diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-11 23:10:57 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-11 23:10:57 +0300 |
commit | 89fd915c402113528750353ad6de9ea68a787e5c (patch) | |
tree | 03ba8e8e6400e43ef518393259941eae39ee32d8 /drivers/nvdimm/btt.c | |
parent | 66c9457df3926efff65529dab1a8c742df756790 (diff) | |
parent | 04c3c982fcc0151ed3574d7ae4f1e62278054d72 (diff) | |
download | linux-89fd915c402113528750353ad6de9ea68a787e5c.tar.xz |
Merge tag 'libnvdimm-for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm from Dan Williams:
"A rework of media error handling in the BTT driver and other updates.
It has appeared in a few -next releases and collected some late-
breaking build-error and warning fixups as a result.
Summary:
- Media error handling support in the Block Translation Table (BTT)
driver is reworked to address sleeping-while-atomic locking and
memory-allocation-context conflicts.
- The dax_device lookup overhead for xfs and ext4 is moved out of the
iomap hot-path to a mount-time lookup.
- A new 'ecc_unit_size' sysfs attribute is added to advertise the
read-modify-write boundary property of a persistent memory range.
- Preparatory fix-ups for arm and powerpc pmem support are included
along with other miscellaneous fixes"
* tag 'libnvdimm-for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (26 commits)
libnvdimm, btt: fix format string warnings
libnvdimm, btt: clean up warning and error messages
ext4: fix null pointer dereference on sbi
libnvdimm, nfit: move the check on nd_reserved2 to the endpoint
dax: fix FS_DAX=n BLOCK=y compilation
libnvdimm: fix integer overflow static analysis warning
libnvdimm, nd_blk: remove mmio_flush_range()
libnvdimm, btt: rework error clearing
libnvdimm: fix potential deadlock while clearing errors
libnvdimm, btt: cache sector_size in arena_info
libnvdimm, btt: ensure that flags were also unchanged during a map_read
libnvdimm, btt: refactor map entry operations with macros
libnvdimm, btt: fix a missed NVDIMM_IO_ATOMIC case in the write path
libnvdimm, nfit: export an 'ecc_unit_size' sysfs attribute
ext4: perform dax_device lookup at mount
ext2: perform dax_device lookup at mount
xfs: perform dax_device lookup at mount
dax: introduce a fs_dax_get_by_bdev() helper
libnvdimm, btt: check memory allocation failure
libnvdimm, label: fix index block size calculation
...
Diffstat (limited to 'drivers/nvdimm/btt.c')
-rw-r--r-- | drivers/nvdimm/btt.c | 197 |
1 files changed, 157 insertions, 40 deletions
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 60491641a8d6..d5612bd1cc81 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -31,6 +31,16 @@ enum log_ent_request { LOG_OLD_ENT }; +static struct device *to_dev(struct arena_info *arena) +{ + return &arena->nd_btt->dev; +} + +static u64 adjust_initial_offset(struct nd_btt *nd_btt, u64 offset) +{ + return offset + nd_btt->initial_offset; +} + static int arena_read_bytes(struct arena_info *arena, resource_size_t offset, void *buf, size_t n, unsigned long flags) { @@ -38,7 +48,7 @@ static int arena_read_bytes(struct arena_info *arena, resource_size_t offset, struct nd_namespace_common *ndns = nd_btt->ndns; /* arena offsets may be shifted from the base of the device */ - offset += arena->nd_btt->initial_offset; + offset = adjust_initial_offset(nd_btt, offset); return nvdimm_read_bytes(ndns, offset, buf, n, flags); } @@ -49,7 +59,7 @@ static int arena_write_bytes(struct arena_info *arena, resource_size_t offset, struct nd_namespace_common *ndns = nd_btt->ndns; /* arena offsets may be shifted from the base of the device */ - offset += arena->nd_btt->initial_offset; + offset = adjust_initial_offset(nd_btt, offset); return nvdimm_write_bytes(ndns, offset, buf, n, flags); } @@ -62,8 +72,10 @@ static int btt_info_write(struct arena_info *arena, struct btt_sb *super) * We rely on that to make sure rw_bytes does error clearing * correctly, so make sure that is the case. */ - WARN_ON_ONCE(!IS_ALIGNED(arena->infooff, 512)); - WARN_ON_ONCE(!IS_ALIGNED(arena->info2off, 512)); + dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->infooff, 512), + "arena->infooff: %#llx is unaligned\n", arena->infooff); + dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->info2off, 512), + "arena->info2off: %#llx is unaligned\n", arena->info2off); ret = arena_write_bytes(arena, arena->info2off, super, sizeof(struct btt_sb), 0); @@ -76,7 +88,6 @@ static int btt_info_write(struct arena_info *arena, struct btt_sb *super) static int btt_info_read(struct arena_info *arena, struct btt_sb *super) { - WARN_ON(!super); return arena_read_bytes(arena, arena->infooff, super, sizeof(struct btt_sb), 0); } @@ -92,7 +103,10 @@ static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping, { u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE); - WARN_ON(lba >= arena->external_nlba); + if (unlikely(lba >= arena->external_nlba)) + dev_err_ratelimited(to_dev(arena), + "%s: lba %#x out of range (max: %#x)\n", + __func__, lba, arena->external_nlba); return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE, flags); } @@ -106,7 +120,7 @@ static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping, * This 'mapping' is supposed to be just the LBA mapping, without * any flags set, so strip the flag bits. */ - mapping &= MAP_LBA_MASK; + mapping = ent_lba(mapping); ze = (z_flag << 1) + e_flag; switch (ze) { @@ -131,7 +145,8 @@ static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping, * construed as a valid 'normal' case, but we decide not to, * to avoid confusion */ - WARN_ONCE(1, "Invalid use of Z and E flags\n"); + dev_err_ratelimited(to_dev(arena), + "Invalid use of Z and E flags\n"); return -EIO; } @@ -147,7 +162,10 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping, u32 raw_mapping, postmap, ze, z_flag, e_flag; u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE); - WARN_ON(lba >= arena->external_nlba); + if (unlikely(lba >= arena->external_nlba)) + dev_err_ratelimited(to_dev(arena), + "%s: lba %#x out of range (max: %#x)\n", + __func__, lba, arena->external_nlba); ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE, rwb_flags); if (ret) @@ -155,10 +173,10 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping, raw_mapping = le32_to_cpu(in); - z_flag = (raw_mapping & MAP_TRIM_MASK) >> MAP_TRIM_SHIFT; - e_flag = (raw_mapping & MAP_ERR_MASK) >> MAP_ERR_SHIFT; + z_flag = ent_z_flag(raw_mapping); + e_flag = ent_e_flag(raw_mapping); ze = (z_flag << 1) + e_flag; - postmap = raw_mapping & MAP_LBA_MASK; + postmap = ent_lba(raw_mapping); /* Reuse the {z,e}_flag variables for *trim and *error */ z_flag = 0; @@ -195,7 +213,6 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping, static int btt_log_read_pair(struct arena_info *arena, u32 lane, struct log_entry *ent) { - WARN_ON(!ent); return arena_read_bytes(arena, arena->logoff + (2 * lane * LOG_ENT_SIZE), ent, 2 * LOG_ENT_SIZE, 0); @@ -299,11 +316,6 @@ static int btt_log_get_old(struct log_entry *ent) return old; } -static struct device *to_dev(struct arena_info *arena) -{ - return &arena->nd_btt->dev; -} - /* * This function copies the desired (old/new) log entry into ent if * it is not NULL. It returns the sub-slot number (0 or 1) @@ -381,7 +393,9 @@ static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub, arena->freelist[lane].sub = 1 - arena->freelist[lane].sub; if (++(arena->freelist[lane].seq) == 4) arena->freelist[lane].seq = 1; - arena->freelist[lane].block = le32_to_cpu(ent->old_map); + if (ent_e_flag(ent->old_map)) + arena->freelist[lane].has_err = 1; + arena->freelist[lane].block = le32_to_cpu(ent_lba(ent->old_map)); return ret; } @@ -407,12 +421,14 @@ static int btt_map_init(struct arena_info *arena) * make sure rw_bytes does error clearing correctly, so make sure that * is the case. */ - WARN_ON_ONCE(!IS_ALIGNED(arena->mapoff, 512)); + dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->mapoff, 512), + "arena->mapoff: %#llx is unaligned\n", arena->mapoff); while (mapsize) { size_t size = min(mapsize, chunk_size); - WARN_ON_ONCE(size < 512); + dev_WARN_ONCE(to_dev(arena), size < 512, + "chunk size: %#zx is unaligned\n", size); ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf, size, 0); if (ret) @@ -449,12 +465,14 @@ static int btt_log_init(struct arena_info *arena) * make sure rw_bytes does error clearing correctly, so make sure that * is the case. */ - WARN_ON_ONCE(!IS_ALIGNED(arena->logoff, 512)); + dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->logoff, 512), + "arena->logoff: %#llx is unaligned\n", arena->logoff); while (logsize) { size_t size = min(logsize, chunk_size); - WARN_ON_ONCE(size < 512); + dev_WARN_ONCE(to_dev(arena), size < 512, + "chunk size: %#zx is unaligned\n", size); ret = arena_write_bytes(arena, arena->logoff + offset, zerobuf, size, 0); if (ret) @@ -480,6 +498,40 @@ static int btt_log_init(struct arena_info *arena) return ret; } +static u64 to_namespace_offset(struct arena_info *arena, u64 lba) +{ + return arena->dataoff + ((u64)lba * arena->internal_lbasize); +} + +static int arena_clear_freelist_error(struct arena_info *arena, u32 lane) +{ + int ret = 0; + + if (arena->freelist[lane].has_err) { + void *zero_page = page_address(ZERO_PAGE(0)); + u32 lba = arena->freelist[lane].block; + u64 nsoff = to_namespace_offset(arena, lba); + unsigned long len = arena->sector_size; + + mutex_lock(&arena->err_lock); + + while (len) { + unsigned long chunk = min(len, PAGE_SIZE); + + ret = arena_write_bytes(arena, nsoff, zero_page, + chunk, 0); + if (ret) + break; + len -= chunk; + nsoff += chunk; + if (len == 0) + arena->freelist[lane].has_err = 0; + } + mutex_unlock(&arena->err_lock); + } + return ret; +} + static int btt_freelist_init(struct arena_info *arena) { int old, new, ret; @@ -505,6 +557,17 @@ static int btt_freelist_init(struct arena_info *arena) arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq)); arena->freelist[i].block = le32_to_cpu(log_new.old_map); + /* + * FIXME: if error clearing fails during init, we want to make + * the BTT read-only + */ + if (ent_e_flag(log_new.old_map)) { + ret = arena_clear_freelist_error(arena, i); + if (ret) + dev_err_ratelimited(to_dev(arena), + "Unable to clear known errors\n"); + } + /* This implies a newly created or untouched flog entry */ if (log_new.old_map == log_new.new_map) continue; @@ -525,7 +588,6 @@ static int btt_freelist_init(struct arena_info *arena) if (ret) return ret; } - } return 0; @@ -566,6 +628,7 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size, if (!arena) return NULL; arena->nd_btt = btt->nd_btt; + arena->sector_size = btt->sector_size; if (!size) return arena; @@ -694,6 +757,7 @@ static int discover_arenas(struct btt *btt) arena->external_lba_start = cur_nlba; parse_arena_meta(arena, super, cur_off); + mutex_init(&arena->err_lock); ret = btt_freelist_init(arena); if (ret) goto out; @@ -904,11 +968,6 @@ static void unlock_map(struct arena_info *arena, u32 premap) spin_unlock(&arena->map_locks[idx].lock); } -static u64 to_namespace_offset(struct arena_info *arena, u64 lba) -{ - return arena->dataoff + ((u64)lba * arena->internal_lbasize); -} - static int btt_data_read(struct arena_info *arena, struct page *page, unsigned int off, u32 lba, u32 len) { @@ -1032,6 +1091,7 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip, */ while (1) { u32 new_map; + int new_t, new_e; if (t_flag) { zero_fill_data(page, off, cur_len); @@ -1050,20 +1110,29 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip, */ barrier(); - ret = btt_map_read(arena, premap, &new_map, &t_flag, - &e_flag, NVDIMM_IO_ATOMIC); + ret = btt_map_read(arena, premap, &new_map, &new_t, + &new_e, NVDIMM_IO_ATOMIC); if (ret) goto out_rtt; - if (postmap == new_map) + if ((postmap == new_map) && (t_flag == new_t) && + (e_flag == new_e)) break; postmap = new_map; + t_flag = new_t; + e_flag = new_e; } ret = btt_data_read(arena, page, off, postmap, cur_len); - if (ret) + if (ret) { + int rc; + + /* Media error - set the e_flag */ + rc = btt_map_write(arena, premap, postmap, 0, 1, + NVDIMM_IO_ATOMIC); goto out_rtt; + } if (bip) { ret = btt_rw_integrity(btt, bip, arena, postmap, READ); @@ -1088,6 +1157,21 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip, return ret; } +/* + * Normally, arena_{read,write}_bytes will take care of the initial offset + * adjustment, but in the case of btt_is_badblock, where we query is_bad_pmem, + * we need the final, raw namespace offset here + */ +static bool btt_is_badblock(struct btt *btt, struct arena_info *arena, + u32 postmap) +{ + u64 nsoff = adjust_initial_offset(arena->nd_btt, + to_namespace_offset(arena, postmap)); + sector_t phys_sector = nsoff >> 9; + + return is_bad_pmem(btt->phys_bb, phys_sector, arena->internal_lbasize); +} + static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, sector_t sector, struct page *page, unsigned int off, unsigned int len) @@ -1100,7 +1184,9 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, while (len) { u32 cur_len; + int e_flag; + retry: lane = nd_region_acquire_lane(btt->nd_region); ret = lba_to_arena(btt, sector, &premap, &arena); @@ -1113,6 +1199,21 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, goto out_lane; } + if (btt_is_badblock(btt, arena, arena->freelist[lane].block)) + arena->freelist[lane].has_err = 1; + + if (mutex_is_locked(&arena->err_lock) + || arena->freelist[lane].has_err) { + nd_region_release_lane(btt->nd_region, lane); + + ret = arena_clear_freelist_error(arena, lane); + if (ret) + return ret; + + /* OK to acquire a different lane/free block */ + goto retry; + } + new_postmap = arena->freelist[lane].block; /* Wait if the new block is being read from */ @@ -1138,7 +1239,7 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, } lock_map(arena, premap); - ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL, + ret = btt_map_read(arena, premap, &old_postmap, NULL, &e_flag, NVDIMM_IO_ATOMIC); if (ret) goto out_map; @@ -1146,6 +1247,8 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, ret = -EIO; goto out_map; } + if (e_flag) + set_e_flag(old_postmap); log.lba = cpu_to_le32(premap); log.old_map = cpu_to_le32(old_postmap); @@ -1156,13 +1259,20 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, if (ret) goto out_map; - ret = btt_map_write(arena, premap, new_postmap, 0, 0, 0); + ret = btt_map_write(arena, premap, new_postmap, 0, 0, + NVDIMM_IO_ATOMIC); if (ret) goto out_map; unlock_map(arena, premap); nd_region_release_lane(btt->nd_region, lane); + if (e_flag) { + ret = arena_clear_freelist_error(arena, lane); + if (ret) + return ret; + } + len -= cur_len; off += cur_len; sector += btt->sector_size >> SECTOR_SHIFT; @@ -1211,11 +1321,13 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) bio_for_each_segment(bvec, bio, iter) { unsigned int len = bvec.bv_len; - BUG_ON(len > PAGE_SIZE); - /* Make sure len is in multiples of sector size. */ - /* XXX is this right? */ - BUG_ON(len < btt->sector_size); - BUG_ON(len % btt->sector_size); + if (len > PAGE_SIZE || len < btt->sector_size || + len % btt->sector_size) { + dev_err_ratelimited(&btt->nd_btt->dev, + "unaligned bio segment (len: %d)\n", len); + bio->bi_status = BLK_STS_IOERR; + break; + } err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset, op_is_write(bio_op(bio)), iter.bi_sector); @@ -1345,6 +1457,7 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize, { int ret; struct btt *btt; + struct nd_namespace_io *nsio; struct device *dev = &nd_btt->dev; btt = devm_kzalloc(dev, sizeof(struct btt), GFP_KERNEL); @@ -1358,6 +1471,8 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize, INIT_LIST_HEAD(&btt->arena_list); mutex_init(&btt->init_lock); btt->nd_region = nd_region; + nsio = to_nd_namespace_io(&nd_btt->ndns->dev); + btt->phys_bb = &nsio->bb; ret = discover_arenas(btt); if (ret) { @@ -1431,6 +1546,8 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns) } btt_sb = devm_kzalloc(&nd_btt->dev, sizeof(*btt_sb), GFP_KERNEL); + if (!btt_sb) + return -ENOMEM; /* * If this returns < 0, that is ok as it just means there wasn't |