nfs: fix a deadlock in nfs client initialization
The following deadlock can occur between a process waiting for a client to initialize in while walking the client list during nfsv4 server trunking detection and another process waiting for the nfs_clid_init_mutex so it can initialize that client: Process 1 Process 2 --------- --------- spin_lock(&nn->nfs_client_lock); list_add_tail(&CLIENTA->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); spin_lock(&nn->nfs_client_lock); list_add_tail(&CLIENTB->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); mutex_lock(&nfs_clid_init_mutex); nfs41_walk_client_list(clp, result, cred); nfs_wait_client_init_complete(CLIENTA); (waiting for nfs_clid_init_mutex) Make sure nfs_match_client() only evaluates clients that have completed initialization in order to prevent that deadlock. This patch also fixes v4.0 trunking behavior by not marking the client NFS_CS_READY until the clientid has been confirmed. Signed-off-by: Scott Mayhew <smayhew@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This commit is contained in:
parent
eb5b46faa6
commit
c156618e15
|
@ -291,12 +291,23 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
|
|||
const struct sockaddr *sap = data->addr;
|
||||
struct nfs_net *nn = net_generic(data->net, nfs_net_id);
|
||||
|
||||
again:
|
||||
list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
|
||||
const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
|
||||
/* Don't match clients that failed to initialise properly */
|
||||
if (clp->cl_cons_state < 0)
|
||||
continue;
|
||||
|
||||
/* If a client is still initializing then we need to wait */
|
||||
if (clp->cl_cons_state > NFS_CS_READY) {
|
||||
refcount_inc(&clp->cl_count);
|
||||
spin_unlock(&nn->nfs_client_lock);
|
||||
nfs_wait_client_init_complete(clp);
|
||||
nfs_put_client(clp);
|
||||
spin_lock(&nn->nfs_client_lock);
|
||||
goto again;
|
||||
}
|
||||
|
||||
/* Different NFS versions cannot share the same nfs_client */
|
||||
if (clp->rpc_ops != data->nfs_mod->rpc_ops)
|
||||
continue;
|
||||
|
|
|
@ -404,15 +404,19 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
|
|||
if (error < 0)
|
||||
goto error;
|
||||
|
||||
if (!nfs4_has_session(clp))
|
||||
nfs_mark_client_ready(clp, NFS_CS_READY);
|
||||
|
||||
error = nfs4_discover_server_trunking(clp, &old);
|
||||
if (error < 0)
|
||||
goto error;
|
||||
|
||||
if (clp != old)
|
||||
if (clp != old) {
|
||||
clp->cl_preserve_clid = true;
|
||||
/*
|
||||
* Mark the client as having failed initialization so other
|
||||
* processes walking the nfs_client_list in nfs_match_client()
|
||||
* won't try to use it.
|
||||
*/
|
||||
nfs_mark_client_ready(clp, -EPERM);
|
||||
}
|
||||
nfs_put_client(clp);
|
||||
clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags);
|
||||
return old;
|
||||
|
@ -539,6 +543,9 @@ int nfs40_walk_client_list(struct nfs_client *new,
|
|||
spin_lock(&nn->nfs_client_lock);
|
||||
list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
|
||||
|
||||
if (pos == new)
|
||||
goto found;
|
||||
|
||||
status = nfs4_match_client(pos, new, &prev, nn);
|
||||
if (status < 0)
|
||||
goto out_unlock;
|
||||
|
@ -559,6 +566,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
|
|||
* way that a SETCLIENTID_CONFIRM to pos can succeed is
|
||||
* if new and pos point to the same server:
|
||||
*/
|
||||
found:
|
||||
refcount_inc(&pos->cl_count);
|
||||
spin_unlock(&nn->nfs_client_lock);
|
||||
|
||||
|
@ -572,6 +580,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
|
|||
case 0:
|
||||
nfs4_swap_callback_idents(pos, new);
|
||||
pos->cl_confirm = new->cl_confirm;
|
||||
nfs_mark_client_ready(pos, NFS_CS_READY);
|
||||
|
||||
prev = NULL;
|
||||
*result = pos;
|
||||
|
|
Loading…
Reference in New Issue