block: use chunk_sectors when evaluating stacked atomic write limits

The atomic write unit max value is limited by any stacked device stripe
size.

It is required that the atomic write unit is a power-of-2 factor of the
stripe size.

Currently we use io_min limit to hold the stripe size, and check for a
io_min <= SECTOR_SIZE when deciding if we have a striped stacked device.

Nilay reports that this causes a problem when the physical block size is
greater than SECTOR_SIZE [0].

Furthermore, io_min may be mutated when stacking devices, and this makes
it a poor candidate to hold the stripe size. Such an example (of when
io_min may change) would be when the io_min is less than the physical
block size.

Use chunk_sectors to hold the stripe size, which is more appropriate.

[0] https://lore.kernel.org/linux-block/888f3b1d-7817-4007-b3b3-1a2ea04df771@linux.ibm.com/T/#mecca17129f72811137d3c2f1e477634e77f06781

Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Tested-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20250711105258.3135198-7-john.g.garry@oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-settings.c

@@ -595,6 +595,38 @@ static bool blk_stack_atomic_writes_boundary_head(struct queue_limits *t,
 	return true;
 }
 
+static void blk_stack_atomic_writes_chunk_sectors(struct queue_limits *t)
+{
+	unsigned int chunk_bytes;
+
+	if (!t->chunk_sectors)
+		return;
+
+	/*
+	 * If chunk sectors is so large that its value in bytes overflows
+	 * UINT_MAX, then just shift it down so it definitely will fit.
+	 * We don't support atomic writes of such a large size anyway.
+	 */
+	if (check_shl_overflow(t->chunk_sectors, SECTOR_SHIFT, &chunk_bytes))
+		chunk_bytes = t->chunk_sectors;
+
+	/*
+	 * Find values for limits which work for chunk size.
+	 * b->atomic_write_hw_unit_{min, max} may not be aligned with chunk
+	 * size, as the chunk size is not restricted to a power-of-2.
+	 * So we need to find highest power-of-2 which works for the chunk
+	 * size.
+	 * As an example scenario, we could have t->unit_max = 16K and
+	 * t->chunk_sectors = 24KB. For this case, reduce t->unit_max to a
+	 * value aligned with both limits, i.e. 8K in this example.
+	 */
+	t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max,
+					max_pow_of_two_factor(chunk_bytes));
+
+	t->atomic_write_hw_unit_min = min(t->atomic_write_hw_unit_min,
+					  t->atomic_write_hw_unit_max);
+	t->atomic_write_hw_max = min(t->atomic_write_hw_max, chunk_bytes);
+}
 
 /* Check stacking of first bottom device */
 static bool blk_stack_atomic_writes_head(struct queue_limits *t,
@@ -604,32 +636,9 @@ static bool blk_stack_atomic_writes_head(struct queue_limits *t,
 	    !blk_stack_atomic_writes_boundary_head(t, b))
 		return false;
 
-	if (t->io_min <= SECTOR_SIZE) {
-		/* No chunk sectors, so use bottom device values directly */
-		t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max;
-		t->atomic_write_hw_unit_min = b->atomic_write_hw_unit_min;
-		t->atomic_write_hw_max = b->atomic_write_hw_max;
-		return true;
-	}
-
-	/*
-	 * Find values for limits which work for chunk size.
-	 * b->atomic_write_hw_unit_{min, max} may not be aligned with chunk
-	 * size (t->io_min), as chunk size is not restricted to a power-of-2.
-	 * So we need to find highest power-of-2 which works for the chunk
-	 * size.
-	 * As an example scenario, we could have b->unit_max = 16K and
-	 * t->io_min = 24K. For this case, reduce t->unit_max to a value
-	 * aligned with both limits, i.e. 8K in this example.
-	 */
 	t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max;
-	while (t->io_min % t->atomic_write_hw_unit_max)
+	t->atomic_write_hw_unit_min = b->atomic_write_hw_unit_min;
-		t->atomic_write_hw_unit_max /= 2;
+	t->atomic_write_hw_max = b->atomic_write_hw_max;
-
-	t->atomic_write_hw_unit_min = min(b->atomic_write_hw_unit_min,
-					  t->atomic_write_hw_unit_max);
-	t->atomic_write_hw_max = min(b->atomic_write_hw_max, t->io_min);
-
 	return true;
 }
 
@@ -657,6 +666,7 @@ static void blk_stack_atomic_writes_limits(struct queue_limits *t,
 
 	if (!blk_stack_atomic_writes_head(t, b))
 		goto unsupported;
+	blk_stack_atomic_writes_chunk_sectors(t);
 	return;
 
 unsupported: