Merge tag 'nfsd-5.16' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "A slow cycle for nfsd: mainly cleanup, including Neil's patch dropping
  support for a filehandle format deprecated 20 years ago, and further
  xdr-related cleanup from Chuck"

* tag 'nfsd-5.16' of git://linux-nfs.org/~bfields/linux: (26 commits)
  nfsd4: remove obselete comment
  nfsd: document server-to-server-copy parameters
  NFSD:fix boolreturn.cocci warning
  nfsd: update create verifier comment
  SUNRPC: Change return value type of .pc_encode
  SUNRPC: Replace the "__be32 *p" parameter to .pc_encode
  NFSD: Save location of NFSv4 COMPOUND status
  SUNRPC: Change return value type of .pc_decode
  SUNRPC: Replace the "__be32 *p" parameter to .pc_decode
  SUNRPC: De-duplicate .pc_release() call sites
  SUNRPC: Simplify the SVC dispatch code path
  SUNRPC: Capture value of xdr_buf::page_base
  SUNRPC: Add trace event when alloc_pages_bulk() makes no progress
  svcrdma: Split svcrmda_wc_{read,write} tracepoints
  svcrdma: Split the svcrdma_wc_send() tracepoint
  svcrdma: Split the svcrdma_wc_receive() tracepoint
  NFSD: Have legacy NFSD WRITE decoders use xdr_stream_subsegment()
  SUNRPC: xdr_stream_subsegment() must handle non-zero page_bases
  NFSD: Initialize pointer ni with NULL and not plain integer 0
  NFSD: simplify struct nfsfh
  ...

8 files changed, 94 insertions, 114 deletions

diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 6e4dbd577a39..d435bffc6199 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -162,8 +162,10 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 			      const size_t buflen, const char *delim,
 			      struct sockaddr_in6 *sin6)
 {
-	char *p;
+	char p[IPV6_SCOPE_ID_LEN + 1];
 	size_t len;
+	u32 scope_id = 0;
+	struct net_device *dev;
 
 	if ((buf + buflen) == delim)
 		return 1;
@@ -175,29 +177,23 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 		return 0;
 
 	len = (buf + buflen) - delim - 1;
-	p = kmemdup_nul(delim + 1, len, GFP_KERNEL);
-	if (p) {
-		u32 scope_id = 0;
-		struct net_device *dev;
-
-		dev = dev_get_by_name(net, p);
-		if (dev != NULL) {
-			scope_id = dev->ifindex;
-			dev_put(dev);
-		} else {
-			if (kstrtou32(p, 10, &scope_id) != 0) {
-				kfree(p);
-				return 0;
-			}
-		}
-
-		kfree(p);
-
-		sin6->sin6_scope_id = scope_id;
-		return 1;
+	if (len > IPV6_SCOPE_ID_LEN)
+		return 0;
+
+	memcpy(p, delim + 1, len);
+	p[len] = 0;
+
+	dev = dev_get_by_name(net, p);
+	if (dev != NULL) {
+		scope_id = dev->ifindex;
+		dev_put(dev);
+	} else {
+		if (kstrtou32(p, 10, &scope_id) != 0)
+			return 0;
 	}
 
-	return 0;
+	sin6->sin6_scope_id = scope_id;
+	return 1;
 }
 
 static size_t rpc_pton6(struct net *net, const char *buf, const size_t buflen,
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 1f2817195549..b87565b64928 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -781,7 +781,7 @@ gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq)
 	svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS);
 	xdr_seq = kmalloc(4, GFP_KERNEL);
 	if (!xdr_seq)
-		return -1;
+		return -ENOMEM;
 	*xdr_seq = htonl(seq);
 
 	iov.iov_base = xdr_seq;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index a3bbe5ce4570..4292278a9552 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1186,45 +1186,6 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
 static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {}
 #endif
 
-static int
-svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp)
-{
-	struct kvec *argv = &rqstp->rq_arg.head[0];
-	struct kvec *resv = &rqstp->rq_res.head[0];
-	const struct svc_procedure *procp = rqstp->rq_procinfo;
-
-	/*
-	 * Decode arguments
-	 * XXX: why do we ignore the return value?
-	 */
-	if (procp->pc_decode &&
-	    !procp->pc_decode(rqstp, argv->iov_base)) {
-		*statp = rpc_garbage_args;
-		return 1;
-	}
-
-	*statp = procp->pc_func(rqstp);
-
-	if (*statp == rpc_drop_reply ||
-	    test_bit(RQ_DROPME, &rqstp->rq_flags))
-		return 0;
-
-	if (rqstp->rq_auth_stat != rpc_auth_ok)
-		return 1;
-
-	if (*statp != rpc_success)
-		return 1;
-
-	/* Encode reply */
-	if (procp->pc_encode &&
-	    !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) {
-		dprintk("svc: failed to encode reply\n");
-		/* serv->sv_stats->rpcsystemerr++; */
-		*statp = rpc_system_err;
-	}
-	return 1;
-}
-
 __be32
 svc_generic_init_request(struct svc_rqst *rqstp,
 		const struct svc_program *progp,
@@ -1291,7 +1252,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	__be32			*statp;
 	u32			prog, vers;
 	__be32			rpc_stat;
-	int			auth_res;
+	int			auth_res, rc;
 	__be32			*reply_statp;
 
 	rpc_stat = rpc_success;
@@ -1392,28 +1353,18 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		svc_reserve_auth(rqstp, procp->pc_xdrressize<<2);
 
 	/* Call the function that processes the request. */
-	if (!process.dispatch) {
-		if (!svc_generic_dispatch(rqstp, statp))
-			goto release_dropit;
-		if (*statp == rpc_garbage_args)
-			goto err_garbage;
-	} else {
-		dprintk("svc: calling dispatcher\n");
-		if (!process.dispatch(rqstp, statp))
-			goto release_dropit; /* Release reply info */
-	}
-
+	rc = process.dispatch(rqstp, statp);
+	if (procp->pc_release)
+		procp->pc_release(rqstp);
+	if (!rc)
+		goto dropit;
 	if (rqstp->rq_auth_stat != rpc_auth_ok)
-		goto err_release_bad_auth;
+		goto err_bad_auth;
 
 	/* Check RPC status result */
 	if (*statp != rpc_success)
 		resv->iov_len = ((void*)statp)  - resv->iov_base + 4;
 
-	/* Release reply info */
-	if (procp->pc_release)
-		procp->pc_release(rqstp);
-
 	if (procp->pc_encode == NULL)
 		goto dropit;
 
@@ -1422,9 +1373,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		goto close_xprt;
 	return 1;		/* Caller can now send it */
 
-release_dropit:
-	if (procp->pc_release)
-		procp->pc_release(rqstp);
  dropit:
 	svc_authorise(rqstp);	/* doesn't hurt to call this twice */
 	dprintk("svc: svc_process dropit\n");
@@ -1451,9 +1399,6 @@ err_bad_rpc:
 	svc_putnl(resv, 2);
 	goto sendit;
 
-err_release_bad_auth:
-	if (procp->pc_release)
-		procp->pc_release(rqstp);
 err_bad_auth:
 	dprintk("svc: authentication failed (%d)\n",
 		be32_to_cpu(rqstp->rq_auth_stat));
@@ -1676,16 +1621,17 @@ EXPORT_SYMBOL_GPL(svc_encode_result_payload);
 /**
  * svc_fill_write_vector - Construct data argument for VFS write call
  * @rqstp: svc_rqst to operate on
- * @pages: list of pages containing data payload
- * @first: buffer containing first section of write payload
- * @total: total number of bytes of write payload
+ * @payload: xdr_buf containing only the write data payload
  *
  * Fills in rqstp::rq_vec, and returns the number of elements.
  */
-unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages,
-				   struct kvec *first, size_t total)
+unsigned int svc_fill_write_vector(struct svc_rqst *rqstp,
+				   struct xdr_buf *payload)
 {
+	struct page **pages = payload->pages;
+	struct kvec *first = payload->head;
 	struct kvec *vec = rqstp->rq_vec;
+	size_t total = payload->len;
 	unsigned int i;
 
 	/* Some types of transport can present the write payload
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 6316bd2b8f37..1e99ba1b9d72 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -687,6 +687,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
 			set_current_state(TASK_RUNNING);
 			return -EINTR;
 		}
+		trace_svc_alloc_arg_err(pages);
 		schedule_timeout(msecs_to_jiffies(500));
 	}
 	rqstp->rq_page_end = &rqstp->rq_pages[pages];
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index ca10ba2626f2..df194cc07035 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1633,7 +1633,7 @@ EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
  * Sets up @subbuf to represent a portion of @xdr. The portion
  * starts at the current offset in @xdr, and extends for a length
  * of @nbytes. If this is successful, @xdr is advanced to the next
- * position following that portion.
+ * XDR data item following that portion.
  *
  * Return values:
  *   %true: @subbuf has been initialized, and @xdr has been advanced.
@@ -1642,29 +1642,31 @@ EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
 bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
 			   unsigned int nbytes)
 {
-	unsigned int remaining, offset, len;
+	unsigned int start = xdr_stream_pos(xdr);
+	unsigned int remaining, len;
 
-	if (xdr_buf_subsegment(xdr->buf, subbuf, xdr_stream_pos(xdr), nbytes))
+	/* Extract @subbuf and bounds-check the fn arguments */
+	if (xdr_buf_subsegment(xdr->buf, subbuf, start, nbytes))
 		return false;
 
-	if (subbuf->head[0].iov_len)
-		if (!__xdr_inline_decode(xdr, subbuf->head[0].iov_len))
-			return false;
-
-	remaining = subbuf->page_len;
-	offset = subbuf->page_base;
-	while (remaining) {
-		len = min_t(unsigned int, remaining, PAGE_SIZE) - offset;
-
+	/* Advance @xdr by @nbytes */
+	for (remaining = nbytes; remaining;) {
 		if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr))
 			return false;
-		if (!__xdr_inline_decode(xdr, len))
-			return false;
 
+		len = (char *)xdr->end - (char *)xdr->p;
+		if (remaining <= len) {
+			xdr->p = (__be32 *)((char *)xdr->p +
+					(remaining + xdr_pad_size(nbytes)));
+			break;
+		}
+
+		xdr->p = (__be32 *)((char *)xdr->p + len);
+		xdr->end = xdr->p;
 		remaining -= len;
-		offset = 0;
 	}
 
+	xdr_stream_set_pos(xdr, start + nbytes);
 	return true;
 }
 EXPORT_SYMBOL_GPL(xdr_stream_subsegment);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 6be23ce7a93d..cf76a6ad127b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -330,9 +330,9 @@ 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_recv_ctxt, rc_cqe);
 
-	trace_svcrdma_wc_receive(wc, &ctxt->rc_cid);
 	if (wc->status != IB_WC_SUCCESS)
 		goto flushed;
+	trace_svcrdma_wc_recv(wc, &ctxt->rc_cid);
 
 	/* If receive posting fails, the connection is about to be
 	 * lost anyway. The server will not be able to send a reply
@@ -345,7 +345,7 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	 */
 	if (rdma->sc_pending_recvs < rdma->sc_max_requests)
 		if (!svc_rdma_refresh_recvs(rdma, rdma->sc_recv_batch, false))
-			goto flushed;
+			goto dropped;
 
 	/* All wc fields are now known to be valid */
 	ctxt->rc_byte_len = wc->byte_len;
@@ -360,6 +360,11 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	return;
 
 flushed:
+	if (wc->status == IB_WC_WR_FLUSH_ERR)
+		trace_svcrdma_wc_recv_flush(wc, &ctxt->rc_cid);
+	else
+		trace_svcrdma_wc_recv_err(wc, &ctxt->rc_cid);
+dropped:
 	svc_rdma_recv_ctxt_put(rdma, ctxt);
 	svc_xprt_deferred_close(&rdma->sc_xprt);
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index e27433f08ca7..5f0155fdefc7 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -155,6 +155,7 @@ struct svc_rdma_chunk_ctxt {
 	struct ib_cqe		cc_cqe;
 	struct svcxprt_rdma	*cc_rdma;
 	struct list_head	cc_rwctxts;
+	ktime_t			cc_posttime;
 	int			cc_sqecount;
 	enum ib_wc_status	cc_status;
 	struct completion	cc_done;
@@ -267,7 +268,16 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct svc_rdma_write_info *info =
 			container_of(cc, struct svc_rdma_write_info, wi_cc);
 
-	trace_svcrdma_wc_write(wc, &cc->cc_cid);
+	switch (wc->status) {
+	case IB_WC_SUCCESS:
+		trace_svcrdma_wc_write(wc, &cc->cc_cid);
+		break;
+	case IB_WC_WR_FLUSH_ERR:
+		trace_svcrdma_wc_write_flush(wc, &cc->cc_cid);
+		break;
+	default:
+		trace_svcrdma_wc_write_err(wc, &cc->cc_cid);
+	}
 
 	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
 
@@ -320,11 +330,22 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_chunk_ctxt *cc =
 			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
-	struct svcxprt_rdma *rdma = cc->cc_rdma;
+	struct svc_rdma_read_info *info;
 
-	trace_svcrdma_wc_read(wc, &cc->cc_cid);
+	switch (wc->status) {
+	case IB_WC_SUCCESS:
+		info = container_of(cc, struct svc_rdma_read_info, ri_cc);
+		trace_svcrdma_wc_read(wc, &cc->cc_cid, info->ri_totalbytes,
+				      cc->cc_posttime);
+		break;
+	case IB_WC_WR_FLUSH_ERR:
+		trace_svcrdma_wc_read_flush(wc, &cc->cc_cid);
+		break;
+	default:
+		trace_svcrdma_wc_read_err(wc, &cc->cc_cid);
+	}
 
-	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
+	svc_rdma_wake_send_waiters(cc->cc_rdma, cc->cc_sqecount);
 	cc->cc_status = wc->status;
 	complete(&cc->cc_done);
 	return;
@@ -363,6 +384,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 	do {
 		if (atomic_sub_return(cc->cc_sqecount,
 				      &rdma->sc_sq_avail) > 0) {
+			cc->cc_posttime = ktime_get();
 			ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
 			if (ret)
 				break;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 599021b2391d..22a871e6fe4d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -280,13 +280,21 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 	struct svc_rdma_send_ctxt *ctxt =
 		container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe);
 
-	trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
-
 	svc_rdma_wake_send_waiters(rdma, 1);
 	complete(&ctxt->sc_done);
 
 	if (unlikely(wc->status != IB_WC_SUCCESS))
-		svc_xprt_deferred_close(&rdma->sc_xprt);
+		goto flushed;
+
+	trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
+	return;
+
+flushed:
+	if (wc->status != IB_WC_WR_FLUSH_ERR)
+		trace_svcrdma_wc_send_err(wc, &ctxt->sc_cid);
+	else
+		trace_svcrdma_wc_send_flush(wc, &ctxt->sc_cid);
+	svc_xprt_deferred_close(&rdma->sc_xprt);
 }
 
 /**