Merge branch 'for-linus' into for-5.5/block

Pull on for-linus to resolve what otherwise would have been a conflict
with the cgroups rstat patchset from Tejun.

* for-linus: (942 commits)
  blkcg: make blkcg_print_stat() print stats only for online blkgs
  nvme: change nvme_passthru_cmd64 to explicitly mark rsvd
  nvme-multipath: fix crash in nvme_mpath_clear_ctrl_paths
  nvme-rdma: fix a segmentation fault during module unload
  iocost: don't nest spin_lock_irq in ioc_weight_write()
  io_uring: ensure we clear io_kiocb->result before each issue
  um-ubd: Entrust re-queue to the upper layers
  nvme-multipath: remove unused groups_only mode in ana log
  nvme-multipath: fix possible io hang after ctrl reconnect
  io_uring: don't touch ctx in setup after ring fd install
  io_uring: Fix leaked shadow_req
  Linux 5.4-rc5
  riscv: cleanup do_trap_break
  nbd: verify socket is supported during setup
  ata: libahci_platform: Fix regulator_get_optional() misuse
  nbd: handle racing with error'ed out commands
  nbd: protect cmd->status with cmd->lock
  io_uring: fix bad inflight accounting for SETUP_IOPOLL|SETUP_SQTHREAD
  io_uring: used cached copies of sq->dropped and cq->overflow
  ARM: dts: stm32: relax qspi pins slew-rate for stm32mp157
  ...

6 files changed, 83 insertions, 43 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b6f20be0fc78..1eb8895be4c6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -934,9 +934,14 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		int i;
 		bool has_stats = false;
 
+		spin_lock_irq(&blkg->q->queue_lock);
+
+		if (!blkg->online)
+			goto skip;
+
 		dname = blkg_dev_name(blkg);
 		if (!dname)
-			continue;
+			goto skip;
 
 		/*
 		 * Hooray string manipulation, count is the size written NOT
@@ -946,8 +951,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		 */
 		off += scnprintf(buf+off, size-off, "%s ", dname);
 
-		spin_lock_irq(&blkg->q->queue_lock);
-
 		blkg_rwstat_recursive_sum(blkg, NULL,
 				offsetof(struct blkcg_gq, stat_bytes), &rwstat);
 		rbytes = rwstat.cnt[BLKG_RWSTAT_READ];
@@ -960,8 +963,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		wios = rwstat.cnt[BLKG_RWSTAT_WRITE];
 		dios = rwstat.cnt[BLKG_RWSTAT_DISCARD];
 
-		spin_unlock_irq(&blkg->q->queue_lock);
-
 		if (rbytes || wbytes || rios || wios) {
 			has_stats = true;
 			off += scnprintf(buf+off, size-off,
@@ -999,6 +1000,8 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 				seq_commit(sf, -1);
 			}
 		}
+	skip:
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 
 	rcu_read_unlock();
@@ -1362,7 +1365,7 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	struct blkg_policy_data *pd_prealloc = NULL;
-	struct blkcg_gq *blkg;
+	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1370,49 +1373,82 @@ int blkcg_activate_policy(struct request_queue *q,
 
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
-pd_prealloc:
-	if (!pd_prealloc) {
-		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root);
-		if (!pd_prealloc) {
-			ret = -ENOMEM;
-			goto out_bypass_end;
-		}
-	}
-
+retry:
 	spin_lock_irq(&q->queue_lock);
 
-	/* blkg_list is pushed at the head, reverse walk to init parents first */
+	/* blkg_list is pushed at the head, reverse walk to allocate parents first */
 	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		struct blkg_policy_data *pd;
 
 		if (blkg->pd[pol->plid])
 			continue;
 
-		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root);
-		if (!pd)
-			swap(pd, pd_prealloc);
+		/* If prealloc matches, use it; otherwise try GFP_NOWAIT */
+		if (blkg == pinned_blkg) {
+			pd = pd_prealloc;
+			pd_prealloc = NULL;
+		} else {
+			pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q,
+					      blkg->blkcg);
+		}
+
 		if (!pd) {
+			/*
+			 * GFP_NOWAIT failed.  Free the existing one and
+			 * prealloc for @blkg w/ GFP_KERNEL.
+			 */
+			if (pinned_blkg)
+				blkg_put(pinned_blkg);
+			blkg_get(blkg);
+			pinned_blkg = blkg;
+
 			spin_unlock_irq(&q->queue_lock);
-			goto pd_prealloc;
+
+			if (pd_prealloc)
+				pol->pd_free_fn(pd_prealloc);
+			pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q,
+						       blkg->blkcg);
+			if (pd_prealloc)
+				goto retry;
+			else
+				goto enomem;
 		}
 
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
-		if (pol->pd_init_fn)
-			pol->pd_init_fn(pd);
 	}
 
+	/* all allocated, init in the same order */
+	if (pol->pd_init_fn)
+		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+			pol->pd_init_fn(blkg->pd[pol->plid]);
+
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
 
 	spin_unlock_irq(&q->queue_lock);
-out_bypass_end:
+out:
 	if (queue_is_mq(q))
 		blk_mq_unfreeze_queue(q);
+	if (pinned_blkg)
+		blkg_put(pinned_blkg);
 	if (pd_prealloc)
 		pol->pd_free_fn(pd_prealloc);
 	return ret;
+
+enomem:
+	/* alloc failed, nothing's initialized yet, free everything */
+	spin_lock_irq(&q->queue_lock);
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		if (blkg->pd[pol->plid]) {
+			pol->pd_free_fn(blkg->pd[pol->plid]);
+			blkg->pd[pol->plid] = NULL;
+		}
+	}
+	spin_unlock_irq(&q->queue_lock);
+	ret = -ENOMEM;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 2a3db80c1dce..a7ed434eae03 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2110,10 +2110,10 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf,
 			goto einval;
 	}
 
-	spin_lock_irq(&iocg->ioc->lock);
+	spin_lock(&iocg->ioc->lock);
 	iocg->cfg_weight = v;
 	weight_updated(iocg);
-	spin_unlock_irq(&iocg->ioc->lock);
+	spin_unlock(&iocg->ioc->lock);
 
 	blkg_conf_finish(&ctx);
 	return nbytes;
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 61b635bc2a31..656460636ad3 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -160,24 +160,27 @@ bool rq_depth_calc_max_depth(struct rq_depth *rqd)
 	return ret;
 }
 
-void rq_depth_scale_up(struct rq_depth *rqd)
+/* Returns true on success and false if scaling up wasn't possible */
+bool rq_depth_scale_up(struct rq_depth *rqd)
 {
 	/*
 	 * Hit max in previous round, stop here
 	 */
 	if (rqd->scaled_max)
-		return;
+		return false;
 
 	rqd->scale_step--;
 
 	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+	return true;
 }
 
 /*
  * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
- * had a latency violation.
+ * had a latency violation. Returns true on success and returns false if
+ * scaling down wasn't possible.
  */
-void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
+bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
 {
 	/*
 	 * Stop scaling down when we've hit the limit. This also prevents
@@ -185,7 +188,7 @@ void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
 	 * keep up.
 	 */
 	if (rqd->max_depth == 1)
-		return;
+		return false;
 
 	if (rqd->scale_step < 0 && hard_throttle)
 		rqd->scale_step = 0;
@@ -194,6 +197,7 @@ void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
 
 	rqd->scaled_max = false;
 	rq_depth_calc_max_depth(rqd);
+	return true;
 }
 
 struct rq_qos_wait_data {
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 08a09dbe0f4b..2bc43e94f4c4 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -108,16 +108,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
 {
-	struct rq_qos *cur, *prev = NULL;
-	for (cur = q->rq_qos; cur; cur = cur->next) {
-		if (cur == rqos) {
-			if (prev)
-				prev->next = rqos->next;
-			else
-				q->rq_qos = cur;
+	struct rq_qos **cur;
+
+	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
+		if (*cur == rqos) {
+			*cur = rqos->next;
 			break;
 		}
-		prev = cur;
 	}
 
 	blk_mq_debugfs_unregister_rqos(rqos);
@@ -130,8 +127,8 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
 		 acquire_inflight_cb_t *acquire_inflight_cb,
 		 cleanup_cb_t *cleanup_cb);
 bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
-void rq_depth_scale_up(struct rq_depth *rqd);
-void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_scale_up(struct rq_depth *rqd);
+bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
 bool rq_depth_calc_max_depth(struct rq_depth *rqd);
 
 void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio);
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 8af553a0ba00..8641ba9793c5 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -308,7 +308,8 @@ static void calc_wb_limits(struct rq_wb *rwb)
 
 static void scale_up(struct rq_wb *rwb)
 {
-	rq_depth_scale_up(&rwb->rq_depth);
+	if (!rq_depth_scale_up(&rwb->rq_depth))
+		return;
 	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
 	rwb_wake_all(rwb);
@@ -317,7 +318,8 @@ static void scale_up(struct rq_wb *rwb)
 
 static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 {
-	rq_depth_scale_down(&rwb->rq_depth, hard_throttle);
+	if (!rq_depth_scale_down(&rwb->rq_depth, hard_throttle))
+		return;
 	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
 	rwb_trace_step(rwb, "scale down");
diff --git a/block/elevator.c b/block/elevator.c
index 0b1db9afb586..4eab3d70e880 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -616,7 +616,8 @@ out:
 
 static inline bool elv_support_iosched(struct request_queue *q)
 {
-	if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED))
+	if (!q->mq_ops ||
+	    (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)))
 		return false;
 	return true;
 }