* wait if count gets too high, wake when it drops to half.
*/
+#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
-#include <linux/config.h>
#include <linux/timer.h>
#include <linux/sched.h>
#include <linux/list.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/buffer_head.h>
-#include <linux/raid/md.h>
-#include <linux/raid/bitmap.h>
+#include "md.h"
+#include "bitmap.h"
/* debug macros */
return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
}
-#define WRITE_POOL_SIZE 256
/*
* just a placeholder - calls kmalloc for bitmap pages
* allocated while we're using it
*/
static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
+__releases(bitmap->lock)
+__acquires(bitmap->lock)
{
unsigned char *mappage;
if (page >= bitmap->pages) {
- printk(KERN_ALERT
- "%s: invalid bitmap page request: %lu (> %lu)\n",
- bmname(bitmap), page, bitmap->pages-1);
+ /* This can happen if bitmap_start_sync goes beyond
+ * End-of-device while looking for a whole page.
+ * It is harmless.
+ */
return -EINVAL;
}
* bitmap file handling - read and write the bitmap file and its superblock
*/
-/* copy the pathname of a file to a buffer */
-char *file_path(struct file *file, char *buf, int count)
-{
- struct dentry *d;
- struct vfsmount *v;
-
- if (!buf)
- return NULL;
-
- d = file->f_dentry;
- v = file->f_vfsmnt;
-
- buf = d_path(d, v, buf, count);
-
- return IS_ERR(buf) ? NULL : buf;
-}
-
/*
* basic page I/O operations
*/
/* IO operations when bitmap is stored near all superblocks */
-static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long index)
+static struct page *read_sb_page(mddev_t *mddev, long offset,
+ struct page *page,
+ unsigned long index, int size)
{
/* choose a good rdev and read the page from there */
mdk_rdev_t *rdev;
- struct list_head *tmp;
- struct page *page = alloc_page(GFP_KERNEL);
sector_t target;
if (!page)
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
return ERR_PTR(-ENOMEM);
- ITERATE_RDEV(mddev, rdev, tmp) {
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
if (! test_bit(In_sync, &rdev->flags)
|| test_bit(Faulty, &rdev->flags))
continue;
- target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);
+ target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
- if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
+ if (sync_page_io(rdev->bdev, target,
+ roundup(size, bdev_logical_block_size(rdev->bdev)),
+ page, READ)) {
page->index = index;
+ attach_page_buffers(page, NULL); /* so that free_buffer will
+ * quietly no-op */
return page;
}
}
}
-static int write_sb_page(mddev_t *mddev, long offset, struct page *page, int wait)
+static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
{
- mdk_rdev_t *rdev;
- struct list_head *tmp;
+ /* Iterate the disks of an mddev, using rcu to protect access to the
+ * linked list, and raising the refcount of devices we return to ensure
+ * they don't disappear while in use.
+ * As devices are only added or removed when raid_disk is < 0 and
+ * nr_pending is 0 and In_sync is clear, the entries we return will
+ * still be in the same position on the list when we re-enter
+ * list_for_each_continue_rcu.
+ */
+ struct list_head *pos;
+ rcu_read_lock();
+ if (rdev == NULL)
+ /* start at the beginning */
+ pos = &mddev->disks;
+ else {
+ /* release the previous rdev and start from there. */
+ rdev_dec_pending(rdev, mddev);
+ pos = &rdev->same_set;
+ }
+ list_for_each_continue_rcu(pos, &mddev->disks) {
+ rdev = list_entry(pos, mdk_rdev_t, same_set);
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags)) {
+ /* this is a usable devices */
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+ return rdev;
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
+}
- ITERATE_RDEV(mddev, rdev, tmp)
- if (test_bit(In_sync, &rdev->flags)
- && !test_bit(Faulty, &rdev->flags))
+static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
+{
+ mdk_rdev_t *rdev = NULL;
+ mddev_t *mddev = bitmap->mddev;
+
+ while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
+ int size = PAGE_SIZE;
+ if (page->index == bitmap->file_pages-1)
+ size = roundup(bitmap->last_page_size,
+ bdev_logical_block_size(rdev->bdev));
+ /* Just make sure we aren't corrupting data or
+ * metadata
+ */
+ if (bitmap->offset < 0) {
+ /* DATA BITMAP METADATA */
+ if (bitmap->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 + bitmap->offset)
+ /* data runs in to bitmap */
+ goto bad_alignment;
+ } else if (rdev->sb_start < rdev->data_offset) {
+ /* METADATA BITMAP DATA */
+ if (rdev->sb_start
+ + bitmap->offset
+ + page->index*(PAGE_SIZE/512) + size/512
+ > rdev->data_offset)
+ /* bitmap runs in to data */
+ goto bad_alignment;
+ } else {
+ /* DATA METADATA BITMAP - no problems */
+ }
md_super_write(mddev, rdev,
- (rdev->sb_offset<<1) + offset
+ rdev->sb_start + bitmap->offset
+ page->index * (PAGE_SIZE/512),
- PAGE_SIZE,
+ size,
page);
+ }
if (wait)
md_super_wait(mddev);
return 0;
+
+ bad_alignment:
+ return -EINVAL;
}
+static void bitmap_file_kick(struct bitmap *bitmap);
/*
* write out a page to a file
*/
-static int write_page(struct bitmap *bitmap, struct page *page, int wait)
+static void write_page(struct bitmap *bitmap, struct page *page, int wait)
{
- int ret = -ENOMEM;
+ struct buffer_head *bh;
+
+ if (bitmap->file == NULL) {
+ switch (write_sb_page(bitmap, page, wait)) {
+ case -EINVAL:
+ bitmap->flags |= BITMAP_WRITE_ERROR;
+ }
+ } else {
- if (bitmap->file == NULL)
- return write_sb_page(bitmap->mddev, bitmap->offset, page, wait);
+ bh = page_buffers(page);
- flush_dcache_page(page); /* make sure visible to anyone reading the file */
+ while (bh && bh->b_blocknr) {
+ atomic_inc(&bitmap->pending_writes);
+ set_buffer_locked(bh);
+ set_buffer_mapped(bh);
+ submit_bh(WRITE, bh);
+ bh = bh->b_this_page;
+ }
- if (wait)
- lock_page(page);
- else {
- if (TestSetPageLocked(page))
- return -EAGAIN; /* already locked */
- if (PageWriteback(page)) {
- unlock_page(page);
- return -EAGAIN;
+ if (wait) {
+ wait_event(bitmap->write_wait,
+ atomic_read(&bitmap->pending_writes)==0);
}
}
+ if (bitmap->flags & BITMAP_WRITE_ERROR)
+ bitmap_file_kick(bitmap);
+}
- ret = page->mapping->a_ops->prepare_write(bitmap->file, page, 0, PAGE_SIZE);
- if (!ret)
- ret = page->mapping->a_ops->commit_write(bitmap->file, page, 0,
- PAGE_SIZE);
- if (ret) {
- unlock_page(page);
- return ret;
+static void end_bitmap_write(struct buffer_head *bh, int uptodate)
+{
+ struct bitmap *bitmap = bh->b_private;
+ unsigned long flags;
+
+ if (!uptodate) {
+ spin_lock_irqsave(&bitmap->lock, flags);
+ bitmap->flags |= BITMAP_WRITE_ERROR;
+ spin_unlock_irqrestore(&bitmap->lock, flags);
}
+ if (atomic_dec_and_test(&bitmap->pending_writes))
+ wake_up(&bitmap->write_wait);
+}
- set_page_dirty(page); /* force it to be written out */
+/* copied from buffer.c */
+static void
+__clear_page_buffers(struct page *page)
+{
+ ClearPagePrivate(page);
+ set_page_private(page, 0);
+ page_cache_release(page);
+}
+static void free_buffers(struct page *page)
+{
+ struct buffer_head *bh = page_buffers(page);
- if (!wait) {
- /* add to list to be waited for */
- struct page_list *item = mempool_alloc(bitmap->write_pool, GFP_NOIO);
- item->page = page;
- spin_lock(&bitmap->write_lock);
- list_add(&item->list, &bitmap->complete_pages);
- spin_unlock(&bitmap->write_lock);
+ while (bh) {
+ struct buffer_head *next = bh->b_this_page;
+ free_buffer_head(bh);
+ bh = next;
}
- return write_one_page(page, wait);
+ __clear_page_buffers(page);
+ put_page(page);
}
-/* read a page from a file, pinning it into cache, and return bytes_read */
+/* read a page from a file.
+ * We both read the page, and attach buffers to the page to record the
+ * address of each block (using bmap). These addresses will be used
+ * to write the block later, completely bypassing the filesystem.
+ * This usage is similar to how swap files are handled, and allows us
+ * to write to a file with no concerns of memory allocation failing.
+ */
static struct page *read_page(struct file *file, unsigned long index,
- unsigned long *bytes_read)
+ struct bitmap *bitmap,
+ unsigned long count)
{
- struct inode *inode = file->f_mapping->host;
struct page *page = NULL;
- loff_t isize = i_size_read(inode);
- unsigned long end_index = isize >> PAGE_SHIFT;
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct buffer_head *bh;
+ sector_t block;
PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE,
(unsigned long long)index << PAGE_SHIFT);
- page = read_cache_page(inode->i_mapping, index,
- (filler_t *)inode->i_mapping->a_ops->readpage, file);
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ page = ERR_PTR(-ENOMEM);
if (IS_ERR(page))
goto out;
- wait_on_page_locked(page);
- if (!PageUptodate(page) || PageError(page)) {
+
+ bh = alloc_page_buffers(page, 1<<inode->i_blkbits, 0);
+ if (!bh) {
put_page(page);
- page = ERR_PTR(-EIO);
+ page = ERR_PTR(-ENOMEM);
goto out;
}
+ attach_page_buffers(page, bh);
+ block = index << (PAGE_SHIFT - inode->i_blkbits);
+ while (bh) {
+ if (count == 0)
+ bh->b_blocknr = 0;
+ else {
+ bh->b_blocknr = bmap(inode, block);
+ if (bh->b_blocknr == 0) {
+ /* Cannot use this file! */
+ free_buffers(page);
+ page = ERR_PTR(-EINVAL);
+ goto out;
+ }
+ bh->b_bdev = inode->i_sb->s_bdev;
+ if (count < (1<<inode->i_blkbits))
+ count = 0;
+ else
+ count -= (1<<inode->i_blkbits);
+
+ bh->b_end_io = end_bitmap_write;
+ bh->b_private = bitmap;
+ atomic_inc(&bitmap->pending_writes);
+ set_buffer_locked(bh);
+ set_buffer_mapped(bh);
+ submit_bh(READ, bh);
+ }
+ block++;
+ bh = bh->b_this_page;
+ }
+ page->index = index;
- if (index > end_index) /* we have read beyond EOF */
- *bytes_read = 0;
- else if (index == end_index) /* possible short read */
- *bytes_read = isize & ~PAGE_MASK;
- else
- *bytes_read = PAGE_SIZE; /* got a full page */
+ wait_event(bitmap->write_wait,
+ atomic_read(&bitmap->pending_writes)==0);
+ if (bitmap->flags & BITMAP_WRITE_ERROR) {
+ free_buffers(page);
+ page = ERR_PTR(-EIO);
+ }
out:
if (IS_ERR(page))
printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
*/
/* update the event counter and sync the superblock to disk */
-int bitmap_update_sb(struct bitmap *bitmap)
+void bitmap_update_sb(struct bitmap *bitmap)
{
bitmap_super_t *sb;
unsigned long flags;
if (!bitmap || !bitmap->mddev) /* no bitmap for this array */
- return 0;
+ return;
spin_lock_irqsave(&bitmap->lock, flags);
if (!bitmap->sb_page) { /* no superblock */
spin_unlock_irqrestore(&bitmap->lock, flags);
- return 0;
+ return;
}
spin_unlock_irqrestore(&bitmap->lock, flags);
sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
sb->events = cpu_to_le64(bitmap->mddev->events);
- if (!bitmap->mddev->degraded)
- sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+ if (bitmap->mddev->events < bitmap->events_cleared) {
+ /* rocking back to read-only */
+ bitmap->events_cleared = bitmap->mddev->events;
+ sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
+ }
kunmap_atomic(sb, KM_USER0);
- return write_page(bitmap, bitmap->sb_page, 1);
+ write_page(bitmap, bitmap->sb_page, 1);
}
/* print out the bitmap file superblock */
char *reason = NULL;
bitmap_super_t *sb;
unsigned long chunksize, daemon_sleep, write_behind;
- unsigned long bytes_read;
unsigned long long events;
int err = -EINVAL;
/* page 0 is the superblock, read it... */
- if (bitmap->file)
- bitmap->sb_page = read_page(bitmap->file, 0, &bytes_read);
- else {
- bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0);
- bytes_read = PAGE_SIZE;
+ if (bitmap->file) {
+ loff_t isize = i_size_read(bitmap->file->f_mapping->host);
+ int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
+
+ bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
+ } else {
+ bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset,
+ NULL,
+ 0, sizeof(bitmap_super_t));
}
if (IS_ERR(bitmap->sb_page)) {
err = PTR_ERR(bitmap->sb_page);
sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
- if (bytes_read < sizeof(*sb)) { /* short read */
- printk(KERN_INFO "%s: bitmap file superblock truncated\n",
- bmname(bitmap));
- err = -ENOSPC;
- goto out;
- }
-
chunksize = le32_to_cpu(sb->chunksize);
daemon_sleep = le32_to_cpu(sb->daemon_sleep);
write_behind = le32_to_cpu(sb->write_behind);
else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
reason = "unrecognized superblock version";
- else if (chunksize < PAGE_SIZE)
+ else if (chunksize < 512)
reason = "bitmap chunksize too small";
else if ((1 << ffz(~chunksize)) != chunksize)
reason = "bitmap chunksize not a power of 2";
printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) "
"-- forcing full recovery\n", bmname(bitmap), events,
(unsigned long long) bitmap->mddev->events);
- sb->state |= BITMAP_STALE;
+ sb->state |= cpu_to_le32(BITMAP_STALE);
}
success:
/* assign fields using values from superblock */
bitmap->daemon_sleep = daemon_sleep;
bitmap->daemon_lastrun = jiffies;
bitmap->max_write_behind = write_behind;
- bitmap->flags |= sb->state;
+ bitmap->flags |= le32_to_cpu(sb->state);
if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
bitmap->flags |= BITMAP_HOSTENDIAN;
bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
- if (sb->state & BITMAP_STALE)
+ if (sb->state & cpu_to_le32(BITMAP_STALE))
bitmap->events_cleared = bitmap->mddev->events;
err = 0;
out:
MASK_UNSET
};
-/* record the state of the bitmap in the superblock */
-static void bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
- enum bitmap_mask_op op)
+/* record the state of the bitmap in the superblock. Return the old value */
+static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
+ enum bitmap_mask_op op)
{
bitmap_super_t *sb;
unsigned long flags;
+ int old;
spin_lock_irqsave(&bitmap->lock, flags);
if (!bitmap->sb_page) { /* can't set the state */
spin_unlock_irqrestore(&bitmap->lock, flags);
- return;
+ return 0;
}
spin_unlock_irqrestore(&bitmap->lock, flags);
sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+ old = le32_to_cpu(sb->state) & bits;
switch (op) {
- case MASK_SET: sb->state |= bits;
+ case MASK_SET: sb->state |= cpu_to_le32(bits);
break;
- case MASK_UNSET: sb->state &= ~bits;
+ case MASK_UNSET: sb->state &= cpu_to_le32(~bits);
break;
default: BUG();
}
kunmap_atomic(sb, KM_USER0);
+ return old;
}
/*
static inline struct page *filemap_get_page(struct bitmap *bitmap,
unsigned long chunk)
{
+ if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
}
while (pages--)
if (map[pages]->index != 0) /* 0 is sb_page, release it below */
- put_page(map[pages]);
+ free_buffers(map[pages]);
kfree(map);
kfree(attr);
- safe_put_page(sb_page);
-}
-
-/* dequeue the next item in a page list -- don't call from irq context */
-static struct page_list *dequeue_page(struct bitmap *bitmap)
-{
- struct page_list *item = NULL;
- struct list_head *head = &bitmap->complete_pages;
-
- spin_lock(&bitmap->write_lock);
- if (list_empty(head))
- goto out;
- item = list_entry(head->prev, struct page_list, list);
- list_del(head->prev);
-out:
- spin_unlock(&bitmap->write_lock);
- return item;
-}
-
-static void drain_write_queues(struct bitmap *bitmap)
-{
- struct page_list *item;
-
- while ((item = dequeue_page(bitmap))) {
- /* don't bother to wait */
- mempool_free(item, bitmap->write_pool);
- }
+ if (sb_page)
+ free_buffers(sb_page);
}
static void bitmap_file_put(struct bitmap *bitmap)
bitmap->file = NULL;
spin_unlock_irqrestore(&bitmap->lock, flags);
- drain_write_queues(bitmap);
-
+ if (file)
+ wait_event(bitmap->write_wait,
+ atomic_read(&bitmap->pending_writes)==0);
bitmap_file_unmap(bitmap);
- if (file)
+ if (file) {
+ struct inode *inode = file->f_path.dentry->d_inode;
+ invalidate_mapping_pages(inode->i_mapping, 0, -1);
fput(file);
+ }
}
{
char *path, *ptr = NULL;
- bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET);
- bitmap_update_sb(bitmap);
+ if (bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET) == 0) {
+ bitmap_update_sb(bitmap);
+
+ if (bitmap->file) {
+ path = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (path)
+ ptr = d_path(&bitmap->file->f_path, path,
+ PAGE_SIZE);
- if (bitmap->file) {
- path = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (path)
- ptr = file_path(bitmap->file, path, PAGE_SIZE);
- printk(KERN_ALERT "%s: kicking failed bitmap file %s from array!\n",
- bmname(bitmap), ptr ? ptr : "");
+ printk(KERN_ALERT
+ "%s: kicking failed bitmap file %s from array!\n",
+ bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
- kfree(path);
+ kfree(path);
+ } else
+ printk(KERN_ALERT
+ "%s: disabling internal bitmap due to errors\n",
+ bmname(bitmap));
}
bitmap_file_put(bitmap);
}
page = filemap_get_page(bitmap, chunk);
+ if (!page) return;
bit = file_page_offset(chunk);
/* set the bit */
}
-static void bitmap_writeback(struct bitmap *bitmap);
-
/* this gets called when the md device is ready to unplug its underlying
* (slave) device queues -- before we let any writes go down, we need to
* sync the dirty pages of the bitmap file to disk */
-int bitmap_unplug(struct bitmap *bitmap)
+void bitmap_unplug(struct bitmap *bitmap)
{
unsigned long i, flags;
int dirty, need_write;
struct page *page;
int wait = 0;
- int err;
if (!bitmap)
- return 0;
+ return;
/* look at each page to see if there are any set bits that need to be
* flushed out to disk */
spin_lock_irqsave(&bitmap->lock, flags);
if (!bitmap->filemap) {
spin_unlock_irqrestore(&bitmap->lock, flags);
- return 0;
+ return;
}
page = bitmap->filemap[i];
dirty = test_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
wait = 1;
spin_unlock_irqrestore(&bitmap->lock, flags);
- if (dirty | need_write) {
- err = write_page(bitmap, page, 0);
- if (err == -EAGAIN) {
- if (dirty)
- err = write_page(bitmap, page, 1);
- else
- err = 0;
- }
- if (err)
- return 1;
- }
+ if (dirty | need_write)
+ write_page(bitmap, page, 0);
}
if (wait) { /* if any writes were performed, we need to wait on them */
if (bitmap->file)
- bitmap_writeback(bitmap);
+ wait_event(bitmap->write_wait,
+ atomic_read(&bitmap->pending_writes)==0);
else
md_super_wait(bitmap->mddev);
}
- return 0;
+ if (bitmap->flags & BITMAP_WRITE_ERROR)
+ bitmap_file_kick(bitmap);
}
static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
struct page *page = NULL, *oldpage = NULL;
unsigned long num_pages, bit_cnt = 0;
struct file *file;
- unsigned long bytes, offset, dummy;
+ unsigned long bytes, offset;
int outofdate;
int ret = -ENOSPC;
void *paddr;
bmname(bitmap),
(unsigned long) i_size_read(file->f_mapping->host),
bytes + sizeof(bitmap_super_t));
- goto out;
+ goto err;
}
ret = -ENOMEM;
bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
if (!bitmap->filemap)
- goto out;
+ goto err;
/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
bitmap->filemap_attr = kzalloc(
- (((num_pages*4/8)+sizeof(unsigned long)-1)
- /sizeof(unsigned long))
- *sizeof(unsigned long),
+ roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
GFP_KERNEL);
if (!bitmap->filemap_attr)
- goto out;
+ goto err;
oldindex = ~0L;
index = file_page_index(i);
bit = file_page_offset(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 == num_pages-1)
+ count = bytes + sizeof(bitmap_super_t)
+ - index * PAGE_SIZE;
+ else
+ count = PAGE_SIZE;
if (index == 0) {
/*
* if we're here then the superblock page
*/
page = bitmap->sb_page;
offset = sizeof(bitmap_super_t);
+ if (!file)
+ read_sb_page(bitmap->mddev,
+ bitmap->offset,
+ page,
+ index, count);
} else if (file) {
- page = read_page(file, index, &dummy);
+ page = read_page(file, index, bitmap, count);
offset = 0;
} else {
- page = read_sb_page(bitmap->mddev, bitmap->offset, index);
+ page = read_sb_page(bitmap->mddev, bitmap->offset,
+ NULL,
+ index, count);
offset = 0;
}
if (IS_ERR(page)) { /* read error */
ret = PTR_ERR(page);
- goto out;
+ goto err;
}
oldindex = index;
oldpage = page;
+ bitmap->filemap[bitmap->file_pages++] = page;
+ bitmap->last_page_size = count;
+
if (outofdate) {
/*
* if bitmap is out of date, dirty the
memset(paddr + offset, 0xff,
PAGE_SIZE - offset);
kunmap_atomic(paddr, KM_USER0);
- ret = write_page(bitmap, page, 1);
- if (ret) {
- /* release, page not in filemap yet */
- put_page(page);
- goto out;
- }
- }
+ write_page(bitmap, page, 1);
- bitmap->filemap[bitmap->file_pages++] = page;
+ ret = -EIO;
+ if (bitmap->flags & BITMAP_WRITE_ERROR)
+ goto err;
+ }
}
paddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
kunmap_atomic(paddr, KM_USER0);
if (b) {
/* if the disk bit is set, set the memory bit */
- bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
- ((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
- );
+ int needed = ((sector_t)(i+1) << (CHUNK_BLOCK_SHIFT(bitmap))
+ >= start);
+ bitmap_set_memory_bits(bitmap,
+ (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
+ needed);
bit_cnt++;
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
md_wakeup_thread(bitmap->mddev->thread);
}
-out:
printk(KERN_INFO "%s: bitmap initialized from disk: "
- "read %lu/%lu pages, set %lu bits, status: %d\n",
- bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, ret);
+ "read %lu/%lu pages, set %lu bits\n",
+ bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);
+ return 0;
+
+ err:
+ printk(KERN_INFO "%s: bitmap initialisation failed: %d\n",
+ bmname(bitmap), ret);
return ret;
}
* out to disk
*/
-int bitmap_daemon_work(struct bitmap *bitmap)
+void bitmap_daemon_work(struct bitmap *bitmap)
{
unsigned long j;
unsigned long flags;
struct page *page = NULL, *lastpage = NULL;
- int err = 0;
int blocks;
void *paddr;
if (bitmap == NULL)
- return 0;
+ return;
if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
- return 0;
+ goto done;
+
bitmap->daemon_lastrun = jiffies;
+ if (bitmap->allclean) {
+ bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+ return;
+ }
+ bitmap->allclean = 1;
+ spin_lock_irqsave(&bitmap->lock, flags);
for (j = 0; j < bitmap->chunks; j++) {
bitmap_counter_t *bmc;
- spin_lock_irqsave(&bitmap->lock, flags);
- if (!bitmap->filemap) {
+ if (!bitmap->filemap)
/* error or shutdown */
- spin_unlock_irqrestore(&bitmap->lock, flags);
break;
- }
page = filemap_get_page(bitmap, j);
spin_unlock_irqrestore(&bitmap->lock, flags);
if (need_write) {
- switch (write_page(bitmap, page, 0)) {
- case -EAGAIN:
- set_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
- break;
- case 0:
- break;
- default:
- bitmap_file_kick(bitmap);
- }
+ write_page(bitmap, page, 0);
+ bitmap->allclean = 0;
}
+ spin_lock_irqsave(&bitmap->lock, flags);
+ j |= (PAGE_BITS - 1);
continue;
}
if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
- err = write_page(bitmap, lastpage, 0);
- if (err == -EAGAIN) {
- err = 0;
- set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
- }
+ write_page(bitmap, lastpage, 0);
} else {
set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
}
- if (err)
- bitmap_file_kick(bitmap);
} else
spin_unlock_irqrestore(&bitmap->lock, flags);
lastpage = page;
-/*
- printk("bitmap clean at page %lu\n", j);
-*/
+
+ /* We are possibly going to clear some bits, so make
+ * sure that events_cleared is up-to-date.
+ */
+ if (bitmap->need_sync) {
+ bitmap_super_t *sb;
+ bitmap->need_sync = 0;
+ sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+ sb->events_cleared =
+ cpu_to_le64(bitmap->events_cleared);
+ kunmap_atomic(sb, KM_USER0);
+ write_page(bitmap, bitmap->sb_page, 1);
+ }
spin_lock_irqsave(&bitmap->lock, flags);
clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
- bmc = bitmap_get_counter(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap),
- &blocks, 0);
+ bmc = bitmap_get_counter(bitmap,
+ (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
+ &blocks, 0);
if (bmc) {
/*
if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
*/
+ if (*bmc)
+ bitmap->allclean = 0;
+
if (*bmc == 2) {
*bmc=1; /* maybe clear the bit next time */
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
} else if (*bmc == 1) {
/* we can clear the bit */
*bmc = 0;
- bitmap_count_page(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap),
+ bitmap_count_page(bitmap,
+ (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
-1);
/* clear the bit */
ext2_clear_bit(file_page_offset(j), paddr);
kunmap_atomic(paddr, KM_USER0);
}
- }
- spin_unlock_irqrestore(&bitmap->lock, flags);
+ } else
+ j |= PAGE_COUNTER_MASK;
}
+ spin_unlock_irqrestore(&bitmap->lock, flags);
/* now sync the final page */
if (lastpage != NULL) {
if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
- err = write_page(bitmap, lastpage, 0);
- if (err == -EAGAIN) {
- set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
- err = 0;
- }
+ write_page(bitmap, lastpage, 0);
} else {
set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
}
}
- return err;
-}
-
-static void bitmap_writeback(struct bitmap *bitmap)
-{
- struct page *page;
- struct page_list *item;
- int err = 0;
-
- PRINTK("%s: bitmap writeback daemon woke up...\n", bmname(bitmap));
- /* wait on bitmap page writebacks */
- while ((item = dequeue_page(bitmap))) {
- page = item->page;
- mempool_free(item, bitmap->write_pool);
- PRINTK("wait on page writeback: %p\n", page);
- wait_on_page_writeback(page);
- PRINTK("finished page writeback: %p\n", page);
-
- err = PageError(page);
- if (err) {
- printk(KERN_WARNING "%s: bitmap file writeback "
- "failed (page %lu): %d\n",
- bmname(bitmap), page->index, err);
- bitmap_file_kick(bitmap);
- break;
- }
- }
+ done:
+ if (bitmap->allclean == 0)
+ bitmap->mddev->thread->timeout = bitmap->daemon_sleep * HZ;
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
sector_t offset, int *blocks,
int create)
+__releases(bitmap->lock)
+__acquires(bitmap->lock)
{
/* If 'create', we might release the lock and reclaim it.
* The lock must have been taken with interrupts enabled.
return 0;
}
+ if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) {
+ DEFINE_WAIT(__wait);
+ /* note that it is safe to do the prepare_to_wait
+ * after the test as long as we do it before dropping
+ * the spinlock.
+ */
+ prepare_to_wait(&bitmap->overflow_wait, &__wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock_irq(&bitmap->lock);
+ blk_unplug(bitmap->mddev->queue);
+ schedule();
+ finish_wait(&bitmap->overflow_wait, &__wait);
+ continue;
+ }
+
switch(*bmc) {
case 0:
bitmap_file_set_bit(bitmap, offset);
bitmap_count_page(bitmap,offset, 1);
- blk_plug_device(bitmap->mddev->queue);
+ blk_plug_device_unlocked(bitmap->mddev->queue);
/* fall through */
case 1:
*bmc = 2;
}
- BUG_ON((*bmc & COUNTER_MAX) == COUNTER_MAX);
+
(*bmc)++;
spin_unlock_irq(&bitmap->lock);
sectors -= blocks;
else sectors = 0;
}
+ bitmap->allclean = 0;
return 0;
}
PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
}
+ if (bitmap->mddev->degraded)
+ /* Never clear bits or update events_cleared when degraded */
+ success = 0;
while (sectors) {
int blocks;
return;
}
+ if (success &&
+ bitmap->events_cleared < bitmap->mddev->events) {
+ bitmap->events_cleared = bitmap->mddev->events;
+ bitmap->need_sync = 1;
+ }
+
if (!success && ! (*bmc & NEEDED_MASK))
*bmc |= NEEDED_MASK;
+ if ((*bmc & COUNTER_MAX) == COUNTER_MAX)
+ wake_up(&bitmap->overflow_wait);
+
(*bmc)--;
if (*bmc <= 2) {
set_page_attr(bitmap,
}
}
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
- int degraded)
+static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+ int degraded)
{
bitmap_counter_t *bmc;
int rv;
}
}
spin_unlock_irq(&bitmap->lock);
+ bitmap->allclean = 0;
+ return rv;
+}
+
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+ int degraded)
+{
+ /* bitmap_start_sync must always report on multiples of whole
+ * pages, otherwise resync (which is very PAGE_SIZE based) will
+ * get confused.
+ * So call __bitmap_start_sync repeatedly (if needed) until
+ * At least PAGE_SIZE>>9 blocks are covered.
+ * Return the 'or' of the result.
+ */
+ int rv = 0;
+ int blocks1;
+
+ *blocks = 0;
+ while (*blocks < (PAGE_SIZE>>9)) {
+ rv |= __bitmap_start_sync(bitmap, offset,
+ &blocks1, degraded);
+ offset += blocks1;
+ *blocks += blocks1;
+ }
return rv;
}
}
unlock:
spin_unlock_irqrestore(&bitmap->lock, flags);
+ bitmap->allclean = 0;
}
void bitmap_close_sync(struct bitmap *bitmap)
*/
sector_t sector = 0;
int blocks;
- if (!bitmap) return;
+ if (!bitmap)
+ return;
while (sector < bitmap->mddev->resync_max_sectors) {
bitmap_end_sync(bitmap, sector, &blocks, 0);
-/*
- if (sector < 500) printk("bitmap_close_sync: sec %llu blks %d\n",
- (unsigned long long)sector, blocks);
-*/ sector += blocks;
+ sector += blocks;
}
}
+void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
+{
+ sector_t s = 0;
+ int blocks;
+
+ if (!bitmap)
+ return;
+ if (sector == 0) {
+ bitmap->last_end_sync = jiffies;
+ return;
+ }
+ if (time_before(jiffies, (bitmap->last_end_sync
+ + bitmap->daemon_sleep * HZ)))
+ return;
+ wait_event(bitmap->mddev->recovery_wait,
+ atomic_read(&bitmap->mddev->recovery_active) == 0);
+
+ bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
+ set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
+ sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
+ s = 0;
+ while (s < sector && s < bitmap->mddev->resync_max_sectors) {
+ bitmap_end_sync(bitmap, s, &blocks, 0);
+ s += blocks;
+ }
+ bitmap->last_end_sync = jiffies;
+ sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
+}
+
static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
{
/* For each chunk covered by any of these sectors, set the
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
spin_unlock_irq(&bitmap->lock);
+ bitmap->allclean = 0;
+}
+/* dirty the memory and file bits for bitmap chunks "s" to "e" */
+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
+{
+ unsigned long chunk;
+
+ for (chunk = s; chunk <= e; chunk++) {
+ sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
+ bitmap_set_memory_bits(bitmap, sec, 1);
+ bitmap_file_set_bit(bitmap, sec);
+ }
}
/*
/* free all allocated memory */
- mempool_destroy(bitmap->write_pool);
-
if (bp) /* deallocate the page memory */
for (k = 0; k < pages; k++)
if (bp[k].map && !bp[k].hijacked)
int bitmap_create(mddev_t *mddev)
{
struct bitmap *bitmap;
- unsigned long blocks = mddev->resync_max_sectors;
+ sector_t blocks = mddev->resync_max_sectors;
unsigned long chunks;
unsigned long pages;
struct file *file = mddev->bitmap_file;
int err;
sector_t start;
- BUG_ON(sizeof(bitmap_super_t) != 256);
+ BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */
return 0;
return -ENOMEM;
spin_lock_init(&bitmap->lock);
- bitmap->mddev = mddev;
+ atomic_set(&bitmap->pending_writes, 0);
+ init_waitqueue_head(&bitmap->write_wait);
+ init_waitqueue_head(&bitmap->overflow_wait);
- spin_lock_init(&bitmap->write_lock);
- INIT_LIST_HEAD(&bitmap->complete_pages);
- bitmap->write_pool = mempool_create_kmalloc_pool(WRITE_POOL_SIZE,
- sizeof(struct page_list));
- err = -ENOMEM;
- if (!bitmap->write_pool)
- goto error;
+ bitmap->mddev = mddev;
bitmap->file = file;
bitmap->offset = mddev->bitmap_offset;
- if (file) get_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, file->f_dentry, 1);
+ }
/* read superblock from bitmap file (this sets bitmap->chunksize) */
err = bitmap_read_sb(bitmap);
if (err)
goto error;
- bitmap->chunkshift = find_first_bit(&bitmap->chunksize,
- sizeof(bitmap->chunksize));
+ bitmap->chunkshift = ffz(~bitmap->chunksize);
/* now that chunksize and chunkshift are set, we can use these macros */
- chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) /
- CHUNK_BLOCK_RATIO(bitmap);
+ chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
+ CHUNK_BLOCK_SHIFT(bitmap);
pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
BUG_ON(!pages);
mddev->thread->timeout = bitmap->daemon_sleep * HZ;
- return bitmap_update_sb(bitmap);
+ bitmap_update_sb(bitmap);
+
+ return (bitmap->flags & BITMAP_WRITE_ERROR) ? -EIO : 0;
error:
bitmap_free(bitmap);
EXPORT_SYMBOL(bitmap_end_sync);
EXPORT_SYMBOL(bitmap_unplug);
EXPORT_SYMBOL(bitmap_close_sync);
-EXPORT_SYMBOL(bitmap_daemon_work);
+EXPORT_SYMBOL(bitmap_cond_end_sync);