From 77fcbe823f002ad18426545351fa2fb94f8d5e61 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 31 Mar 2021 14:41:29 +0200 Subject: [PATCH] KVM: x86: Prevent 'hv_clock->system_time' from going negative in kvm_guest_time_update() When guest time is reset with KVM_SET_CLOCK(0), it is possible for 'hv_clock->system_time' to become a small negative number. This happens because in KVM_SET_CLOCK handling we set 'kvm->arch.kvmclock_offset' based on get_kvmclock_ns(kvm) but when KVM_REQ_CLOCK_UPDATE is handled, kvm_guest_time_update() does (masterclock in use case): hv_clock.system_time = ka->master_kernel_ns + v->kvm->arch.kvmclock_offset; And 'master_kernel_ns' represents the last time when masterclock got updated, it can precede KVM_SET_CLOCK() call. Normally, this is not a problem, the difference is very small, e.g. I'm observing hv_clock.system_time = -70 ns. The issue comes from the fact that 'hv_clock.system_time' is stored as unsigned and 'system_time / 100' in compute_tsc_page_parameters() becomes a very big number. Use 'master_kernel_ns' instead of get_kvmclock_ns() when masterclock is in use and get_kvmclock_base_ns() when it's not to prevent 'system_time' from going negative. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210331124130.337992-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e1960eed921f..eca63625aee4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5727,6 +5727,7 @@ set_pit2_out: } #endif case KVM_SET_CLOCK: { + struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data user_ns; u64 now_ns; @@ -5745,8 +5746,22 @@ set_pit2_out: * pvclock_update_vm_gtod_copy(). */ kvm_gen_update_masterclock(kvm); - now_ns = get_kvmclock_ns(kvm); - kvm->arch.kvmclock_offset += user_ns.clock - now_ns; + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'user_ns.clock' is very small. + */ + spin_lock_irq(&ka->pvclock_gtod_sync_lock); + if (kvm->arch.use_master_clock) + now_ns = ka->master_kernel_ns; + else + now_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = user_ns.clock - now_ns; + spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } -- 2.20.1