The patch titled Subject: memcg: remove PCG_MOVE_LOCK flag from page_cgroup has been removed from the -mm tree. Its filename was memcg-remove-pcg_move_lock-flag-from-page_cgroup.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Subject: memcg: remove PCG_MOVE_LOCK flag from page_cgroup PCG_MOVE_LOCK is used for bit spinlock to avoid race between overwriting pc->mem_cgroup and page statistics accounting per memcg. This lock helps to avoid the race but the race is very rare because moving tasks between cgroup is not a usual job. So, it seems using 1bit per page is too costly. This patch changes this lock as per-memcg spinlock and removes PCG_MOVE_LOCK. If smaller lock is required, we'll be able to add some hashes but I'd like to start from this. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Acked-by: Greg Thelen <gthelen@xxxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> Cc: Ying Han <yinghan@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/page_cgroup.h | 19 --------------- mm/memcontrol.c | 42 +++++++++++++++++++++++++--------- 2 files changed, 32 insertions(+), 29 deletions(-) diff -puN include/linux/page_cgroup.h~memcg-remove-pcg_move_lock-flag-from-page_cgroup include/linux/page_cgroup.h --- a/include/linux/page_cgroup.h~memcg-remove-pcg_move_lock-flag-from-page_cgroup +++ a/include/linux/page_cgroup.h @@ -7,7 +7,6 @@ enum { PCG_USED, /* this object is in use. */ PCG_MIGRATION, /* under page migration */ /* flags for mem_cgroup and file and I/O status */ - PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */ PCG_FILE_MAPPED, /* page is accounted as "mapped" */ __NR_PCG_FLAGS, }; @@ -89,24 +88,6 @@ static inline void unlock_page_cgroup(st bit_spin_unlock(PCG_LOCK, &pc->flags); } -static inline void move_lock_page_cgroup(struct page_cgroup *pc, - unsigned long *flags) -{ - /* - * We know updates to pc->flags of page cache's stats are from both of - * usual context or IRQ context. Disable IRQ to avoid deadlock. - */ - local_irq_save(*flags); - bit_spin_lock(PCG_MOVE_LOCK, &pc->flags); -} - -static inline void move_unlock_page_cgroup(struct page_cgroup *pc, - unsigned long *flags) -{ - bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags); - local_irq_restore(*flags); -} - #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct page_cgroup; diff -puN mm/memcontrol.c~memcg-remove-pcg_move_lock-flag-from-page_cgroup mm/memcontrol.c --- a/mm/memcontrol.c~memcg-remove-pcg_move_lock-flag-from-page_cgroup +++ a/mm/memcontrol.c @@ -300,6 +300,8 @@ struct mem_cgroup { * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; /* * percpu counter. */ @@ -1376,6 +1378,24 @@ static bool mem_cgroup_wait_acct_move(st return false; } +/* + * Take this lock when + * - a code tries to modify page's memcg while it's USED. + * - a code tries to modify page state accounting in a memcg. + * see mem_cgroup_stealed(), too. + */ +static void move_lock_mem_cgroup(struct mem_cgroup *memcg, + unsigned long *flags) +{ + spin_lock_irqsave(&memcg->move_lock, *flags); +} + +static void move_unlock_mem_cgroup(struct mem_cgroup *memcg, + unsigned long *flags) +{ + spin_unlock_irqrestore(&memcg->move_lock, *flags); +} + /** * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode. * @memcg: The memory cgroup that went over limit @@ -1900,7 +1920,7 @@ void mem_cgroup_update_page_stat(struct if (mem_cgroup_disabled()) return; - +again: rcu_read_lock(); memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) @@ -1908,11 +1928,13 @@ void mem_cgroup_update_page_stat(struct /* pc->mem_cgroup is unstable ? */ if (unlikely(mem_cgroup_stealed(memcg))) { /* take a lock against to access pc->mem_cgroup */ - move_lock_page_cgroup(pc, &flags); + move_lock_mem_cgroup(memcg, &flags); + if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) { + move_unlock_mem_cgroup(memcg, &flags); + rcu_read_unlock(); + goto again; + } need_unlock = true; - memcg = pc->mem_cgroup; - if (!memcg || !PageCgroupUsed(pc)) - goto out; } switch (idx) { @@ -1931,7 +1953,7 @@ void mem_cgroup_update_page_stat(struct out: if (unlikely(need_unlock)) - move_unlock_page_cgroup(pc, &flags); + move_unlock_mem_cgroup(memcg, &flags); rcu_read_unlock(); } @@ -2500,8 +2522,7 @@ static void __mem_cgroup_commit_charge(s #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\ - (1 << PCG_MIGRATION)) +#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MIGRATION)) /* * Because tail pages are not marked as "used", set it. We're under * zone->lru_lock, 'splitting on pmd' and compound_lock. @@ -2572,7 +2593,7 @@ static int mem_cgroup_move_account(struc if (!PageCgroupUsed(pc) || pc->mem_cgroup != from) goto unlock; - move_lock_page_cgroup(pc, &flags); + move_lock_mem_cgroup(from, &flags); if (PageCgroupFileMapped(pc)) { /* Update mapped_file data for mem_cgroup */ @@ -2596,7 +2617,7 @@ static int mem_cgroup_move_account(struc * guaranteed that "to" is never removed. So, we don't check rmdir * status here. */ - move_unlock_page_cgroup(pc, &flags); + move_unlock_mem_cgroup(from, &flags); ret = 0; unlock: unlock_page_cgroup(pc); @@ -4971,6 +4992,7 @@ mem_cgroup_create(struct cgroup *cont) atomic_set(&memcg->refcnt, 1); memcg->move_charge_at_immigrate = 0; mutex_init(&memcg->thresholds_lock); + spin_lock_init(&memcg->move_lock); return &memcg->css; free_out: __mem_cgroup_free(memcg); _ Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are origin.patch linux-next.patch mm-hugetlb-cleanup-duplicated-code-in-unmapping-vm-range.patch proc-speedup-proc-stat-handling.patch procfs-add-num_to_str-to-speed-up-proc-stat.patch procfs-add-num_to_str-to-speed-up-proc-stat-fix.patch procfs-add-num_to_str-to-speed-up-proc-stat-fix-2.patch procfs-speed-up-proc-pid-stat-statm.patch procfs-speed-up-proc-pid-stat-statm-checkpatch-fixes.patch seq_file-add-seq_set_overflow-seq_overflow.patch seq_file-add-seq_set_overflow-seq_overflow-fix.patch fs-proc-introduce-proc-pid-task-tid-children-entry-v9.patch c-r-procfs-add-arg_start-end-env_start-end-and-exit_code-members-to-proc-pid-stat.patch c-r-prctl-extend-pr_set_mm-to-set-up-more-mm_struct-entries-v2.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