UPSTREAM: mm: kasan: initial memory quarantine implementation

Quarantine isolates freed objects in a separate queue.  The objects are
returned to the allocator later, which helps to detect use-after-free
errors.

When the object is freed, its state changes from KASAN_STATE_ALLOC to
KASAN_STATE_QUARANTINE.  The object is poisoned and put into quarantine
instead of being returned to the allocator, therefore every subsequent
access to that object triggers a KASAN error, and the error handler is
able to say where the object has been allocated and deallocated.

When it's time for the object to leave quarantine, its state becomes
KASAN_STATE_FREE and it's returned to the allocator.  From now on the
allocator may reuse it for another allocation.  Before that happens,
it's still possible to detect a use-after free on that object (it
retains the allocation/deallocation stacks).

When the allocator reuses this object, the shadow is unpoisoned and old
allocation/deallocation stacks are wiped.  Therefore a use of this
object, even an incorrect one, won't trigger ASan warning.

Without the quarantine, it's not guaranteed that the objects aren't
reused immediately, that's why the probability of catching a
use-after-free is lower than with quarantine in place.

Quarantine isolates freed objects in a separate queue.  The objects are
returned to the allocator later, which helps to detect use-after-free
errors.

Freed objects are first added to per-cpu quarantine queues.  When a
cache is destroyed or memory shrinking is requested, the objects are
moved into the global quarantine queue.  Whenever a kmalloc call allows
memory reclaiming, the oldest objects are popped out of the global queue
until the total size of objects in quarantine is less than 3/4 of the
maximum quarantine size (which is a fraction of installed physical
memory).

As long as an object remains in the quarantine, KASAN is able to report
accesses to it, so the chance of reporting a use-after-free is
increased.  Once the object leaves quarantine, the allocator may reuse
it, in which case the object is unpoisoned and KASAN can't detect
incorrect accesses to it.

Right now quarantine support is only enabled in SLAB allocator.
Unification of KASAN features in SLAB and SLUB will be done later.

This patch is based on the "mm: kasan: quarantine" patch originally
prepared by Dmitry Chernenkov.  A number of improvements have been
suggested by Andrey Ryabinin.

[glider@google.com: v9]
  Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com
Signed-off-by: Alexander Potapenko <glider@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Bug: 64145065
(cherry-picked from 55834c59098d0c5a97b0f3247e55832b67facdcf)
Change-Id: Ib808d72a40f2e5137961d93dad540e85f8bbd2c4
Signed-off-by: Paul Lawrence <paullawrence@google.com>

5 files changed, 361 insertions, 10 deletions

diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 64710148941e..31e73d289e7b 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -6,3 +6,4 @@ CFLAGS_REMOVE_kasan.o = -pg
 CFLAGS_kasan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 obj-y := kasan.o report.o kasan_init.o
+obj-$(CONFIG_SLAB) += quarantine.o
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 38f1dd79acdb..8df666bb23be 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -388,6 +388,16 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size,
 }
 #endif
 
+void kasan_cache_shrink(struct kmem_cache *cache)
+{
+	quarantine_remove_cache(cache);
+}
+
+void kasan_cache_destroy(struct kmem_cache *cache)
+{
+	quarantine_remove_cache(cache);
+}
+
 void kasan_poison_slab(struct page *page)
 {
 	kasan_poison_shadow(page_address(page),
@@ -482,7 +492,7 @@ void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
 	kasan_kmalloc(cache, object, cache->object_size, flags);
 }
 
-void kasan_slab_free(struct kmem_cache *cache, void *object)
+void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
 {
 	unsigned long size = cache->object_size;
 	unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
@@ -491,18 +501,43 @@ void kasan_slab_free(struct kmem_cache *cache, void *object)
 	if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
 		return;
 
+	kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
+}
+
+bool kasan_slab_free(struct kmem_cache *cache, void *object)
+{
 #ifdef CONFIG_SLAB
-	if (cache->flags & SLAB_KASAN) {
-		struct kasan_free_meta *free_info =
-			get_free_info(cache, object);
+	/* RCU slabs could be legally used after free within the RCU period */
+	if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
+		return false;
+
+	if (likely(cache->flags & SLAB_KASAN)) {
 		struct kasan_alloc_meta *alloc_info =
 			get_alloc_info(cache, object);
-		alloc_info->state = KASAN_STATE_FREE;
-		set_track(&free_info->track, GFP_NOWAIT);
+		struct kasan_free_meta *free_info =
+			get_free_info(cache, object);
+
+		switch (alloc_info->state) {
+		case KASAN_STATE_ALLOC:
+			alloc_info->state = KASAN_STATE_QUARANTINE;
+			quarantine_put(free_info, cache);
+			set_track(&free_info->track, GFP_NOWAIT);
+			kasan_poison_slab_free(cache, object);
+			return true;
+		case KASAN_STATE_QUARANTINE:
+		case KASAN_STATE_FREE:
+			pr_err("Double free");
+			dump_stack();
+			break;
+		default:
+			break;
+		}
 	}
+	return false;
+#else
+	kasan_poison_slab_free(cache, object);
+	return false;
 #endif
-
-	kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
 }
 
 void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
@@ -511,6 +546,9 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
+	if (flags & __GFP_RECLAIM)
+		quarantine_reduce();
+
 	if (unlikely(object == NULL))
 		return;
 
@@ -541,6 +579,9 @@ void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
+	if (flags & __GFP_RECLAIM)
+		quarantine_reduce();
+
 	if (unlikely(ptr == NULL))
 		return;
 
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index dd272eaada15..7642ca0d74f7 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -65,6 +65,7 @@ struct kasan_global {
 enum kasan_state {
 	KASAN_STATE_INIT,
 	KASAN_STATE_ALLOC,
+	KASAN_STATE_QUARANTINE,
 	KASAN_STATE_FREE
 };
 
@@ -82,9 +83,14 @@ struct kasan_alloc_meta {
 	u32 reserved;
 };
 
+struct qlist_node {
+	struct qlist_node *next;
+};
 struct kasan_free_meta {
-	/* Allocator freelist pointer, unused by KASAN. */
-	void **freelist;
+	/* This field is used while the object is in the quarantine.
+	 * Otherwise it might be used for the allocator freelist.
+	 */
+	struct qlist_node quarantine_link;
 	struct kasan_track track;
 };
 
@@ -108,4 +114,15 @@ static inline bool kasan_report_enabled(void)
 void kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
 
+#ifdef CONFIG_SLAB
+void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
+void quarantine_reduce(void);
+void quarantine_remove_cache(struct kmem_cache *cache);
+#else
+static inline void quarantine_put(struct kasan_free_meta *info,
+				struct kmem_cache *cache) { }
+static inline void quarantine_reduce(void) { }
+static inline void quarantine_remove_cache(struct kmem_cache *cache) { }
+#endif
+
 #endif
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
new file mode 100644
index 000000000000..4973505a9bdd
--- /dev/null
+++ b/mm/kasan/quarantine.c
@@ -0,0 +1,291 @@
+/*
+ * KASAN quarantine.
+ *
+ * Author: Alexander Potapenko <glider@google.com>
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * Based on code by Dmitry Chernenkov.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#include <linux/gfp.h>
+#include <linux/hash.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/shrinker.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "../slab.h"
+#include "kasan.h"
+
+/* Data structure and operations for quarantine queues. */
+
+/*
+ * Each queue is a signle-linked list, which also stores the total size of
+ * objects inside of it.
+ */
+struct qlist_head {
+	struct qlist_node *head;
+	struct qlist_node *tail;
+	size_t bytes;
+};
+
+#define QLIST_INIT { NULL, NULL, 0 }
+
+static bool qlist_empty(struct qlist_head *q)
+{
+	return !q->head;
+}
+
+static void qlist_init(struct qlist_head *q)
+{
+	q->head = q->tail = NULL;
+	q->bytes = 0;
+}
+
+static void qlist_put(struct qlist_head *q, struct qlist_node *qlink,
+		size_t size)
+{
+	if (unlikely(qlist_empty(q)))
+		q->head = qlink;
+	else
+		q->tail->next = qlink;
+	q->tail = qlink;
+	qlink->next = NULL;
+	q->bytes += size;
+}
+
+static void qlist_move_all(struct qlist_head *from, struct qlist_head *to)
+{
+	if (unlikely(qlist_empty(from)))
+		return;
+
+	if (qlist_empty(to)) {
+		*to = *from;
+		qlist_init(from);
+		return;
+	}
+
+	to->tail->next = from->head;
+	to->tail = from->tail;
+	to->bytes += from->bytes;
+
+	qlist_init(from);
+}
+
+static void qlist_move(struct qlist_head *from, struct qlist_node *last,
+		struct qlist_head *to, size_t size)
+{
+	if (unlikely(last == from->tail)) {
+		qlist_move_all(from, to);
+		return;
+	}
+	if (qlist_empty(to))
+		to->head = from->head;
+	else
+		to->tail->next = from->head;
+	to->tail = last;
+	from->head = last->next;
+	last->next = NULL;
+	from->bytes -= size;
+	to->bytes += size;
+}
+
+
+/*
+ * The object quarantine consists of per-cpu queues and a global queue,
+ * guarded by quarantine_lock.
+ */
+static DEFINE_PER_CPU(struct qlist_head, cpu_quarantine);
+
+static struct qlist_head global_quarantine;
+static DEFINE_SPINLOCK(quarantine_lock);
+
+/* Maximum size of the global queue. */
+static unsigned long quarantine_size;
+
+/*
+ * The fraction of physical memory the quarantine is allowed to occupy.
+ * Quarantine doesn't support memory shrinker with SLAB allocator, so we keep
+ * the ratio low to avoid OOM.
+ */
+#define QUARANTINE_FRACTION 32
+
+#define QUARANTINE_LOW_SIZE (READ_ONCE(quarantine_size) * 3 / 4)
+#define QUARANTINE_PERCPU_SIZE (1 << 20)
+
+static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink)
+{
+	return virt_to_head_page(qlink)->slab_cache;
+}
+
+static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
+{
+	struct kasan_free_meta *free_info =
+		container_of(qlink, struct kasan_free_meta,
+			     quarantine_link);
+
+	return ((void *)free_info) - cache->kasan_info.free_meta_offset;
+}
+
+static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
+{
+	void *object = qlink_to_object(qlink, cache);
+	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
+	unsigned long flags;
+
+	local_irq_save(flags);
+	alloc_info->state = KASAN_STATE_FREE;
+	___cache_free(cache, object, _THIS_IP_);
+	local_irq_restore(flags);
+}
+
+static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
+{
+	struct qlist_node *qlink;
+
+	if (unlikely(qlist_empty(q)))
+		return;
+
+	qlink = q->head;
+	while (qlink) {
+		struct kmem_cache *obj_cache =
+			cache ? cache :	qlink_to_cache(qlink);
+		struct qlist_node *next = qlink->next;
+
+		qlink_free(qlink, obj_cache);
+		qlink = next;
+	}
+	qlist_init(q);
+}
+
+void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
+{
+	unsigned long flags;
+	struct qlist_head *q;
+	struct qlist_head temp = QLIST_INIT;
+
+	local_irq_save(flags);
+
+	q = this_cpu_ptr(&cpu_quarantine);
+	qlist_put(q, &info->quarantine_link, cache->size);
+	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+		qlist_move_all(q, &temp);
+
+	local_irq_restore(flags);
+
+	if (unlikely(!qlist_empty(&temp))) {
+		spin_lock_irqsave(&quarantine_lock, flags);
+		qlist_move_all(&temp, &global_quarantine);
+		spin_unlock_irqrestore(&quarantine_lock, flags);
+	}
+}
+
+void quarantine_reduce(void)
+{
+	size_t new_quarantine_size;
+	unsigned long flags;
+	struct qlist_head to_free = QLIST_INIT;
+	size_t size_to_free = 0;
+	struct qlist_node *last;
+
+	if (likely(READ_ONCE(global_quarantine.bytes) <=
+		   READ_ONCE(quarantine_size)))
+		return;
+
+	spin_lock_irqsave(&quarantine_lock, flags);
+
+	/*
+	 * Update quarantine size in case of hotplug. Allocate a fraction of
+	 * the installed memory to quarantine minus per-cpu queue limits.
+	 */
+	new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
+		QUARANTINE_FRACTION;
+	new_quarantine_size -= QUARANTINE_PERCPU_SIZE * num_online_cpus();
+	WRITE_ONCE(quarantine_size, new_quarantine_size);
+
+	last = global_quarantine.head;
+	while (last) {
+		struct kmem_cache *cache = qlink_to_cache(last);
+
+		size_to_free += cache->size;
+		if (!last->next || size_to_free >
+		    global_quarantine.bytes - QUARANTINE_LOW_SIZE)
+			break;
+		last = last->next;
+	}
+	qlist_move(&global_quarantine, last, &to_free, size_to_free);
+
+	spin_unlock_irqrestore(&quarantine_lock, flags);
+
+	qlist_free_all(&to_free, NULL);
+}
+
+static void qlist_move_cache(struct qlist_head *from,
+				   struct qlist_head *to,
+				   struct kmem_cache *cache)
+{
+	struct qlist_node *prev = NULL, *curr;
+
+	if (unlikely(qlist_empty(from)))
+		return;
+
+	curr = from->head;
+	while (curr) {
+		struct qlist_node *qlink = curr;
+		struct kmem_cache *obj_cache = qlink_to_cache(qlink);
+
+		if (obj_cache == cache) {
+			if (unlikely(from->head == qlink)) {
+				from->head = curr->next;
+				prev = curr;
+			} else
+				prev->next = curr->next;
+			if (unlikely(from->tail == qlink))
+				from->tail = curr->next;
+			from->bytes -= cache->size;
+			qlist_put(to, qlink, cache->size);
+		} else {
+			prev = curr;
+		}
+		curr = curr->next;
+	}
+}
+
+static void per_cpu_remove_cache(void *arg)
+{
+	struct kmem_cache *cache = arg;
+	struct qlist_head to_free = QLIST_INIT;
+	struct qlist_head *q;
+
+	q = this_cpu_ptr(&cpu_quarantine);
+	qlist_move_cache(q, &to_free, cache);
+	qlist_free_all(&to_free, cache);
+}
+
+void quarantine_remove_cache(struct kmem_cache *cache)
+{
+	unsigned long flags;
+	struct qlist_head to_free = QLIST_INIT;
+
+	on_each_cpu(per_cpu_remove_cache, cache, 1);
+
+	spin_lock_irqsave(&quarantine_lock, flags);
+	qlist_move_cache(&global_quarantine, &to_free, cache);
+	spin_unlock_irqrestore(&quarantine_lock, flags);
+
+	qlist_free_all(&to_free, cache);
+}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 4b11c70f4792..a41fb3796262 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -152,6 +152,7 @@ static void object_err(struct kmem_cache *cache, struct page *page,
 		print_track(&alloc_info->track);
 		break;
 	case KASAN_STATE_FREE:
+	case KASAN_STATE_QUARANTINE:
 		pr_err("Object freed, allocated with size %u bytes\n",
 		       alloc_info->alloc_size);
 		free_info = get_free_info(cache, object);