*/
#include <linux/module.h>
-#include <linux/version.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
}
#define WRITE_POOL_SIZE 256
-/* mempool for queueing pending writes on the bitmap file */
-static void *write_pool_alloc(unsigned int gfp_flags, void *data)
-{
- return kmalloc(sizeof(struct page_list), gfp_flags);
-}
-
-static void write_pool_free(void *ptr, void *data)
-{
- kfree(ptr);
-}
/*
* just a placeholder - calls kmalloc for bitmap pages
{
unsigned char *page;
-#if INJECT_FAULTS_1
+#ifdef INJECT_FAULTS_1
page = NULL;
#else
page = kmalloc(PAGE_SIZE, GFP_NOIO);
if (!page)
printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));
else
- printk("%s: bitmap_alloc_page: allocated page at %p\n",
+ PRINTK("%s: bitmap_alloc_page: allocated page at %p\n",
bmname(bitmap), page);
return page;
}
/* if page is completely empty, put it back on the free list, or dealloc it */
/* if page was hijacked, unmark the flag so it might get alloced next time */
/* Note: lock should be held when calling this */
-static inline void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
+static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
{
char *ptr;
* 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)
+{
+ /* 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)
+ return ERR_PTR(-ENOMEM);
+
+ ITERATE_RDEV(mddev, rdev, tmp) {
+ if (! test_bit(In_sync, &rdev->flags)
+ || test_bit(Faulty, &rdev->flags))
+ continue;
+
+ target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);
+
+ if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
+ page->index = index;
+ return page;
+ }
+ }
+ return ERR_PTR(-EIO);
+
+}
+
+static int write_sb_page(mddev_t *mddev, long offset, struct page *page, int wait)
+{
+ mdk_rdev_t *rdev;
+ struct list_head *tmp;
+
+ ITERATE_RDEV(mddev, rdev, tmp)
+ if (test_bit(In_sync, &rdev->flags)
+ && !test_bit(Faulty, &rdev->flags))
+ md_super_write(mddev, rdev,
+ (rdev->sb_offset<<1) + offset
+ + page->index * (PAGE_SIZE/512),
+ PAGE_SIZE,
+ page);
+
+ if (wait)
+ md_super_wait(mddev);
+ return 0;
+}
+
/*
- * write out a page
+ * write out a page to a file
*/
-static int write_page(struct page *page, int wait)
+static int write_page(struct bitmap *bitmap, struct page *page, int wait)
{
int ret = -ENOMEM;
- lock_page(page);
+ if (bitmap->file == NULL)
+ return write_sb_page(bitmap->mddev, bitmap->offset, page, wait);
- if (page->mapping == NULL)
- goto unlock_out;
- else if (i_size_read(page->mapping->host) < page->index << PAGE_SHIFT) {
- ret = -ENOENT;
- goto unlock_out;
+ flush_dcache_page(page); /* make sure visible to anyone reading the file */
+
+ if (wait)
+ lock_page(page);
+ else {
+ if (TestSetPageLocked(page))
+ return -EAGAIN; /* already locked */
+ if (PageWriteback(page)) {
+ unlock_page(page);
+ return -EAGAIN;
+ }
}
- ret = page->mapping->a_ops->prepare_write(NULL, page, 0, PAGE_SIZE);
+ ret = page->mapping->a_ops->prepare_write(bitmap->file, page, 0, PAGE_SIZE);
if (!ret)
- ret = page->mapping->a_ops->commit_write(NULL, page, 0,
+ ret = page->mapping->a_ops->commit_write(bitmap->file, page, 0,
PAGE_SIZE);
if (ret) {
-unlock_out:
unlock_page(page);
return ret;
}
set_page_dirty(page); /* force it to be written out */
+
+ if (!wait) {
+ /* add to list to be waited for by daemon */
+ struct page_list *item = mempool_alloc(bitmap->write_pool, GFP_NOIO);
+ item->page = page;
+ get_page(page);
+ spin_lock(&bitmap->write_lock);
+ list_add(&item->list, &bitmap->complete_pages);
+ spin_unlock(&bitmap->write_lock);
+ md_wakeup_thread(bitmap->writeback_daemon);
+ }
return write_one_page(page, wait);
}
struct inode *inode = file->f_mapping->host;
struct page *page = NULL;
loff_t isize = i_size_read(inode);
- unsigned long end_index = isize >> PAGE_CACHE_SHIFT;
+ unsigned long end_index = isize >> PAGE_SHIFT;
- PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_CACHE_SIZE,
- (unsigned long long)index << PAGE_CACHE_SHIFT);
+ 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);
goto out;
wait_on_page_locked(page);
if (!PageUptodate(page) || PageError(page)) {
- page_cache_release(page);
+ put_page(page);
page = ERR_PTR(-EIO);
goto out;
}
if (index > end_index) /* we have read beyond EOF */
*bytes_read = 0;
else if (index == end_index) /* possible short read */
- *bytes_read = isize & ~PAGE_CACHE_MASK;
+ *bytes_read = isize & ~PAGE_MASK;
else
- *bytes_read = PAGE_CACHE_SIZE; /* got a full page */
+ *bytes_read = PAGE_SIZE; /* got a full page */
out:
if (IS_ERR(page))
printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
- (int)PAGE_CACHE_SIZE,
- (unsigned long long)index << PAGE_CACHE_SHIFT,
+ (int)PAGE_SIZE,
+ (unsigned long long)index << PAGE_SHIFT,
PTR_ERR(page));
return page;
}
spin_unlock_irqrestore(&bitmap->lock, flags);
return 0;
}
- page_cache_get(bitmap->sb_page);
spin_unlock_irqrestore(&bitmap->lock, flags);
- sb = (bitmap_super_t *)kmap(bitmap->sb_page);
+ 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);
- kunmap(bitmap->sb_page);
- write_page(bitmap->sb_page, 0);
- return 0;
+ kunmap_atomic(sb, KM_USER0);
+ return write_page(bitmap, bitmap->sb_page, 1);
}
/* print out the bitmap file superblock */
if (!bitmap || !bitmap->sb_page)
return;
- sb = (bitmap_super_t *)kmap(bitmap->sb_page);
+ sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
- printk(KERN_DEBUG " magic: %08x\n", le32_to_cpu(sb->magic));
- printk(KERN_DEBUG " version: %d\n", le32_to_cpu(sb->version));
- printk(KERN_DEBUG " uuid: %08x.%08x.%08x.%08x\n",
+ printk(KERN_DEBUG " magic: %08x\n", le32_to_cpu(sb->magic));
+ printk(KERN_DEBUG " version: %d\n", le32_to_cpu(sb->version));
+ printk(KERN_DEBUG " uuid: %08x.%08x.%08x.%08x\n",
*(__u32 *)(sb->uuid+0),
*(__u32 *)(sb->uuid+4),
*(__u32 *)(sb->uuid+8),
*(__u32 *)(sb->uuid+12));
- printk(KERN_DEBUG " events: %llu\n",
+ printk(KERN_DEBUG " events: %llu\n",
(unsigned long long) le64_to_cpu(sb->events));
- printk(KERN_DEBUG "events_clred: %llu\n",
+ printk(KERN_DEBUG "events cleared: %llu\n",
(unsigned long long) le64_to_cpu(sb->events_cleared));
- printk(KERN_DEBUG " state: %08x\n", le32_to_cpu(sb->state));
- printk(KERN_DEBUG " chunksize: %d B\n", le32_to_cpu(sb->chunksize));
- printk(KERN_DEBUG "daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
- printk(KERN_DEBUG " sync size: %llu KB\n", le64_to_cpu(sb->sync_size));
- kunmap(bitmap->sb_page);
+ printk(KERN_DEBUG " state: %08x\n", le32_to_cpu(sb->state));
+ printk(KERN_DEBUG " chunksize: %d B\n", le32_to_cpu(sb->chunksize));
+ printk(KERN_DEBUG " daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
+ printk(KERN_DEBUG " sync size: %llu KB\n",
+ (unsigned long long)le64_to_cpu(sb->sync_size)/2);
+ printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind));
+ kunmap_atomic(sb, KM_USER0);
}
/* read the superblock from the bitmap file and initialize some bitmap fields */
{
char *reason = NULL;
bitmap_super_t *sb;
- unsigned long chunksize, daemon_sleep;
+ 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... */
- bitmap->sb_page = read_page(bitmap->file, 0, &bytes_read);
+ 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 (IS_ERR(bitmap->sb_page)) {
err = PTR_ERR(bitmap->sb_page);
bitmap->sb_page = NULL;
return err;
}
- sb = (bitmap_super_t *)kmap(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",
chunksize = le32_to_cpu(sb->chunksize);
daemon_sleep = le32_to_cpu(sb->daemon_sleep);
+ write_behind = le32_to_cpu(sb->write_behind);
/* verify that the bitmap-specific fields are valid */
if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
reason = "bad magic";
- else if (sb->version != cpu_to_le32(BITMAP_MAJOR))
+ else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
+ le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
reason = "unrecognized superblock version";
- else if (chunksize < 512 || chunksize > (1024 * 1024 * 4))
- reason = "bitmap chunksize out of range (512B - 4MB)";
+ else if (chunksize < PAGE_SIZE)
+ reason = "bitmap chunksize too small";
else if ((1 << ffz(~chunksize)) != chunksize)
reason = "bitmap chunksize not a power of 2";
- else if (daemon_sleep < 1 || daemon_sleep > 15)
+ else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT / HZ)
reason = "daemon sleep period out of range";
+ else if (write_behind > COUNTER_MAX)
+ reason = "write-behind limit out of range (0 - 16383)";
if (reason) {
printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",
bmname(bitmap), reason);
/* assign fields using values from superblock */
bitmap->chunksize = chunksize;
bitmap->daemon_sleep = daemon_sleep;
+ bitmap->daemon_lastrun = jiffies;
+ bitmap->max_write_behind = write_behind;
bitmap->flags |= sb->state;
+ 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)
+ bitmap->events_cleared = bitmap->mddev->events;
err = 0;
out:
- kunmap(bitmap->sb_page);
+ kunmap_atomic(sb, KM_USER0);
if (err)
bitmap_print_sb(bitmap);
return err;
unsigned long flags;
spin_lock_irqsave(&bitmap->lock, flags);
- if (!bitmap || !bitmap->sb_page) { /* can't set the state */
+ if (!bitmap->sb_page) { /* can't set the state */
spin_unlock_irqrestore(&bitmap->lock, flags);
return;
}
- page_cache_get(bitmap->sb_page);
+ get_page(bitmap->sb_page);
spin_unlock_irqrestore(&bitmap->lock, flags);
- sb = (bitmap_super_t *)kmap(bitmap->sb_page);
+ sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
switch (op) {
case MASK_SET: sb->state |= bits;
break;
break;
default: BUG();
}
- kunmap(bitmap->sb_page);
- page_cache_release(bitmap->sb_page);
+ kunmap_atomic(sb, KM_USER0);
+ put_page(bitmap->sb_page);
}
/*
while (pages--)
if (map[pages]->index != 0) /* 0 is sb_page, release it below */
- page_cache_release(map[pages]);
+ put_page(map[pages]);
kfree(map);
kfree(attr);
- if (sb_page)
- page_cache_release(sb_page);
+ safe_put_page(sb_page);
}
-static void bitmap_stop_daemons(struct bitmap *bitmap);
+static void bitmap_stop_daemon(struct bitmap *bitmap);
/* dequeue the next item in a page list -- don't call from irq context */
-static struct page_list *dequeue_page(struct bitmap *bitmap,
- struct list_head *head)
+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))
static void drain_write_queues(struct bitmap *bitmap)
{
- struct list_head *queues[] = { &bitmap->complete_pages, NULL };
- struct list_head *head;
struct page_list *item;
- int i;
- for (i = 0; queues[i]; i++) {
- head = queues[i];
- while ((item = dequeue_page(bitmap, head))) {
- page_cache_release(item->page);
- mempool_free(item, bitmap->write_pool);
- }
+ while ((item = dequeue_page(bitmap))) {
+ /* don't bother to wait */
+ put_page(item->page);
+ mempool_free(item, bitmap->write_pool);
}
- spin_lock(&bitmap->write_lock);
- bitmap->writes_pending = 0; /* make sure waiters continue */
wake_up(&bitmap->write_wait);
- spin_unlock(&bitmap->write_lock);
}
static void bitmap_file_put(struct bitmap *bitmap)
bitmap->file = NULL;
spin_unlock_irqrestore(&bitmap->lock, flags);
- bitmap_stop_daemons(bitmap);
+ bitmap_stop_daemon(bitmap);
drain_write_queues(bitmap);
bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET);
bitmap_update_sb(bitmap);
- path = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (path)
- ptr = file_path(bitmap->file, 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), ptr ? ptr : "");
- kfree(path);
+ kfree(path);
+ }
bitmap_file_put(bitmap);
void *kaddr;
unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
- if (!bitmap->file || !bitmap->filemap) {
+ if (!bitmap->filemap) {
return;
}
/* make sure the page stays cached until it gets written out */
if (! (get_page_attr(bitmap, page) & BITMAP_PAGE_DIRTY))
- page_cache_get(page);
+ get_page(page);
/* set the bit */
kaddr = kmap_atomic(page, KM_USER0);
- set_bit(bit, kaddr);
+ if (bitmap->flags & BITMAP_HOSTENDIAN)
+ set_bit(bit, kaddr);
+ else
+ ext2_set_bit(bit, kaddr);
kunmap_atomic(kaddr, KM_USER0);
PRINTK("set file bit %lu page %lu\n", bit, page->index);
unsigned long i, attr, flags;
struct page *page;
int wait = 0;
+ int err;
if (!bitmap)
return 0;
* flushed out to disk */
for (i = 0; i < bitmap->file_pages; i++) {
spin_lock_irqsave(&bitmap->lock, flags);
- if (!bitmap->file || !bitmap->filemap) {
+ if (!bitmap->filemap) {
spin_unlock_irqrestore(&bitmap->lock, flags);
return 0;
}
wait = 1;
spin_unlock_irqrestore(&bitmap->lock, flags);
- if (attr & (BITMAP_PAGE_DIRTY | BITMAP_PAGE_NEEDWRITE))
- write_page(page, 0);
+ if (attr & (BITMAP_PAGE_DIRTY | BITMAP_PAGE_NEEDWRITE)) {
+ err = write_page(bitmap, page, 0);
+ if (err == -EAGAIN) {
+ if (attr & BITMAP_PAGE_DIRTY)
+ err = write_page(bitmap, page, 1);
+ else
+ err = 0;
+ }
+ if (err)
+ return 1;
+ }
}
if (wait) { /* if any writes were performed, we need to wait on them */
- spin_lock_irq(&bitmap->write_lock);
- wait_event_lock_irq(bitmap->write_wait,
- bitmap->writes_pending == 0, bitmap->write_lock,
- wake_up_process(bitmap->writeback_daemon->tsk));
- spin_unlock_irq(&bitmap->write_lock);
+ if (bitmap->file) {
+ spin_lock_irq(&bitmap->write_lock);
+ wait_event_lock_irq(bitmap->write_wait,
+ list_empty(&bitmap->complete_pages), bitmap->write_lock,
+ wake_up_process(bitmap->writeback_daemon->tsk));
+ spin_unlock_irq(&bitmap->write_lock);
+ } else
+ md_super_wait(bitmap->mddev);
}
return 0;
}
-static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset,
- unsigned long sectors, int in_sync);
+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
* 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, int in_sync)
+static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
unsigned long i, chunks, index, oldindex, bit;
struct page *page = NULL, *oldpage = NULL;
unsigned long bytes, offset, dummy;
int outofdate;
int ret = -ENOSPC;
+ void *paddr;
chunks = bitmap->chunks;
file = bitmap->file;
- BUG_ON(!file);
+ BUG_ON(!file && !bitmap->offset);
-#if INJECT_FAULTS_3
+#ifdef INJECT_FAULTS_3
outofdate = 1;
#else
outofdate = bitmap->flags & BITMAP_STALE;
num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE;
- if (i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
+ if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
bmname(bitmap),
(unsigned long) i_size_read(file->f_mapping->host),
if (!bitmap->filemap)
goto out;
- bitmap->filemap_attr = kmalloc(sizeof(long) * num_pages, GFP_KERNEL);
+ bitmap->filemap_attr = kzalloc(sizeof(long) * num_pages, GFP_KERNEL);
if (!bitmap->filemap_attr)
goto out;
- memset(bitmap->filemap_attr, 0, sizeof(long) * num_pages);
-
oldindex = ~0L;
for (i = 0; i < chunks; i++) {
+ int b;
index = file_page_index(i);
bit = file_page_offset(i);
if (index != oldindex) { /* this is a new page, read it in */
/* unmap the old page, we're done with it */
- if (oldpage != NULL)
- kunmap(oldpage);
if (index == 0) {
/*
* if we're here then the superblock page
*/
page = bitmap->sb_page;
offset = sizeof(bitmap_super_t);
- } else {
+ } else if (file) {
page = read_page(file, index, &dummy);
- if (IS_ERR(page)) { /* read error */
- ret = PTR_ERR(page);
- goto out;
- }
offset = 0;
+ } else {
+ page = read_sb_page(bitmap->mddev, bitmap->offset, index);
+ offset = 0;
+ }
+ if (IS_ERR(page)) { /* read error */
+ ret = PTR_ERR(page);
+ goto out;
}
+
oldindex = index;
oldpage = page;
- kmap(page);
if (outofdate) {
/*
* if bitmap is out of date, dirty the
* whole page and write it out
*/
- memset(page_address(page) + offset, 0xff,
- PAGE_SIZE - offset);
- ret = write_page(page, 1);
+ paddr = kmap_atomic(page, KM_USER0);
+ memset(paddr + offset, 0xff,
+ PAGE_SIZE - offset);
+ kunmap_atomic(paddr, KM_USER0);
+ ret = write_page(bitmap, page, 1);
if (ret) {
- kunmap(page);
/* release, page not in filemap yet */
- page_cache_release(page);
+ put_page(page);
goto out;
}
}
bitmap->filemap[bitmap->file_pages++] = page;
}
- if (test_bit(bit, page_address(page))) {
+ paddr = kmap_atomic(page, KM_USER0);
+ if (bitmap->flags & BITMAP_HOSTENDIAN)
+ b = test_bit(bit, paddr);
+ else
+ b = ext2_test_bit(bit, paddr);
+ 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), 1, in_sync);
+ bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
+ ((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
+ );
bit_cnt++;
+ set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
}
ret = 0;
bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
- if (page) /* unmap the last page */
- kunmap(page);
-
if (bit_cnt) { /* Kick recovery if any bits were set */
set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
md_wakeup_thread(bitmap->mddev->thread);
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
+ */
+
+ unsigned long chunks = bitmap->chunks;
+ unsigned long bytes = (chunks+7)/8 + sizeof(bitmap_super_t);
+ unsigned long num_pages = (bytes + PAGE_SIZE-1) / PAGE_SIZE;
+ while (num_pages--)
+ bitmap->filemap_attr[num_pages] |= BITMAP_PAGE_NEEDWRITE;
+}
+
static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
{
int bitmap_daemon_work(struct bitmap *bitmap)
{
- unsigned long bit, j;
+ unsigned long j;
unsigned long flags;
struct page *page = NULL, *lastpage = NULL;
int err = 0;
int blocks;
int attr;
+ void *paddr;
if (bitmap == NULL)
return 0;
for (j = 0; j < bitmap->chunks; j++) {
bitmap_counter_t *bmc;
spin_lock_irqsave(&bitmap->lock, flags);
- if (!bitmap->file || !bitmap->filemap) {
+ if (!bitmap->filemap) {
/* error or shutdown */
spin_unlock_irqrestore(&bitmap->lock, flags);
break;
}
page = filemap_get_page(bitmap, j);
- /* skip this page unless it's marked as needing cleaning */
- if (!((attr=get_page_attr(bitmap, page)) & BITMAP_PAGE_CLEAN)) {
- if (attr & BITMAP_PAGE_NEEDWRITE) {
- page_cache_get(page);
- clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
- }
- spin_unlock_irqrestore(&bitmap->lock, flags);
- if (attr & BITMAP_PAGE_NEEDWRITE) {
- if (write_page(page, 0))
- bitmap_file_kick(bitmap);
- page_cache_release(page);
- }
- continue;
- }
-
- bit = file_page_offset(j);
if (page != lastpage) {
+ /* skip this page unless it's marked as needing cleaning */
+ if (!((attr=get_page_attr(bitmap, page)) & BITMAP_PAGE_CLEAN)) {
+ if (attr & BITMAP_PAGE_NEEDWRITE) {
+ get_page(page);
+ clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
+ }
+ spin_unlock_irqrestore(&bitmap->lock, flags);
+ if (attr & BITMAP_PAGE_NEEDWRITE) {
+ switch (write_page(bitmap, page, 0)) {
+ case -EAGAIN:
+ set_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
+ break;
+ case 0:
+ break;
+ default:
+ bitmap_file_kick(bitmap);
+ }
+ put_page(page);
+ }
+ continue;
+ }
+
/* grab the new page, sync and release the old */
- page_cache_get(page);
+ get_page(page);
if (lastpage != NULL) {
if (get_page_attr(bitmap, lastpage) & BITMAP_PAGE_NEEDWRITE) {
clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
- write_page(lastpage, 0);
+ err = write_page(bitmap, lastpage, 0);
+ if (err == -EAGAIN) {
+ err = 0;
+ set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
+ }
} else {
set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
}
- kunmap(lastpage);
- page_cache_release(lastpage);
+ put_page(lastpage);
if (err)
bitmap_file_kick(bitmap);
} else
spin_unlock_irqrestore(&bitmap->lock, flags);
lastpage = page;
- kmap(page);
/*
printk("bitmap clean at page %lu\n", j);
*/
-1);
/* clear the bit */
- clear_bit(bit, page_address(page));
+ paddr = kmap_atomic(page, KM_USER0);
+ if (bitmap->flags & BITMAP_HOSTENDIAN)
+ clear_bit(file_page_offset(j), paddr);
+ else
+ ext2_clear_bit(file_page_offset(j), paddr);
+ kunmap_atomic(paddr, KM_USER0);
}
}
spin_unlock_irqrestore(&bitmap->lock, flags);
/* now sync the final page */
if (lastpage != NULL) {
- kunmap(lastpage);
spin_lock_irqsave(&bitmap->lock, flags);
if (get_page_attr(bitmap, lastpage) &BITMAP_PAGE_NEEDWRITE) {
clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
- write_page(lastpage, 0);
+ err = write_page(bitmap, lastpage, 0);
+ if (err == -EAGAIN) {
+ set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
+ err = 0;
+ }
} else {
set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
}
- page_cache_release(lastpage);
+ put_page(lastpage);
}
return err;
struct page_list *item;
int err = 0;
- while (1) {
- PRINTK("%s: bitmap writeback daemon waiting...\n", bmname(bitmap));
- down_interruptible(&bitmap->write_done);
- if (signal_pending(current)) {
- printk(KERN_INFO
- "%s: bitmap writeback daemon got signal, exiting...\n",
- bmname(bitmap));
- break;
- }
+ if (signal_pending(current)) {
+ printk(KERN_INFO
+ "%s: bitmap writeback daemon got signal, exiting...\n",
+ bmname(bitmap));
+ err = -EINTR;
+ goto out;
+ }
+ if (bitmap == NULL)
+ /* about to be stopped. */
+ return;
- PRINTK("%s: bitmap writeback daemon woke up...\n", bmname(bitmap));
- /* wait on bitmap page writebacks */
- while ((item = dequeue_page(bitmap, &bitmap->complete_pages))) {
- page = item->page;
- mempool_free(item, bitmap->write_pool);
- PRINTK("wait on page writeback: %p %lu\n", page, bitmap->writes_pending);
- wait_on_page_writeback(page);
- PRINTK("finished page writeback: %p %lu\n", page, bitmap->writes_pending);
- spin_lock(&bitmap->write_lock);
- if (!--bitmap->writes_pending)
- wake_up(&bitmap->write_wait);
- spin_unlock(&bitmap->write_lock);
- err = PageError(page);
- page_cache_release(page);
- if (err) {
- printk(KERN_WARNING "%s: bitmap file writeback "
- "failed (page %lu): %d\n",
- bmname(bitmap), page->index, err);
- bitmap_file_kick(bitmap);
- goto out;
- }
+ 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);
+ put_page(page);
+ if (err) {
+ printk(KERN_WARNING "%s: bitmap file writeback "
+ "failed (page %lu): %d\n",
+ bmname(bitmap), page->index, err);
+ bitmap_file_kick(bitmap);
+ goto out;
}
}
-out:
+ out:
+ wake_up(&bitmap->write_wait);
if (err) {
printk(KERN_INFO "%s: bitmap writeback daemon exiting (%d)\n",
- bmname(bitmap), err);
+ bmname(bitmap), err);
daemon_exit(bitmap, &bitmap->writeback_daemon);
}
- return;
}
-static int bitmap_start_daemon(struct bitmap *bitmap, mdk_thread_t **ptr,
+static mdk_thread_t *bitmap_start_daemon(struct bitmap *bitmap,
void (*func)(mddev_t *), char *name)
{
mdk_thread_t *daemon;
- unsigned long flags;
char namebuf[32];
- spin_lock_irqsave(&bitmap->lock, flags);
- *ptr = NULL;
- if (!bitmap->file) /* no need for daemon if there's no backing file */
- goto out_unlock;
-
- spin_unlock_irqrestore(&bitmap->lock, flags);
-
-#if INJECT_FATAL_FAULT_2
+#ifdef INJECT_FATAL_FAULT_2
daemon = NULL;
#else
sprintf(namebuf, "%%s_%s", name);
if (!daemon) {
printk(KERN_ERR "%s: failed to start bitmap daemon\n",
bmname(bitmap));
- return -ECHILD;
+ return ERR_PTR(-ECHILD);
}
- spin_lock_irqsave(&bitmap->lock, flags);
- *ptr = daemon;
-
md_wakeup_thread(daemon); /* start it running */
PRINTK("%s: %s daemon (pid %d) started...\n",
bmname(bitmap), name, daemon->tsk->pid);
-out_unlock:
- spin_unlock_irqrestore(&bitmap->lock, flags);
- return 0;
-}
-static int bitmap_start_daemons(struct bitmap *bitmap)
-{
- int err = bitmap_start_daemon(bitmap, &bitmap->writeback_daemon,
- bitmap_writeback_daemon, "bitmap_wb");
- return err;
+ return daemon;
}
-static void bitmap_stop_daemon(struct bitmap *bitmap, mdk_thread_t **ptr)
+static void bitmap_stop_daemon(struct bitmap *bitmap)
{
- mdk_thread_t *daemon;
- unsigned long flags;
-
- spin_lock_irqsave(&bitmap->lock, flags);
- daemon = *ptr;
- *ptr = NULL;
- spin_unlock_irqrestore(&bitmap->lock, flags);
- if (daemon)
- md_unregister_thread(daemon); /* destroy the thread */
-}
+ /* the daemon can't stop itself... it'll just exit instead... */
+ if (bitmap->writeback_daemon && ! IS_ERR(bitmap->writeback_daemon) &&
+ current->pid != bitmap->writeback_daemon->tsk->pid) {
+ mdk_thread_t *daemon;
+ unsigned long flags;
-static void bitmap_stop_daemons(struct bitmap *bitmap)
-{
- /* the daemons can't stop themselves... they'll just exit instead... */
- if (bitmap->writeback_daemon &&
- current->pid != bitmap->writeback_daemon->tsk->pid)
- bitmap_stop_daemon(bitmap, &bitmap->writeback_daemon);
+ spin_lock_irqsave(&bitmap->lock, flags);
+ daemon = bitmap->writeback_daemon;
+ bitmap->writeback_daemon = NULL;
+ spin_unlock_irqrestore(&bitmap->lock, flags);
+ if (daemon && ! IS_ERR(daemon))
+ md_unregister_thread(daemon); /* destroy the thread */
+ }
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
}
}
-int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors)
+int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
{
if (!bitmap) return 0;
+
+ if (behind) {
+ atomic_inc(&bitmap->behind_writes);
+ PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n",
+ atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
+ }
+
while (sectors) {
int blocks;
bitmap_counter_t *bmc;
case 1:
*bmc = 2;
}
- if ((*bmc & COUNTER_MAX) == COUNTER_MAX) BUG();
+ BUG_ON((*bmc & COUNTER_MAX) == COUNTER_MAX);
(*bmc)++;
spin_unlock_irq(&bitmap->lock);
}
void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
- int success)
+ int success, int behind)
{
if (!bitmap) return;
+ if (behind) {
+ atomic_dec(&bitmap->behind_writes);
+ PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
+ atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
+ }
+
while (sectors) {
int blocks;
unsigned long flags;
}
}
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks)
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+ int degraded)
{
bitmap_counter_t *bmc;
int rv;
rv = 1;
else if (NEEDED(*bmc)) {
rv = 1;
- *bmc |= RESYNC_MASK;
- *bmc &= ~NEEDED_MASK;
+ if (!degraded) { /* don't set/clear bits if degraded */
+ *bmc |= RESYNC_MASK;
+ *bmc &= ~NEEDED_MASK;
+ }
}
}
spin_unlock_irq(&bitmap->lock);
}
}
-static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset,
- unsigned long sectors, int in_sync)
+static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
{
/* For each chunk covered by any of these sectors, set the
- * counter to 1 and set resync_needed unless in_sync. They should all
+ * counter to 1 and set resync_needed. They should all
* be 0 at this point
*/
- while (sectors) {
- int secs;
- bitmap_counter_t *bmc;
- spin_lock_irq(&bitmap->lock);
- bmc = bitmap_get_counter(bitmap, offset, &secs, 1);
- if (!bmc) {
- spin_unlock_irq(&bitmap->lock);
- return;
- }
- if (! *bmc) {
- struct page *page;
- *bmc = 1 | (in_sync? 0 : NEEDED_MASK);
- bitmap_count_page(bitmap, offset, 1);
- page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
- set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
- }
+
+ int secs;
+ bitmap_counter_t *bmc;
+ spin_lock_irq(&bitmap->lock);
+ bmc = bitmap_get_counter(bitmap, offset, &secs, 1);
+ if (!bmc) {
spin_unlock_irq(&bitmap->lock);
- if (sectors > secs)
- sectors -= secs;
- else
- sectors = 0;
+ return;
+ }
+ if (! *bmc) {
+ struct page *page;
+ *bmc = 1 | (needed?NEEDED_MASK:0);
+ bitmap_count_page(bitmap, offset, 1);
+ page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
+ set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
+ spin_unlock_irq(&bitmap->lock);
+
}
-/* dirty the entire bitmap */
-int bitmap_setallbits(struct bitmap *bitmap)
+/*
+ * flush out any pending updates
+ */
+void bitmap_flush(mddev_t *mddev)
{
- unsigned long flags;
- unsigned long j;
-
- /* dirty the in-memory bitmap */
- bitmap_set_memory_bits(bitmap, 0, bitmap->chunks << CHUNK_BLOCK_SHIFT(bitmap), 1);
-
- /* dirty the bitmap file */
- for (j = 0; j < bitmap->file_pages; j++) {
- struct page *page = bitmap->filemap[j];
+ struct bitmap *bitmap = mddev->bitmap;
+ int sleep;
- spin_lock_irqsave(&bitmap->lock, flags);
- page_cache_get(page);
- spin_unlock_irqrestore(&bitmap->lock, flags);
- memset(kmap(page), 0xff, PAGE_SIZE);
- kunmap(page);
- write_page(page, 0);
- }
+ if (!bitmap) /* there was no bitmap */
+ return;
- return 0;
+ /* run the daemon_work three time to ensure everything is flushed
+ * that can be
+ */
+ sleep = bitmap->daemon_sleep;
+ bitmap->daemon_sleep = 0;
+ bitmap_daemon_work(bitmap);
+ bitmap_daemon_work(bitmap);
+ bitmap_daemon_work(bitmap);
+ bitmap->daemon_sleep = sleep;
+ bitmap_update_sb(bitmap);
}
/*
* free memory that was allocated
*/
-void bitmap_destroy(mddev_t *mddev)
+static void bitmap_free(struct bitmap *bitmap)
{
unsigned long k, pages;
struct bitmap_page *bp;
- struct bitmap *bitmap = mddev->bitmap;
if (!bitmap) /* there was no bitmap */
return;
- mddev->bitmap = NULL; /* disconnect from the md device */
-
/* release the bitmap file and kill the daemon */
bitmap_file_put(bitmap);
kfree(bp);
kfree(bitmap);
}
+void bitmap_destroy(mddev_t *mddev)
+{
+ struct bitmap *bitmap = mddev->bitmap;
+
+ if (!bitmap) /* there was no bitmap */
+ return;
+
+ mddev->bitmap = NULL; /* disconnect from the md device */
+ if (mddev->thread)
+ mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+
+ bitmap_free(bitmap);
+}
/*
* initialize the bitmap structure
unsigned long pages;
struct file *file = mddev->bitmap_file;
int err;
+ sector_t start;
BUG_ON(sizeof(bitmap_super_t) != 256);
- if (!file) /* bitmap disabled, nothing to do */
+ if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */
return 0;
- bitmap = kmalloc(sizeof(*bitmap), GFP_KERNEL);
+ BUG_ON(file && mddev->bitmap_offset);
+
+ bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
if (!bitmap)
return -ENOMEM;
- memset(bitmap, 0, sizeof(*bitmap));
-
spin_lock_init(&bitmap->lock);
bitmap->mddev = mddev;
- mddev->bitmap = bitmap;
spin_lock_init(&bitmap->write_lock);
- init_MUTEX_LOCKED(&bitmap->write_done);
INIT_LIST_HEAD(&bitmap->complete_pages);
init_waitqueue_head(&bitmap->write_wait);
- bitmap->write_pool = mempool_create(WRITE_POOL_SIZE, write_pool_alloc,
- write_pool_free, NULL);
+ bitmap->write_pool = mempool_create_kmalloc_pool(WRITE_POOL_SIZE,
+ sizeof(struct page_list));
+ err = -ENOMEM;
if (!bitmap->write_pool)
- return -ENOMEM;
+ goto error;
bitmap->file = file;
- get_file(file);
+ bitmap->offset = mddev->bitmap_offset;
+ if (file) get_file(file);
/* read superblock from bitmap file (this sets bitmap->chunksize) */
err = bitmap_read_sb(bitmap);
if (err)
- return err;
+ goto error;
bitmap->chunkshift = find_first_bit(&bitmap->chunksize,
sizeof(bitmap->chunksize));
bitmap->syncchunk = ~0UL;
-#if INJECT_FATAL_FAULT_1
+#ifdef INJECT_FATAL_FAULT_1
bitmap->bp = NULL;
#else
- bitmap->bp = kmalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL);
+ bitmap->bp = kzalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL);
#endif
+ err = -ENOMEM;
if (!bitmap->bp)
- return -ENOMEM;
- memset(bitmap->bp, 0, pages * sizeof(*bitmap->bp));
+ goto error;
bitmap->flags |= BITMAP_ACTIVE;
/* now that we have some pages available, initialize the in-memory
* bitmap from the on-disk bitmap */
- err = bitmap_init_from_disk(bitmap, mddev->recovery_cp == MaxSector);
+ start = 0;
+ if (mddev->degraded == 0
+ || bitmap->events_cleared == mddev->events)
+ /* no need to keep dirty bits to optimise a re-add of a missing device */
+ start = mddev->recovery_cp;
+ err = bitmap_init_from_disk(bitmap, start);
+
if (err)
- return err;
+ goto error;
printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
pages, bmname(bitmap));
- /* kick off the bitmap daemons */
- err = bitmap_start_daemons(bitmap);
- if (err)
- return err;
+ mddev->bitmap = bitmap;
+
+ if (file)
+ /* kick off the bitmap writeback daemon */
+ bitmap->writeback_daemon =
+ bitmap_start_daemon(bitmap,
+ bitmap_writeback_daemon,
+ "bitmap_wb");
+
+ if (IS_ERR(bitmap->writeback_daemon))
+ return PTR_ERR(bitmap->writeback_daemon);
+ mddev->thread->timeout = bitmap->daemon_sleep * HZ;
+
return bitmap_update_sb(bitmap);
+
+ error:
+ bitmap_free(bitmap);
+ return err;
}
/* the bitmap API -- for raid personalities */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff