Thread locals don't fully solve the problem. They work well if you immediately call the closure, but what if you want to store the closure and call it later?

    #include <stdlib.h>
    #include <string.h>
    #include <stddef.h>

    typedef int (*comp)(const void *untyped_left, const void *untyped_right);

    thread_local int in_reverse = 0;

    __attribute__((noinline))
    int compare_impl(const void *untyped_left, const void *untyped_right, int in_reverse) {
        const int* left = untyped_left;
        const int* right = untyped_right;
        return (in_reverse) ? *right - *left : *left - *right;
    }

    comp make_sort(int direction) {
        in_reverse = direction;
        int compare(const void *untyped_left, const void *untyped_right) {
            return compare_impl(untyped_left, untyped_right, in_reverse);
        }
        return compare;
    }

    int main(int argc, char* argv[]) {

        int list[] = { 2, 11, 32, 49, 57, 20, 110, 203 };

        comp normal_sort = make_sort(0);
        comp reverse_sort = make_sort(1);

        qsort(list, (sizeof(list)/sizeof(*list)), sizeof(*list), normal_sort);
            
        return list[0];
    }

Yep. Thread locals are probably faster than the other solutions shown too.

It’s confusing to me that thread locals are “not the best idea outside small snippets” meanwhile the top solution is templating on recursion depth with a constexpr limit of 11.

reentrancy.