From 7ec99d6213b579a84c85ad37f2aa8ded4857c53c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Mar 2011 16:42:36 -0700 Subject: memcg: unify charge/uncharge quantities to units of pages There is no clear pattern when we pass a page count and when we pass a byte count that is a multiple of PAGE_SIZE. We never charge or uncharge subpage quantities, so convert it all to page counts. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 135 +++++++++++++++++++++++++++----------------------------- 1 file changed, 65 insertions(+), 70 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9dfbed2aacc..bc02218eab0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1109,16 +1109,16 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, * @mem: the memory cgroup * * Returns the maximum amount of memory @mem can be charged with, in - * bytes. + * pages. */ -static unsigned long long mem_cgroup_margin(struct mem_cgroup *mem) +static unsigned long mem_cgroup_margin(struct mem_cgroup *mem) { unsigned long long margin; margin = res_counter_margin(&mem->res); if (do_swap_account) margin = min(margin, res_counter_margin(&mem->memsw)); - return margin; + return margin >> PAGE_SHIFT; } static unsigned int get_swappiness(struct mem_cgroup *memcg) @@ -1647,7 +1647,7 @@ EXPORT_SYMBOL(mem_cgroup_update_page_stat); * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ -#define CHARGE_SIZE (32 * PAGE_SIZE) +#define CHARGE_BATCH 32U struct memcg_stock_pcp { struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; @@ -1822,9 +1822,10 @@ enum { CHARGE_OOM_DIE, /* the current is killed because of OOM */ }; -static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, - int csize, bool oom_check) +static int mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, + unsigned int nr_pages, bool oom_check) { + unsigned long csize = nr_pages * PAGE_SIZE; struct mem_cgroup *mem_over_limit; struct res_counter *fail_res; unsigned long flags = 0; @@ -1845,14 +1846,13 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, } else mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); /* - * csize can be either a huge page (HPAGE_SIZE), a batch of - * regular pages (CHARGE_SIZE), or a single regular page - * (PAGE_SIZE). + * nr_pages can be either a huge page (HPAGE_PMD_NR), a batch + * of regular pages (CHARGE_BATCH), or a single regular page (1). * * Never reclaim on behalf of optional batching, retry with a * single page instead. */ - if (csize == CHARGE_SIZE) + if (nr_pages == CHARGE_BATCH) return CHARGE_RETRY; if (!(gfp_mask & __GFP_WAIT)) @@ -1860,7 +1860,7 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, gfp_mask, flags); - if (mem_cgroup_margin(mem_over_limit) >= csize) + if (mem_cgroup_margin(mem_over_limit) >= nr_pages) return CHARGE_RETRY; /* * Even though the limit is exceeded at this point, reclaim @@ -1871,7 +1871,7 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, * unlikely to succeed so close to the limit, and we fall back * to regular pages anyway in case of failure. */ - if (csize == PAGE_SIZE && ret) + if (nr_pages == 1 && ret) return CHARGE_RETRY; /* @@ -1897,13 +1897,14 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, */ static int __mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcg, bool oom, - int page_size) + unsigned int nr_pages, + struct mem_cgroup **memcg, + bool oom) { + unsigned int batch = max(CHARGE_BATCH, nr_pages); int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; struct mem_cgroup *mem = NULL; int ret; - int csize = max(CHARGE_SIZE, (unsigned long) page_size); /* * Unlike gloval-vm's OOM-kill, we're not in memory shortage @@ -1928,7 +1929,7 @@ again: VM_BUG_ON(css_is_removed(&mem->css)); if (mem_cgroup_is_root(mem)) goto done; - if (page_size == PAGE_SIZE && consume_stock(mem)) + if (nr_pages == 1 && consume_stock(mem)) goto done; css_get(&mem->css); } else { @@ -1951,7 +1952,7 @@ again: rcu_read_unlock(); goto done; } - if (page_size == PAGE_SIZE && consume_stock(mem)) { + if (nr_pages == 1 && consume_stock(mem)) { /* * It seems dagerous to access memcg without css_get(). * But considering how consume_stok works, it's not @@ -1986,13 +1987,12 @@ again: nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; } - ret = __mem_cgroup_do_charge(mem, gfp_mask, csize, oom_check); - + ret = mem_cgroup_do_charge(mem, gfp_mask, batch, oom_check); switch (ret) { case CHARGE_OK: break; case CHARGE_RETRY: /* not in OOM situation but retry */ - csize = page_size; + batch = nr_pages; css_put(&mem->css); mem = NULL; goto again; @@ -2013,8 +2013,8 @@ again: } } while (ret != CHARGE_OK); - if (csize > page_size) - refill_stock(mem, (csize - page_size) >> PAGE_SHIFT); + if (batch > nr_pages) + refill_stock(mem, batch - nr_pages); css_put(&mem->css); done: *memcg = mem; @@ -2093,12 +2093,10 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, struct page *page, + unsigned int nr_pages, struct page_cgroup *pc, - enum charge_type ctype, - int page_size) + enum charge_type ctype) { - int nr_pages = page_size >> PAGE_SHIFT; - lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); @@ -2187,26 +2185,28 @@ void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail) /** * mem_cgroup_move_account - move account of the page * @page: the page + * @nr_pages: number of regular pages (>1 for huge pages) * @pc: page_cgroup of the page. * @from: mem_cgroup which the page is moved from. * @to: mem_cgroup which the page is moved to. @from != @to. * @uncharge: whether we should call uncharge and css_put against @from. - * @charge_size: number of bytes to charge (regular or huge page) * * The caller must confirm following. * - page is not on LRU (isolate_page() is useful.) - * - compound_lock is held when charge_size > PAGE_SIZE + * - compound_lock is held when nr_pages > 1 * * This function doesn't do "charge" nor css_get to new cgroup. It should be * done by a caller(__mem_cgroup_try_charge would be usefull). If @uncharge is * true, this function does "uncharge" from old cgroup, but it doesn't if * @uncharge is false, so a caller should do "uncharge". */ -static int mem_cgroup_move_account(struct page *page, struct page_cgroup *pc, - struct mem_cgroup *from, struct mem_cgroup *to, - bool uncharge, int charge_size) +static int mem_cgroup_move_account(struct page *page, + unsigned int nr_pages, + struct page_cgroup *pc, + struct mem_cgroup *from, + struct mem_cgroup *to, + bool uncharge) { - int nr_pages = charge_size >> PAGE_SHIFT; unsigned long flags; int ret; @@ -2219,7 +2219,7 @@ static int mem_cgroup_move_account(struct page *page, struct page_cgroup *pc, * hold it. */ ret = -EBUSY; - if (charge_size > PAGE_SIZE && !PageTransHuge(page)) + if (nr_pages > 1 && !PageTransHuge(page)) goto out; lock_page_cgroup(pc); @@ -2277,7 +2277,7 @@ static int mem_cgroup_move_parent(struct page *page, struct cgroup *cg = child->css.cgroup; struct cgroup *pcg = cg->parent; struct mem_cgroup *parent; - int page_size = PAGE_SIZE; + unsigned int nr_pages; unsigned long flags; int ret; @@ -2291,23 +2291,21 @@ static int mem_cgroup_move_parent(struct page *page, if (isolate_lru_page(page)) goto put; - if (PageTransHuge(page)) - page_size = HPAGE_SIZE; + nr_pages = hpage_nr_pages(page); parent = mem_cgroup_from_cont(pcg); - ret = __mem_cgroup_try_charge(NULL, gfp_mask, - &parent, false, page_size); + ret = __mem_cgroup_try_charge(NULL, gfp_mask, nr_pages, &parent, false); if (ret || !parent) goto put_back; - if (page_size > PAGE_SIZE) + if (nr_pages > 1) flags = compound_lock_irqsave(page); - ret = mem_cgroup_move_account(page, pc, child, parent, true, page_size); + ret = mem_cgroup_move_account(page, nr_pages, pc, child, parent, true); if (ret) - __mem_cgroup_cancel_charge(parent, page_size >> PAGE_SHIFT); + __mem_cgroup_cancel_charge(parent, nr_pages); - if (page_size > PAGE_SIZE) + if (nr_pages > 1) compound_unlock_irqrestore(page, flags); put_back: putback_lru_page(page); @@ -2327,13 +2325,13 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, enum charge_type ctype) { struct mem_cgroup *mem = NULL; - int page_size = PAGE_SIZE; + unsigned int nr_pages = 1; struct page_cgroup *pc; bool oom = true; int ret; if (PageTransHuge(page)) { - page_size <<= compound_order(page); + nr_pages <<= compound_order(page); VM_BUG_ON(!PageTransHuge(page)); /* * Never OOM-kill a process for a huge page. The @@ -2345,11 +2343,11 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, pc = lookup_page_cgroup(page); BUG_ON(!pc); /* XXX: remove this and move pc lookup into commit */ - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size); + ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &mem, oom); if (ret || !mem) return ret; - __mem_cgroup_commit_charge(mem, page, pc, ctype, page_size); + __mem_cgroup_commit_charge(mem, page, nr_pages, pc, ctype); return 0; } @@ -2465,13 +2463,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, if (!mem) goto charge_cur_mm; *ptr = mem; - ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, PAGE_SIZE); + ret = __mem_cgroup_try_charge(NULL, mask, 1, ptr, true); css_put(&mem->css); return ret; charge_cur_mm: if (unlikely(!mm)) mm = &init_mm; - return __mem_cgroup_try_charge(mm, mask, ptr, true, PAGE_SIZE); + return __mem_cgroup_try_charge(mm, mask, 1, ptr, true); } static void @@ -2487,7 +2485,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, cgroup_exclude_rmdir(&ptr->css); pc = lookup_page_cgroup(page); mem_cgroup_lru_del_before_commit_swapcache(page); - __mem_cgroup_commit_charge(ptr, page, pc, ctype, PAGE_SIZE); + __mem_cgroup_commit_charge(ptr, page, 1, pc, ctype); mem_cgroup_lru_add_after_commit_swapcache(page); /* * Now swap is on-memory. This means this page may be @@ -2539,12 +2537,13 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) __mem_cgroup_cancel_charge(mem, 1); } -static void -__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype, - int page_size) +static void mem_cgroup_do_uncharge(struct mem_cgroup *mem, + unsigned int nr_pages, + const enum charge_type ctype) { struct memcg_batch_info *batch = NULL; bool uncharge_memsw = true; + /* If swapout, usage of swap doesn't decrease */ if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) uncharge_memsw = false; @@ -2568,7 +2567,7 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype, if (!batch->do_batch || test_thread_flag(TIF_MEMDIE)) goto direct_uncharge; - if (page_size != PAGE_SIZE) + if (nr_pages > 1) goto direct_uncharge; /* @@ -2584,9 +2583,9 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype, batch->memsw_nr_pages++; return; direct_uncharge: - res_counter_uncharge(&mem->res, page_size); + res_counter_uncharge(&mem->res, nr_pages * PAGE_SIZE); if (uncharge_memsw) - res_counter_uncharge(&mem->memsw, page_size); + res_counter_uncharge(&mem->memsw, nr_pages * PAGE_SIZE); if (unlikely(batch->memcg != mem)) memcg_oom_recover(mem); return; @@ -2598,10 +2597,9 @@ direct_uncharge: static struct mem_cgroup * __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { - int count; - struct page_cgroup *pc; struct mem_cgroup *mem = NULL; - int page_size = PAGE_SIZE; + unsigned int nr_pages = 1; + struct page_cgroup *pc; if (mem_cgroup_disabled()) return NULL; @@ -2610,11 +2608,9 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) return NULL; if (PageTransHuge(page)) { - page_size <<= compound_order(page); + nr_pages <<= compound_order(page); VM_BUG_ON(!PageTransHuge(page)); } - - count = page_size >> PAGE_SHIFT; /* * Check if our page_cgroup is valid */ @@ -2647,7 +2643,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } - mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -count); + mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -nr_pages); ClearPageCgroupUsed(pc); /* @@ -2668,7 +2664,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mem_cgroup_get(mem); } if (!mem_cgroup_is_root(mem)) - __do_uncharge(mem, ctype, page_size); + mem_cgroup_do_uncharge(mem, nr_pages, ctype); return mem; @@ -2860,8 +2856,8 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, int mem_cgroup_prepare_migration(struct page *page, struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask) { - struct page_cgroup *pc; struct mem_cgroup *mem = NULL; + struct page_cgroup *pc; enum charge_type ctype; int ret = 0; @@ -2917,7 +2913,7 @@ int mem_cgroup_prepare_migration(struct page *page, return 0; *ptr = mem; - ret = __mem_cgroup_try_charge(NULL, gfp_mask, ptr, false, PAGE_SIZE); + ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, ptr, false); css_put(&mem->css);/* drop extra refcnt */ if (ret || *ptr == NULL) { if (PageAnon(page)) { @@ -2944,7 +2940,7 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - __mem_cgroup_commit_charge(mem, page, pc, ctype, PAGE_SIZE); + __mem_cgroup_commit_charge(mem, page, 1, pc, ctype); return ret; } @@ -4598,8 +4594,7 @@ one_by_one: batch_count = PRECHARGE_COUNT_AT_ONCE; cond_resched(); } - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false, - PAGE_SIZE); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, 1, &mem, false); if (ret || !mem) /* mem_cgroup_clear_mc() will do uncharge later */ return -ENOMEM; @@ -4945,8 +4940,8 @@ retry: if (isolate_lru_page(page)) goto put; pc = lookup_page_cgroup(page); - if (!mem_cgroup_move_account(page, pc, - mc.from, mc.to, false, PAGE_SIZE)) { + if (!mem_cgroup_move_account(page, 1, pc, + mc.from, mc.to, false)) { mc.precharge--; /* we uncharge from mc.from later. */ mc.moved_charge++; -- cgit v1.2.3