1 files changed, 77 insertions, 13 deletions

diff --git a/kernel/scs.c b/kernel/scs.c
index 5d4d9bbdec36..d7809affe740 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -5,26 +5,57 @@
  * Copyright (C) 2019 Google LLC
  */
 
+#include <linux/cpuhotplug.h>
 #include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/scs.h>
-#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/vmstat.h>
 
-static struct kmem_cache *scs_cache;
+#ifdef CONFIG_DYNAMIC_SCS
+DEFINE_STATIC_KEY_FALSE(dynamic_scs_enabled);
+#endif
 
 static void __scs_account(void *s, int account)
 {
-	struct page *scs_page = virt_to_page(s);
+	struct page *scs_page = vmalloc_to_page(s);
 
-	mod_zone_page_state(page_zone(scs_page), NR_KERNEL_SCS_KB,
+	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
 			    account * (SCS_SIZE / SZ_1K));
 }
 
-static void *scs_alloc(int node)
+/* Matches NR_CACHED_STACKS for VMAP_STACK */
+#define NR_CACHED_SCS 2
+static DEFINE_PER_CPU(void *, scs_cache[NR_CACHED_SCS]);
+
+static void *__scs_alloc(int node)
+{
+	int i;
+	void *s;
+
+	for (i = 0; i < NR_CACHED_SCS; i++) {
+		s = this_cpu_xchg(scs_cache[i], NULL);
+		if (s) {
+			s = kasan_unpoison_vmalloc(s, SCS_SIZE,
+						   KASAN_VMALLOC_PROT_NORMAL);
+			memset(s, 0, SCS_SIZE);
+			goto out;
+		}
+	}
+
+	s = __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
+				    GFP_SCS, PAGE_KERNEL, 0, node,
+				    __builtin_return_address(0));
+
+out:
+	return kasan_reset_tag(s);
+}
+
+void *scs_alloc(int node)
 {
-	void *s = kmem_cache_alloc_node(scs_cache, GFP_SCS, node);
+	void *s;
 
+	s = __scs_alloc(node);
 	if (!s)
 		return NULL;
 
@@ -34,27 +65,60 @@ static void *scs_alloc(int node)
 	 * Poison the allocation to catch unintentional accesses to
 	 * the shadow stack when KASAN is enabled.
 	 */
-	kasan_poison_object_data(scs_cache, s);
+	kasan_poison_vmalloc(s, SCS_SIZE);
 	__scs_account(s, 1);
 	return s;
 }
 
-static void scs_free(void *s)
+void scs_free(void *s)
 {
+	int i;
+
 	__scs_account(s, -1);
-	kasan_unpoison_object_data(scs_cache, s);
-	kmem_cache_free(scs_cache, s);
+
+	/*
+	 * We cannot sleep as this can be called in interrupt context,
+	 * so use this_cpu_cmpxchg to update the cache, and vfree_atomic
+	 * to free the stack.
+	 */
+
+	for (i = 0; i < NR_CACHED_SCS; i++)
+		if (this_cpu_cmpxchg(scs_cache[i], 0, s) == NULL)
+			return;
+
+	kasan_unpoison_vmalloc(s, SCS_SIZE, KASAN_VMALLOC_PROT_NORMAL);
+	vfree_atomic(s);
+}
+
+static int scs_cleanup(unsigned int cpu)
+{
+	int i;
+	void **cache = per_cpu_ptr(scs_cache, cpu);
+
+	for (i = 0; i < NR_CACHED_SCS; i++) {
+		vfree(cache[i]);
+		cache[i] = NULL;
+	}
+
+	return 0;
 }
 
 void __init scs_init(void)
 {
-	scs_cache = kmem_cache_create("scs_cache", SCS_SIZE, 0, 0, NULL);
+	if (!scs_is_enabled())
+		return;
+	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL,
+			  scs_cleanup);
 }
 
 int scs_prepare(struct task_struct *tsk, int node)
 {
-	void *s = scs_alloc(node);
+	void *s;
+
+	if (!scs_is_enabled())
+		return 0;
 
+	s = scs_alloc(node);
 	if (!s)
 		return -ENOMEM;
 
@@ -94,7 +158,7 @@ void scs_release(struct task_struct *tsk)
 {
 	void *s = task_scs(tsk);
 
-	if (!s)
+	if (!scs_is_enabled() || !s)
 		return;
 
 	WARN(task_scs_end_corrupted(tsk),