Re: [PATCH bpf-next v3 1/6] vmalloc: introduce execmem_alloc, execmem_free, and execmem_fill

[Song Liu <song@kernel.org>]

On Wed, Nov 16, 2022 at 5:36 PM Luis Chamberlain <mcgrof@kernel.org> wrote:
>
> On Wed, Nov 16, 2022 at 05:06:16PM -0800, Song Liu wrote:
> > +static void move_vmap_to_free_text_tree(void *addr)
> > +{
> > +     struct vmap_area *va;
> > +
> > +     /* remove from vmap_area_root */
> > +     spin_lock(&vmap_area_lock);
> > +     va = __find_vmap_area((unsigned long)addr, &vmap_area_root);
> > +     if (WARN_ON_ONCE(!va)) {
> > +             spin_unlock(&vmap_area_lock);
> > +             return;
> > +     }
> > +     unlink_va(va, &vmap_area_root);
> > +     spin_unlock(&vmap_area_lock);
> > +
> > +     /* make the memory RO+X */
> > +     memset(addr, 0, va->va_end - va->va_start);
> > +     set_memory_ro(va->va_start, (va->va_end - va->va_start) >> PAGE_SHIFT);
> > +     set_memory_x(va->va_start, (va->va_end - va->va_start) >> PAGE_SHIFT);
> > +
> > +     /* add to all_text_vm */
> > +     va->vm->next = all_text_vm;
> > +     all_text_vm = va->vm;
> > +
> > +     /* add to free_text_area_root */
> > +     spin_lock(&free_text_area_lock);
> > +     merge_or_add_vmap_area_augment(va, &free_text_area_root, &free_text_area_list);
> > +     spin_unlock(&free_text_area_lock);
> > +}
>
> <-- snip -->
>
> > +void *execmem_alloc(unsigned long size, unsigned long align)
> > +{
> > +     struct vmap_area *va, *tmp;
> > +     unsigned long addr;
> > +     enum fit_type type;
> > +     int ret;
> > +
> > +     va = kmem_cache_alloc_node(vmap_area_cachep, GFP_KERNEL, NUMA_NO_NODE);
> > +     if (unlikely(!va))
> > +             return NULL;
> > +
> > +again:
> > +     preload_this_cpu_lock(&free_text_area_lock, GFP_KERNEL, NUMA_NO_NODE);
> > +     tmp = find_vmap_lowest_match(&free_text_area_root, size, align, 1, false);
> > +
> > +     if (!tmp) {
> > +             unsigned long alloc_size;
> > +             void *ptr;
> > +
> > +             spin_unlock(&free_text_area_lock);
> > +
> > +             /*
> > +              * Not enough continuous space in free_text_area_root, try
> > +              * allocate more memory. The memory is first added to
> > +              * vmap_area_root, and then moved to free_text_area_root.
> > +              */
> > +             alloc_size = roundup(size, PMD_SIZE * num_online_nodes());
> > +             ptr = __vmalloc_node_range(alloc_size, PMD_SIZE, EXEC_MEM_START,
> > +                                        EXEC_MEM_END, GFP_KERNEL, PAGE_KERNEL,
> > +                                        VM_ALLOW_HUGE_VMAP | VM_NO_GUARD,
> > +                                        NUMA_NO_NODE, __builtin_return_address(0));
> > +             if (unlikely(!ptr))
> > +                     goto err_out;
> > +
> > +             move_vmap_to_free_text_tree(ptr);
>
> It's not perfectly clear to me how we know for sure nothing can take
> this underneath our noses.

This is because ptr points to vmap_area in vmap_area_* tree. It is only
used by the user (this thread). It is like we know vmalloc memory will
not go away until we call vfree on it.

Does this make sense?

Song