Messages in this thread |  | | | Date | Tue, 03 Nov 2009 20:58:52 +0100 | | From | Jan Kiszka <> | | Subject | Re: [PATCH 4/6] hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events |
Frederic Weisbecker wrote: > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index fc2974a..6560129 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -42,6 +42,7 @@ > #define CREATE_TRACE_POINTS > #include "trace.h" > > +#include <asm/debugreg.h> > #include <asm/uaccess.h> > #include <asm/msr.h> > #include <asm/desc.h> > @@ -3643,14 +3644,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) > trace_kvm_entry(vcpu->vcpu_id); > kvm_x86_ops->run(vcpu, kvm_run); > > - if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) { > - set_debugreg(current->thread.debugreg[0], 0); > - set_debugreg(current->thread.debugreg[1], 1); > - set_debugreg(current->thread.debugreg[2], 2); > - set_debugreg(current->thread.debugreg[3], 3); > - set_debugreg(current->thread.debugreg6, 6); > - set_debugreg(current->thread.debugreg7, 7); > - } > + /* > + * CHECKME: is vcpu->arch.switch_db_regs sufficient to check > + * if the guest is using breakpoints? If so we may want to do > + * this check before. > + */ > + hw_breakpoint_restore();
Obviously, this variant will make KVM users very unhappy. But trying to reduce this performance regression via vcpu->arch.switch_db_regs will make hw-breakpoint users unhappy: KVM leaves at least dr7 clobbered behind, even if the guest does not use breakpoints.
We really need a replacement for TIF_DEBUG (but we only need this [1]).
Jan
[1]http://thread.gmane.org/gmane.comp.emulators.kvm.devel/39784/focus=39827
[unhandled content-type:application/pgp-signature] |  |