[v6,4/6] KVM: PPC: Book3S HV: Nested support in H_RPT_INVALIDATE

Enable support for process-scoped invalidations from nested
guests and partition-scoped invalidations for nested guests.

Process-scoped invalidations for any level of nested guests
are handled by implementing H_RPT_INVALIDATE handler in the
nested guest exit path in L0.

Partition-scoped invalidation requests are forwarded to the
right nested guest, handled there and passed down to L0
for eventual handling.

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
	[Nested guest partition-scoped invalidation changes]
---
 arch/powerpc/include/asm/kvm_book3s.h |   3 +
 arch/powerpc/kvm/book3s_hv.c          |  71 +++++++++++++++++-
 arch/powerpc/kvm/book3s_hv_nested.c   | 104 ++++++++++++++++++++++++++
 3 files changed, 175 insertions(+), 3 deletions(-)

On Thu, Mar 11, 2021 at 02:09:37PM +0530, Bharata B Rao wrote:
> Enable support for process-scoped invalidations from nested
> guests and partition-scoped invalidations for nested guests.
> 
> Process-scoped invalidations for any level of nested guests
> are handled by implementing H_RPT_INVALIDATE handler in the
> nested guest exit path in L0.
> 
> Partition-scoped invalidation requests are forwarded to the
> right nested guest, handled there and passed down to L0
> for eventual handling.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> 	[Nested guest partition-scoped invalidation changes]

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  arch/powerpc/include/asm/kvm_book3s.h |   3 +
>  arch/powerpc/kvm/book3s_hv.c          |  71 +++++++++++++++++-
>  arch/powerpc/kvm/book3s_hv_nested.c   | 104 ++++++++++++++++++++++++++
>  3 files changed, 175 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
> index 2f5f919f6cd3..de8fc5a4d19c 100644
> --- a/arch/powerpc/include/asm/kvm_book3s.h
> +++ b/arch/powerpc/include/asm/kvm_book3s.h
> @@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
>  void kvmhv_release_all_nested(struct kvm *kvm);
>  long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
>  long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
> +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
> +			     unsigned long type, unsigned long pg_sizes,
> +			     unsigned long start, unsigned long end);
>  int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
>  			  u64 time_limit, unsigned long lpcr);
>  void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 5d008468347c..03755389efd1 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -922,6 +922,46 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
>  	return yield_count;
>  }
>  
> +/*
> + * H_RPT_INVALIDATE hcall handler for nested guests.
> + *
> + * Handles only nested process-scoped invalidation requests in L0.
> + */
> +static int kvmppc_nested_h_rpt_invalidate(struct kvm_vcpu *vcpu)
> +{
> +	unsigned long type = kvmppc_get_gpr(vcpu, 6);
> +	unsigned long pid, pg_sizes, start, end, psize;
> +	struct kvm_nested_guest *gp;
> +	struct mmu_psize_def *def;
> +
> +	/*
> +	 * The partition-scoped invalidations aren't handled here in L0.
> +	 */
> +	if (type & H_RPTI_TYPE_NESTED)
> +		return RESUME_HOST;
> +
> +	pid = kvmppc_get_gpr(vcpu, 4);
> +	pg_sizes = kvmppc_get_gpr(vcpu, 7);
> +	start = kvmppc_get_gpr(vcpu, 8);
> +	end = kvmppc_get_gpr(vcpu, 9);
> +
> +	gp = kvmhv_get_nested(vcpu->kvm, vcpu->kvm->arch.lpid, false);
> +	if (!gp)
> +		goto out;
> +
> +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +		def = &mmu_psize_defs[psize];
> +		if (pg_sizes & def->h_rpt_pgsize)
> +			do_h_rpt_invalidate_prt(pid, gp->shadow_lpid, type,
> +						(1UL << def->shift), psize,
> +						start, end);
> +	}
> +	kvmhv_put_nested(gp);
> +out:
> +	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
> +	return RESUME_GUEST;
> +}
> +
>  static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
>  				    unsigned long id, unsigned long target,
>  				    unsigned long type, unsigned long pg_sizes,
> @@ -938,10 +978,18 @@ static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
>  
>  	/*
>  	 * Partition-scoped invalidation for nested guests.
> -	 * Not yet supported
>  	 */
> -	if (type & H_RPTI_TYPE_NESTED)
> -		return H_P3;
> +	if (type & H_RPTI_TYPE_NESTED) {
> +		if (!nesting_enabled(vcpu->kvm))
> +			return H_FUNCTION;
> +
> +		/* Support only cores as target */
> +		if (target != H_RPTI_TARGET_CMMU)
> +			return H_P2;
> +
> +		return do_h_rpt_invalidate_pat(vcpu, id, type, pg_sizes,
> +					       start, end);
> +	}
>  
>  	/*
>  	 * Process-scoped invalidation for L1 guests.
> @@ -1636,6 +1684,23 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
>  		if (!xics_on_xive())
>  			kvmppc_xics_rm_complete(vcpu, 0);
>  		break;
> +	case BOOK3S_INTERRUPT_SYSCALL:
> +	{
> +		unsigned long req = kvmppc_get_gpr(vcpu, 3);
> +
> +		/*
> +		 * The H_RPT_INVALIDATE hcalls issued by nested
> +		 * guests for process-scoped invalidations when
> +		 * GTSE=0, are handled here in L0.
> +		 */
> +		if (req == H_RPT_INVALIDATE) {
> +			r = kvmppc_nested_h_rpt_invalidate(vcpu);
> +			break;
> +		}
> +
> +		r = RESUME_HOST;
> +		break;
> +	}
>  	default:
>  		r = RESUME_HOST;
>  		break;
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 0cd0e7aad588..adcc8e26ef22 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -1191,6 +1191,110 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
>  	return H_SUCCESS;
>  }
>  
> +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long ap,
> +					 unsigned long start,
> +					 unsigned long end)
> +{
> +	unsigned long addr = start;
> +	int ret;
> +
> +	do {
> +		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
> +						   get_epn(addr));
> +		if (ret)
> +			return ret;
> +		addr += page_size;
> +	} while (addr < end);
> +
> +	return ret;
> +}
> +
> +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid, unsigned long ric)
> +{
> +	struct kvm *kvm = vcpu->kvm;
> +	struct kvm_nested_guest *gp;
> +
> +	gp = kvmhv_get_nested(kvm, lpid, false);
> +	if (gp) {
> +		kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
> +		kvmhv_put_nested(gp);
> +	}
> +	return H_SUCCESS;
> +}
> +
> +/*
> + * Performs partition-scoped invalidations for nested guests
> + * as part of H_RPT_INVALIDATE hcall.
> + */
> +long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
> +			     unsigned long type, unsigned long pg_sizes,
> +			     unsigned long start, unsigned long end)
> +{
> +	struct kvm_nested_guest *gp;
> +	long ret;
> +	unsigned long psize, ap;
> +
> +	/*
> +	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
> +	 *
> +	 * However, nested KVM issues a L2 lpid flush call when creating
> +	 * partition table entries for L2. This happens even before the
> +	 * corresponding shadow lpid is created in HV which happens in
> +	 * H_ENTER_NESTED call. Since we can't differentiate this case from
> +	 * the invalid case, we ignore such flush requests and return success.
> +	 */
> +	gp = kvmhv_find_nested(vcpu->kvm, lpid);
> +	if (!gp)
> +		return H_SUCCESS;
> +
> +	/*
> +	 * A flush all request can be handled by a full lpid flush only.
> +	 */
> +	if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL)
> +		return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_ALL);
> +
> +#if 0
> +	/*
> +	 * We don't need to handle a PWC flush like process table here,
> +	 * because intermediate partition scoped table in nested guest doesn't
> +	 * really have PWC. Only level we have PWC is in L0 and for nested
> +	 * invalidate at L0 we always do kvm_flush_lpid() which does
> +	 * radix__flush_all_lpid(). For range invalidate at any level, we
> +	 * are not removing the higher level page tables and hence there is
> +	 * no PWC invalidate needed.
> +	 */
> +	if (type & H_RPTI_TYPE_PWC) {
> +		ret = do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_PWC);
> +		if (ret)
> +			return H_P4;
> +	}
> +#endif
> +
> +	if (start == 0 && end == -1)
> +		return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_TLB);
> +
> +	if (type & H_RPTI_TYPE_TLB) {
> +		struct mmu_psize_def *def;
> +
> +		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +			def = &mmu_psize_defs[psize];
> +			if (!(pg_sizes & def->h_rpt_pgsize))
> +				continue;
> +
> +			ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
> +							   (1UL << def->shift),
> +							   ap, start, end);
> +			if (ret)
> +				return H_P4;
> +		}
> +	}
> +	return H_SUCCESS;
> +}
> +
>  /* Used to convert a nested guest real address to a L1 guest real address */
>  static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
>  				       struct kvm_nested_guest *gp,