Merge tag 'win32-pull-request' of https://gitlab.com/marcandre.lureau/qemu into staging

[mirror_qemu.git] / block / rbd.c

diff --git a/block/rbd.c b/block/rbd.c
index def96292e0eb17ab94c19e244652fe0568ac1062..f826410f40f94854698156351edbcb468d52d7b6 100644 (file)
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -831,6 +831,26 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
         error_setg_errno(errp, -r, "error opening pool %s", opts->pool);
         goto failed_shutdown;
     }
+
+#ifdef HAVE_RBD_NAMESPACE_EXISTS
+    if (opts->has_q_namespace && strlen(opts->q_namespace) > 0) {
+        bool exists;
+
+        r = rbd_namespace_exists(*io_ctx, opts->q_namespace, &exists);
+        if (r < 0) {
+            error_setg_errno(errp, -r, "error checking namespace");
+            goto failed_ioctx_destroy;
+        }
+
+        if (!exists) {
+            error_setg(errp, "namespace '%s' does not exist",
+                       opts->q_namespace);
+            r = -ENOENT;
+            goto failed_ioctx_destroy;
+        }
+    }
+#endif
+
     /*
      * Set the namespace after opening the io context on the pool,
      * if nspace == NULL or if nspace == "", it is just as we did nothing
@@ -840,6 +860,10 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
     r = 0;
     goto out;
 
+#ifdef HAVE_RBD_NAMESPACE_EXISTS
+failed_ioctx_destroy:
+    rados_ioctx_destroy(*io_ctx);
+#endif
 failed_shutdown:
     rados_shutdown(*cluster);
 out:
@@ -1107,6 +1131,20 @@ static int coroutine_fn qemu_rbd_start_co(BlockDriverState *bs,
 
     assert(!qiov || qiov->size == bytes);
 
+    if (cmd == RBD_AIO_WRITE || cmd == RBD_AIO_WRITE_ZEROES) {
+        /*
+         * RBD APIs don't allow us to write more than actual size, so in order
+         * to support growing images, we resize the image before write
+         * operations that exceed the current size.
+         */
+        if (offset + bytes > s->image_size) {
+            int r = qemu_rbd_resize(bs, offset + bytes);
+            if (r < 0) {
+                return r;
+            }
+        }
+    }
+
     r = rbd_aio_create_completion(&task,
                                   (rbd_callback_t) qemu_rbd_completion_cb, &c);
     if (r < 0) {
@@ -1182,18 +1220,6 @@ coroutine_fn qemu_rbd_co_pwritev(BlockDriverState *bs, int64_t offset,
                                  int64_t bytes, QEMUIOVector *qiov,
                                  BdrvRequestFlags flags)
 {
-    BDRVRBDState *s = bs->opaque;
-    /*
-     * RBD APIs don't allow us to write more than actual size, so in order
-     * to support growing images, we resize the image before write
-     * operations that exceed the current size.
-     */
-    if (offset + bytes > s->image_size) {
-        int r = qemu_rbd_resize(bs, offset + bytes);
-        if (r < 0) {
-            return r;
-        }
-    }
     return qemu_rbd_start_co(bs, offset, bytes, qiov, flags, RBD_AIO_WRITE);
 }
 
@@ -1279,11 +1305,11 @@ static int qemu_rbd_diff_iterate_cb(uint64_t offs, size_t len,
     RBDDiffIterateReq *req = opaque;
 
     assert(req->offs + req->bytes <= offs);
-    /*
-     * we do not diff against a snapshot so we should never receive a callback
-     * for a hole.
-     */
-    assert(exists);
+
+    /* treat a hole like an unallocated area and bail out */
+    if (!exists) {
+        return 0;
+    }
 
     if (!req->exists && offs > req->offs) {
         /*
@@ -1320,6 +1346,7 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
     int status, r;
     RBDDiffIterateReq req = { .offs = offset };
     uint64_t features, flags;
+    uint64_t head = 0;
 
     assert(offset + bytes <= s->image_size);
 
@@ -1347,7 +1374,43 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
         return status;
     }
 
-    r = rbd_diff_iterate2(s->image, NULL, offset, bytes, true, true,
+#if LIBRBD_VERSION_CODE < LIBRBD_VERSION(1, 17, 0)
+    /*
+     * librbd had a bug until early 2022 that affected all versions of ceph that
+     * supported fast-diff. This bug results in reporting of incorrect offsets
+     * if the offset parameter to rbd_diff_iterate2 is not object aligned.
+     * Work around this bug by rounding down the offset to object boundaries.
+     * This is OK because we call rbd_diff_iterate2 with whole_object = true.
+     * However, this workaround only works for non cloned images with default
+     * striping.
+     *
+     * See: https://tracker.ceph.com/issues/53784
+     */
+
+    /* check if RBD image has non-default striping enabled */
+    if (features & RBD_FEATURE_STRIPINGV2) {
+        return status;
+    }
+
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+    /*
+     * check if RBD image is a clone (= has a parent).
+     *
+     * rbd_get_parent_info is deprecated from Nautilus onwards, but the
+     * replacement rbd_get_parent is not present in Luminous and Mimic.
+     */
+    if (rbd_get_parent_info(s->image, NULL, 0, NULL, 0, NULL, 0) != -ENOENT) {
+        return status;
+    }
+#pragma GCC diagnostic pop
+
+    head = req.offs & (s->object_size - 1);
+    req.offs -= head;
+    bytes += head;
+#endif
+
+    r = rbd_diff_iterate2(s->image, NULL, req.offs, bytes, true, true,
                           qemu_rbd_diff_iterate_cb, &req);
     if (r < 0 && r != QEMU_RBD_EXIT_DIFF_ITERATE2) {
         return status;
@@ -1366,7 +1429,8 @@ static int coroutine_fn qemu_rbd_co_block_status(BlockDriverState *bs,
         status = BDRV_BLOCK_ZERO | BDRV_BLOCK_OFFSET_VALID;
     }
 
-    *pnum = req.bytes;
+    assert(req.bytes > head);
+    *pnum = req.bytes - head;
     return status;
 }