namei.c

来自「基于组件方式开发操作系统的OSKIT源代码」· C语言 代码 · 共 1,434 行 · 第 1/3 页

/*
 *  linux/fs/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  OSKit support added by the University of Utah, 1997
 */

/*
 * Some corrections by tytso.
 */

/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
 * lookup logic.
 */

#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/smp_lock.h>
#include <linux/quotaops.h>

#include <asm/uaccess.h>
#include <asm/unaligned.h>
#include <asm/semaphore.h>
#include <asm/page.h>
#include <asm/pgtable.h>

#include <asm/namei.h>

/* This can be removed after the beta phase. */
#define CACHE_SUPERVISE	/* debug the correctness of dcache entries */
#undef DEBUG		/* some other debugging */


#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])

#ifndef OSKIT
/* [Feb-1997 T. Schoebel-Theuer]
 * Fundamental changes in the pathname lookup mechanisms (namei)
 * were necessary because of omirr.  The reason is that omirr needs
 * to know the _real_ pathname, not the user-supplied one, in case
 * of symlinks (and also when transname replacements occur).
 *
 * The new code replaces the old recursive symlink resolution with
 * an iterative one (in case of non-nested symlink chains).  It does
 * this with calls to <fs>_follow_link().
 * As a side effect, dir_namei(), _namei() and follow_link() are now 
 * replaced with a single function lookup_dentry() that can handle all 
 * the special cases of the former code.
 *
 * With the new dcache, the pathname is stored at each inode, at least as
 * long as the refcount of the inode is positive.  As a side effect, the
 * size of the dcache depends on the inode cache and thus is dynamic.
 *
 * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
 * resolution to correspond with current state of the code.
 *
 * Note that the symlink resolution is not *completely* iterative.
 * There is still a significant amount of tail- and mid- recursion in
 * the algorithm.  Also, note that <fs>_readlink() is not used in
 * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
 * may return different results than <fs>_follow_link().  Many virtual
 * filesystems (including /proc) exhibit this behavior.
 */

/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
 * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
 * and the name already exists in form of a symlink, try to create the new
 * name indicated by the symlink. The old code always complained that the
 * name already exists, due to not following the symlink even if its target
 * is nonexistent.  The new semantics affects also mknod() and link() when
 * the name is a symlink pointing to a non-existant name.
 *
 * I don't know which semantics is the right one, since I have no access
 * to standards. But I found by trial that HP-UX 9.0 has the full "new"
 * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
 * "old" one. Personally, I think the new semantics is much more logical.
 * Note that "ln old new" where "new" is a symlink pointing to a non-existing
 * file does succeed in both HP-UX and SunOs, but not in Solaris
 * and in the old Linux semantics.
 */

/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
 * semantics.  See the comments in "open_namei" and "do_link" below.
 *
 * [10-Sep-98 Alan Modra] Another symlink change.
 */

/* In order to reduce some races, while at the same time doing additional
 * checking and hopefully speeding things up, we copy filenames to the
 * kernel data space before using them..
 *
 * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
 */
static inline int do_getname(const char *filename, char *page)
{
	int retval;
	unsigned long len = PAGE_SIZE;

	if ((unsigned long) filename >= TASK_SIZE) {
		if (!segment_eq(get_fs(), KERNEL_DS))
			return -EFAULT;
	} else if (TASK_SIZE - (unsigned long) filename < PAGE_SIZE)
		len = TASK_SIZE - (unsigned long) filename;

	retval = strncpy_from_user((char *)page, filename, len);
	if (retval > 0) {
		if (retval < len)
			return 0;
		return -ENAMETOOLONG;
	} else if (!retval)
		retval = -ENOENT;
	return retval;
}
#endif /* OSKIT */

char * getname(const char * filename)
{
#ifdef OSKIT
	return (char *)filename;
#else
	char *tmp, *result;

	result = ERR_PTR(-ENOMEM);
	tmp = __getname();
	if (tmp)  {
		int retval = do_getname(filename, tmp);

		result = tmp;
		if (retval < 0) {
			putname(tmp);
			result = ERR_PTR(retval);
		}
	}
	return result;
#endif /* OSKIT */
}

/*
 *	permission()
 *
 * is used to check for read/write/execute permissions on a file.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things..
 */
int permission(struct inode * inode,int mask)
{
	int mode = inode->i_mode;

	if (inode->i_op && inode->i_op->permission)
		return inode->i_op->permission(inode, mask);
	else if ((mask & S_IWOTH) && IS_RDONLY(inode) &&
		 (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
		return -EROFS; /* Nobody gets write access to a read-only fs */
	else if ((mask & S_IWOTH) && IS_IMMUTABLE(inode))
		return -EACCES; /* Nobody gets write access to an immutable file */
	else if (current->fsuid == inode->i_uid)
		mode >>= 6;
	else if (in_group_p(inode->i_gid))
		mode >>= 3;
	if (((mode & mask & S_IRWXO) == mask) || capable(CAP_DAC_OVERRIDE))
		return 0;
	/* read and search access */
	if ((mask == S_IROTH) ||
	    (S_ISDIR(mode)  && !(mask & ~(S_IROTH | S_IXOTH))))
		if (capable(CAP_DAC_READ_SEARCH))
			return 0;
	return -EACCES;
}

/*
 * get_write_access() gets write permission for a file.
 * put_write_access() releases this write permission.
 * This is used for regular files.
 * We cannot support write (and maybe mmap read-write shared) accesses and
 * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
 * can have the following values:
 * 0: no writers, no VM_DENYWRITE mappings
 * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
 * > 0: (i_writecount) users are writing to the file.
 */
int get_write_access(struct inode * inode)
{
#ifdef OSKIT
	/* This doesn't need to do anything since i_writecount is only
	   so exec can do ETXTBSY. */
#else
	if (inode->i_writecount < 0)
		return -ETXTBSY;
	inode->i_writecount++;
#endif /* OSKIT */
	return 0;
}

void put_write_access(struct inode * inode)
{
#ifdef OSKIT
	/* This doesn't need to do anything since i_writecount is only
	   so exec can do ETXTBSY. */
#else
	inode->i_writecount--;
#endif
}

/*
 * "." and ".." are special - ".." especially so because it has to be able
 * to know about the current root directory and parent relationships
 */
static struct dentry * reserved_lookup(struct dentry * parent, struct qstr * name)
{
	struct dentry *result = NULL;
	if (name->name[0] == '.') {
		switch (name->len) {
		default:
			break;
		case 2:	
			if (name->name[1] != '.')
				break;

			if (parent != current->fs->root)
				parent = parent->d_covers->d_parent;
			/* fallthrough */
		case 1:
			result = parent;
		}
	}
	return dget(result);
}

/*
 * Internal lookup() using the new generic dcache.
 */
static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, int flags)
{
	struct dentry * dentry = d_lookup(parent, name);

	if (dentry && dentry->d_op && dentry->d_op->d_revalidate) {
		if (!dentry->d_op->d_revalidate(dentry, flags) && !d_invalidate(dentry)) {
			dput(dentry);
			dentry = NULL;
		}
	}
	return dentry;
}

/*
 * This is called when everything else fails, and we actually have
 * to go to the low-level filesystem to find out what we should do..
 *
 * We get the directory semaphore, and after getting that we also
 * make sure that nobody added the entry to the dcache in the meantime..
 */
static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, int flags)
{
	struct dentry * result;
	struct inode *dir = parent->d_inode;

	down(&dir->i_sem);
	/*
	 * First re-do the cached lookup just in case it was created
	 * while we waited for the directory semaphore..
	 *
	 * FIXME! This could use version numbering or similar to
	 * avoid unnecessary cache lookups.
	 */
	result = cached_lookup(parent, name, flags);
	if (!result) {
		struct dentry * dentry = d_alloc(parent, name);
		result = ERR_PTR(-ENOMEM);
		if (dentry) {
			result = dir->i_op->lookup(dir, dentry);
			if (result)
				dput(dentry);
			else
				result = dentry;
		}
	}
	up(&dir->i_sem);
	return result;
}

static struct dentry * do_follow_link(struct dentry *base, struct dentry *dentry, unsigned int follow)
{
	struct inode * inode = dentry->d_inode;

	if ((follow & LOOKUP_FOLLOW)
	    && inode && inode->i_op && inode->i_op->follow_link) {
		if (current->link_count < 5) {
			struct dentry * result;

			current->link_count++;
			/* This eats the base */
			result = inode->i_op->follow_link(dentry, base, follow);
			current->link_count--;
			dput(dentry);
			return result;
		}
		dput(dentry);
		dentry = ERR_PTR(-ELOOP);
	}
	dput(base);
	return dentry;
}

static inline struct dentry * follow_mount(struct dentry * dentry)
{
	struct dentry * mnt = dentry->d_mounts;

	if (mnt != dentry) {
		dget(mnt);
		dput(dentry);
		dentry = mnt;
	}
	return dentry;
}

/*
 * Name resolution.
 *
 * This is the basic name resolution function, turning a pathname
 * into the final dentry.
 */
struct dentry * lookup_dentry(const char * name, struct dentry * base, unsigned int lookup_flags)
{
	struct dentry * dentry;
	struct inode *inode;

	if (*name == '/') {
		if (base)
			dput(base);
		do {
			name++;
		} while (*name == '/');
		__prefix_lookup_dentry(name, lookup_flags);
		base = dget(current->fs->root);
	} else if (!base) {
		base = dget(current->fs->pwd);
	}

	if (!*name)
		goto return_base;

	inode = base->d_inode;
	lookup_flags &= LOOKUP_FOLLOW | LOOKUP_DIRECTORY | LOOKUP_SLASHOK;

	/* At this point we know we have a real path component. */
	for(;;) {
		int err;
		unsigned long hash;
		struct qstr this;
		unsigned int flags;
		unsigned int c;

		err = permission(inode, MAY_EXEC);
		dentry = ERR_PTR(err);
 		if (err)
			break;

		this.name = name;
		c = *(const unsigned char *)name;

		hash = init_name_hash();
		do {
			name++;
			hash = partial_name_hash(c, hash);
			c = *(const unsigned char *)name;
		} while (c && (c != '/'));
		this.len = name - (const char *) this.name;
		this.hash = end_name_hash(hash);

		/* remove trailing slashes? */
		flags = lookup_flags;
		if (c) {
			char tmp;

			flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
			do {
				tmp = *++name;
			} while (tmp == '/');
			if (tmp)
				flags |= LOOKUP_CONTINUE;
		}

		/*
		 * See if the low-level filesystem might want
		 * to use its own hash..
		 */
		if (base->d_op && base->d_op->d_hash) {
			int error;
			error = base->d_op->d_hash(base, &this);
			if (error < 0) {
				dentry = ERR_PTR(error);
				break;
			}
		}

		/* This does the actual lookups.. */
		dentry = reserved_lookup(base, &this);
		if (!dentry) {
			dentry = cached_lookup(base, &this, flags);
			if (!dentry) {
				dentry = real_lookup(base, &this, flags);
				if (IS_ERR(dentry))
					break;
			}
		}

		/* Check mountpoints.. */
		dentry = follow_mount(dentry);

		base = do_follow_link(base, dentry, flags);
		if (IS_ERR(base))
			goto return_base;

		inode = base->d_inode;
		if (flags & LOOKUP_DIRECTORY) {
			if (!inode)
				goto no_inode;
			dentry = ERR_PTR(-ENOTDIR); 
			if (!inode->i_op || !inode->i_op->lookup)
				break;
			if (flags & LOOKUP_CONTINUE)
				continue;
		}
return_base:
		return base;
/*
 * The case of a nonexisting file is special.
 *
 * In the middle of a pathname lookup (ie when
 * LOOKUP_CONTINUE is set), it's an obvious
 * error and returns ENOENT.
 *
 * At the end of a pathname lookup it's legal,
 * and we return a negative dentry. However, we
 * get here only if there were trailing slashes,
 * which is legal only if we know it's supposed
 * to be a directory (ie "mkdir"). Thus the
 * LOOKUP_SLASHOK flag.
 */
no_inode:
		dentry = ERR_PTR(-ENOENT);
		if (flags & LOOKUP_CONTINUE)
			break;
		if (flags & LOOKUP_SLASHOK)
			goto return_base;
		break;
	}
	dput(base);
	return dentry;
}

/*
 *	namei()
 *
 * is used by most simple commands to get the inode of a specified name.
 * Open, link etc use their own routines, but this is enough for things
 * like 'chmod' etc.
 *
 * namei exists in two versions: namei/lnamei. The only difference is
 * that namei follows links, while lnamei does not.
 */
struct dentry * __namei(const char *pathname, unsigned int lookup_flags)
{
	char *name;
	struct dentry *dentry;

	name = getname(pathname);
	dentry = (struct dentry *) name;
	if (!IS_ERR(name)) {
		dentry = lookup_dentry(name, NULL, lookup_flags);
		putname(name);
		if (!IS_ERR(dentry)) {
			if (!dentry->d_inode) {
				dput(dentry);
				dentry = ERR_PTR(-ENOENT);
			}