Merge tag 'nfsd-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "The bulk of the patches for this release are optimizations, code
  clean-ups, and minor bug fixes.

  One new feature to mention is that NFSD administrators now have the
  ability to revoke NFSv4 open and lock state. NFSD's NFSv3 support has
  had this capability for some time.

  As always I am grateful to NFSD contributors, reviewers, and testers"

* tag 'nfsd-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (75 commits)
  NFSD: Clean up nfsd4_encode_replay()
  NFSD: send OP_CB_RECALL_ANY to clients when number of delegations reaches its limit
  NFSD: Document nfsd_setattr() fill-attributes behavior
  nfsd: Fix NFSv3 atomicity bugs in nfsd_setattr()
  nfsd: Fix a regression in nfsd_setattr()
  NFSD: OP_CB_RECALL_ANY should recall both read and write delegations
  NFSD: handle GETATTR conflict with write delegation
  NFSD: add support for CB_GETATTR callback
  NFSD: Document the phases of CREATE_SESSION
  NFSD: Fix the NFSv4.1 CREATE_SESSION operation
  nfsd: clean up comments over nfs4_client definition
  svcrdma: Add Write chunk WRs to the RPC's Send WR chain
  svcrdma: Post WRs for Write chunks in svc_rdma_sendto()
  svcrdma: Post the Reply chunk and Send WR together
  svcrdma: Move write_info for Reply chunks into struct svc_rdma_send_ctxt
  svcrdma: Post Send WR chain
  svcrdma: Fix retry loop in svc_rdma_send()
  svcrdma: Prevent a UAF in svc_rdma_send()
  svcrdma: Fix SQ wake-ups
  svcrdma: Increase the per-transport rw_ctx count
  ...

4 files changed, 88 insertions, 10 deletions

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 67cf1c9efd80..23617da0e565 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -339,7 +339,6 @@ struct svc_program {
 	const struct svc_version **pg_vers;	/* version array */
 	char *			pg_name;	/* service name */
 	char *			pg_class;	/* class name: services sharing authentication */
-	struct svc_stat *	pg_stats;	/* rpc statistics */
 	enum svc_auth_status	(*pg_authenticate)(struct svc_rqst *rqstp);
 	__be32			(*pg_init_request)(struct svc_rqst *,
 						   const struct svc_program *,
@@ -411,7 +410,9 @@ bool		   svc_rqst_replace_page(struct svc_rqst *rqstp,
 void		   svc_rqst_release_pages(struct svc_rqst *rqstp);
 void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
-struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
+struct svc_serv *  svc_create_pooled(struct svc_program *prog,
+				     struct svc_stat *stats,
+				     unsigned int bufsize,
 				     int (*threadfn)(void *data));
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_info *si, struct file *file);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index e7595ae62fe2..24cd199dd6f3 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -203,6 +203,30 @@ struct svc_rdma_recv_ctxt {
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
+/*
+ * State for sending a Write chunk.
+ *  - Tracks progress of writing one chunk over all its segments
+ *  - Stores arguments for the SGL constructor functions
+ */
+struct svc_rdma_write_info {
+	struct svcxprt_rdma	*wi_rdma;
+	struct list_head	wi_list;
+
+	const struct svc_rdma_chunk	*wi_chunk;
+
+	/* write state of this chunk */
+	unsigned int		wi_seg_off;
+	unsigned int		wi_seg_no;
+
+	/* SGL constructor arguments */
+	const struct xdr_buf	*wi_xdr;
+	unsigned char		*wi_base;
+	unsigned int		wi_next_off;
+
+	struct svc_rdma_chunk_ctxt	wi_cc;
+	struct work_struct	wi_work;
+};
+
 struct svc_rdma_send_ctxt {
 	struct llist_node	sc_node;
 	struct rpc_rdma_cid	sc_cid;
@@ -210,9 +234,15 @@ struct svc_rdma_send_ctxt {
 
 	struct svcxprt_rdma	*sc_rdma;
 	struct ib_send_wr	sc_send_wr;
+	struct ib_send_wr	*sc_wr_chain;
+	int			sc_sqecount;
 	struct ib_cqe		sc_cqe;
 	struct xdr_buf		sc_hdrbuf;
 	struct xdr_stream	sc_stream;
+
+	struct list_head	sc_write_info_list;
+	struct svc_rdma_write_info sc_reply_info;
+
 	void			*sc_xprt_buf;
 	int			sc_page_count;
 	int			sc_cur_sge_no;
@@ -236,18 +266,27 @@ extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt);
 extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
+extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+			     struct svc_rdma_chunk_ctxt *cc);
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
 extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
 			     struct svc_rdma_chunk_ctxt *cc);
 extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
 				struct svc_rdma_chunk_ctxt *cc,
 				enum dma_data_direction dir);
-extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     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,
-				     const struct xdr_buf *xdr);
+extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma,
+					 struct svc_rdma_send_ctxt *ctxt);
+extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma,
+					 struct svc_rdma_send_ctxt *ctxt);
+extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma,
+				       const struct svc_rdma_pcl *write_pcl,
+				       struct svc_rdma_send_ctxt *sctxt,
+				       const struct xdr_buf *xdr);
+extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma,
+					const struct svc_rdma_pcl *write_pcl,
+					const struct svc_rdma_pcl *reply_pcl,
+					struct svc_rdma_send_ctxt *sctxt,
+					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);
@@ -258,8 +297,8 @@ extern struct svc_rdma_send_ctxt *
 		svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma);
 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 svc_rdma_send_ctxt *ctxt);
+extern int svc_rdma_post_send(struct svcxprt_rdma *rdma,
+			      struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_pcl *write_pcl,
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 110c1475c527..027ac3ab457d 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2118,6 +2118,10 @@ DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_write);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_err);
 
+DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_reply);
+DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_reply_flush);
+DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_reply_err);
+
 TRACE_EVENT(svcrdma_qp_error,
 	TP_PROTO(
 		const struct ib_event *event,
diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h
index 0d9d48dca38a..64ab5dac59ce 100644
--- a/include/trace/misc/nfs.h
+++ b/include/trace/misc/nfs.h
@@ -385,3 +385,37 @@ TRACE_DEFINE_ENUM(IOMODE_ANY);
 		{ SEQ4_STATUS_RESTART_RECLAIM_NEEDED,	"RESTART_RECLAIM_NEEDED" }, \
 		{ SEQ4_STATUS_CB_PATH_DOWN_SESSION,	"CB_PATH_DOWN_SESSION" }, \
 		{ SEQ4_STATUS_BACKCHANNEL_FAULT,	"BACKCHANNEL_FAULT" })
+
+TRACE_DEFINE_ENUM(OP_CB_GETATTR);
+TRACE_DEFINE_ENUM(OP_CB_RECALL);
+TRACE_DEFINE_ENUM(OP_CB_LAYOUTRECALL);
+TRACE_DEFINE_ENUM(OP_CB_NOTIFY);
+TRACE_DEFINE_ENUM(OP_CB_PUSH_DELEG);
+TRACE_DEFINE_ENUM(OP_CB_RECALL_ANY);
+TRACE_DEFINE_ENUM(OP_CB_RECALLABLE_OBJ_AVAIL);
+TRACE_DEFINE_ENUM(OP_CB_RECALL_SLOT);
+TRACE_DEFINE_ENUM(OP_CB_SEQUENCE);
+TRACE_DEFINE_ENUM(OP_CB_WANTS_CANCELLED);
+TRACE_DEFINE_ENUM(OP_CB_NOTIFY_LOCK);
+TRACE_DEFINE_ENUM(OP_CB_NOTIFY_DEVICEID);
+TRACE_DEFINE_ENUM(OP_CB_OFFLOAD);
+TRACE_DEFINE_ENUM(OP_CB_ILLEGAL);
+
+#define show_nfs4_cb_op(x) \
+	__print_symbolic(x, \
+		{ 0,				"CB_NULL" }, \
+		{ 1,				"CB_COMPOUND" }, \
+		{ OP_CB_GETATTR,		"CB_GETATTR" }, \
+		{ OP_CB_RECALL,			"CB_RECALL" }, \
+		{ OP_CB_LAYOUTRECALL,		"CB_LAYOUTRECALL" }, \
+		{ OP_CB_NOTIFY,			"CB_NOTIFY" }, \
+		{ OP_CB_PUSH_DELEG,		"CB_PUSH_DELEG" }, \
+		{ OP_CB_RECALL_ANY,		"CB_RECALL_ANY" }, \
+		{ OP_CB_RECALLABLE_OBJ_AVAIL,	"CB_RECALLABLE_OBJ_AVAIL" }, \
+		{ OP_CB_RECALL_SLOT,		"CB_RECALL_SLOT" }, \
+		{ OP_CB_SEQUENCE,		"CB_SEQUENCE" }, \
+		{ OP_CB_WANTS_CANCELLED,	"CB_WANTS_CANCELLED" }, \
+		{ OP_CB_NOTIFY_LOCK,		"CB_NOTIFY_LOCK" }, \
+		{ OP_CB_NOTIFY_DEVICEID,	"CB_NOTIFY_DEVICEID" }, \
+		{ OP_CB_OFFLOAD,		"CB_OFFLOAD" }, \
+		{ OP_CB_ILLEGAL,		"CB_ILLEGAL" })