linux-kernel - [PATCH REBASE V3 1/4] sched/numa: Apply the scan delay to every new vma

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <7a6fbba87c8b51e67efd3e74285bb4cb311a16ca.1677672277.git.raghavendra.kt@amd.com>
Date:   Wed, 1 Mar 2023 17:49:00 +0530
From:   Raghavendra K T <raghavendra.kt@....com>
To:     <linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>
CC:     Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        "Mel Gorman" <mgorman@...e.de>,
        Andrew Morton <akpm@...ux-foundation.org>,
        "David Hildenbrand" <david@...hat.com>, <rppt@...nel.org>,
        Bharata B Rao <bharata@....com>,
        Disha Talreja <dishaa.talreja@....com>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Raghavendra K T <raghavendra.kt@....com>
Subject: [PATCH REBASE V3 1/4] sched/numa: Apply the scan delay to every new vma

From: Mel Gorman <mgorman@...hsingularity.net>

Currently whenever a new task is created we wait for
sysctl_numa_balancing_scan_delay to avoid unnessary scanning
overhead. Extend the same logic to new or very short-lived VMAs.

(Raghavendra: Add initialization in vm_area_dup())

Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
Signed-off-by: Raghavendra K T <raghavendra.kt@....com>
---
 include/linux/mm.h       | 16 ++++++++++++++++
 include/linux/mm_types.h |  7 +++++++
 kernel/fork.c            |  2 ++
 kernel/sched/fair.c      | 19 +++++++++++++++++++
 4 files changed, 44 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3d4bb18dfcb7..2cce434a5e55 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -29,6 +29,7 @@
 #include <linux/pgtable.h>
 #include <linux/kasan.h>
 #include <linux/memremap.h>
+#include <linux/slab.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -626,6 +627,20 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline void vma_numab_state_init(struct vm_area_struct *vma)
+{
+	vma->numab_state = NULL;
+}
+static inline void vma_numab_state_free(struct vm_area_struct *vma)
+{
+	kfree(vma->numab_state);
+}
+#else
+static inline void vma_numab_state_init(struct vm_area_struct *vma) {}
+static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #ifdef CONFIG_PER_VMA_LOCK
 /*
  * Try to read-lock a vma. The function is allowed to occasionally yield false
@@ -727,6 +742,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 	vma->vm_ops = &dummy_vm_ops;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma_mark_detached(vma, false);
+	vma_numab_state_init(vma);
 }
 
 /* Use when VMA is not part of the VMA tree and needs no locking */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 89bbf7d8a312..1cea78f60011 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -475,6 +475,10 @@ struct vma_lock {
 	struct rw_semaphore lock;
 };
 
+struct vma_numab_state {
+	unsigned long next_scan;
+};
+
 /*
  * This struct describes a virtual memory area. There is one of these
  * per VM-area/task. A VM area is any part of the process virtual memory
@@ -565,6 +569,9 @@ struct vm_area_struct {
 #endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
diff --git a/kernel/fork.c b/kernel/fork.c
index 75792157f51a..305f963359dc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -516,6 +516,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 		return NULL;
 	}
 	INIT_LIST_HEAD(&new->anon_vma_chain);
+	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
 
 	return new;
@@ -523,6 +524,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 
 void __vm_area_free(struct vm_area_struct *vma)
 {
+	vma_numab_state_free(vma);
 	free_anon_vma_name(vma);
 	vma_lock_free(vma);
 	kmem_cache_free(vm_area_cachep, vma);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7a1b1f855b96..7c2bbc8d618b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3027,6 +3027,25 @@ static void task_numa_work(struct callback_head *work)
 		if (!vma_is_accessible(vma))
 			continue;
 
+		/* Initialise new per-VMA NUMAB state. */
+		if (!vma->numab_state) {
+			vma->numab_state = kzalloc(sizeof(struct vma_numab_state),
+				GFP_KERNEL);
+			if (!vma->numab_state)
+				continue;
+
+			vma->numab_state->next_scan = now +
+				msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+		}
+
+		/*
+		 * Scanning the VMA's of short lived tasks add more overhead. So
+		 * delay the scan for new VMAs.
+		 */
+		if (mm->numa_scan_seq && time_before(jiffies,
+						vma->numab_state->next_scan))
+			continue;
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
-- 
2.34.1