Merge tag 'block-6.17-20250808' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - MD pull request via Yu:
      - mddev null-ptr-dereference fix, by Erkun
      - md-cluster fail to remove the faulty disk regression fix, by
        Heming
      - minor cleanup, by Li Nan and Jinchao
      - mdadm lifetime regression fix reported by syzkaller, by Yu Kuai

 - MD pull request via Christoph
      - add support for getting the FDP featuee in fabrics passthru path
        (Nitesh Shetty)
      - add capability to connect to an administrative controller
        (Kamaljit Singh)
      - fix a leak on sgl setup error (Keith Busch)
      - initialize discovery subsys after debugfs is initialized
        (Mohamed Khalfella)
      - fix various comment typos (Bjorn Helgaas)
      - remove unneeded semicolons (Jiapeng Chong)

 - nvmet debugfs ordering issue fix

 - Fix UAF in the tag_set in zloop

 - Ensure sbitmap shallow depth covers entire set

 - Reduce lock roundtrips in io context lookup

 - Move scheduler tags alloc/free out of elevator and freeze lock, to
   fix some lockdep found issues

 - Improve robustness of queue limits checking

 - Fix a regression with IO priorities, if no io context exists

* tag 'block-6.17-20250808' of git://git.kernel.dk/linux: (26 commits)
  lib/sbitmap: make sbitmap_get_shallow() internal
  lib/sbitmap: convert shallow_depth from one word to the whole sbitmap
  nvmet: exit debugfs after discovery subsystem exits
  block, bfq: Reorder struct bfq_iocq_bfqq_data
  md: make rdev_addable usable for rcu mode
  md/raid1: remove struct pool_info and related code
  md/raid1: change r1conf->r1bio_pool to a pointer type
  block: ensure discard_granularity is zero when discard is not supported
  zloop: fix KASAN use-after-free of tag set
  block: Fix default IO priority if there is no IO context
  nvme: fix various comment typos
  nvme-auth: remove unneeded semicolon
  nvme-pci: fix leak on sgl setup error
  nvmet: initialize discovery subsys after debugfs is initialized
  nvme: add capability to connect to an administrative controller
  nvmet: add support for FDP in fabrics passthru path
  md: rename recovery_cp to resync_offset
  md/md-cluster: handle REMOVE message earlier
  md: fix create on open mddev lifetime regression
  block: fix potential deadlock while running nr_hw_queue update
  ...

1 files changed, 45 insertions, 29 deletions

diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index d3412984170c..4d188d05db15 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -208,8 +208,28 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
 	return nr;
 }
 
+static unsigned int __map_depth_with_shallow(const struct sbitmap *sb,
+					     int index,
+					     unsigned int shallow_depth)
+{
+	u64 shallow_word_depth;
+	unsigned int word_depth, reminder;
+
+	word_depth = __map_depth(sb, index);
+	if (shallow_depth >= sb->depth)
+		return word_depth;
+
+	shallow_word_depth = word_depth * shallow_depth;
+	reminder = do_div(shallow_word_depth, sb->depth);
+
+	if (reminder >= (index + 1) * word_depth)
+		shallow_word_depth++;
+
+	return (unsigned int)shallow_word_depth;
+}
+
 static int sbitmap_find_bit(struct sbitmap *sb,
-			    unsigned int depth,
+			    unsigned int shallow_depth,
 			    unsigned int index,
 			    unsigned int alloc_hint,
 			    bool wrap)
@@ -218,12 +238,12 @@ static int sbitmap_find_bit(struct sbitmap *sb,
 	int nr = -1;
 
 	for (i = 0; i < sb->map_nr; i++) {
-		nr = sbitmap_find_bit_in_word(&sb->map[index],
-					      min_t(unsigned int,
-						    __map_depth(sb, index),
-						    depth),
-					      alloc_hint, wrap);
+		unsigned int depth = __map_depth_with_shallow(sb, index,
+							      shallow_depth);
 
+		if (depth)
+			nr = sbitmap_find_bit_in_word(&sb->map[index], depth,
+						      alloc_hint, wrap);
 		if (nr != -1) {
 			nr += index << sb->shift;
 			break;
@@ -287,7 +307,22 @@ static int __sbitmap_get_shallow(struct sbitmap *sb,
 	return sbitmap_find_bit(sb, shallow_depth, index, alloc_hint, true);
 }
 
-int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
+/**
+ * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
+ * limiting the depth used from each word.
+ * @sb: Bitmap to allocate from.
+ * @shallow_depth: The maximum number of bits to allocate from the bitmap.
+ *
+ * This rather specific operation allows for having multiple users with
+ * different allocation limits. E.g., there can be a high-priority class that
+ * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
+ * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority
+ * class can only allocate half of the total bits in the bitmap, preventing it
+ * from starving out the high-priority class.
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+static int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
 {
 	int nr;
 	unsigned int hint, depth;
@@ -302,7 +337,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
 
 	return nr;
 }
-EXPORT_SYMBOL_GPL(sbitmap_get_shallow);
 
 bool sbitmap_any_bit_set(const struct sbitmap *sb)
 {
@@ -406,27 +440,9 @@ EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
 static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
 					unsigned int depth)
 {
-	unsigned int wake_batch;
-	unsigned int shallow_depth;
-
-	/*
-	 * Each full word of the bitmap has bits_per_word bits, and there might
-	 * be a partial word. There are depth / bits_per_word full words and
-	 * depth % bits_per_word bits left over. In bitwise arithmetic:
-	 *
-	 * bits_per_word = 1 << shift
-	 * depth / bits_per_word = depth >> shift
-	 * depth % bits_per_word = depth & ((1 << shift) - 1)
-	 *
-	 * Each word can be limited to sbq->min_shallow_depth bits.
-	 */
-	shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
-	depth = ((depth >> sbq->sb.shift) * shallow_depth +
-		 min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
-	wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
-			     SBQ_WAKE_BATCH);
-
-	return wake_batch;
+	return clamp_t(unsigned int,
+		       min(depth, sbq->min_shallow_depth) / SBQ_WAIT_QUEUES,
+		       1, SBQ_WAKE_BATCH);
 }
 
 int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,