Re: [PATCH v1 03/13] KVM: s390: use __kvm_faultin_pfn()

["Christoph Schlameuss" <schlameuss@linux.ibm.com>]

On Wed Jan 8, 2025 at 7:14 PM CET, Claudio Imbrenda wrote:
> Refactor the existing page fault handling code to use __kvm_faultin_pfn().
>
> This possible now that memslots are always present.
>
> Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
> ---
>  arch/s390/kvm/kvm-s390.c | 92 +++++++++++++++++++++++++++++++---------
>  arch/s390/mm/gmap.c      |  1 +
>  2 files changed, 73 insertions(+), 20 deletions(-)

With nits resolved:

Reviewed-by: Christoph Schlameuss <schlameuss@linux.ibm.com>

>
> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
> index 797b8503c162..8e4e7e45238b 100644
> --- a/arch/s390/kvm/kvm-s390.c
> +++ b/arch/s390/kvm/kvm-s390.c
> @@ -4794,11 +4794,66 @@ static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu)
>  		current->thread.gmap_int_code, current->thread.gmap_teid.val);
>  }
>  
> +static int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr,
> +				     unsigned int flags)
> +{
> +	struct kvm_memory_slot *slot;
> +	unsigned int fault_flags;
> +	bool writable, unlocked;
> +	unsigned long vmaddr;
> +	struct page *page;
> +	kvm_pfn_t pfn;
> +	int rc;
> +
> +	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
> +	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
> +		return vcpu_post_run_addressing_exception(vcpu);
> +
> +	fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0;
> +	if (vcpu->arch.gmap->pfault_enabled)
> +		flags |= FOLL_NOWAIT;
> +	vmaddr = __gfn_to_hva_memslot(slot, gfn);
> +
> +try_again:
> +	pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page);
> +
> +	/* Access outside memory, inject addressing exception */
> +	if (is_noslot_pfn(pfn))
> +		return vcpu_post_run_addressing_exception(vcpu);
> +	/* Signal pending: try again */
> +	if (pfn == KVM_PFN_ERR_SIGPENDING)
> +		return -EAGAIN;
> +
> +	/* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */
> +	if (pfn == KVM_PFN_ERR_NEEDS_IO) {
> +		trace_kvm_s390_major_guest_pfault(vcpu);
> +		if (kvm_arch_setup_async_pf(vcpu))
> +			return 0;
> +		vcpu->stat.pfault_sync++;
> +		/* Could not setup async pfault, try again synchronously */
> +		flags &= ~FOLL_NOWAIT;
> +		goto try_again;
> +	}
> +	/* Any other error */
> +	if (is_error_pfn(pfn))
> +		return -EFAULT;
> +
> +	/* Success */
> +	mmap_read_lock(vcpu->arch.gmap->mm);
> +	/* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */
> +	rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked);
> +	if (!rc)
> +		rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr);
> +	kvm_release_faultin_page(vcpu->kvm, page, false, writable);
> +	mmap_read_unlock(vcpu->arch.gmap->mm);
> +	return rc;
> +}
> +
>  static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
>  {
> +	unsigned long gaddr, gaddr_tmp;
>  	unsigned int flags = 0;
> -	unsigned long gaddr;
> -	int rc = 0;
> +	gfn_t gfn;
>  
>  	gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
>  	if (kvm_s390_cur_gmap_fault_is_write())
> @@ -4850,29 +4905,26 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
>  	case PGM_REGION_SECOND_TRANS:
>  	case PGM_REGION_THIRD_TRANS:
>  		kvm_s390_assert_primary_as(vcpu);
> -		if (vcpu->arch.gmap->pfault_enabled) {
> -			rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT);
> -			if (rc == -EFAULT)
> -				return vcpu_post_run_addressing_exception(vcpu);
> -			if (rc == -EAGAIN) {
> -				trace_kvm_s390_major_guest_pfault(vcpu);
> -				if (kvm_arch_setup_async_pf(vcpu))
> -					return 0;
> -				vcpu->stat.pfault_sync++;
> -			} else {
> -				return rc;
> -			}
> -		}
> -		rc = gmap_fault(vcpu->arch.gmap, gaddr, flags);
> -		if (rc == -EFAULT) {
> -			if (kvm_is_ucontrol(vcpu->kvm)) {
> +
> +		gfn = gpa_to_gfn(gaddr);
> +		if (kvm_is_ucontrol(vcpu->kvm)) {
> +			/*
> +			 * This translates the per-vCPU guest address into a
> +			 * fake guest address, which can then be used with the
> +			 * fake memslots that are identity mapping userspace.
> +			 * This allows ucontrol VMs to use the normal fault
> +			 * resolution path, like normal VMs.
> +			 */
> +			gaddr_tmp = gmap_translate(vcpu->arch.gmap, gaddr);
> +			if (gaddr_tmp == -EFAULT) {
>  				vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
>  				vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
>  				vcpu->run->s390_ucontrol.pgm_code = 0x10;

nit: s/0x10/PGM_SEGMENT_TRANSLATION/

>  				return -EREMOTE;
>  			}
> -			return vcpu_post_run_addressing_exception(vcpu);
> +			gfn = gpa_to_gfn(gaddr_tmp);
>  		}
> +		return kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags);
>  		break;

nit: Remove the break after the return here?

>  	default:
>  		KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx",
> @@ -4880,7 +4932,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
>  		send_sig(SIGSEGV, current, 0);
>  		break;
>  	}
> -	return rc;
> +	return 0;
>  }
>  
>  static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
> diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
> index 16b8a36c56de..3aacef77c174 100644
> --- a/arch/s390/mm/gmap.c
> +++ b/arch/s390/mm/gmap.c
> @@ -605,6 +605,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
>  	radix_tree_preload_end();
>  	return rc;
>  }
> +EXPORT_SYMBOL(__gmap_link);
>  
>  /**
>   * fixup_user_fault_nowait - manually resolve a user page fault without waiting