|
TOP
|
|
Linux 中直接 I/O 机制的介绍(三)
|
gt;> PAGE_CACHE_SHIFT;
int err = invalidate_inode_pages2_range(mapping,
offset >> PAGE_CACHE_SHIFT, end);
if (err)
retval = err;
}
}
return retval;
} |
函数 generic_file_direct_IO() 对 WRITE 操作类型进行了一些特殊处理，这在下边介绍 write() 系统调用的时候再做说明。除此之外，它主要是调用了 direct_IO 方法去执行直接 I/O 的读或者写操作。在进行直接 I/O 读操作之前，先将页缓存中的相关脏数据刷回到磁盘上去，这样做可以确保从磁盘上读到的是最新的数据。这里的 direct_IO 方法最终会对应到 __blockdev_direct_IO() 函数上去。__blockdev_direct_IO() 函数的代码如下所示：
清单 7. 函数 __blockdev_direct_IO()
|
ssize_t
__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
int dio_lock_type)
{
int seg;
size_t size;
unsigned long addr;
unsigned blkbits = inode->i_blkbits;
unsigned bdev_blkbits = 0;
unsigned blocksize_mask = (1 << blkbits) - 1;
ssize_t retval = -EINVAL;
loff_t end = offset;
struct dio *dio;
int release_i_mutex = 0;
int acquire_i_mutex = 0;
if (rw & WRITE)
rw = WRITE_SYNC;
if (bdev)
bdev_blkbits = blksize_bits(bdev_hardsect_size(bdev));
if (offset & blocksize_mask) {
if (bdev)
blkbits = bdev_blkbits;
blocksize_mask = (1 << blkbits) - 1;
if (offset & blocksize_mask)
goto out;
}
for (seg = 0; seg < nr_segs; seg++) {
addr = (unsigned long)iov[seg].iov_base;
size = iov[seg].iov_len;
end += size;
if ((addr & blocksize_mask) || (size & blocksize_mask)) {
if (bdev)
blkbits = bdev_blkbits;
blocksize_mask = (1 << blkbits) - 1;
if ((addr & blocksize_mask) || (size & blocksize_mask))
goto out;
}
}
dio = kmalloc(sizeof(*dio), GFP_KERNEL);
retval = -ENOMEM;
if (!dio)
goto out;
dio->lock_type = dio_lock_type;
if (dio_lock_type != DIO_NO_LOCKING) {
if (rw == READ && end > offset) {
struct address_space *mapping;
mapping = iocb->ki_filp->f_mapping;
if (dio_lock_type != DIO_OWN_LOCKING) {
mutex_lock(&inode->i_mutex);
release_i_mutex = 1;
}
retval = filemap_write_and_wait_range(mapping, offset,
end - 1);
if (retval) {
kfree(dio);
goto out;
}
if (dio_lock_type == DIO_OWN_LOCKING) {
mutex_unlock(&inode->i_mutex);
acquire_i_mutex = 1;
}
}
if (dio_lock_type == DIO_LOCKING)
down_read_non_owner(&inode->i_alloc_sem);
}
dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) &&
(end > i_size_read(inode)));
retval = direct_io_worker(rw, iocb, inode, iov, offset,
nr_segs, blkbits, get_block, end_io, dio);
if (rw == READ && dio_lock_type == DIO_LOCKING)
release_i_mutex = 0;
out:
if (release_i_mutex)
mutex_unlock(&inode->i_mutex);
else if (acquire_i_mutex)
mutex_lock(&inode->i_mutex);
return retval;
}
|
该函数将要读或者要写的数据进行拆分，并检查缓冲区对齐的情况。本文在前边介绍 open() 函数的时候指出，使用直接 I/O 读写数据的时候必须要注意缓冲区对齐的问题，从上边的代码可以看出，缓冲区对齐的检查是在 __blockdev_direct_IO() 函数里边进行的。用户地址空间的缓冲区可以通过 iov 数组中的 iovec 描述符确定。直接 I/O 的读操作或者写操作都是同步进行 |