inode.c

/*
 *  linux/fs/nfs/inode.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  nfs inode and superblock handling functions
 *
 *  Modularised by Alan Cox <Alan.Cox@linux.org>, while hacking some
 *  experimental NFS changes. Modularisation taken straight from SYS5 fs.
 *
 *  Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
 *  J.S.Peatfield@damtp.cam.ac.uk
 *
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/init.h>

#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/stats.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
#include <linux/vfs.h>

#include <asm/system.h>
#include <asm/uaccess.h>

#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"

#define NFSDBG_FACILITY		NFSDBG_VFS
#define NFS_PARANOIA 1

/* Maximum number of readahead requests
 * FIXME: this should really be a sysctl so that users may tune it to suit
 *        their needs. People that do NFS over a slow network, might for
 *        instance want to reduce it to something closer to 1 for improved
 *        interactive response.
 */
#define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)

static void nfs_invalidate_inode(struct inode *);
static int nfs_update_inode(struct inode *, struct nfs_fattr *);

static struct inode *nfs_alloc_inode(struct super_block *sb);
static void nfs_destroy_inode(struct inode *);
static int nfs_write_inode(struct inode *,int);
static void nfs_delete_inode(struct inode *);
static void nfs_clear_inode(struct inode *);
static void nfs_umount_begin(struct super_block *);
static int  nfs_statfs(struct super_block *, struct kstatfs *);
static int  nfs_show_options(struct seq_file *, struct vfsmount *);
static void nfs_zap_acl_cache(struct inode *);

static struct rpc_program	nfs_program;

static struct super_operations nfs_sops = { 
	.alloc_inode	= nfs_alloc_inode,
	.destroy_inode	= nfs_destroy_inode,
	.write_inode	= nfs_write_inode,
	.delete_inode	= nfs_delete_inode,
	.statfs		= nfs_statfs,
	.clear_inode	= nfs_clear_inode,
	.umount_begin	= nfs_umount_begin,
	.show_options	= nfs_show_options,
};

/*
 * RPC cruft for NFS
 */
static struct rpc_stat		nfs_rpcstat = {
	.program		= &nfs_program
};
static struct rpc_version *	nfs_version[] = {
	NULL,
	NULL,
	&nfs_version2,
#if defined(CONFIG_NFS_V3)
	&nfs_version3,
#elif defined(CONFIG_NFS_V4)
	NULL,
#endif
#if defined(CONFIG_NFS_V4)
	&nfs_version4,
#endif
};

static struct rpc_program	nfs_program = {
	.name			= "nfs",
	.number			= NFS_PROGRAM,
	.nrvers			= sizeof(nfs_version) / sizeof(nfs_version[0]),
	.version		= nfs_version,
	.stats			= &nfs_rpcstat,
	.pipe_dir_name		= "/nfs",
};

#ifdef CONFIG_NFS_V3_ACL
static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
static struct rpc_version *	nfsacl_version[] = {
	[3]			= &nfsacl_version3,
};

struct rpc_program		nfsacl_program = {
	.name =			"nfsacl",
	.number =		NFS_ACL_PROGRAM,
	.nrvers =		sizeof(nfsacl_version) / sizeof(nfsacl_version[0]),
	.version =		nfsacl_version,
	.stats =		&nfsacl_rpcstat,
};
#endif  /* CONFIG_NFS_V3_ACL */

static inline unsigned long
nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
{
	return nfs_fileid_to_ino_t(fattr->fileid);
}

static int
nfs_write_inode(struct inode *inode, int sync)
{
	int flags = sync ? FLUSH_WAIT : 0;
	int ret;

	ret = nfs_commit_inode(inode, flags);
	if (ret < 0)
		return ret;
	return 0;
}

static void
nfs_delete_inode(struct inode * inode)
{
	dprintk("NFS: delete_inode(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);

	truncate_inode_pages(&inode->i_data, 0);

	nfs_wb_all(inode);
	/*
	 * The following should never happen...
	 */
	if (nfs_have_writebacks(inode)) {
		printk(KERN_ERR "nfs_delete_inode: inode %ld has pending RPC requests\n", inode->i_ino);
	}

	clear_inode(inode);
}

static void
nfs_clear_inode(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct rpc_cred *cred;

	nfs_wb_all(inode);
	BUG_ON (!list_empty(&nfsi->open_files));
	nfs_zap_acl_cache(inode);
	cred = nfsi->cache_access.cred;
	if (cred)
		put_rpccred(cred);
	BUG_ON(atomic_read(&nfsi->data_updates) != 0);
}

void
nfs_umount_begin(struct super_block *sb)
{
	struct rpc_clnt	*rpc = NFS_SB(sb)->client;

	/* -EIO all pending I/O */
	if (!IS_ERR(rpc))
		rpc_killall_tasks(rpc);
	rpc = NFS_SB(sb)->client_acl;
	if (!IS_ERR(rpc))
		rpc_killall_tasks(rpc);
}


static inline unsigned long
nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
{
	/* make sure blocksize is a power of two */
	if ((bsize & (bsize - 1)) || nrbitsp) {
		unsigned char	nrbits;

		for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
			;
		bsize = 1 << nrbits;
		if (nrbitsp)
			*nrbitsp = nrbits;
	}

	return bsize;
}

/*
 * Calculate the number of 512byte blocks used.
 */
static inline unsigned long
nfs_calc_block_size(u64 tsize)
{
	loff_t used = (tsize + 511) >> 9;
	return (used > ULONG_MAX) ? ULONG_MAX : used;
}

/*
 * Compute and set NFS server blocksize
 */
static inline unsigned long
nfs_block_size(unsigned long bsize, unsigned char *nrbitsp)
{
	if (bsize < NFS_MIN_FILE_IO_SIZE)
		bsize = NFS_DEF_FILE_IO_SIZE;
	else if (bsize >= NFS_MAX_FILE_IO_SIZE)
		bsize = NFS_MAX_FILE_IO_SIZE;

	return nfs_block_bits(bsize, nrbitsp);
}

/*
 * Obtain the root inode of the file system.
 */
static struct inode *
nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo)
{
	struct nfs_server	*server = NFS_SB(sb);
	struct inode *rooti;
	int			error;

	error = server->rpc_ops->getroot(server, rootfh, fsinfo);
	if (error < 0) {
		dprintk("nfs_get_root: getattr error = %d\n", -error);
		return ERR_PTR(error);
	}

	rooti = nfs_fhget(sb, rootfh, fsinfo->fattr);
	if (!rooti)
		return ERR_PTR(-ENOMEM);
	return rooti;
}

/*
 * Do NFS version-independent mount processing, and sanity checking
 */
static int
nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor)
{
	struct nfs_server	*server;
	struct inode		*root_inode;
	struct nfs_fattr	fattr;
	struct nfs_fsinfo	fsinfo = {
					.fattr = &fattr,
				};
	struct nfs_pathconf pathinfo = {
			.fattr = &fattr,
	};
	int no_root_error = 0;
	unsigned long max_rpc_payload;

	/* We probably want something more informative here */
	snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));

	server = NFS_SB(sb);

	sb->s_magic      = NFS_SUPER_MAGIC;

	root_inode = nfs_get_root(sb, &server->fh, &fsinfo);
	/* Did getting the root inode fail? */
	if (IS_ERR(root_inode)) {
		no_root_error = PTR_ERR(root_inode);
		goto out_no_root;
	}
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root) {
		no_root_error = -ENOMEM;
		goto out_no_root;
	}
	sb->s_root->d_op = server->rpc_ops->dentry_ops;

	/* Get some general file system info */
	if (server->namelen == 0 &&
	    server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0)
		server->namelen = pathinfo.max_namelen;
	/* Work out a lot of parameters */
	if (server->rsize == 0)
		server->rsize = nfs_block_size(fsinfo.rtpref, NULL);
	if (server->wsize == 0)
		server->wsize = nfs_block_size(fsinfo.wtpref, NULL);

	if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax)
		server->rsize = nfs_block_size(fsinfo.rtmax, NULL);
	if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax)
		server->wsize = nfs_block_size(fsinfo.wtmax, NULL);

	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
	if (server->rsize > max_rpc_payload)
		server->rsize = max_rpc_payload;
	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
		server->rsize = NFS_MAX_FILE_IO_SIZE;
	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

	if (server->wsize > max_rpc_payload)
		server->wsize = max_rpc_payload;
	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
		server->wsize = NFS_MAX_FILE_IO_SIZE;
	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

	if (sb->s_blocksize == 0)
		sb->s_blocksize = nfs_block_bits(server->wsize,
							 &sb->s_blocksize_bits);
	server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL);

	server->dtsize = nfs_block_size(fsinfo.dtpref, NULL);
	if (server->dtsize > PAGE_CACHE_SIZE)
		server->dtsize = PAGE_CACHE_SIZE;
	if (server->dtsize > server->rsize)
		server->dtsize = server->rsize;

	if (server->flags & NFS_MOUNT_NOAC) {
		server->acregmin = server->acregmax = 0;
		server->acdirmin = server->acdirmax = 0;
		sb->s_flags |= MS_SYNCHRONOUS;
	}
	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;

	sb->s_maxbytes = fsinfo.maxfilesize;
	if (sb->s_maxbytes > MAX_LFS_FILESIZE) 
		sb->s_maxbytes = MAX_LFS_FILESIZE; 

	server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0;
	server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0;

	/* We're airborne Set socket buffersize */
	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
	return 0;
	/* Yargs. It didn't work out. */
out_no_root:
	dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error);
	if (!IS_ERR(root_inode))
		iput(root_inode);
	return no_root_error;
}

static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans)
{
	to->to_initval = timeo * HZ / 10;
	to->to_retries = retrans;
	if (!to->to_retries)
		to->to_retries = 2;

	switch (proto) {
	case IPPROTO_TCP:
		if (!to->to_initval)
			to->to_initval = 60 * HZ;
		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
			to->to_initval = NFS_MAX_TCP_TIMEOUT;
		to->to_increment = to->to_initval;
		to->to_maxval = to->to_initval + (to->to_increment * to->to_retries);
		to->to_exponential = 0;
		break;
	case IPPROTO_UDP:
	default:
		if (!to->to_initval)
			to->to_initval = 11 * HZ / 10;
		if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
			to->to_initval = NFS_MAX_UDP_TIMEOUT;
		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
		to->to_exponential = 1;
		break;
	}
}

/*
 * Create an RPC client handle.
 */
static struct rpc_clnt *
nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data)
{
	struct rpc_timeout	timeparms;
	struct rpc_xprt		*xprt = NULL;
	struct rpc_clnt		*clnt = NULL;
	int			proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;

	nfs_init_timeout_values(&timeparms, proto, data->timeo, data->retrans);

	server->retrans_timeo = timeparms.to_initval;
	server->retrans_count = timeparms.to_retries;

	/* create transport and client */
	xprt = xprt_create_proto(proto, &server->addr, &timeparms);
	if (IS_ERR(xprt)) {
		dprintk("%s: cannot create RPC transport. Error = %ld\n",
				__FUNCTION__, PTR_ERR(xprt));
		return (struct rpc_clnt *)xprt;
	}
	clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
				 server->rpc_ops->version, data->pseudoflavor);
	if (IS_ERR(clnt)) {
		dprintk("%s: cannot create RPC client. Error = %ld\n",
				__FUNCTION__, PTR_ERR(xprt));
		goto out_fail;
	}

	clnt->cl_intr     = 1;
	clnt->cl_softrtry = 1;

	return clnt;

out_fail:
	return clnt;
}

/*
 * The way this works is that the mount process passes a structure
 * in the data argument which contains the server's IP address
 * and the root file handle obtained from the server's mount
 * daemon. We stash these away in the private superblock fields.
 */
static int
nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent)
{
	struct nfs_server	*server;
	rpc_authflavor_t	authflavor;

	server           = NFS_SB(sb);
	sb->s_blocksize_bits = 0;
	sb->s_blocksize = 0;
	if (data->bsize)
		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
	if (data->rsize)
		server->rsize = nfs_block_size(data->rsize, NULL);
	if (data->wsize)
		server->wsize = nfs_block_size(data->wsize, NULL);
	server->flags    = data->flags & NFS_MOUNT_FLAGMASK;

	server->acregmin = data->acregmin*HZ;
	server->acregmax = data->acregmax*HZ;
	server->acdirmin = data->acdirmin*HZ;
	server->acdirmax = data->acdirmax*HZ;

	/* Start lockd here, before we might error out */
	if (!(server->flags & NFS_MOUNT_NONLM))
		lockd_up();

	server->namelen  = data->namlen;
	server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL);
	if (!server->hostname)
		return -ENOMEM;
	strcpy(server->hostname, data->hostname);

	/* Check NFS protocol revision and initialize RPC op vector
	 * and file handle pool. */
#ifdef CONFIG_NFS_V3
	if (server->flags & NFS_MOUNT_VER3) {
		server->rpc_ops = &nfs_v3_clientops;
		server->caps |= NFS_CAP_READDIRPLUS;
	} else {
		server->rpc_ops = &nfs_v2_clientops;
	}
#else
	server->rpc_ops = &nfs_v2_clientops;
#endif

	/* Fill in pseudoflavor for mount version < 5 */
	if (!(data->flags & NFS_MOUNT_SECFLAVOUR))
		data->pseudoflavor = RPC_AUTH_UNIX;
	authflavor = data->pseudoflavor;	/* save for sb_init() */
	/* XXX maybe we want to add a server->pseudoflavor field */

	/* Create RPC client handles */
	server->client = nfs_create_client(server, data);
	if (IS_ERR(server->client))
		return PTR_ERR(server->client);
	/* RFC 2623, sec 2.3.2 */
	if (authflavor != RPC_AUTH_UNIX) {
		struct rpc_auth *auth;

		server->client_sys = rpc_clone_client(server->client);
		if (IS_ERR(server->client_sys))
			return PTR_ERR(server->client_sys);
		auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys);
		if (IS_ERR(auth))
			return PTR_ERR(auth);
	} else {
		atomic_inc(&server->client->cl_count);
		server->client_sys = server->client;
	}
	if (server->flags & NFS_MOUNT_VER3) {
#ifdef CONFIG_NFS_V3_ACL
		if (!(server->flags & NFS_MOUNT_NOACL)) {
			server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
			/* No errors! Assume that Sun nfsacls are supported */
			if (!IS_ERR(server->client_acl))
				server->caps |= NFS_CAP_ACLS;
		}
#else
		server->flags &= ~NFS_MOUNT_NOACL;
#endif /* CONFIG_NFS_V3_ACL */
		/*
		 * The VFS shouldn't apply the umask to mode bits. We will
		 * do so ourselves when necessary.
		 */
		sb->s_flags |= MS_POSIXACL;
		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
			server->namelen = NFS3_MAXNAMLEN;
		sb->s_time_gran = 1;
	} else {
		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
			server->namelen = NFS2_MAXNAMLEN;
	}

	sb->s_op = &nfs_sops;
	return nfs_sb_init(sb, authflavor);
}

static int
nfs_statfs(struct super_block *sb, struct kstatfs *buf)
{
	struct nfs_server *server = NFS_SB(sb);
	unsigned char blockbits;
	unsigned long blockres;
	struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode);
	struct nfs_fattr fattr;
	struct nfs_fsstat res = {
			.fattr = &fattr,
	};
	int error;

	lock_kernel();

	error = server->rpc_ops->statfs(server, rootfh, &res);
	buf->f_type = NFS_SUPER_MAGIC;
	if (error < 0)
		goto out_err;

	/*
	 * Current versions of glibc do not correctly handle the
	 * case where f_frsize != f_bsize.  Eventually we want to
	 * report the value of wtmult in this field.
	 */
	buf->f_frsize = sb->s_blocksize;

	/*
	 * On most *nix systems, f_blocks, f_bfree, and f_bavail
	 * are reported in units of f_frsize.  Linux hasn't had
	 * an f_frsize field in its statfs struct until recently,
	 * thus historically Linux's sys_statfs reports these
	 * fields in units of f_bsize.
	 */
	buf->f_bsize = sb->s_blocksize;
	blockbits = sb->s_blocksize_bits;
	blockres = (1 << blockbits) - 1;
	buf->f_blocks = (res.tbytes + blockres) >> blockbits;
	buf->f_bfree = (res.fbytes + blockres) >> blockbits;
	buf->f_bavail = (res.abytes + blockres) >> blockbits;

	buf->f_files = res.tfiles;
	buf->f_ffree = res.afiles;

	buf->f_namelen = server->namelen;
 out:
	unlock_kernel();
	return 0;

 out_err:
	dprintk("%s: statfs error = %d\n", __FUNCTION__, -error);
	buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1;
	goto out;

}

static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	static struct proc_nfs_info {
		int flag;
		char *str;
		char *nostr;
	} nfs_info[] = {
		{ NFS_MOUNT_SOFT, ",soft", ",hard" },
		{ NFS_MOUNT_INTR, ",intr", "" },
		{ NFS_MOUNT_NOCTO, ",nocto", "" },
		{ NFS_MOUNT_NOAC, ",noac", "" },
		{ NFS_MOUNT_NONLM, ",nolock", "" },
		{ NFS_MOUNT_NOACL, ",noacl", "" },
		{ 0, NULL, NULL }
	};
	struct proc_nfs_info *nfs_infop;
	struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);
	char buf[12];
	char *proto;

	seq_printf(m, ",vers=%d", nfss->rpc_ops->version);
	seq_printf(m, ",rsize=%d", nfss->rsize);
	seq_printf(m, ",wsize=%d", nfss->wsize);
	if (nfss->acregmin != 3*HZ)
		seq_printf(m, ",acregmin=%d", nfss->acregmin/HZ);
	if (nfss->acregmax != 60*HZ)
		seq_printf(m, ",acregmax=%d", nfss->acregmax/HZ);
	if (nfss->acdirmin != 30*HZ)
		seq_printf(m, ",acdirmin=%d", nfss->acdirmin/HZ);
	if (nfss->acdirmax != 60*HZ)
		seq_printf(m, ",acdirmax=%d", nfss->acdirmax/HZ);
	for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
		if (nfss->flags & nfs_infop->flag)
			seq_puts(m, nfs_infop->str);
		else
			seq_puts(m, nfs_infop->nostr);
	}
	switch (nfss->client->cl_xprt->prot) {
		case IPPROTO_TCP:
			proto = "tcp";
			break;
		case IPPROTO_UDP:
			proto = "udp";
			break;
		default:
			snprintf(buf, sizeof(buf), "%u", nfss->client->cl_xprt->prot);
			proto = buf;
	}
	seq_printf(m, ",proto=%s", proto);
	seq_printf(m, ",timeo=%lu", 10U * nfss->retrans_timeo / HZ);
	seq_printf(m, ",retrans=%u", nfss->retrans_count);
	seq_puts(m, ",addr=");
	seq_escape(m, nfss->hostname, " \t\n\\");
	return 0;
}

/**
 * nfs_sync_mapping - helper to flush all mmapped dirty data to disk
 */
int nfs_sync_mapping(struct address_space *mapping)
{
	int ret;

	if (mapping->nrpages == 0)
		return 0;
	unmap_mapping_range(mapping, 0, 0, 0);
	ret = filemap_write_and_wait(mapping);
	if (ret != 0)
		goto out;
	ret = nfs_wb_all(mapping->host);
out:
	return ret;
}

/*
 * Invalidate the local caches
 */
static void nfs_zap_caches_locked(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int mode = inode->i_mode;

	NFS_ATTRTIMEO(inode) = NFS_MINATTRTIMEO(inode);
	NFS_ATTRTIMEO_UPDATE(inode) = jiffies;

	memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
	else
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
}

void nfs_zap_caches(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	nfs_zap_caches_locked(inode);
	spin_unlock(&inode->i_lock);
}

static void nfs_zap_acl_cache(struct inode *inode)
{
	void (*clear_acl_cache)(struct inode *);

	clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache;
	if (clear_acl_cache != NULL)
		clear_acl_cache(inode);
	spin_lock(&inode->i_lock);
	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
	spin_unlock(&inode->i_lock);
}

/*
 * Invalidate, but do not unhash, the inode.
 * NB: must be called with inode->i_lock held!
 */
static void nfs_invalidate_inode(struct inode *inode)
{
	set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
	nfs_zap_caches_locked(inode);
}

struct nfs_find_desc {
	struct nfs_fh		*fh;
	struct nfs_fattr	*fattr;
};

/*
 * In NFSv3 we can have 64bit inode numbers. In order to support
 * this, and re-exported directories (also seen in NFSv2)
 * we are forced to allow 2 different inodes to have the same
 * i_ino.
 */
static int
nfs_find_actor(struct inode *inode, void *opaque)
{
	struct nfs_find_desc	*desc = (struct nfs_find_desc *)opaque;
	struct nfs_fh		*fh = desc->fh;
	struct nfs_fattr	*fattr = desc->fattr;

	if (NFS_FILEID(inode) != fattr->fileid)
		return 0;
	if (nfs_compare_fh(NFS_FH(inode), fh))
		return 0;
	if (is_bad_inode(inode) || NFS_STALE(inode))
		return 0;
	return 1;
}

static int
nfs_init_locked(struct inode *inode, void *opaque)
{
	struct nfs_find_desc	*desc = (struct nfs_find_desc *)opaque;
	struct nfs_fattr	*fattr = desc->fattr;

	NFS_FILEID(inode) = fattr->fileid;
	nfs_copy_fh(NFS_FH(inode), desc->fh);
	return 0;
}

/* Don't use READDIRPLUS on directories that we believe are too large */
#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE)

/*
 * This is our front-end to iget that looks up inodes by file handle
 * instead of inode number.
 */
struct inode *
nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
{
	struct nfs_find_desc desc = {
		.fh	= fh,
		.fattr	= fattr
	};
	struct inode *inode = NULL;
	unsigned long hash;

	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
		goto out_no_inode;

	if (!fattr->nlink) {
		printk("NFS: Buggy server - nlink == 0!\n");
		goto out_no_inode;
	}

	hash = nfs_fattr_to_ino_t(fattr);

	if (!(inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc)))
		goto out_no_inode;

	if (inode->i_state & I_NEW) {
		struct nfs_inode *nfsi = NFS_I(inode);

		/* We set i_ino for the few things that still rely on it,
		 * such as stat(2) */
		inode->i_ino = hash;

		/* We can't support update_atime(), since the server will reset it */
		inode->i_flags |= S_NOATIME|S_NOCMTIME;
		inode->i_mode = fattr->mode;
		/* Why so? Because we want revalidate for devices/FIFOs, and
		 * that's precisely what we have in nfs_file_inode_operations.
		 */
		inode->i_op = NFS_SB(sb)->rpc_ops->file_inode_ops;
		if (S_ISREG(inode->i_mode)) {
			inode->i_fop = &nfs_file_operations;
			inode->i_data.a_ops = &nfs_file_aops;
			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
		} else if (S_ISDIR(inode->i_mode)) {
			inode->i_op = NFS_SB(sb)->rpc_ops->dir_inode_ops;
			inode->i_fop = &nfs_dir_operations;
			if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
			    && fattr->size <= NFS_LIMIT_READDIRPLUS)
				set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode));
		} else if (S_ISLNK(inode->i_mode))
			inode->i_op = &nfs_symlink_inode_operations;
		else
			init_special_inode(inode, inode->i_mode, fattr->rdev);

		nfsi->read_cache_jiffies = fattr->time_start;
		nfsi->last_updated = jiffies;
		inode->i_atime = fattr->atime;
		inode->i_mtime = fattr->mtime;
		inode->i_ctime = fattr->ctime;
		if (fattr->valid & NFS_ATTR_FATTR_V4)
			nfsi->change_attr = fattr->change_attr;
		inode->i_size = nfs_size_to_loff_t(fattr->size);
		inode->i_nlink = fattr->nlink;
		inode->i_uid = fattr->uid;
		inode->i_gid = fattr->gid;
		if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
			/*
			 * report the blocks in 512byte units
			 */
			inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
			inode->i_blksize = inode->i_sb->s_blocksize;
		} else {
			inode->i_blocks = fattr->du.nfs2.blocks;
			inode->i_blksize = fattr->du.nfs2.blocksize;
		}
		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
		nfsi->attrtimeo_timestamp = jiffies;
		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
		nfsi->cache_access.cred = NULL;

		unlock_new_inode(inode);
	} else
		nfs_refresh_inode(inode, fattr);
	dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
		inode->i_sb->s_id,
		(long long)NFS_FILEID(inode),
		atomic_read(&inode->i_count));

out:
	return inode;

out_no_inode:
	printk("nfs_fhget: iget failed\n");
	goto out;
}

#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET)

int
nfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct nfs_fattr fattr;
	int error;

	if (attr->ia_valid & ATTR_SIZE) {
		if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode))
			attr->ia_valid &= ~ATTR_SIZE;
	}

	/* Optimization: if the end result is no change, don't RPC */
	attr->ia_valid &= NFS_VALID_ATTRS;
	if (attr->ia_valid == 0)
		return 0;

	lock_kernel();
	nfs_begin_data_update(inode);
	/* Write all dirty data */
	filemap_write_and_wait(inode->i_mapping);
	nfs_wb_all(inode);
	/*
	 * Return any delegations if we're going to change ACLs
	 */
	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
		nfs_inode_return_delegation(inode);
	error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
	if (error == 0)
		nfs_refresh_inode(inode, &fattr);
	nfs_end_data_update(inode);
	unlock_kernel();
	return error;
}

/**
 * nfs_setattr_update_inode - Update inode metadata after a setattr call.
 * @inode: pointer to struct inode
 * @attr: pointer to struct iattr
 *
 * Note: we do this in the *proc.c in order to ensure that
 *       it works for things like exclusive creates too.
 */
void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
{
	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
		if ((attr->ia_valid & ATTR_MODE) != 0) {
			int mode = attr->ia_mode & S_IALLUGO;
			mode |= inode->i_mode & ~S_IALLUGO;
			inode->i_mode = mode;
		}
		if ((attr->ia_valid & ATTR_UID) != 0)
			inode->i_uid = attr->ia_uid;
		if ((attr->ia_valid & ATTR_GID) != 0)
			inode->i_gid = attr->ia_gid;
		spin_lock(&inode->i_lock);
		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
		spin_unlock(&inode->i_lock);
	}
	if ((attr->ia_valid & ATTR_SIZE) != 0) {
		inode->i_size = attr->ia_size;
		vmtruncate(inode, attr->ia_size);
	}
}

static int nfs_wait_schedule(void *word)
{
	if (signal_pending(current))
		return -ERESTARTSYS;
	schedule();
	return 0;
}

/*
 * Wait for the inode to get unlocked.
 */
static int nfs_wait_on_inode(struct inode *inode)
{
	struct rpc_clnt	*clnt = NFS_CLIENT(inode);
	struct nfs_inode *nfsi = NFS_I(inode);
	sigset_t oldmask;
	int error;

	rpc_clnt_sigmask(clnt, &oldmask);
	error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
					nfs_wait_schedule, TASK_INTERRUPTIBLE);
	rpc_clnt_sigunmask(clnt, &oldmask);

	return error;
}

static void nfs_wake_up_inode(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
	smp_mb__after_clear_bit();
	wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
}

int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
	int err;

	/* Flush out writes to the server in order to update c/mtime */
	nfs_sync_inode(inode, 0, 0, FLUSH_WAIT|FLUSH_NOCOMMIT);

	/*
	 * We may force a getattr if the user cares about atime.
	 *
	 * Note that we only have to check the vfsmount flags here:
	 *  - NFS always sets S_NOATIME by so checking it would give a
	 *    bogus result
	 *  - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
	 *    no point in checking those.
	 */
 	if ((mnt->mnt_flags & MNT_NOATIME) ||
 	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
		need_atime = 0;

	if (need_atime)
		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
	else
		err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!err)
		generic_fillattr(inode, stat);
	return err;
}

static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
{
	struct nfs_open_context *ctx;

	ctx = (struct nfs_open_context *)kmalloc(sizeof(*ctx), GFP_KERNEL);
	if (ctx != NULL) {
		atomic_set(&ctx->count, 1);
		ctx->dentry = dget(dentry);
		ctx->vfsmnt = mntget(mnt);
		ctx->cred = get_rpccred(cred);
		ctx->state = NULL;
		ctx->lockowner = current->files;
		ctx->error = 0;
		ctx->dir_cookie = 0;
	}
	return ctx;
}

struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
	if (ctx != NULL)
		atomic_inc(&ctx->count);
	return ctx;