Merge tag 'nfsd-5.11' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull nfsd updates from Chuck Lever:
 "Several substantial changes this time around:

   - Previously, exporting an NFS mount via NFSD was considered to be an
     unsupported feature. With v5.11, the community has attempted to
     make re-exporting a first-class feature of NFSD.

     This would enable the Linux in-kernel NFS server to be used as an
     intermediate cache for a remotely-located primary NFS server, for
     example, even with other NFS server implementations, like a NetApp
     filer, as the primary.

   - A short series of patches brings support for multiple RPC/RDMA data
     chunks per RPC transaction to the Linux NFS server's RPC/RDMA
     transport implementation.

     This is a part of the RPC/RDMA spec that the other premiere
     NFS/RDMA implementation (Solaris) has had for a very long time, and
     completes the implementation of RPC/RDMA version 1 in the Linux
     kernel's NFS server.

   - Long ago, NFSv4 support was introduced to NFSD using a series of C
     macros that hid dprintk's and goto's. Over time, the kernel's XDR
     implementation has been greatly improved, but these C macros have
     remained and become fallow. A series of patches in this pull
     request completely replaces those macros with the use of current
     kernel XDR infrastructure. Benefits include:

       - More robust input sanitization in NFSD's NFSv4 XDR decoders.

       - Make it easier to use common kernel library functions that use
         XDR stream APIs (for example, GSS-API).

       - Align the structure of the source code with the RFCs so it is
         easier to learn, verify, and maintain our XDR implementation.

       - Removal of more than a hundred hidden dprintk() call sites.

       - Removal of some explicit manipulation of pages to help make the
         eventual transition to xdr->bvec smoother.

   - On top of several related fixes in 5.10-rc, there are a few more
     fixes to get the Linux NFSD implementation of NFSv4.2 inter-server
     copy up to speed.

  And as usual, there is a pinch of seasoning in the form of a
  collection of unrelated minor bug fixes and clean-ups.

  Many thanks to all who contributed this time around!"

* tag 'nfsd-5.11' of git://git.linux-nfs.org/projects/cel/cel-2.6: (131 commits)
  nfsd: Record NFSv4 pre/post-op attributes as non-atomic
  nfsd: Set PF_LOCAL_THROTTLE on local filesystems only
  nfsd: Fix up nfsd to ensure that timeout errors don't result in ESTALE
  exportfs: Add a function to return the raw output from fh_to_dentry()
  nfsd: close cached files prior to a REMOVE or RENAME that would replace target
  nfsd: allow filesystems to opt out of subtree checking
  nfsd: add a new EXPORT_OP_NOWCC flag to struct export_operations
  Revert "nfsd4: support change_attr_type attribute"
  nfsd4: don't query change attribute in v2/v3 case
  nfsd: minor nfsd4_change_attribute cleanup
  nfsd: simplify nfsd4_change_info
  nfsd: only call inode_query_iversion in the I_VERSION case
  nfs_common: need lock during iterate through the list
  NFSD: Fix 5 seconds delay when doing inter server copy
  NFSD: Fix sparse warning in nfs4proc.c
  SUNRPC: Remove XDRBUF_SPARSE_PAGES flag in gss_proxy upcall
  sunrpc: clean-up cache downcall
  nfsd: Fix message level for normal termination
  NFSD: Remove macros that are no longer used
  NFSD: Replace READ* macros in nfsd4_decode_compound()
  ...

10 files changed, 375 insertions, 107 deletions

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 3ceb72b67a7a..9f4d4bcbf251 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -213,12 +213,25 @@ struct export_operations {
 			  bool write, u32 *device_generation);
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
+#define	EXPORT_OP_NOWCC			(0x1) /* don't collect v3 wcc data */
+#define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
+#define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
+#define EXPORT_OP_REMOTE_FS		(0x8) /* Filesystem is remote */
+#define EXPORT_OP_NOATOMIC_ATTR		(0x10) /* Filesystem cannot supply
+						  atomic attribute updates
+						*/
+	unsigned long	flags;
 };
 
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
 				    int *max_len, struct inode *parent);
 extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
 	int *max_len, int connectable);
+extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt,
+					     struct fid *fid, int fh_len,
+					     int fileid_type,
+					     int (*acceptable)(void *, struct dentry *),
+					     void *context);
 extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *),
 	void *context);
diff --git a/include/linux/iversion.h b/include/linux/iversion.h
index 2917ef990d43..3bfebde5a1a6 100644
--- a/include/linux/iversion.h
+++ b/include/linux/iversion.h
@@ -328,6 +328,19 @@ inode_query_iversion(struct inode *inode)
 	return cur >> I_VERSION_QUERIED_SHIFT;
 }
 
+/*
+ * For filesystems without any sort of change attribute, the best we can
+ * do is fake one up from the ctime:
+ */
+static inline u64 time_to_chattr(struct timespec64 *t)
+{
+	u64 chattr = t->tv_sec;
+
+	chattr <<= 32;
+	chattr += t->tv_nsec;
+	return chattr;
+}
+
 /**
  * inode_eq_iversion_raw - check whether the raw i_version counter has changed
  * @inode: inode to check
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 9dc7eeac924f..5b4c67c91f56 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -385,13 +385,6 @@ enum lock_type4 {
 	NFS4_WRITEW_LT = 4
 };
 
-enum change_attr_type4 {
-	NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR = 0,
-	NFS4_CHANGE_TYPE_IS_VERSION_COUNTER = 1,
-	NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS = 2,
-	NFS4_CHANGE_TYPE_IS_TIME_METADATA = 3,
-	NFS4_CHANGE_TYPE_IS_UNDEFINED = 4
-};
 
 /* Mandatory Attributes */
 #define FATTR4_WORD0_SUPPORTED_ATTRS    (1UL << 0)
@@ -459,7 +452,6 @@ enum change_attr_type4 {
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_CLONE_BLKSIZE	(1UL << 13)
-#define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 #define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
 #define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 386628b36bc7..34c2a69820e9 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -247,6 +247,8 @@ struct svc_rqst {
 
 	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
+	struct xdr_stream	rq_arg_stream;
+	struct page		*rq_scratch_page;
 	struct xdr_buf		rq_res;
 	struct page		*rq_pages[RPCSVC_MAXPAGES + 1];
 	struct page *		*rq_respages;	/* points into rq_pages */
@@ -519,9 +521,9 @@ 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);
+int		   svc_encode_result_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);
@@ -557,4 +559,18 @@ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space)
 	svc_reserve(rqstp, space + rqstp->rq_auth_slack);
 }
 
+/**
+ * svcxdr_init_decode - Prepare an xdr_stream for svc Call decoding
+ * @rqstp: controlling server RPC transaction context
+ *
+ */
+static inline void svcxdr_init_decode(struct svc_rqst *rqstp)
+{
+	struct xdr_stream *xdr = &rqstp->rq_arg_stream;
+	struct kvec *argv = rqstp->rq_arg.head;
+
+	xdr_init_decode(xdr, &rqstp->rq_arg, argv->iov_base, NULL);
+	xdr_set_scratch_page(xdr, rqstp->rq_scratch_page);
+}
+
 #endif /* SUNRPC_SVC_H */
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 9dc3a3b88391..294b56e61522 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -47,6 +47,8 @@
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/rpc_rdma_cid.h>
+#include <linux/sunrpc/svc_rdma_pcl.h>
+
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
 
@@ -142,10 +144,15 @@ struct svc_rdma_recv_ctxt {
 	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;
+	__be32			rc_msgtype;
+
+	struct svc_rdma_pcl	rc_call_pcl;
+
+	struct svc_rdma_pcl	rc_read_pcl;
+	struct svc_rdma_chunk	*rc_cur_result_payload;
+	struct svc_rdma_pcl	rc_write_pcl;
+	struct svc_rdma_pcl	rc_reply_pcl;
+
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
@@ -171,6 +178,8 @@ extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
 /* svc_rdma_recvfrom.c */
 extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma);
 extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma);
+extern struct svc_rdma_recv_ctxt *
+		svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma);
 extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_recv_ctxt *ctxt);
 extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma);
@@ -179,16 +188,15 @@ extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
-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,
-				     unsigned int offset,
-				     unsigned long length);
+				     const struct svc_rdma_chunk *chunk,
+				     const struct xdr_buf *xdr);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_recv_ctxt *rctxt,
-				     struct xdr_buf *xdr);
+				     const struct xdr_buf *xdr);
+extern int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
+				      struct svc_rqst *rqstp,
+				      struct svc_rdma_recv_ctxt *head);
 
 /* svc_rdma_sendto.c */
 extern void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma);
@@ -201,14 +209,14 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma,
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_recv_ctxt *rctxt,
-				  struct xdr_buf *xdr);
+				  const struct xdr_buf *xdr);
 extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_send_ctxt *sctxt,
 				    struct svc_rdma_recv_ctxt *rctxt,
 				    int status);
 extern int svc_rdma_sendto(struct svc_rqst *);
-extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-				 unsigned int length);
+extern int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+				   unsigned int length);
 
 /* svc_rdma_transport.c */
 extern struct svc_xprt_class svc_rdma_class;
diff --git a/include/linux/sunrpc/svc_rdma_pcl.h b/include/linux/sunrpc/svc_rdma_pcl.h
new file mode 100644
index 000000000000..7516ad0fae80
--- /dev/null
+++ b/include/linux/sunrpc/svc_rdma_pcl.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020, Oracle and/or its affiliates
+ */
+
+#ifndef SVC_RDMA_PCL_H
+#define SVC_RDMA_PCL_H
+
+#include <linux/list.h>
+
+struct svc_rdma_segment {
+	u32			rs_handle;
+	u32			rs_length;
+	u64			rs_offset;
+};
+
+struct svc_rdma_chunk {
+	struct list_head	ch_list;
+
+	u32			ch_position;
+	u32			ch_length;
+	u32			ch_payload_length;
+
+	u32			ch_segcount;
+	struct svc_rdma_segment	ch_segments[];
+};
+
+struct svc_rdma_pcl {
+	unsigned int		cl_count;
+	struct list_head	cl_chunks;
+};
+
+/**
+ * pcl_init - Initialize a parsed chunk list
+ * @pcl: parsed chunk list to initialize
+ *
+ */
+static inline void pcl_init(struct svc_rdma_pcl *pcl)
+{
+	INIT_LIST_HEAD(&pcl->cl_chunks);
+}
+
+/**
+ * pcl_is_empty - Return true if parsed chunk list is empty
+ * @pcl: parsed chunk list
+ *
+ */
+static inline bool pcl_is_empty(const struct svc_rdma_pcl *pcl)
+{
+	return list_empty(&pcl->cl_chunks);
+}
+
+/**
+ * pcl_first_chunk - Return first chunk in a parsed chunk list
+ * @pcl: parsed chunk list
+ *
+ * Returns the first chunk in the list, or NULL if the list is empty.
+ */
+static inline struct svc_rdma_chunk *
+pcl_first_chunk(const struct svc_rdma_pcl *pcl)
+{
+	if (pcl_is_empty(pcl))
+		return NULL;
+	return list_first_entry(&pcl->cl_chunks, struct svc_rdma_chunk,
+				ch_list);
+}
+
+/**
+ * pcl_next_chunk - Return next chunk in a parsed chunk list
+ * @pcl: a parsed chunk list
+ * @chunk: chunk in @pcl
+ *
+ * Returns the next chunk in the list, or NULL if @chunk is already last.
+ */
+static inline struct svc_rdma_chunk *
+pcl_next_chunk(const struct svc_rdma_pcl *pcl, struct svc_rdma_chunk *chunk)
+{
+	if (list_is_last(&chunk->ch_list, &pcl->cl_chunks))
+		return NULL;
+	return list_next_entry(chunk, ch_list);
+}
+
+/**
+ * pcl_for_each_chunk - Iterate over chunks in a parsed chunk list
+ * @pos: the loop cursor
+ * @pcl: a parsed chunk list
+ */
+#define pcl_for_each_chunk(pos, pcl) \
+	for (pos = list_first_entry(&(pcl)->cl_chunks, struct svc_rdma_chunk, ch_list); \
+	     &pos->ch_list != &(pcl)->cl_chunks; \
+	     pos = list_next_entry(pos, ch_list))
+
+/**
+ * pcl_for_each_segment - Iterate over segments in a parsed chunk
+ * @pos: the loop cursor
+ * @chunk: a parsed chunk
+ */
+#define pcl_for_each_segment(pos, chunk) \
+	for (pos = &(chunk)->ch_segments[0]; \
+	     pos <= &(chunk)->ch_segments[(chunk)->ch_segcount - 1]; \
+	     pos++)
+
+/**
+ * pcl_chunk_end_offset - Return offset of byte range following @chunk
+ * @chunk: chunk in @pcl
+ *
+ * Returns starting offset of the region just after @chunk
+ */
+static inline unsigned int
+pcl_chunk_end_offset(const struct svc_rdma_chunk *chunk)
+{
+	return xdr_align_size(chunk->ch_position + chunk->ch_payload_length);
+}
+
+struct svc_rdma_recv_ctxt;
+
+extern void pcl_free(struct svc_rdma_pcl *pcl);
+extern bool pcl_alloc_call(struct svc_rdma_recv_ctxt *rctxt, __be32 *p);
+extern bool pcl_alloc_read(struct svc_rdma_recv_ctxt *rctxt, __be32 *p);
+extern bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt,
+			    struct svc_rdma_pcl *pcl, __be32 *p);
+extern int pcl_process_nonpayloads(const struct svc_rdma_pcl *pcl,
+				   const struct xdr_buf *xdr,
+				   int (*actor)(const struct xdr_buf *,
+						void *),
+				   void *data);
+
+#endif	/* SVC_RDMA_PCL_H */
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index aca35ab5cff2..92455e0d5244 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -21,8 +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);
+	int		(*xpo_result_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 9548d075e06d..9b35ce50cf2b 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -183,7 +183,8 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
  */
 extern void xdr_shift_buf(struct xdr_buf *, size_t);
 extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
-extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
+extern int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
+			      unsigned int base, unsigned int len);
 extern void xdr_buf_trim(struct xdr_buf *, 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);
@@ -247,13 +248,57 @@ extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
 		struct page **pages, unsigned int len);
-extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
 extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
+extern bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
+				  unsigned int len);
+
+/**
+ * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
+ * @xdr: pointer to xdr_stream struct
+ * @buf: pointer to an empty buffer
+ * @buflen: size of 'buf'
+ *
+ * The scratch buffer is used when decoding from an array of pages.
+ * If an xdr_inline_decode() call spans across page boundaries, then
+ * we copy the data into the scratch buffer in order to allow linear
+ * access.
+ */
+static inline void
+xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
+{
+	xdr->scratch.iov_base = buf;
+	xdr->scratch.iov_len = buflen;
+}
+
+/**
+ * xdr_set_scratch_page - Attach a scratch buffer for decoding data
+ * @xdr: pointer to xdr_stream struct
+ * @page: an anonymous page
+ *
+ * See xdr_set_scratch_buffer().
+ */
+static inline void
+xdr_set_scratch_page(struct xdr_stream *xdr, struct page *page)
+{
+	xdr_set_scratch_buffer(xdr, page_address(page), PAGE_SIZE);
+}
+
+/**
+ * xdr_reset_scratch_buffer - Clear scratch buffer information
+ * @xdr: pointer to xdr_stream struct
+ *
+ * See xdr_set_scratch_buffer().
+ */
+static inline void
+xdr_reset_scratch_buffer(struct xdr_stream *xdr)
+{
+	xdr_set_scratch_buffer(xdr, NULL, 0);
+}
 
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
@@ -506,6 +551,27 @@ static inline bool xdr_item_is_present(const __be32 *p)
 }
 
 /**
+ * xdr_stream_decode_bool - Decode a boolean
+ * @xdr: pointer to xdr_stream
+ * @ptr: pointer to a u32 in which to store the result
+ *
+ * Return values:
+ *   %0 on success
+ *   %-EBADMSG on XDR buffer overflow
+ */
+static inline ssize_t
+xdr_stream_decode_bool(struct xdr_stream *xdr, __u32 *ptr)
+{
+	const size_t count = sizeof(*ptr);
+	__be32 *p = xdr_inline_decode(xdr, count);
+
+	if (unlikely(!p))
+		return -EBADMSG;
+	*ptr = (*p != xdr_zero);
+	return 0;
+}
+
+/**
  * xdr_stream_decode_u32 - Decode a 32-bit integer
  * @xdr: pointer to xdr_stream
  * @ptr: location to store integer
@@ -527,6 +593,27 @@ xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr)
 }
 
 /**
+ * xdr_stream_decode_u64 - Decode a 64-bit integer
+ * @xdr: pointer to xdr_stream
+ * @ptr: location to store 64-bit integer
+ *
+ * Return values:
+ *   %0 on success
+ *   %-EBADMSG on XDR buffer overflow
+ */
+static inline ssize_t
+xdr_stream_decode_u64(struct xdr_stream *xdr, __u64 *ptr)
+{
+	const size_t count = sizeof(*ptr);
+	__be32 *p = xdr_inline_decode(xdr, count);
+
+	if (unlikely(!p))
+		return -EBADMSG;
+	xdr_decode_hyper(p, ptr);
+	return 0;
+}
+
+/**
  * xdr_stream_decode_opaque_fixed - Decode fixed length opaque xdr data
  * @xdr: pointer to xdr_stream
  * @ptr: location to store data
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index bf1065772228..896aafc37b09 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1410,101 +1410,112 @@ DEFINE_BADREQ_EVENT(drop);
 DEFINE_BADREQ_EVENT(badproc);
 DEFINE_BADREQ_EVENT(parse);
 
-DECLARE_EVENT_CLASS(svcrdma_segment_event,
+TRACE_EVENT(svcrdma_encode_wseg,
 	TP_PROTO(
+		const struct svc_rdma_send_ctxt *ctxt,
+		u32 segno,
 		u32 handle,
 		u32 length,
 		u64 offset
 	),
 
-	TP_ARGS(handle, length, offset),
+	TP_ARGS(ctxt, segno, handle, length, offset),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(u32, segno)
 		__field(u32, handle)
 		__field(u32, length)
 		__field(u64, offset)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = ctxt->sc_cid.ci_queue_id;
+		__entry->completion_id = ctxt->sc_cid.ci_completion_id;
+		__entry->segno = segno;
 		__entry->handle = handle;
 		__entry->length = length;
 		__entry->offset = offset;
 	),
 
-	TP_printk("%u@0x%016llx:0x%08x",
-		__entry->length, (unsigned long long)__entry->offset,
-		__entry->handle
+	TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
+		__entry->cq_id, __entry->completion_id,
+		__entry->segno, __entry->length,
+		(unsigned long long)__entry->offset, __entry->handle
 	)
 );
 
-#define DEFINE_SEGMENT_EVENT(name)					\
-		DEFINE_EVENT(svcrdma_segment_event, svcrdma_##name,\
-				TP_PROTO(				\
-					u32 handle,			\
-					u32 length,			\
-					u64 offset			\
-				),					\
-				TP_ARGS(handle, length, offset))
-
-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,
+TRACE_EVENT(svcrdma_decode_rseg,
 	TP_PROTO(
-		u32 length
+		const struct rpc_rdma_cid *cid,
+		const struct svc_rdma_chunk *chunk,
+		const struct svc_rdma_segment *segment
 	),
 
-	TP_ARGS(length),
+	TP_ARGS(cid, chunk, segment),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(u32, segno)
+		__field(u32, position)
+		__field(u32, handle)
 		__field(u32, length)
+		__field(u64, offset)
 	),
 
 	TP_fast_assign(
-		__entry->length = length;
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->segno = chunk->ch_segcount;
+		__entry->position = chunk->ch_position;
+		__entry->handle = segment->rs_handle;
+		__entry->length = segment->rs_length;
+		__entry->offset = segment->rs_offset;
 	),
 
-	TP_printk("length=%u",
-		__entry->length
+	TP_printk("cq_id=%u cid=%d segno=%u position=%u %u@0x%016llx:0x%08x",
+		__entry->cq_id, __entry->completion_id,
+		__entry->segno, __entry->position, __entry->length,
+		(unsigned long long)__entry->offset, __entry->handle
 	)
 );
 
-#define DEFINE_CHUNK_EVENT(name)					\
-		DEFINE_EVENT(svcrdma_chunk_event, svcrdma_##name,	\
-				TP_PROTO(				\
-					u32 length			\
-				),					\
-				TP_ARGS(length))
-
-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_send_read_chunk,
+TRACE_EVENT(svcrdma_decode_wseg,
 	TP_PROTO(
-		u32 length,
-		u32 position
+		const struct rpc_rdma_cid *cid,
+		const struct svc_rdma_chunk *chunk,
+		u32 segno
 	),
 
-	TP_ARGS(length, position),
+	TP_ARGS(cid, chunk, segno),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(u32, segno)
+		__field(u32, handle)
 		__field(u32, length)
-		__field(u32, position)
+		__field(u64, offset)
 	),
 
 	TP_fast_assign(
-		__entry->length = length;
-		__entry->position = position;
+		const struct svc_rdma_segment *segment =
+			&chunk->ch_segments[segno];
+
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->segno = segno;
+		__entry->handle = segment->rs_handle;
+		__entry->length = segment->rs_length;
+		__entry->offset = segment->rs_offset;
 	),
 
-	TP_printk("length=%u position=%u",
-		__entry->length, __entry->position
+	TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
+		__entry->cq_id, __entry->completion_id,
+		__entry->segno, __entry->length,
+		(unsigned long long)__entry->offset, __entry->handle
 	)
 );
 
@@ -1581,6 +1592,7 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
 				TP_ARGS(rdma, dma_addr, length))
 
 DEFINE_SVC_DMA_EVENT(dma_map_page);
+DEFINE_SVC_DMA_EVENT(dma_map_err);
 DEFINE_SVC_DMA_EVENT(dma_unmap_page);
 
 TRACE_EVENT(svcrdma_dma_map_rw_err,
@@ -1699,20 +1711,30 @@ TRACE_EVENT(svcrdma_small_wrch_err,
 
 TRACE_EVENT(svcrdma_send_pullup,
 	TP_PROTO(
-		unsigned int len
+		const struct svc_rdma_send_ctxt *ctxt,
+		unsigned int msglen
 	),
 
-	TP_ARGS(len),
+	TP_ARGS(ctxt, msglen),
 
 	TP_STRUCT__entry(
-		__field(unsigned int, len)
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(unsigned int, hdrlen)
+		__field(unsigned int, msglen)
 	),
 
 	TP_fast_assign(
-		__entry->len = len;
+		__entry->cq_id = ctxt->sc_cid.ci_queue_id;
+		__entry->completion_id = ctxt->sc_cid.ci_completion_id;
+		__entry->hdrlen = ctxt->sc_hdrbuf.len,
+		__entry->msglen = msglen;
 	),
 
-	TP_printk("len=%u", __entry->len)
+	TP_printk("cq_id=%u cid=%d hdr=%u msg=%u (total %u)",
+		__entry->cq_id, __entry->completion_id,
+		__entry->hdrlen, __entry->msglen,
+		__entry->hdrlen + __entry->msglen)
 );
 
 TRACE_EVENT(svcrdma_send_err,
@@ -1819,7 +1841,7 @@ TRACE_EVENT(svcrdma_rq_post_err,
 	)
 );
 
-TRACE_EVENT(svcrdma_post_chunk,
+DECLARE_EVENT_CLASS(svcrdma_post_chunk_class,
 	TP_PROTO(
 		const struct rpc_rdma_cid *cid,
 		int sqecount
@@ -1845,6 +1867,19 @@ TRACE_EVENT(svcrdma_post_chunk,
 	)
 );
 
+#define DEFINE_POST_CHUNK_EVENT(name)					\
+		DEFINE_EVENT(svcrdma_post_chunk_class,			\
+				svcrdma_post_##name##_chunk,		\
+				TP_PROTO(				\
+					const struct rpc_rdma_cid *cid,	\
+					int sqecount			\
+				),					\
+				TP_ARGS(cid, sqecount))
+
+DEFINE_POST_CHUNK_EVENT(read);
+DEFINE_POST_CHUNK_EVENT(write);
+DEFINE_POST_CHUNK_EVENT(reply);
+
 DEFINE_COMPLETION_EVENT(svcrdma_wc_read);
 DEFINE_COMPLETION_EVENT(svcrdma_wc_write);
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 2a03263b5f9d..58994e013022 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1500,30 +1500,6 @@ SVC_RQST_FLAG_LIST
 #define show_rqstp_flags(flags)						\
 		__print_flags(flags, "|", SVC_RQST_FLAG_LIST)
 
-TRACE_EVENT(svc_recv,
-	TP_PROTO(struct svc_rqst *rqst, int len),
-
-	TP_ARGS(rqst, len),
-
-	TP_STRUCT__entry(
-		__field(u32, xid)
-		__field(int, len)
-		__field(unsigned long, flags)
-		__string(addr, rqst->rq_xprt->xpt_remotebuf)
-	),
-
-	TP_fast_assign(
-		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->len = len;
-		__entry->flags = rqst->rq_flags;
-		__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
-	),
-
-	TP_printk("addr=%s xid=0x%08x len=%d flags=%s",
-			__get_str(addr), __entry->xid, __entry->len,
-			show_rqstp_flags(__entry->flags))
-);
-
 TRACE_DEFINE_ENUM(SVC_GARBAGE);
 TRACE_DEFINE_ENUM(SVC_SYSERR);
 TRACE_DEFINE_ENUM(SVC_VALID);