summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/acl.c8
-rw-r--r--fs/9p/vfs_addr.c3
-rw-r--r--fs/9p/vfs_dir.c4
-rw-r--r--fs/9p/vfs_inode.c2
-rw-r--r--fs/9p/xattr.c4
-rw-r--r--fs/Kconfig.binfmt8
-rw-r--r--fs/affs/dir.c2
-rw-r--r--fs/affs/file.c5
-rw-r--r--fs/afs/dir.c16
-rw-r--r--fs/afs/rxrpc.c30
-rw-r--r--fs/aio.c9
-rw-r--r--fs/autofs4/root.c4
-rw-r--r--fs/bad_inode.c4
-rw-r--r--fs/befs/befs.h4
-rw-r--r--fs/befs/btree.c16
-rw-r--r--fs/befs/btree.h4
-rw-r--r--fs/befs/datastream.c34
-rw-r--r--fs/befs/datastream.h11
-rw-r--r--fs/befs/io.c4
-rw-r--r--fs/befs/linuxvfs.c14
-rw-r--r--fs/bfs/dir.c2
-rw-r--r--fs/binfmt_aout.c11
-rw-r--r--fs/binfmt_elf.c9
-rw-r--r--fs/binfmt_elf_fdpic.c2
-rw-r--r--fs/block_dev.c110
-rw-r--r--fs/btrfs/acl.c3
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/btrfs_inode.h10
-rw-r--r--fs/btrfs/compression.c85
-rw-r--r--fs/btrfs/ctree.c6
-rw-r--r--fs/btrfs/ctree.h1123
-rw-r--r--fs/btrfs/delayed-inode.c2
-rw-r--r--fs/btrfs/dev-replace.c101
-rw-r--r--fs/btrfs/dev-replace.h4
-rw-r--r--fs/btrfs/disk-io.c130
-rw-r--r--fs/btrfs/extent-tree.c167
-rw-r--r--fs/btrfs/extent_io.c82
-rw-r--r--fs/btrfs/extent_io.h1
-rw-r--r--fs/btrfs/file.c22
-rw-r--r--fs/btrfs/inode-item.c2
-rw-r--r--fs/btrfs/inode.c488
-rw-r--r--fs/btrfs/ioctl.c216
-rw-r--r--fs/btrfs/ordered-data.c26
-rw-r--r--fs/btrfs/ordered-data.h6
-rw-r--r--fs/btrfs/relocation.c13
-rw-r--r--fs/btrfs/root-tree.c4
-rw-r--r--fs/btrfs/scrub.c25
-rw-r--r--fs/btrfs/send.c62
-rw-r--r--fs/btrfs/super.c60
-rw-r--r--fs/btrfs/sysfs.c14
-rw-r--r--fs/btrfs/transaction.c138
-rw-r--r--fs/btrfs/tree-log.c80
-rw-r--r--fs/btrfs/volumes.c456
-rw-r--r--fs/btrfs/volumes.h57
-rw-r--r--fs/btrfs/xattr.c28
-rw-r--r--fs/btrfs/xattr.h3
-rw-r--r--fs/buffer.c10
-rw-r--r--fs/ceph/acl.c16
-rw-r--r--fs/ceph/addr.c3
-rw-r--r--fs/ceph/dir.c7
-rw-r--r--fs/ceph/file.c11
-rw-r--r--fs/ceph/inode.c29
-rw-r--r--fs/ceph/mds_client.c6
-rw-r--r--fs/ceph/super.h8
-rw-r--r--fs/ceph/xattr.c192
-rw-r--r--fs/char_dev.c4
-rw-r--r--fs/cifs/Makefile3
-rw-r--r--fs/cifs/cifs_dfs_ref.c8
-rw-r--r--fs/cifs/cifs_spnego.c67
-rw-r--r--fs/cifs/cifsacl.c2
-rw-r--r--fs/cifs/cifsencrypt.c97
-rw-r--r--fs/cifs/cifsfs.c39
-rw-r--r--fs/cifs/cifsfs.h14
-rw-r--r--fs/cifs/cifsglob.h2
-rw-r--r--fs/cifs/cifsproto.h14
-rw-r--r--fs/cifs/cifssmb.c15
-rw-r--r--fs/cifs/connect.c139
-rw-r--r--fs/cifs/file.c66
-rw-r--r--fs/cifs/inode.c3
-rw-r--r--fs/cifs/readdir.c61
-rw-r--r--fs/cifs/sess.c139
-rw-r--r--fs/cifs/smb2glob.h1
-rw-r--r--fs/cifs/smb2inode.c8
-rw-r--r--fs/cifs/smb2pdu.c16
-rw-r--r--fs/cifs/smb2proto.h2
-rw-r--r--fs/cifs/smb2transport.c107
-rw-r--r--fs/cifs/transport.c141
-rw-r--r--fs/cifs/xattr.c386
-rw-r--r--fs/coda/dir.c18
-rw-r--r--fs/compat.c12
-rw-r--r--fs/configfs/dir.c37
-rw-r--r--fs/configfs/inode.c2
-rw-r--r--fs/coredump.c9
-rw-r--r--fs/cramfs/inode.c2
-rw-r--r--fs/crypto/keyinfo.c120
-rw-r--r--fs/dax.c13
-rw-r--r--fs/dcache.c280
-rw-r--r--fs/debugfs/file.c436
-rw-r--r--fs/debugfs/inode.c108
-rw-r--r--fs/debugfs/internal.h26
-rw-r--r--fs/devpts/inode.c100
-rw-r--r--fs/direct-io.c34
-rw-r--r--fs/ecryptfs/crypto.c37
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h7
-rw-r--r--fs/ecryptfs/file.c73
-rw-r--r--fs/ecryptfs/inode.c115
-rw-r--r--fs/ecryptfs/mmap.c3
-rw-r--r--fs/ecryptfs/super.c5
-rw-r--r--fs/efivarfs/file.c2
-rw-r--r--fs/efivarfs/inode.c40
-rw-r--r--fs/efivarfs/super.c3
-rw-r--r--fs/efs/dir.c3
-rw-r--r--fs/efs/namei.c2
-rw-r--r--fs/efs/super.c4
-rw-r--r--fs/eventpoll.c12
-rw-r--r--fs/exec.c53
-rw-r--r--fs/exofs/dir.c16
-rw-r--r--fs/exofs/inode.c3
-rw-r--r--fs/exofs/super.c4
-rw-r--r--fs/exportfs/expfs.c12
-rw-r--r--fs/ext2/acl.c3
-rw-r--r--fs/ext2/dir.c16
-rw-r--r--fs/ext2/inode.c8
-rw-r--r--fs/ext2/namei.c2
-rw-r--r--fs/ext2/xattr_security.c6
-rw-r--r--fs/ext2/xattr_trusted.c6
-rw-r--r--fs/ext2/xattr_user.c8
-rw-r--r--fs/ext4/acl.c3
-rw-r--r--fs/ext4/dir.c4
-rw-r--r--fs/ext4/file.c9
-rw-r--r--fs/ext4/inode.c23
-rw-r--r--fs/ext4/ioctl.c2
-rw-r--r--fs/ext4/namei.c4
-rw-r--r--fs/ext4/xattr_security.c6
-rw-r--r--fs/ext4/xattr_trusted.c6
-rw-r--r--fs/ext4/xattr_user.c8
-rw-r--r--fs/f2fs/Kconfig8
-rw-r--r--fs/f2fs/acl.c7
-rw-r--r--fs/f2fs/checkpoint.c67
-rw-r--r--fs/f2fs/data.c203
-rw-r--r--fs/f2fs/debug.c25
-rw-r--r--fs/f2fs/dir.c130
-rw-r--r--fs/f2fs/extent_cache.c3
-rw-r--r--fs/f2fs/f2fs.h197
-rw-r--r--fs/f2fs/file.c320
-rw-r--r--fs/f2fs/gc.c27
-rw-r--r--fs/f2fs/inline.c111
-rw-r--r--fs/f2fs/inode.c66
-rw-r--r--fs/f2fs/namei.c2
-rw-r--r--fs/f2fs/node.c316
-rw-r--r--fs/f2fs/recovery.c149
-rw-r--r--fs/f2fs/segment.c8
-rw-r--r--fs/f2fs/segment.h9
-rw-r--r--fs/f2fs/super.c288
-rw-r--r--fs/f2fs/xattr.c17
-rw-r--r--fs/fat/dir.c6
-rw-r--r--fs/fat/inode.c6
-rw-r--r--fs/file.c5
-rw-r--r--fs/freevxfs/vxfs_lookup.c2
-rw-r--r--fs/fs-writeback.c3
-rw-r--r--fs/fuse/dir.c99
-rw-r--r--fs/fuse/file.c7
-rw-r--r--fs/gfs2/acl.c58
-rw-r--r--fs/gfs2/acl.h1
-rw-r--r--fs/gfs2/aops.c11
-rw-r--r--fs/gfs2/file.c40
-rw-r--r--fs/gfs2/glock.c15
-rw-r--r--fs/gfs2/glops.c7
-rw-r--r--fs/gfs2/inode.c89
-rw-r--r--fs/gfs2/meta_io.c7
-rw-r--r--fs/gfs2/meta_io.h8
-rw-r--r--fs/gfs2/ops_fstype.c4
-rw-r--r--fs/gfs2/rgrp.c16
-rw-r--r--fs/gfs2/super.c2
-rw-r--r--fs/gfs2/util.c1
-rw-r--r--fs/gfs2/xattr.c48
-rw-r--r--fs/hfs/attr.c5
-rw-r--r--fs/hfs/catalog.c3
-rw-r--r--fs/hfs/dir.c12
-rw-r--r--fs/hfs/hfs_fs.h5
-rw-r--r--fs/hfs/inode.c9
-rw-r--r--fs/hfsplus/catalog.c3
-rw-r--r--fs/hfsplus/dir.c12
-rw-r--r--fs/hfsplus/hfsplus_fs.h1
-rw-r--r--fs/hfsplus/inode.c8
-rw-r--r--fs/hfsplus/posix_acl.c3
-rw-r--r--fs/hfsplus/super.c1
-rw-r--r--fs/hfsplus/xattr.c10
-rw-r--r--fs/hfsplus/xattr.h2
-rw-r--r--fs/hfsplus/xattr_security.c6
-rw-r--r--fs/hfsplus/xattr_trusted.c6
-rw-r--r--fs/hfsplus/xattr_user.c6
-rw-r--r--fs/hostfs/hostfs_kern.c2
-rw-r--r--fs/hpfs/dir.c12
-rw-r--r--fs/hpfs/dnode.c8
-rw-r--r--fs/hpfs/hpfs_fn.h2
-rw-r--r--fs/inode.c17
-rw-r--r--fs/isofs/dir.c4
-rw-r--r--fs/isofs/rock.c13
-rw-r--r--fs/jbd2/recovery.c2
-rw-r--r--fs/jbd2/transaction.c6
-rw-r--r--fs/jffs2/acl.c2
-rw-r--r--fs/jffs2/dir.c4
-rw-r--r--fs/jffs2/security.c6
-rw-r--r--fs/jffs2/super.c2
-rw-r--r--fs/jffs2/xattr_trusted.c6
-rw-r--r--fs/jffs2/xattr_user.c6
-rw-r--r--fs/jfs/acl.c6
-rw-r--r--fs/jfs/file.c6
-rw-r--r--fs/jfs/inode.c11
-rw-r--r--fs/jfs/jfs_discard.c6
-rw-r--r--fs/jfs/jfs_dtree.c10
-rw-r--r--fs/jfs/jfs_imap.c3
-rw-r--r--fs/jfs/jfs_inode.c2
-rw-r--r--fs/jfs/jfs_logmgr.c14
-rw-r--r--fs/jfs/jfs_txnmgr.c21
-rw-r--r--fs/jfs/jfs_xattr.h6
-rw-r--r--fs/jfs/namei.c12
-rw-r--r--fs/jfs/super.c4
-rw-r--r--fs/jfs/symlink.c12
-rw-r--r--fs/jfs/xattr.c224
-rw-r--r--fs/kernfs/dir.c31
-rw-r--r--fs/kernfs/file.c51
-rw-r--r--fs/kernfs/inode.c21
-rw-r--r--fs/kernfs/kernfs-internal.h4
-rw-r--r--fs/kernfs/mount.c20
-rw-r--r--fs/libfs.c11
-rw-r--r--fs/logfs/dir.c4
-rw-r--r--fs/minix/dir.c2
-rw-r--r--fs/namei.c475
-rw-r--r--fs/nfs/dir.c80
-rw-r--r--fs/nfs/direct.c23
-rw-r--r--fs/nfs/file.c2
-rw-r--r--fs/nfs/inode.c4
-rw-r--r--fs/nfs/nfs3acl.c43
-rw-r--r--fs/nfs/nfs4idmap.c2
-rw-r--r--fs/nfs/nfs4proc.c14
-rw-r--r--fs/nfs/nfstrace.h2
-rw-r--r--fs/nfs/unlink.c192
-rw-r--r--fs/nfsd/nfs3proc.c4
-rw-r--r--fs/nfsd/nfs3xdr.c2
-rw-r--r--fs/nfsd/nfsfh.c2
-rw-r--r--fs/nfsd/vfs.c18
-rw-r--r--fs/nilfs2/alloc.c39
-rw-r--r--fs/nilfs2/alloc.h11
-rw-r--r--fs/nilfs2/bmap.c10
-rw-r--r--fs/nilfs2/bmap.h22
-rw-r--r--fs/nilfs2/btnode.c9
-rw-r--r--fs/nilfs2/btnode.h8
-rw-r--r--fs/nilfs2/btree.c21
-rw-r--r--fs/nilfs2/btree.h6
-rw-r--r--fs/nilfs2/cpfile.c22
-rw-r--r--fs/nilfs2/cpfile.h10
-rw-r--r--fs/nilfs2/dat.c8
-rw-r--r--fs/nilfs2/dat.h8
-rw-r--r--fs/nilfs2/dir.c75
-rw-r--r--fs/nilfs2/direct.c17
-rw-r--r--fs/nilfs2/direct.h6
-rw-r--r--fs/nilfs2/export.h2
-rw-r--r--fs/nilfs2/file.c7
-rw-r--r--fs/nilfs2/gcinode.c9
-rw-r--r--fs/nilfs2/ifile.c14
-rw-r--r--fs/nilfs2/ifile.h9
-rw-r--r--fs/nilfs2/inode.c109
-rw-r--r--fs/nilfs2/ioctl.c17
-rw-r--r--fs/nilfs2/mdt.c63
-rw-r--r--fs/nilfs2/mdt.h21
-rw-r--r--fs/nilfs2/namei.c14
-rw-r--r--fs/nilfs2/nilfs.h33
-rw-r--r--fs/nilfs2/page.c15
-rw-r--r--fs/nilfs2/page.h10
-rw-r--r--fs/nilfs2/recovery.c25
-rw-r--r--fs/nilfs2/segbuf.c10
-rw-r--r--fs/nilfs2/segbuf.h11
-rw-r--r--fs/nilfs2/segment.c125
-rw-r--r--fs/nilfs2/segment.h44
-rw-r--r--fs/nilfs2/sufile.c14
-rw-r--r--fs/nilfs2/sufile.h10
-rw-r--r--fs/nilfs2/super.c21
-rw-r--r--fs/nilfs2/sysfs.c10
-rw-r--r--fs/nilfs2/sysfs.h6
-rw-r--r--fs/nilfs2/the_nilfs.c16
-rw-r--r--fs/nilfs2/the_nilfs.h27
-rw-r--r--fs/notify/fsnotify.h7
-rw-r--r--fs/notify/group.c17
-rw-r--r--fs/notify/mark.c78
-rw-r--r--fs/ntfs/file.c7
-rw-r--r--fs/ocfs2/acl.c87
-rw-r--r--fs/ocfs2/acl.h5
-rw-r--r--fs/ocfs2/alloc.c3
-rw-r--r--fs/ocfs2/aops.c13
-rw-r--r--fs/ocfs2/cluster/heartbeat.c5
-rw-r--r--fs/ocfs2/cluster/tcp.c17
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c2
-rw-r--r--fs/ocfs2/dlmglue.c3
-rw-r--r--fs/ocfs2/file.c6
-rw-r--r--fs/ocfs2/inode.c2
-rw-r--r--fs/ocfs2/namei.c23
-rw-r--r--fs/ocfs2/ocfs2_fs.h2
-rw-r--r--fs/ocfs2/refcounttree.c17
-rw-r--r--fs/ocfs2/slot_map.c6
-rw-r--r--fs/ocfs2/xattr.c34
-rw-r--r--fs/ocfs2/xattr.h4
-rw-r--r--fs/omfs/dir.c2
-rw-r--r--fs/open.c20
-rw-r--r--fs/openpromfs/inode.c2
-rw-r--r--fs/orangefs/file.c4
-rw-r--r--fs/orangefs/orangefs-kernel.h4
-rw-r--r--fs/orangefs/xattr.c10
-rw-r--r--fs/overlayfs/inode.c4
-rw-r--r--fs/overlayfs/overlayfs.h4
-rw-r--r--fs/overlayfs/readdir.c4
-rw-r--r--fs/overlayfs/super.c6
-rw-r--r--fs/pnode.c25
-rw-r--r--fs/posix_acl.c116
-rw-r--r--fs/proc/array.c20
-rw-r--r--fs/proc/base.c82
-rw-r--r--fs/proc/fd.c8
-rw-r--r--fs/proc/generic.c2
-rw-r--r--fs/proc/namespaces.c3
-rw-r--r--fs/proc/page.c2
-rw-r--r--fs/proc/proc_net.c2
-rw-r--r--fs/proc/proc_sysctl.c17
-rw-r--r--fs/proc/root.c4
-rw-r--r--fs/proc/task_mmu.c44
-rw-r--r--fs/proc/vmcore.c2
-rw-r--r--fs/qnx4/dir.c2
-rw-r--r--fs/qnx6/dir.c2
-rw-r--r--fs/quota/netlink.c12
-rw-r--r--fs/ramfs/file-nommu.c8
-rw-r--r--fs/read_write.c51
-rw-r--r--fs/readdir.c37
-rw-r--r--fs/reiserfs/dir.c2
-rw-r--r--fs/reiserfs/file.c6
-rw-r--r--fs/reiserfs/inode.c7
-rw-r--r--fs/reiserfs/ioctl.c6
-rw-r--r--fs/reiserfs/namei.c18
-rw-r--r--fs/reiserfs/objectid.c2
-rw-r--r--fs/reiserfs/xattr.c54
-rw-r--r--fs/reiserfs/xattr.h9
-rw-r--r--fs/reiserfs/xattr_acl.c8
-rw-r--r--fs/reiserfs/xattr_security.c19
-rw-r--r--fs/reiserfs/xattr_trusted.c19
-rw-r--r--fs/reiserfs/xattr_user.c19
-rw-r--r--fs/romfs/super.c4
-rw-r--r--fs/select.c67
-rw-r--r--fs/splice.c3
-rw-r--r--fs/squashfs/dir.c4
-rw-r--r--fs/squashfs/xattr.c6
-rw-r--r--fs/super.c2
-rw-r--r--fs/sysv/dir.c2
-rw-r--r--fs/ubifs/dir.c8
-rw-r--r--fs/ubifs/file.c12
-rw-r--r--fs/ubifs/sb.c2
-rw-r--r--fs/ubifs/super.c1
-rw-r--r--fs/ubifs/ubifs.h7
-rw-r--r--fs/ubifs/xattr.c145
-rw-r--r--fs/udf/dir.c2
-rw-r--r--fs/udf/file.c7
-rw-r--r--fs/udf/inode.c7
-rw-r--r--fs/udf/namei.c2
-rw-r--r--fs/udf/super.c71
-rw-r--r--fs/udf/udf_sb.h4
-rw-r--r--fs/udf/udfdecl.h2
-rw-r--r--fs/udf/unicode.c16
-rw-r--r--fs/ufs/dir.c16
-rw-r--r--fs/ufs/super.c2
-rw-r--r--fs/userfaultfd.c41
-rw-r--r--fs/xattr.c12
-rw-r--r--fs/xfs/xfs_acl.c20
-rw-r--r--fs/xfs/xfs_aops.c7
-rw-r--r--fs/xfs/xfs_dir2_readdir.c23
-rw-r--r--fs/xfs/xfs_file.c25
-rw-r--r--fs/xfs/xfs_xattr.c6
374 files changed, 7173 insertions, 6246 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 9da967f38387..eb3589edf485 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -93,7 +93,7 @@ static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type)
* instantiating the inode (v9fs_inode_from_fid)
*/
acl = get_cached_acl(inode, type);
- BUG_ON(acl == ACL_NOT_CACHED);
+ BUG_ON(is_uncached_acl(acl));
return acl;
}
@@ -213,8 +213,8 @@ int v9fs_acl_mode(struct inode *dir, umode_t *modep,
}
static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
struct v9fs_session_info *v9ses;
struct posix_acl *acl;
@@ -227,7 +227,7 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
return v9fs_xattr_get(dentry, handler->name, buffer, size);
- acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags);
+ acl = v9fs_get_cached_acl(inode, handler->flags);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index ac9225e86bf3..c37fb9c08970 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -245,9 +245,10 @@ static int v9fs_launder_page(struct page *page)
*
*/
static ssize_t
-v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
+ loff_t pos = iocb->ki_pos;
ssize_t n;
int err = 0;
if (iov_iter_rw(iter) == WRITE) {
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 5cc00e56206e..b0405d6aac85 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -246,7 +246,7 @@ int v9fs_dir_release(struct inode *inode, struct file *filp)
const struct file_operations v9fs_dir_operations = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
- .iterate = v9fs_dir_readdir,
+ .iterate_shared = v9fs_dir_readdir,
.open = v9fs_file_open,
.release = v9fs_dir_release,
};
@@ -254,7 +254,7 @@ const struct file_operations v9fs_dir_operations = {
const struct file_operations v9fs_dir_operations_dotl = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
- .iterate = v9fs_dir_readdir_dotl,
+ .iterate_shared = v9fs_dir_readdir_dotl,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.fsync = v9fs_file_fsync_dotl,
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 3a08b3e6ff1d..f4645c515262 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1071,7 +1071,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
if (IS_ERR(st))
return PTR_ERR(st);
- v9fs_stat2inode(st, d_inode(dentry), d_inode(dentry)->i_sb);
+ v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb);
generic_fillattr(d_inode(dentry), stat);
p9stat_free(st);
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 9dd9b47a6c1a..18c62bae9591 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -138,8 +138,8 @@ ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
}
static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
const char *full_name = xattr_full_name(handler, name);
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 2d0cbbd14cfc..72c03354c14b 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -1,6 +1,7 @@
config BINFMT_ELF
bool "Kernel support for ELF binaries"
depends on MMU && (BROKEN || !FRV)
+ select ELFCORE
default y
---help---
ELF (Executable and Linkable Format) is a format for libraries and
@@ -26,6 +27,7 @@ config BINFMT_ELF
config COMPAT_BINFMT_ELF
bool
depends on COMPAT && BINFMT_ELF
+ select ELFCORE
config ARCH_BINFMT_ELF_STATE
bool
@@ -34,6 +36,7 @@ config BINFMT_ELF_FDPIC
bool "Kernel support for FDPIC ELF binaries"
default y
depends on (FRV || BLACKFIN || (SUPERH32 && !MMU) || C6X)
+ select ELFCORE
help
ELF FDPIC binaries are based on ELF, but allow the individual load
segments of a binary to be located in memory independently of each
@@ -43,6 +46,11 @@ config BINFMT_ELF_FDPIC
It is also possible to run FDPIC ELF binaries on MMU linux also.
+config ELFCORE
+ bool
+ help
+ This option enables kernel/elfcore.o.
+
config CORE_DUMP_DEFAULT_ELF_HEADERS
bool "Write ELF core dumps with partial segments"
default y
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index ac4f318aafba..f1e7294381c5 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -20,7 +20,7 @@ static int affs_readdir(struct file *, struct dir_context *);
const struct file_operations affs_dir_operations = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
- .iterate = affs_readdir,
+ .iterate_shared = affs_readdir,
.fsync = affs_file_fsync,
};
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 0cde550050e8..0deec9cc2362 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -389,12 +389,13 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
}
static ssize_t
-affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
ssize_t ret;
if (iov_iter_rw(iter) == WRITE) {
@@ -404,7 +405,7 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
return 0;
}
- ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, affs_get_block);
if (ret < 0 && iov_iter_rw(iter) == WRITE)
affs_write_failed(mapping, offset + count);
return ret;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5fda2bc53cd7..eba541004d90 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -43,7 +43,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
const struct file_operations afs_dir_file_operations = {
.open = afs_dir_open,
.release = afs_release,
- .iterate = afs_readdir,
+ .iterate_shared = afs_readdir,
.lock = afs_lock,
.llseek = generic_file_llseek,
};
@@ -128,7 +128,7 @@ struct afs_lookup_cookie {
/*
* check that a directory page is valid
*/
-static inline void afs_dir_check_page(struct inode *dir, struct page *page)
+static inline bool afs_dir_check_page(struct inode *dir, struct page *page)
{
struct afs_dir_page *dbuf;
loff_t latter;
@@ -168,11 +168,11 @@ static inline void afs_dir_check_page(struct inode *dir, struct page *page)
}
SetPageChecked(page);
- return;
+ return true;
error:
- SetPageChecked(page);
SetPageError(page);
+ return false;
}
/*
@@ -196,10 +196,10 @@ static struct page *afs_dir_get_page(struct inode *dir, unsigned long index,
page = read_cache_page(dir->i_mapping, index, afs_page_filler, key);
if (!IS_ERR(page)) {
kmap(page);
- if (!PageChecked(page))
- afs_dir_check_page(dir, page);
- if (PageError(page))
- goto fail;
+ if (unlikely(!PageChecked(page))) {
+ if (PageError(page) || !afs_dir_check_page(dir, page))
+ goto fail;
+ }
}
return page;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index b50642870a43..63cd9f939f19 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -65,6 +65,12 @@ static void afs_async_workfn(struct work_struct *work)
call->async_workfn(call);
}
+static int afs_wait_atomic_t(atomic_t *p)
+{
+ schedule();
+ return 0;
+}
+
/*
* open an RxRPC socket and bind it to be a server for callback notifications
* - the socket is left in blocking mode and non-blocking ops use MSG_DONTWAIT
@@ -126,13 +132,16 @@ void afs_close_socket(void)
{
_enter("");
+ wait_on_atomic_t(&afs_outstanding_calls, afs_wait_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+ _debug("no outstanding calls");
+
sock_release(afs_socket);
_debug("dework");
destroy_workqueue(afs_async_calls);
ASSERTCMP(atomic_read(&afs_outstanding_skbs), ==, 0);
- ASSERTCMP(atomic_read(&afs_outstanding_calls), ==, 0);
_leave("");
}
@@ -178,8 +187,6 @@ static void afs_free_call(struct afs_call *call)
{
_debug("DONE %p{%s} [%d]",
call, call->type->name, atomic_read(&afs_outstanding_calls));
- if (atomic_dec_return(&afs_outstanding_calls) == -1)
- BUG();
ASSERTCMP(call->rxcall, ==, NULL);
ASSERT(!work_pending(&call->async_work));
@@ -188,6 +195,9 @@ static void afs_free_call(struct afs_call *call)
kfree(call->request);
kfree(call);
+
+ if (atomic_dec_and_test(&afs_outstanding_calls))
+ wake_up_atomic_t(&afs_outstanding_calls);
}
/*
@@ -420,9 +430,11 @@ error_kill_call:
}
/*
- * handles intercepted messages that were arriving in the socket's Rx queue
- * - called with the socket receive queue lock held to ensure message ordering
- * - called with softirqs disabled
+ * Handles intercepted messages that were arriving in the socket's Rx queue.
+ *
+ * Called from the AF_RXRPC call processor in waitqueue process context. For
+ * each call, it is guaranteed this will be called in order of packet to be
+ * delivered.
*/
static void afs_rx_interceptor(struct sock *sk, unsigned long user_call_ID,
struct sk_buff *skb)
@@ -513,6 +525,12 @@ static void afs_deliver_to_call(struct afs_call *call)
call->state = AFS_CALL_ABORTED;
_debug("Rcv ABORT %u -> %d", abort_code, call->error);
break;
+ case RXRPC_SKB_MARK_LOCAL_ABORT:
+ abort_code = rxrpc_kernel_get_abort_code(skb);
+ call->error = call->type->abort_to_error(abort_code);
+ call->state = AFS_CALL_ABORTED;
+ _debug("Loc ABORT %u -> %d", abort_code, call->error);
+ break;
case RXRPC_SKB_MARK_NET_ERROR:
call->error = -rxrpc_kernel_get_error_number(skb);
call->state = AFS_CALL_ERROR;
diff --git a/fs/aio.c b/fs/aio.c
index 155f84253f33..fb8e45b88cd4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -496,7 +496,12 @@ static int aio_setup_ring(struct kioctx *ctx)
ctx->mmap_size = nr_pages * PAGE_SIZE;
pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size);
- down_write(&mm->mmap_sem);
+ if (down_write_killable(&mm->mmap_sem)) {
+ ctx->mmap_size = 0;
+ aio_free_ring(ctx);
+ return -EINTR;
+ }
+
ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
PROT_READ | PROT_WRITE,
MAP_SHARED, 0, &unused);
@@ -1447,8 +1452,6 @@ rw_common:
return ret;
}
- len = ret;
-
if (rw == WRITE)
file_start_write(file);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 7ab923940d18..78bd80298528 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -39,7 +39,7 @@ const struct file_operations autofs4_root_operations = {
.open = dcache_dir_open,
.release = dcache_dir_close,
.read = generic_read_dir,
- .iterate = dcache_readdir,
+ .iterate_shared = dcache_readdir,
.llseek = dcache_dir_lseek,
.unlocked_ioctl = autofs4_root_ioctl,
#ifdef CONFIG_COMPAT
@@ -51,7 +51,7 @@ const struct file_operations autofs4_dir_operations = {
.open = autofs4_dir_open,
.release = dcache_dir_close,
.read = generic_read_dir,
- .iterate = dcache_readdir,
+ .iterate_shared = dcache_readdir,
.llseek = dcache_dir_lseek,
};
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 103f5d7c3083..72e35b721608 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -106,8 +106,8 @@ static int bad_inode_setxattr(struct dentry *dentry, const char *name,
return -EIO;
}
-static ssize_t bad_inode_getxattr(struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+static ssize_t bad_inode_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
return -EIO;
}
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index 35d19e8731e3..e0f59263a96d 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -116,7 +116,7 @@ BEFS_I(const struct inode *inode)
}
static inline befs_blocknr_t
-iaddr2blockno(struct super_block *sb, befs_inode_addr * iaddr)
+iaddr2blockno(struct super_block *sb, const befs_inode_addr *iaddr)
{
return ((iaddr->allocation_group << BEFS_SB(sb)->ag_shift) +
iaddr->start);
@@ -141,7 +141,7 @@ befs_iaddrs_per_block(struct super_block *sb)
}
static inline int
-befs_iaddr_is_empty(befs_inode_addr * iaddr)
+befs_iaddr_is_empty(const befs_inode_addr *iaddr)
{
return (!iaddr->allocation_group) && (!iaddr->start) && (!iaddr->len);
}
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index 22c166280883..307645f9e284 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -88,15 +88,15 @@ struct befs_btree_node {
static const befs_off_t befs_bt_inval = 0xffffffffffffffffULL;
/* local functions */
-static int befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
+static int befs_btree_seekleaf(struct super_block *sb, const befs_data_stream *ds,
befs_btree_super * bt_super,
struct befs_btree_node *this_node,
befs_off_t * node_off);
-static int befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
+static int befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds,
befs_btree_super * sup);
-static int befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
+static int befs_bt_read_node(struct super_block *sb, const befs_data_stream *ds,
struct befs_btree_node *node,
befs_off_t node_off);
@@ -134,7 +134,7 @@ static int befs_compare_strings(const void *key1, int keylen1,
* On failure, BEFS_ERR is returned.
*/
static int
-befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
+befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds,
befs_btree_super * sup)
{
struct buffer_head *bh;
@@ -193,7 +193,7 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
*/
static int
-befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
+befs_bt_read_node(struct super_block *sb, const befs_data_stream *ds,
struct befs_btree_node *node, befs_off_t node_off)
{
uint off = 0;
@@ -247,7 +247,7 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
* actuall value stored with the key.
*/
int
-befs_btree_find(struct super_block *sb, befs_data_stream * ds,
+befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
const char *key, befs_off_t * value)
{
struct befs_btree_node *this_node;
@@ -416,7 +416,7 @@ befs_find_key(struct super_block *sb, struct befs_btree_node *node,
* until the (key_no)th key is found or the tree is out of keys.
*/
int
-befs_btree_read(struct super_block *sb, befs_data_stream * ds,
+befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
loff_t key_no, size_t bufsize, char *keybuf, size_t * keysize,
befs_off_t * value)
{
@@ -548,7 +548,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
* Also checks for an empty tree. If there are no keys, returns BEFS_BT_EMPTY.
*/
static int
-befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
+befs_btree_seekleaf(struct super_block *sb, const befs_data_stream *ds,
befs_btree_super *bt_super,
struct befs_btree_node *this_node,
befs_off_t * node_off)
diff --git a/fs/befs/btree.h b/fs/befs/btree.h
index 92e781e5f30e..f2a8f637e9e0 100644
--- a/fs/befs/btree.h
+++ b/fs/befs/btree.h
@@ -4,10 +4,10 @@
*/
-int befs_btree_find(struct super_block *sb, befs_data_stream * ds,
+int befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
const char *key, befs_off_t * value);
-int befs_btree_read(struct super_block *sb, befs_data_stream * ds,
+int befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
loff_t key_no, size_t bufsize, char *keybuf,
size_t * keysize, befs_off_t * value);
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index ebd50718659f..af1bc19b7c85 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -21,16 +21,16 @@
const befs_inode_addr BAD_IADDR = { 0, 0, 0 };
static int befs_find_brun_direct(struct super_block *sb,
- befs_data_stream * data,
+ const befs_data_stream *data,
befs_blocknr_t blockno, befs_block_run * run);
static int befs_find_brun_indirect(struct super_block *sb,
- befs_data_stream * data,
+ const befs_data_stream *data,
befs_blocknr_t blockno,
befs_block_run * run);
static int befs_find_brun_dblindirect(struct super_block *sb,
- befs_data_stream * data,
+ const befs_data_stream *data,
befs_blocknr_t blockno,
befs_block_run * run);
@@ -45,10 +45,10 @@ static int befs_find_brun_dblindirect(struct super_block *sb,
* if you don't need to know offset just set @off = NULL.
*/
struct buffer_head *
-befs_read_datastream(struct super_block *sb, befs_data_stream * ds,
+befs_read_datastream(struct super_block *sb, const befs_data_stream *ds,
befs_off_t pos, uint * off)
{
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
befs_block_run run;
befs_blocknr_t block; /* block coresponding to pos */
@@ -87,7 +87,7 @@ befs_read_datastream(struct super_block *sb, befs_data_stream * ds,
* 2001-11-15 Will Dyson
*/
int
-befs_fblock2brun(struct super_block *sb, befs_data_stream * data,
+befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
befs_blocknr_t fblock, befs_block_run * run)
{
int err;
@@ -122,12 +122,12 @@ befs_fblock2brun(struct super_block *sb, befs_data_stream * data,
* Returns the number of bytes read
*/
size_t
-befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff,
- befs_off_t len)
+befs_read_lsymlink(struct super_block *sb, const befs_data_stream *ds,
+ void *buff, befs_off_t len)
{
befs_off_t bytes_read = 0; /* bytes readed */
u16 plen;
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
befs_debug(sb, "---> %s length: %llu", __func__, len);
while (bytes_read < len) {
@@ -163,7 +163,7 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff,
*/
befs_blocknr_t
-befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
+befs_count_blocks(struct super_block *sb, const befs_data_stream *ds)
{
befs_blocknr_t blocks;
befs_blocknr_t datablocks; /* File data blocks */
@@ -243,11 +243,11 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
2001-11-15 Will Dyson
*/
static int
-befs_find_brun_direct(struct super_block *sb, befs_data_stream * data,
+befs_find_brun_direct(struct super_block *sb, const befs_data_stream *data,
befs_blocknr_t blockno, befs_block_run * run)
{
int i;
- befs_block_run *array = data->direct;
+ const befs_block_run *array = data->direct;
befs_blocknr_t sum;
befs_blocknr_t max_block =
data->max_direct_range >> BEFS_SB(sb)->block_shift;
@@ -304,7 +304,8 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data,
*/
static int
befs_find_brun_indirect(struct super_block *sb,
- befs_data_stream * data, befs_blocknr_t blockno,
+ const befs_data_stream *data,
+ befs_blocknr_t blockno,
befs_block_run * run)
{
int i, j;
@@ -412,7 +413,8 @@ befs_find_brun_indirect(struct super_block *sb,
*/
static int
befs_find_brun_dblindirect(struct super_block *sb,
- befs_data_stream * data, befs_blocknr_t blockno,
+ const befs_data_stream *data,
+ befs_blocknr_t blockno,
befs_block_run * run)
{
int dblindir_indx;
@@ -427,7 +429,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
struct buffer_head *dbl_indir_block;
struct buffer_head *indir_block;
befs_block_run indir_run;
- befs_disk_inode_addr *iaddr_array = NULL;
+ befs_disk_inode_addr *iaddr_array;
struct befs_sb_info *befs_sb = BEFS_SB(sb);
befs_blocknr_t indir_start_blk =
@@ -486,7 +488,6 @@ befs_find_brun_dblindirect(struct super_block *sb,
iaddr_array = (befs_disk_inode_addr *) dbl_indir_block->b_data;
indir_run = fsrun_to_cpu(sb, iaddr_array[dbl_block_indx]);
brelse(dbl_indir_block);
- iaddr_array = NULL;
/* Read indirect block */
which_block = indir_indx / befs_iaddrs_per_block(sb);
@@ -511,7 +512,6 @@ befs_find_brun_dblindirect(struct super_block *sb,
iaddr_array = (befs_disk_inode_addr *) indir_block->b_data;
*run = fsrun_to_cpu(sb, iaddr_array[block_indx]);
brelse(indir_block);
- iaddr_array = NULL;
blockno_at_run_start = indir_start_blk;
blockno_at_run_start += diblklen * dblindir_indx;
diff --git a/fs/befs/datastream.h b/fs/befs/datastream.h
index 45e8a3c98249..91ba8203d83f 100644
--- a/fs/befs/datastream.h
+++ b/fs/befs/datastream.h
@@ -4,16 +4,17 @@
*/
struct buffer_head *befs_read_datastream(struct super_block *sb,
- befs_data_stream * ds, befs_off_t pos,
- uint * off);
+ const befs_data_stream *ds,
+ befs_off_t pos, uint * off);
-int befs_fblock2brun(struct super_block *sb, befs_data_stream * data,
+int befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
befs_blocknr_t fblock, befs_block_run * run);
-size_t befs_read_lsymlink(struct super_block *sb, befs_data_stream * data,
+size_t befs_read_lsymlink(struct super_block *sb, const befs_data_stream *data,
void *buff, befs_off_t len);
-befs_blocknr_t befs_count_blocks(struct super_block *sb, befs_data_stream * ds);
+befs_blocknr_t befs_count_blocks(struct super_block *sb,
+ const befs_data_stream *ds);
extern const befs_inode_addr BAD_IADDR;
diff --git a/fs/befs/io.c b/fs/befs/io.c
index 7a5b4ec21c56..523c8af2d770 100644
--- a/fs/befs/io.c
+++ b/fs/befs/io.c
@@ -26,7 +26,7 @@
struct buffer_head *
befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
{
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
befs_blocknr_t block = 0;
struct befs_sb_info *befs_sb = BEFS_SB(sb);
@@ -63,7 +63,7 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
struct buffer_head *
befs_bread(struct super_block *sb, befs_blocknr_t block)
{
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
befs_debug(sb, "---> Enter %s %lu", __func__, (unsigned long)block);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index cc0e08252913..7da05b159ade 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -66,7 +66,7 @@ static struct kmem_cache *befs_inode_cachep;
static const struct file_operations befs_dir_operations = {
.read = generic_read_dir,
- .iterate = befs_readdir,
+ .iterate_shared = befs_readdir,
.llseek = generic_file_llseek,
};
@@ -155,9 +155,9 @@ befs_get_block(struct inode *inode, sector_t block,
static struct dentry *
befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
- struct inode *inode = NULL;
+ struct inode *inode;
struct super_block *sb = dir->i_sb;
- befs_data_stream *ds = &BEFS_I(dir)->i_data.ds;
+ const befs_data_stream *ds = &BEFS_I(dir)->i_data.ds;
befs_off_t offset;
int ret;
int utfnamelen;
@@ -207,7 +207,7 @@ befs_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
- befs_data_stream *ds = &BEFS_I(inode)->i_data.ds;
+ const befs_data_stream *ds = &BEFS_I(inode)->i_data.ds;
befs_off_t value;
int result;
size_t keysize;
@@ -294,10 +294,10 @@ static void init_once(void *foo)
static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
{
- struct buffer_head *bh = NULL;
- befs_inode *raw_inode = NULL;
+ struct buffer_head *bh;
+ befs_inode *raw_inode;
struct befs_sb_info *befs_sb = BEFS_SB(sb);
- struct befs_inode_info *befs_ino = NULL;
+ struct befs_inode_info *befs_ino;
struct inode *inode;
long ret = -EIO;
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 3ec6113146c0..34a5bc2f1290 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -70,7 +70,7 @@ static int bfs_readdir(struct file *f, struct dir_context *ctx)
const struct file_operations bfs_dir_operations = {
.read = generic_read_dir,
- .iterate = bfs_readdir,
+ .iterate_shared = bfs_readdir,
.fsync = generic_file_fsync,
.llseek = generic_file_llseek,
};
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 4c556680fa74..2fab9f130e51 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -297,7 +297,10 @@ static int load_aout_binary(struct linux_binprm * bprm)
}
if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
- vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
+ error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
+ if (IS_ERR_VALUE(error))
+ return error;
+
read_code(bprm->file, N_TXTADDR(ex), fd_offset,
ex.a_text + ex.a_data);
goto beyond_if;
@@ -378,8 +381,10 @@ static int load_aout_library(struct file *file)
"N_TXTOFF is not page aligned. Please convert library: %pD\n",
file);
}
- vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-
+ retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
+ if (IS_ERR_VALUE(retval))
+ goto out;
+
read_code(file, start_addr, N_TXTOFF(ex),
ex.a_text + ex.a_data);
retval = 0;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 81381cc0dd17..938fc4ede764 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1176,8 +1176,11 @@ static int load_elf_library(struct file *file)
len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
ELF_MIN_ALIGN - 1);
bss = eppnt->p_memsz + eppnt->p_vaddr;
- if (bss > len)
- vm_brk(len, bss - len);
+ if (bss > len) {
+ error = vm_brk(len, bss - len);
+ if (BAD_ADDR(error))
+ goto out_free_ph;
+ }
error = 0;
out_free_ph:
@@ -2273,7 +2276,7 @@ static int elf_core_dump(struct coredump_params *cprm)
goto end_coredump;
/* Align to page */
- if (!dump_skip(cprm, dataoff - cprm->written))
+ if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 083ea2bc60ab..71ade0e556b7 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1787,7 +1787,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
goto end_coredump;
}
- if (!dump_skip(cprm, dataoff - cprm->written))
+ if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
goto end_coredump;
if (!elf_fdpic_dump_segments(cprm))
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 20a2c02b77c4..1089dbf25925 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -29,6 +29,7 @@
#include <linux/log2.h>
#include <linux/cleancache.h>
#include <linux/dax.h>
+#include <linux/badblocks.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -162,15 +163,15 @@ static struct inode *bdev_file_inode(struct file *file)
}
static ssize_t
-blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = bdev_file_inode(file);
if (IS_DAX(inode))
- return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+ return dax_do_io(iocb, inode, iter, blkdev_get_block,
NULL, DIO_SKIP_DIO_COUNT);
- return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
+ return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter,
blkdev_get_block, NULL, NULL,
DIO_SKIP_DIO_COUNT);
}
@@ -1159,6 +1160,33 @@ void bd_set_size(struct block_device *bdev, loff_t size)
}
EXPORT_SYMBOL(bd_set_size);
+static bool blkdev_dax_capable(struct block_device *bdev)
+{
+ struct gendisk *disk = bdev->bd_disk;
+
+ if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX))
+ return false;
+
+ /*
+ * If the partition is not aligned on a page boundary, we can't
+ * do dax I/O to it.
+ */
+ if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
+ || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+ return false;
+
+ /*
+ * If the device has known bad blocks, force all I/O through the
+ * driver / page cache.
+ *
+ * TODO: support finer grained dax error handling
+ */
+ if (disk->bb && disk->bb->count)
+ return false;
+
+ return true;
+}
+
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
/*
@@ -1660,12 +1688,8 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
- if (ret > 0) {
- ssize_t err;
- err = generic_write_sync(file, iocb->ki_pos - ret, ret);
- if (err < 0)
- ret = err;
- }
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
blk_finish_plug(&plug);
return ret;
}
@@ -1724,79 +1748,13 @@ static const struct address_space_operations def_blk_aops = {
.is_dirty_writeback = buffer_check_dirty_writeback,
};
-#ifdef CONFIG_FS_DAX
-/*
- * In the raw block case we do not need to contend with truncation nor
- * unwritten file extents. Without those concerns there is no need for
- * additional locking beyond the mmap_sem context that these routines
- * are already executing under.
- *
- * Note, there is no protection if the block device is dynamically
- * resized (partition grow/shrink) during a fault. A stable block device
- * size is already not enforced in the blkdev_direct_IO path.
- *
- * For DAX, it is the responsibility of the block device driver to
- * ensure the whole-disk device size is stable while requests are in
- * flight.
- *
- * Finally, unlike the filemap_page_mkwrite() case there is no
- * filesystem superblock to sync against freezing. We still include a
- * pfn_mkwrite callback for dax drivers to receive write fault
- * notifications.
- */
-static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
-{
- return dax_pfn_mkwrite(vma, vmf);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags)
-{
- return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
-}
-
-static const struct vm_operations_struct blkdev_dax_vm_ops = {
- .fault = blkdev_dax_fault,
- .pmd_fault = blkdev_dax_pmd_fault,
- .pfn_mkwrite = blkdev_dax_pfn_mkwrite,
-};
-
-static const struct vm_operations_struct blkdev_default_vm_ops = {
- .fault = filemap_fault,
- .map_pages = filemap_map_pages,
-};
-
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
-{
- struct inode *bd_inode = bdev_file_inode(file);
-
- file_accessed(file);
- if (IS_DAX(bd_inode)) {
- vma->vm_ops = &blkdev_dax_vm_ops;
- vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
- } else {
- vma->vm_ops = &blkdev_default_vm_ops;
- }
-
- return 0;
-}
-#else
-#define blkdev_mmap generic_file_mmap
-#endif
-
const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
- .mmap = blkdev_mmap,
+ .mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 6d263bb1621c..67a607709d4f 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -63,9 +63,6 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
}
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 80e8472d618b..d3090187fd76 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1991,7 +1991,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
ifp = kmalloc(sizeof(*ifp), GFP_NOFS);
if (!ifp) {
- kfree(fspath);
+ vfree(fspath);
return ERR_PTR(-ENOMEM);
}
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 61205e3bbefa..1da5753d886d 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -196,6 +196,16 @@ struct btrfs_inode {
struct list_head delayed_iput;
long delayed_iput_count;
+ /*
+ * To avoid races between lockless (i_mutex not held) direct IO writes
+ * and concurrent fsync requests. Direct IO writes must acquire read
+ * access on this semaphore for creating an extent map and its
+ * corresponding ordered extent. The fast fsync path must acquire write
+ * access on this semaphore before it collects ordered extents and
+ * extent maps.
+ */
+ struct rw_semaphore dio_sem;
+
struct inode vfs_inode;
};
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ff61a41ac90b..658c39b70fba 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -743,8 +743,11 @@ out:
static struct {
struct list_head idle_ws;
spinlock_t ws_lock;
- int num_ws;
- atomic_t alloc_ws;
+ /* Number of free workspaces */
+ int free_ws;
+ /* Total number of allocated workspaces */
+ atomic_t total_ws;
+ /* Waiters for a free workspace */
wait_queue_head_t ws_wait;
} btrfs_comp_ws[BTRFS_COMPRESS_TYPES];
@@ -758,16 +761,34 @@ void __init btrfs_init_compress(void)
int i;
for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+ struct list_head *workspace;
+
INIT_LIST_HEAD(&btrfs_comp_ws[i].idle_ws);
spin_lock_init(&btrfs_comp_ws[i].ws_lock);
- atomic_set(&btrfs_comp_ws[i].alloc_ws, 0);
+ atomic_set(&btrfs_comp_ws[i].total_ws, 0);
init_waitqueue_head(&btrfs_comp_ws[i].ws_wait);
+
+ /*
+ * Preallocate one workspace for each compression type so
+ * we can guarantee forward progress in the worst case
+ */
+ workspace = btrfs_compress_op[i]->alloc_workspace();
+ if (IS_ERR(workspace)) {
+ printk(KERN_WARNING
+ "BTRFS: cannot preallocate compression workspace, will try later");
+ } else {
+ atomic_set(&btrfs_comp_ws[i].total_ws, 1);
+ btrfs_comp_ws[i].free_ws = 1;
+ list_add(workspace, &btrfs_comp_ws[i].idle_ws);
+ }
}
}
/*
- * this finds an available workspace or allocates a new one
- * ERR_PTR is returned if things go bad.
+ * This finds an available workspace or allocates a new one.
+ * If it's not possible to allocate a new one, waits until there's one.
+ * Preallocation makes a forward progress guarantees and we do not return
+ * errors.
*/
static struct list_head *find_workspace(int type)
{
@@ -777,36 +798,58 @@ static struct list_head *find_workspace(int type)
struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws;
spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock;
- atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws;
+ atomic_t *total_ws = &btrfs_comp_ws[idx].total_ws;
wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait;
- int *num_ws = &btrfs_comp_ws[idx].num_ws;
+ int *free_ws = &btrfs_comp_ws[idx].free_ws;
again:
spin_lock(ws_lock);
if (!list_empty(idle_ws)) {
workspace = idle_ws->next;
list_del(workspace);
- (*num_ws)--;
+ (*free_ws)--;
spin_unlock(ws_lock);
return workspace;
}
- if (atomic_read(alloc_ws) > cpus) {
+ if (atomic_read(total_ws) > cpus) {
DEFINE_WAIT(wait);
spin_unlock(ws_lock);
prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (atomic_read(alloc_ws) > cpus && !*num_ws)
+ if (atomic_read(total_ws) > cpus && !*free_ws)
schedule();
finish_wait(ws_wait, &wait);
goto again;
}
- atomic_inc(alloc_ws);
+ atomic_inc(total_ws);
spin_unlock(ws_lock);
workspace = btrfs_compress_op[idx]->alloc_workspace();
if (IS_ERR(workspace)) {
- atomic_dec(alloc_ws);
+ atomic_dec(total_ws);
wake_up(ws_wait);
+
+ /*
+ * Do not return the error but go back to waiting. There's a
+ * workspace preallocated for each type and the compression
+ * time is bounded so we get to a workspace eventually. This
+ * makes our caller's life easier.
+ *
+ * To prevent silent and low-probability deadlocks (when the
+ * initial preallocation fails), check if there are any
+ * workspaces at all.
+ */
+ if (atomic_read(total_ws) == 0) {
+ static DEFINE_RATELIMIT_STATE(_rs,
+ /* once per minute */ 60 * HZ,
+ /* no burst */ 1);
+
+ if (__ratelimit(&_rs)) {
+ printk(KERN_WARNING
+ "no compression workspaces, low memory, retrying");
+ }
+ }
+ goto again;
}
return workspace;
}
@@ -820,21 +863,21 @@ static void free_workspace(int type, struct list_head *workspace)
int idx = type - 1;
struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws;
spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock;
- atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws;
+ atomic_t *total_ws = &btrfs_comp_ws[idx].total_ws;
wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait;
- int *num_ws = &btrfs_comp_ws[idx].num_ws;
+ int *free_ws = &btrfs_comp_ws[idx].free_ws;
spin_lock(ws_lock);
- if (*num_ws < num_online_cpus()) {
+ if (*free_ws < num_online_cpus()) {
list_add(workspace, idle_ws);
- (*num_ws)++;
+ (*free_ws)++;
spin_unlock(ws_lock);
goto wake;
}
spin_unlock(ws_lock);
btrfs_compress_op[idx]->free_workspace(workspace);
- atomic_dec(alloc_ws);
+ atomic_dec(total_ws);
wake:
/*
* Make sure counter is updated before we wake up waiters.
@@ -857,7 +900,7 @@ static void free_workspaces(void)
workspace = btrfs_comp_ws[i].idle_ws.next;
list_del(workspace);
btrfs_compress_op[i]->free_workspace(workspace);
- atomic_dec(&btrfs_comp_ws[i].alloc_ws);
+ atomic_dec(&btrfs_comp_ws[i].total_ws);
}
}
}
@@ -894,8 +937,6 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
int ret;
workspace = find_workspace(type);
- if (IS_ERR(workspace))
- return PTR_ERR(workspace);
ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
start, len, pages,
@@ -930,8 +971,6 @@ static int btrfs_decompress_biovec(int type, struct page **pages_in,
int ret;
workspace = find_workspace(type);
- if (IS_ERR(workspace))
- return PTR_ERR(workspace);
ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
disk_start,
@@ -952,8 +991,6 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
int ret;
workspace = find_workspace(type);
- if (IS_ERR(workspace))
- return PTR_ERR(workspace);
ret = btrfs_compress_op[type-1]->decompress(workspace, data_in,
dest_page, start_byte,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index ec7928a27aaa..decd0a3f5d61 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1011,7 +1011,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
return ret;
if (refs == 0) {
ret = -EROFS;
- btrfs_std_error(root->fs_info, ret, NULL);
+ btrfs_handle_fs_error(root->fs_info, ret, NULL);
return ret;
}
} else {
@@ -1928,7 +1928,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
child = read_node_slot(root, mid, 0);
if (!child) {
ret = -EROFS;
- btrfs_std_error(root->fs_info, ret, NULL);
+ btrfs_handle_fs_error(root->fs_info, ret, NULL);
goto enospc;
}
@@ -2031,7 +2031,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
*/
if (!left) {
ret = -EROFS;
- btrfs_std_error(root->fs_info, ret, NULL);
+ btrfs_handle_fs_error(root->fs_info, ret, NULL);
goto enospc;
}
wret = balance_node_right(trans, root, mid, left);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 84a6a5b3384a..ddcc58f03c79 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -33,6 +33,7 @@
#include <asm/kmap_types.h>
#include <linux/pagemap.h>
#include <linux/btrfs.h>
+#include <linux/btrfs_tree.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/sizes.h>
@@ -64,98 +65,6 @@ struct btrfs_ordered_sum;
#define BTRFS_COMPAT_EXTENT_TREE_V0
-/* holds pointers to all of the tree roots */
-#define BTRFS_ROOT_TREE_OBJECTID 1ULL
-
-/* stores information about which extents are in use, and reference counts */
-#define BTRFS_EXTENT_TREE_OBJECTID 2ULL
-
-/*
- * chunk tree stores translations from logical -> physical block numbering
- * the super block points to the chunk tree
- */
-#define BTRFS_CHUNK_TREE_OBJECTID 3ULL
-
-/*
- * stores information about which areas of a given device are in use.
- * one per device. The tree of tree roots points to the device tree
- */
-#define BTRFS_DEV_TREE_OBJECTID 4ULL
-
-/* one per subvolume, storing files and directories */
-#define BTRFS_FS_TREE_OBJECTID 5ULL
-
-/* directory objectid inside the root tree */
-#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL
-
-/* holds checksums of all the data extents */
-#define BTRFS_CSUM_TREE_OBJECTID 7ULL
-
-/* holds quota configuration and tracking */
-#define BTRFS_QUOTA_TREE_OBJECTID 8ULL
-
-/* for storing items that use the BTRFS_UUID_KEY* types */
-#define BTRFS_UUID_TREE_OBJECTID 9ULL
-
-/* tracks free space in block groups. */
-#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
-
-/* device stats in the device tree */
-#define BTRFS_DEV_STATS_OBJECTID 0ULL
-
-/* for storing balance parameters in the root tree */
-#define BTRFS_BALANCE_OBJECTID -4ULL
-
-/* orhpan objectid for tracking unlinked/truncated files */
-#define BTRFS_ORPHAN_OBJECTID -5ULL
-
-/* does write ahead logging to speed up fsyncs */
-#define BTRFS_TREE_LOG_OBJECTID -6ULL
-#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL
-
-/* for space balancing */
-#define BTRFS_TREE_RELOC_OBJECTID -8ULL
-#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL
-
-/*
- * extent checksums all have this objectid
- * this allows them to share the logging tree
- * for fsyncs
- */
-#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL
-
-/* For storing free space cache */
-#define BTRFS_FREE_SPACE_OBJECTID -11ULL
-
-/*
- * The inode number assigned to the special inode for storing
- * free ino cache
- */
-#define BTRFS_FREE_INO_OBJECTID -12ULL
-
-/* dummy objectid represents multiple objectids */
-#define BTRFS_MULTIPLE_OBJECTIDS -255ULL
-
-/*
- * All files have objectids in this range.
- */
-#define BTRFS_FIRST_FREE_OBJECTID 256ULL
-#define BTRFS_LAST_FREE_OBJECTID -256ULL
-#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL
-
-
-/*
- * the device items go into the chunk tree. The key is in the form
- * [ 1 BTRFS_DEV_ITEM_KEY device_id ]
- */
-#define BTRFS_DEV_ITEMS_OBJECTID 1ULL
-
-#define BTRFS_BTREE_INODE_OBJECTID 1
-
-#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2
-
-#define BTRFS_DEV_REPLACE_DEVID 0ULL
-
/*
* the max metadata block size. This limit is somewhat artificial,
* but the memmove costs go through the roof for larger blocks.
@@ -175,12 +84,6 @@ struct btrfs_ordered_sum;
*/
#define BTRFS_LINK_MAX 65535U
-/* 32 bytes in various csum fields */
-#define BTRFS_CSUM_SIZE 32
-
-/* csum types */
-#define BTRFS_CSUM_TYPE_CRC32 0
-
static const int btrfs_csum_sizes[] = { 4 };
/* four bytes for CRC32 */
@@ -189,17 +92,6 @@ static const int btrfs_csum_sizes[] = { 4 };
/* spefic to btrfs_map_block(), therefore not in include/linux/blk_types.h */
#define REQ_GET_READ_MIRRORS (1 << 30)
-#define BTRFS_FT_UNKNOWN 0
-#define BTRFS_FT_REG_FILE 1
-#define BTRFS_FT_DIR 2
-#define BTRFS_FT_CHRDEV 3
-#define BTRFS_FT_BLKDEV 4
-#define BTRFS_FT_FIFO 5
-#define BTRFS_FT_SOCK 6
-#define BTRFS_FT_SYMLINK 7
-#define BTRFS_FT_XATTR 8
-#define BTRFS_FT_MAX 9
-
/* ioprio of readahead is set to idle */
#define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
@@ -207,138 +99,10 @@ static const int btrfs_csum_sizes[] = { 4 };
#define BTRFS_MAX_EXTENT_SIZE SZ_128M
-/*
- * The key defines the order in the tree, and so it also defines (optimal)
- * block layout.
- *
- * objectid corresponds to the inode number.
- *
- * type tells us things about the object, and is a kind of stream selector.
- * so for a given inode, keys with type of 1 might refer to the inode data,
- * type of 2 may point to file data in the btree and type == 3 may point to
- * extents.
- *
- * offset is the starting byte offset for this key in the stream.
- *
- * btrfs_disk_key is in disk byte order. struct btrfs_key is always
- * in cpu native order. Otherwise they are identical and their sizes
- * should be the same (ie both packed)
- */
-struct btrfs_disk_key {
- __le64 objectid;
- u8 type;
- __le64 offset;
-} __attribute__ ((__packed__));
-
-struct btrfs_key {
- u64 objectid;
- u8 type;
- u64 offset;
-} __attribute__ ((__packed__));
-
struct btrfs_mapping_tree {
struct extent_map_tree map_tree;
};
-struct btrfs_dev_item {
- /* the internal btrfs device id */
- __le64 devid;
-
- /* size of the device */
- __le64 total_bytes;
-
- /* bytes used */
- __le64 bytes_used;
-
- /* optimal io alignment for this device */
- __le32 io_align;
-
- /* optimal io width for this device */
- __le32 io_width;
-
- /* minimal io size for this device */
- __le32 sector_size;
-
- /* type and info about this device */
- __le64 type;
-
- /* expected generation for this device */
- __le64 generation;
-
- /*
- * starting byte of this partition on the device,
- * to allow for stripe alignment in the future
- */
- __le64 start_offset;
-
- /* grouping information for allocation decisions */
- __le32 dev_group;
-
- /* seek speed 0-100 where 100 is fastest */
- u8 seek_speed;
-
- /* bandwidth 0-100 where 100 is fastest */
- u8 bandwidth;
-
- /* btrfs generated uuid for this device */
- u8 uuid[BTRFS_UUID_SIZE];
-
- /* uuid of FS who owns this device */
- u8 fsid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_stripe {
- __le64 devid;
- __le64 offset;
- u8 dev_uuid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_chunk {
- /* size of this chunk in bytes */
- __le64 length;
-
- /* objectid of the root referencing this chunk */
- __le64 owner;
-
- __le64 stripe_len;
- __le64 type;
-
- /* optimal io alignment for this chunk */
- __le32 io_align;
-
- /* optimal io width for this chunk */
- __le32 io_width;
-
- /* minimal io size for this chunk */
- __le32 sector_size;
-
- /* 2^16 stripes is quite a lot, a second limit is the size of a single
- * item in the btree
- */
- __le16 num_stripes;
-
- /* sub stripes only matter for raid10 */
- __le16 sub_stripes;
- struct btrfs_stripe stripe;
- /* additional stripes go here */
-} __attribute__ ((__packed__));
-
-#define BTRFS_FREE_SPACE_EXTENT 1
-#define BTRFS_FREE_SPACE_BITMAP 2
-
-struct btrfs_free_space_entry {
- __le64 offset;
- __le64 bytes;
- u8 type;
-} __attribute__ ((__packed__));
-
-struct btrfs_free_space_header {
- struct btrfs_disk_key location;
- __le64 generation;
- __le64 num_entries;
- __le64 num_bitmaps;
-} __attribute__ ((__packed__));
-
static inline unsigned long btrfs_chunk_item_size(int num_stripes)
{
BUG_ON(num_stripes == 0);
@@ -346,9 +110,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
sizeof(struct btrfs_stripe) * (num_stripes - 1);
}
-#define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0)
-#define BTRFS_HEADER_FLAG_RELOC (1ULL << 1)
-
/*
* File system states
*/
@@ -357,13 +118,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
#define BTRFS_FS_STATE_TRANS_ABORTED 2
#define BTRFS_FS_STATE_DEV_REPLACING 3
-/* Super block flags */
-/* Errors detected */
-#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2)
-
-#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32)
-#define BTRFS_SUPER_FLAG_METADUMP (1ULL << 33)
-
#define BTRFS_BACKREF_REV_MAX 256
#define BTRFS_BACKREF_REV_SHIFT 56
#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \
@@ -410,7 +164,6 @@ struct btrfs_header {
* room to translate 14 chunks with 3 stripes each.
*/
#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048
-#define BTRFS_LABEL_SIZE 256
/*
* just in case we somehow lose the roots and are not able to mount,
@@ -507,31 +260,6 @@ struct btrfs_super_block {
* Compat flags that we support. If any incompat flags are set other than the
* ones specified below then we will fail to mount
*/
-#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0)
-
-#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0)
-#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1)
-#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2)
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3)
-/*
- * some patches floated around with a second compression method
- * lets save that incompat here for when they do get in
- * Note we don't actually support it, we're just reserving the
- * number
- */
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4)
-
-/*
- * older kernels tried to do bigger metadata blocks, but the
- * code was pretty buggy. Lets not let them try anymore.
- */
-#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA (1ULL << 5)
-
-#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6)
-#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7)
-#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8)
-#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9)
-
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL
@@ -624,357 +352,8 @@ struct btrfs_path {
unsigned int need_commit_sem:1;
unsigned int skip_release_on_error:1;
};
-
-/*
- * items in the extent btree are used to record the objectid of the
- * owner of the block and the number of references
- */
-
-struct btrfs_extent_item {
- __le64 refs;
- __le64 generation;
- __le64 flags;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_item_v0 {
- __le32 refs;
-} __attribute__ ((__packed__));
-
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r) >> 4) - \
sizeof(struct btrfs_item))
-
-#define BTRFS_EXTENT_FLAG_DATA (1ULL << 0)
-#define BTRFS_EXTENT_FLAG_TREE_BLOCK (1ULL << 1)
-
-/* following flags only apply to tree blocks */
-
-/* use full backrefs for extent pointers in the block */
-#define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8)
-
-/*
- * this flag is only used internally by scrub and may be changed at any time
- * it is only declared here to avoid collisions
- */
-#define BTRFS_EXTENT_FLAG_SUPER (1ULL << 48)
-
-struct btrfs_tree_block_info {
- struct btrfs_disk_key key;
- u8 level;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_data_ref {
- __le64 root;
- __le64 objectid;
- __le64 offset;
- __le32 count;
-} __attribute__ ((__packed__));
-
-struct btrfs_shared_data_ref {
- __le32 count;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_inline_ref {
- u8 type;
- __le64 offset;
-} __attribute__ ((__packed__));
-
-/* old style backrefs item */
-struct btrfs_extent_ref_v0 {
- __le64 root;
- __le64 generation;
- __le64 objectid;
- __le32 count;
-} __attribute__ ((__packed__));
-
-
-/* dev extents record free space on individual devices. The owner
- * field points back to the chunk allocation mapping tree that allocated
- * the extent. The chunk tree uuid field is a way to double check the owner
- */
-struct btrfs_dev_extent {
- __le64 chunk_tree;
- __le64 chunk_objectid;
- __le64 chunk_offset;
- __le64 length;
- u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_ref {
- __le64 index;
- __le16 name_len;
- /* name goes here */
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_extref {
- __le64 parent_objectid;
- __le64 index;
- __le16 name_len;
- __u8 name[0];
- /* name goes here */
-} __attribute__ ((__packed__));
-
-struct btrfs_timespec {
- __le64 sec;
- __le32 nsec;
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_item {
- /* nfs style generation number */
- __le64 generation;
- /* transid that last touched this inode */
- __le64 transid;
- __le64 size;
- __le64 nbytes;
- __le64 block_group;
- __le32 nlink;
- __le32 uid;
- __le32 gid;
- __le32 mode;
- __le64 rdev;
- __le64 flags;
-
- /* modification sequence number for NFS */
- __le64 sequence;
-
- /*
- * a little future expansion, for more than this we can
- * just grow the inode item and version it
- */
- __le64 reserved[4];
- struct btrfs_timespec atime;
- struct btrfs_timespec ctime;
- struct btrfs_timespec mtime;
- struct btrfs_timespec otime;
-} __attribute__ ((__packed__));
-
-struct btrfs_dir_log_item {
- __le64 end;
-} __attribute__ ((__packed__));
-
-struct btrfs_dir_item {
- struct btrfs_disk_key location;
- __le64 transid;
- __le16 data_len;
- __le16 name_len;
- u8 type;
-} __attribute__ ((__packed__));
-
-#define BTRFS_ROOT_SUBVOL_RDONLY (1ULL << 0)
-
-/*
- * Internal in-memory flag that a subvolume has been marked for deletion but
- * still visible as a directory
- */
-#define BTRFS_ROOT_SUBVOL_DEAD (1ULL << 48)
-
-struct btrfs_root_item {
- struct btrfs_inode_item inode;
- __le64 generation;
- __le64 root_dirid;
- __le64 bytenr;
- __le64 byte_limit;
- __le64 bytes_used;
- __le64 last_snapshot;
- __le64 flags;
- __le32 refs;
- struct btrfs_disk_key drop_progress;
- u8 drop_level;
- u8 level;
-
- /*
- * The following fields appear after subvol_uuids+subvol_times
- * were introduced.
- */
-
- /*
- * This generation number is used to test if the new fields are valid
- * and up to date while reading the root item. Every time the root item
- * is written out, the "generation" field is copied into this field. If
- * anyone ever mounted the fs with an older kernel, we will have
- * mismatching generation values here and thus must invalidate the
- * new fields. See btrfs_update_root and btrfs_find_last_root for
- * details.
- * the offset of generation_v2 is also used as the start for the memset
- * when invalidating the fields.
- */
- __le64 generation_v2;
- u8 uuid[BTRFS_UUID_SIZE];
- u8 parent_uuid[BTRFS_UUID_SIZE];
- u8 received_uuid[BTRFS_UUID_SIZE];
- __le64 ctransid; /* updated when an inode changes */
- __le64 otransid; /* trans when created */
- __le64 stransid; /* trans when sent. non-zero for received subvol */
- __le64 rtransid; /* trans when received. non-zero for received subvol */
- struct btrfs_timespec ctime;
- struct btrfs_timespec otime;
- struct btrfs_timespec stime;
- struct btrfs_timespec rtime;
- __le64 reserved[8]; /* for future */
-} __attribute__ ((__packed__));
-
-/*
- * this is used for both forward and backward root refs
- */
-struct btrfs_root_ref {
- __le64 dirid;
- __le64 sequence;
- __le16 name_len;
-} __attribute__ ((__packed__));
-
-struct btrfs_disk_balance_args {
- /*
- * profiles to operate on, single is denoted by
- * BTRFS_AVAIL_ALLOC_BIT_SINGLE
- */
- __le64 profiles;
-
- /*
- * usage filter
- * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N'
- * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max
- */
- union {
- __le64 usage;
- struct {
- __le32 usage_min;
- __le32 usage_max;
- };
- };
-
- /* devid filter */
- __le64 devid;
-
- /* devid subset filter [pstart..pend) */
- __le64 pstart;
- __le64 pend;
-
- /* btrfs virtual address space subset filter [vstart..vend) */
- __le64 vstart;
- __le64 vend;
-
- /*
- * profile to convert to, single is denoted by
- * BTRFS_AVAIL_ALLOC_BIT_SINGLE
- */
- __le64 target;
-
- /* BTRFS_BALANCE_ARGS_* */
- __le64 flags;
-
- /*
- * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'
- * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum
- * and maximum
- */
- union {
- __le64 limit;
- struct {
- __le32 limit_min;
- __le32 limit_max;
- };
- };
-
- /*
- * Process chunks that cross stripes_min..stripes_max devices,
- * BTRFS_BALANCE_ARGS_STRIPES_RANGE
- */
- __le32 stripes_min;
- __le32 stripes_max;
-
- __le64 unused[6];
-} __attribute__ ((__packed__));
-
-/*
- * store balance parameters to disk so that balance can be properly
- * resumed after crash or unmount
- */
-struct btrfs_balance_item {
- /* BTRFS_BALANCE_* */
- __le64 flags;
-
- struct btrfs_disk_balance_args data;
- struct btrfs_disk_balance_args meta;
- struct btrfs_disk_balance_args sys;
-
- __le64 unused[4];
-} __attribute__ ((__packed__));
-
-#define BTRFS_FILE_EXTENT_INLINE 0
-#define BTRFS_FILE_EXTENT_REG 1
-#define BTRFS_FILE_EXTENT_PREALLOC 2
-
-struct btrfs_file_extent_item {
- /*
- * transaction id that created this extent
- */
- __le64 generation;
- /*
- * max number of bytes to hold this extent in ram
- * when we split a compressed extent we can't know how big
- * each of the resulting pieces will be. So, this is
- * an upper limit on the size of the extent in ram instead of
- * an exact limit.
- */
- __le64 ram_bytes;
-
- /*
- * 32 bits for the various ways we might encode the data,
- * including compression and encryption. If any of these
- * are set to something a given disk format doesn't understand
- * it is treated like an incompat flag for reading and writing,
- * but not for stat.
- */
- u8 compression;
- u8 encryption;
- __le16 other_encoding; /* spare for later use */
-
- /* are we inline data or a real extent? */
- u8 type;
-
- /*
- * disk space consumed by the extent, checksum blocks are included
- * in these numbers
- *
- * At this offset in the structure, the inline extent data start.
- */
- __le64 disk_bytenr;
- __le64 disk_num_bytes;
- /*
- * the logical offset in file blocks (no csums)
- * this extent record is for. This allows a file extent to point
- * into the middle of an existing extent on disk, sharing it
- * between two snapshots (useful if some bytes in the middle of the
- * extent have changed
- */
- __le64 offset;
- /*
- * the logical number of file blocks (no csums included). This
- * always reflects the size uncompressed and without encoding.
- */
- __le64 num_bytes;
-
-} __attribute__ ((__packed__));
-
-struct btrfs_csum_item {
- u8 csum;
-} __attribute__ ((__packed__));
-
-struct btrfs_dev_stats_item {
- /*
- * grow this item struct at the end for future enhancements and keep
- * the existing values unchanged
- */
- __le64 values[BTRFS_DEV_STAT_VALUES_MAX];
-} __attribute__ ((__packed__));
-
-#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS 0
-#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID 1
-#define BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED 0
-#define BTRFS_DEV_REPLACE_ITEM_STATE_STARTED 1
-#define BTRFS_DEV_REPLACE_ITEM_STATE_SUSPENDED 2
-#define BTRFS_DEV_REPLACE_ITEM_STATE_FINISHED 3
-#define BTRFS_DEV_REPLACE_ITEM_STATE_CANCELED 4
-
struct btrfs_dev_replace {
u64 replace_state; /* see #define above */
u64 time_started; /* seconds since 1-Jan-1970 */
@@ -1005,175 +384,6 @@ struct btrfs_dev_replace {
struct btrfs_scrub_progress scrub_progress;
};
-struct btrfs_dev_replace_item {
- /*
- * grow this item struct at the end for future enhancements and keep
- * the existing values unchanged
- */
- __le64 src_devid;
- __le64 cursor_left;
- __le64 cursor_right;
- __le64 cont_reading_from_srcdev_mode;
-
- __le64 replace_state;
- __le64 time_started;
- __le64 time_stopped;
- __le64 num_write_errors;
- __le64 num_uncorrectable_read_errors;
-} __attribute__ ((__packed__));
-
-/* different types of block groups (and chunks) */
-#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0)
-#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1)
-#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2)
-#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3)
-#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4)
-#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5)
-#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6)
-#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7)
-#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8)
-#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
- BTRFS_SPACE_INFO_GLOBAL_RSV)
-
-enum btrfs_raid_types {
- BTRFS_RAID_RAID10,
- BTRFS_RAID_RAID1,
- BTRFS_RAID_DUP,
- BTRFS_RAID_RAID0,
- BTRFS_RAID_SINGLE,
- BTRFS_RAID_RAID5,
- BTRFS_RAID_RAID6,
- BTRFS_NR_RAID_TYPES
-};
-
-#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \
- BTRFS_BLOCK_GROUP_SYSTEM | \
- BTRFS_BLOCK_GROUP_METADATA)
-
-#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \
- BTRFS_BLOCK_GROUP_RAID1 | \
- BTRFS_BLOCK_GROUP_RAID5 | \
- BTRFS_BLOCK_GROUP_RAID6 | \
- BTRFS_BLOCK_GROUP_DUP | \
- BTRFS_BLOCK_GROUP_RAID10)
-#define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \
- BTRFS_BLOCK_GROUP_RAID6)
-
-/*
- * We need a bit for restriper to be able to tell when chunks of type
- * SINGLE are available. This "extended" profile format is used in
- * fs_info->avail_*_alloc_bits (in-memory) and balance item fields
- * (on-disk). The corresponding on-disk bit in chunk.type is reserved
- * to avoid remappings between two formats in future.
- */
-#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48)
-
-/*
- * A fake block group type that is used to communicate global block reserve
- * size to userspace via the SPACE_INFO ioctl.
- */
-#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49)
-
-#define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \
- BTRFS_AVAIL_ALLOC_BIT_SINGLE)
-
-static inline u64 chunk_to_extended(u64 flags)
-{
- if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)
- flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-
- return flags;
-}
-static inline u64 extended_to_chunk(u64 flags)
-{
- return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-}
-
-struct btrfs_block_group_item {
- __le64 used;
- __le64 chunk_objectid;
- __le64 flags;
-} __attribute__ ((__packed__));
-
-struct btrfs_free_space_info {
- __le32 extent_count;
- __le32 flags;
-} __attribute__ ((__packed__));
-
-#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0)
-
-#define BTRFS_QGROUP_LEVEL_SHIFT 48
-static inline u64 btrfs_qgroup_level(u64 qgroupid)
-{
- return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT;
-}
-
-/*
- * is subvolume quota turned on?
- */
-#define BTRFS_QGROUP_STATUS_FLAG_ON (1ULL << 0)
-/*
- * RESCAN is set during the initialization phase
- */
-#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1ULL << 1)
-/*
- * Some qgroup entries are known to be out of date,
- * either because the configuration has changed in a way that
- * makes a rescan necessary, or because the fs has been mounted
- * with a non-qgroup-aware version.
- * Turning qouta off and on again makes it inconsistent, too.
- */
-#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2)
-
-#define BTRFS_QGROUP_STATUS_VERSION 1
-
-struct btrfs_qgroup_status_item {
- __le64 version;
- /*
- * the generation is updated during every commit. As older
- * versions of btrfs are not aware of qgroups, it will be
- * possible to detect inconsistencies by checking the
- * generation on mount time
- */
- __le64 generation;
-
- /* flag definitions see above */
- __le64 flags;
-
- /*
- * only used during scanning to record the progress
- * of the scan. It contains a logical address
- */
- __le64 rescan;
-} __attribute__ ((__packed__));
-
-struct btrfs_qgroup_info_item {
- __le64 generation;
- __le64 rfer;
- __le64 rfer_cmpr;
- __le64 excl;
- __le64 excl_cmpr;
-} __attribute__ ((__packed__));
-
-/* flags definition for qgroup limits */
-#define BTRFS_QGROUP_LIMIT_MAX_RFER (1ULL << 0)
-#define BTRFS_QGROUP_LIMIT_MAX_EXCL (1ULL << 1)
-#define BTRFS_QGROUP_LIMIT_RSV_RFER (1ULL << 2)
-#define BTRFS_QGROUP_LIMIT_RSV_EXCL (1ULL << 3)
-#define BTRFS_QGROUP_LIMIT_RFER_CMPR (1ULL << 4)
-#define BTRFS_QGROUP_LIMIT_EXCL_CMPR (1ULL << 5)
-
-struct btrfs_qgroup_limit_item {
- /*
- * only updated when any of the other values change
- */
- __le64 flags;
- __le64 max_rfer;
- __le64 max_excl;
- __le64 rsv_rfer;
- __le64 rsv_excl;
-} __attribute__ ((__packed__));
-
/* For raid type sysfs entries */
struct raid_kobject {
int raid_type;
@@ -1408,6 +618,27 @@ struct btrfs_block_group_cache {
struct btrfs_io_ctl io_ctl;
+ /*
+ * Incremented when doing extent allocations and holding a read lock
+ * on the space_info's groups_sem semaphore.
+ * Decremented when an ordered extent that represents an IO against this
+ * block group's range is created (after it's added to its inode's
+ * root's list of ordered extents) or immediately after the allocation
+ * if it's a metadata extent or fallocate extent (for these cases we
+ * don't create ordered extents).
+ */
+ atomic_t reservations;
+
+ /*
+ * Incremented while holding the spinlock *lock* by a task checking if
+ * it can perform a nocow write (incremented if the value for the *ro*
+ * field is 0). Decremented by such tasks once they create an ordered
+ * extent or before that if some error happens before reaching that step.
+ * This is to prevent races between block group relocation and nocow
+ * writes through direct IO.
+ */
+ atomic_t nocow_writers;
+
/* Lock for free space tree operations. */
struct mutex free_space_lock;
@@ -2026,228 +1257,6 @@ struct btrfs_root {
atomic_t qgroup_meta_rsv;
};
-struct btrfs_ioctl_defrag_range_args {
- /* start of the defrag operation */
- __u64 start;
-
- /* number of bytes to defrag, use (u64)-1 to say all */
- __u64 len;
-
- /*
- * flags for the operation, which can include turning
- * on compression for this one defrag
- */
- __u64 flags;
-
- /*
- * any extent bigger than this will be considered
- * already defragged. Use 0 to take the kernel default
- * Use 1 to say every single extent must be rewritten
- */
- __u32 extent_thresh;
-
- /*
- * which compression method to use if turning on compression
- * for this defrag operation. If unspecified, zlib will
- * be used
- */
- __u32 compress_type;
-
- /* spare for later */
- __u32 unused[4];
-};
-
-
-/*
- * inode items have the data typically returned from stat and store other
- * info about object characteristics. There is one for every file and dir in
- * the FS
- */
-#define BTRFS_INODE_ITEM_KEY 1
-#define BTRFS_INODE_REF_KEY 12
-#define BTRFS_INODE_EXTREF_KEY 13
-#define BTRFS_XATTR_ITEM_KEY 24
-#define BTRFS_ORPHAN_ITEM_KEY 48
-/* reserve 2-15 close to the inode for later flexibility */
-
-/*
- * dir items are the name -> inode pointers in a directory. There is one
- * for every name in a directory.
- */
-#define BTRFS_DIR_LOG_ITEM_KEY 60
-#define BTRFS_DIR_LOG_INDEX_KEY 72
-#define BTRFS_DIR_ITEM_KEY 84
-#define BTRFS_DIR_INDEX_KEY 96
-/*
- * extent data is for file data
- */
-#define BTRFS_EXTENT_DATA_KEY 108
-
-/*
- * extent csums are stored in a separate tree and hold csums for
- * an entire extent on disk.
- */
-#define BTRFS_EXTENT_CSUM_KEY 128
-
-/*
- * root items point to tree roots. They are typically in the root
- * tree used by the super block to find all the other trees
- */
-#define BTRFS_ROOT_ITEM_KEY 132
-
-/*
- * root backrefs tie subvols and snapshots to the directory entries that
- * reference them
- */
-#define BTRFS_ROOT_BACKREF_KEY 144
-
-/*
- * root refs make a fast index for listing all of the snapshots and
- * subvolumes referenced by a given root. They point directly to the
- * directory item in the root that references the subvol
- */
-#define BTRFS_ROOT_REF_KEY 156
-
-/*
- * extent items are in the extent map tree. These record which blocks
- * are used, and how many references there are to each block
- */
-#define BTRFS_EXTENT_ITEM_KEY 168
-
-/*
- * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know
- * the length, so we save the level in key->offset instead of the length.
- */
-#define BTRFS_METADATA_ITEM_KEY 169
-
-#define BTRFS_TREE_BLOCK_REF_KEY 176
-
-#define BTRFS_EXTENT_DATA_REF_KEY 178
-
-#define BTRFS_EXTENT_REF_V0_KEY 180
-
-#define BTRFS_SHARED_BLOCK_REF_KEY 182
-
-#define BTRFS_SHARED_DATA_REF_KEY 184
-
-/*
- * block groups give us hints into the extent allocation trees. Which
- * blocks are free etc etc
- */
-#define BTRFS_BLOCK_GROUP_ITEM_KEY 192
-
-/*
- * Every block group is represented in the free space tree by a free space info
- * item, which stores some accounting information. It is keyed on
- * (block_group_start, FREE_SPACE_INFO, block_group_length).
- */
-#define BTRFS_FREE_SPACE_INFO_KEY 198
-
-/*
- * A free space extent tracks an extent of space that is free in a block group.
- * It is keyed on (start, FREE_SPACE_EXTENT, length).
- */
-#define BTRFS_FREE_SPACE_EXTENT_KEY 199
-
-/*
- * When a block group becomes very fragmented, we convert it to use bitmaps
- * instead of extents. A free space bitmap is keyed on
- * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with
- * (length / sectorsize) bits.
- */
-#define BTRFS_FREE_SPACE_BITMAP_KEY 200
-
-#define BTRFS_DEV_EXTENT_KEY 204
-#define BTRFS_DEV_ITEM_KEY 216
-#define BTRFS_CHUNK_ITEM_KEY 228
-
-/*
- * Records the overall state of the qgroups.
- * There's only one instance of this key present,
- * (0, BTRFS_QGROUP_STATUS_KEY, 0)
- */
-#define BTRFS_QGROUP_STATUS_KEY 240
-/*
- * Records the currently used space of the qgroup.
- * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid).
- */
-#define BTRFS_QGROUP_INFO_KEY 242
-/*
- * Contains the user configured limits for the qgroup.
- * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid).
- */
-#define BTRFS_QGROUP_LIMIT_KEY 244
-/*
- * Records the child-parent relationship of qgroups. For
- * each relation, 2 keys are present:
- * (childid, BTRFS_QGROUP_RELATION_KEY, parentid)
- * (parentid, BTRFS_QGROUP_RELATION_KEY, childid)
- */
-#define BTRFS_QGROUP_RELATION_KEY 246
-
-/*
- * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
- */
-#define BTRFS_BALANCE_ITEM_KEY 248
-
-/*
- * The key type for tree items that are stored persistently, but do not need to
- * exist for extended period of time. The items can exist in any tree.
- *
- * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
- *
- * Existing items:
- *
- * - balance status item
- * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
- */
-#define BTRFS_TEMPORARY_ITEM_KEY 248
-
-/*
- * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
- */
-#define BTRFS_DEV_STATS_KEY 249
-
-/*
- * The key type for tree items that are stored persistently and usually exist
- * for a long period, eg. filesystem lifetime. The item kinds can be status
- * information, stats or preference values. The item can exist in any tree.
- *
- * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
- *
- * Existing items:
- *
- * - device statistics, store IO stats in the device tree, one key for all
- * stats
- * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
- */
-#define BTRFS_PERSISTENT_ITEM_KEY 249
-
-/*
- * Persistantly stores the device replace state in the device tree.
- * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0).
- */
-#define BTRFS_DEV_REPLACE_KEY 250
-
-/*
- * Stores items that allow to quickly map UUIDs to something else.
- * These items are part of the filesystem UUID tree.
- * The key is built like this:
- * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits).
- */
-#if BTRFS_UUID_SIZE != 16
-#error "UUID items require BTRFS_UUID_SIZE == 16!"
-#endif
-#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */
-#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to
- * received subvols */
-
-/*
- * string items are for debugging. They just store a short string of
- * data in the FS
- */
-#define BTRFS_STRING_ITEM_KEY 253
-
/*
* Flags for mount options.
*
@@ -3499,6 +2508,12 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+ const u64 start);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
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);
@@ -4122,6 +3137,7 @@ void btrfs_test_inode_set_ops(struct inode *inode);
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_update_iflags(struct inode *inode);
void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
@@ -4326,10 +3342,9 @@ static inline void assfail(char *expr, char *file, int line)
#define ASSERT(expr) ((void)0)
#endif
-#define btrfs_assert()
__printf(5, 6)
__cold
-void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
const char *btrfs_decode_error(int errno);
@@ -4339,6 +3354,46 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root, const char *function,
unsigned int line, int errno);
+/*
+ * Call btrfs_abort_transaction as early as possible when an error condition is
+ * detected, that way the exact line number is reported.
+ */
+#define btrfs_abort_transaction(trans, root, errno) \
+do { \
+ /* Report first abort since mount */ \
+ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
+ &((root)->fs_info->fs_state))) { \
+ WARN(1, KERN_DEBUG \
+ "BTRFS: Transaction aborted (error %d)\n", \
+ (errno)); \
+ } \
+ __btrfs_abort_transaction((trans), (root), __func__, \
+ __LINE__, (errno)); \
+} while (0)
+
+#define btrfs_handle_fs_error(fs_info, errno, fmt, args...) \
+do { \
+ __btrfs_handle_fs_error((fs_info), __func__, __LINE__, \
+ (errno), fmt, ##args); \
+} while (0)
+
+__printf(5, 6)
+__cold
+void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+ unsigned int line, int errno, const char *fmt, ...);
+/*
+ * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
+ * will panic(). Otherwise we BUG() here.
+ */
+#define btrfs_panic(fs_info, errno, fmt, args...) \
+do { \
+ __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \
+ BUG(); \
+} while (0)
+
+
+/* compatibility and incompatibility defines */
+
#define btrfs_set_fs_incompat(__fs_info, opt) \
__btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
@@ -4455,44 +3510,6 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag)
return !!(btrfs_super_compat_ro_flags(disk_super) & flag);
}
-/*
- * Call btrfs_abort_transaction as early as possible when an error condition is
- * detected, that way the exact line number is reported.
- */
-#define btrfs_abort_transaction(trans, root, errno) \
-do { \
- /* Report first abort since mount */ \
- if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
- &((root)->fs_info->fs_state))) { \
- WARN(1, KERN_DEBUG \
- "BTRFS: Transaction aborted (error %d)\n", \
- (errno)); \
- } \
- __btrfs_abort_transaction((trans), (root), __func__, \
- __LINE__, (errno)); \
-} while (0)
-
-#define btrfs_std_error(fs_info, errno, fmt, args...) \
-do { \
- __btrfs_std_error((fs_info), __func__, __LINE__, \
- (errno), fmt, ##args); \
-} while (0)
-
-__printf(5, 6)
-__cold
-void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
- unsigned int line, int errno, const char *fmt, ...);
-
-/*
- * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
- * will panic(). Otherwise we BUG() here.
- */
-#define btrfs_panic(fs_info, errno, fmt, args...) \
-do { \
- __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \
- BUG(); \
-} while (0)
-
/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6cef0062f929..61561c2a3f96 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -134,7 +134,7 @@ again:
/* cached in the btrfs inode and can be accessed */
atomic_add(2, &node->refs);
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret) {
kmem_cache_free(delayed_node_cache, node);
return ERR_PTR(ret);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 26bcb487f958..85f12e6e28d2 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -44,9 +44,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev,
struct btrfs_device *tgtdev);
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
- char *srcdev_name,
- struct btrfs_device **device);
static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
static int btrfs_dev_replace_kthread(void *data);
static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);
@@ -305,8 +302,8 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
dev_replace->cursor_left_last_write_of_item;
}
-int btrfs_dev_replace_start(struct btrfs_root *root,
- struct btrfs_ioctl_dev_replace_args *args)
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
+ u64 srcdevid, char *srcdev_name, int read_src)
{
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = root->fs_info;
@@ -315,29 +312,16 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
struct btrfs_device *tgt_device = NULL;
struct btrfs_device *src_device = NULL;
- switch (args->start.cont_reading_from_srcdev_mode) {
- case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
- case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
- break;
- default:
- return -EINVAL;
- }
-
- if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
- args->start.tgtdev_name[0] == '\0')
- return -EINVAL;
-
/* the disk copy procedure reuses the scrub code */
mutex_lock(&fs_info->volume_mutex);
- ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
- args->start.srcdev_name,
- &src_device);
+ ret = btrfs_find_device_by_devspec(root, srcdevid,
+ srcdev_name, &src_device);
if (ret) {
mutex_unlock(&fs_info->volume_mutex);
return ret;
}
- ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
+ ret = btrfs_init_dev_replace_tgtdev(root, tgtdev_name,
src_device, &tgt_device);
mutex_unlock(&fs_info->volume_mutex);
if (ret)
@@ -364,18 +348,17 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
- args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
+ ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
goto leave;
}
- dev_replace->cont_reading_from_srcdev_mode =
- args->start.cont_reading_from_srcdev_mode;
+ dev_replace->cont_reading_from_srcdev_mode = read_src;
WARN_ON(!src_device);
dev_replace->srcdev = src_device;
WARN_ON(!tgt_device);
dev_replace->tgtdev = tgt_device;
- btrfs_info_in_rcu(root->fs_info,
+ btrfs_info_in_rcu(fs_info,
"dev_replace from %s (devid %llu) to %s started",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
@@ -396,14 +379,13 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
dev_replace->item_needs_writeback = 1;
atomic64_set(&dev_replace->num_write_errors, 0);
atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
- args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
btrfs_dev_replace_unlock(dev_replace, 1);
ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
if (ret)
- btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
+ btrfs_err(fs_info, "kobj add dev failed %d\n", ret);
- btrfs_wait_ordered_roots(root->fs_info, -1);
+ btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
/* force writing the updated state information to disk */
trans = btrfs_start_transaction(root, 0);
@@ -421,11 +403,9 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
btrfs_device_get_total_bytes(src_device),
&dev_replace->scrub_progress, 0, 1);
- ret = btrfs_dev_replace_finishing(root->fs_info, ret);
- /* don't warn if EINPROGRESS, someone else might be running scrub */
+ ret = btrfs_dev_replace_finishing(fs_info, ret);
if (ret == -EINPROGRESS) {
- args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
- ret = 0;
+ ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
} else {
WARN_ON(ret);
}
@@ -440,6 +420,35 @@ leave:
return ret;
}
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
+ struct btrfs_ioctl_dev_replace_args *args)
+{
+ int ret;
+
+ switch (args->start.cont_reading_from_srcdev_mode) {
+ case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
+ case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
+ args->start.tgtdev_name[0] == '\0')
+ return -EINVAL;
+
+ ret = btrfs_dev_replace_start(root, args->start.tgtdev_name,
+ args->start.srcdevid,
+ args->start.srcdev_name,
+ args->start.cont_reading_from_srcdev_mode);
+ args->result = ret;
+ /* don't warn if EINPROGRESS, someone else might be running scrub */
+ if (ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS)
+ ret = 0;
+
+ return ret;
+}
+
/*
* blocked until all flighting bios are finished.
*/
@@ -495,7 +504,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return ret;
}
- btrfs_wait_ordered_roots(root->fs_info, -1);
+ btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
@@ -560,10 +569,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
ASSERT(list_empty(&src_device->resized_list));
tgt_device->commit_total_bytes = src_device->commit_total_bytes;
tgt_device->commit_bytes_used = src_device->bytes_used;
- if (fs_info->sb->s_bdev == src_device->bdev)
- fs_info->sb->s_bdev = tgt_device->bdev;
- if (fs_info->fs_devices->latest_bdev == src_device->bdev)
- fs_info->fs_devices->latest_bdev = tgt_device->bdev;
+
+ btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
+
list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
fs_info->fs_devices->rw_devices++;
@@ -626,25 +634,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
write_unlock(&em_tree->lock);
}
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
- char *srcdev_name,
- struct btrfs_device **device)
-{
- int ret;
-
- if (srcdevid) {
- ret = 0;
- *device = btrfs_find_device(root->fs_info, srcdevid, NULL,
- NULL);
- if (!*device)
- ret = -ENOENT;
- } else {
- ret = btrfs_find_device_missing_or_by_path(root, srcdev_name,
- device);
- }
- return ret;
-}
-
void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_dev_replace_args *args)
{
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 29e3ef5f96bd..e922b42d91df 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -25,8 +25,10 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info);
int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_start(struct btrfs_root *root,
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
struct btrfs_ioctl_dev_replace_args *args);
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
+ u64 srcdevid, char *srcdev_name, int read_src);
void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_dev_replace_args *args);
int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4e47849d7427..91d123938cef 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1640,7 +1640,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
{
int ret;
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret)
return ret;
@@ -2417,7 +2417,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
/* returns with log_tree_root freed on success */
ret = btrfs_recover_log_trees(log_tree_root);
if (ret) {
- btrfs_std_error(tree_root->fs_info, ret,
+ btrfs_handle_fs_error(tree_root->fs_info, ret,
"Failed to recover log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
@@ -2517,6 +2517,7 @@ 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);
@@ -2713,7 +2714,7 @@ int open_ctree(struct super_block *sb,
* Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
*/
if (btrfs_check_super_csum(bh->b_data)) {
- printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
+ btrfs_err(fs_info, "superblock checksum mismatch");
err = -EINVAL;
brelse(bh);
goto fail_alloc;
@@ -2733,7 +2734,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
if (ret) {
- printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
+ btrfs_err(fs_info, "superblock contains fatal errors");
err = -EINVAL;
goto fail_alloc;
}
@@ -2768,9 +2769,9 @@ int open_ctree(struct super_block *sb,
features = btrfs_super_incompat_flags(disk_super) &
~BTRFS_FEATURE_INCOMPAT_SUPP;
if (features) {
- printk(KERN_ERR "BTRFS: couldn't mount because of "
- "unsupported optional features (%Lx).\n",
- features);
+ btrfs_err(fs_info,
+ "cannot mount because of unsupported optional features (%llx)",
+ features);
err = -EINVAL;
goto fail_alloc;
}
@@ -2781,7 +2782,7 @@ int open_ctree(struct super_block *sb,
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
- printk(KERN_INFO "BTRFS: has skinny extents\n");
+ btrfs_info(fs_info, "has skinny extents");
/*
* flag our filesystem as having big metadata blocks if
@@ -2789,7 +2790,8 @@ int open_ctree(struct super_block *sb,
*/
if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
+ btrfs_info(fs_info,
+ "flagging fs with big metadata feature");
features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
}
@@ -2805,9 +2807,9 @@ int open_ctree(struct super_block *sb,
*/
if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
(sectorsize != nodesize)) {
- printk(KERN_ERR "BTRFS: unequal leaf/node/sector sizes "
- "are not allowed for mixed block groups on %s\n",
- sb->s_id);
+ btrfs_err(fs_info,
+"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups",
+ nodesize, sectorsize);
goto fail_alloc;
}
@@ -2820,8 +2822,8 @@ int open_ctree(struct super_block *sb,
features = btrfs_super_compat_ro_flags(disk_super) &
~BTRFS_FEATURE_COMPAT_RO_SUPP;
if (!(sb->s_flags & MS_RDONLY) && features) {
- printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
- "unsupported option features (%Lx).\n",
+ btrfs_err(fs_info,
+ "cannot mount read-write because of unsupported optional features (%llx)",
features);
err = -EINVAL;
goto fail_alloc;
@@ -2850,8 +2852,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to read the system "
- "array on %s\n", sb->s_id);
+ btrfs_err(fs_info, "failed to read the system array: %d", ret);
goto fail_sb_buffer;
}
@@ -2865,8 +2866,7 @@ int open_ctree(struct super_block *sb,
generation);
if (IS_ERR(chunk_root->node) ||
!extent_buffer_uptodate(chunk_root->node)) {
- printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read chunk root");
if (!IS_ERR(chunk_root->node))
free_extent_buffer(chunk_root->node);
chunk_root->node = NULL;
@@ -2880,8 +2880,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to read chunk tree on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read chunk tree: %d", ret);
goto fail_tree_roots;
}
@@ -2892,8 +2891,7 @@ int open_ctree(struct super_block *sb,
btrfs_close_extra_devices(fs_devices, 0);
if (!fs_devices->latest_bdev) {
- printk(KERN_ERR "BTRFS: failed to read devices on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read devices");
goto fail_tree_roots;
}
@@ -2905,8 +2903,7 @@ retry_root_backup:
generation);
if (IS_ERR(tree_root->node) ||
!extent_buffer_uptodate(tree_root->node)) {
- printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
- sb->s_id);
+ btrfs_warn(fs_info, "failed to read tree root");
if (!IS_ERR(tree_root->node))
free_extent_buffer(tree_root->node);
tree_root->node = NULL;
@@ -2938,20 +2935,19 @@ retry_root_backup:
ret = btrfs_recover_balance(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to recover balance\n");
+ btrfs_err(fs_info, "failed to recover balance: %d", ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
- ret);
+ btrfs_err(fs_info, "failed to init dev_stats: %d", ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_replace(fs_info);
if (ret) {
- pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
+ btrfs_err(fs_info, "failed to init dev_replace: %d", ret);
goto fail_block_groups;
}
@@ -2959,31 +2955,33 @@ retry_root_backup:
ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
if (ret) {
- pr_err("BTRFS: failed to init sysfs fsid interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
+ ret);
goto fail_block_groups;
}
ret = btrfs_sysfs_add_device(fs_devices);
if (ret) {
- pr_err("BTRFS: failed to init sysfs device interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs device interface: %d",
+ ret);
goto fail_fsdev_sysfs;
}
ret = btrfs_sysfs_add_mounted(fs_info);
if (ret) {
- pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
goto fail_fsdev_sysfs;
}
ret = btrfs_init_space_info(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
+ btrfs_err(fs_info, "failed to initialize space info: %d", ret);
goto fail_sysfs;
}
ret = btrfs_read_block_groups(fs_info->extent_root);
if (ret) {
- printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+ btrfs_err(fs_info, "failed to read block groups: %d", ret);
goto fail_sysfs;
}
fs_info->num_tolerated_disk_barrier_failures =
@@ -2991,12 +2989,20 @@ retry_root_backup:
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(sb->s_flags & MS_RDONLY)) {
- pr_warn("BTRFS: missing devices(%llu) exceeds the limit(%d), writeable mount is not allowed\n",
+ btrfs_warn(fs_info,
+"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed",
fs_info->fs_devices->missing_devices,
fs_info->num_tolerated_disk_barrier_failures);
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))
@@ -3011,8 +3017,7 @@ retry_root_backup:
if (!btrfs_test_opt(tree_root, SSD) &&
!btrfs_test_opt(tree_root, NOSSD) &&
!fs_info->fs_devices->rotating) {
- printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
- "mode\n");
+ btrfs_info(fs_info, "detected SSD devices, enabling SSD mode");
btrfs_set_opt(fs_info->mount_opt, SSD);
}
@@ -3030,8 +3035,9 @@ retry_root_backup:
1 : 0,
fs_info->check_integrity_print_mask);
if (ret)
- printk(KERN_WARNING "BTRFS: failed to initialize"
- " integrity check module %s\n", sb->s_id);
+ btrfs_warn(fs_info,
+ "failed to initialize integrity check module: %d",
+ ret);
}
#endif
ret = btrfs_read_qgroup_config(fs_info);
@@ -3056,17 +3062,17 @@ retry_root_backup:
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto fail_qgroup;
-
- mutex_lock(&fs_info->cleaner_mutex);
+ /* We locked cleaner_mutex before creating cleaner_kthread. */
ret = btrfs_recover_relocation(tree_root);
- mutex_unlock(&fs_info->cleaner_mutex);
if (ret < 0) {
- printk(KERN_WARNING
- "BTRFS: failed to recover relocation\n");
+ btrfs_warn(fs_info, "failed to recover relocation: %d",
+ ret);
err = -EINVAL;
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;
@@ -3083,11 +3089,11 @@ retry_root_backup:
if (btrfs_test_opt(tree_root, FREE_SPACE_TREE) &&
!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- pr_info("BTRFS: creating free space tree\n");
+ btrfs_info(fs_info, "creating free space tree");
ret = btrfs_create_free_space_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to create free space tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to create free space tree: %d", ret);
close_ctree(tree_root);
return ret;
}
@@ -3104,14 +3110,14 @@ retry_root_backup:
ret = btrfs_resume_balance_async(fs_info);
if (ret) {
- printk(KERN_WARNING "BTRFS: failed to resume balance\n");
+ btrfs_warn(fs_info, "failed to resume balance: %d", ret);
close_ctree(tree_root);
return ret;
}
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to resume dev_replace\n");
+ btrfs_warn(fs_info, "failed to resume device replace: %d", ret);
close_ctree(tree_root);
return ret;
}
@@ -3120,33 +3126,33 @@ retry_root_backup:
if (btrfs_test_opt(tree_root, CLEAR_CACHE) &&
btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- pr_info("BTRFS: clearing free space tree\n");
+ btrfs_info(fs_info, "clearing free space tree");
ret = btrfs_clear_free_space_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to clear free space tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to clear free space tree: %d", ret);
close_ctree(tree_root);
return ret;
}
}
if (!fs_info->uuid_root) {
- pr_info("BTRFS: creating UUID tree\n");
+ btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to create the UUID tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to create the UUID tree: %d", ret);
close_ctree(tree_root);
return ret;
}
} else if (btrfs_test_opt(tree_root, RESCAN_UUID_TREE) ||
fs_info->generation !=
btrfs_super_uuid_tree_generation(disk_super)) {
- pr_info("BTRFS: checking UUID tree\n");
+ btrfs_info(fs_info, "checking UUID tree");
ret = btrfs_check_uuid_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to check the UUID tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to check the UUID tree: %d", ret);
close_ctree(tree_root);
return ret;
}
@@ -3180,6 +3186,10 @@ 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:
@@ -3646,7 +3656,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
if (ret) {
mutex_unlock(
&root->fs_info->fs_devices->device_list_mutex);
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"errors while submitting device barriers.");
return ret;
}
@@ -3686,7 +3696,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
/* FUA is masked off if unsupported and can't be the reason */
- btrfs_std_error(root->fs_info, -EIO,
+ btrfs_handle_fs_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
@@ -3704,7 +3714,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
}
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (total_errors > max_errors) {
- btrfs_std_error(root->fs_info, -EIO,
+ btrfs_handle_fs_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 84e060eb0de8..9424864fd01a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3824,6 +3824,59 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
return readonly;
}
+bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+ struct btrfs_block_group_cache *bg;
+ bool ret = true;
+
+ bg = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!bg)
+ return false;
+
+ spin_lock(&bg->lock);
+ if (bg->ro)
+ ret = false;
+ else
+ atomic_inc(&bg->nocow_writers);
+ spin_unlock(&bg->lock);
+
+ /* no put on block group, done by btrfs_dec_nocow_writers */
+ if (!ret)
+ btrfs_put_block_group(bg);
+
+ return ret;
+
+}
+
+void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+ struct btrfs_block_group_cache *bg;
+
+ bg = btrfs_lookup_block_group(fs_info, bytenr);
+ ASSERT(bg);
+ if (atomic_dec_and_test(&bg->nocow_writers))
+ wake_up_atomic_t(&bg->nocow_writers);
+ /*
+ * Once for our lookup and once for the lookup done by a previous call
+ * to btrfs_inc_nocow_writers()
+ */
+ btrfs_put_block_group(bg);
+ btrfs_put_block_group(bg);
+}
+
+static int btrfs_wait_nocow_writers_atomic_t(atomic_t *a)
+{
+ schedule();
+ return 0;
+}
+
+void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
+{
+ wait_on_atomic_t(&bg->nocow_writers,
+ btrfs_wait_nocow_writers_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+}
+
static const char *alloc_name(u64 flags)
{
switch (flags) {
@@ -4141,7 +4194,7 @@ commit_trans:
if (need_commit > 0) {
btrfs_start_delalloc_roots(fs_info, 0, -1);
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
}
trans = btrfs_join_transaction(root);
@@ -4583,7 +4636,8 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root,
*/
btrfs_start_delalloc_roots(root->fs_info, 0, nr_items);
if (!current->journal_info)
- btrfs_wait_ordered_roots(root->fs_info, nr_items);
+ btrfs_wait_ordered_roots(root->fs_info, nr_items,
+ 0, (u64)-1);
}
}
@@ -4620,7 +4674,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
/* Calc the number of the pages we need flush for space reservation */
items = calc_reclaim_items_nr(root, to_reclaim);
- to_reclaim = items * EXTENT_SIZE_PER_ITEM;
+ to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM;
trans = (struct btrfs_trans_handle *)current->journal_info;
block_rsv = &root->fs_info->delalloc_block_rsv;
@@ -4632,7 +4686,8 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
if (trans)
return;
if (wait_ordered)
- btrfs_wait_ordered_roots(root->fs_info, items);
+ btrfs_wait_ordered_roots(root->fs_info, items,
+ 0, (u64)-1);
return;
}
@@ -4671,7 +4726,8 @@ skip_async:
loops++;
if (wait_ordered && !trans) {
- btrfs_wait_ordered_roots(root->fs_info, items);
+ btrfs_wait_ordered_roots(root->fs_info, items,
+ 0, (u64)-1);
} else {
time_left = schedule_timeout_killable(1);
if (time_left)
@@ -6172,6 +6228,57 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log,
return 0;
}
+static void
+btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
+{
+ atomic_inc(&bg->reservations);
+}
+
+void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+ const u64 start)
+{
+ struct btrfs_block_group_cache *bg;
+
+ bg = btrfs_lookup_block_group(fs_info, start);
+ ASSERT(bg);
+ if (atomic_dec_and_test(&bg->reservations))
+ wake_up_atomic_t(&bg->reservations);
+ btrfs_put_block_group(bg);
+}
+
+static int btrfs_wait_bg_reservations_atomic_t(atomic_t *a)
+{
+ schedule();
+ return 0;
+}
+
+void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
+{
+ struct btrfs_space_info *space_info = bg->space_info;
+
+ ASSERT(bg->ro);
+
+ if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA))
+ return;
+
+ /*
+ * Our block group is read only but before we set it to read only,
+ * some task might have had allocated an extent from it already, but it
+ * has not yet created a respective ordered extent (and added it to a
+ * root's list of ordered extents).
+ * Therefore wait for any task currently allocating extents, since the
+ * block group's reservations counter is incremented while a read lock
+ * on the groups' semaphore is held and decremented after releasing
+ * the read access on that semaphore and creating the ordered extent.
+ */
+ down_write(&space_info->groups_sem);
+ up_write(&space_info->groups_sem);
+
+ wait_on_atomic_t(&bg->reservations,
+ btrfs_wait_bg_reservations_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+}
+
/**
* btrfs_update_reserved_bytes - update the block_group and space info counters
* @cache: The cache we are manipulating
@@ -7025,36 +7132,35 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
int delalloc)
{
struct btrfs_block_group_cache *used_bg = NULL;
- bool locked = false;
-again:
+
spin_lock(&cluster->refill_lock);
- if (locked) {
- if (used_bg == cluster->block_group)
+ while (1) {
+ used_bg = cluster->block_group;
+ if (!used_bg)
+ return NULL;
+
+ if (used_bg == block_group)
return used_bg;
- up_read(&used_bg->data_rwsem);
- btrfs_put_block_group(used_bg);
- }
+ btrfs_get_block_group(used_bg);
- used_bg = cluster->block_group;
- if (!used_bg)
- return NULL;
+ if (!delalloc)
+ return used_bg;
- if (used_bg == block_group)
- return used_bg;
+ if (down_read_trylock(&used_bg->data_rwsem))
+ return used_bg;
- btrfs_get_block_group(used_bg);
+ spin_unlock(&cluster->refill_lock);
- if (!delalloc)
- return used_bg;
+ down_read(&used_bg->data_rwsem);
- if (down_read_trylock(&used_bg->data_rwsem))
- return used_bg;
+ spin_lock(&cluster->refill_lock);
+ if (used_bg == cluster->block_group)
+ return used_bg;
- spin_unlock(&cluster->refill_lock);
- down_read(&used_bg->data_rwsem);
- locked = true;
- goto again;
+ up_read(&used_bg->data_rwsem);
+ btrfs_put_block_group(used_bg);
+ }
}
static inline void
@@ -7431,6 +7537,7 @@ checks:
btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
}
+ btrfs_inc_block_group_reservations(block_group);
/* we are all good, lets return */
ins->objectid = search_start;
@@ -7612,8 +7719,10 @@ again:
WARN_ON(num_bytes < root->sectorsize);
ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
flags, delalloc);
-
- if (ret == -ENOSPC) {
+ if (!ret && !is_data) {
+ btrfs_dec_block_group_reservations(root->fs_info,
+ ins->objectid);
+ } else if (ret == -ENOSPC) {
if (!final_tried && ins->offset) {
num_bytes = min(num_bytes >> 1, ins->offset);
num_bytes = round_down(num_bytes, root->sectorsize);
@@ -9058,7 +9167,7 @@ out:
if (!for_reloc && root_dropped == false)
btrfs_add_dead_root(root);
if (err && err != -EAGAIN)
- btrfs_std_error(root->fs_info, err, NULL);
+ btrfs_handle_fs_error(root->fs_info, err, NULL);
return err;
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d247fc0eea19..2f83448d34fe 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3200,14 +3200,10 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
return ret;
}
-static noinline void update_nr_written(struct page *page,
- struct writeback_control *wbc,
- unsigned long nr_written)
+static void update_nr_written(struct page *page, struct writeback_control *wbc,
+ unsigned long nr_written)
{
wbc->nr_to_write -= nr_written;
- if (wbc->range_cyclic || (wbc->nr_to_write > 0 &&
- wbc->range_start == 0 && wbc->range_end == LLONG_MAX))
- page->mapping->writeback_index = page->index + nr_written;
}
/*
@@ -3368,6 +3364,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
while (cur <= end) {
u64 em_end;
+ unsigned long max_nr;
+
if (cur >= i_size) {
if (tree->ops && tree->ops->writepage_end_io_hook)
tree->ops->writepage_end_io_hook(page, cur,
@@ -3423,32 +3421,23 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
continue;
}
- if (tree->ops && tree->ops->writepage_io_hook) {
- ret = tree->ops->writepage_io_hook(page, cur,
- cur + iosize - 1);
- } else {
- ret = 0;
+ max_nr = (i_size >> PAGE_SHIFT) + 1;
+
+ set_range_writeback(tree, cur, cur + iosize - 1);
+ if (!PageWriteback(page)) {
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "page %lu not writeback, cur %llu end %llu",
+ page->index, cur, end);
}
- if (ret) {
- SetPageError(page);
- } else {
- unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1;
- set_range_writeback(tree, cur, cur + iosize - 1);
- if (!PageWriteback(page)) {
- btrfs_err(BTRFS_I(inode)->root->fs_info,
- "page %lu not writeback, cur %llu end %llu",
- page->index, cur, end);
- }
+ ret = submit_extent_page(write_flags, tree, wbc, page,
+ sector, iosize, pg_offset,
+ bdev, &epd->bio, max_nr,
+ end_bio_extent_writepage,
+ 0, 0, 0, false);
+ if (ret)
+ SetPageError(page);
- ret = submit_extent_page(write_flags, tree, wbc, page,
- sector, iosize, pg_offset,
- bdev, &epd->bio, max_nr,
- end_bio_extent_writepage,
- 0, 0, 0, false);
- if (ret)
- SetPageError(page);
- }
cur = cur + iosize;
pg_offset += iosize;
nr++;
@@ -3920,12 +3909,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
struct inode *inode = mapping->host;
int ret = 0;
int done = 0;
- int err = 0;
int nr_to_write_done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
+ pgoff_t done_index;
+ int range_whole = 0;
int scanned = 0;
int tag;
@@ -3948,6 +3938,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
+ if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+ range_whole = 1;
scanned = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL)
@@ -3957,6 +3949,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
+ done_index = index;
while (!done && !nr_to_write_done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
@@ -3966,6 +3959,7 @@ retry:
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ done_index = page->index;
/*
* At this point we hold neither mapping->tree_lock nor
* lock on the page itself: the page may be truncated or
@@ -4007,8 +4001,20 @@ retry:
unlock_page(page);
ret = 0;
}
- if (!err && ret < 0)
- err = ret;
+ if (ret < 0) {
+ /*
+ * done_index is set past this page,
+ * so media errors will not choke
+ * background writeout for the entire
+ * file. This has consequences for
+ * range_cyclic semantics (ie. it may
+ * not be suitable for data integrity
+ * writeout).
+ */
+ done_index = page->index + 1;
+ done = 1;
+ break;
+ }
/*
* the filesystem may choose to bump up nr_to_write.
@@ -4020,7 +4026,7 @@ retry:
pagevec_release(&pvec);
cond_resched();
}
- if (!scanned && !done && !err) {
+ if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
@@ -4029,8 +4035,12 @@ retry:
index = 0;
goto retry;
}
+
+ if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
+ mapping->writeback_index = done_index;
+
btrfs_add_delayed_iput(inode);
- return err;
+ return ret;
}
static void flush_epd_write_bio(struct extent_page_data *epd)
@@ -4822,7 +4832,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
return NULL;
eb->fs_info = fs_info;
again:
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret)
goto free_eb;
spin_lock(&fs_info->buffer_lock);
@@ -4923,7 +4933,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
again:
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret)
goto free_eb;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index b5e0ade90e88..981f402bf754 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -71,7 +71,6 @@ struct extent_io_ops {
u64 start, u64 end, int *page_started,
unsigned long *nr_written);
int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
- int (*writepage_io_hook)(struct page *page, u64 start, u64 end);
extent_submit_bio_hook_t *submit_bio_hook;
int (*merge_bio_hook)(int rw, struct page *page, unsigned long offset,
size_t size, struct bio *bio,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 8d7b5a45c005..c98805c35bab 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1696,25 +1696,26 @@ again:
btrfs_end_write_no_snapshoting(root);
btrfs_delalloc_release_metadata(inode, release_bytes);
} else {
- btrfs_delalloc_release_space(inode, pos, release_bytes);
+ btrfs_delalloc_release_space(inode,
+ round_down(pos, root->sectorsize),
+ release_bytes);
}
}
return num_written ? num_written : ret;
}
-static ssize_t __btrfs_direct_write(struct kiocb *iocb,
- struct iov_iter *from,
- loff_t pos)
+static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
+ loff_t pos = iocb->ki_pos;
ssize_t written;
ssize_t written_buffered;
loff_t endbyte;
int err;
- written = generic_file_direct_write(iocb, from, pos);
+ written = generic_file_direct_write(iocb, from);
if (written < 0 || !iov_iter_count(from))
return written;
@@ -1832,7 +1833,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
atomic_inc(&BTRFS_I(inode)->sync_writers);
if (iocb->ki_flags & IOCB_DIRECT) {
- num_written = __btrfs_direct_write(iocb, from, pos);
+ num_written = __btrfs_direct_write(iocb, from);
} else {
num_written = __btrfs_buffered_write(file, from, pos);
if (num_written > 0)
@@ -1852,11 +1853,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->last_sub_trans = root->log_transid;
spin_unlock(&BTRFS_I(inode)->lock);
- if (num_written > 0) {
- err = generic_write_sync(file, pos, num_written);
- if (err < 0)
- num_written = err;
- }
+ if (num_written > 0)
+ num_written = generic_write_sync(iocb, num_written);
if (sync)
atomic_dec(&BTRFS_I(inode)->sync_writers);
@@ -2956,7 +2954,7 @@ const struct file_operations btrfs_file_operations = {
.fallocate = btrfs_fallocate,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
- .compat_ioctl = btrfs_ioctl,
+ .compat_ioctl = btrfs_compat_ioctl,
#endif
.copy_file_range = btrfs_copy_file_range,
.clone_file_range = btrfs_clone_file_range,
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index be4d22a5022f..b8acc07ac6c2 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -157,7 +157,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
*/
if (!btrfs_find_name_in_ext_backref(path, ref_objectid,
name, name_len, &extref)) {
- btrfs_std_error(root->fs_info, -ENOENT, NULL);
+ btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL);
ret = -EROFS;
goto out;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2aaba58b4856..91419ef79b00 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -824,6 +824,7 @@ retry:
async_extent->ram_size - 1, 0);
goto out_free_reserve;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
/*
* clear dirty, set writeback and unlock the pages.
@@ -861,6 +862,7 @@ retry:
}
return;
out_free_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
@@ -1038,6 +1040,8 @@ static noinline int cow_file_range(struct inode *inode,
goto out_drop_extent_cache;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+
if (disk_num_bytes < cur_alloc_size)
break;
@@ -1066,6 +1070,7 @@ out:
out_drop_extent_cache:
btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
out_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_unlock:
extent_clear_unlock_delalloc(inode, start, end, locked_page,
@@ -1377,6 +1382,9 @@ next_slot:
*/
if (csum_exist_in_range(root, disk_bytenr, num_bytes))
goto out_check;
+ if (!btrfs_inc_nocow_writers(root->fs_info,
+ disk_bytenr))
+ goto out_check;
nocow = 1;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
extent_end = found_key.offset +
@@ -1391,6 +1399,9 @@ out_check:
path->slots[0]++;
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info,
+ disk_bytenr);
goto next_slot;
}
if (!nocow) {
@@ -1411,6 +1422,9 @@ out_check:
if (ret) {
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info,
+ disk_bytenr);
goto error;
}
cow_start = (u64)-1;
@@ -1453,6 +1467,8 @@ out_check:
ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
num_bytes, num_bytes, type);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info, disk_bytenr);
BUG_ON(ret); /* -ENOMEM */
if (root->root_key.objectid ==
@@ -7129,6 +7145,43 @@ out:
return em;
}
+static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
+ const u64 start,
+ const u64 len,
+ const u64 orig_start,
+ const u64 block_start,
+ const u64 block_len,
+ const u64 orig_block_len,
+ const u64 ram_bytes,
+ const int type)
+{
+ struct extent_map *em = NULL;
+ int ret;
+
+ down_read(&BTRFS_I(inode)->dio_sem);
+ if (type != BTRFS_ORDERED_NOCOW) {
+ em = create_pinned_em(inode, start, len, orig_start,
+ block_start, block_len, orig_block_len,
+ ram_bytes, type);
+ if (IS_ERR(em))
+ goto out;
+ }
+ ret = btrfs_add_ordered_extent_dio(inode, start, block_start,
+ len, block_len, type);
+ if (ret) {
+ if (em) {
+ free_extent_map(em);
+ btrfs_drop_extent_cache(inode, start,
+ start + len - 1, 0);
+ }
+ em = ERR_PTR(ret);
+ }
+ out:
+ up_read(&BTRFS_I(inode)->dio_sem);
+
+ return em;
+}
+
static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
u64 start, u64 len)
{
@@ -7144,41 +7197,13 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
if (ret)
return ERR_PTR(ret);
- /*
- * Create the ordered extent before the extent map. This is to avoid
- * races with the fast fsync path that would lead to it logging file
- * extent items that point to disk extents that were not yet written to.
- * The fast fsync path collects ordered extents into a local list and
- * then collects all the new extent maps, so we must create the ordered
- * extent first and make sure the fast fsync path collects any new
- * ordered extents after collecting new extent maps as well.
- * The fsync path simply can not rely on inode_dio_wait() because it
- * causes deadlock with AIO.
- */
- ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
- ins.offset, ins.offset, 0);
- if (ret) {
+ em = btrfs_create_dio_extent(inode, start, ins.offset, start,
+ ins.objectid, ins.offset, ins.offset,
+ ins.offset, 0);
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+ if (IS_ERR(em))
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- return ERR_PTR(ret);
- }
-
- em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
- ins.offset, ins.offset, ins.offset, 0);
- if (IS_ERR(em)) {
- struct btrfs_ordered_extent *oe;
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- oe = btrfs_lookup_ordered_extent(inode, start);
- ASSERT(oe);
- if (WARN_ON(!oe))
- return em;
- set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
- set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
- btrfs_remove_ordered_extent(inode, oe);
- /* Once for our lookup and once for the ordered extents tree. */
- btrfs_put_ordered_extent(oe);
- btrfs_put_ordered_extent(oe);
- }
return em;
}
@@ -7650,24 +7675,21 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
block_start = em->block_start + (start - em->start);
if (can_nocow_extent(inode, start, &len, &orig_start,
- &orig_block_len, &ram_bytes) == 1) {
+ &orig_block_len, &ram_bytes) == 1 &&
+ btrfs_inc_nocow_writers(root->fs_info, block_start)) {
+ struct extent_map *em2;
+
+ em2 = btrfs_create_dio_extent(inode, start, len,
+ orig_start, block_start,
+ len, orig_block_len,
+ ram_bytes, type);
+ btrfs_dec_nocow_writers(root->fs_info, block_start);
if (type == BTRFS_ORDERED_PREALLOC) {
free_extent_map(em);
- em = create_pinned_em(inode, start, len,
- orig_start,
- block_start, len,
- orig_block_len,
- ram_bytes, type);
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto unlock_err;
- }
+ em = em2;
}
-
- ret = btrfs_add_ordered_extent_dio(inode, start,
- block_start, len, len, type);
- if (ret) {
- free_extent_map(em);
+ if (em2 && IS_ERR(em2)) {
+ ret = PTR_ERR(em2);
goto unlock_err;
}
goto unlock;
@@ -8541,13 +8563,13 @@ out:
return retval;
}
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_dio_data dio_data = { 0 };
+ loff_t offset = iocb->ki_pos;
size_t count = 0;
int flags = 0;
bool wakeup = true;
@@ -8607,7 +8629,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
ret = __blockdev_direct_IO(iocb, inode,
BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iter, offset, btrfs_get_blocks_direct, NULL,
+ iter, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (iov_iter_rw(iter) == WRITE) {
current->journal_info = NULL;
@@ -9230,6 +9252,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
RB_CLEAR_NODE(&ei->rb_node);
+ init_rwsem(&ei->dio_sem);
return inode;
}
@@ -9387,10 +9410,281 @@ static int btrfs_getattr(struct vfsmount *mnt,
return 0;
}
+static int btrfs_rename_exchange(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(old_dir)->root;
+ struct btrfs_root *dest = BTRFS_I(new_dir)->root;
+ struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = old_dentry->d_inode;
+ struct timespec ctime = CURRENT_TIME;
+ struct dentry *parent;
+ u64 old_ino = btrfs_ino(old_inode);
+ u64 new_ino = btrfs_ino(new_inode);
+ u64 old_idx = 0;
+ u64 new_idx = 0;
+ u64 root_objectid;
+ int ret;
+ bool root_log_pinned = false;
+ bool dest_log_pinned = false;
+
+ /* we only allow rename subvolume link between subvolumes */
+ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+ return -EXDEV;
+
+ /* close the race window with snapshot create/destroy ioctl */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&root->fs_info->subvol_sem);
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&dest->fs_info->subvol_sem);
+
+ /*
+ * We want to reserve the absolute worst case amount of items. So if
+ * both inodes are subvols and we need to unlink them then that would
+ * require 4 item modifications, but if they are both normal inodes it
+ * would require 5 item modifications, so we'll assume their normal
+ * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items
+ * should cover the worst case number of items we'll modify.
+ */
+ trans = btrfs_start_transaction(root, 12);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
+
+ /*
+ * We need to find a free sequence number both in the source and
+ * in the destination directory for the exchange.
+ */
+ ret = btrfs_set_inode_index(new_dir, &old_idx);
+ if (ret)
+ goto out_fail;
+ ret = btrfs_set_inode_index(old_dir, &new_idx);
+ if (ret)
+ goto out_fail;
+
+ BTRFS_I(old_inode)->dir_index = 0ULL;
+ BTRFS_I(new_inode)->dir_index = 0ULL;
+
+ /* Reference for the source. */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(root->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(root);
+ root_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, dest,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len,
+ old_ino,
+ btrfs_ino(new_dir), old_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* And now for the dest. */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(dest->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(dest);
+ dest_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, root,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len,
+ new_ino,
+ btrfs_ino(old_dir), new_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* Update inode version and ctime/mtime. */
+ inode_inc_iversion(old_dir);
+ inode_inc_iversion(new_dir);
+ inode_inc_iversion(old_inode);
+ inode_inc_iversion(new_inode);
+ old_dir->i_ctime = old_dir->i_mtime = ctime;
+ new_dir->i_ctime = new_dir->i_mtime = ctime;
+ old_inode->i_ctime = ctime;
+ new_inode->i_ctime = ctime;
+
+ if (old_dentry->d_parent != new_dentry->d_parent) {
+ btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
+ btrfs_record_unlink_dir(trans, new_dir, new_inode, 1);
+ }
+
+ /* src is a subvolume */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, root, old_dir,
+ root_objectid,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ } else { /* src is an inode */
+ ret = __btrfs_unlink_inode(trans, root, old_dir,
+ old_dentry->d_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, root, old_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ /* dest is a subvolume */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, dest, new_dir,
+ root_objectid,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ } else { /* dest is an inode */
+ ret = __btrfs_unlink_inode(trans, dest, new_dir,
+ new_dentry->d_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, dest, new_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, new_dir, old_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len, 0, old_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, old_dir, new_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len, 0, new_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ if (old_inode->i_nlink == 1)
+ BTRFS_I(old_inode)->dir_index = old_idx;
+ if (new_inode->i_nlink == 1)
+ BTRFS_I(new_inode)->dir_index = new_idx;
+
+ if (root_log_pinned) {
+ parent = new_dentry->d_parent;
+ btrfs_log_new_name(trans, old_inode, old_dir, parent);
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ parent = old_dentry->d_parent;
+ btrfs_log_new_name(trans, new_inode, new_dir, parent);
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+out_fail:
+ /*
+ * If we have pinned a log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && (root_log_pinned || dest_log_pinned)) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ if (root_log_pinned) {
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+ }
+ ret = btrfs_end_transaction(trans, root);
+out_notrans:
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&dest->fs_info->subvol_sem);
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&root->fs_info->subvol_sem);
+
+ return ret;
+}
+
+static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct inode *dir,
+ struct dentry *dentry)
+{
+ int ret;
+ struct inode *inode;
+ u64 objectid;
+ u64 index;
+
+ ret = btrfs_find_free_ino(root, &objectid);
+ if (ret)
+ return ret;
+
+ inode = btrfs_new_inode(trans, root, dir,
+ dentry->d_name.name,
+ dentry->d_name.len,
+ btrfs_ino(dir),
+ objectid,
+ S_IFCHR | WHITEOUT_MODE,
+ &index);
+
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ return ret;
+ }
+
+ inode->i_op = &btrfs_special_inode_operations;
+ init_special_inode(inode, inode->i_mode,
+ WHITEOUT_DEV);
+
+ ret = btrfs_init_inode_security(trans, inode, dir,
+ &dentry->d_name);
+ if (ret)
+ goto out;
+
+ ret = btrfs_add_nondir(trans, dir, dentry,
+ inode, 0, index);
+ if (ret)
+ goto out;
+
+ ret = btrfs_update_inode(trans, root, inode);
+out:
+ unlock_new_inode(inode);
+ if (ret)
+ inode_dec_link_count(inode);
+ iput(inode);
+
+ return ret;
+}
+
static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct btrfs_trans_handle *trans;
+ unsigned int trans_num_items;
struct btrfs_root *root = BTRFS_I(old_dir)->root;
struct btrfs_root *dest = BTRFS_I(new_dir)->root;
struct inode *new_inode = d_inode(new_dentry);
@@ -9399,6 +9693,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
u64 root_objectid;
int ret;
u64 old_ino = btrfs_ino(old_inode);
+ bool log_pinned = false;
if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
return -EPERM;
@@ -9449,15 +9744,21 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
* We want to reserve the absolute worst case amount of items. So if
* both inodes are subvols and we need to unlink them then that would
* require 4 item modifications, but if they are both normal inodes it
- * would require 5 item modifications, so we'll assume their normal
+ * would require 5 item modifications, so we'll assume they are normal
* inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items
* should cover the worst case number of items we'll modify.
+ * If our rename has the whiteout flag, we need more 5 units for the
+ * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item
+ * when selinux is enabled).
*/
- trans = btrfs_start_transaction(root, 11);
+ trans_num_items = 11;
+ if (flags & RENAME_WHITEOUT)
+ trans_num_items += 5;
+ trans = btrfs_start_transaction(root, trans_num_items);
if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_notrans;
- }
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
if (dest != root)
btrfs_record_root_in_trans(trans, dest);
@@ -9471,6 +9772,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
/* force full log commit if subvolume involved. */
btrfs_set_log_full_commit(root->fs_info, trans);
} else {
+ btrfs_pin_log_trans(root);
+ log_pinned = true;
ret = btrfs_insert_inode_ref(trans, dest,
new_dentry->d_name.name,
new_dentry->d_name.len,
@@ -9478,14 +9781,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
btrfs_ino(new_dir), index);
if (ret)
goto out_fail;
- /*
- * this is an ugly little race, but the rename is required
- * to make sure that if we crash, the inode is either at the
- * old name or the new one. pinning the log transaction lets
- * us make sure we don't allow a log commit to come in after
- * we unlink the name but before we add the new name back in.
- */
- btrfs_pin_log_trans(root);
}
inode_inc_iversion(old_dir);
@@ -9552,12 +9847,46 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (old_inode->i_nlink == 1)
BTRFS_I(old_inode)->dir_index = index;
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+ if (log_pinned) {
struct dentry *parent = new_dentry->d_parent;
+
btrfs_log_new_name(trans, old_inode, old_dir, parent);
btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
+
+ if (flags & RENAME_WHITEOUT) {
+ ret = btrfs_whiteout_for_rename(trans, root, old_dir,
+ old_dentry);
+
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
}
out_fail:
+ /*
+ * If we have pinned the log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && log_pinned) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
btrfs_end_transaction(trans, root);
out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
@@ -9570,10 +9899,14 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
- if (flags & ~RENAME_NOREPLACE)
+ if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
- return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry);
+ if (flags & RENAME_EXCHANGE)
+ return btrfs_rename_exchange(old_dir, old_dentry, new_dir,
+ new_dentry);
+
+ return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
static void btrfs_run_delalloc_work(struct btrfs_work *work)
@@ -9942,6 +10275,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
btrfs_end_transaction(trans, root);
break;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
last_alloc = ins.offset;
ret = insert_reserved_file_extent(trans, inode,
@@ -10160,10 +10494,10 @@ static const struct inode_operations btrfs_dir_inode_operations = {
.symlink = btrfs_symlink,
.setattr = btrfs_setattr,
.mknod = btrfs_mknod,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
@@ -10184,7 +10518,7 @@ static const struct file_operations btrfs_dir_file_operations = {
.iterate = btrfs_real_readdir,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
- .compat_ioctl = btrfs_ioctl,
+ .compat_ioctl = btrfs_compat_ioctl,
#endif
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
@@ -10237,10 +10571,10 @@ static const struct address_space_operations btrfs_symlink_aops = {
static const struct inode_operations btrfs_file_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
@@ -10251,10 +10585,10 @@ static const struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
@@ -10265,10 +10599,10 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.update_time = btrfs_update_time,
};
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5a23806ae418..4e700694b741 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -125,10 +125,10 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
if (flags & BTRFS_INODE_NODATACOW)
iflags |= FS_NOCOW_FL;
- if ((flags & BTRFS_INODE_COMPRESS) && !(flags & BTRFS_INODE_NOCOMPRESS))
- iflags |= FS_COMPR_FL;
- else if (flags & BTRFS_INODE_NOCOMPRESS)
+ if (flags & BTRFS_INODE_NOCOMPRESS)
iflags |= FS_NOCOMP_FL;
+ else if (flags & BTRFS_INODE_COMPRESS)
+ iflags |= FS_COMPR_FL;
return iflags;
}
@@ -439,7 +439,7 @@ static noinline int create_subvol(struct inode *dir,
{
struct btrfs_trans_handle *trans;
struct btrfs_key key;
- struct btrfs_root_item root_item;
+ struct btrfs_root_item *root_item;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -455,16 +455,22 @@ static noinline int create_subvol(struct inode *dir,
u64 qgroup_reserved;
uuid_le new_uuid;
+ root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
+ if (!root_item)
+ return -ENOMEM;
+
ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
if (ret)
- return ret;
+ goto fail_free;
/*
* Don't create subvolume whose level is not zero. Or qgroup will be
* screwed up since it assume subvolme qgroup's level to be 0.
*/
- if (btrfs_qgroup_level(objectid))
- return -ENOSPC;
+ if (btrfs_qgroup_level(objectid)) {
+ ret = -ENOSPC;
+ goto fail_free;
+ }
btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
@@ -474,14 +480,14 @@ static noinline int create_subvol(struct inode *dir,
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
8, &qgroup_reserved, false);
if (ret)
- return ret;
+ goto fail_free;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_subvolume_release_metadata(root, &block_rsv,
qgroup_reserved);
- return ret;
+ goto fail_free;
}
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
@@ -509,47 +515,45 @@ static noinline int create_subvol(struct inode *dir,
BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
- memset(&root_item, 0, sizeof(root_item));
-
- inode_item = &root_item.inode;
+ inode_item = &root_item->inode;
btrfs_set_stack_inode_generation(inode_item, 1);
btrfs_set_stack_inode_size(inode_item, 3);
btrfs_set_stack_inode_nlink(inode_item, 1);
btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
- btrfs_set_root_flags(&root_item, 0);
- btrfs_set_root_limit(&root_item, 0);
+ btrfs_set_root_flags(root_item, 0);
+ btrfs_set_root_limit(root_item, 0);
btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT);
- btrfs_set_root_bytenr(&root_item, leaf->start);
- btrfs_set_root_generation(&root_item, trans->transid);
- btrfs_set_root_level(&root_item, 0);
- btrfs_set_root_refs(&root_item, 1);
- btrfs_set_root_used(&root_item, leaf->len);
- btrfs_set_root_last_snapshot(&root_item, 0);
+ btrfs_set_root_bytenr(root_item, leaf->start);
+ btrfs_set_root_generation(root_item, trans->transid);
+ btrfs_set_root_level(root_item, 0);
+ btrfs_set_root_refs(root_item, 1);
+ btrfs_set_root_used(root_item, leaf->len);
+ btrfs_set_root_last_snapshot(root_item, 0);
- btrfs_set_root_generation_v2(&root_item,
- btrfs_root_generation(&root_item));
+ btrfs_set_root_generation_v2(root_item,
+ btrfs_root_generation(root_item));
uuid_le_gen(&new_uuid);
- memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
- btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec);
- btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec);
- root_item.ctime = root_item.otime;
- btrfs_set_root_ctransid(&root_item, trans->transid);
- btrfs_set_root_otransid(&root_item, trans->transid);
+ memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
+ btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec);
+ btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec);
+ root_item->ctime = root_item->otime;
+ btrfs_set_root_ctransid(root_item, trans->transid);
+ btrfs_set_root_otransid(root_item, trans->transid);
btrfs_tree_unlock(leaf);
free_extent_buffer(leaf);
leaf = NULL;
- btrfs_set_root_dirid(&root_item, new_dirid);
+ btrfs_set_root_dirid(root_item, new_dirid);
key.objectid = objectid;
key.offset = 0;
key.type = BTRFS_ROOT_ITEM_KEY;
ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
- &root_item);
+ root_item);
if (ret)
goto fail;
@@ -601,12 +605,13 @@ static noinline int create_subvol(struct inode *dir,
BUG_ON(ret);
ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
- root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
+ root_item->uuid, BTRFS_UUID_KEY_SUBVOL,
objectid);
if (ret)
btrfs_abort_transaction(trans, root, ret);
fail:
+ kfree(root_item);
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
@@ -629,6 +634,10 @@ fail:
d_instantiate(dentry, inode);
}
return ret;
+
+fail_free:
+ kfree(root_item);
+ return ret;
}
static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
@@ -681,7 +690,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (ret)
goto dec_and_free;
- btrfs_wait_ordered_extents(root, -1);
+ btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);
btrfs_init_block_rsv(&pending_snapshot->block_rsv,
BTRFS_BLOCK_RSV_TEMP);
@@ -837,9 +846,11 @@ static noinline int btrfs_mksubvol(struct path *parent,
struct dentry *dentry;
int error;
- error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- if (error == -EINTR)
- return error;
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ // XXX: should've been
+ // mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ // if (error == -EINTR)
+ // return error;
dentry = lookup_one_len(name, parent->dentry, namelen);
error = PTR_ERR(dentry);
@@ -2366,9 +2377,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
goto out;
- err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- if (err == -EINTR)
- goto out_drop_write;
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ // XXX: should've been
+ // err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ // if (err == -EINTR)
+ // goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -2558,7 +2571,7 @@ out_dput:
dput(dentry);
out_unlock_dir:
inode_unlock(dir);
-out_drop_write:
+//out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
@@ -2667,10 +2680,10 @@ out:
return ret;
}
-static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
+static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
- struct btrfs_ioctl_vol_args *vol_args;
+ struct btrfs_ioctl_vol_args_v2 *vol_args;
int ret;
if (!capable(CAP_SYS_ADMIN))
@@ -2686,7 +2699,9 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
goto err_drop;
}
- vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+ /* Check for compatibility reject unknown flags */
+ if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
+ return -EOPNOTSUPP;
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
@@ -2695,13 +2710,23 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
}
mutex_lock(&root->fs_info->volume_mutex);
- ret = btrfs_rm_device(root, vol_args->name);
+ if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
+ ret = btrfs_rm_device(root, NULL, vol_args->devid);
+ } else {
+ vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+ ret = btrfs_rm_device(root, vol_args->name, 0);
+ }
mutex_unlock(&root->fs_info->volume_mutex);
atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
- if (!ret)
- btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
-
+ if (!ret) {
+ if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
+ btrfs_info(root->fs_info, "device deleted: id %llu",
+ vol_args->devid);
+ else
+ btrfs_info(root->fs_info, "device deleted: %s",
+ vol_args->name);
+ }
out:
kfree(vol_args);
err_drop:
@@ -2709,6 +2734,47 @@ err_drop:
return ret;
}
+static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
+{
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+ struct btrfs_ioctl_vol_args *vol_args;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
+ if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
+ 1)) {
+ ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
+ goto out_drop_write;
+ }
+
+ vol_args = memdup_user(arg, sizeof(*vol_args));
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
+
+ vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+ mutex_lock(&root->fs_info->volume_mutex);
+ ret = btrfs_rm_device(root, vol_args->name, 0);
+ mutex_unlock(&root->fs_info->volume_mutex);
+
+ if (!ret)
+ btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
+ kfree(vol_args);
+out:
+ atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+out_drop_write:
+ mnt_drop_write_file(file);
+
+ return ret;
+}
+
static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
{
struct btrfs_ioctl_fs_info_args *fi_args;
@@ -3468,13 +3534,16 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
u64 last_dest_end = destoff;
ret = -ENOMEM;
- buf = vmalloc(root->nodesize);
- if (!buf)
- return ret;
+ buf = kmalloc(root->nodesize, GFP_KERNEL | __GFP_NOWARN);
+ if (!buf) {
+ buf = vmalloc(root->nodesize);
+ if (!buf)
+ return ret;
+ }
path = btrfs_alloc_path();
if (!path) {
- vfree(buf);
+ kvfree(buf);
return ret;
}
@@ -3775,7 +3844,7 @@ process_slot:
out:
btrfs_free_path(path);
- vfree(buf);
+ kvfree(buf);
return ret;
}
@@ -4376,7 +4445,7 @@ static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg)
1)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
} else {
- ret = btrfs_dev_replace_start(root, p);
+ ret = btrfs_dev_replace_by_ioctl(root, p);
atomic_set(
&root->fs_info->mutually_exclusive_operation_running,
0);
@@ -4847,8 +4916,8 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
/* update qgroup status and info */
err = btrfs_run_qgroups(trans, root->fs_info);
if (err < 0)
- btrfs_std_error(root->fs_info, ret,
- "failed to update qgroup status and info\n");
+ btrfs_handle_fs_error(root->fs_info, err,
+ "failed to update qgroup status and info");
err = btrfs_end_transaction(trans, root);
if (err && !ret)
ret = err;
@@ -5394,9 +5463,15 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
if (ret)
return ret;
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_drop_write;
+ }
spin_lock(&root->fs_info->super_lock);
newflags = btrfs_super_compat_flags(super_block);
@@ -5415,7 +5490,11 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
btrfs_set_super_incompat_flags(super_block, newflags);
spin_unlock(&root->fs_info->super_lock);
- return btrfs_commit_transaction(trans, root);
+ ret = btrfs_commit_transaction(trans, root);
+out_drop_write:
+ mnt_drop_write_file(file);
+
+ return ret;
}
long btrfs_ioctl(struct file *file, unsigned int
@@ -5459,6 +5538,8 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_add_dev(root, argp);
case BTRFS_IOC_RM_DEV:
return btrfs_ioctl_rm_dev(file, argp);
+ case BTRFS_IOC_RM_DEV_V2:
+ return btrfs_ioctl_rm_dev_v2(file, argp);
case BTRFS_IOC_FS_INFO:
return btrfs_ioctl_fs_info(root, argp);
case BTRFS_IOC_DEV_INFO:
@@ -5552,3 +5633,24 @@ long btrfs_ioctl(struct file *file, unsigned int
return -ENOTTY;
}
+
+#ifdef CONFIG_COMPAT
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case FS_IOC32_GETFLAGS:
+ cmd = FS_IOC_GETFLAGS;
+ break;
+ case FS_IOC32_SETFLAGS:
+ cmd = FS_IOC_SETFLAGS;
+ break;
+ case FS_IOC32_GETVERSION:
+ cmd = FS_IOC_GETVERSION;
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+
+ return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 0de7da5a610d..559170464d7c 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -661,14 +661,15 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
* wait for all the ordered extents in a root. This is done when balancing
* space between drives.
*/
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
+ const u64 range_start, const u64 range_len)
{
- struct list_head splice, works;
+ LIST_HEAD(splice);
+ LIST_HEAD(skipped);
+ LIST_HEAD(works);
struct btrfs_ordered_extent *ordered, *next;
int count = 0;
-
- INIT_LIST_HEAD(&splice);
- INIT_LIST_HEAD(&works);
+ const u64 range_end = range_start + range_len;
mutex_lock(&root->ordered_extent_mutex);
spin_lock(&root->ordered_extent_lock);
@@ -676,6 +677,14 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
while (!list_empty(&splice) && nr) {
ordered = list_first_entry(&splice, struct btrfs_ordered_extent,
root_extent_list);
+
+ if (range_end <= ordered->start ||
+ ordered->start + ordered->disk_len <= range_start) {
+ list_move_tail(&ordered->root_extent_list, &skipped);
+ cond_resched_lock(&root->ordered_extent_lock);
+ continue;
+ }
+
list_move_tail(&ordered->root_extent_list,
&root->ordered_extents);
atomic_inc(&ordered->refs);
@@ -694,6 +703,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
nr--;
count++;
}
+ list_splice_tail(&skipped, &root->ordered_extents);
list_splice_tail(&splice, &root->ordered_extents);
spin_unlock(&root->ordered_extent_lock);
@@ -708,7 +718,8 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
return count;
}
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+ const u64 range_start, const u64 range_len)
{
struct btrfs_root *root;
struct list_head splice;
@@ -728,7 +739,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
&fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
- done = btrfs_wait_ordered_extents(root, nr);
+ done = btrfs_wait_ordered_extents(root, nr,
+ range_start, range_len);
btrfs_put_fs_root(root);
spin_lock(&fs_info->ordered_root_lock);
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 23c96059cef2..8ef12623d65c 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -197,8 +197,10 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
struct btrfs_ordered_extent *ordered);
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
u32 *sum, int len);
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr);
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr);
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
+ const u64 range_start, const u64 range_len);
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+ const u64 range_start, const u64 range_len);
void btrfs_get_logged_extents(struct inode *inode,
struct list_head *logged_list,
const loff_t start,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 08ef890deca6..1cfd35cfac76 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2418,7 +2418,7 @@ again:
}
out:
if (ret) {
- btrfs_std_error(root->fs_info, ret, NULL);
+ btrfs_handle_fs_error(root->fs_info, ret, NULL);
if (!list_empty(&reloc_roots))
free_reloc_roots(&reloc_roots);
@@ -4254,12 +4254,11 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu",
rc->block_group->key.objectid, rc->block_group->flags);
- ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
- if (ret < 0) {
- err = ret;
- goto out;
- }
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_block_group_reservations(rc->block_group);
+ btrfs_wait_nocow_writers(rc->block_group);
+ btrfs_wait_ordered_roots(fs_info, -1,
+ rc->block_group->key.objectid,
+ rc->block_group->key.offset);
while (1) {
mutex_lock(&fs_info->cleaner_mutex);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 9fcd6dfc3266..b2b14e7115f1 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -284,7 +284,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
trans = btrfs_join_transaction(tree_root);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- btrfs_std_error(tree_root->fs_info, err,
+ btrfs_handle_fs_error(tree_root->fs_info, err,
"Failed to start trans to delete "
"orphan item");
break;
@@ -293,7 +293,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
root_key.objectid);
btrfs_end_transaction(trans, tree_root);
if (err) {
- btrfs_std_error(tree_root->fs_info, err,
+ btrfs_handle_fs_error(tree_root->fs_info, err,
"Failed to delete root orphan "
"item");
break;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 4678f03e878e..fa35cdc46494 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1350,7 +1350,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
recover->bbio = bbio;
recover->map_length = mapped_length;
- BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO);
+ BUG_ON(page_index >= SCRUB_MAX_PAGES_PER_BLOCK);
nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS);
@@ -2127,6 +2127,8 @@ static void scrub_missing_raid56_end_io(struct bio *bio)
if (bio->bi_error)
sblock->no_io_error_seen = 0;
+ bio_put(bio);
+
btrfs_queue_work(fs_info->scrub_workers, &sblock->work);
}
@@ -2860,7 +2862,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
int extent_mirror_num;
int stop_loop = 0;
- nsectors = map->stripe_len / root->sectorsize;
+ nsectors = div_u64(map->stripe_len, root->sectorsize);
bitmap_len = scrub_calc_parity_bitmap_len(nsectors);
sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len,
GFP_NOFS);
@@ -3070,7 +3072,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
int slot;
u64 nstripes;
struct extent_buffer *l;
- struct btrfs_key key;
u64 physical;
u64 logical;
u64 logic_end;
@@ -3079,7 +3080,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
int mirror_num;
struct reada_control *reada1;
struct reada_control *reada2;
- struct btrfs_key key_start;
+ struct btrfs_key key;
struct btrfs_key key_end;
u64 increment = map->stripe_len;
u64 offset;
@@ -3158,21 +3159,21 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
scrub_blocked_if_needed(fs_info);
/* FIXME it might be better to start readahead at commit root */
- key_start.objectid = logical;
- key_start.type = BTRFS_EXTENT_ITEM_KEY;
- key_start.offset = (u64)0;
+ key.objectid = logical;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = (u64)0;
key_end.objectid = logic_end;
key_end.type = BTRFS_METADATA_ITEM_KEY;
key_end.offset = (u64)-1;
- reada1 = btrfs_reada_add(root, &key_start, &key_end);
+ reada1 = btrfs_reada_add(root, &key, &key_end);
- key_start.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
- key_start.type = BTRFS_EXTENT_CSUM_KEY;
- key_start.offset = logical;
+ key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+ key.type = BTRFS_EXTENT_CSUM_KEY;
+ key.offset = logical;
key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
key_end.type = BTRFS_EXTENT_CSUM_KEY;
key_end.offset = logic_end;
- reada2 = btrfs_reada_add(csum_root, &key_start, &key_end);
+ reada2 = btrfs_reada_add(csum_root, &key, &key_end);
if (!IS_ERR(reada1))
btrfs_reada_wait(reada1);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 8d358c547c59..6a8c86074aa4 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5939,6 +5939,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
u32 i;
u64 *clone_sources_tmp = NULL;
int clone_sources_to_rollback = 0;
+ unsigned alloc_size;
int sort_clone_roots = 0;
int index;
@@ -5978,6 +5979,12 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
goto out;
}
+ if (arg->clone_sources_count >
+ ULLONG_MAX / sizeof(*arg->clone_sources)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (!access_ok(VERIFY_READ, arg->clone_sources,
sizeof(*arg->clone_sources) *
arg->clone_sources_count)) {
@@ -6022,40 +6029,53 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
sctx->clone_roots_cnt = arg->clone_sources_count;
sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
- sctx->send_buf = vmalloc(sctx->send_max_size);
+ sctx->send_buf = kmalloc(sctx->send_max_size, GFP_KERNEL | __GFP_NOWARN);
if (!sctx->send_buf) {
- ret = -ENOMEM;
- goto out;
+ sctx->send_buf = vmalloc(sctx->send_max_size);
+ if (!sctx->send_buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
}
- sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
+ sctx->read_buf = kmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL | __GFP_NOWARN);
if (!sctx->read_buf) {
- ret = -ENOMEM;
- goto out;
+ sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
+ if (!sctx->read_buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
}
sctx->pending_dir_moves = RB_ROOT;
sctx->waiting_dir_moves = RB_ROOT;
sctx->orphan_dirs = RB_ROOT;
- sctx->clone_roots = vzalloc(sizeof(struct clone_root) *
- (arg->clone_sources_count + 1));
+ alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1);
+
+ sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
if (!sctx->clone_roots) {
- ret = -ENOMEM;
- goto out;
+ sctx->clone_roots = vzalloc(alloc_size);
+ if (!sctx->clone_roots) {
+ ret = -ENOMEM;
+ goto out;
+ }
}
+ alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources);
+
if (arg->clone_sources_count) {
- clone_sources_tmp = vmalloc(arg->clone_sources_count *
- sizeof(*arg->clone_sources));
+ clone_sources_tmp = kmalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
if (!clone_sources_tmp) {
- ret = -ENOMEM;
- goto out;
+ clone_sources_tmp = vmalloc(alloc_size);
+ if (!clone_sources_tmp) {
+ ret = -ENOMEM;
+ goto out;
+ }
}
ret = copy_from_user(clone_sources_tmp, arg->clone_sources,
- arg->clone_sources_count *
- sizeof(*arg->clone_sources));
+ alloc_size);
if (ret) {
ret = -EFAULT;
goto out;
@@ -6089,7 +6109,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
sctx->clone_roots[i].root = clone_root;
clone_sources_to_rollback = i + 1;
}
- vfree(clone_sources_tmp);
+ kvfree(clone_sources_tmp);
clone_sources_tmp = NULL;
}
@@ -6207,15 +6227,15 @@ out:
btrfs_root_dec_send_in_progress(sctx->parent_root);
kfree(arg);
- vfree(clone_sources_tmp);
+ kvfree(clone_sources_tmp);
if (sctx) {
if (sctx->send_filp)
fput(sctx->send_filp);
- vfree(sctx->clone_roots);
- vfree(sctx->send_buf);
- vfree(sctx->read_buf);
+ kvfree(sctx->clone_roots);
+ kvfree(sctx->send_buf);
+ kvfree(sctx->read_buf);
name_cache_free(sctx);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 00b8f37cc306..bf71071ab6f6 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -97,15 +97,6 @@ const char *btrfs_decode_error(int errno)
return errstr;
}
-static void save_error_info(struct btrfs_fs_info *fs_info)
-{
- /*
- * today we only save the error info into ram. Long term we'll
- * also send it down to the disk
- */
- set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
-}
-
/* btrfs handle error by forcing the filesystem readonly */
static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
{
@@ -131,11 +122,11 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
}
/*
- * __btrfs_std_error decodes expected errors from the caller and
+ * __btrfs_handle_fs_error decodes expected errors from the caller and
* invokes the approciate error response.
*/
__cold
-void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...)
{
struct super_block *sb = fs_info->sb;
@@ -170,8 +161,13 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
}
#endif
+ /*
+ * Today we only save the error info to memory. Long term we'll
+ * also send it down to the disk
+ */
+ set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
+
/* Don't go through full error handling during mount */
- save_error_info(fs_info);
if (sb->s_flags & MS_BORN)
btrfs_handle_error(fs_info);
}
@@ -252,7 +248,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
/* Wake up anybody who may be waiting on this transaction */
wake_up(&root->fs_info->transaction_wait);
wake_up(&root->fs_info->transaction_blocked_wait);
- __btrfs_std_error(root->fs_info, function, line, errno, NULL);
+ __btrfs_handle_fs_error(root->fs_info, function, line, errno, NULL);
}
/*
* __btrfs_panic decodes unexpected, fatal errors from the caller,
@@ -1160,7 +1156,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
return 0;
}
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
@@ -1488,10 +1484,10 @@ static int setup_security_options(struct btrfs_fs_info *fs_info,
memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
} else {
/*
- * Since SELinux(the only one supports security_mnt_opts) does
- * NOT support changing context during remount/mount same sb,
- * This must be the same or part of the same security options,
- * just free it.
+ * Since SELinux (the only one supporting security_mnt_opts)
+ * does NOT support changing context during remount/mount of
+ * the same sb, this must be the same or part of the same
+ * security options, just free it.
*/
security_free_mnt_opts(sec_opts);
}
@@ -1669,8 +1665,8 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
unsigned long old_opts)
{
/*
- * We need cleanup all defragable inodes if the autodefragment is
- * close or the fs is R/O.
+ * We need to cleanup all defragable inodes if the autodefragment is
+ * close or the filesystem is read only.
*/
if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
(!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
@@ -2051,9 +2047,10 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
u64 thresh = 0;
+ int mixed = 0;
/*
- * holding chunk_muext to avoid allocating new chunks, holding
+ * holding chunk_mutex to avoid allocating new chunks, holding
* device_list_mutex to avoid the device being removed
*/
rcu_read_lock();
@@ -2076,8 +2073,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
}
}
}
- if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
- total_free_meta += found->disk_total - found->disk_used;
+
+ /*
+ * Metadata in mixed block goup profiles are accounted in data
+ */
+ if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
+ if (found->flags & BTRFS_BLOCK_GROUP_DATA)
+ mixed = 1;
+ else
+ total_free_meta += found->disk_total -
+ found->disk_used;
+ }
total_used += found->disk_used;
}
@@ -2090,7 +2096,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
/* Account global block reserve as used, it's in logical size already */
spin_lock(&block_rsv->lock);
- buf->f_bfree -= block_rsv->size >> bits;
+ /* Mixed block groups accounting is not byte-accurate, avoid overflow */
+ if (buf->f_bfree >= block_rsv->size >> bits)
+ buf->f_bfree -= block_rsv->size >> bits;
+ else
+ buf->f_bfree = 0;
spin_unlock(&block_rsv->lock);
buf->f_bavail = div_u64(total_free_data, factor);
@@ -2115,7 +2125,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
*/
thresh = 4 * 1024 * 1024;
- if (total_free_meta - thresh < block_rsv->size)
+ if (!mixed && total_free_meta - thresh < block_rsv->size)
buf->f_bavail = 0;
buf->f_type = BTRFS_SUPER_MAGIC;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 539e7b5e3f86..4879656bda3c 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -120,6 +120,9 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
if (!fs_info)
return -EPERM;
+ if (fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
ret = kstrtoul(skip_spaces(buf), 0, &val);
if (ret)
return ret;
@@ -364,7 +367,13 @@ static ssize_t btrfs_label_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
char *label = fs_info->super_copy->label;
- return snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
+ ssize_t ret;
+
+ spin_lock(&fs_info->super_lock);
+ ret = snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
+ spin_unlock(&fs_info->super_lock);
+
+ return ret;
}
static ssize_t btrfs_label_store(struct kobject *kobj,
@@ -374,6 +383,9 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
size_t p_len;
+ if (!fs_info)
+ return -EPERM;
+
if (fs_info->sb->s_flags & MS_RDONLY)
return -EROFS;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 43885e51b882..5b0b758a3f79 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -311,10 +311,11 @@ loop:
* when the transaction commits
*/
static int record_root_in_trans(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
+ struct btrfs_root *root,
+ int force)
{
- if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
- root->last_trans < trans->transid) {
+ if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ root->last_trans < trans->transid) || force) {
WARN_ON(root == root->fs_info->extent_root);
WARN_ON(root->commit_root != root->node);
@@ -331,7 +332,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
smp_wmb();
spin_lock(&root->fs_info->fs_roots_radix_lock);
- if (root->last_trans == trans->transid) {
+ if (root->last_trans == trans->transid && !force) {
spin_unlock(&root->fs_info->fs_roots_radix_lock);
return 0;
}
@@ -402,7 +403,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
return 0;
mutex_lock(&root->fs_info->reloc_mutex);
- record_root_in_trans(trans, root);
+ record_root_in_trans(trans, root, 0);
mutex_unlock(&root->fs_info->reloc_mutex);
return 0;
@@ -1310,6 +1311,97 @@ 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.
+ *
+ * Will do all needed qgroup inherit and dirty hack like switch commit
+ * roots inside one transaction and write all btree into disk, to make
+ * qgroup works.
+ */
+static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
+ struct btrfs_root *src,
+ struct btrfs_root *parent,
+ struct btrfs_qgroup_inherit *inherit,
+ u64 dst_objectid)
+{
+ struct btrfs_fs_info *fs_info = src->fs_info;
+ int ret;
+
+ /*
+ * Save some performance in the case that qgroups are not
+ * enabled. If this check races with the ioctl, rescan will
+ * kick in anyway.
+ */
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
+ if (!fs_info->quota_enabled) {
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ return 0;
+ }
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
+ /*
+ * We are going to commit transaction, see btrfs_commit_transaction()
+ * comment for reason locking tree_log_mutex
+ */
+ mutex_lock(&fs_info->tree_log_mutex);
+
+ ret = commit_fs_roots(trans, src);
+ if (ret)
+ goto out;
+ ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
+ if (ret < 0)
+ goto out;
+ ret = btrfs_qgroup_account_extents(trans, fs_info);
+ if (ret < 0)
+ goto out;
+
+ /* Now qgroup are all updated, we can inherit it to new qgroups */
+ ret = btrfs_qgroup_inherit(trans, fs_info,
+ src->root_key.objectid, dst_objectid,
+ inherit);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Now we do a simplified commit transaction, which will:
+ * 1) commit all subvolume and extent tree
+ * To ensure all subvolume and extent tree have a valid
+ * commit_root to accounting later insert_dir_item()
+ * 2) write all btree blocks onto disk
+ * This is to make sure later btree modification will be cowed
+ * Or commit_root can be populated and cause wrong qgroup numbers
+ * In this simplified commit, we don't really care about other trees
+ * like chunk and root tree, as they won't affect qgroup.
+ * And we don't write super to avoid half committed status.
+ */
+ ret = commit_cowonly_roots(trans, src);
+ if (ret)
+ goto out;
+ switch_commit_roots(trans->transaction, fs_info);
+ ret = btrfs_write_and_wait_transaction(trans, src);
+ if (ret)
+ btrfs_std_error(fs_info, ret,
+ "Error while writing out transaction for qgroup");
+
+out:
+ mutex_unlock(&fs_info->tree_log_mutex);
+
+ /*
+ * Force parent root to be updated, as we recorded it before so its
+ * last_trans == cur_transid.
+ * Or it won't be committed again onto disk after later
+ * insert_dir_item()
+ */
+ if (!ret)
+ record_root_in_trans(trans, parent, 1);
+ return ret;
+}
+
/*
* new snapshots need to be created at a very specific time in the
* transaction commit. This does the actual creation.
@@ -1383,7 +1475,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
dentry = pending->dentry;
parent_inode = pending->dir;
parent_root = BTRFS_I(parent_inode)->root;
- record_root_in_trans(trans, parent_root);
+ record_root_in_trans(trans, parent_root, 0);
cur_time = current_fs_time(parent_inode->i_sb);
@@ -1420,7 +1512,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
goto fail;
}
- record_root_in_trans(trans, root);
+ record_root_in_trans(trans, root, 0);
btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
btrfs_check_and_init_root_item(new_root_item);
@@ -1516,6 +1608,17 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
goto fail;
}
+ /*
+ * Do special qgroup accounting for snapshot, as we do some qgroup
+ * snapshot hack to do fast snapshot.
+ * To co-operate with that hack, we do hack again.
+ * Or snapshot will be greatly slowed down by a subtree qgroup rescan
+ */
+ ret = qgroup_account_snapshot(trans, root, parent_root,
+ pending->inherit, objectid);
+ if (ret < 0)
+ goto fail;
+
ret = btrfs_insert_dir_item(trans, parent_root,
dentry->d_name.name, dentry->d_name.len,
parent_inode, &key,
@@ -1559,23 +1662,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
goto fail;
}
- /*
- * account qgroup counters before qgroup_inherit()
- */
- ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
- if (ret)
- goto fail;
- ret = btrfs_qgroup_account_extents(trans, fs_info);
- if (ret)
- goto fail;
- ret = btrfs_qgroup_inherit(trans, fs_info,
- root->root_key.objectid,
- objectid, pending->inherit);
- if (ret) {
- btrfs_abort_transaction(trans, root, ret);
- goto fail;
- }
-
fail:
pending->error = ret;
dir_item_existed:
@@ -1821,7 +1907,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
{
if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
}
static inline void
@@ -2145,7 +2231,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
ret = btrfs_write_and_wait_transaction(trans, root);
if (ret) {
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"Error while writing out transaction");
mutex_unlock(&root->fs_info->tree_log_mutex);
goto scrub_continue;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 517d0ccb351e..8aaca5c6af94 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4141,6 +4141,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
INIT_LIST_HEAD(&extents);
+ down_write(&BTRFS_I(inode)->dio_sem);
write_lock(&tree->lock);
test_gen = root->fs_info->last_trans_committed;
@@ -4169,13 +4170,20 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
}
list_sort(NULL, &extents, extent_cmp);
+ btrfs_get_logged_extents(inode, logged_list, start, end);
/*
- * Collect any new ordered extents within the range. This is to
- * prevent logging file extent items without waiting for the disk
- * location they point to being written. We do this only to deal
- * with races against concurrent lockless direct IO writes.
+ * Some ordered extents started by fsync might have completed
+ * before we could collect them into the list logged_list, which
+ * means they're gone, not in our logged_list nor in the inode's
+ * ordered tree. We want the application/user space to know an
+ * error happened while attempting to persist file data so that
+ * it can take proper action. If such error happened, we leave
+ * without writing to the log tree and the fsync must report the
+ * file data write error and not commit the current transaction.
*/
- btrfs_get_logged_extents(inode, logged_list, start, end);
+ ret = btrfs_inode_check_errors(inode);
+ if (ret)
+ ctx->io_err = ret;
process:
while (!list_empty(&extents)) {
em = list_entry(extents.next, struct extent_map, list);
@@ -4202,6 +4210,7 @@ process:
}
WARN_ON(!list_empty(&extents));
write_unlock(&tree->lock);
+ up_write(&BTRFS_I(inode)->dio_sem);
btrfs_release_path(path);
return ret;
@@ -4623,23 +4632,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
mutex_lock(&BTRFS_I(inode)->log_mutex);
/*
- * Collect ordered extents only if we are logging data. This is to
- * ensure a subsequent request to log this inode in LOG_INODE_ALL mode
- * will process the ordered extents if they still exists at the time,
- * because when we collect them we test and set for the flag
- * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the
- * same ordered extents. The consequence for the LOG_INODE_ALL log mode
- * not processing the ordered extents is that we end up logging the
- * corresponding file extent items, based on the extent maps in the
- * inode's extent_map_tree's modified_list, without logging the
- * respective checksums (since the may still be only attached to the
- * ordered extents and have not been inserted in the csum tree by
- * btrfs_finish_ordered_io() yet).
- */
- if (inode_only == LOG_INODE_ALL)
- btrfs_get_logged_extents(inode, &logged_list, start, end);
-
- /*
* a brute force approach to making sure we get the most uptodate
* copies of everything.
*/
@@ -4846,21 +4838,6 @@ log_extents:
goto out_unlock;
}
if (fast_search) {
- /*
- * Some ordered extents started by fsync might have completed
- * before we collected the ordered extents in logged_list, which
- * means they're gone, not in our logged_list nor in the inode's
- * ordered tree. We want the application/user space to know an
- * error happened while attempting to persist file data so that
- * it can take proper action. If such error happened, we leave
- * without writing to the log tree and the fsync must report the
- * file data write error and not commit the current transaction.
- */
- err = btrfs_inode_check_errors(inode);
- if (err) {
- ctx->io_err = err;
- goto out_unlock;
- }
ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
&logged_list, ctx, start, end);
if (ret) {
@@ -4988,7 +4965,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
goto out;
if (!S_ISDIR(inode->i_mode)) {
- if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
goto out;
inode = d_inode(parent);
}
@@ -5009,7 +4986,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
break;
}
- if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
break;
if (IS_ROOT(parent))
@@ -5158,7 +5135,7 @@ process_leaf:
}
ctx->log_new_dentries = false;
- if (type == BTRFS_FT_DIR)
+ if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
log_mode = LOG_INODE_ALL;
btrfs_release_path(path);
ret = btrfs_log_inode(trans, root, di_inode,
@@ -5278,11 +5255,16 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
if (IS_ERR(dir_inode))
continue;
+ if (ctx)
+ ctx->log_new_dentries = false;
ret = btrfs_log_inode(trans, root, dir_inode,
LOG_INODE_ALL, 0, LLONG_MAX, ctx);
if (!ret &&
btrfs_must_commit_transaction(trans, dir_inode))
ret = 1;
+ if (!ret && ctx && ctx->log_new_dentries)
+ ret = log_new_dir_dentries(trans, root,
+ dir_inode, ctx);
iput(dir_inode);
if (ret)
goto out;
@@ -5422,7 +5404,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
}
while (1) {
- if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
break;
inode = d_inode(parent);
@@ -5519,7 +5501,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
ret = walk_log_tree(trans, log_root_tree, &wc);
if (ret) {
- btrfs_std_error(fs_info, ret, "Failed to pin buffers while "
+ btrfs_handle_fs_error(fs_info, ret, "Failed to pin buffers while "
"recovering log root tree.");
goto error;
}
@@ -5533,7 +5515,7 @@ again:
ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);
if (ret < 0) {
- btrfs_std_error(fs_info, ret,
+ btrfs_handle_fs_error(fs_info, ret,
"Couldn't find tree log root.");
goto error;
}
@@ -5551,7 +5533,7 @@ again:
log = btrfs_read_fs_root(log_root_tree, &found_key);
if (IS_ERR(log)) {
ret = PTR_ERR(log);
- btrfs_std_error(fs_info, ret,
+ btrfs_handle_fs_error(fs_info, ret,
"Couldn't read tree log root.");
goto error;
}
@@ -5566,7 +5548,7 @@ again:
free_extent_buffer(log->node);
free_extent_buffer(log->commit_root);
kfree(log);
- btrfs_std_error(fs_info, ret, "Couldn't read target root "
+ btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root "
"for tree log recovery.");
goto error;
}
@@ -5652,11 +5634,9 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
* into the file. When the file is logged we check it and
* don't log the parents if the file is fully on disk.
*/
- if (S_ISREG(inode->i_mode)) {
- mutex_lock(&BTRFS_I(inode)->log_mutex);
- BTRFS_I(inode)->last_unlink_trans = trans->transid;
- mutex_unlock(&BTRFS_I(inode)->log_mutex);
- }
+ mutex_lock(&BTRFS_I(inode)->log_mutex);
+ BTRFS_I(inode)->last_unlink_trans = trans->transid;
+ mutex_unlock(&BTRFS_I(inode)->log_mutex);
/*
* if this directory was already logged any new
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bd0f45fb38c4..2b88127bba5b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -20,13 +20,13 @@
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
-#include <linux/random.h>
#include <linux/iocontext.h>
#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/semaphore.h>
+#include <linux/uuid.h>
#include <asm/div64.h>
#include "ctree.h"
#include "extent_map.h"
@@ -118,6 +118,21 @@ const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID6] = BTRFS_BLOCK_GROUP_RAID6,
};
+/*
+ * Table to convert BTRFS_RAID_* to the error code if minimum number of devices
+ * condition is not met. Zero means there's no corresponding
+ * BTRFS_ERROR_DEV_*_NOT_MET value.
+ */
+const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
+ [BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
+ [BTRFS_RAID_RAID1] = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
+ [BTRFS_RAID_DUP] = 0,
+ [BTRFS_RAID_RAID0] = 0,
+ [BTRFS_RAID_SINGLE] = 0,
+ [BTRFS_RAID_RAID5] = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
+ [BTRFS_RAID_RAID6] = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
+};
+
static int init_first_rw_device(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_device *device);
@@ -699,7 +714,8 @@ static noinline int device_list_add(const char *path,
* if there is new btrfs on an already registered device,
* then remove the stale device entry.
*/
- btrfs_free_stale_device(device);
+ if (ret > 0)
+ btrfs_free_stale_device(device);
*fs_devices_ret = fs_devices;
@@ -988,6 +1004,56 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
return ret;
}
+void btrfs_release_disk_super(struct page *page)
+{
+ kunmap(page);
+ put_page(page);
+}
+
+int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
+ struct page **page, struct btrfs_super_block **disk_super)
+{
+ void *p;
+ pgoff_t index;
+
+ /* make sure our super fits in the device */
+ if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
+ return 1;
+
+ /* make sure our super fits in the page */
+ if (sizeof(**disk_super) > PAGE_SIZE)
+ return 1;
+
+ /* make sure our super doesn't straddle pages on disk */
+ index = bytenr >> PAGE_SHIFT;
+ if ((bytenr + sizeof(**disk_super) - 1) >> PAGE_SHIFT != index)
+ return 1;
+
+ /* pull in the page with our super */
+ *page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
+ index, GFP_KERNEL);
+
+ if (IS_ERR_OR_NULL(*page))
+ return 1;
+
+ p = kmap(*page);
+
+ /* align our pointer to the offset of the super block */
+ *disk_super = p + (bytenr & ~PAGE_MASK);
+
+ if (btrfs_super_bytenr(*disk_super) != bytenr ||
+ btrfs_super_magic(*disk_super) != BTRFS_MAGIC) {
+ btrfs_release_disk_super(*page);
+ return 1;
+ }
+
+ if ((*disk_super)->label[0] &&
+ (*disk_super)->label[BTRFS_LABEL_SIZE - 1])
+ (*disk_super)->label[BTRFS_LABEL_SIZE - 1] = '\0';
+
+ return 0;
+}
+
/*
* Look for a btrfs signature on a device. This may be called out of the mount path
* and we are not allowed to call set_blocksize during the scan. The superblock
@@ -999,13 +1065,11 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
struct btrfs_super_block *disk_super;
struct block_device *bdev;
struct page *page;
- void *p;
int ret = -EINVAL;
u64 devid;
u64 transid;
u64 total_devices;
u64 bytenr;
- pgoff_t index;
/*
* we would like to check all the supers, but that would make
@@ -1018,41 +1082,14 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
mutex_lock(&uuid_mutex);
bdev = blkdev_get_by_path(path, flags, holder);
-
if (IS_ERR(bdev)) {
ret = PTR_ERR(bdev);
goto error;
}
- /* make sure our super fits in the device */
- if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
- goto error_bdev_put;
-
- /* make sure our super fits in the page */
- if (sizeof(*disk_super) > PAGE_SIZE)
- goto error_bdev_put;
-
- /* make sure our super doesn't straddle pages on disk */
- index = bytenr >> PAGE_SHIFT;
- if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index)
- goto error_bdev_put;
-
- /* pull in the page with our super */
- page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
- index, GFP_NOFS);
-
- if (IS_ERR_OR_NULL(page))
+ if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super))
goto error_bdev_put;
- p = kmap(page);
-
- /* align our pointer to the offset of the super block */
- disk_super = p + (bytenr & ~PAGE_MASK);
-
- if (btrfs_super_bytenr(disk_super) != bytenr ||
- btrfs_super_magic(disk_super) != BTRFS_MAGIC)
- goto error_unmap;
-
devid = btrfs_stack_device_id(&disk_super->dev_item);
transid = btrfs_super_generation(disk_super);
total_devices = btrfs_super_num_devices(disk_super);
@@ -1060,8 +1097,6 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
ret = device_list_add(path, disk_super, devid, fs_devices_ret);
if (ret > 0) {
if (disk_super->label[0]) {
- if (disk_super->label[BTRFS_LABEL_SIZE - 1])
- disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
printk(KERN_INFO "BTRFS: device label %s ", disk_super->label);
} else {
printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid);
@@ -1073,9 +1108,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
if (!ret && fs_devices_ret)
(*fs_devices_ret)->total_devices = total_devices;
-error_unmap:
- kunmap(page);
- put_page(page);
+ btrfs_release_disk_super(page);
error_bdev_put:
blkdev_put(bdev, flags);
@@ -1454,7 +1487,7 @@ again:
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_dev_extent);
} else {
- btrfs_std_error(root->fs_info, ret, "Slot search failed");
+ btrfs_handle_fs_error(root->fs_info, ret, "Slot search failed");
goto out;
}
@@ -1462,7 +1495,7 @@ again:
ret = btrfs_del_item(trans, root, path);
if (ret) {
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"Failed to remove dev extent item");
} else {
set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags);
@@ -1688,32 +1721,92 @@ out:
return ret;
}
-int btrfs_rm_device(struct btrfs_root *root, char *device_path)
+/*
+ * Verify that @num_devices satisfies the RAID profile constraints in the whole
+ * filesystem. It's up to the caller to adjust that number regarding eg. device
+ * replace.
+ */
+static int btrfs_check_raid_min_devices(struct btrfs_fs_info *fs_info,
+ u64 num_devices)
+{
+ u64 all_avail;
+ unsigned seq;
+ int i;
+
+ do {
+ seq = read_seqbegin(&fs_info->profiles_lock);
+
+ all_avail = fs_info->avail_data_alloc_bits |
+ fs_info->avail_system_alloc_bits |
+ fs_info->avail_metadata_alloc_bits;
+ } while (read_seqretry(&fs_info->profiles_lock, seq));
+
+ for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+ if (!(all_avail & btrfs_raid_group[i]))
+ continue;
+
+ if (num_devices < btrfs_raid_array[i].devs_min) {
+ int ret = btrfs_raid_mindev_error[i];
+
+ if (ret)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+struct btrfs_device *btrfs_find_next_active_device(struct btrfs_fs_devices *fs_devs,
+ struct btrfs_device *device)
{
- struct btrfs_device *device;
struct btrfs_device *next_device;
- struct block_device *bdev;
- struct buffer_head *bh = NULL;
- struct btrfs_super_block *disk_super;
+
+ list_for_each_entry(next_device, &fs_devs->devices, dev_list) {
+ if (next_device != device &&
+ !next_device->missing && next_device->bdev)
+ return next_device;
+ }
+
+ return NULL;
+}
+
+/*
+ * Helper function to check if the given device is part of s_bdev / latest_bdev
+ * and replace it with the provided or the next active device, in the context
+ * where this function called, there should be always be another device (or
+ * this_dev) which is active.
+ */
+void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *device, struct btrfs_device *this_dev)
+{
+ struct btrfs_device *next_device;
+
+ if (this_dev)
+ next_device = this_dev;
+ else
+ next_device = btrfs_find_next_active_device(fs_info->fs_devices,
+ device);
+ ASSERT(next_device);
+
+ if (fs_info->sb->s_bdev &&
+ (fs_info->sb->s_bdev == device->bdev))
+ fs_info->sb->s_bdev = next_device->bdev;
+
+ if (fs_info->fs_devices->latest_bdev == device->bdev)
+ fs_info->fs_devices->latest_bdev = next_device->bdev;
+}
+
+int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid)
+{
+ struct btrfs_device *device;
struct btrfs_fs_devices *cur_devices;
- u64 all_avail;
- u64 devid;
u64 num_devices;
- u8 *dev_uuid;
- unsigned seq;
int ret = 0;
bool clear_super = false;
+ char *dev_name = NULL;
mutex_lock(&uuid_mutex);
- do {
- seq = read_seqbegin(&root->fs_info->profiles_lock);
-
- all_avail = root->fs_info->avail_data_alloc_bits |
- root->fs_info->avail_system_alloc_bits |
- root->fs_info->avail_metadata_alloc_bits;
- } while (read_seqretry(&root->fs_info->profiles_lock, seq));
-
num_devices = root->fs_info->fs_devices->num_devices;
btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0);
if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) {
@@ -1722,78 +1815,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
}
btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0);
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
- ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET;
- goto out;
- }
-
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) && num_devices <= 2) {
- ret = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET;
+ ret = btrfs_check_raid_min_devices(root->fs_info, num_devices - 1);
+ if (ret)
goto out;
- }
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID5) &&
- root->fs_info->fs_devices->rw_devices <= 2) {
- ret = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET;
- goto out;
- }
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID6) &&
- root->fs_info->fs_devices->rw_devices <= 3) {
- ret = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET;
+ ret = btrfs_find_device_by_devspec(root, devid, device_path,
+ &device);
+ if (ret)
goto out;
- }
-
- if (strcmp(device_path, "missing") == 0) {
- struct list_head *devices;
- struct btrfs_device *tmp;
-
- device = NULL;
- devices = &root->fs_info->fs_devices->devices;
- /*
- * It is safe to read the devices since the volume_mutex
- * is held.
- */
- list_for_each_entry(tmp, devices, dev_list) {
- if (tmp->in_fs_metadata &&
- !tmp->is_tgtdev_for_dev_replace &&
- !tmp->bdev) {
- device = tmp;
- break;
- }
- }
- bdev = NULL;
- bh = NULL;
- disk_super = NULL;
- if (!device) {
- ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
- goto out;
- }
- } else {
- ret = btrfs_get_bdev_and_sb(device_path,
- FMODE_WRITE | FMODE_EXCL,
- root->fs_info->bdev_holder, 0,
- &bdev, &bh);
- if (ret)
- goto out;
- disk_super = (struct btrfs_super_block *)bh->b_data;
- devid = btrfs_stack_device_id(&disk_super->dev_item);
- dev_uuid = disk_super->dev_item.uuid;
- device = btrfs_find_device(root->fs_info, devid, dev_uuid,
- disk_super->fsid);
- if (!device) {
- ret = -ENOENT;
- goto error_brelse;
- }
- }
if (device->is_tgtdev_for_dev_replace) {
ret = BTRFS_ERROR_DEV_TGT_REPLACE;
- goto error_brelse;
+ goto out;
}
if (device->writeable && root->fs_info->fs_devices->rw_devices == 1) {
ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
- goto error_brelse;
+ goto out;
}
if (device->writeable) {
@@ -1801,6 +1839,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
list_del_init(&device->dev_alloc_list);
device->fs_devices->rw_devices--;
unlock_chunks(root);
+ dev_name = kstrdup(device->name->str, GFP_KERNEL);
+ if (!dev_name) {
+ ret = -ENOMEM;
+ goto error_undo;
+ }
clear_super = true;
}
@@ -1842,12 +1885,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
if (device->missing)
device->fs_devices->missing_devices--;
- next_device = list_entry(root->fs_info->fs_devices->devices.next,
- struct btrfs_device, dev_list);
- if (device->bdev == root->fs_info->sb->s_bdev)
- root->fs_info->sb->s_bdev = next_device->bdev;
- if (device->bdev == root->fs_info->fs_devices->latest_bdev)
- root->fs_info->fs_devices->latest_bdev = next_device->bdev;
+ btrfs_assign_next_active_device(root->fs_info, device, NULL);
if (device->bdev) {
device->fs_devices->open_devices--;
@@ -1883,63 +1921,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
* at this point, the device is zero sized. We want to
* remove it from the devices list and zero out the old super
*/
- if (clear_super && disk_super) {
- u64 bytenr;
- int i;
-
- /* make sure this device isn't detected as part of
- * the FS anymore
- */
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
- set_buffer_dirty(bh);
- sync_dirty_buffer(bh);
-
- /* clear the mirror copies of super block on the disk
- * being removed, 0th copy is been taken care above and
- * the below would take of the rest
- */
- for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) {
- bytenr = btrfs_sb_offset(i);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >=
- i_size_read(bdev->bd_inode))
- break;
-
- brelse(bh);
- bh = __bread(bdev, bytenr / 4096,
- BTRFS_SUPER_INFO_SIZE);
- if (!bh)
- continue;
-
- disk_super = (struct btrfs_super_block *)bh->b_data;
-
- if (btrfs_super_bytenr(disk_super) != bytenr ||
- btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- continue;
- }
- memset(&disk_super->magic, 0,
- sizeof(disk_super->magic));
- set_buffer_dirty(bh);
- sync_dirty_buffer(bh);
+ if (clear_super) {
+ struct block_device *bdev;
+
+ bdev = blkdev_get_by_path(dev_name, FMODE_READ | FMODE_EXCL,
+ root->fs_info->bdev_holder);
+ if (!IS_ERR(bdev)) {
+ btrfs_scratch_superblocks(bdev, dev_name);
+ blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
}
}
- ret = 0;
-
- if (bdev) {
- /* Notify udev that device has changed */
- btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
-
- /* Update ctime/mtime for device path for libblkid */
- update_dev_time(device_path);
- }
-
-error_brelse:
- brelse(bh);
- if (bdev)
- blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
out:
+ kfree(dev_name);
+
mutex_unlock(&uuid_mutex);
return ret;
+
error_undo:
if (device->writeable) {
lock_chunks(root);
@@ -1948,7 +1946,7 @@ error_undo:
device->fs_devices->rw_devices++;
unlock_chunks(root);
}
- goto error_brelse;
+ goto out;
}
void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
@@ -1972,11 +1970,8 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
if (srcdev->missing)
fs_devices->missing_devices--;
- if (srcdev->writeable) {
+ if (srcdev->writeable)
fs_devices->rw_devices--;
- /* zero out the old super if it is writable */
- btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
- }
if (srcdev->bdev)
fs_devices->open_devices--;
@@ -1987,6 +1982,10 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
{
struct btrfs_fs_devices *fs_devices = srcdev->fs_devices;
+ if (srcdev->writeable) {
+ /* zero out the old super if it is writable */
+ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
+ }
call_rcu(&srcdev->rcu, free_device);
/*
@@ -2016,32 +2015,33 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
struct btrfs_device *tgtdev)
{
- struct btrfs_device *next_device;
-
mutex_lock(&uuid_mutex);
WARN_ON(!tgtdev);
mutex_lock(&fs_info->fs_devices->device_list_mutex);
btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
- if (tgtdev->bdev) {
- btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+ if (tgtdev->bdev)
fs_info->fs_devices->open_devices--;
- }
+
fs_info->fs_devices->num_devices--;
- next_device = list_entry(fs_info->fs_devices->devices.next,
- struct btrfs_device, dev_list);
- if (tgtdev->bdev == fs_info->sb->s_bdev)
- fs_info->sb->s_bdev = next_device->bdev;
- if (tgtdev->bdev == fs_info->fs_devices->latest_bdev)
- fs_info->fs_devices->latest_bdev = next_device->bdev;
- list_del_rcu(&tgtdev->dev_list);
+ btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
- call_rcu(&tgtdev->rcu, free_device);
+ list_del_rcu(&tgtdev->dev_list);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
mutex_unlock(&uuid_mutex);
+
+ /*
+ * The update_dev_time() with in btrfs_scratch_superblocks()
+ * may lead to a call to btrfs_show_devname() which will try
+ * to hold device_list_mutex. And here this device
+ * is already out of device list, so we don't have to hold
+ * the device_list_mutex lock.
+ */
+ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+ call_rcu(&tgtdev->rcu, free_device);
}
static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,
@@ -2102,6 +2102,31 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
}
/*
+ * Lookup a device given by device id, or the path if the id is 0.
+ */
+int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid,
+ char *devpath,
+ struct btrfs_device **device)
+{
+ int ret;
+
+ if (devid) {
+ ret = 0;
+ *device = btrfs_find_device(root->fs_info, devid, NULL,
+ NULL);
+ if (!*device)
+ ret = -ENOENT;
+ } else {
+ if (!devpath || !devpath[0])
+ return -EINVAL;
+
+ ret = btrfs_find_device_missing_or_by_path(root, devpath,
+ device);
+ }
+ return ret;
+}
+
+/*
* does all the dirty work required for changing file system's UUID.
*/
static int btrfs_prepare_sprout(struct btrfs_root *root)
@@ -2418,7 +2443,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
ret = btrfs_relocate_sys_chunks(root);
if (ret < 0)
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"Failed to relocate sys chunks after "
"device initialization. This can be fixed "
"using the \"btrfs balance\" command.");
@@ -2663,7 +2688,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
if (ret < 0)
goto out;
else if (ret > 0) { /* Logic error or corruption */
- btrfs_std_error(root->fs_info, -ENOENT,
+ btrfs_handle_fs_error(root->fs_info, -ENOENT,
"Failed lookup while freeing chunk.");
ret = -ENOENT;
goto out;
@@ -2671,7 +2696,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
ret = btrfs_del_item(trans, root, path);
if (ret < 0)
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"Failed to delete chunk item.");
out:
btrfs_free_path(path);
@@ -2857,7 +2882,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
chunk_offset);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- btrfs_std_error(root->fs_info, ret, NULL);
+ btrfs_handle_fs_error(root->fs_info, ret, NULL);
return ret;
}
@@ -3402,6 +3427,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
u32 count_meta = 0;
u32 count_sys = 0;
int chunk_reserved = 0;
+ u64 bytes_used = 0;
/* step one make some room on all the devices */
devices = &fs_info->fs_devices->devices;
@@ -3540,7 +3566,13 @@ again:
goto loop;
}
- if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) {
+ ASSERT(fs_info->data_sinfo);
+ spin_lock(&fs_info->data_sinfo->lock);
+ bytes_used = fs_info->data_sinfo->bytes_used;
+ spin_unlock(&fs_info->data_sinfo->lock);
+
+ if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) &&
+ !chunk_reserved && !bytes_used) {
trans = btrfs_start_transaction(chunk_root, 0);
if (IS_ERR(trans)) {
mutex_unlock(&fs_info->delete_unused_bgs_mutex);
@@ -3632,7 +3664,7 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info)
unset_balance_control(fs_info);
ret = del_balance_item(fs_info->tree_root);
if (ret)
- btrfs_std_error(fs_info, ret, NULL);
+ btrfs_handle_fs_error(fs_info, ret, NULL);
atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
}
@@ -3693,10 +3725,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
num_devices--;
}
btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
- allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
- if (num_devices == 1)
- allowed |= BTRFS_BLOCK_GROUP_DUP;
- else if (num_devices > 1)
+ allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP;
+ if (num_devices > 1)
allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
if (num_devices > 2)
allowed |= BTRFS_BLOCK_GROUP_RAID5;
@@ -5278,7 +5308,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
stripe_nr = div64_u64(stripe_nr, stripe_len);
stripe_offset = stripe_nr * stripe_len;
- BUG_ON(offset < stripe_offset);
+ if (offset < stripe_offset) {
+ btrfs_crit(fs_info, "stripe math has gone wrong, "
+ "stripe_offset=%llu, offset=%llu, start=%llu, "
+ "logical=%llu, stripe_len=%llu",
+ stripe_offset, offset, em->start, logical,
+ stripe_len);
+ free_extent_map(em);
+ return -EINVAL;
+ }
/* stripe_offset is the offset of this block in its stripe*/
stripe_offset = offset - stripe_offset;
@@ -5519,7 +5557,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
&stripe_index);
mirror_num = stripe_index + 1;
}
- BUG_ON(stripe_index >= map->num_stripes);
+ if (stripe_index >= map->num_stripes) {
+ btrfs_crit(fs_info, "stripe index math went horribly wrong, "
+ "got stripe_index=%u, num_stripes=%u",
+ stripe_index, map->num_stripes);
+ ret = -EINVAL;
+ goto out;
+ }
num_alloc_stripes = num_stripes;
if (dev_replace_is_ongoing) {
@@ -6242,7 +6286,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
"invalid chunk length %llu", length);
return -EIO;
}
- if (!is_power_of_2(stripe_len)) {
+ if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) {
btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
stripe_len);
return -EIO;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1939ebde63df..0ac90f8d85bd 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -340,14 +340,14 @@ struct btrfs_raid_attr {
};
extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
-
+extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES];
extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES];
struct map_lookup {
u64 type;
int io_align;
int io_width;
- int stripe_len;
+ u64 stripe_len;
int sector_size;
int num_stripes;
int sub_stripes;
@@ -357,52 +357,6 @@ struct map_lookup {
#define map_lookup_size(n) (sizeof(struct map_lookup) + \
(sizeof(struct btrfs_bio_stripe) * (n)))
-/*
- * Restriper's general type filter
- */
-#define BTRFS_BALANCE_DATA (1ULL << 0)
-#define BTRFS_BALANCE_SYSTEM (1ULL << 1)
-#define BTRFS_BALANCE_METADATA (1ULL << 2)
-
-#define BTRFS_BALANCE_TYPE_MASK (BTRFS_BALANCE_DATA | \
- BTRFS_BALANCE_SYSTEM | \
- BTRFS_BALANCE_METADATA)
-
-#define BTRFS_BALANCE_FORCE (1ULL << 3)
-#define BTRFS_BALANCE_RESUME (1ULL << 4)
-
-/*
- * Balance filters
- */
-#define BTRFS_BALANCE_ARGS_PROFILES (1ULL << 0)
-#define BTRFS_BALANCE_ARGS_USAGE (1ULL << 1)
-#define BTRFS_BALANCE_ARGS_DEVID (1ULL << 2)
-#define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3)
-#define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4)
-#define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5)
-#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6)
-#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7)
-#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10)
-
-#define BTRFS_BALANCE_ARGS_MASK \
- (BTRFS_BALANCE_ARGS_PROFILES | \
- BTRFS_BALANCE_ARGS_USAGE | \
- BTRFS_BALANCE_ARGS_DEVID | \
- BTRFS_BALANCE_ARGS_DRANGE | \
- BTRFS_BALANCE_ARGS_VRANGE | \
- BTRFS_BALANCE_ARGS_LIMIT | \
- BTRFS_BALANCE_ARGS_LIMIT_RANGE | \
- BTRFS_BALANCE_ARGS_STRIPES_RANGE | \
- BTRFS_BALANCE_ARGS_USAGE_RANGE)
-
-/*
- * Profile changing flags. When SOFT is set we won't relocate chunk if
- * it already has the target profile (even though it may be
- * half-filled).
- */
-#define BTRFS_BALANCE_ARGS_CONVERT (1ULL << 8)
-#define BTRFS_BALANCE_ARGS_SOFT (1ULL << 9)
-
struct btrfs_balance_args;
struct btrfs_balance_progress;
struct btrfs_balance_control {
@@ -445,13 +399,18 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
struct btrfs_fs_devices **fs_devices_ret);
int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step);
+void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *device, struct btrfs_device *this_dev);
int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
char *device_path,
struct btrfs_device **device);
+int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid,
+ char *devpath,
+ struct btrfs_device **device);
struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
const u64 *devid,
const u8 *uuid);
-int btrfs_rm_device(struct btrfs_root *root, char *device_path);
+int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid);
void btrfs_cleanup_fs_uuids(void);
int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
int btrfs_grow_device(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 145d2b89e62d..3bfb252206c7 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -237,6 +237,9 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
+ if (btrfs_root_readonly(root))
+ return -EROFS;
+
if (trans)
return do_setxattr(trans, inode, name, value, size, flags);
@@ -369,11 +372,9 @@ err:
}
static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- struct inode *inode = d_inode(dentry);
-
name = xattr_full_name(handler, name);
return __btrfs_getxattr(inode, name, buffer, size);
}
@@ -434,25 +435,6 @@ const struct xattr_handler *btrfs_xattr_handlers[] = {
NULL,
};
-int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags)
-{
- struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-
- if (btrfs_root_readonly(root))
- return -EROFS;
- return generic_setxattr(dentry, name, value, size, flags);
-}
-
-int btrfs_removexattr(struct dentry *dentry, const char *name)
-{
- struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-
- if (btrfs_root_readonly(root))
- return -EROFS;
- return generic_removexattr(dentry, name);
-}
-
static int btrfs_initxattrs(struct inode *inode,
const struct xattr *xattr_array, void *fs_info)
{
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 96807b3d22f5..15fc4743dc70 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -28,9 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
extern int __btrfs_setxattr(struct btrfs_trans_handle *trans,
struct inode *inode, const char *name,
const void *value, size_t size, int flags);
-extern int btrfs_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
-extern int btrfs_removexattr(struct dentry *dentry, const char *name);
extern int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir,
diff --git a/fs/buffer.c b/fs/buffer.c
index af0d9a82a8ed..754813a6962b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -255,17 +255,17 @@ out:
*/
static void free_more_memory(void)
{
- struct zone *zone;
+ struct zoneref *z;
int nid;
wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM);
yield();
for_each_online_node(nid) {
- (void)first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
- gfp_zone(GFP_NOFS), NULL,
- &zone);
- if (zone)
+
+ z = first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
+ gfp_zone(GFP_NOFS), NULL);
+ if (z->zone)
try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
GFP_NOFS, NULL);
}
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index f19708487e2f..4f67227f69a5 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -37,6 +37,8 @@ static inline void ceph_set_cached_acl(struct inode *inode,
spin_lock(&ci->i_ceph_lock);
if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
set_cached_acl(inode, type, acl);
+ else
+ forget_cached_acl(inode, type);
spin_unlock(&ci->i_ceph_lock);
}
@@ -88,7 +90,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
char *value = NULL;
struct iattr newattrs;
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
- struct dentry *dentry;
switch (type) {
case ACL_TYPE_ACCESS:
@@ -126,29 +127,26 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
goto out_free;
}
- dentry = d_find_alias(inode);
if (new_mode != old_mode) {
newattrs.ia_mode = new_mode;
newattrs.ia_valid = ATTR_MODE;
- ret = ceph_setattr(dentry, &newattrs);
+ ret = __ceph_setattr(inode, &newattrs);
if (ret)
- goto out_dput;
+ goto out_free;
}
- ret = __ceph_setxattr(dentry, name, value, size, 0);
+ ret = __ceph_setxattr(inode, name, value, size, 0);
if (ret) {
if (new_mode != old_mode) {
newattrs.ia_mode = old_mode;
newattrs.ia_valid = ATTR_MODE;
- ceph_setattr(dentry, &newattrs);
+ __ceph_setattr(inode, &newattrs);
}
- goto out_dput;
+ goto out_free;
}
ceph_set_cached_acl(inode, type, acl);
-out_dput:
- dput(dentry);
out_free:
kfree(value);
out:
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4801571f51cb..43098cd9602b 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1292,8 +1292,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
* intercept O_DIRECT reads and writes early, this function should
* never get called.
*/
-static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter,
- loff_t pos)
+static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter)
{
WARN_ON(1);
return -EINVAL;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4fb2bbc2a272..3ab1192d2029 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -5,6 +5,7 @@
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/sched.h>
+#include <linux/xattr.h>
#include "super.h"
#include "mds_client.h"
@@ -1342,10 +1343,10 @@ const struct inode_operations ceph_dir_iops = {
.permission = ceph_permission,
.getattr = ceph_getattr,
.setattr = ceph_setattr,
- .setxattr = ceph_setxattr,
- .getxattr = ceph_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ceph_listxattr,
- .removexattr = ceph_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ceph_get_acl,
.set_acl = ceph_set_acl,
.mknod = ceph_mknod,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index a79f9269831e..4f1dc7120916 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1382,12 +1382,11 @@ retry_snap:
ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
- if (written >= 0 &&
- ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) ||
- ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
- err = vfs_fsync_range(file, pos, pos + written - 1, 1);
- if (err < 0)
- written = err;
+ if (written >= 0) {
+ if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))
+ iocb->ki_flags |= IOCB_DSYNC;
+
+ written = generic_write_sync(iocb, written);
}
goto out_unlocked;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index edfade037738..e669cfa9d793 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -8,6 +8,7 @@
#include <linux/kernel.h>
#include <linux/writeback.h>
#include <linux/vmalloc.h>
+#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/random.h>
@@ -92,10 +93,10 @@ const struct inode_operations ceph_file_iops = {
.permission = ceph_permission,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
- .setxattr = ceph_setxattr,
- .getxattr = ceph_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ceph_listxattr,
- .removexattr = ceph_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ceph_get_acl,
.set_acl = ceph_set_acl,
};
@@ -1770,22 +1771,18 @@ static const struct inode_operations ceph_symlink_iops = {
.get_link = simple_get_link,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
- .setxattr = ceph_setxattr,
- .getxattr = ceph_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ceph_listxattr,
- .removexattr = ceph_removexattr,
+ .removexattr = generic_removexattr,
};
-/*
- * setattr
- */
-int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+int __ceph_setattr(struct inode *inode, struct iattr *attr)
{
- struct inode *inode = d_inode(dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
const unsigned int ia_valid = attr->ia_valid;
struct ceph_mds_request *req;
- struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
+ struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_cap_flush *prealloc_cf;
int issued;
int release = 0, dirtied = 0;
@@ -2010,6 +2007,14 @@ out_put:
}
/*
+ * setattr
+ */
+int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ return __ceph_setattr(d_inode(dentry), attr);
+}
+
+/*
* Verify that we have a lease on the given mask. If not,
* do a getattr against an mds.
*/
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 541ead4d8965..85b8517f17a0 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -386,9 +386,7 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
if (atomic_dec_and_test(&s->s_ref)) {
if (s->s_auth.authorizer)
- ceph_auth_destroy_authorizer(
- s->s_mdsc->fsc->client->monc.auth,
- s->s_auth.authorizer);
+ ceph_auth_destroy_authorizer(s->s_auth.authorizer);
kfree(s);
}
}
@@ -3900,7 +3898,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
struct ceph_auth_handshake *auth = &s->s_auth;
if (force_new && auth->authorizer) {
- ceph_auth_destroy_authorizer(ac, auth->authorizer);
+ ceph_auth_destroy_authorizer(auth->authorizer);
auth->authorizer = NULL;
}
if (!auth->authorizer) {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index e705c4d612d7..7b99eb756477 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -785,19 +785,15 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
return __ceph_do_getattr(inode, NULL, mask, force);
}
extern int ceph_permission(struct inode *inode, int mask);
+extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
/* xattr.c */
-extern int ceph_setxattr(struct dentry *, const char *, const void *,
- size_t, int);
-int __ceph_setxattr(struct dentry *, const char *, const void *, size_t, int);
+int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
-int __ceph_removexattr(struct dentry *, const char *);
-extern ssize_t ceph_getxattr(struct dentry *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
-extern int ceph_removexattr(struct dentry *, const char *);
extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
extern void __init ceph_xattr_init(void);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 9410abdef3ce..0d66722c6a52 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -16,6 +16,8 @@
static int __remove_xattr(struct ceph_inode_info *ci,
struct ceph_inode_xattr *xattr);
+const struct xattr_handler ceph_other_xattr_handler;
+
/*
* List of handlers for synthetic system.* attributes. Other
* attributes are handled directly.
@@ -25,6 +27,7 @@ const struct xattr_handler *ceph_xattr_handlers[] = {
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
+ &ceph_other_xattr_handler,
NULL,
};
@@ -33,7 +36,6 @@ static bool ceph_is_valid_xattr(const char *name)
return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) ||
!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) ||
- !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) ||
!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
}
@@ -496,19 +498,6 @@ static int __remove_xattr(struct ceph_inode_info *ci,
return 0;
}
-static int __remove_xattr_by_name(struct ceph_inode_info *ci,
- const char *name)
-{
- struct rb_node **p;
- struct ceph_inode_xattr *xattr;
- int err;
-
- p = &ci->i_xattrs.index.rb_node;
- xattr = __get_xattr(ci, name);
- err = __remove_xattr(ci, xattr);
- return err;
-}
-
static char *__copy_xattr_names(struct ceph_inode_info *ci,
char *dest)
{
@@ -740,9 +729,6 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
int req_mask;
int err;
- if (!ceph_is_valid_xattr(name))
- return -ENODATA;
-
/* let's see if a virtual xattr was requested */
vxattr = ceph_match_vxattr(inode, name);
if (vxattr) {
@@ -804,15 +790,6 @@ out:
return err;
}
-ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
- size_t size)
-{
- if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return generic_getxattr(dentry, name, value, size);
-
- return __ceph_getxattr(d_inode(dentry), name, value, size);
-}
-
ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
{
struct inode *inode = d_inode(dentry);
@@ -877,11 +854,10 @@ out:
return err;
}
-static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
+static int ceph_sync_setxattr(struct inode *inode, const char *name,
const char *value, size_t size, int flags)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
- struct inode *inode = d_inode(dentry);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -939,13 +915,12 @@ out:
return err;
}
-int __ceph_setxattr(struct dentry *dentry, const char *name,
+int __ceph_setxattr(struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
struct ceph_vxattr *vxattr;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
+ struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_cap_flush *prealloc_cf = NULL;
int issued;
int err;
@@ -958,8 +933,8 @@ int __ceph_setxattr(struct dentry *dentry, const char *name,
int required_blob_size;
bool lock_snap_rwsem = false;
- if (!ceph_is_valid_xattr(name))
- return -EOPNOTSUPP;
+ if (ceph_snap(inode) != CEPH_NOSNAP)
+ return -EROFS;
vxattr = ceph_match_vxattr(inode, name);
if (vxattr && vxattr->readonly)
@@ -1056,7 +1031,7 @@ do_sync_unlocked:
"during filling trace\n", inode);
err = -EBUSY;
} else {
- err = ceph_sync_setxattr(dentry, name, value, size, flags);
+ err = ceph_sync_setxattr(inode, name, value, size, flags);
}
out:
ceph_free_cap_flush(prealloc_cf);
@@ -1066,146 +1041,29 @@ out:
return err;
}
-int ceph_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
-{
- if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
- return -EROFS;
-
- if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return generic_setxattr(dentry, name, value, size, flags);
-
- if (size == 0)
- value = ""; /* empty EA, do not remove */
-
- return __ceph_setxattr(dentry, name, value, size, flags);
-}
-
-static int ceph_send_removexattr(struct dentry *dentry, const char *name)
+static int ceph_get_xattr_handler(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
- struct ceph_mds_client *mdsc = fsc->mdsc;
- struct inode *inode = d_inode(dentry);
- struct ceph_mds_request *req;
- int err;
-
- req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RMXATTR,
- USE_AUTH_MDS);
- if (IS_ERR(req))
- return PTR_ERR(req);
- req->r_path2 = kstrdup(name, GFP_NOFS);
- if (!req->r_path2)
- return -ENOMEM;
-
- req->r_inode = inode;
- ihold(inode);
- req->r_num_caps = 1;
- req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
- err = ceph_mdsc_do_request(mdsc, NULL, req);
- ceph_mdsc_put_request(req);
- return err;
+ if (!ceph_is_valid_xattr(name))
+ return -EOPNOTSUPP;
+ return __ceph_getxattr(inode, name, value, size);
}
-int __ceph_removexattr(struct dentry *dentry, const char *name)
+static int ceph_set_xattr_handler(const struct xattr_handler *handler,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
- struct ceph_vxattr *vxattr;
- struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
- struct ceph_cap_flush *prealloc_cf = NULL;
- int issued;
- int err;
- int required_blob_size;
- int dirty;
- bool lock_snap_rwsem = false;
-
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
-
- vxattr = ceph_match_vxattr(inode, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
-
- /* pass any unhandled ceph.* xattrs through to the MDS */
- if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
- goto do_sync_unlocked;
-
- prealloc_cf = ceph_alloc_cap_flush();
- if (!prealloc_cf)
- return -ENOMEM;
-
- err = -ENOMEM;
- spin_lock(&ci->i_ceph_lock);
-retry:
- issued = __ceph_caps_issued(ci, NULL);
- if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
- goto do_sync;
-
- if (!lock_snap_rwsem && !ci->i_head_snapc) {
- lock_snap_rwsem = true;
- if (!down_read_trylock(&mdsc->snap_rwsem)) {
- spin_unlock(&ci->i_ceph_lock);
- down_read(&mdsc->snap_rwsem);
- spin_lock(&ci->i_ceph_lock);
- goto retry;
- }
- }
-
- dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
-
- __build_xattrs(inode);
-
- required_blob_size = __get_required_blob_size(ci, 0, 0);
-
- if (!ci->i_xattrs.prealloc_blob ||
- required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
- struct ceph_buffer *blob;
-
- spin_unlock(&ci->i_ceph_lock);
- dout(" preaallocating new blob size=%d\n", required_blob_size);
- blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
- if (!blob)
- goto do_sync_unlocked;
- spin_lock(&ci->i_ceph_lock);
- if (ci->i_xattrs.prealloc_blob)
- ceph_buffer_put(ci->i_xattrs.prealloc_blob);
- ci->i_xattrs.prealloc_blob = blob;
- goto retry;
- }
-
- err = __remove_xattr_by_name(ceph_inode(inode), name);
-
- dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
- &prealloc_cf);
- ci->i_xattrs.dirty = true;
- inode->i_ctime = current_fs_time(inode->i_sb);
- spin_unlock(&ci->i_ceph_lock);
- if (lock_snap_rwsem)
- up_read(&mdsc->snap_rwsem);
- if (dirty)
- __mark_inode_dirty(inode, dirty);
- ceph_free_cap_flush(prealloc_cf);
- return err;
-do_sync:
- spin_unlock(&ci->i_ceph_lock);
-do_sync_unlocked:
- if (lock_snap_rwsem)
- up_read(&mdsc->snap_rwsem);
- ceph_free_cap_flush(prealloc_cf);
- err = ceph_send_removexattr(dentry, name);
- return err;
+ return __ceph_setxattr(d_inode(dentry), name, value, size, flags);
}
-int ceph_removexattr(struct dentry *dentry, const char *name)
-{
- if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
- return -EROFS;
-
- if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return generic_removexattr(dentry, name);
-
- return __ceph_removexattr(dentry, name);
-}
+const struct xattr_handler ceph_other_xattr_handler = {
+ .prefix = "", /* match any name => handlers called with full name */
+ .get = ceph_get_xattr_handler,
+ .set = ceph_set_xattr_handler,
+};
#ifdef CONFIG_SECURITY
bool ceph_security_xattr_wanted(struct inode *in)
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 24b142569ca9..687471dc04a0 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -91,6 +91,10 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor,
break;
}
+ if (i < CHRDEV_MAJOR_DYN_END)
+ pr_warn("CHRDEV \"%s\" major number %d goes below the dynamic allocation range",
+ name, i);
+
if (i == 0) {
ret = -EBUSY;
goto out;
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 1964d212ab08..eed7eb09f46f 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -5,9 +5,10 @@ obj-$(CONFIG_CIFS) += cifs.o
cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
- cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
+ cifs_unicode.o nterr.o cifsencrypt.o \
readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o
+cifs-$(CONFIG_CIFS_XATTR) += xattr.o
cifs-$(CONFIG_CIFS_ACL) += cifsacl.o
cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index e956cba94338..ec9dbbcca3b9 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -151,8 +151,12 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
if (sb_mountdata == NULL)
return ERR_PTR(-EINVAL);
- if (strlen(fullpath) - ref->path_consumed)
+ if (strlen(fullpath) - ref->path_consumed) {
prepath = fullpath + ref->path_consumed;
+ /* skip initial delimiter */
+ if (*prepath == '/' || *prepath == '\\')
+ prepath++;
+ }
*devname = cifs_build_devname(ref->node_name, prepath);
if (IS_ERR(*devname)) {
@@ -302,7 +306,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
if (full_path == NULL)
goto cdda_exit;
- cifs_sb = CIFS_SB(d_inode(mntpt)->i_sb);
+ cifs_sb = CIFS_SB(mntpt->d_sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
mnt = ERR_CAST(tlink);
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 6908080e9b6d..b611fc2e8984 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -24,10 +24,13 @@
#include <linux/string.h>
#include <keys/user-type.h>
#include <linux/key-type.h>
+#include <linux/keyctl.h>
#include <linux/inet.h>
#include "cifsglob.h"
#include "cifs_spnego.h"
#include "cifs_debug.h"
+#include "cifsproto.h"
+static const struct cred *spnego_cred;
/* create a new cifs key */
static int
@@ -102,6 +105,7 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo)
size_t desc_len;
struct key *spnego_key;
const char *hostname = server->hostname;
+ const struct cred *saved_cred;
/* length of fields (with semicolons): ver=0xyz ip4=ipaddress
host=hostname sec=mechanism uid=0xFF user=username */
@@ -163,7 +167,9 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo)
sprintf(dp, ";pid=0x%x", current->pid);
cifs_dbg(FYI, "key description = %s\n", description);
+ saved_cred = override_creds(spnego_cred);
spnego_key = request_key(&cifs_spnego_key_type, description, "");
+ revert_creds(saved_cred);
#ifdef CONFIG_CIFS_DEBUG2
if (cifsFYI && !IS_ERR(spnego_key)) {
@@ -177,3 +183,64 @@ out:
kfree(description);
return spnego_key;
}
+
+int
+init_cifs_spnego(void)
+{
+ struct cred *cred;
+ struct key *keyring;
+ int ret;
+
+ cifs_dbg(FYI, "Registering the %s key type\n",
+ cifs_spnego_key_type.name);
+
+ /*
+ * Create an override credential set with special thread keyring for
+ * spnego upcalls.
+ */
+
+ cred = prepare_kernel_cred(NULL);
+ if (!cred)
+ return -ENOMEM;
+
+ keyring = keyring_alloc(".cifs_spnego",
+ GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred,
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ,
+ KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+ if (IS_ERR(keyring)) {
+ ret = PTR_ERR(keyring);
+ goto failed_put_cred;
+ }
+
+ ret = register_key_type(&cifs_spnego_key_type);
+ if (ret < 0)
+ goto failed_put_key;
+
+ /*
+ * instruct request_key() to use this special keyring as a cache for
+ * the results it looks up
+ */
+ set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags);
+ cred->thread_keyring = keyring;
+ cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+ spnego_cred = cred;
+
+ cifs_dbg(FYI, "cifs spnego keyring: %d\n", key_serial(keyring));
+ return 0;
+
+failed_put_key:
+ key_put(keyring);
+failed_put_cred:
+ put_cred(cred);
+ return ret;
+}
+
+void
+exit_cifs_spnego(void)
+{
+ key_revoke(spnego_cred->thread_keyring);
+ unregister_key_type(&cifs_spnego_key_type);
+ put_cred(spnego_cred);
+ cifs_dbg(FYI, "Unregistered %s key type\n", cifs_spnego_key_type.name);
+}
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 3f93125916bf..71e8a56e9479 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -360,7 +360,7 @@ init_cifs_idmap(void)
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred,
(KEY_POS_ALL & ~KEY_POS_SETATTR) |
KEY_USR_VIEW | KEY_USR_READ,
- KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
if (IS_ERR(keyring)) {
ret = PTR_ERR(keyring);
goto failed_put_cred;
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 4897dacf8944..6aeb8d4616a4 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -66,45 +66,15 @@ cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
return 0;
}
-/*
- * Calculate and return the CIFS signature based on the mac key and SMB PDU.
- * The 16 byte signature must be allocated by the caller. Note we only use the
- * 1st eight bytes and that the smb header signature field on input contains
- * the sequence number before this function is called. Also, this function
- * should be called with the server->srv_mutex held.
- */
-static int cifs_calc_signature(struct smb_rqst *rqst,
- struct TCP_Server_Info *server, char *signature)
+int __cifs_calc_signature(struct smb_rqst *rqst,
+ struct TCP_Server_Info *server, char *signature,
+ struct shash_desc *shash)
{
int i;
int rc;
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
- if (iov == NULL || signature == NULL || server == NULL)
- return -EINVAL;
-
- if (!server->secmech.sdescmd5) {
- rc = cifs_crypto_shash_md5_allocate(server);
- if (rc) {
- cifs_dbg(VFS, "%s: Can't alloc md5 crypto\n", __func__);
- return -1;
- }
- }
-
- rc = crypto_shash_init(&server->secmech.sdescmd5->shash);
- if (rc) {
- cifs_dbg(VFS, "%s: Could not init md5\n", __func__);
- return rc;
- }
-
- rc = crypto_shash_update(&server->secmech.sdescmd5->shash,
- server->session_key.response, server->session_key.len);
- if (rc) {
- cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
- return rc;
- }
-
for (i = 0; i < n_vec; i++) {
if (iov[i].iov_len == 0)
continue;
@@ -117,12 +87,10 @@ static int cifs_calc_signature(struct smb_rqst *rqst,
if (i == 0) {
if (iov[0].iov_len <= 8) /* cmd field at offset 9 */
break; /* nothing to sign or corrupt header */
- rc =
- crypto_shash_update(&server->secmech.sdescmd5->shash,
+ rc = crypto_shash_update(shash,
iov[i].iov_base + 4, iov[i].iov_len - 4);
} else {
- rc =
- crypto_shash_update(&server->secmech.sdescmd5->shash,
+ rc = crypto_shash_update(shash,
iov[i].iov_base, iov[i].iov_len);
}
if (rc) {
@@ -134,21 +102,64 @@ static int cifs_calc_signature(struct smb_rqst *rqst,
/* now hash over the rq_pages array */
for (i = 0; i < rqst->rq_npages; i++) {
- struct kvec p_iov;
+ void *kaddr = kmap(rqst->rq_pages[i]);
+ size_t len = rqst->rq_pagesz;
+
+ if (i == rqst->rq_npages - 1)
+ len = rqst->rq_tailsz;
+
+ crypto_shash_update(shash, kaddr, len);
- cifs_rqst_page_to_kvec(rqst, i, &p_iov);
- crypto_shash_update(&server->secmech.sdescmd5->shash,
- p_iov.iov_base, p_iov.iov_len);
kunmap(rqst->rq_pages[i]);
}
- rc = crypto_shash_final(&server->secmech.sdescmd5->shash, signature);
+ rc = crypto_shash_final(shash, signature);
if (rc)
- cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__);
+ cifs_dbg(VFS, "%s: Could not generate hash\n", __func__);
return rc;
}
+/*
+ * Calculate and return the CIFS signature based on the mac key and SMB PDU.
+ * The 16 byte signature must be allocated by the caller. Note we only use the
+ * 1st eight bytes and that the smb header signature field on input contains
+ * the sequence number before this function is called. Also, this function
+ * should be called with the server->srv_mutex held.
+ */
+static int cifs_calc_signature(struct smb_rqst *rqst,
+ struct TCP_Server_Info *server, char *signature)
+{
+ int rc;
+
+ if (!rqst->rq_iov || !signature || !server)
+ return -EINVAL;
+
+ if (!server->secmech.sdescmd5) {
+ rc = cifs_crypto_shash_md5_allocate(server);
+ if (rc) {
+ cifs_dbg(VFS, "%s: Can't alloc md5 crypto\n", __func__);
+ return -1;
+ }
+ }
+
+ rc = crypto_shash_init(&server->secmech.sdescmd5->shash);
+ if (rc) {
+ cifs_dbg(VFS, "%s: Could not init md5\n", __func__);
+ return rc;
+ }
+
+ rc = crypto_shash_update(&server->secmech.sdescmd5->shash,
+ server->session_key.response, server->session_key.len);
+ if (rc) {
+ cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
+ return rc;
+ }
+
+ return __cifs_calc_signature(rqst, server, signature,
+ &server->secmech.sdescmd5->shash);
+}
+
/* must be called with server->srv_mutex held */
int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server,
__u32 *pexpected_response_sequence_number)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 89201564c346..5d8b7edf8a8f 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -37,6 +37,7 @@
#include <linux/freezer.h>
#include <linux/namei.h>
#include <linux/random.h>
+#include <linux/xattr.h>
#include <net/ipv6.h>
#include "cifsfs.h"
#include "cifspdu.h"
@@ -135,6 +136,7 @@ cifs_read_super(struct super_block *sb)
sb->s_magic = CIFS_MAGIC_NUMBER;
sb->s_op = &cifs_super_ops;
+ sb->s_xattr = cifs_xattr_handlers;
sb->s_bdi = &cifs_sb->bdi;
sb->s_blocksize = CIFS_MAX_MSGSIZE;
sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */
@@ -888,44 +890,33 @@ const struct inode_operations cifs_dir_inode_ops = {
.rmdir = cifs_rmdir,
.rename2 = cifs_rename2,
.permission = cifs_permission,
-/* revalidate:cifs_revalidate, */
.setattr = cifs_setattr,
.symlink = cifs_symlink,
.mknod = cifs_mknod,
-#ifdef CONFIG_CIFS_XATTR
- .setxattr = cifs_setxattr,
- .getxattr = cifs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = cifs_listxattr,
- .removexattr = cifs_removexattr,
-#endif
+ .removexattr = generic_removexattr,
};
const struct inode_operations cifs_file_inode_ops = {
-/* revalidate:cifs_revalidate, */
.setattr = cifs_setattr,
- .getattr = cifs_getattr, /* do we need this anymore? */
+ .getattr = cifs_getattr,
.permission = cifs_permission,
-#ifdef CONFIG_CIFS_XATTR
- .setxattr = cifs_setxattr,
- .getxattr = cifs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = cifs_listxattr,
- .removexattr = cifs_removexattr,
-#endif
+ .removexattr = generic_removexattr,
};
const struct inode_operations cifs_symlink_inode_ops = {
.readlink = generic_readlink,
.get_link = cifs_get_link,
.permission = cifs_permission,
- /* BB add the following two eventually */
- /* revalidate: cifs_revalidate,
- setattr: cifs_notify_change, *//* BB do we need notify change */
-#ifdef CONFIG_CIFS_XATTR
- .setxattr = cifs_setxattr,
- .getxattr = cifs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = cifs_listxattr,
- .removexattr = cifs_removexattr,
-#endif
+ .removexattr = generic_removexattr,
};
static int cifs_clone_file_range(struct file *src_file, loff_t off,
@@ -1083,7 +1074,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
};
const struct file_operations cifs_dir_ops = {
- .iterate = cifs_readdir,
+ .iterate_shared = cifs_readdir,
.release = cifs_closedir,
.read = generic_read_dir,
.unlocked_ioctl = cifs_ioctl,
@@ -1307,7 +1298,7 @@ init_cifs(void)
goto out_destroy_mids;
#ifdef CONFIG_CIFS_UPCALL
- rc = register_key_type(&cifs_spnego_key_type);
+ rc = init_cifs_spnego();
if (rc)
goto out_destroy_request_bufs;
#endif /* CONFIG_CIFS_UPCALL */
@@ -1330,7 +1321,7 @@ out_init_cifs_idmap:
out_register_key_type:
#endif
#ifdef CONFIG_CIFS_UPCALL
- unregister_key_type(&cifs_spnego_key_type);
+ exit_cifs_spnego();
out_destroy_request_bufs:
#endif
cifs_destroy_request_bufs();
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 83aac8ba50b0..9dcf974acc47 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -120,15 +120,19 @@ extern const char *cifs_get_link(struct dentry *, struct inode *,
struct delayed_call *);
extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
const char *symname);
-extern int cifs_removexattr(struct dentry *, const char *);
-extern int cifs_setxattr(struct dentry *, const char *, const void *,
- size_t, int);
-extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t);
+
+#ifdef CONFIG_CIFS_XATTR
+extern const struct xattr_handler *cifs_xattr_handlers[];
extern ssize_t cifs_listxattr(struct dentry *, char *, size_t);
+#else
+# define cifs_xattr_handlers NULL
+# define cifs_listxattr NULL
+#endif
+
extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_CIFS_NFSD_EXPORT
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.08"
+#define CIFS_VERSION "2.09"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index f2cc0b3d1af7..bba106cdc43c 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -615,8 +615,6 @@ struct TCP_Server_Info {
bool sec_mskerberos; /* supports legacy MS Kerberos */
bool large_buf; /* is current buffer large? */
struct delayed_work echo; /* echo ping workqueue job */
- struct kvec *iov; /* reusable kvec array for receives */
- unsigned int nr_iov; /* number of kvecs in array */
char *smallbuf; /* pointer to current "small" buffer */
char *bigbuf; /* pointer to current "big" buffer */
unsigned int total_read; /* total amount of data read in this pass */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index eed7ff50faf0..1243bd326591 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -37,8 +37,6 @@ extern void cifs_buf_release(void *);
extern struct smb_hdr *cifs_small_buf_get(void);
extern void cifs_small_buf_release(void *);
extern void free_rsp_buf(int, void *);
-extern void cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx,
- struct kvec *iov);
extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *,
unsigned int /* length */);
extern unsigned int _get_xid(void);
@@ -60,6 +58,8 @@ do { \
} while (0)
extern int init_cifs_idmap(void);
extern void exit_cifs_idmap(void);
+extern int init_cifs_spnego(void);
+extern void exit_cifs_spnego(void);
extern char *build_path_from_dentry(struct dentry *);
extern char *cifs_build_path_to_root(struct smb_vol *vol,
struct cifs_sb_info *cifs_sb,
@@ -181,10 +181,9 @@ extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
extern void dequeue_mid(struct mid_q_entry *mid, bool malformed);
extern int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
- unsigned int to_read);
-extern int cifs_readv_from_socket(struct TCP_Server_Info *server,
- struct kvec *iov_orig, unsigned int nr_segs,
- unsigned int to_read);
+ unsigned int to_read);
+extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
+ struct page *page, unsigned int to_read);
extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb);
extern int cifs_match_super(struct super_block *, void *);
@@ -512,4 +511,7 @@ int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
struct cifs_sb_info *cifs_sb,
const unsigned char *path, char *pbuf,
unsigned int *pbytes_written);
+int __cifs_calc_signature(struct smb_rqst *rqst,
+ struct TCP_Server_Info *server, char *signature,
+ struct shash_desc *shash);
#endif /* _CIFSPROTO_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index a894bf809ff7..d47197ea4ab6 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1447,10 +1447,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
len = min_t(unsigned int, buflen, server->vals->read_rsp_size) -
HEADER_SIZE(server) + 1;
- rdata->iov.iov_base = buf + HEADER_SIZE(server) - 1;
- rdata->iov.iov_len = len;
-
- length = cifs_readv_from_socket(server, &rdata->iov, 1, len);
+ length = cifs_read_from_socket(server,
+ buf + HEADER_SIZE(server) - 1, len);
if (length < 0)
return length;
server->total_read += length;
@@ -1502,9 +1500,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
len = data_offset - server->total_read;
if (len > 0) {
/* read any junk before data into the rest of smallbuf */
- rdata->iov.iov_base = buf + server->total_read;
- rdata->iov.iov_len = len;
- length = cifs_readv_from_socket(server, &rdata->iov, 1, len);
+ length = cifs_read_from_socket(server,
+ buf + server->total_read, len);
if (length < 0)
return length;
server->total_read += length;
@@ -3366,7 +3363,7 @@ static int cifs_copy_posix_acl(char *trgt, char *src, const int buflen,
if (le16_to_cpu(cifs_acl->version) != CIFS_ACL_VERSION)
return -EOPNOTSUPP;
- if (acl_type & ACL_TYPE_ACCESS) {
+ if (acl_type == ACL_TYPE_ACCESS) {
count = le16_to_cpu(cifs_acl->access_entry_count);
pACE = &cifs_acl->ace_array[0];
size = sizeof(struct cifs_posix_acl);
@@ -3377,7 +3374,7 @@ static int cifs_copy_posix_acl(char *trgt, char *src, const int buflen,
size_of_data_area, size);
return -EINVAL;
}
- } else if (acl_type & ACL_TYPE_DEFAULT) {
+ } else if (acl_type == ACL_TYPE_DEFAULT) {
count = le16_to_cpu(cifs_acl->access_entry_count);
size = sizeof(struct cifs_posix_acl);
size += sizeof(struct cifs_posix_ace) * count;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 6f62ac821a84..66736f57b5ab 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -501,99 +501,34 @@ server_unresponsive(struct TCP_Server_Info *server)
return false;
}
-/*
- * kvec_array_init - clone a kvec array, and advance into it
- * @new: pointer to memory for cloned array
- * @iov: pointer to original array
- * @nr_segs: number of members in original array
- * @bytes: number of bytes to advance into the cloned array
- *
- * This function will copy the array provided in iov to a section of memory
- * and advance the specified number of bytes into the new array. It returns
- * the number of segments in the new array. "new" must be at least as big as
- * the original iov array.
- */
-static unsigned int
-kvec_array_init(struct kvec *new, struct kvec *iov, unsigned int nr_segs,
- size_t bytes)
-{
- size_t base = 0;
-
- while (bytes || !iov->iov_len) {
- int copy = min(bytes, iov->iov_len);
-
- bytes -= copy;
- base += copy;
- if (iov->iov_len == base) {
- iov++;
- nr_segs--;
- base = 0;
- }
- }
- memcpy(new, iov, sizeof(*iov) * nr_segs);
- new->iov_base += base;
- new->iov_len -= base;
- return nr_segs;
-}
-
-static struct kvec *
-get_server_iovec(struct TCP_Server_Info *server, unsigned int nr_segs)
-{
- struct kvec *new_iov;
-
- if (server->iov && nr_segs <= server->nr_iov)
- return server->iov;
-
- /* not big enough -- allocate a new one and release the old */
- new_iov = kmalloc(sizeof(*new_iov) * nr_segs, GFP_NOFS);
- if (new_iov) {
- kfree(server->iov);
- server->iov = new_iov;
- server->nr_iov = nr_segs;
- }
- return new_iov;
-}
-
-int
-cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig,
- unsigned int nr_segs, unsigned int to_read)
+static int
+cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
{
int length = 0;
int total_read;
- unsigned int segs;
- struct msghdr smb_msg;
- struct kvec *iov;
- iov = get_server_iovec(server, nr_segs);
- if (!iov)
- return -ENOMEM;
-
- smb_msg.msg_control = NULL;
- smb_msg.msg_controllen = 0;
+ smb_msg->msg_control = NULL;
+ smb_msg->msg_controllen = 0;
- for (total_read = 0; to_read; total_read += length, to_read -= length) {
+ for (total_read = 0; msg_data_left(smb_msg); total_read += length) {
try_to_freeze();
- if (server_unresponsive(server)) {
- total_read = -ECONNABORTED;
- break;
- }
+ if (server_unresponsive(server))
+ return -ECONNABORTED;
- segs = kvec_array_init(iov, iov_orig, nr_segs, total_read);
+ length = sock_recvmsg(server->ssocket, smb_msg, 0);
- length = kernel_recvmsg(server->ssocket, &smb_msg,
- iov, segs, to_read, 0);
+ if (server->tcpStatus == CifsExiting)
+ return -ESHUTDOWN;
- if (server->tcpStatus == CifsExiting) {
- total_read = -ESHUTDOWN;
- break;
- } else if (server->tcpStatus == CifsNeedReconnect) {
+ if (server->tcpStatus == CifsNeedReconnect) {
cifs_reconnect(server);
- total_read = -ECONNABORTED;
- break;
- } else if (length == -ERESTARTSYS ||
- length == -EAGAIN ||
- length == -EINTR) {
+ return -ECONNABORTED;
+ }
+
+ if (length == -ERESTARTSYS ||
+ length == -EAGAIN ||
+ length == -EINTR) {
/*
* Minimum sleep to prevent looping, allowing socket
* to clear and app threads to set tcpStatus
@@ -602,12 +537,12 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig,
usleep_range(1000, 2000);
length = 0;
continue;
- } else if (length <= 0) {
- cifs_dbg(FYI, "Received no data or error: expecting %d\n"
- "got %d", to_read, length);
+ }
+
+ if (length <= 0) {
+ cifs_dbg(FYI, "Received no data or error: %d\n", length);
cifs_reconnect(server);
- total_read = -ECONNABORTED;
- break;
+ return -ECONNABORTED;
}
}
return total_read;
@@ -617,12 +552,21 @@ int
cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
unsigned int to_read)
{
- struct kvec iov;
+ struct msghdr smb_msg;
+ struct kvec iov = {.iov_base = buf, .iov_len = to_read};
+ iov_iter_kvec(&smb_msg.msg_iter, READ | ITER_KVEC, &iov, 1, to_read);
- iov.iov_base = buf;
- iov.iov_len = to_read;
+ return cifs_readv_from_socket(server, &smb_msg);
+}
- return cifs_readv_from_socket(server, &iov, 1, to_read);
+int
+cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
+ unsigned int to_read)
+{
+ struct msghdr smb_msg;
+ struct bio_vec bv = {.bv_page = page, .bv_len = to_read};
+ iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read);
+ return cifs_readv_from_socket(server, &smb_msg);
}
static bool
@@ -783,7 +727,6 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
}
kfree(server->hostname);
- kfree(server->iov);
kfree(server);
length = atomic_dec_return(&tcpSesAllocCount);
@@ -1196,8 +1139,12 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol)
convert_delimiter(vol->UNC, '\\');
- /* If pos is NULL, or is a bogus trailing delimiter then no prepath */
- if (!*pos++ || !*pos)
+ /* skip any delimiter */
+ if (*pos == '/' || *pos == '\\')
+ pos++;
+
+ /* If pos is NULL then no prepath */
+ if (!*pos)
return 0;
vol->prepath = kstrdup(pos, GFP_KERNEL);
@@ -2918,7 +2865,7 @@ static inline void
cifs_reclassify_socket4(struct socket *sock)
{
struct sock *sk = sock->sk;
- BUG_ON(sock_owned_by_user(sk));
+ BUG_ON(!sock_allow_reclassification(sk));
sock_lock_init_class_and_name(sk, "slock-AF_INET-CIFS",
&cifs_slock_key[0], "sk_lock-AF_INET-CIFS", &cifs_key[0]);
}
@@ -2927,7 +2874,7 @@ static inline void
cifs_reclassify_socket6(struct socket *sock)
{
struct sock *sk = sock->sk;
- BUG_ON(sock_owned_by_user(sk));
+ BUG_ON(!sock_allow_reclassification(sk));
sock_lock_init_class_and_name(sk, "slock-AF_INET6-CIFS",
&cifs_slock_key[1], "sk_lock-AF_INET6-CIFS", &cifs_key[1]);
}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index c03d0744648b..9793ae0bcaa2 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -271,7 +271,7 @@ struct cifsFileInfo *
cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock)
{
- struct dentry *dentry = file->f_path.dentry;
+ struct dentry *dentry = file_dentry(file);
struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifsFileInfo *cfile;
@@ -461,7 +461,7 @@ int cifs_open(struct inode *inode, struct file *file)
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
- full_path = build_path_from_dentry(file->f_path.dentry);
+ full_path = build_path_from_dentry(file_dentry(file));
if (full_path == NULL) {
rc = -ENOMEM;
goto out;
@@ -2687,11 +2687,8 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
out:
inode_unlock(inode);
- if (rc > 0) {
- ssize_t err = generic_write_sync(file, iocb->ki_pos - rc, rc);
- if (err < 0)
- rc = err;
- }
+ if (rc > 0)
+ rc = generic_write_sync(iocb, rc);
up_read(&cinode->lock_sem);
return rc;
}
@@ -2855,39 +2852,31 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
int result = 0;
unsigned int i;
unsigned int nr_pages = rdata->nr_pages;
- struct kvec iov;
rdata->got_bytes = 0;
rdata->tailsz = PAGE_SIZE;
for (i = 0; i < nr_pages; i++) {
struct page *page = rdata->pages[i];
+ size_t n;
- if (len >= PAGE_SIZE) {
- /* enough data to fill the page */
- iov.iov_base = kmap(page);
- iov.iov_len = PAGE_SIZE;
- cifs_dbg(FYI, "%u: iov_base=%p iov_len=%zu\n",
- i, iov.iov_base, iov.iov_len);
- len -= PAGE_SIZE;
- } else if (len > 0) {
- /* enough for partial page, fill and zero the rest */
- iov.iov_base = kmap(page);
- iov.iov_len = len;
- cifs_dbg(FYI, "%u: iov_base=%p iov_len=%zu\n",
- i, iov.iov_base, iov.iov_len);
- memset(iov.iov_base + len, '\0', PAGE_SIZE - len);
- rdata->tailsz = len;
- len = 0;
- } else {
+ if (len <= 0) {
/* no need to hold page hostage */
rdata->pages[i] = NULL;
rdata->nr_pages--;
put_page(page);
continue;
}
-
- result = cifs_readv_from_socket(server, &iov, 1, iov.iov_len);
- kunmap(page);
+ n = len;
+ if (len >= PAGE_SIZE) {
+ /* enough data to fill the page */
+ n = PAGE_SIZE;
+ len -= n;
+ } else {
+ zero_user(page, len, PAGE_SIZE - len);
+ rdata->tailsz = len;
+ len = 0;
+ }
+ result = cifs_read_page_from_socket(server, page, n);
if (result < 0)
break;
@@ -3303,7 +3292,6 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
u64 eof;
pgoff_t eof_index;
unsigned int nr_pages = rdata->nr_pages;
- struct kvec iov;
/* determine the eof that the server (probably) has */
eof = CIFS_I(rdata->mapping->host)->server_eof;
@@ -3314,23 +3302,14 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
rdata->tailsz = PAGE_SIZE;
for (i = 0; i < nr_pages; i++) {
struct page *page = rdata->pages[i];
+ size_t n = PAGE_SIZE;
if (len >= PAGE_SIZE) {
- /* enough data to fill the page */
- iov.iov_base = kmap(page);
- iov.iov_len = PAGE_SIZE;
- cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n",
- i, page->index, iov.iov_base, iov.iov_len);
len -= PAGE_SIZE;
} else if (len > 0) {
/* enough for partial page, fill and zero the rest */
- iov.iov_base = kmap(page);
- iov.iov_len = len;
- cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n",
- i, page->index, iov.iov_base, iov.iov_len);
- memset(iov.iov_base + len,
- '\0', PAGE_SIZE - len);
- rdata->tailsz = len;
+ zero_user(page, len, PAGE_SIZE - len);
+ n = rdata->tailsz = len;
len = 0;
} else if (page->index > eof_index) {
/*
@@ -3360,8 +3339,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
continue;
}
- result = cifs_readv_from_socket(server, &iov, 1, iov.iov_len);
- kunmap(page);
+ result = cifs_read_page_from_socket(server, page, n);
if (result < 0)
break;
@@ -3854,7 +3832,7 @@ void cifs_oplock_break(struct work_struct *work)
* Direct IO is not yet supported in the cached mode.
*/
static ssize_t
-cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter)
{
/*
* FIXME
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 5f9ad5c42180..514dadb0575d 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2418,8 +2418,7 @@ cifs_setattr_exit:
int
cifs_setattr(struct dentry *direntry, struct iattr *attrs)
{
- struct inode *inode = d_inode(direntry);
- struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb);
if (pTcon->unix_ext)
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b30a4a6d98a0..65cf85dcda09 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -78,20 +78,34 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
{
struct dentry *dentry, *alias;
struct inode *inode;
- struct super_block *sb = d_inode(parent)->i_sb;
+ struct super_block *sb = parent->d_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
cifs_dbg(FYI, "%s: for %s\n", __func__, name->name);
dentry = d_hash_and_lookup(parent, name);
+ if (!dentry) {
+ /*
+ * If we know that the inode will need to be revalidated
+ * immediately, then don't create a new dentry for it.
+ * We'll end up doing an on the wire call either way and
+ * this spares us an invalidation.
+ */
+ if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
+ return;
+retry:
+ dentry = d_alloc_parallel(parent, name, &wq);
+ }
if (IS_ERR(dentry))
return;
-
- if (dentry) {
+ if (!d_in_lookup(dentry)) {
inode = d_inode(dentry);
if (inode) {
- if (d_mountpoint(dentry))
- goto out;
+ if (d_mountpoint(dentry)) {
+ dput(dentry);
+ return;
+ }
/*
* If we're generating inode numbers, then we don't
* want to clobber the existing one with the one that
@@ -106,33 +120,22 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
(inode->i_mode & S_IFMT) ==
(fattr->cf_mode & S_IFMT)) {
cifs_fattr_to_inode(inode, fattr);
- goto out;
+ dput(dentry);
+ return;
}
}
d_invalidate(dentry);
dput(dentry);
+ goto retry;
+ } else {
+ inode = cifs_iget(sb, fattr);
+ if (!inode)
+ inode = ERR_PTR(-ENOMEM);
+ alias = d_splice_alias(inode, dentry);
+ d_lookup_done(dentry);
+ if (alias && !IS_ERR(alias))
+ dput(alias);
}
-
- /*
- * If we know that the inode will need to be revalidated immediately,
- * then don't create a new dentry for it. We'll end up doing an on
- * the wire call either way and this spares us an invalidation.
- */
- if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
- return;
-
- dentry = d_alloc(parent, name);
- if (!dentry)
- return;
-
- inode = cifs_iget(sb, fattr);
- if (!inode)
- goto out;
-
- alias = d_splice_alias(inode, dentry);
- if (alias && !IS_ERR(alias))
- dput(alias);
-out:
dput(dentry);
}
@@ -300,7 +303,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file)
cifsFile->invalidHandle = true;
cifsFile->srch_inf.endOfSearch = false;
- full_path = build_path_from_dentry(file->f_path.dentry);
+ full_path = build_path_from_dentry(file_dentry(file));
if (full_path == NULL) {
rc = -ENOMEM;
goto error_exit;
@@ -759,7 +762,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
*/
fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
- cifs_prime_dcache(file->f_path.dentry, &name, &fattr);
+ cifs_prime_dcache(file_dentry(file), &name, &fattr);
ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid);
return !dir_emit(ctx, name.name, name.len, ino, fattr.cf_dtype);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 59727e32ed0f..af0ec2d5ad0e 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -400,19 +400,27 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
sec_blob->LmChallengeResponse.MaximumLength = 0;
sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer);
- rc = setup_ntlmv2_rsp(ses, nls_cp);
- if (rc) {
- cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
- goto setup_ntlmv2_ret;
+ 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;
+
+ sec_blob->NtChallengeResponse.Length =
+ cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+ sec_blob->NtChallengeResponse.MaximumLength =
+ cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+ } else {
+ /*
+ * don't send an NT Response for anonymous access
+ */
+ sec_blob->NtChallengeResponse.Length = 0;
+ sec_blob->NtChallengeResponse.MaximumLength = 0;
}
- 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;
-
- sec_blob->NtChallengeResponse.Length =
- cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
- sec_blob->NtChallengeResponse.MaximumLength =
- cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
if (ses->domainName == NULL) {
sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
@@ -670,20 +678,24 @@ sess_auth_lanman(struct sess_data *sess_data)
pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE;
- /* no capabilities flags in old lanman negotiation */
- pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
-
- /* Calculate hash with password and copy into bcc_ptr.
- * Encryption Key (stored as in cryptkey) gets used if the
- * security mode bit in Negottiate Protocol response states
- * to use challenge/response method (i.e. Password bit is 1).
- */
- rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
- ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
- true : false, lnm_session_key);
-
- memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
- bcc_ptr += CIFS_AUTH_RESP_SIZE;
+ if (ses->user_name != NULL) {
+ /* no capabilities flags in old lanman negotiation */
+ pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+
+ /* Calculate hash with password and copy into bcc_ptr.
+ * Encryption Key (stored as in cryptkey) gets used if the
+ * security mode bit in Negottiate Protocol response states
+ * to use challenge/response method (i.e. Password bit is 1).
+ */
+ rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
+ ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
+ true : false, lnm_session_key);
+
+ memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
+ bcc_ptr += CIFS_AUTH_RESP_SIZE;
+ } else {
+ pSMB->old_req.PasswordLength = 0;
+ }
/*
* can not sign if LANMAN negotiated so no need
@@ -769,26 +781,31 @@ sess_auth_ntlm(struct sess_data *sess_data)
capabilities = cifs_ssetup_hdr(ses, pSMB);
pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities);
- pSMB->req_no_secext.CaseInsensitivePasswordLength =
- cpu_to_le16(CIFS_AUTH_RESP_SIZE);
- pSMB->req_no_secext.CaseSensitivePasswordLength =
- cpu_to_le16(CIFS_AUTH_RESP_SIZE);
-
- /* calculate ntlm response and session key */
- rc = setup_ntlm_response(ses, sess_data->nls_cp);
- if (rc) {
- cifs_dbg(VFS, "Error %d during NTLM authentication\n",
- rc);
- goto out;
- }
+ if (ses->user_name != NULL) {
+ pSMB->req_no_secext.CaseInsensitivePasswordLength =
+ cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+ pSMB->req_no_secext.CaseSensitivePasswordLength =
+ cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+
+ /* calculate ntlm response and session key */
+ rc = setup_ntlm_response(ses, sess_data->nls_cp);
+ if (rc) {
+ cifs_dbg(VFS, "Error %d during NTLM authentication\n",
+ rc);
+ goto out;
+ }
- /* copy ntlm response */
- memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
- CIFS_AUTH_RESP_SIZE);
- bcc_ptr += CIFS_AUTH_RESP_SIZE;
- memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
- CIFS_AUTH_RESP_SIZE);
- bcc_ptr += CIFS_AUTH_RESP_SIZE;
+ /* copy ntlm response */
+ memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+ CIFS_AUTH_RESP_SIZE);
+ bcc_ptr += CIFS_AUTH_RESP_SIZE;
+ memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+ CIFS_AUTH_RESP_SIZE);
+ bcc_ptr += CIFS_AUTH_RESP_SIZE;
+ } else {
+ pSMB->req_no_secext.CaseInsensitivePasswordLength = 0;
+ pSMB->req_no_secext.CaseSensitivePasswordLength = 0;
+ }
if (ses->capabilities & CAP_UNICODE) {
/* unicode strings must be word aligned */
@@ -878,22 +895,26 @@ sess_auth_ntlmv2(struct sess_data *sess_data)
/* LM2 password would be here if we supported it */
pSMB->req_no_secext.CaseInsensitivePasswordLength = 0;
- /* calculate nlmv2 response and session key */
- rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp);
- if (rc) {
- cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc);
- goto out;
- }
+ if (ses->user_name != NULL) {
+ /* calculate nlmv2 response and session key */
+ rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp);
+ if (rc) {
+ cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc);
+ goto out;
+ }
- memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
- ses->auth_key.len - CIFS_SESS_KEY_SIZE);
- bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
+ memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+ ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+ bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
- /* set case sensitive password length after tilen may get
- * assigned, tilen is 0 otherwise.
- */
- pSMB->req_no_secext.CaseSensitivePasswordLength =
- cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+ /* set case sensitive password length after tilen may get
+ * assigned, tilen is 0 otherwise.
+ */
+ pSMB->req_no_secext.CaseSensitivePasswordLength =
+ cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+ } else {
+ pSMB->req_no_secext.CaseSensitivePasswordLength = 0;
+ }
if (ses->capabilities & CAP_UNICODE) {
if (sess_data->iov[0].iov_len % 2) {
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index bc0bb9c34f72..0ffa18094335 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -44,6 +44,7 @@
#define SMB2_OP_DELETE 7
#define SMB2_OP_HARDLINK 8
#define SMB2_OP_SET_EOF 9
+#define SMB2_OP_RMDIR 10
/* Used when constructing chained read requests. */
#define CHAINED_REQUEST 1
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 899bbc86f73e..4f0231e685a9 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -80,6 +80,10 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
* SMB2_open() call.
*/
break;
+ case SMB2_OP_RMDIR:
+ tmprc = SMB2_rmdir(xid, tcon, fid.persistent_fid,
+ fid.volatile_fid);
+ break;
case SMB2_OP_RENAME:
tmprc = SMB2_rename(xid, tcon, fid.persistent_fid,
fid.volatile_fid, (__le16 *)data);
@@ -191,8 +195,8 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
struct cifs_sb_info *cifs_sb)
{
return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
- CREATE_NOT_FILE | CREATE_DELETE_ON_CLOSE,
- NULL, SMB2_OP_DELETE);
+ CREATE_NOT_FILE,
+ NULL, SMB2_OP_RMDIR);
}
int
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 42e1f440eb1e..8f38e33d365b 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2575,6 +2575,22 @@ SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon,
}
int
+SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon,
+ u64 persistent_fid, u64 volatile_fid)
+{
+ __u8 delete_pending = 1;
+ void *data;
+ unsigned int size;
+
+ data = &delete_pending;
+ size = 1; /* sizeof __u8 */
+
+ return send_set_info(xid, tcon, persistent_fid, volatile_fid,
+ current->tgid, FILE_DISPOSITION_INFORMATION, 1, &data,
+ &size);
+}
+
+int
SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, __le16 *target_file)
{
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 4f07dc93608d..eb2cde2f64ba 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -141,6 +141,8 @@ extern int SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
extern int SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid,
__le16 *target_file);
+extern int SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon,
+ u64 persistent_fid, u64 volatile_fid);
extern int SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid,
__le16 *target_file);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 8732a43b1008..bc9a7b634643 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -135,11 +135,10 @@ smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
int
smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
- int i, rc;
+ int rc;
unsigned char smb2_signature[SMB2_HMACSHA256_SIZE];
unsigned char *sigptr = smb2_signature;
struct kvec *iov = rqst->rq_iov;
- int n_vec = rqst->rq_nvec;
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
@@ -171,53 +170,11 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
return rc;
}
- for (i = 0; i < n_vec; i++) {
- if (iov[i].iov_len == 0)
- continue;
- if (iov[i].iov_base == NULL) {
- cifs_dbg(VFS, "null iovec entry\n");
- return -EIO;
- }
- /*
- * The first entry includes a length field (which does not get
- * signed that occupies the first 4 bytes before the header).
- */
- if (i == 0) {
- if (iov[0].iov_len <= 8) /* cmd field at offset 9 */
- break; /* nothing to sign or corrupt header */
- rc =
- crypto_shash_update(
- &server->secmech.sdeschmacsha256->shash,
- iov[i].iov_base + 4, iov[i].iov_len - 4);
- } else {
- rc =
- crypto_shash_update(
- &server->secmech.sdeschmacsha256->shash,
- iov[i].iov_base, iov[i].iov_len);
- }
- if (rc) {
- cifs_dbg(VFS, "%s: Could not update with payload\n",
- __func__);
- return rc;
- }
- }
-
- /* now hash over the rq_pages array */
- for (i = 0; i < rqst->rq_npages; i++) {
- struct kvec p_iov;
-
- cifs_rqst_page_to_kvec(rqst, i, &p_iov);
- crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
- p_iov.iov_base, p_iov.iov_len);
- kunmap(rqst->rq_pages[i]);
- }
-
- rc = crypto_shash_final(&server->secmech.sdeschmacsha256->shash,
- sigptr);
- if (rc)
- cifs_dbg(VFS, "%s: Could not generate sha256 hash\n", __func__);
+ rc = __cifs_calc_signature(rqst, server, sigptr,
+ &server->secmech.sdeschmacsha256->shash);
- memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
+ if (!rc)
+ memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
return rc;
}
@@ -395,12 +352,10 @@ generate_smb311signingkey(struct cifs_ses *ses)
int
smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
- int i;
int rc = 0;
unsigned char smb3_signature[SMB2_CMACAES_SIZE];
unsigned char *sigptr = smb3_signature;
struct kvec *iov = rqst->rq_iov;
- int n_vec = rqst->rq_nvec;
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
@@ -431,54 +386,12 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__);
return rc;
}
+
+ rc = __cifs_calc_signature(rqst, server, sigptr,
+ &server->secmech.sdesccmacaes->shash);
- for (i = 0; i < n_vec; i++) {
- if (iov[i].iov_len == 0)
- continue;
- if (iov[i].iov_base == NULL) {
- cifs_dbg(VFS, "null iovec entry");
- return -EIO;
- }
- /*
- * The first entry includes a length field (which does not get
- * signed that occupies the first 4 bytes before the header).
- */
- if (i == 0) {
- if (iov[0].iov_len <= 8) /* cmd field at offset 9 */
- break; /* nothing to sign or corrupt header */
- rc =
- crypto_shash_update(
- &server->secmech.sdesccmacaes->shash,
- iov[i].iov_base + 4, iov[i].iov_len - 4);
- } else {
- rc =
- crypto_shash_update(
- &server->secmech.sdesccmacaes->shash,
- iov[i].iov_base, iov[i].iov_len);
- }
- if (rc) {
- cifs_dbg(VFS, "%s: Couldn't update cmac aes with payload\n",
- __func__);
- return rc;
- }
- }
-
- /* now hash over the rq_pages array */
- for (i = 0; i < rqst->rq_npages; i++) {
- struct kvec p_iov;
-
- cifs_rqst_page_to_kvec(rqst, i, &p_iov);
- crypto_shash_update(&server->secmech.sdesccmacaes->shash,
- p_iov.iov_base, p_iov.iov_len);
- kunmap(rqst->rq_pages[i]);
- }
-
- rc = crypto_shash_final(&server->secmech.sdesccmacaes->shash,
- sigptr);
- if (rc)
- cifs_dbg(VFS, "%s: Could not generate cmac aes\n", __func__);
-
- memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
+ if (!rc)
+ memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
return rc;
}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 87abe8ed074c..206a597b2293 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -124,41 +124,32 @@ cifs_delete_mid(struct mid_q_entry *mid)
/*
* smb_send_kvec - send an array of kvecs to the server
* @server: Server to send the data to
- * @iov: Pointer to array of kvecs
- * @n_vec: length of kvec array
+ * @smb_msg: Message to send
* @sent: amount of data sent on socket is stored here
*
* Our basic "send data to server" function. Should be called with srv_mutex
* held. The caller is responsible for handling the results.
*/
static int
-smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec,
- size_t *sent)
+smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
+ size_t *sent)
{
int rc = 0;
- int i = 0;
- struct msghdr smb_msg;
- unsigned int remaining;
- size_t first_vec = 0;
+ int retries = 0;
struct socket *ssocket = server->ssocket;
*sent = 0;
- smb_msg.msg_name = (struct sockaddr *) &server->dstaddr;
- smb_msg.msg_namelen = sizeof(struct sockaddr);
- smb_msg.msg_control = NULL;
- smb_msg.msg_controllen = 0;
+ smb_msg->msg_name = (struct sockaddr *) &server->dstaddr;
+ smb_msg->msg_namelen = sizeof(struct sockaddr);
+ smb_msg->msg_control = NULL;
+ smb_msg->msg_controllen = 0;
if (server->noblocksnd)
- smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
+ smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
else
- smb_msg.msg_flags = MSG_NOSIGNAL;
-
- remaining = 0;
- for (i = 0; i < n_vec; i++)
- remaining += iov[i].iov_len;
+ smb_msg->msg_flags = MSG_NOSIGNAL;
- i = 0;
- while (remaining) {
+ while (msg_data_left(smb_msg)) {
/*
* If blocking send, we try 3 times, since each can block
* for 5 seconds. For nonblocking we have to try more
@@ -177,35 +168,21 @@ smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec,
* after the retries we will kill the socket and
* reconnect which may clear the network problem.
*/
- rc = kernel_sendmsg(ssocket, &smb_msg, &iov[first_vec],
- n_vec - first_vec, remaining);
+ rc = sock_sendmsg(ssocket, smb_msg);
if (rc == -EAGAIN) {
- i++;
- if (i >= 14 || (!server->noblocksnd && (i > 2))) {
+ retries++;
+ if (retries >= 14 ||
+ (!server->noblocksnd && (retries > 2))) {
cifs_dbg(VFS, "sends on sock %p stuck for 15 seconds\n",
ssocket);
- rc = -EAGAIN;
- break;
+ return -EAGAIN;
}
- msleep(1 << i);
+ msleep(1 << retries);
continue;
}
if (rc < 0)
- break;
-
- /* send was at least partially successful */
- *sent += rc;
-
- if (rc == remaining) {
- remaining = 0;
- break;
- }
-
- if (rc > remaining) {
- cifs_dbg(VFS, "sent %d requested %d\n", rc, remaining);
- break;
- }
+ return rc;
if (rc == 0) {
/* should never happen, letting socket clear before
@@ -215,59 +192,11 @@ smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec,
continue;
}
- remaining -= rc;
-
- /* the line below resets i */
- for (i = first_vec; i < n_vec; i++) {
- if (iov[i].iov_len) {
- if (rc > iov[i].iov_len) {
- rc -= iov[i].iov_len;
- iov[i].iov_len = 0;
- } else {
- iov[i].iov_base += rc;
- iov[i].iov_len -= rc;
- first_vec = i;
- break;
- }
- }
- }
-
- i = 0; /* in case we get ENOSPC on the next send */
- rc = 0;
+ /* send was at least partially successful */
+ *sent += rc;
+ retries = 0; /* in case we get ENOSPC on the next send */
}
- return rc;
-}
-
-/**
- * rqst_page_to_kvec - Turn a slot in the smb_rqst page array into a kvec
- * @rqst: pointer to smb_rqst
- * @idx: index into the array of the page
- * @iov: pointer to struct kvec that will hold the result
- *
- * Helper function to convert a slot in the rqst->rq_pages array into a kvec.
- * The page will be kmapped and the address placed into iov_base. The length
- * will then be adjusted according to the ptailoff.
- */
-void
-cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx,
- struct kvec *iov)
-{
- /*
- * FIXME: We could avoid this kmap altogether if we used
- * kernel_sendpage instead of kernel_sendmsg. That will only
- * work if signing is disabled though as sendpage inlines the
- * page directly into the fraglist. If userspace modifies the
- * page after we calculate the signature, then the server will
- * reject it and may break the connection. kernel_sendmsg does
- * an extra copy of the data and avoids that issue.
- */
- iov->iov_base = kmap(rqst->rq_pages[idx]);
-
- /* if last page, don't send beyond this offset into page */
- if (idx == (rqst->rq_npages - 1))
- iov->iov_len = rqst->rq_tailsz;
- else
- iov->iov_len = rqst->rq_pagesz;
+ return 0;
}
static unsigned long
@@ -299,8 +228,9 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
unsigned long send_length;
unsigned int i;
- size_t total_len = 0, sent;
+ size_t total_len = 0, sent, size;
struct socket *ssocket = server->ssocket;
+ struct msghdr smb_msg;
int val = 1;
if (ssocket == NULL)
@@ -321,7 +251,13 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
- rc = smb_send_kvec(server, iov, n_vec, &sent);
+ size = 0;
+ for (i = 0; i < n_vec; i++)
+ size += iov[i].iov_len;
+
+ iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, iov, n_vec, size);
+
+ rc = smb_send_kvec(server, &smb_msg, &sent);
if (rc < 0)
goto uncork;
@@ -329,11 +265,16 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
/* now walk the page array and send each page in it */
for (i = 0; i < rqst->rq_npages; i++) {
- struct kvec p_iov;
-
- cifs_rqst_page_to_kvec(rqst, i, &p_iov);
- rc = smb_send_kvec(server, &p_iov, 1, &sent);
- kunmap(rqst->rq_pages[i]);
+ size_t len = i == rqst->rq_npages - 1
+ ? rqst->rq_tailsz
+ : rqst->rq_pagesz;
+ struct bio_vec bvec = {
+ .bv_page = rqst->rq_pages[i],
+ .bv_len = len
+ };
+ iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
+ &bvec, 1, len);
+ rc = smb_send_kvec(server, &smb_msg, &sent);
if (rc < 0)
break;
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index f5dc2f0df4ad..c8b77aa24a1d 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -32,92 +32,24 @@
#include "cifs_unicode.h"
#define MAX_EA_VALUE_SIZE 65535
-#define CIFS_XATTR_DOS_ATTRIB "user.DosAttrib"
#define CIFS_XATTR_CIFS_ACL "system.cifs_acl"
/* BB need to add server (Samba e.g) support for security and trusted prefix */
-int cifs_removexattr(struct dentry *direntry, const char *ea_name)
-{
- int rc = -EOPNOTSUPP;
-#ifdef CONFIG_CIFS_XATTR
- unsigned int xid;
- struct cifs_sb_info *cifs_sb;
- struct tcon_link *tlink;
- struct cifs_tcon *pTcon;
- struct super_block *sb;
- char *full_path = NULL;
-
- if (direntry == NULL)
- return -EIO;
- if (d_really_is_negative(direntry))
- return -EIO;
- sb = d_inode(direntry)->i_sb;
- if (sb == NULL)
- return -EIO;
-
- cifs_sb = CIFS_SB(sb);
- tlink = cifs_sb_tlink(cifs_sb);
- if (IS_ERR(tlink))
- return PTR_ERR(tlink);
- pTcon = tlink_tcon(tlink);
-
- xid = get_xid();
-
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
- goto remove_ea_exit;
- }
- if (ea_name == NULL) {
- cifs_dbg(FYI, "Null xattr names not supported\n");
- } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)
- && (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN))) {
- cifs_dbg(FYI,
- "illegal xattr request %s (only user namespace supported)\n",
- ea_name);
- /* BB what if no namespace prefix? */
- /* Should we just pass them to server, except for
- system and perhaps security prefixes? */
- } else {
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- goto remove_ea_exit;
+enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
- ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- if (pTcon->ses->server->ops->set_EA)
- rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
- full_path, ea_name, NULL, (__u16)0,
- cifs_sb->local_nls, cifs_remap(cifs_sb));
- }
-remove_ea_exit:
- kfree(full_path);
- free_xid(xid);
- cifs_put_tlink(tlink);
-#endif
- return rc;
-}
-
-int cifs_setxattr(struct dentry *direntry, const char *ea_name,
- const void *ea_value, size_t value_size, int flags)
+static int cifs_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
{
int rc = -EOPNOTSUPP;
-#ifdef CONFIG_CIFS_XATTR
unsigned int xid;
- struct cifs_sb_info *cifs_sb;
+ struct super_block *sb = dentry->d_sb;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- struct super_block *sb;
char *full_path;
- if (direntry == NULL)
- return -EIO;
- if (d_really_is_negative(direntry))
- return -EIO;
- sb = d_inode(direntry)->i_sb;
- if (sb == NULL)
- return -EIO;
-
- cifs_sb = CIFS_SB(sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
@@ -125,10 +57,10 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
+ full_path = build_path_from_dentry(dentry);
if (full_path == NULL) {
rc = -ENOMEM;
- goto set_ea_exit;
+ goto out;
}
/* return dos attributes as pseudo xattr */
/* return alt name if available as pseudo attr */
@@ -136,123 +68,93 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
/* if proc/fs/cifs/streamstoxattr is set then
search server for EAs or streams to
returns as xattrs */
- if (value_size > MAX_EA_VALUE_SIZE) {
+ if (size > MAX_EA_VALUE_SIZE) {
cifs_dbg(FYI, "size of EA value too large\n");
rc = -EOPNOTSUPP;
- goto set_ea_exit;
+ goto out;
}
- if (ea_name == NULL) {
- cifs_dbg(FYI, "Null xattr names not supported\n");
- } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)
- == 0) {
+ switch (handler->flags) {
+ case XATTR_USER:
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- goto set_ea_exit;
- if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0)
- cifs_dbg(FYI, "attempt to set cifs inode metadata\n");
+ goto out;
- ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
if (pTcon->ses->server->ops->set_EA)
rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
- full_path, ea_name, ea_value, (__u16)value_size,
+ full_path, name, value, (__u16)size,
cifs_sb->local_nls, cifs_remap(cifs_sb));
- } else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)
- == 0) {
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- goto set_ea_exit;
+ break;
- ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
- if (pTcon->ses->server->ops->set_EA)
- rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
- full_path, ea_name, ea_value, (__u16)value_size,
- cifs_sb->local_nls, cifs_remap(cifs_sb));
- } else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
- strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
+ case XATTR_CIFS_ACL: {
#ifdef CONFIG_CIFS_ACL
struct cifs_ntsd *pacl;
- pacl = kmalloc(value_size, GFP_KERNEL);
+
+ if (!value)
+ goto out;
+ pacl = kmalloc(size, GFP_KERNEL);
if (!pacl) {
rc = -ENOMEM;
} else {
- memcpy(pacl, ea_value, value_size);
- if (pTcon->ses->server->ops->set_acl)
+ memcpy(pacl, value, size);
+ if (value &&
+ pTcon->ses->server->ops->set_acl)
rc = pTcon->ses->server->ops->set_acl(pacl,
- value_size, d_inode(direntry),
+ size, d_inode(dentry),
full_path, CIFS_ACL_DACL);
else
rc = -EOPNOTSUPP;
if (rc == 0) /* force revalidate of the inode */
- CIFS_I(d_inode(direntry))->time = 0;
+ CIFS_I(d_inode(dentry))->time = 0;
kfree(pacl);
}
-#else
- cifs_dbg(FYI, "Set CIFS ACL not supported yet\n");
#endif /* CONFIG_CIFS_ACL */
- } else {
- int temp;
- temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS,
- strlen(XATTR_NAME_POSIX_ACL_ACCESS));
- if (temp == 0) {
+ break;
+ }
+
+ case XATTR_ACL_ACCESS:
#ifdef CONFIG_CIFS_POSIX
- if (sb->s_flags & MS_POSIXACL)
- rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
- ea_value, (const int)value_size,
- ACL_TYPE_ACCESS, cifs_sb->local_nls,
- cifs_remap(cifs_sb));
- cifs_dbg(FYI, "set POSIX ACL rc %d\n", rc);
-#else
- cifs_dbg(FYI, "set POSIX ACL not supported\n");
-#endif
- } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT,
- strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) {
+ if (!value)
+ goto out;
+ if (sb->s_flags & MS_POSIXACL)
+ rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
+ value, (const int)size,
+ ACL_TYPE_ACCESS, cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
+#endif /* CONFIG_CIFS_POSIX */
+ break;
+
+ case XATTR_ACL_DEFAULT:
#ifdef CONFIG_CIFS_POSIX
- if (sb->s_flags & MS_POSIXACL)
- rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
- ea_value, (const int)value_size,
- ACL_TYPE_DEFAULT, cifs_sb->local_nls,
- cifs_remap(cifs_sb));
- cifs_dbg(FYI, "set POSIX default ACL rc %d\n", rc);
-#else
- cifs_dbg(FYI, "set default POSIX ACL not supported\n");
-#endif
- } else {
- cifs_dbg(FYI, "illegal xattr request %s (only user namespace supported)\n",
- ea_name);
- /* BB what if no namespace prefix? */
- /* Should we just pass them to server, except for
- system and perhaps security prefixes? */
- }
+ if (!value)
+ goto out;
+ if (sb->s_flags & MS_POSIXACL)
+ rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
+ value, (const int)size,
+ ACL_TYPE_DEFAULT, cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
+#endif /* CONFIG_CIFS_POSIX */
+ break;
}
-set_ea_exit:
+out:
kfree(full_path);
free_xid(xid);
cifs_put_tlink(tlink);
-#endif
return rc;
}
-ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
- void *ea_value, size_t buf_size)
+static int cifs_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size)
{
ssize_t rc = -EOPNOTSUPP;
-#ifdef CONFIG_CIFS_XATTR
unsigned int xid;
- struct cifs_sb_info *cifs_sb;
+ struct super_block *sb = dentry->d_sb;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- struct super_block *sb;
char *full_path;
- if (direntry == NULL)
- return -EIO;
- if (d_really_is_negative(direntry))
- return -EIO;
- sb = d_inode(direntry)->i_sb;
- if (sb == NULL)
- return -EIO;
-
- cifs_sb = CIFS_SB(sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
@@ -260,98 +162,72 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
+ full_path = build_path_from_dentry(dentry);
if (full_path == NULL) {
rc = -ENOMEM;
- goto get_ea_exit;
+ goto out;
}
/* return dos attributes as pseudo xattr */
/* return alt name if available as pseudo attr */
- if (ea_name == NULL) {
- cifs_dbg(FYI, "Null xattr names not supported\n");
- } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)
- == 0) {
+ switch (handler->flags) {
+ case XATTR_USER:
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- goto get_ea_exit;
+ goto out;
- if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0) {
- cifs_dbg(FYI, "attempt to query cifs inode metadata\n");
- /* revalidate/getattr then populate from inode */
- } /* BB add else when above is implemented */
- ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
if (pTcon->ses->server->ops->query_all_EAs)
rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
- full_path, ea_name, ea_value, buf_size,
+ full_path, name, value, size,
cifs_sb->local_nls, cifs_remap(cifs_sb));
- } else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- goto get_ea_exit;
+ break;
- ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
- if (pTcon->ses->server->ops->query_all_EAs)
- rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
- full_path, ea_name, ea_value, buf_size,
- cifs_sb->local_nls, cifs_remap(cifs_sb));
- } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS,
- strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) {
+ case XATTR_CIFS_ACL: {
+#ifdef CONFIG_CIFS_ACL
+ u32 acllen;
+ struct cifs_ntsd *pacl;
+
+ if (pTcon->ses->server->ops->get_acl == NULL)
+ goto out; /* rc already EOPNOTSUPP */
+
+ pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
+ inode, full_path, &acllen);
+ if (IS_ERR(pacl)) {
+ rc = PTR_ERR(pacl);
+ cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
+ __func__, rc);
+ } else {
+ if (value) {
+ if (acllen > size)
+ acllen = -ERANGE;
+ else
+ memcpy(value, pacl, acllen);
+ }
+ rc = acllen;
+ kfree(pacl);
+ }
+#endif /* CONFIG_CIFS_ACL */
+ break;
+ }
+
+ case XATTR_ACL_ACCESS:
#ifdef CONFIG_CIFS_POSIX
if (sb->s_flags & MS_POSIXACL)
rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
- ea_value, buf_size, ACL_TYPE_ACCESS,
+ value, size, ACL_TYPE_ACCESS,
cifs_sb->local_nls,
cifs_remap(cifs_sb));
-#else
- cifs_dbg(FYI, "Query POSIX ACL not supported yet\n");
-#endif /* CONFIG_CIFS_POSIX */
- } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT,
- strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) {
+#endif /* CONFIG_CIFS_POSIX */
+ break;
+
+ case XATTR_ACL_DEFAULT:
#ifdef CONFIG_CIFS_POSIX
if (sb->s_flags & MS_POSIXACL)
rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
- ea_value, buf_size, ACL_TYPE_DEFAULT,
+ value, size, ACL_TYPE_DEFAULT,
cifs_sb->local_nls,
cifs_remap(cifs_sb));
-#else
- cifs_dbg(FYI, "Query POSIX default ACL not supported yet\n");
-#endif /* CONFIG_CIFS_POSIX */
- } else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
- strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
-#ifdef CONFIG_CIFS_ACL
- u32 acllen;
- struct cifs_ntsd *pacl;
-
- if (pTcon->ses->server->ops->get_acl == NULL)
- goto get_ea_exit; /* rc already EOPNOTSUPP */
-
- pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
- d_inode(direntry), full_path, &acllen);
- if (IS_ERR(pacl)) {
- rc = PTR_ERR(pacl);
- cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
- __func__, rc);
- } else {
- if (ea_value) {
- if (acllen > buf_size)
- acllen = -ERANGE;
- else
- memcpy(ea_value, pacl, acllen);
- }
- rc = acllen;
- kfree(pacl);
- }
-#else
- cifs_dbg(FYI, "Query CIFS ACL not supported yet\n");
-#endif /* CONFIG_CIFS_ACL */
- } else if (strncmp(ea_name,
- XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) {
- cifs_dbg(FYI, "Trusted xattr namespace not supported yet\n");
- } else if (strncmp(ea_name,
- XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) == 0) {
- cifs_dbg(FYI, "Security xattr namespace not supported yet\n");
- } else
- cifs_dbg(FYI,
- "illegal xattr request %s (only user namespace supported)\n",
- ea_name);
+#endif /* CONFIG_CIFS_POSIX */
+ break;
+ }
/* We could add an additional check for streams ie
if proc/fs/cifs/streamstoxattr is set then
@@ -361,34 +237,22 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
if (rc == -EINVAL)
rc = -EOPNOTSUPP;
-get_ea_exit:
+out:
kfree(full_path);
free_xid(xid);
cifs_put_tlink(tlink);
-#endif
return rc;
}
ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
{
ssize_t rc = -EOPNOTSUPP;
-#ifdef CONFIG_CIFS_XATTR
unsigned int xid;
- struct cifs_sb_info *cifs_sb;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- struct super_block *sb;
char *full_path;
- if (direntry == NULL)
- return -EIO;
- if (d_really_is_negative(direntry))
- return -EIO;
- sb = d_inode(direntry)->i_sb;
- if (sb == NULL)
- return -EIO;
-
- cifs_sb = CIFS_SB(sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
return -EOPNOTSUPP;
@@ -419,6 +283,50 @@ list_ea_exit:
kfree(full_path);
free_xid(xid);
cifs_put_tlink(tlink);
-#endif
return rc;
}
+
+static const struct xattr_handler cifs_user_xattr_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .flags = XATTR_USER,
+ .get = cifs_xattr_get,
+ .set = cifs_xattr_set,
+};
+
+/* os2.* attributes are treated like user.* attributes */
+static const struct xattr_handler cifs_os2_xattr_handler = {
+ .prefix = XATTR_OS2_PREFIX,
+ .flags = XATTR_USER,
+ .get = cifs_xattr_get,
+ .set = cifs_xattr_set,
+};
+
+static const struct xattr_handler cifs_cifs_acl_xattr_handler = {
+ .name = CIFS_XATTR_CIFS_ACL,
+ .flags = XATTR_CIFS_ACL,
+ .get = cifs_xattr_get,
+ .set = cifs_xattr_set,
+};
+
+static const struct xattr_handler cifs_posix_acl_access_xattr_handler = {
+ .name = XATTR_NAME_POSIX_ACL_ACCESS,
+ .flags = XATTR_ACL_ACCESS,
+ .get = cifs_xattr_get,
+ .set = cifs_xattr_set,
+};
+
+static const struct xattr_handler cifs_posix_acl_default_xattr_handler = {
+ .name = XATTR_NAME_POSIX_ACL_DEFAULT,
+ .flags = XATTR_ACL_DEFAULT,
+ .get = cifs_xattr_get,
+ .set = cifs_xattr_set,
+};
+
+const struct xattr_handler *cifs_xattr_handlers[] = {
+ &cifs_user_xattr_handler,
+ &cifs_os2_xattr_handler,
+ &cifs_cifs_acl_xattr_handler,
+ &cifs_posix_acl_access_xattr_handler,
+ &cifs_posix_acl_default_xattr_handler,
+ NULL
+};
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 42e731b8c80a..6fb8672c0892 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -424,16 +424,22 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
- if (host_file->f_op->iterate) {
+ if (host_file->f_op->iterate || host_file->f_op->iterate_shared) {
struct inode *host_inode = file_inode(host_file);
-
- inode_lock(host_inode);
ret = -ENOENT;
if (!IS_DEADDIR(host_inode)) {
- ret = host_file->f_op->iterate(host_file, ctx);
- file_accessed(host_file);
+ if (host_file->f_op->iterate_shared) {
+ inode_lock_shared(host_inode);
+ ret = host_file->f_op->iterate_shared(host_file, ctx);
+ file_accessed(host_file);
+ inode_unlock_shared(host_inode);
+ } else {
+ inode_lock(host_inode);
+ ret = host_file->f_op->iterate(host_file, ctx);
+ file_accessed(host_file);
+ inode_unlock(host_inode);
+ }
}
- inode_unlock(host_inode);
return ret;
}
/* Venus: we must read Venus dirents from a file */
diff --git a/fs/compat.c b/fs/compat.c
index f940cb20562f..be6e48b0a46c 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -884,7 +884,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
{
int error;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
struct compat_readdir_callback buf = {
.ctx.actor = compat_fillonedir,
.dirent = dirent
@@ -897,7 +897,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
if (buf.result)
error = buf.result;
- fdput(f);
+ fdput_pos(f);
return error;
}
@@ -977,7 +977,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
if (!access_ok(VERIFY_WRITE, dirent, count))
return -EFAULT;
- f = fdget(fd);
+ f = fdget_pos(fd);
if (!f.file)
return -EBADF;
@@ -991,7 +991,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
else
error = count - buf.count;
}
- fdput(f);
+ fdput_pos(f);
return error;
}
@@ -1066,7 +1066,7 @@ COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd,
if (!access_ok(VERIFY_WRITE, dirent, count))
return -EFAULT;
- f = fdget(fd);
+ f = fdget_pos(fd);
if (!f.file)
return -EBADF;
@@ -1081,7 +1081,7 @@ COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd,
else
error = count - buf.count;
}
- fdput(f);
+ fdput_pos(f);
return error;
}
#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index ea59c891fc53..56fb26127fef 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -494,7 +494,7 @@ out:
* If there is an error, the caller will reset the flags via
* configfs_detach_rollback().
*/
-static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex)
+static int configfs_detach_prep(struct dentry *dentry, struct dentry **wait)
{
struct configfs_dirent *parent_sd = dentry->d_fsdata;
struct configfs_dirent *sd;
@@ -515,8 +515,8 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex
if (sd->s_type & CONFIGFS_USET_DEFAULT) {
/* Abort if racing with mkdir() */
if (sd->s_type & CONFIGFS_USET_IN_MKDIR) {
- if (wait_mutex)
- *wait_mutex = &d_inode(sd->s_dentry)->i_mutex;
+ if (wait)
+ *wait= dget(sd->s_dentry);
return -EAGAIN;
}
@@ -524,7 +524,7 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex
* Yup, recursive. If there's a problem, blame
* deep nesting of default_groups
*/
- ret = configfs_detach_prep(sd->s_dentry, wait_mutex);
+ ret = configfs_detach_prep(sd->s_dentry, wait);
if (!ret)
continue;
} else
@@ -1458,7 +1458,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
* the new link is temporarily attached
*/
do {
- struct mutex *wait_mutex;
+ struct dentry *wait;
mutex_lock(&configfs_symlink_mutex);
spin_lock(&configfs_dirent_lock);
@@ -1469,7 +1469,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
*/
ret = sd->s_dependent_count ? -EBUSY : 0;
if (!ret) {
- ret = configfs_detach_prep(dentry, &wait_mutex);
+ ret = configfs_detach_prep(dentry, &wait);
if (ret)
configfs_detach_rollback(dentry);
}
@@ -1483,8 +1483,9 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
}
/* Wait until the racing operation terminates */
- mutex_lock(wait_mutex);
- mutex_unlock(wait_mutex);
+ inode_lock(d_inode(wait));
+ inode_unlock(d_inode(wait));
+ dput(wait);
}
} while (ret == -EAGAIN);
@@ -1632,11 +1633,9 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx)
if (!dir_emit_dots(file, ctx))
return 0;
- if (ctx->pos == 2) {
- spin_lock(&configfs_dirent_lock);
+ spin_lock(&configfs_dirent_lock);
+ if (ctx->pos == 2)
list_move(q, &parent_sd->s_children);
- spin_unlock(&configfs_dirent_lock);
- }
for (p = q->next; p != &parent_sd->s_children; p = p->next) {
struct configfs_dirent *next;
const char *name;
@@ -1647,9 +1646,6 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx)
if (!next->s_element)
continue;
- name = configfs_get_name(next);
- len = strlen(name);
-
/*
* We'll have a dentry and an inode for
* PINNED items and for open attribute
@@ -1663,7 +1659,6 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx)
* they close it. Beyond that, we don't
* care.
*/
- spin_lock(&configfs_dirent_lock);
dentry = next->s_dentry;
if (dentry)
inode = d_inode(dentry);
@@ -1673,15 +1668,18 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx)
if (!inode)
ino = iunique(sb, 2);
+ name = configfs_get_name(next);
+ len = strlen(name);
+
if (!dir_emit(ctx, name, len, ino, dt_type(next)))
return 0;
spin_lock(&configfs_dirent_lock);
list_move(q, p);
- spin_unlock(&configfs_dirent_lock);
p = q;
ctx->pos++;
}
+ spin_unlock(&configfs_dirent_lock);
return 0;
}
@@ -1689,7 +1687,6 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry * dentry = file->f_path.dentry;
- inode_lock(d_inode(dentry));
switch (whence) {
case 1:
offset += file->f_pos;
@@ -1697,7 +1694,6 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
if (offset >= 0)
break;
default:
- inode_unlock(d_inode(dentry));
return -EINVAL;
}
if (offset != file->f_pos) {
@@ -1723,7 +1719,6 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
spin_unlock(&configfs_dirent_lock);
}
}
- inode_unlock(d_inode(dentry));
return offset;
}
@@ -1732,7 +1727,7 @@ const struct file_operations configfs_dir_operations = {
.release = configfs_dir_close,
.llseek = configfs_dir_lseek,
.read = generic_read_dir,
- .iterate = configfs_readdir,
+ .iterate_shared = configfs_readdir,
};
/**
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 03d124ae27d7..0387968e6f47 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -156,7 +156,7 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
if (depth > 0) {
if (depth <= ARRAY_SIZE(default_group_class)) {
- lockdep_set_class(&inode->i_mutex,
+ lockdep_set_class(&inode->i_rwsem,
&default_group_class[depth - 1]);
} else {
/*
diff --git a/fs/coredump.c b/fs/coredump.c
index 47c32c3bfa1d..38a7ab87e10a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -413,7 +413,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
- down_write(&mm->mmap_sem);
+ if (down_write_killable(&mm->mmap_sem))
+ return -EINTR;
+
if (!mm->core_state)
core_waiters = zap_threads(tsk, mm, core_state, exit_code);
up_write(&mm->mmap_sem);
@@ -803,12 +805,9 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
static char zeroes[PAGE_SIZE];
struct file *file = cprm->file;
if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
- if (cprm->written + nr > cprm->limit)
- return 0;
if (dump_interrupted() ||
file->f_op->llseek(file, nr, SEEK_CUR) < 0)
return 0;
- cprm->written += nr;
return 1;
} else {
while (nr > PAGE_SIZE) {
@@ -823,7 +822,7 @@ EXPORT_SYMBOL(dump_skip);
int dump_align(struct coredump_params *cprm, int align)
{
- unsigned mod = cprm->written & (align - 1);
+ unsigned mod = cprm->file->f_pos & (align - 1);
if (align & (align - 1))
return 0;
return mod ? dump_skip(cprm, align - mod) : 1;
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 3a32ddf98095..7919967488cb 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -561,7 +561,7 @@ static const struct address_space_operations cramfs_aops = {
static const struct file_operations cramfs_directory_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = cramfs_readdir,
+ .iterate_shared = cramfs_readdir,
};
static const struct inode_operations cramfs_dir_inode_operations = {
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 06f5aa478bf2..1ac263eddc4e 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -78,6 +78,67 @@ out:
return res;
}
+static int validate_user_key(struct fscrypt_info *crypt_info,
+ struct fscrypt_context *ctx, u8 *raw_key,
+ u8 *prefix, int prefix_size)
+{
+ u8 *full_key_descriptor;
+ struct key *keyring_key;
+ struct fscrypt_key *master_key;
+ const struct user_key_payload *ukp;
+ int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
+ int res;
+
+ full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
+ if (!full_key_descriptor)
+ return -ENOMEM;
+
+ memcpy(full_key_descriptor, prefix, prefix_size);
+ sprintf(full_key_descriptor + prefix_size,
+ "%*phN", FS_KEY_DESCRIPTOR_SIZE,
+ ctx->master_key_descriptor);
+ full_key_descriptor[full_key_len - 1] = '\0';
+ keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+ kfree(full_key_descriptor);
+ if (IS_ERR(keyring_key))
+ return PTR_ERR(keyring_key);
+
+ if (keyring_key->type != &key_type_logon) {
+ printk_once(KERN_WARNING
+ "%s: key type must be logon\n", __func__);
+ res = -ENOKEY;
+ goto out;
+ }
+ down_read(&keyring_key->sem);
+ ukp = user_key_payload(keyring_key);
+ if (ukp->datalen != sizeof(struct fscrypt_key)) {
+ res = -EINVAL;
+ up_read(&keyring_key->sem);
+ goto out;
+ }
+ master_key = (struct fscrypt_key *)ukp->data;
+ BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+
+ if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+ printk_once(KERN_WARNING
+ "%s: key size incorrect: %d\n",
+ __func__, master_key->size);
+ res = -ENOKEY;
+ up_read(&keyring_key->sem);
+ goto out;
+ }
+ res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
+ up_read(&keyring_key->sem);
+ if (res)
+ goto out;
+
+ crypt_info->ci_keyring_key = keyring_key;
+ return 0;
+out:
+ key_put(keyring_key);
+ return res;
+}
+
static void put_crypt_info(struct fscrypt_info *ci)
{
if (!ci)
@@ -91,12 +152,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
int get_crypt_info(struct inode *inode)
{
struct fscrypt_info *crypt_info;
- u8 full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
- (FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
- struct key *keyring_key = NULL;
- struct fscrypt_key *master_key;
struct fscrypt_context ctx;
- const struct user_key_payload *ukp;
struct crypto_skcipher *ctfm;
const char *cipher_str;
u8 raw_key[FS_MAX_KEY_SIZE];
@@ -167,48 +223,24 @@ retry:
memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
goto got_key;
}
- memcpy(full_key_descriptor, FS_KEY_DESC_PREFIX,
- FS_KEY_DESC_PREFIX_SIZE);
- sprintf(full_key_descriptor + FS_KEY_DESC_PREFIX_SIZE,
- "%*phN", FS_KEY_DESCRIPTOR_SIZE,
- ctx.master_key_descriptor);
- full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
- (2 * FS_KEY_DESCRIPTOR_SIZE)] = '\0';
- keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
- if (IS_ERR(keyring_key)) {
- res = PTR_ERR(keyring_key);
- keyring_key = NULL;
- goto out;
- }
- crypt_info->ci_keyring_key = keyring_key;
- if (keyring_key->type != &key_type_logon) {
- printk_once(KERN_WARNING
- "%s: key type must be logon\n", __func__);
- res = -ENOKEY;
- goto out;
- }
- down_read(&keyring_key->sem);
- ukp = user_key_payload(keyring_key);
- if (ukp->datalen != sizeof(struct fscrypt_key)) {
- res = -EINVAL;
- up_read(&keyring_key->sem);
- goto out;
- }
- master_key = (struct fscrypt_key *)ukp->data;
- BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
- if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
- printk_once(KERN_WARNING
- "%s: key size incorrect: %d\n",
- __func__, master_key->size);
- res = -ENOKEY;
- up_read(&keyring_key->sem);
+ res = validate_user_key(crypt_info, &ctx, raw_key,
+ FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
+ if (res && inode->i_sb->s_cop->key_prefix) {
+ u8 *prefix = NULL;
+ int prefix_size, res2;
+
+ prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
+ res2 = validate_user_key(crypt_info, &ctx, raw_key,
+ prefix, prefix_size);
+ if (res2) {
+ if (res2 == -ENOKEY)
+ res = -ENOKEY;
+ goto out;
+ }
+ } else if (res) {
goto out;
}
- res = derive_key_aes(ctx.nonce, master_key->raw, raw_key);
- up_read(&keyring_key->sem);
- if (res)
- goto out;
got_key:
ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
if (!ctfm || IS_ERR(ctfm)) {
diff --git a/fs/dax.c b/fs/dax.c
index 2494255c5785..7d9df93b3a14 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -32,6 +32,15 @@
#include <linux/pfn_t.h>
#include <linux/sizes.h>
+#define RADIX_DAX_MASK 0xf
+#define RADIX_DAX_SHIFT 4
+#define RADIX_DAX_PTE (0x4 | RADIX_TREE_EXCEPTIONAL_ENTRY)
+#define RADIX_DAX_PMD (0x8 | RADIX_TREE_EXCEPTIONAL_ENTRY)
+#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_MASK)
+#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT))
+#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \
+ RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE)))
+
static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
{
struct request_queue *q = bdev->bd_queue;
@@ -244,7 +253,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
* @iocb: The control block for this I/O
* @inode: The file which the I/O is directed at
* @iter: The addresses to do I/O from or to
- * @pos: The file offset where the I/O starts
* @get_block: The filesystem method used to translate file offsets to blocks
* @end_io: A filesystem callback for I/O completion
* @flags: See below
@@ -257,11 +265,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
* is in progress.
*/
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
- struct iov_iter *iter, loff_t pos, get_block_t get_block,
+ struct iov_iter *iter, get_block_t get_block,
dio_iodone_t end_io, int flags)
{
struct buffer_head bh;
ssize_t retval = -EINVAL;
+ loff_t pos = iocb->ki_pos;
loff_t end = pos + iov_iter_count(iter);
memset(&bh, 0, sizeof(bh));
diff --git a/fs/dcache.c b/fs/dcache.c
index d5ecc6e477da..c622872c12c5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -111,6 +111,17 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
return dentry_hashtable + hash_32(hash, d_hash_shift);
}
+#define IN_LOOKUP_SHIFT 10
+static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT];
+
+static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent,
+ unsigned int hash)
+{
+ hash += (unsigned long) parent / L1_CACHE_BYTES;
+ return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT);
+}
+
+
/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
.age_limit = 45,
@@ -761,6 +772,8 @@ repeat:
/* Slow case: now with the dentry lock held */
rcu_read_unlock();
+ WARN_ON(d_in_lookup(dentry));
+
/* Unreachable? Get rid of it */
if (unlikely(d_unhashed(dentry)))
goto kill_it;
@@ -1558,7 +1571,11 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
* be overwriting an internal NUL character
*/
dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
- if (name->len > DNAME_INLINE_LEN-1) {
+ if (unlikely(!name)) {
+ static const struct qstr anon = QSTR_INIT("/", 1);
+ name = &anon;
+ dname = dentry->d_iname;
+ } else if (name->len > DNAME_INLINE_LEN-1) {
size_t size = offsetof(struct external_name, name[1]);
struct external_name *p = kmalloc(size + name->len,
GFP_KERNEL_ACCOUNT);
@@ -1746,6 +1763,7 @@ type_determined:
static void __d_instantiate(struct dentry *dentry, struct inode *inode)
{
unsigned add_flags = d_flags_for_inode(inode);
+ WARN_ON(d_in_lookup(dentry));
spin_lock(&dentry->d_lock);
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
@@ -1775,11 +1793,11 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
{
BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode) {
+ security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
spin_unlock(&inode->i_lock);
}
- security_d_instantiate(entry, inode);
}
EXPORT_SYMBOL(d_instantiate);
@@ -1796,6 +1814,7 @@ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
{
BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+ security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
spin_unlock(&inode->i_lock);
@@ -1804,7 +1823,6 @@ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
}
__d_instantiate(entry, inode);
spin_unlock(&inode->i_lock);
- security_d_instantiate(entry, inode);
return 0;
}
@@ -1815,9 +1833,7 @@ struct dentry *d_make_root(struct inode *root_inode)
struct dentry *res = NULL;
if (root_inode) {
- static const struct qstr name = QSTR_INIT("/", 1);
-
- res = __d_alloc(root_inode->i_sb, &name);
+ res = __d_alloc(root_inode->i_sb, NULL);
if (res)
d_instantiate(res, root_inode);
else
@@ -1858,7 +1874,6 @@ EXPORT_SYMBOL(d_find_any_alias);
static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
{
- static const struct qstr anonstring = QSTR_INIT("/", 1);
struct dentry *tmp;
struct dentry *res;
unsigned add_flags;
@@ -1872,12 +1887,13 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
if (res)
goto out_iput;
- tmp = __d_alloc(inode->i_sb, &anonstring);
+ tmp = __d_alloc(inode->i_sb, NULL);
if (!tmp) {
res = ERR_PTR(-ENOMEM);
goto out_iput;
}
+ security_d_instantiate(tmp, inode);
spin_lock(&inode->i_lock);
res = __d_find_any_alias(inode);
if (res) {
@@ -1900,13 +1916,10 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
hlist_bl_unlock(&tmp->d_sb->s_anon);
spin_unlock(&tmp->d_lock);
spin_unlock(&inode->i_lock);
- security_d_instantiate(tmp, inode);
return tmp;
out_iput:
- if (res && !IS_ERR(res))
- security_d_instantiate(res, inode);
iput(inode);
return res;
}
@@ -1975,28 +1988,36 @@ EXPORT_SYMBOL(d_obtain_root);
struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
struct qstr *name)
{
- struct dentry *found;
- struct dentry *new;
+ struct dentry *found, *res;
/*
* First check if a dentry matching the name already exists,
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
- if (!found) {
- new = d_alloc(dentry->d_parent, name);
- if (!new) {
- found = ERR_PTR(-ENOMEM);
- } else {
- found = d_splice_alias(inode, new);
- if (found) {
- dput(new);
- return found;
- }
- return new;
+ if (found) {
+ iput(inode);
+ return found;
+ }
+ if (d_in_lookup(dentry)) {
+ found = d_alloc_parallel(dentry->d_parent, name,
+ dentry->d_wait);
+ if (IS_ERR(found) || !d_in_lookup(found)) {
+ iput(inode);
+ return found;
}
+ } else {
+ found = d_alloc(dentry->d_parent, name);
+ if (!found) {
+ iput(inode);
+ return ERR_PTR(-ENOMEM);
+ }
+ }
+ res = d_splice_alias(inode, found);
+ if (res) {
+ dput(found);
+ return res;
}
- iput(inode);
return found;
}
EXPORT_SYMBOL(d_add_ci);
@@ -2363,17 +2384,194 @@ void d_rehash(struct dentry * entry)
}
EXPORT_SYMBOL(d_rehash);
+static inline unsigned start_dir_add(struct inode *dir)
+{
+
+ for (;;) {
+ unsigned n = dir->i_dir_seq;
+ if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+ return n;
+ cpu_relax();
+ }
+}
+
+static inline void end_dir_add(struct inode *dir, unsigned n)
+{
+ smp_store_release(&dir->i_dir_seq, n + 2);
+}
+
+static void d_wait_lookup(struct dentry *dentry)
+{
+ if (d_in_lookup(dentry)) {
+ DECLARE_WAITQUEUE(wait, current);
+ add_wait_queue(dentry->d_wait, &wait);
+ do {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_unlock(&dentry->d_lock);
+ schedule();
+ spin_lock(&dentry->d_lock);
+ } while (d_in_lookup(dentry));
+ }
+}
+
+struct dentry *d_alloc_parallel(struct dentry *parent,
+ const struct qstr *name,
+ wait_queue_head_t *wq)
+{
+ unsigned int len = name->len;
+ unsigned int hash = name->hash;
+ const unsigned char *str = name->name;
+ struct hlist_bl_head *b = in_lookup_hash(parent, hash);
+ struct hlist_bl_node *node;
+ struct dentry *new = d_alloc(parent, name);
+ struct dentry *dentry;
+ unsigned seq, r_seq, d_seq;
+
+ if (unlikely(!new))
+ return ERR_PTR(-ENOMEM);
+
+retry:
+ rcu_read_lock();
+ seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1;
+ r_seq = read_seqbegin(&rename_lock);
+ dentry = __d_lookup_rcu(parent, name, &d_seq);
+ if (unlikely(dentry)) {
+ if (!lockref_get_not_dead(&dentry->d_lockref)) {
+ rcu_read_unlock();
+ goto retry;
+ }
+ if (read_seqcount_retry(&dentry->d_seq, d_seq)) {
+ rcu_read_unlock();
+ dput(dentry);
+ goto retry;
+ }
+ rcu_read_unlock();
+ dput(new);
+ return dentry;
+ }
+ if (unlikely(read_seqretry(&rename_lock, r_seq))) {
+ rcu_read_unlock();
+ goto retry;
+ }
+ hlist_bl_lock(b);
+ if (unlikely(parent->d_inode->i_dir_seq != seq)) {
+ hlist_bl_unlock(b);
+ 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(),
+ * any potential in-lookup matches are going to stay here until
+ * we unlock the chain. All fields are stable in everything
+ * we encounter.
+ */
+ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) {
+ if (dentry->d_name.hash != hash)
+ 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;
+ if (parent->d_op->d_compare(parent, dentry, tlen, tname, name))
+ continue;
+ } else {
+ if (dentry->d_name.len != len)
+ continue;
+ if (dentry_cmp(dentry, str, len))
+ continue;
+ }
+ dget(dentry);
+ hlist_bl_unlock(b);
+ /* somebody is doing lookup for it right now; wait for it */
+ spin_lock(&dentry->d_lock);
+ d_wait_lookup(dentry);
+ /*
+ * it's not in-lookup anymore; in principle we should repeat
+ * everything from dcache lookup, but it's likely to be what
+ * d_lookup() would've found anyway. If it is, just return it;
+ * otherwise we really have to repeat the whole thing.
+ */
+ if (unlikely(dentry->d_name.hash != hash))
+ goto mismatch;
+ if (unlikely(dentry->d_parent != parent))
+ goto mismatch;
+ if (unlikely(d_unhashed(dentry)))
+ goto mismatch;
+ if (parent->d_flags & DCACHE_OP_COMPARE) {
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
+ if (parent->d_op->d_compare(parent, dentry, tlen, tname, name))
+ goto mismatch;
+ } else {
+ if (unlikely(dentry->d_name.len != len))
+ goto mismatch;
+ if (unlikely(dentry_cmp(dentry, str, len)))
+ goto mismatch;
+ }
+ /* OK, it *is* a hashed match; return it */
+ spin_unlock(&dentry->d_lock);
+ dput(new);
+ return dentry;
+ }
+ /* we can't take ->d_lock here; it's OK, though. */
+ new->d_flags |= DCACHE_PAR_LOOKUP;
+ new->d_wait = wq;
+ hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b);
+ hlist_bl_unlock(b);
+ return new;
+mismatch:
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ goto retry;
+}
+EXPORT_SYMBOL(d_alloc_parallel);
+
+void __d_lookup_done(struct dentry *dentry)
+{
+ struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent,
+ dentry->d_name.hash);
+ hlist_bl_lock(b);
+ dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
+ __hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
+ wake_up_all(dentry->d_wait);
+ dentry->d_wait = NULL;
+ hlist_bl_unlock(b);
+ INIT_HLIST_NODE(&dentry->d_u.d_alias);
+ INIT_LIST_HEAD(&dentry->d_lru);
+}
+EXPORT_SYMBOL(__d_lookup_done);
/* inode->i_lock held if inode is non-NULL */
static inline void __d_add(struct dentry *dentry, struct inode *inode)
{
+ struct inode *dir = NULL;
+ unsigned n;
+ spin_lock(&dentry->d_lock);
+ if (unlikely(d_in_lookup(dentry))) {
+ dir = dentry->d_parent->d_inode;
+ n = start_dir_add(dir);
+ __d_lookup_done(dentry);
+ }
if (inode) {
- __d_instantiate(dentry, inode);
+ unsigned add_flags = d_flags_for_inode(inode);
+ hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+ raw_write_seqcount_begin(&dentry->d_seq);
+ __d_set_inode_and_type(dentry, inode, add_flags);
+ raw_write_seqcount_end(&dentry->d_seq);
+ __fsnotify_d_instantiate(dentry);
+ }
+ _d_rehash(dentry);
+ if (dir)
+ end_dir_add(dir, n);
+ spin_unlock(&dentry->d_lock);
+ if (inode)
spin_unlock(&inode->i_lock);
- }
- security_d_instantiate(dentry, inode);
- d_rehash(dentry);
}
/**
@@ -2387,8 +2585,10 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
void d_add(struct dentry *entry, struct inode *inode)
{
- if (inode)
+ if (inode) {
+ security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
+ }
__d_add(entry, inode);
}
EXPORT_SYMBOL(d_add);
@@ -2598,6 +2798,8 @@ static void dentry_unlock_for_move(struct dentry *dentry, struct dentry *target)
static void __d_move(struct dentry *dentry, struct dentry *target,
bool exchange)
{
+ struct inode *dir = NULL;
+ unsigned n;
if (!dentry->d_inode)
printk(KERN_WARNING "VFS: moving negative dcache entry\n");
@@ -2605,6 +2807,11 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
BUG_ON(d_ancestor(target, dentry));
dentry_lock_for_move(dentry, target);
+ if (unlikely(d_in_lookup(target))) {
+ dir = target->d_parent->d_inode;
+ n = start_dir_add(dir);
+ __d_lookup_done(target);
+ }
write_seqcount_begin(&dentry->d_seq);
write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
@@ -2654,6 +2861,8 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
+ if (dir)
+ end_dir_add(dir, n);
dentry_unlock_for_move(dentry, target);
}
@@ -2724,7 +2933,8 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
static int __d_unalias(struct inode *inode,
struct dentry *dentry, struct dentry *alias)
{
- struct mutex *m1 = NULL, *m2 = NULL;
+ struct mutex *m1 = NULL;
+ struct rw_semaphore *m2 = NULL;
int ret = -ESTALE;
/* If alias and dentry share a parent, then no extra locks required */
@@ -2735,15 +2945,15 @@ static int __d_unalias(struct inode *inode,
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
- if (!inode_trylock(alias->d_parent->d_inode))
+ if (!inode_trylock_shared(alias->d_parent->d_inode))
goto out_err;
- m2 = &alias->d_parent->d_inode->i_mutex;
+ m2 = &alias->d_parent->d_inode->i_rwsem;
out_unalias:
__d_move(alias, dentry, false);
ret = 0;
out_err:
if (m2)
- mutex_unlock(m2);
+ up_read(m2);
if (m1)
mutex_unlock(m1);
return ret;
@@ -2782,6 +2992,7 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
if (!inode)
goto out;
+ security_d_instantiate(dentry, inode);
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode)) {
struct dentry *new = __d_find_any_alias(inode);
@@ -2809,7 +3020,6 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
} else {
__d_move(new, dentry, false);
write_sequnlock(&rename_lock);
- security_d_instantiate(new, inode);
}
iput(inode);
return new;
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index d2ba12e23ed9..9c1c9a01b7e5 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -22,6 +22,12 @@
#include <linux/slab.h>
#include <linux/atomic.h>
#include <linux/device.h>
+#include <linux/srcu.h>
+#include <asm/poll.h>
+
+#include "internal.h"
+
+struct poll_table_struct;
static ssize_t default_read_file(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
@@ -35,27 +41,293 @@ static ssize_t default_write_file(struct file *file, const char __user *buf,
return count;
}
-const struct file_operations debugfs_file_operations = {
+const struct file_operations debugfs_noop_file_operations = {
.read = default_read_file,
.write = default_write_file,
.open = simple_open,
.llseek = noop_llseek,
};
-static struct dentry *debugfs_create_mode(const char *name, umode_t mode,
- struct dentry *parent, void *value,
- const struct file_operations *fops,
- const struct file_operations *fops_ro,
- const struct file_operations *fops_wo)
+/**
+ * debugfs_use_file_start - mark the beginning of file data access
+ * @dentry: the dentry object whose data is being accessed.
+ * @srcu_idx: a pointer to some memory to store a SRCU index in.
+ *
+ * Up to a matching call to debugfs_use_file_finish(), any
+ * successive call into the file removing functions debugfs_remove()
+ * and debugfs_remove_recursive() will block. Since associated private
+ * file data may only get freed after a successful return of any of
+ * the removal functions, you may safely access it after a successful
+ * call to debugfs_use_file_start() without worrying about
+ * lifetime issues.
+ *
+ * If -%EIO is returned, the file has already been removed and thus,
+ * it is not safe to access any of its data. If, on the other hand,
+ * it is allowed to access the file data, zero is returned.
+ *
+ * Regardless of the return code, any call to
+ * debugfs_use_file_start() must be followed by a matching call
+ * to debugfs_use_file_finish().
+ */
+int debugfs_use_file_start(const struct dentry *dentry, int *srcu_idx)
+ __acquires(&debugfs_srcu)
+{
+ *srcu_idx = srcu_read_lock(&debugfs_srcu);
+ barrier();
+ if (d_unlinked(dentry))
+ return -EIO;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(debugfs_use_file_start);
+
+/**
+ * debugfs_use_file_finish - mark the end of file data access
+ * @srcu_idx: the SRCU index "created" by a former call to
+ * debugfs_use_file_start().
+ *
+ * Allow any ongoing concurrent call into debugfs_remove() or
+ * debugfs_remove_recursive() blocked by a former call to
+ * debugfs_use_file_start() to proceed and return to its caller.
+ */
+void debugfs_use_file_finish(int srcu_idx) __releases(&debugfs_srcu)
+{
+ srcu_read_unlock(&debugfs_srcu, srcu_idx);
+}
+EXPORT_SYMBOL_GPL(debugfs_use_file_finish);
+
+#define F_DENTRY(filp) ((filp)->f_path.dentry)
+
+#define REAL_FOPS_DEREF(dentry) \
+ ((const struct file_operations *)(dentry)->d_fsdata)
+
+static int open_proxy_open(struct inode *inode, struct file *filp)
+{
+ const struct dentry *dentry = F_DENTRY(filp);
+ const struct file_operations *real_fops = NULL;
+ int srcu_idx, r;
+
+ r = debugfs_use_file_start(dentry, &srcu_idx);
+ if (r) {
+ r = -ENOENT;
+ goto out;
+ }
+
+ real_fops = REAL_FOPS_DEREF(dentry);
+ real_fops = fops_get(real_fops);
+ if (!real_fops) {
+ /* Huh? Module did not clean up after itself at exit? */
+ WARN(1, "debugfs file owner did not clean up at exit: %pd",
+ dentry);
+ r = -ENXIO;
+ goto out;
+ }
+ replace_fops(filp, real_fops);
+
+ if (real_fops->open)
+ r = real_fops->open(inode, filp);
+
+out:
+ fops_put(real_fops);
+ debugfs_use_file_finish(srcu_idx);
+ return r;
+}
+
+const struct file_operations debugfs_open_proxy_file_operations = {
+ .open = open_proxy_open,
+};
+
+#define PROTO(args...) args
+#define ARGS(args...) args
+
+#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args) \
+static ret_type full_proxy_ ## name(proto) \
+{ \
+ const struct dentry *dentry = F_DENTRY(filp); \
+ const struct file_operations *real_fops = \
+ REAL_FOPS_DEREF(dentry); \
+ int srcu_idx; \
+ ret_type r; \
+ \
+ r = debugfs_use_file_start(dentry, &srcu_idx); \
+ if (likely(!r)) \
+ r = real_fops->name(args); \
+ debugfs_use_file_finish(srcu_idx); \
+ return r; \
+}
+
+FULL_PROXY_FUNC(llseek, loff_t, filp,
+ PROTO(struct file *filp, loff_t offset, int whence),
+ ARGS(filp, offset, whence));
+
+FULL_PROXY_FUNC(read, ssize_t, filp,
+ PROTO(struct file *filp, char __user *buf, size_t size,
+ loff_t *ppos),
+ ARGS(filp, buf, size, ppos));
+
+FULL_PROXY_FUNC(write, ssize_t, filp,
+ PROTO(struct file *filp, const char __user *buf, size_t size,
+ loff_t *ppos),
+ ARGS(filp, buf, size, ppos));
+
+FULL_PROXY_FUNC(unlocked_ioctl, long, filp,
+ PROTO(struct file *filp, unsigned int cmd, unsigned long arg),
+ ARGS(filp, cmd, arg));
+
+static unsigned int full_proxy_poll(struct file *filp,
+ struct poll_table_struct *wait)
+{
+ const struct dentry *dentry = F_DENTRY(filp);
+ const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry);
+ int srcu_idx;
+ unsigned int r = 0;
+
+ if (debugfs_use_file_start(dentry, &srcu_idx)) {
+ debugfs_use_file_finish(srcu_idx);
+ return POLLHUP;
+ }
+
+ r = real_fops->poll(filp, wait);
+ debugfs_use_file_finish(srcu_idx);
+ return r;
+}
+
+static int full_proxy_release(struct inode *inode, struct file *filp)
+{
+ const struct dentry *dentry = F_DENTRY(filp);
+ const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry);
+ const struct file_operations *proxy_fops = filp->f_op;
+ int r = 0;
+
+ /*
+ * We must not protect this against removal races here: the
+ * original releaser should be called unconditionally in order
+ * not to leak any resources. Releasers must not assume that
+ * ->i_private is still being meaningful here.
+ */
+ if (real_fops->release)
+ r = real_fops->release(inode, filp);
+
+ replace_fops(filp, d_inode(dentry)->i_fop);
+ kfree((void *)proxy_fops);
+ fops_put(real_fops);
+ return 0;
+}
+
+static void __full_proxy_fops_init(struct file_operations *proxy_fops,
+ const struct file_operations *real_fops)
+{
+ proxy_fops->release = full_proxy_release;
+ if (real_fops->llseek)
+ proxy_fops->llseek = full_proxy_llseek;
+ if (real_fops->read)
+ proxy_fops->read = full_proxy_read;
+ if (real_fops->write)
+ proxy_fops->write = full_proxy_write;
+ if (real_fops->poll)
+ proxy_fops->poll = full_proxy_poll;
+ if (real_fops->unlocked_ioctl)
+ proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl;
+}
+
+static int full_proxy_open(struct inode *inode, struct file *filp)
+{
+ const struct dentry *dentry = F_DENTRY(filp);
+ const struct file_operations *real_fops = NULL;
+ struct file_operations *proxy_fops = NULL;
+ int srcu_idx, r;
+
+ r = debugfs_use_file_start(dentry, &srcu_idx);
+ if (r) {
+ r = -ENOENT;
+ goto out;
+ }
+
+ real_fops = REAL_FOPS_DEREF(dentry);
+ real_fops = fops_get(real_fops);
+ if (!real_fops) {
+ /* Huh? Module did not cleanup after itself at exit? */
+ WARN(1, "debugfs file owner did not clean up at exit: %pd",
+ dentry);
+ r = -ENXIO;
+ goto out;
+ }
+
+ proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL);
+ if (!proxy_fops) {
+ r = -ENOMEM;
+ goto free_proxy;
+ }
+ __full_proxy_fops_init(proxy_fops, real_fops);
+ replace_fops(filp, proxy_fops);
+
+ if (real_fops->open) {
+ r = real_fops->open(inode, filp);
+
+ if (filp->f_op != proxy_fops) {
+ /* No protection against file removal anymore. */
+ WARN(1, "debugfs file owner replaced proxy fops: %pd",
+ dentry);
+ goto free_proxy;
+ }
+ }
+
+ goto out;
+free_proxy:
+ kfree(proxy_fops);
+ fops_put(real_fops);
+out:
+ debugfs_use_file_finish(srcu_idx);
+ return r;
+}
+
+const struct file_operations debugfs_full_proxy_file_operations = {
+ .open = full_proxy_open,
+};
+
+ssize_t debugfs_attr_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ ssize_t ret;
+ int srcu_idx;
+
+ ret = debugfs_use_file_start(F_DENTRY(file), &srcu_idx);
+ if (likely(!ret))
+ ret = simple_attr_read(file, buf, len, ppos);
+ debugfs_use_file_finish(srcu_idx);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(debugfs_attr_read);
+
+ssize_t debugfs_attr_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ ssize_t ret;
+ int srcu_idx;
+
+ ret = debugfs_use_file_start(F_DENTRY(file), &srcu_idx);
+ if (likely(!ret))
+ ret = simple_attr_write(file, buf, len, ppos);
+ debugfs_use_file_finish(srcu_idx);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(debugfs_attr_write);
+
+static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode,
+ struct dentry *parent, void *value,
+ const struct file_operations *fops,
+ const struct file_operations *fops_ro,
+ const struct file_operations *fops_wo)
{
/* if there are no write bits set, make read only */
if (!(mode & S_IWUGO))
- return debugfs_create_file(name, mode, parent, value, fops_ro);
+ return debugfs_create_file_unsafe(name, mode, parent, value,
+ fops_ro);
/* if there are no read bits set, make write only */
if (!(mode & S_IRUGO))
- return debugfs_create_file(name, mode, parent, value, fops_wo);
+ return debugfs_create_file_unsafe(name, mode, parent, value,
+ fops_wo);
- return debugfs_create_file(name, mode, parent, value, fops);
+ return debugfs_create_file_unsafe(name, mode, parent, value, fops);
}
static int debugfs_u8_set(void *data, u64 val)
@@ -68,9 +340,9 @@ static int debugfs_u8_get(void *data, u64 *val)
*val = *(u8 *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u8_ro, debugfs_u8_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_ro, debugfs_u8_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n");
/**
* debugfs_create_u8 - create a debugfs file that is used to read and write an unsigned 8-bit value
@@ -99,7 +371,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n");
struct dentry *debugfs_create_u8(const char *name, umode_t mode,
struct dentry *parent, u8 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_u8,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8,
&fops_u8_ro, &fops_u8_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u8);
@@ -114,9 +386,9 @@ static int debugfs_u16_get(void *data, u64 *val)
*val = *(u16 *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u16_ro, debugfs_u16_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_ro, debugfs_u16_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n");
/**
* debugfs_create_u16 - create a debugfs file that is used to read and write an unsigned 16-bit value
@@ -145,7 +417,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n");
struct dentry *debugfs_create_u16(const char *name, umode_t mode,
struct dentry *parent, u16 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_u16,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16,
&fops_u16_ro, &fops_u16_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u16);
@@ -160,9 +432,9 @@ static int debugfs_u32_get(void *data, u64 *val)
*val = *(u32 *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u32_ro, debugfs_u32_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_ro, debugfs_u32_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
/**
* debugfs_create_u32 - create a debugfs file that is used to read and write an unsigned 32-bit value
@@ -191,7 +463,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
struct dentry *debugfs_create_u32(const char *name, umode_t mode,
struct dentry *parent, u32 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_u32,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
&fops_u32_ro, &fops_u32_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u32);
@@ -207,9 +479,9 @@ static int debugfs_u64_get(void *data, u64 *val)
*val = *(u64 *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_u64, debugfs_u64_get, debugfs_u64_set, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u64_ro, debugfs_u64_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u64, debugfs_u64_get, debugfs_u64_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_ro, debugfs_u64_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
/**
* debugfs_create_u64 - create a debugfs file that is used to read and write an unsigned 64-bit value
@@ -238,7 +510,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
struct dentry *debugfs_create_u64(const char *name, umode_t mode,
struct dentry *parent, u64 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_u64,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64,
&fops_u64_ro, &fops_u64_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u64);
@@ -254,9 +526,10 @@ static int debugfs_ulong_get(void *data, u64 *val)
*val = *(unsigned long *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set,
+ "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n");
/**
* debugfs_create_ulong - create a debugfs file that is used to read and write
@@ -286,26 +559,30 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n");
struct dentry *debugfs_create_ulong(const char *name, umode_t mode,
struct dentry *parent, unsigned long *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_ulong,
- &fops_ulong_ro, &fops_ulong_wo);
+ return debugfs_create_mode_unsafe(name, mode, parent, value,
+ &fops_ulong, &fops_ulong_ro,
+ &fops_ulong_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_ulong);
-DEFINE_SIMPLE_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x16, debugfs_u16_get, debugfs_u16_set, "0x%04llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x16_ro, debugfs_u16_get, NULL, "0x%04llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x16_wo, NULL, debugfs_u16_set, "0x%04llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x16, debugfs_u16_get, debugfs_u16_set,
+ "0x%04llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_ro, debugfs_u16_get, NULL, "0x%04llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_wo, NULL, debugfs_u16_set, "0x%04llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x32, debugfs_u32_get, debugfs_u32_set, "0x%08llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, debugfs_u32_get, debugfs_u32_set,
+ "0x%08llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set,
+ "0x%016llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n");
/*
* debugfs_create_x{8,16,32,64} - create a debugfs file that is used to read and write an unsigned {8,16,32,64}-bit value
@@ -328,7 +605,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n");
struct dentry *debugfs_create_x8(const char *name, umode_t mode,
struct dentry *parent, u8 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_x8,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8,
&fops_x8_ro, &fops_x8_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x8);
@@ -346,7 +623,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_x8);
struct dentry *debugfs_create_x16(const char *name, umode_t mode,
struct dentry *parent, u16 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_x16,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16,
&fops_x16_ro, &fops_x16_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x16);
@@ -364,7 +641,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_x16);
struct dentry *debugfs_create_x32(const char *name, umode_t mode,
struct dentry *parent, u32 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_x32,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32,
&fops_x32_ro, &fops_x32_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x32);
@@ -382,7 +659,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_x32);
struct dentry *debugfs_create_x64(const char *name, umode_t mode,
struct dentry *parent, u64 *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_x64,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64,
&fops_x64_ro, &fops_x64_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x64);
@@ -398,10 +675,10 @@ static int debugfs_size_t_get(void *data, u64 *val)
*val = *(size_t *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set,
- "%llu\n"); /* %llu and %zu are more or less the same */
-DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set,
+ "%llu\n"); /* %llu and %zu are more or less the same */
+DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n");
/**
* debugfs_create_size_t - create a debugfs file that is used to read and write an size_t value
@@ -416,8 +693,9 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n");
struct dentry *debugfs_create_size_t(const char *name, umode_t mode,
struct dentry *parent, size_t *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_size_t,
- &fops_size_t_ro, &fops_size_t_wo);
+ return debugfs_create_mode_unsafe(name, mode, parent, value,
+ &fops_size_t, &fops_size_t_ro,
+ &fops_size_t_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_size_t);
@@ -431,10 +709,12 @@ static int debugfs_atomic_t_get(void *data, u64 *val)
*val = atomic_read((atomic_t *)data);
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get,
+DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get,
debugfs_atomic_t_set, "%lld\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n");
-DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_ro, debugfs_atomic_t_get, NULL,
+ "%lld\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set,
+ "%lld\n");
/**
* debugfs_create_atomic_t - create a debugfs file that is used to read and
@@ -450,8 +730,9 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n");
struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode,
struct dentry *parent, atomic_t *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_atomic_t,
- &fops_atomic_t_ro, &fops_atomic_t_wo);
+ return debugfs_create_mode_unsafe(name, mode, parent, value,
+ &fops_atomic_t, &fops_atomic_t_ro,
+ &fops_atomic_t_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_atomic_t);
@@ -459,9 +740,17 @@ ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
char buf[3];
- bool *val = file->private_data;
+ bool val;
+ int r, srcu_idx;
- if (*val)
+ r = debugfs_use_file_start(F_DENTRY(file), &srcu_idx);
+ if (likely(!r))
+ val = *(bool *)file->private_data;
+ debugfs_use_file_finish(srcu_idx);
+ if (r)
+ return r;
+
+ if (val)
buf[0] = 'Y';
else
buf[0] = 'N';
@@ -477,6 +766,7 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
char buf[32];
size_t buf_size;
bool bv;
+ int r, srcu_idx;
bool *val = file->private_data;
buf_size = min(count, (sizeof(buf)-1));
@@ -484,8 +774,14 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
return -EFAULT;
buf[buf_size] = '\0';
- if (strtobool(buf, &bv) == 0)
- *val = bv;
+ if (strtobool(buf, &bv) == 0) {
+ r = debugfs_use_file_start(F_DENTRY(file), &srcu_idx);
+ if (likely(!r))
+ *val = bv;
+ debugfs_use_file_finish(srcu_idx);
+ if (r)
+ return r;
+ }
return count;
}
@@ -537,7 +833,7 @@ static const struct file_operations fops_bool_wo = {
struct dentry *debugfs_create_bool(const char *name, umode_t mode,
struct dentry *parent, bool *value)
{
- return debugfs_create_mode(name, mode, parent, value, &fops_bool,
+ return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_bool,
&fops_bool_ro, &fops_bool_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_bool);
@@ -546,8 +842,15 @@ static ssize_t read_file_blob(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
struct debugfs_blob_wrapper *blob = file->private_data;
- return simple_read_from_buffer(user_buf, count, ppos, blob->data,
- blob->size);
+ ssize_t r;
+ int srcu_idx;
+
+ r = debugfs_use_file_start(F_DENTRY(file), &srcu_idx);
+ if (likely(!r))
+ r = simple_read_from_buffer(user_buf, count, ppos, blob->data,
+ blob->size);
+ debugfs_use_file_finish(srcu_idx);
+ return r;
}
static const struct file_operations fops_blob = {
@@ -584,7 +887,7 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode,
struct dentry *parent,
struct debugfs_blob_wrapper *blob)
{
- return debugfs_create_file(name, mode, parent, blob, &fops_blob);
+ return debugfs_create_file_unsafe(name, mode, parent, blob, &fops_blob);
}
EXPORT_SYMBOL_GPL(debugfs_create_blob);
@@ -689,7 +992,8 @@ struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
data->array = array;
data->elements = elements;
- return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
+ return debugfs_create_file_unsafe(name, mode, parent, data,
+ &u32_array_fops);
}
EXPORT_SYMBOL_GPL(debugfs_create_u32_array);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 8580831ed237..4bc1f68243c1 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -27,9 +27,14 @@
#include <linux/parser.h>
#include <linux/magic.h>
#include <linux/slab.h>
+#include <linux/srcu.h>
+
+#include "internal.h"
#define DEBUGFS_DEFAULT_MODE 0700
+DEFINE_SRCU(debugfs_srcu);
+
static struct vfsmount *debugfs_mount;
static int debugfs_mount_count;
static bool debugfs_registered;
@@ -39,7 +44,8 @@ static struct inode *debugfs_get_inode(struct super_block *sb)
struct inode *inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ inode->i_atime = inode->i_mtime =
+ inode->i_ctime = current_fs_time(sb);
}
return inode;
}
@@ -294,6 +300,37 @@ static struct dentry *end_creating(struct dentry *dentry)
return dentry;
}
+static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *proxy_fops,
+ const struct file_operations *real_fops)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+
+ if (!(mode & S_IFMT))
+ mode |= S_IFREG;
+ BUG_ON(!S_ISREG(mode));
+ dentry = start_creating(name, parent);
+
+ if (IS_ERR(dentry))
+ return NULL;
+
+ inode = debugfs_get_inode(dentry->d_sb);
+ if (unlikely(!inode))
+ return failed_creating(dentry);
+
+ inode->i_mode = mode;
+ inode->i_private = data;
+
+ inode->i_fop = proxy_fops;
+ dentry->d_fsdata = (void *)real_fops;
+
+ d_instantiate(dentry, inode);
+ fsnotify_create(d_inode(dentry->d_parent), dentry);
+ return end_creating(dentry);
+}
+
/**
* debugfs_create_file - create a file in the debugfs filesystem
* @name: a pointer to a string containing the name of the file to create.
@@ -324,29 +361,52 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops)
{
- struct dentry *dentry;
- struct inode *inode;
- if (!(mode & S_IFMT))
- mode |= S_IFREG;
- BUG_ON(!S_ISREG(mode));
- dentry = start_creating(name, parent);
-
- if (IS_ERR(dentry))
- return NULL;
+ return __debugfs_create_file(name, mode, parent, data,
+ fops ? &debugfs_full_proxy_file_operations :
+ &debugfs_noop_file_operations,
+ fops);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_file);
- inode = debugfs_get_inode(dentry->d_sb);
- if (unlikely(!inode))
- return failed_creating(dentry);
+/**
+ * debugfs_create_file_unsafe - create a file in the debugfs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is NULL, then the
+ * file will be created in the root of the debugfs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ * on. The inode.i_private pointer will point to this value on
+ * the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ * this file.
+ *
+ * debugfs_create_file_unsafe() is completely analogous to
+ * debugfs_create_file(), the only difference being that the fops
+ * handed it will not get protected against file removals by the
+ * debugfs core.
+ *
+ * It is your responsibility to protect your struct file_operation
+ * methods against file removals by means of debugfs_use_file_start()
+ * and debugfs_use_file_finish(). ->open() is still protected by
+ * debugfs though.
+ *
+ * Any struct file_operations defined by means of
+ * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and
+ * thus, may be used here.
+ */
+struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *fops)
+{
- inode->i_mode = mode;
- inode->i_fop = fops ? fops : &debugfs_file_operations;
- inode->i_private = data;
- d_instantiate(dentry, inode);
- fsnotify_create(d_inode(dentry->d_parent), dentry);
- return end_creating(dentry);
+ return __debugfs_create_file(name, mode, parent, data,
+ fops ? &debugfs_open_proxy_file_operations :
+ &debugfs_noop_file_operations,
+ fops);
}
-EXPORT_SYMBOL_GPL(debugfs_create_file);
+EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
/**
* debugfs_create_file_size - create a file in the debugfs filesystem
@@ -461,7 +521,11 @@ struct dentry *debugfs_create_automount(const char *name,
inode->i_flags |= S_AUTOMOUNT;
inode->i_private = data;
dentry->d_fsdata = (void *)f;
+ /* directory inodes start off with i_nlink == 2 (for "." entry) */
+ inc_nlink(inode);
d_instantiate(dentry, inode);
+ inc_nlink(d_inode(dentry->d_parent));
+ fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
return end_creating(dentry);
}
EXPORT_SYMBOL(debugfs_create_automount);
@@ -565,6 +629,8 @@ void debugfs_remove(struct dentry *dentry)
inode_unlock(d_inode(parent));
if (!ret)
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+
+ synchronize_srcu(&debugfs_srcu);
}
EXPORT_SYMBOL_GPL(debugfs_remove);
@@ -642,6 +708,8 @@ void debugfs_remove_recursive(struct dentry *dentry)
if (!__debugfs_remove(child, parent))
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
inode_unlock(d_inode(parent));
+
+ synchronize_srcu(&debugfs_srcu);
}
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
new file mode 100644
index 000000000000..bba52634b995
--- /dev/null
+++ b/fs/debugfs/internal.h
@@ -0,0 +1,26 @@
+/*
+ * internal.h - declarations internal to debugfs
+ *
+ * Copyright (C) 2016 Nicolai Stange <nicstange@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ */
+
+#ifndef _DEBUGFS_INTERNAL_H_
+#define _DEBUGFS_INTERNAL_H_
+
+struct file_operations;
+
+/* declared over in file.c */
+extern const struct file_operations debugfs_noop_file_operations;
+extern const struct file_operations debugfs_open_proxy_file_operations;
+extern const struct file_operations debugfs_full_proxy_file_operations;
+
+struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *fops);
+
+#endif /* _DEBUGFS_INTERNAL_H_ */
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 655f21f99160..0b2954d7172d 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -128,6 +128,7 @@ static const match_table_t tokens = {
struct pts_fs_info {
struct ida allocated_ptys;
struct pts_mount_opts mount_opts;
+ struct super_block *sb;
struct dentry *ptmx_dentry;
};
@@ -358,7 +359,7 @@ static const struct super_operations devpts_sops = {
.show_options = devpts_show_options,
};
-static void *new_pts_fs_info(void)
+static void *new_pts_fs_info(struct super_block *sb)
{
struct pts_fs_info *fsi;
@@ -369,6 +370,7 @@ static void *new_pts_fs_info(void)
ida_init(&fsi->allocated_ptys);
fsi->mount_opts.mode = DEVPTS_DEFAULT_MODE;
fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
+ fsi->sb = sb;
return fsi;
}
@@ -384,7 +386,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
s->s_op = &devpts_sops;
s->s_time_gran = 1;
- s->s_fs_info = new_pts_fs_info();
+ s->s_fs_info = new_pts_fs_info(s);
if (!s->s_fs_info)
goto fail;
@@ -524,17 +526,14 @@ static struct file_system_type devpts_fs_type = {
* to the System V naming convention
*/
-int devpts_new_index(struct inode *ptmx_inode)
+int devpts_new_index(struct pts_fs_info *fsi)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
- struct pts_fs_info *fsi;
int index;
int ida_ret;
- if (!sb)
+ if (!fsi)
return -ENODEV;
- fsi = DEVPTS_SB(sb);
retry:
if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
return -ENOMEM;
@@ -564,11 +563,8 @@ retry:
return index;
}
-void devpts_kill_index(struct inode *ptmx_inode, int idx)
+void devpts_kill_index(struct pts_fs_info *fsi, int idx)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
- struct pts_fs_info *fsi = DEVPTS_SB(sb);
-
mutex_lock(&allocated_ptys_lock);
ida_remove(&fsi->allocated_ptys, idx);
pty_count--;
@@ -578,21 +574,25 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
/*
* pty code needs to hold extra references in case of last /dev/tty close
*/
-
-void devpts_add_ref(struct inode *ptmx_inode)
+struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+ struct super_block *sb;
+ struct pts_fs_info *fsi;
+
+ sb = pts_sb_from_inode(ptmx_inode);
+ if (!sb)
+ return NULL;
+ fsi = DEVPTS_SB(sb);
+ if (!fsi)
+ return NULL;
atomic_inc(&sb->s_active);
- ihold(ptmx_inode);
+ return fsi;
}
-void devpts_del_ref(struct inode *ptmx_inode)
+void devpts_put_ref(struct pts_fs_info *fsi)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-
- iput(ptmx_inode);
- deactivate_super(sb);
+ deactivate_super(fsi->sb);
}
/**
@@ -604,22 +604,20 @@ void devpts_del_ref(struct inode *ptmx_inode)
*
* The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill.
*/
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
- void *priv)
+struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
{
struct dentry *dentry;
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+ struct super_block *sb;
struct inode *inode;
struct dentry *root;
- struct pts_fs_info *fsi;
struct pts_mount_opts *opts;
char s[12];
- if (!sb)
+ if (!fsi)
return ERR_PTR(-ENODEV);
+ sb = fsi->sb;
root = sb->s_root;
- fsi = DEVPTS_SB(sb);
opts = &fsi->mount_opts;
inode = new_inode(sb);
@@ -630,25 +628,21 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
inode->i_uid = opts->setuid ? opts->uid : current_fsuid();
inode->i_gid = opts->setgid ? opts->gid : current_fsgid();
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
- init_special_inode(inode, S_IFCHR|opts->mode, device);
- inode->i_private = priv;
+ init_special_inode(inode, S_IFCHR|opts->mode, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index));
sprintf(s, "%d", index);
- inode_lock(d_inode(root));
-
dentry = d_alloc_name(root, s);
if (dentry) {
+ dentry->d_fsdata = priv;
d_add(dentry, inode);
fsnotify_create(d_inode(root), dentry);
} else {
iput(inode);
- inode = ERR_PTR(-ENOMEM);
+ dentry = ERR_PTR(-ENOMEM);
}
- inode_unlock(d_inode(root));
-
- return inode;
+ return dentry;
}
/**
@@ -657,24 +651,10 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
*
* Returns whatever was passed as priv in devpts_pty_new for a given inode.
*/
-void *devpts_get_priv(struct inode *pts_inode)
+void *devpts_get_priv(struct dentry *dentry)
{
- struct dentry *dentry;
- void *priv = NULL;
-
- BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
-
- /* Ensure dentry has not been deleted by devpts_pty_kill() */
- dentry = d_find_alias(pts_inode);
- if (!dentry)
- return NULL;
-
- if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
- priv = pts_inode->i_private;
-
- dput(dentry);
-
- return priv;
+ WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC);
+ return dentry->d_fsdata;
}
/**
@@ -683,24 +663,14 @@ void *devpts_get_priv(struct inode *pts_inode)
*
* This is an inverse operation of devpts_pty_new.
*/
-void devpts_pty_kill(struct inode *inode)
+void devpts_pty_kill(struct dentry *dentry)
{
- struct super_block *sb = pts_sb_from_inode(inode);
- struct dentry *root = sb->s_root;
- struct dentry *dentry;
+ WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC);
- BUG_ON(inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
-
- inode_lock(d_inode(root));
-
- dentry = d_find_alias(inode);
-
- drop_nlink(inode);
+ dentry->d_fsdata = NULL;
+ drop_nlink(dentry->d_inode);
d_delete(dentry);
dput(dentry); /* d_alloc_name() in devpts_pty_new() */
- dput(dentry); /* d_find_alias above */
-
- inode_unlock(d_inode(root));
}
static int __init init_devpts_fs(void)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 472037732daf..3bf3f20f8ecc 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -224,9 +224,9 @@ static inline struct page *dio_get_page(struct dio *dio,
* filesystems can use it to hold additional state between get_block calls and
* dio_complete.
*/
-static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
- bool is_async)
+static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
{
+ loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
/*
@@ -256,6 +256,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
if (dio->end_io) {
int err;
+ // XXX: ki_pos??
err = dio->end_io(dio->iocb, offset, ret, dio->private);
if (err)
ret = err;
@@ -265,15 +266,15 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
inode_dio_end(dio->inode);
if (is_async) {
- if (dio->rw & WRITE) {
- int err;
-
- err = generic_write_sync(dio->iocb->ki_filp, offset,
- transferred);
- if (err < 0 && ret > 0)
- ret = err;
- }
+ /*
+ * generic_write_sync expects ki_pos to have been updated
+ * already, but the submission path only does this for
+ * synchronous I/O.
+ */
+ dio->iocb->ki_pos += transferred;
+ if (dio->rw & WRITE)
+ ret = generic_write_sync(dio->iocb, transferred);
dio->iocb->ki_complete(dio->iocb, ret, 0);
}
@@ -285,7 +286,7 @@ static void dio_aio_complete_work(struct work_struct *work)
{
struct dio *dio = container_of(work, struct dio, complete_work);
- dio_complete(dio, dio->iocb->ki_pos, 0, true);
+ dio_complete(dio, 0, true);
}
static int dio_bio_complete(struct dio *dio, struct bio *bio);
@@ -314,7 +315,7 @@ static void dio_bio_end_aio(struct bio *bio)
queue_work(dio->inode->i_sb->s_dio_done_wq,
&dio->complete_work);
} else {
- dio_complete(dio, dio->iocb->ki_pos, 0, true);
+ dio_complete(dio, 0, true);
}
}
}
@@ -1113,7 +1114,7 @@ static inline int drop_refcount(struct dio *dio)
static inline ssize_t
do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
- loff_t offset, get_block_t get_block, dio_iodone_t end_io,
+ get_block_t get_block, dio_iodone_t end_io,
dio_submit_t submit_io, int flags)
{
unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits);
@@ -1121,6 +1122,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
unsigned blocksize_mask = (1 << blkbits) - 1;
ssize_t retval = -EINVAL;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
loff_t end = offset + count;
struct dio *dio;
struct dio_submit sdio = { 0, };
@@ -1318,7 +1320,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
dio_await_completion(dio);
if (drop_refcount(dio) == 0) {
- retval = dio_complete(dio, offset, retval, false);
+ retval = dio_complete(dio, retval, false);
} else
BUG_ON(retval != -EIOCBQUEUED);
@@ -1328,7 +1330,7 @@ out:
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
- loff_t offset, get_block_t get_block,
+ get_block_t get_block,
dio_iodone_t end_io, dio_submit_t submit_io,
int flags)
{
@@ -1344,7 +1346,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
prefetch(bdev->bd_queue);
prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
- return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block,
+ return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block,
end_io, submit_io, flags);
}
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index d09cb4cdd09f..ebd40f46ed4c 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -105,19 +105,7 @@ static int ecryptfs_calculate_md5(char *dst,
struct crypto_shash *tfm;
int rc = 0;
- mutex_lock(&crypt_stat->cs_hash_tfm_mutex);
tfm = crypt_stat->hash_tfm;
- if (!tfm) {
- tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0);
- if (IS_ERR(tfm)) {
- rc = PTR_ERR(tfm);
- ecryptfs_printk(KERN_ERR, "Error attempting to "
- "allocate crypto context; rc = [%d]\n",
- rc);
- goto out;
- }
- crypt_stat->hash_tfm = tfm;
- }
rc = ecryptfs_hash_digest(tfm, src, len, dst);
if (rc) {
printk(KERN_ERR
@@ -126,7 +114,6 @@ static int ecryptfs_calculate_md5(char *dst,
goto out;
}
out:
- mutex_unlock(&crypt_stat->cs_hash_tfm_mutex);
return rc;
}
@@ -207,16 +194,29 @@ out:
*
* Initialize the crypt_stat structure.
*/
-void
-ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
+int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
{
+ struct crypto_shash *tfm;
+ int rc;
+
+ tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0);
+ if (IS_ERR(tfm)) {
+ rc = PTR_ERR(tfm);
+ ecryptfs_printk(KERN_ERR, "Error attempting to "
+ "allocate crypto context; rc = [%d]\n",
+ rc);
+ return rc;
+ }
+
memset((void *)crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat));
INIT_LIST_HEAD(&crypt_stat->keysig_list);
mutex_init(&crypt_stat->keysig_list_mutex);
mutex_init(&crypt_stat->cs_mutex);
mutex_init(&crypt_stat->cs_tfm_mutex);
- mutex_init(&crypt_stat->cs_hash_tfm_mutex);
+ crypt_stat->hash_tfm = tfm;
crypt_stat->flags |= ECRYPTFS_STRUCT_INITIALIZED;
+
+ return 0;
}
/**
@@ -1369,7 +1369,9 @@ int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode)
ssize_t size;
int rc = 0;
- size = ecryptfs_getxattr_lower(lower_dentry, ECRYPTFS_XATTR_NAME,
+ size = ecryptfs_getxattr_lower(lower_dentry,
+ ecryptfs_inode_to_lower(ecryptfs_inode),
+ ECRYPTFS_XATTR_NAME,
page_virt, ECRYPTFS_DEFAULT_EXTENT_SIZE);
if (size < 0) {
if (unlikely(ecryptfs_verbosity > 0))
@@ -1391,6 +1393,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
int rc;
rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
+ ecryptfs_inode_to_lower(inode),
ECRYPTFS_XATTR_NAME, file_size,
ECRYPTFS_SIZE_AND_MARKER_BYTES);
if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index d123fbaa28e0..3ec495db7e82 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -242,7 +242,6 @@ struct ecryptfs_crypt_stat {
struct list_head keysig_list;
struct mutex keysig_list_mutex;
struct mutex cs_tfm_mutex;
- struct mutex cs_hash_tfm_mutex;
struct mutex cs_mutex;
};
@@ -577,7 +576,7 @@ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg,
int sg_size);
int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat);
void ecryptfs_rotate_iv(unsigned char *iv);
-void ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat);
+int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat);
void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat);
void ecryptfs_destroy_mount_crypt_stat(
struct ecryptfs_mount_crypt_stat *mount_crypt_stat);
@@ -607,8 +606,8 @@ ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
unsigned char *src, struct dentry *ecryptfs_dentry);
int ecryptfs_truncate(struct dentry *dentry, loff_t new_length);
ssize_t
-ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
- void *value, size_t size);
+ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
+ const char *name, void *value, size_t size);
int
ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index feef8a9c4de7..7000b96b783e 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -112,7 +112,6 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
.sb = inode->i_sb,
};
lower_file = ecryptfs_file_to_lower(file);
- lower_file->f_pos = ctx->pos;
rc = iterate_dir(lower_file, &buf.ctx);
ctx->pos = buf.ctx.pos;
if (rc < 0)
@@ -223,14 +222,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
}
ecryptfs_set_file_lower(
file, ecryptfs_inode_to_private(inode)->lower_file);
- if (d_is_dir(ecryptfs_dentry)) {
- ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
- mutex_lock(&crypt_stat->cs_mutex);
- crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
- mutex_unlock(&crypt_stat->cs_mutex);
- rc = 0;
- goto out;
- }
rc = read_or_initialize_metadata(ecryptfs_dentry);
if (rc)
goto out_put;
@@ -247,6 +238,45 @@ out:
return rc;
}
+/**
+ * ecryptfs_dir_open
+ * @inode: inode speciying file to open
+ * @file: Structure to return filled in
+ *
+ * Opens the file specified by inode.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_dir_open(struct inode *inode, struct file *file)
+{
+ struct dentry *ecryptfs_dentry = file->f_path.dentry;
+ /* Private value of ecryptfs_dentry allocated in
+ * ecryptfs_lookup() */
+ struct ecryptfs_file_info *file_info;
+ struct file *lower_file;
+
+ /* Released in ecryptfs_release or end of function if failure */
+ file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
+ ecryptfs_set_file_private(file, file_info);
+ if (unlikely(!file_info)) {
+ ecryptfs_printk(KERN_ERR,
+ "Error attempting to allocate memory\n");
+ return -ENOMEM;
+ }
+ lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry),
+ file->f_flags, current_cred());
+ if (IS_ERR(lower_file)) {
+ printk(KERN_ERR "%s: Error attempting to initialize "
+ "the lower file for the dentry with name "
+ "[%pd]; rc = [%ld]\n", __func__,
+ ecryptfs_dentry, PTR_ERR(lower_file));
+ kmem_cache_free(ecryptfs_file_info_cache, file_info);
+ return PTR_ERR(lower_file);
+ }
+ ecryptfs_set_file_lower(file, lower_file);
+ return 0;
+}
+
static int ecryptfs_flush(struct file *file, fl_owner_t td)
{
struct file *lower_file = ecryptfs_file_to_lower(file);
@@ -267,6 +297,19 @@ static int ecryptfs_release(struct inode *inode, struct file *file)
return 0;
}
+static int ecryptfs_dir_release(struct inode *inode, struct file *file)
+{
+ fput(ecryptfs_file_to_lower(file));
+ kmem_cache_free(ecryptfs_file_info_cache,
+ ecryptfs_file_to_private(file));
+ return 0;
+}
+
+static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+ return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence);
+}
+
static int
ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
@@ -340,26 +383,22 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
#endif
const struct file_operations ecryptfs_dir_fops = {
- .iterate = ecryptfs_readdir,
+ .iterate_shared = ecryptfs_readdir,
.read = generic_read_dir,
.unlocked_ioctl = ecryptfs_unlocked_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ecryptfs_compat_ioctl,
#endif
- .open = ecryptfs_open,
- .flush = ecryptfs_flush,
- .release = ecryptfs_release,
+ .open = ecryptfs_dir_open,
+ .release = ecryptfs_dir_release,
.fsync = ecryptfs_fsync,
- .fasync = ecryptfs_fasync,
- .splice_read = generic_file_splice_read,
- .llseek = default_llseek,
+ .llseek = ecryptfs_dir_llseek,
};
const struct file_operations ecryptfs_main_fops = {
.llseek = generic_file_llseek,
.read_iter = ecryptfs_read_update_atime,
.write_iter = generic_file_write_iter,
- .iterate = ecryptfs_readdir,
.unlocked_ioctl = ecryptfs_unlocked_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ecryptfs_compat_ioctl,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 224b49e71aa4..318b04689d76 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -324,9 +324,8 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
/**
* ecryptfs_lookup_interpose - Dentry interposition for a lookup
*/
-static int ecryptfs_lookup_interpose(struct dentry *dentry,
- struct dentry *lower_dentry,
- struct inode *dir_inode)
+static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
+ struct dentry *lower_dentry)
{
struct inode *inode, *lower_inode = d_inode(lower_dentry);
struct ecryptfs_dentry_info *dentry_info;
@@ -339,11 +338,12 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
"to allocate ecryptfs_dentry_info struct\n",
__func__);
dput(lower_dentry);
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
}
lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
- fsstack_copy_attr_atime(dir_inode, d_inode(lower_dentry->d_parent));
+ fsstack_copy_attr_atime(d_inode(dentry->d_parent),
+ d_inode(lower_dentry->d_parent));
BUG_ON(!d_count(lower_dentry));
ecryptfs_set_dentry_private(dentry, dentry_info);
@@ -353,27 +353,25 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
if (d_really_is_negative(lower_dentry)) {
/* We want to add because we couldn't find in lower */
d_add(dentry, NULL);
- return 0;
+ return NULL;
}
- inode = __ecryptfs_get_inode(lower_inode, dir_inode->i_sb);
+ inode = __ecryptfs_get_inode(lower_inode, dentry->d_sb);
if (IS_ERR(inode)) {
printk(KERN_ERR "%s: Error interposing; rc = [%ld]\n",
__func__, PTR_ERR(inode));
- return PTR_ERR(inode);
+ return ERR_CAST(inode);
}
if (S_ISREG(inode->i_mode)) {
rc = ecryptfs_i_size_read(dentry, inode);
if (rc) {
make_bad_inode(inode);
- return rc;
+ return ERR_PTR(rc);
}
}
if (inode->i_state & I_NEW)
unlock_new_inode(inode);
- d_add(dentry, inode);
-
- return rc;
+ return d_splice_alias(inode, dentry);
}
/**
@@ -390,55 +388,42 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
unsigned int flags)
{
char *encrypted_and_encoded_name = NULL;
- size_t encrypted_and_encoded_name_size;
- struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct dentry *lower_dir_dentry, *lower_dentry;
+ const char *name = ecryptfs_dentry->d_name.name;
+ size_t len = ecryptfs_dentry->d_name.len;
+ struct dentry *res;
int rc = 0;
lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
- lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name,
- lower_dir_dentry,
- ecryptfs_dentry->d_name.len);
- if (IS_ERR(lower_dentry)) {
- rc = PTR_ERR(lower_dentry);
- ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
- "[%d] on lower_dentry = [%pd]\n", __func__, rc,
- ecryptfs_dentry);
- goto out;
- }
- if (d_really_is_positive(lower_dentry))
- goto interpose;
+
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
- if (!(mount_crypt_stat
- && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)))
- goto interpose;
- dput(lower_dentry);
- rc = ecryptfs_encrypt_and_encode_filename(
- &encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
- mount_crypt_stat, ecryptfs_dentry->d_name.name,
- ecryptfs_dentry->d_name.len);
- if (rc) {
- printk(KERN_ERR "%s: Error attempting to encrypt and encode "
- "filename; rc = [%d]\n", __func__, rc);
- goto out;
+ if (mount_crypt_stat
+ && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
+ rc = ecryptfs_encrypt_and_encode_filename(
+ &encrypted_and_encoded_name, &len,
+ mount_crypt_stat, name, len);
+ if (rc) {
+ printk(KERN_ERR "%s: Error attempting to encrypt and encode "
+ "filename; rc = [%d]\n", __func__, rc);
+ return ERR_PTR(rc);
+ }
+ name = encrypted_and_encoded_name;
}
- lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name,
- lower_dir_dentry,
- encrypted_and_encoded_name_size);
+
+ lower_dentry = lookup_one_len_unlocked(name, lower_dir_dentry, len);
if (IS_ERR(lower_dentry)) {
- rc = PTR_ERR(lower_dentry);
ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
- "[%d] on lower_dentry = [%s]\n", __func__, rc,
- encrypted_and_encoded_name);
- goto out;
+ "[%ld] on lower_dentry = [%s]\n", __func__,
+ PTR_ERR(lower_dentry),
+ name);
+ res = ERR_CAST(lower_dentry);
+ } else {
+ res = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry);
}
-interpose:
- rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry,
- ecryptfs_dir_inode);
-out:
kfree(encrypted_and_encoded_name);
- return ERR_PTR(rc);
+ return res;
}
static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
@@ -898,8 +883,11 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
struct ecryptfs_crypt_stat *crypt_stat;
crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat;
- if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
- ecryptfs_init_crypt_stat(crypt_stat);
+ if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) {
+ rc = ecryptfs_init_crypt_stat(crypt_stat);
+ if (rc)
+ return rc;
+ }
inode = d_inode(dentry);
lower_inode = ecryptfs_inode_to_lower(inode);
lower_dentry = ecryptfs_dentry_to_lower(dentry);
@@ -1033,29 +1021,30 @@ out:
}
ssize_t
-ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
- void *value, size_t size)
+ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
+ const char *name, void *value, size_t size)
{
int rc = 0;
- if (!d_inode(lower_dentry)->i_op->getxattr) {
+ if (!lower_inode->i_op->getxattr) {
rc = -EOPNOTSUPP;
goto out;
}
- inode_lock(d_inode(lower_dentry));
- rc = d_inode(lower_dentry)->i_op->getxattr(lower_dentry, name, value,
- size);
- inode_unlock(d_inode(lower_dentry));
+ inode_lock(lower_inode);
+ rc = lower_inode->i_op->getxattr(lower_dentry, lower_inode,
+ name, value, size);
+ inode_unlock(lower_inode);
out:
return rc;
}
static ssize_t
-ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value,
- size_t size)
+ecryptfs_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size)
{
- return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), name,
- value, size);
+ return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
+ ecryptfs_inode_to_lower(inode),
+ name, value, size);
}
static ssize_t
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index e6b1d80952b9..148d11b514fb 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -436,7 +436,8 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
goto out;
}
inode_lock(lower_inode);
- size = lower_inode->i_op->getxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
+ size = lower_inode->i_op->getxattr(lower_dentry, lower_inode,
+ ECRYPTFS_XATTR_NAME,
xattr_virt, PAGE_SIZE);
if (size < 0)
size = 8;
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 77a486d3a51b..85411ceb0508 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -55,7 +55,10 @@ static struct inode *ecryptfs_alloc_inode(struct super_block *sb)
inode_info = kmem_cache_alloc(ecryptfs_inode_info_cache, GFP_KERNEL);
if (unlikely(!inode_info))
goto out;
- ecryptfs_init_crypt_stat(&inode_info->crypt_stat);
+ if (ecryptfs_init_crypt_stat(&inode_info->crypt_stat)) {
+ kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
+ goto out;
+ }
mutex_init(&inode_info->lower_file_mutex);
atomic_set(&inode_info->lower_file_count, 0);
inode_info->lower_file = NULL;
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index d48e0d261d78..5f22e74bbade 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -157,7 +157,7 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg)
return 0;
}
-long
+static long
efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
{
void __user *arg = (void __user *)p;
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index e2ab6d0497f2..1d73fc6dba13 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -11,6 +11,7 @@
#include <linux/fs.h>
#include <linux/ctype.h>
#include <linux/slab.h>
+#include <linux/uuid.h>
#include "internal.h"
@@ -46,11 +47,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
*/
bool efivarfs_valid_name(const char *str, int len)
{
- static const char dashes[EFI_VARIABLE_GUID_LEN] = {
- [8] = 1, [13] = 1, [18] = 1, [23] = 1
- };
const char *s = str + len - EFI_VARIABLE_GUID_LEN;
- int i;
/*
* We need a GUID, plus at least one letter for the variable name,
@@ -68,37 +65,7 @@ bool efivarfs_valid_name(const char *str, int len)
*
* 12345678-1234-1234-1234-123456789abc
*/
- for (i = 0; i < EFI_VARIABLE_GUID_LEN; i++) {
- if (dashes[i]) {
- if (*s++ != '-')
- return false;
- } else {
- if (!isxdigit(*s++))
- return false;
- }
- }
-
- return true;
-}
-
-static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
-{
- guid->b[0] = hex_to_bin(str[6]) << 4 | hex_to_bin(str[7]);
- guid->b[1] = hex_to_bin(str[4]) << 4 | hex_to_bin(str[5]);
- guid->b[2] = hex_to_bin(str[2]) << 4 | hex_to_bin(str[3]);
- guid->b[3] = hex_to_bin(str[0]) << 4 | hex_to_bin(str[1]);
- guid->b[4] = hex_to_bin(str[11]) << 4 | hex_to_bin(str[12]);
- guid->b[5] = hex_to_bin(str[9]) << 4 | hex_to_bin(str[10]);
- guid->b[6] = hex_to_bin(str[16]) << 4 | hex_to_bin(str[17]);
- guid->b[7] = hex_to_bin(str[14]) << 4 | hex_to_bin(str[15]);
- guid->b[8] = hex_to_bin(str[19]) << 4 | hex_to_bin(str[20]);
- guid->b[9] = hex_to_bin(str[21]) << 4 | hex_to_bin(str[22]);
- guid->b[10] = hex_to_bin(str[24]) << 4 | hex_to_bin(str[25]);
- guid->b[11] = hex_to_bin(str[26]) << 4 | hex_to_bin(str[27]);
- guid->b[12] = hex_to_bin(str[28]) << 4 | hex_to_bin(str[29]);
- guid->b[13] = hex_to_bin(str[30]) << 4 | hex_to_bin(str[31]);
- guid->b[14] = hex_to_bin(str[32]) << 4 | hex_to_bin(str[33]);
- guid->b[15] = hex_to_bin(str[34]) << 4 | hex_to_bin(str[35]);
+ return uuid_is_valid(s);
}
static int efivarfs_create(struct inode *dir, struct dentry *dentry,
@@ -119,8 +86,7 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
/* length of the variable name itself: remove GUID and separator */
namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
- efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
- &var->var.VendorGuid);
+ uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
if (efivar_variable_is_removable(var->var.VendorGuid,
dentry->d_name.name, namelen))
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 553c5d2db4a4..9cb54a38832d 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -216,8 +216,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
INIT_LIST_HEAD(&efivarfs_list);
- err = efivar_init(efivarfs_callback, (void *)sb, false,
- true, &efivarfs_list);
+ err = efivar_init(efivarfs_callback, (void *)sb, true, &efivarfs_list);
if (err)
__efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL);
diff --git a/fs/efs/dir.c b/fs/efs/dir.c
index ce63b24f7c3e..a7be96e5f1cb 100644
--- a/fs/efs/dir.c
+++ b/fs/efs/dir.c
@@ -12,7 +12,7 @@ static int efs_readdir(struct file *, struct dir_context *);
const struct file_operations efs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = efs_readdir,
+ .iterate_shared = efs_readdir,
};
const struct inode_operations efs_dir_inode_operations = {
@@ -100,4 +100,3 @@ static int efs_readdir(struct file *file, struct dir_context *ctx)
ctx->pos = (block << EFS_DIRBSIZE_BITS) | slot;
return 0;
}
-
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index 40ba9cc41bf7..d34a40edcdb2 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -113,7 +113,7 @@ struct dentry *efs_get_parent(struct dentry *child)
ino = efs_find_entry(d_inode(child), "..", 2);
if (ino)
- parent = d_obtain_alias(efs_iget(d_inode(child)->i_sb, ino));
+ parent = d_obtain_alias(efs_iget(child->d_sb, ino));
return parent;
}
diff --git a/fs/efs/super.c b/fs/efs/super.c
index cb68dac4f9d3..368f7dd21c61 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -275,7 +275,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
if (!bh) {
pr_err("cannot read volume header\n");
- return -EINVAL;
+ return -EIO;
}
/*
@@ -293,7 +293,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
bh = sb_bread(s, sb->fs_start + EFS_SUPER);
if (!bh) {
pr_err("cannot read superblock\n");
- return -EINVAL;
+ return -EIO;
}
if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8a74a2a52e0f..10db91218933 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1583,15 +1583,15 @@ static int ep_send_events(struct eventpoll *ep,
return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false);
}
-static inline struct timespec ep_set_mstimeout(long ms)
+static inline struct timespec64 ep_set_mstimeout(long ms)
{
- struct timespec now, ts = {
+ struct timespec64 now, ts = {
.tv_sec = ms / MSEC_PER_SEC,
.tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
};
- ktime_get_ts(&now);
- return timespec_add_safe(now, ts);
+ ktime_get_ts64(&now);
+ return timespec64_add_safe(now, ts);
}
/**
@@ -1621,11 +1621,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
ktime_t expires, *to = NULL;
if (timeout > 0) {
- struct timespec end_time = ep_set_mstimeout(timeout);
+ struct timespec64 end_time = ep_set_mstimeout(timeout);
slack = select_estimate_accuracy(&end_time);
to = &expires;
- *to = timespec_to_ktime(end_time);
+ *to = timespec64_to_ktime(end_time);
} else if (timeout == 0) {
/*
* Avoid the unnecessary trip to the wait queue loop, if the
diff --git a/fs/exec.c b/fs/exec.c
index c4010b8207a1..887c1c955df8 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -243,10 +243,6 @@ static void put_arg_page(struct page *page)
put_page(page);
}
-static void free_arg_page(struct linux_binprm *bprm, int i)
-{
-}
-
static void free_arg_pages(struct linux_binprm *bprm)
{
}
@@ -267,7 +263,10 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
if (!vma)
return -ENOMEM;
- down_write(&mm->mmap_sem);
+ if (down_write_killable(&mm->mmap_sem)) {
+ err = -EINTR;
+ goto err_free;
+ }
vma->vm_mm = mm;
/*
@@ -294,6 +293,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
return 0;
err:
up_write(&mm->mmap_sem);
+err_free:
bprm->vma = NULL;
kmem_cache_free(vm_area_cachep, vma);
return err;
@@ -700,7 +700,9 @@ int setup_arg_pages(struct linux_binprm *bprm,
bprm->loader -= stack_shift;
bprm->exec -= stack_shift;
- down_write(&mm->mmap_sem);
+ if (down_write_killable(&mm->mmap_sem))
+ return -EINTR;
+
vm_flags = VM_STACK_FLAGS;
/*
@@ -850,15 +852,25 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
if (ret)
return ret;
+ ret = deny_write_access(file);
+ if (ret)
+ return ret;
+
i_size = i_size_read(file_inode(file));
- if (max_size > 0 && i_size > max_size)
- return -EFBIG;
- if (i_size <= 0)
- return -EINVAL;
+ if (max_size > 0 && i_size > max_size) {
+ ret = -EFBIG;
+ goto out;
+ }
+ if (i_size <= 0) {
+ ret = -EINVAL;
+ goto out;
+ }
*buf = vmalloc(i_size);
- if (!*buf)
- return -ENOMEM;
+ if (!*buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
pos = 0;
while (pos < i_size) {
@@ -876,18 +888,21 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
if (pos != i_size) {
ret = -EIO;
- goto out;
+ goto out_free;
}
ret = security_kernel_post_read_file(file, *buf, i_size, id);
if (!ret)
*size = pos;
-out:
+out_free:
if (ret < 0) {
vfree(*buf);
*buf = NULL;
}
+
+out:
+ allow_write_access(file);
return ret;
}
EXPORT_SYMBOL_GPL(kernel_read_file);
@@ -1387,7 +1402,12 @@ static void bprm_fill_uid(struct linux_binprm *bprm)
kuid_t uid;
kgid_t gid;
- /* clear any previous set[ug]id data from a previous binary */
+ /*
+ * Since this can be called multiple times (via prepare_binprm),
+ * we must clear any previous work done when setting set[ug]id
+ * bits from any earlier bprm->file uses (for example when run
+ * first for a setuid script then again for its interpreter).
+ */
bprm->cred->euid = current_euid();
bprm->cred->egid = current_egid();
@@ -1481,9 +1501,6 @@ int remove_arg_zero(struct linux_binprm *bprm)
kunmap_atomic(kaddr);
put_arg_page(page);
-
- if (offset == PAGE_SIZE)
- free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1);
} while (offset == PAGE_SIZE);
bprm->p++;
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 547b93cbea63..f69a1b5826a5 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -79,7 +79,7 @@ static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len)
return err;
}
-static void exofs_check_page(struct page *page)
+static bool exofs_check_page(struct page *page)
{
struct inode *dir = page->mapping->host;
unsigned chunk_size = exofs_chunk_size(dir);
@@ -114,7 +114,7 @@ static void exofs_check_page(struct page *page)
goto Eend;
out:
SetPageChecked(page);
- return;
+ return true;
Ebadsize:
EXOFS_ERR("ERROR [exofs_check_page]: "
@@ -150,8 +150,8 @@ Eend:
dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
_LLU(le64_to_cpu(p->inode_no)));
fail:
- SetPageChecked(page);
SetPageError(page);
+ return false;
}
static struct page *exofs_get_page(struct inode *dir, unsigned long n)
@@ -161,10 +161,10 @@ static struct page *exofs_get_page(struct inode *dir, unsigned long n)
if (!IS_ERR(page)) {
kmap(page);
- if (!PageChecked(page))
- exofs_check_page(page);
- if (PageError(page))
- goto fail;
+ if (unlikely(!PageChecked(page))) {
+ if (PageError(page) || !exofs_check_page(page))
+ goto fail;
+ }
}
return page;
@@ -657,5 +657,5 @@ not_empty:
const struct file_operations exofs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = exofs_readdir,
+ .iterate_shared = exofs_readdir,
};
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 49e1bd00b4ec..9dc4c6dbf3c9 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -960,8 +960,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset,
/* TODO: Should be easy enough to do proprly */
-static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
return 0;
}
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 6658a50530a0..1076a4233b39 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -122,7 +122,7 @@ static int parse_options(char *options, struct exofs_mountopt *opts)
if (match_int(&args[0], &option))
return -EINVAL;
if (option <= 0) {
- EXOFS_ERR("Timout must be > 0");
+ EXOFS_ERR("Timeout must be > 0");
return -EINVAL;
}
opts->timeout = option * HZ;
@@ -958,7 +958,7 @@ static struct dentry *exofs_get_parent(struct dentry *child)
if (!ino)
return ERR_PTR(-ESTALE);
- return d_obtain_alias(exofs_iget(d_inode(child)->i_sb, ino));
+ return d_obtain_alias(exofs_iget(child->d_sb, ino));
}
static struct inode *exofs_nfs_get_inode(struct super_block *sb,
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index c46f1a190b8d..207ba8d627ca 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -143,14 +143,18 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
if (err)
goto out_err;
dprintk("%s: found name: %s\n", __func__, nbuf);
- inode_lock(parent->d_inode);
- tmp = lookup_one_len(nbuf, parent, strlen(nbuf));
- inode_unlock(parent->d_inode);
+ tmp = lookup_one_len_unlocked(nbuf, parent, strlen(nbuf));
if (IS_ERR(tmp)) {
dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
goto out_err;
}
if (tmp != dentry) {
+ /*
+ * Somebody has renamed it since exportfs_get_name();
+ * great, since it could've only been renamed if it
+ * got looked up and thus connected, and it would
+ * remain connected afterwards. We are done.
+ */
dput(tmp);
goto out_reconnected;
}
@@ -308,7 +312,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
goto out;
error = -EINVAL;
- if (!file->f_op->iterate)
+ if (!file->f_op->iterate && !file->f_op->iterate_shared)
goto out_close;
buffer.sequence = 0;
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 27695e6f4e46..42f1d1814083 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -172,9 +172,6 @@ ext2_get_acl(struct inode *inode, int type)
acl = ERR_PTR(retval);
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 7ff6fcfa685d..19efd1197fa5 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -110,7 +110,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
return err;
}
-static void ext2_check_page(struct page *page, int quiet)
+static bool ext2_check_page(struct page *page, int quiet)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
@@ -148,7 +148,7 @@ static void ext2_check_page(struct page *page, int quiet)
goto Eend;
out:
SetPageChecked(page);
- return;
+ return true;
/* Too bad, we had an error */
@@ -190,8 +190,8 @@ Eend:
(unsigned long) le32_to_cpu(p->inode));
}
fail:
- SetPageChecked(page);
SetPageError(page);
+ return false;
}
static struct page * ext2_get_page(struct inode *dir, unsigned long n,
@@ -201,10 +201,10 @@ static struct page * ext2_get_page(struct inode *dir, unsigned long n,
struct page *page = read_mapping_page(mapping, n, NULL);
if (!IS_ERR(page)) {
kmap(page);
- if (!PageChecked(page))
- ext2_check_page(page, quiet);
- if (PageError(page))
- goto fail;
+ if (unlikely(!PageChecked(page))) {
+ if (PageError(page) || !ext2_check_page(page, quiet))
+ goto fail;
+ }
}
return page;
@@ -716,7 +716,7 @@ not_empty:
const struct file_operations ext2_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = ext2_readdir,
+ .iterate_shared = ext2_readdir,
.unlocked_ioctl = ext2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext2_compat_ioctl,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 6bd58e6ff038..b675610391b8 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -854,20 +854,20 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
}
static ssize_t
-ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
ssize_t ret;
if (IS_DAX(inode))
- ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL,
+ ret = dax_do_io(iocb, inode, iter, ext2_get_block, NULL,
DIO_LOCKING);
else
- ret = blockdev_direct_IO(iocb, inode, iter, offset,
- ext2_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
if (ret < 0 && iov_iter_rw(iter) == WRITE)
ext2_write_failed(mapping, offset + count);
return ret;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index d34843925b23..d446203127fc 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -82,7 +82,7 @@ struct dentry *ext2_get_parent(struct dentry *child)
unsigned long ino = ext2_inode_by_name(d_inode(child), &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
- return d_obtain_alias(ext2_iget(d_inode(child)->i_sb, ino));
+ return d_obtain_alias(ext2_iget(child->d_sb, ino));
}
/*
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index ba97f243b050..7fd3b867ce65 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -9,10 +9,10 @@
static int
ext2_xattr_security_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name,
buffer, size);
}
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 2c94d1930626..0f85705ff519 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -16,10 +16,10 @@ ext2_xattr_trusted_list(struct dentry *dentry)
static int
ext2_xattr_trusted_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_get(inode, EXT2_XATTR_INDEX_TRUSTED, name,
buffer, size);
}
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index 72a2a96d677f..1fafd27037cc 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -18,12 +18,12 @@ ext2_xattr_user_list(struct dentry *dentry)
static int
ext2_xattr_user_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- if (!test_opt(dentry->d_sb, XATTR_USER))
+ if (!test_opt(inode->i_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER,
+ return ext2_xattr_get(inode, EXT2_XATTR_INDEX_USER,
name, buffer, size);
}
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 69b1e73026a5..c6601a476c02 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -172,9 +172,6 @@ ext4_get_acl(struct inode *inode, int type)
acl = ERR_PTR(retval);
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 4173bfe21114..68323e3da3fa 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -271,7 +271,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
ctx->pos += ext4_rec_len_from_disk(de->rec_len,
sb->s_blocksize);
}
- if ((ctx->pos < inode->i_size) && !dir_relax(inode))
+ if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode))
goto done;
brelse(bh);
bh = NULL;
@@ -649,7 +649,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
const struct file_operations ext4_dir_operations = {
.llseek = ext4_dir_llseek,
.read = generic_read_dir,
- .iterate = ext4_readdir,
+ .iterate_shared = ext4_readdir,
.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 37e28082885a..d478110c32a6 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -169,13 +169,8 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = __generic_file_write_iter(iocb, from);
inode_unlock(inode);
- if (ret > 0) {
- ssize_t err;
-
- err = generic_write_sync(file, iocb->ki_pos - ret, ret);
- if (err < 0)
- ret = err;
- }
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
if (o_direct)
blk_finish_plug(&plug);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f9ab1e8cc416..f7140ca66e3b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3327,13 +3327,13 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
* if the machine crashes during the write.
*
*/
-static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
ssize_t ret;
+ loff_t offset = iocb->ki_pos;
size_t count = iov_iter_count(iter);
int overwrite = 0;
get_block_t *get_block_func = NULL;
@@ -3424,11 +3424,11 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter,
BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
#endif
if (IS_DAX(inode)) {
- ret = dax_do_io(iocb, inode, iter, offset, get_block_func,
+ ret = dax_do_io(iocb, inode, iter, get_block_func,
ext4_end_io_dio, dio_flags);
} else
ret = __blockdev_direct_IO(iocb, inode,
- inode->i_sb->s_bdev, iter, offset,
+ inode->i_sb->s_bdev, iter,
get_block_func,
ext4_end_io_dio, NULL, dio_flags);
@@ -3495,8 +3495,7 @@ out:
return ret;
}
-static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
{
int unlocked = 0;
struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -3517,11 +3516,11 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter,
unlocked = 1;
}
if (IS_DAX(inode)) {
- ret = dax_do_io(iocb, inode, iter, offset, ext4_dio_get_block,
+ ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block,
NULL, unlocked ? 0 : DIO_LOCKING);
} else {
ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, offset, ext4_dio_get_block,
+ iter, ext4_dio_get_block,
NULL, NULL,
unlocked ? 0 : DIO_LOCKING);
}
@@ -3530,12 +3529,12 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter,
return ret;
}
-static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
ssize_t ret;
#ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -3555,9 +3554,9 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
if (iov_iter_rw(iter) == READ)
- ret = ext4_direct_IO_read(iocb, iter, offset);
+ ret = ext4_direct_IO_read(iocb, iter);
else
- ret = ext4_direct_IO_write(iocb, iter, offset);
+ ret = ext4_direct_IO_write(iocb, iter);
trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
return ret;
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 0acf8cacb2be..28cc412852af 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -13,8 +13,8 @@
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/file.h>
-#include <linux/random.h>
#include <linux/quotaops.h>
+#include <linux/uuid.h>
#include <asm/uaccess.h>
#include "ext4_jbd2.h"
#include "ext4.h"
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 672c99a2051b..ec4c39952e84 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1643,13 +1643,13 @@ struct dentry *ext4_get_parent(struct dentry *child)
ino = le32_to_cpu(de->inode);
brelse(bh);
- if (!ext4_valid_inum(d_inode(child)->i_sb, ino)) {
+ if (!ext4_valid_inum(child->d_sb, ino)) {
EXT4_ERROR_INODE(d_inode(child),
"bad parent inode number: %u", ino);
return ERR_PTR(-EFSCORRUPTED);
}
- return d_obtain_alias(ext4_iget_normal(d_inode(child)->i_sb, ino));
+ return d_obtain_alias(ext4_iget_normal(child->d_sb, ino));
}
/*
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 3e81bdca071a..123a7d010efe 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -13,10 +13,10 @@
static int
ext4_xattr_security_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY,
name, buffer, size);
}
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index 2a3c6f9b8cb8..60652fa24cbc 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -20,10 +20,10 @@ ext4_xattr_trusted_list(struct dentry *dentry)
static int
ext4_xattr_trusted_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, void *buffer,
- size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED,
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED,
name, buffer, size);
}
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index d152f431e432..17a446ffecd3 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -19,12 +19,12 @@ ext4_xattr_user_list(struct dentry *dentry)
static int
ext4_xattr_user_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- if (!test_opt(dentry->d_sb, XATTR_USER))
+ if (!test_opt(inode->i_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER,
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER,
name, buffer, size);
}
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 1f8982a957f1..378c221d68a9 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -94,3 +94,11 @@ config F2FS_IO_TRACE
information and block IO patterns in the filesystem level.
If unsure, say N.
+
+config F2FS_FAULT_INJECTION
+ bool "F2FS fault injection facility"
+ depends on F2FS_FS
+ help
+ Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
+
+ If unsure, say N.
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index c8f25f7241f0..a31c7e859af6 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -115,7 +115,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
struct f2fs_acl_entry *entry;
int i;
- f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
+ f2fs_acl = f2fs_kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
sizeof(struct f2fs_acl_entry), GFP_NOFS);
if (!f2fs_acl)
return ERR_PTR(-ENOMEM);
@@ -175,7 +175,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
if (retval > 0) {
- value = kmalloc(retval, GFP_F2FS_ZERO);
+ value = f2fs_kmalloc(retval, GFP_F2FS_ZERO);
if (!value)
return ERR_PTR(-ENOMEM);
retval = f2fs_getxattr(inode, name_index, "", value,
@@ -190,9 +190,6 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
acl = ERR_PTR(retval);
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 0955312e5ca0..389160049993 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -26,6 +26,14 @@
static struct kmem_cache *ino_entry_slab;
struct kmem_cache *inode_entry_slab;
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
+{
+ set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+ sbi->sb->s_flags |= MS_RDONLY;
+ if (!end_io)
+ f2fs_flush_merged_bios(sbi);
+}
+
/*
* We guarantee no failure on the returned page.
*/
@@ -34,7 +42,7 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
struct address_space *mapping = META_MAPPING(sbi);
struct page *page = NULL;
repeat:
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
@@ -64,7 +72,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
if (unlikely(!is_meta))
fio.rw &= ~REQ_META;
repeat:
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
@@ -91,7 +99,7 @@ repeat:
* meta page.
*/
if (unlikely(!PageUptodate(page)))
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
out:
return page;
}
@@ -186,7 +194,8 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
BUG();
}
- page = grab_cache_page(META_MAPPING(sbi), fio.new_blkaddr);
+ page = f2fs_grab_cache_page(META_MAPPING(sbi),
+ fio.new_blkaddr, false);
if (!page)
continue;
if (PageUptodate(page)) {
@@ -211,7 +220,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
bool readahead = false;
page = find_get_page(META_MAPPING(sbi), index);
- if (!page || (page && !PageUptodate(page)))
+ if (!page || !PageUptodate(page))
readahead = true;
f2fs_put_page(page, 0);
@@ -448,12 +457,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
return e ? true : false;
}
-void release_ino_entry(struct f2fs_sb_info *sbi)
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
- for (i = APPEND_INO; i <= UPDATE_INO; i++) {
+ for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
struct inode_management *im = &sbi->im[i];
spin_lock(&im->ino_lock);
@@ -473,6 +482,13 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
int err = 0;
spin_lock(&im->ino_lock);
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_ORPHAN)) {
+ spin_unlock(&im->ino_lock);
+ return -ENOSPC;
+ }
+#endif
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
@@ -777,43 +793,32 @@ void update_dirty_page(struct inode *inode, struct page *page)
!S_ISLNK(inode->i_mode))
return;
- spin_lock(&sbi->inode_lock[type]);
- __add_dirty_inode(inode, type);
- inode_inc_dirty_pages(inode);
- spin_unlock(&sbi->inode_lock[type]);
+ if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH)) {
+ spin_lock(&sbi->inode_lock[type]);
+ __add_dirty_inode(inode, type);
+ spin_unlock(&sbi->inode_lock[type]);
+ }
+ inode_inc_dirty_pages(inode);
SetPagePrivate(page);
f2fs_trace_pid(page);
}
-void add_dirty_dir_inode(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
- spin_lock(&sbi->inode_lock[DIR_INODE]);
- __add_dirty_inode(inode, DIR_INODE);
- spin_unlock(&sbi->inode_lock[DIR_INODE]);
-}
-
void remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
return;
+ if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
+ return;
+
spin_lock(&sbi->inode_lock[type]);
__remove_dirty_inode(inode, type);
spin_unlock(&sbi->inode_lock[type]);
-
- /* Only from the recovery routine */
- if (is_inode_flag_set(fi, FI_DELAY_IPUT)) {
- clear_inode_flag(fi, FI_DELAY_IPUT);
- iput(inode);
- }
}
int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
@@ -892,7 +897,7 @@ retry_flush_nodes:
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
- err = sync_node_pages(sbi, 0, &wbc);
+ err = sync_node_pages(sbi, &wbc);
if (err) {
f2fs_unlock_all(sbi);
goto out;
@@ -917,7 +922,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (!get_pages(sbi, F2FS_WRITEBACK))
+ if (!atomic_read(&sbi->nr_wb_bios))
break;
io_schedule_timeout(5*HZ);
@@ -1082,7 +1087,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
- sbi->alloc_valid_block_count = 0;
+ percpu_counter_set(&sbi->alloc_valid_block_count, 0);
/* Here, we only have one bio having CP pack */
sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
@@ -1098,7 +1103,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
discard_blk);
- release_ino_entry(sbi);
+ release_ino_entry(sbi, false);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5dafb9cef12e..9a8bbc1fb1fa 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -68,13 +68,12 @@ static void f2fs_write_end_io(struct bio *bio)
if (unlikely(bio->bi_error)) {
set_bit(AS_EIO, &page->mapping->flags);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, true);
}
end_page_writeback(page);
- dec_page_count(sbi, F2FS_WRITEBACK);
}
-
- if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
+ if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+ wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
@@ -98,6 +97,14 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
return bio;
}
+static inline void __submit_bio(struct f2fs_sb_info *sbi, int rw,
+ struct bio *bio)
+{
+ if (!is_read_io(rw))
+ atomic_inc(&sbi->nr_wb_bios);
+ submit_bio(rw, bio);
+}
+
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
@@ -110,7 +117,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
else
trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
- submit_bio(fio->rw, io->bio);
+ __submit_bio(io->sbi, fio->rw, io->bio);
io->bio = NULL;
}
@@ -228,7 +235,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
return -EFAULT;
}
- submit_bio(fio->rw, bio);
+ __submit_bio(fio->sbi, fio->rw, bio);
return 0;
}
@@ -248,9 +255,6 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
down_write(&io->io_rwsem);
- if (!is_read)
- inc_page_count(sbi, F2FS_WRITEBACK);
-
if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
io->fio.rw != fio->rw))
__submit_merged_bio(io);
@@ -278,6 +282,16 @@ alloc_new:
trace_f2fs_submit_page_mbio(fio->page, fio);
}
+static void __set_data_blkaddr(struct dnode_of_data *dn)
+{
+ struct f2fs_node *rn = F2FS_NODE(dn->node_page);
+ __le32 *addr_array;
+
+ /* Get physical address of data block */
+ addr_array = blkaddr_in_node(rn);
+ addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
+}
+
/*
* Lock ordering for the change of data block address:
* ->data_page
@@ -286,19 +300,9 @@ alloc_new:
*/
void set_data_blkaddr(struct dnode_of_data *dn)
{
- struct f2fs_node *rn;
- __le32 *addr_array;
- struct page *node_page = dn->node_page;
- unsigned int ofs_in_node = dn->ofs_in_node;
-
- f2fs_wait_on_page_writeback(node_page, NODE, true);
-
- rn = F2FS_NODE(node_page);
-
- /* Get physical address of data block */
- addr_array = blkaddr_in_node(rn);
- addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
- if (set_page_dirty(node_page))
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+ __set_data_blkaddr(dn);
+ if (set_page_dirty(dn->node_page))
dn->node_changed = true;
}
@@ -309,24 +313,53 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
f2fs_update_extent_cache(dn);
}
-int reserve_new_block(struct dnode_of_data *dn)
+/* dn->ofs_in_node will be returned with up-to-date last block pointer */
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ if (!count)
+ return 0;
+
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+ if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
return -ENOSPC;
- trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+ trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
+ dn->ofs_in_node, count);
+
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+
+ for (; count > 0; dn->ofs_in_node++) {
+ block_t blkaddr =
+ datablock_addr(dn->node_page, dn->ofs_in_node);
+ if (blkaddr == NULL_ADDR) {
+ dn->data_blkaddr = NEW_ADDR;
+ __set_data_blkaddr(dn);
+ count--;
+ }
+ }
+
+ if (set_page_dirty(dn->node_page))
+ dn->node_changed = true;
- dn->data_blkaddr = NEW_ADDR;
- set_data_blkaddr(dn);
mark_inode_dirty(dn->inode);
sync_inode_page(dn);
return 0;
}
+/* Should keep dn->ofs_in_node unchanged */
+int reserve_new_block(struct dnode_of_data *dn)
+{
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ int ret;
+
+ ret = reserve_new_blocks(dn, 1);
+ dn->ofs_in_node = ofs_in_node;
+ return ret;
+}
+
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
@@ -545,6 +578,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
struct node_info ni;
int seg = CURSEG_WARM_DATA;
pgoff_t fofs;
+ blkcnt_t count = 1;
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
@@ -553,7 +587,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
if (dn->data_blkaddr == NEW_ADDR)
goto alloc;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+ if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
return -ENOSPC;
alloc:
@@ -582,8 +616,8 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
struct f2fs_map_blocks map;
ssize_t ret = 0;
- map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
- map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+ map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
+ map.m_len = F2FS_BYTES_TO_BLK(iov_iter_count(from));
map.m_next_pgofs = NULL;
if (f2fs_encrypted_inode(inode))
@@ -621,8 +655,10 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
struct dnode_of_data dn;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
- pgoff_t pgofs, end_offset;
+ pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
+ unsigned int ofs_in_node, last_ofs_in_node;
+ blkcnt_t prealloc;
struct extent_info ei;
bool allocated = false;
block_t blkaddr;
@@ -632,6 +668,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
+ end = pgofs + maxblocks;
if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
map->m_pblk = ei.blk + pgofs - ei.fofs;
@@ -648,6 +685,8 @@ next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
+ if (flag == F2FS_GET_BLOCK_BMAP)
+ map->m_pblk = 0;
if (err == -ENOENT) {
err = 0;
if (map->m_next_pgofs)
@@ -657,6 +696,8 @@ next_dnode:
goto unlock_out;
}
+ prealloc = 0;
+ ofs_in_node = dn.ofs_in_node;
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
@@ -669,31 +710,41 @@ next_block:
goto sync_out;
}
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
- if (blkaddr == NULL_ADDR)
- err = reserve_new_block(&dn);
+ if (blkaddr == NULL_ADDR) {
+ prealloc++;
+ last_ofs_in_node = dn.ofs_in_node;
+ }
} else {
err = __allocate_data_block(&dn);
+ if (!err) {
+ set_inode_flag(F2FS_I(inode),
+ FI_APPEND_WRITE);
+ allocated = true;
+ }
}
if (err)
goto sync_out;
- allocated = true;
map->m_flags = F2FS_MAP_NEW;
blkaddr = dn.data_blkaddr;
} else {
+ if (flag == F2FS_GET_BLOCK_BMAP) {
+ map->m_pblk = 0;
+ goto sync_out;
+ }
if (flag == F2FS_GET_BLOCK_FIEMAP &&
blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
}
if (flag != F2FS_GET_BLOCK_FIEMAP ||
- blkaddr != NEW_ADDR) {
- if (flag == F2FS_GET_BLOCK_BMAP)
- err = -ENOENT;
+ blkaddr != NEW_ADDR)
goto sync_out;
- }
}
}
+ if (flag == F2FS_GET_BLOCK_PRE_AIO)
+ goto skip;
+
if (map->m_len == 0) {
/* preallocated unwritten block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
@@ -705,32 +756,49 @@ next_block:
} else if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
- flag == F2FS_GET_BLOCK_PRE_DIO ||
- flag == F2FS_GET_BLOCK_PRE_AIO) {
+ flag == F2FS_GET_BLOCK_PRE_DIO) {
ofs++;
map->m_len++;
} else {
goto sync_out;
}
+skip:
dn.ofs_in_node++;
pgofs++;
- if (map->m_len < maxblocks) {
- if (dn.ofs_in_node < end_offset)
- goto next_block;
+ /* preallocate blocks in batch for one dnode page */
+ if (flag == F2FS_GET_BLOCK_PRE_AIO &&
+ (pgofs == end || dn.ofs_in_node == end_offset)) {
- if (allocated)
- sync_inode_page(&dn);
- f2fs_put_dnode(&dn);
+ dn.ofs_in_node = ofs_in_node;
+ err = reserve_new_blocks(&dn, prealloc);
+ if (err)
+ goto sync_out;
- if (create) {
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, allocated);
+ map->m_len += dn.ofs_in_node - ofs_in_node;
+ if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
+ err = -ENOSPC;
+ goto sync_out;
}
- allocated = false;
- goto next_dnode;
+ dn.ofs_in_node = end_offset;
+ }
+
+ if (pgofs >= end)
+ goto sync_out;
+ else if (dn.ofs_in_node < end_offset)
+ goto next_block;
+
+ if (allocated)
+ sync_inode_page(&dn);
+ f2fs_put_dnode(&dn);
+
+ if (create) {
+ f2fs_unlock_op(sbi);
+ f2fs_balance_fs(sbi, allocated);
}
+ allocated = false;
+ goto next_dnode;
sync_out:
if (allocated)
@@ -983,7 +1051,7 @@ got_it:
*/
if (bio && (last_block_in_bio != block_nr - 1)) {
submit_and_realloc:
- submit_bio(READ, bio);
+ __submit_bio(F2FS_I_SB(inode), READ, bio);
bio = NULL;
}
if (bio == NULL) {
@@ -1026,7 +1094,7 @@ set_error_page:
goto next_page;
confused:
if (bio) {
- submit_bio(READ, bio);
+ __submit_bio(F2FS_I_SB(inode), READ, bio);
bio = NULL;
}
unlock_page(page);
@@ -1036,7 +1104,7 @@ next_page:
}
BUG_ON(pages && !list_empty(pages));
if (bio)
- submit_bio(READ, bio);
+ __submit_bio(F2FS_I_SB(inode), READ, bio);
return 0;
}
@@ -1177,8 +1245,10 @@ write:
goto redirty_out;
if (f2fs_is_drop_cache(inode))
goto out;
- if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
- available_free_memory(sbi, BASE_CHECK))
+ /* we should not write 0'th page having journal header */
+ if (f2fs_is_volatile_file(inode) && (!page->index ||
+ (!wbc->for_reclaim &&
+ available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
/* Dentry blocks are controlled by checkpoint */
@@ -1480,7 +1550,8 @@ restart:
if (pos + len <= MAX_INLINE_DATA) {
read_inline_data(page, ipage);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
- set_inline_node(ipage);
+ if (inode->i_nlink)
+ set_inline_node(ipage);
} else {
err = f2fs_convert_inline_page(&dn, page);
if (err)
@@ -1496,7 +1567,7 @@ restart:
} else {
/* hole case */
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
- if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
+ if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
f2fs_lock_op(sbi);
locked = true;
@@ -1665,12 +1736,12 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
return 0;
}
-static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
int err;
err = check_direct_IO(inode, iter, offset);
@@ -1682,9 +1753,13 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
- if (err < 0 && iov_iter_rw(iter) == WRITE)
- f2fs_write_failed(mapping, offset + count);
+ err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
+ if (iov_iter_rw(iter) == WRITE) {
+ if (err > 0)
+ set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+ else if (err < 0)
+ f2fs_write_failed(mapping, offset + count);
+ }
trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);
@@ -1714,6 +1789,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
if (IS_ATOMIC_WRITTEN_PAGE(page))
return;
+ set_page_private(page, 0);
ClearPagePrivate(page);
}
@@ -1727,6 +1803,7 @@ int f2fs_release_page(struct page *page, gfp_t wait)
if (IS_ATOMIC_WRITTEN_PAGE(page))
return 0;
+ set_page_private(page, 0);
ClearPagePrivate(page);
return 1;
}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index f4a61a5ff79f..d89a425055d0 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -48,7 +48,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
- si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
+ si->wb_bios = atomic_read(&sbi->nr_wb_bios);
si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
si->rsvd_segs = reserved_segments(sbi);
si->overp_segs = overprovision_segments(sbi);
@@ -58,6 +58,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->inline_xattr = atomic_read(&sbi->inline_xattr);
si->inline_inode = atomic_read(&sbi->inline_inode);
si->inline_dir = atomic_read(&sbi->inline_dir);
+ si->orphans = sbi->im[ORPHAN_INO].ino_num;
si->utilization = utilization(sbi);
si->free_segs = free_segments(sbi);
@@ -143,6 +144,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
si->base_mem += 2 * sizeof(struct f2fs_inode_info);
si->base_mem += sizeof(*sbi->ckpt);
+ si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE;
/* build sm */
si->base_mem += sizeof(struct f2fs_sm_info);
@@ -192,7 +194,7 @@ get_cache:
si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
sizeof(struct nat_entry_set);
si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
- for (i = 0; i <= UPDATE_INO; i++)
+ for (i = 0; i <= ORPHAN_INO; i++)
si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
si->cache_mem += atomic_read(&sbi->total_ext_tree) *
sizeof(struct extent_tree);
@@ -216,8 +218,9 @@ static int stat_show(struct seq_file *s, void *v)
list_for_each_entry(si, &f2fs_stat_list, stat_list) {
update_general_status(si->sbi);
- seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n",
- si->sbi->sb->s_bdev, i++);
+ seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n",
+ si->sbi->sb->s_bdev, i++,
+ f2fs_readonly(si->sbi->sb) ? "RO": "RW");
seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
si->sit_area_segs, si->nat_area_segs);
seq_printf(s, "[SSA: %d] [MAIN: %d",
@@ -237,6 +240,8 @@ static int stat_show(struct seq_file *s, void *v)
si->inline_inode);
seq_printf(s, " - Inline_dentry Inode: %u\n",
si->inline_dir);
+ seq_printf(s, " - Orphan Inode: %u\n",
+ si->orphans);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
@@ -295,15 +300,15 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n",
si->ext_tree, si->zombie_tree, si->ext_node);
seq_puts(s, "\nBalancing F2FS Async:\n");
- seq_printf(s, " - inmem: %4d, wb: %4d\n",
- si->inmem_pages, si->wb_pages);
- seq_printf(s, " - nodes: %4d in %4d\n",
+ seq_printf(s, " - inmem: %4lld, wb_bios: %4d\n",
+ si->inmem_pages, si->wb_bios);
+ seq_printf(s, " - nodes: %4lld in %4d\n",
si->ndirty_node, si->node_pages);
- seq_printf(s, " - dents: %4d in dirs:%4d\n",
+ seq_printf(s, " - dents: %4lld in dirs:%4d\n",
si->ndirty_dent, si->ndirty_dirs);
- seq_printf(s, " - datas: %4d in files:%4d\n",
+ seq_printf(s, " - datas: %4lld in files:%4d\n",
si->ndirty_data, si->ndirty_files);
- seq_printf(s, " - meta: %4d in %4d\n",
+ seq_printf(s, " - meta: %4lld in %4d\n",
si->ndirty_meta, si->meta_pages);
seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n",
si->dirty_nats, si->nats, si->dirty_sits, si->sits);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index af819571bce7..f9313f684540 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
[F2FS_FT_SYMLINK] = DT_LNK,
};
-#define S_SHIFT 12
static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+ if (de->file_type < F2FS_FT_MAX)
+ return f2fs_filetype_table[de->file_type];
+ return DT_UNKNOWN;
+}
+
static unsigned long dir_block_index(unsigned int level,
int dir_level, unsigned int idx)
{
@@ -95,11 +101,6 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
else
kunmap(dentry_page);
- /*
- * For the most part, it should be a bug when name_len is zero.
- * We stop here for figuring out where the bugs has occurred.
- */
- f2fs_bug_on(F2FS_P_SB(dentry_page), d.max < 0);
return de;
}
@@ -124,6 +125,11 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
de = &d->dentry[bit_pos];
+ if (unlikely(!de->name_len)) {
+ bit_pos++;
+ continue;
+ }
+
/* encrypted case */
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@@ -141,10 +147,6 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
*max_slots = max_len;
max_len = 0;
- /* remain bug on condition */
- if (unlikely(!de->name_len))
- d->max = -1;
-
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
}
@@ -389,9 +391,14 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
return page;
if (S_ISDIR(inode->i_mode)) {
+ /* in order to handle error case */
+ get_page(page);
err = make_empty_dir(inode, dir, page);
- if (err)
- goto error;
+ if (err) {
+ lock_page(page);
+ goto put_error;
+ }
+ put_page(page);
}
err = f2fs_init_acl(inode, dir, page, dpage);
@@ -435,13 +442,12 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
return page;
put_error:
- f2fs_put_page(page, 1);
-error:
- /* once the failed inode becomes a bad inode, i_mode is S_IFREG */
+ /* truncate empty dir pages */
truncate_inode_pages(&inode->i_data, 0);
- truncate_blocks(inode, 0, false);
- remove_dirty_inode(inode);
- remove_inode_page(inode);
+
+ clear_nlink(inode);
+ update_inode(inode, page);
+ f2fs_put_page(page, 1);
return ERR_PTR(err);
}
@@ -509,11 +515,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
}
}
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
@@ -526,28 +528,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct f2fs_dentry_block *dentry_blk = NULL;
struct f2fs_dentry_ptr d;
struct page *page = NULL;
- struct fscrypt_name fname;
- struct qstr new_name;
- int slots, err;
-
- err = fscrypt_setup_filename(dir, name, 0, &fname);
- if (err)
- return err;
-
- new_name.name = fname_name(&fname);
- new_name.len = fname_len(&fname);
-
- if (f2fs_has_inline_dentry(dir)) {
- err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
- if (!err || err != -EAGAIN)
- goto out;
- else
- err = 0;
- }
+ int slots, err = 0;
level = 0;
- slots = GET_DENTRY_SLOTS(new_name.len);
- dentry_hash = f2fs_dentry_hash(&new_name);
+ slots = GET_DENTRY_SLOTS(new_name->len);
+ dentry_hash = f2fs_dentry_hash(new_name);
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
@@ -556,10 +541,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
}
start:
- if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
- err = -ENOSPC;
- goto out;
- }
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_DIR_DEPTH))
+ return -ENOSPC;
+#endif
+ if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+ return -ENOSPC;
/* Increase the depth, if required */
if (level == current_depth)
@@ -573,10 +560,8 @@ start:
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
- if (IS_ERR(dentry_page)) {
- err = PTR_ERR(dentry_page);
- goto out;
- }
+ if (IS_ERR(dentry_page))
+ return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -596,7 +581,7 @@ add_dentry:
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, &new_name, NULL);
+ page = init_inode_metadata(inode, dir, new_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -606,7 +591,7 @@ add_dentry:
}
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
- f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+ f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
set_page_dirty(dentry_page);
@@ -628,7 +613,34 @@ fail:
}
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
-out:
+
+ return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct fscrypt_name fname;
+ struct qstr new_name;
+ int err;
+
+ err = fscrypt_setup_filename(dir, name, 0, &fname);
+ if (err)
+ return err;
+
+ new_name.name = fname_name(&fname);
+ new_name.len = fname_len(&fname);
+
+ err = -EAGAIN;
+ if (f2fs_has_inline_dentry(dir))
+ err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+ if (err == -EAGAIN)
+ err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode);
+
fscrypt_free_filename(&fname);
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
return err;
@@ -792,10 +804,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
continue;
}
- if (de->file_type < F2FS_FT_MAX)
- d_type = f2fs_filetype_table[de->file_type];
- else
- d_type = DT_UNKNOWN;
+ d_type = get_de_type(de);
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@@ -804,7 +813,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
int save_len = fstr->len;
int ret;
- de_name.name = kmalloc(de_name.len, GFP_NOFS);
+ de_name.name = f2fs_kmalloc(de_name.len, GFP_NOFS);
if (!de_name.name)
return false;
@@ -887,6 +896,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
+ err = 0;
out:
fscrypt_fname_free_buffer(&fstr);
return err;
@@ -902,7 +912,7 @@ static int f2fs_dir_open(struct inode *inode, struct file *filp)
const struct file_operations f2fs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = f2fs_readdir,
+ .iterate_shared = f2fs_readdir,
.fsync = f2fs_sync_file,
.open = f2fs_dir_open,
.unlocked_ioctl = f2fs_ioctl,
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index c859bb044728..5bfcdb9b69f2 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -196,8 +196,7 @@ bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
if (!i_ext || !i_ext->len)
return false;
- set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
- le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
+ get_extent_info(&ei, i_ext);
write_lock(&et->lock);
if (atomic_read(&et->node_cnt))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7a4558d17f36..916e7c238e3d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -37,6 +37,57 @@
} while (0)
#endif
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+enum {
+ FAULT_KMALLOC,
+ FAULT_PAGE_ALLOC,
+ FAULT_ALLOC_NID,
+ FAULT_ORPHAN,
+ FAULT_BLOCK,
+ FAULT_DIR_DEPTH,
+ FAULT_MAX,
+};
+
+struct f2fs_fault_info {
+ atomic_t inject_ops;
+ unsigned int inject_rate;
+ unsigned int inject_type;
+};
+
+extern struct f2fs_fault_info f2fs_fault;
+extern char *fault_name[FAULT_MAX];
+#define IS_FAULT_SET(type) (f2fs_fault.inject_type & (1 << (type)))
+
+static inline bool time_to_inject(int type)
+{
+ if (!f2fs_fault.inject_rate)
+ return false;
+ if (type == FAULT_KMALLOC && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_PAGE_ALLOC && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_ALLOC_NID && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_ORPHAN && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_BLOCK && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_DIR_DEPTH && !IS_FAULT_SET(type))
+ return false;
+
+ atomic_inc(&f2fs_fault.inject_ops);
+ if (atomic_read(&f2fs_fault.inject_ops) >= f2fs_fault.inject_rate) {
+ atomic_set(&f2fs_fault.inject_ops, 0);
+ printk("%sF2FS-fs : inject %s in %pF\n",
+ KERN_INFO,
+ fault_name[type],
+ __builtin_return_address(0));
+ return true;
+ }
+ return false;
+}
+#endif
+
/*
* For mount options
*/
@@ -56,6 +107,7 @@
#define F2FS_MOUNT_EXTENT_CACHE 0x00002000
#define F2FS_MOUNT_FORCE_FG_GC 0x00004000
#define F2FS_MOUNT_DATA_FLUSH 0x00008000
+#define F2FS_MOUNT_FAULT_INJECTION 0x00010000
#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -159,7 +211,6 @@ struct fsync_inode_entry {
struct inode *inode; /* vfs inode pointer */
block_t blkaddr; /* block address locating the last fsync */
block_t last_dentry; /* block address locating the last dentry */
- block_t last_inode; /* block address locating the last inode */
};
#define nats_in_cursum(jnl) (le16_to_cpu(jnl->n_nats))
@@ -385,7 +436,7 @@ struct f2fs_inode_info {
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
struct rw_semaphore i_sem; /* protect fi info */
- atomic_t dirty_pages; /* # of dirty pages */
+ struct percpu_counter dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
nid_t i_xattr_nid; /* node id that contains xattrs */
@@ -398,11 +449,11 @@ struct f2fs_inode_info {
};
static inline void get_extent_info(struct extent_info *ext,
- struct f2fs_extent i_ext)
+ struct f2fs_extent *i_ext)
{
- ext->fofs = le32_to_cpu(i_ext.fofs);
- ext->blk = le32_to_cpu(i_ext.blk);
- ext->len = le32_to_cpu(i_ext.len);
+ ext->fofs = le32_to_cpu(i_ext->fofs);
+ ext->blk = le32_to_cpu(i_ext->blk);
+ ext->len = le32_to_cpu(i_ext->len);
}
static inline void set_raw_extent(struct extent_info *ext,
@@ -599,7 +650,6 @@ struct f2fs_sm_info {
* dirty dentry blocks, dirty node blocks, and dirty meta blocks.
*/
enum count_type {
- F2FS_WRITEBACK,
F2FS_DIRTY_DENTS,
F2FS_DIRTY_DATA,
F2FS_DIRTY_NODES,
@@ -672,6 +722,7 @@ enum {
SBI_IS_CLOSE, /* specify unmounting */
SBI_NEED_FSCK, /* need fsck.f2fs to fix */
SBI_POR_DOING, /* recovery is doing or not */
+ SBI_NEED_SB_WRITE, /* need to recover superblock */
};
enum {
@@ -680,6 +731,10 @@ enum {
MAX_TIME,
};
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+#define F2FS_KEY_DESC_PREFIX "f2fs:"
+#define F2FS_KEY_DESC_PREFIX_SIZE 5
+#endif
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
@@ -687,6 +742,10 @@ struct f2fs_sb_info {
int valid_super_block; /* valid super block no */
int s_flag; /* flags for sbi */
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
+ u8 key_prefix_size;
+#endif
/* for node-related operations */
struct f2fs_nm_info *nm_info; /* node manager */
struct inode *node_inode; /* cache node blocks */
@@ -742,18 +801,24 @@ struct f2fs_sb_info {
unsigned int total_sections; /* total section count */
unsigned int total_node_count; /* total node block count */
unsigned int total_valid_node_count; /* valid node block count */
- unsigned int total_valid_inode_count; /* valid inode count */
loff_t max_file_blocks; /* max block index of file */
int active_logs; /* # of active logs */
int dir_level; /* directory level */
block_t user_block_count; /* # of user blocks */
block_t total_valid_block_count; /* # of valid blocks */
- block_t alloc_valid_block_count; /* # of allocated blocks */
block_t discard_blks; /* discard command candidats */
block_t last_valid_block_count; /* for recovery */
u32 s_next_generation; /* for NFS support */
- atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */
+ atomic_t nr_wb_bios; /* # of writeback bios */
+
+ /* # of pages, see count_type */
+ struct percpu_counter nr_pages[NR_COUNT_TYPE];
+ /* # of allocated blocks */
+ struct percpu_counter alloc_valid_block_count;
+
+ /* valid inode count */
+ struct percpu_counter total_valid_inode_count;
struct f2fs_mount_info mount_opt; /* mount options */
@@ -1055,21 +1120,33 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
}
static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
- struct inode *inode, blkcnt_t count)
+ struct inode *inode, blkcnt_t *count)
{
block_t valid_block_count;
spin_lock(&sbi->stat_lock);
- valid_block_count =
- sbi->total_valid_block_count + (block_t)count;
- if (unlikely(valid_block_count > sbi->user_block_count)) {
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_BLOCK)) {
spin_unlock(&sbi->stat_lock);
return false;
}
- inode->i_blocks += count;
- sbi->total_valid_block_count = valid_block_count;
- sbi->alloc_valid_block_count += (block_t)count;
+#endif
+ valid_block_count =
+ sbi->total_valid_block_count + (block_t)(*count);
+ if (unlikely(valid_block_count > sbi->user_block_count)) {
+ *count = sbi->user_block_count - sbi->total_valid_block_count;
+ if (!*count) {
+ spin_unlock(&sbi->stat_lock);
+ return false;
+ }
+ }
+ /* *count can be recalculated */
+ inode->i_blocks += *count;
+ sbi->total_valid_block_count =
+ sbi->total_valid_block_count + (block_t)(*count);
spin_unlock(&sbi->stat_lock);
+
+ percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
return true;
}
@@ -1087,20 +1164,20 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
- atomic_inc(&sbi->nr_pages[count_type]);
+ percpu_counter_inc(&sbi->nr_pages[count_type]);
set_sbi_flag(sbi, SBI_IS_DIRTY);
}
static inline void inode_inc_dirty_pages(struct inode *inode)
{
- atomic_inc(&F2FS_I(inode)->dirty_pages);
+ percpu_counter_inc(&F2FS_I(inode)->dirty_pages);
inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
}
static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
- atomic_dec(&sbi->nr_pages[count_type]);
+ percpu_counter_dec(&sbi->nr_pages[count_type]);
}
static inline void inode_dec_dirty_pages(struct inode *inode)
@@ -1109,26 +1186,28 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
!S_ISLNK(inode->i_mode))
return;
- atomic_dec(&F2FS_I(inode)->dirty_pages);
+ percpu_counter_dec(&F2FS_I(inode)->dirty_pages);
dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
}
-static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
+static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
{
- return atomic_read(&sbi->nr_pages[count_type]);
+ return percpu_counter_sum_positive(&sbi->nr_pages[count_type]);
}
-static inline int get_dirty_pages(struct inode *inode)
+static inline s64 get_dirty_pages(struct inode *inode)
{
- return atomic_read(&F2FS_I(inode)->dirty_pages);
+ return percpu_counter_sum_positive(&F2FS_I(inode)->dirty_pages);
}
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
- return ((get_pages(sbi, block_type) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+ unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
+ sbi->log_blocks_per_seg;
+
+ return segs / sbi->segs_per_sec;
}
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
@@ -1217,11 +1296,11 @@ static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
if (inode)
inode->i_blocks++;
- sbi->alloc_valid_block_count++;
sbi->total_valid_node_count++;
sbi->total_valid_block_count++;
spin_unlock(&sbi->stat_lock);
+ percpu_counter_inc(&sbi->alloc_valid_block_count);
return true;
}
@@ -1248,28 +1327,30 @@ static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
- sbi->total_valid_inode_count++;
- spin_unlock(&sbi->stat_lock);
+ percpu_counter_inc(&sbi->total_valid_inode_count);
}
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
- sbi->total_valid_inode_count--;
- spin_unlock(&sbi->stat_lock);
+ percpu_counter_dec(&sbi->total_valid_inode_count);
}
-static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
+static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
{
- return sbi->total_valid_inode_count;
+ return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
}
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
pgoff_t index, bool for_write)
{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ struct page *page = find_lock_page(mapping, index);
+ if (page)
+ return page;
+
+ if (time_to_inject(FAULT_PAGE_ALLOC))
+ return NULL;
+#endif
if (!for_write)
return grab_cache_page(mapping, index);
return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
@@ -1435,7 +1516,6 @@ enum {
FI_NO_ALLOC, /* should not allocate any blocks */
FI_FREE_NID, /* free allocated nide */
FI_UPDATE_DIR, /* should update inode block for consistency */
- FI_DELAY_IPUT, /* used for the recovery */
FI_NO_EXTENT, /* not to use the extent cache */
FI_INLINE_XATTR, /* used for inline xattr */
FI_INLINE_DATA, /* used for inline data*/
@@ -1618,12 +1698,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
return is_set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
}
-static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
-{
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- sbi->sb->s_flags |= MS_RDONLY;
-}
-
static inline bool is_dot_dotdot(const struct qstr *str)
{
if (str->len == 1 && str->name[0] == '.')
@@ -1644,6 +1718,15 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
return S_ISREG(inode->i_mode);
}
+static inline void *f2fs_kmalloc(size_t size, gfp_t flags)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_KMALLOC))
+ return NULL;
+#endif
+ return kmalloc(size, flags);
+}
+
static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
@@ -1710,7 +1793,7 @@ struct dentry *f2fs_get_parent(struct dentry *child);
*/
extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
void set_de_type(struct f2fs_dir_entry *, umode_t);
-
+unsigned char get_de_type(struct f2fs_dir_entry *);
struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
@@ -1731,6 +1814,8 @@ void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
const struct qstr *, f2fs_hash_t , unsigned int);
+int f2fs_add_regular_entry(struct inode *, const struct qstr *,
+ struct inode *, nid_t, umode_t);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
umode_t);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
@@ -1781,7 +1866,10 @@ void ra_node_page(struct f2fs_sb_info *, nid_t);
struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_node_page_ra(struct page *, int);
void sync_inode_page(struct dnode_of_data *);
-int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *);
+void move_node_page(struct page *, int);
+int fsync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *,
+ bool);
+int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
bool alloc_nid(struct f2fs_sb_info *, nid_t *);
void alloc_nid_done(struct f2fs_sb_info *, nid_t);
void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
@@ -1843,6 +1931,7 @@ void destroy_segment_manager_caches(void);
/*
* checkpoint.c
*/
+void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool);
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
@@ -1852,7 +1941,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void release_ino_entry(struct f2fs_sb_info *);
+void release_ino_entry(struct f2fs_sb_info *, bool);
bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
int acquire_orphan_inode(struct f2fs_sb_info *);
void release_orphan_inode(struct f2fs_sb_info *);
@@ -1861,7 +1950,6 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
int recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
void remove_dirty_inode(struct inode *);
int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
@@ -1880,6 +1968,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *);
void f2fs_submit_page_mbio(struct f2fs_io_info *);
void set_data_blkaddr(struct dnode_of_data *);
void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
+int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
int reserve_new_block(struct dnode_of_data *);
int f2fs_get_block(struct dnode_of_data *, pgoff_t);
ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
@@ -1906,7 +1995,7 @@ void build_gc_manager(struct f2fs_sb_info *);
/*
* recovery.c
*/
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
bool space_for_roll_forward(struct f2fs_sb_info *);
/*
@@ -1921,12 +2010,12 @@ struct f2fs_stat_info {
unsigned long long hit_largest, hit_cached, hit_rbtree;
unsigned long long hit_total, total_ext;
int ext_tree, zombie_tree, ext_node;
- int ndirty_node, ndirty_meta;
- int ndirty_dent, ndirty_dirs, ndirty_data, ndirty_files;
+ s64 ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, inmem_pages;
+ unsigned int ndirty_dirs, ndirty_files;
int nats, dirty_nats, sits, dirty_sits, fnids;
int total_count, utilization;
- int bg_gc, inmem_pages, wb_pages;
- int inline_xattr, inline_inode, inline_dir;
+ int bg_gc, wb_bios;
+ int inline_xattr, inline_inode, inline_dir, orphans;
unsigned int valid_count, valid_node_count, valid_inode_count;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 90d1157a09f9..f4c0086655c4 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -20,7 +20,7 @@
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
-#include <linux/random.h>
+#include <linux/uuid.h>
#include "f2fs.h"
#include "node.h"
@@ -182,7 +182,8 @@ static void try_to_fix_pino(struct inode *inode)
}
}
-int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
+ int datasync, bool atomic)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -256,7 +257,9 @@ go_write:
goto out;
}
sync_nodes:
- sync_node_pages(sbi, ino, &wbc);
+ ret = fsync_node_pages(sbi, ino, &wbc, atomic);
+ if (ret)
+ goto out;
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi))) {
@@ -288,6 +291,11 @@ out:
return ret;
}
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+ return f2fs_do_sync_file(file, start, end, datasync, false);
+}
+
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
@@ -555,6 +563,9 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
+ if (free_from >= sbi->max_file_blocks)
+ goto free_partial;
+
if (lock)
f2fs_lock_op(sbi);
@@ -573,7 +584,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
- err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
+ err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
@@ -596,7 +607,7 @@ free_next:
out:
if (lock)
f2fs_unlock_op(sbi);
-
+free_partial:
/* lastly zero out the first data page */
if (!err)
err = truncate_partial_data_page(inode, from, truncate_page);
@@ -986,6 +997,49 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
return ret;
}
+static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
+ pgoff_t end)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ pgoff_t index = start;
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ blkcnt_t count = 0;
+ int ret;
+
+ for (; index < end; index++, dn->ofs_in_node++) {
+ if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+ count++;
+ }
+
+ dn->ofs_in_node = ofs_in_node;
+ ret = reserve_new_blocks(dn, count);
+ if (ret)
+ return ret;
+
+ dn->ofs_in_node = ofs_in_node;
+ for (index = start; index < end; index++, dn->ofs_in_node++) {
+ dn->data_blkaddr =
+ datablock_addr(dn->node_page, dn->ofs_in_node);
+ /*
+ * reserve_new_blocks will not guarantee entire block
+ * allocation.
+ */
+ if (dn->data_blkaddr == NULL_ADDR) {
+ ret = -ENOSPC;
+ break;
+ }
+ if (dn->data_blkaddr != NEW_ADDR) {
+ invalidate_blocks(sbi, dn->data_blkaddr);
+ dn->data_blkaddr = NEW_ADDR;
+ set_data_blkaddr(dn);
+ }
+ }
+
+ f2fs_update_extent_cache_range(dn, start, 0, index - start);
+
+ return ret;
+}
+
static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
@@ -1036,35 +1090,32 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
(loff_t)pg_start << PAGE_SHIFT);
}
- for (index = pg_start; index < pg_end; index++) {
+ for (index = pg_start; index < pg_end;) {
struct dnode_of_data dn;
- struct page *ipage;
+ unsigned int end_offset;
+ pgoff_t end;
f2fs_lock_op(sbi);
- ipage = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(ipage)) {
- ret = PTR_ERR(ipage);
- f2fs_unlock_op(sbi);
- goto out;
- }
-
- set_new_dnode(&dn, inode, ipage, NULL, 0);
- ret = f2fs_reserve_block(&dn, index);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
goto out;
}
- if (dn.data_blkaddr != NEW_ADDR) {
- invalidate_blocks(sbi, dn.data_blkaddr);
- f2fs_update_data_blkaddr(&dn, NEW_ADDR);
- }
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ end = min(pg_end, end_offset - dn.ofs_in_node + index);
+
+ ret = f2fs_do_zero_range(&dn, index, end);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
+ if (ret)
+ goto out;
+ index = end;
new_size = max_t(loff_t, new_size,
- (loff_t)(index + 1) << PAGE_SHIFT);
+ (loff_t)index << PAGE_SHIFT);
}
if (off_end) {
@@ -1147,10 +1198,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- pgoff_t index, pg_start, pg_end;
+ struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+ pgoff_t pg_end;
loff_t new_size = i_size_read(inode);
- loff_t off_start, off_end;
- int ret = 0;
+ loff_t off_end;
+ int ret;
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
@@ -1162,43 +1214,35 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
f2fs_balance_fs(sbi, true);
- pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
- pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
-
- off_start = offset & (PAGE_SIZE - 1);
+ pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
off_end = (offset + len) & (PAGE_SIZE - 1);
- f2fs_lock_op(sbi);
+ map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT;
+ map.m_len = pg_end - map.m_lblk;
+ if (off_end)
+ map.m_len++;
- for (index = pg_start; index <= pg_end; index++) {
- struct dnode_of_data dn;
+ ret = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ if (ret) {
+ pgoff_t last_off;
- if (index == pg_end && !off_end)
- goto noalloc;
+ if (!map.m_len)
+ return ret;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = f2fs_reserve_block(&dn, index);
- if (ret)
- break;
-noalloc:
- if (pg_start == pg_end)
- new_size = offset + len;
- else if (index == pg_start && off_start)
- new_size = (loff_t)(index + 1) << PAGE_SHIFT;
- else if (index == pg_end)
- new_size = ((loff_t)index << PAGE_SHIFT) +
- off_end;
- else
- new_size += PAGE_SIZE;
+ last_off = map.m_lblk + map.m_len - 1;
+
+ /* update new size to the failed position */
+ new_size = (last_off == pg_end) ? offset + len:
+ (loff_t)(last_off + 1) << PAGE_SHIFT;
+ } else {
+ new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
}
- if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- i_size_read(inode) < new_size) {
+ if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
update_inode_page(inode);
}
- f2fs_unlock_op(sbi);
return ret;
}
@@ -1254,10 +1298,19 @@ out:
static int f2fs_release_file(struct inode *inode, struct file *filp)
{
+ /*
+ * f2fs_relase_file is called at every close calls. So we should
+ * not drop any inmemory pages by close called by other process.
+ */
+ if (!(filp->f_mode & FMODE_WRITE) ||
+ atomic_read(&inode->i_writecount) != 1)
+ return 0;
+
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
+ clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
@@ -1294,20 +1347,16 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
unsigned int oldflags;
int ret;
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (get_user(flags, (int __user *)arg))
+ return -EFAULT;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
-
- if (get_user(flags, (int __user *)arg)) {
- ret = -EFAULT;
- goto out;
- }
-
flags = f2fs_mask_flags(inode->i_mode, flags);
inode_lock(inode);
@@ -1350,17 +1399,35 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
if (f2fs_is_atomic_file(inode))
- return 0;
+ goto out;
ret = f2fs_convert_inline_inode(inode);
if (ret)
- return ret;
+ goto out;
set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return 0;
+ if (!get_dirty_pages(inode))
+ goto out;
+
+ f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
+ "Unexpected flush for atomic writes: ino=%lu, npages=%lld",
+ inode->i_ino, get_dirty_pages(inode));
+ ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+ if (ret)
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_commit_atomic_write(struct file *filp)
@@ -1371,13 +1438,15 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
- if (f2fs_is_volatile_file(inode))
- return 0;
-
ret = mnt_want_write_file(filp);
if (ret)
return ret;
+ inode_lock(inode);
+
+ if (f2fs_is_volatile_file(inode))
+ goto err_out;
+
if (f2fs_is_atomic_file(inode)) {
clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
ret = commit_inmem_pages(inode);
@@ -1387,8 +1456,9 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
}
}
- ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
err_out:
+ inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
@@ -1401,32 +1471,54 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
if (f2fs_is_volatile_file(inode))
- return 0;
+ goto out;
ret = f2fs_convert_inline_inode(inode);
if (ret)
- return ret;
+ goto out;
set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return 0;
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_release_volatile_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
+ int ret;
if (!inode_owner_or_capable(inode))
return -EACCES;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
if (!f2fs_is_volatile_file(inode))
- return 0;
+ goto out;
- if (!f2fs_is_first_block_written(inode))
- return truncate_partial_data_page(inode, 0, true);
+ if (!f2fs_is_first_block_written(inode)) {
+ ret = truncate_partial_data_page(inode, 0, true);
+ goto out;
+ }
- return punch_hole(inode, 0, F2FS_BLKSIZE);
+ ret = punch_hole(inode, 0, F2FS_BLKSIZE);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_abort_volatile_write(struct file *filp)
@@ -1441,15 +1533,17 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
if (ret)
return ret;
- if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ inode_lock(inode);
+
+ if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
- }
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
- ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
}
+ inode_unlock(inode);
+
mnt_drop_write_file(filp);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
@@ -1461,6 +1555,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct super_block *sb = sbi->sb;
__u32 in;
+ int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1468,31 +1563,38 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
if (get_user(in, (__u32 __user *)arg))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
switch (in) {
case F2FS_GOING_DOWN_FULLSYNC:
sb = freeze_bdev(sb->s_bdev);
if (sb && !IS_ERR(sb)) {
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
thaw_bdev(sb->s_bdev, sb);
}
break;
case F2FS_GOING_DOWN_METASYNC:
/* do checkpoint only */
f2fs_sync_fs(sb, 1);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_NOSYNC:
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_METAFLUSH:
sync_meta_pages(sbi, META, LONG_MAX);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
f2fs_update_time(sbi, REQ_TIME);
- return 0;
+out:
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
@@ -1513,9 +1615,14 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
sizeof(range)))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+ mnt_drop_write_file(filp);
if (ret < 0)
return ret;
@@ -1540,13 +1647,21 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
+ int ret;
if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return fscrypt_process_policy(inode, &policy);
+ ret = fscrypt_process_policy(inode, &policy);
+
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
@@ -1603,6 +1718,7 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
__u32 sync;
+ int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1613,20 +1729,30 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
if (!sync) {
- if (!mutex_trylock(&sbi->gc_mutex))
- return -EBUSY;
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
} else {
mutex_lock(&sbi->gc_mutex);
}
- return f2fs_gc(sbi, sync);
+ ret = f2fs_gc(sbi, sync);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1634,7 +1760,14 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;
- return f2fs_sync_fs(sbi->sb, 1);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ ret = f2fs_sync_fs(sbi->sb, 1);
+
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
@@ -1886,13 +2019,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
}
inode_unlock(inode);
- if (ret > 0) {
- ssize_t err;
-
- err = generic_write_sync(file, iocb->ki_pos - ret, ret);
- if (err < 0)
- ret = err;
- }
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
return ret;
}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b0051a97824c..38d56f678912 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -96,7 +96,7 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
dev_t dev = sbi->sb->s_bdev->bd_dev;
int err = 0;
- gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
+ gc_th = f2fs_kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
if (!gc_th) {
err = -ENOMEM;
goto out;
@@ -465,15 +465,7 @@ next_step:
continue;
}
- /* set page dirty and write it */
- if (gc_type == FG_GC) {
- f2fs_wait_on_page_writeback(node_page, NODE, true);
- set_page_dirty(node_page);
- } else {
- if (!PageWriteback(node_page))
- set_page_dirty(node_page);
- }
- f2fs_put_page(node_page, 1);
+ move_node_page(node_page, gc_type);
stat_inc_node_blk_count(sbi, 1, gc_type);
}
@@ -834,18 +826,9 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
f2fs_put_page(sum_page, 0);
}
- if (gc_type == FG_GC) {
- if (type == SUM_TYPE_NODE) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = LONG_MAX,
- .for_reclaim = 0,
- };
- sync_node_pages(sbi, 0, &wbc);
- } else {
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
- }
- }
+ if (gc_type == FG_GC)
+ f2fs_submit_merged_bio(sbi,
+ (type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
blk_finish_plug(&plug);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index a2fbe6f427d3..a4bb155dd00a 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -161,7 +161,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
if (!f2fs_has_inline_data(inode))
return 0;
- page = grab_cache_page(inode->i_mapping, 0);
+ page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
if (!page)
return -ENOMEM;
@@ -303,11 +303,6 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
else
f2fs_put_page(ipage, 0);
- /*
- * For the most part, it should be a bug when name_len is zero.
- * We stop here for figuring out where the bugs has occurred.
- */
- f2fs_bug_on(sbi, d.max < 0);
return de;
}
@@ -355,7 +350,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
* NOTE: ipage is grabbed by caller, but if any error occurs, we should
* release ipage in this function.
*/
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
@@ -363,7 +358,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
struct f2fs_dentry_block *dentry_blk;
int err;
- page = grab_cache_page(dir->i_mapping, 0);
+ page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
if (!page) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
@@ -405,6 +400,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
stat_dec_inline_dir(dir);
clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
+ F2FS_I(dir)->i_current_depth = 1;
if (i_size_read(dir) < PAGE_SIZE) {
i_size_write(dir, PAGE_SIZE);
set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
@@ -416,6 +412,105 @@ out:
return err;
}
+static int f2fs_add_inline_entries(struct inode *dir,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_dentry_ptr d;
+ unsigned long bit_pos = 0;
+ int err = 0;
+
+ make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+ while (bit_pos < d.max) {
+ struct f2fs_dir_entry *de;
+ struct qstr new_name;
+ nid_t ino;
+ umode_t fake_mode;
+
+ if (!test_bit_le(bit_pos, d.bitmap)) {
+ bit_pos++;
+ continue;
+ }
+
+ de = &d.dentry[bit_pos];
+
+ if (unlikely(!de->name_len)) {
+ bit_pos++;
+ continue;
+ }
+
+ new_name.name = d.filename[bit_pos];
+ new_name.len = de->name_len;
+
+ ino = le32_to_cpu(de->ino);
+ fake_mode = get_de_type(de) << S_SHIFT;
+
+ err = f2fs_add_regular_entry(dir, &new_name, NULL,
+ ino, fake_mode);
+ if (err)
+ goto punch_dentry_pages;
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return 0;
+punch_dentry_pages:
+ truncate_inode_pages(&dir->i_data, 0);
+ truncate_blocks(dir, 0, false);
+ remove_dirty_inode(dir);
+ return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_inline_dentry *backup_dentry;
+ struct f2fs_inode_info *fi = F2FS_I(dir);
+ int err;
+
+ backup_dentry = f2fs_kmalloc(sizeof(struct f2fs_inline_dentry),
+ GFP_F2FS_ZERO);
+ if (!backup_dentry) {
+ f2fs_put_page(ipage, 1);
+ return -ENOMEM;
+ }
+
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+ truncate_inline_inode(ipage, 0);
+
+ unlock_page(ipage);
+
+ err = f2fs_add_inline_entries(dir, backup_dentry);
+ if (err)
+ goto recover;
+
+ lock_page(ipage);
+
+ stat_dec_inline_dir(dir);
+ clear_inode_flag(fi, FI_INLINE_DENTRY);
+ update_inode(dir, ipage);
+ kfree(backup_dentry);
+ return 0;
+recover:
+ lock_page(ipage);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ fi->i_current_depth = 0;
+ i_size_write(dir, MAX_INLINE_DATA);
+ update_inode(dir, ipage);
+ f2fs_put_page(ipage, 1);
+
+ kfree(backup_dentry);
+ return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ if (!F2FS_I(dir)->i_dir_level)
+ return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+ else
+ return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index cb269c46ac25..2e68adab0d64 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -283,7 +283,7 @@ retry:
cond_resched();
goto retry;
} else if (err != -ENOENT) {
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
}
return 0;
}
@@ -344,7 +344,7 @@ void f2fs_evict_inode(struct inode *inode)
sb_start_intwrite(inode->i_sb);
set_inode_flag(fi, FI_NO_ALLOC);
i_size_write(inode, 0);
-
+retry:
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode, true);
@@ -354,6 +354,12 @@ void f2fs_evict_inode(struct inode *inode)
f2fs_unlock_op(sbi);
}
+ /* give more chances, if ENOMEM case */
+ if (err == -ENOMEM) {
+ err = 0;
+ goto retry;
+ }
+
sb_end_intwrite(inode->i_sb);
no_delete:
stat_dec_inline_xattr(inode);
@@ -368,26 +374,11 @@ no_delete:
if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
if (is_inode_flag_set(fi, FI_FREE_NID)) {
- if (err && err != -ENOENT)
- alloc_nid_done(sbi, inode->i_ino);
- else
- alloc_nid_failed(sbi, inode->i_ino);
+ alloc_nid_failed(sbi, inode->i_ino);
clear_inode_flag(fi, FI_FREE_NID);
}
-
- if (err && err != -ENOENT) {
- if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
- /*
- * get here because we failed to release resource
- * of inode previously, reminder our user to run fsck
- * for fixing.
- */
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_msg(sbi->sb, KERN_WARNING,
- "inode (ino:%lu) resource leak, run fsck "
- "to fix this issue!", inode->i_ino);
- }
- }
+ f2fs_bug_on(sbi, err &&
+ !exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
out_clear:
fscrypt_put_encryption_info(inode, NULL);
clear_inode(inode);
@@ -397,37 +388,32 @@ out_clear:
void handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- int err = 0;
+ struct node_info ni;
- clear_nlink(inode);
- make_bad_inode(inode);
+ /* don't make bad inode, since it becomes a regular file. */
unlock_new_inode(inode);
- i_size_write(inode, 0);
- if (F2FS_HAS_BLOCKS(inode))
- err = f2fs_truncate(inode, false);
-
- if (!err)
- err = remove_inode_page(inode);
-
/*
- * if we skip truncate_node in remove_inode_page bacause we failed
- * before, it's better to find another way to release resource of
- * this inode (e.g. valid block count, node block or nid). Here we
- * choose to add this inode to orphan list, so that we can call iput
- * for releasing in orphan recovery flow.
- *
* Note: we should add inode to orphan list before f2fs_unlock_op()
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
- if (err && err != -ENOENT) {
- err = acquire_orphan_inode(sbi);
- if (!err)
+ get_node_info(sbi, inode->i_ino, &ni);
+
+ if (ni.blk_addr != NULL_ADDR) {
+ int err = acquire_orphan_inode(sbi);
+ if (err) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Too many orphan inodes, run fsck to fix.");
+ } else {
add_orphan_inode(sbi, inode->i_ino);
+ }
+ alloc_nid_done(sbi, inode->i_ino);
+ } else {
+ set_inode_flag(F2FS_I(inode), FI_FREE_NID);
}
- set_inode_flag(F2FS_I(inode), FI_FREE_NID);
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 013e57932d61..324ed3812f30 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -202,7 +202,7 @@ struct dentry *f2fs_get_parent(struct dentry *child)
unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
- return d_obtain_alias(f2fs_iget(d_inode(child)->i_sb, ino));
+ return d_obtain_alias(f2fs_iget(child->d_sb, ino));
}
static int __recover_dot_dentries(struct inode *dir, nid_t pino)
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 1a33de9d84b1..1f21aae80c40 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -407,6 +407,29 @@ cache:
up_write(&nm_i->nat_tree_lock);
}
+/*
+ * readahead MAX_RA_NODE number of node pages.
+ */
+static void ra_node_pages(struct page *parent, int start, int n)
+{
+ struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
+ struct blk_plug plug;
+ int i, end;
+ nid_t nid;
+
+ blk_start_plug(&plug);
+
+ /* Then, try readahead for siblings of the desired node */
+ end = start + n;
+ end = min(end, NIDS_PER_BLOCK);
+ for (i = start; i < end; i++) {
+ nid = get_nid(parent, i, false);
+ ra_node_page(sbi, nid);
+ }
+
+ blk_finish_plug(&plug);
+}
+
pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
{
const long direct_index = ADDRS_PER_INODE(dn->inode);
@@ -707,6 +730,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
return PTR_ERR(page);
}
+ ra_node_pages(page, ofs, NIDS_PER_BLOCK);
+
rn = F2FS_NODE(page);
if (depth < 3) {
for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
@@ -784,6 +809,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
}
+ ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
+
/* free direct nodes linked to a partial indirect node */
for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) {
child_nid = get_nid(pages[idx], i, false);
@@ -832,7 +859,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
trace_f2fs_truncate_inode_blocks_enter(inode, from);
level = get_node_path(inode, from, offset, noffset);
-restart:
+
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
@@ -896,10 +923,7 @@ skip_partial:
if (offset[1] == 0 &&
ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
lock_page(page);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
- f2fs_put_page(page, 1);
- goto restart;
- }
+ BUG_ON(page->mapping != NODE_MAPPING(sbi));
f2fs_wait_on_page_writeback(page, NODE, true);
ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
set_page_dirty(page);
@@ -998,7 +1022,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return ERR_PTR(-EPERM);
- page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -1090,7 +1114,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
if (apage)
return;
- apage = grab_cache_page(NODE_MAPPING(sbi), nid);
+ apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!apage)
return;
@@ -1098,29 +1122,6 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
f2fs_put_page(apage, err ? 1 : 0);
}
-/*
- * readahead MAX_RA_NODE number of node pages.
- */
-static void ra_node_pages(struct page *parent, int start)
-{
- struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
- struct blk_plug plug;
- int i, end;
- nid_t nid;
-
- blk_start_plug(&plug);
-
- /* Then, try readahead for siblings of the desired node */
- end = start + MAX_RA_NODE;
- end = min(end, NIDS_PER_BLOCK);
- for (i = start; i < end; i++) {
- nid = get_nid(parent, i, false);
- ra_node_page(sbi, nid);
- }
-
- blk_finish_plug(&plug);
-}
-
static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
struct page *parent, int start)
{
@@ -1131,7 +1132,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
return ERR_PTR(-ENOENT);
f2fs_bug_on(sbi, check_nid_range(sbi, nid));
repeat:
- page = grab_cache_page(NODE_MAPPING(sbi), nid);
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -1144,7 +1145,7 @@ repeat:
}
if (parent)
- ra_node_pages(parent, start + 1);
+ ra_node_pages(parent, start + 1, MAX_RA_NODE);
lock_page(page);
@@ -1196,19 +1197,17 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct page *page;
+ int ret;
/* should flush inline_data before evict_inode */
inode = ilookup(sbi->sb, ino);
if (!inode)
return;
- page = pagecache_get_page(inode->i_mapping, 0, FGP_NOWAIT, 0);
+ page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0);
if (!page)
goto iput_out;
- if (!trylock_page(page))
- goto release_out;
-
if (!PageUptodate(page))
goto page_out;
@@ -1218,24 +1217,214 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
if (!clear_page_dirty_for_io(page))
goto page_out;
- if (!f2fs_write_inline_data(inode, page))
- inode_dec_dirty_pages(inode);
- else
+ ret = f2fs_write_inline_data(inode, page);
+ inode_dec_dirty_pages(inode);
+ if (ret)
set_page_dirty(page);
page_out:
- unlock_page(page);
-release_out:
- f2fs_put_page(page, 0);
+ f2fs_put_page(page, 1);
iput_out:
iput(inode);
}
-int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
- struct writeback_control *wbc)
+void move_node_page(struct page *node_page, int gc_type)
+{
+ if (gc_type == FG_GC) {
+ struct f2fs_sb_info *sbi = F2FS_P_SB(node_page);
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 1,
+ .for_reclaim = 0,
+ };
+
+ set_page_dirty(node_page);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
+
+ f2fs_bug_on(sbi, PageWriteback(node_page));
+ if (!clear_page_dirty_for_io(node_page))
+ goto out_page;
+
+ if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc))
+ unlock_page(node_page);
+ goto release_page;
+ } else {
+ /* set page dirty and write it */
+ if (!PageWriteback(node_page))
+ set_page_dirty(node_page);
+ }
+out_page:
+ unlock_page(node_page);
+release_page:
+ f2fs_put_page(node_page, 0);
+}
+
+static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
{
pgoff_t index, end;
struct pagevec pvec;
- int step = ino ? 2 : 0;
+ struct page *last_page = NULL;
+
+ pagevec_init(&pvec, 0);
+ index = 0;
+ end = ULONG_MAX;
+
+ while (index <= end) {
+ int i, nr_pages;
+ nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_put_page(last_page, 0);
+ pagevec_release(&pvec);
+ return ERR_PTR(-EIO);
+ }
+
+ if (!IS_DNODE(page) || !is_cold_node(page))
+ continue;
+ if (ino_of_node(page) != ino)
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+ if (ino_of_node(page) != ino)
+ goto continue_unlock;
+
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ if (last_page)
+ f2fs_put_page(last_page, 0);
+
+ get_page(page);
+ last_page = page;
+ unlock_page(page);
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+ return last_page;
+}
+
+int fsync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
+ struct writeback_control *wbc, bool atomic)
+{
+ pgoff_t index, end;
+ struct pagevec pvec;
+ int ret = 0;
+ struct page *last_page = NULL;
+ bool marked = false;
+
+ if (atomic) {
+ last_page = last_fsync_dnode(sbi, ino);
+ if (IS_ERR_OR_NULL(last_page))
+ return PTR_ERR_OR_ZERO(last_page);
+ }
+retry:
+ pagevec_init(&pvec, 0);
+ index = 0;
+ end = ULONG_MAX;
+
+ while (index <= end) {
+ int i, nr_pages;
+ nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_put_page(last_page, 0);
+ pagevec_release(&pvec);
+ return -EIO;
+ }
+
+ if (!IS_DNODE(page) || !is_cold_node(page))
+ continue;
+ if (ino_of_node(page) != ino)
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+ if (ino_of_node(page) != ino)
+ goto continue_unlock;
+
+ if (!PageDirty(page) && page != last_page) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ f2fs_wait_on_page_writeback(page, NODE, true);
+ BUG_ON(PageWriteback(page));
+
+ if (!atomic || page == last_page) {
+ set_fsync_mark(page, 1);
+ if (IS_INODE(page))
+ set_dentry_mark(page,
+ need_dentry_mark(sbi, ino));
+ /* may be written by other thread */
+ if (!PageDirty(page))
+ set_page_dirty(page);
+ }
+
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
+ ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc);
+ if (ret) {
+ unlock_page(page);
+ f2fs_put_page(last_page, 0);
+ break;
+ }
+ if (page == last_page) {
+ f2fs_put_page(page, 0);
+ marked = true;
+ break;
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+
+ if (ret || marked)
+ break;
+ }
+ if (!ret && atomic && !marked) {
+ f2fs_msg(sbi->sb, KERN_DEBUG,
+ "Retry to write fsync mark: ino=%u, idx=%lx",
+ ino, last_page->index);
+ lock_page(last_page);
+ set_page_dirty(last_page);
+ unlock_page(last_page);
+ goto retry;
+ }
+ return ret ? -EIO: 0;
+}
+
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
+{
+ pgoff_t index, end;
+ struct pagevec pvec;
+ int step = 0;
int nwritten = 0;
pagevec_init(&pvec, 0);
@@ -1274,15 +1463,8 @@ next_step:
if (step == 2 && (!IS_DNODE(page) ||
!is_cold_node(page)))
continue;
-
- /*
- * If an fsync mode,
- * we should not skip writing node pages.
- */
lock_node:
- if (ino && ino_of_node(page) == ino)
- lock_page(page);
- else if (!trylock_page(page))
+ if (!trylock_page(page))
continue;
if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
@@ -1290,8 +1472,6 @@ continue_unlock:
unlock_page(page);
continue;
}
- if (ino && ino_of_node(page) != ino)
- goto continue_unlock;
if (!PageDirty(page)) {
/* someone wrote it for us */
@@ -1299,7 +1479,7 @@ continue_unlock:
}
/* flush inline_data */
- if (!ino && is_inline_node(page)) {
+ if (is_inline_node(page)) {
clear_inline_node(page);
unlock_page(page);
flush_inline_data(sbi, ino_of_node(page));
@@ -1312,17 +1492,8 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- /* called by fsync() */
- if (ino && IS_DNODE(page)) {
- set_fsync_mark(page, 1);
- if (IS_INODE(page))
- set_dentry_mark(page,
- need_dentry_mark(sbi, ino));
- nwritten++;
- } else {
- set_fsync_mark(page, 0);
- set_dentry_mark(page, 0);
- }
+ set_fsync_mark(page, 0);
+ set_dentry_mark(page, 0);
if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
unlock_page(page);
@@ -1470,7 +1641,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
- sync_node_pages(sbi, 0, wbc);
+ sync_node_pages(sbi, wbc);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
return 0;
@@ -1524,7 +1695,6 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
struct nat_entry *ne;
- bool allocated = false;
if (!available_free_memory(sbi, FREE_NIDS))
return -1;
@@ -1538,8 +1708,6 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
ne = __lookup_nat_cache(nm_i, nid);
if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
nat_get_blkaddr(ne) != NULL_ADDR))
- allocated = true;
- if (allocated)
return 0;
}
@@ -1672,6 +1840,10 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i = NULL;
retry:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_ALLOC_NID))
+ return false;
+#endif
if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
return false;
@@ -1846,7 +2018,7 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
if (unlikely(old_ni.blk_addr != NULL_ADDR))
return -EINVAL;
- ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
+ ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
if (!ipage)
return -ENOMEM;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 011942f94d64..3d7216d7a288 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -49,8 +49,9 @@ static struct kmem_cache *fsync_entry_slab;
bool space_for_roll_forward(struct f2fs_sb_info *sbi)
{
- if (sbi->last_valid_block_count + sbi->alloc_valid_block_count
- > sbi->user_block_count)
+ s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
+
+ if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
return false;
return true;
}
@@ -67,7 +68,30 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
return NULL;
}
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct list_head *head,
+ struct inode *inode)
+{
+ struct fsync_inode_entry *entry;
+
+ entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+ if (!entry)
+ return NULL;
+
+ entry->inode = inode;
+ list_add_tail(&entry->list, head);
+
+ return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+ iput(entry->inode);
+ list_del(&entry->list);
+ kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+ struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,18 +99,29 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
struct qstr name;
struct page *page;
struct inode *dir, *einode;
+ struct fsync_inode_entry *entry;
int err = 0;
- dir = f2fs_iget(inode->i_sb, pino);
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
+ entry = get_fsync_inode(dir_list, pino);
+ if (!entry) {
+ dir = f2fs_iget(inode->i_sb, pino);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
+ }
+
+ entry = add_fsync_inode(dir_list, dir);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(dir);
+ goto out;
+ }
}
- if (file_enc_name(inode)) {
- iput(dir);
+ dir = entry->inode;
+
+ if (file_enc_name(inode))
return 0;
- }
name.len = le32_to_cpu(raw_inode->i_namelen);
name.name = raw_inode->i_name;
@@ -94,7 +129,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
if (unlikely(name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
- goto out_err;
+ goto out;
}
retry:
de = f2fs_find_entry(dir, &name, &page);
@@ -120,23 +155,12 @@ retry:
goto retry;
}
err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
- if (err)
- goto out_err;
-
- if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
- iput(dir);
- } else {
- add_dirty_dir_inode(dir);
- set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
- }
goto out;
out_unmap_put:
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
-out_err:
- iput(dir);
out:
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -198,6 +222,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
+ struct inode *inode;
struct page *page = NULL;
block_t blkaddr;
int err = 0;
@@ -206,8 +231,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- ra_meta_pages(sbi, blkaddr, 1, META_POR, true);
-
while (1) {
struct fsync_inode_entry *entry;
@@ -233,35 +256,32 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- /* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
- if (!entry) {
- err = -ENOMEM;
- break;
- }
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
- if (IS_ERR(entry->inode)) {
- err = PTR_ERR(entry->inode);
- kmem_cache_free(fsync_entry_slab, entry);
+ inode = f2fs_iget(sbi->sb, ino_of_node(page));
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
- list_add_tail(&entry->list, head);
+
+ /* add this fsync inode to the list */
+ entry = add_fsync_inode(head, inode);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(inode);
+ break;
+ }
}
entry->blkaddr = blkaddr;
- if (IS_INODE(page)) {
- entry->last_inode = blkaddr;
- if (is_dent_dnode(page))
- entry->last_dentry = blkaddr;
- }
+ if (IS_INODE(page) && is_dent_dnode(page))
+ entry->last_dentry = blkaddr;
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -277,11 +297,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
{
struct fsync_inode_entry *entry, *tmp;
- list_for_each_entry_safe(entry, tmp, head, list) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ list_for_each_entry_safe(entry, tmp, head, list)
+ del_fsync_inode(entry);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -444,8 +461,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
*/
if (dest == NEW_ADDR) {
truncate_data_blocks_range(&dn, 1);
- err = reserve_new_block(&dn);
- f2fs_bug_on(sbi, err);
+ reserve_new_block(&dn);
continue;
}
@@ -454,6 +470,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ while (err)
+ err = reserve_new_block(&dn);
+#endif
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
}
@@ -486,7 +506,8 @@ out:
return err;
}
-static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+ struct list_head *dir_list)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
@@ -513,7 +534,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- entry = get_fsync_inode(head, ino_of_node(page));
+ entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
@@ -521,10 +542,10 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
* In this case, we can lose the latest inode(x).
* So, call recover_inode for the inode update.
*/
- if (entry->last_inode == blkaddr)
+ if (IS_INODE(page))
recover_inode(entry->inode, page);
if (entry->last_dentry == blkaddr) {
- err = recover_dentry(entry->inode, page);
+ err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
@@ -536,11 +557,8 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- if (entry->blkaddr == blkaddr) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ if (entry->blkaddr == blkaddr)
+ del_fsync_inode(entry);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -551,12 +569,14 @@ next:
return err;
}
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct list_head inode_list;
+ struct list_head dir_list;
block_t blkaddr;
int err;
+ int ret = 0;
bool need_writecp = false;
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -565,6 +585,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
return -ENOMEM;
INIT_LIST_HEAD(&inode_list);
+ INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
@@ -573,21 +594,22 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list);
- if (err)
+ if (err || list_empty(&inode_list))
goto out;
- if (list_empty(&inode_list))
+ if (check_only) {
+ ret = 1;
goto out;
+ }
need_writecp = true;
/* step #2: recover data */
- err = recover_data(sbi, &inode_list);
+ err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
destroy_fsync_dnodes(&inode_list);
- kmem_cache_destroy(fsync_entry_slab);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
@@ -625,5 +647,8 @@ out:
} else {
mutex_unlock(&sbi->cp_mutex);
}
- return err;
+
+ destroy_fsync_dnodes(&dir_list);
+ kmem_cache_destroy(fsync_entry_slab);
+ return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 540669d6978e..2e6f537a0e7d 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -223,9 +223,11 @@ static int __revoke_inmem_pages(struct inode *inode,
f2fs_put_dnode(&dn);
}
next:
- ClearPageUptodate(page);
+ /* we don't need to invalidate this in the sccessful status */
+ if (drop || recover)
+ ClearPageUptodate(page);
set_page_private(page, 0);
- ClearPageUptodate(page);
+ ClearPagePrivate(page);
f2fs_put_page(page, 1);
list_del(&cur->list);
@@ -239,6 +241,8 @@ void drop_inmem_pages(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+
mutex_lock(&fi->inmem_lock);
__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
mutex_unlock(&fi->inmem_lock);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 975c33df65c7..7a756ff5a36d 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -158,16 +158,17 @@ struct victim_sel_policy {
};
struct seg_entry {
- unsigned short valid_blocks; /* # of valid blocks */
+ unsigned int type:6; /* segment type like CURSEG_XXX_TYPE */
+ unsigned int valid_blocks:10; /* # of valid blocks */
+ unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */
+ unsigned int padding:6; /* padding */
unsigned char *cur_valid_map; /* validity bitmap of blocks */
/*
* # of valid blocks and the validity bitmap stored in the the last
* checkpoint pack. This information is used by the SSR mode.
*/
- unsigned short ckpt_valid_blocks;
- unsigned char *ckpt_valid_map;
+ unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */
unsigned char *discard_map;
- unsigned char type; /* segment type like CURSEG_XXX_TYPE */
unsigned long long mtime; /* modification time of the segment */
};
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 006f87d69921..74cc8520b8b1 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -39,6 +39,30 @@ static struct proc_dir_entry *f2fs_proc_root;
static struct kmem_cache *f2fs_inode_cachep;
static struct kset *f2fs_kset;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+struct f2fs_fault_info f2fs_fault;
+
+char *fault_name[FAULT_MAX] = {
+ [FAULT_KMALLOC] = "kmalloc",
+ [FAULT_PAGE_ALLOC] = "page alloc",
+ [FAULT_ALLOC_NID] = "alloc nid",
+ [FAULT_ORPHAN] = "orphan",
+ [FAULT_BLOCK] = "no more block",
+ [FAULT_DIR_DEPTH] = "too big dir depth",
+};
+
+static void f2fs_build_fault_attr(unsigned int rate)
+{
+ if (rate) {
+ atomic_set(&f2fs_fault.inject_ops, 0);
+ f2fs_fault.inject_rate = rate;
+ f2fs_fault.inject_type = (1 << FAULT_MAX) - 1;
+ } else {
+ memset(&f2fs_fault, 0, sizeof(struct f2fs_fault_info));
+ }
+}
+#endif
+
/* f2fs-wide shrinker description */
static struct shrinker f2fs_shrinker_info = {
.scan_objects = f2fs_shrink_scan,
@@ -68,6 +92,7 @@ enum {
Opt_noextent_cache,
Opt_noinline_data,
Opt_data_flush,
+ Opt_fault_injection,
Opt_err,
};
@@ -93,6 +118,7 @@ static match_table_t f2fs_tokens = {
{Opt_noextent_cache, "noextent_cache"},
{Opt_noinline_data, "noinline_data"},
{Opt_data_flush, "data_flush"},
+ {Opt_fault_injection, "fault_injection=%u"},
{Opt_err, NULL},
};
@@ -102,6 +128,10 @@ enum {
SM_INFO, /* struct f2fs_sm_info */
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ FAULT_INFO_RATE, /* struct f2fs_fault_info */
+ FAULT_INFO_TYPE, /* struct f2fs_fault_info */
+#endif
};
struct f2fs_attr {
@@ -123,6 +153,11 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
return (unsigned char *)NM_I(sbi);
else if (struct_type == F2FS_SBI)
return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ else if (struct_type == FAULT_INFO_RATE ||
+ struct_type == FAULT_INFO_TYPE)
+ return (unsigned char *)&f2fs_fault;
+#endif
return NULL;
}
@@ -172,6 +207,10 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret < 0)
return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+ return -EINVAL;
+#endif
*ui = t;
return count;
}
@@ -237,6 +276,10 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
@@ -273,6 +316,22 @@ static struct kobj_type f2fs_ktype = {
.release = f2fs_sb_release,
};
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+/* sysfs for f2fs fault injection */
+static struct kobject f2fs_fault_inject;
+
+static struct attribute *f2fs_fault_attrs[] = {
+ ATTR_LIST(inject_rate),
+ ATTR_LIST(inject_type),
+ NULL
+};
+
+static struct kobj_type f2fs_fault_ktype = {
+ .default_attrs = f2fs_fault_attrs,
+ .sysfs_ops = &f2fs_attr_ops,
+};
+#endif
+
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
{
struct va_format vaf;
@@ -300,6 +359,10 @@ static int parse_options(struct super_block *sb, char *options)
char *p, *name;
int arg = 0;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_build_fault_attr(0);
+#endif
+
if (!options)
return 0;
@@ -433,6 +496,16 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_data_flush:
set_opt(sbi, DATA_FLUSH);
break;
+ case Opt_fault_injection:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_build_fault_attr(arg);
+#else
+ f2fs_msg(sb, KERN_INFO,
+ "FAULT_INJECTION was not selected");
+#endif
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -453,9 +526,13 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
init_once((void *) fi);
+ if (percpu_counter_init(&fi->dirty_pages, 0, GFP_NOFS)) {
+ kmem_cache_free(f2fs_inode_cachep, fi);
+ return NULL;
+ }
+
/* Initialize f2fs-specific inode info */
fi->vfs_inode.i_version = 1;
- atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
init_rwsem(&fi->i_sem);
@@ -530,15 +607,27 @@ static void f2fs_i_callback(struct rcu_head *head)
static void f2fs_destroy_inode(struct inode *inode)
{
+ percpu_counter_destroy(&F2FS_I(inode)->dirty_pages);
call_rcu(&inode->i_rcu, f2fs_i_callback);
}
+static void destroy_percpu_info(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ for (i = 0; i < NR_COUNT_TYPE; i++)
+ percpu_counter_destroy(&sbi->nr_pages[i]);
+ percpu_counter_destroy(&sbi->alloc_valid_block_count);
+ percpu_counter_destroy(&sbi->total_valid_inode_count);
+}
+
static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
@@ -568,15 +657,14 @@ static void f2fs_put_super(struct super_block *sb)
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
- release_ino_entry(sbi);
+ release_ino_entry(sbi, true);
release_discard_addrs(sbi);
f2fs_leave_shrinker(sbi);
mutex_unlock(&sbi->umount_mutex);
/* our cp_error case, we can wait for any writeback page */
- if (get_pages(sbi, F2FS_WRITEBACK))
- f2fs_flush_merged_bios(sbi);
+ f2fs_flush_merged_bios(sbi);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -593,6 +681,8 @@ static void f2fs_put_super(struct super_block *sb)
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->raw_super);
+
+ destroy_percpu_info(sbi);
kfree(sbi);
}
@@ -745,19 +835,47 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset)
return 0;
}
-static int segment_info_open_fs(struct inode *inode, struct file *file)
+static int segment_bits_seq_show(struct seq_file *seq, void *offset)
{
- return single_open(file, segment_info_seq_show, PDE_DATA(inode));
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ unsigned int total_segs =
+ le32_to_cpu(sbi->raw_super->segment_count_main);
+ int i, j;
+
+ seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+ "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+ for (i = 0; i < total_segs; i++) {
+ struct seg_entry *se = get_seg_entry(sbi, i);
+
+ seq_printf(seq, "%-10d", i);
+ seq_printf(seq, "%d|%-3u|", se->type,
+ get_valid_blocks(sbi, i, 1));
+ for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+ seq_printf(seq, "%x ", se->cur_valid_map[j]);
+ seq_putc(seq, '\n');
+ }
+ return 0;
}
-static const struct file_operations f2fs_seq_segment_info_fops = {
- .owner = THIS_MODULE,
- .open = segment_info_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
+#define F2FS_PROC_FILE_DEF(_name) \
+static int _name##_open_fs(struct inode *inode, struct file *file) \
+{ \
+ return single_open(file, _name##_seq_show, PDE_DATA(inode)); \
+} \
+ \
+static const struct file_operations f2fs_seq_##_name##_fops = { \
+ .owner = THIS_MODULE, \
+ .open = _name##_open_fs, \
+ .read = seq_read, \
+ .llseek = seq_lseek, \
+ .release = single_release, \
};
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+
static void default_options(struct f2fs_sb_info *sbi)
{
/* init some FS parameters */
@@ -791,13 +909,15 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
- if (*flags & MS_RDONLY) {
- set_opt(sbi, FASTBOOT);
- set_sbi_flag(sbi, SBI_IS_DIRTY);
+ /* recover superblocks we couldn't write due to previous RO mount */
+ if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
+ err = f2fs_commit_super(sbi, false);
+ f2fs_msg(sb, KERN_INFO,
+ "Try to recover all the superblocks, ret: %d", err);
+ if (!err)
+ clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
}
- sync_filesystem(sb);
-
sbi->mount_opt.opt = 0;
default_options(sbi);
@@ -829,7 +949,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
- f2fs_sync_fs(sb, 1);
need_restart_gc = true;
}
} else if (!sbi->gc_thread) {
@@ -839,6 +958,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
need_stop_gc = true;
}
+ if (*flags & MS_RDONLY) {
+ writeback_inodes_sb(sb, WB_REASON_SYNC);
+ sync_inodes_sb(sb);
+
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ set_sbi_flag(sbi, SBI_IS_CLOSE);
+ f2fs_sync_fs(sb, 1);
+ clear_sbi_flag(sbi, SBI_IS_CLOSE);
+ }
+
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
@@ -852,8 +981,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
}
skip:
/* Update the POSIXACL Flag */
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+
return 0;
restore_gc:
if (need_restart_gc) {
@@ -893,6 +1023,12 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
ctx, len, NULL);
}
+static int f2fs_key_prefix(struct inode *inode, u8 **key)
+{
+ *key = F2FS_I_SB(inode)->key_prefix;
+ return F2FS_I_SB(inode)->key_prefix_size;
+}
+
static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
@@ -909,6 +1045,7 @@ static unsigned f2fs_max_namelen(struct inode *inode)
static struct fscrypt_operations f2fs_cryptops = {
.get_context = f2fs_get_context,
+ .key_prefix = f2fs_key_prefix,
.set_context = f2fs_set_context,
.is_encrypted = f2fs_encrypted_inode,
.empty_dir = f2fs_empty_dir,
@@ -998,11 +1135,12 @@ static int __f2fs_commit_super(struct buffer_head *bh,
return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
}
-static inline bool sanity_check_area_boundary(struct super_block *sb,
+static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
struct buffer_head *bh)
{
struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
(bh->b_data + F2FS_SUPER_OFFSET);
+ struct super_block *sb = sbi->sb;
u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
@@ -1081,6 +1219,7 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
segment0_blkaddr) >> log_blocks_per_seg);
if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+ set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
res = "internally";
} else {
err = __f2fs_commit_super(bh, NULL);
@@ -1098,11 +1237,12 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
return false;
}
-static int sanity_check_raw_super(struct super_block *sb,
+static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
struct buffer_head *bh)
{
struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
(bh->b_data + F2FS_SUPER_OFFSET);
+ struct super_block *sb = sbi->sb;
unsigned int blocksize;
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1169,7 +1309,7 @@ static int sanity_check_raw_super(struct super_block *sb,
}
/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
- if (sanity_check_area_boundary(sb, bh))
+ if (sanity_check_area_boundary(sbi, bh))
return 1;
return 0;
@@ -1201,7 +1341,6 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
static void init_sb_info(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = sbi->raw_super;
- int i;
sbi->log_sectors_per_block =
le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1221,9 +1360,6 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
sbi->cur_victim_sec = NULL_SECNO;
sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
- for (i = 0; i < NR_COUNT_TYPE; i++)
- atomic_set(&sbi->nr_pages[i], 0);
-
sbi->dir_level = DEF_DIR_LEVEL;
sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
@@ -1231,6 +1367,30 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
INIT_LIST_HEAD(&sbi->s_list);
mutex_init(&sbi->umount_mutex);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
+ F2FS_KEY_DESC_PREFIX_SIZE);
+ sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE;
+#endif
+}
+
+static int init_percpu_info(struct f2fs_sb_info *sbi)
+{
+ int i, err;
+
+ for (i = 0; i < NR_COUNT_TYPE; i++) {
+ err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
+ if (err)
+ return err;
+ }
+
+ err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL);
+ if (err)
+ return err;
+
+ return percpu_counter_init(&sbi->total_valid_inode_count, 0,
+ GFP_KERNEL);
}
/*
@@ -1239,10 +1399,11 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
* to get the first valid one. If any one of them is broken, we pass
* them recovery flag back to the caller.
*/
-static int read_raw_super_block(struct super_block *sb,
+static int read_raw_super_block(struct f2fs_sb_info *sbi,
struct f2fs_super_block **raw_super,
int *valid_super_block, int *recovery)
{
+ struct super_block *sb = sbi->sb;
int block;
struct buffer_head *bh;
struct f2fs_super_block *super;
@@ -1262,7 +1423,7 @@ static int read_raw_super_block(struct super_block *sb,
}
/* sanity checking of raw super */
- if (sanity_check_raw_super(sb, bh)) {
+ if (sanity_check_raw_super(sbi, bh)) {
f2fs_msg(sb, KERN_ERR,
"Can't find valid F2FS filesystem in %dth superblock",
block + 1);
@@ -1298,6 +1459,12 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
struct buffer_head *bh;
int err;
+ if ((recover && f2fs_readonly(sbi->sb)) ||
+ bdev_read_only(sbi->sb->s_bdev)) {
+ set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+ return -EROFS;
+ }
+
/* write back-up superblock first */
bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
if (!bh)
@@ -1323,7 +1490,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super;
struct inode *root;
- long err;
+ int err;
bool retry = true, need_fsck = false;
char *options = NULL;
int recovery, i, valid_super_block;
@@ -1340,6 +1507,8 @@ try_onemore:
if (!sbi)
return -ENOMEM;
+ sbi->sb = sb;
+
/* Load the checksum driver */
sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
if (IS_ERR(sbi->s_chksum_driver)) {
@@ -1355,7 +1524,7 @@ try_onemore:
goto free_sbi;
}
- err = read_raw_super_block(sb, &raw_super, &valid_super_block,
+ err = read_raw_super_block(sbi, &raw_super, &valid_super_block,
&recovery);
if (err)
goto free_sbi;
@@ -1390,7 +1559,6 @@ try_onemore:
memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
- sbi->sb = sb;
sbi->raw_super = raw_super;
sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
@@ -1415,6 +1583,10 @@ try_onemore:
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
+ err = init_percpu_info(sbi);
+ if (err)
+ goto free_options;
+
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
@@ -1431,13 +1603,13 @@ try_onemore:
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
- sbi->total_valid_inode_count =
- le32_to_cpu(sbi->ckpt->valid_inode_count);
+ percpu_counter_set(&sbi->total_valid_inode_count,
+ le32_to_cpu(sbi->ckpt->valid_inode_count));
sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
- sbi->alloc_valid_block_count = 0;
+
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
spin_lock_init(&sbi->inode_lock[i]);
@@ -1515,9 +1687,12 @@ try_onemore:
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
- if (sbi->s_proc)
+ if (sbi->s_proc) {
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
+ proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_segment_bits_fops, sb);
+ }
sbi->s_kobj.kset = f2fs_kset;
init_completion(&sbi->s_kobj_unregister);
@@ -1541,14 +1716,24 @@ try_onemore:
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
- err = recover_fsync_data(sbi);
- if (err) {
+ err = recover_fsync_data(sbi, false);
+ if (err < 0) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
- "Cannot recover all fsync data errno=%ld", err);
+ "Cannot recover all fsync data errno=%d", err);
+ goto free_kobj;
+ }
+ } else {
+ err = recover_fsync_data(sbi, true);
+
+ if (!f2fs_readonly(sb) && err > 0) {
+ err = -EINVAL;
+ f2fs_msg(sb, KERN_ERR,
+ "Need to recover fsync data");
goto free_kobj;
}
}
+
/* recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -1565,10 +1750,10 @@ try_onemore:
kfree(options);
/* recover broken superblock */
- if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
+ if (recovery) {
err = f2fs_commit_super(sbi, true);
f2fs_msg(sb, KERN_INFO,
- "Try to recover %dth superblock, ret: %ld",
+ "Try to recover %dth superblock, ret: %d",
sbi->valid_super_block ? 1 : 2, err);
}
@@ -1583,6 +1768,7 @@ free_kobj:
free_proc:
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
f2fs_destroy_stats(sbi);
@@ -1603,6 +1789,7 @@ free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
free_options:
+ destroy_percpu_info(sbi);
kfree(options);
free_sb_buf:
kfree(raw_super);
@@ -1688,6 +1875,16 @@ static int __init init_f2fs_fs(void)
err = -ENOMEM;
goto free_extent_cache;
}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_fault_inject.kset = f2fs_kset;
+ f2fs_build_fault_attr(0);
+ err = kobject_init_and_add(&f2fs_fault_inject, &f2fs_fault_ktype,
+ NULL, "fault_injection");
+ if (err) {
+ f2fs_fault_inject.kset = NULL;
+ goto free_kset;
+ }
+#endif
err = register_shrinker(&f2fs_shrinker_info);
if (err)
goto free_kset;
@@ -1706,6 +1903,10 @@ free_filesystem:
free_shrinker:
unregister_shrinker(&f2fs_shrinker_info);
free_kset:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (f2fs_fault_inject.kset)
+ kobject_put(&f2fs_fault_inject);
+#endif
kset_unregister(f2fs_kset);
free_extent_cache:
destroy_extent_cache();
@@ -1725,14 +1926,17 @@ static void __exit exit_f2fs_fs(void)
{
remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
- unregister_shrinker(&f2fs_shrinker_info);
unregister_filesystem(&f2fs_fs_type);
+ unregister_shrinker(&f2fs_shrinker_info);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ kobject_put(&f2fs_fault_inject);
+#endif
+ kset_unregister(f2fs_kset);
destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();
destroy_inodecache();
- kset_unregister(f2fs_kset);
f2fs_destroy_trace_ios();
}
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 06a72dc0191a..00ea56797258 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -26,10 +26,10 @@
#include "xattr.h"
static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, void *buffer,
- size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
switch (handler->flags) {
case F2FS_XATTR_INDEX_USER:
@@ -45,7 +45,7 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
default:
return -EINVAL;
}
- return f2fs_getxattr(d_inode(dentry), handler->flags, name,
+ return f2fs_getxattr(inode, handler->flags, name,
buffer, size, NULL);
}
@@ -86,11 +86,9 @@ static bool f2fs_xattr_trusted_list(struct dentry *dentry)
}
static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, void *buffer,
- size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- struct inode *inode = d_inode(dentry);
-
if (buffer)
*((char *)buffer) = F2FS_I(inode)->i_advise;
return sizeof(char);
@@ -500,7 +498,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
free = free + ENTRY_SIZE(here);
if (unlikely(free < newsize)) {
- error = -ENOSPC;
+ error = -E2BIG;
goto exit;
}
}
@@ -528,7 +526,6 @@ static int __f2fs_setxattr(struct inode *inode, int index,
* Before we come here, old entry is removed.
* We just write new entry.
*/
- memset(last, 0, newsize);
last->e_name_index = index;
last->e_name_len = len;
memcpy(last->e_name, name, len);
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index d0b95c95079b..663e428596c6 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -769,7 +769,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file,
buf.dirent = dirent;
buf.result = 0;
- inode_lock(inode);
+ inode_lock_shared(inode);
buf.ctx.pos = file->f_pos;
ret = -ENOENT;
if (!IS_DEADDIR(inode)) {
@@ -777,7 +777,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file,
short_only, both ? &buf : NULL);
file->f_pos = buf.ctx.pos;
}
- inode_unlock(inode);
+ inode_unlock_shared(inode);
if (ret >= 0)
ret = buf.result;
return ret;
@@ -861,7 +861,7 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd,
const struct file_operations fat_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = fat_readdir,
+ .iterate_shared = fat_readdir,
.unlocked_ioctl = fat_dir_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = fat_compat_dir_ioctl,
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 226281068a46..3bcf57925dca 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -244,13 +244,13 @@ static int fat_write_end(struct file *file, struct address_space *mapping,
return err;
}
-static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
ssize_t ret;
if (iov_iter_rw(iter) == WRITE) {
@@ -272,7 +272,7 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
* FAT need to use the DIO_LOCKING for avoiding the race
* condition of fat_get_block() and ->truncate().
*/
- ret = blockdev_direct_IO(iocb, inode, iter, offset, fat_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block);
if (ret < 0 && iov_iter_rw(iter) == WRITE)
fat_write_failed(mapping, offset + count);
diff --git a/fs/file.c b/fs/file.c
index 1fbc5c0555a9..6b1acdfe59da 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -784,6 +784,11 @@ unsigned long __fdget_pos(unsigned int fd)
return v;
}
+void __f_unlock_pos(struct file *f)
+{
+ mutex_unlock(&f->f_pos_lock);
+}
+
/*
* We only lock f_pos if we have threads or if the file might be
* shared with another process. In both cases we'll have an elevated
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index a49e0cfbb686..6d576b97f2c8 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -58,7 +58,7 @@ const struct inode_operations vxfs_dir_inode_ops = {
const struct file_operations vxfs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = vxfs_readdir,
+ .iterate_shared = vxfs_readdir,
};
static inline u_long
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 592cea54cea0..989a2cef6b76 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -931,7 +931,8 @@ void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
* This is WB_SYNC_NONE writeback, so if allocation fails just
* wakeup the thread for old dirty data writeback
*/
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ work = kzalloc(sizeof(*work),
+ GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN);
if (!work) {
trace_writeback_nowork(wb);
wb_wakeup(wb);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 4b855b65d457..b9419058108f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1162,7 +1162,6 @@ static int fuse_direntplus_link(struct file *file,
struct fuse_direntplus *direntplus,
u64 attr_version)
{
- int err;
struct fuse_entry_out *o = &direntplus->entry_out;
struct fuse_dirent *dirent = &direntplus->dirent;
struct dentry *parent = file->f_path.dentry;
@@ -1172,6 +1171,7 @@ static int fuse_direntplus_link(struct file *file,
struct inode *dir = d_inode(parent);
struct fuse_conn *fc;
struct inode *inode;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
if (!o->nodeid) {
/*
@@ -1204,65 +1204,61 @@ static int fuse_direntplus_link(struct file *file,
name.hash = full_name_hash(name.name, name.len);
dentry = d_lookup(parent, &name);
- if (dentry) {
+ if (!dentry) {
+retry:
+ dentry = d_alloc_parallel(parent, &name, &wq);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+ }
+ if (!d_in_lookup(dentry)) {
+ struct fuse_inode *fi;
inode = d_inode(dentry);
- if (!inode) {
- d_drop(dentry);
- } else if (get_node_id(inode) != o->nodeid ||
- ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
+ if (!inode ||
+ get_node_id(inode) != o->nodeid ||
+ ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
d_invalidate(dentry);
- } else if (is_bad_inode(inode)) {
- err = -EIO;
- goto out;
- } else {
- struct fuse_inode *fi;
- fi = get_fuse_inode(inode);
- spin_lock(&fc->lock);
- fi->nlookup++;
- spin_unlock(&fc->lock);
-
- fuse_change_attributes(inode, &o->attr,
- entry_attr_timeout(o),
- attr_version);
-
- /*
- * The other branch to 'found' comes via fuse_iget()
- * which bumps nlookup inside
- */
- goto found;
+ dput(dentry);
+ goto retry;
+ }
+ if (is_bad_inode(inode)) {
+ dput(dentry);
+ return -EIO;
}
- dput(dentry);
- }
-
- dentry = d_alloc(parent, &name);
- err = -ENOMEM;
- if (!dentry)
- goto out;
- inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
- &o->attr, entry_attr_timeout(o), attr_version);
- if (!inode)
- goto out;
+ fi = get_fuse_inode(inode);
+ spin_lock(&fc->lock);
+ fi->nlookup++;
+ spin_unlock(&fc->lock);
- alias = d_splice_alias(inode, dentry);
- err = PTR_ERR(alias);
- if (IS_ERR(alias))
- goto out;
+ fuse_change_attributes(inode, &o->attr,
+ entry_attr_timeout(o),
+ attr_version);
+ /*
+ * The other branch comes via fuse_iget()
+ * which bumps nlookup inside
+ */
+ } else {
+ inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
+ &o->attr, entry_attr_timeout(o),
+ attr_version);
+ if (!inode)
+ inode = ERR_PTR(-ENOMEM);
- if (alias) {
- dput(dentry);
- dentry = alias;
+ alias = d_splice_alias(inode, dentry);
+ d_lookup_done(dentry);
+ if (alias) {
+ dput(dentry);
+ dentry = alias;
+ }
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
}
-
-found:
if (fc->readdirplus_auto)
set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
fuse_change_entry_timeout(dentry, o);
- err = 0;
-out:
dput(dentry);
- return err;
+ return 0;
}
static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file,
@@ -1759,10 +1755,9 @@ static int fuse_setxattr(struct dentry *entry, const char *name,
return err;
}
-static ssize_t fuse_getxattr(struct dentry *entry, const char *name,
- void *value, size_t size)
+static ssize_t fuse_getxattr(struct dentry *entry, struct inode *inode,
+ const char *name, void *value, size_t size)
{
- struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
FUSE_ARGS(args);
struct fuse_getxattr_in inarg;
@@ -1893,7 +1888,7 @@ static const struct inode_operations fuse_dir_inode_operations = {
static const struct file_operations fuse_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = fuse_readdir,
+ .iterate_shared = fuse_readdir,
.open = fuse_dir_open,
.release = fuse_dir_release,
.fsync = fuse_dir_fsync,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 719924d6c706..9154f8679024 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1186,7 +1186,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (iocb->ki_flags & IOCB_DIRECT) {
loff_t pos = iocb->ki_pos;
- written = generic_file_direct_write(iocb, from, pos);
+ written = generic_file_direct_write(iocb, from);
if (written < 0 || !iov_iter_count(from))
goto out;
@@ -1295,7 +1295,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
*nbytesp = nbytes;
- return ret;
+ return ret < 0 ? ret : 0;
}
static inline int fuse_iter_npages(const struct iov_iter *ii_p)
@@ -2837,7 +2837,7 @@ static inline loff_t fuse_round_up(loff_t off)
}
static ssize_t
-fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
DECLARE_COMPLETION_ONSTACK(wait);
ssize_t ret = 0;
@@ -2848,6 +2848,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
struct inode *inode;
loff_t i_size;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
struct fuse_io_priv *io;
bool is_sync = is_sync_kiocb(iocb);
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 791932617d1a..363ba9e9d8d0 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -24,6 +24,7 @@
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
+#include "rgrp.h"
#include "trans.h"
#include "util.h"
@@ -38,7 +39,7 @@ static const char *gfs2_acl_name(int type)
return NULL;
}
-struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
+static struct posix_acl *__gfs2_get_acl(struct inode *inode, int type)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct posix_acl *acl;
@@ -50,29 +51,41 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
return NULL;
name = gfs2_acl_name(type);
- if (name == NULL)
- return ERR_PTR(-EINVAL);
-
len = gfs2_xattr_acl_get(ip, name, &data);
- if (len < 0)
+ if (len <= 0)
return ERR_PTR(len);
- if (len == 0)
- return NULL;
-
acl = posix_acl_from_xattr(&init_user_ns, data, len);
kfree(data);
return acl;
}
-int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ bool need_unlock = false;
+ struct posix_acl *acl;
+
+ if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+ int ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+ LM_FLAG_ANY, &gh);
+ if (ret)
+ return ERR_PTR(ret);
+ need_unlock = true;
+ }
+ acl = __gfs2_get_acl(inode, type);
+ if (need_unlock)
+ gfs2_glock_dq_uninit(&gh);
+ return acl;
+}
+
+int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int error;
int len;
char *data;
const char *name = gfs2_acl_name(type);
- BUG_ON(name == NULL);
-
if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
return -E2BIG;
@@ -115,3 +128,26 @@ out:
kfree(data);
return error;
}
+
+int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ bool need_unlock = false;
+ int ret;
+
+ ret = gfs2_rsqa_alloc(ip);
+ if (ret)
+ return ret;
+
+ if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+ ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ if (ret)
+ return ret;
+ need_unlock = true;
+ }
+ ret = __gfs2_set_acl(inode, acl, type);
+ if (need_unlock)
+ gfs2_glock_dq_uninit(&gh);
+ return ret;
+}
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 3af4f407a483..f674fdd22337 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -15,6 +15,7 @@
#define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
+extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
#endif /* __ACL_DOT_H__ */
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1bbbee945f46..37b7bc14c8da 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -977,7 +977,7 @@ static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
if (!list_empty(&bd->bd_list) && !buffer_pinned(bh))
list_del_init(&bd->bd_list);
else
- gfs2_remove_from_journal(bh, current->journal_info, 0);
+ gfs2_remove_from_journal(bh, REMOVE_JDATA);
}
bh->b_bdev = NULL;
clear_buffer_mapped(bh);
@@ -1042,13 +1042,13 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset)
-static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
+ loff_t offset = iocb->ki_pos;
struct gfs2_holder gh;
int rv;
@@ -1063,7 +1063,7 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
rv = gfs2_glock_nq(&gh);
if (rv)
- return rv;
+ goto out_uninit;
rv = gfs2_ok_for_dio(ip, offset);
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
@@ -1099,9 +1099,10 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
}
rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
- offset, gfs2_get_block_direct, NULL, NULL, 0);
+ gfs2_get_block_direct, NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
+out_uninit:
gfs2_holder_uninit(&gh);
return rv;
}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 208efc70ad49..e0f98e483aec 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -160,7 +160,7 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
error = gfs2_glock_nq(&gh);
if (error)
- return error;
+ goto out_uninit;
fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_diskflags);
if (!S_ISDIR(inode->i_mode) && ip->i_diskflags & GFS2_DIF_JDATA)
@@ -169,6 +169,7 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
error = -EFAULT;
gfs2_glock_dq(&gh);
+out_uninit:
gfs2_holder_uninit(&gh);
return error;
}
@@ -895,7 +896,10 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t
mark_inode_dirty(inode);
}
- return generic_write_sync(file, pos, count);
+ if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host))
+ return vfs_fsync_range(file, pos, pos + count - 1,
+ (file->f_flags & __O_SYNC) ? 0 : 1);
+ return 0;
out_trans_fail:
gfs2_inplace_release(ip);
@@ -950,6 +954,30 @@ out_uninit:
return ret;
}
+static ssize_t gfs2_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct inode *inode = in->f_mapping->host;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ inode_lock(inode);
+
+ ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+ if (ret) {
+ inode_unlock(inode);
+ return ret;
+ }
+
+ gfs2_glock_dq_uninit(&gh);
+ inode_unlock(inode);
+
+ return generic_file_splice_read(in, ppos, pipe, len, flags);
+}
+
+
static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
@@ -1112,14 +1140,14 @@ const struct file_operations gfs2_file_fops = {
.fsync = gfs2_fsync,
.lock = gfs2_lock,
.flock = gfs2_flock,
- .splice_read = generic_file_splice_read,
+ .splice_read = gfs2_file_splice_read,
.splice_write = gfs2_file_splice_write,
.setlease = simple_nosetlease,
.fallocate = gfs2_fallocate,
};
const struct file_operations gfs2_dir_fops = {
- .iterate = gfs2_readdir,
+ .iterate_shared = gfs2_readdir,
.unlocked_ioctl = gfs2_ioctl,
.open = gfs2_open,
.release = gfs2_release,
@@ -1140,14 +1168,14 @@ const struct file_operations gfs2_file_fops_nolock = {
.open = gfs2_open,
.release = gfs2_release,
.fsync = gfs2_fsync,
- .splice_read = generic_file_splice_read,
+ .splice_read = gfs2_file_splice_read,
.splice_write = gfs2_file_splice_write,
.setlease = generic_setlease,
.fallocate = gfs2_fallocate,
};
const struct file_operations gfs2_dir_fops_nolock = {
- .iterate = gfs2_readdir,
+ .iterate_shared = gfs2_readdir,
.unlocked_ioctl = gfs2_ioctl,
.open = gfs2_open,
.release = gfs2_release,
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 6539131c52a2..706fd9352f36 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -218,7 +218,7 @@ static void gfs2_holder_wake(struct gfs2_holder *gh)
*
*/
-static inline void do_error(struct gfs2_glock *gl, const int ret)
+static void do_error(struct gfs2_glock *gl, const int ret)
{
struct gfs2_holder *gh, *tmp;
@@ -475,7 +475,14 @@ __acquires(&gl->gl_lockref.lock)
if (sdp->sd_lockstruct.ls_ops->lm_lock) {
/* lock_dlm */
ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
- if (ret) {
+ if (ret == -EINVAL && gl->gl_target == LM_ST_UNLOCKED &&
+ target == LM_ST_UNLOCKED &&
+ test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) {
+ finish_xmote(gl, target);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
+ }
+ else if (ret) {
pr_err("lm_lock ret %d\n", ret);
GLOCK_BUG_ON(gl, 1);
}
@@ -1913,7 +1920,7 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file)
if (seq->buf)
seq->size = GFS2_SEQ_GOODSIZE;
gi->gl = NULL;
- ret = rhashtable_walk_init(&gl_hash_table, &gi->hti);
+ ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
}
return ret;
}
@@ -1941,7 +1948,7 @@ static int gfs2_glstats_open(struct inode *inode, struct file *file)
if (seq->buf)
seq->size = GFS2_SEQ_GOODSIZE;
gi->gl = NULL;
- ret = rhashtable_walk_init(&gl_hash_table, &gi->hti);
+ ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
}
return ret;
}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 437fd73e381e..5db59d444838 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -286,17 +286,10 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
static int inode_go_demote_ok(const struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct gfs2_holder *gh;
if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
return 0;
- if (!list_empty(&gl->gl_holders)) {
- gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
- if (gh->gh_list.next != &gl->gl_holders)
- return 0;
- }
-
return 1;
}
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index bb30f9a72c65..21dc784f66c2 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -93,12 +93,12 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
int error;
inode = iget_locked(sb, (unsigned long)no_addr);
- ip = GFS2_I(inode);
- ip->i_no_addr = no_addr;
-
if (!inode)
return ERR_PTR(-ENOMEM);
+ ip = GFS2_I(inode);
+ ip->i_no_addr = no_addr;
+
if (inode->i_state & I_NEW) {
struct gfs2_sbd *sdp = GFS2_SB(inode);
ip->i_no_formal_ino = no_formal_ino;
@@ -692,12 +692,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
considered free. Any failures need to undo
the gfs2 structures. */
if (default_acl) {
- error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+ error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
posix_acl_release(default_acl);
}
if (acl) {
if (!error)
- error = gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS);
+ error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS);
posix_acl_release(acl);
}
@@ -1948,67 +1948,6 @@ static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
return 0;
}
-static int gfs2_setxattr(struct dentry *dentry, const char *name,
- const void *data, size_t size, int flags)
-{
- struct inode *inode = d_inode(dentry);
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
- ret = gfs2_glock_nq(&gh);
- if (ret == 0) {
- ret = gfs2_rsqa_alloc(ip);
- if (ret == 0)
- ret = generic_setxattr(dentry, name, data, size, flags);
- gfs2_glock_dq(&gh);
- }
- gfs2_holder_uninit(&gh);
- return ret;
-}
-
-static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
- void *data, size_t size)
-{
- struct inode *inode = d_inode(dentry);
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- /* For selinux during lookup */
- if (gfs2_glock_is_locked_by_me(ip->i_gl))
- return generic_getxattr(dentry, name, data, size);
-
- gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
- ret = gfs2_glock_nq(&gh);
- if (ret == 0) {
- ret = generic_getxattr(dentry, name, data, size);
- gfs2_glock_dq(&gh);
- }
- gfs2_holder_uninit(&gh);
- return ret;
-}
-
-static int gfs2_removexattr(struct dentry *dentry, const char *name)
-{
- struct inode *inode = d_inode(dentry);
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
- ret = gfs2_glock_nq(&gh);
- if (ret == 0) {
- ret = gfs2_rsqa_alloc(ip);
- if (ret == 0)
- ret = generic_removexattr(dentry, name);
- gfs2_glock_dq(&gh);
- }
- gfs2_holder_uninit(&gh);
- return ret;
-}
-
static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
@@ -2055,10 +1994,10 @@ const struct inode_operations gfs2_file_iops = {
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
- .setxattr = gfs2_setxattr,
- .getxattr = gfs2_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = gfs2_listxattr,
- .removexattr = gfs2_removexattr,
+ .removexattr = generic_removexattr,
.fiemap = gfs2_fiemap,
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
@@ -2077,10 +2016,10 @@ const struct inode_operations gfs2_dir_iops = {
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
- .setxattr = gfs2_setxattr,
- .getxattr = gfs2_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = gfs2_listxattr,
- .removexattr = gfs2_removexattr,
+ .removexattr = generic_removexattr,
.fiemap = gfs2_fiemap,
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
@@ -2093,10 +2032,10 @@ const struct inode_operations gfs2_symlink_iops = {
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
- .setxattr = gfs2_setxattr,
- .getxattr = gfs2_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = gfs2_listxattr,
- .removexattr = gfs2_removexattr,
+ .removexattr = generic_removexattr,
.fiemap = gfs2_fiemap,
};
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 0448524c11bc..8eaadabbc771 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -325,18 +325,19 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
return 0;
}
-void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
+void gfs2_remove_from_journal(struct buffer_head *bh, int meta)
{
struct address_space *mapping = bh->b_page->mapping;
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
struct gfs2_bufdata *bd = bh->b_private;
+ struct gfs2_trans *tr = current->journal_info;
int was_pinned = 0;
if (test_clear_buffer_pinned(bh)) {
trace_gfs2_pin(bd, 0);
atomic_dec(&sdp->sd_log_pinned);
list_del_init(&bd->bd_list);
- if (meta)
+ if (meta == REMOVE_META)
tr->tr_num_buf_rm++;
else
tr->tr_num_databuf_rm++;
@@ -376,7 +377,7 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
if (bh) {
lock_buffer(bh);
gfs2_log_lock(sdp);
- gfs2_remove_from_journal(bh, current->journal_info, 1);
+ gfs2_remove_from_journal(bh, REMOVE_META);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
brelse(bh);
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index c5086c8af5ed..ffdf6aa3509d 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -57,8 +57,12 @@ extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno,
int create);
-extern void gfs2_remove_from_journal(struct buffer_head *bh,
- struct gfs2_trans *tr, int meta);
+enum {
+ REMOVE_JDATA = 0,
+ REMOVE_META = 1,
+};
+
+extern void gfs2_remove_from_journal(struct buffer_head *bh, int meta);
extern void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
extern int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
struct buffer_head **bhp);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 49b0bff18fe3..45463600fb81 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -824,7 +824,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
* i_mutex on quota files is special. Since this inode is hidden system
* file, we are safe to define locking ourselves.
*/
- lockdep_set_class(&sdp->sd_quota_inode->i_mutex,
+ lockdep_set_class(&sdp->sd_quota_inode->i_rwsem,
&gfs2_quota_imutex_key);
error = gfs2_rindex_update(sdp);
@@ -1360,7 +1360,7 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type,
return ERR_PTR(error);
}
s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags,
- d_inode(path.dentry)->i_sb->s_bdev);
+ path.dentry->d_sb->s_bdev);
path_put(&path);
if (IS_ERR(s)) {
pr_warn("gfs2 mount does not exist\n");
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 99a0bdac8796..5bd216901e89 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -73,8 +73,7 @@ static const char valid_change[16] = {
};
static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
- const struct gfs2_inode *ip, bool nowrap,
- const struct gfs2_alloc_parms *ap);
+ const struct gfs2_inode *ip, bool nowrap);
/**
@@ -1511,7 +1510,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
if (WARN_ON(gfs2_rbm_from_block(&rbm, goal)))
return;
- ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &extlen, ip, true, ap);
+ ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &extlen, ip, true);
if (ret == 0) {
rs->rs_rbm = rbm;
rs->rs_free = extlen;
@@ -1638,7 +1637,6 @@ fail:
* @ip: If set, check for reservations
* @nowrap: Stop looking at the end of the rgrp, rather than wrapping
* around until we've reached the starting point.
- * @ap: the allocation parameters
*
* Side effects:
* - If looking for free blocks, we set GBF_FULL on each bitmap which
@@ -1650,8 +1648,7 @@ fail:
*/
static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
- const struct gfs2_inode *ip, bool nowrap,
- const struct gfs2_alloc_parms *ap)
+ const struct gfs2_inode *ip, bool nowrap)
{
struct buffer_head *bh;
int initial_bii;
@@ -1772,7 +1769,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
while (1) {
down_write(&sdp->sd_log_flush_lock);
error = gfs2_rbm_find(&rbm, GFS2_BLKST_UNLINKED, NULL, NULL,
- true, NULL);
+ true);
up_write(&sdp->sd_log_flush_lock);
if (error == -ENOSPC)
break;
@@ -2329,12 +2326,11 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
int error;
gfs2_set_alloc_start(&rbm, ip, dinode);
- error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, ip, false, NULL);
+ error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, ip, false);
if (error == -ENOSPC) {
gfs2_set_alloc_start(&rbm, ip, dinode);
- error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, NULL, false,
- NULL);
+ error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, NULL, false);
}
/* Since all blocks are reserved in advance, this shouldn't happen */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index f8a0cd821290..9b2ff353e45f 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1176,7 +1176,7 @@ static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *s
static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
{
- struct super_block *sb = d_inode(dentry)->i_sb;
+ struct super_block *sb = dentry->d_sb;
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_statfs_change_host sc;
int error;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index cf645835710f..aee4485ad8a9 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -68,6 +68,7 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
fs_err(sdp, "telling LM to unmount\n");
lm->lm_unmount(sdp);
}
+ set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags);
fs_err(sdp, "withdrawn\n");
dump_stack();
}
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index e8dfb4740c04..f42ab53bd30d 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -583,13 +583,11 @@ out:
*
* Returns: actual size of data on success, -errno on error
*/
-static int gfs2_xattr_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+static int __gfs2_xattr_get(struct inode *inode, const char *name,
+ void *buffer, size_t size, int type)
{
- struct gfs2_inode *ip = GFS2_I(d_inode(dentry));
+ struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_ea_location el;
- int type = handler->flags;
int error;
if (!ip->i_eattr)
@@ -611,6 +609,29 @@ static int gfs2_xattr_get(const struct xattr_handler *handler,
return error;
}
+static int gfs2_xattr_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ bool need_unlock = false;
+ int ret;
+
+ /* During lookup, SELinux calls this function with the glock locked. */
+
+ if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+ ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+ if (ret)
+ return ret;
+ need_unlock = true;
+ }
+ ret = __gfs2_xattr_get(inode, name, buffer, size, handler->flags);
+ if (need_unlock)
+ gfs2_glock_dq_uninit(&gh);
+ return ret;
+}
+
/**
* ea_alloc_blk - allocates a new block for extended attributes.
* @ip: A pointer to the inode that's getting extended attributes
@@ -1233,8 +1254,21 @@ static int gfs2_xattr_set(const struct xattr_handler *handler,
struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
- return __gfs2_xattr_set(d_inode(dentry), name, value,
- size, flags, handler->flags);
+ struct inode *inode = d_inode(dentry);
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ ret = gfs2_rsqa_alloc(ip);
+ if (ret)
+ return ret;
+
+ ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ if (ret)
+ return ret;
+ ret = __gfs2_xattr_set(inode, name, value, size, flags, handler->flags);
+ gfs2_glock_dq_uninit(&gh);
+ return ret;
}
static int ea_dealloc_indirect(struct gfs2_inode *ip)
diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c
index 8d931b157bbe..064f92f17efc 100644
--- a/fs/hfs/attr.c
+++ b/fs/hfs/attr.c
@@ -56,10 +56,9 @@ out:
return res;
}
-ssize_t hfs_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size)
+ssize_t hfs_getxattr(struct dentry *unused, struct inode *inode,
+ const char *name, void *value, size_t size)
{
- struct inode *inode = d_inode(dentry);
struct hfs_find_data fd;
hfs_cat_rec rec;
struct hfs_cat_file *file;
diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c
index 1eb5d415d434..98cde8ba5dc2 100644
--- a/fs/hfs/catalog.c
+++ b/fs/hfs/catalog.c
@@ -240,10 +240,13 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str)
}
}
+ /* we only need to take spinlock for exclusion with ->release() */
+ spin_lock(&HFS_I(dir)->open_dir_lock);
list_for_each_entry(rd, &HFS_I(dir)->open_dir_list, list) {
if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
rd->file->f_pos--;
}
+ spin_unlock(&HFS_I(dir)->open_dir_lock);
res = hfs_brec_remove(&fd);
if (res)
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index e9f2b855f831..163190ecc0d2 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -161,8 +161,14 @@ static int hfs_readdir(struct file *file, struct dir_context *ctx)
}
file->private_data = rd;
rd->file = file;
+ spin_lock(&HFS_I(inode)->open_dir_lock);
list_add(&rd->list, &HFS_I(inode)->open_dir_list);
+ spin_unlock(&HFS_I(inode)->open_dir_lock);
}
+ /*
+ * Can be done after the list insertion; exclusion with
+ * hfs_delete_cat() is provided by directory lock.
+ */
memcpy(&rd->key, &fd.key, sizeof(struct hfs_cat_key));
out:
hfs_find_exit(&fd);
@@ -173,9 +179,9 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
{
struct hfs_readdir_data *rd = file->private_data;
if (rd) {
- inode_lock(inode);
+ spin_lock(&HFS_I(inode)->open_dir_lock);
list_del(&rd->list);
- inode_unlock(inode);
+ spin_unlock(&HFS_I(inode)->open_dir_lock);
kfree(rd);
}
return 0;
@@ -303,7 +309,7 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry,
const struct file_operations hfs_dir_operations = {
.read = generic_read_dir,
- .iterate = hfs_readdir,
+ .iterate_shared = hfs_readdir,
.llseek = generic_file_llseek,
.release = hfs_dir_release,
};
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 1f1c7dcbcc2f..fa3eed86837c 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -69,6 +69,7 @@ struct hfs_inode_info {
struct hfs_cat_key cat_key;
struct list_head open_dir_list;
+ spinlock_t open_dir_lock;
struct inode *rsrc_inode;
struct mutex extents_lock;
@@ -213,8 +214,8 @@ extern void hfs_delete_inode(struct inode *);
/* attr.c */
extern int hfs_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags);
-extern ssize_t hfs_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size);
+extern ssize_t hfs_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size);
extern ssize_t hfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
/* mdb.c */
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index cb1e5faa2fb7..8eed66af5b82 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -124,8 +124,7 @@ static int hfs_releasepage(struct page *page, gfp_t mask)
return res ? try_to_free_buffers(page) : 0;
}
-static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -133,7 +132,7 @@ static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
size_t count = iov_iter_count(iter);
ssize_t ret;
- ret = blockdev_direct_IO(iocb, inode, iter, offset, hfs_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, hfs_get_block);
/*
* In case of error extending write may have instantiated a few
@@ -141,7 +140,7 @@ static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
*/
if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + count;
+ loff_t end = iocb->ki_pos + count;
if (end > isize)
hfs_write_failed(mapping, end);
@@ -187,6 +186,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, umode_t mode)
mutex_init(&HFS_I(inode)->extents_lock);
INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list);
+ spin_lock_init(&HFS_I(inode)->open_dir_lock);
hfs_cat_build_key(sb, (btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name);
inode->i_ino = HFS_SB(sb)->next_id++;
inode->i_mode = mode;
@@ -318,6 +318,7 @@ static int hfs_read_inode(struct inode *inode, void *data)
HFS_I(inode)->rsrc_inode = NULL;
mutex_init(&HFS_I(inode)->extents_lock);
INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list);
+ spin_lock_init(&HFS_I(inode)->open_dir_lock);
/* Initialize the inode */
inode->i_uid = hsb->s_uid;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 022974ab6e3c..fb707e8f423a 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -374,12 +374,15 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC);
}
+ /* we only need to take spinlock for exclusion with ->release() */
+ spin_lock(&HFSPLUS_I(dir)->open_dir_lock);
list_for_each(pos, &HFSPLUS_I(dir)->open_dir_list) {
struct hfsplus_readdir_data *rd =
list_entry(pos, struct hfsplus_readdir_data, list);
if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
rd->file->f_pos--;
}
+ spin_unlock(&HFSPLUS_I(dir)->open_dir_lock);
err = hfs_brec_remove(&fd);
if (err)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index a4e867e08947..42e128661dc1 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -271,8 +271,14 @@ next:
}
file->private_data = rd;
rd->file = file;
+ spin_lock(&HFSPLUS_I(inode)->open_dir_lock);
list_add(&rd->list, &HFSPLUS_I(inode)->open_dir_list);
+ spin_unlock(&HFSPLUS_I(inode)->open_dir_lock);
}
+ /*
+ * Can be done after the list insertion; exclusion with
+ * hfsplus_delete_cat() is provided by directory lock.
+ */
memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key));
out:
kfree(strbuf);
@@ -284,9 +290,9 @@ static int hfsplus_dir_release(struct inode *inode, struct file *file)
{
struct hfsplus_readdir_data *rd = file->private_data;
if (rd) {
- inode_lock(inode);
+ spin_lock(&HFSPLUS_I(inode)->open_dir_lock);
list_del(&rd->list);
- inode_unlock(inode);
+ spin_unlock(&HFSPLUS_I(inode)->open_dir_lock);
kfree(rd);
}
return 0;
@@ -569,7 +575,7 @@ const struct inode_operations hfsplus_dir_inode_operations = {
const struct file_operations hfsplus_dir_operations = {
.fsync = hfsplus_file_fsync,
.read = generic_read_dir,
- .iterate = hfsplus_readdir,
+ .iterate_shared = hfsplus_readdir,
.unlocked_ioctl = hfsplus_ioctl,
.llseek = generic_file_llseek,
.release = hfsplus_dir_release,
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index f91a1faf819e..fdc3446d934a 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -244,6 +244,7 @@ struct hfsplus_inode_info {
u8 userflags; /* BSD user file flags */
u32 subfolders; /* Subfolder count (HFSX only) */
struct list_head open_dir_list;
+ spinlock_t open_dir_lock;
loff_t phys_size;
struct inode vfs_inode;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index b28f39865c3a..ef9fefe364a6 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -122,8 +122,7 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
return res ? try_to_free_buffers(page) : 0;
}
-static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -131,7 +130,7 @@ static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
size_t count = iov_iter_count(iter);
ssize_t ret;
- ret = blockdev_direct_IO(iocb, inode, iter, offset, hfsplus_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, hfsplus_get_block);
/*
* In case of error extending write may have instantiated a few
@@ -139,7 +138,7 @@ static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
*/
if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + count;
+ loff_t end = iocb->ki_pos + count;
if (end > isize)
hfsplus_write_failed(mapping, end);
@@ -374,6 +373,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode)
hip = HFSPLUS_I(inode);
INIT_LIST_HEAD(&hip->open_dir_list);
+ spin_lock_init(&hip->open_dir_lock);
mutex_init(&hip->extents_lock);
atomic_set(&hip->opencnt, 0);
hip->extent_state = 0;
diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c
index afb33eda6d7d..ab7ea2506b4d 100644
--- a/fs/hfsplus/posix_acl.c
+++ b/fs/hfsplus/posix_acl.c
@@ -48,9 +48,6 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type)
hfsplus_destroy_attr_entry((hfsplus_attr_entry *)value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index c35911362ff9..755bf30ba1ce 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -67,6 +67,7 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
return inode;
INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
+ spin_lock_init(&HFSPLUS_I(inode)->open_dir_lock);
mutex_init(&HFSPLUS_I(inode)->extents_lock);
HFSPLUS_I(inode)->flags = 0;
HFSPLUS_I(inode)->extent_state = 0;
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index 70e445ff0cff..4f118d282a7a 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -579,7 +579,7 @@ failed_getxattr_init:
return res;
}
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ssize_t hfsplus_getxattr(struct inode *inode, const char *name,
void *value, size_t size,
const char *prefix, size_t prefixlen)
{
@@ -594,7 +594,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
strcpy(xattr_name, prefix);
strcpy(xattr_name + prefixlen, name);
- res = __hfsplus_getxattr(d_inode(dentry), xattr_name, value, size);
+ res = __hfsplus_getxattr(inode, xattr_name, value, size);
kfree(xattr_name);
return res;
@@ -844,8 +844,8 @@ end_removexattr:
}
static int hfsplus_osx_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
/*
* Don't allow retrieving properly prefixed attributes
@@ -860,7 +860,7 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler,
* creates), so we pass the name through unmodified (after
* ensuring it doesn't conflict with another namespace).
*/
- return __hfsplus_getxattr(d_inode(dentry), name, buffer, size);
+ return __hfsplus_getxattr(inode, name, buffer, size);
}
static int hfsplus_osx_setxattr(const struct xattr_handler *handler,
diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h
index f9b0955b3d28..d04ba6f58df2 100644
--- a/fs/hfsplus/xattr.h
+++ b/fs/hfsplus/xattr.h
@@ -28,7 +28,7 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name,
ssize_t __hfsplus_getxattr(struct inode *inode, const char *name,
void *value, size_t size);
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ssize_t hfsplus_getxattr(struct inode *inode, const char *name,
void *value, size_t size,
const char *prefix, size_t prefixlen);
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
index 72a68a3a0c99..ae2ca8c2e335 100644
--- a/fs/hfsplus/xattr_security.c
+++ b/fs/hfsplus/xattr_security.c
@@ -14,10 +14,10 @@
#include "acl.h"
static int hfsplus_security_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return hfsplus_getxattr(dentry, name, buffer, size,
+ return hfsplus_getxattr(inode, name, buffer, size,
XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
}
diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c
index 95a7704c7abb..eae2947060aa 100644
--- a/fs/hfsplus/xattr_trusted.c
+++ b/fs/hfsplus/xattr_trusted.c
@@ -12,10 +12,10 @@
#include "xattr.h"
static int hfsplus_trusted_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return hfsplus_getxattr(dentry, name, buffer, size,
+ return hfsplus_getxattr(inode, name, buffer, size,
XATTR_TRUSTED_PREFIX,
XATTR_TRUSTED_PREFIX_LEN);
}
diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c
index 6fc269baf959..3c9eec3e4c7b 100644
--- a/fs/hfsplus/xattr_user.c
+++ b/fs/hfsplus/xattr_user.c
@@ -12,11 +12,11 @@
#include "xattr.h"
static int hfsplus_user_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return hfsplus_getxattr(dentry, name, buffer, size,
+ return hfsplus_getxattr(inode, name, buffer, size,
XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
}
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 7016653f3e41..5c57654927a6 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -398,7 +398,7 @@ static const struct file_operations hostfs_file_fops = {
static const struct file_operations hostfs_dir_fops = {
.llseek = generic_file_llseek,
- .iterate = hostfs_readdir,
+ .iterate_shared = hostfs_readdir,
.read = generic_read_dir,
.open = hostfs_open,
.fsync = hostfs_fsync,
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index e57a53c13d86..7b9150c2e75c 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -44,7 +44,11 @@ static loff_t hpfs_dir_lseek(struct file *filp, loff_t off, int whence)
else goto fail;
if (pos == 12) goto fail;
}
- hpfs_add_pos(i, &filp->f_pos);
+ if (unlikely(hpfs_add_pos(i, &filp->f_pos) < 0)) {
+ hpfs_unlock(s);
+ inode_unlock(i);
+ return -ENOMEM;
+ }
ok:
filp->f_pos = new_off;
hpfs_unlock(s);
@@ -141,8 +145,10 @@ static int hpfs_readdir(struct file *file, struct dir_context *ctx)
ctx->pos = 1;
}
if (ctx->pos == 1) {
+ ret = hpfs_add_pos(inode, &file->f_pos);
+ if (unlikely(ret < 0))
+ goto out;
ctx->pos = ((loff_t) hpfs_de_as_down_as_possible(inode->i_sb, hpfs_inode->i_dno) << 4) + 1;
- hpfs_add_pos(inode, &file->f_pos);
file->f_version = inode->i_version;
}
next_pos = ctx->pos;
@@ -324,7 +330,7 @@ const struct file_operations hpfs_dir_ops =
{
.llseek = hpfs_dir_lseek,
.read = generic_read_dir,
- .iterate = hpfs_readdir,
+ .iterate_shared = hpfs_readdir,
.release = hpfs_dir_release,
.fsync = hpfs_file_fsync,
.unlocked_ioctl = hpfs_ioctl,
diff --git a/fs/hpfs/dnode.c b/fs/hpfs/dnode.c
index 2923a7bd82ac..86ab7e790b4e 100644
--- a/fs/hpfs/dnode.c
+++ b/fs/hpfs/dnode.c
@@ -21,7 +21,7 @@ static loff_t get_pos(struct dnode *d, struct hpfs_dirent *fde)
return ((loff_t)le32_to_cpu(d->self) << 4) | (loff_t)1;
}
-void hpfs_add_pos(struct inode *inode, loff_t *pos)
+int hpfs_add_pos(struct inode *inode, loff_t *pos)
{
struct hpfs_inode_info *hpfs_inode = hpfs_i(inode);
int i = 0;
@@ -29,11 +29,12 @@ void hpfs_add_pos(struct inode *inode, loff_t *pos)
if (hpfs_inode->i_rddir_off)
for (; hpfs_inode->i_rddir_off[i]; i++)
- if (hpfs_inode->i_rddir_off[i] == pos) return;
+ if (hpfs_inode->i_rddir_off[i] == pos)
+ return 0;
if (!(i&0x0f)) {
if (!(ppos = kmalloc((i+0x11) * sizeof(loff_t*), GFP_NOFS))) {
pr_err("out of memory for position list\n");
- return;
+ return -ENOMEM;
}
if (hpfs_inode->i_rddir_off) {
memcpy(ppos, hpfs_inode->i_rddir_off, i * sizeof(loff_t));
@@ -43,6 +44,7 @@ void hpfs_add_pos(struct inode *inode, loff_t *pos)
}
hpfs_inode->i_rddir_off[i] = pos;
hpfs_inode->i_rddir_off[i + 1] = NULL;
+ return 0;
}
void hpfs_del_pos(struct inode *inode, loff_t *pos)
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index 975654a63c13..aebb78f9e47f 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -242,7 +242,7 @@ extern const struct file_operations hpfs_dir_ops;
/* dnode.c */
-void hpfs_add_pos(struct inode *, loff_t *);
+int hpfs_add_pos(struct inode *, loff_t *);
void hpfs_del_pos(struct inode *, loff_t *);
struct hpfs_dirent *hpfs_add_de(struct super_block *, struct dnode *,
const unsigned char *, unsigned, secno);
diff --git a/fs/inode.c b/fs/inode.c
index 69b8b526c194..4ccbc21b30ce 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -151,6 +151,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
inode->i_bdev = NULL;
inode->i_cdev = NULL;
inode->i_link = NULL;
+ inode->i_dir_seq = 0;
inode->i_rdev = 0;
inode->dirtied_when = 0;
@@ -165,8 +166,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
spin_lock_init(&inode->i_lock);
lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
- mutex_init(&inode->i_mutex);
- lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
+ init_rwsem(&inode->i_rwsem);
+ lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key);
atomic_set(&inode->i_dio_count, 0);
@@ -238,9 +239,9 @@ void __destroy_inode(struct inode *inode)
}
#ifdef CONFIG_FS_POSIX_ACL
- if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED)
+ if (inode->i_acl && !is_uncached_acl(inode->i_acl))
posix_acl_release(inode->i_acl);
- if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
+ if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl))
posix_acl_release(inode->i_default_acl);
#endif
this_cpu_dec(nr_inodes);
@@ -924,13 +925,13 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode)
struct file_system_type *type = inode->i_sb->s_type;
/* Set new key only if filesystem hasn't already changed it */
- if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) {
+ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
/*
* ensure nobody is actually holding i_mutex
*/
- mutex_destroy(&inode->i_mutex);
- mutex_init(&inode->i_mutex);
- lockdep_set_class(&inode->i_mutex,
+ // mutex_destroy(&inode->i_mutex);
+ init_rwsem(&inode->i_rwsem);
+ lockdep_set_class(&inode->i_rwsem,
&type->i_mutex_dir_key);
}
}
diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c
index b943cbd963bb..e7599615e4e0 100644
--- a/fs/isofs/dir.c
+++ b/fs/isofs/dir.c
@@ -58,7 +58,7 @@ int get_acorn_filename(struct iso_directory_record *de,
std = sizeof(struct iso_directory_record) + de->name_len[0];
if (std & 1)
std++;
- if ((*((unsigned char *) de) - std) != 32)
+ if (de->length[0] - std != 32)
return retnamlen;
chr = ((unsigned char *) de) + std;
if (strncmp(chr, "ARCHIMEDES", 10))
@@ -269,7 +269,7 @@ const struct file_operations isofs_dir_operations =
{
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = isofs_readdir,
+ .iterate_shared = isofs_readdir,
};
/*
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 5384ceb35b1c..98b3eb7d8eaf 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -203,6 +203,8 @@ int get_rock_ridge_filename(struct iso_directory_record *de,
int retnamlen = 0;
int truncate = 0;
int ret = 0;
+ char *p;
+ int len;
if (!ISOFS_SB(inode->i_sb)->s_rock)
return 0;
@@ -267,12 +269,17 @@ repeat:
rr->u.NM.flags);
break;
}
- if ((strlen(retname) + rr->len - 5) >= 254) {
+ len = rr->len - 5;
+ if (retnamlen + len >= 254) {
truncate = 1;
break;
}
- strncat(retname, rr->u.NM.name, rr->len - 5);
- retnamlen += rr->len - 5;
+ p = memchr(rr->u.NM.name, '\0', len);
+ if (unlikely(p))
+ len = p - rr->u.NM.name;
+ memcpy(retname + retnamlen, rr->u.NM.name, len);
+ retnamlen += len;
+ retname[retnamlen] = '\0';
break;
case SIG('R', 'E'):
kfree(rs.buffer);
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 08a456b96e4e..805bc6bcd8ab 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -303,7 +303,7 @@ int jbd2_journal_recover(journal_t *journal)
* Locate any valid recovery information from the journal and set up the
* journal structures in memory to ignore it (presumably because the
* caller has evidence that it is out of date).
- * This function does'nt appear to be exorted..
+ * This function doesn't appear to be exported..
*
* We perform one pass over the journal to allow us to tell the user how
* much recovery information is being erased, and to let us initialise
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index be56c8ca34c2..1749519b362f 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -543,7 +543,7 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved);
*
* Some transactions, such as large extends and truncates, can be done
* atomically all at once or in several stages. The operation requests
- * a credit for a number of buffer modications in advance, but can
+ * a credit for a number of buffer modifications in advance, but can
* extend its credit if it needs more.
*
* jbd2_journal_extend tries to give the running handle more buffer credits.
@@ -627,7 +627,7 @@ error_out:
* If the jbd2_journal_extend() call above fails to grant new buffer credits
* to a running handle, a call to jbd2_journal_restart will commit the
* handle's transaction so far and reattach the handle to a new
- * transaction capabable of guaranteeing the requested number of
+ * transaction capable of guaranteeing the requested number of
* credits. We preserve reserved handle if there's any attached to the
* passed in handle.
*/
@@ -1586,7 +1586,7 @@ drop:
/**
* int jbd2_journal_stop() - complete a transaction
- * @handle: tranaction to complete.
+ * @handle: transaction to complete.
*
* All done for a particular handle.
*
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 2f7a3c090489..bc2693d56298 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -203,8 +203,6 @@ struct posix_acl *jffs2_get_acl(struct inode *inode, int type)
acl = ERR_PTR(rc);
}
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
return acl;
}
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 30c4c9ebb693..84c4bf3631a2 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -40,7 +40,7 @@ static int jffs2_rename (struct inode *, struct dentry *,
const struct file_operations jffs2_dir_operations =
{
.read = generic_read_dir,
- .iterate = jffs2_readdir,
+ .iterate_shared=jffs2_readdir,
.unlocked_ioctl=jffs2_ioctl,
.fsync = jffs2_fsync,
.llseek = generic_file_llseek,
@@ -241,7 +241,7 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry)
static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct dentry *dentry)
{
- struct jffs2_sb_info *c = JFFS2_SB_INFO(d_inode(old_dentry)->i_sb);
+ struct jffs2_sb_info *c = JFFS2_SB_INFO(old_dentry->d_sb);
struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(old_dentry));
struct jffs2_inode_info *dir_f = JFFS2_INODE_INFO(dir_i);
int ret;
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index 7a28facd7175..3ed9a4b49778 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -49,10 +49,10 @@ int jffs2_init_security(struct inode *inode, struct inode *dir,
/* ---- XATTR Handler for "security.*" ----------------- */
static int jffs2_security_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY,
+ return do_jffs2_getxattr(inode, JFFS2_XPREFIX_SECURITY,
name, buffer, size);
}
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 0a9a114bb9d1..5ef21f4c4c77 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -147,7 +147,7 @@ static struct dentry *jffs2_get_parent(struct dentry *child)
JFFS2_DEBUG("Parent of directory ino #%u is #%u\n",
f->inocache->ino, pino);
- return d_obtain_alias(jffs2_iget(d_inode(child)->i_sb, pino));
+ return d_obtain_alias(jffs2_iget(child->d_sb, pino));
}
static const struct export_operations jffs2_export_ops = {
diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c
index b2555ef07a12..4ebecff1d922 100644
--- a/fs/jffs2/xattr_trusted.c
+++ b/fs/jffs2/xattr_trusted.c
@@ -17,10 +17,10 @@
#include "nodelist.h"
static int jffs2_trusted_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED,
+ return do_jffs2_getxattr(inode, JFFS2_XPREFIX_TRUSTED,
name, buffer, size);
}
diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c
index 539bd630b5e4..bce249e1b277 100644
--- a/fs/jffs2/xattr_user.c
+++ b/fs/jffs2/xattr_user.c
@@ -17,10 +17,10 @@
#include "nodelist.h"
static int jffs2_user_getxattr(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER,
+ return do_jffs2_getxattr(inode, JFFS2_XPREFIX_USER,
name, buffer, size);
}
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 49456853e9de..21fa92ba2c19 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -34,10 +34,6 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type)
int size;
char *value = NULL;
- acl = get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
- return acl;
-
switch(type) {
case ACL_TYPE_ACCESS:
ea_name = XATTR_NAME_POSIX_ACL_ACCESS;
@@ -67,8 +63,6 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type)
acl = posix_acl_from_xattr(&init_user_ns, value, size);
}
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
return acl;
}
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 4ce7735dd042..7f1a585a0a94 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -140,10 +140,10 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr)
}
const struct inode_operations jfs_file_inode_operations = {
- .setxattr = jfs_setxattr,
- .getxattr = jfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = jfs_listxattr,
- .removexattr = jfs_removexattr,
+ .removexattr = generic_removexattr,
.setattr = jfs_setattr,
#ifdef CONFIG_JFS_POSIX_ACL
.get_acl = jfs_get_acl,
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 9d9bae63ae2a..ad3e7b1effc4 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -102,8 +102,8 @@ int jfs_commit_inode(struct inode *inode, int wait)
* partitions and may think inode is dirty
*/
if (!special_file(inode->i_mode) && noisy) {
- jfs_err("jfs_commit_inode(0x%p) called on "
- "read-only volume", inode);
+ jfs_err("jfs_commit_inode(0x%p) called on read-only volume",
+ inode);
jfs_err("Is remount racy?");
noisy--;
}
@@ -332,8 +332,7 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block)
return generic_block_bmap(mapping, block, jfs_get_block);
}
-static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -341,7 +340,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
size_t count = iov_iter_count(iter);
ssize_t ret;
- ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, jfs_get_block);
/*
* In case of error extending write may have instantiated a few
@@ -349,7 +348,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
*/
if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + count;
+ loff_t end = iocb->ki_pos + count;
if (end > isize)
jfs_write_failed(mapping, end);
diff --git a/fs/jfs/jfs_discard.c b/fs/jfs/jfs_discard.c
index dfcd50304559..f76ff0a46444 100644
--- a/fs/jfs/jfs_discard.c
+++ b/fs/jfs/jfs_discard.c
@@ -49,14 +49,12 @@ void jfs_issue_discard(struct inode *ip, u64 blkno, u64 nblocks)
r = sb_issue_discard(sb, blkno, nblocks, GFP_NOFS, 0);
if (unlikely(r != 0)) {
- jfs_err("JFS: sb_issue_discard" \
- "(%p, %llu, %llu, GFP_NOFS, 0) = %d => failed!\n",
+ jfs_err("JFS: sb_issue_discard(%p, %llu, %llu, GFP_NOFS, 0) = %d => failed!",
sb, (unsigned long long)blkno,
(unsigned long long)nblocks, r);
}
- jfs_info("JFS: sb_issue_discard" \
- "(%p, %llu, %llu, GFP_NOFS, 0) = %d\n",
+ jfs_info("JFS: sb_issue_discard(%p, %llu, %llu, GFP_NOFS, 0) = %d",
sb, (unsigned long long)blkno,
(unsigned long long)nblocks, r);
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index d88576e23fe4..de2bcb36e079 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -3072,8 +3072,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
}
if (dirtab_slot.flag == DIR_INDEX_FREE) {
if (loop_count++ > JFS_IP(ip)->next_index) {
- jfs_err("jfs_readdir detected "
- "infinite loop!");
+ jfs_err("jfs_readdir detected infinite loop!");
ctx->pos = DIREND;
return 0;
}
@@ -3151,8 +3150,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR))
return 0;
} else {
- jfs_err("jfs_readdir called with "
- "invalid offset!");
+ jfs_err("jfs_readdir called with invalid offset!");
}
dtoffset->pn = 1;
dtoffset->index = 0;
@@ -3165,8 +3163,8 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
}
if ((rc = dtReadNext(ip, &ctx->pos, &btstack))) {
- jfs_err("jfs_readdir: unexpected rc = %d "
- "from dtReadNext", rc);
+ jfs_err("jfs_readdir: unexpected rc = %d from dtReadNext",
+ rc);
ctx->pos = DIREND;
return 0;
}
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index f321986e73d2..6aca224a5d68 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -534,8 +534,7 @@ void diWriteSpecial(struct inode *ip, int secondary)
/* read the page of fixed disk inode (AIT) in raw mode */
mp = read_metapage(ip, address << sbi->l2nbperpage, PSIZE, 1);
if (mp == NULL) {
- jfs_err("diWriteSpecial: failed to read aggregate inode "
- "extent!");
+ jfs_err("diWriteSpecial: failed to read aggregate inode extent!");
return;
}
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index cf7936fe2e68..5e33cb9a190d 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -151,7 +151,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
jfs_inode->xtlid = 0;
jfs_set_inode_flags(inode);
- jfs_info("ialloc returns inode = 0x%p\n", inode);
+ jfs_info("ialloc returns inode = 0x%p", inode);
return inode;
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index a270cb7ff4e0..63759d723920 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1094,7 +1094,7 @@ int lmLogOpen(struct super_block *sb)
if (log->bdev->bd_dev == sbi->logdev) {
if (memcmp(log->uuid, sbi->loguuid,
sizeof(log->uuid))) {
- jfs_warn("wrong uuid on JFS journal\n");
+ jfs_warn("wrong uuid on JFS journal");
mutex_unlock(&jfs_log_mutex);
return -EINVAL;
}
@@ -1333,9 +1333,8 @@ int lmLogInit(struct jfs_log * log)
rc = -EINVAL;
goto errout20;
}
- jfs_info("lmLogInit: inline log:0x%p base:0x%Lx "
- "size:0x%x", log,
- (unsigned long long) log->base, log->size);
+ jfs_info("lmLogInit: inline log:0x%p base:0x%Lx size:0x%x",
+ log, (unsigned long long)log->base, log->size);
} else {
if (memcmp(logsuper->uuid, log->uuid, 16)) {
jfs_warn("wrong uuid on JFS log device");
@@ -1343,9 +1342,8 @@ int lmLogInit(struct jfs_log * log)
}
log->size = le32_to_cpu(logsuper->size);
log->l2bsize = le32_to_cpu(logsuper->l2bsize);
- jfs_info("lmLogInit: external log:0x%p base:0x%Lx "
- "size:0x%x", log,
- (unsigned long long) log->base, log->size);
+ jfs_info("lmLogInit: external log:0x%p base:0x%Lx size:0x%x",
+ log, (unsigned long long)log->base, log->size);
}
log->page = le32_to_cpu(logsuper->end) / LOGPSIZE;
@@ -2136,7 +2134,7 @@ static void lbmStartIO(struct lbuf * bp)
struct bio *bio;
struct jfs_log *log = bp->l_log;
- jfs_info("lbmStartIO\n");
+ jfs_info("lbmStartIO");
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index d595856453b2..eddf2b6eda85 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -1764,7 +1764,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
if (lwm == next)
goto out;
if (lwm > next) {
- jfs_err("xtLog: lwm > next\n");
+ jfs_err("xtLog: lwm > next");
goto out;
}
tlck->flag |= tlckUPDATEMAP;
@@ -1798,8 +1798,8 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
xadlock->xdlist = &p->xad[lwm];
tblk->xflag &= ~COMMIT_LAZY;
}
- jfs_info("xtLog: alloc ip:0x%p mp:0x%p tlck:0x%p lwm:%d "
- "count:%d", tlck->ip, mp, tlck, lwm, xadlock->count);
+ jfs_info("xtLog: alloc ip:0x%p mp:0x%p tlck:0x%p lwm:%d count:%d",
+ tlck->ip, mp, tlck, lwm, xadlock->count);
maplock->index = 1;
@@ -2025,8 +2025,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
xadlock->count = next - lwm;
xadlock->xdlist = &p->xad[lwm];
- jfs_info("xtLog: alloc ip:0x%p mp:0x%p count:%d "
- "lwm:%d next:%d",
+ jfs_info("xtLog: alloc ip:0x%p mp:0x%p count:%d lwm:%d next:%d",
tlck->ip, mp, xadlock->count, lwm, next);
maplock->index++;
xadlock++;
@@ -2047,8 +2046,8 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
pxdlock->count = 1;
pxdlock->pxd = pxd;
- jfs_info("xtLog: truncate ip:0x%p mp:0x%p count:%d "
- "hwm:%d", ip, mp, pxdlock->count, hwm);
+ jfs_info("xtLog: truncate ip:0x%p mp:0x%p count:%d hwm:%d",
+ ip, mp, pxdlock->count, hwm);
maplock->index++;
xadlock++;
}
@@ -2066,8 +2065,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
xadlock->count = hwm - next + 1;
xadlock->xdlist = &p->xad[next];
- jfs_info("xtLog: free ip:0x%p mp:0x%p count:%d "
- "next:%d hwm:%d",
+ jfs_info("xtLog: free ip:0x%p mp:0x%p count:%d next:%d hwm:%d",
tlck->ip, mp, xadlock->count, next, hwm);
maplock->index++;
}
@@ -2523,8 +2521,7 @@ void txFreeMap(struct inode *ip,
xlen = lengthXAD(xad);
dbUpdatePMap(ipbmap, true, xaddr,
(s64) xlen, tblk);
- jfs_info("freePMap: xaddr:0x%lx "
- "xlen:%d",
+ jfs_info("freePMap: xaddr:0x%lx xlen:%d",
(ulong) xaddr, xlen);
}
}
@@ -2814,7 +2811,7 @@ int jfs_lazycommit(void *arg)
if (!list_empty(&TxAnchor.unlock_queue))
jfs_err("jfs_lazycommit being killed w/pending transactions!");
else
- jfs_info("jfs_lazycommit being killed\n");
+ jfs_info("jfs_lazycommit being killed");
return 0;
}
diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h
index e8d717dabca3..561f6af46288 100644
--- a/fs/jfs/jfs_xattr.h
+++ b/fs/jfs/jfs_xattr.h
@@ -19,6 +19,8 @@
#ifndef H_JFS_XATTR
#define H_JFS_XATTR
+#include <linux/xattr.h>
+
/*
* jfs_ea_list describe the on-disk format of the extended attributes.
* I know the null-terminator is redundant since namelen is stored, but
@@ -54,12 +56,8 @@ struct jfs_ea_list {
extern int __jfs_setxattr(tid_t, struct inode *, const char *, const void *,
size_t, int);
-extern int jfs_setxattr(struct dentry *, const char *, const void *, size_t,
- int);
extern ssize_t __jfs_getxattr(struct inode *, const char *, void *, size_t);
-extern ssize_t jfs_getxattr(struct dentry *, const char *, void *, size_t);
extern ssize_t jfs_listxattr(struct dentry *, char *, size_t);
-extern int jfs_removexattr(struct dentry *, const char *);
extern const struct xattr_handler *jfs_xattr_handlers[];
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 701f89370de7..539deddecbb0 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -1225,8 +1225,8 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
rc = dtSearch(new_dir, &new_dname, &ino, &btstack,
JFS_CREATE);
if (rc) {
- jfs_err("jfs_rename didn't expect dtSearch to fail "
- "w/rc = %d", rc);
+ jfs_err("jfs_rename didn't expect dtSearch to fail w/rc = %d",
+ rc);
goto out_tx;
}
@@ -1524,7 +1524,7 @@ struct dentry *jfs_get_parent(struct dentry *dentry)
parent_ino =
le32_to_cpu(JFS_IP(d_inode(dentry))->i_dtroot.header.idotdot);
- return d_obtain_alias(jfs_iget(d_inode(dentry)->i_sb, parent_ino));
+ return d_obtain_alias(jfs_iget(dentry->d_sb, parent_ino));
}
const struct inode_operations jfs_dir_inode_operations = {
@@ -1537,10 +1537,10 @@ const struct inode_operations jfs_dir_inode_operations = {
.rmdir = jfs_rmdir,
.mknod = jfs_mknod,
.rename = jfs_rename,
- .setxattr = jfs_setxattr,
- .getxattr = jfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = jfs_listxattr,
- .removexattr = jfs_removexattr,
+ .removexattr = generic_removexattr,
.setattr = jfs_setattr,
#ifdef CONFIG_JFS_POSIX_ACL
.get_acl = jfs_get_acl,
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 78d599198bf5..cec8814a3b8b 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -84,7 +84,7 @@ static void jfs_handle_error(struct super_block *sb)
panic("JFS (device %s): panic forced after error\n",
sb->s_id);
else if (sbi->flag & JFS_ERR_REMOUNT_RO) {
- jfs_err("ERROR: (device %s): remounting filesystem as read-only\n",
+ jfs_err("ERROR: (device %s): remounting filesystem as read-only",
sb->s_id);
sb->s_flags |= MS_RDONLY;
}
@@ -641,7 +641,7 @@ static int jfs_freeze(struct super_block *sb)
}
rc = updateSuper(sb, FM_CLEAN);
if (rc) {
- jfs_err("jfs_freeze: updateSuper failed\n");
+ jfs_err("jfs_freeze: updateSuper failed");
/*
* Don't fail here. Everything succeeded except
* marking the superblock clean, so there's really
diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c
index f8db4fde0b0b..c94c7e4a1323 100644
--- a/fs/jfs/symlink.c
+++ b/fs/jfs/symlink.c
@@ -25,19 +25,19 @@ const struct inode_operations jfs_fast_symlink_inode_operations = {
.readlink = generic_readlink,
.get_link = simple_get_link,
.setattr = jfs_setattr,
- .setxattr = jfs_setxattr,
- .getxattr = jfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = jfs_listxattr,
- .removexattr = jfs_removexattr,
+ .removexattr = generic_removexattr,
};
const struct inode_operations jfs_symlink_inode_operations = {
.readlink = generic_readlink,
.get_link = page_get_link,
.setattr = jfs_setattr,
- .setxattr = jfs_setxattr,
- .getxattr = jfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = jfs_listxattr,
- .removexattr = jfs_removexattr,
+ .removexattr = generic_removexattr,
};
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 48b15a6e5558..beb182b503b3 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -86,6 +86,14 @@ struct ea_buffer {
#define EA_MALLOC 0x0008
+/*
+ * Mapping of on-disk attribute names: for on-disk attribute names with an
+ * unknown prefix (not "system.", "user.", "security.", or "trusted."), the
+ * prefix "os2." is prepended. On the way back to disk, "os2." prefixes are
+ * stripped and we make sure that the remaining name does not start with one
+ * of the know prefixes.
+ */
+
static int is_known_namespace(const char *name)
{
if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) &&
@@ -97,29 +105,19 @@ static int is_known_namespace(const char *name)
return true;
}
-/*
- * These three routines are used to recognize on-disk extended attributes
- * that are in a recognized namespace. If the attribute is not recognized,
- * "os2." is prepended to the name
- */
-static int is_os2_xattr(struct jfs_ea *ea)
-{
- return !is_known_namespace(ea->name);
-}
-
static inline int name_size(struct jfs_ea *ea)
{
- if (is_os2_xattr(ea))
- return ea->namelen + XATTR_OS2_PREFIX_LEN;
- else
+ if (is_known_namespace(ea->name))
return ea->namelen;
+ else
+ return ea->namelen + XATTR_OS2_PREFIX_LEN;
}
static inline int copy_name(char *buffer, struct jfs_ea *ea)
{
int len = ea->namelen;
- if (is_os2_xattr(ea)) {
+ if (!is_known_namespace(ea->name)) {
memcpy(buffer, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN);
buffer += XATTR_OS2_PREFIX_LEN;
len += XATTR_OS2_PREFIX_LEN;
@@ -665,35 +663,6 @@ static int ea_put(tid_t tid, struct inode *inode, struct ea_buffer *ea_buf,
return 0;
}
-/*
- * Most of the permission checking is done by xattr_permission in the vfs.
- * We also need to verify that this is a namespace that we recognize.
- */
-static int can_set_xattr(struct inode *inode, const char *name,
- const void *value, size_t value_len)
-{
- if (!strncmp(name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)) {
- /*
- * This makes sure that we aren't trying to set an
- * attribute in a different namespace by prefixing it
- * with "os2."
- */
- if (is_known_namespace(name + XATTR_OS2_PREFIX_LEN))
- return -EOPNOTSUPP;
- return 0;
- }
-
- /*
- * Don't allow setting an attribute in an unknown namespace.
- */
- if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) &&
- strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) &&
- strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
- return -EOPNOTSUPP;
-
- return 0;
-}
-
int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name,
const void *value, size_t value_len, int flags)
{
@@ -704,21 +673,10 @@ int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name,
int xattr_size;
int new_size;
int namelen = strlen(name);
- char *os2name = NULL;
int found = 0;
int rc;
int length;
- if (strncmp(name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
- os2name = kmalloc(namelen - XATTR_OS2_PREFIX_LEN + 1,
- GFP_KERNEL);
- if (!os2name)
- return -ENOMEM;
- strcpy(os2name, name + XATTR_OS2_PREFIX_LEN);
- name = os2name;
- namelen -= XATTR_OS2_PREFIX_LEN;
- }
-
down_write(&JFS_IP(inode)->xattr_sem);
xattr_size = ea_get(inode, &ea_buf, 0);
@@ -841,44 +799,6 @@ int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name,
out:
up_write(&JFS_IP(inode)->xattr_sem);
- kfree(os2name);
-
- return rc;
-}
-
-int jfs_setxattr(struct dentry *dentry, const char *name, const void *value,
- size_t value_len, int flags)
-{
- struct inode *inode = d_inode(dentry);
- struct jfs_inode_info *ji = JFS_IP(inode);
- int rc;
- tid_t tid;
-
- /*
- * If this is a request for a synthetic attribute in the system.*
- * namespace use the generic infrastructure to resolve a handler
- * for it via sb->s_xattr.
- */
- if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return generic_setxattr(dentry, name, value, value_len, flags);
-
- if ((rc = can_set_xattr(inode, name, value, value_len)))
- return rc;
-
- if (value == NULL) { /* empty EA, do not remove */
- value = "";
- value_len = 0;
- }
-
- tid = txBegin(inode->i_sb, 0);
- mutex_lock(&ji->commit_mutex);
- rc = __jfs_setxattr(tid, d_inode(dentry), name, value, value_len,
- flags);
- if (!rc)
- rc = txCommit(tid, 1, &inode, 0);
- txEnd(tid);
- mutex_unlock(&ji->commit_mutex);
-
return rc;
}
@@ -933,37 +853,6 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data,
return size;
}
-ssize_t jfs_getxattr(struct dentry *dentry, const char *name, void *data,
- size_t buf_size)
-{
- int err;
-
- /*
- * If this is a request for a synthetic attribute in the system.*
- * namespace use the generic infrastructure to resolve a handler
- * for it via sb->s_xattr.
- */
- if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return generic_getxattr(dentry, name, data, buf_size);
-
- if (strncmp(name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
- /*
- * skip past "os2." prefix
- */
- name += XATTR_OS2_PREFIX_LEN;
- /*
- * Don't allow retrieving properly prefixed attributes
- * by prepending them with "os2."
- */
- if (is_known_namespace(name))
- return -EOPNOTSUPP;
- }
-
- err = __jfs_getxattr(d_inode(dentry), name, data, buf_size);
-
- return err;
-}
-
/*
* No special permissions are needed to list attributes except for trusted.*
*/
@@ -1027,27 +916,16 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size)
return size;
}
-int jfs_removexattr(struct dentry *dentry, const char *name)
+static int __jfs_xattr_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
struct jfs_inode_info *ji = JFS_IP(inode);
- int rc;
tid_t tid;
-
- /*
- * If this is a request for a synthetic attribute in the system.*
- * namespace use the generic infrastructure to resolve a handler
- * for it via sb->s_xattr.
- */
- if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
- return generic_removexattr(dentry, name);
-
- if ((rc = can_set_xattr(inode, name, NULL, 0)))
- return rc;
+ int rc;
tid = txBegin(inode->i_sb, 0);
mutex_lock(&ji->commit_mutex);
- rc = __jfs_setxattr(tid, d_inode(dentry), name, NULL, 0, XATTR_REPLACE);
+ rc = __jfs_setxattr(tid, inode, name, value, size, flags);
if (!rc)
rc = txCommit(tid, 1, &inode, 0);
txEnd(tid);
@@ -1056,15 +934,77 @@ int jfs_removexattr(struct dentry *dentry, const char *name)
return rc;
}
-/*
- * List of handlers for synthetic system.* attributes. All real ondisk
- * attributes are handled directly.
- */
+static int jfs_xattr_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *value, size_t size)
+{
+ name = xattr_full_name(handler, name);
+ return __jfs_getxattr(inode, name, value, size);
+}
+
+static int jfs_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct inode *inode = d_inode(dentry);
+
+ name = xattr_full_name(handler, name);
+ return __jfs_xattr_set(inode, name, value, size, flags);
+}
+
+static int jfs_xattr_get_os2(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *value, size_t size)
+{
+ if (is_known_namespace(name))
+ return -EOPNOTSUPP;
+ return __jfs_getxattr(inode, name, value, size);
+}
+
+static int jfs_xattr_set_os2(const struct xattr_handler *handler,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct inode *inode = d_inode(dentry);
+
+ if (is_known_namespace(name))
+ return -EOPNOTSUPP;
+ return __jfs_xattr_set(inode, name, value, size, flags);
+}
+
+static const struct xattr_handler jfs_user_xattr_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .get = jfs_xattr_get,
+ .set = jfs_xattr_set,
+};
+
+static const struct xattr_handler jfs_os2_xattr_handler = {
+ .prefix = XATTR_OS2_PREFIX,
+ .get = jfs_xattr_get_os2,
+ .set = jfs_xattr_set_os2,
+};
+
+static const struct xattr_handler jfs_security_xattr_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .get = jfs_xattr_get,
+ .set = jfs_xattr_set,
+};
+
+static const struct xattr_handler jfs_trusted_xattr_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .get = jfs_xattr_get,
+ .set = jfs_xattr_set,
+};
+
const struct xattr_handler *jfs_xattr_handlers[] = {
#ifdef CONFIG_JFS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
+ &jfs_os2_xattr_handler,
+ &jfs_user_xattr_handler,
+ &jfs_security_xattr_handler,
+ &jfs_trusted_xattr_handler,
NULL,
};
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 03b688d19f69..8a652404eef6 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -153,9 +153,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
p = buf + len + nlen;
*p = '\0';
for (kn = kn_to; kn != common; kn = kn->parent) {
- nlen = strlen(kn->name);
- p -= nlen;
- memcpy(p, kn->name, nlen);
+ size_t tmp = strlen(kn->name);
+ p -= tmp;
+ memcpy(p, kn->name, tmp);
*(--p) = '/';
}
@@ -753,7 +753,8 @@ int kernfs_add_one(struct kernfs_node *kn)
ps_iattr = parent->iattr;
if (ps_iattr) {
struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
- ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+ ktime_get_real_ts(&ps_iattrs->ia_ctime);
+ ps_iattrs->ia_mtime = ps_iattrs->ia_ctime;
}
mutex_unlock(&kernfs_mutex);
@@ -1279,8 +1280,9 @@ static void __kernfs_remove(struct kernfs_node *kn)
/* update timestamps on the parent */
if (ps_iattr) {
- ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
- ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
+ ktime_get_real_ts(&ps_iattr->ia_iattr.ia_ctime);
+ ps_iattr->ia_iattr.ia_mtime =
+ ps_iattr->ia_iattr.ia_ctime;
}
kernfs_put(pos);
@@ -1643,22 +1645,9 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
return 0;
}
-static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset,
- int whence)
-{
- struct inode *inode = file_inode(file);
- loff_t ret;
-
- inode_lock(inode);
- ret = generic_file_llseek(file, offset, whence);
- inode_unlock(inode);
-
- return ret;
-}
-
const struct file_operations kernfs_dir_fops = {
.read = generic_read_dir,
- .iterate = kernfs_fop_readdir,
+ .iterate_shared = kernfs_fop_readdir,
.release = kernfs_dir_fop_release,
- .llseek = kernfs_dir_fop_llseek,
+ .llseek = generic_file_llseek,
};
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 7247252ee9b1..e1574008adc9 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -190,15 +190,16 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
char *buf;
buf = of->prealloc_buf;
- if (!buf)
+ if (buf)
+ mutex_lock(&of->prealloc_mutex);
+ else
buf = kmalloc(len, GFP_KERNEL);
if (!buf)
return -ENOMEM;
/*
* @of->mutex nests outside active ref and is used both to ensure that
- * the ops aren't called concurrently for the same open file, and
- * to provide exclusive access to ->prealloc_buf (when that exists).
+ * the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
if (!kernfs_get_active(of->kn)) {
@@ -214,21 +215,23 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
else
len = -EINVAL;
+ kernfs_put_active(of->kn);
+ mutex_unlock(&of->mutex);
+
if (len < 0)
- goto out_unlock;
+ goto out_free;
if (copy_to_user(user_buf, buf, len)) {
len = -EFAULT;
- goto out_unlock;
+ goto out_free;
}
*ppos += len;
- out_unlock:
- kernfs_put_active(of->kn);
- mutex_unlock(&of->mutex);
out_free:
- if (buf != of->prealloc_buf)
+ if (buf == of->prealloc_buf)
+ mutex_unlock(&of->prealloc_mutex);
+ else
kfree(buf);
return len;
}
@@ -284,15 +287,22 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
}
buf = of->prealloc_buf;
- if (!buf)
+ if (buf)
+ mutex_lock(&of->prealloc_mutex);
+ else
buf = kmalloc(len + 1, GFP_KERNEL);
if (!buf)
return -ENOMEM;
+ if (copy_from_user(buf, user_buf, len)) {
+ len = -EFAULT;
+ goto out_free;
+ }
+ buf[len] = '\0'; /* guarantee string termination */
+
/*
* @of->mutex nests outside active ref and is used both to ensure that
- * the ops aren't called concurrently for the same open file, and
- * to provide exclusive access to ->prealloc_buf (when that exists).
+ * the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
if (!kernfs_get_active(of->kn)) {
@@ -301,26 +311,22 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
goto out_free;
}
- if (copy_from_user(buf, user_buf, len)) {
- len = -EFAULT;
- goto out_unlock;
- }
- buf[len] = '\0'; /* guarantee string termination */
-
ops = kernfs_ops(of->kn);
if (ops->write)
len = ops->write(of, buf, len, *ppos);
else
len = -EINVAL;
+ kernfs_put_active(of->kn);
+ mutex_unlock(&of->mutex);
+
if (len > 0)
*ppos += len;
-out_unlock:
- kernfs_put_active(of->kn);
- mutex_unlock(&of->mutex);
out_free:
- if (buf != of->prealloc_buf)
+ if (buf == of->prealloc_buf)
+ mutex_unlock(&of->prealloc_mutex);
+ else
kfree(buf);
return len;
}
@@ -687,6 +693,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
error = -ENOMEM;
if (!of->prealloc_buf)
goto err_free;
+ mutex_init(&of->prealloc_mutex);
}
/*
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 16405ae88d2d..1719649d7ad7 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -54,7 +54,10 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
iattrs->ia_mode = kn->mode;
iattrs->ia_uid = GLOBAL_ROOT_UID;
iattrs->ia_gid = GLOBAL_ROOT_GID;
- iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
+
+ ktime_get_real_ts(&iattrs->ia_atime);
+ iattrs->ia_mtime = iattrs->ia_atime;
+ iattrs->ia_ctime = iattrs->ia_atime;
simple_xattrs_init(&kn->iattr->xattrs);
out_unlock:
@@ -208,10 +211,10 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name)
return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE);
}
-ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
- size_t size)
+ssize_t kernfs_iop_getxattr(struct dentry *unused, struct inode *inode,
+ const char *name, void *buf, size_t size)
{
- struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_node *kn = inode->i_private;
struct kernfs_iattrs *attrs;
attrs = kernfs_iattrs(kn);
@@ -236,16 +239,18 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
{
inode->i_mode = mode;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ inode->i_atime = inode->i_mtime =
+ inode->i_ctime = current_fs_time(inode->i_sb);
}
static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
{
+ struct super_block *sb = inode->i_sb;
inode->i_uid = iattr->ia_uid;
inode->i_gid = iattr->ia_gid;
- inode->i_atime = iattr->ia_atime;
- inode->i_mtime = iattr->ia_mtime;
- inode->i_ctime = iattr->ia_ctime;
+ inode->i_atime = timespec_trunc(iattr->ia_atime, sb->s_time_gran);
+ inode->i_mtime = timespec_trunc(iattr->ia_mtime, sb->s_time_gran);
+ inode->i_ctime = timespec_trunc(iattr->ia_ctime, sb->s_time_gran);
}
static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 6762bfbd8207..45c9192c276e 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -84,8 +84,8 @@ int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
int kernfs_iop_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags);
int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
-ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
- size_t size);
+ssize_t kernfs_iop_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *buf, size_t size);
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
/*
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index f73541fbe7af..63534f5f9073 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -15,6 +15,7 @@
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
+#include <linux/seq_file.h>
#include "kernfs-internal.h"
@@ -40,6 +41,19 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
return 0;
}
+static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
+{
+ struct kernfs_node *node = dentry->d_fsdata;
+ struct kernfs_root *root = kernfs_root(node);
+ struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+ if (scops && scops->show_path)
+ return scops->show_path(sf, node, root);
+
+ seq_dentry(sf, dentry, " \t\n\\");
+ return 0;
+}
+
const struct super_operations kernfs_sops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
@@ -47,6 +61,7 @@ const struct super_operations kernfs_sops = {
.remount_fs = kernfs_sop_remount_fs,
.show_options = kernfs_sop_show_options,
+ .show_path = kernfs_sop_show_path,
};
/**
@@ -120,9 +135,8 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
kntmp = find_next_ancestor(kn, knparent);
if (WARN_ON(!kntmp))
return ERR_PTR(-EINVAL);
- mutex_lock(&d_inode(dentry)->i_mutex);
- dtmp = lookup_one_len(kntmp->name, dentry, strlen(kntmp->name));
- mutex_unlock(&d_inode(dentry)->i_mutex);
+ dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
+ strlen(kntmp->name));
dput(dentry);
if (IS_ERR(dtmp))
return dtmp;
diff --git a/fs/libfs.c b/fs/libfs.c
index f3fa82ce9b70..8765ff1adc07 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -89,7 +89,6 @@ EXPORT_SYMBOL(dcache_dir_close);
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry *dentry = file->f_path.dentry;
- inode_lock(d_inode(dentry));
switch (whence) {
case 1:
offset += file->f_pos;
@@ -97,7 +96,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
if (offset >= 0)
break;
default:
- inode_unlock(d_inode(dentry));
return -EINVAL;
}
if (offset != file->f_pos) {
@@ -124,7 +122,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
spin_unlock(&dentry->d_lock);
}
}
- inode_unlock(d_inode(dentry));
return offset;
}
EXPORT_SYMBOL(dcache_dir_lseek);
@@ -190,7 +187,7 @@ const struct file_operations simple_dir_operations = {
.release = dcache_dir_close,
.llseek = dcache_dir_lseek,
.read = generic_read_dir,
- .iterate = dcache_readdir,
+ .iterate_shared = dcache_readdir,
.fsync = noop_fsync,
};
EXPORT_SYMBOL(simple_dir_operations);
@@ -1127,8 +1124,8 @@ static int empty_dir_setxattr(struct dentry *dentry, const char *name,
return -EOPNOTSUPP;
}
-static ssize_t empty_dir_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size)
+static ssize_t empty_dir_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size)
{
return -EOPNOTSUPP;
}
@@ -1169,7 +1166,7 @@ static int empty_dir_readdir(struct file *file, struct dir_context *ctx)
static const struct file_operations empty_dir_operations = {
.llseek = empty_dir_llseek,
.read = generic_read_dir,
- .iterate = empty_dir_readdir,
+ .iterate_shared = empty_dir_readdir,
.fsync = noop_fsync,
};
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index ddbed2be5366..2d5336bd4efd 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -791,7 +791,7 @@ const struct inode_operations logfs_dir_iops = {
const struct file_operations logfs_dir_fops = {
.fsync = logfs_fsync,
.unlocked_ioctl = logfs_ioctl,
- .iterate = logfs_readdir,
+ .iterate_shared = logfs_readdir,
.read = generic_read_dir,
- .llseek = default_llseek,
+ .llseek = generic_file_llseek,
};
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index 33957c07cd11..31dcd515b9d5 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -21,7 +21,7 @@ static int minix_readdir(struct file *, struct dir_context *);
const struct file_operations minix_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = minix_readdir,
+ .iterate_shared = minix_readdir,
.fsync = generic_file_fsync,
};
diff --git a/fs/namei.c b/fs/namei.c
index 1d9ca2d5dff6..5375571cf6e1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -265,7 +265,7 @@ static int check_acl(struct inode *inode, int mask)
if (!acl)
return -EAGAIN;
/* no ->get_acl() calls in RCU mode... */
- if (acl == ACL_NOT_CACHED)
+ if (is_uncached_acl(acl))
return -ECHILD;
return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK);
}
@@ -1603,32 +1603,42 @@ static struct dentry *lookup_slow(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
- struct dentry *dentry;
- inode_lock(dir->d_inode);
- dentry = d_lookup(dir, name);
- if (unlikely(dentry)) {
+ struct dentry *dentry = ERR_PTR(-ENOENT), *old;
+ struct inode *inode = dir->d_inode;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+
+ inode_lock_shared(inode);
+ /* Don't go there if it's already dead */
+ if (unlikely(IS_DEADDIR(inode)))
+ goto out;
+again:
+ dentry = d_alloc_parallel(dir, name, &wq);
+ if (IS_ERR(dentry))
+ goto out;
+ if (unlikely(!d_in_lookup(dentry))) {
if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
!(flags & LOOKUP_NO_REVAL)) {
int error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
- if (!error)
+ if (!error) {
d_invalidate(dentry);
+ dput(dentry);
+ goto again;
+ }
dput(dentry);
dentry = ERR_PTR(error);
}
}
- if (dentry) {
- inode_unlock(dir->d_inode);
- return dentry;
+ } else {
+ old = inode->i_op->lookup(inode, dentry, flags);
+ d_lookup_done(dentry);
+ if (unlikely(old)) {
+ dput(dentry);
+ dentry = old;
}
}
- dentry = d_alloc(dir, name);
- if (unlikely(!dentry)) {
- inode_unlock(dir->d_inode);
- return ERR_PTR(-ENOMEM);
- }
- dentry = lookup_real(dir->d_inode, dentry, flags);
- inode_unlock(dir->d_inode);
+out:
+ inode_unlock_shared(inode);
return dentry;
}
@@ -1794,30 +1804,49 @@ static inline unsigned int fold_hash(unsigned long hash)
return hash_64(hash, 32);
}
+/*
+ * This is George Marsaglia's XORSHIFT generator.
+ * It implements a maximum-period LFSR in only a few
+ * instructions. It also has the property (required
+ * by hash_name()) that mix_hash(0) = 0.
+ */
+static inline unsigned long mix_hash(unsigned long hash)
+{
+ hash ^= hash << 13;
+ hash ^= hash >> 7;
+ hash ^= hash << 17;
+ return hash;
+}
+
#else /* 32-bit case */
#define fold_hash(x) (x)
+static inline unsigned long mix_hash(unsigned long hash)
+{
+ hash ^= hash << 13;
+ hash ^= hash >> 17;
+ hash ^= hash << 5;
+ return hash;
+}
+
#endif
unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
- unsigned long a, mask;
- unsigned long hash = 0;
+ unsigned long a, hash = 0;
for (;;) {
a = load_unaligned_zeropad(name);
if (len < sizeof(unsigned long))
break;
- hash += a;
- hash *= 9;
+ hash = mix_hash(hash + a);
name += sizeof(unsigned long);
len -= sizeof(unsigned long);
if (!len)
goto done;
}
- mask = bytemask_from_count(len);
- hash += mask & a;
+ hash += a & bytemask_from_count(len);
done:
return fold_hash(hash);
}
@@ -1835,7 +1864,7 @@ static inline u64 hash_name(const char *name)
hash = a = 0;
len = -sizeof(unsigned long);
do {
- hash = (hash + a) * 9;
+ hash = mix_hash(hash + a);
len += sizeof(unsigned long);
a = load_unaligned_zeropad(name+len);
b = a ^ REPEAT_BYTE('/');
@@ -2267,6 +2296,33 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
EXPORT_SYMBOL(vfs_path_lookup);
/**
+ * lookup_hash - lookup single pathname component on already hashed name
+ * @name: name and hash to lookup
+ * @base: base directory to lookup from
+ *
+ * The name must have been verified and hashed (see lookup_one_len()). Using
+ * this after just full_name_hash() is unsafe.
+ *
+ * This function also doesn't check for search permission on base directory.
+ *
+ * Use lookup_one_len_unlocked() instead, unless you really know what you are
+ * doing.
+ *
+ * Do not hold i_mutex; this helper takes i_mutex if necessary.
+ */
+struct dentry *lookup_hash(const struct qstr *name, struct dentry *base)
+{
+ struct dentry *ret;
+
+ ret = lookup_dcache(name, base, 0);
+ if (!ret)
+ ret = lookup_slow(name, base, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL(lookup_hash);
+
+/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
* @base: base directory to lookup from
@@ -2337,7 +2393,6 @@ struct dentry *lookup_one_len_unlocked(const char *name,
struct qstr this;
unsigned int c;
int err;
- struct dentry *ret;
this.name = name;
this.len = len;
@@ -2369,10 +2424,7 @@ struct dentry *lookup_one_len_unlocked(const char *name,
if (err)
return ERR_PTR(err);
- ret = lookup_dcache(&this, base, 0);
- if (!ret)
- ret = lookup_slow(&this, base, 0);
- return ret;
+ return lookup_hash(&this, base);
}
EXPORT_SYMBOL(lookup_one_len_unlocked);
@@ -2655,7 +2707,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
return NULL;
}
- mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
+ mutex_lock(&p1->d_sb->s_vfs_rename_mutex);
p = d_ancestor(p2, p1);
if (p) {
@@ -2682,7 +2734,7 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
inode_unlock(p1->d_inode);
if (p1 != p2) {
inode_unlock(p2->d_inode);
- mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
+ mutex_unlock(&p1->d_sb->s_vfs_rename_mutex);
}
}
EXPORT_SYMBOL(unlock_rename);
@@ -2785,7 +2837,7 @@ static inline int open_to_namei_flags(int flag)
return flag;
}
-static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode)
+static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode)
{
int error = security_path_mknod(dir, dentry, mode, 0);
if (error)
@@ -2814,155 +2866,56 @@ static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode)
static int atomic_open(struct nameidata *nd, struct dentry *dentry,
struct path *path, struct file *file,
const struct open_flags *op,
- bool got_write, bool need_lookup,
+ int open_flag, umode_t mode,
int *opened)
{
+ struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
struct inode *dir = nd->path.dentry->d_inode;
- unsigned open_flag = open_to_namei_flags(op->open_flag);
- umode_t mode;
int error;
- int acc_mode;
- int create_error = 0;
- struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
- bool excl;
-
- BUG_ON(dentry->d_inode);
- /* Don't create child dentry for a dead directory. */
- if (unlikely(IS_DEADDIR(dir))) {
- error = -ENOENT;
- goto out;
- }
-
- mode = op->mode;
- if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
- mode &= ~current_umask();
-
- excl = (open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT);
- if (excl)
+ if (!(~open_flag & (O_EXCL | O_CREAT))) /* both O_EXCL and O_CREAT */
open_flag &= ~O_TRUNC;
- /*
- * Checking write permission is tricky, bacuse we don't know if we are
- * going to actually need it: O_CREAT opens should work as long as the
- * file exists. But checking existence breaks atomicity. The trick is
- * to check access and if not granted clear O_CREAT from the flags.
- *
- * Another problem is returing the "right" error value (e.g. for an
- * O_EXCL open we want to return EEXIST not EROFS).
- */
- if (((open_flag & (O_CREAT | O_TRUNC)) ||
- (open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) {
- if (!(open_flag & O_CREAT)) {
- /*
- * No O_CREATE -> atomicity not a requirement -> fall
- * back to lookup + open
- */
- goto no_open;
- } else if (open_flag & (O_EXCL | O_TRUNC)) {
- /* Fall back and fail with the right error */
- create_error = -EROFS;
- goto no_open;
- } else {
- /* No side effects, safe to clear O_CREAT */
- create_error = -EROFS;
- open_flag &= ~O_CREAT;
- }
- }
-
- if (open_flag & O_CREAT) {
- error = may_o_create(&nd->path, dentry, mode);
- if (error) {
- create_error = error;
- if (open_flag & O_EXCL)
- goto no_open;
- open_flag &= ~O_CREAT;
- }
- }
-
if (nd->flags & LOOKUP_DIRECTORY)
open_flag |= O_DIRECTORY;
file->f_path.dentry = DENTRY_NOT_SET;
file->f_path.mnt = nd->path.mnt;
- error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode,
- opened);
- if (error < 0) {
- if (create_error && error == -ENOENT)
- error = create_error;
- goto out;
- }
-
- if (error) { /* returned 1, that is */
+ error = dir->i_op->atomic_open(dir, dentry, file,
+ open_to_namei_flags(open_flag),
+ mode, opened);
+ d_lookup_done(dentry);
+ if (!error) {
+ /*
+ * We didn't have the inode before the open, so check open
+ * permission here.
+ */
+ int acc_mode = op->acc_mode;
+ if (*opened & FILE_CREATED) {
+ WARN_ON(!(open_flag & O_CREAT));
+ fsnotify_create(dir, dentry);
+ acc_mode = 0;
+ }
+ error = may_open(&file->f_path, acc_mode, open_flag);
+ if (WARN_ON(error > 0))
+ error = -EINVAL;
+ } else if (error > 0) {
if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
error = -EIO;
- goto out;
- }
- if (file->f_path.dentry) {
- dput(dentry);
- dentry = file->f_path.dentry;
- }
- if (*opened & FILE_CREATED)
- fsnotify_create(dir, dentry);
- if (!dentry->d_inode) {
- WARN_ON(*opened & FILE_CREATED);
- if (create_error) {
- error = create_error;
- goto out;
- }
} else {
- if (excl && !(*opened & FILE_CREATED)) {
- error = -EEXIST;
- goto out;
+ if (file->f_path.dentry) {
+ dput(dentry);
+ dentry = file->f_path.dentry;
}
+ if (*opened & FILE_CREATED)
+ fsnotify_create(dir, dentry);
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
+ return 1;
}
- goto looked_up;
}
-
- /*
- * We didn't have the inode before the open, so check open permission
- * here.
- */
- acc_mode = op->acc_mode;
- if (*opened & FILE_CREATED) {
- WARN_ON(!(open_flag & O_CREAT));
- fsnotify_create(dir, dentry);
- acc_mode = 0;
- }
- error = may_open(&file->f_path, acc_mode, open_flag);
- if (error)
- fput(file);
-
-out:
dput(dentry);
return error;
-
-no_open:
- if (need_lookup) {
- dentry = lookup_real(dir, dentry, nd->flags);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
-
- if (create_error) {
- int open_flag = op->open_flag;
-
- error = create_error;
- if ((open_flag & O_EXCL)) {
- if (!dentry->d_inode)
- goto out;
- } else if (!dentry->d_inode) {
- goto out;
- } else if ((open_flag & O_TRUNC) &&
- d_is_reg(dentry)) {
- goto out;
- }
- /* will fail later, go on to get the right error */
- }
- }
-looked_up:
- path->dentry = dentry;
- path->mnt = nd->path.mnt;
- return 1;
}
/*
@@ -2990,62 +2943,118 @@ static int lookup_open(struct nameidata *nd, struct path *path,
{
struct dentry *dir = nd->path.dentry;
struct inode *dir_inode = dir->d_inode;
+ int open_flag = op->open_flag;
struct dentry *dentry;
- int error;
- bool need_lookup = false;
+ int error, create_error = 0;
+ umode_t mode = op->mode;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+
+ if (unlikely(IS_DEADDIR(dir_inode)))
+ return -ENOENT;
*opened &= ~FILE_CREATED;
- dentry = lookup_dcache(&nd->last, dir, nd->flags);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
+ dentry = d_lookup(dir, &nd->last);
+ for (;;) {
+ if (!dentry) {
+ dentry = d_alloc_parallel(dir, &nd->last, &wq);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+ }
+ if (d_in_lookup(dentry))
+ break;
- if (!dentry) {
- dentry = d_alloc(dir, &nd->last);
- if (unlikely(!dentry))
- return -ENOMEM;
- need_lookup = true;
- } else if (dentry->d_inode) {
+ if (!(dentry->d_flags & DCACHE_OP_REVALIDATE))
+ break;
+
+ error = d_revalidate(dentry, nd->flags);
+ if (likely(error > 0))
+ break;
+ if (error)
+ goto out_dput;
+ d_invalidate(dentry);
+ dput(dentry);
+ dentry = NULL;
+ }
+ if (dentry->d_inode) {
/* Cached positive dentry: will open in f_op->open */
goto out_no_open;
}
- if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
- return atomic_open(nd, dentry, path, file, op, got_write,
- need_lookup, opened);
+ /*
+ * Checking write permission is tricky, bacuse we don't know if we are
+ * going to actually need it: O_CREAT opens should work as long as the
+ * file exists. But checking existence breaks atomicity. The trick is
+ * to check access and if not granted clear O_CREAT from the flags.
+ *
+ * Another problem is returing the "right" error value (e.g. for an
+ * O_EXCL open we want to return EEXIST not EROFS).
+ */
+ if (open_flag & O_CREAT) {
+ if (!IS_POSIXACL(dir->d_inode))
+ mode &= ~current_umask();
+ if (unlikely(!got_write)) {
+ create_error = -EROFS;
+ open_flag &= ~O_CREAT;
+ if (open_flag & (O_EXCL | O_TRUNC))
+ goto no_open;
+ /* No side effects, safe to clear O_CREAT */
+ } else {
+ create_error = may_o_create(&nd->path, dentry, mode);
+ if (create_error) {
+ open_flag &= ~O_CREAT;
+ if (open_flag & O_EXCL)
+ goto no_open;
+ }
+ }
+ } else if ((open_flag & (O_TRUNC|O_WRONLY|O_RDWR)) &&
+ unlikely(!got_write)) {
+ /*
+ * No O_CREATE -> atomicity not a requirement -> fall
+ * back to lookup + open
+ */
+ goto no_open;
}
- if (need_lookup) {
- BUG_ON(dentry->d_inode);
+ if (dir_inode->i_op->atomic_open) {
+ error = atomic_open(nd, dentry, path, file, op, open_flag,
+ mode, opened);
+ if (unlikely(error == -ENOENT) && create_error)
+ error = create_error;
+ return error;
+ }
- dentry = lookup_real(dir_inode, dentry, nd->flags);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
+no_open:
+ if (d_in_lookup(dentry)) {
+ struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry,
+ nd->flags);
+ d_lookup_done(dentry);
+ if (unlikely(res)) {
+ if (IS_ERR(res)) {
+ error = PTR_ERR(res);
+ goto out_dput;
+ }
+ dput(dentry);
+ dentry = res;
+ }
}
/* Negative dentry, just create the file */
- if (!dentry->d_inode && (op->open_flag & O_CREAT)) {
- umode_t mode = op->mode;
- if (!IS_POSIXACL(dir->d_inode))
- mode &= ~current_umask();
- /*
- * This write is needed to ensure that a
- * rw->ro transition does not occur between
- * the time when the file is created and when
- * a permanent write count is taken through
- * the 'struct file' in finish_open().
- */
- if (!got_write) {
- error = -EROFS;
- goto out_dput;
- }
+ if (!dentry->d_inode && (open_flag & O_CREAT)) {
*opened |= FILE_CREATED;
- error = security_path_mknod(&nd->path, dentry, mode, 0);
- if (error)
+ audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+ if (!dir_inode->i_op->create) {
+ error = -EACCES;
goto out_dput;
- error = vfs_create(dir->d_inode, dentry, mode,
- nd->flags & LOOKUP_EXCL);
+ }
+ error = dir_inode->i_op->create(dir_inode, dentry, mode,
+ open_flag & O_EXCL);
if (error)
goto out_dput;
+ fsnotify_create(dir_inode, dentry);
+ }
+ if (unlikely(create_error) && !dentry->d_inode) {
+ error = create_error;
+ goto out_dput;
}
out_no_open:
path->dentry = dentry;
@@ -3117,7 +3126,7 @@ static int do_last(struct nameidata *nd,
}
retry_lookup:
- if (op->open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
+ if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
error = mnt_want_write(nd->path.mnt);
if (!error)
got_write = true;
@@ -3127,9 +3136,15 @@ retry_lookup:
* dropping this one anyway.
*/
}
- inode_lock(dir->d_inode);
+ if (open_flag & O_CREAT)
+ inode_lock(dir->d_inode);
+ else
+ inode_lock_shared(dir->d_inode);
error = lookup_open(nd, &path, file, op, got_write, opened);
- inode_unlock(dir->d_inode);
+ if (open_flag & O_CREAT)
+ inode_unlock(dir->d_inode);
+ else
+ inode_unlock_shared(dir->d_inode);
if (error <= 0) {
if (error)
@@ -3209,10 +3224,6 @@ finish_open:
return error;
}
audit_inode(nd->name, nd->path.dentry, 0);
- if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) {
- error = -ELOOP;
- goto out;
- }
error = -EISDIR;
if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
goto out;
@@ -3229,11 +3240,9 @@ finish_open:
got_write = true;
}
finish_open_created:
- if (likely(!(open_flag & O_PATH))) {
- error = may_open(&nd->path, acc_mode, open_flag);
- if (error)
- goto out;
- }
+ error = may_open(&nd->path, acc_mode, open_flag);
+ if (error)
+ goto out;
BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
error = vfs_open(&nd->path, file, current_cred());
if (!error) {
@@ -3245,18 +3254,13 @@ finish_open_created:
}
opened:
error = open_check_o_direct(file);
- if (error)
- goto exit_fput;
- error = ima_file_check(file, op->acc_mode, *opened);
- if (error)
- goto exit_fput;
-
- if (will_truncate) {
+ if (!error)
+ error = ima_file_check(file, op->acc_mode, *opened);
+ if (!error && will_truncate)
error = handle_truncate(file);
- if (error)
- goto exit_fput;
- }
out:
+ if (unlikely(error) && (*opened & FILE_OPENED))
+ fput(file);
if (unlikely(error > 0)) {
WARN_ON(1);
error = -EINVAL;
@@ -3266,10 +3270,6 @@ out:
path_put(&save_parent);
return error;
-exit_fput:
- fput(file);
- goto out;
-
stale_open:
/* If no saved parent or already retried then can't retry */
if (!save_parent.dentry || retried)
@@ -3347,6 +3347,18 @@ out:
return error;
}
+static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
+{
+ struct path path;
+ int error = path_lookupat(nd, flags, &path);
+ if (!error) {
+ audit_inode(nd->name, path.dentry, 0);
+ error = vfs_open(&path, file, current_cred());
+ path_put(&path);
+ }
+ return error;
+}
+
static struct file *path_openat(struct nameidata *nd,
const struct open_flags *op, unsigned flags)
{
@@ -3366,6 +3378,13 @@ static struct file *path_openat(struct nameidata *nd,
goto out2;
}
+ if (unlikely(file->f_flags & O_PATH)) {
+ error = do_o_path(nd, flags, file);
+ if (!error)
+ opened |= FILE_OPENED;
+ goto out2;
+ }
+
s = path_init(nd, flags);
if (IS_ERR(s)) {
put_filp(file);
@@ -3608,6 +3627,8 @@ retry:
switch (mode & S_IFMT) {
case 0: case S_IFREG:
error = vfs_create(path.dentry->d_inode,dentry,mode,true);
+ if (!error)
+ ima_post_path_mknod(dentry);
break;
case S_IFCHR: case S_IFBLK:
error = vfs_mknod(path.dentry->d_inode,dentry,mode,
@@ -4213,7 +4234,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
bool new_is_dir = false;
unsigned max_links = new_dir->i_sb->s_max_links;
- if (source == target)
+ /*
+ * Check source == target.
+ * On overlayfs need to look at underlying inodes.
+ */
+ if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0))
return 0;
error = may_delete(old_dir, old_dentry, is_dir);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 33eb81738d03..aaf7bd0cbae2 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -57,7 +57,7 @@ static void nfs_readdir_clear_array(struct page*);
const struct file_operations nfs_dir_operations = {
.llseek = nfs_llseek_dir,
.read = generic_read_dir,
- .iterate = nfs_readdir,
+ .iterate_shared = nfs_readdir,
.open = nfs_opendir,
.release = nfs_closedir,
.fsync = nfs_fsync_dir,
@@ -145,6 +145,7 @@ struct nfs_cache_array_entry {
};
struct nfs_cache_array {
+ atomic_t refcount;
int size;
int eof_index;
u64 last_cookie;
@@ -200,11 +201,20 @@ void nfs_readdir_clear_array(struct page *page)
int i;
array = kmap_atomic(page);
- for (i = 0; i < array->size; i++)
- kfree(array->array[i].string.name);
+ if (atomic_dec_and_test(&array->refcount))
+ for (i = 0; i < array->size; i++)
+ kfree(array->array[i].string.name);
kunmap_atomic(array);
}
+static bool grab_page(struct page *page)
+{
+ struct nfs_cache_array *array = kmap_atomic(page);
+ bool res = atomic_inc_not_zero(&array->refcount);
+ kunmap_atomic(array);
+ return res;
+}
+
/*
* the caller is responsible for freeing qstr.name
* when called by nfs_readdir_add_to_array, the strings will be freed in
@@ -470,6 +480,7 @@ static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
struct qstr filename = QSTR_INIT(entry->name, entry->len);
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = d_inode(parent);
@@ -489,7 +500,13 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
filename.hash = full_name_hash(filename.name, filename.len);
dentry = d_lookup(parent, &filename);
- if (dentry != NULL) {
+again:
+ if (!dentry) {
+ dentry = d_alloc_parallel(parent, &filename, &wq);
+ if (IS_ERR(dentry))
+ return;
+ }
+ if (!d_in_lookup(dentry)) {
/* Is there a mountpoint here? If so, just exit */
if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
&entry->fattr->fsid))
@@ -503,26 +520,21 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
} else {
d_invalidate(dentry);
dput(dentry);
+ dentry = NULL;
+ goto again;
}
}
- dentry = d_alloc(parent, &filename);
- if (dentry == NULL)
- return;
-
inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label);
- if (IS_ERR(inode))
- goto out;
-
alias = d_splice_alias(inode, dentry);
- if (IS_ERR(alias))
- goto out;
- else if (alias) {
- nfs_set_verifier(alias, nfs_save_change_attribute(dir));
- dput(alias);
- } else
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-
+ d_lookup_done(dentry);
+ if (alias) {
+ if (IS_ERR(alias))
+ goto out;
+ dput(dentry);
+ dentry = alias;
+ }
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out:
dput(dentry);
}
@@ -643,6 +655,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
goto out_label_free;
}
memset(array, 0, sizeof(struct nfs_cache_array));
+ atomic_set(&array->refcount, 1);
array->eof_index = -1;
status = nfs_readdir_alloc_pages(pages, array_size);
@@ -705,8 +718,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
- if (!desc->page->mapping)
- nfs_readdir_clear_array(desc->page);
+ nfs_readdir_clear_array(desc->page);
put_page(desc->page);
desc->page = NULL;
}
@@ -714,8 +726,16 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
static
struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
{
- return read_cache_page(file_inode(desc->file)->i_mapping,
+ struct page *page;
+
+ for (;;) {
+ page = read_cache_page(file_inode(desc->file)->i_mapping,
desc->page_index, (filler_t *)nfs_readdir_filler, desc);
+ if (IS_ERR(page) || grab_page(page))
+ break;
+ put_page(page);
+ }
+ return page;
}
/*
@@ -889,7 +909,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->decode = NFS_PROTO(inode)->decode_dirent;
desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
- nfs_block_sillyrename(dentry);
if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
res = nfs_revalidate_mapping(inode, file->f_mapping);
if (res < 0)
@@ -925,7 +944,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
break;
} while (!desc->eof);
out:
- nfs_unblock_sillyrename(dentry);
if (res > 0)
res = 0;
dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);
@@ -934,13 +952,11 @@ out:
static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
- struct inode *inode = file_inode(filp);
struct nfs_open_dir_context *dir_ctx = filp->private_data;
dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
filp, offset, whence);
- inode_lock(inode);
switch (whence) {
case 1:
offset += filp->f_pos;
@@ -948,16 +964,13 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
if (offset >= 0)
break;
default:
- offset = -EINVAL;
- goto out;
+ return -EINVAL;
}
if (offset != filp->f_pos) {
filp->f_pos = offset;
dir_ctx->dir_cookie = 0;
dir_ctx->duped = 0;
}
-out:
- inode_unlock(inode);
return offset;
}
@@ -1383,7 +1396,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
parent = dentry->d_parent;
/* Protect against concurrent sillydeletes */
trace_nfs_lookup_enter(dir, dentry, flags);
- nfs_block_sillyrename(parent);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
if (error == -ENOENT)
goto no_entry;
@@ -1408,7 +1420,6 @@ no_entry:
}
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out_unblock_sillyrename:
- nfs_unblock_sillyrename(parent);
trace_nfs_lookup_exit(dir, dentry, flags, error);
nfs4_label_free(label);
out:
@@ -1520,9 +1531,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
goto out;
trace_nfs_atomic_open_enter(dir, ctx, open_flags);
- nfs_block_sillyrename(dentry->d_parent);
inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
- nfs_unblock_sillyrename(dentry->d_parent);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
@@ -1766,7 +1775,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
trace_nfs_rmdir_enter(dir, dentry);
if (d_really_is_positive(dentry)) {
- nfs_wait_on_sillyrename(dentry);
+ down_write(&NFS_I(d_inode(dentry))->rmdir_sem);
error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
/* Ensure the VFS deletes this inode */
switch (error) {
@@ -1776,6 +1785,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
case -ENOENT:
nfs_dentry_handle_enoent(dentry);
}
+ up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
} else
error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
trace_nfs_rmdir_exit(dir, dentry, error);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index c93826e4a8c6..741a92c470bb 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -250,7 +250,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
* shunt off direct read and write requests before the VFS gets them,
* so this method is only ever called for swap.
*/
-ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -261,7 +261,7 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
if (iov_iter_rw(iter) == READ)
- return nfs_file_direct_read(iocb, iter, pos);
+ return nfs_file_direct_read(iocb, iter);
return nfs_file_direct_write(iocb, iter);
}
@@ -396,7 +396,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
static void nfs_direct_readpage_release(struct nfs_page *req)
{
dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
- d_inode(req->wb_context->dentry)->i_sb->s_id,
+ req->wb_context->dentry->d_sb->s_id,
(unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)),
req->wb_bytes,
(long long)req_offset(req));
@@ -545,7 +545,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_read - file direct read operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers into which to read data
- * @pos: byte offset in file where reading starts
*
* We use this function for direct reads instead of calling
* generic_file_aio_read() in order to avoid gfar's check to see if
@@ -561,8 +560,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* client must read the updated atime from the server back into its
* cache.
*/
-ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
- loff_t pos)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -574,7 +572,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
- file, count, (long long) pos);
+ file, count, (long long) iocb->ki_pos);
result = 0;
if (!count)
@@ -594,7 +592,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
dreq->inode = inode;
dreq->bytes_left = count;
- dreq->io_start = pos;
+ dreq->io_start = iocb->ki_pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
@@ -606,14 +604,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
dreq->iocb = iocb;
NFS_I(inode)->read_io += count;
- result = nfs_direct_read_schedule_iovec(dreq, iter, pos);
+ result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
inode_unlock(inode);
if (!result) {
result = nfs_direct_wait(dreq);
if (result > 0)
- iocb->ki_pos = pos + result;
+ iocb->ki_pos += result;
}
nfs_direct_req_release(dreq);
@@ -969,7 +967,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers from which to write data
- * @pos: byte offset in file where writing starts
*
* We use this function for direct writes instead of calling
* generic_file_aio_write() in order to avoid taking the inode
@@ -1057,7 +1054,9 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
if (i_size_read(inode) < iocb->ki_pos)
i_size_write(inode, iocb->ki_pos);
spin_unlock(&inode->i_lock);
- generic_write_sync(file, pos, result);
+
+ /* XXX: should check the generic_write_sync retval */
+ generic_write_sync(iocb, result);
}
}
nfs_direct_req_release(dreq);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index be01095b97ae..717a8d6af52d 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -164,7 +164,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
ssize_t result;
if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_read(iocb, to, iocb->ki_pos);
+ return nfs_file_direct_read(iocb, to);
dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 738c84a42eb0..52e7d6869e3b 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1958,9 +1958,7 @@ static void init_once(void *foo)
nfsi->nrequests = 0;
nfsi->commit_info.ncommit = 0;
atomic_set(&nfsi->commit_info.rpcs_out, 0);
- atomic_set(&nfsi->silly_count, 1);
- INIT_HLIST_HEAD(&nfsi->silly_list);
- init_waitqueue_head(&nfsi->waitqueue);
+ init_rwsem(&nfsi->rmdir_sem);
nfs4_init_once(nfsi);
}
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 17c0fa1eccfa..720d92f5abfb 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -11,6 +11,38 @@
#define NFSDBG_FACILITY NFSDBG_PROC
+/*
+ * nfs3_prepare_get_acl, nfs3_complete_get_acl, nfs3_abort_get_acl: Helpers for
+ * caching get_acl results in a race-free way. See fs/posix_acl.c:get_acl()
+ * for explanations.
+ */
+static void nfs3_prepare_get_acl(struct posix_acl **p)
+{
+ struct posix_acl *sentinel = uncached_acl_sentinel(current);
+
+ if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED) {
+ /* Not the first reader or sentinel already in place. */
+ }
+}
+
+static void nfs3_complete_get_acl(struct posix_acl **p, struct posix_acl *acl)
+{
+ struct posix_acl *sentinel = uncached_acl_sentinel(current);
+
+ /* Only cache the ACL if our sentinel is still in place. */
+ posix_acl_dup(acl);
+ if (cmpxchg(p, sentinel, acl) != sentinel)
+ posix_acl_release(acl);
+}
+
+static void nfs3_abort_get_acl(struct posix_acl **p)
+{
+ struct posix_acl *sentinel = uncached_acl_sentinel(current);
+
+ /* Remove our sentinel upon failure. */
+ cmpxchg(p, sentinel, ACL_NOT_CACHED);
+}
+
struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
{
struct nfs_server *server = NFS_SERVER(inode);
@@ -55,6 +87,11 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
if (res.fattr == NULL)
return ERR_PTR(-ENOMEM);
+ if (args.mask & NFS_ACL)
+ nfs3_prepare_get_acl(&inode->i_acl);
+ if (args.mask & NFS_DFACL)
+ nfs3_prepare_get_acl(&inode->i_default_acl);
+
status = rpc_call_sync(server->client_acl, &msg, 0);
dprintk("NFS reply getacl: %d\n", status);
@@ -89,12 +126,12 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
}
if (res.mask & NFS_ACL)
- set_cached_acl(inode, ACL_TYPE_ACCESS, res.acl_access);
+ nfs3_complete_get_acl(&inode->i_acl, res.acl_access);
else
forget_cached_acl(inode, ACL_TYPE_ACCESS);
if (res.mask & NFS_DFACL)
- set_cached_acl(inode, ACL_TYPE_DEFAULT, res.acl_default);
+ nfs3_complete_get_acl(&inode->i_default_acl, res.acl_default);
else
forget_cached_acl(inode, ACL_TYPE_DEFAULT);
@@ -108,6 +145,8 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
}
getout:
+ nfs3_abort_get_acl(&inode->i_acl);
+ nfs3_abort_get_acl(&inode->i_default_acl);
posix_acl_release(res.acl_access);
posix_acl_release(res.acl_default);
nfs_free_fattr(res.fattr);
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 5ba22c6b0ffa..c444285bb1b1 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -201,7 +201,7 @@ int nfs_idmap_init(void)
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred,
(KEY_POS_ALL & ~KEY_POS_SETATTR) |
KEY_USR_VIEW | KEY_USR_READ,
- KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
if (IS_ERR(keyring)) {
ret = PTR_ERR(keyring);
goto failed_put_cred;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 327b8c34d360..084e8570da18 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3777,7 +3777,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
{
- nfs4_setup_sequence(NFS_SERVER(data->dir),
+ nfs4_setup_sequence(NFS_SB(data->dentry->d_sb),
&data->args.seq_args,
&data->res.seq_res,
task);
@@ -6263,10 +6263,10 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
}
static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- void *buf, size_t buflen)
+ struct dentry *unused, struct inode *inode,
+ const char *key, void *buf, size_t buflen)
{
- return nfs4_proc_get_acl(d_inode(dentry), buf, buflen);
+ return nfs4_proc_get_acl(inode, buf, buflen);
}
static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
@@ -6288,11 +6288,11 @@ static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
}
static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- void *buf, size_t buflen)
+ struct dentry *unused, struct inode *inode,
+ const char *key, void *buf, size_t buflen)
{
if (security_ismaclabel(key))
- return nfs4_get_security_label(d_inode(dentry), buf, buflen);
+ return nfs4_get_security_label(inode, buf, buflen);
return -EOPNOTSUPP;
}
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 9f80a086b612..0b9e5cc9a747 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -702,7 +702,7 @@ TRACE_EVENT(nfs_sillyrename_unlink,
),
TP_fast_assign(
- struct inode *dir = data->dir;
+ struct inode *dir = d_inode(data->dentry->d_parent);
size_t len = data->args.name.len;
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index fa538b2ba251..1868246f56e6 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -30,45 +30,11 @@
static void
nfs_free_unlinkdata(struct nfs_unlinkdata *data)
{
- iput(data->dir);
put_rpccred(data->cred);
kfree(data->args.name.name);
kfree(data);
}
-#define NAME_ALLOC_LEN(len) ((len+16) & ~15)
-/**
- * nfs_copy_dname - copy dentry name to data structure
- * @dentry: pointer to dentry
- * @data: nfs_unlinkdata
- */
-static int nfs_copy_dname(struct dentry *dentry, struct nfs_unlinkdata *data)
-{
- char *str;
- int len = dentry->d_name.len;
-
- str = kmemdup(dentry->d_name.name, NAME_ALLOC_LEN(len), GFP_KERNEL);
- if (!str)
- return -ENOMEM;
- data->args.name.len = len;
- data->args.name.name = str;
- return 0;
-}
-
-static void nfs_free_dname(struct nfs_unlinkdata *data)
-{
- kfree(data->args.name.name);
- data->args.name.name = NULL;
- data->args.name.len = 0;
-}
-
-static void nfs_dec_sillycount(struct inode *dir)
-{
- struct nfs_inode *nfsi = NFS_I(dir);
- if (atomic_dec_return(&nfsi->silly_count) == 1)
- wake_up(&nfsi->waitqueue);
-}
-
/**
* nfs_async_unlink_done - Sillydelete post-processing
* @task: rpc_task of the sillydelete
@@ -78,7 +44,7 @@ static void nfs_dec_sillycount(struct inode *dir)
static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- struct inode *dir = data->dir;
+ struct inode *dir = d_inode(data->dentry->d_parent);
trace_nfs_sillyrename_unlink(data, task->tk_status);
if (!NFS_PROTO(dir)->unlink_done(task, dir))
@@ -95,17 +61,21 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
static void nfs_async_unlink_release(void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- struct super_block *sb = data->dir->i_sb;
+ struct dentry *dentry = data->dentry;
+ struct super_block *sb = dentry->d_sb;
- nfs_dec_sillycount(data->dir);
+ up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
+ d_lookup_done(dentry);
nfs_free_unlinkdata(data);
+ dput(dentry);
nfs_sb_deactive(sb);
}
static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- NFS_PROTO(data->dir)->unlink_rpc_prepare(task, data);
+ struct inode *dir = d_inode(data->dentry->d_parent);
+ NFS_PROTO(dir)->unlink_rpc_prepare(task, data);
}
static const struct rpc_call_ops nfs_unlink_ops = {
@@ -114,7 +84,7 @@ static const struct rpc_call_ops nfs_unlink_ops = {
.rpc_call_prepare = nfs_unlink_prepare,
};
-static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data)
+static void nfs_do_call_unlink(struct nfs_unlinkdata *data)
{
struct rpc_message msg = {
.rpc_argp = &data->args,
@@ -129,10 +99,31 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
.flags = RPC_TASK_ASYNC,
};
struct rpc_task *task;
+ struct inode *dir = d_inode(data->dentry->d_parent);
+ nfs_sb_active(dir->i_sb);
+ data->args.fh = NFS_FH(dir);
+ nfs_fattr_init(data->res.dir_attr);
+
+ NFS_PROTO(dir)->unlink_setup(&msg, dir);
+
+ task_setup_data.rpc_client = NFS_CLIENT(dir);
+ task = rpc_run_task(&task_setup_data);
+ if (!IS_ERR(task))
+ rpc_put_task_async(task);
+}
+
+static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
+{
+ struct inode *dir = d_inode(dentry->d_parent);
struct dentry *alias;
- alias = d_lookup(parent, &data->args.name);
- if (alias != NULL) {
+ down_read_non_owner(&NFS_I(dir)->rmdir_sem);
+ alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq);
+ if (IS_ERR(alias)) {
+ up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+ return 0;
+ }
+ if (!d_in_lookup(alias)) {
int ret;
void *devname_garbage = NULL;
@@ -140,10 +131,8 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
* Hey, we raced with lookup... See if we need to transfer
* the sillyrename information to the aliased dentry.
*/
- nfs_free_dname(data);
- ret = nfs_copy_dname(alias, data);
spin_lock(&alias->d_lock);
- if (ret == 0 && d_really_is_positive(alias) &&
+ if (d_really_is_positive(alias) &&
!(alias->d_flags & DCACHE_NFSFS_RENAMED)) {
devname_garbage = alias->d_fsdata;
alias->d_fsdata = data;
@@ -152,8 +141,8 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
} else
ret = 0;
spin_unlock(&alias->d_lock);
- nfs_dec_sillycount(dir);
dput(alias);
+ up_read_non_owner(&NFS_I(dir)->rmdir_sem);
/*
* If we'd displaced old cached devname, free it. At that
* point dentry is definitely not a root, so we won't need
@@ -162,94 +151,18 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
kfree(devname_garbage);
return ret;
}
- data->dir = igrab(dir);
- if (!data->dir) {
- nfs_dec_sillycount(dir);
- return 0;
- }
- nfs_sb_active(dir->i_sb);
- data->args.fh = NFS_FH(dir);
- nfs_fattr_init(data->res.dir_attr);
-
- NFS_PROTO(dir)->unlink_setup(&msg, dir);
-
- task_setup_data.rpc_client = NFS_CLIENT(dir);
- task = rpc_run_task(&task_setup_data);
- if (!IS_ERR(task))
- rpc_put_task_async(task);
+ data->dentry = alias;
+ nfs_do_call_unlink(data);
return 1;
}
-static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
-{
- struct dentry *parent;
- struct inode *dir;
- int ret = 0;
-
-
- parent = dget_parent(dentry);
- if (parent == NULL)
- goto out_free;
- dir = d_inode(parent);
- /* Non-exclusive lock protects against concurrent lookup() calls */
- spin_lock(&dir->i_lock);
- if (atomic_inc_not_zero(&NFS_I(dir)->silly_count) == 0) {
- /* Deferred delete */
- hlist_add_head(&data->list, &NFS_I(dir)->silly_list);
- spin_unlock(&dir->i_lock);
- ret = 1;
- goto out_dput;
- }
- spin_unlock(&dir->i_lock);
- ret = nfs_do_call_unlink(parent, dir, data);
-out_dput:
- dput(parent);
-out_free:
- return ret;
-}
-
-void nfs_wait_on_sillyrename(struct dentry *dentry)
-{
- struct nfs_inode *nfsi = NFS_I(d_inode(dentry));
-
- wait_event(nfsi->waitqueue, atomic_read(&nfsi->silly_count) <= 1);
-}
-
-void nfs_block_sillyrename(struct dentry *dentry)
-{
- struct nfs_inode *nfsi = NFS_I(d_inode(dentry));
-
- wait_event(nfsi->waitqueue, atomic_cmpxchg(&nfsi->silly_count, 1, 0) == 1);
-}
-
-void nfs_unblock_sillyrename(struct dentry *dentry)
-{
- struct inode *dir = d_inode(dentry);
- struct nfs_inode *nfsi = NFS_I(dir);
- struct nfs_unlinkdata *data;
-
- atomic_inc(&nfsi->silly_count);
- spin_lock(&dir->i_lock);
- while (!hlist_empty(&nfsi->silly_list)) {
- if (!atomic_inc_not_zero(&nfsi->silly_count))
- break;
- data = hlist_entry(nfsi->silly_list.first, struct nfs_unlinkdata, list);
- hlist_del(&data->list);
- spin_unlock(&dir->i_lock);
- if (nfs_do_call_unlink(dentry, dir, data) == 0)
- nfs_free_unlinkdata(data);
- spin_lock(&dir->i_lock);
- }
- spin_unlock(&dir->i_lock);
-}
-
/**
* nfs_async_unlink - asynchronous unlinking of a file
* @dir: parent directory of dentry
* @dentry: dentry to unlink
*/
static int
-nfs_async_unlink(struct inode *dir, struct dentry *dentry)
+nfs_async_unlink(struct dentry *dentry, struct qstr *name)
{
struct nfs_unlinkdata *data;
int status = -ENOMEM;
@@ -258,13 +171,18 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry)
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data == NULL)
goto out;
+ data->args.name.name = kstrdup(name->name, GFP_KERNEL);
+ if (!data->args.name.name)
+ goto out_free;
+ data->args.name.len = name->len;
data->cred = rpc_lookup_cred();
if (IS_ERR(data->cred)) {
status = PTR_ERR(data->cred);
- goto out_free;
+ goto out_free_name;
}
data->res.dir_attr = &data->dir_attr;
+ init_waitqueue_head(&data->wq);
status = -EBUSY;
spin_lock(&dentry->d_lock);
@@ -284,6 +202,8 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry)
out_unlock:
spin_unlock(&dentry->d_lock);
put_rpccred(data->cred);
+out_free_name:
+ kfree(data->args.name.name);
out_free:
kfree(data);
out:
@@ -302,17 +222,15 @@ out:
void
nfs_complete_unlink(struct dentry *dentry, struct inode *inode)
{
- struct nfs_unlinkdata *data = NULL;
+ struct nfs_unlinkdata *data;
spin_lock(&dentry->d_lock);
- if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
- dentry->d_flags &= ~DCACHE_NFSFS_RENAMED;
- data = dentry->d_fsdata;
- dentry->d_fsdata = NULL;
- }
+ dentry->d_flags &= ~DCACHE_NFSFS_RENAMED;
+ data = dentry->d_fsdata;
+ dentry->d_fsdata = NULL;
spin_unlock(&dentry->d_lock);
- if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data)))
+ if (NFS_STALE(inode) || !nfs_call_unlink(dentry, data))
nfs_free_unlinkdata(data);
}
@@ -559,18 +477,10 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
/* queue unlink first. Can't do this from rpc_release as it
* has to allocate memory
*/
- error = nfs_async_unlink(dir, dentry);
+ error = nfs_async_unlink(dentry, &sdentry->d_name);
if (error)
goto out_dput;
- /* populate unlinkdata with the right dname */
- error = nfs_copy_dname(sdentry,
- (struct nfs_unlinkdata *)dentry->d_fsdata);
- if (error) {
- nfs_cancel_async_unlink(dentry);
- goto out_dput;
- }
-
/* run the rename task, undo unlink if it fails */
task = nfs_async_rename(dir, dir, dentry, sdentry,
nfs_complete_sillyrename);
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 51c3b06e8036..d818e4ffd79f 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -552,7 +552,7 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp,
* different read/write sizes for file systems known to have
* problems with large blocks */
if (nfserr == 0) {
- struct super_block *sb = d_inode(argp->fh.fh_dentry)->i_sb;
+ struct super_block *sb = argp->fh.fh_dentry->d_sb;
/* Note that we don't care for remote fs's here */
if (sb->s_magic == MSDOS_SUPER_MAGIC) {
@@ -588,7 +588,7 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp,
nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP);
if (nfserr == 0) {
- struct super_block *sb = d_inode(argp->fh.fh_dentry)->i_sb;
+ struct super_block *sb = argp->fh.fh_dentry->d_sb;
/* Note that we don't care for remote fs's here */
switch (sb->s_magic) {
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 2246454dec76..93d5853f8c99 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -146,7 +146,7 @@ static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp)
default:
case FSIDSOURCE_DEV:
p = xdr_encode_hyper(p, (u64)huge_encode_dev
- (d_inode(fhp->fh_dentry)->i_sb->s_dev));
+ (fhp->fh_dentry->d_sb->s_dev));
break;
case FSIDSOURCE_FSID:
p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index c1681ce894c5..a8919444c460 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -426,7 +426,7 @@ static bool is_root_export(struct svc_export *exp)
static struct super_block *exp_sb(struct svc_export *exp)
{
- return d_inode(exp->ex_path.dentry)->i_sb;
+ return exp->ex_path.dentry->d_sb;
}
static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index d40010e4f1a9..6fbd81ecb410 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -935,8 +935,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
int stable = *stablep;
int use_wgather;
loff_t pos = offset;
- loff_t end = LLONG_MAX;
unsigned int pflags = current->flags;
+ int flags = 0;
if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
/*
@@ -955,9 +955,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
if (!EX_ISSYNC(exp))
stable = 0;
+ if (stable && !use_wgather)
+ flags |= RWF_SYNC;
+
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
- host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0);
+ host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, flags);
set_fs(oldfs);
if (host_err < 0)
goto out_nfserr;
@@ -965,15 +968,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
nfsdstats.io_write += host_err;
fsnotify_modify(file);
- if (stable) {
- if (use_wgather) {
- host_err = wait_for_concurrent_writes(file);
- } else {
- if (*cnt)
- end = offset + *cnt - 1;
- host_err = vfs_fsync_range(file, offset, end, 0);
- }
- }
+ if (stable && use_wgather)
+ host_err = wait_for_concurrent_writes(file);
out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 2ccbf5531554..1a85d94f5b25 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -13,13 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Original code was written by Koji Sato <koji@osrg.net>.
- * Two allocators were unified by Ryusuke Konishi <ryusuke@osrg.net>,
- * Amagai Yoshiji <amagai@osrg.net>.
+ * Originally written by Koji Sato.
+ * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji.
*/
#include <linux/types.h>
@@ -58,7 +53,7 @@ nilfs_palloc_groups_count(const struct inode *inode)
* @inode: inode of metadata file using this allocator
* @entry_size: size of the persistent object
*/
-int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned entry_size)
+int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned int entry_size)
{
struct nilfs_mdt_info *mi = NILFS_MDT(inode);
@@ -73,13 +68,17 @@ int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned entry_size)
mi->mi_blocks_per_group =
DIV_ROUND_UP(nilfs_palloc_entries_per_group(inode),
mi->mi_entries_per_block) + 1;
- /* Number of blocks in a group including entry blocks and
- a bitmap block */
+ /*
+ * Number of blocks in a group including entry blocks
+ * and a bitmap block
+ */
mi->mi_blocks_per_desc_block =
nilfs_palloc_groups_per_desc_block(inode) *
mi->mi_blocks_per_group + 1;
- /* Number of blocks per descriptor including the
- descriptor block */
+ /*
+ * Number of blocks per descriptor including the
+ * descriptor block
+ */
return 0;
}
@@ -389,7 +388,7 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
*/
static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
unsigned long target,
- unsigned bsize,
+ unsigned int bsize,
spinlock_t *lock)
{
int pos, end = bsize;
@@ -624,7 +623,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
nilfs_warning(inode->i_sb, __func__,
- "entry number %llu already freed: ino=%lu\n",
+ "entry number %llu already freed: ino=%lu",
(unsigned long long)req->pr_entry_nr,
(unsigned long)inode->i_ino);
else
@@ -665,7 +664,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
nilfs_warning(inode->i_sb, __func__,
- "entry number %llu already freed: ino=%lu\n",
+ "entry number %llu already freed: ino=%lu",
(unsigned long long)req->pr_entry_nr,
(unsigned long)inode->i_ino);
else
@@ -740,8 +739,8 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
unsigned long group, group_offset;
__u64 group_min_nr, last_nrs[8];
const unsigned long epg = nilfs_palloc_entries_per_group(inode);
- const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block;
- unsigned entry_start, end, pos;
+ const unsigned int epb = NILFS_MDT(inode)->mi_entries_per_block;
+ unsigned int entry_start, end, pos;
spinlock_t *lock;
int i, j, k, ret;
u32 nfree;
@@ -774,7 +773,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
if (!nilfs_clear_bit_atomic(lock, group_offset,
bitmap)) {
nilfs_warning(inode->i_sb, __func__,
- "entry number %llu already freed: ino=%lu\n",
+ "entry number %llu already freed: ino=%lu",
(unsigned long long)entry_nrs[j],
(unsigned long)inode->i_ino);
} else {
@@ -819,7 +818,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
last_nrs[k]);
if (ret && ret != -ENOENT) {
nilfs_warning(inode->i_sb, __func__,
- "failed to delete block of entry %llu: ino=%lu, err=%d\n",
+ "failed to delete block of entry %llu: ino=%lu, err=%d",
(unsigned long long)last_nrs[k],
(unsigned long)inode->i_ino, ret);
}
@@ -838,7 +837,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
ret = nilfs_palloc_delete_bitmap_block(inode, group);
if (ret && ret != -ENOENT) {
nilfs_warning(inode->i_sb, __func__,
- "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n",
+ "failed to delete bitmap block of group %lu: ino=%lu, err=%d",
group,
(unsigned long)inode->i_ino, ret);
}
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index 6e6f49aa53df..05149e606a78 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -13,13 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Original code was written by Koji Sato <koji@osrg.net>.
- * Two allocators were unified by Ryusuke Konishi <ryusuke@osrg.net>,
- * Amagai Yoshiji <amagai@osrg.net>.
+ * Originally written by Koji Sato.
+ * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji.
*/
#ifndef _NILFS_ALLOC_H
@@ -42,7 +37,7 @@ nilfs_palloc_entries_per_group(const struct inode *inode)
return 1UL << (inode->i_blkbits + 3 /* log2(8 = CHAR_BITS) */);
}
-int nilfs_palloc_init_blockgroup(struct inode *, unsigned);
+int nilfs_palloc_init_blockgroup(struct inode *, unsigned int);
int nilfs_palloc_get_entry_block(struct inode *, __u64, int,
struct buffer_head **);
void *nilfs_palloc_block_get_entry(const struct inode *, __u64,
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index a9fb3636c142..f2a7877e0c8c 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#include <linux/fs.h>
@@ -46,7 +42,7 @@ static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap,
if (err == -EINVAL) {
nilfs_error(inode->i_sb, fname,
- "broken bmap (inode number=%lu)\n", inode->i_ino);
+ "broken bmap (inode number=%lu)", inode->i_ino);
err = -EIO;
}
return err;
@@ -97,7 +93,7 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level,
}
int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp,
- unsigned maxblocks)
+ unsigned int maxblocks)
{
int ret;
diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h
index bfa817ce40b3..b6a4c8f93ac8 100644
--- a/fs/nilfs2/bmap.h
+++ b/fs/nilfs2/bmap.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#ifndef _NILFS_BMAP_H
@@ -61,7 +57,7 @@ struct nilfs_bmap_stats {
struct nilfs_bmap_operations {
int (*bop_lookup)(const struct nilfs_bmap *, __u64, int, __u64 *);
int (*bop_lookup_contig)(const struct nilfs_bmap *, __u64, __u64 *,
- unsigned);
+ unsigned int);
int (*bop_insert)(struct nilfs_bmap *, __u64, __u64);
int (*bop_delete)(struct nilfs_bmap *, __u64);
void (*bop_clear)(struct nilfs_bmap *);
@@ -126,10 +122,14 @@ struct nilfs_bmap {
/* pointer type */
#define NILFS_BMAP_PTR_P 0 /* physical block number (i.e. LBN) */
-#define NILFS_BMAP_PTR_VS 1 /* virtual block number (single
- version) */
-#define NILFS_BMAP_PTR_VM 2 /* virtual block number (has multiple
- versions) */
+#define NILFS_BMAP_PTR_VS 1 /*
+ * virtual block number (single
+ * version)
+ */
+#define NILFS_BMAP_PTR_VM 2 /*
+ * virtual block number (has multiple
+ * versions)
+ */
#define NILFS_BMAP_PTR_U (-1) /* never perform pointer operations */
#define NILFS_BMAP_USE_VBN(bmap) ((bmap)->b_ptr_type > 0)
@@ -154,7 +154,7 @@ struct nilfs_bmap_store {
int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *);
int nilfs_bmap_read(struct nilfs_bmap *, struct nilfs_inode *);
void nilfs_bmap_write(struct nilfs_bmap *, struct nilfs_inode *);
-int nilfs_bmap_lookup_contig(struct nilfs_bmap *, __u64, __u64 *, unsigned);
+int nilfs_bmap_lookup_contig(struct nilfs_bmap *, __u64, __u64 *, unsigned int);
int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec);
int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key);
int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp);
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index e0c9daf9aa22..0576033699bc 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -13,13 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * This file was originally written by Seiji Kihara <kihara@osrg.net>
- * and fully revised by Ryusuke Konishi <ryusuke@osrg.net> for
- * stabilization and simplification.
+ * Originally written by Seiji Kihara.
+ * Fully revised by Ryusuke Konishi for stabilization and simplification.
*
*/
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index d876b565ce64..2cc1b80e18f7 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -13,12 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Seiji Kihara <kihara@osrg.net>
- * Revised by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Seiji Kihara.
+ * Revised by Ryusuke Konishi.
*/
#ifndef _NILFS_BTNODE_H
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 3a3821b00486..eccb1c89ccbb 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#include <linux/slab.h>
@@ -689,7 +685,8 @@ static int nilfs_btree_lookup(const struct nilfs_bmap *btree,
}
static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree,
- __u64 key, __u64 *ptrp, unsigned maxblocks)
+ __u64 key, __u64 *ptrp,
+ unsigned int maxblocks)
{
struct nilfs_btree_path *path;
struct nilfs_btree_node *node;
@@ -1032,12 +1029,12 @@ static __u64 nilfs_btree_find_target_v(const struct nilfs_bmap *btree,
if (ptr != NILFS_BMAP_INVALID_PTR)
/* sequential access */
return ptr;
- else {
- ptr = nilfs_btree_find_near(btree, path);
- if (ptr != NILFS_BMAP_INVALID_PTR)
- /* near */
- return ptr;
- }
+
+ ptr = nilfs_btree_find_near(btree, path);
+ if (ptr != NILFS_BMAP_INVALID_PTR)
+ /* near */
+ return ptr;
+
/* block group */
return nilfs_bmap_find_target_in_group(btree);
}
diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h
index 22c02e35b6ef..df1a25faa83b 100644
--- a/fs/nilfs2/btree.h
+++ b/fs/nilfs2/btree.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#ifndef _NILFS_BTREE_H
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index b6596cab9e99..8a3d3b65af3f 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#include <linux/kernel.h>
@@ -41,6 +37,7 @@ static unsigned long
nilfs_cpfile_get_blkoff(const struct inode *cpfile, __u64 cno)
{
__u64 tcno = cno + NILFS_MDT(cpfile)->mi_first_entry_offset - 1;
+
do_div(tcno, nilfs_cpfile_checkpoints_per_block(cpfile));
return (unsigned long)tcno;
}
@@ -50,6 +47,7 @@ static unsigned long
nilfs_cpfile_get_offset(const struct inode *cpfile, __u64 cno)
{
__u64 tcno = cno + NILFS_MDT(cpfile)->mi_first_entry_offset - 1;
+
return do_div(tcno, nilfs_cpfile_checkpoints_per_block(cpfile));
}
@@ -433,7 +431,8 @@ static void nilfs_cpfile_checkpoint_to_cpinfo(struct inode *cpfile,
}
static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
- void *buf, unsigned cisz, size_t nci)
+ void *buf, unsigned int cisz,
+ size_t nci)
{
struct nilfs_checkpoint *cp;
struct nilfs_cpinfo *ci = buf;
@@ -484,7 +483,8 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
}
static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
- void *buf, unsigned cisz, size_t nci)
+ void *buf, unsigned int cisz,
+ size_t nci)
{
struct buffer_head *bh;
struct nilfs_cpfile_header *header;
@@ -570,7 +570,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
*/
ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode,
- void *buf, unsigned cisz, size_t nci)
+ void *buf, unsigned int cisz, size_t nci)
{
switch (mode) {
case NILFS_CHECKPOINT:
@@ -870,8 +870,10 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
void *kaddr;
int ret;
- /* CP number is invalid if it's zero or larger than the
- largest exist one.*/
+ /*
+ * CP number is invalid if it's zero or larger than the
+ * largest existing one.
+ */
if (cno == 0 || cno >= nilfs_mdt_cno(cpfile))
return -ENOENT;
down_read(&NILFS_MDT(cpfile)->mi_sem);
diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h
index a242b9a314f9..0249744ae234 100644
--- a/fs/nilfs2/cpfile.h
+++ b/fs/nilfs2/cpfile.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#ifndef _NILFS_CPFILE_H
@@ -37,8 +33,8 @@ int nilfs_cpfile_delete_checkpoint(struct inode *, __u64);
int nilfs_cpfile_change_cpmode(struct inode *, __u64, int);
int nilfs_cpfile_is_snapshot(struct inode *, __u64);
int nilfs_cpfile_get_stat(struct inode *, struct nilfs_cpstat *);
-ssize_t nilfs_cpfile_get_cpinfo(struct inode *, __u64 *, int, void *, unsigned,
- size_t);
+ssize_t nilfs_cpfile_get_cpinfo(struct inode *, __u64 *, int, void *,
+ unsigned int, size_t);
int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
struct nilfs_inode *raw_inode, struct inode **inodep);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 7dc23f100e57..7367610ea807 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#include <linux/types.h>
@@ -428,7 +424,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
return ret;
}
-ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned visz,
+ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz,
size_t nvi)
{
struct buffer_head *entry_bh;
diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h
index cbd8e9732503..abbfdabcabea 100644
--- a/fs/nilfs2/dat.h
+++ b/fs/nilfs2/dat.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#ifndef _NILFS_DAT_H
@@ -51,7 +47,7 @@ void nilfs_dat_abort_update(struct inode *, struct nilfs_palloc_req *,
int nilfs_dat_mark_dirty(struct inode *, __u64);
int nilfs_dat_freev(struct inode *, __u64 *, size_t);
int nilfs_dat_move(struct inode *, __u64, sector_t);
-ssize_t nilfs_dat_get_vinfo(struct inode *, void *, unsigned, size_t);
+ssize_t nilfs_dat_get_vinfo(struct inode *, void *, unsigned int, size_t);
int nilfs_dat_read(struct super_block *sb, size_t entry_size,
struct nilfs_inode *raw_inode, struct inode **inodep);
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index e08f064e4bd7..e506f4f7120a 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Modified for NILFS by Amagai Yoshiji <amagai@osrg.net>
+ * Modified for NILFS by Amagai Yoshiji.
*/
/*
* linux/fs/ext2/dir.c
@@ -50,7 +46,7 @@
* nilfs uses block-sized chunks. Arguably, sector-sized ones would be
* more robust, but we have what we have
*/
-static inline unsigned nilfs_chunk_size(struct inode *inode)
+static inline unsigned int nilfs_chunk_size(struct inode *inode)
{
return inode->i_sb->s_blocksize;
}
@@ -65,9 +61,9 @@ static inline void nilfs_put_page(struct page *page)
* Return the offset into page `page_nr' of the last valid
* byte in that page, plus one.
*/
-static unsigned nilfs_last_byte(struct inode *inode, unsigned long page_nr)
+static unsigned int nilfs_last_byte(struct inode *inode, unsigned long page_nr)
{
- unsigned last_byte = inode->i_size;
+ unsigned int last_byte = inode->i_size;
last_byte -= page_nr << PAGE_SHIFT;
if (last_byte > PAGE_SIZE)
@@ -75,20 +71,22 @@ static unsigned nilfs_last_byte(struct inode *inode, unsigned long page_nr)
return last_byte;
}
-static int nilfs_prepare_chunk(struct page *page, unsigned from, unsigned to)
+static int nilfs_prepare_chunk(struct page *page, unsigned int from,
+ unsigned int to)
{
loff_t pos = page_offset(page) + from;
+
return __block_write_begin(page, pos, to - from, nilfs_get_block);
}
static void nilfs_commit_chunk(struct page *page,
struct address_space *mapping,
- unsigned from, unsigned to)
+ unsigned int from, unsigned int to)
{
struct inode *dir = mapping->host;
loff_t pos = page_offset(page) + from;
- unsigned len = to - from;
- unsigned nr_dirty, copied;
+ unsigned int len = to - from;
+ unsigned int nr_dirty, copied;
int err;
nr_dirty = nilfs_page_count_clean_buffers(page, from, to);
@@ -102,14 +100,14 @@ static void nilfs_commit_chunk(struct page *page,
unlock_page(page);
}
-static void nilfs_check_page(struct page *page)
+static bool nilfs_check_page(struct page *page)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
- unsigned chunk_size = nilfs_chunk_size(dir);
+ unsigned int chunk_size = nilfs_chunk_size(dir);
char *kaddr = page_address(page);
- unsigned offs, rec_len;
- unsigned limit = PAGE_SIZE;
+ unsigned int offs, rec_len;
+ unsigned int limit = PAGE_SIZE;
struct nilfs_dir_entry *p;
char *error;
@@ -137,7 +135,7 @@ static void nilfs_check_page(struct page *page)
goto Eend;
out:
SetPageChecked(page);
- return;
+ return true;
/* Too bad, we had an error */
@@ -173,8 +171,8 @@ Eend:
dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
(unsigned long) le64_to_cpu(p->inode));
fail:
- SetPageChecked(page);
SetPageError(page);
+ return false;
}
static struct page *nilfs_get_page(struct inode *dir, unsigned long n)
@@ -184,10 +182,10 @@ static struct page *nilfs_get_page(struct inode *dir, unsigned long n)
if (!IS_ERR(page)) {
kmap(page);
- if (!PageChecked(page))
- nilfs_check_page(page);
- if (PageError(page))
- goto fail;
+ if (unlikely(!PageChecked(page))) {
+ if (PageError(page) || !nilfs_check_page(page))
+ goto fail;
+ }
}
return page;
@@ -259,7 +257,6 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
unsigned int offset = pos & ~PAGE_MASK;
unsigned long n = pos >> PAGE_SHIFT;
unsigned long npages = dir_pages(inode);
-/* unsigned chunk_mask = ~(nilfs_chunk_size(inode)-1); */
if (pos > inode->i_size - NILFS_DIR_REC_LEN(1))
return 0;
@@ -321,7 +318,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
{
const unsigned char *name = qstr->name;
int namelen = qstr->len;
- unsigned reclen = NILFS_DIR_REC_LEN(namelen);
+ unsigned int reclen = NILFS_DIR_REC_LEN(namelen);
unsigned long start, n;
unsigned long npages = dir_pages(dir);
struct page *page = NULL;
@@ -340,6 +337,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
n = start;
do {
char *kaddr;
+
page = nilfs_get_page(dir, n);
if (!IS_ERR(page)) {
kaddr = page_address(page);
@@ -410,8 +408,8 @@ ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)
void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
struct page *page, struct inode *inode)
{
- unsigned from = (char *) de - (char *) page_address(page);
- unsigned to = from + nilfs_rec_len_from_disk(de->rec_len);
+ unsigned int from = (char *)de - (char *)page_address(page);
+ unsigned int to = from + nilfs_rec_len_from_disk(de->rec_len);
struct address_space *mapping = page->mapping;
int err;
@@ -433,15 +431,15 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
struct inode *dir = d_inode(dentry->d_parent);
const unsigned char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
- unsigned chunk_size = nilfs_chunk_size(dir);
- unsigned reclen = NILFS_DIR_REC_LEN(namelen);
+ unsigned int chunk_size = nilfs_chunk_size(dir);
+ unsigned int reclen = NILFS_DIR_REC_LEN(namelen);
unsigned short rec_len, name_len;
struct page *page = NULL;
struct nilfs_dir_entry *de;
unsigned long npages = dir_pages(dir);
unsigned long n;
char *kaddr;
- unsigned from, to;
+ unsigned int from, to;
int err;
/*
@@ -533,13 +531,14 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
struct address_space *mapping = page->mapping;
struct inode *inode = mapping->host;
char *kaddr = page_address(page);
- unsigned from = ((char *)dir - kaddr) & ~(nilfs_chunk_size(inode) - 1);
- unsigned to = ((char *)dir - kaddr) +
- nilfs_rec_len_from_disk(dir->rec_len);
- struct nilfs_dir_entry *pde = NULL;
- struct nilfs_dir_entry *de = (struct nilfs_dir_entry *)(kaddr + from);
+ unsigned int from, to;
+ struct nilfs_dir_entry *de, *pde = NULL;
int err;
+ from = ((char *)dir - kaddr) & ~(nilfs_chunk_size(inode) - 1);
+ to = ((char *)dir - kaddr) + nilfs_rec_len_from_disk(dir->rec_len);
+ de = (struct nilfs_dir_entry *)(kaddr + from);
+
while ((char *)de < (char *)dir) {
if (de->rec_len == 0) {
nilfs_error(inode->i_sb, __func__,
@@ -572,7 +571,7 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent)
{
struct address_space *mapping = inode->i_mapping;
struct page *page = grab_cache_page(mapping, 0);
- unsigned chunk_size = nilfs_chunk_size(inode);
+ unsigned int chunk_size = nilfs_chunk_size(inode);
struct nilfs_dir_entry *de;
int err;
void *kaddr;
@@ -630,8 +629,8 @@ int nilfs_empty_dir(struct inode *inode)
while ((char *)de <= kaddr) {
if (de->rec_len == 0) {
nilfs_error(inode->i_sb, __func__,
- "zero-length directory entry "
- "(kaddr=%p, de=%p)\n", kaddr, de);
+ "zero-length directory entry (kaddr=%p, de=%p)",
+ kaddr, de);
goto not_empty;
}
if (de->inode != 0) {
@@ -661,7 +660,7 @@ not_empty:
const struct file_operations nilfs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = nilfs_readdir,
+ .iterate_shared = nilfs_readdir,
.unlocked_ioctl = nilfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = nilfs_compat_ioctl,
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index ebf89fd8ac1a..251a44928405 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#include <linux/errno.h>
@@ -62,7 +58,7 @@ static int nilfs_direct_lookup(const struct nilfs_bmap *direct,
static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct,
__u64 key, __u64 *ptrp,
- unsigned maxblocks)
+ unsigned int maxblocks)
{
struct inode *dat = NULL;
__u64 ptr, ptr2;
@@ -83,7 +79,8 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct,
ptr = blocknr;
}
- maxblocks = min_t(unsigned, maxblocks, NILFS_DIRECT_KEY_MAX - key + 1);
+ maxblocks = min_t(unsigned int, maxblocks,
+ NILFS_DIRECT_KEY_MAX - key + 1);
for (cnt = 1; cnt < maxblocks &&
(ptr2 = nilfs_direct_get_ptr(direct, key + cnt)) !=
NILFS_BMAP_INVALID_PTR;
@@ -110,9 +107,9 @@ nilfs_direct_find_target_v(const struct nilfs_bmap *direct, __u64 key)
if (ptr != NILFS_BMAP_INVALID_PTR)
/* sequential access */
return ptr;
- else
- /* block group */
- return nilfs_bmap_find_target_in_group(direct);
+
+ /* block group */
+ return nilfs_bmap_find_target_in_group(direct);
}
static int nilfs_direct_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr)
diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h
index dc643de20a25..3015a6e78724 100644
--- a/fs/nilfs2/direct.h
+++ b/fs/nilfs2/direct.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#ifndef _NILFS_DIRECT_H
diff --git a/fs/nilfs2/export.h b/fs/nilfs2/export.h
index 19ccbf9522ab..00107fdb9343 100644
--- a/fs/nilfs2/export.h
+++ b/fs/nilfs2/export.h
@@ -20,6 +20,6 @@ struct nilfs_fid {
u32 parent_gen;
u64 parent_ino;
-} __attribute__ ((packed));
+} __packed;
#endif
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 088ba001c6ef..547381f3ce13 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -13,12 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Amagai Yoshiji <amagai@osrg.net>,
- * Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Amagai Yoshiji and Ryusuke Konishi.
*/
#include <linux/fs.h>
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 0224b7826ace..693aded72498 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -13,13 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Seiji Kihara <kihara@osrg.net>, Amagai Yoshiji <amagai@osrg.net>,
- * and Ryusuke Konishi <ryusuke@osrg.net>.
- * Revised by Ryusuke Konishi <ryusuke@osrg.net>.
+ * Written by Seiji Kihara, Amagai Yoshiji, and Ryusuke Konishi.
+ * Revised by Ryusuke Konishi.
*
*/
/*
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 6548c7851b48..1d2b1805327a 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -13,12 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Amagai Yoshiji <amagai@osrg.net>.
- * Revised by Ryusuke Konishi <ryusuke@osrg.net>.
+ * Written by Amagai Yoshiji.
+ * Revised by Ryusuke Konishi.
*
*/
@@ -68,8 +64,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
struct nilfs_palloc_req req;
int ret;
- req.pr_entry_nr = 0; /* 0 says find free inode from beginning of
- a group. dull code!! */
+ req.pr_entry_nr = 0; /*
+ * 0 says find free inode from beginning
+ * of a group. dull code!!
+ */
req.pr_entry_bh = NULL;
ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h
index 679674d13372..23ad2f091e76 100644
--- a/fs/nilfs2/ifile.h
+++ b/fs/nilfs2/ifile.h
@@ -13,12 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Amagai Yoshiji <amagai@osrg.net>
- * Revised by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Amagai Yoshiji.
+ * Revised by Ryusuke Konishi.
*
*/
@@ -36,6 +32,7 @@ static inline struct nilfs_inode *
nilfs_ifile_map_inode(struct inode *ifile, ino_t ino, struct buffer_head *ibh)
{
void *kaddr = kmap(ibh->b_page);
+
return nilfs_palloc_block_get_entry(ifile, ino, ibh, kaddr);
}
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 534631358b13..a0ebdb17e912 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
@@ -87,7 +83,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
__u64 blknum = 0;
int err = 0, ret;
- unsigned maxblocks = bh_result->b_size >> inode->i_blkbits;
+ unsigned int maxblocks = bh_result->b_size >> inode->i_blkbits;
down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
ret = nilfs_bmap_lookup_contig(ii->i_bmap, blkoff, &blknum, maxblocks);
@@ -133,11 +129,14 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
/* Error handling should be detailed */
set_buffer_new(bh_result);
set_buffer_delay(bh_result);
- map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed
- to proper value */
+ map_bh(bh_result, inode->i_sb, 0);
+ /* Disk block number must be changed to proper value */
+
} else if (ret == -ENOENT) {
- /* not found is not error (e.g. hole); must return without
- the mapped state flag. */
+ /*
+ * not found is not error (e.g. hole); must return without
+ * the mapped state flag.
+ */
;
} else {
err = ret;
@@ -167,7 +166,7 @@ static int nilfs_readpage(struct file *file, struct page *page)
* @nr_pages - number of pages to be read
*/
static int nilfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+ struct list_head *pages, unsigned int nr_pages)
{
return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
}
@@ -226,7 +225,7 @@ static int nilfs_set_page_dirty(struct page *page)
int ret = __set_page_dirty_nobuffers(page);
if (page_has_buffers(page)) {
- unsigned nr_dirty = 0;
+ unsigned int nr_dirty = 0;
struct buffer_head *bh, *head;
/*
@@ -249,7 +248,7 @@ static int nilfs_set_page_dirty(struct page *page)
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
} else if (ret) {
- unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
+ unsigned int nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
nilfs_set_file_dirty(inode, nr_dirty);
}
@@ -291,8 +290,8 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
- unsigned start = pos & (PAGE_SIZE - 1);
- unsigned nr_dirty;
+ unsigned int start = pos & (PAGE_SIZE - 1);
+ unsigned int nr_dirty;
int err;
nr_dirty = nilfs_page_count_clean_buffers(page, start,
@@ -305,7 +304,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
}
static ssize_t
-nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
+nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct inode *inode = file_inode(iocb->ki_filp);
@@ -313,7 +312,7 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
return 0;
/* Needs synchronization with the cleaner */
- return blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block);
+ return blockdev_direct_IO(iocb, inode, iter, nilfs_get_block);
}
const struct address_space_operations nilfs_aops = {
@@ -399,23 +398,26 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
- goto failed_after_creation; /* never occur. When supporting
- nilfs_init_acl(), proper cancellation of
- above jobs should be considered */
+ /*
+ * Never occur. When supporting nilfs_init_acl(),
+ * proper cancellation of above jobs should be considered.
+ */
+ goto failed_after_creation;
return inode;
failed_after_creation:
clear_nlink(inode);
unlock_new_inode(inode);
- iput(inode); /* raw_inode will be deleted through
- nilfs_evict_inode() */
+ iput(inode); /*
+ * raw_inode will be deleted through
+ * nilfs_evict_inode().
+ */
goto failed;
failed_ifile_create_inode:
make_bad_inode(inode);
- iput(inode); /* if i_nlink == 1, generic_forget_inode() will be
- called */
+ iput(inode);
failed:
return ERR_PTR(err);
}
@@ -666,8 +668,10 @@ void nilfs_write_inode_common(struct inode *inode,
else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
raw_inode->i_device_code =
cpu_to_le64(huge_encode_dev(inode->i_rdev));
- /* When extending inode, nilfs->ns_inode_size should be checked
- for substitutions of appended fields */
+ /*
+ * When extending inode, nilfs->ns_inode_size should be checked
+ * for substitutions of appended fields.
+ */
}
void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags)
@@ -685,9 +689,12 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags)
set_bit(NILFS_I_INODE_SYNC, &ii->i_state);
nilfs_write_inode_common(inode, raw_inode, 0);
- /* XXX: call with has_bmap = 0 is a workaround to avoid
- deadlock of bmap. This delays update of i_bmap to just
- before writing */
+ /*
+ * XXX: call with has_bmap = 0 is a workaround to avoid
+ * deadlock of bmap. This delays update of i_bmap to just
+ * before writing.
+ */
+
nilfs_ifile_unmap_inode(ifile, ino, ibh);
}
@@ -752,14 +759,15 @@ void nilfs_truncate(struct inode *inode)
nilfs_mark_inode_dirty(inode);
nilfs_set_file_dirty(inode, 0);
nilfs_transaction_commit(sb);
- /* May construct a logical segment and may fail in sync mode.
- But truncate has no return value. */
+ /*
+ * May construct a logical segment and may fail in sync mode.
+ * But truncate has no return value.
+ */
}
static void nilfs_clear_inode(struct inode *inode)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
- struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
/*
* Free resources allocated in nilfs_read_inode(), here.
@@ -768,8 +776,8 @@ static void nilfs_clear_inode(struct inode *inode)
brelse(ii->i_bh);
ii->i_bh = NULL;
- if (mdi && mdi->mi_palloc_cache)
- nilfs_palloc_destroy_cache(inode);
+ if (nilfs_is_metadata_file_inode(inode))
+ nilfs_mdt_clear(inode);
if (test_bit(NILFS_I_BMAP, &ii->i_state))
nilfs_bmap_clear(ii->i_bmap);
@@ -811,8 +819,10 @@ void nilfs_evict_inode(struct inode *inode)
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_transaction_commit(sb);
- /* May construct a logical segment and may fail in sync mode.
- But delete_inode has no return value. */
+ /*
+ * May construct a logical segment and may fail in sync mode.
+ * But delete_inode has no return value.
+ */
}
int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
@@ -856,6 +866,7 @@ out_err:
int nilfs_permission(struct inode *inode, int mask)
{
struct nilfs_root *root = NILFS_I(inode)->i_root;
+
if ((mask & MAY_WRITE) && root &&
root->cno != NILFS_CPTREE_CURRENT_CNO)
return -EROFS; /* snapshot is not writable */
@@ -906,7 +917,7 @@ int nilfs_inode_dirty(struct inode *inode)
return ret;
}
-int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
+int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
@@ -919,17 +930,23 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
spin_lock(&nilfs->ns_inode_lock);
if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
!test_bit(NILFS_I_BUSY, &ii->i_state)) {
- /* Because this routine may race with nilfs_dispose_list(),
- we have to check NILFS_I_QUEUED here, too. */
+ /*
+ * Because this routine may race with nilfs_dispose_list(),
+ * we have to check NILFS_I_QUEUED here, too.
+ */
if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) {
- /* This will happen when somebody is freeing
- this inode. */
+ /*
+ * This will happen when somebody is freeing
+ * this inode.
+ */
nilfs_warning(inode->i_sb, __func__,
- "cannot get inode (ino=%lu)\n",
+ "cannot get inode (ino=%lu)",
inode->i_ino);
spin_unlock(&nilfs->ns_inode_lock);
- return -EINVAL; /* NILFS_I_DIRTY may remain for
- freeing inode */
+ return -EINVAL; /*
+ * NILFS_I_DIRTY may remain for
+ * freeing inode.
+ */
}
list_move_tail(&ii->i_dirty, &nilfs->ns_dirty_files);
set_bit(NILFS_I_QUEUED, &ii->i_state);
@@ -946,7 +963,7 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
err = nilfs_load_inode_block(inode, &ibh);
if (unlikely(err)) {
nilfs_warning(inode->i_sb, __func__,
- "failed to reget inode block.\n");
+ "failed to reget inode block.");
return err;
}
nilfs_update_inode(inode, ibh, flags);
@@ -973,7 +990,7 @@ void nilfs_dirty_inode(struct inode *inode, int flags)
if (is_bad_inode(inode)) {
nilfs_warning(inode->i_sb, __func__,
- "tried to mark bad_inode dirty. ignored.\n");
+ "tried to mark bad_inode dirty. ignored.");
dump_stack();
return;
}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index e8fe24882b5b..358b57e2cdf9 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#include <linux/fs.h>
@@ -783,6 +779,7 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
size_t nmembs = argv->v_nmembs;
struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap;
struct nilfs_bdesc *bdescs = buf;
+ struct buffer_head *bh;
int ret, i;
for (i = 0; i < nmembs; i++) {
@@ -800,12 +797,16 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
/* skip dead block */
continue;
if (bdescs[i].bd_level == 0) {
- ret = nilfs_mdt_mark_block_dirty(nilfs->ns_dat,
- bdescs[i].bd_offset);
- if (ret < 0) {
+ ret = nilfs_mdt_get_block(nilfs->ns_dat,
+ bdescs[i].bd_offset,
+ false, NULL, &bh);
+ if (unlikely(ret)) {
WARN_ON(ret == -ENOENT);
return ret;
}
+ mark_buffer_dirty(bh);
+ nilfs_mdt_mark_dirty(nilfs->ns_dat);
+ put_bh(bh);
} else {
ret = nilfs_bmap_mark(bmap, bdescs[i].bd_offset,
bdescs[i].bd_level);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index f6982b9153d5..3417d859a03c 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*/
#include <linux/buffer_head.h>
@@ -32,6 +28,7 @@
#include "segment.h"
#include "page.h"
#include "mdt.h"
+#include "alloc.h" /* nilfs_palloc_destroy_cache() */
#include <trace/events/nilfs2.h>
@@ -393,34 +390,6 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
return ret;
}
-/**
- * nilfs_mdt_mark_block_dirty - mark a block on the meta data file dirty.
- * @inode: inode of the meta data file
- * @block: block offset
- *
- * Return Value: On success, it returns 0. On error, the following negative
- * error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EIO - I/O error
- *
- * %-ENOENT - the specified block does not exist (hole block)
- */
-int nilfs_mdt_mark_block_dirty(struct inode *inode, unsigned long block)
-{
- struct buffer_head *bh;
- int err;
-
- err = nilfs_mdt_read_block(inode, block, 0, &bh);
- if (unlikely(err))
- return err;
- mark_buffer_dirty(bh);
- nilfs_mdt_mark_dirty(inode);
- brelse(bh);
- return 0;
-}
-
int nilfs_mdt_fetch_dirty(struct inode *inode)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
@@ -497,8 +466,32 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
return 0;
}
-void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size,
- unsigned header_size)
+/**
+ * nilfs_mdt_clear - do cleanup for the metadata file
+ * @inode: inode of the metadata file
+ */
+void nilfs_mdt_clear(struct inode *inode)
+{
+ struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
+
+ if (mdi->mi_palloc_cache)
+ nilfs_palloc_destroy_cache(inode);
+}
+
+/**
+ * nilfs_mdt_destroy - release resources used by the metadata file
+ * @inode: inode of the metadata file
+ */
+void nilfs_mdt_destroy(struct inode *inode)
+{
+ struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
+
+ kfree(mdi->mi_bgl); /* kfree(NULL) is safe */
+ kfree(mdi);
+}
+
+void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size,
+ unsigned int header_size)
{
struct nilfs_mdt_info *mi = NILFS_MDT(inode);
diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h
index 03246cac3338..3f67f3932097 100644
--- a/fs/nilfs2/mdt.h
+++ b/fs/nilfs2/mdt.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*/
#ifndef _NILFS_MDT_H
@@ -57,8 +53,8 @@ struct nilfs_shadow_map {
struct nilfs_mdt_info {
struct rw_semaphore mi_sem;
struct blockgroup_lock *mi_bgl;
- unsigned mi_entry_size;
- unsigned mi_first_entry_offset;
+ unsigned int mi_entry_size;
+ unsigned int mi_first_entry_offset;
unsigned long mi_entries_per_block;
struct nilfs_palloc_cache *mi_palloc_cache;
struct nilfs_shadow_map *mi_shadow;
@@ -71,6 +67,11 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode)
return inode->i_private;
}
+static inline int nilfs_is_metadata_file_inode(const struct inode *inode)
+{
+ return inode->i_private != NULL;
+}
+
/* Default GFP flags using highmem */
#define NILFS_MDT_GFP (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM)
@@ -83,11 +84,13 @@ int nilfs_mdt_find_block(struct inode *inode, unsigned long start,
struct buffer_head **out_bh);
int nilfs_mdt_delete_block(struct inode *, unsigned long);
int nilfs_mdt_forget_block(struct inode *, unsigned long);
-int nilfs_mdt_mark_block_dirty(struct inode *, unsigned long);
int nilfs_mdt_fetch_dirty(struct inode *);
int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz);
-void nilfs_mdt_set_entry_size(struct inode *, unsigned, unsigned);
+void nilfs_mdt_clear(struct inode *inode);
+void nilfs_mdt_destroy(struct inode *inode);
+
+void nilfs_mdt_set_entry_size(struct inode *, unsigned int, unsigned int);
int nilfs_mdt_setup_shadow_map(struct inode *inode,
struct nilfs_shadow_map *shadow);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 151bc19d47c0..1ec8ae5995a5 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -13,12 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Modified for NILFS by Amagai Yoshiji <amagai@osrg.net>,
- * Ryusuke Konishi <ryusuke@osrg.net>
+ * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi.
*/
/*
* linux/fs/ext2/namei.c
@@ -49,6 +44,7 @@
static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = nilfs_add_link(dentry, inode);
+
if (!err) {
d_instantiate(dentry, inode);
unlock_new_inode(inode);
@@ -143,7 +139,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry,
{
struct nilfs_transaction_info ti;
struct super_block *sb = dir->i_sb;
- unsigned l = strlen(symname)+1;
+ unsigned int l = strlen(symname) + 1;
struct inode *inode;
int err;
@@ -288,7 +284,7 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
if (!inode->i_nlink) {
nilfs_warning(inode->i_sb, __func__,
- "deleting nonexistent file (%lu), %d\n",
+ "deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
set_nlink(inode, 1);
}
@@ -457,7 +453,7 @@ static struct dentry *nilfs_get_parent(struct dentry *child)
root = NILFS_I(d_inode(child))->i_root;
- inode = nilfs_iget(d_inode(child)->i_sb, root, ino);
+ inode = nilfs_iget(child->d_sb, root, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 385704027575..b1d48bc0532d 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -13,12 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>
- * Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Koji Sato and Ryusuke Konishi.
*/
#ifndef _NILFS_H
@@ -69,8 +64,10 @@ struct nilfs_inode_info {
*/
struct rw_semaphore xattr_sem;
#endif
- struct buffer_head *i_bh; /* i_bh contains a new or dirty
- disk inode */
+ struct buffer_head *i_bh; /*
+ * i_bh contains a new or dirty
+ * disk inode.
+ */
struct nilfs_root *i_root;
struct inode vfs_inode;
};
@@ -100,8 +97,10 @@ enum {
NILFS_I_NEW = 0, /* Inode is newly created */
NILFS_I_DIRTY, /* The file is dirty */
NILFS_I_QUEUED, /* inode is in dirty_files list */
- NILFS_I_BUSY, /* inode is grabbed by a segment
- constructor */
+ NILFS_I_BUSY, /*
+ * Inode is grabbed by a segment
+ * constructor
+ */
NILFS_I_COLLECTED, /* All dirty blocks are collected */
NILFS_I_UPDATED, /* The file has been written back */
NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */
@@ -145,8 +144,10 @@ enum {
struct nilfs_transaction_info {
u32 ti_magic;
void *ti_save;
- /* This should never used. If this happens,
- one of other filesystems has a bug. */
+ /*
+ * This should never be used. If it happens,
+ * one of other filesystems has a bug.
+ */
unsigned short ti_flags;
unsigned short ti_count;
};
@@ -156,8 +157,10 @@ struct nilfs_transaction_info {
/* ti_flags */
#define NILFS_TI_DYNAMIC_ALLOC 0x0001 /* Allocated from slab */
-#define NILFS_TI_SYNC 0x0002 /* Force to construct segment at the
- end of transaction. */
+#define NILFS_TI_SYNC 0x0002 /*
+ * Force to construct segment at the
+ * end of transaction.
+ */
#define NILFS_TI_GC 0x0004 /* GC context */
#define NILFS_TI_COMMIT 0x0008 /* Change happened or not */
#define NILFS_TI_WRITER 0x0010 /* Constructor context */
@@ -279,7 +282,7 @@ extern void nilfs_write_failed(struct address_space *mapping, loff_t to);
int nilfs_permission(struct inode *inode, int mask);
int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
extern int nilfs_inode_dirty(struct inode *);
-int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty);
+int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty);
extern int __nilfs_mark_inode_dirty(struct inode *, int);
extern void nilfs_dirty_inode(struct inode *, int flags);
int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 489391561cda..d97ba5f11b77 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -13,12 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>,
- * Seiji Kihara <kihara@osrg.net>.
+ * Written by Ryusuke Konishi and Seiji Kihara.
*/
#include <linux/pagemap.h>
@@ -440,12 +435,12 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
__nilfs_clear_page_dirty(page);
}
-unsigned nilfs_page_count_clean_buffers(struct page *page,
- unsigned from, unsigned to)
+unsigned int nilfs_page_count_clean_buffers(struct page *page,
+ unsigned int from, unsigned int to)
{
- unsigned block_start, block_end;
+ unsigned int block_start, block_end;
struct buffer_head *bh, *head;
- unsigned nc = 0;
+ unsigned int nc = 0;
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index a43b8287d012..f3687c958fa8 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -13,12 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>,
- * Seiji Kihara <kihara@osrg.net>.
+ * Written by Ryusuke Konishi and Seiji Kihara.
*/
#ifndef _NILFS_PAGE_H
@@ -58,7 +53,8 @@ void nilfs_copy_back_pages(struct address_space *, struct address_space *);
void nilfs_clear_dirty_page(struct page *, bool);
void nilfs_clear_dirty_pages(struct address_space *, bool);
void nilfs_mapping_init(struct address_space *mapping, struct inode *inode);
-unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
+unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int,
+ unsigned int);
unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
sector_t start_blk,
sector_t *blkoff);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 5afa77fadc11..d893dc912b62 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*/
#include <linux/buffer_head.h>
@@ -47,8 +43,10 @@ enum {
/* work structure for recovery */
struct nilfs_recovery_block {
- ino_t ino; /* Inode number of the file that this block
- belongs to */
+ ino_t ino; /*
+ * Inode number of the file that this block
+ * belongs to
+ */
sector_t blocknr; /* block number */
__u64 vblocknr; /* virtual block number */
unsigned long blkoff; /* File offset of the data block (per block) */
@@ -156,7 +154,7 @@ int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block,
sr = (struct nilfs_super_root *)bh_sr->b_data;
if (check) {
- unsigned bytes = le16_to_cpu(sr->sr_bytes);
+ unsigned int bytes = le16_to_cpu(sr->sr_bytes);
if (bytes == 0 || bytes > nilfs->ns_blocksize) {
ret = NILFS_SEG_FAIL_CHECKSUM_SUPER_ROOT;
@@ -508,7 +506,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
{
struct inode *inode;
struct nilfs_recovery_block *rb, *n;
- unsigned blocksize = nilfs->ns_blocksize;
+ unsigned int blocksize = nilfs->ns_blocksize;
struct page *page;
loff_t pos;
int err = 0, err2 = 0;
@@ -526,6 +524,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
0, &page, nilfs_get_block);
if (unlikely(err)) {
loff_t isize = inode->i_size;
+
if (pos + blocksize > isize)
nilfs_write_failed(inode->i_mapping,
pos + blocksize);
@@ -872,9 +871,11 @@ int nilfs_search_super_root(struct the_nilfs *nilfs,
flags = le16_to_cpu(sum->ss_flags);
if (!(flags & NILFS_SS_SR) && !scan_newer) {
- /* This will never happen because a superblock
- (last_segment) always points to a pseg
- having a super root. */
+ /*
+ * This will never happen because a superblock
+ * (last_segment) always points to a pseg with
+ * a super root.
+ */
ret = NILFS_SEG_FAIL_CONSISTENCY;
goto failed;
}
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index f63620ce3892..bf36df10540b 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
@@ -133,7 +129,7 @@ int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *segbuf,
return 0;
}
-int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned flags,
+int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned int flags,
time_t ctime, __u64 cno)
{
int err;
@@ -240,7 +236,7 @@ nilfs_segbuf_fill_in_super_root_crc(struct nilfs_segment_buffer *segbuf,
{
struct nilfs_super_root *raw_sr;
struct the_nilfs *nilfs = segbuf->sb_super->s_fs_info;
- unsigned srsize;
+ unsigned int srsize;
u32 crc;
raw_sr = (struct nilfs_super_root *)segbuf->sb_super_root->b_data;
diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h
index b04f08cc2397..7bbccc099709 100644
--- a/fs/nilfs2/segbuf.h
+++ b/fs/nilfs2/segbuf.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
#ifndef _NILFS_SEGBUF_H
@@ -82,7 +78,7 @@ struct nilfs_segment_buffer {
__u64 sb_nextnum;
sector_t sb_fseg_start, sb_fseg_end;
sector_t sb_pseg_start;
- unsigned sb_rest_blocks;
+ unsigned int sb_rest_blocks;
/* Buffers */
struct list_head sb_segsum_buffers;
@@ -124,7 +120,8 @@ void nilfs_segbuf_map_cont(struct nilfs_segment_buffer *segbuf,
struct nilfs_segment_buffer *prev);
void nilfs_segbuf_set_next_segnum(struct nilfs_segment_buffer *, __u64,
struct the_nilfs *);
-int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned, time_t, __u64);
+int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned int, time_t,
+ __u64);
int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *);
int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *,
struct buffer_head **);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 4317f72568e6..e78b68a81aec 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
@@ -49,18 +45,26 @@
*/
#define SC_N_INODEVEC 16 /* Size of locally allocated inode vector */
-#define SC_MAX_SEGDELTA 64 /* Upper limit of the number of segments
- appended in collection retry loop */
+#define SC_MAX_SEGDELTA 64 /*
+ * Upper limit of the number of segments
+ * appended in collection retry loop
+ */
/* Construction mode */
enum {
SC_LSEG_SR = 1, /* Make a logical segment having a super root */
- SC_LSEG_DSYNC, /* Flush data blocks of a given file and make
- a logical segment without a super root */
- SC_FLUSH_FILE, /* Flush data files, leads to segment writes without
- creating a checkpoint */
- SC_FLUSH_DAT, /* Flush DAT file. This also creates segments without
- a checkpoint */
+ SC_LSEG_DSYNC, /*
+ * Flush data blocks of a given file and make
+ * a logical segment without a super root.
+ */
+ SC_FLUSH_FILE, /*
+ * Flush data files, leads to segment writes without
+ * creating a checkpoint.
+ */
+ SC_FLUSH_DAT, /*
+ * Flush DAT file. This also creates segments
+ * without a checkpoint.
+ */
};
/* Stage numbers of dirty block collection */
@@ -154,17 +158,15 @@ static int nilfs_prepare_segment_lock(struct nilfs_transaction_info *ti)
if (cur_ti) {
if (cur_ti->ti_magic == NILFS_TI_MAGIC)
return ++cur_ti->ti_count;
- else {
- /*
- * If journal_info field is occupied by other FS,
- * it is saved and will be restored on
- * nilfs_transaction_commit().
- */
- printk(KERN_WARNING
- "NILFS warning: journal info from a different "
- "FS\n");
- save = current->journal_info;
- }
+
+ /*
+ * If journal_info field is occupied by other FS,
+ * it is saved and will be restored on
+ * nilfs_transaction_commit().
+ */
+ printk(KERN_WARNING
+ "NILFS warning: journal info from a different FS\n");
+ save = current->journal_info;
}
if (!ti) {
ti = kmem_cache_alloc(nilfs_transaction_cachep, GFP_NOFS);
@@ -397,10 +399,10 @@ static void nilfs_transaction_unlock(struct super_block *sb)
static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
struct nilfs_segsum_pointer *ssp,
- unsigned bytes)
+ unsigned int bytes)
{
struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
- unsigned blocksize = sci->sc_super->s_blocksize;
+ unsigned int blocksize = sci->sc_super->s_blocksize;
void *p;
if (unlikely(ssp->offset + bytes > blocksize)) {
@@ -422,8 +424,8 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci)
{
struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
struct buffer_head *sumbh;
- unsigned sumbytes;
- unsigned flags = 0;
+ unsigned int sumbytes;
+ unsigned int flags = 0;
int err;
if (nilfs_doing_gc())
@@ -444,8 +446,10 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci)
{
sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks;
if (NILFS_SEGBUF_IS_LAST(sci->sc_curseg, &sci->sc_segbufs))
- return -E2BIG; /* The current segment is filled up
- (internal code) */
+ return -E2BIG; /*
+ * The current segment is filled up
+ * (internal code)
+ */
sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg);
return nilfs_segctor_reset_segment_buffer(sci);
}
@@ -472,9 +476,9 @@ static int nilfs_segctor_add_super_root(struct nilfs_sc_info *sci)
*/
static int nilfs_segctor_segsum_block_required(
struct nilfs_sc_info *sci, const struct nilfs_segsum_pointer *ssp,
- unsigned binfo_size)
+ unsigned int binfo_size)
{
- unsigned blocksize = sci->sc_super->s_blocksize;
+ unsigned int blocksize = sci->sc_super->s_blocksize;
/* Size of finfo and binfo is enough small against blocksize */
return ssp->offset + binfo_size +
@@ -533,7 +537,7 @@ static void nilfs_segctor_end_finfo(struct nilfs_sc_info *sci,
static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci,
struct buffer_head *bh,
struct inode *inode,
- unsigned binfo_size)
+ unsigned int binfo_size)
{
struct nilfs_segment_buffer *segbuf;
int required, err = 0;
@@ -617,7 +621,7 @@ static void nilfs_write_file_node_binfo(struct nilfs_sc_info *sci,
*vblocknr = binfo->bi_v.bi_vblocknr;
}
-static struct nilfs_sc_operations nilfs_sc_file_ops = {
+static const struct nilfs_sc_operations nilfs_sc_file_ops = {
.collect_data = nilfs_collect_file_data,
.collect_node = nilfs_collect_file_node,
.collect_bmap = nilfs_collect_file_bmap,
@@ -666,7 +670,7 @@ static void nilfs_write_dat_node_binfo(struct nilfs_sc_info *sci,
*binfo_dat = binfo->bi_dat;
}
-static struct nilfs_sc_operations nilfs_sc_dat_ops = {
+static const struct nilfs_sc_operations nilfs_sc_dat_ops = {
.collect_data = nilfs_collect_dat_data,
.collect_node = nilfs_collect_file_node,
.collect_bmap = nilfs_collect_dat_bmap,
@@ -674,7 +678,7 @@ static struct nilfs_sc_operations nilfs_sc_dat_ops = {
.write_node_binfo = nilfs_write_dat_node_binfo,
};
-static struct nilfs_sc_operations nilfs_sc_dsync_ops = {
+static const struct nilfs_sc_operations nilfs_sc_dsync_ops = {
.collect_data = nilfs_collect_file_data,
.collect_node = NULL,
.collect_bmap = NULL,
@@ -777,7 +781,7 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs,
{
struct nilfs_inode_info *ii, *n;
struct nilfs_inode_info *ivec[SC_N_INODEVEC], **pii;
- unsigned nv = 0;
+ unsigned int nv = 0;
while (!list_empty(head)) {
spin_lock(&nilfs->ns_inode_lock);
@@ -875,9 +879,11 @@ static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 1,
&raw_cp, &bh_cp);
if (likely(!err)) {
- /* The following code is duplicated with cpfile. But, it is
- needed to collect the checkpoint even if it was not newly
- created */
+ /*
+ * The following code is duplicated with cpfile. But, it is
+ * needed to collect the checkpoint even if it was not newly
+ * created.
+ */
mark_buffer_dirty(bh_cp);
nilfs_mdt_mark_dirty(nilfs->ns_cpfile);
nilfs_cpfile_put_checkpoint(
@@ -958,7 +964,7 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
{
struct buffer_head *bh_sr;
struct nilfs_super_root *raw_sr;
- unsigned isz, srsz;
+ unsigned int isz, srsz;
bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root;
raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
@@ -1043,7 +1049,7 @@ static size_t nilfs_segctor_buffer_rest(struct nilfs_sc_info *sci)
static int nilfs_segctor_scan_file(struct nilfs_sc_info *sci,
struct inode *inode,
- struct nilfs_sc_operations *sc_ops)
+ const struct nilfs_sc_operations *sc_ops)
{
LIST_HEAD(data_buffers);
LIST_HEAD(node_buffers);
@@ -1406,8 +1412,10 @@ static void nilfs_free_incomplete_logs(struct list_head *logs,
if (atomic_read(&segbuf->sb_err)) {
/* Case 1: The first segment failed */
if (segbuf->sb_pseg_start != segbuf->sb_fseg_start)
- /* Case 1a: Partial segment appended into an existing
- segment */
+ /*
+ * Case 1a: Partial segment appended into an existing
+ * segment
+ */
nilfs_terminate_segment(nilfs, segbuf->sb_fseg_start,
segbuf->sb_fseg_end);
else /* Case 1b: New full segment */
@@ -1550,7 +1558,7 @@ nilfs_segctor_update_payload_blocknr(struct nilfs_sc_info *sci,
sector_t blocknr;
unsigned long nfinfo = segbuf->sb_sum.nfinfo;
unsigned long nblocks = 0, ndatablk = 0;
- struct nilfs_sc_operations *sc_op = NULL;
+ const struct nilfs_sc_operations *sc_op = NULL;
struct nilfs_segsum_pointer ssp;
struct nilfs_finfo *finfo = NULL;
union nilfs_binfo binfo;
@@ -1631,8 +1639,10 @@ static int nilfs_segctor_assign(struct nilfs_sc_info *sci, int mode)
static void nilfs_begin_page_io(struct page *page)
{
if (!page || PageWriteback(page))
- /* For split b-tree node pages, this function may be called
- twice. We ignore the 2nd or later calls by this check. */
+ /*
+ * For split b-tree node pages, this function may be called
+ * twice. We ignore the 2nd or later calls by this check.
+ */
return;
lock_page(page);
@@ -1942,7 +1952,7 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
ifile, ii->vfs_inode.i_ino, &ibh);
if (unlikely(err)) {
nilfs_warning(sci->sc_super, __func__,
- "failed to get inode block.\n");
+ "failed to get inode block.");
return err;
}
mark_buffer_dirty(ibh);
@@ -2395,6 +2405,7 @@ static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode)
static void nilfs_construction_timeout(unsigned long data)
{
struct task_struct *p = (struct task_struct *)data;
+
wake_up_process(p);
}
@@ -2555,10 +2566,10 @@ static int nilfs_segctor_thread(void *arg)
if (timeout || sci->sc_seq_request != sci->sc_seq_done)
mode = SC_LSEG_SR;
- else if (!sci->sc_flush_request)
- break;
- else
+ else if (sci->sc_flush_request)
mode = nilfs_segctor_flush_mode(sci);
+ else
+ break;
spin_unlock(&sci->sc_state_lock);
nilfs_segctor_thread_construct(sci, mode);
@@ -2684,8 +2695,10 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
{
int ret, retrycount = NILFS_SC_CLEANUP_RETRY;
- /* The segctord thread was stopped and its timer was removed.
- But some tasks remain. */
+ /*
+ * The segctord thread was stopped and its timer was removed.
+ * But some tasks remain.
+ */
do {
struct nilfs_transaction_info ti;
@@ -2727,13 +2740,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
if (!list_empty(&sci->sc_dirty_files)) {
nilfs_warning(sci->sc_super, __func__,
- "dirty file(s) after the final construction\n");
+ "dirty file(s) after the final construction");
nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
}
if (!list_empty(&sci->sc_iput_queue)) {
nilfs_warning(sci->sc_super, __func__,
- "iput queue is not empty\n");
+ "iput queue is not empty");
nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
}
@@ -2810,7 +2823,7 @@ void nilfs_detach_log_writer(struct super_block *sb)
if (!list_empty(&nilfs->ns_dirty_files)) {
list_splice_init(&nilfs->ns_dirty_files, &garbage_list);
nilfs_warning(sb, __func__,
- "Hit dirty file after stopped log writer\n");
+ "Hit dirty file after stopped log writer");
}
spin_unlock(&nilfs->ns_inode_lock);
up_write(&nilfs->ns_segctor_sem);
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 0408b9b2814b..6565c10b7b76 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
#ifndef _NILFS_SEGMENT_H
@@ -75,7 +71,7 @@ struct nilfs_recovery_info {
*/
struct nilfs_cstage {
int scnt;
- unsigned flags;
+ unsigned int flags;
struct nilfs_inode_info *dirty_file_ptr;
struct nilfs_inode_info *gc_inode_ptr;
};
@@ -84,7 +80,7 @@ struct nilfs_segment_buffer;
struct nilfs_segsum_pointer {
struct buffer_head *bh;
- unsigned offset; /* offset in bytes */
+ unsigned int offset; /* offset in bytes */
};
/**
@@ -193,11 +189,15 @@ enum {
NILFS_SC_DIRTY, /* One or more dirty meta-data blocks exist */
NILFS_SC_UNCLOSED, /* Logical segment is not closed */
NILFS_SC_SUPER_ROOT, /* The latest segment has a super root */
- NILFS_SC_PRIOR_FLUSH, /* Requesting immediate flush without making a
- checkpoint */
- NILFS_SC_HAVE_DELTA, /* Next checkpoint will have update of files
- other than DAT, cpfile, sufile, or files
- moved by GC */
+ NILFS_SC_PRIOR_FLUSH, /*
+ * Requesting immediate flush without making a
+ * checkpoint
+ */
+ NILFS_SC_HAVE_DELTA, /*
+ * Next checkpoint will have update of files
+ * other than DAT, cpfile, sufile, or files
+ * moved by GC.
+ */
};
/* sc_state */
@@ -207,17 +207,23 @@ enum {
/*
* Constant parameters
*/
-#define NILFS_SC_CLEANUP_RETRY 3 /* Retry count of construction when
- destroying segctord */
+#define NILFS_SC_CLEANUP_RETRY 3 /*
+ * Retry count of construction when
+ * destroying segctord
+ */
/*
* Default values of timeout, in seconds.
*/
-#define NILFS_SC_DEFAULT_TIMEOUT 5 /* Timeout value of dirty blocks.
- It triggers construction of a
- logical segment with a super root */
-#define NILFS_SC_DEFAULT_SR_FREQ 30 /* Maximum frequency of super root
- creation */
+#define NILFS_SC_DEFAULT_TIMEOUT 5 /*
+ * Timeout value of dirty blocks.
+ * It triggers construction of a
+ * logical segment with a super root.
+ */
+#define NILFS_SC_DEFAULT_SR_FREQ 30 /*
+ * Maximum frequency of super root
+ * creation
+ */
/*
* The default threshold amount of data, in block counts.
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 52821ffc11f4..1963595a1580 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -13,12 +13,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
- * Revised by Ryusuke Konishi <ryusuke@osrg.net>.
+ * Written by Koji Sato.
+ * Revised by Ryusuke Konishi.
*/
#include <linux/kernel.h>
@@ -61,6 +57,7 @@ static unsigned long
nilfs_sufile_get_blkoff(const struct inode *sufile, __u64 segnum)
{
__u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;
+
do_div(t, nilfs_sufile_segment_usages_per_block(sufile));
return (unsigned long)t;
}
@@ -69,6 +66,7 @@ static unsigned long
nilfs_sufile_get_offset(const struct inode *sufile, __u64 segnum)
{
__u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;
+
return do_div(t, nilfs_sufile_segment_usages_per_block(sufile));
}
@@ -819,7 +817,7 @@ out:
* %-ENOMEM - Insufficient amount of memory available.
*/
ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
- unsigned sisz, size_t nsi)
+ unsigned int sisz, size_t nsi)
{
struct buffer_head *su_bh;
struct nilfs_segment_usage *su;
@@ -897,7 +895,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
* %-EINVAL - Invalid values in input (segment number, flags or nblocks)
*/
ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
- unsigned supsz, size_t nsup)
+ unsigned int supsz, size_t nsup)
{
struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
struct buffer_head *header_bh, *bh;
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index b8afd72f2379..46e89872294c 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Koji Sato <koji@osrg.net>.
+ * Written by Koji Sato.
*/
#ifndef _NILFS_SUFILE_H
@@ -42,9 +38,9 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum);
int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
unsigned long nblocks, time_t modtime);
int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *);
-ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned,
+ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned int,
size_t);
-ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned , size_t);
+ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned int, size_t);
int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *,
void (*dofunc)(struct inode *, __u64,
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 7f5d3d9f1c37..666107a18a22 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*/
/*
* linux/fs/ext2/super.c
@@ -173,12 +169,10 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
static void nilfs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
- if (mdi) {
- kfree(mdi->mi_bgl); /* kfree(NULL) is safe */
- kfree(mdi);
- }
+ if (nilfs_is_metadata_file_inode(inode))
+ nilfs_mdt_destroy(inode);
+
kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode));
}
@@ -279,7 +273,7 @@ struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb,
}
} else if (sbp[1] &&
sbp[1]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) {
- memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
+ memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
}
if (flip && sbp[1])
@@ -749,6 +743,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
while ((p = strsep(&options, ",")) != NULL) {
int token;
+
if (!*p)
continue;
@@ -891,7 +886,7 @@ int nilfs_store_magic_and_option(struct super_block *sb,
nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval);
nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max);
- return !parse_options(data, sb, 0) ? -EINVAL : 0 ;
+ return !parse_options(data, sb, 0) ? -EINVAL : 0;
}
int nilfs_check_feature_compatibility(struct super_block *sb,
@@ -1316,7 +1311,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
}
if (!s->s_root) {
- s_new = true;
+ s_new = true;
/* New superblock instance created */
s->s_mode = mode;
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index bbb0dcc35905..8ffa42b704d8 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -68,7 +68,7 @@ static ssize_t nilfs_##name##_attr_store(struct kobject *kobj, \
static const struct sysfs_ops nilfs_##name##_attr_ops = { \
.show = nilfs_##name##_attr_show, \
.store = nilfs_##name##_attr_store, \
-};
+}
#define NILFS_DEV_INT_GROUP_TYPE(name, parent_name) \
static void nilfs_##name##_attr_release(struct kobject *kobj) \
@@ -84,7 +84,7 @@ static struct kobj_type nilfs_##name##_ktype = { \
.default_attrs = nilfs_##name##_attrs, \
.sysfs_ops = &nilfs_##name##_attr_ops, \
.release = nilfs_##name##_attr_release, \
-};
+}
#define NILFS_DEV_INT_GROUP_FNS(name, parent_name) \
static int nilfs_sysfs_create_##name##_group(struct the_nilfs *nilfs) \
@@ -756,7 +756,7 @@ nilfs_superblock_sb_write_count_show(struct nilfs_superblock_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- unsigned sbwcount;
+ unsigned int sbwcount;
down_read(&nilfs->ns_sem);
sbwcount = nilfs->ns_sbwcount;
@@ -770,7 +770,7 @@ nilfs_superblock_sb_update_frequency_show(struct nilfs_superblock_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- unsigned sb_update_freq;
+ unsigned int sb_update_freq;
down_read(&nilfs->ns_sem);
sb_update_freq = nilfs->ns_sb_update_freq;
@@ -784,7 +784,7 @@ nilfs_superblock_sb_update_frequency_store(struct nilfs_superblock_attr *attr,
struct the_nilfs *nilfs,
const char *buf, size_t count)
{
- unsigned val;
+ unsigned int val;
int err;
err = kstrtouint(skip_spaces(buf), 0, &val);
diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h
index 677e3a1a8370..648cedf9c06e 100644
--- a/fs/nilfs2/sysfs.h
+++ b/fs/nilfs2/sysfs.h
@@ -66,7 +66,7 @@ struct nilfs_##name##_attr { \
char *); \
ssize_t (*store)(struct kobject *, struct attribute *, \
const char *, size_t); \
-};
+}
NILFS_COMMON_ATTR_STRUCT(feature);
@@ -77,7 +77,7 @@ struct nilfs_##name##_attr { \
char *); \
ssize_t (*store)(struct nilfs_##name##_attr *, struct the_nilfs *, \
const char *, size_t); \
-};
+}
NILFS_DEV_ATTR_STRUCT(dev);
NILFS_DEV_ATTR_STRUCT(segments);
@@ -93,7 +93,7 @@ struct nilfs_##name##_attr { \
char *); \
ssize_t (*store)(struct nilfs_##name##_attr *, struct nilfs_root *, \
const char *, size_t); \
-};
+}
NILFS_CP_ATTR_STRUCT(snapshot);
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 69bd801afb53..809bd2de7ad0 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
@@ -112,8 +108,8 @@ static int nilfs_load_super_root(struct the_nilfs *nilfs,
struct nilfs_super_root *raw_sr;
struct nilfs_super_block **sbp = nilfs->ns_sbp;
struct nilfs_inode *rawi;
- unsigned dat_entry_size, segment_usage_size, checkpoint_size;
- unsigned inode_size;
+ unsigned int dat_entry_size, segment_usage_size, checkpoint_size;
+ unsigned int inode_size;
int err;
err = nilfs_read_super_root_block(nilfs, sr_block, &bh_sr, 1);
@@ -621,8 +617,10 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp);
if (err)
goto out;
- /* not failed_sbh; sbh is released automatically
- when reloading fails. */
+ /*
+ * Not to failed_sbh; sbh is released automatically
+ * when reloading fails.
+ */
}
nilfs->ns_blocksize_bits = sb->s_blocksize_bits;
nilfs->ns_blocksize = blocksize;
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 23778d385836..79369fd6b13b 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -13,11 +13,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
+ * Written by Ryusuke Konishi.
*
*/
@@ -118,10 +114,10 @@ struct the_nilfs {
struct buffer_head *ns_sbh[2];
struct nilfs_super_block *ns_sbp[2];
time_t ns_sbwtime;
- unsigned ns_sbwcount;
- unsigned ns_sbsize;
- unsigned ns_mount_state;
- unsigned ns_sb_update_freq;
+ unsigned int ns_sbwcount;
+ unsigned int ns_sbsize;
+ unsigned int ns_mount_state;
+ unsigned int ns_sb_update_freq;
/*
* Following fields are dedicated to a writable FS-instance.
@@ -226,15 +222,14 @@ THE_NILFS_FNS(SB_DIRTY, sb_dirty)
* Mount option operations
*/
#define nilfs_clear_opt(nilfs, opt) \
- do { (nilfs)->ns_mount_opt &= ~NILFS_MOUNT_##opt; } while (0)
+ ((nilfs)->ns_mount_opt &= ~NILFS_MOUNT_##opt)
#define nilfs_set_opt(nilfs, opt) \
- do { (nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt; } while (0)
+ ((nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt)
#define nilfs_test_opt(nilfs, opt) ((nilfs)->ns_mount_opt & NILFS_MOUNT_##opt)
#define nilfs_write_opt(nilfs, mask, opt) \
- do { (nilfs)->ns_mount_opt = \
+ ((nilfs)->ns_mount_opt = \
(((nilfs)->ns_mount_opt & ~NILFS_MOUNT_##mask) | \
- NILFS_MOUNT_##opt); \
- } while (0)
+ NILFS_MOUNT_##opt)) \
/**
* struct nilfs_root - nilfs root object
@@ -273,6 +268,7 @@ struct nilfs_root {
static inline int nilfs_sb_need_update(struct the_nilfs *nilfs)
{
u64 t = get_seconds();
+
return t < nilfs->ns_sbwtime ||
t > nilfs->ns_sbwtime + nilfs->ns_sb_update_freq;
}
@@ -280,6 +276,7 @@ static inline int nilfs_sb_need_update(struct the_nilfs *nilfs)
static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs)
{
int flip_bits = nilfs->ns_sbwcount & 0x0FL;
+
return (flip_bits != 0x08 && flip_bits != 0x0F);
}
@@ -308,7 +305,7 @@ static inline void nilfs_get_root(struct nilfs_root *root)
static inline int nilfs_valid_fs(struct the_nilfs *nilfs)
{
- unsigned valid_fs;
+ unsigned int valid_fs;
down_read(&nilfs->ns_sem);
valid_fs = (nilfs->ns_mount_state & NILFS_VALID_FS);
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index b44c68a857e7..0a3bc2cf192c 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -56,6 +56,13 @@ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks,
&mnt->mnt_root->d_lock);
}
+/* prepare for freeing all marks associated with given group */
+extern void fsnotify_detach_group_marks(struct fsnotify_group *group);
+/*
+ * wait for fsnotify_mark_srcu period to end and free all marks in destroy_list
+ */
+extern void fsnotify_mark_destroy_list(void);
+
/*
* update the dentry->d_flags of all of inode's children to indicate if inode cares
* about events that happen to its children.
diff --git a/fs/notify/group.c b/fs/notify/group.c
index d16b62cb2854..3e2dd85be5dd 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -47,12 +47,21 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
*/
void fsnotify_destroy_group(struct fsnotify_group *group)
{
- /* clear all inode marks for this group */
- fsnotify_clear_marks_by_group(group);
+ /* clear all inode marks for this group, attach them to destroy_list */
+ fsnotify_detach_group_marks(group);
- synchronize_srcu(&fsnotify_mark_srcu);
+ /*
+ * Wait for fsnotify_mark_srcu period to end and free all marks in
+ * destroy_list
+ */
+ fsnotify_mark_destroy_list();
- /* clear the notification queue of all events */
+ /*
+ * Since we have waited for fsnotify_mark_srcu in
+ * fsnotify_mark_destroy_list() there can be no outstanding event
+ * notification against this group. So clearing the notification queue
+ * of all events is reliable now.
+ */
fsnotify_flush_notify(group);
/*
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 7115c5d7d373..d3fea0bd89e2 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -97,8 +97,8 @@ struct srcu_struct fsnotify_mark_srcu;
static DEFINE_SPINLOCK(destroy_lock);
static LIST_HEAD(destroy_list);
-static void fsnotify_mark_destroy(struct work_struct *work);
-static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy);
+static void fsnotify_mark_destroy_workfn(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);
void fsnotify_get_mark(struct fsnotify_mark *mark)
{
@@ -173,11 +173,15 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
}
/*
- * Free fsnotify mark. The freeing is actually happening from a kthread which
- * first waits for srcu period end. Caller must have a reference to the mark
- * or be protected by fsnotify_mark_srcu.
+ * Prepare mark for freeing and add it to the list of marks prepared for
+ * freeing. The actual freeing must happen after SRCU period ends and the
+ * caller is responsible for this.
+ *
+ * The function returns true if the mark was added to the list of marks for
+ * freeing. The function returns false if someone else has already called
+ * __fsnotify_free_mark() for the mark.
*/
-void fsnotify_free_mark(struct fsnotify_mark *mark)
+static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
{
struct fsnotify_group *group = mark->group;
@@ -185,17 +189,11 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
spin_unlock(&mark->lock);
- return;
+ return false;
}
mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
spin_unlock(&mark->lock);
- spin_lock(&destroy_lock);
- list_add(&mark->g_list, &destroy_list);
- spin_unlock(&destroy_lock);
- queue_delayed_work(system_unbound_wq, &reaper_work,
- FSNOTIFY_REAPER_DELAY);
-
/*
* Some groups like to know that marks are being freed. This is a
* callback to the group function to let it know that this mark
@@ -203,6 +201,25 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
*/
if (group->ops->freeing_mark)
group->ops->freeing_mark(mark, group);
+
+ spin_lock(&destroy_lock);
+ list_add(&mark->g_list, &destroy_list);
+ spin_unlock(&destroy_lock);
+
+ return true;
+}
+
+/*
+ * Free fsnotify mark. The freeing is actually happening from a workqueue which
+ * first waits for srcu period end. Caller must have a reference to the mark
+ * or be protected by fsnotify_mark_srcu.
+ */
+void fsnotify_free_mark(struct fsnotify_mark *mark)
+{
+ if (__fsnotify_free_mark(mark)) {
+ queue_delayed_work(system_unbound_wq, &reaper_work,
+ FSNOTIFY_REAPER_DELAY);
+ }
}
void fsnotify_destroy_mark(struct fsnotify_mark *mark,
@@ -468,11 +485,29 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
}
/*
- * Given a group, destroy all of the marks associated with that group.
+ * Given a group, prepare for freeing all the marks associated with that group.
+ * The marks are attached to the list of marks prepared for destruction, the
+ * caller is responsible for freeing marks in that list after SRCU period has
+ * ended.
*/
-void fsnotify_clear_marks_by_group(struct fsnotify_group *group)
+void fsnotify_detach_group_marks(struct fsnotify_group *group)
{
- fsnotify_clear_marks_by_group_flags(group, (unsigned int)-1);
+ struct fsnotify_mark *mark;
+
+ while (1) {
+ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+ if (list_empty(&group->marks_list)) {
+ mutex_unlock(&group->mark_mutex);
+ break;
+ }
+ mark = list_first_entry(&group->marks_list,
+ struct fsnotify_mark, g_list);
+ fsnotify_get_mark(mark);
+ fsnotify_detach_mark(mark);
+ mutex_unlock(&group->mark_mutex);
+ __fsnotify_free_mark(mark);
+ fsnotify_put_mark(mark);
+ }
}
void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old)
@@ -499,7 +534,11 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
mark->free_mark = free_mark;
}
-static void fsnotify_mark_destroy(struct work_struct *work)
+/*
+ * Destroy all marks in destroy_list, waits for SRCU period to finish before
+ * actually freeing marks.
+ */
+void fsnotify_mark_destroy_list(void)
{
struct fsnotify_mark *mark, *next;
struct list_head private_destroy_list;
@@ -516,3 +555,8 @@ static void fsnotify_mark_destroy(struct work_struct *work)
fsnotify_put_mark(mark);
}
}
+
+static void fsnotify_mark_destroy_workfn(struct work_struct *work)
+{
+ fsnotify_mark_destroy_list();
+}
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 91117ada8528..5622ed5a201e 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1952,12 +1952,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
written = ntfs_perform_write(file, from, iocb->ki_pos);
current->backing_dev_info = NULL;
inode_unlock(vi);
- if (likely(written > 0)) {
- err = generic_write_sync(file, iocb->ki_pos, written);
- if (err < 0)
- written = 0;
- }
iocb->ki_pos += written;
+ if (likely(written > 0))
+ written = generic_write_sync(iocb, written);
return written ? written : err;
}
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 0cdf497c91ef..2162434728c0 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -322,3 +322,90 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
brelse(di_bh);
return acl;
}
+
+int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
+{
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct posix_acl *acl;
+ int ret;
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+ return 0;
+
+ acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh);
+ if (IS_ERR(acl) || !acl)
+ return PTR_ERR(acl);
+ ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+ if (ret)
+ return ret;
+ ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS,
+ acl, NULL, NULL);
+ posix_acl_release(acl);
+ return ret;
+}
+
+/*
+ * Initialize the ACLs of a new inode. If parent directory has default ACL,
+ * then clone to new inode. Called from ocfs2_mknod.
+ */
+int ocfs2_init_acl(handle_t *handle,
+ struct inode *inode,
+ struct inode *dir,
+ struct buffer_head *di_bh,
+ struct buffer_head *dir_bh,
+ struct ocfs2_alloc_context *meta_ac,
+ struct ocfs2_alloc_context *data_ac)
+{
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct posix_acl *acl = NULL;
+ int ret = 0, ret2;
+ umode_t mode;
+
+ if (!S_ISLNK(inode->i_mode)) {
+ if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
+ dir_bh);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ }
+ if (!acl) {
+ mode = inode->i_mode & ~current_umask();
+ ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+ if (ret) {
+ mlog_errno(ret);
+ goto cleanup;
+ }
+ }
+ }
+ if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
+ if (S_ISDIR(inode->i_mode)) {
+ ret = ocfs2_set_acl(handle, inode, di_bh,
+ ACL_TYPE_DEFAULT, acl,
+ meta_ac, data_ac);
+ if (ret)
+ goto cleanup;
+ }
+ mode = inode->i_mode;
+ ret = __posix_acl_create(&acl, GFP_NOFS, &mode);
+ if (ret < 0)
+ return ret;
+
+ ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+ if (ret2) {
+ mlog_errno(ret2);
+ ret = ret2;
+ goto cleanup;
+ }
+ if (ret > 0) {
+ ret = ocfs2_set_acl(handle, inode,
+ di_bh, ACL_TYPE_ACCESS,
+ acl, meta_ac, data_ac);
+ }
+ }
+cleanup:
+ posix_acl_release(acl);
+ return ret;
+}
diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h
index 3fce68d08625..2783a75b3999 100644
--- a/fs/ocfs2/acl.h
+++ b/fs/ocfs2/acl.h
@@ -35,5 +35,10 @@ int ocfs2_set_acl(handle_t *handle,
struct posix_acl *acl,
struct ocfs2_alloc_context *meta_ac,
struct ocfs2_alloc_context *data_ac);
+extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *);
+extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
+ struct buffer_head *, struct buffer_head *,
+ struct ocfs2_alloc_context *,
+ struct ocfs2_alloc_context *);
#endif /* OCFS2_ACL_H */
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index e361d1a0ca09..460c0cedab3a 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5351,7 +5351,7 @@ static int ocfs2_truncate_rec(handle_t *handle,
{
int ret;
u32 left_cpos, rec_range, trunc_range;
- int wants_rotate = 0, is_rightmost_tree_rec = 0;
+ int is_rightmost_tree_rec = 0;
struct super_block *sb = ocfs2_metadata_cache_get_super(et->et_ci);
struct ocfs2_path *left_path = NULL;
struct ocfs2_extent_list *el = path_leaf_el(path);
@@ -5457,7 +5457,6 @@ static int ocfs2_truncate_rec(handle_t *handle,
memset(rec, 0, sizeof(*rec));
ocfs2_cleanup_merge(el, index);
- wants_rotate = 1;
next_free = le16_to_cpu(el->l_next_free_rec);
if (is_rightmost_tree_rec && next_free > 1) {
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ad1577348a92..c034edf3ef38 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2311,7 +2311,7 @@ static void ocfs2_dio_end_io_write(struct inode *inode,
/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
* are in that context. */
if (dwc->dw_writer_pid != task_pid_nr(current)) {
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
locked = 1;
}
@@ -2390,7 +2390,7 @@ out:
ocfs2_free_alloc_context(meta_ac);
ocfs2_run_deallocs(osb, &dealloc);
if (locked)
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
ocfs2_dio_free_write_ctx(inode, dwc);
}
@@ -2423,13 +2423,11 @@ static int ocfs2_dio_end_io(struct kiocb *iocb,
return 0;
}
-static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file)->i_mapping->host;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- loff_t end = offset + iter->count;
get_block_t *get_block;
/*
@@ -2440,7 +2438,8 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
return 0;
/* Fallback to buffered I/O if we do not support append dio. */
- if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb))
+ if (iocb->ki_pos + iter->count > i_size_read(inode) &&
+ !ocfs2_supports_append_dio(osb))
return 0;
if (iov_iter_rw(iter) == READ)
@@ -2449,7 +2448,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
get_block = ocfs2_dio_get_block;
return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, offset, get_block,
+ iter, get_block,
ocfs2_dio_end_io, NULL, 0);
}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 1934abb6b680..a8d15beee5cb 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1456,7 +1456,6 @@ static void o2hb_region_release(struct config_item *item)
static int o2hb_read_block_input(struct o2hb_region *reg,
const char *page,
- size_t count,
unsigned long *ret_bytes,
unsigned int *ret_bits)
{
@@ -1499,8 +1498,8 @@ static ssize_t o2hb_region_block_bytes_store(struct config_item *item,
if (reg->hr_bdev)
return -EINVAL;
- status = o2hb_read_block_input(reg, page, count,
- &block_bytes, &block_bits);
+ status = o2hb_read_block_input(reg, page, &block_bytes,
+ &block_bits);
if (status)
return status;
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2d0acd6678fe..4238eb28889f 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -600,10 +600,11 @@ static void o2net_set_nn_state(struct o2net_node *nn,
static void o2net_data_ready(struct sock *sk)
{
void (*ready)(struct sock *sk);
+ struct o2net_sock_container *sc;
- read_lock(&sk->sk_callback_lock);
- if (sk->sk_user_data) {
- struct o2net_sock_container *sc = sk->sk_user_data;
+ read_lock_bh(&sk->sk_callback_lock);
+ sc = sk->sk_user_data;
+ if (sc) {
sclog(sc, "data_ready hit\n");
o2net_set_data_ready_time(sc);
o2net_sc_queue_work(sc, &sc->sc_rx_work);
@@ -611,7 +612,7 @@ static void o2net_data_ready(struct sock *sk)
} else {
ready = sk->sk_data_ready;
}
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
ready(sk);
}
@@ -622,7 +623,7 @@ static void o2net_state_change(struct sock *sk)
void (*state_change)(struct sock *sk);
struct o2net_sock_container *sc;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
sc = sk->sk_user_data;
if (sc == NULL) {
state_change = sk->sk_state_change;
@@ -649,7 +650,7 @@ static void o2net_state_change(struct sock *sk)
break;
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
state_change(sk);
}
@@ -2012,7 +2013,7 @@ static void o2net_listen_data_ready(struct sock *sk)
{
void (*ready)(struct sock *sk);
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
ready = sk->sk_user_data;
if (ready == NULL) { /* check for teardown race */
ready = sk->sk_data_ready;
@@ -2039,7 +2040,7 @@ static void o2net_listen_data_ready(struct sock *sk)
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
if (ready != NULL)
ready(sk);
}
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 9aed6e202201..13719d3f35f8 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2455,6 +2455,8 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
spin_unlock(&dlm->spinlock);
+ ret = 0;
+
done:
dlm_put(dlm);
return ret;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 474e57f834e6..1eaa9100c889 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -54,6 +54,7 @@
#include "uptodate.h"
#include "quota.h"
#include "refcounttree.h"
+#include "acl.h"
#include "buffer_head_io.h"
@@ -3623,6 +3624,8 @@ static int ocfs2_data_convert_worker(struct ocfs2_lock_res *lockres,
filemap_fdatawait(mapping);
}
+ forget_all_cached_acls(inode);
+
out:
return UNBLOCK_CONTINUE;
}
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 5308841756be..4e7b0dc22450 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1268,20 +1268,20 @@ bail_unlock_rw:
if (size_change)
ocfs2_rw_unlock(inode, 1);
bail:
- brelse(bh);
/* Release quota pointers in case we acquired them */
for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++)
dqput(transfer_to[qtype]);
if (!status && attr->ia_valid & ATTR_MODE) {
- status = posix_acl_chmod(inode, inode->i_mode);
+ status = ocfs2_acl_chmod(inode, bh);
if (status < 0)
mlog_errno(status);
}
if (inode_locked)
ocfs2_inode_unlock(inode, 1);
+ brelse(bh);
return status;
}
@@ -1290,7 +1290,7 @@ int ocfs2_getattr(struct vfsmount *mnt,
struct kstat *stat)
{
struct inode *inode = d_inode(dentry);
- struct super_block *sb = d_inode(dentry)->i_sb;
+ struct super_block *sb = dentry->d_sb;
struct ocfs2_super *osb = sb->s_fs_info;
int err;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 12f4a9e9800f..0748777f2e2a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -262,7 +262,7 @@ static int ocfs2_init_locked_inode(struct inode *inode, void *opaque)
inode->i_ino = args->fi_ino;
OCFS2_I(inode)->ip_blkno = args->fi_blkno;
if (args->fi_sysfile_type != 0)
- lockdep_set_class(&inode->i_mutex,
+ lockdep_set_class(&inode->i_rwsem,
&ocfs2_sysfile_lock_key[args->fi_sysfile_type]);
if (args->fi_sysfile_type == USER_QUOTA_SYSTEM_INODE ||
args->fi_sysfile_type == GROUP_QUOTA_SYSTEM_INODE ||
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 6b3e87189a64..a8f1225e6d9b 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -259,7 +259,6 @@ static int ocfs2_mknod(struct inode *dir,
struct ocfs2_dir_lookup_result lookup = { NULL, };
sigset_t oldset;
int did_block_signals = 0;
- struct posix_acl *default_acl = NULL, *acl = NULL;
struct ocfs2_dentry_lock *dl = NULL;
trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
@@ -367,12 +366,6 @@ static int ocfs2_mknod(struct inode *dir,
goto leave;
}
- status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
- if (status) {
- mlog_errno(status);
- goto leave;
- }
-
handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
S_ISDIR(mode),
xattr_credits));
@@ -421,16 +414,8 @@ static int ocfs2_mknod(struct inode *dir,
inc_nlink(dir);
}
- if (default_acl) {
- status = ocfs2_set_acl(handle, inode, new_fe_bh,
- ACL_TYPE_DEFAULT, default_acl,
- meta_ac, data_ac);
- }
- if (!status && acl) {
- status = ocfs2_set_acl(handle, inode, new_fe_bh,
- ACL_TYPE_ACCESS, acl,
- meta_ac, data_ac);
- }
+ status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh,
+ meta_ac, data_ac);
if (status < 0) {
mlog_errno(status);
@@ -472,10 +457,6 @@ static int ocfs2_mknod(struct inode *dir,
d_instantiate(dentry, inode);
status = 0;
leave:
- if (default_acl)
- posix_acl_release(default_acl);
- if (acl)
- posix_acl_release(acl);
if (status < 0 && did_quota_inode)
dquot_free_inode(inode);
if (handle)
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 540ab5b75dbb..44d178b8d1aa 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -580,7 +580,7 @@ struct ocfs2_extended_slot {
/*00*/ __u8 es_valid;
__u8 es_reserved1[3];
__le32 es_node_num;
-/*10*/
+/*08*/
};
/*
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 744d5d90c363..92bbe93bfe10 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4248,20 +4248,12 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
struct inode *inode = d_inode(old_dentry);
struct buffer_head *old_bh = NULL;
struct inode *new_orphan_inode = NULL;
- struct posix_acl *default_acl, *acl;
- umode_t mode;
if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)))
return -EOPNOTSUPP;
- mode = inode->i_mode;
- error = posix_acl_create(dir, &mode, &default_acl, &acl);
- if (error) {
- mlog_errno(error);
- return error;
- }
- error = ocfs2_create_inode_in_orphan(dir, mode,
+ error = ocfs2_create_inode_in_orphan(dir, inode->i_mode,
&new_orphan_inode);
if (error) {
mlog_errno(error);
@@ -4300,16 +4292,11 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
/* If the security isn't preserved, we need to re-initialize them. */
if (!preserve) {
error = ocfs2_init_security_and_acl(dir, new_orphan_inode,
- &new_dentry->d_name,
- default_acl, acl);
+ &new_dentry->d_name);
if (error)
mlog_errno(error);
}
out:
- if (default_acl)
- posix_acl_release(default_acl);
- if (acl)
- posix_acl_release(acl);
if (!error) {
error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode,
new_dentry);
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 1e09592148ad..d7407994f308 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -535,12 +535,8 @@ void ocfs2_put_slot(struct ocfs2_super *osb)
spin_unlock(&osb->osb_lock);
status = ocfs2_update_disk_slot(osb, si, slot_num);
- if (status < 0) {
+ if (status < 0)
mlog_errno(status);
- goto bail;
- }
-bail:
ocfs2_free_slot_info(osb);
}
-
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 7d3d979f57d9..ad16995c9e7a 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7216,12 +7216,10 @@ out:
*/
int ocfs2_init_security_and_acl(struct inode *dir,
struct inode *inode,
- const struct qstr *qstr,
- struct posix_acl *default_acl,
- struct posix_acl *acl)
+ const struct qstr *qstr)
{
- struct buffer_head *dir_bh = NULL;
int ret = 0;
+ struct buffer_head *dir_bh = NULL;
ret = ocfs2_init_security_get(inode, dir, qstr, NULL);
if (ret) {
@@ -7234,11 +7232,9 @@ int ocfs2_init_security_and_acl(struct inode *dir,
mlog_errno(ret);
goto leave;
}
-
- if (!ret && default_acl)
- ret = ocfs2_iop_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
- if (!ret && acl)
- ret = ocfs2_iop_set_acl(inode, acl, ACL_TYPE_ACCESS);
+ ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL);
+ if (ret)
+ mlog_errno(ret);
ocfs2_inode_unlock(dir, 0);
brelse(dir_bh);
@@ -7250,10 +7246,10 @@ leave:
* 'security' attributes support
*/
static int ocfs2_xattr_security_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY,
+ return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_SECURITY,
name, buffer, size);
}
@@ -7321,10 +7317,10 @@ const struct xattr_handler ocfs2_xattr_security_handler = {
* 'trusted' attributes support
*/
static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED,
+ return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_TRUSTED,
name, buffer, size);
}
@@ -7346,14 +7342,14 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = {
* 'user' attributes support
*/
static int ocfs2_xattr_user_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *buffer, size_t size)
+ struct dentry *unusde, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
return -EOPNOTSUPP;
- return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name,
+ return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_USER, name,
buffer, size);
}
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index f10d5b93c366..1633cc15ea1f 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -94,7 +94,5 @@ int ocfs2_reflink_xattrs(struct inode *old_inode,
bool preserve_security);
int ocfs2_init_security_and_acl(struct inode *dir,
struct inode *inode,
- const struct qstr *qstr,
- struct posix_acl *default_acl,
- struct posix_acl *acl);
+ const struct qstr *qstr);
#endif /* OCFS2_XATTR_H */
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index f833bf8d5792..c8cbf3b60645 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -452,6 +452,6 @@ const struct inode_operations omfs_dir_inops = {
const struct file_operations omfs_dir_operations = {
.read = generic_read_dir,
- .iterate = omfs_readdir,
+ .iterate_shared = omfs_readdir,
.llseek = generic_file_llseek,
};
diff --git a/fs/open.c b/fs/open.c
index 17cb6b1dab75..93ae3cdee4ab 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -65,7 +65,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
return ret;
}
-long vfs_truncate(struct path *path, loff_t length)
+long vfs_truncate(const struct path *path, loff_t length)
{
struct inode *inode;
long error;
@@ -499,7 +499,7 @@ out:
return error;
}
-static int chmod_common(struct path *path, umode_t mode)
+static int chmod_common(const struct path *path, umode_t mode)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
@@ -564,7 +564,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
return sys_fchmodat(AT_FDCWD, filename, mode);
}
-static int chown_common(struct path *path, uid_t user, gid_t group)
+static int chown_common(const struct path *path, uid_t user, gid_t group)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
@@ -713,7 +713,7 @@ static int do_dentry_open(struct file *f,
}
/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
- if (S_ISREG(inode->i_mode))
+ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
f->f_mode |= FMODE_ATOMIC_POS;
f->f_op = fops_get(inode->i_fop);
@@ -840,16 +840,12 @@ EXPORT_SYMBOL(file_path);
int vfs_open(const struct path *path, struct file *file,
const struct cred *cred)
{
- struct dentry *dentry = path->dentry;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = vfs_select_inode(path->dentry, file->f_flags);
- file->f_path = *path;
- if (dentry->d_flags & DCACHE_OP_SELECT_INODE) {
- inode = dentry->d_op->d_select_inode(dentry, file->f_flags);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
- }
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+ file->f_path = *path;
return do_dentry_open(file, inode, NULL, cred);
}
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index b61b883c8ff8..c7a86993d97e 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -166,7 +166,7 @@ static int openpromfs_readdir(struct file *, struct dir_context *);
static const struct file_operations openprom_operations = {
.read = generic_read_dir,
- .iterate = openpromfs_readdir,
+ .iterate_shared = openpromfs_readdir,
.llseek = generic_file_llseek,
};
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index ae92795ed965..491e82c6f705 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -445,7 +445,7 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite
gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n");
- mutex_lock(&file->f_mapping->host->i_mutex);
+ inode_lock(file->f_mapping->host);
/* Make sure generic_write_checks sees an up to date inode size. */
if (file->f_flags & O_APPEND) {
@@ -492,7 +492,7 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite
out:
- mutex_unlock(&file->f_mapping->host->i_mutex);
+ inode_unlock(file->f_mapping->host);
return rc;
}
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index a9925e296ceb..2281882f718e 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -612,11 +612,11 @@ do { \
static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
#endif
i_size_write(inode, i_size);
#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
#endif
}
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
index 63a6280d8c3a..99c19545752c 100644
--- a/fs/orangefs/xattr.c
+++ b/fs/orangefs/xattr.c
@@ -463,12 +463,13 @@ static int orangefs_xattr_set_default(const struct xattr_handler *handler,
}
static int orangefs_xattr_get_default(const struct xattr_handler *handler,
- struct dentry *dentry,
+ struct dentry *unused,
+ struct inode *inode,
const char *name,
void *buffer,
size_t size)
{
- return orangefs_inode_getxattr(dentry->d_inode,
+ return orangefs_inode_getxattr(inode,
ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
name,
buffer,
@@ -492,12 +493,13 @@ static int orangefs_xattr_set_trusted(const struct xattr_handler *handler,
}
static int orangefs_xattr_get_trusted(const struct xattr_handler *handler,
- struct dentry *dentry,
+ struct dentry *unused,
+ struct inode *inode,
const char *name,
void *buffer,
size_t size)
{
- return orangefs_inode_getxattr(dentry->d_inode,
+ return orangefs_inode_getxattr(inode,
ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
name,
buffer,
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index a4ff5d0d7db9..c7b31a03dc9c 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -246,8 +246,8 @@ static bool ovl_need_xattr_filter(struct dentry *dentry,
return false;
}
-ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size)
+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);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 6a7090f4a441..99ec4b035237 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -173,8 +173,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr);
int ovl_permission(struct inode *inode, int mask);
int ovl_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags);
-ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size);
+ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size);
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
int ovl_removexattr(struct dentry *dentry, const char *name);
struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 6ec1e43a9a54..da186ee4f846 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -218,7 +218,9 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
old_cred = override_creds(override_cred);
- err = mutex_lock_killable(&dir->d_inode->i_mutex);
+ inode_lock(dir->d_inode);
+ err = 0;
+ // XXX: err = mutex_lock_killable(&dir->d_inode->i_mutex);
if (!err) {
while (rdd->first_maybe_whiteout) {
p = rdd->first_maybe_whiteout;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 5d972e6cd3fe..ed53ae0fe868 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -274,7 +274,7 @@ static bool ovl_is_opaquedir(struct dentry *dentry)
if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
return false;
- res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
+ res = inode->i_op->getxattr(dentry, inode, OVL_XATTR_OPAQUE, &val, 1);
if (res == 1 && val == 'y')
return true;
@@ -411,9 +411,7 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir,
{
struct dentry *dentry;
- inode_lock(dir->d_inode);
- dentry = lookup_one_len(name->name, dir, name->len);
- inode_unlock(dir->d_inode);
+ dentry = lookup_hash(name, dir);
if (IS_ERR(dentry)) {
if (PTR_ERR(dentry) == -ENOENT)
diff --git a/fs/pnode.c b/fs/pnode.c
index c524fdddc7fb..99899705b105 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -198,7 +198,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
/* all accesses are serialized by namespace_sem */
static struct user_namespace *user_ns;
-static struct mount *last_dest, *last_source, *dest_master;
+static struct mount *last_dest, *first_source, *last_source, *dest_master;
static struct mountpoint *mp;
static struct hlist_head *list;
@@ -221,20 +221,22 @@ static int propagate_one(struct mount *m)
type = CL_MAKE_SHARED;
} else {
struct mount *n, *p;
+ bool done;
for (n = m; ; n = p) {
p = n->mnt_master;
- if (p == dest_master || IS_MNT_MARKED(p)) {
- while (last_dest->mnt_master != p) {
- last_source = last_source->mnt_master;
- last_dest = last_source->mnt_parent;
- }
- if (!peers(n, last_dest)) {
- last_source = last_source->mnt_master;
- last_dest = last_source->mnt_parent;
- }
+ if (p == dest_master || IS_MNT_MARKED(p))
break;
- }
}
+ do {
+ struct mount *parent = last_source->mnt_parent;
+ if (last_source == first_source)
+ break;
+ done = parent->mnt_master == p;
+ if (done && peers(n, parent))
+ break;
+ last_source = last_source->mnt_master;
+ } while (!done);
+
type = CL_SLAVE;
/* beginning of peer group among the slaves? */
if (IS_MNT_SHARED(m))
@@ -286,6 +288,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
*/
user_ns = current->nsproxy->mnt_ns->user_ns;
last_dest = dest_mnt;
+ first_source = source_mnt;
last_source = source_mnt;
mp = dest_mp;
list = tree_list;
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 711dd5170376..2c60f17e7d92 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -21,7 +21,7 @@
#include <linux/export.h>
#include <linux/user_namespace.h>
-struct posix_acl **acl_by_type(struct inode *inode, int type)
+static struct posix_acl **acl_by_type(struct inode *inode, int type)
{
switch (type) {
case ACL_TYPE_ACCESS:
@@ -32,19 +32,22 @@ struct posix_acl **acl_by_type(struct inode *inode, int type)
BUG();
}
}
-EXPORT_SYMBOL(acl_by_type);
struct posix_acl *get_cached_acl(struct inode *inode, int type)
{
struct posix_acl **p = acl_by_type(inode, type);
- struct posix_acl *acl = ACCESS_ONCE(*p);
- if (acl) {
- spin_lock(&inode->i_lock);
- acl = *p;
- if (acl != ACL_NOT_CACHED)
- acl = posix_acl_dup(acl);
- spin_unlock(&inode->i_lock);
+ struct posix_acl *acl;
+
+ for (;;) {
+ rcu_read_lock();
+ acl = rcu_dereference(*p);
+ if (!acl || is_uncached_acl(acl) ||
+ atomic_inc_not_zero(&acl->a_refcount))
+ break;
+ rcu_read_unlock();
+ cpu_relax();
}
+ rcu_read_unlock();
return acl;
}
EXPORT_SYMBOL(get_cached_acl);
@@ -59,58 +62,72 @@ void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl)
{
struct posix_acl **p = acl_by_type(inode, type);
struct posix_acl *old;
- spin_lock(&inode->i_lock);
- old = *p;
- rcu_assign_pointer(*p, posix_acl_dup(acl));
- spin_unlock(&inode->i_lock);
- if (old != ACL_NOT_CACHED)
+
+ old = xchg(p, posix_acl_dup(acl));
+ if (!is_uncached_acl(old))
posix_acl_release(old);
}
EXPORT_SYMBOL(set_cached_acl);
-void forget_cached_acl(struct inode *inode, int type)
+static void __forget_cached_acl(struct posix_acl **p)
{
- struct posix_acl **p = acl_by_type(inode, type);
struct posix_acl *old;
- spin_lock(&inode->i_lock);
- old = *p;
- *p = ACL_NOT_CACHED;
- spin_unlock(&inode->i_lock);
- if (old != ACL_NOT_CACHED)
+
+ old = xchg(p, ACL_NOT_CACHED);
+ if (!is_uncached_acl(old))
posix_acl_release(old);
}
+
+void forget_cached_acl(struct inode *inode, int type)
+{
+ __forget_cached_acl(acl_by_type(inode, type));
+}
EXPORT_SYMBOL(forget_cached_acl);
void forget_all_cached_acls(struct inode *inode)
{
- struct posix_acl *old_access, *old_default;
- spin_lock(&inode->i_lock);
- old_access = inode->i_acl;
- old_default = inode->i_default_acl;
- inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
- spin_unlock(&inode->i_lock);
- if (old_access != ACL_NOT_CACHED)
- posix_acl_release(old_access);
- if (old_default != ACL_NOT_CACHED)
- posix_acl_release(old_default);
+ __forget_cached_acl(&inode->i_acl);
+ __forget_cached_acl(&inode->i_default_acl);
}
EXPORT_SYMBOL(forget_all_cached_acls);
struct posix_acl *get_acl(struct inode *inode, int type)
{
+ void *sentinel;
+ struct posix_acl **p;
struct posix_acl *acl;
+ /*
+ * The sentinel is used to detect when another operation like
+ * set_cached_acl() or forget_cached_acl() races with get_acl().
+ * It is guaranteed that is_uncached_acl(sentinel) is true.
+ */
+
acl = get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
+ if (!is_uncached_acl(acl))
return acl;
if (!IS_POSIXACL(inode))
return NULL;
+ sentinel = uncached_acl_sentinel(current);
+ p = acl_by_type(inode, type);
+
/*
- * A filesystem can force a ACL callback by just never filling the
- * ACL cache. But normally you'd fill the cache either at inode
- * instantiation time, or on the first ->get_acl call.
+ * If the ACL isn't being read yet, set our sentinel. Otherwise, the
+ * current value of the ACL will not be ACL_NOT_CACHED and so our own
+ * sentinel will not be set; another task will update the cache. We
+ * could wait for that other task to complete its job, but it's easier
+ * to just call ->get_acl to fetch the ACL ourself. (This is going to
+ * be an unlikely race.)
+ */
+ if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED)
+ /* fall through */ ;
+
+ /*
+ * Normally, the ACL returned by ->get_acl will be cached.
+ * A filesystem can prevent that by calling
+ * forget_cached_acl(inode, type) in ->get_acl.
*
* If the filesystem doesn't have a get_acl() function at all, we'll
* just create the negative cache entry.
@@ -119,7 +136,24 @@ struct posix_acl *get_acl(struct inode *inode, int type)
set_cached_acl(inode, type, NULL);
return NULL;
}
- return inode->i_op->get_acl(inode, type);
+ acl = inode->i_op->get_acl(inode, type);
+
+ if (IS_ERR(acl)) {
+ /*
+ * Remove our sentinel so that we don't block future attempts
+ * to cache the ACL.
+ */
+ cmpxchg(p, sentinel, ACL_NOT_CACHED);
+ return acl;
+ }
+
+ /*
+ * Cache the result, but only if our sentinel is still in place.
+ */
+ posix_acl_dup(acl);
+ if (unlikely(cmpxchg(p, sentinel, acl) != sentinel))
+ posix_acl_release(acl);
+ return acl;
}
EXPORT_SYMBOL(get_acl);
@@ -763,18 +797,18 @@ EXPORT_SYMBOL (posix_acl_to_xattr);
static int
posix_acl_xattr_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name,
- void *value, size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *value, size_t size)
{
struct posix_acl *acl;
int error;
- if (!IS_POSIXACL(d_backing_inode(dentry)))
+ if (!IS_POSIXACL(inode))
return -EOPNOTSUPP;
- if (d_is_symlink(dentry))
+ if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
- acl = get_acl(d_backing_inode(dentry), handler->flags);
+ acl = get_acl(inode, handler->flags);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index b6c00ce0e29e..88c7de12197b 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -83,6 +83,7 @@
#include <linux/tracehook.h>
#include <linux/string_helpers.h>
#include <linux/user_namespace.h>
+#include <linux/fs_struct.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
@@ -139,12 +140,25 @@ static inline const char *get_task_state(struct task_struct *tsk)
return task_state_array[fls(state)];
}
+static inline int get_task_umask(struct task_struct *tsk)
+{
+ struct fs_struct *fs;
+ int umask = -ENOENT;
+
+ task_lock(tsk);
+ fs = tsk->fs;
+ if (fs)
+ umask = fs->umask;
+ task_unlock(tsk);
+ return umask;
+}
+
static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *p)
{
struct user_namespace *user_ns = seq_user_ns(m);
struct group_info *group_info;
- int g;
+ int g, umask;
struct task_struct *tracer;
const struct cred *cred;
pid_t ppid, tpid = 0, tgid, ngid;
@@ -162,6 +176,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
ngid = task_numa_group_id(p);
cred = get_task_cred(p);
+ umask = get_task_umask(p);
+ if (umask >= 0)
+ seq_printf(m, "Umask:\t%#04o\n", umask);
+
task_lock(p);
if (p->files)
max_fds = files_fdtable(p->files)->max_fds;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b1755b23893e..a11eb7196ec8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -434,7 +434,7 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
&& !lookup_symbol_name(wchan, symname))
seq_printf(m, "%s", symname);
else
- seq_puts(m, "0\n");
+ seq_putc(m, '0');
return 0;
}
@@ -955,7 +955,8 @@ static ssize_t environ_read(struct file *file, char __user *buf,
struct mm_struct *mm = file->private_data;
unsigned long env_start, env_end;
- if (!mm)
+ /* Ensure the process spawned far enough to have an environment. */
+ if (!mm || !mm->env_end)
return 0;
page = (char *)__get_free_page(GFP_TEMPORARY);
@@ -1819,12 +1820,17 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
child = d_hash_and_lookup(dir, &qname);
if (!child) {
- child = d_alloc(dir, &qname);
- if (!child)
- goto end_instantiate;
- if (instantiate(d_inode(dir), child, task, ptr) < 0) {
- dput(child);
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+ child = d_alloc_parallel(dir, &qname, &wq);
+ if (IS_ERR(child))
goto end_instantiate;
+ if (d_in_lookup(child)) {
+ int err = instantiate(d_inode(dir), child, task, ptr);
+ d_lookup_done(child);
+ if (err < 0) {
+ dput(child);
+ goto end_instantiate;
+ }
}
}
inode = d_inode(child);
@@ -2154,8 +2160,8 @@ out:
static const struct file_operations proc_map_files_operations = {
.read = generic_read_dir,
- .iterate = proc_map_files_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_map_files_readdir,
+ .llseek = generic_file_llseek,
};
#ifdef CONFIG_CHECKPOINT_RESTORE
@@ -2502,8 +2508,8 @@ static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx)
static const struct file_operations proc_attr_dir_operations = {
.read = generic_read_dir,
- .iterate = proc_attr_dir_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_attr_dir_readdir,
+ .llseek = generic_file_llseek,
};
static struct dentry *proc_attr_dir_lookup(struct inode *dir,
@@ -2910,8 +2916,8 @@ static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
static const struct file_operations proc_tgid_base_operations = {
.read = generic_read_dir,
- .iterate = proc_tgid_base_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_tgid_base_readdir,
+ .llseek = generic_file_llseek,
};
static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
@@ -3157,6 +3163,44 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
}
/*
+ * proc_tid_comm_permission is a special permission function exclusively
+ * used for the node /proc/<pid>/task/<tid>/comm.
+ * It bypasses generic permission checks in the case where a task of the same
+ * task group attempts to access the node.
+ * The rationale behind this is that glibc and bionic access this node for
+ * cross thread naming (pthread_set/getname_np(!self)). However, if
+ * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0,
+ * which locks out the cross thread naming implementation.
+ * This function makes sure that the node is always accessible for members of
+ * same thread group.
+ */
+static int proc_tid_comm_permission(struct inode *inode, int mask)
+{
+ bool is_same_tgroup;
+ struct task_struct *task;
+
+ task = get_proc_task(inode);
+ if (!task)
+ return -ESRCH;
+ is_same_tgroup = same_thread_group(current, task);
+ put_task_struct(task);
+
+ if (likely(is_same_tgroup && !(mask & MAY_EXEC))) {
+ /* This file (/proc/<pid>/task/<tid>/comm) can always be
+ * read or written by the members of the corresponding
+ * thread group.
+ */
+ return 0;
+ }
+
+ return generic_permission(inode, mask);
+}
+
+static const struct inode_operations proc_tid_comm_inode_operations = {
+ .permission = proc_tid_comm_permission,
+};
+
+/*
* Tasks
*/
static const struct pid_entry tid_base_stuff[] = {
@@ -3174,7 +3218,9 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
- REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+ NOD("comm", S_IFREG|S_IRUGO|S_IWUSR,
+ &proc_tid_comm_inode_operations,
+ &proc_pid_set_comm_operations, {}),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
@@ -3258,8 +3304,8 @@ static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *den
static const struct file_operations proc_tid_base_operations = {
.read = generic_read_dir,
- .iterate = proc_tid_base_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_tid_base_readdir,
+ .llseek = generic_file_llseek,
};
static const struct inode_operations proc_tid_base_inode_operations = {
@@ -3469,6 +3515,6 @@ static const struct inode_operations proc_task_inode_operations = {
static const struct file_operations proc_task_operations = {
.read = generic_read_dir,
- .iterate = proc_task_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_task_readdir,
+ .llseek = generic_file_llseek,
};
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 56afa5ef08f2..01df23cc81f6 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -276,8 +276,8 @@ static int proc_readfd(struct file *file, struct dir_context *ctx)
const struct file_operations proc_fd_operations = {
.read = generic_read_dir,
- .iterate = proc_readfd,
- .llseek = default_llseek,
+ .iterate_shared = proc_readfd,
+ .llseek = generic_file_llseek,
};
static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
@@ -361,6 +361,6 @@ const struct inode_operations proc_fdinfo_inode_operations = {
const struct file_operations proc_fdinfo_operations = {
.read = generic_read_dir,
- .iterate = proc_readfdinfo,
- .llseek = default_llseek,
+ .iterate_shared = proc_readfdinfo,
+ .llseek = generic_file_llseek,
};
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index ff3ffc76a937..c633476616e0 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -318,7 +318,7 @@ int proc_readdir(struct file *file, struct dir_context *ctx)
static const struct file_operations proc_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = proc_readdir,
+ .iterate_shared = proc_readdir,
};
/*
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 72cb26f85d58..51b8b0a8ad91 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -139,7 +139,8 @@ out:
const struct file_operations proc_ns_dir_operations = {
.read = generic_read_dir,
- .iterate = proc_ns_dir_readdir,
+ .iterate_shared = proc_ns_dir_readdir,
+ .llseek = generic_file_llseek,
};
static struct dentry *proc_ns_dir_lookup(struct inode *dir,
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 712f1b9992cc..3ecd445e830d 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -142,7 +142,7 @@ u64 stable_page_flags(struct page *page)
/*
- * Caveats on high order pages: page->_count will only be set
+ * Caveats on high order pages: page->_refcount will only be set
* -1 on the head page; SLUB/SLQB do the same for PG_slab;
* SLOB won't set PG_slab at all on compound pages.
*/
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 350984a19c83..c8bbc68cdb05 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -179,7 +179,7 @@ static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx)
const struct file_operations proc_net_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = proc_tgid_net_readdir,
+ .iterate_shared = proc_tgid_net_readdir,
};
static __net_init int proc_net_ns_init(struct net *net)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index fe5b6e6c4671..5e57c3e46e1d 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -627,18 +627,19 @@ static bool proc_sys_fill_cache(struct file *file,
child = d_lookup(dir, &qname);
if (!child) {
- child = d_alloc(dir, &qname);
- if (child) {
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+ child = d_alloc_parallel(dir, &qname, &wq);
+ if (IS_ERR(child))
+ return false;
+ if (d_in_lookup(child)) {
inode = proc_sys_make_inode(dir->d_sb, head, table);
if (!inode) {
+ d_lookup_done(child);
dput(child);
return false;
- } else {
- d_set_d_op(child, &proc_sys_dentry_operations);
- d_add(child, inode);
}
- } else {
- return false;
+ d_set_d_op(child, &proc_sys_dentry_operations);
+ d_add(child, inode);
}
}
inode = d_inode(child);
@@ -789,7 +790,7 @@ static const struct file_operations proc_sys_file_operations = {
static const struct file_operations proc_sys_dir_file_operations = {
.read = generic_read_dir,
- .iterate = proc_sys_readdir,
+ .iterate_shared = proc_sys_readdir,
.llseek = generic_file_llseek,
};
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 361ab4ee42fc..55bc7d6c8aac 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -226,8 +226,8 @@ static int proc_root_readdir(struct file *file, struct dir_context *ctx)
*/
static const struct file_operations proc_root_operations = {
.read = generic_read_dir,
- .iterate = proc_root_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_root_readdir,
+ .llseek = generic_file_llseek,
};
/*
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 229cb546bee0..4648c7f63ae2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1027,11 +1027,15 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
};
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+ if (down_write_killable(&mm->mmap_sem)) {
+ count = -EINTR;
+ goto out_mm;
+ }
+
/*
* Writing 5 to /proc/pid/clear_refs resets the peak
* resident set size to this mm's current rss value.
*/
- down_write(&mm->mmap_sem);
reset_mm_hiwater_rss(mm);
up_write(&mm->mmap_sem);
goto out_mm;
@@ -1043,7 +1047,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
up_read(&mm->mmap_sem);
- down_write(&mm->mmap_sem);
+ if (down_write_killable(&mm->mmap_sem)) {
+ count = -EINTR;
+ goto out_mm;
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
vma->vm_flags &= ~VM_SOFTDIRTY;
vma_set_page_prot(vma);
@@ -1518,6 +1525,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
return page;
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static struct page *can_gather_numa_stats_pmd(pmd_t pmd,
+ struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct page *page;
+ int nid;
+
+ if (!pmd_present(pmd))
+ return NULL;
+
+ page = vm_normal_page_pmd(vma, addr, pmd);
+ if (!page)
+ return NULL;
+
+ if (PageReserved(page))
+ return NULL;
+
+ nid = page_to_nid(page);
+ if (!node_isset(nid, node_states[N_MEMORY]))
+ return NULL;
+
+ return page;
+}
+#endif
+
static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
@@ -1527,14 +1560,14 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
pte_t *orig_pte;
pte_t *pte;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
- pte_t huge_pte = *(pte_t *)pmd;
struct page *page;
- page = can_gather_numa_stats(huge_pte, vma, addr);
+ page = can_gather_numa_stats_pmd(*pmd, vma, addr);
if (page)
- gather_stats(page, md, pte_dirty(huge_pte),
+ gather_stats(page, md, pmd_dirty(*pmd),
HPAGE_PMD_SIZE/PAGE_SIZE);
spin_unlock(ptl);
return 0;
@@ -1542,6 +1575,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
if (pmd_trans_unstable(pmd))
return 0;
+#endif
orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
do {
struct page *page = can_gather_numa_stats(*pte, vma, addr);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 8afe10cf7df8..8ab782d8b33d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -1071,7 +1071,7 @@ static int __init parse_crash_elf32_headers(void)
/* Do some basic Verification. */
if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
(ehdr.e_type != ET_CORE) ||
- !elf_check_arch(&ehdr) ||
+ !vmcore_elf32_check_arch(&ehdr) ||
ehdr.e_ident[EI_CLASS] != ELFCLASS32||
ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
ehdr.e_version != EV_CURRENT ||
diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c
index b218f965817b..781056a0480f 100644
--- a/fs/qnx4/dir.c
+++ b/fs/qnx4/dir.c
@@ -71,7 +71,7 @@ const struct file_operations qnx4_dir_operations =
{
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = qnx4_readdir,
+ .iterate_shared = qnx4_readdir,
.fsync = generic_file_fsync,
};
diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c
index 144ceda4948e..27637e0bdc9f 100644
--- a/fs/qnx6/dir.c
+++ b/fs/qnx6/dir.c
@@ -272,7 +272,7 @@ found:
const struct file_operations qnx6_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = qnx6_readdir,
+ .iterate_shared = qnx6_readdir,
.fsync = generic_file_fsync,
};
diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c
index d07a2f91d858..8b252673d454 100644
--- a/fs/quota/netlink.c
+++ b/fs/quota/netlink.c
@@ -47,7 +47,7 @@ void quota_send_warning(struct kqid qid, dev_t dev,
void *msg_head;
int ret;
int msg_size = 4 * nla_total_size(sizeof(u32)) +
- 2 * nla_total_size(sizeof(u64));
+ 2 * nla_total_size_64bit(sizeof(u64));
/* We have to allocate using GFP_NOFS as we are called from a
* filesystem performing write and thus further recursion into
@@ -68,8 +68,9 @@ void quota_send_warning(struct kqid qid, dev_t dev,
ret = nla_put_u32(skb, QUOTA_NL_A_QTYPE, qid.type);
if (ret)
goto attr_err_out;
- ret = nla_put_u64(skb, QUOTA_NL_A_EXCESS_ID,
- from_kqid_munged(&init_user_ns, qid));
+ ret = nla_put_u64_64bit(skb, QUOTA_NL_A_EXCESS_ID,
+ from_kqid_munged(&init_user_ns, qid),
+ QUOTA_NL_A_PAD);
if (ret)
goto attr_err_out;
ret = nla_put_u32(skb, QUOTA_NL_A_WARNING, warntype);
@@ -81,8 +82,9 @@ void quota_send_warning(struct kqid qid, dev_t dev,
ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MINOR, MINOR(dev));
if (ret)
goto attr_err_out;
- ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID,
- from_kuid_munged(&init_user_ns, current_uid()));
+ ret = nla_put_u64_64bit(skb, QUOTA_NL_A_CAUSED_ID,
+ from_kuid_munged(&init_user_ns, current_uid()),
+ QUOTA_NL_A_PAD);
if (ret)
goto attr_err_out;
genlmsg_end(skb, msg_head);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index a586467f6ff6..be3ddd189cd4 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -211,14 +211,11 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
struct page **pages = NULL, **ptr, *page;
loff_t isize;
- if (!(flags & MAP_SHARED))
- return addr;
-
/* the mapping mustn't extend beyond the EOF */
lpages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
isize = i_size_read(inode);
- ret = -EINVAL;
+ ret = -ENOSYS;
maxpages = (isize + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= maxpages)
goto out;
@@ -227,7 +224,6 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
goto out;
/* gang-find the pages */
- ret = -ENOMEM;
pages = kcalloc(lpages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto out_free;
@@ -263,7 +259,7 @@ out:
*/
static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma)
{
- if (!(vma->vm_flags & VM_SHARED))
+ if (!(vma->vm_flags & (VM_SHARED | VM_MAYSHARE)))
return -ENOSYS;
file_accessed(file);
diff --git a/fs/read_write.c b/fs/read_write.c
index cf377cf9dfe3..933b53a375b4 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -302,18 +302,6 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
}
EXPORT_SYMBOL(vfs_llseek);
-static inline struct fd fdget_pos(int fd)
-{
- return __to_fd(__fdget_pos(fd));
-}
-
-static inline void fdput_pos(struct fd f)
-{
- if (f.flags & FDPUT_POS_UNLOCK)
- mutex_unlock(&f.file->f_pos_lock);
- fdput(f);
-}
-
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
@@ -410,11 +398,6 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
}
EXPORT_SYMBOL(vfs_iter_write);
-/*
- * rw_verify_area doesn't like huge counts. We limit
- * them to something that fits in "int" so that others
- * won't have to do range checks all the time.
- */
int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
{
struct inode *inode;
@@ -441,11 +424,8 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
if (retval < 0)
return retval;
}
- retval = security_file_permission(file,
+ return security_file_permission(file,
read_write == READ ? MAY_READ : MAY_WRITE);
- if (retval)
- return retval;
- return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
}
static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
@@ -489,8 +469,9 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
return -EFAULT;
ret = rw_verify_area(READ, file, pos, count);
- if (ret >= 0) {
- count = ret;
+ if (!ret) {
+ if (count > MAX_RW_COUNT)
+ count = MAX_RW_COUNT;
ret = __vfs_read(file, buf, count, pos);
if (ret > 0) {
fsnotify_access(file);
@@ -572,8 +553,9 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
- if (ret >= 0) {
- count = ret;
+ if (!ret) {
+ if (count > MAX_RW_COUNT)
+ count = MAX_RW_COUNT;
file_start_write(file);
ret = __vfs_write(file, buf, count, pos);
if (ret > 0) {
@@ -698,12 +680,16 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
struct kiocb kiocb;
ssize_t ret;
- if (flags & ~RWF_HIPRI)
+ if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC))
return -EOPNOTSUPP;
init_sync_kiocb(&kiocb, filp);
if (flags & RWF_HIPRI)
kiocb.ki_flags |= IOCB_HIPRI;
+ if (flags & RWF_DSYNC)
+ kiocb.ki_flags |= IOCB_DSYNC;
+ if (flags & RWF_SYNC)
+ kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
kiocb.ki_pos = *ppos;
ret = fn(&kiocb, iter);
@@ -1323,7 +1309,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
retval = rw_verify_area(READ, in.file, &pos, count);
if (retval < 0)
goto fput_in;
- count = retval;
+ if (count > MAX_RW_COUNT)
+ count = MAX_RW_COUNT;
/*
* Get output file, and verify that it is ok..
@@ -1341,7 +1328,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
retval = rw_verify_area(WRITE, out.file, &out_pos, count);
if (retval < 0)
goto fput_out;
- count = retval;
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
@@ -1485,11 +1471,12 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
if (flags != 0)
return -EINVAL;
- /* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT */
ret = rw_verify_area(READ, file_in, &pos_in, len);
- if (ret >= 0)
- ret = rw_verify_area(WRITE, file_out, &pos_out, len);
- if (ret < 0)
+ if (unlikely(ret))
+ return ret;
+
+ ret = rw_verify_area(WRITE, file_out, &pos_out, len);
+ if (unlikely(ret))
return ret;
if (!(file_in->f_mode & FMODE_READ) ||
diff --git a/fs/readdir.c b/fs/readdir.c
index 5f2d4bee5a73..68ef06efe6bc 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -24,27 +24,40 @@
int iterate_dir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
+ bool shared = false;
int res = -ENOTDIR;
- if (!file->f_op->iterate)
+ if (file->f_op->iterate_shared)
+ shared = true;
+ else if (!file->f_op->iterate)
goto out;
res = security_file_permission(file, MAY_READ);
if (res)
goto out;
- res = mutex_lock_killable(&inode->i_mutex);
- if (res)
- goto out;
+ if (shared)
+ inode_lock_shared(inode);
+ else
+ inode_lock(inode);
+ // res = mutex_lock_killable(&inode->i_mutex);
+ // if (res)
+ // goto out;
res = -ENOENT;
if (!IS_DEADDIR(inode)) {
ctx->pos = file->f_pos;
- res = file->f_op->iterate(file, ctx);
+ if (shared)
+ res = file->f_op->iterate_shared(file, ctx);
+ else
+ res = file->f_op->iterate(file, ctx);
file->f_pos = ctx->pos;
fsnotify_access(file);
file_accessed(file);
}
- inode_unlock(inode);
+ if (shared)
+ inode_unlock_shared(inode);
+ else
+ inode_unlock(inode);
out:
return res;
}
@@ -111,7 +124,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
struct old_linux_dirent __user *, dirent, unsigned int, count)
{
int error;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
struct readdir_callback buf = {
.ctx.actor = fillonedir,
.dirent = dirent
@@ -124,7 +137,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
if (buf.result)
error = buf.result;
- fdput(f);
+ fdput_pos(f);
return error;
}
@@ -210,7 +223,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
if (!access_ok(VERIFY_WRITE, dirent, count))
return -EFAULT;
- f = fdget(fd);
+ f = fdget_pos(fd);
if (!f.file)
return -EBADF;
@@ -224,7 +237,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
else
error = count - buf.count;
}
- fdput(f);
+ fdput_pos(f);
return error;
}
@@ -293,7 +306,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
if (!access_ok(VERIFY_WRITE, dirent, count))
return -EFAULT;
- f = fdget(fd);
+ f = fdget_pos(fd);
if (!f.file)
return -EBADF;
@@ -308,6 +321,6 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
else
error = count - buf.count;
}
- fdput(f);
+ fdput_pos(f);
return error;
}
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 3abd4004184b..45aa05e2232f 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -20,7 +20,7 @@ static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
const struct file_operations reiserfs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = reiserfs_readdir,
+ .iterate_shared = reiserfs_readdir,
.fsync = reiserfs_dir_fsync,
.unlocked_ioctl = reiserfs_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 389773711de4..90f815bdfa8a 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -260,10 +260,10 @@ const struct file_operations reiserfs_file_operations = {
const struct inode_operations reiserfs_file_inode_operations = {
.setattr = reiserfs_setattr,
- .setxattr = reiserfs_setxattr,
- .getxattr = reiserfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = reiserfs_listxattr,
- .removexattr = reiserfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = reiserfs_permission,
.get_acl = reiserfs_get_acl,
.set_acl = reiserfs_set_acl,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index d5c2e9c865de..825455d3e4ba 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3279,15 +3279,14 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags)
* We thank Mingming Cao for helping us understand in great detail what
* to do in this section of the code.
*/
-static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
size_t count = iov_iter_count(iter);
ssize_t ret;
- ret = blockdev_direct_IO(iocb, inode, iter, offset,
+ ret = blockdev_direct_IO(iocb, inode, iter,
reiserfs_get_blocks_direct_io);
/*
@@ -3296,7 +3295,7 @@ static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
*/
if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + count;
+ loff_t end = iocb->ki_pos + count;
if ((end > isize) && inode_newsize_ok(inode, isize) == 0) {
truncate_setsize(inode, isize);
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 57045f423893..2f1ddc908013 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -187,7 +187,11 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
}
/* we need to make sure nobody is changing the file size beneath us */
- reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb);
+{
+ int depth = reiserfs_write_unlock_nested(inode->i_sb);
+ inode_lock(inode);
+ reiserfs_write_lock_nested(inode->i_sb, depth);
+}
reiserfs_write_lock(inode->i_sb);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 2a12d46d7fb4..8a36696d6df9 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -1650,10 +1650,10 @@ const struct inode_operations reiserfs_dir_inode_operations = {
.mknod = reiserfs_mknod,
.rename = reiserfs_rename,
.setattr = reiserfs_setattr,
- .setxattr = reiserfs_setxattr,
- .getxattr = reiserfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = reiserfs_listxattr,
- .removexattr = reiserfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = reiserfs_permission,
.get_acl = reiserfs_get_acl,
.set_acl = reiserfs_set_acl,
@@ -1667,10 +1667,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = {
.readlink = generic_readlink,
.get_link = page_get_link,
.setattr = reiserfs_setattr,
- .setxattr = reiserfs_setxattr,
- .getxattr = reiserfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = reiserfs_listxattr,
- .removexattr = reiserfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = reiserfs_permission,
};
@@ -1679,10 +1679,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = {
*/
const struct inode_operations reiserfs_special_inode_operations = {
.setattr = reiserfs_setattr,
- .setxattr = reiserfs_setxattr,
- .getxattr = reiserfs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = reiserfs_listxattr,
- .removexattr = reiserfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = reiserfs_permission,
.get_acl = reiserfs_get_acl,
.set_acl = reiserfs_set_acl,
diff --git a/fs/reiserfs/objectid.c b/fs/reiserfs/objectid.c
index 99a5d5dae46a..415d66ca87d1 100644
--- a/fs/reiserfs/objectid.c
+++ b/fs/reiserfs/objectid.c
@@ -3,8 +3,8 @@
*/
#include <linux/string.h>
-#include <linux/random.h>
#include <linux/time.h>
+#include <linux/uuid.h>
#include "reiserfs.h"
/* find where objectid map starts */
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 28f5f8b11370..a33812ae9fad 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -764,60 +764,6 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers,
return xah;
}
-
-/*
- * Inode operation getxattr()
- */
-ssize_t
-reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer,
- size_t size)
-{
- const struct xattr_handler *handler;
-
- handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
-
- if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
- return -EOPNOTSUPP;
-
- return handler->get(handler, dentry, name, buffer, size);
-}
-
-/*
- * Inode operation setxattr()
- *
- * d_inode(dentry)->i_mutex down
- */
-int
-reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags)
-{
- const struct xattr_handler *handler;
-
- handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
-
- if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
- return -EOPNOTSUPP;
-
- return handler->set(handler, dentry, name, value, size, flags);
-}
-
-/*
- * Inode operation removexattr()
- *
- * d_inode(dentry)->i_mutex down
- */
-int reiserfs_removexattr(struct dentry *dentry, const char *name)
-{
- const struct xattr_handler *handler;
-
- handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
-
- if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
- return -EOPNOTSUPP;
-
- return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
-}
-
struct listxattr_buf {
struct dir_context ctx;
size_t size;
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index 15dde6262c00..613ff5aef94e 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -2,6 +2,7 @@
#include <linux/init.h>
#include <linux/list.h>
#include <linux/rwsem.h>
+#include <linux/xattr.h>
struct inode;
struct dentry;
@@ -18,12 +19,7 @@ int reiserfs_permission(struct inode *inode, int mask);
#ifdef CONFIG_REISERFS_FS_XATTR
#define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir)
-ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name,
- void *buffer, size_t size);
-int reiserfs_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-int reiserfs_removexattr(struct dentry *dentry, const char *name);
int reiserfs_xattr_get(struct inode *, const char *, void *, size_t);
int reiserfs_xattr_set(struct inode *, const char *, const void *, size_t, int);
@@ -92,10 +88,7 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
#else
-#define reiserfs_getxattr NULL
-#define reiserfs_setxattr NULL
#define reiserfs_listxattr NULL
-#define reiserfs_removexattr NULL
static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
{
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 558a16beaacb..dbed42f755e0 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -197,10 +197,8 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
size = reiserfs_xattr_get(inode, name, NULL, 0);
if (size < 0) {
- if (size == -ENODATA || size == -ENOSYS) {
- set_cached_acl(inode, type, NULL);
+ if (size == -ENODATA || size == -ENOSYS)
return NULL;
- }
return ERR_PTR(size);
}
@@ -220,8 +218,6 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
} else {
acl = reiserfs_posix_acl_from_disk(value, retval);
}
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
kfree(value);
return acl;
@@ -370,7 +366,7 @@ int reiserfs_cache_default_acl(struct inode *inode)
if (IS_PRIVATE(inode))
return 0;
- acl = reiserfs_get_acl(inode, ACL_TYPE_DEFAULT);
+ acl = get_acl(inode, ACL_TYPE_DEFAULT);
if (acl && !IS_ERR(acl)) {
int size = reiserfs_acl_size(acl->a_count);
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index ab0217d32039..86aeb9dd805a 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -9,29 +9,26 @@
#include <linux/uaccess.h>
static int
-security_get(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, void *buffer, size_t size)
+security_get(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, void *buffer, size_t size)
{
- if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
- return -EINVAL;
-
- if (IS_PRIVATE(d_inode(dentry)))
+ if (IS_PRIVATE(inode))
return -EPERM;
- return reiserfs_xattr_get(d_inode(dentry), name, buffer, size);
+ return reiserfs_xattr_get(inode, xattr_full_name(handler, name),
+ buffer, size);
}
static int
security_set(const struct xattr_handler *handler, struct dentry *dentry,
const char *name, const void *buffer, size_t size, int flags)
{
- if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
- return -EINVAL;
-
if (IS_PRIVATE(d_inode(dentry)))
return -EPERM;
- return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
+ return reiserfs_xattr_set(d_inode(dentry),
+ xattr_full_name(handler, name),
+ buffer, size, flags);
}
static bool security_list(struct dentry *dentry)
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index 64b67aa643a9..31837f031f59 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -8,29 +8,26 @@
#include <linux/uaccess.h>
static int
-trusted_get(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, void *buffer, size_t size)
+trusted_get(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, void *buffer, size_t size)
{
- if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
- return -EINVAL;
-
- if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
+ if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
return -EPERM;
- return reiserfs_xattr_get(d_inode(dentry), name, buffer, size);
+ return reiserfs_xattr_get(inode, xattr_full_name(handler, name),
+ buffer, size);
}
static int
trusted_set(const struct xattr_handler *handler, struct dentry *dentry,
const char *name, const void *buffer, size_t size, int flags)
{
- if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
- return -EINVAL;
-
if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
return -EPERM;
- return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
+ return reiserfs_xattr_set(d_inode(dentry),
+ xattr_full_name(handler, name),
+ buffer, size, flags);
}
static bool trusted_list(struct dentry *dentry)
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index 12e6306f562a..f7c39731684b 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -7,27 +7,24 @@
#include <linux/uaccess.h>
static int
-user_get(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, void *buffer, size_t size)
+user_get(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, void *buffer, size_t size)
{
-
- if (strlen(name) < sizeof(XATTR_USER_PREFIX))
- return -EINVAL;
- if (!reiserfs_xattrs_user(dentry->d_sb))
+ if (!reiserfs_xattrs_user(inode->i_sb))
return -EOPNOTSUPP;
- return reiserfs_xattr_get(d_inode(dentry), name, buffer, size);
+ return reiserfs_xattr_get(inode, xattr_full_name(handler, name),
+ buffer, size);
}
static int
user_set(const struct xattr_handler *handler, struct dentry *dentry,
const char *name, const void *buffer, size_t size, int flags)
{
- if (strlen(name) < sizeof(XATTR_USER_PREFIX))
- return -EINVAL;
-
if (!reiserfs_xattrs_user(dentry->d_sb))
return -EOPNOTSUPP;
- return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
+ return reiserfs_xattr_set(d_inode(dentry),
+ xattr_full_name(handler, name),
+ buffer, size, flags);
}
static bool user_list(struct dentry *dentry)
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 6b00ca357c58..d0f8a38dfafa 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -280,8 +280,8 @@ error:
static const struct file_operations romfs_dir_operations = {
.read = generic_read_dir,
- .iterate = romfs_readdir,
- .llseek = default_llseek,
+ .iterate_shared = romfs_readdir,
+ .llseek = generic_file_llseek,
};
static const struct inode_operations romfs_dir_inode_operations = {
diff --git a/fs/select.c b/fs/select.c
index 869293988c2a..8ed9da50896a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -47,7 +47,7 @@
#define MAX_SLACK (100 * NSEC_PER_MSEC)
-static long __estimate_accuracy(struct timespec *tv)
+static long __estimate_accuracy(struct timespec64 *tv)
{
long slack;
int divfactor = 1000;
@@ -70,10 +70,10 @@ static long __estimate_accuracy(struct timespec *tv)
return slack;
}
-u64 select_estimate_accuracy(struct timespec *tv)
+u64 select_estimate_accuracy(struct timespec64 *tv)
{
u64 ret;
- struct timespec now;
+ struct timespec64 now;
/*
* Realtime tasks get a slack of 0 for obvious reasons.
@@ -82,8 +82,8 @@ u64 select_estimate_accuracy(struct timespec *tv)
if (rt_task(current))
return 0;
- ktime_get_ts(&now);
- now = timespec_sub(*tv, now);
+ ktime_get_ts64(&now);
+ now = timespec64_sub(*tv, now);
ret = __estimate_accuracy(&now);
if (ret < current->timer_slack_ns)
return current->timer_slack_ns;
@@ -260,7 +260,7 @@ EXPORT_SYMBOL(poll_schedule_timeout);
/**
* poll_select_set_timeout - helper function to setup the timeout value
- * @to: pointer to timespec variable for the final timeout
+ * @to: pointer to timespec64 variable for the final timeout
* @sec: seconds (from user space)
* @nsec: nanoseconds (from user space)
*
@@ -269,26 +269,28 @@ EXPORT_SYMBOL(poll_schedule_timeout);
*
* Returns -EINVAL if sec/nsec are not normalized. Otherwise 0.
*/
-int poll_select_set_timeout(struct timespec *to, long sec, long nsec)
+int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec)
{
- struct timespec ts = {.tv_sec = sec, .tv_nsec = nsec};
+ struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec};
- if (!timespec_valid(&ts))
+ if (!timespec64_valid(&ts))
return -EINVAL;
/* Optimize for the zero timeout value here */
if (!sec && !nsec) {
to->tv_sec = to->tv_nsec = 0;
} else {
- ktime_get_ts(to);
- *to = timespec_add_safe(*to, ts);
+ ktime_get_ts64(to);
+ *to = timespec64_add_safe(*to, ts);
}
return 0;
}
-static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+static int poll_select_copy_remaining(struct timespec64 *end_time,
+ void __user *p,
int timeval, int ret)
{
+ struct timespec64 rts64;
struct timespec rts;
struct timeval rtv;
@@ -302,16 +304,18 @@ static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
if (!end_time->tv_sec && !end_time->tv_nsec)
return ret;
- ktime_get_ts(&rts);
- rts = timespec_sub(*end_time, rts);
- if (rts.tv_sec < 0)
- rts.tv_sec = rts.tv_nsec = 0;
+ ktime_get_ts64(&rts64);
+ rts64 = timespec64_sub(*end_time, rts64);
+ if (rts64.tv_sec < 0)
+ rts64.tv_sec = rts64.tv_nsec = 0;
+
+ rts = timespec64_to_timespec(rts64);
if (timeval) {
if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
memset(&rtv, 0, sizeof(rtv));
- rtv.tv_sec = rts.tv_sec;
- rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC;
+ rtv.tv_sec = rts64.tv_sec;
+ rtv.tv_usec = rts64.tv_nsec / NSEC_PER_USEC;
if (!copy_to_user(p, &rtv, sizeof(rtv)))
return ret;
@@ -396,7 +400,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
wait->_key |= POLLOUT_SET;
}
-int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
+int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
{
ktime_t expire, *to = NULL;
struct poll_wqueues table;
@@ -522,7 +526,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
* pointer to the expiry value.
*/
if (end_time && !to) {
- expire = timespec_to_ktime(*end_time);
+ expire = timespec64_to_ktime(*end_time);
to = &expire;
}
@@ -545,7 +549,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
* I'm trying ERESTARTNOHAND which restart only when you want to.
*/
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
- fd_set __user *exp, struct timespec *end_time)
+ fd_set __user *exp, struct timespec64 *end_time)
{
fd_set_bits fds;
void *bits;
@@ -622,7 +626,7 @@ out_nofds:
SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
fd_set __user *, exp, struct timeval __user *, tvp)
{
- struct timespec end_time, *to = NULL;
+ struct timespec64 end_time, *to = NULL;
struct timeval tv;
int ret;
@@ -648,15 +652,17 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
const sigset_t __user *sigmask, size_t sigsetsize)
{
sigset_t ksigmask, sigsaved;
- struct timespec ts, end_time, *to = NULL;
+ struct timespec ts;
+ struct timespec64 ts64, end_time, *to = NULL;
int ret;
if (tsp) {
if (copy_from_user(&ts, tsp, sizeof(ts)))
return -EFAULT;
+ ts64 = timespec_to_timespec64(ts);
to = &end_time;
- if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+ if (poll_select_set_timeout(to, ts64.tv_sec, ts64.tv_nsec))
return -EINVAL;
}
@@ -779,7 +785,7 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait,
}
static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
- struct timespec *end_time)
+ struct timespec64 *end_time)
{
poll_table* pt = &wait->pt;
ktime_t expire, *to = NULL;
@@ -854,7 +860,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
* pointer to the expiry value.
*/
if (end_time && !to) {
- expire = timespec_to_ktime(*end_time);
+ expire = timespec64_to_ktime(*end_time);
to = &expire;
}
@@ -868,7 +874,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
sizeof(struct pollfd))
int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
- struct timespec *end_time)
+ struct timespec64 *end_time)
{
struct poll_wqueues table;
int err = -EFAULT, fdcount, len, size;
@@ -936,7 +942,7 @@ static long do_restart_poll(struct restart_block *restart_block)
{
struct pollfd __user *ufds = restart_block->poll.ufds;
int nfds = restart_block->poll.nfds;
- struct timespec *to = NULL, end_time;
+ struct timespec64 *to = NULL, end_time;
int ret;
if (restart_block->poll.has_timeout) {
@@ -957,7 +963,7 @@ static long do_restart_poll(struct restart_block *restart_block)
SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
int, timeout_msecs)
{
- struct timespec end_time, *to = NULL;
+ struct timespec64 end_time, *to = NULL;
int ret;
if (timeout_msecs >= 0) {
@@ -993,7 +999,8 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
size_t, sigsetsize)
{
sigset_t ksigmask, sigsaved;
- struct timespec ts, end_time, *to = NULL;
+ struct timespec ts;
+ struct timespec64 end_time, *to = NULL;
int ret;
if (tsp) {
diff --git a/fs/splice.c b/fs/splice.c
index b018eb485019..dd9bf7e410d2 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1143,6 +1143,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
if (unlikely(ret < 0))
return ret;
+ if (unlikely(len > MAX_RW_COUNT))
+ len = MAX_RW_COUNT;
+
if (in->f_op->splice_read)
splice_read = in->f_op->splice_read;
else
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index d8c2d747be28..a5845f94a2a1 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -231,6 +231,6 @@ failed_read:
const struct file_operations squashfs_dir_ops = {
.read = generic_read_dir,
- .iterate = squashfs_readdir,
- .llseek = default_llseek,
+ .iterate_shared = squashfs_readdir,
+ .llseek = generic_file_llseek,
};
diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c
index 1e9de96288d8..1548b3784548 100644
--- a/fs/squashfs/xattr.c
+++ b/fs/squashfs/xattr.c
@@ -214,10 +214,12 @@ failed:
static int squashfs_xattr_handler_get(const struct xattr_handler *handler,
- struct dentry *d, const char *name,
+ struct dentry *unused,
+ struct inode *inode,
+ const char *name,
void *buffer, size_t size)
{
- return squashfs_xattr_get(d_inode(d), handler->flags, name,
+ return squashfs_xattr_get(inode, handler->flags, name,
buffer, size);
}
diff --git a/fs/super.c b/fs/super.c
index 74914b1bae70..d78b9847e6cb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -285,7 +285,7 @@ static void put_super(struct super_block *sb)
* deactivate_locked_super - drop an active reference to superblock
* @s: superblock to deactivate
*
- * Drops an active reference to superblock, converting it into a temprory
+ * Drops an active reference to superblock, converting it into a temporary
* one if there is no other active references left. In that case we
* tell fs driver to shut it down and drop the temporary reference we
* had just acquired.
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index c0f0a3e643eb..2661b77fc8a7 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -23,7 +23,7 @@ static int sysv_readdir(struct file *, struct dir_context *);
const struct file_operations sysv_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = sysv_readdir,
+ .iterate_shared = sysv_readdir,
.fsync = generic_file_fsync,
};
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 795992a8321e..4b86d3a738e1 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -1182,10 +1182,10 @@ const struct inode_operations ubifs_dir_inode_operations = {
.rename = ubifs_rename,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
- .setxattr = ubifs_setxattr,
- .getxattr = ubifs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ubifs_listxattr,
- .removexattr = ubifs_removexattr,
+ .removexattr = generic_removexattr,
#ifdef CONFIG_UBIFS_ATIME_SUPPORT
.update_time = ubifs_update_time,
#endif
@@ -1195,7 +1195,7 @@ const struct file_operations ubifs_dir_operations = {
.llseek = generic_file_llseek,
.release = ubifs_dir_release,
.read = generic_read_dir,
- .iterate = ubifs_readdir,
+ .iterate_shared = ubifs_readdir,
.fsync = ubifs_fsync,
.unlocked_ioctl = ubifs_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 446753d8ac34..08316972ff93 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1597,10 +1597,10 @@ const struct address_space_operations ubifs_file_address_operations = {
const struct inode_operations ubifs_file_inode_operations = {
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
- .setxattr = ubifs_setxattr,
- .getxattr = ubifs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ubifs_listxattr,
- .removexattr = ubifs_removexattr,
+ .removexattr = generic_removexattr,
#ifdef CONFIG_UBIFS_ATIME_SUPPORT
.update_time = ubifs_update_time,
#endif
@@ -1611,10 +1611,10 @@ const struct inode_operations ubifs_symlink_inode_operations = {
.get_link = simple_get_link,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
- .setxattr = ubifs_setxattr,
- .getxattr = ubifs_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ubifs_listxattr,
- .removexattr = ubifs_removexattr,
+ .removexattr = generic_removexattr,
#ifdef CONFIG_UBIFS_ATIME_SUPPORT
.update_time = ubifs_update_time,
#endif
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index f4fbc7b6b794..3cbb904a6d7d 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -28,8 +28,8 @@
#include "ubifs.h"
#include <linux/slab.h>
-#include <linux/random.h>
#include <linux/math64.h>
+#include <linux/uuid.h>
/*
* Default journal size in logical eraseblocks as a percent of total
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index e98c24ee25a1..70349954e78b 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2040,6 +2040,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
if (c->max_inode_sz > MAX_LFS_FILESIZE)
sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE;
sb->s_op = &ubifs_super_operations;
+ sb->s_xattr = ubifs_xattr_handlers;
mutex_lock(&c->umount_mutex);
err = mount_ubifs(c);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 4cd7e569cd00..ddf9f6b9eee2 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -37,6 +37,7 @@
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/security.h>
+#include <linux/xattr.h>
#include "ubifs-media.h"
/* Version of this UBIFS implementation */
@@ -1732,12 +1733,8 @@ int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
/* xattr.c */
-int ubifs_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
-ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
- size_t size);
+extern const struct xattr_handler *ubifs_xattr_handlers[];
ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-int ubifs_removexattr(struct dentry *dentry, const char *name);
int ubifs_init_security(struct inode *dentry, struct inode *inode,
const struct qstr *qstr);
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index b043e044121d..6c277eb6aef9 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -249,42 +249,6 @@ out_free:
return err;
}
-/**
- * check_namespace - check extended attribute name-space.
- * @nm: extended attribute name
- *
- * This function makes sure the extended attribute name belongs to one of the
- * supported extended attribute name-spaces. Returns name-space index in case
- * of success and a negative error code in case of failure.
- */
-static int check_namespace(const struct qstr *nm)
-{
- int type;
-
- if (nm->len > UBIFS_MAX_NLEN)
- return -ENAMETOOLONG;
-
- if (!strncmp(nm->name, XATTR_TRUSTED_PREFIX,
- XATTR_TRUSTED_PREFIX_LEN)) {
- if (nm->name[XATTR_TRUSTED_PREFIX_LEN] == '\0')
- return -EINVAL;
- type = TRUSTED_XATTR;
- } else if (!strncmp(nm->name, XATTR_USER_PREFIX,
- XATTR_USER_PREFIX_LEN)) {
- if (nm->name[XATTR_USER_PREFIX_LEN] == '\0')
- return -EINVAL;
- type = USER_XATTR;
- } else if (!strncmp(nm->name, XATTR_SECURITY_PREFIX,
- XATTR_SECURITY_PREFIX_LEN)) {
- if (nm->name[XATTR_SECURITY_PREFIX_LEN] == '\0')
- return -EINVAL;
- type = SECURITY_XATTR;
- } else
- return -EOPNOTSUPP;
-
- return type;
-}
-
static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum)
{
struct inode *inode;
@@ -302,24 +266,23 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum)
return ERR_PTR(-EINVAL);
}
-static int setxattr(struct inode *host, const char *name, const void *value,
- size_t size, int flags)
+static int __ubifs_setxattr(struct inode *host, const char *name,
+ const void *value, size_t size, int flags)
{
struct inode *inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_dent_node *xent;
union ubifs_key key;
- int err, type;
+ int err;
ubifs_assert(inode_is_locked(host));
if (size > UBIFS_MAX_INO_DATA)
return -ERANGE;
- type = check_namespace(&nm);
- if (type < 0)
- return type;
+ if (nm.len > UBIFS_MAX_NLEN)
+ return -ENAMETOOLONG;
xent = kmalloc(UBIFS_MAX_XENT_NODE_SZ, GFP_NOFS);
if (!xent)
@@ -363,19 +326,10 @@ out_free:
return err;
}
-int ubifs_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
+static ssize_t __ubifs_getxattr(struct inode *host, const char *name,
+ void *buf, size_t size)
{
- dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
- name, d_inode(dentry)->i_ino, dentry, size);
-
- return setxattr(d_inode(dentry), name, value, size, flags);
-}
-
-ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
- size_t size)
-{
- struct inode *inode, *host = d_inode(dentry);
+ struct inode *inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_inode *ui;
@@ -383,12 +337,8 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
union ubifs_key key;
int err;
- dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name,
- host->i_ino, dentry, size);
-
- err = check_namespace(&nm);
- if (err < 0)
- return err;
+ if (nm.len > UBIFS_MAX_NLEN)
+ return -ENAMETOOLONG;
xent = kmalloc(UBIFS_MAX_XENT_NODE_SZ, GFP_NOFS);
if (!xent)
@@ -460,8 +410,6 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size)
lowest_xent_key(c, &key, host->i_ino);
while (1) {
- int type;
-
xent = ubifs_tnc_next_ent(c, &key, &nm);
if (IS_ERR(xent)) {
err = PTR_ERR(xent);
@@ -471,14 +419,10 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size)
nm.name = xent->name;
nm.len = le16_to_cpu(xent->nlen);
- type = check_namespace(&nm);
- if (unlikely(type < 0)) {
- err = type;
- break;
- }
-
/* Show trusted namespace only for "power" users */
- if (type != TRUSTED_XATTR || capable(CAP_SYS_ADMIN)) {
+ if (strncmp(xent->name, XATTR_TRUSTED_PREFIX,
+ XATTR_TRUSTED_PREFIX_LEN) ||
+ capable(CAP_SYS_ADMIN)) {
memcpy(buffer + written, nm.name, nm.len + 1);
written += nm.len + 1;
}
@@ -538,22 +482,19 @@ out_cancel:
return err;
}
-int ubifs_removexattr(struct dentry *dentry, const char *name)
+static int __ubifs_removexattr(struct inode *host, const char *name)
{
- struct inode *inode, *host = d_inode(dentry);
+ struct inode *inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_dent_node *xent;
union ubifs_key key;
int err;
- dbg_gen("xattr '%s', ino %lu ('%pd')", name,
- host->i_ino, dentry);
ubifs_assert(inode_is_locked(host));
- err = check_namespace(&nm);
- if (err < 0)
- return err;
+ if (nm.len > UBIFS_MAX_NLEN)
+ return -ENAMETOOLONG;
xent = kmalloc(UBIFS_MAX_XENT_NODE_SZ, GFP_NOFS);
if (!xent)
@@ -603,7 +544,7 @@ static int init_xattrs(struct inode *inode, const struct xattr *xattr_array,
}
strcpy(name, XATTR_SECURITY_PREFIX);
strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name);
- err = setxattr(inode, name, xattr->value, xattr->value_len, 0);
+ err = __ubifs_setxattr(inode, name, xattr->value, xattr->value_len, 0);
kfree(name);
if (err < 0)
break;
@@ -626,3 +567,53 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode,
}
return err;
}
+
+static int ubifs_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name,
+ inode->i_ino, dentry, size);
+
+ return __ubifs_getxattr(inode, name, buffer, size);
+}
+
+static int ubifs_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct inode *inode = d_inode(dentry);
+
+ dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
+ name, inode->i_ino, dentry, size);
+
+ if (value)
+ return __ubifs_setxattr(inode, name, value, size, flags);
+ else
+ return __ubifs_removexattr(inode, name);
+}
+
+const struct xattr_handler ubifs_user_xattr_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .get = ubifs_xattr_get,
+ .set = ubifs_xattr_set,
+};
+
+const struct xattr_handler ubifs_trusted_xattr_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .get = ubifs_xattr_get,
+ .set = ubifs_xattr_set,
+};
+
+const struct xattr_handler ubifs_security_xattr_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .get = ubifs_xattr_get,
+ .set = ubifs_xattr_set,
+};
+
+const struct xattr_handler *ubifs_xattr_handlers[] = {
+ &ubifs_user_xattr_handler,
+ &ubifs_trusted_xattr_handler,
+ &ubifs_security_xattr_handler,
+ NULL
+};
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index b51b371b874a..4c5593abc553 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -202,7 +202,7 @@ out:
const struct file_operations udf_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = udf_readdir,
+ .iterate_shared = udf_readdir,
.unlocked_ioctl = udf_ioctl,
.fsync = generic_file_fsync,
};
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 877ba1c9b461..632570617327 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -99,8 +99,7 @@ static int udf_adinicb_write_begin(struct file *file,
return 0;
}
-static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
/* Fallback to buffered I/O. */
return 0;
@@ -153,9 +152,7 @@ out:
if (retval > 0) {
mark_inode_dirty(inode);
- err = generic_write_sync(file, iocb->ki_pos - retval, retval);
- if (err < 0)
- retval = err;
+ retval = generic_write_sync(iocb, retval);
}
return retval;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 2dc461eeb415..f323aff740ef 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -214,8 +214,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
return ret;
}
-static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -223,9 +222,9 @@ static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
size_t count = iov_iter_count(iter);
ssize_t ret;
- ret = blockdev_direct_IO(iocb, inode, iter, offset, udf_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, udf_get_block);
if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE))
- udf_write_failed(mapping, offset + count);
+ udf_write_failed(mapping, iocb->ki_pos + count);
return ret;
}
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index a2ba11eca995..c3e5c9679371 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1250,7 +1250,7 @@ static struct dentry *udf_get_parent(struct dentry *child)
brelse(fibh.sbh);
tloc = lelb_to_cpu(cfi.icb.extLocation);
- inode = udf_iget(d_inode(child)->i_sb, &tloc);
+ inode = udf_iget(child->d_sb, &tloc);
if (IS_ERR(inode))
return ERR_CAST(inode);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index fa92fe839fda..5e2c8c814e1b 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -78,6 +78,15 @@
#define VSD_FIRST_SECTOR_OFFSET 32768
#define VSD_MAX_SECTOR_OFFSET 0x800000
+/*
+ * Maximum number of Terminating Descriptor / Logical Volume Integrity
+ * Descriptor redirections. The chosen numbers are arbitrary - just that we
+ * hopefully don't limit any real use of rewritten inode on write-once media
+ * but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_TD_NESTING 64
+#define UDF_MAX_LVID_NESTING 1000
+
enum { UDF_MAX_LINKS = 0xffff };
/* These are the "meat" - everything else is stuffing */
@@ -919,14 +928,14 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
#endif
}
- ret = udf_CS0toUTF8(outstr, 31, pvoldesc->volIdent, 32);
+ ret = udf_dstrCS0toUTF8(outstr, 31, pvoldesc->volIdent, 32);
if (ret < 0)
goto out_bh;
strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret);
udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident);
- ret = udf_CS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128);
+ ret = udf_dstrCS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128);
if (ret < 0)
goto out_bh;
@@ -1541,42 +1550,52 @@ out_bh:
}
/*
- * udf_load_logicalvolint
- *
+ * Find the prevailing Logical Volume Integrity Descriptor.
*/
static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ad loc)
{
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh, *final_bh;
uint16_t ident;
struct udf_sb_info *sbi = UDF_SB(sb);
struct logicalVolIntegrityDesc *lvid;
+ int indirections = 0;
+
+ while (++indirections <= UDF_MAX_LVID_NESTING) {
+ final_bh = NULL;
+ while (loc.extLength > 0 &&
+ (bh = udf_read_tagged(sb, loc.extLocation,
+ loc.extLocation, &ident))) {
+ if (ident != TAG_IDENT_LVID) {
+ brelse(bh);
+ break;
+ }
+
+ brelse(final_bh);
+ final_bh = bh;
- while (loc.extLength > 0 &&
- (bh = udf_read_tagged(sb, loc.extLocation,
- loc.extLocation, &ident)) &&
- ident == TAG_IDENT_LVID) {
- sbi->s_lvid_bh = bh;
- lvid = (struct logicalVolIntegrityDesc *)bh->b_data;
+ loc.extLength -= sb->s_blocksize;
+ loc.extLocation++;
+ }
- if (lvid->nextIntegrityExt.extLength)
- udf_load_logicalvolint(sb,
- leea_to_cpu(lvid->nextIntegrityExt));
+ if (!final_bh)
+ return;
- if (sbi->s_lvid_bh != bh)
- brelse(bh);
- loc.extLength -= sb->s_blocksize;
- loc.extLocation++;
+ brelse(sbi->s_lvid_bh);
+ sbi->s_lvid_bh = final_bh;
+
+ lvid = (struct logicalVolIntegrityDesc *)final_bh->b_data;
+ if (lvid->nextIntegrityExt.extLength == 0)
+ return;
+
+ loc = leea_to_cpu(lvid->nextIntegrityExt);
}
- if (sbi->s_lvid_bh != bh)
- brelse(bh);
+
+ udf_warn(sb, "Too many LVID indirections (max %u), ignoring.\n",
+ UDF_MAX_LVID_NESTING);
+ brelse(sbi->s_lvid_bh);
+ sbi->s_lvid_bh = NULL;
}
-/*
- * Maximum number of Terminating Descriptor redirections. The chosen number is
- * arbitrary - just that we hopefully don't limit any real use of rewritten
- * inode on write-once media but avoid looping for too long on corrupted media.
- */
-#define UDF_MAX_TD_NESTING 64
/*
* Process a main/reserve volume descriptor sequence.
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 1f32c7bd9f57..27b5335730c9 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -3,9 +3,7 @@
#include <linux/mutex.h>
#include <linux/bitops.h>
-
-/* Since UDF 2.01 is ISO 13346 based... */
-#define UDF_SUPER_MAGIC 0x15013346
+#include <linux/magic.h>
#define UDF_MAX_READ_VERSION 0x0250
#define UDF_MAX_WRITE_VERSION 0x0201
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 972b70625614..263829ef1873 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -212,7 +212,7 @@ extern int udf_get_filename(struct super_block *, const uint8_t *, int,
uint8_t *, int);
extern int udf_put_filename(struct super_block *, const uint8_t *, int,
uint8_t *, int);
-extern int udf_CS0toUTF8(uint8_t *, int, const uint8_t *, int);
+extern int udf_dstrCS0toUTF8(uint8_t *, int, const uint8_t *, int);
/* ialloc.c */
extern void udf_free_inode(struct inode *);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index 3ff42f4437f3..695389a4fc23 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -335,9 +335,21 @@ try_again:
return u_len;
}
-int udf_CS0toUTF8(uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len)
+int udf_dstrCS0toUTF8(uint8_t *utf_o, int o_len,
+ const uint8_t *ocu_i, int i_len)
{
- return udf_name_from_CS0(utf_o, o_len, ocu_i, i_len,
+ int s_len = 0;
+
+ if (i_len > 0) {
+ s_len = ocu_i[i_len - 1];
+ if (s_len >= i_len) {
+ pr_err("incorrect dstring lengths (%d/%d)\n",
+ s_len, i_len);
+ return -EINVAL;
+ }
+ }
+
+ return udf_name_from_CS0(utf_o, o_len, ocu_i, s_len,
udf_uni2char_utf8, 0);
}
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 0b1457292734..57dcceda17d6 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -105,7 +105,7 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
}
-static void ufs_check_page(struct page *page)
+static bool ufs_check_page(struct page *page)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
@@ -143,7 +143,7 @@ static void ufs_check_page(struct page *page)
goto Eend;
out:
SetPageChecked(page);
- return;
+ return true;
/* Too bad, we had an error */
@@ -180,8 +180,8 @@ Eend:
"offset=%lu",
dir->i_ino, (page->index<<PAGE_SHIFT)+offs);
fail:
- SetPageChecked(page);
SetPageError(page);
+ return false;
}
static struct page *ufs_get_page(struct inode *dir, unsigned long n)
@@ -190,10 +190,10 @@ static struct page *ufs_get_page(struct inode *dir, unsigned long n)
struct page *page = read_mapping_page(mapping, n, NULL);
if (!IS_ERR(page)) {
kmap(page);
- if (!PageChecked(page))
- ufs_check_page(page);
- if (PageError(page))
- goto fail;
+ if (unlikely(!PageChecked(page))) {
+ if (PageError(page) || !ufs_check_page(page))
+ goto fail;
+ }
}
return page;
@@ -653,7 +653,7 @@ not_empty:
const struct file_operations ufs_dir_operations = {
.read = generic_read_dir,
- .iterate = ufs_readdir,
+ .iterate_shared = ufs_readdir,
.fsync = generic_file_fsync,
.llseek = generic_file_llseek,
};
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 442fd52ebffe..f04ab232d08d 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -132,7 +132,7 @@ static struct dentry *ufs_get_parent(struct dentry *child)
ino = ufs_inode_by_name(d_inode(child), &dot_dot);
if (!ino)
return ERR_PTR(-ENOENT);
- return d_obtain_alias(ufs_iget(d_inode(child)->i_sb, ino));
+ return d_obtain_alias(ufs_iget(child->d_sb, ino));
}
static const struct export_operations ufs_export_ops = {
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 66cdb44616d5..2d97952e341a 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -137,7 +137,7 @@ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
- mmput(ctx->mm);
+ mmdrop(ctx->mm);
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
}
}
@@ -434,6 +434,9 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
ACCESS_ONCE(ctx->released) = true;
+ if (!mmget_not_zero(mm))
+ goto wakeup;
+
/*
* Flush page faults out of all CPUs. NOTE: all page faults
* must be retried without returning VM_FAULT_SIGBUS if
@@ -466,7 +469,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
up_write(&mm->mmap_sem);
-
+ mmput(mm);
+wakeup:
/*
* After no new page faults can wait on this fault_*wqh, flush
* the last page faults that may have been already waiting on
@@ -760,10 +764,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
start = uffdio_register.range.start;
end = start + uffdio_register.range.len;
+ ret = -ENOMEM;
+ if (!mmget_not_zero(mm))
+ goto out;
+
down_write(&mm->mmap_sem);
vma = find_vma_prev(mm, start, &prev);
-
- ret = -ENOMEM;
if (!vma)
goto out_unlock;
@@ -864,6 +870,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
} while (vma && vma->vm_start < end);
out_unlock:
up_write(&mm->mmap_sem);
+ mmput(mm);
if (!ret) {
/*
* Now that we scanned all vmas we can already tell
@@ -902,10 +909,12 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
start = uffdio_unregister.start;
end = start + uffdio_unregister.len;
+ ret = -ENOMEM;
+ if (!mmget_not_zero(mm))
+ goto out;
+
down_write(&mm->mmap_sem);
vma = find_vma_prev(mm, start, &prev);
-
- ret = -ENOMEM;
if (!vma)
goto out_unlock;
@@ -998,6 +1007,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
} while (vma && vma->vm_start < end);
out_unlock:
up_write(&mm->mmap_sem);
+ mmput(mm);
out:
return ret;
}
@@ -1067,9 +1077,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
goto out;
if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
goto out;
-
- ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
- uffdio_copy.len);
+ if (mmget_not_zero(ctx->mm)) {
+ ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
+ uffdio_copy.len);
+ mmput(ctx->mm);
+ }
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
return -EFAULT;
if (ret < 0)
@@ -1110,8 +1122,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
goto out;
- ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
- uffdio_zeropage.range.len);
+ if (mmget_not_zero(ctx->mm)) {
+ ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
+ uffdio_zeropage.range.len);
+ mmput(ctx->mm);
+ }
if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
return -EFAULT;
if (ret < 0)
@@ -1289,12 +1304,12 @@ static struct file *userfaultfd_file_create(int flags)
ctx->released = false;
ctx->mm = current->mm;
/* prevent the mm struct to be freed */
- atomic_inc(&ctx->mm->mm_users);
+ atomic_inc(&ctx->mm->mm_count);
file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
if (IS_ERR(file)) {
- mmput(ctx->mm);
+ mmdrop(ctx->mm);
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
}
out:
diff --git a/fs/xattr.c b/fs/xattr.c
index 4861322e28e8..b11945e15fde 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -192,7 +192,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
if (!inode->i_op->getxattr)
return -EOPNOTSUPP;
- error = inode->i_op->getxattr(dentry, name, NULL, 0);
+ error = inode->i_op->getxattr(dentry, inode, name, NULL, 0);
if (error < 0)
return error;
@@ -203,7 +203,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
memset(value, 0, error + 1);
}
- error = inode->i_op->getxattr(dentry, name, value, error);
+ error = inode->i_op->getxattr(dentry, inode, name, value, error);
*xattr_value = value;
return error;
}
@@ -236,7 +236,7 @@ vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size)
}
nolsm:
if (inode->i_op->getxattr)
- error = inode->i_op->getxattr(dentry, name, value, size);
+ error = inode->i_op->getxattr(dentry, inode, name, value, size);
else
error = -EOPNOTSUPP;
@@ -691,14 +691,16 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name)
* Find the handler for the prefix and dispatch its get() operation.
*/
ssize_t
-generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size)
+generic_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
const struct xattr_handler *handler;
handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
- return handler->get(handler, dentry, name, buffer, size);
+ return handler->get(handler, dentry, inode,
+ name, buffer, size);
}
/*
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 2d5df1f23bbc..b6e527b8eccb 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -158,22 +158,14 @@ xfs_get_acl(struct inode *inode, int type)
if (error) {
/*
* If the attribute doesn't exist make sure we have a negative
- * cache entry, for any other error assume it is transient and
- * leave the cache entry as ACL_NOT_CACHED.
+ * cache entry, for any other error assume it is transient.
*/
- if (error == -ENOATTR)
- goto out_update_cache;
- acl = ERR_PTR(error);
- goto out;
+ if (error != -ENOATTR)
+ acl = ERR_PTR(error);
+ } else {
+ acl = xfs_acl_from_disk(xfs_acl, len,
+ XFS_ACL_MAX_ENTRIES(ip->i_mount));
}
-
- acl = xfs_acl_from_disk(xfs_acl, len, XFS_ACL_MAX_ENTRIES(ip->i_mount));
- if (IS_ERR(acl))
- goto out;
-
-out_update_cache:
- set_cached_acl(inode, type, acl);
-out:
kmem_free(xfs_acl);
return acl;
}
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index e49b2406d15d..c535887c60a8 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1406,8 +1406,7 @@ xfs_end_io_direct_write(
STATIC ssize_t
xfs_vm_direct_IO(
struct kiocb *iocb,
- struct iov_iter *iter,
- loff_t offset)
+ struct iov_iter *iter)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
dio_iodone_t *endio = NULL;
@@ -1420,12 +1419,12 @@ xfs_vm_direct_IO(
}
if (IS_DAX(inode)) {
- return dax_do_io(iocb, inode, iter, offset,
+ return dax_do_io(iocb, inode, iter,
xfs_get_blocks_direct, endio, 0);
}
bdev = xfs_find_bdev_for_inode(inode);
- return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
+ return __blockdev_direct_IO(iocb, inode, bdev, iter,
xfs_get_blocks_direct, endio, NULL, flags);
}
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 93b3ab0c5435..f44f79996978 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -273,10 +273,11 @@ xfs_dir2_leaf_readbuf(
size_t bufsize,
struct xfs_dir2_leaf_map_info *mip,
xfs_dir2_off_t *curoff,
- struct xfs_buf **bpp)
+ struct xfs_buf **bpp,
+ bool trim_map)
{
struct xfs_inode *dp = args->dp;
- struct xfs_buf *bp = *bpp;
+ struct xfs_buf *bp = NULL;
struct xfs_bmbt_irec *map = mip->map;
struct blk_plug plug;
int error = 0;
@@ -286,13 +287,10 @@ xfs_dir2_leaf_readbuf(
struct xfs_da_geometry *geo = args->geo;
/*
- * If we have a buffer, we need to release it and
- * take it out of the mapping.
+ * If the caller just finished processing a buffer, it will tell us
+ * we need to trim that block out of the mapping now it is done.
*/
-
- if (bp) {
- xfs_trans_brelse(NULL, bp);
- bp = NULL;
+ if (trim_map) {
mip->map_blocks -= geo->fsbcount;
/*
* Loop to get rid of the extents for the
@@ -533,10 +531,17 @@ xfs_dir2_leaf_getdents(
*/
if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) {
int lock_mode;
+ bool trim_map = false;
+
+ if (bp) {
+ xfs_trans_brelse(NULL, bp);
+ bp = NULL;
+ trim_map = true;
+ }
lock_mode = xfs_ilock_data_map_shared(dp);
error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
- &curoff, &bp);
+ &curoff, &bp, trim_map);
xfs_iunlock(dp, lock_mode);
if (error || !map_info->map_valid)
break;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 569938a4a357..85ce3032f815 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -718,18 +718,19 @@ xfs_file_dio_aio_write(
int unaligned_io = 0;
int iolock;
size_t count = iov_iter_count(from);
- loff_t pos = iocb->ki_pos;
loff_t end;
struct iov_iter data;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
- if (!IS_DAX(inode) && ((pos | count) & target->bt_logical_sectormask))
+ if (!IS_DAX(inode) &&
+ ((iocb->ki_pos | count) & target->bt_logical_sectormask))
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
- if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
+ if ((iocb->ki_pos & mp->m_blockmask) ||
+ ((iocb->ki_pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
@@ -760,8 +761,7 @@ xfs_file_dio_aio_write(
if (ret)
goto out;
count = iov_iter_count(from);
- pos = iocb->ki_pos;
- end = pos + count - 1;
+ end = iocb->ki_pos + count - 1;
/*
* See xfs_file_read_iter() for why we do a full-file flush here.
@@ -794,19 +794,18 @@ xfs_file_dio_aio_write(
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
data = *from;
- ret = mapping->a_ops->direct_IO(iocb, &data, pos);
+ ret = mapping->a_ops->direct_IO(iocb, &data);
/* see generic_file_direct_write() for why this is necessary */
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT,
+ iocb->ki_pos >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}
if (ret > 0) {
- pos += ret;
+ iocb->ki_pos += ret;
iov_iter_advance(from, ret);
- iocb->ki_pos = pos;
}
out:
xfs_rw_iunlock(ip, iolock);
@@ -904,14 +903,10 @@ xfs_file_write_iter(
ret = xfs_file_buffered_aio_write(iocb, from);
if (ret > 0) {
- ssize_t err;
-
XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
/* Handle various SYNC-type writes */
- err = generic_write_sync(file, iocb->ki_pos - ret, ret);
- if (err < 0)
- ret = err;
+ ret = generic_write_sync(iocb, ret);
}
return ret;
}
@@ -1714,7 +1709,7 @@ const struct file_operations xfs_file_operations = {
const struct file_operations xfs_dir_file_operations = {
.open = xfs_dir_open,
.read = generic_read_dir,
- .iterate = xfs_file_readdir,
+ .iterate_shared = xfs_file_readdir,
.llseek = generic_file_llseek,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 110f1d7d86b0..d111f691f313 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -32,11 +32,11 @@
static int
-xfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry,
- const char *name, void *value, size_t size)
+xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
+ struct inode *inode, const char *name, void *value, size_t size)
{
int xflags = handler->flags;
- struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ struct xfs_inode *ip = XFS_I(inode);
int error, asize = size;
/* Convert Linux syscall to XFS internal ATTR flags */