Merge tag 'for-5.14/drivers-2021-06-29' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Pretty calm round, mostly just NVMe and a bit of MD:

   - NVMe updates (via Christoph)
        - improve the APST configuration algorithm (Alexey Bogoslavsky)
        - look for StorageD3Enable on companion ACPI device
          (Mario Limonciello)
        - allow selecting the network interface for TCP connections
          (Martin Belanger)
        - misc cleanups (Amit Engel, Chaitanya Kulkarni, Colin Ian King,
          Christoph)
        - move the ACPI StorageD3 code to drivers/acpi/ and add quirks
          for certain AMD CPUs (Mario Limonciello)
        - zoned device support for nvmet (Chaitanya Kulkarni)
        - fix the rules for changing the serial number in nvmet
          (Noam Gottlieb)
        - various small fixes and cleanups (Dan Carpenter, JK Kim,
          Chaitanya Kulkarni, Hannes Reinecke, Wesley Sheng, Geert
          Uytterhoeven, Daniel Wagner)

   - MD updates (Via Song)
        - iostats rewrite (Guoqing Jiang)
        - raid5 lock contention optimization (Gal Ofri)

   - Fall through warning fix (Gustavo)

   - Misc fixes (Gustavo, Jiapeng)"

* tag 'for-5.14/drivers-2021-06-29' of git://git.kernel.dk/linux-block: (78 commits)
  nvmet: use NVMET_MAX_NAMESPACES to set nn value
  loop: Fix missing discard support when using LOOP_CONFIGURE
  nvme.h: add missing nvme_lba_range_type endianness annotations
  nvme: remove zeroout memset call for struct
  nvme-pci: remove zeroout memset call for struct
  nvmet: remove zeroout memset call for struct
  nvmet: add ZBD over ZNS backend support
  nvmet: add Command Set Identifier support
  nvmet: add nvmet_req_bio put helper for backends
  nvmet: add req cns error complete helper
  block: export blk_next_bio()
  nvmet: remove local variable
  nvmet: use nvme status value directly
  nvmet: use u32 type for the local variable nsid
  nvmet: use u32 for nvmet_subsys max_nsid
  nvmet: use req->cmd directly in file-ns fast path
  nvmet: use req->cmd directly in bdev-ns fast path
  nvmet: make ver stable once connection established
  nvmet: allow mn change if subsys not discovered
  nvmet: make sn stable once connection was established
  ...

1 files changed, 65 insertions, 51 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index d806be8cc210..ae8fe54ea358 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -441,30 +441,6 @@ check_suspended:
 }
 EXPORT_SYMBOL(md_handle_request);
 
-struct md_io {
-	struct mddev *mddev;
-	bio_end_io_t *orig_bi_end_io;
-	void *orig_bi_private;
-	struct block_device *orig_bi_bdev;
-	unsigned long start_time;
-};
-
-static void md_end_io(struct bio *bio)
-{
-	struct md_io *md_io = bio->bi_private;
-	struct mddev *mddev = md_io->mddev;
-
-	bio_end_io_acct_remapped(bio, md_io->start_time, md_io->orig_bi_bdev);
-
-	bio->bi_end_io = md_io->orig_bi_end_io;
-	bio->bi_private = md_io->orig_bi_private;
-
-	mempool_free(md_io, &mddev->md_io_pool);
-
-	if (bio->bi_end_io)
-		bio->bi_end_io(bio);
-}
-
 static blk_qc_t md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
@@ -489,21 +465,6 @@ static blk_qc_t md_submit_bio(struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_end_io != md_end_io) {
-		struct md_io *md_io;
-
-		md_io = mempool_alloc(&mddev->md_io_pool, GFP_NOIO);
-		md_io->mddev = mddev;
-		md_io->orig_bi_end_io = bio->bi_end_io;
-		md_io->orig_bi_private = bio->bi_private;
-		md_io->orig_bi_bdev = bio->bi_bdev;
-
-		bio->bi_end_io = md_end_io;
-		bio->bi_private = md_io;
-
-		md_io->start_time = bio_start_io_acct(bio);
-	}
-
 	/* bio could be mergeable after passing to underlayer */
 	bio->bi_opf &= ~REQ_NOMERGE;
 
@@ -824,7 +785,7 @@ out_free_new:
 	return ERR_PTR(error);
 }
 
-static struct attribute_group md_redundancy_group;
+static const struct attribute_group md_redundancy_group;
 
 void mddev_unlock(struct mddev *mddev)
 {
@@ -841,7 +802,7 @@ void mddev_unlock(struct mddev *mddev)
 		 * test it under the same mutex to ensure its correct value
 		 * is seen.
 		 */
-		struct attribute_group *to_remove = mddev->to_remove;
+		const struct attribute_group *to_remove = mddev->to_remove;
 		mddev->to_remove = NULL;
 		mddev->sysfs_active = 1;
 		mutex_unlock(&mddev->reconfig_mutex);
@@ -2379,7 +2340,15 @@ int md_integrity_register(struct mddev *mddev)
 			       bdev_get_integrity(reference->bdev));
 
 	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
-	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
+	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
+	    (mddev->level != 1 && mddev->level != 10 &&
+	     bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE))) {
+		/*
+		 * No need to handle the failure of bioset_integrity_create,
+		 * because the function is called by md_run() -> pers->run(),
+		 * md_run calls bioset_exit -> bioset_integrity_free in case
+		 * of failure case.
+		 */
 		pr_err("md: failed to create integrity pool for %s\n",
 		       mdname(mddev));
 		return -EINVAL;
@@ -5538,7 +5507,7 @@ static struct attribute *md_redundancy_attrs[] = {
 	&md_degraded.attr,
 	NULL,
 };
-static struct attribute_group md_redundancy_group = {
+static const struct attribute_group md_redundancy_group = {
 	.name = NULL,
 	.attrs = md_redundancy_attrs,
 };
@@ -5606,7 +5575,8 @@ static void md_free(struct kobject *ko)
 
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
-	mempool_exit(&mddev->md_io_pool);
+	if (mddev->level != 1 && mddev->level != 10)
+		bioset_exit(&mddev->io_acct_set);
 	kfree(mddev);
 }
 
@@ -5703,11 +5673,6 @@ static int md_alloc(dev_t dev, char *name)
 		 */
 		mddev->hold_active = UNTIL_STOP;
 
-	error = mempool_init_kmalloc_pool(&mddev->md_io_pool, BIO_POOL_SIZE,
-					  sizeof(struct md_io));
-	if (error)
-		goto abort;
-
 	error = -ENOMEM;
 	disk = blk_alloc_disk(NUMA_NO_NODE);
 	if (!disk)
@@ -5900,7 +5865,14 @@ int md_run(struct mddev *mddev)
 	if (!bioset_initialized(&mddev->sync_set)) {
 		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
-			return err;
+			goto exit_bio_set;
+	}
+	if (mddev->level != 1 && mddev->level != 10 &&
+	    !bioset_initialized(&mddev->io_acct_set)) {
+		err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
+				  offsetof(struct md_io_acct, bio_clone), 0);
+		if (err)
+			goto exit_sync_set;
 	}
 
 	spin_lock(&pers_lock);
@@ -6028,6 +6000,7 @@ int md_run(struct mddev *mddev)
 			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
+		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6077,8 +6050,12 @@ bitmap_abort:
 	module_put(pers->owner);
 	md_bitmap_destroy(mddev);
 abort:
-	bioset_exit(&mddev->bio_set);
+	if (mddev->level != 1 && mddev->level != 10)
+		bioset_exit(&mddev->io_acct_set);
+exit_sync_set:
 	bioset_exit(&mddev->sync_set);
+exit_bio_set:
+	bioset_exit(&mddev->bio_set);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -6302,6 +6279,8 @@ void md_stop(struct mddev *mddev)
 	__md_stop(mddev);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
+	if (mddev->level != 1 && mddev->level != 10)
+		bioset_exit(&mddev->io_acct_set);
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
@@ -8606,6 +8585,41 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+static void md_end_io_acct(struct bio *bio)
+{
+	struct md_io_acct *md_io_acct = bio->bi_private;
+	struct bio *orig_bio = md_io_acct->orig_bio;
+
+	orig_bio->bi_status = bio->bi_status;
+
+	bio_end_io_acct(orig_bio, md_io_acct->start_time);
+	bio_put(bio);
+	bio_endio(orig_bio);
+}
+
+/*
+ * Used by personalities that don't already clone the bio and thus can't
+ * easily add the timestamp to their extended bio structure.
+ */
+void md_account_bio(struct mddev *mddev, struct bio **bio)
+{
+	struct md_io_acct *md_io_acct;
+	struct bio *clone;
+
+	if (!blk_queue_io_stat((*bio)->bi_bdev->bd_disk->queue))
+		return;
+
+	clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set);
+	md_io_acct = container_of(clone, struct md_io_acct, bio_clone);
+	md_io_acct->orig_bio = *bio;
+	md_io_acct->start_time = bio_start_io_acct(*bio);
+
+	clone->bi_end_io = md_end_io_acct;
+	clone->bi_private = md_io_acct;
+	*bio = clone;
+}
+EXPORT_SYMBOL_GPL(md_account_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before