1 files changed, 126 insertions, 106 deletions

diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 1fcede228fa2..4d188d05db15 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -60,12 +60,30 @@ static inline void update_alloc_hint_after_get(struct sbitmap *sb,
 /*
  * See if we have deferred clears that we can batch move
  */
-static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
+static inline bool sbitmap_deferred_clear(struct sbitmap_word *map,
+		unsigned int depth, unsigned int alloc_hint, bool wrap)
 {
-	unsigned long mask;
+	unsigned long mask, word_mask;
 
-	if (!READ_ONCE(map->cleared))
-		return false;
+	guard(raw_spinlock_irqsave)(&map->swap_lock);
+
+	if (!map->cleared) {
+		if (depth == 0)
+			return false;
+
+		word_mask = (~0UL) >> (BITS_PER_LONG - depth);
+		/*
+		 * The current behavior is to always retry after moving
+		 * ->cleared to word, and we change it to retry in case
+		 * of any free bits. To avoid an infinite loop, we need
+		 * to take wrap & alloc_hint into account, otherwise a
+		 * soft lockup may occur.
+		 */
+		if (!wrap && alloc_hint)
+			word_mask &= ~((1UL << alloc_hint) - 1);
+
+		return (READ_ONCE(map->word) & word_mask) != word_mask;
+	}
 
 	/*
 	 * First get a stable cleared mask, setting the old mask to 0.
@@ -85,6 +103,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		      bool alloc_hint)
 {
 	unsigned int bits_per_word;
+	int i;
 
 	if (shift < 0)
 		shift = sbitmap_calculate_shift(depth);
@@ -116,6 +135,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		return -ENOMEM;
 	}
 
+	for (i = 0; i < sb->map_nr; i++)
+		raw_spin_lock_init(&sb->map[i].swap_lock);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sbitmap_init_node);
@@ -126,7 +148,7 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth)
 	unsigned int i;
 
 	for (i = 0; i < sb->map_nr; i++)
-		sbitmap_deferred_clear(&sb->map[i]);
+		sbitmap_deferred_clear(&sb->map[i], 0, 0, 0);
 
 	sb->depth = depth;
 	sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
@@ -167,43 +189,61 @@ static int __sbitmap_get_word(unsigned long *word, unsigned long depth,
 	return nr;
 }
 
-static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index,
-				     unsigned int alloc_hint)
+static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
+				    unsigned int depth,
+				    unsigned int alloc_hint,
+				    bool wrap)
 {
-	struct sbitmap_word *map = &sb->map[index];
 	int nr;
 
 	do {
-		nr = __sbitmap_get_word(&map->word, __map_depth(sb, index),
-					alloc_hint, !sb->round_robin);
+		nr = __sbitmap_get_word(&map->word, depth,
+					alloc_hint, wrap);
 		if (nr != -1)
 			break;
-		if (!sbitmap_deferred_clear(map))
+		if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap))
 			break;
 	} while (1);
 
 	return nr;
 }
 
-static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint)
+static unsigned int __map_depth_with_shallow(const struct sbitmap *sb,
+					     int index,
+					     unsigned int shallow_depth)
 {
-	unsigned int i, index;
-	int nr = -1;
+	u64 shallow_word_depth;
+	unsigned int word_depth, reminder;
 
-	index = SB_NR_TO_INDEX(sb, alloc_hint);
+	word_depth = __map_depth(sb, index);
+	if (shallow_depth >= sb->depth)
+		return word_depth;
 
-	/*
-	 * Unless we're doing round robin tag allocation, just use the
-	 * alloc_hint to find the right word index. No point in looping
-	 * twice in find_next_zero_bit() for that case.
-	 */
-	if (sb->round_robin)
-		alloc_hint = SB_NR_TO_BIT(sb, alloc_hint);
-	else
-		alloc_hint = 0;
+	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 shallow_depth,
+			    unsigned int index,
+			    unsigned int alloc_hint,
+			    bool wrap)
+{
+	unsigned int i;
+	int nr = -1;
 
 	for (i = 0; i < sb->map_nr; i++) {
-		nr = sbitmap_find_bit_in_index(sb, index, alloc_hint);
+		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;
@@ -218,6 +258,26 @@ static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint)
 	return nr;
 }
 
+static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint)
+{
+	unsigned int index;
+
+	index = SB_NR_TO_INDEX(sb, alloc_hint);
+
+	/*
+	 * Unless we're doing round robin tag allocation, just use the
+	 * alloc_hint to find the right word index. No point in looping
+	 * twice in find_next_zero_bit() for that case.
+	 */
+	if (sb->round_robin)
+		alloc_hint = SB_NR_TO_BIT(sb, alloc_hint);
+	else
+		alloc_hint = 0;
+
+	return sbitmap_find_bit(sb, UINT_MAX, index, alloc_hint,
+				!sb->round_robin);
+}
+
 int sbitmap_get(struct sbitmap *sb)
 {
 	int nr;
@@ -239,40 +299,30 @@ static int __sbitmap_get_shallow(struct sbitmap *sb,
 				 unsigned int alloc_hint,
 				 unsigned long shallow_depth)
 {
-	unsigned int i, index;
-	int nr = -1;
+	unsigned int index;
 
 	index = SB_NR_TO_INDEX(sb, alloc_hint);
-
-	for (i = 0; i < sb->map_nr; i++) {
-again:
-		nr = __sbitmap_get_word(&sb->map[index].word,
-					min_t(unsigned int,
-					      __map_depth(sb, index),
-					      shallow_depth),
-					SB_NR_TO_BIT(sb, alloc_hint), true);
-		if (nr != -1) {
-			nr += index << sb->shift;
-			break;
-		}
-
-		if (sbitmap_deferred_clear(&sb->map[index]))
-			goto again;
-
-		/* Jump to next index. */
-		index++;
-		alloc_hint = index << sb->shift;
-
-		if (index >= sb->map_nr) {
-			index = 0;
-			alloc_hint = 0;
-		}
-	}
-
-	return nr;
-}
-
-int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
+	alloc_hint = SB_NR_TO_BIT(sb, alloc_hint);
+
+	return sbitmap_find_bit(sb, shallow_depth, index, alloc_hint, true);
+}
+
+/**
+ * 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;
@@ -287,7 +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)
 {
@@ -391,32 +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;
-
-	/*
-	 * For each batch, we wake up one queue. We need to make sure that our
-	 * batch size is small enough that the full depth of the bitmap,
-	 * potentially limited by a shallow depth, is enough to wake up all of
-	 * the queues.
-	 *
-	 * 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,
@@ -464,13 +490,10 @@ void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
 					    unsigned int users)
 {
 	unsigned int wake_batch;
-	unsigned int min_batch;
 	unsigned int depth = (sbq->sb.depth + users - 1) / users;
 
-	min_batch = sbq->sb.depth >= (4 * SBQ_WAIT_QUEUES) ? 4 : 1;
-
 	wake_batch = clamp_val(depth / SBQ_WAIT_QUEUES,
-			min_batch, SBQ_WAKE_BATCH);
+			1, SBQ_WAKE_BATCH);
 
 	WRITE_ONCE(sbq->wake_batch, wake_batch);
 }
@@ -509,23 +532,21 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
 		struct sbitmap_word *map = &sb->map[index];
 		unsigned long get_mask;
 		unsigned int map_depth = __map_depth(sb, index);
+		unsigned long val;
 
-		sbitmap_deferred_clear(map);
-		if (map->word == (1UL << (map_depth - 1)) - 1)
+		sbitmap_deferred_clear(map, 0, 0, 0);
+		val = READ_ONCE(map->word);
+		if (val == (1UL << (map_depth - 1)) - 1)
 			goto next;
 
-		nr = find_first_zero_bit(&map->word, map_depth);
+		nr = find_first_zero_bit(&val, map_depth);
 		if (nr + nr_tags <= map_depth) {
 			atomic_long_t *ptr = (atomic_long_t *) &map->word;
-			unsigned long val;
 
 			get_mask = ((1UL << nr_tags) - 1) << nr;
-			val = READ_ONCE(map->word);
-			do {
-				if ((val & ~get_mask) != val)
-					goto next;
-			} while (!atomic_long_try_cmpxchg(ptr, &val,
-							  get_mask | val));
+			while (!atomic_long_try_cmpxchg(ptr, &val,
+							  get_mask | val))
+				;
 			get_mask = (get_mask & ~val) >> nr;
 			if (get_mask) {
 				*offset = nr + (index << sb->shift);
@@ -562,7 +583,7 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth);
 
 static void __sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr)
 {
-	int i, wake_index;
+	int i, wake_index, woken;
 
 	if (!atomic_read(&sbq->ws_active))
 		return;
@@ -579,13 +600,12 @@ static void __sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr)
 		 */
 		wake_index = sbq_index_inc(wake_index);
 
-		/*
-		 * It is sufficient to wake up at least one waiter to
-		 * guarantee forward progress.
-		 */
-		if (waitqueue_active(&ws->wait) &&
-		    wake_up_nr(&ws->wait, nr))
-			break;
+		if (waitqueue_active(&ws->wait)) {
+			woken = wake_up_nr(&ws->wait, nr);
+			if (woken == nr)
+				break;
+			nr -= woken;
+		}
 	}
 
 	if (wake_index != atomic_read(&sbq->wake_index))