@@ -403,6 +403,7 @@ struct mddev {
sector_t array_sectors; /* exported array size */
int external_size; /* size managed
* externally */
+ unsigned int logical_block_size;
__u64 events;
/* If the last 'event' was simply a clean->dirty transition, and
* we didn't write it to the spares, then it is safe and simple
@@ -180,7 +180,8 @@ typedef struct mdp_superblock_s {
__u32 delta_disks; /* 15 change in number of raid_disks */
__u32 new_layout; /* 16 new layout */
__u32 new_chunk; /* 17 new chunk size (bytes) */
- __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 18];
+ __u32 logical_block_size; /* same as q->limits->logical_block_size */
+ __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 19];
/*
* Personality information
@@ -291,7 +292,8 @@ struct mdp_superblock_1 {
__le64 resync_offset; /* data before this offset (from data_offset) known to be in sync */
__le32 sb_csum; /* checksum up to devs[max_dev] */
__le32 max_dev; /* size of devs[] array to consider */
- __u8 pad3[64-32]; /* set to 0 when writing */
+ __le32 logical_block_size; /* same as q->limits->logical_block_size */
+ __u8 pad3[64-36]; /* set to 0 when writing */
/* device state information. Indexed by dev_number.
* 2 bytes per device
@@ -73,6 +73,7 @@ static int linear_set_limits(struct mddev *mddev)
md_init_stacking_limits(&lim);
lim.max_hw_sectors = mddev->chunk_sectors;
+ lim.logical_block_size = mddev->logical_block_size;
lim.max_write_zeroes_sectors = mddev->chunk_sectors;
lim.io_min = mddev->chunk_sectors << 9;
err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
@@ -1335,6 +1335,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, stru
mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
mddev->bitmap_info.default_space = 64*2 - (MD_SB_BYTES >> 9);
mddev->reshape_backwards = 0;
+ mddev->logical_block_size = sb->logical_block_size;
if (mddev->minor_version >= 91) {
mddev->reshape_position = sb->reshape_position;
@@ -1497,6 +1498,7 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
sb->layout = mddev->layout;
sb->chunk_size = mddev->chunk_sectors << 9;
+ sb->logical_block_size = mddev->logical_block_size;
if (mddev->bitmap && mddev->bitmap_info.file == NULL)
sb->state |= (1<<MD_SB_BITMAP_PRESENT);
@@ -1831,6 +1833,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
mddev->layout = le32_to_cpu(sb->layout);
mddev->raid_disks = le32_to_cpu(sb->raid_disks);
mddev->dev_sectors = le64_to_cpu(sb->size);
+ mddev->logical_block_size = le32_to_cpu(sb->logical_block_size);
mddev->events = ev1;
mddev->bitmap_info.offset = 0;
mddev->bitmap_info.space = 0;
@@ -2040,6 +2043,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
sb->level = cpu_to_le32(mddev->level);
sb->layout = cpu_to_le32(mddev->layout);
+ sb->logical_block_size = cpu_to_le32(mddev->logical_block_size);
if (test_bit(FailFast, &rdev->flags))
sb->devflags |= FailFast1;
else
@@ -5630,6 +5634,65 @@ static struct md_sysfs_entry md_serialize_policy =
__ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show,
serialize_policy_store);
+static int mddev_set_logical_block_size(struct mddev *mddev,
+ unsigned int lbs)
+{
+ int err = 0;
+ struct queue_limits lim;
+
+ if (blk_validate_block_size(lbs) ||
+ queue_logical_block_size(mddev->gendisk->queue) >= lbs) {
+ pr_err("%s: incompatible logical_block_size, can not set\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+
+ lim = queue_limits_start_update(mddev->gendisk->queue);
+ if (blk_set_block_size(&lim, lbs, 0))
+ pr_warn("%s: logical_block_size changes, data may be lost\n",
+ mdname(mddev));
+ err = queue_limits_commit_update(mddev->gendisk->queue, &lim);
+ if (err)
+ return err;
+
+ mddev->logical_block_size = lbs;
+ md_update_sb(mddev, 1);
+
+ return 0;
+}
+
+static ssize_t
+lbs_show(struct mddev *mddev, char *page)
+{
+ return sprintf(page, "%u\n", mddev->logical_block_size);
+}
+
+static ssize_t
+lbs_store(struct mddev *mddev, const char *buf, size_t len)
+{
+ unsigned int lbs;
+ int err;
+
+ err = kstrtouint(buf, 10, &lbs);
+ if (err < 0)
+ return err;
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ err = -EBUSY;
+ if (mddev->pers)
+ goto unlock;
+
+ err = mddev_set_logical_block_size(mddev, lbs);
+
+unlock:
+ mddev_unlock(mddev);
+ return err ?: len;
+}
+
+static struct md_sysfs_entry md_logical_block_size =
+__ATTR(logical_block_size, S_IRUGO|S_IWUSR, lbs_show, lbs_store);
static struct attribute *md_default_attrs[] = {
&md_level.attr,
@@ -5662,6 +5725,7 @@ static struct attribute *md_redundancy_attrs[] = {
&md_scan_mode.attr,
&md_last_scan_mode.attr,
&md_mismatches.attr,
+ &md_logical_block_size.attr,
&md_sync_min.attr,
&md_sync_max.attr,
&md_sync_speed.attr,
@@ -5760,6 +5824,7 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
unsigned int flags)
{
struct md_rdev *rdev;
+ unsigned int lbs = mddev->logical_block_size;
rdev_for_each(rdev, mddev) {
queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
@@ -5768,6 +5833,14 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
!queue_limits_stack_integrity_bdev(lim, rdev->bdev))
return -EINVAL;
}
+ if (lbs) {
+ if (lbs != queue_logical_block_size(mddev->gendisk->queue))
+ pr_warn("%s: logical_block_size is changed, before: %u, now: %u\n",
+ mdname(mddev), lbs,
+ queue_logical_block_size(mddev->gendisk->queue));
+ } else {
+ mddev->logical_block_size = queue_logical_block_size(mddev->gendisk->queue);
+ }
return 0;
}
@@ -6377,6 +6450,7 @@ static void md_clean(struct mddev *mddev)
mddev->chunk_sectors = 0;
mddev->ctime = mddev->utime = 0;
mddev->layout = 0;
+ mddev->logical_block_size = 0;
mddev->max_disks = 0;
mddev->events = 0;
mddev->can_decrease_events = 0;
@@ -382,6 +382,7 @@ static int raid0_set_limits(struct mddev *mddev)
md_init_stacking_limits(&lim);
lim.max_hw_sectors = mddev->chunk_sectors;
lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+ lim.logical_block_size = mddev->logical_block_size;
lim.io_min = mddev->chunk_sectors << 9;
lim.io_opt = lim.io_min * mddev->raid_disks;
lim.features |= BLK_FEAT_ATOMIC_WRITES;
@@ -3217,6 +3217,7 @@ static int raid1_set_limits(struct mddev *mddev)
md_init_stacking_limits(&lim);
lim.max_write_zeroes_sectors = 0;
+ lim.logical_block_size = mddev->logical_block_size;
lim.features |= BLK_FEAT_ATOMIC_WRITES;
err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
if (err)
@@ -4016,6 +4016,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
md_init_stacking_limits(&lim);
lim.max_write_zeroes_sectors = 0;
+ lim.logical_block_size = mddev->logical_block_size;
lim.io_min = mddev->chunk_sectors << 9;
lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
lim.features |= BLK_FEAT_ATOMIC_WRITES;
@@ -7736,6 +7736,7 @@ static int raid5_set_limits(struct mddev *mddev)
stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
md_init_stacking_limits(&lim);
+ lim.logical_block_size = mddev->logical_block_size;
lim.io_min = mddev->chunk_sectors << 9;
lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE;