Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Feng Tang <feng.tang@intel.com>
To:     Andrew Morton <akpm@linux-foundation.org>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@suse.com>, Tejun Heo <tj@kernel.org>,
        Zefan Li <lizefan.x@bytedance.com>,
        Waiman Long <longman@redhat.com>, ying.huang@intel.com,
        aneesh.kumar@linux.ibm.com, linux-mm@kvack.org,
        cgroups@vger.kernel.org
Cc:     linux-kernel@vger.kernel.org, dave.hansen@intel.com,
        tim.c.chen@intel.com, fengwei.yin@intel.com,
        Feng Tang <feng.tang@intel.com>
Subject: [PATCH] mm/vmscan: respect cpuset policy during page demotion
Date:   Wed, 26 Oct 2022 15:43:43 +0800
Message-Id: <20221026074343.6517-1-feng.tang@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In page reclaim path, memory could be demoted from faster memory tier
to slower memory tier. Currently, there is no check about cpuset's
memory policy, that even if the target demotion node is not allowd
by cpuset, the demotion will still happen, which breaks the cpuset
semantics.

So add cpuset policy check in the demotion path and skip demotion
if the demotion targets are not allowed by cpuset.

Signed-off-by: Feng Tang <feng.tang@intel.com>
---
Hi reviewers,

For easy bisectable, I combined the cpuset change and mm change
in one patch, if you prefer to separate them, I can turn it into
2 patches.

Thanks,
Feng

 include/linux/cpuset.h |  6 ++++++
 kernel/cgroup/cpuset.c | 29 +++++++++++++++++++++++++++++
 mm/vmscan.c            | 35 ++++++++++++++++++++++++++++++++---
 3 files changed, 67 insertions(+), 3 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index d58e0476ee8e..6fcce2bd2631 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -178,6 +178,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
+extern void cpuset_get_allowed_mem_nodes(struct cgroup *cgroup,
+						nodemask_t *nmask);
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -299,6 +301,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
+static inline void cpuset_get_allowed_mem_nodes(struct cgroup *cgroup,
+						nodemask_t *nmask)
+{
+}
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3ea2e836e93e..cbb118c0502f 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3750,6 +3750,35 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 	return mask;
 }
 
+/*
+ * Retrieve the allowed memory nodemask for a cgroup.
+ *
+ * Set *nmask to cpuset's effective allowed nodemask for cgroup v2,
+ * and NODE_MASK_ALL (means no constraint) for cgroup v1 where there
+ * is no guaranteed association from a cgroup to a cpuset.
+ */
+void cpuset_get_allowed_mem_nodes(struct cgroup *cgroup, nodemask_t *nmask)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
+
+	if (!is_in_v2_mode()) {
+		*nmask = NODE_MASK_ALL;
+		return;
+	}
+
+	rcu_read_lock();
+	css = cgroup_e_css(cgroup, &cpuset_cgrp_subsys);
+	if (css) {
+		css_get(css);
+		cs = css_cs(css);
+		*nmask = cs->effective_mems;
+		css_put(css);
+	}
+
+	rcu_read_unlock();
+}
+
 /**
  * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed
  * @nodemask: the nodemask to be checked
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 18f6497994ec..c205d98283bc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1537,9 +1537,21 @@ static struct page *alloc_demote_page(struct page *page, unsigned long private)
 {
 	struct page *target_page;
 	nodemask_t *allowed_mask;
-	struct migration_target_control *mtc;
+	struct migration_target_control *mtc = (void *)private;
 
-	mtc = (struct migration_target_control *)private;
+#if IS_ENABLED(CONFIG_MEMCG) && IS_ENABLED(CONFIG_CPUSETS)
+	struct mem_cgroup *memcg;
+	nodemask_t cpuset_nmask;
+
+	memcg = page_memcg(page);
+	cpuset_get_allowed_mem_nodes(memcg->css.cgroup, &cpuset_nmask);
+
+	if (!node_isset(mtc->nid, cpuset_nmask)) {
+		if (mtc->nmask)
+			nodes_and(*mtc->nmask, *mtc->nmask, cpuset_nmask);
+		return alloc_migration_target(page, (unsigned long)mtc);
+	}
+#endif
 
 	allowed_mask = mtc->nmask;
 	/*
@@ -1649,6 +1661,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 		enum folio_references references = FOLIOREF_RECLAIM;
 		bool dirty, writeback;
 		unsigned int nr_pages;
+		bool skip_this_demotion = false;
 
 		cond_resched();
 
@@ -1658,6 +1671,22 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 		if (!folio_trylock(folio))
 			goto keep;
 
+#if IS_ENABLED(CONFIG_MEMCG) && IS_ENABLED(CONFIG_CPUSETS)
+		if (do_demote_pass) {
+			struct mem_cgroup *memcg;
+			nodemask_t nmask, nmask1;
+
+			node_get_allowed_targets(pgdat, &nmask);
+			memcg = folio_memcg(folio);
+			if (memcg)
+				cpuset_get_allowed_mem_nodes(memcg->css.cgroup,
+								&nmask1);
+
+			if (!nodes_intersects(nmask, nmask1))
+				skip_this_demotion = true;
+		}
+#endif
+
 		VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
 
 		nr_pages = folio_nr_pages(folio);
@@ -1799,7 +1828,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 		 * Before reclaiming the folio, try to relocate
 		 * its contents to another node.
 		 */
-		if (do_demote_pass &&
+		if (do_demote_pass && !skip_this_demotion &&
 		    (thp_migration_supported() || !folio_test_large(folio))) {
 			list_add(&folio->lru, &demote_folios);
 			folio_unlock(folio);
-- 
2.27.0