static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
struct scatterlist *data_sg, bool have_data)
{
struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
unsigned int num_out = 0, num_in = 0;
sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
sgs[num_out++] = &hdr;
sg_init_one(&cmd, vbr->sreq.cmd, vbr->sreq.cmd_len);
sgs[num_out++] = &cmd;
if (have_data) {
if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
sgs[num_out++] = data_sg;
else
sgs[num_out + num_in++] = data_sg;
}
sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
sgs[num_out + num_in++] = &sense;
sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
sgs[num_out + num_in++] = &inhdr;
sg_init_one(&status, &vbr->status, sizeof(vbr->status));
sgs[num_out + num_in++] = &status;
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
static int __virtblk_add_req(struct virtqueue *vq,
struct virtblk_req *vbr,
struct scatterlist *data_sg,
bool have_data)
{
struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
unsigned int num_out = 0, num_in = 0;
__virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
sgs[num_out++] = &hdr;
/*
* If this is a packet command we need a couple of additional headers.
* Behind the normal outhdr we put a segment with the scsi command
* block, and before the normal inhdr we put the sense data and the
* inhdr with additional status information.
*/
if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
sgs[num_out++] = &cmd;
}
if (have_data) {
if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
sgs[num_out++] = data_sg;
else
sgs[num_out + num_in++] = data_sg;
}
if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
sgs[num_out + num_in++] = &sense;
sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
sgs[num_out + num_in++] = &inhdr;
}
sg_init_one(&status, &vbr->status, sizeof(vbr->status));
sgs[num_out + num_in++] = &status;
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
static void set_page_pfns(struct virtio_balloon *vb,
__virtio32 pfns[], struct page *page)
{
unsigned int i;
/* Set balloon pfns pointing at this page.
* Note that the first pfn points at start of the page. */
for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
pfns[i] = cpu_to_virtio32(vb->vdev,
page_to_balloon_pfn(page) + i);
}
static int send_cmd_id_start(struct virtio_balloon *vb)
{
struct scatterlist sg;
struct virtqueue *vq = vb->free_page_vq;
int err, unused;
/* Detach all the used buffers from the vq */
while (virtqueue_get_buf(vq, &unused))
;
vb->cmd_id_active = cpu_to_virtio32(vb->vdev, vb->cmd_id_received);
sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
if (!err)
virtqueue_kick(vq);
return err;
}
static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
struct scatterlist *data_sg, bool have_data)
{
struct scatterlist hdr, status, *sgs[3];
unsigned int num_out = 0, num_in = 0;
sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
sgs[num_out++] = &hdr;
if (have_data) {
if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
sgs[num_out++] = data_sg;
else
sgs[num_out + num_in++] = data_sg;
}
sg_init_one(&status, &vbr->status, sizeof(vbr->status));
sgs[num_out + num_in++] = &status;
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct virtio_blk *vblk = hctx->queue->queuedata;
struct request *req = bd->rq;
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
unsigned long flags;
unsigned int num;
int qid = hctx->queue_num;
int err;
bool notify = false;
BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
vbr->req = req;
if (req->cmd_flags & REQ_FLUSH) {
vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
vbr->out_hdr.sector = 0;
vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
} else {
switch (req->cmd_type) {
case REQ_TYPE_FS:
vbr->out_hdr.type = 0;
vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
case REQ_TYPE_BLOCK_PC:
vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
vbr->out_hdr.sector = 0;
vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
case REQ_TYPE_DRV_PRIV:
vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
vbr->out_hdr.sector = 0;
vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
default:
/* We don't put anything else in the queue. */
BUG();
}
}
blk_mq_start_request(req);
num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
if (num) {
if (rq_data_dir(vbr->req) == WRITE)
vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
else
vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
}
spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
err = __virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
if (err) {
virtqueue_kick(vblk->vqs[qid].vq);
blk_mq_stop_hw_queue(hctx);
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
/* Out of mem doesn't actually happen, since we fall back
* to direct descriptors */
if (err == -ENOMEM || err == -ENOSPC)
return BLK_MQ_RQ_QUEUE_BUSY;
return BLK_MQ_RQ_QUEUE_ERROR;
}
if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
notify = true;
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
if (notify)
virtqueue_notify(vblk->vqs[qid].vq);
return BLK_MQ_RQ_QUEUE_OK;
}
static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct virtio_blk *vblk = hctx->queue->queuedata;
struct request *req = bd->rq;
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
unsigned long flags;
unsigned int num;
int qid = hctx->queue_num;
int err;
bool notify = false;
u32 type;
BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
switch (req_op(req)) {
case REQ_OP_READ:
case REQ_OP_WRITE:
type = 0;
break;
case REQ_OP_FLUSH:
type = VIRTIO_BLK_T_FLUSH;
break;
case REQ_OP_SCSI_IN:
case REQ_OP_SCSI_OUT:
type = VIRTIO_BLK_T_SCSI_CMD;
break;
case REQ_OP_DRV_IN:
type = VIRTIO_BLK_T_GET_ID;
break;
default:
WARN_ON_ONCE(1);
return BLK_MQ_RQ_QUEUE_ERROR;
}
vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
vbr->out_hdr.sector = type ?
0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
blk_mq_start_request(req);
num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
if (num) {
if (rq_data_dir(req) == WRITE)
vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
else
vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
}
spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
if (req_op(req) == REQ_OP_SCSI_IN || req_op(req) == REQ_OP_SCSI_OUT)
err = virtblk_add_req_scsi(vblk->vqs[qid].vq, vbr, vbr->sg, num);
else
err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
if (err) {
virtqueue_kick(vblk->vqs[qid].vq);
blk_mq_stop_hw_queue(hctx);
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
/* Out of mem doesn't actually happen, since we fall back
* to direct descriptors */
if (err == -ENOMEM || err == -ENOSPC)
return BLK_MQ_RQ_QUEUE_BUSY;
return BLK_MQ_RQ_QUEUE_ERROR;
}
if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
notify = true;
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
if (notify)
virtqueue_notify(vblk->vqs[qid].vq);
return BLK_MQ_RQ_QUEUE_OK;
}
static int virtballoon_probe(struct virtio_device *vdev)
{
struct virtio_balloon *vb;
__u32 poison_val;
int err;
if (!vdev->config->get) {
dev_err(&vdev->dev, "%s failure: config access disabled\n",
__func__);
return -EINVAL;
}
vdev->priv = vb = kzalloc(sizeof(*vb), GFP_KERNEL);
if (!vb) {
err = -ENOMEM;
goto out;
}
INIT_WORK(&vb->update_balloon_stats_work, update_balloon_stats_func);
INIT_WORK(&vb->update_balloon_size_work, update_balloon_size_func);
spin_lock_init(&vb->stop_update_lock);
mutex_init(&vb->balloon_lock);
init_waitqueue_head(&vb->acked);
vb->vdev = vdev;
balloon_devinfo_init(&vb->vb_dev_info);
err = init_vqs(vb);
if (err)
goto out_free_vb;
#ifdef CONFIG_BALLOON_COMPACTION
balloon_mnt = kern_mount(&balloon_fs);
if (IS_ERR(balloon_mnt)) {
err = PTR_ERR(balloon_mnt);
goto out_del_vqs;
}
vb->vb_dev_info.migratepage = virtballoon_migratepage;
vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
if (IS_ERR(vb->vb_dev_info.inode)) {
err = PTR_ERR(vb->vb_dev_info.inode);
kern_unmount(balloon_mnt);
goto out_del_vqs;
}
vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
#endif
if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
/*
* There is always one entry reserved for cmd id, so the ring
* size needs to be at least two to report free page hints.
*/
if (virtqueue_get_vring_size(vb->free_page_vq) < 2) {
err = -ENOSPC;
goto out_del_vqs;
}
vb->balloon_wq = alloc_workqueue("balloon-wq",
WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
if (!vb->balloon_wq) {
err = -ENOMEM;
goto out_del_vqs;
}
INIT_WORK(&vb->report_free_page_work, report_free_page_func);
vb->cmd_id_received = VIRTIO_BALLOON_CMD_ID_STOP;
vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
VIRTIO_BALLOON_CMD_ID_STOP);
vb->cmd_id_stop = cpu_to_virtio32(vb->vdev,
VIRTIO_BALLOON_CMD_ID_STOP);
vb->num_free_page_blocks = 0;
spin_lock_init(&vb->free_page_list_lock);
INIT_LIST_HEAD(&vb->free_page_list);
if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
memset(&poison_val, PAGE_POISON, sizeof(poison_val));
virtio_cwrite(vb->vdev, struct virtio_balloon_config,
poison_val, &poison_val);
}
}
/*
* We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a
* shrinker needs to be registered to relieve memory pressure.
*/
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
err = virtio_balloon_register_shrinker(vb);
if (err)
goto out_del_balloon_wq;
}
virtio_device_ready(vdev);
if (towards_target(vb))
virtballoon_changed(vdev);
return 0;
out_del_balloon_wq:
if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
destroy_workqueue(vb->balloon_wq);
out_del_vqs:
vdev->config->del_vqs(vdev);
out_free_vb:
kfree(vb);
out:
return err;
}