Merge tag 'nfs-for-6.16-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS clent updates from Anna Schumaker:
 "New Features:

   - Implement the Sunrpc rfc2203 rpcsec_gss sequence number cache

   - Add support for FALLOC_FL_ZERO_RANGE on NFS v4.2

   - Add a localio sysfs attribute

  Stable Fixes:

   - Fix double-unlock bug in nfs_return_empty_folio()

   - Don't check for OPEN feature support in v4.1

   - Always probe for LOCALIO support asynchronously

   - Prevent hang on NFS mounts with xprtsec=[m]tls

  Other Bugfixes:

   - xattr handlers should check for absent nfs filehandles

   - Fix setattr caching of TIME_[MODIFY|ACCESS]_SET when timestamps are
     delegated

   - Fix listxattr to return selinux security labels

   - Connect to NFSv3 DS using TLS if MDS connection uses TLS

   - Clear SB_RDONLY before getting a superblock, and ignore when
     remounting

   - Fix incorrect handling of NFS error codes in nfs4_do_mkdir()

   - Various nfs_localio fixes from Neil Brown that include fixing an
     rcu compilation error found by older gcc versions.

   - Update stats on flexfiles pNFS DSes when receiving NFS4ERR_DELAY

  Cleanups:

   - Add a refcount tracker for struct net in the nfs_client

   - Allow FREE_STATEID to clean up delegations

   - Always set NLINK even if the server doesn't support it

   - Cleanups to the NFS folio writeback code

   - Remove dead code from xs_tcp_tls_setup_socket()"

* tag 'nfs-for-6.16-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (30 commits)
  flexfiles/pNFS: update stats on NFS4ERR_DELAY for v4.1 DSes
  nfs_localio: change nfsd_file_put_local() to take a pointer to __rcu pointer
  nfs_localio: protect race between nfs_uuid_put() and nfs_close_local_fh()
  nfs_localio: duplicate nfs_close_local_fh()
  nfs_localio: simplify interface to nfsd for getting nfsd_file
  nfs_localio: always hold nfsd net ref with nfsd_file ref
  nfs_localio: use cmpxchg() to install new nfs_file_localio
  SUNRPC: Remove dead code from xs_tcp_tls_setup_socket()
  SUNRPC: Prevent hang on NFS mount with xprtsec=[m]tls
  nfs: fix incorrect handling of large-number NFS errors in nfs4_do_mkdir()
  nfs: ignore SB_RDONLY when remounting nfs
  nfs: clear SB_RDONLY before getting superblock
  NFS: always probe for LOCALIO support asynchronously
  pnfs/flexfiles: connect to NFSv3 DS using TLS if MDS connection uses TLS
  NFS: add localio to sysfs
  nfs: use writeback_iter directly
  nfs: refactor nfs_do_writepage
  nfs: don't return AOP_WRITEPAGE_ACTIVATE from nfs_do_writepage
  nfs: fold nfs_page_async_flush into nfs_do_writepage
  NFSv4: Always set NLINK even if the server doesn't support it
  ...

6 files changed, 36 insertions, 17 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index d8cad844870a..e947af6a3684 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -72,6 +72,7 @@ struct nfs4_stateid_struct {
 		NFS4_LAYOUT_STATEID_TYPE,
 		NFS4_PNFS_DS_STATEID_TYPE,
 		NFS4_REVOKED_STATEID_TYPE,
+		NFS4_FREED_STATEID_TYPE,
 	} type;
 };
 
@@ -678,6 +679,7 @@ enum {
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
+	NFSPROC4_CLNT_ZERO_RANGE,
 	NFSPROC4_CLNT_LAYOUTSTATS,
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index ee03f3cef30c..63141320c2a8 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -125,6 +125,7 @@ struct nfs_client {
 	 */
 	char			cl_ipaddr[48];
 	struct net		*cl_net;
+	netns_tracker		cl_ns_tracker;
 	struct list_head	pending_cb_stateids;
 	struct rcu_head		rcu;
 
@@ -303,6 +304,7 @@ struct nfs_server {
 #define NFS_CAP_CASE_PRESERVING	(1U << 7)
 #define NFS_CAP_REBOOT_LAYOUTRETURN	(1U << 8)
 #define NFS_CAP_OFFLOAD_STATUS	(1U << 9)
+#define NFS_CAP_ZERO_RANGE	(1U << 10)
 #define NFS_CAP_OPEN_XOR	(1U << 12)
 #define NFS_CAP_DELEGTIME	(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index 9aa8a43843d7..5c7c92659e73 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -50,10 +50,6 @@ void nfs_localio_invalidate_clients(struct list_head *nn_local_clients,
 				    spinlock_t *nn_local_clients_lock);
 
 /* localio needs to map filehandle -> struct nfsd_file */
-extern struct nfsd_file *
-nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *,
-		   const struct cred *, const struct nfs_fh *,
-		   const fmode_t) __must_hold(rcu);
 void nfs_close_local_fh(struct nfs_file_localio *);
 
 struct nfsd_localio_operations {
@@ -64,10 +60,10 @@ struct nfsd_localio_operations {
 						struct rpc_clnt *,
 						const struct cred *,
 						const struct nfs_fh *,
+						struct nfsd_file __rcu **pnf,
 						const fmode_t);
-	struct net *(*nfsd_file_put_local)(struct nfsd_file *);
-	struct nfsd_file *(*nfsd_file_get)(struct nfsd_file *);
-	void (*nfsd_file_put)(struct nfsd_file *);
+	struct net *(*nfsd_file_put_local)(struct nfsd_file __rcu **);
+	struct nfsd_file *(*nfsd_file_get_local)(struct nfsd_file *);
 	struct file *(*nfsd_file_file)(struct nfsd_file *);
 } ____cacheline_aligned;
 
@@ -77,6 +73,7 @@ extern const struct nfsd_localio_operations *nfs_to;
 struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
 		   struct rpc_clnt *, const struct cred *,
 		   const struct nfs_fh *, struct nfs_file_localio *,
+		   struct nfsd_file __rcu **pnf,
 		   const fmode_t);
 
 static inline void nfs_to_nfsd_net_put(struct net *net)
@@ -91,16 +88,19 @@ static inline void nfs_to_nfsd_net_put(struct net *net)
 	rcu_read_unlock();
 }
 
-static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+static inline void nfs_to_nfsd_file_put_local(struct nfsd_file __rcu **localio)
 {
 	/*
-	 * Must not hold RCU otherwise nfsd_file_put() can easily trigger:
-	 * "Voluntary context switch within RCU read-side critical section!"
-	 * by scheduling deep in underlying filesystem (e.g. XFS).
+	 * Either *localio must be guaranteed to be non-NULL, or caller
+	 * must prevent nfsd shutdown from completing as nfs_close_local_fh()
+	 * does by blocking the nfs_uuid from being finally put.
 	 */
-	struct net *net = nfs_to->nfsd_file_put_local(localio);
+	struct net *net;
 
-	nfs_to_nfsd_net_put(net);
+	net = nfs_to->nfsd_file_put_local(localio);
+
+	if (net)
+		nfs_to_nfsd_net_put(net);
 }
 
 #else   /* CONFIG_NFS_LOCALIO */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 81b952649d35..f46d1fb8f71a 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,6 +30,8 @@
 #define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
 #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
 
+#define RPC_GSS_SEQNO_ARRAY_SIZE 3U
+
 enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
@@ -66,7 +68,8 @@ struct rpc_rqst {
 	struct rpc_cred *	rq_cred;	/* Bound cred */
 	__be32			rq_xid;		/* request XID */
 	int			rq_cong;	/* has incremented xprt->cong */
-	u32			rq_seqno;	/* gss seq no. used on req. */
+	u32			rq_seqnos[RPC_GSS_SEQNO_ARRAY_SIZE];	/* past gss req seq nos. */
+	unsigned int		rq_seqno_count;	/* number of entries in rq_seqnos */
 	int			rq_enc_pages_num;
 	struct page		**rq_enc_pages;	/* scratch pages for use by
 						   gss privacy code */
@@ -119,6 +122,18 @@ struct rpc_rqst {
 #define rq_svec			rq_snd_buf.head
 #define rq_slen			rq_snd_buf.len
 
+static inline int xprt_rqst_add_seqno(struct rpc_rqst *req, u32 seqno)
+{
+	if (likely(req->rq_seqno_count < RPC_GSS_SEQNO_ARRAY_SIZE))
+		req->rq_seqno_count++;
+
+	/* Shift array to make room for the newest element at the beginning */
+	memmove(&req->rq_seqnos[1], &req->rq_seqnos[0],
+		(RPC_GSS_SEQNO_ARRAY_SIZE - 1) * sizeof(req->rq_seqnos[0]));
+	req->rq_seqnos[0] = seqno;
+	return 0;
+}
+
 /* RPC transport layer security policies */
 enum xprtsec_policies {
 	RPC_XPRTSEC_NONE = 0,
diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
index b0b6300a0cab..8aeae06cf434 100644
--- a/include/trace/events/rpcgss.h
+++ b/include/trace/events/rpcgss.h
@@ -409,7 +409,7 @@ TRACE_EVENT(rpcgss_seqno,
 		__entry->task_id = task->tk_pid;
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->seqno = rqst->rq_seqno;
+		__entry->seqno = *rqst->rq_seqnos;
 	),
 
 	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x seqno=%u",
@@ -440,7 +440,7 @@ TRACE_EVENT(rpcgss_need_reencode,
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
 		__entry->seq_xmit = seq_xmit;
-		__entry->seqno = task->tk_rqstp->rq_seqno;
+		__entry->seqno = *task->tk_rqstp->rq_seqnos;
 		__entry->ret = ret;
 	),
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 81f795150097..aad697da1580 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1098,7 +1098,7 @@ TRACE_EVENT(xprt_transmit,
 		__entry->client_id = rqst->rq_task->tk_client ?
 			rqst->rq_task->tk_client->cl_clid : -1;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->seqno = rqst->rq_seqno;
+		__entry->seqno = *rqst->rq_seqnos;
 		__entry->status = status;
 	),