X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fbitmap.c;h=53e8bea295e2c64e615c98779fb48e50e5596156;hb=8018ab057480974e7f26a387bf4ce040e9a5f6f1;hp=220273e81ed6b2599b29dc031d4f7a87c486fb01;hpb=bd926c63b7a6843d3ce2728396c0891e54fce5c4;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 220273e..53e8bea 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -7,7 +7,6 @@ * additions, Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.: * - added disk storage for bitmap * - changes to allow various bitmap chunk sizes - * - added bitmap daemon (to asynchronously clear bitmap bits from disk) */ /* @@ -15,24 +14,21 @@ * * flush after percent set rather than just time based. (maybe both). * wait if count gets too high, wake when it drops to half. - * allow bitmap to be mirrored with superblock (before or after...) - * allow hot-add to re-instate a current device. - * allow hot-add of bitmap after quiessing device */ +#include #include #include #include #include -#include #include #include #include #include #include #include -#include -#include +#include "md.h" +#include "bitmap.h" /* debug macros */ @@ -73,34 +69,6 @@ static inline char * bmname(struct bitmap *bitmap) /* - * test if the bitmap is active - */ -int bitmap_active(struct bitmap *bitmap) -{ - unsigned long flags; - int res = 0; - - if (!bitmap) - return res; - spin_lock_irqsave(&bitmap->lock, flags); - res = bitmap->flags & BITMAP_ACTIVE; - spin_unlock_irqrestore(&bitmap->lock, flags); - return res; -} - -#define WRITE_POOL_SIZE 256 -/* mempool for queueing pending writes on the bitmap file */ -static void *write_pool_alloc(gfp_t gfp_flags, void *data) -{ - return kmalloc(sizeof(struct page_list), gfp_flags); -} - -static void write_pool_free(void *ptr, void *data) -{ - kfree(ptr); -} - -/* * just a placeholder - calls kmalloc for bitmap pages */ static unsigned char *bitmap_alloc_page(struct bitmap *bitmap) @@ -140,13 +108,16 @@ static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page) * allocated while we're using it */ static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create) +__releases(bitmap->lock) +__acquires(bitmap->lock) { unsigned char *mappage; if (page >= bitmap->pages) { - printk(KERN_ALERT - "%s: invalid bitmap page request: %lu (> %lu)\n", - bmname(bitmap), page, bitmap->pages-1); + /* This can happen if bitmap_start_sync goes beyond + * End-of-device while looking for a whole page. + * It is harmless. + */ return -EINVAL; } @@ -200,7 +171,7 @@ out: /* if page is completely empty, put it back on the free list, or dealloc it */ /* if page was hijacked, unmark the flag so it might get alloced next time */ /* Note: lock should be held when calling this */ -static inline void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) +static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) { char *ptr; @@ -236,49 +207,38 @@ static inline 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_dentry; - v = file->f_vfsmnt; - - 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, loff_t 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_logical_block_size(rdev->bdev)), + page, READ)) { page->index = index; + attach_page_buffers(page, NULL); /* so that free_buffer will + * quietly no-op */ return page; } } @@ -286,104 +246,241 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde } -static int write_sb_page(mddev_t *mddev, long offset, struct page *page, int wait) +static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev) { - mdk_rdev_t *rdev; - struct list_head *tmp; + /* 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(Faulty, &rdev->flags)) { + /* this is a usable devices */ + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + return rdev; + } + } + rcu_read_unlock(); + return NULL; +} - ITERATE_RDEV(mddev, rdev, tmp) - if (test_bit(In_sync, &rdev->flags) - && !test_bit(Faulty, &rdev->flags)) +static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) +{ + mdk_rdev_t *rdev = NULL; + mddev_t *mddev = bitmap->mddev; + + while ((rdev = next_active_rdev(rdev, mddev)) != NULL) { + int size = PAGE_SIZE; + loff_t offset = mddev->bitmap_info.offset; + if (page->index == bitmap->file_pages-1) + size = roundup(bitmap->last_page_size, + bdev_logical_block_size(rdev->bdev)); + /* Just make sure we aren't corrupting data or + * metadata + */ + if (mddev->external) { + /* Bitmap could be anywhere. */ + if (rdev->sb_start + offset + (page->index *(PAGE_SIZE/512)) > + rdev->data_offset && + rdev->sb_start + offset < + rdev->data_offset + mddev->dev_sectors + + (PAGE_SIZE/512)) + goto bad_alignment; + } else if (offset < 0) { + /* DATA BITMAP METADATA */ + if (offset + + (long)(page->index * (PAGE_SIZE/512)) + + size/512 > 0) + /* bitmap runs in to metadata */ + goto bad_alignment; + if (rdev->data_offset + mddev->dev_sectors + > rdev->sb_start + offset) + /* data runs in to bitmap */ + goto bad_alignment; + } else if (rdev->sb_start < rdev->data_offset) { + /* METADATA BITMAP DATA */ + if (rdev->sb_start + + offset + + page->index*(PAGE_SIZE/512) + size/512 + > rdev->data_offset) + /* bitmap runs in to data */ + goto bad_alignment; + } else { + /* DATA METADATA BITMAP - no problems */ + } md_super_write(mddev, rdev, - (rdev->sb_offset<<1) + offset + rdev->sb_start + offset + page->index * (PAGE_SIZE/512), - PAGE_SIZE, + size, page); + } if (wait) - wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0); + md_super_wait(mddev); return 0; + + bad_alignment: + return -EINVAL; } +static void bitmap_file_kick(struct bitmap *bitmap); /* * write out a page to a file */ -static int write_page(struct bitmap *bitmap, struct page *page, int wait) +static void write_page(struct bitmap *bitmap, struct page *page, int wait) { - int ret = -ENOMEM; + struct buffer_head *bh; - if (bitmap->file == NULL) - return write_sb_page(bitmap->mddev, bitmap->offset, page, wait); + if (bitmap->file == NULL) { + switch (write_sb_page(bitmap, page, wait)) { + case -EINVAL: + bitmap->flags |= BITMAP_WRITE_ERROR; + } + } else { - if (wait) - lock_page(page); - else { - if (TestSetPageLocked(page)) - return -EAGAIN; /* already locked */ - if (PageWriteback(page)) { - unlock_page(page); - return -EAGAIN; + bh = page_buffers(page); + + while (bh && bh->b_blocknr) { + atomic_inc(&bitmap->pending_writes); + set_buffer_locked(bh); + set_buffer_mapped(bh); + submit_bh(WRITE, bh); + bh = bh->b_this_page; + } + + if (wait) { + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); } } + if (bitmap->flags & BITMAP_WRITE_ERROR) + bitmap_file_kick(bitmap); +} + +static void end_bitmap_write(struct buffer_head *bh, int uptodate) +{ + struct bitmap *bitmap = bh->b_private; + unsigned long flags; - ret = page->mapping->a_ops->prepare_write(NULL, page, 0, PAGE_SIZE); - if (!ret) - ret = page->mapping->a_ops->commit_write(NULL, page, 0, - PAGE_SIZE); - if (ret) { - unlock_page(page); - return ret; + if (!uptodate) { + spin_lock_irqsave(&bitmap->lock, flags); + bitmap->flags |= BITMAP_WRITE_ERROR; + spin_unlock_irqrestore(&bitmap->lock, flags); } + if (atomic_dec_and_test(&bitmap->pending_writes)) + wake_up(&bitmap->write_wait); +} + +/* copied from buffer.c */ +static void +__clear_page_buffers(struct page *page) +{ + ClearPagePrivate(page); + set_page_private(page, 0); + page_cache_release(page); +} +static void free_buffers(struct page *page) +{ + struct buffer_head *bh = page_buffers(page); - set_page_dirty(page); /* force it to be written out */ - - if (!wait) { - /* add to list to be waited for by daemon */ - struct page_list *item = mempool_alloc(bitmap->write_pool, GFP_NOIO); - item->page = page; - page_cache_get(page); - spin_lock(&bitmap->write_lock); - list_add(&item->list, &bitmap->complete_pages); - spin_unlock(&bitmap->write_lock); - md_wakeup_thread(bitmap->writeback_daemon); + while (bh) { + struct buffer_head *next = bh->b_this_page; + free_buffer_head(bh); + bh = next; } - return write_one_page(page, wait); + __clear_page_buffers(page); + put_page(page); } -/* read a page from a file, pinning it into cache, and return bytes_read */ +/* read a page from a file. + * We both read the page, and attach buffers to the page to record the + * address of each block (using bmap). These addresses will be used + * to write the block later, completely bypassing the filesystem. + * This usage is similar to how swap files are handled, and allows us + * to write to a file with no concerns of memory allocation failing. + */ static struct page *read_page(struct file *file, unsigned long index, - unsigned long *bytes_read) + struct bitmap *bitmap, + unsigned long count) { - struct inode *inode = file->f_mapping->host; struct page *page = NULL; - loff_t isize = i_size_read(inode); - unsigned long end_index = isize >> PAGE_CACHE_SHIFT; + struct inode *inode = file->f_path.dentry->d_inode; + struct buffer_head *bh; + sector_t block; - PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_CACHE_SIZE, - (unsigned long long)index << PAGE_CACHE_SHIFT); + PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE, + (unsigned long long)index << PAGE_SHIFT); - page = read_cache_page(inode->i_mapping, index, - (filler_t *)inode->i_mapping->a_ops->readpage, file); + page = alloc_page(GFP_KERNEL); + if (!page) + page = ERR_PTR(-ENOMEM); if (IS_ERR(page)) goto out; - wait_on_page_locked(page); - if (!PageUptodate(page) || PageError(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); + + bh = alloc_page_buffers(page, 1<i_blkbits, 0); + if (!bh) { + put_page(page); + page = ERR_PTR(-ENOMEM); goto out; } + attach_page_buffers(page, bh); + block = index << (PAGE_SHIFT - inode->i_blkbits); + while (bh) { + if (count == 0) + bh->b_blocknr = 0; + else { + bh->b_blocknr = bmap(inode, block); + if (bh->b_blocknr == 0) { + /* Cannot use this file! */ + free_buffers(page); + page = ERR_PTR(-EINVAL); + goto out; + } + bh->b_bdev = inode->i_sb->s_bdev; + if (count < (1<i_blkbits)) + count = 0; + else + count -= (1<i_blkbits); + + bh->b_end_io = end_bitmap_write; + bh->b_private = bitmap; + atomic_inc(&bitmap->pending_writes); + set_buffer_locked(bh); + set_buffer_mapped(bh); + submit_bh(READ, bh); + } + block++; + bh = bh->b_this_page; + } + page->index = index; - if (index > end_index) /* we have read beyond EOF */ - *bytes_read = 0; - else if (index == end_index) /* possible short read */ - *bytes_read = isize & ~PAGE_CACHE_MASK; - else - *bytes_read = PAGE_CACHE_SIZE; /* got a full page */ + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + if (bitmap->flags & BITMAP_WRITE_ERROR) { + free_buffers(page); + page = ERR_PTR(-EIO); + } out: if (IS_ERR(page)) printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n", - (int)PAGE_CACHE_SIZE, - (unsigned long long)index << PAGE_CACHE_SHIFT, + (int)PAGE_SIZE, + (unsigned long long)index << PAGE_SHIFT, PTR_ERR(page)); return page; } @@ -393,25 +490,33 @@ out: */ /* update the event counter and sync the superblock to disk */ -int bitmap_update_sb(struct bitmap *bitmap) +void bitmap_update_sb(struct bitmap *bitmap) { bitmap_super_t *sb; unsigned long flags; if (!bitmap || !bitmap->mddev) /* no bitmap for this array */ - return 0; + return; + if (bitmap->mddev->bitmap_info.external) + return; spin_lock_irqsave(&bitmap->lock, flags); if (!bitmap->sb_page) { /* no superblock */ spin_unlock_irqrestore(&bitmap->lock, flags); - return 0; + return; } spin_unlock_irqrestore(&bitmap->lock, flags); - sb = (bitmap_super_t *)kmap(bitmap->sb_page); + 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); - kunmap(bitmap->sb_page); - return write_page(bitmap, bitmap->sb_page, 1); + 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); + } + /* Just in case these have been changed via sysfs: */ + sb->daemon_sleep = cpu_to_le32(bitmap->mddev->bitmap_info.daemon_sleep/HZ); + sb->write_behind = cpu_to_le32(bitmap->mddev->bitmap_info.max_write_behind); + kunmap_atomic(sb, KM_USER0); + write_page(bitmap, bitmap->sb_page, 1); } /* print out the bitmap file superblock */ @@ -421,7 +526,7 @@ void bitmap_print_sb(struct bitmap *bitmap) if (!bitmap || !bitmap->sb_page) return; - sb = (bitmap_super_t *)kmap(bitmap->sb_page); + sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap)); printk(KERN_DEBUG " magic: %08x\n", le32_to_cpu(sb->magic)); printk(KERN_DEBUG " version: %d\n", le32_to_cpu(sb->version)); @@ -440,7 +545,7 @@ void bitmap_print_sb(struct bitmap *bitmap) printk(KERN_DEBUG " sync size: %llu KB\n", (unsigned long long)le64_to_cpu(sb->sync_size)/2); printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind)); - kunmap(bitmap->sb_page); + kunmap_atomic(sb, KM_USER0); } /* read the superblock from the bitmap file and initialize some bitmap fields */ @@ -449,16 +554,20 @@ static int bitmap_read_sb(struct bitmap *bitmap) char *reason = NULL; bitmap_super_t *sb; unsigned long chunksize, daemon_sleep, write_behind; - unsigned long bytes_read; unsigned long long events; int err = -EINVAL; /* page 0 is the superblock, read it... */ - if (bitmap->file) - bitmap->sb_page = read_page(bitmap->file, 0, &bytes_read); - else { - bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0); - bytes_read = PAGE_SIZE; + if (bitmap->file) { + loff_t isize = i_size_read(bitmap->file->f_mapping->host); + int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize; + + bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes); + } else { + bitmap->sb_page = read_sb_page(bitmap->mddev, + bitmap->mddev->bitmap_info.offset, + NULL, + 0, sizeof(bitmap_super_t)); } if (IS_ERR(bitmap->sb_page)) { err = PTR_ERR(bitmap->sb_page); @@ -466,17 +575,10 @@ static int bitmap_read_sb(struct bitmap *bitmap) return err; } - sb = (bitmap_super_t *)kmap(bitmap->sb_page); - - if (bytes_read < sizeof(*sb)) { /* short read */ - printk(KERN_INFO "%s: bitmap file superblock truncated\n", - bmname(bitmap)); - err = -ENOSPC; - goto out; - } + sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); chunksize = le32_to_cpu(sb->chunksize); - daemon_sleep = le32_to_cpu(sb->daemon_sleep); + daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; write_behind = le32_to_cpu(sb->write_behind); /* verify that the bitmap-specific fields are valid */ @@ -485,12 +587,12 @@ static int bitmap_read_sb(struct bitmap *bitmap) else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO || le32_to_cpu(sb->version) > BITMAP_MAJOR_HI) reason = "unrecognized superblock version"; - else if (chunksize < 512 || chunksize > (1024 * 1024 * 4)) - reason = "bitmap chunksize out of range (512B - 4MB)"; + else if (chunksize < 512) + reason = "bitmap chunksize too small"; else if ((1 << ffz(~chunksize)) != chunksize) reason = "bitmap chunksize not a power of 2"; - else if (daemon_sleep < 1 || daemon_sleep > 15) - reason = "daemon sleep period out of range (1-15s)"; + else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT) + reason = "daemon sleep period out of range"; else if (write_behind > COUNTER_MAX) reason = "write-behind limit out of range (0 - 16383)"; if (reason) { @@ -519,23 +621,22 @@ static int bitmap_read_sb(struct bitmap *bitmap) printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) " "-- forcing full recovery\n", bmname(bitmap), events, (unsigned long long) bitmap->mddev->events); - sb->state |= BITMAP_STALE; + sb->state |= cpu_to_le32(BITMAP_STALE); } success: /* assign fields using values from superblock */ - bitmap->chunksize = chunksize; - bitmap->daemon_sleep = daemon_sleep; - bitmap->daemon_lastrun = jiffies; - bitmap->max_write_behind = write_behind; - bitmap->flags |= sb->state; + bitmap->mddev->bitmap_info.chunksize = chunksize; + bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; + bitmap->mddev->bitmap_info.max_write_behind = write_behind; + bitmap->flags |= le32_to_cpu(sb->state); if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN) bitmap->flags |= BITMAP_HOSTENDIAN; bitmap->events_cleared = le64_to_cpu(sb->events_cleared); - if (sb->state & BITMAP_STALE) + if (sb->state & cpu_to_le32(BITMAP_STALE)) bitmap->events_cleared = bitmap->mddev->events; err = 0; out: - kunmap(bitmap->sb_page); + kunmap_atomic(sb, KM_USER0); if (err) bitmap_print_sb(bitmap); return err; @@ -546,46 +647,57 @@ enum bitmap_mask_op { MASK_UNSET }; -/* record the state of the bitmap in the superblock */ -static void bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits, - enum bitmap_mask_op op) +/* record the state of the bitmap in the superblock. Return the old value */ +static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits, + enum bitmap_mask_op op) { bitmap_super_t *sb; unsigned long flags; + int old; spin_lock_irqsave(&bitmap->lock, flags); - if (!bitmap || !bitmap->sb_page) { /* can't set the state */ + if (!bitmap->sb_page) { /* can't set the state */ spin_unlock_irqrestore(&bitmap->lock, flags); - return; + return 0; } - page_cache_get(bitmap->sb_page); spin_unlock_irqrestore(&bitmap->lock, flags); - sb = (bitmap_super_t *)kmap(bitmap->sb_page); + sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); + old = le32_to_cpu(sb->state) & bits; switch (op) { - case MASK_SET: sb->state |= bits; + case MASK_SET: sb->state |= cpu_to_le32(bits); break; - case MASK_UNSET: sb->state &= ~bits; + case MASK_UNSET: sb->state &= cpu_to_le32(~bits); break; default: BUG(); } - kunmap(bitmap->sb_page); - page_cache_release(bitmap->sb_page); + kunmap_atomic(sb, KM_USER0); + return old; } /* * general bitmap file operations */ +/* + * on-disk bitmap: + * + * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap + * file a page at a time. There's a superblock at the start of the file. + */ /* calculate the index of the page that contains this bit */ -static inline unsigned long file_page_index(unsigned long chunk) +static inline unsigned long file_page_index(struct bitmap *bitmap, unsigned long chunk) { - return CHUNK_BIT_OFFSET(chunk) >> PAGE_BIT_SHIFT; + if (!bitmap->mddev->bitmap_info.external) + chunk += sizeof(bitmap_super_t) << 3; + return chunk >> PAGE_BIT_SHIFT; } /* calculate the (bit) offset of this bit within a page */ -static inline unsigned long file_page_offset(unsigned long chunk) +static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned long chunk) { - return CHUNK_BIT_OFFSET(chunk) & (PAGE_BITS - 1); + if (!bitmap->mddev->bitmap_info.external) + chunk += sizeof(bitmap_super_t) << 3; + return chunk & (PAGE_BITS - 1); } /* @@ -598,7 +710,9 @@ static inline unsigned long file_page_offset(unsigned long chunk) static inline struct page *filemap_get_page(struct bitmap *bitmap, unsigned long chunk) { - return bitmap->filemap[file_page_index(chunk) - file_page_index(0)]; + if (file_page_index(bitmap, chunk) >= bitmap->file_pages) return NULL; + return bitmap->filemap[file_page_index(bitmap, chunk) + - file_page_index(bitmap, 0)]; } @@ -621,50 +735,18 @@ static void bitmap_file_unmap(struct bitmap *bitmap) spin_unlock_irqrestore(&bitmap->lock, flags); while (pages--) - if (map[pages]->index != 0) /* 0 is sb_page, release it below */ - page_cache_release(map[pages]); + if (map[pages] != sb_page) /* 0 is sb_page, release it below */ + free_buffers(map[pages]); kfree(map); kfree(attr); if (sb_page) - page_cache_release(sb_page); -} - -static void bitmap_stop_daemon(struct bitmap *bitmap); - -/* dequeue the next item in a page list -- don't call from irq context */ -static struct page_list *dequeue_page(struct bitmap *bitmap) -{ - struct page_list *item = NULL; - struct list_head *head = &bitmap->complete_pages; - - spin_lock(&bitmap->write_lock); - if (list_empty(head)) - goto out; - item = list_entry(head->prev, struct page_list, list); - list_del(head->prev); -out: - spin_unlock(&bitmap->write_lock); - return item; -} - -static void drain_write_queues(struct bitmap *bitmap) -{ - struct page_list *item; - - while ((item = dequeue_page(bitmap))) { - /* don't bother to wait */ - page_cache_release(item->page); - mempool_free(item, bitmap->write_pool); - } - - wake_up(&bitmap->write_wait); + free_buffers(sb_page); } static void bitmap_file_put(struct bitmap *bitmap) { struct file *file; - struct inode *inode; unsigned long flags; spin_lock_irqsave(&bitmap->lock, flags); @@ -672,17 +754,14 @@ static void bitmap_file_put(struct bitmap *bitmap) bitmap->file = NULL; spin_unlock_irqrestore(&bitmap->lock, flags); - bitmap_stop_daemon(bitmap); - - drain_write_queues(bitmap); - + if (file) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); bitmap_file_unmap(bitmap); if (file) { - inode = file->f_mapping->host; - spin_lock(&inode->i_lock); - atomic_set(&inode->i_writecount, 1); /* allow writes again */ - spin_unlock(&inode->i_lock); + struct inode *inode = file->f_path.dentry->d_inode; + invalidate_mapping_pages(inode->i_mapping, 0, -1); fput(file); } } @@ -697,18 +776,25 @@ static void bitmap_file_kick(struct bitmap *bitmap) { char *path, *ptr = NULL; - bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET); - bitmap_update_sb(bitmap); + if (bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET) == 0) { + bitmap_update_sb(bitmap); - if (bitmap->file) { - path = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (path) - ptr = file_path(bitmap->file, path, PAGE_SIZE); + if (bitmap->file) { + path = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (path) + 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 : ""); - kfree(path); + printk(KERN_ALERT + "%s: kicking failed bitmap file %s from array!\n", + bmname(bitmap), IS_ERR(ptr) ? "" : ptr); + + kfree(path); + } else + printk(KERN_ALERT + "%s: disabling internal bitmap due to errors\n", + bmname(bitmap)); } bitmap_file_put(bitmap); @@ -717,26 +803,27 @@ static void bitmap_file_kick(struct bitmap *bitmap) } enum bitmap_page_attr { - BITMAP_PAGE_DIRTY = 1, // there are set bits that need to be synced - BITMAP_PAGE_CLEAN = 2, // there are bits that might need to be cleared - BITMAP_PAGE_NEEDWRITE=4, // there are cleared bits that need to be synced + BITMAP_PAGE_DIRTY = 0, // there are set bits that need to be synced + BITMAP_PAGE_CLEAN = 1, // there are bits that might need to be cleared + BITMAP_PAGE_NEEDWRITE=2, // there are cleared bits that need to be synced }; static inline void set_page_attr(struct bitmap *bitmap, struct page *page, enum bitmap_page_attr attr) { - bitmap->filemap_attr[page->index] |= attr; + __set_bit((page->index<<2) + attr, bitmap->filemap_attr); } static inline void clear_page_attr(struct bitmap *bitmap, struct page *page, enum bitmap_page_attr attr) { - bitmap->filemap_attr[page->index] &= ~attr; + __clear_bit((page->index<<2) + attr, bitmap->filemap_attr); } -static inline unsigned long get_page_attr(struct bitmap *bitmap, struct page *page) +static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page, + enum bitmap_page_attr attr) { - return bitmap->filemap_attr[page->index]; + return test_bit((page->index<<2) + attr, bitmap->filemap_attr); } /* @@ -758,12 +845,8 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) } page = filemap_get_page(bitmap, chunk); - bit = file_page_offset(chunk); - - - /* make sure the page stays cached until it gets written out */ - if (! (get_page_attr(bitmap, page) & BITMAP_PAGE_DIRTY)) - page_cache_get(page); + if (!page) return; + bit = file_page_offset(bitmap, chunk); /* set the bit */ kaddr = kmap_atomic(page, KM_USER0); @@ -782,15 +865,15 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) /* this gets called when the md device is ready to unplug its underlying * (slave) device queues -- before we let any writes go down, we need to * sync the dirty pages of the bitmap file to disk */ -int bitmap_unplug(struct bitmap *bitmap) +void bitmap_unplug(struct bitmap *bitmap) { - unsigned long i, attr, flags; + unsigned long i, flags; + int dirty, need_write; struct page *page; int wait = 0; - int err; if (!bitmap) - return 0; + return; /* look at each page to see if there are any set bits that need to be * flushed out to disk */ @@ -798,40 +881,29 @@ int bitmap_unplug(struct bitmap *bitmap) spin_lock_irqsave(&bitmap->lock, flags); if (!bitmap->filemap) { spin_unlock_irqrestore(&bitmap->lock, flags); - return 0; + return; } page = bitmap->filemap[i]; - attr = get_page_attr(bitmap, page); + dirty = test_page_attr(bitmap, page, BITMAP_PAGE_DIRTY); + need_write = test_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); clear_page_attr(bitmap, page, BITMAP_PAGE_DIRTY); clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); - if ((attr & BITMAP_PAGE_DIRTY)) + if (dirty) wait = 1; spin_unlock_irqrestore(&bitmap->lock, flags); - if (attr & (BITMAP_PAGE_DIRTY | BITMAP_PAGE_NEEDWRITE)) { - err = write_page(bitmap, page, 0); - if (err == -EAGAIN) { - if (attr & BITMAP_PAGE_DIRTY) - err = write_page(bitmap, page, 1); - else - err = 0; - } - if (err) - return 1; - } + if (dirty | need_write) + write_page(bitmap, page, 0); } if (wait) { /* if any writes were performed, we need to wait on them */ - if (bitmap->file) { - spin_lock_irq(&bitmap->write_lock); - wait_event_lock_irq(bitmap->write_wait, - list_empty(&bitmap->complete_pages), bitmap->write_lock, - wake_up_process(bitmap->writeback_daemon->tsk)); - spin_unlock_irq(&bitmap->write_lock); - } else - wait_event(bitmap->mddev->sb_wait, - atomic_read(&bitmap->mddev->pending_writes)==0); + if (bitmap->file) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + else + md_super_wait(bitmap->mddev); } - return 0; + if (bitmap->flags & BITMAP_WRITE_ERROR) + bitmap_file_kick(bitmap); } static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed); @@ -852,14 +924,15 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) struct page *page = NULL, *oldpage = NULL; unsigned long num_pages, bit_cnt = 0; struct file *file; - unsigned long bytes, offset, dummy; + unsigned long bytes, offset; int outofdate; int ret = -ENOSPC; + void *paddr; chunks = bitmap->chunks; file = bitmap->file; - BUG_ON(!file && !bitmap->offset); + BUG_ON(!file && !bitmap->mddev->bitmap_info.offset); #ifdef INJECT_FAULTS_3 outofdate = 1; @@ -871,40 +944,47 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) "recovery\n", bmname(bitmap)); bytes = (chunks + 7) / 8; + if (!bitmap->mddev->bitmap_info.external) + bytes += sizeof(bitmap_super_t); - num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE; + + num_pages = (bytes + PAGE_SIZE - 1) / PAGE_SIZE; - if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) { + if (file && i_size_read(file->f_mapping->host) < bytes) { printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n", bmname(bitmap), (unsigned long) i_size_read(file->f_mapping->host), - bytes + sizeof(bitmap_super_t)); - goto out; + bytes); + goto err; } ret = -ENOMEM; bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL); if (!bitmap->filemap) - goto out; + goto err; - bitmap->filemap_attr = kmalloc(sizeof(long) * num_pages, GFP_KERNEL); + /* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */ + bitmap->filemap_attr = kzalloc( + roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)), + GFP_KERNEL); if (!bitmap->filemap_attr) - goto out; - - memset(bitmap->filemap_attr, 0, sizeof(long) * num_pages); + goto err; oldindex = ~0L; for (i = 0; i < chunks; i++) { int b; - index = file_page_index(i); - bit = file_page_offset(i); + index = file_page_index(bitmap, i); + bit = file_page_offset(bitmap, i); if (index != oldindex) { /* this is a new page, read it in */ + int count; /* unmap the old page, we're done with it */ - if (oldpage != NULL) - kunmap(oldpage); - if (index == 0) { + if (index == num_pages-1) + count = bytes - index * PAGE_SIZE; + else + count = PAGE_SIZE; + if (index == 0 && bitmap->sb_page) { /* * if we're here then the superblock page * contains some bits (PAGE_SIZE != sizeof sb) @@ -912,49 +992,61 @@ 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->mddev->bitmap_info.offset, + page, + index, count); } else if (file) { - page = read_page(file, index, &dummy); + 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->mddev->bitmap_info.offset, + NULL, + index, count); offset = 0; } if (IS_ERR(page)) { /* read error */ ret = PTR_ERR(page); - goto out; + goto err; } oldindex = index; oldpage = page; - kmap(page); + + bitmap->filemap[bitmap->file_pages++] = page; + bitmap->last_page_size = count; if (outofdate) { /* * if bitmap is out of date, dirty the * whole page and write it out */ - memset(page_address(page) + offset, 0xff, + paddr = kmap_atomic(page, KM_USER0); + memset(paddr + offset, 0xff, PAGE_SIZE - offset); - ret = write_page(bitmap, page, 1); - if (ret) { - kunmap(page); - /* release, page not in filemap yet */ - page_cache_release(page); - goto out; - } - } + kunmap_atomic(paddr, KM_USER0); + write_page(bitmap, page, 1); - bitmap->filemap[bitmap->file_pages++] = page; + ret = -EIO; + if (bitmap->flags & BITMAP_WRITE_ERROR) + goto err; + } } + paddr = kmap_atomic(page, KM_USER0); if (bitmap->flags & BITMAP_HOSTENDIAN) - b = test_bit(bit, page_address(page)); + b = test_bit(bit, paddr); else - b = ext2_test_bit(bit, page_address(page)); + b = ext2_test_bit(bit, paddr); + kunmap_atomic(paddr, KM_USER0); if (b) { /* if the disk bit is set, set the memory bit */ - bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap), - ((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start) - ); + int needed = ((sector_t)(i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) + >= start); + bitmap_set_memory_bits(bitmap, + (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap), + needed); bit_cnt++; set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } @@ -964,19 +1056,20 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) ret = 0; bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET); - if (page) /* unmap the last page */ - kunmap(page); - if (bit_cnt) { /* Kick recovery if any bits were set */ set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery); md_wakeup_thread(bitmap->mddev->thread); } -out: printk(KERN_INFO "%s: bitmap initialized from disk: " - "read %lu/%lu pages, set %lu bits, status: %d\n", - bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, ret); + "read %lu/%lu pages, set %lu bits\n", + bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt); + return 0; + + err: + printk(KERN_INFO "%s: bitmap initialisation failed: %d\n", + bmname(bitmap), ret); return ret; } @@ -985,12 +1078,11 @@ void bitmap_write_all(struct bitmap *bitmap) /* We don't actually write all bitmap blocks here, * just flag them as needing to be written */ + int i; - unsigned long chunks = bitmap->chunks; - unsigned long bytes = (chunks+7)/8 + sizeof(bitmap_super_t); - unsigned long num_pages = (bytes + PAGE_SIZE-1) / PAGE_SIZE; - while (num_pages--) - bitmap->filemap_attr[num_pages] |= BITMAP_PAGE_NEEDWRITE; + for (i=0; i < bitmap->file_pages; i++) + set_page_attr(bitmap, bitmap->filemap[i], + BITMAP_PAGE_NEEDWRITE); } @@ -1014,241 +1106,153 @@ static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap, * out to disk */ -int bitmap_daemon_work(struct bitmap *bitmap) +void bitmap_daemon_work(mddev_t *mddev) { + struct bitmap *bitmap; unsigned long j; unsigned long flags; struct page *page = NULL, *lastpage = NULL; - int err = 0; int blocks; - int attr; + void *paddr; + + /* Use a mutex to guard daemon_work against + * bitmap_destroy. + */ + mutex_lock(&mddev->bitmap_info.mutex); + bitmap = mddev->bitmap; + if (bitmap == NULL) { + mutex_unlock(&mddev->bitmap_info.mutex); + return; + } + if (time_before(jiffies, bitmap->daemon_lastrun + + bitmap->mddev->bitmap_info.daemon_sleep)) + goto done; - if (bitmap == NULL) - return 0; - if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ)) - return 0; bitmap->daemon_lastrun = jiffies; + if (bitmap->allclean) { + bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + goto done; + } + bitmap->allclean = 1; + spin_lock_irqsave(&bitmap->lock, flags); for (j = 0; j < bitmap->chunks; j++) { bitmap_counter_t *bmc; - spin_lock_irqsave(&bitmap->lock, flags); - if (!bitmap->filemap) { + if (!bitmap->filemap) /* error or shutdown */ - spin_unlock_irqrestore(&bitmap->lock, flags); break; - } page = filemap_get_page(bitmap, j); if (page != lastpage) { /* skip this page unless it's marked as needing cleaning */ - if (!((attr=get_page_attr(bitmap, page)) & BITMAP_PAGE_CLEAN)) { - if (attr & BITMAP_PAGE_NEEDWRITE) { - page_cache_get(page); + if (!test_page_attr(bitmap, page, BITMAP_PAGE_CLEAN)) { + int need_write = test_page_attr(bitmap, page, + BITMAP_PAGE_NEEDWRITE); + if (need_write) clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); - } + spin_unlock_irqrestore(&bitmap->lock, flags); - if (attr & BITMAP_PAGE_NEEDWRITE) { - switch (write_page(bitmap, page, 0)) { - case -EAGAIN: - set_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); - break; - case 0: - break; - default: - bitmap_file_kick(bitmap); - } - page_cache_release(page); + if (need_write) { + write_page(bitmap, page, 0); + bitmap->allclean = 0; } + spin_lock_irqsave(&bitmap->lock, flags); + j |= (PAGE_BITS - 1); continue; } /* grab the new page, sync and release the old */ - page_cache_get(page); if (lastpage != NULL) { - if (get_page_attr(bitmap, lastpage) & BITMAP_PAGE_NEEDWRITE) { + if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) { clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); - err = write_page(bitmap, lastpage, 0); - if (err == -EAGAIN) { - err = 0; - set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); - } + write_page(bitmap, lastpage, 0); } else { set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); } - kunmap(lastpage); - page_cache_release(lastpage); - if (err) - bitmap_file_kick(bitmap); } else spin_unlock_irqrestore(&bitmap->lock, flags); lastpage = page; - kmap(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->mddev->bitmap_info.external == 0) { + 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); + if (!bitmap->need_sync) + clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } - bmc = bitmap_get_counter(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap), - &blocks, 0); + bmc = bitmap_get_counter(bitmap, + (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap), + &blocks, 0); if (bmc) { /* 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); - } else if (*bmc == 1) { + } else if (*bmc == 1 && !bitmap->need_sync) { /* we can clear the bit */ *bmc = 0; - bitmap_count_page(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap), + bitmap_count_page(bitmap, + (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap), -1); /* clear the bit */ + paddr = kmap_atomic(page, KM_USER0); if (bitmap->flags & BITMAP_HOSTENDIAN) - clear_bit(file_page_offset(j), page_address(page)); + clear_bit(file_page_offset(bitmap, j), + paddr); else - ext2_clear_bit(file_page_offset(j), page_address(page)); + ext2_clear_bit(file_page_offset(bitmap, j), + paddr); + kunmap_atomic(paddr, KM_USER0); } - } - spin_unlock_irqrestore(&bitmap->lock, flags); + } else + j |= PAGE_COUNTER_MASK; } + spin_unlock_irqrestore(&bitmap->lock, flags); /* now sync the final page */ if (lastpage != NULL) { - kunmap(lastpage); spin_lock_irqsave(&bitmap->lock, flags); - if (get_page_attr(bitmap, lastpage) &BITMAP_PAGE_NEEDWRITE) { + if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) { clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); - err = write_page(bitmap, lastpage, 0); - if (err == -EAGAIN) { - set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); - err = 0; - } + write_page(bitmap, lastpage, 0); } else { set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); } - - page_cache_release(lastpage); - } - - return err; -} - -static void daemon_exit(struct bitmap *bitmap, mdk_thread_t **daemon) -{ - mdk_thread_t *dmn; - unsigned long flags; - - /* if no one is waiting on us, we'll free the md thread struct - * and exit, otherwise we let the waiter clean things up */ - spin_lock_irqsave(&bitmap->lock, flags); - if ((dmn = *daemon)) { /* no one is waiting, cleanup and exit */ - *daemon = NULL; - spin_unlock_irqrestore(&bitmap->lock, flags); - kfree(dmn); - complete_and_exit(NULL, 0); /* do_exit not exported */ - } - spin_unlock_irqrestore(&bitmap->lock, flags); -} - -static void bitmap_writeback_daemon(mddev_t *mddev) -{ - struct bitmap *bitmap = mddev->bitmap; - struct page *page; - struct page_list *item; - int err = 0; - - if (signal_pending(current)) { - printk(KERN_INFO - "%s: bitmap writeback daemon got signal, exiting...\n", - bmname(bitmap)); - err = -EINTR; - goto out; - } - if (bitmap == NULL) - /* about to be stopped. */ - return; - - PRINTK("%s: bitmap writeback daemon woke up...\n", bmname(bitmap)); - /* wait on bitmap page writebacks */ - while ((item = dequeue_page(bitmap))) { - page = item->page; - mempool_free(item, bitmap->write_pool); - PRINTK("wait on page writeback: %p\n", page); - wait_on_page_writeback(page); - PRINTK("finished page writeback: %p\n", page); - - err = PageError(page); - page_cache_release(page); - if (err) { - printk(KERN_WARNING "%s: bitmap file writeback " - "failed (page %lu): %d\n", - bmname(bitmap), page->index, err); - bitmap_file_kick(bitmap); - goto out; - } - } - out: - wake_up(&bitmap->write_wait); - if (err) { - printk(KERN_INFO "%s: bitmap writeback daemon exiting (%d)\n", - bmname(bitmap), err); - daemon_exit(bitmap, &bitmap->writeback_daemon); - } -} - -static mdk_thread_t *bitmap_start_daemon(struct bitmap *bitmap, - void (*func)(mddev_t *), char *name) -{ - mdk_thread_t *daemon; - char namebuf[32]; - -#ifdef INJECT_FATAL_FAULT_2 - daemon = NULL; -#else - sprintf(namebuf, "%%s_%s", name); - daemon = md_register_thread(func, bitmap->mddev, namebuf); -#endif - if (!daemon) { - printk(KERN_ERR "%s: failed to start bitmap daemon\n", - bmname(bitmap)); - return ERR_PTR(-ECHILD); } - md_wakeup_thread(daemon); /* start it running */ - - PRINTK("%s: %s daemon (pid %d) started...\n", - bmname(bitmap), name, daemon->tsk->pid); - - return daemon; -} - -static void bitmap_stop_daemon(struct bitmap *bitmap) -{ - /* the daemon can't stop itself... it'll just exit instead... */ - if (bitmap->writeback_daemon && ! IS_ERR(bitmap->writeback_daemon) && - current->pid != bitmap->writeback_daemon->tsk->pid) { - mdk_thread_t *daemon; - unsigned long flags; - - spin_lock_irqsave(&bitmap->lock, flags); - daemon = bitmap->writeback_daemon; - bitmap->writeback_daemon = NULL; - spin_unlock_irqrestore(&bitmap->lock, flags); - if (daemon && ! IS_ERR(daemon)) - md_unregister_thread(daemon); /* destroy the thread */ - } + done: + if (bitmap->allclean == 0) + bitmap->mddev->thread->timeout = + bitmap->mddev->bitmap_info.daemon_sleep; + mutex_unlock(&mddev->bitmap_info.mutex); } static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap, sector_t offset, int *blocks, int create) +__releases(bitmap->lock) +__acquires(bitmap->lock) { /* If 'create', we might release the lock and reclaim it. * The lock must have been taken with interrupts enabled. @@ -1304,16 +1308,31 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect return 0; } + if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) { + DEFINE_WAIT(__wait); + /* note that it is safe to do the prepare_to_wait + * after the test as long as we do it before dropping + * the spinlock. + */ + prepare_to_wait(&bitmap->overflow_wait, &__wait, + TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&bitmap->lock); + blk_unplug(bitmap->mddev->queue); + schedule(); + finish_wait(&bitmap->overflow_wait, &__wait); + continue; + } + switch(*bmc) { 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; } - if ((*bmc & COUNTER_MAX) == COUNTER_MAX) BUG(); + (*bmc)++; spin_unlock_irq(&bitmap->lock); @@ -1323,6 +1342,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect sectors -= blocks; else sectors = 0; } + bitmap->allclean = 0; return 0; } @@ -1335,6 +1355,9 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n", atomic_read(&bitmap->behind_writes), bitmap->max_write_behind); } + if (bitmap->mddev->degraded) + /* Never clear bits or update events_cleared when degraded */ + success = 0; while (sectors) { int blocks; @@ -1348,9 +1371,19 @@ 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; + sysfs_notify_dirent(bitmap->sysfs_can_clear); + } + if (!success && ! (*bmc & NEEDED_MASK)) *bmc |= NEEDED_MASK; + if ((*bmc & COUNTER_MAX) == COUNTER_MAX) + wake_up(&bitmap->overflow_wait); + (*bmc)--; if (*bmc <= 2) { set_page_attr(bitmap, @@ -1365,8 +1398,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto } } -int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, - int degraded) +static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, + int degraded) { bitmap_counter_t *bmc; int rv; @@ -1390,6 +1423,30 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, } } spin_unlock_irq(&bitmap->lock); + bitmap->allclean = 0; + return rv; +} + +int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, + int degraded) +{ + /* bitmap_start_sync must always report on multiples of whole + * pages, otherwise resync (which is very PAGE_SIZE based) will + * get confused. + * So call __bitmap_start_sync repeatedly (if needed) until + * At least PAGE_SIZE>>9 blocks are covered. + * Return the 'or' of the result. + */ + int rv = 0; + int blocks1; + + *blocks = 0; + while (*blocks < (PAGE_SIZE>>9)) { + rv |= __bitmap_start_sync(bitmap, offset, + &blocks1, degraded); + offset += blocks1; + *blocks += blocks1; + } return rv; } @@ -1426,6 +1483,7 @@ 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) @@ -1436,16 +1494,43 @@ 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->mddev->bitmap_info.daemon_sleep))) + return; + wait_event(bitmap->mddev->recovery_wait, + atomic_read(&bitmap->mddev->recovery_active) == 0); + + bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync; + set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags); + 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; + sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed"); +} + 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 @@ -1469,7 +1554,25 @@ 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" */ +void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e) +{ + unsigned long chunk; + + for (chunk = s; chunk <= e; chunk++) { + sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap); + bitmap_set_memory_bits(bitmap, sec, 1); + bitmap_file_set_bit(bitmap, sec); + if (sec < bitmap->mddev->recovery_cp) + /* We are asserting that the array is dirty, + * so move the recovery_cp address back so + * that it is obvious that it is dirty + */ + bitmap->mddev->recovery_cp = sec; + } } /* @@ -1478,7 +1581,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n void bitmap_flush(mddev_t *mddev) { struct bitmap *bitmap = mddev->bitmap; - int sleep; + long sleep; if (!bitmap) /* there was no bitmap */ return; @@ -1486,12 +1589,13 @@ void bitmap_flush(mddev_t *mddev) /* run the daemon_work three time to ensure everything is flushed * that can be */ - sleep = bitmap->daemon_sleep; - bitmap->daemon_sleep = 0; - bitmap_daemon_work(bitmap); - bitmap_daemon_work(bitmap); - bitmap_daemon_work(bitmap); - bitmap->daemon_sleep = sleep; + sleep = mddev->bitmap_info.daemon_sleep * 2; + bitmap->daemon_lastrun -= sleep; + bitmap_daemon_work(mddev); + bitmap->daemon_lastrun -= sleep; + bitmap_daemon_work(mddev); + bitmap->daemon_lastrun -= sleep; + bitmap_daemon_work(mddev); bitmap_update_sb(bitmap); } @@ -1514,8 +1618,6 @@ static void bitmap_free(struct bitmap *bitmap) /* free all allocated memory */ - mempool_destroy(bitmap->write_pool); - if (bp) /* deallocate the page memory */ for (k = 0; k < pages; k++) if (bp[k].map && !bp[k].hijacked) @@ -1523,6 +1625,7 @@ static void bitmap_free(struct bitmap *bitmap) kfree(bp); kfree(bitmap); } + void bitmap_destroy(mddev_t *mddev) { struct bitmap *bitmap = mddev->bitmap; @@ -1530,7 +1633,14 @@ void bitmap_destroy(mddev_t *mddev) if (!bitmap) /* there was no bitmap */ return; + mutex_lock(&mddev->bitmap_info.mutex); mddev->bitmap = NULL; /* disconnect from the md device */ + mutex_unlock(&mddev->bitmap_info.mutex); + if (mddev->thread) + mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + + if (bitmap->sysfs_can_clear) + sysfs_put(bitmap->sysfs_can_clear); bitmap_free(bitmap); } @@ -1542,52 +1652,68 @@ void bitmap_destroy(mddev_t *mddev) int bitmap_create(mddev_t *mddev) { struct bitmap *bitmap; - unsigned long blocks = mddev->resync_max_sectors; + sector_t blocks = mddev->resync_max_sectors; unsigned long chunks; unsigned long pages; - struct file *file = mddev->bitmap_file; + struct file *file = mddev->bitmap_info.file; int err; sector_t start; + struct sysfs_dirent *bm; - BUG_ON(sizeof(bitmap_super_t) != 256); + BUILD_BUG_ON(sizeof(bitmap_super_t) != 256); - if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */ + if (!file && !mddev->bitmap_info.offset) /* bitmap disabled, nothing to do */ return 0; - BUG_ON(file && mddev->bitmap_offset); + BUG_ON(file && mddev->bitmap_info.offset); - bitmap = kmalloc(sizeof(*bitmap), GFP_KERNEL); + bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL); if (!bitmap) return -ENOMEM; - memset(bitmap, 0, sizeof(*bitmap)); - spin_lock_init(&bitmap->lock); + atomic_set(&bitmap->pending_writes, 0); + init_waitqueue_head(&bitmap->write_wait); + init_waitqueue_head(&bitmap->overflow_wait); + bitmap->mddev = mddev; - spin_lock_init(&bitmap->write_lock); - INIT_LIST_HEAD(&bitmap->complete_pages); - init_waitqueue_head(&bitmap->write_wait); - bitmap->write_pool = mempool_create(WRITE_POOL_SIZE, write_pool_alloc, - write_pool_free, NULL); - err = -ENOMEM; - if (!bitmap->write_pool) - goto error; + bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap"); + if (bm) { + bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear"); + sysfs_put(bm); + } else + bitmap->sysfs_can_clear = NULL; bitmap->file = file; - bitmap->offset = mddev->bitmap_offset; - if (file) get_file(file); - /* read superblock from bitmap file (this sets bitmap->chunksize) */ - err = bitmap_read_sb(bitmap); + if (file) { + get_file(file); + /* As future accesses to this file will use bmap, + * and bypass the page cache, we must sync the file + * first. + */ + vfs_fsync(file, 1); + } + /* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */ + if (!mddev->bitmap_info.external) + err = bitmap_read_sb(bitmap); + else { + err = 0; + if (mddev->bitmap_info.chunksize == 0 || + mddev->bitmap_info.daemon_sleep == 0) + /* chunksize and time_base need to be + * set first. */ + err = -EINVAL; + } if (err) goto error; - bitmap->chunkshift = find_first_bit(&bitmap->chunksize, - sizeof(bitmap->chunksize)); + bitmap->daemon_lastrun = jiffies; + bitmap->chunkshift = ffz(~mddev->bitmap_info.chunksize); /* now that chunksize and chunkshift are set, we can use these macros */ - chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) / - CHUNK_BLOCK_RATIO(bitmap); + chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >> + CHUNK_BLOCK_SHIFT(bitmap); pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO; BUG_ON(!pages); @@ -1602,14 +1728,11 @@ int bitmap_create(mddev_t *mddev) #ifdef INJECT_FATAL_FAULT_1 bitmap->bp = NULL; #else - bitmap->bp = kmalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL); + bitmap->bp = kzalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL); #endif err = -ENOMEM; if (!bitmap->bp) goto error; - memset(bitmap->bp, 0, pages * sizeof(*bitmap->bp)); - - bitmap->flags |= BITMAP_ACTIVE; /* now that we have some pages available, initialize the in-memory * bitmap from the on-disk bitmap */ @@ -1628,22 +1751,276 @@ int bitmap_create(mddev_t *mddev) mddev->bitmap = bitmap; - if (file) - /* kick off the bitmap writeback daemon */ - bitmap->writeback_daemon = - bitmap_start_daemon(bitmap, - bitmap_writeback_daemon, - "bitmap_wb"); + mddev->thread->timeout = mddev->bitmap_info.daemon_sleep; + md_wakeup_thread(mddev->thread); - if (IS_ERR(bitmap->writeback_daemon)) - return PTR_ERR(bitmap->writeback_daemon); - return bitmap_update_sb(bitmap); + bitmap_update_sb(bitmap); + + return (bitmap->flags & BITMAP_WRITE_ERROR) ? -EIO : 0; error: bitmap_free(bitmap); return err; } +static ssize_t +location_show(mddev_t *mddev, char *page) +{ + ssize_t len; + if (mddev->bitmap_info.file) { + len = sprintf(page, "file"); + } else if (mddev->bitmap_info.offset) { + len = sprintf(page, "%+lld", (long long)mddev->bitmap_info.offset); + } else + len = sprintf(page, "none"); + len += sprintf(page+len, "\n"); + return len; +} + +static ssize_t +location_store(mddev_t *mddev, const char *buf, size_t len) +{ + + if (mddev->pers) { + if (!mddev->pers->quiesce) + return -EBUSY; + if (mddev->recovery || mddev->sync_thread) + return -EBUSY; + } + + if (mddev->bitmap || mddev->bitmap_info.file || + mddev->bitmap_info.offset) { + /* bitmap already configured. Only option is to clear it */ + if (strncmp(buf, "none", 4) != 0) + return -EBUSY; + if (mddev->pers) { + mddev->pers->quiesce(mddev, 1); + bitmap_destroy(mddev); + mddev->pers->quiesce(mddev, 0); + } + mddev->bitmap_info.offset = 0; + if (mddev->bitmap_info.file) { + struct file *f = mddev->bitmap_info.file; + mddev->bitmap_info.file = NULL; + restore_bitmap_write_access(f); + fput(f); + } + } else { + /* No bitmap, OK to set a location */ + long long offset; + if (strncmp(buf, "none", 4) == 0) + /* nothing to be done */; + else if (strncmp(buf, "file:", 5) == 0) { + /* Not supported yet */ + return -EINVAL; + } else { + int rv; + if (buf[0] == '+') + rv = strict_strtoll(buf+1, 10, &offset); + else + rv = strict_strtoll(buf, 10, &offset); + if (rv) + return rv; + if (offset == 0) + return -EINVAL; + if (mddev->bitmap_info.external == 0 && + mddev->major_version == 0 && + offset != mddev->bitmap_info.default_offset) + return -EINVAL; + mddev->bitmap_info.offset = offset; + if (mddev->pers) { + mddev->pers->quiesce(mddev, 1); + rv = bitmap_create(mddev); + if (rv) { + bitmap_destroy(mddev); + mddev->bitmap_info.offset = 0; + } + mddev->pers->quiesce(mddev, 0); + if (rv) + return rv; + } + } + } + if (!mddev->external) { + /* Ensure new bitmap info is stored in + * metadata promptly. + */ + set_bit(MD_CHANGE_DEVS, &mddev->flags); + md_wakeup_thread(mddev->thread); + } + return len; +} + +static struct md_sysfs_entry bitmap_location = +__ATTR(location, S_IRUGO|S_IWUSR, location_show, location_store); + +static ssize_t +timeout_show(mddev_t *mddev, char *page) +{ + ssize_t len; + unsigned long secs = mddev->bitmap_info.daemon_sleep / HZ; + unsigned long jifs = mddev->bitmap_info.daemon_sleep % HZ; + + len = sprintf(page, "%lu", secs); + if (jifs) + len += sprintf(page+len, ".%03u", jiffies_to_msecs(jifs)); + len += sprintf(page+len, "\n"); + return len; +} + +static ssize_t +timeout_store(mddev_t *mddev, const char *buf, size_t len) +{ + /* timeout can be set at any time */ + unsigned long timeout; + int rv = strict_strtoul_scaled(buf, &timeout, 4); + if (rv) + return rv; + + /* just to make sure we don't overflow... */ + if (timeout >= LONG_MAX / HZ) + return -EINVAL; + + timeout = timeout * HZ / 10000; + + if (timeout >= MAX_SCHEDULE_TIMEOUT) + timeout = MAX_SCHEDULE_TIMEOUT-1; + if (timeout < 1) + timeout = 1; + mddev->bitmap_info.daemon_sleep = timeout; + if (mddev->thread) { + /* if thread->timeout is MAX_SCHEDULE_TIMEOUT, then + * the bitmap is all clean and we don't need to + * adjust the timeout right now + */ + if (mddev->thread->timeout < MAX_SCHEDULE_TIMEOUT) { + mddev->thread->timeout = timeout; + md_wakeup_thread(mddev->thread); + } + } + return len; +} + +static struct md_sysfs_entry bitmap_timeout = +__ATTR(time_base, S_IRUGO|S_IWUSR, timeout_show, timeout_store); + +static ssize_t +backlog_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%lu\n", mddev->bitmap_info.max_write_behind); +} + +static ssize_t +backlog_store(mddev_t *mddev, const char *buf, size_t len) +{ + unsigned long backlog; + int rv = strict_strtoul(buf, 10, &backlog); + if (rv) + return rv; + if (backlog > COUNTER_MAX) + return -EINVAL; + mddev->bitmap_info.max_write_behind = backlog; + return len; +} + +static struct md_sysfs_entry bitmap_backlog = +__ATTR(backlog, S_IRUGO|S_IWUSR, backlog_show, backlog_store); + +static ssize_t +chunksize_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%lu\n", mddev->bitmap_info.chunksize); +} + +static ssize_t +chunksize_store(mddev_t *mddev, const char *buf, size_t len) +{ + /* Can only be changed when no bitmap is active */ + int rv; + unsigned long csize; + if (mddev->bitmap) + return -EBUSY; + rv = strict_strtoul(buf, 10, &csize); + if (rv) + return rv; + if (csize < 512 || + !is_power_of_2(csize)) + return -EINVAL; + mddev->bitmap_info.chunksize = csize; + return len; +} + +static struct md_sysfs_entry bitmap_chunksize = +__ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store); + +static ssize_t metadata_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%s\n", (mddev->bitmap_info.external + ? "external" : "internal")); +} + +static ssize_t metadata_store(mddev_t *mddev, const char *buf, size_t len) +{ + if (mddev->bitmap || + mddev->bitmap_info.file || + mddev->bitmap_info.offset) + return -EBUSY; + if (strncmp(buf, "external", 8) == 0) + mddev->bitmap_info.external = 1; + else if (strncmp(buf, "internal", 8) == 0) + mddev->bitmap_info.external = 0; + else + return -EINVAL; + return len; +} + +static struct md_sysfs_entry bitmap_metadata = +__ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store); + +static ssize_t can_clear_show(mddev_t *mddev, char *page) +{ + int len; + if (mddev->bitmap) + len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ? + "false" : "true")); + else + len = sprintf(page, "\n"); + return len; +} + +static ssize_t can_clear_store(mddev_t *mddev, const char *buf, size_t len) +{ + if (mddev->bitmap == NULL) + return -ENOENT; + if (strncmp(buf, "false", 5) == 0) + mddev->bitmap->need_sync = 1; + else if (strncmp(buf, "true", 4) == 0) { + if (mddev->degraded) + return -EBUSY; + mddev->bitmap->need_sync = 0; + } else + return -EINVAL; + return len; +} + +static struct md_sysfs_entry bitmap_can_clear = +__ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store); + +static struct attribute *md_bitmap_attrs[] = { + &bitmap_location.attr, + &bitmap_timeout.attr, + &bitmap_backlog.attr, + &bitmap_chunksize.attr, + &bitmap_metadata.attr, + &bitmap_can_clear.attr, + NULL +}; +struct attribute_group md_bitmap_group = { + .name = "bitmap", + .attrs = md_bitmap_attrs, +}; + + /* the bitmap API -- for raid personalities */ EXPORT_SYMBOL(bitmap_startwrite); EXPORT_SYMBOL(bitmap_endwrite); @@ -1651,4 +2028,4 @@ EXPORT_SYMBOL(bitmap_start_sync); EXPORT_SYMBOL(bitmap_end_sync); EXPORT_SYMBOL(bitmap_unplug); EXPORT_SYMBOL(bitmap_close_sync); -EXPORT_SYMBOL(bitmap_daemon_work); +EXPORT_SYMBOL(bitmap_cond_end_sync);