aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-crypt.c10
-rw-r--r--drivers/md/dm-integrity.c11
-rw-r--r--drivers/md/dm-raid.c4
-rw-r--r--drivers/md/dm-verity.h4
-rw-r--r--drivers/md/dm.c26
-rw-r--r--drivers/md/md.c54
-rw-r--r--drivers/md/raid5.c12
7 files changed, 82 insertions, 39 deletions
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 4301f22bbfa6..6866aa2aade3 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -46,11 +46,11 @@
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;
@@ -1627,6 +1627,12 @@ 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 81157801a3dc..f3246f7407d6 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1582,11 +1582,12 @@ static void integrity_metadata(struct work_struct *w)
}
__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+ struct bio_vec bv_copy = bv;
unsigned pos;
char *mem, *checksums_ptr;
again:
- mem = (char *)kmap_atomic(bv.bv_page) + bv.bv_offset;
+ mem = (char *)kmap_atomic(bv_copy.bv_page) + bv_copy.bv_offset;
pos = 0;
checksums_ptr = checksums;
do {
@@ -1595,7 +1596,7 @@ again:
sectors_to_process -= ic->sectors_per_block;
pos += ic->sectors_per_block << SECTOR_SHIFT;
sector += ic->sectors_per_block;
- } while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack);
+ } while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack);
kunmap_atomic(mem);
r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
@@ -1615,9 +1616,9 @@ again:
if (!sectors_to_process)
break;
- if (unlikely(pos < bv.bv_len)) {
- bv.bv_offset += pos;
- bv.bv_len -= pos;
+ if (unlikely(pos < bv_copy.bv_len)) {
+ bv_copy.bv_offset += pos;
+ bv_copy.bv_len -= pos;
goto again;
}
}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 9f05ae2b9019..1ccd765fad93 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3343,14 +3343,14 @@ 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);
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 74ad36b6dbf5..fee7c7a81ce4 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -73,11 +73,11 @@ 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 771167ee552c..a7724ba45b43 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2809,6 +2809,9 @@ 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)
@@ -2817,12 +2820,23 @@ 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 a006f3a9554b..61c3e8df1b55 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1098,6 +1098,7 @@ 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);
@@ -1236,8 +1237,9 @@ 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);
@@ -1752,7 +1754,7 @@ 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);
@@ -1848,13 +1850,15 @@ 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
@@ -1875,8 +1879,38 @@ 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;
@@ -2780,7 +2814,7 @@ 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);
@@ -3690,7 +3724,7 @@ 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) {
@@ -3705,7 +3739,7 @@ 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);
@@ -6610,7 +6644,7 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *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
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f3d60c4b34b8..0bea103f63d5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,7 +36,6 @@
*/
#include <linux/blkdev.h>
-#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
@@ -6335,18 +6334,7 @@ static void raid5d(struct md_thread *thread)
spin_unlock_irq(&conf->device_lock);
md_check_recovery(mddev);
spin_lock_irq(&conf->device_lock);
-
- /*
- * Waiting on MD_SB_CHANGE_PENDING below may deadlock
- * seeing md_check_recovery() is needed to clear
- * the flag when using mdmon.
- */
- continue;
}
-
- wait_event_lock_irq(mddev->sb_wait,
- !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
- conf->device_lock);
}
pr_debug("%d stripes handled\n", handled);
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-06-04 20:13:52 +0000