Merge tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe: "Good amount of cleanups and tech debt removals in here, and as a result, the diffstat shows a nice net reduction in code. - Softirq completion cleanups (Christoph) - Stop using ->queuedata (Christoph) - Cleanup bd claiming (Christoph) - Use check_events, moving away from the legacy media change (Christoph) - Use inode i_blkbits consistently (Christoph) - Remove old unused writeback congestion bits (Christoph) - Cleanup/unify submission path (Christoph) - Use bio_uninit consistently, instead of bio_disassociate_blkg (Christoph) - sbitmap cleared bits handling (John) - Request merging blktrace event addition (Jan) - sysfs add/remove race fixes (Luis) - blk-mq tag fixes/optimizations (Ming) - Duplicate words in comments (Randy) - Flush deferral cleanup (Yufen) - IO context locking/retry fixes (John) - struct_size() usage (Gustavo) - blk-iocost fixes (Chengming) - blk-cgroup IO stats fixes (Boris) - Various little fixes" * tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block: (135 commits) block: blk-timeout: delete duplicated word block: blk-mq-sched: delete duplicated word block: blk-mq: delete duplicated word block: genhd: delete duplicated words block: elevator: delete duplicated word and fix typos block: bio: delete duplicated words block: bfq-iosched: fix duplicated word iocost_monitor: start from the oldest usage index iocost: Fix check condition of iocg abs_vdebt block: Remove callback typedefs for blk_mq_ops block: Use non _rcu version of list functions for tag_set_list blk-cgroup: show global disk stats in root cgroup io.stat blk-cgroup: make iostat functions visible to stat printing block: improve discard bio alignment in __blkdev_issue_discard() block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers block: defer flush request no matter whether we have elevator block: make blk_timeout_init() static block: remove retry loop in ioc_release_fn() block: remove unnecessary ioc nested locking block: integrate bd_start_claiming into __blkdev_get ...
2020-08-03 11:57:03 -07:00
parent 99f6cf61f1 d958e343bd
commit 382625d0d4
157 changed files with 1839 additions and 2648 deletions
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -281,7 +281,7 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 #define INIT_BW		(100 << (20 - PAGE_SHIFT))

 static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
-		   int blkcg_id, gfp_t gfp)
+		   gfp_t gfp)
 {
 	int i, err;

@@ -308,15 +308,9 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	wb->dirty_sleep = jiffies;

-	wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp);
-	if (!wb->congested) {
-		err = -ENOMEM;
-		goto out_put_bdi;
-	}
-
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
-		goto out_put_cong;
+		goto out_put_bdi;

 	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&wb->stat[i], 0, gfp);
@@ -330,8 +324,6 @@ out_destroy_stat:
 	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
-out_put_cong:
-	wb_congested_put(wb->congested);
 out_put_bdi:
 	if (wb != &bdi->wb)
 		bdi_put(bdi);
@@ -374,7 +366,6 @@ static void wb_exit(struct bdi_writeback *wb)
 		percpu_counter_destroy(&wb->stat[i]);

 	fprop_local_destroy_percpu(&wb->completions);
-	wb_congested_put(wb->congested);
 	if (wb != &wb->bdi->wb)
 		bdi_put(wb->bdi);
 }
@@ -384,99 +375,12 @@ static void wb_exit(struct bdi_writeback *wb)
 #include <linux/memcontrol.h>

 /*
- * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree,
- * blkcg->cgwb_list, and memcg->cgwb_list.  bdi->cgwb_tree is also RCU
- * protected.
+ * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list.
+ * bdi->cgwb_tree is also RCU protected.
 */
 static DEFINE_SPINLOCK(cgwb_lock);
 static struct workqueue_struct *cgwb_release_wq;

-/**
- * wb_congested_get_create - get or create a wb_congested
- * @bdi: associated bdi
- * @blkcg_id: ID of the associated blkcg
- * @gfp: allocation mask
- *
- * Look up the wb_congested for @blkcg_id on @bdi.  If missing, create one.
- * The returned wb_congested has its reference count incremented.  Returns
- * NULL on failure.
- */
-struct bdi_writeback_congested *
-wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
-{
-	struct bdi_writeback_congested *new_congested = NULL, *congested;
-	struct rb_node **node, *parent;
-	unsigned long flags;
-retry:
-	spin_lock_irqsave(&cgwb_lock, flags);
-
-	node = &bdi->cgwb_congested_tree.rb_node;
-	parent = NULL;
-
-	while (*node != NULL) {
-		parent = *node;
-		congested = rb_entry(parent, struct bdi_writeback_congested,
-				     rb_node);
-		if (congested->blkcg_id < blkcg_id)
-			node = &parent->rb_left;
-		else if (congested->blkcg_id > blkcg_id)
-			node = &parent->rb_right;
-		else
-			goto found;
-	}
-
-	if (new_congested) {
-		/* !found and storage for new one already allocated, insert */
-		congested = new_congested;
-		rb_link_node(&congested->rb_node, parent, node);
-		rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree);
-		spin_unlock_irqrestore(&cgwb_lock, flags);
-		return congested;
-	}
-
-	spin_unlock_irqrestore(&cgwb_lock, flags);
-
-	/* allocate storage for new one and retry */
-	new_congested = kzalloc(sizeof(*new_congested), gfp);
-	if (!new_congested)
-		return NULL;
-
-	refcount_set(&new_congested->refcnt, 1);
-	new_congested->__bdi = bdi;
-	new_congested->blkcg_id = blkcg_id;
-	goto retry;
-
-found:
-	refcount_inc(&congested->refcnt);
-	spin_unlock_irqrestore(&cgwb_lock, flags);
-	kfree(new_congested);
-	return congested;
-}
-
-/**
- * wb_congested_put - put a wb_congested
- * @congested: wb_congested to put
- *
- * Put @congested and destroy it if the refcnt reaches zero.
- */
-void wb_congested_put(struct bdi_writeback_congested *congested)
-{
-	unsigned long flags;
-
-	if (!refcount_dec_and_lock_irqsave(&congested->refcnt, &cgwb_lock, &flags))
-		return;
-
-	/* bdi might already have been destroyed leaving @congested unlinked */
-	if (congested->__bdi) {
-		rb_erase(&congested->rb_node,
-			 &congested->__bdi->cgwb_congested_tree);
-		congested->__bdi = NULL;
-	}
-
-	spin_unlock_irqrestore(&cgwb_lock, flags);
-	kfree(congested);
-}
-
 static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
@@ -558,7 +462,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 		goto out_put;
 	}

-	ret = wb_init(wb, bdi, blkcg_css->id, gfp);
+	ret = wb_init(wb, bdi, gfp);
 	if (ret)
 		goto err_free;

@@ -696,11 +600,10 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	int ret;

 	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
-	bdi->cgwb_congested_tree = RB_ROOT;
 	mutex_init(&bdi->cgwb_release_mutex);
 	init_rwsem(&bdi->wb_switch_rwsem);

-	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
+	ret = wb_init(&bdi->wb, bdi, GFP_KERNEL);
 	if (!ret) {
 		bdi->wb.memcg_css = &root_mem_cgroup->css;
 		bdi->wb.blkcg_css = blkcg_root_css;
@@ -769,21 +672,6 @@ void wb_blkcg_offline(struct blkcg *blkcg)
 	spin_unlock_irq(&cgwb_lock);
 }

-static void cgwb_bdi_exit(struct backing_dev_info *bdi)
-{
-	struct rb_node *rbn;
-
-	spin_lock_irq(&cgwb_lock);
-	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
-		struct bdi_writeback_congested *congested =
-			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
-
-		rb_erase(rbn, &bdi->cgwb_congested_tree);
-		congested->__bdi = NULL;	/* mark @congested unlinked */
-	}
-	spin_unlock_irq(&cgwb_lock);
-}
-
 static void cgwb_bdi_register(struct backing_dev_info *bdi)
 {
 	spin_lock_irq(&cgwb_lock);
@@ -810,29 +698,11 @@ subsys_initcall(cgwb_init);

 static int cgwb_bdi_init(struct backing_dev_info *bdi)
 {
-	int err;
-
-	bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL);
-	if (!bdi->wb_congested)
-		return -ENOMEM;
-
-	refcount_set(&bdi->wb_congested->refcnt, 1);
-
-	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
-	if (err) {
-		wb_congested_put(bdi->wb_congested);
-		return err;
-	}
-	return 0;
+	return wb_init(&bdi->wb, bdi, GFP_KERNEL);
 }

 static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { }

-static void cgwb_bdi_exit(struct backing_dev_info *bdi)
-{
-	wb_congested_put(bdi->wb_congested);
-}
-
 static void cgwb_bdi_register(struct backing_dev_info *bdi)
 {
 	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
@@ -1023,7 +893,6 @@ static void release_bdi(struct kref *ref)
 		bdi_unregister(bdi);
 	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
-	cgwb_bdi_exit(bdi);
 	kfree(bdi);
 }

@@ -1047,29 +916,29 @@ static wait_queue_head_t congestion_wqh[2] = {
 	};
 static atomic_t nr_wb_congested[2];

-void clear_wb_congested(struct bdi_writeback_congested *congested, int sync)
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 	enum wb_congested_state bit;

 	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (test_and_clear_bit(bit, &congested->state))
+	if (test_and_clear_bit(bit, &bdi->wb.congested))
 		atomic_dec(&nr_wb_congested[sync]);
 	smp_mb__after_atomic();
 	if (waitqueue_active(wqh))
 		wake_up(wqh);
 }
-EXPORT_SYMBOL(clear_wb_congested);
+EXPORT_SYMBOL(clear_bdi_congested);

-void set_wb_congested(struct bdi_writeback_congested *congested, int sync)
+void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum wb_congested_state bit;

 	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (!test_and_set_bit(bit, &congested->state))
+	if (!test_and_set_bit(bit, &bdi->wb.congested))
 		atomic_inc(&nr_wb_congested[sync]);
 }
-EXPORT_SYMBOL(set_wb_congested);
+EXPORT_SYMBOL(set_bdi_congested);

 /**
 * congestion_wait - wait for a backing_dev to become uncongested
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -277,6 +277,23 @@ static inline void count_swpout_vm_event(struct page *page)
 	count_vm_events(PSWPOUT, hpage_nr_pages(page));
 }

+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *css;
+
+	if (!page->mem_cgroup)
+		return;
+
+	rcu_read_lock();
+	css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
+	bio_associate_blkg_from_css(bio, css);
+	rcu_read_unlock();
+}
+#else
+#define bio_associate_blkg_from_page(bio, page)		do { } while (0)
+#endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
+
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		bio_end_io_t end_write_func)
 {
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2929,7 +2929,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 		 * write only restriction.  Hence zoned block devices are not
 		 * suitable for swapping.  Disallow them here.
 		 */
-		if (blk_queue_is_zoned(p->bdev->bd_queue))
+		if (blk_queue_is_zoned(p->bdev->bd_disk->queue))
 			return -EINVAL;
 		p->flags |= SWP_BLKDEV;
 	} else if (S_ISREG(inode->i_mode)) {