tree = &BTRFS_I(page->mapping->host)->io_tree;
- if (page->private == EXTENT_PAGE_PRIVATE)
+ if (page->private == EXTENT_PAGE_PRIVATE) {
+ WARN_ON(1);
goto out;
- if (!page->private)
+ }
+ if (!page->private) {
+ WARN_ON(1);
goto out;
+ }
len = page->private >> 2;
WARN_ON(len == 0);
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
+ if (printk_ratelimit()) {
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
bdevname(bh->b_bdev, b));
bh->b_end_io = btrfs_end_buffer_write_sync;
}
- if (i == last_barrier && do_barriers && device->barriers) {
- ret = submit_bh(WRITE_BARRIER, bh);
- if (ret == -EOPNOTSUPP) {
- printk("btrfs: disabling barriers on dev %s\n",
- device->name);
- set_buffer_uptodate(bh);
- device->barriers = 0;
- /* one reference for submit_bh */
- get_bh(bh);
- lock_buffer(bh);
- ret = submit_bh(WRITE_SYNC, bh);
- }
- } else {
+ if (i == last_barrier && do_barriers)
+ ret = submit_bh(WRITE_FLUSH_FUA, bh);
+ else
ret = submit_bh(WRITE_SYNC, bh);
- }
if (ret)
errors++;
static void btrfs_issue_discard(struct block_device *bdev,
u64 start, u64 len)
{
- blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL,
- BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+ blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0);
}
static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
u64 end = start + extent_key->offset - 1;
em = alloc_extent_map(GFP_NOFS);
- BUG_ON(!em || IS_ERR(em));
+ BUG_ON(!em);
em->start = start;
em->len = extent_key->offset;
static void set_page_extent_head(struct page *page, unsigned long len)
{
+ WARN_ON(!PagePrivate(page));
set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2);
}
* at this point we can safely clear everything except the
* locked bit and the nodatasum bit
*/
- clear_extent_bit(tree, start, end,
+ ret = clear_extent_bit(tree, start, end,
~(EXTENT_LOCKED | EXTENT_NODATASUM),
0, 0, NULL, mask);
+
+ /* if clear_extent_bit failed for enomem reasons,
+ * we can't allow the release to continue.
+ */
+ if (ret < 0)
+ ret = 0;
+ else
+ ret = 1;
}
return ret;
}
eb->len = len;
spin_lock_init(&eb->lock);
init_waitqueue_head(&eb->lock_wq);
- INIT_RCU_HEAD(&eb->rcu_head);
#if LEAK_DEBUG
spin_lock_irqsave(&leak_lock, flags);
}
if (!PageUptodate(p))
uptodate = 0;
- unlock_page(p);
+
+ /*
+ * see below about how we avoid a nasty race with release page
+ * and why we unlock later
+ */
+ if (i != 0)
+ unlock_page(p);
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
atomic_inc(&eb->refs);
spin_unlock(&tree->buffer_lock);
radix_tree_preload_end();
+
+ /*
+ * there is a race where release page may have
+ * tried to find this extent buffer in the radix
+ * but failed. It will tell the VM it is safe to
+ * reclaim the, and it will clear the page private bit.
+ * We must make sure to set the page private bit properly
+ * after the extent buffer is in the radix tree so
+ * it doesn't get lost
+ */
+ set_page_extent_mapped(eb->first_page);
+ set_page_extent_head(eb->first_page, eb->len);
+ if (!page0)
+ unlock_page(eb->first_page);
return eb;
free_eb:
+ if (eb->first_page && !page0)
+ unlock_page(eb->first_page);
+
if (!atomic_dec_and_test(&eb->refs))
return exists;
btrfs_release_extent_buffer(eb);
continue;
lock_page(page);
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
if (i == 0)
set_page_extent_head(page, eb->len);
- else
- set_page_private(page, EXTENT_PAGE_PRIVATE);
clear_page_dirty_for_io(page);
spin_lock_irq(&page->mapping->tree_lock);
for (i = start_i; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
+
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
+ if (i == 0)
+ set_page_extent_head(page, eb->len);
+
if (inc_all_pages)
page_cache_get(page);
if (!PageUptodate(page)) {
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
+#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
split = alloc_extent_map(GFP_NOFS);
if (!split2)
split2 = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!split || !split2);
write_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
return 0;
}
+static long btrfs_fallocate(struct file *file, int mode,
+ loff_t offset, loff_t len)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct extent_state *cached_state = NULL;
+ u64 cur_offset;
+ u64 last_byte;
+ u64 alloc_start;
+ u64 alloc_end;
+ u64 alloc_hint = 0;
+ u64 locked_end;
+ u64 mask = BTRFS_I(inode)->root->sectorsize - 1;
+ struct extent_map *em;
+ int ret;
+
+ alloc_start = offset & ~mask;
+ alloc_end = (offset + len + mask) & ~mask;
+
+ /* We only support the FALLOC_FL_KEEP_SIZE mode */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ return -EOPNOTSUPP;
+
+ /*
+ * wait for ordered IO before we have any locks. We'll loop again
+ * below with the locks held.
+ */
+ btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start);
+
+ mutex_lock(&inode->i_mutex);
+ ret = inode_newsize_ok(inode, alloc_end);
+ if (ret)
+ goto out;
+
+ if (alloc_start > inode->i_size) {
+ ret = btrfs_cont_expand(inode, alloc_start);
+ if (ret)
+ goto out;
+ }
+
+ ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+ if (ret)
+ goto out;
+
+ locked_end = alloc_end - 1;
+ while (1) {
+ struct btrfs_ordered_extent *ordered;
+
+ /* the extent lock is ordered inside the running
+ * transaction
+ */
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
+ locked_end, 0, &cached_state, GFP_NOFS);
+ ordered = btrfs_lookup_first_ordered_extent(inode,
+ alloc_end - 1);
+ if (ordered &&
+ ordered->file_offset + ordered->len > alloc_start &&
+ ordered->file_offset < alloc_end) {
+ btrfs_put_ordered_extent(ordered);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ alloc_start, locked_end,
+ &cached_state, GFP_NOFS);
+ /*
+ * we can't wait on the range with the transaction
+ * running or with the extent lock held
+ */
+ btrfs_wait_ordered_range(inode, alloc_start,
+ alloc_end - alloc_start);
+ } else {
+ if (ordered)
+ btrfs_put_ordered_extent(ordered);
+ break;
+ }
+ }
+
+ cur_offset = alloc_start;
+ while (1) {
+ em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+ alloc_end - cur_offset, 0);
+ BUG_ON(IS_ERR(em) || !em);
+ last_byte = min(extent_map_end(em), alloc_end);
+ last_byte = (last_byte + mask) & ~mask;
+ if (em->block_start == EXTENT_MAP_HOLE ||
+ (cur_offset >= inode->i_size &&
+ !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
+ ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
+ last_byte - cur_offset,
+ 1 << inode->i_blkbits,
+ offset + len,
+ &alloc_hint);
+ if (ret < 0) {
+ free_extent_map(em);
+ break;
+ }
+ }
+ free_extent_map(em);
+
+ cur_offset = last_byte;
+ if (cur_offset >= alloc_end) {
+ ret = 0;
+ break;
+ }
+ }
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
+ &cached_state, GFP_NOFS);
+
+ btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
+out:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}
+
const struct file_operations btrfs_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
.open = generic_file_open,
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
+ .fallocate = btrfs_fallocate,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_ioctl,
async_extent->ram_size - 1, 0);
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = async_extent->start;
em->len = async_extent->ram_size;
em->orig_start = em->start;
BUG_ON(ret);
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = start;
em->orig_start = em->start;
ram_size = ins.offset;
struct extent_map_tree *em_tree;
em_tree = &BTRFS_I(inode)->extent_tree;
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = cur_offset;
em->orig_start = em->start;
em->len = num_bytes;
p = &root->inode_tree.rb_node;
parent = NULL;
- if (hlist_unhashed(&inode->i_hash))
+ if (inode_unhashed(inode))
return;
spin_lock(&root->inode_lock);
int index;
int ret;
- dentry->d_op = &btrfs_dentry_operations;
-
if (dentry->d_name.len > BTRFS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
return inode;
}
-static int btrfs_dentry_delete(struct dentry *dentry)
+static int btrfs_dentry_delete(const struct dentry *dentry)
{
struct btrfs_root *root;
}
btrfs_set_trans_block_group(trans, dir);
- atomic_inc(&inode->i_count);
+ ihold(inode);
err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
return inode;
}
+static void btrfs_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+}
+
void btrfs_destroy_inode(struct inode *inode)
{
struct btrfs_ordered_extent *ordered;
inode_tree_del(inode);
btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
free:
- kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+ call_rcu(&inode->i_rcu, btrfs_i_callback);
}
int btrfs_drop_inode(struct inode *inode)
min_size, actual_len, alloc_hint, trans);
}
-static long btrfs_fallocate(struct inode *inode, int mode,
- loff_t offset, loff_t len)
-{
- struct extent_state *cached_state = NULL;
- u64 cur_offset;
- u64 last_byte;
- u64 alloc_start;
- u64 alloc_end;
- u64 alloc_hint = 0;
- u64 locked_end;
- u64 mask = BTRFS_I(inode)->root->sectorsize - 1;
- struct extent_map *em;
- int ret;
-
- alloc_start = offset & ~mask;
- alloc_end = (offset + len + mask) & ~mask;
-
- /*
- * wait for ordered IO before we have any locks. We'll loop again
- * below with the locks held.
- */
- btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start);
-
- mutex_lock(&inode->i_mutex);
- ret = inode_newsize_ok(inode, alloc_end);
- if (ret)
- goto out;
-
- if (alloc_start > inode->i_size) {
- ret = btrfs_cont_expand(inode, alloc_start);
- if (ret)
- goto out;
- }
-
- ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
- if (ret)
- goto out;
-
- locked_end = alloc_end - 1;
- while (1) {
- struct btrfs_ordered_extent *ordered;
-
- /* the extent lock is ordered inside the running
- * transaction
- */
- lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
- locked_end, 0, &cached_state, GFP_NOFS);
- ordered = btrfs_lookup_first_ordered_extent(inode,
- alloc_end - 1);
- if (ordered &&
- ordered->file_offset + ordered->len > alloc_start &&
- ordered->file_offset < alloc_end) {
- btrfs_put_ordered_extent(ordered);
- unlock_extent_cached(&BTRFS_I(inode)->io_tree,
- alloc_start, locked_end,
- &cached_state, GFP_NOFS);
- /*
- * we can't wait on the range with the transaction
- * running or with the extent lock held
- */
- btrfs_wait_ordered_range(inode, alloc_start,
- alloc_end - alloc_start);
- } else {
- if (ordered)
- btrfs_put_ordered_extent(ordered);
- break;
- }
- }
-
- cur_offset = alloc_start;
- while (1) {
- em = btrfs_get_extent(inode, NULL, 0, cur_offset,
- alloc_end - cur_offset, 0);
- BUG_ON(IS_ERR(em) || !em);
- last_byte = min(extent_map_end(em), alloc_end);
- last_byte = (last_byte + mask) & ~mask;
- if (em->block_start == EXTENT_MAP_HOLE ||
- (cur_offset >= inode->i_size &&
- !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
- ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
- last_byte - cur_offset,
- 1 << inode->i_blkbits,
- offset + len,
- &alloc_hint);
- if (ret < 0) {
- free_extent_map(em);
- break;
- }
- }
- free_extent_map(em);
-
- cur_offset = last_byte;
- if (cur_offset >= alloc_end) {
- ret = 0;
- break;
- }
- }
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
- &cached_state, GFP_NOFS);
-
- btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
-out:
- mutex_unlock(&inode->i_mutex);
- return ret;
-}
-
static int btrfs_set_page_dirty(struct page *page)
{
return __set_page_dirty_nobuffers(page);
}
-static int btrfs_permission(struct inode *inode, int mask)
+static int btrfs_permission(struct inode *inode, int mask, unsigned int flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
return -EROFS;
if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
return -EACCES;
- return generic_permission(inode, mask, btrfs_check_acl);
+ return generic_permission(inode, mask, flags, btrfs_check_acl);
}
static const struct inode_operations btrfs_dir_inode_operations = {
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
- .fallocate = btrfs_fallocate,
.fiemap = btrfs_fiemap,
};
static const struct inode_operations btrfs_special_inode_operations = {
device->work.func = pending_bios_fn;
memcpy(device->uuid, disk_super->dev_item.uuid,
BTRFS_UUID_SIZE);
- device->barriers = 1;
spin_lock_init(&device->io_lock);
device->name = kstrdup(path, GFP_NOFS);
if (!device->name) {
device->devid = orig_dev->devid;
device->work.func = pending_bios_fn;
memcpy(device->uuid, orig_dev->uuid, sizeof(device->uuid));
- device->barriers = 1;
spin_lock_init(&device->io_lock);
INIT_LIST_HEAD(&device->dev_list);
INIT_LIST_HEAD(&device->dev_alloc_list);
continue;
if (device->bdev) {
- close_bdev_exclusive(device->bdev, device->mode);
+ blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
fs_devices->open_devices--;
}
list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (device->bdev) {
- close_bdev_exclusive(device->bdev, device->mode);
+ blkdev_put(device->bdev, device->mode);
fs_devices->open_devices--;
}
if (device->writeable) {
int seeding = 1;
int ret = 0;
+ flags |= FMODE_EXCL;
+
list_for_each_entry(device, head, dev_list) {
if (device->bdev)
continue;
if (!device->name)
continue;
- bdev = open_bdev_exclusive(device->name, flags, holder);
+ bdev = blkdev_get_by_path(device->name, flags, holder);
if (IS_ERR(bdev)) {
printk(KERN_INFO "open %s failed\n", device->name);
goto error;
error_brelse:
brelse(bh);
error_close:
- close_bdev_exclusive(bdev, FMODE_READ);
+ blkdev_put(bdev, flags);
error:
continue;
}
mutex_lock(&uuid_mutex);
- bdev = open_bdev_exclusive(path, flags, holder);
+ flags |= FMODE_EXCL;
+ bdev = blkdev_get_by_path(path, flags, holder);
if (IS_ERR(bdev)) {
ret = PTR_ERR(bdev);
brelse(bh);
error_close:
- close_bdev_exclusive(bdev, flags);
+ blkdev_put(bdev, flags);
error:
mutex_unlock(&uuid_mutex);
return ret;
goto out;
}
} else {
- bdev = open_bdev_exclusive(device_path, FMODE_READ,
- root->fs_info->bdev_holder);
+ bdev = blkdev_get_by_path(device_path, FMODE_READ | FMODE_EXCL,
+ root->fs_info->bdev_holder);
if (IS_ERR(bdev)) {
ret = PTR_ERR(bdev);
goto out;
root->fs_info->fs_devices->latest_bdev = next_device->bdev;
if (device->bdev) {
- close_bdev_exclusive(device->bdev, device->mode);
+ blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
device->fs_devices->open_devices--;
}
brelse(bh);
error_close:
if (bdev)
- close_bdev_exclusive(bdev, FMODE_READ);
+ blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
out:
mutex_unlock(&root->fs_info->volume_mutex);
mutex_unlock(&uuid_mutex);
if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
return -EINVAL;
- bdev = open_bdev_exclusive(device_path, 0, root->fs_info->bdev_holder);
+ bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+ root->fs_info->bdev_holder);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
ret = find_next_devid(root, &device->devid);
if (ret) {
+ kfree(device->name);
kfree(device);
goto error;
}
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
+ kfree(device->name);
kfree(device);
ret = PTR_ERR(trans);
goto error;
lock_chunks(root);
- device->barriers = 1;
device->writeable = 1;
device->work.func = pending_bios_fn;
generate_random_uuid(device->uuid);
mutex_unlock(&root->fs_info->volume_mutex);
return ret;
error:
- close_bdev_exclusive(bdev, 0);
+ blkdev_put(bdev, FMODE_EXCL);
if (seeding_dev) {
mutex_unlock(&uuid_mutex);
up_write(&sb->s_umount);
return NULL;
list_add(&device->dev_list,
&fs_devices->devices);
- device->barriers = 1;
device->dev_root = root->fs_info->dev_root;
device->devid = devid;
device->work.func = pending_bios_fn;
git.openpandora.org / pandora-kernel.git / commitdiff