From 761b3ef50e1c2649cffbfa67a4dcb2dcdb7982ed Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 31 Jan 2012 13:47:36 +0800 Subject: cgroup: remove cgroup_subsys argument from callbacks The argument is not used at all, and it's not necessary, because a specific callback handler of course knows which subsys it belongs to. Now only ->pupulate() takes this argument, because the handlers of this callback always call cgroup_add_file()/cgroup_add_files(). So we reduce a few lines of code, though the shrinking of object size is minimal. 16 files changed, 113 insertions(+), 162 deletions(-) text data bss dec hex filename 5486240 656987 7039960 13183187 c928d3 vmlinux.o.orig 5486170 656987 7039960 13183117 c9288d vmlinux.o Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- mm/memcontrol.c | 48 +++++++++++++++++++----------------------------- 1 file changed, 19 insertions(+), 29 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3dbff4dcde35..ae2f0a8ab761 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4580,10 +4580,9 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) return mem_cgroup_sockets_init(cont, ss); }; -static void kmem_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void kmem_cgroup_destroy(struct cgroup *cont) { - mem_cgroup_sockets_destroy(cont, ss); + mem_cgroup_sockets_destroy(cont); } #else static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) @@ -4591,8 +4590,7 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) return 0; } -static void kmem_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void kmem_cgroup_destroy(struct cgroup *cont) { } #endif @@ -4884,7 +4882,7 @@ err_cleanup: } static struct cgroup_subsys_state * __ref -mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) +mem_cgroup_create(struct cgroup *cont) { struct mem_cgroup *memcg, *parent; long error = -ENOMEM; @@ -4946,20 +4944,18 @@ free_out: return ERR_PTR(error); } -static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static int mem_cgroup_pre_destroy(struct cgroup *cont) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); return mem_cgroup_force_empty(memcg, false); } -static void mem_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void mem_cgroup_destroy(struct cgroup *cont) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - kmem_cgroup_destroy(ss, cont); + kmem_cgroup_destroy(cont); mem_cgroup_put(memcg); } @@ -5296,9 +5292,8 @@ static void mem_cgroup_clear_mc(void) mem_cgroup_end_move(from); } -static int mem_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); int ret = 0; @@ -5336,9 +5331,8 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { mem_cgroup_clear_mc(); } @@ -5453,9 +5447,8 @@ retry: up_read(&mm->mmap_sem); } -static void mem_cgroup_move_task(struct cgroup_subsys *ss, - struct cgroup *cont, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup *cont, + struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); struct mm_struct *mm = get_task_mm(p); @@ -5470,20 +5463,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys *ss, - struct cgroup *cont, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup *cont, + struct cgroup_taskset *tset) { } #endif -- cgit From 59927fb984de1703c67bc640c3e522d8b5276c73 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 15 Mar 2012 15:17:07 -0700 Subject: memcg: free mem_cgroup by RCU to fix oops After fixing the GPF in mem_cgroup_lru_del_list(), three times one machine running a similar load (moving and removing memcgs while swapping) has oopsed in mem_cgroup_zone_nr_lru_pages(), when retrieving memcg zone numbers for get_scan_count() for shrink_mem_cgroup_zone(): this is where a struct mem_cgroup is first accessed after being chosen by mem_cgroup_iter(). Just what protects a struct mem_cgroup from being freed, in between mem_cgroup_iter()'s css_get_next() and its css_tryget()? css_tryget() fails once css->refcnt is zero with CSS_REMOVED set in flags, yes: but what if that memory is freed and reused for something else, which sets "refcnt" non-zero? Hmm, and scope for an indefinite freeze if refcnt is left at zero but flags are cleared. It's tempting to move the css_tryget() into css_get_next(), to make it really "get" the css, but I don't think that actually solves anything: the same difficulty in moving from css_id found to stable css remains. But we already have rcu_read_lock() around the two, so it's easily fixed if __mem_cgroup_free() just uses kfree_rcu() to free mem_cgroup. However, a big struct mem_cgroup is allocated with vzalloc() instead of kzalloc(), and we're not allowed to vfree() at interrupt time: there doesn't appear to be a general vfree_rcu() to help with this, so roll our own using schedule_work(). The compiler decently removes vfree_work() and vfree_rcu() when the config doesn't need them. Signed-off-by: Hugh Dickins Acked-by: KAMEZAWA Hiroyuki Acked-by: Johannes Weiner Cc: Konstantin Khlebnikov Cc: Tejun Heo Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 47 insertions(+), 6 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d0e57a3cda18..58a08fc7414a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -230,10 +230,30 @@ struct mem_cgroup { * the counter to account for memory usage */ struct res_counter res; - /* - * the counter to account for mem+swap usage. - */ - struct res_counter memsw; + + union { + /* + * the counter to account for mem+swap usage. + */ + struct res_counter memsw; + + /* + * rcu_freeing is used only when freeing struct mem_cgroup, + * so put it into a union to avoid wasting more memory. + * It must be disjoint from the css field. It could be + * in a union with the res field, but res plays a much + * larger part in mem_cgroup life than memsw, and might + * be of interest, even at time of free, when debugging. + * So share rcu_head with the less interesting memsw. + */ + struct rcu_head rcu_freeing; + /* + * But when using vfree(), that cannot be done at + * interrupt time, so we must then queue the work. + */ + struct work_struct work_freeing; + }; + /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. @@ -4779,6 +4799,27 @@ out_free: return NULL; } +/* + * Helpers for freeing a vzalloc()ed mem_cgroup by RCU, + * but in process context. The work_freeing structure is overlaid + * on the rcu_freeing structure, which itself is overlaid on memsw. + */ +static void vfree_work(struct work_struct *work) +{ + struct mem_cgroup *memcg; + + memcg = container_of(work, struct mem_cgroup, work_freeing); + vfree(memcg); +} +static void vfree_rcu(struct rcu_head *rcu_head) +{ + struct mem_cgroup *memcg; + + memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing); + INIT_WORK(&memcg->work_freeing, vfree_work); + schedule_work(&memcg->work_freeing); +} + /* * At destroying mem_cgroup, references from swap_cgroup can remain. * (scanning all at force_empty is too costly...) @@ -4802,9 +4843,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_percpu(memcg->stat); if (sizeof(struct mem_cgroup) < PAGE_SIZE) - kfree(memcg); + kfree_rcu(memcg, rcu_freeing); else - vfree(memcg); + call_rcu(&memcg->rcu_freeing, vfree_rcu); } static void mem_cgroup_get(struct mem_cgroup *memcg) -- cgit