[PATCH v2] nfsd: prevent a double put of revoked layout stateids

[Jinpyo Lee <bint4b13@gmail.com>]

nfsd4_free_stateid() finds an admin-revoked layout stateid with
find_stateid_locked(), which does not acquire a reference. The layout
case drops cl_lock without marking the stateid closed, then stops fence
work and calls nfs4_put_stid() without owning a reference. Concurrent
disposal can therefore access a freed layout stateid or drop a reference
owned by another holder.

Mark the layout stateid CLOSED under cl_lock so only one disposal caller
proceeds. Take a temporary reference before dropping cl_lock and hold it
while stopping fence work and draining the remaining layout segments,
then release that reference with the final put. This keeps the stateid
alive even though its IDR owns no reference and its layout segments are
being removed.

Use cl_lock for the CLOSED update in LAYOUTRETURN as well, matching the
common stateid locking rule. Retain ls_mutex from the last segment removal
through the CLOSED update, and recheck CLOSED under cl_lock after taking
ls_mutex in LAYOUTGET. This prevents a stale LAYOUTGET from adding a
segment after the drain. Also make the newly allocated layout stateid the
error-path put target and update the status-locking comment.

Restrict nfs40_clean_admin_revoked() to NFSv4.0 clients. Its timer is
armed only by v4.0 revocations, while session clients dispose of revoked
stateids through FREE_STATEID. Skipping session clients prevents the scan
from repeatedly selecting a CLOSED stateid that remains in the IDR while
an in-flight operation holds a reference.

The vulnerability research and validation were conducted by members of
the Tobabz team as part of the Best of the Best 15th program.

Fixes: 86b9898920a6 ("NFSD: Handle layout stid in nfsd4_drop_revoked_stid()")
Suggested-by: Chuck Lever <cel@kernel.org>
Cc: stable@vger.kernel.org
Assisted-by: LLM
Signed-off-by: Jinpyo Lee <bint4b13@gmail.com>
---
Changes since v1:
- Address Jeff Layton's concern by using cl_lock for layout CLOSED
  checks and updates, without a type-dependent stateid status helper.
- Move LAYOUTRETURN's CLOSED update outside ls_lock while retaining
  ls_mutex, and update the status-locking documentation.
- Clarify the LAYOUTGET serialization and v4.0 cleanup restriction.
- Credit Chuck Lever's suggestion and mark the fix for stable review.
- Rebase onto nfsd-testing c807415bc69013a5f162264ee0e14f8742c182f7.

Validated on the above nfsd-testing base (2026-10-13):
- Applied cleanly, passed strict checkpatch, and built and booted an x86_64
  kernel with GCC 13.3, W=1, Generic KASAN, lockdep, and pNFS block and
  SCSI layouts enabled.
- Loopback pNFS SCSI read, shrink, integrity, revocation, and cleanup tests
  passed, as did NFSv4.2, NFSv4.0, and NFSv3 read/write, fio CRC32C, and
  unmount tests. Tracing observed two successful LAYOUTRETURNs reach the
  modified CLOSED update and release their stateids.
- Two concurrent FREE_STATEID requests from different slots of one NFSv4.1
  session returned one success and one NFS4ERR_BAD_STATEID. A test-only
  two-second pause forced the losing request into the disposal window;
  tracing observed CLOSED, exactly one revoked-layout drain, and one
  layout-state free.
- No KASAN, lockdep, refcount, list-corruption, WARNING, or Oops report
  occurred, and kernel taint remained zero through fixture cleanup.

Build note: Existing format-truncation warnings in target_core_transport.c
were excluded from WERROR; W=1 and WERROR remained enabled otherwise.

The full xfstests suite was not run. Earlier v1 runtime results are not
used as validation of this revision.

 fs/nfsd/nfs4layouts.c | 34 ++++++++++++++++++++++++++++++++--
 fs/nfsd/nfs4state.c   | 14 ++++++++++++++
 fs/nfsd/pnfs.h        |  6 ++++++
 fs/nfsd/state.h       |  5 ++---
 4 files changed, 54 insertions(+), 5 deletions(-)

diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 898776c9d..749ace97e 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -312,6 +312,7 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		status = nfserr_jukebox;
 		if (!ls)
 			goto out;
+		stid = &ls->ls_stid;
 		mutex_lock(&ls->ls_mutex);
 	} else {
 		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
@@ -324,6 +325,15 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 			goto out_unlock_stid;
 	}
 
+	/* A new or looked-up stateid may have been closed before ls_mutex. */
+	spin_lock(&stid->sc_client->cl_lock);
+	if (stid->sc_status & SC_STATUS_CLOSED) {
+		spin_unlock(&stid->sc_client->cl_lock);
+		status = nfserr_bad_stateid;
+		goto out_unlock_stid;
+	}
+	spin_unlock(&stid->sc_client->cl_lock);
+
 	*lsp = ls;
 	return 0;
 
@@ -537,12 +547,18 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
 			nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid);
 		lrp->lrs_present = true;
 	} else {
-		trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid);
-		ls->ls_stid.sc_status |= SC_STATUS_CLOSED;
 		lrp->lrs_present = false;
 	}
 	spin_unlock(&ls->ls_lock);
 
+	if (!lrp->lrs_present) {
+		/* ls_mutex prevents a LAYOUTGET from adding another segment. */
+		spin_lock(&ls->ls_stid.sc_client->cl_lock);
+		ls->ls_stid.sc_status |= SC_STATUS_CLOSED;
+		spin_unlock(&ls->ls_stid.sc_client->cl_lock);
+		trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid);
+	}
+
 	mutex_unlock(&ls->ls_mutex);
 	nfs4_put_stid(&ls->ls_stid);
 	nfsd4_free_layouts(&reaplist);
@@ -594,6 +610,20 @@ nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
 	spin_unlock(&ls->ls_lock);
 }
 
+void nfsd4_return_revoked_layout(struct nfs4_layout_stateid *ls)
+{
+	LIST_HEAD(reaplist);
+
+	/*
+	 * The caller holds a stateid reference until segment draining ends.
+	 * Wait for any LAYOUTGET that passed the CLOSED check.
+	 */
+	mutex_lock(&ls->ls_mutex);
+	nfsd4_return_all_layouts(ls, &reaplist);
+	mutex_unlock(&ls->ls_mutex);
+	nfsd4_free_layouts(&reaplist);
+}
+
 void
 nfsd4_return_all_client_layouts(struct nfs4_client *clp)
 {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 26d2d56a5..1740b86eb 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5873,9 +5873,21 @@ static void nfsd4_drop_revoked_stid(struct nfs4_stid *s)
 		break;
 	case SC_TYPE_LAYOUT:
 		ls = layoutstateid(s);
+		if (s->sc_status & SC_STATUS_CLOSED) {
+			spin_unlock(&cl->cl_lock);
+			break;
+		}
+		s->sc_status |= SC_STATUS_CLOSED;
+		/*
+		 * The IDR does not own a layout stateid reference. Keep ls
+		 * alive while draining worker and segment references below;
+		 * the final put releases this temporary reference.
+		 */
+		refcount_inc(&s->sc_count);
 		list_del_init(&ls->ls_perclnt);
 		spin_unlock(&cl->cl_lock);
 		nfsd4_stop_layout_fence(ls);
+		nfsd4_return_revoked_layout(ls);
 		nfs4_put_stid(s);
 		break;
 	default:
@@ -7901,6 +7913,8 @@ static void nfs40_clean_admin_revoked(struct nfsd_net *nn,
 		unsigned long id, tmp;
 		struct nfs4_stid *stid;
 
+		if (clp->cl_minorversion != 0)
+			continue;
 		if (atomic_read(&clp->cl_admin_revoked) == 0)
 			continue;
 		if (is_client_expired(clp))
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index 559df0e5b..9b0f17a4d 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -75,6 +75,7 @@ struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
 #ifdef CONFIG_NFSD_PNFS
 void nfsd4_setup_layout_type(struct svc_export *exp);
 void nfsd4_return_all_client_layouts(struct nfs4_client *);
+void nfsd4_return_revoked_layout(struct nfs4_layout_stateid *ls);
 void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
 		struct nfs4_file *fp);
 void nfsd4_close_layout(struct nfs4_layout_stateid *ls);
@@ -93,6 +94,11 @@ static inline void nfsd4_setup_layout_type(struct svc_export *exp)
 static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
 {
 }
+
+static inline void nfsd4_return_revoked_layout(struct nfs4_layout_stateid *ls)
+{
+}
+
 static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
 		struct nfs4_file *fp)
 {
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 79dfa47b8..63b581104 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -148,9 +148,8 @@ struct nfs4_stid {
  * nn->deleg_lock protects sc_status for hashed delegation stateids.
  * ->cl_lock protects the bits set as one is disposed of
  * (SC_STATUS_CLOSED, SC_STATUS_FREEABLE, SC_STATUS_FREED) and
- * sc_status for open and lock stateids. ->st_mutex also protects
- * sc_status for open stateids. ->ls_lock protects sc_status for
- * layout stateids.
+ * sc_status for open, lock, and layout stateids. ->st_mutex also protects
+ * sc_status for open stateids.
  */
 /*
  * For an open stateid kept around *only* to process close replays.

base-commit: c807415bc69013a5f162264ee0e14f8742c182f7
-- 
2.50.1 (Apple Git-155)