Merge tag 'nfs-for-5.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Stable bugfixes:
   - Dequeue the request from the receive queue while we're re-encoding
     # v4.20+
   - Fix buffer handling of GSS MIC without slack # 5.1

  Features:
   - Increase xprtrdma maximum transport header and slot table sizes
   - Add support for nfs4_call_sync() calls using a custom
     rpc_task_struct
   - Optimize the default readahead size
   - Enable pNFS filelayout LAYOUTGET on OPEN

  Other bugfixes and cleanups:
   - Fix possible null-pointer dereferences and memory leaks
   - Various NFS over RDMA cleanups
   - Various NFS over RDMA comment updates
   - Don't receive TCP data into a reset request buffer
   - Don't try to parse incomplete RPC messages
   - Fix congestion window race with disconnect
   - Clean up pNFS return-on-close error handling
   - Fixes for NFS4ERR_OLD_STATEID handling"

* tag 'nfs-for-5.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (53 commits)
  pNFS/filelayout: enable LAYOUTGET on OPEN
  NFS: Optimise the default readahead size
  NFSv4: Handle NFS4ERR_OLD_STATEID in LOCKU
  NFSv4: Handle NFS4ERR_OLD_STATEID in CLOSE/OPEN_DOWNGRADE
  NFSv4: Fix OPEN_DOWNGRADE error handling
  pNFS: Handle NFS4ERR_OLD_STATEID on layoutreturn by bumping the state seqid
  NFSv4: Add a helper to increment stateid seqids
  NFSv4: Handle RPC level errors in LAYOUTRETURN
  NFSv4: Handle NFS4ERR_DELAY correctly in return-on-close
  NFSv4: Clean up pNFS return-on-close error handling
  pNFS: Ensure we do clear the return-on-close layout stateid on fatal errors
  NFS: remove unused check for negative dentry
  NFSv3: use nfs_add_or_obtain() to create and reference inodes
  NFS: Refactor nfs_instantiate() for dentry referencing callers
  SUNRPC: Fix congestion window race with disconnect
  SUNRPC: Don't try to parse incomplete RPC messages
  SUNRPC: Rename xdr_buf_read_netobj to xdr_buf_read_mic
  SUNRPC: Fix buffer handling of GSS MIC without slack
  SUNRPC: RPC level errors should always set task->tk_rpc_status
  SUNRPC: Don't receive TCP data into a request buffer that has been reset
  ...

6 files changed, 82 insertions, 19 deletions

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 0a11712a80e3..570a60c2f4f4 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -490,6 +490,9 @@ extern const struct file_operations nfs_dir_operations;
 extern const struct dentry_operations nfs_dentry_operations;
 
 extern void nfs_force_lookup_revalidate(struct inode *dir);
+extern struct dentry *nfs_add_or_obtain(struct dentry *dentry,
+			struct nfs_fh *fh, struct nfs_fattr *fattr,
+			struct nfs4_label *label);
 extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh,
 			struct nfs_fattr *fattr, struct nfs4_label *label);
 extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags);
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 27536b961552..a6ef35184ef1 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -242,9 +242,6 @@ void		rpc_sleep_on_priority_timeout(struct rpc_wait_queue *queue,
 void		rpc_sleep_on_priority(struct rpc_wait_queue *,
 					struct rpc_task *,
 					int priority);
-void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq,
-		struct rpc_wait_queue *queue,
-		struct rpc_task *task);
 void		rpc_wake_up_queued_task(struct rpc_wait_queue *,
 					struct rpc_task *);
 void		rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *,
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 8a87d8bcb197..f33e5013bdfb 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -186,7 +186,7 @@ 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_read_netobj(struct xdr_buf *, struct xdr_netobj *, unsigned int);
+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);
 
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 13e108bcc9eb..d783e15ba898 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -352,6 +352,7 @@ bool			xprt_prepare_transmit(struct rpc_task *task);
 void			xprt_request_enqueue_transmit(struct rpc_task *task);
 void			xprt_request_enqueue_receive(struct rpc_task *task);
 void			xprt_request_wait_receive(struct rpc_task *task);
+void			xprt_request_dequeue_xprt(struct rpc_task *task);
 bool			xprt_request_need_retransmit(struct rpc_task *task);
 void			xprt_transmit(struct rpc_task *task);
 void			xprt_end_transmit(struct rpc_task *task);
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index 86fc38ff0355..16c239e0d6dd 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -49,9 +49,9 @@
  * fully-chunked NFS message (read chunks are the largest). Note only
  * a single chunk type per message is supported currently.
  */
-#define RPCRDMA_MIN_SLOT_TABLE	(2U)
+#define RPCRDMA_MIN_SLOT_TABLE	(4U)
 #define RPCRDMA_DEF_SLOT_TABLE	(128U)
-#define RPCRDMA_MAX_SLOT_TABLE	(256U)
+#define RPCRDMA_MAX_SLOT_TABLE	(16384U)
 
 #define RPCRDMA_MIN_INLINE  (1024)	/* min inline thresh */
 #define RPCRDMA_DEF_INLINE  (4096)	/* default inline thresh */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index f6a4eaa85a3e..a13830616107 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -451,20 +451,81 @@ TRACE_EVENT(xprtrdma_createmrs,
 
 	TP_STRUCT__entry(
 		__field(const void *, r_xprt)
+		__string(addr, rpcrdma_addrstr(r_xprt))
+		__string(port, rpcrdma_portstr(r_xprt))
 		__field(unsigned int, count)
 	),
 
 	TP_fast_assign(
 		__entry->r_xprt = r_xprt;
 		__entry->count = count;
+		__assign_str(addr, rpcrdma_addrstr(r_xprt));
+		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("r_xprt=%p: created %u MRs",
-		__entry->r_xprt, __entry->count
+	TP_printk("peer=[%s]:%s r_xprt=%p: created %u MRs",
+		__get_str(addr), __get_str(port), __entry->r_xprt,
+		__entry->count
 	)
 );
 
-DEFINE_RXPRT_EVENT(xprtrdma_nomrs);
+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,
+	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
+	)
+);
 
 DEFINE_RDCH_EVENT(read);
 DEFINE_WRCH_EVENT(write);
@@ -623,21 +684,21 @@ TRACE_EVENT(xprtrdma_post_send,
 
 TRACE_EVENT(xprtrdma_post_recv,
 	TP_PROTO(
-		const struct ib_cqe *cqe
+		const struct rpcrdma_rep *rep
 	),
 
-	TP_ARGS(cqe),
+	TP_ARGS(rep),
 
 	TP_STRUCT__entry(
-		__field(const void *, cqe)
+		__field(const void *, rep)
 	),
 
 	TP_fast_assign(
-		__entry->cqe = cqe;
+		__entry->rep = rep;
 	),
 
-	TP_printk("cqe=%p",
-		__entry->cqe
+	TP_printk("rep=%p",
+		__entry->rep
 	)
 );
 
@@ -715,14 +776,15 @@ TRACE_EVENT(xprtrdma_wc_receive,
 	TP_ARGS(wc),
 
 	TP_STRUCT__entry(
-		__field(const void *, cqe)
+		__field(const void *, rep)
 		__field(u32, byte_len)
 		__field(unsigned int, status)
 		__field(u32, vendor_err)
 	),
 
 	TP_fast_assign(
-		__entry->cqe = wc->wr_cqe;
+		__entry->rep = container_of(wc->wr_cqe, struct rpcrdma_rep,
+					    rr_cqe);
 		__entry->status = wc->status;
 		if (wc->status) {
 			__entry->byte_len = 0;
@@ -733,8 +795,8 @@ TRACE_EVENT(xprtrdma_wc_receive,
 		}
 	),
 
-	TP_printk("cqe=%p %u bytes: %s (%u/0x%x)",
-		__entry->cqe, __entry->byte_len,
+	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
 	)