| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20250825075924.2696723-3-linan666@huaweicloud.com>
Date: Mon, 25 Aug 2025 15:59:24 +0800
From: linan666@...weicloud.com
To: song@...nel.org,
yukuai3@...wei.com
Cc: linux-raid@...r.kernel.org,
linux-kernel@...r.kernel.org,
martin.petersen@...cle.com,
bvanassche@....org,
hch@...radead.org,
filipe.c.maia@...il.com,
linan666@...weicloud.com,
yangerkun@...wei.com,
yi.zhang@...wei.com
Subject: [PATCH v3 2/2] md: allow configuring logical_block_size
From: Li Nan <linan122@...wei.com>
Previously, raid array used the maximum logical_block_size (LBS) of
all member disks. Adding a larger LBS during disk at runtime could
unexpectedly increase RAID's LBS, risking corruption of existing
partitions.
Simply restricting larger-LBS disks is inflexible. In some scenarios,
only disks with 512 LBS are available currently, but later, disks with
4k LBS may be added to the array.
Making LBS configurable is the best way to solve this scenario.
After this patch, the raid will:
- stores LBS in disk metadata.
- add a read-write sysfs 'mdX/logical_block_size'.
Future mdadm should support setting LBS via metadata field during RAID
creation and the new sysfs. Though the kernel allows runtime LBS changes,
users should avoid modifying it after creating partitions or filesystems
to prevent compatibility issues.
Note that many RAID paths rely on PAGE_SIZE alignment, including for
metadata I/O. A logical_block_size larger than PAGE_SIZE will result in
metadata reads/writes failures. So this config should be prevented.
Signed-off-by: Li Nan <linan122@...wei.com>
---
drivers/md/md.h | 1 +
include/uapi/linux/raid/md_p.h | 6 ++-
drivers/md/md-linear.c | 1 +
drivers/md/md.c | 75 ++++++++++++++++++++++++++++++++++
drivers/md/raid0.c | 1 +
drivers/md/raid1.c | 1 +
drivers/md/raid10.c | 1 +
drivers/md/raid5.c | 1 +
8 files changed, 85 insertions(+), 2 deletions(-)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1979c2d4fe89..0202f6feedea 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -432,6 +432,7 @@ 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
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index ac74133a4768..190d493044a8 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -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
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 5d9b08115375..da8babb8da59 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -72,6 +72,7 @@ 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);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 206434591b97..e78f80d39271 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1467,6 +1467,7 @@ 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;
@@ -1629,6 +1630,7 @@ 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);
@@ -1963,6 +1965,7 @@ 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;
@@ -2172,6 +2175,7 @@ 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
@@ -5900,6 +5904,64 @@ 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 (queue_logical_block_size(mddev->gendisk->queue) >= lbs) {
+ pr_err("%s: incompatible logical_block_size %u, can not set\n",
+ mdname(mddev), lbs);
+ return -EINVAL;
+ }
+
+ lim = queue_limits_start_update(mddev->gendisk->queue);
+ lim.logical_block_size = lbs;
+ pr_info("%s: logical_block_size is changed, 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 = -EBUSY;
+
+ if (mddev->pers)
+ goto unlock;
+
+ err = kstrtouint(buf, 10, &lbs);
+ if (err < 0)
+ return err;
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+
+ 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,
@@ -5933,6 +5995,7 @@ 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_io_depth.attr,
@@ -6052,6 +6115,17 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
return -EINVAL;
}
+ /*
+ * Before RAID adding folio support, the logical_block_size
+ * should be smaller than the page size.
+ */
+ if (lim->logical_block_size > PAGE_SIZE) {
+ pr_err("%s: logical_block_size must not larger than PAGE_SIZE\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ mddev->logical_block_size = lim->logical_block_size;
+
return 0;
}
EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
@@ -6690,6 +6764,7 @@ 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;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f1d8811a542a..705889a09fc1 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -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.chunk_sectors = mddev->chunk_sectors;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0e792b9bfff8..3e422854cafb 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3224,6 +3224,7 @@ 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)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 2411399a7352..2dfff3f9ec8e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4005,6 +4005,7 @@ 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.chunk_sectors = mddev->chunk_sectors;
lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2121f0ff5e30..c6bd6d2e4438 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7733,6 +7733,7 @@ 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;
--
2.39.2
Powered by blists - more mailing lists