> > Could you please to be more specific? I mean how is it connected with huge > > pages mappings? Huge-pages are which have order > 0. Or you mean that > > a special alignments are needed for mapping huge pages? > > Let me try to clarify: > > > KASAN does an exact allocation when onlining a memory block, > __vmalloc_node_range() will try placing huge pages first, increasing the > alignment to e.g., "1 << PMD_SHIFT". > > If we increase the search length in find_vmap_lowest_match(), that > search will fail if the exact allocation is surrounded by other > allocations. In that case, we won't place a huge page although we could > -- because find_vmap_lowest_match() would be imprecise for alignments > > PAGE_SIZE. > > > Memory blocks we online/offline on x86 are at least 128MB. The KASAN > "overhead" we have to allocate is 1/8 of that -- 16 MB, so essentially 8 > huge pages. > > __vmalloc_node_range() will increase the alignment to 2MB to try placing > huge pages first. find_vmap_lowest_match() will search within the given > exact 16MB are a 18MB area (size + align), which won't work. So > __vmalloc_node_range() will fallback to the original PAGE_SIZE alignment > and shift=PAGE_SHIFT. > > __vmalloc_area_node() will set the set_vm_area_page_order effectively to > 0 -- small pages. > > Does that make sense or am I missing something? > Thank you for clarification. OK, we come back anyway to the "problem" with fixed range and an exact allocation plus a special alignment > PAGE_SIZE. Thus the KASAN will not make use of huge pages mappings and go with regular instead as a fallback path. But we would like to utilize huge-mappings for KASAN. I will send the patch you tested and add your "tested-by" tag. Does it sound good? -- Uladzislau Rezki
