summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/acl.c4
-rw-r--r--fs/9p/v9fs.h1
-rw-r--r--fs/9p/v9fs_vfs.h4
-rw-r--r--fs/9p/vfs_addr.c87
-rw-r--r--fs/9p/vfs_dentry.c4
-rw-r--r--fs/9p/vfs_dir.c17
-rw-r--r--fs/9p/vfs_file.c326
-rw-r--r--fs/9p/vfs_inode.c34
-rw-r--r--fs/9p/vfs_inode_dotl.c16
-rw-r--r--fs/9p/vfs_super.c8
-rw-r--r--fs/9p/xattr.c80
-rw-r--r--fs/Kconfig2
-rw-r--r--fs/Kconfig.binfmt3
-rw-r--r--fs/Makefile1
-rw-r--r--fs/adfs/dir_fplus.c1
-rw-r--r--fs/adfs/file.c2
-rw-r--r--fs/adfs/inode.c2
-rw-r--r--fs/adfs/super.c20
-rw-r--r--fs/affs/affs.h28
-rw-r--r--fs/affs/amigaffs.c10
-rw-r--r--fs/affs/file.c34
-rw-r--r--fs/affs/inode.c34
-rw-r--r--fs/affs/namei.c16
-rw-r--r--fs/affs/super.c43
-rw-r--r--fs/afs/dir.c42
-rw-r--r--fs/afs/file.c2
-rw-r--r--fs/afs/inode.c4
-rw-r--r--fs/afs/misc.c16
-rw-r--r--fs/afs/mntpt.c8
-rw-r--r--fs/afs/rxrpc.c5
-rw-r--r--fs/afs/super.c2
-rw-r--r--fs/afs/write.c1
-rw-r--r--fs/aio.c278
-rw-r--r--fs/autofs4/autofs_i.h6
-rw-r--r--fs/autofs4/expire.c2
-rw-r--r--fs/autofs4/inode.c6
-rw-r--r--fs/autofs4/root.c18
-rw-r--r--fs/autofs4/symlink.c2
-rw-r--r--fs/autofs4/waitq.c6
-rw-r--r--fs/befs/befs.h22
-rw-r--r--fs/befs/datastream.c4
-rw-r--r--fs/befs/io.c2
-rw-r--r--fs/befs/linuxvfs.c16
-rw-r--r--fs/befs/super.c4
-rw-r--r--fs/bfs/dir.c12
-rw-r--r--fs/bfs/file.c2
-rw-r--r--fs/bfs/inode.c1
-rw-r--r--fs/binfmt_elf.c31
-rw-r--r--fs/binfmt_misc.c46
-rw-r--r--fs/block_dev.c27
-rw-r--r--fs/btrfs/export.c6
-rw-r--r--fs/btrfs/file.c32
-rw-r--r--fs/btrfs/inode.c59
-rw-r--r--fs/btrfs/ioctl.c22
-rw-r--r--fs/btrfs/super.c8
-rw-r--r--fs/btrfs/tree-log.c14
-rw-r--r--fs/btrfs/xattr.c16
-rw-r--r--fs/buffer.c4
-rw-r--r--fs/cachefiles/bind.c10
-rw-r--r--fs/cachefiles/interface.c6
-rw-r--r--fs/cachefiles/namei.c122
-rw-r--r--fs/cachefiles/rdwr.c14
-rw-r--r--fs/cachefiles/security.c6
-rw-r--r--fs/cachefiles/xattr.c22
-rw-r--r--fs/ceph/addr.c41
-rw-r--r--fs/ceph/caps.c53
-rw-r--r--fs/ceph/debugfs.c2
-rw-r--r--fs/ceph/dir.c108
-rw-r--r--fs/ceph/export.c28
-rw-r--r--fs/ceph/file.c31
-rw-r--r--fs/ceph/inode.c52
-rw-r--r--fs/ceph/mds_client.c85
-rw-r--r--fs/ceph/strings.c1
-rw-r--r--fs/ceph/super.c60
-rw-r--r--fs/ceph/super.h4
-rw-r--r--fs/ceph/xattr.c39
-rw-r--r--fs/cifs/cifs_dfs_ref.c2
-rw-r--r--fs/cifs/cifsencrypt.c6
-rw-r--r--fs/cifs/cifsfs.c14
-rw-r--r--fs/cifs/cifssmb.c4
-rw-r--r--fs/cifs/connect.c19
-rw-r--r--fs/cifs/dir.c8
-rw-r--r--fs/cifs/file.c142
-rw-r--r--fs/cifs/inode.c34
-rw-r--r--fs/cifs/link.c12
-rw-r--r--fs/cifs/misc.c2
-rw-r--r--fs/cifs/readdir.c4
-rw-r--r--fs/cifs/smb1ops.c2
-rw-r--r--fs/cifs/smb2file.c4
-rw-r--r--fs/cifs/smb2misc.c6
-rw-r--r--fs/cifs/smb2ops.c13
-rw-r--r--fs/cifs/smb2pdu.c17
-rw-r--r--fs/cifs/xattr.c22
-rw-r--r--fs/coda/cache.c4
-rw-r--r--fs/coda/dir.c22
-rw-r--r--fs/coda/file.c38
-rw-r--r--fs/coda/inode.c6
-rw-r--r--fs/coda/pioctl.c2
-rw-r--r--fs/coda/upcall.c4
-rw-r--r--fs/compat_ioctl.c2
-rw-r--r--fs/configfs/dir.c70
-rw-r--r--fs/configfs/file.c4
-rw-r--r--fs/configfs/inode.c16
-rw-r--r--fs/configfs/mount.c2
-rw-r--r--fs/coredump.c2
-rw-r--r--fs/dax.c48
-rw-r--r--fs/dcache.c49
-rw-r--r--fs/debugfs/file.c2
-rw-r--r--fs/debugfs/inode.c61
-rw-r--r--fs/devpts/inode.c16
-rw-r--r--fs/direct-io.c51
-rw-r--r--fs/ecryptfs/crypto.c4
-rw-r--r--fs/ecryptfs/dentry.c6
-rw-r--r--fs/ecryptfs/file.c11
-rw-r--r--fs/ecryptfs/inode.c164
-rw-r--r--fs/ecryptfs/kthread.c2
-rw-r--r--fs/ecryptfs/main.c6
-rw-r--r--fs/ecryptfs/mmap.c2
-rw-r--r--fs/efivarfs/inode.c4
-rw-r--r--fs/efivarfs/super.c4
-rw-r--r--fs/efs/namei.c4
-rw-r--r--fs/exec.c91
-rw-r--r--fs/exofs/dir.c4
-rw-r--r--fs/exofs/file.c2
-rw-r--r--fs/exofs/inode.c6
-rw-r--r--fs/exofs/namei.c10
-rw-r--r--fs/exofs/super.c2
-rw-r--r--fs/exofs/symlink.c2
-rw-r--r--fs/ext2/dir.c2
-rw-r--r--fs/ext2/ext2.h1
-rw-r--r--fs/ext2/file.c21
-rw-r--r--fs/ext2/ialloc.c2
-rw-r--r--fs/ext2/inode.c20
-rw-r--r--fs/ext2/namei.c24
-rw-r--r--fs/ext2/symlink.c2
-rw-r--r--fs/ext2/xattr.c4
-rw-r--r--fs/ext2/xattr_security.c4
-rw-r--r--fs/ext2/xattr_trusted.c4
-rw-r--r--fs/ext2/xattr_user.c4
-rw-r--r--fs/ext3/file.c2
-rw-r--r--fs/ext3/ialloc.c2
-rw-r--r--fs/ext3/inode.c18
-rw-r--r--fs/ext3/namei.c34
-rw-r--r--fs/ext3/super.c8
-rw-r--r--fs/ext3/symlink.c2
-rw-r--r--fs/ext3/xattr.c13
-rw-r--r--fs/ext3/xattr_security.c4
-rw-r--r--fs/ext3/xattr_trusted.c4
-rw-r--r--fs/ext3/xattr_user.c4
-rw-r--r--fs/ext4/Kconfig22
-rw-r--r--fs/ext4/Makefile4
-rw-r--r--fs/ext4/acl.c5
-rw-r--r--fs/ext4/balloc.c3
-rw-r--r--fs/ext4/bitmap.c1
-rw-r--r--fs/ext4/block_validity.c1
-rw-r--r--fs/ext4/crypto.c558
-rw-r--r--fs/ext4/crypto_fname.c719
-rw-r--r--fs/ext4/crypto_key.c166
-rw-r--r--fs/ext4/crypto_policy.c198
-rw-r--r--fs/ext4/dir.c81
-rw-r--r--fs/ext4/ext4.h185
-rw-r--r--fs/ext4/ext4_crypto.h156
-rw-r--r--fs/ext4/ext4_jbd2.c6
-rw-r--r--fs/ext4/extents.c106
-rw-r--r--fs/ext4/extents_status.c10
-rw-r--r--fs/ext4/file.c77
-rw-r--r--fs/ext4/fsync.c3
-rw-r--r--fs/ext4/hash.c1
-rw-r--r--fs/ext4/ialloc.c30
-rw-r--r--fs/ext4/indirect.c33
-rw-r--r--fs/ext4/inline.c20
-rw-r--r--fs/ext4/inode.c176
-rw-r--r--fs/ext4/ioctl.c86
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/namei.c621
-rw-r--r--fs/ext4/page-io.c48
-rw-r--r--fs/ext4/readpage.c328
-rw-r--r--fs/ext4/resize.c7
-rw-r--r--fs/ext4/super.c66
-rw-r--r--fs/ext4/symlink.c99
-rw-r--r--fs/ext4/xattr.c14
-rw-r--r--fs/ext4/xattr.h3
-rw-r--r--fs/ext4/xattr_security.c4
-rw-r--r--fs/ext4/xattr_trusted.c4
-rw-r--r--fs/ext4/xattr_user.c4
-rw-r--r--fs/f2fs/Kconfig2
-rw-r--r--fs/f2fs/acl.c14
-rw-r--r--fs/f2fs/checkpoint.c38
-rw-r--r--fs/f2fs/data.c759
-rw-r--r--fs/f2fs/debug.c22
-rw-r--r--fs/f2fs/dir.c93
-rw-r--r--fs/f2fs/f2fs.h175
-rw-r--r--fs/f2fs/file.c70
-rw-r--r--fs/f2fs/gc.c6
-rw-r--r--fs/f2fs/inline.c69
-rw-r--r--fs/f2fs/inode.c25
-rw-r--r--fs/f2fs/namei.c97
-rw-r--r--fs/f2fs/node.c18
-rw-r--r--fs/f2fs/node.h1
-rw-r--r--fs/f2fs/recovery.c76
-rw-r--r--fs/f2fs/segment.c17
-rw-r--r--fs/f2fs/segment.h3
-rw-r--r--fs/f2fs/super.c39
-rw-r--r--fs/f2fs/xattr.c14
-rw-r--r--fs/fat/cache.c2
-rw-r--r--fs/fat/dir.c4
-rw-r--r--fs/fat/fat.h5
-rw-r--r--fs/fat/fatent.c3
-rw-r--r--fs/fat/file.c10
-rw-r--r--fs/fat/inode.c23
-rw-r--r--fs/fat/misc.c4
-rw-r--r--fs/fat/namei_msdos.c10
-rw-r--r--fs/fat/namei_vfat.c16
-rw-r--r--fs/fat/nfs.c4
-rw-r--r--fs/file.c3
-rw-r--r--fs/file_table.c4
-rw-r--r--fs/freevxfs/vxfs_immed.c2
-rw-r--r--fs/fs-writeback.c93
-rw-r--r--fs/fs_pin.c4
-rw-r--r--fs/fuse/control.c6
-rw-r--r--fs/fuse/cuse.c27
-rw-r--r--fs/fuse/dev.c64
-rw-r--r--fs/fuse/dir.c60
-rw-r--r--fs/fuse/file.c151
-rw-r--r--fs/fuse/fuse_i.h1
-rw-r--r--fs/fuse/inode.c4
-rw-r--r--fs/gfs2/acl.c6
-rw-r--r--fs/gfs2/aops.c24
-rw-r--r--fs/gfs2/bmap.c2
-rw-r--r--fs/gfs2/dentry.c12
-rw-r--r--fs/gfs2/export.c8
-rw-r--r--fs/gfs2/file.c108
-rw-r--r--fs/gfs2/glock.c47
-rw-r--r--fs/gfs2/incore.h4
-rw-r--r--fs/gfs2/inode.c52
-rw-r--r--fs/gfs2/ops_fstype.c8
-rw-r--r--fs/gfs2/quota.c90
-rw-r--r--fs/gfs2/quota.h8
-rw-r--r--fs/gfs2/rgrp.c20
-rw-r--r--fs/gfs2/rgrp.h3
-rw-r--r--fs/gfs2/super.c2
-rw-r--r--fs/gfs2/xattr.c8
-rw-r--r--fs/hfs/attr.c6
-rw-r--r--fs/hfs/dir.c12
-rw-r--r--fs/hfs/inode.c14
-rw-r--r--fs/hfs/sysdep.c2
-rw-r--r--fs/hfsplus/bfind.c4
-rw-r--r--fs/hfsplus/brec.c20
-rw-r--r--fs/hfsplus/catalog.c3
-rw-r--r--fs/hfsplus/dir.c16
-rw-r--r--fs/hfsplus/inode.c21
-rw-r--r--fs/hfsplus/ioctl.c14
-rw-r--r--fs/hfsplus/xattr.c90
-rw-r--r--fs/hfsplus/xattr.h22
-rw-r--r--fs/hfsplus/xattr_security.c38
-rw-r--r--fs/hfsplus/xattr_trusted.c37
-rw-r--r--fs/hfsplus/xattr_user.c35
-rw-r--r--fs/hostfs/hostfs.h6
-rw-r--r--fs/hostfs/hostfs_kern.c116
-rw-r--r--fs/hostfs/hostfs_user.c29
-rw-r--r--fs/hpfs/file.c2
-rw-r--r--fs/hpfs/inode.c2
-rw-r--r--fs/hpfs/namei.c8
-rw-r--r--fs/hppfs/hppfs.c20
-rw-r--r--fs/hugetlbfs/inode.c187
-rw-r--r--fs/inode.c20
-rw-r--r--fs/isofs/export.c2
-rw-r--r--fs/jbd2/recovery.c10
-rw-r--r--fs/jbd2/revoke.c18
-rw-r--r--fs/jbd2/transaction.c25
-rw-r--r--fs/jffs2/dir.c40
-rw-r--r--fs/jffs2/file.c2
-rw-r--r--fs/jffs2/fs.c2
-rw-r--r--fs/jffs2/security.c4
-rw-r--r--fs/jffs2/super.c4
-rw-r--r--fs/jffs2/symlink.c2
-rw-r--r--fs/jffs2/xattr.c5
-rw-r--r--fs/jffs2/xattr_trusted.c4
-rw-r--r--fs/jffs2/xattr_user.c4
-rw-r--r--fs/jfs/file.c4
-rw-r--r--fs/jfs/inode.c10
-rw-r--r--fs/jfs/jfs_metapage.c31
-rw-r--r--fs/jfs/jfs_metapage.h1
-rw-r--r--fs/jfs/namei.c18
-rw-r--r--fs/jfs/super.c2
-rw-r--r--fs/jfs/symlink.c2
-rw-r--r--fs/jfs/xattr.c12
-rw-r--r--fs/kernfs/dir.c11
-rw-r--r--fs/kernfs/inode.c8
-rw-r--r--fs/libfs.c26
-rw-r--r--fs/lockd/svcsubs.c2
-rw-r--r--fs/locks.c99
-rw-r--r--fs/logfs/dir.c14
-rw-r--r--fs/logfs/file.c4
-rw-r--r--fs/minix/dir.c4
-rw-r--r--fs/minix/file.c4
-rw-r--r--fs/minix/inode.c4
-rw-r--r--fs/minix/namei.c10
-rw-r--r--fs/namei.c202
-rw-r--r--fs/namespace.c148
-rw-r--r--fs/ncpfs/dir.c48
-rw-r--r--fs/ncpfs/file.c88
-rw-r--r--fs/ncpfs/inode.c6
-rw-r--r--fs/ncpfs/ioctl.c8
-rw-r--r--fs/ncpfs/ncplib_kernel.c8
-rw-r--r--fs/ncpfs/ncplib_kernel.h2
-rw-r--r--fs/ncpfs/symlink.c2
-rw-r--r--fs/nfs/Kconfig2
-rw-r--r--fs/nfs/Makefile2
-rw-r--r--fs/nfs/blocklayout/blocklayout.c1
-rw-r--r--fs/nfs/blocklayout/dev.c2
-rw-r--r--fs/nfs/callback.c6
-rw-r--r--fs/nfs/client.c1
-rw-r--r--fs/nfs/delegation.c4
-rw-r--r--fs/nfs/dir.c63
-rw-r--r--fs/nfs/direct.c93
-rw-r--r--fs/nfs/file.c21
-rw-r--r--fs/nfs/filelayout/filelayout.c10
-rw-r--r--fs/nfs/filelayout/filelayoutdev.c2
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c12
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c2
-rw-r--r--fs/nfs/getroot.c4
-rw-r--r--fs/nfs/inode.c54
-rw-r--r--fs/nfs/namespace.c10
-rw-r--r--fs/nfs/nfs3acl.c2
-rw-r--r--fs/nfs/nfs3proc.c12
-rw-r--r--fs/nfs/nfs42proc.c31
-rw-r--r--fs/nfs/nfs42xdr.c20
-rw-r--r--fs/nfs/nfs4client.c4
-rw-r--r--fs/nfs/nfs4file.c26
-rw-r--r--fs/nfs/nfs4idmap.c (renamed from fs/nfs/idmap.c)2
-rw-r--r--fs/nfs/nfs4idmap.h68
-rw-r--r--fs/nfs/nfs4namespace.c4
-rw-r--r--fs/nfs/nfs4proc.c86
-rw-r--r--fs/nfs/nfs4state.c6
-rw-r--r--fs/nfs/nfs4super.c7
-rw-r--r--fs/nfs/nfs4sysctl.c2
-rw-r--r--fs/nfs/nfs4trace.h4
-rw-r--r--fs/nfs/nfs4xdr.c22
-rw-r--r--fs/nfs/nfstrace.c3
-rw-r--r--fs/nfs/objlayout/objio_osd.c4
-rw-r--r--fs/nfs/pagelist.c2
-rw-r--r--fs/nfs/pnfs.c68
-rw-r--r--fs/nfs/pnfs.h28
-rw-r--r--fs/nfs/pnfs_dev.c21
-rw-r--r--fs/nfs/pnfs_nfs.c12
-rw-r--r--fs/nfs/proc.c4
-rw-r--r--fs/nfs/read.c10
-rw-r--r--fs/nfs/super.c10
-rw-r--r--fs/nfs/symlink.c2
-rw-r--r--fs/nfs/unlink.c20
-rw-r--r--fs/nfs/write.c31
-rw-r--r--fs/nfsd/Kconfig3
-rw-r--r--fs/nfsd/blocklayout.c13
-rw-r--r--fs/nfsd/blocklayoutxdr.c6
-rw-r--r--fs/nfsd/export.c8
-rw-r--r--fs/nfsd/nfs2acl.c8
-rw-r--r--fs/nfsd/nfs3acl.c8
-rw-r--r--fs/nfsd/nfs3proc.c6
-rw-r--r--fs/nfsd/nfs3xdr.c16
-rw-r--r--fs/nfsd/nfs4acl.c54
-rw-r--r--fs/nfsd/nfs4callback.c119
-rw-r--r--fs/nfsd/nfs4layouts.c12
-rw-r--r--fs/nfsd/nfs4proc.c26
-rw-r--r--fs/nfsd/nfs4recover.c22
-rw-r--r--fs/nfsd/nfs4state.c178
-rw-r--r--fs/nfsd/nfs4xdr.c46
-rw-r--r--fs/nfsd/nfscache.c6
-rw-r--r--fs/nfsd/nfsctl.c16
-rw-r--r--fs/nfsd/nfsd.h2
-rw-r--r--fs/nfsd/nfsfh.c20
-rw-r--r--fs/nfsd/nfsfh.h6
-rw-r--r--fs/nfsd/nfsproc.c4
-rw-r--r--fs/nfsd/nfsxdr.c2
-rw-r--r--fs/nfsd/state.h19
-rw-r--r--fs/nfsd/vfs.c62
-rw-r--r--fs/nfsd/xdr4.h6
-rw-r--r--fs/nilfs2/alloc.c5
-rw-r--r--fs/nilfs2/bmap.c48
-rw-r--r--fs/nilfs2/bmap.h13
-rw-r--r--fs/nilfs2/btree.c65
-rw-r--r--fs/nilfs2/cpfile.c58
-rw-r--r--fs/nilfs2/dir.c2
-rw-r--r--fs/nilfs2/direct.c17
-rw-r--r--fs/nilfs2/file.c2
-rw-r--r--fs/nilfs2/inode.c39
-rw-r--r--fs/nilfs2/mdt.c54
-rw-r--r--fs/nilfs2/mdt.h10
-rw-r--r--fs/nilfs2/namei.c18
-rw-r--r--fs/nilfs2/page.c24
-rw-r--r--fs/nilfs2/segment.c17
-rw-r--r--fs/nilfs2/super.c8
-rw-r--r--fs/nsfs.c4
-rw-r--r--fs/ntfs/Makefile2
-rw-r--r--fs/ntfs/file.c778
-rw-r--r--fs/ntfs/inode.c3
-rw-r--r--fs/ntfs/namei.c4
-rw-r--r--fs/ocfs2/alloc.c48
-rw-r--r--fs/ocfs2/aops.c178
-rw-r--r--fs/ocfs2/aops.h2
-rw-r--r--fs/ocfs2/cluster/masklog.h5
-rw-r--r--fs/ocfs2/dcache.c14
-rw-r--r--fs/ocfs2/dir.c15
-rw-r--r--fs/ocfs2/dir.h2
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c13
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c4
-rw-r--r--fs/ocfs2/dlmglue.c5
-rw-r--r--fs/ocfs2/export.c4
-rw-r--r--fs/ocfs2/file.c155
-rw-r--r--fs/ocfs2/inode.c6
-rw-r--r--fs/ocfs2/localalloc.c4
-rw-r--r--fs/ocfs2/namei.c20
-rw-r--r--fs/ocfs2/refcounttree.c12
-rw-r--r--fs/ocfs2/slot_map.c4
-rw-r--r--fs/ocfs2/stack_o2cb.c2
-rw-r--r--fs/ocfs2/stack_user.c8
-rw-r--r--fs/ocfs2/suballoc.c2
-rw-r--r--fs/ocfs2/super.c37
-rw-r--r--fs/ocfs2/xattr.c30
-rw-r--r--fs/omfs/dir.c10
-rw-r--r--fs/omfs/file.c4
-rw-r--r--fs/open.c17
-rw-r--r--fs/pipe.c5
-rw-r--r--fs/pnode.c60
-rw-r--r--fs/pnode.h7
-rw-r--r--fs/posix_acl.c8
-rw-r--r--fs/proc/array.c26
-rw-r--r--fs/proc/base.c114
-rw-r--r--fs/proc/fd.c33
-rw-r--r--fs/proc/generic.c4
-rw-r--r--fs/proc/inode.c2
-rw-r--r--fs/proc/namespaces.c4
-rw-r--r--fs/proc/proc_net.c2
-rw-r--r--fs/proc/proc_sysctl.c12
-rw-r--r--fs/proc/root.c2
-rw-r--r--fs/proc/self.c2
-rw-r--r--fs/proc/thread_self.c2
-rw-r--r--fs/pstore/inode.c13
-rw-r--r--fs/pstore/ram.c3
-rw-r--r--fs/qnx6/inode.c2
-rw-r--r--fs/quota/dquot.c161
-rw-r--r--fs/quota/quota.c217
-rw-r--r--fs/quota/quota_tree.c7
-rw-r--r--fs/quota/quota_v2.c12
-rw-r--r--fs/quota/quotaio_v2.h6
-rw-r--r--fs/ramfs/file-mmu.c2
-rw-r--r--fs/ramfs/file-nommu.c4
-rw-r--r--fs/read_write.c213
-rw-r--r--fs/reiserfs/dir.c4
-rw-r--r--fs/reiserfs/file.c2
-rw-r--r--fs/reiserfs/inode.c12
-rw-r--r--fs/reiserfs/namei.c12
-rw-r--r--fs/reiserfs/reiserfs.h1
-rw-r--r--fs/reiserfs/super.c6
-rw-r--r--fs/reiserfs/xattr.c126
-rw-r--r--fs/reiserfs/xattr.h2
-rw-r--r--fs/reiserfs/xattr_security.c10
-rw-r--r--fs/reiserfs/xattr_trusted.c10
-rw-r--r--fs/reiserfs/xattr_user.c4
-rw-r--r--fs/romfs/mmap-nommu.c1
-rw-r--r--fs/splice.c43
-rw-r--r--fs/squashfs/export.c2
-rw-r--r--fs/squashfs/xattr.c8
-rw-r--r--fs/stat.c6
-rw-r--r--fs/super.c2
-rw-r--r--fs/sysfs/group.c11
-rw-r--r--fs/sysv/dir.c4
-rw-r--r--fs/sysv/file.c4
-rw-r--r--fs/sysv/itree.c2
-rw-r--r--fs/sysv/namei.c10
-rw-r--r--fs/sysv/symlink.c2
-rw-r--r--fs/tracefs/Makefile4
-rw-r--r--fs/tracefs/inode.c650
-rw-r--r--fs/ubifs/budget.c2
-rw-r--r--fs/ubifs/commit.c12
-rw-r--r--fs/ubifs/compress.c22
-rw-r--r--fs/ubifs/debug.c186
-rw-r--r--fs/ubifs/dir.c37
-rw-r--r--fs/ubifs/file.c24
-rw-r--r--fs/ubifs/io.c40
-rw-r--r--fs/ubifs/ioctl.c2
-rw-r--r--fs/ubifs/journal.c21
-rw-r--r--fs/ubifs/log.c4
-rw-r--r--fs/ubifs/lprops.c62
-rw-r--r--fs/ubifs/lpt.c59
-rw-r--r--fs/ubifs/lpt_commit.c34
-rw-r--r--fs/ubifs/master.c6
-rw-r--r--fs/ubifs/orphan.c26
-rw-r--r--fs/ubifs/recovery.c44
-rw-r--r--fs/ubifs/replay.c34
-rw-r--r--fs/ubifs/sb.c30
-rw-r--r--fs/ubifs/scan.c24
-rw-r--r--fs/ubifs/super.c107
-rw-r--r--fs/ubifs/tnc.c20
-rw-r--r--fs/ubifs/tnc_commit.c12
-rw-r--r--fs/ubifs/tnc_misc.c24
-rw-r--r--fs/ubifs/ubifs.h40
-rw-r--r--fs/ubifs/xattr.c28
-rw-r--r--fs/udf/balloc.c20
-rw-r--r--fs/udf/dir.c1
-rw-r--r--fs/udf/directory.c1
-rw-r--r--fs/udf/file.c32
-rw-r--r--fs/udf/inode.c12
-rw-r--r--fs/udf/misc.c1
-rw-r--r--fs/udf/namei.c26
-rw-r--r--fs/udf/partition.c1
-rw-r--r--fs/udf/super.c1
-rw-r--r--fs/udf/symlink.c1
-rw-r--r--fs/udf/truncate.c1
-rw-r--r--fs/ufs/dir.c2
-rw-r--r--fs/ufs/file.c2
-rw-r--r--fs/ufs/namei.c10
-rw-r--r--fs/ufs/super.c4
-rw-r--r--fs/ufs/symlink.c2
-rw-r--r--fs/ufs/truncate.c2
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c104
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c150
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h6
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c554
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h13
-rw-r--r--fs/xfs/libxfs/xfs_btree.c24
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c8
-rw-r--r--fs/xfs/libxfs/xfs_da_format.h14
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c39
-rw-r--r--fs/xfs/libxfs/xfs_format.h62
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c48
-rw-r--r--fs/xfs/libxfs/xfs_sb.c20
-rw-r--r--fs/xfs/xfs_aops.c283
-rw-r--r--fs/xfs/xfs_attr_inactive.c3
-rw-r--r--fs/xfs/xfs_attr_list.c9
-rw-r--r--fs/xfs/xfs_bmap_util.c164
-rw-r--r--fs/xfs/xfs_bmap_util.h2
-rw-r--r--fs/xfs/xfs_buf_item.c4
-rw-r--r--fs/xfs/xfs_discard.c2
-rw-r--r--fs/xfs/xfs_error.c2
-rw-r--r--fs/xfs/xfs_error.h8
-rw-r--r--fs/xfs/xfs_export.c2
-rw-r--r--fs/xfs/xfs_file.c203
-rw-r--r--fs/xfs/xfs_filestream.c4
-rw-r--r--fs/xfs/xfs_fsops.c20
-rw-r--r--fs/xfs/xfs_icache.c4
-rw-r--r--fs/xfs/xfs_inode.c558
-rw-r--r--fs/xfs/xfs_inode.h49
-rw-r--r--fs/xfs/xfs_ioctl.c25
-rw-r--r--fs/xfs/xfs_ioctl32.c12
-rw-r--r--fs/xfs/xfs_iomap.c3
-rw-r--r--fs/xfs/xfs_iops.c109
-rw-r--r--fs/xfs/xfs_iops.h2
-rw-r--r--fs/xfs/xfs_itable.c2
-rw-r--r--fs/xfs/xfs_linux.h9
-rw-r--r--fs/xfs/xfs_log_recover.c4
-rw-r--r--fs/xfs/xfs_mount.c918
-rw-r--r--fs/xfs/xfs_mount.h95
-rw-r--r--fs/xfs/xfs_mru_cache.c2
-rw-r--r--fs/xfs/xfs_pnfs.c7
-rw-r--r--fs/xfs/xfs_pnfs.h5
-rw-r--r--fs/xfs/xfs_qm.c13
-rw-r--r--fs/xfs/xfs_qm.h4
-rw-r--r--fs/xfs/xfs_qm_syscalls.c176
-rw-r--r--fs/xfs/xfs_quotaops.c117
-rw-r--r--fs/xfs/xfs_super.c134
-rw-r--r--fs/xfs/xfs_super.h2
-rw-r--r--fs/xfs/xfs_symlink.c58
-rw-r--r--fs/xfs/xfs_trace.h29
-rw-r--r--fs/xfs/xfs_trans.c234
-rw-r--r--fs/xfs/xfs_xattr.c6
566 files changed, 13488 insertions, 8268 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 8482f2d11606..31c010372660 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -247,7 +247,7 @@ static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name,
if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
return v9fs_remote_get_acl(dentry, name, buffer, size, type);
- acl = v9fs_get_cached_acl(dentry->d_inode, type);
+ acl = v9fs_get_cached_acl(d_inode(dentry), type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -285,7 +285,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
int retval;
struct posix_acl *acl;
struct v9fs_session_info *v9ses;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
if (strcmp(name, "") != 0)
return -EINVAL;
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 099c7712631c..fb9ffcb43277 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -78,7 +78,6 @@ enum p9_cache_modes {
* @cache: cache mode of type &p9_cache_modes
* @cachetag: the tag of the cache associated with this session
* @fscache: session cookie associated with FS-Cache
- * @options: copy of options string given by user
* @uname: string user name to mount hierarchy as
* @aname: mount specifier for remote hierarchy
* @maxdata: maximum data to be sent/recvd per protocol message
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index b83ebfbf3fdc..5a0db6dec8d1 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -68,14 +68,10 @@ int v9fs_file_open(struct inode *inode, struct file *file);
void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
int v9fs_uflags2omode(int uflags, int extended);
-ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64);
-ssize_t v9fs_fid_readn(struct p9_fid *, char *, char __user *, u32, u64);
void v9fs_blank_wstat(struct p9_wstat *wstat);
int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *);
int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
int datasync);
-ssize_t v9fs_file_write_internal(struct inode *, struct p9_fid *,
- const char __user *, size_t, loff_t *, int);
int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode);
static inline void v9fs_invalidate_inode_attr(struct inode *inode)
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index eb14e055ea83..e9e04376c52c 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -33,7 +33,7 @@
#include <linux/pagemap.h>
#include <linux/idr.h>
#include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
@@ -51,12 +51,11 @@
*/
static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
{
- int retval;
- loff_t offset;
- char *buffer;
- struct inode *inode;
+ struct inode *inode = page->mapping->host;
+ struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE};
+ struct iov_iter to;
+ int retval, err;
- inode = page->mapping->host;
p9_debug(P9_DEBUG_VFS, "\n");
BUG_ON(!PageLocked(page));
@@ -65,16 +64,16 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
if (retval == 0)
return retval;
- buffer = kmap(page);
- offset = page_offset(page);
+ iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE);
- retval = v9fs_fid_readn(fid, buffer, NULL, PAGE_CACHE_SIZE, offset);
- if (retval < 0) {
+ retval = p9_client_read(fid, page_offset(page), &to, &err);
+ if (err) {
v9fs_uncache_page(inode, page);
+ retval = err;
goto done;
}
- memset(buffer + retval, 0, PAGE_CACHE_SIZE - retval);
+ zero_user(page, retval, PAGE_SIZE - retval);
flush_dcache_page(page);
SetPageUptodate(page);
@@ -82,7 +81,6 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
retval = 0;
done:
- kunmap(page);
unlock_page(page);
return retval;
}
@@ -161,41 +159,32 @@ static void v9fs_invalidate_page(struct page *page, unsigned int offset,
static int v9fs_vfs_writepage_locked(struct page *page)
{
- char *buffer;
- int retval, len;
- loff_t offset, size;
- mm_segment_t old_fs;
- struct v9fs_inode *v9inode;
struct inode *inode = page->mapping->host;
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ loff_t size = i_size_read(inode);
+ struct iov_iter from;
+ struct bio_vec bvec;
+ int err, len;
- v9inode = V9FS_I(inode);
- size = i_size_read(inode);
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
- set_page_writeback(page);
-
- buffer = kmap(page);
- offset = page_offset(page);
+ bvec.bv_page = page;
+ bvec.bv_offset = 0;
+ bvec.bv_len = len;
+ iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len);
- old_fs = get_fs();
- set_fs(get_ds());
/* We should have writeback_fid always set */
BUG_ON(!v9inode->writeback_fid);
- retval = v9fs_file_write_internal(inode,
- v9inode->writeback_fid,
- (__force const char __user *)buffer,
- len, &offset, 0);
- if (retval > 0)
- retval = 0;
+ set_page_writeback(page);
+
+ p9_client_write(v9inode->writeback_fid, page_offset(page), &from, &err);
- set_fs(old_fs);
- kunmap(page);
end_page_writeback(page);
- return retval;
+ return err;
}
static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -241,11 +230,8 @@ static int v9fs_launder_page(struct page *page)
/**
* v9fs_direct_IO - 9P address space operation for direct I/O
- * @rw: direction (read or write)
* @iocb: target I/O control block
- * @iov: array of vectors that define I/O buffer
* @pos: offset in file to begin the operation
- * @nr_segs: size of iovec array
*
* The presence of v9fs_direct_IO() in the address space ops vector
* allowes open() O_DIRECT flags which would have failed otherwise.
@@ -259,18 +245,23 @@ static int v9fs_launder_page(struct page *page)
*
*/
static ssize_t
-v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
{
- /*
- * FIXME
- * Now that we do caching with cache mode enabled, We need
- * to support direct IO
- */
- p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%pD) off/no(%lld/%lu) EINVAL\n",
- iocb->ki_filp,
- (long long)pos, iter->nr_segs);
-
- return -EINVAL;
+ struct file *file = iocb->ki_filp;
+ ssize_t n;
+ int err = 0;
+ if (iov_iter_rw(iter) == WRITE) {
+ n = p9_client_write(file->private_data, pos, iter, &err);
+ if (n) {
+ struct inode *inode = file_inode(file);
+ loff_t i_size = i_size_read(inode);
+ if (pos + n > i_size)
+ inode_add_bytes(inode, pos + n - i_size);
+ }
+ } else {
+ n = p9_client_read(file->private_data, pos, iter, &err);
+ }
+ return n ? n : err;
}
static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index a345b2d659cc..bd456c668d39 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -53,7 +53,7 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
dentry, dentry);
/* Don't cache negative dentries */
- if (!dentry->d_inode)
+ if (d_really_is_negative(dentry))
return 1;
return 0;
}
@@ -83,7 +83,7 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
if (flags & LOOKUP_RCU)
return -ECHILD;
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
if (!inode)
goto out_valid;
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 4f1151088ebe..5cc00e56206e 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -33,6 +33,7 @@
#include <linux/inet.h>
#include <linux/idr.h>
#include <linux/slab.h>
+#include <linux/uio.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
@@ -115,6 +116,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
int buflen;
int reclen = 0;
struct p9_rdir *rdir;
+ struct kvec kvec;
p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
fid = file->private_data;
@@ -124,16 +126,23 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
rdir = v9fs_alloc_rdir_buf(file, buflen);
if (!rdir)
return -ENOMEM;
+ kvec.iov_base = rdir->buf;
+ kvec.iov_len = buflen;
while (1) {
if (rdir->tail == rdir->head) {
- err = v9fs_file_readn(file, rdir->buf, NULL,
- buflen, ctx->pos);
- if (err <= 0)
+ struct iov_iter to;
+ int n;
+ iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen);
+ n = p9_client_read(file->private_data, ctx->pos, &to,
+ &err);
+ if (err)
return err;
+ if (n == 0)
+ return 0;
rdir->head = 0;
- rdir->tail = err;
+ rdir->tail = n;
}
while (rdir->head < rdir->tail) {
p9stat_init(&st);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index b40133796b87..1ef16bd8280b 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -36,6 +36,8 @@
#include <linux/utsname.h>
#include <asm/uaccess.h>
#include <linux/idr.h>
+#include <linux/uio.h>
+#include <linux/slab.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
@@ -149,7 +151,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct p9_flock flock;
struct p9_fid *fid;
- uint8_t status;
+ uint8_t status = P9_LOCK_ERROR;
int res = 0;
unsigned char fl_type;
@@ -194,7 +196,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
for (;;) {
res = p9_client_lock_dotl(fid, &flock, &status);
if (res < 0)
- break;
+ goto out_unlock;
if (status != P9_LOCK_BLOCKED)
break;
@@ -212,14 +214,16 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
case P9_LOCK_BLOCKED:
res = -EAGAIN;
break;
+ default:
+ WARN_ONCE(1, "unknown lock status code: %d\n", status);
+ /* fallthough */
case P9_LOCK_ERROR:
case P9_LOCK_GRACE:
res = -ENOLCK;
break;
- default:
- BUG();
}
+out_unlock:
/*
* incase server returned error for lock request, revert
* it locally
@@ -285,6 +289,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
fl->fl_end = glock.start + glock.length - 1;
fl->fl_pid = glock.proc_id;
}
+ kfree(glock.client_id);
return res;
}
@@ -364,63 +369,6 @@ out_err:
}
/**
- * v9fs_fid_readn - read from a fid
- * @fid: fid to read
- * @data: data buffer to read data into
- * @udata: user data buffer to read data into
- * @count: size of buffer
- * @offset: offset at which to read data
- *
- */
-ssize_t
-v9fs_fid_readn(struct p9_fid *fid, char *data, char __user *udata, u32 count,
- u64 offset)
-{
- int n, total, size;
-
- p9_debug(P9_DEBUG_VFS, "fid %d offset %llu count %d\n",
- fid->fid, (long long unsigned)offset, count);
- n = 0;
- total = 0;
- size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
- do {
- n = p9_client_read(fid, data, udata, offset, count);
- if (n <= 0)
- break;
-
- if (data)
- data += n;
- if (udata)
- udata += n;
-
- offset += n;
- count -= n;
- total += n;
- } while (count > 0 && n == size);
-
- if (n < 0)
- total = n;
-
- return total;
-}
-
-/**
- * v9fs_file_readn - read from a file
- * @filp: file pointer to read
- * @data: data buffer to read data into
- * @udata: user data buffer to read data into
- * @count: size of buffer
- * @offset: offset at which to read data
- *
- */
-ssize_t
-v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
- u64 offset)
-{
- return v9fs_fid_readn(filp->private_data, data, udata, count, offset);
-}
-
-/**
* v9fs_file_read - read from a file
* @filp: file pointer to read
* @udata: user data buffer to read data into
@@ -430,69 +378,22 @@ v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
*/
static ssize_t
-v9fs_file_read(struct file *filp, char __user *udata, size_t count,
- loff_t * offset)
+v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
- int ret;
- struct p9_fid *fid;
- size_t size;
-
- p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", count, *offset);
- fid = filp->private_data;
+ struct p9_fid *fid = iocb->ki_filp->private_data;
+ int ret, err;
- size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
- if (count > size)
- ret = v9fs_file_readn(filp, NULL, udata, count, *offset);
- else
- ret = p9_client_read(fid, NULL, udata, *offset, count);
+ p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n",
+ iov_iter_count(to), iocb->ki_pos);
- if (ret > 0)
- *offset += ret;
+ ret = p9_client_read(fid, iocb->ki_pos, to, &err);
+ if (!ret)
+ return err;
+ iocb->ki_pos += ret;
return ret;
}
-ssize_t
-v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid,
- const char __user *data, size_t count,
- loff_t *offset, int invalidate)
-{
- int n;
- loff_t i_size;
- size_t total = 0;
- loff_t origin = *offset;
- unsigned long pg_start, pg_end;
-
- p9_debug(P9_DEBUG_VFS, "data %p count %d offset %x\n",
- data, (int)count, (int)*offset);
-
- do {
- n = p9_client_write(fid, NULL, data+total, origin+total, count);
- if (n <= 0)
- break;
- count -= n;
- total += n;
- } while (count > 0);
-
- if (invalidate && (total > 0)) {
- pg_start = origin >> PAGE_CACHE_SHIFT;
- pg_end = (origin + total - 1) >> PAGE_CACHE_SHIFT;
- if (inode->i_mapping && inode->i_mapping->nrpages)
- invalidate_inode_pages2_range(inode->i_mapping,
- pg_start, pg_end);
- *offset += total;
- i_size = i_size_read(inode);
- if (*offset > i_size) {
- inode_add_bytes(inode, *offset - i_size);
- i_size_write(inode, *offset);
- }
- }
- if (n < 0)
- return n;
-
- return total;
-}
-
/**
* v9fs_file_write - write to a file
* @filp: file pointer to write
@@ -502,35 +403,39 @@ v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid,
*
*/
static ssize_t
-v9fs_file_write(struct file *filp, const char __user * data,
- size_t count, loff_t *offset)
+v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- ssize_t retval = 0;
- loff_t origin = *offset;
-
-
- retval = generic_write_checks(filp, &origin, &count, 0);
- if (retval)
- goto out;
+ struct file *file = iocb->ki_filp;
+ ssize_t retval;
+ loff_t origin;
+ int err = 0;
- retval = -EINVAL;
- if ((ssize_t) count < 0)
- goto out;
- retval = 0;
- if (!count)
- goto out;
+ retval = generic_write_checks(iocb, from);
+ if (retval <= 0)
+ return retval;
- retval = v9fs_file_write_internal(file_inode(filp),
- filp->private_data,
- data, count, &origin, 1);
- /* update offset on successful write */
- if (retval > 0)
- *offset = origin;
-out:
- return retval;
+ origin = iocb->ki_pos;
+ retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err);
+ if (retval > 0) {
+ struct inode *inode = file_inode(file);
+ loff_t i_size;
+ unsigned long pg_start, pg_end;
+ pg_start = origin >> PAGE_CACHE_SHIFT;
+ pg_end = (origin + retval - 1) >> PAGE_CACHE_SHIFT;
+ if (inode->i_mapping && inode->i_mapping->nrpages)
+ invalidate_inode_pages2_range(inode->i_mapping,
+ pg_start, pg_end);
+ iocb->ki_pos += retval;
+ i_size = i_size_read(inode);
+ if (iocb->ki_pos > i_size) {
+ inode_add_bytes(inode, iocb->ki_pos - i_size);
+ i_size_write(inode, iocb->ki_pos);
+ }
+ return retval;
+ }
+ return err;
}
-
static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
@@ -657,44 +562,6 @@ out_unlock:
return VM_FAULT_NOPAGE;
}
-static ssize_t
-v9fs_direct_read(struct file *filp, char __user *udata, size_t count,
- loff_t *offsetp)
-{
- loff_t size, offset;
- struct inode *inode;
- struct address_space *mapping;
-
- offset = *offsetp;
- mapping = filp->f_mapping;
- inode = mapping->host;
- if (!count)
- return 0;
- size = i_size_read(inode);
- if (offset < size)
- filemap_write_and_wait_range(mapping, offset,
- offset + count - 1);
-
- return v9fs_file_read(filp, udata, count, offsetp);
-}
-
-/**
- * v9fs_cached_file_read - read from a file
- * @filp: file pointer to read
- * @data: user data buffer to read data into
- * @count: size of buffer
- * @offset: offset at which to read data
- *
- */
-static ssize_t
-v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
- loff_t *offset)
-{
- if (filp->f_flags & O_DIRECT)
- return v9fs_direct_read(filp, data, count, offset);
- return new_sync_read(filp, data, count, offset);
-}
-
/**
* v9fs_mmap_file_read - read from a file
* @filp: file pointer to read
@@ -704,84 +571,12 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
*
*/
static ssize_t
-v9fs_mmap_file_read(struct file *filp, char __user *data, size_t count,
- loff_t *offset)
+v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
/* TODO: Check if there are dirty pages */
- return v9fs_file_read(filp, data, count, offset);
-}
-
-static ssize_t
-v9fs_direct_write(struct file *filp, const char __user * data,
- size_t count, loff_t *offsetp)
-{
- loff_t offset;
- ssize_t retval;
- struct inode *inode;
- struct address_space *mapping;
-
- offset = *offsetp;
- mapping = filp->f_mapping;
- inode = mapping->host;
- if (!count)
- return 0;
-
- mutex_lock(&inode->i_mutex);
- retval = filemap_write_and_wait_range(mapping, offset,
- offset + count - 1);
- if (retval)
- goto err_out;
- /*
- * After a write we want buffered reads to be sure to go to disk to get
- * the new data. We invalidate clean cached page from the region we're
- * about to write. We do this *before* the write so that if we fail
- * here we fall back to buffered write
- */
- if (mapping->nrpages) {
- pgoff_t pg_start = offset >> PAGE_CACHE_SHIFT;
- pgoff_t pg_end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
-
- retval = invalidate_inode_pages2_range(mapping,
- pg_start, pg_end);
- /*
- * If a page can not be invalidated, fall back
- * to buffered write.
- */
- if (retval) {
- if (retval == -EBUSY)
- goto buff_write;
- goto err_out;
- }
- }
- retval = v9fs_file_write(filp, data, count, offsetp);
-err_out:
- mutex_unlock(&inode->i_mutex);
- return retval;
-
-buff_write:
- mutex_unlock(&inode->i_mutex);
- return new_sync_write(filp, data, count, offsetp);
-}
-
-/**
- * v9fs_cached_file_write - write to a file
- * @filp: file pointer to write
- * @data: data buffer to write data from
- * @count: size of buffer
- * @offset: offset at which to write data
- *
- */
-static ssize_t
-v9fs_cached_file_write(struct file *filp, const char __user * data,
- size_t count, loff_t *offset)
-{
-
- if (filp->f_flags & O_DIRECT)
- return v9fs_direct_write(filp, data, count, offset);
- return new_sync_write(filp, data, count, offset);
+ return v9fs_file_read_iter(iocb, to);
}
-
/**
* v9fs_mmap_file_write - write to a file
* @filp: file pointer to write
@@ -791,14 +586,13 @@ v9fs_cached_file_write(struct file *filp, const char __user * data,
*
*/
static ssize_t
-v9fs_mmap_file_write(struct file *filp, const char __user *data,
- size_t count, loff_t *offset)
+v9fs_mmap_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
/*
* TODO: invalidate mmaps on filp's inode between
* offset and offset+count
*/
- return v9fs_file_write(filp, data, count, offset);
+ return v9fs_file_write_iter(iocb, from);
}
static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
@@ -843,8 +637,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
const struct file_operations v9fs_cached_file_operations = {
.llseek = generic_file_llseek,
- .read = v9fs_cached_file_read,
- .write = v9fs_cached_file_write,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.open = v9fs_file_open,
@@ -856,8 +648,6 @@ const struct file_operations v9fs_cached_file_operations = {
const struct file_operations v9fs_cached_file_operations_dotl = {
.llseek = generic_file_llseek,
- .read = v9fs_cached_file_read,
- .write = v9fs_cached_file_write,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.open = v9fs_file_open,
@@ -870,8 +660,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = {
const struct file_operations v9fs_file_operations = {
.llseek = generic_file_llseek,
- .read = v9fs_file_read,
- .write = v9fs_file_write,
+ .read_iter = v9fs_file_read_iter,
+ .write_iter = v9fs_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
@@ -881,8 +671,8 @@ const struct file_operations v9fs_file_operations = {
const struct file_operations v9fs_file_operations_dotl = {
.llseek = generic_file_llseek,
- .read = v9fs_file_read,
- .write = v9fs_file_write,
+ .read_iter = v9fs_file_read_iter,
+ .write_iter = v9fs_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock_dotl,
@@ -893,8 +683,8 @@ const struct file_operations v9fs_file_operations_dotl = {
const struct file_operations v9fs_mmap_file_operations = {
.llseek = generic_file_llseek,
- .read = v9fs_mmap_file_read,
- .write = v9fs_mmap_file_write,
+ .read_iter = v9fs_mmap_file_read_iter,
+ .write_iter = v9fs_mmap_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
@@ -904,8 +694,8 @@ const struct file_operations v9fs_mmap_file_operations = {
const struct file_operations v9fs_mmap_file_operations_dotl = {
.llseek = generic_file_llseek,
- .read = v9fs_mmap_file_read,
- .write = v9fs_mmap_file_write,
+ .read_iter = v9fs_mmap_file_read_iter,
+ .write_iter = v9fs_mmap_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock_dotl,
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 3662f1d1d9cf..703342e309f5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -595,7 +595,7 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
dir, dentry, flags);
v9ses = v9fs_inode2v9ses(dir);
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
dfid = v9fs_fid_lookup(dentry->d_parent);
if (IS_ERR(dfid)) {
retval = PTR_ERR(dfid);
@@ -864,7 +864,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
}
/* Only creates */
- if (!(flags & O_CREAT) || dentry->d_inode)
+ if (!(flags & O_CREAT) || d_really_is_positive(dentry))
return finish_no_open(file, res);
err = 0;
@@ -881,7 +881,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
}
v9fs_invalidate_inode_attr(dir);
- v9inode = V9FS_I(dentry->d_inode);
+ v9inode = V9FS_I(d_inode(dentry));
mutex_lock(&v9inode->v_mutex);
if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
!v9inode->writeback_fid &&
@@ -908,7 +908,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
file->private_data = fid;
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
- v9fs_cache_inode_set_cookie(dentry->d_inode, file);
+ v9fs_cache_inode_set_cookie(d_inode(dentry), file);
*opened |= FILE_CREATED;
out:
@@ -969,8 +969,8 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
p9_debug(P9_DEBUG_VFS, "\n");
retval = 0;
- old_inode = old_dentry->d_inode;
- new_inode = new_dentry->d_inode;
+ old_inode = d_inode(old_dentry);
+ new_inode = d_inode(new_dentry);
v9ses = v9fs_inode2v9ses(old_inode);
oldfid = v9fs_fid_lookup(old_dentry);
if (IS_ERR(oldfid))
@@ -1061,7 +1061,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
v9ses = v9fs_dentry2v9ses(dentry);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
- generic_fillattr(dentry->d_inode, stat);
+ generic_fillattr(d_inode(dentry), stat);
return 0;
}
fid = v9fs_fid_lookup(dentry);
@@ -1072,8 +1072,8 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
if (IS_ERR(st))
return PTR_ERR(st);
- v9fs_stat2inode(st, dentry->d_inode, dentry->d_inode->i_sb);
- generic_fillattr(dentry->d_inode, stat);
+ v9fs_stat2inode(st, d_inode(dentry), d_inode(dentry)->i_sb);
+ generic_fillattr(d_inode(dentry), stat);
p9stat_free(st);
kfree(st);
@@ -1095,7 +1095,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
struct p9_wstat wstat;
p9_debug(P9_DEBUG_VFS, "\n");
- retval = inode_change_ok(dentry->d_inode, iattr);
+ retval = inode_change_ok(d_inode(dentry), iattr);
if (retval)
return retval;
@@ -1128,20 +1128,20 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
/* Write all dirty data */
if (d_is_reg(dentry))
- filemap_write_and_wait(dentry->d_inode->i_mapping);
+ filemap_write_and_wait(d_inode(dentry)->i_mapping);
retval = p9_client_wstat(fid, &wstat);
if (retval < 0)
return retval;
if ((iattr->ia_valid & ATTR_SIZE) &&
- iattr->ia_size != i_size_read(dentry->d_inode))
- truncate_setsize(dentry->d_inode, iattr->ia_size);
+ iattr->ia_size != i_size_read(d_inode(dentry)))
+ truncate_setsize(d_inode(dentry), iattr->ia_size);
- v9fs_invalidate_inode_attr(dentry->d_inode);
+ v9fs_invalidate_inode_attr(d_inode(dentry));
- setattr_copy(dentry->d_inode, iattr);
- mark_inode_dirty(dentry->d_inode);
+ setattr_copy(d_inode(dentry), iattr);
+ mark_inode_dirty(d_inode(dentry));
return 0;
}
@@ -1403,7 +1403,7 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
retval = v9fs_vfs_mkspecial(dir, dentry, P9_DMLINK, name);
__putname(name);
if (!retval) {
- v9fs_refresh_inode(oldfid, old_dentry->d_inode);
+ v9fs_refresh_inode(oldfid, d_inode(old_dentry));
v9fs_invalidate_inode_attr(dir);
}
clunk_fid:
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 6054c16b8fae..9861c7c951a6 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -265,7 +265,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
}
/* Only creates */
- if (!(flags & O_CREAT) || dentry->d_inode)
+ if (!(flags & O_CREAT) || d_really_is_positive(dentry))
return finish_no_open(file, res);
v9ses = v9fs_inode2v9ses(dir);
@@ -481,7 +481,7 @@ v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
v9ses = v9fs_dentry2v9ses(dentry);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
- generic_fillattr(dentry->d_inode, stat);
+ generic_fillattr(d_inode(dentry), stat);
return 0;
}
fid = v9fs_fid_lookup(dentry);
@@ -496,8 +496,8 @@ v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
if (IS_ERR(st))
return PTR_ERR(st);
- v9fs_stat2inode_dotl(st, dentry->d_inode);
- generic_fillattr(dentry->d_inode, stat);
+ v9fs_stat2inode_dotl(st, d_inode(dentry));
+ generic_fillattr(d_inode(dentry), stat);
/* Change block size to what the server returned */
stat->blksize = st->st_blksize;
@@ -557,7 +557,7 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
int retval;
struct p9_fid *fid;
struct p9_iattr_dotl p9attr;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
p9_debug(P9_DEBUG_VFS, "\n");
@@ -795,10 +795,10 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
if (IS_ERR(fid))
return PTR_ERR(fid);
- v9fs_refresh_inode_dotl(fid, old_dentry->d_inode);
+ v9fs_refresh_inode_dotl(fid, d_inode(old_dentry));
}
- ihold(old_dentry->d_inode);
- d_instantiate(dentry, old_dentry->d_inode);
+ ihold(d_inode(old_dentry));
+ d_instantiate(dentry, d_inode(old_dentry));
return err;
}
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 0afd0382822b..e99a338a4638 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -168,8 +168,8 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
retval = PTR_ERR(st);
goto release_sb;
}
- root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
- v9fs_stat2inode_dotl(st, root->d_inode);
+ d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
+ v9fs_stat2inode_dotl(st, d_inode(root));
kfree(st);
} else {
struct p9_wstat *st = NULL;
@@ -179,8 +179,8 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
goto release_sb;
}
- root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
- v9fs_stat2inode(st, root->d_inode, sb);
+ d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
+ v9fs_stat2inode(st, d_inode(root), sb);
p9stat_free(st);
kfree(st);
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index f95e01e058e4..0cf44b6cccd6 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/sched.h>
+#include <linux/uio.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
@@ -25,50 +26,34 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
void *buffer, size_t buffer_size)
{
ssize_t retval;
- int msize, read_count;
- u64 offset = 0, attr_size;
+ u64 attr_size;
struct p9_fid *attr_fid;
+ struct kvec kvec = {.iov_base = buffer, .iov_len = buffer_size};
+ struct iov_iter to;
+ int err;
+
+ iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size);
attr_fid = p9_client_xattrwalk(fid, name, &attr_size);
if (IS_ERR(attr_fid)) {
retval = PTR_ERR(attr_fid);
p9_debug(P9_DEBUG_VFS, "p9_client_attrwalk failed %zd\n",
retval);
- attr_fid = NULL;
- goto error;
- }
- if (!buffer_size) {
- /* request to get the attr_size */
- retval = attr_size;
- goto error;
+ return retval;
}
if (attr_size > buffer_size) {
- retval = -ERANGE;
- goto error;
- }
- msize = attr_fid->clnt->msize;
- while (attr_size) {
- if (attr_size > (msize - P9_IOHDRSZ))
- read_count = msize - P9_IOHDRSZ;
+ if (!buffer_size) /* request to get the attr_size */
+ retval = attr_size;
else
- read_count = attr_size;
- read_count = p9_client_read(attr_fid, ((char *)buffer)+offset,
- NULL, offset, read_count);
- if (read_count < 0) {
- /* error in xattr read */
- retval = read_count;
- goto error;
- }
- offset += read_count;
- attr_size -= read_count;
+ retval = -ERANGE;
+ } else {
+ iov_iter_truncate(&to, attr_size);
+ retval = p9_client_read(attr_fid, 0, &to, &err);
+ if (err)
+ retval = err;
}
- /* Total read xattr bytes */
- retval = offset;
-error:
- if (attr_fid)
- p9_client_clunk(attr_fid);
+ p9_client_clunk(attr_fid);
return retval;
-
}
@@ -120,8 +105,11 @@ int v9fs_xattr_set(struct dentry *dentry, const char *name,
int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
const void *value, size_t value_len, int flags)
{
- u64 offset = 0;
- int retval, msize, write_count;
+ struct kvec kvec = {.iov_base = (void *)value, .iov_len = value_len};
+ struct iov_iter from;
+ int retval;
+
+ iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len);
p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
name, value_len, flags);
@@ -135,29 +123,11 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
* On success fid points to xattr
*/
retval = p9_client_xattrcreate(fid, name, value_len, flags);
- if (retval < 0) {
+ if (retval < 0)
p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n",
retval);
- goto err;
- }
- msize = fid->clnt->msize;
- while (value_len) {
- if (value_len > (msize - P9_IOHDRSZ))
- write_count = msize - P9_IOHDRSZ;
- else
- write_count = value_len;
- write_count = p9_client_write(fid, ((char *)value)+offset,
- NULL, offset, write_count);
- if (write_count < 0) {
- /* error in xattr write */
- retval = write_count;
- goto err;
- }
- offset += write_count;
- value_len -= write_count;
- }
- retval = 0;
-err:
+ else
+ p9_client_write(fid, 0, &from, &retval);
p9_client_clunk(fid);
return retval;
}
diff --git a/fs/Kconfig b/fs/Kconfig
index ec35851e5b71..011f43365d7b 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -32,6 +32,7 @@ source "fs/gfs2/Kconfig"
source "fs/ocfs2/Kconfig"
source "fs/btrfs/Kconfig"
source "fs/nilfs2/Kconfig"
+source "fs/f2fs/Kconfig"
config FS_DAX
bool "Direct Access (DAX) support"
@@ -217,7 +218,6 @@ source "fs/pstore/Kconfig"
source "fs/sysv/Kconfig"
source "fs/ufs/Kconfig"
source "fs/exofs/Kconfig"
-source "fs/f2fs/Kconfig"
endif # MISC_FILESYSTEMS
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 270c48148f79..2d0cbbd14cfc 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -27,9 +27,6 @@ config COMPAT_BINFMT_ELF
bool
depends on COMPAT && BINFMT_ELF
-config ARCH_BINFMT_ELF_RANDOMIZE_PIE
- bool
-
config ARCH_BINFMT_ELF_STATE
bool
diff --git a/fs/Makefile b/fs/Makefile
index a88ac4838c9e..cb92fd4c3172 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -118,6 +118,7 @@ obj-$(CONFIG_HOSTFS) += hostfs/
obj-$(CONFIG_HPPFS) += hppfs/
obj-$(CONFIG_CACHEFILES) += cachefiles/
obj-$(CONFIG_DEBUG_FS) += debugfs/
+obj-$(CONFIG_TRACING) += tracefs/
obj-$(CONFIG_OCFS2_FS) += ocfs2/
obj-$(CONFIG_BTRFS_FS) += btrfs/
obj-$(CONFIG_GFS2_FS) += gfs2/
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index f2ba88ab4aed..82d14cdf70f9 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -61,6 +61,7 @@ adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct
kcalloc(size, sizeof(struct buffer_head *),
GFP_KERNEL);
if (!bh_fplus) {
+ ret = -ENOMEM;
adfs_error(sb, "not enough memory for"
" dir object %X (%d blocks)", id, size);
goto out;
diff --git a/fs/adfs/file.c b/fs/adfs/file.c
index 07c9edce5aa7..46c0d5671cd5 100644
--- a/fs/adfs/file.c
+++ b/fs/adfs/file.c
@@ -23,11 +23,9 @@
const struct file_operations adfs_file_operations = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
.read_iter = generic_file_read_iter,
.mmap = generic_file_mmap,
.fsync = generic_file_fsync,
- .write = new_sync_write,
.write_iter = generic_file_write_iter,
.splice_read = generic_file_splice_read,
};
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index b9acadafa4a1..335055d828e4 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -298,7 +298,7 @@ out:
int
adfs_notify_change(struct dentry *dentry, struct iattr *attr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct super_block *sb = inode->i_sb;
unsigned int ia_valid = attr->ia_valid;
int error;
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 9852bdf34d76..a19c31d3f369 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -316,7 +316,7 @@ static struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_di
dm = kmalloc(nzones * sizeof(*dm), GFP_KERNEL);
if (dm == NULL) {
adfs_error(sb, "not enough memory");
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
for (zone = 0; zone < nzones; zone++, map_addr++) {
@@ -349,7 +349,7 @@ error_free:
brelse(dm[zone].dm_bh);
kfree(dm);
- return NULL;
+ return ERR_PTR(-EIO);
}
static inline unsigned long adfs_discsize(struct adfs_discrecord *dr, int block_bits)
@@ -370,6 +370,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
unsigned char *b_data;
struct adfs_sb_info *asb;
struct inode *root;
+ int ret = -EINVAL;
sb->s_flags |= MS_NODIRATIME;
@@ -391,6 +392,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
sb_set_blocksize(sb, BLOCK_SIZE);
if (!(bh = sb_bread(sb, ADFS_DISCRECORD / BLOCK_SIZE))) {
adfs_error(sb, "unable to read superblock");
+ ret = -EIO;
goto error;
}
@@ -400,6 +402,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
if (!silent)
printk("VFS: Can't find an adfs filesystem on dev "
"%s.\n", sb->s_id);
+ ret = -EINVAL;
goto error_free_bh;
}
@@ -412,6 +415,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
if (!silent)
printk("VPS: Can't find an adfs filesystem on dev "
"%s.\n", sb->s_id);
+ ret = -EINVAL;
goto error_free_bh;
}
@@ -421,11 +425,13 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
if (!bh) {
adfs_error(sb, "couldn't read superblock on "
"2nd try.");
+ ret = -EIO;
goto error;
}
b_data = bh->b_data + (ADFS_DISCRECORD % sb->s_blocksize);
if (adfs_checkbblk(b_data)) {
adfs_error(sb, "disc record mismatch, very weird!");
+ ret = -EINVAL;
goto error_free_bh;
}
dr = (struct adfs_discrecord *)(b_data + ADFS_DR_OFFSET);
@@ -433,6 +439,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
if (!silent)
printk(KERN_ERR "VFS: Unsupported blocksize on dev "
"%s.\n", sb->s_id);
+ ret = -EINVAL;
goto error;
}
@@ -447,10 +454,12 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
asb->s_size = adfs_discsize(dr, sb->s_blocksize_bits);
asb->s_version = dr->format_version;
asb->s_log2sharesize = dr->log2sharesize;
-
+
asb->s_map = adfs_read_map(sb, dr);
- if (!asb->s_map)
+ if (IS_ERR(asb->s_map)) {
+ ret = PTR_ERR(asb->s_map);
goto error_free_bh;
+ }
brelse(bh);
@@ -499,6 +508,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
brelse(asb->s_map[i].dm_bh);
kfree(asb->s_map);
adfs_error(sb, "get root inode failed\n");
+ ret = -EIO;
goto error;
}
return 0;
@@ -508,7 +518,7 @@ error_free_bh:
error:
sb->s_fs_info = NULL;
kfree(asb);
- return -EINVAL;
+ return ret;
}
static struct dentry *adfs_mount(struct file_system_type *fs_type,
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index c8764bd7497d..cffe8370fb44 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -106,18 +106,22 @@ struct affs_sb_info {
spinlock_t work_lock; /* protects sb_work and work_queued */
};
-#define SF_INTL 0x0001 /* International filesystem. */
-#define SF_BM_VALID 0x0002 /* Bitmap is valid. */
-#define SF_IMMUTABLE 0x0004 /* Protection bits cannot be changed */
-#define SF_QUIET 0x0008 /* chmod errors will be not reported */
-#define SF_SETUID 0x0010 /* Ignore Amiga uid */
-#define SF_SETGID 0x0020 /* Ignore Amiga gid */
-#define SF_SETMODE 0x0040 /* Ignore Amiga protection bits */
-#define SF_MUFS 0x0100 /* Use MUFS uid/gid mapping */
-#define SF_OFS 0x0200 /* Old filesystem */
-#define SF_PREFIX 0x0400 /* Buffer for prefix is allocated */
-#define SF_VERBOSE 0x0800 /* Talk about fs when mounting */
-#define SF_NO_TRUNCATE 0x1000 /* Don't truncate filenames */
+#define AFFS_MOUNT_SF_INTL 0x0001 /* International filesystem. */
+#define AFFS_MOUNT_SF_BM_VALID 0x0002 /* Bitmap is valid. */
+#define AFFS_MOUNT_SF_IMMUTABLE 0x0004 /* Protection bits cannot be changed */
+#define AFFS_MOUNT_SF_QUIET 0x0008 /* chmod errors will be not reported */
+#define AFFS_MOUNT_SF_SETUID 0x0010 /* Ignore Amiga uid */
+#define AFFS_MOUNT_SF_SETGID 0x0020 /* Ignore Amiga gid */
+#define AFFS_MOUNT_SF_SETMODE 0x0040 /* Ignore Amiga protection bits */
+#define AFFS_MOUNT_SF_MUFS 0x0100 /* Use MUFS uid/gid mapping */
+#define AFFS_MOUNT_SF_OFS 0x0200 /* Old filesystem */
+#define AFFS_MOUNT_SF_PREFIX 0x0400 /* Buffer for prefix is allocated */
+#define AFFS_MOUNT_SF_VERBOSE 0x0800 /* Talk about fs when mounting */
+#define AFFS_MOUNT_SF_NO_TRUNCATE 0x1000 /* Don't truncate filenames */
+
+#define affs_clear_opt(o, opt) (o &= ~AFFS_MOUNT_##opt)
+#define affs_set_opt(o, opt) (o |= AFFS_MOUNT_##opt)
+#define affs_test_opt(o, opt) ((o) & AFFS_MOUNT_##opt)
/* short cut to get to the affs specific sb data */
static inline struct affs_sb_info *AFFS_SB(struct super_block *sb)
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 388da1ea815d..a8f463c028ce 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -138,7 +138,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino)
static int
affs_remove_link(struct dentry *dentry)
{
- struct inode *dir, *inode = dentry->d_inode;
+ struct inode *dir, *inode = d_inode(dentry);
struct super_block *sb = inode->i_sb;
struct buffer_head *bh = NULL, *link_bh = NULL;
u32 link_ino, ino;
@@ -268,11 +268,11 @@ affs_remove_header(struct dentry *dentry)
struct buffer_head *bh = NULL;
int retval;
- dir = dentry->d_parent->d_inode;
+ dir = d_inode(dentry->d_parent);
sb = dir->i_sb;
retval = -ENOENT;
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
if (!inode)
goto done;
@@ -471,9 +471,9 @@ affs_warning(struct super_block *sb, const char *function, const char *fmt, ...)
bool
affs_nofilenametruncate(const struct dentry *dentry)
{
- struct inode *inode = dentry->d_inode;
- return AFFS_SB(inode->i_sb)->s_flags & SF_NO_TRUNCATE;
+ struct inode *inode = d_inode(dentry);
+ return affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_NO_TRUNCATE);
}
/* Check if the name is valid for a affs object. */
diff --git a/fs/affs/file.c b/fs/affs/file.c
index d2468bf95669..659c579c4588 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -12,7 +12,7 @@
* affs regular file handling primitives
*/
-#include <linux/aio.h>
+#include <linux/uio.h>
#include "affs.h"
static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
@@ -389,8 +389,7 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
}
static ssize_t
-affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -398,15 +397,15 @@ affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
size_t count = iov_iter_count(iter);
ssize_t ret;
- if (rw == WRITE) {
+ if (iov_iter_rw(iter) == WRITE) {
loff_t size = offset + count;
if (AFFS_I(inode)->mmu_private < size)
return 0;
}
- ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, affs_get_block);
- if (ret < 0 && (rw & WRITE))
+ ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block);
+ if (ret < 0 && iov_iter_rw(iter) == WRITE)
affs_write_failed(mapping, offset + count);
return ret;
}
@@ -699,8 +698,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
boff = tmp % bsize;
if (boff) {
bh = affs_bread_ino(inode, bidx, 0);
- if (IS_ERR(bh))
- return PTR_ERR(bh);
+ if (IS_ERR(bh)) {
+ written = PTR_ERR(bh);
+ goto err_first_bh;
+ }
tmp = min(bsize - boff, to - from);
BUG_ON(boff + tmp > bsize || tmp > bsize);
memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
@@ -712,14 +713,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
bidx++;
} else if (bidx) {
bh = affs_bread_ino(inode, bidx - 1, 0);
- if (IS_ERR(bh))
- return PTR_ERR(bh);
+ if (IS_ERR(bh)) {
+ written = PTR_ERR(bh);
+ goto err_first_bh;
+ }
}
while (from + bsize <= to) {
prev_bh = bh;
bh = affs_getemptyblk_ino(inode, bidx);
if (IS_ERR(bh))
- goto out;
+ goto err_bh;
memcpy(AFFS_DATA(bh), data + from, bsize);
if (buffer_new(bh)) {
AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
@@ -751,7 +754,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
prev_bh = bh;
bh = affs_bread_ino(inode, bidx, 1);
if (IS_ERR(bh))
- goto out;
+ goto err_bh;
tmp = min(bsize, to - from);
BUG_ON(tmp > bsize);
memcpy(AFFS_DATA(bh), data + from, tmp);
@@ -790,12 +793,13 @@ done:
if (tmp > inode->i_size)
inode->i_size = AFFS_I(inode)->mmu_private = tmp;
+err_first_bh:
unlock_page(page);
page_cache_release(page);
return written;
-out:
+err_bh:
bh = prev_bh;
if (!written)
written = PTR_ERR(bh);
@@ -910,7 +914,7 @@ affs_truncate(struct inode *inode)
if (inode->i_size) {
AFFS_I(inode)->i_blkcnt = last_blk + 1;
AFFS_I(inode)->i_extcnt = ext + 1;
- if (AFFS_SB(sb)->s_flags & SF_OFS) {
+ if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_OFS)) {
struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0);
u32 tmp;
if (IS_ERR(bh)) {
@@ -964,9 +968,7 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
}
const struct file_operations affs_file_operations = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
.read_iter = generic_file_read_iter,
- .write = new_sync_write,
.write_iter = generic_file_write_iter,
.mmap = generic_file_mmap,
.open = affs_file_open,
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 6f34510449e8..a022f4accd76 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -66,23 +66,23 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
AFFS_I(inode)->i_lastalloc = 0;
AFFS_I(inode)->i_pa_cnt = 0;
- if (sbi->s_flags & SF_SETMODE)
+ if (affs_test_opt(sbi->s_flags, SF_SETMODE))
inode->i_mode = sbi->s_mode;
else
inode->i_mode = prot_to_mode(prot);
id = be16_to_cpu(tail->uid);
- if (id == 0 || sbi->s_flags & SF_SETUID)
+ if (id == 0 || affs_test_opt(sbi->s_flags, SF_SETUID))
inode->i_uid = sbi->s_uid;
- else if (id == 0xFFFF && sbi->s_flags & SF_MUFS)
+ else if (id == 0xFFFF && affs_test_opt(sbi->s_flags, SF_MUFS))
i_uid_write(inode, 0);
else
i_uid_write(inode, id);
id = be16_to_cpu(tail->gid);
- if (id == 0 || sbi->s_flags & SF_SETGID)
+ if (id == 0 || affs_test_opt(sbi->s_flags, SF_SETGID))
inode->i_gid = sbi->s_gid;
- else if (id == 0xFFFF && sbi->s_flags & SF_MUFS)
+ else if (id == 0xFFFF && affs_test_opt(sbi->s_flags, SF_MUFS))
i_gid_write(inode, 0);
else
i_gid_write(inode, id);
@@ -94,7 +94,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
/* fall through */
case ST_USERDIR:
if (be32_to_cpu(tail->stype) == ST_USERDIR ||
- sbi->s_flags & SF_SETMODE) {
+ affs_test_opt(sbi->s_flags, SF_SETMODE)) {
if (inode->i_mode & S_IRUSR)
inode->i_mode |= S_IXUSR;
if (inode->i_mode & S_IRGRP)
@@ -133,7 +133,8 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
}
if (tail->link_chain)
set_nlink(inode, 2);
- inode->i_mapping->a_ops = (sbi->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops;
+ inode->i_mapping->a_ops = affs_test_opt(sbi->s_flags, SF_OFS) ?
+ &affs_aops_ofs : &affs_aops;
inode->i_op = &affs_file_inode_operations;
inode->i_fop = &affs_file_operations;
break;
@@ -190,15 +191,15 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
if (!(inode->i_ino == AFFS_SB(sb)->s_root_block)) {
uid = i_uid_read(inode);
gid = i_gid_read(inode);
- if (AFFS_SB(sb)->s_flags & SF_MUFS) {
+ if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_MUFS)) {
if (uid == 0 || uid == 0xFFFF)
uid = uid ^ ~0;
if (gid == 0 || gid == 0xFFFF)
gid = gid ^ ~0;
}
- if (!(AFFS_SB(sb)->s_flags & SF_SETUID))
+ if (!affs_test_opt(AFFS_SB(sb)->s_flags, SF_SETUID))
tail->uid = cpu_to_be16(uid);
- if (!(AFFS_SB(sb)->s_flags & SF_SETGID))
+ if (!affs_test_opt(AFFS_SB(sb)->s_flags, SF_SETGID))
tail->gid = cpu_to_be16(gid);
}
}
@@ -212,7 +213,7 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
int
affs_notify_change(struct dentry *dentry, struct iattr *attr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int error;
pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid);
@@ -221,11 +222,14 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr)
if (error)
goto out;
- if (((attr->ia_valid & ATTR_UID) && (AFFS_SB(inode->i_sb)->s_flags & SF_SETUID)) ||
- ((attr->ia_valid & ATTR_GID) && (AFFS_SB(inode->i_sb)->s_flags & SF_SETGID)) ||
+ if (((attr->ia_valid & ATTR_UID) &&
+ affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_SETUID)) ||
+ ((attr->ia_valid & ATTR_GID) &&
+ affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_SETGID)) ||
((attr->ia_valid & ATTR_MODE) &&
- (AFFS_SB(inode->i_sb)->s_flags & (SF_SETMODE | SF_IMMUTABLE)))) {
- if (!(AFFS_SB(inode->i_sb)->s_flags & SF_QUIET))
+ (AFFS_SB(inode->i_sb)->s_flags &
+ (AFFS_MOUNT_SF_SETMODE | AFFS_MOUNT_SF_IMMUTABLE)))) {
+ if (!affs_test_opt(AFFS_SB(inode->i_sb)->s_flags, SF_QUIET))
error = -EPERM;
goto out;
}
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index ffb7bd82c2a5..181e05b46e72 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -53,7 +53,8 @@ affs_intl_toupper(int ch)
static inline toupper_t
affs_get_toupper(struct super_block *sb)
{
- return AFFS_SB(sb)->s_flags & SF_INTL ? affs_intl_toupper : affs_toupper;
+ return affs_test_opt(AFFS_SB(sb)->s_flags, SF_INTL) ?
+ affs_intl_toupper : affs_toupper;
}
/*
@@ -250,7 +251,7 @@ int
affs_unlink(struct inode *dir, struct dentry *dentry)
{
pr_debug("%s(dir=%lu, %lu \"%pd\")\n", __func__, dir->i_ino,
- dentry->d_inode->i_ino, dentry);
+ d_inode(dentry)->i_ino, dentry);
return affs_remove_header(dentry);
}
@@ -275,7 +276,8 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
inode->i_op = &affs_file_inode_operations;
inode->i_fop = &affs_file_operations;
- inode->i_mapping->a_ops = (AFFS_SB(sb)->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops;
+ inode->i_mapping->a_ops = affs_test_opt(AFFS_SB(sb)->s_flags, SF_OFS) ?
+ &affs_aops_ofs : &affs_aops;
error = affs_add_entry(dir, inode, dentry, ST_FILE);
if (error) {
clear_nlink(inode);
@@ -318,7 +320,7 @@ int
affs_rmdir(struct inode *dir, struct dentry *dentry)
{
pr_debug("%s(dir=%lu, %lu \"%pd\")\n", __func__, dir->i_ino,
- dentry->d_inode->i_ino, dentry);
+ d_inode(dentry)->i_ino, dentry);
return affs_remove_header(dentry);
}
@@ -401,7 +403,7 @@ err:
int
affs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
pr_debug("%s(%lu, %lu, \"%pd\")\n", __func__, inode->i_ino, dir->i_ino,
dentry);
@@ -428,13 +430,13 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
return retval;
/* Unlink destination if it already exists */
- if (new_dentry->d_inode) {
+ if (d_really_is_positive(new_dentry)) {
retval = affs_remove_header(new_dentry);
if (retval)
return retval;
}
- bh = affs_bread(sb, old_dentry->d_inode->i_ino);
+ bh = affs_bread(sb, d_inode(old_dentry)->i_ino);
if (!bh)
return -EIO;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 4cf0e9113fb6..3f89c9e05b40 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -227,22 +227,22 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
if (match_octal(&args[0], &option))
return 0;
*mode = option & 0777;
- *mount_opts |= SF_SETMODE;
+ affs_set_opt(*mount_opts, SF_SETMODE);
break;
case Opt_mufs:
- *mount_opts |= SF_MUFS;
+ affs_set_opt(*mount_opts, SF_MUFS);
break;
case Opt_notruncate:
- *mount_opts |= SF_NO_TRUNCATE;
+ affs_set_opt(*mount_opts, SF_NO_TRUNCATE);
break;
case Opt_prefix:
*prefix = match_strdup(&args[0]);
if (!*prefix)
return 0;
- *mount_opts |= SF_PREFIX;
+ affs_set_opt(*mount_opts, SF_PREFIX);
break;
case Opt_protect:
- *mount_opts |= SF_IMMUTABLE;
+ affs_set_opt(*mount_opts, SF_IMMUTABLE);
break;
case Opt_reserved:
if (match_int(&args[0], reserved))
@@ -258,7 +258,7 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
*gid = make_kgid(current_user_ns(), option);
if (!gid_valid(*gid))
return 0;
- *mount_opts |= SF_SETGID;
+ affs_set_opt(*mount_opts, SF_SETGID);
break;
case Opt_setuid:
if (match_int(&args[0], &option))
@@ -266,10 +266,10 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
*uid = make_kuid(current_user_ns(), option);
if (!uid_valid(*uid))
return 0;
- *mount_opts |= SF_SETUID;
+ affs_set_opt(*mount_opts, SF_SETUID);
break;
case Opt_verbose:
- *mount_opts |= SF_VERBOSE;
+ affs_set_opt(*mount_opts, SF_VERBOSE);
break;
case Opt_volume: {
char *vol = match_strdup(&args[0]);
@@ -435,30 +435,31 @@ got_root:
case MUFS_FS:
case MUFS_INTLFFS:
case MUFS_DCFFS:
- sbi->s_flags |= SF_MUFS;
+ affs_set_opt(sbi->s_flags, SF_MUFS);
/* fall thru */
case FS_INTLFFS:
case FS_DCFFS:
- sbi->s_flags |= SF_INTL;
+ affs_set_opt(sbi->s_flags, SF_INTL);
break;
case MUFS_FFS:
- sbi->s_flags |= SF_MUFS;
+ affs_set_opt(sbi->s_flags, SF_MUFS);
break;
case FS_FFS:
break;
case MUFS_OFS:
- sbi->s_flags |= SF_MUFS;
+ affs_set_opt(sbi->s_flags, SF_MUFS);
/* fall thru */
case FS_OFS:
- sbi->s_flags |= SF_OFS;
+ affs_set_opt(sbi->s_flags, SF_OFS);
sb->s_flags |= MS_NOEXEC;
break;
case MUFS_DCOFS:
case MUFS_INTLOFS:
- sbi->s_flags |= SF_MUFS;
+ affs_set_opt(sbi->s_flags, SF_MUFS);
case FS_DCOFS:
case FS_INTLOFS:
- sbi->s_flags |= SF_INTL | SF_OFS;
+ affs_set_opt(sbi->s_flags, SF_INTL);
+ affs_set_opt(sbi->s_flags, SF_OFS);
sb->s_flags |= MS_NOEXEC;
break;
default:
@@ -467,7 +468,7 @@ got_root:
return -EINVAL;
}
- if (mount_flags & SF_VERBOSE) {
+ if (affs_test_opt(mount_flags, SF_VERBOSE)) {
u8 len = AFFS_ROOT_TAIL(sb, root_bh)->disk_name[0];
pr_notice("Mounting volume \"%.*s\": Type=%.3s\\%c, Blocksize=%d\n",
len > 31 ? 31 : len,
@@ -478,7 +479,7 @@ got_root:
sb->s_flags |= MS_NODEV | MS_NOSUID;
sbi->s_data_blksize = sb->s_blocksize;
- if (sbi->s_flags & SF_OFS)
+ if (affs_test_opt(sbi->s_flags, SF_OFS))
sbi->s_data_blksize -= 24;
tmp_flags = sb->s_flags;
@@ -493,7 +494,7 @@ got_root:
if (IS_ERR(root_inode))
return PTR_ERR(root_inode);
- if (AFFS_SB(sb)->s_flags & SF_INTL)
+ if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_INTL))
sb->s_d_op = &affs_intl_dentry_operations;
else
sb->s_d_op = &affs_dentry_operations;
@@ -520,10 +521,14 @@ affs_remount(struct super_block *sb, int *flags, char *data)
int root_block;
unsigned long mount_flags;
int res = 0;
- char *new_opts = kstrdup(data, GFP_KERNEL);
+ char *new_opts;
char volume[32];
char *prefix = NULL;
+ new_opts = kstrdup(data, GFP_KERNEL);
+ if (!new_opts)
+ return -ENOMEM;
+
pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
sync_filesystem(sb);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 4ec35e9130e1..e10e17788f06 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -505,7 +505,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
_enter("{%x:%u},%p{%pd},",
vnode->fid.vid, vnode->fid.vnode, dentry, dentry);
- ASSERTCMP(dentry->d_inode, ==, NULL);
+ ASSERTCMP(d_inode(dentry), ==, NULL);
if (dentry->d_name.len >= AFSNAMEMAX) {
_leave(" = -ENAMETOOLONG");
@@ -563,8 +563,8 @@ success:
_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%u }",
fid.vnode,
fid.unique,
- dentry->d_inode->i_ino,
- dentry->d_inode->i_generation);
+ d_inode(dentry)->i_ino,
+ d_inode(dentry)->i_generation);
return NULL;
}
@@ -586,9 +586,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
if (flags & LOOKUP_RCU)
return -ECHILD;
- vnode = AFS_FS_I(dentry->d_inode);
+ vnode = AFS_FS_I(d_inode(dentry));
- if (dentry->d_inode)
+ if (d_really_is_positive(dentry))
_enter("{v={%x:%u} n=%pd fl=%lx},",
vnode->fid.vid, vnode->fid.vnode, dentry,
vnode->flags);
@@ -601,7 +601,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
/* lock down the parent dentry so we can peer at it */
parent = dget_parent(dentry);
- dir = AFS_FS_I(parent->d_inode);
+ dir = AFS_FS_I(d_inode(parent));
/* validate the parent directory */
if (test_bit(AFS_VNODE_MODIFIED, &dir->flags))
@@ -623,9 +623,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
switch (ret) {
case 0:
/* the filename maps to something */
- if (!dentry->d_inode)
+ if (d_really_is_negative(dentry))
goto out_bad;
- if (is_bad_inode(dentry->d_inode)) {
+ if (is_bad_inode(d_inode(dentry))) {
printk("kAFS: afs_d_revalidate: %pd2 has bad inode\n",
dentry);
goto out_bad;
@@ -647,7 +647,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
_debug("%pd: file deleted (uq %u -> %u I:%u)",
dentry, fid.unique,
vnode->fid.unique,
- dentry->d_inode->i_generation);
+ d_inode(dentry)->i_generation);
spin_lock(&vnode->lock);
set_bit(AFS_VNODE_DELETED, &vnode->flags);
spin_unlock(&vnode->lock);
@@ -658,7 +658,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
case -ENOENT:
/* the filename is unknown */
_debug("%pd: dirent not found", dentry);
- if (dentry->d_inode)
+ if (d_really_is_positive(dentry))
goto not_found;
goto out_valid;
@@ -703,9 +703,9 @@ static int afs_d_delete(const struct dentry *dentry)
if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
goto zap;
- if (dentry->d_inode &&
- (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(dentry->d_inode)->flags) ||
- test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(dentry->d_inode)->flags)))
+ if (d_really_is_positive(dentry) &&
+ (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(d_inode(dentry))->flags) ||
+ test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(d_inode(dentry))->flags)))
goto zap;
_leave(" = 0 [keep]");
@@ -814,8 +814,8 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
if (ret < 0)
goto rmdir_error;
- if (dentry->d_inode) {
- vnode = AFS_FS_I(dentry->d_inode);
+ if (d_really_is_positive(dentry)) {
+ vnode = AFS_FS_I(d_inode(dentry));
clear_nlink(&vnode->vfs_inode);
set_bit(AFS_VNODE_DELETED, &vnode->flags);
afs_discard_callback_on_delete(vnode);
@@ -856,8 +856,8 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
goto error;
}
- if (dentry->d_inode) {
- vnode = AFS_FS_I(dentry->d_inode);
+ if (d_really_is_positive(dentry)) {
+ vnode = AFS_FS_I(d_inode(dentry));
/* make sure we have a callback promise on the victim */
ret = afs_validate(vnode, key);
@@ -869,7 +869,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
if (ret < 0)
goto remove_error;
- if (dentry->d_inode) {
+ if (d_really_is_positive(dentry)) {
/* if the file wasn't deleted due to excess hard links, the
* fileserver will break the callback promise on the file - if
* it had one - before it returns to us, and if it was deleted,
@@ -879,7 +879,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
* or it was outstanding on a different server, then it won't
* break it either...
*/
- vnode = AFS_FS_I(dentry->d_inode);
+ vnode = AFS_FS_I(d_inode(dentry));
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
_debug("AFS_VNODE_DELETED");
if (test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags))
@@ -977,7 +977,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
struct key *key;
int ret;
- vnode = AFS_FS_I(from->d_inode);
+ vnode = AFS_FS_I(d_inode(from));
dvnode = AFS_FS_I(dir);
_enter("{%x:%u},{%x:%u},{%pd}",
@@ -1089,7 +1089,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct key *key;
int ret;
- vnode = AFS_FS_I(old_dentry->d_inode);
+ vnode = AFS_FS_I(d_inode(old_dentry));
orig_dvnode = AFS_FS_I(old_dir);
new_dvnode = AFS_FS_I(new_dir);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 932ce07948b3..999bc3caec92 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -31,8 +31,6 @@ const struct file_operations afs_file_operations = {
.open = afs_open,
.release = afs_release,
.llseek = generic_file_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = generic_file_read_iter,
.write_iter = afs_file_write,
.mmap = generic_file_readonly_mmap,
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 8a1d38ef0fc2..e06f5a23352a 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -379,7 +379,7 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
{
struct inode *inode;
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
@@ -458,7 +458,7 @@ void afs_evict_inode(struct inode *inode)
*/
int afs_setattr(struct dentry *dentry, struct iattr *attr)
{
- struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
struct key *key;
int ret;
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 0dd4dafee10b..91ea1aa0d8b3 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -22,9 +22,12 @@
int afs_abort_to_error(u32 abort_code)
{
switch (abort_code) {
+ /* low errno codes inserted into abort namespace */
case 13: return -EACCES;
case 27: return -EFBIG;
case 30: return -EROFS;
+
+ /* VICE "special error" codes; 101 - 111 */
case VSALVAGE: return -EIO;
case VNOVNODE: return -ENOENT;
case VNOVOL: return -ENOMEDIUM;
@@ -36,11 +39,18 @@ int afs_abort_to_error(u32 abort_code)
case VOVERQUOTA: return -EDQUOT;
case VBUSY: return -EBUSY;
case VMOVED: return -ENXIO;
- case 0x2f6df0a: return -EWOULDBLOCK;
+
+ /* Unified AFS error table; ET "uae" == 0x2f6df00 */
+ case 0x2f6df00: return -EPERM;
+ case 0x2f6df01: return -ENOENT;
+ case 0x2f6df04: return -EIO;
+ case 0x2f6df0a: return -EAGAIN;
+ case 0x2f6df0b: return -ENOMEM;
case 0x2f6df0c: return -EACCES;
case 0x2f6df0f: return -EBUSY;
case 0x2f6df10: return -EEXIST;
case 0x2f6df11: return -EXDEV;
+ case 0x2f6df12: return -ENODEV;
case 0x2f6df13: return -ENOTDIR;
case 0x2f6df14: return -EISDIR;
case 0x2f6df15: return -EINVAL;
@@ -54,8 +64,12 @@ int afs_abort_to_error(u32 abort_code)
case 0x2f6df23: return -ENAMETOOLONG;
case 0x2f6df24: return -ENOLCK;
case 0x2f6df26: return -ENOTEMPTY;
+ case 0x2f6df28: return -EWOULDBLOCK;
+ case 0x2f6df69: return -ENOTCONN;
+ case 0x2f6df6c: return -ETIMEDOUT;
case 0x2f6df78: return -EDQUOT;
+ /* RXKAD abort codes; from include/rxrpc/packet.h. ET "RXK" == 0x1260B00 */
case RXKADINCONSISTENCY: return -EPROTO;
case RXKADPACKETSHORT: return -EPROTO;
case RXKADLEVELFAIL: return -EKEYREJECTED;
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 938c5ab06d5a..ccd0b212e82a 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -134,7 +134,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
_enter("{%pd}", mntpt);
- BUG_ON(!mntpt->d_inode);
+ BUG_ON(!d_inode(mntpt));
ret = -ENOMEM;
devname = (char *) get_zeroed_page(GFP_KERNEL);
@@ -145,7 +145,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
if (!options)
goto error_no_options;
- vnode = AFS_FS_I(mntpt->d_inode);
+ vnode = AFS_FS_I(d_inode(mntpt));
if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) {
/* if the directory is a pseudo directory, use the d_name */
static const char afs_root_cell[] = ":root.cell.";
@@ -169,14 +169,14 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
}
} else {
/* read the contents of the AFS special symlink */
- loff_t size = i_size_read(mntpt->d_inode);
+ loff_t size = i_size_read(d_inode(mntpt));
char *buf;
ret = -EINVAL;
if (size > PAGE_SIZE - 1)
goto error_no_page;
- page = read_mapping_page(mntpt->d_inode->i_mapping, 0, NULL);
+ page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL);
if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto error_no_page;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index dbc732e9a5c0..3a57a1b0fb51 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -770,15 +770,12 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb,
void afs_send_empty_reply(struct afs_call *call)
{
struct msghdr msg;
- struct kvec iov[1];
_enter("");
- iov[0].iov_base = NULL;
- iov[0].iov_len = 0;
msg.msg_name = NULL;
msg.msg_namelen = 0;
- iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 0, 0); /* WTF? */
+ iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
diff --git a/fs/afs/super.c b/fs/afs/super.c
index c4861557e385..1fb4a5129f7d 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -529,7 +529,7 @@ static void afs_destroy_inode(struct inode *inode)
static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct afs_volume_status vs;
- struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
struct key *key;
int ret;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c13cb08964ed..0714abcd7f32 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -14,7 +14,6 @@
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
-#include <linux/aio.h>
#include "internal.h"
static int afs_write_back_from_locked_page(struct afs_writeback *wb,
diff --git a/fs/aio.c b/fs/aio.c
index f8e52a1854c1..480440f4701f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -77,6 +77,11 @@ struct kioctx_cpu {
unsigned reqs_available;
};
+struct ctx_rq_wait {
+ struct completion comp;
+ atomic_t count;
+};
+
struct kioctx {
struct percpu_ref users;
atomic_t dead;
@@ -115,7 +120,7 @@ struct kioctx {
/*
* signals when all in-flight requests are done
*/
- struct completion *requests_done;
+ struct ctx_rq_wait *rq_wait;
struct {
/*
@@ -151,6 +156,38 @@ struct kioctx {
unsigned id;
};
+/*
+ * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
+ * cancelled or completed (this makes a certain amount of sense because
+ * successful cancellation - io_cancel() - does deliver the completion to
+ * userspace).
+ *
+ * And since most things don't implement kiocb cancellation and we'd really like
+ * kiocb completion to be lockless when possible, we use ki_cancel to
+ * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
+ * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
+ */
+#define KIOCB_CANCELLED ((void *) (~0ULL))
+
+struct aio_kiocb {
+ struct kiocb common;
+
+ struct kioctx *ki_ctx;
+ kiocb_cancel_fn *ki_cancel;
+
+ struct iocb __user *ki_user_iocb; /* user's aiocb */
+ __u64 ki_user_data; /* user's data for completion */
+
+ struct list_head ki_list; /* the aio core uses this
+ * for cancellation */
+
+ /*
+ * If the aio_resfd field of the userspace iocb is not zero,
+ * this is the underlying eventfd context to deliver events to.
+ */
+ struct eventfd_ctx *ki_eventfd;
+};
+
/*------ sysctl variables----*/
static DEFINE_SPINLOCK(aio_nr_lock);
unsigned long aio_nr; /* current system wide number of aio requests */
@@ -220,7 +257,7 @@ static int __init aio_setup(void)
if (IS_ERR(aio_mnt))
panic("Failed to create aio fs mount.");
- kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
+ kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
@@ -278,11 +315,11 @@ static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
-static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
+static int aio_ring_remap(struct file *file, struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
struct kioctx_table *table;
- int i;
+ int i, res = -EINVAL;
spin_lock(&mm->ioctx_lock);
rcu_read_lock();
@@ -292,13 +329,17 @@ static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
ctx = table->table[i];
if (ctx && ctx->aio_ring_file == file) {
- ctx->user_id = ctx->mmap_base = vma->vm_start;
+ if (!atomic_read(&ctx->dead)) {
+ ctx->user_id = ctx->mmap_base = vma->vm_start;
+ res = 0;
+ }
break;
}
}
rcu_read_unlock();
spin_unlock(&mm->ioctx_lock);
+ return res;
}
static const struct file_operations aio_ring_fops = {
@@ -480,8 +521,9 @@ static int aio_setup_ring(struct kioctx *ctx)
#define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
#define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
-void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
+void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
{
+ struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
struct kioctx *ctx = req->ki_ctx;
unsigned long flags;
@@ -496,7 +538,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);
-static int kiocb_cancel(struct kiocb *kiocb)
+static int kiocb_cancel(struct aio_kiocb *kiocb)
{
kiocb_cancel_fn *old, *cancel;
@@ -514,7 +556,7 @@ static int kiocb_cancel(struct kiocb *kiocb)
cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
} while (cancel != old);
- return cancel(kiocb);
+ return cancel(&kiocb->common);
}
static void free_ioctx(struct work_struct *work)
@@ -535,8 +577,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
/* At this point we know that there are no any in-flight requests */
- if (ctx->requests_done)
- complete(ctx->requests_done);
+ if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
+ complete(&ctx->rq_wait->comp);
INIT_WORK(&ctx->free_work, free_ioctx);
schedule_work(&ctx->free_work);
@@ -550,13 +592,13 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
static void free_ioctx_users(struct percpu_ref *ref)
{
struct kioctx *ctx = container_of(ref, struct kioctx, users);
- struct kiocb *req;
+ struct aio_kiocb *req;
spin_lock_irq(&ctx->ctx_lock);
while (!list_empty(&ctx->active_reqs)) {
req = list_first_entry(&ctx->active_reqs,
- struct kiocb, ki_list);
+ struct aio_kiocb, ki_list);
list_del_init(&req->ki_list);
kiocb_cancel(req);
@@ -655,8 +697,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
nr_events *= 2;
/* Prevent overflows */
- if ((nr_events > (0x10000000U / sizeof(struct io_event))) ||
- (nr_events > (0x10000000U / sizeof(struct kiocb)))) {
+ if (nr_events > (0x10000000U / sizeof(struct io_event))) {
pr_debug("ENOMEM: nr_events too high\n");
return ERR_PTR(-EINVAL);
}
@@ -727,6 +768,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
err_cleanup:
aio_nr_sub(ctx->max_reqs);
err_ctx:
+ atomic_set(&ctx->dead, 1);
+ if (ctx->mmap_size)
+ vm_munmap(ctx->mmap_base, ctx->mmap_size);
aio_free_ring(ctx);
err:
mutex_unlock(&ctx->ring_lock);
@@ -744,15 +788,16 @@ err:
* the rapid destruction of the kioctx.
*/
static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
- struct completion *requests_done)
+ struct ctx_rq_wait *wait)
{
struct kioctx_table *table;
- if (atomic_xchg(&ctx->dead, 1))
+ spin_lock(&mm->ioctx_lock);
+ if (atomic_xchg(&ctx->dead, 1)) {
+ spin_unlock(&mm->ioctx_lock);
return -EINVAL;
+ }
-
- spin_lock(&mm->ioctx_lock);
table = rcu_dereference_raw(mm->ioctx_table);
WARN_ON(ctx != table->table[ctx->id]);
table->table[ctx->id] = NULL;
@@ -773,27 +818,11 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
if (ctx->mmap_size)
vm_munmap(ctx->mmap_base, ctx->mmap_size);
- ctx->requests_done = requests_done;
+ ctx->rq_wait = wait;
percpu_ref_kill(&ctx->users);
return 0;
}
-/* wait_on_sync_kiocb:
- * Waits on the given sync kiocb to complete.
- */
-ssize_t wait_on_sync_kiocb(struct kiocb *req)
-{
- while (!req->ki_ctx) {
- set_current_state(TASK_UNINTERRUPTIBLE);
- if (req->ki_ctx)
- break;
- io_schedule();
- }
- __set_current_state(TASK_RUNNING);
- return req->ki_user_data;
-}
-EXPORT_SYMBOL(wait_on_sync_kiocb);
-
/*
* exit_aio: called when the last user of mm goes away. At this point, there is
* no way for any new requests to be submited or any of the io_* syscalls to be
@@ -805,18 +834,24 @@ EXPORT_SYMBOL(wait_on_sync_kiocb);
void exit_aio(struct mm_struct *mm)
{
struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table);
- int i;
+ struct ctx_rq_wait wait;
+ int i, skipped;
if (!table)
return;
+ atomic_set(&wait.count, table->nr);
+ init_completion(&wait.comp);
+
+ skipped = 0;
for (i = 0; i < table->nr; ++i) {
struct kioctx *ctx = table->table[i];
- struct completion requests_done =
- COMPLETION_INITIALIZER_ONSTACK(requests_done);
- if (!ctx)
+ if (!ctx) {
+ skipped++;
continue;
+ }
+
/*
* We don't need to bother with munmap() here - exit_mmap(mm)
* is coming and it'll unmap everything. And we simply can't,
@@ -825,10 +860,12 @@ void exit_aio(struct mm_struct *mm)
* that it needs to unmap the area, just set it to 0.
*/
ctx->mmap_size = 0;
- kill_ioctx(mm, ctx, &requests_done);
+ kill_ioctx(mm, ctx, &wait);
+ }
+ if (!atomic_sub_and_test(skipped, &wait.count)) {
/* Wait until all IO for the context are done. */
- wait_for_completion(&requests_done);
+ wait_for_completion(&wait.comp);
}
RCU_INIT_POINTER(mm->ioctx_table, NULL);
@@ -948,9 +985,9 @@ static void user_refill_reqs_available(struct kioctx *ctx)
* Allocate a slot for an aio request.
* Returns NULL if no requests are free.
*/
-static inline struct kiocb *aio_get_req(struct kioctx *ctx)
+static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
{
- struct kiocb *req;
+ struct aio_kiocb *req;
if (!get_reqs_available(ctx)) {
user_refill_reqs_available(ctx);
@@ -971,10 +1008,10 @@ out_put:
return NULL;
}
-static void kiocb_free(struct kiocb *req)
+static void kiocb_free(struct aio_kiocb *req)
{
- if (req->ki_filp)
- fput(req->ki_filp);
+ if (req->common.ki_filp)
+ fput(req->common.ki_filp);
if (req->ki_eventfd != NULL)
eventfd_ctx_put(req->ki_eventfd);
kmem_cache_free(kiocb_cachep, req);
@@ -1010,8 +1047,9 @@ out:
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
-void aio_complete(struct kiocb *iocb, long res, long res2)
+static void aio_complete(struct kiocb *kiocb, long res, long res2)
{
+ struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common);
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
struct io_event *ev_page, *event;
@@ -1025,13 +1063,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
* ref, no other paths have a way to get another ref
* - the sync task helpfully left a reference to itself in the iocb
*/
- if (is_sync_kiocb(iocb)) {
- iocb->ki_user_data = res;
- smp_wmb();
- iocb->ki_ctx = ERR_PTR(-EXDEV);
- wake_up_process(iocb->ki_obj.tsk);
- return;
- }
+ BUG_ON(is_sync_kiocb(kiocb));
if (iocb->ki_list.next) {
unsigned long flags;
@@ -1057,7 +1089,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
event = ev_page + pos % AIO_EVENTS_PER_PAGE;
- event->obj = (u64)(unsigned long)iocb->ki_obj.user;
+ event->obj = (u64)(unsigned long)iocb->ki_user_iocb;
event->data = iocb->ki_user_data;
event->res = res;
event->res2 = res2;
@@ -1066,7 +1098,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
- ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
+ ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data,
res, res2);
/* after flagging the request as done, we
@@ -1113,7 +1145,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
percpu_ref_put(&ctx->reqs);
}
-EXPORT_SYMBOL(aio_complete);
/* aio_read_events_ring
* Pull an event off of the ioctx's event ring. Returns the number of
@@ -1313,15 +1344,17 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
{
struct kioctx *ioctx = lookup_ioctx(ctx);
if (likely(NULL != ioctx)) {
- struct completion requests_done =
- COMPLETION_INITIALIZER_ONSTACK(requests_done);
+ struct ctx_rq_wait wait;
int ret;
+ init_completion(&wait.comp);
+ atomic_set(&wait.count, 1);
+
/* Pass requests_done to kill_ioctx() where it can be set
* in a thread-safe way. If we try to set it here then we have
* a race condition if two io_destroy() called simultaneously.
*/
- ret = kill_ioctx(current->mm, ioctx, &requests_done);
+ ret = kill_ioctx(current->mm, ioctx, &wait);
percpu_ref_put(&ioctx->users);
/* Wait until all IO for the context are done. Otherwise kernel
@@ -1329,7 +1362,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
* is destroyed.
*/
if (!ret)
- wait_for_completion(&requests_done);
+ wait_for_completion(&wait.comp);
return ret;
}
@@ -1337,50 +1370,21 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
return -EINVAL;
}
-typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
- unsigned long, loff_t);
typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);
-static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
- int rw, char __user *buf,
- unsigned long *nr_segs,
- struct iovec **iovec,
- bool compat)
+static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len,
+ struct iovec **iovec,
+ bool compat,
+ struct iov_iter *iter)
{
- ssize_t ret;
-
- *nr_segs = kiocb->ki_nbytes;
-
#ifdef CONFIG_COMPAT
if (compat)
- ret = compat_rw_copy_check_uvector(rw,
+ return compat_import_iovec(rw,
(struct compat_iovec __user *)buf,
- *nr_segs, UIO_FASTIOV, *iovec, iovec);
- else
+ len, UIO_FASTIOV, iovec, iter);
#endif
- ret = rw_copy_check_uvector(rw,
- (struct iovec __user *)buf,
- *nr_segs, UIO_FASTIOV, *iovec, iovec);
- if (ret < 0)
- return ret;
-
- /* ki_nbytes now reflect bytes instead of segs */
- kiocb->ki_nbytes = ret;
- return 0;
-}
-
-static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
- int rw, char __user *buf,
- unsigned long *nr_segs,
- struct iovec *iovec)
-{
- if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes)))
- return -EFAULT;
-
- iovec->iov_base = buf;
- iovec->iov_len = kiocb->ki_nbytes;
- *nr_segs = 1;
- return 0;
+ return import_iovec(rw, (struct iovec __user *)buf,
+ len, UIO_FASTIOV, iovec, iter);
}
/*
@@ -1388,14 +1392,12 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
* Performs the initial checks and io submission.
*/
static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
- char __user *buf, bool compat)
+ char __user *buf, size_t len, bool compat)
{
struct file *file = req->ki_filp;
ssize_t ret;
- unsigned long nr_segs;
int rw;
fmode_t mode;
- aio_rw_op *rw_op;
rw_iter_op *iter_op;
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
@@ -1405,7 +1407,6 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
case IOCB_CMD_PREADV:
mode = FMODE_READ;
rw = READ;
- rw_op = file->f_op->aio_read;
iter_op = file->f_op->read_iter;
goto rw_common;
@@ -1413,51 +1414,40 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
case IOCB_CMD_PWRITEV:
mode = FMODE_WRITE;
rw = WRITE;
- rw_op = file->f_op->aio_write;
iter_op = file->f_op->write_iter;
goto rw_common;
rw_common:
if (unlikely(!(file->f_mode & mode)))
return -EBADF;
- if (!rw_op && !iter_op)
+ if (!iter_op)
return -EINVAL;
- ret = (opcode == IOCB_CMD_PREADV ||
- opcode == IOCB_CMD_PWRITEV)
- ? aio_setup_vectored_rw(req, rw, buf, &nr_segs,
- &iovec, compat)
- : aio_setup_single_vector(req, rw, buf, &nr_segs,
- iovec);
+ if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
+ ret = aio_setup_vectored_rw(rw, buf, len,
+ &iovec, compat, &iter);
+ else {
+ ret = import_single_range(rw, buf, len, iovec, &iter);
+ iovec = NULL;
+ }
if (!ret)
- ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+ ret = rw_verify_area(rw, file, &req->ki_pos,
+ iov_iter_count(&iter));
if (ret < 0) {
- if (iovec != inline_vecs)
- kfree(iovec);
+ kfree(iovec);
return ret;
}
- req->ki_nbytes = ret;
-
- /* XXX: move/kill - rw_verify_area()? */
- /* This matches the pread()/pwrite() logic */
- if (req->ki_pos < 0) {
- ret = -EINVAL;
- break;
- }
+ len = ret;
if (rw == WRITE)
file_start_write(file);
- if (iter_op) {
- iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes);
- ret = iter_op(req, &iter);
- } else {
- ret = rw_op(req, iovec, nr_segs, req->ki_pos);
- }
+ ret = iter_op(req, &iter);
if (rw == WRITE)
file_end_write(file);
+ kfree(iovec);
break;
case IOCB_CMD_FDSYNC:
@@ -1479,9 +1469,6 @@ rw_common:
return -EINVAL;
}
- if (iovec != inline_vecs)
- kfree(iovec);
-
if (ret != -EIOCBQUEUED) {
/*
* There's no easy way to restart the syscall since other AIO's
@@ -1500,7 +1487,7 @@ rw_common:
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
{
- struct kiocb *req;
+ struct aio_kiocb *req;
ssize_t ret;
/* enforce forwards compatibility on users */
@@ -1523,11 +1510,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
if (unlikely(!req))
return -EAGAIN;
- req->ki_filp = fget(iocb->aio_fildes);
- if (unlikely(!req->ki_filp)) {
+ req->common.ki_filp = fget(iocb->aio_fildes);
+ if (unlikely(!req->common.ki_filp)) {
ret = -EBADF;
goto out_put_req;
}
+ req->common.ki_pos = iocb->aio_offset;
+ req->common.ki_complete = aio_complete;
+ req->common.ki_flags = iocb_flags(req->common.ki_filp);
if (iocb->aio_flags & IOCB_FLAG_RESFD) {
/*
@@ -1542,6 +1532,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_eventfd = NULL;
goto out_put_req;
}
+
+ req->common.ki_flags |= IOCB_EVENTFD;
}
ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
@@ -1550,13 +1542,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
goto out_put_req;
}
- req->ki_obj.user = user_iocb;
+ req->ki_user_iocb = user_iocb;
req->ki_user_data = iocb->aio_data;
- req->ki_pos = iocb->aio_offset;
- req->ki_nbytes = iocb->aio_nbytes;
- ret = aio_run_iocb(req, iocb->aio_lio_opcode,
+ ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode,
(char __user *)(unsigned long)iocb->aio_buf,
+ iocb->aio_nbytes,
compat);
if (ret)
goto out_put_req;
@@ -1643,10 +1634,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
/* lookup_kiocb
* Finds a given iocb for cancellation.
*/
-static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
- u32 key)
+static struct aio_kiocb *
+lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key)
{
- struct list_head *pos;
+ struct aio_kiocb *kiocb;
assert_spin_locked(&ctx->ctx_lock);
@@ -1654,9 +1645,8 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
return NULL;
/* TODO: use a hash or array, this sucks. */
- list_for_each(pos, &ctx->active_reqs) {
- struct kiocb *kiocb = list_kiocb(pos);
- if (kiocb->ki_obj.user == iocb)
+ list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
+ if (kiocb->ki_user_iocb == iocb)
return kiocb;
}
return NULL;
@@ -1676,7 +1666,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
struct io_event __user *, result)
{
struct kioctx *ctx;
- struct kiocb *kiocb;
+ struct aio_kiocb *kiocb;
u32 key;
int ret;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 8e98cf954bab..5b700ef1e59d 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -213,7 +213,7 @@ void autofs4_clean_ino(struct autofs_info *);
static inline int autofs_prepare_pipe(struct file *pipe)
{
- if (!pipe->f_op->write)
+ if (!(pipe->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
if (!S_ISFIFO(file_inode(pipe)->i_mode))
return -EINVAL;
@@ -235,12 +235,12 @@ static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
static inline u64 autofs4_get_ino(struct autofs_sb_info *sbi)
{
- return sbi->sb->s_root->d_inode->i_ino;
+ return d_inode(sbi->sb->s_root)->i_ino;
}
static inline int simple_positive(struct dentry *dentry)
{
- return dentry->d_inode && !d_unhashed(dentry);
+ return d_really_is_positive(dentry) && !d_unhashed(dentry);
}
static inline void __autofs4_add_expiring(struct dentry *dentry)
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 11dd118f75e2..1cebc3c52fa5 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -374,7 +374,7 @@ static struct dentry *should_expire(struct dentry *dentry,
return NULL;
}
- if (dentry->d_inode && d_is_symlink(dentry)) {
+ if (d_really_is_positive(dentry) && d_is_symlink(dentry)) {
DPRINTK("checking symlink %p %pd", dentry, dentry);
/*
* A symlink can't be "busy" in the usual sense so
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 1c55388ae633..a3ae0b2aeb5a 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -71,7 +71,7 @@ void autofs4_kill_sb(struct super_block *sb)
static int autofs4_show_options(struct seq_file *m, struct dentry *root)
{
struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
- struct inode *root_inode = root->d_sb->s_root->d_inode;
+ struct inode *root_inode = d_inode(root->d_sb->s_root);
if (!sbi)
return 0;
@@ -352,8 +352,8 @@ struct inode *autofs4_get_inode(struct super_block *sb, umode_t mode)
inode->i_mode = mode;
if (sb->s_root) {
- inode->i_uid = sb->s_root->d_inode->i_uid;
- inode->i_gid = sb->s_root->d_inode->i_gid;
+ inode->i_uid = d_inode(sb->s_root)->i_uid;
+ inode->i_gid = d_inode(sb->s_root)->i_gid;
}
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_ino = get_next_ino();
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 7e44fdd03e2d..c6d7d3dbd52a 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -240,7 +240,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry,
spin_lock(&expiring->d_lock);
/* We've already been dentry_iput or unlinked */
- if (!expiring->d_inode)
+ if (d_really_is_negative(expiring))
goto next;
qstr = &expiring->d_name;
@@ -371,7 +371,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
* having d_mountpoint() true, so there's no need to call back
* to the daemon.
*/
- if (dentry->d_inode && d_is_symlink(dentry)) {
+ if (d_really_is_positive(dentry) && d_is_symlink(dentry)) {
spin_unlock(&sbi->fs_lock);
goto done;
}
@@ -459,7 +459,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
return 0;
if (d_mountpoint(dentry))
return 0;
- inode = ACCESS_ONCE(dentry->d_inode);
+ inode = d_inode_rcu(dentry);
if (inode && S_ISLNK(inode->i_mode))
return -EISDIR;
if (list_empty(&dentry->d_subdirs))
@@ -485,7 +485,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
* an incorrect ELOOP error return.
*/
if ((!d_mountpoint(dentry) && !simple_empty(dentry)) ||
- (dentry->d_inode && d_is_symlink(dentry)))
+ (d_really_is_positive(dentry) && d_is_symlink(dentry)))
status = -EISDIR;
}
spin_unlock(&sbi->fs_lock);
@@ -625,8 +625,8 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
}
dput(ino->dentry);
- dentry->d_inode->i_size = 0;
- clear_nlink(dentry->d_inode);
+ d_inode(dentry)->i_size = 0;
+ clear_nlink(d_inode(dentry));
dir->i_mtime = CURRENT_TIME;
@@ -719,8 +719,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
atomic_dec(&p_ino->count);
}
dput(ino->dentry);
- dentry->d_inode->i_size = 0;
- clear_nlink(dentry->d_inode);
+ d_inode(dentry)->i_size = 0;
+ clear_nlink(d_inode(dentry));
if (dir->i_nlink)
drop_nlink(dir);
@@ -839,7 +839,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
*/
int is_autofs4_dentry(struct dentry *dentry)
{
- return dentry && dentry->d_inode &&
+ return dentry && d_really_is_positive(dentry) &&
dentry->d_op == &autofs4_dentry_operations &&
dentry->d_fsdata != NULL;
}
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index 1e8ea192be2b..de58cc7b8076 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -18,7 +18,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
struct autofs_info *ino = autofs4_dentry_ino(dentry);
if (ino && !autofs4_oz_mode(sbi))
ino->last_used = jiffies;
- nd_set_link(nd, dentry->d_inode->i_private);
+ nd_set_link(nd, d_inode(dentry)->i_private);
return NULL;
}
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 116fd38ee472..35b755e79c2d 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -70,7 +70,7 @@ static int autofs4_write(struct autofs_sb_info *sbi,
mutex_lock(&sbi->pipe_mutex);
while (bytes &&
- (wr = file->f_op->write(file,data,bytes,&file->f_pos)) > 0) {
+ (wr = __vfs_write(file,data,bytes,&file->f_pos)) > 0) {
data += wr;
bytes -= wr;
}
@@ -322,7 +322,7 @@ static int validate_request(struct autofs_wait_queue **wait,
* continue on and create a new request.
*/
if (!IS_ROOT(dentry)) {
- if (dentry->d_inode && d_unhashed(dentry)) {
+ if (d_really_is_positive(dentry) && d_unhashed(dentry)) {
struct dentry *parent = dentry->d_parent;
new = d_lookup(parent, &dentry->d_name);
if (new)
@@ -364,7 +364,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
if (pid == 0 || tgid == 0)
return -ENOENT;
- if (!dentry->d_inode) {
+ if (d_really_is_negative(dentry)) {
/*
* A wait for a negative dentry is invalid for certain
* cases. A direct or offset mount "always" has its mount
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index 3a7813ab8c95..1fead8d56a98 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -19,16 +19,16 @@ typedef u64 befs_blocknr_t;
* BeFS in memory structures
*/
-typedef struct befs_mount_options {
+struct befs_mount_options {
kgid_t gid;
kuid_t uid;
int use_gid;
int use_uid;
int debug;
char *iocharset;
-} befs_mount_options;
+};
-typedef struct befs_sb_info {
+struct befs_sb_info {
u32 magic1;
u32 block_size;
u32 block_shift;
@@ -52,12 +52,11 @@ typedef struct befs_sb_info {
befs_inode_addr indices;
u32 magic3;
- befs_mount_options mount_opts;
+ struct befs_mount_options mount_opts;
struct nls_table *nls;
+};
-} befs_sb_info;
-
-typedef struct befs_inode_info {
+struct befs_inode_info {
u32 i_flags;
u32 i_type;
@@ -71,8 +70,7 @@ typedef struct befs_inode_info {
} i_data;
struct inode vfs_inode;
-
-} befs_inode_info;
+};
enum befs_err {
BEFS_OK,
@@ -105,13 +103,13 @@ void befs_dump_index_node(const struct super_block *sb, befs_btree_nodehead *);
/* Gets a pointer to the private portion of the super_block
* structure from the public part
*/
-static inline befs_sb_info *
+static inline struct befs_sb_info *
BEFS_SB(const struct super_block *super)
{
- return (befs_sb_info *) super->s_fs_info;
+ return (struct befs_sb_info *) super->s_fs_info;
}
-static inline befs_inode_info *
+static inline struct befs_inode_info *
BEFS_I(const struct inode *inode)
{
return list_entry(inode, struct befs_inode_info, vfs_inode);
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index 1e8e0b8d8836..ebd50718659f 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -168,7 +168,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
befs_blocknr_t blocks;
befs_blocknr_t datablocks; /* File data blocks */
befs_blocknr_t metablocks; /* FS metadata blocks */
- befs_sb_info *befs_sb = BEFS_SB(sb);
+ struct befs_sb_info *befs_sb = BEFS_SB(sb);
befs_debug(sb, "---> %s", __func__);
@@ -428,7 +428,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
struct buffer_head *indir_block;
befs_block_run indir_run;
befs_disk_inode_addr *iaddr_array = NULL;
- befs_sb_info *befs_sb = BEFS_SB(sb);
+ struct befs_sb_info *befs_sb = BEFS_SB(sb);
befs_blocknr_t indir_start_blk =
data->max_indirect_range >> befs_sb->block_shift;
diff --git a/fs/befs/io.c b/fs/befs/io.c
index 0408a3d601d0..7a5b4ec21c56 100644
--- a/fs/befs/io.c
+++ b/fs/befs/io.c
@@ -28,7 +28,7 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
{
struct buffer_head *bh = NULL;
befs_blocknr_t block = 0;
- befs_sb_info *befs_sb = BEFS_SB(sb);
+ struct befs_sb_info *befs_sb = BEFS_SB(sb);
befs_debug(sb, "---> Enter %s "
"[%u, %hu, %hu]", __func__, iaddr.allocation_group,
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index e089f1985fca..7943533c3868 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -51,7 +51,7 @@ static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
static void befs_put_super(struct super_block *);
static int befs_remount(struct super_block *, int *, char *);
static int befs_statfs(struct dentry *, struct kstatfs *);
-static int parse_options(char *, befs_mount_options *);
+static int parse_options(char *, struct befs_mount_options *);
static const struct super_operations befs_sops = {
.alloc_inode = befs_alloc_inode, /* allocate a new inode */
@@ -304,9 +304,8 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
{
struct buffer_head *bh = NULL;
befs_inode *raw_inode = NULL;
-
- befs_sb_info *befs_sb = BEFS_SB(sb);
- befs_inode_info *befs_ino = NULL;
+ struct befs_sb_info *befs_sb = BEFS_SB(sb);
+ struct befs_inode_info *befs_ino = NULL;
struct inode *inode;
long ret = -EIO;
@@ -472,7 +471,7 @@ static void *
befs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct super_block *sb = dentry->d_sb;
- befs_inode_info *befs_ino = BEFS_I(dentry->d_inode);
+ struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
befs_data_stream *data = &befs_ino->i_data.ds;
befs_off_t len = data->size;
char *link;
@@ -502,7 +501,8 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd)
static void *
befs_fast_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- befs_inode_info *befs_ino = BEFS_I(dentry->d_inode);
+ struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
+
nd_set_link(nd, befs_ino->i_data.symlink);
return NULL;
}
@@ -669,7 +669,7 @@ static const match_table_t befs_tokens = {
};
static int
-parse_options(char *options, befs_mount_options * opts)
+parse_options(char *options, struct befs_mount_options *opts)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -769,7 +769,7 @@ static int
befs_fill_super(struct super_block *sb, void *data, int silent)
{
struct buffer_head *bh;
- befs_sb_info *befs_sb;
+ struct befs_sb_info *befs_sb;
befs_super_block *disk_sb;
struct inode *root;
long ret = -EINVAL;
diff --git a/fs/befs/super.c b/fs/befs/super.c
index ca40f828f64d..aeafc4d84278 100644
--- a/fs/befs/super.c
+++ b/fs/befs/super.c
@@ -24,7 +24,7 @@
int
befs_load_sb(struct super_block *sb, befs_super_block * disk_sb)
{
- befs_sb_info *befs_sb = BEFS_SB(sb);
+ struct befs_sb_info *befs_sb = BEFS_SB(sb);
/* Check the byte order of the filesystem */
if (disk_sb->fs_byte_order == BEFS_BYTEORDER_NATIVE_LE)
@@ -59,7 +59,7 @@ befs_load_sb(struct super_block *sb, befs_super_block * disk_sb)
int
befs_check_sb(struct super_block *sb)
{
- befs_sb_info *befs_sb = BEFS_SB(sb);
+ struct befs_sb_info *befs_sb = BEFS_SB(sb);
/* Check magic headers of super block */
if ((befs_sb->magic1 != BEFS_SUPER_MAGIC1)
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 08063ae0a17c..3ec6113146c0 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -86,7 +86,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
inode = new_inode(s);
if (!inode)
- return -ENOSPC;
+ return -ENOMEM;
mutex_lock(&info->bfs_lock);
ino = find_first_zero_bit(info->si_imap, info->si_lasti + 1);
if (ino > info->si_lasti) {
@@ -153,7 +153,7 @@ static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
static int bfs_link(struct dentry *old, struct inode *dir,
struct dentry *new)
{
- struct inode *inode = old->d_inode;
+ struct inode *inode = d_inode(old);
struct bfs_sb_info *info = BFS_SB(inode->i_sb);
int err;
@@ -176,7 +176,7 @@ static int bfs_link(struct dentry *old, struct inode *dir,
static int bfs_unlink(struct inode *dir, struct dentry *dentry)
{
int error = -ENOENT;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct buffer_head *bh;
struct bfs_dirent *de;
struct bfs_sb_info *info = BFS_SB(inode->i_sb);
@@ -216,7 +216,7 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
int error = -ENOENT;
old_bh = new_bh = NULL;
- old_inode = old_dentry->d_inode;
+ old_inode = d_inode(old_dentry);
if (S_ISDIR(old_inode->i_mode))
return -EINVAL;
@@ -231,7 +231,7 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto end_rename;
error = -EPERM;
- new_inode = new_dentry->d_inode;
+ new_inode = d_inode(new_dentry);
new_bh = bfs_find_entry(new_dir,
new_dentry->d_name.name,
new_dentry->d_name.len, &new_de);
@@ -293,7 +293,7 @@ static int bfs_add_entry(struct inode *dir, const unsigned char *name,
for (block = sblock; block <= eblock; block++) {
bh = sb_bread(dir->i_sb, block);
if (!bh)
- return -ENOSPC;
+ return -EIO;
for (off = 0; off < BFS_BSIZE; off += BFS_DIRENT_SIZE) {
de = (struct bfs_dirent *)(bh->b_data + off);
if (!de->ino) {
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index e7f88ace1a25..97f1b5160155 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -23,9 +23,7 @@
const struct file_operations bfs_file_operations = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
.read_iter = generic_file_read_iter,
- .write = new_sync_write,
.write_iter = generic_file_write_iter,
.mmap = generic_file_mmap,
.splice_read = generic_file_splice_read,
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 90bc079d9982..fdcb4d69f430 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -15,6 +15,7 @@
#include <linux/buffer_head.h>
#include <linux/vfs.h>
#include <linux/writeback.h>
+#include <linux/uio.h>
#include <asm/uaccess.h>
#include "bfs.h"
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 995986b8e36b..241ef68d2893 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -31,6 +31,7 @@
#include <linux/security.h>
#include <linux/random.h>
#include <linux/elf.h>
+#include <linux/elf-randomize.h>
#include <linux/utsname.h>
#include <linux/coredump.h>
#include <linux/sched.h>
@@ -862,6 +863,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
unsigned long k, vaddr;
+ unsigned long total_size = 0;
if (elf_ppnt->p_type != PT_LOAD)
continue;
@@ -909,25 +911,20 @@ static int load_elf_binary(struct linux_binprm *bprm)
* default mmap base, as well as whatever program they
* might try to exec. This is because the brk will
* follow the loader, and is not movable. */
-#ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE
- /* Memory randomization might have been switched off
- * in runtime via sysctl or explicit setting of
- * personality flags.
- * If that is the case, retain the original non-zero
- * load_bias value in order to establish proper
- * non-randomized mappings.
- */
+ load_bias = ELF_ET_DYN_BASE - vaddr;
if (current->flags & PF_RANDOMIZE)
- load_bias = 0;
- else
- load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
-#else
- load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
-#endif
+ load_bias += arch_mmap_rnd();
+ load_bias = ELF_PAGESTART(load_bias);
+ total_size = total_mapping_size(elf_phdata,
+ loc->elf_ex.e_phnum);
+ if (!total_size) {
+ error = -EINVAL;
+ goto out_free_dentry;
+ }
}
error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
- elf_prot, elf_flags, 0);
+ elf_prot, elf_flags, total_size);
if (BAD_ADDR(error)) {
retval = IS_ERR((void *)error) ?
PTR_ERR((void*)error) : -EINVAL;
@@ -1053,15 +1050,13 @@ static int load_elf_binary(struct linux_binprm *bprm)
current->mm->end_data = end_data;
current->mm->start_stack = bprm->p;
-#ifdef arch_randomize_brk
if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
current->mm->brk = current->mm->start_brk =
arch_randomize_brk(current->mm);
-#ifdef CONFIG_COMPAT_BRK
+#ifdef compat_brk_randomized
current->brk_randomized = 1;
#endif
}
-#endif
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 97aff2879cda..78f005f37847 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -9,6 +9,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
@@ -521,9 +522,8 @@ static int parse_command(const char __user *buffer, size_t count)
static void entry_status(Node *e, char *page)
{
- char *dp;
- char *status = "disabled";
- const char *flags = "flags: ";
+ char *dp = page;
+ const char *status = "disabled";
if (test_bit(Enabled, &e->flags))
status = "enabled";
@@ -533,12 +533,10 @@ static void entry_status(Node *e, char *page)
return;
}
- sprintf(page, "%s\ninterpreter %s\n", status, e->interpreter);
- dp = page + strlen(page);
+ dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter);
/* print the special flags */
- sprintf(dp, "%s", flags);
- dp += strlen(flags);
+ dp += sprintf(dp, "flags: ");
if (e->flags & MISC_FMT_PRESERVE_ARGV0)
*dp++ = 'P';
if (e->flags & MISC_FMT_OPEN_BINARY)
@@ -550,21 +548,11 @@ static void entry_status(Node *e, char *page)
if (!test_bit(Magic, &e->flags)) {
sprintf(dp, "extension .%s\n", e->magic);
} else {
- int i;
-
- sprintf(dp, "offset %i\nmagic ", e->offset);
- dp = page + strlen(page);
- for (i = 0; i < e->size; i++) {
- sprintf(dp, "%02x", 0xff & (int) (e->magic[i]));
- dp += 2;
- }
+ dp += sprintf(dp, "offset %i\nmagic ", e->offset);
+ dp = bin2hex(dp, e->magic, e->size);
if (e->mask) {
- sprintf(dp, "\nmask ");
- dp += 6;
- for (i = 0; i < e->size; i++) {
- sprintf(dp, "%02x", 0xff & (int) (e->mask[i]));
- dp += 2;
- }
+ dp += sprintf(dp, "\nmask ");
+ dp = bin2hex(dp, e->mask, e->size);
}
*dp++ = '\n';
*dp = '\0';
@@ -603,7 +591,7 @@ static void kill_node(Node *e)
write_unlock(&entries_lock);
if (dentry) {
- drop_nlink(dentry->d_inode);
+ drop_nlink(d_inode(dentry));
d_drop(dentry);
dput(dentry);
simple_release_fs(&bm_mnt, &entry_count);
@@ -650,11 +638,11 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
case 3:
/* Delete this handler. */
root = dget(file->f_path.dentry->d_sb->s_root);
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
kill_node(e);
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
dput(root);
break;
default:
@@ -687,14 +675,14 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
return PTR_ERR(e);
root = dget(sb->s_root);
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
dentry = lookup_one_len(e->name, root, strlen(e->name));
err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out;
err = -EEXIST;
- if (dentry->d_inode)
+ if (d_really_is_positive(dentry))
goto out2;
inode = bm_get_inode(sb, S_IFREG | 0644);
@@ -723,7 +711,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
out2:
dput(dentry);
out:
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
dput(root);
if (err) {
@@ -766,12 +754,12 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer,
case 3:
/* Delete all handlers. */
root = dget(file->f_path.dentry->d_sb->s_root);
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
while (!list_empty(&entries))
kill_node(list_entry(entries.next, Node, list));
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
dput(root);
break;
default:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 975266be67d3..c7e4163ede87 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -27,7 +27,6 @@
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/cleancache.h>
-#include <linux/aio.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -147,15 +146,14 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
}
static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter,
- offset, blkdev_get_block,
- NULL, NULL, 0);
+ return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
+ blkdev_get_block, NULL, NULL,
+ DIO_SKIP_DIO_COUNT);
}
int __sync_blockdev(struct block_device *bdev, int wait)
@@ -1598,9 +1596,22 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
+ struct inode *bd_inode = file->f_mapping->host;
+ loff_t size = i_size_read(bd_inode);
struct blk_plug plug;
ssize_t ret;
+ if (bdev_read_only(I_BDEV(bd_inode)))
+ return -EPERM;
+
+ if (!iov_iter_count(from))
+ return 0;
+
+ if (iocb->ki_pos >= size)
+ return -ENOSPC;
+
+ iov_iter_truncate(from, size - iocb->ki_pos);
+
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
if (ret > 0) {
@@ -1660,8 +1671,6 @@ const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
.mmap = generic_file_mmap,
@@ -1708,7 +1717,7 @@ struct block_device *lookup_bdev(const char *pathname)
if (error)
return ERR_PTR(error);
- inode = path.dentry->d_inode;
+ inode = d_backing_inode(path.dentry);
error = -ENOTBLK;
if (!S_ISBLK(inode->i_mode))
goto fail;
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 37d164540c3a..8d052209f473 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -152,7 +152,7 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
static struct dentry *btrfs_get_parent(struct dentry *child)
{
- struct inode *dir = child->d_inode;
+ struct inode *dir = d_inode(child);
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_path *path;
struct extent_buffer *leaf;
@@ -220,8 +220,8 @@ fail:
static int btrfs_get_name(struct dentry *parent, char *name,
struct dentry *child)
{
- struct inode *inode = child->d_inode;
- struct inode *dir = parent->d_inode;
+ struct inode *inode = d_inode(child);
+ struct inode *dir = d_inode(parent);
struct btrfs_path *path;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_inode_ref *iref;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 23b6e03f8465..b072e17479aa 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,7 +24,6 @@
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
-#include <linux/aio.h>
#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/writeback.h>
@@ -32,6 +31,7 @@
#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/btrfs.h>
+#include <linux/uio.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@@ -1735,27 +1735,19 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
u64 start_pos;
u64 end_pos;
ssize_t num_written = 0;
- ssize_t err = 0;
- size_t count = iov_iter_count(from);
bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
- loff_t pos = iocb->ki_pos;
+ ssize_t err;
+ loff_t pos;
+ size_t count;
mutex_lock(&inode->i_mutex);
-
- current->backing_dev_info = inode_to_bdi(inode);
- err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
- if (err) {
+ err = generic_write_checks(iocb, from);
+ if (err <= 0) {
mutex_unlock(&inode->i_mutex);
- goto out;
- }
-
- if (count == 0) {
- mutex_unlock(&inode->i_mutex);
- goto out;
+ return err;
}
- iov_iter_truncate(from, count);
-
+ current->backing_dev_info = inode_to_bdi(inode);
err = file_remove_suid(file);
if (err) {
mutex_unlock(&inode->i_mutex);
@@ -1782,6 +1774,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
*/
update_time_for_write(inode);
+ pos = iocb->ki_pos;
+ count = iov_iter_count(from);
start_pos = round_down(pos, root->sectorsize);
if (start_pos > i_size_read(inode)) {
/* Expand hole size to cover write data, preventing empty gap */
@@ -1796,7 +1790,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
if (sync)
atomic_inc(&BTRFS_I(inode)->sync_writers);
- if (file->f_flags & O_DIRECT) {
+ if (iocb->ki_flags & IOCB_DIRECT) {
num_written = __btrfs_direct_write(iocb, from, pos);
} else {
num_written = __btrfs_buffered_write(file, from, pos);
@@ -1868,7 +1862,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct dentry *dentry = file->f_path.dentry;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
struct btrfs_log_ctx ctx;
@@ -2807,8 +2801,6 @@ out:
const struct file_operations btrfs_file_operations = {
.llseek = btrfs_file_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = generic_file_read_iter,
.splice_read = generic_file_splice_read,
.write_iter = btrfs_file_write_iter,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0020b5675fa9..8bb013672aee 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -32,7 +32,6 @@
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
-#include <linux/aio.h>
#include <linux/bit_spinlock.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
@@ -4024,16 +4023,16 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
{
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_trans_handle *trans;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int ret;
trans = __unlink_start_trans(dir);
if (IS_ERR(trans))
return PTR_ERR(trans);
- btrfs_record_unlink_dir(trans, dir, dentry->d_inode, 0);
+ btrfs_record_unlink_dir(trans, dir, d_inode(dentry), 0);
- ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
+ ret = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
dentry->d_name.name, dentry->d_name.len);
if (ret)
goto out;
@@ -4132,7 +4131,7 @@ out:
static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int err = 0;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_trans_handle *trans;
@@ -4159,7 +4158,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
goto out;
/* now the directory is empty */
- err = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
+ err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
dentry->d_name.name, dentry->d_name.len);
if (!err)
btrfs_i_size_write(inode, 0);
@@ -4919,7 +4918,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct btrfs_root *root = BTRFS_I(inode)->root;
int err;
@@ -5551,10 +5550,10 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
static int btrfs_dentry_delete(const struct dentry *dentry)
{
struct btrfs_root *root;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
if (!inode && !IS_ROOT(dentry))
- inode = dentry->d_parent->d_inode;
+ inode = d_inode(dentry->d_parent);
if (inode) {
root = BTRFS_I(inode)->root;
@@ -6361,7 +6360,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
u64 index;
int err;
int drop_inode = 0;
@@ -8216,7 +8215,7 @@ free_ordered:
bio_endio(dio_bio, ret);
}
-static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb,
+static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb,
const struct iov_iter *iter, loff_t offset)
{
int seg;
@@ -8231,7 +8230,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
goto out;
/* If this is a write we don't need to check anymore */
- if (rw & WRITE)
+ if (iov_iter_rw(iter) == WRITE)
return 0;
/*
* Check to make sure we don't have duplicate iov_base's in this
@@ -8249,8 +8248,8 @@ out:
return retval;
}
-static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
- struct iov_iter *iter, loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -8261,10 +8260,10 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
bool relock = false;
ssize_t ret;
- if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset))
+ if (check_direct_IO(BTRFS_I(inode)->root, iocb, iter, offset))
return 0;
- atomic_inc(&inode->i_dio_count);
+ inode_dio_begin(inode);
smp_mb__after_atomic();
/*
@@ -8279,7 +8278,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
filemap_fdatawrite_range(inode->i_mapping, offset,
offset + count - 1);
- if (rw & WRITE) {
+ if (iov_iter_rw(iter) == WRITE) {
/*
* If the write DIO is beyond the EOF, we need update
* the isize, but it is protected by i_mutex. So we can
@@ -8304,16 +8303,16 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
current->journal_info = &outstanding_extents;
} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags)) {
- inode_dio_done(inode);
+ inode_dio_end(inode);
flags = DIO_LOCKING | DIO_SKIP_HOLES;
wakeup = false;
}
- ret = __blockdev_direct_IO(rw, iocb, inode,
- BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iter, offset, btrfs_get_blocks_direct, NULL,
- btrfs_submit_direct, flags);
- if (rw & WRITE) {
+ ret = __blockdev_direct_IO(iocb, inode,
+ BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
+ iter, offset, btrfs_get_blocks_direct, NULL,
+ btrfs_submit_direct, flags);
+ if (iov_iter_rw(iter) == WRITE) {
current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED)
btrfs_delalloc_release_space(inode, count);
@@ -8323,7 +8322,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
}
out:
if (wakeup)
- inode_dio_done(inode);
+ inode_dio_end(inode);
if (relock)
mutex_lock(&inode->i_mutex);
@@ -9010,7 +9009,7 @@ static int btrfs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
u64 delalloc_bytes;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
u32 blocksize = inode->i_sb->s_blocksize;
generic_fillattr(inode, stat);
@@ -9031,8 +9030,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_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 inode *new_inode = d_inode(new_dentry);
+ struct inode *old_inode = d_inode(old_dentry);
struct timespec ctime = CURRENT_TIME;
u64 index = 0;
u64 root_objectid;
@@ -9144,7 +9143,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
old_dentry->d_name.len);
} else {
ret = __btrfs_unlink_inode(trans, root, old_dir,
- old_dentry->d_inode,
+ d_inode(old_dentry),
old_dentry->d_name.name,
old_dentry->d_name.len);
if (!ret)
@@ -9168,12 +9167,12 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
BUG_ON(new_inode->i_nlink == 0);
} else {
ret = btrfs_unlink_inode(trans, dest, new_dir,
- new_dentry->d_inode,
+ d_inode(new_dentry),
new_dentry->d_name.name,
new_dentry->d_name.len);
}
if (!ret && new_inode->i_nlink == 0)
- ret = btrfs_orphan_add(trans, new_dentry->d_inode);
+ ret = btrfs_orphan_add(trans, d_inode(new_dentry));
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto out_fail;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index cdcd98ceddea..1c22c6518504 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -724,7 +724,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (ret)
goto fail;
- inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
+ inode = btrfs_lookup_dentry(d_inode(dentry->d_parent), dentry);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto fail;
@@ -768,10 +768,10 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
{
int error;
- if (!victim->d_inode)
+ if (d_really_is_negative(victim))
return -ENOENT;
- BUG_ON(victim->d_parent->d_inode != dir);
+ BUG_ON(d_inode(victim->d_parent) != dir);
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
@@ -779,8 +779,8 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
return error;
if (IS_APPEND(dir))
return -EPERM;
- if (check_sticky(dir, victim->d_inode) || IS_APPEND(victim->d_inode) ||
- IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
+ if (check_sticky(dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) ||
+ IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim)))
return -EPERM;
if (isdir) {
if (!d_is_dir(victim))
@@ -799,7 +799,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
/* copy of may_create in fs/namei.c() */
static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
{
- if (child->d_inode)
+ if (d_really_is_positive(child))
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
@@ -817,7 +817,7 @@ static noinline int btrfs_mksubvol(struct path *parent,
u64 *async_transid, bool readonly,
struct btrfs_qgroup_inherit *inherit)
{
- struct inode *dir = parent->dentry->d_inode;
+ struct inode *dir = d_inode(parent->dentry);
struct dentry *dentry;
int error;
@@ -831,7 +831,7 @@ static noinline int btrfs_mksubvol(struct path *parent,
goto out_unlock;
error = -EEXIST;
- if (dentry->d_inode)
+ if (d_really_is_positive(dentry))
goto out_dput;
error = btrfs_may_create(dir, dentry);
@@ -2301,7 +2301,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
{
struct dentry *parent = file->f_path.dentry;
struct dentry *dentry;
- struct inode *dir = parent->d_inode;
+ struct inode *dir = d_inode(parent);
struct inode *inode;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *dest = NULL;
@@ -2340,12 +2340,12 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
goto out_unlock_dir;
}
- if (!dentry->d_inode) {
+ if (d_really_is_negative(dentry)) {
err = -ENOENT;
goto out_dput;
}
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
dest = BTRFS_I(inode)->root;
if (!capable(CAP_SYS_ADMIN)) {
/*
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f2c9f9db3b19..9e66f5e724db 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -925,7 +925,7 @@ setup_root:
* a reference to the dentry. We will have already gotten a reference
* to the inode in btrfs_fill_super so we're good to go.
*/
- if (!new && sb->s_root->d_inode == inode) {
+ if (!new && d_inode(sb->s_root) == inode) {
iput(inode);
return dget(sb->s_root);
}
@@ -1230,7 +1230,7 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
root = mount_subtree(mnt, subvol_name);
- if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) {
+ if (!IS_ERR(root) && !is_subvolume_inode(d_inode(root))) {
struct super_block *s = root->d_sb;
dput(root);
root = ERR_PTR(-EINVAL);
@@ -1895,8 +1895,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
/* Mask in the root object ID too, to disambiguate subvols */
- buf->f_fsid.val[0] ^= BTRFS_I(dentry->d_inode)->root->objectid >> 32;
- buf->f_fsid.val[1] ^= BTRFS_I(dentry->d_inode)->root->objectid;
+ buf->f_fsid.val[0] ^= BTRFS_I(d_inode(dentry))->root->objectid >> 32;
+ buf->f_fsid.val[1] ^= BTRFS_I(d_inode(dentry))->root->objectid;
return 0;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index a089b5944efc..d04968374e9d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4474,9 +4474,9 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
goto out;
if (!S_ISDIR(inode->i_mode)) {
- if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
goto out;
- inode = parent->d_inode;
+ inode = d_inode(parent);
}
while (1) {
@@ -4502,7 +4502,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
break;
}
- if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
break;
if (IS_ROOT(parent))
@@ -4511,7 +4511,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
parent = dget_parent(parent);
dput(old_parent);
old_parent = parent;
- inode = parent->d_inode;
+ inode = d_inode(parent);
}
dput(old_parent);
@@ -4777,10 +4777,10 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
log_dentries = true;
while (1) {
- if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
break;
- inode = parent->d_inode;
+ inode = d_inode(parent);
if (root != BTRFS_I(inode)->root)
break;
@@ -4845,7 +4845,7 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
struct dentry *parent = dget_parent(dentry);
int ret;
- ret = btrfs_log_inode_parent(trans, root, dentry->d_inode, parent,
+ ret = btrfs_log_inode_parent(trans, root, d_inode(dentry), parent,
start, end, 0, ctx);
dput(parent);
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 45ea704be030..6f518c90e1c1 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -261,7 +261,7 @@ out:
ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
struct btrfs_key key, found_key;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
struct extent_buffer *leaf;
@@ -411,13 +411,13 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
ret = btrfs_is_valid_xattr(name);
if (ret)
return ret;
- return __btrfs_getxattr(dentry->d_inode, name, buffer, size);
+ return __btrfs_getxattr(d_inode(dentry), name, buffer, size);
}
int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags)
{
- struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
int ret;
/*
@@ -440,19 +440,19 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
return ret;
if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
- return btrfs_set_prop(dentry->d_inode, name,
+ return btrfs_set_prop(d_inode(dentry), name,
value, size, flags);
if (size == 0)
value = ""; /* empty EA, do not remove */
- return __btrfs_setxattr(NULL, dentry->d_inode, name, value, size,
+ return __btrfs_setxattr(NULL, d_inode(dentry), name, value, size,
flags);
}
int btrfs_removexattr(struct dentry *dentry, const char *name)
{
- struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
int ret;
/*
@@ -475,10 +475,10 @@ int btrfs_removexattr(struct dentry *dentry, const char *name)
return ret;
if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
- return btrfs_set_prop(dentry->d_inode, name,
+ return btrfs_set_prop(d_inode(dentry), name,
NULL, 0, XATTR_REPLACE);
- return __btrfs_setxattr(NULL, dentry->d_inode, name, NULL, 0,
+ return __btrfs_setxattr(NULL, d_inode(dentry), name, NULL, 0,
XATTR_REPLACE);
}
diff --git a/fs/buffer.c b/fs/buffer.c
index 20805db2c987..c7a5602d01ee 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3243,8 +3243,8 @@ int try_to_free_buffers(struct page *page)
* to synchronise against __set_page_dirty_buffers and prevent the
* dirty bit from being lost.
*/
- if (ret)
- cancel_dirty_page(page, PAGE_CACHE_SIZE);
+ if (ret && TestClearPageDirty(page))
+ account_page_cleaned(page, mapping);
spin_unlock(&mapping->private_lock);
out:
if (buffers_to_free) {
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index fbb08e97438d..6af790fc3df8 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -123,11 +123,11 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
/* check parameters */
ret = -EOPNOTSUPP;
- if (!root->d_inode ||
- !root->d_inode->i_op->lookup ||
- !root->d_inode->i_op->mkdir ||
- !root->d_inode->i_op->setxattr ||
- !root->d_inode->i_op->getxattr ||
+ if (d_is_negative(root) ||
+ !d_backing_inode(root)->i_op->lookup ||
+ !d_backing_inode(root)->i_op->mkdir ||
+ !d_backing_inode(root)->i_op->setxattr ||
+ !d_backing_inode(root)->i_op->getxattr ||
!root->d_sb->s_op->statfs ||
!root->d_sb->s_op->sync_fs)
goto error_unsupported;
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 232426214fdd..afa023dded5b 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -441,12 +441,12 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
fscache_set_store_limit(&object->fscache, ni_size);
- oi_size = i_size_read(object->backer->d_inode);
+ oi_size = i_size_read(d_backing_inode(object->backer));
if (oi_size == ni_size)
return 0;
cachefiles_begin_secure(cache, &saved_cred);
- mutex_lock(&object->backer->d_inode->i_mutex);
+ mutex_lock(&d_inode(object->backer)->i_mutex);
/* if there's an extension to a partial page at the end of the backing
* file, we need to discard the partial page so that we pick up new
@@ -465,7 +465,7 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
ret = notify_change(object->backer, &newattrs, NULL);
truncate_failed:
- mutex_unlock(&object->backer->d_inode->i_mutex);
+ mutex_unlock(&d_inode(object->backer)->i_mutex);
cachefiles_end_secure(cache, saved_cred);
if (ret == -EIO) {
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 1e51714eb33e..ab857ab9f40d 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -286,13 +286,13 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
if (ret < 0) {
cachefiles_io_error(cache, "Unlink security error");
} else {
- ret = vfs_unlink(dir->d_inode, rep, NULL);
+ ret = vfs_unlink(d_inode(dir), rep, NULL);
if (preemptive)
cachefiles_mark_object_buried(cache, rep);
}
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
if (ret == -EIO)
cachefiles_io_error(cache, "Unlink failed");
@@ -303,7 +303,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
/* directories have to be moved to the graveyard */
_debug("move stale object to graveyard");
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
try_again:
/* first step is to make up a grave dentry in the graveyard */
@@ -355,7 +355,7 @@ try_again:
return -EIO;
}
- if (grave->d_inode) {
+ if (d_is_positive(grave)) {
unlock_rename(cache->graveyard, dir);
dput(grave);
grave = NULL;
@@ -387,8 +387,8 @@ try_again:
if (ret < 0) {
cachefiles_io_error(cache, "Rename security error %d", ret);
} else {
- ret = vfs_rename(dir->d_inode, rep,
- cache->graveyard->d_inode, grave, NULL, 0);
+ ret = vfs_rename(d_inode(dir), rep,
+ d_inode(cache->graveyard), grave, NULL, 0);
if (ret != 0 && ret != -ENOMEM)
cachefiles_io_error(cache,
"Rename failed with error %d", ret);
@@ -415,18 +415,18 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
_enter(",OBJ%x{%p}", object->fscache.debug_id, object->dentry);
ASSERT(object->dentry);
- ASSERT(object->dentry->d_inode);
+ ASSERT(d_backing_inode(object->dentry));
ASSERT(object->dentry->d_parent);
dir = dget_parent(object->dentry);
- mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
if (test_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
/* object allocation for the same key preemptively deleted this
* object's file so that it could create its own file */
_debug("object preemptively buried");
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
ret = 0;
} else {
/* we need to check that our parent is _still_ our parent - it
@@ -438,7 +438,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
/* it got moved, presumably by cachefilesd culling it,
* so it's no longer in the key path and we can ignore
* it */
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
ret = 0;
}
}
@@ -473,7 +473,7 @@ int cachefiles_walk_to_object(struct cachefiles_object *parent,
path.mnt = cache->mnt;
ASSERT(parent->dentry);
- ASSERT(parent->dentry->d_inode);
+ ASSERT(d_backing_inode(parent->dentry));
if (!(d_is_dir(parent->dentry))) {
// TODO: convert file to dir
@@ -497,7 +497,7 @@ lookup_again:
/* search the current directory for the element name */
_debug("lookup '%s'", name);
- mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
start = jiffies;
next = lookup_one_len(name, dir, nlen);
@@ -505,21 +505,21 @@ lookup_again:
if (IS_ERR(next))
goto lookup_error;
- _debug("next -> %p %s", next, next->d_inode ? "positive" : "negative");
+ _debug("next -> %p %s", next, d_backing_inode(next) ? "positive" : "negative");
if (!key)
- object->new = !next->d_inode;
+ object->new = !d_backing_inode(next);
/* if this element of the path doesn't exist, then the lookup phase
* failed, and we can release any readers in the certain knowledge that
* there's nothing for them to actually read */
- if (!next->d_inode)
+ if (d_is_negative(next))
fscache_object_lookup_negative(&object->fscache);
/* we need to create the object if it's negative */
if (key || object->type == FSCACHE_COOKIE_TYPE_INDEX) {
/* index objects and intervening tree levels must be subdirs */
- if (!next->d_inode) {
+ if (d_is_negative(next)) {
ret = cachefiles_has_space(cache, 1, 0);
if (ret < 0)
goto create_error;
@@ -529,26 +529,26 @@ lookup_again:
if (ret < 0)
goto create_error;
start = jiffies;
- ret = vfs_mkdir(dir->d_inode, next, 0);
+ ret = vfs_mkdir(d_inode(dir), next, 0);
cachefiles_hist(cachefiles_mkdir_histogram, start);
if (ret < 0)
goto create_error;
- ASSERT(next->d_inode);
+ ASSERT(d_backing_inode(next));
_debug("mkdir -> %p{%p{ino=%lu}}",
- next, next->d_inode, next->d_inode->i_ino);
+ next, d_backing_inode(next), d_backing_inode(next)->i_ino);
} else if (!d_can_lookup(next)) {
pr_err("inode %lu is not a directory\n",
- next->d_inode->i_ino);
+ d_backing_inode(next)->i_ino);
ret = -ENOBUFS;
goto error;
}
} else {
/* non-index objects start out life as files */
- if (!next->d_inode) {
+ if (d_is_negative(next)) {
ret = cachefiles_has_space(cache, 1, 0);
if (ret < 0)
goto create_error;
@@ -558,21 +558,21 @@ lookup_again:
if (ret < 0)
goto create_error;
start = jiffies;
- ret = vfs_create(dir->d_inode, next, S_IFREG, true);
+ ret = vfs_create(d_inode(dir), next, S_IFREG, true);
cachefiles_hist(cachefiles_create_histogram, start);
if (ret < 0)
goto create_error;
- ASSERT(next->d_inode);
+ ASSERT(d_backing_inode(next));
_debug("create -> %p{%p{ino=%lu}}",
- next, next->d_inode, next->d_inode->i_ino);
+ next, d_backing_inode(next), d_backing_inode(next)->i_ino);
} else if (!d_can_lookup(next) &&
!d_is_reg(next)
) {
pr_err("inode %lu is not a file or directory\n",
- next->d_inode->i_ino);
+ d_backing_inode(next)->i_ino);
ret = -ENOBUFS;
goto error;
}
@@ -581,7 +581,7 @@ lookup_again:
/* process the next component */
if (key) {
_debug("advance");
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(dir);
dir = next;
next = NULL;
@@ -617,7 +617,7 @@ lookup_again:
/* note that we're now using this object */
ret = cachefiles_mark_object_active(cache, object);
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(dir);
dir = NULL;
@@ -646,7 +646,7 @@ lookup_again:
const struct address_space_operations *aops;
ret = -EPERM;
- aops = object->dentry->d_inode->i_mapping->a_ops;
+ aops = d_backing_inode(object->dentry)->i_mapping->a_ops;
if (!aops->bmap)
goto check_error;
@@ -659,7 +659,7 @@ lookup_again:
object->new = 0;
fscache_obtained_object(&object->fscache);
- _leave(" = 0 [%lu]", object->dentry->d_inode->i_ino);
+ _leave(" = 0 [%lu]", d_backing_inode(object->dentry)->i_ino);
return 0;
create_error:
@@ -695,7 +695,7 @@ lookup_error:
cachefiles_io_error(cache, "Lookup failed");
next = NULL;
error:
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(next);
error_out2:
dput(dir);
@@ -719,7 +719,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
_enter(",,%s", dirname);
/* search the current directory for the element name */
- mutex_lock(&dir->d_inode->i_mutex);
+ mutex_lock(&d_inode(dir)->i_mutex);
start = jiffies;
subdir = lookup_one_len(dirname, dir, strlen(dirname));
@@ -731,10 +731,10 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
}
_debug("subdir -> %p %s",
- subdir, subdir->d_inode ? "positive" : "negative");
+ subdir, d_backing_inode(subdir) ? "positive" : "negative");
/* we need to create the subdir if it doesn't exist yet */
- if (!subdir->d_inode) {
+ if (d_is_negative(subdir)) {
ret = cachefiles_has_space(cache, 1, 0);
if (ret < 0)
goto mkdir_error;
@@ -746,22 +746,22 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
ret = security_path_mkdir(&path, subdir, 0700);
if (ret < 0)
goto mkdir_error;
- ret = vfs_mkdir(dir->d_inode, subdir, 0700);
+ ret = vfs_mkdir(d_inode(dir), subdir, 0700);
if (ret < 0)
goto mkdir_error;
- ASSERT(subdir->d_inode);
+ ASSERT(d_backing_inode(subdir));
_debug("mkdir -> %p{%p{ino=%lu}}",
subdir,
- subdir->d_inode,
- subdir->d_inode->i_ino);
+ d_backing_inode(subdir),
+ d_backing_inode(subdir)->i_ino);
}
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
/* we need to make sure the subdir is a directory */
- ASSERT(subdir->d_inode);
+ ASSERT(d_backing_inode(subdir));
if (!d_can_lookup(subdir)) {
pr_err("%s is not a directory\n", dirname);
@@ -770,18 +770,18 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
}
ret = -EPERM;
- if (!subdir->d_inode->i_op->setxattr ||
- !subdir->d_inode->i_op->getxattr ||
- !subdir->d_inode->i_op->lookup ||
- !subdir->d_inode->i_op->mkdir ||
- !subdir->d_inode->i_op->create ||
- (!subdir->d_inode->i_op->rename &&
- !subdir->d_inode->i_op->rename2) ||
- !subdir->d_inode->i_op->rmdir ||
- !subdir->d_inode->i_op->unlink)
+ if (!d_backing_inode(subdir)->i_op->setxattr ||
+ !d_backing_inode(subdir)->i_op->getxattr ||
+ !d_backing_inode(subdir)->i_op->lookup ||
+ !d_backing_inode(subdir)->i_op->mkdir ||
+ !d_backing_inode(subdir)->i_op->create ||
+ (!d_backing_inode(subdir)->i_op->rename &&
+ !d_backing_inode(subdir)->i_op->rename2) ||
+ !d_backing_inode(subdir)->i_op->rmdir ||
+ !d_backing_inode(subdir)->i_op->unlink)
goto check_error;
- _leave(" = [%lu]", subdir->d_inode->i_ino);
+ _leave(" = [%lu]", d_backing_inode(subdir)->i_ino);
return subdir;
check_error:
@@ -790,19 +790,19 @@ check_error:
return ERR_PTR(ret);
mkdir_error:
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(subdir);
pr_err("mkdir %s failed with error %d\n", dirname, ret);
return ERR_PTR(ret);
lookup_error:
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
ret = PTR_ERR(subdir);
pr_err("Lookup %s failed with error %d\n", dirname, ret);
return ERR_PTR(ret);
nomem_d_alloc:
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
_leave(" = -ENOMEM");
return ERR_PTR(-ENOMEM);
}
@@ -827,7 +827,7 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
// dir, filename);
/* look up the victim */
- mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
start = jiffies;
victim = lookup_one_len(filename, dir, strlen(filename));
@@ -836,13 +836,13 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
goto lookup_error;
//_debug("victim -> %p %s",
- // victim, victim->d_inode ? "positive" : "negative");
+ // victim, d_backing_inode(victim) ? "positive" : "negative");
/* if the object is no longer there then we probably retired the object
* at the netfs's request whilst the cull was in progress
*/
- if (!victim->d_inode) {
- mutex_unlock(&dir->d_inode->i_mutex);
+ if (d_is_negative(victim)) {
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(victim);
_leave(" = -ENOENT [absent]");
return ERR_PTR(-ENOENT);
@@ -871,13 +871,13 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
object_in_use:
read_unlock(&cache->active_lock);
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(victim);
//_leave(" = -EBUSY [in use]");
return ERR_PTR(-EBUSY);
lookup_error:
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
ret = PTR_ERR(victim);
if (ret == -ENOENT) {
/* file or dir now absent - probably retired by netfs */
@@ -913,7 +913,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
return PTR_ERR(victim);
_debug("victim -> %p %s",
- victim, victim->d_inode ? "positive" : "negative");
+ victim, d_backing_inode(victim) ? "positive" : "negative");
/* okay... the victim is not being used so we can cull it
* - start by marking it as stale
@@ -936,7 +936,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
return 0;
error_unlock:
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
error:
dput(victim);
if (ret == -ENOENT) {
@@ -971,7 +971,7 @@ int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
if (IS_ERR(victim))
return PTR_ERR(victim);
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(victim);
//_leave(" = 0");
return 0;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index c6cd8d7a4eef..3cbb0e834694 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -74,12 +74,12 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
static int cachefiles_read_reissue(struct cachefiles_object *object,
struct cachefiles_one_read *monitor)
{
- struct address_space *bmapping = object->backer->d_inode->i_mapping;
+ struct address_space *bmapping = d_backing_inode(object->backer)->i_mapping;
struct page *backpage = monitor->back_page, *backpage2;
int ret;
_enter("{ino=%lx},{%lx,%lx}",
- object->backer->d_inode->i_ino,
+ d_backing_inode(object->backer)->i_ino,
backpage->index, backpage->flags);
/* skip if the page was truncated away completely */
@@ -157,7 +157,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
object = container_of(op->op.object,
struct cachefiles_object, fscache);
- _enter("{ino=%lu}", object->backer->d_inode->i_ino);
+ _enter("{ino=%lu}", d_backing_inode(object->backer)->i_ino);
max = 8;
spin_lock_irq(&object->work_lock);
@@ -247,7 +247,7 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
init_waitqueue_func_entry(&monitor->monitor, cachefiles_read_waiter);
/* attempt to get hold of the backing page */
- bmapping = object->backer->d_inode->i_mapping;
+ bmapping = d_backing_inode(object->backer)->i_mapping;
newpage = NULL;
for (;;) {
@@ -408,7 +408,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
if (!object->backer)
goto enobufs;
- inode = object->backer->d_inode;
+ inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
ASSERT(inode->i_mapping->a_ops->bmap);
ASSERT(inode->i_mapping->a_ops->readpages);
@@ -468,7 +468,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
struct list_head *list)
{
struct cachefiles_one_read *monitor = NULL;
- struct address_space *bmapping = object->backer->d_inode->i_mapping;
+ struct address_space *bmapping = d_backing_inode(object->backer)->i_mapping;
struct page *newpage = NULL, *netpage, *_n, *backpage = NULL;
int ret = 0;
@@ -705,7 +705,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
if (cachefiles_has_space(cache, 0, *nr_pages) < 0)
space = 0;
- inode = object->backer->d_inode;
+ inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
ASSERT(inode->i_mapping->a_ops->bmap);
ASSERT(inode->i_mapping->a_ops->readpages);
diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c
index 396c18ea2764..31bbc0528b11 100644
--- a/fs/cachefiles/security.c
+++ b/fs/cachefiles/security.c
@@ -55,14 +55,14 @@ static int cachefiles_check_cache_dir(struct cachefiles_cache *cache,
{
int ret;
- ret = security_inode_mkdir(root->d_inode, root, 0);
+ ret = security_inode_mkdir(d_backing_inode(root), root, 0);
if (ret < 0) {
pr_err("Security denies permission to make dirs: error %d",
ret);
return ret;
}
- ret = security_inode_create(root->d_inode, root, 0);
+ ret = security_inode_create(d_backing_inode(root), root, 0);
if (ret < 0)
pr_err("Security denies permission to create files: error %d",
ret);
@@ -95,7 +95,7 @@ int cachefiles_determine_cache_security(struct cachefiles_cache *cache,
/* use the cache root dir's security context as the basis with
* which create files */
- ret = set_create_files_as(new, root->d_inode);
+ ret = set_create_files_as(new, d_backing_inode(root));
if (ret < 0) {
abort_creds(new);
cachefiles_begin_secure(cache, _saved_cred);
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index a8a68745e11d..d31c1a72d8a5 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -33,7 +33,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
int ret;
ASSERT(dentry);
- ASSERT(dentry->d_inode);
+ ASSERT(d_backing_inode(dentry));
if (!object->fscache.cookie)
strcpy(type, "C3");
@@ -52,7 +52,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
if (ret != -EEXIST) {
pr_err("Can't set xattr on %pd [%lu] (err %d)\n",
- dentry, dentry->d_inode->i_ino,
+ dentry, d_backing_inode(dentry)->i_ino,
-ret);
goto error;
}
@@ -64,7 +64,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
goto bad_type_length;
pr_err("Can't read xattr on %pd [%lu] (err %d)\n",
- dentry, dentry->d_inode->i_ino,
+ dentry, d_backing_inode(dentry)->i_ino,
-ret);
goto error;
}
@@ -84,14 +84,14 @@ error:
bad_type_length:
pr_err("Cache object %lu type xattr length incorrect\n",
- dentry->d_inode->i_ino);
+ d_backing_inode(dentry)->i_ino);
ret = -EIO;
goto error;
bad_type:
xtype[2] = 0;
pr_err("Cache object %pd [%lu] type %s not %s\n",
- dentry, dentry->d_inode->i_ino,
+ dentry, d_backing_inode(dentry)->i_ino,
xtype, type);
ret = -EIO;
goto error;
@@ -165,7 +165,7 @@ int cachefiles_check_auxdata(struct cachefiles_object *object)
int ret;
ASSERT(dentry);
- ASSERT(dentry->d_inode);
+ ASSERT(d_backing_inode(dentry));
ASSERT(object->fscache.cookie->def->check_aux);
auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
@@ -204,7 +204,7 @@ int cachefiles_check_object_xattr(struct cachefiles_object *object,
_enter("%p,#%d", object, auxdata->len);
ASSERT(dentry);
- ASSERT(dentry->d_inode);
+ ASSERT(d_backing_inode(dentry));
auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, cachefiles_gfp);
if (!auxbuf) {
@@ -225,7 +225,7 @@ int cachefiles_check_object_xattr(struct cachefiles_object *object,
cachefiles_io_error_obj(object,
"Can't read xattr on %lu (err %d)",
- dentry->d_inode->i_ino, -ret);
+ d_backing_inode(dentry)->i_ino, -ret);
goto error;
}
@@ -276,7 +276,7 @@ int cachefiles_check_object_xattr(struct cachefiles_object *object,
cachefiles_io_error_obj(object,
"Can't update xattr on %lu"
" (error %d)",
- dentry->d_inode->i_ino, -ret);
+ d_backing_inode(dentry)->i_ino, -ret);
goto error;
}
}
@@ -291,7 +291,7 @@ error:
bad_type_length:
pr_err("Cache object %lu xattr length incorrect\n",
- dentry->d_inode->i_ino);
+ d_backing_inode(dentry)->i_ino);
ret = -EIO;
goto error;
@@ -316,7 +316,7 @@ int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
cachefiles_io_error(cache,
"Can't remove xattr from %lu"
" (error %d)",
- dentry->d_inode->i_ino, -ret);
+ d_backing_inode(dentry)->i_ino, -ret);
}
_leave(" = %d", ret);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index fd5599d32362..e162bcd105ee 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1146,6 +1146,10 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
inode, page, (int)pos, (int)len);
r = ceph_update_writeable_page(file, pos, len, page);
+ if (r < 0)
+ page_cache_release(page);
+ else
+ *pagep = page;
} while (r == -EAGAIN);
return r;
@@ -1198,8 +1202,7 @@ 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(int rw, struct kiocb *iocb,
- struct iov_iter *iter,
+static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter,
loff_t pos)
{
WARN_ON(1);
@@ -1535,19 +1538,27 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
osd_req_op_extent_osd_data_pages(req, 1, &page, len, 0, false, false);
- err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR,
- "inline_version", &inline_version,
- sizeof(inline_version),
- CEPH_OSD_CMPXATTR_OP_GT,
- CEPH_OSD_CMPXATTR_MODE_U64);
- if (err)
- goto out_put;
-
- err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR,
- "inline_version", &inline_version,
- sizeof(inline_version), 0, 0);
- if (err)
- goto out_put;
+ {
+ __le64 xattr_buf = cpu_to_le64(inline_version);
+ err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR,
+ "inline_version", &xattr_buf,
+ sizeof(xattr_buf),
+ CEPH_OSD_CMPXATTR_OP_GT,
+ CEPH_OSD_CMPXATTR_MODE_U64);
+ if (err)
+ goto out_put;
+ }
+
+ {
+ char xattr_buf[32];
+ int xattr_len = snprintf(xattr_buf, sizeof(xattr_buf),
+ "%llu", inline_version);
+ err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR,
+ "inline_version",
+ xattr_buf, xattr_len, 0, 0);
+ if (err)
+ goto out_put;
+ }
ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 8172775428a0..be5ea6af8366 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -896,6 +896,18 @@ int ceph_is_any_caps(struct inode *inode)
return ret;
}
+static void drop_inode_snap_realm(struct ceph_inode_info *ci)
+{
+ struct ceph_snap_realm *realm = ci->i_snap_realm;
+ spin_lock(&realm->inodes_with_caps_lock);
+ list_del_init(&ci->i_snap_realm_item);
+ ci->i_snap_realm_counter++;
+ ci->i_snap_realm = NULL;
+ spin_unlock(&realm->inodes_with_caps_lock);
+ ceph_put_snap_realm(ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc,
+ realm);
+}
+
/*
* Remove a cap. Take steps to deal with a racing iterate_session_caps.
*
@@ -946,15 +958,13 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
if (removed)
ceph_put_cap(mdsc, cap);
- if (!__ceph_is_any_caps(ci) && ci->i_snap_realm) {
- struct ceph_snap_realm *realm = ci->i_snap_realm;
- spin_lock(&realm->inodes_with_caps_lock);
- list_del_init(&ci->i_snap_realm_item);
- ci->i_snap_realm_counter++;
- ci->i_snap_realm = NULL;
- spin_unlock(&realm->inodes_with_caps_lock);
- ceph_put_snap_realm(mdsc, realm);
- }
+ /* when reconnect denied, we remove session caps forcibly,
+ * i_wr_ref can be non-zero. If there are ongoing write,
+ * keep i_snap_realm.
+ */
+ if (!__ceph_is_any_caps(ci) && ci->i_wr_ref == 0 && ci->i_snap_realm)
+ drop_inode_snap_realm(ci);
+
if (!__ceph_is_any_real_caps(ci))
__cap_delay_cancel(mdsc, ci);
}
@@ -1394,6 +1404,13 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
int was = ci->i_dirty_caps;
int dirty = 0;
+ if (!ci->i_auth_cap) {
+ pr_warn("__mark_dirty_caps %p %llx mask %s, "
+ "but no auth cap (session was closed?)\n",
+ inode, ceph_ino(inode), ceph_cap_string(mask));
+ return 0;
+ }
+
dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->vfs_inode,
ceph_cap_string(mask), ceph_cap_string(was),
ceph_cap_string(was | mask));
@@ -1404,7 +1421,6 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
ci->i_snap_realm->cached_context);
dout(" inode %p now dirty snapc %p auth cap %p\n",
&ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap);
- WARN_ON(!ci->i_auth_cap);
BUG_ON(!list_empty(&ci->i_dirty_item));
spin_lock(&mdsc->cap_dirty_lock);
list_add(&ci->i_dirty_item, &mdsc->cap_dirty);
@@ -1545,7 +1561,19 @@ retry_locked:
if (!mdsc->stopping && inode->i_nlink > 0) {
if (want) {
retain |= CEPH_CAP_ANY; /* be greedy */
+ } else if (S_ISDIR(inode->i_mode) &&
+ (issued & CEPH_CAP_FILE_SHARED) &&
+ __ceph_dir_is_complete(ci)) {
+ /*
+ * If a directory is complete, we want to keep
+ * the exclusive cap. So that MDS does not end up
+ * revoking the shared cap on every create/unlink
+ * operation.
+ */
+ want = CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL;
+ retain |= want;
} else {
+
retain |= CEPH_CAP_ANY_SHARED;
/*
* keep RD only if we didn't have the file open RW,
@@ -2309,6 +2337,9 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
wake = 1;
}
}
+ /* see comment in __ceph_remove_cap() */
+ if (!__ceph_is_any_caps(ci) && ci->i_snap_realm)
+ drop_inode_snap_realm(ci);
}
spin_unlock(&ci->i_ceph_lock);
@@ -3391,7 +3422,7 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
int ceph_encode_dentry_release(void **p, struct dentry *dentry,
int mds, int drop, int unless)
{
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
struct ceph_mds_request_release *rel = *p;
struct ceph_dentry_info *di = ceph_dentry(dentry);
int force = 0;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 1b2355109b9f..31f831471ed2 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -84,7 +84,7 @@ static int mdsc_show(struct seq_file *s, void *p)
path = NULL;
spin_lock(&req->r_dentry->d_lock);
seq_printf(s, " #%llx/%pd (%s)",
- ceph_ino(req->r_dentry->d_parent->d_inode),
+ ceph_ino(d_inode(req->r_dentry->d_parent)),
req->r_dentry,
path ? path : "");
spin_unlock(&req->r_dentry->d_lock);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 83e9976f7189..4248307fea90 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -49,9 +49,9 @@ int ceph_init_dentry(struct dentry *dentry)
goto out_unlock;
}
- if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
+ if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP)
d_set_d_op(dentry, &ceph_dentry_ops);
- else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
+ else if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_SNAPDIR)
d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
else
d_set_d_op(dentry, &ceph_snap_dentry_ops);
@@ -77,7 +77,7 @@ struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
spin_lock(&dentry->d_lock);
if (!IS_ROOT(dentry)) {
- inode = dentry->d_parent->d_inode;
+ inode = d_inode(dentry->d_parent);
ihold(inode);
}
spin_unlock(&dentry->d_lock);
@@ -122,7 +122,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
{
struct ceph_file_info *fi = file->private_data;
struct dentry *parent = file->f_path.dentry;
- struct inode *dir = parent->d_inode;
+ struct inode *dir = d_inode(parent);
struct list_head *p;
struct dentry *dentry, *last;
struct ceph_dentry_info *di;
@@ -161,15 +161,15 @@ more:
}
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
if (di->lease_shared_gen == shared_gen &&
- !d_unhashed(dentry) && dentry->d_inode &&
- ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
- ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
+ !d_unhashed(dentry) && d_really_is_positive(dentry) &&
+ ceph_snap(d_inode(dentry)) != CEPH_SNAPDIR &&
+ ceph_ino(d_inode(dentry)) != CEPH_INO_CEPH &&
fpos_cmp(ctx->pos, di->offset) <= 0)
break;
dout(" skipping %p %pd at %llu (%llu)%s%s\n", dentry,
dentry, di->offset,
ctx->pos, d_unhashed(dentry) ? " unhashed" : "",
- !dentry->d_inode ? " null" : "");
+ !d_inode(dentry) ? " null" : "");
spin_unlock(&dentry->d_lock);
p = p->prev;
dentry = list_entry(p, struct dentry, d_child);
@@ -189,11 +189,11 @@ more:
}
dout(" %llu (%llu) dentry %p %pd %p\n", di->offset, ctx->pos,
- dentry, dentry, dentry->d_inode);
+ dentry, dentry, d_inode(dentry));
if (!dir_emit(ctx, dentry->d_name.name,
dentry->d_name.len,
- ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino),
- dentry->d_inode->i_mode >> 12)) {
+ ceph_translate_ino(dentry->d_sb, d_inode(dentry)->i_ino),
+ d_inode(dentry)->i_mode >> 12)) {
if (last) {
/* remember our position */
fi->dentry = last;
@@ -281,6 +281,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
/* can we use the dcache? */
spin_lock(&ci->i_ceph_lock);
if ((ctx->pos == 2 || fi->dentry) &&
+ ceph_test_mount_opt(fsc, DCACHE) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
__ceph_dir_is_complete_ordered(ci) &&
@@ -336,16 +337,23 @@ more:
ceph_mdsc_put_request(req);
return err;
}
- req->r_inode = inode;
- ihold(inode);
- req->r_dentry = dget(file->f_path.dentry);
/* hints to request -> mds selection code */
req->r_direct_mode = USE_AUTH_MDS;
req->r_direct_hash = ceph_frag_value(frag);
req->r_direct_is_hash = true;
- req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
+ if (fi->last_name) {
+ req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
+ if (!req->r_path2) {
+ ceph_mdsc_put_request(req);
+ return -ENOMEM;
+ }
+ }
req->r_readdir_offset = fi->next_offset;
req->r_args.readdir.frag = cpu_to_le32(frag);
+
+ req->r_inode = inode;
+ ihold(inode);
+ req->r_dentry = dget(file->f_path.dentry);
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err < 0) {
ceph_mdsc_put_request(req);
@@ -535,7 +543,7 @@ int ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *dentry, int err)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
- struct inode *parent = dentry->d_parent->d_inode; /* we hold i_mutex */
+ struct inode *parent = d_inode(dentry->d_parent); /* we hold i_mutex */
/* .snap dir? */
if (err == -ENOENT &&
@@ -571,8 +579,8 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
err = 0;
if (!req->r_reply_info.head->is_dentry) {
dout("ENOENT and no trace, dentry %p inode %p\n",
- dentry, dentry->d_inode);
- if (dentry->d_inode) {
+ dentry, d_inode(dentry));
+ if (d_really_is_positive(dentry)) {
d_drop(dentry);
err = -ENOENT;
} else {
@@ -619,7 +627,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
return ERR_PTR(err);
/* can we conclude ENOENT locally? */
- if (dentry->d_inode == NULL) {
+ if (d_really_is_negative(dentry)) {
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
@@ -629,6 +637,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
fsc->mount_options->snapdir_name,
dentry->d_name.len) &&
!is_root_ceph_dentry(dir, dentry) &&
+ ceph_test_mount_opt(fsc, DCACHE) &&
__ceph_dir_is_complete(ci) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
spin_unlock(&ci->i_ceph_lock);
@@ -725,7 +734,7 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
ceph_mdsc_put_request(req);
out:
if (!err)
- ceph_init_inode_acls(dentry->d_inode, &acls);
+ ceph_init_inode_acls(d_inode(dentry), &acls);
else
d_drop(dentry);
ceph_release_acls_info(&acls);
@@ -755,10 +764,15 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
err = PTR_ERR(req);
goto out;
}
- req->r_dentry = dget(dentry);
- req->r_num_caps = 2;
req->r_path2 = kstrdup(dest, GFP_NOFS);
+ if (!req->r_path2) {
+ err = -ENOMEM;
+ ceph_mdsc_put_request(req);
+ goto out;
+ }
req->r_locked_dir = dir;
+ req->r_dentry = dget(dentry);
+ req->r_num_caps = 2;
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
err = ceph_mdsc_do_request(mdsc, dir, req);
@@ -821,7 +835,7 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
ceph_mdsc_put_request(req);
out:
if (!err)
- ceph_init_inode_acls(dentry->d_inode, &acls);
+ ceph_init_inode_acls(d_inode(dentry), &acls);
else
d_drop(dentry);
ceph_release_acls_info(&acls);
@@ -858,8 +872,8 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
if (err) {
d_drop(dentry);
} else if (!req->r_reply_info.head->is_dentry) {
- ihold(old_dentry->d_inode);
- d_instantiate(dentry, old_dentry->d_inode);
+ ihold(d_inode(old_dentry));
+ d_instantiate(dentry, d_inode(old_dentry));
}
ceph_mdsc_put_request(req);
return err;
@@ -892,7 +906,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_mds_request *req;
int err = -EROFS;
int op;
@@ -933,16 +947,20 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
+ int op = CEPH_MDS_OP_RENAME;
int err;
if (ceph_snap(old_dir) != ceph_snap(new_dir))
return -EXDEV;
- if (ceph_snap(old_dir) != CEPH_NOSNAP ||
- ceph_snap(new_dir) != CEPH_NOSNAP)
- return -EROFS;
+ if (ceph_snap(old_dir) != CEPH_NOSNAP) {
+ if (old_dir == new_dir && ceph_snap(old_dir) == CEPH_SNAPDIR)
+ op = CEPH_MDS_OP_RENAMESNAP;
+ else
+ return -EROFS;
+ }
dout("rename dir %p dentry %p to dir %p dentry %p\n",
old_dir, old_dentry, new_dir, new_dentry);
- req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RENAME, USE_AUTH_MDS);
+ req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
ihold(old_dir);
@@ -957,8 +975,8 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
/* release LINK_RDCACHE on source inode (mds will lock it) */
req->r_old_inode_drop = CEPH_CAP_LINK_SHARED;
- if (new_dentry->d_inode)
- req->r_inode_drop = drop_caps_for_unlink(new_dentry->d_inode);
+ if (d_really_is_positive(new_dentry))
+ req->r_inode_drop = drop_caps_for_unlink(d_inode(new_dentry));
err = ceph_mdsc_do_request(mdsc, old_dir, req);
if (!err && !req->r_reply_info.head->is_dentry) {
/*
@@ -1024,7 +1042,7 @@ static int dentry_lease_is_valid(struct dentry *dentry)
if (di->lease_renew_after &&
time_after(jiffies, di->lease_renew_after)) {
/* we should renew */
- dir = dentry->d_parent->d_inode;
+ dir = d_inode(dentry->d_parent);
session = ceph_get_mds_session(s);
seq = di->lease_seq;
di->lease_renew_after = 0;
@@ -1074,22 +1092,22 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
return -ECHILD;
dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
- dentry, dentry->d_inode, ceph_dentry(dentry)->offset);
+ dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
dir = ceph_get_dentry_parent_inode(dentry);
/* always trust cached snapped dentries, snapdir dentry */
if (ceph_snap(dir) != CEPH_NOSNAP) {
dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
- dentry, dentry->d_inode);
+ dentry, d_inode(dentry));
valid = 1;
- } else if (dentry->d_inode &&
- ceph_snap(dentry->d_inode) == CEPH_SNAPDIR) {
+ } else if (d_really_is_positive(dentry) &&
+ ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
valid = 1;
} else if (dentry_lease_is_valid(dentry) ||
dir_lease_is_valid(dir, dentry)) {
- if (dentry->d_inode)
- valid = ceph_is_any_caps(dentry->d_inode);
+ if (d_really_is_positive(dentry))
+ valid = ceph_is_any_caps(d_inode(dentry));
else
valid = 1;
}
@@ -1151,7 +1169,7 @@ static void ceph_d_prune(struct dentry *dentry)
* we hold d_lock, so d_parent is stable, and d_fsdata is never
* cleared until d_release
*/
- ceph_dir_clear_complete(dentry->d_parent->d_inode);
+ ceph_dir_clear_complete(d_inode(dentry->d_parent));
}
/*
@@ -1240,11 +1258,12 @@ static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
dout("dir_fsync %p wait on tid %llu (until %llu)\n",
inode, req->r_tid, last_tid);
if (req->r_timeout) {
- ret = wait_for_completion_timeout(
- &req->r_safe_completion, req->r_timeout);
- if (ret > 0)
+ unsigned long time_left = wait_for_completion_timeout(
+ &req->r_safe_completion,
+ req->r_timeout);
+ if (time_left > 0)
ret = 0;
- else if (ret == 0)
+ else
ret = -EIO; /* timed out */
} else {
wait_for_completion(&req->r_safe_completion);
@@ -1372,6 +1391,7 @@ const struct inode_operations ceph_snapdir_iops = {
.getattr = ceph_getattr,
.mkdir = ceph_mkdir,
.rmdir = ceph_unlink,
+ .rename = ceph_rename,
};
const struct dentry_operations ceph_dentry_ops = {
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 8d7d782f4382..fe02ae7f056a 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -136,8 +136,8 @@ static struct dentry *__get_parent(struct super_block *sb,
return ERR_CAST(req);
if (child) {
- req->r_inode = child->d_inode;
- ihold(child->d_inode);
+ req->r_inode = d_inode(child);
+ ihold(d_inode(child));
} else {
req->r_ino1 = (struct ceph_vino) {
.ino = ino,
@@ -164,7 +164,7 @@ static struct dentry *__get_parent(struct super_block *sb,
return ERR_PTR(err);
}
dout("__get_parent ino %llx parent %p ino %llx.%llx\n",
- child ? ceph_ino(child->d_inode) : ino,
+ child ? ceph_ino(d_inode(child)) : ino,
dentry, ceph_vinop(inode));
return dentry;
}
@@ -172,11 +172,11 @@ static struct dentry *__get_parent(struct super_block *sb,
static struct dentry *ceph_get_parent(struct dentry *child)
{
/* don't re-export snaps */
- if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
+ if (ceph_snap(d_inode(child)) != CEPH_NOSNAP)
return ERR_PTR(-EINVAL);
dout("get_parent %p ino %llx.%llx\n",
- child, ceph_vinop(child->d_inode));
+ child, ceph_vinop(d_inode(child)));
return __get_parent(child->d_sb, child, 0);
}
@@ -209,32 +209,32 @@ static int ceph_get_name(struct dentry *parent, char *name,
struct ceph_mds_request *req;
int err;
- mdsc = ceph_inode_to_client(child->d_inode)->mdsc;
+ mdsc = ceph_inode_to_client(d_inode(child))->mdsc;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
USE_ANY_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
- req->r_inode = child->d_inode;
- ihold(child->d_inode);
- req->r_ino2 = ceph_vino(parent->d_inode);
- req->r_locked_dir = parent->d_inode;
+ req->r_inode = d_inode(child);
+ ihold(d_inode(child));
+ req->r_ino2 = ceph_vino(d_inode(parent));
+ req->r_locked_dir = d_inode(parent);
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
if (!err) {
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
memcpy(name, rinfo->dname, rinfo->dname_len);
name[rinfo->dname_len] = 0;
dout("get_name %p ino %llx.%llx name %s\n",
- child, ceph_vinop(child->d_inode), name);
+ child, ceph_vinop(d_inode(child)), name);
} else {
dout("get_name %p ino %llx.%llx err %d\n",
- child, ceph_vinop(child->d_inode), err);
+ child, ceph_vinop(d_inode(child)), err);
}
ceph_mdsc_put_request(req);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d533075a823d..3b6b522b4b31 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -7,7 +7,6 @@
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/writeback.h>
-#include <linux/aio.h>
#include <linux/falloc.h>
#include "super.h"
@@ -292,14 +291,14 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
}
if (err)
goto out_req;
- if (dn || dentry->d_inode == NULL || d_is_symlink(dentry)) {
+ if (dn || d_really_is_negative(dentry) || d_is_symlink(dentry)) {
/* make vfs retry on splice, ENOENT, or symlink */
dout("atomic_open finish_no_open on dn %p\n", dn);
err = finish_no_open(file, dn);
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
- ceph_init_inode_acls(dentry->d_inode, &acls);
+ ceph_init_inode_acls(d_inode(dentry), &acls);
*opened |= FILE_CREATED;
}
err = finish_open(file, dentry, ceph_open, opened);
@@ -458,7 +457,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
if (ret < 0)
return ret;
- if (file->f_flags & O_DIRECT) {
+ if (iocb->ki_flags & IOCB_DIRECT) {
while (iov_iter_count(i)) {
size_t start;
ssize_t n;
@@ -808,7 +807,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *filp = iocb->ki_filp;
struct ceph_file_info *fi = filp->private_data;
- size_t len = iocb->ki_nbytes;
+ size_t len = iov_iter_count(to);
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
struct page *pinned_page = NULL;
@@ -829,7 +828,7 @@ again:
return ret;
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
- (iocb->ki_filp->f_flags & O_DIRECT) ||
+ (iocb->ki_flags & IOCB_DIRECT) ||
(fi->flags & CEPH_F_SYNC)) {
dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
@@ -942,9 +941,9 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
- ssize_t count = iov_iter_count(from), written = 0;
+ ssize_t count, written = 0;
int err, want, got;
- loff_t pos = iocb->ki_pos;
+ loff_t pos;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
@@ -954,14 +953,12 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
/* We can write back this queue in page reclaim */
current->backing_dev_info = inode_to_bdi(inode);
- err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
- if (err)
- goto out;
-
- if (count == 0)
+ err = generic_write_checks(iocb, from);
+ if (err <= 0)
goto out;
- iov_iter_truncate(from, count);
+ pos = iocb->ki_pos;
+ count = iov_iter_count(from);
err = file_remove_suid(file);
if (err)
goto out;
@@ -998,12 +995,12 @@ retry_snap:
inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
- (file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+ (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
struct iov_iter data;
mutex_unlock(&inode->i_mutex);
/* we might need to revert back to that point */
data = *from;
- if (file->f_flags & O_DIRECT)
+ if (iocb->ki_flags & IOCB_DIRECT)
written = ceph_sync_direct_write(iocb, &data, pos);
else
written = ceph_sync_write(iocb, &data, pos);
@@ -1332,8 +1329,6 @@ const struct file_operations ceph_file_fops = {
.open = ceph_open,
.release = ceph_release,
.llseek = ceph_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = ceph_read_iter,
.write_iter = ceph_write_iter,
.mmap = ceph_mmap,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 119c43c80638..e876e1944519 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -940,7 +940,7 @@ static void update_dentry_lease(struct dentry *dentry,
dentry, duration, ttl);
/* make lease_rdcache_gen match directory */
- dir = dentry->d_parent->d_inode;
+ dir = d_inode(dentry->d_parent);
di->lease_shared_gen = ceph_inode(dir)->i_shared_gen;
if (duration == 0)
@@ -980,7 +980,7 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
{
struct dentry *realdn;
- BUG_ON(dn->d_inode);
+ BUG_ON(d_inode(dn));
/* dn must be unhashed */
if (!d_unhashed(dn))
@@ -998,13 +998,13 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
"inode %p ino %llx.%llx\n",
dn, d_count(dn),
realdn, d_count(realdn),
- realdn->d_inode, ceph_vinop(realdn->d_inode));
+ d_inode(realdn), ceph_vinop(d_inode(realdn)));
dput(dn);
dn = realdn;
} else {
BUG_ON(!ceph_dentry(dn));
dout("dn %p attached to %p ino %llx.%llx\n",
- dn, dn->d_inode, ceph_vinop(dn->d_inode));
+ dn, d_inode(dn), ceph_vinop(d_inode(dn)));
}
if ((!prehash || *prehash) && d_unhashed(dn))
d_rehash(dn);
@@ -1125,11 +1125,11 @@ retry_lookup:
dput(parent);
goto done;
}
- } else if (dn->d_inode &&
- (ceph_ino(dn->d_inode) != vino.ino ||
- ceph_snap(dn->d_inode) != vino.snap)) {
+ } else if (d_really_is_positive(dn) &&
+ (ceph_ino(d_inode(dn)) != vino.ino ||
+ ceph_snap(d_inode(dn)) != vino.snap)) {
dout(" dn %p points to wrong inode %p\n",
- dn, dn->d_inode);
+ dn, d_inode(dn));
d_delete(dn);
dput(dn);
goto retry_lookup;
@@ -1183,7 +1183,7 @@ retry_lookup:
BUG_ON(!dn);
BUG_ON(!dir);
- BUG_ON(dn->d_parent->d_inode != dir);
+ BUG_ON(d_inode(dn->d_parent) != dir);
BUG_ON(ceph_ino(dir) !=
le64_to_cpu(rinfo->diri.in->ino));
BUG_ON(ceph_snap(dir) !=
@@ -1235,7 +1235,7 @@ retry_lookup:
/* null dentry? */
if (!rinfo->head->is_target) {
dout("fill_trace null dentry\n");
- if (dn->d_inode) {
+ if (d_really_is_positive(dn)) {
ceph_dir_clear_ordered(dir);
dout("d_delete %p\n", dn);
d_delete(dn);
@@ -1252,7 +1252,7 @@ retry_lookup:
}
/* attach proper inode */
- if (!dn->d_inode) {
+ if (d_really_is_negative(dn)) {
ceph_dir_clear_ordered(dir);
ihold(in);
dn = splice_dentry(dn, in, &have_lease);
@@ -1261,9 +1261,9 @@ retry_lookup:
goto done;
}
req->r_dentry = dn; /* may have spliced */
- } else if (dn->d_inode && dn->d_inode != in) {
+ } else if (d_really_is_positive(dn) && d_inode(dn) != in) {
dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
- dn, dn->d_inode, ceph_vinop(dn->d_inode),
+ dn, d_inode(dn), ceph_vinop(d_inode(dn)),
ceph_vinop(in));
have_lease = false;
}
@@ -1363,7 +1363,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
return readdir_prepopulate_inodes_only(req, session);
if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
- snapdir = ceph_get_snapdir(parent->d_inode);
+ snapdir = ceph_get_snapdir(d_inode(parent));
parent = d_find_alias(snapdir);
dout("readdir_prepopulate %d items under SNAPDIR dn %p\n",
rinfo->dir_nr, parent);
@@ -1371,7 +1371,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
dout("readdir_prepopulate %d items under dn %p\n",
rinfo->dir_nr, parent);
if (rinfo->dir_dir)
- ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
+ ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
}
/* FIXME: release caps/leases if error occurs */
@@ -1405,11 +1405,11 @@ retry_lookup:
err = ret;
goto out;
}
- } else if (dn->d_inode &&
- (ceph_ino(dn->d_inode) != vino.ino ||
- ceph_snap(dn->d_inode) != vino.snap)) {
+ } else if (d_really_is_positive(dn) &&
+ (ceph_ino(d_inode(dn)) != vino.ino ||
+ ceph_snap(d_inode(dn)) != vino.snap)) {
dout(" dn %p points to wrong inode %p\n",
- dn, dn->d_inode);
+ dn, d_inode(dn));
d_delete(dn);
dput(dn);
goto retry_lookup;
@@ -1423,8 +1423,8 @@ retry_lookup:
}
/* inode */
- if (dn->d_inode) {
- in = dn->d_inode;
+ if (d_really_is_positive(dn)) {
+ in = d_inode(dn);
} else {
in = ceph_get_inode(parent->d_sb, vino);
if (IS_ERR(in)) {
@@ -1440,13 +1440,13 @@ retry_lookup:
req->r_request_started, -1,
&req->r_caps_reservation) < 0) {
pr_err("fill_inode badness on %p\n", in);
- if (!dn->d_inode)
+ if (d_really_is_negative(dn))
iput(in);
d_drop(dn);
goto next_item;
}
- if (!dn->d_inode) {
+ if (d_really_is_negative(dn)) {
struct dentry *realdn = splice_dentry(dn, in, NULL);
if (IS_ERR(realdn)) {
err = PTR_ERR(realdn);
@@ -1693,7 +1693,7 @@ retry:
*/
static void *ceph_sym_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- struct ceph_inode_info *ci = ceph_inode(dentry->d_inode);
+ struct ceph_inode_info *ci = ceph_inode(d_inode(dentry));
nd_set_link(nd, ci->i_symlink);
return NULL;
}
@@ -1714,7 +1714,7 @@ static const struct inode_operations ceph_symlink_iops = {
*/
int ceph_setattr(struct dentry *dentry, struct iattr *attr)
{
- struct inode *inode = dentry->d_inode;
+ 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;
@@ -1990,7 +1990,7 @@ int ceph_permission(struct inode *inode, int mask)
int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
int err;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 71c073f38e54..84f37f34f9aa 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -679,7 +679,7 @@ static struct dentry *get_nonsnap_parent(struct dentry *dentry)
* except to resplice to another snapdir, and either the old or new
* result is a valid result.
*/
- while (!IS_ROOT(dentry) && ceph_snap(dentry->d_inode) != CEPH_NOSNAP)
+ while (!IS_ROOT(dentry) && ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
dentry = dentry->d_parent;
return dentry;
}
@@ -716,20 +716,20 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
} else if (req->r_dentry) {
/* ignore race with rename; old or new d_parent is okay */
struct dentry *parent = req->r_dentry->d_parent;
- struct inode *dir = parent->d_inode;
+ struct inode *dir = d_inode(parent);
if (dir->i_sb != mdsc->fsc->sb) {
/* not this fs! */
- inode = req->r_dentry->d_inode;
+ inode = d_inode(req->r_dentry);
} else if (ceph_snap(dir) != CEPH_NOSNAP) {
/* direct snapped/virtual snapdir requests
* based on parent dir inode */
struct dentry *dn = get_nonsnap_parent(parent);
- inode = dn->d_inode;
+ inode = d_inode(dn);
dout("__choose_mds using nonsnap parent %p\n", inode);
} else {
/* dentry target */
- inode = req->r_dentry->d_inode;
+ inode = d_inode(req->r_dentry);
if (!inode || mode == USE_AUTH_MDS) {
/* dir + name */
inode = dir;
@@ -1021,6 +1021,33 @@ static void cleanup_cap_releases(struct ceph_mds_session *session)
spin_unlock(&session->s_cap_lock);
}
+static void cleanup_session_requests(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session)
+{
+ struct ceph_mds_request *req;
+ struct rb_node *p;
+
+ dout("cleanup_session_requests mds%d\n", session->s_mds);
+ mutex_lock(&mdsc->mutex);
+ while (!list_empty(&session->s_unsafe)) {
+ req = list_first_entry(&session->s_unsafe,
+ struct ceph_mds_request, r_unsafe_item);
+ list_del_init(&req->r_unsafe_item);
+ pr_info(" dropping unsafe request %llu\n", req->r_tid);
+ __unregister_request(mdsc, req);
+ }
+ /* zero r_attempts, so kick_requests() will re-send requests */
+ p = rb_first(&mdsc->request_tree);
+ while (p) {
+ req = rb_entry(p, struct ceph_mds_request, r_node);
+ p = rb_next(p);
+ if (req->r_session &&
+ req->r_session->s_mds == session->s_mds)
+ req->r_attempts = 0;
+ }
+ mutex_unlock(&mdsc->mutex);
+}
+
/*
* Helper to safely iterate over all caps associated with a session, with
* special care taken to handle a racing __ceph_remove_cap().
@@ -1098,7 +1125,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
cap, ci, &ci->vfs_inode);
spin_lock(&ci->i_ceph_lock);
__ceph_remove_cap(cap, false);
- if (!__ceph_is_any_real_caps(ci)) {
+ if (!ci->i_auth_cap) {
struct ceph_mds_client *mdsc =
ceph_sb_to_client(inode->i_sb)->mdsc;
@@ -1120,13 +1147,6 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
mdsc->num_cap_flushing--;
drop = 1;
}
- if (drop && ci->i_wrbuffer_ref) {
- pr_info(" dropping dirty data for %p %lld\n",
- inode, ceph_ino(inode));
- ci->i_wrbuffer_ref = 0;
- ci->i_wrbuffer_ref_head = 0;
- drop++;
- }
spin_unlock(&mdsc->cap_dirty_lock);
}
spin_unlock(&ci->i_ceph_lock);
@@ -1712,7 +1732,7 @@ retry:
seq = read_seqbegin(&rename_lock);
rcu_read_lock();
for (temp = dentry; !IS_ROOT(temp);) {
- struct inode *inode = temp->d_inode;
+ struct inode *inode = d_inode(temp);
if (inode && ceph_snap(inode) == CEPH_SNAPDIR)
len++; /* slash only */
else if (stop_on_nosnap && inode &&
@@ -1736,7 +1756,7 @@ retry:
struct inode *inode;
spin_lock(&temp->d_lock);
- inode = temp->d_inode;
+ inode = d_inode(temp);
if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
dout("build_path path+%d: %p SNAPDIR\n",
pos, temp);
@@ -1770,7 +1790,7 @@ retry:
goto retry;
}
- *base = ceph_ino(temp->d_inode);
+ *base = ceph_ino(d_inode(temp));
*plen = len;
dout("build_path on %p %d built %llx '%.*s'\n",
dentry, d_count(dentry), *base, len, path);
@@ -1783,8 +1803,8 @@ static int build_dentry_path(struct dentry *dentry,
{
char *path;
- if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP) {
- *pino = ceph_ino(dentry->d_parent->d_inode);
+ if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP) {
+ *pino = ceph_ino(d_inode(dentry->d_parent));
*ppath = dentry->d_name.name;
*ppathlen = dentry->d_name.len;
return 0;
@@ -1853,7 +1873,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
*/
static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req,
- int mds)
+ int mds, bool drop_cap_releases)
{
struct ceph_msg *msg;
struct ceph_mds_request_head *head;
@@ -1925,7 +1945,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
releases = 0;
if (req->r_inode_drop)
releases += ceph_encode_inode_release(&p,
- req->r_inode ? req->r_inode : req->r_dentry->d_inode,
+ req->r_inode ? req->r_inode : d_inode(req->r_dentry),
mds, req->r_inode_drop, req->r_inode_unless, 0);
if (req->r_dentry_drop)
releases += ceph_encode_dentry_release(&p, req->r_dentry,
@@ -1935,8 +1955,14 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
mds, req->r_old_dentry_drop, req->r_old_dentry_unless);
if (req->r_old_inode_drop)
releases += ceph_encode_inode_release(&p,
- req->r_old_dentry->d_inode,
+ d_inode(req->r_old_dentry),
mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
+
+ if (drop_cap_releases) {
+ releases = 0;
+ p = msg->front.iov_base + req->r_request_release_offset;
+ }
+
head->num_releases = cpu_to_le16(releases);
/* time stamp */
@@ -1989,7 +2015,7 @@ static void complete_request(struct ceph_mds_client *mdsc,
*/
static int __prepare_send_request(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req,
- int mds)
+ int mds, bool drop_cap_releases)
{
struct ceph_mds_request_head *rhead;
struct ceph_msg *msg;
@@ -2048,7 +2074,7 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
ceph_msg_put(req->r_request);
req->r_request = NULL;
}
- msg = create_request_message(mdsc, req, mds);
+ msg = create_request_message(mdsc, req, mds, drop_cap_releases);
if (IS_ERR(msg)) {
req->r_err = PTR_ERR(msg);
complete_request(mdsc, req);
@@ -2132,7 +2158,7 @@ static int __do_request(struct ceph_mds_client *mdsc,
if (req->r_request_started == 0) /* note request start time */
req->r_request_started = jiffies;
- err = __prepare_send_request(mdsc, req, mds);
+ err = __prepare_send_request(mdsc, req, mds, false);
if (!err) {
ceph_msg_get(req->r_request);
ceph_con_send(&session->s_con, req->r_request);
@@ -2590,6 +2616,7 @@ static void handle_session(struct ceph_mds_session *session,
case CEPH_SESSION_CLOSE:
if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
pr_info("mds%d reconnect denied\n", session->s_mds);
+ cleanup_session_requests(mdsc, session);
remove_session_caps(session);
wake = 2; /* for good measure */
wake_up_all(&mdsc->session_close_wq);
@@ -2658,7 +2685,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
mutex_lock(&mdsc->mutex);
list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item) {
- err = __prepare_send_request(mdsc, req, session->s_mds);
+ err = __prepare_send_request(mdsc, req, session->s_mds, true);
if (!err) {
ceph_msg_get(req->r_request);
ceph_con_send(&session->s_con, req->r_request);
@@ -2679,7 +2706,8 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
continue; /* only old requests */
if (req->r_session &&
req->r_session->s_mds == session->s_mds) {
- err = __prepare_send_request(mdsc, req, session->s_mds);
+ err = __prepare_send_request(mdsc, req,
+ session->s_mds, true);
if (!err) {
ceph_msg_get(req->r_request);
ceph_con_send(&session->s_con, req->r_request);
@@ -2864,7 +2892,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
spin_unlock(&session->s_cap_lock);
/* trim unused caps to reduce MDS's cache rejoin time */
- shrink_dcache_parent(mdsc->fsc->sb->s_root);
+ if (mdsc->fsc->sb->s_root)
+ shrink_dcache_parent(mdsc->fsc->sb->s_root);
ceph_con_close(&session->s_con);
ceph_con_open(&session->s_con,
@@ -3133,7 +3162,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
di->lease_renew_from &&
di->lease_renew_after == 0) {
unsigned long duration =
- le32_to_cpu(h->duration_ms) * HZ / 1000;
+ msecs_to_jiffies(le32_to_cpu(h->duration_ms));
di->lease_seq = seq;
dentry->d_time = di->lease_renew_from + duration;
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index 51cc23e48111..89e6bc321df3 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -75,6 +75,7 @@ const char *ceph_mds_op_name(int op)
case CEPH_MDS_OP_LSSNAP: return "lssnap";
case CEPH_MDS_OP_MKSNAP: return "mksnap";
case CEPH_MDS_OP_RMSNAP: return "rmsnap";
+ case CEPH_MDS_OP_RENAMESNAP: return "renamesnap";
case CEPH_MDS_OP_SETFILELOCK: return "setfilelock";
case CEPH_MDS_OP_GETFILELOCK: return "getfilelock";
}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index a63997b8bcff..4e9905374078 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -44,7 +44,7 @@ static void ceph_put_super(struct super_block *s)
static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
{
- struct ceph_fs_client *fsc = ceph_inode_to_client(dentry->d_inode);
+ struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry));
struct ceph_monmap *monmap = fsc->client->monc.monmap;
struct ceph_statfs st;
u64 fsid;
@@ -345,6 +345,11 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
fsopt->rsize = CEPH_RSIZE_DEFAULT;
fsopt->rasize = CEPH_RASIZE_DEFAULT;
fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+ if (!fsopt->snapdir_name) {
+ err = -ENOMEM;
+ goto out;
+ }
+
fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
@@ -406,31 +411,20 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(root->d_sb);
struct ceph_mount_options *fsopt = fsc->mount_options;
- struct ceph_options *opt = fsc->client->options;
-
- if (opt->flags & CEPH_OPT_FSID)
- seq_printf(m, ",fsid=%pU", &opt->fsid);
- if (opt->flags & CEPH_OPT_NOSHARE)
- seq_puts(m, ",noshare");
- if (opt->flags & CEPH_OPT_NOCRC)
- seq_puts(m, ",nocrc");
- if (opt->flags & CEPH_OPT_NOMSGAUTH)
- seq_puts(m, ",nocephx_require_signatures");
- if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0)
- seq_puts(m, ",notcp_nodelay");
-
- if (opt->name)
- seq_printf(m, ",name=%s", opt->name);
- if (opt->key)
- seq_puts(m, ",secret=<hidden>");
-
- if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
- seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
- if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
- seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
- if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
- seq_printf(m, ",osdkeepalivetimeout=%d",
- opt->osd_keepalive_timeout);
+ size_t pos;
+ int ret;
+
+ /* a comma between MNT/MS and client options */
+ seq_putc(m, ',');
+ pos = m->count;
+
+ ret = ceph_print_client_options(m, fsc->client);
+ if (ret)
+ return ret;
+
+ /* retract our comma if no client options */
+ if (m->count == pos)
+ m->count--;
if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT)
seq_puts(m, ",dirstat");
@@ -438,14 +432,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",norbytes");
if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
seq_puts(m, ",noasyncreaddir");
- if (fsopt->flags & CEPH_MOUNT_OPT_DCACHE)
- seq_puts(m, ",dcache");
- else
+ if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0)
seq_puts(m, ",nodcache");
if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE)
seq_puts(m, ",fsc");
- else
- seq_puts(m, ",nofsc");
#ifdef CONFIG_CEPH_FS_POSIX_ACL
if (fsopt->sb_flags & MS_POSIXACL)
@@ -477,6 +467,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",readdir_max_bytes=%d", fsopt->max_readdir_bytes);
if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
seq_printf(m, ",snapdirname=%s", fsopt->snapdir_name);
+
return 0;
}
@@ -730,6 +721,11 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
if (IS_ERR(req))
return ERR_CAST(req);
req->r_path1 = kstrdup(path, GFP_NOFS);
+ if (!req->r_path1) {
+ root = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
req->r_ino1.ino = CEPH_INO_ROOT;
req->r_ino1.snap = CEPH_NOSNAP;
req->r_started = started;
@@ -976,7 +972,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
if (IS_ERR(res))
goto out_splat;
dout("root %p inode %p ino %llx.%llx\n", res,
- res->d_inode, ceph_vinop(res->d_inode));
+ d_inode(res), ceph_vinop(d_inode(res)));
return res;
out_splat:
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 04c8124ed30e..fa20e1318939 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -36,7 +36,8 @@
#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */
-#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES)
+#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES | \
+ CEPH_MOUNT_OPT_DCACHE)
#define ceph_set_mount_opt(fsc, opt) \
(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
@@ -881,7 +882,6 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
/* file.c */
extern const struct file_operations ceph_file_fops;
-extern const struct address_space_operations ceph_aops;
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 5a492caf34cb..cd7ffad4041d 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -776,12 +776,12 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_getxattr(dentry, name, value, size);
- return __ceph_getxattr(dentry->d_inode, 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 = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_vxattr *vxattrs = ceph_inode_vxattrs(inode);
u32 vir_namelen = 0;
@@ -847,7 +847,7 @@ static int ceph_sync_setxattr(struct dentry *dentry, 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 = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -877,16 +877,23 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
err = PTR_ERR(req);
goto out;
}
- req->r_inode = inode;
- ihold(inode);
- req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
- req->r_num_caps = 1;
+
req->r_args.setxattr.flags = cpu_to_le32(flags);
req->r_path2 = kstrdup(name, GFP_NOFS);
+ if (!req->r_path2) {
+ ceph_mdsc_put_request(req);
+ err = -ENOMEM;
+ goto out;
+ }
req->r_pagelist = pagelist;
pagelist = NULL;
+ req->r_inode = inode;
+ ihold(inode);
+ req->r_num_caps = 1;
+ req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
+
dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
@@ -901,7 +908,7 @@ out:
int __ceph_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_vxattr *vxattr;
struct ceph_inode_info *ci = ceph_inode(inode);
int issued;
@@ -995,7 +1002,7 @@ out:
int ceph_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
- if (ceph_snap(dentry->d_inode) != CEPH_NOSNAP)
+ if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
return -EROFS;
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
@@ -1011,7 +1018,7 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_mds_request *req;
int err;
@@ -1019,12 +1026,14 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
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_inode_drop = CEPH_CAP_XATTR_SHARED;
req->r_num_caps = 1;
- req->r_path2 = kstrdup(name, GFP_NOFS);
-
+ req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
return err;
@@ -1032,7 +1041,7 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
int __ceph_removexattr(struct dentry *dentry, const char *name)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ceph_vxattr *vxattr;
struct ceph_inode_info *ci = ceph_inode(inode);
int issued;
@@ -1098,7 +1107,7 @@ out:
int ceph_removexattr(struct dentry *dentry, const char *name)
{
- if (ceph_snap(dentry->d_inode) != CEPH_NOSNAP)
+ if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
return -EROFS;
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index b8602f199815..430e0348c99e 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -301,7 +301,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
if (full_path == NULL)
goto cdda_exit;
- cifs_sb = CIFS_SB(mntpt->d_inode->i_sb);
+ cifs_sb = CIFS_SB(d_inode(mntpt)->i_sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
mnt = ERR_CAST(tlink);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 4ac7445e6ec7..aa0dc2573374 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -1,6 +1,9 @@
/*
* fs/cifs/cifsencrypt.c
*
+ * Encryption and hashing operations relating to NTLM, NTLMv2. See MS-NLMP
+ * for more detailed information
+ *
* Copyright (C) International Business Machines Corp., 2005,2013
* Author(s): Steve French (sfrench@us.ibm.com)
*
@@ -515,7 +518,8 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
__func__);
return rc;
}
- } else if (ses->serverName) {
+ } else {
+ /* We use ses->serverName if no domain name available */
len = strlen(ses->serverName);
server = kmalloc(2 + (len * 2), GFP_KERNEL);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d72fe37f5420..f5089bde3635 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -607,7 +607,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
p = s = full_path;
do {
- struct inode *dir = dentry->d_inode;
+ struct inode *dir = d_inode(dentry);
struct dentry *child;
if (!dir) {
@@ -906,8 +906,6 @@ const struct inode_operations cifs_symlink_inode_ops = {
};
const struct file_operations cifs_file_ops = {
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.open = cifs_open,
@@ -926,8 +924,6 @@ const struct file_operations cifs_file_ops = {
};
const struct file_operations cifs_file_strict_ops = {
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = cifs_strict_readv,
.write_iter = cifs_strict_writev,
.open = cifs_open,
@@ -947,8 +943,6 @@ const struct file_operations cifs_file_strict_ops = {
const struct file_operations cifs_file_direct_ops = {
/* BB reevaluate whether they can be done with directio, no cache */
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = cifs_user_readv,
.write_iter = cifs_user_writev,
.open = cifs_open,
@@ -967,8 +961,6 @@ const struct file_operations cifs_file_direct_ops = {
};
const struct file_operations cifs_file_nobrl_ops = {
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.open = cifs_open,
@@ -986,8 +978,6 @@ const struct file_operations cifs_file_nobrl_ops = {
};
const struct file_operations cifs_file_strict_nobrl_ops = {
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = cifs_strict_readv,
.write_iter = cifs_strict_writev,
.open = cifs_open,
@@ -1006,8 +996,6 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
const struct file_operations cifs_file_direct_nobrl_ops = {
/* BB reevaluate whether they can be done with directio, no cache */
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = cifs_user_readv,
.write_iter = cifs_user_writev,
.open = cifs_open,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index fa13d5e79f64..84650a51c7c4 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1898,7 +1898,7 @@ static void
cifs_writev_requeue(struct cifs_writedata *wdata)
{
int i, rc = 0;
- struct inode *inode = wdata->cfile->dentry->d_inode;
+ struct inode *inode = d_inode(wdata->cfile->dentry);
struct TCP_Server_Info *server;
unsigned int rest_len;
@@ -1981,7 +1981,7 @@ cifs_writev_complete(struct work_struct *work)
{
struct cifs_writedata *wdata = container_of(work,
struct cifs_writedata, work);
- struct inode *inode = wdata->cfile->dentry->d_inode;
+ struct inode *inode = d_inode(wdata->cfile->dentry);
int i = 0;
if (wdata->result == 0) {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d3aa999ab785..f3bfe08e177b 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -773,8 +773,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
length = atomic_dec_return(&tcpSesAllocCount);
if (length > 0)
- mempool_resize(cifs_req_poolp, length + cifs_min_rcv,
- GFP_KERNEL);
+ mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
}
static int
@@ -848,8 +847,7 @@ cifs_demultiplex_thread(void *p)
length = atomic_inc_return(&tcpSesAllocCount);
if (length > 1)
- mempool_resize(cifs_req_poolp, length + cifs_min_rcv,
- GFP_KERNEL);
+ mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
set_freezable();
while (server->tcpStatus != CifsExiting) {
@@ -1599,6 +1597,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
pr_warn("CIFS: username too long\n");
goto cifs_parse_mount_err;
}
+
+ kfree(vol->username);
vol->username = kstrdup(string, GFP_KERNEL);
if (!vol->username)
goto cifs_parse_mount_err;
@@ -1700,6 +1700,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
goto cifs_parse_mount_err;
}
+ kfree(vol->domainname);
vol->domainname = kstrdup(string, GFP_KERNEL);
if (!vol->domainname) {
pr_warn("CIFS: no memory for domainname\n");
@@ -1731,6 +1732,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
if (strncasecmp(string, "default", 7) != 0) {
+ kfree(vol->iocharset);
vol->iocharset = kstrdup(string,
GFP_KERNEL);
if (!vol->iocharset) {
@@ -2913,8 +2915,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server)
* calling name ends in null (byte 16) from old smb
* convention.
*/
- if (server->workstation_RFC1001_name &&
- server->workstation_RFC1001_name[0] != 0)
+ if (server->workstation_RFC1001_name[0] != 0)
rfc1002mangle(ses_init_buf->trailer.
session_req.calling_name,
server->workstation_RFC1001_name,
@@ -3692,6 +3693,12 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
#endif /* CIFS_WEAK_PW_HASH */
rc = SMBNTencrypt(tcon->password, ses->server->cryptkey,
bcc_ptr, nls_codepage);
+ if (rc) {
+ cifs_dbg(FYI, "%s Can't generate NTLM rsp. Error: %d\n",
+ __func__, rc);
+ cifs_buf_release(smb_buffer);
+ return rc;
+ }
bcc_ptr += CIFS_AUTH_RESP_SIZE;
if (ses->capabilities & CAP_UNICODE) {
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index b72bc29cba23..338d56936f6a 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -745,13 +745,13 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
goto lookup_out;
}
- if (direntry->d_inode != NULL) {
+ if (d_really_is_positive(direntry)) {
cifs_dbg(FYI, "non-NULL inode in lookup\n");
} else {
cifs_dbg(FYI, "NULL inode in lookup\n");
}
cifs_dbg(FYI, "Full path: %s inode = 0x%p\n",
- full_path, direntry->d_inode);
+ full_path, d_inode(direntry));
if (pTcon->unix_ext) {
rc = cifs_get_inode_info_unix(&newInode, full_path,
@@ -792,7 +792,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
if (flags & LOOKUP_RCU)
return -ECHILD;
- if (direntry->d_inode) {
+ if (d_really_is_positive(direntry)) {
if (cifs_revalidate_dentry(direntry))
return 0;
else {
@@ -803,7 +803,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
* attributes will have been updated by
* cifs_revalidate_dentry().
*/
- if (IS_AUTOMOUNT(direntry->d_inode) &&
+ if (IS_AUTOMOUNT(d_inode(direntry)) &&
!(direntry->d_flags & DCACHE_NEED_AUTOMOUNT)) {
spin_lock(&direntry->d_lock);
direntry->d_flags |= DCACHE_NEED_AUTOMOUNT;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index a94b3e673182..cafbf10521d5 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -273,7 +273,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock)
{
struct dentry *dentry = file->f_path.dentry;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifsFileInfo *cfile;
struct cifs_fid_locks *fdlocks;
@@ -357,7 +357,7 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file)
*/
void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
{
- struct inode *inode = cifs_file->dentry->d_inode;
+ struct inode *inode = d_inode(cifs_file->dentry);
struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
struct cifsInodeInfo *cifsi = CIFS_I(inode);
@@ -386,7 +386,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
if (list_empty(&cifsi->openFileList)) {
cifs_dbg(FYI, "closing last open instance for inode %p\n",
- cifs_file->dentry->d_inode);
+ d_inode(cifs_file->dentry));
/*
* In strict cache mode we need invalidate mapping on the last
* close because it may cause a error when we open this file
@@ -572,7 +572,7 @@ static int
cifs_relock_file(struct cifsFileInfo *cfile)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
@@ -620,7 +620,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
return rc;
}
- inode = cfile->dentry->d_inode;
+ inode = d_inode(cfile->dentry);
cifs_sb = CIFS_SB(inode->i_sb);
tcon = tlink_tcon(cfile->tlink);
server = tcon->ses->server;
@@ -874,7 +874,7 @@ cifs_find_lock_conflict(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
{
bool rc = false;
struct cifs_fid_locks *cur;
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
list_for_each_entry(cur, &cinode->llist, llist) {
rc = cifs_find_fid_lock_conflict(cur, offset, length, type,
@@ -899,7 +899,7 @@ cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
{
int rc = 0;
struct cifsLockInfo *conf_lock;
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
bool exist;
@@ -927,7 +927,7 @@ cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
static void
cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
{
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
down_write(&cinode->lock_sem);
list_add_tail(&lock->llist, &cfile->llist->locks);
up_write(&cinode->lock_sem);
@@ -944,7 +944,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
bool wait)
{
struct cifsLockInfo *conf_lock;
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
bool exist;
int rc = 0;
@@ -1125,7 +1125,7 @@ struct lock_to_push {
static int
cifs_push_posix_locks(struct cifsFileInfo *cfile)
{
- struct inode *inode = cfile->dentry->d_inode;
+ struct inode *inode = d_inode(cfile->dentry);
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct file_lock *flock;
struct file_lock_context *flctx = inode->i_flctx;
@@ -1214,7 +1214,7 @@ static int
cifs_push_locks(struct cifsFileInfo *cfile)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
@@ -1382,7 +1382,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
unsigned int max_num, num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifsLockInfo *li, *tmp;
__u64 length = 1 + flock->fl_end - flock->fl_start;
struct list_head tmp_llist;
@@ -1488,7 +1488,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
- struct inode *inode = cfile->dentry->d_inode;
+ struct inode *inode = d_inode(cfile->dentry);
if (posix_lck) {
int posix_lock_type;
@@ -1643,7 +1643,7 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
struct TCP_Server_Info *server;
unsigned int xid;
struct dentry *dentry = open_file->dentry;
- struct cifsInodeInfo *cifsi = CIFS_I(dentry->d_inode);
+ struct cifsInodeInfo *cifsi = CIFS_I(d_inode(dentry));
struct cifs_io_parms io_parms;
cifs_sb = CIFS_SB(dentry->d_sb);
@@ -1676,7 +1676,7 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
break;
}
- len = min(server->ops->wp_retry_size(dentry->d_inode),
+ len = min(server->ops->wp_retry_size(d_inode(dentry)),
(unsigned int)write_size - total_written);
/* iov[0] is reserved for smb header */
iov[1].iov_base = (char *)write_data + total_written;
@@ -1696,9 +1696,9 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
return rc;
}
} else {
- spin_lock(&dentry->d_inode->i_lock);
+ spin_lock(&d_inode(dentry)->i_lock);
cifs_update_eof(cifsi, *offset, bytes_written);
- spin_unlock(&dentry->d_inode->i_lock);
+ spin_unlock(&d_inode(dentry)->i_lock);
*offset += bytes_written;
}
}
@@ -1706,12 +1706,12 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
cifs_stats_bytes_written(tcon, total_written);
if (total_written > 0) {
- spin_lock(&dentry->d_inode->i_lock);
- if (*offset > dentry->d_inode->i_size)
- i_size_write(dentry->d_inode, *offset);
- spin_unlock(&dentry->d_inode->i_lock);
+ spin_lock(&d_inode(dentry)->i_lock);
+ if (*offset > d_inode(dentry)->i_size)
+ i_size_write(d_inode(dentry), *offset);
+ spin_unlock(&d_inode(dentry)->i_lock);
}
- mark_inode_dirty_sync(dentry->d_inode);
+ mark_inode_dirty_sync(d_inode(dentry));
free_xid(xid);
return total_written;
}
@@ -1823,6 +1823,7 @@ refind_writable:
cifsFileInfo_put(inv_file);
spin_lock(&cifs_file_list_lock);
++refind;
+ inv_file = NULL;
goto refind_writable;
}
}
@@ -2405,7 +2406,7 @@ cifs_uncached_writev_complete(struct work_struct *work)
{
struct cifs_writedata *wdata = container_of(work,
struct cifs_writedata, work);
- struct inode *inode = wdata->cfile->dentry->d_inode;
+ struct inode *inode = d_inode(wdata->cfile->dentry);
struct cifsInodeInfo *cifsi = CIFS_I(inode);
spin_lock(&inode->i_lock);
@@ -2559,10 +2560,9 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
return rc;
}
-static ssize_t
-cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset)
+ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
{
- size_t len;
+ struct file *file = iocb->ki_filp;
ssize_t total_written = 0;
struct cifsFileInfo *open_file;
struct cifs_tcon *tcon;
@@ -2572,15 +2572,15 @@ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset)
struct iov_iter saved_from;
int rc;
- len = iov_iter_count(from);
- rc = generic_write_checks(file, poffset, &len, 0);
- if (rc)
- return rc;
-
- if (!len)
- return 0;
+ /*
+ * BB - optimize the way when signing is disabled. We can drop this
+ * extra memory-to-memory copying and use iovec buffers for constructing
+ * write request.
+ */
- iov_iter_truncate(from, len);
+ rc = generic_write_checks(iocb, from);
+ if (rc <= 0)
+ return rc;
INIT_LIST_HEAD(&wdata_list);
cifs_sb = CIFS_FILE_SB(file);
@@ -2592,8 +2592,8 @@ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset)
memcpy(&saved_from, from, sizeof(struct iov_iter));
- rc = cifs_write_from_iter(*poffset, len, from, open_file, cifs_sb,
- &wdata_list);
+ rc = cifs_write_from_iter(iocb->ki_pos, iov_iter_count(from), from,
+ open_file, cifs_sb, &wdata_list);
/*
* If at least one write was successfully sent, then discard any rc
@@ -2632,7 +2632,7 @@ restart_loop:
memcpy(&tmp_from, &saved_from,
sizeof(struct iov_iter));
iov_iter_advance(&tmp_from,
- wdata->offset - *poffset);
+ wdata->offset - iocb->ki_pos);
rc = cifs_write_from_iter(wdata->offset,
wdata->bytes, &tmp_from,
@@ -2649,34 +2649,13 @@ restart_loop:
kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
- if (total_written > 0)
- *poffset += total_written;
+ if (unlikely(!total_written))
+ return rc;
+ iocb->ki_pos += total_written;
+ set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(file_inode(file))->flags);
cifs_stats_bytes_written(tcon, total_written);
- return total_written ? total_written : (ssize_t)rc;
-}
-
-ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
-{
- ssize_t written;
- struct inode *inode;
- loff_t pos = iocb->ki_pos;
-
- inode = file_inode(iocb->ki_filp);
-
- /*
- * BB - optimize the way when signing is disabled. We can drop this
- * extra memory-to-memory copying and use iovec buffers for constructing
- * write request.
- */
-
- written = cifs_iovec_write(iocb->ki_filp, from, &pos);
- if (written > 0) {
- set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
- iocb->ki_pos = pos;
- }
-
- return written;
+ return total_written;
}
static ssize_t
@@ -2687,8 +2666,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = file->f_mapping->host;
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
- ssize_t rc = -EACCES;
- loff_t lock_pos = iocb->ki_pos;
+ ssize_t rc;
/*
* We need to hold the sem to be sure nobody modifies lock list
@@ -2696,23 +2674,24 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
*/
down_read(&cinode->lock_sem);
mutex_lock(&inode->i_mutex);
- if (file->f_flags & O_APPEND)
- lock_pos = i_size_read(inode);
- if (!cifs_find_lock_conflict(cfile, lock_pos, iov_iter_count(from),
+
+ rc = generic_write_checks(iocb, from);
+ if (rc <= 0)
+ goto out;
+
+ if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
server->vals->exclusive_lock_type, NULL,
- CIFS_WRITE_OP)) {
+ CIFS_WRITE_OP))
rc = __generic_file_write_iter(iocb, from);
- mutex_unlock(&inode->i_mutex);
-
- if (rc > 0) {
- ssize_t err;
+ else
+ rc = -EACCES;
+out:
+ mutex_unlock(&inode->i_mutex);
- err = generic_write_sync(file, iocb->ki_pos - rc, rc);
- if (err < 0)
- rc = err;
- }
- } else {
- mutex_unlock(&inode->i_mutex);
+ if (rc > 0) {
+ ssize_t err = generic_write_sync(file, iocb->ki_pos - rc, rc);
+ if (err < 0)
+ rc = err;
}
up_read(&cinode->lock_sem);
return rc;
@@ -3815,7 +3794,7 @@ void cifs_oplock_break(struct work_struct *work)
{
struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
oplock_break);
- struct inode *inode = cfile->dentry->d_inode;
+ struct inode *inode = d_inode(cfile->dentry);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
@@ -3876,8 +3855,7 @@ void cifs_oplock_break(struct work_struct *work)
* Direct IO is not yet supported in the cached mode.
*/
static ssize_t
-cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter,
- loff_t pos)
+cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
{
/*
* FIXME
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2d4f37235ed0..55b58112d122 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -771,6 +771,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
cifs_buf_release(srchinf->ntwrk_buf_start);
}
kfree(srchinf);
+ if (rc)
+ goto cgii_exit;
} else
goto cgii_exit;
@@ -1065,7 +1067,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
int rc;
struct cifs_fid fid;
struct cifs_open_parms oparms;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
@@ -1194,7 +1196,7 @@ cifs_drop_nlink(struct inode *inode)
}
/*
- * If dentry->d_inode is null (usually meaning the cached dentry
+ * If d_inode(dentry) is null (usually meaning the cached dentry
* is a negative dentry) then we would attempt a standard SMB delete, but
* if that fails we can not attempt the fall back mechanisms on EACCESS
* but will return the EACCESS to the caller. Note that the VFS does not call
@@ -1205,7 +1207,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
int rc = 0;
unsigned int xid;
char *full_path = NULL;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifs_inode;
struct super_block *sb = dir->i_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
@@ -1549,13 +1551,13 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
cifs_put_tlink(tlink);
if (!rc) {
- spin_lock(&direntry->d_inode->i_lock);
- i_size_write(direntry->d_inode, 0);
- clear_nlink(direntry->d_inode);
- spin_unlock(&direntry->d_inode->i_lock);
+ spin_lock(&d_inode(direntry)->i_lock);
+ i_size_write(d_inode(direntry), 0);
+ clear_nlink(d_inode(direntry));
+ spin_unlock(&d_inode(direntry)->i_lock);
}
- cifsInode = CIFS_I(direntry->d_inode);
+ cifsInode = CIFS_I(d_inode(direntry));
/* force revalidate to go get info when needed */
cifsInode->time = 0;
@@ -1566,7 +1568,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
*/
cifsInode->time = 0;
- direntry->d_inode->i_ctime = inode->i_ctime = inode->i_mtime =
+ d_inode(direntry)->i_ctime = inode->i_ctime = inode->i_mtime =
current_fs_time(inode->i_sb);
rmdir_exit:
@@ -1725,7 +1727,7 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry,
unlink_target:
/* Try unlinking the target dentry if it's not negative */
- if (target_dentry->d_inode && (rc == -EACCES || rc == -EEXIST)) {
+ if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) {
if (d_is_dir(target_dentry))
tmprc = cifs_rmdir(target_dir, target_dentry);
else
@@ -1865,7 +1867,7 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry)
{
unsigned int xid;
int rc = 0;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct super_block *sb = dentry->d_sb;
char *full_path = NULL;
@@ -1917,7 +1919,7 @@ int cifs_revalidate_file(struct file *filp)
int cifs_revalidate_dentry(struct dentry *dentry)
{
int rc;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
rc = cifs_revalidate_dentry_attr(dentry);
if (rc)
@@ -1931,7 +1933,7 @@ int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
{
struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int rc;
/*
@@ -2108,7 +2110,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
int rc;
unsigned int xid;
char *full_path = NULL;
- struct inode *inode = direntry->d_inode;
+ struct inode *inode = d_inode(direntry);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
@@ -2249,7 +2251,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
unsigned int xid;
kuid_t uid = INVALID_UID;
kgid_t gid = INVALID_GID;
- struct inode *inode = direntry->d_inode;
+ struct inode *inode = d_inode(direntry);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
char *full_path = NULL;
@@ -2407,7 +2409,7 @@ cifs_setattr_exit:
int
cifs_setattr(struct dentry *direntry, struct iattr *attrs)
{
- struct inode *inode = direntry->d_inode;
+ struct inode *inode = d_inode(direntry);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb);
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 2ec6037f61c7..252e672d5604 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -586,12 +586,12 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
* if source file is cached (oplocked) revalidate will not go to server
* until the file is closed or oplock broken so update nlinks locally
*/
- if (old_file->d_inode) {
- cifsInode = CIFS_I(old_file->d_inode);
+ if (d_really_is_positive(old_file)) {
+ cifsInode = CIFS_I(d_inode(old_file));
if (rc == 0) {
- spin_lock(&old_file->d_inode->i_lock);
- inc_nlink(old_file->d_inode);
- spin_unlock(&old_file->d_inode->i_lock);
+ spin_lock(&d_inode(old_file)->i_lock);
+ inc_nlink(d_inode(old_file));
+ spin_unlock(&d_inode(old_file)->i_lock);
/*
* parent dir timestamps will update from srv within a
@@ -629,7 +629,7 @@ cifs_hl_exit:
void *
cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
{
- struct inode *inode = direntry->d_inode;
+ struct inode *inode = d_inode(direntry);
int rc = -ENOMEM;
unsigned int xid;
char *full_path = NULL;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 337946355b29..8442b8b8e0be 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -473,7 +473,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
continue;
cifs_dbg(FYI, "file id match, oplock break\n");
- pCifsInode = CIFS_I(netfile->dentry->d_inode);
+ pCifsInode = CIFS_I(d_inode(netfile->dentry));
set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
&pCifsInode->flags);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index c295338e0a98..b4a47237486b 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -78,7 +78,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
{
struct dentry *dentry, *alias;
struct inode *inode;
- struct super_block *sb = parent->d_inode->i_sb;
+ struct super_block *sb = d_inode(parent)->i_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
cifs_dbg(FYI, "%s: for %s\n", __func__, name->name);
@@ -88,7 +88,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
return;
if (dentry) {
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
if (inode) {
/*
* If we're generating inode numbers, then we don't
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index d2979036a4c7..7bfdd6066276 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -722,7 +722,7 @@ cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
static void
cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
{
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
cfile->fid.netfid = fid->netfid;
cifs_set_oplock_level(cinode, oplock);
cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 7198eac5dddd..2ab297dae5a7 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -95,7 +95,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
unsigned int max_num, num = 0, max_buf;
struct smb2_lock_element *buf, *cur;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifsLockInfo *li, *tmp;
__u64 length = 1 + flock->fl_end - flock->fl_start;
struct list_head tmp_llist;
@@ -231,7 +231,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
unsigned int xid;
unsigned int max_num, max_buf;
struct smb2_lock_element *buf;
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct cifs_fid_locks *fdlocks;
xid = get_xid();
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 689f035915cf..1c5907019045 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -322,7 +322,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
/* return pointer to beginning of data area, ie offset from SMB start */
if ((*off != 0) && (*len != 0))
- return hdr->ProtocolId + *off;
+ return (char *)(&hdr->ProtocolId[0]) + *off;
else
return NULL;
}
@@ -453,7 +453,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
list_for_each(tmp, &tcon->openFileList) {
cfile = list_entry(tmp, struct cifsFileInfo, tlist);
- cinode = CIFS_I(cfile->dentry->d_inode);
+ cinode = CIFS_I(d_inode(cfile->dentry));
if (memcmp(cinode->lease_key, rsp->LeaseKey,
SMB2_LEASE_KEY_SIZE))
@@ -590,7 +590,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
continue;
cifs_dbg(FYI, "file id match, oplock break\n");
- cinode = CIFS_I(cfile->dentry->d_inode);
+ cinode = CIFS_I(d_inode(cfile->dentry));
if (!CIFS_CACHE_WRITE(cinode) &&
rsp->OplockLevel == SMB2_OPLOCK_LEVEL_NONE)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 96b5d40a2ece..54daee5ad4c1 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -524,7 +524,7 @@ smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
static void
smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
{
- struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
cfile->fid.persistent_fid = fid->persistent_fid;
@@ -684,7 +684,8 @@ smb2_clone_range(const unsigned int xid,
/* No need to change MaxChunks since already set to 1 */
chunk_sizes_updated = true;
- }
+ } else
+ goto cchunk_out;
}
cchunk_out:
@@ -792,7 +793,7 @@ smb2_set_file_size(const unsigned int xid, struct cifs_tcon *tcon,
* If extending file more than one page make sparse. Many Linux fs
* make files sparse by default when extending via ftruncate
*/
- inode = cfile->dentry->d_inode;
+ inode = d_inode(cfile->dentry);
if (!set_alloc && (size > inode->i_size + 8192)) {
__u8 set_sparse = 1;
@@ -1031,7 +1032,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
xid = get_xid();
- inode = cfile->dentry->d_inode;
+ inode = d_inode(cfile->dentry);
cifsi = CIFS_I(inode);
/* if file not oplocked can't be sure whether asking to extend size */
@@ -1082,7 +1083,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
xid = get_xid();
- inode = cfile->dentry->d_inode;
+ inode = d_inode(cfile->dentry);
cifsi = CIFS_I(inode);
/* Need to make file sparse, if not already, before freeing range. */
@@ -1114,7 +1115,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
xid = get_xid();
- inode = cfile->dentry->d_inode;
+ inode = d_inode(cfile->dentry);
cifsi = CIFS_I(inode);
/* if file not oplocked can't be sure whether asking to extend size */
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 3417340bf89e..65cd7a84c8bc 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1218,7 +1218,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
struct smb2_ioctl_req *req;
struct smb2_ioctl_rsp *rsp;
struct TCP_Server_Info *server;
- struct cifs_ses *ses = tcon->ses;
+ struct cifs_ses *ses;
struct kvec iov[2];
int resp_buftype;
int num_iovecs;
@@ -1233,6 +1233,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
if (plen)
*plen = 0;
+ if (tcon)
+ ses = tcon->ses;
+ else
+ return -EIO;
+
if (ses && (ses->server))
server = ses->server;
else
@@ -1296,14 +1301,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base;
if ((rc != 0) && (rc != -EINVAL)) {
- if (tcon)
- cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
+ cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
goto ioctl_exit;
} else if (rc == -EINVAL) {
if ((opcode != FSCTL_SRV_COPYCHUNK_WRITE) &&
(opcode != FSCTL_SRV_COPYCHUNK)) {
- if (tcon)
- cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
+ cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
goto ioctl_exit;
}
}
@@ -1629,7 +1632,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
- if ((rc != 0) && tcon)
+ if (rc != 0)
cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE);
free_rsp_buf(resp_buftype, iov[0].iov_base);
@@ -2114,7 +2117,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
struct kvec iov[2];
int rc = 0;
int len;
- int resp_buftype;
+ int resp_buftype = CIFS_NO_BUFFER;
unsigned char *bufptr;
struct TCP_Server_Info *server;
struct cifs_ses *ses = tcon->ses;
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 72a4d10653d6..ff9e1f8b16a4 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -50,9 +50,9 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name)
if (direntry == NULL)
return -EIO;
- if (direntry->d_inode == NULL)
+ if (d_really_is_negative(direntry))
return -EIO;
- sb = direntry->d_inode->i_sb;
+ sb = d_inode(direntry)->i_sb;
if (sb == NULL)
return -EIO;
@@ -111,9 +111,9 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
if (direntry == NULL)
return -EIO;
- if (direntry->d_inode == NULL)
+ if (d_really_is_negative(direntry))
return -EIO;
- sb = direntry->d_inode->i_sb;
+ sb = d_inode(direntry)->i_sb;
if (sb == NULL)
return -EIO;
@@ -177,12 +177,12 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
memcpy(pacl, ea_value, value_size);
if (pTcon->ses->server->ops->set_acl)
rc = pTcon->ses->server->ops->set_acl(pacl,
- value_size, direntry->d_inode,
+ value_size, d_inode(direntry),
full_path, CIFS_ACL_DACL);
else
rc = -EOPNOTSUPP;
if (rc == 0) /* force revalidate of the inode */
- CIFS_I(direntry->d_inode)->time = 0;
+ CIFS_I(d_inode(direntry))->time = 0;
kfree(pacl);
}
#else
@@ -246,9 +246,9 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
if (direntry == NULL)
return -EIO;
- if (direntry->d_inode == NULL)
+ if (d_really_is_negative(direntry))
return -EIO;
- sb = direntry->d_inode->i_sb;
+ sb = d_inode(direntry)->i_sb;
if (sb == NULL)
return -EIO;
@@ -324,7 +324,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
goto get_ea_exit; /* rc already EOPNOTSUPP */
pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
- direntry->d_inode, full_path, &acllen);
+ d_inode(direntry), full_path, &acllen);
if (IS_ERR(pacl)) {
rc = PTR_ERR(pacl);
cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
@@ -382,9 +382,9 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
if (direntry == NULL)
return -EIO;
- if (direntry->d_inode == NULL)
+ if (d_really_is_negative(direntry))
return -EIO;
- sb = direntry->d_inode->i_sb;
+ sb = d_inode(direntry)->i_sb;
if (sb == NULL)
return -EIO;
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 46ee6f238985..5bb630a769e0 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -94,8 +94,8 @@ static void coda_flag_children(struct dentry *parent, int flag)
spin_lock(&parent->d_lock);
list_for_each_entry(de, &parent->d_subdirs, d_child) {
/* don't know what to do with negative dentries */
- if (de->d_inode )
- coda_flag_inode(de->d_inode, flag);
+ if (d_inode(de) )
+ coda_flag_inode(d_inode(de), flag);
}
spin_unlock(&parent->d_lock);
return;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 60cb88c1dd2b..fda9f4311212 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -201,7 +201,7 @@ err_out:
static int coda_link(struct dentry *source_de, struct inode *dir_inode,
struct dentry *de)
{
- struct inode *inode = source_de->d_inode;
+ struct inode *inode = d_inode(source_de);
const char * name = de->d_name.name;
int len = de->d_name.len;
int error;
@@ -266,7 +266,7 @@ static int coda_unlink(struct inode *dir, struct dentry *de)
return error;
coda_dir_update_mtime(dir);
- drop_nlink(de->d_inode);
+ drop_nlink(d_inode(de));
return 0;
}
@@ -279,8 +279,8 @@ static int coda_rmdir(struct inode *dir, struct dentry *de)
error = venus_rmdir(dir->i_sb, coda_i2f(dir), name, len);
if (!error) {
/* VFS may delete the child */
- if (de->d_inode)
- clear_nlink(de->d_inode);
+ if (d_really_is_positive(de))
+ clear_nlink(d_inode(de));
/* fix the link count of the parent */
coda_dir_drop_nlink(dir);
@@ -303,14 +303,14 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
coda_i2f(new_dir), old_length, new_length,
(const char *) old_name, (const char *)new_name);
if (!error) {
- if (new_dentry->d_inode) {
+ if (d_really_is_positive(new_dentry)) {
if (d_is_dir(new_dentry)) {
coda_dir_drop_nlink(old_dir);
coda_dir_inc_nlink(new_dir);
}
coda_dir_update_mtime(old_dir);
coda_dir_update_mtime(new_dir);
- coda_flag_inode(new_dentry->d_inode, C_VATTR);
+ coda_flag_inode(d_inode(new_dentry), C_VATTR);
} else {
coda_flag_inode(old_dir, C_VATTR);
coda_flag_inode(new_dir, C_VATTR);
@@ -449,13 +449,13 @@ static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
if (flags & LOOKUP_RCU)
return -ECHILD;
- inode = de->d_inode;
+ inode = d_inode(de);
if (!inode || is_root_inode(inode))
goto out;
if (is_bad_inode(inode))
goto bad;
- cii = ITOC(de->d_inode);
+ cii = ITOC(d_inode(de));
if (!(cii->c_flags & (C_PURGE | C_FLUSH)))
goto out;
@@ -487,11 +487,11 @@ static int coda_dentry_delete(const struct dentry * dentry)
{
int flags;
- if (!dentry->d_inode)
+ if (d_really_is_negative(dentry))
return 0;
- flags = (ITOC(dentry->d_inode)->c_flags) & C_PURGE;
- if (is_bad_inode(dentry->d_inode) || flags) {
+ flags = (ITOC(d_inode(dentry))->c_flags) & C_PURGE;
+ if (is_bad_inode(d_inode(dentry)) || flags) {
return 1;
}
return 0;
diff --git a/fs/coda/file.c b/fs/coda/file.c
index d244d743a232..1da3805f3ddc 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -27,19 +27,14 @@
#include "coda_int.h"
static ssize_t
-coda_file_read(struct file *coda_file, char __user *buf, size_t count, loff_t *ppos)
+coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
- struct coda_file_info *cfi;
- struct file *host_file;
+ struct file *coda_file = iocb->ki_filp;
+ struct coda_file_info *cfi = CODA_FTOC(coda_file);
- cfi = CODA_FTOC(coda_file);
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
- host_file = cfi->cfi_container;
- if (!host_file->f_op->read)
- return -EINVAL;
-
- return host_file->f_op->read(host_file, buf, count, ppos);
+ return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos);
}
static ssize_t
@@ -64,32 +59,25 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
}
static ssize_t
-coda_file_write(struct file *coda_file, const char __user *buf, size_t count, loff_t *ppos)
+coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
{
- struct inode *host_inode, *coda_inode = file_inode(coda_file);
- struct coda_file_info *cfi;
+ struct file *coda_file = iocb->ki_filp;
+ struct inode *coda_inode = file_inode(coda_file);
+ struct coda_file_info *cfi = CODA_FTOC(coda_file);
struct file *host_file;
ssize_t ret;
- cfi = CODA_FTOC(coda_file);
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
- host_file = cfi->cfi_container;
-
- if (!host_file->f_op->write)
- return -EINVAL;
- host_inode = file_inode(host_file);
+ host_file = cfi->cfi_container;
file_start_write(host_file);
mutex_lock(&coda_inode->i_mutex);
-
- ret = host_file->f_op->write(host_file, buf, count, ppos);
-
- coda_inode->i_size = host_inode->i_size;
+ ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos);
+ coda_inode->i_size = file_inode(host_file)->i_size;
coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9;
coda_inode->i_mtime = coda_inode->i_ctime = CURRENT_TIME_SEC;
mutex_unlock(&coda_inode->i_mutex);
file_end_write(host_file);
-
return ret;
}
@@ -231,8 +219,8 @@ int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync)
const struct file_operations coda_file_operations = {
.llseek = generic_file_llseek,
- .read = coda_file_read,
- .write = coda_file_write,
+ .read_iter = coda_file_read_iter,
+ .write_iter = coda_file_write_iter,
.mmap = coda_file_mmap,
.open = coda_open,
.release = coda_release,
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 82ec68b59208..cac1390b87a3 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -257,15 +257,15 @@ static void coda_evict_inode(struct inode *inode)
int coda_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
- int err = coda_revalidate_inode(dentry->d_inode);
+ int err = coda_revalidate_inode(d_inode(dentry));
if (!err)
- generic_fillattr(dentry->d_inode, stat);
+ generic_fillattr(d_inode(dentry), stat);
return err;
}
int coda_setattr(struct dentry *de, struct iattr *iattr)
{
- struct inode *inode = de->d_inode;
+ struct inode *inode = d_inode(de);
struct coda_vattr vattr;
int error;
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index 4326d172fc27..f36a4040afb8 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -72,7 +72,7 @@ static long coda_pioctl(struct file *filp, unsigned int cmd,
if (error)
return error;
- target_inode = path.dentry->d_inode;
+ target_inode = d_inode(path.dentry);
/* return if it is not a Coda inode */
if (target_inode->i_sb != inode->i_sb) {
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index 5bb6e27298a4..9b1ffaa0572e 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -820,8 +820,8 @@ int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out)
case CODA_FLUSH:
coda_cache_clear_all(sb);
shrink_dcache_sb(sb);
- if (sb->s_root->d_inode)
- coda_flag_inode(sb->s_root->d_inode, C_FLUSH);
+ if (d_really_is_positive(sb->s_root))
+ coda_flag_inode(d_inode(sb->s_root), C_FLUSH);
break;
case CODA_PURGEUSER:
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index afec6450450f..6b8e2f091f5b 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -570,6 +570,7 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp)
#define BNEPCONNDEL _IOW('B', 201, int)
#define BNEPGETCONNLIST _IOR('B', 210, int)
#define BNEPGETCONNINFO _IOR('B', 211, int)
+#define BNEPGETSUPPFEAT _IOR('B', 212, int)
#define CMTPCONNADD _IOW('C', 200, int)
#define CMTPCONNDEL _IOW('C', 201, int)
@@ -1247,6 +1248,7 @@ COMPATIBLE_IOCTL(BNEPCONNADD)
COMPATIBLE_IOCTL(BNEPCONNDEL)
COMPATIBLE_IOCTL(BNEPGETCONNLIST)
COMPATIBLE_IOCTL(BNEPGETCONNINFO)
+COMPATIBLE_IOCTL(BNEPGETSUPPFEAT)
COMPATIBLE_IOCTL(CMTPCONNADD)
COMPATIBLE_IOCTL(CMTPCONNDEL)
COMPATIBLE_IOCTL(CMTPGETCONNLIST)
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index cf0db005d2f5..c81ce7f200a6 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -289,7 +289,7 @@ static int configfs_create_dir(struct config_item *item, struct dentry *dentry)
configfs_set_dir_dirent_depth(p->d_fsdata, dentry->d_fsdata);
error = configfs_create(dentry, mode, init_dir);
if (!error) {
- inc_nlink(p->d_inode);
+ inc_nlink(d_inode(p));
item->ci_dentry = dentry;
} else {
struct configfs_dirent *sd = dentry->d_fsdata;
@@ -375,8 +375,8 @@ static void remove_dir(struct dentry * d)
list_del_init(&sd->s_sibling);
spin_unlock(&configfs_dirent_lock);
configfs_put(sd);
- if (d->d_inode)
- simple_rmdir(parent->d_inode,d);
+ if (d_really_is_positive(d))
+ simple_rmdir(d_inode(parent),d);
pr_debug(" o %pd removing done (%d)\n", d, d_count(d));
@@ -513,7 +513,7 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex
/* Abort if racing with mkdir() */
if (sd->s_type & CONFIGFS_USET_IN_MKDIR) {
if (wait_mutex)
- *wait_mutex = &sd->s_dentry->d_inode->i_mutex;
+ *wait_mutex = &d_inode(sd->s_dentry)->i_mutex;
return -EAGAIN;
}
@@ -624,13 +624,13 @@ static void detach_groups(struct config_group *group)
child = sd->s_dentry;
- mutex_lock(&child->d_inode->i_mutex);
+ mutex_lock(&d_inode(child)->i_mutex);
configfs_detach_group(sd->s_element);
- child->d_inode->i_flags |= S_DEAD;
+ d_inode(child)->i_flags |= S_DEAD;
dont_mount(child);
- mutex_unlock(&child->d_inode->i_mutex);
+ mutex_unlock(&d_inode(child)->i_mutex);
d_delete(child);
dput(child);
@@ -672,7 +672,7 @@ static int create_default_group(struct config_group *parent_group,
sd = child->d_fsdata;
sd->s_type |= CONFIGFS_USET_DEFAULT;
} else {
- BUG_ON(child->d_inode);
+ BUG_ON(d_inode(child));
d_drop(child);
dput(child);
}
@@ -818,11 +818,11 @@ static int configfs_attach_item(struct config_item *parent_item,
* the VFS may already have hit and used them. Thus,
* we must lock them as rmdir() would.
*/
- mutex_lock(&dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(dentry)->i_mutex);
configfs_remove_dir(item);
- dentry->d_inode->i_flags |= S_DEAD;
+ d_inode(dentry)->i_flags |= S_DEAD;
dont_mount(dentry);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
d_delete(dentry);
}
}
@@ -858,16 +858,16 @@ static int configfs_attach_group(struct config_item *parent_item,
* We must also lock the inode to remove it safely in case of
* error, as rmdir() would.
*/
- mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+ mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_CHILD);
configfs_adjust_dir_dirent_depth_before_populate(sd);
ret = populate_groups(to_config_group(item));
if (ret) {
configfs_detach_item(item);
- dentry->d_inode->i_flags |= S_DEAD;
+ d_inode(dentry)->i_flags |= S_DEAD;
dont_mount(dentry);
}
configfs_adjust_dir_dirent_depth_after_populate(sd);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
if (ret)
d_delete(dentry);
}
@@ -1075,7 +1075,7 @@ int configfs_depend_item(struct configfs_subsystem *subsys,
* subsystem is really registered, and so we need to lock out
* configfs_[un]register_subsystem().
*/
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
root_sd = root->d_fsdata;
@@ -1111,7 +1111,7 @@ int configfs_depend_item(struct configfs_subsystem *subsys,
out_unlock_dirent_lock:
spin_unlock(&configfs_dirent_lock);
out_unlock_fs:
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
/*
* If we succeeded, the fs is pinned via other methods. If not,
@@ -1453,11 +1453,11 @@ int configfs_rename_dir(struct config_item * item, const char *new_name)
down_write(&configfs_rename_sem);
parent = item->parent->dentry;
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
new_dentry = lookup_one_len(new_name, parent, strlen(new_name));
if (!IS_ERR(new_dentry)) {
- if (!new_dentry->d_inode) {
+ if (d_really_is_negative(new_dentry)) {
error = config_item_set_name(item, "%s", new_name);
if (!error) {
d_add(new_dentry, NULL);
@@ -1469,7 +1469,7 @@ int configfs_rename_dir(struct config_item * item, const char *new_name)
error = -EEXIST;
dput(new_dentry);
}
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
up_write(&configfs_rename_sem);
return error;
@@ -1482,7 +1482,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file)
struct configfs_dirent * parent_sd = dentry->d_fsdata;
int err;
- mutex_lock(&dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(dentry)->i_mutex);
/*
* Fake invisibility if dir belongs to a group/default groups hierarchy
* being attached
@@ -1495,7 +1495,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file)
else
err = 0;
}
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
return err;
}
@@ -1505,11 +1505,11 @@ static int configfs_dir_close(struct inode *inode, struct file *file)
struct dentry * dentry = file->f_path.dentry;
struct configfs_dirent * cursor = file->private_data;
- mutex_lock(&dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(dentry)->i_mutex);
spin_lock(&configfs_dirent_lock);
list_del_init(&cursor->s_sibling);
spin_unlock(&configfs_dirent_lock);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
release_configfs_dirent(cursor);
@@ -1567,7 +1567,7 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx)
spin_lock(&configfs_dirent_lock);
dentry = next->s_dentry;
if (dentry)
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
if (inode)
ino = inode->i_ino;
spin_unlock(&configfs_dirent_lock);
@@ -1590,7 +1590,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry * dentry = file->f_path.dentry;
- mutex_lock(&dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(dentry)->i_mutex);
switch (whence) {
case 1:
offset += file->f_pos;
@@ -1598,7 +1598,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
if (offset >= 0)
break;
default:
- mutex_unlock(&file_inode(file)->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
return -EINVAL;
}
if (offset != file->f_pos) {
@@ -1624,7 +1624,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
spin_unlock(&configfs_dirent_lock);
}
}
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
return offset;
}
@@ -1654,7 +1654,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
sd = root->d_fsdata;
link_group(to_config_group(sd->s_element), group);
- mutex_lock_nested(&root->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&d_inode(root)->i_mutex, I_MUTEX_PARENT);
err = -ENOMEM;
dentry = d_alloc_name(root, group->cg_item.ci_name);
@@ -1664,7 +1664,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
err = configfs_attach_group(sd->s_element, &group->cg_item,
dentry);
if (err) {
- BUG_ON(dentry->d_inode);
+ BUG_ON(d_inode(dentry));
d_drop(dentry);
dput(dentry);
} else {
@@ -1674,7 +1674,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
}
}
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
if (err) {
unlink_group(group);
@@ -1695,9 +1695,9 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
return;
}
- mutex_lock_nested(&root->d_inode->i_mutex,
+ mutex_lock_nested(&d_inode(root)->i_mutex,
I_MUTEX_PARENT);
- mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+ mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_CHILD);
mutex_lock(&configfs_symlink_mutex);
spin_lock(&configfs_dirent_lock);
if (configfs_detach_prep(dentry, NULL)) {
@@ -1706,13 +1706,13 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
spin_unlock(&configfs_dirent_lock);
mutex_unlock(&configfs_symlink_mutex);
configfs_detach_group(&group->cg_item);
- dentry->d_inode->i_flags |= S_DEAD;
+ d_inode(dentry)->i_flags |= S_DEAD;
dont_mount(dentry);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry)->i_mutex);
d_delete(dentry);
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
dput(dentry);
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 56d2cdc9ae0a..403269ffcdf3 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -326,10 +326,10 @@ int configfs_create_file(struct config_item * item, const struct configfs_attrib
umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
int error = 0;
- mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL);
+ mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_NORMAL);
error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode,
CONFIGFS_ITEM_ATTR);
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
return error;
}
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 5423a6a6ecc8..8d89f5fd0331 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -56,7 +56,7 @@ static const struct inode_operations configfs_inode_operations ={
int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
{
- struct inode * inode = dentry->d_inode;
+ struct inode * inode = d_inode(dentry);
struct configfs_dirent * sd = dentry->d_fsdata;
struct iattr * sd_iattr;
unsigned int ia_valid = iattr->ia_valid;
@@ -186,7 +186,7 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in
if (!dentry)
return -ENOENT;
- if (dentry->d_inode)
+ if (d_really_is_positive(dentry))
return -EEXIST;
sd = dentry->d_fsdata;
@@ -194,7 +194,7 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in
if (!inode)
return -ENOMEM;
- p_inode = dentry->d_parent->d_inode;
+ p_inode = d_inode(dentry->d_parent);
p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
configfs_set_inode_lock_class(sd, inode);
@@ -236,11 +236,11 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
if (dentry) {
spin_lock(&dentry->d_lock);
- if (!d_unhashed(dentry) && dentry->d_inode) {
+ if (!d_unhashed(dentry) && d_really_is_positive(dentry)) {
dget_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
- simple_unlink(parent->d_inode, dentry);
+ simple_unlink(d_inode(parent), dentry);
} else
spin_unlock(&dentry->d_lock);
}
@@ -251,11 +251,11 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
struct configfs_dirent * sd;
struct configfs_dirent * parent_sd = dir->d_fsdata;
- if (dir->d_inode == NULL)
+ if (d_really_is_negative(dir))
/* no inode means this hasn't been made visible yet */
return;
- mutex_lock(&dir->d_inode->i_mutex);
+ mutex_lock(&d_inode(dir)->i_mutex);
list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
if (!sd->s_element)
continue;
@@ -268,5 +268,5 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
break;
}
}
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index da94e41bdbf6..537356742091 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -173,5 +173,5 @@ MODULE_LICENSE("GPL");
MODULE_VERSION("0.0.2");
MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration.");
-module_init(configfs_init);
+core_initcall(configfs_init);
module_exit(configfs_exit);
diff --git a/fs/coredump.c b/fs/coredump.c
index f319926ddf8c..bbbe139ab280 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -657,7 +657,7 @@ void do_coredump(const siginfo_t *siginfo)
*/
if (!uid_eq(inode->i_uid, current_fsuid()))
goto close_fail;
- if (!cprm.file->f_op->write)
+ if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
goto close_fail;
diff --git a/fs/dax.c b/fs/dax.c
index ed1619ec6537..6f65f00e58ec 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -98,9 +98,9 @@ static bool buffer_size_valid(struct buffer_head *bh)
return bh->b_state != 0;
}
-static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
- loff_t start, loff_t end, get_block_t get_block,
- struct buffer_head *bh)
+static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
+ loff_t start, loff_t end, get_block_t get_block,
+ struct buffer_head *bh)
{
ssize_t retval = 0;
loff_t pos = start;
@@ -109,7 +109,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
void *addr;
bool hole = false;
- if (rw != WRITE)
+ if (iov_iter_rw(iter) != WRITE)
end = min(end, i_size_read(inode));
while (pos < end) {
@@ -124,7 +124,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
retval = get_block(inode, block, bh,
- rw == WRITE);
+ iov_iter_rw(iter) == WRITE);
if (retval)
break;
if (!buffer_size_valid(bh))
@@ -137,7 +137,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
bh->b_size -= done;
}
- hole = (rw != WRITE) && !buffer_written(bh);
+ hole = iov_iter_rw(iter) != WRITE && !buffer_written(bh);
if (hole) {
addr = NULL;
size = bh->b_size - first;
@@ -154,7 +154,7 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
max = min(pos + size, end);
}
- if (rw == WRITE)
+ if (iov_iter_rw(iter) == WRITE)
len = copy_from_iter(addr, max - pos, iter);
else if (!hole)
len = copy_to_iter(addr, max - pos, iter);
@@ -173,7 +173,6 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
/**
* dax_do_io - Perform I/O to a DAX file
- * @rw: READ to read or WRITE to write
* @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
@@ -189,9 +188,9 @@ static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
* As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
* is in progress.
*/
-ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
- struct iov_iter *iter, loff_t pos,
- get_block_t get_block, dio_iodone_t end_io, int flags)
+ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
+ struct iov_iter *iter, loff_t pos, get_block_t get_block,
+ dio_iodone_t end_io, int flags)
{
struct buffer_head bh;
ssize_t retval = -EINVAL;
@@ -199,7 +198,7 @@ ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
memset(&bh, 0, sizeof(bh));
- if ((flags & DIO_LOCKING) && (rw == READ)) {
+ if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
struct address_space *mapping = inode->i_mapping;
mutex_lock(&inode->i_mutex);
retval = filemap_write_and_wait_range(mapping, pos, end - 1);
@@ -210,17 +209,17 @@ ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
}
/* Protects against truncate */
- atomic_inc(&inode->i_dio_count);
+ inode_dio_begin(inode);
- retval = dax_io(rw, inode, iter, pos, end, get_block, &bh);
+ retval = dax_io(inode, iter, pos, end, get_block, &bh);
- if ((flags & DIO_LOCKING) && (rw == READ))
+ if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
mutex_unlock(&inode->i_mutex);
if ((retval > 0) && end_io)
end_io(iocb, pos, retval, bh.b_private);
- inode_dio_done(inode);
+ inode_dio_end(inode);
out:
return retval;
}
@@ -464,6 +463,23 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
EXPORT_SYMBOL_GPL(dax_fault);
/**
+ * dax_pfn_mkwrite - handle first write to DAX page
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ *
+ */
+int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+ sb_start_pagefault(sb);
+ file_update_time(vma->vm_file);
+ sb_end_pagefault(sb);
+ return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
+
+/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
diff --git a/fs/dcache.c b/fs/dcache.c
index c71e3732e53b..656ce522a218 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -269,6 +269,41 @@ static inline int dname_external(const struct dentry *dentry)
return dentry->d_name.name != dentry->d_iname;
}
+/*
+ * Make sure other CPUs see the inode attached before the type is set.
+ */
+static inline void __d_set_inode_and_type(struct dentry *dentry,
+ struct inode *inode,
+ unsigned type_flags)
+{
+ unsigned flags;
+
+ dentry->d_inode = inode;
+ smp_wmb();
+ flags = READ_ONCE(dentry->d_flags);
+ flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+ flags |= type_flags;
+ WRITE_ONCE(dentry->d_flags, flags);
+}
+
+/*
+ * Ideally, we want to make sure that other CPUs see the flags cleared before
+ * the inode is detached, but this is really a violation of RCU principles
+ * since the ordering suggests we should always set inode before flags.
+ *
+ * We should instead replace or discard the entire dentry - but that sucks
+ * performancewise on mass deletion/rename.
+ */
+static inline void __d_clear_type_and_inode(struct dentry *dentry)
+{
+ unsigned flags = READ_ONCE(dentry->d_flags);
+
+ flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+ WRITE_ONCE(dentry->d_flags, flags);
+ smp_wmb();
+ dentry->d_inode = NULL;
+}
+
static void dentry_free(struct dentry *dentry)
{
WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
@@ -311,7 +346,7 @@ static void dentry_iput(struct dentry * dentry)
{
struct inode *inode = dentry->d_inode;
if (inode) {
- dentry->d_inode = NULL;
+ __d_clear_type_and_inode(dentry);
hlist_del_init(&dentry->d_u.d_alias);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
@@ -335,8 +370,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
__releases(dentry->d_inode->i_lock)
{
struct inode *inode = dentry->d_inode;
- __d_clear_type(dentry);
- dentry->d_inode = NULL;
+ __d_clear_type_and_inode(dentry);
hlist_del_init(&dentry->d_u.d_alias);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
@@ -1715,11 +1749,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
unsigned add_flags = d_flags_for_inode(inode);
spin_lock(&dentry->d_lock);
- dentry->d_flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
- dentry->d_flags |= add_flags;
if (inode)
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
- dentry->d_inode = inode;
+ __d_set_inode_and_type(dentry, inode, add_flags);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
fsnotify_d_instantiate(dentry, inode);
@@ -1937,8 +1969,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
add_flags |= DCACHE_DISCONNECTED;
spin_lock(&tmp->d_lock);
- tmp->d_inode = inode;
- tmp->d_flags |= add_flags;
+ __d_set_inode_and_type(tmp, inode, add_flags);
hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
hlist_bl_lock(&tmp->d_sb->s_anon);
hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
@@ -2690,7 +2721,7 @@ static int __d_unalias(struct inode *inode,
struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
- int ret = -EBUSY;
+ int ret = -ESTALE;
/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 517e64938438..830a7e76f5c6 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -45,7 +45,7 @@ const struct file_operations debugfs_file_operations = {
static void *debugfs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- nd_set_link(nd, dentry->d_inode->i_private);
+ nd_set_link(nd, d_inode(dentry)->i_private);
return NULL;
}
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 96400ab42d13..c1e7ffb0dab6 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -46,7 +46,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb)
static inline int debugfs_positive(struct dentry *dentry)
{
- return dentry->d_inode && !d_unhashed(dentry);
+ return d_really_is_positive(dentry) && !d_unhashed(dentry);
}
struct debugfs_mount_opts {
@@ -124,7 +124,7 @@ static int debugfs_parse_options(char *data, struct debugfs_mount_opts *opts)
static int debugfs_apply_options(struct super_block *sb)
{
struct debugfs_fs_info *fsi = sb->s_fs_info;
- struct inode *inode = sb->s_root->d_inode;
+ struct inode *inode = d_inode(sb->s_root);
struct debugfs_mount_opts *opts = &fsi->mount_opts;
inode->i_mode &= ~S_IALLUGO;
@@ -188,7 +188,7 @@ static struct vfsmount *debugfs_automount(struct path *path)
{
struct vfsmount *(*f)(void *);
f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata;
- return f(path->dentry->d_inode->i_private);
+ return f(d_inode(path->dentry)->i_private);
}
static const struct dentry_operations debugfs_dops = {
@@ -254,6 +254,9 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
pr_debug("debugfs: creating file '%s'\n",name);
+ if (IS_ERR(parent))
+ return parent;
+
error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
&debugfs_mount_count);
if (error)
@@ -267,20 +270,20 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
if (!parent)
parent = debugfs_mount->mnt_root;
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
dentry = lookup_one_len(name, parent, strlen(name));
- if (!IS_ERR(dentry) && dentry->d_inode) {
+ if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
dput(dentry);
dentry = ERR_PTR(-EEXIST);
}
if (IS_ERR(dentry))
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
return dentry;
}
static struct dentry *failed_creating(struct dentry *dentry)
{
- mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry->d_parent)->i_mutex);
dput(dentry);
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
return NULL;
@@ -288,7 +291,7 @@ static struct dentry *failed_creating(struct dentry *dentry)
static struct dentry *end_creating(struct dentry *dentry)
{
- mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dentry->d_parent)->i_mutex);
return dentry;
}
@@ -341,7 +344,7 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode,
inode->i_fop = fops ? fops : &debugfs_file_operations;
inode->i_private = data;
d_instantiate(dentry, inode);
- fsnotify_create(dentry->d_parent->d_inode, dentry);
+ fsnotify_create(d_inode(dentry->d_parent), dentry);
return end_creating(dentry);
}
EXPORT_SYMBOL_GPL(debugfs_create_file);
@@ -381,7 +384,7 @@ struct dentry *debugfs_create_file_size(const char *name, umode_t mode,
struct dentry *de = debugfs_create_file(name, mode, parent, data, fops);
if (de)
- de->d_inode->i_size = file_size;
+ d_inode(de)->i_size = file_size;
return de;
}
EXPORT_SYMBOL_GPL(debugfs_create_file_size);
@@ -423,8 +426,8 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
d_instantiate(dentry, inode);
- inc_nlink(dentry->d_parent->d_inode);
- fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
+ inc_nlink(d_inode(dentry->d_parent));
+ fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
return end_creating(dentry);
}
EXPORT_SYMBOL_GPL(debugfs_create_dir);
@@ -521,10 +524,10 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
if (debugfs_positive(dentry)) {
dget(dentry);
- if (S_ISDIR(dentry->d_inode->i_mode))
- ret = simple_rmdir(parent->d_inode, dentry);
+ if (d_is_dir(dentry))
+ ret = simple_rmdir(d_inode(parent), dentry);
else
- simple_unlink(parent->d_inode, dentry);
+ simple_unlink(d_inode(parent), dentry);
if (!ret)
d_delete(dentry);
dput(dentry);
@@ -554,12 +557,12 @@ void debugfs_remove(struct dentry *dentry)
return;
parent = dentry->d_parent;
- if (!parent || !parent->d_inode)
+ if (!parent || d_really_is_negative(parent))
return;
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
ret = __debugfs_remove(dentry, parent);
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
if (!ret)
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
@@ -585,12 +588,12 @@ void debugfs_remove_recursive(struct dentry *dentry)
return;
parent = dentry->d_parent;
- if (!parent || !parent->d_inode)
+ if (!parent || d_really_is_negative(parent))
return;
parent = dentry;
down:
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
loop:
/*
* The parent->d_subdirs is protected by the d_lock. Outside that
@@ -605,7 +608,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
/* perhaps simple_empty(child) makes more sense */
if (!list_empty(&child->d_subdirs)) {
spin_unlock(&parent->d_lock);
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
parent = child;
goto down;
}
@@ -626,10 +629,10 @@ void debugfs_remove_recursive(struct dentry *dentry)
}
spin_unlock(&parent->d_lock);
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
child = parent;
parent = parent->d_parent;
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
if (child != dentry)
/* go up */
@@ -637,7 +640,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
if (!__debugfs_remove(child, parent))
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
}
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
@@ -669,27 +672,27 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
trap = lock_rename(new_dir, old_dir);
/* Source or destination directories don't exist? */
- if (!old_dir->d_inode || !new_dir->d_inode)
+ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir))
goto exit;
/* Source does not exist, cyclic rename, or mountpoint? */
- if (!old_dentry->d_inode || old_dentry == trap ||
+ if (d_really_is_negative(old_dentry) || old_dentry == trap ||
d_mountpoint(old_dentry))
goto exit;
dentry = lookup_one_len(new_name, new_dir, strlen(new_name));
/* Lookup failed, cyclic rename or target exists? */
- if (IS_ERR(dentry) || dentry == trap || dentry->d_inode)
+ if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
goto exit;
old_name = fsnotify_oldname_init(old_dentry->d_name.name);
- error = simple_rename(old_dir->d_inode, old_dentry, new_dir->d_inode,
+ error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
dentry);
if (error) {
fsnotify_oldname_free(old_name);
goto exit;
}
d_move(old_dentry, dentry);
- fsnotify_move(old_dir->d_inode, new_dir->d_inode, old_name,
+ fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name,
d_is_dir(old_dentry),
NULL, old_dentry);
fsnotify_oldname_free(old_name);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index cfe8466f7fef..add566303c68 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -253,7 +253,7 @@ static int mknod_ptmx(struct super_block *sb)
if (!uid_valid(root_uid) || !gid_valid(root_gid))
return -EINVAL;
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
/* If we have already created ptmx node, return */
if (fsi->ptmx_dentry) {
@@ -290,7 +290,7 @@ static int mknod_ptmx(struct super_block *sb)
fsi->ptmx_dentry = dentry;
rc = 0;
out:
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
return rc;
}
@@ -298,7 +298,7 @@ static void update_ptmx_mode(struct pts_fs_info *fsi)
{
struct inode *inode;
if (fsi->ptmx_dentry) {
- inode = fsi->ptmx_dentry->d_inode;
+ inode = d_inode(fsi->ptmx_dentry);
inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode;
}
}
@@ -602,18 +602,18 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
sprintf(s, "%d", index);
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
dentry = d_alloc_name(root, s);
if (dentry) {
d_add(dentry, inode);
- fsnotify_create(root->d_inode, dentry);
+ fsnotify_create(d_inode(root), dentry);
} else {
iput(inode);
inode = ERR_PTR(-ENOMEM);
}
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
return inode;
}
@@ -658,7 +658,7 @@ void devpts_pty_kill(struct inode *inode)
BUG_ON(inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
- mutex_lock(&root->d_inode->i_mutex);
+ mutex_lock(&d_inode(root)->i_mutex);
dentry = d_find_alias(inode);
@@ -667,7 +667,7 @@ void devpts_pty_kill(struct inode *inode)
dput(dentry); /* d_alloc_name() in devpts_pty_new() */
dput(dentry); /* d_find_alias above */
- mutex_unlock(&root->d_inode->i_mutex);
+ mutex_unlock(&d_inode(root)->i_mutex);
}
static int __init init_devpts_fs(void)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index e181b6b2e297..745d2342651a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -37,7 +37,6 @@
#include <linux/uio.h>
#include <linux/atomic.h>
#include <linux/prefetch.h>
-#include <linux/aio.h>
/*
* How many user pages to map in one call to get_user_pages(). This determines
@@ -254,7 +253,9 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
if (dio->end_io && dio->result)
dio->end_io(dio->iocb, offset, transferred, dio->private);
- inode_dio_done(dio->inode);
+ if (!(dio->flags & DIO_SKIP_DIO_COUNT))
+ inode_dio_end(dio->inode);
+
if (is_async) {
if (dio->rw & WRITE) {
int err;
@@ -265,7 +266,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
ret = err;
}
- aio_complete(dio->iocb, ret, 0);
+ dio->iocb->ki_complete(dio->iocb, ret, 0);
}
kmem_cache_free(dio_cache, dio);
@@ -1056,7 +1057,7 @@ static inline int drop_refcount(struct dio *dio)
* operation. AIO can if it was a broken operation described above or
* in fact if all the bios race to complete before we get here. In
* that case dio_complete() translates the EIOCBQUEUED into the proper
- * return code that the caller will hand to aio_complete().
+ * return code that the caller will hand to ->complete().
*
* This is managed by the bio_lock instead of being an atomic_t so that
* completion paths can drop their ref and use the remaining count to
@@ -1094,10 +1095,10 @@ static inline int drop_refcount(struct dio *dio)
* for the whole file.
*/
static inline ssize_t
-do_blockdev_direct_IO(int rw, 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,
- dio_submit_t submit_io, int flags)
+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,
+ dio_submit_t submit_io, int flags)
{
unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits);
unsigned blkbits = i_blkbits;
@@ -1111,9 +1112,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct blk_plug plug;
unsigned long align = offset | iov_iter_alignment(iter);
- if (rw & WRITE)
- rw = WRITE_ODIRECT;
-
/*
* Avoid references to bdev if not absolutely needed to give
* the early prefetch in the caller enough time.
@@ -1128,7 +1126,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
}
/* watch out for a 0 len io from a tricksy fs */
- if (rw == READ && !iov_iter_count(iter))
+ if (iov_iter_rw(iter) == READ && !iov_iter_count(iter))
return 0;
dio = kmem_cache_alloc(dio_cache, GFP_KERNEL);
@@ -1144,7 +1142,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
dio->flags = flags;
if (dio->flags & DIO_LOCKING) {
- if (rw == READ) {
+ if (iov_iter_rw(iter) == READ) {
struct address_space *mapping =
iocb->ki_filp->f_mapping;
@@ -1170,19 +1168,19 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
if (is_sync_kiocb(iocb))
dio->is_async = false;
else if (!(dio->flags & DIO_ASYNC_EXTEND) &&
- (rw & WRITE) && end > i_size_read(inode))
+ iov_iter_rw(iter) == WRITE && end > i_size_read(inode))
dio->is_async = false;
else
dio->is_async = true;
dio->inode = inode;
- dio->rw = rw;
+ dio->rw = iov_iter_rw(iter) == WRITE ? WRITE_ODIRECT : READ;
/*
* For AIO O_(D)SYNC writes we need to defer completions to a workqueue
* so that we can call ->fsync.
*/
- if (dio->is_async && (rw & WRITE) &&
+ if (dio->is_async && iov_iter_rw(iter) == WRITE &&
((iocb->ki_filp->f_flags & O_DSYNC) ||
IS_SYNC(iocb->ki_filp->f_mapping->host))) {
retval = dio_set_defer_completion(dio);
@@ -1199,7 +1197,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
/*
* Will be decremented at I/O completion time.
*/
- atomic_inc(&inode->i_dio_count);
+ if (!(dio->flags & DIO_SKIP_DIO_COUNT))
+ inode_dio_begin(inode);
retval = 0;
sdio.blkbits = blkbits;
@@ -1275,7 +1274,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
* we can let i_mutex go now that its achieved its purpose
* of protecting us from looking up uninitialized blocks.
*/
- if (rw == READ && (dio->flags & DIO_LOCKING))
+ if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING))
mutex_unlock(&dio->inode->i_mutex);
/*
@@ -1287,7 +1286,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
*/
BUG_ON(retval == -EIOCBQUEUED);
if (dio->is_async && retval == 0 && dio->result &&
- (rw == READ || dio->result == count))
+ (iov_iter_rw(iter) == READ || dio->result == count))
retval = -EIOCBQUEUED;
else
dio_await_completion(dio);
@@ -1301,11 +1300,11 @@ out:
return retval;
}
-ssize_t
-__blockdev_direct_IO(int rw, 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,
- dio_submit_t submit_io, int flags)
+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,
+ dio_iodone_t end_io, dio_submit_t submit_io,
+ int flags)
{
/*
* The block device state is needed in the end to finally
@@ -1319,8 +1318,8 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
prefetch(bdev->bd_queue);
prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
- return do_blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset,
- get_block, end_io, submit_io, flags);
+ return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block,
+ end_io, submit_io, flags);
}
EXPORT_SYMBOL(__blockdev_direct_IO);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 719e1ce1c609..97315f2f6816 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1326,7 +1326,7 @@ static int ecryptfs_read_headers_virt(char *page_virt,
if (rc)
goto out;
if (!(crypt_stat->flags & ECRYPTFS_I_SIZE_INITIALIZED))
- ecryptfs_i_size_init(page_virt, ecryptfs_dentry->d_inode);
+ ecryptfs_i_size_init(page_virt, d_inode(ecryptfs_dentry));
offset += MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
rc = ecryptfs_process_flags(crypt_stat, (page_virt + offset),
&bytes_read);
@@ -1425,7 +1425,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
{
int rc;
char *page_virt;
- struct inode *ecryptfs_inode = ecryptfs_dentry->d_inode;
+ struct inode *ecryptfs_inode = d_inode(ecryptfs_dentry);
struct ecryptfs_crypt_stat *crypt_stat =
&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 4000f6b3a750..8db0b464483f 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -54,11 +54,11 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
return -ECHILD;
rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
- if (dentry->d_inode) {
+ if (d_really_is_positive(dentry)) {
struct inode *lower_inode =
- ecryptfs_inode_to_lower(dentry->d_inode);
+ ecryptfs_inode_to_lower(d_inode(dentry));
- fsstack_copy_attr_all(dentry->d_inode, lower_inode);
+ fsstack_copy_attr_all(d_inode(dentry), lower_inode);
}
return rc;
}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index fd39bad6f1bd..72afcc629d7b 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -31,7 +31,6 @@
#include <linux/security.h>
#include <linux/compat.h>
#include <linux/fs_stack.h>
-#include <linux/aio.h>
#include "ecryptfs_kernel.h"
/**
@@ -52,12 +51,6 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
struct file *file = iocb->ki_filp;
rc = generic_file_read_iter(iocb, to);
- /*
- * Even though this is a async interface, we need to wait
- * for IO to finish to update atime
- */
- if (-EIOCBQUEUED == rc)
- rc = wait_on_sync_kiocb(iocb);
if (rc >= 0) {
path = ecryptfs_dentry_to_lower_path(file->f_path.dentry);
touch_atime(path);
@@ -137,7 +130,7 @@ struct kmem_cache *ecryptfs_file_info_cache;
static int read_or_initialize_metadata(struct dentry *dentry)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct ecryptfs_crypt_stat *crypt_stat;
int rc;
@@ -365,9 +358,7 @@ const struct file_operations ecryptfs_dir_fops = {
const struct file_operations ecryptfs_main_fops = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
.read_iter = ecryptfs_read_update_atime,
- .write = new_sync_write,
.write_iter = generic_file_write_iter,
.iterate = ecryptfs_readdir,
.unlocked_ioctl = ecryptfs_unlocked_ioctl,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index b08b5187f662..fc850b55db67 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -41,13 +41,13 @@ static struct dentry *lock_parent(struct dentry *dentry)
struct dentry *dir;
dir = dget_parent(dentry);
- mutex_lock_nested(&(dir->d_inode->i_mutex), I_MUTEX_PARENT);
+ mutex_lock_nested(&(d_inode(dir)->i_mutex), I_MUTEX_PARENT);
return dir;
}
static void unlock_dir(struct dentry *dir)
{
- mutex_unlock(&dir->d_inode->i_mutex);
+ mutex_unlock(&d_inode(dir)->i_mutex);
dput(dir);
}
@@ -131,7 +131,7 @@ struct inode *ecryptfs_get_inode(struct inode *lower_inode,
static int ecryptfs_interpose(struct dentry *lower_dentry,
struct dentry *dentry, struct super_block *sb)
{
- struct inode *inode = ecryptfs_get_inode(lower_dentry->d_inode, sb);
+ struct inode *inode = ecryptfs_get_inode(d_inode(lower_dentry), sb);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -189,21 +189,21 @@ ecryptfs_do_create(struct inode *directory_inode,
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true);
+ rc = vfs_create(d_inode(lower_dir_dentry), lower_dentry, mode, true);
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
inode = ERR_PTR(rc);
goto out_lock;
}
- inode = __ecryptfs_get_inode(lower_dentry->d_inode,
+ inode = __ecryptfs_get_inode(d_inode(lower_dentry),
directory_inode->i_sb);
if (IS_ERR(inode)) {
- vfs_unlink(lower_dir_dentry->d_inode, lower_dentry, NULL);
+ vfs_unlink(d_inode(lower_dir_dentry), lower_dentry, NULL);
goto out_lock;
}
- fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
- fsstack_copy_inode_size(directory_inode, lower_dir_dentry->d_inode);
+ fsstack_copy_attr_times(directory_inode, d_inode(lower_dir_dentry));
+ fsstack_copy_inode_size(directory_inode, d_inode(lower_dir_dentry));
out_lock:
unlock_dir(lower_dir_dentry);
return inode;
@@ -332,7 +332,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
struct dentry *lower_dentry,
struct inode *dir_inode)
{
- struct inode *inode, *lower_inode = lower_dentry->d_inode;
+ struct inode *inode, *lower_inode = d_inode(lower_dentry);
struct ecryptfs_dentry_info *dentry_info;
struct vfsmount *lower_mnt;
int rc = 0;
@@ -347,14 +347,14 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
}
lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
- fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode);
+ fsstack_copy_attr_atime(dir_inode, d_inode(lower_dentry->d_parent));
BUG_ON(!d_count(lower_dentry));
ecryptfs_set_dentry_private(dentry, dentry_info);
dentry_info->lower_path.mnt = lower_mnt;
dentry_info->lower_path.dentry = lower_dentry;
- if (!lower_dentry->d_inode) {
+ if (d_really_is_negative(lower_dentry)) {
/* We want to add because we couldn't find in lower */
d_add(dentry, NULL);
return 0;
@@ -400,11 +400,11 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
int rc = 0;
lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
- mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(lower_dir_dentry)->i_mutex);
lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name,
lower_dir_dentry,
ecryptfs_dentry->d_name.len);
- mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(lower_dir_dentry)->i_mutex);
if (IS_ERR(lower_dentry)) {
rc = PTR_ERR(lower_dentry);
ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
@@ -412,7 +412,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
ecryptfs_dentry);
goto out;
}
- if (lower_dentry->d_inode)
+ if (d_really_is_positive(lower_dentry))
goto interpose;
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
@@ -429,11 +429,11 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
"filename; rc = [%d]\n", __func__, rc);
goto out;
}
- mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(lower_dir_dentry)->i_mutex);
lower_dentry = lookup_one_len(encrypted_and_encoded_name,
lower_dir_dentry,
encrypted_and_encoded_name_size);
- mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(lower_dir_dentry)->i_mutex);
if (IS_ERR(lower_dentry)) {
rc = PTR_ERR(lower_dentry);
ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
@@ -458,24 +458,24 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
u64 file_size_save;
int rc;
- file_size_save = i_size_read(old_dentry->d_inode);
+ file_size_save = i_size_read(d_inode(old_dentry));
lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
dget(lower_old_dentry);
dget(lower_new_dentry);
lower_dir_dentry = lock_parent(lower_new_dentry);
- rc = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
+ rc = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry),
lower_new_dentry, NULL);
- if (rc || !lower_new_dentry->d_inode)
+ if (rc || d_really_is_negative(lower_new_dentry))
goto out_lock;
rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
if (rc)
goto out_lock;
- fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
- set_nlink(old_dentry->d_inode,
- ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink);
- i_size_write(new_dentry->d_inode, file_size_save);
+ fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
+ set_nlink(d_inode(old_dentry),
+ ecryptfs_inode_to_lower(d_inode(old_dentry))->i_nlink);
+ i_size_write(d_inode(new_dentry), file_size_save);
out_lock:
unlock_dir(lower_dir_dentry);
dput(lower_new_dentry);
@@ -485,7 +485,7 @@ out_lock:
static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
{
- return ecryptfs_do_unlink(dir, dentry, dentry->d_inode);
+ return ecryptfs_do_unlink(dir, dentry, d_inode(dentry));
}
static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
@@ -510,20 +510,20 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
strlen(symname));
if (rc)
goto out_lock;
- rc = vfs_symlink(lower_dir_dentry->d_inode, lower_dentry,
+ rc = vfs_symlink(d_inode(lower_dir_dentry), lower_dentry,
encoded_symname);
kfree(encoded_symname);
- if (rc || !lower_dentry->d_inode)
+ if (rc || d_really_is_negative(lower_dentry))
goto out_lock;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out_lock;
- fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
+ fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
out_lock:
unlock_dir(lower_dir_dentry);
dput(lower_dentry);
- if (!dentry->d_inode)
+ if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
}
@@ -536,18 +536,18 @@ static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_mkdir(lower_dir_dentry->d_inode, lower_dentry, mode);
- if (rc || !lower_dentry->d_inode)
+ rc = vfs_mkdir(d_inode(lower_dir_dentry), lower_dentry, mode);
+ if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out;
- fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
- set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
+ fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
+ set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
out:
unlock_dir(lower_dir_dentry);
- if (!dentry->d_inode)
+ if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
}
@@ -562,12 +562,12 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
dget(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
dget(lower_dentry);
- rc = vfs_rmdir(lower_dir_dentry->d_inode, lower_dentry);
+ rc = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry);
dput(lower_dentry);
- if (!rc && dentry->d_inode)
- clear_nlink(dentry->d_inode);
- fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
+ if (!rc && d_really_is_positive(dentry))
+ clear_nlink(d_inode(dentry));
+ fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
+ set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
unlock_dir(lower_dir_dentry);
if (!rc)
d_drop(dentry);
@@ -584,17 +584,17 @@ ecryptfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_mknod(lower_dir_dentry->d_inode, lower_dentry, mode, dev);
- if (rc || !lower_dentry->d_inode)
+ rc = vfs_mknod(d_inode(lower_dir_dentry), lower_dentry, mode, dev);
+ if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out;
- fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
+ fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
out:
unlock_dir(lower_dir_dentry);
- if (!dentry->d_inode)
+ if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
}
@@ -617,7 +617,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
dget(lower_new_dentry);
lower_old_dir_dentry = dget_parent(lower_old_dentry);
lower_new_dir_dentry = dget_parent(lower_new_dentry);
- target_inode = new_dentry->d_inode;
+ target_inode = d_inode(new_dentry);
trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
/* source should not be ancestor of target */
if (trap == lower_old_dentry) {
@@ -629,17 +629,17 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
rc = -ENOTEMPTY;
goto out_lock;
}
- rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
- lower_new_dir_dentry->d_inode, lower_new_dentry,
+ rc = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry,
+ d_inode(lower_new_dir_dentry), lower_new_dentry,
NULL, 0);
if (rc)
goto out_lock;
if (target_inode)
fsstack_copy_attr_all(target_inode,
ecryptfs_inode_to_lower(target_inode));
- fsstack_copy_attr_all(new_dir, lower_new_dir_dentry->d_inode);
+ fsstack_copy_attr_all(new_dir, d_inode(lower_new_dir_dentry));
if (new_dir != old_dir)
- fsstack_copy_attr_all(old_dir, lower_old_dir_dentry->d_inode);
+ fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry));
out_lock:
unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
dput(lower_new_dir_dentry);
@@ -662,7 +662,7 @@ static char *ecryptfs_readlink_lower(struct dentry *dentry, size_t *bufsiz)
return ERR_PTR(-ENOMEM);
old_fs = get_fs();
set_fs(get_ds());
- rc = lower_dentry->d_inode->i_op->readlink(lower_dentry,
+ rc = d_inode(lower_dentry)->i_op->readlink(lower_dentry,
(char __user *)lower_buf,
PATH_MAX);
set_fs(old_fs);
@@ -681,8 +681,8 @@ static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd)
char *buf = ecryptfs_readlink_lower(dentry, &len);
if (IS_ERR(buf))
goto out;
- fsstack_copy_attr_atime(dentry->d_inode,
- ecryptfs_dentry_to_lower(dentry)->d_inode);
+ fsstack_copy_attr_atime(d_inode(dentry),
+ d_inode(ecryptfs_dentry_to_lower(dentry)));
buf[len] = '\0';
out:
nd_set_link(nd, buf);
@@ -738,7 +738,7 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
struct iattr *lower_ia)
{
int rc = 0;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ecryptfs_crypt_stat *crypt_stat;
loff_t i_size = i_size_read(inode);
loff_t lower_size_before_truncate;
@@ -751,7 +751,7 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
rc = ecryptfs_get_lower_file(dentry, inode);
if (rc)
return rc;
- crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
+ crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat;
/* Switch on growing or shrinking file */
if (ia->ia_size > i_size) {
char zero[] = { 0x00 };
@@ -858,7 +858,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
struct iattr lower_ia = { .ia_valid = 0 };
int rc;
- rc = ecryptfs_inode_newsize_ok(dentry->d_inode, new_length);
+ rc = ecryptfs_inode_newsize_ok(d_inode(dentry), new_length);
if (rc)
return rc;
@@ -866,9 +866,9 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
if (!rc && lower_ia.ia_valid & ATTR_SIZE) {
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
- mutex_lock(&lower_dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(lower_dentry)->i_mutex);
rc = notify_change(lower_dentry, &lower_ia, NULL);
- mutex_unlock(&lower_dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(lower_dentry)->i_mutex);
}
return rc;
}
@@ -900,10 +900,10 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
struct inode *lower_inode;
struct ecryptfs_crypt_stat *crypt_stat;
- crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->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);
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
lower_inode = ecryptfs_inode_to_lower(inode);
lower_dentry = ecryptfs_dentry_to_lower(dentry);
mutex_lock(&crypt_stat->cs_mutex);
@@ -967,9 +967,9 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
lower_ia.ia_valid &= ~ATTR_MODE;
- mutex_lock(&lower_dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(lower_dentry)->i_mutex);
rc = notify_change(lower_dentry, &lower_ia, NULL);
- mutex_unlock(&lower_dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(lower_dentry)->i_mutex);
out:
fsstack_copy_attr_all(inode, lower_inode);
return rc;
@@ -983,7 +983,7 @@ static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
mount_crypt_stat = &ecryptfs_superblock_to_private(
dentry->d_sb)->mount_crypt_stat;
- generic_fillattr(dentry->d_inode, stat);
+ generic_fillattr(d_inode(dentry), stat);
if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
char *target;
size_t targetsiz;
@@ -1007,9 +1007,9 @@ static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat);
if (!rc) {
- fsstack_copy_attr_all(dentry->d_inode,
- ecryptfs_inode_to_lower(dentry->d_inode));
- generic_fillattr(dentry->d_inode, stat);
+ fsstack_copy_attr_all(d_inode(dentry),
+ ecryptfs_inode_to_lower(d_inode(dentry)));
+ generic_fillattr(d_inode(dentry), stat);
stat->blocks = lower_stat.blocks;
}
return rc;
@@ -1023,14 +1023,14 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!lower_dentry->d_inode->i_op->setxattr) {
+ if (!d_inode(lower_dentry)->i_op->setxattr) {
rc = -EOPNOTSUPP;
goto out;
}
rc = vfs_setxattr(lower_dentry, name, value, size, flags);
- if (!rc && dentry->d_inode)
- fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
+ if (!rc && d_really_is_positive(dentry))
+ fsstack_copy_attr_all(d_inode(dentry), d_inode(lower_dentry));
out:
return rc;
}
@@ -1041,14 +1041,14 @@ ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
{
int rc = 0;
- if (!lower_dentry->d_inode->i_op->getxattr) {
+ if (!d_inode(lower_dentry)->i_op->getxattr) {
rc = -EOPNOTSUPP;
goto out;
}
- mutex_lock(&lower_dentry->d_inode->i_mutex);
- rc = lower_dentry->d_inode->i_op->getxattr(lower_dentry, name, value,
+ mutex_lock(&d_inode(lower_dentry)->i_mutex);
+ rc = d_inode(lower_dentry)->i_op->getxattr(lower_dentry, name, value,
size);
- mutex_unlock(&lower_dentry->d_inode->i_mutex);
+ mutex_unlock(&d_inode(lower_dentry)->i_mutex);
out:
return rc;
}
@@ -1068,13 +1068,13 @@ ecryptfs_listxattr(struct dentry *dentry, char *list, size_t size)
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!lower_dentry->d_inode->i_op->listxattr) {
+ if (!d_inode(lower_dentry)->i_op->listxattr) {
rc = -EOPNOTSUPP;
goto out;
}
- mutex_lock(&lower_dentry->d_inode->i_mutex);
- rc = lower_dentry->d_inode->i_op->listxattr(lower_dentry, list, size);
- mutex_unlock(&lower_dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(lower_dentry)->i_mutex);
+ rc = d_inode(lower_dentry)->i_op->listxattr(lower_dentry, list, size);
+ mutex_unlock(&d_inode(lower_dentry)->i_mutex);
out:
return rc;
}
@@ -1085,13 +1085,13 @@ static int ecryptfs_removexattr(struct dentry *dentry, const char *name)
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!lower_dentry->d_inode->i_op->removexattr) {
+ if (!d_inode(lower_dentry)->i_op->removexattr) {
rc = -EOPNOTSUPP;
goto out;
}
- mutex_lock(&lower_dentry->d_inode->i_mutex);
- rc = lower_dentry->d_inode->i_op->removexattr(lower_dentry, name);
- mutex_unlock(&lower_dentry->d_inode->i_mutex);
+ mutex_lock(&d_inode(lower_dentry)->i_mutex);
+ rc = d_inode(lower_dentry)->i_op->removexattr(lower_dentry, name);
+ mutex_unlock(&d_inode(lower_dentry)->i_mutex);
out:
return rc;
}
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index f1ea610362c6..866bb18efefe 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -144,7 +144,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
/* Corresponding dput() and mntput() are done when the
* lower file is fput() when all eCryptfs files for the inode are
* released. */
- flags |= IS_RDONLY(lower_dentry->d_inode) ? O_RDONLY : O_RDWR;
+ flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
(*lower_file) = dentry_open(&req.path, flags, cred);
if (!IS_ERR(*lower_file))
goto out;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index c095d3264259..4f4d0474bee9 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -546,11 +546,11 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
goto out_free;
}
- if (check_ruid && !uid_eq(path.dentry->d_inode->i_uid, current_uid())) {
+ if (check_ruid && !uid_eq(d_inode(path.dentry)->i_uid, current_uid())) {
rc = -EPERM;
printk(KERN_ERR "Mount of device (uid: %d) not owned by "
"requested user (uid: %d)\n",
- i_uid_read(path.dentry->d_inode),
+ i_uid_read(d_inode(path.dentry)),
from_kuid(&init_user_ns, current_uid()));
goto out_free;
}
@@ -584,7 +584,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
goto out_free;
}
- inode = ecryptfs_get_inode(path.dentry->d_inode, s);
+ inode = ecryptfs_get_inode(d_inode(path.dentry), s);
rc = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_free;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 4626976794e7..cf208522998e 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -420,7 +420,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
void *xattr_virt;
struct dentry *lower_dentry =
ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry;
- struct inode *lower_inode = lower_dentry->d_inode;
+ struct inode *lower_inode = d_inode(lower_dentry);
int rc;
if (!lower_inode->i_op->getxattr || !lower_inode->i_op->setxattr) {
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 07ab49745e31..3381b9da9ee6 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -145,12 +145,12 @@ out:
static int efivarfs_unlink(struct inode *dir, struct dentry *dentry)
{
- struct efivar_entry *var = dentry->d_inode->i_private;
+ struct efivar_entry *var = d_inode(dentry)->i_private;
if (efivar_entry_delete(var))
return -EINVAL;
- drop_nlink(dentry->d_inode);
+ drop_nlink(d_inode(dentry));
dput(dentry);
return 0;
};
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index ddbce42548c9..86a2121828c3 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -121,7 +121,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
int len, i;
int err = -ENOMEM;
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return err;
@@ -144,7 +144,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
- inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0);
+ inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0);
if (!inode)
goto fail_name;
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index bbee8f063dfa..40ba9cc41bf7 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -111,9 +111,9 @@ struct dentry *efs_get_parent(struct dentry *child)
struct dentry *parent = ERR_PTR(-ENOENT);
efs_ino_t ino;
- ino = efs_find_entry(child->d_inode, "..", 2);
+ ino = efs_find_entry(d_inode(child), "..", 2);
if (ino)
- parent = d_obtain_alias(efs_iget(child->d_inode->i_sb, ino));
+ parent = d_obtain_alias(efs_iget(d_inode(child)->i_sb, ino));
return parent;
}
diff --git a/fs/exec.c b/fs/exec.c
index c7f9b733406d..1977c2a553ac 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -659,6 +659,9 @@ int setup_arg_pages(struct linux_binprm *bprm,
if (stack_base > STACK_SIZE_MAX)
stack_base = STACK_SIZE_MAX;
+ /* Add space for stack randomization. */
+ stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+
/* Make sure we didn't let the argument array grow too large. */
if (vma->vm_end - vma->vm_start > stack_base)
return -ENOMEM;
@@ -926,10 +929,14 @@ static int de_thread(struct task_struct *tsk)
if (!thread_group_leader(tsk)) {
struct task_struct *leader = tsk->group_leader;
- sig->notify_count = -1; /* for exit_notify() */
for (;;) {
threadgroup_change_begin(tsk);
write_lock_irq(&tasklist_lock);
+ /*
+ * Do this under tasklist_lock to ensure that
+ * exit_notify() can't miss ->group_exit_task
+ */
+ sig->notify_count = -1;
if (likely(leader->exit_state))
break;
__set_current_state(TASK_KILLABLE);
@@ -1078,7 +1085,13 @@ int flush_old_exec(struct linux_binprm * bprm)
if (retval)
goto out;
+ /*
+ * Must be called _before_ exec_mmap() as bprm->mm is
+ * not visibile until then. This also enables the update
+ * to be lockless.
+ */
set_mm_exe_file(bprm->mm, bprm->file);
+
/*
* Release all of the old mmap stuff
*/
@@ -1265,6 +1278,53 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
spin_unlock(&p->fs->lock);
}
+static void bprm_fill_uid(struct linux_binprm *bprm)
+{
+ struct inode *inode;
+ unsigned int mode;
+ kuid_t uid;
+ kgid_t gid;
+
+ /* clear any previous set[ug]id data from a previous binary */
+ bprm->cred->euid = current_euid();
+ bprm->cred->egid = current_egid();
+
+ if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+ return;
+
+ if (task_no_new_privs(current))
+ return;
+
+ inode = file_inode(bprm->file);
+ mode = READ_ONCE(inode->i_mode);
+ if (!(mode & (S_ISUID|S_ISGID)))
+ return;
+
+ /* Be careful if suid/sgid is set */
+ mutex_lock(&inode->i_mutex);
+
+ /* reload atomically mode/uid/gid now that lock held */
+ mode = inode->i_mode;
+ uid = inode->i_uid;
+ gid = inode->i_gid;
+ mutex_unlock(&inode->i_mutex);
+
+ /* We ignore suid/sgid if there are no mappings for them in the ns */
+ if (!kuid_has_mapping(bprm->cred->user_ns, uid) ||
+ !kgid_has_mapping(bprm->cred->user_ns, gid))
+ return;
+
+ if (mode & S_ISUID) {
+ bprm->per_clear |= PER_CLEAR_ON_SETID;
+ bprm->cred->euid = uid;
+ }
+
+ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+ bprm->per_clear |= PER_CLEAR_ON_SETID;
+ bprm->cred->egid = gid;
+ }
+}
+
/*
* Fill the binprm structure from the inode.
* Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
@@ -1273,36 +1333,9 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
*/
int prepare_binprm(struct linux_binprm *bprm)
{
- struct inode *inode = file_inode(bprm->file);
- umode_t mode = inode->i_mode;
int retval;
-
- /* clear any previous set[ug]id data from a previous binary */
- bprm->cred->euid = current_euid();
- bprm->cred->egid = current_egid();
-
- if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
- !task_no_new_privs(current) &&
- kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
- kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
- /* Set-uid? */
- if (mode & S_ISUID) {
- bprm->per_clear |= PER_CLEAR_ON_SETID;
- bprm->cred->euid = inode->i_uid;
- }
-
- /* Set-gid? */
- /*
- * If setgid is set but no group execute bit then this
- * is a candidate for mandatory locking, not a setgid
- * executable.
- */
- if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
- bprm->per_clear |= PER_CLEAR_ON_SETID;
- bprm->cred->egid = inode->i_gid;
- }
- }
+ bprm_fill_uid(bprm);
/* fill in binprm security blob */
retval = security_bprm_set_creds(bprm);
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index d7defd557601..4deb0b05b011 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -379,7 +379,7 @@ ino_t exofs_parent_ino(struct dentry *child)
struct exofs_dir_entry *de;
ino_t ino;
- de = exofs_dotdot(child->d_inode, &page);
+ de = exofs_dotdot(d_inode(child), &page);
if (!de)
return 0;
@@ -429,7 +429,7 @@ int exofs_set_link(struct inode *dir, struct exofs_dir_entry *de,
int exofs_add_link(struct dentry *dentry, struct inode *inode)
{
- struct inode *dir = dentry->d_parent->d_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 = exofs_chunk_size(dir);
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
index 1a376b42d305..906de66e8e7e 100644
--- a/fs/exofs/file.c
+++ b/fs/exofs/file.c
@@ -67,8 +67,6 @@ static int exofs_flush(struct file *file, fl_owner_t id)
const struct file_operations exofs_file_operations = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.mmap = generic_file_mmap,
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index a198e94813fe..786e4cc8c889 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -963,8 +963,8 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset,
/* TODO: Should be easy enough to do proprly */
-static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb,
- struct iov_iter *iter, loff_t offset)
+static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
return 0;
}
@@ -1028,7 +1028,7 @@ static int _do_truncate(struct inode *inode, loff_t newsize)
*/
int exofs_setattr(struct dentry *dentry, struct iattr *iattr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int error;
/* if we are about to modify an object, and it hasn't been
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index 28907460e8fa..5ae25e431191 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -141,7 +141,7 @@ out_fail:
static int exofs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
inode->i_ctime = CURRENT_TIME;
inode_inc_link_count(inode);
@@ -191,7 +191,7 @@ out_dir:
static int exofs_unlink(struct inode *dir, struct dentry *dentry)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct exofs_dir_entry *de;
struct page *page;
int err = -ENOENT;
@@ -213,7 +213,7 @@ out:
static int exofs_rmdir(struct inode *dir, struct dentry *dentry)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int err = -ENOTEMPTY;
if (exofs_empty_dir(inode)) {
@@ -230,8 +230,8 @@ static int exofs_rmdir(struct inode *dir, struct dentry *dentry)
static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
- struct inode *old_inode = old_dentry->d_inode;
- struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = d_inode(old_dentry);
+ struct inode *new_inode = d_inode(new_dentry);
struct page *dir_page = NULL;
struct exofs_dir_entry *dir_de = NULL;
struct page *old_page;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index fcc2e565f540..b795c567b5e1 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -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(child->d_inode->i_sb, ino));
+ return d_obtain_alias(exofs_iget(d_inode(child)->i_sb, ino));
}
static struct inode *exofs_nfs_get_inode(struct super_block *sb,
diff --git a/fs/exofs/symlink.c b/fs/exofs/symlink.c
index 832e2624b80b..6f6f3a4c1365 100644
--- a/fs/exofs/symlink.c
+++ b/fs/exofs/symlink.c
@@ -37,7 +37,7 @@
static void *exofs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- struct exofs_i_info *oi = exofs_i(dentry->d_inode);
+ struct exofs_i_info *oi = exofs_i(d_inode(dentry));
nd_set_link(nd, (char *)oi->i_data);
return NULL;
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 6e1d4ab09d72..796b491e6978 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -486,7 +486,7 @@ void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
*/
int ext2_add_link (struct dentry *dentry, struct inode *inode)
{
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned chunk_size = ext2_chunk_size(dir);
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 678f9ab08c48..8d15febd0aa3 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -793,7 +793,6 @@ extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
extern const struct inode_operations ext2_file_inode_operations;
extern const struct file_operations ext2_file_operations;
-extern const struct file_operations ext2_dax_file_operations;
/* inode.c */
extern const struct address_space_operations ext2_aops;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index e31701713516..3a0a6c6406d0 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -39,6 +39,7 @@ static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
static const struct vm_operations_struct ext2_dax_vm_ops = {
.fault = ext2_dax_fault,
.page_mkwrite = ext2_dax_mkwrite,
+ .pfn_mkwrite = dax_pfn_mkwrite,
};
static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -92,8 +93,6 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
*/
const struct file_operations ext2_file_operations = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.unlocked_ioctl = ext2_ioctl,
@@ -108,24 +107,6 @@ const struct file_operations ext2_file_operations = {
.splice_write = iter_file_splice_write,
};
-#ifdef CONFIG_FS_DAX
-const struct file_operations ext2_dax_file_operations = {
- .llseek = generic_file_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
- .read_iter = generic_file_read_iter,
- .write_iter = generic_file_write_iter,
- .unlocked_ioctl = ext2_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext2_compat_ioctl,
-#endif
- .mmap = ext2_file_mmap,
- .open = dquot_file_open,
- .release = ext2_release_file,
- .fsync = ext2_fsync,
-};
-#endif
-
const struct inode_operations ext2_file_inode_operations = {
#ifdef CONFIG_EXT2_FS_XATTR
.setxattr = generic_setxattr,
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 6c14bb8322fa..5c04a0ddea80 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -278,7 +278,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
avefreeb = free_blocks / ngroups;
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
- if ((parent == sb->s_root->d_inode) ||
+ if ((parent == d_inode(sb->s_root)) ||
(EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) {
struct ext2_group_desc *best_desc = NULL;
int best_ndir = inodes_per_group;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 6434bc000125..f460ae36d5b7 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,7 +31,7 @@
#include <linux/mpage.h>
#include <linux/fiemap.h>
#include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
#include "ext2.h"
#include "acl.h"
#include "xattr.h"
@@ -851,8 +851,7 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
}
static ssize_t
-ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -861,12 +860,12 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
ssize_t ret;
if (IS_DAX(inode))
- ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block,
- NULL, DIO_LOCKING);
+ ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL,
+ DIO_LOCKING);
else
- ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+ ret = blockdev_direct_IO(iocb, inode, iter, offset,
ext2_get_block);
- if (ret < 0 && (rw & WRITE))
+ if (ret < 0 && iov_iter_rw(iter) == WRITE)
ext2_write_failed(mapping, offset + count);
return ret;
}
@@ -1388,10 +1387,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext2_file_inode_operations;
- if (test_opt(inode->i_sb, DAX)) {
- inode->i_mapping->a_ops = &ext2_aops;
- inode->i_fop = &ext2_dax_file_operations;
- } else if (test_opt(inode->i_sb, NOBH)) {
+ if (test_opt(inode->i_sb, NOBH)) {
inode->i_mapping->a_ops = &ext2_nobh_aops;
inode->i_fop = &ext2_file_operations;
} else {
@@ -1548,7 +1544,7 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc)
int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int error;
error = inode_change_ok(inode, iattr);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 148f6e3789ea..3e074a9ccbe6 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -79,10 +79,10 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, uns
struct dentry *ext2_get_parent(struct dentry *child)
{
struct qstr dotdot = QSTR_INIT("..", 2);
- unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
+ unsigned long ino = ext2_inode_by_name(d_inode(child), &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
- return d_obtain_alias(ext2_iget(child->d_inode->i_sb, ino));
+ return d_obtain_alias(ext2_iget(d_inode(child)->i_sb, ino));
}
/*
@@ -104,10 +104,7 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
return PTR_ERR(inode);
inode->i_op = &ext2_file_inode_operations;
- if (test_opt(inode->i_sb, DAX)) {
- inode->i_mapping->a_ops = &ext2_aops;
- inode->i_fop = &ext2_dax_file_operations;
- } else if (test_opt(inode->i_sb, NOBH)) {
+ if (test_opt(inode->i_sb, NOBH)) {
inode->i_mapping->a_ops = &ext2_nobh_aops;
inode->i_fop = &ext2_file_operations;
} else {
@@ -125,10 +122,7 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
return PTR_ERR(inode);
inode->i_op = &ext2_file_inode_operations;
- if (test_opt(inode->i_sb, DAX)) {
- inode->i_mapping->a_ops = &ext2_aops;
- inode->i_fop = &ext2_dax_file_operations;
- } else if (test_opt(inode->i_sb, NOBH)) {
+ if (test_opt(inode->i_sb, NOBH)) {
inode->i_mapping->a_ops = &ext2_nobh_aops;
inode->i_fop = &ext2_file_operations;
} else {
@@ -214,7 +208,7 @@ out_fail:
static int ext2_link (struct dentry * old_dentry, struct inode * dir,
struct dentry *dentry)
{
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
int err;
dquot_initialize(dir);
@@ -281,7 +275,7 @@ out_dir:
static int ext2_unlink(struct inode * dir, struct dentry *dentry)
{
- struct inode * inode = dentry->d_inode;
+ struct inode * inode = d_inode(dentry);
struct ext2_dir_entry_2 * de;
struct page * page;
int err = -ENOENT;
@@ -305,7 +299,7 @@ out:
static int ext2_rmdir (struct inode * dir, struct dentry *dentry)
{
- struct inode * inode = dentry->d_inode;
+ struct inode * inode = d_inode(dentry);
int err = -ENOTEMPTY;
if (ext2_empty_dir(inode)) {
@@ -322,8 +316,8 @@ static int ext2_rmdir (struct inode * dir, struct dentry *dentry)
static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
struct inode * new_dir, struct dentry * new_dentry )
{
- struct inode * old_inode = old_dentry->d_inode;
- struct inode * new_inode = new_dentry->d_inode;
+ struct inode * old_inode = d_inode(old_dentry);
+ struct inode * new_inode = d_inode(new_dentry);
struct page * dir_page = NULL;
struct ext2_dir_entry_2 * dir_de = NULL;
struct page * old_page;
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index 565cf817bbf1..20608f17c2e5 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -23,7 +23,7 @@
static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- struct ext2_inode_info *ei = EXT2_I(dentry->d_inode);
+ struct ext2_inode_info *ei = EXT2_I(d_inode(dentry));
nd_set_link(nd, (char *)ei->i_data);
return NULL;
}
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 91426141c33a..0b6bfd3a398b 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -243,7 +243,7 @@ cleanup:
static int
ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
struct ext2_xattr_entry *entry;
char *end;
@@ -319,7 +319,7 @@ cleanup:
/*
* Inode operation listxattr()
*
- * dentry->d_inode->i_mutex: don't care
+ * d_inode(dentry)->i_mutex: don't care
*/
ssize_t
ext2_listxattr(struct dentry *dentry, char *buffer, size_t size)
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index c0ebc4db8849..702fc6840246 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -28,7 +28,7 @@ ext2_xattr_security_get(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
buffer, size);
}
@@ -38,7 +38,7 @@ ext2_xattr_security_set(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 7e192574c001..42b6e9874bcc 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -32,7 +32,7 @@ ext2_xattr_trusted_get(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
buffer, size);
}
@@ -42,7 +42,7 @@ ext2_xattr_trusted_set(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index f470e44c4b8d..ecdc4605192c 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -36,7 +36,7 @@ ext2_xattr_user_get(struct dentry *dentry, const char *name,
return -EINVAL;
if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+ return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER,
name, buffer, size);
}
@@ -49,7 +49,7 @@ ext2_xattr_user_set(struct dentry *dentry, const char *name,
if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+ return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_USER,
name, value, size, flags);
}
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index a062fa1e1b11..3b8f650de22c 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -50,8 +50,6 @@ static int ext3_release_file (struct inode * inode, struct file * filp)
const struct file_operations ext3_file_operations = {
.llseek = generic_file_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.unlocked_ioctl = ext3_ioctl,
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index a1b810230cc5..3ad242e5840e 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -210,7 +210,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
avefreeb = freeb / ngroups;
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
- if ((parent == sb->s_root->d_inode) ||
+ if ((parent == d_inode(sb->s_root)) ||
(EXT3_I(parent)->i_flags & EXT3_TOPDIR_FL)) {
int best_ndir = inodes_per_group;
int best_group = -1;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2c6ccc49ba27..2ee2dc4351d1 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -27,7 +27,7 @@
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
#include "ext3.h"
#include "xattr.h"
#include "acl.h"
@@ -1820,8 +1820,8 @@ static int ext3_releasepage(struct page *page, gfp_t wait)
* crashes then stale disk data _may_ be exposed inside the file. But current
* VFS code falls back into buffered path in that case so we are safe.
*/
-static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
- struct iov_iter *iter, loff_t offset)
+static ssize_t ext3_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -1832,9 +1832,9 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
size_t count = iov_iter_count(iter);
int retries = 0;
- trace_ext3_direct_IO_enter(inode, offset, count, rw);
+ trace_ext3_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (rw == WRITE) {
+ if (iov_iter_rw(iter) == WRITE) {
loff_t final_size = offset + count;
if (final_size > inode->i_size) {
@@ -1856,12 +1856,12 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
}
retry:
- ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block);
+ ret = blockdev_direct_IO(iocb, inode, iter, offset, ext3_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
- if (unlikely((rw & WRITE) && ret < 0)) {
+ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
loff_t isize = i_size_read(inode);
loff_t end = offset + count;
@@ -1908,7 +1908,7 @@ retry:
ret = err;
}
out:
- trace_ext3_direct_IO_exit(inode, offset, count, rw, ret);
+ trace_ext3_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
return ret;
}
@@ -3240,7 +3240,7 @@ int ext3_write_inode(struct inode *inode, struct writeback_control *wbc)
*/
int ext3_setattr(struct dentry *dentry, struct iattr *attr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int error, rc = 0;
const unsigned int ia_valid = attr->ia_valid;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index f197736dccfa..4264b9bd0002 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1049,19 +1049,19 @@ struct dentry *ext3_get_parent(struct dentry *child)
struct ext3_dir_entry_2 * de;
struct buffer_head *bh;
- bh = ext3_find_entry(child->d_inode, &dotdot, &de);
+ bh = ext3_find_entry(d_inode(child), &dotdot, &de);
if (!bh)
return ERR_PTR(-ENOENT);
ino = le32_to_cpu(de->inode);
brelse(bh);
- if (!ext3_valid_inum(child->d_inode->i_sb, ino)) {
- ext3_error(child->d_inode->i_sb, "ext3_get_parent",
+ if (!ext3_valid_inum(d_inode(child)->i_sb, ino)) {
+ ext3_error(d_inode(child)->i_sb, "ext3_get_parent",
"bad inode number: %lu", ino);
return ERR_PTR(-EIO);
}
- return d_obtain_alias(ext3_iget(child->d_inode->i_sb, ino));
+ return d_obtain_alias(ext3_iget(d_inode(child)->i_sb, ino));
}
#define S_SHIFT 12
@@ -1243,7 +1243,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
struct inode *inode, struct ext3_dir_entry_2 *de,
struct buffer_head * bh)
{
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned long offset = 0;
@@ -1330,7 +1330,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
struct inode *inode, struct buffer_head *bh)
{
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
struct buffer_head *bh2;
@@ -1435,7 +1435,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
static int ext3_add_entry (handle_t *handle, struct dentry *dentry,
struct inode *inode)
{
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
struct buffer_head * bh;
struct ext3_dir_entry_2 *de;
struct super_block * sb;
@@ -1489,7 +1489,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
struct dx_entry *entries, *at;
struct dx_hash_info hinfo;
struct buffer_head * bh;
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
struct super_block * sb = dir->i_sb;
struct ext3_dir_entry_2 *de;
int err;
@@ -2111,7 +2111,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry)
/* Initialize quotas before so that eventual writes go in
* separate transaction */
dquot_initialize(dir);
- dquot_initialize(dentry->d_inode);
+ dquot_initialize(d_inode(dentry));
handle = ext3_journal_start(dir, EXT3_DELETE_TRANS_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
@@ -2125,7 +2125,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry)
if (IS_DIRSYNC(dir))
handle->h_sync = 1;
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
retval = -EIO;
if (le32_to_cpu(de->inode) != inode->i_ino)
@@ -2173,7 +2173,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry)
/* Initialize quotas before so that eventual writes go
* in separate transaction */
dquot_initialize(dir);
- dquot_initialize(dentry->d_inode);
+ dquot_initialize(d_inode(dentry));
handle = ext3_journal_start(dir, EXT3_DELETE_TRANS_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
@@ -2187,7 +2187,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry)
if (!bh)
goto end_unlink;
- inode = dentry->d_inode;
+ inode = d_inode(dentry);
retval = -EIO;
if (le32_to_cpu(de->inode) != inode->i_ino)
@@ -2328,7 +2328,7 @@ static int ext3_link (struct dentry * old_dentry,
struct inode * dir, struct dentry *dentry)
{
handle_t *handle;
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
int err, retries = 0;
if (inode->i_nlink >= EXT3_LINK_MAX)
@@ -2391,8 +2391,8 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
/* Initialize quotas before so that eventual writes go
* in separate transaction */
- if (new_dentry->d_inode)
- dquot_initialize(new_dentry->d_inode);
+ if (d_really_is_positive(new_dentry))
+ dquot_initialize(d_inode(new_dentry));
handle = ext3_journal_start(old_dir, 2 *
EXT3_DATA_TRANS_BLOCKS(old_dir->i_sb) +
EXT3_INDEX_EXTRA_TRANS_BLOCKS + 2);
@@ -2409,12 +2409,12 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
* and merrily kill the link to whatever was created under the
* same name. Goodbye sticky bit ;-<
*/
- old_inode = old_dentry->d_inode;
+ old_inode = d_inode(old_dentry);
retval = -ENOENT;
if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
goto end_rename;
- new_inode = new_dentry->d_inode;
+ new_inode = d_inode(new_dentry);
new_bh = ext3_find_entry(new_dir, &new_dentry->d_name, &new_de);
if (new_bh) {
if (!new_inode) {
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index d4dbf3c259b3..a9312f0a54e5 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -789,7 +789,7 @@ static const struct quotactl_ops ext3_qctl_operations = {
.quota_on = ext3_quota_on,
.quota_off = dquot_quota_off,
.quota_sync = dquot_quota_sync,
- .get_info = dquot_get_dqinfo,
+ .get_state = dquot_get_state,
.set_info = dquot_set_dqinfo,
.get_dqblk = dquot_get_dqblk,
.set_dqblk = dquot_set_dqblk
@@ -1170,7 +1170,7 @@ static int parse_options (char *options, struct super_block *sb,
return 0;
}
- journal_inode = path.dentry->d_inode;
+ journal_inode = d_inode(path.dentry);
if (!S_ISBLK(journal_inode->i_mode)) {
ext3_msg(sb, KERN_ERR, "error: journal path %s "
"is not a block device", journal_path);
@@ -2947,7 +2947,7 @@ static int ext3_write_info(struct super_block *sb, int type)
handle_t *handle;
/* Data block + inode block */
- handle = ext3_journal_start(sb->s_root->d_inode, 2);
+ handle = ext3_journal_start(d_inode(sb->s_root), 2);
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit_info(sb, type);
@@ -2994,7 +2994,7 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
* When we journal data on quota file, we have to flush journal to see
* all updates to the file when we bypass pagecache...
*/
- if (ext3_should_journal_data(path->dentry->d_inode)) {
+ if (ext3_should_journal_data(d_inode(path->dentry))) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
diff --git a/fs/ext3/symlink.c b/fs/ext3/symlink.c
index 6b01c3eab1f3..ea96df3c58db 100644
--- a/fs/ext3/symlink.c
+++ b/fs/ext3/symlink.c
@@ -23,7 +23,7 @@
static void * ext3_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- struct ext3_inode_info *ei = EXT3_I(dentry->d_inode);
+ struct ext3_inode_info *ei = EXT3_I(d_inode(dentry));
nd_set_link(nd, (char*)ei->i_data);
return NULL;
}
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index c6874be6d58b..7cf36501ccf4 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -137,7 +137,7 @@ ext3_xattr_handler(int name_index)
/*
* Inode operation listxattr()
*
- * dentry->d_inode->i_mutex: don't care
+ * d_inode(dentry)->i_mutex: don't care
*/
ssize_t
ext3_listxattr(struct dentry *dentry, char *buffer, size_t size)
@@ -355,7 +355,7 @@ ext3_xattr_list_entries(struct dentry *dentry, struct ext3_xattr_entry *entry,
static int
ext3_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
int error;
@@ -391,7 +391,7 @@ cleanup:
static int
ext3_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct ext3_xattr_ibody_header *header;
struct ext3_inode *raw_inode;
struct ext3_iloc iloc;
@@ -432,7 +432,7 @@ ext3_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int i_error, b_error;
- down_read(&EXT3_I(dentry->d_inode)->xattr_sem);
+ down_read(&EXT3_I(d_inode(dentry))->xattr_sem);
i_error = ext3_xattr_ibody_list(dentry, buffer, buffer_size);
if (i_error < 0) {
b_error = 0;
@@ -445,7 +445,7 @@ ext3_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
if (b_error < 0)
i_error = 0;
}
- up_read(&EXT3_I(dentry->d_inode)->xattr_sem);
+ up_read(&EXT3_I(d_inode(dentry))->xattr_sem);
return i_error + b_error;
}
@@ -546,8 +546,7 @@ ext3_xattr_set_entry(struct ext3_xattr_info *i, struct ext3_xattr_search *s)
free += EXT3_XATTR_LEN(name_len);
}
if (i->value) {
- if (free < EXT3_XATTR_SIZE(i->value_len) ||
- free < EXT3_XATTR_LEN(name_len) +
+ if (free < EXT3_XATTR_LEN(name_len) +
EXT3_XATTR_SIZE(i->value_len))
return -ENOSPC;
}
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 722c2bf9645d..c9506d5e3b13 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -29,7 +29,7 @@ ext3_xattr_security_get(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_get(dentry->d_inode, EXT3_XATTR_INDEX_SECURITY,
+ return ext3_xattr_get(d_inode(dentry), EXT3_XATTR_INDEX_SECURITY,
name, buffer, size);
}
@@ -39,7 +39,7 @@ ext3_xattr_security_set(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_set(dentry->d_inode, EXT3_XATTR_INDEX_SECURITY,
+ return ext3_xattr_set(d_inode(dentry), EXT3_XATTR_INDEX_SECURITY,
name, value, size, flags);
}
diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c
index d75727cc67fa..206cc66dc285 100644
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@@ -32,7 +32,7 @@ ext3_xattr_trusted_get(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_get(dentry->d_inode, EXT3_XATTR_INDEX_TRUSTED,
+ return ext3_xattr_get(d_inode(dentry), EXT3_XATTR_INDEX_TRUSTED,
name, buffer, size);
}
@@ -42,7 +42,7 @@ ext3_xattr_trusted_set(struct dentry *dentry, const char *name,
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_set(dentry->d_inode, EXT3_XATTR_INDEX_TRUSTED, name,
+ return ext3_xattr_set(d_inode(dentry), EXT3_XATTR_INDEX_TRUSTED, name,
value, size, flags);
}
diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c
index 5612af3567e0..021508ad1616 100644
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@@ -34,7 +34,7 @@ ext3_xattr_user_get(struct dentry *dentry, const char *name, void *buffer,
return -EINVAL;
if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext3_xattr_get(dentry->d_inode, EXT3_XATTR_INDEX_USER,
+ return ext3_xattr_get(d_inode(dentry), EXT3_XATTR_INDEX_USER,
name, buffer, size);
}
@@ -46,7 +46,7 @@ ext3_xattr_user_set(struct dentry *dentry, const char *name,
return -EINVAL;
if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext3_xattr_set(dentry->d_inode, EXT3_XATTR_INDEX_USER,
+ return ext3_xattr_set(d_inode(dentry), EXT3_XATTR_INDEX_USER,
name, value, size, flags);
}
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index efea5d5c44ce..024f2284d3f6 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -64,6 +64,28 @@ config EXT4_FS_SECURITY
If you are not using a security module that requires using
extended attributes for file security labels, say N.
+config EXT4_ENCRYPTION
+ tristate "Ext4 Encryption"
+ depends on EXT4_FS
+ select CRYPTO_AES
+ select CRYPTO_CBC
+ select CRYPTO_ECB
+ select CRYPTO_XTS
+ select CRYPTO_CTS
+ select CRYPTO_SHA256
+ select KEYS
+ select ENCRYPTED_KEYS
+ help
+ Enable encryption of ext4 files and directories. This
+ feature is similar to ecryptfs, but it is more memory
+ efficient since it avoids caching the encrypted and
+ decrypted pages in the page cache.
+
+config EXT4_FS_ENCRYPTION
+ bool
+ default y
+ depends on EXT4_ENCRYPTION
+
config EXT4_DEBUG
bool "EXT4 debugging support"
depends on EXT4_FS
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 0310fec2ee3d..75285ea9aa05 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -8,7 +8,9 @@ ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
mmp.o indirect.o extents_status.o xattr.o xattr_user.o \
- xattr_trusted.o inline.o
+ xattr_trusted.o inline.o readpage.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o
+ext4-$(CONFIG_EXT4_FS_ENCRYPTION) += crypto_policy.o crypto.o \
+ crypto_key.o crypto_fname.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index d40c8dbbb0d6..69b1e73026a5 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -4,11 +4,6 @@
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
*/
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 83a6f497c4e0..955bf49a7945 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -14,7 +14,6 @@
#include <linux/time.h>
#include <linux/capability.h>
#include <linux/fs.h>
-#include <linux/jbd2.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include "ext4.h"
@@ -641,8 +640,6 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
* fail EDQUOT for metdata, but we do account for it.
*/
if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) {
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_alloc_block_nofail(inode,
EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
}
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index b610779a958c..4a606afb171f 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -8,7 +8,6 @@
*/
#include <linux/buffer_head.h>
-#include <linux/jbd2.h>
#include "ext4.h"
unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 41eb9dcfac7e..3522340c7a99 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -16,7 +16,6 @@
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/blkdev.h>
-#include <linux/mutex.h>
#include <linux/slab.h>
#include "ext4.h"
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
new file mode 100644
index 000000000000..8ff15273ab0c
--- /dev/null
+++ b/fs/ext4/crypto.c
@@ -0,0 +1,558 @@
+/*
+ * linux/fs/ext4/crypto.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption functions for ext4
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ * Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ * Ildar Muslukhov, 2014
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/user-type.h>
+#include <keys/encrypted-type.h>
+#include <linux/crypto.h>
+#include <linux/ecryptfs.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/list.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock_types.h>
+
+#include "ext4_extents.h"
+#include "xattr.h"
+
+/* Encryption added and removed here! (L: */
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+ "Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+ "Number of crypto contexts to preallocate");
+
+static mempool_t *ext4_bounce_page_pool;
+
+static LIST_HEAD(ext4_free_crypto_ctxs);
+static DEFINE_SPINLOCK(ext4_crypto_ctx_lock);
+
+/**
+ * ext4_release_crypto_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx)
+{
+ unsigned long flags;
+
+ if (ctx->bounce_page) {
+ if (ctx->flags & EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL)
+ __free_page(ctx->bounce_page);
+ else
+ mempool_free(ctx->bounce_page, ext4_bounce_page_pool);
+ ctx->bounce_page = NULL;
+ }
+ ctx->control_page = NULL;
+ if (ctx->flags & EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+ if (ctx->tfm)
+ crypto_free_tfm(ctx->tfm);
+ kfree(ctx);
+ } else {
+ spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
+ list_add(&ctx->free_list, &ext4_free_crypto_ctxs);
+ spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
+ }
+}
+
+/**
+ * ext4_alloc_and_init_crypto_ctx() - Allocates and inits an encryption context
+ * @mask: The allocation mask.
+ *
+ * Return: An allocated and initialized encryption context on success. An error
+ * value or NULL otherwise.
+ */
+static struct ext4_crypto_ctx *ext4_alloc_and_init_crypto_ctx(gfp_t mask)
+{
+ struct ext4_crypto_ctx *ctx = kzalloc(sizeof(struct ext4_crypto_ctx),
+ mask);
+
+ if (!ctx)
+ return ERR_PTR(-ENOMEM);
+ return ctx;
+}
+
+/**
+ * ext4_get_crypto_ctx() - Gets an encryption context
+ * @inode: The inode for which we are doing the crypto
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
+{
+ struct ext4_crypto_ctx *ctx = NULL;
+ int res = 0;
+ unsigned long flags;
+ struct ext4_encryption_key *key = &EXT4_I(inode)->i_encryption_key;
+
+ if (!ext4_read_workqueue)
+ ext4_init_crypto();
+
+ /*
+ * We first try getting the ctx from a free list because in
+ * the common case the ctx will have an allocated and
+ * initialized crypto tfm, so it's probably a worthwhile
+ * optimization. For the bounce page, we first try getting it
+ * from the kernel allocator because that's just about as fast
+ * as getting it from a list and because a cache of free pages
+ * should generally be a "last resort" option for a filesystem
+ * to be able to do its job.
+ */
+ spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
+ ctx = list_first_entry_or_null(&ext4_free_crypto_ctxs,
+ struct ext4_crypto_ctx, free_list);
+ if (ctx)
+ list_del(&ctx->free_list);
+ spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
+ if (!ctx) {
+ ctx = ext4_alloc_and_init_crypto_ctx(GFP_NOFS);
+ if (IS_ERR(ctx)) {
+ res = PTR_ERR(ctx);
+ goto out;
+ }
+ ctx->flags |= EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ } else {
+ ctx->flags &= ~EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ }
+
+ /* Allocate a new Crypto API context if we don't already have
+ * one or if it isn't the right mode. */
+ BUG_ON(key->mode == EXT4_ENCRYPTION_MODE_INVALID);
+ if (ctx->tfm && (ctx->mode != key->mode)) {
+ crypto_free_tfm(ctx->tfm);
+ ctx->tfm = NULL;
+ ctx->mode = EXT4_ENCRYPTION_MODE_INVALID;
+ }
+ if (!ctx->tfm) {
+ switch (key->mode) {
+ case EXT4_ENCRYPTION_MODE_AES_256_XTS:
+ ctx->tfm = crypto_ablkcipher_tfm(
+ crypto_alloc_ablkcipher("xts(aes)", 0, 0));
+ break;
+ case EXT4_ENCRYPTION_MODE_AES_256_GCM:
+ /* TODO(mhalcrow): AEAD w/ gcm(aes);
+ * crypto_aead_setauthsize() */
+ ctx->tfm = ERR_PTR(-ENOTSUPP);
+ break;
+ default:
+ BUG();
+ }
+ if (IS_ERR_OR_NULL(ctx->tfm)) {
+ res = PTR_ERR(ctx->tfm);
+ ctx->tfm = NULL;
+ goto out;
+ }
+ ctx->mode = key->mode;
+ }
+ BUG_ON(key->size != ext4_encryption_key_size(key->mode));
+
+ /* There shouldn't be a bounce page attached to the crypto
+ * context at this point. */
+ BUG_ON(ctx->bounce_page);
+
+out:
+ if (res) {
+ if (!IS_ERR_OR_NULL(ctx))
+ ext4_release_crypto_ctx(ctx);
+ ctx = ERR_PTR(res);
+ }
+ return ctx;
+}
+
+struct workqueue_struct *ext4_read_workqueue;
+static DEFINE_MUTEX(crypto_init);
+
+/**
+ * ext4_exit_crypto() - Shutdown the ext4 encryption system
+ */
+void ext4_exit_crypto(void)
+{
+ struct ext4_crypto_ctx *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &ext4_free_crypto_ctxs, free_list) {
+ if (pos->bounce_page) {
+ if (pos->flags &
+ EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL) {
+ __free_page(pos->bounce_page);
+ } else {
+ mempool_free(pos->bounce_page,
+ ext4_bounce_page_pool);
+ }
+ }
+ if (pos->tfm)
+ crypto_free_tfm(pos->tfm);
+ kfree(pos);
+ }
+ INIT_LIST_HEAD(&ext4_free_crypto_ctxs);
+ if (ext4_bounce_page_pool)
+ mempool_destroy(ext4_bounce_page_pool);
+ ext4_bounce_page_pool = NULL;
+ if (ext4_read_workqueue)
+ destroy_workqueue(ext4_read_workqueue);
+ ext4_read_workqueue = NULL;
+}
+
+/**
+ * ext4_init_crypto() - Set up for ext4 encryption.
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int ext4_init_crypto(void)
+{
+ int i, res;
+
+ mutex_lock(&crypto_init);
+ if (ext4_read_workqueue)
+ goto already_initialized;
+ ext4_read_workqueue = alloc_workqueue("ext4_crypto", WQ_HIGHPRI, 0);
+ if (!ext4_read_workqueue) {
+ res = -ENOMEM;
+ goto fail;
+ }
+
+ for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+ struct ext4_crypto_ctx *ctx;
+
+ ctx = ext4_alloc_and_init_crypto_ctx(GFP_KERNEL);
+ if (IS_ERR(ctx)) {
+ res = PTR_ERR(ctx);
+ goto fail;
+ }
+ list_add(&ctx->free_list, &ext4_free_crypto_ctxs);
+ }
+
+ ext4_bounce_page_pool =
+ mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+ if (!ext4_bounce_page_pool) {
+ res = -ENOMEM;
+ goto fail;
+ }
+already_initialized:
+ mutex_unlock(&crypto_init);
+ return 0;
+fail:
+ ext4_exit_crypto();
+ mutex_unlock(&crypto_init);
+ return res;
+}
+
+void ext4_restore_control_page(struct page *data_page)
+{
+ struct ext4_crypto_ctx *ctx =
+ (struct ext4_crypto_ctx *)page_private(data_page);
+
+ set_page_private(data_page, (unsigned long)NULL);
+ ClearPagePrivate(data_page);
+ unlock_page(data_page);
+ ext4_release_crypto_ctx(ctx);
+}
+
+/**
+ * ext4_crypt_complete() - The completion callback for page encryption
+ * @req: The asynchronous encryption request context
+ * @res: The result of the encryption operation
+ */
+static void ext4_crypt_complete(struct crypto_async_request *req, int res)
+{
+ struct ext4_completion_result *ecr = req->data;
+
+ if (res == -EINPROGRESS)
+ return;
+ ecr->res = res;
+ complete(&ecr->completion);
+}
+
+typedef enum {
+ EXT4_DECRYPT = 0,
+ EXT4_ENCRYPT,
+} ext4_direction_t;
+
+static int ext4_page_crypto(struct ext4_crypto_ctx *ctx,
+ struct inode *inode,
+ ext4_direction_t rw,
+ pgoff_t index,
+ struct page *src_page,
+ struct page *dest_page)
+
+{
+ u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct scatterlist dst, src;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct crypto_ablkcipher *atfm = __crypto_ablkcipher_cast(ctx->tfm);
+ int res = 0;
+
+ BUG_ON(!ctx->tfm);
+ BUG_ON(ctx->mode != ei->i_encryption_key.mode);
+
+ if (ctx->mode != EXT4_ENCRYPTION_MODE_AES_256_XTS) {
+ printk_ratelimited(KERN_ERR
+ "%s: unsupported crypto algorithm: %d\n",
+ __func__, ctx->mode);
+ return -ENOTSUPP;
+ }
+
+ crypto_ablkcipher_clear_flags(atfm, ~0);
+ crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+
+ res = crypto_ablkcipher_setkey(atfm, ei->i_encryption_key.raw,
+ ei->i_encryption_key.size);
+ if (res) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_ablkcipher_setkey() failed\n",
+ __func__);
+ return res;
+ }
+ req = ablkcipher_request_alloc(atfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_request_alloc() failed\n",
+ __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(
+ req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ ext4_crypt_complete, &ecr);
+
+ BUILD_BUG_ON(EXT4_XTS_TWEAK_SIZE < sizeof(index));
+ memcpy(xts_tweak, &index, sizeof(index));
+ memset(&xts_tweak[sizeof(index)], 0,
+ EXT4_XTS_TWEAK_SIZE - sizeof(index));
+
+ sg_init_table(&dst, 1);
+ sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
+ sg_init_table(&src, 1);
+ sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
+ ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+ xts_tweak);
+ if (rw == EXT4_DECRYPT)
+ res = crypto_ablkcipher_decrypt(req);
+ else
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ ablkcipher_request_free(req);
+ if (res) {
+ printk_ratelimited(
+ KERN_ERR
+ "%s: crypto_ablkcipher_encrypt() returned %d\n",
+ __func__, res);
+ return res;
+ }
+ return 0;
+}
+
+/**
+ * ext4_encrypt() - Encrypts a page
+ * @inode: The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path. The caller must call
+ * ext4_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * Return: An allocated page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *ext4_encrypt(struct inode *inode,
+ struct page *plaintext_page)
+{
+ struct ext4_crypto_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ int err;
+
+ BUG_ON(!PageLocked(plaintext_page));
+
+ ctx = ext4_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return (struct page *) ctx;
+
+ /* The encryption operation will require a bounce page. */
+ ciphertext_page = alloc_page(GFP_NOFS);
+ if (!ciphertext_page) {
+ /* This is a potential bottleneck, but at least we'll have
+ * forward progress. */
+ ciphertext_page = mempool_alloc(ext4_bounce_page_pool,
+ GFP_NOFS);
+ if (WARN_ON_ONCE(!ciphertext_page)) {
+ ciphertext_page = mempool_alloc(ext4_bounce_page_pool,
+ GFP_NOFS | __GFP_WAIT);
+ }
+ ctx->flags &= ~EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
+ } else {
+ ctx->flags |= EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
+ }
+ ctx->bounce_page = ciphertext_page;
+ ctx->control_page = plaintext_page;
+ err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, plaintext_page->index,
+ plaintext_page, ciphertext_page);
+ if (err) {
+ ext4_release_crypto_ctx(ctx);
+ return ERR_PTR(err);
+ }
+ SetPagePrivate(ciphertext_page);
+ set_page_private(ciphertext_page, (unsigned long)ctx);
+ lock_page(ciphertext_page);
+ return ciphertext_page;
+}
+
+/**
+ * ext4_decrypt() - Decrypts a page in-place
+ * @ctx: The encryption context.
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+
+ return ext4_page_crypto(ctx, page->mapping->host,
+ EXT4_DECRYPT, page->index, page, page);
+}
+
+/*
+ * Convenience function which takes care of allocating and
+ * deallocating the encryption context
+ */
+int ext4_decrypt_one(struct inode *inode, struct page *page)
+{
+ int ret;
+
+ struct ext4_crypto_ctx *ctx = ext4_get_crypto_ctx(inode);
+
+ if (!ctx)
+ return -ENOMEM;
+ ret = ext4_decrypt(ctx, page);
+ ext4_release_crypto_ctx(ctx);
+ return ret;
+}
+
+int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+ struct ext4_crypto_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ struct bio *bio;
+ ext4_lblk_t lblk = ex->ee_block;
+ ext4_fsblk_t pblk = ext4_ext_pblock(ex);
+ unsigned int len = ext4_ext_get_actual_len(ex);
+ int err = 0;
+
+ BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
+
+ ctx = ext4_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ ciphertext_page = alloc_page(GFP_NOFS);
+ if (!ciphertext_page) {
+ /* This is a potential bottleneck, but at least we'll have
+ * forward progress. */
+ ciphertext_page = mempool_alloc(ext4_bounce_page_pool,
+ GFP_NOFS);
+ if (WARN_ON_ONCE(!ciphertext_page)) {
+ ciphertext_page = mempool_alloc(ext4_bounce_page_pool,
+ GFP_NOFS | __GFP_WAIT);
+ }
+ ctx->flags &= ~EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
+ } else {
+ ctx->flags |= EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL;
+ }
+ ctx->bounce_page = ciphertext_page;
+
+ while (len--) {
+ err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, lblk,
+ ZERO_PAGE(0), ciphertext_page);
+ if (err)
+ goto errout;
+
+ bio = bio_alloc(GFP_KERNEL, 1);
+ if (!bio) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ bio->bi_bdev = inode->i_sb->s_bdev;
+ bio->bi_iter.bi_sector = pblk;
+ err = bio_add_page(bio, ciphertext_page,
+ inode->i_sb->s_blocksize, 0);
+ if (err) {
+ bio_put(bio);
+ goto errout;
+ }
+ err = submit_bio_wait(WRITE, bio);
+ if (err)
+ goto errout;
+ }
+ err = 0;
+errout:
+ ext4_release_crypto_ctx(ctx);
+ return err;
+}
+
+bool ext4_valid_contents_enc_mode(uint32_t mode)
+{
+ return (mode == EXT4_ENCRYPTION_MODE_AES_256_XTS);
+}
+
+/**
+ * ext4_validate_encryption_key_size() - Validate the encryption key size
+ * @mode: The key mode.
+ * @size: The key size to validate.
+ *
+ * Return: The validated key size for @mode. Zero if invalid.
+ */
+uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
+{
+ if (size == ext4_encryption_key_size(mode))
+ return size;
+ return 0;
+}
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
new file mode 100644
index 000000000000..fded02f72299
--- /dev/null
+++ b/fs/ext4/crypto_fname.c
@@ -0,0 +1,719 @@
+/*
+ * linux/fs/ext4/crypto_fname.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains functions for filename crypto management in ext4
+ *
+ * Written by Uday Savagaonkar, 2014.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ */
+
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/crypto.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/key.h>
+#include <linux/list.h>
+#include <linux/mempool.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock_types.h>
+
+#include "ext4.h"
+#include "ext4_crypto.h"
+#include "xattr.h"
+
+/**
+ * ext4_dir_crypt_complete() -
+ */
+static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res)
+{
+ struct ext4_completion_result *ecr = req->data;
+
+ if (res == -EINPROGRESS)
+ return;
+ ecr->res = res;
+ complete(&ecr->completion);
+}
+
+bool ext4_valid_filenames_enc_mode(uint32_t mode)
+{
+ return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS);
+}
+
+/**
+ * ext4_fname_encrypt() -
+ *
+ * This function encrypts the input filename, and returns the length of the
+ * ciphertext. Errors are returned as negative numbers. We trust the caller to
+ * allocate sufficient memory to oname string.
+ */
+static int ext4_fname_encrypt(struct ext4_fname_crypto_ctx *ctx,
+ const struct qstr *iname,
+ struct ext4_str *oname)
+{
+ u32 ciphertext_len;
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct crypto_ablkcipher *tfm = ctx->ctfm;
+ int res = 0;
+ char iv[EXT4_CRYPTO_BLOCK_SIZE];
+ struct scatterlist sg[1];
+ int padding = 4 << (ctx->flags & EXT4_POLICY_FLAGS_PAD_MASK);
+ char *workbuf;
+
+ if (iname->len <= 0 || iname->len > ctx->lim)
+ return -EIO;
+
+ ciphertext_len = (iname->len < EXT4_CRYPTO_BLOCK_SIZE) ?
+ EXT4_CRYPTO_BLOCK_SIZE : iname->len;
+ ciphertext_len = ext4_fname_crypto_round_up(ciphertext_len, padding);
+ ciphertext_len = (ciphertext_len > ctx->lim)
+ ? ctx->lim : ciphertext_len;
+
+ /* Allocate request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(
+ KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ ext4_dir_crypt_complete, &ecr);
+
+ /* Map the workpage */
+ workbuf = kmap(ctx->workpage);
+
+ /* Copy the input */
+ memcpy(workbuf, iname->name, iname->len);
+ if (iname->len < ciphertext_len)
+ memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
+
+ /* Initialize IV */
+ memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
+
+ /* Create encryption request */
+ sg_init_table(sg, 1);
+ sg_set_page(sg, ctx->workpage, PAGE_SIZE, 0);
+ ablkcipher_request_set_crypt(req, sg, sg, ciphertext_len, iv);
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ if (res >= 0) {
+ /* Copy the result to output */
+ memcpy(oname->name, workbuf, ciphertext_len);
+ res = ciphertext_len;
+ }
+ kunmap(ctx->workpage);
+ ablkcipher_request_free(req);
+ if (res < 0) {
+ printk_ratelimited(
+ KERN_ERR "%s: Error (error code %d)\n", __func__, res);
+ }
+ oname->len = ciphertext_len;
+ return res;
+}
+
+/*
+ * ext4_fname_decrypt()
+ * This function decrypts the input filename, and returns
+ * the length of the plaintext.
+ * Errors are returned as negative numbers.
+ * We trust the caller to allocate sufficient memory to oname string.
+ */
+static int ext4_fname_decrypt(struct ext4_fname_crypto_ctx *ctx,
+ const struct ext4_str *iname,
+ struct ext4_str *oname)
+{
+ struct ext4_str tmp_in[2], tmp_out[1];
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct scatterlist sg[1];
+ struct crypto_ablkcipher *tfm = ctx->ctfm;
+ int res = 0;
+ char iv[EXT4_CRYPTO_BLOCK_SIZE];
+ char *workbuf;
+
+ if (iname->len <= 0 || iname->len > ctx->lim)
+ return -EIO;
+
+ tmp_in[0].name = iname->name;
+ tmp_in[0].len = iname->len;
+ tmp_out[0].name = oname->name;
+
+ /* Allocate request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(
+ KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ ext4_dir_crypt_complete, &ecr);
+
+ /* Map the workpage */
+ workbuf = kmap(ctx->workpage);
+
+ /* Copy the input */
+ memcpy(workbuf, iname->name, iname->len);
+
+ /* Initialize IV */
+ memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
+
+ /* Create encryption request */
+ sg_init_table(sg, 1);
+ sg_set_page(sg, ctx->workpage, PAGE_SIZE, 0);
+ ablkcipher_request_set_crypt(req, sg, sg, iname->len, iv);
+ res = crypto_ablkcipher_decrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ if (res >= 0) {
+ /* Copy the result to output */
+ memcpy(oname->name, workbuf, iname->len);
+ res = iname->len;
+ }
+ kunmap(ctx->workpage);
+ ablkcipher_request_free(req);
+ if (res < 0) {
+ printk_ratelimited(
+ KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n",
+ __func__, res);
+ return res;
+ }
+
+ oname->len = strnlen(oname->name, iname->len);
+ return oname->len;
+}
+
+static const char *lookup_table =
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+/**
+ * ext4_fname_encode_digest() -
+ *
+ * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
+ * The encoded string is roughly 4/3 times the size of the input string.
+ */
+static int digest_encode(const char *src, int len, char *dst)
+{
+ int i = 0, bits = 0, ac = 0;
+ char *cp = dst;
+
+ while (i < len) {
+ ac += (((unsigned char) src[i]) << bits);
+ bits += 8;
+ do {
+ *cp++ = lookup_table[ac & 0x3f];
+ ac >>= 6;
+ bits -= 6;
+ } while (bits >= 6);
+ i++;
+ }
+ if (bits)
+ *cp++ = lookup_table[ac & 0x3f];
+ return cp - dst;
+}
+
+static int digest_decode(const char *src, int len, char *dst)
+{
+ int i = 0, bits = 0, ac = 0;
+ const char *p;
+ char *cp = dst;
+
+ while (i < len) {
+ p = strchr(lookup_table, src[i]);
+ if (p == NULL || src[i] == 0)
+ return -2;
+ ac += (p - lookup_table) << bits;
+ bits += 6;
+ if (bits >= 8) {
+ *cp++ = ac & 0xff;
+ ac >>= 8;
+ bits -= 8;
+ }
+ i++;
+ }
+ if (ac)
+ return -1;
+ return cp - dst;
+}
+
+/**
+ * ext4_free_fname_crypto_ctx() -
+ *
+ * Frees up a crypto context.
+ */
+void ext4_free_fname_crypto_ctx(struct ext4_fname_crypto_ctx *ctx)
+{
+ if (ctx == NULL || IS_ERR(ctx))
+ return;
+
+ if (ctx->ctfm && !IS_ERR(ctx->ctfm))
+ crypto_free_ablkcipher(ctx->ctfm);
+ if (ctx->htfm && !IS_ERR(ctx->htfm))
+ crypto_free_hash(ctx->htfm);
+ if (ctx->workpage && !IS_ERR(ctx->workpage))
+ __free_page(ctx->workpage);
+ kfree(ctx);
+}
+
+/**
+ * ext4_put_fname_crypto_ctx() -
+ *
+ * Return: The crypto context onto free list. If the free list is above a
+ * threshold, completely frees up the context, and returns the memory.
+ *
+ * TODO: Currently we directly free the crypto context. Eventually we should
+ * add code it to return to free list. Such an approach will increase
+ * efficiency of directory lookup.
+ */
+void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx)
+{
+ if (*ctx == NULL || IS_ERR(*ctx))
+ return;
+ ext4_free_fname_crypto_ctx(*ctx);
+ *ctx = NULL;
+}
+
+/**
+ * ext4_search_fname_crypto_ctx() -
+ */
+static struct ext4_fname_crypto_ctx *ext4_search_fname_crypto_ctx(
+ const struct ext4_encryption_key *key)
+{
+ return NULL;
+}
+
+/**
+ * ext4_alloc_fname_crypto_ctx() -
+ */
+struct ext4_fname_crypto_ctx *ext4_alloc_fname_crypto_ctx(
+ const struct ext4_encryption_key *key)
+{
+ struct ext4_fname_crypto_ctx *ctx;
+
+ ctx = kmalloc(sizeof(struct ext4_fname_crypto_ctx), GFP_NOFS);
+ if (ctx == NULL)
+ return ERR_PTR(-ENOMEM);
+ if (key->mode == EXT4_ENCRYPTION_MODE_INVALID) {
+ /* This will automatically set key mode to invalid
+ * As enum for ENCRYPTION_MODE_INVALID is zero */
+ memset(&ctx->key, 0, sizeof(ctx->key));
+ } else {
+ memcpy(&ctx->key, key, sizeof(struct ext4_encryption_key));
+ }
+ ctx->has_valid_key = (EXT4_ENCRYPTION_MODE_INVALID == key->mode)
+ ? 0 : 1;
+ ctx->ctfm_key_is_ready = 0;
+ ctx->ctfm = NULL;
+ ctx->htfm = NULL;
+ ctx->workpage = NULL;
+ return ctx;
+}
+
+/**
+ * ext4_get_fname_crypto_ctx() -
+ *
+ * Allocates a free crypto context and initializes it to hold
+ * the crypto material for the inode.
+ *
+ * Return: NULL if not encrypted. Error value on error. Valid pointer otherwise.
+ */
+struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(
+ struct inode *inode, u32 max_ciphertext_len)
+{
+ struct ext4_fname_crypto_ctx *ctx;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int res;
+
+ /* Check if the crypto policy is set on the inode */
+ res = ext4_encrypted_inode(inode);
+ if (res == 0)
+ return NULL;
+
+ if (!ext4_has_encryption_key(inode))
+ ext4_generate_encryption_key(inode);
+
+ /* Get a crypto context based on the key.
+ * A new context is allocated if no context matches the requested key.
+ */
+ ctx = ext4_search_fname_crypto_ctx(&(ei->i_encryption_key));
+ if (ctx == NULL)
+ ctx = ext4_alloc_fname_crypto_ctx(&(ei->i_encryption_key));
+ if (IS_ERR(ctx))
+ return ctx;
+
+ ctx->flags = ei->i_crypt_policy_flags;
+ if (ctx->has_valid_key) {
+ if (ctx->key.mode != EXT4_ENCRYPTION_MODE_AES_256_CTS) {
+ printk_once(KERN_WARNING
+ "ext4: unsupported key mode %d\n",
+ ctx->key.mode);
+ return ERR_PTR(-ENOKEY);
+ }
+
+ /* As a first cut, we will allocate new tfm in every call.
+ * later, we will keep the tfm around, in case the key gets
+ * re-used */
+ if (ctx->ctfm == NULL) {
+ ctx->ctfm = crypto_alloc_ablkcipher("cts(cbc(aes))",
+ 0, 0);
+ }
+ if (IS_ERR(ctx->ctfm)) {
+ res = PTR_ERR(ctx->ctfm);
+ printk(
+ KERN_DEBUG "%s: error (%d) allocating crypto tfm\n",
+ __func__, res);
+ ctx->ctfm = NULL;
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(res);
+ }
+ if (ctx->ctfm == NULL) {
+ printk(
+ KERN_DEBUG "%s: could not allocate crypto tfm\n",
+ __func__);
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ if (ctx->workpage == NULL)
+ ctx->workpage = alloc_page(GFP_NOFS);
+ if (IS_ERR(ctx->workpage)) {
+ res = PTR_ERR(ctx->workpage);
+ printk(
+ KERN_DEBUG "%s: error (%d) allocating work page\n",
+ __func__, res);
+ ctx->workpage = NULL;
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(res);
+ }
+ if (ctx->workpage == NULL) {
+ printk(
+ KERN_DEBUG "%s: could not allocate work page\n",
+ __func__);
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ ctx->lim = max_ciphertext_len;
+ crypto_ablkcipher_clear_flags(ctx->ctfm, ~0);
+ crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctx->ctfm),
+ CRYPTO_TFM_REQ_WEAK_KEY);
+
+ /* If we are lucky, we will get a context that is already
+ * set up with the right key. Else, we will have to
+ * set the key */
+ if (!ctx->ctfm_key_is_ready) {
+ /* Since our crypto objectives for filename encryption
+ * are pretty weak,
+ * we directly use the inode master key */
+ res = crypto_ablkcipher_setkey(ctx->ctfm,
+ ctx->key.raw, ctx->key.size);
+ if (res) {
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(-EIO);
+ }
+ ctx->ctfm_key_is_ready = 1;
+ } else {
+ /* In the current implementation, key should never be
+ * marked "ready" for a context that has just been
+ * allocated. So we should never reach here */
+ BUG();
+ }
+ }
+ if (ctx->htfm == NULL)
+ ctx->htfm = crypto_alloc_hash("sha256", 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(ctx->htfm)) {
+ res = PTR_ERR(ctx->htfm);
+ printk(KERN_DEBUG "%s: error (%d) allocating hash tfm\n",
+ __func__, res);
+ ctx->htfm = NULL;
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(res);
+ }
+ if (ctx->htfm == NULL) {
+ printk(KERN_DEBUG "%s: could not allocate hash tfm\n",
+ __func__);
+ ext4_put_fname_crypto_ctx(&ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return ctx;
+}
+
+/**
+ * ext4_fname_crypto_round_up() -
+ *
+ * Return: The next multiple of block size
+ */
+u32 ext4_fname_crypto_round_up(u32 size, u32 blksize)
+{
+ return ((size+blksize-1)/blksize)*blksize;
+}
+
+/**
+ * ext4_fname_crypto_namelen_on_disk() -
+ */
+int ext4_fname_crypto_namelen_on_disk(struct ext4_fname_crypto_ctx *ctx,
+ u32 namelen)
+{
+ u32 ciphertext_len;
+ int padding = 4 << (ctx->flags & EXT4_POLICY_FLAGS_PAD_MASK);
+
+ if (ctx == NULL)
+ return -EIO;
+ if (!(ctx->has_valid_key))
+ return -EACCES;
+ ciphertext_len = (namelen < EXT4_CRYPTO_BLOCK_SIZE) ?
+ EXT4_CRYPTO_BLOCK_SIZE : namelen;
+ ciphertext_len = ext4_fname_crypto_round_up(ciphertext_len, padding);
+ ciphertext_len = (ciphertext_len > ctx->lim)
+ ? ctx->lim : ciphertext_len;
+ return (int) ciphertext_len;
+}
+
+/**
+ * ext4_fname_crypto_alloc_obuff() -
+ *
+ * Allocates an output buffer that is sufficient for the crypto operation
+ * specified by the context and the direction.
+ */
+int ext4_fname_crypto_alloc_buffer(struct ext4_fname_crypto_ctx *ctx,
+ u32 ilen, struct ext4_str *crypto_str)
+{
+ unsigned int olen;
+ int padding = 4 << (ctx->flags & EXT4_POLICY_FLAGS_PAD_MASK);
+
+ if (!ctx)
+ return -EIO;
+ if (padding < EXT4_CRYPTO_BLOCK_SIZE)
+ padding = EXT4_CRYPTO_BLOCK_SIZE;
+ olen = ext4_fname_crypto_round_up(ilen, padding);
+ crypto_str->len = olen;
+ if (olen < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2)
+ olen = EXT4_FNAME_CRYPTO_DIGEST_SIZE*2;
+ /* Allocated buffer can hold one more character to null-terminate the
+ * string */
+ crypto_str->name = kmalloc(olen+1, GFP_NOFS);
+ if (!(crypto_str->name))
+ return -ENOMEM;
+ return 0;
+}
+
+/**
+ * ext4_fname_crypto_free_buffer() -
+ *
+ * Frees the buffer allocated for crypto operation.
+ */
+void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str)
+{
+ if (!crypto_str)
+ return;
+ kfree(crypto_str->name);
+ crypto_str->name = NULL;
+}
+
+/**
+ * ext4_fname_disk_to_usr() - converts a filename from disk space to user space
+ */
+int _ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx,
+ struct dx_hash_info *hinfo,
+ const struct ext4_str *iname,
+ struct ext4_str *oname)
+{
+ char buf[24];
+ int ret;
+
+ if (ctx == NULL)
+ return -EIO;
+ if (iname->len < 3) {
+ /*Check for . and .. */
+ if (iname->name[0] == '.' && iname->name[iname->len-1] == '.') {
+ oname->name[0] = '.';
+ oname->name[iname->len-1] = '.';
+ oname->len = iname->len;
+ return oname->len;
+ }
+ }
+ if (ctx->has_valid_key)
+ return ext4_fname_decrypt(ctx, iname, oname);
+
+ if (iname->len <= EXT4_FNAME_CRYPTO_DIGEST_SIZE) {
+ ret = digest_encode(iname->name, iname->len, oname->name);
+ oname->len = ret;
+ return ret;
+ }
+ if (hinfo) {
+ memcpy(buf, &hinfo->hash, 4);
+ memcpy(buf+4, &hinfo->minor_hash, 4);
+ } else
+ memset(buf, 0, 8);
+ memcpy(buf + 8, iname->name + iname->len - 16, 16);
+ oname->name[0] = '_';
+ ret = digest_encode(buf, 24, oname->name+1);
+ oname->len = ret + 1;
+ return ret + 1;
+}
+
+int ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx,
+ struct dx_hash_info *hinfo,
+ const struct ext4_dir_entry_2 *de,
+ struct ext4_str *oname)
+{
+ struct ext4_str iname = {.name = (unsigned char *) de->name,
+ .len = de->name_len };
+
+ return _ext4_fname_disk_to_usr(ctx, hinfo, &iname, oname);
+}
+
+
+/**
+ * ext4_fname_usr_to_disk() - converts a filename from user space to disk space
+ */
+int ext4_fname_usr_to_disk(struct ext4_fname_crypto_ctx *ctx,
+ const struct qstr *iname,
+ struct ext4_str *oname)
+{
+ int res;
+
+ if (ctx == NULL)
+ return -EIO;
+ if (iname->len < 3) {
+ /*Check for . and .. */
+ if (iname->name[0] == '.' &&
+ iname->name[iname->len-1] == '.') {
+ oname->name[0] = '.';
+ oname->name[iname->len-1] = '.';
+ oname->len = iname->len;
+ return oname->len;
+ }
+ }
+ if (ctx->has_valid_key) {
+ res = ext4_fname_encrypt(ctx, iname, oname);
+ return res;
+ }
+ /* Without a proper key, a user is not allowed to modify the filenames
+ * in a directory. Consequently, a user space name cannot be mapped to
+ * a disk-space name */
+ return -EACCES;
+}
+
+/*
+ * Calculate the htree hash from a filename from user space
+ */
+int ext4_fname_usr_to_hash(struct ext4_fname_crypto_ctx *ctx,
+ const struct qstr *iname,
+ struct dx_hash_info *hinfo)
+{
+ struct ext4_str tmp;
+ int ret = 0;
+ char buf[EXT4_FNAME_CRYPTO_DIGEST_SIZE+1];
+
+ if (!ctx ||
+ ((iname->name[0] == '.') &&
+ ((iname->len == 1) ||
+ ((iname->name[1] == '.') && (iname->len == 2))))) {
+ ext4fs_dirhash(iname->name, iname->len, hinfo);
+ return 0;
+ }
+
+ if (!ctx->has_valid_key && iname->name[0] == '_') {
+ if (iname->len != 33)
+ return -ENOENT;
+ ret = digest_decode(iname->name+1, iname->len, buf);
+ if (ret != 24)
+ return -ENOENT;
+ memcpy(&hinfo->hash, buf, 4);
+ memcpy(&hinfo->minor_hash, buf + 4, 4);
+ return 0;
+ }
+
+ if (!ctx->has_valid_key && iname->name[0] != '_') {
+ if (iname->len > 43)
+ return -ENOENT;
+ ret = digest_decode(iname->name, iname->len, buf);
+ ext4fs_dirhash(buf, ret, hinfo);
+ return 0;
+ }
+
+ /* First encrypt the plaintext name */
+ ret = ext4_fname_crypto_alloc_buffer(ctx, iname->len, &tmp);
+ if (ret < 0)
+ return ret;
+
+ ret = ext4_fname_encrypt(ctx, iname, &tmp);
+ if (ret >= 0) {
+ ext4fs_dirhash(tmp.name, tmp.len, hinfo);
+ ret = 0;
+ }
+
+ ext4_fname_crypto_free_buffer(&tmp);
+ return ret;
+}
+
+int ext4_fname_match(struct ext4_fname_crypto_ctx *ctx, struct ext4_str *cstr,
+ int len, const char * const name,
+ struct ext4_dir_entry_2 *de)
+{
+ int ret = -ENOENT;
+ int bigname = (*name == '_');
+
+ if (ctx->has_valid_key) {
+ if (cstr->name == NULL) {
+ struct qstr istr;
+
+ ret = ext4_fname_crypto_alloc_buffer(ctx, len, cstr);
+ if (ret < 0)
+ goto errout;
+ istr.name = name;
+ istr.len = len;
+ ret = ext4_fname_encrypt(ctx, &istr, cstr);
+ if (ret < 0)
+ goto errout;
+ }
+ } else {
+ if (cstr->name == NULL) {
+ cstr->name = kmalloc(32, GFP_KERNEL);
+ if (cstr->name == NULL)
+ return -ENOMEM;
+ if ((bigname && (len != 33)) ||
+ (!bigname && (len > 43)))
+ goto errout;
+ ret = digest_decode(name+bigname, len-bigname,
+ cstr->name);
+ if (ret < 0) {
+ ret = -ENOENT;
+ goto errout;
+ }
+ cstr->len = ret;
+ }
+ if (bigname) {
+ if (de->name_len < 16)
+ return 0;
+ ret = memcmp(de->name + de->name_len - 16,
+ cstr->name + 8, 16);
+ return (ret == 0) ? 1 : 0;
+ }
+ }
+ if (de->name_len != cstr->len)
+ return 0;
+ ret = memcmp(de->name, cstr->name, cstr->len);
+ return (ret == 0) ? 1 : 0;
+errout:
+ kfree(cstr->name);
+ cstr->name = NULL;
+ return ret;
+}
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
new file mode 100644
index 000000000000..52170d0b7c40
--- /dev/null
+++ b/fs/ext4/crypto_key.c
@@ -0,0 +1,166 @@
+/*
+ * linux/fs/ext4/crypto_key.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions for ext4
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+
+#include "ext4.h"
+#include "xattr.h"
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+ struct ext4_completion_result *ecr = req->data;
+
+ if (rc == -EINPROGRESS)
+ return;
+
+ ecr->res = rc;
+ complete(&ecr->completion);
+}
+
+/**
+ * ext4_derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivatio.
+ * @source_key: Source key to which to apply derivation.
+ * @derived_key: Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
+ char source_key[EXT4_AES_256_XTS_KEY_SIZE],
+ char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
+{
+ int res = 0;
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct scatterlist src_sg, dst_sg;
+ struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
+ 0);
+
+ if (IS_ERR(tfm)) {
+ res = PTR_ERR(tfm);
+ tfm = NULL;
+ goto out;
+ }
+ crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ res = -ENOMEM;
+ goto out;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ derive_crypt_complete, &ecr);
+ res = crypto_ablkcipher_setkey(tfm, deriving_key,
+ EXT4_AES_128_ECB_KEY_SIZE);
+ if (res < 0)
+ goto out;
+ sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
+ sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
+ EXT4_AES_256_XTS_KEY_SIZE, NULL);
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+
+out:
+ if (req)
+ ablkcipher_request_free(req);
+ if (tfm)
+ crypto_free_ablkcipher(tfm);
+ return res;
+}
+
+/**
+ * ext4_generate_encryption_key() - generates an encryption key
+ * @inode: The inode to generate the encryption key for.
+ */
+int ext4_generate_encryption_key(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_encryption_key *crypt_key = &ei->i_encryption_key;
+ char full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
+ (EXT4_KEY_DESCRIPTOR_SIZE * 2) + 1];
+ struct key *keyring_key = NULL;
+ struct ext4_encryption_key *master_key;
+ struct ext4_encryption_context ctx;
+ struct user_key_payload *ukp;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx));
+
+ if (res != sizeof(ctx)) {
+ if (res > 0)
+ res = -EINVAL;
+ goto out;
+ }
+ res = 0;
+
+ ei->i_crypt_policy_flags = ctx.flags;
+ if (S_ISREG(inode->i_mode))
+ crypt_key->mode = ctx.contents_encryption_mode;
+ else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ crypt_key->mode = ctx.filenames_encryption_mode;
+ else {
+ printk(KERN_ERR "ext4 crypto: Unsupported inode type.\n");
+ BUG();
+ }
+ crypt_key->size = ext4_encryption_key_size(crypt_key->mode);
+ BUG_ON(!crypt_key->size);
+ if (DUMMY_ENCRYPTION_ENABLED(sbi)) {
+ memset(crypt_key->raw, 0x42, EXT4_AES_256_XTS_KEY_SIZE);
+ goto out;
+ }
+ memcpy(full_key_descriptor, EXT4_KEY_DESC_PREFIX,
+ EXT4_KEY_DESC_PREFIX_SIZE);
+ sprintf(full_key_descriptor + EXT4_KEY_DESC_PREFIX_SIZE,
+ "%*phN", EXT4_KEY_DESCRIPTOR_SIZE,
+ ctx.master_key_descriptor);
+ full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
+ (2 * EXT4_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;
+ }
+ BUG_ON(keyring_key->type != &key_type_logon);
+ ukp = ((struct user_key_payload *)keyring_key->payload.data);
+ if (ukp->datalen != sizeof(struct ext4_encryption_key)) {
+ res = -EINVAL;
+ goto out;
+ }
+ master_key = (struct ext4_encryption_key *)ukp->data;
+ BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE !=
+ EXT4_KEY_DERIVATION_NONCE_SIZE);
+ BUG_ON(master_key->size != EXT4_AES_256_XTS_KEY_SIZE);
+ res = ext4_derive_key_aes(ctx.nonce, master_key->raw, crypt_key->raw);
+out:
+ if (keyring_key)
+ key_put(keyring_key);
+ if (res < 0)
+ crypt_key->mode = EXT4_ENCRYPTION_MODE_INVALID;
+ return res;
+}
+
+int ext4_has_encryption_key(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_encryption_key *crypt_key = &ei->i_encryption_key;
+
+ return (crypt_key->mode != EXT4_ENCRYPTION_MODE_INVALID);
+}
diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c
new file mode 100644
index 000000000000..a6d6291aea16
--- /dev/null
+++ b/fs/ext4/crypto_policy.c
@@ -0,0 +1,198 @@
+/*
+ * linux/fs/ext4/crypto_policy.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption policy functions for ext4
+ *
+ * Written by Michael Halcrow, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "ext4.h"
+#include "xattr.h"
+
+static int ext4_inode_has_encryption_context(struct inode *inode)
+{
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0);
+ return (res > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int ext4_is_encryption_context_consistent_with_policy(
+ struct inode *inode, const struct ext4_encryption_policy *policy)
+{
+ struct ext4_encryption_context ctx;
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx));
+ if (res != sizeof(ctx))
+ return 0;
+ return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (ctx.flags ==
+ policy->flags) &&
+ (ctx.contents_encryption_mode ==
+ policy->contents_encryption_mode) &&
+ (ctx.filenames_encryption_mode ==
+ policy->filenames_encryption_mode));
+}
+
+static int ext4_create_encryption_context_from_policy(
+ struct inode *inode, const struct ext4_encryption_policy *policy)
+{
+ struct ext4_encryption_context ctx;
+ int res = 0;
+
+ ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
+ memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) {
+ printk(KERN_WARNING
+ "%s: Invalid contents encryption mode %d\n", __func__,
+ policy->contents_encryption_mode);
+ return -EINVAL;
+ }
+ if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
+ printk(KERN_WARNING
+ "%s: Invalid filenames encryption mode %d\n", __func__,
+ policy->filenames_encryption_mode);
+ return -EINVAL;
+ }
+ if (policy->flags & ~EXT4_POLICY_FLAGS_VALID)
+ return -EINVAL;
+ ctx.contents_encryption_mode = policy->contents_encryption_mode;
+ ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+ ctx.flags = policy->flags;
+ BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE);
+ get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
+
+ res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), 0);
+ if (!res)
+ ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+ return res;
+}
+
+int ext4_process_policy(const struct ext4_encryption_policy *policy,
+ struct inode *inode)
+{
+ if (policy->version != 0)
+ return -EINVAL;
+
+ if (!ext4_inode_has_encryption_context(inode)) {
+ if (!ext4_empty_dir(inode))
+ return -ENOTEMPTY;
+ return ext4_create_encryption_context_from_policy(inode,
+ policy);
+ }
+
+ if (ext4_is_encryption_context_consistent_with_policy(inode, policy))
+ return 0;
+
+ printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+ __func__);
+ return -EINVAL;
+}
+
+int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy)
+{
+ struct ext4_encryption_context ctx;
+
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx));
+ if (res != sizeof(ctx))
+ return -ENOENT;
+ if (ctx.format != EXT4_ENCRYPTION_CONTEXT_FORMAT_V1)
+ return -EINVAL;
+ policy->version = 0;
+ policy->contents_encryption_mode = ctx.contents_encryption_mode;
+ policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+ policy->flags = ctx.flags;
+ memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ return 0;
+}
+
+int ext4_is_child_context_consistent_with_parent(struct inode *parent,
+ struct inode *child)
+{
+ struct ext4_encryption_context parent_ctx, child_ctx;
+ int res;
+
+ if ((parent == NULL) || (child == NULL)) {
+ pr_err("parent %p child %p\n", parent, child);
+ BUG_ON(1);
+ }
+ /* no restrictions if the parent directory is not encrypted */
+ if (!ext4_encrypted_inode(parent))
+ return 1;
+ res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &parent_ctx, sizeof(parent_ctx));
+ if (res != sizeof(parent_ctx))
+ return 0;
+ /* if the child directory is not encrypted, this is always a problem */
+ if (!ext4_encrypted_inode(child))
+ return 0;
+ res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &child_ctx, sizeof(child_ctx));
+ if (res != sizeof(child_ctx))
+ return 0;
+ return (memcmp(parent_ctx.master_key_descriptor,
+ child_ctx.master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ctx.contents_encryption_mode ==
+ child_ctx.contents_encryption_mode) &&
+ (parent_ctx.filenames_encryption_mode ==
+ child_ctx.filenames_encryption_mode));
+}
+
+/**
+ * ext4_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child: Child inode that inherits the context from @parent.
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int ext4_inherit_context(struct inode *parent, struct inode *child)
+{
+ struct ext4_encryption_context ctx;
+ int res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx));
+
+ if (res != sizeof(ctx)) {
+ if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) {
+ ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
+ ctx.contents_encryption_mode =
+ EXT4_ENCRYPTION_MODE_AES_256_XTS;
+ ctx.filenames_encryption_mode =
+ EXT4_ENCRYPTION_MODE_AES_256_CTS;
+ ctx.flags = 0;
+ memset(ctx.master_key_descriptor, 0x42,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ res = 0;
+ } else {
+ goto out;
+ }
+ }
+ get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
+ res = ext4_xattr_set(child, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), 0);
+out:
+ if (!res)
+ ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT);
+ return res;
+}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index c24143ea9c08..5665d82d2332 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -22,10 +22,8 @@
*/
#include <linux/fs.h>
-#include <linux/jbd2.h>
#include <linux/buffer_head.h>
#include <linux/slab.h>
-#include <linux/rbtree.h>
#include "ext4.h"
#include "xattr.h"
@@ -110,7 +108,10 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
int err;
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
+ struct buffer_head *bh = NULL;
int dir_has_error = 0;
+ struct ext4_fname_crypto_ctx *enc_ctx = NULL;
+ struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
if (is_dx_dir(inode)) {
err = ext4_dx_readdir(file, ctx);
@@ -127,17 +128,28 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
if (ext4_has_inline_data(inode)) {
int has_inline_data = 1;
- int ret = ext4_read_inline_dir(file, ctx,
+ err = ext4_read_inline_dir(file, ctx,
&has_inline_data);
if (has_inline_data)
- return ret;
+ return err;
+ }
+
+ enc_ctx = ext4_get_fname_crypto_ctx(inode, EXT4_NAME_LEN);
+ if (IS_ERR(enc_ctx))
+ return PTR_ERR(enc_ctx);
+ if (enc_ctx) {
+ err = ext4_fname_crypto_alloc_buffer(enc_ctx, EXT4_NAME_LEN,
+ &fname_crypto_str);
+ if (err < 0) {
+ ext4_put_fname_crypto_ctx(&enc_ctx);
+ return err;
+ }
}
offset = ctx->pos & (sb->s_blocksize - 1);
while (ctx->pos < inode->i_size) {
struct ext4_map_blocks map;
- struct buffer_head *bh = NULL;
map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
map.m_len = 1;
@@ -180,6 +192,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
(unsigned long long)ctx->pos);
ctx->pos += sb->s_blocksize - offset;
brelse(bh);
+ bh = NULL;
continue;
}
set_buffer_verified(bh);
@@ -226,25 +239,44 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
offset += ext4_rec_len_from_disk(de->rec_len,
sb->s_blocksize);
if (le32_to_cpu(de->inode)) {
- if (!dir_emit(ctx, de->name,
- de->name_len,
- le32_to_cpu(de->inode),
- get_dtype(sb, de->file_type))) {
- brelse(bh);
- return 0;
+ if (enc_ctx == NULL) {
+ /* Directory is not encrypted */
+ if (!dir_emit(ctx, de->name,
+ de->name_len,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type)))
+ goto done;
+ } else {
+ /* Directory is encrypted */
+ err = ext4_fname_disk_to_usr(enc_ctx,
+ NULL, de, &fname_crypto_str);
+ if (err < 0)
+ goto errout;
+ if (!dir_emit(ctx,
+ fname_crypto_str.name, err,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type)))
+ goto done;
}
}
ctx->pos += ext4_rec_len_from_disk(de->rec_len,
sb->s_blocksize);
}
- offset = 0;
+ if ((ctx->pos < inode->i_size) && !dir_relax(inode))
+ goto done;
brelse(bh);
- if (ctx->pos < inode->i_size) {
- if (!dir_relax(inode))
- return 0;
- }
+ bh = NULL;
+ offset = 0;
}
- return 0;
+done:
+ err = 0;
+errout:
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ ext4_put_fname_crypto_ctx(&enc_ctx);
+ ext4_fname_crypto_free_buffer(&fname_crypto_str);
+#endif
+ brelse(bh);
+ return err;
}
static inline int is_32bit_api(void)
@@ -384,10 +416,15 @@ void ext4_htree_free_dir_info(struct dir_private_info *p)
/*
* Given a directory entry, enter it into the fname rb tree.
+ *
+ * When filename encryption is enabled, the dirent will hold the
+ * encrypted filename, while the htree will hold decrypted filename.
+ * The decrypted filename is passed in via ent_name. parameter.
*/
int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
- struct ext4_dir_entry_2 *dirent)
+ struct ext4_dir_entry_2 *dirent,
+ struct ext4_str *ent_name)
{
struct rb_node **p, *parent = NULL;
struct fname *fname, *new_fn;
@@ -398,17 +435,17 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
p = &info->root.rb_node;
/* Create and allocate the fname structure */
- len = sizeof(struct fname) + dirent->name_len + 1;
+ len = sizeof(struct fname) + ent_name->len + 1;
new_fn = kzalloc(len, GFP_KERNEL);
if (!new_fn)
return -ENOMEM;
new_fn->hash = hash;
new_fn->minor_hash = minor_hash;
new_fn->inode = le32_to_cpu(dirent->inode);
- new_fn->name_len = dirent->name_len;
+ new_fn->name_len = ent_name->len;
new_fn->file_type = dirent->file_type;
- memcpy(new_fn->name, dirent->name, dirent->name_len);
- new_fn->name[dirent->name_len] = 0;
+ memcpy(new_fn->name, ent_name->name, ent_name->len);
+ new_fn->name[ent_name->len] = 0;
while (*p) {
parent = *p;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f63c3d5805c4..9a83f149ac85 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -422,7 +422,7 @@ enum {
EXT4_INODE_DIRTY = 8,
EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */
EXT4_INODE_NOCOMPR = 10, /* Don't compress */
- EXT4_INODE_ENCRYPT = 11, /* Compression error */
+ EXT4_INODE_ENCRYPT = 11, /* Encrypted file */
/* End compression flags --- maybe not all used */
EXT4_INODE_INDEX = 12, /* hash-indexed directory */
EXT4_INODE_IMAGIC = 13, /* AFS directory */
@@ -582,6 +582,15 @@ enum {
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
+/* Encryption algorithms */
+#define EXT4_ENCRYPTION_MODE_INVALID 0
+#define EXT4_ENCRYPTION_MODE_AES_256_XTS 1
+#define EXT4_ENCRYPTION_MODE_AES_256_GCM 2
+#define EXT4_ENCRYPTION_MODE_AES_256_CBC 3
+#define EXT4_ENCRYPTION_MODE_AES_256_CTS 4
+
+#include "ext4_crypto.h"
+
/*
* ioctl commands
*/
@@ -603,6 +612,9 @@ enum {
#define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64)
#define EXT4_IOC_SWAP_BOOT _IO('f', 17)
#define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18)
+#define EXT4_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct ext4_encryption_policy)
+#define EXT4_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
+#define EXT4_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct ext4_encryption_policy)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -899,6 +911,7 @@ struct ext4_inode_info {
/* on-disk additional length */
__u16 i_extra_isize;
+ char i_crypt_policy_flags;
/* Indicate the inline data space. */
u16 i_inline_off;
@@ -939,6 +952,11 @@ struct ext4_inode_info {
/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
__u32 i_csum_seed;
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ /* Encryption params */
+ struct ext4_encryption_key i_encryption_key;
+#endif
};
/*
@@ -1049,12 +1067,6 @@ extern void ext4_set_bits(void *bm, int cur, int len);
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM 1
-/* Encryption algorithms */
-#define EXT4_ENCRYPTION_MODE_INVALID 0
-#define EXT4_ENCRYPTION_MODE_AES_256_XTS 1
-#define EXT4_ENCRYPTION_MODE_AES_256_GCM 2
-#define EXT4_ENCRYPTION_MODE_AES_256_CBC 3
-
/*
* Structure of the super block
*/
@@ -1142,7 +1154,8 @@ struct ext4_super_block {
__le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
__u8 s_log_groups_per_flex; /* FLEX_BG group size */
__u8 s_checksum_type; /* metadata checksum algorithm used */
- __le16 s_reserved_pad;
+ __u8 s_encryption_level; /* versioning level for encryption */
+ __u8 s_reserved_pad; /* Padding to next 32bits */
__le64 s_kbytes_written; /* nr of lifetime kilobytes written */
__le32 s_snapshot_inum; /* Inode number of active snapshot */
__le32 s_snapshot_id; /* sequential ID of active snapshot */
@@ -1169,7 +1182,9 @@ struct ext4_super_block {
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
__le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */
__u8 s_encrypt_algos[4]; /* Encryption algorithms in use */
- __le32 s_reserved[105]; /* Padding to the end of the block */
+ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
+ __le32 s_lpf_ino; /* Location of the lost+found inode */
+ __le32 s_reserved[100]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
@@ -1180,8 +1195,16 @@ struct ext4_super_block {
/*
* run-time mount flags
*/
-#define EXT4_MF_MNTDIR_SAMPLED 0x0001
-#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
+#define EXT4_MF_MNTDIR_SAMPLED 0x0001
+#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
+#define EXT4_MF_TEST_DUMMY_ENCRYPTION 0x0004
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \
+ EXT4_MF_TEST_DUMMY_ENCRYPTION))
+#else
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
+#endif
/* Number of quota types we support */
#define EXT4_MAXQUOTAS 2
@@ -1351,6 +1374,12 @@ struct ext4_sb_info {
struct ratelimit_state s_err_ratelimit_state;
struct ratelimit_state s_warning_ratelimit_state;
struct ratelimit_state s_msg_ratelimit_state;
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ /* Encryption */
+ uint32_t s_file_encryption_mode;
+ uint32_t s_dir_encryption_mode;
+#endif
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1466,6 +1495,18 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_SB(sb) (sb)
#endif
+/*
+ * Returns true if the inode is inode is encrypted
+ */
+static inline int ext4_encrypted_inode(struct inode *inode)
+{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
+#else
+ return 0;
+#endif
+}
+
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
/*
@@ -1575,8 +1616,9 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
EXT4_FEATURE_INCOMPAT_EXTENTS| \
EXT4_FEATURE_INCOMPAT_64BIT| \
EXT4_FEATURE_INCOMPAT_FLEX_BG| \
- EXT4_FEATURE_INCOMPAT_MMP | \
- EXT4_FEATURE_INCOMPAT_INLINE_DATA)
+ EXT4_FEATURE_INCOMPAT_MMP | \
+ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
+ EXT4_FEATURE_INCOMPAT_ENCRYPT)
#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -2001,6 +2043,102 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
+/* crypto_policy.c */
+int ext4_is_child_context_consistent_with_parent(struct inode *parent,
+ struct inode *child);
+int ext4_inherit_context(struct inode *parent, struct inode *child);
+void ext4_to_hex(char *dst, char *src, size_t src_size);
+int ext4_process_policy(const struct ext4_encryption_policy *policy,
+ struct inode *inode);
+int ext4_get_policy(struct inode *inode,
+ struct ext4_encryption_policy *policy);
+
+/* crypto.c */
+bool ext4_valid_contents_enc_mode(uint32_t mode);
+uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
+extern struct workqueue_struct *ext4_read_workqueue;
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode);
+void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
+void ext4_restore_control_page(struct page *data_page);
+struct page *ext4_encrypt(struct inode *inode,
+ struct page *plaintext_page);
+int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page);
+int ext4_decrypt_one(struct inode *inode, struct page *page);
+int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+int ext4_init_crypto(void);
+void ext4_exit_crypto(void);
+static inline int ext4_sb_has_crypto(struct super_block *sb)
+{
+ return EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT);
+}
+#else
+static inline int ext4_init_crypto(void) { return 0; }
+static inline void ext4_exit_crypto(void) { }
+static inline int ext4_sb_has_crypto(struct super_block *sb)
+{
+ return 0;
+}
+#endif
+
+/* crypto_fname.c */
+bool ext4_valid_filenames_enc_mode(uint32_t mode);
+u32 ext4_fname_crypto_round_up(u32 size, u32 blksize);
+int ext4_fname_crypto_alloc_buffer(struct ext4_fname_crypto_ctx *ctx,
+ u32 ilen, struct ext4_str *crypto_str);
+int _ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx,
+ struct dx_hash_info *hinfo,
+ const struct ext4_str *iname,
+ struct ext4_str *oname);
+int ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx,
+ struct dx_hash_info *hinfo,
+ const struct ext4_dir_entry_2 *de,
+ struct ext4_str *oname);
+int ext4_fname_usr_to_disk(struct ext4_fname_crypto_ctx *ctx,
+ const struct qstr *iname,
+ struct ext4_str *oname);
+int ext4_fname_usr_to_hash(struct ext4_fname_crypto_ctx *ctx,
+ const struct qstr *iname,
+ struct dx_hash_info *hinfo);
+int ext4_fname_crypto_namelen_on_disk(struct ext4_fname_crypto_ctx *ctx,
+ u32 namelen);
+int ext4_fname_match(struct ext4_fname_crypto_ctx *ctx, struct ext4_str *cstr,
+ int len, const char * const name,
+ struct ext4_dir_entry_2 *de);
+
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx);
+struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(struct inode *inode,
+ u32 max_len);
+void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str);
+#else
+static inline
+void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx) { }
+static inline
+struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(struct inode *inode,
+ u32 max_len)
+{
+ return NULL;
+}
+static inline void ext4_fname_crypto_free_buffer(struct ext4_str *p) { }
+#endif
+
+
+/* crypto_key.c */
+int ext4_generate_encryption_key(struct inode *inode);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+int ext4_has_encryption_key(struct inode *inode);
+#else
+static inline int ext4_has_encryption_key(struct inode *inode)
+{
+ return 0;
+}
+#endif
+
+
/* dir.c */
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
struct file *,
@@ -2011,17 +2149,20 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
(de), (bh), (buf), (size), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
- __u32 minor_hash,
- struct ext4_dir_entry_2 *dirent);
+ __u32 minor_hash,
+ struct ext4_dir_entry_2 *dirent,
+ struct ext4_str *ent_name);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
struct buffer_head *bh,
void *buf, int buf_size,
const char *name, int namelen,
struct ext4_dir_entry_2 **dest_de);
-void ext4_insert_dentry(struct inode *inode,
+int ext4_insert_dentry(struct inode *dir,
+ struct inode *inode,
struct ext4_dir_entry_2 *de,
int buf_size,
+ const struct qstr *iname,
const char *name, int namelen);
static inline void ext4_update_dx_flag(struct inode *inode)
{
@@ -2099,6 +2240,7 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
/* inode.c */
+int ext4_inode_is_fast_symlink(struct inode *inode);
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
int ext4_get_block_write(struct inode *inode, sector_t iblock,
@@ -2152,8 +2294,8 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
-extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- struct iov_iter *iter, loff_t offset);
+extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
@@ -2189,6 +2331,7 @@ extern int ext4_generic_delete_entry(handle_t *handle,
void *entry_buf,
int buf_size,
int csum_size);
+extern int ext4_empty_dir(struct inode *inode);
/* resize.c */
extern int ext4_group_add(struct super_block *sb,
@@ -2593,7 +2736,6 @@ extern const struct file_operations ext4_dir_operations;
/* file.c */
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
-extern const struct file_operations ext4_dax_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* inline.c */
@@ -2699,6 +2841,10 @@ static inline void ext4_set_de_type(struct super_block *sb,
de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}
+/* readpages.c */
+extern int ext4_mpage_readpages(struct address_space *mapping,
+ struct list_head *pages, struct page *page,
+ unsigned nr_pages);
/* symlink.c */
extern const struct inode_operations ext4_symlink_inode_operations;
@@ -2743,7 +2889,6 @@ extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_ext_calc_metadata_amount(struct inode *inode,
ext4_lblk_t lblocks);
-extern int ext4_extent_tree_init(handle_t *, struct inode *);
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
int num,
struct ext4_ext_path *path);
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
new file mode 100644
index 000000000000..d75159c101ce
--- /dev/null
+++ b/fs/ext4/ext4_crypto.h
@@ -0,0 +1,156 @@
+/*
+ * linux/fs/ext4/ext4_crypto.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption header content for ext4
+ *
+ * Written by Michael Halcrow, 2015.
+ */
+
+#ifndef _EXT4_CRYPTO_H
+#define _EXT4_CRYPTO_H
+
+#include <linux/fs.h>
+
+#define EXT4_KEY_DESCRIPTOR_SIZE 8
+
+/* Policy provided via an ioctl on the topmost directory */
+struct ext4_encryption_policy {
+ char version;
+ char contents_encryption_mode;
+ char filenames_encryption_mode;
+ char flags;
+ char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
+} __attribute__((__packed__));
+
+#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1
+#define EXT4_KEY_DERIVATION_NONCE_SIZE 16
+
+#define EXT4_POLICY_FLAGS_PAD_4 0x00
+#define EXT4_POLICY_FLAGS_PAD_8 0x01
+#define EXT4_POLICY_FLAGS_PAD_16 0x02
+#define EXT4_POLICY_FLAGS_PAD_32 0x03
+#define EXT4_POLICY_FLAGS_PAD_MASK 0x03
+#define EXT4_POLICY_FLAGS_VALID 0x03
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ * 1 byte: Protector format (1 = this version)
+ * 1 byte: File contents encryption mode
+ * 1 byte: File names encryption mode
+ * 1 byte: Reserved
+ * 8 bytes: Master Key descriptor
+ * 16 bytes: Encryption Key derivation nonce
+ */
+struct ext4_encryption_context {
+ char format;
+ char contents_encryption_mode;
+ char filenames_encryption_mode;
+ char flags;
+ char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
+ char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE];
+} __attribute__((__packed__));
+
+/* Encryption parameters */
+#define EXT4_XTS_TWEAK_SIZE 16
+#define EXT4_AES_128_ECB_KEY_SIZE 16
+#define EXT4_AES_256_GCM_KEY_SIZE 32
+#define EXT4_AES_256_CBC_KEY_SIZE 32
+#define EXT4_AES_256_CTS_KEY_SIZE 32
+#define EXT4_AES_256_XTS_KEY_SIZE 64
+#define EXT4_MAX_KEY_SIZE 64
+
+#define EXT4_KEY_DESC_PREFIX "ext4:"
+#define EXT4_KEY_DESC_PREFIX_SIZE 5
+
+struct ext4_encryption_key {
+ uint32_t mode;
+ char raw[EXT4_MAX_KEY_SIZE];
+ uint32_t size;
+};
+
+#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
+#define EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL 0x00000002
+
+struct ext4_crypto_ctx {
+ struct crypto_tfm *tfm; /* Crypto API context */
+ struct page *bounce_page; /* Ciphertext page on write path */
+ struct page *control_page; /* Original page on write path */
+ struct bio *bio; /* The bio for this context */
+ struct work_struct work; /* Work queue for read complete path */
+ struct list_head free_list; /* Free list */
+ int flags; /* Flags */
+ int mode; /* Encryption mode for tfm */
+};
+
+struct ext4_completion_result {
+ struct completion completion;
+ int res;
+};
+
+#define DECLARE_EXT4_COMPLETION_RESULT(ecr) \
+ struct ext4_completion_result ecr = { \
+ COMPLETION_INITIALIZER((ecr).completion), 0 }
+
+static inline int ext4_encryption_key_size(int mode)
+{
+ switch (mode) {
+ case EXT4_ENCRYPTION_MODE_AES_256_XTS:
+ return EXT4_AES_256_XTS_KEY_SIZE;
+ case EXT4_ENCRYPTION_MODE_AES_256_GCM:
+ return EXT4_AES_256_GCM_KEY_SIZE;
+ case EXT4_ENCRYPTION_MODE_AES_256_CBC:
+ return EXT4_AES_256_CBC_KEY_SIZE;
+ case EXT4_ENCRYPTION_MODE_AES_256_CTS:
+ return EXT4_AES_256_CTS_KEY_SIZE;
+ default:
+ BUG();
+ }
+ return 0;
+}
+
+#define EXT4_FNAME_NUM_SCATTER_ENTRIES 4
+#define EXT4_CRYPTO_BLOCK_SIZE 16
+#define EXT4_FNAME_CRYPTO_DIGEST_SIZE 32
+
+struct ext4_str {
+ unsigned char *name;
+ u32 len;
+};
+
+struct ext4_fname_crypto_ctx {
+ u32 lim;
+ char tmp_buf[EXT4_CRYPTO_BLOCK_SIZE];
+ struct crypto_ablkcipher *ctfm;
+ struct crypto_hash *htfm;
+ struct page *workpage;
+ struct ext4_encryption_key key;
+ unsigned flags : 8;
+ unsigned has_valid_key : 1;
+ unsigned ctfm_key_is_ready : 1;
+};
+
+/**
+ * For encrypted symlinks, the ciphertext length is stored at the beginning
+ * of the string in little-endian format.
+ */
+struct ext4_encrypted_symlink_data {
+ __le16 len;
+ char encrypted_path[1];
+} __attribute__((__packed__));
+
+/**
+ * This function is used to calculate the disk space required to
+ * store a filename of length l in encrypted symlink format.
+ */
+static inline u32 encrypted_symlink_data_len(u32 l)
+{
+ if (l < EXT4_CRYPTO_BLOCK_SIZE)
+ l = EXT4_CRYPTO_BLOCK_SIZE;
+ return (l + sizeof(struct ext4_encrypted_symlink_data) - 1);
+}
+
+#endif /* _EXT4_CRYPTO_H */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 3445035c7e01..d41843181818 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -87,6 +87,12 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
ext4_put_nojournal(handle);
return 0;
}
+
+ if (!handle->h_transaction) {
+ err = jbd2_journal_stop(handle);
+ return handle->h_err ? handle->h_err : err;
+ }
+
sb = handle->h_transaction->t_journal->j_private;
err = handle->h_err;
rc = jbd2_journal_stop(handle);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index bed43081720f..e003a1e81dc3 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -377,7 +377,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
ext4_lblk_t last = lblock + len - 1;
- if (lblock > last)
+ if (len == 0 || lblock > last)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
@@ -1717,12 +1717,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
{
unsigned short ext1_ee_len, ext2_ee_len;
- /*
- * Make sure that both extents are initialized. We don't merge
- * unwritten extents so that we can be sure that end_io code has
- * the extent that was written properly split out and conversion to
- * initialized is trivial.
- */
if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
return 0;
@@ -3128,6 +3122,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
ee_len = ext4_ext_get_actual_len(ex);
ee_pblock = ext4_ext_pblock(ex);
+ if (ext4_encrypted_inode(inode))
+ return ext4_encrypted_zeroout(inode, ex);
+
ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS);
if (ret > 0)
ret = 0;
@@ -4535,19 +4532,7 @@ got_allocated_blocks:
*/
reserved_clusters = get_reserved_cluster_alloc(inode,
map->m_lblk, allocated);
- if (map_from_cluster) {
- if (reserved_clusters) {
- /*
- * We have clusters reserved for this range.
- * But since we are not doing actual allocation
- * and are simply using blocks from previously
- * allocated cluster, we should release the
- * reservation and not claim quota.
- */
- ext4_da_update_reserve_space(inode,
- reserved_clusters, 0);
- }
- } else {
+ if (!map_from_cluster) {
BUG_ON(allocated_clusters < reserved_clusters);
if (reserved_clusters < allocated_clusters) {
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -4803,12 +4788,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
else
max_blocks -= lblk;
- flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
- EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
- EXT4_EX_NOCACHE;
- if (mode & FALLOC_FL_KEEP_SIZE)
- flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
-
mutex_lock(&inode->i_mutex);
/*
@@ -4825,15 +4804,28 @@ static long ext4_zero_range(struct file *file, loff_t offset,
ret = inode_newsize_ok(inode, new_size);
if (ret)
goto out_mutex;
- /*
- * If we have a partial block after EOF we have to allocate
- * the entire block.
- */
- if (partial_end)
- max_blocks += 1;
}
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+
+ /* Preallocate the range including the unaligned edges */
+ if (partial_begin || partial_end) {
+ ret = ext4_alloc_file_blocks(file,
+ round_down(offset, 1 << blkbits) >> blkbits,
+ (round_up((offset + len), 1 << blkbits) -
+ round_down(offset, 1 << blkbits)) >> blkbits,
+ new_size, flags, mode);
+ if (ret)
+ goto out_mutex;
+
+ }
+
+ /* Zero range excluding the unaligned edges */
if (max_blocks > 0) {
+ flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+ EXT4_EX_NOCACHE);
/* Now release the pages and zero block aligned part of pages*/
truncate_pagecache_range(inode, start, end - 1);
@@ -4847,19 +4839,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
flags, mode);
if (ret)
goto out_dio;
- /*
- * Remove entire range from the extent status tree.
- *
- * ext4_es_remove_extent(inode, lblk, max_blocks) is
- * NOT sufficient. I'm not sure why this is the case,
- * but let's be conservative and remove the extent
- * status tree for the entire inode. There should be
- * no outstanding delalloc extents thanks to the
- * filemap_write_and_wait_range() call above.
- */
- ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
- if (ret)
- goto out_dio;
}
if (!partial_begin && !partial_end)
goto out_dio;
@@ -4922,6 +4901,20 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
ext4_lblk_t lblk;
unsigned int blkbits = inode->i_blkbits;
+ /*
+ * Encrypted inodes can't handle collapse range or insert
+ * range since we would need to re-encrypt blocks with a
+ * different IV or XTS tweak (which are based on the logical
+ * block number).
+ *
+ * XXX It's not clear why zero range isn't working, but we'll
+ * leave it disabled for encrypted inodes for now. This is a
+ * bug we should fix....
+ */
+ if (ext4_encrypted_inode(inode) &&
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)))
+ return -EOPNOTSUPP;
+
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
@@ -4934,13 +4927,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (ret)
return ret;
- /*
- * currently supporting (pre)allocate mode for extent-based
- * files _only_
- */
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return -EOPNOTSUPP;
-
if (mode & FALLOC_FL_COLLAPSE_RANGE)
return ext4_collapse_range(inode, offset, len);
@@ -4962,6 +4948,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
mutex_lock(&inode->i_mutex);
+ /*
+ * We only support preallocation for extent-based files only
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode)) {
new_size = offset + len;
@@ -5402,6 +5396,14 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
loff_t new_size, ioffset;
int ret;
+ /*
+ * We need to test this early because xfstests assumes that a
+ * collapse range of (0, 1) will return EOPNOTSUPP if the file
+ * system does not support collapse range.
+ */
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return -EOPNOTSUPP;
+
/* Collapse range works only on fs block size aligned offsets. */
if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
len & (EXT4_CLUSTER_SIZE(sb) - 1))
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index e04d45733976..26724aeece73 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -9,12 +9,10 @@
*
* Ext4 extents status tree core functions.
*/
-#include <linux/rbtree.h>
#include <linux/list_sort.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include "ext4.h"
-#include "extents_status.h"
#include <trace/events/ext4.h>
@@ -705,6 +703,14 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
BUG_ON(end < lblk);
+ if ((status & EXTENT_STATUS_DELAYED) &&
+ (status & EXTENT_STATUS_WRITTEN)) {
+ ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as "
+ " delayed and written which can potentially "
+ " cause data loss.\n", lblk, len);
+ WARN_ON(1);
+ }
+
newes.es_lblk = lblk;
newes.es_len = len;
ext4_es_store_pblock_status(&newes, pblk, status);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 33a09da16c9c..0613c256c344 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -20,12 +20,11 @@
#include <linux/time.h>
#include <linux/fs.h>
-#include <linux/jbd2.h>
#include <linux/mount.h>
#include <linux/path.h>
-#include <linux/aio.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
+#include <linux/uio.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -95,11 +94,9 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = file_inode(iocb->ki_filp);
struct mutex *aio_mutex = NULL;
struct blk_plug plug;
- int o_direct = io_is_direct(file);
+ int o_direct = iocb->ki_flags & IOCB_DIRECT;
int overwrite = 0;
- size_t length = iov_iter_count(from);
ssize_t ret;
- loff_t pos = iocb->ki_pos;
/*
* Unaligned direct AIO must be serialized; see comment above
@@ -108,16 +105,17 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (o_direct &&
ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
!is_sync_kiocb(iocb) &&
- (file->f_flags & O_APPEND ||
- ext4_unaligned_aio(inode, from, pos))) {
+ (iocb->ki_flags & IOCB_APPEND ||
+ ext4_unaligned_aio(inode, from, iocb->ki_pos))) {
aio_mutex = ext4_aio_mutex(inode);
mutex_lock(aio_mutex);
ext4_unwritten_wait(inode);
}
mutex_lock(&inode->i_mutex);
- if (file->f_flags & O_APPEND)
- iocb->ki_pos = pos = i_size_read(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out;
/*
* If we have encountered a bitmap-format file, the size limit
@@ -126,22 +124,19 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if ((pos > sbi->s_bitmap_maxbytes) ||
- (pos == sbi->s_bitmap_maxbytes && length > 0)) {
- mutex_unlock(&inode->i_mutex);
+ if (iocb->ki_pos >= sbi->s_bitmap_maxbytes) {
ret = -EFBIG;
- goto errout;
+ goto out;
}
-
- if (pos + length > sbi->s_bitmap_maxbytes)
- iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
+ iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
}
iocb->private = &overwrite;
if (o_direct) {
+ size_t length = iov_iter_count(from);
+ loff_t pos = iocb->ki_pos;
blk_start_plug(&plug);
-
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
@@ -185,7 +180,12 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (o_direct)
blk_finish_plug(&plug);
-errout:
+ if (aio_mutex)
+ mutex_unlock(aio_mutex);
+ return ret;
+
+out:
+ mutex_unlock(&inode->i_mutex);
if (aio_mutex)
mutex_unlock(aio_mutex);
return ret;
@@ -206,6 +206,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
.page_mkwrite = ext4_dax_mkwrite,
+ .pfn_mkwrite = dax_pfn_mkwrite,
};
#else
#define ext4_dax_vm_ops ext4_file_vm_ops
@@ -219,6 +220,13 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
+ struct inode *inode = file->f_mapping->host;
+
+ if (ext4_encrypted_inode(inode)) {
+ int err = ext4_generate_encryption_key(inode);
+ if (err)
+ return 0;
+ }
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
@@ -236,6 +244,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
+ int ret;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
@@ -274,11 +283,17 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
* writing and the journal is present
*/
if (filp->f_mode & FMODE_WRITE) {
- int ret = ext4_inode_attach_jinode(inode);
+ ret = ext4_inode_attach_jinode(inode);
if (ret < 0)
return ret;
}
- return dquot_file_open(inode, filp);
+ ret = dquot_file_open(inode, filp);
+ if (!ret && ext4_encrypted_inode(inode)) {
+ ret = ext4_generate_encryption_key(inode);
+ if (ret)
+ ret = -EACCES;
+ }
+ return ret;
}
/*
@@ -607,8 +622,6 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
const struct file_operations ext4_file_operations = {
.llseek = ext4_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
.read_iter = generic_file_read_iter,
.write_iter = ext4_file_write_iter,
.unlocked_ioctl = ext4_ioctl,
@@ -624,26 +637,6 @@ const struct file_operations ext4_file_operations = {
.fallocate = ext4_fallocate,
};
-#ifdef CONFIG_FS_DAX
-const struct file_operations ext4_dax_file_operations = {
- .llseek = ext4_llseek,
- .read = new_sync_read,
- .write = new_sync_write,
- .read_iter = generic_file_read_iter,
- .write_iter = ext4_file_write_iter,
- .unlocked_ioctl = ext4_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext4_compat_ioctl,
-#endif
- .mmap = ext4_file_mmap,
- .open = ext4_file_open,
- .release = ext4_release_file,
- .fsync = ext4_sync_file,
- /* Splice not yet supported with DAX */
- .fallocate = ext4_fallocate,
-};
-#endif
-
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_getattr,
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a8bc47f75fa0..8850254136ae 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -26,7 +26,6 @@
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/writeback.h>
-#include <linux/jbd2.h>
#include <linux/blkdev.h>
#include "ext4.h"
@@ -56,7 +55,7 @@ static int ext4_sync_parent(struct inode *inode)
dentry = d_find_any_alias(inode);
if (!dentry)
break;
- next = igrab(dentry->d_parent->d_inode);
+ next = igrab(d_inode(dentry->d_parent));
dput(dentry);
if (!next)
break;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 3d586f02883e..e026aa941fd5 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -10,7 +10,6 @@
*/
#include <linux/fs.h>
-#include <linux/jbd2.h>
#include <linux/cryptohash.h>
#include "ext4.h"
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index ac644c31ca67..1eaa6cb96cd0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -14,7 +14,6 @@
#include <linux/time.h>
#include <linux/fs.h>
-#include <linux/jbd2.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
@@ -444,7 +443,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if (S_ISDIR(mode) &&
- ((parent == sb->s_root->d_inode) ||
+ ((parent == d_inode(sb->s_root)) ||
(ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
int best_ndir = inodes_per_group;
int ret = -1;
@@ -997,6 +996,12 @@ got:
ei->i_block_group = group;
ei->i_last_alloc_group = ~0;
+ /* If the directory encrypted, then we should encrypt the inode. */
+ if ((S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) &&
+ (ext4_encrypted_inode(dir) ||
+ DUMMY_ENCRYPTION_ENABLED(sbi)))
+ ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+
ext4_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
ext4_handle_sync(handle);
@@ -1029,11 +1034,28 @@ got:
ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
-