[PATCH v3 1/3] KVM: Introduce vcpu->wants_to_run

[David Matlack]

Introduce vcpu->wants_to_run to indicate when a vCPU is in its core run
loop, i.e. when the vCPU is running the KVM_RUN ioctl and immediate_exit
was not set.

Replace all references to vcpu->run->immediate_exit with
!vcpu->wants_to_run to avoid TOCTOU races with userspace. For example, a
malicious userspace could invoked KVM_RUN with immediate_exit=true and
then after KVM reads it to set wants_to_run=false, flip it to false.
This would result in the vCPU running in KVM_RUN with
wants_to_run=false. This wouldn't cause any real bugs today but is a
dangerous landmine.

Signed-off-by: David Matlack <dmatlack at google.com>
---
 arch/arm64/kvm/arm.c       | 2 +-
 arch/loongarch/kvm/vcpu.c  | 2 +-
 arch/mips/kvm/mips.c       | 2 +-
 arch/powerpc/kvm/powerpc.c | 2 +-
 arch/riscv/kvm/vcpu.c      | 2 +-
 arch/s390/kvm/kvm-s390.c   | 2 +-
 arch/x86/kvm/x86.c         | 4 ++--
 include/linux/kvm_host.h   | 1 +
 virt/kvm/kvm_main.c        | 3 +++
 9 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c4a0a35e02c7..c587e5d9396e 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -986,7 +986,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	vcpu_load(vcpu);
 
-	if (run->immediate_exit) {
+	if (!vcpu->wants_to_run) {
 		ret = -EINTR;
 		goto out;
 	}
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 3a8779065f73..847ef54f3a84 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -1163,7 +1163,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			kvm_complete_iocsr_read(vcpu, run);
 	}
 
-	if (run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		return r;
 
 	/* Clear exit_reason */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 231ac052b506..f1a99962027a 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -436,7 +436,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		vcpu->mmio_needed = 0;
 	}
 
-	if (vcpu->run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		goto out;
 
 	lose_fpu(1);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index d32abe7fe6ab..961aadc71de2 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1852,7 +1852,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_sigset_activate(vcpu);
 
-	if (run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		r = -EINTR;
 	else
 		r = kvmppc_vcpu_run(vcpu);
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index b5ca9f2e98ac..3d8349470ee6 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -711,7 +711,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		return ret;
 	}
 
-	if (run->immediate_exit) {
+	if (!vcpu->wants_to_run) {
 		kvm_vcpu_srcu_read_unlock(vcpu);
 		return -EINTR;
 	}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5147b943a864..b1ea25aacbf9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -5033,7 +5033,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.pv.dumping)
 		return -EINVAL;
 
-	if (kvm_run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		return -EINTR;
 
 	if (kvm_run->kvm_valid_regs & ~KVM_SYNC_S390_VALID_FIELDS ||
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2d2619d3eee4..f70ae1558684 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11396,7 +11396,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_vcpu_srcu_read_lock(vcpu);
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
-		if (kvm_run->immediate_exit) {
+		if (!vcpu->wants_to_run) {
 			r = -EINTR;
 			goto out;
 		}
@@ -11474,7 +11474,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		WARN_ON_ONCE(vcpu->mmio_needed);
 	}
 
-	if (kvm_run->immediate_exit) {
+	if (!vcpu->wants_to_run) {
 		r = -EINTR;
 		goto out;
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index afbc99264ffa..f9b9ce0c3cd9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -380,6 +380,7 @@ struct kvm_vcpu {
 		bool dy_eligible;
 	} spin_loop;
 #endif
+	bool wants_to_run;
 	bool preempted;
 	bool ready;
 	struct kvm_vcpu_arch arch;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 38b498669ef9..bdea5b978f80 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4425,7 +4425,10 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				synchronize_rcu();
 			put_pid(oldpid);
 		}
+		vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit);
 		r = kvm_arch_vcpu_ioctl_run(vcpu);
+		vcpu->wants_to_run = false;
+
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	}
-- 
2.45.0.rc1.225.g2a3ae87e7f-goog