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,
+	iov_iter_bvec(&iter, rw, bvec, segments, blk_rq_bytes(rq));
-		      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 @@ send_pages:
 
 			dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n",
 				req, bvec.bv_len);
-			iov_iter_bvec(&from, ITER_BVEC | WRITE,
+			iov_iter_bvec(&from, WRITE, &bvec, 1, bvec.bv_len);
-				      &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,
+			iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len);
-				      &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,
+		iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, recvbuf_size);
-				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,
+	iov_iter_kvec(&msg.msg_iter, READ, count->iov, count->iov_count, data);
-		      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_iter_kvec(&msg.msg_iter, WRITE, iov, iov_count, data);
-		      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,
+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)
+		if (!*p) {
-			return ERR_PTR(-EINVAL);
+			problem = "nul";
+			goto inval;
+		}
 		if (*p == delim)
 			continue;
 		nr++;
 		if (*p == '[') {
 			p++;
-			if (p == end)
+			if (p == end) {
-				return ERR_PTR(-EINVAL);
+				problem = "brace1";
+				goto inval;
+			}
 			p = memchr(p, ']', end - p);
-			if (!p)
+			if (!p) {
-				return ERR_PTR(-EINVAL);
+				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);
+	vllist = afs_alloc_vlserver_list(1);
-	if (!alist)
+	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 {
-			goto bad_address;
+			problem = "family";
-
-		if (stop != q)
 			goto bad_address;
+		}
 
 		p = q;
+		if (stop != p) {
+			problem = "nostop";
+			goto bad_address;
+		}
+
 		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:
+inval:
-	kfree(alist);
+	_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;
+	struct afs_vlserver_list *vllist;
-	char *vllist = NULL;
+	char *result = NULL;
 	int ret;
 
 	_enter("%s", cell->name);
 
-	ret = dns_query("afsdb", cell->name, cell->name_len,
+	ret = dns_query("afsdb", cell->name, cell->name_len, "srv=1",
-			"", &vllist, _expiry);
+			&result, _expiry);
-	if (ret < 0)
+	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);
+	if (*_expiry == 0)
-	return alist;
+		*_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) {
+	set = ac->alist->responded;
-		ac->index++;
+	failed = ac->alist->failed;
-		if (ac->index == ac->alist->nr_addrs)
+	_enter("%lx-%lx-%lx,%d", set, failed, ac->tried, ac->index);
-			ac->index = 0;
 
-		if (ac->index == ac->start) {
+	ac->nr_iterations++;
-			ac->error = -EDESTADDRREQ;
+
+	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)
+		if (ac->responded &&
-			WRITE_ONCE(alist->index, ac->index);
+		    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;
-}

fs/afs/afs.h

@@ -23,9 +23,9 @@
 #define AFSPATHMAX		1024	/* Maximum length of a pathname plus NUL */
 #define AFSOPAQUEMAX		1024	/* Maximum length of an opaque field */
 
-typedef unsigned			afs_volid_t;
+typedef u64			afs_volid_t;
-typedef unsigned			afs_vnodeid_t;
+typedef u64			afs_vnodeid_t;
-typedef unsigned long long		afs_dataversion_t;
+typedef u64			afs_dataversion_t;
 
 typedef enum {
 	AFSVL_RWVOL,			/* read/write volume */
@@ -52,8 +52,9 @@ typedef enum {
  */
 struct afs_fid {
 	afs_volid_t	vid;		/* volume ID */
-	afs_vnodeid_t	vnode;		/* file index within volume */
+	afs_vnodeid_t	vnode;		/* Lower 64-bits of file index within volume */
-	unsigned	unique;		/* unique ID number (file index version) */
+	u32		vnode_hi;	/* Upper 32-bits of file index */
+	u32		unique;		/* unique ID number (file index version) */
 };
 
 /*
@@ -67,14 +68,14 @@ typedef enum {
 } afs_callback_type_t;
 
 struct afs_callback {
+	time64_t		expires_at;	/* Time at which expires */
 	unsigned		version;	/* Callback version */
-	unsigned		expiry;		/* Time at which expires */
 	afs_callback_type_t	type;		/* Type of callback */
 };
 
 struct afs_callback_break {
 	struct afs_fid		fid;		/* File identifier */
-	struct afs_callback	cb;		/* Callback details */
+	//struct afs_callback	cb;		/* Callback details */
 };
 
 #define AFSCBMAX 50	/* maximum callbacks transferred per bulk op */
@@ -129,19 +130,18 @@ typedef u32 afs_access_t;
 struct afs_file_status {
 	u64			size;		/* file size */
 	afs_dataversion_t	data_version;	/* current data version */
-	time_t			mtime_client;	/* last time client changed data */
+	struct timespec64	mtime_client;	/* Last time client changed data */
-	time_t			mtime_server;	/* last time server changed data */
+	struct timespec64	mtime_server;	/* Last time server changed data */
-	unsigned		abort_code;	/* Abort if bulk-fetching this failed */
+	s64			author;		/* author ID */
-
+	s64			owner;		/* owner ID */
-	afs_file_type_t		type;		/* file type */
+	s64			group;		/* group ID */
-	unsigned		nlink;		/* link count */
-	u32			author;		/* author ID */
-	u32			owner;		/* owner ID */
-	u32			group;		/* group ID */
 	afs_access_t		caller_access;	/* access rights for authenticated caller */
 	afs_access_t		anon_access;	/* access rights for unauthenticated caller */
 	umode_t			mode;		/* UNIX mode */
+	afs_file_type_t		type;		/* file type */
+	u32			nlink;		/* link count */
 	s32			lock_count;	/* file lock count (0=UNLK -1=WRLCK +ve=#RDLCK */
+	u32			abort_code;	/* Abort if bulk-fetching this failed */
 };
 
 /*
@@ -158,25 +158,27 @@ struct afs_file_status {
  * AFS volume synchronisation information
  */
 struct afs_volsync {
-	time_t			creation;	/* volume creation time */
+	time64_t		creation;	/* volume creation time */
 };
 
 /*
  * AFS volume status record
  */
 struct afs_volume_status {
-	u32			vid;		/* volume ID */
+	afs_volid_t		vid;		/* volume ID */
-	u32			parent_id;	/* parent volume ID */
+	afs_volid_t		parent_id;	/* parent volume ID */
 	u8			online;		/* true if volume currently online and available */
 	u8			in_service;	/* true if volume currently in service */
 	u8			blessed;	/* same as in_service */
 	u8			needs_salvage;	/* true if consistency checking required */
 	u32			type;		/* volume type (afs_voltype_t) */
-	u32			min_quota;	/* minimum space set aside (blocks) */
+	u64			min_quota;	/* minimum space set aside (blocks) */
-	u32			max_quota;	/* maximum space this volume may occupy (blocks) */
+	u64			max_quota;	/* maximum space this volume may occupy (blocks) */
-	u32			blocks_in_use;	/* space this volume currently occupies (blocks) */
+	u64			blocks_in_use;	/* space this volume currently occupies (blocks) */
-	u32			part_blocks_avail; /* space available in volume's partition */
+	u64			part_blocks_avail; /* space available in volume's partition */
-	u32			part_max_blocks; /* size of volume's partition */
+	u64			part_max_blocks; /* size of volume's partition */
+	s64			vol_copy_date;
+	s64			vol_backup_date;
 };
 
 #define AFS_BLOCK_SIZE	1024

fs/afs/cache.c

@@ -49,7 +49,7 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 	struct afs_vnode *vnode = cookie_netfs_data;
 	struct afs_vnode_cache_aux aux;
 
-	_enter("{%x,%x,%llx},%p,%u",
+	_enter("{%llx,%x,%llx},%p,%u",
 	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
 	       buffer, buflen);
 

fs/afs/callback.c

@@ -210,12 +210,10 @@ void afs_init_callback_state(struct afs_server *server)
 /*
  * actually break a callback
  */
-void afs_break_callback(struct afs_vnode *vnode)
+void __afs_break_callback(struct afs_vnode *vnode)
 {
 	_enter("");
 
-	write_seqlock(&vnode->cb_lock);
-
 	clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
 	if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
 		vnode->cb_break++;
@@ -230,7 +228,12 @@ void afs_break_callback(struct afs_vnode *vnode)
 			afs_lock_may_be_available(vnode);
 		spin_unlock(&vnode->lock);
 	}
+}
 
+void afs_break_callback(struct afs_vnode *vnode)
+{
+	write_seqlock(&vnode->cb_lock);
+	__afs_break_callback(vnode);
 	write_sequnlock(&vnode->cb_lock);
 }
 
@@ -310,14 +313,10 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
 	/* TODO: Sort the callback break list by volume ID */
 
 	for (; count > 0; callbacks++, count--) {
-		_debug("- Fid { vl=%08x n=%u u=%u }  CB { v=%u x=%u t=%u }",
+		_debug("- Fid { vl=%08llx n=%llu u=%u }",
 		       callbacks->fid.vid,
 		       callbacks->fid.vnode,
-		       callbacks->fid.unique,
+		       callbacks->fid.unique);
-		       callbacks->cb.version,
-		       callbacks->cb.expiry,
-		       callbacks->cb.type
-		       );
 		afs_break_one_callback(server, &callbacks->fid);
 	}
 

fs/afs/cell.c

@@ -20,6 +20,8 @@
 #include "internal.h"
 
 static unsigned __read_mostly afs_cell_gc_delay = 10;
+static unsigned __read_mostly afs_cell_min_ttl = 10 * 60;
+static unsigned __read_mostly afs_cell_max_ttl = 24 * 60 * 60;
 
 static void afs_manage_cell(struct work_struct *);
 
@@ -119,7 +121,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
  */
 static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 				       const char *name, unsigned int namelen,
-				       const char *vllist)
+				       const char *addresses)
 {
 	struct afs_cell *cell;
 	int i, ret;
@@ -134,7 +136,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	if (namelen == 5 && memcmp(name, "@cell", 5) == 0)
 		return ERR_PTR(-EINVAL);
 
-	_enter("%*.*s,%s", namelen, namelen, name, vllist);
+	_enter("%*.*s,%s", namelen, namelen, name, addresses);
 
 	cell = kzalloc(sizeof(struct afs_cell), GFP_KERNEL);
 	if (!cell) {
@@ -153,23 +155,26 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 		       (1 << AFS_CELL_FL_NO_LOOKUP_YET));
 	INIT_LIST_HEAD(&cell->proc_volumes);
 	rwlock_init(&cell->proc_lock);
-	rwlock_init(&cell->vl_addrs_lock);
+	rwlock_init(&cell->vl_servers_lock);
 
 	/* Fill in the VL server list if we were given a list of addresses to
 	 * use.
 	 */
-	if (vllist) {
+	if (addresses) {
-		struct afs_addr_list *alist;
+		struct afs_vlserver_list *vllist;
 
-		alist = afs_parse_text_addrs(vllist, strlen(vllist), ':',
+		vllist = afs_parse_text_addrs(net,
+					      addresses, strlen(addresses), ':',
 					      VL_SERVICE, AFS_VL_PORT);
-		if (IS_ERR(alist)) {
+		if (IS_ERR(vllist)) {
-			ret = PTR_ERR(alist);
+			ret = PTR_ERR(vllist);
 			goto parse_failed;
 		}
 
-		rcu_assign_pointer(cell->vl_addrs, alist);
+		rcu_assign_pointer(cell->vl_servers, vllist);
 		cell->dns_expiry = TIME64_MAX;
+	} else {
+		cell->dns_expiry = ktime_get_real_seconds();
 	}
 
 	_leave(" = %p", cell);
@@ -356,26 +361,40 @@ int afs_cell_init(struct afs_net *net, const char *rootcell)
  */
 static void afs_update_cell(struct afs_cell *cell)
 {
-	struct afs_addr_list *alist, *old;
+	struct afs_vlserver_list *vllist, *old;
-	time64_t now, expiry;
+	unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl);
+	unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl);
+	time64_t now, expiry = 0;
 
 	_enter("%s", cell->name);
 
-	alist = afs_dns_query(cell, &expiry);
+	vllist = afs_dns_query(cell, &expiry);
-	if (IS_ERR(alist)) {
+
-		switch (PTR_ERR(alist)) {
+	now = ktime_get_real_seconds();
+	if (min_ttl > max_ttl)
+		max_ttl = min_ttl;
+	if (expiry < now + min_ttl)
+		expiry = now + min_ttl;
+	else if (expiry > now + max_ttl)
+		expiry = now + max_ttl;
+
+	if (IS_ERR(vllist)) {
+		switch (PTR_ERR(vllist)) {
 		case -ENODATA:
-			/* The DNS said that the cell does not exist */
+		case -EDESTADDRREQ:
+			/* The DNS said that the cell does not exist or there
+			 * weren't any addresses to be had.
+			 */
 			set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
 			clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
-			cell->dns_expiry = ktime_get_real_seconds() + 61;
+			cell->dns_expiry = expiry;
 			break;
 
 		case -EAGAIN:
 		case -ECONNREFUSED:
 		default:
 			set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
-			cell->dns_expiry = ktime_get_real_seconds() + 10;
+			cell->dns_expiry = now + 10;
 			break;
 		}
 
@@ -387,12 +406,12 @@ static void afs_update_cell(struct afs_cell *cell)
 		/* Exclusion on changing vl_addrs is achieved by a
 		 * non-reentrant work item.
 		 */
-		old = rcu_dereference_protected(cell->vl_addrs, true);
+		old = rcu_dereference_protected(cell->vl_servers, true);
-		rcu_assign_pointer(cell->vl_addrs, alist);
+		rcu_assign_pointer(cell->vl_servers, vllist);
 		cell->dns_expiry = expiry;
 
 		if (old)
-			afs_put_addrlist(old);
+			afs_put_vlserverlist(cell->net, old);
 	}
 
 	if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags))
@@ -414,7 +433,7 @@ static void afs_cell_destroy(struct rcu_head *rcu)
 
 	ASSERTCMP(atomic_read(&cell->usage), ==, 0);
 
-	afs_put_addrlist(rcu_access_pointer(cell->vl_addrs));
+	afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers));
 	key_put(cell->anonymous_key);
 	kfree(cell);
 

fs/afs/cmservice.c

@@ -16,6 +16,7 @@
 #include <linux/ip.h>
 #include "internal.h"
 #include "afs_cm.h"
+#include "protocol_yfs.h"
 
 static int afs_deliver_cb_init_call_back_state(struct afs_call *);
 static int afs_deliver_cb_init_call_back_state3(struct afs_call *);
@@ -30,6 +31,8 @@ static void SRXAFSCB_Probe(struct work_struct *);
 static void SRXAFSCB_ProbeUuid(struct work_struct *);
 static void SRXAFSCB_TellMeAboutYourself(struct work_struct *);
 
+static int afs_deliver_yfs_cb_callback(struct afs_call *);
+
 #define CM_NAME(name) \
 	const char afs_SRXCB##name##_name[] __tracepoint_string =	\
 		"CB." #name
@@ -100,13 +103,26 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
 	.work		= SRXAFSCB_TellMeAboutYourself,
 };
 
+/*
+ * YFS CB.CallBack operation type
+ */
+static CM_NAME(YFS_CallBack);
+static const struct afs_call_type afs_SRXYFSCB_CallBack = {
+	.name		= afs_SRXCBYFS_CallBack_name,
+	.deliver	= afs_deliver_yfs_cb_callback,
+	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_CallBack,
+};
+
 /*
  * route an incoming cache manager call
  * - return T if supported, F if not
  */
 bool afs_cm_incoming_call(struct afs_call *call)
 {
-	_enter("{CB.OP %u}", call->operation_ID);
+	_enter("{%u, CB.OP %u}", call->service_id, call->operation_ID);
+
+	call->epoch = rxrpc_kernel_get_epoch(call->net->socket, call->rxcall);
 
 	switch (call->operation_ID) {
 	case CBCallBack:
@@ -127,11 +143,101 @@ bool afs_cm_incoming_call(struct afs_call *call)
 	case CBTellMeAboutYourself:
 		call->type = &afs_SRXCBTellMeAboutYourself;
 		return true;
+	case YFSCBCallBack:
+		if (call->service_id != YFS_CM_SERVICE)
+			return false;
+		call->type = &afs_SRXYFSCB_CallBack;
+		return true;
 	default:
 		return false;
 	}
 }
 
+/*
+ * Record a probe to the cache manager from a server.
+ */
+static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server)
+{
+	_enter("");
+
+	if (test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags) &&
+	    !test_bit(AFS_SERVER_FL_PROBING, &server->flags)) {
+		if (server->cm_epoch == call->epoch)
+			return 0;
+
+		if (!server->probe.said_rebooted) {
+			pr_notice("kAFS: FS rebooted %pU\n", &server->uuid);
+			server->probe.said_rebooted = true;
+		}
+	}
+
+	spin_lock(&server->probe_lock);
+
+	if (!test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) {
+		server->cm_epoch = call->epoch;
+		server->probe.cm_epoch = call->epoch;
+		goto out;
+	}
+
+	if (server->probe.cm_probed &&
+	    call->epoch != server->probe.cm_epoch &&
+	    !server->probe.said_inconsistent) {
+		pr_notice("kAFS: FS endpoints inconsistent %pU\n",
+			  &server->uuid);
+		server->probe.said_inconsistent = true;
+	}
+
+	if (!server->probe.cm_probed || call->epoch == server->cm_epoch)
+		server->probe.cm_epoch = server->cm_epoch;
+
+out:
+	server->probe.cm_probed = true;
+	spin_unlock(&server->probe_lock);
+	return 0;
+}
+
+/*
+ * Find the server record by peer address and record a probe to the cache
+ * manager from a server.
+ */
+static int afs_find_cm_server_by_peer(struct afs_call *call)
+{
+	struct sockaddr_rxrpc srx;
+	struct afs_server *server;
+
+	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+
+	server = afs_find_server(call->net, &srx);
+	if (!server) {
+		trace_afs_cm_no_server(call, &srx);
+		return 0;
+	}
+
+	call->cm_server = server;
+	return afs_record_cm_probe(call, server);
+}
+
+/*
+ * Find the server record by server UUID and record a probe to the cache
+ * manager from a server.
+ */
+static int afs_find_cm_server_by_uuid(struct afs_call *call,
+				      struct afs_uuid *uuid)
+{
+	struct afs_server *server;
+
+	rcu_read_lock();
+	server = afs_find_server_by_uuid(call->net, call->request);
+	rcu_read_unlock();
+	if (!server) {
+		trace_afs_cm_no_server_u(call, call->request);
+		return 0;
+	}
+
+	call->cm_server = server;
+	return afs_record_cm_probe(call, server);
+}
+
 /*
  * Clean up a cache manager call.
  */
@@ -168,7 +274,6 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
 static int afs_deliver_cb_callback(struct afs_call *call)
 {
 	struct afs_callback_break *cb;
-	struct sockaddr_rxrpc srx;
 	__be32 *bp;
 	int ret, loop;
 
@@ -176,32 +281,32 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 
 	switch (call->unmarshall) {
 	case 0:
-		call->offset = 0;
+		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
 		/* extract the FID array and its count in two steps */
 	case 1:
 		_debug("extract FID count");
-		ret = afs_extract_data(call, &call->tmp, 4, true);
+		ret = afs_extract_data(call, true);
 		if (ret < 0)
 			return ret;
 
 		call->count = ntohl(call->tmp);
 		_debug("FID count: %u", call->count);
 		if (call->count > AFSCBMAX)
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_cb_fid_count);
 
 		call->buffer = kmalloc(array3_size(call->count, 3, 4),
 				       GFP_KERNEL);
 		if (!call->buffer)
 			return -ENOMEM;
-		call->offset = 0;
+		afs_extract_to_buf(call, call->count * 3 * 4);
 		call->unmarshall++;
 
 	case 2:
 		_debug("extract FID array");
-		ret = afs_extract_data(call, call->buffer,
+		ret = afs_extract_data(call, true);
-				       call->count * 3 * 4, true);
 		if (ret < 0)
 			return ret;
 
@@ -218,59 +323,46 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 			cb->fid.vid	= ntohl(*bp++);
 			cb->fid.vnode	= ntohl(*bp++);
 			cb->fid.unique	= ntohl(*bp++);
-			cb->cb.type	= AFSCM_CB_UNTYPED;
 		}
 
-		call->offset = 0;
+		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
 		/* extract the callback array and its count in two steps */
 	case 3:
 		_debug("extract CB count");
-		ret = afs_extract_data(call, &call->tmp, 4, true);
+		ret = afs_extract_data(call, true);
 		if (ret < 0)
 			return ret;
 
 		call->count2 = ntohl(call->tmp);
 		_debug("CB count: %u", call->count2);
 		if (call->count2 != call->count && call->count2 != 0)
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
-		call->offset = 0;
+						  afs_eproto_cb_count);
+		call->_iter = &call->iter;
+		iov_iter_discard(&call->iter, READ, call->count2 * 3 * 4);
 		call->unmarshall++;
 
 	case 4:
-		_debug("extract CB array");
+		_debug("extract discard %zu/%u",
-		ret = afs_extract_data(call, call->buffer,
+		       iov_iter_count(&call->iter), call->count2 * 3 * 4);
-				       call->count2 * 3 * 4, false);
+
+		ret = afs_extract_data(call, false);
 		if (ret < 0)
 			return ret;
 
-		_debug("unmarshall CB array");
-		cb = call->request;
-		bp = call->buffer;
-		for (loop = call->count2; loop > 0; loop--, cb++) {
-			cb->cb.version	= ntohl(*bp++);
-			cb->cb.expiry	= ntohl(*bp++);
-			cb->cb.type	= ntohl(*bp++);
-		}
-
-		call->offset = 0;
 		call->unmarshall++;
 	case 5:
 		break;
 	}
 
 	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
-		return -EIO;
+		return afs_io_error(call, afs_io_error_cm_reply);
 
 	/* we'll need the file server record as that tells us which set of
 	 * vnodes to operate upon */
-	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+	return afs_find_cm_server_by_peer(call);
-	call->cm_server = afs_find_server(call->net, &srx);
-	if (!call->cm_server)
-		trace_afs_cm_no_server(call, &srx);
-
-	return afs_queue_call_work(call);
 }
 
 /*
@@ -294,24 +386,18 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
  */
 static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
 {
-	struct sockaddr_rxrpc srx;
 	int ret;
 
 	_enter("");
 
-	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+	afs_extract_discard(call, 0);
-
+	ret = afs_extract_data(call, false);
-	ret = afs_extract_data(call, NULL, 0, false);
 	if (ret < 0)
 		return ret;
 
 	/* we'll need the file server record as that tells us which set of
 	 * vnodes to operate upon */
-	call->cm_server = afs_find_server(call->net, &srx);
+	return afs_find_cm_server_by_peer(call);
-	if (!call->cm_server)
-		trace_afs_cm_no_server(call, &srx);
-
-	return afs_queue_call_work(call);
 }
 
 /*
@@ -330,16 +416,15 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 
 	switch (call->unmarshall) {
 	case 0:
-		call->offset = 0;
 		call->buffer = kmalloc_array(11, sizeof(__be32), GFP_KERNEL);
 		if (!call->buffer)
 			return -ENOMEM;
+		afs_extract_to_buf(call, 11 * sizeof(__be32));
 		call->unmarshall++;
 
 	case 1:
 		_debug("extract UUID");
-		ret = afs_extract_data(call, call->buffer,
+		ret = afs_extract_data(call, false);
-				       11 * sizeof(__be32), false);
 		switch (ret) {
 		case 0:		break;
 		case -EAGAIN:	return 0;
@@ -362,7 +447,6 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		for (loop = 0; loop < 6; loop++)
 			r->node[loop] = ntohl(b[loop + 5]);
 
-		call->offset = 0;
 		call->unmarshall++;
 
 	case 2:
@@ -370,17 +454,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 	}
 
 	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
-		return -EIO;
+		return afs_io_error(call, afs_io_error_cm_reply);
 
 	/* we'll need the file server record as that tells us which set of
 	 * vnodes to operate upon */
-	rcu_read_lock();
+	return afs_find_cm_server_by_uuid(call, call->request);
-	call->cm_server = afs_find_server_by_uuid(call->net, call->request);
-	rcu_read_unlock();
-	if (!call->cm_server)
-		trace_afs_cm_no_server_u(call, call->request);
-
-	return afs_queue_call_work(call);
 }
 
 /*
@@ -405,14 +483,14 @@ static int afs_deliver_cb_probe(struct afs_call *call)
 
 	_enter("");
 
-	ret = afs_extract_data(call, NULL, 0, false);
+	afs_extract_discard(call, 0);
+	ret = afs_extract_data(call, false);
 	if (ret < 0)
 		return ret;
 
 	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
-		return -EIO;
+		return afs_io_error(call, afs_io_error_cm_reply);
-
+	return afs_find_cm_server_by_peer(call);
-	return afs_queue_call_work(call);
 }
 
 /*
@@ -453,16 +531,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 
 	switch (call->unmarshall) {
 	case 0:
-		call->offset = 0;
 		call->buffer = kmalloc_array(11, sizeof(__be32), GFP_KERNEL);
 		if (!call->buffer)
 			return -ENOMEM;
+		afs_extract_to_buf(call, 11 * sizeof(__be32));
 		call->unmarshall++;
 
 	case 1:
 		_debug("extract UUID");
-		ret = afs_extract_data(call, call->buffer,
+		ret = afs_extract_data(call, false);
-				       11 * sizeof(__be32), false);
 		switch (ret) {
 		case 0:		break;
 		case -EAGAIN:	return 0;
@@ -485,7 +562,6 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 		for (loop = 0; loop < 6; loop++)
 			r->node[loop] = ntohl(b[loop + 5]);
 
-		call->offset = 0;
 		call->unmarshall++;
 
 	case 2:
@@ -493,9 +569,8 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 	}
 
 	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
-		return -EIO;
+		return afs_io_error(call, afs_io_error_cm_reply);
-
+	return afs_find_cm_server_by_uuid(call, call->request);
-	return afs_queue_call_work(call);
 }
 
 /*
@@ -570,12 +645,88 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call)
 
 	_enter("");
 
-	ret = afs_extract_data(call, NULL, 0, false);
+	afs_extract_discard(call, 0);
+	ret = afs_extract_data(call, false);
 	if (ret < 0)
 		return ret;
 
 	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
-		return -EIO;
+		return afs_io_error(call, afs_io_error_cm_reply);
-
+	return afs_find_cm_server_by_peer(call);
-	return afs_queue_call_work(call);
+}
+
+/*
+ * deliver request data to a YFS CB.CallBack call
+ */
+static int afs_deliver_yfs_cb_callback(struct afs_call *call)
+{
+	struct afs_callback_break *cb;
+	struct yfs_xdr_YFSFid *bp;
+	size_t size;
+	int ret, loop;
+
+	_enter("{%u}", call->unmarshall);
+
+	switch (call->unmarshall) {
+	case 0:
+		afs_extract_to_tmp(call);
+		call->unmarshall++;
+
+		/* extract the FID array and its count in two steps */
+	case 1:
+		_debug("extract FID count");
+		ret = afs_extract_data(call, true);
+		if (ret < 0)
+			return ret;
+
+		call->count = ntohl(call->tmp);
+		_debug("FID count: %u", call->count);
+		if (call->count > YFSCBMAX)
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_cb_fid_count);
+
+		size = array_size(call->count, sizeof(struct yfs_xdr_YFSFid));
+		call->buffer = kmalloc(size, GFP_KERNEL);
+		if (!call->buffer)
+			return -ENOMEM;
+		afs_extract_to_buf(call, size);
+		call->unmarshall++;
+
+	case 2:
+		_debug("extract FID array");
+		ret = afs_extract_data(call, false);
+		if (ret < 0)
+			return ret;
+
+		_debug("unmarshall FID array");
+		call->request = kcalloc(call->count,
+					sizeof(struct afs_callback_break),
+					GFP_KERNEL);
+		if (!call->request)
+			return -ENOMEM;
+
+		cb = call->request;
+		bp = call->buffer;
+		for (loop = call->count; loop > 0; loop--, cb++) {
+			cb->fid.vid	= xdr_to_u64(bp->volume);
+			cb->fid.vnode	= xdr_to_u64(bp->vnode.lo);
+			cb->fid.vnode_hi = ntohl(bp->vnode.hi);
+			cb->fid.unique	= ntohl(bp->vnode.unique);
+			bp++;
+		}
+
+		afs_extract_to_tmp(call);
+		call->unmarshall++;
+
+	case 3:
+		break;
+	}
+
+	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
+		return afs_io_error(call, afs_io_error_cm_reply);
+
+	/* We'll need the file server record as that tells us which set of
+	 * vnodes to operate upon.
+	 */
+	return afs_find_cm_server_by_peer(call);
 }

fs/afs/dir.c

@@ -138,6 +138,7 @@ static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page,
 			       ntohs(dbuf->blocks[tmp].hdr.magic));
 			trace_afs_dir_check_failed(dvnode, off, i_size);
 			kunmap(page);
+			trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic);
 			goto error;
 		}
 
@@ -190,9 +191,11 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
 retry:
 	i_size = i_size_read(&dvnode->vfs_inode);
 	if (i_size < 2048)
-		return ERR_PTR(-EIO);
+		return ERR_PTR(afs_bad(dvnode, afs_file_error_dir_small));
-	if (i_size > 2048 * 1024)
+	if (i_size > 2048 * 1024) {
+		trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big);
 		return ERR_PTR(-EFBIG);
+	}
 
 	_enter("%llu", i_size);
 
@@ -315,7 +318,8 @@ content_has_grown:
 /*
  * deal with one block in an AFS directory
  */
-static int afs_dir_iterate_block(struct dir_context *ctx,
+static int afs_dir_iterate_block(struct afs_vnode *dvnode,
+				 struct dir_context *ctx,
 				 union afs_xdr_dir_block *block,
 				 unsigned blkoff)
 {
@@ -365,7 +369,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx,
 				       " (len %u/%zu)",
 				       blkoff / sizeof(union afs_xdr_dir_block),
 				       offset, next, tmp, nlen);
-				return -EIO;
+				return afs_bad(dvnode, afs_file_error_dir_over_end);
 			}
 			if (!(block->hdr.bitmap[next / 8] &
 			      (1 << (next % 8)))) {
@@ -373,7 +377,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx,
 				       " %u unmarked extension (len %u/%zu)",
 				       blkoff / sizeof(union afs_xdr_dir_block),
 				       offset, next, tmp, nlen);
-				return -EIO;
+				return afs_bad(dvnode, afs_file_error_dir_unmarked_ext);
 			}
 
 			_debug("ENT[%zu.%u]: ext %u/%zu",
@@ -442,7 +446,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
 		 */
 		page = req->pages[blkoff / PAGE_SIZE];
 		if (!page) {
-			ret = -EIO;
+			ret = afs_bad(dvnode, afs_file_error_dir_missing_page);
 			break;
 		}
 		mark_page_accessed(page);
@@ -455,7 +459,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
 		do {
 			dblock = &dbuf->blocks[(blkoff % PAGE_SIZE) /
 					       sizeof(union afs_xdr_dir_block)];
-			ret = afs_dir_iterate_block(ctx, dblock, blkoff);
+			ret = afs_dir_iterate_block(dvnode, ctx, dblock, blkoff);
 			if (ret != 1) {
 				kunmap(page);
 				goto out;
@@ -548,7 +552,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry,
 	}
 
 	*fid = cookie.fid;
-	_leave(" = 0 { vn=%u u=%u }", fid->vnode, fid->unique);
+	_leave(" = 0 { vn=%llu u=%u }", fid->vnode, fid->unique);
 	return 0;
 }
 
@@ -826,7 +830,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 	struct key *key;
 	int ret;
 
-	_enter("{%x:%u},%p{%pd},",
+	_enter("{%llx:%llu},%p{%pd},",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry, dentry);
 
 	ASSERTCMP(d_inode(dentry), ==, NULL);
@@ -896,7 +900,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 	if (d_really_is_positive(dentry)) {
 		vnode = AFS_FS_I(d_inode(dentry));
-		_enter("{v={%x:%u} n=%pd fl=%lx},",
+		_enter("{v={%llx:%llu} n=%pd fl=%lx},",
 		       vnode->fid.vid, vnode->fid.vnode, dentry,
 		       vnode->flags);
 	} else {
@@ -965,7 +969,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 		/* if the vnode ID has changed, then the dirent points to a
 		 * different file */
 		if (fid.vnode != vnode->fid.vnode) {
-			_debug("%pd: dirent changed [%u != %u]",
+			_debug("%pd: dirent changed [%llu != %llu]",
 			       dentry, fid.vnode,
 			       vnode->fid.vnode);
 			goto not_found;
@@ -1085,6 +1089,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc,
 
 	vnode = AFS_FS_I(inode);
 	set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
+	afs_vnode_commit_status(fc, vnode, 0);
 	d_add(new_dentry, inode);
 }
 
@@ -1104,7 +1109,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	mode |= S_IFDIR;
 
-	_enter("{%x:%u},{%pd},%ho",
+	_enter("{%llx:%llu},{%pd},%ho",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry, mode);
 
 	key = afs_request_key(dvnode->volume->cell);
@@ -1169,12 +1174,12 @@ static void afs_dir_remove_subdir(struct dentry *dentry)
 static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct afs_fs_cursor fc;
-	struct afs_vnode *dvnode = AFS_FS_I(dir);
+	struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL;
 	struct key *key;
 	u64 data_version = dvnode->status.data_version;
 	int ret;
 
-	_enter("{%x:%u},{%pd}",
+	_enter("{%llx:%llu},{%pd}",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry);
 
 	key = afs_request_key(dvnode->volume->cell);
@@ -1183,11 +1188,19 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 		goto error;
 	}
 
+	/* Try to make sure we have a callback promise on the victim. */
+	if (d_really_is_positive(dentry)) {
+		vnode = AFS_FS_I(d_inode(dentry));
+		ret = afs_validate(vnode, key);
+		if (ret < 0)
+			goto error_key;
+	}
+
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
-			afs_fs_remove(&fc, dentry->d_name.name, true,
+			afs_fs_remove(&fc, vnode, dentry->d_name.name, true,
 				      data_version);
 		}
 
@@ -1201,6 +1214,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 		}
 	}
 
+error_key:
 	key_put(key);
 error:
 	return ret;
@@ -1231,7 +1245,9 @@ static int afs_dir_remove_link(struct dentry *dentry, struct key *key,
 	if (d_really_is_positive(dentry)) {
 		struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
 
-		if (dir_valid) {
+		if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
+			/* Already done */
+		} else if (dir_valid) {
 			drop_nlink(&vnode->vfs_inode);
 			if (vnode->vfs_inode.i_nlink == 0) {
 				set_bit(AFS_VNODE_DELETED, &vnode->flags);
@@ -1260,13 +1276,13 @@ static int afs_dir_remove_link(struct dentry *dentry, struct key *key,
 static int afs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct afs_fs_cursor fc;
-	struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode;
+	struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL;
 	struct key *key;
 	unsigned long d_version = (unsigned long)dentry->d_fsdata;
 	u64 data_version = dvnode->status.data_version;
 	int ret;
 
-	_enter("{%x:%u},{%pd}",
+	_enter("{%llx:%llu},{%pd}",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry);
 
 	if (dentry->d_name.len >= AFSNAMEMAX)
@@ -1290,7 +1306,18 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
-			afs_fs_remove(&fc, dentry->d_name.name, false,
+
+			if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) &&
+			    !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) {
+				yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name,
+						    data_version);
+				if (fc.ac.error != -ECONNABORTED ||
+				    fc.ac.abort_code != RXGEN_OPCODE)
+					continue;
+				set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags);
+			}
+
+			afs_fs_remove(&fc, vnode, dentry->d_name.name, false,
 				      data_version);
 		}
 
@@ -1330,7 +1357,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	mode |= S_IFREG;
 
-	_enter("{%x:%u},{%pd},%ho,",
+	_enter("{%llx:%llu},{%pd},%ho,",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry, mode);
 
 	ret = -ENAMETOOLONG;
@@ -1393,7 +1420,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
 	dvnode = AFS_FS_I(dir);
 	data_version = dvnode->status.data_version;
 
-	_enter("{%x:%u},{%x:%u},{%pd}",
+	_enter("{%llx:%llu},{%llx:%llu},{%pd}",
 	       vnode->fid.vid, vnode->fid.vnode,
 	       dvnode->fid.vid, dvnode->fid.vnode,
 	       dentry);
@@ -1464,7 +1491,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 	u64 data_version = dvnode->status.data_version;
 	int ret;
 
-	_enter("{%x:%u},{%pd},%s",
+	_enter("{%llx:%llu},{%pd},%s",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry,
 	       content);
 
@@ -1540,7 +1567,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	orig_data_version = orig_dvnode->status.data_version;
 	new_data_version = new_dvnode->status.data_version;
 
-	_enter("{%x:%u},{%x:%u},{%x:%u},{%pd}",
+	_enter("{%llx:%llu},{%llx:%llu},{%llx:%llu},{%pd}",
 	       orig_dvnode->fid.vid, orig_dvnode->fid.vnode,
 	       vnode->fid.vid, vnode->fid.vnode,
 	       new_dvnode->fid.vid, new_dvnode->fid.vnode,
@@ -1607,7 +1634,7 @@ static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags)
 {
 	struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host);
 
-	_enter("{{%x:%u}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index);
+	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index);
 
 	set_page_private(page, 0);
 	ClearPagePrivate(page);

fs/afs/dynroot.c

@@ -46,7 +46,7 @@ static int afs_probe_cell_name(struct dentry *dentry)
 		return 0;
 	}
 
-	ret = dns_query("afsdb", name, len, "", NULL, NULL);
+	ret = dns_query("afsdb", name, len, "srv=1", NULL, NULL);
 	if (ret == -ENODATA)
 		ret = -EDESTADDRREQ;
 	return ret;
@@ -62,7 +62,7 @@ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir)
 	struct inode *inode;
 	int ret = -ENOENT;
 
-	_enter("%p{%pd}, {%x:%u}",
+	_enter("%p{%pd}, {%llx:%llu}",
 	       dentry, dentry, vnode->fid.vid, vnode->fid.vnode);
 
 	if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))

fs/afs/file.c

@@ -121,7 +121,7 @@ int afs_open(struct inode *inode, struct file *file)
 	struct key *key;
 	int ret;
 
-	_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
+	_enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode);
 
 	key = afs_request_key(vnode->volume->cell);
 	if (IS_ERR(key)) {
@@ -170,7 +170,7 @@ int afs_release(struct inode *inode, struct file *file)
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = file->private_data;
 
-	_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
+	_enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode);
 
 	if ((file->f_mode & FMODE_WRITE))
 		return vfs_fsync(file, 0);
@@ -228,7 +228,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de
 	struct afs_fs_cursor fc;
 	int ret;
 
-	_enter("%s{%x:%u.%u},%x,,,",
+	_enter("%s{%llx:%llu.%u},%x,,,",
 	       vnode->volume->name,
 	       vnode->fid.vid,
 	       vnode->fid.vnode,
@@ -634,7 +634,7 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags)
 	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
 	unsigned long priv;
 
-	_enter("{{%x:%u}[%lu],%lx},%x",
+	_enter("{{%llx:%llu}[%lu],%lx},%x",
 	       vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
 	       gfp_flags);
 

fs/afs/flock.c

@@ -29,7 +29,7 @@ static const struct file_lock_operations afs_lock_ops = {
  */
 void afs_lock_may_be_available(struct afs_vnode *vnode)
 {
-	_enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);
+	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);
 
 	queue_delayed_work(afs_lock_manager, &vnode->lock_work, 0);
 }
@@ -76,7 +76,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key,
 	struct afs_fs_cursor fc;
 	int ret;
 
-	_enter("%s{%x:%u.%u},%x,%u",
+	_enter("%s{%llx:%llu.%u},%x,%u",
 	       vnode->volume->name,
 	       vnode->fid.vid,
 	       vnode->fid.vnode,
@@ -107,7 +107,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key)
 	struct afs_fs_cursor fc;
 	int ret;
 
-	_enter("%s{%x:%u.%u},%x",
+	_enter("%s{%llx:%llu.%u},%x",
 	       vnode->volume->name,
 	       vnode->fid.vid,
 	       vnode->fid.vnode,
@@ -138,7 +138,7 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key)
 	struct afs_fs_cursor fc;
 	int ret;
 
-	_enter("%s{%x:%u.%u},%x",
+	_enter("%s{%llx:%llu.%u},%x",
 	       vnode->volume->name,
 	       vnode->fid.vid,
 	       vnode->fid.vnode,
@@ -175,7 +175,7 @@ void afs_lock_work(struct work_struct *work)
 	struct key *key;
 	int ret;
 
-	_enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);
+	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);
 
 	spin_lock(&vnode->lock);
 
@@ -192,7 +192,7 @@ again:
 		ret = afs_release_lock(vnode, vnode->lock_key);
 		if (ret < 0)
 			printk(KERN_WARNING "AFS:"
-			       " Failed to release lock on {%x:%x} error %d\n",
+			       " Failed to release lock on {%llx:%llx} error %d\n",
 			       vnode->fid.vid, vnode->fid.vnode, ret);
 
 		spin_lock(&vnode->lock);
@@ -229,7 +229,7 @@ again:
 		key_put(key);
 
 		if (ret < 0)
-			pr_warning("AFS: Failed to extend lock on {%x:%x} error %d\n",
+			pr_warning("AFS: Failed to extend lock on {%llx:%llx} error %d\n",
 				   vnode->fid.vid, vnode->fid.vnode, ret);
 
 		spin_lock(&vnode->lock);
@@ -430,7 +430,7 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl)
 	struct key *key = afs_file_key(file);
 	int ret;
 
-	_enter("{%x:%u},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type);
+	_enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type);
 
 	/* only whole-file locks are supported */
 	if (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX)
@@ -582,7 +582,7 @@ static int afs_do_unlk(struct file *file, struct file_lock *fl)
 	struct afs_vnode *vnode = AFS_FS_I(locks_inode(file));
 	int ret;
 
-	_enter("{%x:%u},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type);
+	_enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type);
 
 	/* Flush all pending writes before doing anything with locks. */
 	vfs_fsync(file, 0);
@@ -639,7 +639,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl)
 {
 	struct afs_vnode *vnode = AFS_FS_I(locks_inode(file));
 
-	_enter("{%x:%u},%d,{t=%x,fl=%x,r=%Ld:%Ld}",
+	_enter("{%llx:%llu},%d,{t=%x,fl=%x,r=%Ld:%Ld}",
 	       vnode->fid.vid, vnode->fid.vnode, cmd,
 	       fl->fl_type, fl->fl_flags,
 	       (long long) fl->fl_start, (long long) fl->fl_end);
@@ -662,7 +662,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
 {
 	struct afs_vnode *vnode = AFS_FS_I(locks_inode(file));
 
-	_enter("{%x:%u},%d,{t=%x,fl=%x}",
+	_enter("{%llx:%llu},%d,{t=%x,fl=%x}",
 	       vnode->fid.vid, vnode->fid.vnode, cmd,
 	       fl->fl_type, fl->fl_flags);
 

fs/afs/fs_probe.c

@@ -0,0 +1,270 @@
+/* AFS fileserver probing
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include "afs_fs.h"
+#include "internal.h"
+#include "protocol_yfs.h"
+
+static bool afs_fs_probe_done(struct afs_server *server)
+{
+	if (!atomic_dec_and_test(&server->probe_outstanding))
+		return false;
+
+	wake_up_var(&server->probe_outstanding);
+	clear_bit_unlock(AFS_SERVER_FL_PROBING, &server->flags);
+	wake_up_bit(&server->flags, AFS_SERVER_FL_PROBING);
+	return true;
+}
+
+/*
+ * Process the result of probing a fileserver.  This is called after successful
+ * or failed delivery of an FS.GetCapabilities operation.
+ */
+void afs_fileserver_probe_result(struct afs_call *call)
+{
+	struct afs_addr_list *alist = call->alist;
+	struct afs_server *server = call->reply[0];
+	unsigned int server_index = (long)call->reply[1];
+	unsigned int index = call->addr_ix;
+	unsigned int rtt = UINT_MAX;
+	bool have_result = false;
+	u64 _rtt;
+	int ret = call->error;
+
+	_enter("%pU,%u", &server->uuid, index);
+
+	spin_lock(&server->probe_lock);
+
+	switch (ret) {
+	case 0:
+		server->probe.error = 0;
+		goto responded;
+	case -ECONNABORTED:
+		if (!server->probe.responded) {
+			server->probe.abort_code = call->abort_code;
+			server->probe.error = ret;
+		}
+		goto responded;
+	case -ENOMEM:
+	case -ENONET:
+		server->probe.local_failure = true;
+		afs_io_error(call, afs_io_error_fs_probe_fail);
+		goto out;
+	case -ECONNRESET: /* Responded, but call expired. */
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
+	case -ECONNREFUSED:
+	case -ETIMEDOUT:
+	case -ETIME:
+	default:
+		clear_bit(index, &alist->responded);
+		set_bit(index, &alist->failed);
+		if (!server->probe.responded &&
+		    (server->probe.error == 0 ||
+		     server->probe.error == -ETIMEDOUT ||
+		     server->probe.error == -ETIME))
+			server->probe.error = ret;
+		afs_io_error(call, afs_io_error_fs_probe_fail);
+		goto out;
+	}
+
+responded:
+	set_bit(index, &alist->responded);
+	clear_bit(index, &alist->failed);
+
+	if (call->service_id == YFS_FS_SERVICE) {
+		server->probe.is_yfs = true;
+		set_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
+		alist->addrs[index].srx_service = call->service_id;
+	} else {
+		server->probe.not_yfs = true;
+		if (!server->probe.is_yfs) {
+			clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
+			alist->addrs[index].srx_service = call->service_id;
+		}
+	}
+
+	/* Get the RTT and scale it to fit into a 32-bit value that represents
+	 * over a minute of time so that we can access it with one instruction
+	 * on a 32-bit system.
+	 */
+	_rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
+	_rtt /= 64;
+	rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt;
+	if (rtt < server->probe.rtt) {
+		server->probe.rtt = rtt;
+		alist->preferred = index;
+		have_result = true;
+	}
+
+	smp_wmb(); /* Set rtt before responded. */
+	server->probe.responded = true;
+	set_bit(AFS_SERVER_FL_PROBED, &server->flags);
+out:
+	spin_unlock(&server->probe_lock);
+
+	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
+	       server_index, index, &alist->addrs[index].transport,
+	       (unsigned int)rtt, ret);
+
+	have_result |= afs_fs_probe_done(server);
+	if (have_result) {
+		server->probe.have_result = true;
+		wake_up_var(&server->probe.have_result);
+		wake_up_all(&server->probe_wq);
+	}
+}
+
+/*
+ * Probe all of a fileserver's addresses to find out the best route and to
+ * query its capabilities.
+ */
+static int afs_do_probe_fileserver(struct afs_net *net,
+				   struct afs_server *server,
+				   struct key *key,
+				   unsigned int server_index)
+{
+	struct afs_addr_cursor ac = {
+		.index = 0,
+	};
+	int ret;
+
+	_enter("%pU", &server->uuid);
+
+	read_lock(&server->fs_lock);
+	ac.alist = rcu_dereference_protected(server->addresses,
+					     lockdep_is_held(&server->fs_lock));
+	read_unlock(&server->fs_lock);
+
+	atomic_set(&server->probe_outstanding, ac.alist->nr_addrs);
+	memset(&server->probe, 0, sizeof(server->probe));
+	server->probe.rtt = UINT_MAX;
+
+	for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
+		ret = afs_fs_get_capabilities(net, server, &ac, key, server_index,
+					      true);
+		if (ret != -EINPROGRESS) {
+			afs_fs_probe_done(server);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Send off probes to all unprobed servers.
+ */
+int afs_probe_fileservers(struct afs_net *net, struct key *key,
+			  struct afs_server_list *list)
+{
+	struct afs_server *server;
+	int i, ret;
+
+	for (i = 0; i < list->nr_servers; i++) {
+		server = list->servers[i].server;
+		if (test_bit(AFS_SERVER_FL_PROBED, &server->flags))
+			continue;
+
+		if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags)) {
+			ret = afs_do_probe_fileserver(net, server, key, i);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Wait for the first as-yet untried fileserver to respond.
+ */
+int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
+{
+	struct wait_queue_entry *waits;
+	struct afs_server *server;
+	unsigned int rtt = UINT_MAX;
+	bool have_responders = false;
+	int pref = -1, i;
+
+	_enter("%u,%lx", slist->nr_servers, untried);
+
+	/* Only wait for servers that have a probe outstanding. */
+	for (i = 0; i < slist->nr_servers; i++) {
+		if (test_bit(i, &untried)) {
+			server = slist->servers[i].server;
+			if (!test_bit(AFS_SERVER_FL_PROBING, &server->flags))
+				__clear_bit(i, &untried);
+			if (server->probe.responded)
+				have_responders = true;
+		}
+	}
+	if (have_responders || !untried)
+		return 0;
+
+	waits = kmalloc(array_size(slist->nr_servers, sizeof(*waits)), GFP_KERNEL);
+	if (!waits)
+		return -ENOMEM;
+
+	for (i = 0; i < slist->nr_servers; i++) {
+		if (test_bit(i, &untried)) {
+			server = slist->servers[i].server;
+			init_waitqueue_entry(&waits[i], current);
+			add_wait_queue(&server->probe_wq, &waits[i]);
+		}
+	}
+
+	for (;;) {
+		bool still_probing = false;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		for (i = 0; i < slist->nr_servers; i++) {
+			if (test_bit(i, &untried)) {
+				server = slist->servers[i].server;
+				if (server->probe.responded)
+					goto stop;
+				if (test_bit(AFS_SERVER_FL_PROBING, &server->flags))
+					still_probing = true;
+			}
+		}
+
+		if (!still_probing || unlikely(signal_pending(current)))
+			goto stop;
+		schedule();
+	}
+
+stop:
+	set_current_state(TASK_RUNNING);
+
+	for (i = 0; i < slist->nr_servers; i++) {
+		if (test_bit(i, &untried)) {
+			server = slist->servers[i].server;
+			if (server->probe.responded &&
+			    server->probe.rtt < rtt) {
+				pref = i;
+				rtt = server->probe.rtt;
+			}
+
+			remove_wait_queue(&server->probe_wq, &waits[i]);
+		}
+	}
+
+	kfree(waits);
+
+	if (pref == -1 && signal_pending(current))
+		return -ERESTARTSYS;
+
+	if (pref >= 0)
+		slist->preferred = pref;
+	return 0;
+}

fs/afs/inode.c

@@ -82,7 +82,7 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key)
 	default:
 		printk("kAFS: AFS vnode with undefined type\n");
 		read_sequnlock_excl(&vnode->cb_lock);
-		return afs_protocol_error(NULL, -EBADMSG);
+		return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type);
 	}
 
 	inode->i_blocks		= 0;
@@ -100,7 +100,7 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode)
 	struct afs_fs_cursor fc;
 	int ret;
 
-	_enter("%s,{%x:%u.%u,S=%lx}",
+	_enter("%s,{%llx:%llu.%u,S=%lx}",
 	       vnode->volume->name,
 	       vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique,
 	       vnode->flags);
@@ -127,9 +127,9 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode)
 int afs_iget5_test(struct inode *inode, void *opaque)
 {
 	struct afs_iget_data *data = opaque;
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 
-	return inode->i_ino == data->fid.vnode &&
+	return memcmp(&vnode->fid, &data->fid, sizeof(data->fid)) == 0;
-		inode->i_generation == data->fid.unique;
 }
 
 /*
@@ -150,11 +150,14 @@ static int afs_iget5_set(struct inode *inode, void *opaque)
 	struct afs_iget_data *data = opaque;
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 
-	inode->i_ino = data->fid.vnode;
-	inode->i_generation = data->fid.unique;
 	vnode->fid = data->fid;
 	vnode->volume = data->volume;
 
+	/* YFS supports 96-bit vnode IDs, but Linux only supports
+	 * 64-bit inode numbers.
+	 */
+	inode->i_ino = data->fid.vnode;
+	inode->i_generation = data->fid.unique;
 	return 0;
 }
 
@@ -193,7 +196,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	_debug("GOT INODE %p { ino=%lu, vl=%x, vn=%x, u=%x }",
+	_debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }",
 	       inode, inode->i_ino, data.fid.vid, data.fid.vnode,
 	       data.fid.unique);
 
@@ -252,8 +255,8 @@ static void afs_get_inode_cache(struct afs_vnode *vnode)
 
 	key.vnode_id		= vnode->fid.vnode;
 	key.unique		= vnode->fid.unique;
-	key.vnode_id_ext[0]	= 0;
+	key.vnode_id_ext[0]	= vnode->fid.vnode >> 32;
-	key.vnode_id_ext[1]	= 0;
+	key.vnode_id_ext[1]	= vnode->fid.vnode_hi;
 	aux.data_version	= vnode->status.data_version;
 
 	vnode->cache = fscache_acquire_cookie(vnode->volume->cache,
@@ -277,7 +280,7 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 	struct inode *inode;
 	int ret;
 
-	_enter(",{%x:%u.%u},,", fid->vid, fid->vnode, fid->unique);
+	_enter(",{%llx:%llu.%u},,", fid->vid, fid->vnode, fid->unique);
 
 	as = sb->s_fs_info;
 	data.volume = as->volume;
@@ -289,7 +292,7 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	_debug("GOT INODE %p { vl=%x vn=%x, u=%x }",
+	_debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }",
 	       inode, fid->vid, fid->vnode, fid->unique);
 
 	vnode = AFS_FS_I(inode);
@@ -314,11 +317,11 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 			 * didn't give us a callback) */
 			vnode->cb_version = 0;
 			vnode->cb_type = 0;
-			vnode->cb_expires_at = 0;
+			vnode->cb_expires_at = ktime_get();
 		} else {
 			vnode->cb_version = cb->version;
 			vnode->cb_type = cb->type;
-			vnode->cb_expires_at = cb->expiry;
+			vnode->cb_expires_at = cb->expires_at;
 			vnode->cb_interest = afs_get_cb_interest(cbi);
 			set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
 		}
@@ -352,7 +355,7 @@ bad_inode:
  */
 void afs_zap_data(struct afs_vnode *vnode)
 {
-	_enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);
+	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);
 
 #ifdef CONFIG_AFS_FSCACHE
 	fscache_invalidate(vnode->cache);
@@ -382,7 +385,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	bool valid = false;
 	int ret;
 
-	_enter("{v={%x:%u} fl=%lx},%x",
+	_enter("{v={%llx:%llu} fl=%lx},%x",
 	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
 	       key_serial(key));
 
@@ -501,7 +504,7 @@ void afs_evict_inode(struct inode *inode)
 
 	vnode = AFS_FS_I(inode);
 
-	_enter("{%x:%u.%d}",
+	_enter("{%llx:%llu.%d}",
 	       vnode->fid.vid,
 	       vnode->fid.vnode,
 	       vnode->fid.unique);
@@ -550,7 +553,7 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
 	struct key *key;
 	int ret;
 
-	_enter("{%x:%u},{n=%pd},%x",
+	_enter("{%llx:%llu},{n=%pd},%x",
 	       vnode->fid.vid, vnode->fid.vnode, dentry,
 	       attr->ia_valid);
 

fs/afs/internal.h

@@ -22,6 +22,7 @@
 #include <linux/backing-dev.h>
 #include <linux/uuid.h>
 #include <linux/mm_types.h>
+#include <linux/dns_resolver.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/sock.h>
@@ -75,10 +76,13 @@ struct afs_addr_list {
 	u32			version;	/* Version */
 	unsigned char		max_addrs;
 	unsigned char		nr_addrs;
-	unsigned char		index;		/* Address currently in use */
+	unsigned char		preferred;	/* Preferred address */
 	unsigned char		nr_ipv4;	/* Number of IPv4 addresses */
+	enum dns_record_source	source:8;
+	enum dns_lookup_status	status:8;
 	unsigned long		probed;		/* Mask of servers that have been probed */
-	unsigned long		yfs;		/* Mask of servers that are YFS */
+	unsigned long		failed;		/* Mask of addrs that failed locally/ICMP */
+	unsigned long		responded;	/* Mask of addrs that responded */
 	struct sockaddr_rxrpc	addrs[];
 #define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8))
 };
@@ -88,6 +92,7 @@ struct afs_addr_list {
  */
 struct afs_call {
 	const struct afs_call_type *type;	/* type of call */
+	struct afs_addr_list	*alist;		/* Address is alist[addr_ix] */
 	wait_queue_head_t	waitq;		/* processes awaiting completion */
 	struct work_struct	async_work;	/* async I/O processor */
 	struct work_struct	work;		/* actual work processor */
@@ -98,16 +103,22 @@ struct afs_call {
 	struct afs_cb_interest	*cbi;		/* Callback interest for server used */
 	void			*request;	/* request data (first part) */
 	struct address_space	*mapping;	/* Pages being written from */
+	struct iov_iter		iter;		/* Buffer iterator */
+	struct iov_iter		*_iter;		/* Iterator currently in use */
+	union {	/* Convenience for ->iter */
+		struct kvec	kvec[1];
+		struct bio_vec	bvec[1];
+	};
 	void			*buffer;	/* reply receive buffer */
 	void			*reply[4];	/* Where to put the reply */
 	pgoff_t			first;		/* first page in mapping to deal with */
 	pgoff_t			last;		/* last page in mapping to deal with */
-	size_t			offset;		/* offset into received data store */
 	atomic_t		usage;
 	enum afs_call_state	state;
 	spinlock_t		state_lock;
 	int			error;		/* error code */
 	u32			abort_code;	/* Remote abort ID or 0 */
+	u32			epoch;
 	unsigned		request_size;	/* size of request data */
 	unsigned		reply_max;	/* maximum size of reply */
 	unsigned		first_offset;	/* offset into mapping[first] */
@@ -117,19 +128,28 @@ struct afs_call {
 		unsigned	count2;		/* count used in unmarshalling */
 	};
 	unsigned char		unmarshall;	/* unmarshalling phase */
+	unsigned char		addr_ix;	/* Address in ->alist */
 	bool			incoming;	/* T if incoming call */
 	bool			send_pages;	/* T if data from mapping should be sent */
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			ret_reply0;	/* T if should return reply[0] on success */
 	bool			upgrade;	/* T to request service upgrade */
+	bool			want_reply_time; /* T if want reply_time */
 	u16			service_id;	/* Actual service ID (after upgrade) */
 	unsigned int		debug_id;	/* Trace ID */
 	u32			operation_ID;	/* operation ID for an incoming call */
 	u32			count;		/* count for use in unmarshalling */
-	__be32			tmp;		/* place to extract temporary data */
+	union {					/* place to extract temporary data */
+		struct {
+			__be32	tmp_u;
+			__be32	tmp;
+		} __attribute__((packed));
+		__be64		tmp64;
+	};
 	afs_dataversion_t	expected_version; /* Updated version expected from store */
 	afs_dataversion_t	expected_version_2; /* 2nd updated version expected from store */
+	ktime_t			reply_time;	/* Time of first reply packet */
 };
 
 struct afs_call_type {
@@ -146,6 +166,9 @@ struct afs_call_type {
 
 	/* Work function */
 	void (*work)(struct work_struct *work);
+
+	/* Call done function (gets called immediately on success or failure) */
+	void (*done)(struct afs_call *call);
 };
 
 /*
@@ -185,6 +208,7 @@ struct afs_read {
 	refcount_t		usage;
 	unsigned int		index;		/* Which page we're reading into */
 	unsigned int		nr_pages;
+	unsigned int		offset;		/* offset into current page */
 	void (*page_done)(struct afs_call *, struct afs_read *);
 	struct page		**pages;
 	struct page		*array[];
@@ -343,12 +367,69 @@ struct afs_cell {
 	rwlock_t		proc_lock;
 
 	/* VL server list. */
-	rwlock_t		vl_addrs_lock;	/* Lock on vl_addrs */
+	rwlock_t		vl_servers_lock; /* Lock on vl_servers */
-	struct afs_addr_list	__rcu *vl_addrs; /* List of VL servers */
+	struct afs_vlserver_list __rcu *vl_servers;
+
 	u8			name_len;	/* Length of name */
 	char			name[64 + 1];	/* Cell name, case-flattened and NUL-padded */
 };
 
+/*
+ * Volume Location server record.
+ */
+struct afs_vlserver {
+	struct rcu_head		rcu;
+	struct afs_addr_list	__rcu *addresses; /* List of addresses for this VL server */
+	unsigned long		flags;
+#define AFS_VLSERVER_FL_PROBED	0		/* The VL server has been probed */
+#define AFS_VLSERVER_FL_PROBING	1		/* VL server is being probed */
+#define AFS_VLSERVER_FL_IS_YFS	2		/* Server is YFS not AFS */
+	rwlock_t		lock;		/* Lock on addresses */
+	atomic_t		usage;
+
+	/* Probe state */
+	wait_queue_head_t	probe_wq;
+	atomic_t		probe_outstanding;
+	spinlock_t		probe_lock;
+	struct {
+		unsigned int	rtt;		/* RTT as ktime/64 */
+		u32		abort_code;
+		short		error;
+		bool		have_result;
+		bool		responded:1;
+		bool		is_yfs:1;
+		bool		not_yfs:1;
+		bool		local_failure:1;
+	} probe;
+
+	u16			port;
+	u16			name_len;	/* Length of name */
+	char			name[];		/* Server name, case-flattened */
+};
+
+/*
+ * Weighted list of Volume Location servers.
+ */
+struct afs_vlserver_entry {
+	u16			priority;	/* Preference (as SRV) */
+	u16			weight;		/* Weight (as SRV) */
+	enum dns_record_source	source:8;
+	enum dns_lookup_status	status:8;
+	struct afs_vlserver	*server;
+};
+
+struct afs_vlserver_list {
+	struct rcu_head		rcu;
+	atomic_t		usage;
+	u8			nr_servers;
+	u8			index;		/* Server currently in use */
+	u8			preferred;	/* Preferred server */
+	enum dns_record_source	source:8;
+	enum dns_lookup_status	status:8;
+	rwlock_t		lock;
+	struct afs_vlserver_entry servers[];
+};
+
 /*
  * Cached VLDB entry.
  *
@@ -403,8 +484,12 @@ struct afs_server {
 #define AFS_SERVER_FL_PROBING	6		/* Fileserver is being probed */
 #define AFS_SERVER_FL_NO_IBULK	7		/* Fileserver doesn't support FS.InlineBulkStatus */
 #define AFS_SERVER_FL_MAY_HAVE_CB 8		/* May have callbacks on this fileserver */
+#define AFS_SERVER_FL_IS_YFS	9		/* Server is YFS not AFS */
+#define AFS_SERVER_FL_NO_RM2	10		/* Fileserver doesn't support YFS.RemoveFile2 */
+#define AFS_SERVER_FL_HAVE_EPOCH 11		/* ->epoch is valid */
 	atomic_t		usage;
 	u32			addr_version;	/* Address list version */
+	u32			cm_epoch;	/* Server RxRPC epoch */
 
 	/* file service access */
 	rwlock_t		fs_lock;	/* access lock */
@@ -413,6 +498,26 @@ struct afs_server {
 	struct hlist_head	cb_volumes;	/* List of volume interests on this server */
 	unsigned		cb_s_break;	/* Break-everything counter. */
 	rwlock_t		cb_break_lock;	/* Volume finding lock */
+
+	/* Probe state */
+	wait_queue_head_t	probe_wq;
+	atomic_t		probe_outstanding;
+	spinlock_t		probe_lock;
+	struct {
+		unsigned int	rtt;		/* RTT as ktime/64 */
+		u32		abort_code;
+		u32		cm_epoch;
+		short		error;
+		bool		have_result;
+		bool		responded:1;
+		bool		is_yfs:1;
+		bool		not_yfs:1;
+		bool		local_failure:1;
+		bool		no_epoch:1;
+		bool		cm_probed:1;
+		bool		said_rebooted:1;
+		bool		said_inconsistent:1;
+	} probe;
 };
 
 /*
@@ -447,8 +552,8 @@ struct afs_server_entry {
 
 struct afs_server_list {
 	refcount_t		usage;
-	unsigned short		nr_servers;
+	unsigned char		nr_servers;
-	unsigned short		index;		/* Server currently in use */
+	unsigned char		preferred;	/* Preferred server */
 	unsigned short		vnovol_mask;	/* Servers to be skipped due to VNOVOL */
 	unsigned int		seq;		/* Set to ->servers_seq when installed */
 	rwlock_t		lock;
@@ -550,6 +655,15 @@ struct afs_vnode {
 	afs_callback_type_t	cb_type;	/* type of callback */
 };
 
+static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
+{
+#ifdef CONFIG_AFS_FSCACHE
+	return vnode->cache;
+#else
+	return NULL;
+#endif
+}
+
 /*
  * cached security record for one user's attempt to access a vnode
  */
@@ -586,13 +700,31 @@ struct afs_interface {
  */
 struct afs_addr_cursor {
 	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
-	struct sockaddr_rxrpc	*addr;
+	unsigned long		tried;		/* Tried addresses */
-	u32			abort_code;
+	signed char		index;		/* Current address */
-	unsigned short		start;		/* Starting point in alist->addrs[] */
-	unsigned short		index;		/* Wrapping offset from start to current addr */
-	short			error;
-	bool			begun;		/* T if we've begun iteration */
 	bool			responded;	/* T if the current address responded */
+	unsigned short		nr_iterations;	/* Number of address iterations */
+	short			error;
+	u32			abort_code;
+};
+
+/*
+ * Cursor for iterating over a set of volume location servers.
+ */
+struct afs_vl_cursor {
+	struct afs_addr_cursor	ac;
+	struct afs_cell		*cell;		/* The cell we're querying */
+	struct afs_vlserver_list *server_list;	/* Current server list (pins ref) */
+	struct afs_vlserver	*server;	/* Server on which this resides */
+	struct key		*key;		/* Key for the server */
+	unsigned long		untried;	/* Bitmask of untried servers */
+	short			index;		/* Current server */
+	short			error;
+	unsigned short		flags;
+#define AFS_VL_CURSOR_STOP	0x0001		/* Set to cease iteration */
+#define AFS_VL_CURSOR_RETRY	0x0002		/* Set to do a retry */
+#define AFS_VL_CURSOR_RETRIED	0x0004		/* Set if started a retry */
+	unsigned short		nr_iterations;	/* Number of server iterations */
 };
 
 /*
@@ -604,10 +736,11 @@ struct afs_fs_cursor {
 	struct afs_server_list	*server_list;	/* Current server list (pins ref) */
 	struct afs_cb_interest	*cbi;		/* Server on which this resides (pins ref) */
 	struct key		*key;		/* Key for the server */
+	unsigned long		untried;	/* Bitmask of untried servers */
 	unsigned int		cb_break;	/* cb_break + cb_s_break before the call */
 	unsigned int		cb_break_2;	/* cb_break + cb_s_break (2nd vnode) */
-	unsigned char		start;		/* Initial index in server list */
+	short			index;		/* Current server */
-	unsigned char		index;		/* Number of servers tried beyond start */
+	short			error;
 	unsigned short		flags;
 #define AFS_FS_CURSOR_STOP	0x0001		/* Set to cease iteration */
 #define AFS_FS_CURSOR_VBUSY	0x0002		/* Set if seen VBUSY */
@@ -615,6 +748,7 @@ struct afs_fs_cursor {
 #define AFS_FS_CURSOR_VNOVOL	0x0008		/* Set if seen VNOVOL */
 #define AFS_FS_CURSOR_CUR_ONLY	0x0010		/* Set if current server only (file lock held) */
 #define AFS_FS_CURSOR_NO_VSLEEP	0x0020		/* Set to prevent sleep on VBUSY, VOFFLINE, ... */
+	unsigned short		nr_iterations;	/* Number of server iterations */
 };
 
 /*
@@ -640,12 +774,12 @@ extern struct afs_addr_list *afs_alloc_addrlist(unsigned int,
 						unsigned short,
 						unsigned short);
 extern void afs_put_addrlist(struct afs_addr_list *);
-extern struct afs_addr_list *afs_parse_text_addrs(const char *, size_t, char,
+extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *,
+						      const char *, size_t, char,
 						      unsigned short, unsigned short);
-extern struct afs_addr_list *afs_dns_query(struct afs_cell *, time64_t *);
+extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *);
 extern bool afs_iterate_addresses(struct afs_addr_cursor *);
 extern int afs_end_cursor(struct afs_addr_cursor *);
-extern int afs_set_vl_cursor(struct afs_addr_cursor *, struct afs_cell *);
 
 extern void afs_merge_fs_addr4(struct afs_addr_list *, __be32, u16);
 extern void afs_merge_fs_addr6(struct afs_addr_list *, __be32 *, u16);
@@ -668,6 +802,7 @@ extern struct fscache_cookie_def afs_vnode_cache_index_def;
  * callback.c
  */
 extern void afs_init_callback_state(struct afs_server *);
+extern void __afs_break_callback(struct afs_vnode *);
 extern void afs_break_callback(struct afs_vnode *);
 extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*);
 
@@ -688,10 +823,13 @@ static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
 	return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
 }
 
-static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode,
+static inline bool afs_cb_is_broken(unsigned int cb_break,
-					    struct afs_cb_interest *cbi)
+				    const struct afs_vnode *vnode,
+				    const struct afs_cb_interest *cbi)
 {
-	return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break;
+	return !cbi || cb_break != (vnode->cb_break +
+				    cbi->server->cb_s_break +
+				    vnode->volume->cb_v_break);
 }
 
 /*
@@ -781,7 +919,7 @@ extern int afs_fs_give_up_callbacks(struct afs_net *, struct afs_server *);
 extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *);
 extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, u64,
 			 struct afs_fid *, struct afs_file_status *, struct afs_callback *);
-extern int afs_fs_remove(struct afs_fs_cursor *, const char *, bool, u64);
+extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64);
 extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64);
 extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64,
 			  struct afs_fid *, struct afs_file_status *);
@@ -797,7 +935,7 @@ extern int afs_fs_release_lock(struct afs_fs_cursor *);
 extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *,
 					struct afs_addr_cursor *, struct key *);
 extern int afs_fs_get_capabilities(struct afs_net *, struct afs_server *,
-				   struct afs_addr_cursor *, struct key *);
+				   struct afs_addr_cursor *, struct key *, unsigned int, bool);
 extern int afs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *,
 				     struct afs_fid *, struct afs_file_status *,
 				     struct afs_callback *, unsigned int,
@@ -806,6 +944,13 @@ extern int afs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *,
 			       struct afs_fid *, struct afs_file_status *,
 			       struct afs_callback *, struct afs_volsync *);
 
+/*
+ * fs_probe.c
+ */
+extern void afs_fileserver_probe_result(struct afs_call *);
+extern int afs_probe_fileservers(struct afs_net *, struct key *, struct afs_server_list *);
+extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long);
+
 /*
  * inode.c
  */
@@ -922,7 +1067,6 @@ extern int __net_init afs_open_socket(struct afs_net *);
 extern void __net_exit afs_close_socket(struct afs_net *);
 extern void afs_charge_preallocation(struct work_struct *);
 extern void afs_put_call(struct afs_call *);
-extern int afs_queue_call_work(struct afs_call *);
 extern long afs_make_call(struct afs_addr_cursor *, struct afs_call *, gfp_t, bool);
 extern struct afs_call *afs_alloc_flat_call(struct afs_net *,
 					    const struct afs_call_type *,
@@ -930,12 +1074,39 @@ extern struct afs_call *afs_alloc_flat_call(struct afs_net *,
 extern void afs_flat_call_destructor(struct afs_call *);
 extern void afs_send_empty_reply(struct afs_call *);
 extern void afs_send_simple_reply(struct afs_call *, const void *, size_t);
-extern int afs_extract_data(struct afs_call *, void *, size_t, bool);
+extern int afs_extract_data(struct afs_call *, bool);
-extern int afs_protocol_error(struct afs_call *, int);
+extern int afs_protocol_error(struct afs_call *, int, enum afs_eproto_cause);
+
+static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size)
+{
+	call->kvec[0].iov_base = buf;
+	call->kvec[0].iov_len = size;
+	iov_iter_kvec(&call->iter, READ, call->kvec, 1, size);
+}
+
+static inline void afs_extract_to_tmp(struct afs_call *call)
+{
+	afs_extract_begin(call, &call->tmp, sizeof(call->tmp));
+}
+
+static inline void afs_extract_to_tmp64(struct afs_call *call)
+{
+	afs_extract_begin(call, &call->tmp64, sizeof(call->tmp64));
+}
+
+static inline void afs_extract_discard(struct afs_call *call, size_t size)
+{
+	iov_iter_discard(&call->iter, READ, size);
+}
+
+static inline void afs_extract_to_buf(struct afs_call *call, size_t size)
+{
+	afs_extract_begin(call, call->buffer, size);
+}
 
 static inline int afs_transfer_reply(struct afs_call *call)
 {
-	return afs_extract_data(call, call->buffer, call->reply_max, false);
+	return afs_extract_data(call, false);
 }
 
 static inline bool afs_check_call_state(struct afs_call *call,
@@ -1012,7 +1183,6 @@ extern void afs_put_server(struct afs_net *, struct afs_server *);
 extern void afs_manage_servers(struct work_struct *);
 extern void afs_servers_timer(struct timer_list *);
 extern void __net_exit afs_purge_servers(struct afs_net *);
-extern bool afs_probe_fileserver(struct afs_fs_cursor *);
 extern bool afs_check_server_record(struct afs_fs_cursor *, struct afs_server *);
 
 /*
@@ -1039,14 +1209,51 @@ extern void afs_fs_exit(void);
 /*
  * vlclient.c
  */
-extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *,
+extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *,
-							 struct afs_addr_cursor *,
+							 const char *, int);
-							 struct key *, const char *, int);
+extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uuid_t *);
-extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *, struct afs_addr_cursor *,
+extern int afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, struct key *,
-						struct key *, const uuid_t *);
+				   struct afs_vlserver *, unsigned int, bool);
-extern int afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, struct key *);
+extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *);
-extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *, struct afs_addr_cursor *,
+
-						     struct key *, const uuid_t *);
+/*
+ * vl_probe.c
+ */
+extern void afs_vlserver_probe_result(struct afs_call *);
+extern int afs_send_vl_probes(struct afs_net *, struct key *, struct afs_vlserver_list *);
+extern int afs_wait_for_vl_probes(struct afs_vlserver_list *, unsigned long);
+
+/*
+ * vl_rotate.c
+ */
+extern bool afs_begin_vlserver_operation(struct afs_vl_cursor *,
+					 struct afs_cell *, struct key *);
+extern bool afs_select_vlserver(struct afs_vl_cursor *);
+extern bool afs_select_current_vlserver(struct afs_vl_cursor *);
+extern int afs_end_vlserver_operation(struct afs_vl_cursor *);
+
+/*
+ * vlserver_list.c
+ */
+static inline struct afs_vlserver *afs_get_vlserver(struct afs_vlserver *vlserver)
+{
+	atomic_inc(&vlserver->usage);
+	return vlserver;
+}
+
+static inline struct afs_vlserver_list *afs_get_vlserverlist(struct afs_vlserver_list *vllist)
+{
+	if (vllist)
+		atomic_inc(&vllist->usage);
+	return vllist;
+}
+
+extern struct afs_vlserver *afs_alloc_vlserver(const char *, size_t, unsigned short);
+extern void afs_put_vlserver(struct afs_net *, struct afs_vlserver *);
+extern struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int);
+extern void afs_put_vlserverlist(struct afs_net *, struct afs_vlserver_list *);
+extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *,
+							   const void *, size_t);
 
 /*
  * volume.c
@@ -1089,6 +1296,36 @@ extern int afs_launder_page(struct page *);
 extern const struct xattr_handler *afs_xattr_handlers[];
 extern ssize_t afs_listxattr(struct dentry *, char *, size_t);
 
+/*
+ * yfsclient.c
+ */
+extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_volsync *, bool);
+extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *);
+extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, u64,
+			      struct afs_fid *, struct afs_file_status *, struct afs_callback *);
+extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, u64,
+			 struct afs_fid *, struct afs_file_status *, struct afs_callback *);
+extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64);
+extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64);
+extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64);
+extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64,
+			  struct afs_fid *, struct afs_file_status *);
+extern int yfs_fs_rename(struct afs_fs_cursor *, const char *,
+			 struct afs_vnode *, const char *, u64, u64);
+extern int yfs_fs_store_data(struct afs_fs_cursor *, struct address_space *,
+			     pgoff_t, pgoff_t, unsigned, unsigned);
+extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *);
+extern int yfs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *);
+extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t);
+extern int yfs_fs_extend_lock(struct afs_fs_cursor *);
+extern int yfs_fs_release_lock(struct afs_fs_cursor *);
+extern int yfs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *,
+			       struct afs_fid *, struct afs_file_status *,
+			       struct afs_callback *, struct afs_volsync *);
+extern int yfs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *,
+				     struct afs_fid *, struct afs_file_status *,
+				     struct afs_callback *, unsigned int,
+				     struct afs_volsync *);
 
 /*
  * Miscellaneous inline functions.
@@ -1120,6 +1357,17 @@ static inline void afs_check_for_remote_deletion(struct afs_fs_cursor *fc,
 	}
 }
 
+static inline int afs_io_error(struct afs_call *call, enum afs_io_error where)
+{
+	trace_afs_io_error(call->debug_id, -EIO, where);
+	return -EIO;
+}
+
+static inline int afs_bad(struct afs_vnode *vnode, enum afs_file_error where)
+{
+	trace_afs_file_error(vnode, -EIO, where);
+	return -EIO;
+}
 
 /*****************************************************************************/
 /*

fs/afs/mntpt.c

@@ -130,9 +130,10 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 			goto error_no_page;
 		}
 
-		ret = -EIO;
+		if (PageError(page)) {
-		if (PageError(page))
+			ret = afs_bad(AFS_FS_I(d_inode(mntpt)), afs_file_error_mntpt);
 			goto error;
+		}
 
 		buf = kmap_atomic(page);
 		memcpy(devname, buf, size);

fs/afs/proc.c

@@ -17,6 +17,11 @@
 #include <linux/uaccess.h>
 #include "internal.h"
 
+struct afs_vl_seq_net_private {
+	struct seq_net_private		seq;	/* Must be first */
+	struct afs_vlserver_list	*vllist;
+};
+
 static inline struct afs_net *afs_seq2net(struct seq_file *m)
 {
 	return afs_net(seq_file_net(m));
@@ -32,16 +37,24 @@ static inline struct afs_net *afs_seq2net_single(struct seq_file *m)
  */
 static int afs_proc_cells_show(struct seq_file *m, void *v)
 {
-	struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link);
+	struct afs_vlserver_list *vllist;
+	struct afs_cell *cell;
 
 	if (v == SEQ_START_TOKEN) {
 		/* display header on line 1 */
-		seq_puts(m, "USE NAME\n");
+		seq_puts(m, "USE    TTL SV NAME\n");
 		return 0;
 	}
 
+	cell = list_entry(v, struct afs_cell, proc_link);
+	vllist = rcu_dereference(cell->vl_servers);
+
 	/* display one cell per line on subsequent lines */
-	seq_printf(m, "%3u %s\n", atomic_read(&cell->usage), cell->name);
+	seq_printf(m, "%3u %6lld %2u %s\n",
+		   atomic_read(&cell->usage),
+		   cell->dns_expiry - ktime_get_real_seconds(),
+		   vllist ? vllist->nr_servers : 0,
+		   cell->name);
 	return 0;
 }
 
@@ -208,7 +221,7 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
 		return 0;
 	}
 
-	seq_printf(m, "%3d %08x %s\n",
+	seq_printf(m, "%3d %08llx %s\n",
 		   atomic_read(&vol->usage), vol->vid,
 		   afs_vol_types[vol->type]);
 
@@ -247,61 +260,102 @@ static const struct seq_operations afs_proc_cell_volumes_ops = {
 	.show	= afs_proc_cell_volumes_show,
 };
 
+static const char *const dns_record_sources[NR__dns_record_source + 1] = {
+	[DNS_RECORD_UNAVAILABLE]	= "unav",
+	[DNS_RECORD_FROM_CONFIG]	= "cfg",
+	[DNS_RECORD_FROM_DNS_A]		= "A",
+	[DNS_RECORD_FROM_DNS_AFSDB]	= "AFSDB",
+	[DNS_RECORD_FROM_DNS_SRV]	= "SRV",
+	[DNS_RECORD_FROM_NSS]		= "nss",
+	[NR__dns_record_source]		= "[weird]"
+};
+
+static const char *const dns_lookup_statuses[NR__dns_lookup_status + 1] = {
+	[DNS_LOOKUP_NOT_DONE]		= "no-lookup",
+	[DNS_LOOKUP_GOOD]		= "good",
+	[DNS_LOOKUP_GOOD_WITH_BAD]	= "good/bad",
+	[DNS_LOOKUP_BAD]		= "bad",
+	[DNS_LOOKUP_GOT_NOT_FOUND]	= "not-found",
+	[DNS_LOOKUP_GOT_LOCAL_FAILURE]	= "local-failure",
+	[DNS_LOOKUP_GOT_TEMP_FAILURE]	= "temp-failure",
+	[DNS_LOOKUP_GOT_NS_FAILURE]	= "ns-failure",
+	[NR__dns_lookup_status]		= "[weird]"
+};
+
 /*
  * Display the list of Volume Location servers we're using for a cell.
  */
 static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 {
-	struct sockaddr_rxrpc *addr = v;
+	const struct afs_vl_seq_net_private *priv = m->private;
+	const struct afs_vlserver_list *vllist = priv->vllist;
+	const struct afs_vlserver_entry *entry;
+	const struct afs_vlserver *vlserver;
+	const struct afs_addr_list *alist;
+	int i;
 
-	/* display header on line 1 */
+	if (v == SEQ_START_TOKEN) {
-	if (v == (void *)1) {
+		seq_printf(m, "# source %s, status %s\n",
-		seq_puts(m, "ADDRESS\n");
+			   dns_record_sources[vllist->source],
+			   dns_lookup_statuses[vllist->status]);
 		return 0;
 	}
 
-	/* display one cell per line on subsequent lines */
+	entry = v;
-	seq_printf(m, "%pISp\n", &addr->transport);
+	vlserver = entry->server;
+	alist = rcu_dereference(vlserver->addresses);
+
+	seq_printf(m, "%s [p=%hu w=%hu s=%s,%s]:\n",
+		   vlserver->name, entry->priority, entry->weight,
+		   dns_record_sources[alist ? alist->source : entry->source],
+		   dns_lookup_statuses[alist ? alist->status : entry->status]);
+	if (alist) {
+		for (i = 0; i < alist->nr_addrs; i++)
+			seq_printf(m, " %c %pISpc\n",
+				   alist->preferred == i ? '>' : '-',
+				   &alist->addrs[i].transport);
+	}
 	return 0;
 }
 
 static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos)
 	__acquires(rcu)
 {
-	struct afs_addr_list *alist;
+	struct afs_vl_seq_net_private *priv = m->private;
+	struct afs_vlserver_list *vllist;
 	struct afs_cell *cell = PDE_DATA(file_inode(m->file));
 	loff_t pos = *_pos;
 
 	rcu_read_lock();
 
-	alist = rcu_dereference(cell->vl_addrs);
+	vllist = rcu_dereference(cell->vl_servers);
+	priv->vllist = vllist;
 
-	/* allow for the header line */
+	if (pos < 0)
-	if (!pos)
+		*_pos = pos = 0;
-		return (void *) 1;
+	if (pos == 0)
-	pos--;
+		return SEQ_START_TOKEN;
 
-	if (!alist || pos >= alist->nr_addrs)
+	if (!vllist || pos - 1 >= vllist->nr_servers)
 		return NULL;
 
-	return alist->addrs + pos;
+	return &vllist->servers[pos - 1];
 }
 
 static void *afs_proc_cell_vlservers_next(struct seq_file *m, void *v,
 					  loff_t *_pos)
 {
-	struct afs_addr_list *alist;
+	struct afs_vl_seq_net_private *priv = m->private;
-	struct afs_cell *cell = PDE_DATA(file_inode(m->file));
+	struct afs_vlserver_list *vllist = priv->vllist;
 	loff_t pos;
 
-	alist = rcu_dereference(cell->vl_addrs);
-
 	pos = *_pos;
-	(*_pos)++;
+	pos++;
-	if (!alist || pos >= alist->nr_addrs)
+	*_pos = pos;
+	if (!vllist || pos - 1 >= vllist->nr_servers)
 		return NULL;
 
-	return alist->addrs + pos;
+	return &vllist->servers[pos - 1];
 }
 
 static void afs_proc_cell_vlservers_stop(struct seq_file *m, void *v)
@@ -337,11 +391,11 @@ static int afs_proc_servers_show(struct seq_file *m, void *v)
 		   &server->uuid,
 		   atomic_read(&server->usage),
 		   &alist->addrs[0].transport,
-		   alist->index == 0 ? "*" : "");
+		   alist->preferred == 0 ? "*" : "");
 	for (i = 1; i < alist->nr_addrs; i++)
 		seq_printf(m, "                                         %pISpc%s\n",
 			   &alist->addrs[i].transport,
-			   alist->index == i ? "*" : "");
+			   alist->preferred == i ? "*" : "");
 	return 0;
 }
 
@@ -562,7 +616,7 @@ int afs_proc_cell_setup(struct afs_cell *cell)
 
 	if (!proc_create_net_data("vlservers", 0444, dir,
 				  &afs_proc_cell_vlservers_ops,
-				  sizeof(struct seq_net_private),
+				  sizeof(struct afs_vl_seq_net_private),
 				  cell) ||
 	    !proc_create_net_data("volumes", 0444, dir,
 				  &afs_proc_cell_volumes_ops,

fs/afs/protocol_yfs.h

@@ -0,0 +1,163 @@
+/* YFS protocol bits
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define YFS_FS_SERVICE	2500
+#define YFS_CM_SERVICE	2501
+
+#define YFSCBMAX 1024
+
+enum YFS_CM_Operations {
+	YFSCBProbe		= 206,	/* probe client */
+	YFSCBGetLock		= 207,	/* get contents of CM lock table */
+	YFSCBXStatsVersion	= 209,	/* get version of extended statistics */
+	YFSCBGetXStats		= 210,	/* get contents of extended statistics data */
+	YFSCBInitCallBackState3	= 213,	/* initialise callback state, version 3 */
+	YFSCBProbeUuid		= 214,	/* check the client hasn't rebooted */
+	YFSCBGetServerPrefs	= 215,
+	YFSCBGetCellServDV	= 216,
+	YFSCBGetLocalCell	= 217,
+	YFSCBGetCacheConfig	= 218,
+	YFSCBGetCellByNum	= 65537,
+	YFSCBTellMeAboutYourself = 65538, /* get client capabilities */
+	YFSCBCallBack		= 64204,
+};
+
+enum YFS_FS_Operations {
+	YFSFETCHACL		= 64131, /* YFS Fetch file ACL */
+	YFSFETCHSTATUS		= 64132, /* YFS Fetch file status */
+	YFSSTOREACL		= 64134, /* YFS Store file ACL */
+	YFSSTORESTATUS		= 64135, /* YFS Store file status */
+	YFSREMOVEFILE		= 64136, /* YFS Remove a file */
+	YFSCREATEFILE		= 64137, /* YFS Create a file */
+	YFSRENAME		= 64138, /* YFS Rename or move a file or directory */
+	YFSSYMLINK		= 64139, /* YFS Create a symbolic link */
+	YFSLINK			= 64140, /* YFS Create a hard link */
+	YFSMAKEDIR		= 64141, /* YFS Create a directory */
+	YFSREMOVEDIR		= 64142, /* YFS Remove a directory */
+	YFSGETVOLUMESTATUS	= 64149, /* YFS Get volume status information */
+	YFSSETVOLUMESTATUS	= 64150, /* YFS Set volume status information */
+	YFSSETLOCK		= 64156, /* YFS Request a file lock */
+	YFSEXTENDLOCK		= 64157, /* YFS Extend a file lock */
+	YFSRELEASELOCK		= 64158, /* YFS Release a file lock */
+	YFSLOOKUP		= 64161, /* YFS lookup file in directory */
+	YFSFLUSHCPS		= 64165,
+	YFSFETCHOPAQUEACL	= 64168,
+	YFSWHOAMI		= 64170,
+	YFSREMOVEACL		= 64171,
+	YFSREMOVEFILE2		= 64173,
+	YFSSTOREOPAQUEACL2	= 64174,
+	YFSINLINEBULKSTATUS	= 64536, /* YFS Fetch multiple file statuses with errors */
+	YFSFETCHDATA64		= 64537, /* YFS Fetch file data */
+	YFSSTOREDATA64		= 64538, /* YFS Store file data */
+	YFSUPDATESYMLINK	= 64540,
+};
+
+struct yfs_xdr_u64 {
+	__be32			msw;
+	__be32			lsw;
+} __packed;
+
+static inline u64 xdr_to_u64(const struct yfs_xdr_u64 x)
+{
+	return ((u64)ntohl(x.msw) << 32) | ntohl(x.lsw);
+}
+
+static inline struct yfs_xdr_u64 u64_to_xdr(const u64 x)
+{
+	return (struct yfs_xdr_u64){ .msw = htonl(x >> 32), .lsw = htonl(x) };
+}
+
+struct yfs_xdr_vnode {
+	struct yfs_xdr_u64	lo;
+	__be32			hi;
+	__be32			unique;
+} __packed;
+
+struct yfs_xdr_YFSFid {
+	struct yfs_xdr_u64	volume;
+	struct yfs_xdr_vnode	vnode;
+} __packed;
+
+
+struct yfs_xdr_YFSFetchStatus {
+	__be32			type;
+	__be32			nlink;
+	struct yfs_xdr_u64	size;
+	struct yfs_xdr_u64	data_version;
+	struct yfs_xdr_u64	author;
+	struct yfs_xdr_u64	owner;
+	struct yfs_xdr_u64	group;
+	__be32			mode;
+	__be32			caller_access;
+	__be32			anon_access;
+	struct yfs_xdr_vnode	parent;
+	__be32			data_access_protocol;
+	struct yfs_xdr_u64	mtime_client;
+	struct yfs_xdr_u64	mtime_server;
+	__be32			lock_count;
+	__be32			abort_code;
+} __packed;
+
+struct yfs_xdr_YFSCallBack {
+	__be32			version;
+	struct yfs_xdr_u64	expiration_time;
+	__be32			type;
+} __packed;
+
+struct yfs_xdr_YFSStoreStatus {
+	__be32			mask;
+	__be32			mode;
+	struct yfs_xdr_u64	mtime_client;
+	struct yfs_xdr_u64	owner;
+	struct yfs_xdr_u64	group;
+} __packed;
+
+struct yfs_xdr_RPCFlags {
+	__be32			rpc_flags;
+} __packed;
+
+struct yfs_xdr_YFSVolSync {
+	struct yfs_xdr_u64	vol_creation_date;
+	struct yfs_xdr_u64	vol_update_date;
+	struct yfs_xdr_u64	max_quota;
+	struct yfs_xdr_u64	blocks_in_use;
+	struct yfs_xdr_u64	blocks_avail;
+} __packed;
+
+enum yfs_volume_type {
+	yfs_volume_type_ro = 0,
+	yfs_volume_type_rw = 1,
+};
+
+#define yfs_FVSOnline		0x1
+#define yfs_FVSInservice	0x2
+#define yfs_FVSBlessed		0x4
+#define yfs_FVSNeedsSalvage	0x8
+
+struct yfs_xdr_YFSFetchVolumeStatus {
+	struct yfs_xdr_u64	vid;
+	struct yfs_xdr_u64	parent_id;
+	__be32			flags;
+	__be32			type;
+	struct yfs_xdr_u64	max_quota;
+	struct yfs_xdr_u64	blocks_in_use;
+	struct yfs_xdr_u64	part_blocks_avail;
+	struct yfs_xdr_u64	part_max_blocks;
+	struct yfs_xdr_u64	vol_copy_date;
+	struct yfs_xdr_u64	vol_backup_date;
+} __packed;
+
+struct yfs_xdr_YFSStoreVolumeStatus {
+	__be32			mask;
+	struct yfs_xdr_u64	min_quota;
+	struct yfs_xdr_u64	max_quota;
+	struct yfs_xdr_u64	file_quota;
+} __packed;

fs/afs/rotate.c

@@ -18,14 +18,6 @@
 #include "internal.h"
 #include "afs_fs.h"
 
-/*
- * Initialise a filesystem server cursor for iterating over FS servers.
- */
-static void afs_init_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode)
-{
-	memset(fc, 0, sizeof(*fc));
-}
-
 /*
  * Begin an operation on the fileserver.
  *
@@ -35,13 +27,14 @@ static void afs_init_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode
 bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode,
 			       struct key *key)
 {
-	afs_init_fs_cursor(fc, vnode);
+	memset(fc, 0, sizeof(*fc));
 	fc->vnode = vnode;
 	fc->key = key;
 	fc->ac.error = SHRT_MAX;
+	fc->error = -EDESTADDRREQ;
 
 	if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
-		fc->ac.error = -EINTR;
+		fc->error = -EINTR;
 		fc->flags |= AFS_FS_CURSOR_STOP;
 		return false;
 	}
@@ -65,12 +58,15 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc,
 	fc->server_list = afs_get_serverlist(vnode->volume->servers);
 	read_unlock(&vnode->volume->servers_lock);
 
+	fc->untried = (1UL << fc->server_list->nr_servers) - 1;
+	fc->index = READ_ONCE(fc->server_list->preferred);
+
 	cbi = vnode->cb_interest;
 	if (cbi) {
 		/* See if the vnode's preferred record is still available */
 		for (i = 0; i < fc->server_list->nr_servers; i++) {
 			if (fc->server_list->servers[i].cb_interest == cbi) {
-				fc->start = i;
+				fc->index = i;
 				goto found_interest;
 			}
 		}
@@ -80,7 +76,7 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc,
 		 * and have to return an error.
 		 */
 		if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) {
-			fc->ac.error = -ESTALE;
+			fc->error = -ESTALE;
 			return false;
 		}
 
@@ -94,12 +90,9 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc,
 
 		afs_put_cb_interest(afs_v2net(vnode), cbi);
 		cbi = NULL;
-	} else {
-		fc->start = READ_ONCE(fc->server_list->index);
 	}
 
 found_interest:
-	fc->index = fc->start;
 	return true;
 }
 
@@ -117,7 +110,7 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code)
 	default:		m = "busy";		break;
 	}
 
-	pr_notice("kAFS: Volume %u '%s' is %s\n", volume->vid, volume->name, m);
+	pr_notice("kAFS: Volume %llu '%s' is %s\n", volume->vid, volume->name, m);
 }
 
 /*
@@ -127,7 +120,7 @@ static bool afs_sleep_and_retry(struct afs_fs_cursor *fc)
 {
 	msleep_interruptible(1000);
 	if (signal_pending(current)) {
-		fc->ac.error = -ERESTARTSYS;
+		fc->error = -ERESTARTSYS;
 		return false;
 	}
 
@@ -143,27 +136,32 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 	struct afs_addr_list *alist;
 	struct afs_server *server;
 	struct afs_vnode *vnode = fc->vnode;
+	u32 rtt, abort_code;
+	int error = fc->ac.error, i;
 
-	_enter("%u/%u,%u/%u,%d,%d",
+	_enter("%lx[%d],%lx[%d],%d,%d",
-	       fc->index, fc->start,
+	       fc->untried, fc->index,
-	       fc->ac.index, fc->ac.start,
+	       fc->ac.tried, fc->ac.index,
-	       fc->ac.error, fc->ac.abort_code);
+	       error, fc->ac.abort_code);
 
 	if (fc->flags & AFS_FS_CURSOR_STOP) {
 		_leave(" = f [stopped]");
 		return false;
 	}
 
+	fc->nr_iterations++;
+
 	/* Evaluate the result of the previous operation, if there was one. */
-	switch (fc->ac.error) {
+	switch (error) {
 	case SHRT_MAX:
 		goto start;
 
 	case 0:
 	default:
 		/* Success or local failure.  Stop. */
+		fc->error = error;
 		fc->flags |= AFS_FS_CURSOR_STOP;
-		_leave(" = f [okay/local %d]", fc->ac.error);
+		_leave(" = f [okay/local %d]", error);
 		return false;
 
 	case -ECONNABORTED:
@@ -178,7 +176,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 * - May indicate that the fileserver couldn't attach to the vol.
 			 */
 			if (fc->flags & AFS_FS_CURSOR_VNOVOL) {
-				fc->ac.error = -EREMOTEIO;
+				fc->error = -EREMOTEIO;
 				goto next_server;
 			}
 
@@ -187,12 +185,12 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			write_unlock(&vnode->volume->servers_lock);
 
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
-			fc->ac.error = afs_check_volume_status(vnode->volume, fc->key);
+			error = afs_check_volume_status(vnode->volume, fc->key);
-			if (fc->ac.error < 0)
+			if (error < 0)
-				goto failed;
+				goto failed_set_error;
 
 			if (test_bit(AFS_VOLUME_DELETED, &vnode->volume->flags)) {
-				fc->ac.error = -ENOMEDIUM;
+				fc->error = -ENOMEDIUM;
 				goto failed;
 			}
 
@@ -200,7 +198,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 * it's the fileserver having trouble.
 			 */
 			if (vnode->volume->servers == fc->server_list) {
-				fc->ac.error = -EREMOTEIO;
+				fc->error = -EREMOTEIO;
 				goto next_server;
 			}
 
@@ -215,7 +213,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 		case VONLINE:
 		case VDISKFULL:
 		case VOVERQUOTA:
-			fc->ac.error = afs_abort_to_error(fc->ac.abort_code);
+			fc->error = afs_abort_to_error(fc->ac.abort_code);
 			goto next_server;
 
 		case VOFFLINE:
@@ -224,11 +222,11 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 				clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags);
 			}
 			if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) {
-				fc->ac.error = -EADV;
+				fc->error = -EADV;
 				goto failed;
 			}
 			if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) {
-				fc->ac.error = -ESTALE;
+				fc->error = -ESTALE;
 				goto failed;
 			}
 			goto busy;
@@ -240,7 +238,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 * have a file lock we need to maintain.
 			 */
 			if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) {
-				fc->ac.error = -EBUSY;
+				fc->error = -EBUSY;
 				goto failed;
 			}
 			if (!test_and_set_bit(AFS_VOLUME_BUSY, &vnode->volume->flags)) {
@@ -269,16 +267,16 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 * honour, just in case someone sets up a loop.
 			 */
 			if (fc->flags & AFS_FS_CURSOR_VMOVED) {
-				fc->ac.error = -EREMOTEIO;
+				fc->error = -EREMOTEIO;
 				goto failed;
 			}
 			fc->flags |= AFS_FS_CURSOR_VMOVED;
 
 			set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags);
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
-			fc->ac.error = afs_check_volume_status(vnode->volume, fc->key);
+			error = afs_check_volume_status(vnode->volume, fc->key);
-			if (fc->ac.error < 0)
+			if (error < 0)
-				goto failed;
+				goto failed_set_error;
 
 			/* If the server list didn't change, then the VLDB is
 			 * out of sync with the fileservers.  This is hopefully
@@ -290,7 +288,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 * TODO: Retry a few times with sleeps.
 			 */
 			if (vnode->volume->servers == fc->server_list) {
-				fc->ac.error = -ENOMEDIUM;
+				fc->error = -ENOMEDIUM;
 				goto failed;
 			}
 
@@ -299,20 +297,25 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 		default:
 			clear_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags);
 			clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags);
-			fc->ac.error = afs_abort_to_error(fc->ac.abort_code);
+			fc->error = afs_abort_to_error(fc->ac.abort_code);
 			goto failed;
 		}
 
+	case -ETIMEDOUT:
+	case -ETIME:
+		if (fc->error != -EDESTADDRREQ)
+			goto iterate_address;
+		/* Fall through */
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
 	case -ECONNREFUSED:
-	case -ETIMEDOUT:
-	case -ETIME:
 		_debug("no conn");
+		fc->error = error;
 		goto iterate_address;
 
 	case -ECONNRESET:
 		_debug("call reset");
+		fc->error = error;
 		goto failed;
 	}
 
@@ -328,15 +331,57 @@ start:
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
-	fc->ac.error = afs_check_volume_status(vnode->volume, fc->key);
+	error = afs_check_volume_status(vnode->volume, fc->key);
-	if (fc->ac.error < 0)
+	if (error < 0)
-		goto failed;
+		goto failed_set_error;
 
 	if (!afs_start_fs_iteration(fc, vnode))
 		goto failed;
 
-use_server:
+	_debug("__ VOL %llx __", vnode->volume->vid);
-	_debug("use");
+	error = afs_probe_fileservers(afs_v2net(vnode), fc->key, fc->server_list);
+	if (error < 0)
+		goto failed_set_error;
+
+pick_server:
+	_debug("pick [%lx]", fc->untried);
+
+	error = afs_wait_for_fs_probes(fc->server_list, fc->untried);
+	if (error < 0)
+		goto failed_set_error;
+
+	/* Pick the untried server with the lowest RTT.  If we have outstanding
+	 * callbacks, we stick with the server we're already using if we can.
+	 */
+	if (fc->cbi) {
+		_debug("cbi %u", fc->index);
+		if (test_bit(fc->index, &fc->untried))
+			goto selected_server;
+		afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
+		fc->cbi = NULL;
+		_debug("nocbi");
+	}
+
+	fc->index = -1;
+	rtt = U32_MAX;
+	for (i = 0; i < fc->server_list->nr_servers; i++) {
+		struct afs_server *s = fc->server_list->servers[i].server;
+
+		if (!test_bit(i, &fc->untried) || !s->probe.responded)
+			continue;
+		if (s->probe.rtt < rtt) {
+			fc->index = i;
+			rtt = s->probe.rtt;
+		}
+	}
+
+	if (fc->index == -1)
+		goto no_more_servers;
+
+selected_server:
+	_debug("use %d", fc->index);
+	__clear_bit(fc->index, &fc->untried);
+
 	/* We're starting on a different fileserver from the list.  We need to
 	 * check it, create a callback intercept, find its address list and
 	 * probe its capabilities before we use it.
@@ -354,10 +399,10 @@ use_server:
 	 * break request before we've finished decoding the reply and
 	 * installing the vnode.
 	 */
-	fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list,
+	error = afs_register_server_cb_interest(vnode, fc->server_list,
 						fc->index);
-	if (fc->ac.error < 0)
+	if (error < 0)
-		goto failed;
+		goto failed_set_error;
 
 	fc->cbi = afs_get_cb_interest(vnode->cb_interest);
 
@@ -369,66 +414,88 @@ use_server:
 
 	memset(&fc->ac, 0, sizeof(fc->ac));
 
-	/* Probe the current fileserver if we haven't done so yet. */
-	if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
-		fc->ac.alist = afs_get_addrlist(alist);
-
-		if (!afs_probe_fileserver(fc)) {
-			switch (fc->ac.error) {
-			case -ENOMEM:
-			case -ERESTARTSYS:
-			case -EINTR:
-				goto failed;
-			default:
-				goto next_server;
-			}
-		}
-	}
-
 	if (!fc->ac.alist)
 		fc->ac.alist = alist;
 	else
 		afs_put_addrlist(alist);
 
-	fc->ac.start = READ_ONCE(alist->index);
+	fc->ac.index = -1;
-	fc->ac.index = fc->ac.start;
 
 iterate_address:
 	ASSERT(fc->ac.alist);
-	_debug("iterate %d/%d", fc->ac.index, fc->ac.alist->nr_addrs);
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
 	if (!afs_iterate_addresses(&fc->ac))
 		goto next_server;
 
+	_debug("address [%u] %u/%u", fc->index, fc->ac.index, fc->ac.alist->nr_addrs);
+
 	_leave(" = t");
 	return true;
 
 next_server:
 	_debug("next");
 	afs_end_cursor(&fc->ac);
-	afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
+	goto pick_server;
-	fc->cbi = NULL;
-	fc->index++;
-	if (fc->index >= fc->server_list->nr_servers)
-		fc->index = 0;
-	if (fc->index != fc->start)
-		goto use_server;
 
+no_more_servers:
 	/* That's all the servers poked to no good effect.  Try again if some
 	 * of them were busy.
 	 */
 	if (fc->flags & AFS_FS_CURSOR_VBUSY)
 		goto restart_from_beginning;
 
-	fc->ac.error = -EDESTADDRREQ;
+	abort_code = 0;
-	goto failed;
+	error = -EDESTADDRREQ;
+	for (i = 0; i < fc->server_list->nr_servers; i++) {
+		struct afs_server *s = fc->server_list->servers[i].server;
+		int probe_error = READ_ONCE(s->probe.error);
 
+		switch (probe_error) {
+		case 0:
+			continue;
+		default:
+			if (error == -ETIMEDOUT ||
+			    error == -ETIME)
+				continue;
+		case -ETIMEDOUT:
+		case -ETIME:
+			if (error == -ENOMEM ||
+			    error == -ENONET)
+				continue;
+		case -ENOMEM:
+		case -ENONET:
+			if (error == -ENETUNREACH)
+				continue;
+		case -ENETUNREACH:
+			if (error == -EHOSTUNREACH)
+				continue;
+		case -EHOSTUNREACH:
+			if (error == -ECONNREFUSED)
+				continue;
+		case -ECONNREFUSED:
+			if (error == -ECONNRESET)
+				continue;
+		case -ECONNRESET: /* Responded, but call expired. */
+			if (error == -ECONNABORTED)
+				continue;
+		case -ECONNABORTED:
+			abort_code = s->probe.abort_code;
+			error = probe_error;
+			continue;
+		}
+	}
+
+	if (error == -ECONNABORTED)
+		error = afs_abort_to_error(abort_code);
+
+failed_set_error:
+	fc->error = error;
 failed:
 	fc->flags |= AFS_FS_CURSOR_STOP;
 	afs_end_cursor(&fc->ac);
-	_leave(" = f [failed %d]", fc->ac.error);
+	_leave(" = f [failed %d]", fc->error);
 	return false;
 }
 
@@ -442,13 +509,14 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc)
 	struct afs_vnode *vnode = fc->vnode;
 	struct afs_cb_interest *cbi = vnode->cb_interest;
 	struct afs_addr_list *alist;
+	int error = fc->ac.error;
 
 	_enter("");
 
-	switch (fc->ac.error) {
+	switch (error) {
 	case SHRT_MAX:
 		if (!cbi) {
-			fc->ac.error = -ESTALE;
+			fc->error = -ESTALE;
 			fc->flags |= AFS_FS_CURSOR_STOP;
 			return false;
 		}
@@ -461,25 +529,26 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc)
 		afs_get_addrlist(alist);
 		read_unlock(&cbi->server->fs_lock);
 		if (!alist) {
-			fc->ac.error = -ESTALE;
+			fc->error = -ESTALE;
 			fc->flags |= AFS_FS_CURSOR_STOP;
 			return false;
 		}
 
 		memset(&fc->ac, 0, sizeof(fc->ac));
 		fc->ac.alist = alist;
-		fc->ac.start = READ_ONCE(alist->index);
+		fc->ac.index = -1;
-		fc->ac.index = fc->ac.start;
 		goto iterate_address;
 
 	case 0:
 	default:
 		/* Success or local failure.  Stop. */
+		fc->error = error;
 		fc->flags |= AFS_FS_CURSOR_STOP;
-		_leave(" = f [okay/local %d]", fc->ac.error);
+		_leave(" = f [okay/local %d]", error);
 		return false;
 
 	case -ECONNABORTED:
+		fc->error = afs_abort_to_error(fc->ac.abort_code);
 		fc->flags |= AFS_FS_CURSOR_STOP;
 		_leave(" = f [abort]");
 		return false;
@@ -490,6 +559,7 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc)
 	case -ETIMEDOUT:
 	case -ETIME:
 		_debug("no conn");
+		fc->error = error;
 		goto iterate_address;
 	}
 
@@ -506,13 +576,66 @@ iterate_address:
 	return false;
 }
 
+/*
+ * Dump cursor state in the case of the error being EDESTADDRREQ.
+ */
+static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc)
+{
+	static int count;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3)
+		return;
+	count++;
+
+	rcu_read_lock();
+
+	pr_notice("EDESTADDR occurred\n");
+	pr_notice("FC: cbb=%x cbb2=%x fl=%hx err=%hd\n",
+		  fc->cb_break, fc->cb_break_2, fc->flags, fc->error);
+	pr_notice("FC: ut=%lx ix=%d ni=%u\n",
+		  fc->untried, fc->index, fc->nr_iterations);
+
+	if (fc->server_list) {
+		const struct afs_server_list *sl = fc->server_list;
+		pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n",
+			  sl->nr_servers, sl->preferred, sl->vnovol_mask);
+		for (i = 0; i < sl->nr_servers; i++) {
+			const struct afs_server *s = sl->servers[i].server;
+			pr_notice("FC: server fl=%lx av=%u %pU\n",
+				  s->flags, s->addr_version, &s->uuid);
+			if (s->addresses) {
+				const struct afs_addr_list *a =
+					rcu_dereference(s->addresses);
+				pr_notice("FC:  - av=%u nr=%u/%u/%u pr=%u\n",
+					  a->version,
+					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
+					  a->preferred);
+				pr_notice("FC:  - pr=%lx R=%lx F=%lx\n",
+					  a->probed, a->responded, a->failed);
+				if (a == fc->ac.alist)
+					pr_notice("FC:  - current\n");
+			}
+		}
+	}
+
+	pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n",
+		  fc->ac.tried, fc->ac.index, fc->ac.abort_code, fc->ac.error,
+		  fc->ac.responded, fc->ac.nr_iterations);
+	rcu_read_unlock();
+}
+
 /*
  * Tidy up a filesystem cursor and unlock the vnode.
  */
 int afs_end_vnode_operation(struct afs_fs_cursor *fc)
 {
 	struct afs_net *net = afs_v2net(fc->vnode);
-	int ret;
+
+	if (fc->error == -EDESTADDRREQ ||
+	    fc->error == -ENETUNREACH ||
+	    fc->error == -EHOSTUNREACH)
+		afs_dump_edestaddrreq(fc);
 
 	mutex_unlock(&fc->vnode->io_lock);
 
@@ -520,9 +643,8 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc)
 	afs_put_cb_interest(net, fc->cbi);
 	afs_put_serverlist(net, fc->server_list);
 
-	ret = fc->ac.error;
+	if (fc->error == -ECONNABORTED)
-	if (ret == -ECONNABORTED)
+		fc->error = afs_abort_to_error(fc->ac.abort_code);
-		afs_abort_to_error(fc->ac.abort_code);
 
-	return fc->ac.error;
+	return fc->error;
 }

fs/afs/rxrpc.c

@@ -16,6 +16,7 @@
 #include <net/af_rxrpc.h>
 #include "internal.h"
 #include "afs_cm.h"
+#include "protocol_yfs.h"
 
 struct workqueue_struct *afs_async_calls;
 
@@ -75,6 +76,18 @@ int afs_open_socket(struct afs_net *net)
 	if (ret < 0)
 		goto error_2;
 
+	srx.srx_service = YFS_CM_SERVICE;
+	ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
+	if (ret < 0)
+		goto error_2;
+
+	/* Ideally, we'd turn on service upgrade here, but we can't because
+	 * OpenAFS is buggy and leaks the userStatus field from packet to
+	 * packet and between FS packets and CB packets - so if we try to do an
+	 * upgrade on an FS packet, OpenAFS will leak that into the CB packet
+	 * it sends back to us.
+	 */
+
 	rxrpc_kernel_new_call_notification(socket, afs_rx_new_call,
 					   afs_rx_discard_new_call);
 
@@ -143,6 +156,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net,
 	INIT_WORK(&call->async_work, afs_process_async_call);
 	init_waitqueue_head(&call->waitq);
 	spin_lock_init(&call->state_lock);
+	call->_iter = &call->iter;
 
 	o = atomic_inc_return(&net->nr_outstanding_calls);
 	trace_afs_call(call, afs_call_trace_alloc, 1, o,
@@ -176,6 +190,7 @@ void afs_put_call(struct afs_call *call)
 
 		afs_put_server(call->net, call->cm_server);
 		afs_put_cb_interest(call->net, call->cbi);
+		afs_put_addrlist(call->alist);
 		kfree(call->request);
 
 		trace_afs_call(call, afs_call_trace_free, 0, o,
@@ -189,10 +204,11 @@ void afs_put_call(struct afs_call *call)
 }
 
 /*
- * Queue the call for actual work.  Returns 0 unconditionally for convenience.
+ * Queue the call for actual work.
  */
-int afs_queue_call_work(struct afs_call *call)
+static void afs_queue_call_work(struct afs_call *call)
 {
+	if (call->type->work) {
 		int u = atomic_inc_return(&call->usage);
 
 		trace_afs_call(call, afs_call_trace_work, u,
@@ -203,7 +219,7 @@ int afs_queue_call_work(struct afs_call *call)
 
 		if (!queue_work(afs_wq, &call->work))
 			afs_put_call(call);
-	return 0;
+	}
 }
 
 /*
@@ -233,6 +249,7 @@ struct afs_call *afs_alloc_flat_call(struct afs_net *net,
 			goto nomem_free;
 	}
 
+	afs_extract_to_buf(call, call->reply_max);
 	call->operation_ID = type->op;
 	init_waitqueue_head(&call->waitq);
 	return call;
@@ -286,7 +303,7 @@ static void afs_load_bvec(struct afs_call *call, struct msghdr *msg,
 		offset = 0;
 	}
 
-	iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes);
+	iov_iter_bvec(&msg->msg_iter, WRITE, bv, nr, bytes);
 }
 
 /*
@@ -342,7 +359,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg)
 long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
 		   gfp_t gfp, bool async)
 {
-	struct sockaddr_rxrpc *srx = ac->addr;
+	struct sockaddr_rxrpc *srx = &ac->alist->addrs[ac->index];
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -359,6 +376,8 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
 	       atomic_read(&call->net->nr_outstanding_calls));
 
 	call->async = async;
+	call->addr_ix = ac->index;
+	call->alist = afs_get_addrlist(ac->alist);
 
 	/* Work out the length we're going to transmit.  This is awkward for
 	 * calls such as FS.StoreData where there's an extra injection of data
@@ -390,6 +409,7 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
 					 call->debug_id);
 	if (IS_ERR(rxcall)) {
 		ret = PTR_ERR(rxcall);
+		call->error = ret;
 		goto error_kill_call;
 	}
 
@@ -401,8 +421,7 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
 
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1,
+	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, call->request_size);
-		      call->request_size);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= MSG_WAITALL | (call->send_pages ? MSG_MORE : 0);
@@ -432,7 +451,7 @@ error_do_abort:
 		rxrpc_kernel_abort_call(call->net->socket, rxcall,
 					RX_USER_ABORT, ret, "KSD");
 	} else {
-		iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0);
+		iov_iter_kvec(&msg.msg_iter, READ, NULL, 0, 0);
 		rxrpc_kernel_recv_data(call->net->socket, rxcall,
 				       &msg.msg_iter, false,
 				       &call->abort_code, &call->service_id);
@@ -442,6 +461,8 @@ error_do_abort:
 	call->error = ret;
 	trace_afs_call_done(call);
 error_kill_call:
+	if (call->type->done)
+		call->type->done(call);
 	afs_put_call(call);
 	ac->error = ret;
 	_leave(" = %d", ret);
@@ -466,14 +487,12 @@ static void afs_deliver_to_call(struct afs_call *call)
 	       state == AFS_CALL_SV_AWAIT_ACK
 	       ) {
 		if (state == AFS_CALL_SV_AWAIT_ACK) {
-			struct iov_iter iter;
+			iov_iter_kvec(&call->iter, READ, NULL, 0, 0);
-
-			iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0);
 			ret = rxrpc_kernel_recv_data(call->net->socket,
-						     call->rxcall, &iter, false,
+						     call->rxcall, &call->iter,
-						     &remote_abort,
+						     false, &remote_abort,
 						     &call->service_id);
-			trace_afs_recv_data(call, 0, 0, false, ret);
+			trace_afs_receive_data(call, &call->iter, false, ret);
 
 			if (ret == -EINPROGRESS || ret == -EAGAIN)
 				return;
@@ -485,10 +504,17 @@ static void afs_deliver_to_call(struct afs_call *call)
 			return;
 		}
 
+		if (call->want_reply_time &&
+		    rxrpc_kernel_get_reply_time(call->net->socket,
+						call->rxcall,
+						&call->reply_time))
+			call->want_reply_time = false;
+
 		ret = call->type->deliver(call);
 		state = READ_ONCE(call->state);
 		switch (ret) {
 		case 0:
+			afs_queue_call_work(call);
 			if (state == AFS_CALL_CL_PROC_REPLY) {
 				if (call->cbi)
 					set_bit(AFS_SERVER_FL_MAY_HAVE_CB,
@@ -500,7 +526,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -EINPROGRESS:
 		case -EAGAIN:
 			goto out;
-		case -EIO:
 		case -ECONNABORTED:
 			ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
 			goto done;
@@ -509,6 +534,10 @@ static void afs_deliver_to_call(struct afs_call *call)
 			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
 						abort_code, ret, "KIV");
 			goto local_abort;
+		case -EIO:
+			pr_err("kAFS: Call %u in bad state %u\n",
+			       call->debug_id, state);
+			/* Fall through */
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
@@ -517,12 +546,14 @@ static void afs_deliver_to_call(struct afs_call *call)
 			if (state != AFS_CALL_CL_AWAIT_REPLY)
 				abort_code = RXGEN_SS_UNMARSHAL;
 			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
-						abort_code, -EBADMSG, "KUM");
+						abort_code, ret, "KUM");
 			goto local_abort;
 		}
 	}
 
 done:
+	if (call->type->done)
+		call->type->done(call);
 	if (state == AFS_CALL_COMPLETE && call->incoming)
 		afs_put_call(call);
 out:
@@ -728,6 +759,7 @@ void afs_charge_preallocation(struct work_struct *work)
 			call->async = true;
 			call->state = AFS_CALL_SV_AWAIT_OP_ID;
 			init_waitqueue_head(&call->waitq);
+			afs_extract_to_tmp(call);
 		}
 
 		if (rxrpc_kernel_charge_accept(net->socket,
@@ -773,18 +805,15 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
 {
 	int ret;
 
-	_enter("{%zu}", call->offset);
+	_enter("{%zu}", iov_iter_count(call->_iter));
-
-	ASSERTCMP(call->offset, <, 4);
 
 	/* the operation ID forms the first four bytes of the request data */
-	ret = afs_extract_data(call, &call->tmp, 4, true);
+	ret = afs_extract_data(call, true);
 	if (ret < 0)
 		return ret;
 
 	call->operation_ID = ntohl(call->tmp);
 	afs_set_call_state(call, AFS_CALL_SV_AWAIT_OP_ID, AFS_CALL_SV_AWAIT_REQUEST);
-	call->offset = 0;
 
 	/* ask the cache manager to route the call (it'll change the call type
 	 * if successful) */
@@ -825,7 +854,7 @@ void afs_send_empty_reply(struct afs_call *call)
 
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
+	iov_iter_kvec(&msg.msg_iter, WRITE, NULL, 0, 0);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
@@ -864,7 +893,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	iov[0].iov_len		= len;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
@@ -888,30 +917,19 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 /*
  * Extract a piece of data from the received data socket buffers.
  */
-int afs_extract_data(struct afs_call *call, void *buf, size_t count,
+int afs_extract_data(struct afs_call *call, bool want_more)
-		     bool want_more)
 {
 	struct afs_net *net = call->net;
-	struct iov_iter iter;
+	struct iov_iter *iter = call->_iter;
-	struct kvec iov;
 	enum afs_call_state state;
 	u32 remote_abort = 0;
 	int ret;
 
-	_enter("{%s,%zu},,%zu,%d",
+	_enter("{%s,%zu},%d", call->type->name, iov_iter_count(iter), want_more);
-	       call->type->name, call->offset, count, want_more);
 
-	ASSERTCMP(call->offset, <=, count);
+	ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter,
-
-	iov.iov_base = buf + call->offset;
-	iov.iov_len = count - call->offset;
-	iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset);
-
-	ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter,
 				     want_more, &remote_abort,
 				     &call->service_id);
-	call->offset += (count - call->offset) - iov_iter_count(&iter);
-	trace_afs_recv_data(call, count, call->offset, want_more, ret);
 	if (ret == 0 || ret == -EAGAIN)
 		return ret;
 
@@ -926,7 +944,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count,
 			break;
 		case AFS_CALL_COMPLETE:
 			kdebug("prem complete %d", call->error);
-			return -EIO;
+			return afs_io_error(call, afs_io_error_extract);
 		default:
 			break;
 		}
@@ -940,8 +958,9 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count,
 /*
  * Log protocol error production.
  */
-noinline int afs_protocol_error(struct afs_call *call, int error)
+noinline int afs_protocol_error(struct afs_call *call, int error,
+				enum afs_eproto_cause cause)
 {
-	trace_afs_protocol_error(call, error, __builtin_return_address(0));
+	trace_afs_protocol_error(call, error, cause);
 	return error;
 }

fs/afs/security.c

@@ -126,7 +126,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
 	bool changed = false;
 	int i, j;
 
-	_enter("{%x:%u},%x,%x",
+	_enter("{%llx:%llu},%x,%x",
 	       vnode->fid.vid, vnode->fid.vnode, key_serial(key), caller_access);
 
 	rcu_read_lock();
@@ -147,7 +147,8 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
 					break;
 				}
 
-				if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) {
+				if (afs_cb_is_broken(cb_break, vnode,
+						     vnode->cb_interest)) {
 					changed = true;
 					break;
 				}
@@ -177,7 +178,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
 		}
 	}
 
-	if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest))
+	if (afs_cb_is_broken(cb_break, vnode, vnode->cb_interest))
 		goto someone_else_changed_it;
 
 	/* We need a ref on any permits list we want to copy as we'll have to
@@ -256,7 +257,7 @@ found:
 
 	spin_lock(&vnode->lock);
 	zap = rcu_access_pointer(vnode->permit_cache);
-	if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) &&
+	if (!afs_cb_is_broken(cb_break, vnode, vnode->cb_interest) &&
 	    zap == permits)
 		rcu_assign_pointer(vnode->permit_cache, replacement);
 	else
@@ -289,7 +290,7 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key,
 	bool valid = false;
 	int i, ret;
 
-	_enter("{%x:%u},%x",
+	_enter("{%llx:%llu},%x",
 	       vnode->fid.vid, vnode->fid.vnode, key_serial(key));
 
 	/* check the permits to see if we've got one yet */
@@ -349,7 +350,7 @@ int afs_permission(struct inode *inode, int mask)
 	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
-	_enter("{{%x:%u},%lx},%x,",
+	_enter("{{%llx:%llu},%lx},%x,",
 	       vnode->fid.vid, vnode->fid.vnode, vnode->flags, mask);
 
 	key = afs_request_key(vnode->volume->cell);

fs/afs/server.c

@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include "afs_fs.h"
 #include "internal.h"
+#include "protocol_yfs.h"
 
 static unsigned afs_server_gc_delay = 10;	/* Server record timeout in seconds */
 static unsigned afs_server_update_delay = 30;	/* Time till VLDB recheck in secs */
@@ -230,6 +231,8 @@ static struct afs_server *afs_alloc_server(struct afs_net *net,
 	rwlock_init(&server->fs_lock);
 	INIT_HLIST_HEAD(&server->cb_volumes);
 	rwlock_init(&server->cb_break_lock);
+	init_waitqueue_head(&server->probe_wq);
+	spin_lock_init(&server->probe_lock);
 
 	afs_inc_servers_outstanding(net);
 	_leave(" = %p", server);
@@ -246,41 +249,23 @@ enomem:
 static struct afs_addr_list *afs_vl_lookup_addrs(struct afs_cell *cell,
 						 struct key *key, const uuid_t *uuid)
 {
-	struct afs_addr_cursor ac;
+	struct afs_vl_cursor vc;
-	struct afs_addr_list *alist;
+	struct afs_addr_list *alist = NULL;
 	int ret;
 
-	ret = afs_set_vl_cursor(&ac, cell);
+	ret = -ERESTARTSYS;
-	if (ret < 0)
+	if (afs_begin_vlserver_operation(&vc, cell, key)) {
-		return ERR_PTR(ret);
+		while (afs_select_vlserver(&vc)) {
-
+			if (test_bit(AFS_VLSERVER_FL_IS_YFS, &vc.server->flags))
-	while (afs_iterate_addresses(&ac)) {
+				alist = afs_yfsvl_get_endpoints(&vc, uuid);
-		if (test_bit(ac.index, &ac.alist->yfs))
-			alist = afs_yfsvl_get_endpoints(cell->net, &ac, key, uuid);
 			else
-			alist = afs_vl_get_addrs_u(cell->net, &ac, key, uuid);
+				alist = afs_vl_get_addrs_u(&vc, uuid);
-		switch (ac.error) {
-		case 0:
-			afs_end_cursor(&ac);
-			return alist;
-		case -ECONNABORTED:
-			ac.error = afs_abort_to_error(ac.abort_code);
-			goto error;
-		case -ENOMEM:
-		case -ENONET:
-			goto error;
-		case -ENETUNREACH:
-		case -EHOSTUNREACH:
-		case -ECONNREFUSED:
-			break;
-		default:
-			ac.error = -EIO;
-			goto error;
-		}
 		}
 
-error:
+		ret = afs_end_vlserver_operation(&vc);
-	return ERR_PTR(afs_end_cursor(&ac));
+	}
+
+	return ret < 0 ? ERR_PTR(ret) : alist;
 }
 
 /*
@@ -382,9 +367,7 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
 	struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
 	struct afs_addr_cursor ac = {
 		.alist	= alist,
-		.start	= alist->index,
+		.index	= alist->preferred,
-		.index	= 0,
-		.addr	= &alist->addrs[alist->index],
 		.error	= 0,
 	};
 	_enter("%p", server);
@@ -392,6 +375,9 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
 	if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
 		afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
 
+	wait_var_event(&server->probe_outstanding,
+		       atomic_read(&server->probe_outstanding) == 0);
+
 	call_rcu(&server->rcu, afs_server_rcu);
 	afs_dec_servers_outstanding(net);
 }
@@ -524,99 +510,6 @@ void afs_purge_servers(struct afs_net *net)
 	_leave("");
 }
 
-/*
- * Probe a fileserver to find its capabilities.
- *
- * TODO: Try service upgrade.
- */
-static bool afs_do_probe_fileserver(struct afs_fs_cursor *fc)
-{
-	_enter("");
-
-	fc->ac.addr = NULL;
-	fc->ac.start = READ_ONCE(fc->ac.alist->index);
-	fc->ac.index = fc->ac.start;
-	fc->ac.error = 0;
-	fc->ac.begun = false;
-
-	while (afs_iterate_addresses(&fc->ac)) {
-		afs_fs_get_capabilities(afs_v2net(fc->vnode), fc->cbi->server,
-					&fc->ac, fc->key);
-		switch (fc->ac.error) {
-		case 0:
-			afs_end_cursor(&fc->ac);
-			set_bit(AFS_SERVER_FL_PROBED, &fc->cbi->server->flags);
-			return true;
-		case -ECONNABORTED:
-			fc->ac.error = afs_abort_to_error(fc->ac.abort_code);
-			goto error;
-		case -ENOMEM:
-		case -ENONET:
-			goto error;
-		case -ENETUNREACH:
-		case -EHOSTUNREACH:
-		case -ECONNREFUSED:
-		case -ETIMEDOUT:
-		case -ETIME:
-			break;
-		default:
-			fc->ac.error = -EIO;
-			goto error;
-		}
-	}
-
-error:
-	afs_end_cursor(&fc->ac);
-	return false;
-}
-
-/*
- * If we haven't already, try probing the fileserver to get its capabilities.
- * We try not to instigate parallel probes, but it's possible that the parallel
- * probes will fail due to authentication failure when ours would succeed.
- *
- * TODO: Try sending an anonymous probe if an authenticated probe fails.
- */
-bool afs_probe_fileserver(struct afs_fs_cursor *fc)
-{
-	bool success;
-	int ret, retries = 0;
-
-	_enter("");
-
-retry:
-	if (test_bit(AFS_SERVER_FL_PROBED, &fc->cbi->server->flags)) {
-		_leave(" = t");
-		return true;
-	}
-
-	if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &fc->cbi->server->flags)) {
-		success = afs_do_probe_fileserver(fc);
-		clear_bit_unlock(AFS_SERVER_FL_PROBING, &fc->cbi->server->flags);
-		wake_up_bit(&fc->cbi->server->flags, AFS_SERVER_FL_PROBING);
-		_leave(" = t");
-		return success;
-	}
-
-	_debug("wait");
-	ret = wait_on_bit(&fc->cbi->server->flags, AFS_SERVER_FL_PROBING,
-			  TASK_INTERRUPTIBLE);
-	if (ret == -ERESTARTSYS) {
-		fc->ac.error = ret;
-		_leave(" = f [%d]", ret);
-		return false;
-	}
-
-	retries++;
-	if (retries == 4) {
-		fc->ac.error = -ESTALE;
-		_leave(" = f [stale]");
-		return false;
-	}
-	_debug("retry");
-	goto retry;
-}
-
 /*
  * Get an update for a server's address list.
  */

fs/afs/server_list.c

@@ -118,11 +118,11 @@ bool afs_annotate_server_list(struct afs_server_list *new,
 	return false;
 
 changed:
-	/* Maintain the same current server as before if possible. */
+	/* Maintain the same preferred server as before if possible. */
-	cur = old->servers[old->index].server;
+	cur = old->servers[old->preferred].server;
 	for (j = 0; j < new->nr_servers; j++) {
 		if (new->servers[j].server == cur) {
-			new->index = j;
+			new->preferred = j;
 			break;
 		}
 	}

fs/afs/super.c

@@ -406,10 +406,11 @@ static int afs_fill_super(struct super_block *sb,
 		inode = afs_iget_pseudo_dir(sb, true);
 		sb->s_flags	|= SB_RDONLY;
 	} else {
-		sprintf(sb->s_id, "%u", as->volume->vid);
+		sprintf(sb->s_id, "%llu", as->volume->vid);
 		afs_activate_volume(as->volume);
 		fid.vid		= as->volume->vid;
 		fid.vnode	= 1;
+		fid.vnode_hi	= 0;
 		fid.unique	= 1;
 		inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL);
 	}
@@ -663,7 +664,7 @@ static void afs_destroy_inode(struct inode *inode)
 {
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 
-	_enter("%p{%x:%u}", inode, vnode->fid.vid, vnode->fid.vnode);
+	_enter("%p{%llx:%llu}", inode, vnode->fid.vid, vnode->fid.vnode);
 
 	_debug("DESTROY INODE %p", inode);
 

fs/afs/vl_list.c

@@ -0,0 +1,340 @@
+/* AFS vlserver list management.
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
+					unsigned short port)
+{
+	struct afs_vlserver *vlserver;
+
+	vlserver = kzalloc(struct_size(vlserver, name, name_len + 1),
+			   GFP_KERNEL);
+	if (vlserver) {
+		atomic_set(&vlserver->usage, 1);
+		rwlock_init(&vlserver->lock);
+		init_waitqueue_head(&vlserver->probe_wq);
+		spin_lock_init(&vlserver->probe_lock);
+		vlserver->name_len = name_len;
+		vlserver->port = port;
+		memcpy(vlserver->name, name, name_len);
+	}
+	return vlserver;
+}
+
+static void afs_vlserver_rcu(struct rcu_head *rcu)
+{
+	struct afs_vlserver *vlserver = container_of(rcu, struct afs_vlserver, rcu);
+
+	afs_put_addrlist(rcu_access_pointer(vlserver->addresses));
+	kfree_rcu(vlserver, rcu);
+}
+
+void afs_put_vlserver(struct afs_net *net, struct afs_vlserver *vlserver)
+{
+	if (vlserver) {
+		unsigned int u = atomic_dec_return(&vlserver->usage);
+		//_debug("VL PUT %p{%u}", vlserver, u);
+
+		if (u == 0)
+			call_rcu(&vlserver->rcu, afs_vlserver_rcu);
+	}
+}
+
+struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int nr_servers)
+{
+	struct afs_vlserver_list *vllist;
+
+	vllist = kzalloc(struct_size(vllist, servers, nr_servers), GFP_KERNEL);
+	if (vllist) {
+		atomic_set(&vllist->usage, 1);
+		rwlock_init(&vllist->lock);
+	}
+
+	return vllist;
+}
+
+void afs_put_vlserverlist(struct afs_net *net, struct afs_vlserver_list *vllist)
+{
+	if (vllist) {
+		unsigned int u = atomic_dec_return(&vllist->usage);
+
+		//_debug("VLLS PUT %p{%u}", vllist, u);
+		if (u == 0) {
+			int i;
+
+			for (i = 0; i < vllist->nr_servers; i++) {
+				afs_put_vlserver(net, vllist->servers[i].server);
+			}
+			kfree_rcu(vllist, rcu);
+		}
+	}
+}
+
+static u16 afs_extract_le16(const u8 **_b)
+{
+	u16 val;
+
+	val  = (u16)*(*_b)++ << 0;
+	val |= (u16)*(*_b)++ << 8;
+	return val;
+}
+
+/*
+ * Build a VL server address list from a DNS queried server list.
+ */
+static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
+						  u8 nr_addrs, u16 port)
+{
+	struct afs_addr_list *alist;
+	const u8 *b = *_b;
+	int ret = -EINVAL;
+
+	alist = afs_alloc_addrlist(nr_addrs, VL_SERVICE, port);
+	if (!alist)
+		return ERR_PTR(-ENOMEM);
+	if (nr_addrs == 0)
+		return alist;
+
+	for (; nr_addrs > 0 && end - b >= nr_addrs; nr_addrs--) {
+		struct dns_server_list_v1_address hdr;
+		__be32 x[4];
+
+		hdr.address_type = *b++;
+
+		switch (hdr.address_type) {
+		case DNS_ADDRESS_IS_IPV4:
+			if (end - b < 4) {
+				_leave(" = -EINVAL [short inet]");
+				goto error;
+			}
+			memcpy(x, b, 4);
+			afs_merge_fs_addr4(alist, x[0], port);
+			b += 4;
+			break;
+
+		case DNS_ADDRESS_IS_IPV6:
+			if (end - b < 16) {
+				_leave(" = -EINVAL [short inet6]");
+				goto error;
+			}
+			memcpy(x, b, 16);
+			afs_merge_fs_addr6(alist, x, port);
+			b += 16;
+			break;
+
+		default:
+			_leave(" = -EADDRNOTAVAIL [unknown af %u]",
+			       hdr.address_type);
+			ret = -EADDRNOTAVAIL;
+			goto error;
+		}
+	}
+
+	/* Start with IPv6 if available. */
+	if (alist->nr_ipv4 < alist->nr_addrs)
+		alist->preferred = alist->nr_ipv4;
+
+	*_b = b;
+	return alist;
+
+error:
+	*_b = b;
+	afs_put_addrlist(alist);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Build a VL server list from a DNS queried server list.
+ */
+struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
+						    const void *buffer,
+						    size_t buffer_size)
+{
+	const struct dns_server_list_v1_header *hdr = buffer;
+	struct dns_server_list_v1_server bs;
+	struct afs_vlserver_list *vllist, *previous;
+	struct afs_addr_list *addrs;
+	struct afs_vlserver *server;
+	const u8 *b = buffer, *end = buffer + buffer_size;
+	int ret = -ENOMEM, nr_servers, i, j;
+
+	_enter("");
+
+	/* Check that it's a server list, v1 */
+	if (end - b < sizeof(*hdr) ||
+	    hdr->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST ||
+	    hdr->hdr.version != 1) {
+		pr_notice("kAFS: Got DNS record [%u,%u] len %zu\n",
+			  hdr->hdr.content, hdr->hdr.version, end - b);
+		ret = -EDESTADDRREQ;
+		goto dump;
+	}
+
+	nr_servers = hdr->nr_servers;
+
+	vllist = afs_alloc_vlserver_list(nr_servers);
+	if (!vllist)
+		return ERR_PTR(-ENOMEM);
+
+	vllist->source = (hdr->source < NR__dns_record_source) ?
+		hdr->source : NR__dns_record_source;
+	vllist->status = (hdr->status < NR__dns_lookup_status) ?
+		hdr->status : NR__dns_lookup_status;
+
+	read_lock(&cell->vl_servers_lock);
+	previous = afs_get_vlserverlist(
+		rcu_dereference_protected(cell->vl_servers,
+					  lockdep_is_held(&cell->vl_servers_lock)));
+	read_unlock(&cell->vl_servers_lock);
+
+	b += sizeof(*hdr);
+	while (end - b >= sizeof(bs)) {
+		bs.name_len	= afs_extract_le16(&b);
+		bs.priority	= afs_extract_le16(&b);
+		bs.weight	= afs_extract_le16(&b);
+		bs.port		= afs_extract_le16(&b);
+		bs.source	= *b++;
+		bs.status	= *b++;
+		bs.protocol	= *b++;
+		bs.nr_addrs	= *b++;
+
+		_debug("extract %u %u %u %u %u %u %*.*s",
+		       bs.name_len, bs.priority, bs.weight,
+		       bs.port, bs.protocol, bs.nr_addrs,
+		       bs.name_len, bs.name_len, b);
+
+		if (end - b < bs.name_len)
+			break;
+
+		ret = -EPROTONOSUPPORT;
+		if (bs.protocol == DNS_SERVER_PROTOCOL_UNSPECIFIED) {
+			bs.protocol = DNS_SERVER_PROTOCOL_UDP;
+		} else if (bs.protocol != DNS_SERVER_PROTOCOL_UDP) {
+			_leave(" = [proto %u]", bs.protocol);
+			goto error;
+		}
+
+		if (bs.port == 0)
+			bs.port = AFS_VL_PORT;
+		if (bs.source > NR__dns_record_source)
+			bs.source = NR__dns_record_source;
+		if (bs.status > NR__dns_lookup_status)
+			bs.status = NR__dns_lookup_status;
+
+		server = NULL;
+		if (previous) {
+			/* See if we can update an old server record */
+			for (i = 0; i < previous->nr_servers; i++) {
+				struct afs_vlserver *p = previous->servers[i].server;
+
+				if (p->name_len == bs.name_len &&
+				    p->port == bs.port &&
+				    strncasecmp(b, p->name, bs.name_len) == 0) {
+					server = afs_get_vlserver(p);
+					break;
+				}
+			}
+		}
+
+		if (!server) {
+			ret = -ENOMEM;
+			server = afs_alloc_vlserver(b, bs.name_len, bs.port);
+			if (!server)
+				goto error;
+		}
+
+		b += bs.name_len;
+
+		/* Extract the addresses - note that we can't skip this as we
+		 * have to advance the payload pointer.
+		 */
+		addrs = afs_extract_vl_addrs(&b, end, bs.nr_addrs, bs.port);
+		if (IS_ERR(addrs)) {
+			ret = PTR_ERR(addrs);
+			goto error_2;
+		}
+
+		if (vllist->nr_servers >= nr_servers) {
+			_debug("skip %u >= %u", vllist->nr_servers, nr_servers);
+			afs_put_addrlist(addrs);
+			afs_put_vlserver(cell->net, server);
+			continue;
+		}
+
+		addrs->source = bs.source;
+		addrs->status = bs.status;
+
+		if (addrs->nr_addrs == 0) {
+			afs_put_addrlist(addrs);
+			if (!rcu_access_pointer(server->addresses)) {
+				afs_put_vlserver(cell->net, server);
+				continue;
+			}
+		} else {
+			struct afs_addr_list *old = addrs;
+
+			write_lock(&server->lock);
+			rcu_swap_protected(server->addresses, old,
+					   lockdep_is_held(&server->lock));
+			write_unlock(&server->lock);
+			afs_put_addrlist(old);
+		}
+
+
+		/* TODO: Might want to check for duplicates */
+
+		/* Insertion-sort by priority and weight */
+		for (j = 0; j < vllist->nr_servers; j++) {
+			if (bs.priority < vllist->servers[j].priority)
+				break; /* Lower preferable */
+			if (bs.priority == vllist->servers[j].priority &&
+			    bs.weight > vllist->servers[j].weight)
+				break; /* Higher preferable */
+		}
+
+		if (j < vllist->nr_servers) {
+			memmove(vllist->servers + j + 1,
+				vllist->servers + j,
+				(vllist->nr_servers - j) * sizeof(struct afs_vlserver_entry));
+		}
+
+		clear_bit(AFS_VLSERVER_FL_PROBED, &server->flags);
+
+		vllist->servers[j].priority = bs.priority;
+		vllist->servers[j].weight = bs.weight;
+		vllist->servers[j].server = server;
+		vllist->nr_servers++;
+	}
+
+	if (b != end) {
+		_debug("parse error %zd", b - end);
+		goto error;
+	}
+
+	afs_put_vlserverlist(cell->net, previous);
+	_leave(" = ok [%u]", vllist->nr_servers);
+	return vllist;
+
+error_2:
+	afs_put_vlserver(cell->net, server);
+error:
+	afs_put_vlserverlist(cell->net, vllist);
+	afs_put_vlserverlist(cell->net, previous);
+dump:
+	if (ret != -ENOMEM) {
+		printk(KERN_DEBUG "DNS: at %zu\n", (const void *)b - buffer);
+		print_hex_dump_bytes("DNS: ", DUMP_PREFIX_NONE, buffer, buffer_size);
+	}
+	return ERR_PTR(ret);
+}

fs/afs/vl_probe.c

@@ -0,0 +1,273 @@
+/* AFS vlserver probing
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include "afs_fs.h"
+#include "internal.h"
+#include "protocol_yfs.h"
+
+static bool afs_vl_probe_done(struct afs_vlserver *server)
+{
+	if (!atomic_dec_and_test(&server->probe_outstanding))
+		return false;
+
+	wake_up_var(&server->probe_outstanding);
+	clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags);
+	wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING);
+	return true;
+}
+
+/*
+ * Process the result of probing a vlserver.  This is called after successful
+ * or failed delivery of an VL.GetCapabilities operation.
+ */
+void afs_vlserver_probe_result(struct afs_call *call)
+{
+	struct afs_addr_list *alist = call->alist;
+	struct afs_vlserver *server = call->reply[0];
+	unsigned int server_index = (long)call->reply[1];
+	unsigned int index = call->addr_ix;
+	unsigned int rtt = UINT_MAX;
+	bool have_result = false;
+	u64 _rtt;
+	int ret = call->error;
+
+	_enter("%s,%u,%u,%d,%d", server->name, server_index, index, ret, call->abort_code);
+
+	spin_lock(&server->probe_lock);
+
+	switch (ret) {
+	case 0:
+		server->probe.error = 0;
+		goto responded;
+	case -ECONNABORTED:
+		if (!server->probe.responded) {
+			server->probe.abort_code = call->abort_code;
+			server->probe.error = ret;
+		}
+		goto responded;
+	case -ENOMEM:
+	case -ENONET:
+		server->probe.local_failure = true;
+		afs_io_error(call, afs_io_error_vl_probe_fail);
+		goto out;
+	case -ECONNRESET: /* Responded, but call expired. */
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
+	case -ECONNREFUSED:
+	case -ETIMEDOUT:
+	case -ETIME:
+	default:
+		clear_bit(index, &alist->responded);
+		set_bit(index, &alist->failed);
+		if (!server->probe.responded &&
+		    (server->probe.error == 0 ||
+		     server->probe.error == -ETIMEDOUT ||
+		     server->probe.error == -ETIME))
+			server->probe.error = ret;
+		afs_io_error(call, afs_io_error_vl_probe_fail);
+		goto out;
+	}
+
+responded:
+	set_bit(index, &alist->responded);
+	clear_bit(index, &alist->failed);
+
+	if (call->service_id == YFS_VL_SERVICE) {
+		server->probe.is_yfs = true;
+		set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
+		alist->addrs[index].srx_service = call->service_id;
+	} else {
+		server->probe.not_yfs = true;
+		if (!server->probe.is_yfs) {
+			clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
+			alist->addrs[index].srx_service = call->service_id;
+		}
+	}
+
+	/* Get the RTT and scale it to fit into a 32-bit value that represents
+	 * over a minute of time so that we can access it with one instruction
+	 * on a 32-bit system.
+	 */
+	_rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
+	_rtt /= 64;
+	rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt;
+	if (rtt < server->probe.rtt) {
+		server->probe.rtt = rtt;
+		alist->preferred = index;
+		have_result = true;
+	}
+
+	smp_wmb(); /* Set rtt before responded. */
+	server->probe.responded = true;
+	set_bit(AFS_VLSERVER_FL_PROBED, &server->flags);
+out:
+	spin_unlock(&server->probe_lock);
+
+	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
+	       server_index, index, &alist->addrs[index].transport,
+	       (unsigned int)rtt, ret);
+
+	have_result |= afs_vl_probe_done(server);
+	if (have_result) {
+		server->probe.have_result = true;
+		wake_up_var(&server->probe.have_result);
+		wake_up_all(&server->probe_wq);
+	}
+}
+
+/*
+ * Probe all of a vlserver's addresses to find out the best route and to
+ * query its capabilities.
+ */
+static int afs_do_probe_vlserver(struct afs_net *net,
+				 struct afs_vlserver *server,
+				 struct key *key,
+				 unsigned int server_index)
+{
+	struct afs_addr_cursor ac = {
+		.index = 0,
+	};
+	int ret;
+
+	_enter("%s", server->name);
+
+	read_lock(&server->lock);
+	ac.alist = rcu_dereference_protected(server->addresses,
+					     lockdep_is_held(&server->lock));
+	read_unlock(&server->lock);
+
+	atomic_set(&server->probe_outstanding, ac.alist->nr_addrs);
+	memset(&server->probe, 0, sizeof(server->probe));
+	server->probe.rtt = UINT_MAX;
+
+	for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
+		ret = afs_vl_get_capabilities(net, &ac, key, server,
+					      server_index, true);
+		if (ret != -EINPROGRESS) {
+			afs_vl_probe_done(server);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Send off probes to all unprobed servers.
+ */
+int afs_send_vl_probes(struct afs_net *net, struct key *key,
+		       struct afs_vlserver_list *vllist)
+{
+	struct afs_vlserver *server;
+	int i, ret;
+
+	for (i = 0; i < vllist->nr_servers; i++) {
+		server = vllist->servers[i].server;
+		if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags))
+			continue;
+
+		if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags)) {
+			ret = afs_do_probe_vlserver(net, server, key, i);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Wait for the first as-yet untried server to respond.
+ */
+int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
+			   unsigned long untried)
+{
+	struct wait_queue_entry *waits;
+	struct afs_vlserver *server;
+	unsigned int rtt = UINT_MAX;
+	bool have_responders = false;
+	int pref = -1, i;
+
+	_enter("%u,%lx", vllist->nr_servers, untried);
+
+	/* Only wait for servers that have a probe outstanding. */
+	for (i = 0; i < vllist->nr_servers; i++) {
+		if (test_bit(i, &untried)) {
+			server = vllist->servers[i].server;
+			if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
+				__clear_bit(i, &untried);
+			if (server->probe.responded)
+				have_responders = true;
+		}
+	}
+	if (have_responders || !untried)
+		return 0;
+
+	waits = kmalloc(array_size(vllist->nr_servers, sizeof(*waits)), GFP_KERNEL);
+	if (!waits)
+		return -ENOMEM;
+
+	for (i = 0; i < vllist->nr_servers; i++) {
+		if (test_bit(i, &untried)) {
+			server = vllist->servers[i].server;
+			init_waitqueue_entry(&waits[i], current);
+			add_wait_queue(&server->probe_wq, &waits[i]);
+		}
+	}
+
+	for (;;) {
+		bool still_probing = false;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		for (i = 0; i < vllist->nr_servers; i++) {
+			if (test_bit(i, &untried)) {
+				server = vllist->servers[i].server;
+				if (server->probe.responded)
+					goto stop;
+				if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
+					still_probing = true;
+			}
+		}
+
+		if (!still_probing || unlikely(signal_pending(current)))
+			goto stop;
+		schedule();
+	}
+
+stop:
+	set_current_state(TASK_RUNNING);
+
+	for (i = 0; i < vllist->nr_servers; i++) {
+		if (test_bit(i, &untried)) {
+			server = vllist->servers[i].server;
+			if (server->probe.responded &&
+			    server->probe.rtt < rtt) {
+				pref = i;
+				rtt = server->probe.rtt;
+			}
+
+			remove_wait_queue(&server->probe_wq, &waits[i]);
+		}
+	}
+
+	kfree(waits);
+
+	if (pref == -1 && signal_pending(current))
+		return -ERESTARTSYS;
+
+	if (pref >= 0)
+		vllist->preferred = pref;
+
+	_leave(" = 0 [%u]", pref);
+	return 0;
+}

fs/afs/vl_rotate.c

@@ -0,0 +1,355 @@
+/* Handle vlserver selection and rotation.
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include "internal.h"
+#include "afs_vl.h"
+
+/*
+ * Begin an operation on a volume location server.
+ */
+bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cell,
+				  struct key *key)
+{
+	memset(vc, 0, sizeof(*vc));
+	vc->cell = cell;
+	vc->key = key;
+	vc->error = -EDESTADDRREQ;
+	vc->ac.error = SHRT_MAX;
+
+	if (signal_pending(current)) {
+		vc->error = -EINTR;
+		vc->flags |= AFS_VL_CURSOR_STOP;
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Begin iteration through a server list, starting with the last used server if
+ * possible, or the last recorded good server if not.
+ */
+static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
+{
+	struct afs_cell *cell = vc->cell;
+
+	if (wait_on_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET,
+			TASK_INTERRUPTIBLE)) {
+		vc->error = -ERESTARTSYS;
+		return false;
+	}
+
+	read_lock(&cell->vl_servers_lock);
+	vc->server_list = afs_get_vlserverlist(
+		rcu_dereference_protected(cell->vl_servers,
+					  lockdep_is_held(&cell->vl_servers_lock)));
+	read_unlock(&cell->vl_servers_lock);
+	if (!vc->server_list || !vc->server_list->nr_servers)
+		return false;
+
+	vc->untried = (1UL << vc->server_list->nr_servers) - 1;
+	vc->index = -1;
+	return true;
+}
+
+/*
+ * Select the vlserver to use.  May be called multiple times to rotate
+ * through the vlservers.
+ */
+bool afs_select_vlserver(struct afs_vl_cursor *vc)
+{
+	struct afs_addr_list *alist;
+	struct afs_vlserver *vlserver;
+	u32 rtt;
+	int error = vc->ac.error, abort_code, i;
+
+	_enter("%lx[%d],%lx[%d],%d,%d",
+	       vc->untried, vc->index,
+	       vc->ac.tried, vc->ac.index,
+	       error, vc->ac.abort_code);
+
+	if (vc->flags & AFS_VL_CURSOR_STOP) {
+		_leave(" = f [stopped]");
+		return false;
+	}
+
+	vc->nr_iterations++;
+
+	/* Evaluate the result of the previous operation, if there was one. */
+	switch (error) {
+	case SHRT_MAX:
+		goto start;
+
+	default:
+	case 0:
+		/* Success or local failure.  Stop. */
+		vc->error = error;
+		vc->flags |= AFS_VL_CURSOR_STOP;
+		_leave(" = f [okay/local %d]", vc->ac.error);
+		return false;
+
+	case -ECONNABORTED:
+		/* The far side rejected the operation on some grounds.  This
+		 * might involve the server being busy or the volume having been moved.
+		 */
+		switch (vc->ac.abort_code) {
+		case AFSVL_IO:
+		case AFSVL_BADVOLOPER:
+		case AFSVL_NOMEM:
+			/* The server went weird. */
+			vc->error = -EREMOTEIO;
+			//write_lock(&vc->cell->vl_servers_lock);
+			//vc->server_list->weird_mask |= 1 << vc->index;
+			//write_unlock(&vc->cell->vl_servers_lock);
+			goto next_server;
+
+		default:
+			vc->error = afs_abort_to_error(vc->ac.abort_code);
+			goto failed;
+		}
+
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
+	case -ECONNREFUSED:
+	case -ETIMEDOUT:
+	case -ETIME:
+		_debug("no conn %d", error);
+		vc->error = error;
+		goto iterate_address;
+
+	case -ECONNRESET:
+		_debug("call reset");
+		vc->error = error;
+		vc->flags |= AFS_VL_CURSOR_RETRY;
+		goto next_server;
+	}
+
+restart_from_beginning:
+	_debug("restart");
+	afs_end_cursor(&vc->ac);
+	afs_put_vlserverlist(vc->cell->net, vc->server_list);
+	vc->server_list = NULL;
+	if (vc->flags & AFS_VL_CURSOR_RETRIED)
+		goto failed;
+	vc->flags |= AFS_VL_CURSOR_RETRIED;
+start:
+	_debug("start");
+
+	if (!afs_start_vl_iteration(vc))
+		goto failed;
+
+	error = afs_send_vl_probes(vc->cell->net, vc->key, vc->server_list);
+	if (error < 0)
+		goto failed_set_error;
+
+pick_server:
+	_debug("pick [%lx]", vc->untried);
+
+	error = afs_wait_for_vl_probes(vc->server_list, vc->untried);
+	if (error < 0)
+		goto failed_set_error;
+
+	/* Pick the untried server with the lowest RTT. */
+	vc->index = vc->server_list->preferred;
+	if (test_bit(vc->index, &vc->untried))
+		goto selected_server;
+
+	vc->index = -1;
+	rtt = U32_MAX;
+	for (i = 0; i < vc->server_list->nr_servers; i++) {
+		struct afs_vlserver *s = vc->server_list->servers[i].server;
+
+		if (!test_bit(i, &vc->untried) || !s->probe.responded)
+			continue;
+		if (s->probe.rtt < rtt) {
+			vc->index = i;
+			rtt = s->probe.rtt;
+		}
+	}
+
+	if (vc->index == -1)
+		goto no_more_servers;
+
+selected_server:
+	_debug("use %d", vc->index);
+	__clear_bit(vc->index, &vc->untried);
+
+	/* We're starting on a different vlserver from the list.  We need to
+	 * check it, find its address list and probe its capabilities before we
+	 * use it.
+	 */
+	ASSERTCMP(vc->ac.alist, ==, NULL);
+	vlserver = vc->server_list->servers[vc->index].server;
+	vc->server = vlserver;
+
+	_debug("USING VLSERVER: %s", vlserver->name);
+
+	read_lock(&vlserver->lock);
+	alist = rcu_dereference_protected(vlserver->addresses,
+					  lockdep_is_held(&vlserver->lock));
+	afs_get_addrlist(alist);
+	read_unlock(&vlserver->lock);
+
+	memset(&vc->ac, 0, sizeof(vc->ac));
+
+	if (!vc->ac.alist)
+		vc->ac.alist = alist;
+	else
+		afs_put_addrlist(alist);
+
+	vc->ac.index = -1;
+
+iterate_address:
+	ASSERT(vc->ac.alist);
+	/* Iterate over the current server's address list to try and find an
+	 * address on which it will respond to us.
+	 */
+	if (!afs_iterate_addresses(&vc->ac))
+		goto next_server;
+
+	_debug("VL address %d/%d", vc->ac.index, vc->ac.alist->nr_addrs);
+
+	_leave(" = t %pISpc", &vc->ac.alist->addrs[vc->ac.index].transport);
+	return true;
+
+next_server:
+	_debug("next");
+	afs_end_cursor(&vc->ac);
+	goto pick_server;
+
+no_more_servers:
+	/* That's all the servers poked to no good effect.  Try again if some
+	 * of them were busy.
+	 */
+	if (vc->flags & AFS_VL_CURSOR_RETRY)
+		goto restart_from_beginning;
+
+	abort_code = 0;
+	error = -EDESTADDRREQ;
+	for (i = 0; i < vc->server_list->nr_servers; i++) {
+		struct afs_vlserver *s = vc->server_list->servers[i].server;
+		int probe_error = READ_ONCE(s->probe.error);
+
+		switch (probe_error) {
+		case 0:
+			continue;
+		default:
+			if (error == -ETIMEDOUT ||
+			    error == -ETIME)
+				continue;
+		case -ETIMEDOUT:
+		case -ETIME:
+			if (error == -ENOMEM ||
+			    error == -ENONET)
+				continue;
+		case -ENOMEM:
+		case -ENONET:
+			if (error == -ENETUNREACH)
+				continue;
+		case -ENETUNREACH:
+			if (error == -EHOSTUNREACH)
+				continue;
+		case -EHOSTUNREACH:
+			if (error == -ECONNREFUSED)
+				continue;
+		case -ECONNREFUSED:
+			if (error == -ECONNRESET)
+				continue;
+		case -ECONNRESET: /* Responded, but call expired. */
+			if (error == -ECONNABORTED)
+				continue;
+		case -ECONNABORTED:
+			abort_code = s->probe.abort_code;
+			error = probe_error;
+			continue;
+		}
+	}
+
+	if (error == -ECONNABORTED)
+		error = afs_abort_to_error(abort_code);
+
+failed_set_error:
+	vc->error = error;
+failed:
+	vc->flags |= AFS_VL_CURSOR_STOP;
+	afs_end_cursor(&vc->ac);
+	_leave(" = f [failed %d]", vc->error);
+	return false;
+}
+
+/*
+ * Dump cursor state in the case of the error being EDESTADDRREQ.
+ */
+static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
+{
+	static int count;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3)
+		return;
+	count++;
+
+	rcu_read_lock();
+	pr_notice("EDESTADDR occurred\n");
+	pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n",
+		  vc->untried, vc->index, vc->nr_iterations, vc->flags, vc->error);
+
+	if (vc->server_list) {
+		const struct afs_vlserver_list *sl = vc->server_list;
+		pr_notice("VC: SL nr=%u ix=%u\n",
+			  sl->nr_servers, sl->index);
+		for (i = 0; i < sl->nr_servers; i++) {
+			const struct afs_vlserver *s = sl->servers[i].server;
+			pr_notice("VC: server %s+%hu fl=%lx E=%hd\n",
+				  s->name, s->port, s->flags, s->probe.error);
+			if (s->addresses) {
+				const struct afs_addr_list *a =
+					rcu_dereference(s->addresses);
+				pr_notice("VC:  - nr=%u/%u/%u pf=%u\n",
+					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
+					  a->preferred);
+				pr_notice("VC:  - pr=%lx R=%lx F=%lx\n",
+					  a->probed, a->responded, a->failed);
+				if (a == vc->ac.alist)
+					pr_notice("VC:  - current\n");
+			}
+		}
+	}
+
+	pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n",
+		  vc->ac.tried, vc->ac.index, vc->ac.abort_code, vc->ac.error,
+		  vc->ac.responded, vc->ac.nr_iterations);
+	rcu_read_unlock();
+}
+
+/*
+ * Tidy up a volume location server cursor and unlock the vnode.
+ */
+int afs_end_vlserver_operation(struct afs_vl_cursor *vc)
+{
+	struct afs_net *net = vc->cell->net;
+
+	if (vc->error == -EDESTADDRREQ ||
+	    vc->error == -ENETUNREACH ||
+	    vc->error == -EHOSTUNREACH)
+		afs_vl_dump_edestaddrreq(vc);
+
+	afs_end_cursor(&vc->ac);
+	afs_put_vlserverlist(net, vc->server_list);
+
+	if (vc->error == -ECONNABORTED)
+		vc->error = afs_abort_to_error(vc->ac.abort_code);
+
+	return vc->error;
+}

fs/afs/vlclient.c

@@ -128,14 +128,13 @@ static const struct afs_call_type afs_RXVLGetEntryByNameU = {
  * Dispatch a get volume entry by name or ID operation (uuid variant).  If the
  * volname is a decimal number then it's a volume ID not a volume name.
  */
-struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *net,
+struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc,
-						  struct afs_addr_cursor *ac,
-						  struct key *key,
 						  const char *volname,
 						  int volnamesz)
 {
 	struct afs_vldb_entry *entry;
 	struct afs_call *call;
+	struct afs_net *net = vc->cell->net;
 	size_t reqsz, padsz;
 	__be32 *bp;
 
@@ -155,7 +154,7 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *net,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	call->key = key;
+	call->key = vc->key;
 	call->reply[0] = entry;
 	call->ret_reply0 = true;
 
@@ -168,7 +167,7 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *net,
 		memset((void *)bp + volnamesz, 0, padsz);
 
 	trace_afs_make_vl_call(call);
-	return (struct afs_vldb_entry *)afs_make_call(ac, call, GFP_KERNEL, false);
+	return (struct afs_vldb_entry *)afs_make_call(&vc->ac, call, GFP_KERNEL, false);
 }
 
 /*
@@ -187,19 +186,18 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 	u32 uniquifier, nentries, count;
 	int i, ret;
 
-	_enter("{%u,%zu/%u}", call->unmarshall, call->offset, call->count);
+	_enter("{%u,%zu/%u}",
+	       call->unmarshall, iov_iter_count(call->_iter), call->count);
 
-again:
 	switch (call->unmarshall) {
 	case 0:
-		call->offset = 0;
+		afs_extract_to_buf(call,
+				   sizeof(struct afs_uuid__xdr) + 3 * sizeof(__be32));
 		call->unmarshall++;
 
 		/* Extract the returned uuid, uniquifier, nentries and blkaddrs size */
 	case 1:
-		ret = afs_extract_data(call, call->buffer,
+		ret = afs_extract_data(call, true);
-				       sizeof(struct afs_uuid__xdr) + 3 * sizeof(__be32),
-				       true);
 		if (ret < 0)
 			return ret;
 
@@ -216,28 +214,28 @@ again:
 		call->reply[0] = alist;
 		call->count = count;
 		call->count2 = nentries;
-		call->offset = 0;
 		call->unmarshall++;
 
+	more_entries:
+		count = min(call->count, 4U);
+		afs_extract_to_buf(call, count * sizeof(__be32));
+
 		/* Extract entries */
 	case 2:
-		count = min(call->count, 4U);
+		ret = afs_extract_data(call, call->count > 4);
-		ret = afs_extract_data(call, call->buffer,
-				       count * sizeof(__be32),
-				       call->count > 4);
 		if (ret < 0)
 			return ret;
 
 		alist = call->reply[0];
 		bp = call->buffer;
+		count = min(call->count, 4U);
 		for (i = 0; i < count; i++)
 			if (alist->nr_addrs < call->count2)
 				afs_merge_fs_addr4(alist, *bp++, AFS_FS_PORT);
 
 		call->count -= count;
 		if (call->count > 0)
-			goto again;
+			goto more_entries;
-		call->offset = 0;
 		call->unmarshall++;
 		break;
 	}
@@ -267,14 +265,13 @@ static const struct afs_call_type afs_RXVLGetAddrsU = {
  * Dispatch an operation to get the addresses for a server, where the server is
  * nominated by UUID.
  */
-struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *net,
+struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
-					 struct afs_addr_cursor *ac,
-					 struct key *key,
 					 const uuid_t *uuid)
 {
 	struct afs_ListAddrByAttributes__xdr *r;
 	const struct afs_uuid *u = (const struct afs_uuid *)uuid;
 	struct afs_call *call;
+	struct afs_net *net = vc->cell->net;
 	__be32 *bp;
 	int i;
 
@@ -286,7 +283,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *net,
 	if (!call)
 		return ERR_PTR(-ENOMEM);
 
-	call->key = key;
+	call->key = vc->key;
 	call->reply[0] = NULL;
 	call->ret_reply0 = true;
 
@@ -307,7 +304,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *net,
 		r->uuid.node[i] = htonl(u->node[i]);
 
 	trace_afs_make_vl_call(call);
-	return (struct afs_addr_list *)afs_make_call(ac, call, GFP_KERNEL, false);
+	return (struct afs_addr_list *)afs_make_call(&vc->ac, call, GFP_KERNEL, false);
 }
 
 /*
@@ -318,54 +315,51 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 	u32 count;
 	int ret;
 
-	_enter("{%u,%zu/%u}", call->unmarshall, call->offset, call->count);
+	_enter("{%u,%zu/%u}",
+	       call->unmarshall, iov_iter_count(call->_iter), call->count);
 
-again:
 	switch (call->unmarshall) {
 	case 0:
-		call->offset = 0;
+		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
 		/* Extract the capabilities word count */
 	case 1:
-		ret = afs_extract_data(call, &call->tmp,
+		ret = afs_extract_data(call, true);
-				       1 * sizeof(__be32),
-				       true);
 		if (ret < 0)
 			return ret;
 
 		count = ntohl(call->tmp);
-
 		call->count = count;
 		call->count2 = count;
-		call->offset = 0;
+
 		call->unmarshall++;
+		afs_extract_discard(call, count * sizeof(__be32));
 
 		/* Extract capabilities words */
 	case 2:
-		count = min(call->count, 16U);
+		ret = afs_extract_data(call, false);
-		ret = afs_extract_data(call, call->buffer,
-				       count * sizeof(__be32),
-				       call->count > 16);
 		if (ret < 0)
 			return ret;
 
 		/* TODO: Examine capabilities */
 
-		call->count -= count;
-		if (call->count > 0)
-			goto again;
-		call->offset = 0;
 		call->unmarshall++;
 		break;
 	}
 
-	call->reply[0] = (void *)(unsigned long)call->service_id;
-
 	_leave(" = 0 [done]");
 	return 0;
 }
 
+static void afs_destroy_vl_get_capabilities(struct afs_call *call)
+{
+	struct afs_vlserver *server = call->reply[0];
+
+	afs_put_vlserver(call->net, server);
+	afs_flat_call_destructor(call);
+}
+
 /*
  * VL.GetCapabilities operation type
  */
@@ -373,11 +367,12 @@ static const struct afs_call_type afs_RXVLGetCapabilities = {
 	.name		= "VL.GetCapabilities",
 	.op		= afs_VL_GetCapabilities,
 	.deliver	= afs_deliver_vl_get_capabilities,
-	.destructor	= afs_flat_call_destructor,
+	.done		= afs_vlserver_probe_result,
+	.destructor	= afs_destroy_vl_get_capabilities,
 };
 
 /*
- * Probe a fileserver for the capabilities that it supports.  This can
+ * Probe a volume server for the capabilities that it supports.  This can
  * return up to 196 words.
  *
  * We use this to probe for service upgrade to determine what the server at the
@@ -385,7 +380,10 @@ static const struct afs_call_type afs_RXVLGetCapabilities = {
  */
 int afs_vl_get_capabilities(struct afs_net *net,
 			    struct afs_addr_cursor *ac,
-			    struct key *key)
+			    struct key *key,
+			    struct afs_vlserver *server,
+			    unsigned int server_index,
+			    bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -397,9 +395,10 @@ int afs_vl_get_capabilities(struct afs_net *net,
 		return -ENOMEM;
 
 	call->key = key;
-	call->upgrade = true; /* Let's see if this is a YFS server */
+	call->reply[0] = afs_get_vlserver(server);
-	call->reply[0] = (void *)VLGETCAPABILITIES;
+	call->reply[1] = (void *)(long)server_index;
-	call->ret_reply0 = true;
+	call->upgrade = true;
+	call->want_reply_time = true;
 
 	/* marshall the parameters */
 	bp = call->request;
@@ -407,7 +406,7 @@ int afs_vl_get_capabilities(struct afs_net *net,
 
 	/* Can't take a ref on server */
 	trace_afs_make_vl_call(call);
-	return afs_make_call(ac, call, GFP_KERNEL, false);
+	return afs_make_call(ac, call, GFP_KERNEL, async);
 }
 
 /*
@@ -426,22 +425,19 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 	u32 uniquifier, size;
 	int ret;
 
-	_enter("{%u,%zu/%u,%u}", call->unmarshall, call->offset, call->count, call->count2);
+	_enter("{%u,%zu,%u}",
+	       call->unmarshall, iov_iter_count(call->_iter), call->count2);
 
-again:
 	switch (call->unmarshall) {
 	case 0:
-		call->offset = 0;
+		afs_extract_to_buf(call, sizeof(uuid_t) + 3 * sizeof(__be32));
 		call->unmarshall = 1;
 
 		/* Extract the returned uuid, uniquifier, fsEndpoints count and
 		 * either the first fsEndpoint type or the volEndpoints
 		 * count if there are no fsEndpoints. */
 	case 1:
-		ret = afs_extract_data(call, call->buffer,
+		ret = afs_extract_data(call, true);
-				       sizeof(uuid_t) +
-				       3 * sizeof(__be32),
-				       true);
 		if (ret < 0)
 			return ret;
 
@@ -451,22 +447,19 @@ again:
 		call->count2	= ntohl(*bp); /* Type or next count */
 
 		if (call->count > YFS_MAXENDPOINTS)
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_yvl_fsendpt_num);
 
 		alist = afs_alloc_addrlist(call->count, FS_SERVICE, AFS_FS_PORT);
 		if (!alist)
 			return -ENOMEM;
 		alist->version = uniquifier;
 		call->reply[0] = alist;
-		call->offset = 0;
 
 		if (call->count == 0)
 			goto extract_volendpoints;
 
-		call->unmarshall = 2;
+	next_fsendpoint:
-
-		/* Extract fsEndpoints[] entries */
-	case 2:
 		switch (call->count2) {
 		case YFS_ENDPOINT_IPV4:
 			size = sizeof(__be32) * (1 + 1 + 1);
@@ -475,11 +468,17 @@ again:
 			size = sizeof(__be32) * (1 + 4 + 1);
 			break;
 		default:
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_yvl_fsendpt_type);
 		}
 
 		size += sizeof(__be32);
-		ret = afs_extract_data(call, call->buffer, size, true);
+		afs_extract_to_buf(call, size);
+		call->unmarshall = 2;
+
+		/* Extract fsEndpoints[] entries */
+	case 2:
+		ret = afs_extract_data(call, true);
 		if (ret < 0)
 			return ret;
 
@@ -488,18 +487,21 @@ again:
 		switch (call->count2) {
 		case YFS_ENDPOINT_IPV4:
 			if (ntohl(bp[0]) != sizeof(__be32) * 2)
-				return afs_protocol_error(call, -EBADMSG);
+				return afs_protocol_error(call, -EBADMSG,
+							  afs_eproto_yvl_fsendpt4_len);
 			afs_merge_fs_addr4(alist, bp[1], ntohl(bp[2]));
 			bp += 3;
 			break;
 		case YFS_ENDPOINT_IPV6:
 			if (ntohl(bp[0]) != sizeof(__be32) * 5)
-				return afs_protocol_error(call, -EBADMSG);
+				return afs_protocol_error(call, -EBADMSG,
+							  afs_eproto_yvl_fsendpt6_len);
 			afs_merge_fs_addr6(alist, bp + 1, ntohl(bp[5]));
 			bp += 6;
 			break;
 		default:
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_yvl_fsendpt_type);
 		}
 
 		/* Got either the type of the next entry or the count of
@@ -507,10 +509,9 @@ again:
 		 */
 		call->count2 = ntohl(*bp++);
 
-		call->offset = 0;
 		call->count--;
 		if (call->count > 0)
-			goto again;
+			goto next_fsendpoint;
 
 	extract_volendpoints:
 		/* Extract the list of volEndpoints. */
@@ -518,8 +519,10 @@ again:
 		if (!call->count)
 			goto end;
 		if (call->count > YFS_MAXENDPOINTS)
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_yvl_vlendpt_type);
 
+		afs_extract_to_buf(call, 1 * sizeof(__be32));
 		call->unmarshall = 3;
 
 		/* Extract the type of volEndpoints[0].  Normally we would
@@ -527,17 +530,14 @@ again:
 		 * data of the current one, but this is the first...
 		 */
 	case 3:
-		ret = afs_extract_data(call, call->buffer, sizeof(__be32), true);
+		ret = afs_extract_data(call, true);
 		if (ret < 0)
 			return ret;
 
 		bp = call->buffer;
-		call->count2 = ntohl(*bp++);
-		call->offset = 0;
-		call->unmarshall = 4;
 
-		/* Extract volEndpoints[] entries */
+	next_volendpoint:
-	case 4:
+		call->count2 = ntohl(*bp++);
 		switch (call->count2) {
 		case YFS_ENDPOINT_IPV4:
 			size = sizeof(__be32) * (1 + 1 + 1);
@@ -546,12 +546,18 @@ again:
 			size = sizeof(__be32) * (1 + 4 + 1);
 			break;
 		default:
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_yvl_vlendpt_type);
 		}
 
 		if (call->count > 1)
-			size += sizeof(__be32);
+			size += sizeof(__be32); /* Get next type too */
-		ret = afs_extract_data(call, call->buffer, size, true);
+		afs_extract_to_buf(call, size);
+		call->unmarshall = 4;
+
+		/* Extract volEndpoints[] entries */
+	case 4:
+		ret = afs_extract_data(call, true);
 		if (ret < 0)
 			return ret;
 
@@ -559,34 +565,35 @@ again:
 		switch (call->count2) {
 		case YFS_ENDPOINT_IPV4:
 			if (ntohl(bp[0]) != sizeof(__be32) * 2)
-				return afs_protocol_error(call, -EBADMSG);
+				return afs_protocol_error(call, -EBADMSG,
+							  afs_eproto_yvl_vlendpt4_len);
 			bp += 3;
 			break;
 		case YFS_ENDPOINT_IPV6:
 			if (ntohl(bp[0]) != sizeof(__be32) * 5)
-				return afs_protocol_error(call, -EBADMSG);
+				return afs_protocol_error(call, -EBADMSG,
+							  afs_eproto_yvl_vlendpt6_len);
 			bp += 6;
 			break;
 		default:
-			return afs_protocol_error(call, -EBADMSG);
+			return afs_protocol_error(call, -EBADMSG,
+						  afs_eproto_yvl_vlendpt_type);
 		}
 
 		/* Got either the type of the next entry or the count of
 		 * volEndpoints if no more fsEndpoints.
 		 */
-		call->offset = 0;
 		call->count--;
-		if (call->count > 0) {
+		if (call->count > 0)
-			call->count2 = ntohl(*bp++);
+			goto next_volendpoint;
-			goto again;
-		}
 
 	end:
+		afs_extract_discard(call, 0);
 		call->unmarshall = 5;
 
 		/* Done */
 	case 5:
-		ret = afs_extract_data(call, call->buffer, 0, false);
+		ret = afs_extract_data(call, false);
 		if (ret < 0)
 			return ret;
 		call->unmarshall = 6;
@@ -596,11 +603,6 @@ again:
 	}
 
 	alist = call->reply[0];
-
-	/* Start with IPv6 if available. */
-	if (alist->nr_ipv4 < alist->nr_addrs)
-		alist->index = alist->nr_ipv4;
-
 	_leave(" = 0 [done]");
 	return 0;
 }
@@ -619,12 +621,11 @@ static const struct afs_call_type afs_YFSVLGetEndpoints = {
  * Dispatch an operation to get the addresses for a server, where the server is
  * nominated by UUID.
  */
-struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *net,
+struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
-					      struct afs_addr_cursor *ac,
-					      struct key *key,
 					      const uuid_t *uuid)
 {
 	struct afs_call *call;
+	struct afs_net *net = vc->cell->net;
 	__be32 *bp;
 
 	_enter("");
@@ -635,7 +636,7 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *net,
 	if (!call)
 		return ERR_PTR(-ENOMEM);
 
-	call->key = key;
+	call->key = vc->key;
 	call->reply[0] = NULL;
 	call->ret_reply0 = true;
 
@@ -646,5 +647,5 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *net,
 	memcpy(bp, uuid, sizeof(*uuid)); /* Type opr_uuid */
 
 	trace_afs_make_vl_call(call);
-	return (struct afs_addr_list *)afs_make_call(ac, call, GFP_KERNEL, false);
+	return (struct afs_addr_list *)afs_make_call(&vc->ac, call, GFP_KERNEL, false);
 }

fs/afs/volume.c

@@ -74,55 +74,19 @@ static struct afs_vldb_entry *afs_vl_lookup_vldb(struct afs_cell *cell,
 						 const char *volname,
 						 size_t volnamesz)
 {
-	struct afs_addr_cursor ac;
+	struct afs_vldb_entry *vldb = ERR_PTR(-EDESTADDRREQ);
-	struct afs_vldb_entry *vldb;
+	struct afs_vl_cursor vc;
 	int ret;
 
-	ret = afs_set_vl_cursor(&ac, cell);
+	if (!afs_begin_vlserver_operation(&vc, cell, key))
-	if (ret < 0)
+		return ERR_PTR(-ERESTARTSYS);
-		return ERR_PTR(ret);
 
-	while (afs_iterate_addresses(&ac)) {
+	while (afs_select_vlserver(&vc)) {
-		if (!test_bit(ac.index, &ac.alist->probed)) {
+		vldb = afs_vl_get_entry_by_name_u(&vc, volname, volnamesz);
-			ret = afs_vl_get_capabilities(cell->net, &ac, key);
-			switch (ret) {
-			case VL_SERVICE:
-				clear_bit(ac.index, &ac.alist->yfs);
-				set_bit(ac.index, &ac.alist->probed);
-				ac.addr->srx_service = ret;
-				break;
-			case YFS_VL_SERVICE:
-				set_bit(ac.index, &ac.alist->yfs);
-				set_bit(ac.index, &ac.alist->probed);
-				ac.addr->srx_service = ret;
-				break;
-			}
 	}
 
-		vldb = afs_vl_get_entry_by_name_u(cell->net, &ac, key,
+	ret = afs_end_vlserver_operation(&vc);
-						  volname, volnamesz);
+	return ret < 0 ? ERR_PTR(ret) : vldb;
-		switch (ac.error) {
-		case 0:
-			afs_end_cursor(&ac);
-			return vldb;
-		case -ECONNABORTED:
-			ac.error = afs_abort_to_error(ac.abort_code);
-			goto error;
-		case -ENOMEM:
-		case -ENONET:
-			goto error;
-		case -ENETUNREACH:
-		case -EHOSTUNREACH:
-		case -ECONNREFUSED:
-			break;
-		default:
-			ac.error = -EIO;
-			goto error;
-		}
-	}
-
-error:
-	return ERR_PTR(afs_end_cursor(&ac));
 }
 
 /*
@@ -270,7 +234,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 	/* We look up an ID by passing it as a decimal string in the
 	 * operation's name parameter.
 	 */
-	idsz = sprintf(idbuf, "%u", volume->vid);
+	idsz = sprintf(idbuf, "%llu", volume->vid);
 
 	vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz);
 	if (IS_ERR(vldb)) {

fs/afs/write.c

@@ -33,10 +33,21 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
 			 loff_t pos, unsigned int len, struct page *page)
 {
 	struct afs_read *req;
+	size_t p;
+	void *data;
 	int ret;
 
 	_enter(",,%llu", (unsigned long long)pos);
 
+	if (pos >= vnode->vfs_inode.i_size) {
+		p = pos & ~PAGE_MASK;
+		ASSERTCMP(p + len, <=, PAGE_SIZE);
+		data = kmap(page);
+		memset(data + p, 0, len);
+		kunmap(page);
+		return 0;
+	}
+
 	req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *),
 		      GFP_KERNEL);
 	if (!req)
@@ -81,7 +92,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index = pos >> PAGE_SHIFT;
 	int ret;
 
-	_enter("{%x:%u},{%lx},%u,%u",
+	_enter("{%llx:%llu},{%lx},%u,%u",
 	       vnode->fid.vid, vnode->fid.vnode, index, from, to);
 
 	/* We want to store information about how much of a page is altered in
@@ -181,7 +192,7 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 	loff_t i_size, maybe_i_size;
 	int ret;
 
-	_enter("{%x:%u},{%lx}",
+	_enter("{%llx:%llu},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, page->index);
 
 	maybe_i_size = pos + copied;
@@ -230,7 +241,7 @@ static void afs_kill_pages(struct address_space *mapping,
 	struct pagevec pv;
 	unsigned count, loop;
 
-	_enter("{%x:%u},%lx-%lx",
+	_enter("{%llx:%llu},%lx-%lx",
 	       vnode->fid.vid, vnode->fid.vnode, first, last);
 
 	pagevec_init(&pv);
@@ -272,7 +283,7 @@ static void afs_redirty_pages(struct writeback_control *wbc,
 	struct pagevec pv;
 	unsigned count, loop;
 
-	_enter("{%x:%u},%lx-%lx",
+	_enter("{%llx:%llu},%lx-%lx",
 	       vnode->fid.vid, vnode->fid.vnode, first, last);
 
 	pagevec_init(&pv);
@@ -314,7 +325,7 @@ static int afs_store_data(struct address_space *mapping,
 	struct list_head *p;
 	int ret = -ENOKEY, ret2;
 
-	_enter("%s{%x:%u.%u},%lx,%lx,%x,%x",
+	_enter("%s{%llx:%llu.%u},%lx,%lx,%x,%x",
 	       vnode->volume->name,
 	       vnode->fid.vid,
 	       vnode->fid.vnode,
@@ -533,6 +544,7 @@ no_more:
 	case -ENOENT:
 	case -ENOMEDIUM:
 	case -ENXIO:
+		trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail);
 		afs_kill_pages(mapping, first, last);
 		mapping_set_error(mapping, ret);
 		break;
@@ -675,7 +687,7 @@ void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
 	unsigned count, loop;
 	pgoff_t first = call->first, last = call->last;
 
-	_enter("{%x:%u},{%lx-%lx}",
+	_enter("{%llx:%llu},{%lx-%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, first, last);
 
 	pagevec_init(&pv);
@@ -714,7 +726,7 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t result;
 	size_t count = iov_iter_count(from);
 
-	_enter("{%x.%u},{%zu},",
+	_enter("{%llx:%llu},{%zu},",
 	       vnode->fid.vid, vnode->fid.vnode, count);
 
 	if (IS_SWAPFILE(&vnode->vfs_inode)) {
@@ -742,7 +754,7 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct inode *inode = file_inode(file);
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 
-	_enter("{%x:%u},{n=%pD},%d",
+	_enter("{%llx:%llu},{n=%pD},%d",
 	       vnode->fid.vid, vnode->fid.vnode, file,
 	       datasync);
 
@@ -760,7 +772,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 	unsigned long priv;
 
-	_enter("{{%x:%u}},{%lx}",
+	_enter("{{%llx:%llu}},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, vmf->page->index);
 
 	sb_start_pagefault(inode->i_sb);

fs/afs/xattr.c

@@ -72,7 +72,7 @@ static int afs_xattr_get_fid(const struct xattr_handler *handler,
 	char text[8 + 1 + 8 + 1 + 8 + 1];
 	size_t len;
 
-	len = sprintf(text, "%x:%x:%x",
+	len = sprintf(text, "%llx:%llx:%x",
 		      vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
 	if (size == 0)
 		return len;

fs/block_dev.c

@@ -349,7 +349,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 
 	dio->size = 0;
 	dio->multi_bio = false;
-	dio->should_dirty = is_read && (iter->type == ITER_IOVEC);
+	dio->should_dirty = is_read && iter_is_iovec(iter);
 
 	blk_start_plug(&plug);
 	for (;;) {

fs/ceph/file.c

@@ -615,7 +615,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 
 		more = len < iov_iter_count(to);
 
-		if (unlikely(to->type & ITER_PIPE)) {
+		if (unlikely(iov_iter_is_pipe(to))) {
 			ret = iov_iter_get_pages_alloc(to, &pages, len,
 						       &page_off);
 			if (ret <= 0) {
@@ -662,7 +662,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 			ret += zlen;
 		}
 
-		if (unlikely(to->type & ITER_PIPE)) {
+		if (unlikely(iov_iter_is_pipe(to))) {
 			if (ret > 0) {
 				iov_iter_advance(to, ret);
 				off += ret;
@@ -815,7 +815,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 				aio_req->total_len = rc + zlen;
 			}
 
-			iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs,
+			iov_iter_bvec(&i, READ, osd_data->bvec_pos.bvecs,
 				      osd_data->num_bvecs,
 				      osd_data->bvec_pos.iter.bi_size);
 			iov_iter_advance(&i, rc);
@@ -1038,8 +1038,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 				int zlen = min_t(size_t, len - ret,
 						 size - pos - ret);
 
-				iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages,
+				iov_iter_bvec(&i, READ, bvecs, num_pages, len);
-					      len);
 				iov_iter_advance(&i, ret);
 				iov_iter_zero(zlen, &i);
 				ret += zlen;

fs/cifs/connect.c

@@ -589,7 +589,7 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 {
 	struct msghdr smb_msg;
 	struct kvec iov = {.iov_base = buf, .iov_len = to_read};
-	iov_iter_kvec(&smb_msg.msg_iter, READ | ITER_KVEC, &iov, 1, to_read);
+	iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read);
 
 	return cifs_readv_from_socket(server, &smb_msg);
 }
@@ -601,7 +601,7 @@ cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
 	struct msghdr smb_msg;
 	struct bio_vec bv = {
 		.bv_page = page, .bv_len = to_read, .bv_offset = page_offset};
-	iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read);
+	iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read);
 	return cifs_readv_from_socket(server, &smb_msg);
 }
 

fs/cifs/file.c

@@ -3004,7 +3004,7 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter)
 		size_t copy = min_t(size_t, remaining, PAGE_SIZE);
 		size_t written;
 
-		if (unlikely(iter->type & ITER_PIPE)) {
+		if (unlikely(iov_iter_is_pipe(iter))) {
 			void *addr = kmap_atomic(page);
 
 			written = copy_to_iter(addr, copy, iter);
@@ -3316,7 +3316,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
 	if (!is_sync_kiocb(iocb))
 		ctx->iocb = iocb;
 
-	if (to->type == ITER_IOVEC)
+	if (iter_is_iovec(to))
 		ctx->should_dirty = true;
 
 	rc = setup_aio_ctx_iter(ctx, to, READ);

fs/cifs/misc.c

@@ -788,7 +788,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
 	struct page **pages = NULL;
 	struct bio_vec *bv = NULL;
 
-	if (iter->type & ITER_KVEC) {
+	if (iov_iter_is_kvec(iter)) {
 		memcpy(&ctx->iter, iter, sizeof(struct iov_iter));
 		ctx->len = count;
 		iov_iter_advance(iter, count);
@@ -859,7 +859,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
 	ctx->bv = bv;
 	ctx->len = saved_len - count;
 	ctx->npages = npages;
-	iov_iter_bvec(&ctx->iter, ITER_BVEC | rw, ctx->bv, npages, ctx->len);
+	iov_iter_bvec(&ctx->iter, rw, ctx->bv, npages, ctx->len);
 	return 0;
 }
 

fs/cifs/smb2ops.c

@@ -3152,13 +3152,13 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 			return 0;
 		}
 
-		iov_iter_bvec(&iter, WRITE | ITER_BVEC, bvec, npages, data_len);
+		iov_iter_bvec(&iter, WRITE, bvec, npages, data_len);
 	} else if (buf_len >= data_offset + data_len) {
 		/* read response payload is in buf */
 		WARN_ONCE(npages > 0, "read data can be either in buf or in pages");
 		iov.iov_base = buf + data_offset;
 		iov.iov_len = data_len;
-		iov_iter_kvec(&iter, WRITE | ITER_KVEC, &iov, 1, data_len);
+		iov_iter_kvec(&iter, WRITE, &iov, 1, data_len);
 	} else {
 		/* read response payload cannot be in both buf and pages */
 		WARN_ONCE(1, "buf can not contain only a part of read data");

fs/cifs/smbdirect.c

@@ -2054,14 +2054,22 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
 
 	info->smbd_recv_pending++;
 
-	switch (msg->msg_iter.type) {
+	if (iov_iter_rw(&msg->msg_iter) == WRITE) {
-	case READ | ITER_KVEC:
+		/* It's a bug in upper layer to get there */
+		cifs_dbg(VFS, "CIFS: invalid msg iter dir %u\n",
+			 iov_iter_rw(&msg->msg_iter));
+		rc = -EINVAL;
+		goto out;
+	}
+
+	switch (iov_iter_type(&msg->msg_iter)) {
+	case ITER_KVEC:
 		buf = msg->msg_iter.kvec->iov_base;
 		to_read = msg->msg_iter.kvec->iov_len;
 		rc = smbd_recv_buf(info, buf, to_read);
 		break;
 
-	case READ | ITER_BVEC:
+	case ITER_BVEC:
 		page = msg->msg_iter.bvec->bv_page;
 		page_offset = msg->msg_iter.bvec->bv_offset;
 		to_read = msg->msg_iter.bvec->bv_len;
@@ -2071,10 +2079,11 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
 	default:
 		/* It's a bug in upper layer to get there */
 		cifs_dbg(VFS, "CIFS: invalid msg type %d\n",
-			msg->msg_iter.type);
+			 iov_iter_type(&msg->msg_iter));
 		rc = -EINVAL;
 	}
 
+out:
 	info->smbd_recv_pending--;
 	wake_up(&info->wait_smbd_recv_pending);
 

fs/cifs/transport.c

@@ -316,8 +316,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 			.iov_base = &rfc1002_marker,
 			.iov_len  = 4
 		};
-		iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov,
+		iov_iter_kvec(&smb_msg.msg_iter, WRITE, &hiov, 1, 4);
-			      1, 4);
 		rc = smb_send_kvec(server, &smb_msg, &sent);
 		if (rc < 0)
 			goto uncork;
@@ -338,8 +337,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 			size += iov[i].iov_len;
 		}
 
-		iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC,
+		iov_iter_kvec(&smb_msg.msg_iter, WRITE, iov, n_vec, size);
-			      iov, n_vec, size);
 
 		rc = smb_send_kvec(server, &smb_msg, &sent);
 		if (rc < 0)
@@ -355,7 +353,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 			rqst_page_get_length(&rqst[j], i, &bvec.bv_len,
 					     &bvec.bv_offset);
 
-			iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
+			iov_iter_bvec(&smb_msg.msg_iter, WRITE,
 				      &bvec, 1, bvec.bv_len);
 			rc = smb_send_kvec(server, &smb_msg, &sent);
 			if (rc < 0)

fs/direct-io.c

@@ -1313,7 +1313,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
 
-	dio->should_dirty = (iter->type == ITER_IOVEC);
+	dio->should_dirty = iter_is_iovec(iter) && iov_iter_rw(iter) == READ;
 	sdio.iter = iter;
 	sdio.final_block_in_request = end >> blkbits;
 

fs/dlm/lowcomms.c

@@ -674,7 +674,7 @@ static int receive_from_sock(struct connection *con)
 		nvec = 2;
 	}
 	len = iov[0].iov_len + iov[1].iov_len;
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nvec, len);
+	iov_iter_kvec(&msg.msg_iter, READ, iov, nvec, len);
 
 	r = ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT | MSG_NOSIGNAL);
 	if (ret <= 0)

fs/fuse/file.c

@@ -1275,7 +1275,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 	ssize_t ret = 0;
 
 	/* Special case for kernel I/O: can copy directly into the buffer */
-	if (ii->type & ITER_KVEC) {
+	if (iov_iter_is_kvec(ii)) {
 		unsigned long user_addr = fuse_get_user_addr(ii);
 		size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
 

fs/iomap.c

@@ -1795,7 +1795,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (pos >= dio->i_size)
 			goto out_free_dio;
 
-		if (iter->type == ITER_IOVEC)
+		if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ)
 			dio->flags |= IOMAP_DIO_DIRTY;
 	} else {
 		flags |= IOMAP_WRITE;

fs/nfsd/vfs.c

@@ -923,7 +923,7 @@ __be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int host_err;
 
 	trace_nfsd_read_vector(rqstp, fhp, offset, *count);
-	iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count);
+	iov_iter_kvec(&iter, READ, vec, vlen, *count);
 	host_err = vfs_iter_read(file, &iter, &offset, 0);
 	return nfsd_finish_read(rqstp, fhp, file, offset, count, host_err);
 }
@@ -999,7 +999,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	if (stable && !use_wgather)
 		flags |= RWF_SYNC;
 
-	iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt);
+	iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt);
 	host_err = vfs_iter_write(file, &iter, &pos, flags);
 	if (host_err < 0)
 		goto out_nfserr;

fs/ocfs2/cluster/tcp.c

@@ -916,7 +916,7 @@ static int o2net_recv_tcp_msg(struct socket *sock, void *data, size_t len)
 {
 	struct kvec vec = { .iov_len = len, .iov_base = data, };
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT, };
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, len);
+	iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, len);
 	return sock_recvmsg(sock, &msg, MSG_DONTWAIT);
 }
 

fs/orangefs/inode.c

@@ -25,7 +25,7 @@ static int read_one_page(struct page *page)
 	struct iov_iter to;
 	struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};
 
-	iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);
+	iov_iter_bvec(&to, READ, &bv, 1, PAGE_SIZE);
 
 	gossip_debug(GOSSIP_INODE_DEBUG,
 		    "orangefs_readpage called with page %p\n",

fs/splice.c

@@ -301,7 +301,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 	struct kiocb kiocb;
 	int idx, ret;
 
-	iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len);
+	iov_iter_pipe(&to, READ, pipe, len);
 	idx = to.idx;
 	init_sync_kiocb(&kiocb, in);
 	kiocb.ki_pos = *ppos;
@@ -386,7 +386,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	 */
 	offset = *ppos & ~PAGE_MASK;
 
-	iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset);
+	iov_iter_pipe(&to, READ, pipe, len + offset);
 
 	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
 	if (res <= 0)
@@ -745,8 +745,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 			left -= this_len;
 		}
 
-		iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n,
+		iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left);
-			      sd.total_len - left);
 		ret = vfs_iter_write(out, &from, &sd.pos, 0);
 		if (ret <= 0)
 			break;

include/linux/uio.h

@@ -21,15 +21,16 @@ struct kvec {
 	size_t iov_len;
 };
 
-enum {
+enum iter_type {
 	ITER_IOVEC = 0,
 	ITER_KVEC = 2,
 	ITER_BVEC = 4,
 	ITER_PIPE = 8,
+	ITER_DISCARD = 16,
 };
 
 struct iov_iter {
-	int type;
+	unsigned int type;
 	size_t iov_offset;
 	size_t count;
 	union {
@@ -47,6 +48,41 @@ struct iov_iter {
 	};
 };
 
+static inline enum iter_type iov_iter_type(const struct iov_iter *i)
+{
+	return i->type & ~(READ | WRITE);
+}
+
+static inline bool iter_is_iovec(const struct iov_iter *i)
+{
+	return iov_iter_type(i) == ITER_IOVEC;
+}
+
+static inline bool iov_iter_is_kvec(const struct iov_iter *i)
+{
+	return iov_iter_type(i) == ITER_KVEC;
+}
+
+static inline bool iov_iter_is_bvec(const struct iov_iter *i)
+{
+	return iov_iter_type(i) == ITER_BVEC;
+}
+
+static inline bool iov_iter_is_pipe(const struct iov_iter *i)
+{
+	return iov_iter_type(i) == ITER_PIPE;
+}
+
+static inline bool iov_iter_is_discard(const struct iov_iter *i)
+{
+	return iov_iter_type(i) == ITER_DISCARD;
+}
+
+static inline unsigned char iov_iter_rw(const struct iov_iter *i)
+{
+	return i->type & (READ | WRITE);
+}
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -74,7 +110,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
 }
 
 #define iov_for_each(iov, iter, start)				\
-	if (!((start).type & (ITER_BVEC | ITER_PIPE)))		\
+	if (iov_iter_type(start) == ITER_IOVEC ||		\
+	    iov_iter_type(start) == ITER_KVEC)			\
 	for (iter = (start);					\
 	     (iter).count &&					\
 	     ((iov = iov_iter_iovec(&(iter))), 1);		\
@@ -181,14 +218,15 @@ size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
-void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
+void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
-void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec,
+void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec,
 			unsigned long nr_segs, size_t count);
-void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec,
+void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec,
 			unsigned long nr_segs, size_t count);
-void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe,
+void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe,
 			size_t count);
+void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count);
 ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 			size_t maxsize, unsigned maxpages, size_t *start);
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
@@ -202,19 +240,6 @@ static inline size_t iov_iter_count(const struct iov_iter *i)
 	return i->count;
 }
 
-static inline bool iter_is_iovec(const struct iov_iter *i)
-{
-	return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE));
-}
-
-/*
- * Get one of READ or WRITE out of iter->type without any other flags OR'd in
- * with it.
- *
- * The ?: is just for type safety.
- */
-#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE))
-
 /*
  * Cap the iov_iter by given limit; note that the second argument is
  * *not* the new size - it's upper limit for such.  Passing it a value

include/trace/events/afs.h

@@ -54,6 +54,35 @@ enum afs_fs_operation {
 	afs_FS_StoreData64		= 65538, /* AFS Store file data */
 	afs_FS_GiveUpAllCallBacks	= 65539, /* AFS Give up all our callbacks on a server */
 	afs_FS_GetCapabilities		= 65540, /* AFS Get FS server capabilities */
+
+	yfs_FS_FetchData		= 130,	 /* YFS Fetch file data */
+	yfs_FS_FetchACL			= 64131, /* YFS Fetch file ACL */
+	yfs_FS_FetchStatus		= 64132, /* YFS Fetch file status */
+	yfs_FS_StoreACL			= 64134, /* YFS Store file ACL */
+	yfs_FS_StoreStatus		= 64135, /* YFS Store file status */
+	yfs_FS_RemoveFile		= 64136, /* YFS Remove a file */
+	yfs_FS_CreateFile		= 64137, /* YFS Create a file */
+	yfs_FS_Rename			= 64138, /* YFS Rename or move a file or directory */
+	yfs_FS_Symlink			= 64139, /* YFS Create a symbolic link */
+	yfs_FS_Link			= 64140, /* YFS Create a hard link */
+	yfs_FS_MakeDir			= 64141, /* YFS Create a directory */
+	yfs_FS_RemoveDir		= 64142, /* YFS Remove a directory */
+	yfs_FS_GetVolumeStatus		= 64149, /* YFS Get volume status information */
+	yfs_FS_SetVolumeStatus		= 64150, /* YFS Set volume status information */
+	yfs_FS_SetLock			= 64156, /* YFS Request a file lock */
+	yfs_FS_ExtendLock		= 64157, /* YFS Extend a file lock */
+	yfs_FS_ReleaseLock		= 64158, /* YFS Release a file lock */
+	yfs_FS_Lookup			= 64161, /* YFS lookup file in directory */
+	yfs_FS_FlushCPS			= 64165,
+	yfs_FS_FetchOpaqueACL		= 64168,
+	yfs_FS_WhoAmI			= 64170,
+	yfs_FS_RemoveACL		= 64171,
+	yfs_FS_RemoveFile2		= 64173,
+	yfs_FS_StoreOpaqueACL2		= 64174,
+	yfs_FS_InlineBulkStatus		= 64536, /* YFS Fetch multiple file statuses with errors */
+	yfs_FS_FetchData64		= 64537, /* YFS Fetch file data */
+	yfs_FS_StoreData64		= 64538, /* YFS Store file data */
+	yfs_FS_UpdateSymlink		= 64540,
 };
 
 enum afs_vl_operation {
@@ -84,6 +113,44 @@ enum afs_edit_dir_reason {
 	afs_edit_dir_for_unlink,
 };
 
+enum afs_eproto_cause {
+	afs_eproto_bad_status,
+	afs_eproto_cb_count,
+	afs_eproto_cb_fid_count,
+	afs_eproto_file_type,
+	afs_eproto_ibulkst_cb_count,
+	afs_eproto_ibulkst_count,
+	afs_eproto_motd_len,
+	afs_eproto_offline_msg_len,
+	afs_eproto_volname_len,
+	afs_eproto_yvl_fsendpt4_len,
+	afs_eproto_yvl_fsendpt6_len,
+	afs_eproto_yvl_fsendpt_num,
+	afs_eproto_yvl_fsendpt_type,
+	afs_eproto_yvl_vlendpt4_len,
+	afs_eproto_yvl_vlendpt6_len,
+	afs_eproto_yvl_vlendpt_type,
+};
+
+enum afs_io_error {
+	afs_io_error_cm_reply,
+	afs_io_error_extract,
+	afs_io_error_fs_probe_fail,
+	afs_io_error_vl_lookup_fail,
+	afs_io_error_vl_probe_fail,
+};
+
+enum afs_file_error {
+	afs_file_error_dir_bad_magic,
+	afs_file_error_dir_big,
+	afs_file_error_dir_missing_page,
+	afs_file_error_dir_over_end,
+	afs_file_error_dir_small,
+	afs_file_error_dir_unmarked_ext,
+	afs_file_error_mntpt,
+	afs_file_error_writeback_fail,
+};
+
 #endif /* end __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY */
 
 /*
@@ -119,7 +186,34 @@ enum afs_edit_dir_reason {
 	EM(afs_FS_FetchData64,			"FS.FetchData64") \
 	EM(afs_FS_StoreData64,			"FS.StoreData64") \
 	EM(afs_FS_GiveUpAllCallBacks,		"FS.GiveUpAllCallBacks") \
-	E_(afs_FS_GetCapabilities,		"FS.GetCapabilities")
+	EM(afs_FS_GetCapabilities,		"FS.GetCapabilities") \
+	EM(yfs_FS_FetchACL,			"YFS.FetchACL") \
+	EM(yfs_FS_FetchStatus,			"YFS.FetchStatus") \
+	EM(yfs_FS_StoreACL,			"YFS.StoreACL") \
+	EM(yfs_FS_StoreStatus,			"YFS.StoreStatus") \
+	EM(yfs_FS_RemoveFile,			"YFS.RemoveFile") \
+	EM(yfs_FS_CreateFile,			"YFS.CreateFile") \
+	EM(yfs_FS_Rename,			"YFS.Rename") \
+	EM(yfs_FS_Symlink,			"YFS.Symlink") \
+	EM(yfs_FS_Link,				"YFS.Link") \
+	EM(yfs_FS_MakeDir,			"YFS.MakeDir") \
+	EM(yfs_FS_RemoveDir,			"YFS.RemoveDir") \
+	EM(yfs_FS_GetVolumeStatus,		"YFS.GetVolumeStatus") \
+	EM(yfs_FS_SetVolumeStatus,		"YFS.SetVolumeStatus") \
+	EM(yfs_FS_SetLock,			"YFS.SetLock") \
+	EM(yfs_FS_ExtendLock,			"YFS.ExtendLock") \
+	EM(yfs_FS_ReleaseLock,			"YFS.ReleaseLock") \
+	EM(yfs_FS_Lookup,			"YFS.Lookup") \
+	EM(yfs_FS_FlushCPS,			"YFS.FlushCPS") \
+	EM(yfs_FS_FetchOpaqueACL,		"YFS.FetchOpaqueACL") \
+	EM(yfs_FS_WhoAmI,			"YFS.WhoAmI") \
+	EM(yfs_FS_RemoveACL,			"YFS.RemoveACL") \
+	EM(yfs_FS_RemoveFile2,			"YFS.RemoveFile2") \
+	EM(yfs_FS_StoreOpaqueACL2,		"YFS.StoreOpaqueACL2") \
+	EM(yfs_FS_InlineBulkStatus,		"YFS.InlineBulkStatus") \
+	EM(yfs_FS_FetchData64,			"YFS.FetchData64") \
+	EM(yfs_FS_StoreData64,			"YFS.StoreData64") \
+	E_(yfs_FS_UpdateSymlink,		"YFS.UpdateSymlink")
 
 #define afs_vl_operations \
 	EM(afs_VL_GetEntryByNameU,		"VL.GetEntryByNameU") \
@@ -146,6 +240,40 @@ enum afs_edit_dir_reason {
 	EM(afs_edit_dir_for_symlink,		"Symlnk") \
 	E_(afs_edit_dir_for_unlink,		"Unlink")
 
+#define afs_eproto_causes			\
+	EM(afs_eproto_bad_status,	"BadStatus") \
+	EM(afs_eproto_cb_count,		"CbCount") \
+	EM(afs_eproto_cb_fid_count,	"CbFidCount") \
+	EM(afs_eproto_file_type,	"FileTYpe") \
+	EM(afs_eproto_ibulkst_cb_count,	"IBS.CbCount") \
+	EM(afs_eproto_ibulkst_count,	"IBS.FidCount") \
+	EM(afs_eproto_motd_len,		"MotdLen") \
+	EM(afs_eproto_offline_msg_len,	"OfflineMsgLen") \
+	EM(afs_eproto_volname_len,	"VolNameLen") \
+	EM(afs_eproto_yvl_fsendpt4_len,	"YVL.FsEnd4Len") \
+	EM(afs_eproto_yvl_fsendpt6_len,	"YVL.FsEnd6Len") \
+	EM(afs_eproto_yvl_fsendpt_num,	"YVL.FsEndCount") \
+	EM(afs_eproto_yvl_fsendpt_type,	"YVL.FsEndType") \
+	EM(afs_eproto_yvl_vlendpt4_len,	"YVL.VlEnd4Len") \
+	EM(afs_eproto_yvl_vlendpt6_len,	"YVL.VlEnd6Len") \
+	E_(afs_eproto_yvl_vlendpt_type,	"YVL.VlEndType")
+
+#define afs_io_errors							\
+	EM(afs_io_error_cm_reply,		"CM_REPLY")		\
+	EM(afs_io_error_extract,		"EXTRACT")		\
+	EM(afs_io_error_fs_probe_fail,		"FS_PROBE_FAIL")	\
+	EM(afs_io_error_vl_lookup_fail,		"VL_LOOKUP_FAIL")	\
+	E_(afs_io_error_vl_probe_fail,		"VL_PROBE_FAIL")
+
+#define afs_file_errors							\
+	EM(afs_file_error_dir_bad_magic,	"DIR_BAD_MAGIC")	\
+	EM(afs_file_error_dir_big,		"DIR_BIG")		\
+	EM(afs_file_error_dir_missing_page,	"DIR_MISSING_PAGE")	\
+	EM(afs_file_error_dir_over_end,		"DIR_ENT_OVER_END")	\
+	EM(afs_file_error_dir_small,		"DIR_SMALL")		\
+	EM(afs_file_error_dir_unmarked_ext,	"DIR_UNMARKED_EXT")	\
+	EM(afs_file_error_mntpt,		"MNTPT_READ_FAILED")	\
+	E_(afs_file_error_writeback_fail,	"WRITEBACK_FAILED")
 
 /*
  * Export enum symbols via userspace.
@@ -160,6 +288,9 @@ afs_fs_operations;
 afs_vl_operations;
 afs_edit_dir_ops;
 afs_edit_dir_reasons;
+afs_eproto_causes;
+afs_io_errors;
+afs_file_errors;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -170,17 +301,16 @@ afs_edit_dir_reasons;
 #define EM(a, b)	{ a, b },
 #define E_(a, b)	{ a, b }
 
-TRACE_EVENT(afs_recv_data,
+TRACE_EVENT(afs_receive_data,
-	    TP_PROTO(struct afs_call *call, unsigned count, unsigned offset,
+	    TP_PROTO(struct afs_call *call, struct iov_iter *iter,
 		     bool want_more, int ret),
 
-	    TP_ARGS(call, count, offset, want_more, ret),
+	    TP_ARGS(call, iter, want_more, ret),
 
 	    TP_STRUCT__entry(
+		    __field(loff_t,			remain		)
 		    __field(unsigned int,		call		)
 		    __field(enum afs_call_state,	state		)
-		    __field(unsigned int,		count		)
-		    __field(unsigned int,		offset		)
 		    __field(unsigned short,		unmarshall	)
 		    __field(bool,			want_more	)
 		    __field(int,			ret		)
@@ -190,17 +320,18 @@ TRACE_EVENT(afs_recv_data,
 		    __entry->call	= call->debug_id;
 		    __entry->state	= call->state;
 		    __entry->unmarshall	= call->unmarshall;
-		    __entry->count	= count;
+		    __entry->remain	= iov_iter_count(iter);
-		    __entry->offset	= offset;
 		    __entry->want_more	= want_more;
 		    __entry->ret	= ret;
 			   ),
 
-	    TP_printk("c=%08x s=%u u=%u %u/%u wm=%u ret=%d",
+	    TP_printk("c=%08x r=%llu u=%u w=%u s=%u ret=%d",
 		      __entry->call,
-		      __entry->state, __entry->unmarshall,
+		      __entry->remain,
-		      __entry->offset, __entry->count,
+		      __entry->unmarshall,
-		      __entry->want_more, __entry->ret)
+		      __entry->want_more,
+		      __entry->state,
+		      __entry->ret)
 	    );
 
 TRACE_EVENT(afs_notify_call,
@@ -301,7 +432,7 @@ TRACE_EVENT(afs_make_fs_call,
 		    }
 			   ),
 
-	    TP_printk("c=%08x %06x:%06x:%06x %s",
+	    TP_printk("c=%08x %06llx:%06llx:%06x %s",
 		      __entry->call,
 		      __entry->fid.vid,
 		      __entry->fid.vnode,
@@ -555,24 +686,70 @@ TRACE_EVENT(afs_edit_dir,
 	    );
 
 TRACE_EVENT(afs_protocol_error,
-	    TP_PROTO(struct afs_call *call, int error, const void *where),
+	    TP_PROTO(struct afs_call *call, int error, enum afs_eproto_cause cause),
+
+	    TP_ARGS(call, error, cause),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call		)
+		    __field(int,			error		)
+		    __field(enum afs_eproto_cause,	cause		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call ? call->debug_id : 0;
+		    __entry->error = error;
+		    __entry->cause = cause;
+			   ),
+
+	    TP_printk("c=%08x r=%d %s",
+		      __entry->call, __entry->error,
+		      __print_symbolic(__entry->cause, afs_eproto_causes))
+	    );
+
+TRACE_EVENT(afs_io_error,
+	    TP_PROTO(unsigned int call, int error, enum afs_io_error where),
 
 	    TP_ARGS(call, error, where),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	call		)
 		    __field(int,		error		)
-		    __field(const void *,	where		)
+		    __field(enum afs_io_error,	where		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call ? call->debug_id : 0;
+		    __entry->call = call;
 		    __entry->error = error;
 		    __entry->where = where;
 			   ),
 
-	    TP_printk("c=%08x r=%d sp=%pSR",
+	    TP_printk("c=%08x r=%d %s",
-		      __entry->call, __entry->error, __entry->where)
+		      __entry->call, __entry->error,
+		      __print_symbolic(__entry->where, afs_io_errors))
+	    );
+
+TRACE_EVENT(afs_file_error,
+	    TP_PROTO(struct afs_vnode *vnode, int error, enum afs_file_error where),
+
+	    TP_ARGS(vnode, error, where),
+
+	    TP_STRUCT__entry(
+		    __field_struct(struct afs_fid,	fid		)
+		    __field(int,			error		)
+		    __field(enum afs_file_error,	where		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->fid = vnode->fid;
+		    __entry->error = error;
+		    __entry->where = where;
+			   ),
+
+	    TP_printk("%llx:%llx:%x r=%d %s",
+		      __entry->fid.vid, __entry->fid.vnode, __entry->fid.unique,
+		      __entry->error,
+		      __print_symbolic(__entry->where, afs_file_errors))
 	    );
 
 TRACE_EVENT(afs_cm_no_server,

lib/iov_iter.c

@@ -83,6 +83,7 @@
 			const struct kvec *kvec;		\
 			struct kvec v;				\
 			iterate_kvec(i, n, v, kvec, skip, (K))	\
+		} else if (unlikely(i->type & ITER_DISCARD)) {	\
 		} else {					\
 			const struct iovec *iov;		\
 			struct iovec v;				\
@@ -114,6 +115,8 @@
 			}					\
 			i->nr_segs -= kvec - i->kvec;		\
 			i->kvec = kvec;				\
+		} else if (unlikely(i->type & ITER_DISCARD)) {	\
+			skip += n;				\
 		} else {					\
 			const struct iovec *iov;		\
 			struct iovec v;				\
@@ -428,17 +431,19 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
 }
 EXPORT_SYMBOL(iov_iter_fault_in_readable);
 
-void iov_iter_init(struct iov_iter *i, int direction,
+void iov_iter_init(struct iov_iter *i, unsigned int direction,
 			const struct iovec *iov, unsigned long nr_segs,
 			size_t count)
 {
+	WARN_ON(direction & ~(READ | WRITE));
+	direction &= READ | WRITE;
+
 	/* It will get better.  Eventually... */
 	if (uaccess_kernel()) {
-		direction |= ITER_KVEC;
+		i->type = ITER_KVEC | direction;
-		i->type = direction;
 		i->kvec = (struct kvec *)iov;
 	} else {
-		i->type = direction;
+		i->type = ITER_IOVEC | direction;
 		i->iov = iov;
 	}
 	i->nr_segs = nr_segs;
@@ -558,7 +563,7 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
-	if (unlikely(i->type & ITER_PIPE))
+	if (unlikely(iov_iter_is_pipe(i)))
 		return copy_pipe_to_iter(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
@@ -658,7 +663,7 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
-	if (unlikely(i->type & ITER_PIPE))
+	if (unlikely(iov_iter_is_pipe(i)))
 		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
@@ -692,7 +697,7 @@ EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		WARN_ON(1);
 		return 0;
 	}
@@ -712,7 +717,7 @@ EXPORT_SYMBOL(_copy_from_iter);
 bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		WARN_ON(1);
 		return false;
 	}
@@ -739,7 +744,7 @@ EXPORT_SYMBOL(_copy_from_iter_full);
 size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		WARN_ON(1);
 		return 0;
 	}
@@ -773,7 +778,7 @@ EXPORT_SYMBOL(_copy_from_iter_nocache);
 size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		WARN_ON(1);
 		return 0;
 	}
@@ -794,7 +799,7 @@ EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache);
 bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		WARN_ON(1);
 		return false;
 	}
@@ -836,7 +841,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 		size_t wanted = copy_to_iter(kaddr + offset, bytes, i);
 		kunmap_atomic(kaddr);
 		return wanted;
-	} else if (likely(!(i->type & ITER_PIPE)))
+	} else if (unlikely(iov_iter_is_discard(i)))
+		return bytes;
+	else if (likely(!iov_iter_is_pipe(i)))
 		return copy_page_to_iter_iovec(page, offset, bytes, i);
 	else
 		return copy_page_to_iter_pipe(page, offset, bytes, i);
@@ -848,7 +855,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 {
 	if (unlikely(!page_copy_sane(page, offset, bytes)))
 		return 0;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
 		WARN_ON(1);
 		return 0;
 	}
@@ -888,7 +895,7 @@ static size_t pipe_zero(size_t bytes, struct iov_iter *i)
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(i->type & ITER_PIPE))
+	if (unlikely(iov_iter_is_pipe(i)))
 		return pipe_zero(bytes, i);
 	iterate_and_advance(i, bytes, v,
 		clear_user(v.iov_base, v.iov_len),
@@ -908,7 +915,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 		kunmap_atomic(kaddr);
 		return 0;
 	}
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
 		kunmap_atomic(kaddr);
 		WARN_ON(1);
 		return 0;
@@ -972,10 +979,14 @@ static void pipe_advance(struct iov_iter *i, size_t size)
 
 void iov_iter_advance(struct iov_iter *i, size_t size)
 {
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		pipe_advance(i, size);
 		return;
 	}
+	if (unlikely(iov_iter_is_discard(i))) {
+		i->count -= size;
+		return;
+	}
 	iterate_and_advance(i, size, v, 0, 0, 0)
 }
 EXPORT_SYMBOL(iov_iter_advance);
@@ -987,7 +998,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
 	if (WARN_ON(unroll > MAX_RW_COUNT))
 		return;
 	i->count += unroll;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		struct pipe_inode_info *pipe = i->pipe;
 		int idx = i->idx;
 		size_t off = i->iov_offset;
@@ -1011,12 +1022,14 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
 		pipe_truncate(i);
 		return;
 	}
+	if (unlikely(iov_iter_is_discard(i)))
+		return;
 	if (unroll <= i->iov_offset) {
 		i->iov_offset -= unroll;
 		return;
 	}
 	unroll -= i->iov_offset;
-	if (i->type & ITER_BVEC) {
+	if (iov_iter_is_bvec(i)) {
 		const struct bio_vec *bvec = i->bvec;
 		while (1) {
 			size_t n = (--bvec)->bv_len;
@@ -1049,23 +1062,25 @@ EXPORT_SYMBOL(iov_iter_revert);
  */
 size_t iov_iter_single_seg_count(const struct iov_iter *i)
 {
-	if (unlikely(i->type & ITER_PIPE))
+	if (unlikely(iov_iter_is_pipe(i)))
 		return i->count;	// it is a silly place, anyway
 	if (i->nr_segs == 1)
 		return i->count;
-	else if (i->type & ITER_BVEC)
+	if (unlikely(iov_iter_is_discard(i)))
+		return i->count;
+	else if (iov_iter_is_bvec(i))
 		return min(i->count, i->bvec->bv_len - i->iov_offset);
 	else
 		return min(i->count, i->iov->iov_len - i->iov_offset);
 }
 EXPORT_SYMBOL(iov_iter_single_seg_count);
 
-void iov_iter_kvec(struct iov_iter *i, int direction,
+void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
 			const struct kvec *kvec, unsigned long nr_segs,
 			size_t count)
 {
-	BUG_ON(!(direction & ITER_KVEC));
+	WARN_ON(direction & ~(READ | WRITE));
-	i->type = direction;
+	i->type = ITER_KVEC | (direction & (READ | WRITE));
 	i->kvec = kvec;
 	i->nr_segs = nr_segs;
 	i->iov_offset = 0;
@@ -1073,12 +1088,12 @@ void iov_iter_kvec(struct iov_iter *i, int direction,
 }
 EXPORT_SYMBOL(iov_iter_kvec);
 
-void iov_iter_bvec(struct iov_iter *i, int direction,
+void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
 			const struct bio_vec *bvec, unsigned long nr_segs,
 			size_t count)
 {
-	BUG_ON(!(direction & ITER_BVEC));
+	WARN_ON(direction & ~(READ | WRITE));
-	i->type = direction;
+	i->type = ITER_BVEC | (direction & (READ | WRITE));
 	i->bvec = bvec;
 	i->nr_segs = nr_segs;
 	i->iov_offset = 0;
@@ -1086,13 +1101,13 @@ void iov_iter_bvec(struct iov_iter *i, int direction,
 }
 EXPORT_SYMBOL(iov_iter_bvec);
 
-void iov_iter_pipe(struct iov_iter *i, int direction,
+void iov_iter_pipe(struct iov_iter *i, unsigned int direction,
 			struct pipe_inode_info *pipe,
 			size_t count)
 {
-	BUG_ON(direction != ITER_PIPE);
+	BUG_ON(direction != READ);
 	WARN_ON(pipe->nrbufs == pipe->buffers);
-	i->type = direction;
+	i->type = ITER_PIPE | READ;
 	i->pipe = pipe;
 	i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
 	i->iov_offset = 0;
@@ -1101,12 +1116,30 @@ void iov_iter_pipe(struct iov_iter *i, int direction,
 }
 EXPORT_SYMBOL(iov_iter_pipe);
 
+/**
+ * iov_iter_discard - Initialise an I/O iterator that discards data
+ * @i: The iterator to initialise.
+ * @direction: The direction of the transfer.
+ * @count: The size of the I/O buffer in bytes.
+ *
+ * Set up an I/O iterator that just discards everything that's written to it.
+ * It's only available as a READ iterator.
+ */
+void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
+{
+	BUG_ON(direction != READ);
+	i->type = ITER_DISCARD | READ;
+	i->count = count;
+	i->iov_offset = 0;
+}
+EXPORT_SYMBOL(iov_iter_discard);
+
 unsigned long iov_iter_alignment(const struct iov_iter *i)
 {
 	unsigned long res = 0;
 	size_t size = i->count;
 
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx]))
 			return size | i->iov_offset;
 		return size;
@@ -1125,7 +1158,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
 	unsigned long res = 0;
 	size_t size = i->count;
 
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
 		WARN_ON(1);
 		return ~0U;
 	}
@@ -1193,8 +1226,11 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 	if (maxsize > i->count)
 		maxsize = i->count;
 
-	if (unlikely(i->type & ITER_PIPE))
+	if (unlikely(iov_iter_is_pipe(i)))
 		return pipe_get_pages(i, pages, maxsize, maxpages, start);
+	if (unlikely(iov_iter_is_discard(i)))
+		return -EFAULT;
+
 	iterate_all_kinds(i, maxsize, v, ({
 		unsigned long addr = (unsigned long)v.iov_base;
 		size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
@@ -1205,7 +1241,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 			len = maxpages * PAGE_SIZE;
 		addr &= ~(PAGE_SIZE - 1);
 		n = DIV_ROUND_UP(len, PAGE_SIZE);
-		res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages);
+		res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages);
 		if (unlikely(res < 0))
 			return res;
 		return (res == n ? len : res * PAGE_SIZE) - *start;
@@ -1270,8 +1306,11 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 	if (maxsize > i->count)
 		maxsize = i->count;
 
-	if (unlikely(i->type & ITER_PIPE))
+	if (unlikely(iov_iter_is_pipe(i)))
 		return pipe_get_pages_alloc(i, pages, maxsize, start);
+	if (unlikely(iov_iter_is_discard(i)))
+		return -EFAULT;
+
 	iterate_all_kinds(i, maxsize, v, ({
 		unsigned long addr = (unsigned long)v.iov_base;
 		size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
@@ -1283,7 +1322,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 		p = get_pages_array(n);
 		if (!p)
 			return -ENOMEM;
-		res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p);
+		res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p);
 		if (unlikely(res < 0)) {
 			kvfree(p);
 			return res;
@@ -1313,7 +1352,7 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
 	__wsum sum, next;
 	size_t off = 0;
 	sum = *csum;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
 		WARN_ON(1);
 		return 0;
 	}
@@ -1355,7 +1394,7 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum,
 	__wsum sum, next;
 	size_t off = 0;
 	sum = *csum;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
 		WARN_ON(1);
 		return false;
 	}
@@ -1400,7 +1439,7 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum,
 	__wsum sum, next;
 	size_t off = 0;
 	sum = *csum;
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
 		WARN_ON(1);	/* for now */
 		return 0;
 	}
@@ -1442,8 +1481,10 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages)
 
 	if (!size)
 		return 0;
+	if (unlikely(iov_iter_is_discard(i)))
+		return 0;
 
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(i))) {
 		struct pipe_inode_info *pipe = i->pipe;
 		size_t off;
 		int idx;
@@ -1481,11 +1522,13 @@ EXPORT_SYMBOL(iov_iter_npages);
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 {
 	*new = *old;
-	if (unlikely(new->type & ITER_PIPE)) {
+	if (unlikely(iov_iter_is_pipe(new))) {
 		WARN_ON(1);
 		return NULL;
 	}
-	if (new->type & ITER_BVEC)
+	if (unlikely(iov_iter_is_discard(new)))
+		return NULL;
+	if (iov_iter_is_bvec(new))
 		return new->bvec = kmemdup(new->bvec,
 				    new->nr_segs * sizeof(struct bio_vec),
 				    flags);

mm/filemap.c

@@ -2049,7 +2049,7 @@ find_page:
 					!mapping->a_ops->is_partially_uptodate)
 				goto page_not_up_to_date;
 			/* pipes can't handle partially uptodate pages */
-			if (unlikely(iter->type & ITER_PIPE))
+			if (unlikely(iov_iter_is_pipe(iter)))
 				goto page_not_up_to_date;
 			if (!trylock_page(page))
 				goto page_not_up_to_date;

mm/page_io.c

@@ -294,7 +294,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		};
 		struct iov_iter from;
 
-		iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE);
+		iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE);
 		init_sync_kiocb(&kiocb, swap_file);
 		kiocb.ki_pos = page_file_offset(page);
 

net/9p/client.c

@@ -2066,7 +2066,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	struct kvec kv = {.iov_base = data, .iov_len = count};
 	struct iov_iter to;
 
-	iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count);
+	iov_iter_kvec(&to, READ, &kv, 1, count);
 
 	p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n",
 				fid->fid, (unsigned long long) offset, count);

net/9p/trans_virtio.c

@@ -329,7 +329,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 	if (!iov_iter_count(data))
 		return 0;
 
-	if (!(data->type & ITER_KVEC)) {
+	if (iov_iter_is_kvec(data)) {
 		int n;
 		/*
 		 * We allow only p9_max_pages pinned. We wait for the

net/bluetooth/6lowpan.c

@@ -467,7 +467,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 	iv.iov_len = skb->len;
 
 	memset(&msg, 0, sizeof(msg));
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, skb->len);
 
 	err = l2cap_chan_send(chan, &msg, skb->len);
 	if (err > 0) {

net/bluetooth/a2mp.c

@@ -63,7 +63,7 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *dat
 
 	memset(&msg, 0, sizeof(msg));
 
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, total_len);
 
 	l2cap_chan_send(chan, &msg, total_len);
 

net/bluetooth/smp.c

@@ -622,7 +622,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, iv, 2, 1 + len);
 
 	l2cap_chan_send(chan, &msg, 1 + len);
 

net/ceph/messenger.c

@@ -513,7 +513,7 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
 	if (!buf)
 		msg.msg_flags |= MSG_TRUNC;
 
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
 	r = sock_recvmsg(sock, &msg, msg.msg_flags);
 	if (r == -EAGAIN)
 		r = 0;
@@ -532,7 +532,7 @@ static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
 	int r;
 
 	BUG_ON(page_offset + length > PAGE_SIZE);
-	iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length);
+	iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
 	r = sock_recvmsg(sock, &msg, msg.msg_flags);
 	if (r == -EAGAIN)
 		r = 0;
@@ -594,7 +594,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	else
 		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
 
-	iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size);
+	iov_iter_bvec(&msg.msg_iter, WRITE, &bvec, 1, size);
 	ret = sock_sendmsg(sock, &msg);
 	if (ret == -EAGAIN)
 		ret = 0;

net/netfilter/ipvs/ip_vs_sync.c

@@ -1616,7 +1616,7 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
 	EnterFunction(7);
 
 	/* Receive a packet */
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, buflen);
 	len = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
 	if (len < 0)
 		return len;

net/smc/smc_clc.c

@@ -286,7 +286,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	 */
 	krflags = MSG_PEEK | MSG_WAITALL;
 	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1,
+	iov_iter_kvec(&msg.msg_iter, READ, &vec, 1,
 			sizeof(struct smc_clc_msg_hdr));
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (signal_pending(current)) {
@@ -325,7 +325,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 
 	/* receive the complete CLC message */
 	memset(&msg, 0, sizeof(struct msghdr));
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
+	iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen);
 	krflags = MSG_WAITALL;
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {

net/socket.c

@@ -635,7 +635,7 @@ EXPORT_SYMBOL(sock_sendmsg);
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size)
 {
-	iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+	iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
 	return sock_sendmsg(sock, msg);
 }
 EXPORT_SYMBOL(kernel_sendmsg);
@@ -648,7 +648,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 	if (!sock->ops->sendmsg_locked)
 		return sock_no_sendmsg_locked(sk, msg, size);
 
-	iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+	iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
 
 	return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg));
 }
@@ -823,7 +823,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 	mm_segment_t oldfs = get_fs();
 	int result;
 
-	iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size);
+	iov_iter_kvec(&msg->msg_iter, READ, vec, num, size);
 	set_fs(KERNEL_DS);
 	result = sock_recvmsg(sock, msg, flags);
 	set_fs(oldfs);

net/sunrpc/svcsock.c

@@ -336,7 +336,7 @@ static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
 	rqstp->rq_xprt_hlen = 0;
 
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen);
+	iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen);
 	if (base != 0) {
 		iov_iter_advance(&msg.msg_iter, base);
 		buflen -= base;

net/sunrpc/xprtsock.c

@@ -361,7 +361,7 @@ static ssize_t
 xs_read_kvec(struct socket *sock, struct msghdr *msg, int flags,
 		struct kvec *kvec, size_t count, size_t seek)
 {
-	iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, kvec, 1, count);
+	iov_iter_kvec(&msg->msg_iter, READ, kvec, 1, count);
 	return xs_sock_recvmsg(sock, msg, flags, seek);
 }
 
@@ -370,7 +370,7 @@ xs_read_bvec(struct socket *sock, struct msghdr *msg, int flags,
 		struct bio_vec *bvec, unsigned long nr, size_t count,
 		size_t seek)
 {
-	iov_iter_bvec(&msg->msg_iter, READ | ITER_BVEC, bvec, nr, count);
+	iov_iter_bvec(&msg->msg_iter, READ, bvec, nr, count);
 	return xs_sock_recvmsg(sock, msg, flags, seek);
 }
 

net/tipc/topsrv.c

@@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 	iov.iov_base = &s;
 	iov.iov_len = sizeof(s);
 	msg.msg_name = NULL;
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len);
 	ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
 	if (ret == -EWOULDBLOCK)
 		return -EWOULDBLOCK;

net/tls/tls_device.c

@@ -489,7 +489,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 
 	iov.iov_base = kaddr + offset;
 	iov.iov_len = size;
-	iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
+	iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
 	rc = tls_push_data(sk, &msg_iter, size,
 			   flags, TLS_RECORD_TYPE_DATA);
 	kunmap(page);
@@ -538,7 +538,7 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
 {
 	struct iov_iter	msg_iter;
 
-	iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
+	iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0);
 	return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
 }
 

net/tls/tls_sw.c

@@ -799,7 +799,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send);
 	bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC;
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
-	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool eor = !(msg->msg_flags & MSG_MORE);
 	size_t try_to_copy, copied = 0;
 	struct sk_msg *msg_pl, *msg_en;
@@ -1457,7 +1457,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool cmsg = false;
 	int target, err = 0;
 	long timeo;
-	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	int num_async = 0;
 
 	flags |= nonblock;