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 06/36] cpuset: exclude private nodes from cpuset.mems (default-open)
Date: Mon, 20 Jul 2026 15:34:00 -0400 [thread overview]
Message-ID: <20260720193431.3841992-7-gourry@gourry.net> (raw)
In-Reply-To: <20260720193431.3841992-1-gourry@gourry.net>
N_MEMORY_PRIVATE node access is gated by per-node capabilities and
the zonelist. Isolating by cpuset offers no functionality and
creates issues on rebind when a cpuset loses access to that node
(in particular: it generates migrations that may not be supported).
Do not partition private nodes via cpuset.mem, instead treat them
as globally accessible resources. Do not engage in silent background
operations on these nodes due to cpuset.mem membership changing.
The result: cpuset operations checking for node validity always
allow N_MEMORY_PRIVATE nodes.
On hot-unplug, we still need to rebind memory policies if the
private node has left N_MEMORY_PRIVATE (i.e. no more memory).
Signed-off-by: Gregory Price <gourry@gourry.net>
---
kernel/cgroup/cpuset.c | 26 ++++++++++++++++++++++----
mm/memcontrol.c | 2 ++
2 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index dfd0f827e3b92..05468f95c10bd 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -26,6 +26,7 @@
#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/memory.h>
+#include <linux/node_private.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/sched/deadline.h>
@@ -3867,7 +3868,8 @@ static void cpuset_handle_hotplug(void)
static DECLARE_WORK(hk_sd_work, hk_sd_workfn);
static cpumask_t new_cpus;
static nodemask_t new_mems;
- bool cpus_updated, mems_updated;
+ static nodemask_t prev_priv_mems;
+ bool cpus_updated, mems_updated, priv_shrank;
bool on_dfl = is_in_v2_mode();
struct tmpmasks tmp, *ptmp = NULL;
@@ -3890,6 +3892,14 @@ static void cpuset_handle_hotplug(void)
!cpumask_empty(subpartitions_cpus);
mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
+ /*
+ * Private nodes are not partitioned by cpuset, but if one leaves
+ * N_MEMORY_PRIVATE we still need to run mpol_rebind_* to clean up
+ * mempolicies that are binding them.
+ */
+ priv_shrank = !nodes_subset(prev_priv_mems, node_states[N_MEMORY_PRIVATE]);
+ prev_priv_mems = node_states[N_MEMORY_PRIVATE];
+
/* For v1, synchronize cpus_allowed to cpu_active_mask */
if (cpus_updated) {
cpuset_force_rebuild();
@@ -3922,9 +3932,12 @@ static void cpuset_handle_hotplug(void)
top_cpuset.mems_allowed = new_mems;
top_cpuset.effective_mems = new_mems;
spin_unlock_irq(&callback_lock);
- cpuset_update_tasks_nodemask(&top_cpuset);
}
+ /* Rebind task mempolicies if any memory node changed state */
+ if (mems_updated || priv_shrank)
+ cpuset_update_tasks_nodemask(&top_cpuset);
+
mutex_unlock(&cpuset_mutex);
/* if cpus or mems changed, we need to propagate to descendants */
@@ -4155,11 +4168,13 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
* cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed
* @nodemask: the nodemask to be checked
*
- * Are any of the nodes in the nodemask allowed in current->mems_allowed?
+ * Are any of the nodes in the nodemask usable? N_MEMORY nodes must be in
+ * current->mems_allowed, while N_MEMORY_PRIVATE nodes are always valid.
*/
int cpuset_nodemask_valid_mems_allowed(const nodemask_t *nodemask)
{
- return nodes_intersects(*nodemask, current->mems_allowed);
+ return nodes_intersects(*nodemask, current->mems_allowed) ||
+ nodes_intersects(*nodemask, node_states[N_MEMORY_PRIVATE]);
}
/*
@@ -4223,6 +4238,9 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
if (in_interrupt())
return true;
+ /* N_MEMORY_PRIVATE nodes are not partitioned by cpusets.mems */
+ if (node_is_private(node))
+ return true;
if (node_isset(node, current->mems_allowed))
return true;
/*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8319ad8c5c23a..f0dde52dc9e0e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6069,6 +6069,8 @@ void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask)
* mask is acceptable.
*/
cpuset_nodes_allowed(memcg->css.cgroup, &allowed);
+ /* N_MEMORY_PRIVATE nodes are not partitioned by cpuset, include them */
+ nodes_or(allowed, allowed, node_states[N_MEMORY_PRIVATE]);
nodes_and(*mask, *mask, allowed);
}
--
2.53.0-Meta
next prev parent reply other threads:[~2026-07-20 19:34 UTC|newest]
Thread overview: 43+ 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 ` [PATCH v5 01/36] mm: refactor find_next_best_node to find_next_best_node_in Gregory Price
2026-07-21 5:46 ` 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 ` Gregory Price [this message]
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
2026-07-21 23:46 ` SJ Park
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=20260720193431.3841992-7-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