- 论坛徽章:
- 0
|
本帖最后由 blake326 于 2012-10-09 18:29 编辑
3.6 kernel
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
struct file *file;
ssize_t ret = -EBADF;
int fput_needed;
file = fget_light(fd, &fput_needed);
if (file) {
loff_t pos = file_pos_read(file);
ret = vfs_write(file, buf, count, &pos);
file_pos_write(file, pos);
fput_light(file, fput_needed);
}
return ret;
}
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))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret >= 0) {
count = 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);
add_wchar(current, ret);
}
inc_syscw(current);
}
return ret;
}
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;
kiocb.ki_nbytes = 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;
}
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);
sb_start_write(inode->i_sb);
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;
}
sb_end_write(inode->i_sb);
return ret;
}
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;
/* 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;
err = file_update_time(file);
if (err)
goto out;
/* 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 = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
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;
}
ssize_t
generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos, loff_t *ppos,
size_t count, ssize_t written)
{
struct file *file = iocb->ki_filp;
ssize_t status;
struct iov_iter i;
iov_iter_init(&i, iov, nr_segs, count, written);
status = generic_perform_write(file, &i, pos);
if (likely(status >= 0)) {
written += status;
*ppos = pos + status;
}
return written ? written : status;
}
****************************************************************************************
同sys_read一样，开始调用流程都很明了。
generic_perform_write的pos表示要写的文件内偏移，iov_iter->count保存要写的数据大小。根据这两个参数计算出write涉及到的所有page偏移，对每个page分别处理：
1. a_ops->write_begin，查找或者分配相应的page缓存，有必要为这个page的每个block分配buffer_head，有必要还要从等待从磁盘读取这些数据。基本上write_begin起了一个类似于读取磁盘的作用。
2. iov_iter_copy_from_user_atomic通过kmap_atomic临时内核映射page到一个内核地址，然后把用户buf数据拷贝这个地址中去，然后释放映射。pagefault disable/enable作用？？？
3. a_ops->write_end根据情况更新buffer_head，page的状态，并且调用mark_inode_dirty通知per-bdi内核线程进行回写。
****************************************************************************************
static ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
struct address_space *mapping = file->f_mapping;
const struct address_space_operations *a_ops = mapping->a_ops;
long status = 0;
ssize_t written = 0;
unsigned int flags = 0;
/*
* Copies from kernel address space cannot fail (NFSD is a big user).
*/
if (segment_eq(get_fs(), KERNEL_DS))
flags |= AOP_FLAG_UNINTERRUPTIBLE;
do {
struct page *page;
unsigned long offset; /* Offset into pagecache page */
unsigned long bytes; /* Bytes to write to page */
size_t copied; /* Bytes copied from user */
void *fsdata;
offset = (pos & (PAGE_CACHE_SIZE - 1));
bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
iov_iter_count(i));
again:
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
*
* Not only is this an optimisation, but it is also required
* to check that the address is actually valid, when atomic
* usercopies are used, below.
*/
if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
status = -EFAULT;
break;
}
status = a_ops->write_begin(file, mapping, pos, bytes, flags,
&page, &fsdata);
if (unlikely(status))
break;
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
pagefault_disable();
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
pagefault_enable();
flush_dcache_page(page);
mark_page_accessed(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
if (unlikely(status < 0))
break;
copied = status;
cond_resched();
iov_iter_advance(i, copied);
if (unlikely(copied == 0)) {
/*
* If we were unable to copy any data at all, we must
* fall back to a single segment length write.
*
* If we didn't fallback here, we could livelock
* because not all segments in the iov can be copied at
* once without a pagefault.
*/
bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
iov_iter_single_seg_count(i));
goto again;
}
pos += copied;
written += copied;
balance_dirty_pages_ratelimited(mapping);
if (fatal_signal_pending(current)) {
status = -EINTR;
break;
}
} while (iov_iter_count(i));
return written ? written : status;
}
****************************************************************************************
ext2_write_begin首先调用grab_cache_page_write_begin，查找page，没有则分配一个，但是如果page正在被写回（PG_writeback状态，写请求正在被提交但是没完成），则必须等待上一个写过程完成，要不然数据就乱大了。
然后有必要的话__block_write_begin为page的每个block分配buffer_head，然后对每个buffer_head分别进行处理：
1. 检查该写请求是否涉及到该block，没有设计的话则继续处理下一个block。
2. 如果该buffer_head还没有映射到磁盘，BH_Mapped没有设置，新分配的buffer_head都是没有影射的，所以这里又要使用ext2_get_block去读取这个映射关系了，同sys_read中的区别是，这里只读取一个块的映射关系。
3. 检查page如果已经uptodate，设置buffer_head uptodate。如果用户先sys_read,再sys_write的话这里page一般是uptodate的。
4. 反之假设用户直接sys_write的话，这里的page就不是uptodate的，通过ll_rw_block提交buffer_head读请求将磁盘数据读取出来。
所以block都处理完毕了，一种直接sys_write的情况就是，通过ll_rw_block发出了4个buffer_head读取请求，那么现在必须通过wait_on_buffer等待这些读取全部完成才能继续。
****************************************************************************************
static int ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
int ret;
ret = block_write_begin(mapping, pos, len, flags, pagep,
ext2_get_block);
if (ret < 0)
ext2_write_failed(mapping, pos + len);
return ret;
}
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
unsigned flags, struct page **pagep, get_block_t *get_block)
{
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct page *page;
int status;
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
status = __block_write_begin(page, pos, len, get_block);
if (unlikely(status)) {
unlock_page(page);
page_cache_release(page);
page = NULL;
}
*pagep = page;
return status;
}
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags)
{
int status;
gfp_t gfp_mask;
struct page *page;
gfp_t gfp_notmask = 0;
gfp_mask = mapping_gfp_mask(mapping);
if (mapping_cap_account_dirty(mapping))
gfp_mask |= __GFP_WRITE;
if (flags & AOP_FLAG_NOFS)
gfp_notmask = __GFP_FS;
repeat:
page = find_lock_page(mapping, index);
if (page)
goto found;
page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
if (!page)
return NULL;
status = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL & ~gfp_notmask);
if (unlikely(status)) {
page_cache_release(page);
if (status == -EEXIST)
goto repeat;
return NULL;
}
found:
wait_on_page_writeback(page);
return page;
}
int __block_write_begin(struct page *page, loff_t pos, unsigned len,
get_block_t *get_block)
{
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
unsigned to = from + len;
struct inode *inode = page->mapping->host;
unsigned block_start, block_end;
sector_t block;
int err = 0;
unsigned blocksize, bbits;
struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
BUG_ON(!PageLocked(page));
BUG_ON(from > PAGE_CACHE_SIZE);
BUG_ON(to > PAGE_CACHE_SIZE);
BUG_ON(from > to);
blocksize = 1 << inode->i_blkbits;
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
head = page_buffers(page);
bbits = inode->i_blkbits;
block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
for(bh = head, block_start = 0; bh != head || !block_start;
block++, block_start=block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (PageUptodate(page)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
}
continue;
}
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
break;
if (buffer_new(bh)) {
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
if (PageUptodate(page)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
continue;
}
if (block_end > to || block_start < from)
zero_user_segments(page,
to, block_end,
block_start, from);
continue;
}
}
if (PageUptodate(page)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
ll_rw_block(READ, 1, &bh);
*wait_bh++=bh;
}
}
/*
* If we issued read requests - let them complete.
*/
while(wait_bh > wait) {
wait_on_buffer(*--wait_bh);
if (!buffer_uptodate(*wait_bh))
err = -EIO;
}
if (unlikely(err))
page_zero_new_buffers(page, from, to);
return err;
}
|
评分
-
查看全部评分
|
免费注册
发表于 2012-10-09 18:26
发表于 2012-12-05 11:18
