Merge tag 'nfs-for-5.4-2' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client bugfixes from Anna Schumaker:
 "Stable bugfixes:
   - Fix O_DIRECT accounting of number of bytes read/written # v4.1+

  Other fixes:
   - Fix nfsi->nrequests count error on nfs_inode_remove_request()
   - Remove redundant mirror tracking in O_DIRECT
   - Fix leak of clp->cl_acceptor string
   - Fix race to sk_err after xs_error_report"

* tag 'nfs-for-5.4-2' of git://git.linux-nfs.org/projects/anna/linux-nfs:
  SUNRPC: fix race to sk_err after xs_error_report
  NFSv4: Fix leak of clp->cl_acceptor string
  NFS: Remove redundant mirror tracking in O_DIRECT
  NFS: Fix O_DIRECT accounting of number of bytes read/written
  nfs: Fix nfsi->nrequests count error on nfs_inode_remove_request

5 files changed, 49 insertions, 81 deletions

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 222d7115db71..040a50fd9bf3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -64,13 +64,6 @@
 
 static struct kmem_cache *nfs_direct_cachep;
 
-/*
- * This represents a set of asynchronous requests that we're waiting on
- */
-struct nfs_direct_mirror {
-	ssize_t count;
-};
-
 struct nfs_direct_req {
 	struct kref		kref;		/* release manager */
 
@@ -84,9 +77,6 @@ struct nfs_direct_req {
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
 
-	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
-	int			mirror_count;
-
 	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				max_count,	/* max expected count */
@@ -123,32 +113,42 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 }
 
 static void
-nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
+nfs_direct_handle_truncated(struct nfs_direct_req *dreq,
+			    const struct nfs_pgio_header *hdr,
+			    ssize_t dreq_len)
 {
-	int i;
-	ssize_t count;
+	if (!(test_bit(NFS_IOHDR_ERROR, &hdr->flags) ||
+	      test_bit(NFS_IOHDR_EOF, &hdr->flags)))
+		return;
+	if (dreq->max_count >= dreq_len) {
+		dreq->max_count = dreq_len;
+		if (dreq->count > dreq_len)
+			dreq->count = dreq_len;
+
+		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
+			dreq->error = hdr->error;
+		else /* Clear outstanding error if this is EOF */
+			dreq->error = 0;
+	}
+}
 
-	WARN_ON_ONCE(dreq->count >= dreq->max_count);
+static void
+nfs_direct_count_bytes(struct nfs_direct_req *dreq,
+		       const struct nfs_pgio_header *hdr)
+{
+	loff_t hdr_end = hdr->io_start + hdr->good_bytes;
+	ssize_t dreq_len = 0;
 
-	if (dreq->mirror_count == 1) {
-		dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
-		dreq->count += hdr->good_bytes;
-	} else {
-		/* mirrored writes */
-		count = dreq->mirrors[hdr->pgio_mirror_idx].count;
-		if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
-			count = hdr->io_start + hdr->good_bytes - dreq->io_start;
-			dreq->mirrors[hdr->pgio_mirror_idx].count = count;
-		}
-		/* update the dreq->count by finding the minimum agreed count from all
-		 * mirrors */
-		count = dreq->mirrors[0].count;
+	if (hdr_end > dreq->io_start)
+		dreq_len = hdr_end - dreq->io_start;
 
-		for (i = 1; i < dreq->mirror_count; i++)
-			count = min(count, dreq->mirrors[i].count);
+	nfs_direct_handle_truncated(dreq, hdr, dreq_len);
 
-		dreq->count = count;
-	}
+	if (dreq_len > dreq->max_count)
+		dreq_len = dreq->max_count;
+
+	if (dreq->count < dreq_len)
+		dreq->count = dreq_len;
 }
 
 /*
@@ -293,18 +293,6 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 	cinfo->completion_ops = &nfs_direct_commit_completion_ops;
 }
 
-static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq,
-					     struct nfs_pageio_descriptor *pgio,
-					     struct nfs_page *req)
-{
-	int mirror_count = 1;
-
-	if (pgio->pg_ops->pg_get_mirror_count)
-		mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
-
-	dreq->mirror_count = mirror_count;
-}
-
 static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 {
 	struct nfs_direct_req *dreq;
@@ -319,7 +307,6 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;	/* not set yet */
 	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
-	dreq->mirror_count = 1;
 	spin_lock_init(&dreq->lock);
 
 	return dreq;
@@ -402,20 +389,12 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	struct nfs_direct_req *dreq = hdr->dreq;
 
 	spin_lock(&dreq->lock);
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
-		dreq->error = hdr->error;
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		spin_unlock(&dreq->lock);
 		goto out_put;
 	}
 
-	if (hdr->good_bytes != 0)
-		nfs_direct_good_bytes(dreq, hdr);
-
-	if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
-		dreq->error = 0;
-
+	nfs_direct_count_bytes(dreq, hdr);
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {
@@ -646,29 +625,22 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	LIST_HEAD(reqs);
 	struct nfs_commit_info cinfo;
 	LIST_HEAD(failed);
-	int i;
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
 
 	dreq->count = 0;
+	dreq->max_count = 0;
+	list_for_each_entry(req, &reqs, wb_list)
+		dreq->max_count += req->wb_bytes;
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;
 	nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo);
-	for (i = 0; i < dreq->mirror_count; i++)
-		dreq->mirrors[i].count = 0;
 	get_dreq(dreq);
 
 	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
-	req = nfs_list_entry(reqs.next);
-	nfs_direct_setup_mirroring(dreq, &desc, req);
-	if (desc.pg_error < 0) {
-		list_splice_init(&reqs, &failed);
-		goto out_failed;
-	}
-
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
 		/* Bump the transmission count */
 		req->wb_nio++;
@@ -686,7 +658,6 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	}
 	nfs_pageio_complete(&desc);
 
-out_failed:
 	while (!list_empty(&failed)) {
 		req = nfs_list_entry(failed.next);
 		nfs_list_remove_request(req);
@@ -791,17 +762,13 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 
 	spin_lock(&dreq->lock);
-
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
-		dreq->error = hdr->error;
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		spin_unlock(&dreq->lock);
 		goto out_put;
 	}
 
+	nfs_direct_count_bytes(dreq, hdr);
 	if (hdr->good_bytes != 0) {
-		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
 				request_commit = true;
@@ -923,7 +890,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 				break;
 			}
 
-			nfs_direct_setup_mirroring(dreq, &desc, req);
 			if (desc.pg_error < 0) {
 				nfs_free_request(req);
 				result = desc.pg_error;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 11eafcfc490b..ab8ca20fd579 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6106,6 +6106,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 
 	status = nfs4_call_sync_custom(&task_setup_data);
 	if (setclientid.sc_cred) {
+		kfree(clp->cl_acceptor);
 		clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred);
 		put_rpccred(setclientid.sc_cred);
 	}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 85ca49549b39..52cab65f91cf 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -786,7 +786,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_page *head;
 
-	atomic_long_dec(&nfsi->nrequests);
 	if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
 		head = req->wb_head;
 
@@ -799,8 +798,10 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		spin_unlock(&mapping->private_lock);
 	}
 
-	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
+	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
 		nfs_release_request(req);
+		atomic_long_dec(&nfsi->nrequests);
+	}
 }
 
 static void
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 7638dbe7bc50..a940de03808d 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -61,6 +61,7 @@ struct sock_xprt {
 	struct mutex		recv_mutex;
 	struct sockaddr_storage	srcaddr;
 	unsigned short		srcport;
+	int			xprt_err;
 
 	/*
 	 * UDP socket buffer size parameters
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9ac88722fa83..70e52f567b2a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1249,19 +1249,21 @@ static void xs_error_report(struct sock *sk)
 {
 	struct sock_xprt *transport;
 	struct rpc_xprt *xprt;
-	int err;
 
 	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 
 	transport = container_of(xprt, struct sock_xprt, xprt);
-	err = -sk->sk_err;
-	if (err == 0)
+	transport->xprt_err = -sk->sk_err;
+	if (transport->xprt_err == 0)
 		goto out;
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
-			xprt, -err);
-	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+			xprt, -transport->xprt_err);
+	trace_rpc_socket_error(xprt, sk->sk_socket, transport->xprt_err);
+
+	/* barrier ensures xprt_err is set before XPRT_SOCK_WAKE_ERROR */
+	smp_mb__before_atomic();
 	xs_run_error_worker(transport, XPRT_SOCK_WAKE_ERROR);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -2476,7 +2478,6 @@ static void xs_wake_write(struct sock_xprt *transport)
 static void xs_wake_error(struct sock_xprt *transport)
 {
 	int sockerr;
-	int sockerr_len = sizeof(sockerr);
 
 	if (!test_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state))
 		return;
@@ -2485,9 +2486,7 @@ static void xs_wake_error(struct sock_xprt *transport)
 		goto out;
 	if (!test_and_clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state))
 		goto out;
-	if (kernel_getsockopt(transport->sock, SOL_SOCKET, SO_ERROR,
-				(char *)&sockerr, &sockerr_len) != 0)
-		goto out;
+	sockerr = xchg(&transport->xprt_err, 0);
 	if (sockerr < 0)
 		xprt_wake_pending_tasks(&transport->xprt, sockerr);
 out: