[PATCH 3/6] KVM: PPC: Book3S HV P9: Move cede logic out of XIVE escalation rearming

[Fabiano Rosas]

Nicholas Piggin <npiggin at gmail.com> writes:

> Move the cede abort logic out of xive escalation rearming and into
> the caller to prepare for handling a similar case with nested guest
> entry.
>
> Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
> ---
>  arch/powerpc/include/asm/kvm_ppc.h |  4 ++--
>  arch/powerpc/kvm/book3s_hv.c       | 10 ++++++++--
>  arch/powerpc/kvm/book3s_xive.c     |  9 ++++++---
>  3 files changed, 16 insertions(+), 7 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index a14dbcd1b8ce..94fa5f246657 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -671,7 +671,7 @@ 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);
> -extern void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu);
> +extern bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu);
>
>  static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
>  {
> @@ -709,7 +709,7 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir
>  				      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 void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { }
> +static inline bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { return true; }
>
>  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 5df359053147..a0b674d3a2da 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -4073,10 +4073,16 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
>  		    !(vcpu->arch.shregs.msr & MSR_PR)) {
>  			unsigned long req = kvmppc_get_gpr(vcpu, 3);
>
> -			/* H_CEDE has to be handled now, not later */
> +			/* H_CEDE has to be handled now */
>  			if (req == H_CEDE) {
>  				kvmppc_cede(vcpu);
> -				kvmppc_xive_rearm_escalation(vcpu); /* may un-cede */
> +				if (!kvmppc_xive_rearm_escalation(vcpu)) {
> +					/*
> +					 * Pending escalation so abort
> +					 * the cede.
> +					 */
> +					vcpu->arch.ceded = 0;

This was moved after the mb() in kvmppc_xive_rearm_escalation, so I
think a concurrent H_PROD might continue to see tvcpu->arch.ceded = 1
after the escalation has been set. Is this an issue?

> +				}
>  				kvmppc_set_gpr(vcpu, 3, 0);
>  				trap = 0;
>
> diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
> index e216c068075d..7b513e14cada 100644
> --- a/arch/powerpc/kvm/book3s_xive.c
> +++ b/arch/powerpc/kvm/book3s_xive.c
> @@ -179,12 +179,13 @@ void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu)
>  }
>  EXPORT_SYMBOL_GPL(kvmppc_xive_pull_vcpu);
>
> -void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu)
> +bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu)
>  {
>  	void __iomem *esc_vaddr = (void __iomem *)vcpu->arch.xive_esc_vaddr;
> +	bool ret = true;
>
>  	if (!esc_vaddr)
> -		return;
> +		return ret;
>
>  	/* we are using XIVE with single escalation */
>
> @@ -197,7 +198,7 @@ void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu)
>  		 * we also don't want to set xive_esc_on to 1 here in
>  		 * case we race with xive_esc_irq().
>  		 */
> -		vcpu->arch.ceded = 0;
> +		ret = false;
>  		/*
>  		 * The escalation interrupts are special as we don't EOI them.
>  		 * There is no need to use the load-after-store ordering offset
> @@ -210,6 +211,8 @@ void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu)
>  		__raw_readq(esc_vaddr + XIVE_ESB_SET_PQ_00);
>  	}
>  	mb();
> +
> +	return ret;
>  }
>  EXPORT_SYMBOL_GPL(kvmppc_xive_rearm_escalation);