Bug 1451083

Description of problem:

Regression test failure :

https://build.gluster.org/job/centos6-regression/4602/console


14:09:32 Result: PASS
14:09:32 ./tests/bugs/replicate/bug-765564.t: 1 new core files
14:09:32 End of test ./tests/bugs/replicate/bug-765564.t
14:09:32 ====================================================




14:09:33 Thread 1 (Thread 0x7f0d6a42d700 (LWP 2661)):
14:09:33 #0  0x00007f0d692d8101 in dht_rmdir_do (frame=0x7f0d54001ca0, this=0x7f0d6400e2e0) at /home/jenkins/root/workspace/centos6-regression/xlators/cluster/dht/src/dht-common.c:8058
14:09:33         local = 0x0
14:09:33         conf = 0x7f0d64033820
14:09:33         ret = -1
14:09:33         hashed_subvol = 0x0
14:09:33         gfid = '\000' <repeats 49 times>
14:09:33         __FUNCTION__ = "dht_rmdir_do"
14:09:33 #1  0x00007f0d692db3af in dht_rmdir_opendir_cbk (frame=0x7f0d54001ca0, cookie=0x7f0d6400c920, this=0x7f0d6400e2e0, op_ret=0, op_errno=117, fd=0x7f0d5400c3a0, xdata=0x0) at /home/jenkins/root/workspace/centos6-regression/xlators/cluster/dht/src/dht-common.c:8671
14:09:33         local = 0x7f0d54018500
14:09:33         this_call_cnt = 0
14:09:33         prev = 0x7f0d6400c920
14:09:33         ret = 0
14:09:33         conf = 0x7f0d64033820
14:09:33         dict = 0x7f0d640015b0
14:09:33         i = 1
14:09:33         gfid = '\000' <repeats 49 times>
14:09:33         readdirp_local = 0x7f0d64062eb0
14:09:33         readdirp_frame = 0x7f0d64053d10
14:09:33         __FUNCTION__ = "dht_rmdir_opendir_cbk"
14:09:33 #2  0x00007f0d6952ba79 in afr_opendir_cbk (frame=0x7f0d54008d90, cookie=0x0, this=0x7f0d6400c920, op_ret=0, op_errno=22, fd=0x7f0d5400c3a0, xdata=0x0) at /home/jenkins/root/workspace/centos6-regression/xlators/cluster/afr/src/afr-dir-read.c:69
14:09:33         fn = 0x7f0d692dac18 <dht_rmdir_opendir_cbk>
14:09:33         _parent = 0x7f0d54001ca0
14:09:33         old_THIS = 0x7f0d6400c920
14:09:33         __local = 0x7f0d54003ae0
14:09:33         __this = 0x7f0d6400c920
14:09:33         __op_ret = 0
14:09:33         __op_errno = 117
14:09:33         local = 0x7f0d54003ae0
14:09:33         call_count = 0
14:09:33         child_index = 0
14:09:33         fd_ctx = 0x7f0d5403bab0
14:09:33         __FUNCTION__ = "afr_opendir_cbk"
14:09:33 #3  0x00007f0d697f813f in client3_3_opendir_cbk (req=0x7f0d540099b0, iov=0x7f0d540099f0, count=1, myframe=0x7f0d5400bf90) at /home/jenkins/root/workspace/centos6-regression/xlators/protocol/client/src/client-rpc-fops.c:2771
14:09:33         fn = 0x7f0d6952b58f <afr_opendir_cbk>
14:09:33         _parent = 0x7f0d54008d90
14:09:33         old_THIS = 0x7f0d64007a70
14:09:33         __local = 0x7f0d54008ea0
14:09:33         local = 0x7f0d54008ea0
14:09:33         frame = 0x7f0d5400bf90
14:09:33         fd = 0x7f0d5400c3a0
14:09:33         ret = 0
14:09:33         rsp = {op_ret = 0, op_errno = 22, fd = 0, xdata = {xdata_len = 0, xdata_val = 0x0}}
14:09:33         this = 0x7f0d64007a70
14:09:33         xdata = 0x0
14:09:33         __FUNCTION__ = "client3_3_opendir_cbk"




Thanks to Shyam for the analysis:

In dht_rmdir_opendir_cbk

      for (i = 0; i < conf->subvolume_cnt; i++) {

                readdirp_frame = copy_frame (frame);

                if (!readdirp_frame) {
                        local->call_cnt--;
                        continue;
                }

                readdirp_local = dht_local_init (readdirp_frame, &local->loc,
                                                 local->fd, 0);

                if (!readdirp_local) {
                        DHT_STACK_DESTROY (readdirp_frame);
                        local->call_cnt--;
                        continue;
                }
                readdirp_local->main_frame = frame;
                readdirp_local->op_ret = 0;
                readdirp_local->xattr = dict_ref (dict);
                /* overload this field to save the subvol info */
                readdirp_local->hashed_subvol = conf->subvolumes[i];

                STACK_WIND_COOKIE (readdirp_frame, dht_rmdir_readdirp_cbk,
                                   conf->subvolumes[i], conf->subvolumes[i],
                                   conf->subvolumes[i]->fops->readdirp,
                                   readdirp_local->fd, 4096, 0,
                                   readdirp_local->xattr);
        }

        if (dict)
                dict_unref (dict);

        /* Could not wind readdirp to any subvol */
        if (!local->call_cnt)
                goto err;

        return 0;

err:
        if (is_last_call (this_call_cnt)) {
                dht_rmdir_do (frame, this);
        }

        return 0;
}


If the dht_rmdir_readdirp_cbk unwinds before the check for the local->call_cnt, this could still hit dht_rmdir_do. At this point, the frame contents might no longer be valid.




Version-Release number of selected component (if applicable):


How reproducible:


Steps to Reproduce:
1.
2.
3.

Actual results:


Expected results:


Additional info: