---

yaml
---
r: 309197
b: refs/heads/master
c: 72e06c2
h: refs/heads/master
i:
  309195: 64f0a47
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 6ecf23afab13c39d3bb0e2d826d0984b0dd53733
+refs/heads/master: 72e06c255181537d0b3e1f657a9ed81655d745b1

trunk/block/blk-cgroup.c

@@ -17,8 +17,9 @@
 #include <linux/err.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
-#include "blk-cgroup.h"
 #include <linux/genhd.h>
+#include <linux/delay.h>
+#include "blk-cgroup.h"
 
 #define MAX_KEY_LEN 100
 
@@ -546,6 +547,37 @@ struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
 }
 EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
 
+void blkg_destroy_all(struct request_queue *q)
+{
+	struct blkio_policy_type *pol;
+
+	while (true) {
+		bool done = true;
+
+		spin_lock(&blkio_list_lock);
+		spin_lock_irq(q->queue_lock);
+
+		/*
+		 * clear_queue_fn() might return with non-empty group list
+		 * if it raced cgroup removal and lost.  cgroup removal is
+		 * guaranteed to make forward progress and retrying after a
+		 * while is enough.  This ugliness is scheduled to be
+		 * removed after locking update.
+		 */
+		list_for_each_entry(pol, &blkio_list, list)
+			if (!pol->ops.blkio_clear_queue_fn(q))
+				done = false;
+
+		spin_unlock_irq(q->queue_lock);
+		spin_unlock(&blkio_list_lock);
+
+		if (done)
+			break;
+
+		msleep(10);	/* just some random duration I like */
+	}
+}
+
 static void blkio_reset_stats_cpu(struct blkio_group *blkg)
 {
 	struct blkio_group_stats_cpu *stats_cpu;

trunk/block/blk-cgroup.h

@@ -203,7 +203,7 @@ extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 
 typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
-
+typedef bool (blkio_clear_queue_fn)(struct request_queue *q);
 typedef void (blkio_update_group_weight_fn) (void *key,
 			struct blkio_group *blkg, unsigned int weight);
 typedef void (blkio_update_group_read_bps_fn) (void * key,
@@ -217,6 +217,7 @@ typedef void (blkio_update_group_write_iops_fn) (void *key,
 
 struct blkio_policy_ops {
 	blkio_unlink_group_fn *blkio_unlink_group_fn;
+	blkio_clear_queue_fn *blkio_clear_queue_fn;
 	blkio_update_group_weight_fn *blkio_update_group_weight_fn;
 	blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn;
 	blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn;
@@ -233,6 +234,7 @@ struct blkio_policy_type {
 /* Blkio controller policy registration */
 extern void blkio_policy_register(struct blkio_policy_type *);
 extern void blkio_policy_unregister(struct blkio_policy_type *);
+extern void blkg_destroy_all(struct request_queue *q);
 
 static inline char *blkg_path(struct blkio_group *blkg)
 {
@@ -249,6 +251,7 @@ struct blkio_policy_type {
 
 static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
 static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
+static inline void blkg_destroy_all(struct request_queue *q) { }
 
 static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
 

trunk/block/blk-throttle.c

@@ -989,20 +989,28 @@ throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
 	td->nr_undestroyed_grps--;
 }
 
-static void throtl_release_tgs(struct throtl_data *td)
+static bool throtl_release_tgs(struct throtl_data *td, bool release_root)
 {
 	struct hlist_node *pos, *n;
 	struct throtl_grp *tg;
+	bool empty = true;
 
 	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
+		/* skip root? */
+		if (!release_root && tg == td->root_tg)
+			continue;
+
 		/*
 		 * 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);
+		else
+			empty = false;
 	}
+	return empty;
 }
 
 /*
@@ -1029,6 +1037,20 @@ void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg)
 	spin_unlock_irqrestore(td->queue->queue_lock, flags);
 }
 
+static bool throtl_clear_queue(struct request_queue *q)
+{
+	lockdep_assert_held(q->queue_lock);
+
+	/*
+	 * Clear tgs but leave the root one alone.  This is necessary
+	 * because root_tg is expected to be persistent and safe because
+	 * blk-throtl can never be disabled while @q is alive.  This is a
+	 * kludge to prepare for unified blkg.  This whole function will be
+	 * removed soon.
+	 */
+	return throtl_release_tgs(q->td, false);
+}
+
 static void throtl_update_blkio_group_common(struct throtl_data *td,
 				struct throtl_grp *tg)
 {
@@ -1097,6 +1119,7 @@ static void throtl_shutdown_wq(struct request_queue *q)
 static struct blkio_policy_type blkio_policy_throtl = {
 	.ops = {
 		.blkio_unlink_group_fn = throtl_unlink_blkio_group,
+		.blkio_clear_queue_fn = throtl_clear_queue,
 		.blkio_update_group_read_bps_fn =
 					throtl_update_blkio_group_read_bps,
 		.blkio_update_group_write_bps_fn =
@@ -1282,7 +1305,7 @@ void blk_throtl_exit(struct request_queue *q)
 	throtl_shutdown_wq(q);
 
 	spin_lock_irq(q->queue_lock);
-	throtl_release_tgs(td);
+	throtl_release_tgs(td, true);
 
 	/* If there are other groups */
 	if (td->nr_undestroyed_grps > 0)

trunk/block/cfq-iosched.c

@@ -1225,10 +1225,11 @@ static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	cfq_put_cfqg(cfqg);
 }
 
-static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+static bool cfq_release_cfq_groups(struct cfq_data *cfqd)
 {
 	struct hlist_node *pos, *n;
 	struct cfq_group *cfqg;
+	bool empty = true;
 
 	hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
 		/*
@@ -1238,7 +1239,10 @@ static void cfq_release_cfq_groups(struct cfq_data *cfqd)
 		 */
 		if (!cfq_blkiocg_del_blkio_group(&cfqg->blkg))
 			cfq_destroy_cfqg(cfqd, cfqg);
+		else
+			empty = false;
 	}
+	return empty;
 }
 
 /*
@@ -1265,6 +1269,19 @@ static void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
 }
 
+static struct elevator_type iosched_cfq;
+
+static bool cfq_clear_queue(struct request_queue *q)
+{
+	lockdep_assert_held(q->queue_lock);
+
+	/* shoot down blkgs iff the current elevator is cfq */
+	if (!q->elevator || q->elevator->type != &iosched_cfq)
+		return true;
+
+	return cfq_release_cfq_groups(q->elevator->elevator_data);
+}
+
 #else /* GROUP_IOSCHED */
 static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 {
@@ -3875,6 +3892,7 @@ static struct elevator_type iosched_cfq = {
 static struct blkio_policy_type blkio_policy_cfq = {
 	.ops = {
 		.blkio_unlink_group_fn =	cfq_unlink_blkio_group,
+		.blkio_clear_queue_fn = cfq_clear_queue,
 		.blkio_update_group_weight_fn =	cfq_update_blkio_group_weight,
 	},
 	.plid = BLKIO_POLICY_PROP,

trunk/block/elevator.c

@@ -38,6 +38,7 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-cgroup.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -894,6 +895,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	ioc_clear_queue(q);
 	spin_unlock_irq(q->queue_lock);
 
+	blkg_destroy_all(q);
+
 	/* allocate, init and register new elevator */
 	err = -ENOMEM;
 	q->elevator = elevator_alloc(q, new_e);