libceph: avoid using freed osd in __kick_osd_requests()

If an osd has no requests and no linger requests, __reset_osd()
will just remove it with a call to __remove_osd().  That drops
a reference to the osd, and therefore the osd may have been free
by the time __reset_osd() returns.  That function offers no
indication this may have occurred, and as a result the osd will
continue to be used even when it's no longer valid.

Change__reset_osd() so it returns an error (ENODEV) when it
deletes the osd being reset.  And change __kick_osd_requests() so it
returns immediately (before referencing osd again) if __reset_osd()
returns *any* error.

Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ac7be72..60c74c1 100644 (file)
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -581,7 +581,7 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc,
 
        dout("__kick_osd_requests osd%d\n", osd->o_osd);
        err = __reset_osd(osdc, osd);
-       if (err == -EAGAIN)
+       if (err)
                return;
 
        list_for_each_entry(req, &osd->o_requests, r_osd_item) {
@@ -745,6 +745,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
        if (list_empty(&osd->o_requests) &&
            list_empty(&osd->o_linger_requests)) {
                __remove_osd(osdc, osd);
+               ret = -ENODEV;
        } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd],
                          &osd->o_con.peer_addr,
                          sizeof(osd->o_con.peer_addr)) == 0 &&