Revert "NFSD: Defer sub-object cleanup in export put callbacks"

This reverts commit 48db892356d6cb80f6942885545de4a6dd8d2a29.

Commit 48db892356d6 ("NFSD: Defer sub-object cleanup in export
put callbacks") moved path_put() and auth_domain_put() out of
svc_export_put() and expkey_put() and behind queue_rcu_work() to
close a claimed use-after-free in e_show() and c_show() against
ex_path and ex_client->name. Discussion in [1] shows neither
the diagnosis nor the remedy survives review.

The downstream teardown of both sub-objects is already RCU-deferred.
auth_domain_put() reaches svcauth_unix_domain_release(), which frees
the unix_domain and its ->name through call_rcu(). path_put()
reaches dentry_free(), which frees the dentry through call_rcu(),
and prepend_path() is already structured to tolerate concurrent
dentry teardown. A reader in cache_seq_start_rcu() therefore
observes both sub-objects through the next grace period regardless
of whether svc_export_put() runs synchronously, so the synchronous
form was never unsafe.

The crash signature in the report cited by commit 48db892356d6
("NFSD: Defer sub-object cleanup in export put callbacks") has a
different root cause: a /proc/net/rpc cache file held open across
network-namespace exit lets cache_destroy_net() free cd->hash_table
while a reader is still walking it. The correct fix pins cd->net for
the open fd's lifetime and does not require any deferral inside
svc_export_put().

Meanwhile, deferring path_put() out of svc_export_put() reintroduces
the regression that commit 69d803c40ede ("nfsd: Revert "nfsd:
release svc_expkey/svc_export with rcu_work"") repaired: after
"exportfs -r" drops the last cache reference, the mount reference
held through ex_path lingers in the workqueue, so a subsequent
umount fails with EBUSY.

Restore the synchronous path_put() and auth_domain_put() in
svc_export_put() and expkey_put() and the call_rcu()/kfree_rcu()
free of the containing structures. The unrelated fix for
ex_uuid/ex_stats from commit 2530766492ec ("nfsd: fix UAF when
access ex_uuid or ex_stats") is preserved.

Link: https://lore.kernel.org/all/10019b42-4589-4f9f-8d5b-d8197db1ce3c@huawei.com/ [1]
Fixes: 48db892356d6 ("NFSD: Defer sub-object cleanup in export put callbacks")
Cc: stable@vger.kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Alexandr Alexandrov <alexandr.alexandrov@oracle.com>
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

3 files changed, 12 insertions, 66 deletions

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index eb020054f9a3..a47c90f40422 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -39,30 +39,19 @@
  * second map contains a reference to the entry in the first map.
  */
 
-static struct workqueue_struct *nfsd_export_wq;
-
 #define	EXPKEY_HASHBITS		8
 #define	EXPKEY_HASHMAX		(1 << EXPKEY_HASHBITS)
 #define	EXPKEY_HASHMASK		(EXPKEY_HASHMAX -1)
 
-static void expkey_release(struct work_struct *work)
+static void expkey_put(struct kref *ref)
 {
-	struct svc_expkey *key = container_of(to_rcu_work(work),
-					      struct svc_expkey, ek_rwork);
+	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
 
 	if (test_bit(CACHE_VALID, &key->h.flags) &&
 	    !test_bit(CACHE_NEGATIVE, &key->h.flags))
 		path_put(&key->ek_path);
 	auth_domain_put(key->ek_client);
-	kfree(key);
-}
-
-static void expkey_put(struct kref *ref)
-{
-	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
-
-	INIT_RCU_WORK(&key->ek_rwork, expkey_release);
-	queue_rcu_work(nfsd_export_wq, &key->ek_rwork);
+	kfree_rcu(key, ek_rcu);
 }
 
 static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -633,13 +622,11 @@ static void export_stats_destroy(struct export_stats *stats)
 					    EXP_STATS_COUNTERS_NUM);
 }
 
-static void svc_export_release(struct work_struct *work)
+static void svc_export_release(struct rcu_head *rcu_head)
 {
-	struct svc_export *exp = container_of(to_rcu_work(work),
-					      struct svc_export, ex_rwork);
+	struct svc_export *exp = container_of(rcu_head, struct svc_export,
+			ex_rcu);
 
-	path_put(&exp->ex_path);
-	auth_domain_put(exp->ex_client);
 	nfsd4_fslocs_free(&exp->ex_fslocs);
 	export_stats_destroy(exp->ex_stats);
 	kfree(exp->ex_stats);
@@ -651,8 +638,9 @@ static void svc_export_put(struct kref *ref)
 {
 	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
 
-	INIT_RCU_WORK(&exp->ex_rwork, svc_export_release);
-	queue_rcu_work(nfsd_export_wq, &exp->ex_rwork);
+	path_put(&exp->ex_path);
+	auth_domain_put(exp->ex_client);
+	call_rcu(&exp->ex_rcu, svc_export_release);
 }
 
 /**
@@ -2195,36 +2183,6 @@ const struct seq_operations nfs_exports_op = {
 	.show	= e_show,
 };
 
-/**
- * nfsd_export_wq_init - allocate the export release workqueue
- *
- * Called once at module load. The workqueue runs deferred svc_export and
- * svc_expkey release work scheduled by queue_rcu_work() in the cache put
- * callbacks.
- *
- * Return values:
- *   %0: workqueue allocated
- *   %-ENOMEM: allocation failed
- */
-int nfsd_export_wq_init(void)
-{
-	nfsd_export_wq = alloc_workqueue("nfsd_export", WQ_UNBOUND, 0);
-	if (!nfsd_export_wq)
-		return -ENOMEM;
-	return 0;
-}
-
-/**
- * nfsd_export_wq_shutdown - drain and free the export release workqueue
- *
- * Called once at module unload. Per-namespace teardown in
- * nfsd_export_shutdown() has already drained all deferred work.
- */
-void nfsd_export_wq_shutdown(void)
-{
-	destroy_workqueue(nfsd_export_wq);
-}
-
 /*
  * Initialize the exports module.
  */
@@ -2286,9 +2244,6 @@ nfsd_export_shutdown(struct net *net)
 
 	cache_unregister_net(nn->svc_expkey_cache, net);
 	cache_unregister_net(nn->svc_export_cache, net);
-	/* Drain deferred export and expkey release work. */
-	rcu_barrier();
-	flush_workqueue(nfsd_export_wq);
 	cache_destroy_net(nn->svc_expkey_cache, net);
 	cache_destroy_net(nn->svc_export_cache, net);
 	svcauth_unix_purge(net);
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index b05399374574..d2b09cd76145 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -7,7 +7,6 @@
 
 #include <linux/sunrpc/cache.h>
 #include <linux/percpu_counter.h>
-#include <linux/workqueue.h>
 #include <uapi/linux/nfsd/export.h>
 #include <linux/nfs4.h>
 
@@ -76,7 +75,7 @@ struct svc_export {
 	u32			ex_layout_types;
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
-	struct rcu_work		ex_rwork;
+	struct rcu_head		ex_rcu;
 	unsigned long		ex_xprtsec_modes;
 	struct export_stats	*ex_stats;
 };
@@ -93,7 +92,7 @@ struct svc_expkey {
 	u32			ek_fsid[6];
 
 	struct path		ek_path;
-	struct rcu_work		ek_rwork;
+	struct rcu_head		ek_rcu;
 };
 
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
@@ -111,8 +110,6 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
 /*
  * Function declarations
  */
-int			nfsd_export_wq_init(void);
-void			nfsd_export_wq_shutdown(void);
 int			nfsd_export_init(struct net *);
 void			nfsd_export_shutdown(struct net *);
 void			nfsd_export_flush(struct net *);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 92f4c333f0ff..d0486f4a47ba 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2523,12 +2523,9 @@ static int __init init_nfsd(void)
 	if (retval)
 		goto out_free_pnfs;
 	nfsd_lockd_init();	/* lockd->nfsd callbacks */
-	retval = nfsd_export_wq_init();
-	if (retval)
-		goto out_free_lockd;
 	retval = register_pernet_subsys(&nfsd_net_ops);
 	if (retval < 0)
-		goto out_free_export_wq;
+		goto out_free_lockd;
 	retval = register_cld_notifier();
 	if (retval)
 		goto out_free_subsys;
@@ -2557,8 +2554,6 @@ out_free_cld:
 	unregister_cld_notifier();
 out_free_subsys:
 	unregister_pernet_subsys(&nfsd_net_ops);
-out_free_export_wq:
-	nfsd_export_wq_shutdown();
 out_free_lockd:
 	nfsd_lockd_shutdown();
 	nfsd_drc_slab_free();
@@ -2579,7 +2574,6 @@ static void __exit exit_nfsd(void)
 	nfsd4_destroy_laundry_wq();
 	unregister_cld_notifier();
 	unregister_pernet_subsys(&nfsd_net_ops);
-	nfsd_export_wq_shutdown();
 	nfsd_drc_slab_free();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();