Date:   Mon, 17 Jun 2019 11:07:53 -0400
From:   Tony Krowiak <akrowiak@...ux.ibm.com>
To:     Harald Freudenberger <freude@...ux.ibm.com>,
        linux-s390@...r.kernel.org, linux-kernel@...r.kernel.org,
        kvm@...r.kernel.org
Cc:     borntraeger@...ibm.com, cohuck@...hat.com, frankja@...ux.ibm.com,
        david@...hat.com, mjrosato@...ux.ibm.com, schwidefsky@...ibm.com,
        heiko.carstens@...ibm.com, pmorel@...ux.ibm.com,
        pasic@...ux.ibm.com, alex.williamson@...hat.com,
        kwankhede@...dia.com
Subject: Re: [PATCH v4 5/7] s390: vfio-ap: allow assignment of unavailable AP
 resources to mdev device

On 6/17/19 6:05 AM, Harald Freudenberger wrote:
> On 13.06.19 21:39, Tony Krowiak wrote:
>> The AP architecture does not preclude assignment of AP resources that are
>> not available. Let's go ahead and implement this facet of the AP
>> architecture for linux guests.
>>
>> The current implementation does not allow assignment of AP adapters or
>> domains to an mdev device if the APQNs resulting from the assignment
>> reference AP queue devices that are not bound to the vfio_ap device
>> driver. This patch allows assignment of AP resources to the mdev device as
>> long as the APQNs resulting from the assignment are not reserved by the AP
>> BUS for use by the zcrypt device drivers and the APQNs are not assigned to
>> another mdev device.
>>
>> Signed-off-by: Tony Krowiak <akrowiak@...ux.ibm.com>
>> ---
>>   drivers/s390/crypto/vfio_ap_ops.c | 231 ++++++++------------------------------
>>   1 file changed, 44 insertions(+), 187 deletions(-)
>>
>> diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
>> index 60efd3d7896d..9db86c0db52e 100644
>> --- a/drivers/s390/crypto/vfio_ap_ops.c
>> +++ b/drivers/s390/crypto/vfio_ap_ops.c
>> @@ -406,122 +406,6 @@ static struct attribute_group *vfio_ap_mdev_type_groups[] = {
>>   	NULL,
>>   };
>>   
>> -struct vfio_ap_queue_reserved {
>> -	unsigned long *apid;
>> -	unsigned long *apqi;
>> -	bool reserved;
>> -};
>> -
>> -/**
>> - * vfio_ap_has_queue
>> - *
>> - * @dev: an AP queue device
>> - * @data: a struct vfio_ap_queue_reserved reference
>> - *
>> - * Flags whether the AP queue device (@dev) has a queue ID containing the APQN,
>> - * apid or apqi specified in @data:
>> - *
>> - * - If @data contains both an apid and apqi value, then @data will be flagged
>> - *   as reserved if the APID and APQI fields for the AP queue device matches
>> - *
>> - * - If @data contains only an apid value, @data will be flagged as
>> - *   reserved if the APID field in the AP queue device matches
>> - *
>> - * - If @data contains only an apqi value, @data will be flagged as
>> - *   reserved if the APQI field in the AP queue device matches
>> - *
>> - * Returns 0 to indicate the input to function succeeded. Returns -EINVAL if
>> - * @data does not contain either an apid or apqi.
>> - */
>> -static int vfio_ap_has_queue(struct device *dev, void *data)
>> -{
>> -	struct vfio_ap_queue_reserved *qres = data;
>> -	struct ap_queue *ap_queue = to_ap_queue(dev);
>> -	ap_qid_t qid;
>> -	unsigned long id;
>> -
>> -	if (qres->apid && qres->apqi) {
>> -		qid = AP_MKQID(*qres->apid, *qres->apqi);
>> -		if (qid == ap_queue->qid)
>> -			qres->reserved = true;
>> -	} else if (qres->apid && !qres->apqi) {
>> -		id = AP_QID_CARD(ap_queue->qid);
>> -		if (id == *qres->apid)
>> -			qres->reserved = true;
>> -	} else if (!qres->apid && qres->apqi) {
>> -		id = AP_QID_QUEUE(ap_queue->qid);
>> -		if (id == *qres->apqi)
>> -			qres->reserved = true;
>> -	} else {
>> -		return -EINVAL;
>> -	}
>> -
>> -	return 0;
>> -}
>> -
>> -/**
>> - * vfio_ap_verify_queue_reserved
>> - *
>> - * @matrix_dev: a mediated matrix device
>> - * @apid: an AP adapter ID
>> - * @apqi: an AP queue index
>> - *
>> - * Verifies that the AP queue with @apid/@...i is reserved by the VFIO AP device
>> - * driver according to the following rules:
>> - *
>> - * - If both @apid and @apqi are not NULL, then there must be an AP queue
>> - *   device bound to the vfio_ap driver with the APQN identified by @apid and
>> - *   @apqi
>> - *
>> - * - If only @apid is not NULL, then there must be an AP queue device bound
>> - *   to the vfio_ap driver with an APQN containing @apid
>> - *
>> - * - If only @apqi is not NULL, then there must be an AP queue device bound
>> - *   to the vfio_ap driver with an APQN containing @apqi
>> - *
>> - * Returns 0 if the AP queue is reserved; otherwise, returns -EADDRNOTAVAIL.
>> - */
>> -static int vfio_ap_verify_queue_reserved(unsigned long *apid,
>> -					 unsigned long *apqi)
>> -{
>> -	int ret;
>> -	struct vfio_ap_queue_reserved qres;
>> -
>> -	qres.apid = apid;
>> -	qres.apqi = apqi;
>> -	qres.reserved = false;
>> -
>> -	ret = driver_for_each_device(&matrix_dev->vfio_ap_drv->driver, NULL,
>> -				     &qres, vfio_ap_has_queue);
>> -	if (ret)
>> -		return ret;
>> -
>> -	if (qres.reserved)
>> -		return 0;
>> -
>> -	return -EADDRNOTAVAIL;
>> -}
>> -
>> -static int
>> -vfio_ap_mdev_verify_queues_reserved_for_apid(struct ap_matrix_mdev *matrix_mdev,
>> -					     unsigned long apid)
>> -{
>> -	int ret;
>> -	unsigned long apqi;
>> -	unsigned long nbits = matrix_mdev->matrix.aqm_max + 1;
>> -
>> -	if (find_first_bit_inv(matrix_mdev->matrix.aqm, nbits) >= nbits)
>> -		return vfio_ap_verify_queue_reserved(&apid, NULL);
>> -
>> -	for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, nbits) {
>> -		ret = vfio_ap_verify_queue_reserved(&apid, &apqi);
>> -		if (ret)
>> -			return ret;
>> -	}
>> -
>> -	return 0;
>> -}
>> -
>>   /**
>>    * vfio_ap_mdev_verify_no_sharing
>>    *
>> @@ -529,18 +413,26 @@ vfio_ap_mdev_verify_queues_reserved_for_apid(struct ap_matrix_mdev *matrix_mdev,
>>    * and AP queue indexes comprising the AP matrix are not configured for another
>>    * mediated device. AP queue sharing is not allowed.
>>    *
>> - * @matrix_mdev: the mediated matrix device
>> + * @mdev_apm: the mask identifying the adapters assigned to mdev
>> + * @mdev_apm: the mask identifying the adapters assigned to mdev
> I assume you wanted to write @mdev_aqm ... queues ... at the 2nd line.

You assumed correctly. I also mean to say "domains assigned to mdev".

>>    *
>>    * Returns 0 if the APQNs are not shared, otherwise; returns -EADDRINUSE.
>>    */
>> -static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev)
>> +static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm,
>> +					  unsigned long *mdev_aqm)
>>   {
>>   	struct ap_matrix_mdev *lstdev;
>>   	DECLARE_BITMAP(apm, AP_DEVICES);
>>   	DECLARE_BITMAP(aqm, AP_DOMAINS);
>>   
>>   	list_for_each_entry(lstdev, &matrix_dev->mdev_list, node) {
>> -		if (matrix_mdev == lstdev)
>> +		/*
>> +		 * If either of the input masks belongs to the mdev to which an
>> +		 * AP resource is being assigned, then we don't need to verify
>> +		 * that mdev's masks.
>> +		 */
>> +		if ((mdev_apm == lstdev->matrix.apm) ||
>> +		    (mdev_aqm == lstdev->matrix.aqm))
>>   			continue;
>>   
>>   		memset(apm, 0, sizeof(apm));
>> @@ -550,12 +442,10 @@ static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev)
>>   		 * We work on full longs, as we can only exclude the leftover
>>   		 * bits in non-inverse order. The leftover is all zeros.
>>   		 */
>> -		if (!bitmap_and(apm, matrix_mdev->matrix.apm,
>> -				lstdev->matrix.apm, AP_DEVICES))
>> +		if (!bitmap_and(apm, mdev_apm, lstdev->matrix.apm, AP_DEVICES))
>>   			continue;
>>   
>> -		if (!bitmap_and(aqm, matrix_mdev->matrix.aqm,
>> -				lstdev->matrix.aqm, AP_DOMAINS))
>> +		if (!bitmap_and(aqm, mdev_aqm, lstdev->matrix.aqm, AP_DOMAINS))
>>   			continue;
>>   
>>   		return -EADDRINUSE;
>> @@ -564,6 +454,17 @@ static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev)
>>   	return 0;
>>   }
>>   
>> +static int vfio_ap_mdev_validate_masks(unsigned long *apm, unsigned long *aqm)
>> +{
>> +	int ret;
>> +
>> +	ret = ap_apqn_in_matrix_owned_by_def_drv(apm, aqm);
>> +	if (ret)
>> +		return (ret == 1) ? -EADDRNOTAVAIL : ret;
>> +
>> +	return vfio_ap_mdev_verify_no_sharing(apm, aqm);
>> +}
>> +
>>   /**
>>    * assign_adapter_store
>>    *
>> @@ -602,6 +503,7 @@ static ssize_t assign_adapter_store(struct device *dev,
>>   {
>>   	int ret;
>>   	unsigned long apid;
>> +	DECLARE_BITMAP(apm, AP_DEVICES);
>>   	struct mdev_device *mdev = mdev_from_dev(dev);
>>   	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
>>   
>> @@ -616,32 +518,19 @@ static ssize_t assign_adapter_store(struct device *dev,
>>   	if (apid > matrix_mdev->matrix.apm_max)
>>   		return -ENODEV;
>>   
>> -	/*
>> -	 * Set the bit in the AP mask (APM) corresponding to the AP adapter
>> -	 * number (APID). The bits in the mask, from most significant to least
>> -	 * significant bit, correspond to APIDs 0-255.
>> -	 */
>> -	mutex_lock(&matrix_dev->lock);
>> -
>> -	ret = vfio_ap_mdev_verify_queues_reserved_for_apid(matrix_mdev, apid);
>> -	if (ret)
>> -		goto done;
>> +	memset(apm, 0, ARRAY_SIZE(apm) * sizeof(*apm));
> What about just memset(apm, 0, sizeof(apm));

apm is a pointer to an array of unsigned long, so sizeof(apm) will
yield the number of bytes in the pointer (8), not the number of bytes in
the array (32); or am I wrong about that?

>> +	set_bit_inv(apid, apm);
>>   
>> +	mutex_lock(&matrix_dev->lock);
>> +	ret = vfio_ap_mdev_validate_masks(apm, matrix_mdev->matrix.aqm);
>> +	if (ret) {
>> +		mutex_unlock(&matrix_dev->lock);
>> +		return ret;
>> +	}
>>   	set_bit_inv(apid, matrix_mdev->matrix.apm);
>> -
>> -	ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev);
>> -	if (ret)
>> -		goto share_err;
>> -
>> -	ret = count;
>> -	goto done;
>> -
>> -share_err:
>> -	clear_bit_inv(apid, matrix_mdev->matrix.apm);
>> -done:
>>   	mutex_unlock(&matrix_dev->lock);
>>   
>> -	return ret;
>> +	return count;
>>   }
>>   static DEVICE_ATTR_WO(assign_adapter);
>>   
>> @@ -690,26 +579,6 @@ static ssize_t unassign_adapter_store(struct device *dev,
>>   }
>>   static DEVICE_ATTR_WO(unassign_adapter);
>>   
>> -static int
>> -vfio_ap_mdev_verify_queues_reserved_for_apqi(struct ap_matrix_mdev *matrix_mdev,
>> -					     unsigned long apqi)
>> -{
>> -	int ret;
>> -	unsigned long apid;
>> -	unsigned long nbits = matrix_mdev->matrix.apm_max + 1;
>> -
>> -	if (find_first_bit_inv(matrix_mdev->matrix.apm, nbits) >= nbits)
>> -		return vfio_ap_verify_queue_reserved(NULL, &apqi);
>> -
>> -	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, nbits) {
>> -		ret = vfio_ap_verify_queue_reserved(&apid, &apqi);
>> -		if (ret)
>> -			return ret;
>> -	}
>> -
>> -	return 0;
>> -}
>> -
>>   /**
>>    * assign_domain_store
>>    *
>> @@ -748,6 +617,7 @@ static ssize_t assign_domain_store(struct device *dev,
>>   {
>>   	int ret;
>>   	unsigned long apqi;
>> +	DECLARE_BITMAP(aqm, AP_DEVICES);
> AP_DEVICES -> AP_DOMAINS

Copy and paste error, it should be AP_DOMAINS.

>>   	struct mdev_device *mdev = mdev_from_dev(dev);
>>   	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
>>   	unsigned long max_apqi = matrix_mdev->matrix.aqm_max;
>> @@ -762,27 +632,19 @@ static ssize_t assign_domain_store(struct device *dev,
>>   	if (apqi > max_apqi)
>>   		return -ENODEV;
>>   
>> -	mutex_lock(&matrix_dev->lock);
>> -
>> -	ret = vfio_ap_mdev_verify_queues_reserved_for_apqi(matrix_mdev, apqi);
>> -	if (ret)
>> -		goto done;
>> +	memset(aqm, 0, ARRAY_SIZE(aqm) * sizeof(*aqm));
> memset(aqm, 0, sizeof(aqm));

See response above.

>> +	set_bit_inv(apqi, aqm);
>>   
>> +	mutex_lock(&matrix_dev->lock);
>> +	ret = vfio_ap_mdev_validate_masks(matrix_mdev->matrix.apm, aqm);
>> +	if (ret) {
>> +		mutex_unlock(&matrix_dev->lock);
>> +		return ret;
>> +	}
>>   	set_bit_inv(apqi, matrix_mdev->matrix.aqm);
>> -
>> -	ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev);
>> -	if (ret)
>> -		goto share_err;
>> -
>> -	ret = count;
>> -	goto done;
>> -
>> -share_err:
>> -	clear_bit_inv(apqi, matrix_mdev->matrix.aqm);
>> -done:
>>   	mutex_unlock(&matrix_dev->lock);
>>   
>> -	return ret;
>> +	return count;
>>   }
>>   static DEVICE_ATTR_WO(assign_domain);
>>   
>> @@ -868,11 +730,6 @@ static ssize_t assign_control_domain_store(struct device *dev,
>>   	if (id > matrix_mdev->matrix.adm_max)
>>   		return -ENODEV;
>>   
>> -	/* Set the bit in the ADM (bitmask) corresponding to the AP control
>> -	 * domain number (id). The bits in the mask, from most significant to
>> -	 * least significant, correspond to IDs 0 up to the one less than the
>> -	 * number of control domains that can be assigned.
>> -	 */
>>   	mutex_lock(&matrix_dev->lock);
>>   	set_bit_inv(id, matrix_mdev->matrix.adm);
>>   	mutex_unlock(&matrix_dev->lock);
> 

Powered by blists - more mailing lists