virtio-pci: Introduce admin command sending function

Add support for sending admin command through admin virtqueue interface.
Abort any inflight admin commands once device reset completes. Activate
admin queue when device becomes ready; deactivate on device reset.

To comply to the below specification statement [1], the admin virtqueue
is activated for upper layer users only after setting DRIVER_OK status.

[1] The driver MUST NOT send any buffer available notifications to the
device before setting DRIVER_OK.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-4-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/virtio/virtio_pci_common.h

@@ -29,6 +29,7 @@
 #include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 struct virtio_pci_vq_info {
 	/* the actual virtqueue */
@@ -44,6 +45,8 @@ struct virtio_pci_vq_info {
 struct virtio_pci_admin_vq {
 	/* Virtqueue info associated with this admin queue. */
 	struct virtio_pci_vq_info info;
+	/* serializing admin commands execution and virtqueue deletion */
+	struct mutex cmd_lock;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
 	u16 vq_index;
@@ -152,4 +155,7 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd);
+
 #endif

drivers/virtio/virtio_pci_modern.c

@@ -38,6 +38,132 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 	return index == vp_dev->admin_vq.vq_index;
 }
 
+static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
+				    struct scatterlist **sgs,
+				    unsigned int out_num,
+				    unsigned int in_num,
+				    void *data)
+{
+	struct virtqueue *vq;
+	int ret, len;
+
+	vq = admin_vq->info.vq;
+	if (!vq)
+		return -EIO;
+
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
+	if (ret < 0)
+		return -EIO;
+
+	if (unlikely(!virtqueue_kick(vq)))
+		return -EIO;
+
+	while (!virtqueue_get_buf(vq, &len) &&
+	       !virtqueue_is_broken(vq))
+		cpu_relax();
+
+	if (virtqueue_is_broken(vq))
+		return -EIO;
+
+	return 0;
+}
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd)
+{
+	struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_admin_cmd_status *va_status;
+	unsigned int out_num = 0, in_num = 0;
+	struct virtio_admin_cmd_hdr *va_hdr;
+	u16 status;
+	int ret;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return -EOPNOTSUPP;
+
+	va_status = kzalloc(sizeof(*va_status), GFP_KERNEL);
+	if (!va_status)
+		return -ENOMEM;
+
+	va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL);
+	if (!va_hdr) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	va_hdr->opcode = cmd->opcode;
+	va_hdr->group_type = cmd->group_type;
+	va_hdr->group_member_id = cmd->group_member_id;
+
+	/* Add header */
+	sg_init_one(&hdr, va_hdr, sizeof(*va_hdr));
+	sgs[out_num] = &hdr;
+	out_num++;
+
+	if (cmd->data_sg) {
+		sgs[out_num] = cmd->data_sg;
+		out_num++;
+	}
+
+	/* Add return status */
+	sg_init_one(&stat, va_status, sizeof(*va_status));
+	sgs[out_num + in_num] = &stat;
+	in_num++;
+
+	if (cmd->result_sg) {
+		sgs[out_num + in_num] = cmd->result_sg;
+		in_num++;
+	}
+
+	mutex_lock(&vp_dev->admin_vq.cmd_lock);
+	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, sgs,
+				       out_num, in_num, sgs);
+	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+
+	if (ret) {
+		dev_err(&vdev->dev,
+			"Failed to execute command on admin vq: %d\n.", ret);
+		goto err_cmd_exec;
+	}
+
+	status = le16_to_cpu(va_status->status);
+	if (status != VIRTIO_ADMIN_STATUS_OK) {
+		dev_err(&vdev->dev,
+			"admin command error: status(%#x) qualifier(%#x)\n",
+			status, le16_to_cpu(va_status->status_qualifier));
+		ret = -status;
+	}
+
+err_cmd_exec:
+	kfree(va_hdr);
+err_alloc:
+	kfree(va_status);
+	return ret;
+}
+
+static void vp_modern_avq_activate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_unbreak(admin_vq->info.vq);
+}
+
+static void vp_modern_avq_deactivate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_break(admin_vq->info.vq);
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -213,6 +339,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
 	vp_modern_set_status(&vp_dev->mdev, status);
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK)
+		vp_modern_avq_activate(vdev);
 }
 
 static void vp_reset(struct virtio_device *vdev)
@@ -229,6 +357,9 @@ static void vp_reset(struct virtio_device *vdev)
 	 */
 	while (vp_modern_get_status(mdev))
 		msleep(1);
+
+	vp_modern_avq_deactivate(vdev);
+
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
@@ -404,8 +535,11 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
-	if (is_avq)
+	if (is_avq) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
 		vp_dev->admin_vq.info.vq = vq;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
 
 	return vq;
 
@@ -442,8 +576,11 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
-	if (vp_is_avq(&vp_dev->vdev, vq->index))
+	if (vp_is_avq(&vp_dev->vdev, vq->index)) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
 		vp_dev->admin_vq.info.vq = NULL;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
 
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
@@ -662,6 +799,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
+	mutex_init(&vp_dev->admin_vq.cmd_lock);
 	return 0;
 }
 
@@ -669,5 +807,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	mutex_destroy(&vp_dev->admin_vq.cmd_lock);
 	vp_modern_remove(mdev);
 }

include/linux/virtio.h

@@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
 int virtqueue_reset(struct virtqueue *vq,
 		    void (*recycle)(struct virtqueue *vq, void *buf));
 
+struct virtio_admin_cmd {
+	__le16 opcode;
+	__le16 group_type;
+	__le64 group_member_id;
+	struct scatterlist *data_sg;
+	struct scatterlist *result_sg;
+};
+
 /**
  * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus

include/uapi/linux/virtio_pci.h

@@ -223,4 +223,26 @@ struct virtio_pci_cfg_cap {
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
+/* Admin command status. */
+#define VIRTIO_ADMIN_STATUS_OK		0
+
+struct __packed virtio_admin_cmd_hdr {
+	__le16 opcode;
+	/*
+	 * 1 - SR-IOV
+	 * 2-65535 - reserved
+	 */
+	__le16 group_type;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved1[12];
+	__le64 group_member_id;
+};
+
+struct __packed virtio_admin_cmd_status {
+	__le16 status;
+	__le16 status_qualifier;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved2[4];
+};
+
 #endif