diff options
author | Jens Axboe <axboe@kernel.dk> | 2019-11-12 19:11:30 -0700 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2019-11-12 19:11:30 -0700 |
commit | d29510d3524200f4591d1aac58b4b8fa375bd20a (patch) | |
tree | fdf5a527b8ab866a28ea1ff323e3e9081236df10 /drivers/md | |
parent | 6952a7f8446ee85ea9d10ab87b64797a031eaae3 (diff) | |
parent | da644b2cc1a4664ff7f75d3ae50e3fcf638580d9 (diff) | |
download | linux-d29510d3524200f4591d1aac58b4b8fa375bd20a.tar.bz2 |
Merge branch 'for-5.5/drivers' into for-5.5/zoned
* for-5.5/drivers: (38 commits)
null_blk: add zone open, close, and finish support
dm: add zone open, close and finish support
nvme: Fix parsing of ANA log page
nvmet: stop using bio_set_op_attrs
nvmet: add plugging for read/write when ns is bdev
nvmet: clean up command parsing a bit
nvme-pci: Spelling s/resdicovered/rediscovered/
nvmet: fill discovery controller sn, fr and mn correctly
nvmet: Open code nvmet_req_execute()
nvmet: Remove the data_len field from the nvmet_req struct
nvmet: Introduce nvmet_dsm_len() helper
nvmet: Cleanup discovery execute handlers
nvmet: Introduce common execute function for get_log_page and identify
nvmet-tcp: Don't set the request's data_len
nvmet-tcp: Don't check data_len in nvmet_tcp_map_data()
nvme: Introduce nvme_lba_to_sect()
nvme: Cleanup and rename nvme_block_nr()
nvme: resync include/linux/nvme.h with nvmecli
nvme: move common call to nvme_cleanup_cmd to core layer
nvme: introduce "Command Aborted By host" status code
...
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/dm-flakey.c | 7 | ||||
-rw-r--r-- | drivers/md/dm-linear.c | 2 | ||||
-rw-r--r-- | drivers/md/dm.c | 5 | ||||
-rw-r--r-- | drivers/md/md-bitmap.c | 2 | ||||
-rw-r--r-- | drivers/md/md-linear.c | 5 | ||||
-rw-r--r-- | drivers/md/md-multipath.c | 5 | ||||
-rw-r--r-- | drivers/md/md.c | 68 | ||||
-rw-r--r-- | drivers/md/md.h | 4 | ||||
-rw-r--r-- | drivers/md/raid0.c | 7 | ||||
-rw-r--r-- | drivers/md/raid1.c | 5 | ||||
-rw-r--r-- | drivers/md/raid10.c | 5 | ||||
-rw-r--r-- | drivers/md/raid5.c | 4 |
12 files changed, 83 insertions, 36 deletions
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 2900fbde89b3..76587e9af0ef 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio) struct flakey_c *fc = ti->private; bio_set_dev(bio, fc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector); } @@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); pb->bio_submitted = false; - /* Do not fail reset zone */ - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) goto map_bio; /* Are we alive ? */ @@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) return DM_ENDIO_DONE; if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index ecefe6703736..97acafd48c85 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio) struct linear_c *lc = ti->private; bio_set_dev(bio, lc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = linear_map_sector(ti, bio->bi_iter.bi_sector); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1a5e328c443a..bc143c1b2333 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1174,7 +1174,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, /* * A target may call dm_accept_partial_bio only from the map routine. It is - * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET. + * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, + * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH. * * dm_accept_partial_bio informs the dm that the target only wants to process * additional n_sectors sectors of the bio and the rest of the data should be @@ -1627,7 +1628,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.sector_count = 0; error = __send_empty_flush(&ci); /* dec_pending submits any data associated with flush */ - } else if (bio_op(bio) == REQ_OP_ZONE_RESET) { + } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; ci.sector_count = 0; error = __split_and_process_non_flush(&ci); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index b092c7b5282f..3ad18246fcb3 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, memcpy(page_address(store.sb_page), page_address(bitmap->storage.sb_page), sizeof(bitmap_super_t)); + spin_lock_irq(&bitmap->counts.lock); md_bitmap_file_unmap(&bitmap->storage); bitmap->storage = store; @@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, blocks = min(old_counts.chunks << old_counts.chunkshift, chunks << chunkshift); - spin_lock_irq(&bitmap->counts.lock); /* For cluster raid, need to pre-allocate bitmap */ if (mddev_is_clustered(bitmap->mddev)) { unsigned long page; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index c766c559d36d..26c75c0199fa 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) sector_t start_sector, end_sector, data_offset; sector_t bio_sector = bio->bi_iter.bi_sector; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } tmp_dev = which_dev(mddev, bio_sector); start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 6780938d2991..152f9e65a226 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } mp_bh = mempool_alloc(&conf->pool, GFP_NOIO); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1be7abeb24fd..6f0ecfe8eab2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws) } } -void md_flush_request(struct mddev *mddev, struct bio *bio) +/* + * Manages consolidation of flushes and submitting any flushes needed for + * a bio with REQ_PREFLUSH. Returns true if the bio is finished or is + * being finished in another context. Returns false if the flushing is + * complete but still needs the I/O portion of the bio to be processed. + */ +bool md_flush_request(struct mddev *mddev, struct bio *bio) { ktime_t start = ktime_get_boottime(); spin_lock_irq(&mddev->lock); @@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + return false; } } + return true; } EXPORT_SYMBOL(md_flush_request); @@ -1149,7 +1156,15 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor rdev->desc_nr = sb->this_disk.number; if (!refdev) { - ret = 1; + /* + * Insist on good event counter while assembling, except + * for spares (which don't need an event count) + */ + if (sb->disks[rdev->desc_nr].state & ( + (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; mdp_super_t *refsb = page_address(refdev->sb_page); @@ -1165,7 +1180,14 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor } ev1 = md_event(sb); ev2 = md_event(refsb); - if (ev1 > ev2) + + /* + * Insist on good event counter while assembling, except + * for spares (which don't need an event count) + */ + if (sb->disks[rdev->desc_nr].state & ( + (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)) && + (ev1 > ev2)) ret = 1; else ret = 0; @@ -1525,6 +1547,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sector_t sectors; char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; int bmask; + __u64 role; /* * Calculate the position of the superblock in 512byte sectors. @@ -1658,8 +1681,20 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sb->level != 0) return -EINVAL; + role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); + if (!refdev) { - ret = 1; + /* + * Insist of good event counter while assembling, except for + * spares (which don't need an event count) + */ + if (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (role < MD_DISK_ROLE_MAX || + role == MD_DISK_ROLE_JOURNAL)) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; struct mdp_superblock_1 *refsb = page_address(refdev->sb_page); @@ -1676,7 +1711,14 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ ev1 = le64_to_cpu(sb->events); ev2 = le64_to_cpu(refsb->events); - if (ev1 > ev2) + /* + * Insist of good event counter while assembling, except for + * spares (which don't need an event count) + */ + if (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (role < MD_DISK_ROLE_MAX || + role == MD_DISK_ROLE_JOURNAL) && ev1 > ev2) ret = 1; else ret = 0; @@ -3597,7 +3639,7 @@ abort_free: * Check a full RAID array for plausibility */ -static void analyze_sbs(struct mddev *mddev) +static int analyze_sbs(struct mddev *mddev) { int i; struct md_rdev *rdev, *freshest, *tmp; @@ -3618,6 +3660,12 @@ static void analyze_sbs(struct mddev *mddev) md_kick_rdev_from_array(rdev); } + /* Cannot find a valid fresh disk */ + if (!freshest) { + pr_warn("md: cannot find a valid disk\n"); + return -EINVAL; + } + super_types[mddev->major_version]. validate_super(mddev, freshest); @@ -3652,6 +3700,8 @@ static void analyze_sbs(struct mddev *mddev) clear_bit(In_sync, &rdev->flags); } } + + return 0; } /* Read a fixed-point number. @@ -5570,7 +5620,9 @@ int md_run(struct mddev *mddev) if (!mddev->raid_disks) { if (!mddev->persistent) return -EINVAL; - analyze_sbs(mddev); + err = analyze_sbs(mddev); + if (err) + return -EINVAL; } if (mddev->level != LEVEL_NONE) diff --git a/drivers/md/md.h b/drivers/md/md.h index c5e3ff398b59..5f86f8adb0a4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -550,7 +550,7 @@ struct md_personality int level; struct list_head list; struct module *owner; - bool (*make_request)(struct mddev *mddev, struct bio *bio); + bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() @@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); extern int mddev_congested(struct mddev *mddev, int bits); -extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 1e772287b1c8..b7c20979bd19 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) unsigned chunk_sects; unsigned sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { raid0_handle_discard(mddev, bio); @@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev = map_sector(mddev, zone, sector, §or); break; default: - WARN("md/raid0:%s: Invalid layout\n", mdname(mddev)); + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); bio_io_error(bio); return true; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0466ee2453b4..bb29aeefcbd0 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1567,10 +1567,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio) { sector_t sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } /* * There is a limit to the maximum size, but diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 299c7b1c9718..2eca0a81a8c9 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) int chunk_sects = chunk_mask + 1; int sectors = bio_sectors(bio); - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (!md_write_start(mddev, bio)) return false; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 223e97ab27e6..12a8ce83786e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (ret == 0) return true; if (ret == -ENODEV) { - md_flush_request(mddev, bi); - return true; + if (md_flush_request(mddev, bi)) + return true; } /* ret == -EAGAIN, fallback */ /* |