Merge tag 'block-5.14-2021-08-27' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe: - Revert the mq-deadline priority handling, it's causing serious performance regressions. While experimental patches exists to fix this up, it's too late to do so now. Revert it and re-do it properly for 5.15 instead. - Fix a NULL vs IS_ERR() regression in this release (Dan) - Fix a mq-deadline accounting regression in this release (Bart) - Mark cryptoloop as deprecated. It's broken and dm-crypt fully supports it, and it's actively intefering with loop. Plan on removal for 5.16 (Christoph) * tag 'block-5.14-2021-08-27' of git://git.kernel.dk/linux-block: cryptoloop: add a deprecation warning pd: fix a NULL vs IS_ERR() check Revert "block/mq-deadline: Prioritize high-priority requests" mq-deadline: Fix request accounting

Linus Torvalds committed 5 years ago

Commit 64b4fc42 parents 6f18b82 222013f4 files · +21 −45Browse files

Unified · Split

4 files

block/mq-deadline.c +16 −42
drivers/block/Kconfig +2 −2
drivers/block/cryptoloop.c +2 −0
drivers/block/paride/pd.c +1 −1

block/mq-deadline.c+16−42

  */
 static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
 static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
-/*
- * Time after which to dispatch lower priority requests even if higher
- * priority requests are pending.
- */
-static const int aging_expire = 10 * HZ;
 static const int writes_starved = 2;    /* max times reads can starve a write */
 static const int fifo_batch = 16;       /* # of sequential requests treated as one
 				     by the above parameters. For throughput. */
 	int writes_starved;
 	int front_merges;
 	u32 async_depth;
-	int aging_expire;
 	spinlock_t lock;
 	spinlock_t zone_lock;
 /*
  * deadline_dispatch_requests selects the best request according to
- * read/write expire, fifo_batch, etc and with a start time <= @latest.
+ * read/write expire, fifo_batch, etc
  */
 static struct request *__dd_dispatch_request(struct deadline_data *dd,
-					     struct dd_per_prio *per_prio,
+					     struct dd_per_prio *per_prio)
-					     u64 latest_start_ns)
 {
 	struct request *rq, *next_rq;
 	enum dd_data_dir data_dir;
 	if (!list_empty(&per_prio->dispatch)) {
 		rq = list_first_entry(&per_prio->dispatch, struct request,
 				      queuelist);
-		if (rq->start_time_ns > latest_start_ns)
-			return NULL;
 		list_del_init(&rq->queuelist);
 		goto done;
 	}
 	dd->batching = 0;
 dispatch_request:
-	if (rq->start_time_ns > latest_start_ns)
-		return NULL;
 	/*
 	 * rq is the selected appropriate request.
 	 */
 static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
-	const u64 now_ns = ktime_get_ns();
+	struct request *rq;
-	struct request *rq = NULL;
 	enum dd_prio prio;
 	spin_lock(&dd->lock);
-	/*
-	 * Start with dispatching requests whose deadline expired more than
-	 * aging_expire jiffies ago.
-	 */
-	for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) {
-		rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns -
-					   jiffies_to_nsecs(dd->aging_expire));
-		if (rq)
-			goto unlock;
-	}
-	/*
-	 * Next, dispatch requests in priority order. Ignore lower priority
-	 * requests if any higher priority requests are pending.
-	 */
 	for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
-		rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns);
+		rq = __dd_dispatch_request(dd, &dd->per_prio[prio]);
-		if (rq || dd_queued(dd, prio))
+		if (rq)
 			break;
 	}
-unlock:
 	spin_unlock(&dd->lock);
 	return rq;
 	dd->front_merges = 1;
 	dd->last_dir = DD_WRITE;
 	dd->fifo_batch = fifo_batch;
-	dd->aging_expire = aging_expire;
 	spin_lock_init(&dd->lock);
 	spin_lock_init(&dd->zone_lock);
 	prio = ioprio_class_to_prio[ioprio_class];
 	dd_count(dd, inserted, prio);
+	rq->elv.priv[0] = (void *)(uintptr_t)1;
 	if (blk_mq_sched_try_insert_merge(q, rq, &free)) {
 		blk_mq_free_requests(&free);
 	spin_unlock(&dd->lock);
 }
-/*
+/* Callback from inside blk_mq_rq_ctx_init(). */
- * Nothing to do here. This is defined only to ensure that .finish_request
- * method is called upon request completion.
- */
 static void dd_prepare_request(struct request *rq)
 {
+	rq->elv.priv[0] = NULL;
 }
 /*
 	const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
 	struct dd_per_prio *per_prio = &dd->per_prio[prio];
-	dd_count(dd, completed, prio);
+	/*
+	 * The block layer core may call dd_finish_request() without having
+	 * called dd_insert_requests(). Hence only update statistics for
+	 * requests for which dd_insert_requests() has been called. See also
+	 * blk_mq_request_bypass_insert().
+	 */
+	if (rq->elv.priv[0])
+		dd_count(dd, completed, prio);
 	if (blk_queue_is_zoned(q)) {
 		unsigned long flags;
 #define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR))
 SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]);
 SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]);
-SHOW_JIFFIES(deadline_aging_expire_show, dd->aging_expire);
 SHOW_INT(deadline_writes_starved_show, dd->writes_starved);
 SHOW_INT(deadline_front_merges_show, dd->front_merges);
 SHOW_INT(deadline_async_depth_show, dd->front_merges);
 	STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies)
 STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX);
 STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX);
-STORE_JIFFIES(deadline_aging_expire_store, &dd->aging_expire, 0, INT_MAX);
 STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX);
 STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1);
 STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX);
 	DD_ATTR(front_merges),
 	DD_ATTR(async_depth),
 	DD_ATTR(fifo_batch),
-	DD_ATTR(aging_expire),
 	__ATTR_NULL
 };

drivers/block/Kconfig+2−2

@@ -213,7 +213,7 @@ config BLK_DEV_LOOP_MIN_COUNT · 212 unmodified lines
213	dynamically allocated with the /dev/loop-control interface.	213	dynamically allocated with the /dev/loop-control interface.
214		214
215	config BLK_DEV_CRYPTOLOOP	215	config BLK_DEV_CRYPTOLOOP
216	tristate "Cryptoloop Support"	216	tristate "Cryptoloop Support (DEPRECATED)"
217	select CRYPTO	217	select CRYPTO
218	select CRYPTO_CBC	218	select CRYPTO_CBC
219	depends on BLK_DEV_LOOP	219	depends on BLK_DEV_LOOP
@@ -225,7 +225,7 @@ config BLK_DEV_CRYPTOLOOP · 5 unmodified lines
225	WARNING: This device is not safe for journaled file systems like	225	WARNING: This device is not safe for journaled file systems like
226	ext3 or Reiserfs. Please use the Device Mapper crypto module	226	ext3 or Reiserfs. Please use the Device Mapper crypto module
227	instead, which can be configured to be on-disk compatible with the	227	instead, which can be configured to be on-disk compatible with the
228	cryptoloop device.	228	cryptoloop device. cryptoloop support will be removed in Linux 5.16.
229		229
230	source "drivers/block/drbd/Kconfig"	230	source "drivers/block/drbd/Kconfig"
231		231

drivers/block/cryptoloop.c+2−0

@@ -189,6 +189,8 @@ init_cryptoloop(void) · 188 unmodified lines
189		189
190	if (rc)	190	if (rc)
191	printk(KERN_ERR "cryptoloop: loop_register_transfer failed\n");	191	printk(KERN_ERR "cryptoloop: loop_register_transfer failed\n");
		192	else
		193	pr_warn("the cryptoloop driver has been deprecated and will be removed in in Linux 5.16\n");
192	return rc;	194	return rc;
193	}	195	}
194		196

drivers/block/paride/pd.c+1−1

@@ -892,7 +892,7 @@ static void pd_probe_drive(struct pd_unit *disk) · 891 unmodified lines
892	return;	892	return;
893		893
894	p = blk_mq_alloc_disk(&disk->tag_set, disk);	894	p = blk_mq_alloc_disk(&disk->tag_set, disk);
895	if (!p) {	895	if (IS_ERR(p)) {
896	blk_mq_free_tag_set(&disk->tag_set);	896	blk_mq_free_tag_set(&disk->tag_set);
897	return;	897	return;
898	}	898	}