Currently, ARCH_WANTS_THP_SWAP was limited to 4K page size ARM64 kernels, but large folios requiring swapping also exist in other page size configurations (e.g. 64K). Without this config, large folios in these kernels cannot be swapped out. Here we enable ARCH_WANTS_THP_SWAP for all ARM64 page sizes.

I no longer recall why this was not enabled for sizes other than 4 KB in commit d0637c505f8a ("arm64: enable THP_SWAP for arm64"), but it appears to be fine, and the swap cluster size should also be more friendly to PMD alignment. #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 #define swap_entry_order(order) 0 #endif

Thank you very much for taking the time to review this patch during the holiday. Wishing you a happy holiday as well!

I appreciate you pointing out this optimization. We initially noticed the issue because, on ARM64 kernels with 64K page size, if large folios are used in shmem, they cannot be swapped out as a whole during shmem_writeout() due to the config limitation,
and are forced to split instead—which is something we wanted to avoid.

It seems that this change will help enable better swap operations for large folios. Thank you again for your feedback!

Signed-off-by: Weilin Tong <tongweilin@linux.alibaba.com> --- arch/arm64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 93173f0a09c7..58f7b4405f81 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -120,7 +120,7 @@ config ARM64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_EXECMEM_LATE select ARCH_WANTS_NO_INSTR - select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES + select ARCH_WANTS_THP_SWAP select ARCH_HAS_UBSAN select ARM_AMBA select ARM_ARCH_TIMER -- 2.43.7