#include <linux/fcntl.h>
#include <linux/file.h>
#include <linux/uio.h>
-#include <linux/aio.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/export.h>
#include <asm/unistd.h>
typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
-typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *,
- unsigned long, loff_t);
+typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *);
const struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
- .read = do_sync_read,
- .aio_read = generic_file_aio_read,
+ .read_iter = generic_file_read_iter,
.mmap = generic_file_readonly_mmap,
.splice_read = generic_file_splice_read,
};
return file->f_mode & FMODE_UNSIGNED_OFFSET;
}
-static loff_t lseek_execute(struct file *file, struct inode *inode,
- loff_t offset, loff_t maxsize)
+/**
+ * vfs_setpos - update the file offset for lseek
+ * @file: file structure in question
+ * @offset: file offset to seek to
+ * @maxsize: maximum file size
+ *
+ * This is a low-level filesystem helper for updating the file offset to
+ * the value specified by @offset if the given offset is valid and it is
+ * not equal to the current file offset.
+ *
+ * Return the specified offset on success and -EINVAL on invalid offset.
+ */
+loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
{
if (offset < 0 && !unsigned_offsets(file))
return -EINVAL;
}
return offset;
}
+EXPORT_SYMBOL(vfs_setpos);
/**
* generic_file_llseek_size - generic llseek implementation for regular files
generic_file_llseek_size(struct file *file, loff_t offset, int whence,
loff_t maxsize, loff_t eof)
{
- struct inode *inode = file->f_mapping->host;
-
switch (whence) {
case SEEK_END:
offset += eof;
* like SEEK_SET.
*/
spin_lock(&file->f_lock);
- offset = lseek_execute(file, inode, file->f_pos + offset,
- maxsize);
+ offset = vfs_setpos(file, file->f_pos + offset, maxsize);
spin_unlock(&file->f_lock);
return offset;
case SEEK_DATA:
break;
}
- return lseek_execute(file, inode, offset, maxsize);
+ return vfs_setpos(file, offset, maxsize);
}
EXPORT_SYMBOL(generic_file_llseek_size);
}
EXPORT_SYMBOL(generic_file_llseek);
+/**
+ * fixed_size_llseek - llseek implementation for fixed-sized devices
+ * @file: file structure to seek on
+ * @offset: file offset to seek to
+ * @whence: type of seek
+ * @size: size of the file
+ *
+ */
+loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size)
+{
+ switch (whence) {
+ case SEEK_SET: case SEEK_CUR: case SEEK_END:
+ return generic_file_llseek_size(file, offset, whence,
+ size, size);
+ default:
+ return -EINVAL;
+ }
+}
+EXPORT_SYMBOL(fixed_size_llseek);
+
/**
* noop_llseek - No Operation Performed llseek implementation
* @file: file structure to seek on
fn = no_llseek;
if (file->f_mode & FMODE_LSEEK) {
- if (file->f_op && file->f_op->llseek)
+ if (file->f_op->llseek)
fn = file->f_op->llseek;
}
return fn(file, offset, whence);
}
EXPORT_SYMBOL(vfs_llseek);
+static inline struct fd fdget_pos(int fd)
+{
+ return __to_fd(__fdget_pos(fd));
+}
+
+static inline void fdput_pos(struct fd f)
+{
+ if (f.flags & FDPUT_POS_UNLOCK)
+ mutex_unlock(&f.file->f_pos_lock);
+ fdput(f);
+}
+
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
if (!f.file)
return -EBADF;
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
- fdput(f);
+ fdput_pos(f);
return retval;
}
unsigned int, whence)
{
int retval;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
loff_t offset;
if (!f.file)
retval = 0;
}
out_putf:
- fdput(f);
+ fdput_pos(f);
return retval;
}
#endif
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
+{
+ struct kiocb kiocb;
+ ssize_t ret;
+
+ if (!file->f_op->read_iter)
+ return -EINVAL;
+
+ init_sync_kiocb(&kiocb, file);
+ kiocb.ki_pos = *ppos;
+
+ iter->type |= READ;
+ ret = file->f_op->read_iter(&kiocb, iter);
+ BUG_ON(ret == -EIOCBQUEUED);
+ if (ret > 0)
+ *ppos = kiocb.ki_pos;
+ return ret;
+}
+EXPORT_SYMBOL(vfs_iter_read);
+
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
+{
+ struct kiocb kiocb;
+ ssize_t ret;
+
+ if (!file->f_op->write_iter)
+ return -EINVAL;
+
+ init_sync_kiocb(&kiocb, file);
+ kiocb.ki_pos = *ppos;
+
+ iter->type |= WRITE;
+ ret = file->f_op->write_iter(&kiocb, iter);
+ BUG_ON(ret == -EIOCBQUEUED);
+ if (ret > 0)
+ *ppos = kiocb.ki_pos;
+ return ret;
+}
+EXPORT_SYMBOL(vfs_iter_write);
+
/*
* rw_verify_area doesn't like huge counts. We limit
* them to something that fits in "int" so that others
* won't have to do range checks all the time.
*/
-int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
+int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
{
struct inode *inode;
loff_t pos;
return retval;
}
- if (unlikely(inode->i_flock && mandatory_lock(inode))) {
+ if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
retval = locks_mandatory_area(
read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
inode, file, pos, count);
return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
}
-ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
+static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = buf, .iov_len = len };
struct kiocb kiocb;
+ struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- kiocb.ki_left = len;
- kiocb.ki_nbytes = len;
+ iov_iter_init(&iter, READ, &iov, 1, len);
- ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&kiocb);
+ ret = filp->f_op->read_iter(&kiocb, &iter);
+ BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
-EXPORT_SYMBOL(do_sync_read);
+ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
+ loff_t *pos)
+{
+ if (file->f_op->read)
+ return file->f_op->read(file, buf, count, pos);
+ else if (file->f_op->read_iter)
+ return new_sync_read(file, buf, count, pos);
+ else
+ return -EINVAL;
+}
+EXPORT_SYMBOL(__vfs_read);
ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
if (!(file->f_mode & FMODE_READ))
return -EBADF;
- if (!file->f_op || (!file->f_op->read && !file->f_op->aio_read))
+ if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
return -EFAULT;
ret = rw_verify_area(READ, file, pos, count);
if (ret >= 0) {
count = ret;
- if (file->f_op->read)
- ret = file->f_op->read(file, buf, count, pos);
- else
- ret = do_sync_read(file, buf, count, pos);
+ ret = __vfs_read(file, buf, count, pos);
if (ret > 0) {
fsnotify_access(file);
add_rchar(current, ret);
EXPORT_SYMBOL(vfs_read);
-ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
+static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
struct kiocb kiocb;
+ struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- kiocb.ki_left = len;
- kiocb.ki_nbytes = len;
+ iov_iter_init(&iter, WRITE, &iov, 1, len);
- ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&kiocb);
- *ppos = kiocb.ki_pos;
+ ret = filp->f_op->write_iter(&kiocb, &iter);
+ BUG_ON(ret == -EIOCBQUEUED);
+ if (ret > 0)
+ *ppos = kiocb.ki_pos;
return ret;
}
-EXPORT_SYMBOL(do_sync_write);
+ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
+ loff_t *pos)
+{
+ if (file->f_op->write)
+ return file->f_op->write(file, p, count, pos);
+ else if (file->f_op->write_iter)
+ return new_sync_write(file, p, count, pos);
+ else
+ return -EINVAL;
+}
+EXPORT_SYMBOL(__vfs_write);
ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
{
const char __user *p;
ssize_t ret;
- if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
+ if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
old_fs = get_fs();
p = (__force const char __user *)buf;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
- if (file->f_op->write)
- ret = file->f_op->write(file, p, count, pos);
- else
- ret = do_sync_write(file, p, count, pos);
+ ret = __vfs_write(file, p, count, pos);
set_fs(old_fs);
if (ret > 0) {
fsnotify_modify(file);
return ret;
}
+EXPORT_SYMBOL(__kernel_write);
+
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
- if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
+ if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
if (ret >= 0) {
count = ret;
file_start_write(file);
- if (file->f_op->write)
- ret = file->f_op->write(file, buf, count, pos);
- else
- ret = do_sync_write(file, buf, count, pos);
+ ret = __vfs_write(file, buf, count, pos);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_read(f.file, buf, count, &pos);
- file_pos_write(f.file, pos);
- fdput(f);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput_pos(f);
}
return ret;
}
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_write(f.file, buf, count, &pos);
- file_pos_write(f.file, pos);
- fdput(f);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput_pos(f);
}
return ret;
}
EXPORT_SYMBOL(iov_shorten);
-static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
- unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
+static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
+ loff_t *ppos, iter_fn_t fn)
{
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
- kiocb.ki_left = len;
- kiocb.ki_nbytes = len;
- ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
- if (ret == -EIOCBQUEUED)
- ret = wait_on_sync_kiocb(&kiocb);
+ ret = fn(&kiocb, iter);
+ BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
/* Do it by hand, with file-ops */
-static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos, io_fn_t fn)
+static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
+ loff_t *ppos, io_fn_t fn)
{
- struct iovec *vector = iov;
ssize_t ret = 0;
- while (nr_segs > 0) {
- void __user *base;
- size_t len;
+ while (iov_iter_count(iter)) {
+ struct iovec iovec = iov_iter_iovec(iter);
ssize_t nr;
- base = vector->iov_base;
- len = vector->iov_len;
- vector++;
- nr_segs--;
-
- nr = fn(filp, base, len, ppos);
+ nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
if (nr < 0) {
if (!ret)
break;
}
ret += nr;
- if (nr != len)
+ if (nr != iovec.iov_len)
break;
+ iov_iter_advance(iter, nr);
}
return ret;
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
+ struct iov_iter iter;
ssize_t ret;
io_fn_t fn;
- iov_fn_t fnv;
+ iter_fn_t iter_fn;
- if (!file->f_op) {
- ret = -EINVAL;
- goto out;
- }
+ ret = import_iovec(type, uvector, nr_segs,
+ ARRAY_SIZE(iovstack), &iov, &iter);
+ if (ret < 0)
+ return ret;
- ret = rw_copy_check_uvector(type, uvector, nr_segs,
- ARRAY_SIZE(iovstack), iovstack, &iov);
- if (ret <= 0)
+ tot_len = iov_iter_count(&iter);
+ if (!tot_len)
goto out;
-
- tot_len = ret;
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
- fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
- fnv = file->f_op->aio_read;
+ iter_fn = file->f_op->read_iter;
} else {
fn = (io_fn_t)file->f_op->write;
- fnv = file->f_op->aio_write;
+ iter_fn = file->f_op->write_iter;
file_start_write(file);
}
- if (fnv)
- ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
- pos, fnv);
+ if (iter_fn)
+ ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
else
- ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
+ ret = do_loop_readv_writev(file, &iter, pos, fn);
if (type != READ)
file_end_write(file);
out:
- if (iov != iovstack)
- kfree(iov);
+ kfree(iov);
if ((ret + (type == READ)) > 0) {
if (type == READ)
fsnotify_access(file);
{
if (!(file->f_mode & FMODE_READ))
return -EBADF;
- if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
+ if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
return do_readv_writev(READ, file, vec, vlen, pos);
{
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
- if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
+ if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
return do_readv_writev(WRITE, file, vec, vlen, pos);
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_readv(f.file, vec, vlen, &pos);
- file_pos_write(f.file, pos);
- fdput(f);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput_pos(f);
}
if (ret > 0)
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_writev(f.file, vec, vlen, &pos);
- file_pos_write(f.file, pos);
- fdput(f);
+ if (ret >= 0)
+ file_pos_write(f.file, pos);
+ fdput_pos(f);
}
if (ret > 0)
compat_ssize_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
+ struct iov_iter iter;
ssize_t ret;
io_fn_t fn;
- iov_fn_t fnv;
+ iter_fn_t iter_fn;
- ret = -EINVAL;
- if (!file->f_op)
- goto out;
-
- ret = -EFAULT;
- if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
- goto out;
+ ret = compat_import_iovec(type, uvector, nr_segs,
+ UIO_FASTIOV, &iov, &iter);
+ if (ret < 0)
+ return ret;
- ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
- UIO_FASTIOV, iovstack, &iov);
- if (ret <= 0)
+ tot_len = iov_iter_count(&iter);
+ if (!tot_len)
goto out;
-
- tot_len = ret;
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
- fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
- fnv = file->f_op->aio_read;
+ iter_fn = file->f_op->read_iter;
} else {
fn = (io_fn_t)file->f_op->write;
- fnv = file->f_op->aio_write;
+ iter_fn = file->f_op->write_iter;
file_start_write(file);
}
- if (fnv)
- ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
- pos, fnv);
+ if (iter_fn)
+ ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
else
- ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
+ ret = do_loop_readv_writev(file, &iter, pos, fn);
if (type != READ)
file_end_write(file);
out:
- if (iov != iovstack)
- kfree(iov);
+ kfree(iov);
if ((ret + (type == READ)) > 0) {
if (type == READ)
fsnotify_access(file);
goto out;
ret = -EINVAL;
- if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
+ if (!(file->f_mode & FMODE_CAN_READ))
goto out;
ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
return -EBADF;
pos = f.file->f_pos;
ret = compat_readv(f.file, vec, vlen, &pos);
- f.file->f_pos = pos;
- fdput(f);
+ if (ret >= 0)
+ f.file->f_pos = pos;
+ fdput_pos(f);
return ret;
}
-COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
- const struct compat_iovec __user *,vec,
- unsigned long, vlen, loff_t, pos)
+static long __compat_sys_preadv64(unsigned long fd,
+ const struct compat_iovec __user *vec,
+ unsigned long vlen, loff_t pos)
{
struct fd f;
ssize_t ret;
return ret;
}
+#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
+COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen, loff_t, pos)
+{
+ return __compat_sys_preadv64(fd, vec, vlen, pos);
+}
+#endif
+
COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
- return compat_sys_preadv64(fd, vec, vlen, pos);
+
+ return __compat_sys_preadv64(fd, vec, vlen, pos);
}
static size_t compat_writev(struct file *file,
goto out;
ret = -EINVAL;
- if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
+ if (!(file->f_mode & FMODE_CAN_WRITE))
goto out;
ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
const struct compat_iovec __user *, vec,
compat_ulong_t, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
return -EBADF;
pos = f.file->f_pos;
ret = compat_writev(f.file, vec, vlen, &pos);
- f.file->f_pos = pos;
- fdput(f);
+ if (ret >= 0)
+ f.file->f_pos = pos;
+ fdput_pos(f);
return ret;
}
-COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
- const struct compat_iovec __user *,vec,
- unsigned long, vlen, loff_t, pos)
+static long __compat_sys_pwritev64(unsigned long fd,
+ const struct compat_iovec __user *vec,
+ unsigned long vlen, loff_t pos)
{
struct fd f;
ssize_t ret;
return ret;
}
+#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
+COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
+ const struct compat_iovec __user *,vec,
+ unsigned long, vlen, loff_t, pos)
+{
+ return __compat_sys_pwritev64(fd, vec, vlen, pos);
+}
+#endif
+
COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
- return compat_sys_pwritev64(fd, vec, vlen, pos);
+
+ return __compat_sys_pwritev64(fd, vec, vlen, pos);
}
#endif
if (in.file->f_flags & O_NONBLOCK)
fl = SPLICE_F_NONBLOCK;
#endif
+ file_start_write(out.file);
retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
+ file_end_write(out.file);
if (retval > 0) {
add_rchar(current, retval);