Merge tag 'nfsd-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:

 - Clean-ups in the READ path in anticipation of MSG_SPLICE_PAGES

 - Better NUMA awareness when allocating pages and other objects

 - A number of minor clean-ups to XDR encoding

 - Elimination of a race when accepting a TCP socket

 - Numerous observability enhancements

* tag 'nfsd-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (46 commits)
  nfsd: remove redundant assignments to variable len
  svcrdma: Fix stale comment
  NFSD: Distinguish per-net namespace initialization
  nfsd: move init of percpu reply_cache_stats counters back to nfsd_init_net
  SUNRPC: Address RCU warning in net/sunrpc/svc.c
  SUNRPC: Use sysfs_emit in place of strlcpy/sprintf
  SUNRPC: Remove transport class dprintk call sites
  SUNRPC: Fix comments for transport class registration
  svcrdma: Remove an unused argument from __svc_rdma_put_rw_ctxt()
  svcrdma: trace cc_release calls
  svcrdma: Convert "might sleep" comment into a code annotation
  NFSD: Add an nfsd4_encode_nfstime4() helper
  SUNRPC: Move initialization of rq_stime
  SUNRPC: Optimize page release in svc_rdma_sendto()
  svcrdma: Prevent page release when nothing was received
  svcrdma: Revert 2a1e4f21d841 ("svcrdma: Normalize Send page handling")
  SUNRPC: Revert 579900670ac7 ("svcrdma: Remove unused sc_pages field")
  SUNRPC: Revert cc93ce9529a6 ("svcrdma: Retain the page backing rq_res.head[0].iov_base")
  NFSD: add encoding of op_recall flag for write delegation
  NFSD: Add "official" reviewers for this subsystem
  ...

5 files changed, 59 insertions, 17 deletions

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 762d7231e574..3b10636c51a9 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -509,6 +509,27 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp)
 }
 
 /**
+ * svcxdr_encode_opaque_pages - Insert pages into an xdr_stream
+ * @xdr: xdr_stream to be updated
+ * @pages: array of pages to insert
+ * @base: starting offset of first data byte in @pages
+ * @len: number of data bytes in @pages to insert
+ *
+ * After the @pages are added, the tail iovec is instantiated pointing
+ * to end of the head buffer, and the stream is set up to encode
+ * subsequent items into the tail.
+ */
+static inline void svcxdr_encode_opaque_pages(struct svc_rqst *rqstp,
+					      struct xdr_stream *xdr,
+					      struct page **pages,
+					      unsigned int base,
+					      unsigned int len)
+{
+	xdr_write_pages(xdr, pages, base, len);
+	xdr->page_ptr = rqstp->rq_next_page - 1;
+}
+
+/**
  * svcxdr_set_auth_slack -
  * @rqstp: RPC transaction
  * @slack: buffer space to reserve for the transaction's security flavor
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index fbc4bd423b35..a5ee0af2a310 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -135,7 +135,6 @@ struct svc_rdma_recv_ctxt {
 	struct ib_sge		rc_recv_sge;
 	void			*rc_recv_buf;
 	struct xdr_stream	rc_stream;
-	bool			rc_temp;
 	u32			rc_byte_len;
 	unsigned int		rc_page_count;
 	u32			rc_inv_rkey;
@@ -155,12 +154,12 @@ struct svc_rdma_send_ctxt {
 
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
-	struct completion	sc_done;
 	struct xdr_buf		sc_hdrbuf;
 	struct xdr_stream	sc_stream;
 	void			*sc_xprt_buf;
+	int			sc_page_count;
 	int			sc_cur_sge_no;
-
+	struct page		*sc_pages[RPCSVC_MAXPAGES];
 	struct ib_sge		sc_sges[];
 };
 
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 72014c9216fc..f89ec4b5ea16 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -242,8 +242,7 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
 			   struct page **pages, struct rpc_rqst *rqst);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
-extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec,
-		size_t nbytes);
+extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes);
 extern void __xdr_commit_encode(struct xdr_stream *xdr);
 extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
 extern void xdr_truncate_decode(struct xdr_stream *xdr, size_t len);
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 8f461e04e5f0..f8069ef2ee0f 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2112,6 +2112,14 @@ DEFINE_POST_CHUNK_EVENT(read);
 DEFINE_POST_CHUNK_EVENT(write);
 DEFINE_POST_CHUNK_EVENT(reply);
 
+DEFINE_EVENT(svcrdma_post_chunk_class, svcrdma_cc_release,
+	TP_PROTO(
+		const struct rpc_rdma_cid *cid,
+		int sqecount
+	),
+	TP_ARGS(cid, sqecount)
+);
+
 TRACE_EVENT(svcrdma_wc_read,
 	TP_PROTO(
 		const struct ib_wc *wc,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 31bc7025cb44..69e42ef30979 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -2104,31 +2104,46 @@ DEFINE_SVC_DEFERRED_EVENT(drop);
 DEFINE_SVC_DEFERRED_EVENT(queue);
 DEFINE_SVC_DEFERRED_EVENT(recv);
 
-TRACE_EVENT(svcsock_new_socket,
+DECLARE_EVENT_CLASS(svcsock_lifetime_class,
 	TP_PROTO(
+		const void *svsk,
 		const struct socket *socket
 	),
-
-	TP_ARGS(socket),
-
+	TP_ARGS(svsk, socket),
 	TP_STRUCT__entry(
+		__field(unsigned int, netns_ino)
+		__field(const void *, svsk)
+		__field(const void *, sk)
 		__field(unsigned long, type)
 		__field(unsigned long, family)
-		__field(bool, listener)
+		__field(unsigned long, state)
 	),
-
 	TP_fast_assign(
+		struct sock *sk = socket->sk;
+
+		__entry->netns_ino = sock_net(sk)->ns.inum;
+		__entry->svsk = svsk;
+		__entry->sk = sk;
 		__entry->type = socket->type;
-		__entry->family = socket->sk->sk_family;
-		__entry->listener = (socket->sk->sk_state == TCP_LISTEN);
+		__entry->family = sk->sk_family;
+		__entry->state = sk->sk_state;
 	),
-
-	TP_printk("type=%s family=%s%s",
-		show_socket_type(__entry->type),
+	TP_printk("svsk=%p type=%s family=%s%s",
+		__entry->svsk, show_socket_type(__entry->type),
 		rpc_show_address_family(__entry->family),
-		__entry->listener ? " (listener)" : ""
+		__entry->state == TCP_LISTEN ? " (listener)" : ""
 	)
 );
+#define DEFINE_SVCSOCK_LIFETIME_EVENT(name) \
+	DEFINE_EVENT(svcsock_lifetime_class, name, \
+		TP_PROTO( \
+			const void *svsk, \
+			const struct socket *socket \
+		), \
+		TP_ARGS(svsk, socket))
+
+DEFINE_SVCSOCK_LIFETIME_EVENT(svcsock_new);
+DEFINE_SVCSOCK_LIFETIME_EVENT(svcsock_free);
 
 TRACE_EVENT(svcsock_marker,
 	TP_PROTO(