Bruce reported seeing this warning pop when mounting using v4.1:
------------[ cut here ]------------
WARNING: CPU: 1 PID: 1121 at kernel/sched/core.c:7300 __might_sleep+0xbd/0xd0()
do not call blocking ops when !TASK_RUNNING; state=1 set at [<
ffffffff810ff58f>] prepare_to_wait+0x2f/0x90
Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace sunrpc fscache ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hwdep snd_pcm snd_timer ppdev joydev snd virtio_console virtio_balloon pcspkr serio_raw parport_pc parport pvpanic floppy soundcore i2c_piix4 virtio_blk virtio_net qxl drm_kms_helper ttm drm virtio_pci virtio_ring ata_generic virtio pata_acpi
CPU: 1 PID: 1121 Comm: nfsv4.1-svc Not tainted 3.19.0-rc4+ #25
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140709_153950- 04/01/2014
0000000000000000 000000004e5e3f73 ffff8800b998fb48 ffffffff8186ac78
0000000000000000 ffff8800b998fba0 ffff8800b998fb88 ffffffff810ac9da
ffff8800b998fb68 ffffffff81c923e7 00000000000004d9 0000000000000000
Call Trace:
[<
ffffffff8186ac78>] dump_stack+0x4c/0x65
[<
ffffffff810ac9da>] warn_slowpath_common+0x8a/0xc0
[<
ffffffff810aca65>] warn_slowpath_fmt+0x55/0x70
[<
ffffffff810ff58f>] ? prepare_to_wait+0x2f/0x90
[<
ffffffff810ff58f>] ? prepare_to_wait+0x2f/0x90
[<
ffffffff810dd2ad>] __might_sleep+0xbd/0xd0
[<
ffffffff8124c973>] kmem_cache_alloc_trace+0x243/0x430
[<
ffffffff810d941e>] ? groups_alloc+0x3e/0x130
[<
ffffffff810d941e>] groups_alloc+0x3e/0x130
[<
ffffffffa0301b1e>] svcauth_unix_accept+0x16e/0x290 [sunrpc]
[<
ffffffffa0300571>] svc_authenticate+0xe1/0xf0 [sunrpc]
[<
ffffffffa02fc564>] svc_process_common+0x244/0x6a0 [sunrpc]
[<
ffffffffa02fd044>] bc_svc_process+0x1c4/0x260 [sunrpc]
[<
ffffffffa03d5478>] nfs41_callback_svc+0x128/0x1f0 [nfsv4]
[<
ffffffff810ff970>] ? wait_woken+0xc0/0xc0
[<
ffffffffa03d5350>] ? nfs4_callback_svc+0x60/0x60 [nfsv4]
[<
ffffffff810d45bf>] kthread+0x11f/0x140
[<
ffffffff810ea815>] ? local_clock+0x15/0x30
[<
ffffffff810d44a0>] ? kthread_create_on_node+0x250/0x250
[<
ffffffff81874bfc>] ret_from_fork+0x7c/0xb0
[<
ffffffff810d44a0>] ? kthread_create_on_node+0x250/0x250
---[ end trace
675220a11e30f4f2 ]---
nfs41_callback_svc does most of its work while in TASK_INTERRUPTIBLE,
which is just wrong. Fix that by finishing the wait immediately if we've
found that the list has something on it.
Also, we don't expect this kthread to accept signals, so we should be
using a TASK_UNINTERRUPTIBLE sleep instead. That however, opens us up
hung task warnings from the watchdog, so have the schedule_timeout
wake up every 60s if there's no callback activity.
Reported-by: "J. Bruce Fields" <bfields@fieldses.org>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
if (try_to_freeze())
continue;
- prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+ prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
spin_lock_bh(&serv->sv_cb_lock);
if (!list_empty(&serv->sv_cb_list)) {
req = list_first_entry(&serv->sv_cb_list,
struct rpc_rqst, rq_bc_list);
list_del(&req->rq_bc_list);
spin_unlock_bh(&serv->sv_cb_lock);
+ finish_wait(&serv->sv_cb_waitq, &wq);
dprintk("Invoking bc_svc_process()\n");
error = bc_svc_process(serv, req, rqstp);
dprintk("bc_svc_process() returned w/ error code= %d\n",
error);
} else {
spin_unlock_bh(&serv->sv_cb_lock);
- schedule();
+ /* schedule_timeout to game the hung task watchdog */
+ schedule_timeout(60 * HZ);
+ finish_wait(&serv->sv_cb_waitq, &wq);
}
- finish_wait(&serv->sv_cb_waitq, &wq);
}
return 0;
}