From 52d4b9ac0b985168009c2a57098324e67bae171f Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Sat, 18 Oct 2008 20:28:16 -0700 Subject: memcg: allocate all page_cgroup at boot Allocate all page_cgroup at boot and remove page_cgroup poitner from struct page. This patch adds an interface as struct page_cgroup *lookup_page_cgroup(struct page*) All FLATMEM/DISCONTIGMEM/SPARSEMEM and MEMORY_HOTPLUG is supported. Remove page_cgroup pointer reduces the amount of memory by - 4 bytes per PAGE_SIZE. - 8 bytes per PAGE_SIZE if memory controller is disabled. (even if configured.) On usual 8GB x86-32 server, this saves 8MB of NORMAL_ZONE memory. On my x86-64 server with 48GB of memory, this saves 96MB of memory. I think this reduction makes sense. By pre-allocation, kmalloc/kfree in charge/uncharge are removed. This means - we're not necessary to be afraid of kmalloc faiulre. (this can happen because of gfp_mask type.) - we can avoid calling kmalloc/kfree. - we can avoid allocating tons of small objects which can be fragmented. - we can know what amount of memory will be used for this extra-lru handling. I added printk message as "allocated %ld bytes of page_cgroup" "please try cgroup_disable=memory option if you don't want" maybe enough informative for users. Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 103 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 include/linux/page_cgroup.h (limited to 'include/linux/page_cgroup.h') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h new file mode 100644 index 00000000000..0fd39f2231e --- /dev/null +++ b/include/linux/page_cgroup.h @@ -0,0 +1,103 @@ +#ifndef __LINUX_PAGE_CGROUP_H +#define __LINUX_PAGE_CGROUP_H + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#include +/* + * Page Cgroup can be considered as an extended mem_map. + * A page_cgroup page is associated with every page descriptor. The + * page_cgroup helps us identify information about the cgroup + * All page cgroups are allocated at boot or memory hotplug event, + * then the page cgroup for pfn always exists. + */ +struct page_cgroup { + unsigned long flags; + struct mem_cgroup *mem_cgroup; + struct page *page; + struct list_head lru; /* per cgroup LRU list */ +}; + +void __init pgdat_page_cgroup_init(struct pglist_data *pgdat); +void __init page_cgroup_init(void); +struct page_cgroup *lookup_page_cgroup(struct page *page); + +enum { + /* flags for mem_cgroup */ + PCG_LOCK, /* page cgroup is locked */ + PCG_CACHE, /* charged as cache */ + PCG_USED, /* this object is in use. */ + /* flags for LRU placement */ + PCG_ACTIVE, /* page is active in this cgroup */ + PCG_FILE, /* page is file system backed */ + PCG_UNEVICTABLE, /* page is unevictableable */ +}; + +#define TESTPCGFLAG(uname, lname) \ +static inline int PageCgroup##uname(struct page_cgroup *pc) \ + { return test_bit(PCG_##lname, &pc->flags); } + +#define SETPCGFLAG(uname, lname) \ +static inline void SetPageCgroup##uname(struct page_cgroup *pc)\ + { set_bit(PCG_##lname, &pc->flags); } + +#define CLEARPCGFLAG(uname, lname) \ +static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ + { clear_bit(PCG_##lname, &pc->flags); } + +/* Cache flag is set only once (at allocation) */ +TESTPCGFLAG(Cache, CACHE) + +TESTPCGFLAG(Used, USED) +CLEARPCGFLAG(Used, USED) + +/* LRU management flags (from global-lru definition) */ +TESTPCGFLAG(File, FILE) +SETPCGFLAG(File, FILE) +CLEARPCGFLAG(File, FILE) + +TESTPCGFLAG(Active, ACTIVE) +SETPCGFLAG(Active, ACTIVE) +CLEARPCGFLAG(Active, ACTIVE) + +TESTPCGFLAG(Unevictable, UNEVICTABLE) +SETPCGFLAG(Unevictable, UNEVICTABLE) +CLEARPCGFLAG(Unevictable, UNEVICTABLE) + +static inline int page_cgroup_nid(struct page_cgroup *pc) +{ + return page_to_nid(pc->page); +} + +static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc) +{ + return page_zonenum(pc->page); +} + +static inline void lock_page_cgroup(struct page_cgroup *pc) +{ + bit_spin_lock(PCG_LOCK, &pc->flags); +} + +static inline int trylock_page_cgroup(struct page_cgroup *pc) +{ + return bit_spin_trylock(PCG_LOCK, &pc->flags); +} + +static inline void unlock_page_cgroup(struct page_cgroup *pc) +{ + bit_spin_unlock(PCG_LOCK, &pc->flags); +} + +#else /* CONFIG_CGROUP_MEM_RES_CTLR */ +struct page_cgroup; + +static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat) +{ +} + +static inline struct page_cgroup *lookup_page_cgroup(struct page *page) +{ + return NULL; +} +#endif +#endif -- cgit v1.2.3 From 94b6da5ab8293b04a300ba35c72eddfa94db8b02 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 22 Oct 2008 14:15:05 -0700 Subject: memcg: fix page_cgroup allocation page_cgroup_init() is called from mem_cgroup_init(). But at this point, we cannot call alloc_bootmem(). (and this caused panic at boot.) This patch moves page_cgroup_init() to init/main.c. Time table is following: == parse_args(). # we can trust mem_cgroup_subsys.disabled bit after this. .... cgroup_init_early() # "early" init of cgroup. .... setup_arch() # memmap is allocated. ... page_cgroup_init(); mem_init(); # we cannot call alloc_bootmem after this. .... cgroup_init() # mem_cgroup is initialized. == Before page_cgroup_init(), mem_map must be initialized. So, I added page_cgroup_init() to init/main.c directly. (*) maybe this is not very clean but - cgroup_init_early() is too early - in cgroup_init(), we have to use vmalloc instead of alloc_bootmem(). use of vmalloc area in x86-32 is important and we should avoid very large vmalloc() in x86-32. So, we want to use alloc_bootmem() and added page_cgroup_init() directly to init/main.c [akpm@linux-foundation.org: remove unneeded/bad mem_cgroup_subsys declaration] [akpm@linux-foundation.org: fix build] Acked-by: Balbir Singh Tested-by: Balbir Singh Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 5 +++++ init/main.c | 2 ++ mm/memcontrol.c | 1 - mm/page_cgroup.c | 32 +++++++++++++++++++++++++------- 4 files changed, 32 insertions(+), 8 deletions(-) (limited to 'include/linux/page_cgroup.h') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 0fd39f2231e..f546ad6fc02 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -99,5 +99,10 @@ static inline struct page_cgroup *lookup_page_cgroup(struct page *page) { return NULL; } + +static inline void page_cgroup_init(void) +{ +} + #endif #endif diff --git a/init/main.c b/init/main.c index 3e17a3bafe6..672ae75b205 100644 --- a/init/main.c +++ b/init/main.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include @@ -647,6 +648,7 @@ asmlinkage void __init start_kernel(void) vmalloc_init(); vfs_caches_init_early(); cpuset_init_early(); + page_cgroup_init(); mem_init(); enable_debug_pagealloc(); cpu_hotplug_init(); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d4a92b63e98..866dcc7eeb0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1088,7 +1088,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) int node; if (unlikely((cont->parent) == NULL)) { - page_cgroup_init(); mem = &init_mem_cgroup; } else { mem = mem_cgroup_alloc(); diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 78242b4d7ed..f59d797dc5a 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -4,8 +4,10 @@ #include #include #include +#include #include #include +#include static void __meminit __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn) @@ -67,6 +69,9 @@ void __init page_cgroup_init(void) int nid, fail; + if (mem_cgroup_subsys.disabled) + return; + for_each_online_node(nid) { fail = alloc_node_page_cgroup(nid); if (fail) @@ -107,9 +112,14 @@ int __meminit init_section_page_cgroup(unsigned long pfn) nid = page_to_nid(pfn_to_page(pfn)); table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; - base = kmalloc_node(table_size, GFP_KERNEL, nid); - if (!base) - base = vmalloc_node(table_size, nid); + if (slab_is_available()) { + base = kmalloc_node(table_size, GFP_KERNEL, nid); + if (!base) + base = vmalloc_node(table_size, nid); + } else { + base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + } if (!base) { printk(KERN_ERR "page cgroup allocation failure\n"); @@ -136,11 +146,16 @@ void __free_page_cgroup(unsigned long pfn) if (!ms || !ms->page_cgroup) return; base = ms->page_cgroup + pfn; - ms->page_cgroup = NULL; - if (is_vmalloc_addr(base)) + if (is_vmalloc_addr(base)) { vfree(base); - else - kfree(base); + ms->page_cgroup = NULL; + } else { + struct page *page = virt_to_page(base); + if (!PageReserved(page)) { /* Is bootmem ? */ + kfree(base); + ms->page_cgroup = NULL; + } + } } int online_page_cgroup(unsigned long start_pfn, @@ -214,6 +229,9 @@ void __init page_cgroup_init(void) unsigned long pfn; int fail = 0; + if (mem_cgroup_subsys.disabled) + return; + for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) { if (!pfn_present(pfn)) continue; -- cgit v1.2.3