Merge tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Christoph:
      - Small improvements to the logging functionality (Amit Engel)
      - Authentication cleanups (Hannes Reinecke)
      - Cleanup and optimize the DMA mapping cod in the PCIe driver
        (Keith Busch)
      - Work around the command effects for Format NVM (Keith Busch)
      - Misc cleanups (Keith Busch, Christoph Hellwig)
      - Fix and cleanup freeing single sgl (Keith Busch)

 - MD updates via Song:
      - Fix a rare crash during the takeover process
      - Don't update recovery_cp when curr_resync is ACTIVE
      - Free writes_pending in md_stop
      - Change active_io to percpu

 - Updates to drbd, inching us closer to unifying the out-of-tree driver
   with the in-tree one (Andreas, Christoph, Lars, Robert)

 - BFQ update adding support for multi-actuator drives (Paolo, Federico,
   Davide)

 - Make brd compliant with REQ_NOWAIT (me)

 - Fix for IOPOLL and queue entering, fixing stalled IO waiting on
   timeouts (me)

 - Fix for REQ_NOWAIT with multiple bios (me)

 - Fix memory leak in blktrace cleanup (Greg)

 - Clean up sbitmap and fix a potential hang (Kemeng)

 - Clean up some bits in BFQ, and fix a bug in the request injection
   (Kemeng)

 - Clean up the request allocation and issue code, and fix some bugs
   related to that (Kemeng)

 - ublk updates and fixes:
      - Add support for unprivileged ublk (Ming)
      - Improve device deletion handling (Ming)
      - Misc (Liu, Ziyang)

 - s390 dasd fixes (Alexander, Qiheng)

 - Improve utility of request caching and fixes (Anuj, Xiao)

 - zoned cleanups (Pankaj)

 - More constification for kobjs (Thomas)

 - blk-iocost cleanups (Yu)

 - Remove bio splitting from drivers that don't need it (Christoph)

 - Switch blk-cgroups to use struct gendisk. Some of this is now
   incomplete as select late reverts were done. (Christoph)

 - Add bvec initialization helpers, and convert callers to use that
   rather than open-coding it (Christoph)

 - Misc fixes and cleanups (Jinke, Keith, Arnd, Bart, Li, Martin,
   Matthew, Ulf, Zhong)

* tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux: (169 commits)
  brd: use radix_tree_maybe_preload instead of radix_tree_preload
  block: use proper return value from bio_failfast()
  block: bio-integrity: Copy flags when bio_integrity_payload is cloned
  block: Fix io statistics for cgroup in throttle path
  brd: mark as nowait compatible
  brd: check for REQ_NOWAIT and set correct page allocation mask
  brd: return 0/-error from brd_insert_page()
  block: sync mixed merged request's failfast with 1st bio's
  Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"
  Revert "blk-cgroup: pass a gendisk to blkg_lookup"
  Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"
  Revert "blk-cgroup: delay calling blkcg_exit_disk until disk_release"
  Revert "blk-cgroup: move the cgroup information to struct gendisk"
  nvme-pci: remove iod use_sgls
  nvme-pci: fix freeing single sgl
  block: ublk: check IO buffer based on flag need_get_data
  s390/dasd: Fix potential memleak in dasd_eckd_init()
  s390/dasd: sort out physical vs virtual pointers usage
  block: Remove the ALLOC_CACHE_SLACK constant
  block: make kobj_type structures constant
  ...

1 files changed, 91 insertions, 59 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9ac1efb053e0..bd50b55bdb61 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -118,14 +118,26 @@ static void blkg_free_workfn(struct work_struct *work)
 {
 	struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
 					     free_work);
+	struct request_queue *q = blkg->q;
 	int i;
 
+	/*
+	 * pd_free_fn() can also be called from blkcg_deactivate_policy(),
+	 * in order to make sure pd_free_fn() is called in order, the deletion
+	 * of the list blkg->q_node is delayed to here from blkg_destroy(), and
+	 * blkcg_mutex is used to synchronize blkg_free_workfn() and
+	 * blkcg_deactivate_policy().
+	 */
+	mutex_lock(&q->blkcg_mutex);
 	for (i = 0; i < BLKCG_MAX_POLS; i++)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
+	if (blkg->parent)
+		blkg_put(blkg->parent);
+	list_del_init(&blkg->q_node);
+	mutex_unlock(&q->blkcg_mutex);
 
-	if (blkg->q)
-		blk_put_queue(blkg->q);
+	blk_put_queue(q);
 	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
@@ -158,8 +170,6 @@ static void __blkg_release(struct rcu_head *rcu)
 
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
-	if (blkg->parent)
-		blkg_put(blkg->parent);
 	blkg_free(blkg);
 }
 
@@ -249,16 +259,13 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node);
 	if (!blkg)
 		return NULL;
-
 	if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask))
-		goto err_free;
-
+		goto out_free_blkg;
 	blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
 	if (!blkg->iostat_cpu)
-		goto err_free;
-
+		goto out_exit_refcnt;
 	if (!blk_get_queue(disk->queue))
-		goto err_free;
+		goto out_free_iostat;
 
 	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
@@ -281,19 +288,28 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 			continue;
 
 		/* alloc per-policy data and attach it to blkg */
-		pd = pol->pd_alloc_fn(gfp_mask, disk->queue, blkcg);
+		pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask);
 		if (!pd)
-			goto err_free;
-
+			goto out_free_pds;
 		blkg->pd[i] = pd;
 		pd->blkg = blkg;
 		pd->plid = i;
+		pd->online = false;
 	}
 
 	return blkg;
 
-err_free:
-	blkg_free(blkg);
+out_free_pds:
+	while (--i >= 0)
+		if (blkg->pd[i])
+			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
+	blk_put_queue(disk->queue);
+out_free_iostat:
+	free_percpu(blkg->iostat_cpu);
+out_exit_refcnt:
+	percpu_ref_exit(&blkg->refcnt);
+out_free_blkg:
+	kfree(blkg);
 	return NULL;
 }
 
@@ -359,8 +375,11 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
 
-			if (blkg->pd[i] && pol->pd_online_fn)
-				pol->pd_online_fn(blkg->pd[i]);
+			if (blkg->pd[i]) {
+				if (pol->pd_online_fn)
+					pol->pd_online_fn(blkg->pd[i]);
+				blkg->pd[i]->online = true;
+			}
 		}
 	}
 	blkg->online = true;
@@ -376,7 +395,8 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 err_put_css:
 	css_put(&blkcg->css);
 err_free_blkg:
-	blkg_free(new_blkg);
+	if (new_blkg)
+		blkg_free(new_blkg);
 	return ERR_PTR(ret);
 }
 
@@ -458,21 +478,28 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	lockdep_assert_held(&blkg->q->queue_lock);
 	lockdep_assert_held(&blkcg->lock);
 
-	/* Something wrong if we are trying to remove same group twice */
-	WARN_ON_ONCE(list_empty(&blkg->q_node));
-	WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));
+	/*
+	 * blkg stays on the queue list until blkg_free_workfn(), see details in
+	 * blkg_free_workfn(), hence this function can be called from
+	 * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before
+	 * blkg_free_workfn().
+	 */
+	if (hlist_unhashed(&blkg->blkcg_node))
+		return;
 
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 
-		if (blkg->pd[i] && pol->pd_offline_fn)
-			pol->pd_offline_fn(blkg->pd[i]);
+		if (blkg->pd[i] && blkg->pd[i]->online) {
+			blkg->pd[i]->online = false;
+			if (pol->pd_offline_fn)
+				pol->pd_offline_fn(blkg->pd[i]);
+		}
 	}
 
 	blkg->online = false;
 
 	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
-	list_del_init(&blkg->q_node);
 	hlist_del_init_rcu(&blkg->blkcg_node);
 
 	/*
@@ -559,7 +586,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 
 const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
-	if (!blkg->q->disk || !blkg->q->disk->bdi->dev)
+	if (!blkg->q->disk)
 		return NULL;
 	return bdi_dev_name(blkg->q->disk->bdi);
 }
@@ -1273,6 +1300,7 @@ int blkcg_init_disk(struct gendisk *disk)
 	int ret;
 
 	INIT_LIST_HEAD(&q->blkg_list);
+	mutex_init(&q->blkcg_mutex);
 
 	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
@@ -1349,9 +1377,9 @@ static void blkcg_bind(struct cgroup_subsys_state *root_css)
 
 static void blkcg_exit(struct task_struct *tsk)
 {
-	if (tsk->throttle_queue)
-		blk_put_queue(tsk->throttle_queue);
-	tsk->throttle_queue = NULL;
+	if (tsk->throttle_disk)
+		put_disk(tsk->throttle_disk);
+	tsk->throttle_disk = NULL;
 }
 
 struct cgroup_subsys io_cgrp_subsys = {
@@ -1377,14 +1405,14 @@ struct cgroup_subsys io_cgrp_subsys = {
 EXPORT_SYMBOL_GPL(io_cgrp_subsys);
 
 /**
- * blkcg_activate_policy - activate a blkcg policy on a request_queue
- * @q: request_queue of interest
+ * blkcg_activate_policy - activate a blkcg policy on a gendisk
+ * @disk: gendisk of interest
  * @pol: blkcg policy to activate
  *
- * Activate @pol on @q.  Requires %GFP_KERNEL context.  @q goes through
+ * Activate @pol on @disk.  Requires %GFP_KERNEL context.  @disk goes through
  * bypass mode to populate its blkgs with policy_data for @pol.
  *
- * Activation happens with @q bypassed, so nobody would be accessing blkgs
+ * Activation happens with @disk bypassed, so nobody would be accessing blkgs
  * from IO path.  Update of each blkg is protected by both queue and blkcg
  * locks so that holding either lock and testing blkcg_policy_enabled() is
  * always enough for dereferencing policy data.
@@ -1392,9 +1420,9 @@ EXPORT_SYMBOL_GPL(io_cgrp_subsys);
  * The caller is responsible for synchronizing [de]activations and policy
  * [un]registerations.  Returns 0 on success, -errno on failure.
  */
-int blkcg_activate_policy(struct request_queue *q,
-			  const struct blkcg_policy *pol)
+int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 {
+	struct request_queue *q = disk->queue;
 	struct blkg_policy_data *pd_prealloc = NULL;
 	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
@@ -1419,8 +1447,8 @@ retry:
 			pd = pd_prealloc;
 			pd_prealloc = NULL;
 		} else {
-			pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q,
-					      blkg->blkcg);
+			pd = pol->pd_alloc_fn(disk, blkg->blkcg,
+					      GFP_NOWAIT | __GFP_NOWARN);
 		}
 
 		if (!pd) {
@@ -1437,8 +1465,8 @@ retry:
 
 			if (pd_prealloc)
 				pol->pd_free_fn(pd_prealloc);
-			pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q,
-						       blkg->blkcg);
+			pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg,
+						       GFP_KERNEL);
 			if (pd_prealloc)
 				goto retry;
 			else
@@ -1448,6 +1476,7 @@ retry:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
+		pd->online = false;
 	}
 
 	/* all allocated, init in the same order */
@@ -1455,9 +1484,11 @@ retry:
 		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
 			pol->pd_init_fn(blkg->pd[pol->plid]);
 
-	if (pol->pd_online_fn)
-		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
+		if (pol->pd_online_fn)
 			pol->pd_online_fn(blkg->pd[pol->plid]);
+		blkg->pd[pol->plid]->online = true;
+	}
 
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
@@ -1492,16 +1523,17 @@ enomem:
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
 
 /**
- * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue
- * @q: request_queue of interest
+ * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk
+ * @disk: gendisk of interest
  * @pol: blkcg policy to deactivate
  *
- * Deactivate @pol on @q.  Follows the same synchronization rules as
+ * Deactivate @pol on @disk.  Follows the same synchronization rules as
  * blkcg_activate_policy().
  */
-void blkcg_deactivate_policy(struct request_queue *q,
+void blkcg_deactivate_policy(struct gendisk *disk,
 			     const struct blkcg_policy *pol)
 {
+	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
 
 	if (!blkcg_policy_enabled(q, pol))
@@ -1510,6 +1542,7 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
 
+	mutex_lock(&q->blkcg_mutex);
 	spin_lock_irq(&q->queue_lock);
 
 	__clear_bit(pol->plid, q->blkcg_pols);
@@ -1519,7 +1552,7 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
-			if (pol->pd_offline_fn)
+			if (blkg->pd[pol->plid]->online && pol->pd_offline_fn)
 				pol->pd_offline_fn(blkg->pd[pol->plid]);
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
@@ -1528,6 +1561,7 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	}
 
 	spin_unlock_irq(&q->queue_lock);
+	mutex_unlock(&q->blkcg_mutex);
 
 	if (queue_is_mq(q))
 		blk_mq_unfreeze_queue(q);
@@ -1797,29 +1831,29 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
  *
  * This is only called if we've been marked with set_notify_resume().  Obviously
  * we can be set_notify_resume() for reasons other than blkcg throttling, so we
- * check to see if current->throttle_queue is set and if not this doesn't do
+ * check to see if current->throttle_disk is set and if not this doesn't do
  * anything.  This should only ever be called by the resume code, it's not meant
  * to be called by people willy-nilly as it will actually do the work to
  * throttle the task if it is setup for throttling.
  */
 void blkcg_maybe_throttle_current(void)
 {
-	struct request_queue *q = current->throttle_queue;
+	struct gendisk *disk = current->throttle_disk;
 	struct blkcg *blkcg;
 	struct blkcg_gq *blkg;
 	bool use_memdelay = current->use_memdelay;
 
-	if (!q)
+	if (!disk)
 		return;
 
-	current->throttle_queue = NULL;
+	current->throttle_disk = NULL;
 	current->use_memdelay = false;
 
 	rcu_read_lock();
 	blkcg = css_to_blkcg(blkcg_css());
 	if (!blkcg)
 		goto out;
-	blkg = blkg_lookup(blkcg, q);
+	blkg = blkg_lookup(blkcg, disk->queue);
 	if (!blkg)
 		goto out;
 	if (!blkg_tryget(blkg))
@@ -1828,11 +1862,10 @@ void blkcg_maybe_throttle_current(void)
 
 	blkcg_maybe_throttle_blkg(blkg, use_memdelay);
 	blkg_put(blkg);
-	blk_put_queue(q);
+	put_disk(disk);
 	return;
 out:
 	rcu_read_unlock();
-	blk_put_queue(q);
 }
 
 /**
@@ -1854,18 +1887,17 @@ out:
  */
 void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay)
 {
-	struct request_queue *q = disk->queue;
-
 	if (unlikely(current->flags & PF_KTHREAD))
 		return;
 
-	if (current->throttle_queue != q) {
-		if (!blk_get_queue(q))
+	if (current->throttle_disk != disk) {
+		if (test_bit(GD_DEAD, &disk->state))
 			return;
+		get_device(disk_to_dev(disk));
 
-		if (current->throttle_queue)
-			blk_put_queue(current->throttle_queue);
-		current->throttle_queue = q;
+		if (current->throttle_disk)
+			put_disk(current->throttle_disk);
+		current->throttle_disk = disk;
 	}
 
 	if (use_memdelay)