Re: [PATCH 2/2] mm/vmalloc: Add attempt_larger_order_alloc parameter

[Uladzislau Rezki <urezki@gmail.com>]

On Thu, Dec 18, 2025 at 11:12:15AM +0000, Ryan Roberts wrote:
> On 17/12/2025 19:22, Uladzislau Rezki wrote:
> > On Wed, Dec 17, 2025 at 05:01:19PM +0000, Ryan Roberts wrote:
> >> On 17/12/2025 15:20, Ryan Roberts wrote:
> >>> On 17/12/2025 12:02, Uladzislau Rezki wrote:
> >>>>> On 16/12/2025 21:19, Uladzislau Rezki (Sony) wrote:
> >>>>>> Introduce a module parameter to enable or disable the large-order
> >>>>>> allocation path in vmalloc. High-order allocations are disabled by
> >>>>>> default so far, but users may explicitly enable them at runtime if
> >>>>>> desired.
> >>>>>>
> >>>>>> High-order pages allocated for vmalloc are immediately split into
> >>>>>> order-0 pages and later freed as order-0, which means they do not
> >>>>>> feed the per-CPU page caches. As a result, high-order attempts tend
> >>>>>> to bypass the PCP fastpath and fall back to the buddy allocator that
> >>>>>> can affect performance.
> >>>>>>
> >>>>>> However, when the PCP caches are empty, high-order allocations may
> >>>>>> show better performance characteristics especially for larger
> >>>>>> allocation requests.
> >>>>>
> >>>>> I wonder if a better solution would be "allocate order-0 if available in pcp,
> >>>>> else try large order, else fallback to order-0" Could that provide the best of
> >>>>> all worlds without needing a configuration knob?
> >>>>>
> >>>> I am not sure, to me it looks like a bit odd. 
> >>>
> >>> Perhaps it would feel better if it was generalized to "first try allocation from
> >>> PCP list, highest to lowest order, then try allocation from the buddy, highest
> >>> to lowest order"?
> >>>
> >>>> Ideally it would be
> >>>> good just free it as high-order page and not order-0 peaces.
> >>>
> >>> Yeah perhaps that's better. How about something like this (very lightly tested
> >>> and no performance results yet):
> >>>
> >>> (And I should admit I'm not 100% sure it is safe to call free_frozen_pages()
> >>> with a contiguous run of order-0 pages, but I'm not seeing any warnings or
> >>> memory leaks when running mm selftests...)
> >>>
> >>> ---8<---
> >>> commit caa3e5eb5bfade81a32fa62d1a8924df1eb0f619
> >>> Author: Ryan Roberts <ryan.roberts@arm.com>
> >>> Date:   Wed Dec 17 15:11:08 2025 +0000
> >>>
> >>>     WIP
> >>>
> >>>     Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> >>>
> >>> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> >>> index b155929af5b1..d25f5b867e6b 100644
> >>> --- a/include/linux/gfp.h
> >>> +++ b/include/linux/gfp.h
> >>> @@ -383,6 +383,8 @@ extern void __free_pages(struct page *page, unsigned int order);
> >>>  extern void free_pages_nolock(struct page *page, unsigned int order);
> >>>  extern void free_pages(unsigned long addr, unsigned int order);
> >>>
> >>> +void free_pages_bulk(struct page *page, int nr_pages);
> >>> +
> >>>  #define __free_page(page) __free_pages((page), 0)
> >>>  #define free_page(addr) free_pages((addr), 0)
> >>>
> >>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> >>> index 822e05f1a964..5f11224cf353 100644
> >>> --- a/mm/page_alloc.c
> >>> +++ b/mm/page_alloc.c
> >>> @@ -5304,6 +5304,48 @@ static void ___free_pages(struct page *page, unsigned int
> >>> order,
> >>>  	}
> >>>  }
> >>>
> >>> +static void free_frozen_pages_bulk(struct page *page, int nr_pages)
> >>> +{
> >>> +	while (nr_pages) {
> >>> +		unsigned int fit_order, align_order, order;
> >>> +		unsigned long pfn;
> >>> +
> >>> +		pfn = page_to_pfn(page);
> >>> +		fit_order = ilog2(nr_pages);
> >>> +		align_order = pfn ? __ffs(pfn) : fit_order;
> >>> +		order = min3(fit_order, align_order, MAX_PAGE_ORDER);
> >>> +
> >>> +		free_frozen_pages(page, order);
> >>> +
> >>> +		page += 1U << order;
> >>> +		nr_pages -= 1U << order;
> >>> +	}
> >>> +}
> >>> +
> >>> +void free_pages_bulk(struct page *page, int nr_pages)
> >>> +{
> >>> +	struct page *start = NULL;
> >>> +	bool can_free;
> >>> +	int i;
> >>> +
> >>> +	for (i = 0; i < nr_pages; i++, page++) {
> >>> +		VM_BUG_ON_PAGE(PageHead(page), page);
> >>> +		VM_BUG_ON_PAGE(PageTail(page), page);
> >>> +
> >>> +		can_free = put_page_testzero(page);
> >>> +
> >>> +		if (!can_free && start) {
> >>> +			free_frozen_pages_bulk(start, page - start);
> >>> +			start = NULL;
> >>> +		} else if (can_free && !start) {
> >>> +			start = page;
> >>> +		}
> >>> +	}
> >>> +
> >>> +	if (start)
> >>> +		free_frozen_pages_bulk(start, page - start);
> >>> +}
> >>> +
> >>>  /**
> >>>   * __free_pages - Free pages allocated with alloc_pages().
> >>>   * @page: The page pointer returned from alloc_pages().
> >>> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> >>> index ecbac900c35f..8f782bac1ece 100644
> >>> --- a/mm/vmalloc.c
> >>> +++ b/mm/vmalloc.c
> >>> @@ -3429,7 +3429,8 @@ void vfree_atomic(const void *addr)
> >>>  void vfree(const void *addr)
> >>>  {
> >>>  	struct vm_struct *vm;
> >>> -	int i;
> >>> +	struct page *start;
> >>> +	int i, nr;
> >>>
> >>>  	if (unlikely(in_interrupt())) {
> >>>  		vfree_atomic(addr);
> >>> @@ -3455,17 +3456,26 @@ void vfree(const void *addr)
> >>>  	/* All pages of vm should be charged to same memcg, so use first one. */
> >>>  	if (vm->nr_pages && !(vm->flags & VM_MAP_PUT_PAGES))
> >>>  		mod_memcg_page_state(vm->pages[0], MEMCG_VMALLOC, -vm->nr_pages);
> >>> -	for (i = 0; i < vm->nr_pages; i++) {
> >>> +
> >>> +	start = vm->pages[0];
> >>> +	BUG_ON(!start);
> >>> +	nr = 1;
> >>> +	for (i = 1; i < vm->nr_pages; i++) {
> >>>  		struct page *page = vm->pages[i];
> >>>
> >>>  		BUG_ON(!page);
> >>> -		/*
> >>> -		 * High-order allocs for huge vmallocs are split, so
> >>> -		 * can be freed as an array of order-0 allocations
> >>> -		 */
> >>> -		__free_page(page);
> >>> -		cond_resched();
> >>> +
> >>> +		if (start + nr != page) {
> >>> +			free_pages_bulk(start, nr);
> >>> +			start = page;
> >>> +			nr = 1;
> >>> +			cond_resched();
> >>> +		} else {
> >>> +			nr++;
> >>> +		}
> >>>  	}
> >>> +	free_pages_bulk(start, nr);
> >>> +
> >>>  	if (!(vm->flags & VM_MAP_PUT_PAGES))
> >>>  		atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
> >>>  	kvfree(vm->pages);
> >>> ---8<---
> >>
> >> I tested this on a performance monitoring system and see a huge improvement for 
> >> the test_vmalloc tests.
> >>
> >> Both columns are compared to v6.18. 6-19-0-rc1 has Vishal's change to allocate 
> >> large orders, which I previously reported the regressions for. vfree-high-order 
> >> adds the above patch to free contiguous order-0 pages in bulk.
> >>
> >> (R)/(I) means statistically significant regression/improvement. Results are 
> >> normalized so that less than zero is regression and greater than zero is 
> >> improvement.
> >>
> >> +-----------------+----------------------------------------------------------+--------------+------------------+
> >> | Benchmark       | Result Class                                             |   6-19-0-rc1 | vfree-high-order |
> >> +=================+==========================================================+==============+==================+
> >> | micromm/vmalloc | fix_align_alloc_test: p:1, h:0, l:500000 (usec)          |  (R) -40.69% |        (I) 3.98% |
> >> |                 | fix_size_alloc_test: p:1, h:0, l:500000 (usec)           |        0.10% |           -1.47% |
> >> |                 | fix_size_alloc_test: p:4, h:0, l:500000 (usec)           |  (R) -22.74% |       (I) 11.57% |
> >> |                 | fix_size_alloc_test: p:16, h:0, l:500000 (usec)          |  (R) -23.63% |       (I) 47.42% |
> >> |                 | fix_size_alloc_test: p:16, h:1, l:500000 (usec)          |       -1.58% |      (I) 106.01% |
> >> |                 | fix_size_alloc_test: p:64, h:0, l:100000 (usec)          |  (R) -24.39% |       (I) 99.12% |
> >> |                 | fix_size_alloc_test: p:64, h:1, l:100000 (usec)          |    (I) 2.34% |      (I) 196.87% |
> >> |                 | fix_size_alloc_test: p:256, h:0, l:100000 (usec)         |  (R) -23.29% |      (I) 125.42% |
> >> |                 | fix_size_alloc_test: p:256, h:1, l:100000 (usec)         |    (I) 3.74% |      (I) 238.59% |
> >> |                 | fix_size_alloc_test: p:512, h:0, l:100000 (usec)         |  (R) -23.80% |      (I) 132.38% |
> >> |                 | fix_size_alloc_test: p:512, h:1, l:100000 (usec)         |   (R) -2.84% |      (I) 514.75% |
> >> |                 | full_fit_alloc_test: p:1, h:0, l:500000 (usec)           |        2.74% |            0.33% |
> >> |                 | kvfree_rcu_1_arg_vmalloc_test: p:1, h:0, l:500000 (usec) |        0.58% |            1.36% |
> >> |                 | kvfree_rcu_2_arg_vmalloc_test: p:1, h:0, l:500000 (usec) |       -0.66% |            1.48% |
> >> |                 | long_busy_list_alloc_test: p:1, h:0, l:500000 (usec)     |  (R) -25.24% |       (I) 77.95% |
> >> |                 | pcpu_alloc_test: p:1, h:0, l:500000 (usec)               |       -0.58% |            0.60% |
> >> |                 | random_size_align_alloc_test: p:1, h:0, l:500000 (usec)  |  (R) -45.75% |        (I) 8.51% |
> >> |                 | random_size_alloc_test: p:1, h:0, l:500000 (usec)        |  (R) -28.16% |       (I) 65.34% |
> >> |                 | vm_map_ram_test: p:1, h:0, l:500000 (usec)               |       -0.54% |           -0.33% |
> >> +-----------------+----------------------------------------------------------+--------------+------------------+
> >>
> >> What do you think?
> >>
> > You were first :)
> > 
> > Some figures from me:
> > 
> > # Default(3 pages)
> 
> What is Default? I'm guessing it's the state prior to Vishal's patch?
> 
Right.

> > fix_size_alloc_test passed: 1 failed: 0 xfailed: 0 repeat: 1 loops: 1000000 avg: 541868 usec
> > fix_size_alloc_test passed: 1 failed: 0 xfailed: 0 repeat: 1 loops: 1000000 avg: 542515 usec
> > fix_size_alloc_test passed: 1 failed: 0 xfailed: 0 repeat: 1 loops: 1000000 avg: 541561 usec
> > fix_size_alloc_test passed: 1 failed: 0 xfailed: 0 repeat: 1 loops: 1000000 avg: 542951 usec
> > 
> > # Patch(3 pages)
> 
> What is Patch? I'm guessing state after applying both Vishal's and my patches?
> 
Right.

--
Uladzislau Rezki