Merge tag 'nfs-for-5.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS Client Updates from Anna Schumaker:
 "New Features:
   - Support for eager writes, and the write=eager and write=wait mount
     options

- Other Bugfixes and Cleanups:
   - Fix typos in some comments
   - Fix up fall-through warnings for Clang
   - Cleanups to the NFS readpage codepath
   - Remove FMR support in rpcrdma_convert_iovs()
   - Various other cleanups to xprtrdma
   - Fix xprtrdma pad optimization for servers that don't support
     RFC 8797
   - Improvements to rpcrdma tracepoints
   - Fix up nfs4_bitmask_adjust()
   - Optimize sparse writes past the end of files"

* tag 'nfs-for-5.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (27 commits)
  NFS: Support the '-owrite=' option in /proc/self/mounts and mountinfo
  NFS: Set the stable writes flag when initialising the super block
  NFS: Add mount options supporting eager writes
  NFS: Add support for eager writes
  NFS: 'flags' field should be unsigned in struct nfs_server
  NFS: Don't set NFS_INO_INVALID_XATTR if there is no xattr cache
  NFS: Always clear an invalid mapping when attempting a buffered write
  NFS: Optimise sparse writes past the end of file
  NFS: Fix documenting comment for nfs_revalidate_file_size()
  NFSv4: Fixes for nfs4_bitmask_adjust()
  xprtrdma: Clean up rpcrdma_prepare_readch()
  rpcrdma: Capture bytes received in Receive completion tracepoints
  xprtrdma: Pad optimization, revisited
  rpcrdma: Fix comments about reverse-direction operation
  xprtrdma: Refactor invocations of offset_in_page()
  xprtrdma: Simplify rpcrdma_convert_kvec() and frwr_map()
  xprtrdma: Remove FMR support in rpcrdma_convert_iovs()
  NFS: Add nfs_pageio_complete_read() and remove nfs_readpage_async()
  NFS: Call readpage_async_filler() from nfs_readpage_async()
  NFS: Refactor nfs_readpage() and nfs_readpage_async() to use nfs_readdesc
  ...

7 files changed, 43 insertions, 77 deletions

diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 8241f5a4a01c..09c000d490a1 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -478,6 +478,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode)
 		inode->i_fop = &simple_dir_operations;
 		inode->i_op = &simple_dir_inode_operations;
 		inc_nlink(inode);
+		break;
 	default:
 		break;
 	}
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 946edf2db646..a249837d6a55 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2015-2020, Oracle and/or its affiliates.
  *
- * Support for backward direction RPCs on RPC/RDMA.
+ * Support for reverse-direction RPCs on RPC/RDMA.
  */
 
 #include <linux/sunrpc/xprt.h>
@@ -208,7 +208,7 @@ create_req:
 }
 
 /**
- * rpcrdma_bc_receive_call - Handle a backward direction call
+ * rpcrdma_bc_receive_call - Handle a reverse-direction Call
  * @r_xprt: transport receiving the call
  * @rep: receive buffer containing the call
  *
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index baca49fe83af..766a1048a48a 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -306,20 +306,14 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	if (nsegs > ep->re_max_fr_depth)
 		nsegs = ep->re_max_fr_depth;
 	for (i = 0; i < nsegs;) {
-		if (seg->mr_page)
-			sg_set_page(&mr->mr_sg[i],
-				    seg->mr_page,
-				    seg->mr_len,
-				    offset_in_page(seg->mr_offset));
-		else
-			sg_set_buf(&mr->mr_sg[i], seg->mr_offset,
-				   seg->mr_len);
+		sg_set_page(&mr->mr_sg[i], seg->mr_page,
+			    seg->mr_len, seg->mr_offset);
 
 		++seg;
 		++i;
 		if (ep->re_mrtype == IB_MR_TYPE_SG_GAPS)
 			continue;
-		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+		if ((i < nsegs && seg->mr_offset) ||
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 8f5d0cb68360..292f066d006e 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -204,9 +204,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf)
 	return 0;
 }
 
-/* Split @vec on page boundaries into SGEs. FMR registers pages, not
- * a byte range. Other modes coalesce these SGEs into a single MR
- * when they can.
+/* Convert @vec to a single SGL element.
  *
  * Returns pointer to next available SGE, and bumps the total number
  * of SGEs consumed.
@@ -215,22 +213,11 @@ static struct rpcrdma_mr_seg *
 rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
 		     unsigned int *n)
 {
-	u32 remaining, page_offset;
-	char *base;
-
-	base = vec->iov_base;
-	page_offset = offset_in_page(base);
-	remaining = vec->iov_len;
-	while (remaining) {
-		seg->mr_page = NULL;
-		seg->mr_offset = base;
-		seg->mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining);
-		remaining -= seg->mr_len;
-		base += seg->mr_len;
-		++seg;
-		++(*n);
-		page_offset = 0;
-	}
+	seg->mr_page = virt_to_page(vec->iov_base);
+	seg->mr_offset = offset_in_page(vec->iov_base);
+	seg->mr_len = vec->iov_len;
+	++seg;
+	++(*n);
 	return seg;
 }
 
@@ -259,7 +246,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 	page_base = offset_in_page(xdrbuf->page_base);
 	while (len) {
 		seg->mr_page = *ppages;
-		seg->mr_offset = (char *)page_base;
+		seg->mr_offset = page_base;
 		seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len);
 		len -= seg->mr_len;
 		++ppages;
@@ -268,10 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 		page_base = 0;
 	}
 
-	/* When encoding a Read chunk, the tail iovec contains an
-	 * XDR pad and may be omitted.
-	 */
-	if (type == rpcrdma_readch && r_xprt->rx_ep->re_implicit_roundup)
+	if (type == rpcrdma_readch)
 		goto out;
 
 	/* When encoding a Write chunk, some servers need to see an
@@ -283,7 +267,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 		goto out;
 
 	if (xdrbuf->tail[0].iov_len)
-		seg = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n);
+		rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n);
 
 out:
 	if (unlikely(n > RPCRDMA_MAX_SEGS))
@@ -644,9 +628,8 @@ out_mapping_err:
 	return false;
 }
 
-/* The tail iovec may include an XDR pad for the page list,
- * as well as additional content, and may not reside in the
- * same page as the head iovec.
+/* The tail iovec might not reside in the same page as the
+ * head iovec.
  */
 static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req,
 				     struct xdr_buf *xdr,
@@ -764,27 +747,19 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt,
 				   struct rpcrdma_req *req,
 				   struct xdr_buf *xdr)
 {
+	struct kvec *tail = &xdr->tail[0];
+
 	if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len))
 		return false;
 
-	/* If there is a Read chunk, the page list is being handled
+	/* If there is a Read chunk, the page list is handled
 	 * via explicit RDMA, and thus is skipped here.
 	 */
 
-	/* Do not include the tail if it is only an XDR pad */
-	if (xdr->tail[0].iov_len > 3) {
-		unsigned int page_base, len;
-
-		/* If the content in the page list is an odd length,
-		 * xdr_write_pages() adds a pad at the beginning of
-		 * the tail iovec. Force the tail's non-pad content to
-		 * land at the next XDR position in the Send message.
-		 */
-		page_base = offset_in_page(xdr->tail[0].iov_base);
-		len = xdr->tail[0].iov_len;
-		page_base += len & 3;
-		len -= len & 3;
-		if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len))
+	if (tail->iov_len) {
+		if (!rpcrdma_prepare_tail_iov(req, xdr,
+					      offset_in_page(tail->iov_base),
+					      tail->iov_len))
 			return false;
 		kref_get(&req->rl_kref);
 	}
@@ -1164,14 +1139,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 	 */
 	p = xdr_inline_decode(xdr, 3 * sizeof(*p));
 	if (unlikely(!p))
-		goto out_short;
+		return true;
 
 	rpcrdma_bc_receive_call(r_xprt, rep);
 	return true;
-
-out_short:
-	pr_warn("RPC/RDMA short backward direction call\n");
-	return true;
 }
 #else	/* CONFIG_SUNRPC_BACKCHANNEL */
 {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 63f8be974df2..4a1edbb4028e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2015-2018 Oracle.  All rights reserved.
  *
- * Support for backward direction RPCs on RPC/RDMA (server-side).
+ * Support for reverse-direction RPCs on RPC/RDMA (server-side).
  */
 
 #include <linux/sunrpc/svc_rdma.h>
@@ -59,7 +59,7 @@ out_unlock:
 	spin_unlock(&xprt->queue_lock);
 }
 
-/* Send a backwards direction RPC call.
+/* Send a reverse-direction RPC Call.
  *
  * Caller holds the connection's mutex and has already marshaled
  * the RPC/RDMA request.
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 94b28657aeeb..fe3be985e239 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -98,9 +98,9 @@ struct rpcrdma_ep {
 	atomic_t		re_completion_ids;
 };
 
-/* Pre-allocate extra Work Requests for handling backward receives
- * and sends. This is a fixed value because the Work Queues are
- * allocated when the forward channel is set up, long before the
+/* Pre-allocate extra Work Requests for handling reverse-direction
+ * Receives and Sends. This is a fixed value because the Work Queues
+ * are allocated when the forward channel is set up, long before the
  * backchannel is provisioned. This value is two times
  * NFS4_DEF_CB_SLOT_TABLE_SIZE.
  */
@@ -283,10 +283,11 @@ enum {
 				  RPCRDMA_MAX_IOV_SEGS,
 };
 
-struct rpcrdma_mr_seg {		/* chunk descriptors */
-	u32		mr_len;		/* length of chunk or segment */
-	struct page	*mr_page;	/* owning page, if any */
-	char		*mr_offset;	/* kva if no page, else offset */
+/* Arguments for DMA mapping and registration */
+struct rpcrdma_mr_seg {
+	u32		mr_len;		/* length of segment */
+	struct page	*mr_page;	/* underlying struct page */
+	u64		mr_offset;	/* IN: page offset, OUT: iova */
 };
 
 /* The Send SGE array is provisioned to send a maximum size
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c56a66cdf4ac..e35760f238a4 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -829,7 +829,7 @@ xs_stream_record_marker(struct xdr_buf *xdr)
  *   EAGAIN:	The socket was blocked, please call again later to
  *		complete the request
  * ENOTCONN:	Caller needs to invoke connect logic then call again
- *    other:	Some other error occured, the request was not sent
+ *    other:	Some other error occurred, the request was not sent
  */
 static int xs_local_send_request(struct rpc_rqst *req)
 {
@@ -1665,7 +1665,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
 	 * This ensures that we can continue to establish TCP
 	 * connections even when all local ephemeral ports are already
 	 * a part of some TCP connection.  This makes no difference
-	 * for UDP sockets, but also doens't harm them.
+	 * for UDP sockets, but also doesn't harm them.
 	 *
 	 * If we're asking for any reserved port (i.e. port == 0 &&
 	 * transport->xprt.resvport == 1) xs_get_srcport above will
@@ -1875,6 +1875,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 		xprt->stat.connect_time += (long)jiffies -
 					   xprt->stat.connect_start;
 		xprt_set_connected(xprt);
+		break;
 	case -ENOBUFS:
 		break;
 	case -ENOENT:
@@ -2276,10 +2277,8 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -EHOSTUNREACH:
 	case -EADDRINUSE:
 	case -ENOBUFS:
-		/*
-		 * xs_tcp_force_close() wakes tasks with -EIO.
-		 * We need to wake them first to ensure the
-		 * correct error code.
+		/* xs_tcp_force_close() wakes tasks with a fixed error code.
+		 * We need to wake them first to ensure the correct error code.
 		 */
 		xprt_wake_pending_tasks(xprt, status);
 		xs_tcp_force_close(xprt);
@@ -2380,7 +2379,7 @@ static void xs_error_handle(struct work_struct *work)
 }
 
 /**
- * xs_local_print_stats - display AF_LOCAL socket-specifc stats
+ * xs_local_print_stats - display AF_LOCAL socket-specific stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
  *
@@ -2409,7 +2408,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 }
 
 /**
- * xs_udp_print_stats - display UDP socket-specifc stats
+ * xs_udp_print_stats - display UDP socket-specific stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
  *
@@ -2433,7 +2432,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 }
 
 /**
- * xs_tcp_print_stats - display TCP socket-specifc stats
+ * xs_tcp_print_stats - display TCP socket-specific stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
  *