mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Gregory Price <gourry@gourry.net>
To: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org, kernel-team@meta.com,
	akpm@linux-foundation.org, david@kernel.org, ljs@kernel.org,
	liam@infradead.org, vbabka@kernel.org, rppt@kernel.org,
	surenb@google.com, mhocko@suse.com, 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,
	vschneid@redhat.com, kprateek.nayak@amd.com, ziy@nvidia.com,
	baolin.wang@linux.alibaba.com, nico.pache@linux.dev,
	ryan.roberts@arm.com, dev.jain@arm.com, baohua@kernel.org,
	lance.yang@linux.dev, usama.arif@linux.dev, kas@kernel.org,
	gourry@gourry.net, joshua.hahnjy@gmail.com, rakie.kim@sk.com,
	ying.huang@linux.alibaba.com, matthew.brost@intel.com,
	byungchul@sk.com, apopple@nvidia.com, jannh@google.com,
	pfalcato@suse.de, hannes@cmpxchg.org, shy828301@gmail.com,
	osalvador@suse.de, raghavendra.kt@amd.com,
	stable@vger.kernel.org
Subject: [PATCH v4 4/7] sched/numa: separate VMA placement from scan continuation
Date: Wed, 30 Sep 2026 07:22:03 -0400	[thread overview]
Message-ID: <20260930112206.205083-5-gourry@gourry.net> (raw)
In-Reply-To: <20260930112206.205083-1-gourry@gourry.net>

From: "Gregory Price (Meta)" <gourry@gourry.net>

vma_is_accessed() returns true both when a VMA needs placement
(east-west) sampling and when a VMA is already mid-scan across
multiple scan windows.

Callers cannot distinguish placement eligibility from scan progress.

Rename the helper to vma_needs_placement_scan() and handle continuation
state in task_numa_work(). Record whether an in-progress VMA scan is
promotion-only so a scan resumed in a later scan window finishes with
the policy it started with. The zeroed initial state places no
restriction, so a resumed scan that finds freshly allocated NUMAB state
falls back to the default policy.

This separation allows PID-inactive VMAs to be scanned for promotion
without treating scan continuation as evidence of placement eligibility.
It is a prerequisite for the following fix and must accompany it when
backported.

Fixes: fc137c0ddab2 ("sched/numa: enhance vma scanning logic")
Cc: stable@vger.kernel.org
Assisted-by: LLM
Signed-off-by: Gregory Price (Meta) <gourry@gourry.net>
---
 include/linux/mm_types.h |  6 ++++++
 kernel/sched/fair.c      | 40 ++++++++++++++++++++++++----------------
 2 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1bd3ca7bfff2..d0ac21d02c47 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -803,6 +803,12 @@ struct vma_numab_state {
 	 * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
 	 */
 	int prev_scan_seq;
+
+	/*
+	 * The in-progress scan of this VMA is promotion-only.
+	 * Resumed scans finish with the policy they started with.
+	 */
+	bool promo_only;
 };
 
 #ifdef __HAVE_PFNMAP_TRACKING
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ab9afd3ad49b..3b30786ded3b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4082,7 +4082,8 @@ static void reset_ptenuma_scan(struct task_struct *p)
 	p->mm->numa_scan_offset = 0;
 }
 
-static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
+static bool vma_needs_placement_scan(struct mm_struct *mm,
+		struct vm_area_struct *vma)
 {
 	unsigned long pids;
 	/*
@@ -4098,15 +4099,6 @@ static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids))
 		return true;
 
-	/*
-	 * Complete a scan that has already started regardless of PID access, or
-	 * some VMAs may never be scanned in multi-threaded applications:
-	 */
-	if (mm->numa_scan_offset > vma->vm_start) {
-		trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_IGNORE_PID);
-		return true;
-	}
-
 	/*
 	 * This vma has not been accessed for a while, and if the number
 	 * the threads in the same process is low, which means no other
@@ -4130,6 +4122,7 @@ static void task_numa_work(struct callback_head *work)
 	const unsigned int numab_mode = READ_ONCE(sysctl_numa_balancing_mode);
 	const bool tiering = numab_mode & NUMA_BALANCING_MEMORY_TIERING;
 	const bool balancing = numab_mode & NUMA_BALANCING_NORMAL;
+	bool pid_scan_allowed, placement_due, scan_started;
 	unsigned long migrate, next_scan, now = jiffies;
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
@@ -4316,15 +4309,29 @@ static void task_numa_work(struct callback_head *work)
 		}
 
 		/*
-		 * Do not scan the VMA if task has not accessed it, unless no other
-		 * VMA candidate exists.
+		 * Do not scan the VMA if a task has not accessed it, unless no other
+		 * VMA candidate exists. If a scan is already in-progress, finish it,
+		 * but track continuation separately from starting a new one.
 		 */
-		if (!vma_pids_forced && !vma_is_accessed(mm, vma)) {
-			vma_pids_skipped = true;
-			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_PID_INACTIVE);
-			continue;
+		placement_due = vma_needs_placement_scan(mm, vma);
+		scan_started = mm->numa_scan_offset > vma->vm_start;
+		pid_scan_allowed = vma_pids_forced || placement_due;
+
+		if (!pid_scan_allowed) {
+			if (scan_started) {
+				trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_IGNORE_PID);
+			} else {
+				vma_pids_skipped = true;
+				trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_PID_INACTIVE);
+				continue;
+			}
 		}
 
+		/* Keep scan policy stable while processing a VMA in chunks. */
+		if (scan_started && vma->numab_state->promo_only)
+			placement_scan = false;
+
+		vma->numab_state->promo_only = !placement_scan;
 		cp_flags = MM_CP_PROT_NUMA;
 		if (!placement_scan)
 			cp_flags |= MM_CP_PROT_NUMA_PROMO_ONLY;
@@ -4357,6 +4364,7 @@ static void task_numa_work(struct callback_head *work)
 
 		/* VMA scan is complete, do not scan until next sequence. */
 		vma->numab_state->prev_scan_seq = mm->numa_scan_seq;
+		vma->numab_state->promo_only = false;
 
 		/*
 		 * Only force scan within one VMA at a time, to limit the
-- 
2.55.0


  parent reply	other threads:[~2026-09-30 11:22 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-30 11:21 [PATCH v4 0/7] sched/numa: stop VMA scan filters from gating promotion Gregory Price
2026-09-30 11:22 ` [PATCH v4 1/7] mm: support promotion-only NUMA hinting scans Gregory Price
2026-09-30 11:22 ` [PATCH v4 2/7] mm: allow shared folios to be promoted to a fast tier Gregory Price
2026-10-01 10:34   ` David Hildenbrand (Arm)
2026-09-30 11:22 ` [PATCH v4 3/7] sched/numa: scan read-only file mappings in tiering mode Gregory Price
2026-10-01 10:34   ` David Hildenbrand (Arm)
2026-09-30 11:22 ` Gregory Price [this message]
2026-10-01 10:44   ` [PATCH v4 4/7] sched/numa: separate VMA placement from scan continuation David Hildenbrand (Arm)
2026-10-01 13:29     ` Gregory Price
2026-09-30 11:22 ` [PATCH v4 5/7] sched/numa: scan PID-inactive VMAs for promotion Gregory Price
2026-10-01 10:45   ` David Hildenbrand (Arm)
2026-09-30 11:22 ` [PATCH v4 6/7] mm: use BIT() for change_protection() flags Gregory Price
2026-09-30 11:22 ` [PATCH v4 7/7] mm: use VMA flag helpers in NUMA balancing Gregory Price
2026-10-01 10:45   ` David Hildenbrand (Arm)

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260930112206.205083-5-gourry@gourry.net \
    --to=gourry@gourry.net \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bsegall@google.com \
    --cc=byungchul@sk.com \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=hannes@cmpxchg.org \
    --cc=jannh@google.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=juri.lelli@redhat.com \
    --cc=kas@kernel.org \
    --cc=kernel-team@meta.com \
    --cc=kprateek.nayak@amd.com \
    --cc=lance.yang@linux.dev \
    --cc=liam@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=matthew.brost@intel.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=mingo@redhat.com \
    --cc=nico.pache@linux.dev \
    --cc=osalvador@suse.de \
    --cc=peterz@infradead.org \
    --cc=pfalcato@suse.de \
    --cc=raghavendra.kt@amd.com \
    --cc=rakie.kim@sk.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=shy828301@gmail.com \
    --cc=stable@vger.kernel.org \
    --cc=surenb@google.com \
    --cc=usama.arif@linux.dev \
    --cc=vbabka@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=ying.huang@linux.alibaba.com \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®