sbitmap: introduce __sbitmap_for_each_set()

For blk-mq, we need to be able to iterate software queues starting
from any queue in a round robin fashion, so introduce this helper.
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

include/linux/sbitmap.h

@@ -211,10 +211,14 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb);
  */
 bool sbitmap_any_bit_clear(const struct sbitmap *sb);
 
+#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift)
+#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U))
+
 typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *);
 
 /**
- * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
+ * __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
+ * @start: Where to start the iteration.
  * @sb: Bitmap to iterate over.
  * @fn: Callback. Should return true to continue or false to break early.
  * @data: Pointer to pass to callback.
@@ -222,35 +226,61 @@ typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *);
  * This is inline even though it's non-trivial so that the function calls to the
  * callback will hopefully get optimized away.
  */
-static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn,
-					void *data)
+static inline void __sbitmap_for_each_set(struct sbitmap *sb,
+					  unsigned int start,
+					  sb_for_each_fn fn, void *data)
 {
-	unsigned int i;
+	unsigned int index;
+	unsigned int nr;
+	unsigned int scanned = 0;
 
-	for (i = 0; i < sb->map_nr; i++) {
-		struct sbitmap_word *word = &sb->map[i];
-		unsigned int off, nr;
+	if (start >= sb->depth)
+		start = 0;
+	index = SB_NR_TO_INDEX(sb, start);
+	nr = SB_NR_TO_BIT(sb, start);
 
+	while (scanned < sb->depth) {
+		struct sbitmap_word *word = &sb->map[index];
+		unsigned int depth = min_t(unsigned int, word->depth - nr,
+					   sb->depth - scanned);
+
+		scanned += depth;
 		if (!word->word)
-			continue;
+			goto next;
 
-		nr = 0;
-		off = i << sb->shift;
+		/*
+		 * On the first iteration of the outer loop, we need to add the
+		 * bit offset back to the size of the word for find_next_bit().
+		 * On all other iterations, nr is zero, so this is a noop.
+		 */
+		depth += nr;
 		while (1) {
-			nr = find_next_bit(&word->word, word->depth, nr);
-			if (nr >= word->depth)
+			nr = find_next_bit(&word->word, depth, nr);
+			if (nr >= depth)
 				break;
-
-			if (!fn(sb, off + nr, data))
+			if (!fn(sb, (index << sb->shift) + nr, data))
 				return;
 
 			nr++;
 		}
+next:
+		nr = 0;
+		if (++index >= sb->map_nr)
+			index = 0;
 	}
 }
 
-#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift)
-#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U))
+/**
+ * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
+ * @sb: Bitmap to iterate over.
+ * @fn: Callback. Should return true to continue or false to break early.
+ * @data: Pointer to pass to callback.
+ */
+static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn,
+					void *data)
+{
+	__sbitmap_for_each_set(sb, 0, fn, data);
+}
 
 static inline unsigned long *__sbitmap_word(struct sbitmap *sb,
 					    unsigned int bitnr)