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; pr=C
From:   Bharata B Rao <bharata@amd.com>
To:     <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>
CC:     <mgorman@suse.de>, <peterz@infradead.org>, <mingo@redhat.com>,
        <bp@alien8.de>, <dave.hansen@linux.intel.com>, <x86@kernel.org>,
        <akpm@linux-foundation.org>, <luto@kernel.org>,
        <tglx@linutronix.de>, <yue.li@memverge.com>,
        <Ravikumar.Bangoria@amd.com>, Bharata B Rao <bharata@amd.com>
Subject: [RFC PATCH 5/5] x86/ibs: Delay the collection of HW-provided access info
Date:   Wed, 8 Feb 2023 13:05:33 +0530
Message-ID: <20230208073533.715-6-bharata@amd.com>
In-Reply-To: <20230208073533.715-1-bharata@amd.com>
References: <20230208073533.715-1-bharata@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 08 Feb 2023 07:36:51.3416
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: f743052a-3f22-48a8-74c3-08db09a73e62
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: BN8NAM11FT059.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: IA0PR12MB8328
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Allow an initial delay before enabling the collection
of IBS provided access info.

Signed-off-by: Bharata B Rao <bharata@amd.com>
---
 arch/x86/mm/ibs.c        | 18 ++++++++++++++++++
 include/linux/mm.h       |  2 ++
 include/linux/mm_types.h |  3 +++
 kernel/sched/debug.c     |  2 ++
 kernel/sched/fair.c      |  3 +++
 5 files changed, 28 insertions(+)

diff --git a/arch/x86/mm/ibs.c b/arch/x86/mm/ibs.c
index a479029e9262..dfe5246954c0 100644
--- a/arch/x86/mm/ibs.c
+++ b/arch/x86/mm/ibs.c
@@ -16,6 +16,21 @@ struct ibs_access_work {
 	u64 laddr, paddr;
 };
 
+static bool delay_hw_access_profiling(struct mm_struct *mm)
+{
+	unsigned long delay, now = jiffies;
+
+	if (!mm->numa_hw_access_delay)
+		mm->numa_hw_access_delay = now +
+			msecs_to_jiffies(sysctl_numa_balancing_access_faults_delay);
+
+	delay = mm->numa_hw_access_delay;
+	if (time_before(now, delay))
+		return true;
+
+	return false;
+}
+
 void hw_access_sched_in(struct task_struct *prev, struct task_struct *curr)
 {
 	u64 config = 0;
@@ -28,6 +43,9 @@ void hw_access_sched_in(struct task_struct *prev, struct task_struct *curr)
 	if (!curr->mm)
 		goto out;
 
+	if (delay_hw_access_profiling(curr->mm))
+		goto out;
+
 	if (curr->numa_sample_period)
 		period = curr->numa_sample_period;
 	else
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8f857163ac89..118705a296ef 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1397,6 +1397,8 @@ static inline int folio_nid(const struct folio *folio)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
+extern unsigned int sysctl_numa_balancing_access_faults_delay;
+
 /* page access time bits needs to hold at least 4 seconds */
 #define PAGE_ACCESS_TIME_MIN_BITS	12
 #if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 9757067c3053..8a2fb8bf2d62 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -750,6 +750,9 @@ struct mm_struct {
 
 		/* numa_scan_seq prevents two threads remapping PTEs. */
 		int numa_scan_seq;
+
+		/* HW-provided access info is collected after this initial delay */
+		unsigned long numa_hw_access_delay;
 #endif
 		/*
 		 * An operation with batched TLB flushing is going on. Anything
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 1cf19778a232..5c76a7594358 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -342,6 +342,8 @@ static __init int sched_init_debug(void)
 			   &sysctl_numa_balancing_sample_period_max);
 	debugfs_create_u32("access_faults_threshold", 0644, numa,
 			   &sysctl_numa_balancing_access_faults_threshold);
+	debugfs_create_u32("access_faults_delay", 0644, numa,
+			   &sysctl_numa_balancing_access_faults_delay);
 #endif
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1b0665b034d0..2e2b1e706a24 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1097,6 +1097,7 @@ unsigned int sysctl_numa_balancing_sample_period_def = 10000;
 unsigned int sysctl_numa_balancing_sample_period_min = 5000;
 unsigned int sysctl_numa_balancing_sample_period_max = 20000;
 unsigned int sysctl_numa_balancing_access_faults_threshold = 250;
+unsigned int sysctl_numa_balancing_access_faults_delay = 1000;
 
 /*
  * Approximate time to scan a full NUMA task in ms. The task scan period is
@@ -3189,6 +3190,8 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 		if (mm_users == 1) {
 			mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 			mm->numa_scan_seq = 0;
+			mm->numa_hw_access_delay = jiffies +
+				msecs_to_jiffies(sysctl_numa_balancing_access_faults_delay);
 		}
 	}
 	p->node_stamp			= 0;
-- 
2.25.1