Re: [PATCH Part2 v5 41/45] KVM: SVM: Add support to handle the RMP nested page fault

[Dr. David Alan Gilbert]

* Brijesh Singh (brijesh.singh@xxxxxxx) wrote:
> When SEV-SNP is enabled in the guest, the hardware places restrictions on
> all memory accesses based on the contents of the RMP table. When hardware
> encounters RMP check failure caused by the guest memory access it raises
> the #NPF. The error code contains additional information on the access
> type. See the APM volume 2 for additional information.
> 
> Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
> ---
>  arch/x86/kvm/svm/sev.c | 76 ++++++++++++++++++++++++++++++++++++++++++
>  arch/x86/kvm/svm/svm.c | 14 +++++---
>  arch/x86/kvm/svm/svm.h |  1 +
>  3 files changed, 87 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index 65b578463271..712e8907bc39 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -3651,3 +3651,79 @@ void sev_post_unmap_gfn(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int token)
>  
>  	srcu_read_unlock(&sev->psc_srcu, token);
>  }
> +
> +void handle_rmp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
> +{
> +	int rmp_level, npt_level, rc, assigned;
> +	struct kvm *kvm = vcpu->kvm;
> +	gfn_t gfn = gpa_to_gfn(gpa);
> +	bool need_psc = false;
> +	enum psc_op psc_op;
> +	kvm_pfn_t pfn;
> +	bool private;
> +
> +	write_lock(&kvm->mmu_lock);
> +
> +	if (unlikely(!kvm_mmu_get_tdp_walk(vcpu, gpa, &pfn, &npt_level)))
> +		goto unlock;
> +
> +	assigned = snp_lookup_rmpentry(pfn, &rmp_level);
> +	if (unlikely(assigned < 0))
> +		goto unlock;
> +
> +	private = !!(error_code & PFERR_GUEST_ENC_MASK);
> +
> +	/*
> +	 * If the fault was due to size mismatch, or NPT and RMP page level's
> +	 * are not in sync, then use PSMASH to split the RMP entry into 4K.
> +	 */
> +	if ((error_code & PFERR_GUEST_SIZEM_MASK) ||
> +	    (npt_level == PG_LEVEL_4K && rmp_level == PG_LEVEL_2M && private)) {
> +		rc = snp_rmptable_psmash(kvm, pfn);
> +		if (rc)
> +			pr_err_ratelimited("psmash failed, gpa 0x%llx pfn 0x%llx rc %d\n",
> +					   gpa, pfn, rc);
> +		goto out;
> +	}
> +
> +	/*
> +	 * If it's a private access, and the page is not assigned in the
> +	 * RMP table, create a new private RMP entry. This can happen if
> +	 * guest did not use the PSC VMGEXIT to transition the page state
> +	 * before the access.
> +	 */
> +	if (!assigned && private) {
> +		need_psc = 1;
> +		psc_op = SNP_PAGE_STATE_PRIVATE;
> +		goto out;
> +	}
> +
> +	/*
> +	 * If it's a shared access, but the page is private in the RMP table
> +	 * then make the page shared in the RMP table. This can happen if
> +	 * the guest did not use the PSC VMGEXIT to transition the page
> +	 * state before the access.
> +	 */
> +	if (assigned && !private) {
> +		need_psc = 1;
> +		psc_op = SNP_PAGE_STATE_SHARED;
> +	}
> +
> +out:
> +	write_unlock(&kvm->mmu_lock);
> +
> +	if (need_psc)
> +		rc = __snp_handle_page_state_change(vcpu, psc_op, gpa, PG_LEVEL_4K);

That 'rc' never goes anywhere - should it?

> +	/*
> +	 * The fault handler has updated the RMP pagesize, zap the existing
> +	 * rmaps for large entry ranges so that nested page table gets rebuilt
> +	 * with the updated RMP pagesize.
> +	 */
> +	gfn = gpa_to_gfn(gpa) & ~(KVM_PAGES_PER_HPAGE(PG_LEVEL_2M) - 1);
> +	kvm_zap_gfn_range(kvm, gfn, gfn + PTRS_PER_PMD);
> +	return;
> +
> +unlock:
> +	write_unlock(&kvm->mmu_lock);
> +}
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 3784d389247b..3ba62f21b113 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -1933,15 +1933,21 @@ static int pf_interception(struct kvm_vcpu *vcpu)
>  static int npf_interception(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_svm *svm = to_svm(vcpu);
> +	int rc;
>  
>  	u64 fault_address = svm->vmcb->control.exit_info_2;
>  	u64 error_code = svm->vmcb->control.exit_info_1;
>  
>  	trace_kvm_page_fault(fault_address, error_code);
> -	return kvm_mmu_page_fault(vcpu, fault_address, error_code,
> -			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
> -			svm->vmcb->control.insn_bytes : NULL,
> -			svm->vmcb->control.insn_len);
> +	rc = kvm_mmu_page_fault(vcpu, fault_address, error_code,
> +				static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
> +				svm->vmcb->control.insn_bytes : NULL,
> +				svm->vmcb->control.insn_len);

If kvm_mmu_page_fault failed, (rc!=0) do you still want to call your
handler?

Dave

> +	if (error_code & PFERR_GUEST_RMP_MASK)
> +		handle_rmp_page_fault(vcpu, fault_address, error_code);
> +
> +	return rc;
>  }
>  
>  static int db_interception(struct kvm_vcpu *vcpu)
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index ff91184f9b4a..280072995306 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -626,6 +626,7 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
>  void sev_rmp_page_level_adjust(struct kvm *kvm, kvm_pfn_t pfn, int *level);
>  int sev_post_map_gfn(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int *token);
>  void sev_post_unmap_gfn(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int token);
> +void handle_rmp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
>  
>  /* vmenter.S */
>  
> -- 
> 2.17.1
> 
> 
-- 
Dr. David Alan Gilbert / dgilbert@xxxxxxxxxx / Manchester, UK