block: add new fields in request_queue

hulk inclusion
category: performance
bugzilla: https://gitee.com/openeuler/kernel/issues/I5QK5M
CVE: NA

--------------------------------

Add a new flag QUEUE_FLAG_DISPATCH_ASYNC and two new fields
'dispatch_cpumask' and 'last_dispatch_cpu' for request_queue, prepare
to support dispatch bio asynchronous in specified cpus. This patch also
add sysfs apis.
Signed-off-by: NYu Kuai <yukuai3@huawei.com>
Reviewed-by: NJason Yan <yanaijie@huawei.com>
Signed-off-by: NYongqiang Liu <liuyongqiang13@huawei.com>

block/blk-core.c

@@ -85,6 +85,27 @@ struct kmem_cache *blk_requestq_cachep;
  */
 static struct workqueue_struct *kblockd_workqueue;
 
+static int blk_alloc_queue_dispatch_async(struct request_queue *q)
+{
+	int cpu;
+
+	q->last_dispatch_cpu = alloc_percpu(int);
+	if (!q->last_dispatch_cpu)
+		return -ENOMEM;
+
+	cpumask_setall(&q->dispatch_async_cpus);
+	for_each_possible_cpu(cpu) {
+		*per_cpu_ptr(q->last_dispatch_cpu, cpu) = cpu;
+	}
+
+	return 0;
+}
+
+void blk_free_queue_dispatch_async(struct request_queue *q)
+{
+	free_percpu(q->last_dispatch_cpu);
+}
+
 /**
  * blk_queue_flag_set - atomically set a queue flag
  * @flag: flag to be set
@@ -1049,9 +1070,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
 	q->end_sector = 0;
 	q->boundary_rq = NULL;
 
+	if (blk_alloc_queue_dispatch_async(q))
+		goto fail_q;
+
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
 	if (q->id < 0)
-		goto fail_q;
+		goto fail_dispatch_async;
 
 	ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 	if (ret)
@@ -1130,6 +1154,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
 	bioset_exit(&q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
+fail_dispatch_async:
+	blk_free_queue_dispatch_async(q);
 fail_q:
 	kmem_cache_free(blk_requestq_cachep, q_wrapper);
 	return NULL;

block/blk-sysfs.c

@@ -696,6 +696,42 @@ static struct queue_sysfs_entry queue_wb_lat_entry = {
 	.store = queue_wb_lat_store,
 };
 
+static ssize_t queue_dispatch_async_cpus_show(struct request_queue *q,
+					      char *page)
+{
+	int cpu;
+	ssize_t ret = 0;
+
+	if (!test_bit(QUEUE_FLAG_DISPATCH_ASYNC, &q->queue_flags))
+		return -EOPNOTSUPP;
+
+	for_each_cpu(cpu, &q->dispatch_async_cpus) {
+		ret += sprintf(page + ret, "%d ", cpu);
+	}
+
+	ret += sprintf(page + ret, "\n");
+	return ret;
+}
+
+static struct queue_sysfs_entry queue_dispatch_async_cpus_entry = {
+	.attr = {.name = "dispatch_async_cpus", .mode = 0444 },
+	.show = queue_dispatch_async_cpus_show,
+};
+
+static ssize_t queue_show_dispatch_async(struct request_queue *q,
+					 char *page)
+{
+	if (test_bit(QUEUE_FLAG_DISPATCH_ASYNC, &q->queue_flags))
+		return sprintf(page, "1\n");
+	else
+		return sprintf(page, "0\n");
+}
+
+static struct queue_sysfs_entry queue_dispatch_async_entry = {
+	.attr = {.name = "dispatch_async", .mode = 0444 },
+	.show = queue_show_dispatch_async,
+};
+
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 static struct queue_sysfs_entry throtl_sample_time_entry = {
 	.attr = {.name = "throttle_sample_time", .mode = 0644 },
@@ -738,6 +774,8 @@ static struct attribute *default_attrs[] = {
 	&queue_dax_entry.attr,
 	&queue_wb_lat_entry.attr,
 	&queue_poll_delay_entry.attr,
+	&queue_dispatch_async_cpus_entry.attr,
+	&queue_dispatch_async_entry.attr,
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	&throtl_sample_time_entry.attr,
 #endif
@@ -819,6 +857,7 @@ static void __blk_release_queue(struct work_struct *work)
 	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
+	blk_free_queue_dispatch_async(q);
 
 	if (!blk_queue_dead(q)) {
 		/*

block/blk.h

@@ -460,4 +460,6 @@ extern int blk_iolatency_init(struct request_queue *q);
 static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
 #endif
 
+extern void blk_free_queue_dispatch_async(struct request_queue *q);
+
 #endif /* BLK_INTERNAL_H */

include/linux/blkdev.h

@@ -701,6 +701,10 @@ struct request_queue {
 
 	struct work_struct	release_work;
 
+	/* used when QUEUE_FLAG_DISPATCH_ASYNC is set */
+	struct cpumask		dispatch_async_cpus;
+	int __percpu		*last_dispatch_cpu;
+
 #define BLK_MAX_WRITE_HINTS	5
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
@@ -739,6 +743,8 @@ struct request_queue {
 #define QUEUE_FLAG_FORECE_QUIESCE 29 /* force quiesce when cleanup queue */
 /* queue has bee quiesced, used in block layer */
 #define QUEUE_FLAG_QUIESCED_INTERNAL 30
+/* bio will be dispatched asynchronous */
+#define QUEUE_FLAG_DISPATCH_ASYNC 31
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\