We have situations where we can call kvm_arm_halt_guest() without holding config_lock, which means that halt and resume can overlap in funny ways when called from separate contexts, and result in situations where a vcpu is resumed while other parts of KVM assume it is halted. Consequences are left to the imagination of the reader. Fix this sorry situation by turning kvm_vcpu_arch::pause into an atomic counter, which makes the races described above harmless. Fixes: 3b92830ad41b2 ("KVM: arm/arm64: implement kvm_arm_[halt,resume]_guest") Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba < fuad.tabba@linux.dev> Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org --- arch/arm64/include/asm/kvm_host.h | 7 +++---- arch/arm64/kvm/arm.c | 21 ++++++++++++--------- 2 files changed, 15 insertions(+), 13 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index cd9b9d2462f96..9c068f27f9b8a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -889,11 +889,10 @@ struct kvm_vcpu_arch { /* * Don't run the guest (internal implementation need). * - * Contrary to the flags above, this is set/cleared outside of - * a vcpu context, and thus cannot be mixed with the flags - * themselves (or the flag accesses need to be made atomic). + * Contrary to the flags above, this is updated outside of + * a vcpu context, and thus cannot be mixed with the flags. */ - bool pause; + atomic_t pause; /* * We maintain more than a single set of debug registers to support diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9956049e592ab..07bf8b2e683d5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -565,6 +565,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_arm_pvtime_vcpu_init(&vcpu->arch); vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; + atomic_set(&vcpu->arch.pause, 0); /* * This vCPU may have been created after mpidr_data was initialized. @@ -839,6 +840,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return ret; } +static bool vcpu_can_run(struct kvm_vcpu *vcpu) +{ + return !kvm_arm_vcpu_stopped(vcpu) && !atomic_read(&vcpu->arch.pause); +} + /** * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled * @v: The VCPU pointer @@ -854,8 +860,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) (kvm_timer_should_notify_user(v) || kvm_pmu_should_notify_user(v))); - return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) - && !kvm_arm_vcpu_stopped(v) && !v->arch.pause); + return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) && vcpu_can_run(v)); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) @@ -1018,7 +1023,7 @@ void kvm_arm_halt_guest(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.pause = true; + atomic_inc(&vcpu->arch.pause); kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP); } @@ -1028,8 +1033,8 @@ void kvm_arm_resume_guest(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu->arch.pause = false; - __kvm_vcpu_wake_up(vcpu); + if (atomic_dec_and_test(&vcpu->arch.pause)) + __kvm_vcpu_wake_up(vcpu); } } @@ -1037,11 +1042,9 @@ static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); - rcuwait_wait_event(wait, - (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), - TASK_INTERRUPTIBLE); + rcuwait_wait_event(wait, vcpu_can_run(vcpu), TASK_INTERRUPTIBLE); - if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) { + if (!vcpu_can_run(vcpu)) { /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } -- 2.47.3