Merge tag 'nfsd-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:

 - Mike Snitzer's mechanism for disabling I/O caching introduced in
   v6.18 is extended to include using direct I/O. The goal is to further
   reduce the memory footprint consumed by NFS clients accessing large
   data sets via NFSD.

 - The NFSD community adopted a maintainer entry profile during this
   cycle. See

      Documentation/filesystems/nfs/nfsd-maintainer-entry-profile.rst

 - Work continues on hardening NFSD's implementation of the pNFS block
   layout type. This type enables pNFS clients to directly access the
   underlying block devices that contain an exported file system,
   reducing server overhead and increasing data throughput.

 - The remaining patches are clean-ups and minor optimizations. Many
   thanks to the contributors, reviewers, testers, and bug reporters who
   participated during the v6.19 NFSD development cycle.

* tag 'nfsd-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (38 commits)
  NFSD: nfsd-io-modes: Separate lists
  NFSD: nfsd-io-modes: Wrap shell snippets in literal code blocks
  NFSD: Add toctree entry for NFSD IO modes docs
  NFSD: add Documentation/filesystems/nfs/nfsd-io-modes.rst
  NFSD: Implement NFSD_IO_DIRECT for NFS WRITE
  NFSD: Make FILE_SYNC WRITEs comply with spec
  NFSD: Add trace point for SCSI fencing operation.
  NFSD: use correct reservation type in nfsd4_scsi_fence_client
  xdrgen: Don't generate unnecessary semicolon
  xdrgen: Fix union declarations
  NFSD: don't start nfsd if sv_permsocks is empty
  xdrgen: handle _XdrString in union encoder/decoder
  xdrgen: Fix the variable-length opaque field decoder template
  xdrgen: Make the xdrgen script location-independent
  xdrgen: Generalize/harden pathname construction
  lockd: don't allow locking on reexported NFSv2/3
  MAINTAINERS: add a nfsd blocklayout reviewer
  nfsd: Use MD5 library instead of crypto_shash
  nfsd: stop pretending that we cache the SEQUENCE reply.
  NFS: nfsd-maintainer-entry-profile: Inline function name prefixes
  ...

2 files changed, 60 insertions, 21 deletions

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 16ff6c100821..d61cd9b40491 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -68,6 +68,17 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+/*
+ * For UDP:
+ * 1 for header page
+ * enough pages for RPCSVC_MAXPAYLOAD_UDP
+ * 1 in case payload is not aligned
+ * 1 for tail page
+ */
+enum {
+	SUNRPC_MAX_UDP_SENDPAGES = 1 + RPCSVC_MAXPAYLOAD_UDP / PAGE_SIZE + 1 + 1
+};
+
 /* To-do: to avoid tying up an nfsd thread while waiting for a
  * handshake request, the request could instead be deferred.
  */
@@ -740,14 +751,14 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
 
-	count = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, xdr);
+	count = xdr_buf_to_bvec(svsk->sk_bvec, SUNRPC_MAX_UDP_SENDPAGES, xdr);
 
-	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
 		      count, rqstp->rq_res.len);
 	err = sock_sendmsg(svsk->sk_sock, &msg);
 	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
-		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
 			      count, rqstp->rq_res.len);
 		err = sock_sendmsg(svsk->sk_sock, &msg);
 	}
@@ -1062,9 +1073,10 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
 	return svc_sock_reclen(svsk);
 
 err_too_large:
-	net_notice_ratelimited("svc: %s %s RPC fragment too large: %d\n",
-			       __func__, svsk->sk_xprt.xpt_server->sv_name,
-			       svc_sock_reclen(svsk));
+	net_notice_ratelimited("svc: %s oversized RPC fragment (%u octets) from %pISpc\n",
+			       svsk->sk_xprt.xpt_server->sv_name,
+			       svc_sock_reclen(svsk),
+			       (struct sockaddr *)&svsk->sk_xprt.xpt_remote);
 	svc_xprt_deferred_close(&svsk->sk_xprt);
 err_short:
 	return -EAGAIN;
@@ -1235,19 +1247,19 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
 	int ret;
 
 	/* The stream record marker is copied into a temporary page
-	 * fragment buffer so that it can be included in rq_bvec.
+	 * fragment buffer so that it can be included in sk_bvec.
 	 */
 	buf = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker),
 			      GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 	memcpy(buf, &marker, sizeof(marker));
-	bvec_set_virt(rqstp->rq_bvec, buf, sizeof(marker));
+	bvec_set_virt(svsk->sk_bvec, buf, sizeof(marker));
 
-	count = xdr_buf_to_bvec(rqstp->rq_bvec + 1, rqstp->rq_maxpages,
+	count = xdr_buf_to_bvec(svsk->sk_bvec + 1, rqstp->rq_maxpages,
 				&rqstp->rq_res);
 
-	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
 		      1 + count, sizeof(marker) + rqstp->rq_res.len);
 	ret = sock_sendmsg(svsk->sk_sock, &msg);
 	page_frag_free(buf);
@@ -1392,6 +1404,20 @@ void svc_sock_update_bufs(struct svc_serv *serv)
 	spin_unlock_bh(&serv->sv_lock);
 }
 
+static int svc_sock_sendpages(struct svc_serv *serv, struct socket *sock, int flags)
+{
+	switch (sock->type) {
+	case SOCK_STREAM:
+		/* +1 for TCP record marker */
+		if (flags & SVC_SOCK_TEMPORARY)
+			return svc_serv_maxpages(serv) + 1;
+		return 0;
+	case SOCK_DGRAM:
+		return SUNRPC_MAX_UDP_SENDPAGES;
+	}
+	return -EINVAL;
+}
+
 /*
  * Initialize socket for RPC use and create svc_sock struct
  */
@@ -1402,12 +1428,26 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	struct svc_sock	*svsk;
 	struct sock	*inet;
 	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
+	int		sendpages;
 	unsigned long	pages;
 
+	sendpages = svc_sock_sendpages(serv, sock, flags);
+	if (sendpages < 0)
+		return ERR_PTR(sendpages);
+
 	pages = svc_serv_maxpages(serv);
 	svsk = kzalloc(struct_size(svsk, sk_pages, pages), GFP_KERNEL);
 	if (!svsk)
 		return ERR_PTR(-ENOMEM);
+
+	if (sendpages) {
+		svsk->sk_bvec = kcalloc(sendpages, sizeof(*svsk->sk_bvec), GFP_KERNEL);
+		if (!svsk->sk_bvec) {
+			kfree(svsk);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
 	svsk->sk_maxpages = pages;
 
 	inet = sock->sk;
@@ -1419,6 +1459,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 				     inet->sk_protocol,
 				     ntohs(inet_sk(inet)->inet_sport));
 		if (err < 0) {
+			kfree(svsk->sk_bvec);
 			kfree(svsk);
 			return ERR_PTR(err);
 		}
@@ -1636,5 +1677,6 @@ static void svc_sock_free(struct svc_xprt *xprt)
 		sock_release(sock);
 
 	page_frag_cache_drain(&svsk->sk_frag_cache);
+	kfree(svsk->sk_bvec);
 	kfree(svsk);
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3d7f1413df02..b7b318ad25c4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -591,12 +591,18 @@ static void svc_rdma_detach(struct svc_xprt *xprt)
 	rdma_disconnect(rdma->sc_cm_id);
 }
 
-static void __svc_rdma_free(struct work_struct *work)
+/**
+ * svc_rdma_free - Release class-specific transport resources
+ * @xprt: Generic svc transport object
+ */
+static void svc_rdma_free(struct svc_xprt *xprt)
 {
 	struct svcxprt_rdma *rdma =
-		container_of(work, struct svcxprt_rdma, sc_work);
+		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	struct ib_device *device = rdma->sc_cm_id->device;
 
+	might_sleep();
+
 	/* This blocks until the Completion Queues are empty */
 	if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
 		ib_drain_qp(rdma->sc_qp);
@@ -629,15 +635,6 @@ static void __svc_rdma_free(struct work_struct *work)
 	kfree(rdma);
 }
 
-static void svc_rdma_free(struct svc_xprt *xprt)
-{
-	struct svcxprt_rdma *rdma =
-		container_of(xprt, struct svcxprt_rdma, sc_xprt);
-
-	INIT_WORK(&rdma->sc_work, __svc_rdma_free);
-	schedule_work(&rdma->sc_work);
-}
-
 static int svc_rdma_has_wspace(struct svc_xprt *xprt)
 {
 	struct svcxprt_rdma *rdma =