64_t co_wrapper_mixed_bdrv_rdlock bdrv_getlength(BlockDriverState *bs);

include/sysemu/block-backend-io.h

@@ -72,11 +72,10 @@ int64_t co_wrapper_mixed blk_getlength(BlockBackend *blk);
 
 void coroutine_fn blk_co_get_geometry(BlockBackend *blk,
                                       uint64_t *nb_sectors_ptr);
-void co_wrapper_mixed blk_get_geometry(BlockBackend *blk,
-                                       uint64_t *nb_sectors_ptr);
+void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr);
 
 int64_t coroutine_fn blk_co_nb_sectors(BlockBackend *blk);
-int64_t co_wrapper_mixed blk_nb_sectors(BlockBackend *blk);
+int64_t blk_nb_sectors(BlockBackend *blk);
 
 void *blk_try_blockalign(BlockBackend *blk, size_t size);
 void *blk_blockalign(BlockBackend *blk, size_t size);