X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fbitmap.c;h=719943763391263c7a4ab98ad0201244ce1d3d62;hb=d15cfc3ac77388f1d588c57743d5f26b15eba9a8;hp=7c426d07a555c0426855571552289c6ed9fcaaaa;hpb=85bfb4da8cad483a4e550ec89060d05a4daf895b;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 7c426d0..7199437 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -203,48 +203,35 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) * bitmap file handling - read and write the bitmap file and its superblock */ -/* copy the pathname of a file to a buffer */ -char *file_path(struct file *file, char *buf, int count) -{ - struct dentry *d; - struct vfsmount *v; - - if (!buf) - return NULL; - - d = file->f_path.dentry; - v = file->f_path.mnt; - - buf = d_path(d, v, buf, count); - - return IS_ERR(buf) ? NULL : buf; -} - /* * basic page I/O operations */ /* IO operations when bitmap is stored near all superblocks */ -static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long index) +static struct page *read_sb_page(mddev_t *mddev, long offset, + struct page *page, + unsigned long index, int size) { /* choose a good rdev and read the page from there */ mdk_rdev_t *rdev; - struct list_head *tmp; - struct page *page = alloc_page(GFP_KERNEL); sector_t target; if (!page) + page = alloc_page(GFP_KERNEL); + if (!page) return ERR_PTR(-ENOMEM); - ITERATE_RDEV(mddev, rdev, tmp) { + list_for_each_entry(rdev, &mddev->disks, same_set) { if (! test_bit(In_sync, &rdev->flags) || test_bit(Faulty, &rdev->flags)) continue; - target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512); + target = rdev->sb_start + offset + index * (PAGE_SIZE/512); - if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) { + if (sync_page_io(rdev->bdev, target, + roundup(size, bdev_hardsect_size(rdev->bdev)), + page, READ)) { page->index = index; attach_page_buffers(page, NULL); /* so that free_buffer will * quietly no-op */ @@ -255,15 +242,47 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde } +static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev) +{ + /* Iterate the disks of an mddev, using rcu to protect access to the + * linked list, and raising the refcount of devices we return to ensure + * they don't disappear while in use. + * As devices are only added or removed when raid_disk is < 0 and + * nr_pending is 0 and In_sync is clear, the entries we return will + * still be in the same position on the list when we re-enter + * list_for_each_continue_rcu. + */ + struct list_head *pos; + rcu_read_lock(); + if (rdev == NULL) + /* start at the beginning */ + pos = &mddev->disks; + else { + /* release the previous rdev and start from there. */ + rdev_dec_pending(rdev, mddev); + pos = &rdev->same_set; + } + list_for_each_continue_rcu(pos, &mddev->disks) { + rdev = list_entry(pos, mdk_rdev_t, same_set); + if (rdev->raid_disk >= 0 && + test_bit(In_sync, &rdev->flags) && + !test_bit(Faulty, &rdev->flags)) { + /* this is a usable devices */ + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + return rdev; + } + } + rcu_read_unlock(); + return NULL; +} + static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) { - mdk_rdev_t *rdev; - struct list_head *tmp; + mdk_rdev_t *rdev = NULL; mddev_t *mddev = bitmap->mddev; - ITERATE_RDEV(mddev, rdev, tmp) - if (test_bit(In_sync, &rdev->flags) - && !test_bit(Faulty, &rdev->flags)) { + while ((rdev = next_active_rdev(rdev, mddev)) != NULL) { int size = PAGE_SIZE; if (page->index == bitmap->file_pages-1) size = roundup(bitmap->last_page_size, @@ -277,32 +296,36 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) + (long)(page->index * (PAGE_SIZE/512)) + size/512 > 0) /* bitmap runs in to metadata */ - return -EINVAL; + goto bad_alignment; if (rdev->data_offset + mddev->size*2 - > rdev->sb_offset*2 + bitmap->offset) + > rdev->sb_start + bitmap->offset) /* data runs in to bitmap */ - return -EINVAL; - } else if (rdev->sb_offset*2 < rdev->data_offset) { + goto bad_alignment; + } else if (rdev->sb_start < rdev->data_offset) { /* METADATA BITMAP DATA */ - if (rdev->sb_offset*2 + if (rdev->sb_start + bitmap->offset + page->index*(PAGE_SIZE/512) + size/512 > rdev->data_offset) /* bitmap runs in to data */ - return -EINVAL; + goto bad_alignment; } else { /* DATA METADATA BITMAP - no problems */ } md_super_write(mddev, rdev, - (rdev->sb_offset<<1) + bitmap->offset + rdev->sb_start + bitmap->offset + page->index * (PAGE_SIZE/512), size, page); - } + } if (wait) md_super_wait(mddev); return 0; + + bad_alignment: + rcu_read_unlock(); + return -EINVAL; } static void bitmap_file_kick(struct bitmap *bitmap); @@ -471,8 +494,11 @@ void bitmap_update_sb(struct bitmap *bitmap) spin_unlock_irqrestore(&bitmap->lock, flags); sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); sb->events = cpu_to_le64(bitmap->mddev->events); - if (!bitmap->mddev->degraded) - sb->events_cleared = cpu_to_le64(bitmap->mddev->events); + if (bitmap->mddev->events < bitmap->events_cleared) { + /* rocking back to read-only */ + bitmap->events_cleared = bitmap->mddev->events; + sb->events_cleared = cpu_to_le64(bitmap->events_cleared); + } kunmap_atomic(sb, KM_USER0); write_page(bitmap, bitmap->sb_page, 1); } @@ -522,7 +548,9 @@ static int bitmap_read_sb(struct bitmap *bitmap) bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes); } else { - bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0); + bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, + NULL, + 0, sizeof(bitmap_super_t)); } if (IS_ERR(bitmap->sb_page)) { err = PTR_ERR(bitmap->sb_page); @@ -727,11 +755,13 @@ static void bitmap_file_kick(struct bitmap *bitmap) if (bitmap->file) { path = kmalloc(PAGE_SIZE, GFP_KERNEL); if (path) - ptr = file_path(bitmap->file, path, PAGE_SIZE); + ptr = d_path(&bitmap->file->f_path, path, + PAGE_SIZE); + printk(KERN_ALERT "%s: kicking failed bitmap file %s from array!\n", - bmname(bitmap), ptr ? ptr : ""); + bmname(bitmap), IS_ERR(ptr) ? "" : ptr); kfree(path); } else @@ -933,11 +963,18 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) */ page = bitmap->sb_page; offset = sizeof(bitmap_super_t); + if (!file) + read_sb_page(bitmap->mddev, + bitmap->offset, + page, + index, count); } else if (file) { page = read_page(file, index, bitmap, count); offset = 0; } else { - page = read_sb_page(bitmap->mddev, bitmap->offset, index); + page = read_sb_page(bitmap->mddev, bitmap->offset, + NULL, + index, count); offset = 0; } if (IS_ERR(page)) { /* read error */ @@ -1051,8 +1088,14 @@ void bitmap_daemon_work(struct bitmap *bitmap) if (bitmap == NULL) return; if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ)) - return; + goto done; + bitmap->daemon_lastrun = jiffies; + if (bitmap->allclean) { + bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + return; + } + bitmap->allclean = 1; for (j = 0; j < bitmap->chunks; j++) { bitmap_counter_t *bmc; @@ -1074,8 +1117,10 @@ void bitmap_daemon_work(struct bitmap *bitmap) clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); - if (need_write) + if (need_write) { write_page(bitmap, page, 0); + bitmap->allclean = 0; + } continue; } @@ -1092,9 +1137,19 @@ void bitmap_daemon_work(struct bitmap *bitmap) } else spin_unlock_irqrestore(&bitmap->lock, flags); lastpage = page; -/* - printk("bitmap clean at page %lu\n", j); -*/ + + /* We are possibly going to clear some bits, so make + * sure that events_cleared is up-to-date. + */ + if (bitmap->need_sync) { + bitmap_super_t *sb; + bitmap->need_sync = 0; + sb = kmap_atomic(bitmap->sb_page, KM_USER0); + sb->events_cleared = + cpu_to_le64(bitmap->events_cleared); + kunmap_atomic(sb, KM_USER0); + write_page(bitmap, bitmap->sb_page, 1); + } spin_lock_irqsave(&bitmap->lock, flags); clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } @@ -1104,6 +1159,9 @@ void bitmap_daemon_work(struct bitmap *bitmap) /* if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc); */ + if (*bmc) + bitmap->allclean = 0; + if (*bmc == 2) { *bmc=1; /* maybe clear the bit next time */ set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); @@ -1138,6 +1196,9 @@ void bitmap_daemon_work(struct bitmap *bitmap) } } + done: + if (bitmap->allclean == 0) + bitmap->mddev->thread->timeout = bitmap->daemon_sleep * HZ; } static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap, @@ -1207,8 +1268,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect prepare_to_wait(&bitmap->overflow_wait, &__wait, TASK_UNINTERRUPTIBLE); spin_unlock_irq(&bitmap->lock); - bitmap->mddev->queue - ->unplug_fn(bitmap->mddev->queue); + blk_unplug(bitmap->mddev->queue); schedule(); finish_wait(&bitmap->overflow_wait, &__wait); continue; @@ -1218,7 +1278,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect case 0: bitmap_file_set_bit(bitmap, offset); bitmap_count_page(bitmap,offset, 1); - blk_plug_device(bitmap->mddev->queue); + blk_plug_device_unlocked(bitmap->mddev->queue); /* fall through */ case 1: *bmc = 2; @@ -1233,6 +1293,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect sectors -= blocks; else sectors = 0; } + bitmap->allclean = 0; return 0; } @@ -1258,6 +1319,12 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto return; } + if (success && + bitmap->events_cleared < bitmap->mddev->events) { + bitmap->events_cleared = bitmap->mddev->events; + bitmap->need_sync = 1; + } + if (!success && ! (*bmc & NEEDED_MASK)) *bmc |= NEEDED_MASK; @@ -1303,6 +1370,7 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, } } spin_unlock_irq(&bitmap->lock); + bitmap->allclean = 0; return rv; } @@ -1339,6 +1407,7 @@ void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int ab } unlock: spin_unlock_irqrestore(&bitmap->lock, flags); + bitmap->allclean = 0; } void bitmap_close_sync(struct bitmap *bitmap) @@ -1349,16 +1418,40 @@ void bitmap_close_sync(struct bitmap *bitmap) */ sector_t sector = 0; int blocks; - if (!bitmap) return; + if (!bitmap) + return; while (sector < bitmap->mddev->resync_max_sectors) { bitmap_end_sync(bitmap, sector, &blocks, 0); -/* - if (sector < 500) printk("bitmap_close_sync: sec %llu blks %d\n", - (unsigned long long)sector, blocks); -*/ sector += blocks; + sector += blocks; } } +void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector) +{ + sector_t s = 0; + int blocks; + + if (!bitmap) + return; + if (sector == 0) { + bitmap->last_end_sync = jiffies; + return; + } + if (time_before(jiffies, (bitmap->last_end_sync + + bitmap->daemon_sleep * HZ))) + return; + wait_event(bitmap->mddev->recovery_wait, + atomic_read(&bitmap->mddev->recovery_active) == 0); + + sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1); + s = 0; + while (s < sector && s < bitmap->mddev->resync_max_sectors) { + bitmap_end_sync(bitmap, s, &blocks, 0); + s += blocks; + } + bitmap->last_end_sync = jiffies; +} + static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed) { /* For each chunk covered by any of these sectors, set the @@ -1382,7 +1475,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } spin_unlock_irq(&bitmap->lock); - + bitmap->allclean = 0; } /* dirty the memory and file bits for bitmap chunks "s" to "e" */ @@ -1566,3 +1659,4 @@ EXPORT_SYMBOL(bitmap_start_sync); EXPORT_SYMBOL(bitmap_end_sync); EXPORT_SYMBOL(bitmap_unplug); EXPORT_SYMBOL(bitmap_close_sync); +EXPORT_SYMBOL(bitmap_cond_end_sync);