static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
int connectable)
{
struct inode *inode = dentry->d_inode;
bool encode_parent = connectable && !S_ISDIR(inode->i_mode);
int len = encode_parent ? 6 : 3;
u64 nodeid;
u32 generation;
if (*max_len < len)
return 255;
nodeid = get_fuse_inode(inode)->nodeid;
generation = inode->i_generation;
fh[0] = (u32)(nodeid >> 32);
fh[1] = (u32)(nodeid & 0xffffffff);
fh[2] = generation;
if (encode_parent) {
struct inode *parent;
spin_lock(&dentry->d_lock);
parent = dentry->d_parent->d_inode;
nodeid = get_fuse_inode(parent)->nodeid;
generation = parent->i_generation;
spin_unlock(&dentry->d_lock);
fh[3] = (u32)(nodeid >> 32);
fh[4] = (u32)(nodeid & 0xffffffff);
fh[5] = generation;
}
*max_len = len;
return encode_parent ? 0x82 : 0x81;
}
static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx)
{
struct fuse_conn *fc = get_fuse_conn(dir);
struct fuse_inode *fi = get_fuse_inode(dir);
if (!fc->do_readdirplus)
return false;
if (!fc->readdirplus_auto)
return true;
if (test_and_clear_bit(FUSE_I_ADVISE_RDPLUS, &fi->state))
return true;
if (ctx->pos == 0)
return true;
return false;
}
static int fuse_permission(struct inode *inode, int mask)
{
struct fuse_conn *fc = get_fuse_conn(inode);
bool refreshed = false;
int err = 0;
if (!fuse_allow_task(fc, current))
return -EACCES;
if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) ||
((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
struct fuse_inode *fi = get_fuse_inode(inode);
if (fi->i_time < get_jiffies_64()) {
refreshed = true;
err = fuse_perm_getattr(inode, mask);
if (err)
return err;
}
}
if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
err = generic_permission(inode, mask);
if (err == -EACCES && !refreshed) {
err = fuse_perm_getattr(inode, mask);
if (!err)
err = generic_permission(inode, mask);
}
} else if (mask & (MAY_ACCESS | MAY_CHDIR)) {
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
err = fuse_access(inode, mask);
} else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
if (!(inode->i_mode & S_IXUGO)) {
if (refreshed)
return -EACCES;
err = fuse_perm_getattr(inode, mask);
if (!err && !(inode->i_mode & S_IXUGO))
return -EACCES;
}
}
return err;
}
static int fuse_update_get_attr(struct inode *inode, struct file *file,
struct kstat *stat)
{
struct fuse_inode *fi = get_fuse_inode(inode);
int err = 0;
if (time_before64(fi->i_time, get_jiffies_64())) {
forget_all_cached_acls(inode);
err = fuse_do_getattr(inode, stat, file);
} else if (stat) {
generic_fillattr(inode, stat);
stat->mode = fi->orig_i_mode;
stat->ino = fi->orig_ino;
}
return err;
}
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid, u64 attr_version)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
loff_t oldsize;
struct timespec old_mtime;
spin_lock(&fc->lock);
if ((attr_version != 0 && fi->attr_version > attr_version) ||
test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
spin_unlock(&fc->lock);
return;
}
old_mtime = inode->i_mtime;
fuse_change_attributes_common(inode, attr, attr_valid);
oldsize = inode->i_size;
i_size_write(inode, attr->size);
spin_unlock(&fc->lock);
if (S_ISREG(inode->i_mode)) {
bool inval = false;
if (oldsize != attr->size) {
truncate_pagecache(inode, oldsize, attr->size);
inval = true;
} else if (fc->auto_inval_data) {
struct timespec new_mtime = {
.tv_sec = attr->mtime,
.tv_nsec = attr->mtimensec,
};
/*
* Auto inval mode also checks and invalidates if mtime
* has changed.
*/
if (!timespec_equal(&old_mtime, &new_mtime))
inval = true;
}
if (inval)
invalidate_inode_pages2(inode->i_mapping);
}
}
/*
* Check whether the dentry is still valid
*
* If the entry validity timeout has expired and the dentry is
* positive, try to redo the lookup. If the lookup results in a
* different inode, then let the VFS invalidate the dentry and redo
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
{
struct inode *inode = entry->d_inode;
if (inode && is_bad_inode(inode))
return 0;
else if (time_after(jiffies, entry->d_time)) {
int err;
struct fuse_entry_out outarg;
struct fuse_conn *fc;
struct fuse_req *req;
/* Doesn't hurt to "reset" the validity timeout */
fuse_invalidate_entry_cache(entry);
if (!inode)
return 0;
fc = get_fuse_conn(inode);
req = fuse_get_request(fc);
if (!req)
return 0;
fuse_lookup_init(req, entry->d_parent->d_inode, entry, &outarg);
request_send(fc, req);
err = req->out.h.error;
/* Zero nodeid is same as -ENOENT */
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
fuse_send_forget(fc, req, outarg.nodeid, 1);
return 0;
}
fi->nlookup ++;
}
fuse_put_request(fc, req);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
return 0;
fuse_change_attributes(inode, &outarg.attr);
fuse_change_timeout(entry, &outarg);
}
return 1;
}
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
fi->attr_version = ++fc->attr_version;
fi->i_time = attr_valid;
inode->i_ino = fuse_squash_ino(attr->ino);
inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
set_nlink(inode, attr->nlink);
inode->i_uid = make_kuid(&init_user_ns, attr->uid);
inode->i_gid = make_kgid(&init_user_ns, attr->gid);
inode->i_blocks = attr->blocks;
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
/* mtime from server may be stale due to local buffered write */
if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) {
inode->i_mtime.tv_sec = attr->mtime;
inode->i_mtime.tv_nsec = attr->mtimensec;
inode->i_ctime.tv_sec = attr->ctime;
inode->i_ctime.tv_nsec = attr->ctimensec;
}
if (attr->blksize != 0)
inode->i_blkbits = ilog2(attr->blksize);
else
inode->i_blkbits = inode->i_sb->s_blocksize_bits;
/*
* Don't set the sticky bit in i_mode, unless we want the VFS
* to check permissions. This prevents failures due to the
* check in may_delete().
*/
fi->orig_i_mode = inode->i_mode;
if (!fc->default_permissions)
inode->i_mode &= ~S_ISVTX;
fi->orig_ino = attr->ino;
}
static struct inode *fuse_alloc_inode(struct super_block *sb)
{
struct inode *inode;
struct fuse_inode *fi;
inode = kmem_cache_alloc(fuse_inode_cachep, SLAB_KERNEL);
if (!inode)
return NULL;
fi = get_fuse_inode(inode);
fi->i_time = 0;
fi->nodeid = 0;
fi->nlookup = 0;
fi->forget_req = fuse_request_alloc();
if (!fi->forget_req) {
kmem_cache_free(fuse_inode_cachep, inode);
return NULL;
}
return inode;
}
static int fuse_link(struct dentry *entry, struct inode *newdir,
struct dentry *newent)
{
int err;
struct fuse_link_in inarg;
struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
inarg.oldnodeid = get_node_id(inode);
req->in.h.opcode = FUSE_LINK;
req->in.numargs = 2;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->in.args[1].size = newent->d_name.len + 1;
req->in.args[1].value = newent->d_name.name;
err = create_new_entry(fc, req, newdir, newent, inode->i_mode);
/* Contrary to "normal" filesystems it can happen that link
makes two "logical" inodes point to the same "physical"
inode. We invalidate the attributes of the old one, so it
will reflect changes in the backing inode (link count,
etc.)
*/
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->attr_version = ++fc->attr_version;
inc_nlink(inode);
spin_unlock(&fc->lock);
fuse_invalidate_attr(inode);
} else if (err == -EINTR) {
fuse_invalidate_attr(inode);
}
return err;
}
static int fuse_link(struct dentry *entry, struct inode *newdir,
struct dentry *newent)
{
int err;
struct fuse_link_in inarg;
struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
inarg.oldnodeid = get_node_id(inode);
req->in.h.opcode = FUSE_LINK;
req->in.numargs = 2;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->in.args[1].size = newent->d_name.len + 1;
req->in.args[1].value = newent->d_name.name;
err = create_new_entry(fc, req, newdir, newent, inode->i_mode);
/*
*/
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->attr_version = ++fc->attr_version;
inc_nlink(inode);
spin_unlock(&fc->lock);
fuse_invalidate_attr(inode);
} else if (err == -EINTR) {
fuse_invalidate_attr(inode);
}
return err;
}
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
fi->attr_version = ++fc->attr_version;
fi->i_time = attr_valid;
inode->i_ino = fuse_squash_ino(attr->ino);
inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
set_nlink(inode, attr->nlink);
inode->i_uid = make_kuid(&init_user_ns, attr->uid);
inode->i_gid = make_kgid(&init_user_ns, attr->gid);
inode->i_blocks = attr->blocks;
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
inode->i_mtime.tv_sec = attr->mtime;
inode->i_mtime.tv_nsec = attr->mtimensec;
inode->i_ctime.tv_sec = attr->ctime;
inode->i_ctime.tv_nsec = attr->ctimensec;
if (attr->blksize != 0)
inode->i_blkbits = ilog2(attr->blksize);
else
inode->i_blkbits = inode->i_sb->s_blocksize_bits;
/*
* Don't set the sticky bit in i_mode, unless we want the VFS
* to check permissions. This prevents failures due to the
* check in may_delete().
*/
fi->orig_i_mode = inode->i_mode;
if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
inode->i_mode &= ~S_ISVTX;
fi->orig_ino = attr->ino;
}
static int fuse_unlink(struct inode *dir, struct dentry *entry)
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
req->in.h.opcode = FUSE_UNLINK;
req->in.h.nodeid = get_node_id(dir);
req->in.numargs = 1;
req->in.args[0].size = entry->d_name.len + 1;
req->in.args[0].value = entry->d_name.name;
fuse_request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
struct inode *inode = entry->d_inode;
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->attr_version = ++fc->attr_version;
/*
* If i_nlink == 0 then unlink doesn't make sense, yet this can
* happen if userspace filesystem is careless. It would be
* difficult to enforce correct nlink usage so just ignore this
* condition here
*/
if (inode->i_nlink > 0)
drop_nlink(inode);
spin_unlock(&fc->lock);
fuse_invalidate_attr(inode);
fuse_invalidate_attr(dir);
fuse_invalidate_entry_cache(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
}
struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
int generation, struct fuse_attr *attr)
{
struct inode *inode;
struct fuse_inode *fi;
struct fuse_conn *fc = get_fuse_conn_super(sb);
int retried = 0;
retry:
inode = iget5_locked(sb, nodeid, fuse_inode_eq, fuse_inode_set, &nodeid);
if (!inode)
return NULL;
if ((inode->i_state & I_NEW)) {
#ifdef KERNEL_2_6_8_PLUS
inode->i_flags |= S_NOATIME|S_NOCMTIME;
#else
inode->i_flags |= S_NOATIME;
#endif
inode->i_generation = generation;
inode->i_data.backing_dev_info = &fc->bdi;
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
BUG_ON(retried);
/* Inode has changed type, any I/O on the old should fail */
make_bad_inode(inode);
iput(inode);
retried = 1;
goto retry;
}
fi = get_fuse_inode(inode);
fi->nlookup ++;
fuse_change_attributes(inode, attr);
return inode;
}
static struct inode *fuse_alloc_inode(struct super_block *sb)
{
struct inode *inode;
struct fuse_inode *fi;
inode = kmem_cache_alloc(fuse_inode_cachep, SLAB_KERNEL);
if (!inode)
return NULL;
#ifndef KERNEL_2_6
inode->u.generic_ip = NULL;
#endif
fi = get_fuse_inode(inode);
fi->i_time = jiffies - 1;
fi->nodeid = 0;
fi->nlookup = 0;
fi->forget_req = fuse_request_alloc();
if (!fi->forget_req) {
kmem_cache_free(fuse_inode_cachep, inode);
return NULL;
}
return inode;
}
int fuse_update_attributes(struct inode *inode, struct kstat *stat,
struct file *file, bool *refreshed)
{
struct fuse_inode *fi = get_fuse_inode(inode);
int err;
bool r;
if (fi->i_time < get_jiffies_64()) {
r = true;
err = fuse_do_getattr(inode, stat, file);
} else {
r = false;
err = 0;
if (stat) {
generic_fillattr(inode, stat);
stat->mode = fi->orig_i_mode;
}
}
if (refreshed != NULL)
*refreshed = r;
return err;
}
struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
int generation, struct fuse_attr *attr,
u64 attr_valid, u64 attr_version)
{
struct inode *inode;
struct fuse_inode *fi;
struct fuse_conn *fc = get_fuse_conn_super(sb);
retry:
inode = iget5_locked(sb, nodeid, fuse_inode_eq, fuse_inode_set, &nodeid);
if (!inode)
return NULL;
if ((inode->i_state & I_NEW)) {
inode->i_flags |= S_NOATIME;
if (!fc->writeback_cache || !S_ISREG(inode->i_mode))
inode->i_flags |= S_NOCMTIME;
inode->i_generation = generation;
inode->i_data.backing_dev_info = &fc->bdi;
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
/* Inode has changed type, any I/O on the old should fail */
make_bad_inode(inode);
iput(inode);
goto retry;
}
fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
fuse_change_attributes(inode, attr, attr_valid, attr_version);
return inode;
}
int fuse_do_getattr(struct inode *inode)
{
int err;
struct fuse_attr_out arg;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req = fuse_get_request(fc);
if (!req)
return -EINTR;
req->in.h.opcode = FUSE_GETATTR;
req->in.h.nodeid = get_node_id(inode);
req->inode = inode;
req->out.numargs = 1;
req->out.args[0].size = sizeof(arg);
req->out.args[0].value = &arg;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
if ((inode->i_mode ^ arg.attr.mode) & S_IFMT) {
#ifndef KERNEL_2_6_12_PLUS
if (get_node_id(inode) != FUSE_ROOT_ID)
make_bad_inode(inode);
#else
make_bad_inode(inode);
#endif
err = -EIO;
} else {
struct fuse_inode *fi = get_fuse_inode(inode);
fuse_change_attributes(inode, &arg.attr);
fi->i_time = time_to_jiffies(arg.attr_valid,
arg.attr_valid_nsec);
}
}
return err;
}
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid, u64 attr_version)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
loff_t oldsize;
spin_lock(&fc->lock);
if (attr_version != 0 && fi->attr_version > attr_version) {
spin_unlock(&fc->lock);
return;
}
fuse_change_attributes_common(inode, attr, attr_valid);
oldsize = inode->i_size;
i_size_write(inode, attr->size);
spin_unlock(&fc->lock);
if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
truncate_pagecache(inode, oldsize, attr->size);
invalidate_inode_pages2(inode->i_mapping);
}
}
/*
* Check whether the dentry is still valid
*
* If the entry validity timeout has expired and the dentry is
* positive, try to redo the lookup. If the lookup results in a
* different inode, then let the VFS invalidate the dentry and redo
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
{
struct inode *inode = entry->d_inode;
if (inode && is_bad_inode(inode))
return 0;
else if (fuse_dentry_time(entry) < get_jiffies_64()) {
int err;
struct fuse_entry_out outarg;
struct fuse_conn *fc;
struct fuse_req *req;
struct fuse_req *forget_req;
struct dentry *parent;
u64 attr_version;
/* For negative dentries, always do a fresh lookup */
if (!inode)
return 0;
fc = get_fuse_conn(inode);
req = fuse_get_req(fc);
if (IS_ERR(req))
return 0;
forget_req = fuse_get_req(fc);
if (IS_ERR(forget_req)) {
fuse_put_request(fc, req);
return 0;
}
attr_version = fuse_get_attr_version(fc);
parent = dget_parent(entry);
fuse_lookup_init(fc, req, get_node_id(parent->d_inode),
&entry->d_name, &outarg);
fuse_request_send(fc, req);
dput(parent);
err = req->out.h.error;
fuse_put_request(fc, req);
/* Zero nodeid is same as -ENOENT */
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
fuse_send_forget(fc, forget_req,
outarg.nodeid, 1);
return 0;
}
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
}
fuse_put_request(fc, forget_req);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
return 0;
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
fuse_change_entry_timeout(entry, &outarg);
}
return 1;
}
/*
* Set attributes, and at the same time refresh them.
*
* Truncation is slightly complicated, because the 'truncate' request
* may fail, in which case we don't want to touch the mapping.
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
int fuse_do_setattr(struct inode *inode, struct iattr *attr,
struct file *file)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_req *req;
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
bool is_truncate = false;
loff_t oldsize;
int err;
if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
attr->ia_valid |= ATTR_FORCE;
err = inode_change_ok(inode, attr);
if (err)
return err;
if (attr->ia_valid & ATTR_OPEN) {
if (fc->atomic_o_trunc)
return 0;
file = NULL;
}
if (attr->ia_valid & ATTR_SIZE)
is_truncate = true;
req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
if (is_truncate) {
fuse_set_nowrite(inode);
set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
}
memset(&inarg, 0, sizeof(inarg));
memset(&outarg, 0, sizeof(outarg));
iattr_to_fattr(attr, &inarg);
if (file) {
struct fuse_file *ff = file->private_data;
inarg.valid |= FATTR_FH;
inarg.fh = ff->fh;
}
if (attr->ia_valid & ATTR_SIZE) {
/* For mandatory locking in truncate */
inarg.valid |= FATTR_LOCKOWNER;
inarg.lock_owner = fuse_lock_owner_id(fc, current->files);
}
req->in.h.opcode = FUSE_SETATTR;
req->in.h.nodeid = get_node_id(inode);
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->out.numargs = 1;
if (fc->minor < 9)
req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
else
req->out.args[0].size = sizeof(outarg);
req->out.args[0].value = &outarg;
fuse_request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (err) {
if (err == -EINTR)
fuse_invalidate_attr(inode);
goto error;
}
if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
goto error;
}
spin_lock(&fc->lock);
fuse_change_attributes_common(inode, &outarg.attr,
attr_timeout(&outarg));
oldsize = inode->i_size;
i_size_write(inode, outarg.attr.size);
if (is_truncate) {
/* NOTE: this may release/reacquire fc->lock */
__fuse_release_nowrite(inode);
}
spin_unlock(&fc->lock);
/*
* Only call invalidate_inode_pages2() after removing
* FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
*/
if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
truncate_pagecache(inode, outarg.attr.size);
invalidate_inode_pages2(inode->i_mapping);
}
clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
return 0;
error:
if (is_truncate)
fuse_release_nowrite(inode);
clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
return err;
}
static int fuse_inode_set(struct inode *inode, void *_nodeidp)
{
u64 nodeid = *(u64 *) _nodeidp;
get_fuse_inode(inode)->nodeid = nodeid;
return 0;
}
/*
* Check whether the dentry is still valid
*
* If the entry validity timeout has expired and the dentry is
* positive, try to redo the lookup. If the lookup results in a
* different inode, then let the VFS invalidate the dentry and redo
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
{
struct inode *inode;
struct dentry *parent;
struct fuse_conn *fc;
int ret;
inode = ACCESS_ONCE(entry->d_inode);
if (inode && is_bad_inode(inode))
goto invalid;
else if (fuse_dentry_time(entry) < get_jiffies_64()) {
int err;
struct fuse_entry_out outarg;
struct fuse_req *req;
struct fuse_forget_link *forget;
u64 attr_version;
/* For negative dentries, always do a fresh lookup */
if (!inode)
goto invalid;
ret = -ECHILD;
if (flags & LOOKUP_RCU)
goto out;
fc = get_fuse_conn(inode);
req = fuse_get_req_nopages(fc);
ret = PTR_ERR(req);
if (IS_ERR(req))
goto out;
forget = fuse_alloc_forget();
if (!forget) {
fuse_put_request(fc, req);
ret = -ENOMEM;
goto out;
}
attr_version = fuse_get_attr_version(fc);
parent = dget_parent(entry);
fuse_lookup_init(fc, req, get_node_id(parent->d_inode),
&entry->d_name, &outarg);
fuse_request_send(fc, req);
dput(parent);
err = req->out.h.error;
fuse_put_request(fc, req);
/* Zero nodeid is same as -ENOENT */
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
fuse_queue_forget(fc, forget, outarg.nodeid, 1);
goto invalid;
}
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
}
kfree(forget);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
fuse_change_entry_timeout(entry, &outarg);
} else if (inode) {
fc = get_fuse_conn(inode);
if (fc->readdirplus_auto) {
parent = dget_parent(entry);
fuse_advise_use_readdirplus(parent->d_inode);
dput(parent);
}
}
ret = 1;
out:
return ret;
invalid:
ret = 0;
if (check_submounts_and_drop(entry) != 0)
ret = 1;
goto out;
}
static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
{
struct inode *inode;
inode = ACCESS_ONCE(entry->d_inode);
if (inode && is_bad_inode(inode))
return 0;
else if (fuse_dentry_time(entry) < get_jiffies_64()) {
int err;
struct fuse_entry_out outarg;
struct fuse_conn *fc;
struct fuse_req *req;
struct fuse_forget_link *forget;
struct dentry *parent;
u64 attr_version;
if (!inode)
return 0;
if (nd && (nd->flags & LOOKUP_RCU))
return -ECHILD;
fc = get_fuse_conn(inode);
req = fuse_get_req(fc);
if (IS_ERR(req))
return 0;
forget = fuse_alloc_forget();
if (!forget) {
fuse_put_request(fc, req);
return 0;
}
attr_version = fuse_get_attr_version(fc);
parent = dget_parent(entry);
fuse_lookup_init(fc, req, get_node_id(parent->d_inode),
&entry->d_name, &outarg);
fuse_request_send(fc, req);
dput(parent);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
fuse_queue_forget(fc, forget, outarg.nodeid, 1);
return 0;
}
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
}
kfree(forget);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
return 0;
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
fuse_change_entry_timeout(entry, &outarg);
}
return 1;
}
/*
* Mark the attributes as stale, so that at the next call to
* ->getattr() they will be fetched from userspace
*/
void fuse_invalidate_attr(struct inode *inode)
{
get_fuse_inode(inode)->i_time = 0;
}
static int fuse_direntplus_link(struct file *file,
struct fuse_direntplus *direntplus,
u64 attr_version)
{
int err;
struct fuse_entry_out *o = &direntplus->entry_out;
struct fuse_dirent *dirent = &direntplus->dirent;
struct dentry *parent = file->f_path.dentry;
struct qstr name = QSTR_INIT(dirent->name, dirent->namelen);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = parent->d_inode;
struct fuse_conn *fc;
struct inode *inode;
if (!o->nodeid) {
/*
* Unlike in the case of fuse_lookup, zero nodeid does not mean
* ENOENT. Instead, it only means the userspace filesystem did
* not want to return attributes/handle for this entry.
*
* So do nothing.
*/
return 0;
}
if (name.name[0] == '.') {
/*
* We could potentially refresh the attributes of the directory
* and its parent?
*/
if (name.len == 1)
return 0;
if (name.name[1] == '.' && name.len == 2)
return 0;
}
if (invalid_nodeid(o->nodeid))
return -EIO;
if (!fuse_valid_type(o->attr.mode))
return -EIO;
fc = get_fuse_conn(dir);
name.hash = full_name_hash(name.name, name.len);
dentry = d_lookup(parent, &name);
if (dentry) {
inode = dentry->d_inode;
if (!inode) {
d_drop(dentry);
} else if (get_node_id(inode) != o->nodeid ||
((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
err = d_invalidate(dentry);
if (err)
goto out;
} else if (is_bad_inode(inode)) {
err = -EIO;
goto out;
} else {
struct fuse_inode *fi;
fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
fuse_change_attributes(inode, &o->attr,
entry_attr_timeout(o),
attr_version);
/*
* The other branch to 'found' comes via fuse_iget()
* which bumps nlookup inside
*/
goto found;
}
dput(dentry);
}
dentry = d_alloc(parent, &name);
err = -ENOMEM;
if (!dentry)
goto out;
inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
&o->attr, entry_attr_timeout(o), attr_version);
if (!inode)
goto out;
alias = fuse_materialise_dentry(dentry, inode);
err = PTR_ERR(alias);
if (IS_ERR(alias))
goto out;
if (alias) {
dput(dentry);
dentry = alias;
}
found:
fuse_change_entry_timeout(dentry, o);
err = 0;
out:
dput(dentry);
return err;
}
/*
* Set attributes, and at the same time refresh them.
*
* Truncation is slightly complicated, because the 'truncate' request
* may fail, in which case we don't want to touch the mapping.
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
struct file *file)
{
struct inode *inode = d_inode(dentry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
FUSE_ARGS(args);
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
bool is_truncate = false;
bool is_wb = fc->writeback_cache;
loff_t oldsize;
int err;
bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode);
if (!fc->default_permissions)
attr->ia_valid |= ATTR_FORCE;
err = setattr_prepare(dentry, attr);
if (err)
return err;
if (attr->ia_valid & ATTR_OPEN) {
if (fc->atomic_o_trunc)
return 0;
file = NULL;
}
if (attr->ia_valid & ATTR_SIZE)
is_truncate = true;
if (is_truncate) {
fuse_set_nowrite(inode);
set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
if (trust_local_cmtime && attr->ia_size != inode->i_size)
attr->ia_valid |= ATTR_MTIME | ATTR_CTIME;
}
memset(&inarg, 0, sizeof(inarg));
memset(&outarg, 0, sizeof(outarg));
iattr_to_fattr(attr, &inarg, trust_local_cmtime);
if (file) {
struct fuse_file *ff = file->private_data;
inarg.valid |= FATTR_FH;
inarg.fh = ff->fh;
}
if (attr->ia_valid & ATTR_SIZE) {
/* For mandatory locking in truncate */
inarg.valid |= FATTR_LOCKOWNER;
inarg.lock_owner = fuse_lock_owner_id(fc, current->files);
}
fuse_setattr_fill(fc, &args, inode, &inarg, &outarg);
err = fuse_simple_request(fc, &args);
if (err) {
if (err == -EINTR)
fuse_invalidate_attr(inode);
goto error;
}
if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
goto error;
}
spin_lock(&fc->lock);
/* the kernel maintains i_mtime locally */
if (trust_local_cmtime) {
if (attr->ia_valid & ATTR_MTIME)
inode->i_mtime = attr->ia_mtime;
if (attr->ia_valid & ATTR_CTIME)
inode->i_ctime = attr->ia_ctime;
/* FIXME: clear I_DIRTY_SYNC? */
}
fuse_change_attributes_common(inode, &outarg.attr,
attr_timeout(&outarg));
oldsize = inode->i_size;
/* see the comment in fuse_change_attributes() */
if (!is_wb || is_truncate || !S_ISREG(inode->i_mode))
i_size_write(inode, outarg.attr.size);
if (is_truncate) {
/* NOTE: this may release/reacquire fc->lock */
__fuse_release_nowrite(inode);
}
spin_unlock(&fc->lock);
/*
* Only call invalidate_inode_pages2() after removing
* FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
*/
if ((is_truncate || !is_wb) &&
S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
truncate_pagecache(inode, outarg.attr.size);
invalidate_inode_pages2(inode->i_mapping);
}
clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
return 0;
error:
if (is_truncate)
fuse_release_nowrite(inode);
clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
return err;
}
static void fuse_advise_use_readdirplus(struct inode *dir)
{
struct fuse_inode *fi = get_fuse_inode(dir);
set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
}
/*
* Check whether the dentry is still valid
*
* If the entry validity timeout has expired and the dentry is
* positive, try to redo the lookup. If the lookup results in a
* different inode, then let the VFS invalidate the dentry and redo
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
{
struct inode *inode;
struct dentry *parent;
struct fuse_conn *fc;
struct fuse_inode *fi;
int ret;
inode = d_inode_rcu(entry);
if (inode && is_bad_inode(inode))
goto invalid;
else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
(flags & LOOKUP_REVAL)) {
struct fuse_entry_out outarg;
FUSE_ARGS(args);
struct fuse_forget_link *forget;
u64 attr_version;
/* For negative dentries, always do a fresh lookup */
if (!inode)
goto invalid;
ret = -ECHILD;
if (flags & LOOKUP_RCU)
goto out;
fc = get_fuse_conn(inode);
forget = fuse_alloc_forget();
ret = -ENOMEM;
if (!forget)
goto out;
attr_version = fuse_get_attr_version(fc);
parent = dget_parent(entry);
fuse_lookup_init(fc, &args, get_node_id(d_inode(parent)),
&entry->d_name, &outarg);
ret = fuse_simple_request(fc, &args);
dput(parent);
/* Zero nodeid is same as -ENOENT */
if (!ret && !outarg.nodeid)
ret = -ENOENT;
if (!ret) {
fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
fuse_queue_forget(fc, forget, outarg.nodeid, 1);
goto invalid;
}
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
}
kfree(forget);
if (ret == -ENOMEM)
goto out;
if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
forget_all_cached_acls(inode);
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
fuse_change_entry_timeout(entry, &outarg);
} else if (inode) {
fi = get_fuse_inode(inode);
if (flags & LOOKUP_RCU) {
if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state))
return -ECHILD;
} else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) {
parent = dget_parent(entry);
fuse_advise_use_readdirplus(d_inode(parent));
dput(parent);
}
}
ret = 1;
out:
return ret;
invalid:
ret = 0;
goto out;
}
static int fuse_direntplus_link(struct file *file,
struct fuse_direntplus *direntplus,
u64 attr_version)
{
struct fuse_entry_out *o = &direntplus->entry_out;
struct fuse_dirent *dirent = &direntplus->dirent;
struct dentry *parent = file->f_path.dentry;
struct qstr name = QSTR_INIT(dirent->name, dirent->namelen);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = d_inode(parent);
struct fuse_conn *fc;
struct inode *inode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
if (!o->nodeid) {
/*
* Unlike in the case of fuse_lookup, zero nodeid does not mean
* ENOENT. Instead, it only means the userspace filesystem did
* not want to return attributes/handle for this entry.
*
* So do nothing.
*/
return 0;
}
if (name.name[0] == '.') {
/*
* We could potentially refresh the attributes of the directory
* and its parent?
*/
if (name.len == 1)
return 0;
if (name.name[1] == '.' && name.len == 2)
return 0;
}
if (invalid_nodeid(o->nodeid))
return -EIO;
if (!fuse_valid_type(o->attr.mode))
return -EIO;
fc = get_fuse_conn(dir);
name.hash = full_name_hash(parent, name.name, name.len);
dentry = d_lookup(parent, &name);
if (!dentry) {
retry:
dentry = d_alloc_parallel(parent, &name, &wq);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
}
if (!d_in_lookup(dentry)) {
struct fuse_inode *fi;
inode = d_inode(dentry);
if (!inode ||
get_node_id(inode) != o->nodeid ||
((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
d_invalidate(dentry);
dput(dentry);
goto retry;
}
if (is_bad_inode(inode)) {
dput(dentry);
return -EIO;
}
fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
forget_all_cached_acls(inode);
fuse_change_attributes(inode, &o->attr,
entry_attr_timeout(o),
attr_version);
/*
* The other branch comes via fuse_iget()
* which bumps nlookup inside
*/
} else {
inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
&o->attr, entry_attr_timeout(o),
attr_version);
if (!inode)
inode = ERR_PTR(-ENOMEM);
alias = d_splice_alias(inode, dentry);
d_lookup_done(dentry);
if (alias) {
dput(dentry);
dentry = alias;
}
if (IS_ERR(dentry))
return PTR_ERR(dentry);
}
if (fc->readdirplus_auto)
set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
fuse_change_entry_timeout(dentry, o);
dput(dentry);
return 0;
}
/*
* Set attributes, and at the same time refresh them.
*
* Truncation is slightly complicated, because the 'truncate' request
* may fail, in which case we don't want to touch the mapping.
* vmtruncate() doesn't allow for this case. So do the rlimit
* checking by hand and call vmtruncate() only after the file has
* actually been truncated.
*/
static int fuse_setattr(struct dentry *entry, struct iattr *attr)
{
struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_req *req;
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
int err;
int is_truncate = 0;
if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
err = inode_change_ok(inode, attr);
if (err)
return err;
}
if (attr->ia_valid & ATTR_SIZE) {
unsigned long limit;
is_truncate = 1;
#ifdef KERNEL_2_6_10_PLUS
limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
#else
limit = current->rlim[RLIMIT_FSIZE].rlim_cur;
#endif
if (limit != RLIM_INFINITY && attr->ia_size > (loff_t) limit) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
}
req = fuse_get_request(fc);
if (!req)
return -EINTR;
memset(&inarg, 0, sizeof(inarg));
iattr_to_fattr(attr, &inarg);
req->in.h.opcode = FUSE_SETATTR;
req->in.h.nodeid = get_node_id(inode);
req->inode = inode;
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
req->out.numargs = 1;
req->out.args[0].size = sizeof(outarg);
req->out.args[0].value = &outarg;
request_send(fc, req);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
#ifndef KERNEL_2_6_12_PLUS
if (get_node_id(inode) != FUSE_ROOT_ID)
make_bad_inode(inode);
#else
make_bad_inode(inode);
#endif
err = -EIO;
} else {
if (is_truncate) {
loff_t origsize = i_size_read(inode);
i_size_write(inode, outarg.attr.size);
if (origsize > outarg.attr.size)
vmtruncate(inode, outarg.attr.size);
}
fuse_change_attributes(inode, &outarg.attr);
fi->i_time = time_to_jiffies(outarg.attr_valid,
outarg.attr_valid_nsec);
}
} else if (err == -EINTR)
fuse_invalidate_attr(inode);
return err;
}
