[PATCH v6 16/18] kvm: arm64: Set a limit on the IPA size

[eric.auger@redhat.com (Auger Eric)]

Hi,

On 9/26/18 6:32 PM, Suzuki K Poulose wrote:
> So far we have restricted the IPA size of the VM to the default
> value (40bits). Now that we can manage the IPA size per VM and
> support dynamic stage2 page tables, we can allow VMs to have
> larger IPA. This patch introduces a the maximum IPA size
> supported on the host.
nit: a the -> computes the max IPA size that can be supported for any VM ?

Besides
Reviewed-by: Eric Auger <eric.auger@redhat.com>

Thanks

Eric

 This is decided by the following factors :
> 
>  1) Maximum PARange supported by the CPUs - This can be inferred
>     from the system wide safe value.
>  2) Maximum PA size supported by the host kernel (48 vs 52)
>  3) Number of levels in the host page table (as we base our
>     stage2 tables on the host table helpers).
> 
> Since the stage2 page table code is dependent on the stage1
> page table, we always ensure that :
> 
>   Number of Levels at Stage1 >= Number of Levels at Stage2
> 
> So we limit the IPA to make sure that the above condition
> is satisfied. This will affect the following combinations
> of VA_BITS and IPA for different page sizes.
> 
>   Host configuration | Unsupported IPA ranges
>   39bit VA, 4K       | [44, 48]
>   36bit VA, 16K      | [41, 48]
>   42bit VA, 64K      | [47, 52]
> 
> Supporting the above combinations need independent stage2
> page table manipulation code, which would need substantial
> changes. We could purse the solution independently and
> switch the page table code once we have it ready.
> 
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Marc Zyngier <marc.zyngier@arm.com>
> Cc: Christoffer Dall <cdall@kernel.org>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
> ---
> Changes since v5:
>  - Don't raise the IPA limit to 40bits
>  - Print the KVM IPA limit, WARN if the limit is less than the
>    default size. Drop the per-CPU PARange check
>  - If the limit was reduced due to kernel configuration,
>    report the limiting factor. i.e, kernel virtual vs physical
>    address limit.
> Changes since V2:
>  - Restrict the IPA size to limit the number of page table
>    levels in stage2 to that of stage1 or less.
> ---
>  arch/arm/include/asm/kvm_mmu.h    |  2 ++
>  arch/arm64/include/asm/kvm_host.h | 12 +++------
>  arch/arm64/kvm/reset.c            | 43 +++++++++++++++++++++++++++++++
>  virt/kvm/arm/arm.c                |  2 ++
>  4 files changed, 50 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
> index 12ae5fbbcf01..5ad1a54f98dc 100644
> --- a/arch/arm/include/asm/kvm_mmu.h
> +++ b/arch/arm/include/asm/kvm_mmu.h
> @@ -358,6 +358,8 @@ static inline int hyp_map_aux_data(void)
>  
>  #define kvm_phys_to_vttbr(addr)		(addr)
>  
> +static inline void kvm_set_ipa_limit(void) {}
> +
>  #endif	/* !__ASSEMBLY__ */
>  
>  #endif /* __ARM_KVM_MMU_H__ */
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index 5ecd457bce7d..f008f8866b2a 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -442,15 +442,7 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
>  int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
>  			       struct kvm_device_attr *attr);
>  
> -static inline void __cpu_init_stage2(void)
> -{
> -	u32 ps;
> -
> -	/* Sanity check for minimum IPA size support */
> -	ps = id_aa64mmfr0_parange_to_phys_shift(read_sysreg(id_aa64mmfr0_el1) & 0x7);
> -	WARN_ONCE(ps < 40,
> -		  "PARange is %d bits, unsupported configuration!", ps);
> -}
> +static inline void __cpu_init_stage2(void) {}
>  
>  /* Guest/host FPSIMD coordination helpers */
>  int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
> @@ -513,6 +505,8 @@ static inline int kvm_arm_have_ssbd(void)
>  void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
>  void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
>  
> +void kvm_set_ipa_limit(void);
> +
>  #define __KVM_HAVE_ARCH_VM_ALLOC
>  struct kvm *kvm_arch_alloc_vm(void);
>  void kvm_arch_free_vm(struct kvm *kvm);
> diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
> index 2bf41e007390..96b3f50101bc 100644
> --- a/arch/arm64/kvm/reset.c
> +++ b/arch/arm64/kvm/reset.c
> @@ -34,6 +34,9 @@
>  #include <asm/kvm_coproc.h>
>  #include <asm/kvm_mmu.h>
>  
> +/* Maximum phys_shift supported for any VM on this host */
> +static u32 kvm_ipa_limit;
> +
>  /*
>   * ARMv8 Reset Values
>   */
> @@ -135,6 +138,46 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
>  	return kvm_timer_vcpu_reset(vcpu);
>  }
>  
> +void kvm_set_ipa_limit(void)
> +{
> +	unsigned int ipa_max, pa_max, va_max, parange;
> +
> +	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 0x7;
> +	pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
> +
> +	/* Clamp the IPA limit to the PA size supported by the kernel */
> +	ipa_max = (pa_max > PHYS_MASK_SHIFT) ? PHYS_MASK_SHIFT : pa_max;
> +	/*
> +	 * Since our stage2 table is dependent on the stage1 page table code,
> +	 * we must always honor the following condition:
> +	 *
> +	 *  Number of levels in Stage1 >= Number of levels in Stage2.
> +	 *
> +	 * So clamp the ipa limit further down to limit the number of levels.
> +	 * Since we can concatenate upto 16 tables at entry level, we could
> +	 * go upto 4bits above the maximum VA addressible with the current
> +	 * number of levels.
> +	 */
> +	va_max = PGDIR_SHIFT + PAGE_SHIFT - 3;
> +	va_max += 4;
> +
> +	if (va_max < ipa_max)
> +		ipa_max = va_max;
> +
> +	/*
> +	 * If the final limit is lower than the real physical address
> +	 * limit of the CPUs, report the reason.
> +	 */
> +	if (ipa_max < pa_max)
> +		pr_info("kvm: Limiting the IPA size due to kernel %s Address limit\n",
> +			(va_max < pa_max) ? "Virtual" : "Physical");
> +
> +	WARN(ipa_max < KVM_PHYS_SHIFT,
> +	     "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
> +	kvm_ipa_limit = ipa_max;
> +	kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
> +}
> +
>  /*
>   * Configure the VTCR_EL2 for this VM. The VTCR value is common
>   * across all the physical CPUs on the system. We use system wide
> diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
> index 43e716bc3f08..631f9a3ad99a 100644
> --- a/virt/kvm/arm/arm.c
> +++ b/virt/kvm/arm/arm.c
> @@ -1413,6 +1413,8 @@ static int init_common_resources(void)
>  	kvm_vmid_bits = kvm_get_vmid_bits();
>  	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
>  
> +	kvm_set_ipa_limit();
> +
>  	return 0;
>  }
>  
>