inode.c

linux 内核源代码

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/posix_acl.h>
#include <linux/sort.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/lm_interface.h>
#include <linux/security.h>

#include "gfs2.h"
#include "incore.h"
#include "acl.h"
#include "bmap.h"
#include "dir.h"
#include "eattr.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "ops_address.h"
#include "ops_file.h"
#include "ops_inode.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"

struct gfs2_inum_range_host {
	u64 ir_start;
	u64 ir_length;
};

static int iget_test(struct inode *inode, void *opaque)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	u64 *no_addr = opaque;

	if (ip->i_no_addr == *no_addr &&
	    inode->i_private != NULL)
		return 1;

	return 0;
}

static int iget_set(struct inode *inode, void *opaque)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	u64 *no_addr = opaque;

	inode->i_ino = (unsigned long)*no_addr;
	ip->i_no_addr = *no_addr;
	return 0;
}

struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
{
	unsigned long hash = (unsigned long)no_addr;
	return ilookup5(sb, hash, iget_test, &no_addr);
}

static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
{
	unsigned long hash = (unsigned long)no_addr;
	return iget5_locked(sb, hash, iget_test, iget_set, &no_addr);
}

struct gfs2_skip_data {
	u64	no_addr;
	int	skipped;
};

static int iget_skip_test(struct inode *inode, void *opaque)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_skip_data *data = opaque;

	if (ip->i_no_addr == data->no_addr && inode->i_private != NULL){
		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)){
			data->skipped = 1;
			return 0;
		}
		return 1;
	}
	return 0;
}

static int iget_skip_set(struct inode *inode, void *opaque)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_skip_data *data = opaque;

	if (data->skipped)
		return 1;
	inode->i_ino = (unsigned long)(data->no_addr);
	ip->i_no_addr = data->no_addr;
	return 0;
}

static struct inode *gfs2_iget_skip(struct super_block *sb,
				    u64 no_addr)
{
	struct gfs2_skip_data data;
	unsigned long hash = (unsigned long)no_addr;

	data.no_addr = no_addr;
	data.skipped = 0;
	return iget5_locked(sb, hash, iget_skip_test, iget_skip_set, &data);
}

/**
 * GFS2 lookup code fills in vfs inode contents based on info obtained
 * from directory entry inside gfs2_inode_lookup(). This has caused issues
 * with NFS code path since its get_dentry routine doesn't have the relevant
 * directory entry when gfs2_inode_lookup() is invoked. Part of the code
 * segment inside gfs2_inode_lookup code needs to get moved around.
 *
 * Clean up I_LOCK and I_NEW as well.
 **/

void gfs2_set_iop(struct inode *inode)
{
	umode_t mode = inode->i_mode;

	if (S_ISREG(mode)) {
		inode->i_op = &gfs2_file_iops;
		inode->i_fop = &gfs2_file_fops;
		inode->i_mapping->a_ops = &gfs2_file_aops;
	} else if (S_ISDIR(mode)) {
		inode->i_op = &gfs2_dir_iops;
		inode->i_fop = &gfs2_dir_fops;
	} else if (S_ISLNK(mode)) {
		inode->i_op = &gfs2_symlink_iops;
	} else {
		inode->i_op = &gfs2_dev_iops;
	}

	unlock_new_inode(inode);
}

/**
 * gfs2_inode_lookup - Lookup an inode
 * @sb: The super block
 * @no_addr: The inode number
 * @type: The type of the inode
 * @skip_freeing: set this not return an inode if it is currently being freed.
 *
 * Returns: A VFS inode, or an error
 */

struct inode *gfs2_inode_lookup(struct super_block *sb, 
				unsigned int type,
				u64 no_addr,
				u64 no_formal_ino, int skip_freeing)
{
	struct inode *inode;
	struct gfs2_inode *ip;
	struct gfs2_glock *io_gl;
	int error;

	if (skip_freeing)
		inode = gfs2_iget_skip(sb, no_addr);
	else
		inode = gfs2_iget(sb, no_addr);
	ip = GFS2_I(inode);

	if (!inode)
		return ERR_PTR(-ENOBUFS);

	if (inode->i_state & I_NEW) {
		struct gfs2_sbd *sdp = GFS2_SB(inode);
		inode->i_private = ip;
		ip->i_no_formal_ino = no_formal_ino;

		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
		if (unlikely(error))
			goto fail;
		ip->i_gl->gl_object = ip;

		error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
		if (unlikely(error))
			goto fail_put;

		set_bit(GIF_INVALID, &ip->i_flags);
		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
		if (unlikely(error))
			goto fail_iopen;
		ip->i_iopen_gh.gh_gl->gl_object = ip;

		gfs2_glock_put(io_gl);

		if ((type == DT_UNKNOWN) && (no_formal_ino == 0))
			goto gfs2_nfsbypass;

		inode->i_mode = DT2IF(type);

		/*
		 * We must read the inode in order to work out its type in
		 * this case. Note that this doesn't happen often as we normally
		 * know the type beforehand. This code path only occurs during
		 * unlinked inode recovery (where it is safe to do this glock,
		 * which is not true in the general case).
		 */
		if (type == DT_UNKNOWN) {
			struct gfs2_holder gh;
			error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
			if (unlikely(error))
				goto fail_glock;
			/* Inode is now uptodate */
			gfs2_glock_dq_uninit(&gh);
		}

		gfs2_set_iop(inode);
	}

gfs2_nfsbypass:
	return inode;
fail_glock:
	gfs2_glock_dq(&ip->i_iopen_gh);
fail_iopen:
	gfs2_glock_put(io_gl);
fail_put:
	ip->i_gl->gl_object = NULL;
	gfs2_glock_put(ip->i_gl);
fail:
	iput(inode);
	return ERR_PTR(error);
}

static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
{
	struct gfs2_dinode_host *di = &ip->i_di;
	const struct gfs2_dinode *str = buf;

	if (ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)) {
		if (gfs2_consist_inode(ip))
			gfs2_dinode_print(ip);
		return -EIO;
	}
	ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
	ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
	ip->i_inode.i_rdev = 0;
	switch (ip->i_inode.i_mode & S_IFMT) {
	case S_IFBLK:
	case S_IFCHR:
		ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
					   be32_to_cpu(str->di_minor));
		break;
	};

	ip->i_inode.i_uid = be32_to_cpu(str->di_uid);
	ip->i_inode.i_gid = be32_to_cpu(str->di_gid);
	/*
	 * We will need to review setting the nlink count here in the
	 * light of the forthcoming ro bind mount work. This is a reminder
	 * to do that.
	 */
	ip->i_inode.i_nlink = be32_to_cpu(str->di_nlink);
	di->di_size = be64_to_cpu(str->di_size);
	i_size_write(&ip->i_inode, di->di_size);
	di->di_blocks = be64_to_cpu(str->di_blocks);
	gfs2_set_inode_blocks(&ip->i_inode);
	ip->i_inode.i_atime.tv_sec = be64_to_cpu(str->di_atime);
	ip->i_inode.i_atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
	ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);

	di->di_goal_meta = be64_to_cpu(str->di_goal_meta);
	di->di_goal_data = be64_to_cpu(str->di_goal_data);
	di->di_generation = be64_to_cpu(str->di_generation);

	di->di_flags = be32_to_cpu(str->di_flags);
	gfs2_set_inode_flags(&ip->i_inode);
	di->di_height = be16_to_cpu(str->di_height);

	di->di_depth = be16_to_cpu(str->di_depth);
	di->di_entries = be32_to_cpu(str->di_entries);

	di->di_eattr = be64_to_cpu(str->di_eattr);
	return 0;
}

static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh)
{
	ip->i_cache[0] = bh;
}

/**
 * gfs2_inode_refresh - Refresh the incore copy of the dinode
 * @ip: The GFS2 inode
 *
 * Returns: errno
 */

int gfs2_inode_refresh(struct gfs2_inode *ip)
{
	struct buffer_head *dibh;
	int error;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		return error;

	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) {
		brelse(dibh);
		return -EIO;
	}

	error = gfs2_dinode_in(ip, dibh->b_data);
	brelse(dibh);
	clear_bit(GIF_INVALID, &ip->i_flags);

	return error;
}

int gfs2_dinode_dealloc(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_alloc *al;
	struct gfs2_rgrpd *rgd;
	int error;

	if (ip->i_di.di_blocks != 1) {
		if (gfs2_consist_inode(ip))
			gfs2_dinode_print(ip);
		return -EIO;
	}

	al = gfs2_alloc_get(ip);

	error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
	if (error)
		goto out;

	error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
	if (error)
		goto out_qs;

	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
	if (!rgd) {
		gfs2_consist_inode(ip);
		error = -EIO;
		goto out_rindex_relse;
	}

	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
				   &al->al_rgd_gh);
	if (error)
		goto out_rindex_relse;

	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 1);
	if (error)
		goto out_rg_gunlock;

	gfs2_trans_add_gl(ip->i_gl);

	gfs2_free_di(rgd, ip);

	gfs2_trans_end(sdp);
	clear_bit(GLF_STICKY, &ip->i_gl->gl_flags);

out_rg_gunlock:
	gfs2_glock_dq_uninit(&al->al_rgd_gh);
out_rindex_relse:
	gfs2_glock_dq_uninit(&al->al_ri_gh);
out_qs:
	gfs2_quota_unhold(ip);
out:
	gfs2_alloc_put(ip);
	return error;
}

/**
 * gfs2_change_nlink - Change nlink count on inode
 * @ip: The GFS2 inode
 * @diff: The change in the nlink count required
 *
 * Returns: errno
 */
int gfs2_change_nlink(struct gfs2_inode *ip, int diff)
{
	struct buffer_head *dibh;
	u32 nlink;
	int error;

	BUG_ON(diff != 1 && diff != -1);
	nlink = ip->i_inode.i_nlink + diff;

	/* If we are reducing the nlink count, but the new value ends up being
	   bigger than the old one, we must have underflowed. */
	if (diff < 0 && nlink > ip->i_inode.i_nlink) {
		if (gfs2_consist_inode(ip))
			gfs2_dinode_print(ip);
		return -EIO;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		return error;

	if (diff > 0)
		inc_nlink(&ip->i_inode);
	else
		drop_nlink(&ip->i_inode);

	ip->i_inode.i_ctime = CURRENT_TIME;

	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
	gfs2_dinode_out(ip, dibh->b_data);
	brelse(dibh);
	mark_inode_dirty(&ip->i_inode);

	if (ip->i_inode.i_nlink == 0)
		gfs2_unlink_di(&ip->i_inode); /* mark inode unlinked */

	return error;
}

struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
{
	struct qstr qstr;
	struct inode *inode;
	gfs2_str2qstr(&qstr, name);
	inode = gfs2_lookupi(dip, &qstr, 1, NULL);
	/* gfs2_lookupi has inconsistent callers: vfs
	 * related routines expect NULL for no entry found,
	 * gfs2_lookup_simple callers expect ENOENT
	 * and do not check for NULL.
	 */
	if (inode == NULL)
		return ERR_PTR(-ENOENT);
	else
		return inode;
}


/**
 * gfs2_lookupi - Look up a filename in a directory and return its inode
 * @d_gh: An initialized holder for the directory glock
 * @name: The name of the inode to look for
 * @is_root: If 1, ignore the caller's permissions
 * @i_gh: An uninitialized holder for the new inode glock
 *
 * This can be called via the VFS filldir function when NFS is doing
 * a readdirplus and the inode which its intending to stat isn't
 * already in cache. In this case we must not take the directory glock
 * again, since the readdir call will have already taken that lock.
 *
 * Returns: errno
 */

struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
			   int is_root, struct nameidata *nd)
{
	struct super_block *sb = dir->i_sb;
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_holder d_gh;
	int error = 0;
	struct inode *inode = NULL;
	int unlock = 0;

	if (!name->len || name->len > GFS2_FNAMESIZE)
		return ERR_PTR(-ENAMETOOLONG);