From nobody Tue Dec 16 20:00:50 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id B2E5AC07480 for ; Thu, 19 Oct 2023 22:54:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1346715AbjJSWyW (ORCPT ); Thu, 19 Oct 2023 18:54:22 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58798 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1346700AbjJSWyS (ORCPT ); Thu, 19 Oct 2023 18:54:18 -0400 Received: from out-200.mta0.migadu.com (out-200.mta0.migadu.com [91.218.175.200]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D73F6FA for ; Thu, 19 Oct 2023 15:54:15 -0700 (PDT) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1697756054; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=y1KwfJjJzwSt9NrrtAyc2/Wpa50oBD8kLBiaGTTPdeA=; b=tDTOjE7DTyy4cSZ1350GJsSA3an2i9cqKy1Q4g2SjTywV4u7mYWzqZBqKvIOjqWS/umloV Nq23nSYhq58l4XAmk6FYdMmmNVtkWSCRU7hLVRIZugprr05e2F0LexTYgAcqIDzRXPLir3 PMy2G1M3GhmwtZ5YIE+BY24OtDtLYO8= From: Roman Gushchin To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Johannes Weiner , Michal Hocko , Shakeel Butt , Muchun Song , Dennis Zhou , David Rientjes , Vlastimil Babka , Naresh Kamboju , Roman Gushchin Subject: [PATCH v5 1/6] mm: kmem: optimize get_obj_cgroup_from_current() Date: Thu, 19 Oct 2023 15:53:41 -0700 Message-ID: <20231019225346.1822282-2-roman.gushchin@linux.dev> In-Reply-To: <20231019225346.1822282-1-roman.gushchin@linux.dev> References: <20231019225346.1822282-1-roman.gushchin@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Manually inline memcg_kmem_bypass() and active_memcg() to speed up get_obj_cgroup_from_current() by avoiding duplicate in_task() checks and active_memcg() readings. Also add a likely() macro to __get_obj_cgroup_from_memcg(): obj_cgroup_tryget() should succeed at almost all times except a very unlikely race with the memcg deletion path. Signed-off-by: Roman Gushchin (Cruise) Tested-by: Naresh Kamboju Acked-by: Shakeel Butt Acked-by: Johannes Weiner Reviewed-by: Vlastimil Babka --- mm/memcontrol.c | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9741d62d0424..16ac2a5838fb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1068,19 +1068,6 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_= struct *mm) } EXPORT_SYMBOL(get_mem_cgroup_from_mm); =20 -static __always_inline bool memcg_kmem_bypass(void) -{ - /* Allow remote memcg charging from any context. */ - if (unlikely(active_memcg())) - return false; - - /* Memcg to charge can't be determined. */ - if (!in_task() || !current->mm || (current->flags & PF_KTHREAD)) - return true; - - return false; -} - /** * mem_cgroup_iter - iterate over memory cgroup hierarchy * @root: hierarchy root @@ -3007,7 +2994,7 @@ static struct obj_cgroup *__get_obj_cgroup_from_memcg= (struct mem_cgroup *memcg) =20 for (; !mem_cgroup_is_root(memcg); memcg =3D parent_mem_cgroup(memcg)) { objcg =3D rcu_dereference(memcg->objcg); - if (objcg && obj_cgroup_tryget(objcg)) + if (likely(objcg && obj_cgroup_tryget(objcg))) break; objcg =3D NULL; } @@ -3016,16 +3003,23 @@ static struct obj_cgroup *__get_obj_cgroup_from_mem= cg(struct mem_cgroup *memcg) =20 __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) { - struct obj_cgroup *objcg =3D NULL; struct mem_cgroup *memcg; + struct obj_cgroup *objcg; =20 - if (memcg_kmem_bypass()) - return NULL; + if (in_task()) { + memcg =3D current->active_memcg; + + /* Memcg to charge can't be determined. */ + if (likely(!memcg) && (!current->mm || (current->flags & PF_KTHREAD))) + return NULL; + } else { + memcg =3D this_cpu_read(int_active_memcg); + if (likely(!memcg)) + return NULL; + } =20 rcu_read_lock(); - if (unlikely(active_memcg())) - memcg =3D active_memcg(); - else + if (!memcg) memcg =3D mem_cgroup_from_task(current); objcg =3D __get_obj_cgroup_from_memcg(memcg); rcu_read_unlock(); --=20 2.42.0 From nobody Tue Dec 16 20:00:50 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 53AF9C07480 for ; Thu, 19 Oct 2023 22:54:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1346726AbjJSWy2 (ORCPT ); Thu, 19 Oct 2023 18:54:28 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58822 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1346706AbjJSWyU (ORCPT ); Thu, 19 Oct 2023 18:54:20 -0400 Received: from out-199.mta0.migadu.com (out-199.mta0.migadu.com [IPv6:2001:41d0:1004:224b::c7]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4E737126 for ; Thu, 19 Oct 2023 15:54:18 -0700 (PDT) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1697756056; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=BDgQ0sTDZEWEeAci7LBUiUqwaAWQt9IHTOfrbC8DqQs=; b=fL6Ma5oJS1yv97IrEAJ77mrasInr+A/crITevGQ0uLYteMKKaYIA/cYsV3yA8y96/XCBjG U2IV9UTj9jUvPJfZSNBU/fXC8YCVyL6TuHNvxuu0KaDLplBsBCYB7rdJ2jGH0ZszM6YZoG ScQD3a19KgfN3bbavvQaI7wwRLw/nfM= From: Roman Gushchin To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Johannes Weiner , Michal Hocko , Shakeel Butt , Muchun Song , Dennis Zhou , David Rientjes , Vlastimil Babka , Naresh Kamboju , Roman Gushchin Subject: [PATCH v5 2/6] mm: kmem: add direct objcg pointer to task_struct Date: Thu, 19 Oct 2023 15:53:42 -0700 Message-ID: <20231019225346.1822282-3-roman.gushchin@linux.dev> In-Reply-To: <20231019225346.1822282-1-roman.gushchin@linux.dev> References: <20231019225346.1822282-1-roman.gushchin@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" To charge a freshly allocated kernel object to a memory cgroup, the kernel needs to obtain an objcg pointer. Currently it does it indirectly by obtaining the memcg pointer first and then calling to __get_obj_cgroup_from_memcg(). Usually tasks spend their entire life belonging to the same object cgroup. So it makes sense to save the objcg pointer on task_struct directly, so it can be obtained faster. It requires some work on fork, exit and cgroup migrate paths, but these paths are way colder. To avoid any costly synchronization the following rules are applied: 1) A task sets it's objcg pointer itself. 2) If a task is being migrated to another cgroup, the least significant bit of the objcg pointer is set atomically. 3) On the allocation path the objcg pointer is obtained locklessly using the READ_ONCE() macro and the least significant bit is checked. If it's set, the following procedure is used to update it locklessly: - task->objcg is zeroed using cmpxcg - new objcg pointer is obtained - task->objcg is updated using try_cmpxchg - operation is repeated if try_cmpxcg fails It guarantees that no updates will be lost if task migration is racing against objcg pointer update. It also allows to keep both read and write paths fully lockless. Because the task is keeping a reference to the objcg, it can't go away while the task is alive. This commit doesn't change the way the remote memcg charging works. Signed-off-by: Roman Gushchin (Cruise) Tested-by: Naresh Kamboju Acked-by: Johannes Weiner Acked-by: Shakeel Butt Reviewed-by: Vlastimil Babka --- include/linux/sched.h | 4 ++ mm/memcontrol.c | 139 +++++++++++++++++++++++++++++++++++++++--- 2 files changed, 134 insertions(+), 9 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 77f01ac385f7..60de42715b56 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1443,6 +1443,10 @@ struct task_struct { struct mem_cgroup *active_memcg; #endif =20 +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup *objcg; +#endif + #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 16ac2a5838fb..4c4b1f85f939 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -249,6 +249,9 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressur= e *vmpr) return container_of(vmpr, struct mem_cgroup, vmpressure); } =20 +#define CURRENT_OBJCG_UPDATE_BIT 0 +#define CURRENT_OBJCG_UPDATE_FLAG (1UL << CURRENT_OBJCG_UPDATE_BIT) + #ifdef CONFIG_MEMCG_KMEM static DEFINE_SPINLOCK(objcg_lock); =20 @@ -3001,6 +3004,58 @@ static struct obj_cgroup *__get_obj_cgroup_from_memc= g(struct mem_cgroup *memcg) return objcg; } =20 +static struct obj_cgroup *current_objcg_update(void) +{ + struct mem_cgroup *memcg; + struct obj_cgroup *old, *objcg =3D NULL; + + do { + /* Atomically drop the update bit. */ + old =3D xchg(¤t->objcg, NULL); + if (old) { + old =3D (struct obj_cgroup *) + ((unsigned long)old & ~CURRENT_OBJCG_UPDATE_FLAG); + if (old) + obj_cgroup_put(old); + + old =3D NULL; + } + + /* If new objcg is NULL, no reason for the second atomic update. */ + if (!current->mm || (current->flags & PF_KTHREAD)) + return NULL; + + /* + * Release the objcg pointer from the previous iteration, + * if try_cmpxcg() below fails. + */ + if (unlikely(objcg)) { + obj_cgroup_put(objcg); + objcg =3D NULL; + } + + /* + * Obtain the new objcg pointer. The current task can be + * asynchronously moved to another memcg and the previous + * memcg can be offlined. So let's get the memcg pointer + * and try get a reference to objcg under a rcu read lock. + */ + + rcu_read_lock(); + memcg =3D mem_cgroup_from_task(current); + objcg =3D __get_obj_cgroup_from_memcg(memcg); + rcu_read_unlock(); + + /* + * Try set up a new objcg pointer atomically. If it + * fails, it means the update flag was set concurrently, so + * the whole procedure should be repeated. + */ + } while (!try_cmpxchg(¤t->objcg, &old, objcg)); + + return objcg; +} + __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) { struct mem_cgroup *memcg; @@ -3008,19 +3063,26 @@ __always_inline struct obj_cgroup *get_obj_cgroup_f= rom_current(void) =20 if (in_task()) { memcg =3D current->active_memcg; + if (unlikely(memcg)) + goto from_memcg; =20 - /* Memcg to charge can't be determined. */ - if (likely(!memcg) && (!current->mm || (current->flags & PF_KTHREAD))) - return NULL; + objcg =3D READ_ONCE(current->objcg); + if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG)) + objcg =3D current_objcg_update(); + + if (objcg) { + obj_cgroup_get(objcg); + return objcg; + } } else { memcg =3D this_cpu_read(int_active_memcg); - if (likely(!memcg)) - return NULL; + if (unlikely(memcg)) + goto from_memcg; } + return NULL; =20 +from_memcg: rcu_read_lock(); - if (!memcg) - memcg =3D mem_cgroup_from_task(current); objcg =3D __get_obj_cgroup_from_memcg(memcg); rcu_read_unlock(); return objcg; @@ -6345,6 +6407,7 @@ static void mem_cgroup_move_task(void) mem_cgroup_clear_mc(); } } + #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { @@ -6358,8 +6421,39 @@ static void mem_cgroup_move_task(void) } #endif =20 +#ifdef CONFIG_MEMCG_KMEM +static void mem_cgroup_fork(struct task_struct *task) +{ + /* + * Set the update flag to cause task->objcg to be initialized lazily + * on the first allocation. It can be done without any synchronization + * because it's always performed on the current task, so does + * current_objcg_update(). + */ + task->objcg =3D (struct obj_cgroup *)CURRENT_OBJCG_UPDATE_FLAG; +} + +static void mem_cgroup_exit(struct task_struct *task) +{ + struct obj_cgroup *objcg =3D task->objcg; + + objcg =3D (struct obj_cgroup *) + ((unsigned long)objcg & ~CURRENT_OBJCG_UPDATE_FLAG); + if (objcg) + obj_cgroup_put(objcg); + + /* + * Some kernel allocations can happen after this point, + * but let's ignore them. It can be done without any synchronization + * because it's always performed on the current task, so does + * current_objcg_update(). + */ + task->objcg =3D NULL; +} +#endif + #ifdef CONFIG_LRU_GEN -static void mem_cgroup_attach(struct cgroup_taskset *tset) +static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *css; @@ -6377,10 +6471,31 @@ static void mem_cgroup_attach(struct cgroup_taskset= *tset) task_unlock(task); } #else +static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) {} +#endif /* CONFIG_LRU_GEN */ + +#ifdef CONFIG_MEMCG_KMEM +static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(task, css, tset) { + /* atomically set the update bit */ + set_bit(CURRENT_OBJCG_UPDATE_BIT, (unsigned long *)&task->objcg); + } +} +#else +static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset) {} +#endif /* CONFIG_MEMCG_KMEM */ + +#if defined(CONFIG_LRU_GEN) || defined(CONFIG_MEMCG_KMEM) static void mem_cgroup_attach(struct cgroup_taskset *tset) { + mem_cgroup_lru_gen_attach(tset); + mem_cgroup_kmem_attach(tset); } -#endif /* CONFIG_LRU_GEN */ +#endif =20 static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value) { @@ -6824,9 +6939,15 @@ struct cgroup_subsys memory_cgrp_subsys =3D { .css_reset =3D mem_cgroup_css_reset, .css_rstat_flush =3D mem_cgroup_css_rstat_flush, .can_attach =3D mem_cgroup_can_attach, +#if defined(CONFIG_LRU_GEN) || defined(CONFIG_MEMCG_KMEM) .attach =3D mem_cgroup_attach, +#endif .cancel_attach =3D mem_cgroup_cancel_attach, .post_attach =3D mem_cgroup_move_task, +#ifdef CONFIG_MEMCG_KMEM + .fork =3D mem_cgroup_fork, + .exit =3D mem_cgroup_exit, +#endif .dfl_cftypes =3D memory_files, .legacy_cftypes =3D mem_cgroup_legacy_files, .early_init =3D 0, --=20 2.42.0 From nobody Tue Dec 16 20:00:50 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9BB70C004C0 for ; Thu, 19 Oct 2023 22:54:36 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235564AbjJSWyb (ORCPT ); Thu, 19 Oct 2023 18:54:31 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:58886 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1346716AbjJSWy0 (ORCPT ); Thu, 19 Oct 2023 18:54:26 -0400 Received: from out-201.mta0.migadu.com (out-201.mta0.migadu.com [91.218.175.201]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C9DED130 for ; Thu, 19 Oct 2023 15:54:20 -0700 (PDT) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1697756059; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=TjRbekCofEjC4WvfGU9ZZivZap7GfKCofqK2R8XbFtA=; b=CSSCOtFvi7Ic1PfkshMhl604bLC9wtck8ncGfvc+CVnVI76s2gWESUbI5kqm+wkB4NEvbZ f6YjpCeVY9hDbH+wgY8JXIJC3BqE3wtExzGADF2pr5NRWaoryj7dR2Vq4KjLwkGq+VQNHQ phUAsoG9TN53NmVeOn9ebjkFEG27Nx4= From: Roman Gushchin To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Johannes Weiner , Michal Hocko , Shakeel Butt , Muchun Song , Dennis Zhou , David Rientjes , Vlastimil Babka , Naresh Kamboju , Roman Gushchin Subject: [PATCH v5 3/6] mm: kmem: make memcg keep a reference to the original objcg Date: Thu, 19 Oct 2023 15:53:43 -0700 Message-ID: <20231019225346.1822282-4-roman.gushchin@linux.dev> In-Reply-To: <20231019225346.1822282-1-roman.gushchin@linux.dev> References: <20231019225346.1822282-1-roman.gushchin@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Keep a reference to the original objcg object for the entire life of a memcg structure. This allows to simplify the synchronization on the kernel memory allocation paths: pinning a (live) memcg will also pin the corresponding objcg. The memory overhead of this change is minimal because object cgroups usually outlive their corresponding memory cgroups even without this change, so it's only an additional pointer per memcg. Signed-off-by: Roman Gushchin (Cruise) Tested-by: Naresh Kamboju Acked-by: Shakeel Butt Reviewed-by: Vlastimil Babka --- include/linux/memcontrol.h | 8 +++++++- mm/memcontrol.c | 5 +++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ab94ad4597d0..277690af383d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -299,7 +299,13 @@ struct mem_cgroup { =20 #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; - struct obj_cgroup __rcu *objcg; + /* + * memcg->objcg is wiped out as a part of the objcg repaprenting + * process. memcg->orig_objcg preserves a pointer (and a reference) + * to the original objcg until the end of live of memcg. + */ + struct obj_cgroup __rcu *objcg; + struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4c4b1f85f939..d964b91f00c8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3817,6 +3817,8 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) =20 objcg->memcg =3D memcg; rcu_assign_pointer(memcg->objcg, objcg); + obj_cgroup_get(objcg); + memcg->orig_objcg =3D objcg; =20 static_branch_enable(&memcg_kmem_online_key); =20 @@ -5311,6 +5313,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memc= g) { int node; =20 + if (memcg->orig_objcg) + obj_cgroup_put(memcg->orig_objcg); + for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); kfree(memcg->vmstats); --=20 2.42.0 From nobody Tue Dec 16 20:00:50 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5E9E3C001DF for ; Thu, 19 Oct 2023 22:54:37 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1346728AbjJSWyf (ORCPT ); Thu, 19 Oct 2023 18:54:35 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33752 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1346723AbjJSWy1 (ORCPT ); Thu, 19 Oct 2023 18:54:27 -0400 Received: from out-193.mta0.migadu.com (out-193.mta0.migadu.com [IPv6:2001:41d0:1004:224b::c1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 8358B13E for ; Thu, 19 Oct 2023 15:54:23 -0700 (PDT) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1697756061; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=pDnnpwCoxO5+bFywRQVLc1PnF6OgSg7x79d5yFEGT34=; b=sGeh2eLuqe4WxFhppV5sFaG5eq+hU2ncs7PB5wWtuwi9wuQ83DIpEfCWbmhaaM3Z0oorFh Gywt8n3wZ9fPKg5gzb4CafmEc4yw2GFuunbhvb7QRbVJcJ8Ev4CMG8FjkPrPZ6tItPdg2l 6Qx9XK+gG2BpjvOuaf0sGgY6GvXiHHk= From: Roman Gushchin To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Johannes Weiner , Michal Hocko , Shakeel Butt , Muchun Song , Dennis Zhou , David Rientjes , Vlastimil Babka , Naresh Kamboju , Roman Gushchin Subject: [PATCH v5 4/6] mm: kmem: scoped objcg protection Date: Thu, 19 Oct 2023 15:53:44 -0700 Message-ID: <20231019225346.1822282-5-roman.gushchin@linux.dev> In-Reply-To: <20231019225346.1822282-1-roman.gushchin@linux.dev> References: <20231019225346.1822282-1-roman.gushchin@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Switch to a scope-based protection of the objcg pointer on slab/kmem allocation paths. Instead of using the get_() semantics in the pre-allocation hook and put the reference afterwards, let's rely on the fact that objcg is pinned by the scope. It's possible because: 1) if the objcg is received from the current task struct, the task is keeping a reference to the objcg. 2) if the objcg is received from an active memcg (remote charging), the memcg is pinned by the scope and has a reference to the corresponding objcg. Signed-off-by: Roman Gushchin (Cruise) Tested-by: Naresh Kamboju Acked-by: Shakeel Butt Reviewed-by: Vlastimil Babka --- include/linux/memcontrol.h | 9 ++++++++ include/linux/sched/mm.h | 4 ++++ mm/memcontrol.c | 47 ++++++++++++++++++++++++++++++++++++-- mm/slab.h | 15 ++++++------ 4 files changed, 66 insertions(+), 9 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 277690af383d..a89df289144d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1769,6 +1769,15 @@ bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); =20 +/* + * The returned objcg pointer is safe to use without additional + * protection within a scope. The scope is defined either by + * the current task (similar to the "current" global variable) + * or by set_active_memcg() pair. + * Please, use obj_cgroup_get() to get a reference if the pointer + * needs to be used outside of the local scope. + */ +struct obj_cgroup *current_obj_cgroup(void); struct obj_cgroup *get_obj_cgroup_from_current(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); =20 diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 8d89c8c4fac1..9a19f1b42f64 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -403,6 +403,10 @@ DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); * __GFP_ACCOUNT allocations till the end of the scope will be charged to = the * given memcg. * + * Please, make sure that caller has a reference to the passed memcg struc= ture, + * so its lifetime is guaranteed to exceed the scope between two + * set_active_memcg() calls. + * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d964b91f00c8..e3d4b7fabb7d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3088,6 +3088,49 @@ __always_inline struct obj_cgroup *get_obj_cgroup_fr= om_current(void) return objcg; } =20 +__always_inline struct obj_cgroup *current_obj_cgroup(void) +{ + struct mem_cgroup *memcg; + struct obj_cgroup *objcg; + + if (in_task()) { + memcg =3D current->active_memcg; + if (unlikely(memcg)) + goto from_memcg; + + objcg =3D READ_ONCE(current->objcg); + if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG)) + objcg =3D current_objcg_update(); + /* + * Objcg reference is kept by the task, so it's safe + * to use the objcg by the current task. + */ + return objcg; + } + + memcg =3D this_cpu_read(int_active_memcg); + if (unlikely(memcg)) + goto from_memcg; + + return NULL; + +from_memcg: + for (; !mem_cgroup_is_root(memcg); memcg =3D parent_mem_cgroup(memcg)) { + /* + * Memcg pointer is protected by scope (see set_active_memcg()) + * and is pinning the corresponding objcg, so objcg can't go + * away and can be used within the scope without any additional + * protection. + */ + objcg =3D rcu_dereference_check(memcg->objcg, 1); + if (likely(objcg)) + break; + objcg =3D NULL; + } + + return objcg; +} + struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { struct obj_cgroup *objcg; @@ -3182,15 +3225,15 @@ int __memcg_kmem_charge_page(struct page *page, gfp= _t gfp, int order) struct obj_cgroup *objcg; int ret =3D 0; =20 - objcg =3D get_obj_cgroup_from_current(); + objcg =3D current_obj_cgroup(); if (objcg) { ret =3D obj_cgroup_charge_pages(objcg, gfp, 1 << order); if (!ret) { + obj_cgroup_get(objcg); page->memcg_data =3D (unsigned long)objcg | MEMCG_DATA_KMEM; return 0; } - obj_cgroup_put(objcg); } return ret; } diff --git a/mm/slab.h b/mm/slab.h index 799a315695c6..3d07fb428393 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -484,7 +484,12 @@ static inline bool memcg_slab_pre_alloc_hook(struct km= em_cache *s, if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) return true; =20 - objcg =3D get_obj_cgroup_from_current(); + /* + * The obtained objcg pointer is safe to use within the current scope, + * defined by current task or set_active_memcg() pair. + * obj_cgroup_get() is used to get a permanent reference. + */ + objcg =3D current_obj_cgroup(); if (!objcg) return true; =20 @@ -497,17 +502,14 @@ static inline bool memcg_slab_pre_alloc_hook(struct k= mem_cache *s, css_put(&memcg->css); =20 if (ret) - goto out; + return false; } =20 if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) - goto out; + return false; =20 *objcgp =3D objcg; return true; -out: - obj_cgroup_put(objcg); - return false; } =20 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, @@ -542,7 +544,6 @@ static inline void memcg_slab_post_alloc_hook(struct km= em_cache *s, obj_cgroup_uncharge(objcg, obj_full_size(s)); } } - obj_cgroup_put(objcg); } =20 static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab = *slab, --=20 2.42.0 From nobody Tue Dec 16 20:00:50 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id D1CBEC004C0 for ; Thu, 19 Oct 2023 22:54:39 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1346730AbjJSWyj (ORCPT ); Thu, 19 Oct 2023 18:54:39 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33714 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1346741AbjJSWy3 (ORCPT ); Thu, 19 Oct 2023 18:54:29 -0400 Received: from out-197.mta0.migadu.com (out-197.mta0.migadu.com [IPv6:2001:41d0:1004:224b::c5]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 227D2126 for ; Thu, 19 Oct 2023 15:54:25 -0700 (PDT) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1697756064; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=BnzSFyH1H48PSMDn7iqVZlFC9YDx4r15eixWsUbXpKs=; b=JnrPJVXCVoN8MXZPI6RkQGBCNH63eYwmUrhXUzgISfnhW0IuWEsi18lYzeeVWxfLpgH4GW AMLpenUkuseR/R6nGzgHYvx/b8MQBc71GCbNQ7H4HmhTQkLQ3nhzStsySvA+ZV2v2EjjBo skR/Nl40nvBP7E2e2M3bFod11TDnBcY= From: Roman Gushchin To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Johannes Weiner , Michal Hocko , Shakeel Butt , Muchun Song , Dennis Zhou , David Rientjes , Vlastimil Babka , Naresh Kamboju , Roman Gushchin Subject: [PATCH v5 5/6] percpu: scoped objcg protection Date: Thu, 19 Oct 2023 15:53:45 -0700 Message-ID: <20231019225346.1822282-6-roman.gushchin@linux.dev> In-Reply-To: <20231019225346.1822282-1-roman.gushchin@linux.dev> References: <20231019225346.1822282-1-roman.gushchin@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Similar to slab and kmem, switch to a scope-based protection of the objcg pointer to avoid. Signed-off-by: Roman Gushchin (Cruise) Tested-by: Naresh Kamboju Acked-by: Shakeel Butt Reviewed-by: Vlastimil Babka --- mm/percpu.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/mm/percpu.c b/mm/percpu.c index a7665de8485f..f53ba692d67a 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1628,14 +1628,12 @@ static bool pcpu_memcg_pre_alloc_hook(size_t size, = gfp_t gfp, if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; =20 - objcg =3D get_obj_cgroup_from_current(); + objcg =3D current_obj_cgroup(); if (!objcg) return true; =20 - if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) { - obj_cgroup_put(objcg); + if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; - } =20 *objcgp =3D objcg; return true; @@ -1649,6 +1647,7 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgr= oup *objcg, return; =20 if (likely(chunk && chunk->obj_cgroups)) { + obj_cgroup_get(objcg); chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] =3D objcg; =20 rcu_read_lock(); @@ -1657,7 +1656,6 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgr= oup *objcg, rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); - obj_cgroup_put(objcg); } } =20 --=20 2.42.0 From nobody Tue Dec 16 20:00:50 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7AA68C001DF for ; Thu, 19 Oct 2023 22:54:44 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1346746AbjJSWyn (ORCPT ); Thu, 19 Oct 2023 18:54:43 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33812 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235553AbjJSWyb (ORCPT ); Thu, 19 Oct 2023 18:54:31 -0400 Received: from out-194.mta0.migadu.com (out-194.mta0.migadu.com [91.218.175.194]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 826E2184 for ; Thu, 19 Oct 2023 15:54:28 -0700 (PDT) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1697756066; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=dS7frJRdSMuPJ7DdWWAjQ+cQ8KaRwRE0njPFfiYUqhI=; b=swiyjDzbwvO1ryyH0LOxBsG3sRDrHo8MwhzTCH/GhQa+yLHgJt9YruoXPCzep7ToRdRcIe f2eQNq6gGnHGE7yLa7z373yvV6fk04/R4k49Aiuuzgl3U3AyV/OKYwgN/BLnwOmIAr+Hpk tNxwryf0vISlCXMm0JNVfO9Q0ZShvgY= From: Roman Gushchin To: Andrew Morton Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Johannes Weiner , Michal Hocko , Shakeel Butt , Muchun Song , Dennis Zhou , David Rientjes , Vlastimil Babka , Naresh Kamboju , Roman Gushchin Subject: [PATCH v5 6/6] mm: kmem: reimplement get_obj_cgroup_from_current() Date: Thu, 19 Oct 2023 15:53:46 -0700 Message-ID: <20231019225346.1822282-7-roman.gushchin@linux.dev> In-Reply-To: <20231019225346.1822282-1-roman.gushchin@linux.dev> References: <20231019225346.1822282-1-roman.gushchin@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Reimplement get_obj_cgroup_from_current() using current_obj_cgroup(). get_obj_cgroup_from_current() and current_obj_cgroup() share 80% of the code, so the new implementation is almost trivial. get_obj_cgroup_from_current() is a convenient function used by the bpf subsystem, so there is no reason to get rid of it completely. Signed-off-by: Roman Gushchin (Cruise) --- include/linux/memcontrol.h | 11 ++++++++++- mm/memcontrol.c | 32 -------------------------------- 2 files changed, 10 insertions(+), 33 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a89df289144d..ef26551a633f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1778,9 +1778,18 @@ void __memcg_kmem_uncharge_page(struct page *page, i= nt order); * needs to be used outside of the local scope. */ struct obj_cgroup *current_obj_cgroup(void); -struct obj_cgroup *get_obj_cgroup_from_current(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); =20 +static inline struct obj_cgroup *get_obj_cgroup_from_current(void) +{ + struct obj_cgroup *objcg =3D current_obj_cgroup(); + + if (objcg) + obj_cgroup_get(objcg); + + return objcg; +} + int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); =20 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e3d4b7fabb7d..e13c10912c16 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3056,38 +3056,6 @@ static struct obj_cgroup *current_objcg_update(void) return objcg; } =20 -__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) -{ - struct mem_cgroup *memcg; - struct obj_cgroup *objcg; - - if (in_task()) { - memcg =3D current->active_memcg; - if (unlikely(memcg)) - goto from_memcg; - - objcg =3D READ_ONCE(current->objcg); - if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG)) - objcg =3D current_objcg_update(); - - if (objcg) { - obj_cgroup_get(objcg); - return objcg; - } - } else { - memcg =3D this_cpu_read(int_active_memcg); - if (unlikely(memcg)) - goto from_memcg; - } - return NULL; - -from_memcg: - rcu_read_lock(); - objcg =3D __get_obj_cgroup_from_memcg(memcg); - rcu_read_unlock(); - return objcg; -} - __always_inline struct obj_cgroup *current_obj_cgroup(void) { struct mem_cgroup *memcg; --=20 2.42.0