filemap.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

		cli();
		if (!(total_reada > PROFILE_MAXREADCOUNT)) {
			restore_flags(flags);
			return;
		}

		printk("Readahead average:  max=%ld, len=%ld, win=%ld, async=%ld%%\n",
			total_ramax/total_reada,
			total_ralen/total_reada,
			total_rawin/total_reada,
			(total_async*100)/total_reada);
#ifdef DEBUG_READAHEAD
		printk("Readahead snapshot: max=%ld, len=%ld, win=%ld, raend=%Ld\n",
			filp->f_ramax, filp->f_ralen, filp->f_rawin, filp->f_raend);
#endif

		total_reada	= 0;
		total_async	= 0;
		total_ramax	= 0;
		total_ralen	= 0;
		total_rawin	= 0;

		restore_flags(flags);
	}
}
#endif  /* defined PROFILE_READAHEAD */

/*
 * Read-ahead context:
 * -------------------
 * The read ahead context fields of the "struct file" are the following:
 * - f_raend : position of the first byte after the last page we tried to
 *	       read ahead.
 * - f_ramax : current read-ahead maximum size.
 * - f_ralen : length of the current IO read block we tried to read-ahead.
 * - f_rawin : length of the current read-ahead window.
 *		if last read-ahead was synchronous then
 *			f_rawin = f_ralen
 *		otherwise (was asynchronous)
 *			f_rawin = previous value of f_ralen + f_ralen
 *
 * Read-ahead limits:
 * ------------------
 * MIN_READAHEAD   : minimum read-ahead size when read-ahead.
 * MAX_READAHEAD   : maximum read-ahead size when read-ahead.
 *
 * Synchronous read-ahead benefits:
 * --------------------------------
 * Using reasonable IO xfer length from peripheral devices increase system 
 * performances.
 * Reasonable means, in this context, not too large but not too small.
 * The actual maximum value is:
 *	MAX_READAHEAD + PAGE_CACHE_SIZE = 76k is CONFIG_READA_SMALL is undefined
 *      and 32K if defined (4K page size assumed).
 *
 * Asynchronous read-ahead benefits:
 * ---------------------------------
 * Overlapping next read request and user process execution increase system 
 * performance.
 *
 * Read-ahead risks:
 * -----------------
 * We have to guess which further data are needed by the user process.
 * If these data are often not really needed, it's bad for system 
 * performances.
 * However, we know that files are often accessed sequentially by 
 * application programs and it seems that it is possible to have some good 
 * strategy in that guessing.
 * We only try to read-ahead files that seems to be read sequentially.
 *
 * Asynchronous read-ahead risks:
 * ------------------------------
 * In order to maximize overlapping, we must start some asynchronous read 
 * request from the device, as soon as possible.
 * We must be very careful about:
 * - The number of effective pending IO read requests.
 *   ONE seems to be the only reasonable value.
 * - The total memory pool usage for the file access stream.
 *   This maximum memory usage is implicitly 2 IO read chunks:
 *   2*(MAX_READAHEAD + PAGE_CACHE_SIZE) = 156K if CONFIG_READA_SMALL is undefined,
 *   64k if defined (4K page size assumed).
 */

static inline int get_max_readahead(struct inode * inode)
{
	if (!inode->i_dev || !max_readahead[MAJOR(inode->i_dev)])
		return vm_max_readahead;
	return max_readahead[MAJOR(inode->i_dev)][MINOR(inode->i_dev)];
}

static void generic_file_readahead(int reada_ok,
	struct file * filp, struct inode * inode,
	struct page * page)
{
	unsigned long end_index;
	unsigned long index = page->index;
	unsigned long max_ahead, ahead;
	unsigned long raend;
	int max_readahead = get_max_readahead(inode);

	end_index = inode->i_size >> PAGE_CACHE_SHIFT;

	raend = filp->f_raend;
	max_ahead = 0;

/*
 * The current page is locked.
 * If the current position is inside the previous read IO request, do not
 * try to reread previously read ahead pages.
 * Otherwise decide or not to read ahead some pages synchronously.
 * If we are not going to read ahead, set the read ahead context for this 
 * page only.
 */
	if (PageLocked(page)) {
		if (!filp->f_ralen || index >= raend || index + filp->f_rawin < raend) {
			raend = index;
			if (raend < end_index)
				max_ahead = filp->f_ramax;
			filp->f_rawin = 0;
			filp->f_ralen = 1;
			if (!max_ahead) {
				filp->f_raend  = index + filp->f_ralen;
				filp->f_rawin += filp->f_ralen;
			}
		}
	}
/*
 * The current page is not locked.
 * If we were reading ahead and,
 * if the current max read ahead size is not zero and,
 * if the current position is inside the last read-ahead IO request,
 *   it is the moment to try to read ahead asynchronously.
 * We will later force unplug device in order to force asynchronous read IO.
 */
	else if (reada_ok && filp->f_ramax && raend >= 1 &&
		 index <= raend && index + filp->f_ralen >= raend) {
/*
 * Add ONE page to max_ahead in order to try to have about the same IO max size
 * as synchronous read-ahead (MAX_READAHEAD + 1)*PAGE_CACHE_SIZE.
 * Compute the position of the last page we have tried to read in order to 
 * begin to read ahead just at the next page.
 */
		raend -= 1;
		if (raend < end_index)
			max_ahead = filp->f_ramax + 1;

		if (max_ahead) {
			filp->f_rawin = filp->f_ralen;
			filp->f_ralen = 0;
			reada_ok      = 2;
		}
	}
/*
 * Try to read ahead pages.
 * We hope that ll_rw_blk() plug/unplug, coalescence, requests sort and the
 * scheduler, will work enough for us to avoid too bad actuals IO requests.
 */
	ahead = 0;
	while (ahead < max_ahead) {
		ahead ++;
		if ((raend + ahead) >= end_index)
			break;
		if (page_cache_read(filp, raend + ahead) < 0)
			break;
	}
/*
 * If we tried to read ahead some pages,
 * If we tried to read ahead asynchronously,
 *   Try to force unplug of the device in order to start an asynchronous
 *   read IO request.
 * Update the read-ahead context.
 * Store the length of the current read-ahead window.
 * Double the current max read ahead size.
 *   That heuristic avoid to do some large IO for files that are not really
 *   accessed sequentially.
 */
	if (ahead) {
		filp->f_ralen += ahead;
		filp->f_rawin += filp->f_ralen;
		filp->f_raend = raend + ahead + 1;

		filp->f_ramax += filp->f_ramax;

		if (filp->f_ramax > max_readahead)
			filp->f_ramax = max_readahead;

#ifdef PROFILE_READAHEAD
		profile_readahead((reada_ok == 2), filp);
#endif
	}

	return;
}

/*
 * Mark a page as having seen activity.
 *
 * If it was already so marked, move it
 * to the active queue and drop the referenced
 * bit. Otherwise, just mark it for future
 * action..
 */
void mark_page_accessed(struct page *page)
{
	if (!PageActive(page) && PageReferenced(page)) {
		activate_page(page);
		ClearPageReferenced(page);
		return;
	}

	/* Mark the page referenced, AFTER checking for previous usage.. */
	SetPageReferenced(page);
}

/*
 * This is a generic file read routine, and uses the
 * inode->i_op->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.
 */
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_dentry->d_inode->i_mapping;
	struct inode *inode = mapping->host;
	unsigned long index, offset;
	struct page *cached_page;
	int reada_ok;
	int error;
	int max_readahead = get_max_readahead(inode);

	cached_page = NULL;
	index = *ppos >> PAGE_CACHE_SHIFT;
	offset = *ppos & ~PAGE_CACHE_MASK;

/*
 * If the current position is outside the previous read-ahead window, 
 * we reset the current read-ahead context and set read ahead max to zero
 * (will be set to just needed value later),
 * otherwise, we assume that the file accesses are sequential enough to
 * continue read-ahead.
 */
	if (index > filp->f_raend || index + filp->f_rawin < filp->f_raend) {
		reada_ok = 0;
		filp->f_raend = 0;
		filp->f_ralen = 0;
		filp->f_ramax = 0;
		filp->f_rawin = 0;
	} else {
		reada_ok = 1;
	}
/*
 * Adjust the current value of read-ahead max.
 * If the read operation stay in the first half page, force no readahead.
 * Otherwise try to increase read ahead max just enough to do the read request.
 * Then, at least MIN_READAHEAD if read ahead is ok,
 * and at most MAX_READAHEAD in all cases.
 */
	if (!index && offset + desc->count <= (PAGE_CACHE_SIZE >> 1)) {
		filp->f_ramax = 0;
	} else {
		unsigned long needed;

		needed = ((offset + desc->count) >> PAGE_CACHE_SHIFT) + 1;

		if (filp->f_ramax < needed)
			filp->f_ramax = needed;

		if (reada_ok && filp->f_ramax < vm_min_readahead)
				filp->f_ramax = vm_min_readahead;
		if (filp->f_ramax > max_readahead)
			filp->f_ramax = max_readahead;
	}

	for (;;) {
		struct page *page, **hash;
		unsigned long end_index, nr, ret;

		end_index = inode->i_size >> PAGE_CACHE_SHIFT;
			
		if (index > end_index)
			break;
		nr = PAGE_CACHE_SIZE;
		if (index == end_index) {
			nr = inode->i_size & ~PAGE_CACHE_MASK;
			if (nr <= offset)
				break;
		}

		nr = nr - offset;

		/*
		 * Try to find the data in the page cache..
		 */
		hash = page_hash(mapping, index);

		spin_lock(&pagecache_lock);
		page = __find_page_nolock(mapping, index, *hash);
		if (!page)
			goto no_cached_page;
found_page:
		page_cache_get(page);
		spin_unlock(&pagecache_lock);

		if (!Page_Uptodate(page))
			goto page_not_up_to_date;
		generic_file_readahead(reada_ok, filp, inode, page);
page_ok:
		/* 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->i_mmap_shared != NULL)
			flush_dcache_page(page);

		/*
		 * Mark the page accessed if we read the
		 * beginning or we just did an lseek.
		 */
		if (!offset || !filp->f_reada)
			mark_page_accessed(page);

		/*
		 * 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).
		 */
		ret = actor(desc, page, offset, nr);
		offset += ret;
		index += offset >> PAGE_CACHE_SHIFT;
		offset &= ~PAGE_CACHE_MASK;

		page_cache_release(page);
		if (ret == nr && desc->count)
			continue;
		break;

/*
 * Ok, the page was not immediately readable, so let's try to read ahead while we're at it..
 */
page_not_up_to_date:
		generic_file_readahead(reada_ok, filp, inode, page);

		if (Page_Uptodate(page))
			goto page_ok;

		/* Get exclusive access to the page ... */
		lock_page(page);

		/* Did it get unhashed before we got the lock? */
		if (!page->mapping) {
			UnlockPage(page);
			page_cache_release(page);
			continue;
		}

		/* Did somebody else fill it already? */
		if (Page_Uptodate(page)) {
			UnlockPage(page);
			goto page_ok;
		}

readpage:
		/* ... and start the actual read. The read will unlock the page. */
		error = mapping->a_ops->readpage(filp, page);

		if (!error) {
			if (Page_Uptodate(page))
				goto page_ok;

			/* Again, try some read-ahead while waiting for the page to finish.. */
			generic_file_readahead(reada_ok, filp, inode, page);
			wait_on_page(page);
			if (Page_Uptodate(page))
				goto page_ok;
			error = -EIO;
		}

		/* UHHUH! A synchronous read error occurred. Report it */
		desc->error = error;
		page_cache_release(page);
		break;

no_cached_page:
		/*
		 * Ok, it wasn't cached, so we need to create a new
		 * page..
		 *
		 * We get here with the page cache lock held.
		 */
		if (!cached_page) {
			spin_unlock(&pagecache_lock);
			cached_page = page_cache_alloc(mapping);
			if (!cached_page) {
				desc->error = -ENOMEM;
				break;
			}

			/*
			 * Somebody may have added the page while we
			 * dropped the page cache lock. Check for that.
			 */
			spin_lock(&pagecache_lock);
			page = __find_page_nolock(mapping, index, *hash);
			if (page)
				goto found_page;
		}

		/*
		 * Ok, add the new page to the hash-queues...
		 */
		page = cached_page;
		__add_to_page_cache(page, mapping, index, hash);
		spin_unlock(&pagecache_lock);
		lru_cache_add(page);		
		cached_page = NULL;

		goto readpage;
	}

	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
	filp->f_reada = 1;
	if (cached_page)
		page_cache_release(cached_page);
	UPDATE_ATIME(inode);
}

static ssize_t generic_file_direct_IO(int rw, struct file * filp, char * buf, size_t count, loff_t offset)
{
	ssize_t retval;
	int new_iobuf, chunk_size, blocksize_mask, blocksize, blocksize_bits, iosize, progress;
	struct kiobuf * iobuf;
	struct address_space * mapping = filp->f_dentry->d_inode->i_mapping;
	struct inode * inode = mapping->host;

	new_iobuf = 0;
	iobuf = filp->f_iobuf;
	if (test_and_set_bit(0, &filp->f_iobuf_lock)) {
		/*
		 * A parallel read/write is using the preallocated iobuf
		 * so just run slow and allocate a new one.
		 */
		retval = alloc_kiovec(1, &iobuf);
		if (retval)
			goto out;
		new_iobuf = 1;
	}

	blocksize = 1 << inode->i_blkbits;
	blocksize_bits = inode->i_blkbits;
	blocksize_mask = blocksize - 1;
	chunk_size = KIO_MAX_ATOMIC_IO << 10;

	retval = -EINVAL;
	if ((offset & blocksize_mask) || (count & blocksize_mask))
		goto out_free;
	if (!mapping->a_ops->direct_IO)
		goto out_free;

	/*
	 * Flush to disk exclusively the _data_, metadata must remain
	 * completly asynchronous or performance will go to /dev/null.
	 */
	retval = filemap_fdatasync(mapping);
	if (retval == 0)
		retval = fsync_inode_data_buffers(inode);
	if (retval == 0)
		retval = filemap_fdatawait(mapping);
	if (retval < 0)
		goto out_free;

	progress = retval = 0;
	while (count > 0) {
		iosize = count;
		if (iosize > chunk_size)
			iosize = chunk_size;

		retval = map_user_kiobuf(rw, iobuf, (unsigned long) buf, iosize);
		if (retval)
			break;

		retval = mapping->a_ops->direct_IO(rw, inode, iobuf, (offset+progress) >> blocksize_bits, blocksize);

		if (rw == READ && retval > 0)
			mark_dirty_kiobuf(iobuf, retval);
		
		if (retval >= 0) {
			count -= retval;
			buf += retval;
			progress += retval;
		}

		unmap_kiobuf(iobuf);

		if (retval != iosize)
			break;
	}

	if (progress)
		retval = progress;

 out_free:
	if (!new_iobuf)
		clear_bit(0, &filp->f_iobuf_lock);
	else
		free_kiovec(1, &iobuf);
 out:	
	return retval;
}