blkio: Introduce blkio controller cgroup interface

o This is basic implementation of blkio controller cgroup interface. This is
  the common interface visible to user space and should be used by different
  IO control policies as we implement those.

Signed-off-by: Vivek Goyal <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

block/Kconfig

@@ -77,6 +77,19 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_CGROUP
+	bool
+	depends on CGROUPS
+	default n
+	---help---
+	Generic block IO controller cgroup interface. This is the common
+	cgroup interface which should be used by various IO controlling
+	policies.
+
+	Currently, CFQ IO scheduler uses it to recognize task groups and
+	control disk bandwidth allocation (proportional time slice allocation)
+	to such task groups.
+
 endif # BLOCK
 
 config BLOCK_COMPAT

block/Kconfig.iosched

@@ -23,6 +23,7 @@ config IOSCHED_DEADLINE
 
 config IOSCHED_CFQ
 	tristate "CFQ I/O scheduler"
+	select BLK_CGROUP
 	default y
 	---help---
 	  The CFQ I/O scheduler tries to distribute bandwidth equally

block/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
+obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o

block/blk-cgroup.c

@@ -0,0 +1,177 @@
+/*
+ * Common Block IO controller cgroup interface
+ *
+ * Based on ideas and code from CFQ, CFS and BFQ:
+ * Copyright (C) 2003 Jens Axboe <[email protected]>
+ *
+ * Copyright (C) 2008 Fabio Checconi <[email protected]>
+ *		      Paolo Valente <[email protected]>
+ *
+ * Copyright (C) 2009 Vivek Goyal <[email protected]>
+ * 	              Nauman Rafique <[email protected]>
+ */
+#include <linux/ioprio.h>
+#include "blk-cgroup.h"
+
+struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
+
+struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
+{
+	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
+			    struct blkio_cgroup, css);
+}
+
+void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
+				struct blkio_group *blkg, void *key)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkcg->lock, flags);
+	rcu_assign_pointer(blkg->key, key);
+	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
+	spin_unlock_irqrestore(&blkcg->lock, flags);
+}
+
+int blkiocg_del_blkio_group(struct blkio_group *blkg)
+{
+	/* Implemented later */
+	return 0;
+}
+
+/* called under rcu_read_lock(). */
+struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
+{
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+	void *__key;
+
+	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		__key = blkg->key;
+		if (__key == key)
+			return blkg;
+	}
+
+	return NULL;
+}
+
+#define SHOW_FUNCTION(__VAR)						\
+static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
+				       struct cftype *cftype)		\
+{									\
+	struct blkio_cgroup *blkcg;					\
+									\
+	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
+	return (u64)blkcg->__VAR;					\
+}
+
+SHOW_FUNCTION(weight);
+#undef SHOW_FUNCTION
+
+static int
+blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
+{
+	struct blkio_cgroup *blkcg;
+
+	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
+		return -EINVAL;
+
+	blkcg = cgroup_to_blkio_cgroup(cgroup);
+	blkcg->weight = (unsigned int)val;
+	return 0;
+}
+
+struct cftype blkio_files[] = {
+	{
+		.name = "weight",
+		.read_u64 = blkiocg_weight_read,
+		.write_u64 = blkiocg_weight_write,
+	},
+};
+
+static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, subsys, blkio_files,
+				ARRAY_SIZE(blkio_files));
+}
+
+static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+
+	free_css_id(&blkio_subsys, &blkcg->css);
+	kfree(blkcg);
+}
+
+static struct cgroup_subsys_state *
+blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	struct blkio_cgroup *blkcg, *parent_blkcg;
+
+	if (!cgroup->parent) {
+		blkcg = &blkio_root_cgroup;
+		goto done;
+	}
+
+	/* Currently we do not support hierarchy deeper than two level (0,1) */
+	parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
+	if (css_depth(&parent_blkcg->css) > 0)
+		return ERR_PTR(-EINVAL);
+
+	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
+	if (!blkcg)
+		return ERR_PTR(-ENOMEM);
+
+	blkcg->weight = BLKIO_WEIGHT_DEFAULT;
+done:
+	spin_lock_init(&blkcg->lock);
+	INIT_HLIST_HEAD(&blkcg->blkg_list);
+
+	return &blkcg->css;
+}
+
+/*
+ * We cannot support shared io contexts, as we have no mean to support
+ * two tasks with the same ioc in two different groups without major rework
+ * of the main cic data structures.  For now we allow a task to change
+ * its cgroup only if it's the only owner of its ioc.
+ */
+static int blkiocg_can_attach(struct cgroup_subsys *subsys,
+				struct cgroup *cgroup, struct task_struct *tsk,
+				bool threadgroup)
+{
+	struct io_context *ioc;
+	int ret = 0;
+
+	/* task_lock() is needed to avoid races with exit_io_context() */
+	task_lock(tsk);
+	ioc = tsk->io_context;
+	if (ioc && atomic_read(&ioc->nr_tasks) > 1)
+		ret = -EINVAL;
+	task_unlock(tsk);
+
+	return ret;
+}
+
+static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
+				struct cgroup *prev, struct task_struct *tsk,
+				bool threadgroup)
+{
+	struct io_context *ioc;
+
+	task_lock(tsk);
+	ioc = tsk->io_context;
+	if (ioc)
+		ioc->cgroup_changed = 1;
+	task_unlock(tsk);
+}
+
+struct cgroup_subsys blkio_subsys = {
+	.name = "blkio",
+	.create = blkiocg_create,
+	.can_attach = blkiocg_can_attach,
+	.attach = blkiocg_attach,
+	.destroy = blkiocg_destroy,
+	.populate = blkiocg_populate,
+	.subsys_id = blkio_subsys_id,
+	.use_id = 1,
+};

block/blk-cgroup.h

@@ -0,0 +1,58 @@
+#ifndef _BLK_CGROUP_H
+#define _BLK_CGROUP_H
+/*
+ * Common Block IO controller cgroup interface
+ *
+ * Based on ideas and code from CFQ, CFS and BFQ:
+ * Copyright (C) 2003 Jens Axboe <[email protected]>
+ *
+ * Copyright (C) 2008 Fabio Checconi <[email protected]>
+ *		      Paolo Valente <[email protected]>
+ *
+ * Copyright (C) 2009 Vivek Goyal <[email protected]>
+ * 	              Nauman Rafique <[email protected]>
+ */
+
+#include <linux/cgroup.h>
+
+struct blkio_cgroup {
+	struct cgroup_subsys_state css;
+	unsigned int weight;
+	spinlock_t lock;
+	struct hlist_head blkg_list;
+};
+
+struct blkio_group {
+	/* An rcu protected unique identifier for the group */
+	void *key;
+	struct hlist_node blkcg_node;
+};
+
+#define BLKIO_WEIGHT_MIN	100
+#define BLKIO_WEIGHT_MAX	1000
+#define BLKIO_WEIGHT_DEFAULT	500
+
+#ifdef CONFIG_BLK_CGROUP
+extern struct blkio_cgroup blkio_root_cgroup;
+extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
+extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
+				struct blkio_group *blkg, void *key);
+extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
+extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
+						void *key);
+#else
+static inline struct blkio_cgroup *
+cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
+
+static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
+			struct blkio_group *blkg, void *key)
+{
+}
+
+static inline int
+blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
+
+static inline struct blkio_group *
+blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
+#endif
+#endif /* _BLK_CGROUP_H */

include/linux/cgroup_subsys.h

@@ -60,3 +60,9 @@ SUBSYS(net_cls)
 #endif
 
 /* */
+
+#ifdef CONFIG_BLK_CGROUP
+SUBSYS(blkio)
+#endif
+
+/* */

include/linux/iocontext.h

@@ -68,6 +68,10 @@ struct io_context {
 	unsigned short ioprio;
 	unsigned short ioprio_changed;
 
+#ifdef CONFIG_BLK_CGROUP
+	unsigned short cgroup_changed;
+#endif
+
 	/*
 	 * For request batching
 	 */