From: "Barry Song (Xiaomi)" Allow arch_vmap_pte_range_map_size to batch across multiple CONT_PTE blocks, reducing both PTE setup and TLB flush iterations. For CONT_PTE_SIZE-aligned ranges, return a power-of-two mapping size that may cover multiple CONT_PTE blocks, capped below PMD_SIZE. These sizes are vmalloc mapping spans, not HugeTLB hstate sizes. Signed-off-by: Barry Song (Xiaomi) Signed-off-by: Wen Jiang Tested-by: Xueyuan Chen Tested-by: Leo Yan Reviewed-by: Dev Jain --- arch/arm64/include/asm/vmalloc.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h index 4ec1acd3c1b34..d665f9d687422 100644 --- a/arch/arm64/include/asm/vmalloc.h +++ b/arch/arm64/include/asm/vmalloc.h @@ -23,10 +23,14 @@ static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, u64 pfn, unsigned int max_page_shift) { + unsigned long size; + /* * If the block is at least CONT_PTE_SIZE in size, and is naturally * aligned in both virtual and physical space, then we can pte-map the * block using the PTE_CONT bit for more efficient use of the TLB. + * The returned mapping size may cover multiple CONT_PTE_SIZE blocks, + * capped below PMD_SIZE. */ if (max_page_shift < CONT_PTE_SHIFT) return PAGE_SIZE; @@ -40,7 +44,9 @@ static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, if (!IS_ALIGNED(PFN_PHYS(pfn), CONT_PTE_SIZE)) return PAGE_SIZE; - return CONT_PTE_SIZE; + size = min3(end - addr, 1UL << max_page_shift, PMD_SIZE >> 1); + size = rounddown_pow_of_two(size); + return size; } #define arch_vmap_pte_range_unmap_size arch_vmap_pte_range_unmap_size -- 2.34.1