blkio: Core implementation of throttle policy

o Actual implementation of throttling policy in block layer. Currently it
  implements READ and WRITE bytes per second throttling logic. IOPS throttling
  comes in later patches.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

block/Kconfig

@@ -77,6 +77,18 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_THROTTLING
+	bool "Block layer bio throttling support"
+	depends on BLK_CGROUP=y && EXPERIMENTAL
+	default n
+	---help---
+	Block layer bio throttling support. It can be used to limit
+	the IO rate to a device. IO rate policies are per cgroup and
+	one needs to mount and use blkio cgroup controller for creating
+	cgroups and specifying per device IO rate policies.
+
+	See Documentation/cgroups/blkio-controller.txt for more information.
+
 endif # BLOCK
 
 config BLOCK_COMPAT

block/Makefile

@@ -9,6 +9,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
+obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o

block/blk-core.c

@@ -382,6 +382,7 @@ void blk_sync_queue(struct request_queue *q)
 	del_timer_sync(&q->unplug_timer);
 	del_timer_sync(&q->timeout);
 	cancel_work_sync(&q->unplug_work);
+	throtl_shutdown_timer_wq(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -459,6 +460,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	if (q->elevator)
 		elevator_exit(q->elevator);
 
+	blk_throtl_exit(q);
+
 	blk_put_queue(q);
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
@@ -515,6 +518,11 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 		return NULL;
 	}
 
+	if (blk_throtl_init(q)) {
+		kmem_cache_free(blk_requestq_cachep, q);
+		return NULL;
+	}
+
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	init_timer(&q->unplug_timer);
@@ -1522,6 +1530,15 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
+		blk_throtl_bio(q, &bio);
+
+		/*
+		 * If bio = NULL, bio has been throttled and will be submitted
+		 * later.
+		 */
+		if (!bio)
+			break;
+
 		trace_block_bio_queue(q, bio);
 
 		ret = q->make_request_fn(q, bio);
@@ -2580,6 +2597,13 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
+int kblockd_schedule_delayed_work(struct request_queue *q,
+			struct delayed_work *dwork, unsigned long delay)
+{
+	return queue_delayed_work(kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work);
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *

include/linux/blk_types.h

@@ -130,6 +130,8 @@ enum rq_flag_bits {
 	/* bio only flags */
 	__REQ_UNPLUG,		/* unplug the immediately after submission */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
+	__REQ_THROTTLED,	/* This bio has already been subjected to
+				 * throttling rules. Don't do it again. */
 
 	/* request only flags */
 	__REQ_SORTED,		/* elevator knows about this request */
@@ -172,6 +174,7 @@ enum rq_flag_bits {
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
+#define REQ_THROTTLED		(1 << __REQ_THROTTLED)
 
 #define REQ_SORTED		(1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER		(1 << __REQ_SOFTBARRIER)

include/linux/blkdev.h

@@ -371,6 +371,11 @@ struct request_queue
 #if defined(CONFIG_BLK_DEV_BSG)
 	struct bsg_class_device bsg_dev;
 #endif
+
+#ifdef CONFIG_BLK_DEV_THROTTLING
+	/* Throttle data */
+	struct throtl_data *td;
+#endif
 };
 
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
@@ -1131,6 +1136,7 @@ static inline void put_dev_sector(Sector p)
 
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
+int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
 /*
@@ -1174,6 +1180,24 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 }
 #endif
 
+#ifdef CONFIG_BLK_DEV_THROTTLING
+extern int blk_throtl_init(struct request_queue *q);
+extern void blk_throtl_exit(struct request_queue *q);
+extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
+extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay);
+extern void throtl_shutdown_timer_wq(struct request_queue *q);
+#else /* CONFIG_BLK_DEV_THROTTLING */
+static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
+{
+	return 0;
+}
+
+static inline int blk_throtl_init(struct request_queue *q) { return 0; }
+static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
+static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {}
+static inline void throtl_shutdown_timer_wq(struct request_queue *q) {}
+#endif /* CONFIG_BLK_DEV_THROTTLING */
+
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \

init/Kconfig

@@ -634,11 +634,14 @@ config BLK_CGROUP
 
 	Currently, CFQ IO scheduler uses it to recognize task groups and
 	control disk bandwidth allocation (proportional time slice allocation)
-	to such task groups.
+	to such task groups. It is also used by bio throttling logic in
+	block layer to implement upper limit in IO rates on a device.
 
 	This option only enables generic Block IO controller infrastructure.
-	One needs to also enable actual IO controlling logic in CFQ for it
-	to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y).
+	One needs to also enable actual IO controlling logic/policy. For
+	enabling proportional weight division of disk bandwidth in CFQ seti
+	CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set
+	CONFIG_BLK_THROTTLE=y.
 
 	See Documentation/cgroups/blkio-controller.txt for more information.