summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-02-22 10:22:54 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2021-02-22 10:22:54 -0800
commit325b764089c9bef2be45354db4f15e5b12ae406d (patch)
tree3f06f8a8054874caf45242f57885a9a64e6ea57b /drivers/md
parenta99163e9e708d5d773b7de6da952fcddc341f977 (diff)
parenta666e5c05e7c4aaabb2c5d58117b0946803d03d2 (diff)
Merge tag 'for-5.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper updates from Mike Snitzer: - Fix DM integrity's HMAC support to provide enhanced security of internal_hash and journal_mac capabilities. - Various DM writecache fixes to address performance, fix table output to match what was provided at table creation, fix writing beyond end of device when shrinking underlying data device, and a couple other small cleanups. - Add DM crypt support for using trusted keys. - Fix deadlock when swapping to DM crypt device by throttling number of in-flight REQ_SWAP bios. Implemented in DM core so that other bio-based targets can opt-in by setting ti->limit_swap_bios. - Fix various inverted logic bugs in the .iterate_devices callout functions that are used to assess if specific feature or capability is supported across all devices being combined/stacked by DM. - Fix DM era target bugs that exposed users to lost writes or memory leaks. - Add DM core support for passing through inline crypto support of underlying devices. Includes block/keyslot-manager changes that enable extending this support to DM. - Various small fixes and cleanups (spelling fixes, front padding calculation cleanup, cleanup conditional zoned support in targets, etc). * tag 'for-5.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (31 commits) dm: fix deadlock when swapping to encrypted device dm: simplify target code conditional on CONFIG_BLK_DEV_ZONED dm: set DM_TARGET_PASSES_CRYPTO feature for some targets dm: support key eviction from keyslot managers of underlying devices dm: add support for passing through inline crypto support block/keyslot-manager: Introduce functions for device mapper support block/keyslot-manager: Introduce passthrough keyslot manager dm era: only resize metadata in preresume dm era: Use correct value size in equality function of writeset tree dm era: Fix bitset memory leaks dm era: Verify the data block size hasn't changed dm era: Reinitialize bitset cache before digesting a new writeset dm era: Update in-core bitset after committing the metadata dm era: Recover committed writeset after crash dm writecache: use bdev_nr_sectors() instead of open-coded equivalent dm writecache: fix writing beyond end of underlying device when shrinking dm table: remove needless request_queue NULL pointer checks dm table: fix zoned iterate_devices based device capability checks dm table: fix DAX iterate_devices based device capability checks dm table: fix iterate_devices based device capability checks ...
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/Kconfig1
-rw-r--r--drivers/md/dm-core.h9
-rw-r--r--drivers/md/dm-crypt.c39
-rw-r--r--drivers/md/dm-dust.c2
-rw-r--r--drivers/md/dm-era-target.c93
-rw-r--r--drivers/md/dm-flakey.c6
-rw-r--r--drivers/md/dm-integrity.c140
-rw-r--r--drivers/md/dm-linear.c8
-rw-r--r--drivers/md/dm-table.c399
-rw-r--r--drivers/md/dm-writecache.c80
-rw-r--r--drivers/md/dm.c96
-rw-r--r--drivers/md/dm.h2
-rw-r--r--drivers/md/persistent-data/dm-btree-internal.h2
-rw-r--r--drivers/md/persistent-data/dm-btree-spine.c2
14 files changed, 666 insertions, 213 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 9e44c09f6410..f2014385d48b 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -270,6 +270,7 @@ config DM_CRYPT
tristate "Crypt target support"
depends on BLK_DEV_DM
depends on (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
+ depends on (TRUSTED_KEYS || TRUSTED_KEYS=n)
select CRYPTO
select CRYPTO_CBC
select CRYPTO_ESSIV
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 086d293c2b03..5953ff2bd260 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -13,6 +13,7 @@
#include <linux/ktime.h>
#include <linux/genhd.h>
#include <linux/blk-mq.h>
+#include <linux/keyslot-manager.h>
#include <trace/events/block.h>
@@ -102,6 +103,10 @@ struct mapped_device {
/* kobject and completion */
struct dm_kobject_holder kobj_holder;
+ int swap_bios;
+ struct semaphore swap_bios_semaphore;
+ struct mutex swap_bios_lock;
+
struct dm_stats stats;
/* for blk-mq request-based DM support */
@@ -162,6 +167,10 @@ struct dm_table {
void *event_context;
struct dm_md_mempools *mempools;
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+ struct blk_keyslot_manager *ksm;
+#endif
};
static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 5a55617a08e6..11c105ecd165 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -37,6 +37,7 @@
#include <linux/key-type.h>
#include <keys/user-type.h>
#include <keys/encrypted-type.h>
+#include <keys/trusted-type.h>
#include <linux/device-mapper.h>
@@ -133,7 +134,7 @@ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
DM_CRYPT_WRITE_INLINE };
enum cipher_flags {
- CRYPT_MODE_INTEGRITY_AEAD, /* Use authenticated mode for cihper */
+ CRYPT_MODE_INTEGRITY_AEAD, /* Use authenticated mode for cipher */
CRYPT_IV_LARGE_SECTORS, /* Calculate IV from sector_size, not 512B sectors */
CRYPT_ENCRYPT_PREPROCESS, /* Must preprocess data for encryption (elephant) */
};
@@ -2436,7 +2437,6 @@ static int set_key_user(struct crypt_config *cc, struct key *key)
return 0;
}
-#if defined(CONFIG_ENCRYPTED_KEYS) || defined(CONFIG_ENCRYPTED_KEYS_MODULE)
static int set_key_encrypted(struct crypt_config *cc, struct key *key)
{
const struct encrypted_key_payload *ekp;
@@ -2452,7 +2452,22 @@ static int set_key_encrypted(struct crypt_config *cc, struct key *key)
return 0;
}
-#endif /* CONFIG_ENCRYPTED_KEYS */
+
+static int set_key_trusted(struct crypt_config *cc, struct key *key)
+{
+ const struct trusted_key_payload *tkp;
+
+ tkp = key->payload.data[0];
+ if (!tkp)
+ return -EKEYREVOKED;
+
+ if (cc->key_size != tkp->key_len)
+ return -EINVAL;
+
+ memcpy(cc->key, tkp->key, cc->key_size);
+
+ return 0;
+}
static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string)
{
@@ -2482,11 +2497,14 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
} else if (!strncmp(key_string, "user:", key_desc - key_string + 1)) {
type = &key_type_user;
set_key = set_key_user;
-#if defined(CONFIG_ENCRYPTED_KEYS) || defined(CONFIG_ENCRYPTED_KEYS_MODULE)
- } else if (!strncmp(key_string, "encrypted:", key_desc - key_string + 1)) {
+ } else if (IS_ENABLED(CONFIG_ENCRYPTED_KEYS) &&
+ !strncmp(key_string, "encrypted:", key_desc - key_string + 1)) {
type = &key_type_encrypted;
set_key = set_key_encrypted;
-#endif
+ } else if (IS_ENABLED(CONFIG_TRUSTED_KEYS) &&
+ !strncmp(key_string, "trusted:", key_desc - key_string + 1)) {
+ type = &key_type_trusted;
+ set_key = set_key_trusted;
} else {
return -EINVAL;
}
@@ -3116,7 +3134,6 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
}
#ifdef CONFIG_BLK_DEV_ZONED
-
static int crypt_report_zones(struct dm_target *ti,
struct dm_report_zones_args *args, unsigned int nr_zones)
{
@@ -3127,7 +3144,8 @@ static int crypt_report_zones(struct dm_target *ti,
return blkdev_report_zones(cc->dev->bdev, sector, nr_zones,
dm_report_zones_cb, args);
}
-
+#else
+#define crypt_report_zones NULL
#endif
/*
@@ -3324,6 +3342,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
wake_up_process(cc->write_thread);
ti->num_flush_bios = 1;
+ ti->limit_swap_bios = true;
return 0;
@@ -3558,14 +3577,12 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
static struct target_type crypt_target = {
.name = "crypt",
- .version = {1, 22, 0},
+ .version = {1, 23, 0},
.module = THIS_MODULE,
.ctr = crypt_ctr,
.dtr = crypt_dtr,
-#ifdef CONFIG_BLK_DEV_ZONED
.features = DM_TARGET_ZONED_HM,
.report_zones = crypt_report_zones,
-#endif
.map = crypt_map,
.status = crypt_status,
.postsuspend = crypt_postsuspend,
diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c
index 072ea913cebc..cbe1058ee589 100644
--- a/drivers/md/dm-dust.c
+++ b/drivers/md/dm-dust.c
@@ -130,7 +130,7 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block,
dd->badblock_count++;
if (!dd->quiet_mode) {
- DMINFO("%s: badblock added at block %llu with write fail count %hhu",
+ DMINFO("%s: badblock added at block %llu with write fail count %u",
__func__, block, wr_fail_cnt);
}
spin_unlock_irqrestore(&dd->dust_lock, flags);
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index b24e3839bb3a..d9ac7372108c 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -47,6 +47,7 @@ struct writeset {
static void writeset_free(struct writeset *ws)
{
vfree(ws->bits);
+ ws->bits = NULL;
}
static int setup_on_disk_bitset(struct dm_disk_bitset *info,
@@ -71,8 +72,6 @@ static size_t bitset_size(unsigned nr_bits)
*/
static int writeset_alloc(struct writeset *ws, dm_block_t nr_blocks)
{
- ws->md.nr_bits = nr_blocks;
- ws->md.root = INVALID_WRITESET_ROOT;
ws->bits = vzalloc(bitset_size(nr_blocks));
if (!ws->bits) {
DMERR("%s: couldn't allocate in memory bitset", __func__);
@@ -85,12 +84,14 @@ static int writeset_alloc(struct writeset *ws, dm_block_t nr_blocks)
/*
* Wipes the in-core bitset, and creates a new on disk bitset.
*/
-static int writeset_init(struct dm_disk_bitset *info, struct writeset *ws)
+static int writeset_init(struct dm_disk_bitset *info, struct writeset *ws,
+ dm_block_t nr_blocks)
{
int r;
- memset(ws->bits, 0, bitset_size(ws->md.nr_bits));
+ memset(ws->bits, 0, bitset_size(nr_blocks));
+ ws->md.nr_bits = nr_blocks;
r = setup_on_disk_bitset(info, ws->md.nr_bits, &ws->md.root);
if (r) {
DMERR("%s: setup_on_disk_bitset failed", __func__);
@@ -134,7 +135,7 @@ static int writeset_test_and_set(struct dm_disk_bitset *info,
{
int r;
- if (!test_and_set_bit(block, ws->bits)) {
+ if (!test_bit(block, ws->bits)) {
r = dm_bitset_set_bit(info, ws->md.root, block, &ws->md.root);
if (r) {
/* FIXME: fail mode */
@@ -388,7 +389,7 @@ static void ws_dec(void *context, const void *value)
static int ws_eq(void *context, const void *value1, const void *value2)
{
- return !memcmp(value1, value2, sizeof(struct writeset_metadata));
+ return !memcmp(value1, value2, sizeof(struct writeset_disk));
}
/*----------------------------------------------------------------*/
@@ -564,6 +565,15 @@ static int open_metadata(struct era_metadata *md)
}
disk = dm_block_data(sblock);
+
+ /* Verify the data block size hasn't changed */
+ if (le32_to_cpu(disk->data_block_size) != md->block_size) {
+ DMERR("changing the data block size (from %u to %llu) is not supported",
+ le32_to_cpu(disk->data_block_size), md->block_size);
+ r = -EINVAL;
+ goto bad;
+ }
+
r = dm_tm_open_with_sm(md->bm, SUPERBLOCK_LOCATION,
disk->metadata_space_map_root,
sizeof(disk->metadata_space_map_root),
@@ -575,10 +585,10 @@ static int open_metadata(struct era_metadata *md)
setup_infos(md);
- md->block_size = le32_to_cpu(disk->data_block_size);
md->nr_blocks = le32_to_cpu(disk->nr_blocks);
md->current_era = le32_to_cpu(disk->current_era);
+ ws_unpack(&disk->current_writeset, &md->current_writeset->md);
md->writeset_tree_root = le64_to_cpu(disk->writeset_tree_root);
md->era_array_root = le64_to_cpu(disk->era_array_root);
md->metadata_snap = le64_to_cpu(disk->metadata_snap);
@@ -746,6 +756,12 @@ static int metadata_digest_lookup_writeset(struct era_metadata *md,
ws_unpack(&disk, &d->writeset);
d->value = cpu_to_le32(key);
+ /*
+ * We initialise another bitset info to avoid any caching side effects
+ * with the previous one.
+ */
+ dm_disk_bitset_init(md->tm, &d->info);
+
d->nr_bits = min(d->writeset.nr_bits, md->nr_blocks);
d->current_bit = 0;
d->step = metadata_digest_transcribe_writeset;
@@ -759,12 +775,6 @@ static int metadata_digest_start(struct era_metadata *md, struct digest *d)
return 0;
memset(d, 0, sizeof(*d));
-
- /*
- * We initialise another bitset info to avoid any caching side
- * effects with the previous one.
- */
- dm_disk_bitset_init(md->tm, &d->info);
d->step = metadata_digest_lookup_writeset;
return 0;
@@ -802,6 +812,8 @@ static struct era_metadata *metadata_open(struct block_device *bdev,
static void metadata_close(struct era_metadata *md)
{
+ writeset_free(&md->writesets[0]);
+ writeset_free(&md->writesets[1]);
destroy_persistent_data_objects(md);
kfree(md);
}
@@ -839,6 +851,7 @@ static int metadata_resize(struct era_metadata *md, void *arg)
r = writeset_alloc(&md->writesets[1], *new_size);
if (r) {
DMERR("%s: writeset_alloc failed for writeset 1", __func__);
+ writeset_free(&md->writesets[0]);
return r;
}
@@ -849,6 +862,8 @@ static int metadata_resize(struct era_metadata *md, void *arg)
&value, &md->era_array_root);
if (r) {
DMERR("%s: dm_array_resize failed", __func__);
+ writeset_free(&md->writesets[0]);
+ writeset_free(&md->writesets[1]);
return r;
}
@@ -870,7 +885,6 @@ static int metadata_era_archive(struct era_metadata *md)
}
ws_pack(&md->current_writeset->md, &value);
- md->current_writeset->md.root = INVALID_WRITESET_ROOT;
keys[0] = md->current_era;
__dm_bless_for_disk(&value);
@@ -882,6 +896,7 @@ static int metadata_era_archive(struct era_metadata *md)
return r;
}
+ md->current_writeset->md.root = INVALID_WRITESET_ROOT;
md->archived_writesets = true;
return 0;
@@ -898,7 +913,7 @@ static int metadata_new_era(struct era_metadata *md)
int r;
struct writeset *new_writeset = next_writeset(md);
- r = writeset_init(&md->bitset_info, new_writeset);
+ r = writeset_init(&md->bitset_info, new_writeset, md->nr_blocks);
if (r) {
DMERR("%s: writeset_init failed", __func__);
return r;
@@ -951,7 +966,7 @@ static int metadata_commit(struct era_metadata *md)
int r;
struct dm_block *sblock;
- if (md->current_writeset->md.root != SUPERBLOCK_LOCATION) {
+ if (md->current_writeset->md.root != INVALID_WRITESET_ROOT) {
r = dm_bitset_flush(&md->bitset_info, md->current_writeset->md.root,
&md->current_writeset->md.root);
if (r) {
@@ -1225,8 +1240,10 @@ static void process_deferred_bios(struct era *era)
int r;
struct bio_list deferred_bios, marked_bios;
struct bio *bio;
+ struct blk_plug plug;
bool commit_needed = false;
bool failed = false;
+ struct writeset *ws = era->md->current_writeset;
bio_list_init(&deferred_bios);
bio_list_init(&marked_bios);
@@ -1236,9 +1253,11 @@ static void process_deferred_bios(struct era *era)
bio_list_init(&era->deferred_bios);
spin_unlock(&era->deferred_lock);
+ if (bio_list_empty(&deferred_bios))
+ return;
+
while ((bio = bio_list_pop(&deferred_bios))) {
- r = writeset_test_and_set(&era->md->bitset_info,
- era->md->current_writeset,
+ r = writeset_test_and_set(&era->md->bitset_info, ws,
get_block(era, bio));
if (r < 0) {
/*
@@ -1246,7 +1265,6 @@ static void process_deferred_bios(struct era *era)
* FIXME: finish.
*/
failed = true;
-
} else if (r == 0)
commit_needed = true;
@@ -1262,9 +1280,19 @@ static void process_deferred_bios(struct era *era)
if (failed)
while ((bio = bio_list_pop(&marked_bios)))
bio_io_error(bio);
- else
- while ((bio = bio_list_pop(&marked_bios)))
+ else {
+ blk_start_plug(&plug);
+ while ((bio = bio_list_pop(&marked_bios))) {
+ /*
+ * Only update the in-core writeset if the on-disk one
+ * was updated too.
+ */
+ if (commit_needed)
+ set_bit(get_block(era, bio), ws->bits);
submit_bio_noacct(bio);
+ }
+ blk_finish_plug(&plug);
+ }
}
static void process_rpc_calls(struct era *era)
@@ -1473,15 +1501,6 @@ static int era_ctr(struct dm_target *ti, unsigned argc, char **argv)
}
era->md = md;
- era->nr_blocks = calc_nr_blocks(era);
-
- r = metadata_resize(era->md, &era->nr_blocks);
- if (r) {
- ti->error = "couldn't resize metadata";
- era_destroy(era);
- return -ENOMEM;
- }
-
era->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM);
if (!era->wq) {
ti->error = "could not create workqueue for metadata object";
@@ -1556,16 +1575,24 @@ static int era_preresume(struct dm_target *ti)
dm_block_t new_size = calc_nr_blocks(era);
if (era->nr_blocks != new_size) {
- r = in_worker1(era, metadata_resize, &new_size);
- if (r)
+ r = metadata_resize(era->md, &new_size);
+ if (r) {
+ DMERR("%s: metadata_resize failed", __func__);
+ return r;
+ }
+
+ r = metadata_commit(era->md);
+ if (r) {
+ DMERR("%s: metadata_commit failed", __func__);
return r;
+ }
era->nr_blocks = new_size;
}
start_worker(era);
- r = in_worker0(era, metadata_new_era);
+ r = in_worker0(era, metadata_era_rollover);
if (r) {
DMERR("%s: metadata_era_rollover failed", __func__);
return r;
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index a2cc9e45cbba..b7fee9936f05 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -469,6 +469,8 @@ static int flakey_report_zones(struct dm_target *ti,
return blkdev_report_zones(fc->dev->bdev, sector, nr_zones,
dm_report_zones_cb, args);
}
+#else
+#define flakey_report_zones NULL
#endif
static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
@@ -481,10 +483,8 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_
static struct target_type flakey_target = {
.name = "flakey",
.version = {1, 5, 0},
-#ifdef CONFIG_BLK_DEV_ZONED
- .features = DM_TARGET_ZONED_HM,
+ .features = DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO,
.report_zones = flakey_report_zones,
-#endif
.module = THIS_MODULE,
.ctr = flakey_ctr,
.dtr = flakey_dtr,
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index b64fede032dc..46b5d542b8fe 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -40,6 +40,7 @@
#define BITMAP_BLOCK_SIZE 4096 /* don't change it */
#define BITMAP_FLUSH_INTERVAL (10 * HZ)
#define DISCARD_FILLER 0xf6
+#define SALT_SIZE 16
/*
* Warning - DEBUG_PRINT prints security-sensitive data to the log,
@@ -57,6 +58,7 @@
#define SB_VERSION_2 2
#define SB_VERSION_3 3
#define SB_VERSION_4 4
+#define SB_VERSION_5 5
#define SB_SECTORS 8
#define MAX_SECTORS_PER_BLOCK 8
@@ -72,12 +74,15 @@ struct superblock {
__u8 log2_blocks_per_bitmap_bit;
__u8 pad[2];
__u64 recalc_sector;
+ __u8 pad2[8];
+ __u8 salt[SALT_SIZE];
};
#define SB_FLAG_HAVE_JOURNAL_MAC 0x1
#define SB_FLAG_RECALCULATING 0x2
#define SB_FLAG_DIRTY_BITMAP 0x4
#define SB_FLAG_FIXED_PADDING 0x8
+#define SB_FLAG_FIXED_HMAC 0x10
#define JOURNAL_ENTRY_ROUNDUP 8
@@ -259,6 +264,7 @@ struct dm_integrity_c {
bool recalculate_flag;
bool discard;
bool fix_padding;
+ bool fix_hmac;
bool legacy_recalculate;
struct alg_spec internal_hash_alg;
@@ -389,8 +395,11 @@ static int dm_integrity_failed(struct dm_integrity_c *ic)
static bool dm_integrity_disable_recalculate(struct dm_integrity_c *ic)
{
- if ((ic->internal_hash_alg.key || ic->journal_mac_alg.key) &&
- !ic->legacy_recalculate)
+ if (ic->legacy_recalculate)
+ return false;
+ if (!(ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) ?
+ ic->internal_hash_alg.key || ic->journal_mac_alg.key :
+ ic->internal_hash_alg.key && !ic->journal_mac_alg.key)
return true;
return false;
}
@@ -477,7 +486,9 @@ static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr)
static void sb_set_version(struct dm_integrity_c *ic)
{
- if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING))
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC))
+ ic->sb->version = SB_VERSION_5;
+ else if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING))
ic->sb->version = SB_VERSION_4;
else if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP))
ic->sb->version = SB_VERSION_3;
@@ -487,10 +498,58 @@ static void sb_set_version(struct dm_integrity_c *ic)
ic->sb->version = SB_VERSION_1;
}
+static int sb_mac(struct dm_integrity_c *ic, bool wr)
+{
+ SHASH_DESC_ON_STACK(desc, ic->journal_mac);
+ int r;
+ unsigned size = crypto_shash_digestsize(ic->journal_mac);
+
+ if (sizeof(struct superblock) + size > 1 << SECTOR_SHIFT) {
+ dm_integrity_io_error(ic, "digest is too long", -EINVAL);
+ return -EINVAL;
+ }
+
+ desc->tfm = ic->journal_mac;
+
+ r = crypto_shash_init(desc);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_init", r);
+ return r;
+ }
+
+ r = crypto_shash_update(desc, (__u8 *)ic->sb, (1 << SECTOR_SHIFT) - size);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_update", r);
+ return r;
+ }
+
+ if (likely(wr)) {
+ r = crypto_shash_final(desc, (__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_final", r);
+ return r;
+ }
+ } else {
+ __u8 result[HASH_MAX_DIGESTSIZE];
+ r = crypto_shash_final(desc, result);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_final", r);
+ return r;
+ }
+ if (memcmp((__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size, result, size)) {
+ dm_integrity_io_error(ic, "superblock mac", -EILSEQ);
+ return -EILSEQ;
+ }
+ }
+
+ return 0;
+}
+
static int sync_rw_sb(struct dm_integrity_c *ic, int op, int op_flags)
{
struct dm_io_request io_req;
struct dm_io_region io_loc;
+ int r;
io_req.bi_op = op;
io_req.bi_op_flags = op_flags;
@@ -502,10 +561,28 @@ static int sync_rw_sb(struct dm_integrity_c *ic, int op, int op_flags)
io_loc.sector = ic->start;
io_loc.count = SB_SECTORS;
- if (op == REQ_OP_WRITE)
+ if (op == REQ_OP_WRITE) {
sb_set_version(ic);
+ if (ic->journal_mac && ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
+ r = sb_mac(ic, true);
+ if (unlikely(r))
+ return r;
+ }
+ }
- return dm_io(&io_req, 1, &io_loc, NULL);
+ r = dm_io(&io_req, 1, &io_loc, NULL);
+ if (unlikely(r))
+ return r;
+
+ if (op == REQ_OP_READ) {
+ if (ic->mode != 'R' && ic->journal_mac && ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
+ r = sb_mac(ic, false);
+ if (unlikely(r))
+ return r;
+ }
+ }
+
+ return 0;
}
#define BITMAP_OP_TEST_ALL_SET 0
@@ -722,15 +799,32 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result
desc->tfm = ic->journal_mac;
r = crypto_shash_init(desc);
- if (unlikely(r)) {
+ if (unlikely(r < 0)) {
dm_integrity_io_error(ic, "crypto_shash_init", r);
goto err;
}
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
+ uint64_t section_le;
+
+ r = crypto_shash_update(desc, (__u8 *)&ic->sb->salt, SALT_SIZE);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_update", r);
+ goto err;
+ }
+
+ section_le = cpu_to_le64(section);
+ r = crypto_shash_update(desc, (__u8 *)&section_le, sizeof section_le);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_update", r);
+ goto err;
+ }
+ }
+
for (j = 0; j < ic->journal_section_entries; j++) {
struct journal_entry *je = access_journal_entry(ic, section, j);
r = crypto_shash_update(desc, (__u8 *)&je->u.sector, sizeof je->u.sector);
- if (unlikely(r)) {
+ if (unlikely(r < 0)) {
dm_integrity_io_error(ic, "crypto_shash_update", r);
goto err;
}
@@ -740,7 +834,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result
if (likely(size <= JOURNAL_MAC_SIZE)) {
r = crypto_shash_final(desc, result);
- if (unlikely(r)) {
+ if (unlikely(r < 0)) {
dm_integrity_io_error(ic, "crypto_shash_final", r);
goto err;
}
@@ -753,7 +847,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result
goto err;
}
r = crypto_shash_final(desc, digest);
- if (unlikely(r)) {
+ if (unlikely(r < 0)) {
dm_integrity_io_error(ic, "crypto_shash_final", r);
goto err;
}
@@ -1399,7 +1493,7 @@ static void flush_notify(unsigned long error, void *fr_)
{
struct flush_request *fr = fr_;
if (unlikely(error != 0))
- dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+ dm_integrity_io_error(fr->ic, "flushing disk cache", -EIO);
complete(&fr->comp);
}
@@ -1556,6 +1650,14 @@ static void integrity_sector_checksum(struct dm_integrity_c *ic, sector_t sector
goto failed;
}
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
+ r = crypto_shash_update(req, (__u8 *)&ic->sb->salt, SALT_SIZE);
+ if (unlikely(r < 0)) {
+ dm_integrity_io_error(ic, "crypto_shash_update", r);
+ goto failed;
+ }
+ }
+
r = crypto_shash_update(req, (const __u8 *)&sector_le, sizeof sector_le);
if (unlikely(r < 0)) {
dm_integrity_io_error(ic, "crypto_shash_update", r);
@@ -3149,6 +3251,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
arg_count += !!ic->journal_crypt_alg.alg_string;
arg_count += !!ic->journal_mac_alg.alg_string;
arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0;
+ arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) != 0;
arg_count += ic->legacy_recalculate;
DMEMIT("%s %llu %u %c %u", ic->dev->name, ic->start,
ic->tag_size, ic->mode, arg_count);
@@ -3173,6 +3276,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
}
if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0)
DMEMIT(" fix_padding");
+ if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) != 0)
+ DMEMIT(" fix_hmac");
if (ic->legacy_recalculate)
DMEMIT(" legacy_recalculate");
@@ -3310,6 +3415,11 @@ static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sec
if (!journal_sections)
journal_sections = 1;
+ if (ic->fix_hmac && (ic->internal_hash_alg.alg_string || ic->journal_mac_alg.alg_string)) {
+ ic->sb->flags |= cpu_to_le32(SB_FLAG_FIXED_HMAC);
+ get_random_bytes(ic->sb->salt, SALT_SIZE);
+ }
+
if (!ic->meta_dev) {
if (ic->fix_padding)
ic->sb->flags |= cpu_to_le32(SB_FLAG_FIXED_PADDING);
@@ -3804,7 +3914,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
unsigned extra_args;
struct dm_arg_set as;
static const struct dm_arg _args[] = {
- {0, 16, "Invalid number of feature args"},
+ {0, 17, "Invalid number of feature args"},
};
unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
bool should_write_sb;
@@ -3942,7 +4052,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
if (r)
goto bad;
} else if (!strncmp(opt_string, "journal_mac:", strlen("journal_mac:"))) {
- r = get_alg_and_key(opt_string, &ic->journal_mac_alg, &ti->error,
+ r = get_alg_and_key(opt_string, &ic->journal_mac_alg, &ti->error,
"Invalid journal_mac argument");
if (r)
goto bad;
@@ -3952,6 +4062,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
ic->discard = true;
} else if (!strcmp(opt_string, "fix_padding")) {
ic->fix_padding = true;
+ } else if (!strcmp(opt_string, "fix_hmac")) {
+ ic->fix_hmac = true;
} else if (!strcmp(opt_string, "legacy_recalculate")) {
ic->legacy_recalculate = true;
} else {
@@ -4110,7 +4222,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
should_write_sb = true;
}
- if (!ic->sb->version || ic->sb->version > SB_VERSION_4) {
+ if (!ic->sb->version || ic->sb->version > SB_VERSION_5) {
r = -EINVAL;
ti->error = "Unknown version";
goto bad;
@@ -4442,7 +4554,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
static struct target_type integrity_target = {
.name = "integrity",
- .version = {1, 6, 0},
+ .version = {1, 7, 0},
.module = THIS_MODULE,
.features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
.ctr = dm_integrity_ctr,
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 00774b5d7668..92db0f5e7f28 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -146,6 +146,8 @@ static int linear_report_zones(struct dm_target *ti,
return blkdev_report_zones(lc->dev->bdev, sector, nr_zones,
dm_report_zones_cb, args);
}
+#else
+#define linear_report_zones NULL
#endif
static int linear_iterate_devices(struct dm_target *ti,
@@ -227,13 +229,9 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
static struct target_type linear_target = {
.name = "linear",
.version = {1, 4, 0},
-#ifdef CONFIG_BLK_DEV_ZONED
.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
- DM_TARGET_ZONED_HM,
+ DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO,
.report_zones = linear_report_zones,
-#else
- .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
-#endif
.module = THIS_MODULE,
.ctr = linear_ctr,
.dtr = linear_dtr,
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 4acf2342f7ad..95391f78b8d5 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -187,6 +187,8 @@ static void free_devices(struct list_head *devices, struct mapped_device *md)
}
}
+static void dm_table_destroy_keyslot_manager(struct dm_table *t);
+
void dm_table_destroy(struct dm_table *t)
{
unsigned int i;
@@ -215,6 +217,8 @@ void dm_table_destroy(struct dm_table *t)
dm_free_md_mempools(t->mempools);
+ dm_table_destroy_keyslot_manager(t);
+
kfree(t);
}
@@ -820,24 +824,24 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
EXPORT_SYMBOL_GPL(dm_table_set_type);
/* validate the dax capability of the target device span */
-int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
int blocksize = *(int *) data, id;
bool rc;
id = dax_read_lock();
- rc = dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
+ rc = !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
dax_read_unlock(id);
return rc;
}
/* Check devices support synchronous DAX */
-static int device_dax_synchronous(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
+static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
{
- return dev->dax_dev && dax_synchronous(dev->dax_dev);
+ return !dev->dax_dev || !dax_synchronous(dev->dax_dev);
}
bool dm_table_supports_dax(struct dm_table *t,
@@ -854,7 +858,7 @@ bool dm_table_supports_dax(struct dm_table *t,
return false;
if (!ti->type->iterate_devices ||
- !ti->type->iterate_devices(ti, iterate_fn, blocksize))
+ ti->type->iterate_devices(ti, iterate_fn, blocksize))
return false;
}
@@ -925,7 +929,7 @@ static int dm_table_determine_type(struct dm_table *t)
verify_bio_based:
/* We must use this table as bio-based */
t->type = DM_TYPE_BIO_BASED;
- if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
+ if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) ||
(list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
t->type = DM_TYPE_DAX_BIO_BASED;
}
@@ -1203,6 +1207,210 @@ static int dm_table_register_integrity(struct dm_table *t)
return 0;
}
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+struct dm_keyslot_manager {
+ struct blk_keyslot_manager ksm;
+ struct mapped_device *md;
+};
+
+struct dm_keyslot_evict_args {
+ const struct blk_crypto_key *key;
+ int err;
+};
+
+static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct dm_keyslot_evict_args *args = data;
+ int err;
+
+ err = blk_crypto_evict_key(bdev_get_queue(dev->bdev), args->key);
+ if (!args->err)
+ args->err = err;
+ /* Always try to evict the key from all devices. */
+ return 0;
+}
+
+/*
+ * When an inline encryption key is evicted from a device-mapper device, evict
+ * it from all the underlying devices.
+ */
+static int dm_keyslot_evict(struct blk_keyslot_manager *ksm,
+ const struct blk_crypto_key *key, unsigned int slot)
+{
+ struct dm_keyslot_manager *dksm = container_of(ksm,
+ struct dm_keyslot_manager,
+ ksm);
+ struct mapped_device *md = dksm->md;
+ struct dm_keyslot_evict_args args = { key };
+ struct dm_table *t;
+ int srcu_idx;
+ int i;
+ struct dm_target *ti;
+
+ t = dm_get_live_table(md, &srcu_idx);
+ if (!t)
+ return 0;
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+ if (!ti->type->iterate_devices)
+ continue;
+ ti->type->iterate_devices(ti, dm_keyslot_evict_callback, &args);
+ }
+ dm_put_live_table(md, srcu_idx);
+ return args.err;
+}
+
+static struct blk_ksm_ll_ops dm_ksm_ll_ops = {
+ .keyslot_evict = dm_keyslot_evict,
+};
+
+static int device_intersect_crypto_modes(struct dm_target *ti,
+ struct dm_dev *dev, sector_t start,
+ sector_t len, void *data)
+{
+ struct blk_keyslot_manager *parent = data;
+ struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm;
+
+ blk_ksm_intersect_modes(parent, child);
+ return 0;
+}
+
+void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+{
+ struct dm_keyslot_manager *dksm = container_of(ksm,
+ struct dm_keyslot_manager,
+ ksm);
+
+ if (!ksm)
+ return;
+
+ blk_ksm_destroy(ksm);
+ kfree(dksm);
+}
+
+static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+{
+ dm_destroy_keyslot_manager(t->ksm);
+ t->ksm = NULL;
+}
+
+/*
+ * Constructs and initializes t->ksm with a keyslot manager that
+ * represents the common set of crypto capabilities of the devices
+ * described by the dm_table. However, if the constructed keyslot
+ * manager does not support a superset of the crypto capabilities
+ * supported by the current keyslot manager of the mapped_device,
+ * it returns an error instead, since we don't support restricting
+ * crypto capabilities on table changes. Finally, if the constructed
+ * keyslot manager doesn't actually support any crypto modes at all,
+ * it just returns NULL.
+ */
+static int dm_table_construct_keyslot_manager(struct dm_table *t)
+{
+ struct dm_keyslot_manager *dksm;
+ struct blk_keyslot_manager *ksm;
+ struct dm_target *ti;
+ unsigned int i;
+ bool ksm_is_empty = true;
+
+ dksm = kmalloc(sizeof(*dksm), GFP_KERNEL);
+ if (!dksm)
+ return -ENOMEM;
+ dksm->md = t->md;
+
+ ksm = &dksm->ksm;
+ blk_ksm_init_passthrough(ksm);
+ ksm->ksm_ll_ops = dm_ksm_ll_ops;
+ ksm->max_dun_bytes_supported = UINT_MAX;
+ memset(ksm->crypto_modes_supported, 0xFF,
+ sizeof(ksm->crypto_modes_supported));
+
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+
+ if (!dm_target_passes_crypto(ti->type)) {
+ blk_ksm_intersect_modes(ksm, NULL);
+ break;
+ }
+ if (!ti->type->iterate_devices)
+ continue;
+ ti->type->iterate_devices(ti, device_intersect_crypto_modes,
+ ksm);
+ }
+
+ if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) {
+ DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!");
+ dm_destroy_keyslot_manager(ksm);
+ return -EINVAL;
+ }
+
+ /*
+ * If the new KSM doesn't actually support any crypto modes, we may as
+ * well represent it with a NULL ksm.
+ */
+ ksm_is_empty = true;
+ for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) {
+ if (ksm->crypto_modes_supported[i]) {
+ ksm_is_empty = false;
+ break;
+ }
+ }
+
+ if (ksm_is_empty) {
+ dm_destroy_keyslot_manager(ksm);
+ ksm = NULL;
+ }
+
+ /*
+ * t->ksm is only set temporarily while the table is being set
+ * up, and it gets set to NULL after the capabilities have
+ * been transferred to the request_queue.
+ */
+ t->ksm = ksm;
+
+ return 0;
+}
+
+static void dm_update_keyslot_manager(struct request_queue *q,
+ struct dm_table *t)
+{
+ if (!t->ksm)
+ return;
+
+ /* Make the ksm less restrictive */
+ if (!q->ksm) {
+ blk_ksm_register(t->ksm, q);
+ } else {
+ blk_ksm_update_capabilities(q->ksm, t->ksm);
+ dm_destroy_keyslot_manager(t->ksm);
+ }
+ t->ksm = NULL;
+}
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static int dm_table_construct_keyslot_manager(struct dm_table *t)
+{
+ return 0;
+}
+
+void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+{
+}
+
+static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+{
+}
+
+static void dm_update_keyslot_manager(struct request_queue *q,
+ struct dm_table *t)
+{
+}
+
+#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */
+
/*
* Prepares the table for use by building the indices,
* setting the type, and allocating mempools.
@@ -1229,6 +1437,12 @@ int dm_table_complete(struct dm_table *t)
return r;
}
+ r = dm_table_construct_keyslot_manager(t);
+ if (r) {
+ DMERR("could not construct keyslot manager.");
+ return r;
+ }
+
r = dm_table_alloc_md_mempools(t, t->md);
if (r)
DMERR("unable to allocate mempools");
@@ -1295,6 +1509,46 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
return &t->targets[(KEYS_PER_NODE * n) + k];
}
+/*
+ * type->iterate_devices() should be called when the sanity check needs to
+ * iterate and check all underlying data devices. iterate_devices() will
+ * iterate all underlying data devices until it encounters a non-zero return
+ * code, returned by whether the input iterate_devices_callout_fn, or
+ * iterate_devices() itself internally.
+ *
+ * For some target type (e.g. dm-stripe), one call of iterate_devices() may
+ * iterate multiple underlying devices internally, in which case a non-zero
+ * return code returned by iterate_devices_callout_fn will stop the iteration
+ * in advance.
+ *
+ * Cases requiring _any_ underlying device supporting some kind of attribute,
+ * should use the iteration structure like dm_table_any_dev_attr(), or call
+ * it directly. @func should handle semantics of positive examples, e.g.
+ * capable of something.
+ *
+ * Cases requiring _all_ underlying devices supporting some kind of attribute,
+ * should use the iteration structure like dm_table_supports_nowait() or
+ * dm_table_supports_discards(). Or introduce dm_table_all_devs_attr() that
+ * uses an @anti_func that handle semantics of counter examples, e.g. not
+ * capable of something. So: return !dm_table_any_dev_attr(t, anti_func, data);
+ */
+static bool dm_table_any_dev_attr(struct dm_table *t,
+ iterate_devices_callout_fn func, void *data)
+{
+ struct dm_target *ti;
+ unsigned int 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, func, data))
+ return true;
+ }
+
+ return false;
+}
+
static int count_device(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
@@ -1331,13 +1585,13 @@ 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)
+static int device_not_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;
+ return blk_queue_zoned_model(q) != *zoned_model;
}
static bool dm_table_supports_zoned_model(struct dm_table *t,
@@ -1354,37 +1608,20 @@ static bool dm_table_supports_zoned_model(struct dm_table *t,
return false;
if (!ti->type->iterate_devices ||
- !ti->type->iterate_devices(ti, device_is_zoned_model, &zoned_model))
+ ti->type->iterate_devices(ti, device_not_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)
+static int device_not_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;
+ return blk_queue_zone_sectors(q) != *zone_sectors;
}
static int validate_hardware_zoned_model(struct dm_table *table,
@@ -1404,7 +1641,7 @@ static int validate_hardware_zoned_model(struct dm_table *table,
if (!zone_sectors || !is_power_of_2(zone_sectors))
return -EINVAL;
- if (!dm_table_matches_zone_sectors(table, zone_sectors)) {
+ if (dm_table_any_dev_attr(table, device_not_matches_zone_sectors, &zone_sectors)) {
DMERR("%s: zone sectors is not consistent across all devices",
dm_device_name(table->md));
return -EINVAL;
@@ -1533,7 +1770,7 @@ static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
unsigned long flush = (unsigned long) data;
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && (q->queue_flags & flush);
+ return (q->queue_flags & flush);
}
static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush)
@@ -1578,29 +1815,12 @@ static int device_dax_write_cache_enabled(struct dm_target *ti,
return false;
}
-static int dm_table_supports_dax_write_cache(struct dm_table *t)
-{
- 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_dax_write_cache_enabled, NULL))
- return true;
- }
-
- return false;
-}
-
-static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
+static int device_is_rotational(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);
- return q && blk_queue_nonrot(q);
+ return !blk_queue_nonrot(q);
}
static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
@@ -1608,24 +1828,7 @@ static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && !blk_queue_add_random(q);
-}
-
-static bool dm_table_all_devices_attribute(struct dm_table *t,
- iterate_devices_callout_fn func)
-{
- 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, func, NULL))
- return false;
- }
-
- return true;
+ return !blk_queue_add_random(q);
}
static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
@@ -1633,7 +1836,7 @@ static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *de
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && !q->limits.max_write_same_sectors;
+ return !q->limits.max_write_same_sectors;
}
static bool dm_table_supports_write_same(struct dm_table *t)
@@ -1660,7 +1863,7 @@ static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && !q->limits.max_write_zeroes_sectors;
+ return !q->limits.max_write_zeroes_sectors;
}
static bool dm_table_supports_write_zeroes(struct dm_table *t)
@@ -1687,7 +1890,7 @@ static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && !blk_queue_nowait(q);
+ return !blk_queue_nowait(q);
}
static bool dm_table_supports_nowait(struct dm_table *t)
@@ -1714,7 +1917,7 @@ static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && !blk_queue_discard(q);
+ return !blk_queue_discard(q);
}
static bool dm_table_supports_discards(struct dm_table *t)
@@ -1748,7 +1951,7 @@ static int device_not_secure_erase_capable(struct dm_target *ti,
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && !blk_queue_secure_erase(q);
+ return !blk_queue_secure_erase(q);
}
static bool dm_table_supports_secure_erase(struct dm_table *t)
@@ -1776,28 +1979,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && blk_queue_stable_writes(q);
-}
-
-/*
- * If any underlying device requires stable pages, a table must require
- * them as well. Only targets that support iterate_devices are considered:
- * don't want error, zero, etc to require stable pages.
- */
-static bool dm_table_requires_stable_pages(struct dm_table *t)
-{
- 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_requires_stable_pages, NULL))
- return true;
- }
-
- return false;
+ return blk_queue_stable_writes(q);
}
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
@@ -1837,22 +2019,22 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
}
blk_queue_write_cache(q, wc, fua);
- if (dm_table_supports_dax(t, device_supports_dax, &page_size)) {
+ if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) {
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
- if (dm_table_supports_dax(t, device_dax_synchronous, NULL))
+ if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL))
set_dax_synchronous(t->md->dax_dev);
}
else
blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
- if (dm_table_supports_dax_write_cache(t))
+ if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL))
dax_write_cache(t->md->dax_dev, true);
/* Ensure that all underlying devices are non-rotational. */
- if (dm_table_all_devices_attribute(t, device_is_nonrot))
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- else
+ if (dm_table_any_dev_attr(t, device_is_rotational, NULL))
blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
+ else
+ blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
if (!dm_table_supports_write_same(t))
q->limits.max_write_same_sectors = 0;
@@ -1864,8 +2046,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
/*
* Some devices don't use blk_integrity but still want stable pages
* because they do their own checksumming.
+ * If any underlying device requires stable pages, a table must require
+ * them as well. Only targets that support iterate_devices are considered:
+ * don't want error, zero, etc to require stable pages.
*/
- if (dm_table_requires_stable_pages(t))
+ if (dm_table_any_dev_attr(t, device_requires_stable_pages, NULL))
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
else
blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
@@ -1876,7 +2061,8 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
* Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
* have it set.
*/
- if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random))
+ if (blk_queue_add_random(q) &&
+ dm_table_any_dev_attr(t, device_is_not_random, NULL))
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
/*
@@ -1891,6 +2077,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
}
#endif
+ dm_update_keyslot_manager(q, t);
blk_queue_update_readahead(q);
}
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index d5223a0e5cc5..844c4be11768 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -148,6 +148,7 @@ struct dm_writecache {
size_t metadata_sectors;
size_t n_blocks;
uint64_t seq_count;
+ sector_t data_device_sectors;
void *block_start;
struct wc_entry *entries;
unsigned block_size;
@@ -159,14 +160,22 @@ struct dm_writecache {
bool overwrote_committed:1;
bool memory_vmapped:1;
+ bool start_sector_set:1;
bool high_wm_percent_set:1;
bool low_wm_percent_set:1;
bool max_writeback_jobs_set:1;
bool autocommit_blocks_set:1;
bool autocommit_time_set:1;
+ bool max_age_set:1;
bool writeback_fua_set:1;
bool flush_on_suspend:1;
bool cleaner:1;
+ bool cleaner_set:1;
+
+ unsigned high_wm_percent_value;
+ unsigned low_wm_percent_value;
+ unsigned autocommit_time_value;
+ unsigned max_age_value;
unsigned writeback_all;
struct workqueue_struct *writeback_wq;
@@ -523,7 +532,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc)
region.bdev = wc->ssd_dev->bdev;
region.sector = 0;
- region.count = PAGE_SIZE;
+ region.count = PAGE_SIZE >> SECTOR_SHIFT;
if (unlikely(region.sector + region.count > wc->metadata_sectors))
region.count = wc->metadata_sectors - region.sector;
@@ -969,6 +978,8 @@ static void writecache_resume(struct dm_target *ti)
wc_lock(wc);
+ wc->data_device_sectors = bdev_nr_sectors(wc->dev->bdev);
+
if (WC_MODE_PMEM(wc)) {
persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size);
} else {
@@ -1638,6 +1649,10 @@ static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e, gfp_t
void *address = memory_data(wc, e);
persistent_memory_flush_cache(address, block_size);
+
+ if (unlikely(bio_end_sector(&wb->bio) >= wc->data_device_sectors))
+ return true;
+
return bio_add_page(&wb->bio, persistent_memory_page(address),
block_size, persistent_memory_page_offset(address)) != 0;
}
@@ -1709,6 +1724,9 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba
if (writecache_has_error(wc)) {
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
+ } else if (unlikely(!bio_sectors(bio))) {
+ bio->bi_status = BLK_STS_OK;
+ bio_endio(bio);
} else {
submit_bio(bio);
}
@@ -1752,6 +1770,14 @@ static void __writecache_writeback_ssd(struct dm_writecache *wc, struct writebac
e = f;
}
+ if (unlikely(to.sector + to.count > wc->data_device_sectors)) {
+ if (to.sector >= wc->data_device_sectors) {
+ writecache_copy_endio(0, 0, c);
+ continue;
+ }
+ from.count = to.count = wc->data_device_sectors - to.sector;
+ }
+
dm_kcopyd_copy(wc->dm_kcopyd, &from, 1, &to, 0, writecache_copy_endio, c);
__writeback_throttle(wc, wbl);
@@ -2004,8 +2030,7 @@ static void writecache_dtr(struct dm_target *ti)
if (wc->ssd_dev)
dm_put_device(ti, wc->ssd_dev);
- if (wc->entries)
- vfree(wc->entries);
+ vfree(wc->entries);
if (wc->memory_map) {
if (WC_MODE_PMEM(wc))
@@ -2020,8 +2045,7 @@ static void writecache_dtr(struct dm_target *ti)
if (wc->dm_io)
dm_io_client_destroy(wc->dm_io);
- if (wc->dirty_bitmap)
- vfree(wc->dirty_bitmap);
+ vfree(wc->dirty_bitmap);
kfree(wc);
}
@@ -2205,6 +2229,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1)
goto invalid_optional;
wc->start_sector = start_sector;
+ wc->start_sector_set = true;
if (wc->start_sector != start_sector ||
wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT)
goto invalid_optional;
@@ -2214,6 +2239,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
goto invalid_optional;
if (high_wm_percent < 0 || high_wm_percent > 100)
goto invalid_optional;
+ wc->high_wm_percent_value = high_wm_percent;
wc->high_wm_percent_set = true;
} else if (!strcasecmp(string, "low_watermark") && opt_params >= 1) {
string = dm_shift_arg(&as), opt_params--;
@@ -2221,6 +2247,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
goto invalid_optional;
if (low_wm_percent < 0 || low_wm_percent > 100)
goto invalid_optional;
+ wc->low_wm_percent_value = low_wm_percent;
wc->low_wm_percent_set = true;
} else if (!strcasecmp(string, "writeback_jobs") && opt_params >= 1) {
string = dm_shift_arg(&as), opt_params--;
@@ -2240,6 +2267,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
if (autocommit_msecs > 3600000)
goto invalid_optional;
wc->autocommit_jiffies = msecs_to_jiffies(autocommit_msecs);
+ wc->autocommit_time_value = autocommit_msecs;
wc->autocommit_time_set = true;
} else if (!strcasecmp(string, "max_age") && opt_params >= 1) {
unsigned max_age_msecs;
@@ -2249,7 +2277,10 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
if (max_age_msecs > 86400000)
goto invalid_optional;
wc->max_age = msecs_to_jiffies(max_age_msecs);
+ wc->max_age_set = true;
+ wc->max_age_value = max_age_msecs;
} else if (!strcasecmp(string, "cleaner")) {
+ wc->cleaner_set = true;
wc->cleaner = true;
} else if (!strcasecmp(string, "fua")) {
if (WC_MODE_PMEM(wc)) {
@@ -2455,7 +2486,6 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
struct dm_writecache *wc = ti->private;
unsigned extra_args;
unsigned sz = 0;
- uint64_t x;
switch (type) {
case STATUSTYPE_INFO:
@@ -2467,11 +2497,11 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
DMEMIT("%c %s %s %u ", WC_MODE_PMEM(wc) ? 'p' : 's',
wc->dev->name, wc->ssd_dev->name, wc->block_size);
extra_args = 0;
- if (wc->start_sector)
+ if (wc->start_sector_set)
extra_args += 2;
- if (wc->high_wm_percent_set && !wc->cleaner)
+ if (wc->high_wm_percent_set)
extra_args += 2;
- if (wc->low_wm_percent_set && !wc->cleaner)
+ if (wc->low_wm_percent_set)
extra_args += 2;
if (wc->max_writeback_jobs_set)
extra_args += 2;
@@ -2479,37 +2509,29 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
extra_args += 2;
if (wc->autocommit_time_set)
extra_args += 2;
- if (wc->max_age != MAX_AGE_UNSPECIFIED)
+ if (wc->max_age_set)
extra_args += 2;
- if (wc->cleaner)
+ if (wc->cleaner_set)
extra_args++;
if (wc->writeback_fua_set)
extra_args++;
DMEMIT("%u", extra_args);
- if (wc->start_sector)
+ if (wc->start_sector_set)
DMEMIT(" start_sector %llu", (unsigned long long)wc->start_sector);
- if (wc->high_wm_percent_set && !wc->cleaner) {
- x = (uint64_t)wc->freelist_high_watermark * 100;
- x += wc->n_blocks / 2;
- do_div(x, (size_t)wc->n_blocks);
- DMEMIT(" high_watermark %u", 100 - (unsigned)x);
- }
- if (wc->low_wm_percent_set && !wc->cleaner) {
- x = (uint64_t)wc->freelist_low_watermark * 100;
- x += wc->n_blocks / 2;
- do_div(x, (size_t)wc->n_blocks);
- DMEMIT(" low_watermark %u", 100 - (unsigned)x);
- }
+ if (wc->high_wm_percent_set)
+ DMEMIT(" high_watermark %u", wc->high_wm_percent_value);
+ if (wc->low_wm_percent_set)
+ DMEMIT(" low_watermark %u", wc->low_wm_percent_value);
if (wc->max_writeback_jobs_set)
DMEMIT(" writeback_jobs %u", wc->max_writeback_jobs);
if (wc->autocommit_blocks_set)
DMEMIT(" autocommit_blocks %u", wc->autocommit_blocks);
if (wc->autocommit_time_set)
- DMEMIT(" autocommit_time %u", jiffies_to_msecs(wc->autocommit_jiffies));
- if (wc->max_age != MAX_AGE_UNSPECIFIED)
- DMEMIT(" max_age %u", jiffies_to_msecs(wc->max_age));
- if (wc->cleaner)
+ DMEMIT(" autocommit_time %u", wc->autocommit_time_value);
+ if (wc->max_age_set)
+ DMEMIT(" max_age %u", wc->max_age_value);
+ if (wc->cleaner_set)
DMEMIT(" cleaner");
if (wc->writeback_fua_set)
DMEMIT(" %sfua", wc->writeback_fua ? "" : "no");
@@ -2519,7 +2541,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
static struct target_type writecache_target = {
.name = "writecache",
- .version = {1, 3, 0},
+ .version = {1, 4, 0},
.module = THIS_MODULE,
.ctr = writecache_ctr,
.dtr = writecache_dtr,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 479ec5bea09e..50b693d776d6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -28,6 +28,7 @@
#include <linux/refcount.h>
#include <linux/part_stat.h>
#include <linux/blk-crypto.h>
+#include <linux/keyslot-manager.h>
#define DM_MSG_PREFIX "core"
@@ -105,12 +106,16 @@ struct dm_io {
struct dm_target_io tio;
};
+#define DM_TARGET_IO_BIO_OFFSET (offsetof(struct dm_target_io, clone))
+#define DM_IO_BIO_OFFSET \
+ (offsetof(struct dm_target_io, clone) + offsetof(struct dm_io, tio))
+
void *dm_per_bio_data(struct bio *bio, size_t data_size)
{
struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
if (!tio->inside_dm_io)
- return (char *)bio - offsetof(struct dm_target_io, clone) - data_size;
- return (char *)bio - offsetof(struct dm_target_io, clone) - offsetof(struct dm_io, tio) - data_size;
+ return (char *)bio - DM_TARGET_IO_BIO_OFFSET - data_size;
+ return (char *)bio - DM_IO_BIO_OFFSET - data_size;
}
EXPORT_SYMBOL_GPL(dm_per_bio_data);
@@ -118,9 +123,9 @@ struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size)
{
struct dm_io *io = (struct dm_io *)((char *)data + data_size);
if (io->magic == DM_IO_MAGIC)
- return (struct bio *)((char *)io + offsetof(struct dm_io, tio) + offsetof(struct dm_target_io, clone));
+ return (struct bio *)((char *)io + DM_IO_BIO_OFFSET);
BUG_ON(io->magic != DM_TIO_MAGIC);
- return (struct bio *)((char *)io + offsetof(struct dm_target_io, clone));
+ return (struct bio *)((char *)io + DM_TARGET_IO_BIO_OFFSET);
}
EXPORT_SYMBOL_GPL(dm_bio_from_per_bio_data);
@@ -148,6 +153,16 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);
#define DM_NUMA_NODE NUMA_NO_NODE
static int dm_numa_node = DM_NUMA_NODE;
+#define DEFAULT_SWAP_BIOS (8 * 1048576 / PAGE_SIZE)
+static int swap_bios = DEFAULT_SWAP_BIOS;
+static int get_swap_bios(void)
+{
+ int latch = READ_ONCE(swap_bios);
+ if (unlikely(latch <= 0))
+ latch = DEFAULT_SWAP_BIOS;
+ return latch;
+}
+
/*
* For mempools pre-allocation at the table loading time.
*/
@@ -969,6 +984,11 @@ void disable_write_zeroes(struct mapped_device *md)
limits->max_write_zeroes_sectors = 0;
}
+static bool swap_bios_limit(struct dm_target *ti, struct bio *bio)
+{
+ return unlikely((bio->bi_opf & REQ_SWAP) != 0) && unlikely(ti->limit_swap_bios);
+}
+
static void clone_endio(struct bio *bio)
{
blk_status_t error = bio->bi_status;
@@ -1020,6 +1040,11 @@ static void clone_endio(struct bio *bio)
}
}
+ if (unlikely(swap_bios_limit(tio->ti, bio))) {
+ struct mapped_device *md = io->md;
+ up(&md->swap_bios_semaphore);
+ }
+
free_tio(tio);
dec_pending(io, error);
}
@@ -1129,7 +1154,7 @@ static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bd
if (!map)
goto out;
- ret = dm_table_supports_dax(map, device_supports_dax, &blocksize);
+ ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize);
out:
dm_put_live_table(md, srcu_idx);
@@ -1253,6 +1278,22 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
}
EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
+static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch)
+{
+ mutex_lock(&md->swap_bios_lock);
+ while (latch < md->swap_bios) {
+ cond_resched();
+ down(&md->swap_bios_semaphore);
+ md->swap_bios--;
+ }
+ while (latch > md->swap_bios) {
+ cond_resched();
+ up(&md->swap_bios_semaphore);
+ md->swap_bios++;
+ }
+ mutex_unlock(&md->swap_bios_lock);
+}
+
static blk_qc_t __map_bio(struct dm_target_io *tio)
{
int r;
@@ -1272,6 +1313,14 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
atomic_inc(&io->io_count);
sector = clone->bi_iter.bi_sector;
+ if (unlikely(swap_bios_limit(ti, clone))) {
+ struct mapped_device *md = io->md;
+ int latch = get_swap_bios();
+ if (unlikely(latch != md->swap_bios))
+ __set_swap_bios_limit(md, latch);
+ down(&md->swap_bios_semaphore);
+ }
+
r = ti->type->map(ti, clone);
switch (r) {
case DM_MAPIO_SUBMITTED:
@@ -1282,10 +1331,18 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
ret = submit_bio_noacct(clone);
break;
case DM_MAPIO_KILL:
+ if (unlikely(swap_bios_limit(ti, clone))) {
+ struct mapped_device *md = io->md;
+ up(&md->swap_bios_semaphore);
+ }
free_tio(tio);
dec_pending(io, BLK_STS_IOERR);
break;
case DM_MAPIO_REQUEUE:
+ if (unlikely(swap_bios_limit(ti, clone))) {
+ struct mapped_device *md = io->md;
+ up(&md->swap_bios_semaphore);
+ }
free_tio(tio);
dec_pending(io, BLK_STS_DM_REQUEUE);
break;
@@ -1718,6 +1775,19 @@ static const struct dax_operations dm_dax_ops;
static void dm_wq_work(struct work_struct *work);
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+static void dm_queue_destroy_keyslot_manager(struct request_queue *q)
+{
+ dm_destroy_keyslot_manager(q->ksm);
+}
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline void dm_queue_destroy_keyslot_manager(struct request_queue *q)
+{
+}
+#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */
+
static void cleanup_mapped_device(struct mapped_device *md)
{
if (md->wq)
@@ -1739,14 +1809,17 @@ static void cleanup_mapped_device(struct mapped_device *md)
put_disk(md->disk);
}
- if (md->queue)
+ if (md->queue) {
+ dm_queue_destroy_keyslot_manager(md->queue);
blk_cleanup_queue(md->queue);
+ }
cleanup_srcu_struct(&md->io_barrier);
mutex_destroy(&md->suspend_lock);
mutex_destroy(&md->type_lock);
mutex_destroy(&md->table_devices_lock);
+ mutex_destroy(&md->swap_bios_lock);
dm_mq_cleanup_mapped_device(md);
}
@@ -1814,6 +1887,10 @@ static struct mapped_device *alloc_dev(int minor)
init_waitqueue_head(&md->eventq);
init_completion(&md->kobj_holder.completion);
+ md->swap_bios = get_swap_bios();
+ sema_init(&md->swap_bios_semaphore, md->swap_bios);
+ mutex_init(&md->swap_bios_lock);
+
md->disk->major = _major;
md->disk->first_minor = minor;
md->disk->fops = &dm_blk_dops;
@@ -2849,8 +2926,8 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
case DM_TYPE_BIO_BASED:
case DM_TYPE_DAX_BIO_BASED:
pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
- front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
- io_front_pad = roundup(front_pad, __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
+ front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + DM_TARGET_IO_BIO_OFFSET;
+ io_front_pad = roundup(per_io_data_size, __alignof__(struct dm_io)) + DM_IO_BIO_OFFSET;
ret = bioset_init(&pools->io_bs, pool_size, io_front_pad, 0);
if (ret)
goto out;
@@ -3097,6 +3174,9 @@ MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
module_param(dm_numa_node, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations");
+module_param(swap_bios, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(swap_bios, "Maximum allowed inflight swap IOs");
+
MODULE_DESCRIPTION(DM_NAME " driver");
MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index fffe1e289c53..b441ad772c18 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -73,7 +73,7 @@ void dm_table_free_md_mempools(struct dm_table *t);
struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn,
int *blocksize);
-int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data);
void dm_lock_md_type(struct mapped_device *md);
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index 564896659dd4..fe073d92f01e 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -100,7 +100,7 @@ struct dm_block *shadow_parent(struct shadow_spine *s);
int shadow_has_parent(struct shadow_spine *s);
-int shadow_root(struct shadow_spine *s);
+dm_block_t shadow_root(struct shadow_spine *s);
/*
* Some inlines.
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index e03cb9e48773..8a2bfbfb218b 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -235,7 +235,7 @@ int shadow_has_parent(struct shadow_spine *s)
return s->count >= 2;
}
-int shadow_root(struct shadow_spine *s)
+dm_block_t shadow_root(struct shadow_spine *s)
{
return s->root;
}