static int autofs4_write(struct file *file, const void *addr, int bytes)
{
unsigned long sigpipe, flags;
mm_segment_t fs;
const char *data = (const char *)addr;
ssize_t wr = 0;
/** WARNING: this is not safe for writing more than PIPE_BUF bytes! **/
sigpipe = sigismember(¤t->pending.signal, SIGPIPE);
/* Save pointer to user space and point back to kernel space */
fs = get_fs();
set_fs(KERNEL_DS);
while (bytes &&
(wr = file->f_op->write(file,data,bytes,&tx_cache_get_file(file)->f_pos)) > 0) {
data += wr;
bytes -= wr;
}
set_fs(fs);
/* Keep the currently executing process from receiving a
SIGPIPE unless it was already supposed to get one */
if (wr == -EPIPE && !sigpipe) {
spin_lock_irqsave(¤t->sighand->siglock, flags);
sigdelset(¤t->pending.signal, SIGPIPE);
recalc_sigpending();
spin_unlock_irqrestore(¤t->sighand->siglock, flags);
}
return (bytes > 0);
}
/**
* seq_open - initialize sequential file
* @file: file we initialize
* @op: method table describing the sequence
*
* seq_open() sets @file, associating it with a sequence described
* by @op. @op->start() sets the iterator up and returns the first
* element of sequence. @op->stop() shuts it down. @op->next()
* returns the next element of sequence. @op->show() prints element
* into the buffer. In case of error ->start() and ->next() return
* ERR_PTR(error). In the end of sequence they return %NULL. ->show()
* returns 0 in case of success and negative number in case of error.
*/
int seq_open(struct file *file, const struct seq_operations *op)
{
struct seq_file *p = file->private_data;
struct _file *_file;
if (!p) {
p = kmalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return -ENOMEM;
file->private_data = p;
record_tx_alloc(p, NULL);
}
memset(p, 0, sizeof(*p));
mutex_init(&p->lock);
p->op = op;
/*
* Wrappers around seq_open(e.g. swaps_open) need to be
* aware of this. If they set f_version themselves, they
* should call seq_open first and then set f_version.
*/
_file = tx_cache_get_file(file);
_file->f_version = 0;
/* SEQ files support lseek, but not pread/pwrite */
_file->f_mode &= ~(FMODE_PREAD | FMODE_PWRITE);
return 0;
}
static ssize_t
configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
struct configfs_buffer * buffer = file->private_data;
ssize_t len;
down(&buffer->sem);
len = fill_write_buffer(buffer, buf, count);
if (len > 0)
len = flush_write_buffer(tx_cache_get_file(file)->f_path.dentry, buffer, count);
if (len > 0)
*ppos += len;
up(&buffer->sem);
return len;
}
static ssize_t
configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
struct configfs_buffer * buffer = file->private_data;
ssize_t retval = 0;
down(&buffer->sem);
if (buffer->needs_read_fill) {
if ((retval = fill_read_buffer(tx_cache_get_file(file)->f_path.dentry,buffer)))
goto out;
}
pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n",
__FUNCTION__, count, *ppos, buffer->page);
retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
buffer->count);
out:
up(&buffer->sem);
return retval;
}
static int configfs_release(struct _inode * inode, struct file * filp)
{
struct config_item * item = to_item(file_get_dentry(filp)->d_parent);
struct configfs_attribute * attr = to_attr(tx_cache_get_file(filp)->f_path.dentry);
struct module * owner = attr->ca_owner;
struct configfs_buffer * buffer = filp->private_data;
if (item)
config_item_put(item);
/* After this point, attr should not be accessed. */
module_put(owner);
if (buffer) {
if (buffer->page)
free_page((unsigned long)buffer->page);
kfree(buffer);
}
return 0;
}
static int acct_on(char *name)
{
struct file *file;
struct _file *_file;
int error;
/* Difference from BSD - they don't do O_APPEND */
file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
if (IS_ERR(file))
return PTR_ERR(file);
_file = tx_cache_get_file(file);
if (!S_ISREG(d_get_inode(f_get_dentry_ro(_file))->i_mode)) {
filp_close(file, NULL);
return -EACCES;
}
if (!file->f_op->write) {
filp_close(file, NULL);
return -EIO;
}
error = security_acct(file);
if (error) {
filp_close(file, NULL);
return error;
}
spin_lock(&acct_globals.lock);
mnt_pin(_file->f_path.mnt);
acct_file_reopen(file);
spin_unlock(&acct_globals.lock);
mntput(_file->f_path.mnt); /* it's pinned, now give up active reference */
return 0;
}
/*
* Careful here! We test whether the file pointer is NULL before
* releasing the fd. This ensures that one clone task can't release
* an fd while another clone is opening it.
*/
asmlinkage long sys_close(unsigned int fd)
{
struct file * filp;
struct files_struct *files = current->files;
struct fdtable *fdt;
int retval;
if(need_files_checkpoint())
checkpoint_files();
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
goto out_unlock;
filp = fdt->fd[fd];
if (!filp)
goto out_unlock;
tx_cache_get_file(filp); //get tx refcount on file
rcu_assign_pointer(fdt->fd[fd], NULL);
FD_CLR(fd, fdt->close_on_exec); //??check later
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
retval = filp_close(filp, files);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
retval == -ERESTARTNOINTR ||
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
return retval;
out_unlock:
spin_unlock(&files->file_lock);
return -EBADF;
}
static struct file *__dentry_open(struct _dentry *dentry, struct vfsmount *mnt,
int flags, struct file *f,
int (*open)(struct _inode *, struct file *))
{
struct _inode *inode;
int error;
struct super_block *sb;
struct _file *_f = tx_cache_get_file(f);
_f->f_flags = flags;
_f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
inode = d_get_inode(dentry);
sb = inode->i_sb;
if (_f->f_mode & FMODE_WRITE) {
error = get_write_access(parent(inode));
if (error)
goto cleanup_file;
}
f->f_mapping = inode->i_mapping;
_f->f_path.dentry = parent(dentry);
_f->f_path.mnt = mnt;
_f->f_pos = 0;
f->f_op = fops_get(inode->i_fop);
file_move(f, &sb->s_files);
if (!open && f->f_op)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
_f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra,
tx_cache_get_inode(f->f_mapping->host)->i_mapping);
/* NB: we're sure to have correct a_ops only after f_op->open */
if (_f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops ||
((!f->f_mapping->a_ops->direct_IO) &&
(!f->f_mapping->a_ops->get_xip_page))) {
fput(f);
f = ERR_PTR(-EINVAL);
}
}
return f;
cleanup_all:
fops_put(f->f_op);
if (_f->f_mode & FMODE_WRITE)
put_write_access(parent(inode));
file_kill(f);
_f->f_path.dentry = NULL;
_f->f_path.mnt = NULL;
cleanup_file:
/* Avoid issues if we recycle this object */
if(live_transaction())
early_release(&f->xobj, 1);
put_filp(f);
dput(parent(dentry));
mntput(mnt);
return ERR_PTR(error);
}
/*
* This is used by subsystems that don't want seekable
* file descriptors
*/
int nonseekable_open(struct _inode *inode, struct file *filp)
{
tx_cache_get_file(filp)->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
return 0;
}
/**
* seq_read - ->read() method for sequential files.
* @file: the file to read from
* @buf: the buffer to read to
* @size: the maximum number of bytes to read
* @ppos: the current position in the file
*
* Ready-made ->f_op->read()
*/
ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
{
struct seq_file *m = (struct seq_file *)file->private_data;
size_t copied = 0;
loff_t pos;
size_t n;
void *p;
int err = 0;
struct _file *_file;
mutex_lock(&m->lock);
/*
* seq_file->op->..m_start/m_stop/m_next may do special actions
* or optimisations based on the file->f_version, so we want to
* pass the file->f_version to those methods.
*
* seq_file->version is just copy of f_version, and seq_file
* methods can treat it simply as file version.
* It is copied in first and copied out after all operations.
* It is convenient to have it as part of structure to avoid the
* need of passing another argument to all the seq_file methods.
*/
_file = tx_cache_get_file(file);
m->version = _file->f_version;
/* grab buffer if we didn't have one */
if (!m->buf) {
m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
if (!m->buf)
goto Enomem;
}
/* if not empty - flush it first */
if (m->count) {
n = min(m->count, size);
err = copy_to_user(buf, m->buf + m->from, n);
if (err)
goto Efault;
m->count -= n;
m->from += n;
size -= n;
buf += n;
copied += n;
if (!m->count)
m->index++;
if (!size)
goto Done;
}
/* we need at least one record in buffer */
while (1) {
pos = m->index;
p = m->op->start(m, &pos);
err = PTR_ERR(p);
if (!p || IS_ERR(p))
break;
err = m->op->show(m, p);
if (err)
break;
if (m->count < m->size)
goto Fill;
m->op->stop(m, p);
kfree(m->buf);
m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
if (!m->buf)
goto Enomem;
m->count = 0;
m->version = 0;
}
m->op->stop(m, p);
m->count = 0;
goto Done;
Fill:
/* they want more? let's try to get some more */
while (m->count < size) {
size_t offs = m->count;
loff_t next = pos;
p = m->op->next(m, p, &next);
if (!p || IS_ERR(p)) {
err = PTR_ERR(p);
break;
}
err = m->op->show(m, p);
if (err || m->count == m->size) {
m->count = offs;
break;
}
pos = next;
}
m->op->stop(m, p);
n = min(m->count, size);
err = copy_to_user(buf, m->buf, n);
if (err)
goto Efault;
copied += n;
m->count -= n;
if (m->count)
m->from = n;
else
pos++;
m->index = pos;
Done:
if (!copied)
copied = err;
else
*ppos += copied;
_file->f_version = m->version;
mutex_unlock(&m->lock);
return copied;
Enomem:
err = -ENOMEM;
goto Done;
Efault:
err = -EFAULT;
goto Done;
}
/**
* anon_inode_getfd - creates a new file instance by hooking it up to and
* anonymous inode, and a dentry that describe the "class"
* of the file
*
* @pfd: [out] pointer to the file descriptor
* @dpinode: [out] pointer to the inode
* @pfile: [out] pointer to the file struct
* @name: [in] name of the "class" of the new file
* @fops [in] file operations for the new file
* @priv [in] private data for the new file (will be file's private_data)
*
* Creates a new file by hooking it on a single inode. This is useful for files
* that do not need to have a full-fledged inode in order to operate correctly.
* All the files created with anon_inode_getfd() will share a single inode, by
* hence saving memory and avoiding code duplication for the file/inode/dentry
* setup.
*/
int anon_inode_getfd(int *pfd, struct inode **pinode, struct file **pfile,
const char *name, const struct file_operations *fops,
void *priv)
{
struct qstr this;
struct dentry *dentry;
struct _dentry *_dentry;
struct inode *inode;
struct _inode *_inode;
struct file *file;
struct _file *_file;
int error, fd;
if (IS_ERR(anon_inode_inode))
return -ENODEV;
file = get_empty_filp();
if (!file)
return -ENFILE;
_file = tx_cache_get_file(file);
inode = igrab(anon_inode_inode);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
goto err_put_filp;
}
_inode = tx_cache_get_inode(inode);
error = get_unused_fd();
if (error < 0)
goto err_iput;
fd = error;
/*
* Link the inode to a directory entry by creating a unique name
* using the inode sequence number.
*/
error = -ENOMEM;
this.name = name;
this.len = strlen(name);
this.hash = 0;
dentry = d_alloc(tx_cache_get_dentry(anon_inode_mnt->mnt_sb->s_root), &this);
if (!dentry)
goto err_put_unused_fd;
_dentry = tx_cache_get_dentry(dentry);
_dentry->d_op = &anon_inodefs_dentry_operations;
/* Do not publish this dentry inside the global dentry hash table */
_dentry->d_flags &= ~DCACHE_UNHASHED;
d_instantiate(_dentry, _inode);
_file->f_path.mnt = mntget(anon_inode_mnt);
_file->f_path.dentry = dentry;
file->f_mapping = _inode->i_mapping;
_file->f_pos = 0;
_file->f_flags = O_RDWR;
file->f_op = fops;
_file->f_mode = FMODE_READ | FMODE_WRITE;
_file->f_version = 0;
file->private_data = priv;
fd_install(fd, file);
*pfd = fd;
*pinode = inode;
*pfile = file;
return 0;
err_put_unused_fd:
put_unused_fd(fd);
err_iput:
iput(inode);
err_put_filp:
put_filp(file);
return error;
}
/*
* When you add any new common ioctls to the switches above and below
* please update compat_sys_ioctl() too.
*
* vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
*/
int vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg)
{
unsigned int flag;
int on, error = 0;
umode_t mode;
struct _file *_filp = tx_cache_get_file(filp);
/* Patch up ioctl for bad tx cases*/
if((!_filp) || !_filp->f_dentry ){
#ifdef CONFIG_TX_KSTM_WARNINGS
printk(KERN_ERR "Fixing up ioctl\n");
#endif
return 0;
}
mode = d_get_inode_ro(f_get_dentry(_filp))->i_mode;
switch (cmd) {
case FIOCLEX:
set_close_on_exec(fd, 1);
break;
case FIONCLEX:
set_close_on_exec(fd, 0);
break;
case FIONBIO:
if ((error = get_user(on, (int __user *)arg)) != 0)
break;
flag = O_NONBLOCK;
#ifdef __sparc__
/* SunOS compatibility item. */
if(O_NONBLOCK != O_NDELAY)
flag |= O_NDELAY;
#endif
if (on)
_filp->f_flags |= flag;
else
_filp->f_flags &= ~flag;
break;
case FIOASYNC:
if ((error = get_user(on, (int __user *)arg)) != 0)
break;
flag = on ? FASYNC : 0;
/* Did FASYNC state change ? */
if ((flag ^ _filp->f_flags) & FASYNC) {
if (filp->f_op && filp->f_op->fasync) {
lock_kernel();
error = filp->f_op->fasync(fd, filp, on);
unlock_kernel();
}
else error = -ENOTTY;
}
if (error != 0)
break;
if (on)
_filp->f_flags |= FASYNC;
else
_filp->f_flags &= ~FASYNC;
break;
case FIOQSIZE:
if (S_ISDIR(mode) ||
S_ISREG(mode) ||
S_ISLNK(mode)) {
loff_t res = inode_get_bytes(f_get_dentry(_filp)->d_inode);
error = copy_to_user((loff_t __user *)arg, &res, sizeof(res)) ? -EFAULT : 0;
}
else
error = -ENOTTY;
break;
default:
if(live_transaction()){
/* Short circuit this stupid ioctl */
if(cmd == TIOCGWINSZ){
#ifdef CONFIG_TX_KSTM_WARNINGS
printk(KERN_ERR "Warning: some bozo wants to know the terminal width in a transaction.\n");
#endif
error = -EINVAL;
break;
} else if(cmd != TCGETS)
BUG();
}
if (S_ISREG(mode))
error = file_ioctl(filp, cmd, arg);
else
error = do_ioctl(filp, cmd, arg);
break;
}
return error;
}
static int check_perm(struct _inode * inode, struct file * file)
{
struct config_item *item = configfs_get_config_item(file_get_dentry(file)->d_parent);
struct configfs_attribute * attr;
struct configfs_buffer * buffer;
struct configfs_item_operations * ops = NULL;
struct _file *_file = tx_cache_get_file(file);
int error = 0;
attr = to_attr(_file->f_path.dentry);
if (!item || !attr)
goto Einval;
/* Grab the module reference for this attribute if we have one */
if (!try_module_get(attr->ca_owner)) {
error = -ENODEV;
goto Done;
}
if (item->ci_type)
ops = item->ci_type->ct_item_ops;
else
goto Eaccess;
/* File needs write support.
* The inode's perms must say it's ok,
* and we must have a store method.
*/
if (_file->f_mode & FMODE_WRITE) {
if (!(inode->i_mode & S_IWUGO) || !ops->store_attribute)
goto Eaccess;
}
/* File needs read support.
* The inode's perms must say it's ok, and we there
* must be a show method for it.
*/
if (_file->f_mode & FMODE_READ) {
if (!(inode->i_mode & S_IRUGO) || !ops->show_attribute)
goto Eaccess;
}
/* No error? Great, allocate a buffer for the file, and store it
* it in file->private_data for easy access.
*/
buffer = kzalloc(sizeof(struct configfs_buffer),GFP_KERNEL);
if (!buffer) {
error = -ENOMEM;
goto Enomem;
}
init_MUTEX(&buffer->sem);
buffer->needs_read_fill = 1;
buffer->ops = ops;
file->private_data = buffer;
goto Done;
Einval:
error = -EINVAL;
goto Done;
Eaccess:
error = -EACCES;
Enomem:
module_put(attr->ca_owner);
Done:
if (error && item)
config_item_put(item);
return error;
}
