On Thu, Dec 14, 2023 at 5:53 AM Vitaly Kuznetsov <vkuznets@xxxxxxxxxx> wrote:
>
> "Vineeth Pillai (Google)" <vineeth@xxxxxxxxxxxxxxx> writes:
>
> > Implement a kvm MSR that guest uses to provide the GPA of shared memory
> > for communicating the scheduling information between host and guest.
> >
> > wrmsr(0) disables the feature. wrmsr(valid_gpa) enables the feature and
> > uses the gpa for further communication.
> >
> > Also add a new cpuid feature flag for the host to advertise the feature
> > to the guest.
> >
> > Co-developed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
> > Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
> > Signed-off-by: Vineeth Pillai (Google) <vineeth@xxxxxxxxxxxxxxx>
> > ---
> > arch/x86/include/asm/kvm_host.h | 25 ++++++++++++
> > arch/x86/include/uapi/asm/kvm_para.h | 24 +++++++++++
> > arch/x86/kvm/Kconfig | 12 ++++++
> > arch/x86/kvm/cpuid.c | 2 +
> > arch/x86/kvm/x86.c | 61 ++++++++++++++++++++++++++++
> > include/linux/kvm_host.h | 5 +++
> > 6 files changed, 129 insertions(+)
> >
> > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> > index f72b30d2238a..f89ba1f07d88 100644
> > --- a/arch/x86/include/asm/kvm_host.h
> > +++ b/arch/x86/include/asm/kvm_host.h
> > @@ -987,6 +987,18 @@ struct kvm_vcpu_arch {
> > /* Protected Guests */
> > bool guest_state_protected;
> >
> > +#ifdef CONFIG_PARAVIRT_SCHED_KVM
> > + /*
> > + * MSR to setup a shared memory for scheduling
> > + * information sharing between host and guest.
> > + */
> > + struct {
> > + enum kvm_vcpu_boost_state boost_status;
> > + u64 msr_val;
> > + struct gfn_to_hva_cache data;
> > + } pv_sched;
> > +#endif
> > +
> > /*
> > * Set when PDPTS were loaded directly by the userspace without
> > * reading the guest memory
> > @@ -2217,4 +2229,17 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
> > */
> > #define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
> >
> > +#ifdef CONFIG_PARAVIRT_SCHED_KVM
> > +static inline bool kvm_arch_vcpu_pv_sched_enabled(struct kvm_vcpu_arch *arch)
> > +{
> > + return arch->pv_sched.msr_val;
> > +}
> > +
> > +static inline void kvm_arch_vcpu_set_boost_status(struct kvm_vcpu_arch *arch,
> > + enum kvm_vcpu_boost_state boost_status)
> > +{
> > + arch->pv_sched.boost_status = boost_status;
> > +}
> > +#endif
> > +
> > #endif /* _ASM_X86_KVM_HOST_H */
> > diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
> > index 6e64b27b2c1e..6b1dea07a563 100644
> > --- a/arch/x86/include/uapi/asm/kvm_para.h
> > +++ b/arch/x86/include/uapi/asm/kvm_para.h
> > @@ -36,6 +36,7 @@
> > #define KVM_FEATURE_MSI_EXT_DEST_ID 15
> > #define KVM_FEATURE_HC_MAP_GPA_RANGE 16
> > #define KVM_FEATURE_MIGRATION_CONTROL 17
> > +#define KVM_FEATURE_PV_SCHED 18
> >
> > #define KVM_HINTS_REALTIME 0
> >
> > @@ -58,6 +59,7 @@
> > #define MSR_KVM_ASYNC_PF_INT 0x4b564d06
> > #define MSR_KVM_ASYNC_PF_ACK 0x4b564d07
> > #define MSR_KVM_MIGRATION_CONTROL 0x4b564d08
> > +#define MSR_KVM_PV_SCHED 0x4b564da0
> >
> > struct kvm_steal_time {
> > __u64 steal;
> > @@ -150,4 +152,26 @@ struct kvm_vcpu_pv_apf_data {
> > #define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
> > #define KVM_PV_EOI_DISABLED 0x0
> >
> > +/*
> > + * VCPU boost state shared between the host and guest.
> > + */
> > +enum kvm_vcpu_boost_state {
> > + /* Priority boosting feature disabled in host */
> > + VCPU_BOOST_DISABLED = 0,
> > + /*
> > + * vcpu is not explicitly boosted by the host.
> > + * (Default priority when the guest started)
> > + */
> > + VCPU_BOOST_NORMAL,
> > + /* vcpu is boosted by the host */
> > + VCPU_BOOST_BOOSTED
> > +};
> > +
> > +/*
> > + * Structure passed in via MSR_KVM_PV_SCHED
> > + */
> > +struct pv_sched_data {
> > + __u64 boost_status;
> > +};
> > +
> > #endif /* _UAPI_ASM_X86_KVM_PARA_H */
> > diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> > index 89ca7f4c1464..dbcba73fb508 100644
> > --- a/arch/x86/kvm/Kconfig
> > +++ b/arch/x86/kvm/Kconfig
> > @@ -141,4 +141,16 @@ config KVM_XEN
> > config KVM_EXTERNAL_WRITE_TRACKING
> > bool
> >
> > +config PARAVIRT_SCHED_KVM
> > + bool "Enable paravirt scheduling capability for kvm"
> > + depends on KVM
> > + help
> > + Paravirtualized scheduling facilitates the exchange of scheduling
> > + related information between the host and guest through shared memory,
> > + enhancing the efficiency of vCPU thread scheduling by the hypervisor.
> > + An illustrative use case involves dynamically boosting the priority of
> > + a vCPU thread when the guest is executing a latency-sensitive workload
> > + on that specific vCPU.
> > + This config enables paravirt scheduling in the kvm hypervisor.
> > +
> > endif # VIRTUALIZATION
> > diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> > index 7bdc66abfc92..960ef6e869f2 100644
> > --- a/arch/x86/kvm/cpuid.c
> > +++ b/arch/x86/kvm/cpuid.c
> > @@ -1113,6 +1113,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
> > (1 << KVM_FEATURE_POLL_CONTROL) |
> > (1 << KVM_FEATURE_PV_SCHED_YIELD) |
> > (1 << KVM_FEATURE_ASYNC_PF_INT);
> > + if (IS_ENABLED(CONFIG_PARAVIRT_SCHED_KVM))
> > + entry->eax |= (1 << KVM_FEATURE_PV_SCHED);
> >
> > if (sched_info_on())
> > entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> > index 7bcf1a76a6ab..0f475b50ac83 100644
> > --- a/arch/x86/kvm/x86.c
> > +++ b/arch/x86/kvm/x86.c
> > @@ -3879,6 +3879,33 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
> > return 1;
> > break;
> >
> > +#ifdef CONFIG_PARAVIRT_SCHED_KVM
> > + case MSR_KVM_PV_SCHED:
> > + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED))
> > + return 1;
> > +
> > + if (!(data & KVM_MSR_ENABLED))
> > + break;
> > +
> > + if (!(data & ~KVM_MSR_ENABLED)) {
> > + /*
> > + * Disable the feature
> > + */
> > + vcpu->arch.pv_sched.msr_val = 0;
> > + kvm_set_vcpu_boosted(vcpu, false);
> > + } if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
> > + &vcpu->arch.pv_sched.data, data & ~KVM_MSR_ENABLED,
> > + sizeof(struct pv_sched_data))) {
> > + vcpu->arch.pv_sched.msr_val = data;
> > + kvm_set_vcpu_boosted(vcpu, false);
> > + } else {
> > + pr_warn("MSR_KVM_PV_SCHED: kvm:%p, vcpu:%p, "
> > + "msr value: %llx, kvm_gfn_to_hva_cache_init failed!\n",
> > + vcpu->kvm, vcpu, data & ~KVM_MSR_ENABLED);
>
> As this is triggerable by the guest please drop this print (which is not
> even ratelimited!). I think it would be better to just 'return 1;' in case
> of kvm_gfn_to_hva_cache_init() failure but maybe you also need to
> account for 'msr_info->host_initiated' to not fail setting this MSR from
> the host upon migration.
>
Makes sense, shall remove the pr_warn.
I hadn't thought about migration, thanks for bringing this up. Will
make modifications to account for migration as well.
Thanks,
Vineeth
