1 files changed, 210 insertions, 40 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 76e12f3482a9..452c7437e1f0 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -71,7 +71,6 @@
 #include <linux/writeback.h>
 #include <linux/completion.h>
 #include <linux/highmem.h>
-#include <linux/kthread.h>
 #include <linux/splice.h>
 #include <linux/sysfs.h>
 #include <linux/miscdevice.h>
@@ -79,11 +78,14 @@
 #include <linux/uio.h>
 #include <linux/ioprio.h>
 #include <linux/blk-cgroup.h>
+#include <linux/sched/mm.h>
 
 #include "loop.h"
 
 #include <linux/uaccess.h>
 
+#define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ)
+
 static DEFINE_IDR(loop_index_idr);
 static DEFINE_MUTEX(loop_ctl_mutex);
 
@@ -515,8 +517,6 @@ static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
 {
 	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
 
-	if (cmd->css)
-		css_put(cmd->css);
 	cmd->ret = ret;
 	lo_rw_aio_do_completion(cmd);
 }
@@ -577,8 +577,6 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	cmd->iocb.ki_complete = lo_rw_aio_complete;
 	cmd->iocb.ki_flags = IOCB_DIRECT;
 	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
-	if (cmd->css)
-		kthread_associate_blkcg(cmd->css);
 
 	if (rw == WRITE)
 		ret = call_write_iter(file, &cmd->iocb, &iter);
@@ -586,7 +584,6 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 		ret = call_read_iter(file, &cmd->iocb, &iter);
 
 	lo_rw_aio_do_completion(cmd);
-	kthread_associate_blkcg(NULL);
 
 	if (ret != -EIOCBQUEUED)
 		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
@@ -921,27 +918,100 @@ static void loop_config_discard(struct loop_device *lo)
 	q->limits.discard_alignment = 0;
 }
 
-static void loop_unprepare_queue(struct loop_device *lo)
+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 *blkcg_css;
+	unsigned long last_ran_at;
+};
+
+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);
+
+#ifdef CONFIG_BLK_CGROUP
+static inline int queue_on_root_worker(struct cgroup_subsys_state *css)
 {
-	kthread_flush_worker(&lo->worker);
-	kthread_stop(lo->worker_task);
+	return !css || css == blkcg_root_css;
 }
-
-static int loop_kthread_worker_fn(void *worker_ptr)
+#else
+static inline int queue_on_root_worker(struct cgroup_subsys_state *css)
 {
-	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
-	return kthread_worker_fn(worker_ptr);
+	return !css;
 }
+#endif
 
-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_work_lock);
+
+	if (queue_on_root_worker(cmd->blkcg_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->blkcg_css == cmd->blkcg_css) {
+			worker = cur_worker;
+			break;
+		} else if ((long)cur_worker->blkcg_css < (long)cmd->blkcg_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 and issue the I/O as the rootcg
+	 */
+	if (!worker) {
+		cmd->blkcg_css = NULL;
+		if (cmd->memcg_css)
+			css_put(cmd->memcg_css);
+		cmd->memcg_css = NULL;
+		goto queue_work;
+	}
+
+	worker->blkcg_css = cmd->blkcg_css;
+	css_get(worker->blkcg_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_work_lock);
 }
 
 static void loop_update_rotational(struct loop_device *lo)
@@ -1127,12 +1197,23 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	    !file->f_op->write_iter)
 		lo->lo_flags |= LO_FLAGS_READ_ONLY;
 
-	error = loop_prepare_queue(lo);
-	if (error)
+	lo->workqueue = alloc_workqueue("loop%d",
+					WQ_UNBOUND | WQ_FREEZABLE,
+					0,
+					lo->lo_number);
+	if (!lo->workqueue) {
+		error = -ENOMEM;
 		goto out_unlock;
+	}
 
 	set_disk_ro(lo->lo_disk, (lo->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 = lo->lo_flags & LO_FLAGS_DIRECT_IO;
 	lo->lo_device = bdev;
 	lo->lo_backing_file = file;
@@ -1200,6 +1281,7 @@ 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(&lo->lo_mutex);
 	if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) {
@@ -1219,6 +1301,18 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	/* freeze request queue during the transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
+	destroy_workqueue(lo->workqueue);
+	spin_lock_irq(&lo->lo_work_lock);
+	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->blkcg_css);
+		kfree(worker);
+	}
+	spin_unlock_irq(&lo->lo_work_lock);
+	del_timer_sync(&lo->timer);
+
 	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
@@ -1255,7 +1349,6 @@ 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(&lo->lo_mutex);
 	if (partscan) {
@@ -2008,14 +2101,19 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	}
 
 	/* always use the first bio's css */
+	cmd->blkcg_css = NULL;
+	cmd->memcg_css = NULL;
 #ifdef CONFIG_BLK_CGROUP
-	if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) {
-		cmd->css = &bio_blkcg(rq->bio)->css;
-		css_get(cmd->css);
-	} else
+	if (rq->bio && rq->bio->bi_blkg) {
+		cmd->blkcg_css = &bio_blkcg(rq->bio)->css;
+#ifdef CONFIG_MEMCG
+		cmd->memcg_css =
+			cgroup_get_e_css(cmd->blkcg_css->cgroup,
+					&memory_cgrp_subsys);
+#endif
+	}
 #endif
-		cmd->css = NULL;
-	kthread_queue_work(&lo->worker, &cmd->work);
+	loop_queue_work(lo, cmd);
 
 	return BLK_STS_OK;
 }
@@ -2026,13 +2124,28 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	const bool write = op_is_write(req_op(rq));
 	struct loop_device *lo = rq->q->queuedata;
 	int ret = 0;
+	struct mem_cgroup *old_memcg = NULL;
 
 	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
 		ret = -EIO;
 		goto failed;
 	}
 
+	if (cmd->blkcg_css)
+		kthread_associate_blkcg(cmd->blkcg_css);
+	if (cmd->memcg_css)
+		old_memcg = set_active_memcg(
+			mem_cgroup_from_css(cmd->memcg_css));
+
 	ret = do_req_filebacked(lo, rq);
+
+	if (cmd->blkcg_css)
+		kthread_associate_blkcg(NULL);
+
+	if (cmd->memcg_css) {
+		set_active_memcg(old_memcg);
+		css_put(cmd->memcg_css);
+	}
  failed:
 	/* complete non-aio request */
 	if (!cmd->use_aio || ret) {
@@ -2045,26 +2158,82 @@ 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)
 {
-	struct loop_cmd *cmd =
-		container_of(work, struct loop_cmd, work);
+	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)
+{
+	int orig_flags = current->flags;
+	struct loop_cmd *cmd;
 
-	loop_handle_cmd(cmd);
+	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
+	spin_lock_irq(&lo->lo_work_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_work_lock);
+
+		loop_handle_cmd(cmd);
+		cond_resched();
+
+		spin_lock_irq(&lo->lo_work_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_work_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_work_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->blkcg_css);
+		kfree(worker);
+	}
+	if (!list_empty(&lo->idle_worker_list))
+		loop_set_timer(lo);
+	spin_unlock_irq(&lo->lo_work_lock);
 }
 
 static const struct blk_mq_ops loop_mq_ops = {
 	.queue_rq       = loop_queue_rq,
-	.init_request	= loop_init_request,
 	.complete	= lo_complete_rq,
 };
 
@@ -2153,6 +2322,7 @@ static int loop_add(struct loop_device **l, int i)
 	mutex_init(&lo->lo_mutex);
 	lo->lo_number		= i;
 	spin_lock_init(&lo->lo_lock);
+	spin_lock_init(&lo->lo_work_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;
 	disk->fops		= &lo_fops;