Merge tag 'mm-nonmm-stable-2026-02-12-10-48' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:

 - "ocfs2: give ocfs2 the ability to reclaim suballocator free bg" saves
   disk space by teaching ocfs2 to reclaim suballocator block group
   space (Heming Zhao)

 - "Add ARRAY_END(), and use it to fix off-by-one bugs" adds the
   ARRAY_END() macro and uses it in various places (Alejandro Colomar)

 - "vmcoreinfo: support VMCOREINFO_BYTES larger than PAGE_SIZE" makes
   the vmcore code future-safe, if VMCOREINFO_BYTES ever exceeds the
   page size (Pnina Feder)

 - "kallsyms: Prevent invalid access when showing module buildid" cleans
   up kallsyms code related to module buildid and fixes an invalid
   access crash when printing backtraces (Petr Mladek)

 - "Address page fault in ima_restore_measurement_list()" fixes a
   kexec-related crash that can occur when booting the second-stage
   kernel on x86 (Harshit Mogalapalli)

 - "kho: ABI headers and Documentation updates" updates the kexec
   handover ABI documentation (Mike Rapoport)

 - "Align atomic storage" adds the __aligned attribute to atomic_t and
   atomic64_t definitions to get natural alignment of both types on
   csky, m68k, microblaze, nios2, openrisc and sh (Finn Thain)

 - "kho: clean up page initialization logic" simplifies the page
   initialization logic in kho_restore_page() (Pratyush Yadav)

 - "Unload linux/kernel.h" moves several things out of kernel.h and into
   more appropriate places (Yury Norov)

 - "don't abuse task_struct.group_leader" removes the usage of
   ->group_leader when it is "obviously unnecessary" (Oleg Nesterov)

 - "list private v2 & luo flb" adds some infrastructure improvements to
   the live update orchestrator (Pasha Tatashin)

* tag 'mm-nonmm-stable-2026-02-12-10-48' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (107 commits)
  watchdog/hardlockup: simplify perf event probe and remove per-cpu dependency
  procfs: fix missing RCU protection when reading real_parent in do_task_stat()
  watchdog/softlockup: fix sample ring index wrap in need_counting_irqs()
  kcsan, compiler_types: avoid duplicate type issues in BPF Type Format
  kho: fix doc for kho_restore_pages()
  tests/liveupdate: add in-kernel liveupdate test
  liveupdate: luo_flb: introduce File-Lifecycle-Bound global state
  liveupdate: luo_file: Use private list
  list: add kunit test for private list primitives
  list: add primitives for private list manipulations
  delayacct: fix uapi timespec64 definition
  panic: add panic_force_cpu= parameter to redirect panic to a specific CPU
  netclassid: use thread_group_leader(p) in update_classid_task()
  RDMA/umem: don't abuse current->group_leader
  drm/pan*: don't abuse current->group_leader
  drm/amd: kill the outdated "Only the pthreads threading model is supported" checks
  drm/amdgpu: don't abuse current->group_leader
  android/binder: use same_thread_group(proc->tsk, current) in binder_mmap()
  android/binder: don't abuse current->group_leader
  kho: skip memoryless NUMA nodes when reserving scratch areas
  ...

1 files changed, 206 insertions, 65 deletions

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index 6d08ac05f371..a93df70919df 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -114,48 +114,15 @@ static int ncpus_cmp_func(const void *l, const void *r)
 	return ln->ncpus - rn->ncpus;
 }
 
-/*
- * Allocate group number for each node, so that for each node:
- *
- * 1) the allocated number is >= 1
- *
- * 2) the allocated number is <= active CPU number of this node
- *
- * The actual allocated total groups may be less than @numgrps when
- * active total CPU number is less than @numgrps.
- *
- * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]'
- * for each node.
- */
-static void alloc_nodes_groups(unsigned int numgrps,
-			       cpumask_var_t *node_to_cpumask,
-			       const struct cpumask *cpu_mask,
-			       const nodemask_t nodemsk,
-			       struct cpumask *nmsk,
-			       struct node_groups *node_groups)
+static void alloc_groups_to_nodes(unsigned int numgrps,
+				  unsigned int numcpus,
+				  struct node_groups *node_groups,
+				  unsigned int num_nodes)
 {
-	unsigned n, remaining_ncpus = 0;
-
-	for (n = 0; n < nr_node_ids; n++) {
-		node_groups[n].id = n;
-		node_groups[n].ncpus = UINT_MAX;
-	}
-
-	for_each_node_mask(n, nodemsk) {
-		unsigned ncpus;
-
-		cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
-		ncpus = cpumask_weight(nmsk);
-
-		if (!ncpus)
-			continue;
-		remaining_ncpus += ncpus;
-		node_groups[n].ncpus = ncpus;
-	}
+	unsigned int n, remaining_ncpus = numcpus;
+	unsigned int  ngroups, ncpus;
 
-	numgrps = min_t(unsigned, remaining_ncpus, numgrps);
-
-	sort(node_groups, nr_node_ids, sizeof(node_groups[0]),
+	sort(node_groups, num_nodes, sizeof(node_groups[0]),
 	     ncpus_cmp_func, NULL);
 
 	/*
@@ -226,9 +193,8 @@ static void alloc_nodes_groups(unsigned int numgrps,
 	 * finally for each node X: grps(X) <= ncpu(X).
 	 *
 	 */
-	for (n = 0; n < nr_node_ids; n++) {
-		unsigned ngroups, ncpus;
 
+	for (n = 0; n < num_nodes; n++) {
 		if (node_groups[n].ncpus == UINT_MAX)
 			continue;
 
@@ -246,12 +212,201 @@ static void alloc_nodes_groups(unsigned int numgrps,
 	}
 }
 
+/*
+ * Allocate group number for each node, so that for each node:
+ *
+ * 1) the allocated number is >= 1
+ *
+ * 2) the allocated number is <= active CPU number of this node
+ *
+ * The actual allocated total groups may be less than @numgrps when
+ * active total CPU number is less than @numgrps.
+ *
+ * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]'
+ * for each node.
+ */
+static void alloc_nodes_groups(unsigned int numgrps,
+			       cpumask_var_t *node_to_cpumask,
+			       const struct cpumask *cpu_mask,
+			       const nodemask_t nodemsk,
+			       struct cpumask *nmsk,
+			       struct node_groups *node_groups)
+{
+	unsigned int n, numcpus = 0;
+
+	for (n = 0; n < nr_node_ids; n++) {
+		node_groups[n].id = n;
+		node_groups[n].ncpus = UINT_MAX;
+	}
+
+	for_each_node_mask(n, nodemsk) {
+		unsigned int ncpus;
+
+		cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
+		ncpus = cpumask_weight(nmsk);
+
+		if (!ncpus)
+			continue;
+		numcpus += ncpus;
+		node_groups[n].ncpus = ncpus;
+	}
+
+	numgrps = min_t(unsigned int, numcpus, numgrps);
+	alloc_groups_to_nodes(numgrps, numcpus, node_groups, nr_node_ids);
+}
+
+static void assign_cpus_to_groups(unsigned int ncpus,
+				  struct cpumask *nmsk,
+				  struct node_groups *nv,
+				  struct cpumask *masks,
+				  unsigned int *curgrp,
+				  unsigned int last_grp)
+{
+	unsigned int v, cpus_per_grp, extra_grps;
+	/* Account for rounding errors */
+	extra_grps = ncpus - nv->ngroups * (ncpus / nv->ngroups);
+
+	/* Spread allocated groups on CPUs of the current node */
+	for (v = 0; v < nv->ngroups; v++, *curgrp += 1) {
+		cpus_per_grp = ncpus / nv->ngroups;
+
+		/* Account for extra groups to compensate rounding errors */
+		if (extra_grps) {
+			cpus_per_grp++;
+			--extra_grps;
+		}
+
+		/*
+		 * wrapping has to be considered given 'startgrp'
+		 * may start anywhere
+		 */
+		if (*curgrp >= last_grp)
+			*curgrp = 0;
+		grp_spread_init_one(&masks[*curgrp], nmsk, cpus_per_grp);
+	}
+}
+
+static int alloc_cluster_groups(unsigned int ncpus,
+				unsigned int ngroups,
+				struct cpumask *node_cpumask,
+				cpumask_var_t msk,
+				const struct cpumask ***clusters_ptr,
+				struct node_groups **cluster_groups_ptr)
+{
+	unsigned int ncluster = 0;
+	unsigned int cpu, nc, n;
+	const struct cpumask *cluster_mask;
+	const struct cpumask **clusters;
+	struct node_groups *cluster_groups;
+
+	cpumask_copy(msk, node_cpumask);
+
+	/* Probe how many clusters in this node. */
+	while (1) {
+		cpu = cpumask_first(msk);
+		if (cpu >= nr_cpu_ids)
+			break;
+
+		cluster_mask = topology_cluster_cpumask(cpu);
+		if (!cpumask_weight(cluster_mask))
+			goto no_cluster;
+		/* Clean out CPUs on the same cluster. */
+		cpumask_andnot(msk, msk, cluster_mask);
+		ncluster++;
+	}
+
+	/* If ngroups < ncluster, cross cluster is inevitable, skip. */
+	if (ncluster == 0 || ncluster > ngroups)
+		goto no_cluster;
+
+	/* Allocate memory based on cluster number. */
+	clusters = kcalloc(ncluster, sizeof(struct cpumask *), GFP_KERNEL);
+	if (!clusters)
+		goto no_cluster;
+	cluster_groups = kcalloc(ncluster, sizeof(struct node_groups), GFP_KERNEL);
+	if (!cluster_groups)
+		goto fail_cluster_groups;
+
+	/* Filling cluster info for later process. */
+	cpumask_copy(msk, node_cpumask);
+	for (n = 0; n < ncluster; n++) {
+		cpu = cpumask_first(msk);
+		cluster_mask = topology_cluster_cpumask(cpu);
+		nc = cpumask_weight_and(cluster_mask, node_cpumask);
+		clusters[n] = cluster_mask;
+		cluster_groups[n].id = n;
+		cluster_groups[n].ncpus = nc;
+		cpumask_andnot(msk, msk, cluster_mask);
+	}
+
+	alloc_groups_to_nodes(ngroups, ncpus, cluster_groups, ncluster);
+
+	*clusters_ptr = clusters;
+	*cluster_groups_ptr = cluster_groups;
+	return ncluster;
+
+ fail_cluster_groups:
+	kfree(clusters);
+ no_cluster:
+	return 0;
+}
+
+/*
+ * Try group CPUs evenly for cluster locality within a NUMA node.
+ *
+ * Return: true if success, false otherwise.
+ */
+static bool __try_group_cluster_cpus(unsigned int ncpus,
+				     unsigned int ngroups,
+				     struct cpumask *node_cpumask,
+				     struct cpumask *masks,
+				     unsigned int *curgrp,
+				     unsigned int last_grp)
+{
+	struct node_groups *cluster_groups;
+	const struct cpumask **clusters;
+	unsigned int ncluster;
+	bool ret = false;
+	cpumask_var_t nmsk;
+	unsigned int i, nc;
+
+	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
+		goto fail_nmsk_alloc;
+
+	ncluster = alloc_cluster_groups(ncpus, ngroups, node_cpumask, nmsk,
+					&clusters, &cluster_groups);
+
+	if (ncluster == 0)
+		goto fail_no_clusters;
+
+	for (i = 0; i < ncluster; i++) {
+		struct node_groups *nv = &cluster_groups[i];
+
+		/* Get the cpus on this cluster. */
+		cpumask_and(nmsk, node_cpumask, clusters[nv->id]);
+		nc = cpumask_weight(nmsk);
+		if (!nc)
+			continue;
+		WARN_ON_ONCE(nv->ngroups > nc);
+
+		assign_cpus_to_groups(nc, nmsk, nv, masks, curgrp, last_grp);
+	}
+
+	ret = true;
+	kfree(cluster_groups);
+	kfree(clusters);
+ fail_no_clusters:
+	free_cpumask_var(nmsk);
+ fail_nmsk_alloc:
+	return ret;
+}
+
 static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
 			       cpumask_var_t *node_to_cpumask,
 			       const struct cpumask *cpu_mask,
 			       struct cpumask *nmsk, struct cpumask *masks)
 {
-	unsigned int i, n, nodes, cpus_per_grp, extra_grps, done = 0;
+	unsigned int i, n, nodes, done = 0;
 	unsigned int last_grp = numgrps;
 	unsigned int curgrp = startgrp;
 	nodemask_t nodemsk = NODE_MASK_NONE;
@@ -287,7 +442,7 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
 	alloc_nodes_groups(numgrps, node_to_cpumask, cpu_mask,
 			   nodemsk, nmsk, node_groups);
 	for (i = 0; i < nr_node_ids; i++) {
-		unsigned int ncpus, v;
+		unsigned int ncpus;
 		struct node_groups *nv = &node_groups[i];
 
 		if (nv->ngroups == UINT_MAX)
@@ -301,28 +456,14 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
 
 		WARN_ON_ONCE(nv->ngroups > ncpus);
 
-		/* Account for rounding errors */
-		extra_grps = ncpus - nv->ngroups * (ncpus / nv->ngroups);
-
-		/* Spread allocated groups on CPUs of the current node */
-		for (v = 0; v < nv->ngroups; v++, curgrp++) {
-			cpus_per_grp = ncpus / nv->ngroups;
-
-			/* Account for extra groups to compensate rounding errors */
-			if (extra_grps) {
-				cpus_per_grp++;
-				--extra_grps;
-			}
-
-			/*
-			 * wrapping has to be considered given 'startgrp'
-			 * may start anywhere
-			 */
-			if (curgrp >= last_grp)
-				curgrp = 0;
-			grp_spread_init_one(&masks[curgrp], nmsk,
-						cpus_per_grp);
+		if (__try_group_cluster_cpus(ncpus, nv->ngroups, nmsk,
+					     masks, &curgrp, last_grp)) {
+			done += nv->ngroups;
+			continue;
 		}
+
+		assign_cpus_to_groups(ncpus, nmsk, nv, masks, &curgrp,
+				      last_grp);
 		done += nv->ngroups;
 	}
 	kfree(node_groups);