mm, kfence: insert KFENCE hooks for SLAB

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.

Link: https://lkml.kernel.org/r/20201103175841.3495947-5-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Alexander Potapenko <glider@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Co-developed-by: Marco Elver <elver@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 <andreyknvl@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hillf Danton <hdanton@sina.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joern Engel <joern@purestorage.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 38 insertions, 10 deletions

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/kfence/core.c b/mm/kfence/core.c
index 61c76670a7a9..05c18aa11851 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -317,6 +317,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g
 	/* Set required struct page fields. */
 	page = virt_to_page(meta->addr);
 	page->slab_cache = cache;
+	if (IS_ENABLED(CONFIG_SLAB))
+		page->s_mem = addr;
 
 	raw_spin_unlock_irqrestore(&meta->lock, flags);
 
diff --git a/mm/slab.c b/mm/slab.c
index 35c68d99d460..51fd424e0d6d 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 @@ must_grow:
 }
 
 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 +3427,12 @@ free_done:
 static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
 					 unsigned long caller)
 {
+	if (is_kfence_address(objp)) {
+		kmemleak_free_recursive(objp, cachep->flags);
+		__kfence_free(objp);
+		return;
+	}
+
 	if (unlikely(slab_want_init_on_free(cachep)))
 		memset(objp, 0, cachep->object_size);
 
@@ -3482,7 +3499,7 @@ 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);
@@ -3515,7 +3532,7 @@ 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;
@@ -3548,7 +3565,7 @@ 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,
@@ -3574,7 +3591,7 @@ 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,
@@ -3592,7 +3609,7 @@ 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,
@@ -3673,7 +3690,7 @@ 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,
@@ -4172,7 +4189,10 @@ 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 7c8298c17145..284954ef1da5 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>
@@ -430,6 +431,7 @@ 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
@@ -455,6 +457,7 @@ 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);
@@ -1235,7 +1238,7 @@ size_t ksize(const void *objp)
 	if (unlikely(ZERO_OR_NULL_PTR(objp)) || !kasan_check_byte(objp))
 		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.