Merge tag 'block-6.2-2023-01-20' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:
 "Various little tweaks all over the place:

   - NVMe pull request via Christoph:
       - fix controller shutdown regression in nvme-apple (Janne Grunau)
       - fix a polling on timeout regression in nvme-pci (Keith Busch)

   - Fix a bug in the read request side request allocation caching
     (Pavel)

   - pktcdvd was brought back after we configured a NULL return on bio
     splits, make it consistent with the others (me)

   - BFQ refcount fix (Yu)

   - Block cgroup policy activation fix (Yu)

   - Fix for an md regression introduced in the 6.2 cycle (Adrian)"

* tag 'block-6.2-2023-01-20' of git://git.kernel.dk/linux:
  nvme-pci: fix timeout request state check
  nvme-apple: only reset the controller when RTKit is running
  nvme-apple: reset controller during shutdown
  block: fix hctx checks for batch allocation
  block/rnbd-clt: fix wrong max ID in ida_alloc_max
  blk-cgroup: fix missing pd_online_fn() while activating policy
  pktcdvd: check for NULL returna fter calling bio_split_to_limits()
  block, bfq: switch 'bfqg->ref' to use atomic refcount apis
  md: fix incorrect declaration about claim_rdev in md_import_device

9 files changed, 39 insertions, 15 deletions

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 1b2829e99dad..7d9b15f0dbd5 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -316,14 +316,12 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 
 static void bfqg_get(struct bfq_group *bfqg)
 {
-	bfqg->ref++;
+	refcount_inc(&bfqg->ref);
 }
 
 static void bfqg_put(struct bfq_group *bfqg)
 {
-	bfqg->ref--;
-
-	if (bfqg->ref == 0)
+	if (refcount_dec_and_test(&bfqg->ref))
 		kfree(bfqg);
 }
 
@@ -530,7 +528,7 @@ static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
 	}
 
 	/* see comments in bfq_bic_update_cgroup for why refcounting */
-	bfqg_get(bfqg);
+	refcount_set(&bfqg->ref, 1);
 	return &bfqg->pd;
 }
 
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 41aa151ccc22..466e4865ace6 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -928,7 +928,7 @@ struct bfq_group {
 	char blkg_path[128];
 
 	/* reference counter (see comments in bfq_bic_update_cgroup) */
-	int ref;
+	refcount_t ref;
 	/* Is bfq_group still online? */
 	bool online;
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ce6a2b7d3dfb..4c94a6560f62 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1455,6 +1455,10 @@ 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)
+			pol->pd_online_fn(blkg->pd[pol->plid]);
+
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2c49b4151da1..9d463f7563bc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2890,6 +2890,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 		struct blk_plug *plug, struct bio **bio, unsigned int nsegs)
 {
 	struct request *rq;
+	enum hctx_type type, hctx_type;
 
 	if (!plug)
 		return NULL;
@@ -2902,7 +2903,10 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 		return NULL;
 	}
 
-	if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type)
+	type = blk_mq_get_hctx_type((*bio)->bi_opf);
+	hctx_type = rq->mq_hctx->type;
+	if (type != hctx_type &&
+	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
 		return NULL;
 	if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
 		return NULL;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4cea3b08087e..2f1a92509271 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2400,6 +2400,8 @@ static void pkt_submit_bio(struct bio *bio)
 	struct bio *split;
 
 	bio = bio_split_to_limits(bio);
+	if (!bio)
+		return;
 
 	pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
 		(unsigned long long)bio->bi_iter.bi_sector,
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 78334da74d8b..5eb8c7855970 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1440,7 +1440,7 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
 		goto out_alloc;
 	}
 
-	ret = ida_alloc_max(&index_ida, 1 << (MINORBITS - RNBD_PART_BITS),
+	ret = ida_alloc_max(&index_ida, (1 << (MINORBITS - RNBD_PART_BITS)) - 1,
 			    GFP_KERNEL);
 	if (ret < 0) {
 		pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n",
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8af639296b3c..02b0240e7c71 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3644,7 +3644,7 @@ EXPORT_SYMBOL_GPL(md_rdev_init);
  */
 static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
 {
-	static struct md_rdev *claim_rdev; /* just for claiming the bdev */
+	static struct md_rdev claim_rdev; /* just for claiming the bdev */
 	struct md_rdev *rdev;
 	sector_t size;
 	int err;
@@ -3662,7 +3662,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 
 	rdev->bdev = blkdev_get_by_dev(newdev,
 			FMODE_READ | FMODE_WRITE | FMODE_EXCL,
-			super_format == -2 ? claim_rdev : rdev);
+			super_format == -2 ? &claim_rdev : rdev);
 	if (IS_ERR(rdev->bdev)) {
 		pr_warn("md: could not open device unknown-block(%u,%u).\n",
 			MAJOR(newdev), MINOR(newdev));
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index bf1c60edb7f9..b317ce6c4ec3 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -829,7 +829,23 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 			apple_nvme_remove_cq(anv);
 		}
 
-		nvme_disable_ctrl(&anv->ctrl, shutdown);
+		/*
+		 * Always disable the NVMe controller after shutdown.
+		 * We need to do this to bring it back up later anyway, and we
+		 * can't do it while the firmware is not running (e.g. in the
+		 * resume reset path before RTKit is initialized), so for Apple
+		 * controllers it makes sense to unconditionally do it here.
+		 * Additionally, this sequence of events is reliable, while
+		 * others (like disabling after bringing back the firmware on
+		 * resume) seem to run into trouble under some circumstances.
+		 *
+		 * Both U-Boot and m1n1 also use this convention (i.e. an ANS
+		 * NVMe controller is handed off with firmware shut down, in an
+		 * NVMe disabled state, after a clean shutdown).
+		 */
+		if (shutdown)
+			nvme_disable_ctrl(&anv->ctrl, shutdown);
+		nvme_disable_ctrl(&anv->ctrl, false);
 	}
 
 	WRITE_ONCE(anv->ioq.enabled, false);
@@ -985,11 +1001,11 @@ static void apple_nvme_reset_work(struct work_struct *work)
 		goto out;
 	}
 
-	if (anv->ctrl.ctrl_config & NVME_CC_ENABLE)
-		apple_nvme_disable(anv, false);
-
 	/* RTKit must be shut down cleanly for the (soft)-reset to work */
 	if (apple_rtkit_is_running(anv->rtk)) {
+		/* reset the controller if it is enabled */
+		if (anv->ctrl.ctrl_config & NVME_CC_ENABLE)
+			apple_nvme_disable(anv, false);
 		dev_dbg(anv->dev, "Trying to shut down RTKit before reset.");
 		ret = apple_rtkit_shutdown(anv->rtk);
 		if (ret)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index a2553b7d9bb8..1ff8843bc4b3 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1362,7 +1362,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	else
 		nvme_poll_irqdisable(nvmeq);
 
-	if (blk_mq_request_completed(req)) {
+	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, completion polled\n",
 			 req->tag, nvmeq->qid);