/** * do_generic_file_read - generic file read routine * @filp: the file to read * @ppos: current file position * @desc: read_descriptor * @actor: read method * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. */ static void do_generic_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error; /*计算本次读取的是文件中的第几个page*/ index = *ppos >> PAGE_CACHE_SHIFT; /*上次读取的是第几个page*/ prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE - 1); /*要读取的最后一个page*/ last_index = (*ppos + desc->count + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: /*在radix树中查找相应的page*/ page = find_get_page(mapping, index); if (!page) { /*如果没有找到page,说明内存中没有将数据读入进来 先进行预读*/ page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); /*预读一般是可以找到page的,但是也有可能找不到*/ page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { /*发现找到的page已经是预读的情况了,再继续预读*/ /*这里预读就是一种经验的猜测*/ page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } /*page的内容还没有从磁盘上读出来*/ if (!PageUptodate(page)) { if (inode->i_blkbits == PAGE_CACHE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; if (!mapping->a_ops->is_partially_uptodate(page, desc, offset)) goto page_not_up_to_date_locked; unlock_page(page); } /*page的内容已经是最新的了,接下来准备拷贝到用户空间*/ page_ok: /* * i_size must be checked after we know the page is Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ /*下面这段代码是在page中的内容ok的情况下将page中的内容 拷贝到用户空间去,主要的逻辑分为检查参数是否合法 进性拷贝操作*/ /*合法性检查,是不是长度为0,或者超出文件范围*/ isize = i_size_read(inode); end_index = (isize - 1) >> PAGE_CACHE_SHIFT; if (unlikely(!isize || index > end_index)) { page_cache_release(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ /*合法性检查*/ nr = PAGE_CACHE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; if (nr <= offset) { page_cache_release(page); goto out; } } nr = nr - offset; /* If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... * * The actor routine returns how many bytes were actually used.. * NOTE! This may not be the same as how much of a user buffer * we filled up (we may be padding etc), so we can only update * "pos" here (the actor routine has to update the user buffer * pointers and the remaining count). */ /*实际的拷贝操作*/ ret = actor(desc, page, offset, nr); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; prev_offset = offset; page_cache_release(page); if (ret == nr && desc->count) continue; goto out; page_not_up_to_date: /* Get exclusive access to the page ... */ /*在读一个page之前首先要锁定这个page*/ error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ /*获取到锁之后,发现这个page没有被映射了,可能是在获取锁 之前就被其它模块释放掉了,重新开始获取lock*/ if (!page->mapping) { unlock_page(page); page_cache_release(page); continue; } /*获取到锁后发现page中的数据已经ok了,万事大吉,不需要再 读取数据*/ /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: /* Start the actual read. The read will unlock the page. */ /*实际的读取数据*/ error = mapping->a_ops->readpage(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { page_cache_release(page); goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { /*lock page等待数据返回,可能会休眠*/ error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_inode_pages got it */ unlock_page(page); page_cache_release(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(filp, ra); error = -EIO; goto readpage_error; } unlock_page(page); } /*读取数据成功,进行数据拷贝*/ goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ desc->error = error; page_cache_release(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ /*系统中没有数据,又不进行预读的情况,显示的分配page, 并读取page*/ page = page_cache_alloc_cold(mapping); if (!page) { desc->error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); if (error) { page_cache_release(page); if (error == -EEXIST) goto find_page; desc->error = error; goto out; } goto readpage; } out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_CACHE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; file_accessed(filp); } |