diff mbox series

[V2,for-6.2,2/2] block/rbd: workaround for ceph issue #53784

Message ID 20220113144426.4036493-3-pl@kamp.de
State New
Headers show
Series fixes for bdrv_co_block_status | expand

Commit Message

Peter Lieven Jan. 13, 2022, 2:44 p.m. UTC
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.

This patch works around this bug for pre Quincy versions of librbd.

Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
---
 block/rbd.c | 42 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

Comments

Ilya Dryomov Jan. 14, 2022, 10:57 a.m. UTC | #1
On Thu, Jan 13, 2022 at 3:44 PM Peter Lieven <pl@kamp.de> wrote:
>
> 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.
>
> This patch works around this bug for pre Quincy versions of librbd.
>
> Cc: qemu-stable@nongnu.org
> Signed-off-by: Peter Lieven <pl@kamp.de>
> ---
>  block/rbd.c | 42 ++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 40 insertions(+), 2 deletions(-)
>
> diff --git a/block/rbd.c b/block/rbd.c
> index 20bb896c4a..d174d51659 100644
> --- a/block/rbd.c
> +++ b/block/rbd.c
> @@ -1320,6 +1320,7 @@ 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 +1348,43 @@ 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 */

Nit: extra space

Thanks,

                Ilya
Stefano Garzarella Jan. 17, 2022, 2:23 p.m. UTC | #2
On Thu, Jan 13, 2022 at 03:44:26PM +0100, Peter Lieven wrote:
>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.
>
>This patch works around this bug for pre Quincy versions of librbd.
>

I'm not sure, but maybe we could add the fixes tag also to this patch, 
since without this workaround we can have issues with buggy librbd.

Fixes: 0347a8fd4c3faaedf119be04c197804be40a384b

>Cc: qemu-stable@nongnu.org
>Signed-off-by: Peter Lieven <pl@kamp.de>
>---
> block/rbd.c | 42 ++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 40 insertions(+), 2 deletions(-)

Tested-by: Stefano Garzarella <sgarzare@redhat.com>


>
>diff --git a/block/rbd.c b/block/rbd.c
>index 20bb896c4a..d174d51659 100644
>--- a/block/rbd.c
>+++ b/block/rbd.c
>@@ -1320,6 +1320,7 @@ 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 +1348,43 @@ 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 +1403,8 @@ 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;
> }
>
>-- 
>2.25.1
>
>
>
diff mbox series

Patch

diff --git a/block/rbd.c b/block/rbd.c
index 20bb896c4a..d174d51659 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -1320,6 +1320,7 @@  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 +1348,43 @@  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 +1403,8 @@  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;
 }