展示自己、证明自己
分类： C/C++
2014-07-07 10:46:44
用户程序想要访问IO设备需要调用操作系统提供的接口,即系统调用.当在用户程序中调用一个read操作时,系统先保存好read操作的参数,然后调用 int 80命令(也可能是sysenter)进入内核空间,在内核空间中,读操作的逻辑由sys_read函数实现.
在讲sys_read的实现过程之前,我们先来看看read操作在内核空间需要经历的层次结构.从图中可以看出,read操作首先经过虚拟文件系统曾
(vfs), 接下来是具体的文件系统层,Page cache层,通用块层(generic block layer),I/O调度层(I/O
scheduler layer),块设备驱动层(block device driver layer),最后是块物理设备层(block
device layer).
asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count);
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_read(f.file, buf, count, &pos); //调用vfs layer中的read操作
file_pos_write(f.file, pos);//设置当前文件的位置
fdput(f);
}
return ret;
}
ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
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;
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); //该函数由具体的文件系统指定
} else
ret = do_sync_read(file, buf, count, pos); //内核默认的读文件操作
if (ret > 0) {
fsnotify_access(file);
add_rchar(current, ret);
}
inc_syscr(current);
}
return ret;
}
const struct file_operations ext4_file_operations = {
.llseek = ext4_llseek,
.read = do_sync_read,
.write = do_sync_write,
.aio_read = generic_file_aio_read,
.aio_write = ext4_file_write,
.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
#endif
.mmap = ext4_file_mmap,
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
.fallocate = ext4_fallocate,
};
ssize_t do_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;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);//初始化kiocp,描述符kiocb是用来记录I/O操作的完成状态
kiocb.ki_pos = *ppos;
kiocb.ki_left = len;
kiocb.ki_nbytes = len;
for (;;) {
ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);//调用真正做读操作的函数,ext4文件系统在fs/ext4/file.c中配置
if (ret != -EIOCBRETRY)
break;
wait_on_retry_sync_kiocb(&kiocb);
}
if (-EIOCBQUEUED == ret)
ret = wait_on_sync_kiocb(&kiocb);
*ppos = kiocb.ki_pos;
return ret;
}
ssize_t
generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
ssize_t retval;
unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
count = 0;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
loff_t size;
struct address_space *mapping;
struct inode *inode;
struct timex txc;
do_gettimeofday(&(txc.time));
mapping = filp->f_mapping;
inode = mapping->host;
if (!count)
goto out; /* skip atime */
size = i_size_read(inode);
if (pos < size) {
retval = filemap_write_and_wait_range(mapping, pos,
pos + iov_length(iov, nr_segs) - 1);
if (!retval) {
retval = mapping->a_ops->direct_IO(READ, iocb,
iov, pos, nr_segs);
}
if (retval > 0) {
*ppos = pos + retval;
count -= retval;
}
/*
* Btrfs can have a short DIO read if we encounter
* compressed extents, so if there was an error, or if
* we've already read everything we wanted to, or if
* there was a short read because we hit EOF, go ahead
* and return. Otherwise fallthrough to buffered io for
* the rest of the read.
*/
if (retval < 0 || !count || *ppos >= size) {
file_accessed(filp);
goto out;
}
}
}
count = retval;
for (seg = 0; seg < nr_segs; seg++) {
read_descriptor_t desc;
loff_t offset = 0;
/*
* If we did a short DIO read we need to skip the section of the
* iov that we've already read data into.
*/
if (count) {
if (count > iov[seg].iov_len) {
count -= iov[seg].iov_len;
continue;
}
offset = count;
count = 0;
}
desc.written = 0;
desc.arg.buf = iov[seg].iov_base + offset;
desc.count = iov[seg].iov_len - offset;
if (desc.count == 0)
continue;
desc.error = 0;
do_generic_file_read(filp, ppos, &desc, file_read_actor);
retval += desc.written;
if (desc.error) {
retval = retval ?: desc.error;
break;
}
if (desc.count > 0)
break;
}
out:
return retval;
}
static const struct address_space_operations ext4_ordered_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.write_begin = ext4_write_begin,
.write_end = ext4_ordered_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
int mpage_readpage(struct page *page, get_block_t get_block)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
map_bh.b_state = 0;
map_bh.b_size = 0;
bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
&map_bh, &first_logical_block, get_block);
if (bio)
mpage_bio_submit(READ, bio);
return 0;
}