sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
}
-void blk_mq_freeze_queue_start(struct request_queue *q)
+void blk_freeze_queue_start(struct request_queue *q)
{
int freeze_depth;
blk_mq_run_hw_queues(q, false);
}
}
-EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
+EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
void blk_mq_freeze_queue_wait(struct request_queue *q)
{
* no blk_unfreeze_queue(), and blk_freeze_queue() is not
* exported to drivers as the only user for unfreeze is blk_mq.
*/
- blk_mq_freeze_queue_start(q);
+ blk_freeze_queue_start(q);
blk_mq_freeze_queue_wait(q);
}
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
- blk_stat_set_issue_time(&rq->issue_stat);
+ blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
rq->rq_flags |= RQF_STATS;
wbt_issue(q->rq_wb, &rq->issue_stat);
}
}
EXPORT_SYMBOL(blk_mq_start_request);
+/*
+ * When we reach here because queue is busy, REQ_ATOM_COMPLETE
+ * flag isn't set yet, so there may be race with timeout hanlder,
+ * but given rq->deadline is just set in .queue_rq() under
+ * this situation, the race won't be possible in reality because
+ * rq->timeout should be set as big enough to cover the window
+ * between blk_mq_start_request() called from .queue_rq() and
+ * clearing REQ_ATOM_STARTED here.
+ */
static void __blk_mq_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
{
struct blk_mq_timeout_data *data = priv;
- if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
- /*
- * If a request wasn't started before the queue was
- * marked dying, kill it here or it'll go unnoticed.
- */
- if (unlikely(blk_queue_dying(rq->q))) {
- rq->errors = -EIO;
- blk_mq_end_request(rq, rq->errors);
- }
+ if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
return;
- }
+ /*
+ * The rq being checked may have been freed and reallocated
+ * out already here, we avoid this race by checking rq->deadline
+ * and REQ_ATOM_COMPLETE flag together:
+ *
+ * - if rq->deadline is observed as new value because of
+ * reusing, the rq won't be timed out because of timing.
+ * - if rq->deadline is observed as previous value,
+ * REQ_ATOM_COMPLETE flag won't be cleared in reuse path
+ * because we put a barrier between setting rq->deadline
+ * and clearing the flag in blk_mq_start_request(), so
+ * this rq won't be timed out too.
+ */
if (time_after_eq(jiffies, rq->deadline)) {
if (!blk_mark_rq_complete(rq))
blk_mq_rq_timed_out(rq, reserved);
* percpu_ref_tryget directly, because we need to be able to
* obtain a reference even in the short window between the queue
* starting to freeze, by dropping the first reference in
- * blk_mq_freeze_queue_start, and the moment the last request is
+ * blk_freeze_queue_start, and the moment the last request is
* consumed, marked by the instant q_usage_counter reaches
* zero.
*/
return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
}
-static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
+static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
bool may_sleep)
{
struct request_queue *q = rq->q;
blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
}
-/*
- * Multiple hardware queue variant. This will not use per-process plugs,
- * but will attempt to bypass the hctx queueing if we can go straight to
- * hardware for SYNC IO.
- */
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+ struct request *rq, blk_qc_t *cookie)
+{
+ if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+ rcu_read_lock();
+ __blk_mq_try_issue_directly(rq, cookie, false);
+ rcu_read_unlock();
+ } else {
+ unsigned int srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+ __blk_mq_try_issue_directly(rq, cookie, true);
+ srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+ }
+}
+
static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
{
const int is_sync = op_is_sync(bio->bi_opf);
const int is_flush_fua = op_is_flush(bio->bi_opf);
struct blk_mq_alloc_data data = { .flags = 0 };
struct request *rq;
- unsigned int request_count = 0, srcu_idx;
+ unsigned int request_count = 0;
struct blk_plug *plug;
struct request *same_queue_rq = NULL;
blk_qc_t cookie;
cookie = request_to_qc_t(data.hctx, rq);
- if (unlikely(is_flush_fua)) {
- if (q->elevator)
- goto elv_insert;
- blk_mq_bio_to_request(rq, bio);
- blk_insert_flush(rq);
- goto run_queue;
- }
-
plug = current->plug;
- /*
- * 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 (((plug && !blk_queue_nomerges(q)) || is_sync) &&
- !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
- struct request *old_rq = NULL;
-
+ if (unlikely(is_flush_fua)) {
blk_mq_bio_to_request(rq, bio);
-
- /*
- * We do limited plugging. If the bio can be merged, do that.
- * Otherwise the existing request in the plug list will be
- * issued. So the plug list will have one request at most
- */
- if (plug) {
- /*
- * The plug list might get flushed before this. If that
- * happens, same_queue_rq is invalid and plug list is
- * empty
- */
- if (same_queue_rq && !list_empty(&plug->mq_list)) {
- old_rq = same_queue_rq;
- list_del_init(&old_rq->queuelist);
- }
- list_add_tail(&rq->queuelist, &plug->mq_list);
- } else /* is_sync */
- old_rq = rq;
- blk_mq_put_ctx(data.ctx);
- if (!old_rq)
- goto done;
-
- if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
- rcu_read_lock();
- blk_mq_try_issue_directly(old_rq, &cookie, false);
- rcu_read_unlock();
+ if (q->elevator) {
+ blk_mq_sched_insert_request(rq, false, true, true,
+ true);
} else {
- srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
- blk_mq_try_issue_directly(old_rq, &cookie, true);
- srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
+ blk_insert_flush(rq);
+ blk_mq_run_hw_queue(data.hctx, true);
}
- goto done;
- }
-
- if (q->elevator) {
-elv_insert:
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
- blk_mq_sched_insert_request(rq, false, true,
- !is_sync || is_flush_fua, true);
- goto done;
- }
- if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
- /*
- * For a SYNC request, send it to the hardware immediately. For
- * an ASYNC request, just ensure that we run it later on. The
- * latter allows for merging opportunities and more efficient
- * dispatching.
- */
-run_queue:
- blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
- }
- blk_mq_put_ctx(data.ctx);
-done:
- return cookie;
-}
-
-/*
- * Single hardware queue variant. This will attempt to use any per-process
- * plug for merging and IO deferral.
- */
-static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
-{
- const int is_sync = op_is_sync(bio->bi_opf);
- const int is_flush_fua = op_is_flush(bio->bi_opf);
- struct blk_plug *plug;
- unsigned int request_count = 0;
- struct blk_mq_alloc_data data = { .flags = 0 };
- struct request *rq;
- blk_qc_t cookie;
- unsigned int wb_acct;
-
- blk_queue_bounce(q, &bio);
-
- if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio_io_error(bio);
- return BLK_QC_T_NONE;
- }
-
- blk_queue_split(q, &bio, q->bio_split);
-
- if (!is_flush_fua && !blk_queue_nomerges(q)) {
- if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
- return BLK_QC_T_NONE;
- } else
- request_count = blk_plug_queued_count(q);
-
- if (blk_mq_sched_bio_merge(q, bio))
- return BLK_QC_T_NONE;
-
- wb_acct = wbt_wait(q->rq_wb, bio, NULL);
-
- trace_block_getrq(q, bio, bio->bi_opf);
-
- rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
- if (unlikely(!rq)) {
- __wbt_done(q->rq_wb, wb_acct);
- return BLK_QC_T_NONE;
- }
-
- wbt_track(&rq->issue_stat, wb_acct);
-
- cookie = request_to_qc_t(data.hctx, rq);
-
- if (unlikely(is_flush_fua)) {
- if (q->elevator)
- goto elv_insert;
- blk_mq_bio_to_request(rq, bio);
- blk_insert_flush(rq);
- goto run_queue;
- }
-
- /*
- * A task plug currently exists. Since this is completely lockless,
- * utilize that to temporarily store requests until the task is
- * either done or scheduled away.
- */
- plug = current->plug;
- if (plug) {
+ } else if (plug && q->nr_hw_queues == 1) {
struct request *last = NULL;
blk_mq_bio_to_request(rq, bio);
*/
if (list_empty(&plug->mq_list))
request_count = 0;
+ else if (blk_queue_nomerges(q))
+ request_count = blk_plug_queued_count(q);
+
if (!request_count)
trace_block_plug(q);
else
last = list_entry_rq(plug->mq_list.prev);
- blk_mq_put_ctx(data.ctx);
-
if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_flush_plug_list(plug, false);
}
list_add_tail(&rq->queuelist, &plug->mq_list);
- return cookie;
- }
-
- if (q->elevator) {
-elv_insert:
- blk_mq_put_ctx(data.ctx);
+ } else if (plug && !blk_queue_nomerges(q)) {
blk_mq_bio_to_request(rq, bio);
- blk_mq_sched_insert_request(rq, false, true,
- !is_sync || is_flush_fua, true);
- goto done;
- }
- if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+
/*
- * For a SYNC request, send it to the hardware immediately. For
- * an ASYNC request, just ensure that we run it later on. The
- * latter allows for merging opportunities and more efficient
- * dispatching.
+ * We do limited plugging. If the bio can be merged, do that.
+ * Otherwise the existing request in the plug list will be
+ * issued. So the plug list will have one request at most
+ * The plug list might get flushed before this. If that happens,
+ * the plug list is empty, and same_queue_rq is invalid.
*/
-run_queue:
- blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
+ if (list_empty(&plug->mq_list))
+ same_queue_rq = NULL;
+ if (same_queue_rq)
+ list_del_init(&same_queue_rq->queuelist);
+ list_add_tail(&rq->queuelist, &plug->mq_list);
+
+ if (same_queue_rq)
+ blk_mq_try_issue_directly(data.hctx, same_queue_rq,
+ &cookie);
+ } else if (q->nr_hw_queues > 1 && is_sync) {
+ blk_mq_bio_to_request(rq, bio);
+ blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+ } else if (q->elevator) {
+ blk_mq_bio_to_request(rq, bio);
+ blk_mq_sched_insert_request(rq, false, true, true, true);
+ } else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+ blk_mq_run_hw_queue(data.hctx, true);
}
blk_mq_put_ctx(data.ctx);
-done:
return cookie;
}
INIT_LIST_HEAD(&q->requeue_list);
spin_lock_init(&q->requeue_lock);
- if (q->nr_hw_queues > 1)
- blk_queue_make_request(q, blk_mq_make_request);
- else
- blk_queue_make_request(q, blk_sq_make_request);
+ blk_queue_make_request(q, blk_mq_make_request);
/*
* Do this after blk_queue_make_request() overrides it...
* take place in parallel.
*/
list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_freeze_queue_start(q);
+ blk_freeze_queue_start(q);
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_freeze_queue_wait(q);
set->nr_hw_queues = nr_hw_queues;
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_realloc_hw_ctxs(set, q);
-
- /*
- * Manually set the make_request_fn as blk_queue_make_request
- * resets a lot of the queue settings.
- */
- if (q->nr_hw_queues > 1)
- q->make_request_fn = blk_mq_make_request;
- else
- q->make_request_fn = blk_sq_make_request;
-
blk_mq_queue_reinit(q, cpu_online_mask);
}
projects / mirror_ubuntu-artful-kernel.git / blobdiff