diff options
Diffstat (limited to 'drivers/md/bitmap.c')
| -rw-r--r-- | drivers/md/bitmap.c | 2608 |
1 files changed, 1617 insertions, 991 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 01654fcabc5..67f8b31e205 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -7,129 +7,34 @@ * 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) */ /* * Still to do: * * 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 <linux/blkdev.h> #include <linux/module.h> -#include <linux/version.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> -#include <linux/config.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/raid/md.h> -#include <linux/raid/bitmap.h> +#include <linux/seq_file.h> +#include "md.h" +#include "bitmap.h" -/* debug macros */ - -#define DEBUG 0 - -#if DEBUG -/* these are for debugging purposes only! */ - -/* define one and only one of these */ -#define INJECT_FAULTS_1 0 /* cause bitmap_alloc_page to fail always */ -#define INJECT_FAULTS_2 0 /* cause bitmap file to be kicked when first bit set*/ -#define INJECT_FAULTS_3 0 /* treat bitmap file as kicked at init time */ -#define INJECT_FAULTS_4 0 /* undef */ -#define INJECT_FAULTS_5 0 /* undef */ -#define INJECT_FAULTS_6 0 - -/* if these are defined, the driver will fail! debug only */ -#define INJECT_FATAL_FAULT_1 0 /* fail kmalloc, causing bitmap_create to fail */ -#define INJECT_FATAL_FAULT_2 0 /* undef */ -#define INJECT_FATAL_FAULT_3 0 /* undef */ -#endif - -//#define DPRINTK PRINTK /* set this NULL to avoid verbose debug output */ -#define DPRINTK(x...) do { } while(0) - -#ifndef PRINTK -# if DEBUG > 0 -# define PRINTK(x...) printk(KERN_DEBUG x) -# else -# define PRINTK(x...) -# endif -#endif - -static inline char * bmname(struct bitmap *bitmap) +static inline char *bmname(struct bitmap *bitmap) { return bitmap->mddev ? mdname(bitmap->mddev) : "mdX"; } - -/* - * 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) -{ - unsigned char *page; - -#ifdef INJECT_FAULTS_1 - page = NULL; -#else - page = kmalloc(PAGE_SIZE, GFP_NOIO); -#endif - if (!page) - printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap)); - else - PRINTK("%s: bitmap_alloc_page: allocated page at %p\n", - bmname(bitmap), page); - return page; -} - -/* - * for now just a placeholder -- just calls kfree for bitmap pages - */ -static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page) -{ - PRINTK("%s: bitmap_free_page: free page %p\n", bmname(bitmap), page); - kfree(page); -} - /* * check a page and, if necessary, allocate it (or hijack it if the alloc fails) * @@ -140,18 +45,21 @@ static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page) * 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 *bitmap, unsigned long page, int create) +static int bitmap_checkpage(struct bitmap_counts *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; } - if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */ return 0; @@ -161,47 +69,37 @@ static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int creat if (!create) return -ENOENT; - spin_unlock_irq(&bitmap->lock); - /* this page has not been allocated yet */ - if ((mappage = bitmap_alloc_page(bitmap)) == NULL) { - PRINTK("%s: bitmap map page allocation failed, hijacking\n", - bmname(bitmap)); + spin_unlock_irq(&bitmap->lock); + mappage = kzalloc(PAGE_SIZE, GFP_NOIO); + spin_lock_irq(&bitmap->lock); + + if (mappage == NULL) { + pr_debug("md/bitmap: map page allocation failed, hijacking\n"); /* failed - set the hijacked flag so that we can use the * pointer as a counter */ - spin_lock_irq(&bitmap->lock); if (!bitmap->bp[page].map) bitmap->bp[page].hijacked = 1; - goto out; - } - - /* got a page */ - - spin_lock_irq(&bitmap->lock); - - /* recheck the page */ - - if (bitmap->bp[page].map || bitmap->bp[page].hijacked) { + } else if (bitmap->bp[page].map || + bitmap->bp[page].hijacked) { /* somebody beat us to getting the page */ - bitmap_free_page(bitmap, mappage); + kfree(mappage); return 0; - } + } else { - /* no page was in place and we have one, so install it */ + /* no page was in place and we have one, so install it */ - memset(mappage, 0, PAGE_SIZE); - bitmap->bp[page].map = mappage; - bitmap->missing_pages--; -out: + 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 inline void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) +static void bitmap_checkfree(struct bitmap_counts *bitmap, unsigned long page) { char *ptr; @@ -213,178 +111,285 @@ static inline void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */ bitmap->bp[page].hijacked = 0; bitmap->bp[page].map = NULL; - return; + } else { + /* normal case, free the page */ + ptr = bitmap->bp[page].map; + bitmap->bp[page].map = NULL; + bitmap->missing_pages++; + kfree(ptr); } - - /* normal case, free the page */ - -#if 0 -/* actually ... let's not. We will probably need the page again exactly when - * memory is tight and we are flusing to disk - */ - return; -#else - ptr = bitmap->bp[page].map; - bitmap->bp[page].map = NULL; - bitmap->missing_pages++; - bitmap_free_page(bitmap, ptr); - return; -#endif } - /* * 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 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 */ - mdk_rdev_t *rdev; - struct list_head *tmp; - struct page *page = alloc_page(GFP_KERNEL); + struct md_rdev *rdev; sector_t target; - if (!page) - return ERR_PTR(-ENOMEM); - - ITERATE_RDEV(mddev, rdev, tmp) { - if (! rdev->in_sync || rdev->faulty) + rdev_for_each(rdev, mddev) { + if (! test_bit(In_sync, &rdev->flags) + || test_bit(Faulty, &rdev->flags)) continue; - target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512); + target = offset + index * (PAGE_SIZE/512); - if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) { + if (sync_page_io(rdev, target, + roundup(size, bdev_logical_block_size(rdev->bdev)), + page, READ, true)) { page->index = index; - return page; + return 0; } } - return ERR_PTR(-EIO); - + return -EIO; } -static int write_sb_page(mddev_t *mddev, long offset, struct page *page, int wait) +static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *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_entry_continue_rcu. + */ + rcu_read_lock(); + if (rdev == NULL) + /* start at the beginning */ + rdev = list_entry_rcu(&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; +} - ITERATE_RDEV(mddev, rdev, tmp) - if (rdev->in_sync && !rdev->faulty) - md_super_write(mddev, rdev, - (rdev->sb_offset<<1) + offset - + page->index * (PAGE_SIZE/512), - PAGE_SIZE, - page); +static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) +{ + struct md_rdev *rdev = NULL; + struct block_device *bdev; + struct mddev *mddev = bitmap->mddev; + struct bitmap_storage *store = &bitmap->storage; + + 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) - 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->storage.file == NULL) { + switch (write_sb_page(bitmap, page, wait)) { + case -EINVAL: + set_bit(BITMAP_WRITE_ERROR, &bitmap->flags); + } + } 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 | REQ_SYNC, bh); + bh = bh->b_this_page; } - } - 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 (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); +} - 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); +/* 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; + + if (!PagePrivate(page)) + return; + + bh = page_buffers(page); + 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 */ -static struct page *read_page(struct file *file, unsigned long index, - unsigned long *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 int read_page(struct file *file, unsigned long index, + struct bitmap *bitmap, + unsigned long count, + struct page *page) { - 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; + int ret = 0; + struct inode *inode = file_inode(file); + 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); + pr_debug("read bitmap file (%dB @ %llu)\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); - 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<<inode->i_blkbits, 0); + 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(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 (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) + ret = -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, - PTR_ERR(page)); - return page; + if (ret) + printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %d\n", + (int)PAGE_SIZE, + (unsigned long long)index << PAGE_SHIFT, + ret); + return ret; } /* @@ -392,25 +397,33 @@ 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; - spin_lock_irqsave(&bitmap->lock, flags); - if (!bitmap->sb_page) { /* no superblock */ - spin_unlock_irqrestore(&bitmap->lock, flags); - return 0; - } - spin_unlock_irqrestore(&bitmap->lock, flags); - sb = (bitmap_super_t *)kmap(bitmap->sb_page); + 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->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); + sb->state = cpu_to_le32(bitmap->flags); + /* 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->sectors_reserved = cpu_to_le32(bitmap->mddev-> + bitmap_info.space); + kunmap_atomic(sb); + write_page(bitmap, bitmap->storage.sb_page, 1); } /* print out the bitmap file superblock */ @@ -418,9 +431,9 @@ void bitmap_print_sb(struct bitmap *bitmap) { bitmap_super_t *sb; - if (!bitmap || !bitmap->sb_page) + if (!bitmap || !bitmap->storage.sb_page) return; - sb = (bitmap_super_t *)kmap(bitmap->sb_page); + sb = kmap_atomic(bitmap->storage.sb_page); 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)); @@ -439,7 +452,76 @@ 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); +} + +/* + * 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); + 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); + printk(KERN_ERR "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 < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) { + printk(KERN_INFO "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); + + kunmap_atomic(sb); + + return 0; } /* read the superblock from the bitmap file and initialize some bitmap fields */ @@ -448,47 +530,59 @@ 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; + unsigned long sectors_reserved = 0; int err = -EINVAL; - + struct page *sb_page; + + 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... */ - 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; + sb_page = alloc_page(GFP_KERNEL); + if (!sb_page) + return -ENOMEM; + bitmap->storage.sb_page = sb_page; + + 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, + bitmap->mddev->bitmap_info.offset, + sb_page, + 0, sizeof(bitmap_super_t)); } - if (IS_ERR(bitmap->sb_page)) { - err = PTR_ERR(bitmap->sb_page); - bitmap->sb_page = NULL; + if (err) 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 = kmap_atomic(sb_page); 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); + sectors_reserved = le32_to_cpu(sb->sectors_reserved); /* verify that the bitmap-specific fields are valid */ if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) reason = "bad magic"; - else if (sb->version != cpu_to_le32(BITMAP_MAJOR)) + 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 ((1 << ffz(~chunksize)) != chunksize) + 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 > 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) { @@ -500,190 +594,169 @@ static int bitmap_read_sb(struct bitmap *bitmap) /* 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) - goto success; - - /* - * if we have a persistent array superblock, compare the - * bitmap's UUID and event counter to the mddev's - */ - if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) { - printk(KERN_INFO "%s: bitmap superblock UUID mismatch\n", - bmname(bitmap)); - goto out; - } - events = le64_to_cpu(sb->events); - if (events < bitmap->mddev->events) { - 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; + 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)) { + printk(KERN_INFO + "%s: bitmap superblock UUID mismatch\n", + bmname(bitmap)); + goto out; + } + events = le64_to_cpu(sb->events); + if (events < bitmap->mddev->events) { + 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); + set_bit(BITMAP_STALE, &bitmap->flags); + } } -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->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); - if (sb->state & BITMAP_STALE) - bitmap->events_cleared = bitmap->mddev->events; err = 0; out: - kunmap(bitmap->sb_page); + kunmap_atomic(sb); +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; + 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); return err; } -enum bitmap_mask_op { - MASK_SET, - 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) -{ - bitmap_super_t *sb; - unsigned long flags; - - spin_lock_irqsave(&bitmap->lock, flags); - if (!bitmap || !bitmap->sb_page) { /* can't set the state */ - spin_unlock_irqrestore(&bitmap->lock, flags); - return; - } - page_cache_get(bitmap->sb_page); - spin_unlock_irqrestore(&bitmap->lock, flags); - sb = (bitmap_super_t *)kmap(bitmap->sb_page); - switch (op) { - case MASK_SET: sb->state |= bits; - break; - case MASK_UNSET: sb->state &= ~bits; - break; - default: BUG(); - } - kunmap(bitmap->sb_page); - page_cache_release(bitmap->sb_page); -} - /* * 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_storage *store, + unsigned long chunk) { - return CHUNK_BIT_OFFSET(chunk) >> PAGE_BIT_SHIFT; + 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(unsigned long chunk) +static inline unsigned long file_page_offset(struct bitmap_storage *store, + unsigned long chunk) { - return CHUNK_BIT_OFFSET(chunk) & (PAGE_BITS - 1); + 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 * - * this lookup is complicated by the fact that the bitmap sb might be exactly - * 1 page (e.g., x86) or less than 1 page -- so the bitmap might start on page - * 0 or page 1 */ -static inline struct page *filemap_get_page(struct bitmap *bitmap, - unsigned long chunk) +static inline struct page *filemap_get_page(struct bitmap_storage *store, + unsigned long chunk) { - return bitmap->filemap[file_page_index(chunk) - file_page_index(0)]; + if (file_page_index(store, chunk) >= store->file_pages) + return NULL; + return store->filemap[file_page_index(store, chunk)]; } - -static void bitmap_file_unmap(struct bitmap *bitmap) +static int bitmap_storage_alloc(struct bitmap_storage *store, + unsigned long chunks, int with_super) { - struct page **map, *sb_page; - unsigned long *attr; - int pages; - unsigned long flags; - - spin_lock_irqsave(&bitmap->lock, flags); - map = bitmap->filemap; - bitmap->filemap = NULL; - attr = bitmap->filemap_attr; - bitmap->filemap_attr = NULL; - pages = bitmap->file_pages; - bitmap->file_pages = 0; - sb_page = bitmap->sb_page; - bitmap->sb_page = NULL; - 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]); - kfree(map); - kfree(attr); - - if (sb_page) - page_cache_release(sb_page); -} + int pnum; + unsigned long num_pages; + unsigned long bytes; -static void bitmap_stop_daemon(struct bitmap *bitmap); + bytes = DIV_ROUND_UP(chunks, 8); + if (with_super) + bytes += sizeof(bitmap_super_t); -/* 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; + num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE); - 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; + store->filemap = kmalloc(sizeof(struct page *) + * num_pages, GFP_KERNEL); + if (!store->filemap) + return -ENOMEM; - while ((item = dequeue_page(bitmap))) { - /* don't bother to wait */ - page_cache_release(item->page); - mempool_free(item, bitmap->write_pool); + if (with_super && !store->sb_page) { + store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO); + if (store->sb_page == NULL) + return -ENOMEM; + store->sb_page->index = 0; + } + pnum = 0; + if (store->sb_page) { + store->filemap[0] = store->sb_page; + pnum = 1; } + 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; + } + 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; - wake_up(&bitmap->write_wait); + store->bytes = bytes; + + return 0; } -static void bitmap_file_put(struct bitmap *bitmap) +static void bitmap_file_unmap(struct bitmap_storage *store) { + struct page **map, *sb_page; + int pages; struct file *file; - struct inode *inode; - unsigned long flags; - - spin_lock_irqsave(&bitmap->lock, flags); - file = bitmap->file; - bitmap->file = NULL; - spin_unlock_irqrestore(&bitmap->lock, flags); - bitmap_stop_daemon(bitmap); + file = store->file; + map = store->filemap; + pages = store->file_pages; + sb_page = store->sb_page; - drain_write_queues(bitmap); + while (pages--) + if (map[pages] != sb_page) /* 0 is sb_page, release it below */ + free_buffers(map[pages]); + kfree(map); + kfree(store->filemap_attr); - bitmap_file_unmap(bitmap); + if (sb_page) + free_buffers(sb_page); 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_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 @@ -693,48 +766,58 @@ 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 (!test_and_set_bit(BITMAP_STALE, &bitmap->flags)) { + 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->storage.file) { + path = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (path) + ptr = d_path(&bitmap->storage.file->f_path, + path, PAGE_SIZE); - printk(KERN_ALERT "%s: kicking failed bitmap file %s from array!\n", - bmname(bitmap), ptr ? ptr : ""); + printk(KERN_ALERT + "%s: kicking failed bitmap file %s from array!\n", + bmname(bitmap), IS_ERR(ptr) ? "" : ptr); - kfree(path); + kfree(path); + } else + printk(KERN_ALERT + "%s: disabling internal bitmap due to errors\n", + bmname(bitmap)); } - - bitmap_file_put(bitmap); - - return; } 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_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, struct page *page, - enum bitmap_page_attr attr) +static inline void set_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) { - bitmap->filemap_attr[page->index] |= attr; + set_bit((pnum<<2) + attr, bitmap->storage.filemap_attr); } -static inline void clear_page_attr(struct bitmap *bitmap, struct page *page, - enum bitmap_page_attr attr) +static inline void clear_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) { - bitmap->filemap_attr[page->index] &= ~attr; + clear_bit((pnum<<2) + attr, bitmap->storage.filemap_attr); } -static inline unsigned long get_page_attr(struct bitmap *bitmap, struct page *page) +static inline int test_page_attr(struct bitmap *bitmap, int pnum, + enum bitmap_page_attr attr) { - return bitmap->filemap_attr[page->index]; + 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 @@ -747,85 +830,87 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) unsigned long bit; struct page *page; void *kaddr; - unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap); + unsigned long chunk = block >> bitmap->counts.chunkshift; - if (!bitmap->filemap) { + page = filemap_get_page(&bitmap->storage, chunk); + if (!page) return; - } - - 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); - - /* set the bit */ - kaddr = kmap_atomic(page, KM_USER0); - set_bit(bit, kaddr); - kunmap_atomic(kaddr, KM_USER0); - PRINTK("set file bit %lu page %lu\n", bit, page->index); + 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, BITMAP_PAGE_DIRTY); + set_page_attr(bitmap, page->index, 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; + + 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, BITMAP_PAGE_NEEDWRITE)) { + set_page_attr(bitmap, page->index, BITMAP_PAGE_PENDING); + bitmap->allclean = 0; + } } /* 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; - struct page *page; + unsigned long i; + int dirty, need_write; int wait = 0; - int err; - if (!bitmap) - return 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->file_pages; i++) { - spin_lock_irqsave(&bitmap->lock, flags); - if (!bitmap->filemap) { - spin_unlock_irqrestore(&bitmap->lock, flags); - return 0; + 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) { + clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING); + write_page(bitmap, bitmap->storage.filemap[i], 0); } - page = bitmap->filemap[i]; - attr = get_page_attr(bitmap, page); - 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 (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->storage.file) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + else + md_super_wait(bitmap->mddev); } - return 0; + 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 @@ -842,129 +927,123 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) { unsigned long i, chunks, index, oldindex, bit; - struct page *page = NULL, *oldpage = NULL; - unsigned long num_pages, bit_cnt = 0; + struct page *page = NULL; + unsigned long bit_cnt = 0; struct file *file; - unsigned long bytes, offset, dummy; + unsigned long offset; int outofdate; int ret = -ENOSPC; + void *paddr; + struct bitmap_storage *store = &bitmap->storage; - chunks = bitmap->chunks; - file = bitmap->file; + chunks = bitmap->counts.chunks; + file = store->file; - BUG_ON(!file && !bitmap->offset); + 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; + } -#ifdef INJECT_FAULTS_3 - outofdate = 1; -#else - outofdate = bitmap->flags & BITMAP_STALE; -#endif + outofdate = test_bit(BITMAP_STALE, &bitmap->flags); if (outofdate) printk(KERN_INFO "%s: bitmap file is out of date, doing full " "recovery\n", bmname(bitmap)); - bytes = (chunks + 7) / 8; - - num_pages = (bytes + sizeof(bitmap_super_t) + 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) < store->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; + bmname(bitmap), + (unsigned long) i_size_read(file->f_mapping->host), + store->bytes); + goto err; } - ret = -ENOMEM; - - bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL); - if (!bitmap->filemap) - goto out; - - bitmap->filemap_attr = kmalloc(sizeof(long) * num_pages, GFP_KERNEL); - if (!bitmap->filemap_attr) - goto out; - - memset(bitmap->filemap_attr, 0, sizeof(long) * num_pages); - oldindex = ~0L; + offset = 0; + if (!bitmap->mddev->bitmap_info.external) + offset = sizeof(bitmap_super_t); for (i = 0; i < chunks; i++) { - index = file_page_index(i); - bit = file_page_offset(i); + int b; + index = file_page_index(&bitmap->storage, i); + bit = file_page_offset(&bitmap->storage, 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 we're here then the superblock page - * contains some bits (PAGE_SIZE != sizeof sb) - * we've already read it in, so just use it - */ - page = bitmap->sb_page; - offset = sizeof(bitmap_super_t); - } else if (file) { - page = read_page(file, index, &dummy); - offset = 0; - } else { - page = read_sb_page(bitmap->mddev, bitmap->offset, index); - offset = 0; - } - if (IS_ERR(page)) { /* read error */ - ret = PTR_ERR(page); - goto out; - } + if (index == store->file_pages-1) + count = store->bytes - index * PAGE_SIZE; + else + count = PAGE_SIZE; + page = store->filemap[index]; + if (file) + ret = read_page(file, index, bitmap, + count, page); + else + ret = read_sb_page( + bitmap->mddev, + bitmap->mddev->bitmap_info.offset, + page, + index, count); + + if (ret) + goto err; oldindex = index; - oldpage = page; - kmap(page); if (outofdate) { /* * if bitmap is out of date, dirty the - * whole page and write it out + * whole page and write it out */ - memset(page_address(page) + offset, 0xff, + paddr = kmap_atomic(page); + 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); + write_page(bitmap, page, 1); - bitmap->filemap[bitmap->file_pages++] = page; + ret = -EIO; + if (test_bit(BITMAP_WRITE_ERROR, + &bitmap->flags)) + goto err; + } } - if (test_bit(bit, page_address(page))) { + paddr = kmap_atomic(page); + if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) + b = test_bit(bit, paddr); + else + b = test_bit_le(bit, paddr); + kunmap_atomic(paddr); + 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) << bitmap->counts.chunkshift + >= start); + bitmap_set_memory_bits(bitmap, + (sector_t)i << bitmap->counts.chunkshift, + needed); bit_cnt++; - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } + offset = 0; } - /* everything went OK */ - 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 pages, set %lu of %lu bits\n", + bmname(bitmap), store->file_pages, + bit_cnt, chunks); + return 0; + + err: + printk(KERN_INFO "%s: bitmap initialisation failed: %d\n", + bmname(bitmap), ret); return ret; } @@ -973,28 +1052,41 @@ 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; -} + if (!bitmap || !bitmap->storage.filemap) + return; + if (bitmap->storage.file) + /* Only one copy, so nothing needed */ + return; + for (i = 0; i < bitmap->storage.file_pages; i++) + set_page_attr(bitmap, i, + BITMAP_PAGE_NEEDWRITE); + bitmap->allclean = 0; +} -static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc) +static void bitmap_count_page(struct bitmap_counts *bitmap, + sector_t offset, int inc) { - sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap); + sector_t chunk = offset >> bitmap->chunkshift; unsigned long page = chunk >> PAGE_COUNTER_SHIFT; bitmap->bp[page].count += inc; -/* - if (page == 0) printk("count page 0, offset %llu: %d gives %d\n", - (unsigned long long)offset, inc, bitmap->bp[page].count); -*/ bitmap_checkfree(bitmap, page); } -static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap, - sector_t offset, int *blocks, + +static void bitmap_set_pending(struct bitmap_counts *bitmap, sector_t offset) +{ + sector_t chunk = offset >> bitmap->chunkshift; + unsigned long page = chunk >> PAGE_COUNTER_SHIFT; + struct bitmap_page *bp = &bitmap->bp[page]; + + if (!bp->pending) + bp->pending = 1; +} + +static bitmap_counter_t *bitmap_get_counter(struct bitmap_counts *bitmap, + sector_t offset, sector_t *blocks, int create); /* @@ -1002,356 +1094,289 @@ static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap, * out to disk */ -int bitmap_daemon_work(struct bitmap *bitmap) +void bitmap_daemon_work(struct mddev *mddev) { + struct bitmap *bitmap; unsigned long j; - unsigned long flags; - struct page *page = NULL, *lastpage = NULL; - int err = 0; - int blocks; - int attr; + unsigned long nextpage; + sector_t blocks; + struct bitmap_counts *counts; + + /* 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 + + 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) { + mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + goto done; + } + bitmap->allclean = 1; - for (j = 0; j < bitmap->chunks; j++) { - bitmap_counter_t *bmc; - spin_lock_irqsave(&bitmap->lock, flags); - if (!bitmap->filemap) { - /* error or shutdown */ - spin_unlock_irqrestore(&bitmap->lock, flags); - break; + /* Any file-page which is PENDING now needs to be written. + * So set NEEDWRITE now, then after we make any last-minute changes + * we will write it. + */ + for (j = 0; j < bitmap->storage.file_pages; j++) + if (test_and_clear_page_attr(bitmap, j, + BITMAP_PAGE_PENDING)) + set_page_attr(bitmap, j, + BITMAP_PAGE_NEEDWRITE); + + if (bitmap->need_sync && + mddev->bitmap_info.external == 0) { + /* Arrange for superblock update as well as + * other changes */ + bitmap_super_t *sb; + bitmap->need_sync = 0; + if (bitmap->storage.filemap) { + sb = kmap_atomic(bitmap->storage.sb_page); + sb->events_cleared = + cpu_to_le64(bitmap->events_cleared); + kunmap_atomic(sb); + set_page_attr(bitmap, 0, + BITMAP_PAGE_NEEDWRITE); } + } + /* Now look at the bitmap counters and if any are '2' or '1', + * decrement and handle accordingly. + */ + counts = &bitmap->counts; + spin_lock_irq(&counts->lock); + nextpage = 0; + for (j = 0; j < counts->chunks; j++) { + bitmap_counter_t *bmc; + sector_t block = (sector_t)j << counts->chunkshift; - 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); - 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 (j == nextpage) { + nextpage += PAGE_COUNTER_RATIO; + if (!counts->bp[j >> PAGE_COUNTER_SHIFT].pending) { + j |= PAGE_COUNTER_MASK; 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) { - 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); - } - } 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); -*/ - spin_lock_irqsave(&bitmap->lock, flags); - clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); - } - bmc = bitmap_get_counter(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap), - &blocks, 0); - if (bmc) { -/* - if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc); -*/ - if (*bmc == 2) { - *bmc=1; /* maybe clear the bit next time */ - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); - } else if (*bmc == 1) { - /* we can clear the bit */ - *bmc = 0; - bitmap_count_page(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap), - -1); - - /* clear the bit */ - clear_bit(file_page_offset(j), page_address(page)); - } + counts->bp[j >> PAGE_COUNTER_SHIFT].pending = 0; } - spin_unlock_irqrestore(&bitmap->lock, flags); - } + bmc = bitmap_get_counter(counts, + block, + &blocks, 0); - /* 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) { - 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; - } - } else { - set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); - spin_unlock_irqrestore(&bitmap->lock, flags); + if (!bmc) { + j |= PAGE_COUNTER_MASK; + continue; } - - 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; + if (*bmc == 1 && !bitmap->need_sync) { + /* We can clear the bit */ + *bmc = 0; + bitmap_count_page(counts, block, -1); + bitmap_file_clear_bit(bitmap, block); + } else if (*bmc && *bmc <= 2) { + *bmc = 1; + bitmap_set_pending(counts, block); + bitmap->allclean = 0; } } - 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); + spin_unlock_irq(&counts->lock); + + /* Now start writeout on any page in NEEDWRITE that isn't DIRTY. + * DIRTY pages need to be written by bitmap_unplug so it can wait + * for them. + * If we find any DIRTY page we stop there and let bitmap_unplug + * handle all the rest. This is important in the case where + * the first blocking holds the superblock and it has been updated. + * We mustn't write any other blocks before the superblock. + */ + for (j = 0; + j < bitmap->storage.file_pages + && !test_bit(BITMAP_STALE, &bitmap->flags); + j++) { + + if (test_page_attr(bitmap, j, + BITMAP_PAGE_DIRTY)) + /* bitmap_unplug will handle the rest */ + break; + if (test_and_clear_page_attr(bitmap, j, + BITMAP_PAGE_NEEDWRITE)) { + write_page(bitmap, bitmap->storage.filemap[j], 0); + } } - 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) + mddev->thread->timeout = + 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, +static bitmap_counter_t *bitmap_get_counter(struct bitmap_counts *bitmap, + sector_t offset, sector_t *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. * If !create, we don't release the lock. */ - sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap); + sector_t chunk = offset >> bitmap->chunkshift; unsigned long page = chunk >> PAGE_COUNTER_SHIFT; unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT; sector_t csize; + int err; + + err = bitmap_checkpage(bitmap, page, create); - if (bitmap_checkpage(bitmap, page, create) < 0) { - csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap)); - *blocks = csize - (offset & (csize- 1)); + if (bitmap->bp[page].hijacked || + bitmap->bp[page].map == NULL) + csize = ((sector_t)1) << (bitmap->chunkshift + + PAGE_COUNTER_SHIFT - 1); + else + csize = ((sector_t)1) << bitmap->chunkshift; + *blocks = csize - (offset & (csize - 1)); + + if (err < 0) return NULL; - } + /* now locked ... */ if (bitmap->bp[page].hijacked) { /* hijacked pointer */ /* should we use the first or second counter field * of the hijacked pointer? */ int hi = (pageoff > PAGE_COUNTER_MASK); - csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) + - PAGE_COUNTER_SHIFT - 1); - *blocks = csize - (offset & (csize- 1)); return &((bitmap_counter_t *) &bitmap->bp[page].map)[hi]; - } else { /* page is allocated */ - csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap)); - *blocks = csize - (offset & (csize- 1)); + } else /* page is allocated */ return (bitmap_counter_t *) &(bitmap->bp[page].map[pageoff]); - } } int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind) { - if (!bitmap) return 0; + if (!bitmap) + return 0; if (behind) { + int bw; atomic_inc(&bitmap->behind_writes); - PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n", - atomic_read(&bitmap->behind_writes), bitmap->max_write_behind); + bw = atomic_read(&bitmap->behind_writes); + if (bw > bitmap->behind_writes_used) + bitmap->behind_writes_used = bw; + + pr_debug("inc write-behind count %d/%lu\n", + bw, bitmap->mddev->bitmap_info.max_write_behind); } while (sectors) { - int blocks; + sector_t blocks; bitmap_counter_t *bmc; - spin_lock_irq(&bitmap->lock); - bmc = bitmap_get_counter(bitmap, offset, &blocks, 1); + spin_lock_irq(&bitmap->counts.lock); + bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 1); if (!bmc) { - spin_unlock_irq(&bitmap->lock); + spin_unlock_irq(&bitmap->counts.lock); return 0; } - switch(*bmc) { + if (unlikely(COUNTER(*bmc) == 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->counts.lock); + 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); + bitmap_count_page(&bitmap->counts, offset, 1); /* fall through */ case 1: *bmc = 2; } - if ((*bmc & COUNTER_MAX) == COUNTER_MAX) BUG(); + (*bmc)++; - spin_unlock_irq(&bitmap->lock); + spin_unlock_irq(&bitmap->counts.lock); offset += blocks; if (sectors > blocks) sectors -= blocks; - else sectors = 0; + else + sectors = 0; } return 0; } +EXPORT_SYMBOL(bitmap_startwrite); void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int success, int behind) { - if (!bitmap) return; + if (!bitmap) + return; if (behind) { - atomic_dec(&bitmap->behind_writes); - PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n", - atomic_read(&bitmap->behind_writes), bitmap->max_write_behind); + if (atomic_dec_and_test(&bitmap->behind_writes)) + wake_up(&bitmap->behind_wait); + pr_debug("dec write-behind count %d/%lu\n", + atomic_read(&bitmap->behind_writes), + bitmap->mddev->bitmap_info.max_write_behind); } while (sectors) { - int blocks; + sector_t blocks; unsigned long flags; bitmap_counter_t *bmc; - spin_lock_irqsave(&bitmap->lock, flags); - bmc = bitmap_get_counter(bitmap, offset, &blocks, 0); + spin_lock_irqsave(&bitmap->counts.lock, flags); + bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 0); if (!bmc) { - spin_unlock_irqrestore(&bitmap->lock, flags); + spin_unlock_irqrestore(&bitmap->counts.lock, flags); return; } - if (!success && ! (*bmc & NEEDED_MASK)) + if (success && !bitmap->mddev->degraded && + bitmap->events_cleared < bitmap->mddev->events) { + bitmap->events_cleared = bitmap->mddev->events; + bitmap->need_sync = 1; + sysfs_notify_dirent_safe(bitmap->sysfs_can_clear); + } + + if (!success && !NEEDED(*bmc)) *bmc |= NEEDED_MASK; + if (COUNTER(*bmc) == COUNTER_MAX) + wake_up(&bitmap->overflow_wait); + (*bmc)--; if (*bmc <= 2) { - set_page_attr(bitmap, - filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)), - BITMAP_PAGE_CLEAN); + bitmap_set_pending(&bitmap->counts, offset); + bitmap->allclean = 0; } - spin_unlock_irqrestore(&bitmap->lock, flags); + spin_unlock_irqrestore(&bitmap->counts.lock, flags); offset += blocks; if (sectors > blocks) sectors -= blocks; - else sectors = 0; + else + sectors = 0; } } +EXPORT_SYMBOL(bitmap_endwrite); -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, sector_t *blocks, + int degraded) { bitmap_counter_t *bmc; int rv; @@ -1359,8 +1384,8 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, *blocks = 1024; return 1; /* always resync if no bitmap */ } - spin_lock_irq(&bitmap->lock); - bmc = bitmap_get_counter(bitmap, offset, blocks, 0); + spin_lock_irq(&bitmap->counts.lock); + bmc = bitmap_get_counter(&bitmap->counts, offset, blocks, 0); rv = 0; if (bmc) { /* locked */ @@ -1374,28 +1399,48 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, } } } - spin_unlock_irq(&bitmap->lock); + spin_unlock_irq(&bitmap->counts.lock); return rv; } -void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted) +int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *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; + sector_t blocks1; + + *blocks = 0; + while (*blocks < (PAGE_SIZE>>9)) { + rv |= __bitmap_start_sync(bitmap, offset, + &blocks1, degraded); + offset += blocks1; + *blocks += blocks1; + } + return rv; +} +EXPORT_SYMBOL(bitmap_start_sync); + +void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted) { bitmap_counter_t *bmc; unsigned long flags; -/* - if (offset == 0) printk("bitmap_end_sync 0 (%d)\n", aborted); -*/ if (bitmap == NULL) { + + if (bitmap == NULL) { *blocks = 1024; return; } - spin_lock_irqsave(&bitmap->lock, flags); - bmc = bitmap_get_counter(bitmap, offset, blocks, 0); + spin_lock_irqsave(&bitmap->counts.lock, flags); + bmc = bitmap_get_counter(&bitmap->counts, offset, blocks, 0); if (bmc == NULL) goto unlock; /* locked */ -/* - if (offset == 0) printk("bitmap_end sync found 0x%x, blocks %d\n", *bmc, *blocks); -*/ if (RESYNC(*bmc)) { *bmc &= ~RESYNC_MASK; @@ -1403,15 +1448,15 @@ void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int ab *bmc |= NEEDED_MASK; else { if (*bmc <= 2) { - set_page_attr(bitmap, - filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)), - BITMAP_PAGE_CLEAN); + bitmap_set_pending(&bitmap->counts, offset); + bitmap->allclean = 0; } } } unlock: - spin_unlock_irqrestore(&bitmap->lock, flags); + spin_unlock_irqrestore(&bitmap->counts.lock, flags); } +EXPORT_SYMBOL(bitmap_end_sync); void bitmap_close_sync(struct bitmap *bitmap) { @@ -1420,50 +1465,95 @@ void bitmap_close_sync(struct bitmap *bitmap) * RESYNC bit wherever it is still on */ sector_t sector = 0; - int blocks; - if (!bitmap) return; + sector_t blocks; + 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; } } +EXPORT_SYMBOL(bitmap_close_sync); + +void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector) +{ + sector_t s = 0; + sector_t 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 = sector; + set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags); + sector &= ~((1ULL << bitmap->counts.chunkshift) - 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"); +} +EXPORT_SYMBOL(bitmap_cond_end_sync); 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 - * counter to 1 and set resync_needed. They should all + * counter to 2 and possibly set resync_needed. They should all * be 0 at this point */ - int secs; + sector_t secs; bitmap_counter_t *bmc; - spin_lock_irq(&bitmap->lock); - bmc = bitmap_get_counter(bitmap, offset, &secs, 1); + spin_lock_irq(&bitmap->counts.lock); + bmc = bitmap_get_counter(&bitmap->counts, offset, &secs, 1); if (!bmc) { - spin_unlock_irq(&bitmap->lock); + spin_unlock_irq(&bitmap->counts.lock); return; } - if (! *bmc) { - struct page *page; - *bmc = 1 | (needed?NEEDED_MASK:0); - bitmap_count_page(bitmap, offset, 1); - page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)); - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); + if (!*bmc) { + *bmc = 2 | (needed ? NEEDED_MASK : 0); + bitmap_count_page(&bitmap->counts, offset, 1); + bitmap_set_pending(&bitmap->counts, offset); + bitmap->allclean = 0; } - spin_unlock_irq(&bitmap->lock); + spin_unlock_irq(&bitmap->counts.lock); +} +/* 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 << bitmap->counts.chunkshift; + 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; + } } /* * flush out any pending updates */ -void bitmap_flush(mddev_t *mddev) +void bitmap_flush(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; - int sleep; + long sleep; if (!bitmap) /* there was no bitmap */ return; @@ -1471,12 +1561,13 @@ 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); } @@ -1491,15 +1582,17 @@ static void bitmap_free(struct bitmap *bitmap) if (!bitmap) /* there was no bitmap */ return; - /* release the bitmap file and kill the daemon */ - bitmap_file_put(bitmap); + /* Shouldn't be needed - but just in case.... */ + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes) == 0); - bp = bitmap->bp; - pages = bitmap->pages; + /* release the bitmap file */ + bitmap_file_unmap(&bitmap->storage); - /* free all allocated memory */ + bp = bitmap->counts.bp; + pages = bitmap->counts.pages; - mempool_destroy(bitmap->write_pool); + /* free all allocated memory */ if (bp) /* deallocate the page memory */ for (k = 0; k < pages; k++) @@ -1508,14 +1601,22 @@ static void bitmap_free(struct bitmap *bitmap) kfree(bp); kfree(bitmap); } -void bitmap_destroy(mddev_t *mddev) + +void bitmap_destroy(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; 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); } @@ -1524,116 +1625,641 @@ void bitmap_destroy(mddev_t *mddev) * initialize the bitmap structure * if this returns an error, bitmap_destroy must be called to do clean up */ -int bitmap_create(mddev_t *mddev) +int bitmap_create(struct mddev *mddev) { struct bitmap *bitmap; - unsigned long blocks = mddev->resync_max_sectors; - unsigned long chunks; - unsigned long pages; - struct file *file = mddev->bitmap_file; + sector_t blocks = mddev->resync_max_sectors; + struct file *file = mddev->bitmap_info.file; int err; - sector_t start; - - BUG_ON(sizeof(bitmap_super_t) != 256); + struct kernfs_node *bm = NULL; - if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */ - return 0; + BUILD_BUG_ON(sizeof(bitmap_super_t) != 256); - 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->counts.lock); + atomic_set(&bitmap->pending_writes, 0); + init_waitqueue_head(&bitmap->write_wait); + init_waitqueue_head(&bitmap->overflow_wait); + init_waitqueue_head(&bitmap->behind_wait); - spin_lock_init(&bitmap->lock); 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; + if (mddev->kobj.sd) + bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap"); + if (bm) { + bitmap->sysfs_can_clear = sysfs_get_dirent(bm, "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); + bitmap->storage.file = file; + 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) { + /* + * If 'MD_ARRAY_FIRST_USE' is set, then device-mapper is + * instructing us to create a new on-disk bitmap instance. + */ + if (test_and_clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags)) + err = bitmap_new_disk_sb(bitmap); + else + 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; + err = bitmap_resize(bitmap, blocks, mddev->bitmap_info.chunksize, 1); + if (err) + goto error; - /* now that chunksize and chunkshift are set, we can use these macros */ - chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) / - CHUNK_BLOCK_RATIO(bitmap); - pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO; + printk(KERN_INFO "created bitmap (%lu pages) for device %s\n", + bitmap->counts.pages, bmname(bitmap)); - BUG_ON(!pages); + mddev->bitmap = bitmap; + return test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; - bitmap->chunks = chunks; - bitmap->pages = pages; - bitmap->missing_pages = pages; - bitmap->counter_bits = COUNTER_BITS; + error: + bitmap_free(bitmap); + return err; +} - bitmap->syncchunk = ~0UL; +int bitmap_load(struct mddev *mddev) +{ + int err = 0; + sector_t start = 0; + sector_t sector = 0; + struct bitmap *bitmap = mddev->bitmap; -#ifdef INJECT_FATAL_FAULT_1 - bitmap->bp = NULL; -#else - bitmap->bp = kmalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL); -#endif - err = -ENOMEM; - if (!bitmap->bp) - goto error; - memset(bitmap->bp, 0, pages * sizeof(*bitmap->bp)); + if (!bitmap) + goto out; - bitmap->flags |= BITMAP_ACTIVE; + /* Clear out old bitmap info first: Either there is none, or we + * are resuming after someone else has possibly changed things, + * so we should forget old cached info. + * All chunks should be clean, but some might need_sync. + */ + while (sector < mddev->resync_max_sectors) { + sector_t blocks; + bitmap_start_sync(bitmap, sector, &blocks, 0); + sector += blocks; + } + bitmap_close_sync(bitmap); - /* now that we have some pages available, initialize the in-memory - * bitmap from the on-disk bitmap */ - start = 0; if (mddev->degraded == 0 || bitmap->events_cleared == mddev->events) - /* no need to keep dirty bits to optimise a re-add of a missing device */ + /* no need to keep dirty bits to optimise a + * re-add of a missing device */ start = mddev->recovery_cp; + + mutex_lock(&mddev->bitmap_info.mutex); err = bitmap_init_from_disk(bitmap, start); + mutex_unlock(&mddev->bitmap_info.mutex); if (err) - goto error; - - printk(KERN_INFO "created bitmap (%lu pages) for device %s\n", - pages, bmname(bitmap)); + goto out; + clear_bit(BITMAP_STALE, &bitmap->flags); - mddev->bitmap = bitmap; + /* Kick recovery in case any bits were set */ + set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery); - 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); - error: - bitmap_free(bitmap); + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) + err = -EIO; +out: return err; } +EXPORT_SYMBOL_GPL(bitmap_load); + +void bitmap_status(struct seq_file *seq, struct bitmap *bitmap) +{ + unsigned long chunk_kb; + struct bitmap_counts *counts; + + if (!bitmap) + return; + + counts = &bitmap->counts; + + chunk_kb = bitmap->mddev->bitmap_info.chunksize >> 10; + seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], " + "%lu%s chunk", + counts->pages - counts->missing_pages, + counts->pages, + (counts->pages - counts->missing_pages) + << (PAGE_SHIFT - 10), + chunk_kb ? chunk_kb : bitmap->mddev->bitmap_info.chunksize, + chunk_kb ? "KB" : "B"); + if (bitmap->storage.file) { + seq_printf(seq, ", file: "); + seq_path(seq, &bitmap->storage.file->f_path, " \t\n"); + } + + seq_printf(seq, "\n"); +} + +int bitmap_resize(struct bitmap *bitmap, sector_t blocks, + int chunksize, int init) +{ + /* If chunk_size is 0, choose an appropriate chunk size. + * Then possibly allocate new storage space. + * Then quiesce, copy bits, replace bitmap, and re-start + * + * This function is called both to set up the initial bitmap + * and to resize the bitmap while the array is active. + * If this happens as a result of the array being resized, + * chunksize will be zero, and we need to choose a suitable + * chunksize, otherwise we use what we are given. + */ + struct bitmap_storage store; + struct bitmap_counts old_counts; + unsigned long chunks; + sector_t block; + sector_t old_blocks, new_blocks; + int chunkshift; + int ret = 0; + long pages; + struct bitmap_page *new_bp; + + if (chunksize == 0) { + /* If there is enough space, leave the chunk size unchanged, + * else increase by factor of two until there is enough space. + */ + long bytes; + long space = bitmap->mddev->bitmap_info.space; + + if (space == 0) { + /* We don't know how much space there is, so limit + * to current size - in sectors. + */ + bytes = DIV_ROUND_UP(bitmap->counts.chunks, 8); + if (!bitmap->mddev->bitmap_info.external) + bytes += sizeof(bitmap_super_t); + space = DIV_ROUND_UP(bytes, 512); + bitmap->mddev->bitmap_info.space = space; + } + chunkshift = bitmap->counts.chunkshift; + chunkshift--; + do { + /* 'chunkshift' is shift from block size to chunk size */ + chunkshift++; + chunks = DIV_ROUND_UP_SECTOR_T(blocks, 1 << chunkshift); + bytes = DIV_ROUND_UP(chunks, 8); + if (!bitmap->mddev->bitmap_info.external) + bytes += sizeof(bitmap_super_t); + } while (bytes > (space << 9)); + } else + chunkshift = ffz(~chunksize) - BITMAP_BLOCK_SHIFT; + + chunks = DIV_ROUND_UP_SECTOR_T(blocks, 1 << chunkshift); + memset(&store, 0, sizeof(store)); + if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file) + ret = bitmap_storage_alloc(&store, chunks, + !bitmap->mddev->bitmap_info.external); + if (ret) + goto err; + + pages = DIV_ROUND_UP(chunks, PAGE_COUNTER_RATIO); + + new_bp = kzalloc(pages * sizeof(*new_bp), GFP_KERNEL); + ret = -ENOMEM; + if (!new_bp) { + bitmap_file_unmap(&store); + goto err; + } + + if (!init) + bitmap->mddev->pers->quiesce(bitmap->mddev, 1); + + store.file = bitmap->storage.file; + bitmap->storage.file = NULL; + + if (store.sb_page && bitmap->storage.sb_page) + memcpy(page_address(store.sb_page), + page_address(bitmap->storage.sb_page), + sizeof(bitmap_super_t)); + bitmap_file_unmap(&bitmap->storage); + bitmap->storage = store; + + old_counts = bitmap->counts; + bitmap->counts.bp = new_bp; + bitmap->counts.pages = pages; + bitmap->counts.missing_pages = pages; + bitmap->counts.chunkshift = chunkshift; + bitmap->counts.chunks = chunks; + bitmap->mddev->bitmap_info.chunksize = 1 << (chunkshift + + BITMAP_BLOCK_SHIFT); + + blocks = min(old_counts.chunks << old_counts.chunkshift, + chunks << chunkshift); + + spin_lock_irq(&bitmap->counts.lock); + for (block = 0; block < blocks; ) { + bitmap_counter_t *bmc_old, *bmc_new; + int set; + + bmc_old = bitmap_get_counter(&old_counts, block, + &old_blocks, 0); + set = bmc_old && NEEDED(*bmc_old); + + if (set) { + bmc_new = bitmap_get_counter(&bitmap->counts, block, + &new_blocks, 1); + if (*bmc_new == 0) { + /* need to set on-disk bits too. */ + sector_t end = block + new_blocks; + sector_t start = block >> chunkshift; + start <<= chunkshift; + while (start < end) { + bitmap_file_set_bit(bitmap, block); + start += 1 << chunkshift; + } + *bmc_new = 2; + bitmap_count_page(&bitmap->counts, + block, 1); + bitmap_set_pending(&bitmap->counts, + block); + } + *bmc_new |= NEEDED_MASK; + if (new_blocks < old_blocks) + old_blocks = new_blocks; + } + block += old_blocks; + } + + if (!init) { + int i; + while (block < (chunks << chunkshift)) { + bitmap_counter_t *bmc; + bmc = bitmap_get_counter(&bitmap->counts, block, + &new_blocks, 1); + if (bmc) { + /* new space. It needs to be resynced, so + * we set NEEDED_MASK. + */ + if (*bmc == 0) { + *bmc = NEEDED_MASK | 2; + bitmap_count_page(&bitmap->counts, + block, 1); + bitmap_set_pending(&bitmap->counts, + block); + } + } + block += new_blocks; + } + for (i = 0; i < bitmap->storage.file_pages; i++) + set_page_attr(bitmap, i, BITMAP_PAGE_DIRTY); + } + spin_unlock_irq(&bitmap->counts.lock); + + if (!init) { + bitmap_unplug(bitmap); + bitmap->mddev->pers->quiesce(bitmap->mddev, 0); + } + ret = 0; +err: + return ret; +} +EXPORT_SYMBOL_GPL(bitmap_resize); + +static ssize_t +location_show(struct mddev *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(struct mddev *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; + 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 = kstrtoll(buf+1, 10, &offset); + else + rv = kstrtoll(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) + rv = bitmap_load(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); + +/* 'bitmap/space' is the space available at 'location' for the + * bitmap. This allows the kernel to know when it is safe to + * resize the bitmap to match a resized array. + */ +static ssize_t +space_show(struct mddev *mddev, char *page) +{ + return sprintf(page, "%lu\n", mddev->bitmap_info.space); +} + +static ssize_t +space_store(struct mddev *mddev, const char *buf, size_t len) +{ + unsigned long sectors; + int rv; + + rv = kstrtoul(buf, 10, §ors); + if (rv) + return rv; + + if (sectors == 0) + return -EINVAL; + + if (mddev->bitmap && + sectors < (mddev->bitmap->storage.bytes + 511) >> 9) + return -EFBIG; /* Bitmap is too big for this small space */ + + /* could make sure it isn't too big, but that isn't really + * needed - user-space should be careful. + */ + mddev->bitmap_info.space = sectors; + return len; +} + +static struct md_sysfs_entry bitmap_space = +__ATTR(space, S_IRUGO|S_IWUSR, space_show, space_store); + +static ssize_t +timeout_show(struct mddev *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(struct mddev *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(struct mddev *mddev, char *page) +{ + return sprintf(page, "%lu\n", mddev->bitmap_info.max_write_behind); +} + +static ssize_t +backlog_store(struct mddev *mddev, const char *buf, size_t len) +{ + unsigned long backlog; + int rv = kstrtoul(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(struct mddev *mddev, char *page) +{ + return sprintf(page, "%lu\n", mddev->bitmap_info.chunksize); +} + +static ssize_t +chunksize_store(struct mddev *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 = kstrtoul(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(struct mddev *mddev, char *page) +{ + return sprintf(page, "%s\n", (mddev->bitmap_info.external + ? "external" : "internal")); +} + +static ssize_t metadata_store(struct mddev *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(struct mddev *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(struct mddev *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 ssize_t +behind_writes_used_show(struct mddev *mddev, char *page) +{ + if (mddev->bitmap == NULL) + return sprintf(page, "0\n"); + return sprintf(page, "%lu\n", + mddev->bitmap->behind_writes_used); +} + +static ssize_t +behind_writes_used_reset(struct mddev *mddev, const char *buf, size_t len) +{ + if (mddev->bitmap) + mddev->bitmap->behind_writes_used = 0; + return len; +} + +static struct md_sysfs_entry max_backlog_used = +__ATTR(max_backlog_used, S_IRUGO | S_IWUSR, + behind_writes_used_show, behind_writes_used_reset); + +static struct attribute *md_bitmap_attrs[] = { + &bitmap_location.attr, + &bitmap_space.attr, + &bitmap_timeout.attr, + &bitmap_backlog.attr, + &bitmap_chunksize.attr, + &bitmap_metadata.attr, + &bitmap_can_clear.attr, + &max_backlog_used.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); -EXPORT_SYMBOL(bitmap_start_sync); -EXPORT_SYMBOL(bitmap_end_sync); -EXPORT_SYMBOL(bitmap_unplug); -EXPORT_SYMBOL(bitmap_close_sync); -EXPORT_SYMBOL(bitmap_daemon_work); |