From e1defc4ff0cf57aca6c5e3ff99fa503f5943c1f1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 22 May 2009 17:17:49 -0400 Subject: block: Do away with the notion of hardsect_size Until now we have had a 1:1 mapping between storage device physical block size and the logical block sized used when addressing the device. With SATA 4KB drives coming out that will no longer be the case. The sector size will be 4KB but the logical block size will remain 512-bytes. Hence we need to distinguish between the physical block size and the logical ditto. This patch renames hardsect_size to logical_block_size. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index fccc8343a250..4cbc19f5c304 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1202,7 +1202,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read)); rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256; - bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1; + bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1; if (rdev->sb_size & bmask) rdev->sb_size = (rdev->sb_size | bmask) + 1; -- cgit v1.2.3 From 2ac06c3332898103210b478c5a17c20e28929287 Mon Sep 17 00:00:00 2001 From: raz ben yehuda Date: Tue, 16 Jun 2009 17:01:42 +1000 Subject: md: prepare for non-power-of-two chunk sizes Remove chunk size check from md as this is now performed in the run function in each personality. Replace chunk size power 2 code calculations by a regular division. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown --- drivers/md/md.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 20f6ac338349..a02bde70874b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -444,8 +444,11 @@ static sector_t calc_num_sectors(mdk_rdev_t *rdev, unsigned chunk_size) { sector_t num_sectors = rdev->sb_start; - if (chunk_size) - num_sectors &= ~((sector_t)chunk_size/512 - 1); + if (chunk_size) { + unsigned chunk_sects = chunk_size>>9; + sector_div(num_sectors, chunk_sects); + num_sectors *= chunk_sects; + } return num_sectors; } @@ -1248,8 +1251,12 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) if (rdev->sectors < le64_to_cpu(sb->data_size)) return -EINVAL; rdev->sectors = le64_to_cpu(sb->data_size); - if (le32_to_cpu(sb->chunksize)) - rdev->sectors &= ~((sector_t)le32_to_cpu(sb->chunksize) - 1); + if (le32_to_cpu(sb->chunksize)) { + int chunk_sects = le32_to_cpu(sb->chunksize); + sector_t chunks = rdev->sectors; + sector_div(chunks, chunk_sects); + rdev->sectors = chunks * chunk_sects; + } if (le64_to_cpu(sb->size) > rdev->sectors) return -EINVAL; @@ -3528,7 +3535,8 @@ min_sync_store(mddev_t *mddev, const char *buf, size_t len) /* Must be a multiple of chunk_size */ if (mddev->chunk_size) { - if (min & (sector_t)((mddev->chunk_size>>9)-1)) + sector_t temp = min; + if (sector_div(temp, (mddev->chunk_size>>9))) return -EINVAL; } mddev->resync_min = min; @@ -3565,7 +3573,8 @@ max_sync_store(mddev_t *mddev, const char *buf, size_t len) /* Must be a multiple of chunk_size */ if (mddev->chunk_size) { - if (max & (sector_t)((mddev->chunk_size>>9)-1)) + sector_t temp = max; + if (sector_div(temp, (mddev->chunk_size>>9))) return -EINVAL; } mddev->resync_max = max; @@ -4006,14 +4015,6 @@ static int do_md_run(mddev_t * mddev) chunk_size, MAX_CHUNK_SIZE); return -EINVAL; } - /* - * chunk-size has to be a power of 2 - */ - if ( (1 << ffz(~chunk_size)) != chunk_size) { - printk(KERN_ERR "chunk_size of %d not valid\n", chunk_size); - return -EINVAL; - } - /* devices must have minimum size of one chunk */ list_for_each_entry(rdev, &mddev->disks, same_set) { if (test_bit(Faulty, &rdev->flags)) -- cgit v1.2.3 From 9d8f0363623b3da12c43007cf77f5e1a4e8a5964 Mon Sep 17 00:00:00 2001 From: Andre Noll Date: Thu, 18 Jun 2009 08:45:01 +1000 Subject: md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll Signed-off-by: NeilBrown --- drivers/md/md.c | 51 ++++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 25 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index a02bde70874b..abcc0fef30e3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -869,7 +869,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->minor_version = sb->minor_version; mddev->patch_version = sb->patch_version; mddev->external = 0; - mddev->chunk_size = sb->chunk_size; + mddev->chunk_sectors = sb->chunk_size >> 9; mddev->ctime = sb->ctime; mddev->utime = sb->utime; mddev->level = sb->level; @@ -892,7 +892,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_size; + mddev->new_chunk = mddev->chunk_sectors << 9; } if (sb->state & (1<recovery_cp = 0; sb->layout = mddev->layout; - sb->chunk_size = mddev->chunk_size; + sb->chunk_size = mddev->chunk_sectors << 9; if (mddev->bitmap && mddev->bitmap_file == NULL) sb->state |= (1<major_version = 1; mddev->patch_version = 0; mddev->external = 0; - mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9; + mddev->chunk_sectors = le32_to_cpu(sb->chunksize); mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1); mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1); mddev->level = le32_to_cpu(sb->level); @@ -1310,7 +1310,7 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_size; + mddev->new_chunk = mddev->chunk_sectors << 9; } } else if (mddev->pers == NULL) { @@ -1382,7 +1382,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) sb->raid_disks = cpu_to_le32(mddev->raid_disks); sb->size = cpu_to_le64(mddev->dev_sectors); - sb->chunksize = cpu_to_le32(mddev->chunk_size >> 9); + sb->chunksize = cpu_to_le32(mddev->chunk_sectors); sb->level = cpu_to_le32(mddev->level); sb->layout = cpu_to_le32(mddev->layout); @@ -2753,7 +2753,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len) if (IS_ERR(priv)) { mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_size; + mddev->new_chunk = mddev->chunk_sectors << 9; mddev->raid_disks -= mddev->delta_disks; mddev->delta_disks = 0; module_put(pers->owner); @@ -2771,7 +2771,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len) strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); mddev->level = mddev->new_level; mddev->layout = mddev->new_layout; - mddev->chunk_size = mddev->new_chunk; + mddev->chunk_sectors = mddev->new_chunk >> 9; mddev->delta_disks = 0; pers->run(mddev); mddev_resume(mddev); @@ -2864,10 +2864,10 @@ static ssize_t chunk_size_show(mddev_t *mddev, char *page) { if (mddev->reshape_position != MaxSector && - mddev->chunk_size != mddev->new_chunk) + mddev->chunk_sectors << 9 != mddev->new_chunk) return sprintf(page, "%d (%d)\n", mddev->new_chunk, - mddev->chunk_size); - return sprintf(page, "%d\n", mddev->chunk_size); + mddev->chunk_sectors << 9); + return sprintf(page, "%d\n", mddev->chunk_sectors << 9); } static ssize_t @@ -2889,7 +2889,7 @@ chunk_size_store(mddev_t *mddev, const char *buf, size_t len) } else { mddev->new_chunk = n; if (mddev->reshape_position == MaxSector) - mddev->chunk_size = n; + mddev->chunk_sectors = n >> 9; } return len; } @@ -3534,9 +3534,9 @@ min_sync_store(mddev_t *mddev, const char *buf, size_t len) return -EBUSY; /* Must be a multiple of chunk_size */ - if (mddev->chunk_size) { + if (mddev->chunk_sectors) { sector_t temp = min; - if (sector_div(temp, (mddev->chunk_size>>9))) + if (sector_div(temp, mddev->chunk_sectors)) return -EINVAL; } mddev->resync_min = min; @@ -3572,9 +3572,9 @@ max_sync_store(mddev_t *mddev, const char *buf, size_t len) return -EBUSY; /* Must be a multiple of chunk_size */ - if (mddev->chunk_size) { + if (mddev->chunk_sectors) { sector_t temp = max; - if (sector_div(temp, (mddev->chunk_size>>9))) + if (sector_div(temp, mddev->chunk_sectors)) return -EINVAL; } mddev->resync_max = max; @@ -3665,7 +3665,7 @@ reshape_position_store(mddev_t *mddev, const char *buf, size_t len) mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_size; + mddev->new_chunk = mddev->chunk_sectors << 9; return len; } @@ -4007,7 +4007,7 @@ static int do_md_run(mddev_t * mddev) analyze_sbs(mddev); } - chunk_size = mddev->chunk_size; + chunk_size = mddev->chunk_sectors << 9; if (chunk_size) { if (chunk_size > MAX_CHUNK_SIZE) { @@ -4406,7 +4406,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) mddev->flags = 0; mddev->ro = 0; mddev->metadata_type[0] = 0; - mddev->chunk_size = 0; + mddev->chunk_sectors = 0; mddev->ctime = mddev->utime = 0; mddev->layout = 0; mddev->max_disks = 0; @@ -4619,7 +4619,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg) info.spare_disks = spare; info.layout = mddev->layout; - info.chunk_size = mddev->chunk_size; + info.chunk_size = mddev->chunk_sectors << 9; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; @@ -4844,7 +4844,8 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) rdev->sb_start = rdev->bdev->bd_inode->i_size / 512; } else rdev->sb_start = calc_dev_sboffset(rdev->bdev); - rdev->sectors = calc_num_sectors(rdev, mddev->chunk_size); + rdev->sectors = calc_num_sectors(rdev, + mddev->chunk_sectors << 9); err = bind_rdev_to_array(rdev, mddev); if (err) { @@ -4914,7 +4915,7 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev) else rdev->sb_start = rdev->bdev->bd_inode->i_size / 512; - rdev->sectors = calc_num_sectors(rdev, mddev->chunk_size); + rdev->sectors = calc_num_sectors(rdev, mddev->chunk_sectors << 9); if (test_bit(Faulty, &rdev->flags)) { printk(KERN_WARNING @@ -5063,7 +5064,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) mddev->external = 0; mddev->layout = info->layout; - mddev->chunk_size = info->chunk_size; + mddev->chunk_sectors = info->chunk_size >> 9; mddev->max_disks = MD_SB_DISKS; @@ -5082,7 +5083,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) get_random_bytes(mddev->uuid, 16); mddev->new_level = mddev->level; - mddev->new_chunk = mddev->chunk_size; + mddev->new_chunk = mddev->chunk_sectors << 9; mddev->new_layout = mddev->layout; mddev->delta_disks = 0; @@ -5192,7 +5193,7 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info) mddev->level != info->level || /* mddev->layout != info->layout || */ !mddev->persistent != info->not_persistent|| - mddev->chunk_size != info->chunk_size || + mddev->chunk_sectors != info->chunk_size >> 9 || /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */ ((state^info->state) & 0xfffffe00) ) -- cgit v1.2.3 From 664e7c413f1e90eceb0b2596dd73a0832faec058 Mon Sep 17 00:00:00 2001 From: Andre Noll Date: Thu, 18 Jun 2009 08:45:27 +1000 Subject: md: Convert mddev->new_chunk to sectors. A straight-forward conversion which gets rid of some multiplications/divisions/shifts. The patch also introduces a couple of new ones, most of which are due to conf->chunk_size still being represented in bytes. This will be cleaned up in subsequent patches. Signed-off-by: Andre Noll Signed-off-by: NeilBrown --- drivers/md/md.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index abcc0fef30e3..f996d8342a85 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -886,13 +886,13 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->delta_disks = sb->delta_disks; mddev->new_level = sb->new_level; mddev->new_layout = sb->new_layout; - mddev->new_chunk = sb->new_chunk; + mddev->new_chunk_sectors = sb->new_chunk >> 9; } else { mddev->reshape_position = MaxSector; mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_sectors << 9; + mddev->new_chunk_sectors = mddev->chunk_sectors; } if (sb->state & (1<new_level = mddev->new_level; sb->delta_disks = mddev->delta_disks; sb->new_layout = mddev->new_layout; - sb->new_chunk = mddev->new_chunk; + sb->new_chunk = mddev->new_chunk_sectors << 9; } mddev->minor_version = sb->minor_version; if (mddev->in_sync) @@ -1304,13 +1304,13 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->delta_disks = le32_to_cpu(sb->delta_disks); mddev->new_level = le32_to_cpu(sb->new_level); mddev->new_layout = le32_to_cpu(sb->new_layout); - mddev->new_chunk = le32_to_cpu(sb->new_chunk)<<9; + mddev->new_chunk_sectors = le32_to_cpu(sb->new_chunk); } else { mddev->reshape_position = MaxSector; mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_sectors << 9; + mddev->new_chunk_sectors = mddev->chunk_sectors; } } else if (mddev->pers == NULL) { @@ -1409,7 +1409,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) sb->new_layout = cpu_to_le32(mddev->new_layout); sb->delta_disks = cpu_to_le32(mddev->delta_disks); sb->new_level = cpu_to_le32(mddev->new_level); - sb->new_chunk = cpu_to_le32(mddev->new_chunk>>9); + sb->new_chunk = cpu_to_le32(mddev->new_chunk_sectors); } max_dev = 0; @@ -2753,7 +2753,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len) if (IS_ERR(priv)) { mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_sectors << 9; + mddev->new_chunk_sectors = mddev->chunk_sectors; mddev->raid_disks -= mddev->delta_disks; mddev->delta_disks = 0; module_put(pers->owner); @@ -2771,7 +2771,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len) strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); mddev->level = mddev->new_level; mddev->layout = mddev->new_layout; - mddev->chunk_sectors = mddev->new_chunk >> 9; + mddev->chunk_sectors = mddev->new_chunk_sectors; mddev->delta_disks = 0; pers->run(mddev); mddev_resume(mddev); @@ -2864,8 +2864,9 @@ static ssize_t chunk_size_show(mddev_t *mddev, char *page) { if (mddev->reshape_position != MaxSector && - mddev->chunk_sectors << 9 != mddev->new_chunk) - return sprintf(page, "%d (%d)\n", mddev->new_chunk, + mddev->chunk_sectors != mddev->new_chunk_sectors) + return sprintf(page, "%d (%d)\n", + mddev->new_chunk_sectors << 9, mddev->chunk_sectors << 9); return sprintf(page, "%d\n", mddev->chunk_sectors << 9); } @@ -2887,7 +2888,7 @@ chunk_size_store(mddev_t *mddev, const char *buf, size_t len) if (err) return err; } else { - mddev->new_chunk = n; + mddev->new_chunk_sectors = n >> 9; if (mddev->reshape_position == MaxSector) mddev->chunk_sectors = n >> 9; } @@ -3665,7 +3666,7 @@ reshape_position_store(mddev_t *mddev, const char *buf, size_t len) mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; - mddev->new_chunk = mddev->chunk_sectors << 9; + mddev->new_chunk_sectors = mddev->chunk_sectors; return len; } @@ -4414,7 +4415,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) mddev->delta_disks = 0; mddev->new_level = LEVEL_NONE; mddev->new_layout = 0; - mddev->new_chunk = 0; + mddev->new_chunk_sectors = 0; mddev->curr_resync = 0; mddev->resync_mismatches = 0; mddev->suspend_lo = mddev->suspend_hi = 0; @@ -5083,7 +5084,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) get_random_bytes(mddev->uuid, 16); mddev->new_level = mddev->level; - mddev->new_chunk = mddev->chunk_sectors << 9; + mddev->new_chunk_sectors = mddev->chunk_sectors; mddev->new_layout = mddev->layout; mddev->delta_disks = 0; -- cgit v1.2.3 From 597a711b69cfff95c4b8f6069037e7ad3fc71f56 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 18 Jun 2009 08:47:42 +1000 Subject: md: remove unnecessary arguments from ->reconfig method. Passing the new layout and chunksize as args is not necessary as the mddev has fields for new_check and new_layout. This is preparation for combining the check_reshape and reconfig methods Signed-off-by: NeilBrown --- drivers/md/md.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index f996d8342a85..5caa421c2367 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2809,9 +2809,12 @@ layout_store(mddev_t *mddev, const char *buf, size_t len) int err; if (mddev->pers->reconfig == NULL) return -EBUSY; - err = mddev->pers->reconfig(mddev, n, -1); - if (err) + mddev->new_layout = n; + err = mddev->pers->reconfig(mddev); + if (err) { + mddev->new_layout = mddev->layout; return err; + } } else { mddev->new_layout = n; if (mddev->reshape_position == MaxSector) @@ -2884,9 +2887,12 @@ chunk_size_store(mddev_t *mddev, const char *buf, size_t len) int err; if (mddev->pers->reconfig == NULL) return -EBUSY; - err = mddev->pers->reconfig(mddev, -1, n); - if (err) + mddev->new_chunk_sectors = n >> 9; + err = mddev->pers->reconfig(mddev); + if (err) { + mddev->new_chunk_sectors = mddev->chunk_sectors; return err; + } } else { mddev->new_chunk_sectors = n >> 9; if (mddev->reshape_position == MaxSector) @@ -5220,8 +5226,13 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info) */ if (mddev->pers->reconfig == NULL) return -EINVAL; - else - return mddev->pers->reconfig(mddev, info->layout, -1); + else { + mddev->new_layout = info->layout; + rv = mddev->pers->reconfig(mddev); + if (rv) + mddev->new_layout = mddev->layout; + return rv; + } } if (info->size >= 0 && mddev->dev_sectors / 2 != info->size) rv = update_size(mddev, (sector_t)info->size * 2); -- cgit v1.2.3 From 50ac168a6e0a061bf5346d53aa9e7beb94c97527 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 18 Jun 2009 08:47:55 +1000 Subject: md: merge reconfig and check_reshape methods. The difference between these two methods is artificial. Both check that a pending reshape is valid, and perform any aspect of it that can be done immediately. 'reconfig' handles chunk size and layout. 'check_reshape' handles raid_disks. So make them just one method. Signed-off-by: NeilBrown --- drivers/md/md.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 5caa421c2367..80f039ec3ac2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2807,10 +2807,10 @@ layout_store(mddev_t *mddev, const char *buf, size_t len) if (mddev->pers) { int err; - if (mddev->pers->reconfig == NULL) + if (mddev->pers->check_reshape == NULL) return -EBUSY; mddev->new_layout = n; - err = mddev->pers->reconfig(mddev); + err = mddev->pers->check_reshape(mddev); if (err) { mddev->new_layout = mddev->layout; return err; @@ -2885,10 +2885,10 @@ chunk_size_store(mddev_t *mddev, const char *buf, size_t len) if (mddev->pers) { int err; - if (mddev->pers->reconfig == NULL) + if (mddev->pers->check_reshape == NULL) return -EBUSY; mddev->new_chunk_sectors = n >> 9; - err = mddev->pers->reconfig(mddev); + err = mddev->pers->check_reshape(mddev); if (err) { mddev->new_chunk_sectors = mddev->chunk_sectors; return err; @@ -5224,11 +5224,11 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info) * we don't need to do anything at the md level, the * personality will take care of it all. */ - if (mddev->pers->reconfig == NULL) + if (mddev->pers->check_reshape == NULL) return -EINVAL; else { mddev->new_layout = info->layout; - rv = mddev->pers->reconfig(mddev); + rv = mddev->pers->check_reshape(mddev); if (rv) mddev->new_layout = mddev->layout; return rv; @@ -6731,7 +6731,8 @@ void md_check_recovery(mddev_t *mddev) */ if (mddev->reshape_position != MaxSector) { - if (mddev->pers->check_reshape(mddev) != 0) + if (mddev->pers->check_reshape == NULL || + mddev->pers->check_reshape(mddev) != 0) /* Cannot proceed */ goto unlock; set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); -- cgit v1.2.3 From 8c6ac868b107ed50a46204f6d14e2ad9443ff146 Mon Sep 17 00:00:00 2001 From: Andre Noll Date: Thu, 18 Jun 2009 08:48:06 +1000 Subject: md: Push down reconstruction log message to personality code. Currently, the md layer checks in analyze_sbs() if the raid level supports reconstruction (mddev->level >= 1) and if reconstruction is in progress (mddev->recovery_cp != MaxSector). Move that printk into the personality code of those raid levels that care (levels 1, 4, 5, 6, 10). Signed-off-by: Andre Noll Signed-off-by: NeilBrown --- drivers/md/md.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 80f039ec3ac2..90147370bfd7 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2604,15 +2604,6 @@ static void analyze_sbs(mddev_t * mddev) clear_bit(In_sync, &rdev->flags); } } - - - - if (mddev->recovery_cp != MaxSector && - mddev->level >= 1) - printk(KERN_ERR "md: %s: raid array is not clean" - " -- starting background reconstruction\n", - mdname(mddev)); - } static void md_safemode_timeout(unsigned long data); -- cgit v1.2.3 From 1b57f132231593923cb4ab99943ddd777e8745bc Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 18 Jun 2009 08:48:19 +1000 Subject: md: move assignment of ->utime so that it never gets skipped. Currently the assignment to utime gets skipped for 'external' metadata. So move it to the top of the function so that it always gets effected. This is of largely cosmetic interest. Nothing actually depends on ->utime being right for external arrays. "mdadm --monitor" does use it for 0.90 and 1.x arrays, but with mdadm-3.0, this is not important for external metadata. Signed-off-by: NeilBrown --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 90147370bfd7..d9cce54cc2d5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1904,6 +1904,7 @@ static void md_update_sb(mddev_t * mddev, int force_change) int sync_req; int nospares = 0; + mddev->utime = get_seconds(); if (mddev->external) return; repeat: @@ -1933,7 +1934,6 @@ repeat: nospares = 0; sync_req = mddev->in_sync; - mddev->utime = get_seconds(); /* If this is just a dirty<->clean transition, and the array is clean * and 'events' is odd, we can roll back to the previous clean state */ -- cgit v1.2.3 From 8190e754e0723de7cecb80bdd9eb93911dfa04a1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 18 Jun 2009 08:48:58 +1000 Subject: md: remove chunksize rounding from common code. It is easiest to round sizes to multiples of chunk size in the personality code for those personalities which care. Those personalities now do the rounding, so we can remove that function from common code. Also remove the upper bound on the size of a chunk, and the lower bound on the size of a device (1 chunk), neither of which really buy us anything. Signed-off-by: NeilBrown --- drivers/md/md.c | 52 +++------------------------------------------------- 1 file changed, 3 insertions(+), 49 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index d9cce54cc2d5..0f11fd1417ab 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -440,18 +440,6 @@ static inline sector_t calc_dev_sboffset(struct block_device *bdev) return MD_NEW_SIZE_SECTORS(num_sectors); } -static sector_t calc_num_sectors(mdk_rdev_t *rdev, unsigned chunk_size) -{ - sector_t num_sectors = rdev->sb_start; - - if (chunk_size) { - unsigned chunk_sects = chunk_size>>9; - sector_div(num_sectors, chunk_sects); - num_sectors *= chunk_sects; - } - return num_sectors; -} - static int alloc_disk_sb(mdk_rdev_t * rdev) { if (rdev->sb_page) @@ -839,7 +827,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version else ret = 0; } - rdev->sectors = calc_num_sectors(rdev, sb->chunk_size); + rdev->sectors = rdev->sb_start; if (rdev->sectors < sb->size * 2 && sb->level > 1) /* "this cannot possibly happen" ... */ @@ -1251,13 +1239,6 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) if (rdev->sectors < le64_to_cpu(sb->data_size)) return -EINVAL; rdev->sectors = le64_to_cpu(sb->data_size); - if (le32_to_cpu(sb->chunksize)) { - int chunk_sects = le32_to_cpu(sb->chunksize); - sector_t chunks = rdev->sectors; - sector_div(chunks, chunk_sects); - rdev->sectors = chunks * chunk_sects; - } - if (le64_to_cpu(sb->size) > rdev->sectors) return -EINVAL; return ret; @@ -3983,11 +3964,9 @@ static int start_dirty_degraded; static int do_md_run(mddev_t * mddev) { int err; - int chunk_size; mdk_rdev_t *rdev; struct gendisk *disk; struct mdk_personality *pers; - char b[BDEVNAME_SIZE]; if (list_empty(&mddev->disks)) /* cannot run an array with no devices.. */ @@ -4005,30 +3984,6 @@ static int do_md_run(mddev_t * mddev) analyze_sbs(mddev); } - chunk_size = mddev->chunk_sectors << 9; - - if (chunk_size) { - if (chunk_size > MAX_CHUNK_SIZE) { - printk(KERN_ERR "too big chunk_size: %d > %d\n", - chunk_size, MAX_CHUNK_SIZE); - return -EINVAL; - } - /* devices must have minimum size of one chunk */ - list_for_each_entry(rdev, &mddev->disks, same_set) { - if (test_bit(Faulty, &rdev->flags)) - continue; - if (rdev->sectors < chunk_size / 512) { - printk(KERN_WARNING - "md: Dev %s smaller than chunk_size:" - " %llu < %d\n", - bdevname(rdev->bdev,b), - (unsigned long long)rdev->sectors, - chunk_size / 512); - return -EINVAL; - } - } - } - if (mddev->level != LEVEL_NONE) request_module("md-level-%d", mddev->level); else if (mddev->clevel[0]) @@ -4842,8 +4797,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) rdev->sb_start = rdev->bdev->bd_inode->i_size / 512; } else rdev->sb_start = calc_dev_sboffset(rdev->bdev); - rdev->sectors = calc_num_sectors(rdev, - mddev->chunk_sectors << 9); + rdev->sectors = rdev->sb_start; err = bind_rdev_to_array(rdev, mddev); if (err) { @@ -4913,7 +4867,7 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev) else rdev->sb_start = rdev->bdev->bd_inode->i_size / 512; - rdev->sectors = calc_num_sectors(rdev, mddev->chunk_sectors << 9); + rdev->sectors = rdev->sb_start; if (test_bit(Faulty, &rdev->flags)) { printk(KERN_WARNING -- cgit v1.2.3 From 0894cc3066aaa3e75a99383c0d25feebf9b688ac Mon Sep 17 00:00:00 2001 From: Andre Noll Date: Thu, 18 Jun 2009 08:49:23 +1000 Subject: md: Move check for bitmap presence to personality code. If the superblock of a component device indicates the presence of a bitmap but the corresponding raid personality does not support bitmaps (raid0, linear, multipath, faulty), then something is seriously wrong and we'd better refuse to run such an array. Currently, this check is performed while the superblocks are examined, i.e. before entering personality code. Therefore the generic md layer must know which raid levels support bitmaps and which do not. This patch avoids this layer violation without adding identical code to various personalities. This is accomplished by introducing a new public function to md.c, md_check_no_bitmap(), which replaces the hard-coded checks in the superblock loading functions. A call to md_check_no_bitmap() is added to the ->run method of each personality which does not support bitmaps and assembly is aborted if at least one component device contains a bitmap. Signed-off-by: Andre Noll Signed-off-by: NeilBrown --- drivers/md/md.c | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 0f11fd1417ab..09be637d52cb 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -735,6 +735,24 @@ struct super_type { sector_t num_sectors); }; +/* + * Check that the given mddev has no bitmap. + * + * This function is called from the run method of all personalities that do not + * support bitmaps. It prints an error message and returns non-zero if mddev + * has a bitmap. Otherwise, it returns 0. + * + */ +int md_check_no_bitmap(mddev_t *mddev) +{ + if (!mddev->bitmap_file && !mddev->bitmap_offset) + return 0; + printk(KERN_ERR "%s: bitmaps are not supported for %s\n", + mdname(mddev), mddev->pers->name); + return 1; +} +EXPORT_SYMBOL(md_check_no_bitmap); + /* * load_super for 0.90.0 */ @@ -788,17 +806,6 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version rdev->data_offset = 0; rdev->sb_size = MD_SB_BYTES; - if (sb->state & (1<level != 1 && sb->level != 4 - && sb->level != 5 && sb->level != 6 - && sb->level != 10) { - /* FIXME use a better test */ - printk(KERN_WARNING - "md: bitmaps not supported for this level.\n"); - goto abort; - } - } - if (sb->level == LEVEL_MULTIPATH) rdev->desc_nr = -1; else @@ -1176,17 +1183,6 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) bdevname(rdev->bdev,b)); return -EINVAL; } - if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) { - if (sb->level != cpu_to_le32(1) && - sb->level != cpu_to_le32(4) && - sb->level != cpu_to_le32(5) && - sb->level != cpu_to_le32(6) && - sb->level != cpu_to_le32(10)) { - printk(KERN_WARNING - "md: bitmaps not supported for this level.\n"); - return -EINVAL; - } - } rdev->preferred_minor = 0xffff; rdev->data_offset = le64_to_cpu(sb->data_offset); -- cgit v1.2.3