Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Sender: Tejun Heo <htejun@gmail.com>
From:   Tejun Heo <tj@kernel.org>
To:     axboe@kernel.dk, josef@toxicpanda.com, hch@lst.de
Cc:     linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
        Tejun Heo <tj@kernel.org>
Subject: [PATCH 4/4] blk-iolatency: Make initialization lazy
Date:   Tue, 10 Jan 2023 12:27:14 -1000
Message-Id: <20230110222714.552241-5-tj@kernel.org>
In-Reply-To: <20230110222714.552241-1-tj@kernel.org>
References: <20230110222714.552241-1-tj@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Other rq_qos policies such as wbt and iocost are lazy-initialized when they
are configured for the first time for the device but iolatency is
initialized unconditionally from blkcg_init_disk() during gendisk init. Lazy
init is beneficial because rq_qos policies add runtime overhead when
initialized as every IO has to walk all registered rq_qos callbacks.

This patch switches iolatency to lazy initialization too so that it only
registered its rq_qos policy when it is first configured.

Note that there is a known race condition between blkcg config file writes
and del_gendisk() and this patch makes iolatency susceptible to it by
exposing the init path to race against the deletion path. However, that
problem already exists in iocost and is being worked on.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Josef Bacik <josef@toxicpanda.com>
---
 block/blk-cgroup.c    |  8 --------
 block/blk-iolatency.c | 29 ++++++++++++++++++++++++++++-
 block/blk.h           |  6 ------
 3 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 18fbdea1f756..54e3ab68a9ac 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -33,7 +33,6 @@
 #include "blk-cgroup.h"
 #include "blk-ioprio.h"
 #include "blk-throttle.h"
-#include "blk-rq-qos.h"
 
 /*
  * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
@@ -1324,14 +1323,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	if (ret)
 		goto err_ioprio_exit;
 
-	ret = blk_iolatency_init(disk);
-	if (ret)
-		goto err_throtl_exit;
-
 	return 0;
 
-err_throtl_exit:
-	blk_throtl_exit(disk);
 err_ioprio_exit:
 	blk_ioprio_exit(disk);
 err_destroy_all:
@@ -1347,7 +1340,6 @@ int blkcg_init_disk(struct gendisk *disk)
 void blkcg_exit_disk(struct gendisk *disk)
 {
 	blkg_destroy_all(disk);
-	rq_qos_exit(disk->queue);
 	blk_throtl_exit(disk);
 }
 
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 3601345808d2..3484393dbc4a 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -755,7 +755,7 @@ static void blkiolatency_enable_work_fn(struct work_struct *work)
 	}
 }
 
-int blk_iolatency_init(struct gendisk *disk)
+static int blk_iolatency_init(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	struct blk_iolatency *blkiolat;
@@ -830,6 +830,29 @@ static void iolatency_clear_scaling(struct blkcg_gq *blkg)
 	}
 }
 
+static int blk_iolatency_try_init(struct blkg_conf_ctx *ctx)
+{
+	static DEFINE_MUTEX(init_mutex);
+	int ret;
+
+	ret = blkg_conf_open_bdev(ctx);
+	if (ret)
+		return ret;
+
+	/*
+	 * blk_iolatency_init() may fail after rq_qos_add() succeeds which can
+	 * confuse iolat_rq_qos() test. Make the test and init atomic.
+	 */
+	mutex_lock(&init_mutex);
+
+	if (!iolat_rq_qos(ctx->bdev->bd_queue))
+		ret = blk_iolatency_init(ctx->bdev->bd_disk);
+
+	mutex_unlock(&init_mutex);
+
+	return ret;
+}
+
 static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
 			     size_t nbytes, loff_t off)
 {
@@ -844,6 +867,10 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
 
 	blkg_conf_init(&ctx, buf);
 
+	ret = blk_iolatency_try_init(&ctx);
+	if (ret)
+		goto out;
+
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, &ctx);
 	if (ret)
 		goto out;
diff --git a/block/blk.h b/block/blk.h
index 4c3b3325219a..78f1706cddca 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -392,12 +392,6 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 	return bio;
 }
 
-#ifdef CONFIG_BLK_CGROUP_IOLATENCY
-int blk_iolatency_init(struct gendisk *disk);
-#else
-static inline int blk_iolatency_init(struct gendisk *disk) { return 0; };
-#endif
-
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
 void disk_clear_zone_settings(struct gendisk *disk);
-- 
2.39.0