On Wed, 5 Feb 2025, Hyesoo Yu wrote:
> If a slab object is corrupted or an error occurs in its internal
> value, continuing after restoration may cause other side effects.
> At this point, it is difficult to debug because the problem occurred
> in the past. It is better to use WARN() instead of pr_err to catch
> errors at the point of issue because WARN() could trigger panic for
> system debugging when panic_on_warn is enabled. WARN() should be
> called prior to fixing the value because when a panic is triggered by WARN(),
> it allows us to check corrupted data.
>
I think this makes sense, but it doesn't document why the other changes
are being made, like moving the setting of *freelist to NULL. This is
presumably something that you want in the crash dump when
kernel.panic_on_warn is enabled. Probably best to call that out, but to
also indicate what you're relying on in the crash dump to make forward
progress on in diagnosing the issue.
> Changes in v2:
> - Replace direct calling with BUG_ON with the use of WARN in slab_fix.
>
> Signed-off-by: Hyesoo Yu <hyesoo.yu@xxxxxxxxxxx>
> ---
> mm/slub.c | 10 +++++-----
> 1 file changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 1f50129dcfb3..ea956cb4b8be 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -1043,7 +1043,7 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
> va_start(args, fmt);
> vaf.fmt = fmt;
> vaf.va = &args;
> - pr_err("FIX %s: %pV\n", s->name, &vaf);
> + WARN(1, "FIX %s: %pV\n", s->name, &vaf);
> va_end(args);
> }
>
> @@ -1106,8 +1106,8 @@ static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
> if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
> !check_valid_pointer(s, slab, nextfree) && freelist) {
> object_err(s, slab, *freelist, "Freechain corrupt");
> - *freelist = NULL;
> slab_fix(s, "Isolate corrupted freechain");
> + *freelist = NULL;
> return true;
> }
>
> @@ -1445,9 +1445,9 @@ static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search)
> set_freepointer(s, object, NULL);
> } else {
> slab_err(s, slab, "Freepointer corrupt");
> + slab_fix(s, "Freelist cleared");
> slab->freelist = NULL;
> slab->inuse = slab->objects;
> - slab_fix(s, "Freelist cleared");
> return 0;
> }
> break;
> @@ -1464,14 +1464,14 @@ static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search)
> if (slab->objects != max_objects) {
> slab_err(s, slab, "Wrong number of objects. Found %d but should be %d",
> slab->objects, max_objects);
> - slab->objects = max_objects;
> slab_fix(s, "Number of objects adjusted");
> + slab->objects = max_objects;
> }
> if (slab->inuse != slab->objects - nr) {
> slab_err(s, slab, "Wrong object count. Counter is %d but counted were %d",
> slab->inuse, slab->objects - nr);
> - slab->inuse = slab->objects - nr;
> slab_fix(s, "Object count adjusted");
> + slab->inuse = slab->objects - nr;
> }
> return search == NULL;
> }
> --
> 2.48.0
>
>
