inode.c

linux 内核源代码

/*
 *  linux/fs/nfs/inode.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  nfs inode and superblock handling functions
 *
 *  Modularised by Alan Cox <[e-mail]>, 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.
 *  [e-mail]
 *
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.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/sunrpc/metrics.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 <linux/inet.h>
#include <linux/nfs_xdr.h>

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

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

#define NFSDBG_FACILITY		NFSDBG_VFS

#define NFS_64_BIT_INODE_NUMBERS_ENABLED	1

/* Default is to see 64-bit inode numbers */
static int enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED;

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

static void nfs_zap_acl_cache(struct inode *);

static struct kmem_cache * nfs_inode_cachep;

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

/**
 * nfs_compat_user_ino64 - returns the user-visible inode number
 * @fileid: 64-bit fileid
 *
 * This function returns a 32-bit inode number if the boot parameter
 * nfs.enable_ino64 is zero.
 */
u64 nfs_compat_user_ino64(u64 fileid)
{
	int ino;

	if (enable_ino64)
		return fileid;
	ino = fileid;
	if (sizeof(ino) < sizeof(fileid))
		ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8;
	return ino;
}

int nfs_write_inode(struct inode *inode, int sync)
{
	int ret;

	if (sync) {
		ret = filemap_fdatawait(inode->i_mapping);
		if (ret == 0)
			ret = nfs_commit_inode(inode, FLUSH_SYNC);
	} else
		ret = nfs_commit_inode(inode, 0);
	if (ret >= 0)
		return 0;
	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
	return ret;
}

void nfs_clear_inode(struct inode *inode)
{
	/*
	 * The following should never happen...
	 */
	BUG_ON(nfs_have_writebacks(inode));
	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
	nfs_zap_acl_cache(inode);
	nfs_access_zap_cache(inode);
}

/**
 * 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_inc_stats(inode, NFSIOS_ATTRINVALIDATE);

	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
	nfsi->attrtimeo_timestamp = 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);
}

void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
{
	if (mapping->nrpages != 0) {
		spin_lock(&inode->i_lock);
		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
		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);
}

void nfs_invalidate_atime(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME;
	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 = ERR_PTR(-ENOENT);
	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);

	inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc);
	if (inode == NULL) {
		inode = ERR_PTR(-ENOMEM);
		goto out_no_inode;
	}

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

		/* 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)->nfs_client->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)->nfs_client->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));
			/* Deal with crossing mountpoints */
			if (!nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) {
				if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
					inode->i_op = &nfs_referral_inode_operations;
				else
					inode->i_op = &nfs_mountpoint_inode_operations;
				inode->i_fop = NULL;
			}
		} 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 = now;
		nfsi->cache_change_attribute = now;
		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);
		} else {
			inode->i_blocks = fattr->du.nfs2.blocks;
		}
		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
		nfsi->attrtimeo_timestamp = now;
		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
		nfsi->access_cache = RB_ROOT;

		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:
	dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode));
	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;

	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);

	/* skip mode change if it's just for clearing setuid/setgid */
	if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
		attr->ia_valid &= ~ATTR_MODE;

	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();
	/* Write all dirty data */
	if (S_ISREG(inode->i_mode)) {
		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);
	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) {
		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
		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;
}