Excerpts from Xu Yu's message of December 7, 2021 7:46 pm:
> The area->pages stores the struct pages allocated for vmalloc mappings.
> The allocated memory can be hugepage if arch has HAVE_ARCH_HUGE_VMALLOC
> set, while area->pages itself does not have to be hugepage backed.
>
> Suppose that we want to vmalloc 1026M of memory, then area->pages is
> 2052K in size, which is large than PMD_SIZE when the pagesize is 4K.
> Currently, 4096K will be allocated for area->pages, wherein 2044K is
> wasted.
>
> This introduces __vmalloc_node_no_huge, and makes area->pages backed by
> small pages, because I think to allocate hugepage for area->pages is
> unnecessary and vulnerable to abuse.
Any vmalloc allocation will be subject to internal fragmentation like
this. What makes this one special? Is there a way to improve it for
all with some heuristic?
There would be an argument for a size-optimised vmalloc vs a space
optimised one. An accounting strucutre like this doesn't matter
much for speed. A vfs hash table does. Is it worth doing though? How
much do you gain in practice?
Thanks,
Nick
>
> Signed-off-by: Xu Yu <xuyu@xxxxxxxxxxxxxxxxx>
> ---
> include/linux/vmalloc.h | 2 ++
> mm/vmalloc.c | 15 ++++++++++++---
> 2 files changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index 6e022cc712e6..e93f39eb46a5 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -150,6 +150,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
> const void *caller) __alloc_size(1);
> void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask,
> int node, const void *caller) __alloc_size(1);
> +void *__vmalloc_node_no_huge(unsigned long size, unsigned long align,
> + gfp_t gfp_mask, int node, const void *caller) __alloc_size(1);
> void *vmalloc_no_huge(unsigned long size) __alloc_size(1);
>
> extern void vfree(const void *addr);
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index d2a00ad4e1dd..0bdbb96d3e3f 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2925,17 +2925,18 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
> unsigned long size = get_vm_area_size(area);
> unsigned long array_size;
> unsigned int nr_small_pages = size >> PAGE_SHIFT;
> + unsigned int max_small_pages = ALIGN(size, 1UL << page_shift) >> PAGE_SHIFT;
> unsigned int page_order;
>
> - array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
> + array_size = (unsigned long)max_small_pages * sizeof(struct page *);
> gfp_mask |= __GFP_NOWARN;
> if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
> gfp_mask |= __GFP_HIGHMEM;
>
> /* Please note that the recursion is strictly bounded. */
> if (array_size > PAGE_SIZE) {
> - area->pages = __vmalloc_node(array_size, 1, nested_gfp, node,
> - area->caller);
> + area->pages = __vmalloc_node_no_huge(array_size, 1, nested_gfp,
> + node, area->caller);
> } else {
> area->pages = kmalloc_node(array_size, nested_gfp, node);
> }
> @@ -3114,6 +3115,14 @@ void *__vmalloc_node(unsigned long size, unsigned long align,
> return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
> gfp_mask, PAGE_KERNEL, 0, node, caller);
> }
> +
> +void *__vmalloc_node_no_huge(unsigned long size, unsigned long align,
> + gfp_t gfp_mask, int node, const void *caller)
> +{
> + return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
> + gfp_mask, PAGE_KERNEL, VM_NO_HUGE_VMAP, node, caller);
> +}
> +
> /*
> * This is only for performance analysis of vmalloc and stress purpose.
> * It is required by vmalloc test module, therefore do not use it other
> --
> 2.20.1.2432.ga663e714
>
>
