From: Sean Christopherson <[email protected]>
Add an OVERRIDE flag to KVM_CAP_X86_DISABLE_EXITS allow userspace to
re-enable exits and/or override previous settings. There's no real use
case for the the per-VM ioctl, but a future per-vCPU variant wants to let
userspace toggle interception while the vCPU is running; add the OVERRIDE
functionality now to provide consistent between between the per-VM and
per-vCPU variants.
Signed-off-by: Sean Christopherson <[email protected]>
---
Documentation/virt/kvm/api.rst | 5 +++++
arch/x86/kvm/x86.c | 39 +++++++++++++++++++++++-----------
include/uapi/linux/kvm.h | 4 +++-
3 files changed, 35 insertions(+), 13 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index d0d8749591a8..89e13b6783b5 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6941,6 +6941,7 @@ Valid bits in args[0] are::
#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
+ #define KVM_X86_DISABLE_EXITS_OVERRIDE (1ull << 63)
Enabling this capability on a VM provides userspace with a way to no
longer intercept some instructions for improved latency in some
@@ -6949,6 +6950,10 @@ physical CPUs. More bits can be added in the future; userspace can
just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
all such vmexits.
+By default, this capability only disables exits. To re-enable an exit, or to
+override previous settings, userspace can set KVM_X86_DISABLE_EXITS_OVERRIDE,
+in which case KVM will enable/disable according to the mask (a '1' == disable).
+
Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
7.14 KVM_CAP_S390_HPAGE_1M
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f31ebbb1b94f..7cc8ac550bc7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4201,11 +4201,10 @@ static inline bool kvm_can_mwait_in_guest(void)
static u64 kvm_get_allowed_disable_exits(void)
{
- u64 r = KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
- KVM_X86_DISABLE_EXITS_CSTATE;
+ u64 r = KVM_X86_DISABLE_VALID_EXITS;
- if(kvm_can_mwait_in_guest())
- r |= KVM_X86_DISABLE_EXITS_MWAIT;
+ if (!kvm_can_mwait_in_guest())
+ r &= ~KVM_X86_DISABLE_EXITS_MWAIT;
return r;
}
@@ -5264,6 +5263,28 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu,
return r;
}
+
+#define kvm_ioctl_disable_exits(a, mask) \
+({ \
+ if (!kvm_can_mwait_in_guest()) \
+ (mask) &= KVM_X86_DISABLE_EXITS_MWAIT; \
+ if ((mask) & KVM_X86_DISABLE_EXITS_OVERRIDE) { \
+ (a).mwait_in_guest = (mask) & KVM_X86_DISABLE_EXITS_MWAIT; \
+ (a).hlt_in_guest = (mask) & KVM_X86_DISABLE_EXITS_HLT; \
+ (a).pause_in_guest = (mask) & KVM_X86_DISABLE_EXITS_PAUSE; \
+ (a).cstate_in_guest = (mask) & KVM_X86_DISABLE_EXITS_CSTATE; \
+ } else { \
+ if ((mask) & KVM_X86_DISABLE_EXITS_MWAIT) \
+ (a).mwait_in_guest = true; \
+ if ((mask) & KVM_X86_DISABLE_EXITS_HLT) \
+ (a).hlt_in_guest = true; \
+ if ((mask) & KVM_X86_DISABLE_EXITS_PAUSE) \
+ (a).pause_in_guest = true; \
+ if ((mask) & KVM_X86_DISABLE_EXITS_CSTATE) \
+ (a).cstate_in_guest = true; \
+ } \
+})
+
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
struct kvm_enable_cap *cap)
{
@@ -6018,14 +6039,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
if (kvm->created_vcpus)
goto disable_exits_unlock;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT)
- kvm->arch.mwait_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
- kvm->arch.hlt_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
- kvm->arch.pause_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
- kvm->arch.cstate_in_guest = true;
+ kvm_ioctl_disable_exits(kvm->arch, cap->args[0]);
+
r = 0;
disable_exits_unlock:
mutex_unlock(&kvm->lock);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 5088bd9f1922..f2e76e436be5 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -814,10 +814,12 @@ struct kvm_ioeventfd {
#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
+#define KVM_X86_DISABLE_EXITS_OVERRIDE (1ull << 63)
#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
KVM_X86_DISABLE_EXITS_HLT | \
KVM_X86_DISABLE_EXITS_PAUSE | \
- KVM_X86_DISABLE_EXITS_CSTATE)
+ KVM_X86_DISABLE_EXITS_CSTATE | \
+ KVM_X86_DISABLE_EXITS_OVERRIDE)
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
--
2.32.0
On Tue, Jun 14, 2022 at 06:16:19PM -0700, Kechen Lu wrote:
>From: Sean Christopherson <[email protected]>
>
>Add an OVERRIDE flag to KVM_CAP_X86_DISABLE_EXITS allow userspace to
>re-enable exits and/or override previous settings. There's no real use
>case for the the per-VM ioctl, but a future per-vCPU variant wants to let
>userspace toggle interception while the vCPU is running; add the OVERRIDE
>functionality now to provide consistent between between the per-VM and
>per-vCPU variants.
>
>Signed-off-by: Sean Christopherson <[email protected]>
>---
> Documentation/virt/kvm/api.rst | 5 +++++
> arch/x86/kvm/x86.c | 39 +++++++++++++++++++++++-----------
> include/uapi/linux/kvm.h | 4 +++-
> 3 files changed, 35 insertions(+), 13 deletions(-)
>
>diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
>index d0d8749591a8..89e13b6783b5 100644
>--- a/Documentation/virt/kvm/api.rst
>+++ b/Documentation/virt/kvm/api.rst
>@@ -6941,6 +6941,7 @@ Valid bits in args[0] are::
> #define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
> #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
> #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
>+ #define KVM_X86_DISABLE_EXITS_OVERRIDE (1ull << 63)
>
> Enabling this capability on a VM provides userspace with a way to no
> longer intercept some instructions for improved latency in some
>@@ -6949,6 +6950,10 @@ physical CPUs. More bits can be added in the future; userspace can
> just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
> all such vmexits.
>
>+By default, this capability only disables exits. To re-enable an exit, or to
>+override previous settings, userspace can set KVM_X86_DISABLE_EXITS_OVERRIDE,
>+in which case KVM will enable/disable according to the mask (a '1' == disable).
>+
> Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
>
> 7.14 KVM_CAP_S390_HPAGE_1M
>diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>index f31ebbb1b94f..7cc8ac550bc7 100644
>--- a/arch/x86/kvm/x86.c
>+++ b/arch/x86/kvm/x86.c
>@@ -4201,11 +4201,10 @@ static inline bool kvm_can_mwait_in_guest(void)
>
> static u64 kvm_get_allowed_disable_exits(void)
> {
>- u64 r = KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
>- KVM_X86_DISABLE_EXITS_CSTATE;
>+ u64 r = KVM_X86_DISABLE_VALID_EXITS;
>
>- if(kvm_can_mwait_in_guest())
>- r |= KVM_X86_DISABLE_EXITS_MWAIT;
>+ if (!kvm_can_mwait_in_guest())
>+ r &= ~KVM_X86_DISABLE_EXITS_MWAIT;
This hunk looks like a fix to patch 3; it can be squashed into that patch.
On Wed, Jun 15, 2022, Chao Gao wrote:
> On Tue, Jun 14, 2022 at 06:16:19PM -0700, Kechen Lu wrote:
> > 7.14 KVM_CAP_S390_HPAGE_1M
> >diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> >index f31ebbb1b94f..7cc8ac550bc7 100644
> >--- a/arch/x86/kvm/x86.c
> >+++ b/arch/x86/kvm/x86.c
> >@@ -4201,11 +4201,10 @@ static inline bool kvm_can_mwait_in_guest(void)
> >
> > static u64 kvm_get_allowed_disable_exits(void)
> > {
> >- u64 r = KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
> >- KVM_X86_DISABLE_EXITS_CSTATE;
> >+ u64 r = KVM_X86_DISABLE_VALID_EXITS;
> >
> >- if(kvm_can_mwait_in_guest())
> >- r |= KVM_X86_DISABLE_EXITS_MWAIT;
> >+ if (!kvm_can_mwait_in_guest())
> >+ r &= ~KVM_X86_DISABLE_EXITS_MWAIT;
>
> This hunk looks like a fix to patch 3; it can be squashed into that patch.
It's not a fix, just an inversion of the logic to make it easier to maintain
going forward. I intentionally made the change in patch 4 so that adding the
kvm_get_allowed_disable_exits() is a more "pure" movement of code from the "check"
path to a common helper.
I agree it's kinda odd, but I still think splitting the changes is desirable.