vmalloc() consists of the following: (1) find empty space in the vmalloc space -> (2) get physical pages from the buddy system -> (3) map the pages into the pagetable. It turns out that the cost of (1) and (3) is pretty insignificant. Hence, the cost of vmalloc becomes highly sensitive to physical memory allocation time. Currently, if we decide to use huge mappings, apart from aligning the start of the target vm_struct region to the huge-alignment, we also align the size. This does not seem to produce any benefit (apart from simplification of the code), and there is a clear disadvantage - as mentioned above, the main cost of vmalloc comes from its interaction with the buddy system, and thus requesting more memory than was requested by the caller is suboptimal and unnecessary. This change is also motivated due to the next patch ("arm64/mm: Enable vmalloc-huge by default"). Suppose that some user of vmalloc maps 17 pages, uses that mapping for an extremely short time, and vfree's it. That patch, without this patch, on arm64 will ultimately map 16 * 2 = 32 pages in a contiguous way. Since the mapping is used for a very short time, it is likely that the extra cost of mapping 15 pages defeats any benefit from reduced TLB pressure, and regresses that code path. Signed-off-by: Dev Jain --- mm/vmalloc.c | 38 ++++++++++++++++++++++++++++++-------- 1 file changed, 30 insertions(+), 8 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 798b2ed21e46..ddd9294a4634 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -647,7 +647,7 @@ static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { - unsigned int i, nr = (end - addr) >> PAGE_SHIFT; + unsigned int i, step, nr = (end - addr) >> PAGE_SHIFT; WARN_ON(page_shift < PAGE_SHIFT); @@ -655,7 +655,8 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, page_shift == PAGE_SHIFT) return vmap_small_pages_range_noflush(addr, end, prot, pages); - for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { + step = 1U << (page_shift - PAGE_SHIFT); + for (i = 0; i < ALIGN_DOWN(nr, step); i += step) { int err; err = vmap_range_noflush(addr, addr + (1UL << page_shift), @@ -666,8 +667,9 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, addr += 1UL << page_shift; } - - return 0; + if (IS_ALIGNED(nr, step)) + return 0; + return vmap_small_pages_range_noflush(addr, end, prot, pages + i); } int vmap_pages_range_noflush(unsigned long addr, unsigned long end, @@ -3171,7 +3173,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long requested_size = size; BUG_ON(in_interrupt()); - size = ALIGN(size, 1ul << shift); + size = PAGE_ALIGN(size); if (unlikely(!size)) return NULL; @@ -3327,7 +3329,7 @@ static void vm_reset_perms(struct vm_struct *area) * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map. */ - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < ALIGN_DOWN(area->nr_pages, 1U << page_order); i += (1U << page_order)) { unsigned long addr = (unsigned long)page_address(area->pages[i]); if (addr) { @@ -3339,6 +3341,18 @@ static void vm_reset_perms(struct vm_struct *area) flush_dmap = 1; } } + for (; i < area->nr_pages; ++i) { + unsigned long addr = (unsigned long)page_address(area->pages[i]); + + if (addr) { + unsigned long page_size; + + page_size = PAGE_SIZE; + start = min(addr, start); + end = max(addr + page_size, end); + flush_dmap = 1; + } + } /* * Set direct map to something invalid so that it won't be cached if @@ -3602,6 +3616,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * more permissive. */ if (!order) { +page_map: while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; @@ -3633,13 +3648,18 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * If zero or pages were obtained partly, * fallback to a single page allocator. */ - if (nr != nr_pages_request) + if (nr != nr_pages_request) { + order = 0; break; + } } } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { + if (nr_pages - nr_allocated < (1UL << order)) + goto page_map; + if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) break; @@ -5024,7 +5044,9 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v, memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) + for (nr = 0; nr < ALIGN_DOWN(v->nr_pages, step); nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for (; nr < v->nr_pages; ++nr) counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) -- 2.30.2