summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-core.h2
-rw-r--r--drivers/md/dm-crypt.c10
-rw-r--r--drivers/md/dm-integrity.c2
-rw-r--r--drivers/md/dm-ioctl.c3
-rw-r--r--drivers/md/dm-raid.c6
-rw-r--r--drivers/md/dm-snap.c4
-rw-r--r--drivers/md/dm-table.c9
-rw-r--r--drivers/md/dm-verity.h4
-rw-r--r--drivers/md/dm.c26
-rw-r--r--drivers/md/md.c130
10 files changed, 134 insertions, 62 deletions
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 3db92d9a0..ff73b2c17 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -19,6 +19,8 @@
#include "dm.h"
#define DM_RESERVED_MAX_IOS 1024
+#define DM_MAX_TARGETS 1048576
+#define DM_MAX_TARGET_PARAMS 1024
struct dm_kobject_holder {
struct kobject kobj;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 5d772f322..5deda6c6f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -48,11 +48,11 @@
struct convert_context {
struct completion restart;
struct bio *bio_in;
- struct bio *bio_out;
struct bvec_iter iter_in;
+ struct bio *bio_out;
struct bvec_iter iter_out;
- u64 cc_sector;
atomic_t cc_pending;
+ u64 cc_sector;
union {
struct skcipher_request *req;
struct aead_request *req_aead;
@@ -2064,6 +2064,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
io->ctx.bio_out = clone;
io->ctx.iter_out = clone->bi_iter;
+ if (crypt_integrity_aead(cc)) {
+ bio_copy_data(clone, io->base_bio);
+ io->ctx.bio_in = clone;
+ io->ctx.iter_in = clone->bi_iter;
+ }
+
sector += bio_sectors(clone);
crypt_inc_pending(io);
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 62cae34ca..067be1d9f 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3937,7 +3937,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
} else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) {
log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval);
} else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) {
- if (val >= (uint64_t)UINT_MAX * 1000 / HZ) {
+ if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) {
r = -EINVAL;
ti->error = "Invalid bitmap_flush_interval argument";
goto bad;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 5f9b9178c..4184c8a2d 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1760,7 +1760,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
if (copy_from_user(param_kernel, user, minimum_data_size))
return -EFAULT;
- if (param_kernel->data_size < minimum_data_size)
+ if (unlikely(param_kernel->data_size < minimum_data_size) ||
+ unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS))
return -EINVAL;
secure_data = param_kernel->flags & DM_SECURE_DATA_FLAG;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 140bdf2a6..99995b180 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3329,14 +3329,14 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
struct mddev *mddev = &rs->md;
/*
- * If we're reshaping to add disk(s)), ti->len and
+ * If we're reshaping to add disk(s), ti->len and
* mddev->array_sectors will differ during the process
* (ti->len > mddev->array_sectors), so we have to requeue
* bios with addresses > mddev->array_sectors here or
* there will occur accesses past EOD of the component
* data images thus erroring the raid set.
*/
- if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
+ if (unlikely(bio_has_data(bio) && bio_end_sector(bio) > mddev->array_sectors))
return DM_MAPIO_REQUEUE;
md_handle_request(mddev, bio);
@@ -4019,7 +4019,9 @@ static void raid_resume(struct dm_target *ti)
* Take this opportunity to check whether any failed
* devices are reachable again.
*/
+ mddev_lock_nointr(mddev);
attempt_restore_of_faulty_devices(rs);
+ mddev_unlock(mddev);
}
if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 41735a25d..de73fe796 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -685,8 +685,10 @@ static void dm_exception_table_exit(struct dm_exception_table *et,
for (i = 0; i < size; i++) {
slot = et->table + i;
- hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list)
+ hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) {
kmem_cache_free(mem, ex);
+ cond_resched();
+ }
}
vfree(et->table);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5c590895c..31bcdcd93 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -144,7 +144,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
int dm_table_create(struct dm_table **result, fmode_t mode,
unsigned num_targets, struct mapped_device *md)
{
- struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
+ struct dm_table *t;
+
+ if (num_targets > DM_MAX_TARGETS)
+ return -EOVERFLOW;
+
+ t = kzalloc(sizeof(*t), GFP_KERNEL);
if (!t)
return -ENOMEM;
@@ -158,7 +163,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
if (!num_targets) {
kfree(t);
- return -ENOMEM;
+ return -EOVERFLOW;
}
if (alloc_targets(t, num_targets)) {
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 78d1e5119..f61c89c79 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -74,11 +74,11 @@ struct dm_verity_io {
/* original value of bio->bi_end_io */
bio_end_io_t *orig_bi_end_io;
+ struct bvec_iter iter;
+
sector_t block;
unsigned n_blocks;
- struct bvec_iter iter;
-
struct work_struct work;
/*
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9029c1004..dc8498b4b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2733,6 +2733,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
static void __dm_internal_resume(struct mapped_device *md)
{
+ int r;
+ struct dm_table *map;
+
BUG_ON(!md->internal_suspend_count);
if (--md->internal_suspend_count)
@@ -2741,12 +2744,23 @@ static void __dm_internal_resume(struct mapped_device *md)
if (dm_suspended_md(md))
goto done; /* resume from nested suspend */
- /*
- * NOTE: existing callers don't need to call dm_table_resume_targets
- * (which may fail -- so best to avoid it for now by passing NULL map)
- */
- (void) __dm_resume(md, NULL);
-
+ map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
+ r = __dm_resume(md, map);
+ if (r) {
+ /*
+ * If a preresume method of some target failed, we are in a
+ * tricky situation. We can't return an error to the caller. We
+ * can't fake success because then the "resume" and
+ * "postsuspend" methods would not be paired correctly, and it
+ * would break various targets, for example it would cause list
+ * corruption in the "origin" target.
+ *
+ * So, we fake normal suspend here, to make sure that the
+ * "resume" and "postsuspend" methods will be paired correctly.
+ */
+ DMERR("Preresume method failed: %d", r);
+ set_bit(DMF_SUSPENDED, &md->flags);
+ }
done:
clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
smp_mb__after_atomic();
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6efe49f7b..09c7f5215 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1179,6 +1179,7 @@ struct super_type {
struct md_rdev *refdev,
int minor_version);
int (*validate_super)(struct mddev *mddev,
+ struct md_rdev *freshest,
struct md_rdev *rdev);
void (*sync_super)(struct mddev *mddev,
struct md_rdev *rdev);
@@ -1317,8 +1318,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
/*
* validate_super for 0.90.0
+ * note: we are not using "freshest" for 0.9 superblock
*/
-static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev)
{
mdp_disk_t *desc;
mdp_super_t *sb = page_address(rdev->sb_page);
@@ -1833,7 +1835,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
return ret;
}
-static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev)
{
struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
__u64 ev1 = le64_to_cpu(sb->events);
@@ -1929,13 +1931,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
}
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling, except for
- * spares (which don't need an event count) */
- ++ev1;
+ * spares (which don't need an event count).
+ * Similar to mdadm, we allow event counter difference of 1
+ * from the freshest device.
+ */
if (rdev->desc_nr >= 0 &&
rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
- if (ev1 < mddev->events)
+ if (ev1 + 1 < mddev->events)
return -EINVAL;
} else if (mddev->bitmap) {
/* If adding to array with a bitmap, then we can accept an
@@ -1956,8 +1960,38 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
role = MD_DISK_ROLE_SPARE;
rdev->desc_nr = -1;
- } else
+ } else if (mddev->pers == NULL && freshest && ev1 < mddev->events) {
+ /*
+ * If we are assembling, and our event counter is smaller than the
+ * highest event counter, we cannot trust our superblock about the role.
+ * It could happen that our rdev was marked as Faulty, and all other
+ * superblocks were updated with +1 event counter.
+ * Then, before the next superblock update, which typically happens when
+ * remove_and_add_spares() removes the device from the array, there was
+ * a crash or reboot.
+ * If we allow current rdev without consulting the freshest superblock,
+ * we could cause data corruption.
+ * Note that in this case our event counter is smaller by 1 than the
+ * highest, otherwise, this rdev would not be allowed into array;
+ * both kernel and mdadm allow event counter difference of 1.
+ */
+ struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page);
+ u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev);
+
+ if (rdev->desc_nr >= freshest_max_dev) {
+ /* this is unexpected, better not proceed */
+ pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n",
+ mdname(mddev), rdev->bdev, rdev->desc_nr,
+ freshest->bdev, freshest_max_dev);
+ return -EUCLEAN;
+ }
+
+ role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]);
+ pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n",
+ mdname(mddev), rdev->bdev, role, role, freshest->bdev);
+ } else {
role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+ }
switch(role) {
case MD_DISK_ROLE_SPARE: /* spare */
break;
@@ -2896,7 +2930,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
* and should be added immediately.
*/
super_types[mddev->major_version].
- validate_super(mddev, rdev);
+ validate_super(mddev, NULL/*freshest*/, rdev);
if (add_journal)
mddev_suspend(mddev);
err = mddev->pers->hot_add_disk(mddev, rdev);
@@ -3814,7 +3848,7 @@ static int analyze_sbs(struct mddev *mddev)
}
super_types[mddev->major_version].
- validate_super(mddev, freshest);
+ validate_super(mddev, NULL/*freshest*/, freshest);
i = 0;
rdev_for_each_safe(rdev, tmp, mddev) {
@@ -3829,7 +3863,7 @@ static int analyze_sbs(struct mddev *mddev)
}
if (rdev != freshest) {
if (super_types[mddev->major_version].
- validate_super(mddev, rdev)) {
+ validate_super(mddev, freshest, rdev)) {
pr_warn("md: kicking non-fresh %s from array!\n",
bdevname(rdev->bdev,b));
md_kick_rdev_from_array(rdev);
@@ -6209,7 +6243,15 @@ static void md_clean(struct mddev *mddev)
mddev->persistent = 0;
mddev->level = LEVEL_NONE;
mddev->clevel[0] = 0;
- mddev->flags = 0;
+ /*
+ * Don't clear MD_CLOSING, or mddev can be opened again.
+ * 'hold_active != 0' means mddev is still in the creation
+ * process and will be used later.
+ */
+ if (mddev->hold_active)
+ mddev->flags = 0;
+ else
+ mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
mddev->sb_flags = 0;
mddev->ro = 0;
mddev->metadata_type[0] = 0;
@@ -6817,7 +6859,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info)
rdev->saved_raid_disk = rdev->raid_disk;
} else
super_types[mddev->major_version].
- validate_super(mddev, rdev);
+ validate_super(mddev, NULL/*freshest*/, rdev);
if ((info->state & (1<<MD_DISK_SYNC)) &&
rdev->raid_disk != info->raid_disk) {
/* This was a hot-add request, but events doesn't
@@ -7502,7 +7544,6 @@ static inline bool md_ioctl_valid(unsigned int cmd)
{
switch (cmd) {
case ADD_NEW_DISK:
- case BLKROSET:
case GET_ARRAY_INFO:
case GET_BITMAP_FILE:
case GET_DISK_INFO:
@@ -7529,8 +7570,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
int err = 0;
void __user *argp = (void __user *)arg;
struct mddev *mddev = NULL;
- int ro;
- bool did_set_md_closing = false;
if (!md_ioctl_valid(cmd))
return -ENOTTY;
@@ -7617,7 +7656,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
err = -EBUSY;
goto out;
}
- did_set_md_closing = true;
mutex_unlock(&mddev->open_mutex);
sync_blockdev(bdev);
}
@@ -7712,35 +7750,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
goto unlock;
}
break;
-
- case BLKROSET:
- if (get_user(ro, (int __user *)(arg))) {
- err = -EFAULT;
- goto unlock;
- }
- err = -EINVAL;
-
- /* if the bdev is going readonly the value of mddev->ro
- * does not matter, no writes are coming
- */
- if (ro)
- goto unlock;
-
- /* are we are already prepared for writes? */
- if (mddev->ro != 1)
- goto unlock;
-
- /* transitioning to readauto need only happen for
- * arrays that call md_write_start
- */
- if (mddev->pers) {
- err = restart_array(mddev);
- if (err == 0) {
- mddev->ro = 2;
- set_disk_ro(mddev->gendisk, 0);
- }
- }
- goto unlock;
}
/*
@@ -7810,7 +7819,7 @@ unlock:
mddev->hold_active = 0;
mddev_unlock(mddev);
out:
- if(did_set_md_closing)
+ if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY))
clear_bit(MD_CLOSING, &mddev->flags);
return err;
}
@@ -7834,6 +7843,36 @@ static int md_compat_ioctl(struct block_device *bdev, fmode_t mode,
}
#endif /* CONFIG_COMPAT */
+static int md_set_read_only(struct block_device *bdev, bool ro)
+{
+ struct mddev *mddev = bdev->bd_disk->private_data;
+ int err;
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+
+ if (!mddev->raid_disks && !mddev->external) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+
+ /*
+ * Transitioning to read-auto need only happen for arrays that call
+ * md_write_start and which are not ready for writes yet.
+ */
+ if (!ro && mddev->ro == 1 && mddev->pers) {
+ err = restart_array(mddev);
+ if (err)
+ goto out_unlock;
+ mddev->ro = 2;
+ }
+
+out_unlock:
+ mddev_unlock(mddev);
+ return err;
+}
+
static int md_open(struct block_device *bdev, fmode_t mode)
{
/*
@@ -7910,6 +7949,7 @@ const struct block_device_operations md_fops =
#endif
.getgeo = md_getgeo,
.check_events = md_check_events,
+ .set_read_only = md_set_read_only,
};
static int md_thread(void *arg)
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-23 07:19:26 +0000