与read相同
直接从以下代码看：
函数：do_sync_write
ssize_t do_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;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
kiocb.ki_left = len;
for (;;) {
ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
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;
}
函数:nfs_file_write
static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct dentry * dentry = iocb->ki_filp->f_path.dentry;
struct inode * inode = dentry->d_inode;
ssize_t result;
size_t count = iov_length(iov, nr_segs);
if (iocb->ki_filp->f_flags & O_DIRECT)
return nfs_file_direct_write(iocb, iov, nr_segs, pos);
dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
(unsigned long) count, (long long) pos);
result = -EBUSY;
if (IS_SWAPFILE(inode))
goto out_swapfile;
/*
* O_APPEND implies that we must revalidate the file length.
*/
if (iocb->ki_filp->f_flags & O_APPEND) {
//文件追加选项处理
result = nfs_revalidate_file_size(inode, iocb->ki_filp);
if (result)
goto out;
}
result = count;
if (!count)
goto out;
nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
/核心函数
result = generic_file_aio_write(iocb, iov, nr_segs, pos);
/* Return error values for O_SYNC and IS_SYNC() */
if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
int err = nfs_do_fsync(nfs_file_open_context(iocb->ki_filp), inode);
if (err < 0)
result = err;
}
out:
return result;
out_swapfile:
printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
goto out;
}
函数：generic_file_aio_write
/**
* generic_file_aio_write - write data to a file
* @iocb: IO state structure
* @iov: vector with data to write
* @nr_segs: number of segments in the vector
* @pos: position in file where to write
*
* This is a wrapper around __generic_file_aio_write() to be used by most
* filesystems. It takes care of syncing the file in case of O_SYNC file
* and acquires i_mutex as needed.
*/
ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
if (ret > 0 || ret == -EIOCBQUEUED) {
ssize_t err;
err = generic_write_sync(file, pos, ret);
if (err < 0 && ret > 0)
ret = err;
}
return ret;
函数：直接写要落盘会掉adr_space->do_writepages方法落盘，
这里如果没注册回调默认addr_space.backing_dev_info.congested_fn()方法，这里也就是各个设备的drive的方法了。
一般写则调用generic_perform_write，
/**
* __generic_file_aio_write - write data to a file
* @iocb: IO state structure (file, offset, etc.)
* @iov: vector with data to write
* @nr_segs: number of segments in the vector
* @ppos: position where to write
*
* This function does all the work needed for actually writing data to a
* file. It does all basic checks, removes SUID from the file, updates
* modification times and calls proper subroutines depending on whether we
* do direct IO or a standard buffered write.
*
* It expects i_mutex to be grabbed unless we work on a block device or similar
* object which does not need locking at all.
*
* This function does *not* take care of syncing data in case of O_SYNC write.
* A caller has to handle it. This is mainly due to the fact that we want to
* avoid syncing under i_mutex.
*/
ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
loff_t pos;
ssize_t written;
ssize_t err;
ocount = 0;
err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
if (err)
return err;
count = ocount;
pos = *ppos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
written = 0;
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
if (count == 0)
goto out;
err = file_remove_suid(file);
if (err)
goto out;
file_update_time(file);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
loff_t endbyte;
ssize_t written_buffered;
written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
ppos, count, ocount);
if (written < 0 || written == count)
goto out;
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
pos += written;
count -= written;
written_buffered = generic_file_buffered_write(iocb, iov,
nr_segs, pos, ppos, count,
written);
/*
* If generic_file_buffered_write() retuned a synchronous error
* then we want to return the number of bytes which were
* direct-written, or the error code if that was zero. Note
* that this differs from normal direct-io semantics, which
* will return -EFOO even if some bytes were written.
*/
if (written_buffered < 0) {
err = written_buffered;
goto out;
}
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
endbyte = pos + written_buffered - written - 1;
err = do_sync_mapping_range(file->f_mapping, pos, endbyte,
SYNC_FILE_RANGE_WAIT_BEFORE|
SYNC_FILE_RANGE_WRITE|
SYNC_FILE_RANGE_WAIT_AFTER);
if (err == 0) {
written = written_buffered;
invalidate_mapping_pages(mapping,
pos >> PAGE_CACHE_SHIFT,
endbyte >> PAGE_CACHE_SHIFT);
} else {
/*
* We don't know how much we wrote, so just return
* the number of bytes which were direct-written
*/
}
} else {
written = generic_file_buffered_write(iocb, iov, nr_segs,
pos, ppos, count, written);
}
out:
current->backing_dev_info = NULL;
return written ? written : err;
}