[PATCH v5 07/15] s390/vfio-ap: File ops called to save the vfio device migration state

[Anthony Krowiak <akrowiak@linux.ibm.com>]

Implements the read callback function that was added to the
file_operations structure for the file created to save the state of the
vfio-ap device when the migration state transitioned from STOP to
to the STOP_COPY state.

This function copies the guest's AP configuration information to
userspace. The information copied is comprised of the APQN of each queue
device passed through to the guest along with its hardware information.
This state data will be transferred to the vfio_ap device driver on the
destination host when the state is transitioned to RESUMING.

Signed-off-by: Anthony Krowiak <akrowiak@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_migration.c | 278 +++++++++++++++++++++++-
 1 file changed, 271 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_migration.c b/drivers/s390/crypto/vfio_ap_migration.c
index e566250a88ea..0d949ec205de 100644
--- a/drivers/s390/crypto/vfio_ap_migration.c
+++ b/drivers/s390/crypto/vfio_ap_migration.c
@@ -82,13 +82,6 @@ vfio_ap_release_stop_copy_file(struct vfio_ap_migration_data *mig_data)
 	mig_data->stop_copy_mig_file.filp = NULL;
 }
 
-static ssize_t
-vfio_ap_stop_copy_read(struct file *, char __user *, size_t, loff_t *)
-{
-	/* TODO */
-	return -EOPNOTSUPP;
-}
-
 static int vfio_ap_release_mig_file(struct inode *file_inode, struct file *filp)
 {
 	struct ap_matrix_mdev *matrix_mdev;
@@ -112,6 +105,277 @@ static int vfio_ap_release_mig_file(struct inode *file_inode, struct file *filp)
 	return ret;
 }
 
+/**
+ * validate_stop_copy_read_parms: Validate the input parameters to the
+ *                                vfio_ap_stop_copy_read function
+ *
+ * @matrix_mdev: The object device containing the state to be read
+ * @filp: Pointer to the file stream used to read the vfio-ap device state
+ * @pos:  The file offset from which to start reading data
+ * @len:  The length of the data to be read
+ *
+ * Verify the following:
+ * - @filp private data is an ap_matrix_mdev instance
+ * - @filp is the instance opened when state transitioned from STOP to STOP_COPY
+ * - @pos + @len does not cause integer overflow
+ *
+ * Returns: 0 if the parameters pass validation; otherwise returns an error
+ */
+static int validate_stop_copy_read_parms(struct file *filp, loff_t *pos,
+					 size_t len)
+{
+	struct vfio_ap_migration_data *mig_data;
+	struct ap_matrix_mdev *matrix_mdev;
+	loff_t total_len;
+
+	lockdep_assert_held(&matrix_dev->mdevs_lock);
+
+	if (check_add_overflow((loff_t)len, *pos, &total_len))
+		return -EIO;
+
+	matrix_mdev = filp->private_data;
+
+	if (!matrix_mdev || !matrix_mdev->mig_data)
+		return -ENODEV;
+
+	mig_data = matrix_mdev->mig_data;
+
+	if (mig_data->stop_copy_mig_file.filp != filp)
+		return -EINVAL;
+
+	return 0;
+}
+
+static size_t vfio_ap_config_size(struct ap_matrix_mdev *matrix_mdev,
+				  int *num_queues)
+{
+	size_t qinfo_size;
+
+	lockdep_assert_held(&matrix_dev->mdevs_lock);
+
+	*num_queues = vfio_ap_mdev_get_num_queues(&matrix_mdev->shadow_apcb);
+	qinfo_size = *num_queues * sizeof(struct vfio_ap_queue_info);
+
+	return qinfo_size + sizeof(struct vfio_ap_config);
+}
+
+static int get_hardware_info_for_queue(const char *mdev_name,
+				       struct ap_tapq_hwinfo *hwinfo,
+				       unsigned long apqn)
+{
+	struct ap_queue_status status;
+
+	status = ap_tapq(apqn, hwinfo);
+
+	switch (status.response_code) {
+	case AP_RESPONSE_NORMAL:
+	case AP_RESPONSE_RESET_IN_PROGRESS:
+	case AP_RESPONSE_DECONFIGURED:
+	case AP_RESPONSE_CHECKSTOPPED:
+	case AP_RESPONSE_BUSY:
+		/* For all these RCs the tapq info should be available */
+		return 0;
+	case AP_RESPONSE_Q_NOT_AVAIL:
+		pr_err("vfio_ap_mdev %s: Failed to get hwinfo for queue %02lx.%04lx: TAPQ rc=%d",
+		       mdev_name, AP_QID_CARD(apqn), AP_QID_QUEUE(apqn),
+		       status.response_code);
+		return -ENODEV;
+	default:
+		/*
+		 * Without a pending async error, the tapq info should be
+		 * available
+		 */
+		if (status.async)
+			return 0;
+
+		pr_err("vfio_ap_mdev %s:Failed to get hwinfo for queue %02lx.%04lx: TAPQ rc=%d",
+		       mdev_name, AP_QID_CARD(apqn), AP_QID_QUEUE(apqn),
+		       status.response_code);
+		return -EIO;
+	}
+
+	return -EINVAL;
+}
+
+static int vfio_ap_store_queue_info(const char *mdev_name,
+				    struct vfio_ap_config *ap_config)
+{
+	struct ap_tapq_hwinfo source_hwinfo;
+	unsigned long num_queues;
+	int ret;
+
+	/*
+	 * ap_tapq() is a hardware instruction that may take time to complete.
+	 * It must be called without mdevs_lock held to avoid blocking other
+	 * mdevs. The apqn list was already snapshotted into ap_config->qinfo[]
+	 * by the caller under the lock.
+	 */
+	for (num_queues = 0; num_queues < ap_config->num_queues; num_queues++) {
+		ret = get_hardware_info_for_queue(mdev_name, &source_hwinfo,
+						  ap_config->qinfo[num_queues].apqn);
+		if (ret)
+			return ret;
+
+		ap_config->qinfo[num_queues].data = source_hwinfo.value;
+	}
+
+	return 0;
+}
+
+static int
+vfio_ap_get_config(struct ap_matrix_mdev *matrix_mdev)
+{
+	unsigned long *apm, *aqm, apid, apqi, num_queues;
+	struct vfio_ap_config *ap_configuration;
+	const char *mdev_name;
+	size_t ap_config_size;
+	int ret;
+
+	lockdep_assert_held(&matrix_dev->mdevs_lock);
+
+	ap_config_size = vfio_ap_config_size(matrix_mdev, (int *)&num_queues);
+
+	ap_configuration = kzalloc(ap_config_size, GFP_KERNEL_ACCOUNT);
+	if (!ap_configuration)
+		return -ENOMEM;
+
+	/*
+	 * Snapshot the APQN list from shadow_apcb under the lock so that
+	 * ap_tapq() calls in vfio_ap_store_queue_info() can happen without it.
+	 */
+	apm = matrix_mdev->shadow_apcb.apm;
+	aqm = matrix_mdev->shadow_apcb.aqm;
+	num_queues = 0;
+	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) {
+			ap_configuration->qinfo[num_queues].apqn =
+				AP_MKQID(apid, apqi);
+			num_queues += 1;
+		}
+	}
+	ap_configuration->num_queues = num_queues;
+	memcpy(ap_configuration->adm, matrix_mdev->shadow_apcb.adm,
+	       sizeof(ap_configuration->adm));
+	mdev_name = dev_name(matrix_mdev->vdev.dev);
+
+	/**
+	 * Release the global mdevs_lock which guards access to all mdevs.
+	 * Storing the queue information could take a while if there are a
+	 * large number of queues.
+	 */
+	mutex_unlock(&matrix_dev->mdevs_lock);
+
+	ret = vfio_ap_store_queue_info(mdev_name, ap_configuration);
+	if (ret) {
+		kfree(ap_configuration);
+		mutex_lock(&matrix_dev->mdevs_lock);
+		return ret;
+	}
+
+	/* Retake the mdevs lock so we can safely make updates to the mdev */
+	mutex_lock(&matrix_dev->mdevs_lock);
+
+	/*
+	 * Verify mig_data is still valid - mdevs_lock was dropped, so the
+	 * device could have been closed concurrently.
+	 */
+	if (!matrix_mdev->mig_data) {
+		kfree(ap_configuration);
+		return -ENODEV;
+	}
+
+	matrix_mdev->mig_data->stop_copy_mig_file.ap_config = ap_configuration;
+	matrix_mdev->mig_data->stop_copy_mig_file.config_sz = ap_config_size;
+
+	return 0;
+}
+
+static ssize_t vfio_ap_stop_copy_read(struct file *filp, char __user *buf,
+				      size_t len, loff_t *pos)
+{
+	struct ap_matrix_mdev *matrix_mdev;
+	struct vfio_ap_config *ap_config;
+	ssize_t ret = 0;
+	size_t ap_config_size;
+
+	/*
+	 * When userspace calls read() with an explicit offset (pread), pos is
+	 * non-NULL and the function rejects it with -ESPIPE (illegal seek). For
+	 * normal read() calls, pos is NULL, so we'll use the file's internal
+	 * position filp->f_pos
+	 */
+	if (pos)
+		return -ESPIPE;
+
+	mutex_lock(&matrix_dev->mdevs_lock);
+
+	pos = &filp->f_pos;
+
+	ret = validate_stop_copy_read_parms(filp, pos, len);
+	if (ret) {
+		mutex_unlock(&matrix_dev->mdevs_lock);
+		return ret;
+	}
+
+	matrix_mdev = filp->private_data;
+	if (!matrix_mdev->mig_data->stop_copy_mig_file.ap_config) {
+		ret = vfio_ap_get_config(matrix_mdev);
+		if (ret) {
+			mutex_unlock(&matrix_dev->mdevs_lock);
+			return ret;
+		}
+	}
+
+	ap_config_size = matrix_mdev->mig_data->stop_copy_mig_file.config_sz;
+
+	/*
+	 * If the position exceeds the size of the AP configuration data,
+	 * then indicate EOF; otherwise calculate the length of the data to
+	 * read such that a buffer overrun is prevented.
+	 */
+	if (*pos >= ap_config_size)
+		len = 0;
+	else
+		len = min_t(size_t, ap_config_size - *pos, len);
+
+	/* If we've reached an EOF condition, let the caller know */
+	if (len == 0) {
+		mutex_unlock(&matrix_dev->mdevs_lock);
+		return 0;
+	}
+
+	/*
+	 * Allocate ap_config and copy the content of the object caching the
+	 * AP configuration data between calls to it so we can give up the
+	 * global mdevs_lock while copying the data to userspace.
+	 */
+	ap_config = kzalloc(ap_config_size, GFP_KERNEL_ACCOUNT);
+	if (!ap_config) {
+		mutex_unlock(&matrix_dev->mdevs_lock);
+		return -ENOMEM;
+	}
+
+	memcpy(ap_config, matrix_mdev->mig_data->stop_copy_mig_file.ap_config,
+	       ap_config_size);
+
+	/*
+	 * Give up the global mdevs_lock while copying data to the user; it
+	 * might be a long running operation and we don't want to prevent access
+	 * to other mdevs for an inordinate amount of time.
+	 */
+	mutex_unlock(&matrix_dev->mdevs_lock);
+
+	if (copy_to_user(buf, (char *)ap_config + *pos, len)) {
+		kfree(ap_config);
+		return -EFAULT;
+	}
+
+	kfree(ap_config);
+	*pos += len;
+
+	return len;
+}
+
 static const struct file_operations vfio_ap_stop_copy_fops = {
 	.owner = THIS_MODULE,
 	.read = vfio_ap_stop_copy_read,
-- 
2.53.0