On 11/15/2017 08:34 PM, Alexander Potapenko wrote:
> stackdepot used to call memcmp(), which compiler tools normally
> instrument, therefore every lookup used to unnecessarily call
> instrumented code.
> This is somewhat ok in the case of KASAN, but under KMSAN a lot of time
> was spent in the instrumentation.
>
> Signed-off-by: Alexander Potapenko <[email protected]>
> ---
> lib/stackdepot.c | 21 ++++++++++++++++++---
> 1 file changed, 18 insertions(+), 3 deletions(-)
>
> diff --git a/lib/stackdepot.c b/lib/stackdepot.c
> index f87d138e9672..d372101e8dc2 100644
> --- a/lib/stackdepot.c
> +++ b/lib/stackdepot.c
> @@ -163,6 +163,23 @@ static inline u32 hash_stack(unsigned long *entries,
> unsigned int size)
> STACK_HASH_SEED);
> }
>
> +/* Use our own, non-instrumented version of memcmp().
> + *
> + * We actually don't care about the order, just the equality.
> + */
> +static inline
> +int stackdepot_memcmp(const void *s1, const void *s2, unsigned int n)
> +{
Why 'void *' types? The function treats s1, s2 as array of long, also 'n' is
number of longs here.
> + unsigned long *u1 = (unsigned long *)s1;
> + unsigned long *u2 = (unsigned long *)s2;
> +
> + for ( ; n-- ; u1++, u2++) {
> + if (*u1 != *u2)
> + return 1;
> + }
> + return 0;
> +}
> +
> /* Find a stack that is equal to the one stored in entries in the hash */
> static inline struct stack_record *find_stack(struct stack_record *bucket,
> unsigned long *entries, int size,
> @@ -173,10 +190,8 @@ static inline struct stack_record *find_stack(struct
> stack_record *bucket,
> for (found = bucket; found; found = found->next) {
> if (found->hash == hash &&
> found->size == size &&
> - !memcmp(entries, found->entries,
> - size * sizeof(unsigned long))) {
> + !stackdepot_memcmp(entries, found->entries, size))
> return found;
> - }
> }
> return NULL;
> }
>
