mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "David Hildenbrand (Arm)" <david@kernel.org>
To: Qi Zheng <qi.zheng@linux.dev>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Qi Zheng <zhengqi.arch@bytedance.com>,
	muchun.song@linux.dev, akpm@linux-foundation.org,
	osalvador@suse.de, azpijr@gmail.com, lance.yang@linux.dev
Subject: Re: [PATCH v3 0/3] mm: hugetlb: fix CMA-related issues
Date: Mon, 16 Nov 2026 13:07:16 +0100	[thread overview]
Message-ID: <1e0aa28d-f81b-411f-92a3-6038c3961443@kernel.org> (raw)
In-Reply-To: <bc6ffcff-3aaa-43da-91b4-82f27513c761@linux.dev>


Hi,

sorry somehow I missed your mail.


>>
>>>
>>> Likely cma_reserve_early() must be taught to align (and maybe consume an order
>>> instead of a size), similar to how the dynamic cma allocations work.
>>
>> However, simply adding alignment would leave gaps that the
>> current activation code cannot distinguish from actual reservations.
>>
>> The early allocation path would become:
>>
>> hugetlb_cma_alloc_bootmem()
>>     -> cma_reserve_early()
>>          pfn = ALIGN(cmr->early_pfn, nr_pages);
>>          cmr->early_pfn = pfn + nr_pages;
>>          cma->available_count -= nr_pages;
>>
>> For a CMA range starting at 4 GiB, reserving 32 MiB followed by 1 GiB
>> would produce:
>>
>> 4 GiB       4 GiB + 32 MiB             5 GiB             6 GiB
>> | 32 MiB used |------ 992 MiB gap ------| 1 GiB used       |
>>                                                           ^
>>                                                       early_pfn
>>
>> Later, cma_activate_area() marks the entire prefix below early_pfn as
>> allocated, including the gap:
>>
>> count = early_pfn[r] - cmr->base_pfn;
>> bitmap_count = cma_bitmap_pages_to_bits(cma, count);
>> bitmap_set(cmr->bitmap, 0, bitmap_count);
>>
>> It only initializes and frees pageblocks after that cursor:
>>
>> for (pfn = early_pfn[r]; pfn < cmr->base_pfn + cmr->count;
>>        pfn += pageblock_nr_pages)
>> 	init_cma_reserved_pageblock(pfn_to_page(pfn));
>>
>> The gap therefore remains reserved and marked allocated. Releasing the
>> two HugeTLB folios only clears their own ranges through
>> cma_release_frozen(); neither release covers the gap. Those 992 MiB
>> would be permanently lost from usable CMA capacity.
>>
>> So we would also need to track the gaps, clear their bitmap bits during
>> activation, and initialize them as free CMA pageblocks.

Ugh, what a hacky mess people created.

>>
>>>
>>
>> Another possibility would be to give 32 MiB pages their own pool,
>> similar to the separate PMD-sized pool proposed in the other series. On
>> arm64 with 4 KiB base pages, 2 MiB, 32 MiB and 1 GiB allocations would
>> then use separate pools.

That would be cleanest. Would it break existing setups?


Another quick-fix idea could be to always allocate larger folios first.

That way we should avoid any holes, right>

>>
>> This could work during early boot too: hugetlb_cma_reserve() establishes
>> the CMA areas and their ranges before hugetlb_bootmem_alloc() runs.
>> Although the bitmaps are allocated later, each range already has its
>> own early_pfn. With naturally aligned ranges and one allocation size
>> per pool, the cursors would stay aligned without creating gaps.
>>
>> What do you think?
> 
> Hi David, gentle ping
> 
> I’d like to update to v5 so that I can continue advancing the support

Feel free to fix this issue here independently from the current series.

> for 2M hugetlb CMA. Regarding this issue, would you like me to include a
> fix in v5? If you agree with the "split pool" approach, we can handle it
> as part of the patch set for 2M hugetlb CMA support.


I think we want a stable-first fix for that.


-- 
Cheers,

David

      reply	other threads:[~2026-11-16 12:07 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-07 10:30 Qi Zheng
2026-11-07 10:30 ` [PATCH v3 1/3] x86: hugetlb: disable default CMA reservations on 32-bit kernel Qi Zheng
2026-11-07 10:30 ` [PATCH v3 2/3] mm: gup: allow long-term pins of CMA-allocated HugeTLB folios Qi Zheng
2026-11-07 17:58   ` David Hildenbrand (Arm)
2026-11-09  3:10     ` Qi Zheng
2026-11-11  7:43       ` David Hildenbrand (Arm)
2026-11-11 10:26         ` Qi Zheng
2026-11-11 22:26           ` Frank van der Linden
2026-11-12  3:27             ` Qi Zheng
2026-11-12  8:36             ` David Hildenbrand (Arm)
2026-11-12  8:40           ` David Hildenbrand (Arm)
2026-11-07 10:30 ` [PATCH v3 3/3] mm: hugetlb: fix GFP mask propagation to CMA Qi Zheng
2026-11-07 17:02   ` Oscar Salvador (SUSE)
2026-11-09  3:10     ` Qi Zheng
2026-11-11 22:05 ` [PATCH v3 0/3] mm: hugetlb: fix CMA-related issues David Hildenbrand (Arm)
2026-11-12  3:25   ` Qi Zheng
2026-11-16  2:01     ` Qi Zheng
2026-11-16 12:07       ` David Hildenbrand (Arm) [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1e0aa28d-f81b-411f-92a3-6038c3961443@kernel.org \
    --to=david@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=azpijr@gmail.com \
    --cc=lance.yang@linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=muchun.song@linux.dev \
    --cc=osalvador@suse.de \
    --cc=qi.zheng@linux.dev \
    --cc=zhengqi.arch@bytedance.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®