X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fmd%2Fmd.c;h=4a0c57db2b67657b8c09cfbe67f5d2cfb487ed95;hb=5e0b537c7d94efe3fea0fee8e2533c3231a8af75;hp=c842e34d850eea6a89a9f54e9ed53b1fa7b6087c;hpb=fca4d848f0e6fafdc2b25f8a0cf1e76935f13ac2;p=linux-2.6 diff --git a/drivers/md/md.c b/drivers/md/md.c index c842e34d85..4a0c57db2b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -19,6 +19,9 @@ Neil Brown . + - persistent bitmap code + Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc. + This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) @@ -33,6 +36,7 @@ #include #include #include +#include #include #include #include /* for invalidate_bdev */ @@ -40,6 +44,8 @@ #include +#include + #ifdef CONFIG_KMOD #include #endif @@ -189,8 +195,7 @@ static mddev_t * mddev_find(dev_t unit) if (mddev->unit == unit) { mddev_get(mddev); spin_unlock(&all_mddevs_lock); - if (new) - kfree(new); + kfree(new); return mddev; } @@ -218,6 +223,8 @@ static mddev_t * mddev_find(dev_t unit) INIT_LIST_HEAD(&new->all_mddevs); init_timer(&new->safemode_timer); atomic_set(&new->active, 1); + spin_lock_init(&new->write_lock); + init_waitqueue_head(&new->sb_wait); new->queue = blk_alloc_queue(GFP_KERNEL); if (!new->queue) { @@ -320,6 +327,41 @@ static void free_disk_sb(mdk_rdev_t * rdev) } +static int super_written(struct bio *bio, unsigned int bytes_done, int error) +{ + mdk_rdev_t *rdev = bio->bi_private; + if (bio->bi_size) + return 1; + + if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) + md_error(rdev->mddev, rdev); + + if (atomic_dec_and_test(&rdev->mddev->pending_writes)) + wake_up(&rdev->mddev->sb_wait); + bio_put(bio); + return 0; +} + +void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, + sector_t sector, int size, struct page *page) +{ + /* write first size bytes of page to sector of rdev + * Increment mddev->pending_writes before returning + * and decrement it on completion, waking up sb_wait + * if zero is reached. + * If an error occurred, call md_error + */ + struct bio *bio = bio_alloc(GFP_NOIO, 1); + + bio->bi_bdev = rdev->bdev; + bio->bi_sector = sector; + bio_add_page(bio, page, size, 0); + bio->bi_private = rdev; + bio->bi_end_io = super_written; + atomic_inc(&mddev->pending_writes); + submit_bio((1<bi_size) @@ -329,7 +371,7 @@ static int bi_complete(struct bio *bio, unsigned int bytes_done, int error) return 0; } -static int sync_page_io(struct block_device *bdev, sector_t sector, int size, +int sync_page_io(struct block_device *bdev, sector_t sector, int size, struct page *page, int rw) { struct bio *bio = bio_alloc(GFP_NOIO, 1); @@ -416,11 +458,8 @@ static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2) ret = 1; abort: - if (tmp1) - kfree(tmp1); - if (tmp2) - kfree(tmp2); - + kfree(tmp1); + kfree(tmp2); return ret; } @@ -569,6 +608,8 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) mdp_disk_t *desc; mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page); + rdev->raid_disk = -1; + rdev->in_sync = 0; if (mddev->raid_disks == 0) { mddev->major_version = 0; mddev->minor_version = sb->minor_version; @@ -599,16 +640,35 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) memcpy(mddev->uuid+12,&sb->set_uuid3, 4); mddev->max_disks = MD_SB_DISKS; - } else { - __u64 ev1; - ev1 = md_event(sb); + + if (sb->state & (1<bitmap_file == NULL) { + if (mddev->level != 1) { + /* FIXME use a better test */ + printk(KERN_WARNING "md: bitmaps only support for raid1\n"); + return -EINVAL; + } + mddev->bitmap_offset = (MD_SB_BYTES >> 9); + } + + } else if (mddev->pers == NULL) { + /* Insist on good event counter while assembling */ + __u64 ev1 = md_event(sb); ++ev1; if (ev1 < mddev->events) return -EINVAL; - } + } else if (mddev->bitmap) { + /* if adding to array with a bitmap, then we can accept an + * older device ... but not too old. + */ + __u64 ev1 = md_event(sb); + if (ev1 < mddev->bitmap->events_cleared) + return 0; + } else /* just a hot-add of a new device, leave raid_disk at -1 */ + return 0; + if (mddev->level != LEVEL_MULTIPATH) { - rdev->raid_disk = -1; - rdev->in_sync = rdev->faulty = 0; + rdev->faulty = 0; desc = sb->disks + rdev->desc_nr; if (desc->state & (1<in_sync = 1; rdev->raid_disk = desc->raid_disk; } - } + } else /* MULTIPATH are always insync */ + rdev->in_sync = 1; return 0; } @@ -683,6 +744,9 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev) sb->layout = mddev->layout; sb->chunk_size = mddev->chunk_size; + if (mddev->bitmap && mddev->bitmap_file == NULL) + sb->state |= (1<disks[0].state = (1<bdev->bd_inode->i_size >> 9; sb_offset -= 8*2; - sb_offset &= ~(4*2-1); + sb_offset &= ~(sector_t)(4*2-1); /* convert from sectors to K */ sb_offset /= 2; break; @@ -860,6 +924,8 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) { struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page); + rdev->raid_disk = -1; + rdev->in_sync = 0; if (mddev->raid_disks == 0) { mddev->major_version = 1; mddev->patch_version = 0; @@ -877,13 +943,30 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) memcpy(mddev->uuid, sb->set_uuid, 16); mddev->max_disks = (4096-256)/2; - } else { - __u64 ev1; - ev1 = le64_to_cpu(sb->events); + + if ((le32_to_cpu(sb->feature_map) & 1) && + mddev->bitmap_file == NULL ) { + if (mddev->level != 1) { + printk(KERN_WARNING "md: bitmaps only supported for raid1\n"); + return -EINVAL; + } + mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset); + } + } else if (mddev->pers == NULL) { + /* Insist of good event counter while assembling */ + __u64 ev1 = le64_to_cpu(sb->events); ++ev1; if (ev1 < mddev->events) return -EINVAL; - } + } else if (mddev->bitmap) { + /* If adding to array with a bitmap, then we can accept an + * older device, but not too old. + */ + __u64 ev1 = le64_to_cpu(sb->events); + if (ev1 < mddev->bitmap->events_cleared) + return 0; + } else /* just a hot-add of a new device, leave raid_disk at -1 */ + return 0; if (mddev->level != LEVEL_MULTIPATH) { int role; @@ -891,14 +974,10 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); switch(role) { case 0xffff: /* spare */ - rdev->in_sync = 0; rdev->faulty = 0; - rdev->raid_disk = -1; break; case 0xfffe: /* faulty */ - rdev->in_sync = 0; rdev->faulty = 1; - rdev->raid_disk = -1; break; default: rdev->in_sync = 1; @@ -906,7 +985,9 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) rdev->raid_disk = role; break; } - } + } else /* MULTIPATH are always insync */ + rdev->in_sync = 1; + return 0; } @@ -933,6 +1014,11 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) else sb->resync_offset = cpu_to_le64(0); + if (mddev->bitmap && mddev->bitmap_file == NULL) { + sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset); + sb->feature_map = cpu_to_le32(1); + } + max_dev = 0; ITERATE_RDEV(mddev,rdev2,tmp) if (rdev2->desc_nr+1 > max_dev) @@ -1196,8 +1282,11 @@ void md_print_devices(void) printk("md: * *\n"); printk("md: **********************************\n"); ITERATE_MDDEV(mddev,tmp) { - printk("%s: ", mdname(mddev)); + if (mddev->bitmap) + bitmap_print_sb(mddev->bitmap); + else + printk("%s: ", mdname(mddev)); ITERATE_RDEV(mddev,rdev,tmp2) printk("<%s>", bdevname(rdev->bdev,b)); printk("\n"); @@ -1210,30 +1299,6 @@ void md_print_devices(void) } -static int write_disk_sb(mdk_rdev_t * rdev) -{ - char b[BDEVNAME_SIZE]; - if (!rdev->sb_loaded) { - MD_BUG(); - return 1; - } - if (rdev->faulty) { - MD_BUG(); - return 1; - } - - dprintk(KERN_INFO "(write) %s's sb offset: %llu\n", - bdevname(rdev->bdev,b), - (unsigned long long)rdev->sb_offset); - - if (sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, WRITE)) - return 0; - - printk("md: write_disk_sb failed for device %s\n", - bdevname(rdev->bdev,b)); - return 1; -} - static void sync_sbs(mddev_t * mddev) { mdk_rdev_t *rdev; @@ -1248,12 +1313,14 @@ static void sync_sbs(mddev_t * mddev) static void md_update_sb(mddev_t * mddev) { - int err, count = 100; + int err; struct list_head *tmp; mdk_rdev_t *rdev; + int sync_req; - mddev->sb_dirty = 0; repeat: + spin_lock(&mddev->write_lock); + sync_req = mddev->in_sync; mddev->utime = get_seconds(); mddev->events ++; @@ -1266,20 +1333,26 @@ repeat: MD_BUG(); mddev->events --; } + mddev->sb_dirty = 2; sync_sbs(mddev); /* * do not write anything to disk if using * nonpersistent superblocks */ - if (!mddev->persistent) + if (!mddev->persistent) { + mddev->sb_dirty = 0; + spin_unlock(&mddev->write_lock); + wake_up(&mddev->sb_wait); return; + } + spin_unlock(&mddev->write_lock); dprintk(KERN_INFO "md: updating %s RAID superblock on device (in sync %d)\n", mdname(mddev),mddev->in_sync); - err = 0; + err = bitmap_update_sb(mddev->bitmap); ITERATE_RDEV(mddev,rdev,tmp) { char b[BDEVNAME_SIZE]; dprintk(KERN_INFO "md: "); @@ -1288,22 +1361,32 @@ repeat: dprintk("%s ", bdevname(rdev->bdev,b)); if (!rdev->faulty) { - err += write_disk_sb(rdev); + md_super_write(mddev,rdev, + rdev->sb_offset<<1, MD_SB_BYTES, + rdev->sb_page); + dprintk(KERN_INFO "(write) %s's sb offset: %llu\n", + bdevname(rdev->bdev,b), + (unsigned long long)rdev->sb_offset); + } else dprintk(")\n"); - if (!err && mddev->level == LEVEL_MULTIPATH) + if (mddev->level == LEVEL_MULTIPATH) /* only need to write one superblock... */ break; } - if (err) { - if (--count) { - printk(KERN_ERR "md: errors occurred during superblock" - " update, repeating\n"); - goto repeat; - } - printk(KERN_ERR \ - "md: excessive errors occurred during superblock update, exiting\n"); + wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0); + /* if there was a failure, sb_dirty was set to 1, and we re-write super */ + + spin_lock(&mddev->write_lock); + if (mddev->in_sync != sync_req|| mddev->sb_dirty == 1) { + /* have to write it out again */ + spin_unlock(&mddev->write_lock); + goto repeat; } + mddev->sb_dirty = 0; + spin_unlock(&mddev->write_lock); + wake_up(&mddev->sb_wait); + } /* @@ -1607,12 +1690,19 @@ static int do_md_run(mddev_t * mddev) mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */ - err = mddev->pers->run(mddev); + /* before we start the array running, initialise the bitmap */ + err = bitmap_create(mddev); + if (err) + printk(KERN_ERR "%s: failed to create bitmap (%d)\n", + mdname(mddev), err); + else + err = mddev->pers->run(mddev); if (err) { printk(KERN_ERR "md: pers->run() failed ...\n"); module_put(mddev->pers->owner); mddev->pers = NULL; - return -EINVAL; + bitmap_destroy(mddev); + return err; } atomic_set(&mddev->writes_pending,0); mddev->safemode = 0; @@ -1725,6 +1815,14 @@ static int do_md_stop(mddev_t * mddev, int ro) if (ro) set_disk_ro(disk, 1); } + + bitmap_destroy(mddev); + if (mddev->bitmap_file) { + atomic_set(&mddev->bitmap_file->f_dentry->d_inode->i_writecount, 1); + fput(mddev->bitmap_file); + mddev->bitmap_file = NULL; + } + /* * Free resources if final stop */ @@ -1983,6 +2081,42 @@ static int get_array_info(mddev_t * mddev, void __user * arg) return 0; } +static int get_bitmap_file(mddev_t * mddev, void * arg) +{ + mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */ + char *ptr, *buf = NULL; + int err = -ENOMEM; + + file = kmalloc(sizeof(*file), GFP_KERNEL); + if (!file) + goto out; + + /* bitmap disabled, zero the first byte and copy out */ + if (!mddev->bitmap || !mddev->bitmap->file) { + file->pathname[0] = '\0'; + goto copy_out; + } + + buf = kmalloc(sizeof(file->pathname), GFP_KERNEL); + if (!buf) + goto out; + + ptr = file_path(mddev->bitmap->file, buf, sizeof(file->pathname)); + if (!ptr) + goto out; + + strcpy(file->pathname, ptr); + +copy_out: + err = 0; + if (copy_to_user(arg, file, sizeof(*file))) + err = -EFAULT; +out: + kfree(buf); + kfree(file); + return err; +} + static int get_disk_info(mddev_t * mddev, void __user * arg) { mdu_disk_info_t info; @@ -2078,6 +2212,18 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) PTR_ERR(rdev)); return PTR_ERR(rdev); } + /* set save_raid_disk if appropriate */ + if (!mddev->persistent) { + if (info->state & (1<raid_disk < mddev->raid_disks) + rdev->raid_disk = info->raid_disk; + else + rdev->raid_disk = -1; + } else + super_types[mddev->major_version]. + validate_super(mddev, rdev); + rdev->saved_raid_disk = rdev->raid_disk; + rdev->in_sync = 0; /* just to be sure */ rdev->raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); @@ -2258,6 +2404,49 @@ abort_export: return err; } +/* similar to deny_write_access, but accounts for our holding a reference + * to the file ourselves */ +static int deny_bitmap_write_access(struct file * file) +{ + struct inode *inode = file->f_mapping->host; + + spin_lock(&inode->i_lock); + if (atomic_read(&inode->i_writecount) > 1) { + spin_unlock(&inode->i_lock); + return -ETXTBSY; + } + atomic_set(&inode->i_writecount, -1); + spin_unlock(&inode->i_lock); + + return 0; +} + +static int set_bitmap_file(mddev_t *mddev, int fd) +{ + int err; + + if (mddev->pers) + return -EBUSY; + + mddev->bitmap_file = fget(fd); + + if (mddev->bitmap_file == NULL) { + printk(KERN_ERR "%s: error: failed to get bitmap file\n", + mdname(mddev)); + return -EBADF; + } + + err = deny_bitmap_write_access(mddev->bitmap_file); + if (err) { + printk(KERN_ERR "%s: error: bitmap file is already in use\n", + mdname(mddev)); + fput(mddev->bitmap_file); + mddev->bitmap_file = NULL; + } else + mddev->bitmap_offset = 0; /* file overrides offset */ + return err; +} + /* * set_array_info is used two different ways * The original usage is when creating a new array. @@ -2569,8 +2758,10 @@ static int md_ioctl(struct inode *inode, struct file *file, /* * Commands querying/configuring an existing array: */ - /* if we are initialised yet, only ADD_NEW_DISK or STOP_ARRAY is allowed */ - if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY && cmd != RUN_ARRAY) { + /* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY, + * RUN_ARRAY, and SET_BITMAP_FILE are allowed */ + if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY + && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE) { err = -ENODEV; goto abort_unlock; } @@ -2584,6 +2775,10 @@ static int md_ioctl(struct inode *inode, struct file *file, err = get_array_info(mddev, argp); goto done_unlock; + case GET_BITMAP_FILE: + err = get_bitmap_file(mddev, (void *)arg); + goto done_unlock; + case GET_DISK_INFO: err = get_disk_info(mddev, argp); goto done_unlock; @@ -2664,6 +2859,10 @@ static int md_ioctl(struct inode *inode, struct file *file, err = do_md_run (mddev); goto done_unlock; + case SET_BITMAP_FILE: + err = set_bitmap_file(mddev, (int)arg); + goto done_unlock; + default: if (_IOC_TYPE(cmd) == MD_MAJOR) printk(KERN_WARNING "md: %s(pid %d) used" @@ -2775,10 +2974,10 @@ static int md_thread(void * arg) while (thread->run) { void (*run)(mddev_t *); - wait_event_interruptible(thread->wqueue, - test_bit(THREAD_WAKEUP, &thread->flags)); - if (current->flags & PF_FREEZE) - refrigerator(PF_FREEZE); + wait_event_interruptible_timeout(thread->wqueue, + test_bit(THREAD_WAKEUP, &thread->flags), + thread->timeout); + try_to_freeze(); clear_bit(THREAD_WAKEUP, &thread->flags); @@ -2822,6 +3021,7 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev, thread->run = run; thread->mddev = mddev; thread->name = name; + thread->timeout = MAX_SCHEDULE_TIMEOUT; ret = kernel_thread(md_thread, thread, 0); if (ret < 0) { kfree(thread); @@ -2860,13 +3060,13 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev) if (!rdev || rdev->faulty) return; - +/* dprintk("md_error dev:%s, rdev:(%d:%d), (caller: %p,%p,%p,%p).\n", mdname(mddev), MAJOR(rdev->bdev->bd_dev), MINOR(rdev->bdev->bd_dev), __builtin_return_address(0),__builtin_return_address(1), __builtin_return_address(2),__builtin_return_address(3)); - +*/ if (!mddev->pers->error_handler) return; mddev->pers->error_handler(mddev,rdev); @@ -3020,6 +3220,7 @@ static int md_seq_show(struct seq_file *seq, void *v) struct list_head *tmp2; mdk_rdev_t *rdev; int i; + struct bitmap *bitmap; if (v == (void*)1) { seq_printf(seq, "Personalities : "); @@ -3072,10 +3273,35 @@ static int md_seq_show(struct seq_file *seq, void *v) if (mddev->pers) { mddev->pers->status (seq, mddev); seq_printf(seq, "\n "); - if (mddev->curr_resync > 2) + if (mddev->curr_resync > 2) { status_resync (seq, mddev); - else if (mddev->curr_resync == 1 || mddev->curr_resync == 2) - seq_printf(seq, " resync=DELAYED"); + seq_printf(seq, "\n "); + } else if (mddev->curr_resync == 1 || mddev->curr_resync == 2) + seq_printf(seq, " resync=DELAYED\n "); + } else + seq_printf(seq, "\n "); + + if ((bitmap = mddev->bitmap)) { + unsigned long chunk_kb; + unsigned long flags; + spin_lock_irqsave(&bitmap->lock, flags); + chunk_kb = bitmap->chunksize >> 10; + seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], " + "%lu%s chunk", + bitmap->pages - bitmap->missing_pages, + bitmap->pages, + (bitmap->pages - bitmap->missing_pages) + << (PAGE_SHIFT - 10), + chunk_kb ? chunk_kb : bitmap->chunksize, + chunk_kb ? "KB" : "B"); + if (bitmap->file) { + seq_printf(seq, ", file: "); + seq_path(seq, bitmap->file->f_vfsmnt, + bitmap->file->f_dentry," \t\n"); + } + + seq_printf(seq, "\n"); + spin_unlock_irqrestore(&bitmap->lock, flags); } seq_printf(seq, "\n"); @@ -3178,19 +3404,28 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok) } -void md_write_start(mddev_t *mddev) +/* md_write_start(mddev, bi) + * If we need to update some array metadata (e.g. 'active' flag + * in superblock) before writing, schedule a superblock update + * and wait for it to complete. + */ +void md_write_start(mddev_t *mddev, struct bio *bi) { - if (!atomic_read(&mddev->writes_pending)) { - mddev_lock_uninterruptible(mddev); + DEFINE_WAIT(w); + if (bio_data_dir(bi) != WRITE) + return; + + atomic_inc(&mddev->writes_pending); + if (mddev->in_sync) { + spin_lock(&mddev->write_lock); if (mddev->in_sync) { mddev->in_sync = 0; - del_timer(&mddev->safemode_timer); - md_update_sb(mddev); + mddev->sb_dirty = 1; + md_wakeup_thread(mddev->thread); } - atomic_inc(&mddev->writes_pending); - mddev_unlock(mddev); - } else - atomic_inc(&mddev->writes_pending); + spin_unlock(&mddev->write_lock); + } + wait_event(mddev->sb_wait, mddev->sb_dirty==0); } void md_write_end(mddev_t *mddev) @@ -3212,12 +3447,13 @@ static void md_do_sync(mddev_t *mddev) mddev_t *mddev2; unsigned int currspeed = 0, window; - sector_t max_sectors,j; + sector_t max_sectors,j, io_sectors; unsigned long mark[SYNC_MARKS]; sector_t mark_cnt[SYNC_MARKS]; int last_mark,m; struct list_head *tmp; sector_t last_check; + int skipped = 0; /* just incase thread restarts... */ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) @@ -3283,7 +3519,7 @@ static void md_do_sync(mddev_t *mddev) if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) /* resync follows the size requested by the personality, - * which default to physical size, but can be virtual size + * which defaults to physical size, but can be virtual size */ max_sectors = mddev->resync_max_sectors; else @@ -3298,13 +3534,15 @@ static void md_do_sync(mddev_t *mddev) sysctl_speed_limit_max); is_mddev_idle(mddev); /* this also initializes IO event counters */ - if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) + /* we don't use the checkpoint if there's a bitmap */ + if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap) j = mddev->recovery_cp; else j = 0; + io_sectors = 0; for (m = 0; m < SYNC_MARKS; m++) { mark[m] = jiffies; - mark_cnt[m] = j; + mark_cnt[m] = io_sectors; } last_mark = 0; mddev->resync_mark = mark[last_mark]; @@ -3329,21 +3567,29 @@ static void md_do_sync(mddev_t *mddev) } while (j < max_sectors) { - int sectors; + sector_t sectors; - sectors = mddev->pers->sync_request(mddev, j, currspeed < sysctl_speed_limit_min); - if (sectors < 0) { + skipped = 0; + sectors = mddev->pers->sync_request(mddev, j, &skipped, + currspeed < sysctl_speed_limit_min); + if (sectors == 0) { set_bit(MD_RECOVERY_ERR, &mddev->recovery); goto out; } - atomic_add(sectors, &mddev->recovery_active); + + if (!skipped) { /* actual IO requested */ + io_sectors += sectors; + atomic_add(sectors, &mddev->recovery_active); + } + j += sectors; if (j>1) mddev->curr_resync = j; - if (last_check + window > j || j == max_sectors) + + if (last_check + window > io_sectors || j == max_sectors) continue; - last_check = j; + last_check = io_sectors; if (test_bit(MD_RECOVERY_INTR, &mddev->recovery) || test_bit(MD_RECOVERY_ERR, &mddev->recovery)) @@ -3357,7 +3603,7 @@ static void md_do_sync(mddev_t *mddev) mddev->resync_mark = mark[next]; mddev->resync_mark_cnt = mark_cnt[next]; mark[next] = jiffies; - mark_cnt[next] = j - atomic_read(&mddev->recovery_active); + mark_cnt[next] = io_sectors - atomic_read(&mddev->recovery_active); last_mark = next; } @@ -3384,7 +3630,8 @@ static void md_do_sync(mddev_t *mddev) mddev->queue->unplug_fn(mddev->queue); cond_resched(); - currspeed = ((unsigned long)(j-mddev->resync_mark_cnt))/2/((jiffies-mddev->resync_mark)/HZ +1) +1; + currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2 + /((jiffies-mddev->resync_mark)/HZ +1) +1; if (currspeed > sysctl_speed_limit_min) { if ((currspeed > sysctl_speed_limit_max) || @@ -3404,7 +3651,7 @@ static void md_do_sync(mddev_t *mddev) wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ - mddev->pers->sync_request(mddev, max_sectors, 1); + mddev->pers->sync_request(mddev, max_sectors, &skipped, 1); if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) && mddev->curr_resync > 2 && @@ -3454,7 +3701,8 @@ void md_check_recovery(mddev_t *mddev) struct list_head *rtmp; - dprintk(KERN_INFO "md: recovery thread got woken up ...\n"); + if (mddev->bitmap) + bitmap_daemon_work(mddev->bitmap); if (mddev->ro) return; @@ -3481,6 +3729,7 @@ void md_check_recovery(mddev_t *mddev) if (mddev_trylock(mddev)==0) { int spares =0; + spin_lock(&mddev->write_lock); if (mddev->safemode && !atomic_read(&mddev->writes_pending) && !mddev->in_sync && mddev->recovery_cp == MaxSector) { mddev->in_sync = 1; @@ -3488,9 +3737,12 @@ void md_check_recovery(mddev_t *mddev) } if (mddev->safemode == 1) mddev->safemode = 0; + spin_unlock(&mddev->write_lock); if (mddev->sb_dirty) md_update_sb(mddev); + + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { /* resync/recovery still happening */ @@ -3508,6 +3760,14 @@ void md_check_recovery(mddev_t *mddev) mddev->pers->spare_active(mddev); } md_update_sb(mddev); + + /* if array is no-longer degraded, then any saved_raid_disk + * information must be scrapped + */ + if (!mddev->degraded) + ITERATE_RDEV(mddev,rdev,rtmp) + rdev->saved_raid_disk = -1; + mddev->recovery = 0; /* flag recovery needed just to double check */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); @@ -3550,6 +3810,13 @@ void md_check_recovery(mddev_t *mddev) set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); if (!spares) set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + if (spares && mddev->bitmap && ! mddev->bitmap->file) { + /* We are adding a device or devices to an array + * which has the bitmap stored on all devices. + * So make sure all bitmap pages get written + */ + bitmap_write_all(mddev->bitmap); + } mddev->sync_thread = md_register_thread(md_do_sync, mddev, "%s_resync"); @@ -3617,6 +3884,8 @@ static int __init md_init(void) " MD_SB_DISKS=%d\n", MD_MAJOR_VERSION, MD_MINOR_VERSION, MD_PATCHLEVEL_VERSION, MAX_MD_DEVS, MD_SB_DISKS); + printk(KERN_INFO "md: bitmap version %d.%d\n", BITMAP_MAJOR, + BITMAP_MINOR); if (register_blkdev(MAJOR_NR, "md")) return -1;