Merge tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - BFQ cleanups and fixes (Yu, Zhang, Yahu, Paolo)

 - blk-rq-qos completion fix (Tejun)

 - blk-cgroup merge fix (Tejun)

 - Add offline error return value to distinguish it from an IO error on
   the device (Song)

 - IO stats fixes (Zhang, Christoph)

 - blkcg refcount fixes (Ming, Yu)

 - Fix for indefinite dispatch loop softlockup (Shin'ichiro)

 - blk-mq hardware queue management improvements (Ming)

 - sbitmap dead code removal (Ming, John)

 - Plugging merge improvements (me)

 - Show blk-crypto capabilities in sysfs (Eric)

 - Multiple delayed queue run improvement (David)

 - Block throttling fixes (Ming)

 - Start deprecating auto module loading based on dev_t (Christoph)

 - bio allocation improvements (Christoph, Chaitanya)

 - Get rid of bio_devname (Christoph)

 - bio clone improvements (Christoph)

 - Block plugging improvements (Christoph)

 - Get rid of genhd.h header (Christoph)

 - Ensure drivers use appropriate flush helpers (Christoph)

 - Refcounting improvements (Christoph)

 - Queue initialization and teardown improvements (Ming, Christoph)

 - Misc fixes/improvements (Barry, Chaitanya, Colin, Dan, Jiapeng,
   Lukas, Nian, Yang, Eric, Chengming)

* tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block: (127 commits)
  block: cancel all throttled bios in del_gendisk()
  block: let blkcg_gq grab request queue's refcnt
  block: avoid use-after-free on throttle data
  block: limit request dispatch loop duration
  block/bfq-iosched: Fix spelling mistake "tenative" -> "tentative"
  sr: simplify the local variable initialization in sr_block_open()
  block: don't merge across cgroup boundaries if blkcg is enabled
  block: fix rq-qos breakage from skipping rq_qos_done_bio()
  block: flush plug based on hardware and software queue order
  block: ensure plug merging checks the correct queue at least once
  block: move rq_qos_exit() into disk_release()
  block: do more work in elevator_exit
  block: move blk_exit_queue into disk_release
  block: move q_usage_counter release into blk_queue_release
  block: don't remove hctx debugfs dir from blk_mq_exit_queue
  block: move blkcg initialization/destroy into disk allocation/release handler
  sr: implement ->free_disk to simplify refcounting
  sd: implement ->free_disk to simplify refcounting
  sd: delay calling free_opal_dev
  sd: call sd_zbc_release_disk before releasing the scsi_device reference
  ...

1 files changed, 14 insertions, 37 deletions

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 95df357ec009..dffeb8281c2d 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -28,14 +28,9 @@ struct seq_file;
  */
 struct sbitmap_word {
 	/**
-	 * @depth: Number of bits being used in @word/@cleared
-	 */
-	unsigned long depth;
-
-	/**
 	 * @word: word holding free bits
 	 */
-	unsigned long word ____cacheline_aligned_in_smp;
+	unsigned long word;
 
 	/**
 	 * @cleared: word holding cleared bits
@@ -140,7 +135,7 @@ struct sbitmap_queue {
 
 	/**
 	 * @min_shallow_depth: The minimum shallow depth which may be passed to
-	 * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
+	 * sbitmap_queue_get_shallow()
 	 */
 	unsigned int min_shallow_depth;
 };
@@ -164,6 +159,14 @@ struct sbitmap_queue {
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		      gfp_t flags, int node, bool round_robin, bool alloc_hint);
 
+/* sbitmap internal helper */
+static inline unsigned int __map_depth(const struct sbitmap *sb, int index)
+{
+	if (index == sb->map_nr - 1)
+		return sb->depth - (index << sb->shift);
+	return 1U << sb->shift;
+}
+
 /**
  * sbitmap_free() - Free memory used by a &struct sbitmap.
  * @sb: Bitmap to free.
@@ -251,7 +254,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb,
 	while (scanned < sb->depth) {
 		unsigned long word;
 		unsigned int depth = min_t(unsigned int,
-					   sb->map[index].depth - nr,
+					   __map_depth(sb, index) - nr,
 					   sb->depth - scanned);
 
 		scanned += depth;
@@ -460,7 +463,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
 					unsigned int *offset);
 
 /**
- * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
+ * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
  * sbitmap_queue, limiting the depth used from each word, with preemption
  * already disabled.
  * @sbq: Bitmap queue to allocate from.
@@ -472,8 +475,8 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
-				unsigned int shallow_depth);
+int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+			      unsigned int shallow_depth);
 
 /**
  * sbitmap_queue_get() - Try to allocate a free bit from a &struct
@@ -496,32 +499,6 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
 }
 
 /**
- * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
- * sbitmap_queue, limiting the depth used from each word.
- * @sbq: Bitmap queue to allocate from.
- * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
- *       sbitmap_queue_clear()).
- * @shallow_depth: The maximum number of bits to allocate from a single word.
- * See sbitmap_get_shallow().
- *
- * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
- * initializing @sbq.
- *
- * Return: Non-negative allocated bit number if successful, -1 otherwise.
- */
-static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
-					    unsigned int *cpu,
-					    unsigned int shallow_depth)
-{
-	int nr;
-
-	*cpu = get_cpu();
-	nr = __sbitmap_queue_get_shallow(sbq, shallow_depth);
-	put_cpu();
-	return nr;
-}
-
-/**
  * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the
  * minimum shallow depth that will be used.
  * @sbq: Bitmap queue in question.