[PATCH 18/23] io-controller: blkio_cgroup patches from Ryo to track async bios.

[Vivek Goyal <vgoyal@redhat.com>]

o blkio_cgroup patches from Ryo to track async bios.

o This functionality is used to determine the group of async IO from page
  instead of context of submitting task.

Signed-off-by: Hirokazu Takahashi <taka@valinux.co.jp>
Signed-off-by: Ryo Tsuruta <ryov@valinux.co.jp>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
 block/blk-ioc.c               |   36 +++---
 fs/buffer.c                   |    2 +
 fs/direct-io.c                |    2 +
 include/linux/biotrack.h      |  100 ++++++++++++++
 include/linux/cgroup_subsys.h |    6 +
 include/linux/iocontext.h     |    1 +
 include/linux/memcontrol.h    |    6 +
 include/linux/mmzone.h        |    4 +-
 include/linux/page_cgroup.h   |    5 +-
 init/Kconfig                  |   16 +++
 mm/Makefile                   |    4 +-
 mm/biotrack.c                 |  293 +++++++++++++++++++++++++++++++++++++++++
 mm/bounce.c                   |    2 +
 mm/filemap.c                  |    2 +
 mm/memcontrol.c               |    6 +
 mm/memory.c                   |    5 +
 mm/page-writeback.c           |    2 +
 mm/page_cgroup.c              |   23 ++--
 mm/swap_state.c               |    2 +
 19 files changed, 486 insertions(+), 31 deletions(-)
 create mode 100644 include/linux/biotrack.h
 create mode 100644 mm/biotrack.c

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 0d56336..890d475 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -84,27 +84,31 @@ void exit_io_context(void)
 	}
 }
 
+void init_io_context(struct io_context *ioc)
+{
+	atomic_long_set(&ioc->refcount, 1);
+	atomic_set(&ioc->nr_tasks, 1);
+	spin_lock_init(&ioc->lock);
+	ioc->ioprio_changed = 0;
+	ioc->ioprio = 0;
+#ifdef CONFIG_GROUP_IOSCHED
+	ioc->cgroup_changed = 0;
+#endif
+	ioc->last_waited = jiffies; /* doesn't matter... */
+	ioc->nr_batch_requests = 0; /* because this is 0 */
+	ioc->aic = NULL;
+	INIT_RADIX_TREE(&ioc->radix_root, GFP_ATOMIC | __GFP_HIGH);
+	INIT_HLIST_HEAD(&ioc->cic_list);
+	ioc->ioc_data = NULL;
+}
+
 struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 {
 	struct io_context *ret;
 
 	ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
-	if (ret) {
-		atomic_long_set(&ret->refcount, 1);
-		atomic_set(&ret->nr_tasks, 1);
-		spin_lock_init(&ret->lock);
-		ret->ioprio_changed = 0;
-		ret->ioprio = 0;
-#ifdef CONFIG_GROUP_IOSCHED
-		ret->cgroup_changed = 0;
-#endif
-		ret->last_waited = jiffies; /* doesn't matter... */
-		ret->nr_batch_requests = 0; /* because this is 0 */
-		ret->aic = NULL;
-		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
-		INIT_HLIST_HEAD(&ret->cic_list);
-		ret->ioc_data = NULL;
-	}
+	if (ret)
+		init_io_context(ret);
 
 	return ret;
 }
diff --git a/fs/buffer.c b/fs/buffer.c
index 28f320f..8efcd82 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -36,6 +36,7 @@
 #include <linux/buffer_head.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/bio.h>
+#include <linux/biotrack.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
@@ -668,6 +669,7 @@ static void __set_page_dirty(struct page *page,
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
+		blkio_cgroup_reset_owner_pagedirty(page, current->mm);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 8b10b87..185ba0a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -33,6 +33,7 @@
 #include <linux/err.h>
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
+#include <linux/biotrack.h>
 #include <linux/rwsem.h>
 #include <linux/uio.h>
 #include <asm/atomic.h>
@@ -797,6 +798,7 @@ static int do_direct_IO(struct dio *dio)
 			ret = PTR_ERR(page);
 			goto out;
 		}
+		blkio_cgroup_reset_owner(page, current->mm);
 
 		while (block_in_page < blocks_per_page) {
 			unsigned offset_in_page = block_in_page << blkbits;
diff --git a/include/linux/biotrack.h b/include/linux/biotrack.h
new file mode 100644
index 0000000..2b8bb0b
--- /dev/null
+++ b/include/linux/biotrack.h
@@ -0,0 +1,100 @@
+#include <linux/cgroup.h>
+#include <linux/mm.h>
+#include <linux/page_cgroup.h>
+
+#ifndef _LINUX_BIOTRACK_H
+#define _LINUX_BIOTRACK_H
+
+#ifdef CONFIG_CGROUP_BLKIO
+
+struct io_context;
+struct block_device;
+
+struct blkio_cgroup {
+	struct cgroup_subsys_state css;
+	struct io_context *io_context;	/* default io_context */
+/*	struct radix_tree_root io_context_root; per device io_context */
+};
+
+/**
+ * __init_blkio_page_cgroup() - initialize a blkio_page_cgroup
+ * @pc:		page_cgroup of the page
+ *
+ * Reset the owner ID of a page.
+ */
+static inline void __init_blkio_page_cgroup(struct page_cgroup *pc)
+{
+	pc->blkio_cgroup_id = 0;
+}
+
+/**
+ * blkio_cgroup_disabled() - check whether blkio_cgroup is disabled
+ *
+ * Returns true if disabled, false if not.
+ */
+static inline bool blkio_cgroup_disabled(void)
+{
+	if (blkio_cgroup_subsys.disabled)
+		return true;
+	return false;
+}
+
+extern void blkio_cgroup_set_owner(struct page *page, struct mm_struct *mm);
+extern void blkio_cgroup_reset_owner(struct page *page, struct mm_struct *mm);
+extern void blkio_cgroup_reset_owner_pagedirty(struct page *page,
+						 struct mm_struct *mm);
+extern void blkio_cgroup_copy_owner(struct page *page, struct page *opage);
+
+extern struct io_context *get_blkio_cgroup_iocontext(struct bio *bio);
+extern unsigned long get_blkio_cgroup_id(struct bio *bio);
+extern struct cgroup *get_cgroup_from_page(struct page *page);
+
+#else /* !CONFIG_CGROUP_BLKIO */
+
+struct blkio_cgroup;
+
+static inline void __init_blkio_page_cgroup(struct page_cgroup *pc)
+{
+}
+
+static inline bool blkio_cgroup_disabled(void)
+{
+	return true;
+}
+
+static inline void blkio_cgroup_set_owner(struct page *page, struct mm_struct *mm)
+{
+}
+
+static inline void blkio_cgroup_reset_owner(struct page *page,
+						struct mm_struct *mm)
+{
+}
+
+static inline void blkio_cgroup_reset_owner_pagedirty(struct page *page,
+						struct mm_struct *mm)
+{
+}
+
+static inline void blkio_cgroup_copy_owner(struct page *page, struct page *opage)
+{
+}
+
+static inline struct io_context *get_blkio_cgroup_iocontext(struct bio *bio)
+{
+	return NULL;
+}
+
+static inline unsigned long get_blkio_cgroup_id(struct bio *bio)
+{
+	return 0;
+}
+
+static inline struct cgroup *get_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_CGROUP_BLKIO */
+
+#endif /* _LINUX_BIOTRACK_H */
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index baf544f..78504f3 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -43,6 +43,12 @@ SUBSYS(mem_cgroup)
 
 /* */
 
+#ifdef CONFIG_CGROUP_BLKIO
+SUBSYS(blkio_cgroup)
+#endif
+
+/* */
+
 #ifdef CONFIG_CGROUP_DEVICE
 SUBSYS(devices)
 #endif
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index b343594..1baa6c1 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -109,6 +109,7 @@ int put_io_context(struct io_context *ioc);
 void exit_io_context(void);
 struct io_context *get_io_context(gfp_t gfp_flags, int node);
 struct io_context *alloc_io_context(gfp_t gfp_flags, int node);
+void init_io_context(struct io_context *ioc);
 void copy_io_context(struct io_context **pdst, struct io_context **psrc);
 #else
 static inline void exit_io_context(void)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e46a073..eb45fe9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -37,6 +37,8 @@ struct mm_struct;
  * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
  */
 
+extern void __init_mem_page_cgroup(struct page_cgroup *pc);
+
 extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 /* for swap handling */
@@ -121,6 +123,10 @@ void mem_cgroup_update_mapped_file_stat(struct page *page, int val);
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct mem_cgroup;
 
+static inline void __init_mem_page_cgroup(struct page_cgroup *pc)
+{
+}
+
 static inline int mem_cgroup_newpage_charge(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 8895985..c9d1ed4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -605,7 +605,7 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
 	struct page_cgroup *node_page_cgroup;
 #endif
 #endif
@@ -956,7 +956,7 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
 	/*
 	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
 	 * section. (see memcontrol.h/page_cgroup.h about this.)
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 13f126c..bca6c8a 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -1,7 +1,7 @@
 #ifndef __LINUX_PAGE_CGROUP_H
 #define __LINUX_PAGE_CGROUP_H
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
 #include <linux/bit_spinlock.h>
 /*
  * Page Cgroup can be considered as an extended mem_map.
@@ -14,6 +14,7 @@ struct page_cgroup {
 	unsigned long flags;
 	struct mem_cgroup *mem_cgroup;
 	struct page *page;
+	unsigned long blkio_cgroup_id;
 	struct list_head lru;		/* per cgroup LRU list */
 };
 
@@ -83,7 +84,7 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc)
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
 }
 
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_CGROUP_PAGE */
 struct page_cgroup;
 
 static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
diff --git a/init/Kconfig b/init/Kconfig
index afcaa86..54aa85a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -622,6 +622,22 @@ config GROUP_IOSCHED
 
 endif # CGROUPS
 
+config CGROUP_BLKIO
+	bool
+	depends on CGROUPS && BLOCK
+	select MM_OWNER
+	default n
+	---help---
+	  Provides a Resource Controller which enables to track the onwner
+	  of every Block I/O requests.
+	  The information this subsystem provides can be used from any
+	  kind of module such as dm-ioband device mapper modules or
+	  the cfq-scheduler.
+
+config CGROUP_PAGE
+	def_bool y
+	depends on CGROUP_MEM_RES_CTLR || CGROUP_BLKIO
+
 config MM_OWNER
 	bool
 
diff --git a/mm/Makefile b/mm/Makefile
index 5e0bd64..6208744 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -39,6 +39,8 @@ else
 obj-$(CONFIG_SMP) += allocpercpu.o
 endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o
+obj-$(CONFIG_CGROUP_PAGE) += page_cgroup.o
+obj-$(CONFIG_CGROUP_BLKIO) += biotrack.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
diff --git a/mm/biotrack.c b/mm/biotrack.c
new file mode 100644
index 0000000..1da7d1e
--- /dev/null
+++ b/mm/biotrack.c
@@ -0,0 +1,293 @@
+/* biotrack.c - Block I/O Tracking
+ *
+ * Copyright (C) VA Linux Systems Japan, 2008-2009
+ * Developed by Hirokazu Takahashi <taka@valinux.co.jp>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/bit_spinlock.h>
+#include <linux/blkdev.h>
+#include <linux/biotrack.h>
+#include <linux/mm_inline.h>
+
+/*
+ * The block I/O tracking mechanism is implemented on the cgroup memory
+ * controller framework. It helps to find the the owner of an I/O request
+ * because every I/O request has a target page and the owner of the page
+ * can be easily determined on the framework.
+ */
+
+/* Return the blkio_cgroup that associates with a cgroup. */
+static inline struct blkio_cgroup *cgroup_blkio(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, blkio_cgroup_subsys_id),
+					struct blkio_cgroup, css);
+}
+
+/* Return the blkio_cgroup that associates with a process. */
+static inline struct blkio_cgroup *blkio_cgroup_from_task(struct task_struct *p)
+{
+	return container_of(task_subsys_state(p, blkio_cgroup_subsys_id),
+					struct blkio_cgroup, css);
+}
+
+static struct io_context default_blkio_io_context;
+static struct blkio_cgroup default_blkio_cgroup = {
+	.io_context	= &default_blkio_io_context,
+};
+
+/**
+ * blkio_cgroup_set_owner() - set the owner ID of a page.
+ * @page:	the page we want to tag
+ * @mm:		the mm_struct of a page owner
+ *
+ * Make a given page have the blkio-cgroup ID of the owner of this page.
+ */
+void blkio_cgroup_set_owner(struct page *page, struct mm_struct *mm)
+{
+	struct blkio_cgroup *biog;
+	struct page_cgroup *pc;
+
+	if (blkio_cgroup_disabled())
+		return;
+	pc = lookup_page_cgroup(page);
+	if (unlikely(!pc))
+		return;
+
+	pc->blkio_cgroup_id = 0;	/* 0: default blkio_cgroup id */
+	if (!mm)
+		return;
+	/*
+	 * Locking "pc" isn't necessary here since the current process is
+	 * the only one that can access the members related to blkio_cgroup.
+	 */
+	rcu_read_lock();
+	biog = blkio_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!biog))
+		goto out;
+	/*
+	 * css_get(&bio->css) isn't called to increment the reference
+	 * count of this blkio_cgroup "biog" so pc->blkio_cgroup_id
+	 * might turn invalid even if this page is still active.
+	 * This approach is chosen to minimize the overhead.
+	 */
+	pc->blkio_cgroup_id = css_id(&biog->css);
+out:
+	rcu_read_unlock();
+}
+
+/**
+ * blkio_cgroup_reset_owner() - reset the owner ID of a page
+ * @page:	the page we want to tag
+ * @mm:		the mm_struct of a page owner
+ *
+ * Change the owner of a given page if necessary.
+ */
+void blkio_cgroup_reset_owner(struct page *page, struct mm_struct *mm)
+{
+	/*
+	 * A little trick:
+	 * Just call blkio_cgroup_set_owner() for pages which are already
+	 * active since the blkio_cgroup_id member of page_cgroup can be
+	 * updated without any locks. This is because an integer type of
+	 * variable can be set a new value at once on modern cpus.
+	 */
+	blkio_cgroup_set_owner(page, mm);
+}
+
+/**
+ * blkio_cgroup_reset_owner_pagedirty() - reset the owner ID of a pagecache page
+ * @page:	the page we want to tag
+ * @mm:		the mm_struct of a page owner
+ *
+ * Change the owner of a given page if the page is in the pagecache.
+ */
+void blkio_cgroup_reset_owner_pagedirty(struct page *page, struct mm_struct *mm)
+{
+	if (!page_is_file_cache(page))
+		return;
+	if (current->flags & PF_MEMALLOC)
+		return;
+
+	blkio_cgroup_reset_owner(page, mm);
+}
+
+/**
+ * blkio_cgroup_copy_owner() - copy the owner ID of a page into another page
+ * @npage:	the page where we want to copy the owner
+ * @opage:	the page from which we want to copy the ID
+ *
+ * Copy the owner ID of @opage into @npage.
+ */
+void blkio_cgroup_copy_owner(struct page *npage, struct page *opage)
+{
+	struct page_cgroup *npc, *opc;
+
+	if (blkio_cgroup_disabled())
+		return;
+	npc = lookup_page_cgroup(npage);
+	if (unlikely(!npc))
+		return;
+	opc = lookup_page_cgroup(opage);
+	if (unlikely(!opc))
+		return;
+
+	/*
+	 * Do this without any locks. The reason is the same as
+	 * blkio_cgroup_reset_owner().
+	 */
+	npc->blkio_cgroup_id = opc->blkio_cgroup_id;
+}
+
+/* Create a new blkio-cgroup. */
+static struct cgroup_subsys_state *
+blkio_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct blkio_cgroup *biog;
+	struct io_context *ioc;
+
+	if (!cgrp->parent) {
+		biog = &default_blkio_cgroup;
+		init_io_context(biog->io_context);
+		/* Increment the referrence count not to be released ever. */
+		atomic_long_inc(&biog->io_context->refcount);
+		return &biog->css;
+	}
+
+	biog = kzalloc(sizeof(*biog), GFP_KERNEL);
+	if (!biog)
+		return ERR_PTR(-ENOMEM);
+	ioc = alloc_io_context(GFP_KERNEL, -1);
+	if (!ioc) {
+		kfree(biog);
+		return ERR_PTR(-ENOMEM);
+	}
+	biog->io_context = ioc;
+	return &biog->css;
+}
+
+/* Delete the blkio-cgroup. */
+static void blkio_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct blkio_cgroup *biog = cgroup_blkio(cgrp);
+
+	put_io_context(biog->io_context);
+	free_css_id(&blkio_cgroup_subsys, &biog->css);
+	kfree(biog);
+}
+
+/**
+ * get_blkio_cgroup_id() - determine the blkio-cgroup ID
+ * @bio:	the &struct bio which describes the I/O
+ *
+ * Returns the blkio-cgroup ID of a given bio. A return value zero
+ * means that the page associated with the bio belongs to default_blkio_cgroup.
+ */
+unsigned long get_blkio_cgroup_id(struct bio *bio)
+{
+	struct page_cgroup *pc;
+	struct page *page = bio_iovec_idx(bio, 0)->bv_page;
+	unsigned long id = 0;
+
+	pc = lookup_page_cgroup(page);
+	if (pc)
+		id = pc->blkio_cgroup_id;
+	return id;
+}
+
+/**
+ * get_blkio_cgroup_iocontext() - determine the blkio-cgroup iocontext
+ * @bio:	the &struct bio which describe the I/O
+ *
+ * Returns the iocontext of blkio-cgroup that issued a given bio.
+ */
+struct io_context *get_blkio_cgroup_iocontext(struct bio *bio)
+{
+	struct cgroup_subsys_state *css;
+	struct blkio_cgroup *biog;
+	struct io_context *ioc;
+	unsigned long id;
+
+	id = get_blkio_cgroup_id(bio);
+	rcu_read_lock();
+	css = css_lookup(&blkio_cgroup_subsys, id);
+	if (css)
+		biog = container_of(css, struct blkio_cgroup, css);
+	else
+		biog = &default_blkio_cgroup;
+	ioc = biog->io_context;	/* default io_context for this cgroup */
+	atomic_long_inc(&ioc->refcount);
+	rcu_read_unlock();
+	return ioc;
+}
+
+/**
+ * get_cgroup_from_page() - determine the cgroup from a page.
+ * @page:	the page to be tracked
+ *
+ * Returns the cgroup of a given page. A return value zero means that
+ * the page associated with the page belongs to default_blkio_cgroup.
+ *
+ * Note:
+ * This function must be called under rcu_read_lock().
+ */
+struct cgroup *get_cgroup_from_page(struct page *page)
+{
+	struct page_cgroup *pc;
+	struct cgroup_subsys_state *css;
+
+	pc = lookup_page_cgroup(page);
+	if (!pc)
+		return NULL;
+
+	css = css_lookup(&blkio_cgroup_subsys, pc->blkio_cgroup_id);
+	if (!css)
+		return NULL;
+
+	return css->cgroup;
+}
+
+EXPORT_SYMBOL(get_blkio_cgroup_id);
+EXPORT_SYMBOL(get_blkio_cgroup_iocontext);
+EXPORT_SYMBOL(get_cgroup_from_page);
+
+/* Read the ID of the specified blkio cgroup. */
+static u64 blkio_id_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct blkio_cgroup *biog = cgroup_blkio(cgrp);
+
+	return (u64)css_id(&biog->css);
+}
+
+static struct cftype blkio_files[] = {
+	{
+		.name = "id",
+		.read_u64 = blkio_id_read,
+	},
+};
+
+static int blkio_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	return cgroup_add_files(cgrp, ss, blkio_files,
+					ARRAY_SIZE(blkio_files));
+}
+
+struct cgroup_subsys blkio_cgroup_subsys = {
+	.name		= "blkio",
+	.create		= blkio_cgroup_create,
+	.destroy	= blkio_cgroup_destroy,
+	.populate	= blkio_cgroup_populate,
+	.subsys_id	= blkio_cgroup_subsys_id,
+	.use_id		= 1,
+};
diff --git a/mm/bounce.c b/mm/bounce.c
index a2b76a5..7ad8d44 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
+#include <linux/biotrack.h>
 #include <asm/tlbflush.h>
 
 #include <trace/events/block.h>
@@ -210,6 +211,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		to->bv_len = from->bv_len;
 		to->bv_offset = from->bv_offset;
 		inc_zone_page_state(to->bv_page, NR_BOUNCE);
+		blkio_cgroup_copy_owner(to->bv_page, page);
 
 		if (rw == WRITE) {
 			char *vto, *vfrom;
diff --git a/mm/filemap.c b/mm/filemap.c
index ccea3b6..01c47a1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -33,6 +33,7 @@
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
+#include <linux/biotrack.h>
 #include <linux/mm_inline.h> /* for page_is_file_cache() */
 #include "internal.h"
 
@@ -464,6 +465,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 					gfp_mask & GFP_RECLAIM_MASK);
 	if (error)
 		goto out;
+	blkio_cgroup_set_owner(page, current->mm);
 
 	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
 	if (error == 0) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fd4529d..baf4be7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -129,6 +129,12 @@ struct mem_cgroup_lru_info {
 	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
 };
 
+void __meminit __init_mem_page_cgroup(struct page_cgroup *pc)
+{
+	pc->mem_cgroup = NULL;
+	INIT_LIST_HEAD(&pc->lru);
+}
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
diff --git a/mm/memory.c b/mm/memory.c
index aede2ce..346f368 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -51,6 +51,7 @@
 #include <linux/init.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
+#include <linux/biotrack.h>
 #include <linux/mmu_notifier.h>
 #include <linux/kallsyms.h>
 #include <linux/swapops.h>
@@ -2116,6 +2117,7 @@ gotten:
 		 */
 		ptep_clear_flush_notify(vma, address, page_table);
 		page_add_new_anon_rmap(new_page, vma, address);
+		blkio_cgroup_set_owner(new_page, mm);
 		set_pte_at(mm, address, page_table, entry);
 		update_mmu_cache(vma, address, entry);
 		if (old_page) {
@@ -2581,6 +2583,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	flush_icache_page(vma, page);
 	set_pte_at(mm, address, page_table, pte);
 	page_add_anon_rmap(page, vma, address);
+	blkio_cgroup_reset_owner(page, mm);
 	/* It's better to call commit-charge after rmap is established */
 	mem_cgroup_commit_charge_swapin(page, ptr);
 
@@ -2645,6 +2648,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto release;
 	inc_mm_counter(mm, anon_rss);
 	page_add_new_anon_rmap(page, vma, address);
+	blkio_cgroup_set_owner(page, mm);
 	set_pte_at(mm, address, page_table, entry);
 
 	/* No need to invalidate - it was non-present before */
@@ -2792,6 +2796,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (anon) {
 			inc_mm_counter(mm, anon_rss);
 			page_add_new_anon_rmap(page, vma, address);
+			blkio_cgroup_set_owner(page, mm);
 		} else {
 			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 81627eb..1df421b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/backing-dev.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/biotrack.h>
 #include <linux/blkdev.h>
 #include <linux/mpage.h>
 #include <linux/rmap.h>
@@ -1247,6 +1248,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 			BUG_ON(mapping2 != mapping);
 			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
 			account_page_dirtied(page, mapping);
+			blkio_cgroup_reset_owner_pagedirty(page, current->mm);
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index f22b4eb..29bf26c 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -9,14 +9,15 @@
 #include <linux/vmalloc.h>
 #include <linux/cgroup.h>
 #include <linux/swapops.h>
+#include <linux/biotrack.h>
 
 static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
 {
 	pc->flags = 0;
-	pc->mem_cgroup = NULL;
 	pc->page = pfn_to_page(pfn);
-	INIT_LIST_HEAD(&pc->lru);
+	__init_mem_page_cgroup(pc);
+	__init_blkio_page_cgroup(pc);
 }
 static unsigned long total_usage;
 
@@ -74,7 +75,7 @@ void __init page_cgroup_init_flatmem(void)
 
 	int nid, fail;
 
-	if (mem_cgroup_disabled())
+	if (mem_cgroup_disabled() && blkio_cgroup_disabled())
 		return;
 
 	for_each_online_node(nid)  {
@@ -83,12 +84,13 @@ void __init page_cgroup_init_flatmem(void)
 			goto fail;
 	}
 	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
-	" don't want memory cgroups\n");
+	printk(KERN_INFO "please try 'cgroup_disable=memory,blkio' option"
+	" if you don't want memory and blkio cgroups\n");
 	return;
 fail:
 	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
-	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
+	printk(KERN_CRIT
+		"please try 'cgroup_disable=memory,blkio' boot option\n");
 	panic("Out of memory");
 }
 
@@ -245,7 +247,7 @@ void __init page_cgroup_init(void)
 	unsigned long pfn;
 	int fail = 0;
 
-	if (mem_cgroup_disabled())
+	if (mem_cgroup_disabled() && blkio_cgroup_disabled())
 		return;
 
 	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
@@ -254,14 +256,15 @@ void __init page_cgroup_init(void)
 		fail = init_section_page_cgroup(pfn);
 	}
 	if (fail) {
-		printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
+		printk(KERN_CRIT
+			"try 'cgroup_disable=memory,blkio' boot option\n");
 		panic("Out of memory");
 	} else {
 		hotplug_memory_notifier(page_cgroup_callback, 0);
 	}
 	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
-	" want memory cgroups\n");
+	printk(KERN_INFO "please try 'cgroup_disable=memory,blkio' option"
+	" if you don't want memory and blkio cgroups\n");
 }
 
 void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 42cd38e..6eb96f1 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -18,6 +18,7 @@
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
 #include <linux/page_cgroup.h>
+#include <linux/biotrack.h>
 
 #include <asm/pgtable.h>
 
@@ -307,6 +308,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 */
 		__set_page_locked(new_page);
 		SetPageSwapBacked(new_page);
+		blkio_cgroup_set_owner(new_page, current->mm);
 		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
 		if (likely(!err)) {
 			/*
-- 
1.6.0.6