Merge tag 'nfsd-5.7' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull nfsd updates from Chuck Lever:

 - Fix EXCHANGE_ID response when NFSD runs in a container

 - A battery of new static trace points

 - Socket transports now use bio_vec to send Replies

 - NFS/RDMA now supports filesystems with no .splice_read method

 - Favor memcpy() over DMA mapping for small RPC/RDMA Replies

 - Add pre-requisites for supporting multiple Write chunks

 - Numerous minor fixes and clean-ups

[ Chuck is filling in for Bruce this time while he and his family settle
  into a new house ]

* tag 'nfsd-5.7' of git://git.linux-nfs.org/projects/cel/cel-2.6: (39 commits)
  svcrdma: Fix leak of transport addresses
  SUNRPC: Fix a potential buffer overflow in 'svc_print_xprts()'
  SUNRPC/cache: don't allow invalid entries to be flushed
  nfsd: fsnotify on rmdir under nfsd/clients/
  nfsd4: kill warnings on testing stateids with mismatched clientids
  nfsd: remove read permission bit for ctl sysctl
  NFSD: Fix NFS server build errors
  sunrpc: Add tracing for cache events
  SUNRPC/cache: Allow garbage collection of invalid cache entries
  nfsd: export upcalls must not return ESTALE when mountd is down
  nfsd: Add tracepoints for update of the expkey and export cache entries
  nfsd: Add tracepoints for exp_find_key() and exp_get_by_name()
  nfsd: Add tracing to nfsd_set_fh_dentry()
  nfsd: Don't add locks to closed or closing open stateids
  SUNRPC: Teach server to use xprt_sock_sendmsg for socket sends
  SUNRPC: Refactor xs_sendpages()
  svcrdma: Avoid DMA mapping small RPC Replies
  svcrdma: Fix double sync of transport header buffer
  svcrdma: Refactor chunk list encoders
  SUNRPC: Add encoders for list item discriminators
  ...

9 files changed, 249 insertions, 63 deletions

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 0f64de7caa39..10891b70fc7b 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -179,6 +179,9 @@ sunrpc_cache_update(struct cache_detail *detail,
 
 extern int
 sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h);
+extern int
+sunrpc_cache_pipe_upcall_timeout(struct cache_detail *detail,
+				 struct cache_head *h);
 
 
 extern void cache_clean_deferred(void *owner);
@@ -206,11 +209,11 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd)
 
 static inline bool cache_is_expired(struct cache_detail *detail, struct cache_head *h)
 {
+	if (h->expiry_time < seconds_since_boot())
+		return true;
 	if (!test_bit(CACHE_VALID, &h->flags))
 		return false;
-
-	return  (h->expiry_time < seconds_since_boot()) ||
-		(detail->flush_time >= h->last_refresh);
+	return detail->flush_time >= h->last_refresh;
 }
 
 extern int cache_check(struct cache_detail *detail,
diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index 92d182fd8e3b..320c672d84de 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -58,7 +58,8 @@ enum {
 enum {
 	rpcrdma_fixed_maxsz	= 4,
 	rpcrdma_segment_maxsz	= 4,
-	rpcrdma_readchunk_maxsz	= 2 + rpcrdma_segment_maxsz,
+	rpcrdma_readseg_maxsz	= 1 + rpcrdma_segment_maxsz,
+	rpcrdma_readchunk_maxsz	= 1 + rpcrdma_readseg_maxsz,
 };
 
 /*
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 1afe38eb33f7..fd390894a584 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -380,7 +380,7 @@ struct svc_deferred_req {
 	struct cache_deferred_req handle;
 	size_t			xprt_hlen;
 	int			argslen;
-	__be32			args[0];
+	__be32			args[];
 };
 
 struct svc_process_info {
@@ -517,6 +517,9 @@ void		   svc_wake_up(struct svc_serv *);
 void		   svc_reserve(struct svc_rqst *rqstp, int space);
 struct svc_pool *  svc_pool_for_cpu(struct svc_serv *serv, int cpu);
 char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
+int		   svc_encode_read_payload(struct svc_rqst *rqstp,
+					   unsigned int offset,
+					   unsigned int length);
 unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
 					 struct page **pages,
 					 struct kvec *first, size_t total);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 40f65888dd38..78fe2ac6dc6c 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -52,6 +52,7 @@
 
 /* Default and maximum inline threshold sizes */
 enum {
+	RPCRDMA_PULLUP_THRESH = RPCRDMA_V1_DEF_INLINE_SIZE >> 1,
 	RPCRDMA_DEF_INLINE_THRESH = 4096,
 	RPCRDMA_MAX_INLINE_THRESH = 65536
 };
@@ -132,11 +133,16 @@ struct svc_rdma_recv_ctxt {
 	struct ib_sge		rc_recv_sge;
 	void			*rc_recv_buf;
 	struct xdr_buf		rc_arg;
+	struct xdr_stream	rc_stream;
 	bool			rc_temp;
 	u32			rc_byte_len;
 	unsigned int		rc_page_count;
 	unsigned int		rc_hdr_count;
 	u32			rc_inv_rkey;
+	__be32			*rc_write_list;
+	__be32			*rc_reply_chunk;
+	unsigned int		rc_read_payload_offset;
+	unsigned int		rc_read_payload_length;
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
@@ -144,6 +150,8 @@ struct svc_rdma_send_ctxt {
 	struct list_head	sc_list;
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
+	struct xdr_buf		sc_hdrbuf;
+	struct xdr_stream	sc_stream;
 	void			*sc_xprt_buf;
 	int			sc_page_count;
 	int			sc_cur_sge_no;
@@ -170,9 +178,11 @@ extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
 				    struct svc_rqst *rqstp,
 				    struct svc_rdma_recv_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *wr_ch, struct xdr_buf *xdr);
+				     __be32 *wr_ch, struct xdr_buf *xdr,
+				     unsigned int offset,
+				     unsigned long length);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *rp_ch, bool writelist,
+				     const struct svc_rdma_recv_ctxt *rctxt,
 				     struct xdr_buf *xdr);
 
 /* svc_rdma_sendto.c */
@@ -182,13 +192,13 @@ extern struct svc_rdma_send_ctxt *
 extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr);
-extern void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma,
-				    struct svc_rdma_send_ctxt *ctxt,
-				    unsigned int len);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
-				  struct svc_rdma_send_ctxt *ctxt,
-				  struct xdr_buf *xdr, __be32 *wr_lst);
+				  struct svc_rdma_send_ctxt *sctxt,
+				  const struct svc_rdma_recv_ctxt *rctxt,
+				  struct xdr_buf *xdr);
 extern int svc_rdma_sendto(struct svc_rqst *);
+extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+				 unsigned int length);
 
 /* svc_rdma_transport.c */
 extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index ea6f46be9cb7..9e1e046de176 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -21,6 +21,8 @@ struct svc_xprt_ops {
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
+	int		(*xpo_read_payload)(struct svc_rqst *, unsigned int,
+					    unsigned int);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index b41f34977995..8529d6e33137 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -188,20 +188,6 @@ extern int xdr_buf_read_mic(struct xdr_buf *, struct xdr_netobj *, unsigned int)
 extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 
-/*
- * Helper structure for copying from an sk_buff.
- */
-struct xdr_skb_reader {
-	struct sk_buff	*skb;
-	unsigned int	offset;
-	size_t		count;
-	__wsum		csum;
-};
-
-typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len);
-
-extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *);
-
 extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32);
 extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *);
 
@@ -301,6 +287,59 @@ xdr_align_size(size_t n)
 }
 
 /**
+ * xdr_pad_size - Calculate size of an object's pad
+ * @n: Size of an object being XDR encoded (in bytes)
+ *
+ * This implementation avoids the need for conditional
+ * branches or modulo division.
+ *
+ * Return value:
+ *   Size (in bytes) of the needed XDR pad
+ */
+static inline size_t xdr_pad_size(size_t n)
+{
+	return xdr_align_size(n) - n;
+}
+
+/**
+ * xdr_stream_encode_item_present - Encode a "present" list item
+ * @xdr: pointer to xdr_stream
+ *
+ * Return values:
+ *   On success, returns length in bytes of XDR buffer consumed
+ *   %-EMSGSIZE on XDR buffer overflow
+ */
+static inline ssize_t xdr_stream_encode_item_present(struct xdr_stream *xdr)
+{
+	const size_t len = sizeof(__be32);
+	__be32 *p = xdr_reserve_space(xdr, len);
+
+	if (unlikely(!p))
+		return -EMSGSIZE;
+	*p = xdr_one;
+	return len;
+}
+
+/**
+ * xdr_stream_encode_item_absent - Encode a "not present" list item
+ * @xdr: pointer to xdr_stream
+ *
+ * Return values:
+ *   On success, returns length in bytes of XDR buffer consumed
+ *   %-EMSGSIZE on XDR buffer overflow
+ */
+static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr)
+{
+	const size_t len = sizeof(__be32);
+	__be32 *p = xdr_reserve_space(xdr, len);
+
+	if (unlikely(!p))
+		return -EMSGSIZE;
+	*p = xdr_zero;
+	return len;
+}
+
+/**
  * xdr_stream_encode_u32 - Encode a 32-bit integer
  * @xdr: pointer to xdr_stream
  * @n: integer to encode
diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
index 9827f535f032..32d88c4fb063 100644
--- a/include/trace/events/rpcgss.h
+++ b/include/trace/events/rpcgss.h
@@ -126,7 +126,7 @@ DEFINE_GSSAPI_EVENT(verify_mic);
 DEFINE_GSSAPI_EVENT(wrap);
 DEFINE_GSSAPI_EVENT(unwrap);
 
-TRACE_EVENT(rpcgss_accept_upcall,
+TRACE_EVENT(rpcgss_svc_accept_upcall,
 	TP_PROTO(
 		__be32 xid,
 		u32 major_status,
@@ -154,6 +154,29 @@ TRACE_EVENT(rpcgss_accept_upcall,
 	)
 );
 
+TRACE_EVENT(rpcgss_svc_accept,
+	TP_PROTO(
+		__be32 xid,
+		size_t len
+	),
+
+	TP_ARGS(xid, len),
+
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(size_t, len)
+	),
+
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(xid);
+		__entry->len = len;
+	),
+
+	TP_printk("xid=0x%08x len=%zu",
+		__entry->xid, __entry->len
+	)
+);
+
 
 /**
  ** GSS auth unwrap failures
@@ -268,6 +291,40 @@ TRACE_EVENT(rpcgss_need_reencode,
 		__entry->ret ? "" : "un")
 );
 
+DECLARE_EVENT_CLASS(rpcgss_svc_seqno_class,
+	TP_PROTO(
+		__be32 xid,
+		u32 seqno
+	),
+
+	TP_ARGS(xid, seqno),
+
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(u32, seqno)
+	),
+
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(xid);
+		__entry->seqno = seqno;
+	),
+
+	TP_printk("xid=0x%08x seqno=%u, request discarded",
+		__entry->xid, __entry->seqno)
+);
+
+#define DEFINE_SVC_SEQNO_EVENT(name)					\
+	DEFINE_EVENT(rpcgss_svc_seqno_class, rpcgss_svc_##name,		\
+			TP_PROTO(					\
+				__be32 xid,				\
+				u32 seqno				\
+			),						\
+			TP_ARGS(xid, seqno))
+
+DEFINE_SVC_SEQNO_EVENT(large_seqno);
+DEFINE_SVC_SEQNO_EVENT(old_seqno);
+
+
 /**
  ** gssd upcall related trace events
  **/
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index c0e4c93324f5..9238d233f8cf 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1469,7 +1469,7 @@ DECLARE_EVENT_CLASS(svcrdma_segment_event,
 );
 
 #define DEFINE_SEGMENT_EVENT(name)					\
-		DEFINE_EVENT(svcrdma_segment_event, svcrdma_encode_##name,\
+		DEFINE_EVENT(svcrdma_segment_event, svcrdma_##name,\
 				TP_PROTO(				\
 					u32 handle,			\
 					u32 length,			\
@@ -1477,8 +1477,11 @@ DECLARE_EVENT_CLASS(svcrdma_segment_event,
 				),					\
 				TP_ARGS(handle, length, offset))
 
-DEFINE_SEGMENT_EVENT(rseg);
-DEFINE_SEGMENT_EVENT(wseg);
+DEFINE_SEGMENT_EVENT(decode_wseg);
+DEFINE_SEGMENT_EVENT(encode_rseg);
+DEFINE_SEGMENT_EVENT(send_rseg);
+DEFINE_SEGMENT_EVENT(encode_wseg);
+DEFINE_SEGMENT_EVENT(send_wseg);
 
 DECLARE_EVENT_CLASS(svcrdma_chunk_event,
 	TP_PROTO(
@@ -1501,17 +1504,19 @@ DECLARE_EVENT_CLASS(svcrdma_chunk_event,
 );
 
 #define DEFINE_CHUNK_EVENT(name)					\
-		DEFINE_EVENT(svcrdma_chunk_event, svcrdma_encode_##name,\
+		DEFINE_EVENT(svcrdma_chunk_event, svcrdma_##name,	\
 				TP_PROTO(				\
 					u32 length			\
 				),					\
 				TP_ARGS(length))
 
-DEFINE_CHUNK_EVENT(pzr);
-DEFINE_CHUNK_EVENT(write);
-DEFINE_CHUNK_EVENT(reply);
+DEFINE_CHUNK_EVENT(send_pzr);
+DEFINE_CHUNK_EVENT(encode_write_chunk);
+DEFINE_CHUNK_EVENT(send_write_chunk);
+DEFINE_CHUNK_EVENT(encode_read_chunk);
+DEFINE_CHUNK_EVENT(send_reply_chunk);
 
-TRACE_EVENT(svcrdma_encode_read,
+TRACE_EVENT(svcrdma_send_read_chunk,
 	TP_PROTO(
 		u32 length,
 		u32 position
@@ -1634,6 +1639,24 @@ TRACE_EVENT(svcrdma_dma_map_rwctx,
 	)
 );
 
+TRACE_EVENT(svcrdma_send_pullup,
+	TP_PROTO(
+		unsigned int len
+	),
+
+	TP_ARGS(len),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, len)
+	),
+
+	TP_fast_assign(
+		__entry->len = len;
+	),
+
+	TP_printk("len=%u", __entry->len)
+);
+
 TRACE_EVENT(svcrdma_send_failed,
 	TP_PROTO(
 		const struct svc_rqst *rqst,
@@ -1813,34 +1836,6 @@ TRACE_EVENT(svcrdma_post_rw,
 DEFINE_SENDCOMP_EVENT(read);
 DEFINE_SENDCOMP_EVENT(write);
 
-TRACE_EVENT(svcrdma_cm_event,
-	TP_PROTO(
-		const struct rdma_cm_event *event,
-		const struct sockaddr *sap
-	),
-
-	TP_ARGS(event, sap),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, event)
-		__field(int, status)
-		__array(__u8, addr, INET6_ADDRSTRLEN + 10)
-	),
-
-	TP_fast_assign(
-		__entry->event = event->event;
-		__entry->status = event->status;
-		snprintf(__entry->addr, sizeof(__entry->addr) - 1,
-			 "%pISpc", sap);
-	),
-
-	TP_printk("addr=%s event=%s (%u/%d)",
-		__entry->addr,
-		rdma_show_cm_event(__entry->event),
-		__entry->event, __entry->status
-	)
-);
-
 TRACE_EVENT(svcrdma_qp_error,
 	TP_PROTO(
 		const struct ib_event *event,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ee993575d2fa..ffd2215950dc 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -14,6 +14,49 @@
 #include <linux/net.h>
 #include <linux/tracepoint.h>
 
+DECLARE_EVENT_CLASS(xdr_buf_class,
+	TP_PROTO(
+		const struct xdr_buf *xdr
+	),
+
+	TP_ARGS(xdr),
+
+	TP_STRUCT__entry(
+		__field(const void *, head_base)
+		__field(size_t, head_len)
+		__field(const void *, tail_base)
+		__field(size_t, tail_len)
+		__field(unsigned int, page_len)
+		__field(unsigned int, msg_len)
+	),
+
+	TP_fast_assign(
+		__entry->head_base = xdr->head[0].iov_base;
+		__entry->head_len = xdr->head[0].iov_len;
+		__entry->tail_base = xdr->tail[0].iov_base;
+		__entry->tail_len = xdr->tail[0].iov_len;
+		__entry->page_len = xdr->page_len;
+		__entry->msg_len = xdr->len;
+	),
+
+	TP_printk("head=[%p,%zu] page=%u tail=[%p,%zu] len=%u",
+		__entry->head_base, __entry->head_len, __entry->page_len,
+		__entry->tail_base, __entry->tail_len, __entry->msg_len
+	)
+);
+
+#define DEFINE_XDRBUF_EVENT(name)					\
+		DEFINE_EVENT(xdr_buf_class, name,			\
+				TP_PROTO(				\
+					const struct xdr_buf *xdr	\
+				),					\
+				TP_ARGS(xdr))
+
+DEFINE_XDRBUF_EVENT(xprt_sendto);
+DEFINE_XDRBUF_EVENT(xprt_recvfrom);
+DEFINE_XDRBUF_EVENT(svc_recvfrom);
+DEFINE_XDRBUF_EVENT(svc_sendto);
+
 TRACE_DEFINE_ENUM(RPC_AUTH_OK);
 TRACE_DEFINE_ENUM(RPC_AUTH_BADCRED);
 TRACE_DEFINE_ENUM(RPC_AUTH_REJECTEDCRED);
@@ -1292,6 +1335,39 @@ DECLARE_EVENT_CLASS(svc_deferred_event,
 DEFINE_SVC_DEFERRED_EVENT(drop);
 DEFINE_SVC_DEFERRED_EVENT(revisit);
 
+DECLARE_EVENT_CLASS(cache_event,
+	TP_PROTO(
+		const struct cache_detail *cd,
+		const struct cache_head *h
+	),
+
+	TP_ARGS(cd, h),
+
+	TP_STRUCT__entry(
+		__field(const struct cache_head *, h)
+		__string(name, cd->name)
+	),
+
+	TP_fast_assign(
+		__entry->h = h;
+		__assign_str(name, cd->name);
+	),
+
+	TP_printk("cache=%s entry=%p", __get_str(name), __entry->h)
+);
+#define DEFINE_CACHE_EVENT(name) \
+	DEFINE_EVENT(cache_event, name, \
+			TP_PROTO( \
+				const struct cache_detail *cd, \
+				const struct cache_head *h \
+			), \
+			TP_ARGS(cd, h))
+DEFINE_CACHE_EVENT(cache_entry_expired);
+DEFINE_CACHE_EVENT(cache_entry_upcall);
+DEFINE_CACHE_EVENT(cache_entry_update);
+DEFINE_CACHE_EVENT(cache_entry_make_negative);
+DEFINE_CACHE_EVENT(cache_entry_no_listener);
+
 #endif /* _TRACE_SUNRPC_H */
 
 #include <trace/define_trace.h>