* [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU @ 2012-09-12 8:10 Xudong Hao 2012-09-13 16:26 ` Marcelo Tosatti 2012-09-13 16:38 ` Avi Kivity 0 siblings, 2 replies; 16+ messages in thread From: Xudong Hao @ 2012-09-12 8:10 UTC (permalink / raw) To: avi; +Cc: kvm, xiantao.zhang, Xudong Hao Enable KVM FPU fully eager restore, if there is other FPU state which isn't tracked by CR0.TS bit. v3 changes from v2: - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate bit exist. v2 changes from v1: - Expand KVM_XSTATE_LAZY to 64 bits before negating it. Signed-off-by: Xudong Hao <xudong.hao@intel.com> --- arch/x86/include/asm/kvm.h | 4 ++++ arch/x86/kvm/vmx.c | 2 ++ arch/x86/kvm/x86.c | 15 ++++++++++++++- 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c index 248c2b4..853e875 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!vcpu->fpu_active) hw_cr0 |= X86_CR0_TS | X86_CR0_MP; + else + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 20f2266..183cf60 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) return 1; if (xcr0 & ~host_xcr0) return 1; + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) + vcpu->fpu_active = 1; vcpu->arch.xcr0 = xcr0; vcpu->guest_xcr0_loaded = 0; return 0; @@ -5969,7 +5971,18 @@ 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); } -- 1.5.5 ^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-12 8:10 [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU Xudong Hao @ 2012-09-13 16:26 ` Marcelo Tosatti 2012-09-13 16:29 ` Marcelo Tosatti 2012-09-13 16:38 ` Avi Kivity 1 sibling, 1 reply; 16+ messages in thread From: Marcelo Tosatti @ 2012-09-13 16:26 UTC (permalink / raw) To: Xudong Hao, Avi Kivity; +Cc: kvm, xiantao.zhang On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > tracked by CR0.TS bit. > > v3 changes from v2: > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate bit > exist. How about a "guest_xcr0_can_lazy_saverestore" bool to control this? It only needs to be updated when guest xcr0 is updated. That seems cleaner. Avi? > v2 changes from v1: > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > --- > arch/x86/include/asm/kvm.h | 4 ++++ > arch/x86/kvm/vmx.c | 2 ++ > arch/x86/kvm/x86.c | 15 ++++++++++++++- > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > index 248c2b4..853e875 100644 > --- a/arch/x86/kvm/vmx.c > +++ b/arch/x86/kvm/vmx.c > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > > if (!vcpu->fpu_active) > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > + else > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > vmcs_writel(CR0_READ_SHADOW, cr0); > vmcs_writel(GUEST_CR0, hw_cr0); > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index 20f2266..183cf60 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) > return 1; > if (xcr0 & ~host_xcr0) > return 1; > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > + vcpu->fpu_active = 1; > vcpu->arch.xcr0 = xcr0; > vcpu->guest_xcr0_loaded = 0; > return 0; > @@ -5969,7 +5971,18 @@ 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); > } > > -- > 1.5.5 > > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-13 16:26 ` Marcelo Tosatti @ 2012-09-13 16:29 ` Marcelo Tosatti 2012-09-13 16:40 ` Avi Kivity 2012-09-14 8:54 ` Hao, Xudong 0 siblings, 2 replies; 16+ messages in thread From: Marcelo Tosatti @ 2012-09-13 16:29 UTC (permalink / raw) To: Xudong Hao, Avi Kivity; +Cc: kvm, xiantao.zhang On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: > On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > > tracked by CR0.TS bit. > > > > v3 changes from v2: > > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate bit > > exist. > > How about a "guest_xcr0_can_lazy_saverestore" bool to control this? > It only needs to be updated when guest xcr0 is updated. > > That seems cleaner. Avi? Reasoning below. > > v2 changes from v1: > > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > > > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > > --- > > arch/x86/include/asm/kvm.h | 4 ++++ > > arch/x86/kvm/vmx.c | 2 ++ > > arch/x86/kvm/x86.c | 15 ++++++++++++++- > > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > > index 248c2b4..853e875 100644 > > --- a/arch/x86/kvm/vmx.c > > +++ b/arch/x86/kvm/vmx.c > > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > > > > if (!vcpu->fpu_active) > > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > > + else > > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > > > vmcs_writel(CR0_READ_SHADOW, cr0); > > vmcs_writel(GUEST_CR0, hw_cr0); > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > index 20f2266..183cf60 100644 > > --- a/arch/x86/kvm/x86.c > > +++ b/arch/x86/kvm/x86.c > > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) > > return 1; > > if (xcr0 & ~host_xcr0) > > return 1; > > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > > + vcpu->fpu_active = 1; This is confusing. The variable allows to decrease the number of places the decision is made. > > vcpu->arch.xcr0 = xcr0; > > vcpu->guest_xcr0_loaded = 0; > > return 0; > > @@ -5969,7 +5971,18 @@ 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); > > } > > > > -- > > 1.5.5 > > > > -- > > To unsubscribe from this list: send the line "unsubscribe kvm" in > > the body of a message to majordomo@vger.kernel.org > > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-13 16:29 ` Marcelo Tosatti @ 2012-09-13 16:40 ` Avi Kivity 2012-09-17 2:07 ` Hao, Xudong 2012-09-14 8:54 ` Hao, Xudong 1 sibling, 1 reply; 16+ messages in thread From: Avi Kivity @ 2012-09-13 16:40 UTC (permalink / raw) To: Marcelo Tosatti; +Cc: Xudong Hao, kvm, xiantao.zhang On 09/13/2012 07:29 PM, Marcelo Tosatti wrote: > On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: >> On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: >> > Enable KVM FPU fully eager restore, if there is other FPU state which isn't >> > tracked by CR0.TS bit. >> > >> > v3 changes from v2: >> > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate bit >> > exist. >> >> How about a "guest_xcr0_can_lazy_saverestore" bool to control this? >> It only needs to be updated when guest xcr0 is updated. >> >> That seems cleaner. Avi? > > Reasoning below. > >> > v2 changes from v1: >> > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. >> > >> > Signed-off-by: Xudong Hao <xudong.hao@intel.com> >> > --- >> > arch/x86/include/asm/kvm.h | 4 ++++ >> > arch/x86/kvm/vmx.c | 2 ++ >> > arch/x86/kvm/x86.c | 15 ++++++++++++++- >> > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c >> > index 248c2b4..853e875 100644 >> > --- a/arch/x86/kvm/vmx.c >> > +++ b/arch/x86/kvm/vmx.c >> > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) >> > >> > if (!vcpu->fpu_active) >> > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; >> > + else >> > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); >> > >> > vmcs_writel(CR0_READ_SHADOW, cr0); >> > vmcs_writel(GUEST_CR0, hw_cr0); >> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c >> > index 20f2266..183cf60 100644 >> > --- a/arch/x86/kvm/x86.c >> > +++ b/arch/x86/kvm/x86.c >> > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) >> > return 1; >> > if (xcr0 & ~host_xcr0) >> > return 1; >> > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) >> > + vcpu->fpu_active = 1; > > This is confusing. The variable allows to decrease the number of places > the decision is made. Better to have a helper function (lazy_fpu_allowed(), for example). Variables raise the question of whether they are maintained correctly. -- error compiling committee.c: too many arguments to function ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-13 16:40 ` Avi Kivity @ 2012-09-17 2:07 ` Hao, Xudong 2012-09-17 13:30 ` Marcelo Tosatti 0 siblings, 1 reply; 16+ messages in thread From: Hao, Xudong @ 2012-09-17 2:07 UTC (permalink / raw) To: Avi Kivity, Marcelo Tosatti; +Cc: kvm@vger.kernel.org, Zhang, Xiantao > -----Original Message----- > From: Avi Kivity [mailto:avi@redhat.com] > Sent: Friday, September 14, 2012 12:40 AM > To: Marcelo Tosatti > Cc: Hao, Xudong; kvm@vger.kernel.org; Zhang, Xiantao > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > On 09/13/2012 07:29 PM, Marcelo Tosatti wrote: > > On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: > >> On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > >> > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > >> > tracked by CR0.TS bit. > >> > > >> > v3 changes from v2: > >> > - Make fpu active explicitly while guest xsave is enabling and non-lazy > xstate bit > >> > exist. > >> > >> How about a "guest_xcr0_can_lazy_saverestore" bool to control this? > >> It only needs to be updated when guest xcr0 is updated. > >> > >> That seems cleaner. Avi? > > > > Reasoning below. > > > >> > v2 changes from v1: > >> > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > >> > > >> > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > >> > --- > >> > arch/x86/include/asm/kvm.h | 4 ++++ > >> > arch/x86/kvm/vmx.c | 2 ++ > >> > arch/x86/kvm/x86.c | 15 ++++++++++++++- > >> > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > >> > index 248c2b4..853e875 100644 > >> > --- a/arch/x86/kvm/vmx.c > >> > +++ b/arch/x86/kvm/vmx.c > >> > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, > unsigned long cr0) > >> > > >> > if (!vcpu->fpu_active) > >> > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > >> > + else > >> > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > >> > > >> > vmcs_writel(CR0_READ_SHADOW, cr0); > >> > vmcs_writel(GUEST_CR0, hw_cr0); > >> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > >> > index 20f2266..183cf60 100644 > >> > --- a/arch/x86/kvm/x86.c > >> > +++ b/arch/x86/kvm/x86.c > >> > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 > index, u64 xcr) > >> > return 1; > >> > if (xcr0 & ~host_xcr0) > >> > return 1; > >> > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > >> > + vcpu->fpu_active = 1; > > > > This is confusing. The variable allows to decrease the number of places > > the decision is made. > > Better to have a helper function (lazy_fpu_allowed(), for example). > Variables raise the question of whether they are maintained correctly. > I realized to modifying the fpu_active variable is incorrect, it must update exception bitmap. To avoid the cr0 and xcrs setting order for live migrate case, how about calling fpu_activate() in kvm_set_xcr()? I can add code comments in this function calling. diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index be6d549..e4646d9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -574,6 +574,9 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) kvm_inject_gp(vcpu, 0); return 1; } + if (xcr & ~((u64)KVM_XSTATE_LAZY)) + /* Allow fpu eager restore */ + kvm_x86_ops->fpu_activate(vcpu); return 0; } Thanks, -Xudong ^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-17 2:07 ` Hao, Xudong @ 2012-09-17 13:30 ` Marcelo Tosatti 2012-09-18 1:08 ` Hao, Xudong 0 siblings, 1 reply; 16+ messages in thread From: Marcelo Tosatti @ 2012-09-17 13:30 UTC (permalink / raw) To: Hao, Xudong; +Cc: Avi Kivity, kvm@vger.kernel.org, Zhang, Xiantao On Mon, Sep 17, 2012 at 02:07:43AM +0000, Hao, Xudong wrote: > > -----Original Message----- > > From: Avi Kivity [mailto:avi@redhat.com] > > Sent: Friday, September 14, 2012 12:40 AM > > To: Marcelo Tosatti > > Cc: Hao, Xudong; kvm@vger.kernel.org; Zhang, Xiantao > > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > > > On 09/13/2012 07:29 PM, Marcelo Tosatti wrote: > > > On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: > > >> On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > > >> > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > > >> > tracked by CR0.TS bit. > > >> > > > >> > v3 changes from v2: > > >> > - Make fpu active explicitly while guest xsave is enabling and non-lazy > > xstate bit > > >> > exist. > > >> > > >> How about a "guest_xcr0_can_lazy_saverestore" bool to control this? > > >> It only needs to be updated when guest xcr0 is updated. > > >> > > >> That seems cleaner. Avi? > > > > > > Reasoning below. > > > > > >> > v2 changes from v1: > > >> > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > >> > > > >> > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > > >> > --- > > >> > arch/x86/include/asm/kvm.h | 4 ++++ > > >> > arch/x86/kvm/vmx.c | 2 ++ > > >> > arch/x86/kvm/x86.c | 15 ++++++++++++++- > > >> > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > > >> > index 248c2b4..853e875 100644 > > >> > --- a/arch/x86/kvm/vmx.c > > >> > +++ b/arch/x86/kvm/vmx.c > > >> > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, > > unsigned long cr0) > > >> > > > >> > if (!vcpu->fpu_active) > > >> > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > > >> > + else > > >> > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > >> > > > >> > vmcs_writel(CR0_READ_SHADOW, cr0); > > >> > vmcs_writel(GUEST_CR0, hw_cr0); > > >> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > >> > index 20f2266..183cf60 100644 > > >> > --- a/arch/x86/kvm/x86.c > > >> > +++ b/arch/x86/kvm/x86.c > > >> > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 > > index, u64 xcr) > > >> > return 1; > > >> > if (xcr0 & ~host_xcr0) > > >> > return 1; > > >> > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > > >> > + vcpu->fpu_active = 1; > > > > > > This is confusing. The variable allows to decrease the number of places > > > the decision is made. > > > > Better to have a helper function (lazy_fpu_allowed(), for example). > > Variables raise the question of whether they are maintained correctly. > > > > I realized to modifying the fpu_active variable is incorrect, it must update exception bitmap. > To avoid the cr0 and xcrs setting order for live migrate case, how about calling fpu_activate() in kvm_set_xcr()? I can add code comments in this function calling. The objective of the change is to disable lazy fpu loading (that is, host fpu loaded in guest and vice-versa), when some bit except the initial tree bits set in guest XCR0 (initial tree being XSTATE_FP|XSTATE_SSE| XSTATE_YMM). Yes? If i get that right, then the suggestion seems to be: static bool lazy_fpu_allowed() { return (vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); } On guest entry: if (!lazy_fpu_allowed(vcpu)) kvm_x86_ops->fpu_activate(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); Does that make sense? > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index be6d549..e4646d9 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -574,6 +574,9 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) > kvm_inject_gp(vcpu, 0); > return 1; > } > + if (xcr & ~((u64)KVM_XSTATE_LAZY)) > + /* Allow fpu eager restore */ > + kvm_x86_ops->fpu_activate(vcpu); > return 0; > } > > Thanks, > -Xudong > > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-17 13:30 ` Marcelo Tosatti @ 2012-09-18 1:08 ` Hao, Xudong 2012-09-19 10:23 ` Avi Kivity 0 siblings, 1 reply; 16+ messages in thread From: Hao, Xudong @ 2012-09-18 1:08 UTC (permalink / raw) To: Marcelo Tosatti; +Cc: Avi Kivity, kvm@vger.kernel.org, Zhang, Xiantao > -----Original Message----- > From: Marcelo Tosatti [mailto:mtosatti@redhat.com] > Sent: Monday, September 17, 2012 9:31 PM > To: Hao, Xudong > Cc: Avi Kivity; kvm@vger.kernel.org; Zhang, Xiantao > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > On Mon, Sep 17, 2012 at 02:07:43AM +0000, Hao, Xudong wrote: > > > -----Original Message----- > > > From: Avi Kivity [mailto:avi@redhat.com] > > > Sent: Friday, September 14, 2012 12:40 AM > > > To: Marcelo Tosatti > > > Cc: Hao, Xudong; kvm@vger.kernel.org; Zhang, Xiantao > > > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > > > > > On 09/13/2012 07:29 PM, Marcelo Tosatti wrote: > > > > On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: > > > >> On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > > > >> > Enable KVM FPU fully eager restore, if there is other FPU state which > isn't > > > >> > tracked by CR0.TS bit. > > > >> > > > > >> > v3 changes from v2: > > > >> > - Make fpu active explicitly while guest xsave is enabling and non-lazy > > > xstate bit > > > >> > exist. > > > >> > > > >> How about a "guest_xcr0_can_lazy_saverestore" bool to control this? > > > >> It only needs to be updated when guest xcr0 is updated. > > > >> > > > >> That seems cleaner. Avi? > > > > > > > > Reasoning below. > > > > > > > >> > v2 changes from v1: > > > >> > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > > >> > > > > >> > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > > > >> > --- > > > >> > arch/x86/include/asm/kvm.h | 4 ++++ > > > >> > arch/x86/kvm/vmx.c | 2 ++ > > > >> > arch/x86/kvm/x86.c | 15 ++++++++++++++- > > > >> > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > > > >> > index 248c2b4..853e875 100644 > > > >> > --- a/arch/x86/kvm/vmx.c > > > >> > +++ b/arch/x86/kvm/vmx.c > > > >> > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu > *vcpu, > > > unsigned long cr0) > > > >> > > > > >> > if (!vcpu->fpu_active) > > > >> > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > > > >> > + else > > > >> > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > > >> > > > > >> > vmcs_writel(CR0_READ_SHADOW, cr0); > > > >> > vmcs_writel(GUEST_CR0, hw_cr0); > > > >> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > > >> > index 20f2266..183cf60 100644 > > > >> > --- a/arch/x86/kvm/x86.c > > > >> > +++ b/arch/x86/kvm/x86.c > > > >> > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, > u32 > > > index, u64 xcr) > > > >> > return 1; > > > >> > if (xcr0 & ~host_xcr0) > > > >> > return 1; > > > >> > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > > > >> > + vcpu->fpu_active = 1; > > > > > > > > This is confusing. The variable allows to decrease the number of places > > > > the decision is made. > > > > > > Better to have a helper function (lazy_fpu_allowed(), for example). > > > Variables raise the question of whether they are maintained correctly. > > > > > > > I realized to modifying the fpu_active variable is incorrect, it must update > exception bitmap. > > To avoid the cr0 and xcrs setting order for live migrate case, how about > calling fpu_activate() in kvm_set_xcr()? I can add code comments in this > function calling. > > The objective of the change is to disable lazy fpu loading (that is, > host fpu loaded in guest and vice-versa), when some bit except the > initial tree bits set in guest XCR0 (initial tree being XSTATE_FP|XSTATE_SSE| > XSTATE_YMM). Yes? > Yes, it's just the object. > If i get that right, then the suggestion seems to be: > > static bool lazy_fpu_allowed() > { > return (vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); > } > That may be: static bool lazy_fpu_allowed() { return !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); } > On guest entry: > if (!lazy_fpu_allowed(vcpu)) > kvm_x86_ops->fpu_activate(vcpu); Yes, we can add it into guest entry: kvm_set_xcr(). Avi, other comments? > if (vcpu->fpu_active) > kvm_load_guest_fpu(vcpu); > > > Does that make sense? > ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-18 1:08 ` Hao, Xudong @ 2012-09-19 10:23 ` Avi Kivity 2012-09-20 1:43 ` Hao, Xudong 0 siblings, 1 reply; 16+ messages in thread From: Avi Kivity @ 2012-09-19 10:23 UTC (permalink / raw) To: Hao, Xudong; +Cc: Marcelo Tosatti, kvm@vger.kernel.org, Zhang, Xiantao On 09/18/2012 04:08 AM, Hao, Xudong wrote: >> >> The objective of the change is to disable lazy fpu loading (that is, >> host fpu loaded in guest and vice-versa), Not vice versa. We allow the guest fpu loaded in the host, but save it on heavyweight exit or task switch. when some bit except the >> initial tree bits set in guest XCR0 (initial tree being XSTATE_FP|XSTATE_SSE| >> XSTATE_YMM). Yes? >> > > Yes, it's just the object. > >> If i get that right, then the suggestion seems to be: >> >> static bool lazy_fpu_allowed() >> { >> return (vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); >> } >> > > That may be: > > static bool lazy_fpu_allowed() > { > return !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); > } Shouldn't it depend on cr4.osxsave as well? > >> On guest entry: >> if (!lazy_fpu_allowed(vcpu)) >> kvm_x86_ops->fpu_activate(vcpu); > But we already have that: if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); so why not manage fpu_active to be always set when needed? I don't want more checks in the entry path. -- error compiling committee.c: too many arguments to function ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-19 10:23 ` Avi Kivity @ 2012-09-20 1:43 ` Hao, Xudong 2012-09-20 9:19 ` Avi Kivity 0 siblings, 1 reply; 16+ messages in thread From: Hao, Xudong @ 2012-09-20 1:43 UTC (permalink / raw) To: Avi Kivity; +Cc: Marcelo Tosatti, kvm@vger.kernel.org, Zhang, Xiantao > -----Original Message----- > From: Avi Kivity [mailto:avi@redhat.com] > Sent: Wednesday, September 19, 2012 6:24 PM > To: Hao, Xudong > Cc: Marcelo Tosatti; kvm@vger.kernel.org; Zhang, Xiantao > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > That may be: > > > > static bool lazy_fpu_allowed() > > { > > return !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); > > } > > Shouldn't it depend on cr4.osxsave as well? > It do need to check cr4.osxsave due to a separate function. static bool lazy_fpu_allowed(struct kvm_vcpu *vcpu) { return !kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) || !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); } > > > >> On guest entry: > >> if (!lazy_fpu_allowed(vcpu)) > >> kvm_x86_ops->fpu_activate(vcpu); > > > > But we already have that: > > if (vcpu->fpu_active) > kvm_load_guest_fpu(vcpu); > > so why not manage fpu_active to be always set when needed? I don't want > more checks in the entry path. > I means add fpu_active() in kvm_set_xcr(), not in guest entry. Then the fpu_active will be set always when guest initialize xstate. @@ -574,6 +574,9 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) kvm_inject_gp(vcpu, 0); return 1; } + if (!lazy_fpu_allowed(vcpu)) + kvm_x86_ops->fpu_activate(vcpu); return 0; ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-20 1:43 ` Hao, Xudong @ 2012-09-20 9:19 ` Avi Kivity 2012-09-21 8:47 ` Hao, Xudong 0 siblings, 1 reply; 16+ messages in thread From: Avi Kivity @ 2012-09-20 9:19 UTC (permalink / raw) To: Hao, Xudong; +Cc: Marcelo Tosatti, kvm@vger.kernel.org, Zhang, Xiantao On 09/20/2012 04:43 AM, Hao, Xudong wrote: >> -----Original Message----- >> From: Avi Kivity [mailto:avi@redhat.com] >> Sent: Wednesday, September 19, 2012 6:24 PM >> To: Hao, Xudong >> Cc: Marcelo Tosatti; kvm@vger.kernel.org; Zhang, Xiantao >> Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU >> > That may be: >> > >> > static bool lazy_fpu_allowed() >> > { >> > return !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); >> > } >> >> Shouldn't it depend on cr4.osxsave as well? >> > > It do need to check cr4.osxsave due to a separate function. > > static bool lazy_fpu_allowed(struct kvm_vcpu *vcpu) > { > return !kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) || > !(vcpu->arch.xcr0 & ~((u64)KVM_XSTATE_LAZY)); > } Yes. > >> > >> >> On guest entry: >> >> if (!lazy_fpu_allowed(vcpu)) >> >> kvm_x86_ops->fpu_activate(vcpu); >> > >> >> But we already have that: >> >> if (vcpu->fpu_active) >> kvm_load_guest_fpu(vcpu); >> >> so why not manage fpu_active to be always set when needed? I don't want >> more checks in the entry path. >> > I means add fpu_active() in kvm_set_xcr(), not in guest entry. Then the fpu_active will be set always when guest initialize xstate. > > @@ -574,6 +574,9 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) > kvm_inject_gp(vcpu, 0); > return 1; > } > + if (!lazy_fpu_allowed(vcpu)) > + kvm_x86_ops->fpu_activate(vcpu); > return 0; > And of course on cr4 update. So a function update_lazy_fpu() to be called from both places is needed. -- error compiling committee.c: too many arguments to function ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-20 9:19 ` Avi Kivity @ 2012-09-21 8:47 ` Hao, Xudong 2012-09-23 9:03 ` Avi Kivity 0 siblings, 1 reply; 16+ messages in thread From: Hao, Xudong @ 2012-09-21 8:47 UTC (permalink / raw) To: Avi Kivity; +Cc: Marcelo Tosatti, kvm@vger.kernel.org, Zhang, Xiantao > -----Original Message----- > From: Avi Kivity [mailto:avi@redhat.com] > Sent: Thursday, September 20, 2012 5:20 PM > To: Hao, Xudong > Cc: Marcelo Tosatti; kvm@vger.kernel.org; Zhang, Xiantao > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > >> >> On guest entry: > >> >> if (!lazy_fpu_allowed(vcpu)) > >> >> kvm_x86_ops->fpu_activate(vcpu); > >> > > >> > >> But we already have that: > >> > >> if (vcpu->fpu_active) > >> kvm_load_guest_fpu(vcpu); > >> > >> so why not manage fpu_active to be always set when needed? I don't > want > >> more checks in the entry path. > >> > > I means add fpu_active() in kvm_set_xcr(), not in guest entry. Then the > fpu_active will be set always when guest initialize xstate. > > > > @@ -574,6 +574,9 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, > u64 xcr) > > kvm_inject_gp(vcpu, 0); > > return 1; > > } > > + if (!lazy_fpu_allowed(vcpu)) > > + kvm_x86_ops->fpu_activate(vcpu); > > return 0; > > > > And of course on cr4 update. So a function update_lazy_fpu() to be > called from both places is needed. > Complete consideration, thanks. So I will define a function update_lazy_fpu(), insert it into kvm_set_xcr() and handle_cr(). Comments? ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-21 8:47 ` Hao, Xudong @ 2012-09-23 9:03 ` Avi Kivity 0 siblings, 0 replies; 16+ messages in thread From: Avi Kivity @ 2012-09-23 9:03 UTC (permalink / raw) To: Hao, Xudong; +Cc: Marcelo Tosatti, kvm@vger.kernel.org, Zhang, Xiantao On 09/21/2012 11:47 AM, Hao, Xudong wrote: > > -----Original Message----- > > From: Avi Kivity [mailto:avi@redhat.com] > > Sent: Thursday, September 20, 2012 5:20 PM > > To: Hao, Xudong > > Cc: Marcelo Tosatti; kvm@vger.kernel.org; Zhang, Xiantao > > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > >> >> On guest entry: > > >> >> if (!lazy_fpu_allowed(vcpu)) > > >> >> kvm_x86_ops->fpu_activate(vcpu); > > >> > > > >> > > >> But we already have that: > > >> > > >> if (vcpu->fpu_active) > > >> kvm_load_guest_fpu(vcpu); > > >> > > >> so why not manage fpu_active to be always set when needed? I don't > > want > > >> more checks in the entry path. > > >> > > > I means add fpu_active() in kvm_set_xcr(), not in guest entry. Then the > > fpu_active will be set always when guest initialize xstate. > > > > > > @@ -574,6 +574,9 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, > > u64 xcr) > > > kvm_inject_gp(vcpu, 0); > > > return 1; > > > } > > > + if (!lazy_fpu_allowed(vcpu)) > > > + kvm_x86_ops->fpu_activate(vcpu); > > > return 0; > > > > > > > And of course on cr4 update. So a function update_lazy_fpu() to be > > called from both places is needed. > > > > Complete consideration, thanks. > > So I will define a function update_lazy_fpu(), insert it into kvm_set_xcr() and handle_cr(). Comments? Sounds good. -- I have a truly marvellous patch that fixes the bug which this signature is too narrow to contain. ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-13 16:29 ` Marcelo Tosatti 2012-09-13 16:40 ` Avi Kivity @ 2012-09-14 8:54 ` Hao, Xudong 2012-09-14 9:35 ` Marcelo Tosatti 1 sibling, 1 reply; 16+ messages in thread From: Hao, Xudong @ 2012-09-14 8:54 UTC (permalink / raw) To: Marcelo Tosatti, Avi Kivity; +Cc: kvm@vger.kernel.org, Zhang, Xiantao > -----Original Message----- > From: kvm-owner@vger.kernel.org [mailto:kvm-owner@vger.kernel.org] On > Behalf Of Marcelo Tosatti > Sent: Friday, September 14, 2012 12:29 AM > To: Hao, Xudong; Avi Kivity > Cc: kvm@vger.kernel.org; Zhang, Xiantao > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: > > On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > > > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > > > tracked by CR0.TS bit. > > > > > > v3 changes from v2: > > > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate > bit > > > exist. > > > > How about a "guest_xcr0_can_lazy_saverestore" bool to control this? > > It only needs to be updated when guest xcr0 is updated. > > > > That seems cleaner. Avi? > > Reasoning below. > > > > v2 changes from v1: > > > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > > > > > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > > > --- > > > arch/x86/include/asm/kvm.h | 4 ++++ > > > arch/x86/kvm/vmx.c | 2 ++ > > > arch/x86/kvm/x86.c | 15 ++++++++++++++- > > > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > > > index 248c2b4..853e875 100644 > > > --- a/arch/x86/kvm/vmx.c > > > +++ b/arch/x86/kvm/vmx.c > > > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, > unsigned long cr0) > > > > > > if (!vcpu->fpu_active) > > > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > > > + else > > > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > > > > > vmcs_writel(CR0_READ_SHADOW, cr0); > > > vmcs_writel(GUEST_CR0, hw_cr0); > > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > > index 20f2266..183cf60 100644 > > > --- a/arch/x86/kvm/x86.c > > > +++ b/arch/x86/kvm/x86.c > > > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 > index, u64 xcr) > > > return 1; > > > if (xcr0 & ~host_xcr0) > > > return 1; > > > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > > > + vcpu->fpu_active = 1; > > This is confusing. The variable allows to decrease the number of places > the decision is made. > Hi, Marcelo, What does it mean? ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-14 8:54 ` Hao, Xudong @ 2012-09-14 9:35 ` Marcelo Tosatti 0 siblings, 0 replies; 16+ messages in thread From: Marcelo Tosatti @ 2012-09-14 9:35 UTC (permalink / raw) To: Hao, Xudong; +Cc: Avi Kivity, kvm@vger.kernel.org, Zhang, Xiantao On Fri, Sep 14, 2012 at 08:54:40AM +0000, Hao, Xudong wrote: > > -----Original Message----- > > From: kvm-owner@vger.kernel.org [mailto:kvm-owner@vger.kernel.org] On > > Behalf Of Marcelo Tosatti > > Sent: Friday, September 14, 2012 12:29 AM > > To: Hao, Xudong; Avi Kivity > > Cc: kvm@vger.kernel.org; Zhang, Xiantao > > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > > > On Thu, Sep 13, 2012 at 01:26:36PM -0300, Marcelo Tosatti wrote: > > > On Wed, Sep 12, 2012 at 04:10:24PM +0800, Xudong Hao wrote: > > > > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > > > > tracked by CR0.TS bit. > > > > > > > > v3 changes from v2: > > > > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate > > bit > > > > exist. > > > > > > How about a "guest_xcr0_can_lazy_saverestore" bool to control this? > > > It only needs to be updated when guest xcr0 is updated. > > > > > > That seems cleaner. Avi? > > > > Reasoning below. > > > > > > v2 changes from v1: > > > > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > > > > > > > Signed-off-by: Xudong Hao <xudong.hao@intel.com> > > > > --- > > > > arch/x86/include/asm/kvm.h | 4 ++++ > > > > arch/x86/kvm/vmx.c | 2 ++ > > > > arch/x86/kvm/x86.c | 15 ++++++++++++++- > > > > 3 files changed, 20 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/vmx.c b/arch/x86/kvm/vmx.c > > > > index 248c2b4..853e875 100644 > > > > --- a/arch/x86/kvm/vmx.c > > > > +++ b/arch/x86/kvm/vmx.c > > > > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, > > unsigned long cr0) > > > > > > > > if (!vcpu->fpu_active) > > > > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > > > > + else > > > > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > > > > > > > vmcs_writel(CR0_READ_SHADOW, cr0); > > > > vmcs_writel(GUEST_CR0, hw_cr0); > > > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > > > index 20f2266..183cf60 100644 > > > > --- a/arch/x86/kvm/x86.c > > > > +++ b/arch/x86/kvm/x86.c > > > > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 > > index, u64 xcr) > > > > return 1; > > > > if (xcr0 & ~host_xcr0) > > > > return 1; > > > > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > > > > + vcpu->fpu_active = 1; > > > > This is confusing. The variable allows to decrease the number of places > > the decision is made. > > > > Hi, Marcelo, What does it mean? See Avi's reply. Better create a function lazy_fpu_allowed Which can be used to decide whether or not to allow guest owning FPU state. ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-12 8:10 [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU Xudong Hao 2012-09-13 16:26 ` Marcelo Tosatti @ 2012-09-13 16:38 ` Avi Kivity 2012-09-14 8:52 ` Hao, Xudong 1 sibling, 1 reply; 16+ messages in thread From: Avi Kivity @ 2012-09-13 16:38 UTC (permalink / raw) To: Xudong Hao; +Cc: kvm, xiantao.zhang On 09/12/2012 11:10 AM, Xudong Hao wrote: > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > tracked by CR0.TS bit. > > v3 changes from v2: > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate bit > exist. > > v2 changes from v1: > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c > index 248c2b4..853e875 100644 > --- a/arch/x86/kvm/vmx.c > +++ b/arch/x86/kvm/vmx.c > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > > if (!vcpu->fpu_active) > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > + else > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > Why? The guest may wish to receive #NM faults. > vmcs_writel(CR0_READ_SHADOW, cr0); > vmcs_writel(GUEST_CR0, hw_cr0); > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index 20f2266..183cf60 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) > return 1; > if (xcr0 & ~host_xcr0) > return 1; > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > + vcpu->fpu_active = 1; > vcpu->arch.xcr0 = xcr0; > vcpu->guest_xcr0_loaded = 0; > return 0; > @@ -5969,7 +5971,18 @@ 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 "currently", "till now", don't tell someone reading the code in six months anything. Just say how the code works. > + * 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); > } > > -- error compiling committee.c: too many arguments to function ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU 2012-09-13 16:38 ` Avi Kivity @ 2012-09-14 8:52 ` Hao, Xudong 0 siblings, 0 replies; 16+ messages in thread From: Hao, Xudong @ 2012-09-14 8:52 UTC (permalink / raw) To: Avi Kivity; +Cc: kvm@vger.kernel.org, Zhang, Xiantao > -----Original Message----- > From: kvm-owner@vger.kernel.org [mailto:kvm-owner@vger.kernel.org] On > Behalf Of Avi Kivity > Sent: Friday, September 14, 2012 12:39 AM > To: Hao, Xudong > Cc: kvm@vger.kernel.org; Zhang, Xiantao > Subject: Re: [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU > > On 09/12/2012 11:10 AM, Xudong Hao wrote: > > Enable KVM FPU fully eager restore, if there is other FPU state which isn't > > tracked by CR0.TS bit. > > > > v3 changes from v2: > > - Make fpu active explicitly while guest xsave is enabling and non-lazy xstate > bit > > exist. > > > > v2 changes from v1: > > - Expand KVM_XSTATE_LAZY to 64 bits before negating it. > > > > diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c > > index 248c2b4..853e875 100644 > > --- a/arch/x86/kvm/vmx.c > > +++ b/arch/x86/kvm/vmx.c > > @@ -3028,6 +3028,8 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, > unsigned long cr0) > > > > if (!vcpu->fpu_active) > > hw_cr0 |= X86_CR0_TS | X86_CR0_MP; > > + else > > + hw_cr0 &= ~(X86_CR0_TS | X86_CR0_MP); > > > > Why? The guest may wish to receive #NM faults. > Hmm, I wanted to clear TS bit to avoid vmexit if fpu_active=1, but missing to consider the guest inside. > > vmcs_writel(CR0_READ_SHADOW, cr0); > > vmcs_writel(GUEST_CR0, hw_cr0); > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > index 20f2266..183cf60 100644 > > --- a/arch/x86/kvm/x86.c > > +++ b/arch/x86/kvm/x86.c > > @@ -560,6 +560,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, > u64 xcr) > > return 1; > > if (xcr0 & ~host_xcr0) > > return 1; > > + if (xcr0 & ~((u64)KVM_XSTATE_LAZY)) > > + vcpu->fpu_active = 1; > > vcpu->arch.xcr0 = xcr0; > > vcpu->guest_xcr0_loaded = 0; > > return 0; > > @@ -5969,7 +5971,18 @@ 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 > > "currently", "till now", don't tell someone reading the code in six > months anything. Just say how the code works. > Okay. ^ permalink raw reply [flat|nested] 16+ messages in thread
end of thread, other threads:[~2012-09-23 9:03 UTC | newest] Thread overview: 16+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2012-09-12 8:10 [PATCH v3] kvm/fpu: Enable fully eager restore kvm FPU Xudong Hao 2012-09-13 16:26 ` Marcelo Tosatti 2012-09-13 16:29 ` Marcelo Tosatti 2012-09-13 16:40 ` Avi Kivity 2012-09-17 2:07 ` Hao, Xudong 2012-09-17 13:30 ` Marcelo Tosatti 2012-09-18 1:08 ` Hao, Xudong 2012-09-19 10:23 ` Avi Kivity 2012-09-20 1:43 ` Hao, Xudong 2012-09-20 9:19 ` Avi Kivity 2012-09-21 8:47 ` Hao, Xudong 2012-09-23 9:03 ` Avi Kivity 2012-09-14 8:54 ` Hao, Xudong 2012-09-14 9:35 ` Marcelo Tosatti 2012-09-13 16:38 ` Avi Kivity 2012-09-14 8:52 ` Hao, Xudong
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.