/*
 *  Copyright (c) 2006,2007 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Andy Adamson <andros@citi.umich.edu>
 *  Fred Isaman <iisaman@umich.edu>
 *
 * permission is granted to use, copy, create derivative works and
 * redistribute this software and such derivative works for any purpose,
 * so long as the name of the university of michigan is not used in
 * any advertising or publicity pertaining to the use or distribution
 * of this software without specific, written prior authorization.  if
 * the above copyright notice or any other identification of the
 * university of michigan is included in any copy of any portion of
 * this software, then the disclaimer below must also be included.
 *
 * this software is provided as is, without representation from the
 * university of michigan as to its fitness for any purpose, and without
 * warranty by the university of michigan of any kind, either express
 * or implied, including without limitation the implied warranties of
 * merchantability and fitness for a particular purpose.  the regents
 * of the university of michigan shall not be liable for any damages,
 * including special, indirect, incidental, or consequential damages,
 * with respect to any claim arising out or in connection with the use
 * of the software, even if it has been or is hereafter advised of the
 * possibility of such damages.
 */

#include <linux/module.h>
#include <linux/blkdev.h>

#include "blocklayout.h"

#define NFSDBG_FACILITY         NFSDBG_PNFS_LD

static void
nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b)
{
	int i;

	*p++ = cpu_to_be32(1);
	*p++ = cpu_to_be32(b->type);
	*p++ = cpu_to_be32(b->simple.nr_sigs);
	for (i = 0; i < b->simple.nr_sigs; i++) {
		p = xdr_encode_hyper(p, b->simple.sigs[i].offset);
		p = xdr_encode_opaque(p, b->simple.sigs[i].sig,
					 b->simple.sigs[i].sig_len);
	}
}

dev_t
bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
		gfp_t gfp_mask)
{
	struct net *net = server->nfs_client->cl_net;
	struct nfs_net *nn = net_generic(net, nfs_net_id);
	struct bl_dev_msg *reply = &nn->bl_mount_reply;
	struct rpc_pipe_msg *msg = &nn->bl_pipe_msg;
	struct rpc_pipe *pipe = nn->bl_device_pipe;
	struct bl_msg_hdr *bl_msg;
	dev_t dev = 0;
	int rc;

	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);

	mutex_lock(&nn->bl_mutex);

	b->simple.len += 4;	/* single volume */
	if (b->simple.len > PAGE_SIZE)
		goto out_unlock;

	memset(msg, 0, sizeof(*msg));
	msg->len = sizeof(*bl_msg) + b->simple.len;
	msg->data = kzalloc(msg->len, gfp_mask);
	if (!msg->data)
		goto out_unlock;

	bl_msg = msg->data;
	bl_msg->type = BL_DEVICE_MOUNT;
	bl_msg->totallen = b->simple.len;
	nfs4_encode_simple(msg->data + sizeof(*bl_msg), b);

	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
	reinit_completion(&nn->bl_done);
	rc = rpc_queue_upcall(pipe, msg);
	if (rc < 0)
		goto out_free_data;

	wait_for_completion(&nn->bl_done);

	if (msg->errno < 0)
		goto out_free_data;
	if (reply->status != BL_DEVICE_REQUEST_PROC) {
		printk(KERN_WARNING "%s failed to decode device: %d\n",
			__func__, reply->status);
		goto out_free_data;
	}

	dev = MKDEV(reply->major, reply->minor);
out_free_data:
	kfree(msg->data);
out_unlock:
	mutex_unlock(&nn->bl_mutex);
	return dev;
}

static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
			 size_t mlen)
{
	struct nfs_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info,
					 nfs_net_id);
	struct rpc_pipe *pipe = nn->bl_device_pipe;
	struct bl_dev_msg reply;
	bool accepted;

	if (mlen != sizeof(reply))
		return -EINVAL;
	if (copy_from_user(&reply, src, mlen) != 0)
		return -EFAULT;

	/*
	 * Accept a reply only after blkmapd has read the whole upcall.
	 * Completion retires the message, here and in
	 * bl_pipe_destroy_msg(), so a later reply finds nothing in
	 * flight.
	 */
	spin_lock(&pipe->lock);
	accepted = rpc_msg_is_inflight(&nn->bl_pipe_msg);
	if (accepted) {
		nn->bl_pipe_msg.copied = 0;
		nn->bl_mount_reply = reply;
		complete(&nn->bl_done);
	}
	spin_unlock(&pipe->lock);
	if (!accepted)
		return -EINVAL;
	return mlen;
}

static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
{
	struct nfs_net *nn = container_of(msg, struct nfs_net, bl_pipe_msg);
	struct rpc_pipe *pipe = nn->bl_device_pipe;

	if (msg->errno >= 0)
		return;

	spin_lock(&pipe->lock);
	msg->copied = 0;
	spin_unlock(&pipe->lock);
	complete(&nn->bl_done);
}

/*
 * An upcall blkmapd has consumed is off every pipe list, so the
 * purges in rpc_pipe_release() and rpc_close_pipes() cannot reach it.
 * No downcall can arrive once the pipe is closed; release its waiter
 * here.
 */
static void bl_release_pipe(struct inode *inode)
{
	struct nfs_net *nn = net_generic(inode->i_sb->s_fs_info, nfs_net_id);
	struct rpc_pipe *pipe = nn->bl_device_pipe;

	spin_lock(&pipe->lock);
	if (rpc_msg_is_inflight(&nn->bl_pipe_msg)) {
		nn->bl_pipe_msg.copied = 0;
		nn->bl_pipe_msg.errno = -EPIPE;
		complete(&nn->bl_done);
	}
	spin_unlock(&pipe->lock);
}

static const struct rpc_pipe_ops bl_upcall_ops = {
	.upcall		= rpc_pipe_generic_upcall,
	.downcall	= bl_pipe_downcall,
	.destroy_msg	= bl_pipe_destroy_msg,
	.release_pipe	= bl_release_pipe,
};

static int nfs4blocklayout_register_sb(struct super_block *sb,
					    struct rpc_pipe *pipe)
{
	struct dentry *dir;
	int err;

	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
	if (dir == NULL)
		return -ENOENT;
	err = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
	dput(dir);
	return err;
}

static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
			   void *ptr)
{
	struct super_block *sb = ptr;
	struct net *net = sb->s_fs_info;
	struct nfs_net *nn = net_generic(net, nfs_net_id);
	int ret = 0;

	if (!try_module_get(THIS_MODULE))
		return 0;

	if (nn->bl_device_pipe == NULL) {
		module_put(THIS_MODULE);
		return 0;
	}

	switch (event) {
	case RPC_PIPEFS_MOUNT:
		ret = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
		break;
	case RPC_PIPEFS_UMOUNT:
		rpc_unlink(nn->bl_device_pipe);
		break;
	default:
		ret = -ENOTSUPP;
		break;
	}
	module_put(THIS_MODULE);
	return ret;
}

static struct notifier_block nfs4blocklayout_block = {
	.notifier_call = rpc_pipefs_event,
};

static int nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe)
{
	struct super_block *pipefs_sb;
	int ret;

	pipefs_sb = rpc_get_sb_net(net);
	if (!pipefs_sb)
		return 0;
	ret = nfs4blocklayout_register_sb(pipefs_sb, pipe);
	rpc_put_sb_net(net);
	return ret;
}

static void nfs4blocklayout_unregister_net(struct net *net,
					   struct rpc_pipe *pipe)
{
	struct super_block *pipefs_sb;

	pipefs_sb = rpc_get_sb_net(net);
	if (pipefs_sb) {
		rpc_unlink(pipe);
		rpc_put_sb_net(net);
	}
}

static int nfs4blocklayout_net_init(struct net *net)
{
	struct nfs_net *nn = net_generic(net, nfs_net_id);
	int err;

	mutex_init(&nn->bl_mutex);
	init_completion(&nn->bl_done);
	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
	if (IS_ERR(nn->bl_device_pipe))
		return PTR_ERR(nn->bl_device_pipe);
	err = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
	if (unlikely(err))
		rpc_destroy_pipe_data(nn->bl_device_pipe);
	return err;
}

static void nfs4blocklayout_net_exit(struct net *net)
{
	struct nfs_net *nn = net_generic(net, nfs_net_id);

	nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
	rpc_destroy_pipe_data(nn->bl_device_pipe);
	nn->bl_device_pipe = NULL;
}

static struct pernet_operations nfs4blocklayout_net_ops = {
	.init = nfs4blocklayout_net_init,
	.exit = nfs4blocklayout_net_exit,
};

int __init bl_init_pipefs(void)
{
	int ret;

	ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
	if (ret)
		goto out;
	ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
	if (ret)
		goto out_unregister_notifier;
	return 0;

out_unregister_notifier:
	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
out:
	return ret;
}

void bl_cleanup_pipefs(void)
{
	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
}