eba.c

基于linux-2.6.28的mtd驱动

	vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi));
	ubi_msg("try another PEB");
	goto retry;
}

/*
 * ubi_eba_atomic_leb_change - change logical eraseblock atomically.
 * @ubi: UBI device description object
 * @vol: volume description object
 * @lnum: logical eraseblock number
 * @buf: data to write
 * @len: how many bytes to write
 * @dtype: data type
 *
 * This function changes the contents of a logical eraseblock atomically. @buf
 * has to contain new logical eraseblock data, and @len - the length of the
 * data, which has to be aligned. This function guarantees that in case of an
 * unclean reboot the old contents is preserved. Returns zero in case of
 * success and a negative error code in case of failure.
 *
 * UBI reserves one LEB for the "atomic LEB change" operation, so only one
 * LEB change may be done at a time. This is ensured by @ubi->alc_mutex.
 */
int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
			      int lnum, const void *buf, int len, int dtype)
{
	int err, pnum, tries = 0, vol_id = vol->vol_id;
	struct ubi_vid_hdr *vid_hdr;
	uint32_t crc;

	if (ubi->ro_mode)
		return -EROFS;

	if (len == 0) {
		/*
		 * Special case when data length is zero. In this case the LEB
		 * has to be unmapped and mapped somewhere else.
		 */
		err = ubi_eba_unmap_leb(ubi, vol, lnum);
		if (err)
			return err;
		return ubi_eba_write_leb(ubi, vol, lnum, NULL, 0, 0, dtype);
	}

	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
	if (!vid_hdr)
		return -ENOMEM;

	mutex_lock(&ubi->alc_mutex);
	err = leb_write_lock(ubi, vol_id, lnum);
	if (err)
		goto out_mutex;

	vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi));
	vid_hdr->vol_id = cpu_to_be32(vol_id);
	vid_hdr->lnum = cpu_to_be32(lnum);
	vid_hdr->compat = ubi_get_compat(ubi, vol_id);
	vid_hdr->data_pad = cpu_to_be32(vol->data_pad);

	crc = crc32(UBI_CRC32_INIT, buf, len);
	vid_hdr->vol_type = UBI_VID_DYNAMIC;
	vid_hdr->data_size = cpu_to_be32(len);
	vid_hdr->copy_flag = 1;
	vid_hdr->data_crc = cpu_to_be32(crc);

retry:
	pnum = ubi_wl_get_peb(ubi, dtype);
	if (pnum < 0) {
		err = pnum;
		goto out_leb_unlock;
	}

	dbg_eba("change LEB %d:%d, PEB %d, write VID hdr to PEB %d",
		vol_id, lnum, vol->eba_tbl[lnum], pnum);

	err = ubi_io_write_vid_hdr(ubi, pnum, vid_hdr);
	if (err) {
		ubi_warn("failed to write VID header to LEB %d:%d, PEB %d",
			 vol_id, lnum, pnum);
		goto write_error;
	}

	err = ubi_io_write_data(ubi, buf, pnum, 0, len);
	if (err) {
		ubi_warn("failed to write %d bytes of data to PEB %d",
			 len, pnum);
		goto write_error;
	}

	if (vol->eba_tbl[lnum] >= 0) {
		err = ubi_wl_put_peb(ubi, vol->eba_tbl[lnum], 0);
		if (err)
			goto out_leb_unlock;
	}

	vol->eba_tbl[lnum] = pnum;

out_leb_unlock:
	leb_write_unlock(ubi, vol_id, lnum);
out_mutex:
	mutex_unlock(&ubi->alc_mutex);
	ubi_free_vid_hdr(ubi, vid_hdr);
	return err;

write_error:
	if (err != -EIO || !ubi->bad_allowed) {
		/*
		 * This flash device does not admit of bad eraseblocks or
		 * something nasty and unexpected happened. Switch to read-only
		 * mode just in case.
		 */
		ubi_ro_mode(ubi);
		goto out_leb_unlock;
	}

	err = ubi_wl_put_peb(ubi, pnum, 1);
	if (err || ++tries > UBI_IO_RETRIES) {
		ubi_ro_mode(ubi);
		goto out_leb_unlock;
	}

	vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi));
	ubi_msg("try another PEB");
	goto retry;
}

/**
 * ubi_eba_copy_leb - copy logical eraseblock.
 * @ubi: UBI device description object
 * @from: physical eraseblock number from where to copy
 * @to: physical eraseblock number where to copy
 * @vid_hdr: VID header of the @from physical eraseblock
 *
 * This function copies logical eraseblock from physical eraseblock @from to
 * physical eraseblock @to. The @vid_hdr buffer may be changed by this
 * function. Returns:
 *   o %0  in case of success;
 *   o %1 if the operation was canceled and should be tried later (e.g.,
 *     because a bit-flip was detected at the target PEB);
 *   o %2 if the volume is being deleted and this LEB should not be moved.
 */
int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
		     struct ubi_vid_hdr *vid_hdr)
{
	int err, vol_id, lnum, data_size, aldata_size, idx;
	struct ubi_volume *vol;
	uint32_t crc;

	vol_id = be32_to_cpu(vid_hdr->vol_id);
	lnum = be32_to_cpu(vid_hdr->lnum);

	dbg_eba("copy LEB %d:%d, PEB %d to PEB %d", vol_id, lnum, from, to);

	if (vid_hdr->vol_type == UBI_VID_STATIC) {
		data_size = be32_to_cpu(vid_hdr->data_size);
		aldata_size = ALIGN(data_size, ubi->min_io_size);
	} else
		data_size = aldata_size =
			    ubi->leb_size - be32_to_cpu(vid_hdr->data_pad);

	idx = vol_id2idx(ubi, vol_id);
	spin_lock(&ubi->volumes_lock);
	/*
	 * Note, we may race with volume deletion, which means that the volume
	 * this logical eraseblock belongs to might be being deleted. Since the
	 * volume deletion unmaps all the volume's logical eraseblocks, it will
	 * be locked in 'ubi_wl_put_peb()' and wait for the WL worker to finish.
	 */
	vol = ubi->volumes[idx];
	if (!vol) {
		/* No need to do further work, cancel */
		dbg_eba("volume %d is being removed, cancel", vol_id);
		spin_unlock(&ubi->volumes_lock);
		return 2;
	}
	spin_unlock(&ubi->volumes_lock);

	/*
	 * We do not want anybody to write to this logical eraseblock while we
	 * are moving it, so lock it.
	 *
	 * Note, we are using non-waiting locking here, because we cannot sleep
	 * on the LEB, since it may cause deadlocks. Indeed, imagine a task is
	 * unmapping the LEB which is mapped to the PEB we are going to move
	 * (@from). This task locks the LEB and goes sleep in the
	 * 'ubi_wl_put_peb()' function on the @ubi->move_mutex. In turn, we are
	 * holding @ubi->move_mutex and go sleep on the LEB lock. So, if the
	 * LEB is already locked, we just do not move it and return %1.
	 */
	err = leb_write_trylock(ubi, vol_id, lnum);
	if (err) {
		dbg_eba("contention on LEB %d:%d, cancel", vol_id, lnum);
		return err;
	}

	/*
	 * The LEB might have been put meanwhile, and the task which put it is
	 * probably waiting on @ubi->move_mutex. No need to continue the work,
	 * cancel it.
	 */
	if (vol->eba_tbl[lnum] != from) {
		dbg_eba("LEB %d:%d is no longer mapped to PEB %d, mapped to "
			"PEB %d, cancel", vol_id, lnum, from,
			vol->eba_tbl[lnum]);
		err = 1;
		goto out_unlock_leb;
	}

	/*
	 * OK, now the LEB is locked and we can safely start moving it. Since
	 * this function utilizes thie @ubi->peb1_buf buffer which is shared
	 * with some other functions, so lock the buffer by taking the
	 * @ubi->buf_mutex.
	 */
	mutex_lock(&ubi->buf_mutex);
	dbg_eba("read %d bytes of data", aldata_size);
	err = ubi_io_read_data(ubi, ubi->peb_buf1, from, 0, aldata_size);
	if (err && err != UBI_IO_BITFLIPS) {
		ubi_warn("error %d while reading data from PEB %d",
			 err, from);
		goto out_unlock_buf;
	}

	/*
	 * Now we have got to calculate how much data we have to to copy. In
	 * case of a static volume it is fairly easy - the VID header contains
	 * the data size. In case of a dynamic volume it is more difficult - we
	 * have to read the contents, cut 0xFF bytes from the end and copy only
	 * the first part. We must do this to avoid writing 0xFF bytes as it
	 * may have some side-effects. And not only this. It is important not
	 * to include those 0xFFs to CRC because later the they may be filled
	 * by data.
	 */
	if (vid_hdr->vol_type == UBI_VID_DYNAMIC)
		aldata_size = data_size =
			ubi_calc_data_len(ubi, ubi->peb_buf1, data_size);

	cond_resched();
	crc = crc32(UBI_CRC32_INIT, ubi->peb_buf1, data_size);
	cond_resched();

	/*
	 * It may turn out to me that the whole @from physical eraseblock
	 * contains only 0xFF bytes. Then we have to only write the VID header
	 * and do not write any data. This also means we should not set
	 * @vid_hdr->copy_flag, @vid_hdr->data_size, and @vid_hdr->data_crc.
	 */
	if (data_size > 0) {
		vid_hdr->copy_flag = 1;
		vid_hdr->data_size = cpu_to_be32(data_size);
		vid_hdr->data_crc = cpu_to_be32(crc);
	}
	vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi));

	err = ubi_io_write_vid_hdr(ubi, to, vid_hdr);
	if (err)
		goto out_unlock_buf;

	cond_resched();

	/* Read the VID header back and check if it was written correctly */
	err = ubi_io_read_vid_hdr(ubi, to, vid_hdr, 1);
	if (err) {
		if (err != UBI_IO_BITFLIPS)
			ubi_warn("cannot read VID header back from PEB %d", to);
		else
			err = 1;
		goto out_unlock_buf;
	}

	if (data_size > 0) {
		err = ubi_io_write_data(ubi, ubi->peb_buf1, to, 0, aldata_size);
		if (err)
			goto out_unlock_buf;

		cond_resched();

		/*
		 * We've written the data and are going to read it back to make
		 * sure it was written correctly.
		 */

		err = ubi_io_read_data(ubi, ubi->peb_buf2, to, 0, aldata_size);
		if (err) {
			if (err != UBI_IO_BITFLIPS)
				ubi_warn("cannot read data back from PEB %d",
					 to);
			else
				err = 1;
			goto out_unlock_buf;
		}

		cond_resched();

		if (memcmp(ubi->peb_buf1, ubi->peb_buf2, aldata_size)) {
			ubi_warn("read data back from PEB %d - it is different",
				 to);
			goto out_unlock_buf;
		}
	}

	ubi_assert(vol->eba_tbl[lnum] == from);
	vol->eba_tbl[lnum] = to;

out_unlock_buf:
	mutex_unlock(&ubi->buf_mutex);
out_unlock_leb:
	leb_write_unlock(ubi, vol_id, lnum);
	return err;
}

/**
 * ubi_eba_init_scan - initialize the EBA sub-system using scanning information.
 * @ubi: UBI device description object
 * @si: scanning information
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
int ubi_eba_init_scan(struct ubi_device *ubi, struct ubi_scan_info *si)
{
	int i, j, err, num_volumes;
	struct ubi_scan_volume *sv;
	struct ubi_volume *vol;
	struct ubi_scan_leb *seb;
	struct rb_node *rb;

	dbg_eba("initialize EBA sub-system");

	spin_lock_init(&ubi->ltree_lock);
	mutex_init(&ubi->alc_mutex);
	ubi->ltree = RB_ROOT;

	ubi->global_sqnum = si->max_sqnum + 1;
	num_volumes = ubi->vtbl_slots + UBI_INT_VOL_COUNT;

	for (i = 0; i < num_volumes; i++) {
		vol = ubi->volumes[i];
		if (!vol)
			continue;

		cond_resched();

		vol->eba_tbl = kmalloc(vol->reserved_pebs * sizeof(int),
				       GFP_KERNEL);
		if (!vol->eba_tbl) {
			err = -ENOMEM;
			goto out_free;
		}

		for (j = 0; j < vol->reserved_pebs; j++)
			vol->eba_tbl[j] = UBI_LEB_UNMAPPED;

		sv = ubi_scan_find_sv(si, idx2vol_id(ubi, i));
		if (!sv)
			continue;

		ubi_rb_for_each_entry(rb, seb, &sv->root, u.rb) {
			if (seb->lnum >= vol->reserved_pebs)
				/*
				 * This may happen in case of an unclean reboot
				 * during re-size.
				 */
				ubi_scan_move_to_list(sv, seb, &si->erase);
			vol->eba_tbl[seb->lnum] = seb->pnum;
		}
	}

	if (ubi->avail_pebs < EBA_RESERVED_PEBS) {
		ubi_err("no enough physical eraseblocks (%d, need %d)",
			ubi->avail_pebs, EBA_RESERVED_PEBS);
		err = -ENOSPC;
		goto out_free;
	}
	ubi->avail_pebs -= EBA_RESERVED_PEBS;
	ubi->rsvd_pebs += EBA_RESERVED_PEBS;

	if (ubi->bad_allowed) {
		ubi_calculate_reserved(ubi);

		if (ubi->avail_pebs < ubi->beb_rsvd_level) {
			/* No enough free physical eraseblocks */
			ubi->beb_rsvd_pebs = ubi->avail_pebs;
			ubi_warn("cannot reserve enough PEBs for bad PEB "
				 "handling, reserved %d, need %d",
				 ubi->beb_rsvd_pebs, ubi->beb_rsvd_level);
		} else
			ubi->beb_rsvd_pebs = ubi->beb_rsvd_level;

		ubi->avail_pebs -= ubi->beb_rsvd_pebs;
		ubi->rsvd_pebs  += ubi->beb_rsvd_pebs;
	}

	dbg_eba("EBA sub-system is initialized");
	return 0;

out_free:
	for (i = 0; i < num_volumes; i++) {
		if (!ubi->volumes[i])
			continue;
		kfree(ubi->volumes[i]->eba_tbl);
	}
	return err;
}