Skip to content

L
linux
Commit d891ea7b authored by Neil Brown's avatar Neil Brown Committed by Linus Torvalds
Browse files
Options

[PATCH] - kNFSd in 2.5.15 - Require export operations for exporting a filesystem 

This removes the old alternates to export_operations for exporting a
filesystem.

It removes fh_to_dentry, dentry_to_fh, and s_nfsd_free_path_sem.  It
also removes a lot of code.

The fs/ntfs change is because it was setting fh_to_dentry and
dentry_to_fh (which no longer exist) to NULL.
parent b64b7f8e
Show whitespace changes
Inline Side-by-side
Showing with 14 additions and 598 deletions
Documentation/filesystems/porting
View file @ d891ea7b
......@@ -146,3 +146,9 @@ support for this helper, particularly get_parent.
It is planned that this will be required for exporting once the code
settles down a bit.
[mandatory]
s_export_op is now required for exporting a filesystem.
isofs, ext2, ext3, resierfs, fat
can be used as examples of very different filesystems.
fs/nfsd/export.c
View file @ d891ea7b
......@@ -313,15 +313,12 @@ exp_export(struct nfsctl_export *nxp)
* either a device number (so FS_REQUIRES_DEV needed)
* or an FSID number (so NFSEXP_FSID needed).
* 2: We must be able to find an inode from a filehandle.
* either using fh_to_dentry (prefered)
* or using read_inode (the hack).
* This means that s_export_op must be set.
*/
if (((inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV)
|| (nxp->ex_flags & NFSEXP_FSID))
&&
(inode->i_sb->s_op->read_inode
|| inode->i_sb->s_export_op
|| inode->i_sb->s_op->fh_to_dentry))
inode->i_sb->s_export_op)
/* Ok, we can export it */;
else {
dprintk("exp_export: export of invalid fs type.\n");
......
fs/nfsd/nfsfh.c
View file @ d891ea7b
......@@ -34,474 +34,6 @@ extern struct export_operations export_op_default;
#define CALL(ops,fun) ((ops->fun)?(ops->fun):export_op_default.fun)
struct nfsd_getdents_callback {
char *name; /* name that was found. It already points to a buffer NAME_MAX+1 is size */
unsigned long ino; /* the inum we are looking for */
int found; /* inode matched? */
int sequence; /* sequence counter */
};
/*
* A rather strange filldir function to capture
* the name matching the specified inode number.
*/
static int filldir_one(void * __buf, const char * name, int len,
loff_t pos, ino_t ino, unsigned int d_type)
{
struct nfsd_getdents_callback *buf = __buf;
int result = 0;
buf->sequence++;
#ifdef NFSD_DEBUG_VERBOSE
dprintk("filldir_one: seq=%d, ino=%ld, name=%s\n", buf->sequence, ino, name);
#endif
if (buf->ino == ino) {
memcpy(buf->name, name, len);
buf->name[len] = '\0';
buf->found = 1;
result = -1;
}
return result;
}
static int nfsd_get_name(struct dentry *dentry, char *name,
struct dentry *child)
{
struct inode *dir = dentry->d_inode;
int error;
struct file file;
struct nfsd_getdents_callback buffer;
error = -ENOTDIR;
if (!dir || !S_ISDIR(dir->i_mode))
goto out;
error = -EINVAL;
if (!dir->i_fop)
goto out;
/*
* Open the directory ...
*/
error = init_private_file(&file, dentry, FMODE_READ);
if (error)
goto out;
error = -EINVAL;
if (!file.f_op->readdir)
goto out_close;
buffer.name = name;
buffer.ino = child->d_inode->i_ino;
buffer.found = 0;
buffer.sequence = 0;
while (1) {
int old_seq = buffer.sequence;
error = vfs_readdir(&file, filldir_one, &buffer);
if (error < 0)
break;
error = 0;
if (buffer.found)
break;
error = -ENOENT;
if (old_seq == buffer.sequence)
break;
}
out_close:
if (file.f_op->release)
file.f_op->release(dir, &file);
out:
return error;
}
static struct dentry *nfsd_iget(struct super_block *sb, unsigned long ino, __u32 generation)
{
/* iget isn't really right if the inode is currently unallocated!!
* This should really all be done inside each filesystem
*
* ext2fs' read_inode has been strengthed to return a bad_inode if the inode
* had been deleted.
*
* Currently we don't know the generation for parent directory, so a generation
* of 0 means "accept any"
*/
struct inode *inode;
struct dentry *result;
if (ino == 0)
return ERR_PTR(-ESTALE);
inode = iget(sb, ino);
if (inode == NULL)
return ERR_PTR(-ENOMEM);
if (is_bad_inode(inode)
|| (generation && inode->i_generation != generation)
) {
/* we didn't find the right inode.. */
dprintk("fh_verify: Inode %lu, Bad count: %d %d or version %u %u\n",
inode->i_ino,
inode->i_nlink, atomic_read(&inode->i_count),
inode->i_generation,
generation);
iput(inode);
return ERR_PTR(-ESTALE);
}
/* now to find a dentry.
* If possible, get a well-connected one
*/
result = d_alloc_anon(inode);
if (!result) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
result->d_vfs_flags |= DCACHE_REFERENCED;
return result;
}
static struct dentry *nfsd_get_dentry(struct super_block *sb, __u32 *fh,
int len, int fhtype, int parent)
{
if (sb->s_op->fh_to_dentry)
return sb->s_op->fh_to_dentry(sb, fh, len, fhtype, parent);
switch (fhtype) {
case 1:
if (len < 2)
break;
if (parent)
break;
return nfsd_iget(sb, fh[0], fh[1]);
case 2:
if (len < 3)
break;
if (parent)
return nfsd_iget(sb,fh[2],0);
return nfsd_iget(sb,fh[0],fh[1]);
default: break;
}
return ERR_PTR(-EINVAL);
}
/* this routine links an IS_ROOT dentry into the dcache tree. It gains "parent"
* as a parent and "name" as a name
* It should possibly go in dcache.c
*/
int d_splice(struct dentry *target, struct dentry *parent, struct qstr *name)
{
struct dentry *tdentry;
#ifdef NFSD_PARANOIA
if (!IS_ROOT(target))
printk("nfsd: d_splice with no-root target: %s/%s\n", parent->d_name.name, name->name);
if (!(target->d_flags & DCACHE_DISCONNECTED))
printk("nfsd: d_splice with non-DISCONNECTED target: %s/%s\n", parent->d_name.name, name->name);
#endif
tdentry = d_alloc(parent, name);
if (tdentry == NULL)
return -ENOMEM;
d_move(target, tdentry);
d_rehash(target);
dput(tdentry);
/* if parent is properly connected, then we can assert that
* the children are connected, but it must be a singluar (non-forking)
* branch
*/
if (!(parent->d_flags & DCACHE_DISCONNECTED)) {
while (target) {
target->d_flags &= ~DCACHE_DISCONNECTED;
parent = target;
spin_lock(&dcache_lock);
if (list_empty(&parent->d_subdirs))
target = NULL;
else {
target = list_entry(parent->d_subdirs.next, struct dentry, d_child);
#ifdef NFSD_PARANOIA
/* must be only child */
if (target->d_child.next != &parent->d_subdirs
|| target->d_child.prev != &parent->d_subdirs) {
printk("nfsd: d_splice found non-singular disconnected branch: %s/%s\n",
parent->d_name.name, target->d_name.name);
spin_unlock(&dcache_lock);
return 0;
}
#endif
}
spin_unlock(&dcache_lock);
}
}
return 0;
}
/* this routine finds the dentry of the parent of a given directory
* it assumes lookup("..") works.
*/
struct dentry *nfsd_findparent(struct dentry *child)
{
struct dentry *tdentry, *pdentry;
tdentry = d_alloc(child, &(const struct qstr) {"..", 2, 0});
if (!tdentry)
return ERR_PTR(-ENOMEM);
/* I'm going to assume that if the returned dentry is different, then
* it is well connected. But nobody returns different dentrys do they?
*/
down(&child->d_inode->i_sem);
pdentry = child->d_inode->i_op->lookup(child->d_inode, tdentry);
up(&child->d_inode->i_sem);
d_drop(tdentry); /* we never want ".." hashed */
if (!pdentry && tdentry->d_inode == NULL) {
/* File system cannot find ".." ... sad but possible */
pdentry = ERR_PTR(-EINVAL);
}
if (!pdentry) {
/* I don't want to return a ".." dentry.
* I would prefer to return an unconnected "IS_ROOT" dentry,
* though a properly connected dentry is even better
*/
/* if first or last of alias list is not tdentry, use that
* else make a root dentry
*/
struct list_head *aliases = &tdentry->d_inode->i_dentry;
spin_lock(&dcache_lock);
if (aliases->next != aliases) {
pdentry = list_entry(aliases->next, struct dentry, d_alias);
if (pdentry == tdentry)
pdentry = list_entry(aliases->prev, struct dentry, d_alias);
if (pdentry == tdentry)
pdentry = NULL;
if (pdentry) dget_locked(pdentry);
}
spin_unlock(&dcache_lock);
if (pdentry == NULL) {
pdentry = d_alloc_root(tdentry->d_inode);
if (pdentry) {
igrab(tdentry->d_inode);
pdentry->d_flags |= DCACHE_DISCONNECTED;
}
}
if (pdentry == NULL)
pdentry = ERR_PTR(-ENOMEM);
}
dput(tdentry); /* it is not hashed, it will be discarded */
return pdentry;
}
static struct dentry *splice(struct dentry *child, struct dentry *parent)
{
int err = 0, nerr;
struct qstr qs;
char namebuf[256];
struct list_head *lp;
/* child is an IS_ROOT (anonymous) dentry, but it is hypothesised that
* it should be a child of parent.
* We see if we can find a name and, if we can - splice it in.
* We lookup the name before locking (i_sem) the directory as namelookup
* also claims i_sem. If the name gets changed then we will loop around
* and try again in find_fh_dentry.
*/
nerr = nfsd_get_name(parent, namebuf, child);
/*
* We now claim the parent i_sem so that no-one else tries to create
* a dentry in the parent while we are.
*/
down(&parent->d_inode->i_sem);
/* Now, things might have changed while we waited.
* Possibly a friendly filesystem found child and spliced it in in response
* to a lookup (though nobody does this yet). In this case, just succeed.
*/
if (child->d_parent == parent) goto out;
/* Possibly a new dentry has been made for this child->d_inode in
* parent by a lookup. In this case return that dentry. Caller must
* notice and act accordingly
*/
spin_lock(&dcache_lock);
list_for_each(lp, &child->d_inode->i_dentry) {
struct dentry *tmp = list_entry(lp,struct dentry, d_alias);
if (!list_empty(&tmp->d_hash) &&
tmp->d_parent == parent) {
child = dget_locked(tmp);
spin_unlock(&dcache_lock);
goto out;
}
}
spin_unlock(&dcache_lock);
/* now we need that name. If there was an error getting it, now is th
* time to bail out.
*/
if ((err = nerr))
goto out;
qs.name = namebuf;
qs.len = strlen(namebuf);
if (find_inode_number(parent, &qs) != 0) {
/* Now that IS odd. I wonder what it means... */
err = -EEXIST;
printk("nfsd-fh: found a name that I didn't expect: %s/%s\n", parent->d_name.name, qs.name);
goto out;
}
err = d_splice(child, parent, &qs);
dprintk("nfsd_fh: found name %s for ino %ld\n", child->d_name.name, child->d_inode->i_ino);
out:
up(&parent->d_inode->i_sem);
if (err)
return ERR_PTR(err);
else
return child;
}
/*
* This is the basic lookup mechanism for turning an NFS file handle
* into a dentry.
* We use nfsd_iget and if that doesn't return a suitably connected dentry,
* we try to find the parent, and the parent of that and so-on until a
* connection if made.
*/
static struct dentry *
find_fh_dentry(struct super_block *sb, __u32 *datap, int len, int fhtype, int needpath)
{
struct dentry *dentry, *result = NULL;
struct dentry *tmp;
int err = -ESTALE;
/* the sb->s_nfsd_free_path_sem semaphore is needed to make sure that only one unconnected (free)
* dcache path ever exists, as otherwise two partial paths might get
* joined together, which would be very confusing.
* If there is ever an unconnected non-root directory, then this lock
* must be held.
*/
nfsdstats.fh_lookup++;
/*
* Attempt to find the inode.
*/
retry:
down(&sb->s_nfsd_free_path_sem);
result = nfsd_get_dentry(sb, datap, len, fhtype, 0);
if (IS_ERR(result)
|| !(result->d_flags & DCACHE_DISCONNECTED)
|| (!S_ISDIR(result->d_inode->i_mode) && ! needpath)) {
up(&sb->s_nfsd_free_path_sem);
err = PTR_ERR(result);
if (IS_ERR(result))
goto err_out;
if ((result->d_flags & DCACHE_DISCONNECTED))
nfsdstats.fh_anon++;
return result;
}
/* It's a directory, or we are required to confirm the file's
* location in the tree.
*/
dprintk("nfs_fh: need to look harder for %s/%d\n", sb->s_id, datap[0]);
lock_kernel();
if (!S_ISDIR(result->d_inode->i_mode)) {
nfsdstats.fh_nocache_nondir++;
/* need to iget dirino and make sure this inode is in that directory */
dentry = nfsd_get_dentry(sb, datap, len, fhtype, 1);
err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto err_result;
err = -ESTALE;
if (!dentry->d_inode
|| !S_ISDIR(dentry->d_inode->i_mode)) {
goto err_dentry;
}
tmp = splice(result, dentry);
err = PTR_ERR(tmp);
if (IS_ERR(tmp))
goto err_dentry;
if (tmp != result) {
/* it is safe to just use tmp instead, but we must discard result first */
d_drop(result);
dput(result);
result = tmp;
}
} else {
nfsdstats.fh_nocache_dir++;
dentry = dget(result);
}
while(dentry->d_flags & DCACHE_DISCONNECTED) {
/* LOOP INVARIANT */
/* haven't found a place in the tree yet, but we do have a free path
* from dentry down to result, and dentry is a directory.
* Have a hold on dentry and result */
struct dentry *pdentry;
struct inode *parent;
pdentry = nfsd_findparent(dentry);
err = PTR_ERR(pdentry);
if (IS_ERR(pdentry))
goto err_dentry;
parent = pdentry->d_inode;
err = -EACCES;
if (!parent) {
dput(pdentry);
goto err_dentry;
}
tmp = splice(dentry, pdentry);
if (tmp != dentry) {
/* Something wrong. We need to drop the whole dentry->result path
* whatever it was
*/
/*
* FIXME: the loop below will do Bad Things(tm) if
* dentry (or one of its ancestors) become attached
* to the tree (e.g. due to VFAT-style alias handling)
*/
struct dentry *d;
for (d=result ; d ; d=(d->d_parent == d)?NULL:d->d_parent)
d_drop(d);
}
if (IS_ERR(tmp)) {
err = PTR_ERR(tmp);
dput(pdentry);
goto err_dentry;
}
if (tmp != dentry) {
/* we lost a race, try again
*/
dput(pdentry);
dput(tmp);
dput(dentry);
dput(result); /* this will discard the whole free path, so we can up the semaphore */
up(&sb->s_nfsd_free_path_sem);
unlock_kernel();
goto retry;
}
dput(dentry);
dentry = pdentry;
}
dput(dentry);
up(&sb->s_nfsd_free_path_sem);
unlock_kernel();
return result;
err_dentry:
dput(dentry);
err_result:
dput(result);
up(&sb->s_nfsd_free_path_sem);
unlock_kernel();
err_out:
if (err == -ESTALE)
nfsdstats.fh_stale++;
return ERR_PTR(err);
}
/*
* our acceptability function.
* if NOSUBTREECHECK, accept anything
......@@ -660,15 +192,10 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
dentry = dget(exp->ex_dentry);
else {
struct export_operations *nop = exp->ex_mnt->mnt_sb->s_export_op;
if (nop)
dentry = CALL(nop,decode_fh)(exp->ex_mnt->mnt_sb,
datap, data_left,
fileid_type,
nfsd_acceptable, exp);
else
dentry = find_fh_dentry(exp->ex_dentry->d_sb,
datap, data_left, fileid_type,
!(exp->ex_flags & NFSEXP_NOSUBTREECHECK));
}
if (dentry == NULL)
goto out;
......@@ -716,56 +243,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
goto out;
}
/*
* Security: Check that the export is valid for dentry <gam3@acm.org>
* This is only needed with subtree_check, and if export_operations is
* not being used - export_operations does the check via the "acceptable"
* callback
*/
error = 0;
if (exp->ex_mnt->mnt_sb->s_export_op == NULL &&
!(exp->ex_flags & NFSEXP_NOSUBTREECHECK)) {
if (exp->ex_dentry != dentry) {
struct dentry *tdentry = dentry;
spin_lock(&dcache_lock);
do {
tdentry = tdentry->d_parent;
if (exp->ex_dentry == tdentry)
break;
/* executable only by root and we can't be root */
/*
* FIXME: permissions check is not that simple
*/
if (current->fsuid
&& (exp->ex_flags & NFSEXP_ROOTSQUASH)
&& !(tdentry->d_inode->i_uid
&& (tdentry->d_inode->i_mode & S_IXUSR))
&& !(tdentry->d_inode->i_gid
&& (tdentry->d_inode->i_mode & S_IXGRP))
&& !(tdentry->d_inode->i_mode & S_IXOTH)
) {
error = nfserr_stale;
dprintk("fh_verify: no root_squashed access.\n");
}
} while ((tdentry != tdentry->d_parent));
if (exp->ex_dentry != tdentry) {
error = nfserr_stale;
printk("nfsd Security: %s/%s bad export.\n",
dentry->d_parent->d_name.name,
dentry->d_name.name);
spin_unlock(&dcache_lock);
goto out;
}
spin_unlock(&dcache_lock);
}
}
/* Finally, check access permissions. */
if (!error) {
error = nfsd_permission(exp, dentry, access);
}
#ifdef NFSD_PARANOIA_EXTREME
if (error) {
printk("fh_verify: %s/%s permission failure, acc=%x, error=%d\n",
......@@ -790,38 +270,14 @@ inline int _fh_update(struct dentry *dentry, struct svc_export *exp,
__u32 *datap, int *maxsize)
{
struct export_operations *nop = exp->ex_mnt->mnt_sb->s_export_op;
struct super_block *sb = dentry->d_sb;
if (dentry == exp->ex_dentry) {
*maxsize = 0;
return 0;
}
if (nop)
return CALL(nop,encode_fh)(dentry, datap, maxsize,
!(exp->ex_flags&NFSEXP_NOSUBTREECHECK));
if (sb->s_op->dentry_to_fh) {
int need_parent = !S_ISDIR(dentry->d_inode->i_mode) &&
!(exp->ex_flags & NFSEXP_NOSUBTREECHECK);
int type = sb->s_op->dentry_to_fh(dentry, datap, maxsize, need_parent);
return type;
}
if (*maxsize < 2)
return 255;
*datap++ = ino_t_to_u32(dentry->d_inode->i_ino);
*datap++ = dentry->d_inode->i_generation;
if (*maxsize ==2 ||
S_ISDIR(dentry->d_inode->i_mode) ||
(exp->ex_flags & NFSEXP_NOSUBTREECHECK)) {
*maxsize = 2;
return 1;
}
*datap++ = ino_t_to_u32(parent_ino(dentry));
*maxsize = 3;
return 2;
}
/*
......@@ -845,7 +301,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, st
* of the same version, where possible.
* Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
* Then create a 32byte filehandle using nfs_fhbase_old
* But only do this if dentry_to_fh is not available
*
*/
......@@ -870,8 +325,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, st
fhp->fh_export = exp;
if (ref_fh &&
ref_fh->fh_handle.fh_version == 0xca &&
dentry->d_sb->s_op->dentry_to_fh == NULL) {
ref_fh->fh_handle.fh_version == 0xca) {
/* old style filehandle please */
memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
fhp->fh_handle.fh_size = NFS_FHSIZE;
......
fs/ntfs/super.c
View file @ d891ea7b
......@@ -1441,14 +1441,7 @@ struct super_operations ntfs_sops = {
clear_inode: ntfs_clear_big_inode, /* VFS: Called when an inode is
removed from memory. */
umount_begin: NULL, /* Forced umount. */
/*
* These are NFSd support functions but NTFS is a standard fs so
* shouldn't need to implement these manually. At least we can try
* without and if it doesn't work in some way we can always implement
* something here.
*/
fh_to_dentry: NULL, /* Get dentry for given file handle. */
dentry_to_fh: NULL, /* Get file handle for given dentry. */
show_options: ntfs_show_options, /* Show mount options in proc. */
};
......
fs/super.c
View file @ d891ea7b
......@@ -58,7 +58,6 @@ static struct super_block *alloc_super(void)
s->s_count = S_BIAS;
atomic_set(&s->s_active, 1);
sema_init(&s->s_vfs_rename_sem,1);
sema_init(&s->s_nfsd_free_path_sem,1);
sema_init(&s->s_dquot.dqio_sem, 1);
sema_init(&s->s_dquot.dqoff_sem, 1);
s->s_maxbytes = MAX_NON_LFS;
......
include/linux/fs.h
View file @ d891ea7b
......@@ -660,15 +660,6 @@ struct super_block {
* even looking at it. You had been warned.
*/
struct semaphore s_vfs_rename_sem; /* Kludge */
/* The next field is used by knfsd when converting a (inode number based)
* file handle into a dentry. As it builds a path in the dcache tree from
* the bottom up, there may for a time be a subpath of dentrys which is not
* connected to the main tree. This semaphore ensure that there is only ever
* one such free path per filesystem. Note that unconnected files (or other
* non-directories) are allowed, but not unconnected diretories.
*/
struct semaphore s_nfsd_free_path_sem;
};
/*
......@@ -798,30 +789,6 @@ struct super_operations {
void (*clear_inode) (struct inode *);
void (*umount_begin) (struct super_block *);
/* Following are for knfsd to interact with "interesting" filesystems
* Currently just reiserfs, but possibly FAT and others later
*
* fh_to_dentry is given a filehandle fragement with length, and a type flag
* and must return a dentry for the referenced object or, if "parent" is
* set, a dentry for the parent of the object.
* If a dentry cannot be found, a "root" dentry should be created and
* flaged as DCACHE_DISCONNECTED. nfsd_iget is an example implementation.
*
* dentry_to_fh is given a dentry and must generate the filesys specific
* part of the file handle. Available length is passed in *lenp and used
* length should be returned therein.
* If need_parent is set, then dentry_to_fh should encode sufficient information
* to find the (current) parent.
* dentry_to_fh should return a 1byte "type" which will be passed back in
* the fhtype arguement to fh_to_dentry. Type of 0 is reserved.
* If filesystem was exportable before the introduction of fh_to_dentry,
* types 1 and 2 should be used is that same way as the generic code.
* Type 255 means error.
*
* Lengths are in units of 4bytes, not bytes.
*/
struct dentry * (*fh_to_dentry)(struct super_block *sb, __u32 *fh, int len, int fhtype, int parent);
int (*dentry_to_fh)(struct dentry *, __u32 *fh, int *lenp, int need_parent);
int (*show_options)(struct seq_file *, struct vfsmount *);
};
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7