fork: free vmapped stacks in cache when cpus are offline

Using virtually mapped stack, kernel stacks are allocated via vmalloc.

In the current implementation, two stacks per cpu can be cached when
tasks are freed and the cached stacks are used again in task
duplications.  But the cached stacks may remain unfreed even when cpu
are offline.  By adding a cpu hotplug callback to free the cached stacks
when a cpu goes offline, the pages of the cached stacks are not wasted.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Hoeun Ryu <[email protected]>
Reviewed-by: Thomas Gleixner <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: "Eric W. Biederman" <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Mateusz Guzik <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

kernel/fork.c

@@ -179,6 +179,24 @@ void __weak arch_release_thread_stack(unsigned long *stack)
  */
 #define NR_CACHED_STACKS 2
 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+
+static int free_vm_stack_cache(unsigned int cpu)
+{
+	struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
+	int i;
+
+	for (i = 0; i < NR_CACHED_STACKS; i++) {
+		struct vm_struct *vm_stack = cached_vm_stacks[i];
+
+		if (!vm_stack)
+			continue;
+
+		vfree(vm_stack->addr);
+		cached_vm_stacks[i] = NULL;
+	}
+
+	return 0;
+}
 #endif
 
 static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
@@ -467,6 +485,11 @@ void __init fork_init(void)
 	for (i = 0; i < UCOUNT_COUNTS; i++) {
 		init_user_ns.ucount_max[i] = max_threads/2;
 	}
+
+#ifdef CONFIG_VMAP_STACK
+	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
+			  NULL, free_vm_stack_cache);
+#endif
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,