[PATCH 6.6.y] KVM: arm64: Validate the host vCPU's VM before reading it under pKVM

[Sasha Levin <sashal@kernel.org>]

From: Fuad Tabba <fuad.tabba@linux.dev>

[ Upstream commit cf533b4d3630b229d78ad55567c5db2f365052a2 ]

On an MTE-capable host under pKVM, enter_exception64() reads the VM's
MTE flag through vcpu->kvm, which for a host vCPU is a host-writable
pointer nothing validates. The host can point it at any address in the
hyp linear map and read back bit 1 of that word through PSR_TCO in the
vCPU's CPSR, or panic the hypervisor with an unmapped one.

Get the VM through a get/put pair around the read: a loaded vCPU's is
the hyp VM, an unloaded host vCPU's is read once and pinned, and a
pointer the host never shared leaves TCO clear.

Fixes: ea7fc1bb1cd1b ("KVM: arm64: Introduce MTE VM feature")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://lore.kernel.org/all/20260914070536.877D91F000FF@smtp.kernel.org/
Reviewed-by: Vincent Donnefort <vdonnefort@google.com>
Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
Link: https://patch.msgid.link/20261001135711.1640520-3-fuad.tabba@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
[ sashal: replaced unavailable pkvm_get_loaded_hyp_vcpu() with a NULL-checked lookup through host_ctxt->__hyp_running_vcpu. ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm64/kvm/hyp/exception.c             |  5 ++-
 arch/arm64/kvm/hyp/include/hyp/adjust_pc.h | 28 ++++++++++++++
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h     |  2 +
 arch/arm64/kvm/hyp/nvhe/pkvm.c             | 43 ++++++++++++++++++++++
 4 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 424a5107cddb5..e20979138305a 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -92,6 +92,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 			      enum exception_type type)
 {
 	unsigned long sctlr, vbar, old, new, mode;
+	struct kvm *kvm;
 	u64 exc_offset;
 
 	mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
@@ -131,8 +132,10 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	new |= (old & PSR_C_BIT);
 	new |= (old & PSR_V_BIT);
 
-	if (kvm_has_mte(kern_hyp_va(vcpu->kvm)))
+	kvm = vcpu_get_kvm(vcpu);
+	if (kvm && kvm_has_mte(kvm))
 		new |= PSR_TCO_BIT;
+	vcpu_put_kvm(vcpu, kvm);
 
 	new |= (old & PSR_DIT_BIT);
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
index 4fdfeabefeb43..f55950ee2a7e4 100644
--- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
+++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
@@ -13,6 +13,34 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
 
+#ifdef __KVM_NVHE_HYPERVISOR__
+#include <nvhe/pkvm.h>
+
+/* Under pKVM a host vCPU's ->kvm is host-writable. */
+static inline struct kvm *vcpu_get_kvm(struct kvm_vcpu *vcpu)
+{
+	if (is_protected_kvm_enabled())
+		return pkvm_vcpu_get_kvm(vcpu);
+
+	return kern_hyp_va(vcpu->kvm);
+}
+
+static inline void vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm)
+{
+	if (is_protected_kvm_enabled())
+		pkvm_vcpu_put_kvm(vcpu, kvm);
+}
+#else
+static inline struct kvm *vcpu_get_kvm(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm;
+}
+
+static inline void vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm)
+{
+}
+#endif
+
 static inline void kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index 82b3d62538a61..d8efb924d57fd 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -64,5 +64,7 @@ int __pkvm_teardown_vm(pkvm_handle_t handle);
 struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 					 unsigned int vcpu_idx);
 void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
+struct kvm *pkvm_vcpu_get_kvm(struct kvm_vcpu *vcpu);
+void pkvm_vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm);
 
 #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index fd3e0b2891c60..471cef3e29df6 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -258,6 +258,49 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	hyp_spin_unlock(&vm_table_lock);
 }
 
+static struct pkvm_hyp_vm *pkvm_get_loaded_hyp_vm(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	struct kvm_vcpu *running_vcpu = host_ctxt->__hyp_running_vcpu;
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+
+	if (!running_vcpu)
+		return NULL;
+
+	hyp_vcpu = container_of(running_vcpu, struct pkvm_hyp_vcpu, vcpu);
+
+	if (vcpu == &hyp_vcpu->vcpu || vcpu == hyp_vcpu->host_vcpu)
+		return pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
+
+	return NULL;
+}
+
+/*
+ * A loaded vCPU's VM is the hyp VM. An unloaded host vCPU's is mapped at
+ * EL2 only while pinned, so it's read once and pinned; the pin fails for
+ * memory the host isn't sharing.
+ */
+struct kvm *pkvm_vcpu_get_kvm(struct kvm_vcpu *vcpu)
+{
+	struct pkvm_hyp_vm *hyp_vm = pkvm_get_loaded_hyp_vm(vcpu);
+	struct kvm *kvm;
+
+	if (hyp_vm)
+		return &hyp_vm->kvm;
+
+	kvm = kern_hyp_va(READ_ONCE(vcpu->kvm));
+	if (hyp_pin_shared_mem(kvm, kvm + 1))
+		return NULL;
+
+	return kvm;
+}
+
+void pkvm_vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm)
+{
+	if (kvm && !pkvm_get_loaded_hyp_vm(vcpu))
+		hyp_unpin_shared_mem(kvm, kvm + 1);
+}
+
 static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu)
 {
 	if (host_vcpu)
-- 
2.53.0