From 47acca884f714f41d95dc654f802845544554784 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 18 Feb 2025 16:50:30 -0500
Subject: NFSv4: Don't trigger uneccessary scans for return-on-close
 delegations

The amount of looping through the list of delegations is occasionally
leading to soft lockups. Avoid at least some loops by not requiring the
NFSv4 state manager to scan for delegations that are marked for
return-on-close. Instead, either mark them for immediate return (if
possible) or else leave it up to nfs4_inode_return_delegation_on_close()
to return them once the file is closed by the application.

Fixes: b757144fd77c ("NFSv4: Be less aggressive about returning delegations for open files")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/delegation.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 4db912f56230..df77d68d9ff9 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -590,17 +590,6 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
-	else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) {
-		struct inode *inode;
-
-		spin_lock(&delegation->lock);
-		inode = delegation->inode;
-		if (inode && list_empty(&NFS_I(inode)->open_files))
-			ret = true;
-		spin_unlock(&delegation->lock);
-	}
-	if (ret)
-		clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
 	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
@@ -878,11 +867,25 @@ int nfs4_inode_make_writeable(struct inode *inode)
 	return nfs4_inode_return_delegation(inode);
 }
 
-static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
-		struct nfs_delegation *delegation)
+static void
+nfs_mark_return_if_closed_delegation(struct nfs_server *server,
+				     struct nfs_delegation *delegation)
 {
-	set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
-	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
+	struct inode *inode;
+
+	if (test_bit(NFS_DELEGATION_RETURN, &delegation->flags) ||
+	    test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags))
+		return;
+	spin_lock(&delegation->lock);
+	inode = delegation->inode;
+	if (!inode)
+		goto out;
+	if (list_empty(&NFS_I(inode)->open_files))
+		nfs_mark_return_delegation(server, delegation);
+	else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out:
+	spin_unlock(&delegation->lock);
 }
 
 static bool nfs_server_mark_return_all_delegations(struct nfs_server *server)
-- 
cgit v1.2.3


From 35a566a24e58f1b5f89737edf60b77de58719ed0 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 18 Feb 2025 18:14:26 -0500
Subject: NFSv4: Avoid unnecessary scans of filesystems for returning
 delegations

The amount of looping through the list of delegations is occasionally
leading to soft lockups. If the state manager was asked to return
delegations asynchronously, it should only scan those filesystems that
hold delegations that need to be returned.

Fixes: af3b61bf6131 ("NFSv4: Clean up nfs_client_return_marked_delegations()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/delegation.c       | 5 +++++
 include/linux/nfs_fs_sb.h | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'fs')

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index df77d68d9ff9..d1f5e497729c 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -79,6 +79,7 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
 				       struct nfs_delegation *delegation)
 {
 	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
+	set_bit(NFS4SERV_DELEGRETURN, &server->delegation_flags);
 	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 }
 
@@ -608,6 +609,9 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
 	struct nfs_delegation *place_holder_deleg = NULL;
 	int err = 0;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGRETURN,
+				&server->delegation_flags))
+		return 0;
 restart:
 	/*
 	 * To avoid quadratic looping we hold a reference
@@ -659,6 +663,7 @@ restart:
 		cond_resched();
 		if (!err)
 			goto restart;
+		set_bit(NFS4SERV_DELEGRETURN, &server->delegation_flags);
 		set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 		goto out;
 	}
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index f00bfcee7120..4e9ad6f6e907 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -250,6 +250,8 @@ struct nfs_server {
 	struct list_head	ss_copies;
 	struct list_head	ss_src_copies;
 
+	unsigned long		delegation_flags;
+#define NFS4SERV_DELEGRETURN		(1)
 	unsigned long		delegation_gen;
 	unsigned long		mig_gen;
 	unsigned long		mig_status;
-- 
cgit v1.2.3


From f163aa81a799e2d46d7f8f0b42a0e7770eaa0d06 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 18 Feb 2025 19:03:21 -0500
Subject: NFSv4: Avoid unnecessary scans of filesystems for expired delegations

The amount of looping through the list of delegations is occasionally
leading to soft lockups.  If the state manager was asked to reap the
expired delegations, it should scan only those filesystems that hold
delegations that need to be reaped.

Fixes: 7f156ef0bf45 ("NFSv4: Clean up nfs_delegation_reap_expired()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/delegation.c       | 7 +++++++
 include/linux/nfs_fs_sb.h | 1 +
 2 files changed, 8 insertions(+)

(limited to 'fs')

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index d1f5e497729c..abd952cc47e4 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1284,6 +1284,7 @@ static void nfs_mark_test_expired_delegation(struct nfs_server *server,
 		return;
 	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
 	set_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
+	set_bit(NFS4SERV_DELEGATION_EXPIRED, &server->delegation_flags);
 	set_bit(NFS4CLNT_DELEGATION_EXPIRED, &server->nfs_client->cl_state);
 }
 
@@ -1362,6 +1363,9 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
 	nfs4_stateid stateid;
 	unsigned long gen = ++server->delegation_gen;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGATION_EXPIRED,
+				&server->delegation_flags))
+		return 0;
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
@@ -1391,6 +1395,9 @@ restart:
 			goto restart;
 		}
 		nfs_inode_mark_test_expired_delegation(server,inode);
+		set_bit(NFS4SERV_DELEGATION_EXPIRED, &server->delegation_flags);
+		set_bit(NFS4CLNT_DELEGATION_EXPIRED,
+			&server->nfs_client->cl_state);
 		iput(inode);
 		return -EAGAIN;
 	}
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 4e9ad6f6e907..7d6f164036fa 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -252,6 +252,7 @@ struct nfs_server {
 
 	unsigned long		delegation_flags;
 #define NFS4SERV_DELEGRETURN		(1)
+#define NFS4SERV_DELEGATION_EXPIRED	(2)
 	unsigned long		delegation_gen;
 	unsigned long		mig_gen;
 	unsigned long		mig_status;
-- 
cgit v1.2.3


From e767b59e29b8327d25edde65efc743f479f30d0a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 18 Feb 2025 18:37:51 -0500
Subject: NFSv4: Avoid unnecessary scans of filesystems for delayed delegations

The amount of looping through the list of delegations is occasionally
leading to soft lockups. If the state manager was asked to manage the
delayed return of delegations, then only scan those filesystems
containing delegations that were marked as being delayed.

Fixes: be20037725d1 ("NFSv4: Fix delegation return in cases where we have to retry")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/delegation.c       | 18 ++++++++++++------
 include/linux/nfs_fs_sb.h |  1 +
 2 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index abd952cc47e4..325ba0663a6d 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -331,14 +331,16 @@ nfs_start_delegation_return(struct nfs_inode *nfsi)
 }
 
 static void nfs_abort_delegation_return(struct nfs_delegation *delegation,
-					struct nfs_client *clp, int err)
+					struct nfs_server *server, int err)
 {
-
 	spin_lock(&delegation->lock);
 	clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 	if (err == -EAGAIN) {
 		set_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags);
-		set_bit(NFS4CLNT_DELEGRETURN_DELAYED, &clp->cl_state);
+		set_bit(NFS4SERV_DELEGRETURN_DELAYED,
+			&server->delegation_flags);
+		set_bit(NFS4CLNT_DELEGRETURN_DELAYED,
+			&server->nfs_client->cl_state);
 	}
 	spin_unlock(&delegation->lock);
 }
@@ -548,7 +550,7 @@ out:
  */
 static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync)
 {
-	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct nfs_server *server = NFS_SERVER(inode);
 	unsigned int mode = O_WRONLY | O_RDWR;
 	int err = 0;
 
@@ -570,11 +572,11 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 		/*
 		 * Guard against state recovery
 		 */
-		err = nfs4_wait_clnt_recover(clp);
+		err = nfs4_wait_clnt_recover(server->nfs_client);
 	}
 
 	if (err) {
-		nfs_abort_delegation_return(delegation, clp, err);
+		nfs_abort_delegation_return(delegation, server, err);
 		goto out;
 	}
 
@@ -678,6 +680,9 @@ static bool nfs_server_clear_delayed_delegations(struct nfs_server *server)
 	struct nfs_delegation *d;
 	bool ret = false;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGRETURN_DELAYED,
+				&server->delegation_flags))
+		goto out;
 	list_for_each_entry_rcu (d, &server->delegations, super_list) {
 		if (!test_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags))
 			continue;
@@ -685,6 +690,7 @@ static bool nfs_server_clear_delayed_delegations(struct nfs_server *server)
 		clear_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags);
 		ret = true;
 	}
+out:
 	return ret;
 }
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7d6f164036fa..108862d81b57 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -253,6 +253,7 @@ struct nfs_server {
 	unsigned long		delegation_flags;
 #define NFS4SERV_DELEGRETURN		(1)
 #define NFS4SERV_DELEGATION_EXPIRED	(2)
+#define NFS4SERV_DELEGRETURN_DELAYED	(3)
 	unsigned long		delegation_gen;
 	unsigned long		mig_gen;
 	unsigned long		mig_status;
-- 
cgit v1.2.3


From 43502f6e8d1e767d6736ea0676cc784025cf6eeb Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Wed, 4 Dec 2024 13:53:09 +1100
Subject: NFS: fix open_owner_id_maxsz and related fields.

A recent change increased the size of an NFSv4 open owner, but didn't
increase the corresponding max_sz defines.  This is not know to have
caused failure, but should be fixed.

This patch also fixes some relates _maxsz fields that are wrong.

Note that the XXX_owner_id_maxsz values now are only the size of the id
and do NOT include the len field that will always preceed the id in xdr
encoding.  I think this is clearer.

Reported-by: David Disseldorp <ddiss@suse.com>
Fixes: d98f72272500 ("nfs: simplify and guarantee owner uniqueness.")
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4xdr.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e8ac3f615f93..71f45cc0ca74 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -82,9 +82,8 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
  * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT  >> 2)
  */
 #define pagepad_maxsz		(1)
-#define open_owner_id_maxsz	(1 + 2 + 1 + 1 + 2)
-#define lock_owner_id_maxsz	(1 + 1 + 4)
-#define decode_lockowner_maxsz	(1 + XDR_QUADLEN(IDMAP_NAMESZ))
+#define open_owner_id_maxsz	(2 + 1 + 2 + 2)
+#define lock_owner_id_maxsz	(2 + 1 + 2)
 #define compound_encode_hdr_maxsz	(3 + (NFS4_MAXTAGLEN >> 2))
 #define compound_decode_hdr_maxsz	(3 + (NFS4_MAXTAGLEN >> 2))
 #define op_encode_hdr_maxsz	(1)
@@ -185,7 +184,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 #define encode_claim_null_maxsz	(1 + nfs4_name_maxsz)
 #define encode_open_maxsz	(op_encode_hdr_maxsz + \
 				2 + encode_share_access_maxsz + 2 + \
-				open_owner_id_maxsz + \
+				1 + open_owner_id_maxsz + \
 				encode_opentype_maxsz + \
 				encode_claim_null_maxsz)
 #define decode_space_limit_maxsz	(3)
@@ -255,13 +254,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 #define encode_link_maxsz	(op_encode_hdr_maxsz + \
 				nfs4_name_maxsz)
 #define decode_link_maxsz	(op_decode_hdr_maxsz + decode_change_info_maxsz)
-#define encode_lockowner_maxsz	(7)
+#define encode_lockowner_maxsz	(2 + 1 + lock_owner_id_maxsz)
+
 #define encode_lock_maxsz	(op_encode_hdr_maxsz + \
 				 7 + \
 				 1 + encode_stateid_maxsz + 1 + \
 				 encode_lockowner_maxsz)
 #define decode_lock_denied_maxsz \
-				(8 + decode_lockowner_maxsz)
+				(2 + 2 + 1 + 2 + 1 + lock_owner_id_maxsz)
 #define decode_lock_maxsz	(op_decode_hdr_maxsz + \
 				 decode_lock_denied_maxsz)
 #define encode_lockt_maxsz	(op_encode_hdr_maxsz + 5 + \
@@ -617,7 +617,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 				 encode_lockowner_maxsz)
 #define NFS4_dec_release_lockowner_sz \
 				(compound_decode_hdr_maxsz + \
-				 decode_lockowner_maxsz)
+				 decode_release_lockowner_maxsz)
 #define NFS4_enc_access_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
@@ -1412,7 +1412,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
 	__be32 *p;
  /*
  * opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4,
- * owner 4 = 32
+ * owner 28
  */
 	encode_nfs4_seqid(xdr, arg->seqid);
 	encode_share_access(xdr, arg->share_access);
@@ -5077,7 +5077,7 @@ static int decode_link(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
 /*
  * We create the owner, so we know a proper owner.id length is 4.
  */
-static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
+static int decode_lock_denied(struct xdr_stream *xdr, struct file_lock *fl)
 {
 	uint64_t offset, length, clientid;
 	__be32 *p;
-- 
cgit v1.2.3


From 8955e7ce61fb6ba28f88e0a38479c992991ba6ab Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 13 Jan 2025 10:32:39 -0500
Subject: NFS: Implement NFSv4.2's OFFLOAD_STATUS XDR

Add XDR encoding and decoding functions for the NFSv4.2
OFFLOAD_STATUS operation.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Link: https://lore.kernel.org/r/20250113153235.48706-13-cel@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42xdr.c       | 86 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4xdr.c        |  1 +
 include/linux/nfs4.h    |  1 +
 include/linux/nfs_xdr.h |  5 +--
 4 files changed, 91 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 5072d7ea72e9..b1b663468249 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -35,6 +35,11 @@
 #define encode_offload_cancel_maxsz	(op_encode_hdr_maxsz + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE))
 #define decode_offload_cancel_maxsz	(op_decode_hdr_maxsz)
+#define encode_offload_status_maxsz	(op_encode_hdr_maxsz + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_offload_status_maxsz	(op_decode_hdr_maxsz + \
+					 2 /* osr_count */ + \
+					 2 /* osr_complete */)
 #define encode_copy_notify_maxsz	(op_encode_hdr_maxsz + \
 					 XDR_QUADLEN(NFS4_STATEID_SIZE) + \
 					 1 + /* nl4_type */ \
@@ -143,6 +148,14 @@
 					 decode_sequence_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_offload_cancel_maxsz)
+#define NFS4_enc_offload_status_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_offload_status_maxsz)
+#define NFS4_dec_offload_status_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_offload_status_maxsz)
 #define NFS4_enc_copy_notify_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -345,6 +358,14 @@ static void encode_offload_cancel(struct xdr_stream *xdr,
 	encode_nfs4_stateid(xdr, &args->osa_stateid);
 }
 
+static void encode_offload_status(struct xdr_stream *xdr,
+				  const struct nfs42_offload_status_args *args,
+				  struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_OFFLOAD_STATUS, decode_offload_status_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->osa_stateid);
+}
+
 static void encode_copy_notify(struct xdr_stream *xdr,
 			       const struct nfs42_copy_notify_args *args,
 			       struct compound_hdr *hdr)
@@ -569,6 +590,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode OFFLOAD_STATUS request
+ */
+static void nfs4_xdr_enc_offload_status(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					const void *data)
+{
+	const struct nfs42_offload_status_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->osa_seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->osa_seq_args, &hdr);
+	encode_putfh(xdr, args->osa_src_fh, &hdr);
+	encode_offload_status(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode COPY_NOTIFY request
  */
@@ -921,6 +961,26 @@ static int decode_offload_cancel(struct xdr_stream *xdr,
 	return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
 }
 
+static int decode_offload_status(struct xdr_stream *xdr,
+				 struct nfs42_offload_status_res *res)
+{
+	ssize_t result;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_OFFLOAD_STATUS);
+	if (status)
+		return status;
+	/* osr_count */
+	if (xdr_stream_decode_u64(xdr, &res->osr_count) < 0)
+		return -EIO;
+	/* osr_complete<1> */
+	result = xdr_stream_decode_uint32_array(xdr, &res->osr_complete, 1);
+	if (result < 0)
+		return -EIO;
+	res->complete_count = result;
+	return 0;
+}
+
 static int decode_copy_notify(struct xdr_stream *xdr,
 			      struct nfs42_copy_notify_res *res)
 {
@@ -1370,6 +1430,32 @@ out:
 	return status;
 }
 
+/*
+ * Decode OFFLOAD_STATUS response
+ */
+static int nfs4_xdr_dec_offload_status(struct rpc_rqst *rqstp,
+				       struct xdr_stream *xdr,
+				       void *data)
+{
+	struct nfs42_offload_status_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->osr_seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_offload_status(xdr, res);
+
+out:
+	return status;
+}
+
 /*
  * Decode COPY_NOTIFY response
  */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 71f45cc0ca74..55bef5fbfa47 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7702,6 +7702,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(CLONE,		enc_clone,		dec_clone),
 	PROC42(COPY,		enc_copy,		dec_copy),
 	PROC42(OFFLOAD_CANCEL,	enc_offload_cancel,	dec_offload_cancel),
+	PROC42(OFFLOAD_STATUS,	enc_offload_status,	dec_offload_status),
 	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC42(LAYOUTERROR,	enc_layouterror,	dec_layouterror),
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 9ac83ca88326..5fa60fe441b5 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -691,6 +691,7 @@ enum {
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
 	NFSPROC4_CLNT_READ_PLUS,
+	NFSPROC4_CLNT_OFFLOAD_STATUS,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9155a6ffc370..dc5288111999 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1515,8 +1515,9 @@ struct nfs42_offload_status_args {
 
 struct nfs42_offload_status_res {
 	struct nfs4_sequence_res	osr_seq_res;
-	uint64_t			osr_count;
-	int				osr_status;
+	u64				osr_count;
+	int				complete_count;
+	u32				osr_complete;
 };
 
 struct nfs42_copy_notify_args {
-- 
cgit v1.2.3


From 77dd8a302f56679178924f82a29eaf437857ea75 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 13 Jan 2025 10:32:40 -0500
Subject: NFS: Implement NFSv4.2's OFFLOAD_STATUS operation

Enable the Linux NFS client to observe the progress of an offloaded
asynchronous COPY operation. This new operation will be put to use
in a subsequent patch.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Link: https://lore.kernel.org/r/20250113153235.48706-14-cel@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42proc.c        | 103 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4proc.c         |   3 +-
 include/linux/nfs_fs_sb.h |   1 +
 3 files changed, 106 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 1924c4a2077b..3e359e16c324 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -21,6 +21,8 @@
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
+static int nfs42_proc_offload_status(struct file *file, nfs4_stateid *stateid,
+				     u64 *copied);
 
 static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr)
 {
@@ -582,6 +584,107 @@ static int nfs42_do_offload_cancel_async(struct file *dst,
 	return status;
 }
 
+static int
+_nfs42_proc_offload_status(struct nfs_server *server, struct file *file,
+			   struct nfs42_offload_data *data)
+{
+	struct nfs_open_context *ctx = nfs_file_open_context(file);
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_OFFLOAD_STATUS],
+		.rpc_argp	= &data->args,
+		.rpc_resp	= &data->res,
+		.rpc_cred	= ctx->cred,
+	};
+	int status;
+
+	status = nfs4_call_sync(server->client, server, &msg,
+				&data->args.osa_seq_args,
+				&data->res.osr_seq_res, 1);
+	switch (status) {
+	case 0:
+		break;
+
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+		/*
+		 * Server does not recognize the COPY stateid. CB_OFFLOAD
+		 * could have purged it, or server might have rebooted.
+		 * Since COPY stateids don't have an associated inode,
+		 * avoid triggering state recovery.
+		 */
+		status = -EBADF;
+		break;
+	case -NFS4ERR_NOTSUPP:
+	case -ENOTSUPP:
+	case -EOPNOTSUPP:
+		server->caps &= ~NFS_CAP_OFFLOAD_STATUS;
+		status = -EOPNOTSUPP;
+		break;
+	}
+
+	return status;
+}
+
+/**
+ * nfs42_proc_offload_status - Poll completion status of an async copy operation
+ * @dst: handle of file being copied into
+ * @stateid: copy stateid (from async COPY result)
+ * @copied: OUT: number of bytes copied so far
+ *
+ * Return values:
+ *   %0: Server returned an NFS4_OK completion status
+ *   %-EINPROGRESS: Server returned no completion status
+ *   %-EREMOTEIO: Server returned an error completion status
+ *   %-EBADF: Server did not recognize the copy stateid
+ *   %-EOPNOTSUPP: Server does not support OFFLOAD_STATUS
+ *   %-ERESTARTSYS: Wait interrupted by signal
+ *
+ * Other negative errnos indicate the client could not complete the
+ * request.
+ */
+static int __maybe_unused
+nfs42_proc_offload_status(struct file *dst, nfs4_stateid *stateid, u64 *copied)
+{
+	struct inode *inode = file_inode(dst);
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs4_exception exception = {
+		.inode = inode,
+	};
+	struct nfs42_offload_data *data;
+	int status;
+
+	if (!(server->caps & NFS_CAP_OFFLOAD_STATUS))
+		return -EOPNOTSUPP;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	data->seq_server = server;
+	data->args.osa_src_fh = NFS_FH(inode);
+	memcpy(&data->args.osa_stateid, stateid,
+		sizeof(data->args.osa_stateid));
+	exception.stateid = &data->args.osa_stateid;
+	do {
+		status = _nfs42_proc_offload_status(server, dst, data);
+		if (status == -EOPNOTSUPP)
+			goto out;
+		status = nfs4_handle_exception(server, status, &exception);
+	} while (exception.retry);
+	if (status)
+		goto out;
+
+	*copied = data->res.osr_count;
+	if (!data->res.complete_count)
+		status = -EINPROGRESS;
+	else if (data->res.osr_complete != NFS_OK)
+		status = -EREMOTEIO;
+
+out:
+	kfree(data);
+	return status;
+}
+
 static int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
 				   struct nfs42_copy_notify_args *args,
 				   struct nfs42_copy_notify_res *res)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6e95db6c17e9..24406fc1352d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10781,7 +10781,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_CLONE
 		| NFS_CAP_LAYOUTERROR
 		| NFS_CAP_READ_PLUS
-		| NFS_CAP_MOVEABLE,
+		| NFS_CAP_MOVEABLE
+		| NFS_CAP_OFFLOAD_STATUS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 108862d81b57..1711eefcf24f 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -293,6 +293,7 @@ struct nfs_server {
 #define NFS_CAP_CASE_INSENSITIVE	(1U << 6)
 #define NFS_CAP_CASE_PRESERVING	(1U << 7)
 #define NFS_CAP_REBOOT_LAYOUTRETURN	(1U << 8)
+#define NFS_CAP_OFFLOAD_STATUS	(1U << 9)
 #define NFS_CAP_OPEN_XOR	(1U << 12)
 #define NFS_CAP_DELEGTIME	(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
-- 
cgit v1.2.3


From adcc0aef9ed41a82590be4f0090bb404c28a2f2f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 13 Jan 2025 10:32:41 -0500
Subject: NFS: Use NFSv4.2's OFFLOAD_STATUS operation

We've found that there are cases where a transport disconnection
results in the loss of callback RPCs. NFS servers typically do not
retransmit callback operations after a disconnect.

This can be a problem for the Linux NFS client's current
implementation of asynchronous COPY, which waits indefinitely for a
CB_OFFLOAD callback. If a transport disconnect occurs while an async
COPY is running, there's a good chance the client will never get the
completing CB_OFFLOAD.

Fix this by implementing the OFFLOAD_STATUS operation so that the
Linux NFS client can probe the NFS server if it doesn't see a
CB_OFFLOAD in a reasonable amount of time.

This patch implements a simplistic check. As future work, the client
might also be able to detect whether there is no forward progress on
the request asynchronous COPY operation, and CANCEL it.

Suggested-by: Olga Kornievskaia <kolga@netapp.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218735
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Link: https://lore.kernel.org/r/20250113153235.48706-15-cel@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42proc.c | 70 +++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 59 insertions(+), 11 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 3e359e16c324..82ada136ee6a 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -175,6 +175,20 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
+static void nfs4_copy_dequeue_callback(struct nfs_server *dst_server,
+				       struct nfs_server *src_server,
+				       struct nfs4_copy_state *copy)
+{
+	spin_lock(&dst_server->nfs_client->cl_lock);
+	list_del_init(&copy->copies);
+	spin_unlock(&dst_server->nfs_client->cl_lock);
+	if (dst_server != src_server) {
+		spin_lock(&src_server->nfs_client->cl_lock);
+		list_del_init(&copy->src_copies);
+		spin_unlock(&src_server->nfs_client->cl_lock);
+	}
+}
+
 static int handle_async_copy(struct nfs42_copy_res *res,
 			     struct nfs_server *dst_server,
 			     struct nfs_server *src_server,
@@ -184,9 +198,12 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 			     bool *restart)
 {
 	struct nfs4_copy_state *copy, *tmp_copy = NULL, *iter;
-	int status = NFS4_OK;
 	struct nfs_open_context *dst_ctx = nfs_file_open_context(dst);
 	struct nfs_open_context *src_ctx = nfs_file_open_context(src);
+	struct nfs_client *clp = dst_server->nfs_client;
+	unsigned long timeout = 3 * HZ;
+	int status = NFS4_OK;
+	u64 copied;
 
 	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL);
 	if (!copy)
@@ -224,15 +241,12 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 		spin_unlock(&src_server->nfs_client->cl_lock);
 	}
 
-	status = wait_for_completion_interruptible(&copy->completion);
-	spin_lock(&dst_server->nfs_client->cl_lock);
-	list_del_init(&copy->copies);
-	spin_unlock(&dst_server->nfs_client->cl_lock);
-	if (dst_server != src_server) {
-		spin_lock(&src_server->nfs_client->cl_lock);
-		list_del_init(&copy->src_copies);
-		spin_unlock(&src_server->nfs_client->cl_lock);
-	}
+wait:
+	status = wait_for_completion_interruptible_timeout(&copy->completion,
+							   timeout);
+	if (!status)
+		goto timeout;
+	nfs4_copy_dequeue_callback(dst_server, src_server, copy);
 	if (status == -ERESTARTSYS) {
 		goto out_cancel;
 	} else if (copy->flags || copy->error == NFS4ERR_PARTNER_NO_AUTH) {
@@ -242,6 +256,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 	}
 out:
 	res->write_res.count = copy->count;
+	/* Copy out the updated write verifier provided by CB_OFFLOAD. */
 	memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
 	status = -copy->error;
 
@@ -253,6 +268,39 @@ out_cancel:
 	if (!nfs42_files_from_same_server(src, dst))
 		nfs42_do_offload_cancel_async(src, src_stateid);
 	goto out_free;
+timeout:
+	timeout <<= 1;
+	if (timeout > (clp->cl_lease_time >> 1))
+		timeout = clp->cl_lease_time >> 1;
+	status = nfs42_proc_offload_status(dst, &copy->stateid, &copied);
+	if (status == -EINPROGRESS)
+		goto wait;
+	nfs4_copy_dequeue_callback(dst_server, src_server, copy);
+	switch (status) {
+	case 0:
+		/* The server recognized the copy stateid, so it hasn't
+		 * rebooted. Don't overwrite the verifier returned in the
+		 * COPY result. */
+		res->write_res.count = copied;
+		goto out_free;
+	case -EREMOTEIO:
+		/* COPY operation failed on the server. */
+		status = -EOPNOTSUPP;
+		res->write_res.count = copied;
+		goto out_free;
+	case -EBADF:
+		/* Server did not recognize the copy stateid. It has
+		 * probably restarted and lost the plot. */
+		res->write_res.count = 0;
+		status = -EOPNOTSUPP;
+		break;
+	case -EOPNOTSUPP:
+		/* RFC 7862 REQUIREs server to support OFFLOAD_STATUS when
+		 * it has signed up for an async COPY, so server is not
+		 * spec-compliant. */
+		res->write_res.count = 0;
+	}
+	goto out_free;
 }
 
 static int process_copy_commit(struct file *dst, loff_t pos_dst,
@@ -643,7 +691,7 @@ _nfs42_proc_offload_status(struct nfs_server *server, struct file *file,
  * Other negative errnos indicate the client could not complete the
  * request.
  */
-static int __maybe_unused
+static int
 nfs42_proc_offload_status(struct file *dst, nfs4_stateid *stateid, u64 *copied)
 {
 	struct inode *inode = file_inode(dst);
-- 
cgit v1.2.3


From 2d6a194f4b27e0fe524bb6da433d6b0f7032e27d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 13 Jan 2025 10:32:42 -0500
Subject: NFS: Refactor trace_nfs4_offload_cancel

Add a trace_nfs4_offload_status trace point that looks just like
trace_nfs4_offload_cancel. Promote that event to an event class to
avoid duplicating code.

An alternative approach would be to expand trace_nfs4_offload_status
to report more of the actual OFFLOAD_STATUS result.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Link: https://lore.kernel.org/r/20250113153235.48706-16-cel@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42proc.c |  1 +
 fs/nfs/nfs4trace.h | 11 ++++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 82ada136ee6a..5cf52ece96ac 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -648,6 +648,7 @@ _nfs42_proc_offload_status(struct nfs_server *server, struct file *file,
 	status = nfs4_call_sync(server->client, server, &msg,
 				&data->args.osa_seq_args,
 				&data->res.osr_seq_res, 1);
+	trace_nfs4_offload_status(&data->args, status);
 	switch (status) {
 	case 0:
 		break;
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 22c973316f0b..bc67fe6801b1 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -2608,7 +2608,7 @@ TRACE_EVENT(nfs4_copy_notify,
 		)
 );
 
-TRACE_EVENT(nfs4_offload_cancel,
+DECLARE_EVENT_CLASS(nfs4_offload_class,
 		TP_PROTO(
 			const struct nfs42_offload_status_args *args,
 			int error
@@ -2640,6 +2640,15 @@ TRACE_EVENT(nfs4_offload_cancel,
 			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
+#define DEFINE_NFS4_OFFLOAD_EVENT(name) \
+	DEFINE_EVENT(nfs4_offload_class, name,  \
+			TP_PROTO( \
+				const struct nfs42_offload_status_args *args, \
+				int error \
+			), \
+			TP_ARGS(args, error))
+DEFINE_NFS4_OFFLOAD_EVENT(nfs4_offload_cancel);
+DEFINE_NFS4_OFFLOAD_EVENT(nfs4_offload_status);
 
 DECLARE_EVENT_CLASS(nfs4_xattr_event,
 		TP_PROTO(
-- 
cgit v1.2.3


From cfe1f8776f23fd6dfe4ba9fcb695b129f0761187 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Thu, 13 Mar 2025 13:01:22 -0400
Subject: NFS: Extend rdirplus mount option with "force|none"

There are certain users that wish to force the NFS client to choose
READDIRPLUS over READDIR for a particular mount.  Update the "rdirplus" mount
option to optionally accept values.  For "rdirplus=force", the NFS client
will always attempt to use READDDIRPLUS.  The setting of "rdirplus=none" is
aliased to the existing "nordirplus".

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Link: https://lore.kernel.org/r/c4cf0de4c8be0930b91bc74bee310d289781cd3b.1741885071.git.bcodding@redhat.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c              |  2 ++
 fs/nfs/fs_context.c       | 32 ++++++++++++++++++++++++++++----
 fs/nfs/super.c            |  1 +
 include/linux/nfs_fs_sb.h |  1 +
 4 files changed, 32 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2b04038b0e40..5c4566a8dabb 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -666,6 +666,8 @@ static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx,
 {
 	if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
 		return false;
+	if (NFS_SERVER(dir)->flags & NFS_MOUNT_FORCE_RDIRPLUS)
+		return true;
 	if (ctx->pos == 0 ||
 	    cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD)
 		return true;
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index b069385eea17..1cabba1231d6 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -72,6 +72,8 @@ enum nfs_param {
 	Opt_posix,
 	Opt_proto,
 	Opt_rdirplus,
+	Opt_rdirplus_none,
+	Opt_rdirplus_force,
 	Opt_rdma,
 	Opt_resvport,
 	Opt_retrans,
@@ -174,7 +176,8 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_u32   ("port",		Opt_port),
 	fsparam_flag_no("posix",	Opt_posix),
 	fsparam_string("proto",		Opt_proto),
-	fsparam_flag_no("rdirplus",	Opt_rdirplus),
+	fsparam_flag_no("rdirplus", Opt_rdirplus), // rdirplus|nordirplus
+	fsparam_string("rdirplus",  Opt_rdirplus), // rdirplus=...
 	fsparam_flag  ("rdma",		Opt_rdma),
 	fsparam_flag_no("resvport",	Opt_resvport),
 	fsparam_u32   ("retrans",	Opt_retrans),
@@ -288,6 +291,12 @@ static const struct constant_table nfs_xprtsec_policies[] = {
 	{}
 };
 
+static const struct constant_table nfs_rdirplus_tokens[] = {
+	{ "none",	Opt_rdirplus_none },
+	{ "force",	Opt_rdirplus_force },
+	{}
+};
+
 /*
  * Sanity-check a server address provided by the mount command.
  *
@@ -636,10 +645,25 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 			ctx->flags &= ~NFS_MOUNT_NOACL;
 		break;
 	case Opt_rdirplus:
-		if (result.negated)
+		if (result.negated) {
+			ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS;
 			ctx->flags |= NFS_MOUNT_NORDIRPLUS;
-		else
-			ctx->flags &= ~NFS_MOUNT_NORDIRPLUS;
+		} else if (!param->string) {
+			ctx->flags &= ~(NFS_MOUNT_NORDIRPLUS | NFS_MOUNT_FORCE_RDIRPLUS);
+		} else {
+			switch (lookup_constant(nfs_rdirplus_tokens, param->string, -1)) {
+			case Opt_rdirplus_none:
+				ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS;
+				ctx->flags |= NFS_MOUNT_NORDIRPLUS;
+				break;
+			case Opt_rdirplus_force:
+				ctx->flags &= ~NFS_MOUNT_NORDIRPLUS;
+				ctx->flags |= NFS_MOUNT_FORCE_RDIRPLUS;
+				break;
+			default:
+				goto out_invalid_value;
+			}
+		}
 		break;
 	case Opt_sharecache:
 		if (result.negated)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index aeb715b4a690..96de658a7886 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -454,6 +454,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		{ NFS_MOUNT_NONLM, ",nolock", "" },
 		{ NFS_MOUNT_NOACL, ",noacl", "" },
 		{ NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" },
+		{ NFS_MOUNT_FORCE_RDIRPLUS, ",rdirplus=force", "" },
 		{ NFS_MOUNT_UNSHARED, ",nosharecache", "" },
 		{ NFS_MOUNT_NORESVPORT, ",noresvport", "" },
 		{ 0, NULL, NULL }
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 1711eefcf24f..b83d16a42afc 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -167,6 +167,7 @@ struct nfs_server {
 #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
 #define NFS_MOUNT_SHUTDOWN			0x08000000
 #define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
+#define NFS_MOUNT_FORCE_RDIRPLUS	0x20000000
 
 	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
-- 
cgit v1.2.3


From e171b965008de4e3c7fec49ce634c698c8bc924d Mon Sep 17 00:00:00 2001
From: Anna Schumaker <anna.schumaker@oracle.com>
Date: Fri, 7 Feb 2025 15:42:21 -0500
Subject: NFS: Add implid to sysfs

The Linux NFS server added support for returning this information during
an EXCHANGE_ID in Linux v6.13. This is something and admin might want to
query, so let's add it to sysfs.

Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
Link: https://lore.kernel.org/r/20250207204225.594002-2-anna@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/sysfs.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

(limited to 'fs')

diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 7b59a40d40c0..b30401b2c939 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -272,6 +272,38 @@ out:
 
 static struct kobj_attribute nfs_sysfs_attr_shutdown = __ATTR_RW(shutdown);
 
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+static ssize_t
+implid_domain_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid;
+
+	if (!impl_id || strlen(impl_id->domain) == 0)
+		return 0; //sysfs_emit(buf, "");
+	return sysfs_emit(buf, "%s\n", impl_id->domain);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_implid_domain = __ATTR_RO(implid_domain);
+
+
+static ssize_t
+implid_name_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid;
+
+	if (!impl_id || strlen(impl_id->name) == 0)
+		return 0; //sysfs_emit(buf, "");
+	return sysfs_emit(buf, "%s\n", impl_id->name);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_implid_name = __ATTR_RO(implid_name);
+
+#endif /* IS_ENABLED(CONFIG_NFS_V4_1) */
+
 #define RPC_CLIENT_NAME_SIZE 64
 
 void nfs_sysfs_link_rpc_client(struct nfs_server *server,
@@ -309,6 +341,32 @@ static struct kobj_type nfs_sb_ktype = {
 	.child_ns_type = nfs_netns_object_child_ns_type,
 };
 
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+static void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
+{
+	int ret;
+
+	if (!server->nfs_client->cl_implid)
+		return;
+
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_domain.attr,
+					   nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_name.attr,
+				   nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+}
+#else /* CONFIG_NFS_V4_1 */
+static inline void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 void nfs_sysfs_add_server(struct nfs_server *server)
 {
 	int ret;
@@ -325,6 +383,8 @@ void nfs_sysfs_add_server(struct nfs_server *server)
 	if (ret < 0)
 		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
 			server->s_sysfs_id, ret);
+
+	nfs_sysfs_add_nfsv41_server(server);
 }
 EXPORT_SYMBOL_GPL(nfs_sysfs_add_server);
 
-- 
cgit v1.2.3


From 487fae09d7e266a58a13784983cc1ef6a2076526 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 20 Mar 2025 11:45:06 -0400
Subject: NFS: Add a mount option to make ENETUNREACH errors fatal

If the NFS client was initially created in a container, and that
container is torn down, there is usually no possibity to go back and
destroy any NFS clients that are hung because their virtual network
devices have been unlinked.

Add a flag that tells the NFS client that in these circumstances, it
should treat ENETDOWN and ENETUNREACH errors as fatal to the NFS client.

The option defaults to being on when the mount happens from inside a net
namespace that is not "init_net".

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/fs_context.c       | 39 +++++++++++++++++++++++++++++++++++++++
 fs/nfs/super.c            |  3 +++
 include/linux/nfs_fs_sb.h |  1 +
 3 files changed, 43 insertions(+)

(limited to 'fs')

diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 1cabba1231d6..13f71ca8c974 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -50,6 +50,7 @@ enum nfs_param {
 	Opt_clientaddr,
 	Opt_cto,
 	Opt_alignwrite,
+	Opt_fatal_neterrors,
 	Opt_fg,
 	Opt_fscache,
 	Opt_fscache_flag,
@@ -97,6 +98,20 @@ enum nfs_param {
 	Opt_xprtsec,
 };
 
+enum {
+	Opt_fatal_neterrors_default,
+	Opt_fatal_neterrors_enetunreach,
+	Opt_fatal_neterrors_none,
+};
+
+static const struct constant_table nfs_param_enums_fatal_neterrors[] = {
+	{ "default",			Opt_fatal_neterrors_default },
+	{ "ENETDOWN:ENETUNREACH",	Opt_fatal_neterrors_enetunreach },
+	{ "ENETUNREACH:ENETDOWN",	Opt_fatal_neterrors_enetunreach },
+	{ "none",			Opt_fatal_neterrors_none },
+	{}
+};
+
 enum {
 	Opt_local_lock_all,
 	Opt_local_lock_flock,
@@ -153,6 +168,8 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_string("clientaddr",	Opt_clientaddr),
 	fsparam_flag_no("cto",		Opt_cto),
 	fsparam_flag_no("alignwrite",	Opt_alignwrite),
+	fsparam_enum("fatal_neterrors", Opt_fatal_neterrors,
+		     nfs_param_enums_fatal_neterrors),
 	fsparam_flag  ("fg",		Opt_fg),
 	fsparam_flag_no("fsc",		Opt_fscache_flag),
 	fsparam_string("fsc",		Opt_fscache),
@@ -896,6 +913,25 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 			goto out_of_bounds;
 		ctx->nfs_server.max_connect = result.uint_32;
 		break;
+	case Opt_fatal_neterrors:
+		trace_nfs_mount_assign(param->key, param->string);
+		switch (result.uint_32) {
+		case Opt_fatal_neterrors_default:
+			if (fc->net_ns != &init_net)
+				ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL;
+			else
+				ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL;
+			break;
+		case Opt_fatal_neterrors_enetunreach:
+			ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL;
+			break;
+		case Opt_fatal_neterrors_none:
+			ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL;
+			break;
+		default:
+			goto out_invalid_value;
+		}
+		break;
 	case Opt_lookupcache:
 		trace_nfs_mount_assign(param->key, param->string);
 		switch (result.uint_32) {
@@ -1675,6 +1711,9 @@ static int nfs_init_fs_context(struct fs_context *fc)
 		ctx->xprtsec.cert_serial	= TLS_NO_CERT;
 		ctx->xprtsec.privkey_serial	= TLS_NO_PRIVKEY;
 
+		if (fc->net_ns != &init_net)
+			ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL;
+
 		fc->s_iflags		|= SB_I_STABLE_WRITES;
 	}
 	fc->fs_private = ctx;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 96de658a7886..9eea9e62afc9 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -457,6 +457,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		{ NFS_MOUNT_FORCE_RDIRPLUS, ",rdirplus=force", "" },
 		{ NFS_MOUNT_UNSHARED, ",nosharecache", "" },
 		{ NFS_MOUNT_NORESVPORT, ",noresvport", "" },
+		{ NFS_MOUNT_NETUNREACH_FATAL,
+		  ",fatal_neterrors=ENETDOWN:ENETUNREACH",
+		  ",fatal_neterrors=none" },
 		{ 0, NULL, NULL }
 	};
 	const struct proc_nfs_info *nfs_infop;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b83d16a42afc..a6ce8590eaaf 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -168,6 +168,7 @@ struct nfs_server {
 #define NFS_MOUNT_SHUTDOWN			0x08000000
 #define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
 #define NFS_MOUNT_FORCE_RDIRPLUS	0x20000000
+#define NFS_MOUNT_NETUNREACH_FATAL	0x40000000
 
 	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
-- 
cgit v1.2.3


From 9827144bfb2b1baf1e78600da73dcc9e92e28415 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 20 Mar 2025 10:50:26 -0400
Subject: NFS: Treat ENETUNREACH errors as fatal in containers

Propagate the NFS_MOUNT_NETUNREACH_FATAL flag to work with the generic
NFS client. If the flag is set, the client will receive ENETDOWN and
ENETUNREACH errors from the RPC layer, and is expected to treat them as
being fatal.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/client.c               |  5 +++++
 fs/nfs/nfs4client.c           |  2 ++
 fs/nfs/nfs4proc.c             |  3 +++
 include/linux/nfs_fs_sb.h     |  1 +
 include/linux/sunrpc/clnt.h   |  5 ++++-
 include/linux/sunrpc/sched.h  |  1 +
 include/trace/events/sunrpc.h |  1 +
 net/sunrpc/clnt.c             | 30 ++++++++++++++++++++++--------
 8 files changed, 39 insertions(+), 9 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 3b0918ade53c..02c916a55020 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -546,6 +546,8 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 		args.flags |= RPC_CLNT_CREATE_NOPING;
 	if (test_bit(NFS_CS_REUSEPORT, &clp->cl_flags))
 		args.flags |= RPC_CLNT_CREATE_REUSEPORT;
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+		args.flags |= RPC_CLNT_CREATE_NETUNREACH_FATAL;
 
 	if (!IS_ERR(clp->cl_rpcclient))
 		return 0;
@@ -709,6 +711,9 @@ static int nfs_init_server(struct nfs_server *server,
 	if (ctx->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
+	if (ctx->flags & NFS_MOUNT_NETUNREACH_FATAL)
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
+
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
 	if (IS_ERR(clp))
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 83378f69b35e..8f7d40844cdc 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -233,6 +233,8 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
 	if (test_bit(NFS_CS_PNFS, &cl_init->init_flags))
 		__set_bit(NFS_CS_PNFS, &clp->cl_flags);
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &cl_init->init_flags))
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags);
 	/*
 	 * Set up the connection to the server before we add add to the
 	 * global list.
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 24406fc1352d..889511650ceb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -195,6 +195,9 @@ static int nfs4_map_errors(int err)
 		return -EBUSY;
 	case -NFS4ERR_NOT_SAME:
 		return -ENOTSYNC;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		break;
 	default:
 		dprintk("%s could not handle NFSv4 error %d\n",
 				__func__, -err);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a6ce8590eaaf..71319637a84e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -50,6 +50,7 @@ struct nfs_client {
 #define NFS_CS_DS		7		/* - Server is a DS */
 #define NFS_CS_REUSEPORT	8		/* - reuse src port on reconnect */
 #define NFS_CS_PNFS		9		/* - Server used for pnfs */
+#define NFS_CS_NETUNREACH_FATAL	10		/* - ENETUNREACH errors are fatal */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index fec976e58174..f8b406b0a1af 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -64,7 +64,9 @@ struct rpc_clnt {
 				cl_noretranstimeo: 1,/* No retransmit timeouts */
 				cl_autobind : 1,/* use getport() */
 				cl_chatty   : 1,/* be verbose */
-				cl_shutdown : 1;/* rpc immediate -EIO */
+				cl_shutdown : 1,/* rpc immediate -EIO */
+				cl_netunreach_fatal : 1;
+						/* Treat ENETUNREACH errors as fatal */
 	struct xprtsec_parms	cl_xprtsec;	/* transport security policy */
 
 	struct rpc_rtt *	cl_rtt;		/* RTO estimator data */
@@ -175,6 +177,7 @@ struct rpc_add_xprt_test {
 #define RPC_CLNT_CREATE_SOFTERR		(1UL << 10)
 #define RPC_CLNT_CREATE_REUSEPORT	(1UL << 11)
 #define RPC_CLNT_CREATE_CONNECTED	(1UL << 12)
+#define RPC_CLNT_CREATE_NETUNREACH_FATAL	(1UL << 13)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index eac57914dcf3..ccba79ebf893 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -134,6 +134,7 @@ struct rpc_task_setup {
 #define RPC_TASK_MOVEABLE	0x0004		/* nfs4.1+ rpc tasks */
 #define RPC_TASK_NULLCREDS	0x0010		/* Use AUTH_NULL credential */
 #define RPC_CALL_MAJORSEEN	0x0020		/* major timeout seen */
+#define RPC_TASK_NETUNREACH_FATAL 0x0040	/* ENETUNREACH is fatal */
 #define RPC_TASK_DYNAMIC	0x0080		/* task was kmalloc'ed */
 #define	RPC_TASK_NO_ROUND_ROBIN	0x0100		/* send requests on "main" xprt */
 #define RPC_TASK_SOFT		0x0200		/* Use soft timeouts */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 851841336ee6..5d331383047b 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -343,6 +343,7 @@ TRACE_EVENT(rpc_request,
 		{ RPC_TASK_MOVEABLE, "MOVEABLE" },			\
 		{ RPC_TASK_NULLCREDS, "NULLCREDS" },			\
 		{ RPC_CALL_MAJORSEEN, "MAJORSEEN" },			\
+		{ RPC_TASK_NETUNREACH_FATAL, "NETUNREACH_FATAL"},	\
 		{ RPC_TASK_DYNAMIC, "DYNAMIC" },			\
 		{ RPC_TASK_NO_ROUND_ROBIN, "NO_ROUND_ROBIN" },		\
 		{ RPC_TASK_SOFT, "SOFT" },				\
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 2fe88ea79a70..1cfaf93ceec1 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -512,6 +512,8 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 		clnt->cl_discrtry = 1;
 	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
 		clnt->cl_chatty = 1;
+	if (args->flags & RPC_CLNT_CREATE_NETUNREACH_FATAL)
+		clnt->cl_netunreach_fatal = 1;
 
 	return clnt;
 }
@@ -662,6 +664,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	new->cl_noretranstimeo = clnt->cl_noretranstimeo;
 	new->cl_discrtry = clnt->cl_discrtry;
 	new->cl_chatty = clnt->cl_chatty;
+	new->cl_netunreach_fatal = clnt->cl_netunreach_fatal;
 	new->cl_principal = clnt->cl_principal;
 	new->cl_max_connect = clnt->cl_max_connect;
 	return new;
@@ -1195,6 +1198,8 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
 		task->tk_flags |= RPC_TASK_TIMEOUT;
 	if (clnt->cl_noretranstimeo)
 		task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT;
+	if (clnt->cl_netunreach_fatal)
+		task->tk_flags |= RPC_TASK_NETUNREACH_FATAL;
 	atomic_inc(&clnt->cl_task_count);
 }
 
@@ -2102,14 +2107,17 @@ call_bind_status(struct rpc_task *task)
 	case -EPROTONOSUPPORT:
 		trace_rpcb_bind_version_err(task);
 		goto retry_timeout;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL)
+			break;
+		fallthrough;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENOTCONN:
 	case -EHOSTDOWN:
-	case -ENETDOWN:
 	case -EHOSTUNREACH:
-	case -ENETUNREACH:
 	case -EPIPE:
 		trace_rpcb_unreachable_err(task);
 		if (!RPC_IS_SOFTCONN(task)) {
@@ -2191,19 +2199,22 @@ call_connect_status(struct rpc_task *task)
 
 	task->tk_status = 0;
 	switch (status) {
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL)
+			break;
+		fallthrough;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 		/* A positive refusal suggests a rebind is needed. */
-		if (RPC_IS_SOFTCONN(task))
-			break;
 		if (clnt->cl_autobind) {
 			rpc_force_rebind(clnt);
+			if (RPC_IS_SOFTCONN(task))
+				break;
 			goto out_retry;
 		}
 		fallthrough;
 	case -ECONNABORTED:
-	case -ENETDOWN:
-	case -ENETUNREACH:
 	case -EHOSTUNREACH:
 	case -EPIPE:
 	case -EPROTO:
@@ -2455,10 +2466,13 @@ call_status(struct rpc_task *task)
 	trace_rpc_call_status(task);
 	task->tk_status = 0;
 	switch(status) {
-	case -EHOSTDOWN:
 	case -ENETDOWN:
-	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+		if (task->tk_flags & RPC_TASK_NETUNREACH_FATAL)
+			goto out_exit;
+		fallthrough;
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
 	case -EPERM:
 		if (RPC_IS_SOFTCONN(task))
 			goto out_exit;
-- 
cgit v1.2.3


From 8c9f0df7a82a9f3bbdab4c796d302b20a33c1cc6 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 20 Mar 2025 08:04:35 -0400
Subject: pNFS/flexfiles: Treat ENETUNREACH errors as fatal in containers

Propagate the NFS_MOUNT_NETUNREACH_FATAL flag to work with the pNFS
flexfiles client. In these circumstances, the client needs to treat the
ENETDOWN and ENETUNREACH errors as fatal, and should abandon the
attempted I/O.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 23 +++++++++++++++++++++--
 fs/nfs/nfs3client.c                    |  2 ++
 fs/nfs/nfs4client.c                    |  5 +++++
 include/linux/nfs4.h                   |  1 +
 4 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 98b45b636be3..f89fdba7289d 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1154,10 +1154,14 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		goto reset;
 	/* RPC connection errors */
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+			return -NFS4ERR_FATAL_IOERROR;
+		fallthrough;
 	case -ECONNREFUSED:
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
-	case -ENETUNREACH:
 	case -EIO:
 	case -ETIMEDOUT:
 	case -EPIPE:
@@ -1183,6 +1187,7 @@ reset:
 
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
+					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
 					   u32 idx)
 {
@@ -1200,6 +1205,11 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 	case -EJUKEBOX:
 		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
 		goto out_retry;
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+			return -NFS4ERR_FATAL_IOERROR;
+		fallthrough;
 	default:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
@@ -1234,7 +1244,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 
 	switch (vers) {
 	case 3:
-		return ff_layout_async_handle_error_v3(task, lseg, idx);
+		return ff_layout_async_handle_error_v3(task, clp, lseg, idx);
 	case 4:
 		return ff_layout_async_handle_error_v4(task, state, clp,
 						       lseg, idx);
@@ -1337,6 +1347,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 		return task->tk_status;
 	case -EAGAIN:
 		goto out_eagain;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	return 0;
@@ -1507,6 +1520,9 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 		return task->tk_status;
 	case -EAGAIN:
 		return -EAGAIN;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
@@ -1551,6 +1567,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 	case -EAGAIN:
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
+	case -NFS4ERR_FATAL_IOERROR:
+		task->tk_status = -EIO;
+		return 0;
 	}
 
 	ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index b0c8a39c2bbd..0d7310c1ee0c 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -120,6 +120,8 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &mds_clp->cl_flags))
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
 
 	__set_bit(NFS_CS_DS, &cl_init.init_flags);
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8f7d40844cdc..162c85a83a14 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -939,6 +939,9 @@ static int nfs4_set_client(struct nfs_server *server,
 		__set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
 	server->port = rpc_get_port((struct sockaddr *)addr);
 
+	if (server->flags & NFS_MOUNT_NETUNREACH_FATAL)
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
+
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
 	if (IS_ERR(clp))
@@ -1013,6 +1016,8 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (test_bit(NFS_CS_NETUNREACH_FATAL, &mds_clp->cl_flags))
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
 
 	__set_bit(NFS_CS_PNFS, &cl_init.init_flags);
 	cl_init.max_connect = NFS_MAX_TRANSPORTS;
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 5fa60fe441b5..d8cad844870a 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -300,6 +300,7 @@ enum nfsstat4 {
 /* error codes for internal client use */
 #define NFS4ERR_RESET_TO_MDS   12001
 #define NFS4ERR_RESET_TO_PNFS  12002
+#define NFS4ERR_FATAL_IOERROR  12003
 
 static inline bool seqid_mutating_err(u32 err)
 {
-- 
cgit v1.2.3


From aa42add73ce9b9e3714723d385c254b75814e335 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 20 Mar 2025 12:45:01 -0400
Subject: pNFS/flexfiles: Report ENETDOWN as a connection error

If the client should see an ENETDOWN when trying to connect to the data
server, it might still be able to talk to the metadata server through
another NIC. If so, report the error.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs')

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index f89fdba7289d..61ad269c825f 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1274,6 +1274,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		case -ECONNRESET:
 		case -EHOSTDOWN:
 		case -EHOSTUNREACH:
+		case -ENETDOWN:
 		case -ENETUNREACH:
 		case -EADDRINUSE:
 		case -ENOBUFS:
-- 
cgit v1.2.3


From 2d3e998a0bc7fe26a724f87a8ce217848040520e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 25 Mar 2025 17:58:50 -0400
Subject: NFS: Shut down the nfs_client only after all the superblocks

The nfs_client manages state for all the superblocks in the
"cl_superblocks" list, so it must not be shut down until all of them are
gone.

Fixes: 7d3e26a054c8 ("NFS: Cancel all existing RPC tasks when shutdown")
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/sysfs.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index b30401b2c939..37cb2b776435 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -14,6 +14,7 @@
 #include <linux/rcupdate.h>
 #include <linux/lockd/lockd.h>
 
+#include "internal.h"
 #include "nfs4_fs.h"
 #include "netns.h"
 #include "sysfs.h"
@@ -228,6 +229,25 @@ static void shutdown_client(struct rpc_clnt *clnt)
 	rpc_cancel_tasks(clnt, -EIO, shutdown_match_client, NULL);
 }
 
+/*
+ * Shut down the nfs_client only once all the superblocks
+ * have been shut down.
+ */
+static void shutdown_nfs_client(struct nfs_client *clp)
+{
+	struct nfs_server *server;
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		if (!(server->flags & NFS_MOUNT_SHUTDOWN)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+	nfs_mark_client_ready(clp, -EIO);
+	shutdown_client(clp->cl_rpcclient);
+}
+
 static ssize_t
 shutdown_show(struct kobject *kobj, struct kobj_attribute *attr,
 				char *buf)
@@ -259,7 +279,6 @@ shutdown_store(struct kobject *kobj, struct kobj_attribute *attr,
 
 	server->flags |= NFS_MOUNT_SHUTDOWN;
 	shutdown_client(server->client);
-	shutdown_client(server->nfs_client->cl_rpcclient);
 
 	if (!IS_ERR(server->client_acl))
 		shutdown_client(server->client_acl);
@@ -267,6 +286,7 @@ shutdown_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (server->nlm_host)
 		shutdown_client(server->nlm_host->h_rpcclnt);
 out:
+	shutdown_nfs_client(server->nfs_client);
 	return count;
 }
 
-- 
cgit v1.2.3


From 3eba080e4d4f7bcc22ba19b43ab5fd412d99d1ba Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 25 Mar 2025 18:18:40 -0400
Subject: NFSv4: Further cleanups to shutdown loops

Replace the tests for the RPC client being shut down with tests for
whether the nfs_client is in an error state.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4proc.c  | 2 +-
 fs/nfs/nfs4state.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 889511650ceb..50be54e0f578 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9580,7 +9580,7 @@ static void nfs41_sequence_call_done(struct rpc_task *task, void *data)
 		return;
 
 	trace_nfs4_sequence(clp, task->tk_status);
-	if (task->tk_status < 0 && !task->tk_client->cl_shutdown) {
+	if (task->tk_status < 0 && clp->cl_cons_state >= 0) {
 		dprintk("%s ERROR %d\n", __func__, task->tk_status);
 		if (refcount_read(&clp->cl_count) == 1)
 			return;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 542cdf71229f..f1f7eaa97973 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1198,7 +1198,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 	struct rpc_clnt *clnt = clp->cl_rpcclient;
 	bool swapon = false;
 
-	if (clnt->cl_shutdown)
+	if (clp->cl_cons_state < 0)
 		return;
 
 	set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
-- 
cgit v1.2.3


From c81d5bcb7b38ab0322aea93152c091451b82d3f3 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 24 Mar 2025 20:03:03 -0400
Subject: NFSv4: clp->cl_cons_state < 0 signifies an invalid nfs_client

If someone calls nfs_mark_client_ready(clp, status) with a negative
value for status, then that should signal that the nfs_client is no
longer valid.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4state.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f1f7eaa97973..272d2ebdae0f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1403,7 +1403,7 @@ int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_
 	dprintk("%s: scheduling stateid recovery for server %s\n", __func__,
 			clp->cl_hostname);
 	nfs4_schedule_state_manager(clp);
-	return 0;
+	return clp->cl_cons_state < 0 ? clp->cl_cons_state : 0;
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
 
-- 
cgit v1.2.3


From 0af5fb5ed3d2fd9e110c6112271f022b744a849a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 24 Mar 2025 20:35:33 -0400
Subject: NFSv4: Treat ENETUNREACH errors as fatal for state recovery

If a containerised process is killed and causes an ENETUNREACH or
ENETDOWN error to be propagated to the state manager, then mark the
nfs_client as being dead so that we don't loop in functions that are
expecting recovery to succeed.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4state.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 272d2ebdae0f..7612e977e80b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2739,7 +2739,15 @@ out_error:
 	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
 			" with error %d\n", section_sep, section,
 			clp->cl_hostname, -status);
-	ssleep(1);
+	switch (status) {
+	case -ENETDOWN:
+	case -ENETUNREACH:
+		nfs_mark_client_ready(clp, -EIO);
+		break;
+	default:
+		ssleep(1);
+		break;
+	}
 out_drain:
 	memalloc_nofs_restore(memflags);
 	nfs4_end_drain_session(clp);
-- 
cgit v1.2.3


From 8d3ca331026a7f9700d3747eed59a67b8f828cdc Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 28 Mar 2025 13:19:18 -0400
Subject: NFS: Don't allow waiting for exiting tasks

Once a task calls exit_signals() it can no longer be signalled. So do
not allow it to do killable waits.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/inode.c    | 2 ++
 fs/nfs/internal.h | 5 +++++
 fs/nfs/nfs3proc.c | 2 +-
 fs/nfs/nfs4proc.c | 9 +++++++--
 4 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 1aa67fca69b2..119e447758b9 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -74,6 +74,8 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
 
 int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index fae2c7ae4acc..2133b3c20bad 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -912,6 +912,11 @@ static inline u32 nfs_stateid_hash(nfs4_stateid *stateid)
 }
 #endif
 
+static inline bool nfs_current_task_exiting(void)
+{
+	return (current->flags & PF_EXITING) != 0;
+}
+
 static inline bool nfs_error_is_fatal(int err)
 {
 	switch (err) {
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 0c3bc98cd999..c1736dbb92b6 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -39,7 +39,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 		__set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 		schedule_timeout(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
-	} while (!fatal_signal_pending(current));
+	} while (!fatal_signal_pending(current) && !nfs_current_task_exiting());
 	return res;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 50be54e0f578..da97f87ecaa9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -446,6 +446,8 @@ static int nfs4_delay_killable(long *timeout)
 {
 	might_sleep();
 
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	__set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 	schedule_timeout(nfs4_update_delay(timeout));
 	if (!__fatal_signal_pending(current))
@@ -457,6 +459,8 @@ static int nfs4_delay_interruptible(long *timeout)
 {
 	might_sleep();
 
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE_UNSAFE);
 	schedule_timeout(nfs4_update_delay(timeout));
 	if (!signal_pending(current))
@@ -1777,7 +1781,8 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state,
 		rcu_read_unlock();
 		trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0);
 
-		if (!fatal_signal_pending(current)) {
+		if (!fatal_signal_pending(current) &&
+		    !nfs_current_task_exiting()) {
 			if (schedule_timeout(5*HZ) == 0)
 				status = -EAGAIN;
 			else
@@ -3581,7 +3586,7 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst,
 		write_sequnlock(&state->seqlock);
 		trace_nfs4_close_stateid_update_wait(state->inode, dst, 0);
 
-		if (fatal_signal_pending(current))
+		if (fatal_signal_pending(current) || nfs_current_task_exiting())
 			status = -EINTR;
 		else
 			if (schedule_timeout(5*HZ) != 0)
-- 
cgit v1.2.3


From 9e8f324bd44c1fe026b582b75213de4eccfa1163 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 27 Mar 2025 19:20:53 -0400
Subject: NFSv4: Check for delegation validity in
 nfs_start_delegation_return_locked()

Check that the delegation is still attached after taking the spin lock
in nfs_start_delegation_return_locked().

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/delegation.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 325ba0663a6d..8bdbc4dca89c 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -307,7 +307,8 @@ nfs_start_delegation_return_locked(struct nfs_inode *nfsi)
 	if (delegation == NULL)
 		goto out;
 	spin_lock(&delegation->lock);
-	if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+	if (delegation->inode &&
+	    !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
 		clear_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags);
 		/* Refcount matched in nfs_end_delegation_return() */
 		ret = nfs_get_delegation(delegation);
-- 
cgit v1.2.3


From 8e5419d6542fdf2dca9a0acdef2b8255f0e4ba69 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 2 Apr 2025 14:02:40 +0300
Subject: nfs: Add missing release on error in nfs_lock_and_join_requests()

Call nfs_release_request() on this error path before returning.

Fixes: c3f2235782c3 ("nfs: fold nfs_folio_find_and_lock_request into nfs_lock_and_join_requests")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/3aaaa3d5-1c8a-41e4-98c7-717801ddd171@stanley.mountain
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/write.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index aa3d8bea3ec0..23df8b214474 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -579,8 +579,10 @@ retry:
 
 	while (!nfs_lock_request(head)) {
 		ret = nfs_wait_on_request(head);
-		if (ret < 0)
+		if (ret < 0) {
+			nfs_release_request(head);
 			return ERR_PTR(ret);
+		}
 	}
 
 	/* Ensure that nobody removed the request before we locked it */
-- 
cgit v1.2.3