From dd88d313bef0277e27597aa394607ed26c658724 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Mon, 8 May 2017 16:40:43 -0700
Subject: [PATCH] dm table: add zoned block devices validation
Git-commit: dd88d313bef0277e27597aa394607ed26c658724
Patch-mainline: v4.13-rc1
References: fate#322738,fate#322919,fate#322950,fate#323773
1) Introduce DM_TARGET_ZONED_HM feature flag:
The target drivers currently available will not operate correctly if a
table target maps onto a host-managed zoned block device.
To avoid problems, introduce the new feature flag DM_TARGET_ZONED_HM to
allow a target to explicitly state that it supports host-managed zoned
block devices. This feature is checked for all targets in a table if
any of the table's block devices are host-managed.
Note that as host-aware zoned block devices are backward compatible with
regular block devices, they can be used by any of the current target
types. This new feature is thus restricted to host-managed zoned block
devices.
2) Check device area zone alignment:
If a target maps to a zoned block device, check that the device area is
aligned on zone boundaries to avoid problems with REQ_OP_ZONE_RESET
operations (resetting a partially mapped sequential zone would not be
possible). This also facilitates the processing of zone report with
REQ_OP_ZONE_REPORT bios.
3) Check block devices zone model compatibility
When setting the DM device's queue limits, several possibilities exists
for zoned block devices:
1) The DM target driver may want to expose a different zone model
(e.g. host-managed device emulation or regular block device on top of
host-managed zoned block devices)
2) Expose the underlying zone model of the devices as-is
To allow both cases, the underlying block device zone model must be set
in the target limits in dm_set_device_limits() and the compatibility of
all devices checked similarly to the logical block size alignment. For
this last check, introduce validate_hardware_zoned_model() to check that
all targets of a table have the same zone model and that the zone size
of the target devices are equal.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
[Mike Snitzer refactored Damien's original work to simplify the code]
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Coly Li <colyli@suse.de>
---
drivers/md/dm-table.c | 162 ++++++++++++++++++++++++++++++++++++++++++
include/linux/device-mapper.h | 6 ++
2 files changed, 168 insertions(+)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5f5eae41f804..a39bcd9b982a 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -319,6 +319,39 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
return 1;
}
+ /*
+ * If the target is mapped to zoned block device(s), check
+ * that the zones are not partially mapped.
+ */
+ if (bdev_zoned_model(bdev) != BLK_ZONED_NONE) {
+ unsigned int zone_sectors = bdev_zone_sectors(bdev);
+
+ if (start & (zone_sectors - 1)) {
+ DMWARN("%s: start=%llu not aligned to h/w zone size %u of %s",
+ dm_device_name(ti->table->md),
+ (unsigned long long)start,
+ zone_sectors, bdevname(bdev, b));
+ return 1;
+ }
+
+ /*
+ * Note: The last zone of a zoned block device may be smaller
+ * than other zones. So for a target mapping the end of a
+ * zoned block device with such a zone, len would not be zone
+ * aligned. We do not allow such last smaller zone to be part
+ * of the mapping here to ensure that mappings with multiple
+ * devices do not end up with a smaller zone in the middle of
+ * the sector range.
+ */
+ if (len & (zone_sectors - 1)) {
+ DMWARN("%s: len=%llu not aligned to h/w zone size %u of %s",
+ dm_device_name(ti->table->md),
+ (unsigned long long)len,
+ zone_sectors, bdevname(bdev, b));
+ return 1;
+ }
+ }
+
if (logical_block_size_sectors <= 1)
return 0;
@@ -456,6 +489,8 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
q->limits.alignment_offset,
(unsigned long long) start << SECTOR_SHIFT);
+ limits->zoned = blk_queue_zoned_model(q);
+
return 0;
}
@@ -1346,6 +1381,88 @@ bool dm_table_has_no_data_devices(struct dm_table *table)
return true;
}
+static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+ enum blk_zoned_model *zoned_model = data;
+
+ return q && blk_queue_zoned_model(q) == *zoned_model;
+}
+
+static bool dm_table_supports_zoned_model(struct dm_table *t,
+ enum blk_zoned_model zoned_model)
+{
+ struct dm_target *ti;
+ unsigned i;
+
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+
+ if (zoned_model == BLK_ZONED_HM &&
+ !dm_target_supports_zoned_hm(ti->type))
+ return false;
+
+ if (!ti->type->iterate_devices ||
+ !ti->type->iterate_devices(ti, device_is_zoned_model, &zoned_model))
+ return false;
+ }
+
+ return true;
+}
+
+static int device_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+ unsigned int *zone_sectors = data;
+
+ return q && blk_queue_zone_sectors(q) == *zone_sectors;
+}
+
+static bool dm_table_matches_zone_sectors(struct dm_table *t,
+ unsigned int zone_sectors)
+{
+ struct dm_target *ti;
+ unsigned i;
+
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+
+ if (!ti->type->iterate_devices ||
+ !ti->type->iterate_devices(ti, device_matches_zone_sectors, &zone_sectors))
+ return false;
+ }
+
+ return true;
+}
+
+static int validate_hardware_zoned_model(struct dm_table *table,
+ enum blk_zoned_model zoned_model,
+ unsigned int zone_sectors)
+{
+ if (zoned_model == BLK_ZONED_NONE)
+ return 0;
+
+ if (!dm_table_supports_zoned_model(table, zoned_model)) {
+ DMERR("%s: zoned model is not consistent across all devices",
+ dm_device_name(table->md));
+ return -EINVAL;
+ }
+
+ /* Check zone size validity and compatibility */
+ if (!zone_sectors || !is_power_of_2(zone_sectors))
+ return -EINVAL;
+
+ if (!dm_table_matches_zone_sectors(table, zone_sectors)) {
+ DMERR("%s: zone sectors is not consistent across all devices",
+ dm_device_name(table->md));
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/*
* Establish the new table's queue_limits and validate them.
*/
@@ -1355,6 +1472,8 @@ int dm_calculate_queue_limits(struct dm_table *table,
struct dm_target *ti;
struct queue_limits ti_limits;
unsigned i;
+ enum blk_zoned_model zoned_model = BLK_ZONED_NONE;
+ unsigned int zone_sectors = 0;
blk_set_stacking_limits(limits);
@@ -1372,6 +1491,15 @@ int dm_calculate_queue_limits(struct dm_table *table,
ti->type->iterate_devices(ti, dm_set_device_limits,
&ti_limits);
+ if (zoned_model == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
+ /*
+ * After stacking all limits, validate all devices
+ * in table support this zoned model and zone sectors.
+ */
+ zoned_model = ti_limits.zoned;
+ zone_sectors = ti_limits.chunk_sectors;
+ }
+
/* Set I/O hints portion of queue limits */
if (ti->type->io_hints)
ti->type->io_hints(ti, &ti_limits);
@@ -1396,8 +1524,42 @@ int dm_calculate_queue_limits(struct dm_table *table,
dm_device_name(table->md),
(unsigned long long) ti->begin,
(unsigned long long) ti->len);
+
+ /*
+ * FIXME: this should likely be moved to blk_stack_limits(), would
+ * also eliminate limits->zoned stacking hack in dm_set_device_limits()
+ */
+ if (limits->zoned == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
+ /*
+ * By default, the stacked limits zoned model is set to
+ * BLK_ZONED_NONE in blk_set_stacking_limits(). Update
+ * this model using the first target model reported
+ * that is not BLK_ZONED_NONE. This will be either the
+ * first target device zoned model or the model reported
+ * by the target .io_hints.
+ */
+ limits->zoned = ti_limits.zoned;
+ }
}
+ /*
+ * Verify that the zoned model and zone sectors, as determined before
+ * any .io_hints override, are the same across all devices in the table.
+ * - this is especially relevant if .io_hints is emulating a disk-managed
+ * zoned model (aka BLK_ZONED_NONE) on host-managed zoned block devices.
+ * BUT...
+ */
+ if (limits->zoned != BLK_ZONED_NONE) {
+ /*
+ * ...IF the above limits stacking determined a zoned model
+ * validate that all of the table's devices conform to it.
+ */
+ zoned_model = limits->zoned;
+ zone_sectors = limits->chunk_sectors;
+ }
+ if (validate_hardware_zoned_model(table, zoned_model, zone_sectors))
+ return -EINVAL;
+
return validate_hardware_logical_block_alignment(table, limits);
}
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 19bc7fdfd6da..186ef74009cb 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -237,6 +237,12 @@ typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio)
#define DM_TARGET_PASSES_INTEGRITY 0x00000020
#define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY)
+/*
+ * Indicates that a target supports host-managed zoned block devices.
+ */
+#define DM_TARGET_ZONED_HM 0x00000040
+#define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM)
+
struct dm_target {
struct dm_table *table;
struct target_type *type;
--
2.13.1