From: Gregory Price <gourry@gourry.net>
To: lsf-pc@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org, linux-cxl@vger.kernel.org,
cgroups@vger.kernel.org, linux-mm@kvack.org,
linux-trace-kernel@vger.kernel.org, damon@lists.linux.dev,
kernel-team@meta.com, gregkh@linuxfoundation.org,
rafael@kernel.org, dakr@kernel.org, dave@stgolabs.net,
jonathan.cameron@huawei.com, dave.jiang@intel.com,
alison.schofield@intel.com, vishal.l.verma@intel.com,
ira.weiny@intel.com, dan.j.williams@intel.com,
longman@redhat.com, akpm@linux-foundation.org, david@kernel.org,
lorenzo.stoakes@oracle.com, Liam.Howlett@oracle.com,
vbabka@suse.cz, rppt@kernel.org, surenb@google.com,
mhocko@suse.com, osalvador@suse.de, ziy@nvidia.com,
matthew.brost@intel.com, joshua.hahnjy@gmail.com,
rakie.kim@sk.com, byungchul@sk.com, gourry@gourry.net,
ying.huang@linux.alibaba.com, apopple@nvidia.com,
axelrasmussen@google.com, yuanchu@google.com, weixugc@google.com,
yury.norov@gmail.com, linux@rasmusvillemoes.dk,
mhiramat@kernel.org, mathieu.desnoyers@efficios.com,
tj@kernel.org, hannes@cmpxchg.org, mkoutny@suse.com,
jackmanb@google.com, sj@kernel.org,
baolin.wang@linux.alibaba.com, npache@redhat.com,
ryan.roberts@arm.com, dev.jain@arm.com, baohua@kernel.org,
lance.yang@linux.dev, muchun.song@linux.dev, xu.xin16@zte.com.cn,
chengming.zhou@linux.dev, jannh@google.com, linmiaohe@huawei.com,
nao.horiguchi@gmail.com, pfalcato@suse.de, rientjes@google.com,
shakeel.butt@linux.dev, riel@surriel.com, harry.yoo@oracle.com,
cl@gentwo.org, roman.gushchin@linux.dev, chrisl@kernel.org,
kasong@tencent.com, shikemeng@huaweicloud.com, nphamcs@gmail.com,
bhe@redhat.com, zhengqi.arch@bytedance.com, terry.bowman@amd.com
Subject: [RFC PATCH v4 17/27] mm/oom: NP_OPS_OOM_ELIGIBLE - private node OOM participation
Date: Sun, 22 Feb 2026 03:48:32 -0500 [thread overview]
Message-ID: <20260222084842.1824063-18-gourry@gourry.net> (raw)
In-Reply-To: <20260222084842.1824063-1-gourry@gourry.net>
The OOM killer must know whether killing a task can actually free
memory such that pressure is reduced.
A private node only contributes to relieving pressure if it participates
in both reclaim and demotion. Without this check, the check, the OOM
killer may select an undeserving victim.
Introduce NP_OPS_OOM_ELIGIBLE and helpers node_oom_eligible() and
zone_oom_eligible().
Replace cpuset_mems_allowed_intersects() in oom_cpuset_eligible()
with oom_mems_intersect() that iterates N_MEMORY nodes and skips
ineligible private nodes.
Update constrained_alloc() to use zone_oom_eligible() for constraint
detection and node_oom_eligible() to exclude ineligible nodes from
totalpages accounting.
Remove cpuset_mems_allowed_intersects() as it has no remaining callers.
Signed-off-by: Gregory Price <gourry@gourry.net>
---
include/linux/cpuset.h | 9 -------
include/linux/node_private.h | 3 +++
kernel/cgroup/cpuset.c | 17 ------------
mm/oom_kill.c | 52 ++++++++++++++++++++++++++++++++----
4 files changed, 50 insertions(+), 31 deletions(-)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 7b2f3f6b68a9..53ccfb00b277 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -97,9 +97,6 @@ static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
return true;
}
-extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
- const struct task_struct *tsk2);
-
#ifdef CONFIG_CPUSETS_V1
#define cpuset_memory_pressure_bump() \
do { \
@@ -241,12 +238,6 @@ static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
return true;
}
-static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
- const struct task_struct *tsk2)
-{
- return 1;
-}
-
static inline void cpuset_memory_pressure_bump(void) {}
static inline void cpuset_task_status_allowed(struct seq_file *m,
diff --git a/include/linux/node_private.h b/include/linux/node_private.h
index 34be52383255..34d862f09e24 100644
--- a/include/linux/node_private.h
+++ b/include/linux/node_private.h
@@ -141,6 +141,9 @@ struct node_private_ops {
/* Kernel reclaim (kswapd, direct reclaim, OOM) operates on this node */
#define NP_OPS_RECLAIM BIT(4)
+/* Private node is OOM-eligible: reclaim can run and pages can be demoted here */
+#define NP_OPS_OOM_ELIGIBLE (NP_OPS_RECLAIM | NP_OPS_DEMOTION)
+
/**
* struct node_private - Per-node container for N_MEMORY_PRIVATE nodes
*
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 1a597f0c7c6c..29789d544fd5 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4530,23 +4530,6 @@ int cpuset_mem_spread_node(void)
return cpuset_spread_node(¤t->cpuset_mem_spread_rotor);
}
-/**
- * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's?
- * @tsk1: pointer to task_struct of some task.
- * @tsk2: pointer to task_struct of some other task.
- *
- * Description: Return true if @tsk1's mems_allowed intersects the
- * mems_allowed of @tsk2. Used by the OOM killer to determine if
- * one of the task's memory usage might impact the memory available
- * to the other.
- **/
-
-int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
- const struct task_struct *tsk2)
-{
- return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed);
-}
-
/**
* cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed
*
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5eb11fbba704..cd0d65ccd1e8 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -74,7 +74,45 @@ static inline bool is_memcg_oom(struct oom_control *oc)
return oc->memcg != NULL;
}
+/* Private nodes are only eligible if they support both reclaim and demotion */
+static inline bool node_oom_eligible(int nid)
+{
+ if (!node_state(nid, N_MEMORY_PRIVATE))
+ return true;
+ return (node_private_flags(nid) & NP_OPS_OOM_ELIGIBLE) ==
+ NP_OPS_OOM_ELIGIBLE;
+}
+
+static inline bool zone_oom_eligible(struct zone *zone, gfp_t gfp_mask)
+{
+ if (!node_oom_eligible(zone_to_nid(zone)))
+ return false;
+ return cpuset_zone_allowed(zone, gfp_mask);
+}
+
#ifdef CONFIG_NUMA
+/*
+ * Killing a task can only relieve system pressure if freed memory can be
+ * demoted there and reclaim can operate on the node's pages, so we
+ * omit private nodes that aren't eligible.
+ */
+static bool oom_mems_intersect(const struct task_struct *tsk1,
+ const struct task_struct *tsk2)
+{
+ int nid;
+
+ for_each_node_state(nid, N_MEMORY) {
+ if (!node_isset(nid, tsk1->mems_allowed))
+ continue;
+ if (!node_isset(nid, tsk2->mems_allowed))
+ continue;
+ if (!node_oom_eligible(nid))
+ continue;
+ return true;
+ }
+ return false;
+}
+
/**
* oom_cpuset_eligible() - check task eligibility for kill
* @start: task struct of which task to consider
@@ -107,9 +145,10 @@ static bool oom_cpuset_eligible(struct task_struct *start,
} else {
/*
* This is not a mempolicy constrained oom, so only
- * check the mems of tsk's cpuset.
+ * check the mems of tsk's cpuset, excluding private
+ * nodes that do not participate in kernel reclaim.
*/
- ret = cpuset_mems_allowed_intersects(current, tsk);
+ ret = oom_mems_intersect(current, tsk);
}
if (ret)
break;
@@ -291,16 +330,19 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
return CONSTRAINT_MEMORY_POLICY;
}
- /* Check this allocation failure is caused by cpuset's wall function */
+ /* Check this allocation failure is caused by cpuset or private node constraints */
for_each_zone_zonelist_nodemask(zone, z, oc->zonelist,
highest_zoneidx, oc->nodemask)
- if (!cpuset_zone_allowed(zone, oc->gfp_mask))
+ if (!zone_oom_eligible(zone, oc->gfp_mask))
cpuset_limited = true;
if (cpuset_limited) {
oc->totalpages = total_swap_pages;
- for_each_node_mask(nid, cpuset_current_mems_allowed)
+ for_each_node_mask(nid, cpuset_current_mems_allowed) {
+ if (!node_oom_eligible(nid))
+ continue;
oc->totalpages += node_present_pages(nid);
+ }
return CONSTRAINT_CPUSET;
}
return CONSTRAINT_NONE;
--
2.53.0
next prev parent reply other threads:[~2026-02-22 8:50 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-22 8:48 [LSF/MM/BPF TOPIC][RFC PATCH v4 00/27] Private Memory Nodes (w/ Compressed RAM) Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 01/27] numa: introduce N_MEMORY_PRIVATE node state Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 02/27] mm,cpuset: gate allocations from N_MEMORY_PRIVATE behind __GFP_PRIVATE Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 03/27] mm/page_alloc: add numa_zone_allowed() and wire it up Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 04/27] mm/page_alloc: Add private node handling to build_zonelists Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 05/27] mm: introduce folio_is_private_managed() unified predicate Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 06/27] mm/mlock: skip mlock for managed-memory folios Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 07/27] mm/madvise: skip madvise " Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 08/27] mm/ksm: skip KSM " Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 09/27] mm/khugepaged: skip private node folios when trying to collapse Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 10/27] mm/swap: add free_folio callback for folio release cleanup Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 11/27] mm/huge_memory.c: add private node folio split notification callback Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 12/27] mm/migrate: NP_OPS_MIGRATION - support private node user migration Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 13/27] mm/mempolicy: NP_OPS_MEMPOLICY - support private node mempolicy Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 14/27] mm/memory-tiers: NP_OPS_DEMOTION - support private node demotion Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 15/27] mm/mprotect: NP_OPS_PROTECT_WRITE - gate PTE/PMD write-upgrades Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 16/27] mm: NP_OPS_RECLAIM - private node reclaim participation Gregory Price
2026-02-22 8:48 ` Gregory Price [this message]
2026-02-22 8:48 ` [RFC PATCH v4 18/27] mm/memory: NP_OPS_NUMA_BALANCING - private node NUMA balancing Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 19/27] mm/compaction: NP_OPS_COMPACTION - private node compaction support Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 20/27] mm/gup: NP_OPS_LONGTERM_PIN - private node longterm pin support Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 21/27] mm/memory-failure: add memory_failure callback to node_private_ops Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 22/27] mm/memory_hotplug: add add_private_memory_driver_managed() Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 23/27] mm/cram: add compressed ram memory management subsystem Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 24/27] cxl/core: Add cxl_sysram region type Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 25/27] cxl/core: Add private node support to cxl_sysram Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 26/27] cxl: add cxl_mempolicy sample PCI driver Gregory Price
2026-02-22 8:48 ` [RFC PATCH v4 27/27] cxl: add cxl_compression " 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=20260222084842.1824063-18-gourry@gourry.net \
--to=gourry@gourry.net \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=alison.schofield@intel.com \
--cc=apopple@nvidia.com \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=bhe@redhat.com \
--cc=byungchul@sk.com \
--cc=cgroups@vger.kernel.org \
--cc=chengming.zhou@linux.dev \
--cc=chrisl@kernel.org \
--cc=cl@gentwo.org \
--cc=dakr@kernel.org \
--cc=damon@lists.linux.dev \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=dave@stgolabs.net \
--cc=david@kernel.org \
--cc=dev.jain@arm.com \
--cc=gregkh@linuxfoundation.org \
--cc=hannes@cmpxchg.org \
--cc=harry.yoo@oracle.com \
--cc=ira.weiny@intel.com \
--cc=jackmanb@google.com \
--cc=jannh@google.com \
--cc=jonathan.cameron@huawei.com \
--cc=joshua.hahnjy@gmail.com \
--cc=kasong@tencent.com \
--cc=kernel-team@meta.com \
--cc=lance.yang@linux.dev \
--cc=linmiaohe@huawei.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=linux@rasmusvillemoes.dk \
--cc=longman@redhat.com \
--cc=lorenzo.stoakes@oracle.com \
--cc=lsf-pc@lists.linux-foundation.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=matthew.brost@intel.com \
--cc=mhiramat@kernel.org \
--cc=mhocko@suse.com \
--cc=mkoutny@suse.com \
--cc=muchun.song@linux.dev \
--cc=nao.horiguchi@gmail.com \
--cc=npache@redhat.com \
--cc=nphamcs@gmail.com \
--cc=osalvador@suse.de \
--cc=pfalcato@suse.de \
--cc=rafael@kernel.org \
--cc=rakie.kim@sk.com \
--cc=riel@surriel.com \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=rppt@kernel.org \
--cc=ryan.roberts@arm.com \
--cc=shakeel.butt@linux.dev \
--cc=shikemeng@huaweicloud.com \
--cc=sj@kernel.org \
--cc=surenb@google.com \
--cc=terry.bowman@amd.com \
--cc=tj@kernel.org \
--cc=vbabka@suse.cz \
--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=zhengqi.arch@bytedance.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