From 78fb74669e80883323391090e4d26d17fe29488f Mon Sep 17 00:00:00 2001 From: Pavel Emelianov Date: Thu, 7 Feb 2008 00:13:51 -0800 Subject: [PATCH] Memory controller: accounting setup Basic setup routines, the mm_struct has a pointer to the cgroup that it belongs to and the the page has a page_cgroup associated with it. Signed-off-by: Pavel Emelianov Signed-off-by: Balbir Singh Cc: Paul Menage Cc: Peter Zijlstra Cc: "Eric W. Biederman" Cc: Nick Piggin Cc: Kirill Korotaev Cc: Herbert Poetzl Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 36 ++++++++++++++++++++++++ include/linux/mm_types.h | 6 ++++ include/linux/sched.h | 1 + kernel/fork.c | 11 ++++++-- mm/memcontrol.c | 57 +++++++++++++++++++++++++++++++++++--- 5 files changed, 104 insertions(+), 7 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3f121b2767..7d1f119c79 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -3,6 +3,9 @@ * Copyright IBM Corporation, 2007 * Author Balbir Singh * + * Copyright 2007 OpenVZ SWsoft Inc + * Author: Pavel Emelianov + * * 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 @@ -17,5 +20,38 @@ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H +struct mem_cgroup; +struct page_cgroup; + +#ifdef CONFIG_CGROUP_MEM_CONT + +extern void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p); +extern void mm_free_cgroup(struct mm_struct *mm); +extern void page_assign_page_cgroup(struct page *page, + struct page_cgroup *pc); +extern struct page_cgroup *page_get_page_cgroup(struct page *page); + +#else /* CONFIG_CGROUP_MEM_CONT */ +static inline void mm_init_cgroup(struct mm_struct *mm, + struct task_struct *p) +{ +} + +static inline void mm_free_cgroup(struct mm_struct *mm) +{ +} + +static inline void page_assign_page_cgroup(struct page *page, + struct page_cgroup *pc) +{ +} + +static inline struct page_cgroup *page_get_page_cgroup(struct page *page) +{ + return NULL; +} + +#endif /* CONFIG_CGROUP_MEM_CONT */ + #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f4c03e0b35..34023c65d4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -88,6 +88,9 @@ struct page { void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_CGROUP_MEM_CONT + unsigned long page_cgroup; +#endif }; /* @@ -219,6 +222,9 @@ struct mm_struct { /* aio bits */ rwlock_t ioctx_list_lock; struct kioctx *ioctx_list; +#ifdef CONFIG_CGROUP_MEM_CONT + struct mem_cgroup *mem_cgroup; +#endif }; #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 7c8ca05c3c..8a4812c1c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -92,6 +92,7 @@ struct sched_param { #include +struct mem_cgroup; struct exec_domain; struct futex_pi_state; struct robust_list_head; diff --git a/kernel/fork.c b/kernel/fork.c index 3995297567..b2ef8e4fad 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -340,7 +341,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); #include -static struct mm_struct * mm_init(struct mm_struct * mm) +static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); @@ -357,11 +358,14 @@ static struct mm_struct * mm_init(struct mm_struct * mm) mm->ioctx_list = NULL; mm->free_area_cache = TASK_UNMAPPED_BASE; mm->cached_hole_size = ~0UL; + mm_init_cgroup(mm, p); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; return mm; } + + mm_free_cgroup(mm); free_mm(mm); return NULL; } @@ -376,7 +380,7 @@ struct mm_struct * mm_alloc(void) mm = allocate_mm(); if (mm) { memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm); + mm = mm_init(mm, current); } return mm; } @@ -390,6 +394,7 @@ void fastcall __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); mm_free_pgd(mm); + mm_free_cgroup(mm); destroy_context(mm); free_mm(mm); } @@ -511,7 +516,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk) mm->token_priority = 0; mm->last_interval = 0; - if (!mm_init(mm)) + if (!mm_init(mm, tsk)) goto fail_nomem; if (init_new_context(tsk, mm)) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 80e48cd9d0..4d4805eb37 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3,6 +3,9 @@ * Copyright IBM Corporation, 2007 * Author Balbir Singh * + * Copyright 2007 OpenVZ SWsoft Inc + * Author: Pavel Emelianov + * * 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 @@ -17,6 +20,7 @@ #include #include #include +#include struct cgroup_subsys mem_cgroup_subsys; @@ -35,6 +39,13 @@ struct mem_cgroup { * the counter to account for memory usage */ struct res_counter res; + /* + * Per cgroup active and inactive list, similar to the + * per zone LRU lists. + * TODO: Consider making these lists per zone + */ + struct list_head active_list; + struct list_head inactive_list; }; /* @@ -56,6 +67,37 @@ struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) css); } +static inline +struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) +{ + return container_of(task_subsys_state(p, mem_cgroup_subsys_id), + struct mem_cgroup, css); +} + +void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p) +{ + struct mem_cgroup *mem; + + mem = mem_cgroup_from_task(p); + css_get(&mem->css); + mm->mem_cgroup = mem; +} + +void mm_free_cgroup(struct mm_struct *mm) +{ + css_put(&mm->mem_cgroup->css); +} + +void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc) +{ + page->page_cgroup = (unsigned long)pc; +} + +struct page_cgroup *page_get_page_cgroup(struct page *page) +{ + return page->page_cgroup; +} + static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, struct file *file, char __user *userbuf, size_t nbytes, loff_t *ppos) @@ -91,14 +133,21 @@ static struct cftype mem_cgroup_files[] = { }, }; +static struct mem_cgroup init_mem_cgroup; + static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem; - mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL); - if (!mem) - return -ENOMEM; + if (unlikely((cont->parent) == NULL)) { + mem = &init_mem_cgroup; + init_mm.mem_cgroup = mem; + } else + mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL); + + if (mem == NULL) + return NULL; res_counter_init(&mem->res); return &mem->css; @@ -123,5 +172,5 @@ struct cgroup_subsys mem_cgroup_subsys = { .create = mem_cgroup_create, .destroy = mem_cgroup_destroy, .populate = mem_cgroup_populate, - .early_init = 0, + .early_init = 1, }; -- 2.39.5