Merge tag 'for-5.15/block-2021-08-30' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Nothing major in here - lots of good cleanups and tech debt handling,
  which is also evident in the diffstats. In particular:

   - Add disk sequence numbers (Matteo)

   - Discard merge fix (Ming)

   - Relax disk zoned reporting restrictions (Niklas)

   - Bio error handling zoned leak fix (Pavel)

   - Start of proper add_disk() error handling (Luis, Christoph)

   - blk crypto fix (Eric)

   - Non-standard GPT location support (Dmitry)

   - IO priority improvements and cleanups (Damien)o

   - blk-throtl improvements (Chunguang)

   - diskstats_show() stack reduction (Abd-Alrhman)

   - Loop scheduler selection (Bart)

   - Switch block layer to use kmap_local_page() (Christoph)

   - Remove obsolete disk_name helper (Christoph)

   - block_device refcounting improvements (Christoph)

   - Ensure gendisk always has a request queue reference (Christoph)

   - Misc fixes/cleanups (Shaokun, Oliver, Guoqing)"

* tag 'for-5.15/block-2021-08-30' of git://git.kernel.dk/linux-block: (129 commits)
  sg: pass the device name to blk_trace_setup
  block, bfq: cleanup the repeated declaration
  blk-crypto: fix check for too-large dun_bytes
  blk-zoned: allow BLKREPORTZONE without CAP_SYS_ADMIN
  blk-zoned: allow zone management send operations without CAP_SYS_ADMIN
  block: mark blkdev_fsync static
  block: refine the disk_live check in del_gendisk
  mmc: sdhci-tegra: Enable MMC_CAP2_ALT_GPT_TEGRA
  mmc: block: Support alternative_gpt_sector() operation
  partitions/efi: Support non-standard GPT location
  block: Add alternative_gpt_sector() operation
  bio: fix page leak bio_add_hw_page failure
  block: remove CONFIG_DEBUG_BLOCK_EXT_DEVT
  block: remove a pointless call to MINOR() in device_add_disk
  null_blk: add error handling support for add_disk()
  virtio_blk: add error handling support for add_disk()
  block: add error handling for device_add_disk / add_disk
  block: return errors from disk_alloc_events
  block: return errors from blk_integrity_add
  block: call blk_register_queue earlier in device_add_disk
  ...

1 files changed, 32 insertions, 0 deletions

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index b1b22d863bdf..55c49015e533 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -178,6 +178,9 @@ struct throtl_grp {
 	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
 	unsigned long bio_cnt_reset_time;
 
+	atomic_t io_split_cnt[2];
+	atomic_t last_io_split_cnt[2];
+
 	struct blkg_rwstat stat_bytes;
 	struct blkg_rwstat stat_ios;
 };
@@ -777,6 +780,8 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
 	tg->bytes_disp[rw] = 0;
 	tg->io_disp[rw] = 0;
 
+	atomic_set(&tg->io_split_cnt[rw], 0);
+
 	/*
 	 * Previous slice has expired. We must have trimmed it after last
 	 * bio dispatch. That means since start of last slice, we never used
@@ -799,6 +804,9 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 	tg->io_disp[rw] = 0;
 	tg->slice_start[rw] = jiffies;
 	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
+
+	atomic_set(&tg->io_split_cnt[rw], 0);
+
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -1031,6 +1039,9 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 				jiffies + tg->td->throtl_slice);
 	}
 
+	if (iops_limit != UINT_MAX)
+		tg->io_disp[rw] += atomic_xchg(&tg->io_split_cnt[rw], 0);
+
 	if (tg_with_in_bps_limit(tg, bio, bps_limit, &bps_wait) &&
 	    tg_with_in_iops_limit(tg, bio, iops_limit, &iops_wait)) {
 		if (wait)
@@ -2052,12 +2063,14 @@ static void throtl_downgrade_check(struct throtl_grp *tg)
 	}
 
 	if (tg->iops[READ][LIMIT_LOW]) {
+		tg->last_io_disp[READ] += atomic_xchg(&tg->last_io_split_cnt[READ], 0);
 		iops = tg->last_io_disp[READ] * HZ / elapsed_time;
 		if (iops >= tg->iops[READ][LIMIT_LOW])
 			tg->last_low_overflow_time[READ] = now;
 	}
 
 	if (tg->iops[WRITE][LIMIT_LOW]) {
+		tg->last_io_disp[WRITE] += atomic_xchg(&tg->last_io_split_cnt[WRITE], 0);
 		iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
 		if (iops >= tg->iops[WRITE][LIMIT_LOW])
 			tg->last_low_overflow_time[WRITE] = now;
@@ -2176,6 +2189,25 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 }
 #endif
 
+void blk_throtl_charge_bio_split(struct bio *bio)
+{
+	struct blkcg_gq *blkg = bio->bi_blkg;
+	struct throtl_grp *parent = blkg_to_tg(blkg);
+	struct throtl_service_queue *parent_sq;
+	bool rw = bio_data_dir(bio);
+
+	do {
+		if (!parent->has_rules[rw])
+			break;
+
+		atomic_inc(&parent->io_split_cnt[rw]);
+		atomic_inc(&parent->last_io_split_cnt[rw]);
+
+		parent_sq = parent->service_queue.parent_sq;
+		parent = sq_to_tg(parent_sq);
+	} while (parent);
+}
+
 bool blk_throtl_bio(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;