Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com;
From:   Bharata B Rao <bharata@amd.com>
To:     <linux-kernel@vger.kernel.org>
CC:     <mingo@redhat.com>, <peterz@infradead.org>,
        <juri.lelli@redhat.com>, <vincent.guittot@linaro.org>,
        <dietmar.eggemann@arm.com>, <rostedt@goodmis.org>,
        <bsegall@google.com>, <mgorman@suse.de>, <bristot@redhat.com>,
        <dishaa.talreja@amd.com>, Wei Huang <wei.huang2@amd.com>,
        Bharata B Rao <bharata@amd.com>
Subject: [RFC PATCH v0 2/3] sched/numa: Add cumulative history of per-process fault stats
Date:   Fri, 28 Jan 2022 10:58:50 +0530
Message-ID: <20220128052851.17162-3-bharata@amd.com>
In-Reply-To: <20220128052851.17162-1-bharata@amd.com>
References: <20220128052851.17162-1-bharata@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 28 Jan 2022 05:29:18.5269
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: b3dd799a-5009-4fcb-24fb-08d9e21f21ab
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: DM6NAM11FT050.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BL0PR12MB4865
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

From: Disha Talreja <dishaa.talreja@amd.com>

The cumulative history of local/remote (lr) and private/shared (ps)
will be used for calculating adaptive scan period.

Co-developed-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Disha Talreja <dishaa.talreja@amd.com>
Signed-off-by: Bharata B Rao <bharata@amd.com>
---
 include/linux/mm_types.h |  2 ++
 kernel/sched/fair.c      | 49 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4f978c09d3db..2c6f119b947f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -614,6 +614,8 @@ struct mm_struct {
 		/* Process-based Adaptive NUMA */
 		atomic_long_t faults_locality[2];
 		atomic_long_t faults_shared[2];
+		unsigned long faults_locality_history[2];
+		unsigned long faults_shared_history[2];
 
 		spinlock_t pan_numa_lock;
 		unsigned int numa_scan_period;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1d6404b2d42e..4911b3841d00 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2102,14 +2102,56 @@ static void numa_group_count_active_nodes(struct numa_group *numa_group)
 /**********************************************/
 /*  Process-based Adaptive NUMA (PAN) Design  */
 /**********************************************/
+/*
+ * Update the cumulative history of local/remote and private/shared
+ * statistics. If the numbers are too small worthy of updating,
+ * return FALSE, otherwise return TRUE.
+ */
+static bool pan_update_history(struct task_struct *p)
+{
+	unsigned long local, remote, shared, private;
+	long diff;
+	int i;
+
+	remote = atomic_long_read(&p->mm->faults_locality[0]);
+	local = atomic_long_read(&p->mm->faults_locality[1]);
+	shared = atomic_long_read(&p->mm->faults_shared[0]);
+	private = atomic_long_read(&p->mm->faults_shared[1]);
+
+	/* skip if the activities in this window are too small */
+	if (local + remote < 100)
+		return false;
+
+	/* decay over the time window by 1/4 */
+	diff = local - (long)(p->mm->faults_locality_history[1] / 4);
+	p->mm->faults_locality_history[1] += diff;
+	diff = remote - (long)(p->mm->faults_locality_history[0] / 4);
+	p->mm->faults_locality_history[0] += diff;
+
+	/* decay over the time window by 1/2 */
+	diff = shared - (long)(p->mm->faults_shared_history[0] / 2);
+	p->mm->faults_shared_history[0] += diff;
+	diff = private - (long)(p->mm->faults_shared_history[1] / 2);
+	p->mm->faults_shared_history[1] += diff;
+
+	/* clear the statistics for the next window */
+	for (i = 0; i < 2; i++) {
+		atomic_long_set(&(p->mm->faults_locality[i]), 0);
+		atomic_long_set(&(p->mm->faults_shared[i]), 0);
+	}
+
+	return true;
+}
+
 /*
  * Updates mm->numa_scan_period under mm->pan_numa_lock.
- *
  * Returns p->numa_scan_period now but updated to return
  * p->mm->numa_scan_period in a later patch.
  */
 static unsigned long pan_get_scan_period(struct task_struct *p)
 {
+	pan_update_history(p);
+
 	return p->numa_scan_period;
 }
 
@@ -2836,10 +2878,15 @@ static void task_numa_work(struct callback_head *work)
 static void pan_init_numa(struct task_struct *p)
 {
 	struct mm_struct *mm = p->mm;
+	int i;
 
 	spin_lock_init(&mm->pan_numa_lock);
 	mm->numa_scan_period = sysctl_numa_balancing_scan_delay;
 
+	for (i = 0; i < 2; i++) {
+		mm->faults_locality_history[i] = 0;
+		mm->faults_shared_history[i] = 0;
+	}
 }
 
 void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
-- 
2.25.1