| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20150814174354.492845501@linuxfoundation.org>
Date: Fri, 14 Aug 2015 10:44:58 -0700
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Alex Elder <elder@...aro.org>,
Ilya Dryomov <idryomov@...il.com>
Subject: [PATCH 3.10 20/35] rbd: fix copyup completion race
3.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ilya Dryomov <idryomov@...il.com>
commit 2761713d35e370fd640b5781109f753066b746c4 upstream.
For write/discard obj_requests that involved a copyup method call, the
opcode of the first op is CEPH_OSD_OP_CALL and the ->callback is
rbd_img_obj_copyup_callback(). The latter frees copyup pages, sets
->xferred and delegates to rbd_img_obj_callback(), the "normal" image
object callback, for reporting to block layer and putting refs.
rbd_osd_req_callback() however treats CEPH_OSD_OP_CALL as a trivial op,
which means obj_request is marked done in rbd_osd_trivial_callback(),
*before* ->callback is invoked and rbd_img_obj_copyup_callback() has
a chance to run. Marking obj_request done essentially means giving
rbd_img_obj_callback() a license to end it at any moment, so if another
obj_request from the same img_request is being completed concurrently,
rbd_img_obj_end_request() may very well be called on such prematurally
marked done request:
<obj_request-1/2 reply>
handle_reply()
rbd_osd_req_callback()
rbd_osd_trivial_callback()
rbd_obj_request_complete()
rbd_img_obj_copyup_callback()
rbd_img_obj_callback()
<obj_request-2/2 reply>
handle_reply()
rbd_osd_req_callback()
rbd_osd_trivial_callback()
for_each_obj_request(obj_request->img_request) {
rbd_img_obj_end_request(obj_request-1/2)
rbd_img_obj_end_request(obj_request-2/2) <--
}
Calling rbd_img_obj_end_request() on such a request leads to trouble,
in particular because its ->xfferred is 0. We report 0 to the block
layer with blk_update_request(), get back 1 for "this request has more
data in flight" and then trip on
rbd_assert(more ^ (which == img_request->obj_request_count));
with rhs (which == ...) being 1 because rbd_img_obj_end_request() has
been called for both requests and lhs (more) being 1 because we haven't
got a chance to set ->xfferred in rbd_img_obj_copyup_callback() yet.
To fix this, leverage that rbd wants to call class methods in only two
cases: one is a generic method call wrapper (obj_request is standalone)
and the other is a copyup (obj_request is part of an img_request). So
make a dedicated handler for CEPH_OSD_OP_CALL and directly invoke
rbd_img_obj_copyup_callback() from it if obj_request is part of an
img_request, similar to how CEPH_OSD_OP_READ handler invokes
rbd_img_obj_request_read_callback().
Since rbd_img_obj_copyup_callback() is now being called from the OSD
request callback (only), it is renamed to rbd_osd_copyup_callback().
Cc: Alex Elder <elder@...aro.org>
Signed-off-by: Ilya Dryomov <idryomov@...il.com>
Reviewed-by: Alex Elder <elder@...aro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
drivers/block/rbd.c | 22 +++++++++++++++++-----
1 file changed, 17 insertions(+), 5 deletions(-)
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -457,6 +457,7 @@ void rbd_warn(struct rbd_device *rbd_dev
# define rbd_assert(expr) ((void) 0)
#endif /* !RBD_DEBUG */
+static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request);
static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request);
static void rbd_img_parent_read(struct rbd_obj_request *obj_request);
static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
@@ -1670,6 +1671,16 @@ static void rbd_osd_stat_callback(struct
obj_request_done_set(obj_request);
}
+static void rbd_osd_call_callback(struct rbd_obj_request *obj_request)
+{
+ dout("%s: obj %p\n", __func__, obj_request);
+
+ if (obj_request_img_data_test(obj_request))
+ rbd_osd_copyup_callback(obj_request);
+ else
+ obj_request_done_set(obj_request);
+}
+
static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
struct ceph_msg *msg)
{
@@ -1708,6 +1719,8 @@ static void rbd_osd_req_callback(struct
rbd_osd_stat_callback(obj_request);
break;
case CEPH_OSD_OP_CALL:
+ rbd_osd_call_callback(obj_request);
+ break;
case CEPH_OSD_OP_NOTIFY_ACK:
case CEPH_OSD_OP_WATCH:
rbd_osd_trivial_callback(obj_request);
@@ -2305,13 +2318,15 @@ out_unwind:
}
static void
-rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
+rbd_osd_copyup_callback(struct rbd_obj_request *obj_request)
{
struct rbd_img_request *img_request;
struct rbd_device *rbd_dev;
struct page **pages;
u32 page_count;
+ dout("%s: obj %p\n", __func__, obj_request);
+
rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
rbd_assert(obj_request_img_data_test(obj_request));
img_request = obj_request->img_request;
@@ -2337,9 +2352,7 @@ rbd_img_obj_copyup_callback(struct rbd_o
if (!obj_request->result)
obj_request->xferred = obj_request->length;
- /* Finish up with the normal image object callback */
-
- rbd_img_obj_callback(obj_request);
+ obj_request_done_set(obj_request);
}
static void
@@ -2436,7 +2449,6 @@ rbd_img_obj_parent_read_full_callback(st
/* All set, send it off. */
- orig_request->callback = rbd_img_obj_copyup_callback;
osdc = &rbd_dev->rbd_client->client->osdc;
img_result = rbd_obj_request_submit(osdc, orig_request);
if (!img_result)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists