/*
 * fs/logfs/dev_bdev.c	- Device access methods for block devices
 *
 * As should be obvious for Linux kernel code, license is GPLv2
 *
 * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
 */
#include "logfs.h"
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/prefetch.h>

#define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))

static int sync_request(struct page *page, struct block_device *bdev, int op)
{
	struct bio bio;
	struct bio_vec bio_vec;

	bio_init(&bio, &bio_vec, 1);
	bio.bi_bdev = bdev;
	bio_add_page(&bio, page, PAGE_SIZE, 0);
	bio.bi_iter.bi_sector = page->index * (PAGE_SIZE >> 9);
	bio_set_op_attrs(&bio, op, 0);

	return submit_bio_wait(&bio);
}

static int bdev_readpage(void *_sb, struct page *page)
{
	struct super_block *sb = _sb;
	struct block_device *bdev = logfs_super(sb)->s_bdev;
	int err;

	err = sync_request(page, bdev, READ);
	if (err) {
		ClearPageUptodate(page);
		SetPageError(page);
	} else {
		SetPageUptodate(page);
		ClearPageError(page);
	}
	unlock_page(page);
	return err;
}

static DECLARE_WAIT_QUEUE_HEAD(wq);

static void writeseg_end_io(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;
	struct super_block *sb = bio->bi_private;
	struct logfs_super *super = logfs_super(sb);

	BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */

	bio_for_each_segment_all(bvec, bio, i) {
		end_page_writeback(bvec->bv_page);
		put_page(bvec->bv_page);
	}
	bio_put(bio);
	if (atomic_dec_and_test(&super->s_pending_writes))
		wake_up(&wq);
}

static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
		size_t nr_pages)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	struct bio *bio = NULL;
	struct page *page;
	unsigned int max_pages;
	int i, ret;

	max_pages = min_t(size_t, nr_pages, BIO_MAX_PAGES);

	for (i = 0; i < nr_pages; i++) {
		if (!bio) {
			bio = bio_alloc(GFP_NOFS, max_pages);
			BUG_ON(!bio);

			bio->bi_bdev = super->s_bdev;
			bio->bi_iter.bi_sector = ofs >> 9;
			bio->bi_private = sb;
			bio->bi_end_io = writeseg_end_io;
			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
		}
		page = find_lock_page(mapping, index + i);
		BUG_ON(!page);
		ret = bio_add_page(bio, page, PAGE_SIZE, 0);

		BUG_ON(PageWriteback(page));
		set_page_writeback(page);
		unlock_page(page);

		if (!ret) {
			/* Block layer cannot split bios :( */
			ofs += bio->bi_iter.bi_size;
			atomic_inc(&super->s_pending_writes);
			submit_bio(bio);
			bio = NULL;
		}
	}

	if (bio) {
		atomic_inc(&super->s_pending_writes);
		submit_bio(bio);
	}
	return 0;
}

static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len)
{
	struct logfs_super *super = logfs_super(sb);
	int head;

	BUG_ON(super->s_flags & LOGFS_SB_FLAG_RO);

	if (len == 0) {
		/* This can happen when the object fit perfectly into a
		 * segment, the segment gets written per sync and subsequently
		 * closed.
		 */
		return;
	}
	head = ofs & (PAGE_SIZE - 1);
	if (head) {
		ofs -= head;
		len += head;
	}
	len = PAGE_ALIGN(len);
	__bdev_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT);
}


static void erase_end_io(struct bio *bio)
{ 
	struct super_block *sb = bio->bi_private; 
	struct logfs_super *super = logfs_super(sb); 

	BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */ 
	bio_put(bio); 
	if (atomic_dec_and_test(&super->s_pending_writes))
		wake_up(&wq); 
} 

static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
		size_t nr_pages)
{
	struct logfs_super *super = logfs_super(sb);
	struct bio *bio = NULL;
	unsigned int max_pages;
	int i, ret;

	max_pages = min_t(size_t, nr_pages, BIO_MAX_PAGES);

	for (i = 0; i < nr_pages; i++) {
		if (!bio) {
			bio = bio_alloc(GFP_NOFS, max_pages);
			BUG_ON(!bio);

			bio->bi_bdev = super->s_bdev;
			bio->bi_iter.bi_sector = ofs >> 9;
			bio->bi_private = sb;
			bio->bi_end_io = erase_end_io;
			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
		}
		ret = bio_add_page(bio, super->s_erase_page, PAGE_SIZE, 0);
		if (!ret) {
			/* Block layer cannot split bios :( */
			ofs += bio->bi_iter.bi_size;
			atomic_inc(&super->s_pending_writes);
			submit_bio(bio);
		}
	}
	if (bio) {
		atomic_inc(&super->s_pending_writes);
		submit_bio(bio);
	}
	return 0;
}

static int bdev_erase(struct super_block *sb, loff_t to, size_t len,
		int ensure_write)
{
	struct logfs_super *super = logfs_super(sb);

	BUG_ON(to & (PAGE_SIZE - 1));
	BUG_ON(len & (PAGE_SIZE - 1));

	if (super->s_flags & LOGFS_SB_FLAG_RO)
		return -EROFS;

	if (ensure_write) {
		/*
		 * Object store doesn't care whether erases happen or not.
		 * But for the journal they are required.  Otherwise a scan
		 * can find an old commit entry and assume it is the current
		 * one, travelling back in time.
		 */
		do_erase(sb, to, to >> PAGE_SHIFT, len >> PAGE_SHIFT);
	}

	return 0;
}

static void bdev_sync(struct super_block *sb)
{
	struct logfs_super *super = logfs_super(sb);

	wait_event(wq, atomic_read(&super->s_pending_writes) == 0);
}

static struct page *bdev_find_first_sb(struct super_block *sb, u64 *ofs)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	filler_t *filler = bdev_readpage;

	*ofs = 0;
	return read_cache_page(mapping, 0, filler, sb);
}

static struct page *bdev_find_last_sb(struct super_block *sb, u64 *ofs)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	filler_t *filler = bdev_readpage;
	u64 pos = (super->s_bdev->bd_inode->i_size & ~0xfffULL) - 0x1000;
	pgoff_t index = pos >> PAGE_SHIFT;

	*ofs = pos;
	return read_cache_page(mapping, index, filler, sb);
}

static int bdev_write_sb(struct super_block *sb, struct page *page)
{
	struct block_device *bdev = logfs_super(sb)->s_bdev;

	/* Nothing special to do for block devices. */
	return sync_request(page, bdev, WRITE);
}

static void bdev_put_device(struct logfs_super *s)
{
	blkdev_put(s->s_bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}

static int bdev_can_write_buf(struct super_block *sb, u64 ofs)
{
	return 0;
}

static const struct logfs_device_ops bd_devops = {
	.find_first_sb	= bdev_find_first_sb,
	.find_last_sb	= bdev_find_last_sb,
	.write_sb	= bdev_write_sb,
	.readpage	= bdev_readpage,
	.writeseg	= bdev_writeseg,
	.erase		= bdev_erase,
	.can_write_buf	= bdev_can_write_buf,
	.sync		= bdev_sync,
	.put_device	= bdev_put_device,
};

int logfs_get_sb_bdev(struct logfs_super *p, struct file_system_type *type,
		const char *devname)
{
	struct block_device *bdev;

	bdev = blkdev_get_by_path(devname, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
				  type);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);

	if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
		int mtdnr = MINOR(bdev->bd_dev);
		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
		return logfs_get_sb_mtd(p, mtdnr);
	}

	p->s_bdev = bdev;
	p->s_mtd = NULL;
	p->s_devops = &bd_devops;
	return 0;
}