[v6,4/9] mm, kfence: insert KFENCE hooks for SLAB

Commit Message

Marco Elver Oct. 29, 2020, 1:16 p.m. UTC

From: Alexander Potapenko <[e-mail]>

Inserts KFENCE hooks into the SLAB allocator.

To pass the originally requested size to KFENCE, add an argument
'orig_size' to slab_alloc*(). The additional argument is required to
preserve the requested original size for kmalloc() allocations, which
uses size classes (e.g. an allocation of 272 bytes will return an object
of size 512). Therefore, kmem_cache::size does not represent the
kmalloc-caller's requested size, and we must introduce the argument
'orig_size' to propagate the originally requested size to KFENCE.

Without the originally requested size, we would not be able to detect
out-of-bounds accesses for objects placed at the end of a KFENCE object
page if that object is not equal to the kmalloc-size class it was
bucketed into.

When KFENCE is disabled, there is no additional overhead, since
slab_alloc*() functions are __always_inline.

Reviewed-by: Dmitry Vyukov <[e-mail]>
Co-developed-by: Marco Elver <[e-mail]>
Signed-off-by: Marco Elver <[e-mail]>
Signed-off-by: Alexander Potapenko <[e-mail]>
---
v5:
* New kfence_shutdown_cache(): we need to defer kfence_shutdown_cache()
  to before the cache is actually freed. In case of SLAB_TYPESAFE_BY_RCU,
  the objects may still legally be used until the next RCU grace period.
* Fix objs_per_slab_page for kfence objects.
* Revert and use fixed obj_to_index() in __check_heap_object().

v3:
* Rewrite patch description to clarify need for 'orig_size'
  [reported by Christopher Lameter].
---
 include/linux/slab_def.h |  3 +++
 mm/slab.c                | 37 ++++++++++++++++++++++++++++---------
 mm/slab_common.c         |  5 ++++-
 3 files changed, 35 insertions(+), 10 deletions(-)

Comments

Jann Horn Oct. 30, 2020, 2:49 a.m. UTC | #1

On Thu, Oct 29, 2020 at 2:17 PM Marco Elver <[e-mail]> wrote:
> Inserts KFENCE hooks into the SLAB allocator.
[...]
> diff --git a/mm/slab.c b/mm/slab.c
[...]
> @@ -3416,6 +3427,11 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
>  static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
>                                          unsigned long caller)
>  {
> +       if (kfence_free(objp)) {
> +               kmemleak_free_recursive(objp, cachep->flags);
> +               return;
> +       }

This looks dodgy. Normally kmemleak is told that an object is being
freed *before* the object is actually released. I think that if this
races really badly, we'll make kmemleak stumble over this bit in
create_object():

kmemleak_stop("Cannot insert 0x%lx into the object search tree
(overlaps existing)\n",
      ptr);


> +
>         /* Put the object into the quarantine, don't touch it for now. */
>         if (kasan_slab_free(cachep, objp, _RET_IP_))
>                 return;

Marco Elver Oct. 30, 2020, 3:41 p.m. UTC | #2

On Fri, 30 Oct 2020 at 03:49, Jann Horn <[e-mail]> wrote:
> On Thu, Oct 29, 2020 at 2:17 PM Marco Elver <[e-mail]> wrote:
> > Inserts KFENCE hooks into the SLAB allocator.
> [...]
> > diff --git a/mm/slab.c b/mm/slab.c
> [...]
> > @@ -3416,6 +3427,11 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
> >  static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
> >                                          unsigned long caller)
> >  {
> > +       if (kfence_free(objp)) {
> > +               kmemleak_free_recursive(objp, cachep->flags);
> > +               return;
> > +       }
>
> This looks dodgy. Normally kmemleak is told that an object is being
> freed *before* the object is actually released. I think that if this
> races really badly, we'll make kmemleak stumble over this bit in
> create_object():
>
> kmemleak_stop("Cannot insert 0x%lx into the object search tree
> (overlaps existing)\n",
>       ptr);

Good catch. Although extremely unlikely, let's just avoid it by moving
the freeing after.

>
> > +
> >         /* Put the object into the quarantine, don't touch it for now. */
> >         if (kasan_slab_free(cachep, objp, _RET_IP_))
> >                 return;

Patch

diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 9eb430c163c2..3aa5e1e73ab6 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -2,6 +2,7 @@ 
 #ifndef _LINUX_SLAB_DEF_H
 #define	_LINUX_SLAB_DEF_H
 
+#include <linux/kfence.h>
 #include <linux/reciprocal_div.h>
 
 /*
@@ -114,6 +115,8 @@  static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 static inline int objs_per_slab_page(const struct kmem_cache *cache,
 				     const struct page *page)
 {
+	if (is_kfence_address(page_address(page)))
+		return 1;
 	return cache->num;
 }
 
diff --git a/mm/slab.c b/mm/slab.c
index b1113561b98b..ebff1c333558 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -100,6 +100,7 @@ 
 #include	<linux/seq_file.h>
 #include	<linux/notifier.h>
 #include	<linux/kallsyms.h>
+#include	<linux/kfence.h>
 #include	<linux/cpu.h>
 #include	<linux/sysctl.h>
 #include	<linux/module.h>
@@ -3208,7 +3209,7 @@  static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 }
 
 static __always_inline void *
-slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
+slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, size_t orig_size,
 		   unsigned long caller)
 {
 	unsigned long save_flags;
@@ -3221,6 +3222,10 @@  slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	if (unlikely(!cachep))
 		return NULL;
 
+	ptr = kfence_alloc(cachep, orig_size, flags);
+	if (unlikely(ptr))
+		goto out_hooks;
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 
@@ -3253,6 +3258,7 @@  slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr)
 		memset(ptr, 0, cachep->object_size);
 
+out_hooks:
 	slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr);
 	return ptr;
 }
@@ -3290,7 +3296,7 @@  __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 #endif /* CONFIG_NUMA */
 
 static __always_inline void *
-slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
+slab_alloc(struct kmem_cache *cachep, gfp_t flags, size_t orig_size, unsigned long caller)
 {
 	unsigned long save_flags;
 	void *objp;
@@ -3301,6 +3307,10 @@  slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 	if (unlikely(!cachep))
 		return NULL;
 
+	objp = kfence_alloc(cachep, orig_size, flags);
+	if (unlikely(objp))
+		goto out;
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 	objp = __do_cache_alloc(cachep, flags);
@@ -3311,6 +3321,7 @@  slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 	if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp)
 		memset(objp, 0, cachep->object_size);
 
+out:
 	slab_post_alloc_hook(cachep, objcg, flags, 1, &objp);
 	return objp;
 }
@@ -3416,6 +3427,11 @@  static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
 static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
 					 unsigned long caller)
 {
+	if (kfence_free(objp)) {
+		kmemleak_free_recursive(objp, cachep->flags);
+		return;
+	}
+
 	/* Put the object into the quarantine, don't touch it for now. */
 	if (kasan_slab_free(cachep, objp, _RET_IP_))
 		return;
@@ -3481,7 +3497,7 @@  void ___cache_free(struct kmem_cache *cachep, void *objp,
  */
 void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
-	void *ret = slab_alloc(cachep, flags, _RET_IP_);
+	void *ret = slab_alloc(cachep, flags, cachep->object_size, _RET_IP_);
 
 	trace_kmem_cache_alloc(_RET_IP_, ret,
 			       cachep->object_size, cachep->size, flags);
@@ -3514,7 +3530,7 @@  int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 
 	local_irq_disable();
 	for (i = 0; i < size; i++) {
-		void *objp = __do_cache_alloc(s, flags);
+		void *objp = kfence_alloc(s, s->object_size, flags) ?: __do_cache_alloc(s, flags);
 
 		if (unlikely(!objp))
 			goto error;
@@ -3547,7 +3563,7 @@  kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
 {
 	void *ret;
 
-	ret = slab_alloc(cachep, flags, _RET_IP_);
+	ret = slab_alloc(cachep, flags, size, _RET_IP_);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
 	trace_kmalloc(_RET_IP_, ret,
@@ -3573,7 +3589,7 @@  EXPORT_SYMBOL(kmem_cache_alloc_trace);
  */
 void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
-	void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
+	void *ret = slab_alloc_node(cachep, flags, nodeid, cachep->object_size, _RET_IP_);
 
 	trace_kmem_cache_alloc_node(_RET_IP_, ret,
 				    cachep->object_size, cachep->size,
@@ -3591,7 +3607,7 @@  void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
 {
 	void *ret;
 
-	ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
+	ret = slab_alloc_node(cachep, flags, nodeid, size, _RET_IP_);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
 	trace_kmalloc_node(_RET_IP_, ret,
@@ -3652,7 +3668,7 @@  static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	cachep = kmalloc_slab(size, flags);
 	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
 		return cachep;
-	ret = slab_alloc(cachep, flags, caller);
+	ret = slab_alloc(cachep, flags, size, caller);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
 	trace_kmalloc(caller, ret,
@@ -4151,7 +4167,10 @@  void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 	BUG_ON(objnr >= cachep->num);
 
 	/* Find offset within object. */
-	offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
+	if (is_kfence_address(ptr))
+		offset = ptr - kfence_object_start(ptr);
+	else
+		offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
 
 	/* Allow address range falling entirely within usercopy region. */
 	if (offset >= cachep->useroffset &&
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f9ccd5dc13f3..13125773dae2 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -12,6 +12,7 @@ 
 #include <linux/memory.h>
 #include <linux/cache.h>
 #include <linux/compiler.h>
+#include <linux/kfence.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/uaccess.h>
@@ -435,6 +436,7 @@  static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
 	rcu_barrier();
 
 	list_for_each_entry_safe(s, s2, &to_destroy, list) {
+		kfence_shutdown_cache(s);
 #ifdef SLAB_SUPPORTS_SYSFS
 		sysfs_slab_release(s);
 #else
@@ -460,6 +462,7 @@  static int shutdown_cache(struct kmem_cache *s)
 		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
 		schedule_work(&slab_caches_to_rcu_destroy_work);
 	} else {
+		kfence_shutdown_cache(s);
 #ifdef SLAB_SUPPORTS_SYSFS
 		sysfs_slab_unlink(s);
 		sysfs_slab_release(s);
@@ -1171,7 +1174,7 @@  size_t ksize(const void *objp)
 	if (unlikely(ZERO_OR_NULL_PTR(objp)) || !__kasan_check_read(objp, 1))
 		return 0;
 
-	size = __ksize(objp);
+	size = kfence_ksize(objp) ?: __ksize(objp);
 	/*
 	 * We assume that ksize callers could use whole allocated area,
 	 * so we need to unpoison this area.