From b84e04f1baeebe6872b22a027cfc558621e842d4 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Mon, 15 Aug 2022 05:53:53 +1000 Subject: kfence: add sysfs interface to disable kfence for selected slabs. By default kfence allocation can happen for any slab object, whose size is up to PAGE_SIZE, as long as that allocation is the first allocation after expiration of kfence sample interval. But in certain debugging scenarios we may be interested in debugging corruptions involving some specific slub objects like dentry or ext4_* etc. In such cases limiting kfence for allocations involving only specific slub objects will increase the probablity of catching the issue since kfence pool will not be consumed by other slab objects. This patch introduces a sysfs interface '/sys/kernel/slab//skip_kfence' to disable kfence for specific slabs. Having the interface work in this way does not impact current/default behavior of kfence and allows us to use kfence for specific slabs (when needed) as well. The decision to skip/use kfence is taken depending on whether kmem_cache.flags has (newly introduced) SLAB_SKIP_KFENCE flag set or not. Link: https://lkml.kernel.org/r/20220814195353.2540848-1-imran.f.khan@oracle.com Signed-off-by: Imran Khan Reviewed-by: Vlastimil Babka Reviewed-by: Marco Elver Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Roman Gushchin Signed-off-by: Andrew Morton --- mm/slub.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'mm/slub.c') diff --git a/mm/slub.c b/mm/slub.c index 862dbd9af4f5..6953c3367bc2 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5745,6 +5745,29 @@ STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node); STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain); #endif /* CONFIG_SLUB_STATS */ +#ifdef CONFIG_KFENCE +static ssize_t skip_kfence_show(struct kmem_cache *s, char *buf) +{ + return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_SKIP_KFENCE)); +} + +static ssize_t skip_kfence_store(struct kmem_cache *s, + const char *buf, size_t length) +{ + int ret = length; + + if (buf[0] == '0') + s->flags &= ~SLAB_SKIP_KFENCE; + else if (buf[0] == '1') + s->flags |= SLAB_SKIP_KFENCE; + else + ret = -EINVAL; + + return ret; +} +SLAB_ATTR(skip_kfence); +#endif + static struct attribute *slab_attrs[] = { &slab_size_attr.attr, &object_size_attr.attr, @@ -5812,6 +5835,9 @@ static struct attribute *slab_attrs[] = { &failslab_attr.attr, #endif &usersize_attr.attr, +#ifdef CONFIG_KFENCE + &skip_kfence_attr.attr, +#endif NULL }; -- cgit v1.2.3 From 68ef169a1dd20df5cfa5a161b7304ad9fdd14c36 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 15 Sep 2022 17:03:49 +0200 Subject: mm: kmsan: call KMSAN hooks from SLUB code In order to report uninitialized memory coming from heap allocations KMSAN has to poison them unless they're created with __GFP_ZERO. It's handy that we need KMSAN hooks in the places where init_on_alloc/init_on_free initialization is performed. In addition, we apply __no_kmsan_checks to get_freepointer_safe() to suppress reports when accessing freelist pointers that reside in freed objects. Link: https://lkml.kernel.org/r/20220915150417.722975-16-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Stephen Rothwell Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 57 ++++++++++++++++++++++++++++++++++++++ mm/kmsan/hooks.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++ mm/slab.h | 1 + mm/slub.c | 17 ++++++++++++ 4 files changed, 151 insertions(+) (limited to 'mm/slub.c') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index b36bf3db835e..5c4e0079054e 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -14,6 +14,7 @@ #include struct page; +struct kmem_cache; #ifdef CONFIG_KMSAN @@ -48,6 +49,44 @@ void kmsan_free_page(struct page *page, unsigned int order); */ void kmsan_copy_page_meta(struct page *dst, struct page *src); +/** + * kmsan_slab_alloc() - Notify KMSAN about a slab allocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * @flags: GFP flags passed to the allocator. + * + * Depending on cache flags and GFP flags, KMSAN sets up the metadata of the + * newly created object, marking it as initialized or uninitialized. + */ +void kmsan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); + +/** + * kmsan_slab_free() - Notify KMSAN about a slab deallocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * + * KMSAN marks the freed object as uninitialized. + */ +void kmsan_slab_free(struct kmem_cache *s, void *object); + +/** + * kmsan_kmalloc_large() - Notify KMSAN about a large slab allocation. + * @ptr: object pointer. + * @size: object size. + * @flags: GFP flags passed to the allocator. + * + * Similar to kmsan_slab_alloc(), but for large allocations. + */ +void kmsan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); + +/** + * kmsan_kfree_large() - Notify KMSAN about a large slab deallocation. + * @ptr: object pointer. + * + * Similar to kmsan_slab_free(), but for large allocations. + */ +void kmsan_kfree_large(const void *ptr); + /** * kmsan_map_kernel_range_noflush() - Notify KMSAN about a vmap. * @start: start of vmapped range. @@ -114,6 +153,24 @@ static inline void kmsan_copy_page_meta(struct page *dst, struct page *src) { } +static inline void kmsan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags) +{ +} + +static inline void kmsan_slab_free(struct kmem_cache *s, void *object) +{ +} + +static inline void kmsan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags) +{ +} + +static inline void kmsan_kfree_large(const void *ptr) +{ +} + static inline void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, pgprot_t prot, diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 040111bb9f6a..000703c563a4 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -27,6 +27,82 @@ * skipping effects of functions like memset() inside instrumented code. */ +void kmsan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) +{ + if (unlikely(object == NULL)) + return; + if (!kmsan_enabled || kmsan_in_runtime()) + return; + /* + * There's a ctor or this is an RCU cache - do nothing. The memory + * status hasn't changed since last use. + */ + if (s->ctor || (s->flags & SLAB_TYPESAFE_BY_RCU)) + return; + + kmsan_enter_runtime(); + if (flags & __GFP_ZERO) + kmsan_internal_unpoison_memory(object, s->object_size, + KMSAN_POISON_CHECK); + else + kmsan_internal_poison_memory(object, s->object_size, flags, + KMSAN_POISON_CHECK); + kmsan_leave_runtime(); +} + +void kmsan_slab_free(struct kmem_cache *s, void *object) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + /* RCU slabs could be legally used after free within the RCU period */ + if (unlikely(s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))) + return; + /* + * If there's a constructor, freed memory must remain in the same state + * until the next allocation. We cannot save its state to detect + * use-after-free bugs, instead we just keep it unpoisoned. + */ + if (s->ctor) + return; + kmsan_enter_runtime(); + kmsan_internal_poison_memory(object, s->object_size, GFP_KERNEL, + KMSAN_POISON_CHECK | KMSAN_POISON_FREE); + kmsan_leave_runtime(); +} + +void kmsan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) +{ + if (unlikely(ptr == NULL)) + return; + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + if (flags & __GFP_ZERO) + kmsan_internal_unpoison_memory((void *)ptr, size, + /*checked*/ true); + else + kmsan_internal_poison_memory((void *)ptr, size, flags, + KMSAN_POISON_CHECK); + kmsan_leave_runtime(); +} + +void kmsan_kfree_large(const void *ptr) +{ + struct page *page; + + if (!kmsan_enabled || kmsan_in_runtime()) + return; + kmsan_enter_runtime(); + page = virt_to_head_page((void *)ptr); + KMSAN_WARN_ON(ptr != page_address(page)); + kmsan_internal_poison_memory((void *)ptr, + PAGE_SIZE << compound_order(page), + GFP_KERNEL, + KMSAN_POISON_CHECK | KMSAN_POISON_FREE); + kmsan_leave_runtime(); +} + static unsigned long vmalloc_shadow(unsigned long addr) { return (unsigned long)kmsan_get_metadata((void *)addr, diff --git a/mm/slab.h b/mm/slab.h index 4ec82bec15ec..9d0afd2985df 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -729,6 +729,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, memset(p[i], 0, s->object_size); kmemleak_alloc_recursive(p[i], s->object_size, 1, s->flags, flags); + kmsan_slab_alloc(s, p[i], flags); } memcg_slab_post_alloc_hook(s, objcg, flags, size, p); diff --git a/mm/slub.c b/mm/slub.c index 6953c3367bc2..ce8310e131b3 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -359,6 +360,17 @@ static void prefetch_freepointer(const struct kmem_cache *s, void *object) prefetchw(object + s->offset); } +/* + * When running under KMSAN, get_freepointer_safe() may return an uninitialized + * pointer value in the case the current thread loses the race for the next + * memory chunk in the freelist. In that case this_cpu_cmpxchg_double() in + * slab_alloc_node() will fail, so the uninitialized value won't be used, but + * KMSAN will still check all arguments of cmpxchg because of imperfect + * handling of inline assembly. + * To work around this problem, we apply __no_kmsan_checks to ensure that + * get_freepointer_safe() returns initialized memory. + */ +__no_kmsan_checks static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) { unsigned long freepointer_addr; @@ -1709,6 +1721,7 @@ static inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) ptr = kasan_kmalloc_large(ptr, size, flags); /* As ptr might get tagged, call kmemleak hook after KASAN. */ kmemleak_alloc(ptr, size, 1, flags); + kmsan_kmalloc_large(ptr, size, flags); return ptr; } @@ -1716,12 +1729,14 @@ static __always_inline void kfree_hook(void *x) { kmemleak_free(x); kasan_kfree_large(x); + kmsan_kfree_large(x); } static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x, bool init) { kmemleak_free_recursive(x, s->flags); + kmsan_slab_free(s, x); debug_check_no_locks_freed(x, s->object_size); @@ -5941,6 +5956,7 @@ static char *create_unique_id(struct kmem_cache *s) p += sprintf(p, "%07u", s->size); BUG_ON(p > name + ID_STR_LENGTH - 1); + kmsan_unpoison_memory(name, p - name); return name; } @@ -6042,6 +6058,7 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name) al->name = name; al->next = alias_list; alias_list = al; + kmsan_unpoison_memory(al, sizeof(*al)); return 0; } -- cgit v1.2.3