Re: [PATCH] IO Controller: Add per-device weight and ioprio_class handling

[Gui Jianfeng <guijianfeng@cn.fujitsu.com>]

Hi Vivek,

This patch enables per-cgroup per-device weight and ioprio_class handling.
A new cgroup interface "policy" is introduced. You can make use of this 
file to configure weight and ioprio_class for each device in a given cgroup.
The original "weight" and "ioprio_class" files are still available. If you
don't do special configuration for a particular device, "weight" and 
"ioprio_class" are used as default values in this device.

You can use the following format to play with the new interface.
#echo DEV:weight:ioprio_class > /patch/to/cgroup/policy
weight=0 means removing the policy for DEV.

Examples:
Configure weight=300 ioprio_class=2 on /dev/hdb in this cgroup
# echo /dev/hdb:300:2 > io.policy
# cat io.policy
dev weight class
/dev/hdb 300 2

Configure weight=500 ioprio_class=1 on /dev/hda in this cgroup
# echo /dev/hda:500:1 > io.policy
# cat io.policy
dev weight class
/dev/hda 500 1
/dev/hdb 300 2

Remove the policy for /dev/hda in this cgroup
# echo /dev/hda:0:1 > io.policy
# cat io.policy
dev weight class
/dev/hdb 300 2

Changelog (v1 -> v2)
- Rename some structures
- Use spin_lock_irqsave() and spin_lock_irqrestore() version to prevent
  from enabling the interrupts unconditionally.
- Fix policy setup bug when switching to another io scheduler.
- If a policy is available for a specific device, don't update weight and
  io class when writing "weight" and "iprio_class".
- Fix a bug when parsing policy string.

Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
---
 block/elevator-fq.c |  258 +++++++++++++++++++++++++++++++++++++++++++++++++--
 block/elevator-fq.h |   12 +++
 2 files changed, 261 insertions(+), 9 deletions(-)

diff --git a/block/elevator-fq.c b/block/elevator-fq.c
index 69435ab..43b30a4 100644
--- a/block/elevator-fq.c
+++ b/block/elevator-fq.c
@@ -12,6 +12,9 @@
 #include "elevator-fq.h"
 #include <linux/blktrace_api.h>
 #include <linux/biotrack.h>
+#include <linux/seq_file.h>
+#include <linux/genhd.h>
+
 
 /* Values taken from cfq */
 const int elv_slice_sync = HZ / 10;
@@ -1045,12 +1048,31 @@ struct io_group *io_lookup_io_group_current(struct request_queue *q)
 }
 EXPORT_SYMBOL(io_lookup_io_group_current);
 
-void io_group_init_entity(struct io_cgroup *iocg, struct io_group *iog)
+static struct io_policy_node *policy_search_node(const struct io_cgroup *iocg,
+						 dev_t dev);
+
+void io_group_init_entity(struct io_cgroup *iocg, struct io_group *iog,
+			  dev_t dev)
 {
 	struct io_entity *entity = &iog->entity;
+	struct io_policy_node *pn;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iocg->lock, flags);
+	pn = policy_search_node(iocg, dev);
+	if (pn) {
+		entity->weight = pn->weight;
+		entity->new_weight = pn->weight;
+		entity->ioprio_class = pn->ioprio_class;
+		entity->new_ioprio_class = pn->ioprio_class;
+	} else {
+		entity->weight = iocg->weight;
+		entity->new_weight = iocg->weight;
+		entity->ioprio_class = iocg->ioprio_class;
+		entity->new_ioprio_class = iocg->ioprio_class;
+	}
+	spin_unlock_irqrestore(&iocg->lock, flags);
 
-	entity->weight = entity->new_weight = iocg->weight;
-	entity->ioprio_class = entity->new_ioprio_class = iocg->ioprio_class;
 	entity->ioprio_changed = 1;
 	entity->my_sched_data = &iog->sched_data;
 }
@@ -1114,6 +1136,7 @@ static int io_cgroup_##__VAR##_write(struct cgroup *cgroup,		\
 	struct io_cgroup *iocg;					\
 	struct io_group *iog;						\
 	struct hlist_node *n;						\
+	struct io_policy_node *pn;					\
 									\
 	if (val < (__MIN) || val > (__MAX))				\
 		return -EINVAL;						\
@@ -1126,6 +1149,9 @@ static int io_cgroup_##__VAR##_write(struct cgroup *cgroup,		\
 	spin_lock_irq(&iocg->lock);					\
 	iocg->__VAR = (unsigned long)val;				\
 	hlist_for_each_entry(iog, n, &iocg->group_data, group_node) {	\
+		pn = policy_search_node(iocg, iog->dev);		\
+		if (pn)							\
+			continue;					\
 		iog->entity.new_##__VAR = (unsigned long)val;		\
 		smp_wmb();						\
 		iog->entity.ioprio_changed = 1;				\
@@ -1237,7 +1263,7 @@ static u64 io_cgroup_disk_sectors_read(struct cgroup *cgroup,
  * to the root has already an allocated group on @bfqd.
  */
 struct io_group *io_group_chain_alloc(struct request_queue *q, void *key,
-					struct cgroup *cgroup)
+				      struct cgroup *cgroup, struct bio *bio)
 {
 	struct io_cgroup *iocg;
 	struct io_group *iog, *leaf = NULL, *prev = NULL;
@@ -1263,12 +1289,17 @@ struct io_group *io_group_chain_alloc(struct request_queue *q, void *key,
 		atomic_set(&iog->ref, 0);
 		iog->deleting = 0;
 
-		io_group_init_entity(iocg, iog);
-		iog->my_entity = &iog->entity;
 #ifdef CONFIG_DEBUG_GROUP_IOSCHED
 		iog->iocg_id = css_id(&iocg->css);
+		if (bio) {
+			struct gendisk *disk = bio->bi_bdev->bd_disk;
+			iog->dev = MKDEV(disk->major, disk->first_minor);
+		}
 #endif
 
+		io_group_init_entity(iocg, iog, iog->dev);
+		iog->my_entity = &iog->entity;
+
 		blk_init_request_list(&iog->rl);
 
 		if (leaf == NULL) {
@@ -1379,7 +1410,7 @@ void io_group_chain_link(struct request_queue *q, void *key,
  */
 struct io_group *io_find_alloc_group(struct request_queue *q,
 			struct cgroup *cgroup, struct elv_fq_data *efqd,
-			int create)
+			     int create, struct bio *bio)
 {
 	struct io_cgroup *iocg = cgroup_to_io_cgroup(cgroup);
 	struct io_group *iog = NULL;
@@ -1390,7 +1421,7 @@ struct io_group *io_find_alloc_group(struct request_queue *q,
 	if (iog != NULL || !create)
 		return iog;
 
-	iog = io_group_chain_alloc(q, key, cgroup);
+	iog = io_group_chain_alloc(q, key, cgroup, bio);
 	if (iog != NULL)
 		io_group_chain_link(q, key, cgroup, iog, efqd);
 
@@ -1489,7 +1520,7 @@ struct io_group *io_get_io_group_bio(struct request_queue *q, struct bio *bio,
 		goto out;
 	}
 
-	iog = io_find_alloc_group(q, cgroup, efqd, create);
+	iog = io_find_alloc_group(q, cgroup, efqd, create, bio);
 	if (!iog) {
 		if (create)
 			iog = efqd->root_group;
@@ -1549,8 +1580,209 @@ struct io_group *io_alloc_root_group(struct request_queue *q,
 	return iog;
 }
 
+static int io_cgroup_policy_read(struct cgroup *cgrp, struct cftype *cft,
+				  struct seq_file *m)
+{
+	struct io_cgroup *iocg;
+	struct io_policy_node *pn;
+
+	iocg = cgroup_to_io_cgroup(cgrp);
+
+	if (list_empty(&iocg->policy_list))
+		goto out;
+
+	seq_printf(m, "dev weight class\n");
+
+	spin_lock_irq(&iocg->lock);
+	list_for_each_entry(pn, &iocg->policy_list, node) {
+		seq_printf(m, "%s %lu %lu\n", pn->dev_name,
+			   pn->weight, pn->ioprio_class);
+	}
+	spin_unlock_irq(&iocg->lock);
+out:
+	return 0;
+}
+
+static inline void policy_insert_node(struct io_cgroup *iocg,
+					  struct io_policy_node *pn)
+{
+	list_add(&pn->node, &iocg->policy_list);
+}
+
+/* Must be called with iocg->lock held */
+static inline void policy_delete_node(struct io_policy_node *pn)
+{
+	list_del(&pn->node);
+}
+
+/* Must be called with iocg->lock held */
+static struct io_policy_node *policy_search_node(const struct io_cgroup *iocg,
+						 dev_t dev)
+{
+	struct io_policy_node *pn;
+
+	if (list_empty(&iocg->policy_list))
+		return NULL;
+
+	list_for_each_entry(pn, &iocg->policy_list, node) {
+		if (pn->dev == dev)
+			return pn;
+	}
+
+	return NULL;
+}
+
+static int devname_to_devnum(const char *buf, dev_t *dev)
+{
+	struct block_device *bdev;
+	struct gendisk *disk;
+	int part;
+
+	bdev = lookup_bdev(buf);
+	if (IS_ERR(bdev))
+		return -ENODEV;
+
+	disk = get_gendisk(bdev->bd_dev, &part);
+	*dev = MKDEV(disk->major, disk->first_minor);
+	bdput(bdev);
+
+	return 0;
+}
+
+static int policy_parse_and_set(char *buf, struct io_policy_node *newpn)
+{
+	char *s[3], *p;
+	int ret;
+	int i = 0;
+
+	memset(s, 0, sizeof(s));
+	while ((p = strsep(&buf, ":")) != NULL) {
+		if (!*p)
+			continue;
+		s[i++] = p;
+	}
+
+	ret = devname_to_devnum(s[0], &newpn->dev);
+	if (ret)
+		return ret;
+
+	strcpy(newpn->dev_name, s[0]);
+
+	if (s[1] == NULL)
+		return -EINVAL;
+
+	ret = strict_strtoul(s[1], 10, &newpn->weight);
+	if (ret || newpn->weight > WEIGHT_MAX)
+		return -EINVAL;
+
+	if (s[2] == NULL)
+		return -EINVAL;
+
+	ret = strict_strtoul(s[2], 10, &newpn->ioprio_class);
+	if (ret || newpn->ioprio_class < IOPRIO_CLASS_RT ||
+	    newpn->ioprio_class > IOPRIO_CLASS_IDLE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int io_cgroup_policy_write(struct cgroup *cgrp, struct cftype *cft,
+			    const char *buffer)
+{
+	struct io_cgroup *iocg;
+	struct io_policy_node *newpn, *pn;
+	char *buf;
+	int ret = 0;
+	int keep_newpn = 0;
+	struct hlist_node *n;
+	struct io_group *iog;
+
+	buf = kstrdup(buffer, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
+	if (!newpn) {
+		ret = -ENOMEM;
+		goto free_buf;
+	}
+
+	ret = policy_parse_and_set(buf, newpn);
+	if (ret)
+		goto free_newpn;
+
+	if (!cgroup_lock_live_group(cgrp)) {
+		ret = -ENODEV;
+		goto free_newpn;
+	}
+
+	iocg = cgroup_to_io_cgroup(cgrp);
+	spin_lock_irq(&iocg->lock);
+
+	pn = policy_search_node(iocg, newpn->dev);
+	if (!pn) {
+		if (newpn->weight != 0) {
+			policy_insert_node(iocg, newpn);
+			keep_newpn = 1;
+		}
+		goto update_io_group;
+	}
+
+	if (newpn->weight == 0) {
+		/* weight == 0 means deleteing a policy */
+		policy_delete_node(pn);
+		goto update_io_group;
+	}
+
+	pn->weight = newpn->weight;
+	pn->ioprio_class = newpn->ioprio_class;
+
+update_io_group:
+	hlist_for_each_entry(iog, n, &iocg->group_data, group_node) {
+		if (iog->dev == newpn->dev) {
+			if (newpn->weight) {
+				iog->entity.new_weight = newpn->weight;
+				iog->entity.new_ioprio_class =
+					newpn->ioprio_class;
+				/*
+				 * iog weight and ioprio_class updating
+				 * actually happens if ioprio_changed is set.
+				 * So ensure ioprio_changed is not set until
+				 * new weight and new ioprio_class are updated.
+				 */
+				smp_wmb();
+				iog->entity.ioprio_changed = 1;
+			} else {
+				iog->entity.new_weight = iocg->weight;
+				iog->entity.new_ioprio_class =
+					iocg->ioprio_class;
+
+				/* The same as above */
+				smp_wmb();
+				iog->entity.ioprio_changed = 1;
+			}
+		}
+	}
+	spin_unlock_irq(&iocg->lock);
+
+	cgroup_unlock();
+
+free_newpn:
+	if (!keep_newpn)
+		kfree(newpn);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
 struct cftype bfqio_files[] = {
 	{
+		.name = "policy",
+		.read_seq_string = io_cgroup_policy_read,
+		.write_string = io_cgroup_policy_write,
+		.max_write_len = 256,
+	},
+	{
 		.name = "weight",
 		.read_u64 = io_cgroup_weight_read,
 		.write_u64 = io_cgroup_weight_write,
@@ -1592,6 +1824,7 @@ struct cgroup_subsys_state *iocg_create(struct cgroup_subsys *subsys,
 	INIT_HLIST_HEAD(&iocg->group_data);
 	iocg->weight = IO_DEFAULT_GRP_WEIGHT;
 	iocg->ioprio_class = IO_DEFAULT_GRP_CLASS;
+	INIT_LIST_HEAD(&iocg->policy_list);
 
 	return &iocg->css;
 }
@@ -1750,6 +1983,7 @@ void iocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 	unsigned long flags, flags1;
 	int queue_lock_held = 0;
 	struct elv_fq_data *efqd;
+	struct io_policy_node *pn, *pntmp;
 
 	/*
 	 * io groups are linked in two lists. One list is maintained
@@ -1823,6 +2057,12 @@ locked:
 	BUG_ON(!hlist_empty(&iocg->group_data));
 
 	free_css_id(&io_subsys, &iocg->css);
+
+	list_for_each_entry_safe(pn, pntmp, &iocg->policy_list, node) {
+		policy_delete_node(pn);
+		kfree(pn);
+	}
+
 	kfree(iocg);
 }
 
diff --git a/block/elevator-fq.h b/block/elevator-fq.h
index db3a347..b1d97e6 100644
--- a/block/elevator-fq.h
+++ b/block/elevator-fq.h
@@ -250,9 +250,18 @@ struct io_group {
 
 #ifdef CONFIG_DEBUG_GROUP_IOSCHED
 	unsigned short iocg_id;
+	dev_t dev;
 #endif
 };
 
+struct io_policy_node {
+	struct list_head node;
+	char dev_name[32];
+	dev_t dev;
+	unsigned long weight;
+	unsigned long ioprio_class;
+};
+
 /**
  * struct bfqio_cgroup - bfq cgroup data structure.
  * @css: subsystem state for bfq in the containing cgroup.
@@ -269,6 +278,9 @@ struct io_cgroup {
 
 	unsigned long weight, ioprio_class;
 
+	/* list of io_policy_node */
+	struct list_head policy_list;
+
 	spinlock_t lock;
 	struct hlist_head group_data;
 };
-- 
1.5.4.rc3