block: Support atomic writes limits for stacked devices

Allow stacked devices to support atomic writes by aggregating the minimum
capability of all bottom devices.

Flag BLK_FEAT_ATOMIC_WRITES_STACKED is set for stacked devices which
have been enabled to support atomic writes.

Some things to note on the implementation:
- For simplicity, all bottom devices must have same atomic write boundary
  value (if any)
- The atomic write boundary must be a power-of-2 already, but this
  restriction could be relaxed. Furthermore, it is now required that the
  chunk sectors for a top device must be aligned with this boundary.
- If a bottom device atomic write unit min/max are not aligned with the
  top device chunk sectors, the top device atomic write unit min/max are
  reduced to a value which works for the chunk sectors.

Reviewed-by: Christoph Hellwig <hch@lst.de>
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/20241118105018.1870052-3-john.g.garry@oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-settings.c

@@ -501,6 +501,119 @@ static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lb
 	return sectors;
 }
 
+/* Check if second and later bottom devices are compliant */
+static bool blk_stack_atomic_writes_tail(struct queue_limits *t,
+				struct queue_limits *b)
+{
+	/* We're not going to support different boundary sizes.. yet */
+	if (t->atomic_write_hw_boundary != b->atomic_write_hw_boundary)
+		return false;
+
+	/* Can't support this */
+	if (t->atomic_write_hw_unit_min > b->atomic_write_hw_unit_max)
+		return false;
+
+	/* Or this */
+	if (t->atomic_write_hw_unit_max < b->atomic_write_hw_unit_min)
+		return false;
+
+	t->atomic_write_hw_max = min(t->atomic_write_hw_max,
+				b->atomic_write_hw_max);
+	t->atomic_write_hw_unit_min = max(t->atomic_write_hw_unit_min,
+				b->atomic_write_hw_unit_min);
+	t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max,
+				b->atomic_write_hw_unit_max);
+	return true;
+}
+
+/* Check for valid boundary of first bottom device */
+static bool blk_stack_atomic_writes_boundary_head(struct queue_limits *t,
+				struct queue_limits *b)
+{
+	/*
+	 * Ensure atomic write boundary is aligned with chunk sectors. Stacked
+	 * devices store chunk sectors in t->io_min.
+	 */
+	if (b->atomic_write_hw_boundary > t->io_min &&
+	    b->atomic_write_hw_boundary % t->io_min)
+		return false;
+	if (t->io_min > b->atomic_write_hw_boundary &&
+	    t->io_min % b->atomic_write_hw_boundary)
+		return false;
+
+	t->atomic_write_hw_boundary = b->atomic_write_hw_boundary;
+	return true;
+}
+
+
+/* Check stacking of first bottom device */
+static bool blk_stack_atomic_writes_head(struct queue_limits *t,
+				struct queue_limits *b)
+{
+	if (b->atomic_write_hw_boundary &&
+	    !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_max /= 2;
+
+	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;
+}
+
+static void blk_stack_atomic_writes_limits(struct queue_limits *t,
+				struct queue_limits *b)
+{
+	if (!(t->features & BLK_FEAT_ATOMIC_WRITES_STACKED))
+		goto unsupported;
+
+	if (!b->atomic_write_unit_min)
+		goto unsupported;
+
+	/*
+	 * If atomic_write_hw_max is set, we have already stacked 1x bottom
+	 * device, so check for compliance.
+	 */
+	if (t->atomic_write_hw_max) {
+		if (!blk_stack_atomic_writes_tail(t, b))
+			goto unsupported;
+		return;
+	}
+
+	if (!blk_stack_atomic_writes_head(t, b))
+		goto unsupported;
+	return;
+
+unsupported:
+	t->atomic_write_hw_max = 0;
+	t->atomic_write_hw_unit_max = 0;
+	t->atomic_write_hw_unit_min = 0;
+	t->atomic_write_hw_boundary = 0;
+	t->features &= ~BLK_FEAT_ATOMIC_WRITES_STACKED;
+}
+
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top device)
@@ -661,6 +774,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		t->zone_write_granularity = 0;
 		t->max_zone_append_sectors = 0;
 	}
+	blk_stack_atomic_writes_limits(t, b);
+
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);

include/linux/blkdev.h

@@ -333,6 +333,10 @@ typedef unsigned int __bitwise blk_features_t;
 #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \
 	((__force blk_features_t)(1u << 15))
 
+/* stacked device can/does support atomic writes */
+#define BLK_FEAT_ATOMIC_WRITES_STACKED \
+	((__force blk_features_t)(1u << 16))
+
 /*
  * Flags automatically inherited when stacking limits.
  */