From 935fe0983e09f4f7331ebf5ea4ae2124f6e9f9e8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 10 Oct 2017 17:02:41 -0400 Subject: md: rename some drivers/md/ files to have an "md-" prefix Motivated by the desire to illiminate the imprecise nature of DM-specific patches being unnecessarily sent to both the MD maintainer and mailing-list. Which is born out of the fact that DM files also reside in drivers/md/ Now all MD-specific files in drivers/md/ start with either "raid" or "md-" and the MAINTAINERS file has been updated accordingly. Shaohua: don't change module name Signed-off-by: Mike Snitzer Signed-off-by: Shaohua Li --- MAINTAINERS | 7 +- drivers/md/Makefile | 5 +- drivers/md/bitmap.c | 2591 --------------------------------------------- drivers/md/bitmap.h | 277 ----- drivers/md/dm-raid.c | 2 +- drivers/md/faulty.c | 372 ------- drivers/md/linear.c | 348 ------ drivers/md/linear.h | 16 - drivers/md/md-bitmap.c | 2591 +++++++++++++++++++++++++++++++++++++++++++++ drivers/md/md-bitmap.h | 277 +++++ drivers/md/md-cluster.c | 2 +- drivers/md/md-faulty.c | 372 +++++++ drivers/md/md-linear.c | 348 ++++++ drivers/md/md-linear.h | 16 + drivers/md/md-multipath.c | 509 +++++++++ drivers/md/md-multipath.h | 31 + drivers/md/md.c | 2 +- drivers/md/multipath.c | 509 --------- drivers/md/multipath.h | 31 - drivers/md/raid1.c | 2 +- drivers/md/raid10.c | 2 +- drivers/md/raid5-cache.c | 2 +- drivers/md/raid5.c | 2 +- 23 files changed, 4161 insertions(+), 4153 deletions(-) delete mode 100644 drivers/md/bitmap.c delete mode 100644 drivers/md/bitmap.h delete mode 100644 drivers/md/faulty.c delete mode 100644 drivers/md/linear.c delete mode 100644 drivers/md/linear.h create mode 100644 drivers/md/md-bitmap.c create mode 100644 drivers/md/md-bitmap.h create mode 100644 drivers/md/md-faulty.c create mode 100644 drivers/md/md-linear.c create mode 100644 drivers/md/md-linear.h create mode 100644 drivers/md/md-multipath.c create mode 100644 drivers/md/md-multipath.h delete mode 100644 drivers/md/multipath.c delete mode 100644 drivers/md/multipath.h diff --git a/MAINTAINERS b/MAINTAINERS index 65b0c88d5ee0..7649877692b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4091,6 +4091,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git T: quilt http://people.redhat.com/agk/patches/linux/editing/ S: Maintained F: Documentation/device-mapper/ +F: drivers/md/Makefile +F: drivers/md/Kconfig F: drivers/md/dm* F: drivers/md/persistent-data/ F: include/linux/device-mapper.h @@ -12446,7 +12448,10 @@ M: Shaohua Li L: linux-raid@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/shli/md.git S: Supported -F: drivers/md/ +F: drivers/md/Makefile +F: drivers/md/Kconfig +F: drivers/md/md* +F: drivers/md/raid* F: include/linux/raid/ F: include/uapi/linux/raid/ diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 786ec9e86d65..693602ffdd38 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -18,9 +18,12 @@ dm-cache-y += dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o \ dm-cache-smq-y += dm-cache-policy-smq.o dm-era-y += dm-era-target.o dm-verity-y += dm-verity-target.o -md-mod-y += md.o bitmap.o +md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o +linear-y += md-linear.o +multipath-y += md-multipath.o +faulty-y += md-faulty.o # Note: link order is important. All raid personalities # and must come before md.o, as they each initialise diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c deleted file mode 100644 index cae57b5be817..000000000000 --- a/drivers/md/bitmap.c +++ /dev/null @@ -1,2591 +0,0 @@ -/* - * 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 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "md.h" -#include "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<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<i_blkbits)) - count = 0; - else - count -= (1<i_blkbits); - - bh->b_end_io = end_bitmap_write; - bh->b_private = bitmap; - atomic_inc(&bitmap->pending_writes); - set_buffer_locked(bh); - set_buffer_mapped(bh); - submit_bh(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); - 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->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)); - - for (i = 0; i < chunks; 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 (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 + node_offset, count); - - if (ret) - goto err; - - oldindex = index; - - if (outofdate) { - /* - * if bitmap is out of date, dirty the - * whole page and write it out - */ - paddr = kmap_atomic(page); - memset(paddr + offset, 0xff, - PAGE_SIZE - offset); - kunmap_atomic(paddr); - write_page(bitmap, page, 1); - - ret = -EIO; - if (test_bit(BITMAP_WRITE_ERROR, - &bitmap->flags)) - goto err; - } - } - 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 */ - int needed = ((sector_t)(i+1) << bitmap->counts.chunkshift - >= start); - bitmap_set_memory_bits(bitmap, - (sector_t)i << bitmap->counts.chunkshift, - needed); - bit_cnt++; - } - offset = 0; - } - - pr_debug("%s: bitmap initialized from disk: read %lu pages, set %lu of %lu bits\n", - bmname(bitmap), store->file_pages, - bit_cnt, chunks); - - return 0; - - err: - pr_warn("%s: bitmap initialisation failed: %d\n", - bmname(bitmap), ret); - return ret; -} - -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; - - 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_counts *bitmap, - sector_t offset, int inc) -{ - sector_t chunk = offset >> bitmap->chunkshift; - unsigned long page = chunk >> PAGE_COUNTER_SHIFT; - bitmap->bp[page].count += inc; - bitmap_checkfree(bitmap, page); -} - -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); - -/* - * bitmap daemon -- periodically wakes up to clean bits and flush pages - * out to disk - */ - -void bitmap_daemon_work(struct mddev *mddev) -{ - struct bitmap *bitmap; - unsigned long j; - 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; - - bitmap->daemon_lastrun = jiffies; - if (bitmap->allclean) { - mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; - goto done; - } - bitmap->allclean = 1; - - if (bitmap->mddev->queue) - blk_add_trace_msg(bitmap->mddev->queue, - "md bitmap_daemon_work"); - - /* 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; - - if (j == nextpage) { - nextpage += PAGE_COUNTER_RATIO; - if (!counts->bp[j >> PAGE_COUNTER_SHIFT].pending) { - j |= PAGE_COUNTER_MASK; - continue; - } - counts->bp[j >> PAGE_COUNTER_SHIFT].pending = 0; - } - bmc = bitmap_get_counter(counts, - block, - &blocks, 0); - - if (!bmc) { - j |= PAGE_COUNTER_MASK; - continue; - } - 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; - } - } - spin_unlock_irq(&counts->lock); - - bitmap_wait_writes(bitmap); - /* 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); - } - } - - 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_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 >> 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, 0); - - 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); - return &((bitmap_counter_t *) - &bitmap->bp[page].map)[hi]; - } 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 (behind) { - int bw; - atomic_inc(&bitmap->behind_writes); - 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) { - sector_t blocks; - bitmap_counter_t *bmc; - - spin_lock_irq(&bitmap->counts.lock); - bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 1); - if (!bmc) { - spin_unlock_irq(&bitmap->counts.lock); - return 0; - } - - 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->counts, offset, 1); - /* fall through */ - case 1: - *bmc = 2; - } - - (*bmc)++; - - spin_unlock_irq(&bitmap->counts.lock); - - offset += blocks; - if (sectors > blocks) - sectors -= blocks; - 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 (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) { - sector_t blocks; - unsigned long flags; - bitmap_counter_t *bmc; - - spin_lock_irqsave(&bitmap->counts.lock, flags); - bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 0); - if (!bmc) { - spin_unlock_irqrestore(&bitmap->counts.lock, flags); - return; - } - - 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) { - bitmap_set_pending(&bitmap->counts, offset); - bitmap->allclean = 0; - } - spin_unlock_irqrestore(&bitmap->counts.lock, flags); - offset += blocks; - if (sectors > blocks) - sectors -= blocks; - else - sectors = 0; - } -} -EXPORT_SYMBOL(bitmap_endwrite); - -static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, - int degraded) -{ - bitmap_counter_t *bmc; - int rv; - if (bitmap == NULL) {/* FIXME or bitmap set as 'failed' */ - *blocks = 1024; - return 1; /* always resync if no bitmap */ - } - spin_lock_irq(&bitmap->counts.lock); - bmc = bitmap_get_counter(&bitmap->counts, offset, blocks, 0); - rv = 0; - if (bmc) { - /* locked */ - if (RESYNC(*bmc)) - rv = 1; - else if (NEEDED(*bmc)) { - rv = 1; - if (!degraded) { /* don't set/clear bits if degraded */ - *bmc |= RESYNC_MASK; - *bmc &= ~NEEDED_MASK; - } - } - } - spin_unlock_irq(&bitmap->counts.lock); - return rv; -} - -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 (bitmap == NULL) { - *blocks = 1024; - return; - } - spin_lock_irqsave(&bitmap->counts.lock, flags); - bmc = bitmap_get_counter(&bitmap->counts, offset, blocks, 0); - if (bmc == NULL) - goto unlock; - /* locked */ - if (RESYNC(*bmc)) { - *bmc &= ~RESYNC_MASK; - - if (!NEEDED(*bmc) && aborted) - *bmc |= NEEDED_MASK; - else { - if (*bmc <= 2) { - bitmap_set_pending(&bitmap->counts, offset); - bitmap->allclean = 0; - } - } - } - unlock: - spin_unlock_irqrestore(&bitmap->counts.lock, flags); -} -EXPORT_SYMBOL(bitmap_end_sync); - -void bitmap_close_sync(struct bitmap *bitmap) -{ - /* Sync has finished, and any bitmap chunks that weren't synced - * properly have been aborted. It remains to us to clear the - * RESYNC bit wherever it is still on - */ - sector_t sector = 0; - sector_t blocks; - if (!bitmap) - return; - while (sector < bitmap->mddev->resync_max_sectors) { - bitmap_end_sync(bitmap, sector, &blocks, 0); - sector += blocks; - } -} -EXPORT_SYMBOL(bitmap_close_sync); - -void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force) -{ - sector_t s = 0; - sector_t blocks; - - if (!bitmap) - return; - if (sector == 0) { - bitmap->last_end_sync = jiffies; - return; - } - if (!force && 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_SB_CHANGE_CLEAN, &bitmap->mddev->sb_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); - -void bitmap_sync_with_cluster(struct mddev *mddev, - sector_t old_lo, sector_t old_hi, - sector_t new_lo, sector_t new_hi) -{ - struct bitmap *bitmap = mddev->bitmap; - sector_t sector, blocks = 0; - - for (sector = old_lo; sector < new_lo; ) { - bitmap_end_sync(bitmap, sector, &blocks, 0); - sector += blocks; - } - WARN((blocks > new_lo) && old_lo, "alignment is not correct for lo\n"); - - for (sector = old_hi; sector < new_hi; ) { - bitmap_start_sync(bitmap, sector, &blocks, 0); - sector += blocks; - } - WARN((blocks > new_hi) && old_hi, "alignment is not correct for hi\n"); -} -EXPORT_SYMBOL(bitmap_sync_with_cluster); - -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 2 and possibly set resync_needed. They should all - * be 0 at this point - */ - - sector_t secs; - bitmap_counter_t *bmc; - spin_lock_irq(&bitmap->counts.lock); - bmc = bitmap_get_counter(&bitmap->counts, offset, &secs, 1); - if (!bmc) { - spin_unlock_irq(&bitmap->counts.lock); - return; - } - if (!*bmc) { - *bmc = 2; - bitmap_count_page(&bitmap->counts, offset, 1); - bitmap_set_pending(&bitmap->counts, offset); - bitmap->allclean = 0; - } - if (needed) - *bmc |= NEEDED_MASK; - 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(struct mddev *mddev) -{ - struct bitmap *bitmap = mddev->bitmap; - long sleep; - - if (!bitmap) /* there was no bitmap */ - return; - - /* run the daemon_work three time to ensure everything is flushed - * that can be - */ - 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); -} - -/* - * free memory that was allocated - */ -void bitmap_free(struct bitmap *bitmap) -{ - unsigned long k, pages; - struct bitmap_page *bp; - - if (!bitmap) /* there was no bitmap */ - return; - - if (bitmap->sysfs_can_clear) - sysfs_put(bitmap->sysfs_can_clear); - - if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info && - bitmap->cluster_slot == md_cluster_ops->slot_number(bitmap->mddev)) - md_cluster_stop(bitmap->mddev); - - /* Shouldn't be needed - but just in case.... */ - wait_event(bitmap->write_wait, - atomic_read(&bitmap->pending_writes) == 0); - - /* release the bitmap file */ - bitmap_file_unmap(&bitmap->storage); - - bp = bitmap->counts.bp; - pages = bitmap->counts.pages; - - /* free all allocated memory */ - - if (bp) /* deallocate the page memory */ - for (k = 0; k < pages; k++) - if (bp[k].map && !bp[k].hijacked) - kfree(bp[k].map); - kfree(bp); - kfree(bitmap); -} -EXPORT_SYMBOL(bitmap_free); - -void bitmap_wait_behind_writes(struct mddev *mddev) -{ - struct bitmap *bitmap = mddev->bitmap; - - /* wait for behind writes to complete */ - if (bitmap && atomic_read(&bitmap->behind_writes) > 0) { - pr_debug("md:%s: behind writes in progress - waiting to stop.\n", - mdname(mddev)); - /* need to kick something here to make sure I/O goes? */ - wait_event(bitmap->behind_wait, - atomic_read(&bitmap->behind_writes) == 0); - } -} - -void bitmap_destroy(struct mddev *mddev) -{ - struct bitmap *bitmap = mddev->bitmap; - - if (!bitmap) /* there was no bitmap */ - return; - - bitmap_wait_behind_writes(mddev); - - mutex_lock(&mddev->bitmap_info.mutex); - spin_lock(&mddev->lock); - mddev->bitmap = NULL; /* disconnect from the md device */ - spin_unlock(&mddev->lock); - mutex_unlock(&mddev->bitmap_info.mutex); - if (mddev->thread) - mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; - - bitmap_free(bitmap); -} - -/* - * initialize the bitmap structure - * if this returns an error, bitmap_destroy must be called to do clean up - * once mddev->bitmap is set - */ -struct bitmap *bitmap_create(struct mddev *mddev, int slot) -{ - struct bitmap *bitmap; - sector_t blocks = mddev->resync_max_sectors; - struct file *file = mddev->bitmap_info.file; - int err; - struct kernfs_node *bm = NULL; - - BUILD_BUG_ON(sizeof(bitmap_super_t) != 256); - - BUG_ON(file && mddev->bitmap_info.offset); - - bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL); - if (!bitmap) - return ERR_PTR(-ENOMEM); - - 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); - - bitmap->mddev = mddev; - bitmap->cluster_slot = slot; - - 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->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->daemon_lastrun = jiffies; - err = bitmap_resize(bitmap, blocks, mddev->bitmap_info.chunksize, 1); - if (err) - goto error; - - pr_debug("created bitmap (%lu pages) for device %s\n", - bitmap->counts.pages, bmname(bitmap)); - - err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; - if (err) - goto error; - - return bitmap; - error: - bitmap_free(bitmap); - return ERR_PTR(err); -} - -int bitmap_load(struct mddev *mddev) -{ - int err = 0; - sector_t start = 0; - sector_t sector = 0; - struct bitmap *bitmap = mddev->bitmap; - - if (!bitmap) - goto out; - - if (mddev_is_clustered(mddev)) - md_cluster_ops->load_bitmaps(mddev, mddev->bitmap_info.nodes); - - /* 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); - - if (mddev->degraded == 0 - || bitmap->events_cleared == mddev->events) - /* 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 out; - clear_bit(BITMAP_STALE, &bitmap->flags); - - /* Kick recovery in case any bits were set */ - set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery); - - mddev->thread->timeout = mddev->bitmap_info.daemon_sleep; - md_wakeup_thread(mddev->thread); - - bitmap_update_sb(bitmap); - - if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) - err = -EIO; -out: - return err; -} -EXPORT_SYMBOL_GPL(bitmap_load); - -struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot) -{ - int rv = 0; - struct bitmap *bitmap; - - bitmap = bitmap_create(mddev, slot); - if (IS_ERR(bitmap)) { - rv = PTR_ERR(bitmap); - return ERR_PTR(rv); - } - - rv = bitmap_init_from_disk(bitmap, 0); - if (rv) { - bitmap_free(bitmap); - return ERR_PTR(rv); - } - - return bitmap; -} -EXPORT_SYMBOL(get_bitmap_from_slot); - -/* Loads the bitmap associated with slot and copies the resync information - * to our bitmap - */ -int bitmap_copy_from_slot(struct mddev *mddev, int slot, - sector_t *low, sector_t *high, bool clear_bits) -{ - int rv = 0, i, j; - sector_t block, lo = 0, hi = 0; - struct bitmap_counts *counts; - struct bitmap *bitmap; - - bitmap = get_bitmap_from_slot(mddev, slot); - if (IS_ERR(bitmap)) { - pr_err("%s can't get bitmap from slot %d\n", __func__, slot); - return -1; - } - - counts = &bitmap->counts; - for (j = 0; j < counts->chunks; j++) { - block = (sector_t)j << counts->chunkshift; - if (bitmap_file_test_bit(bitmap, block)) { - if (!lo) - lo = block; - hi = block; - bitmap_file_clear_bit(bitmap, block); - bitmap_set_memory_bits(mddev->bitmap, block, 1); - bitmap_file_set_bit(mddev->bitmap, block); - } - } - - if (clear_bits) { - bitmap_update_sb(bitmap); - /* BITMAP_PAGE_PENDING is set, but bitmap_unplug needs - * BITMAP_PAGE_DIRTY or _NEEDWRITE to write ... */ - for (i = 0; i < bitmap->storage.file_pages; i++) - if (test_page_attr(bitmap, i, BITMAP_PAGE_PENDING)) - set_page_attr(bitmap, i, BITMAP_PAGE_NEEDWRITE); - bitmap_unplug(bitmap); - } - bitmap_unplug(mddev->bitmap); - *low = lo; - *high = hi; - - return rv; -} -EXPORT_SYMBOL_GPL(bitmap_copy_from_slot); - - -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_file_path(seq, bitmap->storage.file, " \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 (bitmap->storage.file && !init) { - pr_info("md: cannot resize file-based bitmap\n"); - return -EINVAL; - } - - 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, - mddev_is_clustered(bitmap->mddev) - ? bitmap->cluster_slot : 0); - if (ret) { - bitmap_file_unmap(&store); - 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 cluster raid, need to pre-allocate bitmap */ - if (mddev_is_clustered(bitmap->mddev)) { - unsigned long page; - for (page = 0; page < pages; page++) { - ret = bitmap_checkpage(&bitmap->counts, page, 1, 1); - if (ret) { - unsigned long k; - - /* deallocate the page memory */ - for (k = 0; k < page; k++) { - kfree(new_bp[k].map); - } - - /* restore some fields from old_counts */ - bitmap->counts.bp = old_counts.bp; - bitmap->counts.pages = old_counts.pages; - bitmap->counts.missing_pages = old_counts.pages; - bitmap->counts.chunkshift = old_counts.chunkshift; - bitmap->counts.chunks = old_counts.chunks; - bitmap->mddev->bitmap_info.chunksize = 1 << (old_counts.chunkshift + - BITMAP_BLOCK_SHIFT); - blocks = old_counts.chunks << old_counts.chunkshift; - pr_warn("Could not pre-allocate in-memory bitmap for cluster raid\n"); - break; - } else - bitmap->counts.bp[page].count += 1; - } - } - - 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) -{ - int rv; - - rv = mddev_lock(mddev); - if (rv) - return rv; - if (mddev->pers) { - if (!mddev->pers->quiesce) { - rv = -EBUSY; - goto out; - } - if (mddev->recovery || mddev->sync_thread) { - rv = -EBUSY; - goto out; - } - } - - 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) { - rv = -EBUSY; - goto out; - } - 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 */ - rv = -EINVAL; - goto out; - } else { - if (buf[0] == '+') - rv = kstrtoll(buf+1, 10, &offset); - else - rv = kstrtoll(buf, 10, &offset); - if (rv) - goto out; - if (offset == 0) { - rv = -EINVAL; - goto out; - } - if (mddev->bitmap_info.external == 0 && - mddev->major_version == 0 && - offset != mddev->bitmap_info.default_offset) { - rv = -EINVAL; - goto out; - } - mddev->bitmap_info.offset = offset; - if (mddev->pers) { - struct bitmap *bitmap; - mddev->pers->quiesce(mddev, 1); - bitmap = bitmap_create(mddev, -1); - if (IS_ERR(bitmap)) - rv = PTR_ERR(bitmap); - else { - mddev->bitmap = bitmap; - rv = bitmap_load(mddev); - if (rv) - mddev->bitmap_info.offset = 0; - } - mddev->pers->quiesce(mddev, 0); - if (rv) { - bitmap_destroy(mddev); - goto out; - } - } - } - } - if (!mddev->external) { - /* Ensure new bitmap info is stored in - * metadata promptly. - */ - set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); - md_wakeup_thread(mddev->thread); - } - rv = 0; -out: - mddev_unlock(mddev); - if (rv) - return rv; - 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) -{ - if (mddev_is_clustered(mddev)) - return sprintf(page, "clustered\n"); - 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) || - (strncmp(buf, "clustered", 9) == 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; - spin_lock(&mddev->lock); - if (mddev->bitmap) - len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ? - "false" : "true")); - else - len = sprintf(page, "\n"); - spin_unlock(&mddev->lock); - 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) -{ - ssize_t ret; - spin_lock(&mddev->lock); - if (mddev->bitmap == NULL) - ret = sprintf(page, "0\n"); - else - ret = sprintf(page, "%lu\n", - mddev->bitmap->behind_writes_used); - spin_unlock(&mddev->lock); - return ret; -} - -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, -}; - diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h deleted file mode 100644 index d15721ac07a6..000000000000 --- a/drivers/md/bitmap.h +++ /dev/null @@ -1,277 +0,0 @@ -/* - * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003 - * - * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc. - */ -#ifndef BITMAP_H -#define BITMAP_H 1 - -#define BITMAP_MAJOR_LO 3 -/* version 4 insists the bitmap is in little-endian order - * with version 3, it is host-endian which is non-portable - * Version 5 is currently set only for clustered devices - */ -#define BITMAP_MAJOR_HI 4 -#define BITMAP_MAJOR_CLUSTERED 5 -#define BITMAP_MAJOR_HOSTENDIAN 3 - -/* - * in-memory bitmap: - * - * Use 16 bit block counters to track pending writes to each "chunk". - * The 2 high order bits are special-purpose, the first is a flag indicating - * whether a resync is needed. The second is a flag indicating whether a - * resync is active. - * This means that the counter is actually 14 bits: - * - * +--------+--------+------------------------------------------------+ - * | resync | resync | counter | - * | needed | active | | - * | (0-1) | (0-1) | (0-16383) | - * +--------+--------+------------------------------------------------+ - * - * The "resync needed" bit is set when: - * a '1' bit is read from storage at startup. - * a write request fails on some drives - * a resync is aborted on a chunk with 'resync active' set - * It is cleared (and resync-active set) when a resync starts across all drives - * of the chunk. - * - * - * The "resync active" bit is set when: - * a resync is started on all drives, and resync_needed is set. - * resync_needed will be cleared (as long as resync_active wasn't already set). - * It is cleared when a resync completes. - * - * The counter counts pending write requests, plus the on-disk bit. - * When the counter is '1' and the resync bits are clear, the on-disk - * bit can be cleared as well, thus setting the counter to 0. - * When we set a bit, or in the counter (to start a write), if the fields is - * 0, we first set the disk bit and set the counter to 1. - * - * If the counter is 0, the on-disk bit is clear and the stripe is clean - * Anything that dirties the stripe pushes the counter to 2 (at least) - * and sets the on-disk bit (lazily). - * If a periodic sweep find the counter at 2, it is decremented to 1. - * If the sweep find the counter at 1, the on-disk bit is cleared and the - * counter goes to zero. - * - * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block - * counters as a fallback when "page" memory cannot be allocated: - * - * Normal case (page memory allocated): - * - * page pointer (32-bit) - * - * [ ] ------+ - * | - * +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters) - * c1 c2 c2048 - * - * Hijacked case (page memory allocation failed): - * - * hijacked page pointer (32-bit) - * - * [ ][ ] (no page memory allocated) - * counter #1 (16-bit) counter #2 (16-bit) - * - */ - -#ifdef __KERNEL__ - -#define PAGE_BITS (PAGE_SIZE << 3) -#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3) - -typedef __u16 bitmap_counter_t; -#define COUNTER_BITS 16 -#define COUNTER_BIT_SHIFT 4 -#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3) - -#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1))) -#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2))) -#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1) -#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK) -#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK) -#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX) - -/* how many counters per page? */ -#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS) -/* same, except a shift value for more efficient bitops */ -#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT) -/* same, except a mask value for more efficient bitops */ -#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1) - -#define BITMAP_BLOCK_SHIFT 9 - -#endif - -/* - * bitmap structures: - */ - -#define BITMAP_MAGIC 0x6d746962 - -/* use these for bitmap->flags and bitmap->sb->state bit-fields */ -enum bitmap_state { - BITMAP_STALE = 1, /* the bitmap file is out of date or had -EIO */ - BITMAP_WRITE_ERROR = 2, /* A write error has occurred */ - BITMAP_HOSTENDIAN =15, -}; - -/* the superblock at the front of the bitmap file -- little endian */ -typedef struct bitmap_super_s { - __le32 magic; /* 0 BITMAP_MAGIC */ - __le32 version; /* 4 the bitmap major for now, could change... */ - __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */ - __le64 events; /* 24 event counter for the bitmap (1)*/ - __le64 events_cleared;/*32 event counter when last bit cleared (2) */ - __le64 sync_size; /* 40 the size of the md device's sync range(3) */ - __le32 state; /* 48 bitmap state information */ - __le32 chunksize; /* 52 the bitmap chunk size in bytes */ - __le32 daemon_sleep; /* 56 seconds between disk flushes */ - __le32 write_behind; /* 60 number of outstanding write-behind writes */ - __le32 sectors_reserved; /* 64 number of 512-byte sectors that are - * reserved for the bitmap. */ - __le32 nodes; /* 68 the maximum number of nodes in cluster. */ - __u8 cluster_name[64]; /* 72 cluster name to which this md belongs */ - __u8 pad[256 - 136]; /* set to zero */ -} bitmap_super_t; - -/* notes: - * (1) This event counter is updated before the eventcounter in the md superblock - * When a bitmap is loaded, it is only accepted if this event counter is equal - * to, or one greater than, the event counter in the superblock. - * (2) This event counter is updated when the other one is *if*and*only*if* the - * array is not degraded. As bits are not cleared when the array is degraded, - * this represents the last time that any bits were cleared. - * If a device is being added that has an event count with this value or - * higher, it is accepted as conforming to the bitmap. - * (3)This is the number of sectors represented by the bitmap, and is the range that - * resync happens across. For raid1 and raid5/6 it is the size of individual - * devices. For raid10 it is the size of the array. - */ - -#ifdef __KERNEL__ - -/* the in-memory bitmap is represented by bitmap_pages */ -struct bitmap_page { - /* - * map points to the actual memory page - */ - char *map; - /* - * in emergencies (when map cannot be alloced), hijack the map - * pointer and use it as two counters itself - */ - unsigned int hijacked:1; - /* - * If any counter in this page is '1' or '2' - and so could be - * cleared then that page is marked as 'pending' - */ - unsigned int pending:1; - /* - * count of dirty bits on the page - */ - unsigned int count:30; -}; - -/* the main bitmap structure - one per mddev */ -struct bitmap { - - struct bitmap_counts { - spinlock_t lock; - struct bitmap_page *bp; - unsigned long pages; /* total number of pages - * in the bitmap */ - unsigned long missing_pages; /* number of pages - * not yet allocated */ - unsigned long chunkshift; /* chunksize = 2^chunkshift - * (for bitops) */ - unsigned long chunks; /* Total number of data - * chunks for the array */ - } counts; - - struct mddev *mddev; /* the md device that the bitmap is for */ - - __u64 events_cleared; - int need_sync; - - struct bitmap_storage { - struct file *file; /* backing disk file */ - struct page *sb_page; /* cached copy of the bitmap - * file superblock */ - struct page **filemap; /* list of cache pages for - * the file */ - unsigned long *filemap_attr; /* attributes associated - * w/ filemap pages */ - unsigned long file_pages; /* number of pages in the file*/ - unsigned long bytes; /* total bytes in the bitmap */ - } storage; - - unsigned long flags; - - int allclean; - - atomic_t behind_writes; - unsigned long behind_writes_used; /* highest actual value at runtime */ - - /* - * the bitmap daemon - periodically wakes up and sweeps the bitmap - * file, cleaning up bits and flushing out pages to disk as necessary - */ - unsigned long daemon_lastrun; /* jiffies of last run */ - unsigned long last_end_sync; /* when we lasted called end_sync to - * update bitmap with resync progress */ - - atomic_t pending_writes; /* pending writes to the bitmap file */ - wait_queue_head_t write_wait; - wait_queue_head_t overflow_wait; - wait_queue_head_t behind_wait; - - struct kernfs_node *sysfs_can_clear; - int cluster_slot; /* Slot offset for clustered env */ -}; - -/* the bitmap API */ - -/* these are used only by md/bitmap */ -struct bitmap *bitmap_create(struct mddev *mddev, int slot); -int bitmap_load(struct mddev *mddev); -void bitmap_flush(struct mddev *mddev); -void bitmap_destroy(struct mddev *mddev); - -void bitmap_print_sb(struct bitmap *bitmap); -void bitmap_update_sb(struct bitmap *bitmap); -void bitmap_status(struct seq_file *seq, struct bitmap *bitmap); - -int bitmap_setallbits(struct bitmap *bitmap); -void bitmap_write_all(struct bitmap *bitmap); - -void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e); - -/* these are exported */ -int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, - unsigned long sectors, int behind); -void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, - unsigned long sectors, int success, int behind); -int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded); -void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted); -void bitmap_close_sync(struct bitmap *bitmap); -void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force); -void bitmap_sync_with_cluster(struct mddev *mddev, - sector_t old_lo, sector_t old_hi, - sector_t new_lo, sector_t new_hi); - -void bitmap_unplug(struct bitmap *bitmap); -void bitmap_daemon_work(struct mddev *mddev); - -int bitmap_resize(struct bitmap *bitmap, sector_t blocks, - int chunksize, int init); -struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot); -int bitmap_copy_from_slot(struct mddev *mddev, int slot, - sector_t *lo, sector_t *hi, bool clear_bits); -void bitmap_free(struct bitmap *bitmap); -void bitmap_wait_behind_writes(struct mddev *mddev); -#endif - -#endif diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 1ac58c5651b7..252770696a05 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -12,7 +12,7 @@ #include "raid1.h" #include "raid5.h" #include "raid10.h" -#include "bitmap.h" +#include "md-bitmap.h" #include diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c deleted file mode 100644 index 38264b38420f..000000000000 --- a/drivers/md/faulty.c +++ /dev/null @@ -1,372 +0,0 @@ -/* - * faulty.c : Multiple Devices driver for Linux - * - * Copyright (C) 2004 Neil Brown - * - * fautly-device-simulator personality for md - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * You should have received a copy of the GNU General Public License - * (for example /usr/src/linux/COPYING); if not, write to the Free - * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - - -/* - * The "faulty" personality causes some requests to fail. - * - * Possible failure modes are: - * reads fail "randomly" but succeed on retry - * writes fail "randomly" but succeed on retry - * reads for some address fail and then persist until a write - * reads for some address fail and then persist irrespective of write - * writes for some address fail and persist - * all writes fail - * - * Different modes can be active at a time, but only - * one can be set at array creation. Others can be added later. - * A mode can be one-shot or recurrent with the recurrence being - * once in every N requests. - * The bottom 5 bits of the "layout" indicate the mode. The - * remainder indicate a period, or 0 for one-shot. - * - * There is an implementation limit on the number of concurrently - * persisting-faulty blocks. When a new fault is requested that would - * exceed the limit, it is ignored. - * All current faults can be clear using a layout of "0". - * - * Requests are always sent to the device. If they are to fail, - * we clone the bio and insert a new b_end_io into the chain. - */ - -#define WriteTransient 0 -#define ReadTransient 1 -#define WritePersistent 2 -#define ReadPersistent 3 -#define WriteAll 4 /* doesn't go to device */ -#define ReadFixable 5 -#define Modes 6 - -#define ClearErrors 31 -#define ClearFaults 30 - -#define AllPersist 100 /* internal use only */ -#define NoPersist 101 - -#define ModeMask 0x1f -#define ModeShift 5 - -#define MaxFault 50 -#include -#include -#include -#include -#include "md.h" -#include - - -static void faulty_fail(struct bio *bio) -{ - struct bio *b = bio->bi_private; - - b->bi_iter.bi_size = bio->bi_iter.bi_size; - b->bi_iter.bi_sector = bio->bi_iter.bi_sector; - - bio_put(bio); - - bio_io_error(b); -} - -struct faulty_conf { - int period[Modes]; - atomic_t counters[Modes]; - sector_t faults[MaxFault]; - int modes[MaxFault]; - int nfaults; - struct md_rdev *rdev; -}; - -static int check_mode(struct faulty_conf *conf, int mode) -{ - if (conf->period[mode] == 0 && - atomic_read(&conf->counters[mode]) <= 0) - return 0; /* no failure, no decrement */ - - - if (atomic_dec_and_test(&conf->counters[mode])) { - if (conf->period[mode]) - atomic_set(&conf->counters[mode], conf->period[mode]); - return 1; - } - return 0; -} - -static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir) -{ - /* If we find a ReadFixable sector, we fix it ... */ - int i; - for (i=0; infaults; i++) - if (conf->faults[i] >= start && - conf->faults[i] < end) { - /* found it ... */ - switch (conf->modes[i] * 2 + dir) { - case WritePersistent*2+WRITE: return 1; - case ReadPersistent*2+READ: return 1; - case ReadFixable*2+READ: return 1; - case ReadFixable*2+WRITE: - conf->modes[i] = NoPersist; - return 0; - case AllPersist*2+READ: - case AllPersist*2+WRITE: return 1; - default: - return 0; - } - } - return 0; -} - -static void add_sector(struct faulty_conf *conf, sector_t start, int mode) -{ - int i; - int n = conf->nfaults; - for (i=0; infaults; i++) - if (conf->faults[i] == start) { - switch(mode) { - case NoPersist: conf->modes[i] = mode; return; - case WritePersistent: - if (conf->modes[i] == ReadPersistent || - conf->modes[i] == ReadFixable) - conf->modes[i] = AllPersist; - else - conf->modes[i] = WritePersistent; - return; - case ReadPersistent: - if (conf->modes[i] == WritePersistent) - conf->modes[i] = AllPersist; - else - conf->modes[i] = ReadPersistent; - return; - case ReadFixable: - if (conf->modes[i] == WritePersistent || - conf->modes[i] == ReadPersistent) - conf->modes[i] = AllPersist; - else - conf->modes[i] = ReadFixable; - return; - } - } else if (conf->modes[i] == NoPersist) - n = i; - - if (n >= MaxFault) - return; - conf->faults[n] = start; - conf->modes[n] = mode; - if (conf->nfaults == n) - conf->nfaults = n+1; -} - -static bool faulty_make_request(struct mddev *mddev, struct bio *bio) -{ - struct faulty_conf *conf = mddev->private; - int failit = 0; - - if (bio_data_dir(bio) == WRITE) { - /* write request */ - if (atomic_read(&conf->counters[WriteAll])) { - /* special case - don't decrement, don't generic_make_request, - * just fail immediately - */ - bio_io_error(bio); - return true; - } - - if (check_sector(conf, bio->bi_iter.bi_sector, - bio_end_sector(bio), WRITE)) - failit = 1; - if (check_mode(conf, WritePersistent)) { - add_sector(conf, bio->bi_iter.bi_sector, - WritePersistent); - failit = 1; - } - if (check_mode(conf, WriteTransient)) - failit = 1; - } else { - /* read request */ - if (check_sector(conf, bio->bi_iter.bi_sector, - bio_end_sector(bio), READ)) - failit = 1; - if (check_mode(conf, ReadTransient)) - failit = 1; - if (check_mode(conf, ReadPersistent)) { - add_sector(conf, bio->bi_iter.bi_sector, - ReadPersistent); - failit = 1; - } - if (check_mode(conf, ReadFixable)) { - add_sector(conf, bio->bi_iter.bi_sector, - ReadFixable); - failit = 1; - } - } - if (failit) { - struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set); - - bio_set_dev(b, conf->rdev->bdev); - b->bi_private = bio; - b->bi_end_io = faulty_fail; - bio = b; - } else - bio_set_dev(bio, conf->rdev->bdev); - - generic_make_request(bio); - return true; -} - -static void faulty_status(struct seq_file *seq, struct mddev *mddev) -{ - struct faulty_conf *conf = mddev->private; - int n; - - if ((n=atomic_read(&conf->counters[WriteTransient])) != 0) - seq_printf(seq, " WriteTransient=%d(%d)", - n, conf->period[WriteTransient]); - - if ((n=atomic_read(&conf->counters[ReadTransient])) != 0) - seq_printf(seq, " ReadTransient=%d(%d)", - n, conf->period[ReadTransient]); - - if ((n=atomic_read(&conf->counters[WritePersistent])) != 0) - seq_printf(seq, " WritePersistent=%d(%d)", - n, conf->period[WritePersistent]); - - if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0) - seq_printf(seq, " ReadPersistent=%d(%d)", - n, conf->period[ReadPersistent]); - - - if ((n=atomic_read(&conf->counters[ReadFixable])) != 0) - seq_printf(seq, " ReadFixable=%d(%d)", - n, conf->period[ReadFixable]); - - if ((n=atomic_read(&conf->counters[WriteAll])) != 0) - seq_printf(seq, " WriteAll"); - - seq_printf(seq, " nfaults=%d", conf->nfaults); -} - - -static int faulty_reshape(struct mddev *mddev) -{ - int mode = mddev->new_layout & ModeMask; - int count = mddev->new_layout >> ModeShift; - struct faulty_conf *conf = mddev->private; - - if (mddev->new_layout < 0) - return 0; - - /* new layout */ - if (mode == ClearFaults) - conf->nfaults = 0; - else if (mode == ClearErrors) { - int i; - for (i=0 ; i < Modes ; i++) { - conf->period[i] = 0; - atomic_set(&conf->counters[i], 0); - } - } else if (mode < Modes) { - conf->period[mode] = count; - if (!count) count++; - atomic_set(&conf->counters[mode], count); - } else - return -EINVAL; - mddev->new_layout = -1; - mddev->layout = -1; /* makes sure further changes come through */ - return 0; -} - -static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - WARN_ONCE(raid_disks, - "%s does not support generic reshape\n", __func__); - - if (sectors == 0) - return mddev->dev_sectors; - - return sectors; -} - -static int faulty_run(struct mddev *mddev) -{ - struct md_rdev *rdev; - int i; - struct faulty_conf *conf; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - - conf = kmalloc(sizeof(*conf), GFP_KERNEL); - if (!conf) - return -ENOMEM; - - for (i=0; icounters[i], 0); - conf->period[i] = 0; - } - conf->nfaults = 0; - - rdev_for_each(rdev, mddev) { - conf->rdev = rdev; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - } - - md_set_array_sectors(mddev, faulty_size(mddev, 0, 0)); - mddev->private = conf; - - faulty_reshape(mddev); - - return 0; -} - -static void faulty_free(struct mddev *mddev, void *priv) -{ - struct faulty_conf *conf = priv; - - kfree(conf); -} - -static struct md_personality faulty_personality = -{ - .name = "faulty", - .level = LEVEL_FAULTY, - .owner = THIS_MODULE, - .make_request = faulty_make_request, - .run = faulty_run, - .free = faulty_free, - .status = faulty_status, - .check_reshape = faulty_reshape, - .size = faulty_size, -}; - -static int __init raid_init(void) -{ - return register_md_personality(&faulty_personality); -} - -static void raid_exit(void) -{ - unregister_md_personality(&faulty_personality); -} - -module_init(raid_init); -module_exit(raid_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Fault injection personality for MD"); -MODULE_ALIAS("md-personality-10"); /* faulty */ -MODULE_ALIAS("md-faulty"); -MODULE_ALIAS("md-level--5"); diff --git a/drivers/md/linear.c b/drivers/md/linear.c deleted file mode 100644 index c464fb48039a..000000000000 --- a/drivers/md/linear.c +++ /dev/null @@ -1,348 +0,0 @@ -/* - linear.c : Multiple Devices driver for Linux - Copyright (C) 1994-96 Marc ZYNGIER - or - - - Linear mode management functions. - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2, or (at your option) - any later version. - - You should have received a copy of the GNU General Public License - (for example /usr/src/linux/COPYING); if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. -*/ - -#include -#include -#include -#include -#include -#include -#include "md.h" -#include "linear.h" - -/* - * find which device holds a particular offset - */ -static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) -{ - int lo, mid, hi; - struct linear_conf *conf; - - lo = 0; - hi = mddev->raid_disks - 1; - conf = mddev->private; - - /* - * Binary Search - */ - - while (hi > lo) { - - mid = (hi + lo) / 2; - if (sector < conf->disks[mid].end_sector) - hi = mid; - else - lo = mid + 1; - } - - return conf->disks + lo; -} - -/* - * In linear_congested() conf->raid_disks is used as a copy of - * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks - * and conf->disks[] are created in linear_conf(), they are always - * consitent with each other, but mddev->raid_disks does not. - */ -static int linear_congested(struct mddev *mddev, int bits) -{ - struct linear_conf *conf; - int i, ret = 0; - - rcu_read_lock(); - conf = rcu_dereference(mddev->private); - - for (i = 0; i < conf->raid_disks && !ret ; i++) { - struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - rcu_read_unlock(); - return ret; -} - -static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - struct linear_conf *conf; - sector_t array_sectors; - - conf = mddev->private; - WARN_ONCE(sectors || raid_disks, - "%s does not support generic reshape\n", __func__); - array_sectors = conf->array_sectors; - - return array_sectors; -} - -static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) -{ - struct linear_conf *conf; - struct md_rdev *rdev; - int i, cnt; - bool discard_supported = false; - - conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info), - GFP_KERNEL); - if (!conf) - return NULL; - - cnt = 0; - conf->array_sectors = 0; - - rdev_for_each(rdev, mddev) { - int j = rdev->raid_disk; - struct dev_info *disk = conf->disks + j; - sector_t sectors; - - if (j < 0 || j >= raid_disks || disk->rdev) { - pr_warn("md/linear:%s: disk numbering problem. Aborting!\n", - mdname(mddev)); - goto out; - } - - disk->rdev = rdev; - if (mddev->chunk_sectors) { - sectors = rdev->sectors; - sector_div(sectors, mddev->chunk_sectors); - rdev->sectors = sectors * mddev->chunk_sectors; - } - - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - conf->array_sectors += rdev->sectors; - cnt++; - - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; - } - if (cnt != raid_disks) { - pr_warn("md/linear:%s: not enough drives present. Aborting!\n", - mdname(mddev)); - goto out; - } - - if (!discard_supported) - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - else - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - - /* - * Here we calculate the device offsets. - */ - conf->disks[0].end_sector = conf->disks[0].rdev->sectors; - - for (i = 1; i < raid_disks; i++) - conf->disks[i].end_sector = - conf->disks[i-1].end_sector + - conf->disks[i].rdev->sectors; - - /* - * conf->raid_disks is copy of mddev->raid_disks. The reason to - * keep a copy of mddev->raid_disks in struct linear_conf is, - * mddev->raid_disks may not be consistent with pointers number of - * conf->disks[] when it is updated in linear_add() and used to - * iterate old conf->disks[] earray in linear_congested(). - * Here conf->raid_disks is always consitent with number of - * pointers in conf->disks[] array, and mddev->private is updated - * with rcu_assign_pointer() in linear_addr(), such race can be - * avoided. - */ - conf->raid_disks = raid_disks; - - return conf; - -out: - kfree(conf); - return NULL; -} - -static int linear_run (struct mddev *mddev) -{ - struct linear_conf *conf; - int ret; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - conf = linear_conf(mddev, mddev->raid_disks); - - if (!conf) - return 1; - mddev->private = conf; - md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - - ret = md_integrity_register(mddev); - if (ret) { - kfree(conf); - mddev->private = NULL; - } - return ret; -} - -static int linear_add(struct mddev *mddev, struct md_rdev *rdev) -{ - /* Adding a drive to a linear array allows the array to grow. - * It is permitted if the new drive has a matching superblock - * already on it, with raid_disk equal to raid_disks. - * It is achieved by creating a new linear_private_data structure - * and swapping it in in-place of the current one. - * The current one is never freed until the array is stopped. - * This avoids races. - */ - struct linear_conf *newconf, *oldconf; - - if (rdev->saved_raid_disk != mddev->raid_disks) - return -EINVAL; - - rdev->raid_disk = rdev->saved_raid_disk; - rdev->saved_raid_disk = -1; - - newconf = linear_conf(mddev,mddev->raid_disks+1); - - if (!newconf) - return -ENOMEM; - - /* newconf->raid_disks already keeps a copy of * the increased - * value of mddev->raid_disks, WARN_ONCE() is just used to make - * sure of this. It is possible that oldconf is still referenced - * in linear_congested(), therefore kfree_rcu() is used to free - * oldconf until no one uses it anymore. - */ - mddev_suspend(mddev); - oldconf = rcu_dereference_protected(mddev->private, - lockdep_is_held(&mddev->reconfig_mutex)); - mddev->raid_disks++; - WARN_ONCE(mddev->raid_disks != newconf->raid_disks, - "copied raid_disks doesn't match mddev->raid_disks"); - rcu_assign_pointer(mddev->private, newconf); - md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - set_capacity(mddev->gendisk, mddev->array_sectors); - mddev_resume(mddev); - revalidate_disk(mddev->gendisk); - kfree_rcu(oldconf, rcu); - return 0; -} - -static void linear_free(struct mddev *mddev, void *priv) -{ - struct linear_conf *conf = priv; - - kfree(conf); -} - -static bool linear_make_request(struct mddev *mddev, struct bio *bio) -{ - char b[BDEVNAME_SIZE]; - struct dev_info *tmp_dev; - sector_t start_sector, end_sector, data_offset; - sector_t bio_sector = bio->bi_iter.bi_sector; - - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); - return true; - } - - tmp_dev = which_dev(mddev, bio_sector); - start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; - end_sector = tmp_dev->end_sector; - data_offset = tmp_dev->rdev->data_offset; - - if (unlikely(bio_sector >= end_sector || - bio_sector < start_sector)) - goto out_of_bounds; - - if (unlikely(bio_end_sector(bio) > end_sector)) { - /* This bio crosses a device boundary, so we have to split it */ - struct bio *split = bio_split(bio, end_sector - bio_sector, - GFP_NOIO, mddev->bio_set); - bio_chain(split, bio); - generic_make_request(bio); - bio = split; - } - - bio_set_dev(bio, tmp_dev->rdev->bdev); - bio->bi_iter.bi_sector = bio->bi_iter.bi_sector - - start_sector + data_offset; - - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_disk->queue))) { - /* Just ignore it */ - bio_endio(bio); - } else { - if (mddev->gendisk) - trace_block_bio_remap(bio->bi_disk->queue, - bio, disk_devt(mddev->gendisk), - bio_sector); - mddev_check_writesame(mddev, bio); - mddev_check_write_zeroes(mddev, bio); - generic_make_request(bio); - } - return true; - -out_of_bounds: - pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n", - mdname(mddev), - (unsigned long long)bio->bi_iter.bi_sector, - bdevname(tmp_dev->rdev->bdev, b), - (unsigned long long)tmp_dev->rdev->sectors, - (unsigned long long)start_sector); - bio_io_error(bio); - return true; -} - -static void linear_status (struct seq_file *seq, struct mddev *mddev) -{ - seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); -} - -static void linear_quiesce(struct mddev *mddev, int state) -{ -} - -static struct md_personality linear_personality = -{ - .name = "linear", - .level = LEVEL_LINEAR, - .owner = THIS_MODULE, - .make_request = linear_make_request, - .run = linear_run, - .free = linear_free, - .status = linear_status, - .hot_add_disk = linear_add, - .size = linear_size, - .quiesce = linear_quiesce, - .congested = linear_congested, -}; - -static int __init linear_init (void) -{ - return register_md_personality (&linear_personality); -} - -static void linear_exit (void) -{ - unregister_md_personality (&linear_personality); -} - -module_init(linear_init); -module_exit(linear_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Linear device concatenation personality for MD"); -MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ -MODULE_ALIAS("md-linear"); -MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/linear.h b/drivers/md/linear.h deleted file mode 100644 index 8d392e6098b3..000000000000 --- a/drivers/md/linear.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef _LINEAR_H -#define _LINEAR_H - -struct dev_info { - struct md_rdev *rdev; - sector_t end_sector; -}; - -struct linear_conf -{ - struct rcu_head rcu; - sector_t array_sectors; - int raid_disks; /* a copy of mddev->raid_disks */ - struct dev_info disks[0]; -}; -#endif diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c new file mode 100644 index 000000000000..b843b53b0f65 --- /dev/null +++ b/drivers/md/md-bitmap.c @@ -0,0 +1,2591 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#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<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<i_blkbits)) + count = 0; + else + count -= (1<i_blkbits); + + bh->b_end_io = end_bitmap_write; + bh->b_private = bitmap; + atomic_inc(&bitmap->pending_writes); + set_buffer_locked(bh); + set_buffer_mapped(bh); + submit_bh(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); + 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->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)); + + for (i = 0; i < chunks; 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 (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 + node_offset, count); + + if (ret) + goto err; + + oldindex = index; + + if (outofdate) { + /* + * if bitmap is out of date, dirty the + * whole page and write it out + */ + paddr = kmap_atomic(page); + memset(paddr + offset, 0xff, + PAGE_SIZE - offset); + kunmap_atomic(paddr); + write_page(bitmap, page, 1); + + ret = -EIO; + if (test_bit(BITMAP_WRITE_ERROR, + &bitmap->flags)) + goto err; + } + } + 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 */ + int needed = ((sector_t)(i+1) << bitmap->counts.chunkshift + >= start); + bitmap_set_memory_bits(bitmap, + (sector_t)i << bitmap->counts.chunkshift, + needed); + bit_cnt++; + } + offset = 0; + } + + pr_debug("%s: bitmap initialized from disk: read %lu pages, set %lu of %lu bits\n", + bmname(bitmap), store->file_pages, + bit_cnt, chunks); + + return 0; + + err: + pr_warn("%s: bitmap initialisation failed: %d\n", + bmname(bitmap), ret); + return ret; +} + +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; + + 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_counts *bitmap, + sector_t offset, int inc) +{ + sector_t chunk = offset >> bitmap->chunkshift; + unsigned long page = chunk >> PAGE_COUNTER_SHIFT; + bitmap->bp[page].count += inc; + bitmap_checkfree(bitmap, page); +} + +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); + +/* + * bitmap daemon -- periodically wakes up to clean bits and flush pages + * out to disk + */ + +void bitmap_daemon_work(struct mddev *mddev) +{ + struct bitmap *bitmap; + unsigned long j; + 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; + + bitmap->daemon_lastrun = jiffies; + if (bitmap->allclean) { + mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + goto done; + } + bitmap->allclean = 1; + + if (bitmap->mddev->queue) + blk_add_trace_msg(bitmap->mddev->queue, + "md bitmap_daemon_work"); + + /* 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; + + if (j == nextpage) { + nextpage += PAGE_COUNTER_RATIO; + if (!counts->bp[j >> PAGE_COUNTER_SHIFT].pending) { + j |= PAGE_COUNTER_MASK; + continue; + } + counts->bp[j >> PAGE_COUNTER_SHIFT].pending = 0; + } + bmc = bitmap_get_counter(counts, + block, + &blocks, 0); + + if (!bmc) { + j |= PAGE_COUNTER_MASK; + continue; + } + 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; + } + } + spin_unlock_irq(&counts->lock); + + bitmap_wait_writes(bitmap); + /* 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); + } + } + + 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_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 >> 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, 0); + + 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); + return &((bitmap_counter_t *) + &bitmap->bp[page].map)[hi]; + } 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 (behind) { + int bw; + atomic_inc(&bitmap->behind_writes); + 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) { + sector_t blocks; + bitmap_counter_t *bmc; + + spin_lock_irq(&bitmap->counts.lock); + bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 1); + if (!bmc) { + spin_unlock_irq(&bitmap->counts.lock); + return 0; + } + + 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->counts, offset, 1); + /* fall through */ + case 1: + *bmc = 2; + } + + (*bmc)++; + + spin_unlock_irq(&bitmap->counts.lock); + + offset += blocks; + if (sectors > blocks) + sectors -= blocks; + 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 (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) { + sector_t blocks; + unsigned long flags; + bitmap_counter_t *bmc; + + spin_lock_irqsave(&bitmap->counts.lock, flags); + bmc = bitmap_get_counter(&bitmap->counts, offset, &blocks, 0); + if (!bmc) { + spin_unlock_irqrestore(&bitmap->counts.lock, flags); + return; + } + + 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) { + bitmap_set_pending(&bitmap->counts, offset); + bitmap->allclean = 0; + } + spin_unlock_irqrestore(&bitmap->counts.lock, flags); + offset += blocks; + if (sectors > blocks) + sectors -= blocks; + else + sectors = 0; + } +} +EXPORT_SYMBOL(bitmap_endwrite); + +static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, + int degraded) +{ + bitmap_counter_t *bmc; + int rv; + if (bitmap == NULL) {/* FIXME or bitmap set as 'failed' */ + *blocks = 1024; + return 1; /* always resync if no bitmap */ + } + spin_lock_irq(&bitmap->counts.lock); + bmc = bitmap_get_counter(&bitmap->counts, offset, blocks, 0); + rv = 0; + if (bmc) { + /* locked */ + if (RESYNC(*bmc)) + rv = 1; + else if (NEEDED(*bmc)) { + rv = 1; + if (!degraded) { /* don't set/clear bits if degraded */ + *bmc |= RESYNC_MASK; + *bmc &= ~NEEDED_MASK; + } + } + } + spin_unlock_irq(&bitmap->counts.lock); + return rv; +} + +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 (bitmap == NULL) { + *blocks = 1024; + return; + } + spin_lock_irqsave(&bitmap->counts.lock, flags); + bmc = bitmap_get_counter(&bitmap->counts, offset, blocks, 0); + if (bmc == NULL) + goto unlock; + /* locked */ + if (RESYNC(*bmc)) { + *bmc &= ~RESYNC_MASK; + + if (!NEEDED(*bmc) && aborted) + *bmc |= NEEDED_MASK; + else { + if (*bmc <= 2) { + bitmap_set_pending(&bitmap->counts, offset); + bitmap->allclean = 0; + } + } + } + unlock: + spin_unlock_irqrestore(&bitmap->counts.lock, flags); +} +EXPORT_SYMBOL(bitmap_end_sync); + +void bitmap_close_sync(struct bitmap *bitmap) +{ + /* Sync has finished, and any bitmap chunks that weren't synced + * properly have been aborted. It remains to us to clear the + * RESYNC bit wherever it is still on + */ + sector_t sector = 0; + sector_t blocks; + if (!bitmap) + return; + while (sector < bitmap->mddev->resync_max_sectors) { + bitmap_end_sync(bitmap, sector, &blocks, 0); + sector += blocks; + } +} +EXPORT_SYMBOL(bitmap_close_sync); + +void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force) +{ + sector_t s = 0; + sector_t blocks; + + if (!bitmap) + return; + if (sector == 0) { + bitmap->last_end_sync = jiffies; + return; + } + if (!force && 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_SB_CHANGE_CLEAN, &bitmap->mddev->sb_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); + +void bitmap_sync_with_cluster(struct mddev *mddev, + sector_t old_lo, sector_t old_hi, + sector_t new_lo, sector_t new_hi) +{ + struct bitmap *bitmap = mddev->bitmap; + sector_t sector, blocks = 0; + + for (sector = old_lo; sector < new_lo; ) { + bitmap_end_sync(bitmap, sector, &blocks, 0); + sector += blocks; + } + WARN((blocks > new_lo) && old_lo, "alignment is not correct for lo\n"); + + for (sector = old_hi; sector < new_hi; ) { + bitmap_start_sync(bitmap, sector, &blocks, 0); + sector += blocks; + } + WARN((blocks > new_hi) && old_hi, "alignment is not correct for hi\n"); +} +EXPORT_SYMBOL(bitmap_sync_with_cluster); + +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 2 and possibly set resync_needed. They should all + * be 0 at this point + */ + + sector_t secs; + bitmap_counter_t *bmc; + spin_lock_irq(&bitmap->counts.lock); + bmc = bitmap_get_counter(&bitmap->counts, offset, &secs, 1); + if (!bmc) { + spin_unlock_irq(&bitmap->counts.lock); + return; + } + if (!*bmc) { + *bmc = 2; + bitmap_count_page(&bitmap->counts, offset, 1); + bitmap_set_pending(&bitmap->counts, offset); + bitmap->allclean = 0; + } + if (needed) + *bmc |= NEEDED_MASK; + 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(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + long sleep; + + if (!bitmap) /* there was no bitmap */ + return; + + /* run the daemon_work three time to ensure everything is flushed + * that can be + */ + 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); +} + +/* + * free memory that was allocated + */ +void bitmap_free(struct bitmap *bitmap) +{ + unsigned long k, pages; + struct bitmap_page *bp; + + if (!bitmap) /* there was no bitmap */ + return; + + if (bitmap->sysfs_can_clear) + sysfs_put(bitmap->sysfs_can_clear); + + if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info && + bitmap->cluster_slot == md_cluster_ops->slot_number(bitmap->mddev)) + md_cluster_stop(bitmap->mddev); + + /* Shouldn't be needed - but just in case.... */ + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes) == 0); + + /* release the bitmap file */ + bitmap_file_unmap(&bitmap->storage); + + bp = bitmap->counts.bp; + pages = bitmap->counts.pages; + + /* free all allocated memory */ + + if (bp) /* deallocate the page memory */ + for (k = 0; k < pages; k++) + if (bp[k].map && !bp[k].hijacked) + kfree(bp[k].map); + kfree(bp); + kfree(bitmap); +} +EXPORT_SYMBOL(bitmap_free); + +void bitmap_wait_behind_writes(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + + /* wait for behind writes to complete */ + if (bitmap && atomic_read(&bitmap->behind_writes) > 0) { + pr_debug("md:%s: behind writes in progress - waiting to stop.\n", + mdname(mddev)); + /* need to kick something here to make sure I/O goes? */ + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); + } +} + +void bitmap_destroy(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + + if (!bitmap) /* there was no bitmap */ + return; + + bitmap_wait_behind_writes(mddev); + + mutex_lock(&mddev->bitmap_info.mutex); + spin_lock(&mddev->lock); + mddev->bitmap = NULL; /* disconnect from the md device */ + spin_unlock(&mddev->lock); + mutex_unlock(&mddev->bitmap_info.mutex); + if (mddev->thread) + mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + + bitmap_free(bitmap); +} + +/* + * initialize the bitmap structure + * if this returns an error, bitmap_destroy must be called to do clean up + * once mddev->bitmap is set + */ +struct bitmap *bitmap_create(struct mddev *mddev, int slot) +{ + struct bitmap *bitmap; + sector_t blocks = mddev->resync_max_sectors; + struct file *file = mddev->bitmap_info.file; + int err; + struct kernfs_node *bm = NULL; + + BUILD_BUG_ON(sizeof(bitmap_super_t) != 256); + + BUG_ON(file && mddev->bitmap_info.offset); + + bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL); + if (!bitmap) + return ERR_PTR(-ENOMEM); + + 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); + + bitmap->mddev = mddev; + bitmap->cluster_slot = slot; + + 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->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->daemon_lastrun = jiffies; + err = bitmap_resize(bitmap, blocks, mddev->bitmap_info.chunksize, 1); + if (err) + goto error; + + pr_debug("created bitmap (%lu pages) for device %s\n", + bitmap->counts.pages, bmname(bitmap)); + + err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; + if (err) + goto error; + + return bitmap; + error: + bitmap_free(bitmap); + return ERR_PTR(err); +} + +int bitmap_load(struct mddev *mddev) +{ + int err = 0; + sector_t start = 0; + sector_t sector = 0; + struct bitmap *bitmap = mddev->bitmap; + + if (!bitmap) + goto out; + + if (mddev_is_clustered(mddev)) + md_cluster_ops->load_bitmaps(mddev, mddev->bitmap_info.nodes); + + /* 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); + + if (mddev->degraded == 0 + || bitmap->events_cleared == mddev->events) + /* 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 out; + clear_bit(BITMAP_STALE, &bitmap->flags); + + /* Kick recovery in case any bits were set */ + set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery); + + mddev->thread->timeout = mddev->bitmap_info.daemon_sleep; + md_wakeup_thread(mddev->thread); + + bitmap_update_sb(bitmap); + + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) + err = -EIO; +out: + return err; +} +EXPORT_SYMBOL_GPL(bitmap_load); + +struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot) +{ + int rv = 0; + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, slot); + if (IS_ERR(bitmap)) { + rv = PTR_ERR(bitmap); + return ERR_PTR(rv); + } + + rv = bitmap_init_from_disk(bitmap, 0); + if (rv) { + bitmap_free(bitmap); + return ERR_PTR(rv); + } + + return bitmap; +} +EXPORT_SYMBOL(get_bitmap_from_slot); + +/* Loads the bitmap associated with slot and copies the resync information + * to our bitmap + */ +int bitmap_copy_from_slot(struct mddev *mddev, int slot, + sector_t *low, sector_t *high, bool clear_bits) +{ + int rv = 0, i, j; + sector_t block, lo = 0, hi = 0; + struct bitmap_counts *counts; + struct bitmap *bitmap; + + bitmap = get_bitmap_from_slot(mddev, slot); + if (IS_ERR(bitmap)) { + pr_err("%s can't get bitmap from slot %d\n", __func__, slot); + return -1; + } + + counts = &bitmap->counts; + for (j = 0; j < counts->chunks; j++) { + block = (sector_t)j << counts->chunkshift; + if (bitmap_file_test_bit(bitmap, block)) { + if (!lo) + lo = block; + hi = block; + bitmap_file_clear_bit(bitmap, block); + bitmap_set_memory_bits(mddev->bitmap, block, 1); + bitmap_file_set_bit(mddev->bitmap, block); + } + } + + if (clear_bits) { + bitmap_update_sb(bitmap); + /* BITMAP_PAGE_PENDING is set, but bitmap_unplug needs + * BITMAP_PAGE_DIRTY or _NEEDWRITE to write ... */ + for (i = 0; i < bitmap->storage.file_pages; i++) + if (test_page_attr(bitmap, i, BITMAP_PAGE_PENDING)) + set_page_attr(bitmap, i, BITMAP_PAGE_NEEDWRITE); + bitmap_unplug(bitmap); + } + bitmap_unplug(mddev->bitmap); + *low = lo; + *high = hi; + + return rv; +} +EXPORT_SYMBOL_GPL(bitmap_copy_from_slot); + + +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_file_path(seq, bitmap->storage.file, " \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 (bitmap->storage.file && !init) { + pr_info("md: cannot resize file-based bitmap\n"); + return -EINVAL; + } + + 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, + mddev_is_clustered(bitmap->mddev) + ? bitmap->cluster_slot : 0); + if (ret) { + bitmap_file_unmap(&store); + 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 cluster raid, need to pre-allocate bitmap */ + if (mddev_is_clustered(bitmap->mddev)) { + unsigned long page; + for (page = 0; page < pages; page++) { + ret = bitmap_checkpage(&bitmap->counts, page, 1, 1); + if (ret) { + unsigned long k; + + /* deallocate the page memory */ + for (k = 0; k < page; k++) { + kfree(new_bp[k].map); + } + + /* restore some fields from old_counts */ + bitmap->counts.bp = old_counts.bp; + bitmap->counts.pages = old_counts.pages; + bitmap->counts.missing_pages = old_counts.pages; + bitmap->counts.chunkshift = old_counts.chunkshift; + bitmap->counts.chunks = old_counts.chunks; + bitmap->mddev->bitmap_info.chunksize = 1 << (old_counts.chunkshift + + BITMAP_BLOCK_SHIFT); + blocks = old_counts.chunks << old_counts.chunkshift; + pr_warn("Could not pre-allocate in-memory bitmap for cluster raid\n"); + break; + } else + bitmap->counts.bp[page].count += 1; + } + } + + 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) +{ + int rv; + + rv = mddev_lock(mddev); + if (rv) + return rv; + if (mddev->pers) { + if (!mddev->pers->quiesce) { + rv = -EBUSY; + goto out; + } + if (mddev->recovery || mddev->sync_thread) { + rv = -EBUSY; + goto out; + } + } + + 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) { + rv = -EBUSY; + goto out; + } + 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 */ + rv = -EINVAL; + goto out; + } else { + if (buf[0] == '+') + rv = kstrtoll(buf+1, 10, &offset); + else + rv = kstrtoll(buf, 10, &offset); + if (rv) + goto out; + if (offset == 0) { + rv = -EINVAL; + goto out; + } + if (mddev->bitmap_info.external == 0 && + mddev->major_version == 0 && + offset != mddev->bitmap_info.default_offset) { + rv = -EINVAL; + goto out; + } + mddev->bitmap_info.offset = offset; + if (mddev->pers) { + struct bitmap *bitmap; + mddev->pers->quiesce(mddev, 1); + bitmap = bitmap_create(mddev, -1); + if (IS_ERR(bitmap)) + rv = PTR_ERR(bitmap); + else { + mddev->bitmap = bitmap; + rv = bitmap_load(mddev); + if (rv) + mddev->bitmap_info.offset = 0; + } + mddev->pers->quiesce(mddev, 0); + if (rv) { + bitmap_destroy(mddev); + goto out; + } + } + } + } + if (!mddev->external) { + /* Ensure new bitmap info is stored in + * metadata promptly. + */ + set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); + md_wakeup_thread(mddev->thread); + } + rv = 0; +out: + mddev_unlock(mddev); + if (rv) + return rv; + 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) +{ + if (mddev_is_clustered(mddev)) + return sprintf(page, "clustered\n"); + 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) || + (strncmp(buf, "clustered", 9) == 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; + spin_lock(&mddev->lock); + if (mddev->bitmap) + len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ? + "false" : "true")); + else + len = sprintf(page, "\n"); + spin_unlock(&mddev->lock); + 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) +{ + ssize_t ret; + spin_lock(&mddev->lock); + if (mddev->bitmap == NULL) + ret = sprintf(page, "0\n"); + else + ret = sprintf(page, "%lu\n", + mddev->bitmap->behind_writes_used); + spin_unlock(&mddev->lock); + return ret; +} + +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, +}; + diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h new file mode 100644 index 000000000000..d15721ac07a6 --- /dev/null +++ b/drivers/md/md-bitmap.h @@ -0,0 +1,277 @@ +/* + * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003 + * + * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc. + */ +#ifndef BITMAP_H +#define BITMAP_H 1 + +#define BITMAP_MAJOR_LO 3 +/* version 4 insists the bitmap is in little-endian order + * with version 3, it is host-endian which is non-portable + * Version 5 is currently set only for clustered devices + */ +#define BITMAP_MAJOR_HI 4 +#define BITMAP_MAJOR_CLUSTERED 5 +#define BITMAP_MAJOR_HOSTENDIAN 3 + +/* + * in-memory bitmap: + * + * Use 16 bit block counters to track pending writes to each "chunk". + * The 2 high order bits are special-purpose, the first is a flag indicating + * whether a resync is needed. The second is a flag indicating whether a + * resync is active. + * This means that the counter is actually 14 bits: + * + * +--------+--------+------------------------------------------------+ + * | resync | resync | counter | + * | needed | active | | + * | (0-1) | (0-1) | (0-16383) | + * +--------+--------+------------------------------------------------+ + * + * The "resync needed" bit is set when: + * a '1' bit is read from storage at startup. + * a write request fails on some drives + * a resync is aborted on a chunk with 'resync active' set + * It is cleared (and resync-active set) when a resync starts across all drives + * of the chunk. + * + * + * The "resync active" bit is set when: + * a resync is started on all drives, and resync_needed is set. + * resync_needed will be cleared (as long as resync_active wasn't already set). + * It is cleared when a resync completes. + * + * The counter counts pending write requests, plus the on-disk bit. + * When the counter is '1' and the resync bits are clear, the on-disk + * bit can be cleared as well, thus setting the counter to 0. + * When we set a bit, or in the counter (to start a write), if the fields is + * 0, we first set the disk bit and set the counter to 1. + * + * If the counter is 0, the on-disk bit is clear and the stripe is clean + * Anything that dirties the stripe pushes the counter to 2 (at least) + * and sets the on-disk bit (lazily). + * If a periodic sweep find the counter at 2, it is decremented to 1. + * If the sweep find the counter at 1, the on-disk bit is cleared and the + * counter goes to zero. + * + * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block + * counters as a fallback when "page" memory cannot be allocated: + * + * Normal case (page memory allocated): + * + * page pointer (32-bit) + * + * [ ] ------+ + * | + * +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters) + * c1 c2 c2048 + * + * Hijacked case (page memory allocation failed): + * + * hijacked page pointer (32-bit) + * + * [ ][ ] (no page memory allocated) + * counter #1 (16-bit) counter #2 (16-bit) + * + */ + +#ifdef __KERNEL__ + +#define PAGE_BITS (PAGE_SIZE << 3) +#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3) + +typedef __u16 bitmap_counter_t; +#define COUNTER_BITS 16 +#define COUNTER_BIT_SHIFT 4 +#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3) + +#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1))) +#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2))) +#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1) +#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK) +#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK) +#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX) + +/* how many counters per page? */ +#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS) +/* same, except a shift value for more efficient bitops */ +#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT) +/* same, except a mask value for more efficient bitops */ +#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1) + +#define BITMAP_BLOCK_SHIFT 9 + +#endif + +/* + * bitmap structures: + */ + +#define BITMAP_MAGIC 0x6d746962 + +/* use these for bitmap->flags and bitmap->sb->state bit-fields */ +enum bitmap_state { + BITMAP_STALE = 1, /* the bitmap file is out of date or had -EIO */ + BITMAP_WRITE_ERROR = 2, /* A write error has occurred */ + BITMAP_HOSTENDIAN =15, +}; + +/* the superblock at the front of the bitmap file -- little endian */ +typedef struct bitmap_super_s { + __le32 magic; /* 0 BITMAP_MAGIC */ + __le32 version; /* 4 the bitmap major for now, could change... */ + __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */ + __le64 events; /* 24 event counter for the bitmap (1)*/ + __le64 events_cleared;/*32 event counter when last bit cleared (2) */ + __le64 sync_size; /* 40 the size of the md device's sync range(3) */ + __le32 state; /* 48 bitmap state information */ + __le32 chunksize; /* 52 the bitmap chunk size in bytes */ + __le32 daemon_sleep; /* 56 seconds between disk flushes */ + __le32 write_behind; /* 60 number of outstanding write-behind writes */ + __le32 sectors_reserved; /* 64 number of 512-byte sectors that are + * reserved for the bitmap. */ + __le32 nodes; /* 68 the maximum number of nodes in cluster. */ + __u8 cluster_name[64]; /* 72 cluster name to which this md belongs */ + __u8 pad[256 - 136]; /* set to zero */ +} bitmap_super_t; + +/* notes: + * (1) This event counter is updated before the eventcounter in the md superblock + * When a bitmap is loaded, it is only accepted if this event counter is equal + * to, or one greater than, the event counter in the superblock. + * (2) This event counter is updated when the other one is *if*and*only*if* the + * array is not degraded. As bits are not cleared when the array is degraded, + * this represents the last time that any bits were cleared. + * If a device is being added that has an event count with this value or + * higher, it is accepted as conforming to the bitmap. + * (3)This is the number of sectors represented by the bitmap, and is the range that + * resync happens across. For raid1 and raid5/6 it is the size of individual + * devices. For raid10 it is the size of the array. + */ + +#ifdef __KERNEL__ + +/* the in-memory bitmap is represented by bitmap_pages */ +struct bitmap_page { + /* + * map points to the actual memory page + */ + char *map; + /* + * in emergencies (when map cannot be alloced), hijack the map + * pointer and use it as two counters itself + */ + unsigned int hijacked:1; + /* + * If any counter in this page is '1' or '2' - and so could be + * cleared then that page is marked as 'pending' + */ + unsigned int pending:1; + /* + * count of dirty bits on the page + */ + unsigned int count:30; +}; + +/* the main bitmap structure - one per mddev */ +struct bitmap { + + struct bitmap_counts { + spinlock_t lock; + struct bitmap_page *bp; + unsigned long pages; /* total number of pages + * in the bitmap */ + unsigned long missing_pages; /* number of pages + * not yet allocated */ + unsigned long chunkshift; /* chunksize = 2^chunkshift + * (for bitops) */ + unsigned long chunks; /* Total number of data + * chunks for the array */ + } counts; + + struct mddev *mddev; /* the md device that the bitmap is for */ + + __u64 events_cleared; + int need_sync; + + struct bitmap_storage { + struct file *file; /* backing disk file */ + struct page *sb_page; /* cached copy of the bitmap + * file superblock */ + struct page **filemap; /* list of cache pages for + * the file */ + unsigned long *filemap_attr; /* attributes associated + * w/ filemap pages */ + unsigned long file_pages; /* number of pages in the file*/ + unsigned long bytes; /* total bytes in the bitmap */ + } storage; + + unsigned long flags; + + int allclean; + + atomic_t behind_writes; + unsigned long behind_writes_used; /* highest actual value at runtime */ + + /* + * the bitmap daemon - periodically wakes up and sweeps the bitmap + * file, cleaning up bits and flushing out pages to disk as necessary + */ + unsigned long daemon_lastrun; /* jiffies of last run */ + unsigned long last_end_sync; /* when we lasted called end_sync to + * update bitmap with resync progress */ + + atomic_t pending_writes; /* pending writes to the bitmap file */ + wait_queue_head_t write_wait; + wait_queue_head_t overflow_wait; + wait_queue_head_t behind_wait; + + struct kernfs_node *sysfs_can_clear; + int cluster_slot; /* Slot offset for clustered env */ +}; + +/* the bitmap API */ + +/* these are used only by md/bitmap */ +struct bitmap *bitmap_create(struct mddev *mddev, int slot); +int bitmap_load(struct mddev *mddev); +void bitmap_flush(struct mddev *mddev); +void bitmap_destroy(struct mddev *mddev); + +void bitmap_print_sb(struct bitmap *bitmap); +void bitmap_update_sb(struct bitmap *bitmap); +void bitmap_status(struct seq_file *seq, struct bitmap *bitmap); + +int bitmap_setallbits(struct bitmap *bitmap); +void bitmap_write_all(struct bitmap *bitmap); + +void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e); + +/* these are exported */ +int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, + unsigned long sectors, int behind); +void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, + unsigned long sectors, int success, int behind); +int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded); +void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted); +void bitmap_close_sync(struct bitmap *bitmap); +void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force); +void bitmap_sync_with_cluster(struct mddev *mddev, + sector_t old_lo, sector_t old_hi, + sector_t new_lo, sector_t new_hi); + +void bitmap_unplug(struct bitmap *bitmap); +void bitmap_daemon_work(struct mddev *mddev); + +int bitmap_resize(struct bitmap *bitmap, sector_t blocks, + int chunksize, int init); +struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot); +int bitmap_copy_from_slot(struct mddev *mddev, int slot, + sector_t *lo, sector_t *hi, bool clear_bits); +void bitmap_free(struct bitmap *bitmap); +void bitmap_wait_behind_writes(struct mddev *mddev); +#endif + +#endif diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index bf41492a2cb0..bc81ecc24c96 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -15,7 +15,7 @@ #include #include #include "md.h" -#include "bitmap.h" +#include "md-bitmap.h" #include "md-cluster.h" #define LVB_SIZE 64 diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c new file mode 100644 index 000000000000..38264b38420f --- /dev/null +++ b/drivers/md/md-faulty.c @@ -0,0 +1,372 @@ +/* + * faulty.c : Multiple Devices driver for Linux + * + * Copyright (C) 2004 Neil Brown + * + * fautly-device-simulator personality for md + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * You should have received a copy of the GNU General Public License + * (for example /usr/src/linux/COPYING); if not, write to the Free + * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + + +/* + * The "faulty" personality causes some requests to fail. + * + * Possible failure modes are: + * reads fail "randomly" but succeed on retry + * writes fail "randomly" but succeed on retry + * reads for some address fail and then persist until a write + * reads for some address fail and then persist irrespective of write + * writes for some address fail and persist + * all writes fail + * + * Different modes can be active at a time, but only + * one can be set at array creation. Others can be added later. + * A mode can be one-shot or recurrent with the recurrence being + * once in every N requests. + * The bottom 5 bits of the "layout" indicate the mode. The + * remainder indicate a period, or 0 for one-shot. + * + * There is an implementation limit on the number of concurrently + * persisting-faulty blocks. When a new fault is requested that would + * exceed the limit, it is ignored. + * All current faults can be clear using a layout of "0". + * + * Requests are always sent to the device. If they are to fail, + * we clone the bio and insert a new b_end_io into the chain. + */ + +#define WriteTransient 0 +#define ReadTransient 1 +#define WritePersistent 2 +#define ReadPersistent 3 +#define WriteAll 4 /* doesn't go to device */ +#define ReadFixable 5 +#define Modes 6 + +#define ClearErrors 31 +#define ClearFaults 30 + +#define AllPersist 100 /* internal use only */ +#define NoPersist 101 + +#define ModeMask 0x1f +#define ModeShift 5 + +#define MaxFault 50 +#include +#include +#include +#include +#include "md.h" +#include + + +static void faulty_fail(struct bio *bio) +{ + struct bio *b = bio->bi_private; + + b->bi_iter.bi_size = bio->bi_iter.bi_size; + b->bi_iter.bi_sector = bio->bi_iter.bi_sector; + + bio_put(bio); + + bio_io_error(b); +} + +struct faulty_conf { + int period[Modes]; + atomic_t counters[Modes]; + sector_t faults[MaxFault]; + int modes[MaxFault]; + int nfaults; + struct md_rdev *rdev; +}; + +static int check_mode(struct faulty_conf *conf, int mode) +{ + if (conf->period[mode] == 0 && + atomic_read(&conf->counters[mode]) <= 0) + return 0; /* no failure, no decrement */ + + + if (atomic_dec_and_test(&conf->counters[mode])) { + if (conf->period[mode]) + atomic_set(&conf->counters[mode], conf->period[mode]); + return 1; + } + return 0; +} + +static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir) +{ + /* If we find a ReadFixable sector, we fix it ... */ + int i; + for (i=0; infaults; i++) + if (conf->faults[i] >= start && + conf->faults[i] < end) { + /* found it ... */ + switch (conf->modes[i] * 2 + dir) { + case WritePersistent*2+WRITE: return 1; + case ReadPersistent*2+READ: return 1; + case ReadFixable*2+READ: return 1; + case ReadFixable*2+WRITE: + conf->modes[i] = NoPersist; + return 0; + case AllPersist*2+READ: + case AllPersist*2+WRITE: return 1; + default: + return 0; + } + } + return 0; +} + +static void add_sector(struct faulty_conf *conf, sector_t start, int mode) +{ + int i; + int n = conf->nfaults; + for (i=0; infaults; i++) + if (conf->faults[i] == start) { + switch(mode) { + case NoPersist: conf->modes[i] = mode; return; + case WritePersistent: + if (conf->modes[i] == ReadPersistent || + conf->modes[i] == ReadFixable) + conf->modes[i] = AllPersist; + else + conf->modes[i] = WritePersistent; + return; + case ReadPersistent: + if (conf->modes[i] == WritePersistent) + conf->modes[i] = AllPersist; + else + conf->modes[i] = ReadPersistent; + return; + case ReadFixable: + if (conf->modes[i] == WritePersistent || + conf->modes[i] == ReadPersistent) + conf->modes[i] = AllPersist; + else + conf->modes[i] = ReadFixable; + return; + } + } else if (conf->modes[i] == NoPersist) + n = i; + + if (n >= MaxFault) + return; + conf->faults[n] = start; + conf->modes[n] = mode; + if (conf->nfaults == n) + conf->nfaults = n+1; +} + +static bool faulty_make_request(struct mddev *mddev, struct bio *bio) +{ + struct faulty_conf *conf = mddev->private; + int failit = 0; + + if (bio_data_dir(bio) == WRITE) { + /* write request */ + if (atomic_read(&conf->counters[WriteAll])) { + /* special case - don't decrement, don't generic_make_request, + * just fail immediately + */ + bio_io_error(bio); + return true; + } + + if (check_sector(conf, bio->bi_iter.bi_sector, + bio_end_sector(bio), WRITE)) + failit = 1; + if (check_mode(conf, WritePersistent)) { + add_sector(conf, bio->bi_iter.bi_sector, + WritePersistent); + failit = 1; + } + if (check_mode(conf, WriteTransient)) + failit = 1; + } else { + /* read request */ + if (check_sector(conf, bio->bi_iter.bi_sector, + bio_end_sector(bio), READ)) + failit = 1; + if (check_mode(conf, ReadTransient)) + failit = 1; + if (check_mode(conf, ReadPersistent)) { + add_sector(conf, bio->bi_iter.bi_sector, + ReadPersistent); + failit = 1; + } + if (check_mode(conf, ReadFixable)) { + add_sector(conf, bio->bi_iter.bi_sector, + ReadFixable); + failit = 1; + } + } + if (failit) { + struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set); + + bio_set_dev(b, conf->rdev->bdev); + b->bi_private = bio; + b->bi_end_io = faulty_fail; + bio = b; + } else + bio_set_dev(bio, conf->rdev->bdev); + + generic_make_request(bio); + return true; +} + +static void faulty_status(struct seq_file *seq, struct mddev *mddev) +{ + struct faulty_conf *conf = mddev->private; + int n; + + if ((n=atomic_read(&conf->counters[WriteTransient])) != 0) + seq_printf(seq, " WriteTransient=%d(%d)", + n, conf->period[WriteTransient]); + + if ((n=atomic_read(&conf->counters[ReadTransient])) != 0) + seq_printf(seq, " ReadTransient=%d(%d)", + n, conf->period[ReadTransient]); + + if ((n=atomic_read(&conf->counters[WritePersistent])) != 0) + seq_printf(seq, " WritePersistent=%d(%d)", + n, conf->period[WritePersistent]); + + if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0) + seq_printf(seq, " ReadPersistent=%d(%d)", + n, conf->period[ReadPersistent]); + + + if ((n=atomic_read(&conf->counters[ReadFixable])) != 0) + seq_printf(seq, " ReadFixable=%d(%d)", + n, conf->period[ReadFixable]); + + if ((n=atomic_read(&conf->counters[WriteAll])) != 0) + seq_printf(seq, " WriteAll"); + + seq_printf(seq, " nfaults=%d", conf->nfaults); +} + + +static int faulty_reshape(struct mddev *mddev) +{ + int mode = mddev->new_layout & ModeMask; + int count = mddev->new_layout >> ModeShift; + struct faulty_conf *conf = mddev->private; + + if (mddev->new_layout < 0) + return 0; + + /* new layout */ + if (mode == ClearFaults) + conf->nfaults = 0; + else if (mode == ClearErrors) { + int i; + for (i=0 ; i < Modes ; i++) { + conf->period[i] = 0; + atomic_set(&conf->counters[i], 0); + } + } else if (mode < Modes) { + conf->period[mode] = count; + if (!count) count++; + atomic_set(&conf->counters[mode], count); + } else + return -EINVAL; + mddev->new_layout = -1; + mddev->layout = -1; /* makes sure further changes come through */ + return 0; +} + +static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks) +{ + WARN_ONCE(raid_disks, + "%s does not support generic reshape\n", __func__); + + if (sectors == 0) + return mddev->dev_sectors; + + return sectors; +} + +static int faulty_run(struct mddev *mddev) +{ + struct md_rdev *rdev; + int i; + struct faulty_conf *conf; + + if (md_check_no_bitmap(mddev)) + return -EINVAL; + + conf = kmalloc(sizeof(*conf), GFP_KERNEL); + if (!conf) + return -ENOMEM; + + for (i=0; icounters[i], 0); + conf->period[i] = 0; + } + conf->nfaults = 0; + + rdev_for_each(rdev, mddev) { + conf->rdev = rdev; + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + } + + md_set_array_sectors(mddev, faulty_size(mddev, 0, 0)); + mddev->private = conf; + + faulty_reshape(mddev); + + return 0; +} + +static void faulty_free(struct mddev *mddev, void *priv) +{ + struct faulty_conf *conf = priv; + + kfree(conf); +} + +static struct md_personality faulty_personality = +{ + .name = "faulty", + .level = LEVEL_FAULTY, + .owner = THIS_MODULE, + .make_request = faulty_make_request, + .run = faulty_run, + .free = faulty_free, + .status = faulty_status, + .check_reshape = faulty_reshape, + .size = faulty_size, +}; + +static int __init raid_init(void) +{ + return register_md_personality(&faulty_personality); +} + +static void raid_exit(void) +{ + unregister_md_personality(&faulty_personality); +} + +module_init(raid_init); +module_exit(raid_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fault injection personality for MD"); +MODULE_ALIAS("md-personality-10"); /* faulty */ +MODULE_ALIAS("md-faulty"); +MODULE_ALIAS("md-level--5"); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c new file mode 100644 index 000000000000..773fc70dced7 --- /dev/null +++ b/drivers/md/md-linear.c @@ -0,0 +1,348 @@ +/* + linear.c : Multiple Devices driver for Linux + Copyright (C) 1994-96 Marc ZYNGIER + or + + + Linear mode management functions. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + You should have received a copy of the GNU General Public License + (for example /usr/src/linux/COPYING); if not, write to the Free + Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#include +#include +#include +#include +#include +#include +#include "md.h" +#include "md-linear.h" + +/* + * find which device holds a particular offset + */ +static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) +{ + int lo, mid, hi; + struct linear_conf *conf; + + lo = 0; + hi = mddev->raid_disks - 1; + conf = mddev->private; + + /* + * Binary Search + */ + + while (hi > lo) { + + mid = (hi + lo) / 2; + if (sector < conf->disks[mid].end_sector) + hi = mid; + else + lo = mid + 1; + } + + return conf->disks + lo; +} + +/* + * In linear_congested() conf->raid_disks is used as a copy of + * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks + * and conf->disks[] are created in linear_conf(), they are always + * consitent with each other, but mddev->raid_disks does not. + */ +static int linear_congested(struct mddev *mddev, int bits) +{ + struct linear_conf *conf; + int i, ret = 0; + + rcu_read_lock(); + conf = rcu_dereference(mddev->private); + + for (i = 0; i < conf->raid_disks && !ret ; i++) { + struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); + ret |= bdi_congested(q->backing_dev_info, bits); + } + + rcu_read_unlock(); + return ret; +} + +static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) +{ + struct linear_conf *conf; + sector_t array_sectors; + + conf = mddev->private; + WARN_ONCE(sectors || raid_disks, + "%s does not support generic reshape\n", __func__); + array_sectors = conf->array_sectors; + + return array_sectors; +} + +static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) +{ + struct linear_conf *conf; + struct md_rdev *rdev; + int i, cnt; + bool discard_supported = false; + + conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info), + GFP_KERNEL); + if (!conf) + return NULL; + + cnt = 0; + conf->array_sectors = 0; + + rdev_for_each(rdev, mddev) { + int j = rdev->raid_disk; + struct dev_info *disk = conf->disks + j; + sector_t sectors; + + if (j < 0 || j >= raid_disks || disk->rdev) { + pr_warn("md/linear:%s: disk numbering problem. Aborting!\n", + mdname(mddev)); + goto out; + } + + disk->rdev = rdev; + if (mddev->chunk_sectors) { + sectors = rdev->sectors; + sector_div(sectors, mddev->chunk_sectors); + rdev->sectors = sectors * mddev->chunk_sectors; + } + + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + + conf->array_sectors += rdev->sectors; + cnt++; + + if (blk_queue_discard(bdev_get_queue(rdev->bdev))) + discard_supported = true; + } + if (cnt != raid_disks) { + pr_warn("md/linear:%s: not enough drives present. Aborting!\n", + mdname(mddev)); + goto out; + } + + if (!discard_supported) + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + else + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + + /* + * Here we calculate the device offsets. + */ + conf->disks[0].end_sector = conf->disks[0].rdev->sectors; + + for (i = 1; i < raid_disks; i++) + conf->disks[i].end_sector = + conf->disks[i-1].end_sector + + conf->disks[i].rdev->sectors; + + /* + * conf->raid_disks is copy of mddev->raid_disks. The reason to + * keep a copy of mddev->raid_disks in struct linear_conf is, + * mddev->raid_disks may not be consistent with pointers number of + * conf->disks[] when it is updated in linear_add() and used to + * iterate old conf->disks[] earray in linear_congested(). + * Here conf->raid_disks is always consitent with number of + * pointers in conf->disks[] array, and mddev->private is updated + * with rcu_assign_pointer() in linear_addr(), such race can be + * avoided. + */ + conf->raid_disks = raid_disks; + + return conf; + +out: + kfree(conf); + return NULL; +} + +static int linear_run (struct mddev *mddev) +{ + struct linear_conf *conf; + int ret; + + if (md_check_no_bitmap(mddev)) + return -EINVAL; + conf = linear_conf(mddev, mddev->raid_disks); + + if (!conf) + return 1; + mddev->private = conf; + md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); + + ret = md_integrity_register(mddev); + if (ret) { + kfree(conf); + mddev->private = NULL; + } + return ret; +} + +static int linear_add(struct mddev *mddev, struct md_rdev *rdev) +{ + /* Adding a drive to a linear array allows the array to grow. + * It is permitted if the new drive has a matching superblock + * already on it, with raid_disk equal to raid_disks. + * It is achieved by creating a new linear_private_data structure + * and swapping it in in-place of the current one. + * The current one is never freed until the array is stopped. + * This avoids races. + */ + struct linear_conf *newconf, *oldconf; + + if (rdev->saved_raid_disk != mddev->raid_disks) + return -EINVAL; + + rdev->raid_disk = rdev->saved_raid_disk; + rdev->saved_raid_disk = -1; + + newconf = linear_conf(mddev,mddev->raid_disks+1); + + if (!newconf) + return -ENOMEM; + + /* newconf->raid_disks already keeps a copy of * the increased + * value of mddev->raid_disks, WARN_ONCE() is just used to make + * sure of this. It is possible that oldconf is still referenced + * in linear_congested(), therefore kfree_rcu() is used to free + * oldconf until no one uses it anymore. + */ + mddev_suspend(mddev); + oldconf = rcu_dereference_protected(mddev->private, + lockdep_is_held(&mddev->reconfig_mutex)); + mddev->raid_disks++; + WARN_ONCE(mddev->raid_disks != newconf->raid_disks, + "copied raid_disks doesn't match mddev->raid_disks"); + rcu_assign_pointer(mddev->private, newconf); + md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); + set_capacity(mddev->gendisk, mddev->array_sectors); + mddev_resume(mddev); + revalidate_disk(mddev->gendisk); + kfree_rcu(oldconf, rcu); + return 0; +} + +static void linear_free(struct mddev *mddev, void *priv) +{ + struct linear_conf *conf = priv; + + kfree(conf); +} + +static bool linear_make_request(struct mddev *mddev, struct bio *bio) +{ + char b[BDEVNAME_SIZE]; + struct dev_info *tmp_dev; + sector_t start_sector, end_sector, data_offset; + sector_t bio_sector = bio->bi_iter.bi_sector; + + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { + md_flush_request(mddev, bio); + return true; + } + + tmp_dev = which_dev(mddev, bio_sector); + start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; + end_sector = tmp_dev->end_sector; + data_offset = tmp_dev->rdev->data_offset; + + if (unlikely(bio_sector >= end_sector || + bio_sector < start_sector)) + goto out_of_bounds; + + if (unlikely(bio_end_sector(bio) > end_sector)) { + /* This bio crosses a device boundary, so we have to split it */ + struct bio *split = bio_split(bio, end_sector - bio_sector, + GFP_NOIO, mddev->bio_set); + bio_chain(split, bio); + generic_make_request(bio); + bio = split; + } + + bio_set_dev(bio, tmp_dev->rdev->bdev); + bio->bi_iter.bi_sector = bio->bi_iter.bi_sector - + start_sector + data_offset; + + if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && + !blk_queue_discard(bio->bi_disk->queue))) { + /* Just ignore it */ + bio_endio(bio); + } else { + if (mddev->gendisk) + trace_block_bio_remap(bio->bi_disk->queue, + bio, disk_devt(mddev->gendisk), + bio_sector); + mddev_check_writesame(mddev, bio); + mddev_check_write_zeroes(mddev, bio); + generic_make_request(bio); + } + return true; + +out_of_bounds: + pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n", + mdname(mddev), + (unsigned long long)bio->bi_iter.bi_sector, + bdevname(tmp_dev->rdev->bdev, b), + (unsigned long long)tmp_dev->rdev->sectors, + (unsigned long long)start_sector); + bio_io_error(bio); + return true; +} + +static void linear_status (struct seq_file *seq, struct mddev *mddev) +{ + seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); +} + +static void linear_quiesce(struct mddev *mddev, int state) +{ +} + +static struct md_personality linear_personality = +{ + .name = "linear", + .level = LEVEL_LINEAR, + .owner = THIS_MODULE, + .make_request = linear_make_request, + .run = linear_run, + .free = linear_free, + .status = linear_status, + .hot_add_disk = linear_add, + .size = linear_size, + .quiesce = linear_quiesce, + .congested = linear_congested, +}; + +static int __init linear_init (void) +{ + return register_md_personality (&linear_personality); +} + +static void linear_exit (void) +{ + unregister_md_personality (&linear_personality); +} + +module_init(linear_init); +module_exit(linear_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Linear device concatenation personality for MD"); +MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ +MODULE_ALIAS("md-linear"); +MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/md-linear.h b/drivers/md/md-linear.h new file mode 100644 index 000000000000..8d392e6098b3 --- /dev/null +++ b/drivers/md/md-linear.h @@ -0,0 +1,16 @@ +#ifndef _LINEAR_H +#define _LINEAR_H + +struct dev_info { + struct md_rdev *rdev; + sector_t end_sector; +}; + +struct linear_conf +{ + struct rcu_head rcu; + sector_t array_sectors; + int raid_disks; /* a copy of mddev->raid_disks */ + struct dev_info disks[0]; +}; +#endif diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c new file mode 100644 index 000000000000..5c70176fa24d --- /dev/null +++ b/drivers/md/md-multipath.c @@ -0,0 +1,509 @@ +/* + * multipath.c : Multiple Devices driver for Linux + * + * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat + * + * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman + * + * MULTIPATH management functions. + * + * derived from raid1.c. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * You should have received a copy of the GNU General Public License + * (for example /usr/src/linux/COPYING); if not, write to the Free + * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include +#include +#include +#include +#include +#include "md.h" +#include "md-multipath.h" + +#define MAX_WORK_PER_DISK 128 + +#define NR_RESERVED_BUFS 32 + +static int multipath_map (struct mpconf *conf) +{ + int i, disks = conf->raid_disks; + + /* + * Later we do read balancing on the read side + * now we use the first available disk. + */ + + rcu_read_lock(); + for (i = 0; i < disks; i++) { + struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); + if (rdev && test_bit(In_sync, &rdev->flags) && + !test_bit(Faulty, &rdev->flags)) { + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + return i; + } + } + rcu_read_unlock(); + + pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n"); + return (-1); +} + +static void multipath_reschedule_retry (struct multipath_bh *mp_bh) +{ + unsigned long flags; + struct mddev *mddev = mp_bh->mddev; + struct mpconf *conf = mddev->private; + + spin_lock_irqsave(&conf->device_lock, flags); + list_add(&mp_bh->retry_list, &conf->retry_list); + spin_unlock_irqrestore(&conf->device_lock, flags); + md_wakeup_thread(mddev->thread); +} + +/* + * multipath_end_bh_io() is called when we have finished servicing a multipathed + * operation and are ready to return a success/failure code to the buffer + * cache layer. + */ +static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status) +{ + struct bio *bio = mp_bh->master_bio; + struct mpconf *conf = mp_bh->mddev->private; + + bio->bi_status = status; + bio_endio(bio); + mempool_free(mp_bh, conf->pool); +} + +static void multipath_end_request(struct bio *bio) +{ + struct multipath_bh *mp_bh = bio->bi_private; + struct mpconf *conf = mp_bh->mddev->private; + struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev; + + if (!bio->bi_status) + multipath_end_bh_io(mp_bh, 0); + else if (!(bio->bi_opf & REQ_RAHEAD)) { + /* + * oops, IO error: + */ + char b[BDEVNAME_SIZE]; + md_error (mp_bh->mddev, rdev); + pr_info("multipath: %s: rescheduling sector %llu\n", + bdevname(rdev->bdev,b), + (unsigned long long)bio->bi_iter.bi_sector); + multipath_reschedule_retry(mp_bh); + } else + multipath_end_bh_io(mp_bh, bio->bi_status); + rdev_dec_pending(rdev, conf->mddev); +} + +static bool multipath_make_request(struct mddev *mddev, struct bio * bio) +{ + struct mpconf *conf = mddev->private; + struct multipath_bh * mp_bh; + struct multipath_info *multipath; + + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { + md_flush_request(mddev, bio); + return true; + } + + mp_bh = mempool_alloc(conf->pool, GFP_NOIO); + + mp_bh->master_bio = bio; + mp_bh->mddev = mddev; + + mp_bh->path = multipath_map(conf); + if (mp_bh->path < 0) { + bio_io_error(bio); + mempool_free(mp_bh, conf->pool); + return true; + } + multipath = conf->multipaths + mp_bh->path; + + bio_init(&mp_bh->bio, NULL, 0); + __bio_clone_fast(&mp_bh->bio, bio); + + mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset; + bio_set_dev(&mp_bh->bio, multipath->rdev->bdev); + mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT; + mp_bh->bio.bi_end_io = multipath_end_request; + mp_bh->bio.bi_private = mp_bh; + mddev_check_writesame(mddev, &mp_bh->bio); + mddev_check_write_zeroes(mddev, &mp_bh->bio); + generic_make_request(&mp_bh->bio); + return true; +} + +static void multipath_status(struct seq_file *seq, struct mddev *mddev) +{ + struct mpconf *conf = mddev->private; + int i; + + seq_printf (seq, " [%d/%d] [", conf->raid_disks, + conf->raid_disks - mddev->degraded); + rcu_read_lock(); + for (i = 0; i < conf->raid_disks; i++) { + struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); + seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); + } + rcu_read_unlock(); + seq_printf (seq, "]"); +} + +static int multipath_congested(struct mddev *mddev, int bits) +{ + struct mpconf *conf = mddev->private; + int i, ret = 0; + + rcu_read_lock(); + for (i = 0; i < mddev->raid_disks ; i++) { + struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); + if (rdev && !test_bit(Faulty, &rdev->flags)) { + struct request_queue *q = bdev_get_queue(rdev->bdev); + + ret |= bdi_congested(q->backing_dev_info, bits); + /* Just like multipath_map, we just check the + * first available device + */ + break; + } + } + rcu_read_unlock(); + return ret; +} + +/* + * Careful, this can execute in IRQ contexts as well! + */ +static void multipath_error (struct mddev *mddev, struct md_rdev *rdev) +{ + struct mpconf *conf = mddev->private; + char b[BDEVNAME_SIZE]; + + if (conf->raid_disks - mddev->degraded <= 1) { + /* + * Uh oh, we can do nothing if this is our last path, but + * first check if this is a queued request for a device + * which has just failed. + */ + pr_warn("multipath: only one IO path left and IO error.\n"); + /* leave it active... it's all we have */ + return; + } + /* + * Mark disk as unusable + */ + if (test_and_clear_bit(In_sync, &rdev->flags)) { + unsigned long flags; + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded++; + spin_unlock_irqrestore(&conf->device_lock, flags); + } + set_bit(Faulty, &rdev->flags); + set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); + pr_err("multipath: IO failure on %s, disabling IO path.\n" + "multipath: Operation continuing on %d IO paths.\n", + bdevname(rdev->bdev, b), + conf->raid_disks - mddev->degraded); +} + +static void print_multipath_conf (struct mpconf *conf) +{ + int i; + struct multipath_info *tmp; + + pr_debug("MULTIPATH conf printout:\n"); + if (!conf) { + pr_debug("(conf==NULL)\n"); + return; + } + pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, + conf->raid_disks); + + for (i = 0; i < conf->raid_disks; i++) { + char b[BDEVNAME_SIZE]; + tmp = conf->multipaths + i; + if (tmp->rdev) + pr_debug(" disk%d, o:%d, dev:%s\n", + i,!test_bit(Faulty, &tmp->rdev->flags), + bdevname(tmp->rdev->bdev,b)); + } +} + +static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) +{ + struct mpconf *conf = mddev->private; + struct request_queue *q; + int err = -EEXIST; + int path; + struct multipath_info *p; + int first = 0; + int last = mddev->raid_disks - 1; + + if (rdev->raid_disk >= 0) + first = last = rdev->raid_disk; + + print_multipath_conf(conf); + + for (path = first; path <= last; path++) + if ((p=conf->multipaths+path)->rdev == NULL) { + q = rdev->bdev->bd_disk->queue; + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + + err = md_integrity_add_rdev(rdev, mddev); + if (err) + break; + spin_lock_irq(&conf->device_lock); + mddev->degraded--; + rdev->raid_disk = path; + set_bit(In_sync, &rdev->flags); + spin_unlock_irq(&conf->device_lock); + rcu_assign_pointer(p->rdev, rdev); + err = 0; + break; + } + + print_multipath_conf(conf); + + return err; +} + +static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev) +{ + struct mpconf *conf = mddev->private; + int err = 0; + int number = rdev->raid_disk; + struct multipath_info *p = conf->multipaths + number; + + print_multipath_conf(conf); + + if (rdev == p->rdev) { + if (test_bit(In_sync, &rdev->flags) || + atomic_read(&rdev->nr_pending)) { + pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number); + err = -EBUSY; + goto abort; + } + p->rdev = NULL; + if (!test_bit(RemoveSynchronized, &rdev->flags)) { + synchronize_rcu(); + if (atomic_read(&rdev->nr_pending)) { + /* lost the race, try later */ + err = -EBUSY; + p->rdev = rdev; + goto abort; + } + } + err = md_integrity_register(mddev); + } +abort: + + print_multipath_conf(conf); + return err; +} + +/* + * This is a kernel thread which: + * + * 1. Retries failed read operations on working multipaths. + * 2. Updates the raid superblock when problems encounter. + * 3. Performs writes following reads for array syncronising. + */ + +static void multipathd(struct md_thread *thread) +{ + struct mddev *mddev = thread->mddev; + struct multipath_bh *mp_bh; + struct bio *bio; + unsigned long flags; + struct mpconf *conf = mddev->private; + struct list_head *head = &conf->retry_list; + + md_check_recovery(mddev); + for (;;) { + char b[BDEVNAME_SIZE]; + spin_lock_irqsave(&conf->device_lock, flags); + if (list_empty(head)) + break; + mp_bh = list_entry(head->prev, struct multipath_bh, retry_list); + list_del(head->prev); + spin_unlock_irqrestore(&conf->device_lock, flags); + + bio = &mp_bh->bio; + bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector; + + if ((mp_bh->path = multipath_map (conf))<0) { + pr_err("multipath: %s: unrecoverable IO read error for block %llu\n", + bio_devname(bio, b), + (unsigned long long)bio->bi_iter.bi_sector); + multipath_end_bh_io(mp_bh, BLK_STS_IOERR); + } else { + pr_err("multipath: %s: redirecting sector %llu to another IO path\n", + bio_devname(bio, b), + (unsigned long long)bio->bi_iter.bi_sector); + *bio = *(mp_bh->master_bio); + bio->bi_iter.bi_sector += + conf->multipaths[mp_bh->path].rdev->data_offset; + bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev); + bio->bi_opf |= REQ_FAILFAST_TRANSPORT; + bio->bi_end_io = multipath_end_request; + bio->bi_private = mp_bh; + generic_make_request(bio); + } + } + spin_unlock_irqrestore(&conf->device_lock, flags); +} + +static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks) +{ + WARN_ONCE(sectors || raid_disks, + "%s does not support generic reshape\n", __func__); + + return mddev->dev_sectors; +} + +static int multipath_run (struct mddev *mddev) +{ + struct mpconf *conf; + int disk_idx; + struct multipath_info *disk; + struct md_rdev *rdev; + int working_disks; + + if (md_check_no_bitmap(mddev)) + return -EINVAL; + + if (mddev->level != LEVEL_MULTIPATH) { + pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n", + mdname(mddev), mddev->level); + goto out; + } + /* + * copy the already verified devices into our private MULTIPATH + * bookkeeping area. [whatever we allocate in multipath_run(), + * should be freed in multipath_free()] + */ + + conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL); + mddev->private = conf; + if (!conf) + goto out; + + conf->multipaths = kzalloc(sizeof(struct multipath_info)*mddev->raid_disks, + GFP_KERNEL); + if (!conf->multipaths) + goto out_free_conf; + + working_disks = 0; + rdev_for_each(rdev, mddev) { + disk_idx = rdev->raid_disk; + if (disk_idx < 0 || + disk_idx >= mddev->raid_disks) + continue; + + disk = conf->multipaths + disk_idx; + disk->rdev = rdev; + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + + if (!test_bit(Faulty, &rdev->flags)) + working_disks++; + } + + conf->raid_disks = mddev->raid_disks; + conf->mddev = mddev; + spin_lock_init(&conf->device_lock); + INIT_LIST_HEAD(&conf->retry_list); + + if (!working_disks) { + pr_warn("multipath: no operational IO paths for %s\n", + mdname(mddev)); + goto out_free_conf; + } + mddev->degraded = conf->raid_disks - working_disks; + + conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS, + sizeof(struct multipath_bh)); + if (conf->pool == NULL) + goto out_free_conf; + + mddev->thread = md_register_thread(multipathd, mddev, + "multipath"); + if (!mddev->thread) + goto out_free_conf; + + pr_info("multipath: array %s active with %d out of %d IO paths\n", + mdname(mddev), conf->raid_disks - mddev->degraded, + mddev->raid_disks); + /* + * Ok, everything is just fine now + */ + md_set_array_sectors(mddev, multipath_size(mddev, 0, 0)); + + if (md_integrity_register(mddev)) + goto out_free_conf; + + return 0; + +out_free_conf: + mempool_destroy(conf->pool); + kfree(conf->multipaths); + kfree(conf); + mddev->private = NULL; +out: + return -EIO; +} + +static void multipath_free(struct mddev *mddev, void *priv) +{ + struct mpconf *conf = priv; + + mempool_destroy(conf->pool); + kfree(conf->multipaths); + kfree(conf); +} + +static struct md_personality multipath_personality = +{ + .name = "multipath", + .level = LEVEL_MULTIPATH, + .owner = THIS_MODULE, + .make_request = multipath_make_request, + .run = multipath_run, + .free = multipath_free, + .status = multipath_status, + .error_handler = multipath_error, + .hot_add_disk = multipath_add_disk, + .hot_remove_disk= multipath_remove_disk, + .size = multipath_size, + .congested = multipath_congested, +}; + +static int __init multipath_init (void) +{ + return register_md_personality (&multipath_personality); +} + +static void __exit multipath_exit (void) +{ + unregister_md_personality (&multipath_personality); +} + +module_init(multipath_init); +module_exit(multipath_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("simple multi-path personality for MD"); +MODULE_ALIAS("md-personality-7"); /* MULTIPATH */ +MODULE_ALIAS("md-multipath"); +MODULE_ALIAS("md-level--4"); diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h new file mode 100644 index 000000000000..717c60f62898 --- /dev/null +++ b/drivers/md/md-multipath.h @@ -0,0 +1,31 @@ +#ifndef _MULTIPATH_H +#define _MULTIPATH_H + +struct multipath_info { + struct md_rdev *rdev; +}; + +struct mpconf { + struct mddev *mddev; + struct multipath_info *multipaths; + int raid_disks; + spinlock_t device_lock; + struct list_head retry_list; + + mempool_t *pool; +}; + +/* + * this is our 'private' 'collective' MULTIPATH buffer head. + * it contains information about what kind of IO operations were started + * for this MULTIPATH operation, and about their status: + */ + +struct multipath_bh { + struct mddev *mddev; + struct bio *master_bio; + struct bio bio; + int path; + struct list_head retry_list; +}; +#endif diff --git a/drivers/md/md.c b/drivers/md/md.c index 707471e3cb01..97afb28c6f51 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -69,7 +69,7 @@ #include #include "md.h" -#include "bitmap.h" +#include "md-bitmap.h" #include "md-cluster.h" #ifndef MODULE diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c deleted file mode 100644 index b68e0666b9b0..000000000000 --- a/drivers/md/multipath.c +++ /dev/null @@ -1,509 +0,0 @@ -/* - * multipath.c : Multiple Devices driver for Linux - * - * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat - * - * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman - * - * MULTIPATH management functions. - * - * derived from raid1.c. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * You should have received a copy of the GNU General Public License - * (for example /usr/src/linux/COPYING); if not, write to the Free - * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include -#include -#include -#include -#include -#include "md.h" -#include "multipath.h" - -#define MAX_WORK_PER_DISK 128 - -#define NR_RESERVED_BUFS 32 - -static int multipath_map (struct mpconf *conf) -{ - int i, disks = conf->raid_disks; - - /* - * Later we do read balancing on the read side - * now we use the first available disk. - */ - - rcu_read_lock(); - for (i = 0; i < disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); - if (rdev && test_bit(In_sync, &rdev->flags) && - !test_bit(Faulty, &rdev->flags)) { - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - return i; - } - } - rcu_read_unlock(); - - pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n"); - return (-1); -} - -static void multipath_reschedule_retry (struct multipath_bh *mp_bh) -{ - unsigned long flags; - struct mddev *mddev = mp_bh->mddev; - struct mpconf *conf = mddev->private; - - spin_lock_irqsave(&conf->device_lock, flags); - list_add(&mp_bh->retry_list, &conf->retry_list); - spin_unlock_irqrestore(&conf->device_lock, flags); - md_wakeup_thread(mddev->thread); -} - -/* - * multipath_end_bh_io() is called when we have finished servicing a multipathed - * operation and are ready to return a success/failure code to the buffer - * cache layer. - */ -static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status) -{ - struct bio *bio = mp_bh->master_bio; - struct mpconf *conf = mp_bh->mddev->private; - - bio->bi_status = status; - bio_endio(bio); - mempool_free(mp_bh, conf->pool); -} - -static void multipath_end_request(struct bio *bio) -{ - struct multipath_bh *mp_bh = bio->bi_private; - struct mpconf *conf = mp_bh->mddev->private; - struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev; - - if (!bio->bi_status) - multipath_end_bh_io(mp_bh, 0); - else if (!(bio->bi_opf & REQ_RAHEAD)) { - /* - * oops, IO error: - */ - char b[BDEVNAME_SIZE]; - md_error (mp_bh->mddev, rdev); - pr_info("multipath: %s: rescheduling sector %llu\n", - bdevname(rdev->bdev,b), - (unsigned long long)bio->bi_iter.bi_sector); - multipath_reschedule_retry(mp_bh); - } else - multipath_end_bh_io(mp_bh, bio->bi_status); - rdev_dec_pending(rdev, conf->mddev); -} - -static bool multipath_make_request(struct mddev *mddev, struct bio * bio) -{ - struct mpconf *conf = mddev->private; - struct multipath_bh * mp_bh; - struct multipath_info *multipath; - - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); - return true; - } - - mp_bh = mempool_alloc(conf->pool, GFP_NOIO); - - mp_bh->master_bio = bio; - mp_bh->mddev = mddev; - - mp_bh->path = multipath_map(conf); - if (mp_bh->path < 0) { - bio_io_error(bio); - mempool_free(mp_bh, conf->pool); - return true; - } - multipath = conf->multipaths + mp_bh->path; - - bio_init(&mp_bh->bio, NULL, 0); - __bio_clone_fast(&mp_bh->bio, bio); - - mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset; - bio_set_dev(&mp_bh->bio, multipath->rdev->bdev); - mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT; - mp_bh->bio.bi_end_io = multipath_end_request; - mp_bh->bio.bi_private = mp_bh; - mddev_check_writesame(mddev, &mp_bh->bio); - mddev_check_write_zeroes(mddev, &mp_bh->bio); - generic_make_request(&mp_bh->bio); - return true; -} - -static void multipath_status(struct seq_file *seq, struct mddev *mddev) -{ - struct mpconf *conf = mddev->private; - int i; - - seq_printf (seq, " [%d/%d] [", conf->raid_disks, - conf->raid_disks - mddev->degraded); - rcu_read_lock(); - for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); - seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); - } - rcu_read_unlock(); - seq_printf (seq, "]"); -} - -static int multipath_congested(struct mddev *mddev, int bits) -{ - struct mpconf *conf = mddev->private; - int i, ret = 0; - - rcu_read_lock(); - for (i = 0; i < mddev->raid_disks ; i++) { - struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - /* Just like multipath_map, we just check the - * first available device - */ - break; - } - } - rcu_read_unlock(); - return ret; -} - -/* - * Careful, this can execute in IRQ contexts as well! - */ -static void multipath_error (struct mddev *mddev, struct md_rdev *rdev) -{ - struct mpconf *conf = mddev->private; - char b[BDEVNAME_SIZE]; - - if (conf->raid_disks - mddev->degraded <= 1) { - /* - * Uh oh, we can do nothing if this is our last path, but - * first check if this is a queued request for a device - * which has just failed. - */ - pr_warn("multipath: only one IO path left and IO error.\n"); - /* leave it active... it's all we have */ - return; - } - /* - * Mark disk as unusable - */ - if (test_and_clear_bit(In_sync, &rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded++; - spin_unlock_irqrestore(&conf->device_lock, flags); - } - set_bit(Faulty, &rdev->flags); - set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); - pr_err("multipath: IO failure on %s, disabling IO path.\n" - "multipath: Operation continuing on %d IO paths.\n", - bdevname(rdev->bdev, b), - conf->raid_disks - mddev->degraded); -} - -static void print_multipath_conf (struct mpconf *conf) -{ - int i; - struct multipath_info *tmp; - - pr_debug("MULTIPATH conf printout:\n"); - if (!conf) { - pr_debug("(conf==NULL)\n"); - return; - } - pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, - conf->raid_disks); - - for (i = 0; i < conf->raid_disks; i++) { - char b[BDEVNAME_SIZE]; - tmp = conf->multipaths + i; - if (tmp->rdev) - pr_debug(" disk%d, o:%d, dev:%s\n", - i,!test_bit(Faulty, &tmp->rdev->flags), - bdevname(tmp->rdev->bdev,b)); - } -} - -static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) -{ - struct mpconf *conf = mddev->private; - struct request_queue *q; - int err = -EEXIST; - int path; - struct multipath_info *p; - int first = 0; - int last = mddev->raid_disks - 1; - - if (rdev->raid_disk >= 0) - first = last = rdev->raid_disk; - - print_multipath_conf(conf); - - for (path = first; path <= last; path++) - if ((p=conf->multipaths+path)->rdev == NULL) { - q = rdev->bdev->bd_disk->queue; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - err = md_integrity_add_rdev(rdev, mddev); - if (err) - break; - spin_lock_irq(&conf->device_lock); - mddev->degraded--; - rdev->raid_disk = path; - set_bit(In_sync, &rdev->flags); - spin_unlock_irq(&conf->device_lock); - rcu_assign_pointer(p->rdev, rdev); - err = 0; - break; - } - - print_multipath_conf(conf); - - return err; -} - -static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev) -{ - struct mpconf *conf = mddev->private; - int err = 0; - int number = rdev->raid_disk; - struct multipath_info *p = conf->multipaths + number; - - print_multipath_conf(conf); - - if (rdev == p->rdev) { - if (test_bit(In_sync, &rdev->flags) || - atomic_read(&rdev->nr_pending)) { - pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number); - err = -EBUSY; - goto abort; - } - p->rdev = NULL; - if (!test_bit(RemoveSynchronized, &rdev->flags)) { - synchronize_rcu(); - if (atomic_read(&rdev->nr_pending)) { - /* lost the race, try later */ - err = -EBUSY; - p->rdev = rdev; - goto abort; - } - } - err = md_integrity_register(mddev); - } -abort: - - print_multipath_conf(conf); - return err; -} - -/* - * This is a kernel thread which: - * - * 1. Retries failed read operations on working multipaths. - * 2. Updates the raid superblock when problems encounter. - * 3. Performs writes following reads for array syncronising. - */ - -static void multipathd(struct md_thread *thread) -{ - struct mddev *mddev = thread->mddev; - struct multipath_bh *mp_bh; - struct bio *bio; - unsigned long flags; - struct mpconf *conf = mddev->private; - struct list_head *head = &conf->retry_list; - - md_check_recovery(mddev); - for (;;) { - char b[BDEVNAME_SIZE]; - spin_lock_irqsave(&conf->device_lock, flags); - if (list_empty(head)) - break; - mp_bh = list_entry(head->prev, struct multipath_bh, retry_list); - list_del(head->prev); - spin_unlock_irqrestore(&conf->device_lock, flags); - - bio = &mp_bh->bio; - bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector; - - if ((mp_bh->path = multipath_map (conf))<0) { - pr_err("multipath: %s: unrecoverable IO read error for block %llu\n", - bio_devname(bio, b), - (unsigned long long)bio->bi_iter.bi_sector); - multipath_end_bh_io(mp_bh, BLK_STS_IOERR); - } else { - pr_err("multipath: %s: redirecting sector %llu to another IO path\n", - bio_devname(bio, b), - (unsigned long long)bio->bi_iter.bi_sector); - *bio = *(mp_bh->master_bio); - bio->bi_iter.bi_sector += - conf->multipaths[mp_bh->path].rdev->data_offset; - bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev); - bio->bi_opf |= REQ_FAILFAST_TRANSPORT; - bio->bi_end_io = multipath_end_request; - bio->bi_private = mp_bh; - generic_make_request(bio); - } - } - spin_unlock_irqrestore(&conf->device_lock, flags); -} - -static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - WARN_ONCE(sectors || raid_disks, - "%s does not support generic reshape\n", __func__); - - return mddev->dev_sectors; -} - -static int multipath_run (struct mddev *mddev) -{ - struct mpconf *conf; - int disk_idx; - struct multipath_info *disk; - struct md_rdev *rdev; - int working_disks; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - - if (mddev->level != LEVEL_MULTIPATH) { - pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n", - mdname(mddev), mddev->level); - goto out; - } - /* - * copy the already verified devices into our private MULTIPATH - * bookkeeping area. [whatever we allocate in multipath_run(), - * should be freed in multipath_free()] - */ - - conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL); - mddev->private = conf; - if (!conf) - goto out; - - conf->multipaths = kzalloc(sizeof(struct multipath_info)*mddev->raid_disks, - GFP_KERNEL); - if (!conf->multipaths) - goto out_free_conf; - - working_disks = 0; - rdev_for_each(rdev, mddev) { - disk_idx = rdev->raid_disk; - if (disk_idx < 0 || - disk_idx >= mddev->raid_disks) - continue; - - disk = conf->multipaths + disk_idx; - disk->rdev = rdev; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - if (!test_bit(Faulty, &rdev->flags)) - working_disks++; - } - - conf->raid_disks = mddev->raid_disks; - conf->mddev = mddev; - spin_lock_init(&conf->device_lock); - INIT_LIST_HEAD(&conf->retry_list); - - if (!working_disks) { - pr_warn("multipath: no operational IO paths for %s\n", - mdname(mddev)); - goto out_free_conf; - } - mddev->degraded = conf->raid_disks - working_disks; - - conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS, - sizeof(struct multipath_bh)); - if (conf->pool == NULL) - goto out_free_conf; - - mddev->thread = md_register_thread(multipathd, mddev, - "multipath"); - if (!mddev->thread) - goto out_free_conf; - - pr_info("multipath: array %s active with %d out of %d IO paths\n", - mdname(mddev), conf->raid_disks - mddev->degraded, - mddev->raid_disks); - /* - * Ok, everything is just fine now - */ - md_set_array_sectors(mddev, multipath_size(mddev, 0, 0)); - - if (md_integrity_register(mddev)) - goto out_free_conf; - - return 0; - -out_free_conf: - mempool_destroy(conf->pool); - kfree(conf->multipaths); - kfree(conf); - mddev->private = NULL; -out: - return -EIO; -} - -static void multipath_free(struct mddev *mddev, void *priv) -{ - struct mpconf *conf = priv; - - mempool_destroy(conf->pool); - kfree(conf->multipaths); - kfree(conf); -} - -static struct md_personality multipath_personality = -{ - .name = "multipath", - .level = LEVEL_MULTIPATH, - .owner = THIS_MODULE, - .make_request = multipath_make_request, - .run = multipath_run, - .free = multipath_free, - .status = multipath_status, - .error_handler = multipath_error, - .hot_add_disk = multipath_add_disk, - .hot_remove_disk= multipath_remove_disk, - .size = multipath_size, - .congested = multipath_congested, -}; - -static int __init multipath_init (void) -{ - return register_md_personality (&multipath_personality); -} - -static void __exit multipath_exit (void) -{ - unregister_md_personality (&multipath_personality); -} - -module_init(multipath_init); -module_exit(multipath_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("simple multi-path personality for MD"); -MODULE_ALIAS("md-personality-7"); /* MULTIPATH */ -MODULE_ALIAS("md-multipath"); -MODULE_ALIAS("md-level--4"); diff --git a/drivers/md/multipath.h b/drivers/md/multipath.h deleted file mode 100644 index 717c60f62898..000000000000 --- a/drivers/md/multipath.h +++ /dev/null @@ -1,31 +0,0 @@ -#ifndef _MULTIPATH_H -#define _MULTIPATH_H - -struct multipath_info { - struct md_rdev *rdev; -}; - -struct mpconf { - struct mddev *mddev; - struct multipath_info *multipaths; - int raid_disks; - spinlock_t device_lock; - struct list_head retry_list; - - mempool_t *pool; -}; - -/* - * this is our 'private' 'collective' MULTIPATH buffer head. - * it contains information about what kind of IO operations were started - * for this MULTIPATH operation, and about their status: - */ - -struct multipath_bh { - struct mddev *mddev; - struct bio *master_bio; - struct bio bio; - int path; - struct list_head retry_list; -}; -#endif diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 35264ad0ec70..efdabd3040e7 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -43,7 +43,7 @@ #include "md.h" #include "raid1.h" -#include "bitmap.h" +#include "md-bitmap.h" #define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_HAS_JOURNAL) | \ diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 950fbefbedbb..862cbd162e1c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -29,7 +29,7 @@ #include "md.h" #include "raid10.h" #include "raid0.h" -#include "bitmap.h" +#include "md-bitmap.h" /* * RAID10 provides a combination of RAID0 and RAID1 functionality. diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 0b7406ac8ce1..2b450eee21fa 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -23,7 +23,7 @@ #include #include "md.h" #include "raid5.h" -#include "bitmap.h" +#include "md-bitmap.h" #include "raid5-log.h" /* diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 928e24a07133..10c0d87074f0 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -63,7 +63,7 @@ #include "md.h" #include "raid5.h" #include "raid0.h" -#include "bitmap.h" +#include "md-bitmap.h" #include "raid5-log.h" #define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED) -- cgit v1.2.3