whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit cffd425b90147296c627dfb13f7ea8f361d962b2
parent c04e2a780caf7073c31c4289c4b7c3d62f9c0130
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Fri, 25 Jan 2019 09:07:18 +1300

Merge tag 'for-5.0/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix DM crypt's parsing of extended IV arguments.

 - Fix DM thinp's discard passdown to properly account for extra
   reference that is taken to guard against reallocating a block before
   a discard has been issued.

 - Fix bio-based DM's redundant IO accounting that was occurring for
   bios that must be split due to the nature of the DM target (e.g.
   dm-stripe, dm-thinp, etc).

* tag 'for-5.0/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: add missing trace_block_split() to __split_and_process_bio()
  dm: fix dm_wq_work() to only use __split_and_process_bio() if appropriate
  dm: fix redundant IO accounting for bios that need splitting
  dm: fix clone_bio() to trigger blk_recount_segments()
  dm thin: fix passdown_double_checking_shared_status()
  dm crypt: fix parsing of extended IV arguments

Diffstat:
Mdrivers/md/dm-crypt.c | 25+++++++++++++++++--------
Mdrivers/md/dm-thin-metadata.c | 4++--
Mdrivers/md/dm-thin-metadata.h | 2+-
Mdrivers/md/dm-thin.c | 10+++++-----
Mdrivers/md/dm.c | 43+++++++++++++++++++++++++++++++------------
5 files changed, 56 insertions(+), 28 deletions(-)

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c @@ -2414,9 +2414,21 @@ static int crypt_ctr_cipher_new(struct dm_target *ti, char *cipher_in, char *key * capi:cipher_api_spec-iv:ivopts */ tmp = &cipher_in[strlen("capi:")]; - cipher_api = strsep(&tmp, "-"); - *ivmode = strsep(&tmp, ":"); - *ivopts = tmp; + + /* Separate IV options if present, it can contain another '-' in hash name */ + *ivopts = strrchr(tmp, ':'); + if (*ivopts) { + **ivopts = '\0'; + (*ivopts)++; + } + /* Parse IV mode */ + *ivmode = strrchr(tmp, '-'); + if (*ivmode) { + **ivmode = '\0'; + (*ivmode)++; + } + /* The rest is crypto API spec */ + cipher_api = tmp; if (*ivmode && !strcmp(*ivmode, "lmk")) cc->tfms_count = 64; @@ -2486,11 +2498,8 @@ static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key goto bad_mem; chainmode = strsep(&tmp, "-"); - *ivopts = strsep(&tmp, "-"); - *ivmode = strsep(&*ivopts, ":"); - - if (tmp) - DMWARN("Ignoring unexpected additional cipher options"); + *ivmode = strsep(&tmp, ":"); + *ivopts = tmp; /* * For compatibility with the original dm-crypt mapping format, if diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c @@ -1678,7 +1678,7 @@ int dm_thin_remove_range(struct dm_thin_device *td, return r; } -int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result) +int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *result) { int r; uint32_t ref_count; @@ -1686,7 +1686,7 @@ int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *resu down_read(&pmd->root_lock); r = dm_sm_get_count(pmd->data_sm, b, &ref_count); if (!r) - *result = (ref_count != 0); + *result = (ref_count > 1); up_read(&pmd->root_lock); return r; diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h @@ -195,7 +195,7 @@ int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd, int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result); -int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result); +int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *result); int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e); int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c @@ -1048,7 +1048,7 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m * passdown we have to check that these blocks are now unused. */ int r = 0; - bool used = true; + bool shared = true; struct thin_c *tc = m->tc; struct pool *pool = tc->pool; dm_block_t b = m->data_block, e, end = m->data_block + m->virt_end - m->virt_begin; @@ -1058,11 +1058,11 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m while (b != end) { /* find start of unmapped run */ for (; b < end; b++) { - r = dm_pool_block_is_used(pool->pmd, b, &used); + r = dm_pool_block_is_shared(pool->pmd, b, &shared); if (r) goto out; - if (!used) + if (!shared) break; } @@ -1071,11 +1071,11 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m /* find end of run */ for (e = b + 1; e != end; e++) { - r = dm_pool_block_is_used(pool->pmd, e, &used); + r = dm_pool_block_is_shared(pool->pmd, e, &shared); if (r) goto out; - if (used) + if (shared) break; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c @@ -1320,7 +1320,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, __bio_clone_fast(clone, bio); - if (unlikely(bio_integrity(bio) != NULL)) { + if (bio_integrity(bio)) { int r; if (unlikely(!dm_target_has_integrity(tio->ti->type) && @@ -1336,11 +1336,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); - clone->bi_iter.bi_size = to_bytes(len); - - if (unlikely(bio_integrity(bio) != NULL)) - bio_integrity_trim(clone); + bio_trim(clone, sector - clone->bi_iter.bi_sector, len); return 0; } @@ -1588,6 +1584,9 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md, ci->sector = bio->bi_iter.bi_sector; } +#define __dm_part_stat_sub(part, field, subnd) \ + (part_stat_get(part, field) -= (subnd)) + /* * Entry point to split a bio into clones and submit them to the targets. */ @@ -1642,7 +1641,21 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count, GFP_NOIO, &md->queue->bio_split); ci.io->orig_bio = b; + + /* + * Adjust IO stats for each split, otherwise upon queue + * reentry there will be redundant IO accounting. + * NOTE: this is a stop-gap fix, a proper fix involves + * significant refactoring of DM core's bio splitting + * (by eliminating DM's splitting and just using bio_split) + */ + part_stat_lock(); + __dm_part_stat_sub(&dm_disk(md)->part0, + sectors[op_stat_group(bio_op(bio))], ci.sector_count); + part_stat_unlock(); + bio_chain(b, bio); + trace_block_split(md->queue, b, bio->bi_iter.bi_sector); ret = generic_make_request(bio); break; } @@ -1713,6 +1726,15 @@ out: return ret; } +static blk_qc_t dm_process_bio(struct mapped_device *md, + struct dm_table *map, struct bio *bio) +{ + if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED) + return __process_bio(md, map, bio); + else + return __split_and_process_bio(md, map, bio); +} + static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) { struct mapped_device *md = q->queuedata; @@ -1733,10 +1755,7 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) return ret; } - if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED) - ret = __process_bio(md, map, bio); - else - ret = __split_and_process_bio(md, map, bio); + ret = dm_process_bio(md, map, bio); dm_put_live_table(md, srcu_idx); return ret; @@ -2415,9 +2434,9 @@ static void dm_wq_work(struct work_struct *work) break; if (dm_request_based(md)) - generic_make_request(c); + (void) generic_make_request(c); else - __split_and_process_bio(md, map, c); + (void) dm_process_bio(md, map, c); } dm_put_live_table(md, srcu_idx);