vfs.c

linux 内核源代码

#define MSNFS	/* HACK HACK */
/*
 * linux/fs/nfsd/vfs.c
 *
 * File operations used by nfsd. Some of these have been ripped from
 * other parts of the kernel because they weren't exported, others
 * are partial duplicates with added or changed functionality.
 *
 * Note that several functions dget() the dentry upon which they want
 * to act, most notably those that create directory entries. Response
 * dentry's are dput()'d if necessary in the release callback.
 * So if you notice code paths that apparently fail to dput() the
 * dentry, don't worry--they have been taken care of.
 *
 * Copyright (C) 1995-1999 Olaf Kirch <[e-mail]>
 * Zerocpy NFS support (C) 2002 Hirokazu Takahashi <[e-mail]>
 */

#include <linux/string.h>
#include <linux/time.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/major.h>
#include <linux/splice.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/in.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/vfs.h>
#include <linux/delay.h>
#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#ifdef CONFIG_NFSD_V3
#include <linux/nfs3.h>
#include <linux/nfsd/xdr3.h>
#endif /* CONFIG_NFSD_V3 */
#include <linux/nfsd/nfsfh.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>
#ifdef CONFIG_NFSD_V4
#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>
#include <linux/nfsd_idmap.h>
#include <linux/security.h>
#endif /* CONFIG_NFSD_V4 */
#include <linux/jhash.h>

#include <asm/uaccess.h>

#define NFSDDBG_FACILITY		NFSDDBG_FILEOP


/*
 * This is a cache of readahead params that help us choose the proper
 * readahead strategy. Initially, we set all readahead parameters to 0
 * and let the VFS handle things.
 * If you increase the number of cached files very much, you'll need to
 * add a hash table here.
 */
struct raparms {
	struct raparms		*p_next;
	unsigned int		p_count;
	ino_t			p_ino;
	dev_t			p_dev;
	int			p_set;
	struct file_ra_state	p_ra;
	unsigned int		p_hindex;
};

struct raparm_hbucket {
	struct raparms		*pb_head;
	spinlock_t		pb_lock;
} ____cacheline_aligned_in_smp;

static struct raparms *		raparml;
#define RAPARM_HASH_BITS	4
#define RAPARM_HASH_SIZE	(1<<RAPARM_HASH_BITS)
#define RAPARM_HASH_MASK	(RAPARM_HASH_SIZE-1)
static struct raparm_hbucket	raparm_hash[RAPARM_HASH_SIZE];

/* 
 * Called from nfsd_lookup and encode_dirent. Check if we have crossed 
 * a mount point.
 * Returns -EAGAIN or -ETIMEDOUT leaving *dpp and *expp unchanged,
 *  or nfs_ok having possibly changed *dpp and *expp
 */
int
nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, 
		        struct svc_export **expp)
{
	struct svc_export *exp = *expp, *exp2 = NULL;
	struct dentry *dentry = *dpp;
	struct vfsmount *mnt = mntget(exp->ex_mnt);
	struct dentry *mounts = dget(dentry);
	int err = 0;

	while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts));

	exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts);
	if (IS_ERR(exp2)) {
		if (PTR_ERR(exp2) != -ENOENT)
			err = PTR_ERR(exp2);
		dput(mounts);
		mntput(mnt);
		goto out;
	}
	if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
		/* successfully crossed mount point */
		exp_put(exp);
		*expp = exp2;
		dput(dentry);
		*dpp = mounts;
	} else {
		exp_put(exp2);
		dput(mounts);
	}
	mntput(mnt);
out:
	return err;
}

__be32
nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
		   const char *name, int len,
		   struct svc_export **exp_ret, struct dentry **dentry_ret)
{
	struct svc_export	*exp;
	struct dentry		*dparent;
	struct dentry		*dentry;
	__be32			err;
	int			host_err;

	dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);

	/* Obtain dentry and export. */
	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
	if (err)
		return err;

	dparent = fhp->fh_dentry;
	exp  = fhp->fh_export;
	exp_get(exp);

	/* Lookup the name, but don't follow links */
	if (isdotent(name, len)) {
		if (len==1)
			dentry = dget(dparent);
		else if (dparent != exp->ex_dentry) {
			dentry = dget_parent(dparent);
		} else  if (!EX_NOHIDE(exp))
			dentry = dget(dparent); /* .. == . just like at / */
		else {
			/* checking mountpoint crossing is very different when stepping up */
			struct svc_export *exp2 = NULL;
			struct dentry *dp;
			struct vfsmount *mnt = mntget(exp->ex_mnt);
			dentry = dget(dparent);
			while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
				;
			dp = dget_parent(dentry);
			dput(dentry);
			dentry = dp;

			exp2 = rqst_exp_parent(rqstp, mnt, dentry);
			if (PTR_ERR(exp2) == -ENOENT) {
				dput(dentry);
				dentry = dget(dparent);
			} else if (IS_ERR(exp2)) {
				host_err = PTR_ERR(exp2);
				dput(dentry);
				mntput(mnt);
				goto out_nfserr;
			} else {
				exp_put(exp);
				exp = exp2;
			}
			mntput(mnt);
		}
	} else {
		fh_lock(fhp);
		dentry = lookup_one_len(name, dparent, len);
		host_err = PTR_ERR(dentry);
		if (IS_ERR(dentry))
			goto out_nfserr;
		/*
		 * check if we have crossed a mount point ...
		 */
		if (d_mountpoint(dentry)) {
			if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
				dput(dentry);
				goto out_nfserr;
			}
		}
	}
	*dentry_ret = dentry;
	*exp_ret = exp;
	return 0;

out_nfserr:
	exp_put(exp);
	return nfserrno(host_err);
}

/*
 * Look up one component of a pathname.
 * N.B. After this call _both_ fhp and resfh need an fh_put
 *
 * If the lookup would cross a mountpoint, and the mounted filesystem
 * is exported to the client with NFSEXP_NOHIDE, then the lookup is
 * accepted as it stands and the mounted directory is
 * returned. Otherwise the covered directory is returned.
 * NOTE: this mountpoint crossing is not supported properly by all
 *   clients and is explicitly disallowed for NFSv3
 *      NeilBrown <[e-mail]>
 */
__be32
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
					int len, struct svc_fh *resfh)
{
	struct svc_export	*exp;
	struct dentry		*dentry;
	__be32 err;

	err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
	if (err)
		return err;
	err = check_nfsd_access(exp, rqstp);
	if (err)
		goto out;
	/*
	 * Note: we compose the file handle now, but as the
	 * dentry may be negative, it may need to be updated.
	 */
	err = fh_compose(resfh, exp, dentry, fhp);
	if (!err && !dentry->d_inode)
		err = nfserr_noent;
out:
	dput(dentry);
	exp_put(exp);
	return err;
}


/*
 * Set various file attributes.
 * N.B. After this call fhp needs an fh_put
 */
__be32
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
	     int check_guard, time_t guardtime)
{
	struct dentry	*dentry;
	struct inode	*inode;
	int		accmode = MAY_SATTR;
	int		ftype = 0;
	int		imode;
	__be32		err;
	int		host_err;
	int		size_change = 0;

	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
		accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE;
	if (iap->ia_valid & ATTR_SIZE)
		ftype = S_IFREG;

	/* Get inode */
	err = fh_verify(rqstp, fhp, ftype, accmode);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	/* Ignore any mode updates on symlinks */
	if (S_ISLNK(inode->i_mode))
		iap->ia_valid &= ~ATTR_MODE;

	if (!iap->ia_valid)
		goto out;

	/*
	 * NFSv2 does not differentiate between "set-[ac]time-to-now"
	 * which only requires access, and "set-[ac]time-to-X" which
	 * requires ownership.
	 * So if it looks like it might be "set both to the same time which
	 * is close to now", and if inode_change_ok fails, then we
	 * convert to "set to now" instead of "set to explicit time"
	 *
	 * We only call inode_change_ok as the last test as technically
	 * it is not an interface that we should be using.  It is only
	 * valid if the filesystem does not define it's own i_op->setattr.
	 */
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define	MAX_TOUCH_TIME_ERROR (30*60)
	if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
	    iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
		/*
		 * Looks probable.
		 *
		 * Now just make sure time is in the right ballpark.
		 * Solaris, at least, doesn't seem to care what the time
		 * request is.  We require it be within 30 minutes of now.
		 */
		time_t delta = iap->ia_atime.tv_sec - get_seconds();
		if (delta < 0)
			delta = -delta;
		if (delta < MAX_TOUCH_TIME_ERROR &&
		    inode_change_ok(inode, iap) != 0) {
			/*
			 * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
			 * This will cause notify_change to set these times
			 * to "now"
			 */
			iap->ia_valid &= ~BOTH_TIME_SET;
		}
	}
	    
	/*
	 * The size case is special.
	 * It changes the file as well as the attributes.
	 */
	if (iap->ia_valid & ATTR_SIZE) {
		if (iap->ia_size < inode->i_size) {
			err = nfsd_permission(rqstp, fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
			if (err)
				goto out;
		}

		/*
		 * If we are changing the size of the file, then
		 * we need to break all leases.
		 */
		host_err = break_lease(inode, FMODE_WRITE | O_NONBLOCK);
		if (host_err == -EWOULDBLOCK)
			host_err = -ETIMEDOUT;
		if (host_err) /* ENOMEM or EWOULDBLOCK */
			goto out_nfserr;

		host_err = get_write_access(inode);
		if (host_err)
			goto out_nfserr;

		size_change = 1;
		host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
		if (host_err) {
			put_write_access(inode);
			goto out_nfserr;
		}
		DQUOT_INIT(inode);
	}

	imode = inode->i_mode;
	if (iap->ia_valid & ATTR_MODE) {
		iap->ia_mode &= S_IALLUGO;
		imode = iap->ia_mode |= (imode & ~S_IALLUGO);
		/* if changing uid/gid revoke setuid/setgid in mode */
		if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) {
			iap->ia_valid |= ATTR_KILL_PRIV;
			iap->ia_mode &= ~S_ISUID;
		}
		if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
			iap->ia_mode &= ~S_ISGID;
	} else {
		/*
		 * Revoke setuid/setgid bit on chown/chgrp
		 */
		if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid)
			iap->ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV;
		if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
			iap->ia_valid |= ATTR_KILL_SGID;
	}

	/* Change the attributes. */

	iap->ia_valid |= ATTR_CTIME;

	err = nfserr_notsync;
	if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
		fh_lock(fhp);
		host_err = notify_change(dentry, iap);
		err = nfserrno(host_err);
		fh_unlock(fhp);
	}
	if (size_change)
		put_write_access(inode);
	if (!err)
		if (EX_ISSYNC(fhp->fh_export))
			write_inode_now(inode, 1);
out:
	return err;

out_nfserr:
	err = nfserrno(host_err);
	goto out;
}

#if defined(CONFIG_NFSD_V2_ACL) || \
    defined(CONFIG_NFSD_V3_ACL) || \
    defined(CONFIG_NFSD_V4)
static ssize_t nfsd_getxattr(struct dentry *dentry, char *key, void **buf)
{
	ssize_t buflen;

	buflen = vfs_getxattr(dentry, key, NULL, 0);
	if (buflen <= 0)
		return buflen;

	*buf = kmalloc(buflen, GFP_KERNEL);
	if (!*buf)
		return -ENOMEM;

	return vfs_getxattr(dentry, key, *buf, buflen);
}
#endif

#if defined(CONFIG_NFSD_V4)
static int
set_nfsv4_acl_one(struct dentry *dentry, struct posix_acl *pacl, char *key)
{
	int len;
	size_t buflen;
	char *buf = NULL;
	int error = 0;

	buflen = posix_acl_xattr_size(pacl->a_count);
	buf = kmalloc(buflen, GFP_KERNEL);
	error = -ENOMEM;
	if (buf == NULL)
		goto out;

	len = posix_acl_to_xattr(pacl, buf, buflen);
	if (len < 0) {
		error = len;
		goto out;
	}

	error = vfs_setxattr(dentry, key, buf, len, 0);
out:
	kfree(buf);
	return error;
}

__be32
nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
    struct nfs4_acl *acl)
{
	__be32 error;
	int host_error;
	struct dentry *dentry;
	struct inode *inode;
	struct posix_acl *pacl = NULL, *dpacl = NULL;
	unsigned int flags = 0;

	/* Get inode */
	error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, MAY_SATTR);
	if (error)
		return error;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;
	if (S_ISDIR(inode->i_mode))
		flags = NFS4_ACL_DIR;

	host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
	if (host_error == -EINVAL) {
		return nfserr_attrnotsupp;
	} else if (host_error < 0)
		goto out_nfserr;

	host_error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS);
	if (host_error < 0)
		goto out_release;

	if (S_ISDIR(inode->i_mode))
		host_error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT);

out_release:
	posix_acl_release(pacl);
	posix_acl_release(dpacl);
out_nfserr:
	if (host_error == -EOPNOTSUPP)
		return nfserr_attrnotsupp;
	else
		return nfserrno(host_error);
}

static struct posix_acl *
_get_posix_acl(struct dentry *dentry, char *key)
{
	void *buf = NULL;
	struct posix_acl *pacl = NULL;
	int buflen;

	buflen = nfsd_getxattr(dentry, key, &buf);
	if (!buflen)
		buflen = -ENODATA;
	if (buflen <= 0)
		return ERR_PTR(buflen);

	pacl = posix_acl_from_xattr(buf, buflen);
	kfree(buf);
	return pacl;