> -----Original Message----- > From: kvm-owner@xxxxxxxxxxxxxxx [mailto:kvm-owner@xxxxxxxxxxxxxxx] On > Behalf Of Avi Kivity > Sent: Thursday, September 06, 2012 4:16 PM > To: Hao, Xudong > Cc: kvm@xxxxxxxxxxxxxxx; Zhang, Xiantao; Joerg.Roedel@xxxxxxx > Subject: Re: [PATCH v2] kvm/fpu: Enable fully eager restore kvm FPU > > On 09/06/2012 05:13 AM, Hao, Xudong wrote: > >> -----Original Message----- > >> From: Avi Kivity [mailto:avi@xxxxxxxxxx] > >> Sent: Wednesday, September 05, 2012 9:13 PM > >> To: Hao, Xudong > >> Cc: kvm@xxxxxxxxxxxxxxx; Zhang, Xiantao; Joerg.Roedel@xxxxxxx > >> Subject: Re: [PATCH v2] kvm/fpu: Enable fully eager restore kvm FPU > >> > >> On 09/05/2012 04:26 AM, Xudong Hao wrote: > >> > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > >> > tracked by CR0.TS bit. > >> > > >> > Changes from v1: > >> > Expand KVM_XSTATE_LAZY to 64 bits before negating it. > >> > > >> > Signed-off-by: Xudong Hao <xudong.hao@xxxxxxxxx> > >> > --- > >> > arch/x86/include/asm/kvm.h | 4 ++++ > >> > arch/x86/kvm/x86.c | 13 ++++++++++++- > >> > 2 files changed, 16 insertions(+), 1 deletions(-) > >> > > >> > diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h > >> > index 521bf25..4c27056 100644 > >> > --- a/arch/x86/include/asm/kvm.h > >> > +++ b/arch/x86/include/asm/kvm.h > >> > @@ -8,6 +8,8 @@ > >> > > >> > #include <linux/types.h> > >> > #include <linux/ioctl.h> > >> > +#include <asm/user.h> > >> > +#include <asm/xsave.h> > >> > > >> > /* Select x86 specific features in <linux/kvm.h> */ > >> > #define __KVM_HAVE_PIT > >> > @@ -30,6 +32,8 @@ > >> > /* Architectural interrupt line count. */ > >> > #define KVM_NR_INTERRUPTS 256 > >> > > >> > +#define KVM_XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) > >> > + > >> > struct kvm_memory_alias { > >> > __u32 slot; /* this has a different namespace than memory slots */ > >> > __u32 flags; > >> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > >> > index 20f2266..a632042 100644 > >> > --- a/arch/x86/kvm/x86.c > >> > +++ b/arch/x86/kvm/x86.c > >> > @@ -5969,7 +5969,18 @@ void kvm_put_guest_fpu(struct kvm_vcpu > *vcpu) > >> > vcpu->guest_fpu_loaded = 0; > >> > fpu_save_init(&vcpu->arch.guest_fpu); > >> > ++vcpu->stat.fpu_reload; > >> > - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); > >> > + /* > >> > + * Currently KVM trigger FPU restore by #NM (via CR0.TS), > >> > + * till now only XCR0.bit0, XCR0.bit1, XCR0.bit2 is tracked > >> > + * by TS bit, there might be other FPU state is not tracked > >> > + * by TS bit. Here it only make FPU deactivate request and do > >> > + * FPU lazy restore for these cases: 1)xsave isn't enabled > >> > + * in guest, 2)all guest FPU states can be tracked by TS bit. > >> > + * For others, doing fully FPU eager restore. > >> > + */ > >> > + if (!kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) || > >> > + !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY))) > >> > + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); > >> > trace_kvm_fpu(0); > >> > } > >> > > >> > >> I think something is missing. This patch prevents > >> KVM_REQ_DEACTIVATE_FPU, but the fpu may not be active when non-lazy > bits > >> are added to xcr0 (or cr4.osxsave is enabled). I think you need to > >> activate the fpu at that time as well. > >> > > > > Mmh, I thought fpu is active by default, but it's better to make fpu active > explicitly here. > > If the following patch is fine, I'll make it another version. > > > > It is, but a previous pass through kvm_put_guest_fpu() could have > deactivated it. > > > - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); > > + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && > > + (vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY))) > > + kvm_x86_ops->fpu_activate(vcpu); > > + else > > + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); > > > > Doesn't help. We can have: > > host: deactivate fpu for some reason > guest: set cr4.osxsave, xcr0.bit3 > host: enter guest with deactivated fpu > guest: touch fpu > > result: host fpu corrupted. Avi, I'm not sure if I fully understand of you. Do you mean enter guest with a fpu_active=0 and then fpu does not restore? If so, I will add fpu_active=1 in the no-lazy case. - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && + (vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY))) { + kvm_x86_ops->fpu_activate(vcpu); + vcpu->fpu_active=1; + } + else + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
