Re: [PATCH v2 18/30] KVM: s390: pci: provide routines for enabling/disabling interpretation

[Pierre Morel <pmorel@linux.ibm.com>]

On 1/14/22 21:31, Matthew Rosato wrote:
> These routines will be wired into the vfio_pci_zdev ioctl handlers to
> respond to requests to enable / disable a device for zPCI Load/Store
> interpretation.
> 
> The first time such a request is received, enable the necessary facilities
> for the guest.
> 
> Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
> ---
>   arch/s390/include/asm/kvm_pci.h |  4 ++
>   arch/s390/kvm/pci.c             | 99 +++++++++++++++++++++++++++++++++
>   arch/s390/pci/pci.c             |  3 +
>   3 files changed, 106 insertions(+)
> 
> diff --git a/arch/s390/include/asm/kvm_pci.h b/arch/s390/include/asm/kvm_pci.h
> index aafee2976929..072401aa7922 100644
> --- a/arch/s390/include/asm/kvm_pci.h
> +++ b/arch/s390/include/asm/kvm_pci.h
> @@ -26,4 +26,8 @@ int kvm_s390_pci_dev_open(struct zpci_dev *zdev);
>   void kvm_s390_pci_dev_release(struct zpci_dev *zdev);
>   void kvm_s390_pci_attach_kvm(struct zpci_dev *zdev, struct kvm *kvm);
>   
> +int kvm_s390_pci_interp_probe(struct zpci_dev *zdev);
> +int kvm_s390_pci_interp_enable(struct zpci_dev *zdev);
> +int kvm_s390_pci_interp_disable(struct zpci_dev *zdev);
> +
>   #endif /* ASM_KVM_PCI_H */
> diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
> index dae853da6df1..122d0992b521 100644
> --- a/arch/s390/kvm/pci.c
> +++ b/arch/s390/kvm/pci.c
> @@ -12,7 +12,9 @@
>   #include <asm/kvm_pci.h>
>   #include <asm/pci.h>
>   #include <asm/pci_insn.h>
> +#include <asm/sclp.h>
>   #include "pci.h"
> +#include "kvm-s390.h"
>   
>   struct zpci_aift *aift;
>   
> @@ -143,6 +145,103 @@ int kvm_s390_pci_aen_init(u8 nisc)
>   	return rc;
>   }
>   
> +int kvm_s390_pci_interp_probe(struct zpci_dev *zdev)
> +{
> +	/* Must have appropriate hardware facilities */
> +	if (!(sclp.has_zpci_lsi && test_facility(69)))

Should'nt we also test the other facilities we need for the 
interpretation like ARNI, AISII, ASI and GISA ?

Or are we sure they are always there when ZPCI load/store interpretation 
is available?


> +		return -EINVAL;
> +
> +	/* Must have a KVM association registered */
> +	if (!zdev->kzdev || !zdev->kzdev->kvm)
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(kvm_s390_pci_interp_probe);
> +
> +int kvm_s390_pci_interp_enable(struct zpci_dev *zdev)
> +{
> +	u32 gd;
> +	int rc;
> +
> +	if (!zdev->kzdev || !zdev->kzdev->kvm)
> +		return -EINVAL;
> +
> +	/*
> +	 * If this is the first request to use an interpreted device, make the
> +	 * necessary vcpu changes
> +	 */
> +	if (!zdev->kzdev->kvm->arch.use_zpci_interp)
> +		kvm_s390_vcpu_pci_enable_interp(zdev->kzdev->kvm);
> +
> +	/*
> +	 * In the event of a system reset in userspace, the GISA designation
> +	 * may still be assigned because the device is still enabled.
> +	 * Verify it's the same guest before proceeding.
> +	 */
> +	gd = (u32)(u64)&zdev->kzdev->kvm->arch.sie_page2->gisa;

should use the virt_to_phys transformation ?

> +	if (zdev->gd != 0 && zdev->gd != gd)
> +		return -EPERM;
> +
> +	if (zdev_enabled(zdev)) {
> +		zdev->gd = 0;
> +		rc = zpci_disable_device(zdev);
> +		if (rc)
> +			return rc;
> +	}
> +
> +	/*
> +	 * Store information about the identity of the kvm guest allowed to
> +	 * access this device via interpretation to be used by host CLP
> +	 */
> +	zdev->gd = gd;
> +
> +	rc = zpci_enable_device(zdev);
> +	if (rc)
> +		goto err;
> +
> +	/* Re-register the IOMMU that was already created */
> +	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
> +				virt_to_phys(zdev->dma_table));
> +	if (rc)
> +		goto err;
> +
> +	return rc;
> +
> +err:
> +	zdev->gd = 0;
> +	return rc;
> +}
> +EXPORT_SYMBOL_GPL(kvm_s390_pci_interp_enable);
> +
> +int kvm_s390_pci_interp_disable(struct zpci_dev *zdev)
> +{
> +	int rc;
> +
> +	if (zdev->gd == 0)
> +		return -EINVAL;
> +
> +	/* Remove the host CLP guest designation */
> +	zdev->gd = 0;
> +
> +	if (zdev_enabled(zdev)) {
> +		rc = zpci_disable_device(zdev);
> +		if (rc)
> +			return rc;
> +	}
> +
> +	rc = zpci_enable_device(zdev);
> +	if (rc)
> +		return rc;
> +
> +	/* Re-register the IOMMU that was already created */
> +	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
> +				virt_to_phys(zdev->dma_table));
> +
> +	return rc;
> +}
> +EXPORT_SYMBOL_GPL(kvm_s390_pci_interp_disable);
> +
>   int kvm_s390_pci_dev_open(struct zpci_dev *zdev)
>   {
>   	struct kvm_zdev *kzdev;
> diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
> index 2a19becbc14c..58673f633869 100644
> --- a/arch/s390/pci/pci.c
> +++ b/arch/s390/pci/pci.c
> @@ -147,6 +147,7 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
>   		zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
>   	return cc;
>   }
> +EXPORT_SYMBOL_GPL(zpci_register_ioat);
>   
>   /* Modify PCI: Unregister I/O address translation parameters */
>   int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
> @@ -727,6 +728,7 @@ int zpci_enable_device(struct zpci_dev *zdev)
>   		zpci_update_fh(zdev, fh);
>   	return rc;
>   }
> +EXPORT_SYMBOL_GPL(zpci_enable_device);
>   
>   int zpci_disable_device(struct zpci_dev *zdev)
>   {
> @@ -750,6 +752,7 @@ int zpci_disable_device(struct zpci_dev *zdev)
>   	}
>   	return rc;
>   }
> +EXPORT_SYMBOL_GPL(zpci_disable_device);
>   
>   /**
>    * zpci_hot_reset_device - perform a reset of the given zPCI function
> 

-- 
Pierre Morel
IBM Lab Boeblingen