Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754756AbYKTLLO (ORCPT ); Thu, 20 Nov 2008 06:11:14 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754036AbYKTLK6 (ORCPT ); Thu, 20 Nov 2008 06:10:58 -0500 Received: from cn.fujitsu.com ([222.73.24.84]:52740 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1754047AbYKTLK4 (ORCPT ); Thu, 20 Nov 2008 06:10:56 -0500 Message-ID: <49254512.9050900@cn.fujitsu.com> Date: Thu, 20 Nov 2008 19:08:02 +0800 From: Gui Jianfeng User-Agent: Thunderbird 2.0.0.5 (Windows/20070716) MIME-Version: 1.0 To: Andrea Righi , Ryo Tsuruta , Hirokazu Takahashi CC: menage@google.com, containers@lists.linux-foundation.org, linux-kernel@vger.kernel.org, Andrew Morton , KAMEZAWA Hiroyuki Subject: [PATCH 1/7] porting bio-cgroup to 2.6.28-rc2-mm1 References: <4925445C.10302@cn.fujitsu.com> In-Reply-To: <4925445C.10302@cn.fujitsu.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 24722 Lines: 860 From: Ryo Tsuruta porting bio-cgroup to 2.6.28-rc2-mm1 Signed-off-by: Ryo Tsuruta Signed-off-by: Hirokazu Takahashi --- block/blk-ioc.c | 30 +++-- fs/buffer.c | 2 + fs/direct-io.c | 2 + include/linux/biotrack.h | 82 ++++++++++++ include/linux/cgroup_subsys.h | 6 + include/linux/iocontext.h | 1 + include/linux/memcontrol.h | 14 ++- include/linux/mmzone.h | 4 +- include/linux/page_cgroup.h | 11 ++- init/Kconfig | 15 +++ mm/Makefile | 4 +- mm/biotrack.c | 274 +++++++++++++++++++++++++++++++++++++++++ mm/bounce.c | 2 + mm/filemap.c | 2 + mm/memcontrol.c | 5 + mm/memory.c | 5 + mm/page-writeback.c | 2 + mm/page_cgroup.c | 15 ++- mm/swap_state.c | 2 + 19 files changed, 452 insertions(+), 26 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 012f065..ef8cac0 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -84,24 +84,28 @@ void exit_io_context(void) } } +void init_io_context(struct io_context *ioc) +{ + atomic_set(&ioc->refcount, 1); + atomic_set(&ioc->nr_tasks, 1); + spin_lock_init(&ioc->lock); + ioc->ioprio_changed = 0; + ioc->ioprio = 0; + 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_set(&ret->refcount, 1); - atomic_set(&ret->nr_tasks, 1); - spin_lock_init(&ret->lock); - ret->ioprio_changed = 0; - ret->ioprio = 0; - 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 f624fc7..0edbac0 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -779,6 +780,7 @@ static int __set_page_dirty(struct page *page, BDI_RECLAIMABLE); task_io_account_write(PAGE_CACHE_SIZE); } + bio_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 af0558d..222a970 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -799,6 +800,7 @@ static int do_direct_IO(struct dio *dio) ret = PTR_ERR(page); goto out; } + bio_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..d352abd --- /dev/null +++ b/include/linux/biotrack.h @@ -0,0 +1,82 @@ +#include +#include +#include + +#ifndef _LINUX_BIOTRACK_H +#define _LINUX_BIOTRACK_H + +#ifdef CONFIG_CGROUP_BIO + +struct io_context; +struct block_device; + +struct bio_cgroup { + struct cgroup_subsys_state css; + int id; + struct io_context *io_context; /* default io_context */ +/* struct radix_tree_root io_context_root; per device io_context */ +}; + +static inline void __init_bio_page_cgroup(struct page_cgroup *pc) +{ + pc->bio_cgroup_id = 0; +} + +static inline int bio_cgroup_disabled(void) +{ + return bio_cgroup_subsys.disabled; +} + +extern void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm); +extern void bio_cgroup_reset_owner(struct page *page, struct mm_struct *mm); +extern void bio_cgroup_reset_owner_pagedirty(struct page *page, + struct mm_struct *mm); +extern void bio_cgroup_copy_owner(struct page *page, struct page *opage); + +extern struct io_context *get_bio_cgroup_iocontext(struct bio *bio); +extern int get_bio_cgroup_id(struct bio *bio); + +#else /* CONFIG_CGROUP_BIO */ + +struct bio_cgroup; + +static inline void __init_bio_page_cgroup(struct page_cgroup *pc) +{ +} + +static inline int bio_cgroup_disabled(void) +{ + return 1; +} + +static inline void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm) +{ +} + +static inline void bio_cgroup_reset_owner(struct page *page, + struct mm_struct *mm) +{ +} + +static inline void bio_cgroup_reset_owner_pagedirty(struct page *page, + struct mm_struct *mm) +{ +} + +static inline void bio_cgroup_copy_owner(struct page *page, struct page *opage) +{ +} + +static inline struct io_context *get_bio_cgroup_iocontext(struct bio *bio) +{ + return NULL; +} + +static inline int get_bio_cgroup_id(struct bio *bio) +{ + return 0; +} + +#endif /* CONFIG_CGROUP_BIO */ + +#endif /* _LINUX_BIOTRACK_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 9c22396..8eb6f48 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -43,6 +43,12 @@ SUBSYS(mem_cgroup) /* */ +#ifdef CONFIG_CGROUP_BIO +SUBSYS(bio_cgroup) +#endif + +/* */ + #ifdef CONFIG_CGROUP_DEVICE SUBSYS(devices) #endif diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 08b987b..be37c27 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -104,6 +104,7 @@ 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 1fbe14d..f519a88 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -20,12 +20,14 @@ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H -struct mem_cgroup; +#struct mem_cgroup; struct page_cgroup; struct page; struct mm_struct; #ifdef CONFIG_CGROUP_MEM_RES_CTLR +extern void __init_mem_page_cgroup(struct page_cgroup *pc); +#define mem_cgroup_disabled() mem_cgroup_subsys.disabled extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); @@ -71,6 +73,16 @@ extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, #else /* CONFIG_CGROUP_MEM_RES_CTLR */ +static inline void __init_mem_page_cgroup(struct page_cgroup *pc) +{ +} + +static inline int mem_cgroup_disabled(void) +{ + return 1; +} + + static inline int mem_cgroup_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 35a7b5e..bf7b6e2 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -603,7 +603,7 @@ 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 @@ -952,7 +952,7 @@ 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 f546ad6..07aba8b 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 /* * Page Cgroup can be considered as an extended mem_map. @@ -12,9 +12,14 @@ */ struct page_cgroup { unsigned long flags; - struct mem_cgroup *mem_cgroup; struct page *page; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR + struct mem_cgroup *mem_cgroup; struct list_head lru; /* per cgroup LRU list */ +#endif +#ifdef CONFIG_CGROUP_BIO + int bio_cgroup_id; +#endif }; void __init pgdat_page_cgroup_init(struct pglist_data *pgdat); @@ -88,7 +93,7 @@ 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 pgdat_page_cgroup_init(struct pglist_data *pgdat) diff --git a/init/Kconfig b/init/Kconfig index 3c9d79b..6394a25 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -393,6 +393,21 @@ config RESOURCE_COUNTERS infrastructure that works with cgroups depends on CGROUPS +config CGROUP_BIO + bool "Block I/O cgroup subsystem" + depends on CGROUPS && BLOCK + select MM_OWNER + 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_BIO + config MM_OWNER bool diff --git a/mm/Makefile b/mm/Makefile index f35fcc3..5f3ba89 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -34,5 +34,7 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_SMP) += allocpercpu.o obj-$(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_BIO) += biotrack.o obj-$(CONFIG_KMEMTRACE) += kmemtrace.o diff --git a/mm/biotrack.c b/mm/biotrack.c new file mode 100644 index 0000000..1af5910 --- /dev/null +++ b/mm/biotrack.c @@ -0,0 +1,274 @@ +/* biotrack.c - Block I/O Tracking + * + * Copyright (C) VA Linux Systems Japan, 2008 + * Developed by Hirokazu Takahashi + * + * 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 +#include +#include +#include +#include +#include + +/* + * 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 bio_cgroup that associates with a cgroup. */ +static inline struct bio_cgroup *cgroup_bio(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, bio_cgroup_subsys_id), + struct bio_cgroup, css); +} + +/* Return the bio_cgroup that associates with a process. */ +static inline struct bio_cgroup *bio_cgroup_from_task(struct task_struct *p) +{ + return container_of(task_subsys_state(p, bio_cgroup_subsys_id), + struct bio_cgroup, css); +} + +static struct idr bio_cgroup_id; +static DEFINE_SPINLOCK(bio_cgroup_idr_lock); +static struct io_context default_bio_io_context; +static struct bio_cgroup default_bio_cgroup = { + .id = 0, + .io_context = &default_bio_io_context, +}; + +/* + * This function is used to make a given page have the bio-cgroup id of + * the owner of this page. + */ +void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm) +{ + struct bio_cgroup *biog; + struct page_cgroup *pc; + + if (bio_cgroup_disabled()) + return; + pc = lookup_page_cgroup(page); + if (unlikely(!pc)) + return; + + pc->bio_cgroup_id = 0; /* 0: default bio_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 bio_cgroup. + */ + rcu_read_lock(); + biog = bio_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 bio_cgroup "biog" so pc->bio_cgroup_id might turn + * invalid even if this page is still active. + * This approach is chosen to minimize the overhead. + */ + pc->bio_cgroup_id = biog->id; +out: + rcu_read_unlock(); +} + +/* + * Change the owner of a given page if necessary. + */ +void bio_cgroup_reset_owner(struct page *page, struct mm_struct *mm) +{ + /* + * A little trick: + * Just call bio_cgroup_set_owner() for pages which are already + * active since the bio_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. + */ + bio_cgroup_set_owner(page, mm); +} + +/* + * Change the owner of a given page. This function is only effective for + * pages in the pagecache. + */ +void bio_cgroup_reset_owner_pagedirty(struct page *page, struct mm_struct *mm) +{ + if (PageSwapCache(page) || PageAnon(page)) + return; + if (current->flags & PF_MEMALLOC) + return; + + bio_cgroup_reset_owner(page, mm); +} + +/* + * Assign "page" the same owner as "opage." + */ +void bio_cgroup_copy_owner(struct page *npage, struct page *opage) +{ + struct page_cgroup *npc, *opc; + + if (bio_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 + * bio_cgroup_reset_owner(). + */ + npc->bio_cgroup_id = opc->bio_cgroup_id; +} + +/* Create a new bio-cgroup. */ +static struct cgroup_subsys_state * +bio_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct bio_cgroup *biog; + struct io_context *ioc; + int ret; + + if (!cgrp->parent) { + biog = &default_bio_cgroup; + init_io_context(biog->io_context); + /* Increment the referrence count not to be released ever. */ + atomic_inc(&biog->io_context->refcount); + idr_init(&bio_cgroup_id); + return &biog->css; + } + + biog = kzalloc(sizeof(*biog), GFP_KERNEL); + ioc = alloc_io_context(GFP_KERNEL, -1); + if (!ioc || !biog) { + ret = -ENOMEM; + goto out_err; + } + biog->io_context = ioc; +retry: + if (!idr_pre_get(&bio_cgroup_id, GFP_KERNEL)) { + ret = -EAGAIN; + goto out_err; + } + spin_lock_irq(&bio_cgroup_idr_lock); + ret = idr_get_new_above(&bio_cgroup_id, (void *)biog, 1, &biog->id); + spin_unlock_irq(&bio_cgroup_idr_lock); + if (ret == -EAGAIN) + goto retry; + else if (ret) + goto out_err; + + return &biog->css; +out_err: + if (biog) + kfree(biog); + if (ioc) + put_io_context(ioc); + return ERR_PTR(ret); +} + +/* Delete the bio-cgroup. */ +static void bio_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct bio_cgroup *biog = cgroup_bio(cgrp); + + put_io_context(biog->io_context); + + spin_lock_irq(&bio_cgroup_idr_lock); + idr_remove(&bio_cgroup_id, biog->id); + spin_unlock_irq(&bio_cgroup_idr_lock); + + kfree(biog); +} + +static struct bio_cgroup *find_bio_cgroup(int id) +{ + struct bio_cgroup *biog; + spin_lock_irq(&bio_cgroup_idr_lock); + /* + * It might fail to find A bio-group associated with "id" since it + * is allowed to remove the bio-cgroup even when some of I/O requests + * this group issued haven't completed yet. + */ + biog = (struct bio_cgroup *)idr_find(&bio_cgroup_id, id); + spin_unlock_irq(&bio_cgroup_idr_lock); + return biog; +} + +/* Determine the bio-cgroup id of a given bio. */ +int get_bio_cgroup_id(struct bio *bio) +{ + struct page_cgroup *pc; + struct page *page = bio_iovec_idx(bio, 0)->bv_page; + int id = 0; + + pc = lookup_page_cgroup(page); + if (pc) + id = pc->bio_cgroup_id; + return id; +} + +/* Determine the iocontext of the bio-cgroup that issued a given bio. */ +struct io_context *get_bio_cgroup_iocontext(struct bio *bio) +{ + struct bio_cgroup *biog = NULL; + struct io_context *ioc; + int id = 0; + + id = get_bio_cgroup_id(bio); + if (id) + biog = find_bio_cgroup(id); + if (!biog) + biog = &default_bio_cgroup; + ioc = biog->io_context; /* default io_context for this cgroup */ + atomic_inc(&ioc->refcount); + return ioc; +} +EXPORT_SYMBOL(get_bio_cgroup_iocontext); +EXPORT_SYMBOL(get_bio_cgroup_id); + +static u64 bio_id_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct bio_cgroup *biog = cgroup_bio(cgrp); + return (u64) biog->id; +} + + +static struct cftype bio_files[] = { + { + .name = "id", + .read_u64 = bio_id_read, + }, +}; + +static int bio_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + return cgroup_add_files(cgrp, ss, bio_files, ARRAY_SIZE(bio_files)); +} + +struct cgroup_subsys bio_cgroup_subsys = { + .name = "bio", + .create = bio_cgroup_create, + .destroy = bio_cgroup_destroy, + .populate = bio_cgroup_populate, + .subsys_id = bio_cgroup_subsys_id, +}; + diff --git a/mm/bounce.c b/mm/bounce.c index 06722c4..02096a6 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #define POOL_SIZE 64 @@ -204,6 +205,7 @@ 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); + bio_cgroup_copy_owner(to->bv_page, page); if (rw == WRITE) { char *vto, *vfrom; diff --git a/mm/filemap.c b/mm/filemap.c index 721eace..fe58262 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -33,6 +33,7 @@ #include #include /* for BUG_ON(!in_atomic()) only */ #include +#include #include /* 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_HIGHMEM); if (error) goto out; + bio_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 866dcc7..95048fe 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -157,6 +157,11 @@ pcg_default_flags[NR_CHARGE_TYPE] = { 0, /* FORCE */ }; +void __meminit __init_mem_page_cgroup(struct page_cgroup *pc) +{ + pc->mem_cgroup = NULL; +} + /* * Always modified under lru lock. Then, not necessary to preempt_disable() */ diff --git a/mm/memory.c b/mm/memory.c index fd7d89b..4447ebe 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -1915,6 +1916,7 @@ gotten: */ ptep_clear_flush_notify(vma, address, page_table); SetPageSwapBacked(new_page); + bio_cgroup_set_owner(new_page, mm); lru_cache_add_active_or_unevictable(new_page, vma); page_add_new_anon_rmap(new_page, vma, address); @@ -2353,6 +2355,7 @@ 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); + bio_cgroup_reset_owner(page, mm); swap_free(entry); if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) @@ -2414,6 +2417,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, goto release; inc_mm_counter(mm, anon_rss); SetPageSwapBacked(page); + bio_cgroup_set_owner(page, mm); lru_cache_add_active_or_unevictable(page, vma); page_add_new_anon_rmap(page, vma, address); set_pte_at(mm, address, page_table, entry); @@ -2563,6 +2567,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (anon) { inc_mm_counter(mm, anon_rss); SetPageSwapBacked(page); + bio_cgroup_set_owner(page, mm); lru_cache_add_active_or_unevictable(page, vma); page_add_new_anon_rmap(page, vma, address); } else { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b3584bf..f24daaa 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -1100,6 +1101,7 @@ int __set_page_dirty_nobuffers(struct page *page) BDI_RECLAIMABLE); task_io_account_write(PAGE_CACHE_SIZE); } + bio_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 f59d797..e6a882a 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -8,13 +8,16 @@ #include #include #include +#include +#include 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_mem_page_cgroup(pc); + __init_bio_page_cgroup(pc); } static unsigned long total_usage; @@ -69,7 +72,7 @@ void __init page_cgroup_init(void) int nid, fail; - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled() && bio_cgroup_disabled()) return; for_each_online_node(nid) { @@ -78,12 +81,12 @@ void __init page_cgroup_init(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" + printk(KERN_INFO "please try cgroup_disable=memory,bio option if you" " don't want\n"); return; fail: printk(KERN_CRIT "allocation of page_cgroup was failed.\n"); - printk(KERN_CRIT "please try cgroup_disable=memory boot option\n"); + printk(KERN_CRIT "please try cgroup_disable=memory,bio boot options\n"); panic("Out of memory"); } @@ -229,7 +232,7 @@ void __init page_cgroup_init(void) unsigned long pfn; int fail = 0; - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled() && bio_cgroup_disabled()) return; for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) { @@ -244,7 +247,7 @@ void __init page_cgroup_init(void) 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" + printk(KERN_INFO "please try cgroup_disable=memory,bio option if you don't" " want\n"); } diff --git a/mm/swap_state.c b/mm/swap_state.c index 3353c90..42a5b45 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -305,6 +306,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, */ __set_page_locked(new_page); SetPageSwapBacked(new_page); + bio_cgroup_set_owner(new_page, current->mm); err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL); if (likely(!err)) { /* -- 1.5.4.rc3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/