Re: [PATCH v5 5/7] arm64: KVM: Add interface to set guest value for TRFCR register

[Suzuki K Poulose <suzuki.poulose@arm.com>]

On 20/02/2024 10:09, James Clark wrote:
> Add an interface for the Coresight driver to use to set the value of the
> TRFCR register for the guest. This register controls the exclude
> settings for trace at different exception levels, and is used to honor
> the exclude_host and exclude_guest parameters from the Perf session.
> This will be used to later write TRFCR_EL1 on nVHE at guest switch. For
> VHE, the host trace is controlled by TRFCR_EL2 and thus we can write to
> the TRFCR_EL1 immediately. Because guest writes to the register are
> trapped, the value will persist and can't be modified.
> 
> Instead of adding a load of infrastructure to share the host's per-cpu
> offsets with the hypervisor, just define the new storage as a NR_CPUS
> array.
> 
> Signed-off-by: James Clark <james.clark@arm.com>
> ---
>   arch/arm64/include/asm/kvm_host.h |  3 +++
>   arch/arm64/kernel/image-vars.h    |  1 +
>   arch/arm64/kvm/debug.c            | 26 ++++++++++++++++++++++++++
>   3 files changed, 30 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index 85b5477bd1b4..56b7f7eca195 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -509,6 +509,7 @@ struct kvm_host_psci_config {
>   	bool psci_0_1_cpu_off_implemented;
>   	bool psci_0_1_migrate_implemented;
>   };
> +extern u64 ____cacheline_aligned kvm_guest_trfcr[NR_CPUS];
>   
>   extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
>   #define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)
> @@ -1174,6 +1175,7 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
>   void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
>   void kvm_clr_pmu_events(u32 clr);
>   bool kvm_set_pmuserenr(u64 val);
> +void kvm_etm_set_guest_trfcr(u64 trfcr_guest);
>   #else
>   static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
>   static inline void kvm_clr_pmu_events(u32 clr) {}
> @@ -1181,6 +1183,7 @@ static inline bool kvm_set_pmuserenr(u64 val)
>   {
>   	return false;
>   }
> +static inline void kvm_etm_set_guest_trfcr(u64 trfcr_guest) {}
>   #endif
>   
>   void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
> diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
> index 5e4dc72ab1bd..a451e4f10804 100644
> --- a/arch/arm64/kernel/image-vars.h
> +++ b/arch/arm64/kernel/image-vars.h
> @@ -59,6 +59,7 @@ KVM_NVHE_ALIAS(alt_cb_patch_nops);
>   
>   /* Global kernel state accessed by nVHE hyp code. */
>   KVM_NVHE_ALIAS(kvm_vgic_global_state);
> +KVM_NVHE_ALIAS(kvm_guest_trfcr);
>   
>   /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
>   KVM_NVHE_ALIAS(nvhe_hyp_panic_handler);
> diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
> index 49a13e72ddd2..c8d936ce6e2b 100644
> --- a/arch/arm64/kvm/debug.c
> +++ b/arch/arm64/kvm/debug.c
> @@ -22,6 +22,7 @@
>   				DBG_MDSCR_MDE)
>   
>   static DEFINE_PER_CPU(u64, mdcr_el2);
> +u64 ____cacheline_aligned kvm_guest_trfcr[NR_CPUS];
>   
>   /*
>    * save/restore_guest_debug_regs
> @@ -359,3 +360,28 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu)
>   	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE);
>   	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRFCR);
>   }
> +
> +/*
> + * Interface for the Coresight driver to use to set the value of the TRFCR
> + * register for the guest. This register controls the exclude settings for trace
> + * at different exception levels, and is used to honor the exclude_host and
> + * exclude_guest parameters from the Perf session.
> + *
> + * This will be used to later write TRFCR_EL1 on nVHE at guest switch. For VHE,
> + * the host trace is controlled by TRFCR_EL2 and thus we can write to the
> + * TRFCR_EL1 immediately. Because guest writes to the register are trapped, the
> + * value will persist and can't be modified. For pKVM, kvm_guest_trfcr can't
> + * be read by the hypervisor, so don't bother writing it.
> + */
> +void kvm_etm_set_guest_trfcr(u64 trfcr_guest)
> +{
> +	if (WARN_ON_ONCE(!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
> +							       ID_AA64DFR0_EL1_TraceFilt_SHIFT)))
> +		return;
> +
> +	if (has_vhe())
> +		write_sysreg_s(trfcr_guest, SYS_TRFCR_EL12);
> +	else if (!is_protected_kvm_enabled())
> +		kvm_guest_trfcr[smp_processor_id()] = trfcr_guest;

smp_processor_id() could sleep in some configurations ? Should we switch 
to raw_smp_processor_id() to be safer ?

Otherwise looks good to me.

Suzuki

> +}
> +EXPORT_SYMBOL_GPL(kvm_etm_set_guest_trfcr);