diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst index c00f9f11e3f3..8439d2ae689b 100644 --- a/Documentation/admin-guide/device-mapper/dm-integrity.rst +++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst @@ -182,12 +182,15 @@ fix_padding space-efficient. If this option is not present, large padding is used - that is for compatibility with older kernels. +allow_discards + Allow block discard requests (a.k.a. TRIM) for the integrity device. + Discards are only allowed to devices using internal hash. -The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can -be changed when reloading the target (load an inactive table and swap the -tables with suspend and resume). The other arguments should not be changed -when reloading the target because the layout of disk data depend on them -and the reloaded target would be non-functional. +The journal mode (D/J), buffer_sectors, journal_watermark, commit_time and +allow_discards can be changed when reloading the target (load an inactive +table and swap the tables with suspend and resume). The other arguments +should not be changed when reloading the target because the layout of disk +data depend on them and the reloaded target would be non-functional. The layout of the formatted block device: diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 58fd137b6ae1..3e500098132f 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -585,10 +585,12 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) /* Do we need to select a new pgpath? */ pgpath = READ_ONCE(m->current_pgpath); - queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags); - if (!pgpath || !queue_io) + if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) pgpath = choose_pgpath(m, bio->bi_iter.bi_size); + /* MPATHF_QUEUE_IO might have been cleared by choose_pgpath. */ + queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags); + if ((pgpath && queue_io) || (!pgpath && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))) { /* Queue for the daemon to resubmit */ diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 49147e634046..fb41b4f23c48 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -435,7 +435,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, fio->level++; if (type == DM_VERITY_BLOCK_TYPE_METADATA) - block += v->data_blocks; + block = block - v->hash_start + v->data_blocks; /* * For RS(M, N), the continuous FEC data is divided into blocks of N diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 114927da9cc9..613c171b1b6d 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -931,6 +931,24 @@ static int writecache_alloc_entries(struct dm_writecache *wc) return 0; } +static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors) +{ + struct dm_io_region region; + struct dm_io_request req; + + region.bdev = wc->ssd_dev->bdev; + region.sector = wc->start_sector; + region.count = n_sectors; + req.bi_op = REQ_OP_READ; + req.bi_op_flags = REQ_SYNC; + req.mem.type = DM_IO_VMA; + req.mem.ptr.vma = (char *)wc->memory_map; + req.client = wc->dm_io; + req.notify.fn = NULL; + + return dm_io(&req, 1, ®ion, NULL); +} + static void writecache_resume(struct dm_target *ti) { struct dm_writecache *wc = ti->private; @@ -941,8 +959,18 @@ static void writecache_resume(struct dm_target *ti) wc_lock(wc); - if (WC_MODE_PMEM(wc)) + if (WC_MODE_PMEM(wc)) { persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size); + } else { + r = writecache_read_metadata(wc, wc->metadata_sectors); + if (r) { + size_t sb_entries_offset; + writecache_error(wc, r, "unable to read metadata: %d", r); + sb_entries_offset = offsetof(struct wc_memory_superblock, entries); + memset((char *)wc->memory_map + sb_entries_offset, -1, + (wc->metadata_sectors << SECTOR_SHIFT) - sb_entries_offset); + } + } wc->tree = RB_ROOT; INIT_LIST_HEAD(&wc->lru); @@ -2102,6 +2130,12 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->error = "Invalid block size"; goto bad; } + if (wc->block_size < bdev_logical_block_size(wc->dev->bdev) || + wc->block_size < bdev_logical_block_size(wc->ssd_dev->bdev)) { + r = -EINVAL; + ti->error = "Block size is smaller than device logical block size"; + goto bad; + } wc->block_size_bits = __ffs(wc->block_size); wc->max_writeback_jobs = MAX_WRITEBACK_JOBS; @@ -2200,8 +2234,6 @@ invalid_optional: goto bad; } } else { - struct dm_io_region region; - struct dm_io_request req; size_t n_blocks, n_metadata_blocks; uint64_t n_bitmap_bits; @@ -2258,19 +2290,9 @@ invalid_optional: goto bad; } - region.bdev = wc->ssd_dev->bdev; - region.sector = wc->start_sector; - region.count = wc->metadata_sectors; - req.bi_op = REQ_OP_READ; - req.bi_op_flags = REQ_SYNC; - req.mem.type = DM_IO_VMA; - req.mem.ptr.vma = (char *)wc->memory_map; - req.client = wc->dm_io; - req.notify.fn = NULL; - - r = dm_io(&req, 1, ®ion, NULL); + r = writecache_read_metadata(wc, wc->block_size >> SECTOR_SHIFT); if (r) { - ti->error = "Unable to read metadata"; + ti->error = "Unable to read first block of metadata"; goto bad; } }