The patch titled memcg: memory cgroup resource counters for hierarchy has been added to the -mm tree. Its filename is memory-cgroup-resource-counters-for-hierarchy-v4.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: memcg: memory cgroup resource counters for hierarchy From: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> Add support for building hierarchies in resource counters. Cgroups allows us to build a deep hierarchy, but we currently don't link the resource counters belonging to the memory controller control groups, in the same fashion as the corresponding cgroup entries in the cgroup hierarchy. This patch provides the infrastructure for resource counters that have the same hiearchy as their cgroup counter parts. These set of patches are based on the resource counter hiearchy patches posted by Pavel Emelianov. NOTE: Building hiearchies is expensive, deeper hierarchies imply charging the all the way up to the root. It is known that hiearchies are expensive, so the user needs to be careful and aware of the trade-offs before creating very deep ones. Signed-off-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> Cc: YAMAMOTO Takashi <yamamoto@xxxxxxxxxxxxx> Cc: Paul Menage <menage@xxxxxxxxxx> Cc: Li Zefan <lizf@xxxxxxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Pavel Emelianov <xemul@xxxxxxxxxx> Cc: Dhaval Giani <dhaval@xxxxxxxxxxxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/res_counter.h | 8 ++++-- kernel/res_counter.c | 42 +++++++++++++++++++++++++++------- mm/memcontrol.c | 20 ++++++++++------ 3 files changed, 53 insertions(+), 17 deletions(-) diff -puN include/linux/res_counter.h~memory-cgroup-resource-counters-for-hierarchy-v4 include/linux/res_counter.h --- a/include/linux/res_counter.h~memory-cgroup-resource-counters-for-hierarchy-v4 +++ a/include/linux/res_counter.h @@ -43,6 +43,10 @@ struct res_counter { * the routines below consider this to be IRQ-safe */ spinlock_t lock; + /* + * Parent counter, used for hierarchial resource accounting + */ + struct res_counter *parent; }; /** @@ -87,7 +91,7 @@ enum { * helpers for accounting */ -void res_counter_init(struct res_counter *counter); +void res_counter_init(struct res_counter *counter, struct res_counter *parent); /* * charge - try to consume more resource. @@ -103,7 +107,7 @@ void res_counter_init(struct res_counter int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val); + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released diff -puN kernel/res_counter.c~memory-cgroup-resource-counters-for-hierarchy-v4 kernel/res_counter.c --- a/kernel/res_counter.c~memory-cgroup-resource-counters-for-hierarchy-v4 +++ a/kernel/res_counter.c @@ -15,10 +15,11 @@ #include <linux/uaccess.h> #include <linux/mm.h> -void res_counter_init(struct res_counter *counter) +void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); counter->limit = (unsigned long long)LLONG_MAX; + counter->parent = parent; } int res_counter_charge_locked(struct res_counter *counter, unsigned long val) @@ -34,14 +35,34 @@ int res_counter_charge_locked(struct res return 0; } -int res_counter_charge(struct res_counter *counter, unsigned long val) +int res_counter_charge(struct res_counter *counter, unsigned long val, + struct res_counter **limit_fail_at) { int ret; unsigned long flags; + struct res_counter *c, *u; - spin_lock_irqsave(&counter->lock, flags); - ret = res_counter_charge_locked(counter, val); - spin_unlock_irqrestore(&counter->lock, flags); + *limit_fail_at = NULL; + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + ret = res_counter_charge_locked(c, val); + spin_unlock(&c->lock); + if (ret < 0) { + *limit_fail_at = c; + goto undo; + } + } + ret = 0; + goto done; +undo: + for (u = counter; u != c; u = u->parent) { + spin_lock(&u->lock); + res_counter_uncharge_locked(u, val); + spin_unlock(&u->lock); + } +done: + local_irq_restore(flags); return ret; } @@ -56,10 +77,15 @@ void res_counter_uncharge_locked(struct void res_counter_uncharge(struct res_counter *counter, unsigned long val) { unsigned long flags; + struct res_counter *c; - spin_lock_irqsave(&counter->lock, flags); - res_counter_uncharge_locked(counter, val); - spin_unlock_irqrestore(&counter->lock, flags); + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + res_counter_uncharge_locked(c, val); + spin_unlock(&c->lock); + } + local_irq_restore(flags); } diff -puN mm/memcontrol.c~memory-cgroup-resource-counters-for-hierarchy-v4 mm/memcontrol.c --- a/mm/memcontrol.c~memory-cgroup-resource-counters-for-hierarchy-v4 +++ a/mm/memcontrol.c @@ -471,6 +471,7 @@ static int __mem_cgroup_try_charge(struc { struct mem_cgroup *mem; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + struct res_counter *fail_res; /* * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the @@ -499,11 +500,12 @@ static int __mem_cgroup_try_charge(struc int ret; bool noswap = false; - ret = res_counter_charge(&mem->res, PAGE_SIZE); + ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; - ret = res_counter_charge(&mem->memsw, PAGE_SIZE); + ret = res_counter_charge(&mem->memsw, PAGE_SIZE, + &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ @@ -1699,22 +1701,26 @@ static void __init enable_swap_cgroup(vo static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { - struct mem_cgroup *mem; + struct mem_cgroup *mem, *parent; int node; mem = mem_cgroup_alloc(); if (!mem) return ERR_PTR(-ENOMEM); - res_counter_init(&mem->res); - res_counter_init(&mem->memsw); - for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; /* root ? */ - if (cont->parent == NULL) + if (cont->parent == NULL) { enable_swap_cgroup(); + parent = NULL; + } else + parent = mem_cgroup_from_cont(cont->parent); + + res_counter_init(&mem->res, parent ? &parent->res : NULL); + res_counter_init(&mem->memsw, parent ? &parent->memsw : NULL); + return &mem->css; free_out: _ Patches currently in -mm which might be from balbir@xxxxxxxxxxxxxxxxxx are linux-next.patch cgroup-fix-potential-deadlock-in-pre_destroy-v2.patch memcg-swap-cgroup-for-remembering-usage-fix-2.patch memcg-swap-cgroup-for-remembering-usage-fix-3.patch memory-cgroup-hierarchy-documentation-v4.patch memory-cgroup-resource-counters-for-hierarchy-v4.patch memory-cgroup-hierarchical-reclaim-v4.patch memory-cgroup-hierarchy-feature-selector-v4.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