[PATCH v4 2/6] KVM: arm64: Implement __kvm_tlb_flush_vmid_range()

[Marc Zyngier]

On Fri, 19 May 2023 01:52:27 +0100,
Raghavendra Rao Ananta <rananta at google.com> wrote:
> 
> Define  __kvm_tlb_flush_vmid_range() (for VHE and nVHE)
> to flush a range of stage-2 page-tables using IPA in one go.
> If the system supports FEAT_TLBIRANGE, the following patches
> would conviniently replace global TLBI such as vmalls12e1is
> in the map, unmap, and dirty-logging paths with ripas2e1is
> instead.
> 
> Signed-off-by: Raghavendra Rao Ananta <rananta at google.com>
> ---
>  arch/arm64/include/asm/kvm_asm.h   |  3 +++
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c | 11 +++++++++
>  arch/arm64/kvm/hyp/nvhe/tlb.c      | 39 ++++++++++++++++++++++++++++++
>  arch/arm64/kvm/hyp/vhe/tlb.c       | 35 +++++++++++++++++++++++++++
>  4 files changed, 88 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 43c3bc0f9544d..33352d9399e32 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -79,6 +79,7 @@ enum __kvm_host_smccc_func {
>  	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
> +	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,

nit: please keep this close to the other TLB operations.

>  };
>  
>  #define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
> @@ -225,6 +226,8 @@ extern void __kvm_flush_vm_context(void);
>  extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
>  extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
>  				     int level);
> +extern void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
> +					phys_addr_t start, phys_addr_t end);
>  extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
>  
>  extern void __kvm_timer_set_cntvoff(u64 cntvoff);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 728e01d4536b0..81d30737dc7c9 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -125,6 +125,16 @@ static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt)
>  	__kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level);
>  }
>  
> +static void
> +handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
> +{
> +	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
> +	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
> +	DECLARE_REG(phys_addr_t, end, host_ctxt, 3);
> +
> +	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, end);
> +}
> +
>  static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
>  {
>  	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
> @@ -315,6 +325,7 @@ static const hcall_t host_hcall[] = {
>  	HANDLE_FUNC(__kvm_vcpu_run),
>  	HANDLE_FUNC(__kvm_flush_vm_context),
>  	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
> +	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
>  	HANDLE_FUNC(__kvm_tlb_flush_vmid),
>  	HANDLE_FUNC(__kvm_flush_cpu_context),
>  	HANDLE_FUNC(__kvm_timer_set_cntvoff),
> diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
> index 978179133f4b9..d4ea549c4b5c4 100644
> --- a/arch/arm64/kvm/hyp/nvhe/tlb.c
> +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
> @@ -130,6 +130,45 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
>  	__tlb_switch_to_host(&cxt);
>  }
>  
> +void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
> +				phys_addr_t start, phys_addr_t end)
> +{
> +	struct tlb_inv_context cxt;
> +	unsigned long pages, stride;
> +
> +	/*
> +	 * Since the range of addresses may not be mapped at
> +	 * the same level, assume the worst case as PAGE_SIZE
> +	 */
> +	stride = PAGE_SIZE;
> +	start = round_down(start, stride);
> +	end = round_up(end, stride);
> +	pages = (end - start) >> PAGE_SHIFT;
> +
> +	if (!system_supports_tlb_range() || pages >= MAX_TLBI_RANGE_PAGES) {
> +		__kvm_tlb_flush_vmid(mmu);
> +		return;

Why do we give up on "pages >= MAX_TLBI_RANGE_PAGES"? I see no
rationale for it in the patch. My understanding is that this is the
maximum representable as a range, in which case this is a programming
error.

Or are you *on purpose* making the two equivalent?

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.