Merge tag 'nfs-for-5.18-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client fixes from Trond Myklebust:
 "Stable fixes:

   - SUNRPC: Ensure we flush any closed sockets before xs_xprt_free()

  Bugfixes:

   - Fix an Oopsable condition due to SLAB_ACCOUNT setting in the
     NFSv4.2 xattr code.

   - Fix for open() using an file open mode of '3' in NFSv4

   - Replace readdir's use of xxhash() with hash_64()

   - Several patches to handle malloc() failure in SUNRPC"

* tag 'nfs-for-5.18-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  SUNRPC: Move the call to xprt_send_pagedata() out of xprt_sock_sendmsg()
  SUNRPC: svc_tcp_sendmsg() should handle errors from xdr_alloc_bvec()
  SUNRPC: Handle allocation failure in rpc_new_task()
  NFS: Ensure rpc_run_task() cannot fail in nfs_async_rename()
  NFSv4/pnfs: Handle RPC allocation errors in nfs4_proc_layoutget
  SUNRPC: Handle low memory situations in call_status()
  SUNRPC: Handle ENOMEM in call_transmit_status()
  NFSv4.2: Fix missing removal of SLAB_ACCOUNT on kmem_cache allocation
  SUNRPC: Ensure we flush any closed sockets before xs_xprt_free()
  NFS: Replace readdir's use of xxhash() with hash_64()
  SUNRPC: handle malloc failure in ->request_prepare
  NFSv4: fix open failure with O_ACCMODE flag
  Revert "NFSv4: Handle the special Linux file open access mode"

fs/file_table.c

@@ -412,6 +412,7 @@ void __fput_sync(struct file *file)
 }
 
 EXPORT_SYMBOL(fput);
+EXPORT_SYMBOL(__fput_sync);
 
 void __init files_init(void)
 {

fs/nfs/Kconfig

@@ -4,10 +4,6 @@ config NFS_FS
 	depends on INET && FILE_LOCKING && MULTIUSER
 	select LOCKD
 	select SUNRPC
-	select CRYPTO
-	select CRYPTO_HASH
-	select XXHASH
-	select CRYPTO_XXHASH
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
 	help
 	  Choose Y here if you want to access files residing on other

fs/nfs/dir.c

@@ -39,7 +39,7 @@
 #include <linux/sched.h>
 #include <linux/kmemleak.h>
 #include <linux/xattr.h>
-#include <linux/xxhash.h>
+#include <linux/hash.h>
 
 #include "delegation.h"
 #include "iostat.h"
@@ -350,10 +350,7 @@ static int nfs_readdir_page_array_append(struct page *page,
  * of directory cookies. Content is addressed by the value of the
  * cookie index of the first readdir entry in a page.
  *
- * The xxhash algorithm is chosen because it is fast, and is supposed
- * to result in a decent flat distribution of hashes.
- *
- * We then select only the first 18 bits to avoid issues with excessive
+ * We select only the first 18 bits to avoid issues with excessive
  * memory use for the page cache XArray. 18 bits should allow the caching
  * of 262144 pages of sequences of readdir entries. Since each page holds
  * 127 readdir entries for a typical 64-bit system, that works out to a
@@ -363,7 +360,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie)
 {
 	if (cookie == 0)
 		return 0;
-	return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK;
+	return hash_64(cookie, 18);
 }
 
 static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie,
@@ -1991,16 +1988,6 @@ const struct dentry_operations nfs4_dentry_operations = {
 };
 EXPORT_SYMBOL_GPL(nfs4_dentry_operations);
 
-static fmode_t flags_to_mode(int flags)
-{
-	fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
-	if ((flags & O_ACCMODE) != O_WRONLY)
-		res |= FMODE_READ;
-	if ((flags & O_ACCMODE) != O_RDONLY)
-		res |= FMODE_WRITE;
-	return res;
-}
-
 static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp)
 {
 	return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp);

fs/nfs/inode.c

@@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp)
 	nfs_fscache_open_file(inode, filp);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nfs_open);
 
 /*
  * This function is called whenever some part of NFS notices that

fs/nfs/internal.h

@@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry)
 	return true;
 }
 
+static inline fmode_t flags_to_mode(int flags)
+{
+	fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
+	if ((flags & O_ACCMODE) != O_WRONLY)
+		res |= FMODE_READ;
+	if ((flags & O_ACCMODE) != O_RDONLY)
+		res |= FMODE_WRITE;
+	return res;
+}
+
 /*
  * Note: RFC 1813 doesn't limit the number of auth flavors that
  * a server can return, so make something up.

fs/nfs/nfs42xattr.c

@@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void)
 
 	nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache",
 	    sizeof(struct nfs4_xattr_cache), 0,
-	    (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+	    (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
 	    nfs4_xattr_cache_init_once);
 	if (nfs4_xattr_cache_cachep == NULL)
 		return -ENOMEM;

fs/nfs/nfs4file.c

@@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	struct dentry *parent = NULL;
 	struct inode *dir;
 	unsigned openflags = filp->f_flags;
+	fmode_t f_mode;
 	struct iattr attr;
 	int err;
 
@@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	if (err)
 		return err;
 
+	f_mode = filp->f_mode;
 	if ((openflags & O_ACCMODE) == 3)
-		return nfs_open(inode, filp);
+		f_mode |= flags_to_mode(openflags);
 
 	/* We can't create new files here */
 	openflags &= ~(O_CREAT|O_EXCL);
@@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	parent = dget_parent(dentry);
 	dir = d_inode(parent);
 
-	ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp);
+	ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp);
 	err = PTR_ERR(ctx);
 	if (IS_ERR(ctx))
 		goto out;

fs/nfs/nfs4proc.c

@@ -9615,6 +9615,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
 
 	task = rpc_run_task(&task_setup_data);
+	if (IS_ERR(task))
+		return ERR_CAST(task);
 
 	status = rpc_wait_for_completion_task(task);
 	if (status != 0)

fs/nfs/unlink.c

@@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (data == NULL)
 		return ERR_PTR(-ENOMEM);
+	task_setup_data.task = &data->task;
 	task_setup_data.callback_data = data;
 
 	data->cred = get_current_cred();

include/linux/nfs_xdr.h

@@ -1694,6 +1694,7 @@ struct nfs_unlinkdata {
 struct nfs_renamedata {
 	struct nfs_renameargs	args;
 	struct nfs_renameres	res;
+	struct rpc_task		task;
 	const struct cred	*cred;
 	struct inode		*old_dir;
 	struct dentry		*old_dentry;

include/linux/sunrpc/xprt.h

@@ -144,7 +144,7 @@ struct rpc_xprt_ops {
 	unsigned short	(*get_srcport)(struct rpc_xprt *xprt);
 	int		(*buf_alloc)(struct rpc_task *task);
 	void		(*buf_free)(struct rpc_task *task);
-	void		(*prepare_request)(struct rpc_rqst *req);
+	int		(*prepare_request)(struct rpc_rqst *req);
 	int		(*send_request)(struct rpc_rqst *req);
 	void		(*wait_for_reply_request)(struct rpc_task *task);
 	void		(*timer)(struct rpc_xprt *xprt, struct rpc_task *task);
@@ -358,10 +358,9 @@ int			xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_free_slot(struct rpc_xprt *xprt,
 				       struct rpc_rqst *req);
-void			xprt_request_prepare(struct rpc_rqst *req);
 bool			xprt_prepare_transmit(struct rpc_task *task);
 void			xprt_request_enqueue_transmit(struct rpc_task *task);
-void			xprt_request_enqueue_receive(struct rpc_task *task);
+int			xprt_request_enqueue_receive(struct rpc_task *task);
 void			xprt_request_wait_receive(struct rpc_task *task);
 void			xprt_request_dequeue_xprt(struct rpc_task *task);
 bool			xprt_request_need_retransmit(struct rpc_task *task);

include/trace/events/sunrpc.h

@@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force);
-DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy);
 
 DECLARE_EVENT_CLASS(rpc_xprt_event,

net/sunrpc/clnt.c

@@ -1127,6 +1127,8 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data)
 	struct rpc_task *task;
 
 	task = rpc_new_task(task_setup_data);
+	if (IS_ERR(task))
+		return task;
 
 	if (!RPC_IS_ASYNC(task))
 		task->tk_flags |= RPC_TASK_CRED_NOREF;
@@ -1227,6 +1229,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
 	 * Create an rpc_task to send the data
 	 */
 	task = rpc_new_task(&task_setup_data);
+	if (IS_ERR(task)) {
+		xprt_free_bc_request(req);
+		return task;
+	}
+
 	xprt_init_bc_request(req, task);
 
 	task->tk_action = call_bc_encode;
@@ -1858,6 +1865,9 @@ call_encode(struct rpc_task *task)
 	xprt_request_dequeue_xprt(task);
 	/* Encode here so that rpcsec_gss can use correct sequence number. */
 	rpc_xdr_encode(task);
+	/* Add task to reply queue before transmission to avoid races */
+	if (task->tk_status == 0 && rpc_reply_expected(task))
+		task->tk_status = xprt_request_enqueue_receive(task);
 	/* Did the encode result in an error condition? */
 	if (task->tk_status != 0) {
 		/* Was the error nonfatal? */
@@ -1881,9 +1891,6 @@ call_encode(struct rpc_task *task)
 		return;
 	}
 
-	/* Add task to reply queue before transmission to avoid races */
-	if (rpc_reply_expected(task))
-		xprt_request_enqueue_receive(task);
 	xprt_request_enqueue_transmit(task);
 out:
 	task->tk_action = call_transmit;
@@ -2200,6 +2207,7 @@ call_transmit_status(struct rpc_task *task)
 		 * socket just returned a connection error,
 		 * then hold onto the transport lock.
 		 */
+	case -ENOMEM:
 	case -ENOBUFS:
 		rpc_delay(task, HZ>>2);
 		fallthrough;
@@ -2283,6 +2291,7 @@ call_bc_transmit_status(struct rpc_task *task)
 	case -ENOTCONN:
 	case -EPIPE:
 		break;
+	case -ENOMEM:
 	case -ENOBUFS:
 		rpc_delay(task, HZ>>2);
 		fallthrough;
@@ -2365,6 +2374,11 @@ call_status(struct rpc_task *task)
 	case -EPIPE:
 	case -EAGAIN:
 		break;
+	case -ENFILE:
+	case -ENOBUFS:
+	case -ENOMEM:
+		rpc_delay(task, HZ>>2);
+		break;
 	case -EIO:
 		/* shutdown or soft timeout */
 		goto out_exit;

net/sunrpc/sched.c

@@ -1128,6 +1128,11 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data)
 
 	if (task == NULL) {
 		task = rpc_alloc_task();
+		if (task == NULL) {
+			rpc_release_calldata(setup_data->callback_ops,
+					     setup_data->callback_data);
+			return ERR_PTR(-ENOMEM);
+		}
 		flags = RPC_TASK_DYNAMIC;
 	}
 

net/sunrpc/socklib.c

@@ -221,12 +221,6 @@ static int xprt_send_kvec(struct socket *sock, struct msghdr *msg,
 static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg,
 			      struct xdr_buf *xdr, size_t base)
 {
-	int err;
-
-	err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask());
-	if (err < 0)
-		return err;
-
 	iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, xdr_buf_pagecount(xdr),
 		      xdr->page_len + xdr->page_base);
 	return xprt_sendmsg(sock, msg, base + xdr->page_base);

net/sunrpc/svcsock.c

@@ -579,15 +579,18 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
 
+	err = xdr_alloc_bvec(xdr, GFP_KERNEL);
+	if (err < 0)
+		goto out_unlock;
+
 	err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
-	xdr_free_bvec(xdr);
 	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
 		err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
-		xdr_free_bvec(xdr);
 	}
+	xdr_free_bvec(xdr);
 	trace_svcsock_udp_send(xprt, err);
-
+out_unlock:
 	mutex_unlock(&xprt->xpt_mutex);
 	if (err < 0)
 		return err;
@@ -1096,7 +1099,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
 	int ret;
 
 	*sentp = 0;
-	xdr_alloc_bvec(xdr, GFP_KERNEL);
+	ret = xdr_alloc_bvec(xdr, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
 
 	ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len);
 	if (ret < 0)

net/sunrpc/xprt.c

@@ -73,6 +73,7 @@ static void	 xprt_init(struct rpc_xprt *xprt, struct net *net);
 static __be32	xprt_alloc_xid(struct rpc_xprt *xprt);
 static void	xprt_destroy(struct rpc_xprt *xprt);
 static void	xprt_request_init(struct rpc_task *task);
+static int	xprt_request_prepare(struct rpc_rqst *req);
 
 static DEFINE_SPINLOCK(xprt_list_lock);
 static LIST_HEAD(xprt_list);
@@ -929,12 +930,7 @@ void xprt_connect(struct rpc_task *task)
 	if (!xprt_lock_write(xprt, task))
 		return;
 
-	if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
-		trace_xprt_disconnect_cleanup(xprt);
-		xprt->ops->close(xprt);
-	}
-
-	if (!xprt_connected(xprt)) {
+	if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
 		task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie;
 		rpc_sleep_on_timeout(&xprt->pending, task, NULL,
 				xprt_request_timeout(task->tk_rqstp));
@@ -1143,16 +1139,19 @@ xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req)
  * @task: RPC task
  *
  */
-void
+int
 xprt_request_enqueue_receive(struct rpc_task *task)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
+	int ret;
 
 	if (!xprt_request_need_enqueue_receive(task, req))
-		return;
+		return 0;
 
-	xprt_request_prepare(task->tk_rqstp);
+	ret = xprt_request_prepare(task->tk_rqstp);
+	if (ret)
+		return ret;
 	spin_lock(&xprt->queue_lock);
 
 	/* Update the softirq receive buffer */
@@ -1166,6 +1165,7 @@ xprt_request_enqueue_receive(struct rpc_task *task)
 
 	/* Turn off autodisconnect */
 	del_singleshot_timer_sync(&xprt->timer);
+	return 0;
 }
 
 /**
@@ -1452,14 +1452,16 @@ xprt_request_dequeue_xprt(struct rpc_task *task)
  *
  * Calls into the transport layer to do whatever is needed to prepare
  * the request for transmission or receive.
+ * Returns error, or zero.
  */
-void
+static int
 xprt_request_prepare(struct rpc_rqst *req)
 {
 	struct rpc_xprt *xprt = req->rq_xprt;
 
 	if (xprt->ops->prepare_request)
-		xprt->ops->prepare_request(req);
+		return xprt->ops->prepare_request(req);
+	return 0;
 }
 
 /**

net/sunrpc/xprtsock.c

@@ -822,12 +822,17 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait)
 	return ret;
 }
 
-static void
+static int
 xs_stream_prepare_request(struct rpc_rqst *req)
 {
+	gfp_t gfp = rpc_task_gfp_mask();
+	int ret;
+
+	ret = xdr_alloc_bvec(&req->rq_snd_buf, gfp);
+	if (ret < 0)
+		return ret;
 	xdr_free_bvec(&req->rq_rcv_buf);
-	req->rq_task->tk_status = xdr_alloc_bvec(
-		&req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	return xdr_alloc_bvec(&req->rq_rcv_buf, gfp);
 }
 
 /*
@@ -879,7 +884,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
 
 	/* Close the stream if the previous transmission was incomplete */
 	if (xs_send_request_was_aborted(transport, req)) {
-		xs_close(xprt);
+		xprt_force_disconnect(xprt);
 		return -ENOTCONN;
 	}
 
@@ -915,7 +920,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
 			-status);
 		fallthrough;
 	case -EPIPE:
-		xs_close(xprt);
+		xprt_force_disconnect(xprt);
 		status = -ENOTCONN;
 	}
 
@@ -956,6 +961,9 @@ static int xs_udp_send_request(struct rpc_rqst *req)
 	if (!xprt_request_get_cong(xprt, req))
 		return -EBADSLT;
 
+	status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask());
+	if (status < 0)
+		return status;
 	req->rq_xtime = ktime_get();
 	status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent);
 
@@ -1185,6 +1193,16 @@ static void xs_reset_transport(struct sock_xprt *transport)
 
 	if (sk == NULL)
 		return;
+	/*
+	 * Make sure we're calling this in a context from which it is safe
+	 * to call __fput_sync(). In practice that means rpciod and the
+	 * system workqueue.
+	 */
+	if (!(current->flags & PF_WQ_WORKER)) {
+		WARN_ON_ONCE(1);
+		set_bit(XPRT_CLOSE_WAIT, &xprt->state);
+		return;
+	}
 
 	if (atomic_read(&transport->xprt.swapper))
 		sk_clear_memalloc(sk);
@@ -1208,7 +1226,7 @@ static void xs_reset_transport(struct sock_xprt *transport)
 	mutex_unlock(&transport->recv_mutex);
 
 	trace_rpc_socket_close(xprt, sock);
-	fput(filp);
+	__fput_sync(filp);
 
 	xprt_disconnect_done(xprt);
 }
@@ -2544,6 +2562,9 @@ static int bc_sendto(struct rpc_rqst *req)
 	int err;
 
 	req->rq_xtime = ktime_get();
+	err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask());
+	if (err < 0)
+		return err;
 	err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent);
 	xdr_free_bvec(xdr);
 	if (err < 0 || sent != (xdr->len + sizeof(marker)))