ubi: fastmap: Fix high cpu usage of ubi_bgt by making sure wl_pool not empty

There at least 6 PEBs reserved on UBI device:
1. EBA_RESERVED_PEBS[1]
2. WL_RESERVED_PEBS[1]
3. UBI_LAYOUT_VOLUME_EBS[2]
4. MIN_FASTMAP_RESERVED_PEBS[2]

When all ubi volumes take all their PEBs, there are 3 (EBA_RESERVED_PEBS +
WL_RESERVED_PEBS + MIN_FASTMAP_RESERVED_PEBS - MIN_FASTMAP_TAKEN_PEBS[1])
free PEBs. Since commit f9c34bb529 ("ubi: Fix producing anchor PEBs")
and commit 4b68bf9a69 ("ubi: Select fastmap anchor PEBs considering
wear level rules") applied, there is only 1 (3 - FASTMAP_ANCHOR_PEBS[1] -
FASTMAP_NEXT_ANCHOR_PEBS[1]) free PEB to fill pool and wl_pool, after
filling pool, wl_pool is always empty. So, UBI could be stuck in an
infinite loop:

	ubi_thread	   system_wq
wear_leveling_worker <--------------------------------------------------
  get_peb_for_wl							|
    // fm_wl_pool, used = size = 0					|
    schedule_work(&ubi->fm_work)					|
									|
		    update_fastmap_work_fn				|
		      ubi_update_fastmap				|
			ubi_refill_pools				|
			// ubi->free_count - ubi->beb_rsvd_pebs < 5	|
			// wl_pool is not filled with any PEBs		|
			schedule_erase(old_fm_anchor)			|
			ubi_ensure_anchor_pebs				|
			  __schedule_ubi_work(wear_leveling_worker)	|
									|
__erase_worker								|
  ensure_wear_leveling							|
    __schedule_ubi_work(wear_leveling_worker) --------------------------

, which cause high cpu usage of ubi_bgt:
top - 12:10:42 up 5 min,  2 users,  load average: 1.76, 0.68, 0.27
Tasks: 123 total,   3 running,  54 sleeping,   0 stopped,   0 zombie

  PID USER PR   NI VIRT    RES    SHR S  %CPU %MEM     TIME+ COMMAND
 1589 root 20   0   0      0      0 R  45.0  0.0   0:38.86 ubi_bgt0d
  319 root 20   0   0      0      0 I  15.2  0.0   0:15.29 kworker/0:3-eve
  371 root 20   0   0      0      0 I  14.9  0.0   0:12.85 kworker/3:3-eve
   20 root 20   0   0      0      0 I  11.3  0.0   0:05.33 kworker/1:0-eve
  202 root 20   0   0      0      0 I  11.3  0.0   0:04.93 kworker/2:3-eve

In commit 4b68bf9a69 ("ubi: Select fastmap anchor PEBs considering
wear level rules"), there are three key changes:
  1) Choose the fastmap anchor when the most free PEBs are available.
  2) Enable anchor move within the anchor area again as it is useful
     for distributing wear.
  3) Import a candidate fm anchor and check this PEB's erase count during
     wear leveling. If the wear leveling limit is exceeded, use the used
     anchor area PEB with the lowest erase count to replace it.

The anchor candidate can be removed, we can check fm_anchor PEB's erase
count during wear leveling. Fix it by:
  1) Removing 'fm_next_anchor' and check 'fm_anchor' during wear leveling.
  2) Preferentially filling one free peb into fm_wl_pool in condition of
     ubi->free_count > ubi->beb_rsvd_pebs, then try to reserve enough
     free count for fastmap non anchor pebs after the above prerequisites
     are met.
Then, there are at least 1 PEB in pool and 1 PEB in wl_pool after calling
ubi_refill_pools() with all erase works done.

Fetch a reproducer in [Link].

Fixes: 4b68bf9a69 ("ubi: Select fastmap anchor PEBs ... rules")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215407
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>

drivers/mtd/ubi/fastmap-wl.c

@@ -97,6 +97,33 @@ out:
 	return e;
 }
 
+/*
+ * has_enough_free_count - whether ubi has enough free pebs to fill fm pools
+ * @ubi: UBI device description object
+ * @is_wl_pool: whether UBI is filling wear leveling pool
+ *
+ * This helper function checks whether there are enough free pebs (deducted
+ * by fastmap pebs) to fill fm_pool and fm_wl_pool, above rule works after
+ * there is at least one of free pebs is filled into fm_wl_pool.
+ * For wear leveling pool, UBI should also reserve free pebs for bad pebs
+ * handling, because there maybe no enough free pebs for user volumes after
+ * producing new bad pebs.
+ */
+static bool has_enough_free_count(struct ubi_device *ubi, bool is_wl_pool)
+{
+	int fm_used = 0;	// fastmap non anchor pebs.
+	int beb_rsvd_pebs;
+
+	if (!ubi->free.rb_node)
+		return false;
+
+	beb_rsvd_pebs = is_wl_pool ? ubi->beb_rsvd_pebs : 0;
+	if (ubi->fm_wl_pool.size > 0 && !(ubi->ro_mode || ubi->fm_disabled))
+		fm_used = ubi->fm_size / ubi->leb_size - 1;
+
+	return ubi->free_count - beb_rsvd_pebs > fm_used;
+}
+
 /**
  * ubi_refill_pools - refills all fastmap PEB pools.
  * @ubi: UBI device description object
@@ -120,21 +147,17 @@ void ubi_refill_pools(struct ubi_device *ubi)
 		wl_tree_add(ubi->fm_anchor, &ubi->free);
 		ubi->free_count++;
 	}
-	if (ubi->fm_next_anchor) {
-		wl_tree_add(ubi->fm_next_anchor, &ubi->free);
-		ubi->free_count++;
-	}
 
-	/* All available PEBs are in ubi->free, now is the time to get
+	/*
+	 * All available PEBs are in ubi->free, now is the time to get
 	 * the best anchor PEBs.
 	 */
 	ubi->fm_anchor = ubi_wl_get_fm_peb(ubi, 1);
-	ubi->fm_next_anchor = ubi_wl_get_fm_peb(ubi, 1);
 
 	for (;;) {
 		enough = 0;
 		if (pool->size < pool->max_size) {
-			if (!ubi->free.rb_node)
+			if (!has_enough_free_count(ubi, false))
 				break;
 
 			e = wl_get_wle(ubi);
@@ -147,8 +170,7 @@ void ubi_refill_pools(struct ubi_device *ubi)
 			enough++;
 
 		if (wl_pool->size < wl_pool->max_size) {
-			if (!ubi->free.rb_node ||
+			if (!has_enough_free_count(ubi, true))
-			   (ubi->free_count - ubi->beb_rsvd_pebs < 5))
 				break;
 
 			e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF);
@@ -286,20 +308,26 @@ static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi)
 int ubi_ensure_anchor_pebs(struct ubi_device *ubi)
 {
 	struct ubi_work *wrk;
+	struct ubi_wl_entry *anchor;
 
 	spin_lock(&ubi->wl_lock);
 
-	/* Do we have a next anchor? */
+	/* Do we already have an anchor? */
-	if (!ubi->fm_next_anchor) {
+	if (ubi->fm_anchor) {
-		ubi->fm_next_anchor = ubi_wl_get_fm_peb(ubi, 1);
+		spin_unlock(&ubi->wl_lock);
-		if (!ubi->fm_next_anchor)
+		return 0;
-			/* Tell wear leveling to produce a new anchor PEB */
-			ubi->fm_do_produce_anchor = 1;
 	}
 
-	/* Do wear leveling to get a new anchor PEB or check the
+	/* See if we can find an anchor PEB on the list of free PEBs */
-	 * existing next anchor candidate.
+	anchor = ubi_wl_get_fm_peb(ubi, 1);
-	 */
+	if (anchor) {
+		ubi->fm_anchor = anchor;
+		spin_unlock(&ubi->wl_lock);
+		return 0;
+	}
+
+	ubi->fm_do_produce_anchor = 1;
+	/* No luck, trigger wear leveling to produce a new anchor PEB. */
 	if (ubi->wl_scheduled) {
 		spin_unlock(&ubi->wl_lock);
 		return 0;
@@ -381,11 +409,6 @@ static void ubi_fastmap_close(struct ubi_device *ubi)
 		ubi->fm_anchor = NULL;
 	}
 
-	if (ubi->fm_next_anchor) {
-		return_unused_peb(ubi, ubi->fm_next_anchor);
-		ubi->fm_next_anchor = NULL;
-	}
-
 	if (ubi->fm) {
 		for (i = 0; i < ubi->fm->used_blocks; i++)
 			kfree(ubi->fm->e[i]);

drivers/mtd/ubi/fastmap.c

@@ -1230,17 +1230,6 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		fm_pos += sizeof(*fec);
 		ubi_assert(fm_pos <= ubi->fm_size);
 	}
-	if (ubi->fm_next_anchor) {
-		fec = (struct ubi_fm_ec *)(fm_raw + fm_pos);
-
-		fec->pnum = cpu_to_be32(ubi->fm_next_anchor->pnum);
-		set_seen(ubi, ubi->fm_next_anchor->pnum, seen_pebs);
-		fec->ec = cpu_to_be32(ubi->fm_next_anchor->ec);
-
-		free_peb_count++;
-		fm_pos += sizeof(*fec);
-		ubi_assert(fm_pos <= ubi->fm_size);
-	}
 	fmh->free_peb_count = cpu_to_be32(free_peb_count);
 
 	ubi_for_each_used_peb(ubi, wl_e, tmp_rb) {

drivers/mtd/ubi/ubi.h

@@ -489,8 +489,7 @@ struct ubi_debug_info {
  * @fm_work: fastmap work queue
  * @fm_work_scheduled: non-zero if fastmap work was scheduled
  * @fast_attach: non-zero if UBI was attached by fastmap
- * @fm_anchor: The new anchor PEB used during fastmap update
+ * @fm_anchor: The next anchor PEB to use for fastmap
- * @fm_next_anchor: An anchor PEB candidate for the next time fastmap is updated
  * @fm_do_produce_anchor: If true produce an anchor PEB in wl
  *
  * @used: RB-tree of used physical eraseblocks
@@ -601,7 +600,6 @@ struct ubi_device {
 	int fm_work_scheduled;
 	int fast_attach;
 	struct ubi_wl_entry *fm_anchor;
-	struct ubi_wl_entry *fm_next_anchor;
 	int fm_do_produce_anchor;
 
 	/* Wear-leveling sub-system's stuff */

drivers/mtd/ubi/wl.c

@@ -689,16 +689,16 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 
 #ifdef CONFIG_MTD_UBI_FASTMAP
 	e1 = find_anchor_wl_entry(&ubi->used);
-	if (e1 && ubi->fm_next_anchor &&
+	if (e1 && ubi->fm_anchor &&
-	    (ubi->fm_next_anchor->ec - e1->ec >= UBI_WL_THRESHOLD)) {
+	    (ubi->fm_anchor->ec - e1->ec >= UBI_WL_THRESHOLD)) {
 		ubi->fm_do_produce_anchor = 1;
-		/* fm_next_anchor is no longer considered a good anchor
+		/*
-		 * candidate.
+		 * fm_anchor is no longer considered a good anchor.
 		 * NULL assignment also prevents multiple wear level checks
 		 * of this PEB.
 		 */
-		wl_tree_add(ubi->fm_next_anchor, &ubi->free);
+		wl_tree_add(ubi->fm_anchor, &ubi->free);
-		ubi->fm_next_anchor = NULL;
+		ubi->fm_anchor = NULL;
 		ubi->free_count++;
 	}
 
@@ -1085,12 +1085,13 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk)
 	if (!err) {
 		spin_lock(&ubi->wl_lock);
 
-		if (!ubi->fm_disabled && !ubi->fm_next_anchor &&
+		if (!ubi->fm_disabled && !ubi->fm_anchor &&
 		    e->pnum < UBI_FM_MAX_START) {
-			/* Abort anchor production, if needed it will be
+			/*
+			 * Abort anchor production, if needed it will be
 			 * enabled again in the wear leveling started below.
 			 */
-			ubi->fm_next_anchor = e;
+			ubi->fm_anchor = e;
 			ubi->fm_do_produce_anchor = 0;
 		} else {
 			wl_tree_add(e, &ubi->free);