From patchwork Mon Apr 20 22:39:29 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dan Schatzberg X-Patchwork-Id: 11500029 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 17E1F112C for ; Mon, 20 Apr 2020 22:41:33 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E939222202 for ; Mon, 20 Apr 2020 22:41:32 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="L9z7d6El" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726562AbgDTWlc (ORCPT ); Mon, 20 Apr 2020 18:41:32 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42722 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725958AbgDTWlb (ORCPT ); Mon, 20 Apr 2020 18:41:31 -0400 Received: from mail-qv1-xf41.google.com (mail-qv1-xf41.google.com [IPv6:2607:f8b0:4864:20::f41]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 701AFC061A0C; Mon, 20 Apr 2020 15:41:31 -0700 (PDT) Received: by mail-qv1-xf41.google.com with SMTP id p19so5650576qve.0; Mon, 20 Apr 2020 15:41:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=I53GuE/PpryNkjZAMmbvbjvTLp76oWX+vv7/Vav/aVI=; b=L9z7d6ElJQd/6gEEUGAg434Q0L+P99t4FngUseYUNBcQKomHG5udaf7w4S8UU/g9U9 IO3s8UdjtJ99I9jbpGht9XifOB7/ANCNaq8yRr4kbnbH5wR/amOnD6C1Phei1GWu1Plf z4SkSoysYKSbcyXiTsmb4j/gyGzf/ARtz+V2Pkpyow3YujXb9WHP/bGHHZFfX7Tia5sR JuYrU+qN3HErhDx/9qYUqMnuf5GvCIursi4MK9Ypm0hUWLnCw91Dxkb9cGfO3ASHrcv6 sLqteZ/a7uJgVauXLGR16sSVFG7Q78g+etC3CT/o/IvN6SLsXUoGv6IXn9NXeHPPvwFa AiTQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=I53GuE/PpryNkjZAMmbvbjvTLp76oWX+vv7/Vav/aVI=; b=PUgBd0uu9INnjS6Q+f7u+BbPvxki5pE93oW9117xjMWxTXFyPHdLQUQjYcll16bT3R Prgk1VEK99UMvCPhKqJpw3qVvcMlu0KyC/kzBhYx3CpsXmQgR/Z7zJ5fgk4cqFLk+LFx pJh/3RjV6PNW2YVmboe+7/LN2T3x3z3nLrUaXemRTHns60Bbl5RnW2qHsac8H9gtUDMH ZxAm71r9qz+5DEdPNUjwyN19Pbv4/AQyEyZQAOC/Z6Fvc0by1x+oJqlt0qbIrfIhGdrm 22xWjkJbjdtD4dFcTZZ51YNQ8/77O6iKvp+RJepCEB1fp+CrlleQ7wb5BKeV23qnSD6V C2Sw== X-Gm-Message-State: AGi0Pub3Tyk6ufD/oCfs2wh4weS6rv6fbju2GCKh71XmT7xmLf3+C6HD JAzEbwCewTCp9sj5vWzeDXs= X-Google-Smtp-Source: APiQypJNjAIXQw726NC6gLPclR5KgakscQJxzfArhJX+NkNQ9hVK+Q2rmE3PSI6OTj1ce/oUA+8dYQ== X-Received: by 2002:a0c:ed26:: with SMTP id u6mr17005587qvq.220.1587422490480; Mon, 20 Apr 2020 15:41:30 -0700 (PDT) Received: from dschatzberg-fedora-PC0Y6AEN.thefacebook.com ([2620:10d:c091:480::1:b0d9]) by smtp.gmail.com with ESMTPSA id j90sm511052qte.20.2020.04.20.15.41.28 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 20 Apr 2020 15:41:29 -0700 (PDT) From: Dan Schatzberg Cc: Dan Schatzberg , Jens Axboe , Alexander Viro , Jan Kara , Amir Goldstein , Tejun Heo , Li Zefan , Johannes Weiner , Michal Hocko , Vladimir Davydov , Andrew Morton , Hugh Dickins , Roman Gushchin , Shakeel Butt , Chris Down , Yang Shi , Ingo Molnar , "Peter Zijlstra (Intel)" , Mathieu Desnoyers , Thomas Gleixner , Andrea Arcangeli , linux-block@vger.kernel.org (open list:BLOCK LAYER), linux-kernel@vger.kernel.org (open list), linux-fsdevel@vger.kernel.org (open list:FILESYSTEMS (VFS and infrastructure)), cgroups@vger.kernel.org (open list:CONTROL GROUP (CGROUP)), linux-mm@kvack.org (open list:CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)) Subject: [PATCH 1/4] loop: Use worker per cgroup instead of kworker Date: Mon, 20 Apr 2020 18:39:29 -0400 Message-Id: <20200420223936.6773-2-schatzberg.dan@gmail.com> X-Mailer: git-send-email 2.21.1 In-Reply-To: <20200420223936.6773-1-schatzberg.dan@gmail.com> References: <20200420223936.6773-1-schatzberg.dan@gmail.com> MIME-Version: 1.0 To: unlisted-recipients:; (no To-header on input) Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Existing uses of loop device may have multiple cgroups reading/writing to the same device. Simply charging resources for I/O to the backing file could result in priority inversion where one cgroup gets synchronously blocked, holding up all other I/O to the loop device. In order to avoid this priority inversion, we use a single workqueue where each work item is a "struct loop_worker" which contains a queue of struct loop_cmds to issue. The loop device maintains a tree mapping blk css_id -> loop_worker. This allows each cgroup to independently make forward progress issuing I/O to the backing file. There is also a single queue for I/O associated with the rootcg which can be used in cases of extreme memory shortage where we cannot allocate a loop_worker. The locking for the tree and queues is fairly heavy handed - we acquire the per-loop-device spinlock any time either is accessed. The existing implementation serializes all I/O through a single thread anyways, so I don't believe this is any worse. Signed-off-by: Dan Schatzberg --- drivers/block/loop.c | 207 ++++++++++++++++++++++++++++++++++++------- drivers/block/loop.h | 11 ++- 2 files changed, 180 insertions(+), 38 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index da693e6a834e..3a109975d2df 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -70,7 +70,6 @@ #include #include #include -#include #include #include #include @@ -83,6 +82,8 @@ #include +#define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) + static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); @@ -778,12 +779,18 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) { ssize_t ret; char *p = NULL; + struct file *filp = NULL; spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) - p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1); + filp = get_file(lo->lo_backing_file); spin_unlock_irq(&lo->lo_lock); + if (filp) { + p = file_path(filp, buf, PAGE_SIZE - 1); + fput(filp); + } + if (IS_ERR_OR_NULL(p)) ret = PTR_ERR(p); else { @@ -911,27 +918,83 @@ static void loop_config_discard(struct loop_device *lo) blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } -static void loop_unprepare_queue(struct loop_device *lo) -{ - kthread_flush_worker(&lo->worker); - kthread_stop(lo->worker_task); -} +struct loop_worker { + struct rb_node rb_node; + struct work_struct work; + struct list_head cmd_list; + struct list_head idle_list; + struct loop_device *lo; + struct cgroup_subsys_state *css; + unsigned long last_ran_at; +}; -static int loop_kthread_worker_fn(void *worker_ptr) -{ - current->flags |= PF_LESS_THROTTLE | PF_MEMALLOC_NOIO; - return kthread_worker_fn(worker_ptr); -} +static void loop_workfn(struct work_struct *work); +static void loop_rootcg_workfn(struct work_struct *work); +static void loop_free_idle_workers(struct timer_list *timer); -static int loop_prepare_queue(struct loop_device *lo) +static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd) { - kthread_init_worker(&lo->worker); - lo->worker_task = kthread_run(loop_kthread_worker_fn, - &lo->worker, "loop%d", lo->lo_number); - if (IS_ERR(lo->worker_task)) - return -ENOMEM; - set_user_nice(lo->worker_task, MIN_NICE); - return 0; + struct rb_node **node = &(lo->worker_tree.rb_node), *parent = NULL; + struct loop_worker *cur_worker, *worker = NULL; + struct work_struct *work; + struct list_head *cmd_list; + + spin_lock_irq(&lo->lo_lock); + + if (!cmd->css) + goto queue_work; + + node = &lo->worker_tree.rb_node; + + while (*node) { + parent = *node; + cur_worker = container_of(*node, struct loop_worker, rb_node); + if (cur_worker->css == cmd->css) { + worker = cur_worker; + break; + } else if ((long)cur_worker->css < (long)cmd->css) { + node = &(*node)->rb_left; + } else { + node = &(*node)->rb_right; + } + } + if (worker) + goto queue_work; + + worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT | __GFP_NOWARN); + /* + * In the event we cannot allocate a worker, just queue on the + * rootcg worker + */ + if (!worker) + goto queue_work; + + worker->css = cmd->css; + css_get(worker->css); + INIT_WORK(&worker->work, loop_workfn); + INIT_LIST_HEAD(&worker->cmd_list); + INIT_LIST_HEAD(&worker->idle_list); + worker->lo = lo; + rb_link_node(&worker->rb_node, parent, node); + rb_insert_color(&worker->rb_node, &lo->worker_tree); +queue_work: + if (worker) { + /* + * We need to remove from the idle list here while + * holding the lock so that the idle timer doesn't + * free the worker + */ + if (!list_empty(&worker->idle_list)) + list_del_init(&worker->idle_list); + work = &worker->work; + cmd_list = &worker->cmd_list; + } else { + work = &lo->rootcg_work; + cmd_list = &lo->rootcg_cmd_list; + } + list_add_tail(&cmd->list_entry, cmd_list); + queue_work(lo->workqueue, work); + spin_unlock_irq(&lo->lo_lock); } static void loop_update_rotational(struct loop_device *lo) @@ -1007,14 +1070,25 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, size = get_loop_size(lo, file); if ((loff_t)(sector_t)size != size) goto out_unlock; - error = loop_prepare_queue(lo); - if (error) + lo->workqueue = alloc_workqueue("loop%d", + WQ_UNBOUND | WQ_FREEZABLE | + WQ_MEM_RECLAIM, + lo->lo_number); + if (!lo->workqueue) { + error = -ENOMEM; goto out_unlock; + } error = 0; set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0); + INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); + INIT_LIST_HEAD(&lo->rootcg_cmd_list); + INIT_LIST_HEAD(&lo->idle_worker_list); + lo->worker_tree = RB_ROOT; + timer_setup(&lo->timer, loop_free_idle_workers, + TIMER_DEFERRABLE); lo->use_dio = false; lo->lo_device = bdev; lo->lo_flags = lo_flags; @@ -1123,6 +1197,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) int err = 0; bool partscan = false; int lo_number; + struct loop_worker *pos, *worker; mutex_lock(&loop_ctl_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { @@ -1140,8 +1215,17 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); + destroy_workqueue(lo->workqueue); lo->lo_backing_file = NULL; + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->css); + kfree(worker); + } spin_unlock_irq(&lo->lo_lock); + del_timer_sync(&lo->timer); loop_release_xfer(lo); lo->transfer = NULL; @@ -1176,7 +1260,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; lo_number = lo->lo_number; - loop_unprepare_queue(lo); out_unlock: mutex_unlock(&loop_ctl_mutex); if (partscan) { @@ -1954,7 +2037,7 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, } else #endif cmd->css = NULL; - kthread_queue_work(&lo->worker, &cmd->work); + loop_queue_work(lo, cmd); return BLK_STS_OK; } @@ -1983,26 +2066,82 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } } -static void loop_queue_work(struct kthread_work *work) +static void loop_set_timer(struct loop_device *lo) +{ + timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); +} + +static void loop_process_work(struct loop_worker *worker, + struct list_head *cmd_list, struct loop_device *lo) { - struct loop_cmd *cmd = - container_of(work, struct loop_cmd, work); + int orig_flags = current->flags; + struct loop_cmd *cmd; - loop_handle_cmd(cmd); + current->flags |= PF_LESS_THROTTLE | PF_MEMALLOC_NOIO; + spin_lock_irq(&lo->lo_lock); + while (!list_empty(cmd_list)) { + cmd = container_of( + cmd_list->next, struct loop_cmd, list_entry); + list_del(cmd_list->next); + spin_unlock_irq(&lo->lo_lock); + + loop_handle_cmd(cmd); + cond_resched(); + + spin_lock_irq(&lo->lo_lock); + } + + /* + * We only add to the idle list if there are no pending cmds + * *and* the worker will not run again which ensures that it + * is safe to free any worker on the idle list + */ + if (worker && !work_pending(&worker->work)) { + worker->last_ran_at = jiffies; + list_add_tail(&worker->idle_list, &lo->idle_worker_list); + loop_set_timer(lo); + } + spin_unlock_irq(&lo->lo_lock); + current->flags = orig_flags; } -static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq, - unsigned int hctx_idx, unsigned int numa_node) +static void loop_workfn(struct work_struct *work) { - struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); + struct loop_worker *worker = + container_of(work, struct loop_worker, work); + loop_process_work(worker, &worker->cmd_list, worker->lo); +} - kthread_init_work(&cmd->work, loop_queue_work); - return 0; +static void loop_rootcg_workfn(struct work_struct *work) +{ + struct loop_device *lo = + container_of(work, struct loop_device, rootcg_work); + loop_process_work(NULL, &lo->rootcg_cmd_list, lo); +} + +static void loop_free_idle_workers(struct timer_list *timer) +{ + struct loop_device *lo = container_of(timer, struct loop_device, timer); + struct loop_worker *pos, *worker; + + spin_lock_irq(&lo->lo_lock); + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + if (time_is_after_jiffies(worker->last_ran_at + + LOOP_IDLE_WORKER_TIMEOUT)) + break; + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->css); + kfree(worker); + } + if (!list_empty(&lo->idle_worker_list)) + loop_set_timer(lo); + spin_unlock_irq(&lo->lo_lock); } static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, - .init_request = loop_init_request, .complete = lo_complete_rq, }; diff --git a/drivers/block/loop.h b/drivers/block/loop.h index af75a5ee4094..87fd0e372227 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -14,7 +14,6 @@ #include #include #include -#include #include /* Possible states of device */ @@ -54,8 +53,12 @@ struct loop_device { spinlock_t lo_lock; int lo_state; - struct kthread_worker worker; - struct task_struct *worker_task; + struct workqueue_struct *workqueue; + struct work_struct rootcg_work; + struct list_head rootcg_cmd_list; + struct list_head idle_worker_list; + struct rb_root worker_tree; + struct timer_list timer; bool use_dio; bool sysfs_inited; @@ -65,7 +68,7 @@ struct loop_device { }; struct loop_cmd { - struct kthread_work work; + struct list_head list_entry; bool use_aio; /* use AIO interface to handle I/O */ atomic_t ref; /* only for aio */ long ret;