wl.c

基于linux-2.6.28的mtd驱动

		spin_unlock(&ubi->volumes_lock);
		ubi_err("no reserved physical eraseblocks");
		goto out_ro;
	}

	spin_unlock(&ubi->volumes_lock);
	ubi_msg("mark PEB %d as bad", pnum);

	err = ubi_io_mark_bad(ubi, pnum);
	if (err)
		goto out_ro;

	spin_lock(&ubi->volumes_lock);
	ubi->beb_rsvd_pebs -= 1;
	ubi->bad_peb_count += 1;
	ubi->good_peb_count -= 1;
	ubi_calculate_reserved(ubi);
	if (ubi->beb_rsvd_pebs == 0)
		ubi_warn("last PEB from the reserved pool was used");
	spin_unlock(&ubi->volumes_lock);

	return err;

out_ro:
	ubi_ro_mode(ubi);
	return err;
}

/**
 * ubi_wl_put_peb - return a PEB to the wear-leveling sub-system.
 * @ubi: UBI device description object
 * @pnum: physical eraseblock to return
 * @torture: if this physical eraseblock has to be tortured
 *
 * This function is called to return physical eraseblock @pnum to the pool of
 * free physical eraseblocks. The @torture flag has to be set if an I/O error
 * occurred to this @pnum and it has to be tested. This function returns zero
 * in case of success, and a negative error code in case of failure.
 */
int ubi_wl_put_peb(struct ubi_device *ubi, int pnum, int torture)
{
	int err;
	struct ubi_wl_entry *e;

	dbg_wl("PEB %d", pnum);
	ubi_assert(pnum >= 0);
	ubi_assert(pnum < ubi->peb_count);

retry:
	spin_lock(&ubi->wl_lock);
	e = ubi->lookuptbl[pnum];
	if (e == ubi->move_from) {
		/*
		 * User is putting the physical eraseblock which was selected to
		 * be moved. It will be scheduled for erasure in the
		 * wear-leveling worker.
		 */
		dbg_wl("PEB %d is being moved, wait", pnum);
		spin_unlock(&ubi->wl_lock);

		/* Wait for the WL worker by taking the @ubi->move_mutex */
		mutex_lock(&ubi->move_mutex);
		mutex_unlock(&ubi->move_mutex);
		goto retry;
	} else if (e == ubi->move_to) {
		/*
		 * User is putting the physical eraseblock which was selected
		 * as the target the data is moved to. It may happen if the EBA
		 * sub-system already re-mapped the LEB in 'ubi_eba_copy_leb()'
		 * but the WL sub-system has not put the PEB to the "used" tree
		 * yet, but it is about to do this. So we just set a flag which
		 * will tell the WL worker that the PEB is not needed anymore
		 * and should be scheduled for erasure.
		 */
		dbg_wl("PEB %d is the target of data moving", pnum);
		ubi_assert(!ubi->move_to_put);
		ubi->move_to_put = 1;
		spin_unlock(&ubi->wl_lock);
		return 0;
	} else {
		if (in_wl_tree(e, &ubi->used)) {
			paranoid_check_in_wl_tree(e, &ubi->used);
			rb_erase(&e->rb, &ubi->used);
		} else if (in_wl_tree(e, &ubi->scrub)) {
			paranoid_check_in_wl_tree(e, &ubi->scrub);
			rb_erase(&e->rb, &ubi->scrub);
		} else {
			err = prot_tree_del(ubi, e->pnum);
			if (err) {
				ubi_err("PEB %d not found", pnum);
				ubi_ro_mode(ubi);
				spin_unlock(&ubi->wl_lock);
				return err;
			}
		}
	}
	spin_unlock(&ubi->wl_lock);

	err = schedule_erase(ubi, e, torture);
	if (err) {
		spin_lock(&ubi->wl_lock);
		wl_tree_add(e, &ubi->used);
		spin_unlock(&ubi->wl_lock);
	}

	return err;
}

/**
 * ubi_wl_scrub_peb - schedule a physical eraseblock for scrubbing.
 * @ubi: UBI device description object
 * @pnum: the physical eraseblock to schedule
 *
 * If a bit-flip in a physical eraseblock is detected, this physical eraseblock
 * needs scrubbing. This function schedules a physical eraseblock for
 * scrubbing which is done in background. This function returns zero in case of
 * success and a negative error code in case of failure.
 */
int ubi_wl_scrub_peb(struct ubi_device *ubi, int pnum)
{
	struct ubi_wl_entry *e;

	dbg_msg("schedule PEB %d for scrubbing", pnum);

retry:
	spin_lock(&ubi->wl_lock);
	e = ubi->lookuptbl[pnum];
	if (e == ubi->move_from || in_wl_tree(e, &ubi->scrub)) {
		spin_unlock(&ubi->wl_lock);
		return 0;
	}

	if (e == ubi->move_to) {
		/*
		 * This physical eraseblock was used to move data to. The data
		 * was moved but the PEB was not yet inserted to the proper
		 * tree. We should just wait a little and let the WL worker
		 * proceed.
		 */
		spin_unlock(&ubi->wl_lock);
		dbg_wl("the PEB %d is not in proper tree, retry", pnum);
		yield();
		goto retry;
	}

	if (in_wl_tree(e, &ubi->used)) {
		paranoid_check_in_wl_tree(e, &ubi->used);
		rb_erase(&e->rb, &ubi->used);
	} else {
		int err;

		err = prot_tree_del(ubi, e->pnum);
		if (err) {
			ubi_err("PEB %d not found", pnum);
			ubi_ro_mode(ubi);
			spin_unlock(&ubi->wl_lock);
			return err;
		}
	}

	wl_tree_add(e, &ubi->scrub);
	spin_unlock(&ubi->wl_lock);

	/*
	 * Technically scrubbing is the same as wear-leveling, so it is done
	 * by the WL worker.
	 */
	return ensure_wear_leveling(ubi);
}

/**
 * ubi_wl_flush - flush all pending works.
 * @ubi: UBI device description object
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
int ubi_wl_flush(struct ubi_device *ubi)
{
	int err;

	/*
	 * Erase while the pending works queue is not empty, but not more then
	 * the number of currently pending works.
	 */
	dbg_wl("flush (%d pending works)", ubi->works_count);
	while (ubi->works_count) {
		err = do_work(ubi);
		if (err)
			return err;
	}

	/*
	 * Make sure all the works which have been done in parallel are
	 * finished.
	 */
	down_write(&ubi->work_sem);
	up_write(&ubi->work_sem);

	/*
	 * And in case last was the WL worker and it cancelled the LEB
	 * movement, flush again.
	 */
	while (ubi->works_count) {
		dbg_wl("flush more (%d pending works)", ubi->works_count);
		err = do_work(ubi);
		if (err)
			return err;
	}

	return 0;
}

/**
 * tree_destroy - destroy an RB-tree.
 * @root: the root of the tree to destroy
 */
static void tree_destroy(struct rb_root *root)
{
	struct rb_node *rb;
	struct ubi_wl_entry *e;

	rb = root->rb_node;
	while (rb) {
		if (rb->rb_left)
			rb = rb->rb_left;
		else if (rb->rb_right)
			rb = rb->rb_right;
		else {
			e = rb_entry(rb, struct ubi_wl_entry, rb);

			rb = rb_parent(rb);
			if (rb) {
				if (rb->rb_left == &e->rb)
					rb->rb_left = NULL;
				else
					rb->rb_right = NULL;
			}

			kmem_cache_free(ubi_wl_entry_slab, e);
		}
	}
}

/**
 * ubi_thread - UBI background thread.
 * @u: the UBI device description object pointer
 */
int ubi_thread(void *u)
{
	int failures = 0;
	struct ubi_device *ubi = u;

	ubi_msg("background thread \"%s\" started, PID %d",
		ubi->bgt_name, task_pid_nr(current));

	set_freezable();
	for (;;) {
		int err;

		if (kthread_should_stop())
			break;

		if (try_to_freeze())
			continue;

		spin_lock(&ubi->wl_lock);
		if (list_empty(&ubi->works) || ubi->ro_mode ||
			       !ubi->thread_enabled) {
			set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock(&ubi->wl_lock);
			schedule();
			continue;
		}
		spin_unlock(&ubi->wl_lock);

		err = do_work(ubi);
		if (err) {
			ubi_err("%s: work failed with error code %d",
				ubi->bgt_name, err);
			if (failures++ > WL_MAX_FAILURES) {
				/*
				 * Too many failures, disable the thread and
				 * switch to read-only mode.
				 */
				ubi_msg("%s: %d consecutive failures",
					ubi->bgt_name, WL_MAX_FAILURES);
				ubi_ro_mode(ubi);
				ubi->thread_enabled = 0;
				continue;
			}
		} else
			failures = 0;

		cond_resched();
	}

	dbg_wl("background thread \"%s\" is killed", ubi->bgt_name);
	return 0;
}

/**
 * cancel_pending - cancel all pending works.
 * @ubi: UBI device description object
 */
static void cancel_pending(struct ubi_device *ubi)
{
	while (!list_empty(&ubi->works)) {
		struct ubi_work *wrk;

		wrk = list_entry(ubi->works.next, struct ubi_work, list);
		list_del(&wrk->list);
		wrk->func(ubi, wrk, 1);
		ubi->works_count -= 1;
		ubi_assert(ubi->works_count >= 0);
	}
}

/**
 * ubi_wl_init_scan - initialize the WL 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_wl_init_scan(struct ubi_device *ubi, struct ubi_scan_info *si)
{
	int err;
	struct rb_node *rb1, *rb2;
	struct ubi_scan_volume *sv;
	struct ubi_scan_leb *seb, *tmp;
	struct ubi_wl_entry *e;


	ubi->used = ubi->free = ubi->scrub = RB_ROOT;
	ubi->prot.pnum = ubi->prot.aec = RB_ROOT;
	spin_lock_init(&ubi->wl_lock);
	mutex_init(&ubi->move_mutex);
	init_rwsem(&ubi->work_sem);
	ubi->max_ec = si->max_ec;
	INIT_LIST_HEAD(&ubi->works);

	sprintf(ubi->bgt_name, UBI_BGT_NAME_PATTERN, ubi->ubi_num);

	err = -ENOMEM;
	ubi->lookuptbl = kzalloc(ubi->peb_count * sizeof(void *), GFP_KERNEL);
	if (!ubi->lookuptbl)
		return err;

	list_for_each_entry_safe(seb, tmp, &si->erase, u.list) {
		cond_resched();

		e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
		if (!e)
			goto out_free;

		e->pnum = seb->pnum;
		e->ec = seb->ec;
		ubi->lookuptbl[e->pnum] = e;
		if (schedule_erase(ubi, e, 0)) {
			kmem_cache_free(ubi_wl_entry_slab, e);
			goto out_free;
		}
	}

	list_for_each_entry(seb, &si->free, u.list) {
		cond_resched();

		e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
		if (!e)
			goto out_free;

		e->pnum = seb->pnum;
		e->ec = seb->ec;
		ubi_assert(e->ec >= 0);
		wl_tree_add(e, &ubi->free);
		ubi->lookuptbl[e->pnum] = e;
	}

	list_for_each_entry(seb, &si->corr, u.list) {
		cond_resched();

		e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
		if (!e)
			goto out_free;

		e->pnum = seb->pnum;
		e->ec = seb->ec;
		ubi->lookuptbl[e->pnum] = e;
		if (schedule_erase(ubi, e, 0)) {
			kmem_cache_free(ubi_wl_entry_slab, e);
			goto out_free;
		}
	}

	ubi_rb_for_each_entry(rb1, sv, &si->volumes, rb) {
		ubi_rb_for_each_entry(rb2, seb, &sv->root, u.rb) {
			cond_resched();

			e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
			if (!e)
				goto out_free;

			e->pnum = seb->pnum;
			e->ec = seb->ec;
			ubi->lookuptbl[e->pnum] = e;
			if (!seb->scrub) {
				dbg_wl("add PEB %d EC %d to the used tree",
				       e->pnum, e->ec);
				wl_tree_add(e, &ubi->used);
			} else {
				dbg_wl("add PEB %d EC %d to the scrub tree",
				       e->pnum, e->ec);
				wl_tree_add(e, &ubi->scrub);
			}
		}
	}

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

	/* Schedule wear-leveling if needed */
	err = ensure_wear_leveling(ubi);
	if (err)
		goto out_free;

	return 0;

out_free:
	cancel_pending(ubi);
	tree_destroy(&ubi->used);
	tree_destroy(&ubi->free);
	tree_destroy(&ubi->scrub);
	kfree(ubi->lookuptbl);
	return err;
}

/**
 * protection_trees_destroy - destroy the protection RB-trees.
 * @ubi: UBI device description object
 */
static void protection_trees_destroy(struct ubi_device *ubi)
{
	struct rb_node *rb;
	struct ubi_wl_prot_entry *pe;

	rb = ubi->prot.aec.rb_node;
	while (rb) {
		if (rb->rb_left)
			rb = rb->rb_left;
		else if (rb->rb_right)
			rb = rb->rb_right;
		else {
			pe = rb_entry(rb, struct ubi_wl_prot_entry, rb_aec);

			rb = rb_parent(rb);
			if (rb) {
				if (rb->rb_left == &pe->rb_aec)
					rb->rb_left = NULL;
				else
					rb->rb_right = NULL;
			}

			kmem_cache_free(ubi_wl_entry_slab, pe->e);
			kfree(pe);
		}
	}
}

/**
 * ubi_wl_close - close the wear-leveling sub-system.
 * @ubi: UBI device description object
 */
void ubi_wl_close(struct ubi_device *ubi)
{
	dbg_wl("close the WL sub-system");
	cancel_pending(ubi);
	protection_trees_destroy(ubi);
	tree_destroy(&ubi->used);
	tree_destroy(&ubi->free);
	tree_destroy(&ubi->scrub);
	kfree(ubi->lookuptbl);
}

#ifdef CONFIG_MTD_UBI_DEBUG_PARANOID

/**
 * paranoid_check_ec - make sure that the erase counter of a PEB is correct.
 * @ubi: UBI device description object
 * @pnum: the physical eraseblock number to check
 * @ec: the erase counter to check
 *
 * This function returns zero if the erase counter of physical eraseblock @pnum
 * is equivalent to @ec, %1 if not, and a negative error code if an error
 * occurred.
 */
static int paranoid_check_ec(struct ubi_device *ubi, int pnum, int ec)
{
	int err;
	long long read_ec;
	struct ubi_ec_hdr *ec_hdr;

	ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS);
	if (!ec_hdr)
		return -ENOMEM;

	err = ubi_io_read_ec_hdr(ubi, pnum, ec_hdr, 0);
	if (err && err != UBI_IO_BITFLIPS) {
		/* The header does not have to exist */
		err = 0;
		goto out_free;
	}

	read_ec = be64_to_cpu(ec_hdr->ec);
	if (ec != read_ec) {
		ubi_err("paranoid check failed for PEB %d", pnum);
		ubi_err("read EC is %lld, should be %d", read_ec, ec);
		ubi_dbg_dump_stack();
		err = 1;
	} else
		err = 0;

out_free:
	kfree(ec_hdr);
	return err;
}

/**
 * paranoid_check_in_wl_tree - check that wear-leveling entry is in WL RB-tree.
 * @e: the wear-leveling entry to check
 * @root: the root of the tree
 *
 * This function returns zero if @e is in the @root RB-tree and %1 if it is
 * not.
 */
static int paranoid_check_in_wl_tree(struct ubi_wl_entry *e,
				     struct rb_root *root)
{
	if (in_wl_tree(e, root))
		return 0;

	ubi_err("paranoid check failed for PEB %d, EC %d, RB-tree %p ",
		e->pnum, e->ec, root);
	ubi_dbg_dump_stack();
	return 1;
}

#endif /* CONFIG_MTD_UBI_DEBUG_PARANOID */