--- zzzz-none-000/linux-3.10.107/drivers/block/virtio_blk.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/block/virtio_blk.c 2021-02-04 17:41:59.000000000 +0000 @@ -11,67 +11,54 @@ #include #include #include +#include +#include #define PART_BITS 4 - -static bool use_bio; -module_param(use_bio, bool, S_IRUGO); +#define VQ_NAME_LEN 16 static int major; static DEFINE_IDA(vd_index_ida); -struct workqueue_struct *virtblk_wq; +static struct workqueue_struct *virtblk_wq; -struct virtio_blk -{ - struct virtio_device *vdev; +struct virtio_blk_vq { struct virtqueue *vq; - wait_queue_head_t queue_wait; + spinlock_t lock; + char name[VQ_NAME_LEN]; +} ____cacheline_aligned_in_smp; + +struct virtio_blk { + struct virtio_device *vdev; /* The disk structure for the kernel. */ struct gendisk *disk; - mempool_t *pool; + /* Block layer tags. */ + struct blk_mq_tag_set tag_set; /* Process context for config space updates */ struct work_struct config_work; - /* Lock for config space updates */ - struct mutex config_lock; - - /* enable config space updates */ - bool config_enable; - /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems; /* Ida index - used to track minor number allocations. */ int index; - /* Scatterlist: can be too big for stack. */ - struct scatterlist sg[/*sg_elems*/]; + /* num of vqs */ + int num_vqs; + struct virtio_blk_vq *vqs; }; -struct virtblk_req -{ +struct virtblk_req { struct request *req; - struct bio *bio; struct virtio_blk_outhdr out_hdr; struct virtio_scsi_inhdr in_hdr; - struct work_struct work; - struct virtio_blk *vblk; - int flags; u8 status; struct scatterlist sg[]; }; -enum { - VBLK_IS_FLUSH = 1, - VBLK_REQ_FLUSH = 2, - VBLK_REQ_DATA = 4, - VBLK_REQ_FUA = 8, -}; - static inline int virtblk_result(struct virtblk_req *vbr) { switch (vbr->status) { @@ -84,22 +71,6 @@ } } -static inline struct virtblk_req *virtblk_alloc_req(struct virtio_blk *vblk, - gfp_t gfp_mask) -{ - struct virtblk_req *vbr; - - vbr = mempool_alloc(vblk->pool, gfp_mask); - if (!vbr) - return NULL; - - vbr->vblk = vblk; - if (use_bio) - sg_init_table(vbr->sg, vblk->sg_elems); - - return vbr; -} - static int __virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr, struct scatterlist *data_sg, @@ -107,7 +78,7 @@ { struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6]; unsigned int num_out = 0, num_in = 0; - int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT; + __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; @@ -118,19 +89,19 @@ * block, and before the normal inhdr we put the sense data and the * inhdr with additional status information. */ - if (type == VIRTIO_BLK_T_SCSI_CMD) { + 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 & VIRTIO_BLK_T_OUT) + 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 == VIRTIO_BLK_T_SCSI_CMD) { + 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)); @@ -143,198 +114,84 @@ return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); } -static void virtblk_add_req(struct virtblk_req *vbr, bool have_data) -{ - struct virtio_blk *vblk = vbr->vblk; - DEFINE_WAIT(wait); - int ret; - - spin_lock_irq(vblk->disk->queue->queue_lock); - while (unlikely((ret = __virtblk_add_req(vblk->vq, vbr, vbr->sg, - have_data)) < 0)) { - prepare_to_wait_exclusive(&vblk->queue_wait, &wait, - TASK_UNINTERRUPTIBLE); - - spin_unlock_irq(vblk->disk->queue->queue_lock); - io_schedule(); - spin_lock_irq(vblk->disk->queue->queue_lock); - - finish_wait(&vblk->queue_wait, &wait); - } - - virtqueue_kick(vblk->vq); - spin_unlock_irq(vblk->disk->queue->queue_lock); -} - -static void virtblk_bio_send_flush(struct virtblk_req *vbr) -{ - vbr->flags |= VBLK_IS_FLUSH; - vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH; - vbr->out_hdr.sector = 0; - vbr->out_hdr.ioprio = 0; - - virtblk_add_req(vbr, false); -} - -static void virtblk_bio_send_data(struct virtblk_req *vbr) -{ - struct virtio_blk *vblk = vbr->vblk; - struct bio *bio = vbr->bio; - bool have_data; - - vbr->flags &= ~VBLK_IS_FLUSH; - vbr->out_hdr.type = 0; - vbr->out_hdr.sector = bio->bi_sector; - vbr->out_hdr.ioprio = bio_prio(bio); - - if (blk_bio_map_sg(vblk->disk->queue, bio, vbr->sg)) { - have_data = true; - if (bio->bi_rw & REQ_WRITE) - vbr->out_hdr.type |= VIRTIO_BLK_T_OUT; - else - vbr->out_hdr.type |= VIRTIO_BLK_T_IN; - } else - have_data = false; - - virtblk_add_req(vbr, have_data); -} - -static void virtblk_bio_send_data_work(struct work_struct *work) -{ - struct virtblk_req *vbr; - - vbr = container_of(work, struct virtblk_req, work); - - virtblk_bio_send_data(vbr); -} - -static void virtblk_bio_send_flush_work(struct work_struct *work) +static inline void virtblk_request_done(struct request *req) { - struct virtblk_req *vbr; - - vbr = container_of(work, struct virtblk_req, work); - - virtblk_bio_send_flush(vbr); -} - -static inline void virtblk_request_done(struct virtblk_req *vbr) -{ - struct virtio_blk *vblk = vbr->vblk; - struct request *req = vbr->req; + struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); + struct virtio_blk *vblk = req->q->queuedata; int error = virtblk_result(vbr); if (req->cmd_type == REQ_TYPE_BLOCK_PC) { - req->resid_len = vbr->in_hdr.residual; - req->sense_len = vbr->in_hdr.sense_len; - req->errors = vbr->in_hdr.errors; - } else if (req->cmd_type == REQ_TYPE_SPECIAL) { + req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual); + req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len); + req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors); + } else if (req->cmd_type == REQ_TYPE_DRV_PRIV) { req->errors = (error != 0); } - __blk_end_request_all(req, error); - mempool_free(vbr, vblk->pool); -} - -static inline void virtblk_bio_flush_done(struct virtblk_req *vbr) -{ - struct virtio_blk *vblk = vbr->vblk; - - if (vbr->flags & VBLK_REQ_DATA) { - /* Send out the actual write data */ - INIT_WORK(&vbr->work, virtblk_bio_send_data_work); - queue_work(virtblk_wq, &vbr->work); - } else { - bio_endio(vbr->bio, virtblk_result(vbr)); - mempool_free(vbr, vblk->pool); - } -} - -static inline void virtblk_bio_data_done(struct virtblk_req *vbr) -{ - struct virtio_blk *vblk = vbr->vblk; - - if (unlikely(vbr->flags & VBLK_REQ_FUA)) { - /* Send out a flush before end the bio */ - vbr->flags &= ~VBLK_REQ_DATA; - INIT_WORK(&vbr->work, virtblk_bio_send_flush_work); - queue_work(virtblk_wq, &vbr->work); - } else { - bio_endio(vbr->bio, virtblk_result(vbr)); - mempool_free(vbr, vblk->pool); - } -} - -static inline void virtblk_bio_done(struct virtblk_req *vbr) -{ - if (unlikely(vbr->flags & VBLK_IS_FLUSH)) - virtblk_bio_flush_done(vbr); - else - virtblk_bio_data_done(vbr); + blk_mq_end_request(req, error); } static void virtblk_done(struct virtqueue *vq) { struct virtio_blk *vblk = vq->vdev->priv; - bool bio_done = false, req_done = false; + bool req_done = false; + int qid = vq->index; struct virtblk_req *vbr; unsigned long flags; unsigned int len; - spin_lock_irqsave(vblk->disk->queue->queue_lock, flags); + spin_lock_irqsave(&vblk->vqs[qid].lock, flags); do { virtqueue_disable_cb(vq); - while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) { - if (vbr->bio) { - virtblk_bio_done(vbr); - bio_done = true; - } else { - virtblk_request_done(vbr); - req_done = true; - } + while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) { + blk_mq_complete_request(vbr->req, vbr->req->errors); + req_done = true; } + if (unlikely(virtqueue_is_broken(vq))) + break; } while (!virtqueue_enable_cb(vq)); + /* In case queue is stopped waiting for more buffers. */ if (req_done) - blk_start_queue(vblk->disk->queue); - spin_unlock_irqrestore(vblk->disk->queue->queue_lock, flags); - - if (bio_done) - wake_up(&vblk->queue_wait); + blk_mq_start_stopped_hw_queues(vblk->disk->queue, true); + spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); } -static bool do_req(struct request_queue *q, struct virtio_blk *vblk, - struct request *req) +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; - struct virtblk_req *vbr; + int qid = hctx->queue_num; + int err; + bool notify = false; - vbr = virtblk_alloc_req(vblk, GFP_ATOMIC); - if (!vbr) - /* When another request finishes we'll try again. */ - return false; + BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); vbr->req = req; - vbr->bio = NULL; if (req->cmd_flags & REQ_FLUSH) { - vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH; + vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH); vbr->out_hdr.sector = 0; - vbr->out_hdr.ioprio = req_get_ioprio(vbr->req); + 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 = blk_rq_pos(vbr->req); - vbr->out_hdr.ioprio = req_get_ioprio(vbr->req); + 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 = VIRTIO_BLK_T_SCSI_CMD; + vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD); vbr->out_hdr.sector = 0; - vbr->out_hdr.ioprio = req_get_ioprio(vbr->req); + vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req)); break; - case REQ_TYPE_SPECIAL: - vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID; + 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 = req_get_ioprio(vbr->req); + 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. */ @@ -342,71 +199,36 @@ } } - num = blk_rq_map_sg(q, vbr->req, vblk->sg); + 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 |= VIRTIO_BLK_T_OUT; + vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT); else - vbr->out_hdr.type |= VIRTIO_BLK_T_IN; + vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN); } - if (__virtblk_add_req(vblk->vq, vbr, vblk->sg, num) < 0) { - mempool_free(vbr, vblk->pool); - return false; - } - - return true; -} - -static void virtblk_request(struct request_queue *q) -{ - struct virtio_blk *vblk = q->queuedata; - struct request *req; - unsigned int issued = 0; - - while ((req = blk_peek_request(q)) != NULL) { - BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); - - /* If this request fails, stop queue and wait for something to - finish to restart it. */ - if (!do_req(q, vblk, req)) { - blk_stop_queue(q); - break; - } - blk_start_request(req); - issued++; - } - - if (issued) - virtqueue_kick(vblk->vq); -} - -static void virtblk_make_request(struct request_queue *q, struct bio *bio) -{ - struct virtio_blk *vblk = q->queuedata; - struct virtblk_req *vbr; - - BUG_ON(bio->bi_phys_segments + 2 > vblk->sg_elems); - - vbr = virtblk_alloc_req(vblk, GFP_NOIO); - if (!vbr) { - bio_endio(bio, -ENOMEM); - return; - } - - vbr->bio = bio; - vbr->flags = 0; - if (bio->bi_rw & REQ_FLUSH) - vbr->flags |= VBLK_REQ_FLUSH; - if (bio->bi_rw & REQ_FUA) - vbr->flags |= VBLK_REQ_FUA; - if (bio->bi_size) - vbr->flags |= VBLK_REQ_DATA; - - if (unlikely(vbr->flags & VBLK_REQ_FLUSH)) - virtblk_bio_send_flush(vbr); - else - virtblk_bio_send_data(vbr); + 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; } /* return id (s/n) string for *disk to *id_str @@ -429,7 +251,7 @@ return PTR_ERR(req); } - req->cmd_type = REQ_TYPE_SPECIAL; + req->cmd_type = REQ_TYPE_DRV_PRIV; err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false); blk_put_request(req); @@ -456,18 +278,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { struct virtio_blk *vblk = bd->bd_disk->private_data; - struct virtio_blk_geometry vgeo; - int err; /* see if the host passed in geometry config */ - err = virtio_config_val(vblk->vdev, VIRTIO_BLK_F_GEOMETRY, - offsetof(struct virtio_blk_config, geometry), - &vgeo); - - if (!err) { - geo->heads = vgeo.heads; - geo->sectors = vgeo.sectors; - geo->cylinders = vgeo.cylinders; + if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) { + virtio_cread(vblk->vdev, struct virtio_blk_config, + geometry.cylinders, &geo->cylinders); + virtio_cread(vblk->vdev, struct virtio_blk_config, + geometry.heads, &geo->heads); + virtio_cread(vblk->vdev, struct virtio_blk_config, + geometry.sectors, &geo->sectors); } else { /* some standard values, similar to sd */ geo->heads = 1 << 6; @@ -512,7 +331,8 @@ return err; } -DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL); + +static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL); static void virtblk_config_changed_work(struct work_struct *work) { @@ -522,15 +342,10 @@ struct request_queue *q = vblk->disk->queue; char cap_str_2[10], cap_str_10[10]; char *envp[] = { "RESIZE=1", NULL }; - u64 capacity, size; - - mutex_lock(&vblk->config_lock); - if (!vblk->config_enable) - goto done; + u64 capacity; /* Host must always specify the capacity. */ - vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity), - &capacity, sizeof(capacity)); + virtio_cread(vdev, struct virtio_blk_config, capacity, &capacity); /* If capacity is too big, truncate with warning. */ if ((sector_t)capacity != capacity) { @@ -539,9 +354,10 @@ capacity = (sector_t)-1; } - size = capacity * queue_logical_block_size(q); - string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); - string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); + string_get_size(capacity, queue_logical_block_size(q), + STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); + string_get_size(capacity, queue_logical_block_size(q), + STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); dev_notice(&vdev->dev, "new size: %llu %d-byte logical blocks (%s/%s)\n", @@ -552,8 +368,6 @@ set_capacity(vblk->disk, capacity); revalidate_disk(vblk->disk); kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp); -done: - mutex_unlock(&vblk->config_lock); } static void virtblk_config_changed(struct virtio_device *vdev) @@ -566,12 +380,64 @@ static int init_vq(struct virtio_blk *vblk) { int err = 0; + int i; + vq_callback_t **callbacks; + const char **names; + struct virtqueue **vqs; + unsigned short num_vqs; + struct virtio_device *vdev = vblk->vdev; + + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ, + struct virtio_blk_config, num_queues, + &num_vqs); + if (err) + num_vqs = 1; + + vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL); + if (!vblk->vqs) { + err = -ENOMEM; + goto out; + } - /* We expect one virtqueue, for output. */ - vblk->vq = virtio_find_single_vq(vblk->vdev, virtblk_done, "requests"); - if (IS_ERR(vblk->vq)) - err = PTR_ERR(vblk->vq); + names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL); + if (!names) + goto err_names; + + callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL); + if (!callbacks) + goto err_callbacks; + + vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL); + if (!vqs) + goto err_vqs; + + for (i = 0; i < num_vqs; i++) { + callbacks[i] = virtblk_done; + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i); + names[i] = vblk->vqs[i].name; + } + + /* Discover virtqueues and write information to configuration. */ + err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names); + if (err) + goto err_find_vqs; + for (i = 0; i < num_vqs; i++) { + spin_lock_init(&vblk->vqs[i].lock); + vblk->vqs[i].vq = vqs[i]; + } + vblk->num_vqs = num_vqs; + + err_find_vqs: + kfree(vqs); + err_vqs: + kfree(callbacks); + err_callbacks: + kfree(names); + err_names: + if (err) + kfree(vblk->vqs); + out: return err; } @@ -608,9 +474,9 @@ u8 writeback; int err; - err = virtio_config_val(vdev, VIRTIO_BLK_F_CONFIG_WCE, - offsetof(struct virtio_blk_config, wce), - &writeback); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE, + struct virtio_blk_config, wce, + &writeback); if (err) writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE); @@ -642,7 +508,6 @@ struct virtio_blk *vblk = disk->private_data; struct virtio_device *vdev = vblk->vdev; int i; - u8 writeback; BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE)); for (i = ARRAY_SIZE(virtblk_cache_types); --i >= 0; ) @@ -652,11 +517,7 @@ if (i < 0) return -EINVAL; - writeback = i; - vdev->config->set(vdev, - offsetof(struct virtio_blk_config, wce), - &writeback, sizeof(writeback)); - + virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i); virtblk_update_cache_mode(vdev); return count; } @@ -680,18 +541,44 @@ __ATTR(cache_type, S_IRUGO|S_IWUSR, virtblk_cache_type_show, virtblk_cache_type_store); +static int virtblk_init_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int request_idx, + unsigned int numa_node) +{ + struct virtio_blk *vblk = data; + struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq); + + sg_init_table(vbr->sg, vblk->sg_elems); + return 0; +} + +static struct blk_mq_ops virtio_mq_ops = { + .queue_rq = virtio_queue_rq, + .map_queue = blk_mq_map_queue, + .complete = virtblk_request_done, + .init_request = virtblk_init_request, +}; + +static unsigned int virtblk_queue_depth; +module_param_named(queue_depth, virtblk_queue_depth, uint, 0444); + static int virtblk_probe(struct virtio_device *vdev) { struct virtio_blk *vblk; struct request_queue *q; int err, index; - int pool_size; u64 cap; u32 v, blk_size, sg_elems, opt_io_size; u16 min_io_size; u8 physical_block_exp, alignment_offset; + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS), GFP_KERNEL); if (err < 0) @@ -699,9 +586,9 @@ index = err; /* We need to know how many segments before we allocate. */ - err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX, - offsetof(struct virtio_blk_config, seg_max), - &sg_elems); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX, + struct virtio_blk_config, seg_max, + &sg_elems); /* We need at least one SG element, whatever they say. */ if (err || !sg_elems) @@ -709,50 +596,57 @@ /* We need an extra sg elements at head and tail. */ sg_elems += 2; - vdev->priv = vblk = kmalloc(sizeof(*vblk) + - sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL); + vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL); if (!vblk) { err = -ENOMEM; goto out_free_index; } - init_waitqueue_head(&vblk->queue_wait); vblk->vdev = vdev; vblk->sg_elems = sg_elems; - sg_init_table(vblk->sg, vblk->sg_elems); - mutex_init(&vblk->config_lock); INIT_WORK(&vblk->config_work, virtblk_config_changed_work); - vblk->config_enable = true; err = init_vq(vblk); if (err) goto out_free_vblk; - pool_size = sizeof(struct virtblk_req); - if (use_bio) - pool_size += sizeof(struct scatterlist) * sg_elems; - vblk->pool = mempool_create_kmalloc_pool(1, pool_size); - if (!vblk->pool) { - err = -ENOMEM; - goto out_free_vq; - } - /* FIXME: How many partitions? How long is a piece of string? */ vblk->disk = alloc_disk(1 << PART_BITS); if (!vblk->disk) { err = -ENOMEM; - goto out_mempool; + goto out_free_vq; } - q = vblk->disk->queue = blk_init_queue(virtblk_request, NULL); - if (!q) { - err = -ENOMEM; + /* Default queue sizing is to fill the ring. */ + if (!virtblk_queue_depth) { + virtblk_queue_depth = vblk->vqs[0].vq->num_free; + /* ... but without indirect descs, we use 2 descs per req */ + if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) + virtblk_queue_depth /= 2; + } + + memset(&vblk->tag_set, 0, sizeof(vblk->tag_set)); + vblk->tag_set.ops = &virtio_mq_ops; + vblk->tag_set.queue_depth = virtblk_queue_depth; + vblk->tag_set.numa_node = NUMA_NO_NODE; + vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + vblk->tag_set.cmd_size = + sizeof(struct virtblk_req) + + sizeof(struct scatterlist) * sg_elems; + vblk->tag_set.driver_data = vblk; + vblk->tag_set.nr_hw_queues = vblk->num_vqs; + + err = blk_mq_alloc_tag_set(&vblk->tag_set); + if (err) goto out_put_disk; + + q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set); + if (IS_ERR(q)) { + err = -ENOMEM; + goto out_free_tags; } - if (use_bio) - blk_queue_make_request(q, virtblk_make_request); q->queuedata = vblk; virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN); @@ -762,6 +656,7 @@ vblk->disk->private_data = vblk; vblk->disk->fops = &virtblk_fops; vblk->disk->driverfs_dev = &vdev->dev; + vblk->disk->flags |= GENHD_FL_EXT_DEVT; vblk->index = index; /* configure queue flush support */ @@ -772,8 +667,7 @@ set_disk_ro(vblk->disk, 1); /* Host must always specify the capacity. */ - vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity), - &cap, sizeof(cap)); + virtio_cread(vdev, struct virtio_blk_config, capacity, &cap); /* If capacity is too big, truncate with warning. */ if ((sector_t)cap != cap) { @@ -794,49 +688,50 @@ /* Host can optionally specify maximum segment size and number of * segments. */ - err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX, - offsetof(struct virtio_blk_config, size_max), - &v); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SIZE_MAX, + struct virtio_blk_config, size_max, &v); if (!err) blk_queue_max_segment_size(q, v); else blk_queue_max_segment_size(q, -1U); /* Host can optionally specify the block size of the device */ - err = virtio_config_val(vdev, VIRTIO_BLK_F_BLK_SIZE, - offsetof(struct virtio_blk_config, blk_size), - &blk_size); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE, + struct virtio_blk_config, blk_size, + &blk_size); if (!err) blk_queue_logical_block_size(q, blk_size); else blk_size = queue_logical_block_size(q); /* Use topology information if available */ - err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY, - offsetof(struct virtio_blk_config, physical_block_exp), - &physical_block_exp); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, + struct virtio_blk_config, physical_block_exp, + &physical_block_exp); if (!err && physical_block_exp) blk_queue_physical_block_size(q, blk_size * (1 << physical_block_exp)); - err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY, - offsetof(struct virtio_blk_config, alignment_offset), - &alignment_offset); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, + struct virtio_blk_config, alignment_offset, + &alignment_offset); if (!err && alignment_offset) blk_queue_alignment_offset(q, blk_size * alignment_offset); - err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY, - offsetof(struct virtio_blk_config, min_io_size), - &min_io_size); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, + struct virtio_blk_config, min_io_size, + &min_io_size); if (!err && min_io_size) blk_queue_io_min(q, blk_size * min_io_size); - err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY, - offsetof(struct virtio_blk_config, opt_io_size), - &opt_io_size); + err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, + struct virtio_blk_config, opt_io_size, + &opt_io_size); if (!err && opt_io_size) blk_queue_io_opt(q, blk_size * opt_io_size); + virtio_device_ready(vdev); + add_disk(vblk->disk); err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial); if (err) @@ -855,10 +750,10 @@ out_del_disk: del_gendisk(vblk->disk); blk_cleanup_queue(vblk->disk->queue); +out_free_tags: + blk_mq_free_tag_set(&vblk->tag_set); out_put_disk: put_disk(vblk->disk); -out_mempool: - mempool_destroy(vblk->pool); out_free_vq: vdev->config->del_vqs(vdev); out_free_vblk: @@ -875,23 +770,21 @@ int index = vblk->index; int refc; - /* Prevent config work handler from accessing the device. */ - mutex_lock(&vblk->config_lock); - vblk->config_enable = false; - mutex_unlock(&vblk->config_lock); + /* Make sure no work handler is accessing the device. */ + flush_work(&vblk->config_work); del_gendisk(vblk->disk); blk_cleanup_queue(vblk->disk->queue); + blk_mq_free_tag_set(&vblk->tag_set); + /* Stop all the virtqueues. */ vdev->config->reset(vdev); - flush_work(&vblk->config_work); - refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount); put_disk(vblk->disk); - mempool_destroy(vblk->pool); vdev->config->del_vqs(vdev); + kfree(vblk->vqs); kfree(vblk); /* Only free device id if we don't have any users */ @@ -899,7 +792,7 @@ ida_simple_remove(&vd_index_ida, index); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; @@ -907,17 +800,10 @@ /* Ensure we don't receive any more interrupts */ vdev->config->reset(vdev); - /* Prevent config work handler from accessing the device. */ - mutex_lock(&vblk->config_lock); - vblk->config_enable = false; - mutex_unlock(&vblk->config_lock); - + /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); - spin_lock_irq(vblk->disk->queue->queue_lock); - blk_stop_queue(vblk->disk->queue); - spin_unlock_irq(vblk->disk->queue->queue_lock); - blk_sync_queue(vblk->disk->queue); + blk_mq_stop_hw_queues(vblk->disk->queue); vdev->config->del_vqs(vdev); return 0; @@ -928,14 +814,14 @@ struct virtio_blk *vblk = vdev->priv; int ret; - vblk->config_enable = true; ret = init_vq(vdev->priv); - if (!ret) { - spin_lock_irq(vblk->disk->queue->queue_lock); - blk_start_queue(vblk->disk->queue); - spin_unlock_irq(vblk->disk->queue->queue_lock); - } - return ret; + if (ret) + return ret; + + virtio_device_ready(vdev); + + blk_mq_start_stopped_hw_queues(vblk->disk->queue, true); + return 0; } #endif @@ -944,24 +830,34 @@ { 0 }, }; -static unsigned int features[] = { +static unsigned int features_legacy[] = { VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI, - VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE + VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, + VIRTIO_BLK_F_MQ, +} +; +static unsigned int features[] = { + VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY, + VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, + VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, + VIRTIO_BLK_F_MQ, }; static struct virtio_driver virtio_blk = { - .feature_table = features, - .feature_table_size = ARRAY_SIZE(features), - .driver.name = KBUILD_MODNAME, - .driver.owner = THIS_MODULE, - .id_table = id_table, - .probe = virtblk_probe, - .remove = virtblk_remove, - .config_changed = virtblk_config_changed, -#ifdef CONFIG_PM - .freeze = virtblk_freeze, - .restore = virtblk_restore, + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .feature_table_legacy = features_legacy, + .feature_table_size_legacy = ARRAY_SIZE(features_legacy), + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = virtblk_probe, + .remove = virtblk_remove, + .config_changed = virtblk_config_changed, +#ifdef CONFIG_PM_SLEEP + .freeze = virtblk_freeze, + .restore = virtblk_restore, #endif }; @@ -993,8 +889,8 @@ static void __exit fini(void) { - unregister_blkdev(major, "virtblk"); unregister_virtio_driver(&virtio_blk); + unregister_blkdev(major, "virtblk"); destroy_workqueue(virtblk_wq); } module_init(init);