| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20081102144237.59ab5f03.kamezawa.hiroyu@jp.fujitsu.com>
Date: Sun, 2 Nov 2008 14:42:37 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Balbir Singh <balbir@...ux.vnet.ibm.com>
Cc: linux-mm@...ck.org, YAMAMOTO Takashi <yamamoto@...inux.co.jp>,
Paul Menage <menage@...gle.com>, lizf@...fujitsu.com,
linux-kernel@...r.kernel.org,
Nick Piggin <nickpiggin@...oo.com.au>,
David Rientjes <rientjes@...gle.com>,
Pavel Emelianov <xemul@...nvz.org>,
Dhaval Giani <dhaval@...ux.vnet.ibm.com>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [mm] [PATCH 2/4] Memory cgroup resource counters for hierarchy
On Sun, 02 Nov 2008 00:18:37 +0530
Balbir Singh <balbir@...ux.vnet.ibm.com> wrote:
>
> 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, which are linked in
> cgroup hiearchy. 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.
>
...isn't it better to add "root_lock" to res_counter rather than taking
all levels of lock one by one ?
spin_lock(&res_counter->hierarchy_root->lock);
do all charge/uncharge to hierarchy
spin_unlock(&res_counter->hierarchy_root->lock);
Hmm ?
Thaks,
-Kame
>
> Signed-off-by: Balbir Singh <balbir@...ux.vnet.ibm.com>
> ---
>
> include/linux/res_counter.h | 8 ++++++--
> kernel/res_counter.c | 42 ++++++++++++++++++++++++++++++++++--------
> mm/memcontrol.c | 9 ++++++---
> 3 files changed, 46 insertions(+), 13 deletions(-)
>
> diff -puN include/linux/res_counter.h~resource-counters-hierarchy-support include/linux/res_counter.h
> --- linux-2.6.28-rc2/include/linux/res_counter.h~resource-counters-hierarchy-support 2008-11-02 00:14:58.000000000 +0530
> +++ linux-2.6.28-rc2-balbir/include/linux/res_counter.h 2008-11-02 00:14:58.000000000 +0530
> @@ -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~resource-counters-hierarchy-support kernel/res_counter.c
> --- linux-2.6.28-rc2/kernel/res_counter.c~resource-counters-hierarchy-support 2008-11-02 00:14:58.000000000 +0530
> +++ linux-2.6.28-rc2-balbir/kernel/res_counter.c 2008-11-02 00:14:58.000000000 +0530
> @@ -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~resource-counters-hierarchy-support mm/memcontrol.c
> --- linux-2.6.28-rc2/mm/memcontrol.c~resource-counters-hierarchy-support 2008-11-02 00:14:58.000000000 +0530
> +++ linux-2.6.28-rc2-balbir/mm/memcontrol.c 2008-11-02 00:14:58.000000000 +0530
> @@ -485,6 +485,7 @@ int mem_cgroup_try_charge(struct mm_stru
> {
> 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
> @@ -510,7 +511,7 @@ int mem_cgroup_try_charge(struct mm_stru
> }
>
>
> - while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) {
> + while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE, &fail_res))) {
> if (!(gfp_mask & __GFP_WAIT))
> goto nomem;
>
> @@ -1175,18 +1176,20 @@ static void mem_cgroup_free(struct mem_c
> 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;
>
> if (unlikely((cont->parent) == NULL)) {
> mem = &init_mem_cgroup;
> + parent = NULL;
> } else {
> mem = mem_cgroup_alloc();
> + parent = mem_cgroup_from_cont(cont->parent);
> if (!mem)
> return ERR_PTR(-ENOMEM);
> }
>
> - res_counter_init(&mem->res);
> + res_counter_init(&mem->res, parent ? &parent->res : NULL);
>
> for_each_node_state(node, N_POSSIBLE)
> if (alloc_mem_cgroup_per_zone_info(mem, node))
> _
>
> --
> Balbir
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists