[RFC Part2 PATCH 30/30] KVM: X86: Add support to handle the RMP nested page fault

[Brijesh Singh]

Follow the recommendation from APM2 section 15.36.10 and 15.36.11 to
resolve the RMP violation encountered during the NPT table walk.

Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Joerg Roedel <jroedel@xxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: "Peter Zijlstra (Intel)" <peterz@xxxxxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Cc: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Cc: Wanpeng Li <wanpengli@xxxxxxxxxxx>
Cc: Jim Mattson <jmattson@xxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: kvm@xxxxxxxxxxxxxxx
Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/mmu/mmu.c          | 20 ++++++++++++
 arch/x86/kvm/svm/sev.c          | 57 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  2 ++
 5 files changed, 82 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5ea584606885..79dec4f93808 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1311,6 +1311,8 @@ struct kvm_x86_ops {
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 	int (*get_tdp_max_page_level)(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level);
+	int (*handle_rmp_page_fault)(struct kvm_vcpu *vcpu, gpa_t gpa, kvm_pfn_t pfn,
+			int level, u64 error_code);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1e057e046ca4..ec396169706f 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5105,6 +5105,18 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
 
+static int handle_rmp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
+{
+	kvm_pfn_t pfn;
+	int level;
+
+	if (unlikely(!kvm_mmu_get_tdp_walk(vcpu, gpa, &pfn, &level)))
+		return RET_PF_RETRY;
+
+	kvm_x86_ops.handle_rmp_page_fault(vcpu, gpa, pfn, level, error_code);
+	return RET_PF_RETRY;
+}
+
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
@@ -5121,6 +5133,14 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 			goto emulate;
 	}
 
+	if (unlikely(error_code & PFERR_GUEST_RMP_MASK)) {
+		r = handle_rmp_page_fault(vcpu, cr2_or_gpa, error_code);
+		if (r == RET_PF_RETRY)
+			return 1;
+		else
+			return r;
+	}
+
 	if (r == RET_PF_INVALID) {
 		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
 					  lower_32_bits(error_code), false);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 35e7a7bbf878..dbb4f15de9ba 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2924,3 +2924,60 @@ int sev_get_tdp_max_page_level(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level)
 
 	return min_t(uint32_t, level, max_level);
 }
+
+int snp_handle_rmp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, kvm_pfn_t pfn,
+			      int level, u64 error_code)
+{
+	int rlevel, rc = 0;
+	rmpentry_t *e;
+	bool private;
+	gfn_t gfn;
+
+	e = lookup_page_in_rmptable(pfn_to_page(pfn), &rlevel);
+	if (!e)
+		return 1;
+
+	private = !!(error_code & PFERR_GUEST_ENC_MASK);
+
+	/*
+	 * See APM section 15.36.11 on how to handle the RMP fault for the large pages.
+	 *
+	 *  npt	     rmp    access      action
+	 *  --------------------------------------------------
+	 *  4k       2M     C=1       psmash
+	 *  x        x      C=1       if page is not private then add a new RMP entry
+	 *  x        x      C=0       if page is private then make it shared
+	 *  2M       4k     C=x       zap
+	 */
+	if ((error_code & PFERR_GUEST_SIZEM_MASK) ||
+	    ((level == PG_LEVEL_4K) && (rlevel == PG_LEVEL_2M) && private)) {
+		rc = snp_rmptable_psmash(vcpu, pfn);
+		goto zap_gfn;
+	}
+
+	/*
+	 * If it's a private access, and the page is not assigned in the RMP table, create a
+	 * new private RMP entry.
+	 */
+	if (!rmpentry_assigned(e) && private) {
+		rc = snp_make_page_private(vcpu, gpa, pfn, PG_LEVEL_4K);
+		goto zap_gfn;
+	}
+
+	/*
+	 * If it's a shared access, then make the page shared in the RMP table.
+	 */
+	if (rmpentry_assigned(e) && !private)
+		rc = snp_make_page_shared(vcpu, gpa, pfn, PG_LEVEL_4K);
+
+zap_gfn:
+	/*
+	 * Now that we have 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(vcpu->kvm, gfn, gfn + 512);
+
+	return 0;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 73259a3564eb..ab30c3e3956f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4564,6 +4564,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
 	.get_tdp_max_page_level = sev_get_tdp_max_page_level,
+	.handle_rmp_page_fault = snp_handle_rmp_page_fault,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9fcfceb4d71e..eacae54de9b5 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -637,6 +637,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
 void sev_snp_init_vmcb(struct vcpu_svm *svm);
 int sev_get_tdp_max_page_level(struct kvm_vcpu *vcpu, gpa_t gpa, int max_level);
+int snp_handle_rmp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, kvm_pfn_t pfn,
+			      int level, u64 error_code);
 
 /* vmenter.S */
 
-- 
2.17.1