void unlock_buffer(struct buffer_head *bh)
{
- smp_mb__before_clear_bit();
- clear_buffer_locked(bh);
+ clear_bit_unlock(BH_Lock, &bh->b_state);
smp_mb__after_clear_bit();
wake_up_bit(&bh->b_state, BH_Lock);
}
page_cache_release(page);
}
+
+static int quiet_error(struct buffer_head *bh)
+{
+ if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit())
+ return 0;
+ return 1;
+}
+
+
static void buffer_io_error(struct buffer_head *bh)
{
char b[BDEVNAME_SIZE];
-
printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n",
bdevname(bh->b_bdev, b),
(unsigned long long)bh->b_blocknr);
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
+ if (!buffer_eopnotsupp(bh) && !quiet_error(bh)) {
buffer_io_error(bh);
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
}
/*
- * Write out and wait upon all the dirty data associated with a block
- * device via its mapping. Does not take the superblock lock.
- */
-int sync_blockdev(struct block_device *bdev)
-{
- int ret = 0;
-
- 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
- * device. Filesystem data as well as the underlying block
- * device. Takes the superblock lock.
- */
-int fsync_bdev(struct block_device *bdev)
-{
- struct super_block *sb = get_super(bdev);
- if (sb) {
- int res = fsync_super(sb);
- drop_super(sb);
- return res;
- }
- return sync_blockdev(bdev);
-}
-
-/**
- * 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
- * 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 *freeze_bdev(struct block_device *bdev)
-{
- struct super_block *sb;
-
- down(&bdev->bd_mount_sem);
- sb = get_super(bdev);
- if (sb && !(sb->s_flags & MS_RDONLY)) {
- sb->s_frozen = SB_FREEZE_WRITE;
- smp_wmb();
-
- __fsync_super(sb);
-
- sb->s_frozen = SB_FREEZE_TRANS;
- smp_wmb();
-
- sync_blockdev(sb->s_bdev);
-
- if (sb->s_op->write_super_lockfs)
- sb->s_op->write_super_lockfs(sb);
- }
-
- sync_blockdev(bdev);
- return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */
-}
-EXPORT_SYMBOL(freeze_bdev);
-
-/**
- * thaw_bdev -- unlock filesystem
- * @bdev: blockdevice to unlock
- * @sb: associated superblock
- *
- * Unlocks the filesystem and marks it writeable again after freeze_bdev().
- */
-void thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
- if (sb) {
- BUG_ON(sb->s_bdev != bdev);
-
- if (sb->s_op->unlockfs)
- sb->s_op->unlockfs(sb);
- sb->s_frozen = SB_UNFROZEN;
- smp_wmb();
- wake_up(&sb->s_wait_unfrozen);
- drop_super(sb);
- }
-
- up(&bdev->bd_mount_sem);
-}
-EXPORT_SYMBOL(thaw_bdev);
-
-/*
* 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
&zone);
if (zone)
try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
- GFP_NOFS);
+ GFP_NOFS, NULL);
}
}
set_buffer_uptodate(bh);
} else {
clear_buffer_uptodate(bh);
- if (printk_ratelimit())
+ if (!quiet_error(bh))
buffer_io_error(bh);
SetPageError(page);
}
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (printk_ratelimit()) {
+ if (!quiet_error(bh)) {
buffer_io_error(bh);
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
/*
* The buffer's backing address_space's private_lock must be held
*/
-static inline void __remove_assoc_queue(struct buffer_head *bh)
+static void __remove_assoc_queue(struct buffer_head *bh)
{
list_del_init(&bh->b_assoc_buffers);
WARN_ON(!bh->b_assoc_map);
return err;
}
+void do_thaw_all(unsigned long unused)
+{
+ struct super_block *sb;
+ char b[BDEVNAME_SIZE];
+
+ spin_lock(&sb_lock);
+restart:
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ sb->s_count++;
+ spin_unlock(&sb_lock);
+ down_read(&sb->s_umount);
+ while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+ printk(KERN_WARNING "Emergency Thaw on %s\n",
+ bdevname(sb->s_bdev, b));
+ up_read(&sb->s_umount);
+ spin_lock(&sb_lock);
+ if (__put_super_and_need_restart(sb))
+ goto restart;
+ }
+ spin_unlock(&sb_lock);
+ printk(KERN_WARNING "Emergency Thaw complete\n");
+}
+
+/**
+ * emergency_thaw_all -- forcibly thaw every frozen filesystem
+ *
+ * Used for emergency unfreeze of all filesystems via SysRq
+ */
+void emergency_thaw_all(void)
+{
+ pdflush_operation(do_thaw_all, 0);
+}
+
/**
* sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
* @mapping: the mapping which wants those buffers written
* If warn is true, then emit a warning if the page is not uptodate and has
* not been truncated.
*/
-static int __set_page_dirty(struct page *page,
+static void __set_page_dirty(struct page *page,
struct address_space *mapping, int warn)
{
- if (unlikely(!mapping))
- return !TestSetPageDirty(page);
-
- if (TestSetPageDirty(page))
- return 0;
-
spin_lock_irq(&mapping->tree_lock);
if (page->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
-
- if (mapping_cap_account_dirty(mapping)) {
- __inc_zone_page_state(page, NR_FILE_DIRTY);
- __inc_bdi_stat(mapping->backing_dev_info,
- BDI_RECLAIMABLE);
- task_io_account_write(PAGE_CACHE_SIZE);
- }
+ account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-
- return 1;
}
/*
*/
int __set_page_dirty_buffers(struct page *page)
{
+ int newly_dirty;
struct address_space *mapping = page_mapping(page);
if (unlikely(!mapping))
bh = bh->b_this_page;
} while (bh != head);
}
+ newly_dirty = !TestSetPageDirty(page);
spin_unlock(&mapping->private_lock);
- return __set_page_dirty(page, mapping, 1);
+ if (newly_dirty)
+ __set_page_dirty(page, mapping, 1);
+ return newly_dirty;
}
EXPORT_SYMBOL(__set_page_dirty_buffers);
spin_unlock(&buffer_mapping->private_lock);
}
}
+EXPORT_SYMBOL(invalidate_inode_buffers);
/*
* Remove any clean buffers from the inode's buffer list. This is called
return;
}
- if (!test_set_buffer_dirty(bh))
- __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
+ if (!test_set_buffer_dirty(bh)) {
+ struct page *page = bh->b_page;
+ if (!TestSetPageDirty(page))
+ __set_page_dirty(page, page_mapping(page), 0);
+ }
}
/*
put_bh(buf);
return;
}
- printk(KERN_ERR "VFS: brelse: Trying to free free buffer\n");
- WARN_ON(1);
+ WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}
/*
*/
if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
lock_buffer(bh);
- } else if (test_set_buffer_locked(bh)) {
+ } else if (!trylock_buffer(bh)) {
redirty_page_for_writepage(wbc, page);
continue;
}
page = *pagep;
if (page == NULL) {
ownpage = 1;
- page = __grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
status = -ENOMEM;
goto out;
if (pos + len > inode->i_size)
vmtruncate(inode, inode->i_size);
}
- goto out;
}
out:
EXPORT_SYMBOL(generic_write_end);
/*
+ * block_is_partially_uptodate checks whether buffers within a page are
+ * uptodate or not.
+ *
+ * Returns true if all buffers which correspond to a file portion
+ * we want to read are uptodate.
+ */
+int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
+ unsigned long from)
+{
+ struct inode *inode = page->mapping->host;
+ unsigned block_start, block_end, blocksize;
+ unsigned to;
+ struct buffer_head *bh, *head;
+ int ret = 1;
+
+ if (!page_has_buffers(page))
+ return 0;
+
+ blocksize = 1 << inode->i_blkbits;
+ to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
+ to = from + to;
+ if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
+ return 0;
+
+ head = page_buffers(page);
+ bh = head;
+ block_start = 0;
+ do {
+ block_end = block_start + blocksize;
+ if (block_end > from && block_start < to) {
+ if (!buffer_uptodate(bh)) {
+ ret = 0;
+ break;
+ }
+ if (block_end >= to)
+ break;
+ }
+ block_start = block_end;
+ bh = bh->b_this_page;
+ } while (bh != head);
+
+ return ret;
+}
+EXPORT_SYMBOL(block_is_partially_uptodate);
+
+/*
* Generic "read page" function for block devices that have the normal
* get_block functionality. This is most of the block device filesystems.
* Reads the page asynchronously --- the unlock_buffer() and
* unlock the page.
*/
int
-block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
+ struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
unsigned long end;
loff_t size;
- int ret = -EINVAL;
+ int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
lock_page(page);
size = i_size_read(inode);
if (!ret)
ret = block_commit_write(page, 0, end);
+ if (unlikely(ret)) {
+ if (ret == -ENOMEM)
+ ret = VM_FAULT_OOM;
+ else /* -ENOSPC, -EIO, etc */
+ ret = VM_FAULT_SIGBUS;
+ }
+
out_unlock:
unlock_page(page);
return ret;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
- page = __grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
struct buffer_head *bh;
BUG_ON(fsdata != NULL && page_has_buffers(page));
- if (unlikely(copied < len) && !page_has_buffers(page))
+ if (unlikely(copied < len) && head)
attach_nobh_buffers(page, head);
if (page_has_buffers(page))
return generic_write_end(file, mapping, pos, len,
set_bit(BH_Eopnotsupp, &bh->b_state);
}
+ if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
+ set_bit(BH_Quiet, &bh->b_state);
+
bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
bio_put(bio);
}
BUG_ON(!buffer_mapped(bh));
BUG_ON(!bh->b_end_io);
- if (buffer_ordered(bh) && (rw == WRITE))
- rw = WRITE_BARRIER;
+ /*
+ * Mask in barrier bit for a write (could be either a WRITE or a
+ * WRITE_SYNC
+ */
+ if (buffer_ordered(bh) && (rw & WRITE))
+ rw |= WRITE_BARRIER;
/*
- * Only clear out a write error when rewriting, should this
- * include WRITE_SYNC as well?
+ * Only clear out a write error when rewriting
*/
- if (test_set_buffer_req(bh) && (rw == WRITE || rw == WRITE_BARRIER))
+ if (test_set_buffer_req(bh) && (rw & WRITE))
clear_buffer_write_io_error(bh);
/*
if (rw == SWRITE || rw == SWRITE_SYNC)
lock_buffer(bh);
- else if (test_set_buffer_locked(bh))
+ else if (!trylock_buffer(bh))
continue;
if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
if (test_clear_buffer_dirty(bh)) {
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(WRITE_SYNC, bh);
+ ret = submit_bh(WRITE, bh);
wait_on_buffer(bh);
if (buffer_eopnotsupp(bh)) {
clear_buffer_eopnotsupp(bh);
* Use of bdflush() is deprecated and will be removed in a future kernel.
* The `pdflush' kernel threads fully replace bdflush daemons and this call.
*/
-asmlinkage long sys_bdflush(int func, long data)
+SYSCALL_DEFINE2(bdflush, int, func, long, data)
{
static int msg_count;
EXPORT_SYMBOL(bh_submit_read);
static void
-init_buffer_head(struct kmem_cache *cachep, void *data)
+init_buffer_head(void *data)
{
struct buffer_head *bh = data;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff