Commit 86298d8b authored Sep 11, 2023 by Qi Zheng Committed by Andrew Morton Oct 04, 2023

md/raid5: dynamically allocate the md-raid5 shrinker

In preparation for implementing lockless slab shrink, use new APIs to
dynamically allocate the md-raid5 shrinker, so that it can be freed
asynchronously via RCU. Then it doesn't need to wait for RCU read-side
critical section when releasing the struct r5conf.

Link: https://lkml.kernel.org/r/20230911094444.68966-26-zhengqi.arch@bytedance.com


Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Song Liu <song@kernel.org>
Cc: Abhinav Kumar <quic_abhinavk@quicinc.com>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Carlos Llamas <cmllamas@google.com>
Cc: Chandan Babu R <chandan.babu@oracle.com>
Cc: Chao Yu <chao@kernel.org>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Chuck Lever <cel@kernel.org>
Cc: Coly Li <colyli@suse.de>
Cc: Dai Ngo <Dai.Ngo@oracle.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Airlie <airlied@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Gao Xiang <hsiangkao@linux.alibaba.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Jeffle Xu <jefflexu@linux.alibaba.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Kirill Tkhai <tkhai@ya.ru>
Cc: Marijn Suijten <marijn.suijten@somainline.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Mike Snitzer <snitzer@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nadav Amit <namit@vmware.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Olga Kornievskaia <kolga@netapp.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sean Paul <sean@poorly.run>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: Yue Hu <huyue2@coolpad.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

parent ba3d6aca

drivers/md/raid5.c

+15 −11

Original line number	Diff line number	Diff line
		@@ -7401,7 +7401,7 @@ static void free_conf(struct r5conf *conf)

		log_exit(conf);

		unregister_shrinker(&conf->shrinker);
		shrinker_free(conf->shrinker);
		free_thread_groups(conf);
		shrink_stripes(conf);
		raid5_free_percpu(conf);
		@@ -7449,7 +7449,7 @@ static int raid5_alloc_percpu(struct r5conf *conf)
		static unsigned long raid5_cache_scan(struct shrinker *shrink,
		struct shrink_control *sc)
		{
		struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
		struct r5conf *conf = shrink->private_data;
		unsigned long ret = SHRINK_STOP;

		if (mutex_trylock(&conf->cache_size_mutex)) {
		@@ -7470,7 +7470,7 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink,
		static unsigned long raid5_cache_count(struct shrinker *shrink,
		struct shrink_control *sc)
		{
		struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
		struct r5conf *conf = shrink->private_data;

		if (conf->max_nr_stripes < conf->min_nr_stripes)
		/* unlikely, but not impossible */
		@@ -7705,18 +7705,22 @@ static struct r5conf setup_conf(struct mddev mddev)
		* it reduces the queue depth and so can hurt throughput.
		* So set it rather large, scaled by number of devices.
		*/
		conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
		conf->shrinker.scan_objects = raid5_cache_scan;
		conf->shrinker.count_objects = raid5_cache_count;
		conf->shrinker.batch = 128;
		conf->shrinker.flags = 0;
		ret = register_shrinker(&conf->shrinker, "md-raid5:%s", mdname(mddev));
		if (ret) {
		pr_warn("md/raid:%s: couldn't register shrinker.\n",
		conf->shrinker = shrinker_alloc(0, "md-raid5:%s", mdname(mddev));
		if (!conf->shrinker) {
		ret = -ENOMEM;
		pr_warn("md/raid:%s: couldn't allocate shrinker.\n",
		mdname(mddev));
		goto abort;
		}

		conf->shrinker->seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
		conf->shrinker->scan_objects = raid5_cache_scan;
		conf->shrinker->count_objects = raid5_cache_count;
		conf->shrinker->batch = 128;
		conf->shrinker->private_data = conf;

		shrinker_register(conf->shrinker);

		sprintf(pers_name, "raid%d", mddev->new_level);
		rcu_assign_pointer(conf->thread,
		md_register_thread(raid5d, mddev, pers_name));

drivers/md/raid5.h

+1 −1

Original line number	Diff line number	Diff line
		@@ -670,7 +670,7 @@ struct r5conf {
		wait_queue_head_t wait_for_stripe;
		wait_queue_head_t wait_for_overlap;
		unsigned long cache_state;
		struct shrinker shrinker;
		struct shrinker *shrinker;
		int pool_size; /* number of disks in stripeheads in pool */
		spinlock_t device_lock;
		struct disk_info *disks;