1 files changed, 280 insertions, 122 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 0ecc897b225c..619a79b51068 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -95,9 +95,6 @@ static void __blkg_release(struct rcu_head *rcu)
 	css_put(&blkg->blkcg->css);
 	if (blkg->parent)
 		blkg_put(blkg->parent);
-
-	wb_congested_put(blkg->wb_congested);
-
 	blkg_free(blkg);
 }
 
@@ -227,7 +224,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 				    struct blkcg_gq *new_blkg)
 {
 	struct blkcg_gq *blkg;
-	struct bdi_writeback_congested *wb_congested;
 	int i, ret;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
@@ -245,31 +241,22 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 		goto err_free_blkg;
 	}
 
-	wb_congested = wb_congested_get_create(q->backing_dev_info,
-					       blkcg->css.id,
-					       GFP_NOWAIT | __GFP_NOWARN);
-	if (!wb_congested) {
-		ret = -ENOMEM;
-		goto err_put_css;
-	}
-
 	/* allocate */
 	if (!new_blkg) {
 		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
 		if (unlikely(!new_blkg)) {
 			ret = -ENOMEM;
-			goto err_put_congested;
+			goto err_put_css;
 		}
 	}
 	blkg = new_blkg;
-	blkg->wb_congested = wb_congested;
 
 	/* link parent */
 	if (blkcg_parent(blkcg)) {
 		blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
 		if (WARN_ON_ONCE(!blkg->parent)) {
 			ret = -ENODEV;
-			goto err_put_congested;
+			goto err_put_css;
 		}
 		blkg_get(blkg->parent);
 	}
@@ -306,8 +293,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 	blkg_put(blkg);
 	return ERR_PTR(ret);
 
-err_put_congested:
-	wb_congested_put(wb_congested);
 err_put_css:
 	css_put(&blkcg->css);
 err_free_blkg:
@@ -316,30 +301,35 @@ err_free_blkg:
 }
 
 /**
- * __blkg_lookup_create - lookup blkg, try to create one if not there
+ * blkg_lookup_create - lookup blkg, try to create one if not there
  * @blkcg: blkcg of interest
  * @q: request_queue of interest
  *
  * Lookup blkg for the @blkcg - @q pair.  If it doesn't exist, try to
  * create one.  blkg creation is performed recursively from blkcg_root such
  * that all non-root blkg's have access to the parent blkg.  This function
- * should be called under RCU read lock and @q->queue_lock.
+ * should be called under RCU read lock and takes @q->queue_lock.
  *
  * Returns the blkg or the closest blkg if blkg_create() fails as it walks
  * down from root.
  */
-struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
-				      struct request_queue *q)
+static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
+		struct request_queue *q)
 {
 	struct blkcg_gq *blkg;
+	unsigned long flags;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
-	lockdep_assert_held(&q->queue_lock);
 
-	blkg = __blkg_lookup(blkcg, q, true);
+	blkg = blkg_lookup(blkcg, q);
 	if (blkg)
 		return blkg;
 
+	spin_lock_irqsave(&q->queue_lock, flags);
+	blkg = __blkg_lookup(blkcg, q, true);
+	if (blkg)
+		goto found;
+
 	/*
 	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
 	 * non-root blkgs have access to their parents.  Returns the closest
@@ -362,34 +352,16 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
 		}
 
 		blkg = blkg_create(pos, q, NULL);
-		if (IS_ERR(blkg))
-			return ret_blkg;
+		if (IS_ERR(blkg)) {
+			blkg = ret_blkg;
+			break;
+		}
 		if (pos == blkcg)
-			return blkg;
-	}
-}
-
-/**
- * blkg_lookup_create - find or create a blkg
- * @blkcg: target block cgroup
- * @q: target request_queue
- *
- * This looks up or creates the blkg representing the unique pair
- * of the blkcg and the request_queue.
- */
-struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
-				    struct request_queue *q)
-{
-	struct blkcg_gq *blkg = blkg_lookup(blkcg, q);
-
-	if (unlikely(!blkg)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&q->queue_lock, flags);
-		blkg = __blkg_lookup_create(blkcg, q);
-		spin_unlock_irqrestore(&q->queue_lock, flags);
+			break;
 	}
 
+found:
+	spin_unlock_irqrestore(&q->queue_lock, flags);
 	return blkg;
 }
 
@@ -739,12 +711,137 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] += src->bytes[i];
+		dst->ios[i] += src->ios[i];
+	}
+}
+
+static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] -= src->bytes[i];
+		dst->ios[i] -= src->ios[i];
+	}
+}
+
+static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkcg_gq *parent = blkg->parent;
+		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
+		struct blkg_iostat cur, delta;
+		unsigned int seq;
+
+		/* fetch the current per-cpu values */
+		do {
+			seq = u64_stats_fetch_begin(&bisc->sync);
+			blkg_iostat_set(&cur, &bisc->cur);
+		} while (u64_stats_fetch_retry(&bisc->sync, seq));
+
+		/* propagate percpu delta to global */
+		u64_stats_update_begin(&blkg->iostat.sync);
+		blkg_iostat_set(&delta, &cur);
+		blkg_iostat_sub(&delta, &bisc->last);
+		blkg_iostat_add(&blkg->iostat.cur, &delta);
+		blkg_iostat_add(&bisc->last, &delta);
+		u64_stats_update_end(&blkg->iostat.sync);
+
+		/* propagate global delta to parent */
+		if (parent) {
+			u64_stats_update_begin(&parent->iostat.sync);
+			blkg_iostat_set(&delta, &blkg->iostat.cur);
+			blkg_iostat_sub(&delta, &blkg->iostat.last);
+			blkg_iostat_add(&parent->iostat.cur, &delta);
+			blkg_iostat_add(&blkg->iostat.last, &delta);
+			u64_stats_update_end(&parent->iostat.sync);
+		}
+	}
+
+	rcu_read_unlock();
+}
+
+/*
+ * The rstat algorithms intentionally don't handle the root cgroup to avoid
+ * incurring overhead when no cgroups are defined. For that reason,
+ * cgroup_rstat_flush in blkcg_print_stat does not actually fill out the
+ * iostat in the root cgroup's blkcg_gq.
+ *
+ * However, we would like to re-use the printing code between the root and
+ * non-root cgroups to the extent possible. For that reason, we simulate
+ * flushing the root cgroup's stats by explicitly filling in the iostat
+ * with disk level statistics.
+ */
+static void blkcg_fill_root_iostats(void)
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+		struct hd_struct *part = disk_get_part(disk, 0);
+		struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue);
+		struct blkg_iostat tmp;
+		int cpu;
+
+		memset(&tmp, 0, sizeof(tmp));
+		for_each_possible_cpu(cpu) {
+			struct disk_stats *cpu_dkstats;
+
+			cpu_dkstats = per_cpu_ptr(part->dkstats, cpu);
+			tmp.ios[BLKG_IOSTAT_READ] +=
+				cpu_dkstats->ios[STAT_READ];
+			tmp.ios[BLKG_IOSTAT_WRITE] +=
+				cpu_dkstats->ios[STAT_WRITE];
+			tmp.ios[BLKG_IOSTAT_DISCARD] +=
+				cpu_dkstats->ios[STAT_DISCARD];
+			// convert sectors to bytes
+			tmp.bytes[BLKG_IOSTAT_READ] +=
+				cpu_dkstats->sectors[STAT_READ] << 9;
+			tmp.bytes[BLKG_IOSTAT_WRITE] +=
+				cpu_dkstats->sectors[STAT_WRITE] << 9;
+			tmp.bytes[BLKG_IOSTAT_DISCARD] +=
+				cpu_dkstats->sectors[STAT_DISCARD] << 9;
+
+			u64_stats_update_begin(&blkg->iostat.sync);
+			blkg_iostat_set(&blkg->iostat.cur, &tmp);
+			u64_stats_update_end(&blkg->iostat.sync);
+		}
+	}
+}
+
 static int blkcg_print_stat(struct seq_file *sf, void *v)
 {
 	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
 	struct blkcg_gq *blkg;
 
-	cgroup_rstat_flush(blkcg->css.cgroup);
+	if (!seq_css(sf)->parent)
+		blkcg_fill_root_iostats();
+	else
+		cgroup_rstat_flush(blkcg->css.cgroup);
+
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
@@ -833,7 +930,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 static struct cftype blkcg_files[] = {
 	{
 		.name = "stat",
-		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = blkcg_print_stat,
 	},
 	{ }	/* terminate */
@@ -1025,7 +1121,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
  * blkcg_init_queue - initialize blkcg part of request queue
  * @q: request_queue to initialize
  *
- * Called from __blk_alloc_queue(). Responsible for initializing blkcg
+ * Called from blk_alloc_queue(). Responsible for initializing blkcg
  * part of new request_queue @q.
  *
  * RETURNS:
@@ -1114,77 +1210,6 @@ static int blkcg_can_attach(struct cgroup_taskset *tset)
 	return ret;
 }
 
-static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
-{
-	int i;
-
-	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
-		dst->bytes[i] = src->bytes[i];
-		dst->ios[i] = src->ios[i];
-	}
-}
-
-static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
-{
-	int i;
-
-	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
-		dst->bytes[i] += src->bytes[i];
-		dst->ios[i] += src->ios[i];
-	}
-}
-
-static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src)
-{
-	int i;
-
-	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
-		dst->bytes[i] -= src->bytes[i];
-		dst->ios[i] -= src->ios[i];
-	}
-}
-
-static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
-{
-	struct blkcg *blkcg = css_to_blkcg(css);
-	struct blkcg_gq *blkg;
-
-	rcu_read_lock();
-
-	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
-		struct blkcg_gq *parent = blkg->parent;
-		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
-		struct blkg_iostat cur, delta;
-		unsigned seq;
-
-		/* fetch the current per-cpu values */
-		do {
-			seq = u64_stats_fetch_begin(&bisc->sync);
-			blkg_iostat_set(&cur, &bisc->cur);
-		} while (u64_stats_fetch_retry(&bisc->sync, seq));
-
-		/* propagate percpu delta to global */
-		u64_stats_update_begin(&blkg->iostat.sync);
-		blkg_iostat_set(&delta, &cur);
-		blkg_iostat_sub(&delta, &bisc->last);
-		blkg_iostat_add(&blkg->iostat.cur, &delta);
-		blkg_iostat_add(&bisc->last, &delta);
-		u64_stats_update_end(&blkg->iostat.sync);
-
-		/* propagate global delta to parent */
-		if (parent) {
-			u64_stats_update_begin(&parent->iostat.sync);
-			blkg_iostat_set(&delta, &blkg->iostat.cur);
-			blkg_iostat_sub(&delta, &blkg->iostat.last);
-			blkg_iostat_add(&parent->iostat.cur, &delta);
-			blkg_iostat_add(&blkg->iostat.last, &delta);
-			u64_stats_update_end(&parent->iostat.sync);
-		}
-	}
-
-	rcu_read_unlock();
-}
-
 static void blkcg_bind(struct cgroup_subsys_state *root_css)
 {
 	int i;
@@ -1727,6 +1752,139 @@ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
 	atomic64_add(delta, &blkg->delay_nsec);
 }
 
+/**
+ * blkg_tryget_closest - try and get a blkg ref on the closet blkg
+ * @bio: target bio
+ * @css: target css
+ *
+ * As the failure mode here is to walk up the blkg tree, this ensure that the
+ * blkg->parent pointers are always valid.  This returns the blkg that it ended
+ * up taking a reference on or %NULL if no reference was taken.
+ */
+static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio,
+		struct cgroup_subsys_state *css)
+{
+	struct blkcg_gq *blkg, *ret_blkg = NULL;
+
+	rcu_read_lock();
+	blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_disk->queue);
+	while (blkg) {
+		if (blkg_tryget(blkg)) {
+			ret_blkg = blkg;
+			break;
+		}
+		blkg = blkg->parent;
+	}
+	rcu_read_unlock();
+
+	return ret_blkg;
+}
+
+/**
+ * bio_associate_blkg_from_css - associate a bio with a specified css
+ * @bio: target bio
+ * @css: target css
+ *
+ * Associate @bio with the blkg found by combining the css's blkg and the
+ * request_queue of the @bio.  An association failure is handled by walking up
+ * the blkg tree.  Therefore, the blkg associated can be anything between @blkg
+ * and q->root_blkg.  This situation only happens when a cgroup is dying and
+ * then the remaining bios will spill to the closest alive blkg.
+ *
+ * A reference will be taken on the blkg and will be released when @bio is
+ * freed.
+ */
+void bio_associate_blkg_from_css(struct bio *bio,
+				 struct cgroup_subsys_state *css)
+{
+	if (bio->bi_blkg)
+		blkg_put(bio->bi_blkg);
+
+	if (css && css->parent) {
+		bio->bi_blkg = blkg_tryget_closest(bio, css);
+	} else {
+		blkg_get(bio->bi_disk->queue->root_blkg);
+		bio->bi_blkg = bio->bi_disk->queue->root_blkg;
+	}
+}
+EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
+
+/**
+ * bio_associate_blkg - associate a bio with a blkg
+ * @bio: target bio
+ *
+ * Associate @bio with the blkg found from the bio's css and request_queue.
+ * If one is not found, bio_lookup_blkg() creates the blkg.  If a blkg is
+ * already associated, the css is reused and association redone as the
+ * request_queue may have changed.
+ */
+void bio_associate_blkg(struct bio *bio)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+
+	if (bio->bi_blkg)
+		css = &bio_blkcg(bio)->css;
+	else
+		css = blkcg_css();
+
+	bio_associate_blkg_from_css(bio, css);
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(bio_associate_blkg);
+
+/**
+ * bio_clone_blkg_association - clone blkg association from src to dst bio
+ * @dst: destination bio
+ * @src: source bio
+ */
+void bio_clone_blkg_association(struct bio *dst, struct bio *src)
+{
+	if (src->bi_blkg) {
+		if (dst->bi_blkg)
+			blkg_put(dst->bi_blkg);
+		blkg_get(src->bi_blkg);
+		dst->bi_blkg = src->bi_blkg;
+	}
+}
+EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
+
+static int blk_cgroup_io_type(struct bio *bio)
+{
+	if (op_is_discard(bio->bi_opf))
+		return BLKG_IOSTAT_DISCARD;
+	if (op_is_write(bio->bi_opf))
+		return BLKG_IOSTAT_WRITE;
+	return BLKG_IOSTAT_READ;
+}
+
+void blk_cgroup_bio_start(struct bio *bio)
+{
+	int rwd = blk_cgroup_io_type(bio), cpu;
+	struct blkg_iostat_set *bis;
+
+	cpu = get_cpu();
+	bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu);
+	u64_stats_update_begin(&bis->sync);
+
+	/*
+	 * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split
+	 * bio and we would have already accounted for the size of the bio.
+	 */
+	if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
+		bio_set_flag(bio, BIO_CGROUP_ACCT);
+		bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
+	}
+	bis->cur.ios[rwd]++;
+
+	u64_stats_update_end(&bis->sync);
+	if (cgroup_subsys_on_dfl(io_cgrp_subsys))
+		cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu);
+	put_cpu();
+}
+
 static int __init blkcg_init(void)
 {
 	blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",