* async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de>
*/
-#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
+#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/quotaops.h>
{
int ret = 0;
- if (bdev) {
- int err;
-
- ret = filemap_fdatawrite(bdev->bd_inode->i_mapping);
- err = filemap_fdatawait(bdev->bd_inode->i_mapping);
- if (!ret)
- ret = err;
- }
+ if (bdev)
+ ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
return ret;
}
EXPORT_SYMBOL(sync_blockdev);
/*
* Write out and wait upon all dirty data associated with this
- * superblock. Filesystem data as well as the underlying block
- * device. Takes the superblock lock.
- */
-int fsync_super(struct super_block *sb)
-{
- sync_inodes_sb(sb, 0);
- DQUOT_SYNC(sb);
- lock_super(sb);
- if (sb->s_dirt && sb->s_op->write_super)
- sb->s_op->write_super(sb);
- unlock_super(sb);
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, 1);
- sync_blockdev(sb->s_bdev);
- sync_inodes_sb(sb, 1);
-
- return sync_blockdev(sb->s_bdev);
-}
-
-/*
- * Write out and wait upon all dirty data associated with this
* device. Filesystem data as well as the underlying block
* device. Takes the superblock lock.
*/
* freeze_bdev -- lock a filesystem and force it into a consistent state
* @bdev: blockdevice to lock
*
- * This takes the block device bd_mount_sem to make sure no new mounts
+ * This takes the block device bd_mount_mutex to make sure no new mounts
* happen on bdev until thaw_bdev() is called.
* If a superblock is found on this device, we take the s_umount semaphore
* on it to make sure nobody unmounts until the snapshot creation is done.
{
struct super_block *sb;
- down(&bdev->bd_mount_sem);
+ mutex_lock(&bdev->bd_mount_mutex);
sb = get_super(bdev);
if (sb && !(sb->s_flags & MS_RDONLY)) {
sb->s_frozen = SB_FREEZE_WRITE;
smp_wmb();
- sync_inodes_sb(sb, 0);
- DQUOT_SYNC(sb);
-
- lock_super(sb);
- if (sb->s_dirt && sb->s_op->write_super)
- sb->s_op->write_super(sb);
- unlock_super(sb);
-
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, 1);
-
- sync_blockdev(sb->s_bdev);
- sync_inodes_sb(sb, 1);
+ __fsync_super(sb);
sb->s_frozen = SB_FREEZE_TRANS;
smp_wmb();
drop_super(sb);
}
- up(&bdev->bd_mount_sem);
+ mutex_unlock(&bdev->bd_mount_mutex);
}
EXPORT_SYMBOL(thaw_bdev);
/*
- * sync everything. Start out by waking pdflush, because that writes back
- * all queues in parallel.
- */
-static void do_sync(unsigned long wait)
-{
- wakeup_pdflush(0);
- sync_inodes(0); /* All mappings, inodes and their blockdevs */
- DQUOT_SYNC(NULL);
- sync_supers(); /* Write the superblocks */
- sync_filesystems(0); /* Start syncing the filesystems */
- sync_filesystems(wait); /* Waitingly sync the filesystems */
- sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */
- if (!wait)
- printk("Emergency Sync complete\n");
- if (unlikely(laptop_mode))
- laptop_sync_completion();
-}
-
-asmlinkage long sys_sync(void)
-{
- do_sync(1);
- return 0;
-}
-
-void emergency_sync(void)
-{
- pdflush_operation(do_sync, 0);
-}
-
-/*
- * Generic function to fsync a file.
- *
- * filp may be NULL if called via the msync of a vma.
- */
-
-int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
-{
- struct inode * inode = dentry->d_inode;
- struct super_block * sb;
- int ret, err;
-
- /* sync the inode to buffers */
- ret = write_inode_now(inode, 0);
-
- /* sync the superblock to buffers */
- sb = inode->i_sb;
- lock_super(sb);
- if (sb->s_op->write_super)
- sb->s_op->write_super(sb);
- unlock_super(sb);
-
- /* .. finally sync the buffers to disk */
- err = sync_blockdev(sb->s_bdev);
- if (!ret)
- ret = err;
- return ret;
-}
-
-static long do_fsync(unsigned int fd, int datasync)
-{
- struct file * file;
- struct address_space *mapping;
- int ret, err;
-
- ret = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
-
- ret = -EINVAL;
- if (!file->f_op || !file->f_op->fsync) {
- /* Why? We can still call filemap_fdatawrite */
- goto out_putf;
- }
-
- mapping = file->f_mapping;
-
- current->flags |= PF_SYNCWRITE;
- ret = filemap_fdatawrite(mapping);
-
- /*
- * We need to protect against concurrent writers,
- * which could cause livelocks in fsync_buffers_list
- */
- down(&mapping->host->i_sem);
- err = file->f_op->fsync(file, file->f_dentry, datasync);
- if (!ret)
- ret = err;
- up(&mapping->host->i_sem);
- err = filemap_fdatawait(mapping);
- if (!ret)
- ret = err;
- current->flags &= ~PF_SYNCWRITE;
-
-out_putf:
- fput(file);
-out:
- return ret;
-}
-
-asmlinkage long sys_fsync(unsigned int fd)
-{
- return do_fsync(fd, 0);
-}
-
-asmlinkage long sys_fdatasync(unsigned int fd)
-{
- return do_fsync(fd, 1);
-}
-
-/*
* Various filesystems appear to want __find_get_block to be non-blocking.
* But it's the page lock which protects the buffers. To get around this,
* we get exclusion from try_to_free_buffers with the blockdev mapping's
if (all_mapped) {
printk("__find_get_block_slow() failed. "
"block=%llu, b_blocknr=%llu\n",
- (unsigned long long)block, (unsigned long long)bh->b_blocknr);
- printk("b_state=0x%08lx, b_size=%u\n", bh->b_state, bh->b_size);
+ (unsigned long long)block,
+ (unsigned long long)bh->b_blocknr);
+ printk("b_state=0x%08lx, b_size=%zu\n",
+ bh->b_state, bh->b_size);
printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits);
}
out_unlock:
pass does the actual I/O. */
void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers)
{
+ struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+ if (mapping->nrpages == 0)
+ return;
+
invalidate_bh_lrus();
/*
* FIXME: what about destroy_dirty_buffers?
* We really want to use invalidate_inode_pages2() for
* that, but not until that's cleaned up.
*/
- invalidate_inode_pages(bdev->bd_inode->i_mapping);
+ invalidate_inode_pages(mapping);
}
/*
wakeup_pdflush(1024);
yield();
- for_each_pgdat(pgdat) {
+ for_each_online_pgdat(pgdat) {
zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
if (*zones)
try_to_free_pages(zones, GFP_NOFS);
* Completion handler for block_write_full_page() - pages which are unlocked
* during I/O, and which have PageWriteback cleared upon I/O completion.
*/
-void end_buffer_async_write(struct buffer_head *bh, int uptodate)
+static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
char b[BDEVNAME_SIZE];
unsigned long flags;
if (!mapping->assoc_mapping) {
mapping->assoc_mapping = buffer_mapping;
} else {
- if (mapping->assoc_mapping != buffer_mapping)
- BUG();
+ BUG_ON(mapping->assoc_mapping != buffer_mapping);
}
if (list_empty(&bh->b_assoc_buffers)) {
spin_lock(&buffer_mapping->private_lock);
*/
int __set_page_dirty_buffers(struct page *page)
{
- struct address_space * const mapping = page->mapping;
+ struct address_space * const mapping = page_mapping(page);
+
+ if (unlikely(!mapping))
+ return !TestSetPageDirty(page);
spin_lock(&mapping->private_lock);
if (page_has_buffers(page)) {
write_lock_irq(&mapping->tree_lock);
if (page->mapping) { /* Race with truncate? */
if (mapping_cap_account_dirty(mapping))
- inc_page_state(nr_dirty);
+ __inc_zone_page_state(page, NR_FILE_DIRTY);
radix_tree_tag_set(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
}
write_unlock_irq(&mapping->tree_lock);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ return 1;
}
-
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_buffers);
bh->b_state = 0;
atomic_set(&bh->b_count, 0);
+ bh->b_private = NULL;
bh->b_size = size;
/* Link the buffer to its page */
set_bh_page(bh, page, offset);
- bh->b_end_io = NULL;
+ init_buffer(bh, NULL, NULL);
}
return head;
/*
if (!page)
return NULL;
- if (!PageLocked(page))
- BUG();
+ BUG_ON(!PageLocked(page));
if (page_has_buffers(page)) {
bh = page_buffers(page);
* some of those buffers may be aliases of filesystem data.
* grow_dev_page() will go BUG() if this happens.
*/
-static inline int
+static int
grow_buffers(struct block_device *bdev, sector_t block, int size)
{
struct page *page;
/*
* Look up the bh in this cpu's LRU. If it's there, move it to the head.
*/
-static inline struct buffer_head *
+static struct buffer_head *
lookup_bh_lru(struct block_device *bdev, sector_t block, int size)
{
struct buffer_head *ret = NULL;
struct page *page, unsigned long offset)
{
bh->b_page = page;
- if (offset >= PAGE_SIZE)
- BUG();
+ BUG_ON(offset >= PAGE_SIZE);
if (PageHighMem(page))
/*
* This catches illegal uses and preserves the offset:
/*
* Called when truncating a buffer on a page completely.
*/
-static inline void discard_buffer(struct buffer_head * bh)
+static void discard_buffer(struct buffer_head * bh)
{
lock_buffer(bh);
clear_buffer_dirty(bh);
}
/**
- * try_to_release_page() - release old fs-specific metadata on a page
- *
- * @page: the page which the kernel is trying to free
- * @gfp_mask: memory allocation flags (and I/O mode)
- *
- * The address_space is to try to release any data against the page
- * (presumably at page->private). If the release was successful, return `1'.
- * Otherwise return zero.
- *
- * The @gfp_mask argument specifies whether I/O may be performed to release
- * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
- *
- * NOTE: @gfp_mask may go away, and this function may become non-blocking.
- */
-int try_to_release_page(struct page *page, gfp_t gfp_mask)
-{
- struct address_space * const mapping = page->mapping;
-
- BUG_ON(!PageLocked(page));
- if (PageWriteback(page))
- return 0;
-
- if (mapping && mapping->a_ops->releasepage)
- return mapping->a_ops->releasepage(page, gfp_mask);
- return try_to_free_buffers(page);
-}
-EXPORT_SYMBOL(try_to_release_page);
-
-/**
* block_invalidatepage - invalidate part of all of a buffer-backed page
*
* @page: the page which is affected
* point. Because the caller is about to free (and possibly reuse) those
* blocks on-disk.
*/
-int block_invalidatepage(struct page *page, unsigned long offset)
+void block_invalidatepage(struct page *page, unsigned long offset)
{
struct buffer_head *head, *bh, *next;
unsigned int curr_off = 0;
- int ret = 1;
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
* so real IO is not possible anymore.
*/
if (offset == 0)
- ret = try_to_release_page(page, 0);
+ try_to_release_page(page, 0);
out:
- return ret;
+ return;
}
EXPORT_SYMBOL(block_invalidatepage);
-int do_invalidatepage(struct page *page, unsigned long offset)
-{
- int (*invalidatepage)(struct page *, unsigned long);
- invalidatepage = page->mapping->a_ops->invalidatepage;
- if (invalidatepage == NULL)
- invalidatepage = block_invalidatepage;
- return (*invalidatepage)(page, offset);
-}
-
/*
* We attach and possibly dirty the buffers atomically wrt
* __set_page_dirty_buffers() via private_lock. try_to_free_buffers
sector_t block;
sector_t last_block;
struct buffer_head *bh, *head;
+ const unsigned blocksize = 1 << inode->i_blkbits;
int nr_underway = 0;
BUG_ON(!PageLocked(page));
last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;
if (!page_has_buffers(page)) {
- create_empty_buffers(page, 1 << inode->i_blkbits,
+ create_empty_buffers(page, blocksize,
(1 << BH_Dirty)|(1 << BH_Uptodate));
}
* handle that here by just cleaning them.
*/
- block = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
head = page_buffers(page);
bh = head;
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
} else if (!buffer_mapped(bh) && buffer_dirty(bh)) {
+ WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
goto recover;
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
+ WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
break;
fully_mapped = 0;
if (iblock < lblock) {
+ WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
if (err)
SetPageError(page);
__block_commit_write(inode,page,from,to);
/*
* No need to use i_size_read() here, the i_size
- * cannot change under us because we hold i_sem.
+ * cannot change under us because we hold i_mutex.
*/
if (pos > inode->i_size) {
i_size_write(inode, pos);
create = 1;
if (block_start >= to)
create = 0;
+ map_bh.b_size = blocksize;
ret = get_block(inode, block_in_file + block_in_page,
&map_bh, create);
if (ret)
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned to;
struct page *page;
- struct address_space_operations *a_ops = mapping->a_ops;
+ const struct address_space_operations *a_ops = mapping->a_ops;
char *kaddr;
int ret = 0;
pgoff_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize;
- pgoff_t iblock;
+ sector_t iblock;
unsigned length, pos;
struct inode *inode = mapping->host;
struct page *page;
return 0;
length = blocksize - length;
- iblock = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
page = grab_cache_page(mapping, index);
err = -ENOMEM;
err = 0;
if (!buffer_mapped(bh)) {
+ WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
if (err)
goto unlock;
struct inode *inode = mapping->host;
tmp.b_state = 0;
tmp.b_blocknr = 0;
+ tmp.b_size = 1 << inode->i_blkbits;
get_block(inode, block, &tmp, 0);
return tmp.b_blocknr;
}
else if (test_set_buffer_locked(bh))
continue;
- get_bh(bh);
if (rw == WRITE || rw == SWRITE) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
+ get_bh(bh);
submit_bh(WRITE, bh);
continue;
}
} else {
if (!buffer_uptodate(bh)) {
bh->b_end_io = end_buffer_read_sync;
+ get_bh(bh);
submit_bh(rw, bh);
continue;
}
}
unlock_buffer(bh);
- put_bh(bh);
}
}
spin_lock(&mapping->private_lock);
ret = drop_buffers(page, &buffers_to_free);
+ spin_unlock(&mapping->private_lock);
if (ret) {
/*
* If the filesystem writes its buffers by hand (eg ext3)
*/
clear_page_dirty(page);
}
- spin_unlock(&mapping->private_lock);
out:
if (buffers_to_free) {
struct buffer_head *bh = buffers_to_free;
}
EXPORT_SYMBOL(try_to_free_buffers);
-int block_sync_page(struct page *page)
+void block_sync_page(struct page *page)
{
struct address_space *mapping;
mapping = page_mapping(page);
if (mapping)
blk_run_backing_dev(mapping->backing_dev_info, page);
- return 0;
}
/*
if (__get_cpu_var(bh_accounting).ratelimit++ < 4096)
return;
__get_cpu_var(bh_accounting).ratelimit = 0;
- for_each_cpu(i)
+ for_each_online_cpu(i)
tot += per_cpu(bh_accounting, i).nr;
buffer_heads_over_limit = (tot > max_buffer_heads);
}
brelse(b->bhs[i]);
b->bhs[i] = NULL;
}
+ get_cpu_var(bh_accounting).nr += per_cpu(bh_accounting, cpu).nr;
+ per_cpu(bh_accounting, cpu).nr = 0;
+ put_cpu_var(bh_accounting);
}
static int buffer_cpu_notify(struct notifier_block *self,
int nrpages;
bh_cachep = kmem_cache_create("buffer_head",
- sizeof(struct buffer_head), 0,
- SLAB_RECLAIM_ACCOUNT|SLAB_PANIC, init_buffer_head, NULL);
+ sizeof(struct buffer_head), 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
+ SLAB_MEM_SPREAD),
+ init_buffer_head,
+ NULL);
/*
* Limit the bh occupancy to 10% of ZONE_NORMAL
EXPORT_SYMBOL(block_truncate_page);
EXPORT_SYMBOL(block_write_full_page);
EXPORT_SYMBOL(cont_prepare_write);
-EXPORT_SYMBOL(end_buffer_async_write);
EXPORT_SYMBOL(end_buffer_read_sync);
EXPORT_SYMBOL(end_buffer_write_sync);
EXPORT_SYMBOL(file_fsync);