#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
+#include <linux/splice.h>
#include "read_write.h"
#include <asm/uaccess.h>
.read = do_sync_read,
.aio_read = generic_file_aio_read,
.mmap = generic_file_readonly_mmap,
- .sendfile = generic_file_sendfile,
+ .splice_read = generic_file_splice_read,
};
EXPORT_SYMBOL(generic_ro_fops);
-loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
+/**
+ * generic_file_llseek_unlocked - lockless generic llseek implementation
+ * @file: file structure to seek on
+ * @offset: file offset to seek to
+ * @origin: type of seek
+ *
+ * Updates the file offset to the value specified by @offset and @origin.
+ * Locking must be provided by the caller.
+ */
+loff_t
+generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
{
- long long retval;
struct inode *inode = file->f_mapping->host;
- mutex_lock(&inode->i_mutex);
switch (origin) {
- case 2:
- offset += inode->i_size;
- break;
- case 1:
- offset += file->f_pos;
- }
- retval = -EINVAL;
- if (offset>=0 && offset<=inode->i_sb->s_maxbytes) {
- if (offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
- retval = offset;
+ case SEEK_END:
+ offset += inode->i_size;
+ break;
+ case SEEK_CUR:
+ /*
+ * Here we special-case the lseek(fd, 0, SEEK_CUR)
+ * position-querying operation. Avoid rewriting the "same"
+ * f_pos value back to the file because a concurrent read(),
+ * write() or lseek() might have altered it
+ */
+ if (offset == 0)
+ return file->f_pos;
+ offset += file->f_pos;
+ break;
+ }
+
+ if (offset < 0 || offset > inode->i_sb->s_maxbytes)
+ return -EINVAL;
+
+ /* Special lock needed here? */
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
}
- mutex_unlock(&inode->i_mutex);
- return retval;
-}
-EXPORT_SYMBOL(generic_file_llseek);
+ return offset;
+}
+EXPORT_SYMBOL(generic_file_llseek_unlocked);
-loff_t remote_llseek(struct file *file, loff_t offset, int origin)
+/**
+ * generic_file_llseek - generic llseek implementation for regular files
+ * @file: file structure to seek on
+ * @offset: file offset to seek to
+ * @origin: type of seek
+ *
+ * This is a generic implemenation of ->llseek useable for all normal local
+ * filesystems. It just updates the file offset to the value specified by
+ * @offset and @origin under i_mutex.
+ */
+loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
{
- long long retval;
+ loff_t rval;
- lock_kernel();
- switch (origin) {
- case 2:
- offset += i_size_read(file->f_path.dentry->d_inode);
- break;
- case 1:
- offset += file->f_pos;
- }
- retval = -EINVAL;
- if (offset>=0 && offset<=file->f_path.dentry->d_inode->i_sb->s_maxbytes) {
- if (offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
- retval = offset;
- }
- unlock_kernel();
- return retval;
+ mutex_lock(&file->f_dentry->d_inode->i_mutex);
+ rval = generic_file_llseek_unlocked(file, offset, origin);
+ mutex_unlock(&file->f_dentry->d_inode->i_mutex);
+
+ return rval;
}
-EXPORT_SYMBOL(remote_llseek);
+EXPORT_SYMBOL(generic_file_llseek);
loff_t no_llseek(struct file *file, loff_t offset, int origin)
{
loff_t default_llseek(struct file *file, loff_t offset, int origin)
{
- long long retval;
+ loff_t retval;
lock_kernel();
switch (origin) {
- case 2:
+ case SEEK_END:
offset += i_size_read(file->f_path.dentry->d_inode);
break;
- case 1:
+ case SEEK_CUR:
+ if (offset == 0) {
+ retval = file->f_pos;
+ goto out;
+ }
offset += file->f_pos;
}
retval = -EINVAL;
}
retval = offset;
}
+out:
unlock_kernel();
return retval;
}
}
EXPORT_SYMBOL(vfs_llseek);
-asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, unsigned int origin)
+SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
{
off_t retval;
struct file * file;
goto bad;
retval = -EINVAL;
- if (origin <= 2) {
+ if (origin <= SEEK_MAX) {
loff_t res = vfs_llseek(file, offset, origin);
retval = res;
if (res != (loff_t)retval)
}
#ifdef __ARCH_WANT_SYS_LLSEEK
-asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
- unsigned long offset_low, loff_t __user * result,
- unsigned int origin)
+SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
+ unsigned long, offset_low, loff_t __user *, result,
+ unsigned int, origin)
{
int retval;
struct file * file;
goto bad;
retval = -EINVAL;
- if (origin > 2)
+ if (origin > SEEK_MAX)
goto out_putf;
offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
{
struct inode *inode;
loff_t pos;
+ int retval = -EINVAL;
+ inode = file->f_path.dentry->d_inode;
if (unlikely((ssize_t) count < 0))
- goto Einval;
+ return retval;
pos = *ppos;
if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
- goto Einval;
+ return retval;
- inode = file->f_path.dentry->d_inode;
- if (unlikely(inode->i_flock && MANDATORY_LOCK(inode))) {
- int retval = locks_mandatory_area(
+ if (unlikely(inode->i_flock && mandatory_lock(inode))) {
+ retval = locks_mandatory_area(
read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
inode, file, pos, count);
if (retval < 0)
return retval;
}
+ retval = security_file_permission(file,
+ read_write == READ ? MAY_READ : MAY_WRITE);
+ if (retval)
+ return retval;
return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
-
-Einval:
- return -EINVAL;
}
static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
ret = rw_verify_area(READ, file, pos, count);
if (ret >= 0) {
count = 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) {
- fsnotify_access(file->f_path.dentry);
- add_rchar(current, ret);
- }
- inc_syscr(current);
+ 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) {
+ fsnotify_access(file->f_path.dentry);
+ add_rchar(current, ret);
}
+ inc_syscr(current);
}
return ret;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret >= 0) {
count = 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) {
- fsnotify_modify(file->f_path.dentry);
- add_wchar(current, ret);
- }
- inc_syscw(current);
+ 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) {
+ fsnotify_modify(file->f_path.dentry);
+ add_wchar(current, ret);
}
+ inc_syscw(current);
}
return ret;
file->f_pos = pos;
}
-asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count)
+SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
struct file *file;
ssize_t ret = -EBADF;
return ret;
}
-EXPORT_SYMBOL_GPL(sys_read);
-asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t count)
+SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
+ size_t, count)
{
struct file *file;
ssize_t ret = -EBADF;
return ret;
}
-asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
- size_t count, loff_t pos)
+SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf,
+ size_t count, loff_t pos)
{
struct file *file;
ssize_t ret = -EBADF;
return ret;
}
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos)
+{
+ return SYSC_pread64((unsigned int) fd, (char __user *) buf,
+ (size_t) count, pos);
+}
+SYSCALL_ALIAS(sys_pread64, SyS_pread64);
+#endif
-asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf,
- size_t count, loff_t pos)
+SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf,
+ size_t count, loff_t pos)
{
struct file *file;
ssize_t ret = -EBADF;
return ret;
}
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos)
+{
+ return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf,
+ (size_t) count, pos);
+}
+SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64);
+#endif
/*
* Reduce an iovec's length in-place. Return the resulting number of segments
}
return seg;
}
+EXPORT_SYMBOL(iov_shorten);
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)
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
- ret = security_file_permission(file, type == READ ? MAY_READ : MAY_WRITE);
- if (ret)
- goto out;
fnv = NULL;
if (type == READ) {
EXPORT_SYMBOL(vfs_writev);
-asmlinkage ssize_t
-sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
+SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen)
{
struct file *file;
ssize_t ret = -EBADF;
return ret;
}
-asmlinkage ssize_t
-sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
+SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen)
{
struct file *file;
ssize_t ret = -EBADF;
return ret;
}
+static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
+{
+#define HALF_LONG_BITS (BITS_PER_LONG / 2)
+ return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+ struct file *file;
+ ssize_t ret = -EBADF;
+ int fput_needed;
+
+ if (pos < 0)
+ return -EINVAL;
+
+ file = fget_light(fd, &fput_needed);
+ if (file) {
+ ret = -ESPIPE;
+ if (file->f_mode & FMODE_PREAD)
+ ret = vfs_readv(file, vec, vlen, &pos);
+ fput_light(file, fput_needed);
+ }
+
+ if (ret > 0)
+ add_rchar(current, ret);
+ inc_syscr(current);
+ return ret;
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+ struct file *file;
+ ssize_t ret = -EBADF;
+ int fput_needed;
+
+ if (pos < 0)
+ return -EINVAL;
+
+ file = fget_light(fd, &fput_needed);
+ if (file) {
+ ret = -ESPIPE;
+ if (file->f_mode & FMODE_PWRITE)
+ ret = vfs_writev(file, vec, vlen, &pos);
+ fput_light(file, fput_needed);
+ }
+
+ if (ret > 0)
+ add_wchar(current, ret);
+ inc_syscw(current);
+ return ret;
+}
+
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
struct inode * in_inode, * out_inode;
loff_t pos;
ssize_t retval;
- int fput_needed_in, fput_needed_out;
+ int fput_needed_in, fput_needed_out, fl;
/*
* Get input file, and verify that it is ok..
goto out;
if (!(in_file->f_mode & FMODE_READ))
goto fput_in;
- retval = -EINVAL;
- in_inode = in_file->f_path.dentry->d_inode;
- if (!in_inode)
- goto fput_in;
- if (!in_file->f_op || !in_file->f_op->sendfile)
- goto fput_in;
retval = -ESPIPE;
if (!ppos)
ppos = &in_file->f_pos;
goto fput_in;
count = retval;
- retval = security_file_permission (in_file, MAY_READ);
- if (retval)
- goto fput_in;
-
/*
* Get output file, and verify that it is ok..
*/
if (!(out_file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
- if (!out_file->f_op || !out_file->f_op->sendpage)
- goto fput_out;
+ in_inode = in_file->f_path.dentry->d_inode;
out_inode = out_file->f_path.dentry->d_inode;
retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
if (retval < 0)
goto fput_out;
count = retval;
- retval = security_file_permission (out_file, MAY_WRITE);
- if (retval)
- goto fput_out;
-
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
pos = *ppos;
- retval = -EINVAL;
- if (unlikely(pos < 0))
- goto fput_out;
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
count = max - pos;
}
- retval = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file);
+ fl = 0;
+#if 0
+ /*
+ * We need to debate whether we can enable this or not. The
+ * man page documents EAGAIN return for the output at least,
+ * and the application is arguably buggy if it doesn't expect
+ * EAGAIN on a non-blocking file descriptor.
+ */
+ if (in_file->f_flags & O_NONBLOCK)
+ fl = SPLICE_F_NONBLOCK;
+#endif
+ retval = do_splice_direct(in_file, ppos, out_file, count, fl);
if (retval > 0) {
add_rchar(current, retval);
return retval;
}
-asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, size_t count)
+SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count)
{
loff_t pos;
off_t off;
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
-asmlinkage ssize_t sys_sendfile64(int out_fd, int in_fd, loff_t __user *offset, size_t count)
+SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count)
{
loff_t pos;
ssize_t ret;