ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
struct inode *inode = file->f_dentry->d_inode;
ssize_t ret;
if (!(file->f_mode & FMODE_READ))
return -EBADF;
if (!file->f_op || (!file->f_op->read && !file->f_op->aio_read))
return -EINVAL;
ret = locks_verify_area(FLOCK_VERIFY_READ, inode, file, *pos, count);
if (!ret) {
ret = security_file_permission (file, MAY_READ);
if (!ret) {
if (file->f_op->read)
ret = file->f_op->read(file, buf, count, pos);
else
ret = do_sync_read(file, buf, count, pos);
if (ret > 0)
dnotify_parent(file->f_dentry, DN_ACCESS);
}
}
return ret;
}
/**
* sysfs_update_file - update the modified timestamp on an object attribute.
* @kobj: object we're acting for.
* @attr: attribute descriptor.
*
* Also call dnotify for the dentry, which lots of userspace programs
* use.
*/
int sysfs_update_file(struct kobject * kobj, const struct attribute * attr)
{
struct dentry * dir = kobj->dentry;
struct dentry * victim;
int res = -ENOENT;
down(&dir->d_inode->i_sem);
victim = sysfs_get_dentry(dir, attr->name);
if (!IS_ERR(victim)) {
/* make sure dentry is really there */
if (victim->d_inode &&
(victim->d_parent->d_inode == dir->d_inode)) {
victim->d_inode->i_mtime = CURRENT_TIME;
dnotify_parent(victim, DN_MODIFY);
/**
* Drop reference from initial sysfs_get_dentry().
*/
dput(victim);
res = 0;
}
/**
* Drop the reference acquired from sysfs_get_dentry() above.
*/
dput(victim);
}
up(&dir->d_inode->i_sem);
return res;
}
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
struct inode *inode = file->f_dentry->d_inode;
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
return -EINVAL;
ret = locks_verify_area(FLOCK_VERIFY_WRITE, inode, file, *pos, count);
if (!ret) {
ret = security_file_permission (file, MAY_WRITE);
if (!ret) {
if (file->f_op->write)
ret = file->f_op->write(file, buf, count, pos);
else
ret = do_sync_write(file, buf, count, pos);
if (ret > 0)
dnotify_parent(file->f_dentry, DN_MODIFY);
}
}
return ret;
}
asmlinkage ssize_t sys_pread(unsigned int fd, char * buf,
size_t count, loff_t pos)
{
ssize_t ret;
struct file * file;
ssize_t (*read)(struct file *, char *, size_t, loff_t *);
ret = -EBADF;
file = fget(fd);
if (!file)
goto bad_file;
if (!(file->f_mode & FMODE_READ))
goto out;
ret = locks_verify_area(FLOCK_VERIFY_READ, file->f_dentry->d_inode,
file, pos, count);
if (ret)
goto out;
ret = -EINVAL;
if (!file->f_op || !(read = file->f_op->read))
goto out;
if (pos < 0)
goto out;
ret = read(file, buf, count, &pos);
if (ret > 0)
dnotify_parent(file->f_dentry, DN_ACCESS);
out:
fput(file);
bad_file:
return ret;
}
asmlinkage ssize_t sys_pwrite(unsigned int fd, const char * buf,
size_t count, loff_t pos)
{
ssize_t ret;
struct file * file;
ssize_t (*write)(struct file *, const char *, size_t, loff_t *);
ret = -EBADF;
file = fget(fd);
if (!file)
goto bad_file;
if (!(file->f_mode & FMODE_WRITE))
goto out;
ret = locks_verify_area(FLOCK_VERIFY_WRITE, file->f_dentry->d_inode,
file, pos, count);
if (ret)
goto out;
ret = -EINVAL;
if (!file->f_op || !(write = file->f_op->write))
goto out;
if (pos < 0)
goto out;
ret = write(file, buf, count, &pos);
if (ret > 0)
dnotify_parent(file->f_dentry, DN_MODIFY);
out:
fput(file);
bad_file:
return ret;
}
asmlinkage ssize_t sys_write(unsigned int fd, const char * buf, size_t count)
{
ssize_t ret;
struct file * file;
ret = -EBADF;
file = fget(fd);
if (file) {
if (file->f_mode & FMODE_WRITE) {
struct inode *inode = file->f_dentry->d_inode;
ret = locks_verify_area(FLOCK_VERIFY_WRITE, inode, file,
file->f_pos, count);
if (!ret) {
ssize_t (*write)(struct file *, const char *, size_t, loff_t *);
ret = -EINVAL;
if (file->f_op && (write = file->f_op->write) != NULL)
ret = write(file, buf, count, &file->f_pos);
}
}
if (ret > 0)
dnotify_parent(file->f_dentry, DN_MODIFY);
fput(file);
}
return ret;
}
/*
* Flush all pending data to disk. This operation will block.
*/
static int
alq_doio(struct alq *alq)
{
mm_segment_t oldfs;
struct iovec aiov[2];
struct file *fp;
struct ale *ale;
struct ale *alstart;
int totlen;
int iov;
int err;
fp = alq->aq_fp;
totlen = 0;
iov = 0;
alstart = ale = alq->aq_entvalid;
alq->aq_entvalid = NULL;
memset(&aiov, 0, sizeof(aiov));
do {
if (aiov[iov].iov_base == NULL)
aiov[iov].iov_base = ale->ae_data;
aiov[iov].iov_len += alq->aq_entlen;
totlen += alq->aq_entlen;
/* Check to see if we're wrapping the buffer */
if (ale->ae_data + alq->aq_entlen != ale->ae_next->ae_data)
iov++;
ale->ae_flags &= ~AE_VALID;
ale = ale->ae_next;
} while (ale->ae_flags & AE_VALID);
alq->aq_flags |= AQ_FLUSHING;
spin_unlock_irq(&alq->aq_lock);
if (iov == 2 || aiov[iov].iov_base == NULL)
iov--;
oldfs = get_fs(); set_fs(KERNEL_DS);
/* XXX ignore errors */
err = fp->f_op->writev(fp, aiov, iov + 1, &fp->f_pos);
set_fs(oldfs);
if (err >= 0)
dnotify_parent(fp->f_dentry, DN_MODIFY);
spin_lock_irq(&alq->aq_lock);
alq->aq_flags &= ~AQ_FLUSHING;
if (alq->aq_entfree == NULL)
alq->aq_entfree = alstart;
if (alq->aq_flags & AQ_WANTED) {
alq->aq_flags &= ~AQ_WANTED;
return (1);
}
return(0);
}
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
int error;
time_t now = CURRENT_TIME;
unsigned int ia_valid = attr->ia_valid;
if (!inode)
BUG();
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
lock_kernel();
if (inode->i_op && inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else {
error = inode_change_ok(inode, attr);
if (!error) {
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid))
error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
if (!error)
error = inode_setattr(inode, attr);
}
}
unlock_kernel();
if (!error) {
unsigned long dn_mask = setattr_mask(ia_valid);
if (dn_mask)
dnotify_parent(dentry, dn_mask);
}
return error;
}
asmlinkage ssize_t sys_read(unsigned int fd, char * buf, size_t count)
{
ssize_t ret;
struct file * file;
ret = -EBADF;
file = fget(fd);
if (file) {
if (file->f_mode & FMODE_READ) {
ret = locks_verify_area(FLOCK_VERIFY_READ, file->f_dentry->d_inode,
file, file->f_pos, count);
if (!ret) {
ssize_t (*read)(struct file *, char *, size_t, loff_t *);
ret = -EINVAL;
if (file->f_op && (read = file->f_op->read) != NULL)
ret = read(file, buf, count, &file->f_pos);
}
}
if (ret > 0)
dnotify_parent(file->f_dentry, DN_ACCESS);
fput(file);
}
return ret;
}
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec __user * uvector,
unsigned long nr_segs, loff_t *pos)
{
typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *);
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov=iovstack, *vector;
ssize_t ret;
int seg;
io_fn_t fn;
iov_fn_t fnv;
struct inode *inode;
/*
* SuS says "The readv() function *may* fail if the iovcnt argument
* was less than or equal to 0, or greater than {IOV_MAX}. Linux has
* traditionally returned zero for zero segments, so...
*/
ret = 0;
if (nr_segs == 0)
goto out;
/*
* First get the "struct iovec" from user memory and
* verify all the pointers
*/
ret = -EINVAL;
if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0))
goto out;
if (!file->f_op)
goto out;
if (nr_segs > UIO_FASTIOV) {
ret = -ENOMEM;
iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
if (!iov)
goto out;
}
ret = -EFAULT;
if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector)))
goto out;
/*
* Single unix specification:
* We should -EINVAL if an element length is not >= 0 and fitting an
* ssize_t. The total length is fitting an ssize_t
*
* Be careful here because iov_len is a size_t not an ssize_t
*/
tot_len = 0;
ret = -EINVAL;
for (seg = 0; seg < nr_segs; seg++) {
ssize_t len = (ssize_t)iov[seg].iov_len;
if (len < 0) /* size_t not fitting an ssize_t .. */
goto out;
tot_len += len;
if ((ssize_t)tot_len < 0) /* maths overflow on the ssize_t */
goto out;
}
if (tot_len == 0) {
ret = 0;
goto out;
}
inode = file->f_dentry->d_inode;
/* VERIFY_WRITE actually means a read, as we write to user space */
ret = locks_verify_area((type == READ
? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE),
inode, file, *pos, tot_len);
if (ret)
goto out;
fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
fnv = file->f_op->readv;
} else {
fn = (io_fn_t)file->f_op->write;
fnv = file->f_op->writev;
}
if (fnv) {
ret = fnv(file, iov, nr_segs, pos);
goto out;
}
/* Do it by hand, with file-ops */
ret = 0;
vector = iov;
while (nr_segs > 0) {
void __user * base;
size_t len;
ssize_t nr;
base = vector->iov_base;
len = vector->iov_len;
vector++;
nr_segs--;
nr = fn(file, base, len, pos);
if (nr < 0) {
if (!ret) ret = nr;
break;
}
ret += nr;
if (nr != len)
break;
}
out:
if (iov != iovstack)
kfree(iov);
if ((ret + (type == READ)) > 0)
dnotify_parent(file->f_dentry,
(type == READ) ? DN_ACCESS : DN_MODIFY);
return ret;
}
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec * vector,
unsigned long count)
{
typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *);
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov=iovstack;
ssize_t ret, i;
iov_fn_t fnv;
struct inode *inode;
/*
* First get the "struct iovec" from user memory and
* verify all the pointers
*/
ret = 0;
if (!count)
goto out_nofree;
ret = -EINVAL;
if (count > UIO_MAXIOV)
goto out_nofree;
if (!file->f_op)
goto out_nofree;
if (count > UIO_FASTIOV) {
ret = -ENOMEM;
iov = kmalloc(count*sizeof(struct iovec), GFP_KERNEL);
if (!iov)
goto out_nofree;
}
ret = -EFAULT;
if (copy_from_user(iov, vector, count*sizeof(*vector)))
goto out;
/*
* Single unix specification:
* We should -EINVAL if an element length is not >= 0 and fitting an ssize_t
* The total length is fitting an ssize_t
*
* Be careful here because iov_len is a size_t not an ssize_t
*/
tot_len = 0;
ret = -EINVAL;
for (i = 0 ; i < count ; i++) {
ssize_t len = (ssize_t) iov[i].iov_len;
if (len < 0) /* size_t not fitting an ssize_t .. */
goto out;
tot_len += len;
/* We must do this work unsigned - signed overflow is
undefined and gcc 3.2 now uses that fact sometimes...
FIXME: put in a proper limits.h for each platform */
#if BITS_PER_LONG==64
if (tot_len > 0x7FFFFFFFFFFFFFFFUL)
#else
if (tot_len > 0x7FFFFFFFUL)
#endif
goto out;
}
inode = file->f_dentry->d_inode;
/* VERIFY_WRITE actually means a read, as we write to user space */
ret = locks_verify_area((type == VERIFY_WRITE
? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE),
inode, file, file->f_pos, tot_len);
if (ret) goto out;
fnv = (type == VERIFY_WRITE ? file->f_op->readv : file->f_op->writev);
if (fnv) {
ret = fnv(file, iov, count, &file->f_pos);
goto out;
}
ret = fallback_readv_writev(type == VERIFY_WRITE ? READ : WRITE,
file, iov, count, &file->f_pos);
out:
if (iov != iovstack)
kfree(iov);
out_nofree:
/* VERIFY_WRITE actually means a read, as we write to user space */
if ((ret + (type == VERIFY_WRITE)) > 0)
dnotify_parent(file->f_dentry,
(type == VERIFY_WRITE) ? DN_ACCESS : DN_MODIFY);
return ret;
}
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
mode_t mode = inode->i_mode;
int error;
struct timespec now = CURRENT_TIME;
unsigned int ia_valid = attr->ia_valid;
if (!inode)
BUG();
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_SUID) {
attr->ia_valid &= ~ATTR_KILL_SUID;
if (mode & S_ISUID) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISUID;
}
}
if (ia_valid & ATTR_KILL_SGID) {
attr->ia_valid &= ~ ATTR_KILL_SGID;
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!attr->ia_valid)
return 0;
if (inode->i_op && inode->i_op->setattr) {
error = security_inode_setattr(dentry, attr);
if (!error)
error = inode->i_op->setattr(dentry, attr);
} else {
error = inode_change_ok(inode, attr);
if (!error)
error = security_inode_setattr(dentry, attr);
if (!error) {
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid))
error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
if (!error)
error = inode_setattr(inode, attr);
}
}
if (!error) {
#ifdef CONFIG_MOT_FEAT_INOTIFY
fsnotify_change(dentry, ia_valid);
#else
unsigned long dn_mask = setattr_mask(ia_valid);
if (dn_mask)
dnotify_parent(dentry, dn_mask);
#endif
}
return error;
}
