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()
  ...

2 files changed, 89 insertions, 78 deletions

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);