Merge tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Features:

   - NFSv3: Add emulation of lookupp() to improve open_by_filehandle()
     support

   - A series of patches to improve readdir performance, particularly
     with large directories

   - Basic support for using NFS/RDMA with the pNFS files and flexfiles
     drivers

   - Micro-optimisations for RDMA

   - RDMA tracing improvements

  Bugfixes:

   - Fix a long standing bug with xs_read_xdr_buf() when receiving
     partial pages (Dan Aloni)

   - Various fixes for getxattr and listxattr, when used over non-TCP
     transports

   - Fixes for containerised NFS from Sargun Dhillon

   - switch nfsiod to be an UNBOUND workqueue (Neil Brown)

   - READDIR should not ask for security label information if there is
     no LSM policy (Olga Kornievskaia)

   - Avoid using interval-based rebinding with TCP in lockd (Calum
     Mackay)

   - A series of RPC and NFS layer fixes to support the NFSv4.2
     READ_PLUS code

   - A couple of fixes for pnfs/flexfiles read failover

  Cleanups:

   - Various cleanups for the SUNRPC xdr code in conjunction with the
     READ_PLUS fixes"

* tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (90 commits)
  NFS/pNFS: Fix a typo in ff_layout_resend_pnfs_read()
  pNFS/flexfiles: Avoid spurious layout returns in ff_layout_choose_ds_for_read
  NFSv4/pnfs: Add tracing for the deviceid cache
  fs/lockd: convert comma to semicolon
  NFSv4.2: fix error return on memory allocation failure
  NFSv4.2/pnfs: Don't use READ_PLUS with pNFS yet
  NFSv4.2: Deal with potential READ_PLUS data extent buffer overflow
  NFSv4.2: Don't error when exiting early on a READ_PLUS buffer overflow
  NFSv4.2: Handle hole lengths that exceed the READ_PLUS read buffer
  NFSv4.2: decode_read_plus_hole() needs to check the extent offset
  NFSv4.2: decode_read_plus_data() must skip padding after data segment
  NFSv4.2: Ensure we always reset the result->count in decode_read_plus()
  SUNRPC: When expanding the buffer, we may need grow the sparse pages
  SUNRPC: Cleanup - constify a number of xdr_buf helpers
  SUNRPC: Clean up open coded setting of the xdr_stream 'nwords' field
  SUNRPC: _copy_to/from_pages() now check for zero length
  SUNRPC: Cleanup xdr_shrink_bufhead()
  SUNRPC: Fix xdr_expand_hole()
  SUNRPC: Fixes for xdr_align_data()
  SUNRPC: _shift_data_left/right_pages should check the shift length
  ...

5 files changed, 249 insertions, 257 deletions

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index a2c6455ea3fa..681ed98e4ba8 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -46,6 +46,11 @@
 #define NFS_RPC_SWAPFLAGS		(RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS)
 
 /*
+ * Size of the NFS directory verifier
+ */
+#define NFS_DIR_VERIFIER_SIZE		2
+
+/*
  * NFSv3/v4 Access mode cache entry
  */
 struct nfs_access_entry {
@@ -88,8 +93,8 @@ struct nfs_open_context {
 
 struct nfs_open_dir_context {
 	struct list_head list;
-	const struct cred *cred;
 	unsigned long attr_gencount;
+	__be32	verf[NFS_DIR_VERIFIER_SIZE];
 	__u64 dir_cookie;
 	__u64 dup_cookie;
 	signed char duped;
@@ -157,7 +162,7 @@ struct nfs_inode {
 	 * This is the cookie verifier used for NFSv3 readdir
 	 * operations
 	 */
-	__be32			cookieverf[2];
+	__be32			cookieverf[NFS_DIR_VERIFIER_SIZE];
 
 	atomic_long_t		nrequests;
 	struct nfs_mds_commit_info commit_info;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index d63cb862d58e..3327239fa2f9 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -750,6 +750,20 @@ struct nfs_entry {
 	struct nfs_server *	server;
 };
 
+struct nfs_readdir_arg {
+	struct dentry		*dentry;
+	const struct cred	*cred;
+	__be32			*verf;
+	u64			cookie;
+	struct page		**pages;
+	unsigned int		page_len;
+	bool			plus;
+};
+
+struct nfs_readdir_res {
+	__be32			*verf;
+};
+
 /*
  * The following types are for NFSv2 only.
  */
@@ -1744,8 +1758,7 @@ struct nfs_rpc_ops {
 			    unsigned int, struct iattr *);
 	int	(*mkdir)   (struct inode *, struct dentry *, struct iattr *);
 	int	(*rmdir)   (struct inode *, const struct qstr *);
-	int	(*readdir) (struct dentry *, const struct cred *,
-			    u64, struct page **, unsigned int, bool);
+	int	(*readdir) (struct nfs_readdir_arg *, struct nfs_readdir_res *);
 	int	(*mknod)   (struct inode *, struct dentry *, struct iattr *,
 			    dev_t);
 	int	(*statfs)  (struct nfs_server *, struct nfs_fh *,
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 9b35ce50cf2b..19b6dea27367 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -128,8 +128,8 @@ __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
 
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
-void	xdr_terminate_string(struct xdr_buf *, const u32);
-size_t	xdr_buf_pagecount(struct xdr_buf *buf);
+void	xdr_terminate_string(const struct xdr_buf *, const u32);
+size_t	xdr_buf_pagecount(const struct xdr_buf *buf);
 int	xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp);
 void	xdr_free_bvec(struct xdr_buf *buf);
 
@@ -182,15 +182,14 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
  * XDR buffer helper functions
  */
 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(const struct xdr_buf *buf, struct xdr_buf *subbuf,
-			      unsigned int base, unsigned int len);
+extern void xdr_buf_from_iov(const struct kvec *, struct xdr_buf *);
+extern int xdr_buf_subsegment(const struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
 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);
+extern int read_bytes_from_xdr_buf(const struct xdr_buf *, unsigned int, void *, unsigned int);
+extern int write_bytes_to_xdr_buf(const struct xdr_buf *, unsigned int, void *, unsigned int);
 
-extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32);
-extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *);
+extern int xdr_encode_word(const struct xdr_buf *, unsigned int, u32);
+extern int xdr_decode_word(const struct xdr_buf *, unsigned int, u32 *);
 
 struct xdr_array2_desc;
 typedef int (*xdr_xcode_elem_t)(struct xdr_array2_desc *desc, void *elem);
@@ -201,9 +200,9 @@ struct xdr_array2_desc {
 	xdr_xcode_elem_t xcode;
 };
 
-extern int xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
+extern int xdr_decode_array2(const struct xdr_buf *buf, unsigned int base,
 			     struct xdr_array2_desc *desc);
-extern int xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
+extern int xdr_encode_array2(const struct xdr_buf *buf, unsigned int base,
 			     struct xdr_array2_desc *desc);
 extern void _copy_from_pages(char *p, struct page **pages, size_t pgbase,
 			     size_t len);
@@ -251,9 +250,9 @@ extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
 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 int xdr_process_buf(const struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern unsigned int xdr_align_data(struct xdr_stream *, unsigned int offset, unsigned int length);
+extern unsigned int xdr_expand_hole(struct xdr_stream *, unsigned int offset, unsigned int length);
 extern bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
 				  unsigned int len);
 
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a603d48d2b2c..d2e97ee802af 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -330,6 +330,7 @@ struct xprt_class {
 	struct rpc_xprt *	(*setup)(struct xprt_create *);
 	struct module		*owner;
 	char			name[32];
+	const char *		netid[];
 };
 
 /*
@@ -384,7 +385,7 @@ xprt_disable_swap(struct rpc_xprt *xprt)
  */
 int			xprt_register_transport(struct xprt_class *type);
 int			xprt_unregister_transport(struct xprt_class *type);
-int			xprt_load_transport(const char *);
+int			xprt_find_transport_ident(const char *);
 void			xprt_wait_for_reply_request_def(struct rpc_task *task);
 void			xprt_wait_for_reply_request_rtt(struct rpc_task *task);
 void			xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status);
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 896aafc37b09..76e85e16854b 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -60,7 +60,7 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class,
 				),					\
 				TP_ARGS(wc, cid))
 
-DECLARE_EVENT_CLASS(xprtrdma_reply_event,
+DECLARE_EVENT_CLASS(xprtrdma_reply_class,
 	TP_PROTO(
 		const struct rpcrdma_rep *rep
 	),
@@ -68,29 +68,30 @@ DECLARE_EVENT_CLASS(xprtrdma_reply_event,
 	TP_ARGS(rep),
 
 	TP_STRUCT__entry(
-		__field(const void *, rep)
-		__field(const void *, r_xprt)
 		__field(u32, xid)
 		__field(u32, version)
 		__field(u32, proc)
+		__string(addr, rpcrdma_addrstr(rep->rr_rxprt))
+		__string(port, rpcrdma_portstr(rep->rr_rxprt))
 	),
 
 	TP_fast_assign(
-		__entry->rep = rep;
-		__entry->r_xprt = rep->rr_rxprt;
 		__entry->xid = be32_to_cpu(rep->rr_xid);
 		__entry->version = be32_to_cpu(rep->rr_vers);
 		__entry->proc = be32_to_cpu(rep->rr_proc);
+		__assign_str(addr, rpcrdma_addrstr(rep->rr_rxprt));
+		__assign_str(port, rpcrdma_portstr(rep->rr_rxprt));
 	),
 
-	TP_printk("rxprt %p xid=0x%08x rep=%p: version %u proc %u",
-		__entry->r_xprt, __entry->xid, __entry->rep,
-		__entry->version, __entry->proc
+	TP_printk("peer=[%s]:%s xid=0x%08x version=%u proc=%u",
+		__get_str(addr), __get_str(port),
+		__entry->xid, __entry->version, __entry->proc
 	)
 );
 
 #define DEFINE_REPLY_EVENT(name)					\
-		DEFINE_EVENT(xprtrdma_reply_event, name,		\
+		DEFINE_EVENT(xprtrdma_reply_class,			\
+				xprtrdma_reply_##name##_err,		\
 				TP_PROTO(				\
 					const struct rpcrdma_rep *rep	\
 				),					\
@@ -261,54 +262,67 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event,
 				),					\
 				TP_ARGS(task, mr, nsegs))
 
-DECLARE_EVENT_CLASS(xprtrdma_frwr_done,
+TRACE_DEFINE_ENUM(DMA_BIDIRECTIONAL);
+TRACE_DEFINE_ENUM(DMA_TO_DEVICE);
+TRACE_DEFINE_ENUM(DMA_FROM_DEVICE);
+TRACE_DEFINE_ENUM(DMA_NONE);
+
+#define xprtrdma_show_direction(x)					\
+		__print_symbolic(x,					\
+				{ DMA_BIDIRECTIONAL, "BIDIR" },		\
+				{ DMA_TO_DEVICE, "TO_DEVICE" },		\
+				{ DMA_FROM_DEVICE, "FROM_DEVICE" },	\
+				{ DMA_NONE, "NONE" })
+
+DECLARE_EVENT_CLASS(xprtrdma_mr_class,
 	TP_PROTO(
-		const struct ib_wc *wc,
-		const struct rpcrdma_frwr *frwr
+		const struct rpcrdma_mr *mr
 	),
 
-	TP_ARGS(wc, frwr),
+	TP_ARGS(mr),
 
 	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
 		__field(u32, mr_id)
-		__field(unsigned int, status)
-		__field(unsigned int, vendor_err)
+		__field(int, nents)
+		__field(u32, handle)
+		__field(u32, length)
+		__field(u64, offset)
+		__field(u32, dir)
 	),
 
 	TP_fast_assign(
-		__entry->mr_id = frwr->fr_mr->res.id;
-		__entry->status = wc->status;
-		__entry->vendor_err = __entry->status ? wc->vendor_err : 0;
+		const struct rpcrdma_req *req = mr->mr_req;
+		const struct rpc_task *task = req->rl_slot.rq_task;
+
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client->cl_clid;
+		__entry->mr_id  = mr->frwr.fr_mr->res.id;
+		__entry->nents  = mr->mr_nents;
+		__entry->handle = mr->mr_handle;
+		__entry->length = mr->mr_length;
+		__entry->offset = mr->mr_offset;
+		__entry->dir    = mr->mr_dir;
 	),
 
-	TP_printk(
-		"mr.id=%u: %s (%u/0x%x)",
-		__entry->mr_id, rdma_show_wc_status(__entry->status),
-		__entry->status, __entry->vendor_err
+	TP_printk("task:%u@%u mr.id=%u nents=%d %u@0x%016llx:0x%08x (%s)",
+		__entry->task_id, __entry->client_id,
+		__entry->mr_id, __entry->nents, __entry->length,
+		(unsigned long long)__entry->offset, __entry->handle,
+		xprtrdma_show_direction(__entry->dir)
 	)
 );
 
-#define DEFINE_FRWR_DONE_EVENT(name)					\
-		DEFINE_EVENT(xprtrdma_frwr_done, name,			\
+#define DEFINE_MR_EVENT(name)						\
+		DEFINE_EVENT(xprtrdma_mr_class,				\
+				xprtrdma_mr_##name,			\
 				TP_PROTO(				\
-					const struct ib_wc *wc,		\
-					const struct rpcrdma_frwr *frwr	\
+					const struct rpcrdma_mr *mr	\
 				),					\
-				TP_ARGS(wc, frwr))
-
-TRACE_DEFINE_ENUM(DMA_BIDIRECTIONAL);
-TRACE_DEFINE_ENUM(DMA_TO_DEVICE);
-TRACE_DEFINE_ENUM(DMA_FROM_DEVICE);
-TRACE_DEFINE_ENUM(DMA_NONE);
-
-#define xprtrdma_show_direction(x)					\
-		__print_symbolic(x,					\
-				{ DMA_BIDIRECTIONAL, "BIDIR" },		\
-				{ DMA_TO_DEVICE, "TO_DEVICE" },		\
-				{ DMA_FROM_DEVICE, "FROM_DEVICE" },	\
-				{ DMA_NONE, "NONE" })
+				TP_ARGS(mr))
 
-DECLARE_EVENT_CLASS(xprtrdma_mr,
+DECLARE_EVENT_CLASS(xprtrdma_anonymous_mr_class,
 	TP_PROTO(
 		const struct rpcrdma_mr *mr
 	),
@@ -340,45 +354,47 @@ DECLARE_EVENT_CLASS(xprtrdma_mr,
 	)
 );
 
-#define DEFINE_MR_EVENT(name) \
-		DEFINE_EVENT(xprtrdma_mr, xprtrdma_mr_##name, \
-				TP_PROTO( \
-					const struct rpcrdma_mr *mr \
-				), \
+#define DEFINE_ANON_MR_EVENT(name)					\
+		DEFINE_EVENT(xprtrdma_anonymous_mr_class,		\
+				xprtrdma_mr_##name,			\
+				TP_PROTO(				\
+					const struct rpcrdma_mr *mr	\
+				),					\
 				TP_ARGS(mr))
 
-DECLARE_EVENT_CLASS(xprtrdma_cb_event,
+DECLARE_EVENT_CLASS(xprtrdma_callback_class,
 	TP_PROTO(
+		const struct rpcrdma_xprt *r_xprt,
 		const struct rpc_rqst *rqst
 	),
 
-	TP_ARGS(rqst),
+	TP_ARGS(r_xprt, rqst),
 
 	TP_STRUCT__entry(
-		__field(const void *, rqst)
-		__field(const void *, rep)
-		__field(const void *, req)
 		__field(u32, xid)
+		__string(addr, rpcrdma_addrstr(r_xprt))
+		__string(port, rpcrdma_portstr(r_xprt))
 	),
 
 	TP_fast_assign(
-		__entry->rqst = rqst;
-		__entry->req = rpcr_to_rdmar(rqst);
-		__entry->rep = rpcr_to_rdmar(rqst)->rl_reply;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
+		__assign_str(addr, rpcrdma_addrstr(r_xprt));
+		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("xid=0x%08x, rqst=%p req=%p rep=%p",
-		__entry->xid, __entry->rqst, __entry->req, __entry->rep
+	TP_printk("peer=[%s]:%s xid=0x%08x",
+		__get_str(addr), __get_str(port), __entry->xid
 	)
 );
 
-#define DEFINE_CB_EVENT(name)						\
-		DEFINE_EVENT(xprtrdma_cb_event, name,			\
+#define DEFINE_CALLBACK_EVENT(name)					\
+		DEFINE_EVENT(xprtrdma_callback_class,			\
+				xprtrdma_cb_##name,			\
 				TP_PROTO(				\
+					const struct rpcrdma_xprt *r_xprt, \
 					const struct rpc_rqst *rqst	\
 				),					\
-				TP_ARGS(rqst))
+				TP_ARGS(r_xprt, rqst))
 
 /**
  ** Connection events
@@ -549,61 +565,33 @@ TRACE_EVENT(xprtrdma_createmrs,
 	)
 );
 
-TRACE_EVENT(xprtrdma_mr_get,
-	TP_PROTO(
-		const struct rpcrdma_req *req
-	),
-
-	TP_ARGS(req),
-
-	TP_STRUCT__entry(
-		__field(const void *, req)
-		__field(unsigned int, task_id)
-		__field(unsigned int, client_id)
-		__field(u32, xid)
-	),
-
-	TP_fast_assign(
-		const struct rpc_rqst *rqst = &req->rl_slot;
-
-		__entry->req = req;
-		__entry->task_id = rqst->rq_task->tk_pid;
-		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
-		__entry->xid = be32_to_cpu(rqst->rq_xid);
-	),
-
-	TP_printk("task:%u@%u xid=0x%08x req=%p",
-		__entry->task_id, __entry->client_id, __entry->xid,
-		__entry->req
-	)
-);
-
-TRACE_EVENT(xprtrdma_nomrs,
+TRACE_EVENT(xprtrdma_nomrs_err,
 	TP_PROTO(
+		const struct rpcrdma_xprt *r_xprt,
 		const struct rpcrdma_req *req
 	),
 
-	TP_ARGS(req),
+	TP_ARGS(r_xprt, req),
 
 	TP_STRUCT__entry(
-		__field(const void *, req)
 		__field(unsigned int, task_id)
 		__field(unsigned int, client_id)
-		__field(u32, xid)
+		__string(addr, rpcrdma_addrstr(r_xprt))
+		__string(port, rpcrdma_portstr(r_xprt))
 	),
 
 	TP_fast_assign(
 		const struct rpc_rqst *rqst = &req->rl_slot;
 
-		__entry->req = req;
 		__entry->task_id = rqst->rq_task->tk_pid;
 		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
-		__entry->xid = be32_to_cpu(rqst->rq_xid);
+		__assign_str(addr, rpcrdma_addrstr(r_xprt));
+		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("task:%u@%u xid=0x%08x req=%p",
-		__entry->task_id, __entry->client_id, __entry->xid,
-		__entry->req
+	TP_printk("peer=[%s]:%s task:%u@%u",
+		__get_str(addr), __get_str(port),
+		__entry->task_id, __entry->client_id
 	)
 );
 
@@ -735,8 +723,8 @@ TRACE_EVENT(xprtrdma_post_send,
 	TP_ARGS(req),
 
 	TP_STRUCT__entry(
-		__field(const void *, req)
-		__field(const void *, sc)
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(unsigned int, task_id)
 		__field(unsigned int, client_id)
 		__field(int, num_sge)
@@ -745,20 +733,21 @@ TRACE_EVENT(xprtrdma_post_send,
 
 	TP_fast_assign(
 		const struct rpc_rqst *rqst = &req->rl_slot;
+		const struct rpcrdma_sendctx *sc = req->rl_sendctx;
 
+		__entry->cq_id = sc->sc_cid.ci_queue_id;
+		__entry->completion_id = sc->sc_cid.ci_completion_id;
 		__entry->task_id = rqst->rq_task->tk_pid;
 		__entry->client_id = rqst->rq_task->tk_client ?
 				     rqst->rq_task->tk_client->cl_clid : -1;
-		__entry->req = req;
-		__entry->sc = req->rl_sendctx;
 		__entry->num_sge = req->rl_wr.num_sge;
 		__entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED;
 	),
 
-	TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %s",
+	TP_printk("task:%u@%u cq.id=%u cid=%d (%d SGE%s) %s",
 		__entry->task_id, __entry->client_id,
-		__entry->req, __entry->sc, __entry->num_sge,
-		(__entry->num_sge == 1 ? "" : "s"),
+		__entry->cq_id, __entry->completion_id,
+		__entry->num_sge, (__entry->num_sge == 1 ? "" : "s"),
 		(__entry->signaled ? "signaled" : "")
 	)
 );
@@ -771,15 +760,17 @@ TRACE_EVENT(xprtrdma_post_recv,
 	TP_ARGS(rep),
 
 	TP_STRUCT__entry(
-		__field(const void *, rep)
+		__field(u32, cq_id)
+		__field(int, completion_id)
 	),
 
 	TP_fast_assign(
-		__entry->rep = rep;
+		__entry->cq_id = rep->rr_cid.ci_queue_id;
+		__entry->completion_id = rep->rr_cid.ci_completion_id;
 	),
 
-	TP_printk("rep=%p",
-		__entry->rep
+	TP_printk("cq.id=%d cid=%d",
+		__entry->cq_id, __entry->completion_id
 	)
 );
 
@@ -816,7 +807,7 @@ TRACE_EVENT(xprtrdma_post_recvs,
 	)
 );
 
-TRACE_EVENT(xprtrdma_post_linv,
+TRACE_EVENT(xprtrdma_post_linv_err,
 	TP_PROTO(
 		const struct rpcrdma_req *req,
 		int status
@@ -825,19 +816,21 @@ TRACE_EVENT(xprtrdma_post_linv,
 	TP_ARGS(req, status),
 
 	TP_STRUCT__entry(
-		__field(const void *, req)
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
 		__field(int, status)
-		__field(u32, xid)
 	),
 
 	TP_fast_assign(
-		__entry->req = req;
+		const struct rpc_task *task = req->rl_slot.rq_task;
+
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client->cl_clid;
 		__entry->status = status;
-		__entry->xid = be32_to_cpu(req->rl_slot.rq_xid);
 	),
 
-	TP_printk("req=%p xid=0x%08x status=%d",
-		__entry->req, __entry->xid, __entry->status
+	TP_printk("task:%u@%u status=%d",
+		__entry->task_id, __entry->client_id, __entry->status
 	)
 );
 
@@ -845,75 +838,12 @@ TRACE_EVENT(xprtrdma_post_linv,
  ** Completion events
  **/
 
-TRACE_EVENT(xprtrdma_wc_send,
-	TP_PROTO(
-		const struct rpcrdma_sendctx *sc,
-		const struct ib_wc *wc
-	),
-
-	TP_ARGS(sc, wc),
-
-	TP_STRUCT__entry(
-		__field(const void *, req)
-		__field(const void *, sc)
-		__field(unsigned int, unmap_count)
-		__field(unsigned int, status)
-		__field(unsigned int, vendor_err)
-	),
-
-	TP_fast_assign(
-		__entry->req = sc->sc_req;
-		__entry->sc = sc;
-		__entry->unmap_count = sc->sc_unmap_count;
-		__entry->status = wc->status;
-		__entry->vendor_err = __entry->status ? wc->vendor_err : 0;
-	),
-
-	TP_printk("req=%p sc=%p unmapped=%u: %s (%u/0x%x)",
-		__entry->req, __entry->sc, __entry->unmap_count,
-		rdma_show_wc_status(__entry->status),
-		__entry->status, __entry->vendor_err
-	)
-);
-
-TRACE_EVENT(xprtrdma_wc_receive,
-	TP_PROTO(
-		const struct ib_wc *wc
-	),
-
-	TP_ARGS(wc),
-
-	TP_STRUCT__entry(
-		__field(const void *, rep)
-		__field(u32, byte_len)
-		__field(unsigned int, status)
-		__field(u32, vendor_err)
-	),
-
-	TP_fast_assign(
-		__entry->rep = container_of(wc->wr_cqe, struct rpcrdma_rep,
-					    rr_cqe);
-		__entry->status = wc->status;
-		if (wc->status) {
-			__entry->byte_len = 0;
-			__entry->vendor_err = wc->vendor_err;
-		} else {
-			__entry->byte_len = wc->byte_len;
-			__entry->vendor_err = 0;
-		}
-	),
-
-	TP_printk("rep=%p %u bytes: %s (%u/0x%x)",
-		__entry->rep, __entry->byte_len,
-		rdma_show_wc_status(__entry->status),
-		__entry->status, __entry->vendor_err
-	)
-);
-
-DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_fastreg);
-DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li);
-DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_wake);
-DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_done);
+DEFINE_COMPLETION_EVENT(xprtrdma_wc_receive);
+DEFINE_COMPLETION_EVENT(xprtrdma_wc_send);
+DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg);
+DEFINE_COMPLETION_EVENT(xprtrdma_wc_li);
+DEFINE_COMPLETION_EVENT(xprtrdma_wc_li_wake);
+DEFINE_COMPLETION_EVENT(xprtrdma_wc_li_done);
 
 TRACE_EVENT(xprtrdma_frwr_alloc,
 	TP_PROTO(
@@ -1036,9 +966,9 @@ TRACE_EVENT(xprtrdma_frwr_maperr,
 
 DEFINE_MR_EVENT(localinv);
 DEFINE_MR_EVENT(map);
-DEFINE_MR_EVENT(unmap);
-DEFINE_MR_EVENT(reminv);
-DEFINE_MR_EVENT(recycle);
+
+DEFINE_ANON_MR_EVENT(unmap);
+DEFINE_ANON_MR_EVENT(recycle);
 
 TRACE_EVENT(xprtrdma_dma_maperr,
 	TP_PROTO(
@@ -1066,17 +996,14 @@ TRACE_EVENT(xprtrdma_reply,
 	TP_PROTO(
 		const struct rpc_task *task,
 		const struct rpcrdma_rep *rep,
-		const struct rpcrdma_req *req,
 		unsigned int credits
 	),
 
-	TP_ARGS(task, rep, req, credits),
+	TP_ARGS(task, rep, credits),
 
 	TP_STRUCT__entry(
 		__field(unsigned int, task_id)
 		__field(unsigned int, client_id)
-		__field(const void *, rep)
-		__field(const void *, req)
 		__field(u32, xid)
 		__field(unsigned int, credits)
 	),
@@ -1084,49 +1011,102 @@ TRACE_EVENT(xprtrdma_reply,
 	TP_fast_assign(
 		__entry->task_id = task->tk_pid;
 		__entry->client_id = task->tk_client->cl_clid;
-		__entry->rep = rep;
-		__entry->req = req;
 		__entry->xid = be32_to_cpu(rep->rr_xid);
 		__entry->credits = credits;
 	),
 
-	TP_printk("task:%u@%u xid=0x%08x, %u credits, rep=%p -> req=%p",
+	TP_printk("task:%u@%u xid=0x%08x credits=%u",
 		__entry->task_id, __entry->client_id, __entry->xid,
-		__entry->credits, __entry->rep, __entry->req
+		__entry->credits
 	)
 );
 
-TRACE_EVENT(xprtrdma_defer_cmp,
+DEFINE_REPLY_EVENT(vers);
+DEFINE_REPLY_EVENT(rqst);
+DEFINE_REPLY_EVENT(short);
+DEFINE_REPLY_EVENT(hdr);
+
+TRACE_EVENT(xprtrdma_err_vers,
 	TP_PROTO(
-		const struct rpcrdma_rep *rep
+		const struct rpc_rqst *rqst,
+		__be32 *min,
+		__be32 *max
 	),
 
-	TP_ARGS(rep),
+	TP_ARGS(rqst, min, max),
 
 	TP_STRUCT__entry(
 		__field(unsigned int, task_id)
 		__field(unsigned int, client_id)
-		__field(const void *, rep)
 		__field(u32, xid)
+		__field(u32, min)
+		__field(u32, max)
 	),
 
 	TP_fast_assign(
-		__entry->task_id = rep->rr_rqst->rq_task->tk_pid;
-		__entry->client_id = rep->rr_rqst->rq_task->tk_client->cl_clid;
-		__entry->rep = rep;
-		__entry->xid = be32_to_cpu(rep->rr_xid);
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
+		__entry->xid = be32_to_cpu(rqst->rq_xid);
+		__entry->min = be32_to_cpup(min);
+		__entry->max = be32_to_cpup(max);
 	),
 
-	TP_printk("task:%u@%u xid=0x%08x rep=%p",
+	TP_printk("task:%u@%u xid=0x%08x versions=[%u, %u]",
 		__entry->task_id, __entry->client_id, __entry->xid,
-		__entry->rep
+		__entry->min, __entry->max
+	)
+);
+
+TRACE_EVENT(xprtrdma_err_chunk,
+	TP_PROTO(
+		const struct rpc_rqst *rqst
+	),
+
+	TP_ARGS(rqst),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, xid)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
+		__entry->xid = be32_to_cpu(rqst->rq_xid);
+	),
+
+	TP_printk("task:%u@%u xid=0x%08x",
+		__entry->task_id, __entry->client_id, __entry->xid
 	)
 );
 
-DEFINE_REPLY_EVENT(xprtrdma_reply_vers);
-DEFINE_REPLY_EVENT(xprtrdma_reply_rqst);
-DEFINE_REPLY_EVENT(xprtrdma_reply_short);
-DEFINE_REPLY_EVENT(xprtrdma_reply_hdr);
+TRACE_EVENT(xprtrdma_err_unrecognized,
+	TP_PROTO(
+		const struct rpc_rqst *rqst,
+		__be32 *procedure
+	),
+
+	TP_ARGS(rqst, procedure),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, xid)
+		__field(u32, procedure)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
+		__entry->procedure = be32_to_cpup(procedure);
+	),
+
+	TP_printk("task:%u@%u xid=0x%08x procedure=%u",
+		__entry->task_id, __entry->client_id, __entry->xid,
+		__entry->procedure
+	)
+);
 
 TRACE_EVENT(xprtrdma_fixup,
 	TP_PROTO(
@@ -1187,6 +1167,28 @@ TRACE_EVENT(xprtrdma_decode_seg,
 	)
 );
 
+TRACE_EVENT(xprtrdma_mrs_zap,
+	TP_PROTO(
+		const struct rpc_task *task
+	),
+
+	TP_ARGS(task),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client->cl_clid;
+	),
+
+	TP_printk("task:%u@%u",
+		__entry->task_id, __entry->client_id
+	)
+);
+
 /**
  ** Callback events
  **/
@@ -1219,36 +1221,8 @@ TRACE_EVENT(xprtrdma_cb_setup,
 	)
 );
 
-DEFINE_CB_EVENT(xprtrdma_cb_call);
-DEFINE_CB_EVENT(xprtrdma_cb_reply);
-
-TRACE_EVENT(xprtrdma_leaked_rep,
-	TP_PROTO(
-		const struct rpc_rqst *rqst,
-		const struct rpcrdma_rep *rep
-	),
-
-	TP_ARGS(rqst, rep),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, task_id)
-		__field(unsigned int, client_id)
-		__field(u32, xid)
-		__field(const void *, rep)
-	),
-
-	TP_fast_assign(
-		__entry->task_id = rqst->rq_task->tk_pid;
-		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
-		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->rep = rep;
-	),
-
-	TP_printk("task:%u@%u xid=0x%08x rep=%p",
-		__entry->task_id, __entry->client_id, __entry->xid,
-		__entry->rep
-	)
-);
+DEFINE_CALLBACK_EVENT(call);
+DEFINE_CALLBACK_EVENT(reply);
 
 /**
  ** Server-side RPC/RDMA events