[PATCH v2 3/3] KVM: arm64: Honour the requested IPA size under pKVM

[Fuad Tabba]

pKVM gives every VM the host's IPA limit, whatever size the VMM
requested with KVM_VM_TYPE_ARM_IPA_SIZE, so the vgic_init selftest fails
on any pKVM host whose limit exceeds 40 bits: the addresses it expects a
40-bit VM to reject are in range. EL2 also sizes the guest's stage 2
from the host stage 2's VTCR, which on a 64K kernel built for 48-bit PAs
on a 52-bit part is 48 bits where the limit is 52. KVM_RUN then returns
-ERANGE on the guest's first access to a memslot above 2^48 that the
host accepted.

Have EL2 take the IPA size from the VM's VTCR, the one the host sized
the donated PGD from, and drop the host-side override, so the request
is checked and honoured as on any other host. A VMM passing the default
type then gets 40 bits, and -EINVAL on a host whose limit is below 40,
as without pKVM. EL2 rejects a size below 32 bits or beyond the host's
IPA limit, which kvm_hyp_init_symbols() copies to EL2 before the host
drops its privileges.

Fixes: 60dfe093ec13 ("KVM: arm64: Instantiate guest stage-2 page-tables at EL2")
Signed-off-by: Fuad Tabba <fuad.tabba@xxxxxxxxx>
---
 arch/arm64/include/asm/kvm_hyp.h |  1 +
 arch/arm64/kvm/arm.c             |  1 +
 arch/arm64/kvm/hyp/nvhe/pkvm.c   | 20 ++++++++++++++++----
 arch/arm64/kvm/mmu.c             |  4 +---
 4 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index b0e42be3d9eef..8cffdf614af46 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -154,6 +154,7 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);
 
 extern unsigned long kvm_nvhe_sym(__icache_flags);
 extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits);
+extern u32 kvm_nvhe_sym(kvm_ipa_limit);
 extern enum mitigation_state kvm_nvhe_sym(spectre_v2_state);
 extern enum mitigation_state kvm_nvhe_sym(spectre_v4_state);
 extern enum mitigation_state kvm_nvhe_sym(spectre_bhb_state);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 157bf4b812020..81262193ffaca 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2836,6 +2836,7 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1);
 	kvm_nvhe_sym(__icache_flags) = __icache_flags;
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
+	kvm_nvhe_sym(kvm_ipa_limit) = get_kvm_ipa_limit();
 
 	kvm_nvhe_sym(spectre_v2_state) = arm64_get_spectre_v2_state();
 	kvm_nvhe_sym(spectre_v4_state) = arm64_get_spectre_v4_state();
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 820baf9ff74a2..0cbe15b15d08b 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -30,6 +30,8 @@ unsigned long __icache_flags;
 /* Used by kvm_get_vttbr(). */
 unsigned int kvm_arm_vmid_bits;
 
+u32 kvm_ipa_limit;
+
 unsigned int kvm_host_sve_max_vl;
 
 /*
@@ -505,7 +507,8 @@ static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[],
 }
 
 static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
-			     unsigned int nr_vcpus, pkvm_handle_t handle)
+			     unsigned int nr_vcpus, pkvm_handle_t handle,
+			     u64 vtcr)
 {
 	struct kvm_s2_mmu *mmu = &hyp_vm->kvm.arch.mmu;
 	int idx = vm_handle_to_idx(handle);
@@ -525,7 +528,7 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
 	/* VMID 0 is reserved for the host */
 	atomic64_set(&mmu->vmid.id, idx + 1);
 
-	mmu->vtcr = host_mmu.arch.mmu.vtcr;
+	mmu->vtcr = vtcr;
 	mmu->arch = &hyp_vm->kvm.arch;
 	mmu->pgt = &hyp_vm->pgt;
 }
@@ -908,6 +911,8 @@ int __pkvm_init_vm(struct kvm *host_kvm, void __kern *pgd_hva)
 	unsigned int nr_vcpus;
 	pkvm_handle_t handle;
 	void *pgd = NULL;
+	u32 phys_shift;
+	u64 vtcr;
 	int ret;
 
 	ret = hyp_pin_shared_mem(host_kvm, host_kvm + 1);
@@ -926,8 +931,15 @@ int __pkvm_init_vm(struct kvm *host_kvm, void __kern *pgd_hva)
 		goto err_unpin_kvm;
 	}
 
+	phys_shift = VTCR_EL2_IPA(READ_ONCE(host_kvm->arch.mmu.vtcr));
+	if (phys_shift < ARM64_MIN_PARANGE_BITS || phys_shift > kvm_ipa_limit) {
+		ret = -EINVAL;
+		goto err_unpin_kvm;
+	}
+
+	vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val, id_aa64mmfr1_el1_sys_val, phys_shift);
 	vm_size = pkvm_get_hyp_vm_size(nr_vcpus);
-	pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.mmu.vtcr);
+	pgd_size = kvm_pgtable_stage2_pgd_size(vtcr);
 	if (!IS_ALIGNED((unsigned long)pgd_hva, pgd_size)) {
 		ret = -EINVAL;
 		goto err_unpin_kvm;
@@ -945,7 +957,7 @@ int __pkvm_init_vm(struct kvm *host_kvm, void __kern *pgd_hva)
 	if (!pgd)
 		goto err_free_hyp_vm;
 
-	init_pkvm_hyp_vm(host_kvm, hyp_vm, nr_vcpus, handle);
+	init_pkvm_hyp_vm(host_kvm, hyp_vm, nr_vcpus, handle, vtcr);
 
 	ret = kvm_guest_prepare_stage2(hyp_vm, pgd);
 	if (ret)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1db10d8d6db73..861d10983d0d0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -972,9 +972,7 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 	u32 phys_shift;
 
 	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
-	if (is_protected_kvm_enabled()) {
-		phys_shift = kvm_ipa_limit;
-	} else if (phys_shift) {
+	if (phys_shift) {
 		if (phys_shift > kvm_ipa_limit ||
 		    phys_shift < ARM64_MIN_PARANGE_BITS)
 			return -EINVAL;
-- 
2.47.3