Re: [PATCH RESEND v4 2/3] KVM: arm64: Introduce KVM_PGTABLE_WALK_SKIP_LEVEL* walk flags

[Suzuki K Poulose <suzuki.poulose@arm.com>]

On 06/11/2026 16:12, Leonardo Bras wrote:
> Add new walking flags KVM_PGTABLE_WALK_SKIP_LEVEL{0-3}.
> When used, they make the kvm_pgtable_walk() skip the given level, as well
> as levels higher than that.
> 
> Being able to skip levels substancially decreases the runtime of a

minor nit: substantially

> pagetable walk when the callback function does nothing on that level.
> 
> Signed-off-by: Leonardo Bras <leo.bras@arm.com>
> ---
>   arch/arm64/include/asm/kvm_pgtable.h | 14 ++++++++++++++
>   arch/arm64/kvm/hyp/pgtable.c         | 16 +++++++++++++---
>   2 files changed, 27 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> index 41a8687938eb..5f37ceef8d63 100644
> --- a/arch/arm64/include/asm/kvm_pgtable.h
> +++ b/arch/arm64/include/asm/kvm_pgtable.h
> @@ -311,31 +311,45 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
>    * @KVM_PGTABLE_WALK_SHARED:		Indicates the page-tables may be shared
>    *					with other software walkers.
>    * @KVM_PGTABLE_WALK_IGNORE_EAGAIN:	Don't terminate the walk early if
>    *					the walker returns -EAGAIN.
>    * @KVM_PGTABLE_WALK_SKIP_BBM_TLBI:	Visit and update table entries
>    *					without Break-before-make's
>    *					TLB invalidation.
>    * @KVM_PGTABLE_WALK_SKIP_CMO:		Visit and update table entries
>    *					without Cache maintenance
>    *					operations required.
> + * @KVM_PGTABLE_WALK_SKIP_LEVEL0:	Skip visiting level 0+ entries
> + * @KVM_PGTABLE_WALK_SKIP_LEVEL1:	Skip visiting level 1+ entries
> + * @KVM_PGTABLE_WALK_SKIP_LEVEL2:	Skip visiting level 2+ entries
> + * @KVM_PGTABLE_WALK_SKIP_LEVEL3:	Skip visiting level 3 entries
>    */
>   enum kvm_pgtable_walk_flags {
>   	KVM_PGTABLE_WALK_LEAF			= BIT(0),
>   	KVM_PGTABLE_WALK_TABLE_PRE		= BIT(1),
>   	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
>   	KVM_PGTABLE_WALK_SHARED			= BIT(3),
>   	KVM_PGTABLE_WALK_IGNORE_EAGAIN		= BIT(4),
>   	KVM_PGTABLE_WALK_SKIP_BBM_TLBI		= BIT(5),
>   	KVM_PGTABLE_WALK_SKIP_CMO		= BIT(6),
> +	/* SKIP_LEVEL* flags should not be split nor reordered */
> +	KVM_PGTABLE_WALK_SKIP_LEVEL0		= BIT(7),
> +	KVM_PGTABLE_WALK_SKIP_LEVEL1		= BIT(8),
> +	KVM_PGTABLE_WALK_SKIP_LEVEL2		= BIT(9),
> +	KVM_PGTABLE_WALK_SKIP_LEVEL3		= BIT(10),
>   };
>   
> +#define KVM_PGTABLE_WALK_SKIP_LEVELS 	(KVM_PGTABLE_WALK_SKIP_LEVEL0 | \
> +					 KVM_PGTABLE_WALK_SKIP_LEVEL1 | \
> +					 KVM_PGTABLE_WALK_SKIP_LEVEL2 | \
> +					 KVM_PGTABLE_WALK_SKIP_LEVEL3 )
> +
>   struct kvm_pgtable_visit_ctx {
>   	kvm_pte_t				*ptep;
>   	kvm_pte_t				old;
>   	void					*arg;
>   	struct kvm_pgtable_mm_ops		*mm_ops;
>   	u64					start;
>   	u64					addr;
>   	u64					end;
>   	s8					level;
>   	enum kvm_pgtable_walk_flags		flags;
> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> index 7a51f78b6446..80744478c810 100644
> --- a/arch/arm64/kvm/hyp/pgtable.c
> +++ b/arch/arm64/kvm/hyp/pgtable.c
> @@ -137,20 +137,27 @@ static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
>   	 * Ignore the return code altogether for walkers outside a fault handler
>   	 * (e.g. write protecting a range of memory) and chug along with the
>   	 * page table walk.
>   	 */
>   	if (r == -EAGAIN)
>   		return walker->flags & KVM_PGTABLE_WALK_IGNORE_EAGAIN;
>   
>   	return !r;
>   }
>   
> +static bool kvm_pgtable_skip_level(s8 level, enum kvm_pgtable_walk_flags flags)
> +{
> +	u32 skip = FIELD_GET(KVM_PGTABLE_WALK_SKIP_LEVELS, flags);
> +
> +	return unlikely(skip && level >= ffs(skip) - 1);
> +}
> +
>   static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
>   			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level);
>   
>   static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
>   				      struct kvm_pgtable_mm_ops *mm_ops,
>   				      kvm_pteref_t pteref, s8 level)
>   {
>   	enum kvm_pgtable_walk_flags flags = data->walker->flags;
>   	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
>   	struct kvm_pgtable_visit_ctx ctx = {
> @@ -185,35 +192,35 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
>   	 * into a newly installed or replaced table.
>   	 */
>   	if (reload) {
>   		ctx.old = READ_ONCE(*ptep);
>   		table = kvm_pte_table(ctx.old, level);
>   	}
>   
>   	if (!kvm_pgtable_walk_continue(data->walker, ret))
>   		return ret;
>   
> -	if (!table) {
> +	if (!table || kvm_pgtable_skip_level(level + 1, ctx.flags)) {
>   		data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
>   		data->addr += kvm_granule_size(level);
>   		goto out;
>   	}
>   
>   	childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops);
>   	ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1);
>   	if (!kvm_pgtable_walk_continue(data->walker, ret))
>   		return ret;
>   
> -	if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST)
> +out:
> +	if (table && ctx.flags & KVM_PGTABLE_WALK_TABLE_POST)
>   		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST);
>   
> -out:
>   	if (kvm_pgtable_walk_continue(data->walker, ret))
>   		return 0;
>   
>   	return ret;
>   }
>   
>   static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
>   			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level)
>   {
>   	u32 idx;
> @@ -242,20 +249,23 @@ static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_da
>   	u32 idx;
>   	int ret = 0;
>   	u64 limit = BIT(pgt->ia_bits);
>   
>   	if (data->addr > limit || data->end > limit)
>   		return -ERANGE;
>   
>   	if (!pgt->pgd)
>   		return -EINVAL;
>   
> +	if (kvm_pgtable_skip_level(pgt->start_level, data->walker->flags))
> +		return 0;
> +

Should we rather return an error here ? A walk skipping the start level,
is that any meaningful ?

Suzuki


>   	for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) {
>   		kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE];
>   
>   		ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level);
>   		if (ret)
>   			break;
>   	}
>   
>   	return ret;
>   }