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/<name>/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.
Signed-off-by: Imran Khan <[email protected]>
---
This RFC patch is implementing the sysfs work mentioned in [1]. Since the
approach taken in [1] was not proper, I am sending this RFC patch as a
separate change.
[1]: https://lore.kernel.org/lkml/[email protected]/
include/linux/slab.h | 6 ++++++
mm/kfence/core.c | 7 +++++++
mm/slub.c | 27 +++++++++++++++++++++++++++
3 files changed, 40 insertions(+)
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 0fefdf528e0d..947d912fd08c 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -119,6 +119,12 @@
*/
#define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U)
+#ifdef CONFIG_KFENCE
+#define SLAB_SKIP_KFENCE ((slab_flags_t __force)0x20000000U)
+#else
+#define SLAB_SKIP_KFENCE 0
+#endif
+
/* The following flags affect the page allocator grouping pages by mobility */
/* Objects are reclaimable */
#define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U)
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index c252081b11df..8c08ae2101d7 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -1003,6 +1003,13 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
return NULL;
}
+ /*
+ * Skip allocations for this slab, if KFENCE has been disabled for
+ * this slab.
+ */
+ if (s->flags & SLAB_SKIP_KFENCE)
+ return NULL;
+
if (atomic_inc_return(&kfence_allocation_gate) > 1)
return NULL;
#ifdef CONFIG_KFENCE_STATIC_KEYS
diff --git a/mm/slub.c b/mm/slub.c
index 862dbd9af4f5..ee8b48327536 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5745,6 +5745,30 @@ 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 +5836,9 @@ static struct attribute *slab_attrs[] = {
&failslab_attr.attr,
#endif
&usersize_attr.attr,
+#ifdef CONFIG_KFENCE
+ &skip_kfence_attr.attr,
+#endif
NULL
};
base-commit: 40d43a7507e1547dd45cb02af2e40d897c591870
--
2.30.2
On Thu, 11 Aug 2022 at 09:26, Imran Khan <[email protected]> wrote:
>
> 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/<name>/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.
>
> Signed-off-by: Imran Khan <[email protected]>
> ---
>
> This RFC patch is implementing the sysfs work mentioned in [1]. Since the
> approach taken in [1] was not proper, I am sending this RFC patch as a
> separate change.
This design is much simpler and looks good to me. Feel free to send as
a non-RFC.
> [1]: https://lore.kernel.org/lkml/[email protected]/
>
> include/linux/slab.h | 6 ++++++
> mm/kfence/core.c | 7 +++++++
> mm/slub.c | 27 +++++++++++++++++++++++++++
> 3 files changed, 40 insertions(+)
>
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index 0fefdf528e0d..947d912fd08c 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -119,6 +119,12 @@
> */
> #define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U)
>
> +#ifdef CONFIG_KFENCE
> +#define SLAB_SKIP_KFENCE ((slab_flags_t __force)0x20000000U)
> +#else
> +#define SLAB_SKIP_KFENCE 0
> +#endif
> +
> /* The following flags affect the page allocator grouping pages by mobility */
> /* Objects are reclaimable */
> #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U)
> diff --git a/mm/kfence/core.c b/mm/kfence/core.c
> index c252081b11df..8c08ae2101d7 100644
> --- a/mm/kfence/core.c
> +++ b/mm/kfence/core.c
> @@ -1003,6 +1003,13 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
> return NULL;
> }
>
> + /*
> + * Skip allocations for this slab, if KFENCE has been disabled for
> + * this slab.
> + */
> + if (s->flags & SLAB_SKIP_KFENCE)
> + return NULL;
> +
> if (atomic_inc_return(&kfence_allocation_gate) > 1)
> return NULL;
> #ifdef CONFIG_KFENCE_STATIC_KEYS
> diff --git a/mm/slub.c b/mm/slub.c
> index 862dbd9af4f5..ee8b48327536 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -5745,6 +5745,30 @@ 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);
> +
^ unnecessary space?
> +#endif
> +
> static struct attribute *slab_attrs[] = {
> &slab_size_attr.attr,
> &object_size_attr.attr,
> @@ -5812,6 +5836,9 @@ static struct attribute *slab_attrs[] = {
> &failslab_attr.attr,
> #endif
> &usersize_attr.attr,
> +#ifdef CONFIG_KFENCE
> + &skip_kfence_attr.attr,
> +#endif
>
> NULL
> };
>
> base-commit: 40d43a7507e1547dd45cb02af2e40d897c591870
> --
> 2.30.2
>
Hello,
On 11/8/22 6:40 pm, Marco Elver wrote:
> On Thu, 11 Aug 2022 at 09:26, Imran Khan <[email protected]> wrote:
>>
>> 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/<name>/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.
>>
>> Signed-off-by: Imran Khan <[email protected]>
>> ---
>>
>> This RFC patch is implementing the sysfs work mentioned in [1]. Since the
>> approach taken in [1] was not proper, I am sending this RFC patch as a
>> separate change.
>
> This design is much simpler and looks good to me. Feel free to send as
> a non-RFC.
>
Thanks for reviewing this. I have sent non-RFC version of this change.
Thanks,
-- Imran