block: Fix incorrect alignment offset reporting and update documentation
queue_sector_alignment_offset returned the wrong value which caused
partitions to report an incorrect alignment_offset. Since offset
alignment calculation is needed several places it has been split into a
separate helper function. The topology stacking function has been
updated accordingly.
Furthermore, comments have been added to clarify how the stacking
function works.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Tested-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/block/blk-settings.c b/block/blk-settings.c
index e14fcbc..d52d4ad 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -505,20 +505,30 @@
/**
* blk_stack_limits - adjust queue_limits for stacked devices
- * @t: the stacking driver limits (top)
- * @b: the underlying queue limits (bottom)
+ * @t: the stacking driver limits (top device)
+ * @b: the underlying queue limits (bottom, component device)
* @offset: offset to beginning of data within component device
*
* Description:
- * Merges two queue_limit structs. Returns 0 if alignment didn't
- * change. Returns -1 if adding the bottom device caused
- * misalignment.
+ * This function is used by stacking drivers like MD and DM to ensure
+ * that all component devices have compatible block sizes and
+ * alignments. The stacking driver must provide a queue_limits
+ * struct (top) and then iteratively call the stacking function for
+ * all component (bottom) devices. The stacking function will
+ * attempt to combine the values and ensure proper alignment.
+ *
+ * Returns 0 if the top and bottom queue_limits are compatible. The
+ * top device's block sizes and alignment offsets may be adjusted to
+ * ensure alignment with the bottom device. If no compatible sizes
+ * and alignments exist, -1 is returned and the resulting top
+ * queue_limits will have the misaligned flag set to indicate that
+ * the alignment_offset is undefined.
*/
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t offset)
{
sector_t alignment;
- unsigned int top, bottom, granularity;
+ unsigned int top, bottom;
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
@@ -536,15 +546,18 @@
t->max_segment_size = min_not_zero(t->max_segment_size,
b->max_segment_size);
- granularity = max(b->physical_block_size, b->io_min);
- alignment = b->alignment_offset - (offset & (granularity - 1));
+ alignment = queue_limit_alignment_offset(b, offset);
+ /* Bottom device has different alignment. Check that it is
+ * compatible with the current top alignment.
+ */
if (t->alignment_offset != alignment) {
top = max(t->physical_block_size, t->io_min)
+ t->alignment_offset;
- bottom = granularity + alignment;
+ bottom = max(b->physical_block_size, b->io_min) + alignment;
+ /* Verify that top and bottom intervals line up */
if (max(top, bottom) & (min(top, bottom) - 1))
t->misaligned = 1;
}
@@ -561,32 +574,39 @@
t->no_cluster |= b->no_cluster;
t->discard_zeroes_data &= b->discard_zeroes_data;
+ /* Physical block size a multiple of the logical block size? */
if (t->physical_block_size & (t->logical_block_size - 1)) {
t->physical_block_size = t->logical_block_size;
t->misaligned = 1;
}
+ /* Minimum I/O a multiple of the physical block size? */
if (t->io_min & (t->physical_block_size - 1)) {
t->io_min = t->physical_block_size;
t->misaligned = 1;
}
+ /* Optimal I/O a multiple of the physical block size? */
if (t->io_opt & (t->physical_block_size - 1)) {
t->io_opt = 0;
t->misaligned = 1;
}
+ /* Find lowest common alignment_offset */
t->alignment_offset = lcm(t->alignment_offset, alignment)
& (max(t->physical_block_size, t->io_min) - 1);
+ /* Verify that new alignment_offset is on a logical block boundary */
if (t->alignment_offset & (t->logical_block_size - 1))
t->misaligned = 1;
/* Discard alignment and granularity */
if (b->discard_granularity) {
+ unsigned int granularity = b->discard_granularity;
+ offset &= granularity - 1;
- alignment = b->discard_alignment -
- (offset & (b->discard_granularity - 1));
+ alignment = (granularity + b->discard_alignment - offset)
+ & (granularity - 1);
if (t->discard_granularity != 0 &&
t->discard_alignment != alignment) {
@@ -598,6 +618,8 @@
t->discard_misaligned = 1;
}
+ t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
+ b->max_discard_sectors);
t->discard_granularity = max(t->discard_granularity,
b->discard_granularity);
t->discard_alignment = lcm(t->discard_alignment, alignment) &
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 784a919..59b832b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1116,11 +1116,18 @@
return q->limits.alignment_offset;
}
+static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t offset)
+{
+ unsigned int granularity = max(lim->physical_block_size, lim->io_min);
+
+ offset &= granularity - 1;
+ return (granularity + lim->alignment_offset - offset) & (granularity - 1);
+}
+
static inline int queue_sector_alignment_offset(struct request_queue *q,
sector_t sector)
{
- return ((sector << 9) - q->limits.alignment_offset)
- & (q->limits.io_min - 1);
+ return queue_limit_alignment_offset(&q->limits, sector << 9);
}
static inline int bdev_alignment_offset(struct block_device *bdev)