Re: [PATCH v2 1/3] rcu/kasan: record and print call_rcu() call stack

From: Dmitry Vyukov
Date: Mon May 11 2020 - 07:08:44 EST


On Mon, May 11, 2020 at 4:31 AM Walter Wu <walter-zh.wu@xxxxxxxxxxxx> wrote:
>
> This feature will record first and last call_rcu() call stack and
> print two call_rcu() call stack in KASAN report.
>
> When call_rcu() is called, we store the call_rcu() call stack into
> slub alloc meta-data, so that KASAN report can print rcu stack.
>
> It doesn't increase the cost of memory consumption. Because we don't
> enlarge struct kasan_alloc_meta size.
> - add two call_rcu() call stack into kasan_alloc_meta, size is 8 bytes.
> - remove free track from kasan_alloc_meta, size is 8 bytes.
>
> [1]https://bugzilla.kernel.org/show_bug.cgi?id=198437
> [2]https://groups.google.com/forum/#!searchin/kasan-dev/better$20stack$20traces$20for$20rcu%7Csort:date/kasan-dev/KQsjT_88hDE/7rNUZprRBgAJ
>
> Signed-off-by: Walter Wu <walter-zh.wu@xxxxxxxxxxxx>
> Suggested-by: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
> Cc: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
> Cc: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
> Cc: Alexander Potapenko <glider@xxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
> Cc: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
> Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> Cc: Lai Jiangshan <jiangshanlai@xxxxxxxxx>
> Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
> ---
> include/linux/kasan.h | 2 ++
> kernel/rcu/tree.c | 3 +++
> lib/Kconfig.kasan | 2 ++
> mm/kasan/common.c | 4 ++--
> mm/kasan/generic.c | 29 +++++++++++++++++++++++++++++
> mm/kasan/kasan.h | 19 +++++++++++++++++++
> mm/kasan/report.c | 21 +++++++++++++++++----
> 7 files changed, 74 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/kasan.h b/include/linux/kasan.h
> index 31314ca7c635..23b7ee00572d 100644
> --- a/include/linux/kasan.h
> +++ b/include/linux/kasan.h
> @@ -174,11 +174,13 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
>
> void kasan_cache_shrink(struct kmem_cache *cache);
> void kasan_cache_shutdown(struct kmem_cache *cache);
> +void kasan_record_aux_stack(void *ptr);
>
> #else /* CONFIG_KASAN_GENERIC */
>
> static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
> static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
> +static inline void kasan_record_aux_stack(void *ptr) {}
>
> #endif /* CONFIG_KASAN_GENERIC */
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 06548e2ebb72..de872b6cc261 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -57,6 +57,7 @@
> #include <linux/slab.h>
> #include <linux/sched/isolation.h>
> #include <linux/sched/clock.h>
> +#include <linux/kasan.h>
> #include "../time/tick-internal.h"
>
> #include "tree.h"
> @@ -2694,6 +2695,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
> trace_rcu_callback(rcu_state.name, head,
> rcu_segcblist_n_cbs(&rdp->cblist));
>
> + kasan_record_aux_stack(head);

This happens after we queued the object onto some queue and after some
return statements. I think this is wrong.
We need to do this somewhere at the very beginning of the function.

This is what I meant by "hard to review". This is completely invisible
in the diff.


> /* Go handle any RCU core processing required. */
> if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
> unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
> diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
> index 81f5464ea9e1..56a89291f1cc 100644
> --- a/lib/Kconfig.kasan
> +++ b/lib/Kconfig.kasan
> @@ -58,6 +58,8 @@ config KASAN_GENERIC
> For better error detection enable CONFIG_STACKTRACE.
> Currently CONFIG_KASAN_GENERIC doesn't work with CONFIG_DEBUG_SLAB
> (the resulting kernel does not boot).
> + Currently CONFIG_KASAN_GENERIC will print first and last call_rcu()
> + call stack. It doesn't increase the cost of memory consumption.
>
> config KASAN_SW_TAGS
> bool "Software tag-based mode"
> diff --git a/mm/kasan/common.c b/mm/kasan/common.c
> index 2906358e42f0..8bc618289bb1 100644
> --- a/mm/kasan/common.c
> +++ b/mm/kasan/common.c
> @@ -41,7 +41,7 @@
> #include "kasan.h"
> #include "../slab.h"
>
> -static inline depot_stack_handle_t save_stack(gfp_t flags)
> +depot_stack_handle_t kasan_save_stack(gfp_t flags)
> {
> unsigned long entries[KASAN_STACK_DEPTH];
> unsigned int nr_entries;
> @@ -54,7 +54,7 @@ static inline depot_stack_handle_t save_stack(gfp_t flags)
> static inline void set_track(struct kasan_track *track, gfp_t flags)
> {
> track->pid = current->pid;
> - track->stack = save_stack(flags);
> + track->stack = kasan_save_stack(flags);
> }
>
> void kasan_enable_current(void)
> diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
> index 56ff8885fe2e..b86880c338e2 100644
> --- a/mm/kasan/generic.c
> +++ b/mm/kasan/generic.c
> @@ -325,3 +325,32 @@ DEFINE_ASAN_SET_SHADOW(f2);
> DEFINE_ASAN_SET_SHADOW(f3);
> DEFINE_ASAN_SET_SHADOW(f5);
> DEFINE_ASAN_SET_SHADOW(f8);
> +
> +void kasan_record_aux_stack(void *addr)
> +{
> + struct page *page = kasan_addr_to_page(addr);
> + struct kmem_cache *cache;
> + struct kasan_alloc_meta *alloc_info;
> + void *object;
> +
> + if (!(page && PageSlab(page)))
> + return;
> +
> + cache = page->slab_cache;
> + object = nearest_obj(cache, page, addr);
> + alloc_info = get_alloc_info(cache, object);
> +
> + if (!alloc_info->rcu_stack[0])
> + /* record first call_rcu() call stack */
> + alloc_info->rcu_stack[0] = kasan_save_stack(GFP_NOWAIT);
> + else
> + /* record last call_rcu() call stack */
> + alloc_info->rcu_stack[1] = kasan_save_stack(GFP_NOWAIT);
> +}
> +
> +struct kasan_track *kasan_get_aux_stack(struct kasan_alloc_meta *alloc_info,
> + u8 idx)
> +{
> + return container_of(&alloc_info->rcu_stack[idx],
> + struct kasan_track, stack);
> +}
> diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
> index e8f37199d885..1cc1fb7b0de3 100644
> --- a/mm/kasan/kasan.h
> +++ b/mm/kasan/kasan.h
> @@ -96,15 +96,28 @@ struct kasan_track {
> depot_stack_handle_t stack;
> };
>
> +#ifdef CONFIG_KASAN_GENERIC
> +#define SIZEOF_PTR sizeof(void *)
> +#define KASAN_NR_RCU_CALL_STACKS 2
> +#else /* CONFIG_KASAN_GENERIC */
> #ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
> #define KASAN_NR_FREE_STACKS 5
> #else
> #define KASAN_NR_FREE_STACKS 1
> #endif
> +#endif /* CONFIG_KASAN_GENERIC */
>
> struct kasan_alloc_meta {
> struct kasan_track alloc_track;
> +#ifdef CONFIG_KASAN_GENERIC
> + /*
> + * call_rcu() call stack is stored into struct kasan_alloc_meta.
> + * The free stack is stored into freed object.
> + */
> + depot_stack_handle_t rcu_stack[KASAN_NR_RCU_CALL_STACKS];
> +#else
> struct kasan_track free_track[KASAN_NR_FREE_STACKS];
> +#endif
> #ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
> u8 free_pointer_tag[KASAN_NR_FREE_STACKS];
> u8 free_track_idx;
> @@ -159,16 +172,22 @@ void kasan_report_invalid_free(void *object, unsigned long ip);
>
> struct page *kasan_addr_to_page(const void *addr);
>
> +depot_stack_handle_t kasan_save_stack(gfp_t flags);
> +
> #if defined(CONFIG_KASAN_GENERIC) && \
> (defined(CONFIG_SLAB) || defined(CONFIG_SLUB))
> void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
> void quarantine_reduce(void);
> void quarantine_remove_cache(struct kmem_cache *cache);
> +struct kasan_track *kasan_get_aux_stack(struct kasan_alloc_meta *alloc_info,
> + u8 idx);
> #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) { }
> +static inline struct kasan_track *kasan_get_aux_stack(
> + struct kasan_alloc_meta *alloc_info, u8 idx) { return NULL; }
> #endif
>
> #ifdef CONFIG_KASAN_SW_TAGS
> diff --git a/mm/kasan/report.c b/mm/kasan/report.c
> index 80f23c9da6b0..f16a1a210815 100644
> --- a/mm/kasan/report.c
> +++ b/mm/kasan/report.c
> @@ -105,9 +105,13 @@ static void end_report(unsigned long *flags)
> kasan_enable_current();
> }
>
> -static void print_track(struct kasan_track *track, const char *prefix)
> +static void print_track(struct kasan_track *track, const char *prefix,
> + bool is_callrcu)
> {
> - pr_err("%s by task %u:\n", prefix, track->pid);
> + if (is_callrcu)
> + pr_err("%s:\n", prefix);
> + else
> + pr_err("%s by task %u:\n", prefix, track->pid);
> if (track->stack) {
> unsigned long *entries;
> unsigned int nr_entries;
> @@ -187,11 +191,20 @@ static void describe_object(struct kmem_cache *cache, void *object,
> if (cache->flags & SLAB_KASAN) {
> struct kasan_track *free_track;
>
> - print_track(&alloc_info->alloc_track, "Allocated");
> + print_track(&alloc_info->alloc_track, "Allocated", false);
> pr_err("\n");
> free_track = kasan_get_free_track(cache, object, tag);
> - print_track(free_track, "Freed");
> + print_track(free_track, "Freed", false);
> pr_err("\n");
> +
> + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) {
> + free_track = kasan_get_aux_stack(alloc_info, 0);
> + print_track(free_track, "First call_rcu() call stack", true);
> + pr_err("\n");
> + free_track = kasan_get_aux_stack(alloc_info, 1);
> + print_track(free_track, "Last call_rcu() call stack", true);
> + pr_err("\n");
> + }
> }
>
> describe_object_addr(cache, object, addr);
> --
> 2.18.0
>
> --
> You received this message because you are subscribed to the Google Groups "kasan-dev" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to kasan-dev+unsubscribe@xxxxxxxxxxxxxxxxx
> To view this discussion on the web visit https://groups.google.com/d/msgid/kasan-dev/20200511023111.15310-1-walter-zh.wu%40mediatek.com.