Merge tag 'nfsd-4.10' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "The one new feature is support for a new NFSv4.2 mode_umask attribute
  that makes ACL inheritance a little more useful in environments that
  default to restrictive umasks. Requires client-side support, also on
  its way for 4.10.

  Other than that, miscellaneous smaller fixes and cleanup, especially
  to the server rdma code"

[ The client side of the umask attribute was merged yesterday ]

* tag 'nfsd-4.10' of git://linux-nfs.org/~bfields/linux:
  nfsd: add support for the umask attribute
  sunrpc: use DEFINE_SPINLOCK()
  svcrdma: Further clean-up of svc_rdma_get_inv_rkey()
  svcrdma: Break up dprintk format in svc_rdma_accept()
  svcrdma: Remove unused variable in rdma_copy_tail()
  svcrdma: Remove unused variables in xprt_rdma_bc_allocate()
  svcrdma: Remove svc_rdma_op_ctxt::wc_status
  svcrdma: Remove DMA map accounting
  svcrdma: Remove BH-disabled spin locking in svc_rdma_send()
  svcrdma: Renovate sendto chunk list parsing
  svcauth_gss: Close connection when dropping an incoming message
  svcrdma: Clear xpt_bc_xps in xprt_setup_rdma_bc() error exit arm
  nfsd: constify reply_cache_stats_operations structure
  nfsd: update workqueue creation
  sunrpc: GFP_KERNEL should be GFP_NOFS in crypto code
  nfsd: catch errors in decode_fattr earlier
  nfsd: clean up supported attribute handling
  nfsd: fix error handling for clients that fail to return the layout
  nfsd: more robust allocation failure handling in nfsd_reply_cache_init

4 files changed, 83 insertions, 153 deletions

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 20027f8de129..288e35c2d8f4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -164,13 +164,9 @@ static int
 xprt_rdma_bc_allocate(struct rpc_task *task)
 {
 	struct rpc_rqst *rqst = task->tk_rqstp;
-	struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt;
 	size_t size = rqst->rq_callsize;
-	struct svcxprt_rdma *rdma;
 	struct page *page;
 
-	rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt);
-
 	if (size > PAGE_SIZE) {
 		WARN_ONCE(1, "svcrdma: large bc buffer request (size %zu)\n",
 			  size);
@@ -359,6 +355,7 @@ xprt_setup_rdma_bc(struct xprt_create *args)
 out_fail:
 	xprt_rdma_free_addresses(xprt);
 	args->bc_xprt->xpt_bc_xprt = NULL;
+	args->bc_xprt->xpt_bc_xps = NULL;
 	xprt_put(xprt);
 	xprt_free(xprt);
 	return ERR_PTR(-EINVAL);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index ad1df979b3f0..57d35fbb1c28 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -279,7 +279,6 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 		       frmr->sg);
 		return -ENOMEM;
 	}
-	atomic_inc(&xprt->sc_dma_used);
 
 	n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, NULL, PAGE_SIZE);
 	if (unlikely(n != frmr->sg_nents)) {
@@ -374,9 +373,7 @@ rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head,
 	       u32 position, u32 byte_count, u32 page_offset, int page_no)
 {
 	char *srcp, *destp;
-	int ret;
 
-	ret = 0;
 	srcp = head->arg.head[0].iov_base + position;
 	byte_count = head->arg.head[0].iov_len - position;
 	if (byte_count > PAGE_SIZE) {
@@ -415,6 +412,20 @@ done:
 	return 1;
 }
 
+/* Returns the address of the first read chunk or <nul> if no read chunk
+ * is present
+ */
+static struct rpcrdma_read_chunk *
+svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp)
+{
+	struct rpcrdma_read_chunk *ch =
+		(struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
+
+	if (ch->rc_discrim == xdr_zero)
+		return NULL;
+	return ch;
+}
+
 static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			    struct rpcrdma_msg *rmsgp,
 			    struct svc_rqst *rqstp,
@@ -627,8 +638,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 			goto defer;
 		goto out;
 	}
-	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n",
-		ctxt, rdma_xprt, rqstp, ctxt->wc_status);
+	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p\n",
+		ctxt, rdma_xprt, rqstp);
 	atomic_inc(&rdma_stat_recv);
 
 	/* Build up the XDR from the receive buffers. */
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index f5a91edcd233..ad4d286a83c5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -153,76 +153,35 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
 	return dma_addr;
 }
 
-/* Returns the address of the first read chunk or <nul> if no read chunk
- * is present
+/* Parse the RPC Call's transport header.
  */
-struct rpcrdma_read_chunk *
-svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp)
+static void svc_rdma_get_write_arrays(struct rpcrdma_msg *rmsgp,
+				      struct rpcrdma_write_array **write,
+				      struct rpcrdma_write_array **reply)
 {
-	struct rpcrdma_read_chunk *ch =
-		(struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
+	__be32 *p;
 
-	if (ch->rc_discrim == xdr_zero)
-		return NULL;
-	return ch;
-}
+	p = (__be32 *)&rmsgp->rm_body.rm_chunks[0];
 
-/* Returns the address of the first read write array element or <nul>
- * if no write array list is present
- */
-static struct rpcrdma_write_array *
-svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp)
-{
-	if (rmsgp->rm_body.rm_chunks[0] != xdr_zero ||
-	    rmsgp->rm_body.rm_chunks[1] == xdr_zero)
-		return NULL;
-	return (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[1];
-}
+	/* Read list */
+	while (*p++ != xdr_zero)
+		p += 5;
 
-/* Returns the address of the first reply array element or <nul> if no
- * reply array is present
- */
-static struct rpcrdma_write_array *
-svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp,
-			 struct rpcrdma_write_array *wr_ary)
-{
-	struct rpcrdma_read_chunk *rch;
-	struct rpcrdma_write_array *rp_ary;
-
-	/* XXX: Need to fix when reply chunk may occur with read list
-	 *	and/or write list.
-	 */
-	if (rmsgp->rm_body.rm_chunks[0] != xdr_zero ||
-	    rmsgp->rm_body.rm_chunks[1] != xdr_zero)
-		return NULL;
-
-	rch = svc_rdma_get_read_chunk(rmsgp);
-	if (rch) {
-		while (rch->rc_discrim != xdr_zero)
-			rch++;
-
-		/* The reply chunk follows an empty write array located
-		 * at 'rc_position' here. The reply array is at rc_target.
-		 */
-		rp_ary = (struct rpcrdma_write_array *)&rch->rc_target;
-		goto found_it;
-	}
-
-	if (wr_ary) {
-		int chunk = be32_to_cpu(wr_ary->wc_nchunks);
-
-		rp_ary = (struct rpcrdma_write_array *)
-			 &wr_ary->wc_array[chunk].wc_target.rs_length;
-		goto found_it;
+	/* Write list */
+	if (*p != xdr_zero) {
+		*write = (struct rpcrdma_write_array *)p;
+		while (*p++ != xdr_zero)
+			p += 1 + be32_to_cpu(*p) * 4;
+	} else {
+		*write = NULL;
+		p++;
 	}
 
-	/* No read list, no write list */
-	rp_ary = (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[2];
-
- found_it:
-	if (rp_ary->wc_discrim == xdr_zero)
-		return NULL;
-	return rp_ary;
+	/* Reply chunk */
+	if (*p != xdr_zero)
+		*reply = (struct rpcrdma_write_array *)p;
+	else
+		*reply = NULL;
 }
 
 /* RPC-over-RDMA Version One private extension: Remote Invalidation.
@@ -240,31 +199,22 @@ static u32 svc_rdma_get_inv_rkey(struct rpcrdma_msg *rdma_argp,
 {
 	struct rpcrdma_read_chunk *rd_ary;
 	struct rpcrdma_segment *arg_ch;
-	u32 inv_rkey;
 
-	inv_rkey = 0;
-
-	rd_ary = svc_rdma_get_read_chunk(rdma_argp);
-	if (rd_ary) {
-		inv_rkey = be32_to_cpu(rd_ary->rc_target.rs_handle);
-		goto out;
-	}
+	rd_ary = (struct rpcrdma_read_chunk *)&rdma_argp->rm_body.rm_chunks[0];
+	if (rd_ary->rc_discrim != xdr_zero)
+		return be32_to_cpu(rd_ary->rc_target.rs_handle);
 
 	if (wr_ary && be32_to_cpu(wr_ary->wc_nchunks)) {
 		arg_ch = &wr_ary->wc_array[0].wc_target;
-		inv_rkey = be32_to_cpu(arg_ch->rs_handle);
-		goto out;
+		return be32_to_cpu(arg_ch->rs_handle);
 	}
 
 	if (rp_ary && be32_to_cpu(rp_ary->wc_nchunks)) {
 		arg_ch = &rp_ary->wc_array[0].wc_target;
-		inv_rkey = be32_to_cpu(arg_ch->rs_handle);
-		goto out;
+		return be32_to_cpu(arg_ch->rs_handle);
 	}
 
-out:
-	dprintk("svcrdma: Send With Invalidate rkey=%08x\n", inv_rkey);
-	return inv_rkey;
+	return 0;
 }
 
 /* Assumptions:
@@ -622,8 +572,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 	 * places this at the start of page 0.
 	 */
 	rdma_argp = page_address(rqstp->rq_pages[0]);
-	wr_ary = svc_rdma_get_write_array(rdma_argp);
-	rp_ary = svc_rdma_get_reply_array(rdma_argp, wr_ary);
+	svc_rdma_get_write_arrays(rdma_argp, &wr_ary, &rp_ary);
 
 	inv_rkey = 0;
 	if (rdma->sc_snd_w_inv)
@@ -636,7 +585,12 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 		goto err0;
 	inline_bytes = rqstp->rq_res.len;
 
-	/* Create the RDMA response header */
+	/* Create the RDMA response header. xprt->xpt_mutex,
+	 * acquired in svc_send(), serializes RPC replies. The
+	 * code path below that inserts the credit grant value
+	 * into each transport header runs only inside this
+	 * critical section.
+	 */
 	ret = -ENOMEM;
 	res_page = alloc_page(GFP_KERNEL);
 	if (!res_page)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 1334de2715c2..ca2799af05a6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -41,6 +41,7 @@
  */
 
 #include <linux/sunrpc/svc_xprt.h>
+#include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/interrupt.h>
@@ -226,25 +227,22 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt)
 	struct svcxprt_rdma *xprt = ctxt->xprt;
 	struct ib_device *device = xprt->sc_cm_id->device;
 	u32 lkey = xprt->sc_pd->local_dma_lkey;
-	unsigned int i, count;
+	unsigned int i;
 
-	for (count = 0, i = 0; i < ctxt->mapped_sges; i++) {
+	for (i = 0; i < ctxt->mapped_sges; i++) {
 		/*
 		 * Unmap the DMA addr in the SGE if the lkey matches
 		 * the local_dma_lkey, otherwise, ignore it since it is
 		 * an FRMR lkey and will be unmapped later when the
 		 * last WR that uses it completes.
 		 */
-		if (ctxt->sge[i].lkey == lkey) {
-			count++;
+		if (ctxt->sge[i].lkey == lkey)
 			ib_dma_unmap_page(device,
 					    ctxt->sge[i].addr,
 					    ctxt->sge[i].length,
 					    ctxt->direction);
-		}
 	}
 	ctxt->mapped_sges = 0;
-	atomic_sub(count, &xprt->sc_dma_used);
 }
 
 void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
@@ -398,7 +396,6 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 
 	/* WARNING: Only wc->wr_cqe and wc->status are reliable */
 	ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe);
-	ctxt->wc_status = wc->status;
 	svc_rdma_unmap_dma(ctxt);
 
 	if (wc->status != IB_WC_SUCCESS)
@@ -436,7 +433,7 @@ static void svc_rdma_send_wc_common(struct svcxprt_rdma *xprt,
 		goto err;
 
 out:
-	atomic_dec(&xprt->sc_sq_count);
+	atomic_inc(&xprt->sc_sq_avail);
 	wake_up(&xprt->sc_send_wait);
 	return;
 
@@ -946,7 +943,6 @@ void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
 	if (frmr) {
 		ib_dma_unmap_sg(rdma->sc_cm_id->device,
 				frmr->sg, frmr->sg_nents, frmr->direction);
-		atomic_dec(&rdma->sc_dma_used);
 		spin_lock_bh(&rdma->sc_frmr_q_lock);
 		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
 		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
@@ -973,6 +969,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	struct rpcrdma_connect_private pmsg;
 	struct ib_qp_init_attr qp_attr;
 	struct ib_device *dev;
+	struct sockaddr *sap;
 	unsigned int i;
 	int ret = 0;
 
@@ -1010,6 +1007,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	newxprt->sc_rq_depth = newxprt->sc_max_requests +
 			       newxprt->sc_max_bc_requests;
 	newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_rq_depth;
+	atomic_set(&newxprt->sc_sq_avail, newxprt->sc_sq_depth);
 
 	if (!svc_rdma_prealloc_ctxts(newxprt))
 		goto errout;
@@ -1052,18 +1050,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	qp_attr.qp_type = IB_QPT_RC;
 	qp_attr.send_cq = newxprt->sc_sq_cq;
 	qp_attr.recv_cq = newxprt->sc_rq_cq;
-	dprintk("svcrdma: newxprt->sc_cm_id=%p, newxprt->sc_pd=%p\n"
-		"    cm_id->device=%p, sc_pd->device=%p\n"
-		"    cap.max_send_wr = %d\n"
-		"    cap.max_recv_wr = %d\n"
-		"    cap.max_send_sge = %d\n"
-		"    cap.max_recv_sge = %d\n",
-		newxprt->sc_cm_id, newxprt->sc_pd,
-		dev, newxprt->sc_pd->device,
-		qp_attr.cap.max_send_wr,
-		qp_attr.cap.max_recv_wr,
-		qp_attr.cap.max_send_sge,
-		qp_attr.cap.max_recv_sge);
+	dprintk("svcrdma: newxprt->sc_cm_id=%p, newxprt->sc_pd=%p\n",
+		newxprt->sc_cm_id, newxprt->sc_pd);
+	dprintk("    cap.max_send_wr = %d, cap.max_recv_wr = %d\n",
+		qp_attr.cap.max_send_wr, qp_attr.cap.max_recv_wr);
+	dprintk("    cap.max_send_sge = %d, cap.max_recv_sge = %d\n",
+		qp_attr.cap.max_send_sge, qp_attr.cap.max_recv_sge);
 
 	ret = rdma_create_qp(newxprt->sc_cm_id, newxprt->sc_pd, &qp_attr);
 	if (ret) {
@@ -1146,31 +1138,16 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 		goto errout;
 	}
 
-	dprintk("svcrdma: new connection %p accepted with the following "
-		"attributes:\n"
-		"    local_ip        : %pI4\n"
-		"    local_port	     : %d\n"
-		"    remote_ip       : %pI4\n"
-		"    remote_port     : %d\n"
-		"    max_sge         : %d\n"
-		"    max_sge_rd      : %d\n"
-		"    sq_depth        : %d\n"
-		"    max_requests    : %d\n"
-		"    ord             : %d\n",
-		newxprt,
-		&((struct sockaddr_in *)&newxprt->sc_cm_id->
-			 route.addr.src_addr)->sin_addr.s_addr,
-		ntohs(((struct sockaddr_in *)&newxprt->sc_cm_id->
-		       route.addr.src_addr)->sin_port),
-		&((struct sockaddr_in *)&newxprt->sc_cm_id->
-			 route.addr.dst_addr)->sin_addr.s_addr,
-		ntohs(((struct sockaddr_in *)&newxprt->sc_cm_id->
-		       route.addr.dst_addr)->sin_port),
-		newxprt->sc_max_sge,
-		newxprt->sc_max_sge_rd,
-		newxprt->sc_sq_depth,
-		newxprt->sc_max_requests,
-		newxprt->sc_ord);
+	dprintk("svcrdma: new connection %p accepted:\n", newxprt);
+	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr;
+	dprintk("    local address   : %pIS:%u\n", sap, rpc_get_port(sap));
+	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
+	dprintk("    remote address  : %pIS:%u\n", sap, rpc_get_port(sap));
+	dprintk("    max_sge         : %d\n", newxprt->sc_max_sge);
+	dprintk("    max_sge_rd      : %d\n", newxprt->sc_max_sge_rd);
+	dprintk("    sq_depth        : %d\n", newxprt->sc_sq_depth);
+	dprintk("    max_requests    : %d\n", newxprt->sc_max_requests);
+	dprintk("    ord             : %d\n", newxprt->sc_ord);
 
 	return &newxprt->sc_xprt;
 
@@ -1257,9 +1234,6 @@ static void __svc_rdma_free(struct work_struct *work)
 	if (rdma->sc_ctxt_used != 0)
 		pr_err("svcrdma: ctxt still in use? (%d)\n",
 		       rdma->sc_ctxt_used);
-	if (atomic_read(&rdma->sc_dma_used) != 0)
-		pr_err("svcrdma: dma still in use? (%d)\n",
-		       atomic_read(&rdma->sc_dma_used));
 
 	/* Final put of backchannel client transport */
 	if (xprt->xpt_bc_xprt) {
@@ -1339,15 +1313,13 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 
 	/* If the SQ is full, wait until an SQ entry is available */
 	while (1) {
-		spin_lock_bh(&xprt->sc_lock);
-		if (xprt->sc_sq_depth < atomic_read(&xprt->sc_sq_count) + wr_count) {
-			spin_unlock_bh(&xprt->sc_lock);
+		if ((atomic_sub_return(wr_count, &xprt->sc_sq_avail) < 0)) {
 			atomic_inc(&rdma_stat_sq_starve);
 
 			/* Wait until SQ WR available if SQ still full */
+			atomic_add(wr_count, &xprt->sc_sq_avail);
 			wait_event(xprt->sc_send_wait,
-				   atomic_read(&xprt->sc_sq_count) <
-				   xprt->sc_sq_depth);
+				   atomic_read(&xprt->sc_sq_avail) > wr_count);
 			if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
 				return -ENOTCONN;
 			continue;
@@ -1357,21 +1329,17 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 			svc_xprt_get(&xprt->sc_xprt);
 
 		/* Bump used SQ WR count and post */
-		atomic_add(wr_count, &xprt->sc_sq_count);
 		ret = ib_post_send(xprt->sc_qp, wr, &bad_wr);
 		if (ret) {
 			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-			atomic_sub(wr_count, &xprt->sc_sq_count);
 			for (i = 0; i < wr_count; i ++)
 				svc_xprt_put(&xprt->sc_xprt);
-			dprintk("svcrdma: failed to post SQ WR rc=%d, "
-			       "sc_sq_count=%d, sc_sq_depth=%d\n",
-			       ret, atomic_read(&xprt->sc_sq_count),
-			       xprt->sc_sq_depth);
-		}
-		spin_unlock_bh(&xprt->sc_lock);
-		if (ret)
+			dprintk("svcrdma: failed to post SQ WR rc=%d\n", ret);
+			dprintk("    sc_sq_avail=%d, sc_sq_depth=%d\n",
+				atomic_read(&xprt->sc_sq_avail),
+				xprt->sc_sq_depth);
 			wake_up(&xprt->sc_send_wait);
+		}
 		break;
 	}
 	return ret;