that requests are restarted in the order they were queue. This may happen
if the driver needs to use blk_queue_invalidate_tags().
-Tagging also defines a new request flag, REQ_QUEUED. This is set whenever
-a request is currently tagged. You should not use this flag directly,
-blk_rq_tagged(rq) is the portable way to do so.
-
3.3 I/O Submission
The routine submit_bio() is used to submit a single io. Higher level i/o
request safely. The io scheduler may still
want to stop a merge at this point if it
results in some sort of conflict internally,
- this hook allows it to do that.
+ this hook allows it to do that. Note however
+ that two *requests* can still be merged at later
+ time. Currently the io scheduler has no way to
+ prevent that. It can only learn about the fact
+ from elevator_merge_req_fn callback.
elevator_dispatch_fn* fills the dispatch queue with ready requests.
I/O schedulers are free to postpone requests by
del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
blk_sync_queue(q);
+ if (q->mq_ops)
+ blk_mq_free_queue(q);
+
spin_lock_irq(lock);
if (q->queue_lock != &q->__queue_lock)
q->queue_lock = &q->__queue_lock;
blk_clear_rq_complete(rq);
trace_block_rq_requeue(q, rq);
- if (blk_rq_tagged(rq))
+ if (rq->cmd_flags & REQ_QUEUED)
blk_queue_end_tag(q, rq);
BUG_ON(blk_queued_rq(rq));
}
EXPORT_SYMBOL_GPL(part_round_stats);
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
static void blk_pm_put_request(struct request *rq)
{
if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending)
}
}
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
/*
* Don't process normal requests when queue is suspended
* or in the process of suspending/resuming
*/
void blk_finish_request(struct request *req, int error)
{
- if (blk_rq_tagged(req))
+ if (req->cmd_flags & REQ_QUEUED)
blk_queue_end_tag(req->q, req);
BUG_ON(blk_queued_rq(req));
}
EXPORT_SYMBOL(blk_finish_plug);
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
/**
* blk_pm_runtime_init - Block layer runtime PM initialization routine
* @q: the queue of the device
static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
{
int tag, org_last_tag, end;
+ bool wrap = last_tag != 0;
org_last_tag = last_tag;
end = bm->depth;
* We started with an offset, start from 0 to
* exhaust the map.
*/
- if (org_last_tag && last_tag) {
- end = last_tag;
+ if (wrap) {
+ wrap = false;
+ end = org_last_tag;
last_tag = 0;
goto restart;
}
return -1;
}
last_tag = tag + 1;
- } while (test_and_set_bit_lock(tag, &bm->word));
+ } while (test_and_set_bit(tag, &bm->word));
return tag;
}
if (!(data->gfp & __GFP_WAIT))
return -1;
- bs = bt_wait_ptr(bt, hctx);
do {
+ bs = bt_wait_ptr(bt, hctx);
prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
tag = __bt_get(hctx, bt, last_tag);
if (tag != -1)
break;
+ /*
+ * We're out of tags on this hardware queue, kick any
+ * pending IO submits before going to sleep waiting for
+ * some to complete.
+ */
+ blk_mq_run_hw_queue(hctx, false);
+
+ /*
+ * Retry tag allocation after running the hardware queue,
+ * as running the queue may also have found completions.
+ */
+ tag = __bt_get(hctx, bt, last_tag);
+ if (tag != -1)
+ break;
+
blk_mq_put_ctx(data->ctx);
io_schedule();
hctx = data->hctx;
bt = &hctx->tags->bitmap_tags;
}
- finish_wait(&bs->wait, &wait);
- bs = bt_wait_ptr(bt, hctx);
} while (1);
finish_wait(&bs->wait, &wait);
struct bt_wait_state *bs;
int wait_cnt;
- /*
- * The unlock memory barrier need to order access to req in free
- * path and clearing tag bit
- */
- clear_bit_unlock(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+ clear_bit(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+
+ /* Ensure that the wait list checks occur after clear_bit(). */
+ smp_mb();
bs = bt_wake_ptr(bt);
if (!bs)
}
}
- static void __blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
- {
- BUG_ON(tag >= tags->nr_tags);
-
- bt_clear_tag(&tags->bitmap_tags, tag);
- }
-
- static void __blk_mq_put_reserved_tag(struct blk_mq_tags *tags,
- unsigned int tag)
- {
- BUG_ON(tag >= tags->nr_reserved_tags);
-
- bt_clear_tag(&tags->breserved_tags, tag);
- }
-
void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
unsigned int *last_tag)
{
if (tag >= tags->nr_reserved_tags) {
const int real_tag = tag - tags->nr_reserved_tags;
- __blk_mq_put_tag(tags, real_tag);
+ BUG_ON(real_tag >= tags->nr_tags);
+ bt_clear_tag(&tags->bitmap_tags, real_tag);
*last_tag = real_tag;
- } else
- __blk_mq_put_reserved_tag(tags, tag);
+ } else {
+ BUG_ON(tag >= tags->nr_reserved_tags);
+ bt_clear_tag(&tags->breserved_tags, tag);
+ }
}
static void bt_for_each(struct blk_mq_hw_ctx *hctx,
return 0;
}
+/**
+ * blk_mq_unique_tag() - return a tag that is unique queue-wide
+ * @rq: request for which to compute a unique tag
+ *
+ * The tag field in struct request is unique per hardware queue but not over
+ * all hardware queues. Hence this function that returns a tag with the
+ * hardware context index in the upper bits and the per hardware queue tag in
+ * the lower bits.
+ *
+ * Note: When called for a request that is queued on a non-multiqueue request
+ * queue, the hardware context index is set to zero.
+ */
+u32 blk_mq_unique_tag(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ struct blk_mq_hw_ctx *hctx;
+ int hwq = 0;
+
+ if (q->mq_ops) {
+ hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+ hwq = hctx->queue_num;
+ }
+
+ return (hwq << BLK_MQ_UNIQUE_TAG_BITS) |
+ (rq->tag & BLK_MQ_UNIQUE_TAG_MASK);
+}
+EXPORT_SYMBOL(blk_mq_unique_tag);
+
ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
{
char *orig_page = page;
wake_up_all(&q->mq_freeze_wq);
}
-/*
- * Guarantee no request is in use, so we can change any data structure of
- * the queue afterward.
- */
-void blk_mq_freeze_queue(struct request_queue *q)
+static void blk_mq_freeze_queue_start(struct request_queue *q)
{
bool freeze;
percpu_ref_kill(&q->mq_usage_counter);
blk_mq_run_queues(q, false);
}
+}
+
+static void blk_mq_freeze_queue_wait(struct request_queue *q)
+{
wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
}
+/*
+ * Guarantee no request is in use, so we can change any data structure of
+ * the queue afterward.
+ */
+void blk_mq_freeze_queue(struct request_queue *q)
+{
+ blk_mq_freeze_queue_start(q);
+ blk_mq_freeze_queue_wait(q);
+}
+
static void blk_mq_unfreeze_queue(struct request_queue *q)
{
bool wake;
blk_mq_queue_exit(q);
}
- void blk_mq_free_request(struct request *rq)
+ void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
- struct blk_mq_hw_ctx *hctx;
- struct request_queue *q = rq->q;
ctx->rq_completed[rq_is_sync(rq)]++;
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
__blk_mq_free_request(hctx, ctx, rq);
+
+ }
+ EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
+
+ void blk_mq_free_request(struct request *rq)
+ {
+ struct blk_mq_hw_ctx *hctx;
+ struct request_queue *q = rq->q;
+
+ hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+ blk_mq_free_hctx_request(hctx, rq);
}
+ EXPORT_SYMBOL_GPL(blk_mq_free_request);
inline void __blk_mq_end_request(struct request *rq, int error)
{
* If not software queues are currently mapped to this
* hardware queue, there's nothing to check
*/
- if (!hctx->nr_ctx || !hctx->tags)
+ if (!blk_mq_hw_queue_mapped(hctx))
continue;
blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data);
struct request_queue *q = hctx->queue;
struct request *rq;
LIST_HEAD(rq_list);
+ LIST_HEAD(driver_list);
+ struct list_head *dptr;
int queued;
WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
spin_unlock(&hctx->lock);
}
+ /*
+ * Start off with dptr being NULL, so we start the first request
+ * immediately, even if we have more pending.
+ */
+ dptr = NULL;
+
/*
* Now process all the entries, sending them to the driver.
*/
queued = 0;
while (!list_empty(&rq_list)) {
+ struct blk_mq_queue_data bd;
int ret;
rq = list_first_entry(&rq_list, struct request, queuelist);
list_del_init(&rq->queuelist);
- ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
+ bd.rq = rq;
+ bd.list = dptr;
+ bd.last = list_empty(&rq_list);
+
+ ret = q->mq_ops->queue_rq(hctx, &bd);
switch (ret) {
case BLK_MQ_RQ_QUEUE_OK:
queued++;
if (ret == BLK_MQ_RQ_QUEUE_BUSY)
break;
+
+ /*
+ * We've done the first request. If we have more than 1
+ * left in the list, set dptr to defer issue.
+ */
+ if (!dptr && rq_list.next != rq_list.prev)
+ dptr = &driver_list;
}
if (!queued)
*/
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
{
- int cpu = hctx->next_cpu;
+ if (hctx->queue->nr_hw_queues == 1)
+ return WORK_CPU_UNBOUND;
if (--hctx->next_cpu_batch <= 0) {
- int next_cpu;
+ int cpu = hctx->next_cpu, next_cpu;
next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
if (next_cpu >= nr_cpu_ids)
hctx->next_cpu = next_cpu;
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+
+ return cpu;
}
- return cpu;
+ return hctx->next_cpu;
}
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
- if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
+ if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state) ||
+ !blk_mq_hw_queue_mapped(hctx)))
return;
- if (!async && cpumask_test_cpu(smp_processor_id(), hctx->cpumask))
- __blk_mq_run_hw_queue(hctx);
- else if (hctx->queue->nr_hw_queues == 1)
- kblockd_schedule_delayed_work(&hctx->run_work, 0);
- else {
- unsigned int cpu;
+ if (!async) {
+ int cpu = get_cpu();
+ if (cpumask_test_cpu(cpu, hctx->cpumask)) {
+ __blk_mq_run_hw_queue(hctx);
+ put_cpu();
+ return;
+ }
- cpu = blk_mq_hctx_next_cpu(hctx);
- kblockd_schedule_delayed_work_on(cpu, &hctx->run_work, 0);
+ put_cpu();
}
+
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->run_work, 0);
}
void blk_mq_run_queues(struct request_queue *q, bool async)
test_bit(BLK_MQ_S_STOPPED, &hctx->state))
continue;
- preempt_disable();
blk_mq_run_hw_queue(hctx, async);
- preempt_enable();
}
}
EXPORT_SYMBOL(blk_mq_run_queues);
{
clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
- preempt_disable();
blk_mq_run_hw_queue(hctx, false);
- preempt_enable();
}
EXPORT_SYMBOL(blk_mq_start_hw_queue);
continue;
clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
- preempt_disable();
blk_mq_run_hw_queue(hctx, async);
- preempt_enable();
}
}
EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
- unsigned long tmo = msecs_to_jiffies(msecs);
-
- if (hctx->queue->nr_hw_queues == 1)
- kblockd_schedule_delayed_work(&hctx->delay_work, tmo);
- else {
- unsigned int cpu;
+ if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
+ return;
- cpu = blk_mq_hctx_next_cpu(hctx);
- kblockd_schedule_delayed_work_on(cpu, &hctx->delay_work, tmo);
- }
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->delay_work, msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_queue);
goto run_queue;
}
- if (is_sync) {
+ /*
+ * If the driver supports defer issued based on 'last', then
+ * queue it up like normal since we can potentially save some
+ * CPU this way.
+ */
+ if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
+ struct blk_mq_queue_data bd = {
+ .rq = rq,
+ .list = NULL,
+ .last = 1
+ };
int ret;
blk_mq_bio_to_request(rq, bio);
* error (busy), just add it to our list as we previously
* would have done
*/
- ret = q->mq_ops->queue_rq(data.hctx, rq, true);
+ ret = q->mq_ops->queue_rq(data.hctx, &bd);
if (ret == BLK_MQ_RQ_QUEUE_OK)
goto done;
else {
if (!ctx)
return ERR_PTR(-ENOMEM);
- /*
- * If a crashdump is active, then we are potentially in a very
- * memory constrained environment. Limit us to 1 queue and
- * 64 tags to prevent using too much memory.
- */
- if (is_kdump_kernel()) {
- set->nr_hw_queues = 1;
- set->queue_depth = min(64U, set->queue_depth);
- }
-
hctxs = kmalloc_node(set->nr_hw_queues * sizeof(*hctxs), GFP_KERNEL,
set->numa_node);
/* Basically redo blk_mq_init_queue with queue frozen */
static void blk_mq_queue_reinit(struct request_queue *q)
{
- blk_mq_freeze_queue(q);
+ WARN_ON_ONCE(!q->mq_freeze_depth);
blk_mq_sysfs_unregister(q);
blk_mq_map_swqueue(q);
blk_mq_sysfs_register(q);
-
- blk_mq_unfreeze_queue(q);
}
static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
return NOTIFY_OK;
mutex_lock(&all_q_mutex);
+
+ /*
+ * We need to freeze and reinit all existing queues. Freezing
+ * involves synchronous wait for an RCU grace period and doing it
+ * one by one may take a long time. Start freezing all queues in
+ * one swoop and then wait for the completions so that freezing can
+ * take place in parallel.
+ */
+ list_for_each_entry(q, &all_q_list, all_q_node)
+ blk_mq_freeze_queue_start(q);
+ list_for_each_entry(q, &all_q_list, all_q_node)
+ blk_mq_freeze_queue_wait(q);
+
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_queue_reinit(q);
+
+ list_for_each_entry(q, &all_q_list, all_q_node)
+ blk_mq_unfreeze_queue(q);
+
mutex_unlock(&all_q_mutex);
return NOTIFY_OK;
}
*/
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
+ BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
+
if (!set->nr_hw_queues)
return -EINVAL;
if (!set->queue_depth)
set->queue_depth = BLK_MQ_MAX_DEPTH;
}
+ /*
+ * If a crashdump is active, then we are potentially in a very
+ * memory constrained environment. Limit us to 1 queue and
+ * 64 tags to prevent using too much memory.
+ */
+ if (is_kdump_kernel()) {
+ set->nr_hw_queues = 1;
+ set->queue_depth = min(64U, set->queue_depth);
+ }
+
set->tags = kmalloc_node(set->nr_hw_queues *
sizeof(struct blk_mq_tags *),
GFP_KERNEL, set->numa_node);
}
}
- static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
- bool last)
+ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *bd)
{
- struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
- cmd->rq = rq;
+ cmd->rq = bd->rq;
cmd->nq = hctx->driver_data;
- blk_mq_start_request(rq);
+ blk_mq_start_request(bd->rq);
null_handle_cmd(cmd);
return BLK_MQ_RQ_QUEUE_OK;
ret = setup_commands(nq);
if (ret)
- goto err_queue;
+ return ret;
nullb->nr_queues++;
}
-
return 0;
-err_queue:
- cleanup_queues(nullb);
- return ret;
}
static int null_add_dev(void)
goto out_cleanup_queues;
}
blk_queue_make_request(nullb->q, null_queue_bio);
- init_driver_queues(nullb);
+ rv = init_driver_queues(nullb);
+ if (rv)
+ goto out_cleanup_blk_queue;
} else {
nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node);
if (!nullb->q) {
}
blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
- init_driver_queues(nullb);
+ rv = init_driver_queues(nullb);
+ if (rv)
+ goto out_cleanup_blk_queue;
}
nullb->q->queuedata = nullb;
{
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;
* 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));
static inline void virtblk_request_done(struct request *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;
+ 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_SPECIAL) {
req->errors = (error != 0);
}
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
}
- static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
- bool last)
+ 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;
vbr->req = req;
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;
+ 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. */
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);
}
spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
return BLK_MQ_RQ_QUEUE_ERROR;
}
- if (last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
+ if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
notify = true;
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
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)
{
struct virtio_blk_config, wce,
&writeback);
if (err)
- writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+ writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) ||
+ virtio_has_feature(vdev, VIRTIO_F_VERSION_1);
return writeback;
}
{ 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_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_TOPOLOGY,
+ 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,
+ .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,
+ .freeze = virtblk_freeze,
+ .restore = virtblk_restore,
#endif
};
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);
#include <linux/hardirq.h>
#include <linux/scatterlist.h>
#include <linux/blk-mq.h>
+#include <linux/ratelimit.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
mempool_t *pool;
};
-#define SP(x) { x, "sgpool-" __stringify(x) }
+#define SP(x) { .size = x, "sgpool-" __stringify(x) }
#if (SCSI_MAX_SG_SEGMENTS < 32)
#error SCSI_MAX_SG_SEGMENTS is too small (must be 32 or greater)
#endif
put_device(&sdev->sdev_gendev);
}
-void scsi_next_command(struct scsi_cmnd *cmd)
-{
- struct scsi_device *sdev = cmd->device;
- struct request_queue *q = sdev->request_queue;
-
- scsi_put_command(cmd);
- scsi_run_queue(q);
-
- put_device(&sdev->sdev_gendev);
-}
-
void scsi_run_host_queues(struct Scsi_Host *shost)
{
struct scsi_device *sdev;
__sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free);
}
-static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents,
- gfp_t gfp_mask, bool mq)
+static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, bool mq)
{
struct scatterlist *first_chunk = NULL;
+ gfp_t gfp_mask = mq ? GFP_NOIO : GFP_ATOMIC;
int ret;
BUG_ON(!nents);
kblockd_schedule_work(&sdev->requeue_work);
else
blk_mq_start_stopped_hw_queues(q, true);
-
- put_device(&sdev->sdev_gendev);
} else {
unsigned long flags;
spin_unlock_irqrestore(q->queue_lock, flags);
scsi_release_buffers(cmd);
- scsi_next_command(cmd);
+
+ scsi_put_command(cmd);
+ scsi_run_queue(q);
}
+ put_device(&sdev->sdev_gendev);
return false;
}
struct request *req = cmd->request;
int error = 0;
struct scsi_sense_hdr sshdr;
- int sense_valid = 0;
- int sense_deferred = 0;
+ bool sense_valid = false;
+ int sense_deferred = 0, level = 0;
enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
ACTION_DELAYED_RETRY} action;
unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
;
else if (!(req->cmd_flags & REQ_QUIET))
- scsi_print_sense("", cmd);
+ scsi_print_sense(cmd);
result = 0;
/* BLOCK_PC may have set error */
error = 0;
case ACTION_FAIL:
/* Give up and fail the remainder of the request */
if (!(req->cmd_flags & REQ_QUIET)) {
- scsi_print_result(cmd);
- if (driver_byte(result) & DRIVER_SENSE)
- scsi_print_sense("", cmd);
- scsi_print_command(cmd);
+ static DEFINE_RATELIMIT_STATE(_rs,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+
+ if (unlikely(scsi_logging_level))
+ level = SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
+ SCSI_LOG_MLCOMPLETE_BITS);
+
+ /*
+ * if logging is enabled the failure will be printed
+ * in scsi_log_completion(), so avoid duplicate messages
+ */
+ if (!level && __ratelimit(&_rs)) {
+ scsi_print_result(cmd, NULL, FAILED);
+ if (driver_byte(result) & DRIVER_SENSE)
+ scsi_print_sense(cmd);
+ scsi_print_command(cmd);
+ }
}
if (!scsi_end_request(req, error, blk_rq_err_bytes(req), 0))
return;
}
}
-static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
- gfp_t gfp_mask)
+static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
{
int count;
* If sg table allocation fails, requeue request later.
*/
if (unlikely(scsi_alloc_sgtable(sdb, req->nr_phys_segments,
- gfp_mask, req->mq_ctx != NULL)))
+ req->mq_ctx != NULL)))
return BLKPREP_DEFER;
/*
* BLKPREP_DEFER if the failure is retryable
* BLKPREP_KILL if the failure is fatal
*/
-int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
+int scsi_init_io(struct scsi_cmnd *cmd)
{
struct scsi_device *sdev = cmd->device;
struct request *rq = cmd->request;
BUG_ON(!rq->nr_phys_segments);
- error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask);
+ error = scsi_init_sgtable(rq, &cmd->sdb);
if (error)
goto err_exit;
rq->next_rq->special = bidi_sdb;
}
- error = scsi_init_sgtable(rq->next_rq, rq->next_rq->special,
- GFP_ATOMIC);
+ error = scsi_init_sgtable(rq->next_rq, rq->next_rq->special);
if (error)
goto err_exit;
}
BUG_ON(prot_sdb == NULL);
ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
- if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask, is_mq)) {
+ if (scsi_alloc_sgtable(prot_sdb, ivecs, is_mq)) {
error = BLKPREP_DEFER;
goto err_exit;
}
* submit a request without an attached bio.
*/
if (req->bio) {
- int ret = scsi_init_io(cmd, GFP_ATOMIC);
+ int ret = scsi_init_io(cmd);
if (unlikely(ret))
return ret;
} else {
}
}
+/**
+ * scsi_dispatch_command - Dispatch a command to the low-level driver.
+ * @cmd: command block we are dispatching.
+ *
+ * Return: nonzero return request was rejected and device's queue needs to be
+ * plugged.
+ */
+static int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
+{
+ struct Scsi_Host *host = cmd->device->host;
+ int rtn = 0;
+
+ atomic_inc(&cmd->device->iorequest_cnt);
+
+ /* check if the device is still usable */
+ if (unlikely(cmd->device->sdev_state == SDEV_DEL)) {
+ /* in SDEV_DEL we error all commands. DID_NO_CONNECT
+ * returns an immediate error upwards, and signals
+ * that the device is no longer present */
+ cmd->result = DID_NO_CONNECT << 16;
+ goto done;
+ }
+
+ /* Check to see if the scsi lld made this device blocked. */
+ if (unlikely(scsi_device_blocked(cmd->device))) {
+ /*
+ * in blocked state, the command is just put back on
+ * the device queue. The suspend state has already
+ * blocked the queue so future requests should not
+ * occur until the device transitions out of the
+ * suspend state.
+ */
+ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
+ "queuecommand : device blocked\n"));
+ return SCSI_MLQUEUE_DEVICE_BUSY;
+ }
+
+ /* Store the LUN value in cmnd, if needed. */
+ if (cmd->device->lun_in_cdb)
+ cmd->cmnd[1] = (cmd->cmnd[1] & 0x1f) |
+ (cmd->device->lun << 5 & 0xe0);
+
+ scsi_log_send(cmd);
+
+ /*
+ * Before we queue this command, check if the command
+ * length exceeds what the host adapter can handle.
+ */
+ if (cmd->cmd_len > cmd->device->host->max_cmd_len) {
+ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
+ "queuecommand : command too long. "
+ "cdb_size=%d host->max_cmd_len=%d\n",
+ cmd->cmd_len, cmd->device->host->max_cmd_len));
+ cmd->result = (DID_ABORT << 16);
+ goto done;
+ }
+
+ if (unlikely(host->shost_state == SHOST_DEL)) {
+ cmd->result = (DID_NO_CONNECT << 16);
+ goto done;
+
+ }
+
+ trace_scsi_dispatch_cmd_start(cmd);
+ rtn = host->hostt->queuecommand(host, cmd);
+ if (rtn) {
+ trace_scsi_dispatch_cmd_error(cmd, rtn);
+ if (rtn != SCSI_MLQUEUE_DEVICE_BUSY &&
+ rtn != SCSI_MLQUEUE_TARGET_BUSY)
+ rtn = SCSI_MLQUEUE_HOST_BUSY;
+
+ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd,
+ "queuecommand : request rejected\n"));
+ }
+
+ return rtn;
+ done:
+ cmd->scsi_done(cmd);
+ return 0;
+}
+
/**
* scsi_done - Invoke completion on finished SCSI command.
* @cmd: The SCSI Command for which a low-level device driver (LLDD) gives
* we add the dev to the starved list so it eventually gets
* a run when a tag is freed.
*/
- if (blk_queue_tagged(q) && !blk_rq_tagged(req)) {
+ if (blk_queue_tagged(q) && !(req->cmd_flags & REQ_QUEUED)) {
spin_lock_irq(shost->host_lock);
if (list_empty(&sdev->starved_entry))
list_add_tail(&sdev->starved_entry,
if (!scsi_host_queue_ready(q, shost, sdev))
goto host_not_ready;
+
+ if (sdev->simple_tags)
+ cmd->flags |= SCMD_TAGGED;
+ else
+ cmd->flags &= ~SCMD_TAGGED;
/*
* Finally, initialize any error handling parameters, and set up
blk_mq_complete_request(cmd->request);
}
- static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
- bool last)
+ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *bd)
{
+ struct request *req = bd->rq;
struct request_queue *q = req->q;
struct scsi_device *sdev = q->queuedata;
struct Scsi_Host *shost = sdev->host;
blk_mq_start_request(req);
}
+ if (sdev->simple_tags)
+ cmd->flags |= SCMD_TAGGED;
+ else
+ cmd->flags &= ~SCMD_TAGGED;
+
scsi_init_cmd_errh(cmd);
cmd->scsi_done = scsi_mq_done;
memset(&shost->tag_set, 0, sizeof(shost->tag_set));
shost->tag_set.ops = &scsi_mq_ops;
- shost->tag_set.nr_hw_queues = 1;
+ shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1;
shost->tag_set.queue_depth = shost->can_queue;
shost->tag_set.cmd_size = cmd_size;
shost->tag_set.numa_node = NUMA_NO_NODE;
struct list_head tag_list;
};
- typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *, bool);
+ struct blk_mq_queue_data {
+ struct request *rq;
+ struct list_head *list;
+ bool last;
+ };
+
+ typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
BLK_MQ_F_TAG_SHARED = 1 << 1,
BLK_MQ_F_SG_MERGE = 1 << 2,
BLK_MQ_F_SYSFS_UP = 1 << 3,
+ BLK_MQ_F_DEFER_ISSUE = 1 << 4,
BLK_MQ_S_STOPPED = 0,
BLK_MQ_S_TAG_ACTIVE = 1,
void blk_mq_insert_request(struct request *, bool, bool, bool);
void blk_mq_run_queues(struct request_queue *q, bool async);
void blk_mq_free_request(struct request *rq);
+ void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
gfp_t gfp, bool reserved);
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+enum {
+ BLK_MQ_UNIQUE_TAG_BITS = 16,
+ BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1,
+};
+
+u32 blk_mq_unique_tag(struct request *rq);
+
+static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag)
+{
+ return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS;
+}
+
+static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
+{
+ return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
+}
+
struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
*/
struct kobject mq_kobj;
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
struct device *dev;
int rpm_status;
unsigned int nr_pending;
/*
* block layer runtime pm functions
*/
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
extern int blk_pre_runtime_suspend(struct request_queue *q);
extern void blk_post_runtime_suspend(struct request_queue *q, int err);
/*
* tag stuff
*/
-#define blk_rq_tagged(rq) \
- ((rq)->mq_ctx || ((rq)->cmd_flags & REQ_QUEUED))
extern int blk_queue_start_tag(struct request_queue *, struct request *);
extern struct request *blk_queue_find_tag(struct request_queue *, int);
extern void blk_queue_end_tag(struct request_queue *, struct request *);
enum blk_default_limits {
BLK_MAX_SEGMENTS = 128,
BLK_SAFE_MAX_SECTORS = 255,
- BLK_DEF_MAX_SECTORS = 1024,
BLK_MAX_SEGMENT_SIZE = 65536,
BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
};
struct request *r1,
struct request *r2)
{
- return 0;
+ return true;
}
static inline bool blk_integrity_merge_bio(struct request_queue *rq,
struct request *r,
struct bio *b)
{
- return 0;
+ return true;
}
static inline bool blk_integrity_is_initialized(struct gendisk *g)
{
r->sector_from = be64_to_cpu(sector_from);
}
-typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
+typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act);
-static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
+static void blk_log_action_classic(struct trace_iterator *iter, const char *act)
{
char rwbs[RWBS_LEN];
unsigned long long ts = iter->ts;
fill_rwbs(rwbs, t);
- return trace_seq_printf(&iter->seq,
- "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
- MAJOR(t->device), MINOR(t->device), iter->cpu,
- secs, nsec_rem, iter->ent->pid, act, rwbs);
+ trace_seq_printf(&iter->seq,
+ "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
+ MAJOR(t->device), MINOR(t->device), iter->cpu,
+ secs, nsec_rem, iter->ent->pid, act, rwbs);
}
-static int blk_log_action(struct trace_iterator *iter, const char *act)
+static void blk_log_action(struct trace_iterator *iter, const char *act)
{
char rwbs[RWBS_LEN];
const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
fill_rwbs(rwbs, t);
- return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
- MAJOR(t->device), MINOR(t->device), act, rwbs);
+ trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
+ MAJOR(t->device), MINOR(t->device), act, rwbs);
}
-static int blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
{
const unsigned char *pdu_buf;
int pdu_len;
- int i, end, ret;
+ int i, end;
pdu_buf = pdu_start(ent);
pdu_len = te_blk_io_trace(ent)->pdu_len;
if (!pdu_len)
- return 1;
+ return;
/* find the last zero that needs to be printed */
for (end = pdu_len - 1; end >= 0; end--)
break;
end++;
- if (!trace_seq_putc(s, '('))
- return 0;
+ trace_seq_putc(s, '(');
for (i = 0; i < pdu_len; i++) {
- ret = trace_seq_printf(s, "%s%02x",
- i == 0 ? "" : " ", pdu_buf[i]);
- if (!ret)
- return ret;
+ trace_seq_printf(s, "%s%02x",
+ i == 0 ? "" : " ", pdu_buf[i]);
/*
* stop when the rest is just zeroes and indicate so
* with a ".." appended
*/
- if (i == end && end != pdu_len - 1)
- return trace_seq_puts(s, " ..) ");
+ if (i == end && end != pdu_len - 1) {
+ trace_seq_puts(s, " ..) ");
+ return;
+ }
}
- return trace_seq_puts(s, ") ");
+ trace_seq_puts(s, ") ");
}
-static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
{
char cmd[TASK_COMM_LEN];
trace_find_cmdline(ent->pid, cmd);
if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
- int ret;
-
- ret = trace_seq_printf(s, "%u ", t_bytes(ent));
- if (!ret)
- return 0;
- ret = blk_log_dump_pdu(s, ent);
- if (!ret)
- return 0;
- return trace_seq_printf(s, "[%s]\n", cmd);
+ trace_seq_printf(s, "%u ", t_bytes(ent));
+ blk_log_dump_pdu(s, ent);
+ trace_seq_printf(s, "[%s]\n", cmd);
} else {
if (t_sec(ent))
- return trace_seq_printf(s, "%llu + %u [%s]\n",
+ trace_seq_printf(s, "%llu + %u [%s]\n",
t_sector(ent), t_sec(ent), cmd);
- return trace_seq_printf(s, "[%s]\n", cmd);
+ else
+ trace_seq_printf(s, "[%s]\n", cmd);
}
}
-static int blk_log_with_error(struct trace_seq *s,
+static void blk_log_with_error(struct trace_seq *s,
const struct trace_entry *ent)
{
if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
- int ret;
-
- ret = blk_log_dump_pdu(s, ent);
- if (ret)
- return trace_seq_printf(s, "[%d]\n", t_error(ent));
- return 0;
+ blk_log_dump_pdu(s, ent);
+ trace_seq_printf(s, "[%d]\n", t_error(ent));
} else {
if (t_sec(ent))
- return trace_seq_printf(s, "%llu + %u [%d]\n",
- t_sector(ent),
- t_sec(ent), t_error(ent));
- return trace_seq_printf(s, "%llu [%d]\n",
- t_sector(ent), t_error(ent));
+ trace_seq_printf(s, "%llu + %u [%d]\n",
+ t_sector(ent),
+ t_sec(ent), t_error(ent));
+ else
+ trace_seq_printf(s, "%llu [%d]\n",
+ t_sector(ent), t_error(ent));
}
}
-static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
{
struct blk_io_trace_remap r = { .device_from = 0, };
get_pdu_remap(ent, &r);
- return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
- t_sector(ent), t_sec(ent),
- MAJOR(r.device_from), MINOR(r.device_from),
- (unsigned long long)r.sector_from);
+ trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
+ t_sector(ent), t_sec(ent),
+ MAJOR(r.device_from), MINOR(r.device_from),
+ (unsigned long long)r.sector_from);
}
-static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
{
char cmd[TASK_COMM_LEN];
trace_find_cmdline(ent->pid, cmd);
- return trace_seq_printf(s, "[%s]\n", cmd);
+ trace_seq_printf(s, "[%s]\n", cmd);
}
-static int blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent)
{
char cmd[TASK_COMM_LEN];
trace_find_cmdline(ent->pid, cmd);
- return trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent));
+ trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent));
}
-static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
{
char cmd[TASK_COMM_LEN];
trace_find_cmdline(ent->pid, cmd);
- return trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent),
- get_pdu_int(ent), cmd);
+ trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent),
+ get_pdu_int(ent), cmd);
}
-static int blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
{
- int ret;
const struct blk_io_trace *t = te_blk_io_trace(ent);
- ret = trace_seq_putmem(s, t + 1, t->pdu_len);
- if (ret)
- return trace_seq_putc(s, '\n');
- return ret;
+ trace_seq_putmem(s, t + 1, t->pdu_len);
+ trace_seq_putc(s, '\n');
}
/*
static const struct {
const char *act[2];
- int (*print)(struct trace_seq *s, const struct trace_entry *ent);
+ void (*print)(struct trace_seq *s, const struct trace_entry *ent);
} what2act[] = {
[__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic },
[__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic },
struct trace_seq *s = &iter->seq;
const struct blk_io_trace *t;
u16 what;
- int ret;
bool long_act;
blk_log_action_t *log_action;
log_action = classic ? &blk_log_action_classic : &blk_log_action;
if (t->action == BLK_TN_MESSAGE) {
- ret = log_action(iter, long_act ? "message" : "m");
- if (ret)
- ret = blk_log_msg(s, iter->ent);
- goto out;
+ log_action(iter, long_act ? "message" : "m");
+ blk_log_msg(s, iter->ent);
}
if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
- ret = trace_seq_printf(s, "Unknown action %x\n", what);
+ trace_seq_printf(s, "Unknown action %x\n", what);
else {
- ret = log_action(iter, what2act[what].act[long_act]);
- if (ret)
- ret = what2act[what].print(s, iter->ent);
+ log_action(iter, what2act[what].act[long_act]);
+ what2act[what].print(s, iter->ent);
}
-out:
- return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+
+ return trace_handle_return(s);
}
static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
return print_one_line(iter, false);
}
-static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
+static void blk_trace_synthesize_old_trace(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
struct blk_io_trace *t = (struct blk_io_trace *)iter->ent;
.time = iter->ts,
};
- if (!trace_seq_putmem(s, &old, offset))
- return 0;
- return trace_seq_putmem(s, &t->sector,
- sizeof(old) - offset + t->pdu_len);
+ trace_seq_putmem(s, &old, offset);
+ trace_seq_putmem(s, &t->sector,
+ sizeof(old) - offset + t->pdu_len);
}
static enum print_line_t
blk_trace_event_print_binary(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
- return blk_trace_synthesize_old_trace(iter) ?
- TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+ blk_trace_synthesize_old_trace(iter);
+
+ return trace_handle_return(&iter->seq);
}
static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
if (atomic_dec_and_test(&blk_probes_ref))
blk_unregister_tracepoints();
- spin_lock_irq(&running_trace_lock);
- list_del(&bt->running_list);
- spin_unlock_irq(&running_trace_lock);
blk_trace_free(bt);
return 0;
}