Merge tag 'nfs-for-4.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable fixes:

   - Fix a 1-byte stack overflow in nfs_idmap_read_and_verify_message

   - Fix a hang due to incorrect error returns in rpcrdma_convert_iovs()

   - Revert an incorrect change to the NFSv4.1 callback channel

   - Fix a bug in the NFSv4.1 sequence error handling

  Features and optimisations:

   - Support for piggybacking a LAYOUTGET operation to the OPEN compound

   - RDMA performance enhancements to deal with transport congestion

   - Add proper SPDX tags for NetApp-contributed RDMA source

   - Do not request delegated file attributes (size+change) from the
     server

   - Optimise away a GETATTR in the lookup revalidate code when doing
     NFSv4 OPEN

   - Optimise away unnecessary lookups for rename targets

   - Misc performance improvements when freeing NFSv4 delegations

  Bugfixes and cleanups:

   - Try to fail quickly if proto=rdma

   - Clean up RDMA receive trace points

   - Fix sillyrename to return the delegation when appropriate

   - Misc attribute revalidation fixes

   - Immediately clear the pNFS layout on a file when the server returns
     ESTALE

   - Return NFS4ERR_DELAY when delegation/layout recalls fail due to
     igrab()

   - Fix the client behaviour on NFS4ERR_SEQ_FALSE_RETRY"

* tag 'nfs-for-4.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (80 commits)
  skip LAYOUTRETURN if layout is invalid
  NFSv4.1: Fix the client behaviour on NFS4ERR_SEQ_FALSE_RETRY
  NFSv4: Fix a typo in nfs41_sequence_process
  NFSv4: Revert commit 5f83d86cf531d ("NFSv4.x: Fix wraparound issues..")
  NFSv4: Return NFS4ERR_DELAY when a layout recall fails due to igrab()
  NFSv4: Return NFS4ERR_DELAY when a delegation recall fails due to igrab()
  NFSv4.0: Remove transport protocol name from non-UCS client ID
  NFSv4.0: Remove cl_ipaddr from non-UCS client ID
  NFSv4: Fix a compiler warning when CONFIG_NFS_V4_1 is undefined
  NFS: Filter cache invalidation when holding a delegation
  NFS: Ignore NFS_INO_REVAL_FORCED in nfs_check_inode_attributes()
  NFS: Improve caching while holding a delegation
  NFS: Fix attribute revalidation
  NFS: fix up nfs_setattr_update_inode
  NFSv4: Ensure the inode is clean when we set a delegation
  NFSv4: Ignore NFS_INO_REVAL_FORCED in nfs4_proc_access
  NFSv4: Don't ask for delegated attributes when adding a hard link
  NFSv4: Don't ask for delegated attributes when revalidating the inode
  NFS: Pass the inode down to the getattr() callback
  NFSv4: Don't request size+change attribute if they are delegated to us
  ...

7 files changed, 86 insertions, 28 deletions

diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 4e735be53e70..74ae3e1d19a0 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -28,6 +28,7 @@ struct nfs41_impl_id;
 struct nfs_client {
 	refcount_t		cl_count;
 	atomic_t		cl_mds_count;
+	seqcount_t		cl_callback_count;
 	int			cl_cons_state;	/* current construction state (-ve: init error) */
 #define NFS_CS_READY		0		/* ready to be used */
 #define NFS_CS_INITING		1		/* busy initialising */
@@ -235,6 +236,7 @@ struct nfs_server {
 #define NFS_CAP_ACLS		(1U << 3)
 #define NFS_CAP_ATOMIC_OPEN	(1U << 4)
 /* #define NFS_CAP_CHANGE_ATTR	(1U << 5) */
+#define NFS_CAP_LGOPEN		(1U << 5)
 #define NFS_CAP_FILEID		(1U << 6)
 #define NFS_CAP_MODE		(1U << 7)
 #define NFS_CAP_NLINK		(1U << 8)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 34d28564ecf3..9dee3c23895d 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -259,6 +259,7 @@ struct nfs4_layoutget_args {
 
 struct nfs4_layoutget_res {
 	struct nfs4_sequence_res seq_res;
+	int status;
 	__u32 return_on_close;
 	struct pnfs_layout_range range;
 	__u32 type;
@@ -270,6 +271,7 @@ struct nfs4_layoutget {
 	struct nfs4_layoutget_args args;
 	struct nfs4_layoutget_res res;
 	struct rpc_cred *cred;
+	unsigned callback_count;
 	gfp_t gfp_flags;
 };
 
@@ -435,6 +437,7 @@ struct nfs_openargs {
 	enum createmode4	createmode;
 	const struct nfs4_label *label;
 	umode_t			umask;
+	struct nfs4_layoutget_args *lg_args;
 };
 
 struct nfs_openres {
@@ -457,6 +460,7 @@ struct nfs_openres {
 	__u32			access_request;
 	__u32			access_supported;
 	__u32			access_result;
+	struct nfs4_layoutget_res *lg_res;
 };
 
 /*
@@ -1577,7 +1581,8 @@ struct nfs_rpc_ops {
 	struct dentry *(*try_mount) (int, const char *, struct nfs_mount_info *,
 				     struct nfs_subversion *);
 	int	(*getattr) (struct nfs_server *, struct nfs_fh *,
-			    struct nfs_fattr *, struct nfs4_label *);
+			    struct nfs_fattr *, struct nfs4_label *,
+			    struct inode *);
 	int	(*setattr) (struct dentry *, struct nfs_fattr *,
 			    struct iattr *);
 	int	(*lookup)  (struct inode *, const struct qstr *,
@@ -1591,7 +1596,7 @@ struct nfs_rpc_ops {
 	int	(*create)  (struct inode *, struct dentry *,
 			    struct iattr *, int);
 	int	(*remove)  (struct inode *, struct dentry *);
-	void	(*unlink_setup)  (struct rpc_message *, struct dentry *);
+	void	(*unlink_setup)  (struct rpc_message *, struct dentry *, struct inode *);
 	void	(*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *);
 	int	(*unlink_done) (struct rpc_task *, struct inode *);
 	void	(*rename_setup)  (struct rpc_message *msg,
@@ -1620,9 +1625,11 @@ struct nfs_rpc_ops {
 				    struct nfs_pgio_header *);
 	void	(*read_setup)(struct nfs_pgio_header *, struct rpc_message *);
 	int	(*read_done)(struct rpc_task *, struct nfs_pgio_header *);
-	void	(*write_setup)(struct nfs_pgio_header *, struct rpc_message *);
+	void	(*write_setup)(struct nfs_pgio_header *, struct rpc_message *,
+				struct rpc_clnt **);
 	int	(*write_done)(struct rpc_task *, struct nfs_pgio_header *);
-	void	(*commit_setup) (struct nfs_commit_data *, struct rpc_message *);
+	void	(*commit_setup) (struct nfs_commit_data *, struct rpc_message *,
+				struct rpc_clnt **);
 	void	(*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *);
 	int	(*commit_done) (struct rpc_task *, struct nfs_commit_data *);
 	int	(*lock)(struct file *, int, struct file_lock *);
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 127f534fec94..36df6ccbc874 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -404,6 +404,19 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
 	     pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 /**
+ * list_for_each_entry_from_rcu - iterate over a list from current point
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_node within the struct.
+ *
+ * Iterate over the tail of a list starting from a given position,
+ * which must have been in the list when the RCU read lock was taken.
+ */
+#define list_for_each_entry_from_rcu(pos, head, member)			\
+	for (; &(pos)->member != (head);					\
+		pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member))
+
+/**
  * hlist_del_rcu - deletes entry from hash list without re-initialization
  * @n: the element to delete from the hash list.
  *
diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index 8f144db73e38..92d182fd8e3b 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (c) 2015-2017 Oracle. All rights reserved.
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 5fea0fb420df..336fd1a19cca 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -84,7 +84,6 @@ struct rpc_rqst {
 	void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */
 	struct list_head	rq_list;
 
-	void			*rq_xprtdata;	/* Per-xprt private data */
 	void			*rq_buffer;	/* Call XDR encode buffer */
 	size_t			rq_callsize;
 	void			*rq_rbuffer;	/* Reply XDR decode buffer */
@@ -127,6 +126,8 @@ struct rpc_xprt_ops {
 	int		(*reserve_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
 	void		(*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
 	void		(*alloc_slot)(struct rpc_xprt *xprt, struct rpc_task *task);
+	void		(*free_slot)(struct rpc_xprt *xprt,
+				     struct rpc_rqst *req);
 	void		(*rpcbind)(struct rpc_task *task);
 	void		(*set_port)(struct rpc_xprt *xprt, unsigned short port);
 	void		(*connect)(struct rpc_xprt *xprt, struct rpc_task *task);
@@ -324,10 +325,13 @@ struct xprt_class {
 struct rpc_xprt		*xprt_create_transport(struct xprt_create *args);
 void			xprt_connect(struct rpc_task *task);
 void			xprt_reserve(struct rpc_task *task);
+void			xprt_request_init(struct rpc_task *task);
 void			xprt_retry_reserve(struct rpc_task *task);
 int			xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 int			xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
+void			xprt_free_slot(struct rpc_xprt *xprt,
+				       struct rpc_rqst *req);
 void			xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
 bool			xprt_prepare_transmit(struct rpc_task *task);
 void			xprt_transmit(struct rpc_task *task);
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index 5859563e3c1f..86fc38ff0355 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
  *
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 094a676d92a7..53df203b8057 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -530,24 +530,54 @@ TRACE_EVENT(xprtrdma_post_send,
 
 TRACE_EVENT(xprtrdma_post_recv,
 	TP_PROTO(
-		const struct rpcrdma_rep *rep,
+		const struct ib_cqe *cqe
+	),
+
+	TP_ARGS(cqe),
+
+	TP_STRUCT__entry(
+		__field(const void *, cqe)
+	),
+
+	TP_fast_assign(
+		__entry->cqe = cqe;
+	),
+
+	TP_printk("cqe=%p",
+		__entry->cqe
+	)
+);
+
+TRACE_EVENT(xprtrdma_post_recvs,
+	TP_PROTO(
+		const struct rpcrdma_xprt *r_xprt,
+		unsigned int count,
 		int status
 	),
 
-	TP_ARGS(rep, status),
+	TP_ARGS(r_xprt, count, status),
 
 	TP_STRUCT__entry(
-		__field(const void *, rep)
+		__field(const void *, r_xprt)
+		__field(unsigned int, count)
 		__field(int, status)
+		__field(int, posted)
+		__string(addr, rpcrdma_addrstr(r_xprt))
+		__string(port, rpcrdma_portstr(r_xprt))
 	),
 
 	TP_fast_assign(
-		__entry->rep = rep;
+		__entry->r_xprt = r_xprt;
+		__entry->count = count;
 		__entry->status = status;
+		__entry->posted = r_xprt->rx_buf.rb_posted_receives;
+		__assign_str(addr, rpcrdma_addrstr(r_xprt));
+		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("rep=%p status=%d",
-		__entry->rep, __entry->status
+	TP_printk("peer=[%s]:%s r_xprt=%p: %u new recvs, %d active (rc %d)",
+		__get_str(addr), __get_str(port), __entry->r_xprt,
+		__entry->count, __entry->posted, __entry->status
 	)
 );
 
@@ -586,28 +616,32 @@ TRACE_EVENT(xprtrdma_wc_send,
 
 TRACE_EVENT(xprtrdma_wc_receive,
 	TP_PROTO(
-		const struct rpcrdma_rep *rep,
 		const struct ib_wc *wc
 	),
 
-	TP_ARGS(rep, wc),
+	TP_ARGS(wc),
 
 	TP_STRUCT__entry(
-		__field(const void *, rep)
-		__field(unsigned int, byte_len)
+		__field(const void *, cqe)
+		__field(u32, byte_len)
 		__field(unsigned int, status)
-		__field(unsigned int, vendor_err)
+		__field(u32, vendor_err)
 	),
 
 	TP_fast_assign(
-		__entry->rep = rep;
-		__entry->byte_len = wc->byte_len;
+		__entry->cqe = wc->wr_cqe;
 		__entry->status = wc->status;
-		__entry->vendor_err = __entry->status ? wc->vendor_err : 0;
+		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,
+	TP_printk("cqe=%p %u bytes: %s (%u/0x%x)",
+		__entry->cqe, __entry->byte_len,
 		rdma_show_wc_status(__entry->status),
 		__entry->status, __entry->vendor_err
 	)
@@ -618,6 +652,7 @@ DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li);
 DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_wake);
 
 DEFINE_MR_EVENT(xprtrdma_localinv);
+DEFINE_MR_EVENT(xprtrdma_dma_map);
 DEFINE_MR_EVENT(xprtrdma_dma_unmap);
 DEFINE_MR_EVENT(xprtrdma_remoteinv);
 DEFINE_MR_EVENT(xprtrdma_recover_mr);
@@ -801,7 +836,6 @@ TRACE_EVENT(xprtrdma_allocate,
 		__field(unsigned int, task_id)
 		__field(unsigned int, client_id)
 		__field(const void *, req)
-		__field(const void *, rep)
 		__field(size_t, callsize)
 		__field(size_t, rcvsize)
 	),
@@ -810,15 +844,13 @@ TRACE_EVENT(xprtrdma_allocate,
 		__entry->task_id = task->tk_pid;
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->req = req;
-		__entry->rep = req ? req->rl_reply : NULL;
 		__entry->callsize = task->tk_rqstp->rq_callsize;
 		__entry->rcvsize = task->tk_rqstp->rq_rcvsize;
 	),
 
-	TP_printk("task:%u@%u req=%p rep=%p (%zu, %zu)",
+	TP_printk("task:%u@%u req=%p (%zu, %zu)",
 		__entry->task_id, __entry->client_id,
-		__entry->req, __entry->rep,
-		__entry->callsize, __entry->rcvsize
+		__entry->req, __entry->callsize, __entry->rcvsize
 	)
 );
 
@@ -850,8 +882,6 @@ TRACE_EVENT(xprtrdma_rpc_done,
 	)
 );
 
-DEFINE_RXPRT_EVENT(xprtrdma_noreps);
-
 /**
  ** Callback events
  **/