kfence: alloc kfence_pool after system startup

mainline inclusion
from mainline-v5.18-rc1
commit b33f778b
category: feature
bugzilla: 187071, https://gitee.com/openeuler/kernel/issues/I5DLA7
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b33f778bba5ef3f76fe6708c611346c1ea03acd4

--------------------------------

Allow enabling KFENCE after system startup by allocating its pool via the
page allocator. This provides the flexibility to enable KFENCE even if it
wasn't enabled at boot time.

Link: https://lkml.kernel.org/r/20220307074516.6920-3-dtcccc@linux.alibaba.comSigned-off-by: NTianchen Ding <dtcccc@linux.alibaba.com>
Reviewed-by: NMarco Elver <elver@google.com>
Tested-by: NPeng Liu <liupeng256@huawei.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
Conflicts:
	mm/kfence/core.c
Signed-off-by: NLiu Shixin <liushixin2@huawei.com>
Reviewed-by: NKefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

mm/kfence/core.c

@@ -109,7 +109,7 @@ static unsigned long kfence_skip_covered_thresh __read_mostly = 75;
 module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644);
 
 /* The pool of pages used for guard pages and objects. */
-char *__kfence_pool __ro_after_init;
+char *__kfence_pool __read_mostly;
 EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */
 
 #ifdef CONFIG_KFENCE_DYNAMIC_OBJECTS
@@ -633,17 +633,19 @@ static void rcu_guarded_free(struct rcu_head *h)
 	kfence_guarded_free((void *)meta->addr, meta, false);
 }
 
-static bool __init kfence_init_pool(void)
+/*
+ * Initialization of the KFENCE pool after its allocation.
+ * Returns 0 on success; otherwise returns the address up to
+ * which partial initialization succeeded.
+ */
+static unsigned long kfence_init_pool(void)
 {
 	unsigned long addr = (unsigned long)__kfence_pool;
 	struct page *pages;
 	int i;
 
-	if (!__kfence_pool)
-		return false;
-
 	if (!arch_kfence_init_pool())
-		goto err;
+		return addr;
 
 	pages = virt_to_page(addr);
 
@@ -661,7 +663,7 @@ static bool __init kfence_init_pool(void)
 
 		/* Verify we do not have a compound head page. */
 		if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
-			goto err;
+			return addr;
 
 		__SetPageSlab(&pages[i]);
 	}
@@ -674,7 +676,7 @@ static bool __init kfence_init_pool(void)
 	 */
 	for (i = 0; i < 2; i++) {
 		if (unlikely(!kfence_protect(addr)))
-			goto err;
+			return addr;
 
 		addr += PAGE_SIZE;
 	}
@@ -691,7 +693,7 @@ static bool __init kfence_init_pool(void)
 
 		/* Protect the right redzone. */
 		if (unlikely(!kfence_protect(addr + PAGE_SIZE)))
-			goto err;
+			return addr;
 
 		addr += 2 * PAGE_SIZE;
 	}
@@ -704,9 +706,21 @@ static bool __init kfence_init_pool(void)
 	 */
 	kmemleak_free(__kfence_pool);
 
-	return true;
+	return 0;
+}
+
+static bool __init kfence_init_pool_early(void)
+{
+	unsigned long addr;
+
+	if (!__kfence_pool)
+		return false;
+
+	addr = kfence_init_pool();
+
+	if (!addr)
+		return true;
 
-err:
 	/*
 	 * Only release unprotected pages, and do not try to go back and change
 	 * page attributes due to risk of failing to do so as well. If changing
@@ -719,6 +733,26 @@ static bool __init kfence_init_pool(void)
 	return false;
 }
 
+static bool kfence_init_pool_late(void)
+{
+	unsigned long addr, free_size;
+
+	addr = kfence_init_pool();
+
+	if (!addr)
+		return true;
+
+	/* Same as above. */
+	free_size = KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool);
+#ifdef CONFIG_CONTIG_ALLOC
+	free_contig_range(page_to_pfn(virt_to_page(addr)), free_size / PAGE_SIZE);
+#else
+	free_pages_exact((void *)addr, free_size);
+#endif
+	__kfence_pool = NULL;
+	return false;
+}
+
 /* === DebugFS Interface ==================================================== */
 
 static int stats_show(struct seq_file *seq, void *v)
@@ -927,31 +961,66 @@ void __init kfence_alloc_pool(void)
 	}
 }
 
+static void kfence_init_enable(void)
+{
+	if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS))
+		static_branch_enable(&kfence_allocation_key);
+	WRITE_ONCE(kfence_enabled, true);
+	queue_delayed_work(system_unbound_wq, &kfence_timer, 0);
+	pr_info("initialized - using %lu bytes for %lu objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE,
+		(unsigned long)KFENCE_NR_OBJECTS, (void *)__kfence_pool,
+		(void *)(__kfence_pool + KFENCE_POOL_SIZE));
+}
+
 void __init kfence_init(void)
 {
+	stack_hash_seed = (u32)random_get_entropy();
+
 	/* Setting kfence_sample_interval to 0 on boot disables KFENCE. */
 	if (!kfence_sample_interval)
 		return;
 
-	stack_hash_seed = (u32)random_get_entropy();
-	if (!kfence_init_pool()) {
+	if (!kfence_init_pool_early()) {
 		pr_err("%s failed\n", __func__);
 		return;
 	}
 
-	if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS))
-		static_branch_enable(&kfence_allocation_key);
-	WRITE_ONCE(kfence_enabled, true);
-	queue_delayed_work(system_unbound_wq, &kfence_timer, 0);
-	pr_info("initialized - using %lu bytes for %lu objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE,
-		(unsigned long)KFENCE_NR_OBJECTS, (void *)__kfence_pool,
-		(void *)(__kfence_pool + KFENCE_POOL_SIZE));
+	kfence_init_enable();
+}
+
+static int kfence_init_late(void)
+{
+	const unsigned long nr_pages = KFENCE_POOL_SIZE / PAGE_SIZE;
+#ifdef CONFIG_CONTIG_ALLOC
+	struct page *pages;
+
+	pages = alloc_contig_pages(nr_pages, GFP_KERNEL, first_online_node, NULL);
+	if (!pages)
+		return -ENOMEM;
+	__kfence_pool = page_to_virt(pages);
+#else
+	if (nr_pages > MAX_ORDER_NR_PAGES) {
+		pr_warn("KFENCE_NUM_OBJECTS too large for buddy allocator\n");
+		return -EINVAL;
+	}
+	__kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE, GFP_KERNEL);
+	if (!__kfence_pool)
+		return -ENOMEM;
+#endif
+
+	if (!kfence_init_pool_late()) {
+		pr_err("%s failed\n", __func__);
+		return -EBUSY;
+	}
+
+	kfence_init_enable();
+	return 0;
 }
 
 static int kfence_enable_late(void)
 {
 	if (!__kfence_pool)
-		return -EINVAL;
+		return kfence_init_late();
 
 	WRITE_ONCE(kfence_enabled, true);
 	queue_delayed_work(system_unbound_wq, &kfence_timer, 0);