Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1030694Ab3HISr5 (ORCPT ); Fri, 9 Aug 2013 14:47:57 -0400 Received: from usmamail.tilera.com ([12.216.194.151]:59057 "EHLO USMAMAIL.TILERA.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030353Ab3HISrz (ORCPT ); Fri, 9 Aug 2013 14:47:55 -0400 Message-ID: <201308091847.r79IlstZ015094@farm-0021.internal.tilera.com> From: Chris Metcalf In-Reply-To: <20130809174009.GV20515@mtj.dyndns.org> Date: Fri, 9 Aug 2013 13:52:22 -0400 Subject: [PATCH v6 2/2] mm: make lru_add_drain_all() selective To: , , Tejun Heo , Thomas Gleixner , Frederic Weisbecker , Cody P Schafer MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2941 Lines: 97 This change makes lru_add_drain_all() only selectively interrupt the cpus that have per-cpu free pages that can be drained. This is important in nohz mode where calling mlockall(), for example, otherwise will interrupt every core unnecessarily. Signed-off-by: Chris Metcalf --- v6: add Tejun's Acked-by, and add missing get/put_cpu_online to lru_add_drain_all(). v5: provide validity checking on the cpumask for schedule_on_cpu_mask. By providing an all-or-nothing EINVAL check, we impose the requirement that the calling code actually know clearly what it's trying to do. (Note: no change to the mm/swap.c commit) v4: don't lose possible -ENOMEM in schedule_on_each_cpu() (Note: no change to the mm/swap.c commit) v3: split commit into two, one for workqueue and one for mm, though both should probably be taken through -mm. mm/swap.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) diff --git a/mm/swap.c b/mm/swap.c index 4a1d0d2..f42561a 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -405,6 +405,11 @@ static void activate_page_drain(int cpu) pagevec_lru_move_fn(pvec, __activate_page, NULL); } +static bool need_activate_page_drain(int cpu) +{ + return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0; +} + void activate_page(struct page *page) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { @@ -422,6 +427,11 @@ static inline void activate_page_drain(int cpu) { } +static bool need_activate_page_drain(int cpu) +{ + return false; +} + void activate_page(struct page *page) { struct zone *zone = page_zone(page); @@ -683,7 +693,34 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) */ int lru_add_drain_all(void) { - return schedule_on_each_cpu(lru_add_drain_per_cpu); + cpumask_var_t mask; + int cpu, rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_clear(mask); + get_online_cpus(); + + /* + * Figure out which cpus need flushing. It's OK if we race + * with changes to the per-cpu lru pvecs, since it's no worse + * than if we flushed all cpus, since a cpu could still end + * up putting pages back on its pvec before we returned. + * And this avoids interrupting other cpus unnecessarily. + */ + for_each_online_cpu(cpu) { + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + need_activate_page_drain(cpu)) + cpumask_set_cpu(cpu, mask); + } + + rc = schedule_on_cpu_mask(lru_add_drain_per_cpu, mask); + + put_online_cpus(); + free_cpumask_var(mask); + return rc; } /* -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/