The patch titled Subject: memcg: move HugeTLB resource count to parent cgroup on memcg removal has been removed from the -mm tree. Its filename was memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal.patch This patch was dropped because an updated version will be merged The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ From: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx> Subject: memcg: move HugeTLB resource count to parent cgroup on memcg removal Add support for memcg removal with HugeTLB resource usage. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Hillf Danton <dhillf@xxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/hugetlb.h | 8 ++++ include/linux/memcontrol.h | 14 +++++++ mm/hugetlb.c | 43 +++++++++++++++++++++++ mm/memcontrol.c | 65 +++++++++++++++++++++++++++++------ 4 files changed, 120 insertions(+), 10 deletions(-) diff -puN include/linux/hugetlb.h~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal include/linux/hugetlb.h --- a/include/linux/hugetlb.h~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal +++ a/include/linux/hugetlb.h @@ -348,4 +348,12 @@ static inline unsigned int pages_per_hug #define hstate_index(h) 0 #endif +#ifdef CONFIG_MEM_RES_CTLR_HUGETLB +extern int hugetlb_force_memcg_empty(struct cgroup *cgroup); +#else +static inline int hugetlb_force_memcg_empty(struct cgroup *cgroup) +{ + return 0; +} +#endif #endif /* _LINUX_HUGETLB_H */ diff -puN include/linux/memcontrol.h~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal include/linux/memcontrol.h --- a/include/linux/memcontrol.h~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal +++ a/include/linux/memcontrol.h @@ -429,6 +429,9 @@ extern void mem_cgroup_hugetlb_uncharge_ extern void mem_cgroup_hugetlb_uncharge_memcg(int idx, unsigned long nr_pages, struct mem_cgroup *memcg); extern int mem_cgroup_hugetlb_file_init(int idx) __init; +extern int mem_cgroup_move_hugetlb_parent(int idx, struct cgroup *cgroup, + struct page *page); +extern bool mem_cgroup_have_hugetlb_usage(struct cgroup *cgroup); #else static inline int @@ -465,6 +468,17 @@ static inline int mem_cgroup_hugetlb_fil return 0; } +static inline int +mem_cgroup_move_hugetlb_parent(int idx, struct cgroup *cgroup, + struct page *page) +{ + return 0; +} + +static inline bool mem_cgroup_have_hugetlb_usage(struct cgroup *cgroup) +{ + return 0; +} #endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ #endif /* _LINUX_MEMCONTROL_H */ diff -puN mm/hugetlb.c~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal mm/hugetlb.c --- a/mm/hugetlb.c~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal +++ a/mm/hugetlb.c @@ -1909,6 +1909,49 @@ static int __init hugetlb_init(void) } module_init(hugetlb_init); +#ifdef CONFIG_MEM_RES_CTLR_HUGETLB +/* + * Force the memcg to empty the hugetlb resources by moving them to + * the parent cgroup. We can fail if the parent cgroup's limit prevented + * the charging. This should only happen if use_hierarchy is not set. + */ +int hugetlb_force_memcg_empty(struct cgroup *cgroup) +{ + struct hstate *h; + struct page *page; + int ret = 0, idx = 0; + + do { + if (cgroup_task_count(cgroup) || !list_empty(&cgroup->children)) + goto out; + /* + * If the task doing the cgroup_rmdir got a signal + * we don't really need to loop till the hugetlb resource + * usage become zero. + */ + if (signal_pending(current)) { + ret = -EINTR; + goto out; + } + for_each_hstate(h) { + spin_lock(&hugetlb_lock); + list_for_each_entry(page, &h->hugepage_activelist, lru) { + ret = mem_cgroup_move_hugetlb_parent(idx, cgroup, page); + if (ret) { + spin_unlock(&hugetlb_lock); + goto out; + } + } + spin_unlock(&hugetlb_lock); + idx++; + } + cond_resched(); + } while (mem_cgroup_have_hugetlb_usage(cgroup)); +out: + return ret; +} +#endif + /* Should be called on processing a hugepagesz=... option */ void __init hugetlb_add_hstate(unsigned order) { diff -puN mm/memcontrol.c~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal mm/memcontrol.c --- a/mm/memcontrol.c~memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal +++ a/mm/memcontrol.c @@ -3186,9 +3186,11 @@ static inline int mem_cgroup_move_swap_a #endif #ifdef CONFIG_MEM_RES_CTLR_HUGETLB -static bool mem_cgroup_have_hugetlb_usage(struct mem_cgroup *memcg) +bool mem_cgroup_have_hugetlb_usage(struct cgroup *cgroup) { int idx; + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup); + for (idx = 0; idx < hugetlb_max_hstate; idx++) { if ((res_counter_read_u64(&memcg->hugepage[idx], RES_USAGE)) > 0) return 1; @@ -3286,10 +3288,54 @@ void mem_cgroup_hugetlb_uncharge_memcg(i res_counter_uncharge(&memcg->hugepage[idx], csize); return; } -#else -static bool mem_cgroup_have_hugetlb_usage(struct mem_cgroup *memcg) + +int mem_cgroup_move_hugetlb_parent(int idx, struct cgroup *cgroup, + struct page *page) { - return 0; + struct page_cgroup *pc; + int csize, ret = 0; + struct res_counter *fail_res; + struct cgroup *pcgrp = cgroup->parent; + struct mem_cgroup *parent = mem_cgroup_from_cont(pcgrp); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup); + + if (!get_page_unless_zero(page)) + goto out; + + pc = lookup_page_cgroup(page); + lock_page_cgroup(pc); + if (!PageCgroupUsed(pc) || pc->mem_cgroup != memcg) + goto err_out; + + csize = PAGE_SIZE << compound_order(page); + /* + * If we have use_hierarchy set we can never fail here. So instead of + * using res_counter_uncharge use the open-coded variant which just + * uncharge the child res_counter. The parent will retain the charge. + */ + if (parent->use_hierarchy) { + unsigned long flags; + struct res_counter *counter; + + counter = &memcg->hugepage[idx]; + spin_lock_irqsave(&counter->lock, flags); + res_counter_uncharge_locked(counter, csize); + spin_unlock_irqrestore(&counter->lock, flags); + } else { + ret = res_counter_charge(&parent->hugepage[idx], + csize, &fail_res); + if (ret) { + ret = -EBUSY; + goto err_out; + } + res_counter_uncharge(&memcg->hugepage[idx], csize); + } + pc->mem_cgroup = parent; +err_out: + unlock_page_cgroup(pc); + put_page(page); +out: + return ret; } #endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ @@ -3818,6 +3864,11 @@ static int mem_cgroup_force_empty(struct /* should free all ? */ if (free_all) goto try_to_free; + + /* move the hugetlb charges */ + ret = hugetlb_force_memcg_empty(cgrp); + if (ret) + goto out; move_account: do { ret = -EBUSY; @@ -5095,12 +5146,6 @@ free_out: static int mem_cgroup_pre_destroy(struct cgroup *cont) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - /* - * Don't allow memcg removal if we have HugeTLB resource - * usage. - */ - if (mem_cgroup_have_hugetlb_usage(memcg)) - return -EBUSY; return mem_cgroup_force_empty(memcg, false); } _ Patches currently in -mm which might be from aneesh.kumar@xxxxxxxxxxxxxxxxxx are linux-next.patch memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal-fix.patch memcg-move-hugetlb-resource-count-to-parent-cgroup-on-memcg-removal-fix-fix.patch hugetlb-migrate-memcg-info-from-oldpage-to-new-page-during-migration.patch hugetlb-migrate-memcg-info-from-oldpage-to-new-page-during-migration-fix.patch hugetlb-migrate-memcg-info-from-oldpage-to-new-page-during-migration-fix-2.patch memcg-add-memory-controller-documentation-for-hugetlb-management.patch memcg-fix-error-code-in-hugetlb_force_memcg_empty.patch memcg-fix-error-code-in-hugetlb_force_memcg_empty-v2.patch memcg-fix-error-code-in-hugetlb_force_memcg_empty-v2-checkpatch-fixes.patch memcg-use-res_counter_uncharge_until-in-mem_cgroup_move_hugetlb_parent.patch memcg-move-charges-to-root-cgroup-if-use_hierarchy=0-in-mem_cgroup_move_hugetlb_parent.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html