Merge branch 'block-6.17' into for-next

* block-6.17:
  blk-ioc: don't hold queue_lock for ioc_lookup_icq()
  block: Enforce power-of-2 physical block size
  block: avoid possible overflow for chunk_sectors check in blk_stack_limits()
  block: Improve read ahead size for rotational devices

Author: axboe

block/bfq-iosched.c

@@ -454,17 +454,10 @@ static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
  */
 static struct bfq_io_cq *bfq_bic_lookup(struct request_queue *q)
 {
-	struct bfq_io_cq *icq;
-	unsigned long flags;
-
 	if (!current->io_context)
 		return NULL;
 
-	spin_lock_irqsave(&q->queue_lock, flags);
-	icq = icq_to_bic(ioc_lookup_icq(q));
-	spin_unlock_irqrestore(&q->queue_lock, flags);
-
-	return icq;
+	return icq_to_bic(ioc_lookup_icq(q));
 }
 
 /*
@@ -2457,15 +2450,8 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
-	struct request *free = NULL;
-	/*
-	 * bfq_bic_lookup grabs the queue_lock: invoke it now and
-	 * store its return value for later use, to avoid nesting
-	 * queue_lock inside the bfqd->lock. We assume that the bic
-	 * returned by bfq_bic_lookup does not go away before
-	 * bfqd->lock is taken.
-	 */
 	struct bfq_io_cq *bic = bfq_bic_lookup(q);
+	struct request *free = NULL;
 	bool ret;
 
 	spin_lock_irq(&bfqd->lock);

block/blk-ioc.c

@@ -308,24 +308,23 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk)
 
 #ifdef CONFIG_BLK_ICQ
 /**
- * ioc_lookup_icq - lookup io_cq from ioc
+ * ioc_lookup_icq - lookup io_cq from ioc in io issue path
  * @q: the associated request_queue
  *
  * Look up io_cq associated with @ioc - @q pair from @ioc.  Must be called
- * with @q->queue_lock held.
+ * from io issue path, either return NULL if current issue io to @q for the
+ * first time, or return a valid icq.
  */
 struct io_cq *ioc_lookup_icq(struct request_queue *q)
 {
 	struct io_context *ioc = current->io_context;
 	struct io_cq *icq;
 
-	lockdep_assert_held(&q->queue_lock);
-
 	/*
 	 * icq's are indexed from @ioc using radix tree and hint pointer,
-	 * both of which are protected with RCU.  All removals are done
-	 * holding both q and ioc locks, and we're holding q lock - if we
-	 * find a icq which points to us, it's guaranteed to be valid.
+	 * both of which are protected with RCU, io issue path ensures that
+	 * both request_queue and current task are valid, the found icq
+	 * is guaranteed to be valid until the io is done.
 	 */
 	rcu_read_lock();
 	icq = rcu_dereference(ioc->icq_hint);
@@ -419,10 +418,7 @@ struct io_cq *ioc_find_get_icq(struct request_queue *q)
 		task_unlock(current);
 	} else {
 		get_io_context(ioc);
-
-		spin_lock_irq(&q->queue_lock);
 		icq = ioc_lookup_icq(q);
-		spin_unlock_irq(&q->queue_lock);
 	}
 
 	if (!icq) {

block/blk-settings.c

@@ -62,16 +62,24 @@ EXPORT_SYMBOL(blk_set_stacking_limits);
 void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 		struct queue_limits *lim)
 {
+	u64 io_opt = lim->io_opt;
+
 	/*
 	 * For read-ahead of large files to be effective, we need to read ahead
-	 * at least twice the optimal I/O size.
+	 * at least twice the optimal I/O size. For rotational devices that do
+	 * not report an optimal I/O size (e.g. ATA HDDs), use the maximum I/O
+	 * size to avoid falling back to the (rather inefficient) small default
+	 * read-ahead size.
 	 *
 	 * There is no hardware limitation for the read-ahead size and the user
 	 * might have increased the read-ahead size through sysfs, so don't ever
 	 * decrease it.
 	 */
+	if (!io_opt && (lim->features & BLK_FEAT_ROTATIONAL))
+		io_opt = (u64)lim->max_sectors << SECTOR_SHIFT;
+
 	bdi->ra_pages = max3(bdi->ra_pages,
-				lim->io_opt * 2 / PAGE_SIZE,
+				io_opt * 2 >> PAGE_SHIFT,
 				VM_READAHEAD_PAGES);
 	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
 }
@@ -312,8 +320,12 @@ int blk_validate_limits(struct queue_limits *lim)
 		pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size);
 		return -EINVAL;
 	}
-	if (lim->physical_block_size < lim->logical_block_size)
+	if (lim->physical_block_size < lim->logical_block_size) {
 		lim->physical_block_size = lim->logical_block_size;
+	} else if (!is_power_of_2(lim->physical_block_size)) {
+		pr_warn("Invalid physical block size (%d)\n", lim->physical_block_size);
+		return -EINVAL;
+	}
 
 	/*
 	 * The minimum I/O size defaults to the physical block size unless
@@ -849,7 +861,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	}
 
 	/* chunk_sectors a multiple of the physical block size? */
-	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
+	if (t->chunk_sectors % (t->physical_block_size >> SECTOR_SHIFT)) {
 		t->chunk_sectors = 0;
 		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;