lkml.org 
[lkml]   [2021]   [Jun]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 5.10 121/131] NFSv4: Fix deadlock between nfs4_evict_inode() and nfs4_opendata_get_inode()
Date
From: Trond Myklebust <trond.myklebust@hammerspace.com>

[ Upstream commit dfe1fe75e00e4c724ede7b9e593f6f680e446c5f ]

If the inode is being evicted, but has to return a delegation first,
then it can cause a deadlock in the corner case where the server reboots
before the delegreturn completes, but while the call to iget5_locked() in
nfs4_opendata_get_inode() is waiting for the inode free to complete.
Since the open call still holds a session slot, the reboot recovery
cannot proceed.

In order to break the logjam, we can turn the delegation return into a
privileged operation for the case where we're evicting the inode. We
know that in that case, there can be no other state recovery operation
that conflicts.

Reported-by: zhangxiaoxu (A) <zhangxiaoxu5@huawei.com>
Fixes: 5fcdfacc01f3 ("NFSv4: Return delegations synchronously in evict_inode")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
fs/nfs/nfs4_fs.h | 1 +
fs/nfs/nfs4proc.c | 12 +++++++++++-
2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 065cb04222a1..543d916f79ab 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -205,6 +205,7 @@ struct nfs4_exception {
struct inode *inode;
nfs4_stateid *stateid;
long timeout;
+ unsigned char task_is_privileged : 1;
unsigned char delay : 1,
recovering : 1,
retry : 1;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c92d6ff0fcea..959c2aa2180d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -592,6 +592,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
goto out_retry;
}
if (exception->recovering) {
+ if (exception->task_is_privileged)
+ return -EDEADLOCK;
ret = nfs4_wait_clnt_recover(clp);
if (test_bit(NFS_MIG_FAILED, &server->mig_status))
return -EIO;
@@ -617,6 +619,8 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
goto out_retry;
}
if (exception->recovering) {
+ if (exception->task_is_privileged)
+ return -EDEADLOCK;
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
@@ -6383,6 +6387,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
struct nfs4_exception exception = {
.inode = data->inode,
.stateid = &data->stateid,
+ .task_is_privileged = data->args.seq_args.sa_privileged,
};

if (!nfs4_sequence_done(task, &data->res.seq_res))
@@ -6506,7 +6511,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
data = kzalloc(sizeof(*data), GFP_NOFS);
if (data == NULL)
return -ENOMEM;
- nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0);

nfs4_state_protect(server->nfs_client,
NFS_SP4_MACH_CRED_CLEANUP,
@@ -6537,6 +6541,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
}
}

+ if (!data->inode)
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+ 1);
+ else
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+ 0);
task_setup_data.callback_data = data;
msg.rpc_argp = &data->args;
msg.rpc_resp = &data->res;
--
2.30.2


\
 
 \ /
  Last update: 2021-06-14 13:20    [W:0.415 / U:0.508 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site