Merge tag 'nfs-for-4.11-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Highlights include:

  Stable bugfixes:
   - NFSv4: Fix memory and state leak in _nfs4_open_and_get_state
   - xprtrdma: Fix Read chunk padding
   - xprtrdma: Per-connection pad optimization
   - xprtrdma: Disable pad optimization by default
   - xprtrdma: Reduce required number of send SGEs
   - nlm: Ensure callback code also checks that the files match
   - pNFS/flexfiles: If the layout is invalid, it must be updated before
     retrying
   - NFSv4: Fix reboot recovery in copy offload
   - Revert "NFSv4.1: Handle NFS4ERR_BADSESSION/NFS4ERR_DEADSESSION
     replies to OP_SEQUENCE"
   - NFSv4: fix getacl head length estimation
   - NFSv4: fix getacl ERANGE for sum ACL buffer sizes

  Features:
   - Add and use dprintk_cont macros
   - Various cleanups to NFS v4.x to reduce code duplication and
     complexity
   - Remove unused cr_magic related code
   - Improvements to sunrpc "read from buffer" code
   - Clean up sunrpc timeout code and allow changing TCP timeout
     parameters
   - Remove duplicate mw_list management code in xprtrdma
   - Add generic functions for encoding and decoding xdr streams

  Bugfixes:
   - Clean up nfs_show_mountd_netid
   - Make layoutreturn_ops static and use NULL instead of 0 to fix
     sparse warnings
   - Properly handle -ERESTARTSYS in nfs_rename()
   - Check if register_shrinker() failed during rpcauth_init()
   - Properly clean up procfs/pipefs entries
   - Various NFS over RDMA related fixes
   - Silence unititialized variable warning in sunrpc"

* tag 'nfs-for-4.11-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (64 commits)
  NFSv4: fix getacl ERANGE for some ACL buffer sizes
  NFSv4: fix getacl head length estimation
  Revert "NFSv4.1: Handle NFS4ERR_BADSESSION/NFS4ERR_DEADSESSION replies to OP_SEQUENCE"
  NFSv4: Fix reboot recovery in copy offload
  pNFS/flexfiles: If the layout is invalid, it must be updated before retrying
  NFSv4: Clean up owner/group attribute decode
  SUNRPC: Add a helper function xdr_stream_decode_string_dup()
  NFSv4: Remove bogus "struct nfs_client" argument from decode_ace()
  NFSv4: Fix the underestimation of delegation XDR space reservation
  NFSv4: Replace callback string decode function with a generic
  NFSv4: Replace the open coded decode_opaque_inline() with the new generic
  NFSv4: Replace ad-hoc xdr encode/decode helpers with xdr_stream_* generics
  SUNRPC: Add generic helpers for xdr_stream encode/decode
  sunrpc: silence uninitialized variable warning
  nlm: Ensure callback code also checks that the files match
  sunrpc: Allow xprt->ops->timer method to sleep
  xprtrdma: Refactor management of mw_list field
  xprtrdma: Handle stale connection rejection
  xprtrdma: Properly recover FRWRs with in-flight FASTREG WRs
  xprtrdma: Shrink send SGEs array
  ...

1 files changed, 51 insertions, 31 deletions

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c52e0f2ffe52..a044be2d6ad7 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -125,14 +125,34 @@ void rpcrdma_set_max_header_sizes(struct rpcrdma_xprt *r_xprt)
 /* The client can send a request inline as long as the RPCRDMA header
  * plus the RPC call fit under the transport's inline limit. If the
  * combined call message size exceeds that limit, the client must use
- * the read chunk list for this operation.
+ * a Read chunk for this operation.
+ *
+ * A Read chunk is also required if sending the RPC call inline would
+ * exceed this device's max_sge limit.
  */
 static bool rpcrdma_args_inline(struct rpcrdma_xprt *r_xprt,
 				struct rpc_rqst *rqst)
 {
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct xdr_buf *xdr = &rqst->rq_snd_buf;
+	unsigned int count, remaining, offset;
+
+	if (xdr->len > r_xprt->rx_ia.ri_max_inline_write)
+		return false;
+
+	if (xdr->page_len) {
+		remaining = xdr->page_len;
+		offset = xdr->page_base & ~PAGE_MASK;
+		count = 0;
+		while (remaining) {
+			remaining -= min_t(unsigned int,
+					   PAGE_SIZE - offset, remaining);
+			offset = 0;
+			if (++count > r_xprt->rx_ia.ri_max_send_sges)
+				return false;
+		}
+	}
 
-	return rqst->rq_snd_buf.len <= ia->ri_max_inline_write;
+	return true;
 }
 
 /* The client can't know how large the actual reply will be. Thus it
@@ -186,9 +206,9 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, int n)
  */
 
 static int
-rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
-	enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg,
-	bool reminv_expected)
+rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
+		     unsigned int pos, enum rpcrdma_chunktype type,
+		     struct rpcrdma_mr_seg *seg)
 {
 	int len, n, p, page_base;
 	struct page **ppages;
@@ -226,22 +246,21 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	if (len && n == RPCRDMA_MAX_SEGS)
 		goto out_overflow;
 
-	/* When encoding the read list, the tail is always sent inline */
-	if (type == rpcrdma_readch)
+	/* When encoding a Read chunk, the tail iovec contains an
+	 * XDR pad and may be omitted.
+	 */
+	if (type == rpcrdma_readch && r_xprt->rx_ia.ri_implicit_roundup)
 		return n;
 
-	/* When encoding the Write list, some servers need to see an extra
-	 * segment for odd-length Write chunks. The upper layer provides
-	 * space in the tail iovec for this purpose.
+	/* When encoding a Write chunk, some servers need to see an
+	 * extra segment for non-XDR-aligned Write chunks. The upper
+	 * layer provides space in the tail iovec that may be used
+	 * for this purpose.
 	 */
-	if (type == rpcrdma_writech && reminv_expected)
+	if (type == rpcrdma_writech && r_xprt->rx_ia.ri_implicit_roundup)
 		return n;
 
 	if (xdrbuf->tail[0].iov_len) {
-		/* the rpcrdma protocol allows us to omit any trailing
-		 * xdr pad bytes, saving the server an RDMA operation. */
-		if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
-			return n;
 		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n);
 		if (n == RPCRDMA_MAX_SEGS)
 			goto out_overflow;
@@ -293,7 +312,8 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 	if (rtype == rpcrdma_areadch)
 		pos = 0;
 	seg = req->rl_segments;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg, false);
+	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_snd_buf, pos,
+				     rtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -302,7 +322,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 						 false, &mw);
 		if (n < 0)
 			return ERR_PTR(n);
-		list_add(&mw->mw_list, &req->rl_registered);
+		rpcrdma_push_mw(mw, &req->rl_registered);
 
 		*iptr++ = xdr_one;	/* item present */
 
@@ -355,10 +375,9 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	}
 
 	seg = req->rl_segments;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf,
+	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf,
 				     rqst->rq_rcv_buf.head[0].iov_len,
-				     wtype, seg,
-				     r_xprt->rx_ia.ri_reminv_expected);
+				     wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -371,7 +390,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 						 true, &mw);
 		if (n < 0)
 			return ERR_PTR(n);
-		list_add(&mw->mw_list, &req->rl_registered);
+		rpcrdma_push_mw(mw, &req->rl_registered);
 
 		iptr = xdr_encode_rdma_segment(iptr, mw);
 
@@ -423,8 +442,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 	}
 
 	seg = req->rl_segments;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg,
-				     r_xprt->rx_ia.ri_reminv_expected);
+	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -437,7 +455,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 						 true, &mw);
 		if (n < 0)
 			return ERR_PTR(n);
-		list_add(&mw->mw_list, &req->rl_registered);
+		rpcrdma_push_mw(mw, &req->rl_registered);
 
 		iptr = xdr_encode_rdma_segment(iptr, mw);
 
@@ -741,13 +759,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	iptr = headerp->rm_body.rm_chunks;
 	iptr = rpcrdma_encode_read_list(r_xprt, req, rqst, iptr, rtype);
 	if (IS_ERR(iptr))
-		goto out_unmap;
+		goto out_err;
 	iptr = rpcrdma_encode_write_list(r_xprt, req, rqst, iptr, wtype);
 	if (IS_ERR(iptr))
-		goto out_unmap;
+		goto out_err;
 	iptr = rpcrdma_encode_reply_chunk(r_xprt, req, rqst, iptr, wtype);
 	if (IS_ERR(iptr))
-		goto out_unmap;
+		goto out_err;
 	hdrlen = (unsigned char *)iptr - (unsigned char *)headerp;
 
 	dprintk("RPC: %5u %s: %s/%s: hdrlen %zd rpclen %zd\n",
@@ -758,12 +776,14 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	if (!rpcrdma_prepare_send_sges(&r_xprt->rx_ia, req, hdrlen,
 				       &rqst->rq_snd_buf, rtype)) {
 		iptr = ERR_PTR(-EIO);
-		goto out_unmap;
+		goto out_err;
 	}
 	return 0;
 
-out_unmap:
-	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
+out_err:
+	pr_err("rpcrdma: rpcrdma_marshal_req failed, status %ld\n",
+	       PTR_ERR(iptr));
+	r_xprt->rx_stats.failed_marshal_count++;
 	return PTR_ERR(iptr);
 }