On Thu, May 1, 2025 at 7:24 AM Zi Yan [off-list ref] wrote:

On 1 May 2025, at 1:25, Juan Yescas wrote:

quoted

Problem: On large page size configurations (16KiB, 64KiB), the CMA
alignment requirement (CMA_MIN_ALIGNMENT_BYTES) increases considerably,
and this causes the CMA reservations to be larger than necessary.
This means that system will have less available MIGRATE_UNMOVABLE and
MIGRATE_RECLAIMABLE page blocks since MIGRATE_CMA can't fallback to them.

The CMA_MIN_ALIGNMENT_BYTES increases because it depends on
MAX_PAGE_ORDER which depends on ARCH_FORCE_MAX_ORDER. The value of
ARCH_FORCE_MAX_ORDER increases on 16k and 64k kernels.

For example, the CMA alignment requirement when:

- CONFIG_ARCH_FORCE_MAX_ORDER default value is used
- CONFIG_TRANSPARENT_HUGEPAGE is set:

PAGE_SIZE | MAX_PAGE_ORDER | pageblock_order | CMA_MIN_ALIGNMENT_BYTES
-----------------------------------------------------------------------
   4KiB   |      10        |      10         |  4KiB * (2 ^ 10)  =  4MiB
  16Kib   |      11        |      11         | 16KiB * (2 ^ 11) =  32MiB
  64KiB   |      13        |      13         | 64KiB * (2 ^ 13) = 512MiB

There are some extreme cases for the CMA alignment requirement when:

- CONFIG_ARCH_FORCE_MAX_ORDER maximum value is set
- CONFIG_TRANSPARENT_HUGEPAGE is NOT set:
- CONFIG_HUGETLB_PAGE is NOT set

PAGE_SIZE | MAX_PAGE_ORDER | pageblock_order |  CMA_MIN_ALIGNMENT_BYTES
------------------------------------------------------------------------
   4KiB   |      15        |      15         |  4KiB * (2 ^ 15) = 128MiB
  16Kib   |      13        |      13         | 16KiB * (2 ^ 13) = 128MiB
  64KiB   |      13        |      13         | 64KiB * (2 ^ 13) = 512MiB

This affects the CMA reservations for the drivers. If a driver in a
4KiB kernel needs 4MiB of CMA memory, in a 16KiB kernel, the minimal
reservation has to be 32MiB due to the alignment requirements:

reserved-memory {
    ...
    cma_test_reserve: cma_test_reserve {
        compatible = "shared-dma-pool";
        size = <0x0 0x400000>; /* 4 MiB */
        ...
    };
};

reserved-memory {
    ...
    cma_test_reserve: cma_test_reserve {
        compatible = "shared-dma-pool";
        size = <0x0 0x2000000>; /* 32 MiB */
        ...
    };
};

Solution: Add a new config ARCH_FORCE_PAGE_BLOCK_ORDER that
allows to set the page block order. The maximum page block
order will be given by ARCH_FORCE_MAX_ORDER.

Why not use a boot time parameter to change page block order?

That is a good option. The main tradeoff is:

- The bootloader would have to be updated on the devices to pass the right
pageblock_order value depending on the kernel page size. Currently,
We can boot 4k/16k kernels without any change in the bootloader.

Otherwise, you will need to maintain an additional kernel
binary for your use case.

Unfortunately, we still need 2 kernel binaries, one for 4k and another for 16k.
There are several data structures that are aligned at compile time based on the
PAGE_SIZE (__aligned(PAGE_SIZE)) that makes it difficult to have only one
binary.

For example:

static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE)
__ro_after_init,
 kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init;

https://elixir.bootlin.com/linux/v6.14.4/source/arch/arm64/mm/mmu.c#L780

Thanks
Juan

--
Best Regards,
Yan, Zi