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 24/36] mm/mempolicy: add in-kernel MPOL_BIND interfaces for drivers/services
Date: Mon, 20 Jul 2026 15:34:18 -0400 [thread overview]
Message-ID: <20260720193431.3841992-25-gourry@gourry.net> (raw)
In-Reply-To: <20260720193431.3841992-1-gourry@gourry.net>
Add and export interfaces to enable modules to build a mempolicy with
(MPOL_BIND | MPOL_F_PRIVATE) pinned to a private NUMA node, so the
drivers can stamp it onto VMAs they control (via vma->vm_policy).
mpol_bind_node() - acts the same as a userland mbind()
mpol_private_bind() - bypasses the CAP_USER_NUMA check.
Export it to modules (private:kmem, bind:kvm).
Widen __mpol_put()'s module export to kmem so the driver can
release the policy.
Adjust mpol_set_nodemask to check for a pre-set MPOL_F_PRIVATE flag
to allow the mpol_private_bind() check to bypass the N_MEMORY filter.
Signed-off-by: Gregory Price <gourry@gourry.net>
---
include/linux/mempolicy.h | 14 ++++++
mm/mempolicy.c | 102 +++++++++++++++++++++++++++++++++++++-
2 files changed, 114 insertions(+), 2 deletions(-)
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 65c732d440d2f..715951a5b03c1 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -7,6 +7,7 @@
#define _LINUX_MEMPOLICY_H 1
#include <linux/sched.h>
+#include <linux/err.h>
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
@@ -128,6 +129,9 @@ void mpol_free_shared_policy(struct shared_policy *sp);
struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
pgoff_t idx);
+struct mempolicy *mpol_private_bind(int nid);
+struct mempolicy *mpol_bind_node(int nid);
+
struct mempolicy *get_task_policy(struct task_struct *p);
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx);
@@ -226,6 +230,16 @@ mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx)
return NULL;
}
+static inline struct mempolicy *mpol_private_bind(int nid)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline struct mempolicy *mpol_bind_node(int nid)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, int order, pgoff_t *ilx)
{
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e83c2c7a94c1d..a3ffb09897489 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -406,7 +406,7 @@ static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
static int mpol_set_nodemask(struct mempolicy *pol,
const nodemask_t *nodes, struct nodemask_scratch *nsc)
{
- int ret;
+ int ret, nid;
/*
* Default (pol==NULL) resp. local memory policies are not a
@@ -432,6 +432,18 @@ static int mpol_set_nodemask(struct mempolicy *pol,
else
pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed;
+ /*
+ * Private nodes are not in cpuset.mems, so they're always stripped.
+ * Driver-allocated policies will already have MPOL_F_PRIVATE set,
+ * if that's the case, add back in the requested set of private nodes.
+ */
+ for_each_node_mask(nid, *nodes) {
+ if (!node_is_private(nid))
+ continue;
+ if (pol->flags & MPOL_F_PRIVATE)
+ node_set(nid, nsc->mask2);
+ }
+
/* If any private nodes left in the nodemask - add the private flag */
if (nodes_intersects(nsc->mask2, node_states[N_MEMORY_PRIVATE]))
pol->flags |= MPOL_F_PRIVATE;
@@ -501,7 +513,7 @@ void __mpol_put(struct mempolicy *pol)
*/
kfree_rcu(pol, rcu);
}
-EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm");
+EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm,kmem");
static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
{
@@ -1126,6 +1138,92 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
return ret;
}
+/*
+ * Build a refcounted MPOL_BIND policy targeting the single node @nid,
+ * contextualised to the caller's cpuset like a userspace mbind().
+ *
+ * @flags is MPOL_F_PRIVATE for the an explicit in-kernel user, letting
+ * a private node be bound without checking CAP_USER_NUMA. Otherwise,
+ * CAP_USER_NUMA is enforced.
+ *
+ * The caller owns the reference and frees it with mpol_put().
+ */
+static struct mempolicy *__mpol_bind_node(int nid, unsigned short flags)
+{
+ struct mempolicy *pol;
+ nodemask_t nodes;
+ int err;
+
+ NODEMASK_SCRATCH(scratch);
+
+ if (!scratch)
+ return ERR_PTR(-ENOMEM);
+
+ nodes_clear(nodes);
+ node_set(nid, nodes);
+
+ pol = mpol_new(MPOL_BIND, flags, &nodes);
+ if (IS_ERR(pol)) {
+ NODEMASK_SCRATCH_FREE(scratch);
+ return pol;
+ }
+
+ err = mpol_set_nodemask(pol, &nodes, scratch);
+ NODEMASK_SCRATCH_FREE(scratch);
+ if (err) {
+ mpol_put(pol);
+ return ERR_PTR(err);
+ }
+ return pol;
+}
+
+/**
+ * mpol_private_bind - build an MPOL_BIND policy pinned to a private node
+ * @nid: an N_MEMORY_PRIVATE node
+ *
+ * Returns a refcounted mempolicy that binds allocations to @nid with the
+ * private-placement intent (MPOL_F_PRIVATE). This binds to @nid regardless
+ * of the node's CAP_USER_NUMA, providing a privileged way for node-owners
+ * to bind driver/service owned VMAs to the node.
+ *
+ * Like any MPOL_BIND it is relaxable: an unsatisfiable request falls back
+ * rather than failing.
+ *
+ * Must be called while @nid is N_MEMORY_PRIVATE.
+ *
+ * The caller owns the reference and frees it with mpol_put().
+ *
+ * Return: the policy, or an ERR_PTR on failure.
+ */
+struct mempolicy *mpol_private_bind(int nid)
+{
+ if (!node_is_private(nid))
+ return ERR_PTR(-EINVAL);
+ return __mpol_bind_node(nid, MPOL_F_PRIVATE);
+}
+EXPORT_SYMBOL_FOR_MODULES(mpol_private_bind, "kmem");
+
+/**
+ * mpol_bind_node - build an MPOL_BIND policy targeting @nid for in-kernel use
+ * @nid: the node to bind to
+ *
+ * Returns a refcounted MPOL_BIND policy that places allocations on @nid,
+ * contextualised to the caller's cpuset exactly like a userspace mbind().
+ *
+ * This interface should be used by services implenting mempolicy support with
+ * user-provided node bindings. N_MEMORY_PRIVATE node bindings are honored if
+ * the node has CAP_USER_NUMA, otherwise return -EINVAL.
+ *
+ * The caller owns the reference and frees it with mpol_put().
+ *
+ * Return: the policy, or an ERR_PTR on failure.
+ */
+struct mempolicy *mpol_bind_node(int nid)
+{
+ return __mpol_bind_node(nid, 0);
+}
+EXPORT_SYMBOL_FOR_MODULES(mpol_bind_node, "kvm");
+
/*
* Return nodemask for policy for get_mempolicy() query
*
--
2.53.0-Meta
next prev parent reply other threads:[~2026-07-20 19:35 UTC|newest]
Thread overview: 44+ 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 ` [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
2026-07-21 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 ` Gregory Price [this message]
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
2026-07-22 8:29 ` Balbir Singh
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=20260720193431.3841992-25-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