[PATCH 5/8] block: Implement support for zoned block devices

[Hannes Reinecke <hare@suse.de>]

Implement a RB-Tree holding the zone information and
add support functions for maintaining the RB-Tree.

Signed-off-by: Hannes Reinecke <hare@suse.de>
---
 block/Kconfig          |  9 +++++++
 block/Makefile         |  1 +
 block/blk-core.c       |  5 ++++
 block/blk-zoned.c      | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/blkdev.h | 47 +++++++++++++++++++++++++++++++++
 5 files changed, 132 insertions(+)
 create mode 100644 block/blk-zoned.c

diff --git a/block/Kconfig b/block/Kconfig
index 161491d..bc9c28ae 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -100,6 +100,15 @@ config BLK_DEV_THROTTLING
 
 	See Documentation/cgroups/blkio-controller.txt for more information.
 
+config BLK_DEV_ZONED
+	bool "Zoned block device support"
+	default n
+	---help---
+	Block layer zoned block device support. This option enables
+	support for zoned block (ZAC/ZBC) devices.
+
+	Say yes here if you have a ZAC or ZBC storage device.
+
 config BLK_CMDLINE_PARSER
 	bool "Block device command line partition parser"
 	default n
diff --git a/block/Makefile b/block/Makefile
index 00ecc97..171b572 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
+obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
diff --git a/block/blk-core.c b/block/blk-core.c
index 627ed0c..82d8ce9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -573,6 +573,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
 
+	blk_drop_zones(q);
+
 	spin_lock_irq(lock);
 	if (q->queue_lock != &q->__queue_lock)
 		q->queue_lock = &q->__queue_lock;
@@ -664,6 +666,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 #ifdef CONFIG_BLK_CGROUP
 	INIT_LIST_HEAD(&q->blkg_list);
 #endif
+#ifdef CONFIG_BLK_DEV_ZONED
+	q->zones = RB_ROOT;
+#endif
 	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
new file mode 100644
index 0000000..975e863
--- /dev/null
+++ b/block/blk-zoned.c
@@ -0,0 +1,70 @@
+/*
+ * Zoned block device handling
+ *
+ * Copyright (c) 2015, Hannes Reinecke
+ * Copyright (c) 2015, SUSE Linux GmbH
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/rbtree.h>
+
+struct blk_zone *blk_lookup_zone(struct request_queue *q, sector_t lba)
+{
+	struct rb_root *root = &q->zones;
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct blk_zone *zone = container_of(node, struct blk_zone,
+						     node);
+
+		if (lba < zone->start)
+			node = node->rb_left;
+		else if (lba >= zone->start + zone->len)
+			node = node->rb_right;
+		else
+			return zone;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(blk_lookup_zone);
+
+struct blk_zone *blk_insert_zone(struct request_queue *q, struct blk_zone *data)
+{
+	struct rb_root *root = &q->zones;
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct blk_zone *this = container_of(*new, struct blk_zone,
+						     node);
+		parent = *new;
+		if (data->start + data->len <= this->start)
+			new = &((*new)->rb_left);
+		else if (data->start >= this->start + this->len)
+			new = &((*new)->rb_right);
+		else {
+			/* Return existing zone */
+			return this;
+		}
+	}
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(blk_insert_zone);
+
+void blk_drop_zones(struct request_queue *q)
+{
+	struct rb_root *root = &q->zones;
+	struct blk_zone *zone, *next;
+
+	rbtree_postorder_for_each_entry_safe(zone, next, root, node) {
+		kfree(zone);
+	}
+	q->zones = RB_ROOT;
+}
+EXPORT_SYMBOL_GPL(blk_drop_zones);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d4068c1..746ea82 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -255,6 +255,50 @@ struct blk_queue_tag {
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
 
+#ifdef CONFIG_BLK_DEV_ZONED
+enum blk_zone_type {
+	BLK_ZONE_TYPE_UNKNOWN,
+	BLK_ZONE_TYPE_CONVENTIONAL,
+	BLK_ZONE_TYPE_SEQWRITE_REQ,
+	BLK_ZONE_TYPE_SEQWRITE_PREF,
+	BLK_ZONE_TYPE_RESERVED,
+};
+
+enum blk_zone_state {
+	BLK_ZONE_UNKNOWN,
+	BLK_ZONE_NO_WP,
+	BLK_ZONE_OPEN,
+	BLK_ZONE_READONLY,
+	BLK_ZONE_OFFLINE,
+	BLK_ZONE_BUSY,
+};
+
+struct blk_zone {
+	struct rb_node node;
+	spinlock_t lock;
+	uint64_t start;
+	uint64_t len;
+	uint64_t wp;
+	enum blk_zone_type type;
+	enum blk_zone_state state;
+	void *private_data;
+};
+
+#define blk_zone_is_smr(z) ((z)->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||	\
+			    (z)->type == BLK_ZONE_TYPE_SEQWRITE_PREF)
+
+#define blk_zone_is_cmr(z) ((z)->type == BLK_ZONE_TYPE_CONVENTIONAL)
+#define blk_zone_is_full(z) ((z)->wp == (z)->start + (z)->len)
+#define blk_zone_is_empty(z) ((z)->wp == (z)->start)
+
+extern struct blk_zone *blk_lookup_zone(struct request_queue *, sector_t);
+extern struct blk_zone *blk_insert_zone(struct request_queue *,
+					struct blk_zone *);
+extern void blk_drop_zones(struct request_queue *);
+#else
+static inline void blk_drop_zones(struct request_queue *q) { };
+#endif
+
 struct queue_limits {
 	unsigned long		bounce_pfn;
 	unsigned long		seg_boundary_mask;
@@ -420,6 +464,9 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
+#ifdef CONFIG_BLK_DEV_ZONED
+	struct rb_root		zones;
+#endif
 	/*
 	 * sg stuff
 	 */
-- 
1.8.5.2