* These are optimistic limits taken from all the
* targets, some targets will need smaller limits.
*/
- struct io_restrictions limits;
+ struct queue_limits limits;
/* events get handed up using this callback */
void (*event_fn)(void *);
return result;
}
-/*
- * Returns the minimum that is _not_ zero, unless both are zero.
- */
-#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
-
-/*
- * Combine two io_restrictions, always taking the lower value.
- */
-static void combine_restrictions_low(struct io_restrictions *lhs,
- struct io_restrictions *rhs)
-{
- lhs->max_sectors =
- min_not_zero(lhs->max_sectors, rhs->max_sectors);
-
- lhs->max_phys_segments =
- min_not_zero(lhs->max_phys_segments, rhs->max_phys_segments);
-
- lhs->max_hw_segments =
- min_not_zero(lhs->max_hw_segments, rhs->max_hw_segments);
-
- lhs->hardsect_size = max(lhs->hardsect_size, rhs->hardsect_size);
-
- lhs->max_segment_size =
- min_not_zero(lhs->max_segment_size, rhs->max_segment_size);
-
- lhs->max_hw_sectors =
- min_not_zero(lhs->max_hw_sectors, rhs->max_hw_sectors);
-
- lhs->seg_boundary_mask =
- min_not_zero(lhs->seg_boundary_mask, rhs->seg_boundary_mask);
-
- lhs->bounce_pfn = min_not_zero(lhs->bounce_pfn, rhs->bounce_pfn);
-
- lhs->no_cluster |= rhs->no_cluster;
-}
-
/*
* Calculate the index of the child node of the n'th node k'th key.
*/
list_for_each_safe(tmp, next, devices) {
struct dm_dev_internal *dd =
list_entry(tmp, struct dm_dev_internal, list);
+ DMWARN("dm_table_destroy: dm_put_device call missing for %s",
+ dd->dm_dev.name);
kfree(dd);
}
}
vfree(t->highs);
/* free the device list */
- if (t->devices.next != &t->devices) {
- DMWARN("devices still present during destroy: "
- "dm_table_remove_device calls missing");
-
+ if (t->devices.next != &t->devices)
free_devices(&t->devices);
- }
kfree(t);
}
/*
* If possible, this checks an area of a destination device is valid.
*/
-static int check_device_area(struct dm_dev_internal *dd, sector_t start,
- sector_t len)
+static int device_area_is_valid(struct dm_target *ti, struct block_device *bdev,
+ sector_t start, sector_t len)
{
- sector_t dev_size = dd->dm_dev.bdev->bd_inode->i_size >> SECTOR_SHIFT;
+ sector_t dev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ unsigned short logical_block_size_sectors =
+ ti->limits.logical_block_size >> SECTOR_SHIFT;
+ char b[BDEVNAME_SIZE];
if (!dev_size)
return 1;
- return ((start < dev_size) && (len <= (dev_size - start)));
+ if ((start >= dev_size) || (start + len > dev_size)) {
+ DMWARN("%s: %s too small for target",
+ dm_device_name(ti->table->md), bdevname(bdev, b));
+ return 0;
+ }
+
+ if (logical_block_size_sectors <= 1)
+ return 1;
+
+ if (start & (logical_block_size_sectors - 1)) {
+ DMWARN("%s: start=%llu not aligned to h/w "
+ "logical block size %hu of %s",
+ dm_device_name(ti->table->md),
+ (unsigned long long)start,
+ ti->limits.logical_block_size, bdevname(bdev, b));
+ return 0;
+ }
+
+ if (len & (logical_block_size_sectors - 1)) {
+ DMWARN("%s: len=%llu not aligned to h/w "
+ "logical block size %hu of %s",
+ dm_device_name(ti->table->md),
+ (unsigned long long)len,
+ ti->limits.logical_block_size, bdevname(bdev, b));
+ return 0;
+ }
+
+ return 1;
}
/*
}
atomic_inc(&dd->count);
- if (!check_device_area(dd, start, len)) {
- DMWARN("device %s too small for target", path);
- dm_put_device(ti, &dd->dm_dev);
- return -EINVAL;
- }
-
*result = &dd->dm_dev;
-
return 0;
}
+/*
+ * Returns the minimum that is _not_ zero, unless both are zero.
+ */
+#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
+
void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
- struct io_restrictions *rs = &ti->limits;
char b[BDEVNAME_SIZE];
if (unlikely(!q)) {
return;
}
- /*
- * Combine the device limits low.
- *
- * FIXME: if we move an io_restriction struct
- * into q this would just be a call to
- * combine_restrictions_low()
- */
- rs->max_sectors =
- min_not_zero(rs->max_sectors, q->max_sectors);
+ if (blk_stack_limits(&ti->limits, &q->limits, 0) < 0)
+ DMWARN("%s: target device %s is misaligned",
+ dm_device_name(ti->table->md), bdevname(bdev, b));
/*
* Check if merge fn is supported.
*/
if (q->merge_bvec_fn && !ti->type->merge)
- rs->max_sectors =
- min_not_zero(rs->max_sectors,
+ ti->limits.max_sectors =
+ min_not_zero(ti->limits.max_sectors,
(unsigned int) (PAGE_SIZE >> 9));
-
- rs->max_phys_segments =
- min_not_zero(rs->max_phys_segments,
- q->max_phys_segments);
-
- rs->max_hw_segments =
- min_not_zero(rs->max_hw_segments, q->max_hw_segments);
-
- rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
-
- rs->max_segment_size =
- min_not_zero(rs->max_segment_size, q->max_segment_size);
-
- rs->max_hw_sectors =
- min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);
-
- rs->seg_boundary_mask =
- min_not_zero(rs->seg_boundary_mask,
- q->seg_boundary_mask);
-
- rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);
-
- rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
}
EXPORT_SYMBOL_GPL(dm_set_device_limits);
int r = __table_get_device(ti->table, ti, path,
start, len, mode, result);
- if (!r)
- dm_set_device_limits(ti, (*result)->bdev);
+ if (r)
+ return r;
+
+ dm_set_device_limits(ti, (*result)->bdev);
+
+ if (!device_area_is_valid(ti, (*result)->bdev, start, len)) {
+ dm_put_device(ti, *result);
+ *result = NULL;
+ return -EINVAL;
+ }
return r;
}
return 0;
}
-static void check_for_valid_limits(struct io_restrictions *rs)
+static void init_valid_queue_limits(struct queue_limits *limits)
{
- if (!rs->max_sectors)
- rs->max_sectors = SAFE_MAX_SECTORS;
- if (!rs->max_hw_sectors)
- rs->max_hw_sectors = SAFE_MAX_SECTORS;
- if (!rs->max_phys_segments)
- rs->max_phys_segments = MAX_PHYS_SEGMENTS;
- if (!rs->max_hw_segments)
- rs->max_hw_segments = MAX_HW_SEGMENTS;
- if (!rs->hardsect_size)
- rs->hardsect_size = 1 << SECTOR_SHIFT;
- if (!rs->max_segment_size)
- rs->max_segment_size = MAX_SEGMENT_SIZE;
- if (!rs->seg_boundary_mask)
- rs->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
- if (!rs->bounce_pfn)
- rs->bounce_pfn = -1;
+ if (!limits->max_sectors)
+ limits->max_sectors = SAFE_MAX_SECTORS;
+ if (!limits->max_hw_sectors)
+ limits->max_hw_sectors = SAFE_MAX_SECTORS;
+ if (!limits->max_phys_segments)
+ limits->max_phys_segments = MAX_PHYS_SEGMENTS;
+ if (!limits->max_hw_segments)
+ limits->max_hw_segments = MAX_HW_SEGMENTS;
+ if (!limits->logical_block_size)
+ limits->logical_block_size = 1 << SECTOR_SHIFT;
+ if (!limits->physical_block_size)
+ limits->physical_block_size = 1 << SECTOR_SHIFT;
+ if (!limits->io_min)
+ limits->io_min = 1 << SECTOR_SHIFT;
+ if (!limits->max_segment_size)
+ limits->max_segment_size = MAX_SEGMENT_SIZE;
+ if (!limits->seg_boundary_mask)
+ limits->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+ if (!limits->bounce_pfn)
+ limits->bounce_pfn = -1;
+ /*
+ * The other fields (alignment_offset, io_opt, misaligned)
+ * hold 0 from the kzalloc().
+ */
+}
+
+/*
+ * Impose necessary and sufficient conditions on a devices's table such
+ * that any incoming bio which respects its logical_block_size can be
+ * processed successfully. If it falls across the boundary between
+ * two or more targets, the size of each piece it gets split into must
+ * be compatible with the logical_block_size of the target processing it.
+ */
+static int validate_hardware_logical_block_alignment(struct dm_table *table)
+{
+ /*
+ * This function uses arithmetic modulo the logical_block_size
+ * (in units of 512-byte sectors).
+ */
+ unsigned short device_logical_block_size_sects =
+ table->limits.logical_block_size >> SECTOR_SHIFT;
+
+ /*
+ * Offset of the start of the next table entry, mod logical_block_size.
+ */
+ unsigned short next_target_start = 0;
+
+ /*
+ * Given an aligned bio that extends beyond the end of a
+ * target, how many sectors must the next target handle?
+ */
+ unsigned short remaining = 0;
+
+ struct dm_target *uninitialized_var(ti);
+ unsigned i = 0;
+
+ /*
+ * Check each entry in the table in turn.
+ */
+ while (i < dm_table_get_num_targets(table)) {
+ ti = dm_table_get_target(table, i++);
+
+ /*
+ * If the remaining sectors fall entirely within this
+ * table entry are they compatible with its logical_block_size?
+ */
+ if (remaining < ti->len &&
+ remaining & ((ti->limits.logical_block_size >>
+ SECTOR_SHIFT) - 1))
+ break; /* Error */
+
+ next_target_start =
+ (unsigned short) ((next_target_start + ti->len) &
+ (device_logical_block_size_sects - 1));
+ remaining = next_target_start ?
+ device_logical_block_size_sects - next_target_start : 0;
+ }
+
+ if (remaining) {
+ DMWARN("%s: table line %u (start sect %llu len %llu) "
+ "not aligned to hardware logical block size %hu",
+ dm_device_name(table->md), i,
+ (unsigned long long) ti->begin,
+ (unsigned long long) ti->len,
+ table->limits.logical_block_size);
+ return -EINVAL;
+ }
+
+ return 0;
}
int dm_table_add_target(struct dm_table *t, const char *type,
t->highs[t->num_targets++] = tgt->begin + tgt->len - 1;
- /* FIXME: the plan is to combine high here and then have
- * the merge fn apply the target level restrictions. */
- combine_restrictions_low(&t->limits, &tgt->limits);
+ if (blk_stack_limits(&t->limits, &tgt->limits, 0) < 0)
+ DMWARN("%s: target device (start sect %llu len %llu) "
+ "is misaligned",
+ dm_device_name(t->md),
+ (unsigned long long) tgt->begin,
+ (unsigned long long) tgt->len);
return 0;
bad:
int r = 0;
unsigned int leaf_nodes;
- check_for_valid_limits(&t->limits);
+ init_valid_queue_limits(&t->limits);
+
+ r = validate_hardware_logical_block_alignment(t);
+ if (r)
+ return r;
/* how many indexes will the btree have ? */
leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE);
* restrictions.
*/
blk_queue_max_sectors(q, t->limits.max_sectors);
- q->max_phys_segments = t->limits.max_phys_segments;
- q->max_hw_segments = t->limits.max_hw_segments;
- q->hardsect_size = t->limits.hardsect_size;
- q->max_segment_size = t->limits.max_segment_size;
- q->max_hw_sectors = t->limits.max_hw_sectors;
- q->seg_boundary_mask = t->limits.seg_boundary_mask;
- q->bounce_pfn = t->limits.bounce_pfn;
+ blk_queue_max_phys_segments(q, t->limits.max_phys_segments);
+ blk_queue_max_hw_segments(q, t->limits.max_hw_segments);
+ blk_queue_logical_block_size(q, t->limits.logical_block_size);
+ blk_queue_max_segment_size(q, t->limits.max_segment_size);
+ blk_queue_max_hw_sectors(q, t->limits.max_hw_sectors);
+ blk_queue_segment_boundary(q, t->limits.seg_boundary_mask);
+ blk_queue_bounce_limit(q, t->limits.bounce_pfn);
if (t->limits.no_cluster)
queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);