* 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/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 */
* 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_path.dentry;
- v = file->f_path.mnt;
-
- 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 */
}
+static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *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_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;
+}
+
static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
{
- mdk_rdev_t *rdev;
- struct list_head *tmp;
+ mdk_rdev_t *rdev = NULL;
mddev_t *mddev = bitmap->mddev;
- ITERATE_RDEV(mddev, rdev, tmp)
- if (test_bit(In_sync, &rdev->flags)
- && !test_bit(Faulty, &rdev->flags)) {
+ 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_hardsect_size(rdev->bdev));
+ bdev_logical_block_size(rdev->bdev));
/* Just make sure we aren't corrupting data or
* metadata
*/
+ (long)(page->index * (PAGE_SIZE/512))
+ size/512 > 0)
/* bitmap runs in to metadata */
- return -EINVAL;
- if (rdev->data_offset + mddev->size*2
- > rdev->sb_offset*2 + bitmap->offset)
+ goto bad_alignment;
+ if (rdev->data_offset + mddev->dev_sectors
+ > rdev->sb_start + bitmap->offset)
/* data runs in to bitmap */
- return -EINVAL;
- } else if (rdev->sb_offset*2 < rdev->data_offset) {
+ goto bad_alignment;
+ } else if (rdev->sb_start < rdev->data_offset) {
/* METADATA BITMAP DATA */
- if (rdev->sb_offset*2
+ if (rdev->sb_start
+ bitmap->offset
+ page->index*(PAGE_SIZE/512) + size/512
> rdev->data_offset)
/* bitmap runs in to data */
- return -EINVAL;
+ goto bad_alignment;
} else {
/* DATA METADATA BITMAP - no problems */
}
md_super_write(mddev, rdev,
- (rdev->sb_offset<<1) + bitmap->offset
+ rdev->sb_start + bitmap->offset
+ page->index * (PAGE_SIZE/512),
size,
page);
- }
+ }
if (wait)
md_super_wait(mddev);
return 0;
+
+ bad_alignment:
+ return -EINVAL;
}
static void bitmap_file_kick(struct bitmap *bitmap);
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);
write_page(bitmap, bitmap->sb_page, 1);
}
bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
} else {
- bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0);
+ 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);
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";
if (bitmap->file) {
path = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (path)
- ptr = file_path(bitmap->file, path, PAGE_SIZE);
+ ptr = d_path(&bitmap->file->f_path, path,
+ PAGE_SIZE);
+
printk(KERN_ALERT
"%s: kicking failed bitmap file %s from array!\n",
- bmname(bitmap), ptr ? ptr : "");
+ bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
kfree(path);
} else
*/
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, 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 */
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
write_page(bitmap, page, 1);
ret = -EIO;
- if (bitmap->flags & BITMAP_WRITE_ERROR) {
- /* release, page not in filemap yet */
- put_page(page);
+ if (bitmap->flags & BITMAP_WRITE_ERROR)
goto err;
- }
}
-
- bitmap->filemap[bitmap->file_pages++] = page;
- bitmap->last_page_size = count;
}
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);
}
if (bitmap == NULL)
return;
if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
- return;
+ 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);
clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
- if (need_write)
+ if (need_write) {
write_page(bitmap, page, 0);
+ bitmap->allclean = 0;
+ }
+ spin_lock_irqsave(&bitmap->lock, flags);
+ j |= (PAGE_BITS - 1);
continue;
}
} 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) {
}
}
+ 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.
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;
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;
}
}
-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" */
unsigned long chunk;
for (chunk = s; chunk <= e; chunk++) {
- sector_t sec = chunk << CHUNK_BLOCK_SHIFT(bitmap);
+ sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
bitmap_set_memory_bits(bitmap, sec, 1);
bitmap_file_set_bit(bitmap, sec);
}
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;
bitmap->offset = mddev->bitmap_offset;
if (file) {
get_file(file);
- do_sync_mapping_range(file->f_mapping, 0, LLONG_MAX,
- SYNC_FILE_RANGE_WAIT_BEFORE |
- SYNC_FILE_RANGE_WRITE |
- SYNC_FILE_RANGE_WAIT_AFTER);
+ /* 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);
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);
EXPORT_SYMBOL(bitmap_end_sync);
EXPORT_SYMBOL(bitmap_unplug);
EXPORT_SYMBOL(bitmap_close_sync);
+EXPORT_SYMBOL(bitmap_cond_end_sync);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff