linux_dsm_epyc7002/fs/nfs_common/grace.c
Cheng Lin 2deeead49c nfs_common: need lock during iterate through the list
[ Upstream commit 4a9d81caf841cd2c0ae36abec9c2963bf21d0284 ]

If the elem is deleted during be iterated on it, the iteration
process will fall into an endless loop.

kernel: NMI watchdog: BUG: soft lockup - CPU#4 stuck for 22s! [nfsd:17137]

PID: 17137  TASK: ffff8818d93c0000  CPU: 4   COMMAND: "nfsd"
    [exception RIP: __state_in_grace+76]
    RIP: ffffffffc00e817c  RSP: ffff8818d3aefc98  RFLAGS: 00000246
    RAX: ffff881dc0c38298  RBX: ffffffff81b03580  RCX: ffff881dc02c9f50
    RDX: ffff881e3fce8500  RSI: 0000000000000001  RDI: ffffffff81b03580
    RBP: ffff8818d3aefca0   R8: 0000000000000020   R9: ffff8818d3aefd40
    R10: ffff88017fc03800  R11: ffff8818e83933c0  R12: ffff8818d3aefd40
    R13: 0000000000000000  R14: ffff8818e8391068  R15: ffff8818fa6e4000
    CS: 0010  SS: 0018
 #0 [ffff8818d3aefc98] opens_in_grace at ffffffffc00e81e3 [grace]
 #1 [ffff8818d3aefca8] nfs4_preprocess_stateid_op at ffffffffc02a3e6c [nfsd]
 #2 [ffff8818d3aefd18] nfsd4_write at ffffffffc028ed5b [nfsd]
 #3 [ffff8818d3aefd80] nfsd4_proc_compound at ffffffffc0290a0d [nfsd]
 #4 [ffff8818d3aefdd0] nfsd_dispatch at ffffffffc027b800 [nfsd]
 #5 [ffff8818d3aefe08] svc_process_common at ffffffffc02017f3 [sunrpc]
 #6 [ffff8818d3aefe70] svc_process at ffffffffc0201ce3 [sunrpc]
 #7 [ffff8818d3aefe98] nfsd at ffffffffc027b117 [nfsd]
 #8 [ffff8818d3aefec8] kthread at ffffffff810b88c1
 #9 [ffff8818d3aeff50] ret_from_fork at ffffffff816d1607

The troublemake elem:
crash> lock_manager ffff881dc0c38298
struct lock_manager {
  list = {
    next = 0xffff881dc0c38298,
    prev = 0xffff881dc0c38298
  },
  block_opens = false
}

Fixes: c87fb4a378 ("lockd: NLM grace period shouldn't block NFSv4 opens")
Signed-off-by: Cheng Lin <cheng.lin130@zte.com.cn>
Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-12-30 11:53:45 +01:00

144 lines
3.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Common code for control of lockd and nfsv4 grace periods.
*
* Transplanted from lockd code
*/
#include <linux/module.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <linux/fs.h>
static unsigned int grace_net_id;
static DEFINE_SPINLOCK(grace_lock);
/**
* locks_start_grace
* @net: net namespace that this lock manager belongs to
* @lm: who this grace period is for
*
* A grace period is a period during which locks should not be given
* out. Currently grace periods are only enforced by the two lock
* managers (lockd and nfsd), using the locks_in_grace() function to
* check when they are in a grace period.
*
* This function is called to start a grace period.
*/
void
locks_start_grace(struct net *net, struct lock_manager *lm)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
spin_lock(&grace_lock);
if (list_empty(&lm->list))
list_add(&lm->list, grace_list);
else
WARN(1, "double list_add attempt detected in net %x %s\n",
net->ns.inum, (net == &init_net) ? "(init_net)" : "");
spin_unlock(&grace_lock);
}
EXPORT_SYMBOL_GPL(locks_start_grace);
/**
* locks_end_grace
* @net: net namespace that this lock manager belongs to
* @lm: who this grace period is for
*
* Call this function to state that the given lock manager is ready to
* resume regular locking. The grace period will not end until all lock
* managers that called locks_start_grace() also call locks_end_grace().
* Note that callers count on it being safe to call this more than once,
* and the second call should be a no-op.
*/
void
locks_end_grace(struct lock_manager *lm)
{
spin_lock(&grace_lock);
list_del_init(&lm->list);
spin_unlock(&grace_lock);
}
EXPORT_SYMBOL_GPL(locks_end_grace);
static bool
__state_in_grace(struct net *net, bool open)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
struct lock_manager *lm;
if (!open)
return !list_empty(grace_list);
spin_lock(&grace_lock);
list_for_each_entry(lm, grace_list, list) {
if (lm->block_opens) {
spin_unlock(&grace_lock);
return true;
}
}
spin_unlock(&grace_lock);
return false;
}
/**
* locks_in_grace
*
* Lock managers call this function to determine when it is OK for them
* to answer ordinary lock requests, and when they should accept only
* lock reclaims.
*/
bool locks_in_grace(struct net *net)
{
return __state_in_grace(net, false);
}
EXPORT_SYMBOL_GPL(locks_in_grace);
bool opens_in_grace(struct net *net)
{
return __state_in_grace(net, true);
}
EXPORT_SYMBOL_GPL(opens_in_grace);
static int __net_init
grace_init_net(struct net *net)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
INIT_LIST_HEAD(grace_list);
return 0;
}
static void __net_exit
grace_exit_net(struct net *net)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
WARN_ONCE(!list_empty(grace_list),
"net %x %s: grace_list is not empty\n",
net->ns.inum, __func__);
}
static struct pernet_operations grace_net_ops = {
.init = grace_init_net,
.exit = grace_exit_net,
.id = &grace_net_id,
.size = sizeof(struct list_head),
};
static int __init
init_grace(void)
{
return register_pernet_subsys(&grace_net_ops);
}
static void __exit
exit_grace(void)
{
unregister_pernet_subsys(&grace_net_ops);
}
MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>");
MODULE_LICENSE("GPL");
module_init(init_grace)
module_exit(exit_grace)