Merge tag 'for-5.19/block-2022-05-22' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Here are the core block changes for 5.19. This contains:

   - blk-throttle accounting fix (Laibin)

   - Series removing redundant assignments (Michal)

   - Expose bio cache via the bio_set, so that DM can use it (Mike)

   - Finish off the bio allocation interface cleanups by dealing with
     the weirdest member of the family. bio_kmalloc combines a kmalloc
     for the bio and bio_vecs with a hidden bio_init call and magic
     cleanup semantics (Christoph)

   - Clean up the block layer API so that APIs consumed by file systems
     are (almost) only struct block_device based, so that file systems
     don't have to poke into block layer internals like the
     request_queue (Christoph)

   - Clean up the blk_execute_rq* API (Christoph)

   - Clean up various lose end in the blk-cgroup code to make it easier
     to follow in preparation of reworking the blkcg assignment for bios
     (Christoph)

   - Fix use-after-free issues in BFQ when processes with merged queues
     get moved to different cgroups (Jan)

   - BFQ fixes (Jan)

   - Various fixes and cleanups (Bart, Chengming, Fanjun, Julia, Ming,
     Wolfgang, me)"

* tag 'for-5.19/block-2022-05-22' of git://git.kernel.dk/linux-block: (83 commits)
  blk-mq: fix typo in comment
  bfq: Remove bfq_requeue_request_body()
  bfq: Remove superfluous conversion from RQ_BIC()
  bfq: Allow current waker to defend against a tentative one
  bfq: Relax waker detection for shared queues
  blk-cgroup: delete rcu_read_lock_held() WARN_ON_ONCE()
  blk-throttle: Set BIO_THROTTLED when bio has been throttled
  blk-cgroup: Remove unnecessary rcu_read_lock/unlock()
  blk-cgroup: always terminate io.stat lines
  block, bfq: make bfq_has_work() more accurate
  block, bfq: protect 'bfqd->queued' by 'bfqd->lock'
  block: cleanup the VM accounting in submit_bio
  block: Fix the bio.bi_opf comment
  block: reorder the REQ_ flags
  blk-iocost: combine local_stat and desc_stat to stat
  block: improve the error message from bio_check_eod
  block: allow passing a NULL bdev to bio_alloc_clone/bio_init_clone
  block: remove superfluous calls to blkcg_bio_issue_init
  kthread: unexport kthread_blkcg
  blk-cgroup: cleanup blkcg_maybe_throttle_current
  ...

1 files changed, 42 insertions, 52 deletions

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index b7216c186ba4..a6280dcb3767 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1204,50 +1204,40 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
 }
 
 static void decide_on_discard_support(struct drbd_device *device,
-			struct request_queue *q,
-			struct request_queue *b,
-			bool discard_zeroes_if_aligned)
+		struct drbd_backing_dev *bdev)
 {
-	/* q = drbd device queue (device->rq_queue)
-	 * b = backing device queue (device->ldev->backing_bdev->bd_disk->queue),
-	 *     or NULL if diskless
-	 */
-	struct drbd_connection *connection = first_peer_device(device)->connection;
-	bool can_do = b ? blk_queue_discard(b) : true;
-
-	if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) {
-		can_do = false;
-		drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n");
-	}
-	if (can_do) {
-		/* We don't care for the granularity, really.
-		 * Stacking limits below should fix it for the local
-		 * device.  Whether or not it is a suitable granularity
-		 * on the remote device is not our problem, really. If
-		 * you care, you need to use devices with similar
-		 * topology on all peers. */
-		blk_queue_discard_granularity(q, 512);
-		q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-		q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection);
-	} else {
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
-		blk_queue_discard_granularity(q, 0);
-		q->limits.max_discard_sectors = 0;
-		q->limits.max_write_zeroes_sectors = 0;
-	}
-}
+	struct drbd_connection *connection =
+		first_peer_device(device)->connection;
+	struct request_queue *q = device->rq_queue;
 
-static void fixup_discard_if_not_supported(struct request_queue *q)
-{
-	/* To avoid confusion, if this queue does not support discard, clear
-	 * max_discard_sectors, which is what lsblk -D reports to the user.
-	 * Older kernels got this wrong in "stack limits".
-	 * */
-	if (!blk_queue_discard(q)) {
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_discard_granularity(q, 0);
+	if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev))
+		goto not_supported;
+
+	if (connection->cstate >= C_CONNECTED &&
+	    !(connection->agreed_features & DRBD_FF_TRIM)) {
+		drbd_info(connection,
+			"peer DRBD too old, does not support TRIM: disabling discards\n");
+		goto not_supported;
 	}
+
+	/*
+	 * We don't care for the granularity, really.
+	 *
+	 * Stacking limits below should fix it for the local device.  Whether or
+	 * not it is a suitable granularity on the remote device is not our
+	 * problem, really. If you care, you need to use devices with similar
+	 * topology on all peers.
+	 */
+	blk_queue_discard_granularity(q, 512);
+	q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
+	q->limits.max_write_zeroes_sectors =
+		drbd_max_discard_sectors(connection);
+	return;
+
+not_supported:
+	blk_queue_discard_granularity(q, 0);
+	q->limits.max_discard_sectors = 0;
+	q->limits.max_write_zeroes_sectors = 0;
 }
 
 static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
@@ -1273,7 +1263,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 	unsigned int max_segments = 0;
 	struct request_queue *b = NULL;
 	struct disk_conf *dc;
-	bool discard_zeroes_if_aligned = true;
 
 	if (bdev) {
 		b = bdev->backing_bdev->bd_disk->queue;
@@ -1282,7 +1271,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 		rcu_read_lock();
 		dc = rcu_dereference(device->ldev->disk_conf);
 		max_segments = dc->max_bio_bvecs;
-		discard_zeroes_if_aligned = dc->discard_zeroes_if_aligned;
 		rcu_read_unlock();
 
 		blk_set_stacking_limits(&q->limits);
@@ -1292,13 +1280,12 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 	/* This is the workaround for "bio would need to, but cannot, be split" */
 	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
 	blk_queue_segment_boundary(q, PAGE_SIZE-1);
-	decide_on_discard_support(device, q, b, discard_zeroes_if_aligned);
+	decide_on_discard_support(device, bdev);
 
 	if (b) {
 		blk_stack_limits(&q->limits, &b->limits, 0);
 		disk_update_readahead(device->vdisk);
 	}
-	fixup_discard_if_not_supported(q);
 	fixup_write_zeroes(device, q);
 }
 
@@ -1437,14 +1424,14 @@ static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b)
 static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *disk_conf,
 			       struct drbd_backing_dev *nbc)
 {
-	struct request_queue * const q = nbc->backing_bdev->bd_disk->queue;
+	struct block_device *bdev = nbc->backing_bdev;
 
 	if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
 		disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
 	if (disk_conf->al_extents > drbd_al_extents_max(nbc))
 		disk_conf->al_extents = drbd_al_extents_max(nbc);
 
-	if (!blk_queue_discard(q)) {
+	if (!bdev_max_discard_sectors(bdev)) {
 		if (disk_conf->rs_discard_granularity) {
 			disk_conf->rs_discard_granularity = 0; /* disable feature */
 			drbd_info(device, "rs_discard_granularity feature disabled\n");
@@ -1453,16 +1440,19 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 
 	if (disk_conf->rs_discard_granularity) {
 		int orig_value = disk_conf->rs_discard_granularity;
+		sector_t discard_size = bdev_max_discard_sectors(bdev) << 9;
+		unsigned int discard_granularity = bdev_discard_granularity(bdev);
 		int remainder;
 
-		if (q->limits.discard_granularity > disk_conf->rs_discard_granularity)
-			disk_conf->rs_discard_granularity = q->limits.discard_granularity;
+		if (discard_granularity > disk_conf->rs_discard_granularity)
+			disk_conf->rs_discard_granularity = discard_granularity;
 
-		remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity;
+		remainder = disk_conf->rs_discard_granularity %
+				discard_granularity;
 		disk_conf->rs_discard_granularity += remainder;
 
-		if (disk_conf->rs_discard_granularity > q->limits.max_discard_sectors << 9)
-			disk_conf->rs_discard_granularity = q->limits.max_discard_sectors << 9;
+		if (disk_conf->rs_discard_granularity > discard_size)
+			disk_conf->rs_discard_granularity = discard_size;
 
 		if (disk_conf->rs_discard_granularity != orig_value)
 			drbd_info(device, "rs_discard_granularity changed to %d\n",