Merge tag 'nfs-for-5.16-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Features:
   - NFSv4.1 can always retrieve and cache the ACCESS mode on OPEN
   - Optimisations for READDIR and the 'ls -l' style workload
   - Further replacements of dprintk() with tracepoints and other
     tracing improvements
   - Ensure we re-probe NFSv4 server capabilities when the user does a
     "mount -o remount"

  Bugfixes:
   - Fix an Oops in pnfs_mark_request_commit()
   - Fix up deadlocks in the commit code
   - Fix regressions in NFSv2/v3 attribute revalidation due to the
     change_attr_type optimisations
   - Fix some dentry verifier races
   - Fix some missing dentry verifier settings
   - Fix a performance regression in nfs_set_open_stateid_locked()
   - SUNRPC was sending multiple SYN calls when re-establishing a TCP
     connection.
   - Fix multiple NFSv4 issues due to missing sanity checking of server
     return values
   - Fix a potential Oops when FREE_STATEID races with an unmount

  Cleanups:
   - Clean up the labelled NFS code
   - Remove unused header <linux/pnfs_osd_xdr.h>"

* tag 'nfs-for-5.16-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (84 commits)
  NFSv4: Sanity check the parameters in nfs41_update_target_slotid()
  NFS: Remove the nfs4_label argument from decode_getattr_*() functions
  NFS: Remove the nfs4_label argument from nfs_setsecurity
  NFS: Remove the nfs4_label argument from nfs_fhget()
  NFS: Remove the nfs4_label argument from nfs_add_or_obtain()
  NFS: Remove the nfs4_label argument from nfs_instantiate()
  NFS: Remove the nfs4_label from the nfs_setattrres
  NFS: Remove the nfs4_label from the nfs4_getattr_res
  NFS: Remove the f_label from the nfs4_opendata and nfs_openres
  NFS: Remove the nfs4_label from the nfs4_lookupp_res struct
  NFS: Remove the label from the nfs4_lookup_res struct
  NFS: Remove the nfs4_label from the nfs4_link_res struct
  NFS: Remove the nfs4_label from the nfs4_create_res struct
  NFS: Remove the nfs4_label from the nfs_entry struct
  NFS: Create a new nfs_alloc_fattr_with_label() function
  NFS: Always initialise fattr->label in nfs_fattr_alloc()
  NFSv4.2: alloc_file_pseudo() takes an open flag, not an f_mode
  NFS: Don't allocate nfs_fattr on the stack in __nfs42_ssc_open()
  NFSv4: Remove unnecessary 'minor version' check
  NFSv4: Fix potential Oops in decode_op_map()
  ...

4 files changed, 62 insertions, 18 deletions

diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index f700b34a5bfd..ff699307e820 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -515,8 +515,8 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * a single ib_post_send() call.
 	 */
 	prev = &first;
-	while ((mr = rpcrdma_mr_pop(&req->rl_registered))) {
-
+	mr = rpcrdma_mr_pop(&req->rl_registered);
+	do {
 		trace_xprtrdma_mr_localinv(mr);
 		r_xprt->rx_stats.local_inv_needed++;
 
@@ -533,7 +533,8 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 
 		*prev = last;
 		prev = &last->next;
-	}
+	} while ((mr = rpcrdma_mr_pop(&req->rl_registered)));
+
 	mr = container_of(last, struct rpcrdma_mr, mr_invwr);
 
 	/* Strong send queue ordering guarantees that when the
@@ -617,8 +618,8 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * a single ib_post_send() call.
 	 */
 	prev = &first;
-	while ((mr = rpcrdma_mr_pop(&req->rl_registered))) {
-
+	mr = rpcrdma_mr_pop(&req->rl_registered);
+	do {
 		trace_xprtrdma_mr_localinv(mr);
 		r_xprt->rx_stats.local_inv_needed++;
 
@@ -635,7 +636,7 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 
 		*prev = last;
 		prev = &last->next;
-	}
+	} while ((mr = rpcrdma_mr_pop(&req->rl_registered)));
 
 	/* Strong send queue ordering guarantees that when the
 	 * last WR in the chain completes, all WRs in the chain
@@ -666,3 +667,38 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 */
 	rpcrdma_force_disconnect(ep);
 }
+
+/**
+ * frwr_wp_create - Create an MR for padding Write chunks
+ * @r_xprt: transport resources to use
+ *
+ * Return 0 on success, negative errno on failure.
+ */
+int frwr_wp_create(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_ep *ep = r_xprt->rx_ep;
+	struct rpcrdma_mr_seg seg;
+	struct rpcrdma_mr *mr;
+
+	mr = rpcrdma_mr_get(r_xprt);
+	if (!mr)
+		return -EAGAIN;
+	mr->mr_req = NULL;
+	ep->re_write_pad_mr = mr;
+
+	seg.mr_len = XDR_UNIT;
+	seg.mr_page = virt_to_page(ep->re_write_pad);
+	seg.mr_offset = offset_in_page(ep->re_write_pad);
+	if (IS_ERR(frwr_map(r_xprt, &seg, 1, true, xdr_zero, mr)))
+		return -EIO;
+	trace_xprtrdma_mr_fastreg(mr);
+
+	mr->mr_cqe.done = frwr_wc_fastreg;
+	mr->mr_regwr.wr.next = NULL;
+	mr->mr_regwr.wr.wr_cqe = &mr->mr_cqe;
+	mr->mr_regwr.wr.num_sge = 0;
+	mr->mr_regwr.wr.opcode = IB_WR_REG_MR;
+	mr->mr_regwr.wr.send_flags = 0;
+
+	return ib_post_send(ep->re_id->qp, &mr->mr_regwr.wr, NULL);
+}
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c335c1361564..8035a983c8ce 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -255,15 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 		page_base = 0;
 	}
 
-	if (type == rpcrdma_readch)
-		goto out;
-
-	/* 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 && r_xprt->rx_ep->re_implicit_roundup)
+	if (type == rpcrdma_readch || type == rpcrdma_writech)
 		goto out;
 
 	if (xdrbuf->tail[0].iov_len)
@@ -405,6 +397,7 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt,
 				     enum rpcrdma_chunktype wtype)
 {
 	struct xdr_stream *xdr = &req->rl_stream;
+	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	struct rpcrdma_mr_seg *seg;
 	struct rpcrdma_mr *mr;
 	int nsegs, nchunks;
@@ -443,6 +436,18 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt,
 		nsegs -= mr->mr_nents;
 	} while (nsegs);
 
+	if (xdr_pad_size(rqst->rq_rcv_buf.page_len)) {
+		if (encode_rdma_segment(xdr, ep->re_write_pad_mr) < 0)
+			return -EMSGSIZE;
+
+		trace_xprtrdma_chunk_wp(rqst->rq_task, ep->re_write_pad_mr,
+					nsegs);
+		r_xprt->rx_stats.write_chunk_count++;
+		r_xprt->rx_stats.total_rdma_request += mr->mr_length;
+		nchunks++;
+		nsegs -= mr->mr_nents;
+	}
+
 	/* Update count of segments in this Write chunk */
 	*segcount = cpu_to_be32(nchunks);
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index aaec3c9be8db..3d3673ba9e1e 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -205,14 +205,12 @@ static void rpcrdma_update_cm_private(struct rpcrdma_ep *ep,
 	unsigned int rsize, wsize;
 
 	/* Default settings for RPC-over-RDMA Version One */
-	ep->re_implicit_roundup = xprt_rdma_pad_optimize;
 	rsize = RPCRDMA_V1_DEF_INLINE_SIZE;
 	wsize = RPCRDMA_V1_DEF_INLINE_SIZE;
 
 	if (pmsg &&
 	    pmsg->cp_magic == rpcrdma_cmp_magic &&
 	    pmsg->cp_version == RPCRDMA_CMP_VERSION) {
-		ep->re_implicit_roundup = true;
 		rsize = rpcrdma_decode_buffer_size(pmsg->cp_send_size);
 		wsize = rpcrdma_decode_buffer_size(pmsg->cp_recv_size);
 	}
@@ -551,6 +549,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt)
 		goto out;
 	}
 	rpcrdma_mrs_create(r_xprt);
+	frwr_wp_create(r_xprt);
 
 out:
 	trace_xprtrdma_connect(r_xprt, rc);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index d91f54eae00b..c79f92eeda76 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -68,13 +68,14 @@
 /*
  * RDMA Endpoint -- connection endpoint details
  */
+struct rpcrdma_mr;
 struct rpcrdma_ep {
 	struct kref		re_kref;
 	struct rdma_cm_id 	*re_id;
 	struct ib_pd		*re_pd;
 	unsigned int		re_max_rdma_segs;
 	unsigned int		re_max_fr_depth;
-	bool			re_implicit_roundup;
+	struct rpcrdma_mr	*re_write_pad_mr;
 	enum ib_mr_type		re_mrtype;
 	struct completion	re_done;
 	unsigned int		re_send_count;
@@ -97,6 +98,8 @@ struct rpcrdma_ep {
 	unsigned int		re_inline_recv;	/* negotiated */
 
 	atomic_t		re_completion_ids;
+
+	char			re_write_pad[XDR_UNIT];
 };
 
 /* Pre-allocate extra Work Requests for handling reverse-direction
@@ -535,6 +538,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
 void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs);
 void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
 void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
+int frwr_wp_create(struct rpcrdma_xprt *r_xprt);
 
 /*
  * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c