From patchwork Fri Feb 11 22:35:34 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sebastian Andrzej Siewior X-Patchwork-Id: 12744024 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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2AABEC433FE for ; Fri, 11 Feb 2022 22:35:51 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 3AA338D0001; Fri, 11 Feb 2022 17:35:49 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 2E5146B007B; Fri, 11 Feb 2022 17:35:49 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id E072B6B007D; Fri, 11 Feb 2022 17:35:48 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0143.hostedemail.com [216.40.44.143]) by kanga.kvack.org (Postfix) with ESMTP id C81386B007B for ; Fri, 11 Feb 2022 17:35:48 -0500 (EST) Received: from smtpin30.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with ESMTP id 8B02F998D5 for ; Fri, 11 Feb 2022 22:35:48 +0000 (UTC) X-FDA: 79131957576.30.3303AA6 Received: from galois.linutronix.de (Galois.linutronix.de [193.142.43.55]) by imf21.hostedemail.com (Postfix) with ESMTP id CD2A21C000E for ; Fri, 11 Feb 2022 22:35:47 +0000 (UTC) From: Sebastian Andrzej Siewior DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020; t=1644618945; 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=CEAzjeAy8cKiKlYL0fu8G573D2IU9l14d7NwNaWhxG0=; b=moHj9TSKQ3mEmbTWUxZMJCpO54B2EeIut6YwWex8ouzmjckojF0UQ5QJ38qWrGnSTD9GkY RwmkXHoJti0UzcI5PsU6Ebxak9itBwVH37rJqIFpfV7OoJq6uBnck5Mn3TVProxTqUAMrx vyeji30+hEt+ovgxrV6x7zr+V1ou7kW9rMYF+FQXutQf0X4oxkrzeqfypY1OiLPLzPpP8r L/DX+8RAA2Hygz4LUpiEVNBIQDm0Yw150EYuQQkCn4T2TZW/s3IOqaABwLBqO75jCCFpfi d2VGj4JP9geBpSVVMkb+tlxLTJ688n5utMsRlLD9FljLp4KJy0sYv0aM9tZjDA== DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020e; t=1644618945; 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=CEAzjeAy8cKiKlYL0fu8G573D2IU9l14d7NwNaWhxG0=; b=Rn1DqHXX2PBHGgXEi5KBkFZMYZBoTCs5Vnp1+Syg+zCBQmxTywdMTx0ynVKfDMrayiV63G BAZgC8fXn4qVAoCg== To: cgroups@vger.kernel.org, linux-mm@kvack.org Cc: Andrew Morton , Johannes Weiner , Michal Hocko , =?utf-8?q?Michal_Koutn=C3=BD?= , Peter Zijlstra , Thomas Gleixner , Vladimir Davydov , Waiman Long , Michal Hocko , Sebastian Andrzej Siewior Subject: [PATCH v2 1/4] mm/memcg: Revert ("mm/memcg: optimize user context object stock access") Date: Fri, 11 Feb 2022 23:35:34 +0100 Message-Id: <20220211223537.2175879-2-bigeasy@linutronix.de> In-Reply-To: <20220211223537.2175879-1-bigeasy@linutronix.de> References: <20220211223537.2175879-1-bigeasy@linutronix.de> MIME-Version: 1.0 X-Rspam-User: X-Rspamd-Server: rspam04 X-Rspamd-Queue-Id: CD2A21C000E X-Stat-Signature: 38h1weitcyydgyor6u65cwqtsfqj7m87 Authentication-Results: imf21.hostedemail.com; dkim=pass header.d=linutronix.de header.s=2020 header.b=moHj9TSK; dkim=pass header.d=linutronix.de header.s=2020e header.b=Rn1DqHXX; dmarc=pass (policy=none) header.from=linutronix.de; spf=pass (imf21.hostedemail.com: domain of bigeasy@linutronix.de designates 193.142.43.55 as permitted sender) smtp.mailfrom=bigeasy@linutronix.de X-HE-Tag: 1644618947-44412 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: Michal Hocko The optimisation is based on a micro benchmark where local_irq_save() is more expensive than a preempt_disable(). There is no evidence that it is visible in a real-world workload and there are CPUs where the opposite is true (local_irq_save() is cheaper than preempt_disable()). Based on micro benchmarks, the optimisation makes sense on PREEMPT_NONE where preempt_disable() is optimized away. There is no improvement with PREEMPT_DYNAMIC since the preemption counter is always available. The optimization makes also the PREEMPT_RT integration more complicated since most of the assumption are not true on PREEMPT_RT. Revert the optimisation since it complicates the PREEMPT_RT integration and the improvement is hardly visible. [ bigeasy: Patch body around Michal's diff ] Link: https://lore.kernel.org/all/YgOGkXXCrD%2F1k+p4@dhcp22.suse.cz Link: https://lkml.kernel.org/r/YdX+INO9gQje6d0S@linutronix.de Signed-off-by: Michal Hocko Signed-off-by: Sebastian Andrzej Siewior Acked-by: Johannes Weiner Acked-by: Roman Gushchin --- mm/memcontrol.c | 94 ++++++++++++++----------------------------------- 1 file changed, 27 insertions(+), 67 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09d342c7cbd0d..4b1572ae990d8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2085,23 +2085,17 @@ void unlock_page_memcg(struct page *page) folio_memcg_unlock(page_folio(page)); } -struct obj_stock { +struct memcg_stock_pcp { + struct mem_cgroup *cached; /* this never be root cgroup */ + unsigned int nr_pages; + #ifdef CONFIG_MEMCG_KMEM struct obj_cgroup *cached_objcg; struct pglist_data *cached_pgdat; unsigned int nr_bytes; int nr_slab_reclaimable_b; int nr_slab_unreclaimable_b; -#else - int dummy[0]; #endif -}; - -struct memcg_stock_pcp { - struct mem_cgroup *cached; /* this never be root cgroup */ - unsigned int nr_pages; - struct obj_stock task_obj; - struct obj_stock irq_obj; struct work_struct work; unsigned long flags; @@ -2111,12 +2105,12 @@ static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); static DEFINE_MUTEX(percpu_charge_mutex); #ifdef CONFIG_MEMCG_KMEM -static void drain_obj_stock(struct obj_stock *stock); +static void drain_obj_stock(struct memcg_stock_pcp *stock); static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, struct mem_cgroup *root_memcg); #else -static inline void drain_obj_stock(struct obj_stock *stock) +static inline void drain_obj_stock(struct memcg_stock_pcp *stock) { } static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, @@ -2193,9 +2187,7 @@ static void drain_local_stock(struct work_struct *dummy) local_irq_save(flags); stock = this_cpu_ptr(&memcg_stock); - drain_obj_stock(&stock->irq_obj); - if (in_task()) - drain_obj_stock(&stock->task_obj); + drain_obj_stock(stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); @@ -2770,41 +2762,6 @@ static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) */ #define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) -/* - * Most kmem_cache_alloc() calls are from user context. The irq disable/enable - * sequence used in this case to access content from object stock is slow. - * To optimize for user context access, there are now two object stocks for - * task context and interrupt context access respectively. - * - * The task context object stock can be accessed by disabling preemption only - * which is cheap in non-preempt kernel. The interrupt context object stock - * can only be accessed after disabling interrupt. User context code can - * access interrupt object stock, but not vice versa. - */ -static inline struct obj_stock *get_obj_stock(unsigned long *pflags) -{ - struct memcg_stock_pcp *stock; - - if (likely(in_task())) { - *pflags = 0UL; - preempt_disable(); - stock = this_cpu_ptr(&memcg_stock); - return &stock->task_obj; - } - - local_irq_save(*pflags); - stock = this_cpu_ptr(&memcg_stock); - return &stock->irq_obj; -} - -static inline void put_obj_stock(unsigned long flags) -{ - if (likely(in_task())) - preempt_enable(); - else - local_irq_restore(flags); -} - /* * mod_objcg_mlstate() may be called with irq enabled, so * mod_memcg_lruvec_state() should be used. @@ -3075,10 +3032,13 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, enum node_stat_item idx, int nr) { + struct memcg_stock_pcp *stock; unsigned long flags; - struct obj_stock *stock = get_obj_stock(&flags); int *bytes; + local_irq_save(flags); + stock = this_cpu_ptr(&memcg_stock); + /* * Save vmstat data in stock and skip vmstat array update unless * accumulating over a page of vmstat data or when pgdat or idx @@ -3129,26 +3089,29 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, if (nr) mod_objcg_mlstate(objcg, pgdat, idx, nr); - put_obj_stock(flags); + local_irq_restore(flags); } static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) { + struct memcg_stock_pcp *stock; unsigned long flags; - struct obj_stock *stock = get_obj_stock(&flags); bool ret = false; + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { stock->nr_bytes -= nr_bytes; ret = true; } - put_obj_stock(flags); + local_irq_restore(flags); return ret; } -static void drain_obj_stock(struct obj_stock *stock) +static void drain_obj_stock(struct memcg_stock_pcp *stock) { struct obj_cgroup *old = stock->cached_objcg; @@ -3204,13 +3167,8 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, { struct mem_cgroup *memcg; - if (in_task() && stock->task_obj.cached_objcg) { - memcg = obj_cgroup_memcg(stock->task_obj.cached_objcg); - if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) - return true; - } - if (stock->irq_obj.cached_objcg) { - memcg = obj_cgroup_memcg(stock->irq_obj.cached_objcg); + if (stock->cached_objcg) { + memcg = obj_cgroup_memcg(stock->cached_objcg); if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) return true; } @@ -3221,10 +3179,13 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, bool allow_uncharge) { + struct memcg_stock_pcp *stock; unsigned long flags; - struct obj_stock *stock = get_obj_stock(&flags); unsigned int nr_pages = 0; + local_irq_save(flags); + + stock = this_cpu_ptr(&memcg_stock); if (stock->cached_objcg != objcg) { /* reset if necessary */ drain_obj_stock(stock); obj_cgroup_get(objcg); @@ -3240,7 +3201,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, stock->nr_bytes &= (PAGE_SIZE - 1); } - put_obj_stock(flags); + local_irq_restore(flags); if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); @@ -6821,7 +6782,6 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; - bool use_objcg = folio_memcg_kmem(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); @@ -6830,7 +6790,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) * folio memcg or objcg at this point, we have fully * exclusive access to the folio. */ - if (use_objcg) { + if (folio_memcg_kmem(folio)) { objcg = __folio_objcg(folio); /* * This get matches the put at the end of the function and @@ -6858,7 +6818,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) nr_pages = folio_nr_pages(folio); - if (use_objcg) { + if (folio_memcg_kmem(folio)) { ug->nr_memory += nr_pages; ug->nr_kmem += nr_pages;