summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_file.c6
-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/ctree.c6
-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.c6
-rw-r--r--fs/btrfs/extent-tree.c15
-rw-r--r--fs/btrfs/extent_io.c7
-rw-r--r--fs/btrfs/file.c44
-rw-r--r--fs/btrfs/inode.c11
-rw-r--r--fs/btrfs/ordered-data.c3
-rw-r--r--fs/btrfs/tests/btrfs-tests.c2
-rw-r--r--fs/btrfs/transaction.c3
-rw-r--r--fs/btrfs/volumes.c4
-rw-r--r--fs/ceph/export.c10
-rw-r--r--fs/cifs/cifs_unicode.c33
-rw-r--r--fs/cifs/cifs_unicode.h2
-rw-r--r--fs/cifs/cifsfs.c3
-rw-r--r--fs/cifs/cifsglob.h1
-rw-r--r--fs/cifs/connect.c4
-rw-r--r--fs/cifs/file.c14
-rw-r--r--fs/cifs/ntlmssp.h2
-rw-r--r--fs/cifs/sess.c80
-rw-r--r--fs/cifs/smb2pdu.c37
-rw-r--r--fs/dax.c7
-rw-r--r--fs/dcache.c75
-rw-r--r--fs/fuse/dir.c4
-rw-r--r--fs/fuse/fuse_i.h9
-rw-r--r--fs/fuse/inode.c19
-rw-r--r--fs/internal.h1
-rw-r--r--fs/jbd2/journal.c32
-rw-r--r--fs/libfs.c113
-rw-r--r--fs/lockd/svc.c13
-rw-r--r--fs/locks.c2
-rw-r--r--fs/namespace.c5
-rw-r--r--fs/nfs/dir.c11
-rw-r--r--fs/nfs/direct.c10
-rw-r--r--fs/nfs/inode.c1
-rw-r--r--fs/nfs/nfs4proc.c18
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/nfs/pnfs.c10
-rw-r--r--fs/nfs/pnfs_nfs.c12
-rw-r--r--fs/nfs/read.c4
-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/nilfs2/the_nilfs.c2
-rw-r--r--fs/ocfs2/Makefile2
-rw-r--r--fs/ocfs2/buffer_head_io.c5
-rw-r--r--fs/overlayfs/inode.c29
-rw-r--r--fs/overlayfs/super.c12
-rw-r--r--fs/posix_acl.c42
-rw-r--r--fs/ubifs/file.c24
57 files changed, 593 insertions, 299 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index b84c291ba1eb..d7b78d531e63 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -74,7 +74,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
v9fs_proto_dotu(v9ses));
fid = file->private_data;
if (!fid) {
- fid = v9fs_fid_clone(file->f_path.dentry);
+ fid = v9fs_fid_clone(file_dentry(file));
if (IS_ERR(fid))
return PTR_ERR(fid);
@@ -100,7 +100,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
* because we want write after unlink usecase
* to work.
*/
- fid = v9fs_writeback_fid(file->f_path.dentry);
+ fid = v9fs_writeback_fid(file_dentry(file));
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
mutex_unlock(&v9inode->v_mutex);
@@ -516,7 +516,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
* because we want write after unlink usecase
* to work.
*/
- fid = v9fs_writeback_fid(filp->f_path.dentry);
+ fid = v9fs_writeback_fid(file_dentry(filp));
if (IS_ERR(fid)) {
retval = PTR_ERR(fid);
mutex_unlock(&v9inode->v_mutex);
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/ctree.c b/fs/btrfs/ctree.c
index 6276add8538a..a85cf7d23309 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1786,10 +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 {
@@ -2830,6 +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 54cca7a1572b..60ce1190307b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2806,7 +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));
@@ -4133,9 +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) &&
- (btrfs_super_stripesize(sb) != 4096))) {
+ 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 29e5d000bbee..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
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index aaee3ef55ed8..75533adef998 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5342,6 +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,
@@ -5356,7 +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 d2be95cfb6d1..4421954720b8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4558,6 +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,
@@ -5757,6 +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)
@@ -5774,7 +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;
@@ -5921,8 +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;
}
@@ -10534,7 +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/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 765845742fde..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;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2f631b58ae00..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;
}
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 6e72c98162d5..1780218a48f0 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -95,10 +95,8 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
}
dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- iput(inode);
+ if (IS_ERR(dentry))
return dentry;
- }
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
@@ -167,10 +165,8 @@ static struct dentry *__get_parent(struct super_block *sb,
return ERR_PTR(-ENOENT);
dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- iput(inode);
+ if (IS_ERR(dentry))
return dentry;
- }
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
@@ -210,7 +206,7 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
dout("fh_to_parent %llx\n", cfh->parent_ino);
dentry = __get_parent(sb, NULL, cfh->ino);
- if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT)
+ if (unlikely(dentry == ERR_PTR(-ENOENT)))
dentry = __fh_to_dentry(sb, cfh->parent_ino);
return dentry;
}
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 5a53ac6b1e02..02b071bf3732 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -101,6 +101,12 @@ convert_sfm_char(const __u16 src_char, char *target)
case SFM_SLASH:
*target = '\\';
break;
+ case SFM_SPACE:
+ *target = ' ';
+ break;
+ case SFM_PERIOD:
+ *target = '.';
+ break;
default:
return false;
}
@@ -404,7 +410,7 @@ static __le16 convert_to_sfu_char(char src_char)
return dest_char;
}
-static __le16 convert_to_sfm_char(char src_char)
+static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
{
__le16 dest_char;
@@ -427,6 +433,18 @@ static __le16 convert_to_sfm_char(char src_char)
case '|':
dest_char = cpu_to_le16(SFM_PIPE);
break;
+ case '.':
+ if (end_of_string)
+ dest_char = cpu_to_le16(SFM_PERIOD);
+ else
+ dest_char = 0;
+ break;
+ case ' ':
+ if (end_of_string)
+ dest_char = cpu_to_le16(SFM_SPACE);
+ else
+ dest_char = 0;
+ break;
default:
dest_char = 0;
}
@@ -469,9 +487,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
/* see if we must remap this char */
if (map_chars == SFU_MAP_UNI_RSVD)
dst_char = convert_to_sfu_char(src_char);
- else if (map_chars == SFM_MAP_UNI_RSVD)
- dst_char = convert_to_sfm_char(src_char);
- else
+ else if (map_chars == SFM_MAP_UNI_RSVD) {
+ bool end_of_string;
+
+ if (i == srclen - 1)
+ end_of_string = true;
+ else
+ end_of_string = false;
+
+ dst_char = convert_to_sfm_char(src_char, end_of_string);
+ } else
dst_char = 0;
/*
* FIXME: We can not handle remapping backslash (UNI_SLASH)
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index bdc52cb9a676..479bc0a941f3 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -64,6 +64,8 @@
#define SFM_LESSTHAN ((__u16) 0xF023)
#define SFM_PIPE ((__u16) 0xF027)
#define SFM_SLASH ((__u16) 0xF026)
+#define SFM_PERIOD ((__u16) 0xF028)
+#define SFM_SPACE ((__u16) 0xF029)
/*
* Mapping mechanism to use when one of the seven reserved characters is
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5d8b7edf8a8f..5d841f39c4b7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -87,6 +87,7 @@ extern mempool_t *cifs_req_poolp;
extern mempool_t *cifs_mid_poolp;
struct workqueue_struct *cifsiod_wq;
+__u32 cifs_lock_secret;
/*
* Bumps refcount for cifs super block.
@@ -1266,6 +1267,8 @@ init_cifs(void)
spin_lock_init(&cifs_file_list_lock);
spin_lock_init(&GlobalMid_Lock);
+ get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret));
+
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index bba106cdc43c..8f1d8c1e72be 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1619,6 +1619,7 @@ void cifs_oplock_break(struct work_struct *work);
extern const struct slow_work_ops cifs_oplock_break_ops;
extern struct workqueue_struct *cifsiod_wq;
+extern __u32 cifs_lock_secret;
extern mempool_t *cifs_mid_poolp;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 66736f57b5ab..7d2b15c06090 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -428,7 +428,9 @@ cifs_echo_request(struct work_struct *work)
* server->ops->need_neg() == true. Also, no need to ping if
* we got a response recently.
*/
- if (!server->ops->need_neg || server->ops->need_neg(server) ||
+
+ if (server->tcpStatus == CifsNeedReconnect ||
+ server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
(server->ops->can_echo && !server->ops->can_echo(server)) ||
time_before(jiffies, server->lstrp + echo_interval - HZ))
goto requeue_echo;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9793ae0bcaa2..d4890b6dc22d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1112,6 +1112,12 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
return rc;
}
+static __u32
+hash_lockowner(fl_owner_t owner)
+{
+ return cifs_lock_secret ^ hash32_ptr((const void *)owner);
+}
+
struct lock_to_push {
struct list_head llist;
__u64 offset;
@@ -1178,7 +1184,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
else
type = CIFS_WRLCK;
lck = list_entry(el, struct lock_to_push, llist);
- lck->pid = flock->fl_pid;
+ lck->pid = hash_lockowner(flock->fl_owner);
lck->netfid = cfile->fid.netfid;
lck->length = length;
lck->type = type;
@@ -1305,7 +1311,8 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
posix_lock_type = CIFS_RDLCK;
else
posix_lock_type = CIFS_WRLCK;
- rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid,
+ rc = CIFSSMBPosixLock(xid, tcon, netfid,
+ hash_lockowner(flock->fl_owner),
flock->fl_start, length, flock,
posix_lock_type, wait_flag);
return rc;
@@ -1505,7 +1512,8 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
posix_lock_type = CIFS_UNLCK;
rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid,
- current->tgid, flock->fl_start, length,
+ hash_lockowner(flock->fl_owner),
+ flock->fl_start, length,
NULL, posix_lock_type, wait_flag);
goto out;
}
diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h
index 848249fa120f..3079b38f0afb 100644
--- a/fs/cifs/ntlmssp.h
+++ b/fs/cifs/ntlmssp.h
@@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE {
int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses);
void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses);
-int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen,
+int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
struct cifs_ses *ses,
const struct nls_table *nls_cp);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index af0ec2d5ad0e..538d9b55699a 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
sec_blob->DomainName.MaximumLength = 0;
}
-/* We do not malloc the blob, it is passed in pbuffer, because its
- maximum possible size is fixed and small, making this approach cleaner.
- This function returns the length of the data in the blob */
-int build_ntlmssp_auth_blob(unsigned char *pbuffer,
+static int size_of_ntlmssp_blob(struct cifs_ses *ses)
+{
+ int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len
+ - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
+
+ if (ses->domainName)
+ sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ else
+ sz += 2;
+
+ if (ses->user_name)
+ sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+ else
+ sz += 2;
+
+ return sz;
+}
+
+int build_ntlmssp_auth_blob(unsigned char **pbuffer,
u16 *buflen,
struct cifs_ses *ses,
const struct nls_table *nls_cp)
{
int rc;
- AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer;
+ AUTHENTICATE_MESSAGE *sec_blob;
__u32 flags;
unsigned char *tmp;
+ rc = setup_ntlmv2_rsp(ses, nls_cp);
+ if (rc) {
+ cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
+ *buflen = 0;
+ goto setup_ntlmv2_ret;
+ }
+ *pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL);
+ sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer;
+
memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
sec_blob->MessageType = NtLmAuthenticate;
@@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
}
- tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
+ tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
sec_blob->NegotiateFlags = cpu_to_le32(flags);
sec_blob->LmChallengeResponse.BufferOffset =
@@ -399,13 +423,9 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
sec_blob->LmChallengeResponse.Length = 0;
sec_blob->LmChallengeResponse.MaximumLength = 0;
- sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->NtChallengeResponse.BufferOffset =
+ cpu_to_le32(tmp - *pbuffer);
if (ses->user_name != NULL) {
- rc = setup_ntlmv2_rsp(ses, nls_cp);
- if (rc) {
- cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
- goto setup_ntlmv2_ret;
- }
memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
ses->auth_key.len - CIFS_SESS_KEY_SIZE);
tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
@@ -423,23 +443,23 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
}
if (ses->domainName == NULL) {
- sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->DomainName.Length = 0;
sec_blob->DomainName.MaximumLength = 0;
tmp += 2;
} else {
int len;
len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
- CIFS_MAX_USERNAME_LEN, nls_cp);
+ CIFS_MAX_DOMAINNAME_LEN, nls_cp);
len *= 2; /* unicode is 2 bytes each */
- sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->DomainName.Length = cpu_to_le16(len);
sec_blob->DomainName.MaximumLength = cpu_to_le16(len);
tmp += len;
}
if (ses->user_name == NULL) {
- sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->UserName.Length = 0;
sec_blob->UserName.MaximumLength = 0;
tmp += 2;
@@ -448,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
CIFS_MAX_USERNAME_LEN, nls_cp);
len *= 2; /* unicode is 2 bytes each */
- sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->UserName.Length = cpu_to_le16(len);
sec_blob->UserName.MaximumLength = cpu_to_le16(len);
tmp += len;
}
- sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->WorkstationName.Length = 0;
sec_blob->WorkstationName.MaximumLength = 0;
tmp += 2;
@@ -463,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
(ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
&& !calc_seckey(ses)) {
memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
- sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
sec_blob->SessionKey.MaximumLength =
cpu_to_le16(CIFS_CPHTXT_SIZE);
tmp += CIFS_CPHTXT_SIZE;
} else {
- sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+ sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->SessionKey.Length = 0;
sec_blob->SessionKey.MaximumLength = 0;
}
+ *buflen = tmp - *pbuffer;
setup_ntlmv2_ret:
- *buflen = tmp - pbuffer;
return rc;
}
@@ -690,6 +710,8 @@ sess_auth_lanman(struct sess_data *sess_data)
rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
true : false, lnm_session_key);
+ if (rc)
+ goto out;
memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
bcc_ptr += CIFS_AUTH_RESP_SIZE;
@@ -1266,7 +1288,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
struct cifs_ses *ses = sess_data->ses;
__u16 bytes_remaining;
char *bcc_ptr;
- char *ntlmsspblob = NULL;
+ unsigned char *ntlmsspblob = NULL;
u16 blob_len;
cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n");
@@ -1279,19 +1301,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
/* Build security blob before we assemble the request */
pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
smb_buf = (struct smb_hdr *)pSMB;
- /*
- * 5 is an empirical value, large enough to hold
- * authenticate message plus max 10 of av paris,
- * domain, user, workstation names, flags, etc.
- */
- ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE),
- GFP_KERNEL);
- if (!ntlmsspblob) {
- rc = -ENOMEM;
- goto out;
- }
-
- rc = build_ntlmssp_auth_blob(ntlmsspblob,
+ rc = build_ntlmssp_auth_blob(&ntlmsspblob,
&blob_len, ses, sess_data->nls_cp);
if (rc)
goto out_free_ntlmsspblob;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 8f38e33d365b..29e06db5f187 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -588,7 +588,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
u16 blob_length = 0;
struct key *spnego_key = NULL;
char *security_blob = NULL;
- char *ntlmssp_blob = NULL;
+ unsigned char *ntlmssp_blob = NULL;
bool use_spnego = false; /* else use raw ntlmssp */
cifs_dbg(FYI, "Session Setup\n");
@@ -713,13 +713,7 @@ ssetup_ntlmssp_authenticate:
iov[1].iov_len = blob_length;
} else if (phase == NtLmAuthenticate) {
req->hdr.SessionId = ses->Suid;
- ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
- GFP_KERNEL);
- if (ntlmssp_blob == NULL) {
- rc = -ENOMEM;
- goto ssetup_exit;
- }
- rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses,
+ rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
nls_cp);
if (rc) {
cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n",
@@ -1818,6 +1812,33 @@ SMB2_echo(struct TCP_Server_Info *server)
cifs_dbg(FYI, "In echo request\n");
+ if (server->tcpStatus == CifsNeedNegotiate) {
+ struct list_head *tmp, *tmp2;
+ struct cifs_ses *ses;
+ struct cifs_tcon *tcon;
+
+ cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+ spin_lock(&cifs_tcp_ses_lock);
+ list_for_each(tmp, &server->smb_ses_list) {
+ ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+ list_for_each(tmp2, &ses->tcon_list) {
+ tcon = list_entry(tmp2, struct cifs_tcon,
+ tcon_list);
+ /* add check for persistent handle reconnect */
+ if (tcon && tcon->need_reconnect) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ rc = smb2_reconnect(SMB2_ECHO, tcon);
+ spin_lock(&cifs_tcp_ses_lock);
+ }
+ }
+ }
+ spin_unlock(&cifs_tcp_ses_lock);
+ }
+
+ /* if no session, renegotiate failed above */
+ if (server->tcpStatus == CifsNeedNegotiate)
+ return -EIO;
+
rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
if (rc)
return rc;
diff --git a/fs/dax.c b/fs/dax.c
index 761495bf5eb9..e207f8f9b700 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -208,7 +208,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
dax.addr += first;
size = map_len - first;
}
- max = min(pos + size, end);
+ /*
+ * pos + size is one past the last offset for IO,
+ * so pos + size can overflow loff_t at extreme offsets.
+ * Cast to u64 to catch this and get the true minimum.
+ */
+ max = min_t(u64, pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
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/fuse/dir.c b/fs/fuse/dir.c
index ccd4971cc6c1..264f07c7754e 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -341,8 +341,10 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
struct dentry *newent;
bool outarg_valid = true;
+ fuse_lock_inode(dir);
err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
&outarg, &inode);
+ fuse_unlock_inode(dir);
if (err == -ENOENT) {
outarg_valid = false;
err = 0;
@@ -1341,7 +1343,9 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx)
fuse_read_fill(req, file, ctx->pos, PAGE_SIZE,
FUSE_READDIR);
}
+ fuse_lock_inode(inode);
fuse_request_send(fc, req);
+ fuse_unlock_inode(inode);
nbytes = req->out.args[0].size;
err = req->out.h.error;
fuse_put_request(fc, req);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index eddbe02c4028..929c383432b0 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -110,6 +110,9 @@ struct fuse_inode {
/** Miscellaneous bits describing inode state */
unsigned long state;
+
+ /** Lock for serializing lookup and readdir for back compatibility*/
+ struct mutex mutex;
};
/** FUSE inode state bits */
@@ -540,6 +543,9 @@ struct fuse_conn {
/** write-back cache policy (default is write-through) */
unsigned writeback_cache:1;
+ /** allow parallel lookups and readdir (default is serialized) */
+ unsigned parallel_dirops:1;
+
/*
* The following bitfields are only for optimization purposes
* and hence races in setting them will not cause malfunction
@@ -956,4 +962,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
void fuse_set_initialized(struct fuse_conn *fc);
+void fuse_unlock_inode(struct inode *inode);
+void fuse_lock_inode(struct inode *inode);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1ce67668a8e1..9961d8432ce3 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -97,6 +97,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&fi->queued_writes);
INIT_LIST_HEAD(&fi->writepages);
init_waitqueue_head(&fi->page_waitq);
+ mutex_init(&fi->mutex);
fi->forget = fuse_alloc_forget();
if (!fi->forget) {
kmem_cache_free(fuse_inode_cachep, inode);
@@ -117,6 +118,7 @@ static void fuse_destroy_inode(struct inode *inode)
struct fuse_inode *fi = get_fuse_inode(inode);
BUG_ON(!list_empty(&fi->write_files));
BUG_ON(!list_empty(&fi->queued_writes));
+ mutex_destroy(&fi->mutex);
kfree(fi->forget);
call_rcu(&inode->i_rcu, fuse_i_callback);
}
@@ -351,6 +353,18 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
return 0;
}
+void fuse_lock_inode(struct inode *inode)
+{
+ if (!get_fuse_conn(inode)->parallel_dirops)
+ mutex_lock(&get_fuse_inode(inode)->mutex);
+}
+
+void fuse_unlock_inode(struct inode *inode)
+{
+ if (!get_fuse_conn(inode)->parallel_dirops)
+ mutex_unlock(&get_fuse_inode(inode)->mutex);
+}
+
static void fuse_umount_begin(struct super_block *sb)
{
fuse_abort_conn(get_fuse_conn_super(sb));
@@ -898,6 +912,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->async_dio = 1;
if (arg->flags & FUSE_WRITEBACK_CACHE)
fc->writeback_cache = 1;
+ if (arg->flags & FUSE_PARALLEL_DIROPS)
+ fc->parallel_dirops = 1;
if (arg->time_gran && arg->time_gran <= 1000000000)
fc->sb->s_time_gran = arg->time_gran;
} else {
@@ -928,7 +944,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
- FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
+ FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
+ FUSE_PARALLEL_DIROPS;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
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..74dc8b9e7f53 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;
}
@@ -86,6 +84,61 @@ int dcache_dir_close(struct inode *inode, struct file *file)
}
EXPORT_SYMBOL(dcache_dir_close);
+/* parent is locked at least shared */
+static struct dentry *next_positive(struct dentry *parent,
+ struct list_head *from,
+ int count)
+{
+ unsigned *seq = &parent->d_inode->i_dir_seq, n;
+ struct dentry *res;
+ struct list_head *p;
+ bool skipped;
+ int i;
+
+retry:
+ i = count;
+ skipped = false;
+ n = smp_load_acquire(seq) & ~1;
+ res = NULL;
+ rcu_read_lock();
+ for (p = from->next; p != &parent->d_subdirs; p = p->next) {
+ struct dentry *d = list_entry(p, struct dentry, d_child);
+ if (!simple_positive(d)) {
+ skipped = true;
+ } else if (!--i) {
+ res = d;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ if (skipped) {
+ smp_rmb();
+ if (unlikely(*seq != n))
+ goto retry;
+ }
+ return res;
+}
+
+static void move_cursor(struct dentry *cursor, struct list_head *after)
+{
+ struct dentry *parent = cursor->d_parent;
+ unsigned n, *seq = &parent->d_inode->i_dir_seq;
+ spin_lock(&parent->d_lock);
+ for (;;) {
+ n = *seq;
+ if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
+ break;
+ cpu_relax();
+ }
+ __list_del(cursor->d_child.prev, cursor->d_child.next);
+ if (after)
+ list_add(&cursor->d_child, after);
+ else
+ list_add_tail(&cursor->d_child, &parent->d_subdirs);
+ smp_store_release(seq, n + 2);
+ spin_unlock(&parent->d_lock);
+}
+
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry *dentry = file->f_path.dentry;
@@ -101,25 +154,14 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
if (offset != file->f_pos) {
file->f_pos = offset;
if (file->f_pos >= 2) {
- struct list_head *p;
struct dentry *cursor = file->private_data;
+ struct dentry *to;
loff_t n = file->f_pos - 2;
- spin_lock(&dentry->d_lock);
- /* d_lock not required for cursor */
- list_del(&cursor->d_child);
- p = dentry->d_subdirs.next;
- while (n && p != &dentry->d_subdirs) {
- struct dentry *next;
- next = list_entry(p, struct dentry, d_child);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- if (simple_positive(next))
- n--;
- spin_unlock(&next->d_lock);
- p = p->next;
- }
- list_add_tail(&cursor->d_child, p);
- spin_unlock(&dentry->d_lock);
+ inode_lock_shared(dentry->d_inode);
+ to = next_positive(dentry, &dentry->d_subdirs, n);
+ move_cursor(cursor, to ? &to->d_child : NULL);
+ inode_unlock_shared(dentry->d_inode);
}
}
return offset;
@@ -142,36 +184,25 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dentry = file->f_path.dentry;
struct dentry *cursor = file->private_data;
- struct list_head *p, *q = &cursor->d_child;
+ struct list_head *p = &cursor->d_child;
+ struct dentry *next;
+ bool moved = false;
if (!dir_emit_dots(file, ctx))
return 0;
- spin_lock(&dentry->d_lock);
- if (ctx->pos == 2)
- list_move(q, &dentry->d_subdirs);
- for (p = q->next; p != &dentry->d_subdirs; p = p->next) {
- struct dentry *next = list_entry(p, struct dentry, d_child);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- if (!simple_positive(next)) {
- spin_unlock(&next->d_lock);
- continue;
- }
-
- spin_unlock(&next->d_lock);
- spin_unlock(&dentry->d_lock);
+ if (ctx->pos == 2)
+ p = &dentry->d_subdirs;
+ while ((next = next_positive(dentry, p, 1)) != NULL) {
if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
d_inode(next)->i_ino, dt_type(d_inode(next))))
- return 0;
- spin_lock(&dentry->d_lock);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- /* next is still alive */
- list_move(q, p);
- spin_unlock(&next->d_lock);
- p = q;
+ break;
+ moved = true;
+ p = &next->d_child;
ctx->pos++;
}
- spin_unlock(&dentry->d_lock);
+ if (moved)
+ move_cursor(cursor, p);
return 0;
}
EXPORT_SYMBOL(dcache_readdir);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 154a107cd376..fc4084ef4736 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -335,12 +335,17 @@ static struct notifier_block lockd_inet6addr_notifier = {
};
#endif
-static void lockd_svc_exit_thread(void)
+static void lockd_unregister_notifiers(void)
{
unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
#if IS_ENABLED(CONFIG_IPV6)
unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
#endif
+}
+
+static void lockd_svc_exit_thread(void)
+{
+ lockd_unregister_notifiers();
svc_exit_thread(nlmsvc_rqst);
}
@@ -462,7 +467,7 @@ int lockd_up(struct net *net)
* Note: svc_serv structures have an initial use count of 1,
* so we exit through here on both success and failure.
*/
-err_net:
+err_put:
svc_destroy(serv);
err_create:
mutex_unlock(&nlmsvc_mutex);
@@ -470,7 +475,9 @@ err_create:
err_start:
lockd_down_net(serv, net);
- goto err_net;
+err_net:
+ lockd_unregister_notifiers();
+ goto err_put;
}
EXPORT_SYMBOL_GPL(lockd_up);
diff --git a/fs/locks.c b/fs/locks.c
index 7c5f91be9b65..ee1b15f6fc13 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1628,7 +1628,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
{
struct file_lock *fl, *my_fl = NULL, *lease;
struct dentry *dentry = filp->f_path.dentry;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct file_lock_context *ctx;
bool is_deleg = (*flp)->fl_flags & FL_DELEG;
int error;
diff --git a/fs/namespace.c b/fs/namespace.c
index a7ec92c051f5..419f746d851d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1562,6 +1562,7 @@ void __detach_mounts(struct dentry *dentry)
goto out_unlock;
lock_mount_hash();
+ event++;
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
@@ -3247,6 +3248,10 @@ 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/nfs/dir.c b/fs/nfs/dir.c
index aaf7bd0cbae2..d8015a03db4c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -424,12 +424,17 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
static
int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
{
+ struct inode *inode;
struct nfs_inode *nfsi;
if (d_really_is_negative(dentry))
return 0;
- nfsi = NFS_I(d_inode(dentry));
+ inode = d_inode(dentry);
+ if (is_bad_inode(inode) || NFS_STALE(inode))
+ return 0;
+
+ nfsi = NFS_I(inode);
if (entry->fattr->fileid == nfsi->fileid)
return 1;
if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
@@ -1363,7 +1368,6 @@ EXPORT_SYMBOL_GPL(nfs_dentry_operations);
struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *res;
- struct dentry *parent;
struct inode *inode = NULL;
struct nfs_fh *fhandle = NULL;
struct nfs_fattr *fattr = NULL;
@@ -1393,7 +1397,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
if (IS_ERR(label))
goto out;
- parent = dentry->d_parent;
/* Protect against concurrent sillydeletes */
trace_nfs_lookup_enter(dir, dentry, flags);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
@@ -1536,9 +1539,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
err = PTR_ERR(inode);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
put_nfs_open_context(ctx);
+ d_drop(dentry);
switch (err) {
case -ENOENT:
- d_drop(dentry);
d_add(dentry, NULL);
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
break;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 979b3c4dee6a..c7326c2af2c3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -353,10 +353,12 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq)
result = wait_for_completion_killable(&dreq->completion);
+ if (!result) {
+ result = dreq->count;
+ WARN_ON_ONCE(dreq->count < 0);
+ }
if (!result)
result = dreq->error;
- if (!result)
- result = dreq->count;
out:
return (ssize_t) result;
@@ -386,8 +388,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
if (dreq->iocb) {
long res = (long) dreq->error;
- if (!res)
+ if (dreq->count != 0) {
res = (long) dreq->count;
+ WARN_ON_ONCE(dreq->count < 0);
+ }
dreq->iocb->ki_complete(dreq->iocb, res, 0);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 52e7d6869e3b..dda689d7a8a7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -282,6 +282,7 @@ nfs_init_locked(struct inode *inode, void *opaque)
struct nfs_fattr *fattr = desc->fattr;
set_nfs_fileid(inode, fattr->fileid);
+ inode->i_mode = fattr->mode;
nfs_copy_fh(NFS_FH(inode), desc->fh);
return 0;
}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index de97567795a5..ff416d0e24bc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2882,12 +2882,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
call_close |= is_wronly;
else if (is_wronly)
calldata->arg.fmode |= FMODE_WRITE;
+ if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE))
+ call_close |= is_rdwr;
} else if (is_rdwr)
calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
- if (calldata->arg.fmode == 0)
- call_close |= is_rdwr;
-
if (!nfs4_valid_open_stateid(state))
call_close = 0;
spin_unlock(&state->owner->so_lock);
@@ -7924,8 +7923,8 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
break;
}
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match(&lgp->args.stateid,
- &lo->plh_stateid)) {
+ if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) &&
+ nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
LIST_HEAD(head);
/*
@@ -7936,10 +7935,10 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
+ status = -EAGAIN;
+ goto out;
} else
spin_unlock(&inode->i_lock);
- status = -EAGAIN;
- goto out;
}
status = nfs4_handle_exception(server, status, exception);
@@ -8036,7 +8035,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
.flags = RPC_TASK_ASYNC,
};
struct pnfs_layout_segment *lseg = NULL;
- struct nfs4_exception exception = { .timeout = *timeout };
+ struct nfs4_exception exception = {
+ .inode = inode,
+ .timeout = *timeout,
+ };
int status = 0;
dprintk("--> %s\n", __func__);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9679f4749364..834b875900d6 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1488,9 +1488,9 @@ restart:
}
spin_unlock(&state->state_lock);
}
- nfs4_put_open_state(state);
clear_bit(NFS_STATE_RECLAIM_NOGRACE,
&state->flags);
+ nfs4_put_open_state(state);
spin_lock(&sp->so_lock);
goto restart;
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0c7e0d45a4de..0fbe734cc38c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -361,8 +361,10 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
list_del_init(&lseg->pls_list);
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
- if (list_empty(&lo->plh_segs))
+ if (list_empty(&lo->plh_segs)) {
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+ }
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
}
@@ -1290,6 +1292,7 @@ alloc_init_layout_hdr(struct inode *ino,
INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
lo->plh_lc_cred = get_rpccred(ctx->cred);
+ lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID;
return lo;
}
@@ -1297,6 +1300,8 @@ static struct pnfs_layout_hdr *
pnfs_find_alloc_layout(struct inode *ino,
struct nfs_open_context *ctx,
gfp_t gfp_flags)
+ __releases(&ino->i_lock)
+ __acquires(&ino->i_lock)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct pnfs_layout_hdr *new = NULL;
@@ -1565,8 +1570,7 @@ lookup_again:
* stateid, or it has been invalidated, then we must use the open
* stateid.
*/
- if (lo->plh_stateid.seqid == 0 ||
- test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+ if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
/*
* The first layoutget for the file. Need to serialize per
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 0dfc476da3e1..b38e3c0dc790 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -247,7 +247,11 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
}
/* Helper function for pnfs_generic_commit_pagelist to catch an empty
- * page list. This can happen when two commits race. */
+ * page list. This can happen when two commits race.
+ *
+ * This must be called instead of nfs_init_commit - call one or the other, but
+ * not both!
+ */
static bool
pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
struct nfs_commit_data *data,
@@ -256,7 +260,11 @@ pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
if (list_empty(pages)) {
if (atomic_dec_and_test(&cinfo->mds->rpcs_out))
wake_up_atomic_t(&cinfo->mds->rpcs_out);
- nfs_commitdata_release(data);
+ /* don't call nfs_commitdata_release - it tries to put
+ * the open_context which is not acquired until nfs_init_commit
+ * which has not been called on @data */
+ WARN_ON_ONCE(data->context);
+ nfs_commit_free(data);
return true;
}
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 6776d7a7839e..572e5b3b06f1 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -367,13 +367,13 @@ readpage_async_filler(void *data, struct page *page)
nfs_list_remove_request(new);
nfs_readpage_release(new);
error = desc->pgio->pg_error;
- goto out_unlock;
+ goto out;
}
return 0;
out_error:
error = PTR_ERR(new);
-out_unlock:
unlock_page(page);
+out:
return error;
}
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/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/inode.c b/fs/overlayfs/inode.c
index 1dbeab6cf96e..c831c2e5f803 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -59,16 +59,37 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
if (err)
goto out;
+ if (attr->ia_valid & ATTR_SIZE) {
+ struct inode *realinode = d_inode(ovl_dentry_real(dentry));
+
+ err = -ETXTBSY;
+ if (atomic_read(&realinode->i_writecount) < 0)
+ goto out_drop_write;
+ }
+
err = ovl_copy_up(dentry);
if (!err) {
+ struct inode *winode = NULL;
+
upperdentry = ovl_dentry_upper(dentry);
+ if (attr->ia_valid & ATTR_SIZE) {
+ winode = d_inode(upperdentry);
+ err = get_write_access(winode);
+ if (err)
+ goto out_drop_write;
+ }
+
inode_lock(upperdentry->d_inode);
err = notify_change(upperdentry, attr, NULL);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
+
+ if (winode)
+ put_write_access(winode);
}
+out_drop_write:
ovl_drop_write(dentry);
out:
return err;
@@ -121,16 +142,18 @@ int ovl_permission(struct inode *inode, int mask)
err = vfs_getattr(&realpath, &stat);
if (err)
- return err;
+ goto out_dput;
+ err = -ESTALE;
if ((stat.mode ^ inode->i_mode) & S_IFMT)
- return -ESTALE;
+ goto out_dput;
inode->i_mode = stat.mode;
inode->i_uid = stat.uid;
inode->i_gid = stat.gid;
- return generic_permission(inode, mask);
+ err = generic_permission(inode, mask);
+ goto out_dput;
}
/* Careful in RCU walk mode */
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index ce02f46029da..9a7693d5f8ff 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1082,11 +1082,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (err < 0)
goto out_put_workdir;
- if (!err) {
- pr_err("overlayfs: upper fs needs to support d_type.\n");
- err = -EINVAL;
- goto out_put_workdir;
- }
+ /*
+ * We allowed this configuration and don't want to
+ * break users over kernel upgrade. So warn instead
+ * of erroring out.
+ */
+ if (!err)
+ pr_warn("overlayfs: upper fs needs to support d_type.\n");
}
}
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/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,
};