Because hypervisors may need to create HPTs without knowing the guest page size, the smallest used page-size (4k) may be chosen, resulting in a HPT that is possibly bigger than needed.
On a guest with bigger page-sizes, the amount of entries for HTP may be too high, causing the guest to ask for a HPT resize-down on the first hotplug. This becomes a problem when HPT resize-down fails, and causes the HPT resize to be performed on every LMB added, until HPT size is compatible to guest memory size, causing a major slowdown. So, avoiding HPT resizing-down on hot-add significantly improves memory hotplug times. As an example, hotplugging 256GB on a 129GB guest took 710s without this patch, and 21s after applied. Signed-off-by: Leonardo Bras <leobra...@gmail.com> --- arch/powerpc/mm/book3s64/hash_utils.c | 36 ++++++++++++++++----------- 1 file changed, 21 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 73b06adb6eeb..cfb3ec164f56 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -794,7 +794,7 @@ static unsigned long __init htab_get_table_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG -static int resize_hpt_for_hotplug(unsigned long new_mem_size) +static int resize_hpt_for_hotplug(unsigned long new_mem_size, bool shrinking) { unsigned target_hpt_shift; @@ -803,19 +803,25 @@ static int resize_hpt_for_hotplug(unsigned long new_mem_size) target_hpt_shift = htab_shift_for_mem_size(new_mem_size); - /* - * To avoid lots of HPT resizes if memory size is fluctuating - * across a boundary, we deliberately have some hysterisis - * here: we immediately increase the HPT size if the target - * shift exceeds the current shift, but we won't attempt to - * reduce unless the target shift is at least 2 below the - * current shift - */ - if (target_hpt_shift > ppc64_pft_size || - target_hpt_shift < ppc64_pft_size - 1) - return mmu_hash_ops.resize_hpt(target_hpt_shift); + if (shrinking) { - return 0; + /* + * To avoid lots of HPT resizes if memory size is fluctuating + * across a boundary, we deliberately have some hysterisis + * here: we immediately increase the HPT size if the target + * shift exceeds the current shift, but we won't attempt to + * reduce unless the target shift is at least 2 below the + * current shift + */ + + if (target_hpt_shift >= ppc64_pft_size - 1) + return 0; + + } else if (target_hpt_shift <= ppc64_pft_size) { + return 0; + } + + return mmu_hash_ops.resize_hpt(target_hpt_shift); } int hash__create_section_mapping(unsigned long start, unsigned long end, @@ -828,7 +834,7 @@ int hash__create_section_mapping(unsigned long start, unsigned long end, return -1; } - resize_hpt_for_hotplug(memblock_phys_mem_size()); + resize_hpt_for_hotplug(memblock_phys_mem_size(), false); rc = htab_bolt_mapping(start, end, __pa(start), pgprot_val(prot), mmu_linear_psize, @@ -847,7 +853,7 @@ int hash__remove_section_mapping(unsigned long start, unsigned long end) int rc = htab_remove_mapping(start, end, mmu_linear_psize, mmu_kernel_ssize); - if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC) + if (resize_hpt_for_hotplug(memblock_phys_mem_size(), true) == -ENOSPC) pr_warn("Hash collision while resizing HPT\n"); return rc; -- 2.29.2