7 files changed, 73 insertions, 12 deletions
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 8f3f93fa119e..03f97d71984c 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -154,6 +154,12 @@ SYM_CODE_END(\label)
 	esb
 	stp	x0, x1, [sp, #-16]!
 662:
+	/*
+	 * spectre vectors __bp_harden_hyp_vecs generate br instructions at runtime
+	 * that jump at offset 8 at __kvm_hyp_vector.
+	 * As hyp .text is guarded section, it needs bti j.
+	 */
+	bti j
 	b	\target
 
 check_preamble_length 661b, 662b
@@ -165,6 +171,8 @@ check_preamble_length 661b, 662b
 	nop
 	stp	x0, x1, [sp, #-16]!
 662:
+	/* Check valid_vect */
+	bti j
 	b	\target
 
 check_preamble_length 661b, 662b
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 4bddb8541bec..34f222af6165 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -457,6 +457,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu)
 	 */
 	val &= ~(TCR_HD | TCR_HA);
 	write_sysreg_el1(val, SYS_TCR);
+	__kvm_skip_instr(vcpu);
 	return true;
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index 58dcd92bf346..ab4f5d160c58 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -705,7 +705,20 @@ int hyp_ffa_init(void *pages)
 	if (res.a0 == FFA_RET_NOT_SUPPORTED)
 		return 0;
 
-	if (res.a0 != FFA_VERSION_1_0)
+	/*
+	 * Firmware returns the maximum supported version of the FF-A
+	 * implementation. Check that the returned version is
+	 * backwards-compatible with the hyp according to the rules in DEN0077A
+	 * v1.1 REL0 13.2.1.
+	 *
+	 * Of course, things are never simple when dealing with firmware. v1.1
+	 * broke ABI with v1.0 on several structures, which is itself
+	 * incompatible with the aforementioned versioning scheme. The
+	 * expectation is that v1.x implementations that do not support the v1.0
+	 * ABI return NOT_SUPPORTED rather than a version number, according to
+	 * DEN0077A v1.1 REL0 18.6.4.
+	 */
+	if (FFA_MAJOR_VERSION(res.a0) != 1)
 		return -EOPNOTSUPP;
 
 	arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res);
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index c87c63133e10..7693a6757cd7 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -297,3 +297,13 @@ SYM_CODE_START(__kvm_hyp_host_forward_smc)
 
 	ret
 SYM_CODE_END(__kvm_hyp_host_forward_smc)
+
+/*
+ * kvm_host_psci_cpu_entry is called through br instruction, which requires
+ * bti j instruction as compilers (gcc and llvm) doesn't insert bti j for external
+ * functions, but bti c instead.
+ */
+SYM_CODE_START(kvm_host_psci_cpu_entry)
+       bti j
+       b __kvm_host_psci_cpu_entry
+SYM_CODE_END(kvm_host_psci_cpu_entry)
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 08508783ec3d..24543d2a3490 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -200,7 +200,7 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 			 __hyp_pa(init_params), 0);
 }
 
-asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on)
+asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 {
 	struct psci_boot_args *boot_args;
 	struct kvm_cpu_context *host_ctxt;
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 0a6271052def..e89a23153e85 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -63,7 +63,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
-	write_sysreg(val, cptr_el2);
+	kvm_write_cptr_el2(val);
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
 
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index aa740a974e02..f7a93ef29250 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1195,25 +1195,54 @@ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 	return pte;
 }
 
-kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
+struct stage2_age_data {
+	bool	mkold;
+	bool	young;
+};
+
+static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			     enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL, 0);
+	kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data *data = ctx->arg;
+
+	if (!kvm_pte_valid(ctx->old) || new == ctx->old)
+		return 0;
+
+	data->young = true;
+
+	/*
+	 * stage2_age_walker() is always called while holding the MMU lock for
+	 * write, so this will always succeed. Nonetheless, this deliberately
+	 * follows the race detection pattern of the other stage-2 walkers in
+	 * case the locking mechanics of the MMU notifiers is ever changed.
+	 */
+	if (data->mkold && !stage2_try_set_pte(ctx, new))
+		return -EAGAIN;
+
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
 	 *
 	 * See the '->clear_flush_young()' callback on the KVM mmu notifier.
 	 */
-	return pte;
+	return 0;
 }
 
-bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
+bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
+					 u64 size, bool mkold)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0);
-	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data data = {
+		.mkold		= mkold,
+	};
+	struct kvm_pgtable_walker walker = {
+		.cb		= stage2_age_walker,
+		.arg		= &data,
+		.flags		= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+	return data.young;
 }
 
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,