diff options
Diffstat (limited to 'drivers/md/md-bitmap.c')
| -rw-r--r-- | drivers/md/md-bitmap.c | 2610 |
1 files changed, 2610 insertions, 0 deletions
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c new file mode 100644 index 000000000000..239c7bb3929b --- /dev/null +++ b/drivers/md/md-bitmap.c @@ -0,0 +1,2610 @@ +/* + * bitmap.c two-level bitmap (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003 + * + * bitmap_create - sets up the bitmap structure + * bitmap_destroy - destroys the bitmap structure + * + * additions, Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.: + * - added disk storage for bitmap + * - changes to allow various bitmap chunk sizes + */ + +/* + * Still to do: + * + * flush after percent set rather than just time based. (maybe both). + */ + +#include <linux/blkdev.h> +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/timer.h> +#include <linux/sched.h> +#include <linux/list.h> +#include <linux/file.h> +#include <linux/mount.h> +#include <linux/buffer_head.h> +#include <linux/seq_file.h> +#include <trace/events/block.h> +#include "md.h" +#include "md-bitmap.h" + +static inline char *bmname(struct bitmap *bitmap) +{ + return bitmap->mddev ? mdname(bitmap->mddev) : "mdX"; +} + +/* + * check a page and, if necessary, allocate it (or hijack it if the alloc fails) + * + * 1) check to see if this page is allocated, if it's not then try to alloc + * 2) if the alloc fails, set the page's hijacked flag so we'll use the + * page pointer directly as a counter + * + * if we find our page, we increment the page's refcount so that it stays + * allocated while we're using it + */ +static int bitmap_checkpage(struct bitmap_counts *bitmap, + unsigned long page, int create, int no_hijack) +__releases(bitmap->lock) +__acquires(bitmap->lock) +{ + unsigned char *mappage; + + if (page >= bitmap->pages) { + /* This can happen if bitmap_start_sync goes beyond + * End-of-device while looking for a whole page. + * It is harmless. + */ + return -EINVAL; + } + + if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */ + return 0; + + if (bitmap->bp[page].map) /* page is already allocated, just return */ + return 0; + + if (!create) + return -ENOENT; + + /* this page has not been allocated yet */ + + spin_unlock_irq(&bitmap->lock); + /* It is possible that this is being called inside a + * prepare_to_wait/finish_wait loop from raid5c:make_request(). + * In general it is not permitted to sleep in that context as it + * can cause the loop to spin freely. + * That doesn't apply here as we can only reach this point + * once with any loop. + * When this function completes, either bp[page].map or + * bp[page].hijacked. In either case, this function will + * abort before getting to this point again. So there is + * no risk of a free-spin, and so it is safe to assert + * that sleeping here is allowed. + */ + sched_annotate_sleep(); + mappage = kzalloc(PAGE_SIZE, GFP_NOIO); + spin_lock_irq(&bitmap->lock); + + if (mappage == NULL) { + pr_debug("md/bitmap: map page allocation failed, hijacking\n"); + /* We don't support hijack for cluster raid */ + if (no_hijack) + return -ENOMEM; + /* failed - set the hijacked flag so that we can use the + * pointer as a counter */ + if (!bitmap->bp[page].map) + bitmap->bp[page].hijacked = 1; + } else if (bitmap->bp[page].map || + bitmap->bp[page].hijacked) { + /* somebody beat us to getting the page */ + kfree(mappage); + } else { + + /* no page was in place and we have one, so install it */ + + bitmap->bp[page].map = mappage; + bitmap->missing_pages--; + } + return 0; +} + +/* 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 void bitmap_checkfree(struct bitmap_counts *bitmap, unsigned long page) +{ + char *ptr; + + if (bitmap->bp[page].count) /* page is still busy */ + return; + + /* page is no longer in use, it can be released */ + + if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */ + bitmap->bp[page].hijacked = 0; + bitmap->bp[page].map = NULL; + } else { + /* normal case, free the page */ + ptr = bitmap->bp[page].map; + bitmap->bp[page].map = NULL; + bitmap->missing_pages++; + kfree(ptr); + } +} + +/* + * bitmap file handling - read and write the bitmap file and its superblock + */ + +/* + * basic page I/O operations + */ + +/* IO operations when bitmap is stored near all superblocks */ +static int read_sb_page(struct mddev *mddev, loff_t offset, + struct page *page, + unsigned long index, int size) +{ + /* choose a good rdev and read the page from there */ + + struct md_rdev *rdev; + sector_t target; + + rdev_for_each(rdev, mddev) { + if (! test_bit(In_sync, &rdev->flags) + || test_bit(Faulty, &rdev->flags) + || test_bit(Bitmap_sync, &rdev->flags)) + continue; + + target = offset + index * (PAGE_SIZE/512); + + if (sync_page_io(rdev, target, + roundup(size, bdev_logical_block_size(rdev->bdev)), + page, REQ_OP_READ, 0, true)) { + page->index = index; + return 0; + } + } + return -EIO; +} + +static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *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_entry_continue_rcu. + * + * Note that if entered with 'rdev == NULL' to start at the + * beginning, we temporarily assign 'rdev' to an address which + * isn't really an rdev, but which can be used by + * list_for_each_entry_continue_rcu() to find the first entry. + */ + rcu_read_lock(); + if (rdev == NULL) + /* start at the beginning */ + rdev = list_entry(&mddev->disks, struct md_rdev, same_set); + else { + /* release the previous rdev and start from there. */ + rdev_dec_pending(rdev, mddev); + } + list_for_each_entry_continue_rcu(rdev, &mddev->disks, 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; +} + +static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) +{ + struct md_rdev *rdev; + struct block_device *bdev; + struct mddev *mddev = bitmap->mddev; + struct bitmap_storage *store = &bitmap->storage; + +restart: + rdev = NULL; + while ((rdev = next_active_rdev(rdev, mddev)) != NULL) { + int size = PAGE_SIZE; + loff_t offset = mddev->bitmap_info.offset; + + bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev; + + if (page->index == store->file_pages-1) { + int last_page_size = store->bytes & (PAGE_SIZE-1); + if (last_page_size == 0) + last_page_size = PAGE_SIZE; + size = roundup(last_page_size, + bdev_logical_block_size(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_start + offset + + page->index * (PAGE_SIZE/512), + size, + page); + } + + if (wait && md_super_wait(mddev) < 0) + goto restart; + return 0; + + bad_alignment: + return -EINVAL; +} + +static void bitmap_file_kick(struct bitmap *bitmap); +/* + * write out a page to a file + */ +static void write_page(struct bitmap *bitmap, struct page *page, int wait) +{ + struct buffer_head *bh; + + if (bitmap->storage.file == NULL) { + switch (write_sb_page(bitmap, page, wait)) { + case -EINVAL: + set_bit(BITMAP_WRITE_ERROR, &bitmap->flags); + } + } else { + + bh = page_buffers(page); + + while (bh && bh->b_blocknr) { + atomic_inc(&bitmap->pending_writes); + set_buffer_locked(bh); + set_buffer_mapped(bh); + submit_bh(REQ_OP_WRITE, REQ_SYNC, bh); + bh = bh->b_this_page; + } + + if (wait) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + } + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) + bitmap_file_kick(bitmap); +} + +static void end_bitmap_write(struct buffer_head *bh, int uptodate) +{ + struct bitmap *bitmap = bh->b_private; + + if (!uptodate) + set_bit(BITMAP_WRITE_ERROR, &bitmap->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); + put_page(page); +} +static void free_buffers(struct page *page) +{ + struct buffer_head *bh; + + if (!PagePrivate(page)) + return; + + bh = page_buffers(page); + while (bh) { + struct buffer_head *next = bh->b_this_page; + free_buffer_head(bh); + bh = next; + } + __clear_page_buffers(page); + put_page(page); +} + +/* 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 int read_page(struct file *file, unsigned long index, + struct bitmap *bitmap, + unsigned long count, + struct page *page) +{ + int ret = 0; + struct inode *inode = file_inode(file); + struct buffer_head *bh; + sector_t block; + + pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE, + (unsigned long long)index << PAGE_SHIFT); + + bh = alloc_page_buffers(page, 1<<inode->i_blkbits, false); + if (!bh) { + ret = -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! */ + ret = -EINVAL; + goto out; + } + bh->b_bdev = inode->i_sb->s_bdev; + if (count < (1<<inode->i_blkbits)) + count = 0; + else + count -= (1<<inode->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(REQ_OP_READ, 0, bh); + } + block++; + bh = bh->b_this_page; + } + page->index = index; + + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) + ret = -EIO; +out: + if (ret) + pr_err("md: bitmap read error: (%dB @ %llu): %d\n", + (int)PAGE_SIZE, + (unsigned long long)index << PAGE_SHIFT, + ret); + return ret; +} + +/* + * bitmap file superblock operations + */ + +/* + * bitmap_wait_writes() should be called before writing any bitmap + * blocks, to ensure previous writes, particularly from + * bitmap_daemon_work(), have completed. + */ +static void bitmap_wait_writes(struct bitmap *bitmap) +{ + if (bitmap->storage.file) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + else + /* Note that we ignore the return value. The writes + * might have failed, but that would just mean that + * some bits which should be cleared haven't been, + * which is safe. The relevant bitmap blocks will + * probably get written again, but there is no great + * loss if they aren't. + */ + md_super_wait(bitmap->mddev); +} + + +/* update the event counter and sync the superblock to disk */ +void bitmap_update_sb(struct bitmap *bitmap) +{ + bitmap_super_t *sb; + + if (!bitmap || !bitmap->mddev) /* no bitmap for this array */ + return; + if (bitmap->mddev->bitmap_info.external) + return; + if (!bitmap->storage.sb_page) /* no superblock */ + return; + sb = kmap_atomic(bitmap->storage.sb_page); + sb->events = 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); + /* + * clear BITMAP_WRITE_ERROR bit to protect against the case that + * a bitmap write error occurred but the later writes succeeded. + */ + sb->state = cpu_to_le32(bitmap->flags & ~BIT(BITMAP_WRITE_ERROR)); + /* 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); + /* This might have been changed by a reshape */ + sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); + sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize); + sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes); + sb->sectors_reserved = cpu_to_le32(bitmap->mddev-> + bitmap_info.space); + kunmap_atomic(sb); + write_page(bitmap, bitmap->storage.sb_page, 1); +} +EXPORT_SYMBOL(bitmap_update_sb); + +/* print out the bitmap file superblock */ +void bitmap_print_sb(struct bitmap *bitmap) +{ + bitmap_super_t *sb; + + if (!bitmap || !bitmap->storage.sb_page) + return; + sb = kmap_atomic(bitmap->storage.sb_page); + pr_debug("%s: bitmap file superblock:\n", bmname(bitmap)); + pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic)); + pr_debug(" version: %d\n", le32_to_cpu(sb->version)); + pr_debug(" uuid: %08x.%08x.%08x.%08x\n", + le32_to_cpu(*(__u32 *)(sb->uuid+0)), + le32_to_cpu(*(__u32 *)(sb->uuid+4)), + le32_to_cpu(*(__u32 *)(sb->uuid+8)), + le32_to_cpu(*(__u32 *)(sb->uuid+12))); + pr_debug(" events: %llu\n", + (unsigned long long) le64_to_cpu(sb->events)); + pr_debug("events cleared: %llu\n", + (unsigned long long) le64_to_cpu(sb->events_cleared)); + pr_debug(" state: %08x\n", le32_to_cpu(sb->state)); + pr_debug(" chunksize: %d B\n", le32_to_cpu(sb->chunksize)); + pr_debug(" daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep)); + pr_debug(" sync size: %llu KB\n", + (unsigned long long)le64_to_cpu(sb->sync_size)/2); + pr_debug("max write behind: %d\n", le32_to_cpu(sb->write_behind)); + kunmap_atomic(sb); +} + +/* + * bitmap_new_disk_sb + * @bitmap + * + * This function is somewhat the reverse of bitmap_read_sb. bitmap_read_sb + * reads and verifies the on-disk bitmap superblock and populates bitmap_info. + * This function verifies 'bitmap_info' and populates the on-disk bitmap + * structure, which is to be written to disk. + * + * Returns: 0 on success, -Exxx on error + */ +static int bitmap_new_disk_sb(struct bitmap *bitmap) +{ + bitmap_super_t *sb; + unsigned long chunksize, daemon_sleep, write_behind; + + bitmap->storage.sb_page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (bitmap->storage.sb_page == NULL) + return -ENOMEM; + bitmap->storage.sb_page->index = 0; + + sb = kmap_atomic(bitmap->storage.sb_page); + + sb->magic = cpu_to_le32(BITMAP_MAGIC); + sb->version = cpu_to_le32(BITMAP_MAJOR_HI); + + chunksize = bitmap->mddev->bitmap_info.chunksize; + BUG_ON(!chunksize); + if (!is_power_of_2(chunksize)) { + kunmap_atomic(sb); + pr_warn("bitmap chunksize not a power of 2\n"); + return -EINVAL; + } + sb->chunksize = cpu_to_le32(chunksize); + + daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep; + if (!daemon_sleep || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) { + pr_debug("Choosing daemon_sleep default (5 sec)\n"); + daemon_sleep = 5 * HZ; + } + sb->daemon_sleep = cpu_to_le32(daemon_sleep); + bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; + + /* + * FIXME: write_behind for RAID1. If not specified, what + * is a good choice? We choose COUNTER_MAX / 2 arbitrarily. + */ + write_behind = bitmap->mddev->bitmap_info.max_write_behind; + if (write_behind > COUNTER_MAX) + write_behind = COUNTER_MAX / 2; + sb->write_behind = cpu_to_le32(write_behind); + bitmap->mddev->bitmap_info.max_write_behind = write_behind; + + /* keep the array size field of the bitmap superblock up to date */ + sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); + + memcpy(sb->uuid, bitmap->mddev->uuid, 16); + + set_bit(BITMAP_STALE, &bitmap->flags); + sb->state = cpu_to_le32(bitmap->flags); + bitmap->events_cleared = bitmap->mddev->events; + sb->events_cleared = cpu_to_le64(bitmap->mddev->events); + bitmap->mddev->bitmap_info.nodes = 0; + + kunmap_atomic(sb); + + return 0; +} + +/* read the superblock from the bitmap file and initialize some bitmap fields */ +static int bitmap_read_sb(struct bitmap *bitmap) +{ + char *reason = NULL; + bitmap_super_t *sb; + unsigned long chunksize, daemon_sleep, write_behind; + unsigned long long events; + int nodes = 0; + unsigned long sectors_reserved = 0; + int err = -EINVAL; + struct page *sb_page; + loff_t offset = bitmap->mddev->bitmap_info.offset; + + if (!bitmap->storage.file && !bitmap->mddev->bitmap_info.offset) { + chunksize = 128 * 1024 * 1024; + daemon_sleep = 5 * HZ; + write_behind = 0; + set_bit(BITMAP_STALE, &bitmap->flags); + err = 0; + goto out_no_sb; + } + /* page 0 is the superblock, read it... */ + sb_page = alloc_page(GFP_KERNEL); + if (!sb_page) + return -ENOMEM; + bitmap->storage.sb_page = sb_page; + +re_read: + /* If cluster_slot is set, the cluster is setup */ + if (bitmap->cluster_slot >= 0) { + sector_t bm_blocks = bitmap->mddev->resync_max_sectors; + + sector_div(bm_blocks, + bitmap->mddev->bitmap_info.chunksize >> 9); + /* bits to bytes */ + bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t); + /* to 4k blocks */ + bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096); + offset = bitmap->mddev->bitmap_info.offset + (bitmap->cluster_slot * (bm_blocks << 3)); + pr_debug("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__, + bitmap->cluster_slot, offset); + } + + if (bitmap->storage.file) { + loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host); + int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize; + + err = read_page(bitmap->storage.file, 0, + bitmap, bytes, sb_page); + } else { + err = read_sb_page(bitmap->mddev, + offset, + sb_page, + 0, sizeof(bitmap_super_t)); + } + if (err) + return err; + + err = -EINVAL; + sb = kmap_atomic(sb_page); + + chunksize = le32_to_cpu(sb->chunksize); + daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; + write_behind = le32_to_cpu(sb->write_behind); + sectors_reserved = le32_to_cpu(sb->sectors_reserved); + /* Setup nodes/clustername only if bitmap version is + * cluster-compatible + */ + if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) { + nodes = le32_to_cpu(sb->nodes); + strlcpy(bitmap->mddev->bitmap_info.cluster_name, + sb->cluster_name, 64); + } + + /* verify that the bitmap-specific fields are valid */ + if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) + reason = "bad magic"; + else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO || + le32_to_cpu(sb->version) > BITMAP_MAJOR_CLUSTERED) + reason = "unrecognized superblock version"; + else if (chunksize < 512) + reason = "bitmap chunksize too small"; + else if (!is_power_of_2(chunksize)) + reason = "bitmap chunksize not a power of 2"; + 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) { + pr_warn("%s: invalid bitmap file superblock: %s\n", + bmname(bitmap), reason); + goto out; + } + + /* keep the array size field of the bitmap superblock up to date */ + sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); + + if (bitmap->mddev->persistent) { + /* + * We have a persistent array superblock, so compare the + * bitmap's UUID and event counter to the mddev's + */ + if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) { + pr_warn("%s: bitmap superblock UUID mismatch\n", + bmname(bitmap)); + goto out; + } + events = le64_to_cpu(sb->events); + if (!nodes && (events < bitmap->mddev->events)) { + pr_warn("%s: bitmap file is out of date (%llu < %llu) -- forcing full recovery\n", + bmname(bitmap), events, + (unsigned long long) bitmap->mddev->events); + set_bit(BITMAP_STALE, &bitmap->flags); + } + } + + /* assign fields using values from superblock */ + bitmap->flags |= le32_to_cpu(sb->state); + if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN) + set_bit(BITMAP_HOSTENDIAN, &bitmap->flags); + bitmap->events_cleared = le64_to_cpu(sb->events_cleared); + strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); + err = 0; + +out: + kunmap_atomic(sb); + /* Assigning chunksize is required for "re_read" */ + bitmap->mddev->bitmap_info.chunksize = chunksize; + if (err == 0 && nodes && (bitmap->cluster_slot < 0)) { + err = md_setup_cluster(bitmap->mddev, nodes); + if (err) { + pr_warn("%s: Could not setup cluster service (%d)\n", + bmname(bitmap), err); + goto out_no_sb; + } + bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev); + goto re_read; + } + + +out_no_sb: + if (test_bit(BITMAP_STALE, &bitmap->flags)) + bitmap->events_cleared = bitmap->mddev->events; + bitmap->mddev->bitmap_info.chunksize = chunksize; + bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; + bitmap->mddev->bitmap_info.max_write_behind = write_behind; + bitmap->mddev->bitmap_info.nodes = nodes; + if (bitmap->mddev->bitmap_info.space == 0 || + bitmap->mddev->bitmap_info.space > sectors_reserved) + bitmap->mddev->bitmap_info.space = sectors_reserved; + if (err) { + bitmap_print_sb(bitmap); + if (bitmap->cluster_slot < 0) + md_cluster_stop(bitmap->mddev); + } + return err; +} + +/* + * 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(struct bitmap_storage *store, + unsigned long chunk) +{ + if (store->sb_page) + 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(struct bitmap_storage *store, + unsigned long chunk) +{ + if (store->sb_page) + chunk += sizeof(bitmap_super_t) << 3; + return chunk & (PAGE_BITS - 1); +} + +/* + * return a pointer to the page in the filemap that contains the given bit + * + */ +static inline struct page *filemap_get_page(struct bitmap_storage *store, + unsigned long chunk) +{ + if (file_page_index(store, chunk) >= store->file_pages) + return NULL; + return store->filemap[file_page_index(store, chunk)]; +} + +static int bitmap_storage_alloc(struct bitmap_storage *store, + unsigned long chunks, int with_super, + int slot_number) +{ + int pnum, offset = 0; + unsigned long num_pages; + unsigned long bytes; + + bytes = DIV_ROUND_UP(chunks, 8); + if (with_super) + bytes += sizeof(bitmap_super_t); + + num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE); + offset = slot_number * num_pages; + + store->filemap = kmalloc(sizeof(struct page *) + * num_pages, GFP_KERNEL); + if (!store->filemap) + return -ENOMEM; + + if (with_super && !store->sb_page) { + store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO); + if (store->sb_page == NULL) + return -ENOMEM; + } + + pnum = 0; + if (store->sb_page) { + store->filemap[0] = store->sb_page; + pnum = 1; + store->sb_page->index = offset; + } + + for ( ; pnum < num_pages; pnum++) { + store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO); + if (!store->filemap[pnum]) { + store->file_pages = pnum; + return -ENOMEM; + } + store->filemap[pnum]->index = pnum + offset; + } + store->file_pages = pnum; + + /* We need 4 bits per page, rounded up to a multiple + * of sizeof(unsigned long) */ + store->filemap_attr = kzalloc( + roundup(DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)), + GFP_KERNEL); + if (!store->filemap_attr) + return -ENOMEM; + + store->bytes = bytes; + + return 0; +} + +static void bitmap_file_unmap(struct bitmap_storage *store) +{ + struct page **map, *sb_page; + int pages; + struct file *file; + + file = store->file; + map = store->filemap; + pages = store->file_pages; + sb_page = store->sb_page; + + while (pages--) + if (map[pages] != sb_page) /* 0 is sb_page, release it below */ + free_buffers(map[pages]); + kfree(map); + kfree(store->filemap_attr); + + if (sb_page) + free_buffers(sb_page); + + if (file) { + struct inode *inode = file_inode(file); + invalidate_mapping_pages(inode->i_mapping, 0, -1); + fput(file); + } +} + +/* + * bitmap_file_kick - if an error occurs while manipulating the bitmap file + * then it is no longer reliable, so we stop using it and we mark the file + * as failed in the superblock + */ +static void bitmap_file_kick(struct bitmap *bitmap) +{ + char *path, *ptr = NULL; + + if (!test_and_set_bit(BITMAP_STALE, &bitmap->flags)) { + bitmap_update_sb(bitmap); + + if (bitmap->storage.file) { + path = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (path) + ptr = file_path(bitmap->storage.file, + path, PAGE_SIZE); + + pr_warn("%s: kicking failed bitmap file %s from array!\n", + bmname(bitmap), IS_ERR(ptr) ? "" : ptr); + + kfree(path); + } else + pr_warn("%s: disabling internal bitmap due to errors\n", + bmname(bitmap)); + } +} + +enum bitmap_page_attr { + BITMAP_PAGE_DIRTY = 0, /* there are set bits that need to be synced */ + BITMAP_PAGE_PENDING = 1, /* there are bits that are being cleaned. + * i.e. counter is 1 or 2. */ + BITMAP_PAGE_NEEDWRITE = 2, /* there are cleared bits that need to be synced */ +}; + +static inline void set_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) +{ + set_bit((pnum<<2) + attr, bitmap->storage.filemap_attr); +} + +static inline void clear_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) +{ + clear_bit((pnum<<2) + attr, bitmap->storage.filemap_attr); +} + +static inline int test_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) +{ + return test_bit((pnum<<2) + attr, bitmap->storage.filemap_attr); +} + +static inline int test_and_clear_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) +{ + return test_and_clear_bit((pnum<<2) + attr, + bitmap->storage.filemap_attr); +} +/* + * bitmap_file_set_bit -- called before performing a write to the md device + * to set (and eventually sync) a particular bit in the bitmap file + * + * we set the bit immediately, then we record the page number so that + * when an unplug occurs, we can flush the dirty pages out to disk + */ +static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) +{ + unsigned long bit; + struct page *page; + void *kaddr; + unsigned long chunk = block >> bitmap->counts.chunkshift; + struct bitmap_storage *store = &bitmap->storage; + unsigned long node_offset = 0; + + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * store->file_pages; + + page = filemap_get_page(&bitmap->storage, chunk); + if (!page) + return; + bit = file_page_offset(&bitmap->storage, chunk); + + /* set the bit */ + kaddr = kmap_atomic(page); + if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) + set_bit(bit, kaddr); + else + set_bit_le(bit, kaddr); + kunmap_atomic(kaddr); + pr_debug("set file bit %lu page %lu\n", bit, page->index); + /* record page number so it gets flushed to disk when unplug occurs */ + set_page_attr(bitmap, page->index - node_offset, BITMAP_PAGE_DIRTY); +} + +static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block) +{ + unsigned long bit; + struct page *page; + void *paddr; + unsigned long chunk = block >> bitmap->counts.chunkshift; + struct bitmap_storage *store = &bitmap->storage; + unsigned long node_offset = 0; + + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * store->file_pages; + + page = filemap_get_page(&bitmap->storage, chunk); + if (!page) + return; + bit = file_page_offset(&bitmap->storage, chunk); + paddr = kmap_atomic(page); + if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) + clear_bit(bit, paddr); + else + clear_bit_le(bit, paddr); + kunmap_atomic(paddr); + if (!test_page_attr(bitmap, page->index - node_offset, BITMAP_PAGE_NEEDWRITE)) { + set_page_attr(bitmap, page->index - node_offset, BITMAP_PAGE_PENDING); + bitmap->allclean = 0; + } +} + +static int bitmap_file_test_bit(struct bitmap *bitmap, sector_t block) +{ + unsigned long bit; + struct page *page; + void *paddr; + unsigned long chunk = block >> bitmap->counts.chunkshift; + int set = 0; + + page = filemap_get_page(&bitmap->storage, chunk); + if (!page) + return -EINVAL; + bit = file_page_offset(&bitmap->storage, chunk); + paddr = kmap_atomic(page); + if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) + set = test_bit(bit, paddr); + else + set = test_bit_le(bit, paddr); + kunmap_atomic(paddr); + return set; +} + + +/* 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 */ +void bitmap_unplug(struct bitmap *bitmap) +{ + unsigned long i; + int dirty, need_write; + int writing = 0; + + if (!bitmap || !bitmap->storage.filemap || + test_bit(BITMAP_STALE, &bitmap->flags)) + return; + + /* look at each page to see if there are any set bits that need to be + * flushed out to disk */ + for (i = 0; i < bitmap->storage.file_pages; i++) { + if (!bitmap->storage.filemap) + return; + dirty = test_and_clear_page_attr(bitmap, i, BITMAP_PAGE_DIRTY); + need_write = test_and_clear_page_attr(bitmap, i, + BITMAP_PAGE_NEEDWRITE); + if (dirty || need_write) { + if (!writing) { + bitmap_wait_writes(bitmap); + if (bitmap->mddev->queue) + blk_add_trace_msg(bitmap->mddev->queue, + "md bitmap_unplug"); + } + clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING); + write_page(bitmap, bitmap->storage.filemap[i], 0); + writing = 1; + } + } + if (writing) + bitmap_wait_writes(bitmap); + + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) + bitmap_file_kick(bitmap); +} +EXPORT_SYMBOL(bitmap_unplug); + +static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed); +/* * bitmap_init_from_disk -- called at bitmap_create time to initialize + * the in-memory bitmap from the on-disk bitmap -- also, sets up the + * memory mapping of the bitmap file + * Special cases: + * if there's no bitmap file, or if the bitmap file had been + * previously kicked from the array, we mark all the bits as + * 1's in order to cause a full resync. + * + * We ignore all bits for sectors that end earlier than 'start'. + * This is used when reading an out-of-date bitmap... + */ +static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) +{ + unsigned long i, chunks, index, oldindex, bit, node_offset = 0; + struct page *page = NULL; + unsigned long bit_cnt = 0; + struct file *file; + unsigned long offset; + int outofdate; + int ret = -ENOSPC; + void *paddr; + struct bitmap_storage *store = &bitmap->storage; + + chunks = bitmap->counts.chunks; + file = store->file; + + if (!file && !bitmap->mddev->bitmap_info.offset) { + /* No permanent bitmap - fill with '1s'. */ + store->filemap = NULL; + store->file_pages = 0; + for (i = 0; i < chunks ; i++) { + /* if the disk bit is set, set the memory bit */ + int needed = ((sector_t)(i+1) << (bitmap->counts.chunkshift) + >= start); + bitmap_set_memory_bits(bitmap, + (sector_t)i << bitmap->counts.chunkshift, + needed); + } + return 0; + } + + outofdate = test_bit(BITMAP_STALE, &bitmap->flags); + if (outofdate) + pr_warn("%s: bitmap file is out of date, doing full recovery\n", bmname(bitmap)); + + if (file && i_size_read(file->f_mapping->host) < store->bytes) { + pr_warn("%s: bitmap file too short %lu < %lu\n", + bmname(bitmap), + (unsigned long) i_size_read(file->f_mapping->host), + store->bytes); + goto err; + } + + oldindex = ~0L; + offset = 0; + if (!bitmap->mddev->bitmap_info.external) + offset = sizeof(bitmap_super_t); + + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * (DIV_ROUND_UP(store->bytes, PAGE_SIZE)); + + f |