Merge tag 'nfsd-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "The big ticket item for this release is that support for RPC-with-TLS
  [RFC 9289] has been added to the Linux NFS server.

  The goal is to provide a simple-to-deploy, low-overhead in-transit
  confidentiality and peer authentication mechanism. It can supplement
  NFS Kerberos and it can protect the use of legacy non-cryptographic
  user authentication flavors such as AUTH_SYS. The TLS Record protocol
  is handled entirely by kTLS, meaning it can use either software
  encryption or offload encryption to smart NICs.

  Aside from that, work continues on improving NFSD's open file cache.
  Among the many clean-ups in that area is a patch to convert the
  rhashtable to use the list-hashing version of that data structure"

* tag 'nfsd-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (31 commits)
  NFSD: Handle new xprtsec= export option
  SUNRPC: Support TLS handshake in the server-side TCP socket code
  NFSD: Clean up xattr memory allocation flags
  NFSD: Fix problem of COMMIT and NFS4ERR_DELAY in infinite loop
  SUNRPC: Clear rq_xid when receiving a new RPC Call
  SUNRPC: Recognize control messages in server-side TCP socket code
  SUNRPC: Be even lazier about releasing pages
  SUNRPC: Convert svc_xprt_release() to the release_pages() API
  SUNRPC: Relocate svc_free_res_pages()
  nfsd: simplify the delayed disposal list code
  SUNRPC: Ignore return value of ->xpo_sendto
  SUNRPC: Ensure server-side sockets have a sock->file
  NFSD: Watch for rq_pages bounds checking errors in nfsd_splice_actor()
  sunrpc: simplify two-level sysctl registration for svcrdma_parm_table
  SUNRPC: return proper error from get_expiry()
  lockd: add some client-side tracepoints
  nfs: move nfs_fhandle_hash to common include file
  lockd: server should unlock lock if client rejects the grant
  lockd: fix races in client GRANTED_MSG wait logic
  lockd: move struct nlm_wait to lockd.h
  ...

10 files changed, 109 insertions, 37 deletions

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 601700fedc91..9edb29101ec8 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -220,6 +220,7 @@ struct export_operations {
 #define EXPORT_OP_NOATOMIC_ATTR		(0x10) /* Filesystem cannot supply
 						  atomic attribute updates
 						*/
+#define EXPORT_OP_FLUSH_ON_CLOSE	(0x20) /* fs flushes file data on close */
 	unsigned long	flags;
 };
 
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 0168ac9fdda8..f42594a9efe0 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -99,21 +99,11 @@ struct nsm_handle {
 /*
  * Rigorous type checking on sockaddr type conversions
  */
-static inline struct sockaddr_in *nlm_addr_in(const struct nlm_host *host)
-{
-	return (struct sockaddr_in *)&host->h_addr;
-}
-
 static inline struct sockaddr *nlm_addr(const struct nlm_host *host)
 {
 	return (struct sockaddr *)&host->h_addr;
 }
 
-static inline struct sockaddr_in *nlm_srcaddr_in(const struct nlm_host *host)
-{
-	return (struct sockaddr_in *)&host->h_srcaddr;
-}
-
 static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host)
 {
 	return (struct sockaddr *)&host->h_srcaddr;
@@ -131,7 +121,16 @@ struct nlm_lockowner {
 	uint32_t pid;
 };
 
-struct nlm_wait;
+/*
+ * This is the representation of a blocked client lock.
+ */
+struct nlm_wait {
+	struct list_head	b_list;		/* linked list */
+	wait_queue_head_t	b_wait;		/* where to wait on */
+	struct nlm_host		*b_host;
+	struct file_lock	*b_lock;	/* local file lock */
+	__be32			b_status;	/* grant callback status */
+};
 
 /*
  * Memory chunk for NLM client RPC request.
@@ -212,9 +211,11 @@ struct nlm_rqst * nlm_alloc_call(struct nlm_host *host);
 int		  nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *);
 int		  nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *);
 void		  nlmclnt_release_call(struct nlm_rqst *);
-struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl);
-void		  nlmclnt_finish_block(struct nlm_wait *block);
-int		  nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout);
+void		  nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host,
+					struct file_lock *fl);
+void		  nlmclnt_queue_block(struct nlm_wait *block);
+__be32		  nlmclnt_dequeue_block(struct nlm_wait *block);
+int		  nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout);
 __be32		  nlmclnt_grant(const struct sockaddr *addr,
 				const struct nlm_lock *lock);
 void		  nlmclnt_recovery(struct nlm_host *);
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index b06375e88e58..ceb70a926b95 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -10,6 +10,7 @@
 
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/string.h>
+#include <linux/crc32.h>
 #include <uapi/linux/nfs.h>
 
 /*
@@ -44,4 +45,23 @@ enum nfs3_stable_how {
 	/* used by direct.c to mark verf as invalid */
 	NFS_INVALID_STABLE_HOW = -1
 };
+
+#ifdef CONFIG_CRC32
+/**
+ * nfs_fhandle_hash - calculate the crc32 hash for the filehandle
+ * @fh - pointer to filehandle
+ *
+ * returns a crc32 hash for the filehandle that is compatible with
+ * the one displayed by "wireshark".
+ */
+static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
+{
+	return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size);
+}
+#else /* CONFIG_CRC32 */
+static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
+{
+	return 0;
+}
+#endif /* CONFIG_CRC32 */
 #endif /* _LINUX_NFS_H */
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index ec5a555df96f..518bd28f5ab8 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -300,17 +300,18 @@ static inline int get_time(char **bpp, time64_t *time)
 	return 0;
 }
 
-static inline time64_t get_expiry(char **bpp)
+static inline int get_expiry(char **bpp, time64_t *rvp)
 {
-	time64_t rv;
+	int error;
 	struct timespec64 boot;
 
-	if (get_time(bpp, &rv))
-		return 0;
-	if (rv < 0)
-		return 0;
+	error = get_time(bpp, rvp);
+	if (error)
+		return error;
+
 	getboottime64(&boot);
-	return rv - boot.tv_sec;
+	(*rvp) -= boot.tv_sec;
+	return 0;
 }
 
 #endif /*  _LINUX_SUNRPC_CACHE_H_ */
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 877891536c2f..762d7231e574 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -309,17 +309,6 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst)
 	return (struct sockaddr *) &rqst->rq_daddr;
 }
 
-static inline void svc_free_res_pages(struct svc_rqst *rqstp)
-{
-	while (rqstp->rq_next_page != rqstp->rq_respages) {
-		struct page **pp = --rqstp->rq_next_page;
-		if (*pp) {
-			put_page(*pp);
-			*pp = NULL;
-		}
-	}
-}
-
 struct svc_deferred_req {
 	u32			prot;	/* protocol (UDP or TCP) */
 	struct svc_xprt		*xprt;
@@ -422,15 +411,16 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int,
 			    int (*threadfn)(void *data));
 struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv,
 					struct svc_pool *pool, int node);
-void		   svc_rqst_replace_page(struct svc_rqst *rqstp,
+bool		   svc_rqst_replace_page(struct svc_rqst *rqstp,
 					 struct page *page);
+void		   svc_rqst_release_pages(struct svc_rqst *rqstp);
 void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 				     int (*threadfn)(void *data));
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
-int		   svc_process(struct svc_rqst *);
+void		   svc_process(struct svc_rqst *rqstp);
 int		   bc_svc_process(struct svc_serv *, struct rpc_rqst *,
 			struct svc_rqst *);
 int		   svc_register(const struct svc_serv *, struct net *, const int,
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 775368802762..867479204840 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -27,7 +27,7 @@ struct svc_xprt_ops {
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);
 	void		(*xpo_kill_temp_xprt)(struct svc_xprt *);
-	void		(*xpo_start_tls)(struct svc_xprt *);
+	void		(*xpo_handshake)(struct svc_xprt *xprt);
 };
 
 struct svc_xprt_class {
@@ -70,6 +70,9 @@ struct svc_xprt {
 #define XPT_LOCAL	12		/* connection from loopback interface */
 #define XPT_KILL_TEMP   13		/* call xpo_kill_temp_xprt before closing */
 #define XPT_CONG_CTRL	14		/* has congestion control */
+#define XPT_HANDSHAKE	15		/* xprt requests a handshake */
+#define XPT_TLS_SESSION	16		/* transport-layer security established */
+#define XPT_PEER_AUTH	17		/* peer has been authenticated */
 
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index bcc555c7ae9c..d16ae621782c 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -38,6 +38,8 @@ struct svc_sock {
 	/* Number of queued send requests */
 	atomic_t		sk_sendqlen;
 
+	struct completion	sk_handshake_done;
+
 	struct page *		sk_pages[RPCSVC_MAXPAGES];	/* received data */
 };
 
@@ -56,7 +58,7 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk)
  */
 void		svc_close_net(struct svc_serv *, struct net *);
 int		svc_recv(struct svc_rqst *, long);
-int		svc_send(struct svc_rqst *);
+void		svc_send(struct svc_rqst *rqstp);
 void		svc_drop(struct svc_rqst *);
 void		svc_sock_update_bufs(struct svc_serv *serv);
 bool		svc_alien_sock(struct net *net, int fd);
diff --git a/include/net/tls.h b/include/net/tls.h
index 154949c7b0c8..6056ce5a2aa5 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -69,6 +69,8 @@ extern const struct tls_cipher_size_desc tls_cipher_size_desc[];
 
 #define TLS_CRYPTO_INFO_READY(info)	((info)->cipher_type)
 
+#define TLS_RECORD_TYPE_ALERT		0x15
+#define TLS_RECORD_TYPE_HANDSHAKE	0x16
 #define TLS_RECORD_TYPE_DATA		0x17
 
 #define TLS_AAD_SPACE_SIZE		13
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 3ca54536f8f7..31bc7025cb44 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1790,6 +1790,31 @@ DEFINE_EVENT(svc_rqst_status, svc_send,
 	TP_PROTO(const struct svc_rqst *rqst, int status),
 	TP_ARGS(rqst, status));
 
+TRACE_EVENT(svc_replace_page_err,
+	TP_PROTO(const struct svc_rqst *rqst),
+
+	TP_ARGS(rqst),
+	TP_STRUCT__entry(
+		SVC_RQST_ENDPOINT_FIELDS(rqst)
+
+		__field(const void *, begin)
+		__field(const void *, respages)
+		__field(const void *, nextpage)
+	),
+
+	TP_fast_assign(
+		SVC_RQST_ENDPOINT_ASSIGNMENTS(rqst);
+
+		__entry->begin = rqst->rq_pages;
+		__entry->respages = rqst->rq_respages;
+		__entry->nextpage = rqst->rq_next_page;
+	),
+
+	TP_printk(SVC_RQST_ENDPOINT_FORMAT " begin=%p respages=%p nextpage=%p",
+		SVC_RQST_ENDPOINT_VARARGS,
+		__entry->begin, __entry->respages, __entry->nextpage)
+);
+
 TRACE_EVENT(svc_stats_latency,
 	TP_PROTO(
 		const struct svc_rqst *rqst
@@ -1832,7 +1857,10 @@ TRACE_EVENT(svc_stats_latency,
 		{ BIT(XPT_CACHE_AUTH),		"CACHE_AUTH" },		\
 		{ BIT(XPT_LOCAL),		"LOCAL" },		\
 		{ BIT(XPT_KILL_TEMP),		"KILL_TEMP" },		\
-		{ BIT(XPT_CONG_CTRL),		"CONG_CTRL" })
+		{ BIT(XPT_CONG_CTRL),		"CONG_CTRL" },		\
+		{ BIT(XPT_HANDSHAKE),		"HANDSHAKE" },		\
+		{ BIT(XPT_TLS_SESSION),		"TLS_SESSION" },	\
+		{ BIT(XPT_PEER_AUTH),		"PEER_AUTH" })
 
 TRACE_EVENT(svc_xprt_create_err,
 	TP_PROTO(
@@ -1965,6 +1993,17 @@ DEFINE_SVC_XPRT_EVENT(close);
 DEFINE_SVC_XPRT_EVENT(detach);
 DEFINE_SVC_XPRT_EVENT(free);
 
+#define DEFINE_SVC_TLS_EVENT(name) \
+	DEFINE_EVENT(svc_xprt_event, svc_tls_##name, \
+		TP_PROTO(const struct svc_xprt *xprt), \
+		TP_ARGS(xprt))
+
+DEFINE_SVC_TLS_EVENT(start);
+DEFINE_SVC_TLS_EVENT(upcall);
+DEFINE_SVC_TLS_EVENT(unavailable);
+DEFINE_SVC_TLS_EVENT(not_started);
+DEFINE_SVC_TLS_EVENT(timed_out);
+
 TRACE_EVENT(svc_xprt_accept,
 	TP_PROTO(
 		const struct svc_xprt *xprt,
diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h
index 2124ba904779..a73ca3703abb 100644
--- a/include/uapi/linux/nfsd/export.h
+++ b/include/uapi/linux/nfsd/export.h
@@ -62,5 +62,18 @@
 					| NFSEXP_ALLSQUASH \
 					| NFSEXP_INSECURE_PORT)
 
+/*
+ * Transport layer security policies that are permitted to access
+ * an export
+ */
+#define NFSEXP_XPRTSEC_NONE	0x0001
+#define NFSEXP_XPRTSEC_TLS	0x0002
+#define NFSEXP_XPRTSEC_MTLS	0x0004
+
+#define NFSEXP_XPRTSEC_NUM	(3)
+
+#define NFSEXP_XPRTSEC_ALL	(NFSEXP_XPRTSEC_NONE | \
+				 NFSEXP_XPRTSEC_TLS | \
+				 NFSEXP_XPRTSEC_MTLS)
 
 #endif /* _UAPINFSD_EXPORT_H */