From 13f05c8d8e98bbdce89158bfdb2e380940695a88 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 10 Sep 2010 20:50:10 +0200
Subject: block/scsi: Provide a limit on the number of integrity segments

Some controllers have a hardware limit on the number of protection
information scatter-gather list segments they can handle.

Introduce a max_integrity_segments limit in the block layer and provide
a new scsi_host_template setting that allows HBA drivers to provide a
value suitable for the hardware.

Add support for honoring the integrity segment limit when merging both
bios and requests.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@carl.home.kernel.dk>
---
 include/linux/blkdev.h | 33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c54906f678..7e661106270 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -124,6 +124,9 @@ struct request {
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	unsigned short nr_integrity_segments;
+#endif
 
 	unsigned short ioprio;
 
@@ -243,6 +246,7 @@ struct queue_limits {
 
 	unsigned short		logical_block_size;
 	unsigned short		max_segments;
+	unsigned short		max_integrity_segments;
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
@@ -1213,8 +1217,13 @@ struct blk_integrity {
 extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
 extern void blk_integrity_unregister(struct gendisk *);
 extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
-extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
-extern int blk_rq_count_integrity_sg(struct request *);
+extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
+				   struct scatterlist *);
+extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
+extern int blk_integrity_merge_rq(struct request_queue *, struct request *,
+				  struct request *);
+extern int blk_integrity_merge_bio(struct request_queue *, struct request *,
+				   struct bio *);
 
 static inline
 struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
@@ -1235,16 +1244,32 @@ static inline int blk_integrity_rq(struct request *rq)
 	return bio_integrity(rq->bio);
 }
 
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+						    unsigned int segs)
+{
+	q->limits.max_integrity_segments = segs;
+}
+
+static inline unsigned short
+queue_max_integrity_segments(struct request_queue *q)
+{
+	return q->limits.max_integrity_segments;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 #define blk_integrity_rq(rq)			(0)
-#define blk_rq_count_integrity_sg(a)		(0)
-#define blk_rq_map_integrity_sg(a, b)		(0)
+#define blk_rq_count_integrity_sg(a, b)		(0)
+#define blk_rq_map_integrity_sg(a, b, c)	(0)
 #define bdev_get_integrity(a)			(0)
 #define blk_get_integrity(a)			(0)
 #define blk_integrity_compare(a, b)		(0)
 #define blk_integrity_register(a, b)		(0)
 #define blk_integrity_unregister(a)		do { } while (0);
+#define blk_queue_max_integrity_segments(a, b)	do { } while (0);
+#define queue_max_integrity_segments(a)		(0)
+#define blk_integrity_merge_rq(a, b, c)		(0)
+#define blk_integrity_merge_bio(a, b, c)	(0)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-- 
cgit v1.2.3-70-g09d2


From 144177991ca624841ddbd1e7edff958fc0f6d1fe Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@gmail.com>
Date: Wed, 15 Sep 2010 13:08:27 +0200
Subject: block: fix an address space warning in blk-map.c

Change type of 2nd parameter of blk_rq_aligned() into unsigned long
and remove unnecessary casting. Now we can call it with 'uaddr'
instead of 'ubuf' in __blk_rq_map_user() so that it can remove
following warnings from sparse:

 block/blk-map.c:57:31: warning: incorrect type in argument 2 (different address spaces)
 block/blk-map.c:57:31:    expected void *addr
 block/blk-map.c:57:31:    got void [noderef] <asn:1>*ubuf

However blk_rq_map_kern() needs one more local variable to handle it.

Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-map.c        | 5 +++--
 include/linux/blkdev.h | 4 ++--
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-map.c b/block/blk-map.c
index c65d7593f7f..ac0f7d46db6 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -54,7 +54,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
 	 * direct dma. else, set up kernel bounce buffers
 	 */
 	uaddr = (unsigned long) ubuf;
-	if (blk_rq_aligned(q, ubuf, len) && !map_data)
+	if (blk_rq_aligned(q, uaddr, len) && !map_data)
 		bio = bio_map_user(q, NULL, uaddr, len, reading, gfp_mask);
 	else
 		bio = bio_copy_user(q, map_data, uaddr, len, reading, gfp_mask);
@@ -288,6 +288,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		    unsigned int len, gfp_t gfp_mask)
 {
 	int reading = rq_data_dir(rq) == READ;
+	unsigned long addr = (unsigned long) kbuf;
 	int do_copy = 0;
 	struct bio *bio;
 	int ret;
@@ -297,7 +298,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (!len || !kbuf)
 		return -EINVAL;
 
-	do_copy = !blk_rq_aligned(q, kbuf, len) || object_is_on_stack(kbuf);
+	do_copy = !blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf);
 	if (do_copy)
 		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
 	else
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7e661106270..780824edac1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1097,11 +1097,11 @@ static inline int queue_dma_alignment(struct request_queue *q)
 	return q ? q->dma_alignment : 511;
 }
 
-static inline int blk_rq_aligned(struct request_queue *q, void *addr,
+static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
 				 unsigned int len)
 {
 	unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
-	return !((unsigned long)addr & alignment) && !(len & alignment);
+	return !(addr & alignment) && !(len & alignment);
 }
 
 /* assumes size > 256 */
-- 
cgit v1.2.3-70-g09d2


From e43473b7f223ec866f7db273697e76c337c390f9 Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Wed, 15 Sep 2010 17:06:35 -0400
Subject: 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             |  12 +
 block/Makefile            |   1 +
 block/blk-core.c          |  24 ++
 block/blk-throttle.c      | 909 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/blk_types.h |   3 +
 include/linux/blkdev.h    |  24 ++
 init/Kconfig              |   9 +-
 7 files changed, 979 insertions(+), 3 deletions(-)
 create mode 100644 block/blk-throttle.c

(limited to 'include/linux/blkdev.h')

diff --git a/block/Kconfig b/block/Kconfig
index 9be0b56eaee..6c9213ef15a 100644
--- a/block/Kconfig
+++ b/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
diff --git a/block/Makefile b/block/Makefile
index 0bb499a739c..c850d5ef80a 100644
--- a/block/Makefile
+++ b/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
diff --git a/block/blk-core.c b/block/blk-core.c
index 8d07c1b7e70..797d5095eb8 100644
--- a/block/blk-core.c
+++ b/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 *
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
new file mode 100644
index 00000000000..4b492011e0d
--- /dev/null
+++ b/block/blk-throttle.c
@@ -0,0 +1,909 @@
+/*
+ * Interface for controlling IO bandwidth on a request queue
+ *
+ * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/blktrace_api.h>
+#include "blk-cgroup.h"
+
+/* Max dispatch from a group in 1 round */
+static int throtl_grp_quantum = 8;
+
+/* Total max dispatch from all groups in one round */
+static int throtl_quantum = 32;
+
+/* Throttling is performed over 100ms slice and after that slice is renewed */
+static unsigned long throtl_slice = HZ/10;	/* 100 ms */
+
+struct throtl_rb_root {
+	struct rb_root rb;
+	struct rb_node *left;
+	unsigned int count;
+	unsigned long min_disptime;
+};
+
+#define THROTL_RB_ROOT	(struct throtl_rb_root) { .rb = RB_ROOT, .left = NULL, \
+			.count = 0, .min_disptime = 0}
+
+#define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
+
+struct throtl_grp {
+	/* List of throtl groups on the request queue*/
+	struct hlist_node tg_node;
+
+	/* active throtl group service_tree member */
+	struct rb_node rb_node;
+
+	/*
+	 * Dispatch time in jiffies. This is the estimated time when group
+	 * will unthrottle and is ready to dispatch more bio. It is used as
+	 * key to sort active groups in service tree.
+	 */
+	unsigned long disptime;
+
+	struct blkio_group blkg;
+	atomic_t ref;
+	unsigned int flags;
+
+	/* Two lists for READ and WRITE */
+	struct bio_list bio_lists[2];
+
+	/* Number of queued bios on READ and WRITE lists */
+	unsigned int nr_queued[2];
+
+	/* bytes per second rate limits */
+	uint64_t bps[2];
+
+	/* Number of bytes disptached in current slice */
+	uint64_t bytes_disp[2];
+
+	/* When did we start a new slice */
+	unsigned long slice_start[2];
+	unsigned long slice_end[2];
+};
+
+struct throtl_data
+{
+	/* List of throtl groups */
+	struct hlist_head tg_list;
+
+	/* service tree for active throtl groups */
+	struct throtl_rb_root tg_service_tree;
+
+	struct throtl_grp root_tg;
+	struct request_queue *queue;
+
+	/* Total Number of queued bios on READ and WRITE lists */
+	unsigned int nr_queued[2];
+
+	/*
+	 * number of total undestroyed groups (excluding root group)
+	 */
+	unsigned int nr_undestroyed_grps;
+
+	/* Work for dispatching throttled bios */
+	struct delayed_work throtl_work;
+};
+
+enum tg_state_flags {
+	THROTL_TG_FLAG_on_rr = 0,	/* on round-robin busy list */
+};
+
+#define THROTL_TG_FNS(name)						\
+static inline void throtl_mark_tg_##name(struct throtl_grp *tg)		\
+{									\
+	(tg)->flags |= (1 << THROTL_TG_FLAG_##name);			\
+}									\
+static inline void throtl_clear_tg_##name(struct throtl_grp *tg)	\
+{									\
+	(tg)->flags &= ~(1 << THROTL_TG_FLAG_##name);			\
+}									\
+static inline int throtl_tg_##name(const struct throtl_grp *tg)		\
+{									\
+	return ((tg)->flags & (1 << THROTL_TG_FLAG_##name)) != 0;	\
+}
+
+THROTL_TG_FNS(on_rr);
+
+#define throtl_log_tg(td, tg, fmt, args...)				\
+	blk_add_trace_msg((td)->queue, "throtl %s " fmt,		\
+				blkg_path(&(tg)->blkg), ##args);      	\
+
+#define throtl_log(td, fmt, args...)	\
+	blk_add_trace_msg((td)->queue, "throtl " fmt, ##args)
+
+static inline struct throtl_grp *tg_of_blkg(struct blkio_group *blkg)
+{
+	if (blkg)
+		return container_of(blkg, struct throtl_grp, blkg);
+
+	return NULL;
+}
+
+static inline int total_nr_queued(struct throtl_data *td)
+{
+	return (td->nr_queued[0] + td->nr_queued[1]);
+}
+
+static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg)
+{
+	atomic_inc(&tg->ref);
+	return tg;
+}
+
+static void throtl_put_tg(struct throtl_grp *tg)
+{
+	BUG_ON(atomic_read(&tg->ref) <= 0);
+	if (!atomic_dec_and_test(&tg->ref))
+		return;
+	kfree(tg);
+}
+
+static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
+			struct cgroup *cgroup)
+{
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+	struct throtl_grp *tg = NULL;
+	void *key = td;
+	struct backing_dev_info *bdi = &td->queue->backing_dev_info;
+	unsigned int major, minor;
+
+	/*
+	 * TODO: Speed up blkiocg_lookup_group() by maintaining a radix
+	 * tree of blkg (instead of traversing through hash list all
+	 * the time.
+	 */
+	tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+	/* Fill in device details for root group */
+	if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		tg->blkg.dev = MKDEV(major, minor);
+		goto done;
+	}
+
+	if (tg)
+		goto done;
+
+	tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
+	if (!tg)
+		goto done;
+
+	INIT_HLIST_NODE(&tg->tg_node);
+	RB_CLEAR_NODE(&tg->rb_node);
+	bio_list_init(&tg->bio_lists[0]);
+	bio_list_init(&tg->bio_lists[1]);
+
+	/*
+	 * Take the initial reference that will be released on destroy
+	 * This can be thought of a joint reference by cgroup and
+	 * request queue which will be dropped by either request queue
+	 * exit or cgroup deletion path depending on who is exiting first.
+	 */
+	atomic_set(&tg->ref, 1);
+
+	/* Add group onto cgroup list */
+	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+	blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td,
+				MKDEV(major, minor), BLKIO_POLICY_THROTL);
+
+	tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
+	tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
+
+	hlist_add_head(&tg->tg_node, &td->tg_list);
+	td->nr_undestroyed_grps++;
+done:
+	return tg;
+}
+
+static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+{
+	struct cgroup *cgroup;
+	struct throtl_grp *tg = NULL;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(current, blkio_subsys_id);
+	tg = throtl_find_alloc_tg(td, cgroup);
+	if (!tg)
+		tg = &td->root_tg;
+	rcu_read_unlock();
+	return tg;
+}
+
+static struct throtl_grp *throtl_rb_first(struct throtl_rb_root *root)
+{
+	/* Service tree is empty */
+	if (!root->count)
+		return NULL;
+
+	if (!root->left)
+		root->left = rb_first(&root->rb);
+
+	if (root->left)
+		return rb_entry_tg(root->left);
+
+	return NULL;
+}
+
+static void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+
+static void throtl_rb_erase(struct rb_node *n, struct throtl_rb_root *root)
+{
+	if (root->left == n)
+		root->left = NULL;
+	rb_erase_init(n, &root->rb);
+	--root->count;
+}
+
+static void update_min_dispatch_time(struct throtl_rb_root *st)
+{
+	struct throtl_grp *tg;
+
+	tg = throtl_rb_first(st);
+	if (!tg)
+		return;
+
+	st->min_disptime = tg->disptime;
+}
+
+static void
+tg_service_tree_add(struct throtl_rb_root *st, struct throtl_grp *tg)
+{
+	struct rb_node **node = &st->rb.rb_node;
+	struct rb_node *parent = NULL;
+	struct throtl_grp *__tg;
+	unsigned long key = tg->disptime;
+	int left = 1;
+
+	while (*node != NULL) {
+		parent = *node;
+		__tg = rb_entry_tg(parent);
+
+		if (time_before(key, __tg->disptime))
+			node = &parent->rb_left;
+		else {
+			node = &parent->rb_right;
+			left = 0;
+		}
+	}
+
+	if (left)
+		st->left = &tg->rb_node;
+
+	rb_link_node(&tg->rb_node, parent, node);
+	rb_insert_color(&tg->rb_node, &st->rb);
+}
+
+static void __throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	struct throtl_rb_root *st = &td->tg_service_tree;
+
+	tg_service_tree_add(st, tg);
+	throtl_mark_tg_on_rr(tg);
+	st->count++;
+}
+
+static void throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	if (!throtl_tg_on_rr(tg))
+		__throtl_enqueue_tg(td, tg);
+}
+
+static void __throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	throtl_rb_erase(&tg->rb_node, &td->tg_service_tree);
+	throtl_clear_tg_on_rr(tg);
+}
+
+static void throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	if (throtl_tg_on_rr(tg))
+		__throtl_dequeue_tg(td, tg);
+}
+
+static void throtl_schedule_next_dispatch(struct throtl_data *td)
+{
+	struct throtl_rb_root *st = &td->tg_service_tree;
+
+	/*
+	 * If there are more bios pending, schedule more work.
+	 */
+	if (!total_nr_queued(td))
+		return;
+
+	BUG_ON(!st->count);
+
+	update_min_dispatch_time(st);
+
+	if (time_before_eq(st->min_disptime, jiffies))
+		throtl_schedule_delayed_work(td->queue, 0);
+	else
+		throtl_schedule_delayed_work(td->queue,
+				(st->min_disptime - jiffies));
+}
+
+static inline void
+throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+	tg->bytes_disp[rw] = 0;
+	tg->slice_start[rw] = jiffies;
+	tg->slice_end[rw] = jiffies + throtl_slice;
+	throtl_log_tg(td, tg, "[%c] new slice start=%lu end=%lu jiffies=%lu",
+			rw == READ ? 'R' : 'W', tg->slice_start[rw],
+			tg->slice_end[rw], jiffies);
+}
+
+static inline void throtl_extend_slice(struct throtl_data *td,
+		struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
+{
+	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+	throtl_log_tg(td, tg, "[%c] extend slice start=%lu end=%lu jiffies=%lu",
+			rw == READ ? 'R' : 'W', tg->slice_start[rw],
+			tg->slice_end[rw], jiffies);
+}
+
+/* Determine if previously allocated or extended slice is complete or not */
+static bool
+throtl_slice_used(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+	if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
+		return 0;
+
+	return 1;
+}
+
+/* Trim the used slices and adjust slice start accordingly */
+static inline void
+throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+	unsigned long nr_slices, bytes_trim, time_elapsed;
+
+	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
+
+	/*
+	 * If bps are unlimited (-1), then time slice don't get
+	 * renewed. Don't try to trim the slice if slice is used. A new
+	 * slice will start when appropriate.
+	 */
+	if (throtl_slice_used(td, tg, rw))
+		return;
+
+	time_elapsed = jiffies - tg->slice_start[rw];
+
+	nr_slices = time_elapsed / throtl_slice;
+
+	if (!nr_slices)
+		return;
+
+	bytes_trim = (tg->bps[rw] * throtl_slice * nr_slices)/HZ;
+
+	if (!bytes_trim)
+		return;
+
+	if (tg->bytes_disp[rw] >= bytes_trim)
+		tg->bytes_disp[rw] -= bytes_trim;
+	else
+		tg->bytes_disp[rw] = 0;
+
+	tg->slice_start[rw] += nr_slices * throtl_slice;
+
+	throtl_log_tg(td, tg, "[%c] trim slice nr=%lu bytes=%lu"
+			" start=%lu end=%lu jiffies=%lu",
+			rw == READ ? 'R' : 'W', nr_slices, bytes_trim,
+			tg->slice_start[rw], tg->slice_end[rw], jiffies);
+}
+
+/*
+ * Returns whether one can dispatch a bio or not. Also returns approx number
+ * of jiffies to wait before this bio is with-in IO rate and can be dispatched
+ */
+static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg,
+				struct bio *bio, unsigned long *wait)
+{
+	bool rw = bio_data_dir(bio);
+	u64 bytes_allowed, extra_bytes;
+	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
+
+	/*
+	 * Currently whole state machine of group depends on first bio
+	 * queued in the group bio list. So one should not be calling
+	 * this function with a different bio if there are other bios
+	 * queued.
+	 */
+	BUG_ON(tg->nr_queued[rw] && bio != bio_list_peek(&tg->bio_lists[rw]));
+
+	/* If tg->bps = -1, then BW is unlimited */
+	if (tg->bps[rw] == -1) {
+		if (wait)
+			*wait = 0;
+		return 1;
+	}
+
+	/*
+	 * If previous slice expired, start a new one otherwise renew/extend
+	 * existing slice to make sure it is at least throtl_slice interval
+	 * long since now.
+	 */
+	if (throtl_slice_used(td, tg, rw))
+		throtl_start_new_slice(td, tg, rw);
+	else {
+		if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
+			throtl_extend_slice(td, tg, rw, jiffies + throtl_slice);
+	}
+
+	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
+
+	/* Slice has just started. Consider one slice interval */
+	if (!jiffy_elapsed)
+		jiffy_elapsed_rnd = throtl_slice;
+
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+
+	bytes_allowed = (tg->bps[rw] * jiffies_to_msecs(jiffy_elapsed_rnd))
+				/ MSEC_PER_SEC;
+
+	if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) {
+		if (wait)
+			*wait = 0;
+		return 1;
+	}
+
+	/* Calc approx time to dispatch */
+	extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed;
+	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+
+	if (!jiffy_wait)
+		jiffy_wait = 1;
+
+	/*
+	 * This wait time is without taking into consideration the rounding
+	 * up we did. Add that time also.
+	 */
+	jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
+
+	if (wait)
+		*wait = jiffy_wait;
+
+	if (time_before(tg->slice_end[rw], jiffies + jiffy_wait))
+		throtl_extend_slice(td, tg, rw, jiffies + jiffy_wait);
+
+	return 0;
+}
+
+static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
+{
+	bool rw = bio_data_dir(bio);
+	bool sync = bio->bi_rw & REQ_SYNC;
+
+	/* Charge the bio to the group */
+	tg->bytes_disp[rw] += bio->bi_size;
+
+	/*
+	 * TODO: This will take blkg->stats_lock. Figure out a way
+	 * to avoid this cost.
+	 */
+	blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync);
+
+}
+
+static void throtl_add_bio_tg(struct throtl_data *td, struct throtl_grp *tg,
+			struct bio *bio)
+{
+	bool rw = bio_data_dir(bio);
+
+	bio_list_add(&tg->bio_lists[rw], bio);
+	/* Take a bio reference on tg */
+	throtl_ref_get_tg(tg);
+	tg->nr_queued[rw]++;
+	td->nr_queued[rw]++;
+	throtl_enqueue_tg(td, tg);
+}
+
+static void tg_update_disptime(struct throtl_data *td, struct throtl_grp *tg)
+{
+	unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
+	struct bio *bio;
+
+	if ((bio = bio_list_peek(&tg->bio_lists[READ])))
+		tg_may_dispatch(td, tg, bio, &read_wait);
+
+	if ((bio = bio_list_peek(&tg->bio_lists[WRITE])))
+		tg_may_dispatch(td, tg, bio, &write_wait);
+
+	min_wait = min(read_wait, write_wait);
+	disptime = jiffies + min_wait;
+
+	/*
+	 * If group is already on active tree, then update dispatch time
+	 * only if it is lesser than existing dispatch time. Otherwise
+	 * always update the dispatch time
+	 */
+
+	if (throtl_tg_on_rr(tg) && time_before(disptime, tg->disptime))
+		return;
+
+	/* Update dispatch time */
+	throtl_dequeue_tg(td, tg);
+	tg->disptime = disptime;
+	throtl_enqueue_tg(td, tg);
+}
+
+static void tg_dispatch_one_bio(struct throtl_data *td, struct throtl_grp *tg,
+				bool rw, struct bio_list *bl)
+{
+	struct bio *bio;
+
+	bio = bio_list_pop(&tg->bio_lists[rw]);
+	tg->nr_queued[rw]--;
+	/* Drop bio reference on tg */
+	throtl_put_tg(tg);
+
+	BUG_ON(td->nr_queued[rw] <= 0);
+	td->nr_queued[rw]--;
+
+	throtl_charge_bio(tg, bio);
+	bio_list_add(bl, bio);
+	bio->bi_rw |= REQ_THROTTLED;
+
+	throtl_trim_slice(td, tg, rw);
+}
+
+static int throtl_dispatch_tg(struct throtl_data *td, struct throtl_grp *tg,
+				struct bio_list *bl)
+{
+	unsigned int nr_reads = 0, nr_writes = 0;
+	unsigned int max_nr_reads = throtl_grp_quantum*3/4;
+	unsigned int max_nr_writes = throtl_grp_quantum - nr_reads;
+	struct bio *bio;
+
+	/* Try to dispatch 75% READS and 25% WRITES */
+
+	while ((bio = bio_list_peek(&tg->bio_lists[READ]))
+		&& tg_may_dispatch(td, tg, bio, NULL)) {
+
+		tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl);
+		nr_reads++;
+
+		if (nr_reads >= max_nr_reads)
+			break;
+	}
+
+	while ((bio = bio_list_peek(&tg->bio_lists[WRITE]))
+		&& tg_may_dispatch(td, tg, bio, NULL)) {
+
+		tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl);
+		nr_writes++;
+
+		if (nr_writes >= max_nr_writes)
+			break;
+	}
+
+	return nr_reads + nr_writes;
+}
+
+static int throtl_select_dispatch(struct throtl_data *td, struct bio_list *bl)
+{
+	unsigned int nr_disp = 0;
+	struct throtl_grp *tg;
+	struct throtl_rb_root *st = &td->tg_service_tree;
+
+	while (1) {
+		tg = throtl_rb_first(st);
+
+		if (!tg)
+			break;
+
+		if (time_before(jiffies, tg->disptime))
+			break;
+
+		throtl_dequeue_tg(td, tg);
+
+		nr_disp += throtl_dispatch_tg(td, tg, bl);
+
+		if (tg->nr_queued[0] || tg->nr_queued[1]) {
+			tg_update_disptime(td, tg);
+			throtl_enqueue_tg(td, tg);
+		}
+
+		if (nr_disp >= throtl_quantum)
+			break;
+	}
+
+	return nr_disp;
+}
+
+/* Dispatch throttled bios. Should be called without queue lock held. */
+static int throtl_dispatch(struct request_queue *q)
+{
+	struct throtl_data *td = q->td;
+	unsigned int nr_disp = 0;
+	struct bio_list bio_list_on_stack;
+	struct bio *bio;
+
+	spin_lock_irq(q->queue_lock);
+
+	if (!total_nr_queued(td))
+		goto out;
+
+	bio_list_init(&bio_list_on_stack);
+
+	throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u",
+			total_nr_queued(td), td->nr_queued[READ],
+			td->nr_queued[WRITE]);
+
+	nr_disp = throtl_select_dispatch(td, &bio_list_on_stack);
+
+	if (nr_disp)
+		throtl_log(td, "bios disp=%u", nr_disp);
+
+	throtl_schedule_next_dispatch(td);
+out:
+	spin_unlock_irq(q->queue_lock);
+
+	/*
+	 * If we dispatched some requests, unplug the queue to make sure
+	 * immediate dispatch
+	 */
+	if (nr_disp) {
+		while((bio = bio_list_pop(&bio_list_on_stack)))
+			generic_make_request(bio);
+		blk_unplug(q);
+	}
+	return nr_disp;
+}
+
+void blk_throtl_work(struct work_struct *work)
+{
+	struct throtl_data *td = container_of(work, struct throtl_data,
+					throtl_work.work);
+	struct request_queue *q = td->queue;
+
+	throtl_dispatch(q);
+}
+
+/* Call with queue lock held */
+void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
+{
+
+	struct throtl_data *td = q->td;
+	struct delayed_work *dwork = &td->throtl_work;
+
+	if (total_nr_queued(td) > 0) {
+		/*
+		 * We might have a work scheduled to be executed in future.
+		 * Cancel that and schedule a new one.
+		 */
+		__cancel_delayed_work(dwork);
+		kblockd_schedule_delayed_work(q, dwork, delay);
+		throtl_log(td, "schedule work. delay=%lu jiffies=%lu",
+				delay, jiffies);
+	}
+}
+EXPORT_SYMBOL(throtl_schedule_delayed_work);
+
+static void
+throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	/* Something wrong if we are trying to remove same group twice */
+	BUG_ON(hlist_unhashed(&tg->tg_node));
+
+	hlist_del_init(&tg->tg_node);
+
+	/*
+	 * Put the reference taken at the time of creation so that when all
+	 * queues are gone, group can be destroyed.
+	 */
+	throtl_put_tg(tg);
+	td->nr_undestroyed_grps--;
+}
+
+static void throtl_release_tgs(struct throtl_data *td)
+{
+	struct hlist_node *pos, *n;
+	struct throtl_grp *tg;
+
+	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
+		/*
+		 * If cgroup removal path got to blk_group first and removed
+		 * it from cgroup list, then it will take care of destroying
+		 * cfqg also.
+		 */
+		if (!blkiocg_del_blkio_group(&tg->blkg))
+			throtl_destroy_tg(td, tg);
+	}
+}
+
+static void throtl_td_free(struct throtl_data *td)
+{
+	kfree(td);
+}
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid throtl_data pointer as long as we are
+ * rcu read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if queue was going away, cgroup deltion
+ * path got to it first.
+ */
+void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+	unsigned long flags;
+	struct throtl_data *td = key;
+
+	spin_lock_irqsave(td->queue->queue_lock, flags);
+	throtl_destroy_tg(td, tg_of_blkg(blkg));
+	spin_unlock_irqrestore(td->queue->queue_lock, flags);
+}
+
+static void throtl_update_blkio_group_read_bps (struct blkio_group *blkg,
+			u64 read_bps)
+{
+	tg_of_blkg(blkg)->bps[READ] = read_bps;
+}
+
+static void throtl_update_blkio_group_write_bps (struct blkio_group *blkg,
+			u64 write_bps)
+{
+	tg_of_blkg(blkg)->bps[WRITE] = write_bps;
+}
+
+void throtl_shutdown_timer_wq(struct request_queue *q)
+{
+	struct throtl_data *td = q->td;
+
+	cancel_delayed_work_sync(&td->throtl_work);
+}
+
+static struct blkio_policy_type blkio_policy_throtl = {
+	.ops = {
+		.blkio_unlink_group_fn = throtl_unlink_blkio_group,
+		.blkio_update_group_read_bps_fn =
+					throtl_update_blkio_group_read_bps,
+		.blkio_update_group_write_bps_fn =
+					throtl_update_blkio_group_write_bps,
+	},
+};
+
+int blk_throtl_bio(struct request_queue *q, struct bio **biop)
+{
+	struct throtl_data *td = q->td;
+	struct throtl_grp *tg;
+	struct bio *bio = *biop;
+	bool rw = bio_data_dir(bio), update_disptime = true;
+
+	if (bio->bi_rw & REQ_THROTTLED) {
+		bio->bi_rw &= ~REQ_THROTTLED;
+		return 0;
+	}
+
+	spin_lock_irq(q->queue_lock);
+	tg = throtl_get_tg(td);
+
+	if (tg->nr_queued[rw]) {
+		/*
+		 * There is already another bio queued in same dir. No
+		 * need to update dispatch time.
+		 */
+		update_disptime = false;
+		goto queue_bio;
+	}
+
+	/* Bio is with-in rate limit of group */
+	if (tg_may_dispatch(td, tg, bio, NULL)) {
+		throtl_charge_bio(tg, bio);
+		goto out;
+	}
+
+queue_bio:
+	throtl_log_tg(td, tg, "[%c] bio. disp=%u sz=%u bps=%llu"
+			" queued=%d/%d", rw == READ ? 'R' : 'W',
+			tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
+			tg->nr_queued[READ], tg->nr_queued[WRITE]);
+
+	throtl_add_bio_tg(q->td, tg, bio);
+	*biop = NULL;
+
+	if (update_disptime) {
+		tg_update_disptime(td, tg);
+		throtl_schedule_next_dispatch(td);
+	}
+
+out:
+	spin_unlock_irq(q->queue_lock);
+	return 0;
+}
+
+int blk_throtl_init(struct request_queue *q)
+{
+	struct throtl_data *td;
+	struct throtl_grp *tg;
+
+	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
+	if (!td)
+		return -ENOMEM;
+
+	INIT_HLIST_HEAD(&td->tg_list);
+	td->tg_service_tree = THROTL_RB_ROOT;
+
+	/* Init root group */
+	tg = &td->root_tg;
+	INIT_HLIST_NODE(&tg->tg_node);
+	RB_CLEAR_NODE(&tg->rb_node);
+	bio_list_init(&tg->bio_lists[0]);
+	bio_list_init(&tg->bio_lists[1]);
+
+	/* Practically unlimited BW */
+	tg->bps[0] = tg->bps[1] = -1;
+	atomic_set(&tg->ref, 1);
+
+	INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
+
+	rcu_read_lock();
+	blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td,
+					0, BLKIO_POLICY_THROTL);
+	rcu_read_unlock();
+
+	/* Attach throtl data to request queue */
+	td->queue = q;
+	q->td = td;
+	return 0;
+}
+
+void blk_throtl_exit(struct request_queue *q)
+{
+	struct throtl_data *td = q->td;
+	bool wait = false;
+
+	BUG_ON(!td);
+
+	throtl_shutdown_timer_wq(q);
+
+	spin_lock_irq(q->queue_lock);
+	throtl_release_tgs(td);
+	blkiocg_del_blkio_group(&td->root_tg.blkg);
+
+	/* If there are other groups */
+	if (td->nr_undestroyed_grps >= 1)
+		wait = true;
+
+	spin_unlock_irq(q->queue_lock);
+
+	/*
+	 * Wait for tg->blkg->key accessors to exit their grace periods.
+	 * Do this wait only if there are other undestroyed groups out
+	 * there (other than root group). This can happen if cgroup deletion
+	 * path claimed the responsibility of cleaning up a group before
+	 * queue cleanup code get to the group.
+	 *
+	 * Do not call synchronize_rcu() unconditionally as there are drivers
+	 * which create/delete request queue hundreds of times during scan/boot
+	 * and synchronize_rcu() can take significant time and slow down boot.
+	 */
+	if (wait)
+		synchronize_rcu();
+	throtl_td_free(td);
+}
+
+static int __init throtl_init(void)
+{
+	blkio_policy_register(&blkio_policy_throtl);
+	return 0;
+}
+
+module_init(throtl_init);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ca83a97c971..10a0c291b55 100644
--- a/include/linux/blk_types.h
+++ b/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)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 780824edac1..1341df5806d 100644
--- a/include/linux/blkdev.h
+++ b/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) \
diff --git a/init/Kconfig b/init/Kconfig
index 2de5b1cbadd..950ba26f723 100644
--- a/init/Kconfig
+++ b/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.
 
-- 
cgit v1.2.3-70-g09d2


From 892b6f90db81cccb723d5d92f4fddc2d68b206e1 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Wed, 13 Oct 2010 21:18:03 +0200
Subject: block: Ensure physical block size is unsigned int

Physical block size was declared unsigned int to accomodate the maximum
size reported by READ CAPACITY(16).  Make sure we use the right type in
the related functions.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-settings.c   | 2 +-
 include/linux/blkdev.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index a3600a7ab8b..315b88c8cbb 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -344,7 +344,7 @@ EXPORT_SYMBOL(blk_queue_logical_block_size);
  *   hardware can operate on without reverting to read-modify-write
  *   operations.
  */
-void blk_queue_physical_block_size(struct request_queue *q, unsigned short size)
+void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
 {
 	q->limits.physical_block_size = size;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1341df5806d..8f3dd981b97 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -860,7 +860,7 @@ extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
-extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
@@ -1013,7 +1013,7 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q)
 	return q->limits.physical_block_size;
 }
 
-static inline int bdev_physical_block_size(struct block_device *bdev)
+static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
 {
 	return queue_physical_block_size(bdev_get_queue(bdev));
 }
-- 
cgit v1.2.3-70-g09d2


From 7681bfeeccff5efa9eb29bf09249a3c400b15327 Mon Sep 17 00:00:00 2001
From: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Date: Tue, 19 Oct 2010 09:05:00 +0200
Subject: block: fix accounting bug on cross partition merges

/proc/diskstats would display a strange output as follows.

$ cat /proc/diskstats |grep sda
   8       0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089
   8       1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691
                                                ~~~~~~~~~~
   8       2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390
   8       3 sda3 54 487 2188 92 0 0 0 0 0 88 92
   8       4 sda4 4 0 8 0 0 0 0 0 0 0 0
   8       5 sda5 81 2027 2130 138 0 0 0 0 0 87 137

Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is
merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE.

The detailed root cause is as follows.

Assuming that there are two partition, sda1 and sda2.

1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight
   is 0 and sda2's one is 1.

        | hd_struct->in_flight
   ---------------------------
   sda1 |          0
   sda2 |          1
   ---------------------------

2. A bio belongs to sda1 is issued and is merged into the request mentioned on
   step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed
   from sda2 region to sda1 region. However the two partition's
   hd_struct->in_flight are not changed.

        | hd_struct->in_flight
   ---------------------------
   sda1 |          0
   sda2 |          1
   ---------------------------

3. The request is finished and blk_account_io_done() is called. In this case,
   sda2's hd_struct->in_flight, not a sda1's one, is decremented.

        | hd_struct->in_flight
   ---------------------------
   sda1 |         -1
   sda2 |          1
   ---------------------------

The patch fixes the problem by caching the partition lookup
inside the request structure, hence making sure that the increment
and decrement will always happen on the same partition struct. This
also speeds up IO with accounting enabled, since it cuts down on
the number of lookups we have to do.

When reloading partition tables, quiesce IO to ensure that no
request references to the partition struct exists. When it is safe
to free the partition table, the IO for that device is restarted
again.

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c         | 24 ++++++++++++++++--------
 block/blk-merge.c        |  2 +-
 block/blk.h              |  4 ----
 block/genhd.c            | 14 ++++++++++++++
 fs/partitions/check.c    | 12 ++++++++++++
 include/linux/blkdev.h   |  1 +
 include/linux/elevator.h |  2 ++
 include/linux/genhd.h    |  1 +
 8 files changed, 47 insertions(+), 13 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 797d5095eb8..ddc68332d65 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,13 +64,15 @@ static void drive_stat_acct(struct request *rq, int new_io)
 		return;
 
 	cpu = part_stat_lock();
-	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 
-	if (!new_io)
+	if (!new_io) {
+		part = rq->part;
 		part_stat_inc(cpu, part, merges[rw]);
-	else {
+	} else {
+		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 		part_round_stats(cpu, part);
 		part_inc_in_flight(part, rw);
+		rq->part = part;
 	}
 
 	part_stat_unlock();
@@ -128,6 +130,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->ref_count = 1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
+	rq->part = NULL;
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -804,11 +807,16 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	rl->starved[is_sync] = 0;
 
 	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
-	if (priv)
+	if (priv) {
 		rl->elvpriv++;
 
-	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		/*
+		 * Don't do stats for non-priv requests
+		 */
+		if (blk_queue_io_stat(q))
+			rw_flags |= REQ_IO_STAT;
+	}
+
 	spin_unlock_irq(q->queue_lock);
 
 	rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
@@ -1777,7 +1785,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1797,7 +1805,7 @@ static void blk_account_io_done(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 6a725461654..38ff234012a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 
 		part_round_stats(cpu, part);
 		part_dec_in_flight(part, rq_data_dir(req));
diff --git a/block/blk.h b/block/blk.h
index 6738831ba44..1340cce5721 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -110,10 +110,6 @@ void blk_queue_congestion_threshold(struct request_queue *q);
 
 int blk_dev_init(void);
 
-void elv_quiesce_start(struct request_queue *q);
-void elv_quiesce_end(struct request_queue *q);
-
-
 /*
  * Return the threshold (number of used requests) at which the queue is
  * considered to be congested.  It include a little hysteresis to keep the
diff --git a/block/genhd.c b/block/genhd.c
index 7923e720ddf..8313834596d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -932,8 +932,15 @@ static void disk_free_ptbl_rcu_cb(struct rcu_head *head)
 {
 	struct disk_part_tbl *ptbl =
 		container_of(head, struct disk_part_tbl, rcu_head);
+	struct gendisk *disk = ptbl->disk;
+	struct request_queue *q = disk->queue;
+	unsigned long flags;
 
 	kfree(ptbl);
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	elv_quiesce_end(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 /**
@@ -951,11 +958,17 @@ static void disk_replace_part_tbl(struct gendisk *disk,
 				  struct disk_part_tbl *new_ptbl)
 {
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
+	struct request_queue *q = disk->queue;
 
 	rcu_assign_pointer(disk->part_tbl, new_ptbl);
 
 	if (old_ptbl) {
 		rcu_assign_pointer(old_ptbl->last_lookup, NULL);
+
+		spin_lock_irq(q->queue_lock);
+		elv_quiesce_start(q);
+		spin_unlock_irq(q->queue_lock);
+
 		call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb);
 	}
 }
@@ -996,6 +1009,7 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 		return -ENOMEM;
 
 	new_ptbl->len = target;
+	new_ptbl->disk = disk;
 
 	for (i = 0; i < len; i++)
 		rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]);
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 6dfbee03ccc..30f46c2cb9d 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -365,17 +365,25 @@ struct device_type part_type = {
 static void delete_partition_rcu_cb(struct rcu_head *head)
 {
 	struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
+	struct gendisk *disk = part_to_disk(part);
+	struct request_queue *q = disk->queue;
+	unsigned long flags;
 
 	part->start_sect = 0;
 	part->nr_sects = 0;
 	part_stat_set_all(part, 0);
 	put_device(part_to_dev(part));
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	elv_quiesce_end(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 void delete_partition(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = disk->part_tbl;
 	struct hd_struct *part;
+	struct request_queue *q = disk->queue;
 
 	if (partno >= ptbl->len)
 		return;
@@ -390,6 +398,10 @@ void delete_partition(struct gendisk *disk, int partno)
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
 
+	spin_lock_irq(q->queue_lock);
+	elv_quiesce_start(q);
+	spin_unlock_irq(q->queue_lock);
+
 	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8f3dd981b97..16f7f1be1ac 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -115,6 +115,7 @@ struct request {
 	void *elevator_private3;
 
 	struct gendisk *rq_disk;
+	struct hd_struct *part;
 	unsigned long start_time;
 #ifdef CONFIG_BLK_CGROUP
 	unsigned long long start_time_ns;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 2c958f4fce1..df1ee866d71 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -121,6 +121,8 @@ extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *, struct request *, gfp_t);
 extern void elv_put_request(struct request_queue *, struct request *);
 extern void elv_drain_elevator(struct request_queue *);
+extern void elv_quiesce_start(struct request_queue *);
+extern void elv_quiesce_end(struct request_queue *);
 
 /*
  * io scheduler registration
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 66e26b5a153..57647ecfc1b 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -140,6 +140,7 @@ struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
 	struct hd_struct *last_lookup;
+	struct gendisk *disk;
 	struct hd_struct *part[];
 };
 
-- 
cgit v1.2.3-70-g09d2