Linux debuggers
 help / color / mirror / Atom feed
From: Gregory Price <gourry@gourry.net>
To: linux-mm@kvack.org
Cc: Zhigang.Luo@amd.com, arun.george@samsung.com, balbirs@nvidia.com,
	brendan.jackman@linux.dev, yuzenghui@huawei.com,
	apopple@nvidia.com, alucerop@amd.com, matthew.brost@intel.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, corbet@lwn.net,
	skhan@linuxfoundation.org, gregkh@linuxfoundation.org,
	rafael@kernel.org, dakr@kernel.org, djbw@kernel.org,
	vishal.l.verma@intel.com, dave.jiang@intel.com,
	alison.schofield@intel.com, osandov@osandov.com,
	jannh@google.com, pfalcato@suse.de, jackmanb@google.com,
	hannes@cmpxchg.org, ziy@nvidia.com, pbonzini@redhat.com,
	osalvador@suse.de, joshua.hahnjy@gmail.com, rakie.kim@sk.com,
	byungchul@sk.com, gourry@gourry.net,
	ying.huang@linux.alibaba.com, kasong@tencent.com,
	qi.zheng@linux.dev, shakeel.butt@linux.dev, baohua@kernel.org,
	axelrasmussen@google.com, yuanchu@google.com, weixugc@google.com,
	yury.norov@gmail.com, linux@rasmusvillemoes.dk,
	longman@redhat.com, ridong.chen@linux.dev, tj@kernel.org,
	mkoutny@suse.com, sj@kernel.org, jgg@ziepe.ca,
	jhubbard@nvidia.com, peterx@redhat.com,
	baolin.wang@linux.alibaba.com, npache@redhat.com,
	ryan.roberts@arm.com, dev.jain@arm.com, lance.yang@linux.dev,
	usama.arif@linux.dev, xu.xin16@zte.com.cn,
	chengming.zhou@linux.dev, roman.gushchin@linux.dev,
	muchun.song@linux.dev, linux-kernel@vger.kernel.org,
	linux-doc@vger.kernel.org, driver-core@lists.linux.dev,
	nvdimm@lists.linux.dev, linux-cxl@vger.kernel.org,
	linux-debuggers@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	kvm@vger.kernel.org, cgroups@vger.kernel.org,
	damon@lists.linux.dev, linux-kselftest@vger.kernel.org,
	kernel-team@meta.com
Subject: [PATCH v5 01/36] mm: refactor find_next_best_node to find_next_best_node_in
Date: Mon, 20 Jul 2026 15:33:55 -0400	[thread overview]
Message-ID: <20260720193431.3841992-2-gourry@gourry.net> (raw)
In-Reply-To: <20260720193431.3841992-1-gourry@gourry.net>

find_next_best_node() picks the next-closest node for a fallback list
from the full N_MEMORY set. Refactor it into find_next_best_node_in(),
which takes an explicit candidates nodemask.

This enables building fallback lists with non-N_MEMORY candidates.

No functional change: every caller still selects from N_MEMORY.

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 mm/internal.h     |  6 ++++--
 mm/memory-tiers.c |  7 ++++---
 mm/page_alloc.c   | 13 ++++++++-----
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index f26423de4ca28..96d78a7778e88 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1103,7 +1103,8 @@ extern int node_reclaim_mode;
 
 extern unsigned long node_reclaim(struct pglist_data *pgdat,
 				  gfp_t gfp_mask, unsigned int order);
-extern int find_next_best_node(int node, nodemask_t *used_node_mask);
+extern int find_next_best_node_in(int node, nodemask_t *used_node_mask,
+				  const nodemask_t *candidates);
 #else
 #define node_reclaim_mode 0
 
@@ -1112,7 +1113,8 @@ static inline unsigned long node_reclaim(struct pglist_data *pgdat,
 {
 	return 0;
 }
-static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
+static inline int find_next_best_node_in(int node, nodemask_t *used_node_mask,
+					 const nodemask_t *candidates)
 {
 	return NUMA_NO_NODE;
 }
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 54851d8a195b0..25e121851b586 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -370,7 +370,7 @@ int next_demotion_node(int node, const nodemask_t *allowed_mask)
 	 * closest demotion target.
 	 */
 	nodes_complement(mask, *allowed_mask);
-	return find_next_best_node(node, &mask);
+	return find_next_best_node_in(node, &mask, &node_states[N_MEMORY]);
 }
 
 static void disable_all_demotion_targets(void)
@@ -450,7 +450,7 @@ static void establish_demotion_targets(void)
 		memtier = list_next_entry(memtier, list);
 		tier_nodes = get_memtier_nodemask(memtier);
 		/*
-		 * find_next_best_node, use 'used' nodemask as a skip list.
+		 * find_next_best_node_in, use 'used' nodemask as a skip list.
 		 * Add all memory nodes except the selected memory tier
 		 * nodelist to skip list so that we find the best node from the
 		 * memtier nodelist.
@@ -463,7 +463,8 @@ static void establish_demotion_targets(void)
 		 * in the preferred mask when allocating pages during demotion.
 		 */
 		do {
-			target = find_next_best_node(node, &tier_nodes);
+			target = find_next_best_node_in(node, &tier_nodes,
+							&node_states[N_MEMORY]);
 			if (target == NUMA_NO_NODE)
 				break;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f93a6bb9a872d..acf096f525f49 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5743,9 +5743,10 @@ static int numa_zonelist_order_handler(const struct ctl_table *table, int write,
 static int node_load[MAX_NUMNODES];
 
 /**
- * find_next_best_node - find the next node that should appear in a given node's fallback list
+ * find_next_best_node_in - find the next node that should appear in a given node's fallback list
  * @node: node whose fallback list we're appending
  * @used_node_mask: nodemask_t of already used nodes
+ * @candidates: nodemask_t of nodes eligible for selection
  *
  * We use a number of factors to determine which is the next node that should
  * appear on a given node's fallback list.  The node should not have appeared
@@ -5757,7 +5758,8 @@ static int node_load[MAX_NUMNODES];
  *
  * Return: node id of the found node or %NUMA_NO_NODE if no node is found.
  */
-int find_next_best_node(int node, nodemask_t *used_node_mask)
+int find_next_best_node_in(int node, nodemask_t *used_node_mask,
+			   const nodemask_t *candidates)
 {
 	int n, val;
 	int min_val = INT_MAX;
@@ -5767,12 +5769,12 @@ int find_next_best_node(int node, nodemask_t *used_node_mask)
 	 * Use the local node if we haven't already, but for memoryless local
 	 * node, we should skip it and fall back to other nodes.
 	 */
-	if (!node_isset(node, *used_node_mask) && node_state(node, N_MEMORY)) {
+	if (!node_isset(node, *used_node_mask) && node_isset(node, *candidates)) {
 		node_set(node, *used_node_mask);
 		return node;
 	}
 
-	for_each_node_state(n, N_MEMORY) {
+	for_each_node_mask(n, *candidates) {
 
 		/* Don't want a node to appear more than once */
 		if (node_isset(n, *used_node_mask))
@@ -5857,7 +5859,8 @@ static void build_zonelists(pg_data_t *pgdat)
 	prev_node = local_node;
 
 	memset(node_order, 0, sizeof(node_order));
-	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+	while ((node = find_next_best_node_in(local_node, &used_mask,
+					      &node_states[N_MEMORY])) >= 0) {
 		/*
 		 * We don't want to pressure a particular node.
 		 * So adding penalty to the first node in same
-- 
2.53.0-Meta


  reply	other threads:[~2026-07-20 19:34 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-20 19:33 [PATCH v5 00/36] Private Memory NUMA Nodes Gregory Price
2026-07-20 19:33 ` Gregory Price [this message]
2026-07-21  5:46   ` [PATCH v5 01/36] mm: refactor find_next_best_node to find_next_best_node_in Balbir Singh
2026-07-20 19:33 ` [PATCH v5 02/36] mm/page_alloc: refactor build_node_zonelist() out of build_zonelists() Gregory Price
2026-07-20 19:33 ` [PATCH v5 03/36] mm/page_alloc: let the bulk and folio allocators carry alloc_flags Gregory Price
2026-07-20 19:33 ` [PATCH v5 04/36] numa: introduce N_MEMORY_PRIVATE Gregory Price
2026-07-20 19:33 ` [PATCH v5 05/36] mm: add ZONELIST_PRIVATE(_NOFALLBACK) for N_MEMORY_PRIVATE nodes Gregory Price
2026-07-20 19:34 ` [PATCH v5 06/36] cpuset: exclude private nodes from cpuset.mems (default-open) Gregory Price
2026-07-20 19:34 ` [PATCH v5 07/36] mm/memory_hotplug: disallow migration-driven private node hotunplug Gregory Price
2026-07-20 19:34 ` [PATCH v5 08/36] mm/mempolicy: skip private node folios when queueing for migration Gregory Price
2026-07-20 19:34 ` [PATCH v5 09/36] mm/migrate: disallow userland driven migration for private nodes Gregory Price
2026-07-20 19:34 ` [PATCH v5 10/36] mm/madvise: disallow madvise operations on private node folios Gregory Price
2026-07-20 19:34 ` [PATCH v5 11/36] mm/compaction: disallow compaction on private nodes Gregory Price
2026-07-20 19:34 ` [PATCH v5 12/36] mm/page_alloc: clear private node watermarks and system reserves Gregory Price
2026-07-20 19:34 ` [PATCH v5 13/36] mm/mempolicy: disallow NUMA Balancing prot_none on private nodes Gregory Price
2026-07-20 19:34 ` [PATCH v5 14/36] mm/damon: skip private node memory in DAMON migration and pageout Gregory Price
2026-07-20 19:34 ` [PATCH v5 15/36] mm/ksm: skip KSM for managed-memory folios Gregory Price
2026-07-20 19:34 ` [PATCH v5 16/36] mm/khugepaged: skip private node folios when trying to collapse Gregory Price
2026-07-20 19:34 ` [PATCH v5 17/36] mm/vmscan: disallow reclaim of private node memory Gregory Price
2026-07-20 19:34 ` [PATCH v5 18/36] mm/gup: disallow longterm pin of private node folios Gregory Price
2026-07-20 19:34 ` [PATCH v5 19/36] proc: include N_MEMORY_PRIVATE nodes in numa_maps output Gregory Price
2026-07-20 19:34 ` [PATCH v5 20/36] mm/memcontrol: account private-node memory in per-node stats Gregory Price
2026-07-20 19:34 ` [PATCH v5 21/36] proc/kcore: include private-node RAM in the kcore RAM map Gregory Price
2026-07-20 20:05   ` Omar Sandoval
2026-07-20 19:34 ` [PATCH v5 22/36] mm/mempolicy: add MPOL_F_PRIVATE and zonelist selection Gregory Price
2026-07-20 19:34 ` [PATCH v5 23/36] mm/mempolicy: apply policy at the kernel zone for private-node binds Gregory Price
2026-07-20 19:34 ` [PATCH v5 24/36] mm/mempolicy: add in-kernel MPOL_BIND interfaces for drivers/services Gregory Price
2026-07-20 19:34 ` [PATCH v5 25/36] mm/memory_hotplug: support N_MEMORY_PRIVATE node hotplug Gregory Price
2026-07-20 19:34 ` [PATCH v5 26/36] mm: add NODE_PRIVATE_CAP_RECLAIM for opted-in private node reclaim Gregory Price
2026-07-20 19:34 ` [PATCH v5 27/36] mm: add NODE_PRIVATE_CAP_USER_NUMA for userland numa controls Gregory Price
2026-07-20 19:34 ` [PATCH v5 28/36] mm: add NODE_PRIVATE_CAP_HOTUNPLUG for opted-in private nodes Gregory Price
2026-07-20 19:34 ` [PATCH v5 29/36] mm: add NODE_PRIVATE_CAP_DEMOTION for private-node tiering demotion Gregory Price
2026-07-20 19:34 ` [PATCH v5 30/36] mm: add NODE_PRIVATE_CAP_NUMA_BALANCING for private-node NUMA balancing Gregory Price
2026-07-20 19:34 ` [PATCH v5 31/36] mm: add NODE_PRIVATE_CAP_LTPIN for private node folio pinning Gregory Price
2026-07-20 19:34 ` [PATCH v5 32/36] mm/khugepaged: base private node collapse eligiblity on actor/cap bits Gregory Price
2026-07-20 19:34 ` [PATCH v5 33/36] Documentation/mm: describe private (N_MEMORY_PRIVATE) memory nodes Gregory Price
2026-07-20 19:34 ` [PATCH v5 34/36] mm/mempolicy: add mpol_set_shared_policy_range() Gregory Price
2026-07-20 19:34 ` [PATCH v5 35/36] KVM: guest_memfd: bind backing memory to a NUMA node at creation Gregory Price
2026-07-21  3:46 ` [PATCH v5 00/36] Private Memory NUMA Nodes Balbir Singh
2026-07-21 18:16   ` Gregory Price
2026-07-21 13:26 ` Zenghui Yu
2026-07-21 17:18   ` Gregory Price

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=20260720193431.3841992-2-gourry@gourry.net \
    --to=gourry@gourry.net \
    --cc=Zhigang.Luo@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=alison.schofield@intel.com \
    --cc=alucerop@amd.com \
    --cc=apopple@nvidia.com \
    --cc=arun.george@samsung.com \
    --cc=axelrasmussen@google.com \
    --cc=balbirs@nvidia.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=brendan.jackman@linux.dev \
    --cc=byungchul@sk.com \
    --cc=cgroups@vger.kernel.org \
    --cc=chengming.zhou@linux.dev \
    --cc=corbet@lwn.net \
    --cc=dakr@kernel.org \
    --cc=damon@lists.linux.dev \
    --cc=dave.jiang@intel.com \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=djbw@kernel.org \
    --cc=driver-core@lists.linux.dev \
    --cc=gregkh@linuxfoundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=jackmanb@google.com \
    --cc=jannh@google.com \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=kasong@tencent.com \
    --cc=kernel-team@meta.com \
    --cc=kvm@vger.kernel.org \
    --cc=lance.yang@linux.dev \
    --cc=liam@infradead.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-debuggers@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=ljs@kernel.org \
    --cc=longman@redhat.com \
    --cc=matthew.brost@intel.com \
    --cc=mhocko@suse.com \
    --cc=mkoutny@suse.com \
    --cc=muchun.song@linux.dev \
    --cc=npache@redhat.com \
    --cc=nvdimm@lists.linux.dev \
    --cc=osalvador@suse.de \
    --cc=osandov@osandov.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pfalcato@suse.de \
    --cc=qi.zheng@linux.dev \
    --cc=rafael@kernel.org \
    --cc=rakie.kim@sk.com \
    --cc=ridong.chen@linux.dev \
    --cc=roman.gushchin@linux.dev \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=shakeel.butt@linux.dev \
    --cc=sj@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=surenb@google.com \
    --cc=tj@kernel.org \
    --cc=usama.arif@linux.dev \
    --cc=vbabka@kernel.org \
    --cc=vishal.l.verma@intel.com \
    --cc=weixugc@google.com \
    --cc=xu.xin16@zte.com.cn \
    --cc=ying.huang@linux.alibaba.com \
    --cc=yuanchu@google.com \
    --cc=yury.norov@gmail.com \
    --cc=yuzenghui@huawei.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