[PATCH 00/20] bcache patches for Linux v5.12

@@ -2517,7 +2517,7 @@ static void register_cache_worker(struct work_struct *work)
 	module_put(THIS_MODULE);
 }
 
-static void register_device_aync(struct async_reg_args *args)
+static void register_device_async(struct async_reg_args *args)
 {
 	if (SB_IS_BDEV(args->sb))
 		INIT_DELAYED_WORK(&args->reg_work, register_bdev_worker);

@@ -2611,7 +2611,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		args->sb	= sb;
 		args->sb_disk	= sb_disk;
 		args->bdev	= bdev;
-		register_device_aync(args);
+		register_device_async(args);
 		/* No wait and returns to user space */
 		goto async_done;
 	}

@@ -373,6 +373,7 @@ struct cached_dev {
 	unsigned int		partial_stripes_expensive:1;
 	unsigned int		writeback_metadata:1;
 	unsigned int		writeback_running:1;
+	unsigned int		writeback_consider_fragment:1;
 	unsigned char		writeback_percent;
 	unsigned int		writeback_delay;
 

@@ -385,6 +386,9 @@ struct cached_dev {
 	unsigned int		writeback_rate_update_seconds;
 	unsigned int		writeback_rate_i_term_inverse;
 	unsigned int		writeback_rate_p_term_inverse;
+	unsigned int		writeback_rate_fp_term_low;
+	unsigned int		writeback_rate_fp_term_mid;
+	unsigned int		writeback_rate_fp_term_high;
 	unsigned int		writeback_rate_minimum;
 
 	enum stop_on_failure	stop_when_cache_set_failed;

@@ -117,10 +117,14 @@ rw_attribute(writeback_running);
 rw_attribute(writeback_percent);
 rw_attribute(writeback_delay);
 rw_attribute(writeback_rate);
+rw_attribute(writeback_consider_fragment);
 
 rw_attribute(writeback_rate_update_seconds);
 rw_attribute(writeback_rate_i_term_inverse);
 rw_attribute(writeback_rate_p_term_inverse);
+rw_attribute(writeback_rate_fp_term_low);
+rw_attribute(writeback_rate_fp_term_mid);
+rw_attribute(writeback_rate_fp_term_high);
 rw_attribute(writeback_rate_minimum);
 read_attribute(writeback_rate_debug);
 

@@ -195,6 +199,7 @@ SHOW(__bch_cached_dev)
 	var_printf(bypass_torture_test,	"%i");
 	var_printf(writeback_metadata,	"%i");
 	var_printf(writeback_running,	"%i");
+	var_printf(writeback_consider_fragment,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
 	sysfs_hprint(writeback_rate,

@@ -205,6 +210,9 @@ SHOW(__bch_cached_dev)
 	var_print(writeback_rate_update_seconds);
 	var_print(writeback_rate_i_term_inverse);
 	var_print(writeback_rate_p_term_inverse);
+	var_print(writeback_rate_fp_term_low);
+	var_print(writeback_rate_fp_term_mid);
+	var_print(writeback_rate_fp_term_high);
 	var_print(writeback_rate_minimum);
 
 	if (attr == &sysfs_writeback_rate_debug) {

@@ -303,6 +311,7 @@ STORE(__cached_dev)
 	sysfs_strtoul_bool(bypass_torture_test, dc->bypass_torture_test);
 	sysfs_strtoul_bool(writeback_metadata, dc->writeback_metadata);
 	sysfs_strtoul_bool(writeback_running, dc->writeback_running);
+	sysfs_strtoul_bool(writeback_consider_fragment, dc->writeback_consider_fragment);
 	sysfs_strtoul_clamp(writeback_delay, dc->writeback_delay, 0, UINT_MAX);
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent,

@@ -331,6 +340,16 @@ STORE(__cached_dev)
 	sysfs_strtoul_clamp(writeback_rate_p_term_inverse,
 			    dc->writeback_rate_p_term_inverse,
 			    1, UINT_MAX);
+	sysfs_strtoul_clamp(writeback_rate_fp_term_low,
+			    dc->writeback_rate_fp_term_low,
+			    1, dc->writeback_rate_fp_term_mid - 1);
+	sysfs_strtoul_clamp(writeback_rate_fp_term_mid,
+			    dc->writeback_rate_fp_term_mid,
+			    dc->writeback_rate_fp_term_low + 1,
+			    dc->writeback_rate_fp_term_high - 1);
+	sysfs_strtoul_clamp(writeback_rate_fp_term_high,
+			    dc->writeback_rate_fp_term_high,
+			    dc->writeback_rate_fp_term_mid + 1, UINT_MAX);
 	sysfs_strtoul_clamp(writeback_rate_minimum,
 			    dc->writeback_rate_minimum,
 			    1, UINT_MAX);

@@ -499,9 +518,13 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_writeback_delay,
 	&sysfs_writeback_percent,
 	&sysfs_writeback_rate,
+	&sysfs_writeback_consider_fragment,
 	&sysfs_writeback_rate_update_seconds,
 	&sysfs_writeback_rate_i_term_inverse,
 	&sysfs_writeback_rate_p_term_inverse,
+	&sysfs_writeback_rate_fp_term_low,
+	&sysfs_writeback_rate_fp_term_mid,
+	&sysfs_writeback_rate_fp_term_high,
 	&sysfs_writeback_rate_minimum,
 	&sysfs_writeback_rate_debug,
 	&sysfs_io_errors,

@@ -88,6 +88,44 @@ static void __update_writeback_rate(struct cached_dev *dc)
 	int64_t integral_scaled;
 	uint32_t new_rate;
 
+	/*
+	 * We need to consider the number of dirty buckets as well
+	 * when calculating the proportional_scaled, Otherwise we might
+	 * have an unreasonable small writeback rate at a highly fragmented situation
+	 * when very few dirty sectors consumed a lot dirty buckets, the
+	 * worst case is when dirty buckets reached cutoff_writeback_sync and
+	 * dirty data is still not even reached to writeback percent, so the rate
+	 * still will be at the minimum value, which will cause the write
+	 * stuck at a non-writeback mode.
+	 */
+	struct cache_set *c = dc->disk.c;
+
+	int64_t dirty_buckets = c->nbuckets - c->avail_nbuckets;
+
+	if (dc->writeback_consider_fragment &&
+		c->gc_stats.in_use > BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW && dirty > 0) {
+		int64_t fragment =
+			div_s64((dirty_buckets *  c->cache->sb.bucket_size), dirty);
+		int64_t fp_term;
+		int64_t fps;
+
+		if (c->gc_stats.in_use <= BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID) {
+			fp_term = dc->writeback_rate_fp_term_low *
+			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW);
+		} else if (c->gc_stats.in_use <= BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH) {
+			fp_term = dc->writeback_rate_fp_term_mid *
+			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID);
+		} else {
+			fp_term = dc->writeback_rate_fp_term_high *
+			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH);
+		}
+		fps = div_s64(dirty, dirty_buckets) * fp_term;
+		if (fragment > 3 && fps > proportional_scaled) {
+			/* Only overrite the p when fragment > 3 */
+			proportional_scaled = fps;
+		}
+	}
+
 	if ((error < 0 && dc->writeback_rate_integral > 0) ||
 	    (error > 0 && time_before64(local_clock(),
 			 dc->writeback_rate.next + NSEC_PER_MSEC))) {

@@ -977,6 +1015,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 
 	dc->writeback_metadata		= true;
 	dc->writeback_running		= false;
+	dc->writeback_consider_fragment = true;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
 	atomic_long_set(&dc->writeback_rate.rate, 1024);

@@ -984,6 +1023,9 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 
 	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
 	dc->writeback_rate_p_term_inverse = 40;
+	dc->writeback_rate_fp_term_low = 1;
+	dc->writeback_rate_fp_term_mid = 10;
+	dc->writeback_rate_fp_term_high = 1000;
 	dc->writeback_rate_i_term_inverse = 10000;
 
 	WARN_ON(test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags));

@@ -16,6 +16,10 @@
 
 #define BCH_AUTO_GC_DIRTY_THRESHOLD	50
 
+#define BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW 50
+#define BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID 57
+#define BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH 64
+
 #define BCH_DIRTY_INIT_THRD_MAX	64
 /*
  * 14 (16384ths) is chosen here as something that each backing device

@@ -1046,5 +1046,7 @@ void bch_debug_exit(void);
 void bch_debug_init(void);
 void bch_request_exit(void);
 int bch_request_init(void);
+void bch_btree_exit(void);
+int bch_btree_init(void);
 
 #endif /* _BCACHE_H */

@@ -99,6 +99,8 @@
 #define PTR_HASH(c, k)							\
 	(((k)->ptr[0] >> c->bucket_bits) | PTR_GEN(k, 0))
 
+static struct workqueue_struct *btree_io_wq;
+
 #define insert_lock(s, b)	((b)->level <= (s)->lock)
 
 

@@ -308,7 +310,7 @@ static void __btree_node_write_done(struct closure *cl)
 	btree_complete_write(b, w);
 
 	if (btree_node_dirty(b))
-		schedule_delayed_work(&b->work, 30 * HZ);
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }

@@ -481,7 +483,7 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref)
 	BUG_ON(!i->keys);
 
 	if (!btree_node_dirty(b))
-		schedule_delayed_work(&b->work, 30 * HZ);
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
 	set_btree_node_dirty(b);
 

@@ -2764,3 +2766,18 @@ void bch_keybuf_init(struct keybuf *buf)
 	spin_lock_init(&buf->lock);
 	array_allocator_init(&buf->freelist);
 }
+
+void bch_btree_exit(void)
+{
+	if (btree_io_wq)
+		destroy_workqueue(btree_io_wq);
+}
+
+int __init bch_btree_init(void)
+{
+	btree_io_wq = create_singlethread_workqueue("bch_btree_io");
+	if (!btree_io_wq)
+		return -ENOMEM;
+
+	return 0;
+}

@@ -2821,6 +2821,7 @@ static void bcache_exit(void)
 		destroy_workqueue(bcache_wq);
 	if (bch_journal_wq)
 		destroy_workqueue(bch_journal_wq);
+	bch_btree_exit();
 
 	if (bcache_major)
 		unregister_blkdev(bcache_major, "bcache");

@@ -2876,6 +2877,9 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
+	if (bch_btree_init())
+		goto err;
+
 	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
 	if (!bcache_wq)
 		goto err;

@@ -2775,7 +2775,7 @@ void bch_btree_exit(void)
 
 int __init bch_btree_init(void)
 {
-	btree_io_wq = create_singlethread_workqueue("bch_btree_io");
+	btree_io_wq = alloc_workqueue("bch_btree_io", WQ_MEM_RECLAIM, 0);
 	if (!btree_io_wq)
 		return -ENOMEM;
 

@@ -1005,6 +1005,7 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
 extern struct workqueue_struct *bch_journal_wq;
+extern struct workqueue_struct *bch_flush_wq;
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 

@@ -932,8 +932,8 @@ atomic_t *bch_journal(struct cache_set *c,
 		journal_try_write(c);
 	} else if (!w->dirty) {
 		w->dirty = true;
-		schedule_delayed_work(&c->journal.work,
-				      msecs_to_jiffies(c->journal_delay_ms));
+		queue_delayed_work(bch_flush_wq, &c->journal.work,
+				   msecs_to_jiffies(c->journal_delay_ms));
 		spin_unlock(&c->journal.lock);
 	} else {
 		spin_unlock(&c->journal.lock);

@@ -49,6 +49,7 @@ static int bcache_major;
 static DEFINE_IDA(bcache_device_idx);
 static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_flush_wq;
 struct workqueue_struct *bch_journal_wq;
 
 

@@ -2821,6 +2822,8 @@ static void bcache_exit(void)
 		destroy_workqueue(bcache_wq);
 	if (bch_journal_wq)
 		destroy_workqueue(bch_journal_wq);
+	if (bch_flush_wq)
+		destroy_workqueue(bch_flush_wq);
 	bch_btree_exit();
 
 	if (bcache_major)

@@ -2884,6 +2887,19 @@ static int __init bcache_init(void)
 	if (!bcache_wq)
 		goto err;
 
+	/*
+	 * Let's not make this `WQ_MEM_RECLAIM` for the following reasons:
+	 *
+	 * 1. It used `system_wq` before which also does no memory reclaim.
+	 * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and
+	 *    reduced throughput can be observed.
+	 *
+	 * We still want to user our own queue to not congest the `system_wq`.
+	 */
+	bch_flush_wq = alloc_workqueue("bch_flush", 0, 0);
+	if (!bch_flush_wq)
+		goto err;
+
 	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
 	if (!bch_journal_wq)
 		goto err;

@@ -712,8 +712,10 @@ void bch_bset_build_written_tree(struct btree_keys *b)
 	for (j = inorder_next(0, t->size);
 	     j;
 	     j = inorder_next(j, t->size)) {
-		while (bkey_to_cacheline(t, k) < cacheline)
-			prev = k, k = bkey_next(k);
+		while (bkey_to_cacheline(t, k) < cacheline) {
+			prev = k;
+			k = bkey_next(k);
+		}
 
 		t->prev[j] = bkey_u64s(prev);
 		t->tree[j].m = bkey_to_cacheline_offset(t, cacheline++, k);

@@ -901,8 +903,10 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	status = BTREE_INSERT_STATUS_INSERT;
 
 	while (m != bset_bkey_last(i) &&
-	       bkey_cmp(k, b->ops->is_extents ? &START_KEY(m) : m) > 0)
-		prev = m, m = bkey_next(m);
+	       bkey_cmp(k, b->ops->is_extents ? &START_KEY(m) : m) > 0) {
+		prev = m;
+		m = bkey_next(m);
+	}
 
 	/* prev is in the tree, if we merge we're done */
 	status = BTREE_INSERT_STATUS_BACK_MERGE;

@@ -1094,8 +1094,10 @@ SHOW(__bch_cache)
 			--n;
 
 		while (cached < p + n &&
-		       *cached == BTREE_PRIO)
-			cached++, n--;
+		       *cached == BTREE_PRIO) {
+			cached++;
+			n--;
+		}
 
 		for (i = 0; i < n; i++)
 			sum += INITIAL_PRIO - cached[i];

@@ -124,6 +124,127 @@ static inline void remove_owner_space(struct bch_nvm_namespace *ns,
 	bitmap_set(ns->pages_bitmap, pgoff, nr);
 }
 
+/* If not found, it will create if create == true */
+static struct bch_owner_list *find_owner_list(const char *owner_uuid, bool create)
+{
+	struct bch_owner_list *owner_list;
+	int i;
+
+	for (i = 0; i < only_set->owner_list_used; i++) {
+		if (!memcmp(owner_uuid, only_set->owner_lists[i]->owner_uuid, 16))
+			return only_set->owner_lists[i];
+	}
+
+	if (create) {
+		owner_list = alloc_owner_list(owner_uuid, NULL, only_set->total_namespaces_nr);
+		only_set->owner_lists[only_set->owner_list_used++] = owner_list;
+		return owner_list;
+	} else
+		return NULL;
+}
+
+static struct bch_nvm_alloced_recs *find_nvm_alloced_recs(struct bch_owner_list *owner_list,
+		struct bch_nvm_namespace *ns, bool create)
+{
+	int position = ns->sb.this_namespace_nr;
+
+	if (create && !owner_list->alloced_recs[position]) {
+		struct bch_nvm_alloced_recs *alloced_recs =
+			kzalloc(sizeof(*alloced_recs), GFP_KERNEL|__GFP_NOFAIL);
+
+		alloced_recs->ns = ns;
+		INIT_LIST_HEAD(&alloced_recs->extent_head);
+		owner_list->alloced_recs[position] = alloced_recs;
+		return alloced_recs;
+	} else
+		return owner_list->alloced_recs[position];
+}
+
+static inline void *extent_end_addr(struct bch_extent *extent)
+{
+	return extent->kaddr + ((u64)(extent->nr) << PAGE_SHIFT);
+}
+
+static void add_extent(struct bch_nvm_alloced_recs *alloced_recs, void *addr, int order)
+{
+	struct list_head *list = alloced_recs->extent_head.next;
+	struct bch_extent *extent, *tmp;
+	void *end_addr = addr + (((u64)1 << order) << PAGE_SHIFT);
+
+	while (list != &alloced_recs->extent_head) {
+		extent = container_of(list, struct bch_extent, list);
+		if (addr > extent->kaddr) {
+			list = list->next;
+			continue;
+		}
+		break;
+	}
+
+	extent = kzalloc(sizeof(*extent), GFP_KERNEL);
+	extent->kaddr = addr;
+	extent->nr = 1 << order;
+	list_add_tail(&extent->list, list);
+	alloced_recs->nr++;
+}
+
+void *bch_nvm_alloc_pages(int order, const char *owner_uuid)
+{
+	void *kaddr = NULL;
+	struct bch_owner_list *owner_list;
+	struct bch_nvm_alloced_recs *alloced_recs;
+	int i, j;
+
+	mutex_lock(&only_set->lock);
+	owner_list = find_owner_list(owner_uuid, true);
+
+	for (j = 0; j < only_set->total_namespaces_nr; j++) {
+		struct bch_nvm_namespace *ns = only_set->nss[j];
+
+		if (!ns || (ns->free < (1 << order)))
+			continue;
+
+		for (i = order; i < BCH_MAX_ORDER; i++) {
+			struct list_head *list;
+			struct page *page, *buddy_page;
+
+			if (list_empty(&ns->free_area[i]))
+				continue;
+
+			list = ns->free_area[i].next;
+			page = container_of((void *)list, struct page, zone_device_data);
+
+			list_del(list);
+
+			while (i != order) {
+				buddy_page = nvm_vaddr_to_page(ns,
+					nvm_pgoff_to_vaddr(ns, page->index + (1 << (i - 1))));
+				set_page_private(buddy_page, i - 1);
+				buddy_page->index = page->index + (1 << (i - 1));
+				__SetPageBuddy(buddy_page);
+				list_add((struct list_head *)&buddy_page->zone_device_data,
+					&ns->free_area[i - 1]);
+				i--;
+			}
+
+			set_page_private(page, order);
+			__ClearPageBuddy(page);
+			ns->free -= 1 << order;
+			kaddr = nvm_pgoff_to_vaddr(ns, page->index);
+			break;
+		}
+
+		if (i != BCH_MAX_ORDER) {
+			alloced_recs = find_nvm_alloced_recs(owner_list, ns, true);
+			add_extent(alloced_recs, kaddr, order);
+			break;
+		}
+	}
+
+	mutex_unlock(&only_set->lock);
+	return kaddr;
+}
+EXPORT_SYMBOL_GPL(bch_nvm_alloc_pages);
+
 static int init_owner_info(struct bch_nvm_namespace *ns)
 {
 	struct bch_owner_list_head *owner_list_head;

@@ -79,6 +79,7 @@ extern struct bch_nvm_set *only_set;
 struct bch_nvm_namespace *bch_register_namespace(const char *dev_path);
 int bch_nvm_init(void);
 void bch_nvm_exit(void);
+void *bch_nvm_alloc_pages(int order, const char *owner_uuid);
 
 #else
 

@@ -92,6 +93,11 @@ static inline int bch_nvm_init(void)
 }
 static inline void bch_nvm_exit(void) { }
 
+static inline void *bch_nvm_alloc_pages(int order, const char *owner_uuid)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_BCACHE_NVM_PAGES */
 
 #endif /* _BCACHE_NVM_PAGES_H */

@@ -93,6 +93,7 @@ static void release_nvm_namespaces(struct bch_nvm_set *nvm_set)
 	int i;
 
 	for (i = 0; i < nvm_set->total_namespaces_nr; i++) {
+		kvfree(nvm_set->nss[i]->pages_bitmap);
 		blkdev_put(nvm_set->nss[i]->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXEC);
 		kfree(nvm_set->nss[i]);
 	}

@@ -112,6 +113,17 @@ static void *nvm_pgoff_to_vaddr(struct bch_nvm_namespace *ns, pgoff_t pgoff)
 	return ns->kaddr + (pgoff << PAGE_SHIFT);
 }
 
+static struct page *nvm_vaddr_to_page(struct bch_nvm_namespace *ns, void *addr)
+{
+	return virt_to_page(addr);
+}
+
+static inline void remove_owner_space(struct bch_nvm_namespace *ns,
+					pgoff_t pgoff, u32 nr)
+{
+	bitmap_set(ns->pages_bitmap, pgoff, nr);
+}
+
 static int init_owner_info(struct bch_nvm_namespace *ns)
 {
 	struct bch_owner_list_head *owner_list_head;

@@ -129,6 +141,8 @@ static int init_owner_info(struct bch_nvm_namespace *ns)
 	only_set->owner_list_size = owner_list_head->size;
 	only_set->owner_list_used = owner_list_head->used;
 
+	remove_owner_space(ns, 0, ns->pages_offset/ns->page_size);
+
 	for (i = 0; i < owner_list_head->used; i++) {
 		owner_head = &owner_list_head->heads[i];
 		owner_list = alloc_owner_list(owner_head->uuid, owner_head->label,

@@ -162,6 +176,8 @@ static int init_owner_info(struct bch_nvm_namespace *ns)
 
 			do {
 				struct bch_pgalloc_rec *rec;
+				int order;
+				struct page *page;
 
 				for (k = 0; k < nvm_pgalloc_recs->used; k++) {
 					rec = &nvm_pgalloc_recs->recs[k];

@@ -172,7 +188,17 @@ static int init_owner_info(struct bch_nvm_namespace *ns)
 					}
 					extent->kaddr = nvm_pgoff_to_vaddr(extents->ns, rec->pgoff);
 					extent->nr = rec->nr;
+					WARN_ON(!is_power_of_2(extent->nr));
+
+					/*init struct page: index/private */
+					order = ilog2(extent->nr);
+					page = nvm_vaddr_to_page(ns, extent->kaddr);
+					set_page_private(page, order);
+					page->index = rec->pgoff;
+
 					list_add_tail(&extent->list, &extents->extent_head);
+					/*remove already alloced space*/
+					remove_owner_space(extents->ns, rec->pgoff, rec->nr);
 				}
 				extents->nr += nvm_pgalloc_recs->used;
 

@@ -197,6 +223,36 @@ static int init_owner_info(struct bch_nvm_namespace *ns)
 	return 0;
 }
 
+static void init_nvm_free_space(struct bch_nvm_namespace *ns)
+{
+	unsigned int start, end, i;
+	struct page *page;
+	long long pages;
+	pgoff_t pgoff_start;
+
+	bitmap_for_each_clear_region(ns->pages_bitmap, start, end, 0, ns->pages_total) {
+		pgoff_start = start;
+		pages = end - start;
+
+		while (pages) {
+			for (i = BCH_MAX_ORDER - 1; i >= 0 ; i--) {
+				if ((pgoff_start % (1 << i) == 0) && (pages >= (1 << i)))
+					break;
+			}
+
+			page = nvm_vaddr_to_page(ns, nvm_pgoff_to_vaddr(ns, pgoff_start));
+			page->index = pgoff_start;
+			set_page_private(page, i);
+			__SetPageBuddy(page);
+			list_add((struct list_head *)&page->zone_device_data, &ns->free_area[i]);
+
+			pgoff_start += 1 << i;
+			pages -= 1 << i;
+		}
+	}
+
+}
+
 static bool attach_nvm_set(struct bch_nvm_namespace *ns)
 {
 	bool rc = true;

@@ -261,7 +317,7 @@ static int read_nvdimm_meta_super(struct block_device *bdev,
 struct bch_nvm_namespace *bch_register_namespace(const char *dev_path)
 {
 	struct bch_nvm_namespace *ns;
-	int err;
+	int i, err;
 	pgoff_t pgoff;
 	char buf[BDEVNAME_SIZE];
 	struct block_device *bdev;

@@ -357,6 +413,16 @@ struct bch_nvm_namespace *bch_register_namespace(const char *dev_path)
 	ns->bdev = bdev;
 	ns->nvm_set = only_set;
 
+	ns->pages_bitmap = kvcalloc(BITS_TO_LONGS(ns->pages_total),
+					sizeof(unsigned long), GFP_KERNEL);
+	if (!ns->pages_bitmap) {
+		err = -ENOMEM;
+		goto free_ns;
+	}
+
+	for (i = 0; i < BCH_MAX_ORDER; i++)
+		INIT_LIST_HEAD(&ns->free_area[i]);
+
 	mutex_init(&ns->lock);
 
 	if (ns->sb.this_namespace_nr == 0) {

@@ -364,12 +430,17 @@ struct bch_nvm_namespace *bch_register_namespace(const char *dev_path)
 		err = init_owner_info(ns);
 		if (err < 0) {
 			pr_info("init_owner_info met error %d\n", err);
-			goto free_ns;
+			goto free_bitmap;
 		}
+		/* init buddy allocator */
+		init_nvm_free_space(ns);
 	}
 
 	kfree(path);
 	return ns;
+
+free_bitmap:
+	kvfree(ns->pages_bitmap);
 free_ns:
 	kfree(ns);
 bdput:

@@ -34,6 +34,7 @@ struct bch_owner_list {
 	struct bch_nvm_alloced_recs **alloced_recs;
 };
 
+#define BCH_MAX_ORDER 20
 struct bch_nvm_namespace {
 	struct bch_nvm_pages_sb sb;
 	void *kaddr;

@@ -45,6 +46,10 @@ struct bch_nvm_namespace {
 	u64 pages_total;
 	pfn_t start_pfn;
 
+	unsigned long *pages_bitmap;
+	struct list_head free_area[BCH_MAX_ORDER];
+
+
 	struct dax_device *dax_dev;
 	struct block_device *bdev;
 	struct bch_nvm_set *nvm_set;

@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_BCACHE_NVM_H
+#define _UAPI_BCACHE_NVM_H
+
+/*
+ * Bcache on NVDIMM data structures
+ */
+
+/*
+ * - struct bch_nvm_pages_sb
+ *   This is the super block allocated on each nvdimm namespace. A nvdimm
+ * set may have multiple namespaces, bch_nvm_pages_sb->set_uuid is used to mark
+ * which nvdimm set this name space belongs to. Normally we will use the
+ * bcache's cache set UUID to initialize this uuid, to connect this nvdimm
+ * set to a specified bcache cache set.
+ *
+ * - struct bch_owner_list_head
+ *   This is a table for all heads of all owner lists. A owner list records
+ * which page(s) allocated to which owner. After reboot from power failure,
+ * the ownwer may find all its requested and allocated pages from the owner
+ * list by a handler which is converted by a UUID.
+ *
+ * - struct bch_nvm_pages_owner_head
+ *   This is a head of an owner list. Each owner only has one owner list,
+ * and a nvm page only belongs to an specific owner. uuid[] will be set to
+ * owner's uuid, for bcache it is the bcache's cache set uuid. label is not
+ * mandatory, it is a human-readable string for debug purpose. The pointer
+ * recs references to separated nvm page which hold the table of struct
+ * bch_pgalloc_rec.
+ *
+ *- struct bch_nvm_pgalloc_recs
+ *  This structure occupies a whole page, owner_uuid should match the uuid
+ * in struct bch_nvm_pages_owner_head. recs[] is the real table contains all
+ * allocated records.
+ *
+ * - struct bch_pgalloc_rec
+ *   Each structure records a range of allocated nvm pages. pgoff is offset
+ * in unit of page size of this allocated nvm page range. The adjoint page
+ * ranges of same owner can be merged into a larger one, therefore pages_nr
+ * is NOT always power of 2.
+ *
+ *
+ * Memory layout on nvdimm namespace 0
+ *
+ *    0 +---------------------------------+
+ *      |                                 |
+ *  4KB +---------------------------------+
+ *      |         bch_nvm_pages_sb        |
+ *  8KB +---------------------------------+ <--- bch_nvm_pages_sb.bch_owner_list_head
+ *      |       bch_owner_list_head       |
+ *      |                                 |
+ * 16KB +---------------------------------+ <--- bch_owner_list_head.heads[0].recs[0]
+ *      |       bch_nvm_pgalloc_recs      |
+ *      |  (nvm pages internal usage)     |
+ * 24KB +---------------------------------+
+ *      |                                 |
+ *      |                                 |
+ * 16MB  +---------------------------------+
+ *      |      allocable nvm pages        |
+ *      |      for buddy allocator        |
+ * end  +---------------------------------+
+ *
+ *
+ *
+ * Memory layout on nvdimm namespace N
+ * (doesn't have owner list)
+ *
+ *    0 +---------------------------------+
+ *      |                                 |
+ *  4KB +---------------------------------+
+ *      |         bch_nvm_pages_sb        |
+ *  8KB +---------------------------------+
+ *      |                                 |
+ *      |                                 |
+ *      |                                 |
+ *      |                                 |
+ *      |                                 |
+ *      |                                 |
+ * 16MB  +---------------------------------+
+ *      |      allocable nvm pages        |
+ *      |      for buddy allocator        |
+ * end  +---------------------------------+
+ *
+ */
+
+#include <linux/types.h>
+
+/* In sectors */
+#define BCH_NVM_PAGES_SB_OFFSET			4096
+#define BCH_NVM_PAGES_OFFSET			(16 << 20)
+
+#define BCH_NVM_PAGES_LABEL_SIZE		32
+#define BCH_NVM_PAGES_NAMESPACES_MAX		8
+
+#define BCH_NVM_PAGES_OWNER_LIST_HEAD_OFFSET	(8<<10)
+#define BCH_NVM_PAGES_SYS_RECS_HEAD_OFFSET	(16<<10)
+
+#define BCH_NVM_PAGES_SB_VERSION		0
+#define BCH_NVM_PAGES_SB_VERSION_MAX		0
+
+static const char bch_nvm_pages_magic[] = {
+	0x17, 0xbd, 0x53, 0x7f, 0x1b, 0x23, 0xd6, 0x83,
+	0x46, 0xa4, 0xf8, 0x28, 0x17, 0xda, 0xec, 0xa9 };
+static const char bch_nvm_pages_pgalloc_magic[] = {
+	0x39, 0x25, 0x3f, 0xf7, 0x27, 0x17, 0xd0, 0xb9,
+	0x10, 0xe6, 0xd2, 0xda, 0x38, 0x68, 0x26, 0xae };
+
+struct bch_pgalloc_rec {
+	__u32			pgoff;
+	__u32			nr;
+};
+
+struct bch_nvm_pgalloc_recs {
+union {
+	struct {
+		struct bch_nvm_pages_owner_head	*owner;
+		struct bch_nvm_pgalloc_recs	*next;
+		__u8				magic[16];
+		__u8				owner_uuid[16];
+		__u32				size;
+		__u32				used;
+		__u64				_pad[4];
+		struct bch_pgalloc_rec		recs[];
+	};
+	__u8	pad[8192];
+};
+};
+#define BCH_MAX_RECS					\
+	((sizeof(struct bch_nvm_pgalloc_recs) -		\
+	 offsetof(struct bch_nvm_pgalloc_recs, recs)) /	\
+	 sizeof(struct bch_pgalloc_rec))
+
+struct bch_nvm_pages_owner_head {
+	__u8			uuid[16];
+	char			label[BCH_NVM_PAGES_LABEL_SIZE];
+	/* Per-namespace own lists */
+	struct bch_nvm_pgalloc_recs	*recs[BCH_NVM_PAGES_NAMESPACES_MAX];
+};
+
+/* heads[0] is always for nvm_pages internal usage */
+struct bch_owner_list_head {
+union {
+	struct {
+		__u32				size;
+		__u32				used;
+		__u64				_pad[4];
+		struct bch_nvm_pages_owner_head	heads[];
+	};
+	__u8	pad[8192];
+};
+};
+#define BCH_MAX_OWNER_LIST				\
+	((sizeof(struct bch_owner_list_head) -		\
+	 offsetof(struct bch_owner_list_head, heads)) /	\
+	 sizeof(struct bch_nvm_pages_owner_head))
+
+/* The on-media bit order is local CPU order */
+struct bch_nvm_pages_sb {
+	__u64			csum;
+	__u64			ns_start;
+	__u64			sb_offset;
+	__u64			version;
+	__u8			magic[16];
+	__u8			uuid[16];
+	__u32			page_size;
+	__u32			total_namespaces_nr;
+	__u32			this_namespace_nr;
+	union {
+		__u8		set_uuid[16];
+		__u64		set_magic;
+	};
+
+	__u64			flags;
+	__u64			seq;
+
+	__u64			feature_compat;
+	__u64			feature_incompat;
+	__u64			feature_ro_compat;
+
+	/* For allocable nvm pages from buddy systems */
+	__u64			pages_offset;
+	__u64			pages_total;
+
+	__u64			pad[8];
+
+	/* Only on the first name space */
+	struct bch_owner_list_head	*owner_list_head;
+
+	/* Just for csum_set() */
+	__u32			keys;
+	__u64			d[0];
+};
+
+#endif /* _UAPI_BCACHE_NVM_H */

@@ -374,6 +374,45 @@ void *bch_nvm_alloc_pages(int order, const char *owner_uuid)
 }
 EXPORT_SYMBOL_GPL(bch_nvm_alloc_pages);
 
+struct bch_extent *bch_get_allocated_pages(const char *owner_uuid)
+{
+	struct bch_owner_list *owner_list = find_owner_list(owner_uuid, false);
+	struct bch_nvm_alloced_recs *alloced_recs;
+	struct bch_extent *head = NULL, *e, *tmp;
+	int i;
+
+	if (!owner_list)
+		return NULL;
+
+	for (i = 0; i < only_set->total_namespaces_nr; i++) {
+		struct list_head *l;
+
+		alloced_recs = owner_list->alloced_recs[i];
+
+		if (!alloced_recs || alloced_recs->nr == 0)
+			continue;
+
+		l = alloced_recs->extent_head.next;
+		while (l != &alloced_recs->extent_head) {
+			e = container_of(l, struct bch_extent, list);
+			tmp = kzalloc(sizeof(*tmp), GFP_KERNEL|__GFP_NOFAIL);
+
+			INIT_LIST_HEAD(&tmp->list);
+			tmp->kaddr = e->kaddr;
+			tmp->nr = e->nr;
+
+			if (head)
+				list_add_tail(&tmp->list, &head->list);
+			else
+				head = tmp;
+
+			l = l->next;
+		}
+	}
+	return head;
+}
+EXPORT_SYMBOL_GPL(bch_get_allocated_pages);
+
 static int init_owner_info(struct bch_nvm_namespace *ns)
 {
 	struct bch_owner_list_head *owner_list_head;