Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...

1 files changed, 77 insertions, 17 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ed761c62ad0a..50ac0dce95b8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -59,6 +59,37 @@ static struct workqueue_struct *blkcg_punt_bio_wq;
 
 #define BLKG_DESTROY_BATCH_SIZE  64
 
+/*
+ * Lockless lists for tracking IO stats update
+ *
+ * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg).
+ * There are multiple blkg's (one for each block device) attached to each
+ * blkcg. The rstat code keeps track of which cpu has IO stats updated,
+ * but it doesn't know which blkg has the updated stats. If there are many
+ * block devices in a system, the cost of iterating all the blkg's to flush
+ * out the IO stats can be high. To reduce such overhead, a set of percpu
+ * lockless lists (lhead) per blkcg are used to track the set of recently
+ * updated iostat_cpu's since the last flush. An iostat_cpu will be put
+ * onto the lockless list on the update side [blk_cgroup_bio_start()] if
+ * not there yet and then removed when being flushed [blkcg_rstat_flush()].
+ * References to blkg are gotten and then put back in the process to
+ * protect against blkg removal.
+ *
+ * Return: 0 if successful or -ENOMEM if allocation fails.
+ */
+static int init_blkcg_llists(struct blkcg *blkcg)
+{
+	int cpu;
+
+	blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL);
+	if (!blkcg->lhead)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu)
+		init_llist_head(per_cpu_ptr(blkcg->lhead, cpu));
+	return 0;
+}
+
 /**
  * blkcg_css - find the current css
  *
@@ -236,8 +267,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg->blkcg = blkcg;
 
 	u64_stats_init(&blkg->iostat.sync);
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
 		u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync);
+		per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg;
+	}
 
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
@@ -577,7 +610,7 @@ EXPORT_SYMBOL_GPL(blkcg_print_blkgs);
  * @pd: policy private data of interest
  * @v: value to print
  *
- * Print @v to @sf for the device assocaited with @pd.
+ * Print @v to @sf for the device associated with @pd.
  */
 u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
 {
@@ -765,7 +798,7 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 
 /**
  * blkg_conf_finish - finish up per-blkg config update
- * @ctx: blkg_conf_ctx intiailized by blkg_conf_prep()
+ * @ctx: blkg_conf_ctx initialized by blkg_conf_prep()
  *
  * Finish up after per-blkg config update.  This function must be paired
  * with blkg_conf_prep().
@@ -827,7 +860,9 @@ static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur,
 static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
-	struct blkcg_gq *blkg;
+	struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu);
+	struct llist_node *lnode;
+	struct blkg_iostat_set *bisc, *next_bisc;
 
 	/* Root-level stats are sourced from system-wide IO stats */
 	if (!cgroup_parent(css->cgroup))
@@ -835,12 +870,21 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 
 	rcu_read_lock();
 
-	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+	lnode = llist_del_all(lhead);
+	if (!lnode)
+		goto out;
+
+	/*
+	 * Iterate only the iostat_cpu's queued in the lockless list.
+	 */
+	llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) {
+		struct blkcg_gq *blkg = bisc->blkg;
 		struct blkcg_gq *parent = blkg->parent;
-		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
 		struct blkg_iostat cur;
 		unsigned int seq;
 
+		WRITE_ONCE(bisc->lqueued, false);
+
 		/* fetch the current per-cpu values */
 		do {
 			seq = u64_stats_fetch_begin(&bisc->sync);
@@ -853,8 +897,10 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 		if (parent && parent->parent)
 			blkcg_iostat_update(parent, &blkg->iostat.cur,
 					    &blkg->iostat.last);
+		percpu_ref_put(&blkg->refcnt);
 	}
 
+out:
 	rcu_read_unlock();
 }
 
@@ -1132,6 +1178,7 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
 
 	mutex_unlock(&blkcg_pol_mutex);
 
+	free_percpu(blkcg->lhead);
 	kfree(blkcg);
 }
 
@@ -1139,7 +1186,6 @@ static struct cgroup_subsys_state *
 blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct blkcg *blkcg;
-	struct cgroup_subsys_state *ret;
 	int i;
 
 	mutex_lock(&blkcg_pol_mutex);
@@ -1148,12 +1194,13 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 		blkcg = &blkcg_root;
 	} else {
 		blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
-		if (!blkcg) {
-			ret = ERR_PTR(-ENOMEM);
+		if (!blkcg)
 			goto unlock;
-		}
 	}
 
+	if (init_blkcg_llists(blkcg))
+		goto free_blkcg;
+
 	for (i = 0; i < BLKCG_MAX_POLS ; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkcg_policy_data *cpd;
@@ -1168,10 +1215,9 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 			continue;
 
 		cpd = pol->cpd_alloc_fn(GFP_KERNEL);
-		if (!cpd) {
-			ret = ERR_PTR(-ENOMEM);
+		if (!cpd)
 			goto free_pd_blkcg;
-		}
+
 		blkcg->cpd[i] = cpd;
 		cpd->blkcg = blkcg;
 		cpd->plid = i;
@@ -1195,12 +1241,13 @@ free_pd_blkcg:
 	for (i--; i >= 0; i--)
 		if (blkcg->cpd[i])
 			blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);
-
+	free_percpu(blkcg->lhead);
+free_blkcg:
 	if (blkcg != &blkcg_root)
 		kfree(blkcg);
 unlock:
 	mutex_unlock(&blkcg_pol_mutex);
-	return ret;
+	return ERR_PTR(-ENOMEM);
 }
 
 static int blkcg_css_online(struct cgroup_subsys_state *css)
@@ -1784,7 +1831,7 @@ out:
 
 /**
  * blkcg_schedule_throttle - this task needs to check for throttling
- * @gendisk: disk to throttle
+ * @disk: disk to throttle
  * @use_memdelay: do we charge this to memory delay for PSI
  *
  * This is called by the IO controller when we know there's delay accumulated
@@ -1943,6 +1990,7 @@ static int blk_cgroup_io_type(struct bio *bio)
 
 void blk_cgroup_bio_start(struct bio *bio)
 {
+	struct blkcg *blkcg = bio->bi_blkg->blkcg;
 	int rwd = blk_cgroup_io_type(bio), cpu;
 	struct blkg_iostat_set *bis;
 	unsigned long flags;
@@ -1961,9 +2009,21 @@ void blk_cgroup_bio_start(struct bio *bio)
 	}
 	bis->cur.ios[rwd]++;
 
+	/*
+	 * If the iostat_cpu isn't in a lockless list, put it into the
+	 * list to indicate that a stat update is pending.
+	 */
+	if (!READ_ONCE(bis->lqueued)) {
+		struct llist_head *lhead = this_cpu_ptr(blkcg->lhead);
+
+		llist_add(&bis->lnode, lhead);
+		WRITE_ONCE(bis->lqueued, true);
+		percpu_ref_get(&bis->blkg->refcnt);
+	}
+
 	u64_stats_update_end_irqrestore(&bis->sync, flags);
 	if (cgroup_subsys_on_dfl(io_cgrp_subsys))
-		cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu);
+		cgroup_rstat_updated(blkcg->css.cgroup, cpu);
 	put_cpu();
 }