[RFC PATCH v7 25/28] KVM: arm64: at: Use callback for reading descriptor

[Lorenzo Stoakes (ARM)]

On Thu, Sep 03, 2026 at 05:06:20PM +0100, Alexandru Elisei wrote:
> Allow callers of __kvm_translate_va() to use a custom function for reading
> the translation table descriptor from guest memory. This will be useful for
> handling stage 2 faults reported by SPE, to map the stage 1 translation
> tables at stage 2.
>
> Suggested-by: James Morse <james.morse at arm.com>
> Signed-off-by: Alexandru Elisei <alexandru.elisei at arm.com>

This is nice, only some nits here really. So, with those addressed, LGTM and:

Reviewed-by: Lorenzo Stoakes (ARM) <ljs at kernel.org>

> ---
>  arch/arm64/include/asm/kvm_nested.h |  7 +++++++
>  arch/arm64/kvm/at.c                 | 22 ++++++++++++++--------
>  arch/arm64/kvm/nested.c             |  7 ++++---
>  3 files changed, 25 insertions(+), 11 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
> index 1ed708335809..d812137dcd9e 100644
> --- a/arch/arm64/include/asm/kvm_nested.h
> +++ b/arch/arm64/include/asm/kvm_nested.h
> @@ -350,8 +350,15 @@ struct s1_walk_filter {
>  	void	*priv;
>  };
>
> +typedef int (*read_desc_fn)(struct kvm_vcpu *, u64, u64 *,
> +			    struct s1_walk_info *);

NIT: This seems a little too generic I think.

Other function pointer types in asm/kvm_*.h are kvm_pgtable_*_t, so perhaps
something like kvm_s1_read_desc_fn_t?

> +
> +int kvm_vcpu_read_s1_desc(struct kvm_vcpu *vcpu, u64 pa, u64 *desc,
> +			  struct s1_walk_info *wi);
> +
>  struct s1_walk_info {
>  	struct s1_walk_filter	*filter;
> +	read_desc_fn		read_s1_desc;
>  	u64	     		baddr;
>  	enum trans_regime	regime;
>  	unsigned int		max_oa_bits;
> diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
> index 0926426b8798..6e77beced96c 100644
> --- a/arch/arm64/kvm/at.c
> +++ b/arch/arm64/kvm/at.c
> @@ -224,6 +224,9 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
>  	unsigned int stride, x;
>  	bool va55, tbi, lva, upper_range;
>
> +	if (!wi->read_s1_desc)
> +		return -EINVAL;
> +

This might be a little too cautious, all the callers are in arch/arm64/kvm so
maybe fine to assume the right thing is done?

If not then this should probably be a WARN_ON_ONCE() or something, as it would
be a bug in the kernel code.

>  	va55 = va & BIT(55);
>  	upper_range = va55 && wi->regime != TR_EL2;
>
> @@ -427,8 +430,8 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
>  	return -EFAULT;
>  }
>
> -static int kvm_read_s1_desc(struct kvm_vcpu *vcpu, u64 pa, u64 *desc,
> -			    struct s1_walk_info *wi)
> +int kvm_vcpu_read_s1_desc(struct kvm_vcpu *vcpu, u64 pa, u64 *desc,

Hmm, why rename it? Seems a bit out of place.

> +			  struct s1_walk_info *wi)
>  {
>  	u64 val;
>  	int r;
> @@ -513,7 +516,7 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
>  				return ret;
>  		}
>
> -		ret = kvm_read_s1_desc(vcpu, ipa, &desc, wi);
> +		ret = wi->read_s1_desc(vcpu, ipa, &desc, wi);
>  		if (ret) {
>  			fail_s1_walk(wr, ESR_ELx_FSC_SEA_TTW(level), false);
>  			return ret;
> @@ -1324,6 +1327,7 @@ static int handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr, u64 *par)
>  	bool perm_fail = false;
>  	int ret, idx;
>
> +	wi.read_s1_desc = kvm_vcpu_read_s1_desc;
>  	wi.regime = compute_translation_regime(vcpu, op);
>  	wi.as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W);
>  	wi.pan = (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) &&
> @@ -1657,9 +1661,10 @@ int __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
>  }
>
>  /*
> - * Translate a VA for a given EL in a given translation regime, with
> - * or without PAN. This requires wi->{regime, as_el0, pan} to be
> - * set. The rest of the wi and wr should be 0-initialised.
> + * Translate a VA for a given EL in a given translation regime, with or without
> + * PAN. This requires wi->{regime, as_el0, pan, read_s1_desc} to be set.
> + * Setting wi->filter is optional. The rest of the wi and wr should be
> + * 0-initialised.
>   */
>  int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
>  		       struct s1_walk_result *wr, u64 va)
> @@ -1716,8 +1721,9 @@ int __kvm_find_s1_desc_level(struct kvm_vcpu *vcpu, u64 va, u64 ipa, int *level)
>  			.fn	= match_s1_desc,
>  			.priv	= &dm,
>  		},
> -		.as_el0	= false,
> -		.pan	= false,
> +		.read_s1_desc	= kvm_vcpu_read_s1_desc,
> +		.as_el0		= false,
> +		.pan		= false,
>  	};
>  	struct s1_walk_result wr = {};
>  	int ret;
> diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
> index 17123f0b6dab..e3e71628f8c5 100644
> --- a/arch/arm64/kvm/nested.c
> +++ b/arch/arm64/kvm/nested.c
> @@ -1435,9 +1435,10 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
>  			invalidate_vncr(vcpu->kvm, vt);
>
>  		vt->wi = (struct s1_walk_info) {
> -			.regime	= TR_EL20,
> -			.as_el0	= false,
> -			.pan	= false,
> +			.read_s1_desc	= kvm_vcpu_read_s1_desc,
> +			.regime		= TR_EL20,
> +			.as_el0		= false,
> +			.pan		= false,
>  		};
>  		vt->wr = (struct s1_walk_result){};
>  	}
> --
> 2.43.0
>
>

--
Cheers, Lorenzo