summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/autofs_i.h8
-rw-r--r--fs/autofs4/expire.c27
-rw-r--r--fs/autofs4/root.c2
-rw-r--r--fs/autofs4/waitq.c7
-rw-r--r--fs/btrfs/check-integrity.c2
-rw-r--r--fs/btrfs/ctree.c13
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/delayed-inode.c27
-rw-r--r--fs/btrfs/delayed-inode.h10
-rw-r--r--fs/btrfs/disk-io.c38
-rw-r--r--fs/btrfs/extent-tree.c27
-rw-r--r--fs/btrfs/extent_io.c22
-rw-r--r--fs/btrfs/file.c44
-rw-r--r--fs/btrfs/inode.c22
-rw-r--r--fs/btrfs/ordered-data.c3
-rw-r--r--fs/btrfs/super.c4
-rw-r--r--fs/btrfs/tests/btrfs-tests.c2
-rw-r--r--fs/btrfs/transaction.c10
-rw-r--r--fs/btrfs/transaction.h2
-rw-r--r--fs/btrfs/tree-log.c4
-rw-r--r--fs/btrfs/volumes.c8
-rw-r--r--fs/dcache.c75
-rw-r--r--fs/debugfs/file.c7
-rw-r--r--fs/internal.h1
-rw-r--r--fs/jbd2/journal.c32
-rw-r--r--fs/libfs.c4
-rw-r--r--fs/namespace.c4
-rw-r--r--fs/nfsd/blocklayout.c2
-rw-r--r--fs/nfsd/nfs2acl.c20
-rw-r--r--fs/nfsd/nfs3acl.c16
-rw-r--r--fs/nfsd/nfs4acl.c16
-rw-r--r--fs/nfsd/nfs4callback.c18
-rw-r--r--fs/nfsd/nfs4state.c67
-rw-r--r--fs/nfsd/state.h2
-rw-r--r--fs/nilfs2/the_nilfs.c2
-rw-r--r--fs/ocfs2/Makefile2
-rw-r--r--fs/ocfs2/buffer_head_io.c5
-rw-r--r--fs/overlayfs/dir.c13
-rw-r--r--fs/overlayfs/inode.c26
-rw-r--r--fs/posix_acl.c42
-rw-r--r--fs/reiserfs/super.c9
-rw-r--r--fs/ubifs/file.c24
-rw-r--r--fs/udf/partition.c13
-rw-r--r--fs/udf/super.c22
-rw-r--r--fs/udf/udf_sb.h5
45 files changed, 418 insertions, 293 deletions
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index f0d268b97d19..a439548de785 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -70,9 +70,13 @@ struct autofs_info {
};
#define AUTOFS_INF_EXPIRING (1<<0) /* dentry in the process of expiring */
-#define AUTOFS_INF_NO_RCU (1<<1) /* the dentry is being considered
+#define AUTOFS_INF_WANT_EXPIRE (1<<1) /* the dentry is being considered
* for expiry, so RCU_walk is
- * not permitted
+ * not permitted. If it progresses to
+ * actual expiry attempt, the flag is
+ * not cleared when EXPIRING is set -
+ * in that case it gets cleared only
+ * when it comes to clearing EXPIRING.
*/
#define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 9510d8d2e9cd..b493909e7492 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -316,19 +316,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
if (ino->flags & AUTOFS_INF_PENDING)
goto out;
if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
- ino->flags |= AUTOFS_INF_NO_RCU;
+ ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
spin_lock(&sbi->fs_lock);
if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
ino->flags |= AUTOFS_INF_EXPIRING;
- smp_mb();
- ino->flags &= ~AUTOFS_INF_NO_RCU;
init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
return root;
}
- ino->flags &= ~AUTOFS_INF_NO_RCU;
+ ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
}
out:
spin_unlock(&sbi->fs_lock);
@@ -446,7 +444,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
while ((dentry = get_next_positive_subdir(dentry, root))) {
spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(dentry);
- if (ino->flags & AUTOFS_INF_NO_RCU)
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
expired = NULL;
else
expired = should_expire(dentry, mnt, timeout, how);
@@ -455,7 +453,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
continue;
}
ino = autofs4_dentry_ino(expired);
- ino->flags |= AUTOFS_INF_NO_RCU;
+ ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
spin_lock(&sbi->fs_lock);
@@ -465,7 +463,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
goto found;
}
- ino->flags &= ~AUTOFS_INF_NO_RCU;
+ ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
if (expired != dentry)
dput(expired);
spin_unlock(&sbi->fs_lock);
@@ -475,17 +473,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
found:
pr_debug("returning %p %pd\n", expired, expired);
ino->flags |= AUTOFS_INF_EXPIRING;
- smp_mb();
- ino->flags &= ~AUTOFS_INF_NO_RCU;
init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
- spin_lock(&sbi->lookup_lock);
- spin_lock(&expired->d_parent->d_lock);
- spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&expired->d_parent->d_subdirs, &expired->d_child);
- spin_unlock(&expired->d_lock);
- spin_unlock(&expired->d_parent->d_lock);
- spin_unlock(&sbi->lookup_lock);
return expired;
}
@@ -496,7 +485,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
int status;
/* Block on any pending expire */
- if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)))
+ if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
return 0;
if (rcu_walk)
return -ECHILD;
@@ -554,7 +543,7 @@ int autofs4_expire_run(struct super_block *sb,
ino = autofs4_dentry_ino(dentry);
/* avoid rapid-fire expire attempts if expiry fails */
ino->last_used = now;
- ino->flags &= ~AUTOFS_INF_EXPIRING;
+ ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
@@ -583,7 +572,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
spin_lock(&sbi->fs_lock);
/* avoid rapid-fire expire attempts if expiry fails */
ino->last_used = now;
- ino->flags &= ~AUTOFS_INF_EXPIRING;
+ ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
dput(dentry);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 78bd80298528..3767f6641af1 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -458,7 +458,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
*/
struct inode *inode;
- if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
return 0;
if (d_mountpoint(dentry))
return 0;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 0146d911f468..631f1554c87b 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -66,11 +66,12 @@ static int autofs4_write(struct autofs_sb_info *sbi,
set_fs(KERNEL_DS);
mutex_lock(&sbi->pipe_mutex);
- wr = __vfs_write(file, data, bytes, &file->f_pos);
- while (bytes && wr) {
+ while (bytes) {
+ wr = __vfs_write(file, data, bytes, &file->f_pos);
+ if (wr <= 0)
+ break;
data += wr;
bytes -= wr;
- wr = __vfs_write(file, data, bytes, &file->f_pos);
}
mutex_unlock(&sbi->pipe_mutex);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b677a6ea6001..7706c8dc5fa6 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -2645,7 +2645,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
* This algorithm is recursive because the amount of used stack space
* is very small and the max recursion depth is limited.
*/
- indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)",
+ indent_add = sprintf(buf, "%c-%llu(%s/%llu/%u)",
btrfsic_get_block_type(state, block),
block->logical_bytenr, block->dev_state->name,
block->dev_bytenr, block->mirror_num);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 46025688f1d0..a85cf7d23309 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1554,6 +1554,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
trans->transid, root->fs_info->generation);
if (!should_cow_block(trans, root, buf)) {
+ trans->dirty = true;
*cow_ret = buf;
return 0;
}
@@ -1785,10 +1786,12 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
if (!err) {
tmp = (struct btrfs_disk_key *)(kaddr + offset -
map_start);
- } else {
+ } else if (err == 1) {
read_extent_buffer(eb, &unaligned,
offset, sizeof(unaligned));
tmp = &unaligned;
+ } else {
+ return err;
}
} else {
@@ -2512,6 +2515,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
if (!btrfs_buffer_uptodate(tmp, 0, 0))
ret = -EIO;
free_extent_buffer(tmp);
+ } else {
+ ret = PTR_ERR(tmp);
}
return ret;
}
@@ -2775,8 +2780,10 @@ again:
* then we don't want to set the path blocking,
* so we test it here
*/
- if (!should_cow_block(trans, root, b))
+ if (!should_cow_block(trans, root, b)) {
+ trans->dirty = true;
goto cow_done;
+ }
/*
* must have write locks on this node and the
@@ -2825,6 +2832,8 @@ cow_done:
}
ret = key_search(b, key, level, &prev_cmp, &slot);
+ if (ret < 0)
+ goto done;
if (level != 0) {
int dec = 0;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 101c3cfd3f7c..4274a7bfdaed 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2518,7 +2518,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
int btrfs_async_run_delayed_refs(struct btrfs_root *root,
- unsigned long count, int wait);
+ unsigned long count, u64 transid, int wait);
int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 61561c2a3f96..d3aaabbfada0 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1606,15 +1606,23 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode)
return 0;
}
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
- struct list_head *del_list)
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list)
{
struct btrfs_delayed_node *delayed_node;
struct btrfs_delayed_item *item;
delayed_node = btrfs_get_delayed_node(inode);
if (!delayed_node)
- return;
+ return false;
+
+ /*
+ * We can only do one readdir with delayed items at a time because of
+ * item->readdir_list.
+ */
+ inode_unlock_shared(inode);
+ inode_lock(inode);
mutex_lock(&delayed_node->mutex);
item = __btrfs_first_delayed_insertion_item(delayed_node);
@@ -1641,10 +1649,13 @@ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
* requeue or dequeue this delayed node.
*/
atomic_dec(&delayed_node->refs);
+
+ return true;
}
-void btrfs_put_delayed_items(struct list_head *ins_list,
- struct list_head *del_list)
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list)
{
struct btrfs_delayed_item *curr, *next;
@@ -1659,6 +1670,12 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
if (atomic_dec_and_test(&curr->refs))
kfree(curr);
}
+
+ /*
+ * The VFS is going to do up_read(), so we need to downgrade back to a
+ * read lock.
+ */
+ downgrade_write(&inode->i_rwsem);
}
int btrfs_should_delete_dir_index(struct list_head *del_list,
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 0167853c84ae..2495b3d4075f 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -137,10 +137,12 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
void btrfs_destroy_delayed_inodes(struct btrfs_root *root);
/* Used for readdir() */
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
- struct list_head *del_list);
-void btrfs_put_delayed_items(struct list_head *ins_list,
- struct list_head *del_list);
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list);
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+ struct list_head *ins_list,
+ struct list_head *del_list);
int btrfs_should_delete_dir_index(struct list_head *del_list,
u64 index);
int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1142127f6e5e..60ce1190307b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
struct inode *btree_inode = root->fs_info->btree_inode;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
+ if (IS_ERR(buf))
return;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
buf, 0, WAIT_NONE, btree_get_extent, 0);
@@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
int ret;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
+ if (IS_ERR(buf))
return 0;
set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
@@ -1172,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
int ret;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(buf))
+ return buf;
ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
if (ret) {
@@ -1806,6 +1806,13 @@ static int cleaner_kthread(void *arg)
if (btrfs_need_cleaner_sleep(root))
goto sleep;
+ /*
+ * Do not do anything if we might cause open_ctree() to block
+ * before we have finished mounting the filesystem.
+ */
+ if (!root->fs_info->open)
+ goto sleep;
+
if (!mutex_trylock(&root->fs_info->cleaner_mutex))
goto sleep;
@@ -2520,7 +2527,6 @@ int open_ctree(struct super_block *sb,
int num_backups_tried = 0;
int backup_index = 0;
int max_active;
- bool cleaner_mutex_locked = false;
tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2800,7 +2806,7 @@ int open_ctree(struct super_block *sb,
nodesize = btrfs_super_nodesize(disk_super);
sectorsize = btrfs_super_sectorsize(disk_super);
- stripesize = btrfs_super_stripesize(disk_super);
+ stripesize = sectorsize;
fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
@@ -2999,13 +3005,6 @@ retry_root_backup:
goto fail_sysfs;
}
- /*
- * Hold the cleaner_mutex thread here so that we don't block
- * for a long time on btrfs_recover_relocation. cleaner_kthread
- * will wait for us to finish mounting the filesystem.
- */
- mutex_lock(&fs_info->cleaner_mutex);
- cleaner_mutex_locked = true;
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
"btrfs-cleaner");
if (IS_ERR(fs_info->cleaner_kthread))
@@ -3065,8 +3064,10 @@ retry_root_backup:
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto fail_qgroup;
- /* We locked cleaner_mutex before creating cleaner_kthread. */
+
+ mutex_lock(&fs_info->cleaner_mutex);
ret = btrfs_recover_relocation(tree_root);
+ mutex_unlock(&fs_info->cleaner_mutex);
if (ret < 0) {
btrfs_warn(fs_info, "failed to recover relocation: %d",
ret);
@@ -3074,8 +3075,6 @@ retry_root_backup:
goto fail_qgroup;
}
}
- mutex_unlock(&fs_info->cleaner_mutex);
- cleaner_mutex_locked = false;
location.objectid = BTRFS_FS_TREE_OBJECTID;
location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3189,10 +3188,6 @@ fail_cleaner:
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
fail_sysfs:
- if (cleaner_mutex_locked) {
- mutex_unlock(&fs_info->cleaner_mutex);
- cleaner_mutex_locked = false;
- }
btrfs_sysfs_remove_mounted(fs_info);
fail_fsdev_sysfs:
@@ -4138,8 +4133,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
btrfs_super_bytes_used(sb));
ret = -EINVAL;
}
- if (!is_power_of_2(btrfs_super_stripesize(sb)) ||
- btrfs_super_stripesize(sb) != sectorsize) {
+ if (!is_power_of_2(btrfs_super_stripesize(sb))) {
btrfs_err(fs_info, "invalid stripesize %u",
btrfs_super_stripesize(sb));
ret = -EINVAL;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 689d25ac6a68..82b912a293ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2835,6 +2835,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
struct async_delayed_refs {
struct btrfs_root *root;
+ u64 transid;
int count;
int error;
int sync;
@@ -2850,6 +2851,10 @@ static void delayed_ref_async_start(struct btrfs_work *work)
async = container_of(work, struct async_delayed_refs, work);
+ /* if the commit is already started, we don't need to wait here */
+ if (btrfs_transaction_blocked(async->root->fs_info))
+ goto done;
+
trans = btrfs_join_transaction(async->root);
if (IS_ERR(trans)) {
async->error = PTR_ERR(trans);
@@ -2861,10 +2866,15 @@ static void delayed_ref_async_start(struct btrfs_work *work)
* wait on delayed refs
*/
trans->sync = true;
+
+ /* Don't bother flushing if we got into a different transaction */
+ if (trans->transid > async->transid)
+ goto end;
+
ret = btrfs_run_delayed_refs(trans, async->root, async->count);
if (ret)
async->error = ret;
-
+end:
ret = btrfs_end_transaction(trans, async->root);
if (ret && !async->error)
async->error = ret;
@@ -2876,7 +2886,7 @@ done:
}
int btrfs_async_run_delayed_refs(struct btrfs_root *root,
- unsigned long count, int wait)
+ unsigned long count, u64 transid, int wait)
{
struct async_delayed_refs *async;
int ret;
@@ -2888,6 +2898,7 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
async->root = root->fs_info->tree_root;
async->count = count;
async->error = 0;
+ async->transid = transid;
if (wait)
async->sync = 1;
else
@@ -8016,8 +8027,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(buf))
+ return buf;
+
btrfs_set_header_generation(buf, trans->transid);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
@@ -8044,7 +8056,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
buf->start + buf->len - 1, GFP_NOFS);
}
- trans->blocks_used++;
+ trans->dirty = true;
/* this returns a buffer locked for blocking */
return buf;
}
@@ -8659,8 +8671,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
next = btrfs_find_tree_block(root->fs_info, bytenr);
if (!next) {
next = btrfs_find_create_tree_block(root, bytenr);
- if (!next)
- return -ENOMEM;
+ if (IS_ERR(next))
+ return PTR_ERR(next);
+
btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
level - 1);
reada = 1;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a3412d68ad37..75533adef998 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4892,18 +4892,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
int uptodate = 1;
int ret;
+ if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) {
+ btrfs_err(fs_info, "bad tree block start %llu", start);
+ return ERR_PTR(-EINVAL);
+ }
+
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
- return NULL;
+ return ERR_PTR(-ENOMEM);
for (i = 0; i < num_pages; i++, index++) {
p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
- if (!p)
+ if (!p) {
+ exists = ERR_PTR(-ENOMEM);
goto free_eb;
+ }
spin_lock(&mapping->private_lock);
if (PagePrivate(p)) {
@@ -4948,8 +4955,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
again:
ret = radix_tree_preload(GFP_NOFS);
- if (ret)
+ if (ret) {
+ exists = ERR_PTR(ret);
goto free_eb;
+ }
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
@@ -5333,6 +5342,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
return ret;
}
+/*
+ * return 0 if the item is found within a page.
+ * return 1 if the item spans two pages.
+ * return -EINVAL otherwise.
+ */
int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
unsigned long min_len, char **map,
unsigned long *map_start,
@@ -5347,7 +5361,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
PAGE_SHIFT;
if (i != end_i)
- return -EINVAL;
+ return 1;
if (i == 0) {
offset = start_offset;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e0c9bd3fb02d..2234e88cf674 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1534,30 +1534,30 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
reserve_bytes = round_up(write_bytes + sector_offset,
root->sectorsize);
- if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
- BTRFS_INODE_PREALLOC)) &&
- check_can_nocow(inode, pos, &write_bytes) > 0) {
- /*
- * For nodata cow case, no need to reserve
- * data space.
- */
- only_release_metadata = true;
- /*
- * our prealloc extent may be smaller than
- * write_bytes, so scale down.
- */
- num_pages = DIV_ROUND_UP(write_bytes + offset,
- PAGE_SIZE);
- reserve_bytes = round_up(write_bytes + sector_offset,
- root->sectorsize);
- goto reserve_metadata;
- }
-
ret = btrfs_check_data_free_space(inode, pos, write_bytes);
- if (ret < 0)
- break;
+ if (ret < 0) {
+ if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) &&
+ check_can_nocow(inode, pos, &write_bytes) > 0) {
+ /*
+ * For nodata cow case, no need to reserve
+ * data space.
+ */
+ only_release_metadata = true;
+ /*
+ * our prealloc extent may be smaller than
+ * write_bytes, so scale down.
+ */
+ num_pages = DIV_ROUND_UP(write_bytes + offset,
+ PAGE_SIZE);
+ reserve_bytes = round_up(write_bytes +
+ sector_offset,
+ root->sectorsize);
+ } else {
+ break;
+ }
+ }
-reserve_metadata:
ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
if (ret) {
if (!only_release_metadata)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8b1212e8f7a8..4421954720b8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3271,7 +3271,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
/* grab metadata reservation from transaction handle */
if (reserve) {
ret = btrfs_orphan_reserve_metadata(trans, inode);
- BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
+ ASSERT(!ret);
+ if (ret) {
+ atomic_dec(&root->orphan_inodes);
+ clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+ &BTRFS_I(inode)->runtime_flags);
+ if (insert)
+ clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+ &BTRFS_I(inode)->runtime_flags);
+ return ret;
+ }
}
/* insert an orphan item to track this unlinked/truncated file */
@@ -4549,6 +4558,7 @@ delete:
BUG_ON(ret);
if (btrfs_should_throttle_delayed_refs(trans, root))
btrfs_async_run_delayed_refs(root,
+ trans->transid,
trans->delayed_ref_updates * 2, 0);
if (be_nice) {
if (truncate_space_check(trans, root,
@@ -5748,6 +5758,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
int name_len;
int is_curr = 0; /* ctx->pos points to the current index? */
bool emitted;
+ bool put = false;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
@@ -5765,7 +5776,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
if (key_type == BTRFS_DIR_INDEX_KEY) {
INIT_LIST_HEAD(&ins_list);
INIT_LIST_HEAD(&del_list);
- btrfs_get_delayed_items(inode, &ins_list, &del_list);
+ put = btrfs_readdir_get_delayed_items(inode, &ins_list,
+ &del_list);
}
key.type = key_type;
@@ -5912,8 +5924,8 @@ next:
nopos:
ret = 0;
err:
- if (key_type == BTRFS_DIR_INDEX_KEY)
- btrfs_put_delayed_items(&ins_list, &del_list);
+ if (put)
+ btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
btrfs_free_path(path);
return ret;
}
@@ -10525,7 +10537,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = {
static const struct file_operations btrfs_dir_file_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = btrfs_real_readdir,
+ .iterate_shared = btrfs_real_readdir,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_compat_ioctl,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index e96634a725c3..aca8264f4a49 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -968,6 +968,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
struct rb_node *prev = NULL;
struct btrfs_ordered_extent *test;
int ret = 1;
+ u64 orig_offset = offset;
spin_lock_irq(&tree->lock);
if (ordered) {
@@ -983,7 +984,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
/* truncate file */
if (disk_i_size > i_size) {
- BTRFS_I(inode)->disk_i_size = i_size;
+ BTRFS_I(inode)->disk_i_size = orig_offset;
ret = 0;
goto out;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 4339b6613f19..60e7179ed4b7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -235,7 +235,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
trans->aborted = errno;
/* Nothing used. The other threads that have joined this
* transaction may be able to continue. */
- if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
+ if (!trans->dirty && list_empty(&trans->new_bgs)) {
const char *errstr;
errstr = btrfs_decode_error(errno);
@@ -1807,6 +1807,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
}
}
sb->s_flags &= ~MS_RDONLY;
+
+ fs_info->open = 1;
}
out:
wake_up_process(fs_info->transaction_kthread);
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 10eb249ef891..02223f3f78f4 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -68,7 +68,7 @@ int btrfs_init_test_fs(void)
if (IS_ERR(test_mnt)) {
printk(KERN_ERR "btrfs: cannot mount test file system\n");
unregister_filesystem(&test_type);
- return ret;
+ return PTR_ERR(test_mnt);
}
return 0;
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f6e24cb423ae..948aa186b353 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -818,6 +818,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
{
struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *info = root->fs_info;
+ u64 transid = trans->transid;
unsigned long cur = trans->delayed_ref_updates;
int lock = (trans->type != TRANS_JOIN_NOLOCK);
int err = 0;
@@ -905,7 +906,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
kmem_cache_free(btrfs_trans_handle_cachep, trans);
if (must_run_delayed_refs) {
- btrfs_async_run_delayed_refs(root, cur,
+ btrfs_async_run_delayed_refs(root, cur, transid,
must_run_delayed_refs == 1);
}
return err;
@@ -1311,11 +1312,6 @@ int btrfs_defrag_root(struct btrfs_root *root)
return ret;
}
-/* Bisesctability fixup, remove in 4.8 */
-#ifndef btrfs_std_error
-#define btrfs_std_error btrfs_handle_fs_error
-#endif
-
/*
* Do all special snapshot related qgroup dirty hack.
*
@@ -1385,7 +1381,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
switch_commit_roots(trans->transaction, fs_info);
ret = btrfs_write_and_wait_transaction(trans, src);
if (ret)
- btrfs_std_error(fs_info, ret,
+ btrfs_handle_fs_error(fs_info, ret,
"Error while writing out transaction for qgroup");
out:
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 9fe0ec2bf0fe..c5abee4f01ad 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -110,7 +110,6 @@ struct btrfs_trans_handle {
u64 chunk_bytes_reserved;
unsigned long use_count;
unsigned long blocks_reserved;
- unsigned long blocks_used;
unsigned long delayed_ref_updates;
struct btrfs_transaction *transaction;
struct btrfs_block_rsv *block_rsv;
@@ -121,6 +120,7 @@ struct btrfs_trans_handle {
bool can_flush_pending_bgs;
bool reloc_reserved;
bool sync;
+ bool dirty;
unsigned int type;
/*
* this root is only needed to validate that the root passed to
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index b7665af471d8..c05f69a8ec42 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2422,8 +2422,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
root_owner = btrfs_header_owner(parent);
next = btrfs_find_create_tree_block(root, bytenr);
- if (!next)
- return -ENOMEM;
+ if (IS_ERR(next))
+ return PTR_ERR(next);
if (*level == 1) {
ret = wc->process_func(root, next, wc, ptr_gen);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 548faaa9e169..589f128173b1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4694,12 +4694,12 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
if (type & BTRFS_BLOCK_GROUP_RAID5) {
raid_stripe_len = find_raid56_stripe_len(ndevs - 1,
- btrfs_super_stripesize(info->super_copy));
+ extent_root->stripesize);
data_stripes = num_stripes - 1;
}
if (type & BTRFS_BLOCK_GROUP_RAID6) {
raid_stripe_len = find_raid56_stripe_len(ndevs - 2,
- btrfs_super_stripesize(info->super_copy));
+ extent_root->stripesize);
data_stripes = num_stripes - 2;
}
@@ -6607,8 +6607,8 @@ int btrfs_read_sys_array(struct btrfs_root *root)
* overallocate but we can keep it as-is, only the first page is used.
*/
sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
- if (!sb)
- return -ENOMEM;
+ if (IS_ERR(sb))
+ return PTR_ERR(sb);
set_extent_buffer_uptodate(sb);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
/*
diff --git a/fs/dcache.c b/fs/dcache.c
index 817c243c1ff1..d6847d7b123d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -507,6 +507,44 @@ void d_drop(struct dentry *dentry)
}
EXPORT_SYMBOL(d_drop);
+static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
+{
+ struct dentry *next;
+ /*
+ * Inform d_walk() and shrink_dentry_list() that we are no longer
+ * attached to the dentry tree
+ */
+ dentry->d_flags |= DCACHE_DENTRY_KILLED;
+ if (unlikely(list_empty(&dentry->d_child)))
+ return;
+ __list_del_entry(&dentry->d_child);
+ /*
+ * Cursors can move around the list of children. While we'd been
+ * a normal list member, it didn't matter - ->d_child.next would've
+ * been updated. However, from now on it won't be and for the
+ * things like d_walk() it might end up with a nasty surprise.
+ * Normally d_walk() doesn't care about cursors moving around -
+ * ->d_lock on parent prevents that and since a cursor has no children
+ * of its own, we get through it without ever unlocking the parent.
+ * There is one exception, though - if we ascend from a child that
+ * gets killed as soon as we unlock it, the next sibling is found
+ * using the value left in its ->d_child.next. And if _that_
+ * pointed to a cursor, and cursor got moved (e.g. by lseek())
+ * before d_walk() regains parent->d_lock, we'll end up skipping
+ * everything the cursor had been moved past.
+ *
+ * Solution: make sure that the pointer left behind in ->d_child.next
+ * points to something that won't be moving around. I.e. skip the
+ * cursors.
+ */
+ while (dentry->d_child.next != &parent->d_subdirs) {
+ next = list_entry(dentry->d_child.next, struct dentry, d_child);
+ if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
+ break;
+ dentry->d_child.next = next->d_child.next;
+ }
+}
+
static void __dentry_kill(struct dentry *dentry)
{
struct dentry *parent = NULL;
@@ -532,12 +570,7 @@ static void __dentry_kill(struct dentry *dentry)
}
/* if it was on the hash then remove it */
__d_drop(dentry);
- __list_del_entry(&dentry->d_child);
- /*
- * Inform d_walk() that we are no longer attached to the
- * dentry tree
- */
- dentry->d_flags |= DCACHE_DENTRY_KILLED;
+ dentry_unlist(dentry, parent);
if (parent)
spin_unlock(&parent->d_lock);
dentry_iput(dentry);
@@ -1203,6 +1236,9 @@ resume:
struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
+ if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
+ continue;
+
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
ret = enter(data, dentry);
@@ -1651,6 +1687,16 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
}
EXPORT_SYMBOL(d_alloc);
+struct dentry *d_alloc_cursor(struct dentry * parent)
+{
+ struct dentry *dentry = __d_alloc(parent->d_sb, NULL);
+ if (dentry) {
+ dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR;
+ dentry->d_parent = dget(parent);
+ }
+ return dentry;
+}
+
/**
* d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
* @sb: the superblock
@@ -2457,7 +2503,6 @@ retry:
rcu_read_unlock();
goto retry;
}
- rcu_read_unlock();
/*
* No changes for the parent since the beginning of d_lookup().
* Since all removals from the chain happen with hlist_bl_lock(),
@@ -2470,8 +2515,6 @@ retry:
continue;
if (dentry->d_parent != parent)
continue;
- if (d_unhashed(dentry))
- continue;
if (parent->d_flags & DCACHE_OP_COMPARE) {
int tlen = dentry->d_name.len;
const char *tname = dentry->d_name.name;
@@ -2483,9 +2526,18 @@ retry:
if (dentry_cmp(dentry, str, len))
continue;
}
- dget(dentry);
hlist_bl_unlock(b);
- /* somebody is doing lookup for it right now; wait for it */
+ /* now we can try to grab a reference */
+ if (!lockref_get_not_dead(&dentry->d_lockref)) {
+ rcu_read_unlock();
+ goto retry;
+ }
+
+ rcu_read_unlock();
+ /*
+ * somebody is likely to be still doing lookup for it;
+ * wait for them to finish
+ */
spin_lock(&dentry->d_lock);
d_wait_lookup(dentry);
/*
@@ -2516,6 +2568,7 @@ retry:
dput(new);
return dentry;
}
+ rcu_read_unlock();
/* we can't take ->d_lock here; it's OK, though. */
new->d_flags |= DCACHE_PAR_LOOKUP;
new->d_wait = wq;
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 9c1c9a01b7e5..592059f88e04 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -127,7 +127,6 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
r = real_fops->open(inode, filp);
out:
- fops_put(real_fops);
debugfs_use_file_finish(srcu_idx);
return r;
}
@@ -262,8 +261,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
if (real_fops->open) {
r = real_fops->open(inode, filp);
-
- if (filp->f_op != proxy_fops) {
+ if (r) {
+ replace_fops(filp, d_inode(dentry)->i_fop);
+ goto free_proxy;
+ } else if (filp->f_op != proxy_fops) {
/* No protection against file removal anymore. */
WARN(1, "debugfs file owner replaced proxy fops: %pd",
dentry);
diff --git a/fs/internal.h b/fs/internal.h
index b71deeecea17..f57ced528cde 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -130,6 +130,7 @@ extern int invalidate_inodes(struct super_block *, bool);
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern int d_set_mounted(struct dentry *dentry);
extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
+extern struct dentry *d_alloc_cursor(struct dentry *);
/*
* read_write.c
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index b31852f76f46..e3ca4b4cac84 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -2329,18 +2329,10 @@ void *jbd2_alloc(size_t size, gfp_t flags)
BUG_ON(size & (size-1)); /* Must be a power of 2 */
- flags |= __GFP_REPEAT;
- if (size == PAGE_SIZE)
- ptr = (void *)__get_free_pages(flags, 0);
- else if (size > PAGE_SIZE) {
- int order = get_order(size);
-
- if (order < 3)
- ptr = (void *)__get_free_pages(flags, order);
- else
- ptr = vmalloc(size);
- } else
+ if (size < PAGE_SIZE)
ptr = kmem_cache_alloc(get_slab(size), flags);
+ else
+ ptr = (void *)__get_free_pages(flags, get_order(size));
/* Check alignment; SLUB has gotten this wrong in the past,
* and this can lead to user data corruption! */
@@ -2351,20 +2343,10 @@ void *jbd2_alloc(size_t size, gfp_t flags)
void jbd2_free(void *ptr, size_t size)
{
- if (size == PAGE_SIZE) {
- free_pages((unsigned long)ptr, 0);
- return;
- }
- if (size > PAGE_SIZE) {
- int order = get_order(size);
-
- if (order < 3)
- free_pages((unsigned long)ptr, order);
- else
- vfree(ptr);
- return;
- }
- kmem_cache_free(get_slab(size), ptr);
+ if (size < PAGE_SIZE)
+ kmem_cache_free(get_slab(size), ptr);
+ else
+ free_pages((unsigned long)ptr, get_order(size));
};
/*
diff --git a/fs/libfs.c b/fs/libfs.c
index 3db2721144c2..cedeacbae303 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -71,9 +71,7 @@ EXPORT_SYMBOL(simple_lookup);
int dcache_dir_open(struct inode *inode, struct file *file)
{
- static struct qstr cursor_name = QSTR_INIT(".", 1);
-
- file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
+ file->private_data = d_alloc_cursor(file->f_path.dentry);
return file->private_data ? 0 : -ENOMEM;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index a7ec92c051f5..783004af5707 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3247,6 +3247,10 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC)
mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC);
+ /* Don't miss readonly hidden in the superblock flags */
+ if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY)
+ mnt_flags |= MNT_LOCK_READONLY;
+
/* Verify the mount flags are equal to or more permissive
* than the proposed new mount.
*/
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index e55b5242614d..31f3df193bdb 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -290,7 +290,7 @@ out_free_buf:
return error;
}
-#define NFSD_MDS_PR_KEY 0x0100000000000000
+#define NFSD_MDS_PR_KEY 0x0100000000000000ULL
/*
* We use the client ID as a unique key for the reservations.
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 1580ea6fd64d..d08cd88155c7 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -104,22 +104,21 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
goto out;
inode = d_inode(fh->fh_dentry);
- if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
- error = -EOPNOTSUPP;
- goto out_errno;
- }
error = fh_want_write(fh);
if (error)
goto out_errno;
- error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+ fh_lock(fh);
+
+ error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
if (error)
- goto out_drop_write;
- error = inode->i_op->set_acl(inode, argp->acl_default,
- ACL_TYPE_DEFAULT);
+ goto out_drop_lock;
+ error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
if (error)
- goto out_drop_write;
+ goto out_drop_lock;
+
+ fh_unlock(fh);
fh_drop_write(fh);
@@ -131,7 +130,8 @@ out:
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
return nfserr;
-out_drop_write:
+out_drop_lock:
+ fh_unlock(fh);
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 01df4cd7c753..0c890347cde3 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -95,22 +95,20 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
goto out;
inode = d_inode(fh->fh_dentry);
- if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
- error = -EOPNOTSUPP;
- goto out_errno;
- }
error = fh_want_write(fh);
if (error)
goto out_errno;
- error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+ fh_lock(fh);
+
+ error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
if (error)
- goto out_drop_write;
- error = inode->i_op->set_acl(inode, argp->acl_default,
- ACL_TYPE_DEFAULT);
+ goto out_drop_lock;
+ error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
-out_drop_write:
+out_drop_lock:
+ fh_unlock(fh);
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 6adabd6049b7..71292a0d6f09 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -770,9 +770,6 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
dentry = fhp->fh_dentry;
inode = d_inode(dentry);
- if (!inode->i_op->set_acl || !IS_POSIXACL(inode))
- return nfserr_attrnotsupp;
-
if (S_ISDIR(inode->i_mode))
flags = NFS4_ACL_DIR;
@@ -782,16 +779,19 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (host_error < 0)
goto out_nfserr;
- host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS);
+ fh_lock(fhp);
+
+ host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl);
if (host_error < 0)
- goto out_release;
+ goto out_drop_lock;
if (S_ISDIR(inode->i_mode)) {
- host_error = inode->i_op->set_acl(inode, dpacl,
- ACL_TYPE_DEFAULT);
+ host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl);
}
-out_release:
+out_drop_lock:
+ fh_unlock(fhp);
+
posix_acl_release(pacl);
posix_acl_release(dpacl);
out_nfserr:
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7389cb1d7409..04c68d900324 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
}
}
-static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
-{
- struct rpc_xprt *xprt;
-
- if (args->protocol != XPRT_TRANSPORT_BC_TCP)
- return rpc_create(args);
-
- xprt = args->bc_xprt->xpt_bc_xprt;
- if (xprt) {
- xprt_get(xprt);
- return rpc_create_xprt(args, xprt);
- }
-
- return rpc_create(args);
-}
-
static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
{
int maxtime = max_cb_time(clp->net);
@@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
args.authflavor = ses->se_cb_sec.flavor;
}
/* Create RPC client */
- client = create_backchannel_client(&args);
+ client = rpc_create(&args);
if (IS_ERR(client)) {
dprintk("NFSD: couldn't create callback client: %ld\n",
PTR_ERR(client));
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f5f82e145018..70d0b9b33031 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3480,12 +3480,17 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
}
static struct nfs4_ol_stateid *
-init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
- struct nfsd4_open *open)
+init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
{
struct nfs4_openowner *oo = open->op_openowner;
struct nfs4_ol_stateid *retstp = NULL;
+ struct nfs4_ol_stateid *stp;
+
+ stp = open->op_stp;
+ /* We are moving these outside of the spinlocks to avoid the warnings */
+ mutex_init(&stp->st_mutex);
+ mutex_lock(&stp->st_mutex);
spin_lock(&oo->oo_owner.so_client->cl_lock);
spin_lock(&fp->fi_lock);
@@ -3493,6 +3498,8 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
retstp = nfsd4_find_existing_open(fp, open);
if (retstp)
goto out_unlock;
+
+ open->op_stp = NULL;
atomic_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
@@ -3502,14 +3509,19 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
stp->st_access_bmap = 0;
stp->st_deny_bmap = 0;
stp->st_openstp = NULL;
- init_rwsem(&stp->st_rwsem);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
out_unlock:
spin_unlock(&fp->fi_lock);
spin_unlock(&oo->oo_owner.so_client->cl_lock);
- return retstp;
+ if (retstp) {
+ mutex_lock(&retstp->st_mutex);
+ /* To keep mutex tracking happy */
+ mutex_unlock(&stp->st_mutex);
+ stp = retstp;
+ }
+ return stp;
}
/*
@@ -4305,7 +4317,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
struct nfs4_file *fp = NULL;
struct nfs4_ol_stateid *stp = NULL;
- struct nfs4_ol_stateid *swapstp = NULL;
struct nfs4_delegation *dp = NULL;
__be32 status;
@@ -4335,32 +4346,28 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
*/
if (stp) {
/* Stateid was found, this is an OPEN upgrade */
- down_read(&stp->st_rwsem);
+ mutex_lock(&stp->st_mutex);
status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
if (status) {
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
goto out;
}
} else {
- stp = open->op_stp;
- open->op_stp = NULL;
- swapstp = init_open_stateid(stp, fp, open);
- if (swapstp) {
- nfs4_put_stid(&stp->st_stid);
- stp = swapstp;
- down_read(&stp->st_rwsem);
+ /* stp is returned locked. */
+ stp = init_open_stateid(fp, open);
+ /* See if we lost the race to some other thread */
+ if (stp->st_access_bmap != 0) {
status = nfs4_upgrade_open(rqstp, fp, current_fh,
stp, open);
if (status) {
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
goto out;
}
goto upgrade_out;
}
- down_read(&stp->st_rwsem);
status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
if (status) {
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
release_open_stateid(stp);
goto out;
}
@@ -4372,7 +4379,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
}
upgrade_out:
nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
- up_read(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
if (nfsd4_has_session(&resp->cstate)) {
if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4977,12 +4984,12 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
* revoked delegations are kept only for free_stateid.
*/
return nfserr_bad_stateid;
- down_write(&stp->st_rwsem);
+ mutex_lock(&stp->st_mutex);
status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
if (status == nfs_ok)
status = nfs4_check_fh(current_fh, &stp->st_stid);
if (status != nfs_ok)
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
return status;
}
@@ -5030,7 +5037,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
return status;
oo = openowner(stp->st_stateowner);
if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfs4_put_stid(&stp->st_stid);
return nfserr_bad_stateid;
}
@@ -5062,12 +5069,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
oo = openowner(stp->st_stateowner);
status = nfserr_bad_stateid;
if (oo->oo_flags & NFS4_OO_CONFIRMED) {
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
goto put_stateid;
}
oo->oo_flags |= NFS4_OO_CONFIRMED;
nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
@@ -5143,7 +5150,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
status = nfs_ok;
put_stateid:
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfs4_put_stid(&stp->st_stid);
out:
nfsd4_bump_seqid(cstate, status);
@@ -5196,7 +5203,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfsd4_close_open_stateid(stp);
@@ -5422,7 +5429,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
- init_rwsem(&stp->st_rwsem);
+ mutex_init(&stp->st_mutex);
list_add(&stp->st_locks, &open_stp->st_locks);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
spin_lock(&fp->fi_lock);
@@ -5591,7 +5598,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&open_stp, nn);
if (status)
goto out;
- up_write(&open_stp->st_rwsem);
+ mutex_unlock(&open_stp->st_mutex);
open_sop = openowner(open_stp->st_stateowner);
status = nfserr_bad_stateid;
if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5600,7 +5607,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = lookup_or_create_lock_state(cstate, open_stp, lock,
&lock_stp, &new);
if (status == nfs_ok)
- down_write(&lock_stp->st_rwsem);
+ mutex_lock(&lock_stp->st_mutex);
} else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
@@ -5704,7 +5711,7 @@ out:
seqid_mutating_err(ntohl(status)))
lock_sop->lo_owner.so_seqid++;
- up_write(&lock_stp->st_rwsem);
+ mutex_unlock(&lock_stp->st_mutex);
/*
* If this is a new, never-before-used stateid, and we are
@@ -5874,7 +5881,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fput:
fput(filp);
put_stateid:
- up_write(&stp->st_rwsem);
+ mutex_unlock(&stp->st_mutex);
nfs4_put_stid(&stp->st_stid);
out:
nfsd4_bump_seqid(cstate, status);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 986e51e5ceac..64053eadeb81 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -535,7 +535,7 @@ struct nfs4_ol_stateid {
unsigned char st_access_bmap;
unsigned char st_deny_bmap;
struct nfs4_ol_stateid *st_openstp;
- struct rw_semaphore st_rwsem;
+ struct mutex st_mutex;
};
static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 809bd2de7ad0..e9fd241b9a0a 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -439,7 +439,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp)
if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC)
return 0;
bytes = le16_to_cpu(sbp->s_bytes);
- if (bytes > BLOCK_SIZE)
+ if (bytes < sumoff + 4 || bytes > BLOCK_SIZE)
return 0;
crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp,
sumoff);
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index e27e6527912b..4342c7ee7d20 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -1,7 +1,5 @@
ccflags-y := -Ifs/ocfs2
-ccflags-y += -DCATCH_BH_JBD_RACES
-
obj-$(CONFIG_OCFS2_FS) += \
ocfs2.o \
ocfs2_stackglue.o
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index fe50ded1b4ce..498641eed2db 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -139,11 +139,16 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
lock_buffer(bh);
if (buffer_jbd(bh)) {
+#ifdef CATCH_BH_JBD_RACES
mlog(ML_ERROR,
"block %llu had the JBD bit set "
"while I was in lock_buffer!",
(unsigned long long)bh->b_blocknr);
BUG();
+#else
+ unlock_buffer(bh);
+ continue;
+#endif
}
clear_buffer_uptodate(bh);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 22f0253a3567..c2a6b0894022 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -405,12 +405,21 @@ static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev,
err = ovl_create_upper(dentry, inode, &stat, link, hardlink);
} else {
const struct cred *old_cred;
+ struct cred *override_cred;
old_cred = ovl_override_creds(dentry->d_sb);
- err = ovl_create_over_whiteout(dentry, inode, &stat, link,
- hardlink);
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (override_cred) {
+ override_cred->fsuid = old_cred->fsuid;
+ override_cred->fsgid = old_cred->fsgid;
+ put_cred(override_creds(override_cred));
+ put_cred(override_cred);
+ err = ovl_create_over_whiteout(dentry, inode, &stat,
+ link, hardlink);
+ }
revert_creds(old_cred);
}
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 0ed7c4012437..1dbeab6cf96e 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -238,41 +238,27 @@ out:
return err;
}
-static bool ovl_need_xattr_filter(struct dentry *dentry,
- enum ovl_path_type type)
-{
- if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER)
- return S_ISDIR(dentry->d_inode->i_mode);
- else
- return false;
-}
-
ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
const char *name, void *value, size_t size)
{
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+ struct dentry *realdentry = ovl_dentry_real(dentry);
- if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+ if (ovl_is_private_xattr(name))
return -ENODATA;
- return vfs_getxattr(realpath.dentry, name, value, size);
+ return vfs_getxattr(realdentry, name, value, size);
}
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+ struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
int off;
- res = vfs_listxattr(realpath.dentry, list, size);
+ res = vfs_listxattr(realdentry, list, size);
if (res <= 0 || size == 0)
return res;
- if (!ovl_need_xattr_filter(dentry, type))
- return res;
-
/* filter out private xattrs */
for (off = 0; off < res;) {
char *s = list + off;
@@ -302,7 +288,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name)
goto out;
err = -ENODATA;
- if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+ if (ovl_is_private_xattr(name))
goto out_drop_write;
if (!OVL_TYPE_UPPER(type)) {
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 8a4a266beff3..edc452c2a563 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -820,39 +820,43 @@ posix_acl_xattr_get(const struct xattr_handler *handler,
return error;
}
-static int
-posix_acl_xattr_set(const struct xattr_handler *handler,
- struct dentry *unused, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+int
+set_posix_acl(struct inode *inode, int type, struct posix_acl *acl)
{
- struct posix_acl *acl = NULL;
- int ret;
-
if (!IS_POSIXACL(inode))
return -EOPNOTSUPP;
if (!inode->i_op->set_acl)
return -EOPNOTSUPP;
- if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
- return value ? -EACCES : 0;
+ if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+ return acl ? -EACCES : 0;
if (!inode_owner_or_capable(inode))
return -EPERM;
+ if (acl) {
+ int ret = posix_acl_valid(acl);
+ if (ret)
+ return ret;
+ }
+ return inode->i_op->set_acl(inode, acl, type);
+}
+EXPORT_SYMBOL(set_posix_acl);
+
+static int
+posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ struct posix_acl *acl = NULL;
+ int ret;
+
if (value) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
-
- if (acl) {
- ret = posix_acl_valid(acl);
- if (ret)
- goto out;
- }
}
-
- ret = inode->i_op->set_acl(inode, acl, handler->flags);
-out:
+ ret = set_posix_acl(inode, handler->flags, acl);
posix_acl_release(acl);
return ret;
}
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b8f2d1e8c645..c72c16c5a60f 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1393,7 +1393,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
unsigned long safe_mask = 0;
unsigned int commit_max_age = (unsigned int)-1;
struct reiserfs_journal *journal = SB_JOURNAL(s);
- char *new_opts = kstrdup(arg, GFP_KERNEL);
+ char *new_opts;
int err;
char *qf_names[REISERFS_MAXQUOTAS];
unsigned int qfmt = 0;
@@ -1401,6 +1401,10 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
int i;
#endif
+ new_opts = kstrdup(arg, GFP_KERNEL);
+ if (arg && !new_opts)
+ return -ENOMEM;
+
sync_filesystem(s);
reiserfs_write_lock(s);
@@ -1546,7 +1550,8 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
}
out_ok_unlocked:
- replace_mount_options(s, new_opts);
+ if (new_opts)
+ replace_mount_options(s, new_opts);
return 0;
out_err_unlock:
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 08316972ff93..7bbf420d1289 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -52,6 +52,7 @@
#include "ubifs.h"
#include <linux/mount.h>
#include <linux/slab.h>
+#include <linux/migrate.h>
static int read_block(struct inode *inode, void *addr, unsigned int block,
struct ubifs_data_node *dn)
@@ -1452,6 +1453,26 @@ static int ubifs_set_page_dirty(struct page *page)
return ret;
}
+#ifdef CONFIG_MIGRATION
+static int ubifs_migrate_page(struct address_space *mapping,
+ struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+ int rc;
+
+ rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+ if (rc != MIGRATEPAGE_SUCCESS)
+ return rc;
+
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ SetPagePrivate(newpage);
+ }
+
+ migrate_page_copy(newpage, page);
+ return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
{
/*
@@ -1591,6 +1612,9 @@ const struct address_space_operations ubifs_file_address_operations = {
.write_end = ubifs_write_end,
.invalidatepage = ubifs_invalidatepage,
.set_page_dirty = ubifs_set_page_dirty,
+#ifdef CONFIG_MIGRATION
+ .migratepage = ubifs_migrate_page,
+#endif
.releasepage = ubifs_releasepage,
};
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index 5f861ed287c3..888c364b2fe9 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -295,7 +295,8 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block,
map = &UDF_SB(sb)->s_partmaps[partition];
/* map to sparable/physical partition desc */
phyblock = udf_get_pblock(sb, eloc.logicalBlockNum,
- map->s_partition_num, ext_offset + offset);
+ map->s_type_specific.s_metadata.s_phys_partition_ref,
+ ext_offset + offset);
}
brelse(epos.bh);
@@ -317,14 +318,18 @@ uint32_t udf_get_pblock_meta25(struct super_block *sb, uint32_t block,
mdata = &map->s_type_specific.s_metadata;
inode = mdata->s_metadata_fe ? : mdata->s_mirror_fe;
- /* We shouldn't mount such media... */
- BUG_ON(!inode);
+ if (!inode)
+ return 0xFFFFFFFF;
+
retblk = udf_try_read_meta(inode, block, partition, offset);
if (retblk == 0xFFFFFFFF && mdata->s_metadata_fe) {
udf_warn(sb, "error reading from METADATA, trying to read from MIRROR\n");
if (!(mdata->s_flags & MF_MIRROR_FE_LOADED)) {
mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb,
- mdata->s_mirror_file_loc, map->s_partition_num);
+ mdata->s_mirror_file_loc,
+ mdata->s_phys_partition_ref);
+ if (IS_ERR(mdata->s_mirror_fe))
+ mdata->s_mirror_fe = NULL;
mdata->s_flags |= MF_MIRROR_FE_LOADED;
}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5e2c8c814e1b..4942549e7dc8 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -951,13 +951,13 @@ out2:
}
struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
- u32 meta_file_loc, u32 partition_num)
+ u32 meta_file_loc, u32 partition_ref)
{
struct kernel_lb_addr addr;
struct inode *metadata_fe;
addr.logicalBlockNum = meta_file_loc;
- addr.partitionReferenceNum = partition_num;
+ addr.partitionReferenceNum = partition_ref;
metadata_fe = udf_iget_special(sb, &addr);
@@ -974,7 +974,8 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
return metadata_fe;
}
-static int udf_load_metadata_files(struct super_block *sb, int partition)
+static int udf_load_metadata_files(struct super_block *sb, int partition,
+ int type1_index)
{
struct udf_sb_info *sbi = UDF_SB(sb);
struct udf_part_map *map;
@@ -984,20 +985,21 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
map = &sbi->s_partmaps[partition];
mdata = &map->s_type_specific.s_metadata;
+ mdata->s_phys_partition_ref = type1_index;
/* metadata address */
udf_debug("Metadata file location: block = %d part = %d\n",
- mdata->s_meta_file_loc, map->s_partition_num);
+ mdata->s_meta_file_loc, mdata->s_phys_partition_ref);
fe = udf_find_metadata_inode_efe(sb, mdata->s_meta_file_loc,
- map->s_partition_num);
+ mdata->s_phys_partition_ref);
if (IS_ERR(fe)) {
/* mirror file entry */
udf_debug("Mirror metadata file location: block = %d part = %d\n",
- mdata->s_mirror_file_loc, map->s_partition_num);
+ mdata->s_mirror_file_loc, mdata->s_phys_partition_ref);
fe = udf_find_metadata_inode_efe(sb, mdata->s_mirror_file_loc,
- map->s_partition_num);
+ mdata->s_phys_partition_ref);
if (IS_ERR(fe)) {
udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n");
@@ -1015,7 +1017,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
*/
if (mdata->s_bitmap_file_loc != 0xFFFFFFFF) {
addr.logicalBlockNum = mdata->s_bitmap_file_loc;
- addr.partitionReferenceNum = map->s_partition_num;
+ addr.partitionReferenceNum = mdata->s_phys_partition_ref;
udf_debug("Bitmap file location: block = %d part = %d\n",
addr.logicalBlockNum, addr.partitionReferenceNum);
@@ -1283,7 +1285,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
p = (struct partitionDesc *)bh->b_data;
partitionNumber = le16_to_cpu(p->partitionNumber);
- /* First scan for TYPE1, SPARABLE and METADATA partitions */
+ /* First scan for TYPE1 and SPARABLE partitions */
for (i = 0; i < sbi->s_partitions; i++) {
map = &sbi->s_partmaps[i];
udf_debug("Searching map: (%d == %d)\n",
@@ -1333,7 +1335,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
goto out_bh;
if (map->s_partition_type == UDF_METADATA_MAP25) {
- ret = udf_load_metadata_files(sb, i);
+ ret = udf_load_metadata_files(sb, i, type1_idx);
if (ret < 0) {
udf_err(sb, "error loading MetaData partition map %d\n",
i);
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 27b5335730c9..c13875d669c0 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -61,6 +61,11 @@ struct udf_meta_data {
__u32 s_bitmap_file_loc;
__u32 s_alloc_unit_size;
__u16 s_align_unit_size;
+ /*
+ * Partition Reference Number of the associated physical / sparable
+ * partition
+ */
+ __u16 s_phys_partition_ref;
int s_flags;
struct inode *s_metadata_fe;
struct inode *s_mirror_fe;