Merge branch 'work.afs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull AFS updates from Al Viro:
 "AFS series, with some iov_iter bits included"

* 'work.afs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (26 commits)
  missing bits of "iov_iter: Separate type from direction and use accessor functions"
  afs: Probe multiple fileservers simultaneously
  afs: Fix callback handling
  afs: Eliminate the address pointer from the address list cursor
  afs: Allow dumping of server cursor on operation failure
  afs: Implement YFS support in the fs client
  afs: Expand data structure fields to support YFS
  afs: Get the target vnode in afs_rmdir() and get a callback on it
  afs: Calc callback expiry in op reply delivery
  afs: Fix FS.FetchStatus delivery from updating wrong vnode
  afs: Implement the YFS cache manager service
  afs: Remove callback details from afs_callback_break struct
  afs: Commit the status on a new file/dir/symlink
  afs: Increase to 64-bit volume ID and 96-bit vnode ID for YFS
  afs: Don't invoke the server to read data beyond EOF
  afs: Add a couple of tracepoints to log I/O errors
  afs: Handle EIO from delivery function
  afs: Fix TTL on VL server and address lists
  afs: Implement VL server rotation
  afs: Improve FS server rotation error handling
  ...

block/bio.c

@@ -1256,7 +1256,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	/*
 	 * success
 	 */
-	if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) ||
+	if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) ||
 	    (map_data && map_data->from_user)) {
 		ret = bio_copy_from_iter(bio, iter);
 		if (ret)

drivers/block/drbd/drbd_main.c

@@ -1856,7 +1856,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 
 	/* THINK  if (signal_pending) return ... ? */
 
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
+	iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size);
 
 	if (sock == connection->data.socket) {
 		rcu_read_lock();

drivers/block/drbd/drbd_receiver.c

@@ -516,7 +516,7 @@ static int drbd_recv_short(struct socket *sock, void *buf, size_t size, int flag
 	struct msghdr msg = {
 		.msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL)
 	};
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, size);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size);
 	return sock_recvmsg(sock, &msg, msg.msg_flags);
 }
 

drivers/block/loop.c

@@ -269,7 +269,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
 	struct iov_iter i;
 	ssize_t bw;
 
-	iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len);
+	iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len);
 
 	file_start_write(file);
 	bw = vfs_iter_write(file, &i, ppos, 0);
@@ -347,7 +347,7 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq,
 	ssize_t len;
 
 	rq_for_each_segment(bvec, rq, iter) {
-		iov_iter_bvec(&i, ITER_BVEC, &bvec, 1, bvec.bv_len);
+		iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len);
 		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
 		if (len < 0)
 			return len;
@@ -388,7 +388,7 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq,
 		b.bv_offset = 0;
 		b.bv_len = bvec.bv_len;
 
-		iov_iter_bvec(&i, ITER_BVEC, &b, 1, b.bv_len);
+		iov_iter_bvec(&i, READ, &b, 1, b.bv_len);
 		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
 		if (len < 0) {
 			ret = len;
@@ -555,8 +555,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	}
 	atomic_set(&cmd->ref, 2);
 
-	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
-		      segments, blk_rq_bytes(rq));
+	iov_iter_bvec(&iter, rw, bvec, segments, blk_rq_bytes(rq));
 	iter.iov_offset = offset;
 
 	cmd->iocb.ki_pos = pos;

drivers/block/nbd.c

@@ -473,7 +473,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	u32 nbd_cmd_flags = 0;
 	int sent = nsock->sent, skip = 0;
 
-	iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
+	iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request));
 
 	switch (req_op(req)) {
 	case REQ_OP_DISCARD:
@@ -564,8 +564,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 
 			dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n",
 				req, bvec.bv_len);
-			iov_iter_bvec(&from, ITER_BVEC | WRITE,
-				      &bvec, 1, bvec.bv_len);
+			iov_iter_bvec(&from, WRITE, &bvec, 1, bvec.bv_len);
 			if (skip) {
 				if (skip >= iov_iter_count(&from)) {
 					skip -= iov_iter_count(&from);
@@ -624,7 +623,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	int ret = 0;
 
 	reply.magic = 0;
-	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
+	iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply));
 	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
 	if (result <= 0) {
 		if (!nbd_disconnected(config))
@@ -678,8 +677,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		struct bio_vec bvec;
 
 		rq_for_each_segment(bvec, req, iter) {
-			iov_iter_bvec(&to, ITER_BVEC | READ,
-				      &bvec, 1, bvec.bv_len);
+			iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len);
 			result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
@@ -1073,7 +1071,7 @@ static void send_disconnects(struct nbd_device *nbd)
 	for (i = 0; i < config->num_connections; i++) {
 		struct nbd_sock *nsock = config->socks[i];
 
-		iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
+		iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request));
 		mutex_lock(&nsock->tx_lock);
 		ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
 		if (ret <= 0)

drivers/fsi/fsi-sbefifo.c

@@ -638,7 +638,7 @@ static void sbefifo_collect_async_ffdc(struct sbefifo *sbefifo)
 	}
         ffdc_iov.iov_base = ffdc;
 	ffdc_iov.iov_len = SBEFIFO_MAX_FFDC_SIZE;
-        iov_iter_kvec(&ffdc_iter, WRITE | ITER_KVEC, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE);
+        iov_iter_kvec(&ffdc_iter, WRITE, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE);
 	cmd[0] = cpu_to_be32(2);
 	cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_SBE_FFDC);
 	rc = sbefifo_do_command(sbefifo, cmd, 2, &ffdc_iter);
@@ -735,7 +735,7 @@ int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len,
 	rbytes = (*resp_len) * sizeof(__be32);
 	resp_iov.iov_base = response;
 	resp_iov.iov_len = rbytes;
-        iov_iter_kvec(&resp_iter, WRITE | ITER_KVEC, &resp_iov, 1, rbytes);
+        iov_iter_kvec(&resp_iter, WRITE, &resp_iov, 1, rbytes);
 
 	/* Perform the command */
 	mutex_lock(&sbefifo->lock);

drivers/gpu/drm/amd/display/dc/os_types.h

@@ -40,8 +40,6 @@
 #define LITTLEENDIAN_CPU
 #endif
 
-#undef READ
-#undef WRITE
 #undef FRAME_SIZE
 
 #define dm_output_to_console(fmt, ...) DRM_DEBUG_KMS(fmt, ##__VA_ARGS__)

drivers/isdn/mISDN/l1oip_core.c

@@ -718,8 +718,7 @@ l1oip_socket_thread(void *data)
 		printk(KERN_DEBUG "%s: socket created and open\n",
 		       __func__);
 	while (!signal_pending(current)) {
-		iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1,
-				recvbuf_size);
+		iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, recvbuf_size);
 		recvlen = sock_recvmsg(socket, &msg, 0);
 		if (recvlen > 0) {
 			l1oip_socket_parse(hc, &sin_rx, recvbuf, recvlen);

drivers/misc/vmw_vmci/vmci_queue_pair.c

@@ -3030,7 +3030,7 @@ ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair,
 	if (!qpair || !buf)
 		return VMCI_ERROR_INVALID_ARGS;
 
-	iov_iter_kvec(&from, WRITE | ITER_KVEC, &v, 1, buf_size);
+	iov_iter_kvec(&from, WRITE, &v, 1, buf_size);
 
 	qp_lock(qpair);
 
@@ -3074,7 +3074,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair,
 	if (!qpair || !buf)
 		return VMCI_ERROR_INVALID_ARGS;
 
-	iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size);
+	iov_iter_kvec(&to, READ, &v, 1, buf_size);
 
 	qp_lock(qpair);
 
@@ -3119,7 +3119,7 @@ ssize_t vmci_qpair_peek(struct vmci_qp *qpair,
 	if (!qpair || !buf)
 		return VMCI_ERROR_INVALID_ARGS;
 
-	iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size);
+	iov_iter_kvec(&to, READ, &v, 1, buf_size);
 
 	qp_lock(qpair);
 

drivers/nvme/target/io-cmd-file.c

@@ -101,7 +101,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 		rw = READ;
 	}
 
-	iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count);
+	iov_iter_bvec(&iter, rw, req->f.bvec, nr_segs, count);
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;

drivers/target/iscsi/iscsi_target_util.c

@@ -1245,8 +1245,7 @@ static int iscsit_do_rx_data(
 		return -1;
 
 	memset(&msg, 0, sizeof(struct msghdr));
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC,
-		      count->iov, count->iov_count, data);
+	iov_iter_kvec(&msg.msg_iter, READ, count->iov, count->iov_count, data);
 
 	while (msg_data_left(&msg)) {
 		rx_loop = sock_recvmsg(conn->sock, &msg, MSG_WAITALL);
@@ -1302,8 +1301,7 @@ int tx_data(
 
 	memset(&msg, 0, sizeof(struct msghdr));
 
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC,
-		      iov, iov_count, data);
+	iov_iter_kvec(&msg.msg_iter, WRITE, iov, iov_count, data);
 
 	while (msg_data_left(&msg)) {
 		int tx_loop = sock_sendmsg(conn->sock, &msg);

drivers/target/target_core_file.c

@@ -303,7 +303,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		len += sg->length;
 	}
 
-	iov_iter_bvec(&iter, ITER_BVEC | is_write, bvec, sgl_nents, len);
+	iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len);
 
 	aio_cmd->cmd = cmd;
 	aio_cmd->len = len;
@@ -353,7 +353,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd,
 		len += sg->length;
 	}
 
-	iov_iter_bvec(&iter, ITER_BVEC, bvec, sgl_nents, len);
+	iov_iter_bvec(&iter, READ, bvec, sgl_nents, len);
 	if (is_write)
 		ret = vfs_iter_write(fd, &iter, &pos, 0);
 	else
@@ -490,7 +490,7 @@ fd_execute_write_same(struct se_cmd *cmd)
 		len += se_dev->dev_attrib.block_size;
 	}
 
-	iov_iter_bvec(&iter, ITER_BVEC, bvec, nolb, len);
+	iov_iter_bvec(&iter, READ, bvec, nolb, len);
 	ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0);
 
 	kfree(bvec);

drivers/usb/usbip/usbip_common.c

@@ -309,7 +309,7 @@ int usbip_recv(struct socket *sock, void *buf, int size)
 	if (!sock || !buf || !size)
 		return -EINVAL;
 
-	iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size);
 
 	usbip_dbg_xmit("enter\n");
 

drivers/xen/pvcalls-back.c

@@ -137,13 +137,13 @@ static void pvcalls_conn_back_read(void *opaque)
 	if (masked_prod < masked_cons) {
 		vec[0].iov_base = data->in + masked_prod;
 		vec[0].iov_len = wanted;
-		iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 1, wanted);
+		iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, wanted);
 	} else {
 		vec[0].iov_base = data->in + masked_prod;
 		vec[0].iov_len = array_size - masked_prod;
 		vec[1].iov_base = data->in;
 		vec[1].iov_len = wanted - vec[0].iov_len;
-		iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 2, wanted);
+		iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, wanted);
 	}
 
 	atomic_set(&map->read, 0);
@@ -195,13 +195,13 @@ static void pvcalls_conn_back_write(struct sock_mapping *map)
 	if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) {
 		vec[0].iov_base = data->out + pvcalls_mask(cons, array_size);
 		vec[0].iov_len = size;
-		iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 1, size);
+		iov_iter_kvec(&msg.msg_iter, READ, vec, 1, size);
 	} else {
 		vec[0].iov_base = data->out + pvcalls_mask(cons, array_size);
 		vec[0].iov_len = array_size - pvcalls_mask(cons, array_size);
 		vec[1].iov_base = data->out;
 		vec[1].iov_len = size - vec[0].iov_len;
-		iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 2, size);
+		iov_iter_kvec(&msg.msg_iter, READ, vec, 2, size);
 	}
 
 	atomic_set(&map->write, 0);

fs/9p/vfs_addr.c

@@ -65,7 +65,7 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
 	if (retval == 0)
 		return retval;
 
-	iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE);
+	iov_iter_bvec(&to, READ, &bvec, 1, PAGE_SIZE);
 
 	retval = p9_client_read(fid, page_offset(page), &to, &err);
 	if (err) {
@@ -175,7 +175,7 @@ static int v9fs_vfs_writepage_locked(struct page *page)
 	bvec.bv_page = page;
 	bvec.bv_offset = 0;
 	bvec.bv_len = len;
-	iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len);
+	iov_iter_bvec(&from, WRITE, &bvec, 1, len);
 
 	/* We should have writeback_fid always set */
 	BUG_ON(!v9inode->writeback_fid);

fs/9p/vfs_dir.c

@@ -123,7 +123,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 		if (rdir->tail == rdir->head) {
 			struct iov_iter to;
 			int n;
-			iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen);
+			iov_iter_kvec(&to, READ, &kvec, 1, buflen);
 			n = p9_client_read(file->private_data, ctx->pos, &to,
 					   &err);
 			if (err)

fs/9p/xattr.c

@@ -32,7 +32,7 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
 	struct iov_iter to;
 	int err;
 
-	iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size);
+	iov_iter_kvec(&to, READ, &kvec, 1, buffer_size);
 
 	attr_fid = p9_client_xattrwalk(fid, name, &attr_size);
 	if (IS_ERR(attr_fid)) {
@@ -107,7 +107,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
 	struct iov_iter from;
 	int retval, err;
 
-	iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len);
+	iov_iter_kvec(&from, WRITE, &kvec, 1, value_len);
 
 	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
 		 name, value_len, flags);

fs/afs/Kconfig

@@ -27,3 +27,15 @@ config AFS_FSCACHE
 	help
 	  Say Y here if you want AFS data to be cached locally on disk through
 	  the generic filesystem cache manager
+
+config AFS_DEBUG_CURSOR
+	bool "AFS server cursor debugging"
+	depends on AFS_FS
+	help
+	  Say Y here to cause the contents of a server cursor to be dumped to
+	  the dmesg log if the server rotation algorithm fails to successfully
+	  contact a server.
+
+	  See <file:Documentation/filesystems/afs.txt> for more information.
+
+	  If unsure, say N.

fs/afs/Makefile

@@ -17,6 +17,7 @@ kafs-y := \
 	file.o \
 	flock.o \
 	fsclient.o \
+	fs_probe.o \
 	inode.o \
 	main.o \
 	misc.o \
@@ -29,9 +30,13 @@ kafs-y := \
 	super.o \
 	netdevices.o \
 	vlclient.o \
+	vl_list.o \
+	vl_probe.o \
+	vl_rotate.o \
 	volume.o \
 	write.o \
-	xattr.o
+	xattr.o \
+	yfsclient.o
 
 kafs-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_AFS_FS)  := kafs.o

fs/afs/addr_list.c

@@ -64,19 +64,25 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
 /*
  * Parse a text string consisting of delimited addresses.
  */
-struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
-					   char delim,
-					   unsigned short service,
-					   unsigned short port)
+struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
+					       const char *text, size_t len,
+					       char delim,
+					       unsigned short service,
+					       unsigned short port)
 {
+	struct afs_vlserver_list *vllist;
 	struct afs_addr_list *alist;
 	const char *p, *end = text + len;
+	const char *problem;
 	unsigned int nr = 0;
+	int ret = -ENOMEM;
 
 	_enter("%*.*s,%c", (int)len, (int)len, text, delim);
 
-	if (!len)
+	if (!len) {
+		_leave(" = -EDESTADDRREQ [empty]");
 		return ERR_PTR(-EDESTADDRREQ);
+	}
 
 	if (delim == ':' && (memchr(text, ',', len) || !memchr(text, '.', len)))
 		delim = ',';
@@ -84,18 +90,24 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 	/* Count the addresses */
 	p = text;
 	do {
-		if (!*p)
-			return ERR_PTR(-EINVAL);
+		if (!*p) {
+			problem = "nul";
+			goto inval;
+		}
 		if (*p == delim)
 			continue;
 		nr++;
 		if (*p == '[') {
 			p++;
-			if (p == end)
-				return ERR_PTR(-EINVAL);
+			if (p == end) {
+				problem = "brace1";
+				goto inval;
+			}
 			p = memchr(p, ']', end - p);
-			if (!p)
-				return ERR_PTR(-EINVAL);
+			if (!p) {
+				problem = "brace2";
+				goto inval;
+			}
 			p++;
 			if (p >= end)
 				break;
@@ -109,10 +121,19 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 
 	_debug("%u/%u addresses", nr, AFS_MAX_ADDRESSES);
 
-	alist = afs_alloc_addrlist(nr, service, port);
-	if (!alist)
+	vllist = afs_alloc_vlserver_list(1);
+	if (!vllist)
 		return ERR_PTR(-ENOMEM);
 
+	vllist->nr_servers = 1;
+	vllist->servers[0].server = afs_alloc_vlserver("<dummy>", 7, AFS_VL_PORT);
+	if (!vllist->servers[0].server)
+		goto error_vl;
+
+	alist = afs_alloc_addrlist(nr, service, AFS_VL_PORT);
+	if (!alist)
+		goto error;
+
 	/* Extract the addresses */
 	p = text;
 	do {
@@ -135,17 +156,21 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 					break;
 		}
 
-		if (in4_pton(p, q - p, (u8 *)&x[0], -1, &stop))
+		if (in4_pton(p, q - p, (u8 *)&x[0], -1, &stop)) {
 			family = AF_INET;
-		else if (in6_pton(p, q - p, (u8 *)x, -1, &stop))
+		} else if (in6_pton(p, q - p, (u8 *)x, -1, &stop)) {
 			family = AF_INET6;
-		else
+		} else {
+			problem = "family";
 			goto bad_address;
+		}
 
-		if (stop != q)
+		p = q;
+		if (stop != p) {
+			problem = "nostop";
 			goto bad_address;
+		}
 
-		p = q;
 		if (q < end && *q == ']')
 			p++;
 
@@ -154,18 +179,23 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 				/* Port number specification "+1234" */
 				xport = 0;
 				p++;
-				if (p >= end || !isdigit(*p))
+				if (p >= end || !isdigit(*p)) {
+					problem = "port";
 					goto bad_address;
+				}
 				do {
 					xport *= 10;
 					xport += *p - '0';
-					if (xport > 65535)
+					if (xport > 65535) {
+						problem = "pval";
 						goto bad_address;
+					}
 					p++;
 				} while (p < end && isdigit(*p));
 			} else if (*p == delim) {
 				p++;
 			} else {
+				problem = "weird";
 				goto bad_address;
 			}
 		}
@@ -177,12 +207,23 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 
 	} while (p < end);
 
+	rcu_assign_pointer(vllist->servers[0].server->addresses, alist);
 	_leave(" = [nr %u]", alist->nr_addrs);
-	return alist;
+	return vllist;
 
-bad_address:
-	kfree(alist);
+inval:
+	_leave(" = -EINVAL [%s %zu %*.*s]",
+	       problem, p - text, (int)len, (int)len, text);
 	return ERR_PTR(-EINVAL);
+bad_address:
+	_leave(" = -EINVAL [%s %zu %*.*s]",
+	       problem, p - text, (int)len, (int)len, text);
+	ret = -EINVAL;
+error:
+	afs_put_addrlist(alist);
+error_vl:
+	afs_put_vlserverlist(net, vllist);
+	return ERR_PTR(ret);
 }
 
 /*
@@ -201,30 +242,34 @@ static int afs_cmp_addr_list(const struct afs_addr_list *a1,
 /*
  * Perform a DNS query for VL servers and build a up an address list.
  */
-struct afs_addr_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry)
+struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry)
 {
-	struct afs_addr_list *alist;
-	char *vllist = NULL;
+	struct afs_vlserver_list *vllist;
+	char *result = NULL;
 	int ret;
 
 	_enter("%s", cell->name);
 
-	ret = dns_query("afsdb", cell->name, cell->name_len,
-			"", &vllist, _expiry);
-	if (ret < 0)
+	ret = dns_query("afsdb", cell->name, cell->name_len, "srv=1",
+			&result, _expiry);
+	if (ret < 0) {
+		_leave(" = %d [dns]", ret);
 		return ERR_PTR(ret);
-
-	alist = afs_parse_text_addrs(vllist, strlen(vllist), ',',
-				     VL_SERVICE, AFS_VL_PORT);
-	if (IS_ERR(alist)) {
-		kfree(vllist);
-		if (alist != ERR_PTR(-ENOMEM))
-			pr_err("Failed to parse DNS data\n");
-		return alist;
 	}
 
-	kfree(vllist);
-	return alist;
+	if (*_expiry == 0)
+		*_expiry = ktime_get_real_seconds() + 60;
+
+	if (ret > 1 && result[0] == 0)
+		vllist = afs_extract_vlserver_list(cell, result, ret);
+	else
+		vllist = afs_parse_text_addrs(cell->net, result, ret, ',',
+					      VL_SERVICE, AFS_VL_PORT);
+	kfree(result);
+	if (IS_ERR(vllist) && vllist != ERR_PTR(-ENOMEM))
+		pr_err("Failed to parse DNS data %ld\n", PTR_ERR(vllist));
+
+	return vllist;
 }
 
 /*
@@ -258,6 +303,8 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
 	srx = &alist->addrs[i];
+	srx->srx_family = AF_RXRPC;
+	srx->transport_type = SOCK_DGRAM;
 	srx->transport_len = sizeof(srx->transport.sin);
 	srx->transport.sin.sin_family = AF_INET;
 	srx->transport.sin.sin_port = htons(port);
@@ -296,6 +343,8 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
 	srx = &alist->addrs[i];
+	srx->srx_family = AF_RXRPC;
+	srx->transport_type = SOCK_DGRAM;
 	srx->transport_len = sizeof(srx->transport.sin6);
 	srx->transport.sin6.sin6_family = AF_INET6;
 	srx->transport.sin6.sin6_port = htons(port);
@@ -308,25 +357,33 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
  */
 bool afs_iterate_addresses(struct afs_addr_cursor *ac)
 {
-	_enter("%hu+%hd", ac->start, (short)ac->index);
+	unsigned long set, failed;
+	int index;
 
 	if (!ac->alist)
 		return false;
 
-	if (ac->begun) {
-		ac->index++;
-		if (ac->index == ac->alist->nr_addrs)
-			ac->index = 0;
+	set = ac->alist->responded;
+	failed = ac->alist->failed;
+	_enter("%lx-%lx-%lx,%d", set, failed, ac->tried, ac->index);
 
-		if (ac->index == ac->start) {
-			ac->error = -EDESTADDRREQ;
-			return false;
-		}
-	}
+	ac->nr_iterations++;
+
+	set &= ~(failed | ac->tried);
+
+	if (!set)
+		return false;
 
-	ac->begun = true;
+	index = READ_ONCE(ac->alist->preferred);
+	if (test_bit(index, &set))
+		goto selected;
+
+	index = __ffs(set);
+
+selected:
+	ac->index = index;
+	set_bit(index, &ac->tried);
 	ac->responded = false;
-	ac->addr = &ac->alist->addrs[ac->index];
 	return true;
 }
 
@@ -339,53 +396,13 @@ int afs_end_cursor(struct afs_addr_cursor *ac)
 
 	alist = ac->alist;
 	if (alist) {
-		if (ac->responded && ac->index != ac->start)
-			WRITE_ONCE(alist->index, ac->index);
+		if (ac->responded &&
+		    ac->index != alist->preferred &&
+		    test_bit(ac->alist->preferred, &ac->tried))
+			WRITE_ONCE(alist->preferred, ac->index);
 		afs_put_addrlist(alist);
+		ac->alist = NULL;
 	}
 
-	ac->addr = NULL;
-	ac->alist = NULL;
-	ac->begun = false;
 	return ac->error;
 }
-
-/*
- * Set the address cursor for iterating over VL servers.
- */
-int afs_set_vl_cursor(struct afs_addr_cursor *ac, struct afs_cell *cell)
-{
-	struct afs_addr_list *alist;
-	int ret;
-
-	if (!rcu_access_pointer(cell->vl_addrs)) {
-		ret = wait_on_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET,
-				  TASK_INTERRUPTIBLE);
-		if (ret < 0)
-			return ret;
-
-		if (!rcu_access_pointer(cell->vl_addrs) &&
-		    ktime_get_real_seconds() < cell->dns_expiry)
-			return cell->error;
-	}
-
-	read_lock(&cell->vl_addrs_lock);
-	alist = rcu_dereference_protected(cell->vl_addrs,
-					  lockdep_is_held(&cell->vl_addrs_lock));
-	if (alist->nr_addrs > 0)
-		afs_get_addrlist(alist);
-	else
-		alist = NULL;
-	read_unlock(&cell->vl_addrs_lock);
-
-	if (!alist)
-		return -EDESTADDRREQ;
-
-	ac->alist = alist;
-	ac->addr = NULL;
-	ac->start = READ_ONCE(alist->index);
-	ac->index = ac->start;
-	ac->error = 0;
-	ac->begun = false;
-	return 0;
-}