Re: [PATCH 5/6] KVM: x86: Implement kvm_arch_vcpu_pre_fault_memory()

[Xiaoyao Li <xiaoyao.li@intel.com>]

On 4/19/2024 4:59 PM, Paolo Bonzini wrote:
> From: Isaku Yamahata <isaku.yamahata@intel.com>
> 
> Wire KVM_PRE_FAULT_MEMORY ioctl to __kvm_mmu_do_page_fault() to populate guest
> memory.  It can be called right after KVM_CREATE_VCPU creates a vCPU,
> since at that point kvm_mmu_create() and kvm_init_mmu() are called and
> the vCPU is ready to invoke the KVM page fault handler.
> 
> The helper function kvm_mmu_map_tdp_page take care of the logic to
> process RET_PF_* return values and convert them to success or errno.
> 
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> Message-ID: <9b866a0ae7147f96571c439e75429a03dcb659b6.1712785629.git.isaku.yamahata@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   arch/x86/kvm/Kconfig   |  1 +
>   arch/x86/kvm/mmu/mmu.c | 72 ++++++++++++++++++++++++++++++++++++++++++
>   arch/x86/kvm/x86.c     |  3 ++
>   3 files changed, 76 insertions(+)
> 
> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> index 7632fe6e4db9..54c155432793 100644
> --- a/arch/x86/kvm/Kconfig
> +++ b/arch/x86/kvm/Kconfig
> @@ -44,6 +44,7 @@ config KVM
>   	select KVM_VFIO
>   	select HAVE_KVM_PM_NOTIFIER if PM
>   	select KVM_GENERIC_HARDWARE_ENABLING
> +	select KVM_GENERIC_PRE_FAULT_MEMORY
>   	help
>   	  Support hosting fully virtualized guest machines using hardware
>   	  virtualization extensions.  You will need a fairly recent
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 10e90788b263..a045b23964c0 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -4647,6 +4647,78 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>   	return direct_page_fault(vcpu, fault);
>   }
>   
> +static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
> +		     u8 *level)
> +{
> +	int r;
> +
> +	/* Restrict to TDP page fault. */
> +	if (vcpu->arch.mmu->page_fault != kvm_tdp_page_fault)
> +		return -EOPNOTSUPP;
> +
> +retry:
> +	r = __kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level);
> +	if (r < 0)
> +		return r;
> +
> +	switch (r) {
> +	case RET_PF_RETRY:
> +		if (signal_pending(current))
> +			return -EINTR;
> +		cond_resched();
> +		goto retry;
> +
> +	case RET_PF_FIXED:
> +	case RET_PF_SPURIOUS:
> +		break;
> +
> +	case RET_PF_EMULATE:
> +		return -ENOENT;
> +
> +	case RET_PF_CONTINUE:
> +	case RET_PF_INVALID:
> +	default:
> +		WARN_ON_ONCE(r);
> +		return -EIO;

Need to update patch 1 for -EIO

> +	}
> +
> +	return 0;
> +}
> +
> +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
> +				    struct kvm_pre_fault_memory *range)
> +{
> +	u64 error_code = PFERR_GUEST_FINAL_MASK;
> +	u8 level = PG_LEVEL_4K;
> +	u64 end;
> +	int r;
> +
> +	/*
> +	 * reload is efficient when called repeatedly, so we can do it on
> +	 * every iteration.
> +	 */
> +	kvm_mmu_reload(vcpu);
> +
> +	if (kvm_arch_has_private_mem(vcpu->kvm) &&
> +	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
> +		error_code |= PFERR_PRIVATE_ACCESS;
> +
> +	/*
> +	 * Shadow paging uses GVA for kvm page fault, so restrict to
> +	 * two-dimensional paging.
> +	 */
> +	r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
> +	if (r < 0)
> +		return r;
> +
> +	/*
> +	 * If the mapping that covers range->gpa can use a huge page, it
> +	 * may start below it or end after range->gpa + range->size.
> +	 */
> +	end = (range->gpa & KVM_HPAGE_MASK(level)) + KVM_HPAGE_SIZE(level);
> +	return min(range->size, end - range->gpa);
> +}
> +
>   static void nonpaging_init_context(struct kvm_mmu *context)
>   {
>   	context->page_fault = nonpaging_page_fault;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 83b8260443a3..619ad713254e 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4715,6 +4715,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>   	case KVM_CAP_MEMORY_FAULT_INFO:
>   		r = 1;
>   		break;
> +	case KVM_CAP_PRE_FAULT_MEMORY:
> +		r = tdp_enabled;
> +		break;
>   	case KVM_CAP_EXIT_HYPERCALL:
>   		r = KVM_EXIT_HYPERCALL_VALID_MASK;
>   		break;