[PATCH v1] KVM: PPC: Book3S HV P9: implement kvmppc_xive_pull_vcpu in C

[Cédric Le Goater]

On 4/13/21 3:38 PM, Nicholas Piggin wrote:
> This is more symmetric with kvmppc_xive_push_vcpu, and has the advantage
> that it runs with the MMU on.
> 
> The extra test added to the asm will go away with a future change.
> 
> Reviewed-by: Cédric Le Goater <clg at kaod.org>
> Reviewed-by: Alexey Kardashevskiy <aik at ozlabs.ru>
> Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
> ---
> Another bit that came from the KVM Cify series.
> 
> Thanks,
> Nick
> 
>  arch/powerpc/include/asm/kvm_ppc.h      |  2 ++
>  arch/powerpc/kvm/book3s_hv.c            |  2 ++
>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |  5 ++++
>  arch/powerpc/kvm/book3s_xive.c          | 31 +++++++++++++++++++++++++
>  4 files changed, 40 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 9531b1c1b190..73b1ca5a6471 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -672,6 +672,7 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
>  extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
>  			       int level, bool line_status);
>  extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
> +extern void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu);
>  
>  static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
>  {
> @@ -712,6 +713,7 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur
>  static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
>  				      int level, bool line_status) { return -ENODEV; }
>  static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
> +static inline void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) { }
>  
>  static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
>  	{ return 0; }
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 4a532410e128..981bcaf787a8 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -3570,6 +3570,8 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
>  
>  	trap = __kvmhv_vcpu_entry_p9(vcpu);
>  
> +	kvmppc_xive_pull_vcpu(vcpu);
> +
>  	/* Advance host PURR/SPURR by the amount used by guest */
>  	purr = mfspr(SPRN_PURR);
>  	spurr = mfspr(SPRN_SPURR);
> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> index 75405ef53238..c11597f815e4 100644
> --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> @@ -1442,6 +1442,11 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
>  	bl	kvmhv_accumulate_time
>  #endif
>  #ifdef CONFIG_KVM_XICS
> +	/* If we came in through the P9 short path, xive pull is done in C */
> +	lwz	r0, STACK_SLOT_SHORT_PATH(r1)
> +	cmpwi	r0, 0
> +	bne	1f
> +
>  	/* We are exiting, pull the VP from the XIVE */
>  	lbz	r0, VCPU_XIVE_PUSHED(r9)
>  	cmpwi	cr0, r0, 0
> diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
> index e7219b6f5f9a..741bf1f4387a 100644
> --- a/arch/powerpc/kvm/book3s_xive.c
> +++ b/arch/powerpc/kvm/book3s_xive.c
> @@ -127,6 +127,37 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu)
>  }
>  EXPORT_SYMBOL_GPL(kvmppc_xive_push_vcpu);
>  
> +/*
> + * Pull a vcpu's context from the XIVE on guest exit.
> + * This assumes we are in virtual mode (MMU on)
> + */
> +void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu)
> +{
> +	void __iomem *tima = local_paca->kvm_hstate.xive_tima_virt;
> +
> +	if (!vcpu->arch.xive_pushed)
> +		return;
> +
> +	/*
> +	 * Should not have been pushed if there is no tima
> +	 */
> +	if (WARN_ON(!tima))
> +		return;
> +
> +	eieio();
> +	/* First load to pull the context, we ignore the value */
> +	__raw_readl(tima + TM_SPC_PULL_OS_CTX);
> +	/* Second load to recover the context state (Words 0 and 1) */
> +	vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS);

This load could be removed on P10, since HW is configured to do the same.
It should save a few cycles.

C. 

> +	/* Fixup some of the state for the next load */
> +	vcpu->arch.xive_saved_state.lsmfb = 0;
> +	vcpu->arch.xive_saved_state.ack = 0xff;
> +	vcpu->arch.xive_pushed = 0;
> +	eieio();
> +}
> +EXPORT_SYMBOL_GPL(kvmppc_xive_pull_vcpu);
> +
>  /*
>   * This is a simple trigger for a generic XIVE IRQ. This must
>   * only be called for interrupts that support a trigger page
>