fork: stop ignoring NUMA while handling cached thread stacks

1. the numa parameter was straight up ignored.
2. nothing was done to check if the to-be-cached/allocated stack matches
   the local node

The id remains ignored on free in case of memoryless nodes.

Note the current caching is already bad as the cache keeps overflowing
and a different solution is needed for the long run, to be worked
out(tm).

Stats collected over a kernel build with the patch with the following
topology:
  NUMA node(s):              2
  NUMA node0 CPU(s):         0-11
  NUMA node1 CPU(s):         12-23

caller's node vs stack backing pages on free:
matching:	50083 (70%)
mismatched:	21492 (30%)

caching efficiency:
cached:		32651 (65.2%)
dropped:	17432 (34.8%)

Link: https://lkml.kernel.org/r/20251120054015.3019419-1-mjguzik@gmail.com
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Linus Waleij <linus.walleij@linaro.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 53 insertions, 10 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 3da0f08615a9..17fcb75ca5d5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -208,15 +208,62 @@ struct vm_stack {
 	struct vm_struct *stack_vm_area;
 };
 
+static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node)
+{
+	struct vm_struct *vm_area;
+	unsigned int i;
+
+	/*
+	 * If the node has memory, we are guaranteed the stacks are backed by local pages.
+	 * Otherwise the pages are arbitrary.
+	 *
+	 * Note that depending on cpuset it is possible we will get migrated to a different
+	 * node immediately after allocating here, so this does *not* guarantee locality for
+	 * arbitrary callers.
+	 */
+	scoped_guard(preempt) {
+		if (node != NUMA_NO_NODE && numa_node_id() != node)
+			return NULL;
+
+		for (i = 0; i < NR_CACHED_STACKS; i++) {
+			vm_area = this_cpu_xchg(cached_stacks[i], NULL);
+			if (vm_area)
+				return vm_area;
+		}
+	}
+
+	return NULL;
+}
+
 static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area)
 {
 	unsigned int i;
+	int nid;
 
-	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		struct vm_struct *tmp = NULL;
+	/*
+	 * Don't cache stacks if any of the pages don't match the local domain, unless
+	 * there is no local memory to begin with.
+	 *
+	 * Note that lack of local memory does not automatically mean it makes no difference
+	 * performance-wise which other domain backs the stack. In this case we are merely
+	 * trying to avoid constantly going to vmalloc.
+	 */
+	scoped_guard(preempt) {
+		nid = numa_node_id();
+		if (node_state(nid, N_MEMORY)) {
+			for (i = 0; i < vm_area->nr_pages; i++) {
+				struct page *page = vm_area->pages[i];
+				if (page_to_nid(page) != nid)
+					return false;
+			}
+		}
+
+		for (i = 0; i < NR_CACHED_STACKS; i++) {
+			struct vm_struct *tmp = NULL;
 
-		if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area))
-			return true;
+			if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area))
+				return true;
+		}
 	}
 	return false;
 }
@@ -283,13 +330,9 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 {
 	struct vm_struct *vm_area;
 	void *stack;
-	int i;
-
-	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		vm_area = this_cpu_xchg(cached_stacks[i], NULL);
-		if (!vm_area)
-			continue;
 
+	vm_area = alloc_thread_stack_node_from_cache(tsk, node);
+	if (vm_area) {
 		if (memcg_charge_kernel_stack(vm_area)) {
 			vfree(vm_area->addr);
 			return -ENOMEM;