summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/v9fs.c16
-rw-r--r--fs/9p/vfs_super.c5
-rw-r--r--fs/Kconfig5
-rw-r--r--fs/Makefile1
-rw-r--r--fs/adfs/super.c3
-rw-r--r--fs/affs/super.c7
-rw-r--r--fs/afs/file.c2
-rw-r--r--fs/afs/fsclient.c8
-rw-r--r--fs/afs/internal.h2
-rw-r--r--fs/afs/mntpt.c4
-rw-r--r--fs/afs/rxrpc.c3
-rw-r--r--fs/afs/super.c7
-rw-r--r--fs/aio.c121
-rw-r--r--fs/anon_inodes.c109
-rw-r--r--fs/attr.c2
-rw-r--r--fs/autofs4/autofs_i.h1
-rw-r--r--fs/autofs4/dev-ioctl.c1
-rw-r--r--fs/autofs4/expire.c2
-rw-r--r--fs/autofs4/init.c6
-rw-r--r--fs/autofs4/inode.c12
-rw-r--r--fs/autofs4/waitq.c22
-rw-r--r--fs/bad_inode.c2
-rw-r--r--fs/befs/linuxvfs.c3
-rw-r--r--fs/bfs/inode.c3
-rw-r--r--fs/binfmt_aout.c18
-rw-r--r--fs/binfmt_elf.c37
-rw-r--r--fs/binfmt_elf_fdpic.c6
-rw-r--r--fs/binfmt_em86.c3
-rw-r--r--fs/binfmt_flat.c6
-rw-r--r--fs/binfmt_misc.c10
-rw-r--r--fs/binfmt_script.c3
-rw-r--r--fs/binfmt_som.c4
-rw-r--r--fs/bio-integrity.c10
-rw-r--r--fs/bio.c12
-rw-r--r--fs/block_dev.c21
-rw-r--r--fs/btrfs/backref.c14
-rw-r--r--fs/btrfs/check-integrity.c14
-rw-r--r--fs/btrfs/compression.c14
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/disk-io.c19
-rw-r--r--fs/btrfs/extent-tree.c100
-rw-r--r--fs/btrfs/extent_io.c131
-rw-r--r--fs/btrfs/extent_io.h1
-rw-r--r--fs/btrfs/extent_map.h4
-rw-r--r--fs/btrfs/file-item.c4
-rw-r--r--fs/btrfs/file.c29
-rw-r--r--fs/btrfs/free-space-cache.c8
-rw-r--r--fs/btrfs/inode-map.c6
-rw-r--r--fs/btrfs/inode.c76
-rw-r--r--fs/btrfs/ioctl.c61
-rw-r--r--fs/btrfs/lzo.c4
-rw-r--r--fs/btrfs/reada.c2
-rw-r--r--fs/btrfs/scrub.c16
-rw-r--r--fs/btrfs/super.c8
-rw-r--r--fs/btrfs/transaction.c16
-rw-r--r--fs/btrfs/tree-log.c6
-rw-r--r--fs/btrfs/volumes.c33
-rw-r--r--fs/btrfs/zlib.c4
-rw-r--r--fs/buffer.c2
-rw-r--r--fs/cachefiles/namei.c3
-rw-r--r--fs/ceph/caps.c4
-rw-r--r--fs/ceph/dir.c4
-rw-r--r--fs/ceph/inode.c11
-rw-r--r--fs/ceph/mds_client.c17
-rw-r--r--fs/ceph/mds_client.h7
-rw-r--r--fs/ceph/snap.c2
-rw-r--r--fs/ceph/super.c22
-rw-r--r--fs/ceph/super.h4
-rw-r--r--fs/ceph/xattr.c202
-rw-r--r--fs/cifs/Kconfig7
-rw-r--r--fs/cifs/README6
-rw-r--r--fs/cifs/cifs_debug.c14
-rw-r--r--fs/cifs/cifs_spnego.c10
-rw-r--r--fs/cifs/cifs_unicode.c41
-rw-r--r--fs/cifs/cifs_unicode.h20
-rw-r--r--fs/cifs/cifsacl.c3
-rw-r--r--fs/cifs/cifsencrypt.c21
-rw-r--r--fs/cifs/cifsfs.c32
-rw-r--r--fs/cifs/cifsglob.h49
-rw-r--r--fs/cifs/cifsproto.h9
-rw-r--r--fs/cifs/cifssmb.c180
-rw-r--r--fs/cifs/connect.c362
-rw-r--r--fs/cifs/dir.c26
-rw-r--r--fs/cifs/file.c74
-rw-r--r--fs/cifs/inode.c28
-rw-r--r--fs/cifs/misc.c19
-rw-r--r--fs/cifs/readdir.c9
-rw-r--r--fs/cifs/sess.c45
-rw-r--r--fs/cifs/smbencrypt.c2
-rw-r--r--fs/cifs/transport.c78
-rw-r--r--fs/cifs/xattr.c6
-rw-r--r--fs/coda/inode.c6
-rw-r--r--fs/compat.c57
-rw-r--r--fs/compat_ioctl.c3
-rw-r--r--fs/configfs/configfs_internal.h7
-rw-r--r--fs/configfs/dir.c72
-rw-r--r--fs/configfs/inode.c62
-rw-r--r--fs/configfs/mount.c16
-rw-r--r--fs/configfs/symlink.c12
-rw-r--r--fs/cramfs/inode.c12
-rw-r--r--fs/dcache.c101
-rw-r--r--fs/dcookies.c2
-rw-r--r--fs/debugfs/file.c4
-rw-r--r--fs/debugfs/inode.c149
-rw-r--r--fs/devpts/inode.c88
-rw-r--r--fs/direct-io.c4
-rw-r--r--fs/dlm/dir.c17
-rw-r--r--fs/dlm/lock.c8
-rw-r--r--fs/dlm/lock.h3
-rw-r--r--fs/dlm/lowcomms.c24
-rw-r--r--fs/ecryptfs/crypto.c122
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h11
-rw-r--r--fs/ecryptfs/file.c9
-rw-r--r--fs/ecryptfs/inode.c50
-rw-r--r--fs/ecryptfs/keystore.c14
-rw-r--r--fs/ecryptfs/main.c19
-rw-r--r--fs/ecryptfs/miscdev.c140
-rw-r--r--fs/ecryptfs/mmap.c12
-rw-r--r--fs/ecryptfs/read_write.c100
-rw-r--r--fs/ecryptfs/super.c15
-rw-r--r--fs/efs/super.c3
-rw-r--r--fs/eventfd.c2
-rw-r--r--fs/eventpoll.c79
-rw-r--r--fs/exec.c79
-rw-r--r--fs/exofs/dir.c4
-rw-r--r--fs/exofs/namei.c13
-rw-r--r--fs/exofs/super.c4
-rw-r--r--fs/ext2/dir.c4
-rw-r--r--fs/ext2/ioctl.c22
-rw-r--r--fs/ext2/namei.c13
-rw-r--r--fs/ext2/super.c4
-rw-r--r--fs/ext3/balloc.c84
-rw-r--r--fs/ext3/inode.c9
-rw-r--r--fs/ext3/super.c3
-rw-r--r--fs/ext4/balloc.c63
-rw-r--r--fs/ext4/dir.c13
-rw-r--r--fs/ext4/ext4.h34
-rw-r--r--fs/ext4/ext4_extents.h4
-rw-r--r--fs/ext4/ext4_jbd2.h128
-rw-r--r--fs/ext4/extents.c330
-rw-r--r--fs/ext4/fsync.c2
-rw-r--r--fs/ext4/ialloc.c260
-rw-r--r--fs/ext4/inode.c95
-rw-r--r--fs/ext4/mballoc.c342
-rw-r--r--fs/ext4/mballoc.h20
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/mmp.c4
-rw-r--r--fs/ext4/namei.c2
-rw-r--r--fs/ext4/page-io.c18
-rw-r--r--fs/ext4/resize.c37
-rw-r--r--fs/ext4/super.c1083
-rw-r--r--fs/ext4/xattr.c25
-rw-r--r--fs/fat/inode.c8
-rw-r--r--fs/fat/namei_vfat.c83
-rw-r--r--fs/file.c2
-rw-r--r--fs/file_table.c3
-rw-r--r--fs/freevxfs/vxfs_super.c3
-rw-r--r--fs/fs-writeback.c42
-rw-r--r--fs/fs_struct.c31
-rw-r--r--fs/fuse/dev.c4
-rw-r--r--fs/fuse/file.c4
-rw-r--r--fs/fuse/inode.c9
-rw-r--r--fs/gfs2/aops.c12
-rw-r--r--fs/gfs2/bmap.c4
-rw-r--r--fs/gfs2/file.c15
-rw-r--r--fs/gfs2/glock.c224
-rw-r--r--fs/gfs2/incore.h50
-rw-r--r--fs/gfs2/inode.c9
-rw-r--r--fs/gfs2/lock_dlm.c123
-rw-r--r--fs/gfs2/log.c244
-rw-r--r--fs/gfs2/log.h5
-rw-r--r--fs/gfs2/lops.c103
-rw-r--r--fs/gfs2/main.c18
-rw-r--r--fs/gfs2/ops_fstype.c17
-rw-r--r--fs/gfs2/quota.c6
-rw-r--r--fs/gfs2/rgrp.c202
-rw-r--r--fs/gfs2/rgrp.h10
-rw-r--r--fs/gfs2/super.c3
-rw-r--r--fs/gfs2/trace_gfs2.h60
-rw-r--r--fs/gfs2/util.c1
-rw-r--r--fs/gfs2/util.h3
-rw-r--r--fs/gfs2/xattr.c4
-rw-r--r--fs/hfs/super.c6
-rw-r--r--fs/hfsplus/hfsplus_fs.h5
-rw-r--r--fs/hfsplus/hfsplus_raw.h2
-rw-r--r--fs/hfsplus/inode.c2
-rw-r--r--fs/hfsplus/ioctl.c34
-rw-r--r--fs/hfsplus/super.c17
-rw-r--r--fs/hostfs/hostfs.h3
-rw-r--r--fs/hostfs/hostfs_kern.c9
-rw-r--r--fs/hostfs/hostfs_user.c4
-rw-r--r--fs/hpfs/super.c6
-rw-r--r--fs/hppfs/hppfs.c9
-rw-r--r--fs/hugetlbfs/inode.c151
-rw-r--r--fs/inode.c40
-rw-r--r--fs/ioctl.c2
-rw-r--r--fs/ioprio.c2
-rw-r--r--fs/isofs/inode.c3
-rw-r--r--fs/jbd/checkpoint.c27
-rw-r--r--fs/jbd/journal.c14
-rw-r--r--fs/jbd/recovery.c4
-rw-r--r--fs/jbd/transaction.c4
-rw-r--r--fs/jbd2/checkpoint.c140
-rw-r--r--fs/jbd2/commit.c51
-rw-r--r--fs/jbd2/journal.c375
-rw-r--r--fs/jbd2/recovery.c5
-rw-r--r--fs/jbd2/revoke.c12
-rw-r--r--fs/jbd2/transaction.c52
-rw-r--r--fs/jffs2/compr.c2
-rw-r--r--fs/jffs2/erase.c2
-rw-r--r--fs/jffs2/fs.c6
-rw-r--r--fs/jfs/namei.c13
-rw-r--r--fs/jfs/super.c12
-rw-r--r--fs/libfs.c10
-rw-r--r--fs/lockd/clnt4xdr.c2
-rw-r--r--fs/lockd/clntlock.c3
-rw-r--r--fs/lockd/clntxdr.c8
-rw-r--r--fs/lockd/host.c42
-rw-r--r--fs/lockd/mon.c21
-rw-r--r--fs/lockd/netns.h12
-rw-r--r--fs/lockd/svc.c117
-rw-r--r--fs/lockd/svclock.c59
-rw-r--r--fs/logfs/dev_mtd.c6
-rw-r--r--fs/logfs/dir.c23
-rw-r--r--fs/logfs/file.c2
-rw-r--r--fs/logfs/gc.c2
-rw-r--r--fs/logfs/inode.c4
-rw-r--r--fs/logfs/journal.c1
-rw-r--r--fs/logfs/logfs.h5
-rw-r--r--fs/logfs/readwrite.c89
-rw-r--r--fs/logfs/segment.c55
-rw-r--r--fs/logfs/super.c15
-rw-r--r--fs/minix/dir.c4
-rw-r--r--fs/minix/inode.c38
-rw-r--r--fs/minix/minix.h1
-rw-r--r--fs/minix/namei.c14
-rw-r--r--fs/mpage.c2
-rw-r--r--fs/namei.c222
-rw-r--r--fs/ncpfs/inode.c6
-rw-r--r--fs/nfs/Kconfig29
-rw-r--r--fs/nfs/blocklayout/blocklayout.c161
-rw-r--r--fs/nfs/blocklayout/blocklayout.h11
-rw-r--r--fs/nfs/blocklayout/blocklayoutdev.c46
-rw-r--r--fs/nfs/blocklayout/blocklayoutdm.c33
-rw-r--r--fs/nfs/blocklayout/extents.c2
-rw-r--r--fs/nfs/cache_lib.c61
-rw-r--r--fs/nfs/cache_lib.h10
-rw-r--r--fs/nfs/callback.c19
-rw-r--r--fs/nfs/callback.h3
-rw-r--r--fs/nfs/callback_proc.c99
-rw-r--r--fs/nfs/callback_xdr.c21
-rw-r--r--fs/nfs/client.c247
-rw-r--r--fs/nfs/delegation.c68
-rw-r--r--fs/nfs/delegation.h4
-rw-r--r--fs/nfs/dir.c35
-rw-r--r--fs/nfs/direct.c6
-rw-r--r--fs/nfs/dns_resolve.c130
-rw-r--r--fs/nfs/dns_resolve.h14
-rw-r--r--fs/nfs/file.c2
-rw-r--r--fs/nfs/fscache.c2
-rw-r--r--fs/nfs/getroot.c6
-rw-r--r--fs/nfs/idmap.c734
-rw-r--r--fs/nfs/inode.c119
-rw-r--r--fs/nfs/internal.h15
-rw-r--r--fs/nfs/mount_clnt.c16
-rw-r--r--fs/nfs/namespace.c5
-rw-r--r--fs/nfs/netns.h27
-rw-r--r--fs/nfs/nfs2xdr.c2
-rw-r--r--fs/nfs/nfs3acl.c2
-rw-r--r--fs/nfs/nfs3proc.c24
-rw-r--r--fs/nfs/nfs3xdr.c4
-rw-r--r--fs/nfs/nfs4_fs.h58
-rw-r--r--fs/nfs/nfs4filelayout.c272
-rw-r--r--fs/nfs/nfs4filelayout.h7
-rw-r--r--fs/nfs/nfs4filelayoutdev.c90
-rw-r--r--fs/nfs/nfs4namespace.c10
-rw-r--r--fs/nfs/nfs4proc.c691
-rw-r--r--fs/nfs/nfs4state.c353
-rw-r--r--fs/nfs/nfs4xdr.c702
-rw-r--r--fs/nfs/nfsroot.c2
-rw-r--r--fs/nfs/objlayout/objio_osd.c54
-rw-r--r--fs/nfs/objlayout/objlayout.c142
-rw-r--r--fs/nfs/objlayout/objlayout.h2
-rw-r--r--fs/nfs/pagelist.c92
-rw-r--r--fs/nfs/pnfs.c46
-rw-r--r--fs/nfs/pnfs.h98
-rw-r--r--fs/nfs/pnfs_dev.c4
-rw-r--r--fs/nfs/proc.c24
-rw-r--r--fs/nfs/read.c14
-rw-r--r--fs/nfs/super.c167
-rw-r--r--fs/nfs/sysctl.c2
-rw-r--r--fs/nfs/unlink.c45
-rw-r--r--fs/nfs/write.c213
-rw-r--r--fs/nfsd/fault_inject.c2
-rw-r--r--fs/nfsd/nfs4callback.c8
-rw-r--r--fs/nfsd/nfs4state.c2
-rw-r--r--fs/nfsd/nfsctl.c6
-rw-r--r--fs/nfsd/nfssvc.c4
-rw-r--r--fs/nfsd/stats.c5
-rw-r--r--fs/nfsd/vfs.c11
-rw-r--r--fs/nilfs2/cpfile.c94
-rw-r--r--fs/nilfs2/dat.c38
-rw-r--r--fs/nilfs2/dir.c4
-rw-r--r--fs/nilfs2/ifile.c4
-rw-r--r--fs/nilfs2/ioctl.c2
-rw-r--r--fs/nilfs2/mdt.c4
-rw-r--r--fs/nilfs2/namei.c11
-rw-r--r--fs/nilfs2/page.c8
-rw-r--r--fs/nilfs2/recovery.c4
-rw-r--r--fs/nilfs2/segbuf.c4
-rw-r--r--fs/nilfs2/sufile.c68
-rw-r--r--fs/nilfs2/super.c4
-rw-r--r--fs/nilfs2/the_nilfs.c7
-rw-r--r--fs/notify/notification.c3
-rw-r--r--fs/ntfs/aops.c20
-rw-r--r--fs/ntfs/attrib.c26
-rw-r--r--fs/ntfs/file.c16
-rw-r--r--fs/ntfs/layout.h4
-rw-r--r--fs/ntfs/mft.c6
-rw-r--r--fs/ntfs/super.c21
-rw-r--r--fs/ocfs2/aops.c16
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c14
-rw-r--r--fs/ocfs2/namei.c2
-rw-r--r--fs/ocfs2/super.c51
-rw-r--r--fs/omfs/inode.c6
-rw-r--r--fs/openpromfs/inode.c3
-rw-r--r--fs/pipe.c9
-rw-r--r--fs/posix_acl.c2
-rw-r--r--fs/proc/array.c119
-rw-r--r--fs/proc/base.c141
-rw-r--r--fs/proc/inode.c16
-rw-r--r--fs/proc/internal.h12
-rw-r--r--fs/proc/kcore.c8
-rw-r--r--fs/proc/namespaces.c2
-rw-r--r--fs/proc/page.c2
-rw-r--r--fs/proc/proc_sysctl.c1276
-rw-r--r--fs/proc/stat.c62
-rw-r--r--fs/proc/task_mmu.c360
-rw-r--r--fs/proc/task_nommu.c69
-rw-r--r--fs/proc/vmcore.c23
-rw-r--r--fs/pstore/inode.c25
-rw-r--r--fs/pstore/platform.c30
-rw-r--r--fs/qnx4/inode.c88
-rw-r--r--fs/qnx4/namei.c9
-rw-r--r--fs/qnx4/qnx4.h2
-rw-r--r--fs/qnx6/Kconfig26
-rw-r--r--fs/qnx6/Makefile7
-rw-r--r--fs/qnx6/README8
-rw-r--r--fs/qnx6/dir.c291
-rw-r--r--fs/qnx6/inode.c698
-rw-r--r--fs/qnx6/namei.c42
-rw-r--r--fs/qnx6/qnx6.h135
-rw-r--r--fs/qnx6/super_mmi.c150
-rw-r--r--fs/quota/dquot.c198
-rw-r--r--fs/quota/quota.c24
-rw-r--r--fs/ramfs/inode.c30
-rw-r--r--fs/read_write.c2
-rw-r--r--fs/readdir.c2
-rw-r--r--fs/reiserfs/acl.h76
-rw-r--r--fs/reiserfs/bitmap.c4
-rw-r--r--fs/reiserfs/dir.c2
-rw-r--r--fs/reiserfs/do_balan.c2
-rw-r--r--fs/reiserfs/file.c6
-rw-r--r--fs/reiserfs/fix_node.c2
-rw-r--r--fs/reiserfs/hashes.c2
-rw-r--r--fs/reiserfs/ibalance.c2
-rw-r--r--fs/reiserfs/inode.c6
-rw-r--r--fs/reiserfs/ioctl.c2
-rw-r--r--fs/reiserfs/item_ops.c2
-rw-r--r--fs/reiserfs/journal.c2
-rw-r--r--fs/reiserfs/lbalance.c4
-rw-r--r--fs/reiserfs/lock.c2
-rw-r--r--fs/reiserfs/namei.c6
-rw-r--r--fs/reiserfs/objectid.c3
-rw-r--r--fs/reiserfs/prints.c4
-rw-r--r--fs/reiserfs/procfs.c3
-rw-r--r--fs/reiserfs/reiserfs.h2923
-rw-r--r--fs/reiserfs/resize.c3
-rw-r--r--fs/reiserfs/stree.c6
-rw-r--r--fs/reiserfs/super.c12
-rw-r--r--fs/reiserfs/tail_conversion.c6
-rw-r--r--fs/reiserfs/xattr.c6
-rw-r--r--fs/reiserfs/xattr.h122
-rw-r--r--fs/reiserfs/xattr_acl.c6
-rw-r--r--fs/reiserfs/xattr_security.c4
-rw-r--r--fs/reiserfs/xattr_trusted.c4
-rw-r--r--fs/reiserfs/xattr_user.c4
-rw-r--r--fs/romfs/super.c6
-rw-r--r--fs/select.c44
-rw-r--r--fs/seq_file.c114
-rw-r--r--fs/signalfd.c15
-rw-r--r--fs/splice.c9
-rw-r--r--fs/squashfs/file.c8
-rw-r--r--fs/squashfs/super.c3
-rw-r--r--fs/squashfs/symlink.c4
-rw-r--r--fs/stack.c2
-rw-r--r--fs/stat.c4
-rw-r--r--fs/statfs.c2
-rw-r--r--fs/super.c27
-rw-r--r--fs/sync.c2
-rw-r--r--fs/sysfs/dir.c224
-rw-r--r--fs/sysfs/file.c6
-rw-r--r--fs/sysfs/inode.c16
-rw-r--r--fs/sysfs/mount.c5
-rw-r--r--fs/sysfs/sysfs.h17
-rw-r--r--fs/sysv/namei.c12
-rw-r--r--fs/sysv/super.c27
-rw-r--r--fs/sysv/sysv.h1
-rw-r--r--fs/ubifs/debug.c410
-rw-r--r--fs/ubifs/debug.h3
-rw-r--r--fs/ubifs/dir.c18
-rw-r--r--fs/ubifs/file.c4
-rw-r--r--fs/ubifs/recovery.c3
-rw-r--r--fs/ubifs/sb.c19
-rw-r--r--fs/ubifs/super.c6
-rw-r--r--fs/ubifs/ubifs.h11
-rw-r--r--fs/udf/balloc.c84
-rw-r--r--fs/udf/file.c6
-rw-r--r--fs/udf/ialloc.c1
-rw-r--r--fs/udf/inode.c20
-rw-r--r--fs/udf/namei.c13
-rw-r--r--fs/udf/super.c11
-rw-r--r--fs/udf/udf_i.h1
-rw-r--r--fs/ufs/namei.c14
-rw-r--r--fs/ufs/super.c7
-rw-r--r--fs/xattr.c2
-rw-r--r--fs/xattr_acl.c2
-rw-r--r--fs/xfs/xfs_rename.c11
-rw-r--r--fs/xfs/xfs_super.c7
-rw-r--r--fs/xfs/xfs_utils.c2
-rw-r--r--fs/xfs/xfs_vnodeops.c16
431 files changed, 15816 insertions, 7391 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 1964f98..b85efa7 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -594,21 +594,21 @@ static int __init init_v9fs(void)
int err;
pr_info("Installing v9fs 9p2000 file system support\n");
/* TODO: Setup list of registered trasnport modules */
- err = register_filesystem(&v9fs_fs_type);
- if (err < 0) {
- pr_err("Failed to register filesystem\n");
- return err;
- }
err = v9fs_cache_register();
if (err < 0) {
pr_err("Failed to register v9fs for caching\n");
- goto out_fs_unreg;
+ return err;
}
err = v9fs_sysfs_init();
if (err < 0) {
pr_err("Failed to register with sysfs\n");
+ goto out_cache;
+ }
+ err = register_filesystem(&v9fs_fs_type);
+ if (err < 0) {
+ pr_err("Failed to register filesystem\n");
goto out_sysfs_cleanup;
}
@@ -617,8 +617,8 @@ static int __init init_v9fs(void)
out_sysfs_cleanup:
v9fs_sysfs_cleanup();
-out_fs_unreg:
- unregister_filesystem(&v9fs_fs_type);
+out_cache:
+ v9fs_cache_unregister();
return err;
}
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 7b0cd87..8c92a9b 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -155,9 +155,8 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
goto release_sb;
}
- root = d_alloc_root(inode);
+ root = d_make_root(inode);
if (!root) {
- iput(inode);
retval = -ENOMEM;
goto release_sb;
}
@@ -260,7 +259,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
if (v9fs_proto_dotl(v9ses)) {
res = p9_client_statfs(fid, &rs);
if (res == 0) {
- buf->f_type = V9FS_MAGIC;
+ buf->f_type = rs.type;
buf->f_bsize = rs.bsize;
buf->f_blocks = rs.blocks;
buf->f_bfree = rs.bfree;
diff --git a/fs/Kconfig b/fs/Kconfig
index d621f02..f95ae3a 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -4,6 +4,10 @@
menu "File systems"
+# Use unaligned word dcache accesses
+config DCACHE_WORD_ACCESS
+ bool
+
if BLOCK
source "fs/ext2/Kconfig"
@@ -210,6 +214,7 @@ source "fs/minix/Kconfig"
source "fs/omfs/Kconfig"
source "fs/hpfs/Kconfig"
source "fs/qnx4/Kconfig"
+source "fs/qnx6/Kconfig"
source "fs/romfs/Kconfig"
source "fs/pstore/Kconfig"
source "fs/sysv/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index 93804d4..2fb9779 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -102,6 +102,7 @@ obj-$(CONFIG_UBIFS_FS) += ubifs/
obj-$(CONFIG_AFFS_FS) += affs/
obj-$(CONFIG_ROMFS_FS) += romfs/
obj-$(CONFIG_QNX4FS_FS) += qnx4/
+obj-$(CONFIG_QNX6FS_FS) += qnx6/
obj-$(CONFIG_AUTOFS4_FS) += autofs4/
obj-$(CONFIG_ADFS_FS) += adfs/
obj-$(CONFIG_FUSE_FS) += fuse/
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 8e3b36a..06fdcc9 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -483,10 +483,9 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_d_op = &adfs_dentry_operations;
root = adfs_iget(sb, &root_obj);
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
int i;
- iput(root);
for (i = 0; i < asb->s_map_size; i++)
brelse(asb->s_map[i].dm_bh);
kfree(asb->s_map);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 8ba73fe..0782653 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -473,7 +473,7 @@ got_root:
root_inode = affs_iget(sb, root_block);
if (IS_ERR(root_inode)) {
ret = PTR_ERR(root_inode);
- goto out_error_noinode;
+ goto out_error;
}
if (AFFS_SB(sb)->s_flags & SF_INTL)
@@ -481,7 +481,7 @@ got_root:
else
sb->s_d_op = &affs_dentry_operations;
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (!sb->s_root) {
printk(KERN_ERR "AFFS: Get root inode failed\n");
goto out_error;
@@ -494,9 +494,6 @@ got_root:
* Begin the cascaded cleanup ...
*/
out_error:
- if (root_inode)
- iput(root_inode);
-out_error_noinode:
kfree(sbi->s_bitmap);
affs_brelse(root_bh);
kfree(sbi->s_prefix);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 14d89fa..8f6e923 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -251,7 +251,7 @@ static int afs_readpages(struct file *file, struct address_space *mapping,
ASSERT(key != NULL);
vnode = AFS_FS_I(mapping->host);
- if (vnode->flags & AFS_VNODE_DELETED) {
+ if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
_leave(" = -ESTALE");
return -ESTALE;
}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 2f213d1..b960ff0 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -365,10 +365,10 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
_debug("extract data");
if (call->count > 0) {
page = call->reply3;
- buffer = kmap_atomic(page, KM_USER0);
+ buffer = kmap_atomic(page);
ret = afs_extract_data(call, skb, last, buffer,
call->count);
- kunmap_atomic(buffer, KM_USER0);
+ kunmap_atomic(buffer);
switch (ret) {
case 0: break;
case -EAGAIN: return 0;
@@ -411,9 +411,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
if (call->count < PAGE_SIZE) {
_debug("clear");
page = call->reply3;
- buffer = kmap_atomic(page, KM_USER0);
+ buffer = kmap_atomic(page);
memset(buffer + call->count, 0, PAGE_SIZE - call->count);
- kunmap_atomic(buffer, KM_USER0);
+ kunmap_atomic(buffer);
}
_leave(" = 0 [done]");
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index d2b0888..a306bb6 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -109,7 +109,7 @@ struct afs_call {
unsigned reply_size; /* current size of reply */
unsigned first_offset; /* offset into mapping[first] */
unsigned last_to; /* amount of mapping[last] */
- unsigned short offset; /* offset into received data store */
+ unsigned offset; /* offset into received data store */
unsigned char unmarshall; /* unmarshalling phase */
bool incoming; /* T if incoming call */
bool send_pages; /* T if data from mapping should be sent */
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 8f4ce26..298cf89 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -200,9 +200,9 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
if (PageError(page))
goto error;
- buf = kmap_atomic(page, KM_USER0);
+ buf = kmap_atomic(page);
memcpy(devname, buf, size);
- kunmap_atomic(buf, KM_USER0);
+ kunmap_atomic(buf);
page_cache_release(page);
page = NULL;
}
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index e45a323..8ad8c2a 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -314,6 +314,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
struct msghdr msg;
struct kvec iov[1];
int ret;
+ struct sk_buff *skb;
_enter("%x,{%d},", addr->s_addr, ntohs(call->port));
@@ -380,6 +381,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
error_do_abort:
rxrpc_kernel_abort_call(rxcall, RX_USER_ABORT);
+ while ((skb = skb_dequeue(&call->rx_queue)))
+ afs_free_skb(skb);
rxrpc_kernel_end_call(rxcall);
call->rxcall = NULL;
error_kill_call:
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 983ec59..f02b31e 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -301,7 +301,6 @@ static int afs_fill_super(struct super_block *sb,
{
struct afs_super_info *as = sb->s_fs_info;
struct afs_fid fid;
- struct dentry *root = NULL;
struct inode *inode = NULL;
int ret;
@@ -327,18 +326,16 @@ static int afs_fill_super(struct super_block *sb,
set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);
ret = -ENOMEM;
- root = d_alloc_root(inode);
- if (!root)
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root)
goto error;
sb->s_d_op = &afs_fs_dentry_operations;
- sb->s_root = root;
_leave(" = 0");
return 0;
error:
- iput(inode);
_leave(" = %d", ret);
return ret;
}
diff --git a/fs/aio.c b/fs/aio.c
index 969beb0..4f71627 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -13,7 +13,7 @@
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/aio_abi.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/backing-dev.h>
#include <linux/uio.h>
@@ -160,7 +160,7 @@ static int aio_setup_ring(struct kioctx *ctx)
info->nr = nr_events; /* trusted copy */
- ring = kmap_atomic(info->ring_pages[0], KM_USER0);
+ ring = kmap_atomic(info->ring_pages[0]);
ring->nr = nr_events; /* user copy */
ring->id = ctx->user_id;
ring->head = ring->tail = 0;
@@ -168,47 +168,38 @@ static int aio_setup_ring(struct kioctx *ctx)
ring->compat_features = AIO_RING_COMPAT_FEATURES;
ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
ring->header_length = sizeof(struct aio_ring);
- kunmap_atomic(ring, KM_USER0);
+ kunmap_atomic(ring);
return 0;
}
/* aio_ring_event: returns a pointer to the event at the given index from
- * kmap_atomic(, km). Release the pointer with put_aio_ring_event();
+ * kmap_atomic(). Release the pointer with put_aio_ring_event();
*/
#define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event))
#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)
-#define aio_ring_event(info, nr, km) ({ \
+#define aio_ring_event(info, nr) ({ \
unsigned pos = (nr) + AIO_EVENTS_OFFSET; \
struct io_event *__event; \
__event = kmap_atomic( \
- (info)->ring_pages[pos / AIO_EVENTS_PER_PAGE], km); \
+ (info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
__event += pos % AIO_EVENTS_PER_PAGE; \
__event; \
})
-#define put_aio_ring_event(event, km) do { \
+#define put_aio_ring_event(event) do { \
struct io_event *__event = (event); \
(void)__event; \
- kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK), km); \
+ kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \
} while(0)
static void ctx_rcu_free(struct rcu_head *head)
{
struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
- unsigned nr_events = ctx->max_reqs;
-
kmem_cache_free(kioctx_cachep, ctx);
-
- if (nr_events) {
- spin_lock(&aio_nr_lock);
- BUG_ON(aio_nr - nr_events > aio_nr);
- aio_nr -= nr_events;
- spin_unlock(&aio_nr_lock);
- }
}
/* __put_ioctx
@@ -217,23 +208,23 @@ static void ctx_rcu_free(struct rcu_head *head)
*/
static void __put_ioctx(struct kioctx *ctx)
{
+ unsigned nr_events = ctx->max_reqs;
BUG_ON(ctx->reqs_active);
- cancel_delayed_work(&ctx->wq);
- cancel_work_sync(&ctx->wq.work);
+ cancel_delayed_work_sync(&ctx->wq);
aio_free_ring(ctx);
mmdrop(ctx->mm);
ctx->mm = NULL;
+ if (nr_events) {
+ spin_lock(&aio_nr_lock);
+ BUG_ON(aio_nr - nr_events > aio_nr);
+ aio_nr -= nr_events;
+ spin_unlock(&aio_nr_lock);
+ }
pr_debug("__put_ioctx: freeing %p\n", ctx);
call_rcu(&ctx->rcu_head, ctx_rcu_free);
}
-static inline void get_ioctx(struct kioctx *kioctx)
-{
- BUG_ON(atomic_read(&kioctx->users) <= 0);
- atomic_inc(&kioctx->users);
-}
-
static inline int try_get_ioctx(struct kioctx *kioctx)
{
return atomic_inc_not_zero(&kioctx->users);
@@ -253,7 +244,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
{
struct mm_struct *mm;
struct kioctx *ctx;
- int did_sync = 0;
+ int err = -ENOMEM;
/* Prevent overflows */
if ((nr_events > (0x10000000U / sizeof(struct io_event))) ||
@@ -262,7 +253,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
return ERR_PTR(-EINVAL);
}
- if ((unsigned long)nr_events > aio_max_nr)
+ if (!nr_events || (unsigned long)nr_events > aio_max_nr)
return ERR_PTR(-EAGAIN);
ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL);
@@ -273,7 +264,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
mm = ctx->mm = current->mm;
atomic_inc(&mm->mm_count);
- atomic_set(&ctx->users, 1);
+ atomic_set(&ctx->users, 2);
spin_lock_init(&ctx->ctx_lock);
spin_lock_init(&ctx->ring_info.ring_lock);
init_waitqueue_head(&ctx->wait);
@@ -286,25 +277,14 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
goto out_freectx;
/* limit the number of system wide aios */
- do {
- spin_lock_bh(&aio_nr_lock);
- if (aio_nr + nr_events > aio_max_nr ||
- aio_nr + nr_events < aio_nr)
- ctx->max_reqs = 0;
- else
- aio_nr += ctx->max_reqs;
- spin_unlock_bh(&aio_nr_lock);
- if (ctx->max_reqs || did_sync)
- break;
-
- /* wait for rcu callbacks to have completed before giving up */
- synchronize_rcu();
- did_sync = 1;
- ctx->max_reqs = nr_events;
- } while (1);
-
- if (ctx->max_reqs == 0)
+ spin_lock(&aio_nr_lock);
+ if (aio_nr + nr_events > aio_max_nr ||
+ aio_nr + nr_events < aio_nr) {
+ spin_unlock(&aio_nr_lock);
goto out_cleanup;
+ }
+ aio_nr += ctx->max_reqs;
+ spin_unlock(&aio_nr_lock);
/* now link into global list. */
spin_lock(&mm->ioctx_lock);
@@ -316,16 +296,13 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
return ctx;
out_cleanup:
- __put_ioctx(ctx);
- return ERR_PTR(-EAGAIN);
-
+ err = -EAGAIN;
+ aio_free_ring(ctx);
out_freectx:
mmdrop(mm);
kmem_cache_free(kioctx_cachep, ctx);
- ctx = ERR_PTR(-ENOMEM);
-
- dprintk("aio: error allocating ioctx %p\n", ctx);
- return ctx;
+ dprintk("aio: error allocating ioctx %d\n", err);
+ return ERR_PTR(err);
}
/* aio_cancel_all
@@ -413,10 +390,6 @@ void exit_aio(struct mm_struct *mm)
aio_cancel_all(ctx);
wait_for_all_aios(ctx);
- /*
- * Ensure we don't leave the ctx on the aio_wq
- */
- cancel_work_sync(&ctx->wq.work);
if (1 != atomic_read(&ctx->users))
printk(KERN_DEBUG
@@ -490,6 +463,8 @@ static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
kmem_cache_free(kiocb_cachep, req);
ctx->reqs_active--;
}
+ if (unlikely(!ctx->reqs_active && ctx->dead))
+ wake_up_all(&ctx->wait);
spin_unlock_irq(&ctx->ctx_lock);
}
@@ -607,11 +582,16 @@ static void aio_fput_routine(struct work_struct *data)
fput(req->ki_filp);
/* Link the iocb into the context's free list */
+ rcu_read_lock();
spin_lock_irq(&ctx->ctx_lock);
really_put_req(ctx, req);
+ /*
+ * at that point ctx might've been killed, but actual
+ * freeing is RCU'd
+ */
spin_unlock_irq(&ctx->ctx_lock);
+ rcu_read_unlock();
- put_ioctx(ctx);
spin_lock_irq(&fput_lock);
}
spin_unlock_irq(&fput_lock);
@@ -642,7 +622,6 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
* this function will be executed w/out any aio kthread wakeup.
*/
if (unlikely(!fput_atomic(req->ki_filp))) {
- get_ioctx(ctx);
spin_lock(&fput_lock);
list_add(&req->ki_list, &fput_head);
spin_unlock(&fput_lock);
@@ -920,7 +899,7 @@ static void aio_kick_handler(struct work_struct *work)
unuse_mm(mm);
set_fs(oldfs);
/*
- * we're in a worker thread already, don't use queue_delayed_work,
+ * we're in a worker thread already; no point using non-zero delay
*/
if (requeue)
queue_delayed_work(aio_wq, &ctx->wq, 0);
@@ -1019,10 +998,10 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
if (kiocbIsCancelled(iocb))
goto put_rq;
- ring = kmap_atomic(info->ring_pages[0], KM_IRQ1);
+ ring = kmap_atomic(info->ring_pages[0]);
tail = info->tail;
- event = aio_ring_event(info, tail, KM_IRQ0);
+ event = aio_ring_event(info, tail);
if (++tail >= info->nr)
tail = 0;
@@ -1043,8 +1022,8 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
info->tail = tail;
ring->tail = tail;
- put_aio_ring_event(event, KM_IRQ0);
- kunmap_atomic(ring, KM_IRQ1);
+ put_aio_ring_event(event);
+ kunmap_atomic(ring);
pr_debug("added to ring %p at [%lu]\n", iocb, tail);
@@ -1089,7 +1068,7 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
unsigned long head;
int ret = 0;
- ring = kmap_atomic(info->ring_pages[0], KM_USER0);
+ ring = kmap_atomic(info->ring_pages[0]);
dprintk("in aio_read_evt h%lu t%lu m%lu\n",
(unsigned long)ring->head, (unsigned long)ring->tail,
(unsigned long)ring->nr);
@@ -1101,18 +1080,18 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
head = ring->head % info->nr;
if (head != ring->tail) {
- struct io_event *evp = aio_ring_event(info, head, KM_USER1);
+ struct io_event *evp = aio_ring_event(info, head);
*ent = *evp;
head = (head + 1) % info->nr;
smp_mb(); /* finish reading the event before updatng the head */
ring->head = head;
ret = 1;
- put_aio_ring_event(evp, KM_USER1);
+ put_aio_ring_event(evp);
}
spin_unlock(&info->ring_lock);
out:
- kunmap_atomic(ring, KM_USER0);
+ kunmap_atomic(ring);
dprintk("leaving aio_read_evt: %d h%lu t%lu\n", ret,
(unsigned long)ring->head, (unsigned long)ring->tail);
return ret;
@@ -1336,10 +1315,10 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
ret = PTR_ERR(ioctx);
if (!IS_ERR(ioctx)) {
ret = put_user(ioctx->user_id, ctxp);
- if (!ret)
+ if (!ret) {
+ put_ioctx(ioctx);
return 0;
-
- get_ioctx(ioctx); /* io_destroy() expects us to hold a ref */
+ }
io_destroy(ioctx);
}
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index f11e43e..28d39fb 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -39,19 +39,6 @@ static const struct dentry_operations anon_inodefs_dentry_operations = {
.d_dname = anon_inodefs_dname,
};
-static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
-{
- return mount_pseudo(fs_type, "anon_inode:", NULL,
- &anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
-}
-
-static struct file_system_type anon_inode_fs_type = {
- .name = "anon_inodefs",
- .mount = anon_inodefs_mount,
- .kill_sb = kill_anon_super,
-};
-
/*
* nop .set_page_dirty method so that people can use .page_mkwrite on
* anon inodes.
@@ -65,6 +52,62 @@ static const struct address_space_operations anon_aops = {
.set_page_dirty = anon_set_page_dirty,
};
+/*
+ * A single inode exists for all anon_inode files. Contrary to pipes,
+ * anon_inode inodes have no associated per-instance data, so we need
+ * only allocate one of them.
+ */
+static struct inode *anon_inode_mkinode(struct super_block *s)
+{
+ struct inode *inode = new_inode_pseudo(s);
+
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+
+ inode->i_ino = get_next_ino();
+ inode->i_fop = &anon_inode_fops;
+
+ inode->i_mapping->a_ops = &anon_aops;
+
+ /*
+ * Mark the inode dirty from the very beginning,
+ * that way it will never be moved to the dirty
+ * list because mark_inode_dirty() will think
+ * that it already _is_ on the dirty list.
+ */
+ inode->i_state = I_DIRTY;
+ inode->i_mode = S_IRUSR | S_IWUSR;
+ inode->i_uid = current_fsuid();
+ inode->i_gid = current_fsgid();
+ inode->i_flags |= S_PRIVATE;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ return inode;
+}
+
+static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ struct dentry *root;
+ root = mount_pseudo(fs_type, "anon_inode:", NULL,
+ &anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
+ if (!IS_ERR(root)) {
+ struct super_block *s = root->d_sb;
+ anon_inode_inode = anon_inode_mkinode(s);
+ if (IS_ERR(anon_inode_inode)) {
+ dput(root);
+ deactivate_locked_super(s);
+ root = ERR_CAST(anon_inode_inode);
+ }
+ }
+ return root;
+}
+
+static struct file_system_type anon_inode_fs_type = {
+ .name = "anon_inodefs",
+ .mount = anon_inodefs_mount,
+ .kill_sb = kill_anon_super,
+};
+
/**
* anon_inode_getfile - creates a new file instance by hooking it up to an
* anonymous inode, and a dentry that describe the "class"
@@ -180,38 +223,6 @@ err_put_unused_fd:
}
EXPORT_SYMBOL_GPL(anon_inode_getfd);
-/*
- * A single inode exists for all anon_inode files. Contrary to pipes,
- * anon_inode inodes have no associated per-instance data, so we need
- * only allocate one of them.
- */
-static struct inode *anon_inode_mkinode(void)
-{
- struct inode *inode = new_inode_pseudo(anon_inode_mnt->mnt_sb);
-
- if (!inode)
- return ERR_PTR(-ENOMEM);
-
- inode->i_ino = get_next_ino();
- inode->i_fop = &anon_inode_fops;
-
- inode->i_mapping->a_ops = &anon_aops;
-
- /*
- * Mark the inode dirty from the very beginning,
- * that way it will never be moved to the dirty
- * list because mark_inode_dirty() will think
- * that it already _is_ on the dirty list.
- */
- inode->i_state = I_DIRTY;
- inode->i_mode = S_IRUSR | S_IWUSR;
- inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
- inode->i_flags |= S_PRIVATE;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- return inode;
-}
-
static int __init anon_inode_init(void)
{
int error;
@@ -224,16 +235,8 @@ static int __init anon_inode_init(void)
error = PTR_ERR(anon_inode_mnt);
goto err_unregister_filesystem;
}
- anon_inode_inode = anon_inode_mkinode();
- if (IS_ERR(anon_inode_inode)) {
- error = PTR_ERR(anon_inode_inode);
- goto err_mntput;
- }
-
return 0;
-err_mntput:
- kern_unmount(anon_inode_mnt);
err_unregister_filesystem:
unregister_filesystem(&anon_inode_fs_type);
err_exit:
diff --git a/fs/attr.c b/fs/attr.c
index 95053ad..73f69a6 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -5,7 +5,7 @@
* changes by Thomas Schoebel-Theuer
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/string.h>
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index d8d8e7b..eb1cc92 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -110,6 +110,7 @@ struct autofs_sb_info {
int sub_version;
int min_proto;
int max_proto;
+ int compat_daemon;
unsigned long exp_timeout;
unsigned int type;
int reghost_enabled;
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 76741d8..85f1fcd 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -385,6 +385,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
sbi->pipefd = pipefd;
sbi->pipe = pipe;
sbi->catatonic = 0;
+ sbi->compat_daemon = is_compat_task();
}
out:
mutex_unlock(&sbi->wq_mutex);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 450f529..1feb68e 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -124,6 +124,7 @@ start:
/* Negative dentry - try next */
if (!simple_positive(q)) {
spin_unlock(&p->d_lock);
+ lock_set_subclass(&q->d_lock.dep_map, 0, _RET_IP_);
p = q;
goto again;
}
@@ -186,6 +187,7 @@ again:
/* Negative dentry - try next */
if (!simple_positive(ret)) {
spin_unlock(&p->d_lock);
+ lock_set_subclass(&ret->d_lock.dep_map, 0, _RET_IP_);
p = ret;
goto again;
}
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index c038727..cddc74b 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -31,11 +31,11 @@ static int __init init_autofs4_fs(void)
{
int err;
+ autofs_dev_ioctl_init();
+
err = register_filesystem(&autofs_fs_type);
if (err)
- return err;
-
- autofs_dev_ioctl_init();
+ autofs_dev_ioctl_exit();
return err;
}
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index e16980b..d8dc002 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -19,6 +19,7 @@
#include <linux/parser.h>
#include <linux/bitops.h>
#include <linux/magic.h>
+#include <linux/compat.h>
#include "autofs_i.h"
#include <linux/module.h>
@@ -224,6 +225,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
set_autofs_type_indirect(&sbi->type);
sbi->min_proto = 0;
sbi->max_proto = 0;
+ sbi->compat_daemon = is_compat_task();
mutex_init(&sbi->wq_mutex);
mutex_init(&sbi->pipe_mutex);
spin_lock_init(&sbi->fs_lock);
@@ -245,12 +247,9 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
if (!ino)
goto fail_free;
root_inode = autofs4_get_inode(s, S_IFDIR | 0755);
- if (!root_inode)
- goto fail_ino;
-
- root = d_alloc_root(root_inode);
+ root = d_make_root(root_inode);
if (!root)
- goto fail_iput;
+ goto fail_ino;
pipe = NULL;
root->d_fsdata = ino;
@@ -315,9 +314,6 @@ fail_fput:
fail_dput:
dput(root);
goto fail_free;
-fail_iput:
- printk("autofs: get root dentry failed\n");
- iput(root_inode);
fail_ino:
kfree(ino);
fail_free:
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index da8876d..9c098db 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -91,7 +91,24 @@ static int autofs4_write(struct autofs_sb_info *sbi,
return (bytes > 0);
}
-
+
+/*
+ * The autofs_v5 packet was misdesigned.
+ *
+ * The packets are identical on x86-32 and x86-64, but have different
+ * alignment. Which means that 'sizeof()' will give different results.
+ * Fix it up for the case of running 32-bit user mode on a 64-bit kernel.
+ */
+static noinline size_t autofs_v5_packet_size(struct autofs_sb_info *sbi)
+{
+ size_t pktsz = sizeof(struct autofs_v5_packet);
+#if defined(CONFIG_X86_64) && defined(CONFIG_COMPAT)
+ if (sbi->compat_daemon > 0)
+ pktsz -= 4;
+#endif
+ return pktsz;
+}
+
static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
struct autofs_wait_queue *wq,
int type)
@@ -155,8 +172,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
{
struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet;
- pktsz = sizeof(*packet);
-
+ pktsz = autofs_v5_packet_size(sbi);
packet->wait_queue_token = wq->wait_queue_token;
packet->len = wq->name.len;
memcpy(packet->name, wq->name.name, wq->name.len);
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 22e9a78..37268c5 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -9,7 +9,7 @@
*/
#include <linux/fs.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/stat.h>
#include <linux/time.h>
#include <linux/namei.h>
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 6e6d536..e18da23 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -852,9 +852,8 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
ret = PTR_ERR(root);
goto unacquire_priv_sbp;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
- iput(root);
befs_error(sb, "get root inode failed");
goto unacquire_priv_sbp;
}
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index b0391bc..e23dc7c 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -367,9 +367,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
ret = PTR_ERR(inode);
goto out2;
}
- s->s_root = d_alloc_root(inode);
+ s->s_root = d_make_root(inode);
if (!s->s_root) {
- iput(inode);
ret = -ENOMEM;
goto out2;
}
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index a6395bd..4d5e6d2 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -259,8 +259,14 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
current->mm->free_area_cache = current->mm->mmap_base;
current->mm->cached_hole_size = 0;
+ retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
+ if (retval < 0) {
+ /* Someone check-me: is this error path enough? */
+ send_sig(SIGKILL, current, 0);
+ return retval;
+ }
+
install_exec_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
if (N_MAGIC(ex) == OMAGIC) {
unsigned long text_addr, map_size;
@@ -352,13 +358,6 @@ beyond_if:
return retval;
}
- retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
- if (retval < 0) {
- /* Someone check-me: is this error path enough? */
- send_sig(SIGKILL, current, 0);
- return retval;
- }
-
current->mm->start_stack =
(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);
#ifdef __alpha__
@@ -454,7 +453,8 @@ out:
static int __init init_aout_binfmt(void)
{
- return register_binfmt(&aout_format);
+ register_binfmt(&aout_format);
+ return 0;
}
static void __exit exit_aout_binfmt(void)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index bcb884e..504b6eee 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -712,7 +712,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
goto out_free_dentry;
/* OK, This is the point of no return */
- current->flags &= ~PF_FORKNOEXEC;
current->mm->def_flags = def_flags;
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
@@ -934,7 +933,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
install_exec_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
retval = create_elf_tables(bprm, &loc->elf_ex,
load_addr, interp_load_addr);
if (retval < 0) {
@@ -1095,6 +1093,29 @@ out:
*/
/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+ /* Any vsyscall mappings? */
+ if (vma == get_gate_vma(vma->vm_mm))
+ return true;
+ /*
+ * arch_vma_name() returns non-NULL for special architecture mappings,
+ * such as vDSO sections.
+ */
+ if (arch_vma_name(vma))
+ return true;
+
+ return false;
+}
+
+/*
* Decide what to dump of a segment, part, all or none.
*/
static unsigned long vma_dump_size(struct vm_area_struct *vma,
@@ -1102,10 +1123,13 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
{
#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
- /* The vma can be set up to tell us the answer directly. */
- if (vma->vm_flags & VM_ALWAYSDUMP)
+ /* always dump the vdso and vsyscall sections */
+ if (always_dump_vma(vma))
goto whole;
+ if (vma->vm_flags & VM_NODUMP)
+ return 0;
+
/* Hugetlb memory check */
if (vma->vm_flags & VM_HUGETLB) {
if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
@@ -1421,7 +1445,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
for (i = 1; i < view->n; ++i) {
const struct user_regset *regset = &view->regsets[i];
do_thread_regset_writeback(t->task, regset);
- if (regset->core_note_type &&
+ if (regset->core_note_type && regset->get &&
(!regset->active || regset->active(t->task, regset))) {
int ret;
size_t size = regset->n * regset->size;
@@ -2077,7 +2101,8 @@ out:
static int __init init_elf_binfmt(void)
{
- return register_binfmt(&elf_format);
+ register_binfmt(&elf_format);
+ return 0;
}
static void __exit exit_elf_binfmt(void)
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 30745f4..c64bf5e 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -91,7 +91,8 @@ static struct linux_binfmt elf_fdpic_format = {
static int __init init_elf_fdpic_binfmt(void)
{
- return register_binfmt(&elf_fdpic_format);
+ register_binfmt(&elf_fdpic_format);
+ return 0;
}
static void __exit exit_elf_fdpic_binfmt(void)
@@ -334,8 +335,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
current->mm->context.exec_fdpic_loadmap = 0;
current->mm->context.interp_fdpic_loadmap = 0;
- current->flags &= ~PF_FORKNOEXEC;
-
#ifdef CONFIG_MMU
elf_fdpic_arch_lay_out_mm(&exec_params,
&interp_params,
@@ -413,7 +412,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
#endif
install_exec_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
if (create_elf_fdpic_tables(bprm, current->mm,
&exec_params, &interp_params) < 0)
goto error_kill;
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index b8e8b0a..2790c7e 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -100,7 +100,8 @@ static struct linux_binfmt em86_format = {
static int __init init_em86_binfmt(void)
{
- return register_binfmt(&em86_format);
+ register_binfmt(&em86_format);
+ return 0;
}
static void __exit exit_em86_binfmt(void)
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 1bffbe0..5979027 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -15,7 +15,7 @@
* JAN/99 -- coded full program relocation (gerg@snapgear.com)
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
@@ -902,7 +902,6 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs)
libinfo.lib_list[j].start_data:UNLOADED_LIB;
install_exec_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
set_binfmt(&flat_format);
@@ -950,7 +949,8 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs)
static int __init init_flat_binfmt(void)
{
- return register_binfmt(&flat_format);
+ register_binfmt(&flat_format);
+ return 0;
}
/****************************************************************************/
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index a9198df..613aa06 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
+#include <linux/magic.h>
#include <linux/binfmts.h>
#include <linux/slab.h>
#include <linux/ctype.h>
@@ -699,7 +700,7 @@ static int bm_fill_super(struct super_block * sb, void * data, int silent)
[3] = {"register", &bm_register_operations, S_IWUSR},
/* last one */ {""}
};
- int err = simple_fill_super(sb, 0x42494e4d, bm_files);
+ int err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
if (!err)
sb->s_op = &s_ops;
return err;
@@ -726,11 +727,8 @@ static struct file_system_type bm_fs_type = {
static int __init init_misc_binfmt(void)
{
int err = register_filesystem(&bm_fs_type);
- if (!err) {
- err = insert_binfmt(&misc_format);
- if (err)
- unregister_filesystem(&bm_fs_type);
- }
+ if (!err)
+ insert_binfmt(&misc_format);
return err;
}
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 396a988..d3b8c1f 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -105,7 +105,8 @@ static struct linux_binfmt script_format = {
static int __init init_script_binfmt(void)
{
- return register_binfmt(&script_format);
+ register_binfmt(&script_format);
+ return 0;
}
static void __exit exit_script_binfmt(void)
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index cc8560f..e4fc746 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -225,7 +225,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
goto out_free;
/* OK, This is the point of no return */
- current->flags &= ~PF_FORKNOEXEC;
current->personality = PER_HPUX;
setup_new_exec(bprm);
@@ -289,7 +288,8 @@ static int load_som_library(struct file *f)
static int __init init_som_binfmt(void)
{
- return register_binfmt(&som_format);
+ register_binfmt(&som_format);
+ return 0;
}
static void __exit exit_som_binfmt(void)
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index c2183f3..e85c04b 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -357,7 +357,7 @@ static void bio_integrity_generate(struct bio *bio)
bix.sector_size = bi->sector_size;
bio_for_each_segment(bv, bio, i) {
- void *kaddr = kmap_atomic(bv->bv_page, KM_USER0);
+ void *kaddr = kmap_atomic(bv->bv_page);
bix.data_buf = kaddr + bv->bv_offset;
bix.data_size = bv->bv_len;
bix.prot_buf = prot_buf;
@@ -371,7 +371,7 @@ static void bio_integrity_generate(struct bio *bio)
total += sectors * bi->tuple_size;
BUG_ON(total > bio->bi_integrity->bip_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
}
@@ -498,7 +498,7 @@ static int bio_integrity_verify(struct bio *bio)
bix.sector_size = bi->sector_size;
bio_for_each_segment(bv, bio, i) {
- void *kaddr = kmap_atomic(bv->bv_page, KM_USER0);
+ void *kaddr = kmap_atomic(bv->bv_page);
bix.data_buf = kaddr + bv->bv_offset;
bix.data_size = bv->bv_len;
bix.prot_buf = prot_buf;
@@ -507,7 +507,7 @@ static int bio_integrity_verify(struct bio *bio)
ret = bi->verify_fn(&bix);
if (ret) {
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
return ret;
}
@@ -517,7 +517,7 @@ static int bio_integrity_verify(struct bio *bio)
total += sectors * bi->tuple_size;
BUG_ON(total > bio->bi_integrity->bip_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
return ret;
diff --git a/fs/bio.c b/fs/bio.c
index b1fe82c..e453924 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -22,7 +22,7 @@
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <scsi/sg.h> /* for struct sg_iovec */
@@ -505,13 +505,9 @@ EXPORT_SYMBOL(bio_clone);
int bio_get_nr_vecs(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
- int nr_pages;
-
- nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (nr_pages > queue_max_segments(q))
- nr_pages = queue_max_segments(q);
-
- return nr_pages;
+ return min_t(unsigned,
+ queue_max_segments(q),
+ queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
}
EXPORT_SYMBOL(bio_get_nr_vecs);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0e575d1..e08f6a20 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -16,6 +16,7 @@
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
+#include <linux/magic.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/pagevec.h>
@@ -109,7 +110,7 @@ void invalidate_bdev(struct block_device *bdev)
/* 99% of the time, we don't need to flush the cleancache on the bdev.
* But, for the strange corners, lets be cautious
*/
- cleancache_flush_inode(mapping);
+ cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);
@@ -506,7 +507,7 @@ static const struct super_operations bdev_sops = {
static struct dentry *bd_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, 0x62646576);
+ return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
}
static struct file_system_type bd_type = {
@@ -1183,8 +1184,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
* The latter is necessary to prevent ghost
* partitions on a removed medium.
*/
- if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
- rescan_partitions(disk, bdev);
+ if (bdev->bd_invalidated) {
+ if (!ret)
+ rescan_partitions(disk, bdev);
+ else if (ret == -ENOMEDIUM)
+ invalidate_partitions(disk, bdev);
+ }
if (ret)
goto out_clear;
} else {
@@ -1214,8 +1219,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
if (bdev->bd_disk->fops->open)
ret = bdev->bd_disk->fops->open(bdev, mode);
/* the same as first opener case, read comment there */
- if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
- rescan_partitions(bdev->bd_disk, bdev);
+ if (bdev->bd_invalidated) {
+ if (!ret)
+ rescan_partitions(bdev->bd_disk, bdev);
+ else if (ret == -ENOMEDIUM)
+ invalidate_partitions(bdev->bd_disk, bdev);
+ }
if (ret)
goto out_unlock_bdev;
}
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b9a8432..0436c12 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -297,7 +297,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
struct btrfs_delayed_extent_op *extent_op = head->extent_op;
struct rb_node *n = &head->node.rb_node;
int sgn;
- int ret;
+ int ret = 0;
if (extent_op && extent_op->update_key)
btrfs_disk_key_to_cpu(info_key, &extent_op->key);
@@ -392,7 +392,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info,
struct btrfs_key *info_key, int *info_level,
struct list_head *prefs)
{
- int ret;
+ int ret = 0;
int slot;
struct extent_buffer *leaf;
struct btrfs_key key;
@@ -583,7 +583,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
struct btrfs_path *path;
struct btrfs_key info_key = { 0 };
struct btrfs_delayed_ref_root *delayed_refs = NULL;
- struct btrfs_delayed_ref_head *head = NULL;
+ struct btrfs_delayed_ref_head *head;
int info_level = 0;
int ret;
struct list_head prefs_delayed;
@@ -607,6 +607,8 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
* at a specified point in time
*/
again:
+ head = NULL;
+
ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0);
if (ret < 0)
goto out;
@@ -635,8 +637,10 @@ again:
goto again;
}
ret = __add_delayed_refs(head, seq, &info_key, &prefs_delayed);
- if (ret)
+ if (ret) {
+ spin_unlock(&delayed_refs->lock);
goto out;
+ }
}
spin_unlock(&delayed_refs->lock);
@@ -892,6 +896,8 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
if (eb != eb_in)
free_extent_buffer(eb);
ret = inode_ref_info(parent, 0, fs_root, path, &found_key);
+ if (ret > 0)
+ ret = -ENOENT;
if (ret)
break;
next_inum = found_key.offset;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index ad0b3ba..c053e90 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -89,7 +89,6 @@
#include "disk-io.h"
#include "transaction.h"
#include "extent_io.h"
-#include "disk-io.h"
#include "volumes.h"
#include "print-tree.h"
#include "locking.h"
@@ -644,7 +643,7 @@ static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(
static int btrfsic_process_superblock(struct btrfsic_state *state,
struct btrfs_fs_devices *fs_devices)
{
- int ret;
+ int ret = 0;
struct btrfs_super_block *selected_super;
struct list_head *dev_head = &fs_devices->devices;
struct btrfs_device *device;
@@ -1662,7 +1661,7 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state,
block = btrfsic_block_hashtable_lookup(bdev, dev_bytenr,
&state->block_hashtable);
if (NULL != block) {
- u64 bytenr;
+ u64 bytenr = 0;
struct list_head *elem_ref_to;
struct list_head *tmp_ref_to;
@@ -2777,9 +2776,10 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh)
printk(KERN_INFO
"submit_bh(rw=0x%x, blocknr=%lu (bytenr %llu),"
" size=%lu, data=%p, bdev=%p)\n",
- rw, bh->b_blocknr,
- (unsigned long long)dev_bytenr, bh->b_size,
- bh->b_data, bh->b_bdev);
+ rw, (unsigned long)bh->b_blocknr,
+ (unsigned long long)dev_bytenr,
+ (unsigned long)bh->b_size, bh->b_data,
+ bh->b_bdev);
btrfsic_process_written_block(dev_state, dev_bytenr,
bh->b_data, bh->b_size, NULL,
NULL, bh, rw);
@@ -2844,7 +2844,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
printk(KERN_INFO
"submit_bio(rw=0x%x, bi_vcnt=%u,"
" bi_sector=%lu (bytenr %llu), bi_bdev=%p)\n",
- rw, bio->bi_vcnt, bio->bi_sector,
+ rw, bio->bi_vcnt, (unsigned long)bio->bi_sector,
(unsigned long long)dev_bytenr,
bio->bi_bdev);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 14f1c5a..b805afb 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -120,10 +120,10 @@ static int check_compressed_csum(struct inode *inode,
page = cb->compressed_pages[i];
csum = ~(u32)0;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
csum = btrfs_csum_data(root, kaddr, csum, PAGE_CACHE_SIZE);
btrfs_csum_final(csum, (char *)&csum);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (csum != *cb_sum) {
printk(KERN_INFO "btrfs csum failed ino %llu "
@@ -521,10 +521,10 @@ static noinline int add_ra_bio_pages(struct inode *inode,
if (zero_offset) {
int zeros;
zeros = PAGE_CACHE_SIZE - zero_offset;
- userpage = kmap_atomic(page, KM_USER0);
+ userpage = kmap_atomic(page);
memset(userpage + zero_offset, 0, zeros);
flush_dcache_page(page);
- kunmap_atomic(userpage, KM_USER0);
+ kunmap_atomic(userpage);
}
}
@@ -588,6 +588,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
page_offset(bio->bi_io_vec->bv_page),
PAGE_CACHE_SIZE);
read_unlock(&em_tree->lock);
+ if (!em)
+ return -EIO;
compressed_len = em->block_len;
cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS);
@@ -991,9 +993,9 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
bytes = min(PAGE_CACHE_SIZE - *pg_offset,
PAGE_CACHE_SIZE - buf_offset);
bytes = min(bytes, working_bytes);
- kaddr = kmap_atomic(page_out, KM_USER0);
+ kaddr = kmap_atomic(page_out);
memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
flush_dcache_page(page_out);
*pg_offset += bytes;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 27ebe61..80b6486 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -886,7 +886,7 @@ struct btrfs_block_rsv {
u64 reserved;
struct btrfs_space_info *space_info;
spinlock_t lock;
- unsigned int full:1;
+ unsigned int full;
};
/*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7aa9cd3..534266f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -962,6 +962,13 @@ static int btree_releasepage(struct page *page, gfp_t gfp_flags)
tree = &BTRFS_I(page->mapping->host)->io_tree;
map = &BTRFS_I(page->mapping->host)->extent_tree;
+ /*
+ * We need to mask out eg. __GFP_HIGHMEM and __GFP_DMA32 as we're doing
+ * slab allocation from alloc_extent_state down the callchain where
+ * it'd hit a BUG_ON as those flags are not allowed.
+ */
+ gfp_flags &= ~GFP_SLAB_BUG_MASK;
+
ret = try_release_extent_state(map, tree, page, gfp_flags);
if (!ret)
return 0;
@@ -2253,6 +2260,12 @@ int open_ctree(struct super_block *sb,
goto fail_sb_buffer;
}
+ if (sectorsize < PAGE_SIZE) {
+ printk(KERN_WARNING "btrfs: Incompatible sector size "
+ "found on %s\n", sb->s_id);
+ goto fail_sb_buffer;
+ }
+
mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
@@ -2294,6 +2307,12 @@ int open_ctree(struct super_block *sb,
btrfs_close_extra_devices(fs_devices);
+ if (!fs_devices->latest_bdev) {
+ printk(KERN_CRIT "btrfs: failed to read devices on %s\n",
+ sb->s_id);
+ goto fail_tree_roots;
+ }
+
retry_root_backup:
blocksize = btrfs_level_size(tree_root,
btrfs_super_root_level(disk_super));
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 700879e..37e0a80 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -34,23 +34,24 @@
#include "locking.h"
#include "free-space-cache.h"
-/* control flags for do_chunk_alloc's force field
+/*
+ * control flags for do_chunk_alloc's force field
* CHUNK_ALLOC_NO_FORCE means to only allocate a chunk
* if we really need one.
*
- * CHUNK_ALLOC_FORCE means it must try to allocate one
- *
* CHUNK_ALLOC_LIMITED means to only try and allocate one
* if we have very few chunks already allocated. This is
* used as part of the clustering code to help make sure
* we have a good pool of storage to cluster in, without
* filling the FS with empty chunks
*
+ * CHUNK_ALLOC_FORCE means it must try to allocate one
+ *
*/
enum {
CHUNK_ALLOC_NO_FORCE = 0,
- CHUNK_ALLOC_FORCE = 1,
- CHUNK_ALLOC_LIMITED = 2,
+ CHUNK_ALLOC_LIMITED = 1,
+ CHUNK_ALLOC_FORCE = 2,
};
/*
@@ -3311,7 +3312,8 @@ commit_trans:
}
data_sinfo->bytes_may_use += bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
- (u64)data_sinfo, bytes, 1);
+ (u64)(unsigned long)data_sinfo,
+ bytes, 1);
spin_unlock(&data_sinfo->lock);
return 0;
@@ -3332,7 +3334,8 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
spin_lock(&data_sinfo->lock);
data_sinfo->bytes_may_use -= bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
- (u64)data_sinfo, bytes, 0);
+ (u64)(unsigned long)data_sinfo,
+ bytes, 0);
spin_unlock(&data_sinfo->lock);
}
@@ -3414,7 +3417,7 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
again:
spin_lock(&space_info->lock);
- if (space_info->force_alloc)
+ if (force < space_info->force_alloc)
force = space_info->force_alloc;
if (space_info->full) {
spin_unlock(&space_info->lock);
@@ -3610,12 +3613,15 @@ static int may_commit_transaction(struct btrfs_root *root,
if (space_info != delayed_rsv->space_info)
return -ENOSPC;
+ spin_lock(&space_info->lock);
spin_lock(&delayed_rsv->lock);
- if (delayed_rsv->size < bytes) {
+ if (space_info->bytes_pinned + delayed_rsv->size < bytes) {
spin_unlock(&delayed_rsv->lock);
+ spin_unlock(&space_info->lock);
return -ENOSPC;
}
spin_unlock(&delayed_rsv->lock);
+ spin_unlock(&space_info->lock);
commit:
trans = btrfs_join_transaction(root);
@@ -3694,9 +3700,9 @@ again:
if (used + orig_bytes <= space_info->total_bytes) {
space_info->bytes_may_use += orig_bytes;
trace_btrfs_space_reservation(root->fs_info,
- "space_info",
- (u64)space_info,
- orig_bytes, 1);
+ "space_info",
+ (u64)(unsigned long)space_info,
+ orig_bytes, 1);
ret = 0;
} else {
/*
@@ -3765,9 +3771,9 @@ again:
if (used + num_bytes < space_info->total_bytes + avail) {
space_info->bytes_may_use += orig_bytes;
trace_btrfs_space_reservation(root->fs_info,
- "space_info",
- (u64)space_info,
- orig_bytes, 1);
+ "space_info",
+ (u64)(unsigned long)space_info,
+ orig_bytes, 1);
ret = 0;
} else {
wait_ordered = true;
@@ -3912,8 +3918,8 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
spin_lock(&space_info->lock);
space_info->bytes_may_use -= num_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
- (u64)space_info,
- num_bytes, 0);
+ (u64)(unsigned long)space_info,
+ num_bytes, 0);
space_info->reservation_progress++;
spin_unlock(&space_info->lock);
}
@@ -4104,7 +4110,7 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
num_bytes += div64_u64(data_used + meta_used, 50);
if (num_bytes * 3 > meta_used)
- num_bytes = div64_u64(meta_used, 3);
+ num_bytes = div64_u64(meta_used, 3) * 2;
return ALIGN(num_bytes, fs_info->extent_root->leafsize << 10);
}
@@ -4131,14 +4137,14 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
block_rsv->reserved += num_bytes;
sinfo->bytes_may_use += num_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
- (u64)sinfo, num_bytes, 1);
+ (u64)(unsigned long)sinfo, num_bytes, 1);
}
if (block_rsv->reserved >= block_rsv->size) {
num_bytes = block_rsv->reserved - block_rsv->size;
sinfo->bytes_may_use -= num_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
- (u64)sinfo, num_bytes, 0);
+ (u64)(unsigned long)sinfo, num_bytes, 0);
sinfo->reservation_progress++;
block_rsv->reserved = block_rsv->size;
block_rsv->full = 1;
@@ -4191,7 +4197,8 @@ void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
if (!trans->bytes_reserved)
return;
- trace_btrfs_space_reservation(root->fs_info, "transaction", (u64)trans,
+ trace_btrfs_space_reservation(root->fs_info, "transaction",
+ (u64)(unsigned long)trans,
trans->bytes_reserved, 0);
btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
trans->bytes_reserved = 0;
@@ -4709,9 +4716,9 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
space_info->bytes_reserved += num_bytes;
if (reserve == RESERVE_ALLOC) {
trace_btrfs_space_reservation(cache->fs_info,
- "space_info",
- (u64)space_info,
- num_bytes, 0);
+ "space_info",
+ (u64)(unsigned long)space_info,
+ num_bytes, 0);
space_info->bytes_may_use -= num_bytes;
}
}
@@ -5794,6 +5801,7 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
u64 search_end, struct btrfs_key *ins,
u64 data)
{
+ bool final_tried = false;
int ret;
u64 search_start = 0;
@@ -5813,22 +5821,25 @@ again:
search_start, search_end, hint_byte,
ins, data);
- if (ret == -ENOSPC && num_bytes > min_alloc_size) {
- num_bytes = num_bytes >> 1;
- num_bytes = num_bytes & ~(root->sectorsize - 1);
- num_bytes = max(num_bytes, min_alloc_size);
- do_chunk_alloc(trans, root->fs_info->extent_root,
- num_bytes, data, CHUNK_ALLOC_FORCE);
- goto again;
- }
- if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) {
- struct btrfs_space_info *sinfo;
-
- sinfo = __find_space_info(root->fs_info, data);
- printk(KERN_ERR "btrfs allocation failed flags %llu, "
- "wanted %llu\n", (unsigned long long)data,
- (unsigned long long)num_bytes);
- dump_space_info(sinfo, num_bytes, 1);
+ if (ret == -ENOSPC) {
+ if (!final_tried) {
+ num_bytes = num_bytes >> 1;
+ num_bytes = num_bytes & ~(root->sectorsize - 1);
+ num_bytes = max(num_bytes, min_alloc_size);
+ do_chunk_alloc(trans, root->fs_info->extent_root,
+ num_bytes, data, CHUNK_ALLOC_FORCE);
+ if (num_bytes == min_alloc_size)
+ final_tried = true;
+ goto again;
+ } else if (btrfs_test_opt(root, ENOSPC_DEBUG)) {
+ struct btrfs_space_info *sinfo;
+
+ sinfo = __find_space_info(root->fs_info, data);
+ printk(KERN_ERR "btrfs allocation failed flags %llu, "
+ "wanted %llu\n", (unsigned long long)data,
+ (unsigned long long)num_bytes);
+ dump_space_info(sinfo, num_bytes, 1);
+ }
}
trace_btrfs_reserved_extent_alloc(root, ins->objectid, ins->offset);
@@ -7881,9 +7892,16 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
u64 start;
u64 end;
u64 trimmed = 0;
+ u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
int ret = 0;
- cache = btrfs_lookup_block_group(fs_info, range->start);
+ /*
+ * try to trim all FS space, our block group may start from non-zero.
+ */
+ if (range->len == total_bytes)
+ cache = btrfs_lookup_first_block_group(fs_info, range->start);
+ else
+ cache = btrfs_lookup_block_group(fs_info, range->start);
while (cache) {
if (cache->key.objectid >= (range->start + range->len)) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9d09a4f..2862454 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -513,6 +513,15 @@ hit_next:
WARN_ON(state->end < start);
last_end = state->end;
+ if (state->end < end && !need_resched())
+ next_node = rb_next(&state->rb_node);
+ else
+ next_node = NULL;
+
+ /* the state doesn't have the wanted bits, go ahead */
+ if (!(state->state & bits))
+ goto next;
+
/*
* | ---- desired range ---- |
* | state | or
@@ -565,20 +574,15 @@ hit_next:
goto out;
}
- if (state->end < end && prealloc && !need_resched())
- next_node = rb_next(&state->rb_node);
- else
- next_node = NULL;
-
set |= clear_state_bit(tree, state, &bits, wake);
+next:
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
if (start <= end && next_node) {
state = rb_entry(next_node, struct extent_state,
rb_node);
- if (state->start == start)
- goto hit_next;
+ goto hit_next;
}
goto search_again;
@@ -961,8 +965,6 @@ hit_next:
set_state_bits(tree, state, &bits);
clear_state_bit(tree, state, &clear_bits, 0);
-
- merge_state(tree, state);
if (last_end == (u64)-1)
goto out;
@@ -1007,7 +1009,6 @@ hit_next:
if (state->end <= end) {
set_state_bits(tree, state, &bits);
clear_state_bit(tree, state, &clear_bits, 0);
- merge_state(tree, state);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
@@ -1068,8 +1069,6 @@ hit_next:
set_state_bits(tree, prealloc, &bits);
clear_state_bit(tree, prealloc, &clear_bits, 0);
-
- merge_state(tree, prealloc);
prealloc = NULL;
goto out;
}
@@ -2154,13 +2153,46 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page,
"this_mirror=%d, num_copies=%d, in_validation=%d\n", read_mode,
failrec->this_mirror, num_copies, failrec->in_validation);
- tree->ops->submit_bio_hook(inode, read_mode, bio, failrec->this_mirror,
- failrec->bio_flags, 0);
- return 0;
+ ret = tree->ops->submit_bio_hook(inode, read_mode, bio,
+ failrec->this_mirror,
+ failrec->bio_flags, 0);
+ return ret;
}
/* lots and lots of room for performance fixes in the end_bio funcs */
+int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
+{
+ int uptodate = (err == 0);
+ struct extent_io_tree *tree;
+ int ret;
+
+ tree = &BTRFS_I(page->mapping->host)->io_tree;
+
+ if (tree->ops && tree->ops->writepage_end_io_hook) {
+ ret = tree->ops->writepage_end_io_hook(page, start,
+ end, NULL, uptodate);
+ if (ret)
+ uptodate = 0;
+ }
+
+ if (!uptodate && tree->ops &&
+ tree->ops->writepage_io_failed_hook) {
+ ret = tree->ops->writepage_io_failed_hook(NULL, page,
+ start, end, NULL);
+ /* Writeback already completed */
+ if (ret == 0)
+ return 1;
+ }
+
+ if (!uptodate) {
+ clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS);
+ ClearPageUptodate(page);
+ SetPageError(page);
+ }
+ return 0;
+}
+
/*
* after a writepage IO is done, we need to:
* clear the uptodate bits on error
@@ -2172,13 +2204,11 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page,
*/
static void end_bio_extent_writepage(struct bio *bio, int err)
{
- int uptodate = err == 0;
struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
struct extent_io_tree *tree;
u64 start;
u64 end;
int whole_page;
- int ret;
do {
struct page *page = bvec->bv_page;
@@ -2195,28 +2225,9 @@ static void end_bio_extent_writepage(struct bio *bio, int err)
if (--bvec >= bio->bi_io_vec)
prefetchw(&bvec->bv_page->flags);
- if (tree->ops && tree->ops->writepage_end_io_hook) {
- ret = tree->ops->writepage_end_io_hook(page, start,
- end, NULL, uptodate);
- if (ret)
- uptodate = 0;
- }
-
- if (!uptodate && tree->ops &&
- tree->ops->writepage_io_failed_hook) {
- ret = tree->ops->writepage_io_failed_hook(bio, page,
- start, end, NULL);
- if (ret == 0) {
- uptodate = (err == 0);
- continue;
- }
- }
- if (!uptodate) {
- clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS);
- ClearPageUptodate(page);
- SetPageError(page);
- }
+ if (end_extent_writepage(page, err, start, end))
+ continue;
if (whole_page)
end_page_writeback(page);
@@ -2535,10 +2546,10 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
if (zero_offset) {
iosize = PAGE_CACHE_SIZE - zero_offset;
- userpage = kmap_atomic(page, KM_USER0);
+ userpage = kmap_atomic(page);
memset(userpage + zero_offset, 0, iosize);
flush_dcache_page(page);
- kunmap_atomic(userpage, KM_USER0);
+ kunmap_atomic(userpage);
}
}
while (cur <= end) {
@@ -2547,10 +2558,10 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
struct extent_state *cached = NULL;
iosize = PAGE_CACHE_SIZE - pg_offset;
- userpage = kmap_atomic(page, KM_USER0);
+ userpage = kmap_atomic(page);
memset(userpage + pg_offset, 0, iosize);
flush_dcache_page(page);
- kunmap_atomic(userpage, KM_USER0);
+ kunmap_atomic(userpage);
set_extent_uptodate(tree, cur, cur + iosize - 1,
&cached, GFP_NOFS);
unlock_extent_cached(tree, cur, cur + iosize - 1,
@@ -2596,10 +2607,10 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
char *userpage;
struct extent_state *cached = NULL;
- userpage = kmap_atomic(page, KM_USER0);
+ userpage = kmap_atomic(page);
memset(userpage + pg_offset, 0, iosize);
flush_dcache_page(page);
- kunmap_atomic(userpage, KM_USER0);
+ kunmap_atomic(userpage);
set_extent_uptodate(tree, cur, cur + iosize - 1,
&cached, GFP_NOFS);
@@ -2745,10 +2756,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
if (page->index == end_index) {
char *userpage;
- userpage = kmap_atomic(page, KM_USER0);
+ userpage = kmap_atomic(page);
memset(userpage + pg_offset, 0,
PAGE_CACHE_SIZE - pg_offset);
- kunmap_atomic(userpage, KM_USER0);
+ kunmap_atomic(userpage);
flush_dcache_page(page);
}
pg_offset = 0;
@@ -2779,9 +2790,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
delalloc_start = delalloc_end + 1;
continue;
}
- tree->ops->fill_delalloc(inode, page, delalloc_start,
- delalloc_end, &page_started,
- &nr_written);
+ ret = tree->ops->fill_delalloc(inode, page,
+ delalloc_start,
+ delalloc_end,
+ &page_started,
+ &nr_written);
+ BUG_ON(ret);
/*
* delalloc_end is already one less than the total
* length, so we don't subtract one from
@@ -2818,8 +2832,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
if (tree->ops && tree->ops->writepage_start_hook) {
ret = tree->ops->writepage_start_hook(page, start,
page_end);
- if (ret == -EAGAIN) {
- redirty_page_for_writepage(wbc, page);
+ if (ret) {
+ /* Fixup worker will requeue */
+ if (ret == -EBUSY)
+ wbc->pages_skipped++;
+ else
+ redirty_page_for_writepage(wbc, page);
update_nr_written(page, wbc, nr_written);
unlock_page(page);
ret = 0;
@@ -3289,7 +3307,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
len = end - start + 1;
write_lock(&map->lock);
em = lookup_extent_mapping(map, start, len);
- if (IS_ERR_OR_NULL(em)) {
+ if (!em) {
write_unlock(&map->lock);
break;
}
@@ -3853,10 +3871,9 @@ int clear_extent_buffer_uptodate(struct extent_io_tree *tree,
num_pages = num_extent_pages(eb->start, eb->len);
clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
- if (eb_straddles_pages(eb)) {
- clear_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
- cached_state, GFP_NOFS);
- }
+ clear_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
+ cached_state, GFP_NOFS);
+
for (i = 0; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
if (page)
@@ -3909,6 +3926,8 @@ int extent_range_uptodate(struct extent_io_tree *tree,
while (start <= end) {
index = start >> PAGE_CACHE_SHIFT;
page = find_get_page(tree->mapping, index);
+ if (!page)
+ return 1;
uptodate = PageUptodate(page);
page_cache_release(page);
if (!uptodate) {
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index bc6a042cb..cecc351 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -319,4 +319,5 @@ struct btrfs_mapping_tree;
int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start,
u64 length, u64 logical, struct page *page,
int mirror_num);
+int end_extent_writepage(struct page *page, int err, u64 start, u64 end);
#endif
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 33a7890..1195f09 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -26,8 +26,8 @@ struct extent_map {
unsigned long flags;
struct block_device *bdev;
atomic_t refs;
- unsigned int in_tree:1;
- unsigned int compress_type:4;
+ unsigned int in_tree;
+ unsigned int compress_type;
};
struct extent_map_tree {
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index c7fb3a4..078b4fd 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -447,13 +447,13 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
sums->bytenr = ordered->start;
}
- data = kmap_atomic(bvec->bv_page, KM_USER0);
+ data = kmap_atomic(bvec->bv_page);
sector_sum->sum = ~(u32)0;
sector_sum->sum = btrfs_csum_data(root,
data + bvec->bv_offset,
sector_sum->sum,
bvec->bv_len);
- kunmap_atomic(data, KM_USER0);
+ kunmap_atomic(data);
btrfs_csum_final(sector_sum->sum,
(char *)&sector_sum->sum);
sector_sum->bytenr = disk_bytenr;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 859ba2d..e8d06b6 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1605,6 +1605,14 @@ static long btrfs_fallocate(struct file *file, int mode,
return -EOPNOTSUPP;
/*
+ * Make sure we have enough space before we do the
+ * allocation.
+ */
+ ret = btrfs_check_data_free_space(inode, len);
+ if (ret)
+ return ret;
+
+ /*
* wait for ordered IO before we have any locks. We'll loop again
* below with the locks held.
*/
@@ -1667,27 +1675,12 @@ static long btrfs_fallocate(struct file *file, int mode,
if (em->block_start == EXTENT_MAP_HOLE ||
(cur_offset >= inode->i_size &&
!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
-
- /*
- * Make sure we have enough space before we do the
- * allocation.
- */
- ret = btrfs_check_data_free_space(inode, last_byte -
- cur_offset);
- if (ret) {
- free_extent_map(em);
- break;
- }
-
ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
last_byte - cur_offset,
1 << inode->i_blkbits,
offset + len,
&alloc_hint);
- /* Let go of our reservation. */
- btrfs_free_reserved_data_space(inode, last_byte -
- cur_offset);
if (ret < 0) {
free_extent_map(em);
break;
@@ -1715,6 +1708,8 @@ static long btrfs_fallocate(struct file *file, int mode,
&cached_state, GFP_NOFS);
out:
mutex_unlock(&inode->i_mutex);
+ /* Let go of our reservation. */
+ btrfs_free_reserved_data_space(inode, len);
return ret;
}
@@ -1761,7 +1756,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
start - root->sectorsize,
root->sectorsize, 0);
if (IS_ERR(em)) {
- ret = -ENXIO;
+ ret = PTR_ERR(em);
goto out;
}
last_end = em->start + em->len;
@@ -1773,7 +1768,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
while (1) {
em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0);
if (IS_ERR(em)) {
- ret = -ENXIO;
+ ret = PTR_ERR(em);
break;
}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d20ff87..b02e379 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -777,6 +777,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
spin_lock(&block_group->lock);
if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) {
spin_unlock(&block_group->lock);
+ btrfs_free_path(path);
goto out;
}
spin_unlock(&block_group->lock);
@@ -1067,7 +1068,7 @@ int btrfs_write_out_cache(struct btrfs_root *root,
spin_unlock(&block_group->lock);
ret = 0;
#ifdef DEBUG
- printk(KERN_ERR "btrfs: failed to write free space cace "
+ printk(KERN_ERR "btrfs: failed to write free space cache "
"for block group %llu\n", block_group->key.objectid);
#endif
}
@@ -2242,7 +2243,7 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
if (entry->bitmap) {
ret = btrfs_alloc_from_bitmap(block_group,
cluster, entry, bytes,
- min_start);
+ cluster->window_start);
if (ret == 0) {
node = rb_next(&entry->offset_index);
if (!node)
@@ -2251,6 +2252,7 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
offset_index);
continue;
}
+ cluster->window_start += bytes;
} else {
ret = entry->offset;
@@ -2475,7 +2477,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
}
list_for_each_entry(entry, bitmaps, list) {
- if (entry->bytes < min_bytes)
+ if (entry->bytes < bytes)
continue;
ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
bytes, cont1_bytes, min_bytes);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 213ffa8..ee15d88 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -438,7 +438,8 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
trans->bytes_reserved);
if (ret)
goto out;
- trace_btrfs_space_reservation(root->fs_info, "ino_cache", (u64)trans,
+ trace_btrfs_space_reservation(root->fs_info, "ino_cache",
+ (u64)(unsigned long)trans,
trans->bytes_reserved, 1);
again:
inode = lookup_free_ino_inode(root, path);
@@ -500,7 +501,8 @@ again:
out_put:
iput(inode);
out_release:
- trace_btrfs_space_reservation(root->fs_info, "ino_cache", (u64)trans,
+ trace_btrfs_space_reservation(root->fs_info, "ino_cache",
+ (u64)(unsigned long)trans,
trans->bytes_reserved, 0);
btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
out:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0da19a0..3a0b5c1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -173,9 +173,9 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
cur_size = min_t(unsigned long, compressed_size,
PAGE_CACHE_SIZE);
- kaddr = kmap_atomic(cpage, KM_USER0);
+ kaddr = kmap_atomic(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
i++;
ptr += cur_size;
@@ -187,10 +187,10 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
page = find_get_page(inode->i_mapping,
start >> PAGE_CACHE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
offset = start & (PAGE_CACHE_SIZE - 1);
write_extent_buffer(leaf, kaddr + offset, ptr, size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
page_cache_release(page);
}
btrfs_mark_buffer_dirty(leaf);
@@ -422,10 +422,10 @@ again:
* sending it down to disk
*/
if (offset) {
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr + offset, 0,
PAGE_CACHE_SIZE - offset);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
will_compress = 1;
}
@@ -1555,6 +1555,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
struct inode *inode;
u64 page_start;
u64 page_end;
+ int ret;
fixup = container_of(work, struct btrfs_writepage_fixup, work);
page = fixup->page;
@@ -1582,12 +1583,21 @@ again:
page_end, &cached_state, GFP_NOFS);
unlock_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
goto again;
}
- BUG();
+ ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ if (ret) {
+ mapping_set_error(page->mapping, ret);
+ end_extent_writepage(page, ret, page_start, page_end);
+ ClearPageChecked(page);
+ goto out;
+ }
+
btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state);
ClearPageChecked(page);
+ set_page_dirty(page);
out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state, GFP_NOFS);
@@ -1630,7 +1640,7 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
fixup->work.func = btrfs_writepage_fixup_worker;
fixup->page = page;
btrfs_queue_worker(&root->fs_info->fixup_workers, &fixup->work);
- return -EAGAIN;
+ return -EBUSY;
}
static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
@@ -1863,7 +1873,7 @@ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
} else {
ret = get_state_private(io_tree, start, &private);
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
if (ret)
goto zeroit;
@@ -1872,7 +1882,7 @@ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
if (csum != private)
goto zeroit;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
good:
return 0;
@@ -1884,7 +1894,7 @@ zeroit:
(unsigned long long)private);
memset(kaddr + offset, 1, end - start + 1);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (private == 0)
return 0;
return -EIO;
@@ -4575,7 +4585,8 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
ret = btrfs_insert_dir_item(trans, root, name, name_len,
parent_inode, &key,
btrfs_inode_type(inode), index);
- BUG_ON(ret);
+ if (ret)
+ goto fail_dir_item;
btrfs_i_size_write(parent_inode, parent_inode->i_size +
name_len * 2);
@@ -4583,6 +4594,23 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
ret = btrfs_update_inode(trans, root, parent_inode);
}
return ret;
+
+fail_dir_item:
+ if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
+ u64 local_index;
+ int err;
+ err = btrfs_del_root_ref(trans, root->fs_info->tree_root,
+ key.objectid, root->root_key.objectid,
+ parent_ino, &local_index, name, name_len);
+
+ } else if (add_backref) {
+ u64 local_index;
+ int err;
+
+ err = btrfs_del_inode_ref(trans, root, name, name_len,
+ ino, parent_ino, &local_index);
+ }
+ return ret;
}
static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
@@ -4909,12 +4937,12 @@ static noinline int uncompress_inline(struct btrfs_path *path,
ret = btrfs_decompress(compress_type, tmp, page,
extent_offset, inline_size, max_size);
if (ret) {
- char *kaddr = kmap_atomic(page, KM_USER0);
+ char *kaddr = kmap_atomic(page);
unsigned long copy_size = min_t(u64,
PAGE_CACHE_SIZE - pg_offset,
max_size - extent_offset);
memset(kaddr + pg_offset, 0, copy_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
kfree(tmp);
return 0;
@@ -5691,11 +5719,11 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
unsigned long flags;
local_irq_save(flags);
- kaddr = kmap_atomic(page, KM_IRQ0);
+ kaddr = kmap_atomic(page);
csum = btrfs_csum_data(root, kaddr + bvec->bv_offset,
csum, bvec->bv_len);
btrfs_csum_final(csum, (char *)&csum);
- kunmap_atomic(kaddr, KM_IRQ0);
+ kunmap_atomic(kaddr);
local_irq_restore(flags);
flush_dcache_page(bvec->bv_page);
@@ -6401,18 +6429,23 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
unsigned long zero_start;
loff_t size;
int ret;
+ int reserved = 0;
u64 page_start;
u64 page_end;
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
- if (!ret)
+ if (!ret) {
ret = btrfs_update_time(vma->vm_file);
+ reserved = 1;
+ }
if (ret) {
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
else /* -ENOSPC, -EIO, etc */
ret = VM_FAULT_SIGBUS;
- goto out;
+ if (reserved)
+ goto out;
+ goto out_noreserve;
}
ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
@@ -6495,6 +6528,7 @@ out_unlock:
unlock_page(page);
out:
btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+out_noreserve:
return ret;
}
@@ -6690,8 +6724,10 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
int err;
u64 index = 0;
- inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, new_dirid,
- new_dirid, S_IFDIR | 0700, &index);
+ inode = btrfs_new_inode(trans, new_root, NULL, "..", 2,
+ new_dirid, new_dirid,
+ S_IFDIR | (~current_umask() & S_IRWXUGO),
+ &index);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &btrfs_dir_inode_operations;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ab62001..d8b5471 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -861,6 +861,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
int i_done;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
+ struct extent_io_tree *tree;
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
if (isize == 0)
@@ -871,18 +872,34 @@ static int cluster_pages_for_defrag(struct inode *inode,
num_pages << PAGE_CACHE_SHIFT);
if (ret)
return ret;
-again:
- ret = 0;
i_done = 0;
+ tree = &BTRFS_I(inode)->io_tree;
/* step one, lock all the pages */
for (i = 0; i < num_pages; i++) {
struct page *page;
+again:
page = find_or_create_page(inode->i_mapping,
- start_index + i, mask);
+ start_index + i, mask);
if (!page)
break;
+ page_start = page_offset(page);
+ page_end = page_start + PAGE_CACHE_SIZE - 1;
+ while (1) {
+ lock_extent(tree, page_start, page_end, GFP_NOFS);
+ ordered = btrfs_lookup_ordered_extent(inode,
+ page_start);
+ unlock_extent(tree, page_start, page_end, GFP_NOFS);
+ if (!ordered)
+ break;
+
+ unlock_page(page);
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
+ lock_page(page);
+ }
+
if (!PageUptodate(page)) {
btrfs_readpage(NULL, page);
lock_page(page);
@@ -893,15 +910,22 @@ again:
break;
}
}
+
isize = i_size_read(inode);
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
- if (!isize || page->index > file_end ||
- page->mapping != inode->i_mapping) {
+ if (!isize || page->index > file_end) {
/* whoops, we blew past eof, skip this page */
unlock_page(page);
page_cache_release(page);
break;
}
+
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+ page_cache_release(page);
+ goto again;
+ }
+
pages[i] = page;
i_done++;
}
@@ -924,25 +948,6 @@ again:
lock_extent_bits(&BTRFS_I(inode)->io_tree,
page_start, page_end - 1, 0, &cached_state,
GFP_NOFS);
- ordered = btrfs_lookup_first_ordered_extent(inode, page_end - 1);
- if (ordered &&
- ordered->file_offset + ordered->len > page_start &&
- ordered->file_offset < page_end) {
- btrfs_put_ordered_extent(ordered);
- unlock_extent_cached(&BTRFS_I(inode)->io_tree,
- page_start, page_end - 1,
- &cached_state, GFP_NOFS);
- for (i = 0; i < i_done; i++) {
- unlock_page(pages[i]);
- page_cache_release(pages[i]);
- }
- btrfs_wait_ordered_range(inode, page_start,
- page_end - page_start);
- goto again;
- }
- if (ordered)
- btrfs_put_ordered_extent(ordered);
-
clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
@@ -1065,7 +1070,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
i = range->start >> PAGE_CACHE_SHIFT;
}
if (!max_to_defrag)
- max_to_defrag = last_index;
+ max_to_defrag = last_index + 1;
/*
* make writeback starts from i, so the defrag range can be
@@ -1327,6 +1332,12 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
goto out;
}
+ if (name[0] == '.' &&
+ (namelen == 1 || (name[1] == '.' && namelen == 2))) {
+ ret = -EEXIST;
+ goto out;
+ }
+
if (subvol) {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
NULL, transid, readonly);
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index a178f5e..743b86f 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -411,9 +411,9 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
bytes = min_t(unsigned long, destlen, out_len - start_byte);
- kaddr = kmap_atomic(dest_page, KM_USER0);
+ kaddr = kmap_atomic(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
out:
return ret;
}
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 2373b39..22db045 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -305,7 +305,7 @@ again:
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&dev->reada_zones,
- (unsigned long)zone->end >> PAGE_CACHE_SHIFT,
+ (unsigned long)(zone->end >> PAGE_CACHE_SHIFT),
zone);
spin_unlock(&fs_info->reada_lock);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9770cc5..390e710 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -591,7 +591,7 @@ static int scrub_fixup_check(struct scrub_bio *sbio, int ix)
u64 flags = sbio->spag[ix].flags;
page = sbio->bio->bi_io_vec[ix].bv_page;
- buffer = kmap_atomic(page, KM_USER0);
+ buffer = kmap_atomic(page);
if (flags & BTRFS_EXTENT_FLAG_DATA) {
ret = scrub_checksum_data(sbio->sdev,
sbio->spag + ix, buffer);
@@ -603,7 +603,7 @@ static int scrub_fixup_check(struct scrub_bio *sbio, int ix)
} else {
WARN_ON(1);
}
- kunmap_atomic(buffer, KM_USER0);
+ kunmap_atomic(buffer);
return ret;
}
@@ -792,7 +792,7 @@ static void scrub_checksum(struct btrfs_work *work)
}
for (i = 0; i < sbio->count; ++i) {
page = sbio->bio->bi_io_vec[i].bv_page;
- buffer = kmap_atomic(page, KM_USER0);
+ buffer = kmap_atomic(page);
flags = sbio->spag[i].flags;
logical = sbio->logical + i * PAGE_SIZE;
ret = 0;
@@ -807,7 +807,7 @@ static void scrub_checksum(struct btrfs_work *work)
} else {
WARN_ON(1);
}
- kunmap_atomic(buffer, KM_USER0);
+ kunmap_atomic(buffer);
if (ret) {
ret = scrub_recheck_error(sbio, i);
if (!ret) {
@@ -1367,7 +1367,8 @@ out:
}
static noinline_for_stack int scrub_chunk(struct scrub_dev *sdev,
- u64 chunk_tree, u64 chunk_objectid, u64 chunk_offset, u64 length)
+ u64 chunk_tree, u64 chunk_objectid, u64 chunk_offset, u64 length,
+ u64 dev_offset)
{
struct btrfs_mapping_tree *map_tree =
&sdev->dev->dev_root->fs_info->mapping_tree;
@@ -1391,7 +1392,8 @@ static noinline_for_stack int scrub_chunk(struct scrub_dev *sdev,
goto out;
for (i = 0; i < map->num_stripes; ++i) {
- if (map->stripes[i].dev == sdev->dev) {
+ if (map->stripes[i].dev == sdev->dev &&
+ map->stripes[i].physical == dev_offset) {
ret = scrub_stripe(sdev, map, i, chunk_offset, length);
if (ret)
goto out;
@@ -1487,7 +1489,7 @@ int scrub_enumerate_chunks(struct scrub_dev *sdev, u64 start, u64 end)
break;
}
ret = scrub_chunk(sdev, chunk_tree, chunk_objectid,
- chunk_offset, length);
+ chunk_offset, length, found_key.offset);
btrfs_put_block_group(cache);
if (ret)
break;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3ce97b2..81df3fe 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -629,7 +629,6 @@ static int btrfs_fill_super(struct super_block *sb,
void *data, int silent)
{
struct inode *inode;
- struct dentry *root_dentry;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_key key;
int err;
@@ -660,15 +659,12 @@ static int btrfs_fill_super(struct super_block *sb,
goto fail_close;
}
- root_dentry = d_alloc_root(inode);
- if (!root_dentry) {
- iput(inode);
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root) {
err = -ENOMEM;
goto fail_close;
}
- sb->s_root = root_dentry;
-
save_mount_options(sb, data);
cleancache_init_fs(sb);
sb->s_flags |= MS_ACTIVE;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 287a672..04b77e3 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -327,7 +327,8 @@ again:
if (num_bytes) {
trace_btrfs_space_reservation(root->fs_info, "transaction",
- (u64)h, num_bytes, 1);
+ (u64)(unsigned long)h,
+ num_bytes, 1);
h->block_rsv = &root->fs_info->trans_block_rsv;
h->bytes_reserved = num_bytes;
}
@@ -915,7 +916,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
dentry->d_name.name, dentry->d_name.len,
parent_inode, &key,
BTRFS_FT_DIR, index);
- BUG_ON(ret);
+ if (ret) {
+ pending->error = -EEXIST;
+ dput(parent);
+ goto fail;
+ }
btrfs_i_size_write(parent_inode, parent_inode->i_size +
dentry->d_name.len * 2);
@@ -993,12 +998,9 @@ static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans,
{
struct btrfs_pending_snapshot *pending;
struct list_head *head = &trans->transaction->pending_snapshots;
- int ret;
- list_for_each_entry(pending, head, list) {
- ret = create_pending_snapshot(trans, fs_info, pending);
- BUG_ON(ret);
- }
+ list_for_each_entry(pending, head, list)
+ create_pending_snapshot(trans, fs_info, pending);
return 0;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index cb877e0..966cc74 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1957,7 +1957,8 @@ static int wait_log_commit(struct btrfs_trans_handle *trans,
finish_wait(&root->log_commit_wait[index], &wait);
mutex_lock(&root->log_mutex);
- } while (root->log_transid < transid + 2 &&
+ } while (root->fs_info->last_trans_log_full_commit !=
+ trans->transid && root->log_transid < transid + 2 &&
atomic_read(&root->log_commit[index]));
return 0;
}
@@ -1966,7 +1967,8 @@ static int wait_for_writer(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
DEFINE_WAIT(wait);
- while (atomic_read(&root->log_writers)) {
+ while (root->fs_info->last_trans_log_full_commit !=
+ trans->transid && atomic_read(&root->log_writers)) {
prepare_to_wait(&root->log_writer_wait,
&wait, TASK_UNINTERRUPTIBLE);
mutex_unlock(&root->log_mutex);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0b4e2af..ef41f28 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -459,12 +459,23 @@ int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device, *next;
+ struct block_device *latest_bdev = NULL;
+ u64 latest_devid = 0;
+ u64 latest_transid = 0;
+
mutex_lock(&uuid_mutex);
again:
/* This is the initialized path, it is safe to release the devices. */
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
- if (device->in_fs_metadata)
+ if (device->in_fs_metadata) {
+ if (!latest_transid ||
+ device->generation > latest_transid) {
+ latest_devid = device->devid;
+ latest_transid = device->generation;
+ latest_bdev = device->bdev;
+ }
continue;
+ }
if (device->bdev) {
blkdev_put(device->bdev, device->mode);
@@ -487,6 +498,10 @@ again:
goto again;
}
+ fs_devices->latest_bdev = latest_bdev;
+ fs_devices->latest_devid = latest_devid;
+ fs_devices->latest_trans = latest_transid;
+
mutex_unlock(&uuid_mutex);
return 0;
}
@@ -1953,7 +1968,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
em = lookup_extent_mapping(em_tree, chunk_offset, 1);
read_unlock(&em_tree->lock);
- BUG_ON(em->start > chunk_offset ||
+ BUG_ON(!em || em->start > chunk_offset ||
em->start + em->len < chunk_offset);
map = (struct map_lookup *)em->bdev;
@@ -4356,6 +4371,20 @@ int btrfs_read_sys_array(struct btrfs_root *root)
return -ENOMEM;
btrfs_set_buffer_uptodate(sb);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
+ /*
+ * The sb extent buffer is artifical and just used to read the system array.
+ * btrfs_set_buffer_uptodate() call does not properly mark all it's
+ * pages up-to-date when the page is larger: extent does not cover the
+ * whole page and consequently check_page_uptodate does not find all
+ * the page's extents up-to-date (the hole beyond sb),
+ * write_extent_buffer then triggers a WARN_ON.
+ *
+ * Regular short extents go through mark_extent_buffer_dirty/writeback cycle,
+ * but sb spans only this function. Add an explicit SetPageUptodate call
+ * to silence the warning eg. on PowerPC 64.
+ */
+ if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE)
+ SetPageUptodate(sb->first_page);
write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
array_size = btrfs_super_sys_array_size(super_copy);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index faccd47..92c2065 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -370,9 +370,9 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
PAGE_CACHE_SIZE - buf_offset);
bytes = min(bytes, bytes_left);
- kaddr = kmap_atomic(dest_page, KM_USER0);
+ kaddr = kmap_atomic(dest_page);
memcpy(kaddr + pg_offset, workspace->buf + buf_offset, bytes);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
pg_offset += bytes;
bytes_left -= bytes;
diff --git a/fs/buffer.c b/fs/buffer.c
index 1a30db7..70e2017 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -29,7 +29,7 @@
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/writeback.h>
#include <linux/hash.h>
#include <linux/suspend.h>
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index a0358c2..7f0771d 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -646,7 +646,8 @@ lookup_again:
* (this is used to keep track of culling, and atimes are only
* updated by read, write and readdir but not lookup or
* open) */
- touch_atime(cache->mnt, next);
+ path.dentry = next;
+ touch_atime(&path);
}
/* open a file interface onto a data file */
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b60fc8bf..620daad 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -641,10 +641,10 @@ static int __cap_is_valid(struct ceph_cap *cap)
unsigned long ttl;
u32 gen;
- spin_lock(&cap->session->s_cap_lock);
+ spin_lock(&cap->session->s_gen_ttl_lock);
gen = cap->session->s_cap_gen;
ttl = cap->session->s_cap_ttl;
- spin_unlock(&cap->session->s_cap_lock);
+ spin_unlock(&cap->session->s_gen_ttl_lock);
if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
dout("__cap_is_valid %p cap %p issued %s "
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 618246b..3e8094b 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -975,10 +975,10 @@ static int dentry_lease_is_valid(struct dentry *dentry)
di = ceph_dentry(dentry);
if (di->lease_session) {
s = di->lease_session;
- spin_lock(&s->s_cap_lock);
+ spin_lock(&s->s_gen_ttl_lock);
gen = s->s_cap_gen;
ttl = s->s_cap_ttl;
- spin_unlock(&s->s_cap_lock);
+ spin_unlock(&s->s_gen_ttl_lock);
if (di->lease_gen == gen &&
time_before(jiffies, dentry->d_time) &&
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2c48937..9fff9f3 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -677,18 +677,19 @@ static int fill_inode(struct inode *inode,
case S_IFLNK:
inode->i_op = &ceph_symlink_iops;
if (!ci->i_symlink) {
- int symlen = iinfo->symlink_len;
+ u32 symlen = iinfo->symlink_len;
char *sym;
- BUG_ON(symlen != inode->i_size);
spin_unlock(&ci->i_ceph_lock);
+ err = -EINVAL;
+ if (WARN_ON(symlen != inode->i_size))
+ goto out;
+
err = -ENOMEM;
- sym = kmalloc(symlen+1, GFP_NOFS);
+ sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
if (!sym)
goto out;
- memcpy(sym, iinfo->symlink, symlen);
- sym[symlen] = 0;
spin_lock(&ci->i_ceph_lock);
if (!ci->i_symlink)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 23ab6a3..89971e1 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -262,6 +262,7 @@ static int parse_reply_info(struct ceph_msg *msg,
/* trace */
ceph_decode_32_safe(&p, end, len, bad);
if (len > 0) {
+ ceph_decode_need(&p, end, len, bad);
err = parse_reply_info_trace(&p, p+len, info, features);
if (err < 0)
goto out_bad;
@@ -270,6 +271,7 @@ static int parse_reply_info(struct ceph_msg *msg,
/* extra */
ceph_decode_32_safe(&p, end, len, bad);
if (len > 0) {
+ ceph_decode_need(&p, end, len, bad);
err = parse_reply_info_extra(&p, p+len, info, features);
if (err < 0)
goto out_bad;
@@ -398,9 +400,11 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
s->s_con.peer_name.num = cpu_to_le64(mds);
- spin_lock_init(&s->s_cap_lock);
+ spin_lock_init(&s->s_gen_ttl_lock);
s->s_cap_gen = 0;
- s->s_cap_ttl = 0;
+ s->s_cap_ttl = jiffies - 1;
+
+ spin_lock_init(&s->s_cap_lock);
s->s_renew_requested = 0;
s->s_renew_seq = 0;
INIT_LIST_HEAD(&s->s_caps);
@@ -1079,8 +1083,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
int wake = 0;
spin_lock(&session->s_cap_lock);
- was_stale = is_renew && (session->s_cap_ttl == 0 ||
- time_after_eq(jiffies, session->s_cap_ttl));
+ was_stale = is_renew && time_after_eq(jiffies, session->s_cap_ttl);
session->s_cap_ttl = session->s_renew_requested +
mdsc->mdsmap->m_session_timeout*HZ;
@@ -2326,10 +2329,10 @@ static void handle_session(struct ceph_mds_session *session,
case CEPH_SESSION_STALE:
pr_info("mds%d caps went stale, renewing\n",
session->s_mds);
- spin_lock(&session->s_cap_lock);
+ spin_lock(&session->s_gen_ttl_lock);
session->s_cap_gen++;
- session->s_cap_ttl = 0;
- spin_unlock(&session->s_cap_lock);
+ session->s_cap_ttl = jiffies - 1;
+ spin_unlock(&session->s_gen_ttl_lock);
send_renew_caps(mdsc, session);
break;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index a50ca0e..8c7c04e 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -117,10 +117,13 @@ struct ceph_mds_session {
void *s_authorizer_buf, *s_authorizer_reply_buf;
size_t s_authorizer_buf_len, s_authorizer_reply_buf_len;
- /* protected by s_cap_lock */
- spinlock_t s_cap_lock;
+ /* protected by s_gen_ttl_lock */
+ spinlock_t s_gen_ttl_lock;
u32 s_cap_gen; /* inc each time we get mds stale msg */
unsigned long s_cap_ttl; /* when session caps expire */
+
+ /* protected by s_cap_lock */
+ spinlock_t s_cap_lock;
struct list_head s_caps; /* all caps issued by this session */
int s_nr_caps, s_trim_caps;
int s_num_cap_releases;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index a559c80..f04c096 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
/* alloc new snap context */
err = -ENOMEM;
- if (num > ULONG_MAX / sizeof(u64) - sizeof(*snapc))
+ if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64))
goto fail;
snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
if (!snapc)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 00de2c9..1e67dd7 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -130,10 +130,12 @@ enum {
Opt_nodirstat,
Opt_rbytes,
Opt_norbytes,
+ Opt_asyncreaddir,
Opt_noasyncreaddir,
Opt_dcache,
Opt_nodcache,
Opt_ino32,
+ Opt_noino32,
};
static match_table_t fsopt_tokens = {
@@ -153,10 +155,12 @@ static match_table_t fsopt_tokens = {
{Opt_nodirstat, "nodirstat"},
{Opt_rbytes, "rbytes"},
{Opt_norbytes, "norbytes"},
+ {Opt_asyncreaddir, "asyncreaddir"},
{Opt_noasyncreaddir, "noasyncreaddir"},
{Opt_dcache, "dcache"},
{Opt_nodcache, "nodcache"},
{Opt_ino32, "ino32"},
+ {Opt_noino32, "noino32"},
{-1, NULL}
};
@@ -232,6 +236,9 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_norbytes:
fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
break;
+ case Opt_asyncreaddir:
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR;
+ break;
case Opt_noasyncreaddir:
fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
break;
@@ -244,6 +251,9 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_ino32:
fsopt->flags |= CEPH_MOUNT_OPT_INO32;
break;
+ case Opt_noino32:
+ fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
+ break;
default:
BUG_ON(token);
}
@@ -334,10 +344,12 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
*path += 2;
dout("server path '%s'\n", *path);
- err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+ *popt = ceph_parse_options(options, dev_name, dev_name_end,
parse_fsopt_token, (void *)fsopt);
- if (err)
+ if (IS_ERR(*popt)) {
+ err = PTR_ERR(*popt);
goto out;
+ }
/* success */
*pfsopt = fsopt;
@@ -655,9 +667,8 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
dout("open_root_inode success\n");
if (ceph_ino(inode) == CEPH_INO_ROOT &&
fsc->sb->s_root == NULL) {
- root = d_alloc_root(inode);
+ root = d_make_root(inode);
if (!root) {
- iput(inode);
root = ERR_PTR(-ENOMEM);
goto out;
}
@@ -927,6 +938,7 @@ static int __init init_ceph(void)
if (ret)
goto out;
+ ceph_xattr_init();
ret = register_filesystem(&ceph_fs_type);
if (ret)
goto out_icache;
@@ -936,6 +948,7 @@ static int __init init_ceph(void)
return 0;
out_icache:
+ ceph_xattr_exit();
destroy_caches();
out:
return ret;
@@ -945,6 +958,7 @@ static void __exit exit_ceph(void)
{
dout("exit_ceph\n");
unregister_filesystem(&ceph_fs_type);
+ ceph_xattr_exit();
destroy_caches();
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1421f3d..fc35036 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -367,7 +367,7 @@ static inline u32 ceph_ino_to_ino32(__u64 vino)
u32 ino = vino & 0xffffffff;
ino ^= vino >> 32;
if (!ino)
- ino = 1;
+ ino = 2;
return ino;
}
@@ -733,6 +733,8 @@ extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
extern int ceph_removexattr(struct dentry *, const char *);
extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
+extern void __init ceph_xattr_init(void);
+extern void ceph_xattr_exit(void);
/* caps.c */
extern const char *ceph_cap_string(int c);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 857214a..35b8633 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -8,9 +8,12 @@
#include <linux/xattr.h>
#include <linux/slab.h>
+#define XATTR_CEPH_PREFIX "ceph."
+#define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
+
static bool ceph_is_valid_xattr(const char *name)
{
- return !strncmp(name, "ceph.", 5) ||
+ return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) ||
!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
@@ -21,79 +24,91 @@ static bool ceph_is_valid_xattr(const char *name)
* These define virtual xattrs exposing the recursive directory
* statistics and layout metadata.
*/
-struct ceph_vxattr_cb {
- bool readonly;
+struct ceph_vxattr {
char *name;
+ size_t name_size; /* strlen(name) + 1 (for '\0') */
size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
+ bool readonly;
};
/* directories */
-static size_t ceph_vxattrcb_entries(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs);
}
-static size_t ceph_vxattrcb_files(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_files);
}
-static size_t ceph_vxattrcb_subdirs(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_subdirs);
}
-static size_t ceph_vxattrcb_rentries(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs);
}
-static size_t ceph_vxattrcb_rfiles(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rfiles);
}
-static size_t ceph_vxattrcb_rsubdirs(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rsubdirs);
}
-static size_t ceph_vxattrcb_rbytes(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rbytes);
}
-static size_t ceph_vxattrcb_rctime(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
size_t size)
{
- return snprintf(val, size, "%ld.%ld", (long)ci->i_rctime.tv_sec,
+ return snprintf(val, size, "%ld.09%ld", (long)ci->i_rctime.tv_sec,
(long)ci->i_rctime.tv_nsec);
}
-static struct ceph_vxattr_cb ceph_dir_vxattrs[] = {
- { true, "ceph.dir.entries", ceph_vxattrcb_entries},
- { true, "ceph.dir.files", ceph_vxattrcb_files},
- { true, "ceph.dir.subdirs", ceph_vxattrcb_subdirs},
- { true, "ceph.dir.rentries", ceph_vxattrcb_rentries},
- { true, "ceph.dir.rfiles", ceph_vxattrcb_rfiles},
- { true, "ceph.dir.rsubdirs", ceph_vxattrcb_rsubdirs},
- { true, "ceph.dir.rbytes", ceph_vxattrcb_rbytes},
- { true, "ceph.dir.rctime", ceph_vxattrcb_rctime},
- { true, NULL, NULL }
+#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
+
+#define XATTR_NAME_CEPH(_type, _name) \
+ { \
+ .name = CEPH_XATTR_NAME(_type, _name), \
+ .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
+ .readonly = true, \
+ }
+
+static struct ceph_vxattr ceph_dir_vxattrs[] = {
+ XATTR_NAME_CEPH(dir, entries),
+ XATTR_NAME_CEPH(dir, files),
+ XATTR_NAME_CEPH(dir, subdirs),
+ XATTR_NAME_CEPH(dir, rentries),
+ XATTR_NAME_CEPH(dir, rfiles),
+ XATTR_NAME_CEPH(dir, rsubdirs),
+ XATTR_NAME_CEPH(dir, rbytes),
+ XATTR_NAME_CEPH(dir, rctime),
+ { 0 } /* Required table terminator */
};
+static size_t ceph_dir_vxattrs_name_size; /* total size of all names */
/* files */
-static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
size_t size)
{
int ret;
@@ -103,19 +118,32 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
(unsigned long long)ceph_file_layout_su(ci->i_layout),
(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
(unsigned long long)ceph_file_layout_object_size(ci->i_layout));
- if (ceph_file_layout_pg_preferred(ci->i_layout))
- ret += snprintf(val + ret, size, "preferred_osd=%lld\n",
+
+ if (ceph_file_layout_pg_preferred(ci->i_layout) >= 0) {
+ val += ret;
+ size -= ret;
+ ret += snprintf(val, size, "preferred_osd=%lld\n",
(unsigned long long)ceph_file_layout_pg_preferred(
ci->i_layout));
+ }
+
return ret;
}
-static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
- { true, "ceph.layout", ceph_vxattrcb_layout},
- { NULL, NULL }
+static struct ceph_vxattr ceph_file_vxattrs[] = {
+ XATTR_NAME_CEPH(file, layout),
+ /* The following extended attribute name is deprecated */
+ {
+ .name = XATTR_CEPH_PREFIX "layout",
+ .name_size = sizeof (XATTR_CEPH_PREFIX "layout"),
+ .getxattr_cb = ceph_vxattrcb_file_layout,
+ .readonly = true,
+ },
+ { 0 } /* Required table terminator */
};
+static size_t ceph_file_vxattrs_name_size; /* total size of all names */
-static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
+static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode)
{
if (S_ISDIR(inode->i_mode))
return ceph_dir_vxattrs;
@@ -124,14 +152,59 @@ static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
return NULL;
}
-static struct ceph_vxattr_cb *ceph_match_vxattr(struct ceph_vxattr_cb *vxattr,
+static size_t ceph_vxattrs_name_size(struct ceph_vxattr *vxattrs)
+{
+ if (vxattrs == ceph_dir_vxattrs)
+ return ceph_dir_vxattrs_name_size;
+ if (vxattrs == ceph_file_vxattrs)
+ return ceph_file_vxattrs_name_size;
+ BUG();
+
+ return 0;
+}
+
+/*
+ * Compute the aggregate size (including terminating '\0') of all
+ * virtual extended attribute names in the given vxattr table.
+ */
+static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs)
+{
+ struct ceph_vxattr *vxattr;
+ size_t size = 0;
+
+ for (vxattr = vxattrs; vxattr->name; vxattr++)
+ size += vxattr->name_size;
+
+ return size;
+}
+
+/* Routines called at initialization and exit time */
+
+void __init ceph_xattr_init(void)
+{
+ ceph_dir_vxattrs_name_size = vxattrs_name_size(ceph_dir_vxattrs);
+ ceph_file_vxattrs_name_size = vxattrs_name_size(ceph_file_vxattrs);
+}
+
+void ceph_xattr_exit(void)
+{
+ ceph_dir_vxattrs_name_size = 0;
+ ceph_file_vxattrs_name_size = 0;
+}
+
+static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
const char *name)
{
- do {
- if (strcmp(vxattr->name, name) == 0)
- return vxattr;
- vxattr++;
- } while (vxattr->name);
+ struct ceph_vxattr *vxattr = ceph_inode_vxattrs(inode);
+
+ if (vxattr) {
+ while (vxattr->name) {
+ if (!strcmp(vxattr->name, name))
+ return vxattr;
+ vxattr++;
+ }
+ }
+
return NULL;
}
@@ -500,17 +573,15 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
{
struct inode *inode = dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
int err;
struct ceph_inode_xattr *xattr;
- struct ceph_vxattr_cb *vxattr = NULL;
+ struct ceph_vxattr *vxattr = NULL;
if (!ceph_is_valid_xattr(name))
return -ENODATA;
/* let's see if a virtual xattr was requested */
- if (vxattrs)
- vxattr = ceph_match_vxattr(vxattrs, name);
+ vxattr = ceph_match_vxattr(inode, name);
spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
@@ -566,7 +637,7 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
{
struct inode *inode = dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+ struct ceph_vxattr *vxattrs = ceph_inode_vxattrs(inode);
u32 vir_namelen = 0;
u32 namelen;
int err;
@@ -594,11 +665,12 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
goto out;
list_xattr:
- vir_namelen = 0;
- /* include virtual dir xattrs */
- if (vxattrs)
- for (i = 0; vxattrs[i].name; i++)
- vir_namelen += strlen(vxattrs[i].name) + 1;
+ /*
+ * Start with virtual dir xattr names (if any) (including
+ * terminating '\0' characters for each).
+ */
+ vir_namelen = ceph_vxattrs_name_size(vxattrs);
+
/* adding 1 byte per each variable due to the null termination */
namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
err = -ERANGE;
@@ -696,17 +768,17 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
+ struct ceph_vxattr *vxattr;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+ int issued;
int err;
+ int dirty;
int name_len = strlen(name);
int val_len = size;
char *newname = NULL;
char *newval = NULL;
struct ceph_inode_xattr *xattr = NULL;
- int issued;
int required_blob_size;
- int dirty;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
@@ -714,12 +786,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
- if (vxattrs) {
- struct ceph_vxattr_cb *vxattr =
- ceph_match_vxattr(vxattrs, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
- }
+ vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && vxattr->readonly)
+ return -EOPNOTSUPP;
/* preallocate memory for xattr name, value, index node */
err = -ENOMEM;
@@ -728,11 +797,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
goto out;
if (val_len) {
- newval = kmalloc(val_len + 1, GFP_NOFS);
+ newval = kmemdup(value, val_len, GFP_NOFS);
if (!newval)
goto out;
- memcpy(newval, value, val_len);
- newval[val_len] = '\0';
}
xattr = kmalloc(sizeof(struct ceph_inode_xattr), GFP_NOFS);
@@ -742,6 +809,7 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
spin_lock(&ci->i_ceph_lock);
retry:
issued = __ceph_caps_issued(ci, NULL);
+ dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
if (!(issued & CEPH_CAP_XATTR_EXCL))
goto do_sync;
__build_xattrs(inode);
@@ -750,7 +818,7 @@ retry:
if (!ci->i_xattrs.prealloc_blob ||
required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
- struct ceph_buffer *blob = NULL;
+ struct ceph_buffer *blob;
spin_unlock(&ci->i_ceph_lock);
dout(" preaallocating new blob size=%d\n", required_blob_size);
@@ -764,12 +832,13 @@ retry:
goto retry;
}
- dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
err = __set_xattr(ci, newname, name_len, newval,
val_len, 1, 1, 1, &xattr);
+
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
ci->i_xattrs.dirty = true;
inode->i_ctime = CURRENT_TIME;
+
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
@@ -814,8 +883,8 @@ 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 ceph_vxattr *vxattr;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
int issued;
int err;
int required_blob_size;
@@ -827,22 +896,19 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
- if (vxattrs) {
- struct ceph_vxattr_cb *vxattr =
- ceph_match_vxattr(vxattrs, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
- }
+ vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && vxattr->readonly)
+ return -EOPNOTSUPP;
err = -ENOMEM;
spin_lock(&ci->i_ceph_lock);
- __build_xattrs(inode);
retry:
issued = __ceph_caps_issued(ci, NULL);
dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
if (!(issued & CEPH_CAP_XATTR_EXCL))
goto do_sync;
+ __build_xattrs(inode);
required_blob_size = __get_required_blob_size(ci, 0, 0);
@@ -863,10 +929,10 @@ retry:
}
err = __remove_xattr_by_name(ceph_inode(inode), name);
+
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
ci->i_xattrs.dirty = true;
inode->i_ctime = CURRENT_TIME;
-
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index f66cc16..2b243af 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -139,8 +139,7 @@ config CIFS_DFS_UPCALL
points. If unsure, say N.
config CIFS_FSCACHE
- bool "Provide CIFS client caching support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ bool "Provide CIFS client caching support"
depends on CIFS=m && FSCACHE || CIFS=y && FSCACHE=y
help
Makes CIFS FS-Cache capable. Say Y here if you want your CIFS data
@@ -148,8 +147,8 @@ config CIFS_FSCACHE
manager. If unsure, say N.
config CIFS_ACL
- bool "Provide CIFS ACL support (EXPERIMENTAL)"
- depends on EXPERIMENTAL && CIFS_XATTR && KEYS
+ bool "Provide CIFS ACL support"
+ depends on CIFS_XATTR && KEYS
help
Allows to fetch CIFS/NTFS ACL from the server. The DACL blob
is handed over to the application/caller.
diff --git a/fs/cifs/README b/fs/cifs/README
index 895da1d..b7d782b 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -753,10 +753,6 @@ module loading or during the runtime by using the interface
i.e. echo "value" > /sys/module/cifs/parameters/<param>
-1. echo_retries - The number of echo attempts before giving up and
- reconnecting to the server. The default is 5. The value 0
- means never reconnect.
-
-2. enable_oplocks - Enable or disable oplocks. Oplocks are enabled by default.
+1. enable_oplocks - Enable or disable oplocks. Oplocks are enabled by default.
[Y/y/1]. To disable use any of [N/n/0].
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 84e8c07..573b899 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -171,8 +171,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
seq_printf(m, "TCP status: %d\n\tLocal Users To "
"Server: %d SecMode: 0x%x Req On Wire: %d",
server->tcpStatus, server->srv_count,
- server->sec_mode,
- atomic_read(&server->inFlight));
+ server->sec_mode, in_flight(server));
#ifdef CONFIG_CIFS_STATS2
seq_printf(m, " In Send: %d In MaxReq Wait: %d",
@@ -676,14 +675,23 @@ static ssize_t cifs_multiuser_mount_proc_write(struct file *file,
{
char c;
int rc;
+ static bool warned;
rc = get_user(c, buffer);
if (rc)
return rc;
if (c == '0' || c == 'n' || c == 'N')
multiuser_mount = 0;
- else if (c == '1' || c == 'y' || c == 'Y')
+ else if (c == '1' || c == 'y' || c == 'Y') {
multiuser_mount = 1;
+ if (!warned) {
+ warned = true;
+ printk(KERN_WARNING "CIFS VFS: The legacy multiuser "
+ "mount code is scheduled to be deprecated in "
+ "3.5. Please switch to using the multiuser "
+ "mount option.");
+ }
+ }
return count;
}
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 2272fd5..e622863 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -113,9 +113,11 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo)
MAX_MECH_STR_LEN +
UID_KEY_LEN + (sizeof(uid_t) * 2) +
CREDUID_KEY_LEN + (sizeof(uid_t) * 2) +
- USER_KEY_LEN + strlen(sesInfo->user_name) +
PID_KEY_LEN + (sizeof(pid_t) * 2) + 1;
+ if (sesInfo->user_name)
+ desc_len += USER_KEY_LEN + strlen(sesInfo->user_name);
+
spnego_key = ERR_PTR(-ENOMEM);
description = kzalloc(desc_len, GFP_KERNEL);
if (description == NULL)
@@ -152,8 +154,10 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo)
dp = description + strlen(description);
sprintf(dp, ";creduid=0x%x", sesInfo->cred_uid);
- dp = description + strlen(description);
- sprintf(dp, ";user=%s", sesInfo->user_name);
+ if (sesInfo->user_name) {
+ dp = description + strlen(description);
+ sprintf(dp, ";user=%s", sesInfo->user_name);
+ }
dp = description + strlen(description);
sprintf(dp, ";pid=0x%x", current->pid);
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 1b2e180..fbb9da9 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -27,17 +27,17 @@
#include "cifs_debug.h"
/*
- * cifs_ucs2_bytes - how long will a string be after conversion?
- * @ucs - pointer to input string
+ * cifs_utf16_bytes - how long will a string be after conversion?
+ * @utf16 - pointer to input string
* @maxbytes - don't go past this many bytes of input string
* @codepage - destination codepage
*
- * Walk a ucs2le string and return the number of bytes that the string will
+ * Walk a utf16le string and return the number of bytes that the string will
* be after being converted to the given charset, not including any null
* termination required. Don't walk past maxbytes in the source buffer.
*/
int
-cifs_ucs2_bytes(const __le16 *from, int maxbytes,
+cifs_utf16_bytes(const __le16 *from, int maxbytes,
const struct nls_table *codepage)
{
int i;
@@ -122,7 +122,7 @@ cp_convert:
}
/*
- * cifs_from_ucs2 - convert utf16le string to local charset
+ * cifs_from_utf16 - convert utf16le string to local charset
* @to - destination buffer
* @from - source buffer
* @tolen - destination buffer size (in bytes)
@@ -130,7 +130,7 @@ cp_convert:
* @codepage - codepage to which characters should be converted
* @mapchar - should characters be remapped according to the mapchars option?
*
- * Convert a little-endian ucs2le string (as sent by the server) to a string
+ * Convert a little-endian utf16le string (as sent by the server) to a string
* in the provided codepage. The tolen and fromlen parameters are to ensure
* that the code doesn't walk off of the end of the buffer (which is always
* a danger if the alignment of the source buffer is off). The destination
@@ -139,12 +139,12 @@ cp_convert:
* null terminator).
*
* Note that some windows versions actually send multiword UTF-16 characters
- * instead of straight UCS-2. The linux nls routines however aren't able to
+ * instead of straight UTF16-2. The linux nls routines however aren't able to
* deal with those characters properly. In the event that we get some of
* those characters, they won't be translated properly.
*/
int
-cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
+cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
const struct nls_table *codepage, bool mapchar)
{
int i, charlen, safelen;
@@ -190,13 +190,13 @@ cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
}
/*
- * NAME: cifs_strtoUCS()
+ * NAME: cifs_strtoUTF16()
*
* FUNCTION: Convert character string to unicode string
*
*/
int
-cifs_strtoUCS(__le16 *to, const char *from, int len,
+cifs_strtoUTF16(__le16 *to, const char *from, int len,
const struct nls_table *codepage)
{
int charlen;
@@ -206,7 +206,7 @@ cifs_strtoUCS(__le16 *to, const char *from, int len,
for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
charlen = codepage->char2uni(from, len, &wchar_to);
if (charlen < 1) {
- cERROR(1, "strtoUCS: char2uni of 0x%x returned %d",
+ cERROR(1, "strtoUTF16: char2uni of 0x%x returned %d",
*from, charlen);
/* A question mark */
wchar_to = 0x003f;
@@ -220,7 +220,8 @@ cifs_strtoUCS(__le16 *to, const char *from, int len,
}
/*
- * cifs_strndup_from_ucs - copy a string from wire format to the local codepage
+ * cifs_strndup_from_utf16 - copy a string from wire format to the local
+ * codepage
* @src - source string
* @maxlen - don't walk past this many bytes in the source string
* @is_unicode - is this a unicode string?
@@ -231,19 +232,19 @@ cifs_strtoUCS(__le16 *to, const char *from, int len,
* error.
*/
char *
-cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode,
- const struct nls_table *codepage)
+cifs_strndup_from_utf16(const char *src, const int maxlen,
+ const bool is_unicode, const struct nls_table *codepage)
{
int len;
char *dst;
if (is_unicode) {
- len = cifs_ucs2_bytes((__le16 *) src, maxlen, codepage);
+ len = cifs_utf16_bytes((__le16 *) src, maxlen, codepage);
len += nls_nullsize(codepage);
dst = kmalloc(len, GFP_KERNEL);
if (!dst)
return NULL;
- cifs_from_ucs2(dst, (__le16 *) src, len, maxlen, codepage,
+ cifs_from_utf16(dst, (__le16 *) src, len, maxlen, codepage,
false);
} else {
len = strnlen(src, maxlen);
@@ -264,7 +265,7 @@ cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode,
* names are little endian 16 bit Unicode on the wire
*/
int
-cifsConvertToUCS(__le16 *target, const char *source, int srclen,
+cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
const struct nls_table *cp, int mapChars)
{
int i, j, charlen;
@@ -273,7 +274,7 @@ cifsConvertToUCS(__le16 *target, const char *source, int srclen,
wchar_t tmp;
if (!mapChars)
- return cifs_strtoUCS(target, source, PATH_MAX, cp);
+ return cifs_strtoUTF16(target, source, PATH_MAX, cp);
for (i = 0, j = 0; i < srclen; j++) {
src_char = source[i];
@@ -281,7 +282,7 @@ cifsConvertToUCS(__le16 *target, const char *source, int srclen,
switch (src_char) {
case 0:
put_unaligned(0, &target[j]);
- goto ctoUCS_out;
+ goto ctoUTF16_out;
case ':':
dst_char = cpu_to_le16(UNI_COLON);
break;
@@ -326,7 +327,7 @@ cifsConvertToUCS(__le16 *target, const char *source, int srclen,
put_unaligned(dst_char, &target[j]);
}
-ctoUCS_out:
+ctoUTF16_out:
return i;
}
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index 6d02fd56..a513a54 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -74,16 +74,16 @@ extern const struct UniCaseRange CifsUniLowerRange[];
#endif /* UNIUPR_NOLOWER */
#ifdef __KERNEL__
-int cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
- const struct nls_table *codepage, bool mapchar);
-int cifs_ucs2_bytes(const __le16 *from, int maxbytes,
- const struct nls_table *codepage);
-int cifs_strtoUCS(__le16 *, const char *, int, const struct nls_table *);
-char *cifs_strndup_from_ucs(const char *src, const int maxlen,
- const bool is_unicode,
- const struct nls_table *codepage);
-extern int cifsConvertToUCS(__le16 *target, const char *source, int maxlen,
- const struct nls_table *cp, int mapChars);
+int cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
+ const struct nls_table *codepage, bool mapchar);
+int cifs_utf16_bytes(const __le16 *from, int maxbytes,
+ const struct nls_table *codepage);
+int cifs_strtoUTF16(__le16 *, const char *, int, const struct nls_table *);
+char *cifs_strndup_from_utf16(const char *src, const int maxlen,
+ const bool is_unicode,
+ const struct nls_table *codepage);
+extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen,
+ const struct nls_table *cp, int mapChars);
#endif
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 72ddf23..3cc1b25 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -556,6 +556,7 @@ init_cifs_idmap(void)
/* instruct request_key() to use this special keyring as a cache for
* the results it looks up */
+ set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags);
cred->thread_keyring = keyring;
cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
root_cred = cred;
@@ -909,6 +910,8 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl,
umode_t group_mask = S_IRWXG;
umode_t other_mask = S_IRWXU | S_IRWXG | S_IRWXO;
+ if (num_aces > ULONG_MAX / sizeof(struct cifs_ace *))
+ return;
ppace = kmalloc(num_aces * sizeof(struct cifs_ace *),
GFP_KERNEL);
if (!ppace) {
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 5d9b9ac..63c460e 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -327,7 +327,7 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp)
attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_DOMAIN_NAME);
attrptr->length = cpu_to_le16(2 * dlen);
blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name);
- cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp);
+ cifs_strtoUTF16((__le16 *)blobptr, ses->domainName, dlen, nls_cp);
return 0;
}
@@ -376,7 +376,7 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
kmalloc(attrsize + 1, GFP_KERNEL);
if (!ses->domainName)
return -ENOMEM;
- cifs_from_ucs2(ses->domainName,
+ cifs_from_utf16(ses->domainName,
(__le16 *)blobptr, attrsize, attrsize,
nls_cp, false);
break;
@@ -420,15 +420,20 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
}
/* convert ses->user_name to unicode and uppercase */
- len = strlen(ses->user_name);
+ len = ses->user_name ? strlen(ses->user_name) : 0;
user = kmalloc(2 + (len * 2), GFP_KERNEL);
if (user == NULL) {
cERROR(1, "calc_ntlmv2_hash: user mem alloc failure\n");
rc = -ENOMEM;
return rc;
}
- len = cifs_strtoUCS((__le16 *)user, ses->user_name, len, nls_cp);
- UniStrupr(user);
+
+ if (len) {
+ len = cifs_strtoUTF16((__le16 *)user, ses->user_name, len, nls_cp);
+ UniStrupr(user);
+ } else {
+ memset(user, '\0', 2);
+ }
rc = crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash,
(char *)user, 2 * len);
@@ -448,8 +453,8 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
rc = -ENOMEM;
return rc;
}
- len = cifs_strtoUCS((__le16 *)domain, ses->domainName, len,
- nls_cp);
+ len = cifs_strtoUTF16((__le16 *)domain, ses->domainName, len,
+ nls_cp);
rc =
crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash,
(char *)domain, 2 * len);
@@ -468,7 +473,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
rc = -ENOMEM;
return rc;
}
- len = cifs_strtoUCS((__le16 *)server, ses->serverName, len,
+ len = cifs_strtoUTF16((__le16 *)server, ses->serverName, len,
nls_cp);
rc =
crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash,
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index b1fd382..eee522c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -76,12 +76,7 @@ MODULE_PARM_DESC(cifs_min_small, "Small network buffers in pool. Default: 30 "
unsigned int cifs_max_pending = CIFS_MAX_REQ;
module_param(cifs_max_pending, int, 0444);
MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server. "
- "Default: 50 Range: 2 to 256");
-unsigned short echo_retries = 5;
-module_param(echo_retries, ushort, 0644);
-MODULE_PARM_DESC(echo_retries, "Number of echo attempts before giving up and "
- "reconnecting server. Default: 5. 0 means "
- "never reconnect.");
+ "Default: 32767 Range: 2 to 32767.");
module_param(enable_oplocks, bool, 0644);
MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks (bool). Default:"
"y/Y/1");
@@ -119,12 +114,10 @@ cifs_read_super(struct super_block *sb)
if (IS_ERR(inode)) {
rc = PTR_ERR(inode);
- inode = NULL;
goto out_no_root;
}
- sb->s_root = d_alloc_root(inode);
-
+ sb->s_root = d_make_root(inode);
if (!sb->s_root) {
rc = -ENOMEM;
goto out_no_root;
@@ -147,9 +140,6 @@ cifs_read_super(struct super_block *sb)
out_no_root:
cERROR(1, "cifs_read_super: get root inode failed");
- if (inode)
- iput(inode);
-
return rc;
}
@@ -1116,9 +1106,9 @@ init_cifs(void)
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
cFYI(1, "cifs_max_pending set to min of 2");
- } else if (cifs_max_pending > 256) {
- cifs_max_pending = 256;
- cFYI(1, "cifs_max_pending set to max of 256");
+ } else if (cifs_max_pending > CIFS_MAX_REQ) {
+ cifs_max_pending = CIFS_MAX_REQ;
+ cFYI(1, "cifs_max_pending set to max of %u", CIFS_MAX_REQ);
}
rc = cifs_fscache_register();
@@ -1180,11 +1170,8 @@ static void __exit
exit_cifs(void)
{
cFYI(DBG2, "exit_cifs");
- cifs_proc_clean();
- cifs_fscache_unregister();
-#ifdef CONFIG_CIFS_DFS_UPCALL
+ unregister_filesystem(&cifs_fs_type);
cifs_dfs_release_automount_timer();
-#endif
#ifdef CONFIG_CIFS_ACL
cifs_destroy_idmaptrees();
exit_cifs_idmap();
@@ -1192,10 +1179,11 @@ exit_cifs(void)
#ifdef CONFIG_CIFS_UPCALL
unregister_key_type(&cifs_spnego_key_type);
#endif
- unregister_filesystem(&cifs_fs_type);
- cifs_destroy_inodecache();
- cifs_destroy_mids();
cifs_destroy_request_bufs();
+ cifs_destroy_mids();
+ cifs_destroy_inodecache();
+ cifs_fscache_unregister();
+ cifs_proc_clean();
}
MODULE_AUTHOR("Steve French <sfrench@us.ibm.com>");
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index ba53c1c..339ebe3 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -55,14 +55,9 @@
/*
* MAX_REQ is the maximum number of requests that WE will send
- * on one socket concurrently. It also matches the most common
- * value of max multiplex returned by servers. We may
- * eventually want to use the negotiated value (in case
- * future servers can handle more) when we are more confident that
- * we will not have problems oveloading the socket with pending
- * write data.
+ * on one socket concurrently.
*/
-#define CIFS_MAX_REQ 50
+#define CIFS_MAX_REQ 32767
#define RFC1001_NAME_LEN 15
#define RFC1001_NAME_LEN_WITH_NULL (RFC1001_NAME_LEN + 1)
@@ -255,7 +250,9 @@ struct TCP_Server_Info {
bool noblocksnd; /* use blocking sendmsg */
bool noautotune; /* do not autotune send buf sizes */
bool tcp_nodelay;
- atomic_t inFlight; /* number of requests on the wire to server */
+ int credits; /* send no more requests at once */
+ unsigned int in_flight; /* number of requests on the wire to server */
+ spinlock_t req_lock; /* protect the two values above */
struct mutex srv_mutex;
struct task_struct *tsk;
char server_GUID[16];
@@ -263,6 +260,7 @@ struct TCP_Server_Info {
bool session_estab; /* mark when very first sess is established */
u16 dialect; /* dialect index that server chose */
enum securityEnum secType;
+ bool oplocks:1; /* enable oplocks */
unsigned int maxReq; /* Clients should submit no more */
/* than maxReq distinct unanswered SMBs to the server when using */
/* multiplexed reads or writes */
@@ -307,6 +305,36 @@ struct TCP_Server_Info {
#endif
};
+static inline unsigned int
+in_flight(struct TCP_Server_Info *server)
+{
+ unsigned int num;
+ spin_lock(&server->req_lock);
+ num = server->in_flight;
+ spin_unlock(&server->req_lock);
+ return num;
+}
+
+static inline int*
+get_credits_field(struct TCP_Server_Info *server)
+{
+ /*
+ * This will change to switch statement when we reserve slots for echos
+ * and oplock breaks.
+ */
+ return &server->credits;
+}
+
+static inline bool
+has_credits(struct TCP_Server_Info *server, int *credits)
+{
+ int num;
+ spin_lock(&server->req_lock);
+ num = *credits;
+ spin_unlock(&server->req_lock);
+ return num > 0;
+}
+
/*
* Macros to allow the TCP_Server_Info->net field and related code to drop out
* when CONFIG_NET_NS isn't set.
@@ -879,6 +907,8 @@ require use of the stronger protocol */
#define CIFSSEC_MASK 0xB70B7 /* current flags supported if weak */
#endif /* UPCALL */
#else /* do not allow weak pw hash */
+#define CIFSSEC_MUST_LANMAN 0
+#define CIFSSEC_MUST_PLNTXT 0
#ifdef CONFIG_CIFS_UPCALL
#define CIFSSEC_MASK 0x8F08F /* flags supported if no weak allowed */
#else
@@ -1008,9 +1038,6 @@ GLOBAL_EXTERN unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */
GLOBAL_EXTERN unsigned int cifs_min_small; /* min size of small buf pool */
GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/
-/* reconnect after this many failed echo attempts */
-GLOBAL_EXTERN unsigned short echo_retries;
-
#ifdef CONFIG_CIFS_ACL
GLOBAL_EXTERN struct rb_root uidtree;
GLOBAL_EXTERN struct rb_root gidtree;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 6f4e243..503e73d 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -88,6 +88,9 @@ extern int SendReceiveBlockingLock(const unsigned int xid,
struct smb_hdr *in_buf ,
struct smb_hdr *out_buf,
int *bytes_returned);
+extern void cifs_add_credits(struct TCP_Server_Info *server,
+ const unsigned int add);
+extern void cifs_set_credits(struct TCP_Server_Info *server, const int val);
extern int checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length);
extern bool is_valid_oplock_break(struct smb_hdr *smb,
struct TCP_Server_Info *);
@@ -168,7 +171,13 @@ extern struct smb_vol *cifs_get_volume_info(char *mount_data,
const char *devname);
extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *);
extern void cifs_umount(struct cifs_sb_info *);
+
+#if IS_ENABLED(CONFIG_CIFS_DFS_UPCALL)
extern void cifs_dfs_release_automount_timer(void);
+#else /* ! IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) */
+#define cifs_dfs_release_automount_timer() do { } while (0)
+#endif /* ! IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) */
+
void cifs_proc_init(void);
void cifs_proc_clean(void);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 6600aa2..70aac35c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -458,7 +458,10 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses)
goto neg_err_exit;
}
server->sec_mode = (__u8)le16_to_cpu(rsp->SecurityMode);
- server->maxReq = le16_to_cpu(rsp->MaxMpxCount);
+ server->maxReq = min_t(unsigned int,
+ le16_to_cpu(rsp->MaxMpxCount),
+ cifs_max_pending);
+ cifs_set_credits(server, server->maxReq);
server->maxBuf = le16_to_cpu(rsp->MaxBufSize);
server->max_vcs = le16_to_cpu(rsp->MaxNumberVcs);
/* even though we do not use raw we might as well set this
@@ -564,7 +567,9 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses)
/* one byte, so no need to convert this or EncryptionKeyLen from
little endian */
- server->maxReq = le16_to_cpu(pSMBr->MaxMpxCount);
+ server->maxReq = min_t(unsigned int, le16_to_cpu(pSMBr->MaxMpxCount),
+ cifs_max_pending);
+ cifs_set_credits(server, server->maxReq);
/* probably no need to store and check maxvcs */
server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize);
server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
@@ -716,8 +721,7 @@ cifs_echo_callback(struct mid_q_entry *mid)
struct TCP_Server_Info *server = mid->callback_data;
DeleteMidQEntry(mid);
- atomic_dec(&server->inFlight);
- wake_up(&server->request_q);
+ cifs_add_credits(server, 1);
}
int
@@ -821,8 +825,8 @@ PsxDelete:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB add path length overrun check */
@@ -893,8 +897,8 @@ DelFileRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->fileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->fileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve check for buffer overruns BB */
@@ -938,8 +942,8 @@ RmDirRetry:
return rc;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- name_len = cifsConvertToUCS((__le16 *) pSMB->DirName, dirName,
- PATH_MAX, nls_codepage, remap);
+ name_len = cifsConvertToUTF16((__le16 *) pSMB->DirName, dirName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve check for buffer overruns BB */
@@ -981,8 +985,8 @@ MkDirRetry:
return rc;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- name_len = cifsConvertToUCS((__le16 *) pSMB->DirName, name,
- PATH_MAX, nls_codepage, remap);
+ name_len = cifsConvertToUTF16((__le16 *) pSMB->DirName, name,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve check for buffer overruns BB */
@@ -1030,8 +1034,8 @@ PsxCreat:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, name,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, name,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -1197,8 +1201,8 @@ OldOpenRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
count = 1; /* account for one byte pad to word boundary */
name_len =
- cifsConvertToUCS((__le16 *) (pSMB->fileName + 1),
- fileName, PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) (pSMB->fileName + 1),
+ fileName, PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve check for buffer overruns BB */
@@ -1304,8 +1308,8 @@ openRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
count = 1; /* account for one byte pad to word boundary */
name_len =
- cifsConvertToUCS((__le16 *) (pSMB->fileName + 1),
- fileName, PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) (pSMB->fileName + 1),
+ fileName, PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
pSMB->NameLength = cpu_to_le16(name_len);
@@ -1669,8 +1673,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
queue_work(system_nrt_wq, &rdata->work);
DeleteMidQEntry(mid);
- atomic_dec(&server->inFlight);
- wake_up(&server->request_q);
+ cifs_add_credits(server, 1);
}
/* cifs_async_readv - send an async write, and set up mid to handle result */
@@ -2110,8 +2113,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
queue_work(system_nrt_wq, &wdata->work);
DeleteMidQEntry(mid);
- atomic_dec(&tcon->ses->server->inFlight);
- wake_up(&tcon->ses->server->request_q);
+ cifs_add_credits(tcon->ses->server, 1);
}
/* cifs_async_writev - send an async write, and set up mid to handle result */
@@ -2649,16 +2651,16 @@ renameRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->OldFileName, fromName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->OldFileName, fromName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
pSMB->OldFileName[name_len] = 0x04; /* pad */
/* protocol requires ASCII signature byte on Unicode string */
pSMB->OldFileName[name_len + 1] = 0x00;
name_len2 =
- cifsConvertToUCS((__le16 *)&pSMB->OldFileName[name_len + 2],
- toName, PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *)&pSMB->OldFileName[name_len+2],
+ toName, PATH_MAX, nls_codepage, remap);
name_len2 += 1 /* trailing null */ + 1 /* Signature word */ ;
name_len2 *= 2; /* convert to bytes */
} else { /* BB improve the check for buffer overruns BB */
@@ -2738,10 +2740,12 @@ int CIFSSMBRenameOpenFile(const int xid, struct cifs_tcon *pTcon,
/* unicode only call */
if (target_name == NULL) {
sprintf(dummy_string, "cifs%x", pSMB->hdr.Mid);
- len_of_str = cifsConvertToUCS((__le16 *)rename_info->target_name,
+ len_of_str =
+ cifsConvertToUTF16((__le16 *)rename_info->target_name,
dummy_string, 24, nls_codepage, remap);
} else {
- len_of_str = cifsConvertToUCS((__le16 *)rename_info->target_name,
+ len_of_str =
+ cifsConvertToUTF16((__le16 *)rename_info->target_name,
target_name, PATH_MAX, nls_codepage,
remap);
}
@@ -2795,17 +2799,17 @@ copyRetry:
pSMB->Flags = cpu_to_le16(flags & COPY_TREE);
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- name_len = cifsConvertToUCS((__le16 *) pSMB->OldFileName,
- fromName, PATH_MAX, nls_codepage,
- remap);
+ name_len = cifsConvertToUTF16((__le16 *) pSMB->OldFileName,
+ fromName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
pSMB->OldFileName[name_len] = 0x04; /* pad */
/* protocol requires ASCII signature byte on Unicode string */
pSMB->OldFileName[name_len + 1] = 0x00;
name_len2 =
- cifsConvertToUCS((__le16 *)&pSMB->OldFileName[name_len + 2],
- toName, PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *)&pSMB->OldFileName[name_len+2],
+ toName, PATH_MAX, nls_codepage, remap);
name_len2 += 1 /* trailing null */ + 1 /* Signature word */ ;
name_len2 *= 2; /* convert to bytes */
} else { /* BB improve the check for buffer overruns BB */
@@ -2861,9 +2865,9 @@ createSymLinkRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifs_strtoUCS((__le16 *) pSMB->FileName, fromName, PATH_MAX
- /* find define for this maxpathcomponent */
- , nls_codepage);
+ cifs_strtoUTF16((__le16 *) pSMB->FileName, fromName,
+ /* find define for this maxpathcomponent */
+ PATH_MAX, nls_codepage);
name_len++; /* trailing null */
name_len *= 2;
@@ -2885,9 +2889,9 @@ createSymLinkRetry:
data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len_target =
- cifs_strtoUCS((__le16 *) data_offset, toName, PATH_MAX
- /* find define for this maxpathcomponent */
- , nls_codepage);
+ cifs_strtoUTF16((__le16 *) data_offset, toName, PATH_MAX
+ /* find define for this maxpathcomponent */
+ , nls_codepage);
name_len_target++; /* trailing null */
name_len_target *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -2949,8 +2953,8 @@ createHardLinkRetry:
return rc;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- name_len = cifsConvertToUCS((__le16 *) pSMB->FileName, toName,
- PATH_MAX, nls_codepage, remap);
+ name_len = cifsConvertToUTF16((__le16 *) pSMB->FileName, toName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
@@ -2972,8 +2976,8 @@ createHardLinkRetry:
data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len_target =
- cifsConvertToUCS((__le16 *) data_offset, fromName, PATH_MAX,
- nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) data_offset, fromName,
+ PATH_MAX, nls_codepage, remap);
name_len_target++; /* trailing null */
name_len_target *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -3042,8 +3046,8 @@ winCreateHardLinkRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->OldFileName, fromName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->OldFileName, fromName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
@@ -3051,8 +3055,8 @@ winCreateHardLinkRetry:
pSMB->OldFileName[name_len] = 0x04;
pSMB->OldFileName[name_len + 1] = 0x00; /* pad */
name_len2 =
- cifsConvertToUCS((__le16 *)&pSMB->OldFileName[name_len + 2],
- toName, PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *)&pSMB->OldFileName[name_len+2],
+ toName, PATH_MAX, nls_codepage, remap);
name_len2 += 1 /* trailing null */ + 1 /* Signature word */ ;
name_len2 *= 2; /* convert to bytes */
} else { /* BB improve the check for buffer overruns BB */
@@ -3108,8 +3112,8 @@ querySymLinkRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifs_strtoUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage);
+ cifs_strtoUTF16((__le16 *) pSMB->FileName, searchName,
+ PATH_MAX, nls_codepage);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -3166,8 +3170,8 @@ querySymLinkRetry:
is_unicode = false;
/* BB FIXME investigate remapping reserved chars here */
- *symlinkinfo = cifs_strndup_from_ucs(data_start, count,
- is_unicode, nls_codepage);
+ *symlinkinfo = cifs_strndup_from_utf16(data_start,
+ count, is_unicode, nls_codepage);
if (!*symlinkinfo)
rc = -ENOMEM;
}
@@ -3450,8 +3454,9 @@ queryAclRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName,
+ searchName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
pSMB->FileName[name_len] = 0;
@@ -3537,8 +3542,8 @@ setAclRetry:
return rc;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -3948,8 +3953,9 @@ QInfRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName,
+ searchName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
} else {
@@ -4086,8 +4092,8 @@ QPathInfoRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, searchName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -4255,8 +4261,8 @@ UnixQPathInfoRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, searchName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -4344,8 +4350,8 @@ findFirstRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, searchName,
+ PATH_MAX, nls_codepage, remap);
/* We can not add the asterik earlier in case
it got remapped to 0xF03A as if it were part of the
directory name instead of a wildcard */
@@ -4656,8 +4662,9 @@ GetInodeNumberRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName,
+ searchName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -4794,9 +4801,9 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
rc = -ENOMEM;
goto parse_DFS_referrals_exit;
}
- cifsConvertToUCS((__le16 *) tmp, searchName,
- PATH_MAX, nls_codepage, remap);
- node->path_consumed = cifs_ucs2_bytes(tmp,
+ cifsConvertToUTF16((__le16 *) tmp, searchName,
+ PATH_MAX, nls_codepage, remap);
+ node->path_consumed = cifs_utf16_bytes(tmp,
le16_to_cpu(pSMBr->PathConsumed),
nls_codepage);
kfree(tmp);
@@ -4809,8 +4816,8 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
/* copy DfsPath */
temp = (char *)ref + le16_to_cpu(ref->DfsPathOffset);
max_len = data_end - temp;
- node->path_name = cifs_strndup_from_ucs(temp, max_len,
- is_unicode, nls_codepage);
+ node->path_name = cifs_strndup_from_utf16(temp, max_len,
+ is_unicode, nls_codepage);
if (!node->path_name) {
rc = -ENOMEM;
goto parse_DFS_referrals_exit;
@@ -4819,8 +4826,8 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
/* copy link target UNC */
temp = (char *)ref + le16_to_cpu(ref->NetworkAddressOffset);
max_len = data_end - temp;
- node->node_name = cifs_strndup_from_ucs(temp, max_len,
- is_unicode, nls_codepage);
+ node->node_name = cifs_strndup_from_utf16(temp, max_len,
+ is_unicode, nls_codepage);
if (!node->node_name)
rc = -ENOMEM;
}
@@ -4873,8 +4880,9 @@ getDFSRetry:
if (ses->capabilities & CAP_UNICODE) {
pSMB->hdr.Flags2 |= SMBFLG2_UNICODE;
name_len =
- cifsConvertToUCS((__le16 *) pSMB->RequestFileName,
- searchName, PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->RequestFileName,
+ searchName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -5506,8 +5514,8 @@ SetEOFRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -5796,8 +5804,8 @@ SetTimesRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -5877,8 +5885,8 @@ SetAttrLgcyRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- ConvertToUCS((__le16 *) pSMB->fileName, fileName,
- PATH_MAX, nls_codepage);
+ ConvertToUTF16((__le16 *) pSMB->fileName, fileName,
+ PATH_MAX, nls_codepage);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -6030,8 +6038,8 @@ setPermsRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -6123,8 +6131,8 @@ QAllEAsRetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
list_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, searchName,
+ PATH_MAX, nls_codepage, remap);
list_len++; /* trailing null */
list_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -6301,8 +6309,8 @@ SetEARetry:
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifsConvertToUCS((__le16 *) pSMB->FileName, fileName,
- PATH_MAX, nls_codepage, remap);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fileName,
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 4666780..5560e1d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -38,6 +38,7 @@
#include <asm/processor.h>
#include <linux/inet.h>
#include <linux/module.h>
+#include <keys/user-type.h>
#include <net/ipv6.h>
#include "cifspdu.h"
#include "cifsglob.h"
@@ -225,74 +226,90 @@ static int check2ndT2(struct smb_hdr *pSMB)
static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
{
- struct smb_t2_rsp *pSMB2 = (struct smb_t2_rsp *)psecond;
+ struct smb_t2_rsp *pSMBs = (struct smb_t2_rsp *)psecond;
struct smb_t2_rsp *pSMBt = (struct smb_t2_rsp *)pTargetSMB;
- char *data_area_of_target;
- char *data_area_of_buf2;
+ char *data_area_of_tgt;
+ char *data_area_of_src;
int remaining;
- unsigned int byte_count, total_in_buf;
- __u16 total_data_size, total_in_buf2;
+ unsigned int byte_count, total_in_tgt;
+ __u16 tgt_total_cnt, src_total_cnt, total_in_src;
- total_data_size = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount);
+ src_total_cnt = get_unaligned_le16(&pSMBs->t2_rsp.TotalDataCount);
+ tgt_total_cnt = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount);
- if (total_data_size !=
- get_unaligned_le16(&pSMB2->t2_rsp.TotalDataCount))
- cFYI(1, "total data size of primary and secondary t2 differ");
+ if (tgt_total_cnt != src_total_cnt)
+ cFYI(1, "total data count of primary and secondary t2 differ "
+ "source=%hu target=%hu", src_total_cnt, tgt_total_cnt);
- total_in_buf = get_unaligned_le16(&pSMBt->t2_rsp.DataCount);
+ total_in_tgt = get_unaligned_le16(&pSMBt->t2_rsp.DataCount);
- remaining = total_data_size - total_in_buf;
+ remaining = tgt_total_cnt - total_in_tgt;
- if (remaining < 0)
+ if (remaining < 0) {
+ cFYI(1, "Server sent too much data. tgt_total_cnt=%hu "
+ "total_in_tgt=%hu", tgt_total_cnt, total_in_tgt);
return -EPROTO;
+ }
- if (remaining == 0) /* nothing to do, ignore */
+ if (remaining == 0) {
+ /* nothing to do, ignore */
+ cFYI(1, "no more data remains");
return 0;
+ }
- total_in_buf2 = get_unaligned_le16(&pSMB2->t2_rsp.DataCount);
- if (remaining < total_in_buf2) {
+ total_in_src = get_unaligned_le16(&pSMBs->t2_rsp.DataCount);
+ if (remaining < total_in_src)
cFYI(1, "transact2 2nd response contains too much data");
- }
/* find end of first SMB data area */
- data_area_of_target = (char *)&pSMBt->hdr.Protocol +
+ data_area_of_tgt = (char *)&pSMBt->hdr.Protocol +
get_unaligned_le16(&pSMBt->t2_rsp.DataOffset);
- /* validate target area */
- data_area_of_buf2 = (char *)&pSMB2->hdr.Protocol +
- get_unaligned_le16(&pSMB2->t2_rsp.DataOffset);
+ /* validate target area */
+ data_area_of_src = (char *)&pSMBs->hdr.Protocol +
+ get_unaligned_le16(&pSMBs->t2_rsp.DataOffset);
- data_area_of_target += total_in_buf;
+ data_area_of_tgt += total_in_tgt;
- /* copy second buffer into end of first buffer */
- total_in_buf += total_in_buf2;
+ total_in_tgt += total_in_src;
/* is the result too big for the field? */
- if (total_in_buf > USHRT_MAX)
+ if (total_in_tgt > USHRT_MAX) {
+ cFYI(1, "coalesced DataCount too large (%u)", total_in_tgt);
return -EPROTO;
- put_unaligned_le16(total_in_buf, &pSMBt->t2_rsp.DataCount);
+ }
+ put_unaligned_le16(total_in_tgt, &pSMBt->t2_rsp.DataCount);
/* fix up the BCC */
byte_count = get_bcc(pTargetSMB);
- byte_count += total_in_buf2;
+ byte_count += total_in_src;
/* is the result too big for the field? */
- if (byte_count > USHRT_MAX)
+ if (byte_count > USHRT_MAX) {
+ cFYI(1, "coalesced BCC too large (%u)", byte_count);
return -EPROTO;
+ }
put_bcc(byte_count, pTargetSMB);
byte_count = be32_to_cpu(pTargetSMB->smb_buf_length);
- byte_count += total_in_buf2;
+ byte_count += total_in_src;
/* don't allow buffer to overflow */
- if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4)
+ if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
+ cFYI(1, "coalesced BCC exceeds buffer size (%u)", byte_count);
return -ENOBUFS;
+ }
pTargetSMB->smb_buf_length = cpu_to_be32(byte_count);
- memcpy(data_area_of_target, data_area_of_buf2, total_in_buf2);
+ /* copy second buffer into end of first buffer */
+ memcpy(data_area_of_tgt, data_area_of_src, total_in_src);
- if (remaining == total_in_buf2) {
- cFYI(1, "found the last secondary response");
- return 0; /* we are done */
- } else /* more responses to go */
+ if (remaining != total_in_src) {
+ /* more responses to go */
+ cFYI(1, "waiting for more secondary responses");
return 1;
+ }
+
+ /* we are done */
+ cFYI(1, "found the last secondary response");
+ return 0;
}
static void
@@ -356,12 +373,22 @@ allocate_buffers(struct TCP_Server_Info *server)
static bool
server_unresponsive(struct TCP_Server_Info *server)
{
- if (echo_retries > 0 && server->tcpStatus == CifsGood &&
- time_after(jiffies, server->lstrp +
- (echo_retries * SMB_ECHO_INTERVAL))) {
+ /*
+ * We need to wait 2 echo intervals to make sure we handle such
+ * situations right:
+ * 1s client sends a normal SMB request
+ * 2s client gets a response
+ * 30s echo workqueue job pops, and decides we got a response recently
+ * and don't need to send another
+ * ...
+ * 65s kernel_recvmsg times out, and we see that we haven't gotten
+ * a response in >60s.
+ */
+ if (server->tcpStatus == CifsGood &&
+ time_after(jiffies, server->lstrp + 2 * SMB_ECHO_INTERVAL)) {
cERROR(1, "Server %s has not responded in %d seconds. "
"Reconnecting...", server->hostname,
- (echo_retries * SMB_ECHO_INTERVAL / HZ));
+ (2 * SMB_ECHO_INTERVAL) / HZ);
cifs_reconnect(server);
wake_up(&server->response_q);
return true;
@@ -625,19 +652,11 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
spin_unlock(&GlobalMid_Lock);
wake_up_all(&server->response_q);
- /*
- * Check if we have blocked requests that need to free. Note that
- * cifs_max_pending is normally 50, but can be set at module install
- * time to as little as two.
- */
- spin_lock(&GlobalMid_Lock);
- if (atomic_read(&server->inFlight) >= cifs_max_pending)
- atomic_set(&server->inFlight, cifs_max_pending - 1);
- /*
- * We do not want to set the max_pending too low or we could end up
- * with the counter going negative.
- */
- spin_unlock(&GlobalMid_Lock);
+ /* check if we have blocked requests that need to free */
+ spin_lock(&server->req_lock);
+ if (server->credits <= 0)
+ server->credits = 1;
+ spin_unlock(&server->req_lock);
/*
* Although there should not be any requests blocked on this queue it
* can not hurt to be paranoid and try to wake up requests that may
@@ -756,10 +775,11 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
cifs_dump_mem("Bad SMB: ", buf,
min_t(unsigned int, server->total_read, 48));
- if (mid)
- handle_mid(mid, server, smb_buffer, length);
+ if (!mid)
+ return length;
- return length;
+ handle_mid(mid, server, smb_buffer, length);
+ return 0;
}
static int
@@ -1578,11 +1598,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
}
- if (vol->multiuser && !(vol->secFlg & CIFSSEC_MAY_KRB5)) {
- cERROR(1, "Multiuser mounts currently require krb5 "
- "authentication!");
+#ifndef CONFIG_KEYS
+ /* Muliuser mounts require CONFIG_KEYS support */
+ if (vol->multiuser) {
+ cERROR(1, "Multiuser mounts require kernels with "
+ "CONFIG_KEYS enabled.");
goto cifs_parse_mount_err;
}
+#endif
if (vol->UNCip == NULL)
vol->UNCip = &vol->UNC[2];
@@ -1888,7 +1911,8 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
tcp_ses->noblocksnd = volume_info->noblocksnd;
tcp_ses->noautotune = volume_info->noautotune;
tcp_ses->tcp_nodelay = volume_info->sockopt_tcp_nodelay;
- atomic_set(&tcp_ses->inFlight, 0);
+ tcp_ses->in_flight = 0;
+ tcp_ses->credits = 1;
init_waitqueue_head(&tcp_ses->response_q);
init_waitqueue_head(&tcp_ses->request_q);
INIT_LIST_HEAD(&tcp_ses->pending_mid_q);
@@ -1981,10 +2005,16 @@ static int match_session(struct cifs_ses *ses, struct smb_vol *vol)
return 0;
break;
default:
+ /* NULL username means anonymous session */
+ if (ses->user_name == NULL) {
+ if (!vol->nullauth)
+ return 0;
+ break;
+ }
+
/* anything else takes username/password */
- if (ses->user_name == NULL)
- return 0;
- if (strncmp(ses->user_name, vol->username,
+ if (strncmp(ses->user_name,
+ vol->username ? vol->username : "",
MAX_USERNAME_SIZE))
return 0;
if (strlen(vol->username) != 0 &&
@@ -2039,6 +2069,132 @@ cifs_put_smb_ses(struct cifs_ses *ses)
cifs_put_tcp_session(server);
}
+#ifdef CONFIG_KEYS
+
+/* strlen("cifs:a:") + INET6_ADDRSTRLEN + 1 */
+#define CIFSCREDS_DESC_SIZE (7 + INET6_ADDRSTRLEN + 1)
+
+/* Populate username and pw fields from keyring if possible */
+static int
+cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses)
+{
+ int rc = 0;
+ char *desc, *delim, *payload;
+ ssize_t len;
+ struct key *key;
+ struct TCP_Server_Info *server = ses->server;
+ struct sockaddr_in *sa;
+ struct sockaddr_in6 *sa6;
+ struct user_key_payload *upayload;
+
+ desc = kmalloc(CIFSCREDS_DESC_SIZE, GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ /* try to find an address key first */
+ switch (server->dstaddr.ss_family) {
+ case AF_INET:
+ sa = (struct sockaddr_in *)&server->dstaddr;
+ sprintf(desc, "cifs:a:%pI4", &sa->sin_addr.s_addr);
+ break;
+ case AF_INET6:
+ sa6 = (struct sockaddr_in6 *)&server->dstaddr;
+ sprintf(desc, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr);
+ break;
+ default:
+ cFYI(1, "Bad ss_family (%hu)", server->dstaddr.ss_family);
+ rc = -EINVAL;
+ goto out_err;
+ }
+
+ cFYI(1, "%s: desc=%s", __func__, desc);
+ key = request_key(&key_type_logon, desc, "");
+ if (IS_ERR(key)) {
+ if (!ses->domainName) {
+ cFYI(1, "domainName is NULL");
+ rc = PTR_ERR(key);
+ goto out_err;
+ }
+
+ /* didn't work, try to find a domain key */
+ sprintf(desc, "cifs:d:%s", ses->domainName);
+ cFYI(1, "%s: desc=%s", __func__, desc);
+ key = request_key(&key_type_logon, desc, "");
+ if (IS_ERR(key)) {
+ rc = PTR_ERR(key);
+ goto out_err;
+ }
+ }
+
+ down_read(&key->sem);
+ upayload = key->payload.data;
+ if (IS_ERR_OR_NULL(upayload)) {
+ rc = upayload ? PTR_ERR(upayload) : -EINVAL;
+ goto out_key_put;
+ }
+
+ /* find first : in payload */
+ payload = (char *)upayload->data;
+ delim = strnchr(payload, upayload->datalen, ':');
+ cFYI(1, "payload=%s", payload);
+ if (!delim) {
+ cFYI(1, "Unable to find ':' in payload (datalen=%d)",
+ upayload->datalen);
+ rc = -EINVAL;
+ goto out_key_put;
+ }
+
+ len = delim - payload;
+ if (len > MAX_USERNAME_SIZE || len <= 0) {
+ cFYI(1, "Bad value from username search (len=%zd)", len);
+ rc = -EINVAL;
+ goto out_key_put;
+ }
+
+ vol->username = kstrndup(payload, len, GFP_KERNEL);
+ if (!vol->username) {
+ cFYI(1, "Unable to allocate %zd bytes for username", len);
+ rc = -ENOMEM;
+ goto out_key_put;
+ }
+ cFYI(1, "%s: username=%s", __func__, vol->username);
+
+ len = key->datalen - (len + 1);
+ if (len > MAX_PASSWORD_SIZE || len <= 0) {
+ cFYI(1, "Bad len for password search (len=%zd)", len);
+ rc = -EINVAL;
+ kfree(vol->username);
+ vol->username = NULL;
+ goto out_key_put;
+ }
+
+ ++delim;
+ vol->password = kstrndup(delim, len, GFP_KERNEL);
+ if (!vol->password) {
+ cFYI(1, "Unable to allocate %zd bytes for password", len);
+ rc = -ENOMEM;
+ kfree(vol->username);
+ vol->username = NULL;
+ goto out_key_put;
+ }
+
+out_key_put:
+ up_read(&key->sem);
+ key_put(key);
+out_err:
+ kfree(desc);
+ cFYI(1, "%s: returning %d", __func__, rc);
+ return rc;
+}
+#else /* ! CONFIG_KEYS */
+static inline int
+cifs_set_cifscreds(struct smb_vol *vol __attribute__((unused)),
+ struct cifs_ses *ses __attribute__((unused)))
+{
+ return -ENOSYS;
+}
+#endif /* CONFIG_KEYS */
+
static bool warned_on_ntlm; /* globals init to false automatically */
static struct cifs_ses *
@@ -2914,18 +3070,33 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
#define CIFS_DEFAULT_IOSIZE (1024 * 1024)
/*
- * Windows only supports a max of 60k reads. Default to that when posix
- * extensions aren't in force.
+ * Windows only supports a max of 60kb reads and 65535 byte writes. Default to
+ * those values when posix extensions aren't in force. In actuality here, we
+ * use 65536 to allow for a write that is a multiple of 4k. Most servers seem
+ * to be ok with the extra byte even though Windows doesn't send writes that
+ * are that large.
+ *
+ * Citation:
+ *
+ * http://blogs.msdn.com/b/openspecification/archive/2009/04/10/smb-maximum-transmit-buffer-size-and-performance-tuning.aspx
*/
#define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024)
+#define CIFS_DEFAULT_NON_POSIX_WSIZE (65536)
static unsigned int
cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info)
{
__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
struct TCP_Server_Info *server = tcon->ses->server;
- unsigned int wsize = pvolume_info->wsize ? pvolume_info->wsize :
- CIFS_DEFAULT_IOSIZE;
+ unsigned int wsize;
+
+ /* start with specified wsize, or default */
+ if (pvolume_info->wsize)
+ wsize = pvolume_info->wsize;
+ else if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_WRITE_CAP))
+ wsize = CIFS_DEFAULT_IOSIZE;
+ else
+ wsize = CIFS_DEFAULT_NON_POSIX_WSIZE;
/* can server support 24-bit write sizes? (via UNIX extensions) */
if (!tcon->unix_ext || !(unix_cap & CIFS_UNIX_LARGE_WRITE_CAP))
@@ -3136,10 +3307,9 @@ cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data,
return -EINVAL;
if (volume_info->nullauth) {
- cFYI(1, "null user");
- volume_info->username = kzalloc(1, GFP_KERNEL);
- if (volume_info->username == NULL)
- return -ENOMEM;
+ cFYI(1, "Anonymous login");
+ kfree(volume_info->username);
+ volume_info->username = NULL;
} else if (volume_info->username) {
/* BB fixme parse for domain name here */
cFYI(1, "Username: %s", volume_info->username);
@@ -3204,7 +3374,7 @@ cifs_ra_pages(struct cifs_sb_info *cifs_sb)
int
cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
{
- int rc = 0;
+ int rc;
int xid;
struct cifs_ses *pSesInfo;
struct cifs_tcon *tcon;
@@ -3231,6 +3401,7 @@ try_mount_again:
FreeXid(xid);
}
#endif
+ rc = 0;
tcon = NULL;
pSesInfo = NULL;
srvTcp = NULL;
@@ -3478,7 +3649,7 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses,
if (ses->capabilities & CAP_UNICODE) {
smb_buffer->Flags2 |= SMBFLG2_UNICODE;
length =
- cifs_strtoUCS((__le16 *) bcc_ptr, tree,
+ cifs_strtoUTF16((__le16 *) bcc_ptr, tree,
6 /* max utf8 char length in bytes */ *
(/* server len*/ + 256 /* share len */), nls_codepage);
bcc_ptr += 2 * length; /* convert num 16 bit words to bytes */
@@ -3533,7 +3704,7 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses,
/* mostly informational -- no need to fail on error here */
kfree(tcon->nativeFileSystem);
- tcon->nativeFileSystem = cifs_strndup_from_ucs(bcc_ptr,
+ tcon->nativeFileSystem = cifs_strndup_from_utf16(bcc_ptr,
bytes_left, is_unicode,
nls_codepage);
@@ -3592,9 +3763,11 @@ int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses)
if (server->maxBuf != 0)
return 0;
+ cifs_set_credits(server, 1);
rc = CIFSSMBNegotiate(xid, ses);
if (rc == -EAGAIN) {
/* retry only once on 1st time connection */
+ cifs_set_credits(server, 1);
rc = CIFSSMBNegotiate(xid, ses);
if (rc == -EAGAIN)
rc = -EHOSTDOWN;
@@ -3657,25 +3830,43 @@ int cifs_setup_session(unsigned int xid, struct cifs_ses *ses,
return rc;
}
+static int
+cifs_set_vol_auth(struct smb_vol *vol, struct cifs_ses *ses)
+{
+ switch (ses->server->secType) {
+ case Kerberos:
+ vol->secFlg = CIFSSEC_MUST_KRB5;
+ return 0;
+ case NTLMv2:
+ vol->secFlg = CIFSSEC_MUST_NTLMV2;
+ break;
+ case NTLM:
+ vol->secFlg = CIFSSEC_MUST_NTLM;
+ break;
+ case RawNTLMSSP:
+ vol->secFlg = CIFSSEC_MUST_NTLMSSP;
+ break;
+ case LANMAN:
+ vol->secFlg = CIFSSEC_MUST_LANMAN;
+ break;
+ }
+
+ return cifs_set_cifscreds(vol, ses);
+}
+
static struct cifs_tcon *
cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid)
{
+ int rc;
struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb);
struct cifs_ses *ses;
struct cifs_tcon *tcon = NULL;
struct smb_vol *vol_info;
- char username[28]; /* big enough for "krb50x" + hex of ULONG_MAX 6+16 */
- /* We used to have this as MAX_USERNAME which is */
- /* way too big now (256 instead of 32) */
vol_info = kzalloc(sizeof(*vol_info), GFP_KERNEL);
- if (vol_info == NULL) {
- tcon = ERR_PTR(-ENOMEM);
- goto out;
- }
+ if (vol_info == NULL)
+ return ERR_PTR(-ENOMEM);
- snprintf(username, sizeof(username), "krb50x%x", fsuid);
- vol_info->username = username;
vol_info->local_nls = cifs_sb->local_nls;
vol_info->linux_uid = fsuid;
vol_info->cred_uid = fsuid;
@@ -3685,8 +3876,11 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid)
vol_info->local_lease = master_tcon->local_lease;
vol_info->no_linux_ext = !master_tcon->unix_ext;
- /* FIXME: allow for other secFlg settings */
- vol_info->secFlg = CIFSSEC_MUST_KRB5;
+ rc = cifs_set_vol_auth(vol_info, master_tcon->ses);
+ if (rc) {
+ tcon = ERR_PTR(rc);
+ goto out;
+ }
/* get a reference for the same TCP session */
spin_lock(&cifs_tcp_ses_lock);
@@ -3709,6 +3903,8 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid)
if (ses->capabilities & CAP_UNIX)
reset_cifs_unix_caps(0, tcon, NULL, vol_info);
out:
+ kfree(vol_info->username);
+ kfree(vol_info->password);
kfree(vol_info);
return tcon;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index df8fecb..d172c8e 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -171,7 +171,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
}
tcon = tlink_tcon(tlink);
- if (enable_oplocks)
+ if (tcon->ses->server->oplocks)
oplock = REQ_OPLOCK;
if (nd)
@@ -492,7 +492,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
{
int xid;
int rc = 0; /* to get around spurious gcc warning, set to zero here */
- __u32 oplock = 0;
+ __u32 oplock;
__u16 fileHandle = 0;
bool posix_open = false;
struct cifs_sb_info *cifs_sb;
@@ -518,6 +518,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
}
pTcon = tlink_tcon(tlink);
+ oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0;
+
/*
* Don't allow the separator character in a path component.
* The VFS will not allow "/", but "\" is allowed by posix.
@@ -584,10 +586,26 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
* If either that or op not supported returned, follow
* the normal lookup.
*/
- if ((rc == 0) || (rc == -ENOENT))
+ switch (rc) {
+ case 0:
+ /*
+ * The server may allow us to open things like
+ * FIFOs, but the client isn't set up to deal
+ * with that. If it's not a regular file, just
+ * close it and proceed as if it were a normal
+ * lookup.
+ */
+ if (newInode && !S_ISREG(newInode->i_mode)) {
+ CIFSSMBClose(xid, pTcon, fileHandle);
+ break;
+ }
+ case -ENOENT:
posix_open = true;
- else if ((rc == -EINVAL) || (rc != -EOPNOTSUPP))
+ case -EOPNOTSUPP:
+ break;
+ default:
pTcon->broken_posix_open = true;
+ }
}
if (!posix_open)
rc = cifs_get_inode_info_unix(&newInode, full_path,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4dd9283..159fcc5 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -380,7 +380,7 @@ int cifs_open(struct inode *inode, struct file *file)
cFYI(1, "inode = 0x%p file flags are 0x%x for %s",
inode, file->f_flags, full_path);
- if (enable_oplocks)
+ if (tcon->ses->server->oplocks)
oplock = REQ_OPLOCK;
else
oplock = 0;
@@ -505,7 +505,7 @@ static int cifs_reopen_file(struct cifsFileInfo *pCifsFile, bool can_flush)
cFYI(1, "inode = 0x%p file flags 0x%x for %s",
inode, pCifsFile->f_flags, full_path);
- if (enable_oplocks)
+ if (tcon->ses->server->oplocks)
oplock = REQ_OPLOCK;
else
oplock = 0;
@@ -920,16 +920,26 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
for (lockp = &inode->i_flock; *lockp != NULL; \
lockp = &(*lockp)->fl_next)
+struct lock_to_push {
+ struct list_head llist;
+ __u64 offset;
+ __u64 length;
+ __u32 pid;
+ __u16 netfid;
+ __u8 type;
+};
+
static int
cifs_push_posix_locks(struct cifsFileInfo *cfile)
{
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct file_lock *flock, **before;
- struct cifsLockInfo *lck, *tmp;
+ unsigned int count = 0, i = 0;
int rc = 0, xid, type;
+ struct list_head locks_to_send, *el;
+ struct lock_to_push *lck, *tmp;
__u64 length;
- struct list_head locks_to_send;
xid = GetXid();
@@ -940,29 +950,56 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
return rc;
}
+ lock_flocks();
+ cifs_for_each_lock(cfile->dentry->d_inode, before) {
+ if ((*before)->fl_flags & FL_POSIX)
+ count++;
+ }
+ unlock_flocks();
+
INIT_LIST_HEAD(&locks_to_send);
+ /*
+ * Allocating count locks is enough because no FL_POSIX locks can be
+ * added to the list while we are holding cinode->lock_mutex that
+ * protects locking operations of this inode.
+ */
+ for (; i < count; i++) {
+ lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
+ if (!lck) {
+ rc = -ENOMEM;
+ goto err_out;
+ }
+ list_add_tail(&lck->llist, &locks_to_send);
+ }
+
+ el = locks_to_send.next;
lock_flocks();
cifs_for_each_lock(cfile->dentry->d_inode, before) {
flock = *before;
+ if ((flock->fl_flags & FL_POSIX) == 0)
+ continue;
+ if (el == &locks_to_send) {
+ /*
+ * The list ended. We don't have enough allocated
+ * structures - something is really wrong.
+ */
+ cERROR(1, "Can't push all brlocks!");
+ break;
+ }
length = 1 + flock->fl_end - flock->fl_start;
if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK)
type = CIFS_RDLCK;
else
type = CIFS_WRLCK;
-
- lck = cifs_lock_init(flock->fl_start, length, type,
- cfile->netfid);
- if (!lck) {
- rc = -ENOMEM;
- goto send_locks;
- }
+ lck = list_entry(el, struct lock_to_push, llist);
lck->pid = flock->fl_pid;
-
- list_add_tail(&lck->llist, &locks_to_send);
+ lck->netfid = cfile->netfid;
+ lck->length = length;
+ lck->type = type;
+ lck->offset = flock->fl_start;
+ el = el->next;
}
-
-send_locks:
unlock_flocks();
list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
@@ -979,11 +1016,18 @@ send_locks:
kfree(lck);
}
+out:
cinode->can_cache_brlcks = false;
mutex_unlock(&cinode->lock_mutex);
FreeXid(xid);
return rc;
+err_out:
+ list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
+ list_del(&lck->llist);
+ kfree(lck);
+ }
+ goto out;
}
static int
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a5f54b7..745da3d 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -534,6 +534,11 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
fattr->cf_mode = S_IFDIR | cifs_sb->mnt_dir_mode;
fattr->cf_dtype = DT_DIR;
+ /*
+ * Server can return wrong NumberOfLinks value for directories
+ * when Unix extensions are disabled - fake it.
+ */
+ fattr->cf_nlink = 2;
} else {
fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode;
fattr->cf_dtype = DT_REG;
@@ -541,9 +546,9 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
/* clear write bits if ATTR_READONLY is set */
if (fattr->cf_cifsattrs & ATTR_READONLY)
fattr->cf_mode &= ~(S_IWUGO);
- }
- fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
+ fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
+ }
fattr->cf_uid = cifs_sb->mnt_uid;
fattr->cf_gid = cifs_sb->mnt_gid;
@@ -1322,7 +1327,6 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
}
/*BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if need
to set uid/gid */
- inc_nlink(inode);
cifs_unix_basic_to_fattr(&fattr, pInfo, cifs_sb);
cifs_fill_uniqueid(inode->i_sb, &fattr);
@@ -1355,7 +1359,6 @@ mkdir_retry_old:
d_drop(direntry);
} else {
mkdir_get_info:
- inc_nlink(inode);
if (pTcon->unix_ext)
rc = cifs_get_inode_info_unix(&newinode, full_path,
inode->i_sb, xid);
@@ -1436,6 +1439,11 @@ mkdir_get_info:
}
}
mkdir_out:
+ /*
+ * Force revalidate to get parent dir info when needed since cached
+ * attributes are invalid now.
+ */
+ CIFS_I(inode)->time = 0;
kfree(full_path);
FreeXid(xid);
cifs_put_tlink(tlink);
@@ -1475,7 +1483,6 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
cifs_put_tlink(tlink);
if (!rc) {
- drop_nlink(inode);
spin_lock(&direntry->d_inode->i_lock);
i_size_write(direntry->d_inode, 0);
clear_nlink(direntry->d_inode);
@@ -1483,12 +1490,15 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
}
cifsInode = CIFS_I(direntry->d_inode);
- cifsInode->time = 0; /* force revalidate to go get info when
- needed */
+ /* force revalidate to go get info when needed */
+ cifsInode->time = 0;
cifsInode = CIFS_I(inode);
- cifsInode->time = 0; /* force revalidate to get parent dir info
- since cached search results now invalid */
+ /*
+ * Force revalidate to get parent dir info when needed since cached
+ * attributes are invalid now.
+ */
+ cifsInode->time = 0;
direntry->d_inode->i_ctime = inode->i_ctime = inode->i_mtime =
current_fs_time(inode->i_sb);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 703ef5c..c273c12 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -690,3 +690,22 @@ backup_cred(struct cifs_sb_info *cifs_sb)
return false;
}
+
+void
+cifs_add_credits(struct TCP_Server_Info *server, const unsigned int add)
+{
+ spin_lock(&server->req_lock);
+ server->credits += add;
+ server->in_flight--;
+ spin_unlock(&server->req_lock);
+ wake_up(&server->request_q);
+}
+
+void
+cifs_set_credits(struct TCP_Server_Info *server, const int val)
+{
+ spin_lock(&server->req_lock);
+ server->credits = val;
+ server->oplocks = val > 1 ? enable_oplocks : false;
+ spin_unlock(&server->req_lock);
+}
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index a090bbe..e2bbc68 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -647,10 +647,11 @@ static int cifs_filldir(char *find_entry, struct file *file, filldir_t filldir,
name.name = scratch_buf;
name.len =
- cifs_from_ucs2((char *)name.name, (__le16 *)de.name,
- UNICODE_NAME_MAX,
- min(de.namelen, (size_t)max_len), nlt,
- cifs_sb->mnt_cifs_flags &
+ cifs_from_utf16((char *)name.name, (__le16 *)de.name,
+ UNICODE_NAME_MAX,
+ min_t(size_t, de.namelen,
+ (size_t)max_len), nlt,
+ cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
name.len -= nls_nullsize(nlt);
} else {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 4ec3ee9..551d0c2 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -167,16 +167,16 @@ unicode_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp)
int bytes_ret = 0;
/* Copy OS version */
- bytes_ret = cifs_strtoUCS((__le16 *)bcc_ptr, "Linux version ", 32,
- nls_cp);
+ bytes_ret = cifs_strtoUTF16((__le16 *)bcc_ptr, "Linux version ", 32,
+ nls_cp);
bcc_ptr += 2 * bytes_ret;
- bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, init_utsname()->release,
- 32, nls_cp);
+ bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, init_utsname()->release,
+ 32, nls_cp);
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* trailing null */
- bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, CIFS_NETWORK_OPSYS,
- 32, nls_cp);
+ bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, CIFS_NETWORK_OPSYS,
+ 32, nls_cp);
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* trailing null */
@@ -197,8 +197,8 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
*(bcc_ptr+1) = 0;
bytes_ret = 0;
} else
- bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->domainName,
- 256, nls_cp);
+ bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->domainName,
+ 256, nls_cp);
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* account for null terminator */
@@ -226,8 +226,8 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
*bcc_ptr = 0;
*(bcc_ptr+1) = 0;
} else {
- bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->user_name,
- MAX_USERNAME_SIZE, nls_cp);
+ bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->user_name,
+ MAX_USERNAME_SIZE, nls_cp);
}
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* account for null termination */
@@ -246,16 +246,15 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
/* copy user */
/* BB what about null user mounts - check that we do this BB */
/* copy user */
- if (ses->user_name != NULL)
+ if (ses->user_name != NULL) {
strncpy(bcc_ptr, ses->user_name, MAX_USERNAME_SIZE);
+ bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE);
+ }
/* else null user mount */
-
- bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE);
*bcc_ptr = 0;
bcc_ptr++; /* account for null termination */
/* copy domain */
-
if (ses->domainName != NULL) {
strncpy(bcc_ptr, ses->domainName, 256);
bcc_ptr += strnlen(ses->domainName, 256);
@@ -287,7 +286,7 @@ decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifs_ses *ses,
cFYI(1, "bleft %d", bleft);
kfree(ses->serverOS);
- ses->serverOS = cifs_strndup_from_ucs(data, bleft, true, nls_cp);
+ ses->serverOS = cifs_strndup_from_utf16(data, bleft, true, nls_cp);
cFYI(1, "serverOS=%s", ses->serverOS);
len = (UniStrnlen((wchar_t *) data, bleft / 2) * 2) + 2;
data += len;
@@ -296,7 +295,7 @@ decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifs_ses *ses,
return;
kfree(ses->serverNOS);
- ses->serverNOS = cifs_strndup_from_ucs(data, bleft, true, nls_cp);
+ ses->serverNOS = cifs_strndup_from_utf16(data, bleft, true, nls_cp);
cFYI(1, "serverNOS=%s", ses->serverNOS);
len = (UniStrnlen((wchar_t *) data, bleft / 2) * 2) + 2;
data += len;
@@ -305,7 +304,7 @@ decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifs_ses *ses,
return;
kfree(ses->serverDomain);
- ses->serverDomain = cifs_strndup_from_ucs(data, bleft, true, nls_cp);
+ ses->serverDomain = cifs_strndup_from_utf16(data, bleft, true, nls_cp);
cFYI(1, "serverDomain=%s", ses->serverDomain);
return;
@@ -395,6 +394,10 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags);
tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset);
tilen = le16_to_cpu(pblob->TargetInfoArray.Length);
+ if (tioffset > blob_len || tioffset + tilen > blob_len) {
+ cERROR(1, "tioffset + tilen too high %u + %u", tioffset, tilen);
+ return -EINVAL;
+ }
if (tilen) {
ses->auth_key.response = kmalloc(tilen, GFP_KERNEL);
if (!ses->auth_key.response) {
@@ -502,8 +505,8 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
tmp += 2;
} else {
int len;
- len = cifs_strtoUCS((__le16 *)tmp, ses->domainName,
- MAX_USERNAME_SIZE, nls_cp);
+ len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
+ MAX_USERNAME_SIZE, nls_cp);
len *= 2; /* unicode is 2 bytes each */
sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
sec_blob->DomainName.Length = cpu_to_le16(len);
@@ -518,8 +521,8 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
tmp += 2;
} else {
int len;
- len = cifs_strtoUCS((__le16 *)tmp, ses->user_name,
- MAX_USERNAME_SIZE, nls_cp);
+ len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
+ MAX_USERNAME_SIZE, nls_cp);
len *= 2; /* unicode is 2 bytes each */
sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
sec_blob->UserName.Length = cpu_to_le16(len);
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 80d8508..d5cd9aa 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -213,7 +213,7 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16,
/* Password cannot be longer than 128 characters */
if (passwd) /* Password must be converted to NT unicode */
- len = cifs_strtoUCS(wpwd, passwd, 128, codepage);
+ len = cifs_strtoUTF16(wpwd, passwd, 128, codepage);
else {
len = 0;
*wpwd = 0; /* Ensure string is null terminated */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 0cc9584..310918b 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -254,44 +254,60 @@ smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer,
return smb_sendv(server, &iov, 1);
}
-static int wait_for_free_request(struct TCP_Server_Info *server,
- const int long_op)
+static int
+wait_for_free_credits(struct TCP_Server_Info *server, const int optype,
+ int *credits)
{
- if (long_op == CIFS_ASYNC_OP) {
+ int rc;
+
+ spin_lock(&server->req_lock);
+ if (optype == CIFS_ASYNC_OP) {
/* oplock breaks must not be held up */
- atomic_inc(&server->inFlight);
+ server->in_flight++;
+ *credits -= 1;
+ spin_unlock(&server->req_lock);
return 0;
}
- spin_lock(&GlobalMid_Lock);
while (1) {
- if (atomic_read(&server->inFlight) >= cifs_max_pending) {
- spin_unlock(&GlobalMid_Lock);
+ if (*credits <= 0) {
+ spin_unlock(&server->req_lock);
cifs_num_waiters_inc(server);
- wait_event(server->request_q,
- atomic_read(&server->inFlight)
- < cifs_max_pending);
+ rc = wait_event_killable(server->request_q,
+ has_credits(server, credits));
cifs_num_waiters_dec(server);
- spin_lock(&GlobalMid_Lock);
+ if (rc)
+ return rc;
+ spin_lock(&server->req_lock);
} else {
if (server->tcpStatus == CifsExiting) {
- spin_unlock(&GlobalMid_Lock);
+ spin_unlock(&server->req_lock);
return -ENOENT;
}
- /* can not count locking commands against total
- as they are allowed to block on server */
+ /*
+ * Can not count locking commands against total
+ * as they are allowed to block on server.
+ */
/* update # of requests on the wire to server */
- if (long_op != CIFS_BLOCKING_OP)
- atomic_inc(&server->inFlight);
- spin_unlock(&GlobalMid_Lock);
+ if (optype != CIFS_BLOCKING_OP) {
+ *credits -= 1;
+ server->in_flight++;
+ }
+ spin_unlock(&server->req_lock);
break;
}
}
return 0;
}
+static int
+wait_for_free_request(struct TCP_Server_Info *server, const int optype)
+{
+ return wait_for_free_credits(server, optype, get_credits_field(server));
+}
+
static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf,
struct mid_q_entry **ppmidQ)
{
@@ -359,7 +375,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
mid = AllocMidQEntry(hdr, server);
if (mid == NULL) {
mutex_unlock(&server->srv_mutex);
- atomic_dec(&server->inFlight);
+ cifs_add_credits(server, 1);
wake_up(&server->request_q);
return -ENOMEM;
}
@@ -392,7 +408,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
return rc;
out_err:
delete_mid(mid);
- atomic_dec(&server->inFlight);
+ cifs_add_credits(server, 1);
wake_up(&server->request_q);
return rc;
}
@@ -564,8 +580,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
mutex_unlock(&ses->server->srv_mutex);
cifs_small_buf_release(in_buf);
/* Update # of requests on wire to server */
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
rc = cifs_sign_smb2(iov, n_vec, ses->server, &midQ->sequence_number);
@@ -601,8 +616,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
cifs_small_buf_release(in_buf);
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
spin_unlock(&GlobalMid_Lock);
@@ -612,8 +626,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
rc = cifs_sync_mid_result(midQ, ses->server);
if (rc != 0) {
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
@@ -637,8 +650,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
midQ->resp_buf = NULL;
out:
delete_mid(midQ);
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
@@ -688,8 +700,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
if (rc) {
mutex_unlock(&ses->server->srv_mutex);
/* Update # of requests on wire to server */
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
@@ -721,8 +732,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
/* no longer considered to be "in-flight" */
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
spin_unlock(&GlobalMid_Lock);
@@ -730,8 +740,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
rc = cifs_sync_mid_result(midQ, ses->server);
if (rc != 0) {
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
@@ -747,8 +756,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
rc = cifs_check_receive(midQ, ses->server, 0);
out:
delete_mid(midQ);
- atomic_dec(&ses->server->inFlight);
- wake_up(&ses->server->request_q);
+ cifs_add_credits(ses->server, 1);
return rc;
}
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 45f07c4..10d92cf 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -105,7 +105,6 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
struct cifs_tcon *pTcon;
struct super_block *sb;
char *full_path;
- struct cifs_ntsd *pacl;
if (direntry == NULL)
return -EIO;
@@ -164,23 +163,24 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
+#ifdef CONFIG_CIFS_ACL
+ struct cifs_ntsd *pacl;
pacl = kmalloc(value_size, GFP_KERNEL);
if (!pacl) {
cFYI(1, "%s: Can't allocate memory for ACL",
__func__);
rc = -ENOMEM;
} else {
-#ifdef CONFIG_CIFS_ACL
memcpy(pacl, ea_value, value_size);
rc = set_cifs_acl(pacl, value_size,
direntry->d_inode, full_path, CIFS_ACL_DACL);
if (rc == 0) /* force revalidate of the inode */
CIFS_I(direntry->d_inode)->time = 0;
kfree(pacl);
+ }
#else
cFYI(1, "Set CIFS ACL not supported yet");
#endif /* CONFIG_CIFS_ACL */
- }
} else {
int temp;
temp = strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 5e2e1b3..05156c1 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -208,13 +208,12 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
if (IS_ERR(root)) {
error = PTR_ERR(root);
printk("Failure of coda_cnode_make for root: error %d\n", error);
- root = NULL;
goto error;
}
printk("coda_read_super: rootinode is %ld dev %s\n",
root->i_ino, root->i_sb->s_id);
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
error = -EINVAL;
goto error;
@@ -222,9 +221,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
return 0;
error:
- if (root)
- iput(root);
-
mutex_lock(&vc->vc_mutex);
bdi_destroy(&vc->bdi);
vc->vc_sb = NULL;
diff --git a/fs/compat.c b/fs/compat.c
index fa9d721..14483a7 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -33,7 +33,6 @@
#include <linux/nfs4_mount.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>
-#include <linux/module.h>
#include <linux/dirent.h>
#include <linux/fsnotify.h>
#include <linux/highuid.h>
@@ -131,41 +130,35 @@ asmlinkage long compat_sys_utimes(const char __user *filename, struct compat_tim
static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
{
- compat_ino_t ino = stat->ino;
- typeof(ubuf->st_uid) uid = 0;
- typeof(ubuf->st_gid) gid = 0;
- int err;
+ struct compat_stat tmp;
- SET_UID(uid, stat->uid);
- SET_GID(gid, stat->gid);
+ if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
+ return -EOVERFLOW;
- if ((u64) stat->size > MAX_NON_LFS ||
- !old_valid_dev(stat->dev) ||
- !old_valid_dev(stat->rdev))
+ memset(&tmp, 0, sizeof(tmp));
+ tmp.st_dev = old_encode_dev(stat->dev);
+ tmp.st_ino = stat->ino;
+ if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
return -EOVERFLOW;
- if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino)
+ tmp.st_mode = stat->mode;
+ tmp.st_nlink = stat->nlink;
+ if (tmp.st_nlink != stat->nlink)
return -EOVERFLOW;
-
- if (clear_user(ubuf, sizeof(*ubuf)))
- return -EFAULT;
-
- err = __put_user(old_encode_dev(stat->dev), &ubuf->st_dev);
- err |= __put_user(ino, &ubuf->st_ino);
- err |= __put_user(stat->mode, &ubuf->st_mode);
- err |= __put_user(stat->nlink, &ubuf->st_nlink);
- err |= __put_user(uid, &ubuf->st_uid);
- err |= __put_user(gid, &ubuf->st_gid);
- err |= __put_user(old_encode_dev(stat->rdev), &ubuf->st_rdev);
- err |= __put_user(stat->size, &ubuf->st_size);
- err |= __put_user(stat->atime.tv_sec, &ubuf->st_atime);
- err |= __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec);
- err |= __put_user(stat->mtime.tv_sec, &ubuf->st_mtime);
- err |= __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec);
- err |= __put_user(stat->ctime.tv_sec, &ubuf->st_ctime);
- err |= __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec);
- err |= __put_user(stat->blksize, &ubuf->st_blksize);
- err |= __put_user(stat->blocks, &ubuf->st_blocks);
- return err;
+ SET_UID(tmp.st_uid, stat->uid);
+ SET_GID(tmp.st_gid, stat->gid);
+ tmp.st_rdev = old_encode_dev(stat->rdev);
+ if ((u64) stat->size > MAX_NON_LFS)
+ return -EOVERFLOW;
+ tmp.st_size = stat->size;
+ tmp.st_atime = stat->atime.tv_sec;
+ tmp.st_atime_nsec = stat->atime.tv_nsec;
+ tmp.st_mtime = stat->mtime.tv_sec;
+ tmp.st_mtime_nsec = stat->mtime.tv_nsec;
+ tmp.st_ctime = stat->ctime.tv_sec;
+ tmp.st_ctime_nsec = stat->ctime.tv_nsec;
+ tmp.st_blocks = stat->blocks;
+ tmp.st_blksize = stat->blksize;
+ return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}
asmlinkage long compat_sys_newstat(const char __user * filename,
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index a26bea1..debdfe0 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -34,7 +34,7 @@
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/ppp_defs.h>
-#include <linux/if_ppp.h>
+#include <linux/ppp-ioctl.h>
#include <linux/if_pppox.h>
#include <linux/mtio.h>
#include <linux/auto_fs.h>
@@ -49,7 +49,6 @@
#include <linux/elevator.h>
#include <linux/rtc.h>
#include <linux/pci.h>
-#include <linux/module.h>
#include <linux/serial.h>
#include <linux/if_tun.h>
#include <linux/ctype.h>
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index ede857d..b5f0a3b 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -58,12 +58,11 @@ struct configfs_dirent {
extern struct mutex configfs_symlink_mutex;
extern spinlock_t configfs_dirent_lock;
-extern struct vfsmount * configfs_mount;
extern struct kmem_cache *configfs_dir_cachep;
extern int configfs_is_root(struct config_item *item);
-extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *);
+extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *);
extern int configfs_create(struct dentry *, umode_t mode, int (*init)(struct inode *));
extern int configfs_inode_init(void);
extern void configfs_inode_exit(void);
@@ -80,15 +79,15 @@ extern const unsigned char * configfs_get_name(struct configfs_dirent *sd);
extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent);
extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr);
-extern int configfs_pin_fs(void);
+extern struct dentry *configfs_pin_fs(void);
extern void configfs_release_fs(void);
extern struct rw_semaphore configfs_rename_sem;
-extern struct super_block * configfs_sb;
extern const struct file_operations configfs_dir_operations;
extern const struct file_operations configfs_file_operations;
extern const struct file_operations bin_fops;
extern const struct inode_operations configfs_dir_inode_operations;
+extern const struct inode_operations configfs_root_inode_operations;
extern const struct inode_operations configfs_symlink_inode_operations;
extern const struct dentry_operations configfs_dentry_ops;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 5ddd7eb..7e6c52d 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -264,11 +264,13 @@ static int init_symlink(struct inode * inode)
return 0;
}
-static int create_dir(struct config_item * k, struct dentry * p,
- struct dentry * d)
+static int create_dir(struct config_item *k, struct dentry *d)
{
int error;
umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
+ struct dentry *p = d->d_parent;
+
+ BUG_ON(!k);
error = configfs_dirent_exists(p->d_fsdata, d->d_name.name);
if (!error)
@@ -304,19 +306,7 @@ static int create_dir(struct config_item * k, struct dentry * p,
static int configfs_create_dir(struct config_item * item, struct dentry *dentry)
{
- struct dentry * parent;
- int error = 0;
-
- BUG_ON(!item);
-
- if (item->ci_parent)
- parent = item->ci_parent->ci_dentry;
- else if (configfs_mount)
- parent = configfs_mount->mnt_root;
- else
- return -EFAULT;
-
- error = create_dir(item,parent,dentry);
+ int error = create_dir(item, dentry);
if (!error)
item->ci_dentry = dentry;
return error;
@@ -1079,23 +1069,24 @@ int configfs_depend_item(struct configfs_subsystem *subsys,
int ret;
struct configfs_dirent *p, *root_sd, *subsys_sd = NULL;
struct config_item *s_item = &subsys->su_group.cg_item;
+ struct dentry *root;
/*
* Pin the configfs filesystem. This means we can safely access
* the root of the configfs filesystem.
*/
- ret = configfs_pin_fs();
- if (ret)
- return ret;
+ root = configfs_pin_fs();
+ if (IS_ERR(root))
+ return PTR_ERR(root);
/*
* Next, lock the root directory. We're going to check that the
* subsystem is really registered, and so we need to lock out
* configfs_[un]register_subsystem().
*/
- mutex_lock(&configfs_sb->s_root->d_inode->i_mutex);
+ mutex_lock(&root->d_inode->i_mutex);
- root_sd = configfs_sb->s_root->d_fsdata;
+ root_sd = root->d_fsdata;
list_for_each_entry(p, &root_sd->s_children, s_sibling) {
if (p->s_type & CONFIGFS_DIR) {
@@ -1129,7 +1120,7 @@ int configfs_depend_item(struct configfs_subsystem *subsys,
out_unlock_dirent_lock:
spin_unlock(&configfs_dirent_lock);
out_unlock_fs:
- mutex_unlock(&configfs_sb->s_root->d_inode->i_mutex);
+ mutex_unlock(&root->d_inode->i_mutex);
/*
* If we succeeded, the fs is pinned via other methods. If not,
@@ -1183,11 +1174,6 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
struct module *subsys_owner = NULL, *new_item_owner = NULL;
char *name;
- if (dentry->d_parent == configfs_sb->s_root) {
- ret = -EPERM;
- goto out;
- }
-
sd = dentry->d_parent->d_fsdata;
/*
@@ -1359,9 +1345,6 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
struct module *subsys_owner = NULL, *dead_item_owner = NULL;
int ret;
- if (dentry->d_parent == configfs_sb->s_root)
- return -EPERM;
-
sd = dentry->d_fsdata;
if (sd->s_type & CONFIGFS_USET_DEFAULT)
return -EPERM;
@@ -1459,6 +1442,11 @@ const struct inode_operations configfs_dir_inode_operations = {
.setattr = configfs_setattr,
};
+const struct inode_operations configfs_root_inode_operations = {
+ .lookup = configfs_lookup,
+ .setattr = configfs_setattr,
+};
+
#if 0
int configfs_rename_dir(struct config_item * item, const char *new_name)
{
@@ -1546,6 +1534,7 @@ static inline unsigned char dt_type(struct configfs_dirent *sd)
static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
struct dentry *dentry = filp->f_path.dentry;
+ struct super_block *sb = dentry->d_sb;
struct configfs_dirent * parent_sd = dentry->d_fsdata;
struct configfs_dirent *cursor = filp->private_data;
struct list_head *p, *q = &cursor->s_sibling;
@@ -1608,7 +1597,7 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
ino = inode->i_ino;
spin_unlock(&configfs_dirent_lock);
if (!inode)
- ino = iunique(configfs_sb, 2);
+ ino = iunique(sb, 2);
if (filldir(dirent, name, len, filp->f_pos, ino,
dt_type(next)) < 0)
@@ -1680,27 +1669,27 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
struct config_group *group = &subsys->su_group;
struct qstr name;
struct dentry *dentry;
+ struct dentry *root;
struct configfs_dirent *sd;
- err = configfs_pin_fs();
- if (err)
- return err;
+ root = configfs_pin_fs();
+ if (IS_ERR(root))
+ return PTR_ERR(root);
if (!group->cg_item.ci_name)
group->cg_item.ci_name = group->cg_item.ci_namebuf;
- sd = configfs_sb->s_root->d_fsdata;
+ sd = root->d_fsdata;
link_group(to_config_group(sd->s_element), group);
- mutex_lock_nested(&configfs_sb->s_root->d_inode->i_mutex,
- I_MUTEX_PARENT);
+ mutex_lock_nested(&root->d_inode->i_mutex, I_MUTEX_PARENT);
name.name = group->cg_item.ci_name;
name.len = strlen(name.name);
name.hash = full_name_hash(name.name, name.len);
err = -ENOMEM;
- dentry = d_alloc(configfs_sb->s_root, &name);
+ dentry = d_alloc(root, &name);
if (dentry) {
d_add(dentry, NULL);
@@ -1717,7 +1706,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
}
}
- mutex_unlock(&configfs_sb->s_root->d_inode->i_mutex);
+ mutex_unlock(&root->d_inode->i_mutex);
if (err) {
unlink_group(group);
@@ -1731,13 +1720,14 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
{
struct config_group *group = &subsys->su_group;
struct dentry *dentry = group->cg_item.ci_dentry;
+ struct dentry *root = dentry->d_sb->s_root;
- if (dentry->d_parent != configfs_sb->s_root) {
+ if (dentry->d_parent != root) {
printk(KERN_ERR "configfs: Tried to unregister non-subsystem!\n");
return;
}
- mutex_lock_nested(&configfs_sb->s_root->d_inode->i_mutex,
+ mutex_lock_nested(&root->d_inode->i_mutex,
I_MUTEX_PARENT);
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
mutex_lock(&configfs_symlink_mutex);
@@ -1754,7 +1744,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
d_delete(dentry);
- mutex_unlock(&configfs_sb->s_root->d_inode->i_mutex);
+ mutex_unlock(&root->d_inode->i_mutex);
dput(dentry);
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 3ee36d4..0074362 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -44,8 +44,6 @@
static struct lock_class_key default_group_class[MAX_LOCK_DEPTH];
#endif
-extern struct super_block * configfs_sb;
-
static const struct address_space_operations configfs_aops = {
.readpage = simple_readpage,
.write_begin = simple_write_begin,
@@ -132,9 +130,10 @@ static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
inode->i_ctime = iattr->ia_ctime;
}
-struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent * sd)
+struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
+ struct super_block *s)
{
- struct inode * inode = new_inode(configfs_sb);
+ struct inode * inode = new_inode(s);
if (inode) {
inode->i_ino = get_next_ino();
inode->i_mapping->a_ops = &configfs_aops;
@@ -188,36 +187,35 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
int configfs_create(struct dentry * dentry, umode_t mode, int (*init)(struct inode *))
{
int error = 0;
- struct inode * inode = NULL;
- if (dentry) {
- if (!dentry->d_inode) {
- struct configfs_dirent *sd = dentry->d_fsdata;
- if ((inode = configfs_new_inode(mode, sd))) {
- if (dentry->d_parent && dentry->d_parent->d_inode) {
- struct inode *p_inode = dentry->d_parent->d_inode;
- p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
- }
- configfs_set_inode_lock_class(sd, inode);
- goto Proceed;
- }
- else
- error = -ENOMEM;
- } else
- error = -EEXIST;
- } else
- error = -ENOENT;
- goto Done;
+ struct inode *inode = NULL;
+ struct configfs_dirent *sd;
+ struct inode *p_inode;
+
+ if (!dentry)
+ return -ENOENT;
+
+ if (dentry->d_inode)
+ return -EEXIST;
- Proceed:
- if (init)
+ sd = dentry->d_fsdata;
+ inode = configfs_new_inode(mode, sd, dentry->d_sb);
+ if (!inode)
+ return -ENOMEM;
+
+ p_inode = dentry->d_parent->d_inode;
+ p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
+ configfs_set_inode_lock_class(sd, inode);
+
+ if (init) {
error = init(inode);
- if (!error) {
- d_instantiate(dentry, inode);
- if (S_ISDIR(mode) || S_ISLNK(mode))
- dget(dentry); /* pin link and directory dentries in core */
- } else
- iput(inode);
- Done:
+ if (error) {
+ iput(inode);
+ return error;
+ }
+ }
+ d_instantiate(dentry, inode);
+ if (S_ISDIR(mode) || S_ISLNK(mode))
+ dget(dentry); /* pin link and directory dentries in core */
return error;
}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 276e15c..aee0a7e 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -37,8 +37,7 @@
/* Random magic number */
#define CONFIGFS_MAGIC 0x62656570
-struct vfsmount * configfs_mount = NULL;
-struct super_block * configfs_sb = NULL;
+static struct vfsmount *configfs_mount = NULL;
struct kmem_cache *configfs_dir_cachep;
static int configfs_mnt_count = 0;
@@ -77,12 +76,11 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_magic = CONFIGFS_MAGIC;
sb->s_op = &configfs_ops;
sb->s_time_gran = 1;
- configfs_sb = sb;
inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
- &configfs_root);
+ &configfs_root, sb);
if (inode) {
- inode->i_op = &configfs_dir_inode_operations;
+ inode->i_op = &configfs_root_inode_operations;
inode->i_fop = &configfs_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
@@ -91,10 +89,9 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
return -ENOMEM;
}
- root = d_alloc_root(inode);
+ root = d_make_root(inode);
if (!root) {
pr_debug("%s: could not get root dentry!\n",__func__);
- iput(inode);
return -ENOMEM;
}
config_group_init(&configfs_root_group);
@@ -118,10 +115,11 @@ static struct file_system_type configfs_fs_type = {
.kill_sb = kill_litter_super,
};
-int configfs_pin_fs(void)
+struct dentry *configfs_pin_fs(void)
{
- return simple_pin_fs(&configfs_fs_type, &configfs_mount,
+ int err = simple_pin_fs(&configfs_fs_type, &configfs_mount,
&configfs_mnt_count);
+ return err ? ERR_PTR(err) : configfs_mount->mnt_root;
}
void configfs_release_fs(void)
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 0f3eb41..cc9f254 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -110,13 +110,13 @@ out:
static int get_target(const char *symname, struct path *path,
- struct config_item **target)
+ struct config_item **target, struct super_block *sb)
{
int ret;
ret = kern_path(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, path);
if (!ret) {
- if (path->dentry->d_sb == configfs_sb) {
+ if (path->dentry->d_sb == sb) {
*target = configfs_get_config_item(path->dentry);
if (!*target) {
ret = -ENOENT;
@@ -141,10 +141,6 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna
struct config_item *target_item = NULL;
struct config_item_type *type;
- ret = -EPERM; /* What lack-of-symlink returns */
- if (dentry->d_parent == configfs_sb->s_root)
- goto out;
-
sd = dentry->d_parent->d_fsdata;
/*
* Fake invisibility if dir belongs to a group/default groups hierarchy
@@ -162,7 +158,7 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna
!type->ct_item_ops->allow_link)
goto out_put;
- ret = get_target(symname, &path, &target_item);
+ ret = get_target(symname, &path, &target_item, dentry->d_sb);
if (ret)
goto out_put;
@@ -198,8 +194,6 @@ int configfs_unlink(struct inode *dir, struct dentry *dentry)
if (!(sd->s_type & CONFIGFS_ITEM_LINK))
goto out;
- BUG_ON(dentry->d_parent == configfs_sb->s_root);
-
sl = sd->s_element;
parent_item = configfs_get_config_item(dentry->d_parent);
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index a2ee8f9..d013c46 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -257,10 +257,10 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
/* Do sanity checks on the superblock */
if (super.magic != CRAMFS_MAGIC) {
- /* check for wrong endianess */
+ /* check for wrong endianness */
if (super.magic == CRAMFS_MAGIC_WEND) {
if (!silent)
- printk(KERN_ERR "cramfs: wrong endianess\n");
+ printk(KERN_ERR "cramfs: wrong endianness\n");
goto out;
}
@@ -270,7 +270,7 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
mutex_unlock(&read_mutex);
if (super.magic != CRAMFS_MAGIC) {
if (super.magic == CRAMFS_MAGIC_WEND && !silent)
- printk(KERN_ERR "cramfs: wrong endianess\n");
+ printk(KERN_ERR "cramfs: wrong endianness\n");
else if (!silent)
printk(KERN_ERR "cramfs: wrong magic\n");
goto out;
@@ -318,11 +318,9 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
root = get_cramfs_inode(sb, &super.root, 0);
if (IS_ERR(root))
goto out;
- sb->s_root = d_alloc_root(root);
- if (!sb->s_root) {
- iput(root);
+ sb->s_root = d_make_root(root);
+ if (!sb->s_root)
goto out;
- }
return 0;
out:
kfree(sbi);
diff --git a/fs/dcache.c b/fs/dcache.c
index 16a53cc..b60ddc4 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -23,7 +23,7 @@
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/cache.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <asm/uaccess.h>
@@ -104,11 +104,11 @@ static unsigned int d_hash_shift __read_mostly;
static struct hlist_bl_head *dentry_hashtable __read_mostly;
-static inline struct hlist_bl_head *d_hash(struct dentry *parent,
- unsigned long hash)
+static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
+ unsigned int hash)
{
- hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
- hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
+ hash += (unsigned long) parent / L1_CACHE_BYTES;
+ hash = hash + (hash >> D_HASHBITS);
return dentry_hashtable + (hash & D_HASHMASK);
}
@@ -137,6 +137,49 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
}
#endif
+/*
+ * Compare 2 name strings, return 0 if they match, otherwise non-zero.
+ * The strings are both count bytes long, and count is non-zero.
+ */
+static inline int dentry_cmp(const unsigned char *cs, size_t scount,
+ const unsigned char *ct, size_t tcount)
+{
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+ unsigned long a,b,mask;
+
+ if (unlikely(scount != tcount))
+ return 1;
+
+ for (;;) {
+ a = *(unsigned long *)cs;
+ b = *(unsigned long *)ct;
+ if (tcount < sizeof(unsigned long))
+ break;
+ if (unlikely(a != b))
+ return 1;
+ cs += sizeof(unsigned long);
+ ct += sizeof(unsigned long);
+ tcount -= sizeof(unsigned long);
+ if (!tcount)
+ return 0;
+ }
+ mask = ~(~0ul << tcount*8);
+ return unlikely(!!((a ^ b) & mask));
+#else
+ if (scount != tcount)
+ return 1;
+
+ do {
+ if (*cs != *ct)
+ return 1;
+ cs++;
+ ct++;
+ tcount--;
+ } while (tcount);
+ return 0;
+#endif
+}
+
static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
@@ -1423,30 +1466,6 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
EXPORT_SYMBOL(d_instantiate_unique);
-/**
- * d_alloc_root - allocate root dentry
- * @root_inode: inode to allocate the root for
- *
- * Allocate a root ("/") dentry for the inode given. The inode is
- * instantiated and returned. %NULL is returned if there is insufficient
- * memory or the inode passed is %NULL.
- */
-
-struct dentry * d_alloc_root(struct inode * root_inode)
-{
- struct dentry *res = NULL;
-
- if (root_inode) {
- static const struct qstr name = { .name = "/", .len = 1 };
-
- res = __d_alloc(root_inode->i_sb, &name);
- if (res)
- d_instantiate(res, root_inode);
- }
- return res;
-}
-EXPORT_SYMBOL(d_alloc_root);
-
struct dentry *d_make_root(struct inode *root_inode)
{
struct dentry *res = NULL;
@@ -1694,7 +1713,7 @@ EXPORT_SYMBOL(d_add_ci);
* __d_lookup_rcu - search for a dentry (racy, store-free)
* @parent: parent dentry
* @name: qstr of name we wish to find
- * @seq: returns d_seq value at the point where the dentry was found
+ * @seqp: returns d_seq value at the point where the dentry was found
* @inode: returns dentry->d_inode when the inode was found valid.
* Returns: dentry, or NULL
*
@@ -1717,8 +1736,9 @@ EXPORT_SYMBOL(d_add_ci);
* child is looked up. Thus, an interlocking stepping of sequence lock checks
* is formed, giving integrity down the path walk.
*/
-struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
- unsigned *seq, struct inode **inode)
+struct dentry *__d_lookup_rcu(const struct dentry *parent,
+ const struct qstr *name,
+ unsigned *seqp, struct inode **inode)
{
unsigned int len = name->len;
unsigned int hash = name->hash;
@@ -1748,6 +1768,7 @@ struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
* See Documentation/filesystems/path-lookup.txt for more details.
*/
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
+ unsigned seq;
struct inode *i;
const char *tname;
int tlen;
@@ -1756,7 +1777,7 @@ struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
continue;
seqretry:
- *seq = read_seqcount_begin(&dentry->d_seq);
+ seq = read_seqcount_begin(&dentry->d_seq);
if (dentry->d_parent != parent)
continue;
if (d_unhashed(dentry))
@@ -1771,7 +1792,7 @@ seqretry:
* edge of memory when walking. If we could load this
* atomically some other way, we could drop this check.
*/
- if (read_seqcount_retry(&dentry->d_seq, *seq))
+ if (read_seqcount_retry(&dentry->d_seq, seq))
goto seqretry;
if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
if (parent->d_op->d_compare(parent, *inode,
@@ -1788,6 +1809,7 @@ seqretry:
* order to do anything useful with the returned dentry
* anyway.
*/
+ *seqp = seq;
*inode = i;
return dentry;
}
@@ -2382,6 +2404,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
if (d_ancestor(alias, dentry)) {
/* Check for loops */
actual = ERR_PTR(-ELOOP);
+ spin_unlock(&inode->i_lock);
} else if (IS_ROOT(alias)) {
/* Is this an anonymous mountpoint that we
* could splice into our tree? */
@@ -2391,7 +2414,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
goto found;
} else {
/* Nope, but we must(!) avoid directory
- * aliasing */
+ * aliasing. This drops inode->i_lock */
actual = __d_unalias(inode, dentry, alias);
}
write_sequnlock(&rename_lock);
@@ -2968,7 +2991,7 @@ __setup("dhash_entries=", set_dhash_entries);
static void __init dcache_init_early(void)
{
- int loop;
+ unsigned int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
@@ -2986,13 +3009,13 @@ static void __init dcache_init_early(void)
&d_hash_mask,
0);
- for (loop = 0; loop < (1 << d_hash_shift); loop++)
+ for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
static void __init dcache_init(void)
{
- int loop;
+ unsigned int loop;
/*
* A constructor could be added for stable state like the lists,
@@ -3016,7 +3039,7 @@ static void __init dcache_init(void)
&d_hash_mask,
0);
- for (loop = 0; loop < (1 << d_hash_shift); loop++)
+ for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
diff --git a/fs/dcookies.c b/fs/dcookies.c
index dda0dc7..17c7799 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -13,7 +13,7 @@
*/
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/mount.h>
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index f65d445..21e9360 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -540,7 +540,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_blob);
* debugfs_print_regs32 - use seq_print to describe a set of registers
* @s: the seq_file structure being used to generate output
* @regs: an array if struct debugfs_reg32 structures
- * @mregs: the length of the above array
+ * @nregs: the length of the above array
* @base: the base address to be used in reading the registers
* @prefix: a string to be prefixed to every output line
*
@@ -611,7 +611,7 @@ static const struct file_operations fops_regset32 = {
* %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
* code.
*/
-struct dentry *debugfs_create_regset32(const char *name, mode_t mode,
+struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
struct dentry *parent,
struct debugfs_regset32 *regset)
{
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 956d5dd..b80bc84 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -23,9 +23,13 @@
#include <linux/debugfs.h>
#include <linux/fsnotify.h>
#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/parser.h>
#include <linux/magic.h>
#include <linux/slab.h>
+#define DEBUGFS_DEFAULT_MODE 0755
+
static struct vfsmount *debugfs_mount;
static int debugfs_mount_count;
static bool debugfs_registered;
@@ -125,11 +129,154 @@ static inline int debugfs_positive(struct dentry *dentry)
return dentry->d_inode && !d_unhashed(dentry);
}
+struct debugfs_mount_opts {
+ uid_t uid;
+ gid_t gid;
+ umode_t mode;
+};
+
+enum {
+ Opt_uid,
+ Opt_gid,
+ Opt_mode,
+ Opt_err
+};
+
+static const match_table_t tokens = {
+ {Opt_uid, "uid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_mode, "mode=%o"},
+ {Opt_err, NULL}
+};
+
+struct debugfs_fs_info {
+ struct debugfs_mount_opts mount_opts;
+};
+
+static int debugfs_parse_options(char *data, struct debugfs_mount_opts *opts)
+{
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+ int token;
+ char *p;
+
+ opts->mode = DEBUGFS_DEFAULT_MODE;
+
+ while ((p = strsep(&data, ",")) != NULL) {
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_uid:
+ if (match_int(&args[0], &option))
+ return -EINVAL;
+ opts->uid = option;
+ break;
+ case Opt_gid:
+ if (match_octal(&args[0], &option))
+ return -EINVAL;
+ opts->gid = option;
+ break;
+ case Opt_mode:
+ if (match_octal(&args[0], &option))
+ return -EINVAL;
+ opts->mode = option & S_IALLUGO;
+ break;
+ /*
+ * We might like to report bad mount options here;
+ * but traditionally debugfs has ignored all mount options
+ */
+ }
+ }
+
+ return 0;
+}
+
+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 debugfs_mount_opts *opts = &fsi->mount_opts;
+
+ inode->i_mode &= ~S_IALLUGO;
+ inode->i_mode |= opts->mode;
+
+ inode->i_uid = opts->uid;
+ inode->i_gid = opts->gid;
+
+ return 0;
+}
+
+static int debugfs_remount(struct super_block *sb, int *flags, char *data)
+{
+ int err;
+ struct debugfs_fs_info *fsi = sb->s_fs_info;
+
+ err = debugfs_parse_options(data, &fsi->mount_opts);
+ if (err)
+ goto fail;
+
+ debugfs_apply_options(sb);
+
+fail:
+ return err;
+}
+
+static int debugfs_show_options(struct seq_file *m, struct dentry *root)
+{
+ struct debugfs_fs_info *fsi = root->d_sb->s_fs_info;
+ struct debugfs_mount_opts *opts = &fsi->mount_opts;
+
+ if (opts->uid != 0)
+ seq_printf(m, ",uid=%u", opts->uid);
+ if (opts->gid != 0)
+ seq_printf(m, ",gid=%u", opts->gid);
+ if (opts->mode != DEBUGFS_DEFAULT_MODE)
+ seq_printf(m, ",mode=%o", opts->mode);
+
+ return 0;
+}
+
+static const struct super_operations debugfs_super_operations = {
+ .statfs = simple_statfs,
+ .remount_fs = debugfs_remount,
+ .show_options = debugfs_show_options,
+};
+
static int debug_fill_super(struct super_block *sb, void *data, int silent)
{
static struct tree_descr debug_files[] = {{""}};
+ struct debugfs_fs_info *fsi;
+ int err;
+
+ save_mount_options(sb, data);
+
+ fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
+ sb->s_fs_info = fsi;
+ if (!fsi) {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ err = debugfs_parse_options(data, &fsi->mount_opts);
+ if (err)
+ goto fail;
+
+ err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
+ if (err)
+ goto fail;
+
+ sb->s_op = &debugfs_super_operations;
+
+ debugfs_apply_options(sb);
+
+ return 0;
- return simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
+fail:
+ kfree(fsi);
+ sb->s_fs_info = NULL;
+ return err;
}
static struct dentry *debug_mount(struct file_system_type *fs_type,
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index c4e2a58..10f5e0b 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -36,7 +36,61 @@
#define DEVPTS_DEFAULT_PTMX_MODE 0000
#define PTMX_MINOR 2
-extern int pty_limit; /* Config limit on Unix98 ptys */
+/*
+ * sysctl support for setting limits on the number of Unix98 ptys allocated.
+ * Otherwise one can eat up all kernel memory by opening /dev/ptmx repeatedly.
+ */
+static int pty_limit = NR_UNIX98_PTY_DEFAULT;
+static int pty_reserve = NR_UNIX98_PTY_RESERVE;
+static int pty_limit_min;
+static int pty_limit_max = INT_MAX;
+static int pty_count;
+
+static struct ctl_table pty_table[] = {
+ {
+ .procname = "max",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .data = &pty_limit,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &pty_limit_min,
+ .extra2 = &pty_limit_max,
+ }, {
+ .procname = "reserve",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .data = &pty_reserve,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &pty_limit_min,
+ .extra2 = &pty_limit_max,
+ }, {
+ .procname = "nr",
+ .maxlen = sizeof(int),
+ .mode = 0444,
+ .data = &pty_count,
+ .proc_handler = proc_dointvec,
+ },
+ {}
+};
+
+static struct ctl_table pty_kern_table[] = {
+ {
+ .procname = "pty",
+ .mode = 0555,
+ .child = pty_table,
+ },
+ {}
+};
+
+static struct ctl_table pty_root_table[] = {
+ {
+ .procname = "kernel",
+ .mode = 0555,
+ .child = pty_kern_table,
+ },
+ {}
+};
+
static DEFINE_MUTEX(allocated_ptys_lock);
static struct vfsmount *devpts_mnt;
@@ -49,10 +103,11 @@ struct pts_mount_opts {
umode_t mode;
umode_t ptmxmode;
int newinstance;
+ int max;
};
enum {
- Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance,
+ Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance, Opt_max,
Opt_err
};
@@ -63,6 +118,7 @@ static const match_table_t tokens = {
#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
{Opt_ptmxmode, "ptmxmode=%o"},
{Opt_newinstance, "newinstance"},
+ {Opt_max, "max=%d"},
#endif
{Opt_err, NULL}
};
@@ -109,6 +165,7 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
opts->gid = 0;
opts->mode = DEVPTS_DEFAULT_MODE;
opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
+ opts->max = NR_UNIX98_PTY_MAX;
/* newinstance makes sense only on initial mount */
if (op == PARSE_MOUNT)
@@ -152,6 +209,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
if (op == PARSE_MOUNT)
opts->newinstance = 1;
break;
+ case Opt_max:
+ if (match_int(&args[0], &option) ||
+ option < 0 || option > NR_UNIX98_PTY_MAX)
+ return -EINVAL;
+ opts->max = option;
+ break;
#endif
default:
printk(KERN_ERR "devpts: called with bogus options\n");
@@ -258,6 +321,8 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root)
seq_printf(seq, ",mode=%03o", opts->mode);
#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
+ if (opts->max < NR_UNIX98_PTY_MAX)
+ seq_printf(seq, ",max=%d", opts->max);
#endif
return 0;
@@ -309,12 +374,11 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
inode->i_fop = &simple_dir_operations;
set_nlink(inode, 2);
- s->s_root = d_alloc_root(inode);
+ s->s_root = d_make_root(inode);
if (s->s_root)
return 0;
printk(KERN_ERR "devpts: get root dentry failed\n");
- iput(inode);
fail:
return -ENOMEM;
@@ -438,6 +502,12 @@ retry:
return -ENOMEM;
mutex_lock(&allocated_ptys_lock);
+ if (pty_count >= pty_limit -
+ (fsi->mount_opts.newinstance ? pty_reserve : 0)) {
+ mutex_unlock(&allocated_ptys_lock);
+ return -ENOSPC;
+ }
+
ida_ret = ida_get_new(&fsi->allocated_ptys, &index);
if (ida_ret < 0) {
mutex_unlock(&allocated_ptys_lock);
@@ -446,11 +516,12 @@ retry:
return -EIO;
}
- if (index >= pty_limit) {
+ if (index >= fsi->mount_opts.max) {
ida_remove(&fsi->allocated_ptys, index);
mutex_unlock(&allocated_ptys_lock);
- return -EIO;
+ return -ENOSPC;
}
+ pty_count++;
mutex_unlock(&allocated_ptys_lock);
return index;
}
@@ -462,6 +533,7 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
mutex_lock(&allocated_ptys_lock);
ida_remove(&fsi->allocated_ptys, idx);
+ pty_count--;
mutex_unlock(&allocated_ptys_lock);
}
@@ -558,11 +630,15 @@ void devpts_pty_kill(struct tty_struct *tty)
static int __init init_devpts_fs(void)
{
int err = register_filesystem(&devpts_fs_type);
+ struct ctl_table_header *table;
+
if (!err) {
+ table = register_sysctl_table(pty_root_table);
devpts_mnt = kern_mount(&devpts_fs_type);
if (IS_ERR(devpts_mnt)) {
err = PTR_ERR(devpts_mnt);
unregister_filesystem(&devpts_fs_type);
+ unregister_sysctl_table(table);
}
}
return err;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 4a588db..f4aadd1 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -173,7 +173,7 @@ void inode_dio_wait(struct inode *inode)
if (atomic_read(&inode->i_dio_count))
__inode_dio_wait(inode);
}
-EXPORT_SYMBOL_GPL(inode_dio_wait);
+EXPORT_SYMBOL(inode_dio_wait);
/*
* inode_dio_done - signal finish of a direct I/O requests
@@ -187,7 +187,7 @@ void inode_dio_done(struct inode *inode)
if (atomic_dec_and_test(&inode->i_dio_count))
wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}
-EXPORT_SYMBOL_GPL(inode_dio_done);
+EXPORT_SYMBOL(inode_dio_done);
/*
* How many pages are in the queue?
diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 8364157..dc5eb59 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -351,11 +351,28 @@ int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen,
static struct dlm_rsb *find_rsb_root(struct dlm_ls *ls, char *name, int len)
{
struct dlm_rsb *r;
+ uint32_t hash, bucket;
+ int rv;
+
+ hash = jhash(name, len, 0);
+ bucket = hash & (ls->ls_rsbtbl_size - 1);
+
+ spin_lock(&ls->ls_rsbtbl[bucket].lock);
+ rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[bucket].keep, name, len, 0, &r);
+ if (rv)
+ rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[bucket].toss,
+ name, len, 0, &r);
+ spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+
+ if (!rv)
+ return r;
down_read(&ls->ls_root_sem);
list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
if (len == r->res_length && !memcmp(name, r->res_name, len)) {
up_read(&ls->ls_root_sem);
+ log_error(ls, "find_rsb_root revert to root_list %s",
+ r->res_name);
return r;
}
}
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index d471830..fa5c07d 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -411,8 +411,8 @@ static int rsb_cmp(struct dlm_rsb *r, const char *name, int nlen)
return memcmp(r->res_name, maxname, DLM_RESNAME_MAXLEN);
}
-static int search_rsb_tree(struct rb_root *tree, char *name, int len,
- unsigned int flags, struct dlm_rsb **r_ret)
+int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+ unsigned int flags, struct dlm_rsb **r_ret)
{
struct rb_node *node = tree->rb_node;
struct dlm_rsb *r;
@@ -474,12 +474,12 @@ static int _search_rsb(struct dlm_ls *ls, char *name, int len, int b,
struct dlm_rsb *r;
int error;
- error = search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, flags, &r);
+ error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, flags, &r);
if (!error) {
kref_get(&r->res_ref);
goto out;
}
- error = search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, flags, &r);
+ error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, flags, &r);
if (error)
goto out;
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index 265017a..1a25530 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -28,6 +28,9 @@ void dlm_scan_waiters(struct dlm_ls *ls);
void dlm_scan_timeout(struct dlm_ls *ls);
void dlm_adjust_timeouts(struct dlm_ls *ls);
+int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+ unsigned int flags, struct dlm_rsb **r_ret);
+
int dlm_purge_locks(struct dlm_ls *ls);
void dlm_purge_mstcpy_locks(struct dlm_rsb *r);
void dlm_grant_after_purge(struct dlm_ls *ls);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 0b3109e..133ef6d 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -52,6 +52,7 @@
#include <linux/mutex.h>
#include <linux/sctp.h>
#include <linux/slab.h>
+#include <net/sctp/sctp.h>
#include <net/sctp/user.h>
#include <net/ipv6.h>
@@ -474,9 +475,6 @@ static void process_sctp_notification(struct connection *con,
int prim_len, ret;
int addr_len;
struct connection *new_con;
- sctp_peeloff_arg_t parg;
- int parglen = sizeof(parg);
- int err;
/*
* We get this before any data for an association.
@@ -525,23 +523,19 @@ static void process_sctp_notification(struct connection *con,
return;
/* Peel off a new sock */
- parg.associd = sn->sn_assoc_change.sac_assoc_id;
- ret = kernel_getsockopt(con->sock, IPPROTO_SCTP,
- SCTP_SOCKOPT_PEELOFF,
- (void *)&parg, &parglen);
+ sctp_lock_sock(con->sock->sk);
+ ret = sctp_do_peeloff(con->sock->sk,
+ sn->sn_assoc_change.sac_assoc_id,
+ &new_con->sock);
+ sctp_release_sock(con->sock->sk);
if (ret < 0) {
log_print("Can't peel off a socket for "
"connection %d to node %d: err=%d",
- parg.associd, nodeid, ret);
- return;
- }
- new_con->sock = sockfd_lookup(parg.sd, &err);
- if (!new_con->sock) {
- log_print("sockfd_lookup error %d", err);
+ (int)sn->sn_assoc_change.sac_assoc_id,
+ nodeid, ret);
return;
}
add_sock(new_con->sock, new_con);
- sockfd_put(new_con->sock);
log_print("connecting to %d sctp association %d",
nodeid, (int)sn->sn_assoc_change.sac_assoc_id);
@@ -1082,7 +1076,7 @@ static void init_local(void)
int i;
dlm_local_count = 0;
- for (i = 0; i < DLM_MAX_ADDR_COUNT - 1; i++) {
+ for (i = 0; i < DLM_MAX_ADDR_COUNT; i++) {
if (dlm_our_addr(&sas, i))
break;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 2a83425..ea99312 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -417,17 +417,6 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
(unsigned long long)(extent_base + extent_offset), rc);
goto out;
}
- if (unlikely(ecryptfs_verbosity > 0)) {
- ecryptfs_printk(KERN_DEBUG, "Encrypting extent "
- "with iv:\n");
- ecryptfs_dump_hex(extent_iv, crypt_stat->iv_bytes);
- ecryptfs_printk(KERN_DEBUG, "First 8 bytes before "
- "encryption:\n");
- ecryptfs_dump_hex((char *)
- (page_address(page)
- + (extent_offset * crypt_stat->extent_size)),
- 8);
- }
rc = ecryptfs_encrypt_page_offset(crypt_stat, enc_extent_page, 0,
page, (extent_offset
* crypt_stat->extent_size),
@@ -440,14 +429,6 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
goto out;
}
rc = 0;
- if (unlikely(ecryptfs_verbosity > 0)) {
- ecryptfs_printk(KERN_DEBUG, "Encrypt extent [0x%.16llx]; "
- "rc = [%d]\n",
- (unsigned long long)(extent_base + extent_offset), rc);
- ecryptfs_printk(KERN_DEBUG, "First 8 bytes after "
- "encryption:\n");
- ecryptfs_dump_hex((char *)(page_address(enc_extent_page)), 8);
- }
out:
return rc;
}
@@ -543,17 +524,6 @@ static int ecryptfs_decrypt_extent(struct page *page,
(unsigned long long)(extent_base + extent_offset), rc);
goto out;
}
- if (unlikely(ecryptfs_verbosity > 0)) {
- ecryptfs_printk(KERN_DEBUG, "Decrypting extent "
- "with iv:\n");
- ecryptfs_dump_hex(extent_iv, crypt_stat->iv_bytes);
- ecryptfs_printk(KERN_DEBUG, "First 8 bytes before "
- "decryption:\n");
- ecryptfs_dump_hex((char *)
- (page_address(enc_extent_page)
- + (extent_offset * crypt_stat->extent_size)),
- 8);
- }
rc = ecryptfs_decrypt_page_offset(crypt_stat, page,
(extent_offset
* crypt_stat->extent_size),
@@ -567,16 +537,6 @@ static int ecryptfs_decrypt_extent(struct page *page,
goto out;
}
rc = 0;
- if (unlikely(ecryptfs_verbosity > 0)) {
- ecryptfs_printk(KERN_DEBUG, "Decrypt extent [0x%.16llx]; "
- "rc = [%d]\n",
- (unsigned long long)(extent_base + extent_offset), rc);
- ecryptfs_printk(KERN_DEBUG, "First 8 bytes after "
- "decryption:\n");
- ecryptfs_dump_hex((char *)(page_address(page)
- + (extent_offset
- * crypt_stat->extent_size)), 8);
- }
out:
return rc;
}
@@ -1590,8 +1550,8 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
*/
int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
{
- int rc = 0;
- char *page_virt = NULL;
+ int rc;
+ char *page_virt;
struct inode *ecryptfs_inode = ecryptfs_dentry->d_inode;
struct ecryptfs_crypt_stat *crypt_stat =
&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
@@ -1616,11 +1576,13 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
ecryptfs_dentry,
ECRYPTFS_VALIDATE_HEADER_SIZE);
if (rc) {
+ /* metadata is not in the file header, so try xattrs */
memset(page_virt, 0, PAGE_CACHE_SIZE);
rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode);
if (rc) {
printk(KERN_DEBUG "Valid eCryptfs headers not found in "
- "file header region or xattr region\n");
+ "file header region or xattr region, inode %lu\n",
+ ecryptfs_inode->i_ino);
rc = -EINVAL;
goto out;
}
@@ -1629,7 +1591,8 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
ECRYPTFS_DONT_VALIDATE_HEADER_SIZE);
if (rc) {
printk(KERN_DEBUG "Valid eCryptfs headers not found in "
- "file xattr region either\n");
+ "file xattr region either, inode %lu\n",
+ ecryptfs_inode->i_ino);
rc = -EINVAL;
}
if (crypt_stat->mount_crypt_stat->flags
@@ -1640,7 +1603,8 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
"crypto metadata only in the extended attribute "
"region, but eCryptfs was mounted without "
"xattr support enabled. eCryptfs will not treat "
- "this like an encrypted file.\n");
+ "this like an encrypted file, inode %lu\n",
+ ecryptfs_inode->i_ino);
rc = -EINVAL;
}
}
@@ -2026,6 +1990,17 @@ out:
return;
}
+static size_t ecryptfs_max_decoded_size(size_t encoded_size)
+{
+ /* Not exact; conservatively long. Every block of 4
+ * encoded characters decodes into a block of 3
+ * decoded characters. This segment of code provides
+ * the caller with the maximum amount of allocated
+ * space that @dst will need to point to in a
+ * subsequent call. */
+ return ((encoded_size + 1) * 3) / 4;
+}
+
/**
* ecryptfs_decode_from_filename
* @dst: If NULL, this function only sets @dst_size and returns. If
@@ -2044,13 +2019,7 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
size_t dst_byte_offset = 0;
if (dst == NULL) {
- /* Not exact; conservatively long. Every block of 4
- * encoded characters decodes into a block of 3
- * decoded characters. This segment of code provides
- * the caller with the maximum amount of allocated
- * space that @dst will need to point to in a
- * subsequent call. */
- (*dst_size) = (((src_size + 1) * 3) / 4);
+ (*dst_size) = ecryptfs_max_decoded_size(src_size);
goto out;
}
while (src_byte_offset < src_size) {
@@ -2275,3 +2244,52 @@ out_free:
out:
return rc;
}
+
+#define ENC_NAME_MAX_BLOCKLEN_8_OR_16 143
+
+int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
+{
+ struct blkcipher_desc desc;
+ struct mutex *tfm_mutex;
+ size_t cipher_blocksize;
+ int rc;
+
+ if (!(mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
+ (*namelen) = lower_namelen;
+ return 0;
+ }
+
+ rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+ mount_crypt_stat->global_default_fn_cipher_name);
+ if (unlikely(rc)) {
+ (*namelen) = 0;
+ return rc;
+ }
+
+ mutex_lock(tfm_mutex);
+ cipher_blocksize = crypto_blkcipher_blocksize(desc.tfm);
+ mutex_unlock(tfm_mutex);
+
+ /* Return an exact amount for the common cases */
+ if (lower_namelen == NAME_MAX
+ && (cipher_blocksize == 8 || cipher_blocksize == 16)) {
+ (*namelen) = ENC_NAME_MAX_BLOCKLEN_8_OR_16;
+ return 0;
+ }
+
+ /* Return a safe estimate for the uncommon cases */
+ (*namelen) = lower_namelen;
+ (*namelen) -= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE;
+ /* Since this is the max decoded size, subtract 1 "decoded block" len */
+ (*namelen) = ecryptfs_max_decoded_size(*namelen) - 3;
+ (*namelen) -= ECRYPTFS_TAG_70_MAX_METADATA_SIZE;
+ (*namelen) -= ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES;
+ /* Worst case is that the filename is padded nearly a full block size */
+ (*namelen) -= cipher_blocksize - 1;
+
+ if ((*namelen) < 0)
+ (*namelen) = 0;
+
+ return 0;
+}
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index a9f29b1..867b64c 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -151,12 +151,21 @@ ecryptfs_get_key_payload_data(struct key *key)
* dentry name */
#define ECRYPTFS_TAG_73_PACKET_TYPE 0x49 /* FEK-encrypted filename as
* metadata */
+#define ECRYPTFS_MIN_PKT_LEN_SIZE 1 /* Min size to specify packet length */
+#define ECRYPTFS_MAX_PKT_LEN_SIZE 2 /* Pass at least this many bytes to
+ * ecryptfs_parse_packet_length() and
+ * ecryptfs_write_packet_length()
+ */
/* Constraint: ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES >=
* ECRYPTFS_MAX_IV_BYTES */
#define ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES 16
#define ECRYPTFS_NON_NULL 0x42 /* A reasonable substitute for NULL */
#define MD5_DIGEST_SIZE 16
#define ECRYPTFS_TAG_70_DIGEST_SIZE MD5_DIGEST_SIZE
+#define ECRYPTFS_TAG_70_MIN_METADATA_SIZE (1 + ECRYPTFS_MIN_PKT_LEN_SIZE \
+ + ECRYPTFS_SIG_SIZE + 1 + 1)
+#define ECRYPTFS_TAG_70_MAX_METADATA_SIZE (1 + ECRYPTFS_MAX_PKT_LEN_SIZE \
+ + ECRYPTFS_SIG_SIZE + 1 + 1)
#define ECRYPTFS_FEK_ENCRYPTED_FILENAME_PREFIX "ECRYPTFS_FEK_ENCRYPTED."
#define ECRYPTFS_FEK_ENCRYPTED_FILENAME_PREFIX_SIZE 23
#define ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX "ECRYPTFS_FNEK_ENCRYPTED."
@@ -696,6 +705,8 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
size_t *packet_size,
struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
char *data, size_t max_packet_size);
+int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat);
int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat,
loff_t offset);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index d3f95f9..2b17f2f 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -48,8 +48,7 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
unsigned long nr_segs, loff_t pos)
{
ssize_t rc;
- struct dentry *lower_dentry;
- struct vfsmount *lower_vfsmount;
+ struct path lower;
struct file *file = iocb->ki_filp;
rc = generic_file_aio_read(iocb, iov, nr_segs, pos);
@@ -60,9 +59,9 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
if (-EIOCBQUEUED == rc)
rc = wait_on_sync_kiocb(iocb);
if (rc >= 0) {
- lower_dentry = ecryptfs_dentry_to_lower(file->f_path.dentry);
- lower_vfsmount = ecryptfs_dentry_to_lower_mnt(file->f_path.dentry);
- touch_atime(lower_vfsmount, lower_dentry);
+ lower.dentry = ecryptfs_dentry_to_lower(file->f_path.dentry);
+ lower.mnt = ecryptfs_dentry_to_lower_mnt(file->f_path.dentry);
+ touch_atime(&lower);
}
return rc;
}
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 19a8ca4..ab35b11 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -822,18 +822,6 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
size_t num_zeros = (PAGE_CACHE_SIZE
- (ia->ia_size & ~PAGE_CACHE_MASK));
-
- /*
- * XXX(truncate) this should really happen at the begginning
- * of ->setattr. But the code is too messy to that as part
- * of a larger patch. ecryptfs is also totally missing out
- * on the inode_change_ok check at the beginning of
- * ->setattr while would include this.
- */
- rc = inode_newsize_ok(inode, ia->ia_size);
- if (rc)
- goto out;
-
if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
truncate_setsize(inode, ia->ia_size);
lower_ia->ia_size = ia->ia_size;
@@ -883,6 +871,28 @@ out:
return rc;
}
+static int ecryptfs_inode_newsize_ok(struct inode *inode, loff_t offset)
+{
+ struct ecryptfs_crypt_stat *crypt_stat;
+ loff_t lower_oldsize, lower_newsize;
+
+ crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
+ lower_oldsize = upper_size_to_lower_size(crypt_stat,
+ i_size_read(inode));
+ lower_newsize = upper_size_to_lower_size(crypt_stat, offset);
+ if (lower_newsize > lower_oldsize) {
+ /*
+ * The eCryptfs inode and the new *lower* size are mixed here
+ * because we may not have the lower i_mutex held and/or it may
+ * not be appropriate to call inode_newsize_ok() with inodes
+ * from other filesystems.
+ */
+ return inode_newsize_ok(inode, lower_newsize);
+ }
+
+ return 0;
+}
+
/**
* ecryptfs_truncate
* @dentry: The ecryptfs layer dentry
@@ -899,6 +909,10 @@ 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);
+ if (rc)
+ return rc;
+
rc = truncate_upper(dentry, &ia, &lower_ia);
if (!rc && lower_ia.ia_valid & ATTR_SIZE) {
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
@@ -978,6 +992,16 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
}
}
mutex_unlock(&crypt_stat->cs_mutex);
+
+ rc = inode_change_ok(inode, ia);
+ if (rc)
+ goto out;
+ if (ia->ia_valid & ATTR_SIZE) {
+ rc = ecryptfs_inode_newsize_ok(inode, ia->ia_size);
+ if (rc)
+ goto out;
+ }
+
if (S_ISREG(inode->i_mode)) {
rc = filemap_write_and_wait(inode->i_mapping);
if (rc)
@@ -1061,6 +1085,8 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
}
rc = vfs_setxattr(lower_dentry, name, value, size, flags);
+ if (!rc)
+ fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
out:
return rc;
}
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index ac1ad48..2333203 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -109,7 +109,7 @@ int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
(*size) += ((unsigned char)(data[1]) + 192);
(*length_size) = 2;
} else if (data[0] == 255) {
- /* Five-byte length; we're not supposed to see this */
+ /* If support is added, adjust ECRYPTFS_MAX_PKT_LEN_SIZE */
ecryptfs_printk(KERN_ERR, "Five-byte packet length not "
"supported\n");
rc = -EINVAL;
@@ -126,7 +126,7 @@ out:
/**
* ecryptfs_write_packet_length
* @dest: The byte array target into which to write the length. Must
- * have at least 5 bytes allocated.
+ * have at least ECRYPTFS_MAX_PKT_LEN_SIZE bytes allocated.
* @size: The length to write.
* @packet_size_length: The number of bytes used to encode the packet
* length is written to this address.
@@ -146,6 +146,7 @@ int ecryptfs_write_packet_length(char *dest, size_t size,
dest[1] = ((size - 192) % 256);
(*packet_size_length) = 2;
} else {
+ /* If support is added, adjust ECRYPTFS_MAX_PKT_LEN_SIZE */
rc = -EINVAL;
ecryptfs_printk(KERN_WARNING,
"Unsupported packet size: [%zd]\n", size);
@@ -678,10 +679,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
* Octets N3-N4: Block-aligned encrypted filename
* - Consists of a minimum number of random characters, a \0
* separator, and then the filename */
- s->max_packet_size = (1 /* Tag 70 identifier */
- + 3 /* Max Tag 70 packet size */
- + ECRYPTFS_SIG_SIZE /* FNEK sig */
- + 1 /* Cipher identifier */
+ s->max_packet_size = (ECRYPTFS_TAG_70_MAX_METADATA_SIZE
+ s->block_aligned_filename_size);
if (dest == NULL) {
(*packet_size) = s->max_packet_size;
@@ -933,10 +931,10 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
goto out;
}
s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- if (max_packet_size < (1 + 1 + ECRYPTFS_SIG_SIZE + 1 + 1)) {
+ if (max_packet_size < ECRYPTFS_TAG_70_MIN_METADATA_SIZE) {
printk(KERN_WARNING "%s: max_packet_size is [%zd]; it must be "
"at least [%d]\n", __func__, max_packet_size,
- (1 + 1 + ECRYPTFS_SIG_SIZE + 1 + 1));
+ ECRYPTFS_TAG_70_MIN_METADATA_SIZE);
rc = -EINVAL;
goto out;
}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index b4a6bef..6895493 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -550,9 +550,8 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
if (IS_ERR(inode))
goto out_free;
- s->s_root = d_alloc_root(inode);
+ s->s_root = d_make_root(inode);
if (!s->s_root) {
- iput(inode);
rc = -ENOMEM;
goto out_free;
}
@@ -795,15 +794,10 @@ static int __init ecryptfs_init(void)
"Failed to allocate one or more kmem_cache objects\n");
goto out;
}
- rc = register_filesystem(&ecryptfs_fs_type);
- if (rc) {
- printk(KERN_ERR "Failed to register filesystem\n");
- goto out_free_kmem_caches;
- }
rc = do_sysfs_registration();
if (rc) {
printk(KERN_ERR "sysfs registration failed\n");
- goto out_unregister_filesystem;
+ goto out_free_kmem_caches;
}
rc = ecryptfs_init_kthread();
if (rc) {
@@ -824,19 +818,24 @@ static int __init ecryptfs_init(void)
"rc = [%d]\n", rc);
goto out_release_messaging;
}
+ rc = register_filesystem(&ecryptfs_fs_type);
+ if (rc) {
+ printk(KERN_ERR "Failed to register filesystem\n");
+ goto out_destroy_crypto;
+ }
if (ecryptfs_verbosity > 0)
printk(KERN_CRIT "eCryptfs verbosity set to %d. Secret values "
"will be written to the syslog!\n", ecryptfs_verbosity);
goto out;
+out_destroy_crypto:
+ ecryptfs_destroy_crypto();
out_release_messaging:
ecryptfs_release_messaging();
out_destroy_kthread:
ecryptfs_destroy_kthread();
out_do_sysfs_unregistration:
do_sysfs_unregistration();
-out_unregister_filesystem:
- unregister_filesystem(&ecryptfs_fs_type);
out_free_kmem_caches:
ecryptfs_free_kmem_caches();
out:
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 940a82e..3a06f40 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -218,6 +218,29 @@ out_unlock:
return rc;
}
+/*
+ * miscdevfs packet format:
+ * Octet 0: Type
+ * Octets 1-4: network byte order msg_ctx->counter
+ * Octets 5-N0: Size of struct ecryptfs_message to follow
+ * Octets N0-N1: struct ecryptfs_message (including data)
+ *
+ * Octets 5-N1 not written if the packet type does not include a message
+ */
+#define PKT_TYPE_SIZE 1
+#define PKT_CTR_SIZE 4
+#define MIN_NON_MSG_PKT_SIZE (PKT_TYPE_SIZE + PKT_CTR_SIZE)
+#define MIN_MSG_PKT_SIZE (PKT_TYPE_SIZE + PKT_CTR_SIZE \
+ + ECRYPTFS_MIN_PKT_LEN_SIZE)
+/* 4 + ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES comes from tag 65 packet format */
+#define MAX_MSG_PKT_SIZE (PKT_TYPE_SIZE + PKT_CTR_SIZE \
+ + ECRYPTFS_MAX_PKT_LEN_SIZE \
+ + sizeof(struct ecryptfs_message) \
+ + 4 + ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES)
+#define PKT_TYPE_OFFSET 0
+#define PKT_CTR_OFFSET PKT_TYPE_SIZE
+#define PKT_LEN_OFFSET (PKT_TYPE_SIZE + PKT_CTR_SIZE)
+
/**
* ecryptfs_miscdev_read - format and send message from queue
* @file: fs/ecryptfs/euid miscdevfs handle (ignored)
@@ -237,7 +260,7 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count,
struct ecryptfs_daemon *daemon;
struct ecryptfs_msg_ctx *msg_ctx;
size_t packet_length_size;
- char packet_length[3];
+ char packet_length[ECRYPTFS_MAX_PKT_LEN_SIZE];
size_t i;
size_t total_length;
uid_t euid = current_euid();
@@ -305,15 +328,8 @@ check_list:
packet_length_size = 0;
msg_ctx->msg_size = 0;
}
- /* miscdevfs packet format:
- * Octet 0: Type
- * Octets 1-4: network byte order msg_ctx->counter
- * Octets 5-N0: Size of struct ecryptfs_message to follow
- * Octets N0-N1: struct ecryptfs_message (including data)
- *
- * Octets 5-N1 not written if the packet type does not
- * include a message */
- total_length = (1 + 4 + packet_length_size + msg_ctx->msg_size);
+ total_length = (PKT_TYPE_SIZE + PKT_CTR_SIZE + packet_length_size
+ + msg_ctx->msg_size);
if (count < total_length) {
rc = 0;
printk(KERN_WARNING "%s: Only given user buffer of "
@@ -324,9 +340,10 @@ check_list:
rc = -EFAULT;
if (put_user(msg_ctx->type, buf))
goto out_unlock_msg_ctx;
- if (put_user(cpu_to_be32(msg_ctx->counter), (__be32 __user *)(buf + 1)))
+ if (put_user(cpu_to_be32(msg_ctx->counter),
+ (__be32 __user *)(&buf[PKT_CTR_OFFSET])))
goto out_unlock_msg_ctx;
- i = 5;
+ i = PKT_TYPE_SIZE + PKT_CTR_SIZE;
if (msg_ctx->msg) {
if (copy_to_user(&buf[i], packet_length, packet_length_size))
goto out_unlock_msg_ctx;
@@ -391,12 +408,6 @@ out:
* @count: Amount of data in @buf
* @ppos: Pointer to offset in file (ignored)
*
- * miscdevfs packet format:
- * Octet 0: Type
- * Octets 1-4: network byte order msg_ctx->counter (0's for non-response)
- * Octets 5-N0: Size of struct ecryptfs_message to follow
- * Octets N0-N1: struct ecryptfs_message (including data)
- *
* Returns the number of bytes read from @buf
*/
static ssize_t
@@ -405,60 +416,78 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf,
{
__be32 counter_nbo;
u32 seq;
- size_t packet_size, packet_size_length, i;
- ssize_t sz = 0;
+ size_t packet_size, packet_size_length;
char *data;
uid_t euid = current_euid();
- int rc;
+ unsigned char packet_size_peek[ECRYPTFS_MAX_PKT_LEN_SIZE];
+ ssize_t rc;
- if (count == 0)
- goto out;
+ if (count == 0) {
+ return 0;
+ } else if (count == MIN_NON_MSG_PKT_SIZE) {
+ /* Likely a harmless MSG_HELO or MSG_QUIT - no packet length */
+ goto memdup;
+ } else if (count < MIN_MSG_PKT_SIZE || count > MAX_MSG_PKT_SIZE) {
+ printk(KERN_WARNING "%s: Acceptable packet size range is "
+ "[%d-%zu], but amount of data written is [%zu].",
+ __func__, MIN_MSG_PKT_SIZE, MAX_MSG_PKT_SIZE, count);
+ return -EINVAL;
+ }
+
+ if (copy_from_user(packet_size_peek, &buf[PKT_LEN_OFFSET],
+ sizeof(packet_size_peek))) {
+ printk(KERN_WARNING "%s: Error while inspecting packet size\n",
+ __func__);
+ return -EFAULT;
+ }
+ rc = ecryptfs_parse_packet_length(packet_size_peek, &packet_size,
+ &packet_size_length);
+ if (rc) {
+ printk(KERN_WARNING "%s: Error parsing packet length; "
+ "rc = [%zd]\n", __func__, rc);
+ return rc;
+ }
+
+ if ((PKT_TYPE_SIZE + PKT_CTR_SIZE + packet_size_length + packet_size)
+ != count) {
+ printk(KERN_WARNING "%s: Invalid packet size [%zu]\n", __func__,
+ packet_size);
+ return -EINVAL;
+ }
+
+memdup:
data = memdup_user(buf, count);
if (IS_ERR(data)) {
printk(KERN_ERR "%s: memdup_user returned error [%ld]\n",
__func__, PTR_ERR(data));
- goto out;
+ return PTR_ERR(data);
}
- sz = count;
- i = 0;
- switch (data[i++]) {
+ switch (data[PKT_TYPE_OFFSET]) {
case ECRYPTFS_MSG_RESPONSE:
- if (count < (1 + 4 + 1 + sizeof(struct ecryptfs_message))) {
+ if (count < (MIN_MSG_PKT_SIZE
+ + sizeof(struct ecryptfs_message))) {
printk(KERN_WARNING "%s: Minimum acceptable packet "
"size is [%zd], but amount of data written is "
"only [%zd]. Discarding response packet.\n",
__func__,
- (1 + 4 + 1 + sizeof(struct ecryptfs_message)),
- count);
+ (MIN_MSG_PKT_SIZE
+ + sizeof(struct ecryptfs_message)), count);
+ rc = -EINVAL;
goto out_free;
}
- memcpy(&counter_nbo, &data[i], 4);
+ memcpy(&counter_nbo, &data[PKT_CTR_OFFSET], PKT_CTR_SIZE);
seq = be32_to_cpu(counter_nbo);
- i += 4;
- rc = ecryptfs_parse_packet_length(&data[i], &packet_size,
- &packet_size_length);
+ rc = ecryptfs_miscdev_response(
+ &data[PKT_LEN_OFFSET + packet_size_length],
+ packet_size, euid, current_user_ns(),
+ task_pid(current), seq);
if (rc) {
- printk(KERN_WARNING "%s: Error parsing packet length; "
- "rc = [%d]\n", __func__, rc);
- goto out_free;
- }
- i += packet_size_length;
- if ((1 + 4 + packet_size_length + packet_size) != count) {
- printk(KERN_WARNING "%s: (1 + packet_size_length([%zd])"
- " + packet_size([%zd]))([%zd]) != "
- "count([%zd]). Invalid packet format.\n",
- __func__, packet_size_length, packet_size,
- (1 + packet_size_length + packet_size), count);
- goto out_free;
- }
- rc = ecryptfs_miscdev_response(&data[i], packet_size,
- euid, current_user_ns(),
- task_pid(current), seq);
- if (rc)
printk(KERN_WARNING "%s: Failed to deliver miscdev "
- "response to requesting operation; rc = [%d]\n",
+ "response to requesting operation; rc = [%zd]\n",
__func__, rc);
+ goto out_free;
+ }
break;
case ECRYPTFS_MSG_HELO:
case ECRYPTFS_MSG_QUIT:
@@ -467,12 +496,13 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf,
ecryptfs_printk(KERN_WARNING, "Dropping miscdev "
"message of unrecognized type [%d]\n",
data[0]);
- break;
+ rc = -EINVAL;
+ goto out_free;
}
+ rc = count;
out_free:
kfree(data);
-out:
- return sz;
+ return rc;
}
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 6a44148..a46b3a8 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -57,6 +57,10 @@ struct page *ecryptfs_get_locked_page(struct inode *inode, loff_t index)
* @page: Page that is locked before this call is made
*
* Returns zero on success; non-zero otherwise
+ *
+ * This is where we encrypt the data and pass the encrypted data to
+ * the lower filesystem. In OpenPGP-compatible mode, we operate on
+ * entire underlying packets.
*/
static int ecryptfs_writepage(struct page *page, struct writeback_control *wbc)
{
@@ -146,7 +150,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
/* This is a header extent */
char *page_virt;
- page_virt = kmap_atomic(page, KM_USER0);
+ page_virt = kmap_atomic(page);
memset(page_virt, 0, PAGE_CACHE_SIZE);
/* TODO: Support more than one header extent */
if (view_extent_num == 0) {
@@ -159,7 +163,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
crypt_stat,
&written);
}
- kunmap_atomic(page_virt, KM_USER0);
+ kunmap_atomic(page_virt);
flush_dcache_page(page);
if (rc) {
printk(KERN_ERR "%s: Error reading xattr "
@@ -481,10 +485,6 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
* @copied: The amount of data copied
* @page: The eCryptfs page
* @fsdata: The fsdata (unused)
- *
- * This is where we encrypt the data and pass the encrypted data to
- * the lower filesystem. In OpenPGP-compatible mode, we operate on
- * entire underlying packets.
*/
static int ecryptfs_write_end(struct file *file,
struct address_space *mapping,
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 3745f7c..b2a34a1 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -130,13 +130,18 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
pgoff_t ecryptfs_page_idx = (pos >> PAGE_CACHE_SHIFT);
size_t start_offset_in_page = (pos & ~PAGE_CACHE_MASK);
size_t num_bytes = (PAGE_CACHE_SIZE - start_offset_in_page);
- size_t total_remaining_bytes = ((offset + size) - pos);
+ loff_t total_remaining_bytes = ((offset + size) - pos);
+
+ if (fatal_signal_pending(current)) {
+ rc = -EINTR;
+ break;
+ }
if (num_bytes > total_remaining_bytes)
num_bytes = total_remaining_bytes;
if (pos < offset) {
/* remaining zeros to write, up to destination offset */
- size_t total_remaining_zeros = (offset - pos);
+ loff_t total_remaining_zeros = (offset - pos);
if (num_bytes > total_remaining_zeros)
num_bytes = total_remaining_zeros;
@@ -151,7 +156,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
ecryptfs_page_idx, rc);
goto out;
}
- ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0);
+ ecryptfs_page_virt = kmap_atomic(ecryptfs_page);
/*
* pos: where we're now writing, offset: where the request was
@@ -174,7 +179,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
(data + data_offset), num_bytes);
data_offset += num_bytes;
}
- kunmap_atomic(ecryptfs_page_virt, KM_USER0);
+ kunmap_atomic(ecryptfs_page_virt);
flush_dcache_page(ecryptfs_page);
SetPageUptodate(ecryptfs_page);
unlock_page(ecryptfs_page);
@@ -193,15 +198,19 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
}
pos += num_bytes;
}
- if ((offset + size) > ecryptfs_file_size) {
- i_size_write(ecryptfs_inode, (offset + size));
+ if (pos > ecryptfs_file_size) {
+ i_size_write(ecryptfs_inode, pos);
if (crypt_stat->flags & ECRYPTFS_ENCRYPTED) {
- rc = ecryptfs_write_inode_size_to_metadata(
+ int rc2;
+
+ rc2 = ecryptfs_write_inode_size_to_metadata(
ecryptfs_inode);
- if (rc) {
+ if (rc2) {
printk(KERN_ERR "Problem with "
"ecryptfs_write_inode_size_to_metadata; "
- "rc = [%d]\n", rc);
+ "rc = [%d]\n", rc2);
+ if (!rc)
+ rc = rc2;
goto out;
}
}
@@ -273,76 +282,3 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
flush_dcache_page(page_for_ecryptfs);
return rc;
}
-
-#if 0
-/**
- * ecryptfs_read
- * @data: The virtual address into which to write the data read (and
- * possibly decrypted) from the lower file
- * @offset: The offset in the decrypted view of the file from which to
- * read into @data
- * @size: The number of bytes to read into @data
- * @ecryptfs_file: The eCryptfs file from which to read
- *
- * Read an arbitrary amount of data from an arbitrary location in the
- * eCryptfs page cache. This is done on an extent-by-extent basis;
- * individual extents are decrypted and read from the lower page
- * cache (via VFS reads). This function takes care of all the
- * address translation to locations in the lower filesystem.
- *
- * Returns zero on success; non-zero otherwise
- */
-int ecryptfs_read(char *data, loff_t offset, size_t size,
- struct file *ecryptfs_file)
-{
- struct inode *ecryptfs_inode = ecryptfs_file->f_dentry->d_inode;
- struct page *ecryptfs_page;
- char *ecryptfs_page_virt;
- loff_t ecryptfs_file_size = i_size_read(ecryptfs_inode);
- loff_t data_offset = 0;
- loff_t pos;
- int rc = 0;
-
- if ((offset + size) > ecryptfs_file_size) {
- rc = -EINVAL;
- printk(KERN_ERR "%s: Attempt to read data past the end of the "
- "file; offset = [%lld]; size = [%td]; "
- "ecryptfs_file_size = [%lld]\n",
- __func__, offset, size, ecryptfs_file_size);
- goto out;
- }
- pos = offset;
- while (pos < (offset + size)) {
- pgoff_t ecryptfs_page_idx = (pos >> PAGE_CACHE_SHIFT);
- size_t start_offset_in_page = (pos & ~PAGE_CACHE_MASK);
- size_t num_bytes = (PAGE_CACHE_SIZE - start_offset_in_page);
- size_t total_remaining_bytes = ((offset + size) - pos);
-
- if (num_bytes > total_remaining_bytes)
- num_bytes = total_remaining_bytes;
- ecryptfs_page = ecryptfs_get_locked_page(ecryptfs_inode,
- ecryptfs_page_idx);
- if (IS_ERR(ecryptfs_page)) {
- rc = PTR_ERR(ecryptfs_page);
- printk(KERN_ERR "%s: Error getting page at "
- "index [%ld] from eCryptfs inode "
- "mapping; rc = [%d]\n", __func__,
- ecryptfs_page_idx, rc);
- goto out;
- }
- ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0);
- memcpy((data + data_offset),
- ((char *)ecryptfs_page_virt + start_offset_in_page),
- num_bytes);
- kunmap_atomic(ecryptfs_page_virt, KM_USER0);
- flush_dcache_page(ecryptfs_page);
- SetPageUptodate(ecryptfs_page);
- unlock_page(ecryptfs_page);
- page_cache_release(ecryptfs_page);
- pos += num_bytes;
- data_offset += num_bytes;
- }
-out:
- return rc;
-}
-#endif /* 0 */
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 9df7fd6..2dd946b 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -30,6 +30,8 @@
#include <linux/seq_file.h>
#include <linux/file.h>
#include <linux/crypto.h>
+#include <linux/statfs.h>
+#include <linux/magic.h>
#include "ecryptfs_kernel.h"
struct kmem_cache *ecryptfs_inode_info_cache;
@@ -102,10 +104,20 @@ static void ecryptfs_destroy_inode(struct inode *inode)
static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
+ int rc;
if (!lower_dentry->d_sb->s_op->statfs)
return -ENOSYS;
- return lower_dentry->d_sb->s_op->statfs(lower_dentry, buf);
+
+ rc = lower_dentry->d_sb->s_op->statfs(lower_dentry, buf);
+ if (rc)
+ return rc;
+
+ buf->f_type = ECRYPTFS_SUPER_MAGIC;
+ rc = ecryptfs_set_f_namelen(&buf->f_namelen, buf->f_namelen,
+ &ecryptfs_superblock_to_private(dentry->d_sb)->mount_crypt_stat);
+
+ return rc;
}
/**
@@ -172,7 +184,6 @@ static int ecryptfs_show_options(struct seq_file *m, struct dentry *root)
const struct super_operations ecryptfs_sops = {
.alloc_inode = ecryptfs_alloc_inode,
.destroy_inode = ecryptfs_destroy_inode,
- .drop_inode = generic_drop_inode,
.statfs = ecryptfs_statfs,
.remount_fs = NULL,
.evict_inode = ecryptfs_evict_inode,
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 9811064..e755ec7 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -317,10 +317,9 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
goto out_no_fs;
}
- s->s_root = d_alloc_root(root);
+ s->s_root = d_make_root(root);
if (!(s->s_root)) {
printk(KERN_ERR "EFS: get root dentry failed\n");
- iput(root);
ret = -ENOMEM;
goto out_no_fs;
}
diff --git a/fs/eventfd.c b/fs/eventfd.c
index d9a5917..dba15fe 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -16,7 +16,7 @@
#include <linux/spinlock.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/kref.h>
#include <linux/eventfd.h>
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index aabdfc3..629e9ed 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -320,6 +320,11 @@ static inline int ep_is_linked(struct list_head *p)
return !list_empty(p);
}
+static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p)
+{
+ return container_of(p, struct eppoll_entry, wait);
+}
+
/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
{
@@ -422,6 +427,31 @@ out_unlock:
return error;
}
+/*
+ * As described in commit 0ccf831cb lockdep: annotate epoll
+ * the use of wait queues used by epoll is done in a very controlled
+ * manner. Wake ups can nest inside each other, but are never done
+ * with the same locking. For example:
+ *
+ * dfd = socket(...);
+ * efd1 = epoll_create();
+ * efd2 = epoll_create();
+ * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...);
+ * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...);
+ *
+ * When a packet arrives to the device underneath "dfd", the net code will
+ * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a
+ * callback wakeup entry on that queue, and the wake_up() performed by the
+ * "dfd" net code will end up in ep_poll_callback(). At this point epoll
+ * (efd1) notices that it may have some event ready, so it needs to wake up
+ * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake()
+ * that ends up in another wake_up(), after having checked about the
+ * recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to
+ * avoid stack blasting.
+ *
+ * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle
+ * this special case of epoll.
+ */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
unsigned long events, int subclass)
@@ -467,6 +497,18 @@ static void ep_poll_safewake(wait_queue_head_t *wq)
put_cpu();
}
+static void ep_remove_wait_queue(struct eppoll_entry *pwq)
+{
+ wait_queue_head_t *whead;
+
+ rcu_read_lock();
+ /* If it is cleared by POLLFREE, it should be rcu-safe */
+ whead = rcu_dereference(pwq->whead);
+ if (whead)
+ remove_wait_queue(whead, &pwq->wait);
+ rcu_read_unlock();
+}
+
/*
* This function unregisters poll callbacks from the associated file
* descriptor. Must be called with "mtx" held (or "epmutex" if called from
@@ -481,7 +523,7 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
list_del(&pwq->llink);
- remove_wait_queue(pwq->whead, &pwq->wait);
+ ep_remove_wait_queue(pwq);
kmem_cache_free(pwq_cache, pwq);
}
}
@@ -682,9 +724,12 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
{
struct epitem *epi, *tmp;
+ poll_table pt;
+ init_poll_funcptr(&pt, NULL);
list_for_each_entry_safe(epi, tmp, head, rdllink) {
- if (epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
+ pt._key = epi->event.events;
+ if (epi->ffd.file->f_op->poll(epi->ffd.file, &pt) &
epi->event.events)
return POLLIN | POLLRDNORM;
else {
@@ -842,6 +887,17 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
+ if ((unsigned long)key & POLLFREE) {
+ ep_pwq_from_wait(wait)->whead = NULL;
+ /*
+ * whead = NULL above can race with ep_remove_wait_queue()
+ * which can do another remove_wait_queue() after us, so we
+ * can't use __remove_wait_queue(). whead->lock is held by
+ * the caller.
+ */
+ list_del_init(&wait->task_list);
+ }
+
spin_lock_irqsave(&ep->lock, flags);
/*
@@ -960,6 +1016,10 @@ static int path_count[PATH_ARR_SIZE];
static int path_count_inc(int nests)
{
+ /* Allow an arbitrary number of depth 1 paths */
+ if (nests == 0)
+ return 0;
+
if (++path_count[nests] > path_limits[nests])
return -1;
return 0;
@@ -1017,13 +1077,11 @@ static int reverse_path_check_proc(void *priv, void *cookie, int call_nests)
*/
static int reverse_path_check(void)
{
- int length = 0;
int error = 0;
struct file *current_file;
/* let's call this for all tfiles */
list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) {
- length++;
path_count_init();
error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
reverse_path_check_proc, current_file,
@@ -1065,6 +1123,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
/* Initialize the poll table using the queue callback */
epq.epi = epi;
init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
+ epq.pt._key = event->events;
/*
* Attach the item to the poll hooks and get current event bits.
@@ -1159,6 +1218,9 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
{
int pwake = 0;
unsigned int revents;
+ poll_table pt;
+
+ init_poll_funcptr(&pt, NULL);
/*
* Set the new event interest mask before calling f_op->poll();
@@ -1166,13 +1228,14 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
* f_op->poll() call and the new event set registering.
*/
epi->event.events = event->events;
+ pt._key = event->events;
epi->event.data = event->data; /* protected by mtx */
/*
* Get current event bits. We can safely use the file* here because
* its usage count has been increased by the caller of this function.
*/
- revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
+ revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt);
/*
* If the item is "hot" and it is not registered inside the ready
@@ -1207,6 +1270,9 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
unsigned int revents;
struct epitem *epi;
struct epoll_event __user *uevent;
+ poll_table pt;
+
+ init_poll_funcptr(&pt, NULL);
/*
* We can loop without lock because we are passed a task private list.
@@ -1219,7 +1285,8 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
list_del_init(&epi->rdllink);
- revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
+ pt._key = epi->event.events;
+ revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt) &
epi->event.events;
/*
diff --git a/fs/exec.c b/fs/exec.c
index aeb135c..23559c2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -63,6 +63,8 @@
#include <trace/events/task.h>
#include "internal.h"
+#include <trace/events/sched.h>
+
int core_uses_pid;
char core_pattern[CORENAME_MAX_SIZE] = "core";
unsigned int core_pipe_limit;
@@ -79,15 +81,13 @@ static atomic_t call_count = ATOMIC_INIT(1);
static LIST_HEAD(formats);
static DEFINE_RWLOCK(binfmt_lock);
-int __register_binfmt(struct linux_binfmt * fmt, int insert)
+void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
- if (!fmt)
- return -EINVAL;
+ BUG_ON(!fmt);
write_lock(&binfmt_lock);
insert ? list_add(&fmt->lh, &formats) :
list_add_tail(&fmt->lh, &formats);
write_unlock(&binfmt_lock);
- return 0;
}
EXPORT_SYMBOL(__register_binfmt);
@@ -822,7 +822,7 @@ static int exec_mmap(struct mm_struct *mm)
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
- sync_mm_rss(tsk, old_mm);
+ sync_mm_rss(old_mm);
mm_release(tsk, old_mm);
if (old_mm) {
@@ -848,6 +848,7 @@ static int exec_mmap(struct mm_struct *mm)
if (old_mm) {
up_read(&old_mm->mmap_sem);
BUG_ON(active_mm != old_mm);
+ setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm);
mm_update_next_owner(old_mm);
mmput(old_mm);
return 0;
@@ -975,8 +976,8 @@ static int de_thread(struct task_struct *tsk)
sig->notify_count = 0;
no_thread_group:
- if (current->mm)
- setmax_mm_hiwater_rss(&sig->maxrss, current->mm);
+ /* we have changed execution domain */
+ tsk->exit_signal = SIGCHLD;
exit_itimers(sig);
flush_itimer_signals();
@@ -1071,6 +1072,21 @@ void set_task_comm(struct task_struct *tsk, char *buf)
perf_event_comm(tsk);
}
+static void filename_to_taskname(char *tcomm, const char *fn, unsigned int len)
+{
+ int i, ch;
+
+ /* Copies the binary name from after last slash */
+ for (i = 0; (ch = *(fn++)) != '\0';) {
+ if (ch == '/')
+ i = 0; /* overwrite what we wrote */
+ else
+ if (i < len - 1)
+ tcomm[i++] = ch;
+ }
+ tcomm[i] = '\0';
+}
+
int flush_old_exec(struct linux_binprm * bprm)
{
int retval;
@@ -1085,6 +1101,7 @@ int flush_old_exec(struct linux_binprm * bprm)
set_mm_exe_file(bprm->mm, bprm->file);
+ filename_to_taskname(bprm->tcomm, bprm->filename, sizeof(bprm->tcomm));
/*
* Release all of the old mmap stuff
*/
@@ -1096,7 +1113,7 @@ int flush_old_exec(struct linux_binprm * bprm)
bprm->mm = NULL; /* We're using it now */
set_fs(USER_DS);
- current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD);
+ current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD);
flush_thread();
current->personality &= ~bprm->per_clear;
@@ -1116,10 +1133,6 @@ EXPORT_SYMBOL(would_dump);
void setup_new_exec(struct linux_binprm * bprm)
{
- int i, ch;
- const char *name;
- char tcomm[sizeof(current->comm)];
-
arch_pick_mmap_layout(current->mm);
/* This is the point of no return */
@@ -1130,18 +1143,7 @@ void setup_new_exec(struct linux_binprm * bprm)
else
set_dumpable(current->mm, suid_dumpable);
- name = bprm->filename;
-
- /* Copies the binary name from after last slash */
- for (i=0; (ch = *(name++)) != '\0';) {
- if (ch == '/')
- i = 0; /* overwrite what we wrote */
- else
- if (i < (sizeof(tcomm) - 1))
- tcomm[i++] = ch;
- }
- tcomm[i] = '\0';
- set_task_comm(current, tcomm);
+ set_task_comm(current, bprm->tcomm);
/* Set the new mm task size. We have to do that late because it may
* depend on TIF_32BIT which is only updated in flush_thread() on
@@ -1338,13 +1340,13 @@ int remove_arg_zero(struct linux_binprm *bprm)
ret = -EFAULT;
goto out;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
for (; offset < PAGE_SIZE && kaddr[offset];
offset++, bprm->p++)
;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
put_arg_page(page);
if (offset == PAGE_SIZE)
@@ -1401,9 +1403,10 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
*/
bprm->recursion_depth = depth;
if (retval >= 0) {
- if (depth == 0)
- ptrace_event(PTRACE_EVENT_EXEC,
- old_pid);
+ if (depth == 0) {
+ trace_sched_process_exec(current, old_pid, bprm);
+ ptrace_event(PTRACE_EVENT_EXEC, old_pid);
+ }
put_binfmt(fmt);
allow_write_access(bprm->file);
if (bprm->file)
@@ -1914,7 +1917,6 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
- struct completion *vfork_done;
int core_waiters = -EBUSY;
init_completion(&core_state->startup);
@@ -1926,22 +1928,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
core_waiters = zap_threads(tsk, mm, core_state, exit_code);
up_write(&mm->mmap_sem);
- if (unlikely(core_waiters < 0))
- goto fail;
-
- /*
- * Make sure nobody is waiting for us to release the VM,
- * otherwise we can deadlock when we wait on each other
- */
- vfork_done = tsk->vfork_done;
- if (vfork_done) {
- tsk->vfork_done = NULL;
- complete(vfork_done);
- }
-
- if (core_waiters)
+ if (core_waiters > 0)
wait_for_completion(&core_state->startup);
-fail:
+
return core_waiters;
}
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 8040583..c61e62a 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -597,7 +597,7 @@ int exofs_make_empty(struct inode *inode, struct inode *parent)
goto fail;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
de = (struct exofs_dir_entry *)kaddr;
de->name_len = 1;
de->rec_len = cpu_to_le16(EXOFS_DIR_REC_LEN(1));
@@ -611,7 +611,7 @@ int exofs_make_empty(struct inode *inode, struct inode *parent)
de->inode_no = cpu_to_le64(parent->i_ino);
memcpy(de->name, PARENT_DIR, sizeof(PARENT_DIR));
exofs_set_de_type(de, inode);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
err = exofs_commit_chunk(page, 0, chunk_size);
fail:
page_cache_release(page);
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index 9dbf0c3..fc7161d 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -143,9 +143,6 @@ static int exofs_link(struct dentry *old_dentry, struct inode *dir,
{
struct inode *inode = old_dentry->d_inode;
- if (inode->i_nlink >= EXOFS_LINK_MAX)
- return -EMLINK;
-
inode->i_ctime = CURRENT_TIME;
inode_inc_link_count(inode);
ihold(inode);
@@ -156,10 +153,7 @@ static int exofs_link(struct dentry *old_dentry, struct inode *dir,
static int exofs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode;
- int err = -EMLINK;
-
- if (dir->i_nlink >= EXOFS_LINK_MAX)
- goto out;
+ int err;
inode_inc_link_count(dir);
@@ -275,11 +269,6 @@ static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (err)
goto out_dir;
} else {
- if (dir_de) {
- err = -EMLINK;
- if (new_dir->i_nlink >= EXOFS_LINK_MAX)
- goto out_dir;
- }
err = exofs_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index d22cd16..7f2b590 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -754,6 +754,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_blocksize = EXOFS_BLKSIZE;
sb->s_blocksize_bits = EXOFS_BLKSHIFT;
sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_max_links = EXOFS_LINK_MAX;
atomic_set(&sbi->s_curr_pending, 0);
sb->s_bdev = NULL;
sb->s_dev = 0;
@@ -818,9 +819,8 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
ret = PTR_ERR(root);
goto free_sbi;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
- iput(root);
EXOFS_ERR("ERROR: get root inode failed\n");
ret = -ENOMEM;
goto free_sbi;
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index d37df35..0f4f5c9 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -645,7 +645,7 @@ int ext2_make_empty(struct inode *inode, struct inode *parent)
unlock_page(page);
goto fail;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr, 0, chunk_size);
de = (struct ext2_dir_entry_2 *)kaddr;
de->name_len = 1;
@@ -660,7 +660,7 @@ int ext2_make_empty(struct inode *inode, struct inode *parent)
de->inode = cpu_to_le32(parent->i_ino);
memcpy (de->name, "..\0", 4);
ext2_set_de_type (de, inode);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
err = ext2_commit_chunk(page, 0, chunk_size);
fail:
page_cache_release(page);
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 1089f76..2de655f 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -77,10 +77,11 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
flags = flags & EXT2_FL_USER_MODIFIABLE;
flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE;
ei->i_flags = flags;
- mutex_unlock(&inode->i_mutex);
ext2_set_inode_flags(inode);
inode->i_ctime = CURRENT_TIME_SEC;
+ mutex_unlock(&inode->i_mutex);
+
mark_inode_dirty(inode);
setflags_out:
mnt_drop_write_file(filp);
@@ -88,20 +89,29 @@ setflags_out:
}
case EXT2_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *) arg);
- case EXT2_IOC_SETVERSION:
+ case EXT2_IOC_SETVERSION: {
+ __u32 generation;
+
if (!inode_owner_or_capable(inode))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
- if (get_user(inode->i_generation, (int __user *) arg)) {
+ if (get_user(generation, (int __user *) arg)) {
ret = -EFAULT;
- } else {
- inode->i_ctime = CURRENT_TIME_SEC;
- mark_inode_dirty(inode);
+ goto setversion_out;
}
+
+ mutex_lock(&inode->i_mutex);
+ inode->i_ctime = CURRENT_TIME_SEC;
+ inode->i_generation = generation;
+ mutex_unlock(&inode->i_mutex);
+
+ mark_inode_dirty(inode);
+setversion_out:
mnt_drop_write_file(filp);
return ret;
+ }
case EXT2_IOC_GETRSVSZ:
if (test_opt(inode->i_sb, RESERVATION)
&& S_ISREG(inode->i_mode)
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 0804198..dffb865 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -195,9 +195,6 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
struct inode *inode = old_dentry->d_inode;
int err;
- if (inode->i_nlink >= EXT2_LINK_MAX)
- return -EMLINK;
-
dquot_initialize(dir);
inode->i_ctime = CURRENT_TIME_SEC;
@@ -217,10 +214,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
{
struct inode * inode;
- int err = -EMLINK;
-
- if (dir->i_nlink >= EXT2_LINK_MAX)
- goto out;
+ int err;
dquot_initialize(dir);
@@ -346,11 +340,6 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
- if (dir_de) {
- err = -EMLINK;
- if (new_dir->i_nlink >= EXT2_LINK_MAX)
- goto out_dir;
- }
err = ext2_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 0090595..e1025c7 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -919,6 +919,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
}
sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);
+ sb->s_max_links = EXT2_LINK_MAX;
if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
@@ -1087,9 +1088,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount3;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
- iput(root);
ext2_msg(sb, KERN_ERR, "error: get root inode failed");
ret = -ENOMEM;
goto failed_mount3;
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index a203892..1e036b7 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -1743,8 +1743,11 @@ allocated:
*errp = 0;
brelse(bitmap_bh);
- dquot_free_block(inode, *count-num);
- *count = num;
+
+ if (num < *count) {
+ dquot_free_block(inode, *count-num);
+ *count = num;
+ }
trace_ext3_allocate_blocks(inode, goal, num,
(unsigned long long)ret_block);
@@ -1970,7 +1973,7 @@ static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
sbi = EXT3_SB(sb);
/* Walk through the whole group */
- while (start < max) {
+ while (start <= max) {
start = bitmap_search_next_usable_block(start, bitmap_bh, max);
if (start < 0)
break;
@@ -1980,7 +1983,7 @@ static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
* Allocate contiguous free extents by setting bits in the
* block bitmap
*/
- while (next < max
+ while (next <= max
&& claim_block(sb_bgl_lock(sbi, group),
next, bitmap_bh)) {
next++;
@@ -2091,73 +2094,74 @@ err_out:
*/
int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range)
{
- ext3_grpblk_t last_block, first_block, free_blocks;
- unsigned long first_group, last_group;
- unsigned long group, ngroups;
+ ext3_grpblk_t last_block, first_block;
+ unsigned long group, first_group, last_group;
struct ext3_group_desc *gdp;
struct ext3_super_block *es = EXT3_SB(sb)->s_es;
- uint64_t start, len, minlen, trimmed;
+ uint64_t start, minlen, end, trimmed = 0;
+ ext3_fsblk_t first_data_blk =
+ le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block);
ext3_fsblk_t max_blks = le32_to_cpu(es->s_blocks_count);
int ret = 0;
- start = (range->start >> sb->s_blocksize_bits) +
- le32_to_cpu(es->s_first_data_block);
- len = range->len >> sb->s_blocksize_bits;
+ start = range->start >> sb->s_blocksize_bits;
+ end = start + (range->len >> sb->s_blocksize_bits) - 1;
minlen = range->minlen >> sb->s_blocksize_bits;
- trimmed = 0;
- if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)))
+ if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) ||
+ unlikely(start >= max_blks))
return -EINVAL;
- if (start >= max_blks)
- return -EINVAL;
- if (start + len > max_blks)
- len = max_blks - start;
+ if (end >= max_blks)
+ end = max_blks - 1;
+ if (end <= first_data_blk)
+ goto out;
+ if (start < first_data_blk)
+ start = first_data_blk;
- ngroups = EXT3_SB(sb)->s_groups_count;
smp_rmb();
/* Determine first and last group to examine based on start and len */
ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) start,
&first_group, &first_block);
- ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) (start + len),
+ ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) end,
&last_group, &last_block);
- last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
- last_block = EXT3_BLOCKS_PER_GROUP(sb);
- if (first_group > last_group)
- return -EINVAL;
+ /* end now represents the last block to discard in this group */
+ end = EXT3_BLOCKS_PER_GROUP(sb) - 1;
for (group = first_group; group <= last_group; group++) {
gdp = ext3_get_group_desc(sb, group, NULL);
if (!gdp)
break;
- free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
- if (free_blocks < minlen)
- continue;
-
/*
* For all the groups except the last one, last block will
- * always be EXT3_BLOCKS_PER_GROUP(sb), so we only need to
- * change it for the last group in which case first_block +
- * len < EXT3_BLOCKS_PER_GROUP(sb).
+ * always be EXT3_BLOCKS_PER_GROUP(sb)-1, so we only need to
+ * change it for the last group, note that last_block is
+ * already computed earlier by ext3_get_group_no_and_offset()
*/
- if (first_block + len < EXT3_BLOCKS_PER_GROUP(sb))
- last_block = first_block + len;
- len -= last_block - first_block;
+ if (group == last_group)
+ end = last_block;
- ret = ext3_trim_all_free(sb, group, first_block,
- last_block, minlen);
- if (ret < 0)
- break;
+ if (le16_to_cpu(gdp->bg_free_blocks_count) >= minlen) {
+ ret = ext3_trim_all_free(sb, group, first_block,
+ end, minlen);
+ if (ret < 0)
+ break;
+ trimmed += ret;
+ }
- trimmed += ret;
+ /*
+ * For every group except the first one, we are sure
+ * that the first block to discard will be block #0.
+ */
first_block = 0;
}
- if (ret >= 0)
+ if (ret > 0)
ret = 0;
- range->len = trimmed * sb->s_blocksize;
+out:
+ range->len = trimmed * sb->s_blocksize;
return ret;
}
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2d0afec..6d34186 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -756,6 +756,7 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode,
struct ext3_block_alloc_info *block_i;
ext3_fsblk_t current_block;
struct ext3_inode_info *ei = EXT3_I(inode);
+ struct timespec now;
block_i = ei->i_block_alloc_info;
/*
@@ -795,9 +796,11 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode,
}
/* We are done with atomic stuff, now do the rest of housekeeping */
-
- inode->i_ctime = CURRENT_TIME_SEC;
- ext3_mark_inode_dirty(handle, inode);
+ now = CURRENT_TIME_SEC;
+ if (!timespec_equal(&inode->i_ctime, &now) || !where->bh) {
+ inode->i_ctime = now;
+ ext3_mark_inode_dirty(handle, inode);
+ }
/* ext3_mark_inode_dirty already updated i_sync_tid */
atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 726c7ef..e0b45b9 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2046,10 +2046,9 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
ext3_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck");
goto failed_mount3;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
ext3_msg(sb, KERN_ERR, "error: get root dentry failed");
- iput(root);
ret = -ENOMEM;
goto failed_mount3;
}
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f9e2cd8..4bbd07a 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -336,10 +336,10 @@ err_out:
* Return buffer_head on success or NULL in case of failure.
*/
struct buffer_head *
-ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
ext4_fsblk_t bitmap_blk;
desc = ext4_get_group_desc(sb, block_group, NULL);
@@ -348,9 +348,9 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_block_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, "Cannot read block bitmap - "
- "block_group = %u, block_bitmap = %llu",
- block_group, bitmap_blk);
+ ext4_error(sb, "Cannot get buffer for block bitmap - "
+ "block_group = %u, block_bitmap = %llu",
+ block_group, bitmap_blk);
return NULL;
}
@@ -382,25 +382,50 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
return bh;
}
/*
- * submit the buffer_head for read. We can
- * safely mark the bitmap as uptodate now.
- * We do it here so the bitmap uptodate bit
- * get set with buffer lock held.
+ * submit the buffer_head for reading
*/
+ set_buffer_new(bh);
trace_ext4_read_block_bitmap_load(sb, block_group);
- set_bitmap_uptodate(bh);
- if (bh_submit_read(bh) < 0) {
- put_bh(bh);
+ bh->b_end_io = ext4_end_bitmap_read;
+ get_bh(bh);
+ submit_bh(READ, bh);
+ return bh;
+}
+
+/* Returns 0 on success, 1 on error */
+int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
+ struct buffer_head *bh)
+{
+ struct ext4_group_desc *desc;
+
+ if (!buffer_new(bh))
+ return 0;
+ desc = ext4_get_group_desc(sb, block_group, NULL);
+ if (!desc)
+ return 1;
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh)) {
ext4_error(sb, "Cannot read block bitmap - "
- "block_group = %u, block_bitmap = %llu",
- block_group, bitmap_blk);
- return NULL;
+ "block_group = %u, block_bitmap = %llu",
+ block_group, (unsigned long long) bh->b_blocknr);
+ return 1;
}
+ clear_buffer_new(bh);
+ /* Panic or remount fs read-only if block bitmap is invalid */
ext4_valid_block_bitmap(sb, desc, block_group, bh);
- /*
- * file system mounted not to panic on error,
- * continue with corrupt bitmap
- */
+ return 0;
+}
+
+struct buffer_head *
+ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+{
+ struct buffer_head *bh;
+
+ bh = ext4_read_block_bitmap_nowait(sb, block_group);
+ if (ext4_wait_block_bitmap(sb, block_group, bh)) {
+ put_bh(bh);
+ return NULL;
+ }
return bh;
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 164c560..ad56866 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -91,17 +91,17 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
return 0;
if (filp)
- ext4_error_file(filp, function, line, bh ? bh->b_blocknr : 0,
+ ext4_error_file(filp, function, line, bh->b_blocknr,
"bad entry in directory: %s - offset=%u(%u), "
"inode=%u, rec_len=%d, name_len=%d",
- error_msg, (unsigned) (offset%bh->b_size),
+ error_msg, (unsigned) (offset % bh->b_size),
offset, le32_to_cpu(de->inode),
rlen, de->name_len);
else
- ext4_error_inode(dir, function, line, bh ? bh->b_blocknr : 0,
+ ext4_error_inode(dir, function, line, bh->b_blocknr,
"bad entry in directory: %s - offset=%u(%u), "
"inode=%u, rec_len=%d, name_len=%d",
- error_msg, (unsigned) (offset%bh->b_size),
+ error_msg, (unsigned) (offset % bh->b_size),
offset, le32_to_cpu(de->inode),
rlen, de->name_len);
@@ -425,8 +425,9 @@ static int call_filldir(struct file *filp, void *dirent,
sb = inode->i_sb;
if (!fname) {
- printk(KERN_ERR "EXT4-fs: call_filldir: called with "
- "null fname?!?\n");
+ ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: "
+ "called with null fname?!?", __func__, __LINE__,
+ inode->i_ino, current->comm);
return 0;
}
curr_pos = hash2pos(fname->hash, fname->minor_hash);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 513004f..ded731a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -53,7 +53,7 @@
printk(KERN_DEBUG f, ## a); \
} while (0)
#else
-#define ext4_debug(f, a...) do {} while (0)
+#define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
#define EXT4_ERROR_INODE(inode, fmt, a...) \
@@ -184,6 +184,8 @@ struct mpage_da_data {
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
#define EXT4_IO_END_QUEUED 0x0004
+#define EXT4_IO_END_DIRECT 0x0008
+#define EXT4_IO_END_IN_FSYNC 0x0010
struct ext4_io_page {
struct page *p_page;
@@ -192,18 +194,25 @@ struct ext4_io_page {
#define MAX_IO_PAGES 128
+/*
+ * For converting uninitialized extents on a work queue.
+ *
+ * 'page' is only used from the writepage() path; 'pages' is only used for
+ * buffered writes; they are used to keep page references until conversion
+ * takes place. For AIO/DIO, neither field is filled in.
+ */
typedef struct ext4_io_end {
struct list_head list; /* per-file finished IO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
- struct page *page; /* page struct for buffer write */
+ struct page *page; /* for writepage() path */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
struct kiocb *iocb; /* iocb struct for AIO */
int result; /* error value for AIO */
- int num_io_pages;
- struct ext4_io_page *pages[MAX_IO_PAGES];
+ int num_io_pages; /* for writepages() */
+ struct ext4_io_page *pages[MAX_IO_PAGES]; /* for writepages() */
} ext4_io_end_t;
struct ext4_io_submit {
@@ -923,6 +932,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */
#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */
+#define EXT4_MOUNT_ERRORS_MASK 0x00070
#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
@@ -941,7 +951,6 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
-#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
#define EXT4_MOUNT_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
@@ -1142,6 +1151,7 @@ struct ext4_sb_info {
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
unsigned int s_mount_flags;
+ unsigned int s_def_mount_opt;
ext4_fsblk_t s_sb_block;
uid_t s_resuid;
gid_t s_resgid;
@@ -1420,8 +1430,9 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
-#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x2000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */
#define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */
+#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x8000 /* data in inode */
#define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1794,8 +1805,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
struct buffer_head ** bh);
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
-struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
- ext4_group_t block_group);
+
+extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
+ ext4_group_t block_group);
+extern int ext4_wait_block_bitmap(struct super_block *sb,
+ ext4_group_t block_group,
+ struct buffer_head *bh);
+extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+ ext4_group_t block_group);
extern void ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh,
ext4_group_t group,
@@ -1841,6 +1858,7 @@ extern void ext4_check_inodes_bitmap(struct super_block *);
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
extern int ext4_init_inode_table(struct super_block *sb,
ext4_group_t group, int barrier);
+extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
/* mballoc.c */
extern long ext4_mb_stats;
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index a52db3a..0f58b86 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -47,9 +47,9 @@
*/
#define EXT_DEBUG__
#ifdef EXT_DEBUG
-#define ext_debug(a...) printk(a)
+#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__)
#else
-#define ext_debug(a...)
+#define ext_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
/*
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5802fa1..83b20fc 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -104,6 +104,78 @@
#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+/**
+ * struct ext4_journal_cb_entry - Base structure for callback information.
+ *
+ * This struct is a 'seed' structure for a using with your own callback
+ * structs. If you are using callbacks you must allocate one of these
+ * or another struct of your own definition which has this struct
+ * as it's first element and pass it to ext4_journal_callback_add().
+ */
+struct ext4_journal_cb_entry {
+ /* list information for other callbacks attached to the same handle */
+ struct list_head jce_list;
+
+ /* Function to call with this callback structure */
+ void (*jce_func)(struct super_block *sb,
+ struct ext4_journal_cb_entry *jce, int error);
+
+ /* user data goes here */
+};
+
+/**
+ * ext4_journal_callback_add: add a function to call after transaction commit
+ * @handle: active journal transaction handle to register callback on
+ * @func: callback function to call after the transaction has committed:
+ * @sb: superblock of current filesystem for transaction
+ * @jce: returned journal callback data
+ * @rc: journal state at commit (0 = transaction committed properly)
+ * @jce: journal callback data (internal and function private data struct)
+ *
+ * The registered function will be called in the context of the journal thread
+ * after the transaction for which the handle was created has completed.
+ *
+ * No locks are held when the callback function is called, so it is safe to
+ * call blocking functions from within the callback, but the callback should
+ * not block or run for too long, or the filesystem will be blocked waiting for
+ * the next transaction to commit. No journaling functions can be used, or
+ * there is a risk of deadlock.
+ *
+ * There is no guaranteed calling order of multiple registered callbacks on
+ * the same transaction.
+ */
+static inline void ext4_journal_callback_add(handle_t *handle,
+ void (*func)(struct super_block *sb,
+ struct ext4_journal_cb_entry *jce,
+ int rc),
+ struct ext4_journal_cb_entry *jce)
+{
+ struct ext4_sb_info *sbi =
+ EXT4_SB(handle->h_transaction->t_journal->j_private);
+
+ /* Add the jce to transaction's private list */
+ jce->jce_func = func;
+ spin_lock(&sbi->s_md_lock);
+ list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
+ spin_unlock(&sbi->s_md_lock);
+}
+
+/**
+ * ext4_journal_callback_del: delete a registered callback
+ * @handle: active journal transaction handle on which callback was registered
+ * @jce: registered journal callback entry to unregister
+ */
+static inline void ext4_journal_callback_del(handle_t *handle,
+ struct ext4_journal_cb_entry *jce)
+{
+ struct ext4_sb_info *sbi =
+ EXT4_SB(handle->h_transaction->t_journal->j_private);
+
+ spin_lock(&sbi->s_md_lock);
+ list_del_init(&jce->jce_list);
+ spin_unlock(&sbi->s_md_lock);
+}
+
int
ext4_mark_iloc_dirty(handle_t *handle,
struct inode *inode,
@@ -261,43 +333,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
/* super.c */
int ext4_force_commit(struct super_block *sb);
-static inline int ext4_should_journal_data(struct inode *inode)
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
{
if (EXT4_JOURNAL(inode) == NULL)
- return 0;
- if (!S_ISREG(inode->i_mode))
- return 1;
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
- return 1;
- if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
- return 1;
- return 0;
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ /* We do not support data journalling with delayed allocation */
+ if (!S_ISREG(inode->i_mode) ||
+ test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+ !test_opt(inode->i_sb, DELALLOC))
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ else
+ BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
}
static inline int ext4_should_order_data(struct inode *inode)
{
- if (EXT4_JOURNAL(inode) == NULL)
- return 0;
- if (!S_ISREG(inode->i_mode))
- return 0;
- if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
- return 0;
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
- return 1;
- return 0;
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
}
static inline int ext4_should_writeback_data(struct inode *inode)
{
- if (EXT4_JOURNAL(inode) == NULL)
- return 1;
- if (!S_ISREG(inode->i_mode))
- return 0;
- if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
- return 0;
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
- return 1;
- return 0;
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
}
/*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74f23c2..1421938 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -44,6 +44,14 @@
#include <trace/events/ext4.h>
+/*
+ * used by extent splitting.
+ */
+#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
+ due to ENOSPC */
+#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
+#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
+
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
@@ -51,6 +59,13 @@ static int ext4_split_extent(handle_t *handle,
int split_flag,
int flags);
+static int ext4_split_extent_at(handle_t *handle,
+ struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t split,
+ int split_flag,
+ int flags);
+
static int ext4_ext_truncate_extend_restart(handle_t *handle,
struct inode *inode,
int needed)
@@ -300,6 +315,8 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
+ if (len == 0)
+ return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
@@ -2308,7 +2325,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
struct ext4_extent *ex;
/* the header must be checked already in ext4_ext_remove_space() */
- ext_debug("truncate since %u in leaf\n", start);
+ ext_debug("truncate since %u in leaf to %u\n", start, end);
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
@@ -2343,14 +2360,17 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ext_debug(" border %u:%u\n", a, b);
/* If this extent is beyond the end of the hole, skip it */
- if (end <= ex_ee_block) {
+ if (end < ex_ee_block) {
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
continue;
} else if (b != ex_ee_block + ex_ee_len - 1) {
- EXT4_ERROR_INODE(inode," bad truncate %u:%u\n",
- start, end);
+ EXT4_ERROR_INODE(inode,
+ "can not handle truncate %u:%u "
+ "on extent %u:%u",
+ start, end, ex_ee_block,
+ ex_ee_block + ex_ee_len - 1);
err = -EIO;
goto out;
} else if (a != ex_ee_block) {
@@ -2482,7 +2502,8 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
return 1;
}
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+ ext4_lblk_t end)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
@@ -2491,7 +2512,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
handle_t *handle;
int i, err;
- ext_debug("truncate since %u\n", start);
+ ext_debug("truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
handle = ext4_journal_start(inode, depth + 1);
@@ -2504,6 +2525,61 @@ again:
trace_ext4_ext_remove_space(inode, start, depth);
/*
+ * Check if we are removing extents inside the extent tree. If that
+ * is the case, we are going to punch a hole inside the extent tree
+ * so we have to check whether we need to split the extent covering
+ * the last block to remove so we can easily remove the part of it
+ * in ext4_ext_rm_leaf().
+ */
+ if (end < EXT_MAX_BLOCKS - 1) {
+ struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+
+ /* find extent for this block */
+ path = ext4_ext_find_extent(inode, end, NULL);
+ if (IS_ERR(path)) {
+ ext4_journal_stop(handle);
+ return PTR_ERR(path);
+ }
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ if (!ex)
+ goto cont;
+
+ ee_block = le32_to_cpu(ex->ee_block);
+
+ /*
+ * See if the last block is inside the extent, if so split
+ * the extent at 'end' block so we can easily remove the
+ * tail of the first part of the split extent in
+ * ext4_ext_rm_leaf().
+ */
+ if (end >= ee_block &&
+ end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
+ int split_flag = 0;
+
+ if (ext4_ext_is_uninitialized(ex))
+ split_flag = EXT4_EXT_MARK_UNINIT1 |
+ EXT4_EXT_MARK_UNINIT2;
+
+ /*
+ * Split the extent in two so that 'end' is the last
+ * block in the first new extent
+ */
+ err = ext4_split_extent_at(handle, inode, path,
+ end + 1, split_flag,
+ EXT4_GET_BLOCKS_PRE_IO |
+ EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+
+ if (err < 0)
+ goto out;
+ }
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+cont:
+
+ /*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
@@ -2515,6 +2591,7 @@ again:
}
path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
+
if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
err = -EIO;
goto out;
@@ -2526,7 +2603,7 @@ again:
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
&partial_cluster, start,
- EXT_MAX_BLOCKS - 1);
+ end);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
@@ -2651,17 +2728,17 @@ void ext4_ext_init(struct super_block *sb)
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
- printk(KERN_INFO "EXT4-fs: file extents enabled");
+ printk(KERN_INFO "EXT4-fs: file extents enabled"
#ifdef AGGRESSIVE_TEST
- printk(", aggressive tests");
+ ", aggressive tests"
#endif
#ifdef CHECK_BINSEARCH
- printk(", check binsearch");
+ ", check binsearch"
#endif
#ifdef EXTENTS_STATS
- printk(", stats");
+ ", stats"
#endif
- printk("\n");
+ "\n");
#endif
#ifdef EXTENTS_STATS
spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
@@ -2709,14 +2786,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
}
/*
- * used by extent splitting.
- */
-#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
- due to ENOSPC */
-#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
-#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
-
-/*
* ext4_split_extent_at() splits an extent at given block.
*
* @handle: the journal handle
@@ -3224,11 +3293,13 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
depth = ext_depth(inode);
eh = path[depth].p_hdr;
- if (unlikely(!eh->eh_entries)) {
- EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
- "EOFBLOCKS_FL set");
- return -EIO;
- }
+ /*
+ * We're going to remove EOFBLOCKS_FL entirely in future so we
+ * do not care for this case anymore. Simply remove the flag
+ * if there are no extents.
+ */
+ if (unlikely(!eh->eh_entries))
+ goto out;
last_ex = EXT_LAST_EXTENT(eh);
/*
* We should clear the EOFBLOCKS_FL flag if we are writing the
@@ -3252,6 +3323,7 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
for (i = depth-1; i >= 0; i--)
if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
return 0;
+out:
ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
return ext4_mark_inode_dirty(handle, inode);
}
@@ -3710,8 +3782,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
int free_on_err = 0, err = 0, depth, ret;
unsigned int allocated = 0, offset = 0;
unsigned int allocated_clusters = 0;
- unsigned int punched_out = 0;
- unsigned int result = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
ext4_lblk_t cluster_offset;
@@ -3721,8 +3791,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* check in cache */
- if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
- ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
+ if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
if (!newex.ee_start_lo && !newex.ee_start_hi) {
if ((sbi->s_cluster_ratio > 1) &&
ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
@@ -3790,113 +3859,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/* if found extent covers block, simply return it */
if (in_range(map->m_lblk, ee_block, ee_len)) {
- struct ext4_map_blocks punch_map;
- ext4_fsblk_t partial_cluster = 0;
-
newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (map->m_lblk - ee_block);
ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
ee_block, ee_len, newblock);
- if ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0) {
- /*
- * Do not put uninitialized extent
- * in the cache
- */
- if (!ext4_ext_is_uninitialized(ex)) {
- ext4_ext_put_in_cache(inode, ee_block,
- ee_len, ee_start);
- goto out;
- }
- ret = ext4_ext_handle_uninitialized_extents(
- handle, inode, map, path, flags,
- allocated, newblock);
- return ret;
- }
-
- /*
- * Punch out the map length, but only to the
- * end of the extent
- */
- punched_out = allocated < map->m_len ?
- allocated : map->m_len;
-
/*
- * Sense extents need to be converted to
- * uninitialized, they must fit in an
- * uninitialized extent
+ * Do not put uninitialized extent
+ * in the cache
*/
- if (punched_out > EXT_UNINIT_MAX_LEN)
- punched_out = EXT_UNINIT_MAX_LEN;
-
- punch_map.m_lblk = map->m_lblk;
- punch_map.m_pblk = newblock;
- punch_map.m_len = punched_out;
- punch_map.m_flags = 0;
-
- /* Check to see if the extent needs to be split */
- if (punch_map.m_len != ee_len ||
- punch_map.m_lblk != ee_block) {
-
- ret = ext4_split_extent(handle, inode,
- path, &punch_map, 0,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
- EXT4_GET_BLOCKS_PRE_IO);
-
- if (ret < 0) {
- err = ret;
- goto out2;
- }
- /*
- * find extent for the block at
- * the start of the hole
- */
- ext4_ext_drop_refs(path);
- kfree(path);
-
- path = ext4_ext_find_extent(inode,
- map->m_lblk, NULL);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- path = NULL;
- goto out2;
- }
-
- depth = ext_depth(inode);
- ex = path[depth].p_ext;
- ee_len = ext4_ext_get_actual_len(ex);
- ee_block = le32_to_cpu(ex->ee_block);
- ee_start = ext4_ext_pblock(ex);
-
- }
-
- ext4_ext_mark_uninitialized(ex);
-
- ext4_ext_invalidate_cache(inode);
-
- err = ext4_ext_rm_leaf(handle, inode, path,
- &partial_cluster, map->m_lblk,
- map->m_lblk + punched_out);
-
- if (!err && path->p_hdr->eh_entries == 0) {
- /*
- * Punch hole freed all of this sub tree,
- * so we need to correct eh_depth
- */
- err = ext4_ext_get_access(handle, inode, path);
- if (err == 0) {
- ext_inode_hdr(inode)->eh_depth = 0;
- ext_inode_hdr(inode)->eh_max =
- cpu_to_le16(ext4_ext_space_root(
- inode, 0));
-
- err = ext4_ext_dirty(
- handle, inode, path);
- }
+ if (!ext4_ext_is_uninitialized(ex)) {
+ ext4_ext_put_in_cache(inode, ee_block,
+ ee_len, ee_start);
+ goto out;
}
-
- goto out2;
+ ret = ext4_ext_handle_uninitialized_extents(
+ handle, inode, map, path, flags,
+ allocated, newblock);
+ return ret;
}
}
@@ -4165,13 +4146,11 @@ out2:
ext4_ext_drop_refs(path);
kfree(path);
}
- result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
- punched_out : allocated;
trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
- newblock, map->m_len, err ? err : result);
+ newblock, map->m_len, err ? err : allocated);
- return err ? err : result;
+ return err ? err : allocated;
}
void ext4_ext_truncate(struct inode *inode)
@@ -4228,7 +4207,7 @@ void ext4_ext_truncate(struct inode *inode)
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
- err = ext4_ext_remove_space(inode, last_block);
+ err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
/* In a multi-transaction truncate, we only make the final
* transaction synchronous.
@@ -4436,10 +4415,11 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
EXT4_GET_BLOCKS_IO_CONVERT_EXT);
if (ret <= 0) {
WARN_ON(ret <= 0);
- printk(KERN_ERR "%s: ext4_ext_map_blocks "
- "returned error inode#%lu, block=%u, "
- "max_blocks=%u", __func__,
- inode->i_ino, map.m_lblk, map.m_len);
+ ext4_msg(inode->i_sb, KERN_ERR,
+ "%s:%d: inode #%lu: block %u: len %u: "
+ "ext4_ext_map_blocks returned %d",
+ __func__, __LINE__, inode->i_ino, map.m_lblk,
+ map.m_len, ret);
}
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
@@ -4705,14 +4685,12 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
{
struct inode *inode = file->f_path.dentry->d_inode;
struct super_block *sb = inode->i_sb;
- struct ext4_ext_cache cache_ex;
- ext4_lblk_t first_block, last_block, num_blocks, iblock, max_blocks;
+ ext4_lblk_t first_block, stop_block;
struct address_space *mapping = inode->i_mapping;
- struct ext4_map_blocks map;
handle_t *handle;
loff_t first_page, last_page, page_len;
loff_t first_page_offset, last_page_offset;
- int ret, credits, blocks_released, err = 0;
+ int credits, err = 0;
/* No need to punch hole beyond i_size */
if (offset >= inode->i_size)
@@ -4728,10 +4706,6 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
offset;
}
- first_block = (offset + sb->s_blocksize - 1) >>
- EXT4_BLOCK_SIZE_BITS(sb);
- last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
last_page = (offset + length) >> PAGE_CACHE_SHIFT;
@@ -4810,7 +4784,6 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
}
}
-
/*
* If i_size is contained in the last page, we need to
* unmap and zero the partial page after i_size
@@ -4830,73 +4803,22 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
}
}
+ first_block = (offset + sb->s_blocksize - 1) >>
+ EXT4_BLOCK_SIZE_BITS(sb);
+ stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
/* If there are no blocks to remove, return now */
- if (first_block >= last_block)
+ if (first_block >= stop_block)
goto out;
down_write(&EXT4_I(inode)->i_data_sem);
ext4_ext_invalidate_cache(inode);
ext4_discard_preallocations(inode);
- /*
- * Loop over all the blocks and identify blocks
- * that need to be punched out
- */
- iblock = first_block;
- blocks_released = 0;
- while (iblock < last_block) {
- max_blocks = last_block - iblock;
- num_blocks = 1;
- memset(&map, 0, sizeof(map));
- map.m_lblk = iblock;
- map.m_len = max_blocks;
- ret = ext4_ext_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
-
- if (ret > 0) {
- blocks_released += ret;
- num_blocks = ret;
- } else if (ret == 0) {
- /*
- * If map blocks could not find the block,
- * then it is in a hole. If the hole was
- * not already cached, then map blocks should
- * put it in the cache. So we can get the hole
- * out of the cache
- */
- memset(&cache_ex, 0, sizeof(cache_ex));
- if ((ext4_ext_check_cache(inode, iblock, &cache_ex)) &&
- !cache_ex.ec_start) {
-
- /* The hole is cached */
- num_blocks = cache_ex.ec_block +
- cache_ex.ec_len - iblock;
-
- } else {
- /* The block could not be identified */
- err = -EIO;
- break;
- }
- } else {
- /* Map blocks error */
- err = ret;
- break;
- }
-
- if (num_blocks == 0) {
- /* This condition should never happen */
- ext_debug("Block lookup failed");
- err = -EIO;
- break;
- }
-
- iblock += num_blocks;
- }
+ err = ext4_ext_remove_space(inode, first_block, stop_block - 1);
- if (blocks_released > 0) {
- ext4_ext_invalidate_cache(inode);
- ext4_discard_preallocations(inode);
- }
+ ext4_ext_invalidate_cache(inode);
+ ext4_discard_preallocations(inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 00a2cb7..bb6c7d8 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -89,6 +89,7 @@ int ext4_flush_completed_IO(struct inode *inode)
io = list_entry(ei->i_completed_io_list.next,
ext4_io_end_t, list);
list_del_init(&io->list);
+ io->flag |= EXT4_IO_END_IN_FSYNC;
/*
* Calling ext4_end_io_nolock() to convert completed
* IO to written.
@@ -108,6 +109,7 @@ int ext4_flush_completed_IO(struct inode *inode)
if (ret < 0)
ret2 = ret;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ io->flag &= ~EXT4_IO_END_IN_FSYNC;
}
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
return (ret2 < 0) ? ret2 : 0;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 25d8c97..409c2ee 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -92,6 +92,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
return EXT4_INODES_PER_GROUP(sb);
}
+void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate)
+{
+ if (uptodate) {
+ set_buffer_uptodate(bh);
+ set_bitmap_uptodate(bh);
+ }
+ unlock_buffer(bh);
+ put_bh(bh);
+}
+
/*
* Read the inode allocation bitmap for a given block_group, reading
* into the specified slot in the superblock's bitmap cache.
@@ -147,18 +157,18 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
return bh;
}
/*
- * submit the buffer_head for read. We can
- * safely mark the bitmap as uptodate now.
- * We do it here so the bitmap uptodate bit
- * get set with buffer lock held.
+ * submit the buffer_head for reading
*/
trace_ext4_load_inode_bitmap(sb, block_group);
- set_bitmap_uptodate(bh);
- if (bh_submit_read(bh) < 0) {
+ bh->b_end_io = ext4_end_bitmap_read;
+ get_bh(bh);
+ submit_bh(READ, bh);
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh)) {
put_bh(bh);
ext4_error(sb, "Cannot read inode bitmap - "
- "block_group = %u, inode_bitmap = %llu",
- block_group, bitmap_blk);
+ "block_group = %u, inode_bitmap = %llu",
+ block_group, bitmap_blk);
return NULL;
}
return bh;
@@ -194,19 +204,20 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
struct ext4_sb_info *sbi;
int fatal = 0, err, count, cleared;
- if (atomic_read(&inode->i_count) > 1) {
- printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
- atomic_read(&inode->i_count));
+ if (!sb) {
+ printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
+ "nonexistent device\n", __func__, __LINE__);
return;
}
- if (inode->i_nlink) {
- printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
- inode->i_nlink);
+ if (atomic_read(&inode->i_count) > 1) {
+ ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d",
+ __func__, __LINE__, inode->i_ino,
+ atomic_read(&inode->i_count));
return;
}
- if (!sb) {
- printk(KERN_ERR "ext4_free_inode: inode on "
- "nonexistent device\n");
+ if (inode->i_nlink) {
+ ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: nlink=%d\n",
+ __func__, __LINE__, inode->i_ino, inode->i_nlink);
return;
}
sbi = EXT4_SB(sb);
@@ -593,94 +604,6 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
}
/*
- * claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's ext4_group_lock
- * and clear the uninit flag. The inode bitmap update
- * and group desc uninit flag clear should be done
- * after holding ext4_group_lock so that ext4_read_inode_bitmap
- * doesn't race with the ext4_claim_inode
- */
-static int ext4_claim_inode(struct super_block *sb,
- struct buffer_head *inode_bitmap_bh,
- unsigned long ino, ext4_group_t group, umode_t mode)
-{
- int free = 0, retval = 0, count;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_group_info *grp = ext4_get_group_info(sb, group);
- struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
-
- /*
- * We have to be sure that new inode allocation does not race with
- * inode table initialization, because otherwise we may end up
- * allocating and writing new inode right before sb_issue_zeroout
- * takes place and overwriting our new inode with zeroes. So we
- * take alloc_sem to prevent it.
- */
- down_read(&grp->alloc_sem);
- ext4_lock_group(sb, group);
- if (ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data)) {
- /* not a free inode */
- retval = 1;
- goto err_ret;
- }
- ino++;
- if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
- ino > EXT4_INODES_PER_GROUP(sb)) {
- ext4_unlock_group(sb, group);
- up_read(&grp->alloc_sem);
- ext4_error(sb, "reserved inode or inode > inodes count - "
- "block_group = %u, inode=%lu", group,
- ino + group * EXT4_INODES_PER_GROUP(sb));
- return 1;
- }
- /* If we didn't allocate from within the initialized part of the inode
- * table then we need to initialize up to this inode. */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
-
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
- gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
- /* When marking the block group with
- * ~EXT4_BG_INODE_UNINIT we don't want to depend
- * on the value of bg_itable_unused even though
- * mke2fs could have initialized the same for us.
- * Instead we calculated the value below
- */
-
- free = 0;
- } else {
- free = EXT4_INODES_PER_GROUP(sb) -
- ext4_itable_unused_count(sb, gdp);
- }
-
- /*
- * Check the relative inode number against the last used
- * relative inode number in this group. if it is greater
- * we need to update the bg_itable_unused count
- *
- */
- if (ino > free)
- ext4_itable_unused_set(sb, gdp,
- (EXT4_INODES_PER_GROUP(sb) - ino));
- }
- count = ext4_free_inodes_count(sb, gdp) - 1;
- ext4_free_inodes_set(sb, gdp, count);
- if (S_ISDIR(mode)) {
- count = ext4_used_dirs_count(sb, gdp) + 1;
- ext4_used_dirs_set(sb, gdp, count);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t f = ext4_flex_group(sbi, group);
-
- atomic_inc(&sbi->s_flex_groups[f].used_dirs);
- }
- }
- gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
-err_ret:
- ext4_unlock_group(sb, group);
- up_read(&grp->alloc_sem);
- return retval;
-}
-
-/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
@@ -741,6 +664,11 @@ got_group:
if (ret2 == -1)
goto out;
+ /*
+ * Normally we will only go through one pass of this loop,
+ * unless we get unlucky and it turns out the group we selected
+ * had its last inode grabbed by someone else.
+ */
for (i = 0; i < ngroups; i++, ino = 0) {
err = -EIO;
@@ -757,51 +685,24 @@ repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
EXT4_INODES_PER_GROUP(sb), ino);
-
- if (ino < EXT4_INODES_PER_GROUP(sb)) {
-
- BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle,
- inode_bitmap_bh);
- if (err)
- goto fail;
-
- BUFFER_TRACE(group_desc_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle,
- group_desc_bh);
- if (err)
- goto fail;
- if (!ext4_claim_inode(sb, inode_bitmap_bh,
- ino, group, mode)) {
- /* we won it */
- BUFFER_TRACE(inode_bitmap_bh,
- "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle,
- NULL,
- inode_bitmap_bh);
- if (err)
- goto fail;
- /* zero bit is inode number 1*/
- ino++;
- goto got;
- }
- /* we lost it */
- ext4_handle_release_buffer(handle, inode_bitmap_bh);
- ext4_handle_release_buffer(handle, group_desc_bh);
-
- if (++ino < EXT4_INODES_PER_GROUP(sb))
- goto repeat_in_this_group;
+ if (ino >= EXT4_INODES_PER_GROUP(sb)) {
+ if (++group == ngroups)
+ group = 0;
+ continue;
}
-
- /*
- * This case is possible in concurrent environment. It is very
- * rare. We cannot repeat the find_group_xxx() call because
- * that will simply return the same blockgroup, because the
- * group descriptor metadata has not yet been updated.
- * So we just go onto the next blockgroup.
- */
- if (++group == ngroups)
- group = 0;
+ if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
+ ext4_error(sb, "reserved inode found cleared - "
+ "inode=%lu", ino + 1);
+ continue;
+ }
+ ext4_lock_group(sb, group);
+ ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
+ ext4_unlock_group(sb, group);
+ ino++; /* the inode bitmap is zero-based */
+ if (!ret2)
+ goto got; /* we grabbed the inode! */
+ if (ino < EXT4_INODES_PER_GROUP(sb))
+ goto repeat_in_this_group;
}
err = -ENOSPC;
goto out;
@@ -838,6 +739,59 @@ got:
if (err)
goto fail;
}
+
+ BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
+ if (err)
+ goto fail;
+
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, group_desc_bh);
+ if (err)
+ goto fail;
+
+ /* Update the relevant bg descriptor fields */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+ int free;
+ struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+ down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
+ ext4_lock_group(sb, group); /* while we modify the bg desc */
+ free = EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp);
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+ free = 0;
+ }
+ /*
+ * Check the relative inode number against the last used
+ * relative inode number in this group. if it is greater
+ * we need to update the bg_itable_unused count
+ */
+ if (ino > free)
+ ext4_itable_unused_set(sb, gdp,
+ (EXT4_INODES_PER_GROUP(sb) - ino));
+ up_read(&grp->alloc_sem);
+ }
+ ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+ if (S_ISDIR(mode)) {
+ ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1);
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t f = ext4_flex_group(sbi, group);
+
+ atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+ }
+ }
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+ ext4_unlock_group(sb, group);
+ }
+
+ BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
+ if (err)
+ goto fail;
+
BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
if (err)
@@ -1101,7 +1055,7 @@ unsigned long ext4_count_dirs(struct super_block * sb)
* where it is called from on active part of filesystem is ext4lazyinit
* thread, so we do not need any special locks, however we have to prevent
* inode allocation from the current group, so we take alloc_sem lock, to
- * block ext4_claim_inode until we are finished.
+ * block ext4_new_inode() until we are finished.
*/
int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
int barrier)
@@ -1149,9 +1103,9 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
sbi->s_inodes_per_block);
if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
- ext4_error(sb, "Something is wrong with group %u\n"
- "Used itable blocks: %d"
- "itable unused count: %u\n",
+ ext4_error(sb, "Something is wrong with group %u: "
+ "used itable blocks: %d; "
+ "itable unused count: %u",
group, used_blks,
ext4_itable_unused_count(sb, gdp));
ret = 1;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index feaa82f..c77b0bd 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -272,7 +272,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
- "with only %d reserved data blocks\n",
+ "with only %d reserved data blocks",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
WARN_ON(1);
@@ -1165,7 +1165,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
*/
ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
- "data blocks\n", inode->i_ino, to_free,
+ "data blocks", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
WARN_ON(1);
to_free = ei->i_reserved_data_blocks;
@@ -1428,20 +1428,22 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- printk(KERN_CRIT "Total free blocks count %lld\n",
+ struct super_block *sb = inode->i_sb;
+
+ ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
EXT4_C2B(EXT4_SB(inode->i_sb),
ext4_count_free_clusters(inode->i_sb)));
- printk(KERN_CRIT "Free/Dirty block details\n");
- printk(KERN_CRIT "free_blocks=%lld\n",
+ ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
+ ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(inode->i_sb),
percpu_counter_sum(&sbi->s_freeclusters_counter)));
- printk(KERN_CRIT "dirty_blocks=%lld\n",
+ ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(inode->i_sb),
percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
- printk(KERN_CRIT "Block reservation details\n");
- printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
- EXT4_I(inode)->i_reserved_data_blocks);
- printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
+ ext4_msg(sb, KERN_CRIT, "Block reservation details");
+ ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
+ EXT4_I(inode)->i_reserved_data_blocks);
+ ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u",
EXT4_I(inode)->i_reserved_meta_blocks);
return;
}
@@ -2482,13 +2484,14 @@ static int ext4_da_write_end(struct file *file,
int write_mode = (int)(unsigned long)fsdata;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
- if (ext4_should_order_data(inode)) {
+ switch (ext4_inode_journal_mode(inode)) {
+ case EXT4_INODE_ORDERED_DATA_MODE:
return ext4_ordered_write_end(file, mapping, pos,
len, copied, page, fsdata);
- } else if (ext4_should_writeback_data(inode)) {
+ case EXT4_INODE_WRITEBACK_DATA_MODE:
return ext4_writeback_write_end(file, mapping, pos,
len, copied, page, fsdata);
- } else {
+ default:
BUG();
}
}
@@ -2763,7 +2766,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
goto out;
ext_debug("ext4_end_io_dio(): io_end 0x%p "
- "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
+ "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
iocb->private, io_end->inode->i_ino, iocb, offset,
size);
@@ -2795,9 +2798,6 @@ out:
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
-
- /* XXX: probably should move into the real I/O completion handler */
- inode_dio_done(inode);
}
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
@@ -2811,8 +2811,9 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
goto out;
if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
- printk("sb umounted, discard end_io request for inode %lu\n",
- io_end->inode->i_ino);
+ ext4_msg(io_end->inode->i_sb, KERN_INFO,
+ "sb umounted, discard end_io request for inode %lu",
+ io_end->inode->i_ino);
ext4_free_io_end(io_end);
goto out;
}
@@ -2921,9 +2922,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
iocb->private = NULL;
EXT4_I(inode)->cur_aio_dio = NULL;
if (!is_sync_kiocb(iocb)) {
- iocb->private = ext4_init_io_end(inode, GFP_NOFS);
- if (!iocb->private)
+ ext4_io_end_t *io_end =
+ ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_end)
return -ENOMEM;
+ io_end->flag |= EXT4_IO_END_DIRECT;
+ iocb->private = io_end;
/*
* we save the io structure for current async
* direct IO, so that later ext4_map_blocks()
@@ -2940,7 +2944,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
ext4_get_block_write,
ext4_end_io_dio,
NULL,
- DIO_LOCKING | DIO_SKIP_HOLES);
+ DIO_LOCKING);
if (iocb->private)
EXT4_I(inode)->cur_aio_dio = NULL;
/*
@@ -3086,18 +3090,25 @@ static const struct address_space_operations ext4_da_aops = {
void ext4_set_aops(struct inode *inode)
{
- if (ext4_should_order_data(inode) &&
- test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else if (ext4_should_order_data(inode))
- inode->i_mapping->a_ops = &ext4_ordered_aops;
- else if (ext4_should_writeback_data(inode) &&
- test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else if (ext4_should_writeback_data(inode))
- inode->i_mapping->a_ops = &ext4_writeback_aops;
- else
+ switch (ext4_inode_journal_mode(inode)) {
+ case EXT4_INODE_ORDERED_DATA_MODE:
+ if (test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_ordered_aops;
+ break;
+ case EXT4_INODE_WRITEBACK_DATA_MODE:
+ if (test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_writeback_aops;
+ break;
+ case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
+ break;
+ default:
+ BUG();
+ }
}
@@ -3329,16 +3340,16 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
struct inode *inode = file->f_path.dentry->d_inode;
if (!S_ISREG(inode->i_mode))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
/* TODO: Add support for non extent hole punching */
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
/* TODO: Add support for bigalloc file systems */
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
return ext4_ext_punch_hole(file, offset, length);
@@ -3924,10 +3935,8 @@ static int ext4_do_update_inode(handle_t *handle,
ext4_update_dynamic_rev(sb);
EXT4_SET_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
- sb->s_dirt = 1;
ext4_handle_sync(handle);
- err = ext4_handle_dirty_metadata(handle, NULL,
- EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_super(handle, sb);
}
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
@@ -4152,11 +4161,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
}
if (attr->ia_valid & ATTR_SIZE) {
- if (attr->ia_size != i_size_read(inode)) {
+ if (attr->ia_size != i_size_read(inode))
truncate_setsize(inode, attr->ia_size);
- ext4_truncate(inode);
- } else if (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
- ext4_truncate(inode);
+ ext4_truncate(inode);
}
if (!rc) {
@@ -4314,7 +4321,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
{
int err = 0;
- if (test_opt(inode->i_sb, I_VERSION))
+ if (IS_I_VERSION(inode))
inode_inc_iversion(inode);
/* the do_update_inode consumes one bh->b_count */
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cb990b2..99ab428 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -21,6 +21,7 @@
* mballoc.c contains the multiblocks allocation routines
*/
+#include "ext4_jbd2.h"
#include "mballoc.h"
#include <linux/debugfs.h>
#include <linux/slab.h>
@@ -339,7 +340,7 @@
*/
static struct kmem_cache *ext4_pspace_cachep;
static struct kmem_cache *ext4_ac_cachep;
-static struct kmem_cache *ext4_free_ext_cachep;
+static struct kmem_cache *ext4_free_data_cachep;
/* We create slab caches for groupinfo data structures based on the
* superblock block size. There will be one per mounted filesystem for
@@ -357,7 +358,8 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group);
static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
ext4_group_t group);
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
+static void ext4_free_data_callback(struct super_block *sb,
+ struct ext4_journal_cb_entry *jce, int rc);
static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
{
@@ -425,7 +427,7 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
{
char *bb;
- BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
+ BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
BUG_ON(max == NULL);
if (order > e4b->bd_blkbits + 1) {
@@ -436,10 +438,10 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
/* at order 0 we see each particular block */
if (order == 0) {
*max = 1 << (e4b->bd_blkbits + 3);
- return EXT4_MB_BITMAP(e4b);
+ return e4b->bd_bitmap;
}
- bb = EXT4_MB_BUDDY(e4b) + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
+ bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
*max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order];
return bb;
@@ -588,7 +590,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
for (j = 0; j < (1 << order); j++) {
k = (i * (1 << order)) + j;
MB_CHECK_ASSERT(
- !mb_test_bit(k, EXT4_MB_BITMAP(e4b)));
+ !mb_test_bit(k, e4b->bd_bitmap));
}
count++;
}
@@ -782,7 +784,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
int groups_per_page;
int err = 0;
int i;
- ext4_group_t first_group;
+ ext4_group_t first_group, group;
int first_block;
struct super_block *sb;
struct buffer_head *bhs;
@@ -806,24 +808,23 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
/* allocate buffer_heads to read bitmaps */
if (groups_per_page > 1) {
- err = -ENOMEM;
i = sizeof(struct buffer_head *) * groups_per_page;
bh = kzalloc(i, GFP_NOFS);
- if (bh == NULL)
+ if (bh == NULL) {
+ err = -ENOMEM;
goto out;
+ }
} else
bh = &bhs;
first_group = page->index * blocks_per_page / 2;
/* read all groups the page covers into the cache */
- for (i = 0; i < groups_per_page; i++) {
- struct ext4_group_desc *desc;
-
- if (first_group + i >= ngroups)
+ for (i = 0, group = first_group; i < groups_per_page; i++, group++) {
+ if (group >= ngroups)
break;
- grinfo = ext4_get_group_info(sb, first_group + i);
+ grinfo = ext4_get_group_info(sb, group);
/*
* If page is uptodate then we came here after online resize
* which added some new uninitialized group info structs, so
@@ -834,69 +835,21 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
bh[i] = NULL;
continue;
}
-
- err = -EIO;
- desc = ext4_get_group_desc(sb, first_group + i, NULL);
- if (desc == NULL)
- goto out;
-
- err = -ENOMEM;
- bh[i] = sb_getblk(sb, ext4_block_bitmap(sb, desc));
- if (bh[i] == NULL)
+ if (!(bh[i] = ext4_read_block_bitmap_nowait(sb, group))) {
+ err = -ENOMEM;
goto out;
-
- if (bitmap_uptodate(bh[i]))
- continue;
-
- lock_buffer(bh[i]);
- if (bitmap_uptodate(bh[i])) {
- unlock_buffer(bh[i]);
- continue;
- }
- ext4_lock_group(sb, first_group + i);
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
- ext4_init_block_bitmap(sb, bh[i],
- first_group + i, desc);
- set_bitmap_uptodate(bh[i]);
- set_buffer_uptodate(bh[i]);
- ext4_unlock_group(sb, first_group + i);
- unlock_buffer(bh[i]);
- continue;
}
- ext4_unlock_group(sb, first_group + i);
- if (buffer_uptodate(bh[i])) {
- /*
- * if not uninit if bh is uptodate,
- * bitmap is also uptodate
- */
- set_bitmap_uptodate(bh[i]);
- unlock_buffer(bh[i]);
- continue;
- }
- get_bh(bh[i]);
- /*
- * submit the buffer_head for read. We can
- * safely mark the bitmap as uptodate now.
- * We do it here so the bitmap uptodate bit
- * get set with buffer lock held.
- */
- set_bitmap_uptodate(bh[i]);
- bh[i]->b_end_io = end_buffer_read_sync;
- submit_bh(READ, bh[i]);
- mb_debug(1, "read bitmap for group %u\n", first_group + i);
+ mb_debug(1, "read bitmap for group %u\n", group);
}
/* wait for I/O completion */
- for (i = 0; i < groups_per_page; i++)
- if (bh[i])
- wait_on_buffer(bh[i]);
-
- err = -EIO;
- for (i = 0; i < groups_per_page; i++)
- if (bh[i] && !buffer_uptodate(bh[i]))
+ for (i = 0, group = first_group; i < groups_per_page; i++, group++) {
+ if (bh[i] && ext4_wait_block_bitmap(sb, group, bh[i])) {
+ err = -EIO;
goto out;
+ }
+ }
- err = 0;
first_block = page->index * blocks_per_page;
for (i = 0; i < blocks_per_page; i++) {
int group;
@@ -1250,10 +1203,10 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
int order = 1;
void *bb;
- BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
+ BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
BUG_ON(block >= (1 << (e4b->bd_blkbits + 3)));
- bb = EXT4_MB_BUDDY(e4b);
+ bb = e4b->bd_buddy;
while (order <= e4b->bd_blkbits + 1) {
block = block >> 1;
if (!mb_test_bit(block, bb)) {
@@ -1323,9 +1276,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
/* let's maintain fragments counter */
if (first != 0)
- block = !mb_test_bit(first - 1, EXT4_MB_BITMAP(e4b));
+ block = !mb_test_bit(first - 1, e4b->bd_bitmap);
if (first + count < EXT4_SB(sb)->s_mb_maxs[0])
- max = !mb_test_bit(first + count, EXT4_MB_BITMAP(e4b));
+ max = !mb_test_bit(first + count, e4b->bd_bitmap);
if (block && max)
e4b->bd_info->bb_fragments--;
else if (!block && !max)
@@ -1336,7 +1289,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
block = first++;
order = 0;
- if (!mb_test_bit(block, EXT4_MB_BITMAP(e4b))) {
+ if (!mb_test_bit(block, e4b->bd_bitmap)) {
ext4_fsblk_t blocknr;
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
@@ -1347,7 +1300,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
"freeing already freed block "
"(bit %u)", block);
}
- mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
+ mb_clear_bit(block, e4b->bd_bitmap);
e4b->bd_info->bb_counters[order]++;
/* start of the buddy */
@@ -1429,7 +1382,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
break;
next = (block + 1) * (1 << order);
- if (mb_test_bit(next, EXT4_MB_BITMAP(e4b)))
+ if (mb_test_bit(next, e4b->bd_bitmap))
break;
order = mb_find_order_for_block(e4b, next);
@@ -1466,9 +1419,9 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
/* let's maintain fragments counter */
if (start != 0)
- mlen = !mb_test_bit(start - 1, EXT4_MB_BITMAP(e4b));
+ mlen = !mb_test_bit(start - 1, e4b->bd_bitmap);
if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0])
- max = !mb_test_bit(start + len, EXT4_MB_BITMAP(e4b));
+ max = !mb_test_bit(start + len, e4b->bd_bitmap);
if (mlen && max)
e4b->bd_info->bb_fragments++;
else if (!mlen && !max)
@@ -1511,7 +1464,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
}
mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
- ext4_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+ ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
mb_check_buddy(e4b);
return ret;
@@ -1810,7 +1763,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
struct ext4_buddy *e4b)
{
struct super_block *sb = ac->ac_sb;
- void *bitmap = EXT4_MB_BITMAP(e4b);
+ void *bitmap = e4b->bd_bitmap;
struct ext4_free_extent ex;
int i;
int free;
@@ -1870,7 +1823,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
{
struct super_block *sb = ac->ac_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- void *bitmap = EXT4_MB_BITMAP(e4b);
+ void *bitmap = e4b->bd_bitmap;
struct ext4_free_extent ex;
ext4_fsblk_t first_group_block;
ext4_fsblk_t a;
@@ -2224,7 +2177,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
EXT4_DESC_PER_BLOCK_BITS(sb);
meta_group_info = kmalloc(metalen, GFP_KERNEL);
if (meta_group_info == NULL) {
- ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate mem "
+ ext4_msg(sb, KERN_ERR, "can't allocate mem "
"for a buddy group");
goto exit_meta_group_info;
}
@@ -2238,7 +2191,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
if (meta_group_info[i] == NULL) {
- ext4_msg(sb, KERN_ERR, "EXT4-fs: can't allocate buddy mem");
+ ext4_msg(sb, KERN_ERR, "can't allocate buddy mem");
goto exit_group_info;
}
memset(meta_group_info[i], 0, kmem_cache_size(cachep));
@@ -2522,9 +2475,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
&ext4_mb_seq_groups_fops, sb);
- if (sbi->s_journal)
- sbi->s_journal->j_commit_callback = release_blocks_on_commit;
-
return 0;
out_free_locality_groups:
@@ -2637,58 +2587,55 @@ static inline int ext4_issue_discard(struct super_block *sb,
* This function is called by the jbd2 layer once the commit has finished,
* so we know we can free the blocks that were released with that commit.
*/
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
+static void ext4_free_data_callback(struct super_block *sb,
+ struct ext4_journal_cb_entry *jce,
+ int rc)
{
- struct super_block *sb = journal->j_private;
+ struct ext4_free_data *entry = (struct ext4_free_data *)jce;
struct ext4_buddy e4b;
struct ext4_group_info *db;
int err, count = 0, count2 = 0;
- struct ext4_free_data *entry;
- struct list_head *l, *ltmp;
- list_for_each_safe(l, ltmp, &txn->t_private_list) {
- entry = list_entry(l, struct ext4_free_data, list);
+ mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
+ entry->efd_count, entry->efd_group, entry);
- mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
- entry->count, entry->group, entry);
+ if (test_opt(sb, DISCARD))
+ ext4_issue_discard(sb, entry->efd_group,
+ entry->efd_start_cluster, entry->efd_count);
- if (test_opt(sb, DISCARD))
- ext4_issue_discard(sb, entry->group,
- entry->start_cluster, entry->count);
+ err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b);
+ /* we expect to find existing buddy because it's pinned */
+ BUG_ON(err != 0);
- err = ext4_mb_load_buddy(sb, entry->group, &e4b);
- /* we expect to find existing buddy because it's pinned */
- BUG_ON(err != 0);
- db = e4b.bd_info;
- /* there are blocks to put in buddy to make them really free */
- count += entry->count;
- count2++;
- ext4_lock_group(sb, entry->group);
- /* Take it out of per group rb tree */
- rb_erase(&entry->node, &(db->bb_free_root));
- mb_free_blocks(NULL, &e4b, entry->start_cluster, entry->count);
+ db = e4b.bd_info;
+ /* there are blocks to put in buddy to make them really free */
+ count += entry->efd_count;
+ count2++;
+ ext4_lock_group(sb, entry->efd_group);
+ /* Take it out of per group rb tree */
+ rb_erase(&entry->efd_node, &(db->bb_free_root));
+ mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count);
- /*
- * Clear the trimmed flag for the group so that the next
- * ext4_trim_fs can trim it.
- * If the volume is mounted with -o discard, online discard
- * is supported and the free blocks will be trimmed online.
- */
- if (!test_opt(sb, DISCARD))
- EXT4_MB_GRP_CLEAR_TRIMMED(db);
+ /*
+ * Clear the trimmed flag for the group so that the next
+ * ext4_trim_fs can trim it.
+ * If the volume is mounted with -o discard, online discard
+ * is supported and the free blocks will be trimmed online.
+ */
+ if (!test_opt(sb, DISCARD))
+ EXT4_MB_GRP_CLEAR_TRIMMED(db);
- if (!db->bb_free_root.rb_node) {
- /* No more items in the per group rb tree
- * balance refcounts from ext4_mb_free_metadata()
- */
- page_cache_release(e4b.bd_buddy_page);
- page_cache_release(e4b.bd_bitmap_page);
- }
- ext4_unlock_group(sb, entry->group);
- kmem_cache_free(ext4_free_ext_cachep, entry);
- ext4_mb_unload_buddy(&e4b);
+ if (!db->bb_free_root.rb_node) {
+ /* No more items in the per group rb tree
+ * balance refcounts from ext4_mb_free_metadata()
+ */
+ page_cache_release(e4b.bd_buddy_page);
+ page_cache_release(e4b.bd_bitmap_page);
}
+ ext4_unlock_group(sb, entry->efd_group);
+ kmem_cache_free(ext4_free_data_cachep, entry);
+ ext4_mb_unload_buddy(&e4b);
mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
}
@@ -2741,9 +2688,9 @@ int __init ext4_init_mballoc(void)
return -ENOMEM;
}
- ext4_free_ext_cachep = KMEM_CACHE(ext4_free_data,
- SLAB_RECLAIM_ACCOUNT);
- if (ext4_free_ext_cachep == NULL) {
+ ext4_free_data_cachep = KMEM_CACHE(ext4_free_data,
+ SLAB_RECLAIM_ACCOUNT);
+ if (ext4_free_data_cachep == NULL) {
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
return -ENOMEM;
@@ -2761,7 +2708,7 @@ void ext4_exit_mballoc(void)
rcu_barrier();
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
- kmem_cache_destroy(ext4_free_ext_cachep);
+ kmem_cache_destroy(ext4_free_data_cachep);
ext4_groupinfo_destroy_slabs();
ext4_remove_debugfs_entry();
}
@@ -2815,7 +2762,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
if (!ext4_data_block_valid(sbi, block, len)) {
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
- "fs metadata\n", block, block+len);
+ "fs metadata", block, block+len);
/* File system mounted not to panic on error
* Fix the bitmap and repeat the block allocation
* We leak some of the blocks here.
@@ -2911,7 +2858,8 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int bsbits, max;
ext4_lblk_t end;
- loff_t size, orig_size, start_off;
+ loff_t size, start_off;
+ loff_t orig_size __maybe_unused;
ext4_lblk_t start;
struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
struct ext4_prealloc_space *pa;
@@ -3321,8 +3269,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
n = rb_first(&(grp->bb_free_root));
while (n) {
- entry = rb_entry(n, struct ext4_free_data, node);
- ext4_set_bits(bitmap, entry->start_cluster, entry->count);
+ entry = rb_entry(n, struct ext4_free_data, efd_node);
+ ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
n = rb_next(n);
}
return;
@@ -3916,11 +3864,11 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
return;
- ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: Can't allocate:"
+ ext4_msg(ac->ac_sb, KERN_ERR, "Can't allocate:"
" Allocation context details:");
- ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: status %d flags %d",
+ ext4_msg(ac->ac_sb, KERN_ERR, "status %d flags %d",
ac->ac_status, ac->ac_flags);
- ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: orig %lu/%lu/%lu@%lu, "
+ ext4_msg(ac->ac_sb, KERN_ERR, "orig %lu/%lu/%lu@%lu, "
"goal %lu/%lu/%lu@%lu, "
"best %lu/%lu/%lu@%lu cr %d",
(unsigned long)ac->ac_o_ex.fe_group,
@@ -3936,9 +3884,9 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
(unsigned long)ac->ac_b_ex.fe_len,
(unsigned long)ac->ac_b_ex.fe_logical,
(int)ac->ac_criteria);
- ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: %lu scanned, %d found",
+ ext4_msg(ac->ac_sb, KERN_ERR, "%lu scanned, %d found",
ac->ac_ex_scanned, ac->ac_found);
- ext4_msg(ac->ac_sb, KERN_ERR, "EXT4-fs: groups: ");
+ ext4_msg(ac->ac_sb, KERN_ERR, "groups: ");
ngroups = ext4_get_groups_count(sb);
for (i = 0; i < ngroups; i++) {
struct ext4_group_info *grp = ext4_get_group_info(sb, i);
@@ -4428,9 +4376,9 @@ out:
static int can_merge(struct ext4_free_data *entry1,
struct ext4_free_data *entry2)
{
- if ((entry1->t_tid == entry2->t_tid) &&
- (entry1->group == entry2->group) &&
- ((entry1->start_cluster + entry1->count) == entry2->start_cluster))
+ if ((entry1->efd_tid == entry2->efd_tid) &&
+ (entry1->efd_group == entry2->efd_group) &&
+ ((entry1->efd_start_cluster + entry1->efd_count) == entry2->efd_start_cluster))
return 1;
return 0;
}
@@ -4452,8 +4400,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
- new_node = &new_entry->node;
- cluster = new_entry->start_cluster;
+ new_node = &new_entry->efd_node;
+ cluster = new_entry->efd_start_cluster;
if (!*n) {
/* first free block exent. We need to
@@ -4466,10 +4414,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
}
while (*n) {
parent = *n;
- entry = rb_entry(parent, struct ext4_free_data, node);
- if (cluster < entry->start_cluster)
+ entry = rb_entry(parent, struct ext4_free_data, efd_node);
+ if (cluster < entry->efd_start_cluster)
n = &(*n)->rb_left;
- else if (cluster >= (entry->start_cluster + entry->count))
+ else if (cluster >= (entry->efd_start_cluster + entry->efd_count))
n = &(*n)->rb_right;
else {
ext4_grp_locked_error(sb, group, 0,
@@ -4486,34 +4434,29 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
/* Now try to see the extent can be merged to left and right */
node = rb_prev(new_node);
if (node) {
- entry = rb_entry(node, struct ext4_free_data, node);
+ entry = rb_entry(node, struct ext4_free_data, efd_node);
if (can_merge(entry, new_entry)) {
- new_entry->start_cluster = entry->start_cluster;
- new_entry->count += entry->count;
+ new_entry->efd_start_cluster = entry->efd_start_cluster;
+ new_entry->efd_count += entry->efd_count;
rb_erase(node, &(db->bb_free_root));
- spin_lock(&sbi->s_md_lock);
- list_del(&entry->list);
- spin_unlock(&sbi->s_md_lock);
- kmem_cache_free(ext4_free_ext_cachep, entry);
+ ext4_journal_callback_del(handle, &entry->efd_jce);
+ kmem_cache_free(ext4_free_data_cachep, entry);
}
}
node = rb_next(new_node);
if (node) {
- entry = rb_entry(node, struct ext4_free_data, node);
+ entry = rb_entry(node, struct ext4_free_data, efd_node);
if (can_merge(new_entry, entry)) {
- new_entry->count += entry->count;
+ new_entry->efd_count += entry->efd_count;
rb_erase(node, &(db->bb_free_root));
- spin_lock(&sbi->s_md_lock);
- list_del(&entry->list);
- spin_unlock(&sbi->s_md_lock);
- kmem_cache_free(ext4_free_ext_cachep, entry);
+ ext4_journal_callback_del(handle, &entry->efd_jce);
+ kmem_cache_free(ext4_free_data_cachep, entry);
}
}
/* Add the extent to transaction's private list */
- spin_lock(&sbi->s_md_lock);
- list_add(&new_entry->list, &handle->h_transaction->t_private_list);
- spin_unlock(&sbi->s_md_lock);
+ ext4_journal_callback_add(handle, ext4_free_data_callback,
+ &new_entry->efd_jce);
return 0;
}
@@ -4691,15 +4634,15 @@ do_more:
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
*/
- new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
if (!new_entry) {
err = -ENOMEM;
goto error_return;
}
- new_entry->start_cluster = bit;
- new_entry->group = block_group;
- new_entry->count = count_clusters;
- new_entry->t_tid = handle->h_transaction->t_tid;
+ new_entry->efd_start_cluster = bit;
+ new_entry->efd_group = block_group;
+ new_entry->efd_count = count_clusters;
+ new_entry->efd_tid = handle->h_transaction->t_tid;
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
@@ -4971,11 +4914,11 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
start = (e4b.bd_info->bb_first_free > start) ?
e4b.bd_info->bb_first_free : start;
- while (start < max) {
- start = mb_find_next_zero_bit(bitmap, max, start);
- if (start >= max)
+ while (start <= max) {
+ start = mb_find_next_zero_bit(bitmap, max + 1, start);
+ if (start > max)
break;
- next = mb_find_next_bit(bitmap, max, start);
+ next = mb_find_next_bit(bitmap, max + 1, start);
if ((next - start) >= minblocks) {
ext4_trim_extent(sb, start,
@@ -5027,37 +4970,36 @@ out:
int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
{
struct ext4_group_info *grp;
- ext4_group_t first_group, last_group;
- ext4_group_t group, ngroups = ext4_get_groups_count(sb);
+ ext4_group_t group, first_group, last_group;
ext4_grpblk_t cnt = 0, first_cluster, last_cluster;
- uint64_t start, len, minlen, trimmed = 0;
+ uint64_t start, end, minlen, trimmed = 0;
ext4_fsblk_t first_data_blk =
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+ ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
int ret = 0;
start = range->start >> sb->s_blocksize_bits;
- len = range->len >> sb->s_blocksize_bits;
+ end = start + (range->len >> sb->s_blocksize_bits) - 1;
minlen = range->minlen >> sb->s_blocksize_bits;
- if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)))
+ if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) ||
+ unlikely(start >= max_blks))
return -EINVAL;
- if (start + len <= first_data_blk)
+ if (end >= max_blks)
+ end = max_blks - 1;
+ if (end <= first_data_blk)
goto out;
- if (start < first_data_blk) {
- len -= first_data_blk - start;
+ if (start < first_data_blk)
start = first_data_blk;
- }
- /* Determine first and last group to examine based on start and len */
+ /* Determine first and last group to examine based on start and end */
ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
&first_group, &first_cluster);
- ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
+ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end,
&last_group, &last_cluster);
- last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
- last_cluster = EXT4_CLUSTERS_PER_GROUP(sb);
- if (first_group > last_group)
- return -EINVAL;
+ /* end now represents the last cluster to discard in this group */
+ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
for (group = first_group; group <= last_group; group++) {
grp = ext4_get_group_info(sb, group);
@@ -5069,31 +5011,35 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
}
/*
- * For all the groups except the last one, last block will
- * always be EXT4_BLOCKS_PER_GROUP(sb), so we only need to
- * change it for the last group in which case start +
- * len < EXT4_BLOCKS_PER_GROUP(sb).
+ * For all the groups except the last one, last cluster will
+ * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to
+ * change it for the last group, note that last_cluster is
+ * already computed earlier by ext4_get_group_no_and_offset()
*/
- if (first_cluster + len < EXT4_CLUSTERS_PER_GROUP(sb))
- last_cluster = first_cluster + len;
- len -= last_cluster - first_cluster;
+ if (group == last_group)
+ end = last_cluster;
if (grp->bb_free >= minlen) {
cnt = ext4_trim_all_free(sb, group, first_cluster,
- last_cluster, minlen);
+ end, minlen);
if (cnt < 0) {
ret = cnt;
break;
}
+ trimmed += cnt;
}
- trimmed += cnt;
+
+ /*
+ * For every group except the first one, we are sure
+ * that the first cluster to discard will be cluster #0.
+ */
first_cluster = 0;
}
- range->len = trimmed * sb->s_blocksize;
if (!ret)
atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
out:
+ range->len = trimmed * sb->s_blocksize;
return ret;
}
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 47705f3..c070618 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -96,21 +96,23 @@ extern u8 mb_enable_debug;
struct ext4_free_data {
- /* this links the free block information from group_info */
- struct rb_node node;
+ /* MUST be the first member */
+ struct ext4_journal_cb_entry efd_jce;
+
+ /* ext4_free_data private data starts from here */
- /* this links the free block information from ext4_sb_info */
- struct list_head list;
+ /* this links the free block information from group_info */
+ struct rb_node efd_node;
/* group which free block extent belongs */
- ext4_group_t group;
+ ext4_group_t efd_group;
/* free block extent */
- ext4_grpblk_t start_cluster;
- ext4_grpblk_t count;
+ ext4_grpblk_t efd_start_cluster;
+ ext4_grpblk_t efd_count;
/* transaction which freed this extent */
- tid_t t_tid;
+ tid_t efd_tid;
};
struct ext4_prealloc_space {
@@ -210,8 +212,6 @@ struct ext4_buddy {
__u16 bd_blkbits;
ext4_group_t bd_group;
};
-#define EXT4_MB_BITMAP(e4b) ((e4b)->bd_bitmap)
-#define EXT4_MB_BUDDY(e4b) ((e4b)->bd_buddy)
static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
struct ext4_free_extent *fex)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index e7d6bb0..f39f80f 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -471,7 +471,7 @@ int ext4_ext_migrate(struct inode *inode)
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
S_IFREG, NULL, goal, owner);
if (IS_ERR(tmp_inode)) {
- retval = PTR_ERR(inode);
+ retval = PTR_ERR(tmp_inode);
ext4_journal_stop(handle);
return retval;
}
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 7ea4ba4..ed6548d 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -257,8 +257,8 @@ int ext4_multi_mount_protect(struct super_block *sb,
* If check_interval in MMP block is larger, use that instead of
* update_interval from the superblock.
*/
- if (mmp->mmp_check_interval > mmp_check_interval)
- mmp_check_interval = mmp->mmp_check_interval;
+ if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval)
+ mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval);
seq = le32_to_cpu(mmp->mmp_seq);
if (seq == EXT4_MMP_SEQ_CLEAN)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2043f48..349d7b3 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -468,7 +468,7 @@ fail2:
fail:
if (*err == ERR_BAD_DX_DIR)
ext4_warning(dir->i_sb,
- "Corrupt dir inode %ld, running e2fsck is "
+ "Corrupt dir inode %lu, running e2fsck is "
"recommended.", dir->i_ino);
return NULL;
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 4758518..74cd1f7 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -60,7 +60,6 @@ void ext4_ioend_wait(struct inode *inode)
static void put_io_page(struct ext4_io_page *io_page)
{
if (atomic_dec_and_test(&io_page->p_count)) {
- end_page_writeback(io_page->p_page);
put_page(io_page->p_page);
kmem_cache_free(io_page_cachep, io_page);
}
@@ -110,6 +109,8 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
+ if (io->flag & EXT4_IO_END_DIRECT)
+ inode_dio_done(inode);
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
wake_up_all(ext4_ioend_wq(io->inode));
@@ -127,12 +128,18 @@ static void ext4_end_io_work(struct work_struct *work)
unsigned long flags;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ if (io->flag & EXT4_IO_END_IN_FSYNC)
+ goto requeue;
if (list_empty(&io->list)) {
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
goto free;
}
if (!mutex_trylock(&inode->i_mutex)) {
+ bool was_queued;
+requeue:
+ was_queued = !!(io->flag & EXT4_IO_END_QUEUED);
+ io->flag |= EXT4_IO_END_QUEUED;
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/*
* Requeue the work instead of waiting so that the work
@@ -145,9 +152,8 @@ static void ext4_end_io_work(struct work_struct *work)
* yield the cpu if it sees an end_io request that has already
* been requeued.
*/
- if (io->flag & EXT4_IO_END_QUEUED)
+ if (was_queued)
yield();
- io->flag |= EXT4_IO_END_QUEUED;
return;
}
list_del_init(&io->list);
@@ -227,9 +233,9 @@ static void ext4_end_bio(struct bio *bio, int error)
} while (bh != head);
}
- put_io_page(io_end->pages[i]);
+ if (atomic_read(&io_end->pages[i]->p_count) == 1)
+ end_page_writeback(io_end->pages[i]->p_page);
}
- io_end->num_io_pages = 0;
inode = io_end->inode;
if (error) {
@@ -421,6 +427,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
+ if (atomic_read(&io_page->p_count) == 1)
+ end_page_writeback(page);
put_io_page(io_page);
return ret;
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f9d948f..59fa0be 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1163,8 +1163,11 @@ static void ext4_update_super(struct super_block *sb,
do_div(reserved_blocks, 100);
ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
+ ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
flex_gd->count);
+ le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) *
+ flex_gd->count);
/*
* We need to protect s_groups_count against other CPUs seeing
@@ -1465,6 +1468,7 @@ static int ext4_group_extend_no_check(struct super_block *sb,
}
ext4_blocks_count_set(es, o_blocks_count + add);
+ ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
@@ -1512,16 +1516,17 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
o_blocks_count = ext4_blocks_count(es);
if (test_opt(sb, DEBUG))
- printk(KERN_DEBUG "EXT4-fs: extending last group from %llu to %llu blocks\n",
- o_blocks_count, n_blocks_count);
+ ext4_msg(sb, KERN_DEBUG,
+ "extending last group from %llu to %llu blocks",
+ o_blocks_count, n_blocks_count);
if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
return 0;
if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
- printk(KERN_ERR "EXT4-fs: filesystem on %s:"
- " too large to resize to %llu blocks safely\n",
- sb->s_id, n_blocks_count);
+ ext4_msg(sb, KERN_ERR,
+ "filesystem too large to resize to %llu blocks safely",
+ n_blocks_count);
if (sizeof(sector_t) < 8)
ext4_warning(sb, "CONFIG_LBDAF not enabled");
return -EINVAL;
@@ -1582,7 +1587,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
ext4_fsblk_t o_blocks_count;
ext4_group_t o_group;
ext4_group_t n_group;
- ext4_grpblk_t offset;
+ ext4_grpblk_t offset, add;
unsigned long n_desc_blocks;
unsigned long o_desc_blocks;
unsigned long desc_blocks;
@@ -1591,8 +1596,8 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
o_blocks_count = ext4_blocks_count(es);
if (test_opt(sb, DEBUG))
- printk(KERN_DEBUG "EXT4-fs: resizing filesystem from %llu "
- "upto %llu blocks\n", o_blocks_count, n_blocks_count);
+ ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu "
+ "to %llu blocks", o_blocks_count, n_blocks_count);
if (n_blocks_count < o_blocks_count) {
/* On-line shrinking not supported */
@@ -1605,7 +1610,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
return 0;
ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
- ext4_get_group_no_and_offset(sb, o_blocks_count, &o_group, &offset);
+ ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
EXT4_DESC_PER_BLOCK(sb);
@@ -1634,10 +1639,12 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
}
brelse(bh);
- if (offset != 0) {
- /* extend the last group */
- ext4_grpblk_t add;
- add = EXT4_BLOCKS_PER_GROUP(sb) - offset;
+ /* extend the last group */
+ if (n_group == o_group)
+ add = n_blocks_count - o_blocks_count;
+ else
+ add = EXT4_BLOCKS_PER_GROUP(sb) - (offset + 1);
+ if (add > 0) {
err = ext4_group_extend_no_check(sb, o_blocks_count, add);
if (err)
goto out;
@@ -1674,7 +1681,7 @@ out:
iput(resize_inode);
if (test_opt(sb, DEBUG))
- printk(KERN_DEBUG "EXT4-fs: resized filesystem from %llu "
- "upto %llu blocks\n", o_blocks_count, n_blocks_count);
+ ext4_msg(sb, KERN_DEBUG, "resized filesystem from %llu "
+ "upto %llu blocks", o_blocks_count, n_blocks_count);
return err;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 502c61f..ceebaf8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -62,6 +62,7 @@ static struct ext4_features *ext4_feat;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
+static int ext4_show_options(struct seq_file *seq, struct dentry *root);
static int ext4_commit_super(struct super_block *sb, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
@@ -375,7 +376,7 @@ void ext4_journal_abort_handle(const char *caller, unsigned int line,
if (is_handle_aborted(handle))
return;
- printk(KERN_ERR "%s:%d: aborting transaction: %s in %s\n",
+ printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
caller, line, errstr, err_fn);
jbd2_journal_abort_handle(handle);
@@ -431,6 +432,22 @@ static int block_device_ejected(struct super_block *sb)
return bdi->dev == NULL;
}
+static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
+{
+ struct super_block *sb = journal->j_private;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ int error = is_journal_aborted(journal);
+ struct ext4_journal_cb_entry *jce, *tmp;
+
+ spin_lock(&sbi->s_md_lock);
+ list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) {
+ list_del_init(&jce->jce_list);
+ spin_unlock(&sbi->s_md_lock);
+ jce->jce_func(sb, jce, error);
+ spin_lock(&sbi->s_md_lock);
+ }
+ spin_unlock(&sbi->s_md_lock);
+}
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
@@ -498,11 +515,16 @@ void ext4_error_inode(struct inode *inode, const char *function,
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
- inode->i_sb->s_id, function, line, inode->i_ino);
if (block)
- printk(KERN_CONT "block %llu: ", block);
- printk(KERN_CONT "comm %s: %pV\n", current->comm, &vaf);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: block %llu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, &vaf);
+ else
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, &vaf);
va_end(args);
ext4_handle_error(inode->i_sb);
@@ -524,15 +546,21 @@ void ext4_error_file(struct file *file, const char *function,
path = d_path(&(file->f_path), pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
- inode->i_sb->s_id, function, line, inode->i_ino);
- if (block)
- printk(KERN_CONT "block %llu: ", block);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_CONT "comm %s: path %s: %pV\n", current->comm, path, &vaf);
+ if (block)
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "block %llu: comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, path, &vaf);
+ else
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, path, &vaf);
va_end(args);
ext4_handle_error(inode->i_sb);
@@ -808,9 +836,6 @@ static void ext4_put_super(struct super_block *sb)
destroy_workqueue(sbi->dio_unwritten_wq);
lock_super(sb);
- if (sb->s_dirt)
- ext4_commit_super(sb, 1);
-
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
@@ -827,9 +852,12 @@ static void ext4_put_super(struct super_block *sb)
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
- ext4_commit_super(sb, 1);
}
+ if (sb->s_dirt || !(sb->s_flags & MS_RDONLY))
+ ext4_commit_super(sb, 1);
+
if (sbi->s_proc) {
+ remove_proc_entry("options", sbi->s_proc);
remove_proc_entry(sb->s_id, ext4_proc_root);
}
kobject_del(&sbi->s_kobj);
@@ -990,180 +1018,6 @@ void ext4_clear_inode(struct inode *inode)
}
}
-static inline void ext4_show_quota_options(struct seq_file *seq,
- struct super_block *sb)
-{
-#if defined(CONFIG_QUOTA)
- struct ext4_sb_info *sbi = EXT4_SB(sb);
-
- if (sbi->s_jquota_fmt) {
- char *fmtname = "";
-
- switch (sbi->s_jquota_fmt) {
- case QFMT_VFS_OLD:
- fmtname = "vfsold";
- break;
- case QFMT_VFS_V0:
- fmtname = "vfsv0";
- break;
- case QFMT_VFS_V1:
- fmtname = "vfsv1";
- break;
- }
- seq_printf(seq, ",jqfmt=%s", fmtname);
- }
-
- if (sbi->s_qf_names[USRQUOTA])
- seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
-
- if (sbi->s_qf_names[GRPQUOTA])
- seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
-
- if (test_opt(sb, USRQUOTA))
- seq_puts(seq, ",usrquota");
-
- if (test_opt(sb, GRPQUOTA))
- seq_puts(seq, ",grpquota");
-#endif
-}
-
-/*
- * Show an option if
- * - it's set to a non-default value OR
- * - if the per-sb default is different from the global default
- */
-static int ext4_show_options(struct seq_file *seq, struct dentry *root)
-{
- int def_errors;
- unsigned long def_mount_opts;
- struct super_block *sb = root->d_sb;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_super_block *es = sbi->s_es;
-
- def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
- def_errors = le16_to_cpu(es->s_errors);
-
- if (sbi->s_sb_block != 1)
- seq_printf(seq, ",sb=%llu", sbi->s_sb_block);
- if (test_opt(sb, MINIX_DF))
- seq_puts(seq, ",minixdf");
- if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS))
- seq_puts(seq, ",grpid");
- if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS))
- seq_puts(seq, ",nogrpid");
- if (sbi->s_resuid != EXT4_DEF_RESUID ||
- le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) {
- seq_printf(seq, ",resuid=%u", sbi->s_resuid);
- }
- if (sbi->s_resgid != EXT4_DEF_RESGID ||
- le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) {
- seq_printf(seq, ",resgid=%u", sbi->s_resgid);
- }
- if (test_opt(sb, ERRORS_RO)) {
- if (def_errors == EXT4_ERRORS_PANIC ||
- def_errors == EXT4_ERRORS_CONTINUE) {
- seq_puts(seq, ",errors=remount-ro");
- }
- }
- if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
- seq_puts(seq, ",errors=continue");
- if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
- seq_puts(seq, ",errors=panic");
- if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16))
- seq_puts(seq, ",nouid32");
- if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
- seq_puts(seq, ",debug");
-#ifdef CONFIG_EXT4_FS_XATTR
- if (test_opt(sb, XATTR_USER))
- seq_puts(seq, ",user_xattr");
- if (!test_opt(sb, XATTR_USER))
- seq_puts(seq, ",nouser_xattr");
-#endif
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
- if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
- seq_puts(seq, ",acl");
- if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
- seq_puts(seq, ",noacl");
-#endif
- if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
- seq_printf(seq, ",commit=%u",
- (unsigned) (sbi->s_commit_interval / HZ));
- }
- if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
- seq_printf(seq, ",min_batch_time=%u",
- (unsigned) sbi->s_min_batch_time);
- }
- if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
- seq_printf(seq, ",max_batch_time=%u",
- (unsigned) sbi->s_max_batch_time);
- }
-
- /*
- * We're changing the default of barrier mount option, so
- * let's always display its mount state so it's clear what its
- * status is.
- */
- seq_puts(seq, ",barrier=");
- seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
- if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
- seq_puts(seq, ",journal_async_commit");
- else if (test_opt(sb, JOURNAL_CHECKSUM))
- seq_puts(seq, ",journal_checksum");
- if (test_opt(sb, I_VERSION))
- seq_puts(seq, ",i_version");
- if (!test_opt(sb, DELALLOC) &&
- !(def_mount_opts & EXT4_DEFM_NODELALLOC))
- seq_puts(seq, ",nodelalloc");
-
- if (!test_opt(sb, MBLK_IO_SUBMIT))
- seq_puts(seq, ",nomblk_io_submit");
- if (sbi->s_stripe)
- seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
- /*
- * journal mode get enabled in different ways
- * So just print the value even if we didn't specify it
- */
- if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
- seq_puts(seq, ",data=journal");
- else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
- seq_puts(seq, ",data=ordered");
- else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
- seq_puts(seq, ",data=writeback");
-
- if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
- seq_printf(seq, ",inode_readahead_blks=%u",
- sbi->s_inode_readahead_blks);
-
- if (test_opt(sb, DATA_ERR_ABORT))
- seq_puts(seq, ",data_err=abort");
-
- if (test_opt(sb, NO_AUTO_DA_ALLOC))
- seq_puts(seq, ",noauto_da_alloc");
-
- if (test_opt(sb, DISCARD) && !(def_mount_opts & EXT4_DEFM_DISCARD))
- seq_puts(seq, ",discard");
-
- if (test_opt(sb, NOLOAD))
- seq_puts(seq, ",norecovery");
-
- if (test_opt(sb, DIOREAD_NOLOCK))
- seq_puts(seq, ",dioread_nolock");
-
- if (test_opt(sb, BLOCK_VALIDITY) &&
- !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
- seq_puts(seq, ",block_validity");
-
- if (!test_opt(sb, INIT_INODE_TABLE))
- seq_puts(seq, ",noinit_itable");
- else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
- seq_printf(seq, ",init_itable=%u",
- (unsigned) sbi->s_li_wait_mult);
-
- ext4_show_quota_options(seq, sb);
-
- return 0;
-}
-
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
@@ -1316,18 +1170,17 @@ static const struct export_operations ext4_export_ops = {
enum {
Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
- Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
+ Opt_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
- Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_nobh, Opt_bh,
+ Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
- Opt_journal_update, Opt_journal_dev,
- Opt_journal_checksum, Opt_journal_async_commit,
+ Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
- Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
- Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
+ Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
+ Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
@@ -1350,20 +1203,19 @@ static const match_table_t tokens = {
{Opt_err_ro, "errors=remount-ro"},
{Opt_nouid32, "nouid32"},
{Opt_debug, "debug"},
- {Opt_oldalloc, "oldalloc"},
- {Opt_orlov, "orlov"},
+ {Opt_removed, "oldalloc"},
+ {Opt_removed, "orlov"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
- {Opt_noload, "noload"},
{Opt_noload, "norecovery"},
- {Opt_nobh, "nobh"},
- {Opt_bh, "bh"},
+ {Opt_noload, "noload"},
+ {Opt_removed, "nobh"},
+ {Opt_removed, "bh"},
{Opt_commit, "commit=%u"},
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
- {Opt_journal_update, "journal=update"},
{Opt_journal_dev, "journal_dev=%u"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
@@ -1389,7 +1241,6 @@ static const match_table_t tokens = {
{Opt_nobarrier, "nobarrier"},
{Opt_i_version, "i_version"},
{Opt_stripe, "stripe=%u"},
- {Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_mblk_io_submit, "mblk_io_submit"},
@@ -1408,6 +1259,11 @@ static const match_table_t tokens = {
{Opt_init_itable, "init_itable=%u"},
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
+ {Opt_removed, "check=none"}, /* mount option from ext2/3 */
+ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */
+ {Opt_removed, "reservation"}, /* mount option from ext2/3 */
+ {Opt_removed, "noreservation"}, /* mount option from ext2/3 */
+ {Opt_removed, "journal=%u"}, /* mount option from ext2/3 */
{Opt_err, NULL},
};
@@ -1496,420 +1352,273 @@ static int clear_qf_name(struct super_block *sb, int qtype)
}
#endif
-static int parse_options(char *options, struct super_block *sb,
- unsigned long *journal_devnum,
- unsigned int *journal_ioprio,
- ext4_fsblk_t *n_blocks_count, int is_remount)
-{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int data_opt = 0;
- int option;
+#define MOPT_SET 0x0001
+#define MOPT_CLEAR 0x0002
+#define MOPT_NOSUPPORT 0x0004
+#define MOPT_EXPLICIT 0x0008
+#define MOPT_CLEAR_ERR 0x0010
+#define MOPT_GTE0 0x0020
#ifdef CONFIG_QUOTA
- int qfmt;
+#define MOPT_Q 0
+#define MOPT_QFMT 0x0040
+#else
+#define MOPT_Q MOPT_NOSUPPORT
+#define MOPT_QFMT MOPT_NOSUPPORT
#endif
-
- if (!options)
- return 1;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
- if (!*p)
- continue;
-
- /*
- * Initialize args struct so we know whether arg was
- * found; some options take optional arguments.
- */
- args[0].to = args[0].from = NULL;
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_bsd_df:
- ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- clear_opt(sb, MINIX_DF);
- break;
- case Opt_minix_df:
- ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- set_opt(sb, MINIX_DF);
-
- break;
- case Opt_grpid:
- ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- set_opt(sb, GRPID);
-
- break;
- case Opt_nogrpid:
- ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- clear_opt(sb, GRPID);
-
- break;
- case Opt_resuid:
- if (match_int(&args[0], &option))
- return 0;
- sbi->s_resuid = option;
- break;
- case Opt_resgid:
- if (match_int(&args[0], &option))
- return 0;
- sbi->s_resgid = option;
- break;
- case Opt_sb:
- /* handled by get_sb_block() instead of here */
- /* *sb_block = match_int(&args[0]); */
- break;
- case Opt_err_panic:
- clear_opt(sb, ERRORS_CONT);
- clear_opt(sb, ERRORS_RO);
- set_opt(sb, ERRORS_PANIC);
- break;
- case Opt_err_ro:
- clear_opt(sb, ERRORS_CONT);
- clear_opt(sb, ERRORS_PANIC);
- set_opt(sb, ERRORS_RO);
- break;
- case Opt_err_cont:
- clear_opt(sb, ERRORS_RO);
- clear_opt(sb, ERRORS_PANIC);
- set_opt(sb, ERRORS_CONT);
- break;
- case Opt_nouid32:
- set_opt(sb, NO_UID32);
- break;
- case Opt_debug:
- set_opt(sb, DEBUG);
- break;
- case Opt_oldalloc:
- ext4_msg(sb, KERN_WARNING,
- "Ignoring deprecated oldalloc option");
- break;
- case Opt_orlov:
- ext4_msg(sb, KERN_WARNING,
- "Ignoring deprecated orlov option");
- break;
+#define MOPT_DATAJ 0x0080
+
+static const struct mount_opts {
+ int token;
+ int mount_opt;
+ int flags;
+} ext4_mount_opts[] = {
+ {Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET},
+ {Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR},
+ {Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET},
+ {Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR},
+ {Opt_mblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_SET},
+ {Opt_nomblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_CLEAR},
+ {Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET},
+ {Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR},
+ {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_SET},
+ {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_CLEAR},
+ {Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET},
+ {Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR},
+ {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_SET | MOPT_EXPLICIT},
+ {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_CLEAR | MOPT_EXPLICIT},
+ {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_SET},
+ {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
+ EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_SET},
+ {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_SET},
+ {Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
+ {Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
+ {Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
+ {Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_SET},
+ {Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_CLEAR},
+ {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
+ {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
+ {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
+ {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR},
+ {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR},
+ {Opt_commit, 0, MOPT_GTE0},
+ {Opt_max_batch_time, 0, MOPT_GTE0},
+ {Opt_min_batch_time, 0, MOPT_GTE0},
+ {Opt_inode_readahead_blks, 0, MOPT_GTE0},
+ {Opt_init_itable, 0, MOPT_GTE0},
+ {Opt_stripe, 0, MOPT_GTE0},
+ {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_DATAJ},
+ {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_DATAJ},
+ {Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, MOPT_DATAJ},
#ifdef CONFIG_EXT4_FS_XATTR
- case Opt_user_xattr:
- set_opt(sb, XATTR_USER);
- break;
- case Opt_nouser_xattr:
- clear_opt(sb, XATTR_USER);
- break;
+ {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
+ {Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
#else
- case Opt_user_xattr:
- case Opt_nouser_xattr:
- ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported");
- break;
+ {Opt_user_xattr, 0, MOPT_NOSUPPORT},
+ {Opt_nouser_xattr, 0, MOPT_NOSUPPORT},
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
- case Opt_acl:
- set_opt(sb, POSIX_ACL);
- break;
- case Opt_noacl:
- clear_opt(sb, POSIX_ACL);
- break;
+ {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
+ {Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR},
#else
- case Opt_acl:
- case Opt_noacl:
- ext4_msg(sb, KERN_ERR, "(no)acl options not supported");
- break;
+ {Opt_acl, 0, MOPT_NOSUPPORT},
+ {Opt_noacl, 0, MOPT_NOSUPPORT},
#endif
- case Opt_journal_update:
- /* @@@ FIXME */
- /* Eventually we will want to be able to create
- a journal file here. For now, only allow the
- user to specify an existing inode to be the
- journal file. */
- if (is_remount) {
- ext4_msg(sb, KERN_ERR,
- "Cannot specify journal on remount");
- return 0;
- }
- set_opt(sb, UPDATE_JOURNAL);
- break;
- case Opt_journal_dev:
- if (is_remount) {
+ {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
+ {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
+ {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
+ {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
+ MOPT_SET | MOPT_Q},
+ {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA,
+ MOPT_SET | MOPT_Q},
+ {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
+ EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q},
+ {Opt_usrjquota, 0, MOPT_Q},
+ {Opt_grpjquota, 0, MOPT_Q},
+ {Opt_offusrjquota, 0, MOPT_Q},
+ {Opt_offgrpjquota, 0, MOPT_Q},
+ {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
+ {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
+ {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
+ {Opt_err, 0, 0}
+};
+
+static int handle_mount_opt(struct super_block *sb, char *opt, int token,
+ substring_t *args, unsigned long *journal_devnum,
+ unsigned int *journal_ioprio, int is_remount)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ const struct mount_opts *m;
+ int arg = 0;
+
+ if (args->from && match_int(args, &arg))
+ return -1;
+ switch (token) {
+ case Opt_noacl:
+ case Opt_nouser_xattr:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5");
+ break;
+ case Opt_sb:
+ return 1; /* handled by get_sb_block() */
+ case Opt_removed:
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring removed %s option", opt);
+ return 1;
+ case Opt_resuid:
+ sbi->s_resuid = arg;
+ return 1;
+ case Opt_resgid:
+ sbi->s_resgid = arg;
+ return 1;
+ case Opt_abort:
+ sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ return 1;
+ case Opt_i_version:
+ sb->s_flags |= MS_I_VERSION;
+ return 1;
+ case Opt_journal_dev:
+ if (is_remount) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot specify journal on remount");
+ return -1;
+ }
+ *journal_devnum = arg;
+ return 1;
+ case Opt_journal_ioprio:
+ if (arg < 0 || arg > 7)
+ return -1;
+ *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
+ return 1;
+ }
+
+ for (m = ext4_mount_opts; m->token != Opt_err; m++) {
+ if (token != m->token)
+ continue;
+ if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
+ return -1;
+ if (m->flags & MOPT_EXPLICIT)
+ set_opt2(sb, EXPLICIT_DELALLOC);
+ if (m->flags & MOPT_CLEAR_ERR)
+ clear_opt(sb, ERRORS_MASK);
+ if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
+ ext4_msg(sb, KERN_ERR, "Cannot change quota "
+ "options when quota turned on");
+ return -1;
+ }
+
+ if (m->flags & MOPT_NOSUPPORT) {
+ ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
+ } else if (token == Opt_commit) {
+ if (arg == 0)
+ arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
+ sbi->s_commit_interval = HZ * arg;
+ } else if (token == Opt_max_batch_time) {
+ if (arg == 0)
+ arg = EXT4_DEF_MAX_BATCH_TIME;
+ sbi->s_max_batch_time = arg;
+ } else if (token == Opt_min_batch_time) {
+ sbi->s_min_batch_time = arg;
+ } else if (token == Opt_inode_readahead_blks) {
+ if (arg > (1 << 30))
+ return -1;
+ if (arg && !is_power_of_2(arg)) {
ext4_msg(sb, KERN_ERR,
- "Cannot specify journal on remount");
- return 0;
+ "EXT4-fs: inode_readahead_blks"
+ " must be a power of 2");
+ return -1;
}
- if (match_int(&args[0], &option))
- return 0;
- *journal_devnum = option;
- break;
- case Opt_journal_checksum:
- set_opt(sb, JOURNAL_CHECKSUM);
- break;
- case Opt_journal_async_commit:
- set_opt(sb, JOURNAL_ASYNC_COMMIT);
- set_opt(sb, JOURNAL_CHECKSUM);
- break;
- case Opt_noload:
- set_opt(sb, NOLOAD);
- break;
- case Opt_commit:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0)
- return 0;
- if (option == 0)
- option = JBD2_DEFAULT_MAX_COMMIT_AGE;
- sbi->s_commit_interval = HZ * option;
- break;
- case Opt_max_batch_time:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0)
- return 0;
- if (option == 0)
- option = EXT4_DEF_MAX_BATCH_TIME;
- sbi->s_max_batch_time = option;
- break;
- case Opt_min_batch_time:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0)
- return 0;
- sbi->s_min_batch_time = option;
- break;
- case Opt_data_journal:
- data_opt = EXT4_MOUNT_JOURNAL_DATA;
- goto datacheck;
- case Opt_data_ordered:
- data_opt = EXT4_MOUNT_ORDERED_DATA;
- goto datacheck;
- case Opt_data_writeback:
- data_opt = EXT4_MOUNT_WRITEBACK_DATA;
- datacheck:
+ sbi->s_inode_readahead_blks = arg;
+ } else if (token == Opt_init_itable) {
+ set_opt(sb, INIT_INODE_TABLE);
+ if (!args->from)
+ arg = EXT4_DEF_LI_WAIT_MULT;
+ sbi->s_li_wait_mult = arg;
+ } else if (token == Opt_stripe) {
+ sbi->s_stripe = arg;
+ } else if (m->flags & MOPT_DATAJ) {
if (is_remount) {
if (!sbi->s_journal)
ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
- else if (test_opt(sb, DATA_FLAGS) != data_opt) {
+ else if (test_opt(sb, DATA_FLAGS) !=
+ m->mount_opt) {
ext4_msg(sb, KERN_ERR,
- "Cannot change data mode on remount");
- return 0;
+ "Cannot change data mode on remount");
+ return -1;
}
} else {
clear_opt(sb, DATA_FLAGS);
- sbi->s_mount_opt |= data_opt;
+ sbi->s_mount_opt |= m->mount_opt;
}
- break;
- case Opt_data_err_abort:
- set_opt(sb, DATA_ERR_ABORT);
- break;
- case Opt_data_err_ignore:
- clear_opt(sb, DATA_ERR_ABORT);
- break;
#ifdef CONFIG_QUOTA
- case Opt_usrjquota:
+ } else if (token == Opt_usrjquota) {
if (!set_qf_name(sb, USRQUOTA, &args[0]))
- return 0;
- break;
- case Opt_grpjquota:
+ return -1;
+ } else if (token == Opt_grpjquota) {
if (!set_qf_name(sb, GRPQUOTA, &args[0]))
- return 0;
- break;
- case Opt_offusrjquota:
+ return -1;
+ } else if (token == Opt_offusrjquota) {
if (!clear_qf_name(sb, USRQUOTA))
- return 0;
- break;
- case Opt_offgrpjquota:
+ return -1;
+ } else if (token == Opt_offgrpjquota) {
if (!clear_qf_name(sb, GRPQUOTA))
- return 0;
- break;
-
- case Opt_jqfmt_vfsold:
- qfmt = QFMT_VFS_OLD;
- goto set_qf_format;
- case Opt_jqfmt_vfsv0:
- qfmt = QFMT_VFS_V0;
- goto set_qf_format;
- case Opt_jqfmt_vfsv1:
- qfmt = QFMT_VFS_V1;
-set_qf_format:
+ return -1;
+ } else if (m->flags & MOPT_QFMT) {
if (sb_any_quota_loaded(sb) &&
- sbi->s_jquota_fmt != qfmt) {
- ext4_msg(sb, KERN_ERR, "Cannot change "
- "journaled quota options when "
- "quota turned on");
- return 0;
+ sbi->s_jquota_fmt != m->mount_opt) {
+ ext4_msg(sb, KERN_ERR, "Cannot "
+ "change journaled quota options "
+ "when quota turned on");
+ return -1;
}
- sbi->s_jquota_fmt = qfmt;
- break;
- case Opt_quota:
- case Opt_usrquota:
- set_opt(sb, QUOTA);
- set_opt(sb, USRQUOTA);
- break;
- case Opt_grpquota:
- set_opt(sb, QUOTA);
- set_opt(sb, GRPQUOTA);
- break;
- case Opt_noquota:
- if (sb_any_quota_loaded(sb)) {
- ext4_msg(sb, KERN_ERR, "Cannot change quota "
- "options when quota turned on");
- return 0;
- }
- clear_opt(sb, QUOTA);
- clear_opt(sb, USRQUOTA);
- clear_opt(sb, GRPQUOTA);
- break;
-#else
- case Opt_quota:
- case Opt_usrquota:
- case Opt_grpquota:
- ext4_msg(sb, KERN_ERR,
- "quota options not supported");
- break;
- case Opt_usrjquota:
- case Opt_grpjquota:
- case Opt_offusrjquota:
- case Opt_offgrpjquota:
- case Opt_jqfmt_vfsold:
- case Opt_jqfmt_vfsv0:
- case Opt_jqfmt_vfsv1:
- ext4_msg(sb, KERN_ERR,
- "journaled quota options not supported");
- break;
- case Opt_noquota:
- break;
+ sbi->s_jquota_fmt = m->mount_opt;
#endif
- case Opt_abort:
- sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
- break;
- case Opt_nobarrier:
- clear_opt(sb, BARRIER);
- break;
- case Opt_barrier:
- if (args[0].from) {
- if (match_int(&args[0], &option))
- return 0;
- } else
- option = 1; /* No argument, default to 1 */
- if (option)
- set_opt(sb, BARRIER);
- else
- clear_opt(sb, BARRIER);
- break;
- case Opt_ignore:
- break;
- case Opt_resize:
- if (!is_remount) {
- ext4_msg(sb, KERN_ERR,
- "resize option only available "
- "for remount");
- return 0;
- }
- if (match_int(&args[0], &option) != 0)
- return 0;
- *n_blocks_count = option;
- break;
- case Opt_nobh:
- ext4_msg(sb, KERN_WARNING,
- "Ignoring deprecated nobh option");
- break;
- case Opt_bh:
- ext4_msg(sb, KERN_WARNING,
- "Ignoring deprecated bh option");
- break;
- case Opt_i_version:
- set_opt(sb, I_VERSION);
- sb->s_flags |= MS_I_VERSION;
- break;
- case Opt_nodelalloc:
- clear_opt(sb, DELALLOC);
- clear_opt2(sb, EXPLICIT_DELALLOC);
- break;
- case Opt_mblk_io_submit:
- set_opt(sb, MBLK_IO_SUBMIT);
- break;
- case Opt_nomblk_io_submit:
- clear_opt(sb, MBLK_IO_SUBMIT);
- break;
- case Opt_stripe:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0)
- return 0;
- sbi->s_stripe = option;
- break;
- case Opt_delalloc:
- set_opt(sb, DELALLOC);
- set_opt2(sb, EXPLICIT_DELALLOC);
- break;
- case Opt_block_validity:
- set_opt(sb, BLOCK_VALIDITY);
- break;
- case Opt_noblock_validity:
- clear_opt(sb, BLOCK_VALIDITY);
- break;
- case Opt_inode_readahead_blks:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0 || option > (1 << 30))
- return 0;
- if (option && !is_power_of_2(option)) {
- ext4_msg(sb, KERN_ERR,
- "EXT4-fs: inode_readahead_blks"
- " must be a power of 2");
- return 0;
+ } else {
+ if (!args->from)
+ arg = 1;
+ if (m->flags & MOPT_CLEAR)
+ arg = !arg;
+ else if (unlikely(!(m->flags & MOPT_SET))) {
+ ext4_msg(sb, KERN_WARNING,
+ "buggy handling of option %s", opt);
+ WARN_ON(1);
+ return -1;
}
- sbi->s_inode_readahead_blks = option;
- break;
- case Opt_journal_ioprio:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0 || option > 7)
- break;
- *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
- option);
- break;
- case Opt_noauto_da_alloc:
- set_opt(sb, NO_AUTO_DA_ALLOC);
- break;
- case Opt_auto_da_alloc:
- if (args[0].from) {
- if (match_int(&args[0], &option))
- return 0;
- } else
- option = 1; /* No argument, default to 1 */
- if (option)
- clear_opt(sb, NO_AUTO_DA_ALLOC);
+ if (arg != 0)
+ sbi->s_mount_opt |= m->mount_opt;
else
- set_opt(sb,NO_AUTO_DA_ALLOC);
- break;
- case Opt_discard:
- set_opt(sb, DISCARD);
- break;
- case Opt_nodiscard:
- clear_opt(sb, DISCARD);
- break;
- case Opt_dioread_nolock:
- set_opt(sb, DIOREAD_NOLOCK);
- break;
- case Opt_dioread_lock:
- clear_opt(sb, DIOREAD_NOLOCK);
- break;
- case Opt_init_itable:
- set_opt(sb, INIT_INODE_TABLE);
- if (args[0].from) {
- if (match_int(&args[0], &option))
- return 0;
- } else
- option = EXT4_DEF_LI_WAIT_MULT;
- if (option < 0)
- return 0;
- sbi->s_li_wait_mult = option;
- break;
- case Opt_noinit_itable:
- clear_opt(sb, INIT_INODE_TABLE);
- break;
- default:
- ext4_msg(sb, KERN_ERR,
- "Unrecognized mount option \"%s\" "
- "or missing value", p);
- return 0;
+ sbi->s_mount_opt &= ~m->mount_opt;
}
+ return 1;
+ }
+ ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
+ "or missing value", opt);
+ return -1;
+}
+
+static int parse_options(char *options, struct super_block *sb,
+ unsigned long *journal_devnum,
+ unsigned int *journal_ioprio,
+ int is_remount)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ char *p;
+ substring_t args[MAX_OPT_ARGS];
+ int token;
+
+ if (!options)
+ return 1;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ if (!*p)
+ continue;
+ /*
+ * Initialize args struct so we know whether arg was
+ * found; some options take optional arguments.
+ */
+ args[0].to = args[0].from = 0;
+ token = match_token(p, tokens, args);
+ if (handle_mount_opt(sb, p, token, args, journal_devnum,
+ journal_ioprio, is_remount) < 0)
+ return 0;
}
#ifdef CONFIG_QUOTA
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
@@ -1942,6 +1651,160 @@ set_qf_format:
return 1;
}
+static inline void ext4_show_quota_options(struct seq_file *seq,
+ struct super_block *sb)
+{
+#if defined(CONFIG_QUOTA)
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (sbi->s_jquota_fmt) {
+ char *fmtname = "";
+
+ switch (sbi->s_jquota_fmt) {
+ case QFMT_VFS_OLD:
+ fmtname = "vfsold";
+ break;
+ case QFMT_VFS_V0:
+ fmtname = "vfsv0";
+ break;
+ case QFMT_VFS_V1:
+ fmtname = "vfsv1";
+ break;
+ }
+ seq_printf(seq, ",jqfmt=%s", fmtname);
+ }
+
+ if (sbi->s_qf_names[USRQUOTA])
+ seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
+
+ if (sbi->s_qf_names[GRPQUOTA])
+ seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
+
+ if (test_opt(sb, USRQUOTA))
+ seq_puts(seq, ",usrquota");
+
+ if (test_opt(sb, GRPQUOTA))
+ seq_puts(seq, ",grpquota");
+#endif
+}
+
+static const char *token2str(int token)
+{
+ static const struct match_token *t;
+
+ for (t = tokens; t->token != Opt_err; t++)
+ if (t->token == token && !strchr(t->pattern, '='))
+ break;
+ return t->pattern;
+}
+
+/*
+ * Show an option if
+ * - it's set to a non-default value OR
+ * - if the per-sb default is different from the global default
+ */
+static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
+ int nodefs)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ int def_errors, def_mount_opt = nodefs ? 0 : sbi->s_def_mount_opt;
+ const struct mount_opts *m;
+ char sep = nodefs ? '\n' : ',';
+
+#define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep)
+#define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg)
+
+ if (sbi->s_sb_block != 1)
+ SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block);
+
+ for (m = ext4_mount_opts; m->token != Opt_err; m++) {
+ int want_set = m->flags & MOPT_SET;
+ if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
+ (m->flags & MOPT_CLEAR_ERR))
+ continue;
+ if (!(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
+ continue; /* skip if same as the default */
+ if ((want_set &&
+ (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) ||
+ (!want_set && (sbi->s_mount_opt & m->mount_opt)))
+ continue; /* select Opt_noFoo vs Opt_Foo */
+ SEQ_OPTS_PRINT("%s", token2str(m->token));
+ }
+
+ if (nodefs || sbi->s_resuid != EXT4_DEF_RESUID ||
+ le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
+ SEQ_OPTS_PRINT("resuid=%u", sbi->s_resuid);
+ if (nodefs || sbi->s_resgid != EXT4_DEF_RESGID ||
+ le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
+ SEQ_OPTS_PRINT("resgid=%u", sbi->s_resgid);
+ def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
+ if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
+ SEQ_OPTS_PUTS("errors=remount-ro");
+ if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
+ SEQ_OPTS_PUTS("errors=continue");
+ if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
+ SEQ_OPTS_PUTS("errors=panic");
+ if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ)
+ SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ);
+ if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME)
+ SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
+ if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
+ SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
+ if (sb->s_flags & MS_I_VERSION)
+ SEQ_OPTS_PUTS("i_version");
+ if (nodefs || sbi->s_stripe)
+ SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
+ if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ def_mount_opt)) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ SEQ_OPTS_PUTS("data=journal");
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ SEQ_OPTS_PUTS("data=ordered");
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ SEQ_OPTS_PUTS("data=writeback");
+ }
+ if (nodefs ||
+ sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
+ SEQ_OPTS_PRINT("inode_readahead_blks=%u",
+ sbi->s_inode_readahead_blks);
+
+ if (nodefs || (test_opt(sb, INIT_INODE_TABLE) &&
+ (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
+ SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
+
+ ext4_show_quota_options(seq, sb);
+ return 0;
+}
+
+static int ext4_show_options(struct seq_file *seq, struct dentry *root)
+{
+ return _ext4_show_options(seq, root->d_sb, 0);
+}
+
+static int options_seq_show(struct seq_file *seq, void *offset)
+{
+ struct super_block *sb = seq->private;
+ int rc;
+
+ seq_puts(seq, (sb->s_flags & MS_RDONLY) ? "ro" : "rw");
+ rc = _ext4_show_options(seq, sb, 1);
+ seq_puts(seq, "\n");
+ return rc;
+}
+
+static int options_open_fs(struct inode *inode, struct file *file)
+{
+ return single_open(file, options_seq_show, PDE(inode)->data);
+}
+
+static const struct file_operations ext4_seq_options_fops = {
+ .owner = THIS_MODULE,
+ .open = options_open_fs,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
int read_only)
{
@@ -2945,7 +2808,7 @@ static int ext4_run_lazyinit_thread(void)
ext4_clear_request_list();
kfree(ext4_li_info);
ext4_li_info = NULL;
- printk(KERN_CRIT "EXT4: error %d creating inode table "
+ printk(KERN_CRIT "EXT4-fs: error %d creating inode table "
"initialization thread\n",
err);
return err;
@@ -3183,11 +3046,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_opt(sb, INIT_INODE_TABLE);
if (def_mount_opts & EXT4_DEFM_DEBUG)
set_opt(sb, DEBUG);
- if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
- ext4_msg(sb, KERN_WARNING, deprecated_msg, "bsdgroups",
- "2.6.38");
+ if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
set_opt(sb, GRPID);
- }
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sb, NO_UID32);
/* xattr user namespace & acls are now defaulted on */
@@ -3240,13 +3100,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
- &journal_devnum, &journal_ioprio, NULL, 0)) {
+ &journal_devnum, &journal_ioprio, 0)) {
ext4_msg(sb, KERN_WARNING,
"failed to parse options in superblock: %s",
sbi->s_es->s_mount_opts);
}
+ sbi->s_def_mount_opt = sbi->s_mount_opt;
if (!parse_options((char *) data, sb, &journal_devnum,
- &journal_ioprio, NULL, 0))
+ &journal_ioprio, 0))
goto failed_mount;
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
@@ -3416,7 +3277,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
#else
es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
- sb->s_dirt = 1;
}
/* Handle clustersize */
@@ -3540,6 +3400,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
+ if (sbi->s_proc)
+ proc_create_data("options", S_IRUGO, sbi->s_proc,
+ &ext4_seq_options_fops, sb);
+
bgl_lock_init(sbi->s_blockgroup_lock);
for (i = 0; i < db_count; i++) {
@@ -3694,6 +3558,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
+
/*
* The journal may have updated the bg summary counts, so we
* need to update the global counters.
@@ -3735,9 +3601,8 @@ no_journal:
iput(root);
goto failed_mount4;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
- iput(root);
ext4_msg(sb, KERN_ERR, "get root dentry failed");
ret = -ENOMEM;
goto failed_mount4;
@@ -3862,6 +3727,7 @@ failed_mount2:
ext4_kvfree(sbi->s_group_desc);
failed_mount:
if (sbi->s_proc) {
+ remove_proc_entry("options", sbi->s_proc);
remove_proc_entry(sb->s_id, ext4_proc_root);
}
#ifdef CONFIG_QUOTA
@@ -4091,15 +3957,6 @@ static int ext4_load_journal(struct super_block *sb,
if (!(journal->j_flags & JBD2_BARRIER))
ext4_msg(sb, KERN_INFO, "barriers disabled");
- if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
- err = jbd2_journal_update_format(journal);
- if (err) {
- ext4_msg(sb, KERN_ERR, "error updating journal");
- jbd2_journal_destroy(journal);
- return err;
- }
- }
-
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
err = jbd2_journal_wipe(journal, !really_read_only);
if (!err) {
@@ -4386,7 +4243,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
{
struct ext4_super_block *es;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- ext4_fsblk_t n_blocks_count = 0;
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
int enable_quota = 0;
@@ -4419,8 +4275,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
/*
* Allow the "check" option to be passed as a remount option.
*/
- if (!parse_options(data, sb, NULL, &journal_ioprio,
- &n_blocks_count, 1)) {
+ if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
err = -EINVAL;
goto restore_opts;
}
@@ -4438,8 +4293,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
}
- if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
- n_blocks_count > ext4_blocks_count(es)) {
+ if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
err = -EROFS;
goto restore_opts;
@@ -4514,8 +4368,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_journal)
ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
- if ((err = ext4_group_extend(sb, es, n_blocks_count)))
- goto restore_opts;
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
@@ -5056,6 +4908,9 @@ static int __init ext4_init_fs(void)
{
int i, err;
+ ext4_li_info = NULL;
+ mutex_init(&ext4_li_mtx);
+
ext4_check_flag_values();
for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
@@ -5094,8 +4949,6 @@ static int __init ext4_init_fs(void)
if (err)
goto out;
- ext4_li_info = NULL;
- mutex_init(&ext4_li_mtx);
return 0;
out:
unregister_as_ext2();
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 93a00d8..e88748e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -82,8 +82,8 @@
printk("\n"); \
} while (0)
#else
-# define ea_idebug(f...)
-# define ea_bdebug(f...)
+# define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
+# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
static void ext4_xattr_cache_insert(struct buffer_head *);
@@ -158,13 +158,10 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
static inline int
ext4_xattr_check_block(struct buffer_head *bh)
{
- int error;
-
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1))
return -EIO;
- error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
- return error;
+ return ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
}
static inline int
@@ -220,7 +217,8 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
error = -ENODATA;
if (!EXT4_I(inode)->i_file_acl)
goto cleanup;
- ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+ ea_idebug(inode, "reading block %llu",
+ (unsigned long long)EXT4_I(inode)->i_file_acl);
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
if (!bh)
goto cleanup;
@@ -363,7 +361,8 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
error = 0;
if (!EXT4_I(inode)->i_file_acl)
goto cleanup;
- ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+ ea_idebug(inode, "reading block %llu",
+ (unsigned long long)EXT4_I(inode)->i_file_acl);
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
error = -EIO;
if (!bh)
@@ -487,18 +486,19 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
ext4_free_blocks(handle, inode, bh, 0, 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
+ unlock_buffer(bh);
} else {
le32_add_cpu(&BHDR(bh)->h_refcount, -1);
+ if (ce)
+ mb_cache_entry_release(ce);
+ unlock_buffer(bh);
error = ext4_handle_dirty_metadata(handle, inode, bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
dquot_free_block(inode, 1);
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
- if (ce)
- mb_cache_entry_release(ce);
}
- unlock_buffer(bh);
out:
ext4_std_error(inode->i_sb, error);
return;
@@ -834,7 +834,8 @@ inserted:
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
- ea_idebug(inode, "creating block %d", block);
+ ea_idebug(inode, "creating block %llu",
+ (unsigned long long)block);
new_bh = sb_getblk(sb, block);
if (!new_bh) {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 3ab8410..21687e3 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1496,11 +1496,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
root_inode->i_ino = MSDOS_ROOT_INO;
root_inode->i_version = 1;
error = fat_read_root(root_inode);
- if (error < 0)
+ if (error < 0) {
+ iput(root_inode);
goto out_fail;
+ }
error = -ENOMEM;
insert_inode_hash(root_inode);
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (!sb->s_root) {
fat_msg(sb, KERN_ERR, "get root inode failed");
goto out_fail;
@@ -1516,8 +1518,6 @@ out_invalid:
out_fail:
if (fat_inode)
iput(fat_inode);
- if (root_inode)
- iput(root_inode);
unload_nls(sbi->nls_io);
unload_nls(sbi->nls_disk);
if (sbi->options.iocharset != fat_default_iocharset)
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index a81eb23..98ae804 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -521,57 +521,46 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
op = &outname[*outlen * sizeof(wchar_t)];
} else {
- if (nls) {
- for (i = 0, ip = name, op = outname, *outlen = 0;
- i < len && *outlen <= FAT_LFN_LEN;
- *outlen += 1)
- {
- if (escape && (*ip == ':')) {
- if (i > len - 5)
- return -EINVAL;
- ec = 0;
- for (k = 1; k < 5; k++) {
- nc = ip[k];
- ec <<= 4;
- if (nc >= '0' && nc <= '9') {
- ec |= nc - '0';
- continue;
- }
- if (nc >= 'a' && nc <= 'f') {
- ec |= nc - ('a' - 10);
- continue;
- }
- if (nc >= 'A' && nc <= 'F') {
- ec |= nc - ('A' - 10);
- continue;
- }
- return -EINVAL;
+ for (i = 0, ip = name, op = outname, *outlen = 0;
+ i < len && *outlen < FAT_LFN_LEN;
+ *outlen += 1) {
+ if (escape && (*ip == ':')) {
+ if (i > len - 5)
+ return -EINVAL;
+ ec = 0;
+ for (k = 1; k < 5; k++) {
+ nc = ip[k];
+ ec <<= 4;
+ if (nc >= '0' && nc <= '9') {
+ ec |= nc - '0';
+ continue;
}
- *op++ = ec & 0xFF;
- *op++ = ec >> 8;
- ip += 5;
- i += 5;
- } else {
- if ((charlen = nls->char2uni(ip, len - i, (wchar_t *)op)) < 0)
- return -EINVAL;
- ip += charlen;
- i += charlen;
- op += 2;
+ if (nc >= 'a' && nc <= 'f') {
+ ec |= nc - ('a' - 10);
+ continue;
+ }
+ if (nc >= 'A' && nc <= 'F') {
+ ec |= nc - ('A' - 10);
+ continue;
+ }
+ return -EINVAL;
}
+ *op++ = ec & 0xFF;
+ *op++ = ec >> 8;
+ ip += 5;
+ i += 5;
+ } else {
+ charlen = nls->char2uni(ip, len - i,
+ (wchar_t *)op);
+ if (charlen < 0)
+ return -EINVAL;
+ ip += charlen;
+ i += charlen;
+ op += 2;
}
- if (i < len)
- return -ENAMETOOLONG;
- } else {
- for (i = 0, ip = name, op = outname, *outlen = 0;
- i < len && *outlen <= FAT_LFN_LEN;
- i++, *outlen += 1)
- {
- *op++ = *ip++;
- *op++ = 0;
- }
- if (i < len)
- return -ENAMETOOLONG;
}
+ if (i < len)
+ return -ENAMETOOLONG;
}
*longlen = *outlen;
diff --git a/fs/file.c b/fs/file.c
index 4c6992d..3c426de 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -6,7 +6,7 @@
* Manage the dynamic fd arrays in the process files_struct.
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
diff --git a/fs/file_table.c b/fs/file_table.c
index 20002e3..70f2a0f 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -204,7 +204,7 @@ EXPORT_SYMBOL(alloc_file);
* to write to @file, along with access to write through
* its vfsmount.
*/
-void drop_file_write_access(struct file *file)
+static void drop_file_write_access(struct file *file)
{
struct vfsmount *mnt = file->f_path.mnt;
struct dentry *dentry = file->f_path.dentry;
@@ -219,7 +219,6 @@ void drop_file_write_access(struct file *file)
mnt_drop_write(mnt);
file_release_write(file);
}
-EXPORT_SYMBOL_GPL(drop_file_write_access);
/* the real guts of fput() - releasing the last reference to file
*/
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index 9d1c995..d4fabd2 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -224,9 +224,8 @@ static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent)
ret = PTR_ERR(root);
goto out;
}
- sbp->s_root = d_alloc_root(root);
+ sbp->s_root = d_make_root(root);
if (!sbp->s_root) {
- iput(root);
printk(KERN_WARNING "vxfs: unable to get root dentry.\n");
goto out_free_ilist;
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f855916..539f36c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -14,7 +14,7 @@
*/
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
@@ -53,14 +53,6 @@ struct wb_writeback_work {
};
/*
- * Include the creation of the trace points after defining the
- * wb_writeback_work structure so that the definition remains local to this
- * file.
- */
-#define CREATE_TRACE_POINTS
-#include <trace/events/writeback.h>
-
-/*
* We don't actually have pdflush, but this one is exported though /proc...
*/
int nr_pdflush_threads;
@@ -92,6 +84,14 @@ static inline struct inode *wb_inode(struct list_head *head)
return list_entry(head, struct inode, i_wb_list);
}
+/*
+ * Include the creation of the trace points after defining the
+ * wb_writeback_work structure and inline functions so that the definition
+ * remains local to this file.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/writeback.h>
+
/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
{
@@ -256,7 +256,8 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
}
/*
- * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
+ * Move expired (dirtied after work->older_than_this) dirty inodes from
+ * @delaying_queue to @dispatch_queue.
*/
static int move_expired_inodes(struct list_head *delaying_queue,
struct list_head *dispatch_queue,
@@ -1148,23 +1149,6 @@ out_unlock_inode:
}
EXPORT_SYMBOL(__mark_inode_dirty);
-/*
- * Write out a superblock's list of dirty inodes. A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched. For other superblocks,
- * assume that all inodes are backed by the same queue.
- *
- * The inodes to be written are parked on bdi->b_io. They are moved back onto
- * bdi->b_dirty as they are selected for writing. This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
- */
static void wait_sb_inodes(struct super_block *sb)
{
struct inode *inode, *old_inode = NULL;
@@ -1284,7 +1268,7 @@ int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason)
EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
/**
- * writeback_inodes_sb_if_idle - start writeback if none underway
+ * writeback_inodes_sb_nr_if_idle - start writeback if none underway
* @sb: the superblock
* @nr: the number of pages to write
* @reason: reason why some writeback work was initiated
@@ -1364,8 +1348,6 @@ int write_inode_now(struct inode *inode, int sync)
ret = writeback_single_inode(inode, wb, &wbc);
spin_unlock(&inode->i_lock);
spin_unlock(&wb->list_lock);
- if (sync)
- inode_sync_wait(inode);
return ret;
}
EXPORT_SYMBOL(write_inode_now);
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 78b519c..e159e68 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/path.h>
@@ -26,11 +26,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
{
struct path old_root;
+ path_get_longterm(path);
spin_lock(&fs->lock);
write_seqcount_begin(&fs->seq);
old_root = fs->root;
fs->root = *path;
- path_get_longterm(path);
write_seqcount_end(&fs->seq);
spin_unlock(&fs->lock);
if (old_root.dentry)
@@ -45,11 +45,11 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
{
struct path old_pwd;
+ path_get_longterm(path);
spin_lock(&fs->lock);
write_seqcount_begin(&fs->seq);
old_pwd = fs->pwd;
fs->pwd = *path;
- path_get_longterm(path);
write_seqcount_end(&fs->seq);
spin_unlock(&fs->lock);
@@ -57,6 +57,14 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
path_put_longterm(&old_pwd);
}
+static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
+{
+ if (likely(p->dentry != old->dentry || p->mnt != old->mnt))
+ return 0;
+ *p = *new;
+ return 1;
+}
+
void chroot_fs_refs(struct path *old_root, struct path *new_root)
{
struct task_struct *g, *p;
@@ -68,21 +76,16 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
task_lock(p);
fs = p->fs;
if (fs) {
+ int hits = 0;
spin_lock(&fs->lock);
write_seqcount_begin(&fs->seq);
- if (fs->root.dentry == old_root->dentry
- && fs->root.mnt == old_root->mnt) {
- path_get_longterm(new_root);
- fs->root = *new_root;
+ hits += replace_path(&fs->root, old_root, new_root);
+ hits += replace_path(&fs->pwd, old_root, new_root);
+ write_seqcount_end(&fs->seq);
+ while (hits--) {
count++;
- }
- if (fs->pwd.dentry == old_root->dentry
- && fs->pwd.mnt == old_root->mnt) {
path_get_longterm(new_root);
- fs->pwd = *new_root;
- count++;
}
- write_seqcount_end(&fs->seq);
spin_unlock(&fs->lock);
}
task_unlock(p);
@@ -107,10 +110,8 @@ void exit_fs(struct task_struct *tsk)
int kill;
task_lock(tsk);
spin_lock(&fs->lock);
- write_seqcount_begin(&fs->seq);
tsk->fs = NULL;
kill = !--fs->users;
- write_seqcount_end(&fs->seq);
spin_unlock(&fs->lock);
task_unlock(tsk);
if (kill)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 5f3368a..7df2b5e 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -838,10 +838,10 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
}
}
if (page) {
- void *mapaddr = kmap_atomic(page, KM_USER0);
+ void *mapaddr = kmap_atomic(page);
void *buf = mapaddr + offset;
offset += fuse_copy_do(cs, &buf, &count);
- kunmap_atomic(mapaddr, KM_USER0);
+ kunmap_atomic(mapaddr);
} else
offset += fuse_copy_do(cs, NULL, &count);
}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 4a199fd..a841868 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1887,11 +1887,11 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
goto out;
- vaddr = kmap_atomic(pages[0], KM_USER0);
+ vaddr = kmap_atomic(pages[0]);
err = fuse_copy_ioctl_iovec(fc, iov_page, vaddr,
transferred, in_iovs + out_iovs,
(flags & FUSE_IOCTL_COMPAT) != 0);
- kunmap_atomic(vaddr, KM_USER0);
+ kunmap_atomic(vaddr);
if (err)
goto out;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 64cf8d0..4aec599 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -988,14 +988,9 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
err = -ENOMEM;
root = fuse_get_root_inode(sb, d.rootmode);
- if (!root)
+ root_dentry = d_make_root(root);
+ if (!root_dentry)
goto err_put_conn;
-
- root_dentry = d_alloc_root(root);
- if (!root_dentry) {
- iput(root);
- goto err_put_conn;
- }
/* only now - we want root dentry with NULL ->d_op */
sb->s_d_op = &fuse_dentry_operations;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 501e5cb..38b7a74 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -434,12 +434,12 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
if (error)
return error;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
dsize = (dibh->b_size - sizeof(struct gfs2_dinode));
memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
flush_dcache_page(page);
brelse(dibh);
SetPageUptodate(page);
@@ -542,9 +542,9 @@ int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
if (IS_ERR(page))
return PTR_ERR(page);
- p = kmap_atomic(page, KM_USER0);
+ p = kmap_atomic(page);
memcpy(buf + copied, p + offset, amt);
- kunmap_atomic(p, KM_USER0);
+ kunmap_atomic(p);
mark_page_accessed(page);
page_cache_release(page);
copied += amt;
@@ -788,11 +788,11 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(buf + pos, kaddr + pos, copied);
memset(kaddr + pos + copied, 0, len - copied);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (!PageUptodate(page))
SetPageUptodate(page);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 14a7040..197c5c4 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -60,7 +60,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
int release = 0;
if (!page || page->index) {
- page = grab_cache_page(inode->i_mapping, 0);
+ page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
if (!page)
return -ENOMEM;
release = 1;
@@ -930,7 +930,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
struct page *page;
int err;
- page = grab_cache_page(mapping, index);
+ page = find_or_create_page(mapping, index, GFP_NOFS);
if (!page)
return 0;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index c5fb359..7683458 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -313,6 +313,8 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return gfs2_get_flags(filp, (u32 __user *)arg);
case FS_IOC_SETFLAGS:
return gfs2_set_flags(filp, (u32 __user *)arg);
+ case FITRIM:
+ return gfs2_fitrim(filp, (void __user *)arg);
}
return -ENOTTY;
}
@@ -674,6 +676,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *dibh;
int error;
+ loff_t size = len;
unsigned int nr_blks;
sector_t lblock = offset >> inode->i_blkbits;
@@ -707,8 +710,8 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
goto out;
}
}
- if (offset + len > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
- i_size_write(inode, offset + len);
+ if (offset + size > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
+ i_size_write(inode, offset + size);
mark_inode_dirty(inode);
@@ -777,12 +780,14 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
if (unlikely(error))
goto out_uninit;
- if (!gfs2_write_alloc_required(ip, offset, len))
- goto out_unlock;
-
while (len > 0) {
if (len < bytes)
bytes = len;
+ if (!gfs2_write_alloc_required(ip, offset, bytes)) {
+ len -= bytes;
+ offset += bytes;
+ continue;
+ }
qa = gfs2_qadata_get(ip);
if (!qa) {
error = -ENOMEM;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 376816f..dab2526 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -29,6 +29,7 @@
#include <linux/rcupdate.h>
#include <linux/rculist_bl.h>
#include <linux/bit_spinlock.h>
+#include <linux/percpu.h>
#include "gfs2.h"
#include "incore.h"
@@ -167,14 +168,19 @@ void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
spin_unlock(&lru_lock);
}
-static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
+static void __gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
{
- spin_lock(&lru_lock);
if (!list_empty(&gl->gl_lru)) {
list_del_init(&gl->gl_lru);
atomic_dec(&lru_count);
clear_bit(GLF_LRU, &gl->gl_flags);
}
+}
+
+static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
+{
+ spin_lock(&lru_lock);
+ __gfs2_glock_remove_from_lru(gl);
spin_unlock(&lru_lock);
}
@@ -217,11 +223,12 @@ void gfs2_glock_put(struct gfs2_glock *gl)
struct gfs2_sbd *sdp = gl->gl_sbd;
struct address_space *mapping = gfs2_glock2aspace(gl);
- if (atomic_dec_and_test(&gl->gl_ref)) {
+ if (atomic_dec_and_lock(&gl->gl_ref, &lru_lock)) {
+ __gfs2_glock_remove_from_lru(gl);
+ spin_unlock(&lru_lock);
spin_lock_bucket(gl->gl_hash);
hlist_bl_del_rcu(&gl->gl_list);
spin_unlock_bucket(gl->gl_hash);
- gfs2_glock_remove_from_lru(gl);
GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
trace_gfs2_glock_put(gl);
@@ -537,6 +544,11 @@ __acquires(&gl->gl_spin)
do_error(gl, 0); /* Fail queued try locks */
}
gl->gl_req = target;
+ set_bit(GLF_BLOCKING, &gl->gl_flags);
+ if ((gl->gl_req == LM_ST_UNLOCKED) ||
+ (gl->gl_state == LM_ST_EXCLUSIVE) ||
+ (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB)))
+ clear_bit(GLF_BLOCKING, &gl->gl_flags);
spin_unlock(&gl->gl_spin);
if (glops->go_xmote_th)
glops->go_xmote_th(gl);
@@ -738,6 +750,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
return -ENOMEM;
atomic_inc(&sdp->sd_glock_disposal);
+ gl->gl_sbd = sdp;
gl->gl_flags = 0;
gl->gl_name = name;
atomic_set(&gl->gl_ref, 1);
@@ -746,12 +759,17 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
gl->gl_demote_state = LM_ST_EXCLUSIVE;
gl->gl_hash = hash;
gl->gl_ops = glops;
- snprintf(gl->gl_strname, GDLM_STRNAME_BYTES, "%8x%16llx", name.ln_type, (unsigned long long)number);
+ gl->gl_dstamp = ktime_set(0, 0);
+ preempt_disable();
+ /* We use the global stats to estimate the initial per-glock stats */
+ gl->gl_stats = this_cpu_ptr(sdp->sd_lkstats)->lkstats[glops->go_type];
+ preempt_enable();
+ gl->gl_stats.stats[GFS2_LKS_DCOUNT] = 0;
+ gl->gl_stats.stats[GFS2_LKS_QCOUNT] = 0;
memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
gl->gl_tchange = jiffies;
gl->gl_object = NULL;
- gl->gl_sbd = sdp;
gl->gl_hold_time = GL_GLOCK_DFT_HOLD;
INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
INIT_WORK(&gl->gl_delete, delete_work_func);
@@ -993,6 +1011,8 @@ fail:
}
set_bit(GLF_QUEUED, &gl->gl_flags);
trace_gfs2_glock_queue(gh, 1);
+ gfs2_glstats_inc(gl, GFS2_LKS_QCOUNT);
+ gfs2_sbstats_inc(gl, GFS2_LKS_QCOUNT);
if (likely(insert_pt == NULL)) {
list_add_tail(&gh->gh_list, &gl->gl_holders);
if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
@@ -1652,6 +1672,8 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
*p++ = 'L';
if (gl->gl_object)
*p++ = 'o';
+ if (test_bit(GLF_BLOCKING, gflags))
+ *p++ = 'b';
*p = 0;
return buf;
}
@@ -1708,8 +1730,78 @@ out:
return error;
}
+static int gfs2_glstats_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+ struct gfs2_glock *gl = iter_ptr;
+
+ seq_printf(seq, "G: n:%u/%llx rtt:%lld/%lld rttb:%lld/%lld irt:%lld/%lld dcnt: %lld qcnt: %lld\n",
+ gl->gl_name.ln_type,
+ (unsigned long long)gl->gl_name.ln_number,
+ (long long)gl->gl_stats.stats[GFS2_LKS_SRTT],
+ (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVAR],
+ (long long)gl->gl_stats.stats[GFS2_LKS_SRTTB],
+ (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVARB],
+ (long long)gl->gl_stats.stats[GFS2_LKS_SIRT],
+ (long long)gl->gl_stats.stats[GFS2_LKS_SIRTVAR],
+ (long long)gl->gl_stats.stats[GFS2_LKS_DCOUNT],
+ (long long)gl->gl_stats.stats[GFS2_LKS_QCOUNT]);
+ return 0;
+}
+
+static const char *gfs2_gltype[] = {
+ "type",
+ "reserved",
+ "nondisk",
+ "inode",
+ "rgrp",
+ "meta",
+ "iopen",
+ "flock",
+ "plock",
+ "quota",
+ "journal",
+};
+
+static const char *gfs2_stype[] = {
+ [GFS2_LKS_SRTT] = "srtt",
+ [GFS2_LKS_SRTTVAR] = "srttvar",
+ [GFS2_LKS_SRTTB] = "srttb",
+ [GFS2_LKS_SRTTVARB] = "srttvarb",
+ [GFS2_LKS_SIRT] = "sirt",
+ [GFS2_LKS_SIRTVAR] = "sirtvar",
+ [GFS2_LKS_DCOUNT] = "dlm",
+ [GFS2_LKS_QCOUNT] = "queue",
+};
+
+#define GFS2_NR_SBSTATS (ARRAY_SIZE(gfs2_gltype) * ARRAY_SIZE(gfs2_stype))
+
+static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+ struct gfs2_glock_iter *gi = seq->private;
+ struct gfs2_sbd *sdp = gi->sdp;
+ unsigned index = gi->hash >> 3;
+ unsigned subindex = gi->hash & 0x07;
+ s64 value;
+ int i;
+
+ if (index == 0 && subindex != 0)
+ return 0;
+ seq_printf(seq, "%-10s %8s:", gfs2_gltype[index],
+ (index == 0) ? "cpu": gfs2_stype[subindex]);
+ for_each_possible_cpu(i) {
+ const struct gfs2_pcpu_lkstats *lkstats = per_cpu_ptr(sdp->sd_lkstats, i);
+ if (index == 0) {
+ value = i;
+ } else {
+ value = lkstats->lkstats[index - 1].stats[subindex];
+ }
+ seq_printf(seq, " %15lld", (long long)value);
+ }
+ seq_putc(seq, '\n');
+ return 0;
+}
int __init gfs2_glock_init(void)
{
@@ -1822,6 +1914,35 @@ static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
return dump_glock(seq, iter_ptr);
}
+static void *gfs2_sbstats_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ struct gfs2_glock_iter *gi = seq->private;
+
+ gi->hash = *pos;
+ if (*pos >= GFS2_NR_SBSTATS)
+ return NULL;
+ preempt_disable();
+ return SEQ_START_TOKEN;
+}
+
+static void *gfs2_sbstats_seq_next(struct seq_file *seq, void *iter_ptr,
+ loff_t *pos)
+{
+ struct gfs2_glock_iter *gi = seq->private;
+ (*pos)++;
+ gi->hash++;
+ if (gi->hash >= GFS2_NR_SBSTATS) {
+ preempt_enable();
+ return NULL;
+ }
+ return SEQ_START_TOKEN;
+}
+
+static void gfs2_sbstats_seq_stop(struct seq_file *seq, void *iter_ptr)
+{
+ preempt_enable();
+}
+
static const struct seq_operations gfs2_glock_seq_ops = {
.start = gfs2_glock_seq_start,
.next = gfs2_glock_seq_next,
@@ -1829,7 +1950,21 @@ static const struct seq_operations gfs2_glock_seq_ops = {
.show = gfs2_glock_seq_show,
};
-static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+static const struct seq_operations gfs2_glstats_seq_ops = {
+ .start = gfs2_glock_seq_start,
+ .next = gfs2_glock_seq_next,
+ .stop = gfs2_glock_seq_stop,
+ .show = gfs2_glstats_seq_show,
+};
+
+static const struct seq_operations gfs2_sbstats_seq_ops = {
+ .start = gfs2_sbstats_seq_start,
+ .next = gfs2_sbstats_seq_next,
+ .stop = gfs2_sbstats_seq_stop,
+ .show = gfs2_sbstats_seq_show,
+};
+
+static int gfs2_glocks_open(struct inode *inode, struct file *file)
{
int ret = seq_open_private(file, &gfs2_glock_seq_ops,
sizeof(struct gfs2_glock_iter));
@@ -1841,9 +1976,49 @@ static int gfs2_debugfs_open(struct inode *inode, struct file *file)
return ret;
}
-static const struct file_operations gfs2_debug_fops = {
+static int gfs2_glstats_open(struct inode *inode, struct file *file)
+{
+ int ret = seq_open_private(file, &gfs2_glstats_seq_ops,
+ sizeof(struct gfs2_glock_iter));
+ if (ret == 0) {
+ struct seq_file *seq = file->private_data;
+ struct gfs2_glock_iter *gi = seq->private;
+ gi->sdp = inode->i_private;
+ }
+ return ret;
+}
+
+static int gfs2_sbstats_open(struct inode *inode, struct file *file)
+{
+ int ret = seq_open_private(file, &gfs2_sbstats_seq_ops,
+ sizeof(struct gfs2_glock_iter));
+ if (ret == 0) {
+ struct seq_file *seq = file->private_data;
+ struct gfs2_glock_iter *gi = seq->private;
+ gi->sdp = inode->i_private;
+ }
+ return ret;
+}
+
+static const struct file_operations gfs2_glocks_fops = {
+ .owner = THIS_MODULE,
+ .open = gfs2_glocks_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static const struct file_operations gfs2_glstats_fops = {
.owner = THIS_MODULE,
- .open = gfs2_debugfs_open,
+ .open = gfs2_glstats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static const struct file_operations gfs2_sbstats_fops = {
+ .owner = THIS_MODULE,
+ .open = gfs2_sbstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
@@ -1857,20 +2032,45 @@ int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
S_IFREG | S_IRUGO,
sdp->debugfs_dir, sdp,
- &gfs2_debug_fops);
+ &gfs2_glocks_fops);
if (!sdp->debugfs_dentry_glocks)
- return -ENOMEM;
+ goto fail;
+
+ sdp->debugfs_dentry_glstats = debugfs_create_file("glstats",
+ S_IFREG | S_IRUGO,
+ sdp->debugfs_dir, sdp,
+ &gfs2_glstats_fops);
+ if (!sdp->debugfs_dentry_glstats)
+ goto fail;
+
+ sdp->debugfs_dentry_sbstats = debugfs_create_file("sbstats",
+ S_IFREG | S_IRUGO,
+ sdp->debugfs_dir, sdp,
+ &gfs2_sbstats_fops);
+ if (!sdp->debugfs_dentry_sbstats)
+ goto fail;
return 0;
+fail:
+ gfs2_delete_debugfs_file(sdp);
+ return -ENOMEM;
}
void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
{
- if (sdp && sdp->debugfs_dir) {
+ if (sdp->debugfs_dir) {
if (sdp->debugfs_dentry_glocks) {
debugfs_remove(sdp->debugfs_dentry_glocks);
sdp->debugfs_dentry_glocks = NULL;
}
+ if (sdp->debugfs_dentry_glstats) {
+ debugfs_remove(sdp->debugfs_dentry_glstats);
+ sdp->debugfs_dentry_glstats = NULL;
+ }
+ if (sdp->debugfs_dentry_sbstats) {
+ debugfs_remove(sdp->debugfs_dentry_sbstats);
+ sdp->debugfs_dentry_sbstats = NULL;
+ }
debugfs_remove(sdp->debugfs_dir);
sdp->debugfs_dir = NULL;
}
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 97742a7..47d0bda 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -19,6 +19,8 @@
#include <linux/rculist_bl.h>
#include <linux/completion.h>
#include <linux/rbtree.h>
+#include <linux/ktime.h>
+#include <linux/percpu.h>
#define DIO_WAIT 0x00000010
#define DIO_METADATA 0x00000020
@@ -205,6 +207,22 @@ struct gfs2_glock_operations {
};
enum {
+ GFS2_LKS_SRTT = 0, /* Non blocking smoothed round trip time */
+ GFS2_LKS_SRTTVAR = 1, /* Non blocking smoothed variance */
+ GFS2_LKS_SRTTB = 2, /* Blocking smoothed round trip time */
+ GFS2_LKS_SRTTVARB = 3, /* Blocking smoothed variance */
+ GFS2_LKS_SIRT = 4, /* Smoothed Inter-request time */
+ GFS2_LKS_SIRTVAR = 5, /* Smoothed Inter-request variance */
+ GFS2_LKS_DCOUNT = 6, /* Count of dlm requests */
+ GFS2_LKS_QCOUNT = 7, /* Count of gfs2_holder queues */
+ GFS2_NR_LKSTATS
+};
+
+struct gfs2_lkstats {
+ s64 stats[GFS2_NR_LKSTATS];
+};
+
+enum {
/* States */
HIF_HOLDER = 6, /* Set for gh that "holds" the glock */
HIF_FIRST = 7,
@@ -238,10 +256,12 @@ enum {
GLF_QUEUED = 12,
GLF_LRU = 13,
GLF_OBJECT = 14, /* Used only for tracing */
+ GLF_BLOCKING = 15,
};
struct gfs2_glock {
struct hlist_bl_node gl_list;
+ struct gfs2_sbd *gl_sbd;
unsigned long gl_flags; /* GLF_... */
struct lm_lockname gl_name;
atomic_t gl_ref;
@@ -261,16 +281,14 @@ struct gfs2_glock {
struct list_head gl_holders;
const struct gfs2_glock_operations *gl_ops;
- char gl_strname[GDLM_STRNAME_BYTES];
+ ktime_t gl_dstamp;
+ struct gfs2_lkstats gl_stats;
struct dlm_lksb gl_lksb;
char gl_lvb[32];
unsigned long gl_tchange;
void *gl_object;
struct list_head gl_lru;
-
- struct gfs2_sbd *gl_sbd;
-
struct list_head gl_ail_list;
atomic_t gl_ail_count;
atomic_t gl_revokes;
@@ -560,8 +578,14 @@ struct lm_lockstruct {
uint32_t *ls_recover_result; /* result of last jid recovery */
};
+struct gfs2_pcpu_lkstats {
+ /* One struct for each glock type */
+ struct gfs2_lkstats lkstats[10];
+};
+
struct gfs2_sbd {
struct super_block *sd_vfs;
+ struct gfs2_pcpu_lkstats __percpu *sd_lkstats;
struct kobject sd_kobj;
unsigned long sd_flags; /* SDF_... */
struct gfs2_sb_host sd_sb;
@@ -620,7 +644,6 @@ struct gfs2_sbd {
int sd_rindex_uptodate;
spinlock_t sd_rindex_spin;
- struct mutex sd_rindex_mutex;
struct rb_root sd_rindex_tree;
unsigned int sd_rgrps;
unsigned int sd_max_rg_data;
@@ -725,8 +748,23 @@ struct gfs2_sbd {
unsigned long sd_last_warning;
struct dentry *debugfs_dir; /* debugfs directory */
- struct dentry *debugfs_dentry_glocks; /* for debugfs */
+ struct dentry *debugfs_dentry_glocks;
+ struct dentry *debugfs_dentry_glstats;
+ struct dentry *debugfs_dentry_sbstats;
};
+static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which)
+{
+ gl->gl_stats.stats[which]++;
+}
+
+static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which)
+{
+ const struct gfs2_sbd *sdp = gl->gl_sbd;
+ preempt_disable();
+ this_cpu_ptr(sdp->sd_lkstats)->lkstats[gl->gl_name.ln_type].stats[which]++;
+ preempt_enable();
+}
+
#endif /* __INCORE_DOT_H__ */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index a7d611b..c98a60e 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -391,10 +391,6 @@ static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
int error;
int dblocks = 1;
- error = gfs2_rindex_update(sdp);
- if (error)
- fs_warn(sdp, "rindex update returns %d\n", error);
-
error = gfs2_inplace_reserve(dip, RES_DINODE);
if (error)
goto out;
@@ -1040,9 +1036,10 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
- rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+ rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
if (!rgd)
goto out_inodes;
+
gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
@@ -1258,7 +1255,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
* this is the case of the target file already existing
* so we unlink before doing the rename
*/
- nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
+ nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr, 1);
if (nrgd)
gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
}
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 8944d1e..f8411bd 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -18,14 +18,106 @@
#include "glock.h"
#include "util.h"
#include "sys.h"
+#include "trace_gfs2.h"
extern struct workqueue_struct *gfs2_control_wq;
+/**
+ * gfs2_update_stats - Update time based stats
+ * @mv: Pointer to mean/variance structure to update
+ * @sample: New data to include
+ *
+ * @delta is the difference between the current rtt sample and the
+ * running average srtt. We add 1/8 of that to the srtt in order to
+ * update the current srtt estimate. The varience estimate is a bit
+ * more complicated. We subtract the abs value of the @delta from
+ * the current variance estimate and add 1/4 of that to the running
+ * total.
+ *
+ * Note that the index points at the array entry containing the smoothed
+ * mean value, and the variance is always in the following entry
+ *
+ * Reference: TCP/IP Illustrated, vol 2, p. 831,832
+ * All times are in units of integer nanoseconds. Unlike the TCP/IP case,
+ * they are not scaled fixed point.
+ */
+
+static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index,
+ s64 sample)
+{
+ s64 delta = sample - s->stats[index];
+ s->stats[index] += (delta >> 3);
+ index++;
+ s->stats[index] += ((abs64(delta) - s->stats[index]) >> 2);
+}
+
+/**
+ * gfs2_update_reply_times - Update locking statistics
+ * @gl: The glock to update
+ *
+ * This assumes that gl->gl_dstamp has been set earlier.
+ *
+ * The rtt (lock round trip time) is an estimate of the time
+ * taken to perform a dlm lock request. We update it on each
+ * reply from the dlm.
+ *
+ * The blocking flag is set on the glock for all dlm requests
+ * which may potentially block due to lock requests from other nodes.
+ * DLM requests where the current lock state is exclusive, the
+ * requested state is null (or unlocked) or where the TRY or
+ * TRY_1CB flags are set are classified as non-blocking. All
+ * other DLM requests are counted as (potentially) blocking.
+ */
+static inline void gfs2_update_reply_times(struct gfs2_glock *gl)
+{
+ struct gfs2_pcpu_lkstats *lks;
+ const unsigned gltype = gl->gl_name.ln_type;
+ unsigned index = test_bit(GLF_BLOCKING, &gl->gl_flags) ?
+ GFS2_LKS_SRTTB : GFS2_LKS_SRTT;
+ s64 rtt;
+
+ preempt_disable();
+ rtt = ktime_to_ns(ktime_sub(ktime_get_real(), gl->gl_dstamp));
+ lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+ gfs2_update_stats(&gl->gl_stats, index, rtt); /* Local */
+ gfs2_update_stats(&lks->lkstats[gltype], index, rtt); /* Global */
+ preempt_enable();
+
+ trace_gfs2_glock_lock_time(gl, rtt);
+}
+
+/**
+ * gfs2_update_request_times - Update locking statistics
+ * @gl: The glock to update
+ *
+ * The irt (lock inter-request times) measures the average time
+ * between requests to the dlm. It is updated immediately before
+ * each dlm call.
+ */
+
+static inline void gfs2_update_request_times(struct gfs2_glock *gl)
+{
+ struct gfs2_pcpu_lkstats *lks;
+ const unsigned gltype = gl->gl_name.ln_type;
+ ktime_t dstamp;
+ s64 irt;
+
+ preempt_disable();
+ dstamp = gl->gl_dstamp;
+ gl->gl_dstamp = ktime_get_real();
+ irt = ktime_to_ns(ktime_sub(gl->gl_dstamp, dstamp));
+ lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+ gfs2_update_stats(&gl->gl_stats, GFS2_LKS_SIRT, irt); /* Local */
+ gfs2_update_stats(&lks->lkstats[gltype], GFS2_LKS_SIRT, irt); /* Global */
+ preempt_enable();
+}
+
static void gdlm_ast(void *arg)
{
struct gfs2_glock *gl = arg;
unsigned ret = gl->gl_state;
+ gfs2_update_reply_times(gl);
BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED);
if (gl->gl_lksb.sb_flags & DLM_SBF_VALNOTVALID)
@@ -111,7 +203,7 @@ static int make_mode(const unsigned int lmstate)
static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
const int req)
{
- u32 lkf = 0;
+ u32 lkf = DLM_LKF_VALBLK;
if (gfs_flags & LM_FLAG_TRY)
lkf |= DLM_LKF_NOQUEUE;
@@ -138,26 +230,43 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
if (lkid != 0)
lkf |= DLM_LKF_CONVERT;
- lkf |= DLM_LKF_VALBLK;
-
return lkf;
}
+static void gfs2_reverse_hex(char *c, u64 value)
+{
+ while (value) {
+ *c-- = hex_asc[value & 0x0f];
+ value >>= 4;
+ }
+}
+
static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
unsigned int flags)
{
struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
int req;
u32 lkf;
+ char strname[GDLM_STRNAME_BYTES] = "";
req = make_mode(req_state);
lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
-
+ gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
+ gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
+ if (gl->gl_lksb.sb_lkid) {
+ gfs2_update_request_times(gl);
+ } else {
+ memset(strname, ' ', GDLM_STRNAME_BYTES - 1);
+ strname[GDLM_STRNAME_BYTES - 1] = '\0';
+ gfs2_reverse_hex(strname + 7, gl->gl_name.ln_type);
+ gfs2_reverse_hex(strname + 23, gl->gl_name.ln_number);
+ gl->gl_dstamp = ktime_get_real();
+ }
/*
* Submit the actual lock request.
*/
- return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
+ return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname,
GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
}
@@ -172,6 +281,10 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
return;
}
+ clear_bit(GLF_BLOCKING, &gl->gl_flags);
+ gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
+ gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
+ gfs2_update_request_times(gl);
error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK,
NULL, gl);
if (error) {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 756fae9..4752ead 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -19,6 +19,7 @@
#include <linux/freezer.h>
#include <linux/bio.h>
#include <linux/writeback.h>
+#include <linux/list_sort.h>
#include "gfs2.h"
#include "incore.h"
@@ -358,7 +359,7 @@ retry:
return 0;
}
-static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
+u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
{
struct gfs2_journal_extent *je;
@@ -467,8 +468,8 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
void gfs2_log_incr_head(struct gfs2_sbd *sdp)
{
- if (sdp->sd_log_flush_head == sdp->sd_log_tail)
- BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);
+ BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
+ (sdp->sd_log_flush_head != sdp->sd_log_head));
if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
sdp->sd_log_flush_head = 0;
@@ -476,99 +477,6 @@ void gfs2_log_incr_head(struct gfs2_sbd *sdp)
}
}
-/**
- * gfs2_log_write_endio - End of I/O for a log buffer
- * @bh: The buffer head
- * @uptodate: I/O Status
- *
- */
-
-static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
-{
- struct gfs2_sbd *sdp = bh->b_private;
- bh->b_private = NULL;
-
- end_buffer_write_sync(bh, uptodate);
- if (atomic_dec_and_test(&sdp->sd_log_in_flight))
- wake_up(&sdp->sd_log_flush_wait);
-}
-
-/**
- * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
- * @sdp: The GFS2 superblock
- *
- * Returns: the buffer_head
- */
-
-struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
-{
- u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
- struct buffer_head *bh;
-
- bh = sb_getblk(sdp->sd_vfs, blkno);
- lock_buffer(bh);
- memset(bh->b_data, 0, bh->b_size);
- set_buffer_uptodate(bh);
- clear_buffer_dirty(bh);
- gfs2_log_incr_head(sdp);
- atomic_inc(&sdp->sd_log_in_flight);
- bh->b_private = sdp;
- bh->b_end_io = gfs2_log_write_endio;
-
- return bh;
-}
-
-/**
- * gfs2_fake_write_endio -
- * @bh: The buffer head
- * @uptodate: The I/O Status
- *
- */
-
-static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
-{
- struct buffer_head *real_bh = bh->b_private;
- struct gfs2_bufdata *bd = real_bh->b_private;
- struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
-
- end_buffer_write_sync(bh, uptodate);
- free_buffer_head(bh);
- unlock_buffer(real_bh);
- brelse(real_bh);
- if (atomic_dec_and_test(&sdp->sd_log_in_flight))
- wake_up(&sdp->sd_log_flush_wait);
-}
-
-/**
- * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
- * @sdp: the filesystem
- * @data: the data the buffer_head should point to
- *
- * Returns: the log buffer descriptor
- */
-
-struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
- struct buffer_head *real)
-{
- u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
- struct buffer_head *bh;
-
- bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
- atomic_set(&bh->b_count, 1);
- bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
- set_bh_page(bh, real->b_page, bh_offset(real));
- bh->b_blocknr = blkno;
- bh->b_size = sdp->sd_sb.sb_bsize;
- bh->b_bdev = sdp->sd_vfs->s_bdev;
- bh->b_private = real;
- bh->b_end_io = gfs2_fake_write_endio;
-
- gfs2_log_incr_head(sdp);
- atomic_inc(&sdp->sd_log_in_flight);
-
- return bh;
-}
-
static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
{
unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
@@ -583,66 +491,8 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
sdp->sd_log_tail = new_tail;
}
-/**
- * log_write_header - Get and initialize a journal header buffer
- * @sdp: The GFS2 superblock
- *
- * Returns: the initialized log buffer descriptor
- */
-static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
-{
- u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
- struct buffer_head *bh;
- struct gfs2_log_header *lh;
- unsigned int tail;
- u32 hash;
-
- bh = sb_getblk(sdp->sd_vfs, blkno);
- lock_buffer(bh);
- memset(bh->b_data, 0, bh->b_size);
- set_buffer_uptodate(bh);
- clear_buffer_dirty(bh);
-
- gfs2_ail1_empty(sdp);
- tail = current_tail(sdp);
-
- lh = (struct gfs2_log_header *)bh->b_data;
- memset(lh, 0, sizeof(struct gfs2_log_header));
- lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
- lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
- lh->lh_header.__pad0 = cpu_to_be64(0);
- lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
- lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
- lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
- lh->lh_flags = cpu_to_be32(flags);
- lh->lh_tail = cpu_to_be32(tail);
- lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
- hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
- lh->lh_hash = cpu_to_be32(hash);
-
- bh->b_end_io = end_buffer_write_sync;
- get_bh(bh);
- if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
- submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
- else
- submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
- wait_on_buffer(bh);
-
- if (!buffer_uptodate(bh))
- gfs2_io_error_bh(sdp, bh);
- brelse(bh);
-
- if (sdp->sd_log_tail != tail)
- log_pull_tail(sdp, tail);
- else
- gfs2_assert_withdraw(sdp, !pull);
-
- sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
- gfs2_log_incr_head(sdp);
-}
-
-static void log_flush_commit(struct gfs2_sbd *sdp)
+static void log_flush_wait(struct gfs2_sbd *sdp)
{
DEFINE_WAIT(wait);
@@ -655,8 +505,20 @@ static void log_flush_commit(struct gfs2_sbd *sdp)
} while(atomic_read(&sdp->sd_log_in_flight));
finish_wait(&sdp->sd_log_flush_wait, &wait);
}
+}
+
+static int bd_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+ struct gfs2_bufdata *bda, *bdb;
- log_write_header(sdp, 0, 0);
+ bda = list_entry(a, struct gfs2_bufdata, bd_le.le_list);
+ bdb = list_entry(b, struct gfs2_bufdata, bd_le.le_list);
+
+ if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
+ return -1;
+ if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
+ return 1;
+ return 0;
}
static void gfs2_ordered_write(struct gfs2_sbd *sdp)
@@ -666,6 +528,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
LIST_HEAD(written);
gfs2_log_lock(sdp);
+ list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp);
while (!list_empty(&sdp->sd_log_le_ordered)) {
bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
list_move(&bd->bd_le.le_list, &written);
@@ -711,6 +574,68 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
}
/**
+ * log_write_header - Get and initialize a journal header buffer
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the initialized log buffer descriptor
+ */
+
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
+{
+ u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head);
+ struct buffer_head *bh;
+ struct gfs2_log_header *lh;
+ unsigned int tail;
+ u32 hash;
+
+ bh = sb_getblk(sdp->sd_vfs, blkno);
+ lock_buffer(bh);
+ memset(bh->b_data, 0, bh->b_size);
+ set_buffer_uptodate(bh);
+ clear_buffer_dirty(bh);
+
+ gfs2_ail1_empty(sdp);
+ tail = current_tail(sdp);
+
+ lh = (struct gfs2_log_header *)bh->b_data;
+ memset(lh, 0, sizeof(struct gfs2_log_header));
+ lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+ lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+ lh->lh_header.__pad0 = cpu_to_be64(0);
+ lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+ lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+ lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
+ lh->lh_flags = cpu_to_be32(flags);
+ lh->lh_tail = cpu_to_be32(tail);
+ lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+ hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
+ lh->lh_hash = cpu_to_be32(hash);
+
+ bh->b_end_io = end_buffer_write_sync;
+ get_bh(bh);
+ if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
+ gfs2_ordered_wait(sdp);
+ log_flush_wait(sdp);
+ submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
+ } else {
+ submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+ }
+ wait_on_buffer(bh);
+
+ if (!buffer_uptodate(bh))
+ gfs2_io_error_bh(sdp, bh);
+ brelse(bh);
+
+ if (sdp->sd_log_tail != tail)
+ log_pull_tail(sdp, tail);
+ else
+ gfs2_assert_withdraw(sdp, !pull);
+
+ sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
+ gfs2_log_incr_head(sdp);
+}
+
+/**
* gfs2_log_flush - flush incore transaction(s)
* @sdp: the filesystem
* @gl: The glock structure to flush. If NULL, flush the whole incore log
@@ -753,11 +678,10 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
gfs2_ordered_write(sdp);
lops_before_commit(sdp);
- gfs2_ordered_wait(sdp);
- if (sdp->sd_log_head != sdp->sd_log_flush_head)
- log_flush_commit(sdp);
- else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
+ if (sdp->sd_log_head != sdp->sd_log_flush_head) {
+ log_write_header(sdp, 0, 0);
+ } else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
gfs2_log_lock(sdp);
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
trace_gfs2_log_blocks(sdp, -1);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index ab06216..ff07454 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -53,10 +53,7 @@ extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
extern void gfs2_log_incr_head(struct gfs2_sbd *sdp);
-
-extern struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
-extern struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
- struct buffer_head *real);
+extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn);
extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 0301be6..6b1efb5 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -12,6 +12,7 @@
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
+#include <linux/mempool.h>
#include <linux/gfs2_ondisk.h>
#include <linux/bio.h>
#include <linux/fs.h>
@@ -76,7 +77,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd)
if (bi->bi_clone == 0)
return;
if (sdp->sd_args.ar_discard)
- gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi);
+ gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL);
memcpy(bi->bi_clone + bi->bi_offset,
bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
clear_bit(GBF_FULL, &bi->bi_flags);
@@ -143,6 +144,98 @@ static inline __be64 *bh_ptr_end(struct buffer_head *bh)
return (__force __be64 *)(bh->b_data + bh->b_size);
}
+/**
+ * gfs2_log_write_endio - End of I/O for a log buffer
+ * @bh: The buffer head
+ * @uptodate: I/O Status
+ *
+ */
+
+static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
+{
+ struct gfs2_sbd *sdp = bh->b_private;
+ bh->b_private = NULL;
+
+ end_buffer_write_sync(bh, uptodate);
+ if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+ wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
+ * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
+ * @sdp: The GFS2 superblock
+ *
+ * tReturns: the buffer_head
+ */
+
+static struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
+{
+ u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head);
+ struct buffer_head *bh;
+
+ bh = sb_getblk(sdp->sd_vfs, blkno);
+ lock_buffer(bh);
+ memset(bh->b_data, 0, bh->b_size);
+ set_buffer_uptodate(bh);
+ clear_buffer_dirty(bh);
+ gfs2_log_incr_head(sdp);
+ atomic_inc(&sdp->sd_log_in_flight);
+ bh->b_private = sdp;
+ bh->b_end_io = gfs2_log_write_endio;
+
+ return bh;
+}
+
+/**
+ * gfs2_fake_write_endio -
+ * @bh: The buffer head
+ * @uptodate: The I/O Status
+ *
+ */
+
+static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
+{
+ struct buffer_head *real_bh = bh->b_private;
+ struct gfs2_bufdata *bd = real_bh->b_private;
+ struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
+
+ end_buffer_write_sync(bh, uptodate);
+ mempool_free(bh, gfs2_bh_pool);
+ unlock_buffer(real_bh);
+ brelse(real_bh);
+ if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+ wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
+ * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
+ * @sdp: the filesystem
+ * @data: the data the buffer_head should point to
+ *
+ * Returns: the log buffer descriptor
+ */
+
+static struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
+ struct buffer_head *real)
+{
+ u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head);
+ struct buffer_head *bh;
+
+ bh = mempool_alloc(gfs2_bh_pool, GFP_NOFS);
+ atomic_set(&bh->b_count, 1);
+ bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
+ set_bh_page(bh, real->b_page, bh_offset(real));
+ bh->b_blocknr = blkno;
+ bh->b_size = sdp->sd_sb.sb_bsize;
+ bh->b_bdev = sdp->sd_vfs->s_bdev;
+ bh->b_private = real;
+ bh->b_end_io = gfs2_fake_write_endio;
+
+ gfs2_log_incr_head(sdp);
+ atomic_inc(&sdp->sd_log_in_flight);
+
+ return bh;
+}
static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type)
{
@@ -553,11 +646,11 @@ static void gfs2_check_magic(struct buffer_head *bh)
__be32 *ptr;
clear_buffer_escaped(bh);
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
ptr = kaddr + bh_offset(bh);
if (*ptr == cpu_to_be32(GFS2_MAGIC))
set_buffer_escaped(bh);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
@@ -594,10 +687,10 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
if (buffer_escaped(bd->bd_bh)) {
void *kaddr;
bh1 = gfs2_log_get_buf(sdp);
- kaddr = kmap_atomic(bd->bd_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bd->bd_bh->b_page);
memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh),
bh1->b_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
*(__be32 *)bh1->b_data = 0;
clear_buffer_escaped(bd->bd_bh);
unlock_buffer(bd->bd_bh);
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index a8d9bcd..754426b 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -17,6 +17,7 @@
#include <linux/rcupdate.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
+#include <linux/mempool.h>
#include "gfs2.h"
#include "incore.h"
@@ -69,6 +70,16 @@ static void gfs2_init_gl_aspace_once(void *foo)
address_space_init_once(mapping);
}
+static void *gfs2_bh_alloc(gfp_t mask, void *data)
+{
+ return alloc_buffer_head(mask);
+}
+
+static void gfs2_bh_free(void *ptr, void *data)
+{
+ return free_buffer_head(ptr);
+}
+
/**
* init_gfs2_fs - Register GFS2 as a filesystem
*
@@ -151,6 +162,10 @@ static int __init init_gfs2_fs(void)
gfs2_control_wq = alloc_workqueue("gfs2_control",
WQ_NON_REENTRANT | WQ_UNBOUND | WQ_FREEZABLE, 0);
if (!gfs2_control_wq)
+ goto fail_recovery;
+
+ gfs2_bh_pool = mempool_create(1024, gfs2_bh_alloc, gfs2_bh_free, NULL);
+ if (!gfs2_bh_pool)
goto fail_control;
gfs2_register_debugfs();
@@ -160,6 +175,8 @@ static int __init init_gfs2_fs(void)
return 0;
fail_control:
+ destroy_workqueue(gfs2_control_wq);
+fail_recovery:
destroy_workqueue(gfs_recovery_wq);
fail_wq:
unregister_filesystem(&gfs2meta_fs_type);
@@ -208,6 +225,7 @@ static void __exit exit_gfs2_fs(void)
rcu_barrier();
+ mempool_destroy(gfs2_bh_pool);
kmem_cache_destroy(gfs2_quotad_cachep);
kmem_cache_destroy(gfs2_rgrpd_cachep);
kmem_cache_destroy(gfs2_bufdata_cachep);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 6aacf3f..6f3a18f 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -68,6 +68,12 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
sb->s_fs_info = sdp;
sdp->sd_vfs = sb;
+ sdp->sd_lkstats = alloc_percpu(struct gfs2_pcpu_lkstats);
+ if (!sdp->sd_lkstats) {
+ kfree(sdp);
+ return NULL;
+ }
+
set_bit(SDF_NOJOURNALID, &sdp->sd_flags);
gfs2_tune_init(&sdp->sd_tune);
@@ -77,7 +83,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
spin_lock_init(&sdp->sd_statfs_spin);
spin_lock_init(&sdp->sd_rindex_spin);
- mutex_init(&sdp->sd_rindex_mutex);
sdp->sd_rindex_tree.rb_node = NULL;
INIT_LIST_HEAD(&sdp->sd_jindex_list);
@@ -431,10 +436,9 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
return PTR_ERR(inode);
}
- dentry = d_alloc_root(inode);
+ dentry = d_make_root(inode);
if (!dentry) {
fs_err(sdp, "can't alloc %s dentry\n", name);
- iput(inode);
return -ENOMEM;
}
*dptr = dentry;
@@ -800,6 +804,11 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
fs_err(sdp, "can't get quota file inode: %d\n", error);
goto fail_rindex;
}
+
+ error = gfs2_rindex_update(sdp);
+ if (error)
+ goto fail_qinode;
+
return 0;
fail_qinode:
@@ -1216,6 +1225,7 @@ fail_sys:
gfs2_sys_fs_del(sdp);
fail:
gfs2_delete_debugfs_file(sdp);
+ free_percpu(sdp->sd_lkstats);
kfree(sdp);
sb->s_fs_info = NULL;
return error;
@@ -1388,6 +1398,7 @@ static void gfs2_kill_sb(struct super_block *sb)
shrink_dcache_sb(sb);
kill_block_super(sb);
gfs2_delete_debugfs_file(sdp);
+ free_percpu(sdp->sd_lkstats);
kfree(sdp);
}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index a45b21b..6019da3 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -681,7 +681,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
ptr = qp;
nbytes = sizeof(struct gfs2_quota);
get_a_page:
- page = grab_cache_page(mapping, index);
+ page = find_or_create_page(mapping, index, GFP_NOFS);
if (!page)
return -ENOMEM;
@@ -720,12 +720,12 @@ get_a_page:
gfs2_trans_add_bh(ip->i_gl, bh, 0);
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
if (offset + sizeof(struct gfs2_quota) > PAGE_CACHE_SIZE)
nbytes = PAGE_CACHE_SIZE - offset;
memcpy(kaddr + offset, ptr, nbytes);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
unlock_page(page);
page_cache_release(page);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 981bfa3..19bde40 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -327,23 +327,34 @@ static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
* Returns: The resource group, or NULL if not found
*/
-struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
+struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk, bool exact)
{
- struct rb_node **newn;
+ struct rb_node *n, *next;
struct gfs2_rgrpd *cur;
+ if (gfs2_rindex_update(sdp))
+ return NULL;
+
spin_lock(&sdp->sd_rindex_spin);
- newn = &sdp->sd_rindex_tree.rb_node;
- while (*newn) {
- cur = rb_entry(*newn, struct gfs2_rgrpd, rd_node);
+ n = sdp->sd_rindex_tree.rb_node;
+ while (n) {
+ cur = rb_entry(n, struct gfs2_rgrpd, rd_node);
+ next = NULL;
if (blk < cur->rd_addr)
- newn = &((*newn)->rb_left);
+ next = n->rb_left;
else if (blk >= cur->rd_data0 + cur->rd_data)
- newn = &((*newn)->rb_right);
- else {
+ next = n->rb_right;
+ if (next == NULL) {
spin_unlock(&sdp->sd_rindex_spin);
+ if (exact) {
+ if (blk < cur->rd_addr)
+ return NULL;
+ if (blk >= cur->rd_data0 + cur->rd_data)
+ return NULL;
+ }
return cur;
}
+ n = next;
}
spin_unlock(&sdp->sd_rindex_spin);
@@ -532,7 +543,6 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp)
struct file_ra_state ra_state;
int error, rgrps;
- mutex_lock(&sdp->sd_rindex_mutex);
file_ra_state_init(&ra_state, inode->i_mapping);
for (rgrps = 0;; rgrps++) {
loff_t pos = rgrps * sizeof(struct gfs2_rindex);
@@ -545,11 +555,10 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp)
break;
total_data += be32_to_cpu(((struct gfs2_rindex *)buf)->ri_data);
}
- mutex_unlock(&sdp->sd_rindex_mutex);
return total_data;
}
-static void rgd_insert(struct gfs2_rgrpd *rgd)
+static int rgd_insert(struct gfs2_rgrpd *rgd)
{
struct gfs2_sbd *sdp = rgd->rd_sbd;
struct rb_node **newn = &sdp->sd_rindex_tree.rb_node, *parent = NULL;
@@ -565,11 +574,13 @@ static void rgd_insert(struct gfs2_rgrpd *rgd)
else if (rgd->rd_addr > cur->rd_addr)
newn = &((*newn)->rb_right);
else
- return;
+ return -EEXIST;
}
rb_link_node(&rgd->rd_node, parent, newn);
rb_insert_color(&rgd->rd_node, &sdp->sd_rindex_tree);
+ sdp->sd_rgrps++;
+ return 0;
}
/**
@@ -623,10 +634,12 @@ static int read_rindex_entry(struct gfs2_inode *ip,
if (rgd->rd_data > sdp->sd_max_rg_data)
sdp->sd_max_rg_data = rgd->rd_data;
spin_lock(&sdp->sd_rindex_spin);
- rgd_insert(rgd);
- sdp->sd_rgrps++;
+ error = rgd_insert(rgd);
spin_unlock(&sdp->sd_rindex_spin);
- return error;
+ if (!error)
+ return 0;
+
+ error = 0; /* someone else read in the rgrp; free it and ignore it */
fail:
kfree(rgd->rd_bits);
@@ -683,20 +696,22 @@ int gfs2_rindex_update(struct gfs2_sbd *sdp)
struct gfs2_glock *gl = ip->i_gl;
struct gfs2_holder ri_gh;
int error = 0;
+ int unlock_required = 0;
/* Read new copy from disk if we don't have the latest */
if (!sdp->sd_rindex_uptodate) {
- mutex_lock(&sdp->sd_rindex_mutex);
- error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, &ri_gh);
- if (error)
- return error;
+ if (!gfs2_glock_is_locked_by_me(gl)) {
+ error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, &ri_gh);
+ if (error)
+ return error;
+ unlock_required = 1;
+ }
if (!sdp->sd_rindex_uptodate)
error = gfs2_ri_update(ip);
- gfs2_glock_dq_uninit(&ri_gh);
- mutex_unlock(&sdp->sd_rindex_mutex);
+ if (unlock_required)
+ gfs2_glock_dq_uninit(&ri_gh);
}
-
return error;
}
@@ -805,9 +820,9 @@ void gfs2_rgrp_go_unlock(struct gfs2_holder *gh)
}
-void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
struct buffer_head *bh,
- const struct gfs2_bitmap *bi)
+ const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed)
{
struct super_block *sb = sdp->sd_vfs;
struct block_device *bdev = sb->s_bdev;
@@ -818,11 +833,19 @@ void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
sector_t nr_sects = 0;
int rv;
unsigned int x;
+ u32 trimmed = 0;
+ u8 diff;
for (x = 0; x < bi->bi_len; x++) {
- const u8 *orig = bh->b_data + bi->bi_offset + x;
- const u8 *clone = bi->bi_clone + bi->bi_offset + x;
- u8 diff = ~(*orig | (*orig >> 1)) & (*clone | (*clone >> 1));
+ const u8 *clone = bi->bi_clone ? bi->bi_clone : bi->bi_bh->b_data;
+ clone += bi->bi_offset;
+ clone += x;
+ if (bh) {
+ const u8 *orig = bh->b_data + bi->bi_offset + x;
+ diff = ~(*orig | (*orig >> 1)) & (*clone | (*clone >> 1));
+ } else {
+ diff = ~(*clone | (*clone >> 1));
+ }
diff &= 0x55;
if (diff == 0)
continue;
@@ -833,11 +856,14 @@ void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
if (nr_sects == 0)
goto start_new_extent;
if ((start + nr_sects) != blk) {
- rv = blkdev_issue_discard(bdev, start,
- nr_sects, GFP_NOFS,
- 0);
- if (rv)
- goto fail;
+ if (nr_sects >= minlen) {
+ rv = blkdev_issue_discard(bdev,
+ start, nr_sects,
+ GFP_NOFS, 0);
+ if (rv)
+ goto fail;
+ trimmed += nr_sects;
+ }
nr_sects = 0;
start_new_extent:
start = blk;
@@ -848,15 +874,104 @@ start_new_extent:
blk += sects_per_blk;
}
}
- if (nr_sects) {
+ if (nr_sects >= minlen) {
rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0);
if (rv)
goto fail;
+ trimmed += nr_sects;
}
- return;
+ if (ptrimmed)
+ *ptrimmed = trimmed;
+ return 0;
+
fail:
- fs_warn(sdp, "error %d on discard request, turning discards off for this filesystem", rv);
+ if (sdp->sd_args.ar_discard)
+ fs_warn(sdp, "error %d on discard request, turning discards off for this filesystem", rv);
sdp->sd_args.ar_discard = 0;
+ return -EIO;
+}
+
+/**
+ * gfs2_fitrim - Generate discard requests for unused bits of the filesystem
+ * @filp: Any file on the filesystem
+ * @argp: Pointer to the arguments (also used to pass result)
+ *
+ * Returns: 0 on success, otherwise error code
+ */
+
+int gfs2_fitrim(struct file *filp, void __user *argp)
+{
+ struct inode *inode = filp->f_dentry->d_inode;
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ struct request_queue *q = bdev_get_queue(sdp->sd_vfs->s_bdev);
+ struct buffer_head *bh;
+ struct gfs2_rgrpd *rgd;
+ struct gfs2_rgrpd *rgd_end;
+ struct gfs2_holder gh;
+ struct fstrim_range r;
+ int ret = 0;
+ u64 amt;
+ u64 trimmed = 0;
+ unsigned int x;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (argp == NULL) {
+ r.start = 0;
+ r.len = ULLONG_MAX;
+ r.minlen = 0;
+ } else if (copy_from_user(&r, argp, sizeof(r)))
+ return -EFAULT;
+
+ rgd = gfs2_blk2rgrpd(sdp, r.start, 0);
+ rgd_end = gfs2_blk2rgrpd(sdp, r.start + r.len, 0);
+
+ while (1) {
+
+ ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ if (ret)
+ goto out;
+
+ if (!(rgd->rd_flags & GFS2_RGF_TRIMMED)) {
+ /* Trim each bitmap in the rgrp */
+ for (x = 0; x < rgd->rd_length; x++) {
+ struct gfs2_bitmap *bi = rgd->rd_bits + x;
+ ret = gfs2_rgrp_send_discards(sdp, rgd->rd_data0, NULL, bi, r.minlen, &amt);
+ if (ret) {
+ gfs2_glock_dq_uninit(&gh);
+ goto out;
+ }
+ trimmed += amt;
+ }
+
+ /* Mark rgrp as having been trimmed */
+ ret = gfs2_trans_begin(sdp, RES_RG_HDR, 0);
+ if (ret == 0) {
+ bh = rgd->rd_bits[0].bi_bh;
+ rgd->rd_flags |= GFS2_RGF_TRIMMED;
+ gfs2_trans_add_bh(rgd->rd_gl, bh, 1);
+ gfs2_rgrp_out(rgd, bh->b_data);
+ gfs2_trans_end(sdp);
+ }
+ }
+ gfs2_glock_dq_uninit(&gh);
+
+ if (rgd == rgd_end)
+ break;
+
+ rgd = gfs2_rgrpd_get_next(rgd);
+ }
+
+out:
+ r.len = trimmed << 9;
+ if (argp && copy_to_user(argp, &r, sizeof(r)))
+ return -EFAULT;
+
+ return ret;
}
/**
@@ -1003,7 +1118,7 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, ip->i_goal))
rgd = begin = ip->i_rgd;
else
- rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal);
+ rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1);
if (rgd == NULL)
return -EBADSLT;
@@ -1288,7 +1403,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
u32 length, rgrp_blk, buf_blk;
unsigned int buf;
- rgd = gfs2_blk2rgrpd(sdp, bstart);
+ rgd = gfs2_blk2rgrpd(sdp, bstart, 1);
if (!rgd) {
if (gfs2_consist(sdp))
fs_err(sdp, "block = %llu\n", (unsigned long long)bstart);
@@ -1469,7 +1584,7 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta)
return;
trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
-
+ rgd->rd_flags &= ~GFS2_RGF_TRIMMED;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
@@ -1555,14 +1670,9 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
{
struct gfs2_rgrpd *rgd;
struct gfs2_holder rgd_gh;
- int error;
-
- error = gfs2_rindex_update(sdp);
- if (error)
- return error;
+ int error = -EINVAL;
- error = -EINVAL;
- rgd = gfs2_blk2rgrpd(sdp, no_addr);
+ rgd = gfs2_blk2rgrpd(sdp, no_addr, 1);
if (!rgd)
goto fail;
@@ -1605,7 +1715,7 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, block))
rgd = ip->i_rgd;
else
- rgd = gfs2_blk2rgrpd(sdp, block);
+ rgd = gfs2_blk2rgrpd(sdp, block, 1);
if (!rgd) {
fs_err(sdp, "rlist_add: no rgrp for block %llu\n", (unsigned long long)block);
return;
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index ceec910..b4b10f4 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -11,6 +11,7 @@
#define __RGRP_DOT_H__
#include <linux/slab.h>
+#include <linux/uaccess.h>
struct gfs2_rgrpd;
struct gfs2_sbd;
@@ -18,7 +19,7 @@ struct gfs2_holder;
extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
-extern struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
+extern struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk, bool exact);
extern struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
extern struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
@@ -62,8 +63,9 @@ extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
-extern void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
- struct buffer_head *bh,
- const struct gfs2_bitmap *bi);
+extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+ struct buffer_head *bh,
+ const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed);
+extern int gfs2_fitrim(struct file *filp, void __user *argp);
#endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 4553ce5..6172fa7 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1417,7 +1417,7 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
if (error)
goto out;
- rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+ rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
if (!rgd) {
gfs2_consist_inode(ip);
error = -EIO;
@@ -1557,6 +1557,7 @@ out:
end_writeback(inode);
gfs2_dir_hash_inval(ip);
ip->i_gl->gl_object = NULL;
+ flush_delayed_work_sync(&ip->i_gl->gl_work);
gfs2_glock_add_to_lru(ip->i_gl);
gfs2_glock_put(ip->i_gl);
ip->i_gl = NULL;
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index 5d07609..dfa89cd 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -11,6 +11,7 @@
#include <linux/dlmconstants.h>
#include <linux/gfs2_ondisk.h>
#include <linux/writeback.h>
+#include <linux/ktime.h>
#include "incore.h"
#include "glock.h"
@@ -43,7 +44,8 @@
{(1UL << GLF_FROZEN), "F" }, \
{(1UL << GLF_QUEUED), "q" }, \
{(1UL << GLF_LRU), "L" }, \
- {(1UL << GLF_OBJECT), "o" })
+ {(1UL << GLF_OBJECT), "o" }, \
+ {(1UL << GLF_BLOCKING), "b" })
#ifndef NUMPTY
#define NUMPTY
@@ -236,6 +238,62 @@ TRACE_EVENT(gfs2_glock_queue,
glock_trace_name(__entry->state))
);
+/* DLM sends a reply to GFS2 */
+TRACE_EVENT(gfs2_glock_lock_time,
+
+ TP_PROTO(const struct gfs2_glock *gl, s64 tdiff),
+
+ TP_ARGS(gl, tdiff),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, glnum )
+ __field( u32, gltype )
+ __field( int, status )
+ __field( char, flags )
+ __field( s64, tdiff )
+ __field( s64, srtt )
+ __field( s64, srttvar )
+ __field( s64, srttb )
+ __field( s64, srttvarb )
+ __field( s64, sirt )
+ __field( s64, sirtvar )
+ __field( s64, dcount )
+ __field( s64, qcount )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = gl->gl_sbd->sd_vfs->s_dev;
+ __entry->glnum = gl->gl_name.ln_number;
+ __entry->gltype = gl->gl_name.ln_type;
+ __entry->status = gl->gl_lksb.sb_status;
+ __entry->flags = gl->gl_lksb.sb_flags;
+ __entry->tdiff = tdiff;
+ __entry->srtt = gl->gl_stats.stats[GFS2_LKS_SRTT];
+ __entry->srttvar = gl->gl_stats.stats[GFS2_LKS_SRTTVAR];
+ __entry->srttb = gl->gl_stats.stats[GFS2_LKS_SRTTB];
+ __entry->srttvarb = gl->gl_stats.stats[GFS2_LKS_SRTTVARB];
+ __entry->sirt = gl->gl_stats.stats[GFS2_LKS_SIRT];
+ __entry->sirtvar = gl->gl_stats.stats[GFS2_LKS_SIRTVAR];
+ __entry->dcount = gl->gl_stats.stats[GFS2_LKS_DCOUNT];
+ __entry->qcount = gl->gl_stats.stats[GFS2_LKS_QCOUNT];
+ ),
+
+ TP_printk("%u,%u glock %d:%lld status:%d flags:%02x tdiff:%lld srtt:%lld/%lld srttb:%lld/%lld sirt:%lld/%lld dcnt:%lld qcnt:%lld",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+ (unsigned long long)__entry->glnum,
+ __entry->status, __entry->flags,
+ (long long)__entry->tdiff,
+ (long long)__entry->srtt,
+ (long long)__entry->srttvar,
+ (long long)__entry->srttb,
+ (long long)__entry->srttvarb,
+ (long long)__entry->sirt,
+ (long long)__entry->sirtvar,
+ (long long)__entry->dcount,
+ (long long)__entry->qcount)
+);
+
/* Section 2 - Log/journal
*
* Objectives:
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 5351129..9e7765e 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -25,6 +25,7 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly;
struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
struct kmem_cache *gfs2_quotad_cachep __read_mostly;
+mempool_t *gfs2_bh_pool __read_mostly;
void gfs2_assert_i(struct gfs2_sbd *sdp)
{
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index b432e04..a4ce76c 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -10,6 +10,8 @@
#ifndef __UTIL_DOT_H__
#define __UTIL_DOT_H__
+#include <linux/mempool.h>
+
#include "incore.h"
#define fs_printk(level, fs, fmt, arg...) \
@@ -150,6 +152,7 @@ extern struct kmem_cache *gfs2_inode_cachep;
extern struct kmem_cache *gfs2_bufdata_cachep;
extern struct kmem_cache *gfs2_rgrpd_cachep;
extern struct kmem_cache *gfs2_quotad_cachep;
+extern mempool_t *gfs2_bh_pool;
static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
unsigned int *p)
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index e963659..2e5ba42 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -251,7 +251,7 @@ static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh,
if (!blks)
return 0;
- rgd = gfs2_blk2rgrpd(sdp, bn);
+ rgd = gfs2_blk2rgrpd(sdp, bn, 1);
if (!rgd) {
gfs2_consist_inode(ip);
return -EIO;
@@ -1439,7 +1439,7 @@ static int ea_dealloc_block(struct gfs2_inode *ip)
struct gfs2_holder gh;
int error;
- rgd = gfs2_blk2rgrpd(sdp, ip->i_eattr);
+ rgd = gfs2_blk2rgrpd(sdp, ip->i_eattr, 1);
if (!rgd) {
gfs2_consist_inode(ip);
return -EIO;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 8137fb3..7b4c537 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -430,15 +430,13 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_d_op = &hfs_dentry_operations;
res = -ENOMEM;
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (!sb->s_root)
- goto bail_iput;
+ goto bail_no_root;
/* everything's okay */
return 0;
-bail_iput:
- iput(root_inode);
bail_no_root:
printk(KERN_ERR "hfs: get root inode failed.\n");
bail:
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 21a5b7f..4e75ac6 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -317,6 +317,11 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
/*
+ * hfs+-specific ioctl for making the filesystem bootable
+ */
+#define HFSPLUS_IOC_BLESS _IO('h', 0x80)
+
+/*
* Functions in any *.c used in other files
*/
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 927cdd6..921967e 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -117,7 +117,7 @@ struct hfsplus_vh {
__be32 write_count;
__be64 encodings_bmp;
- u8 finder_info[32];
+ u32 finder_info[8];
struct hfsplus_fork_raw alloc_file;
struct hfsplus_fork_raw ext_file;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 6643b24..82b69ee 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -193,6 +193,7 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir,
mutex_init(&hip->extents_lock);
hip->extent_state = 0;
hip->flags = 0;
+ hip->userflags = 0;
set_bit(HFSPLUS_I_RSRC, &hip->flags);
err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
@@ -400,6 +401,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode)
atomic_set(&hip->opencnt, 0);
hip->extent_state = 0;
hip->flags = 0;
+ hip->userflags = 0;
memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
hip->alloc_blocks = 0;
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index f66c765..c640ba5 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -20,6 +20,38 @@
#include <asm/uaccess.h>
#include "hfsplus_fs.h"
+/*
+ * "Blessing" an HFS+ filesystem writes metadata to the superblock informing
+ * the platform firmware which file to boot from
+ */
+static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags)
+{
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+ struct hfsplus_vh *vh = sbi->s_vhdr;
+ struct hfsplus_vh *bvh = sbi->s_backup_vhdr;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ mutex_lock(&sbi->vh_mutex);
+
+ /* Directory containing the bootable system */
+ vh->finder_info[0] = bvh->finder_info[0] =
+ cpu_to_be32(parent_ino(dentry));
+
+ /* Bootloader */
+ vh->finder_info[1] = bvh->finder_info[1] = cpu_to_be32(inode->i_ino);
+
+ /* Per spec, the OS X system folder - same as finder_info[0] here */
+ vh->finder_info[5] = bvh->finder_info[5] =
+ cpu_to_be32(parent_ino(dentry));
+
+ mutex_unlock(&sbi->vh_mutex);
+ return 0;
+}
+
static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
{
struct inode *inode = file->f_path.dentry->d_inode;
@@ -108,6 +140,8 @@ long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return hfsplus_ioctl_getflags(file, argp);
case HFSPLUS_IOC_EXT2_SETFLAGS:
return hfsplus_ioctl_setflags(file, argp);
+ case HFSPLUS_IOC_BLESS:
+ return hfsplus_ioctl_bless(file, argp);
default:
return -ENOTTY;
}
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 427682c..ceb1c28 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -465,6 +465,13 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
goto out_put_alloc_file;
}
+ sb->s_d_op = &hfsplus_dentry_operations;
+ sb->s_root = d_make_root(root);
+ if (!sb->s_root) {
+ err = -ENOMEM;
+ goto out_put_alloc_file;
+ }
+
str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
str.name = HFSP_HIDDENDIR_NAME;
err = hfs_find_init(sbi->cat_tree, &fd);
@@ -515,13 +522,6 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
}
}
- sb->s_d_op = &hfsplus_dentry_operations;
- sb->s_root = d_alloc_root(root);
- if (!sb->s_root) {
- err = -ENOMEM;
- goto out_put_hidden_dir;
- }
-
unload_nls(sbi->nls);
sbi->nls = nls;
return 0;
@@ -529,7 +529,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
out_put_hidden_dir:
iput(sbi->hidden_dir);
out_put_root:
- iput(root);
+ dput(sb->s_root);
+ sb->s_root = NULL;
out_put_alloc_file:
iput(sbi->alloc_file);
out_close_cat_tree:
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index 3cbfa93..1fe7313 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -67,7 +67,8 @@ extern int access_file(char *path, int r, int w, int x);
extern int open_file(char *path, int r, int w, int append);
extern void *open_dir(char *path, int *err_out);
extern char *read_dir(void *stream, unsigned long long *pos,
- unsigned long long *ino_out, int *len_out);
+ unsigned long long *ino_out, int *len_out,
+ unsigned int *type_out);
extern void close_file(void *stream);
extern int replace_file(int oldfd, int fd);
extern void close_dir(void *stream);
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index e130bd4..07c516b 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -283,6 +283,7 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
char *name;
unsigned long long next, ino;
int error, len;
+ unsigned int type;
name = dentry_name(file->f_path.dentry);
if (name == NULL)
@@ -292,9 +293,9 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
if (dir == NULL)
return -error;
next = file->f_pos;
- while ((name = read_dir(dir, &next, &ino, &len)) != NULL) {
+ while ((name = read_dir(dir, &next, &ino, &len, &type)) != NULL) {
error = (*filldir)(ent, name, len, file->f_pos,
- ino, DT_UNKNOWN);
+ ino, type);
if (error) break;
file->f_pos = next;
}
@@ -966,9 +967,9 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
}
err = -ENOMEM;
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (sb->s_root == NULL)
- goto out_put;
+ goto out;
return 0;
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index dd7bc38..a74ad0d 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -98,7 +98,8 @@ void *open_dir(char *path, int *err_out)
}
char *read_dir(void *stream, unsigned long long *pos,
- unsigned long long *ino_out, int *len_out)
+ unsigned long long *ino_out, int *len_out,
+ unsigned int *type_out)
{
DIR *dir = stream;
struct dirent *ent;
@@ -109,6 +110,7 @@ char *read_dir(void *stream, unsigned long long *pos,
return NULL;
*len_out = strlen(ent->d_name);
*ino_out = ent->d_ino;
+ *type_out = ent->d_type;
*pos = telldir(dir);
return ent->d_name;
}
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 3690467..54f6ecc 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -625,11 +625,9 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
hpfs_init_inode(root);
hpfs_read_inode(root);
unlock_new_inode(root);
- s->s_root = d_alloc_root(root);
- if (!s->s_root) {
- iput(root);
+ s->s_root = d_make_root(root);
+ if (!s->s_root)
goto bail0;
- }
/*
* find the root directory's . pointer & finish filling in the inode
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index d92f4ce..a80e45a 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -726,17 +726,12 @@ static int hppfs_fill_super(struct super_block *sb, void *d, int silent)
err = -ENOMEM;
root_inode = get_inode(sb, dget(proc_mnt->mnt_root));
- if (!root_inode)
- goto out_mntput;
-
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (!sb->s_root)
- goto out_iput;
+ goto out_mntput;
return 0;
- out_iput:
- iput(root_inode);
out_mntput:
mntput(proc_mnt);
out:
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 1e85a7a..ea25174 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -41,6 +41,25 @@ const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
+struct hugetlbfs_config {
+ uid_t uid;
+ gid_t gid;
+ umode_t mode;
+ long nr_blocks;
+ long nr_inodes;
+ struct hstate *hstate;
+};
+
+struct hugetlbfs_inode_info {
+ struct shared_policy policy;
+ struct inode vfs_inode;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+ return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
static struct backing_dev_info hugetlbfs_backing_dev_info = {
.name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
@@ -154,10 +173,12 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
return addr;
}
- start_addr = mm->free_area_cache;
-
- if (len <= mm->cached_hole_size)
+ if (len > mm->cached_hole_size)
+ start_addr = mm->free_area_cache;
+ else {
start_addr = TASK_UNMAPPED_BASE;
+ mm->cached_hole_size = 0;
+ }
full_search:
addr = ALIGN(start_addr, huge_page_size(h));
@@ -171,13 +192,18 @@ full_search:
*/
if (start_addr != TASK_UNMAPPED_BASE) {
start_addr = TASK_UNMAPPED_BASE;
+ mm->cached_hole_size = 0;
goto full_search;
}
return -ENOMEM;
}
- if (!vma || addr + len <= vma->vm_start)
+ if (!vma || addr + len <= vma->vm_start) {
+ mm->free_area_cache = addr + len;
return addr;
+ }
+ if (addr + mm->cached_hole_size < vma->vm_start)
+ mm->cached_hole_size = vma->vm_start - addr;
addr = ALIGN(vma->vm_end, huge_page_size(h));
}
}
@@ -238,17 +264,10 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
loff_t isize;
ssize_t retval = 0;
- mutex_lock(&inode->i_mutex);
-
/* validate length */
if (len == 0)
goto out;
- isize = i_size_read(inode);
- if (!isize)
- goto out;
-
- end_index = (isize - 1) >> huge_page_shift(h);
for (;;) {
struct page *page;
unsigned long nr, ret;
@@ -256,18 +275,21 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
/* nr is the maximum number of bytes to copy from this page */
nr = huge_page_size(h);
+ isize = i_size_read(inode);
+ if (!isize)
+ goto out;
+ end_index = (isize - 1) >> huge_page_shift(h);
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
- if (nr <= offset) {
+ if (nr <= offset)
goto out;
- }
}
nr = nr - offset;
/* Find the page */
- page = find_get_page(mapping, index);
+ page = find_lock_page(mapping, index);
if (unlikely(page == NULL)) {
/*
* We have a HOLE, zero out the user-buffer for the
@@ -279,17 +301,18 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
else
ra = 0;
} else {
+ unlock_page(page);
+
/*
* We have the page, copy it to user space buffer.
*/
ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
ret = ra;
+ page_cache_release(page);
}
if (ra < 0) {
if (retval == 0)
retval = ra;
- if (page)
- page_cache_release(page);
goto out;
}
@@ -299,16 +322,12 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
- if (page)
- page_cache_release(page);
-
/* short read or no more work */
if ((ret != nr) || (len == 0))
break;
}
out:
*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
- mutex_unlock(&inode->i_mutex);
return retval;
}
@@ -607,9 +626,15 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
spin_lock(&sbinfo->stat_lock);
/* If no limits set, just report 0 for max/free/used
* blocks, like simple_statfs() */
- if (sbinfo->max_blocks >= 0) {
- buf->f_blocks = sbinfo->max_blocks;
- buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+ if (sbinfo->spool) {
+ long free_pages;
+
+ spin_lock(&sbinfo->spool->lock);
+ buf->f_blocks = sbinfo->spool->max_hpages;
+ free_pages = sbinfo->spool->max_hpages
+ - sbinfo->spool->used_hpages;
+ buf->f_bavail = buf->f_bfree = free_pages;
+ spin_unlock(&sbinfo->spool->lock);
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
@@ -625,6 +650,10 @@ static void hugetlbfs_put_super(struct super_block *sb)
if (sbi) {
sb->s_fs_info = NULL;
+
+ if (sbi->spool)
+ hugepage_put_subpool(sbi->spool);
+
kfree(sbi);
}
}
@@ -831,8 +860,6 @@ bad_val:
static int
hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
{
- struct inode * inode;
- struct dentry * root;
int ret;
struct hugetlbfs_config config;
struct hugetlbfs_sb_info *sbinfo;
@@ -855,60 +882,31 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_fs_info = sbinfo;
sbinfo->hstate = config.hstate;
spin_lock_init(&sbinfo->stat_lock);
- sbinfo->max_blocks = config.nr_blocks;
- sbinfo->free_blocks = config.nr_blocks;
sbinfo->max_inodes = config.nr_inodes;
sbinfo->free_inodes = config.nr_inodes;
+ sbinfo->spool = NULL;
+ if (config.nr_blocks != -1) {
+ sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
+ if (!sbinfo->spool)
+ goto out_free;
+ }
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = huge_page_size(config.hstate);
sb->s_blocksize_bits = huge_page_shift(config.hstate);
sb->s_magic = HUGETLBFS_MAGIC;
sb->s_op = &hugetlbfs_ops;
sb->s_time_gran = 1;
- inode = hugetlbfs_get_root(sb, &config);
- if (!inode)
- goto out_free;
-
- root = d_alloc_root(inode);
- if (!root) {
- iput(inode);
+ sb->s_root = d_make_root(hugetlbfs_get_root(sb, &config));
+ if (!sb->s_root)
goto out_free;
- }
- sb->s_root = root;
return 0;
out_free:
+ if (sbinfo->spool)
+ kfree(sbinfo->spool);
kfree(sbinfo);
return -ENOMEM;
}
-int hugetlb_get_quota(struct address_space *mapping, long delta)
-{
- int ret = 0;
- struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
- if (sbinfo->free_blocks > -1) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks - delta >= 0)
- sbinfo->free_blocks -= delta;
- else
- ret = -ENOMEM;
- spin_unlock(&sbinfo->stat_lock);
- }
-
- return ret;
-}
-
-void hugetlb_put_quota(struct address_space *mapping, long delta)
-{
- struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
- if (sbinfo->free_blocks > -1) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += delta;
- spin_unlock(&sbinfo->stat_lock);
- }
-}
-
static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
@@ -928,8 +926,8 @@ static int can_do_hugetlb_shm(void)
return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
}
-struct file *hugetlb_file_setup(const char *name, size_t size,
- vm_flags_t acctflag,
+struct file *hugetlb_file_setup(const char *name, unsigned long addr,
+ size_t size, vm_flags_t acctflag,
struct user_struct **user, int creat_flags)
{
int error = -ENOMEM;
@@ -938,6 +936,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
struct path path;
struct dentry *root;
struct qstr quick_string;
+ struct hstate *hstate;
+ unsigned long num_pages;
*user = NULL;
if (!hugetlbfs_vfsmount)
@@ -946,7 +946,11 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
*user = current_user();
if (user_shm_lock(size, *user)) {
- printk_once(KERN_WARNING "Using mlock ulimits for SHM_HUGETLB is deprecated\n");
+ task_lock(current);
+ printk_once(KERN_WARNING
+ "%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+ current->comm, current->pid);
+ task_unlock(current);
} else {
*user = NULL;
return ERR_PTR(-EPERM);
@@ -967,10 +971,12 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
if (!inode)
goto out_dentry;
+ hstate = hstate_inode(inode);
+ size += addr & ~huge_page_mask(hstate);
+ num_pages = ALIGN(size, huge_page_size(hstate)) >>
+ huge_page_shift(hstate);
error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0,
- size >> huge_page_shift(hstate_inode(inode)), NULL,
- acctflag))
+ if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
goto out_inode;
d_instantiate(path.dentry, inode);
@@ -1006,6 +1012,7 @@ static int __init init_hugetlbfs_fs(void)
if (error)
return error;
+ error = -ENOMEM;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
0, 0, init_once);
@@ -1024,10 +1031,10 @@ static int __init init_hugetlbfs_fs(void)
}
error = PTR_ERR(vfsmount);
+ unregister_filesystem(&hugetlbfs_fs_type);
out:
- if (error)
- kmem_cache_destroy(hugetlbfs_inode_cachep);
+ kmem_cache_destroy(hugetlbfs_inode_cachep);
out2:
bdi_destroy(&hugetlbfs_backing_dev_info);
return error;
diff --git a/fs/inode.c b/fs/inode.c
index fb10d86..9f4f5fe 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2,29 +2,19 @@
* (C) 1997 Linus Torvalds
* (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
*/
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/mm.h>
-#include <linux/dcache.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/writeback.h>
-#include <linux/module.h>
#include <linux/backing-dev.h>
-#include <linux/wait.h>
-#include <linux/rwsem.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
-#include <linux/pagemap.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
-#include <linux/async.h>
#include <linux/posix_acl.h>
#include <linux/prefetch.h>
-#include <linux/ima.h>
-#include <linux/cred.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
#include "internal.h"
@@ -938,8 +928,7 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode)
struct file_system_type *type = inode->i_sb->s_type;
/* Set new key only if filesystem hasn't already changed it */
- if (!lockdep_match_class(&inode->i_mutex,
- &type->i_mutex_key)) {
+ if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) {
/*
* ensure nobody is actually holding i_mutex
*/
@@ -966,6 +955,7 @@ void unlock_new_inode(struct inode *inode)
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW;
+ smp_mb();
wake_up_bit(&inode->i_state, __I_NEW);
spin_unlock(&inode->i_lock);
}
@@ -1369,17 +1359,6 @@ int generic_delete_inode(struct inode *inode)
EXPORT_SYMBOL(generic_delete_inode);
/*
- * Normal UNIX filesystem behaviour: delete the
- * inode when the usage count drops to zero, and
- * i_nlink is zero.
- */
-int generic_drop_inode(struct inode *inode)
-{
- return !inode->i_nlink || inode_unhashed(inode);
-}
-EXPORT_SYMBOL_GPL(generic_drop_inode);
-
-/*
* Called when we're dropping the last reference
* to an inode.
*
@@ -1510,9 +1489,10 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
-void touch_atime(struct vfsmount *mnt, struct dentry *dentry)
+void touch_atime(struct path *path)
{
- struct inode *inode = dentry->d_inode;
+ struct vfsmount *mnt = path->mnt;
+ struct inode *inode = path->dentry->d_inode;
struct timespec now;
if (inode->i_flags & S_NOATIME)
@@ -1651,7 +1631,7 @@ __setup("ihash_entries=", set_ihash_entries);
*/
void __init inode_init_early(void)
{
- int loop;
+ unsigned int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
@@ -1669,13 +1649,13 @@ void __init inode_init_early(void)
&i_hash_mask,
0);
- for (loop = 0; loop < (1 << i_hash_shift); loop++)
+ for (loop = 0; loop < (1U << i_hash_shift); loop++)
INIT_HLIST_HEAD(&inode_hashtable[loop]);
}
void __init inode_init(void)
{
- int loop;
+ unsigned int loop;
/* inode slab cache */
inode_cachep = kmem_cache_create("inode_cache",
@@ -1699,7 +1679,7 @@ void __init inode_init(void)
&i_hash_mask,
0);
- for (loop = 0; loop < (1 << i_hash_shift); loop++)
+ for (loop = 0; loop < (1U << i_hash_shift); loop++)
INIT_HLIST_HEAD(&inode_hashtable[loop]);
}
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 066836e..29167be 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -10,7 +10,7 @@
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/security.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/uaccess.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
diff --git a/fs/ioprio.c b/fs/ioprio.c
index f84b380..0f1b951 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -51,7 +51,7 @@ int set_task_ioprio(struct task_struct *task, int ioprio)
ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
if (ioc) {
ioc_ioprio_changed(ioc, ioprio);
- put_io_context(ioc, NULL);
+ put_io_context(ioc);
}
return err;
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index bd62c76..29037c3 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -947,9 +947,8 @@ root_found:
s->s_d_op = &isofs_dentry_ops[table];
/* get the root dentry */
- s->s_root = d_alloc_root(inode);
+ s->s_root = d_make_root(inode);
if (!(s->s_root)) {
- iput(inode);
error = -ENOMEM;
goto out_no_inode;
}
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 5d1a00a..05f0754 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -453,8 +453,6 @@ out:
*
* Return <0 on error, 0 on success, 1 if there was nothing to clean up.
*
- * Called with the journal lock held.
- *
* This is the only part of the journaling code which really needs to be
* aware of transaction aborts. Checkpointing involves writing to the
* main filesystem area rather than to the journal, so it can proceed
@@ -472,13 +470,14 @@ int cleanup_journal_tail(journal_t *journal)
if (is_journal_aborted(journal))
return 1;
- /* OK, work out the oldest transaction remaining in the log, and
+ /*
+ * OK, work out the oldest transaction remaining in the log, and
* the log block it starts at.
*
* If the log is now empty, we need to work out which is the
* next transaction ID we will write, and where it will
- * start. */
-
+ * start.
+ */
spin_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
transaction = journal->j_checkpoint_transactions;
@@ -504,7 +503,25 @@ int cleanup_journal_tail(journal_t *journal)
spin_unlock(&journal->j_state_lock);
return 1;
}
+ spin_unlock(&journal->j_state_lock);
+
+ /*
+ * We need to make sure that any blocks that were recently written out
+ * --- perhaps by log_do_checkpoint() --- are flushed out before we
+ * drop the transactions from the journal. It's unlikely this will be
+ * necessary, especially with an appropriately sized journal, but we
+ * need this to guarantee correctness. Fortunately
+ * cleanup_journal_tail() doesn't get called all that often.
+ */
+ if (journal->j_flags & JFS_BARRIER)
+ blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+ spin_lock(&journal->j_state_lock);
+ if (!tid_gt(first_tid, journal->j_tail_sequence)) {
+ spin_unlock(&journal->j_state_lock);
+ /* Someone else cleaned up journal so return 0 */
+ return 0;
+ }
/* OK, update the superblock to recover the freed space.
* Physical blocks come first: have we wrapped beyond the end of
* the log? */
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 59c09f9..0971e92 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -129,6 +129,8 @@ static int kjournald(void *arg)
setup_timer(&journal->j_commit_timer, commit_timeout,
(unsigned long)current);
+ set_freezable();
+
/* Record that the journal thread is running */
journal->j_task = current;
wake_up(&journal->j_wait_done_commit);
@@ -328,7 +330,7 @@ repeat:
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
}
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
/*
* Check for escaping
*/
@@ -337,7 +339,7 @@ repeat:
need_copy_out = 1;
do_escape = 1;
}
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
/*
* Do we need to do a data copy?
@@ -354,9 +356,9 @@ repeat:
}
jh_in->b_frozen_data = tmp;
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
new_page = virt_to_page(tmp);
new_offset = offset_in_page(tmp);
@@ -368,9 +370,9 @@ repeat:
* copying, we can finally do so.
*/
if (do_escape) {
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
*((unsigned int *)(mapped_data + new_offset)) = 0;
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
}
set_bh_page(new_bh, new_page, new_offset);
diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c
index 5b43e96..008bf06 100644
--- a/fs/jbd/recovery.c
+++ b/fs/jbd/recovery.c
@@ -20,6 +20,7 @@
#include <linux/fs.h>
#include <linux/jbd.h>
#include <linux/errno.h>
+#include <linux/blkdev.h>
#endif
/*
@@ -263,6 +264,9 @@ int journal_recover(journal_t *journal)
err2 = sync_blockdev(journal->j_fs_dev);
if (!err)
err = err2;
+ /* Flush disk caches to get replayed data on the permanent storage */
+ if (journal->j_flags & JFS_BARRIER)
+ blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
return err;
}
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 7fce94b..b2a7e52 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -718,9 +718,9 @@ done:
"Possible IO failure.\n");
page = jh2bh(jh)->b_page;
offset = offset_in_page(jh2bh(jh)->b_data);
- source = kmap_atomic(page, KM_USER0);
+ source = kmap_atomic(page);
memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
- kunmap_atomic(source, KM_USER0);
+ kunmap_atomic(source);
}
jbd_unlock_bh_state(bh);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index d49d202..c78841e 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -88,14 +88,13 @@ static inline void __buffer_relink_io(struct journal_head *jh)
* whole transaction.
*
* Requires j_list_lock
- * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
*/
static int __try_to_free_cp_buf(struct journal_head *jh)
{
int ret = 0;
struct buffer_head *bh = jh2bh(jh);
- if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
+ if (jh->b_transaction == NULL && !buffer_locked(bh) &&
!buffer_dirty(bh) && !buffer_write_io_error(bh)) {
/*
* Get our reference so that bh cannot be freed before
@@ -104,11 +103,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
get_bh(bh);
JBUFFER_TRACE(jh, "remove from checkpoint list");
ret = __jbd2_journal_remove_checkpoint(jh) + 1;
- jbd_unlock_bh_state(bh);
BUFFER_TRACE(bh, "release");
__brelse(bh);
- } else {
- jbd_unlock_bh_state(bh);
}
return ret;
}
@@ -180,21 +176,6 @@ void __jbd2_log_wait_for_space(journal_t *journal)
}
/*
- * We were unable to perform jbd_trylock_bh_state() inside j_list_lock.
- * The caller must restart a list walk. Wait for someone else to run
- * jbd_unlock_bh_state().
- */
-static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
- __releases(journal->j_list_lock)
-{
- get_bh(bh);
- spin_unlock(&journal->j_list_lock);
- jbd_lock_bh_state(bh);
- jbd_unlock_bh_state(bh);
- put_bh(bh);
-}
-
-/*
* Clean up transaction's list of buffers submitted for io.
* We wait for any pending IO to complete and remove any clean
* buffers. Note that we take the buffers in the opposite ordering
@@ -222,15 +203,9 @@ restart:
while (!released && transaction->t_checkpoint_io_list) {
jh = transaction->t_checkpoint_io_list;
bh = jh2bh(jh);
- if (!jbd_trylock_bh_state(bh)) {
- jbd_sync_bh(journal, bh);
- spin_lock(&journal->j_list_lock);
- goto restart;
- }
get_bh(bh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
@@ -246,7 +221,6 @@ restart:
* it has been written out and so we can drop it from the list
*/
released = __jbd2_journal_remove_checkpoint(jh);
- jbd_unlock_bh_state(bh);
__brelse(bh);
}
@@ -266,7 +240,6 @@ __flush_batch(journal_t *journal, int *batch_count)
for (i = 0; i < *batch_count; i++) {
struct buffer_head *bh = journal->j_chkpt_bhs[i];
- clear_buffer_jwrite(bh);
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
}
@@ -281,7 +254,6 @@ __flush_batch(journal_t *journal, int *batch_count)
* be written out.
*
* Called with j_list_lock held and drops it if 1 is returned
- * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
*/
static int __process_buffer(journal_t *journal, struct journal_head *jh,
int *batch_count, transaction_t *transaction)
@@ -292,7 +264,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
if (buffer_locked(bh)) {
get_bh(bh);
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
@@ -304,7 +275,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
transaction->t_chp_stats.cs_forced_to_close++;
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
if (unlikely(journal->j_flags & JBD2_UNMOUNT))
/*
* The journal thread is dead; so starting and
@@ -323,11 +293,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
if (unlikely(buffer_write_io_error(bh)))
ret = -EIO;
get_bh(bh);
- J_ASSERT_JH(jh, !buffer_jbddirty(bh));
BUFFER_TRACE(bh, "remove from checkpoint");
__jbd2_journal_remove_checkpoint(jh);
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
__brelse(bh);
} else {
/*
@@ -340,10 +308,8 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
BUFFER_TRACE(bh, "queue");
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
- set_buffer_jwrite(bh);
journal->j_chkpt_bhs[*batch_count] = bh;
__buffer_relink_io(jh);
- jbd_unlock_bh_state(bh);
transaction->t_chp_stats.cs_written++;
(*batch_count)++;
if (*batch_count == JBD2_NR_BATCH) {
@@ -407,15 +373,7 @@ restart:
int retry = 0, err;
while (!retry && transaction->t_checkpoint_list) {
- struct buffer_head *bh;
-
jh = transaction->t_checkpoint_list;
- bh = jh2bh(jh);
- if (!jbd_trylock_bh_state(bh)) {
- jbd_sync_bh(journal, bh);
- retry = 1;
- break;
- }
retry = __process_buffer(journal, jh, &batch_count,
transaction);
if (retry < 0 && !result)
@@ -478,79 +436,28 @@ out:
int jbd2_cleanup_journal_tail(journal_t *journal)
{
- transaction_t * transaction;
tid_t first_tid;
- unsigned long blocknr, freed;
+ unsigned long blocknr;
if (is_journal_aborted(journal))
return 1;
- /* OK, work out the oldest transaction remaining in the log, and
- * the log block it starts at.
- *
- * If the log is now empty, we need to work out which is the
- * next transaction ID we will write, and where it will
- * start. */
-
- write_lock(&journal->j_state_lock);
- spin_lock(&journal->j_list_lock);
- transaction = journal->j_checkpoint_transactions;
- if (transaction) {
- first_tid = transaction->t_tid;
- blocknr = transaction->t_log_start;
- } else if ((transaction = journal->j_committing_transaction) != NULL) {
- first_tid = transaction->t_tid;
- blocknr = transaction->t_log_start;
- } else if ((transaction = journal->j_running_transaction) != NULL) {
- first_tid = transaction->t_tid;
- blocknr = journal->j_head;
- } else {
- first_tid = journal->j_transaction_sequence;
- blocknr = journal->j_head;
- }
- spin_unlock(&journal->j_list_lock);
- J_ASSERT(blocknr != 0);
-
- /* If the oldest pinned transaction is at the tail of the log
- already then there's not much we can do right now. */
- if (journal->j_tail_sequence == first_tid) {
- write_unlock(&journal->j_state_lock);
+ if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr))
return 1;
- }
-
- /* OK, update the superblock to recover the freed space.
- * Physical blocks come first: have we wrapped beyond the end of
- * the log? */
- freed = blocknr - journal->j_tail;
- if (blocknr < journal->j_tail)
- freed = freed + journal->j_last - journal->j_first;
-
- trace_jbd2_cleanup_journal_tail(journal, first_tid, blocknr, freed);
- jbd_debug(1,
- "Cleaning journal tail from %d to %d (offset %lu), "
- "freeing %lu\n",
- journal->j_tail_sequence, first_tid, blocknr, freed);
-
- journal->j_free += freed;
- journal->j_tail_sequence = first_tid;
- journal->j_tail = blocknr;
- write_unlock(&journal->j_state_lock);
+ J_ASSERT(blocknr != 0);
/*
- * If there is an external journal, we need to make sure that
- * any data blocks that were recently written out --- perhaps
- * by jbd2_log_do_checkpoint() --- are flushed out before we
- * drop the transactions from the external journal. It's
- * unlikely this will be necessary, especially with a
- * appropriately sized journal, but we need this to guarantee
- * correctness. Fortunately jbd2_cleanup_journal_tail()
- * doesn't get called all that often.
+ * We need to make sure that any blocks that were recently written out
+ * --- perhaps by jbd2_log_do_checkpoint() --- are flushed out before
+ * we drop the transactions from the journal. It's unlikely this will
+ * be necessary, especially with an appropriately sized journal, but we
+ * need this to guarantee correctness. Fortunately
+ * jbd2_cleanup_journal_tail() doesn't get called all that often.
*/
- if ((journal->j_fs_dev != journal->j_dev) &&
- (journal->j_flags & JBD2_BARRIER))
+ if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
- if (!(journal->j_flags & JBD2_ABORT))
- jbd2_journal_update_superblock(journal, 1);
+
+ __jbd2_update_log_tail(journal, first_tid, blocknr);
return 0;
}
@@ -582,15 +489,12 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
do {
jh = next_jh;
next_jh = jh->b_cpnext;
- /* Use trylock because of the ranking */
- if (jbd_trylock_bh_state(jh2bh(jh))) {
- ret = __try_to_free_cp_buf(jh);
- if (ret) {
- freed++;
- if (ret == 2) {
- *released = 1;
- return freed;
- }
+ ret = __try_to_free_cp_buf(jh);
+ if (ret) {
+ freed++;
+ if (ret == 2) {
+ *released = 1;
+ return freed;
}
}
/*
@@ -673,9 +577,7 @@ out:
* The function can free jh and bh.
*
* This function is called with j_list_lock held.
- * This function is called with jbd_lock_bh_state(jh2bh(jh))
*/
-
int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
{
struct transaction_chp_stats_s *stats;
@@ -722,7 +624,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
transaction->t_tid, stats);
__jbd2_journal_drop_transaction(journal, transaction);
- kfree(transaction);
+ jbd2_journal_free_transaction(transaction);
/* Just in case anybody was waiting for more transactions to be
checkpointed... */
@@ -797,5 +699,7 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
J_ASSERT(journal->j_committing_transaction != transaction);
J_ASSERT(journal->j_running_transaction != transaction);
+ trace_jbd2_drop_transaction(journal, transaction);
+
jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
}
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 5069b84..17f557f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -286,10 +286,10 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
char *addr;
__u32 checksum;
- addr = kmap_atomic(page, KM_USER0);
+ addr = kmap_atomic(page);
checksum = crc32_be(crc32_sum,
(void *)(addr + offset_in_page(bh->b_data)), bh->b_size);
- kunmap_atomic(addr, KM_USER0);
+ kunmap_atomic(addr);
return checksum;
}
@@ -331,6 +331,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
struct buffer_head *cbh = NULL; /* For transactional checksums */
__u32 crc32_sum = ~0;
struct blk_plug plug;
+ /* Tail of the journal */
+ unsigned long first_block;
+ tid_t first_tid;
+ int update_tail;
/*
* First job: lock down the current transaction and wait for
@@ -340,7 +344,18 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/* Do we need to erase the effects of a prior jbd2_journal_flush? */
if (journal->j_flags & JBD2_FLUSHED) {
jbd_debug(3, "super block updated\n");
- jbd2_journal_update_superblock(journal, 1);
+ mutex_lock(&journal->j_checkpoint_mutex);
+ /*
+ * We hold j_checkpoint_mutex so tail cannot change under us.
+ * We don't need any special data guarantees for writing sb
+ * since journal is empty and it is ok for write to be
+ * flushed only with transaction commit.
+ */
+ jbd2_journal_update_sb_log_tail(journal,
+ journal->j_tail_sequence,
+ journal->j_tail,
+ WRITE_SYNC);
+ mutex_unlock(&journal->j_checkpoint_mutex);
} else {
jbd_debug(3, "superblock not updated\n");
}
@@ -677,10 +692,30 @@ start_journal_io:
err = 0;
}
+ /*
+ * Get current oldest transaction in the log before we issue flush
+ * to the filesystem device. After the flush we can be sure that
+ * blocks of all older transactions are checkpointed to persistent
+ * storage and we will be safe to update journal start in the
+ * superblock with the numbers we get here.
+ */
+ update_tail =
+ jbd2_journal_get_log_tail(journal, &first_tid, &first_block);
+
write_lock(&journal->j_state_lock);
+ if (update_tail) {
+ long freed = first_block - journal->j_tail;
+
+ if (first_block < journal->j_tail)
+ freed += journal->j_last - journal->j_first;
+ /* Update tail only if we free significant amount of space */
+ if (freed < journal->j_maxlen / 4)
+ update_tail = 0;
+ }
J_ASSERT(commit_transaction->t_state == T_COMMIT);
commit_transaction->t_state = T_COMMIT_DFLUSH;
write_unlock(&journal->j_state_lock);
+
/*
* If the journal is not located on the file system device,
* then we must flush the file system device before we issue
@@ -831,6 +866,14 @@ wait_for_iobuf:
if (err)
jbd2_journal_abort(journal, err);
+ /*
+ * Now disk caches for filesystem device are flushed so we are safe to
+ * erase checkpointed transactions from the log by updating journal
+ * superblock.
+ */
+ if (update_tail)
+ jbd2_update_log_tail(journal, first_tid, first_block);
+
/* End of a transaction! Finally, we can do checkpoint
processing: any buffers committed as a result of this
transaction can be removed from any checkpoint list it was on
@@ -1048,7 +1091,7 @@ restart_loop:
jbd_debug(1, "JBD2: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
if (to_free)
- kfree(commit_transaction);
+ jbd2_journal_free_transaction(commit_transaction);
wake_up(&journal->j_wait_done_commit);
}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c0a5f9f..98ed6db 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -71,7 +71,6 @@ EXPORT_SYMBOL(jbd2_journal_revoke);
EXPORT_SYMBOL(jbd2_journal_init_dev);
EXPORT_SYMBOL(jbd2_journal_init_inode);
-EXPORT_SYMBOL(jbd2_journal_update_format);
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
@@ -96,7 +95,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
EXPORT_SYMBOL(jbd2_inode_cache);
-static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
static int jbd2_journal_create_slab(size_t slab_size);
@@ -139,6 +137,8 @@ static int kjournald2(void *arg)
setup_timer(&journal->j_commit_timer, commit_timeout,
(unsigned long)current);
+ set_freezable();
+
/* Record that the journal thread is running */
journal->j_task = current;
wake_up(&journal->j_wait_done_commit);
@@ -345,7 +345,7 @@ repeat:
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
}
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
/*
* Fire data frozen trigger if data already wasn't frozen. Do this
* before checking for escaping, as the trigger may modify the magic
@@ -364,7 +364,7 @@ repeat:
need_copy_out = 1;
do_escape = 1;
}
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
/*
* Do we need to do a data copy?
@@ -385,9 +385,9 @@ repeat:
}
jh_in->b_frozen_data = tmp;
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
new_page = virt_to_page(tmp);
new_offset = offset_in_page(tmp);
@@ -406,9 +406,9 @@ repeat:
* copying, we can finally do so.
*/
if (do_escape) {
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
*((unsigned int *)(mapped_data + new_offset)) = 0;
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
}
set_bh_page(new_bh, new_page, new_offset);
@@ -744,6 +744,98 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
return jbd2_journal_add_journal_head(bh);
}
+/*
+ * Return tid of the oldest transaction in the journal and block in the journal
+ * where the transaction starts.
+ *
+ * If the journal is now empty, return which will be the next transaction ID
+ * we will write and where will that transaction start.
+ *
+ * The return value is 0 if journal tail cannot be pushed any further, 1 if
+ * it can.
+ */
+int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
+ unsigned long *block)
+{
+ transaction_t *transaction;
+ int ret;
+
+ read_lock(&journal->j_state_lock);
+ spin_lock(&journal->j_list_lock);
+ transaction = journal->j_checkpoint_transactions;
+ if (transaction) {
+ *tid = transaction->t_tid;
+ *block = transaction->t_log_start;
+ } else if ((transaction = journal->j_committing_transaction) != NULL) {
+ *tid = transaction->t_tid;
+ *block = transaction->t_log_start;
+ } else if ((transaction = journal->j_running_transaction) != NULL) {
+ *tid = transaction->t_tid;
+ *block = journal->j_head;
+ } else {
+ *tid = journal->j_transaction_sequence;
+ *block = journal->j_head;
+ }
+ ret = tid_gt(*tid, journal->j_tail_sequence);
+ spin_unlock(&journal->j_list_lock);
+ read_unlock(&journal->j_state_lock);
+
+ return ret;
+}
+
+/*
+ * Update information in journal structure and in on disk journal superblock
+ * about log tail. This function does not check whether information passed in
+ * really pushes log tail further. It's responsibility of the caller to make
+ * sure provided log tail information is valid (e.g. by holding
+ * j_checkpoint_mutex all the time between computing log tail and calling this
+ * function as is the case with jbd2_cleanup_journal_tail()).
+ *
+ * Requires j_checkpoint_mutex
+ */
+void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+{
+ unsigned long freed;
+
+ BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
+
+ /*
+ * We cannot afford for write to remain in drive's caches since as
+ * soon as we update j_tail, next transaction can start reusing journal
+ * space and if we lose sb update during power failure we'd replay
+ * old transaction with possibly newly overwritten data.
+ */
+ jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA);
+ write_lock(&journal->j_state_lock);
+ freed = block - journal->j_tail;
+ if (block < journal->j_tail)
+ freed += journal->j_last - journal->j_first;
+
+ trace_jbd2_update_log_tail(journal, tid, block, freed);
+ jbd_debug(1,
+ "Cleaning journal tail from %d to %d (offset %lu), "
+ "freeing %lu\n",
+ journal->j_tail_sequence, tid, block, freed);
+
+ journal->j_free += freed;
+ journal->j_tail_sequence = tid;
+ journal->j_tail = block;
+ write_unlock(&journal->j_state_lock);
+}
+
+/*
+ * This is a variaon of __jbd2_update_log_tail which checks for validity of
+ * provided log tail and locks j_checkpoint_mutex. So it is safe against races
+ * with other threads updating log tail.
+ */
+void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+{
+ mutex_lock(&journal->j_checkpoint_mutex);
+ if (tid_gt(tid, journal->j_tail_sequence))
+ __jbd2_update_log_tail(journal, tid, block);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+}
+
struct jbd2_stats_proc_session {
journal_t *journal;
struct transaction_stats_s *stats;
@@ -1112,40 +1204,45 @@ static int journal_reset(journal_t *journal)
journal->j_max_transaction_buffers = journal->j_maxlen / 4;
- /* Add the dynamic fields and write it to disk. */
- jbd2_journal_update_superblock(journal, 1);
- return jbd2_journal_start_thread(journal);
-}
-
-/**
- * void jbd2_journal_update_superblock() - Update journal sb on disk.
- * @journal: The journal to update.
- * @wait: Set to '0' if you don't want to wait for IO completion.
- *
- * Update a journal's dynamic superblock fields and write it to disk,
- * optionally waiting for the IO to complete.
- */
-void jbd2_journal_update_superblock(journal_t *journal, int wait)
-{
- journal_superblock_t *sb = journal->j_superblock;
- struct buffer_head *bh = journal->j_sb_buffer;
-
/*
* As a special case, if the on-disk copy is already marked as needing
- * no recovery (s_start == 0) and there are no outstanding transactions
- * in the filesystem, then we can safely defer the superblock update
- * until the next commit by setting JBD2_FLUSHED. This avoids
+ * no recovery (s_start == 0), then we can safely defer the superblock
+ * update until the next commit by setting JBD2_FLUSHED. This avoids
* attempting a write to a potential-readonly device.
*/
- if (sb->s_start == 0 && journal->j_tail_sequence ==
- journal->j_transaction_sequence) {
+ if (sb->s_start == 0) {
jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
"(start %ld, seq %d, errno %d)\n",
journal->j_tail, journal->j_tail_sequence,
journal->j_errno);
- goto out;
+ journal->j_flags |= JBD2_FLUSHED;
+ } else {
+ /* Lock here to make assertions happy... */
+ mutex_lock(&journal->j_checkpoint_mutex);
+ /*
+ * Update log tail information. We use WRITE_FUA since new
+ * transaction will start reusing journal space and so we
+ * must make sure information about current log tail is on
+ * disk before that.
+ */
+ jbd2_journal_update_sb_log_tail(journal,
+ journal->j_tail_sequence,
+ journal->j_tail,
+ WRITE_FUA);
+ mutex_unlock(&journal->j_checkpoint_mutex);
}
+ return jbd2_journal_start_thread(journal);
+}
+static void jbd2_write_superblock(journal_t *journal, int write_op)
+{
+ struct buffer_head *bh = journal->j_sb_buffer;
+ int ret;
+
+ trace_jbd2_write_superblock(journal, write_op);
+ if (!(journal->j_flags & JBD2_BARRIER))
+ write_op &= ~(REQ_FUA | REQ_FLUSH);
+ lock_buffer(bh);
if (buffer_write_io_error(bh)) {
/*
* Oh, dear. A previous attempt to write the journal
@@ -1161,48 +1258,106 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
clear_buffer_write_io_error(bh);
set_buffer_uptodate(bh);
}
+ get_bh(bh);
+ bh->b_end_io = end_buffer_write_sync;
+ ret = submit_bh(write_op, bh);
+ wait_on_buffer(bh);
+ if (buffer_write_io_error(bh)) {
+ clear_buffer_write_io_error(bh);
+ set_buffer_uptodate(bh);
+ ret = -EIO;
+ }
+ if (ret) {
+ printk(KERN_ERR "JBD2: Error %d detected when updating "
+ "journal superblock for %s.\n", ret,
+ journal->j_devname);
+ }
+}
+/**
+ * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk.
+ * @journal: The journal to update.
+ * @tail_tid: TID of the new transaction at the tail of the log
+ * @tail_block: The first block of the transaction at the tail of the log
+ * @write_op: With which operation should we write the journal sb
+ *
+ * Update a journal's superblock information about log tail and write it to
+ * disk, waiting for the IO to complete.
+ */
+void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
+ unsigned long tail_block, int write_op)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+
+ BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
+ jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
+ tail_block, tail_tid);
+
+ sb->s_sequence = cpu_to_be32(tail_tid);
+ sb->s_start = cpu_to_be32(tail_block);
+
+ jbd2_write_superblock(journal, write_op);
+
+ /* Log is no longer empty */
+ write_lock(&journal->j_state_lock);
+ WARN_ON(!sb->s_sequence);
+ journal->j_flags &= ~JBD2_FLUSHED;
+ write_unlock(&journal->j_state_lock);
+}
+
+/**
+ * jbd2_mark_journal_empty() - Mark on disk journal as empty.
+ * @journal: The journal to update.
+ *
+ * Update a journal's dynamic superblock fields to show that journal is empty.
+ * Write updated superblock to disk waiting for IO to complete.
+ */
+static void jbd2_mark_journal_empty(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+
+ BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
read_lock(&journal->j_state_lock);
- jbd_debug(1, "JBD2: updating superblock (start %ld, seq %d, errno %d)\n",
- journal->j_tail, journal->j_tail_sequence, journal->j_errno);
+ jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
+ journal->j_tail_sequence);
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
- sb->s_start = cpu_to_be32(journal->j_tail);
- sb->s_errno = cpu_to_be32(journal->j_errno);
+ sb->s_start = cpu_to_be32(0);
read_unlock(&journal->j_state_lock);
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- if (wait) {
- sync_dirty_buffer(bh);
- if (buffer_write_io_error(bh)) {
- printk(KERN_ERR "JBD2: I/O error detected "
- "when updating journal superblock for %s.\n",
- journal->j_devname);
- clear_buffer_write_io_error(bh);
- set_buffer_uptodate(bh);
- }
- } else
- write_dirty_buffer(bh, WRITE);
-
-out:
- /* If we have just flushed the log (by marking s_start==0), then
- * any future commit will have to be careful to update the
- * superblock again to re-record the true start of the log. */
+ jbd2_write_superblock(journal, WRITE_FUA);
+ /* Log is no longer empty */
write_lock(&journal->j_state_lock);
- if (sb->s_start)
- journal->j_flags &= ~JBD2_FLUSHED;
- else
- journal->j_flags |= JBD2_FLUSHED;
+ journal->j_flags |= JBD2_FLUSHED;
write_unlock(&journal->j_state_lock);
}
+
+/**
+ * jbd2_journal_update_sb_errno() - Update error in the journal.
+ * @journal: The journal to update.
+ *
+ * Update a journal's errno. Write updated superblock to disk waiting for IO
+ * to complete.
+ */
+static void jbd2_journal_update_sb_errno(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+
+ read_lock(&journal->j_state_lock);
+ jbd_debug(1, "JBD2: updating superblock error (errno %d)\n",
+ journal->j_errno);
+ sb->s_errno = cpu_to_be32(journal->j_errno);
+ read_unlock(&journal->j_state_lock);
+
+ jbd2_write_superblock(journal, WRITE_SYNC);
+}
+
/*
* Read the superblock for a given journal, performing initial
* validation of the format.
*/
-
static int journal_get_superblock(journal_t *journal)
{
struct buffer_head *bh;
@@ -1396,14 +1551,11 @@ int jbd2_journal_destroy(journal_t *journal)
if (journal->j_sb_buffer) {
if (!is_journal_aborted(journal)) {
- /* We can now mark the journal as empty. */
- journal->j_tail = 0;
- journal->j_tail_sequence =
- ++journal->j_transaction_sequence;
- jbd2_journal_update_superblock(journal, 1);
- } else {
+ mutex_lock(&journal->j_checkpoint_mutex);
+ jbd2_mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ } else
err = -EIO;
- }
brelse(journal->j_sb_buffer);
}
@@ -1550,61 +1702,6 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
EXPORT_SYMBOL(jbd2_journal_clear_features);
/**
- * int jbd2_journal_update_format () - Update on-disk journal structure.
- * @journal: Journal to act on.
- *
- * Given an initialised but unloaded journal struct, poke about in the
- * on-disk structure to update it to the most recent supported version.
- */
-int jbd2_journal_update_format (journal_t *journal)
-{
- journal_superblock_t *sb;
- int err;
-
- err = journal_get_superblock(journal);
- if (err)
- return err;
-
- sb = journal->j_superblock;
-
- switch (be32_to_cpu(sb->s_header.h_blocktype)) {
- case JBD2_SUPERBLOCK_V2:
- return 0;
- case JBD2_SUPERBLOCK_V1:
- return journal_convert_superblock_v1(journal, sb);
- default:
- break;
- }
- return -EINVAL;
-}
-
-static int journal_convert_superblock_v1(journal_t *journal,
- journal_superblock_t *sb)
-{
- int offset, blocksize;
- struct buffer_head *bh;
-
- printk(KERN_WARNING
- "JBD2: Converting superblock from version 1 to 2.\n");
-
- /* Pre-initialise new fields to zero */
- offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
- blocksize = be32_to_cpu(sb->s_blocksize);
- memset(&sb->s_feature_compat, 0, blocksize-offset);
-
- sb->s_nr_users = cpu_to_be32(1);
- sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
- journal->j_format_version = 2;
-
- bh = journal->j_sb_buffer;
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- sync_dirty_buffer(bh);
- return 0;
-}
-
-
-/**
* int jbd2_journal_flush () - Flush journal
* @journal: Journal to act on.
*
@@ -1617,7 +1714,6 @@ int jbd2_journal_flush(journal_t *journal)
{
int err = 0;
transaction_t *transaction = NULL;
- unsigned long old_tail;
write_lock(&journal->j_state_lock);
@@ -1652,6 +1748,7 @@ int jbd2_journal_flush(journal_t *journal)
if (is_journal_aborted(journal))
return -EIO;
+ mutex_lock(&journal->j_checkpoint_mutex);
jbd2_cleanup_journal_tail(journal);
/* Finally, mark the journal as really needing no recovery.
@@ -1659,14 +1756,9 @@ int jbd2_journal_flush(journal_t *journal)
* the magic code for a fully-recovered superblock. Any future
* commits of data to the journal will restore the current
* s_start value. */
+ jbd2_mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
write_lock(&journal->j_state_lock);
- old_tail = journal->j_tail;
- journal->j_tail = 0;
- write_unlock(&journal->j_state_lock);
- jbd2_journal_update_superblock(journal, 1);
- write_lock(&journal->j_state_lock);
- journal->j_tail = old_tail;
-
J_ASSERT(!journal->j_running_transaction);
J_ASSERT(!journal->j_committing_transaction);
J_ASSERT(!journal->j_checkpoint_transactions);
@@ -1706,8 +1798,12 @@ int jbd2_journal_wipe(journal_t *journal, int write)
write ? "Clearing" : "Ignoring");
err = jbd2_journal_skip_recovery(journal);
- if (write)
- jbd2_journal_update_superblock(journal, 1);
+ if (write) {
+ /* Lock to make assertions happy... */
+ mutex_lock(&journal->j_checkpoint_mutex);
+ jbd2_mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ }
no_recovery:
return err;
@@ -1757,7 +1853,7 @@ static void __journal_abort_soft (journal_t *journal, int errno)
__jbd2_journal_abort_hard(journal);
if (errno)
- jbd2_journal_update_superblock(journal, 1);
+ jbd2_journal_update_sb_errno(journal);
}
/**
@@ -2015,7 +2111,7 @@ static struct kmem_cache *jbd2_journal_head_cache;
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
#endif
-static int journal_init_jbd2_journal_head_cache(void)
+static int jbd2_journal_init_journal_head_cache(void)
{
int retval;
@@ -2033,7 +2129,7 @@ static int journal_init_jbd2_journal_head_cache(void)
return retval;
}
-static void jbd2_journal_destroy_jbd2_journal_head_cache(void)
+static void jbd2_journal_destroy_journal_head_cache(void)
{
if (jbd2_journal_head_cache) {
kmem_cache_destroy(jbd2_journal_head_cache);
@@ -2321,7 +2417,7 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void)
struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache;
-static int __init journal_init_handle_cache(void)
+static int __init jbd2_journal_init_handle_cache(void)
{
jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
if (jbd2_handle_cache == NULL) {
@@ -2356,17 +2452,20 @@ static int __init journal_init_caches(void)
ret = jbd2_journal_init_revoke_caches();
if (ret == 0)
- ret = journal_init_jbd2_journal_head_cache();
+ ret = jbd2_journal_init_journal_head_cache();
+ if (ret == 0)
+ ret = jbd2_journal_init_handle_cache();
if (ret == 0)
- ret = journal_init_handle_cache();
+ ret = jbd2_journal_init_transaction_cache();
return ret;
}
static void jbd2_journal_destroy_caches(void)
{
jbd2_journal_destroy_revoke_caches();
- jbd2_journal_destroy_jbd2_journal_head_cache();
+ jbd2_journal_destroy_journal_head_cache();
jbd2_journal_destroy_handle_cache();
+ jbd2_journal_destroy_transaction_cache();
jbd2_journal_destroy_slabs();
}
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index da6d7ba..c1a0335 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -21,6 +21,7 @@
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/crc32.h>
+#include <linux/blkdev.h>
#endif
/*
@@ -265,7 +266,9 @@ int jbd2_journal_recover(journal_t *journal)
err2 = sync_blockdev(journal->j_fs_dev);
if (!err)
err = err2;
-
+ /* Make sure all replayed data is on permanent storage */
+ if (journal->j_flags & JBD2_BARRIER)
+ blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
return err;
}
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 30b2867..6973705 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -208,17 +208,13 @@ int __init jbd2_journal_init_revoke_caches(void)
J_ASSERT(!jbd2_revoke_record_cache);
J_ASSERT(!jbd2_revoke_table_cache);
- jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
- sizeof(struct jbd2_revoke_record_s),
- 0,
- SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
- NULL);
+ jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s,
+ SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY);
if (!jbd2_revoke_record_cache)
goto record_cache_failure;
- jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
- sizeof(struct jbd2_revoke_table_s),
- 0, SLAB_TEMPORARY, NULL);
+ jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s,
+ SLAB_TEMPORARY);
if (!jbd2_revoke_table_cache)
goto table_cache_failure;
return 0;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 35ae096..ddcd354 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -33,6 +33,35 @@
static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
static void __jbd2_journal_unfile_buffer(struct journal_head *jh);
+static struct kmem_cache *transaction_cache;
+int __init jbd2_journal_init_transaction_cache(void)
+{
+ J_ASSERT(!transaction_cache);
+ transaction_cache = kmem_cache_create("jbd2_transaction_s",
+ sizeof(transaction_t),
+ 0,
+ SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
+ NULL);
+ if (transaction_cache)
+ return 0;
+ return -ENOMEM;
+}
+
+void jbd2_journal_destroy_transaction_cache(void)
+{
+ if (transaction_cache) {
+ kmem_cache_destroy(transaction_cache);
+ transaction_cache = NULL;
+ }
+}
+
+void jbd2_journal_free_transaction(transaction_t *transaction)
+{
+ if (unlikely(ZERO_OR_NULL_PTR(transaction)))
+ return;
+ kmem_cache_free(transaction_cache, transaction);
+}
+
/*
* jbd2_get_transaction: obtain a new transaction_t object.
*
@@ -133,7 +162,8 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
alloc_transaction:
if (!journal->j_running_transaction) {
- new_transaction = kzalloc(sizeof(*new_transaction), gfp_mask);
+ new_transaction = kmem_cache_alloc(transaction_cache,
+ gfp_mask | __GFP_ZERO);
if (!new_transaction) {
/*
* If __GFP_FS is not present, then we may be
@@ -162,7 +192,7 @@ repeat:
if (is_journal_aborted(journal) ||
(journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
read_unlock(&journal->j_state_lock);
- kfree(new_transaction);
+ jbd2_journal_free_transaction(new_transaction);
return -EROFS;
}
@@ -284,7 +314,7 @@ repeat:
read_unlock(&journal->j_state_lock);
lock_map_acquire(&handle->h_lockdep_map);
- kfree(new_transaction);
+ jbd2_journal_free_transaction(new_transaction);
return 0;
}
@@ -783,12 +813,12 @@ done:
"Possible IO failure.\n");
page = jh2bh(jh)->b_page;
offset = offset_in_page(jh2bh(jh)->b_data);
- source = kmap_atomic(page, KM_USER0);
+ source = kmap_atomic(page);
/* Fire data frozen trigger just before we copy the data */
jbd2_buffer_frozen_trigger(jh, source + offset,
jh->b_triggers);
memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
- kunmap_atomic(source, KM_USER0);
+ kunmap_atomic(source);
/*
* Now that the frozen data is saved off, we need to store
@@ -1549,9 +1579,9 @@ __blist_del_buffer(struct journal_head **list, struct journal_head *jh)
* of these pointers, it could go bad. Generally the caller needs to re-read
* the pointer from the transaction_t.
*
- * Called under j_list_lock. The journal may not be locked.
+ * Called under j_list_lock.
*/
-void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
+static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
{
struct journal_head **list = NULL;
transaction_t *transaction;
@@ -1646,10 +1676,8 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
spin_lock(&journal->j_list_lock);
if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
/* written-back checkpointed metadata buffer */
- if (jh->b_jlist == BJ_None) {
- JBUFFER_TRACE(jh, "remove from checkpoint list");
- __jbd2_journal_remove_checkpoint(jh);
- }
+ JBUFFER_TRACE(jh, "remove from checkpoint list");
+ __jbd2_journal_remove_checkpoint(jh);
}
spin_unlock(&journal->j_list_lock);
out:
@@ -1949,6 +1977,8 @@ zap_buffer_unlocked:
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
+ clear_buffer_delay(bh);
+ clear_buffer_unwritten(bh);
bh->b_bdev = NULL;
return may_free;
}
diff --git a/fs/jffs2/compr.c b/fs/jffs2/compr.c
index 5b6c9d1..96ed3c9 100644
--- a/fs/jffs2/compr.c
+++ b/fs/jffs2/compr.c
@@ -340,7 +340,7 @@ int jffs2_unregister_compressor(struct jffs2_compressor *comp)
if (comp->usecount) {
spin_unlock(&jffs2_compressor_list_lock);
- printk(KERN_WARNING "JFFS2: Compressor modul is in use. Unregister failed.\n");
+ printk(KERN_WARNING "JFFS2: Compressor module is in use. Unregister failed.\n");
return -1;
}
list_del(&comp->list);
diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c
index a01cdad..eafb8d3 100644
--- a/fs/jffs2/erase.c
+++ b/fs/jffs2/erase.c
@@ -335,7 +335,7 @@ static int jffs2_block_check_erase(struct jffs2_sb_info *c, struct jffs2_erasebl
void *ebuf;
uint32_t ofs;
size_t retlen;
- int ret = -EIO;
+ int ret;
unsigned long *wordebuf;
ret = mtd_point(c->mtd, jeb->offset, c->sector_size, &retlen,
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 2e01238..c0d5c9d 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -561,9 +561,9 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
ret = -ENOMEM;
D1(printk(KERN_DEBUG "jffs2_do_fill_super(): d_alloc_root()\n"));
- sb->s_root = d_alloc_root(root_i);
+ sb->s_root = d_make_root(root_i);
if (!sb->s_root)
- goto out_root_i;
+ goto out_root;
sb->s_maxbytes = 0xFFFFFFFF;
sb->s_blocksize = PAGE_CACHE_SIZE;
@@ -573,8 +573,6 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
jffs2_start_garbage_collect_thread(c);
return 0;
- out_root_i:
- iput(root_i);
out_root:
jffs2_free_ino_caches(c);
jffs2_free_raw_node_refs(c);
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 5f7c160..07c91ca 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -220,12 +220,6 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
dquot_initialize(dip);
- /* link count overflow on parent directory ? */
- if (dip->i_nlink == JFS_LINK_MAX) {
- rc = -EMLINK;
- goto out1;
- }
-
/*
* search parent directory for entry/freespace
* (dtSearch() returns parent directory page pinned)
@@ -806,9 +800,6 @@ static int jfs_link(struct dentry *old_dentry,
jfs_info("jfs_link: %s %s", old_dentry->d_name.name,
dentry->d_name.name);
- if (ip->i_nlink == JFS_LINK_MAX)
- return -EMLINK;
-
dquot_initialize(dir);
tid = txBegin(ip->i_sb, 0);
@@ -1138,10 +1129,6 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
rc = -ENOTEMPTY;
goto out3;
}
- } else if ((new_dir != old_dir) &&
- (new_dir->i_nlink == JFS_LINK_MAX)) {
- rc = -EMLINK;
- goto out3;
}
} else if (new_ip) {
IWRITE_LOCK(new_ip, RDWRLOCK_NORMAL);
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 682bca6..4a82950 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -441,6 +441,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
return -ENOMEM;
sb->s_fs_info = sbi;
+ sb->s_max_links = JFS_LINK_MAX;
sbi->sb = sb;
sbi->uid = sbi->gid = sbi->umask = -1;
@@ -521,7 +522,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
ret = PTR_ERR(inode);
goto out_no_rw;
}
- sb->s_root = d_alloc_root(inode);
+ sb->s_root = d_make_root(inode);
if (!sb->s_root)
goto out_no_root;
@@ -539,7 +540,6 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
out_no_root:
jfs_err("jfs_read_super: get root dentry failed");
- iput(inode);
out_no_rw:
rc = jfs_umount(sb);
@@ -860,8 +860,14 @@ static int __init init_jfs_fs(void)
jfs_proc_init();
#endif
- return register_filesystem(&jfs_fs_type);
+ rc = register_filesystem(&jfs_fs_type);
+ if (!rc)
+ return 0;
+#ifdef PROC_FS_JFS
+ jfs_proc_clean();
+#endif
+ kthread_stop(jfsSyncThread);
kill_committask:
for (i = 0; i < commit_threads; i++)
kthread_stop(jfsCommitThread[i]);
diff --git a/fs/libfs.c b/fs/libfs.c
index 5b2dbb3..4a0d1f0 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -3,7 +3,7 @@
* Library for filesystems writers.
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/mount.h>
@@ -491,11 +491,9 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
set_nlink(inode, 2);
- root = d_alloc_root(inode);
- if (!root) {
- iput(inode);
+ root = d_make_root(inode);
+ if (!root)
return -ENOMEM;
- }
for (i = 0; !files->name || files->name[0]; i++, files++) {
if (!files->name)
continue;
@@ -536,7 +534,7 @@ int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *c
spin_lock(&pin_fs_lock);
if (unlikely(!*mount)) {
spin_unlock(&pin_fs_lock);
- mnt = vfs_kern_mount(type, 0, type->name, NULL);
+ mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, NULL);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
spin_lock(&pin_fs_lock);
diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index f848b52..3ddcbb1 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -598,7 +598,7 @@ static struct rpc_procinfo nlm4_procedures[] = {
PROC(GRANTED_RES, res, norep),
};
-struct rpc_version nlm_version4 = {
+const struct rpc_version nlm_version4 = {
.number = 4,
.nrprocs = ARRAY_SIZE(nlm4_procedures),
.procs = nlm4_procedures,
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 8d4ea83..ba1dc2e 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -62,7 +62,8 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
host = nlmclnt_lookup_host(nlm_init->address, nlm_init->addrlen,
nlm_init->protocol, nlm_version,
- nlm_init->hostname, nlm_init->noresvport);
+ nlm_init->hostname, nlm_init->noresvport,
+ nlm_init->net);
if (host == NULL) {
lockd_down();
return ERR_PTR(-ENOLCK);
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 180ac34..3d35e3e 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -596,19 +596,19 @@ static struct rpc_procinfo nlm_procedures[] = {
PROC(GRANTED_RES, res, norep),
};
-static struct rpc_version nlm_version1 = {
+static const struct rpc_version nlm_version1 = {
.number = 1,
.nrprocs = ARRAY_SIZE(nlm_procedures),
.procs = nlm_procedures,
};
-static struct rpc_version nlm_version3 = {
+static const struct rpc_version nlm_version3 = {
.number = 3,
.nrprocs = ARRAY_SIZE(nlm_procedures),
.procs = nlm_procedures,
};
-static struct rpc_version *nlm_versions[] = {
+static const struct rpc_version *nlm_versions[] = {
[1] = &nlm_version1,
[3] = &nlm_version3,
#ifdef CONFIG_LOCKD_V4
@@ -618,7 +618,7 @@ static struct rpc_version *nlm_versions[] = {
static struct rpc_stat nlm_rpc_stats;
-struct rpc_program nlm_program = {
+const struct rpc_program nlm_program = {
.name = "lockd",
.number = NLM_PROGRAM,
.nrvers = ARRAY_SIZE(nlm_versions),
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 6f29836..eb75ca7 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -17,6 +17,8 @@
#include <linux/lockd/lockd.h>
#include <linux/mutex.h>
+#include <linux/sunrpc/svc_xprt.h>
+
#include <net/ipv6.h>
#define NLMDBG_FACILITY NLMDBG_HOSTCACHE
@@ -54,6 +56,7 @@ struct nlm_lookup_host_info {
const char *hostname; /* remote's hostname */
const size_t hostname_len; /* it's length */
const int noresvport; /* use non-priv port */
+ struct net *net; /* network namespace to bind */
};
/*
@@ -155,6 +158,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
INIT_LIST_HEAD(&host->h_reclaim);
host->h_nsmhandle = nsm;
host->h_addrbuf = nsm->sm_addrbuf;
+ host->net = ni->net;
out:
return host;
@@ -206,7 +210,8 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
const unsigned short protocol,
const u32 version,
const char *hostname,
- int noresvport)
+ int noresvport,
+ struct net *net)
{
struct nlm_lookup_host_info ni = {
.server = 0,
@@ -217,6 +222,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
.hostname = hostname,
.hostname_len = strlen(hostname),
.noresvport = noresvport,
+ .net = net,
};
struct hlist_head *chain;
struct hlist_node *pos;
@@ -231,6 +237,8 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
chain = &nlm_client_hosts[nlm_hash_address(sap)];
hlist_for_each_entry(host, pos, chain, h_hash) {
+ if (host->net != net)
+ continue;
if (!rpc_cmp_addr(nlm_addr(host), sap))
continue;
@@ -318,6 +326,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
struct nsm_handle *nsm = NULL;
struct sockaddr *src_sap = svc_daddr(rqstp);
size_t src_len = rqstp->rq_daddrlen;
+ struct net *net = rqstp->rq_xprt->xpt_net;
struct nlm_lookup_host_info ni = {
.server = 1,
.sap = svc_addr(rqstp),
@@ -326,6 +335,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
.version = rqstp->rq_vers,
.hostname = hostname,
.hostname_len = hostname_len,
+ .net = net,
};
dprintk("lockd: %s(host='%*s', vers=%u, proto=%s)\n", __func__,
@@ -339,6 +349,8 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
chain = &nlm_server_hosts[nlm_hash_address(ni.sap)];
hlist_for_each_entry(host, pos, chain, h_hash) {
+ if (host->net != net)
+ continue;
if (!rpc_cmp_addr(nlm_addr(host), ni.sap))
continue;
@@ -431,7 +443,7 @@ nlm_bind_host(struct nlm_host *host)
.to_retries = 5U,
};
struct rpc_create_args args = {
- .net = &init_net,
+ .net = host->net,
.protocol = host->h_proto,
.address = nlm_addr(host),
.addrsize = host->h_addrlen,
@@ -553,12 +565,8 @@ void nlm_host_rebooted(const struct nlm_reboot *info)
nsm_release(nsm);
}
-/*
- * Shut down the hosts module.
- * Note that this routine is called only at server shutdown time.
- */
void
-nlm_shutdown_hosts(void)
+nlm_shutdown_hosts_net(struct net *net)
{
struct hlist_head *chain;
struct hlist_node *pos;
@@ -570,6 +578,8 @@ nlm_shutdown_hosts(void)
/* First, make all hosts eligible for gc */
dprintk("lockd: nuking all hosts...\n");
for_each_host(host, pos, chain, nlm_server_hosts) {
+ if (net && host->net != net)
+ continue;
host->h_expires = jiffies - 1;
if (host->h_rpcclnt) {
rpc_shutdown_client(host->h_rpcclnt);
@@ -580,15 +590,29 @@ nlm_shutdown_hosts(void)
/* Then, perform a garbage collection pass */
nlm_gc_hosts();
mutex_unlock(&nlm_host_mutex);
+}
+
+/*
+ * Shut down the hosts module.
+ * Note that this routine is called only at server shutdown time.
+ */
+void
+nlm_shutdown_hosts(void)
+{
+ struct hlist_head *chain;
+ struct hlist_node *pos;
+ struct nlm_host *host;
+
+ nlm_shutdown_hosts_net(NULL);
/* complain if any hosts are left */
if (nrhosts != 0) {
printk(KERN_WARNING "lockd: couldn't shutdown host module!\n");
dprintk("lockd: %lu hosts left:\n", nrhosts);
for_each_host(host, pos, chain, nlm_server_hosts) {
- dprintk(" %s (cnt %d use %d exp %ld)\n",
+ dprintk(" %s (cnt %d use %d exp %ld net %p)\n",
host->h_name, atomic_read(&host->h_count),
- host->h_inuse, host->h_expires);
+ host->h_inuse, host->h_expires, host->net);
}
}
}
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 65ba36b..7ef14b3 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -47,7 +47,7 @@ struct nsm_res {
u32 state;
};
-static struct rpc_program nsm_program;
+static const struct rpc_program nsm_program;
static LIST_HEAD(nsm_handles);
static DEFINE_SPINLOCK(nsm_lock);
@@ -62,14 +62,14 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
return (struct sockaddr *)&nsm->sm_addr;
}
-static struct rpc_clnt *nsm_create(void)
+static struct rpc_clnt *nsm_create(struct net *net)
{
struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
};
struct rpc_create_args args = {
- .net = &init_net,
+ .net = net,
.protocol = XPRT_TRANSPORT_UDP,
.address = (struct sockaddr *)&sin,
.addrsize = sizeof(sin),
@@ -83,7 +83,8 @@ static struct rpc_clnt *nsm_create(void)
return rpc_create(&args);
}
-static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
+static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
+ struct net *net)
{
struct rpc_clnt *clnt;
int status;
@@ -99,7 +100,7 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
.rpc_resp = res,
};
- clnt = nsm_create();
+ clnt = nsm_create(net);
if (IS_ERR(clnt)) {
status = PTR_ERR(clnt);
dprintk("lockd: failed to create NSM upcall transport, "
@@ -149,7 +150,7 @@ int nsm_monitor(const struct nlm_host *host)
*/
nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
- status = nsm_mon_unmon(nsm, NSMPROC_MON, &res);
+ status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host->net);
if (unlikely(res.status != 0))
status = -EIO;
if (unlikely(status < 0)) {
@@ -183,7 +184,7 @@ void nsm_unmonitor(const struct nlm_host *host)
&& nsm->sm_monitored && !nsm->sm_sticky) {
dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
- status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res);
+ status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host->net);
if (res.status != 0)
status = -EIO;
if (status < 0)
@@ -534,19 +535,19 @@ static struct rpc_procinfo nsm_procedures[] = {
},
};
-static struct rpc_version nsm_version1 = {
+static const struct rpc_version nsm_version1 = {
.number = 1,
.nrprocs = ARRAY_SIZE(nsm_procedures),
.procs = nsm_procedures
};
-static struct rpc_version * nsm_version[] = {
+static const struct rpc_version *nsm_version[] = {
[1] = &nsm_version1,
};
static struct rpc_stat nsm_stats;
-static struct rpc_program nsm_program = {
+static const struct rpc_program nsm_program = {
.name = "statd",
.number = NSM_PROGRAM,
.nrvers = ARRAY_SIZE(nsm_version),
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
new file mode 100644
index 0000000..ce227e0
--- /dev/null
+++ b/fs/lockd/netns.h
@@ -0,0 +1,12 @@
+#ifndef __LOCKD_NETNS_H__
+#define __LOCKD_NETNS_H__
+
+#include <net/netns/generic.h>
+
+struct lockd_net {
+ unsigned int nlmsvc_users;
+};
+
+extern int lockd_net_id;
+
+#endif
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index c061b9a..2774e10 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -35,6 +35,8 @@
#include <linux/lockd/lockd.h>
#include <linux/nfs.h>
+#include "netns.h"
+
#define NLMDBG_FACILITY NLMDBG_SVC
#define LOCKD_BUFSIZE (1024 + NLMSVC_XDRSIZE)
#define ALLOWED_SIGS (sigmask(SIGKILL))
@@ -50,6 +52,8 @@ static struct task_struct *nlmsvc_task;
static struct svc_rqst *nlmsvc_rqst;
unsigned long nlmsvc_timeout;
+int lockd_net_id;
+
/*
* These can be set at insmod time (useful for NFS as root filesystem),
* and also changed through the sysctl interface. -- Jamie Lokier, Aug 2003
@@ -189,27 +193,29 @@ lockd(void *vrqstp)
}
static int create_lockd_listener(struct svc_serv *serv, const char *name,
- const int family, const unsigned short port)
+ struct net *net, const int family,
+ const unsigned short port)
{
struct svc_xprt *xprt;
- xprt = svc_find_xprt(serv, name, family, 0);
+ xprt = svc_find_xprt(serv, name, net, family, 0);
if (xprt == NULL)
- return svc_create_xprt(serv, name, &init_net, family, port,
+ return svc_create_xprt(serv, name, net, family, port,
SVC_SOCK_DEFAULTS);
svc_xprt_put(xprt);
return 0;
}
-static int create_lockd_family(struct svc_serv *serv, const int family)
+static int create_lockd_family(struct svc_serv *serv, struct net *net,
+ const int family)
{
int err;
- err = create_lockd_listener(serv, "udp", family, nlm_udpport);
+ err = create_lockd_listener(serv, "udp", net, family, nlm_udpport);
if (err < 0)
return err;
- return create_lockd_listener(serv, "tcp", family, nlm_tcpport);
+ return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport);
}
/*
@@ -222,16 +228,16 @@ static int create_lockd_family(struct svc_serv *serv, const int family)
* Returns zero if all listeners are available; otherwise a
* negative errno value is returned.
*/
-static int make_socks(struct svc_serv *serv)
+static int make_socks(struct svc_serv *serv, struct net *net)
{
static int warned;
int err;
- err = create_lockd_family(serv, PF_INET);
+ err = create_lockd_family(serv, net, PF_INET);
if (err < 0)
goto out_err;
- err = create_lockd_family(serv, PF_INET6);
+ err = create_lockd_family(serv, net, PF_INET6);
if (err < 0 && err != -EAFNOSUPPORT)
goto out_err;
@@ -245,6 +251,47 @@ out_err:
return err;
}
+static int lockd_up_net(struct net *net)
+{
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
+ struct svc_serv *serv = nlmsvc_rqst->rq_server;
+ int error;
+
+ if (ln->nlmsvc_users)
+ return 0;
+
+ error = svc_rpcb_setup(serv, net);
+ if (error)
+ goto err_rpcb;
+
+ error = make_socks(serv, net);
+ if (error < 0)
+ goto err_socks;
+ return 0;
+
+err_socks:
+ svc_rpcb_cleanup(serv, net);
+err_rpcb:
+ return error;
+}
+
+static void lockd_down_net(struct net *net)
+{
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
+ struct svc_serv *serv = nlmsvc_rqst->rq_server;
+
+ if (ln->nlmsvc_users) {
+ if (--ln->nlmsvc_users == 0) {
+ nlm_shutdown_hosts_net(net);
+ svc_shutdown_net(serv, net);
+ }
+ } else {
+ printk(KERN_ERR "lockd_down_net: no users! task=%p, net=%p\n",
+ nlmsvc_task, net);
+ BUG();
+ }
+}
+
/*
* Bring up the lockd process if it's not already up.
*/
@@ -252,13 +299,16 @@ int lockd_up(void)
{
struct svc_serv *serv;
int error = 0;
+ struct net *net = current->nsproxy->net_ns;
mutex_lock(&nlmsvc_mutex);
/*
* Check whether we're already up and running.
*/
- if (nlmsvc_rqst)
+ if (nlmsvc_rqst) {
+ error = lockd_up_net(net);
goto out;
+ }
/*
* Sanity check: if there's no pid,
@@ -275,7 +325,7 @@ int lockd_up(void)
goto out;
}
- error = make_socks(serv);
+ error = make_socks(serv, net);
if (error < 0)
goto destroy_and_out;
@@ -313,8 +363,12 @@ int lockd_up(void)
destroy_and_out:
svc_destroy(serv);
out:
- if (!error)
+ if (!error) {
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+ ln->nlmsvc_users++;
nlmsvc_users++;
+ }
mutex_unlock(&nlmsvc_mutex);
return error;
}
@@ -328,8 +382,10 @@ lockd_down(void)
{
mutex_lock(&nlmsvc_mutex);
if (nlmsvc_users) {
- if (--nlmsvc_users)
+ if (--nlmsvc_users) {
+ lockd_down_net(current->nsproxy->net_ns);
goto out;
+ }
} else {
printk(KERN_ERR "lockd_down: no users! task=%p\n",
nlmsvc_task);
@@ -497,24 +553,55 @@ module_param_call(nlm_tcpport, param_set_port, param_get_int,
module_param(nsm_use_hostnames, bool, 0644);
module_param(nlm_max_connections, uint, 0644);
+static int lockd_init_net(struct net *net)
+{
+ return 0;
+}
+
+static void lockd_exit_net(struct net *net)
+{
+}
+
+static struct pernet_operations lockd_net_ops = {
+ .init = lockd_init_net,
+ .exit = lockd_exit_net,
+ .id = &lockd_net_id,
+ .size = sizeof(struct lockd_net),
+};
+
+
/*
* Initialising and terminating the module.
*/
static int __init init_nlm(void)
{
+ int err;
+
#ifdef CONFIG_SYSCTL
+ err = -ENOMEM;
nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root);
- return nlm_sysctl_table ? 0 : -ENOMEM;
-#else
+ if (nlm_sysctl_table == NULL)
+ goto err_sysctl;
+#endif
+ err = register_pernet_subsys(&lockd_net_ops);
+ if (err)
+ goto err_pernet;
return 0;
+
+err_pernet:
+#ifdef CONFIG_SYSCTL
+ unregister_sysctl_table(nlm_sysctl_table);
#endif
+err_sysctl:
+ return err;
}
static void __exit exit_nlm(void)
{
/* FIXME: delete all NLM clients */
nlm_shutdown_hosts();
+ unregister_pernet_subsys(&lockd_net_ops);
#ifdef CONFIG_SYSCTL
unregister_sysctl_table(nlm_sysctl_table);
#endif
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index f0179c3..e46353f 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -46,7 +46,6 @@ static void nlmsvc_remove_block(struct nlm_block *block);
static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock);
static void nlmsvc_freegrantargs(struct nlm_rqst *call);
static const struct rpc_call_ops nlmsvc_grant_ops;
-static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie);
/*
* The list of blocked locks to retry
@@ -54,6 +53,35 @@ static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie);
static LIST_HEAD(nlm_blocked);
static DEFINE_SPINLOCK(nlm_blocked_lock);
+#ifdef LOCKD_DEBUG
+static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
+{
+ /*
+ * We can get away with a static buffer because we're only
+ * called with BKL held.
+ */
+ static char buf[2*NLM_MAXCOOKIELEN+1];
+ unsigned int i, len = sizeof(buf);
+ char *p = buf;
+
+ len--; /* allow for trailing \0 */
+ if (len < 3)
+ return "???";
+ for (i = 0 ; i < cookie->len ; i++) {
+ if (len < 2) {
+ strcpy(p-3, "...");
+ break;
+ }
+ sprintf(p, "%02x", cookie->data[i]);
+ p += 2;
+ len -= 2;
+ }
+ *p = '\0';
+
+ return buf;
+}
+#endif
+
/*
* Insert a blocked lock into the global list
*/
@@ -935,32 +963,3 @@ nlmsvc_retry_blocked(void)
return timeout;
}
-
-#ifdef RPC_DEBUG
-static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
-{
- /*
- * We can get away with a static buffer because we're only
- * called with BKL held.
- */
- static char buf[2*NLM_MAXCOOKIELEN+1];
- unsigned int i, len = sizeof(buf);
- char *p = buf;
-
- len--; /* allow for trailing \0 */
- if (len < 3)
- return "???";
- for (i = 0 ; i < cookie->len ; i++) {
- if (len < 2) {
- strcpy(p-3, "...");
- break;
- }
- sprintf(p, "%02x", cookie->data[i]);
- p += 2;
- len -= 2;
- }
- *p = '\0';
-
- return buf;
-}
-#endif
diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c
index e97404d..9c50144 100644
--- a/fs/logfs/dev_mtd.c
+++ b/fs/logfs/dev_mtd.c
@@ -152,9 +152,6 @@ static struct page *logfs_mtd_find_first_sb(struct super_block *sb, u64 *ofs)
filler_t *filler = logfs_mtd_readpage;
struct mtd_info *mtd = super->s_mtd;
- if (!mtd_can_have_bb(mtd))
- return NULL;
-
*ofs = 0;
while (mtd_block_isbad(mtd, *ofs)) {
*ofs += mtd->erasesize;
@@ -172,9 +169,6 @@ static struct page *logfs_mtd_find_last_sb(struct super_block *sb, u64 *ofs)
filler_t *filler = logfs_mtd_readpage;
struct mtd_info *mtd = super->s_mtd;
- if (!mtd_can_have_bb(mtd))
- return NULL;
-
*ofs = mtd->size - mtd->erasesize;
while (mtd_block_isbad(mtd, *ofs)) {
*ofs -= mtd->erasesize;
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 501043e..bea5d1b 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -71,7 +71,7 @@ static int write_dir(struct inode *dir, struct logfs_disk_dentry *dd,
static int write_inode(struct inode *inode)
{
- return __logfs_write_inode(inode, WF_LOCK);
+ return __logfs_write_inode(inode, NULL, WF_LOCK);
}
static s64 dir_seek_data(struct inode *inode, s64 pos)
@@ -177,17 +177,17 @@ static struct page *logfs_get_dd_page(struct inode *dir, struct dentry *dentry)
(filler_t *)logfs_readpage, NULL);
if (IS_ERR(page))
return page;
- dd = kmap_atomic(page, KM_USER0);
+ dd = kmap_atomic(page);
BUG_ON(dd->namelen == 0);
if (name->len != be16_to_cpu(dd->namelen) ||
memcmp(name->name, dd->name, name->len)) {
- kunmap_atomic(dd, KM_USER0);
+ kunmap_atomic(dd);
page_cache_release(page);
continue;
}
- kunmap_atomic(dd, KM_USER0);
+ kunmap_atomic(dd);
return page;
}
return NULL;
@@ -365,9 +365,9 @@ static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry,
return NULL;
}
index = page->index;
- dd = kmap_atomic(page, KM_USER0);
+ dd = kmap_atomic(page);
ino = be64_to_cpu(dd->ino);
- kunmap_atomic(dd, KM_USER0);
+ kunmap_atomic(dd);
page_cache_release(page);
inode = logfs_iget(dir->i_sb, ino);
@@ -402,12 +402,12 @@ static int logfs_write_dir(struct inode *dir, struct dentry *dentry,
if (!page)
return -ENOMEM;
- dd = kmap_atomic(page, KM_USER0);
+ dd = kmap_atomic(page);
memset(dd, 0, sizeof(*dd));
dd->ino = cpu_to_be64(inode->i_ino);
dd->type = logfs_type(inode);
logfs_set_name(dd, &dentry->d_name);
- kunmap_atomic(dd, KM_USER0);
+ kunmap_atomic(dd);
err = logfs_write_buf(dir, page, WF_LOCK);
unlock_page(page);
@@ -558,9 +558,6 @@ static int logfs_link(struct dentry *old_dentry, struct inode *dir,
{
struct inode *inode = old_dentry->d_inode;
- if (inode->i_nlink >= LOGFS_LINK_MAX)
- return -EMLINK;
-
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
ihold(inode);
inc_nlink(inode);
@@ -579,9 +576,9 @@ static int logfs_get_dd(struct inode *dir, struct dentry *dentry,
if (IS_ERR(page))
return PTR_ERR(page);
*pos = page->index;
- map = kmap_atomic(page, KM_USER0);
+ map = kmap_atomic(page);
memcpy(dd, map, sizeof(*dd));
- kunmap_atomic(map, KM_USER0);
+ kunmap_atomic(map);
page_cache_release(page);
return 0;
}
diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index b548c87..3886cde 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -230,7 +230,9 @@ int logfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
return ret;
mutex_lock(&inode->i_mutex);
+ logfs_get_wblocks(sb, NULL, WF_LOCK);
logfs_write_anchor(sb);
+ logfs_put_wblocks(sb, NULL, WF_LOCK);
mutex_unlock(&inode->i_mutex);
return 0;
diff --git a/fs/logfs/gc.c b/fs/logfs/gc.c
index caa4419..d4efb06 100644
--- a/fs/logfs/gc.c
+++ b/fs/logfs/gc.c
@@ -367,7 +367,7 @@ static struct gc_candidate *get_candidate(struct super_block *sb)
int i, max_dist;
struct gc_candidate *cand = NULL, *this;
- max_dist = min(no_free_segments(sb), LOGFS_NO_AREAS);
+ max_dist = min(no_free_segments(sb), LOGFS_NO_AREAS - 1);
for (i = max_dist; i >= 0; i--) {
this = first_in_list(&super->s_low_list[i]);
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index 388df1a..a422f42 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -286,7 +286,7 @@ static int logfs_write_inode(struct inode *inode, struct writeback_control *wbc)
if (logfs_inode(inode)->li_flags & LOGFS_IF_STILLBORN)
return 0;
- ret = __logfs_write_inode(inode, flags);
+ ret = __logfs_write_inode(inode, NULL, flags);
LOGFS_BUG_ON(ret, inode->i_sb);
return ret;
}
@@ -363,7 +363,9 @@ static void logfs_init_once(void *_li)
static int logfs_sync_fs(struct super_block *sb, int wait)
{
+ logfs_get_wblocks(sb, NULL, WF_LOCK);
logfs_write_anchor(sb);
+ logfs_put_wblocks(sb, NULL, WF_LOCK);
return 0;
}
diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 9da2970..1e1c369 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -612,7 +612,6 @@ static size_t __logfs_write_je(struct super_block *sb, void *buf, u16 type,
if (len == 0)
return logfs_write_header(super, header, 0, type);
- BUG_ON(len > sb->s_blocksize);
compr_len = logfs_compress(buf, data, len, sb->s_blocksize);
if (compr_len < 0 || type == JE_ANCHOR) {
memcpy(data, buf, len);
diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 9263738..5f09376 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -528,7 +528,7 @@ void logfs_destroy_inode_cache(void);
void logfs_set_blocks(struct inode *inode, u64 no);
/* these logically belong into inode.c but actually reside in readwrite.c */
int logfs_read_inode(struct inode *inode);
-int __logfs_write_inode(struct inode *inode, long flags);
+int __logfs_write_inode(struct inode *inode, struct page *, long flags);
void logfs_evict_inode(struct inode *inode);
/* journal.c */
@@ -577,6 +577,8 @@ void initialize_block_counters(struct page *page, struct logfs_block *block,
__be64 *array, int page_is_empty);
int logfs_exist_block(struct inode *inode, u64 bix);
int get_page_reserve(struct inode *inode, struct page *page);
+void logfs_get_wblocks(struct super_block *sb, struct page *page, int lock);
+void logfs_put_wblocks(struct super_block *sb, struct page *page, int lock);
extern struct logfs_block_ops indirect_block_ops;
/* segment.c */
@@ -594,6 +596,7 @@ int logfs_init_mapping(struct super_block *sb);
void logfs_sync_area(struct logfs_area *area);
void logfs_sync_segments(struct super_block *sb);
void freeseg(struct super_block *sb, u32 segno);
+void free_areas(struct super_block *sb);
/* area handling */
int logfs_init_areas(struct super_block *sb);
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 2ac4217..e3ab5e5 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -244,8 +244,7 @@ static void preunlock_page(struct super_block *sb, struct page *page, int lock)
* is waiting for s_write_mutex. We annotate this fact by setting PG_pre_locked
* in addition to PG_locked.
*/
-static void logfs_get_wblocks(struct super_block *sb, struct page *page,
- int lock)
+void logfs_get_wblocks(struct super_block *sb, struct page *page, int lock)
{
struct logfs_super *super = logfs_super(sb);
@@ -260,8 +259,7 @@ static void logfs_get_wblocks(struct super_block *sb, struct page *page,
}
}
-static void logfs_put_wblocks(struct super_block *sb, struct page *page,
- int lock)
+void logfs_put_wblocks(struct super_block *sb, struct page *page, int lock)
{
struct logfs_super *super = logfs_super(sb);
@@ -424,7 +422,7 @@ static void inode_write_block(struct logfs_block *block)
if (inode->i_ino == LOGFS_INO_MASTER)
logfs_write_anchor(inode->i_sb);
else {
- ret = __logfs_write_inode(inode, 0);
+ ret = __logfs_write_inode(inode, NULL, 0);
/* see indirect_write_block comment */
BUG_ON(ret);
}
@@ -519,9 +517,9 @@ static int indirect_write_alias(struct super_block *sb,
ino = page->mapping->host->i_ino;
logfs_unpack_index(page->index, &bix, &level);
- child = kmap_atomic(page, KM_USER0);
+ child = kmap_atomic(page);
val = child[pos];
- kunmap_atomic(child, KM_USER0);
+ kunmap_atomic(child);
err = write_one_alias(sb, ino, bix, level, pos, val);
if (err)
return err;
@@ -560,8 +558,13 @@ static void inode_free_block(struct super_block *sb, struct logfs_block *block)
static void indirect_free_block(struct super_block *sb,
struct logfs_block *block)
{
- ClearPagePrivate(block->page);
- block->page->private = 0;
+ struct page *page = block->page;
+
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ page_cache_release(page);
+ set_page_private(page, 0);
+ }
__free_block(sb, block);
}
@@ -650,8 +653,11 @@ static void alloc_data_block(struct inode *inode, struct page *page)
logfs_unpack_index(page->index, &bix, &level);
block = __alloc_block(inode->i_sb, inode->i_ino, bix, level);
block->page = page;
+
SetPagePrivate(page);
- page->private = (unsigned long)block;
+ page_cache_get(page);
+ set_page_private(page, (unsigned long) block);
+
block->ops = &indirect_block_ops;
}
@@ -667,9 +673,9 @@ static void alloc_indirect_block(struct inode *inode, struct page *page,
alloc_data_block(inode, page);
block = logfs_block(page);
- array = kmap_atomic(page, KM_USER0);
+ array = kmap_atomic(page);
initialize_block_counters(page, block, array, page_is_empty);
- kunmap_atomic(array, KM_USER0);
+ kunmap_atomic(array);
}
static void block_set_pointer(struct page *page, int index, u64 ptr)
@@ -679,10 +685,10 @@ static void block_set_pointer(struct page *page, int index, u64 ptr)
u64 oldptr;
BUG_ON(!block);
- array = kmap_atomic(page, KM_USER0);
+ array = kmap_atomic(page);
oldptr = be64_to_cpu(array[index]);
array[index] = cpu_to_be64(ptr);
- kunmap_atomic(array, KM_USER0);
+ kunmap_atomic(array);
SetPageUptodate(page);
block->full += !!(ptr & LOGFS_FULLY_POPULATED)
@@ -695,9 +701,9 @@ static u64 block_get_pointer(struct page *page, int index)
__be64 *block;
u64 ptr;
- block = kmap_atomic(page, KM_USER0);
+ block = kmap_atomic(page);
ptr = be64_to_cpu(block[index]);
- kunmap_atomic(block, KM_USER0);
+ kunmap_atomic(block);
return ptr;
}
@@ -844,7 +850,7 @@ static u64 seek_holedata_loop(struct inode *inode, u64 bix, int data)
}
slot = get_bits(bix, SUBLEVEL(level));
- rblock = kmap_atomic(page, KM_USER0);
+ rblock = kmap_atomic(page);
while (slot < LOGFS_BLOCK_FACTOR) {
if (data && (rblock[slot] != 0))
break;
@@ -855,12 +861,12 @@ static u64 seek_holedata_loop(struct inode *inode, u64 bix, int data)
bix &= ~(increment - 1);
}
if (slot >= LOGFS_BLOCK_FACTOR) {
- kunmap_atomic(rblock, KM_USER0);
+ kunmap_atomic(rblock);
logfs_put_read_page(page);
return bix;
}
bofs = be64_to_cpu(rblock[slot]);
- kunmap_atomic(rblock, KM_USER0);
+ kunmap_atomic(rblock);
logfs_put_read_page(page);
if (!bofs) {
BUG_ON(data);
@@ -1570,11 +1576,15 @@ int logfs_write_buf(struct inode *inode, struct page *page, long flags)
static int __logfs_delete(struct inode *inode, struct page *page)
{
long flags = WF_DELETE;
+ int err;
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
if (page->index < I0_BLOCKS)
return logfs_write_direct(inode, page, flags);
+ err = grow_inode(inode, page->index, 0);
+ if (err)
+ return err;
return logfs_write_rec(inode, page, page->index, 0, flags);
}
@@ -1623,7 +1633,7 @@ int logfs_rewrite_block(struct inode *inode, u64 bix, u64 ofs,
if (inode->i_ino == LOGFS_INO_MASTER)
logfs_write_anchor(inode->i_sb);
else {
- err = __logfs_write_inode(inode, flags);
+ err = __logfs_write_inode(inode, page, flags);
}
}
}
@@ -1873,7 +1883,7 @@ int logfs_truncate(struct inode *inode, u64 target)
logfs_get_wblocks(sb, NULL, 1);
err = __logfs_truncate(inode, size);
if (!err)
- err = __logfs_write_inode(inode, 0);
+ err = __logfs_write_inode(inode, NULL, 0);
logfs_put_wblocks(sb, NULL, 1);
}
@@ -1901,8 +1911,11 @@ static void move_page_to_inode(struct inode *inode, struct page *page)
li->li_block = block;
block->page = NULL;
- page->private = 0;
- ClearPagePrivate(page);
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ page_cache_release(page);
+ set_page_private(page, 0);
+ }
}
static void move_inode_to_page(struct page *page, struct inode *inode)
@@ -1918,8 +1931,12 @@ static void move_inode_to_page(struct page *page, struct inode *inode)
BUG_ON(PagePrivate(page));
block->ops = &indirect_block_ops;
block->page = page;
- page->private = (unsigned long)block;
- SetPagePrivate(page);
+
+ if (!PagePrivate(page)) {
+ SetPagePrivate(page);
+ page_cache_get(page);
+ set_page_private(page, (unsigned long) block);
+ }
block->inode = NULL;
li->li_block = NULL;
@@ -1944,9 +1961,9 @@ int logfs_read_inode(struct inode *inode)
if (IS_ERR(page))
return PTR_ERR(page);
- di = kmap_atomic(page, KM_USER0);
+ di = kmap_atomic(page);
logfs_disk_to_inode(di, inode);
- kunmap_atomic(di, KM_USER0);
+ kunmap_atomic(di);
move_page_to_inode(inode, page);
page_cache_release(page);
return 0;
@@ -1965,9 +1982,9 @@ static struct page *inode_to_page(struct inode *inode)
if (!page)
return NULL;
- di = kmap_atomic(page, KM_USER0);
+ di = kmap_atomic(page);
logfs_inode_to_disk(inode, di);
- kunmap_atomic(di, KM_USER0);
+ kunmap_atomic(di);
move_inode_to_page(page, inode);
return page;
}
@@ -2024,13 +2041,13 @@ static void logfs_mod_segment_entry(struct super_block *sb, u32 segno,
if (write)
alloc_indirect_block(inode, page, 0);
- se = kmap_atomic(page, KM_USER0);
+ se = kmap_atomic(page);
change_se(se + child_no, arg);
if (write) {
logfs_set_alias(sb, logfs_block(page), child_no);
BUG_ON((int)be32_to_cpu(se[child_no].valid) > super->s_segsize);
}
- kunmap_atomic(se, KM_USER0);
+ kunmap_atomic(se);
logfs_put_write_page(page);
}
@@ -2106,14 +2123,14 @@ void logfs_set_segment_unreserved(struct super_block *sb, u32 segno, u32 ec)
ec_level);
}
-int __logfs_write_inode(struct inode *inode, long flags)
+int __logfs_write_inode(struct inode *inode, struct page *page, long flags)
{
struct super_block *sb = inode->i_sb;
int ret;
- logfs_get_wblocks(sb, NULL, flags & WF_LOCK);
+ logfs_get_wblocks(sb, page, flags & WF_LOCK);
ret = do_write_inode(inode);
- logfs_put_wblocks(sb, NULL, flags & WF_LOCK);
+ logfs_put_wblocks(sb, page, flags & WF_LOCK);
return ret;
}
@@ -2228,10 +2245,10 @@ int logfs_inode_write(struct inode *inode, const void *buf, size_t count,
if (!page)
return -ENOMEM;
- pagebuf = kmap_atomic(page, KM_USER0);
+ pagebuf = kmap_atomic(page);
memcpy(pagebuf, buf, count);
flush_dcache_page(page);
- kunmap_atomic(pagebuf, KM_USER0);
+ kunmap_atomic(pagebuf);
if (i_size_read(inode) < pos + LOGFS_BLOCKSIZE)
i_size_write(inode, pos + LOGFS_BLOCKSIZE);
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 9d51873..e28d090 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -86,7 +86,11 @@ int __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
BUG_ON(!page); /* FIXME: reserve a pool */
SetPageUptodate(page);
memcpy(page_address(page) + offset, buf, copylen);
- SetPagePrivate(page);
+
+ if (!PagePrivate(page)) {
+ SetPagePrivate(page);
+ page_cache_get(page);
+ }
page_cache_release(page);
buf += copylen;
@@ -110,7 +114,10 @@ static void pad_partial_page(struct logfs_area *area)
page = get_mapping_page(sb, index, 0);
BUG_ON(!page); /* FIXME: reserve a pool */
memset(page_address(page) + offset, 0xff, len);
- SetPagePrivate(page);
+ if (!PagePrivate(page)) {
+ SetPagePrivate(page);
+ page_cache_get(page);
+ }
page_cache_release(page);
}
}
@@ -130,7 +137,10 @@ static void pad_full_pages(struct logfs_area *area)
BUG_ON(!page); /* FIXME: reserve a pool */
SetPageUptodate(page);
memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
- SetPagePrivate(page);
+ if (!PagePrivate(page)) {
+ SetPagePrivate(page);
+ page_cache_get(page);
+ }
page_cache_release(page);
index++;
no_indizes--;
@@ -485,8 +495,12 @@ static void move_btree_to_page(struct inode *inode, struct page *page,
mempool_free(item, super->s_alias_pool);
}
block->page = page;
- SetPagePrivate(page);
- page->private = (unsigned long)block;
+
+ if (!PagePrivate(page)) {
+ SetPagePrivate(page);
+ page_cache_get(page);
+ set_page_private(page, (unsigned long) block);
+ }
block->ops = &indirect_block_ops;
initialize_block_counters(page, block, data, 0);
}
@@ -529,15 +543,19 @@ void move_page_to_btree(struct page *page)
BUG_ON(!item); /* mempool empty */
memset(item, 0, sizeof(*item));
- child = kmap_atomic(page, KM_USER0);
+ child = kmap_atomic(page);
item->val = child[pos];
- kunmap_atomic(child, KM_USER0);
+ kunmap_atomic(child);
item->child_no = pos;
list_add(&item->list, &block->item_list);
}
block->page = NULL;
- ClearPagePrivate(page);
- page->private = 0;
+
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ page_cache_release(page);
+ set_page_private(page, 0);
+ }
block->ops = &btree_block_ops;
err = alias_tree_insert(block->sb, block->ino, block->bix, block->level,
block);
@@ -702,7 +720,10 @@ void freeseg(struct super_block *sb, u32 segno)
page = find_get_page(mapping, ofs >> PAGE_SHIFT);
if (!page)
continue;
- ClearPagePrivate(page);
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ page_cache_release(page);
+ }
page_cache_release(page);
}
}
@@ -841,6 +862,16 @@ static void free_area(struct logfs_area *area)
kfree(area);
}
+void free_areas(struct super_block *sb)
+{
+ struct logfs_super *super = logfs_super(sb);
+ int i;
+
+ for_each_area(i)
+ free_area(super->s_area[i]);
+ free_area(super->s_journal_area);
+}
+
static struct logfs_area *alloc_area(struct super_block *sb)
{
struct logfs_area *area;
@@ -923,10 +954,6 @@ err:
void logfs_cleanup_areas(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
- int i;
btree_grim_visitor128(&super->s_object_alias_tree, 0, kill_alias);
- for_each_area(i)
- free_area(super->s_area[i]);
- free_area(super->s_journal_area);
}
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index e795c234..97bca62 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -315,11 +315,9 @@ static int logfs_get_sb_final(struct super_block *sb)
if (IS_ERR(rootdir))
goto fail;
- sb->s_root = d_alloc_root(rootdir);
- if (!sb->s_root) {
- iput(rootdir);
+ sb->s_root = d_make_root(rootdir);
+ if (!sb->s_root)
goto fail;
- }
/* at that point we know that ->put_super() will be called */
super->s_erase_page = alloc_pages(GFP_KERNEL, 0);
@@ -486,14 +484,15 @@ static void logfs_kill_sb(struct super_block *sb)
/* Alias entries slow down mount, so evict as many as possible */
sync_filesystem(sb);
logfs_write_anchor(sb);
+ free_areas(sb);
/*
* From this point on alias entries are simply dropped - and any
* writes to the object store are considered bugs.
*/
- super->s_flags |= LOGFS_SB_FLAG_SHUTDOWN;
log_super("LogFS: Now in shutdown\n");
generic_shutdown_super(sb);
+ super->s_flags |= LOGFS_SB_FLAG_SHUTDOWN;
BUG_ON(super->s_dirty_used_bytes || super->s_dirty_free_bytes);
@@ -541,6 +540,7 @@ static struct dentry *logfs_get_sb_device(struct logfs_super *super,
* the filesystem incompatible with 32bit systems.
*/
sb->s_maxbytes = (1ull << 43) - 1;
+ sb->s_max_links = LOGFS_LINK_MAX;
sb->s_op = &logfs_super_operations;
sb->s_flags = flags | MS_NOATIME;
@@ -626,7 +626,10 @@ static int __init logfs_init(void)
if (ret)
goto out2;
- return register_filesystem(&logfs_fs_type);
+ ret = register_filesystem(&logfs_fs_type);
+ if (!ret)
+ return 0;
+ logfs_destroy_inode_cache();
out2:
logfs_compr_exit();
out1:
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index 085a926..685b2d9 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -335,7 +335,7 @@ int minix_make_empty(struct inode *inode, struct inode *dir)
goto fail;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr, 0, PAGE_CACHE_SIZE);
if (sbi->s_version == MINIX_V3) {
@@ -355,7 +355,7 @@ int minix_make_empty(struct inode *inode, struct inode *dir)
de->inode = dir->i_ino;
strcpy(de->name, "..");
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
err = dir_commit_chunk(page, 0, 2 * sbi->s_dirsize);
fail:
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index fa8b612..fcb05d2 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -190,24 +190,24 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
sbi->s_version = MINIX_V1;
sbi->s_dirsize = 16;
sbi->s_namelen = 14;
- sbi->s_link_max = MINIX_LINK_MAX;
+ s->s_max_links = MINIX_LINK_MAX;
} else if (s->s_magic == MINIX_SUPER_MAGIC2) {
sbi->s_version = MINIX_V1;
sbi->s_dirsize = 32;
sbi->s_namelen = 30;
- sbi->s_link_max = MINIX_LINK_MAX;
+ s->s_max_links = MINIX_LINK_MAX;
} else if (s->s_magic == MINIX2_SUPER_MAGIC) {
sbi->s_version = MINIX_V2;
sbi->s_nzones = ms->s_zones;
sbi->s_dirsize = 16;
sbi->s_namelen = 14;
- sbi->s_link_max = MINIX2_LINK_MAX;
+ s->s_max_links = MINIX2_LINK_MAX;
} else if (s->s_magic == MINIX2_SUPER_MAGIC2) {
sbi->s_version = MINIX_V2;
sbi->s_nzones = ms->s_zones;
sbi->s_dirsize = 32;
sbi->s_namelen = 30;
- sbi->s_link_max = MINIX2_LINK_MAX;
+ s->s_max_links = MINIX2_LINK_MAX;
} else if ( *(__u16 *)(bh->b_data + 24) == MINIX3_SUPER_MAGIC) {
m3s = (struct minix3_super_block *) bh->b_data;
s->s_magic = m3s->s_magic;
@@ -221,9 +221,9 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
sbi->s_dirsize = 64;
sbi->s_namelen = 60;
sbi->s_version = MINIX_V3;
- sbi->s_link_max = MINIX2_LINK_MAX;
sbi->s_mount_state = MINIX_VALID_FS;
sb_set_blocksize(s, m3s->s_blocksize);
+ s->s_max_links = MINIX2_LINK_MAX;
} else
goto out_no_fs;
@@ -254,14 +254,6 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
minix_set_bit(0,sbi->s_imap[0]->b_data);
minix_set_bit(0,sbi->s_zmap[0]->b_data);
- /* set up enough so that it can read an inode */
- s->s_op = &minix_sops;
- root_inode = minix_iget(s, MINIX_ROOT_INO);
- if (IS_ERR(root_inode)) {
- ret = PTR_ERR(root_inode);
- goto out_no_root;
- }
-
/* Apparently minix can create filesystems that allocate more blocks for
* the bitmaps than needed. We simply ignore that, but verify it didn't
* create one with not enough blocks and bail out if so.
@@ -270,7 +262,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
if (sbi->s_imap_blocks < block) {
printk("MINIX-fs: file system does not have enough "
"imap blocks allocated. Refusing to mount\n");
- goto out_iput;
+ goto out_no_bitmap;
}
block = minix_blocks_needed(
@@ -279,13 +271,21 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
if (sbi->s_zmap_blocks < block) {
printk("MINIX-fs: file system does not have enough "
"zmap blocks allocated. Refusing to mount.\n");
- goto out_iput;
+ goto out_no_bitmap;
+ }
+
+ /* set up enough so that it can read an inode */
+ s->s_op = &minix_sops;
+ root_inode = minix_iget(s, MINIX_ROOT_INO);
+ if (IS_ERR(root_inode)) {
+ ret = PTR_ERR(root_inode);
+ goto out_no_root;
}
ret = -ENOMEM;
- s->s_root = d_alloc_root(root_inode);
+ s->s_root = d_make_root(root_inode);
if (!s->s_root)
- goto out_iput;
+ goto out_no_root;
if (!(s->s_flags & MS_RDONLY)) {
if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */
@@ -301,10 +301,6 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
return 0;
-out_iput:
- iput(root_inode);
- goto out_freemap;
-
out_no_root:
if (!silent)
printk("MINIX-fs: get root inode failed\n");
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index c889ef0..1ebd118 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -34,7 +34,6 @@ struct minix_sb_info {
unsigned long s_max_size;
int s_dirsize;
int s_namelen;
- int s_link_max;
struct buffer_head ** s_imap;
struct buffer_head ** s_zmap;
struct buffer_head * s_sbh;
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 2f76e38..2d0ee17 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -94,9 +94,6 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir,
{
struct inode *inode = old_dentry->d_inode;
- if (inode->i_nlink >= minix_sb(inode->i_sb)->s_link_max)
- return -EMLINK;
-
inode->i_ctime = CURRENT_TIME_SEC;
inode_inc_link_count(inode);
ihold(inode);
@@ -106,10 +103,7 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir,
static int minix_mkdir(struct inode * dir, struct dentry *dentry, umode_t mode)
{
struct inode * inode;
- int err = -EMLINK;
-
- if (dir->i_nlink >= minix_sb(dir->i_sb)->s_link_max)
- goto out;
+ int err;
inode_inc_link_count(dir);
@@ -181,7 +175,6 @@ static int minix_rmdir(struct inode * dir, struct dentry *dentry)
static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
struct inode * new_dir, struct dentry *new_dentry)
{
- struct minix_sb_info * info = minix_sb(old_dir->i_sb);
struct inode * old_inode = old_dentry->d_inode;
struct inode * new_inode = new_dentry->d_inode;
struct page * dir_page = NULL;
@@ -219,11 +212,6 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
- if (dir_de) {
- err = -EMLINK;
- if (new_dir->i_nlink >= info->s_link_max)
- goto out_dir;
- }
err = minix_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
diff --git a/fs/mpage.c b/fs/mpage.c
index 643e9f5..0face1c 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -13,7 +13,7 @@
*/
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm.h>
#include <linux/kdev_t.h>
#include <linux/gfp.h>
diff --git a/fs/namei.c b/fs/namei.c
index 208c6aa..e615ff3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -15,7 +15,7 @@
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
@@ -161,7 +161,7 @@ static char *getname_flags(const char __user *filename, int flags, int *empty)
char *getname(const char __user * filename)
{
- return getname_flags(filename, 0, 0);
+ return getname_flags(filename, 0, NULL);
}
#ifdef CONFIG_AUDITSYSCALL
@@ -642,7 +642,7 @@ follow_link(struct path *link, struct nameidata *nd, void **p)
cond_resched();
current->total_link_count++;
- touch_atime(link->mnt, dentry);
+ touch_atime(link);
nd_set_link(nd, NULL);
error = security_inode_follow_link(link->dentry, nd);
@@ -1095,8 +1095,10 @@ static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentr
struct dentry *old;
/* Don't create child dentry for a dead directory. */
- if (unlikely(IS_DEADDIR(inode)))
+ if (unlikely(IS_DEADDIR(inode))) {
+ dput(dentry);
return ERR_PTR(-ENOENT);
+ }
old = inode->i_op->lookup(inode, dentry, nd);
if (unlikely(old)) {
@@ -1373,6 +1375,157 @@ static inline int can_lookup(struct inode *inode)
}
/*
+ * We can do the critical dentry name comparison and hashing
+ * operations one word at a time, but we are limited to:
+ *
+ * - Architectures with fast unaligned word accesses. We could
+ * do a "get_unaligned()" if this helps and is sufficiently
+ * fast.
+ *
+ * - Little-endian machines (so that we can generate the mask
+ * of low bytes efficiently). Again, we *could* do a byte
+ * swapping load on big-endian architectures if that is not
+ * expensive enough to make the optimization worthless.
+ *
+ * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
+ * do not trap on the (extremely unlikely) case of a page
+ * crossing operation.
+ *
+ * - Furthermore, we need an efficient 64-bit compile for the
+ * 64-bit case in order to generate the "number of bytes in
+ * the final mask". Again, that could be replaced with a
+ * efficient population count instruction or similar.
+ */
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+ return mask*0x0001020304050608ul >> 56;
+}
+
+static inline unsigned int fold_hash(unsigned long hash)
+{
+ hash += hash >> (8*sizeof(int));
+ return hash;
+}
+
+#else /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+#define fold_hash(x) (x)
+
+#endif
+
+unsigned int full_name_hash(const unsigned char *name, unsigned int len)
+{
+ unsigned long a, mask;
+ unsigned long hash = 0;
+
+ for (;;) {
+ a = *(unsigned long *)name;
+ if (len < sizeof(unsigned long))
+ break;
+ hash += a;
+ hash *= 9;
+ name += sizeof(unsigned long);
+ len -= sizeof(unsigned long);
+ if (!len)
+ goto done;
+ }
+ mask = ~(~0ul << len*8);
+ hash += mask & a;
+done:
+ return fold_hash(hash);
+}
+EXPORT_SYMBOL(full_name_hash);
+
+#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
+#define ONEBYTES REPEAT_BYTE(0x01)
+#define SLASHBYTES REPEAT_BYTE('/')
+#define HIGHBITS REPEAT_BYTE(0x80)
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+ return ((a - ONEBYTES) & ~a) & HIGHBITS;
+}
+
+/*
+ * Calculate the length and hash of the path component, and
+ * return the length of the component;
+ */
+static inline unsigned long hash_name(const char *name, unsigned int *hashp)
+{
+ unsigned long a, mask, hash, len;
+
+ hash = a = 0;
+ len = -sizeof(unsigned long);
+ do {
+ hash = (hash + a) * 9;
+ len += sizeof(unsigned long);
+ a = *(unsigned long *)(name+len);
+ /* Do we have any NUL or '/' bytes in this word? */
+ mask = has_zero(a) | has_zero(a ^ SLASHBYTES);
+ } while (!mask);
+
+ /* The mask *below* the first high bit set */
+ mask = (mask - 1) & ~mask;
+ mask >>= 7;
+ hash += a & mask;
+ *hashp = fold_hash(hash);
+
+ return len + count_masked_bytes(mask);
+}
+
+#else
+
+unsigned int full_name_hash(const unsigned char *name, unsigned int len)
+{
+ unsigned long hash = init_name_hash();
+ while (len--)
+ hash = partial_name_hash(*name++, hash);
+ return end_name_hash(hash);
+}
+EXPORT_SYMBOL(full_name_hash);
+
+/*
+ * We know there's a real path component here of at least
+ * one character.
+ */
+static inline unsigned long hash_name(const char *name, unsigned int *hashp)
+{
+ unsigned long hash = init_name_hash();
+ unsigned long len = 0, c;
+
+ c = (unsigned char)*name;
+ do {
+ len++;
+ hash = partial_name_hash(c, hash);
+ c = (unsigned char)name[len];
+ } while (c && c != '/');
+ *hashp = end_name_hash(hash);
+ return len;
+}
+
+#endif
+
+/*
* Name resolution.
* This is the basic name resolution function, turning a pathname into
* the final dentry. We expect 'base' to be positive and a directory.
@@ -1392,31 +1545,22 @@ static int link_path_walk(const char *name, struct nameidata *nd)
/* At this point we know we have a real path component. */
for(;;) {
- unsigned long hash;
struct qstr this;
- unsigned int c;
+ long len;
int type;
err = may_lookup(nd);
if (err)
break;
+ len = hash_name(name, &this.hash);
this.name = name;
- c = *(const unsigned char *)name;
-
- hash = init_name_hash();
- do {
- name++;
- hash = partial_name_hash(c, hash);
- c = *(const unsigned char *)name;
- } while (c && (c != '/'));
- this.len = name - (const char *) this.name;
- this.hash = end_name_hash(hash);
+ this.len = len;
type = LAST_NORM;
- if (this.name[0] == '.') switch (this.len) {
+ if (name[0] == '.') switch (len) {
case 2:
- if (this.name[1] == '.') {
+ if (name[1] == '.') {
type = LAST_DOTDOT;
nd->flags |= LOOKUP_JUMPED;
}
@@ -1435,12 +1579,18 @@ static int link_path_walk(const char *name, struct nameidata *nd)
}
}
- /* remove trailing slashes? */
- if (!c)
+ if (!name[len])
goto last_component;
- while (*++name == '/');
- if (!*name)
+ /*
+ * If it wasn't NUL, we know it was '/'. Skip that
+ * slash, and continue until no more slashes.
+ */
+ do {
+ len++;
+ } while (unlikely(name[len] == '/'));
+ if (!name[len])
goto last_component;
+ name += len;
err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
if (err < 0)
@@ -1773,24 +1923,21 @@ static struct dentry *lookup_hash(struct nameidata *nd)
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
struct qstr this;
- unsigned long hash;
unsigned int c;
WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
this.name = name;
this.len = len;
+ this.hash = full_name_hash(name, len);
if (!len)
return ERR_PTR(-EACCES);
- hash = init_name_hash();
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
return ERR_PTR(-EACCES);
- hash = partial_name_hash(c, hash);
}
- this.hash = end_name_hash(hash);
/*
* See if the low-level filesystem might want
* to use its own hash..
@@ -1825,7 +1972,7 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
int user_path_at(int dfd, const char __user *name, unsigned flags,
struct path *path)
{
- return user_path_at_empty(dfd, name, flags, path, 0);
+ return user_path_at_empty(dfd, name, flags, path, NULL);
}
static int user_path_parent(int dfd, const char __user *path,
@@ -2138,7 +2285,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
/* sayonara */
error = complete_walk(nd);
if (error)
- return ERR_PTR(-ECHILD);
+ return ERR_PTR(error);
error = -ENOTDIR;
if (nd->flags & LOOKUP_DIRECTORY) {
@@ -2237,7 +2384,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
/* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */
error = complete_walk(nd);
if (error)
- goto exit;
+ return ERR_PTR(error);
error = -EISDIR;
if (S_ISDIR(nd->inode->i_mode))
goto exit;
@@ -2545,6 +2692,7 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int error = may_create(dir, dentry);
+ unsigned max_links = dir->i_sb->s_max_links;
if (error)
return error;
@@ -2557,6 +2705,9 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
if (error)
return error;
+ if (max_links && dir->i_nlink >= max_links)
+ return -EMLINK;
+
error = dir->i_op->mkdir(dir, dentry, mode);
if (!error)
fsnotify_mkdir(dir, dentry);
@@ -2887,6 +3038,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
{
struct inode *inode = old_dentry->d_inode;
+ unsigned max_links = dir->i_sb->s_max_links;
int error;
if (!inode)
@@ -2917,6 +3069,8 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
/* Make sure we don't allow creating hardlink to an unlinked file */
if (inode->i_nlink == 0)
error = -ENOENT;
+ else if (max_links && inode->i_nlink >= max_links)
+ error = -EMLINK;
else
error = dir->i_op->link(old_dentry, dir, new_dentry);
mutex_unlock(&inode->i_mutex);
@@ -3026,6 +3180,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
{
int error = 0;
struct inode *target = new_dentry->d_inode;
+ unsigned max_links = new_dir->i_sb->s_max_links;
/*
* If we are going to change the parent - check write permissions,
@@ -3049,6 +3204,11 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
goto out;
+ error = -EMLINK;
+ if (max_links && !target && new_dir != old_dir &&
+ new_dir->i_nlink >= max_links)
+ goto out;
+
if (target)
shrink_dcache_parent(new_dentry);
error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
@@ -3347,9 +3507,9 @@ retry:
if (err)
goto fail;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(kaddr, symname, len-1);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
page, fsdata);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 3d1e34f..49df0e7 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -716,13 +716,11 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
if (!root_inode)
goto out_disconnect;
DPRINTK("ncp_fill_super: root vol=%d\n", NCP_FINFO(root_inode)->volNumber);
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (!sb->s_root)
- goto out_no_root;
+ goto out_disconnect;
return 0;
-out_no_root:
- iput(root_inode);
out_disconnect:
ncp_lock_server(server);
ncp_disconnect(server);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index dbcd821..2a0e6c5 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -64,6 +64,7 @@ config NFS_V4
bool "NFS client support for NFS version 4"
depends on NFS_FS
select SUNRPC_GSS
+ select KEYS
help
This option enables support for version 4 of the NFS protocol
(RFC 3530) in the kernel's NFS client.
@@ -98,6 +99,18 @@ config PNFS_OBJLAYOUT
depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
default m
+config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
+ string "NFSv4.1 Implementation ID Domain"
+ depends on NFS_V4_1
+ default "kernel.org"
+ help
+ This option defines the domain portion of the implementation ID that
+ may be sent in the NFS exchange_id operation. The value must be in
+ the format of a DNS domain name and should be set to the DNS domain
+ name of the distribution.
+ If the NFS client is unchanged from the upstream kernel, this
+ option should be set to the default "kernel.org".
+
config ROOT_NFS
bool "Root file system on NFS"
depends on NFS_FS=y && IP_PNP
@@ -130,16 +143,10 @@ config NFS_USE_KERNEL_DNS
bool
depends on NFS_V4 && !NFS_USE_LEGACY_DNS
select DNS_RESOLVER
- select KEYS
default y
-config NFS_USE_NEW_IDMAPPER
- bool "Use the new idmapper upcall routine"
- depends on NFS_V4 && KEYS
- help
- Say Y here if you want NFS to use the new idmapper upcall functions.
- You will need /sbin/request-key (usually provided by the keyutils
- package). For details, read
- <file:Documentation/filesystems/nfs/idmapper.txt>.
-
- If you are unsure, say N.
+config NFS_DEBUG
+ bool
+ depends on NFS_FS && SUNRPC_DEBUG
+ select CRC32
+ default y
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 48cfac3..9c94297 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -46,9 +46,6 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
-struct dentry *bl_device_pipe;
-wait_queue_head_t bl_wq;
-
static void print_page(struct page *page)
{
dprintk("PRINTPAGE page %p\n", page);
@@ -236,12 +233,11 @@ bl_read_pagelist(struct nfs_read_data *rdata)
sector_t isect, extent_length = 0;
struct parallel_io *par;
loff_t f_offset = rdata->args.offset;
- size_t count = rdata->args.count;
struct page **pages = rdata->args.pages;
int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
- dprintk("%s enter nr_pages %u offset %lld count %Zd\n", __func__,
- rdata->npages, f_offset, count);
+ dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
+ rdata->npages, f_offset, (unsigned int)rdata->args.count);
par = alloc_parallel(rdata);
if (!par)
@@ -1025,10 +1021,128 @@ static const struct rpc_pipe_ops bl_upcall_ops = {
.destroy_msg = bl_pipe_destroy_msg,
};
+static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+ struct rpc_pipe *pipe)
+{
+ struct dentry *dir, *dentry;
+
+ dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
+ if (dir == NULL)
+ return ERR_PTR(-ENOENT);
+ dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+ dput(dir);
+ return dentry;
+}
+
+static void nfs4blocklayout_unregister_sb(struct super_block *sb,
+ struct rpc_pipe *pipe)
+{
+ if (pipe->dentry)
+ rpc_unlink(pipe->dentry);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct super_block *sb = ptr;
+ struct net *net = sb->s_fs_info;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct dentry *dentry;
+ int ret = 0;
+
+ if (!try_module_get(THIS_MODULE))
+ return 0;
+
+ if (nn->bl_device_pipe == NULL) {
+ module_put(THIS_MODULE);
+ return 0;
+ }
+
+ switch (event) {
+ case RPC_PIPEFS_MOUNT:
+ dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
+ if (IS_ERR(dentry)) {
+ ret = PTR_ERR(dentry);
+ break;
+ }
+ nn->bl_device_pipe->dentry = dentry;
+ break;
+ case RPC_PIPEFS_UMOUNT:
+ if (nn->bl_device_pipe->dentry)
+ nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+ break;
+ default:
+ ret = -ENOTSUPP;
+ break;
+ }
+ module_put(THIS_MODULE);
+ return ret;
+}
+
+static struct notifier_block nfs4blocklayout_block = {
+ .notifier_call = rpc_pipefs_event,
+};
+
+static struct dentry *nfs4blocklayout_register_net(struct net *net,
+ struct rpc_pipe *pipe)
+{
+ struct super_block *pipefs_sb;
+ struct dentry *dentry;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (!pipefs_sb)
+ return NULL;
+ dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+ rpc_put_sb_net(net);
+ return dentry;
+}
+
+static void nfs4blocklayout_unregister_net(struct net *net,
+ struct rpc_pipe *pipe)
+{
+ struct super_block *pipefs_sb;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (pipefs_sb) {
+ nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+ rpc_put_sb_net(net);
+ }
+}
+
+static int nfs4blocklayout_net_init(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct dentry *dentry;
+
+ init_waitqueue_head(&nn->bl_wq);
+ nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
+ if (IS_ERR(nn->bl_device_pipe))
+ return PTR_ERR(nn->bl_device_pipe);
+ dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+ if (IS_ERR(dentry)) {
+ rpc_destroy_pipe_data(nn->bl_device_pipe);
+ return PTR_ERR(dentry);
+ }
+ nn->bl_device_pipe->dentry = dentry;
+ return 0;
+}
+
+static void nfs4blocklayout_net_exit(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+ nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
+ rpc_destroy_pipe_data(nn->bl_device_pipe);
+ nn->bl_device_pipe = NULL;
+}
+
+static struct pernet_operations nfs4blocklayout_net_ops = {
+ .init = nfs4blocklayout_net_init,
+ .exit = nfs4blocklayout_net_exit,
+};
+
static int __init nfs4blocklayout_init(void)
{
- struct vfsmount *mnt;
- struct path path;
int ret;
dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
@@ -1037,32 +1151,17 @@ static int __init nfs4blocklayout_init(void)
if (ret)
goto out;
- init_waitqueue_head(&bl_wq);
-
- mnt = rpc_get_mount();
- if (IS_ERR(mnt)) {
- ret = PTR_ERR(mnt);
+ ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+ if (ret)
goto out_remove;
- }
-
- ret = vfs_path_lookup(mnt->mnt_root,
- mnt,
- NFS_PIPE_DIRNAME, 0, &path);
+ ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
if (ret)
- goto out_putrpc;
-
- bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
- &bl_upcall_ops, 0);
- path_put(&path);
- if (IS_ERR(bl_device_pipe)) {
- ret = PTR_ERR(bl_device_pipe);
- goto out_putrpc;
- }
+ goto out_notifier;
out:
return ret;
-out_putrpc:
- rpc_put_mount();
+out_notifier:
+ rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
out_remove:
pnfs_unregister_layoutdriver(&blocklayout_type);
return ret;
@@ -1073,9 +1172,9 @@ static void __exit nfs4blocklayout_exit(void)
dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
__func__);
+ rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+ unregister_pernet_subsys(&nfs4blocklayout_net_ops);
pnfs_unregister_layoutdriver(&blocklayout_type);
- rpc_unlink(bl_device_pipe);
- rpc_put_mount();
}
MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index e31a2df..0335069 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -37,6 +37,7 @@
#include <linux/sunrpc/rpc_pipe_fs.h>
#include "../pnfs.h"
+#include "../netns.h"
#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
@@ -50,6 +51,7 @@ struct pnfs_block_dev {
struct list_head bm_node;
struct nfs4_deviceid bm_mdevid; /* associated devid */
struct block_device *bm_mdev; /* meta device itself */
+ struct net *net;
};
enum exstate4 {
@@ -151,9 +153,9 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
return BLK_LO2EXT(lseg->pls_layout);
}
-struct bl_dev_msg {
- int32_t status;
- uint32_t major, minor;
+struct bl_pipe_msg {
+ struct rpc_pipe_msg msg;
+ wait_queue_head_t *bl_wq;
};
struct bl_msg_hdr {
@@ -161,9 +163,6 @@ struct bl_msg_hdr {
u16 totallen; /* length of entire message, including hdr itself */
};
-extern struct dentry *bl_device_pipe;
-extern wait_queue_head_t bl_wq;
-
#define BL_DEVICE_UMOUNT 0x0 /* Umount--delete devices */
#define BL_DEVICE_MOUNT 0x1 /* Mount--create devices*/
#define BL_DEVICE_REQUEST_INIT 0x0 /* Start request */
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index d08ba91..a5c88a5 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -46,7 +46,7 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
*rp = xdr_decode_hyper(*rp, &s);
if (s & 0x1ff) {
- printk(KERN_WARNING "%s: sector not aligned\n", __func__);
+ printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
return -1;
}
*sp = s >> SECTOR_SHIFT;
@@ -79,27 +79,30 @@ int nfs4_blkdev_put(struct block_device *bdev)
return blkdev_put(bdev, FMODE_READ);
}
-static struct bl_dev_msg bl_mount_reply;
-
ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
size_t mlen)
{
+ struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+ nfs_net_id);
+
if (mlen != sizeof (struct bl_dev_msg))
return -EINVAL;
- if (copy_from_user(&bl_mount_reply, src, mlen) != 0)
+ if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
return -EFAULT;
- wake_up(&bl_wq);
+ wake_up(&nn->bl_wq);
return mlen;
}
void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
{
+ struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg);
+
if (msg->errno >= 0)
return;
- wake_up(&bl_wq);
+ wake_up(bl_pipe_msg->bl_wq);
}
/*
@@ -111,29 +114,33 @@ nfs4_blk_decode_device(struct nfs_server *server,
{
struct pnfs_block_dev *rv;
struct block_device *bd = NULL;
- struct rpc_pipe_msg msg;
+ struct bl_pipe_msg bl_pipe_msg;
+ struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
struct bl_msg_hdr bl_msg = {
.type = BL_DEVICE_MOUNT,
.totallen = dev->mincount,
};
uint8_t *dataptr;
DECLARE_WAITQUEUE(wq, current);
- struct bl_dev_msg *reply = &bl_mount_reply;
int offset, len, i, rc;
+ struct net *net = server->nfs_client->net;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct bl_dev_msg *reply = &nn->bl_mount_reply;
dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
dev->mincount);
- memset(&msg, 0, sizeof(msg));
- msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
- if (!msg.data) {
+ bl_pipe_msg.bl_wq = &nn->bl_wq;
+ memset(msg, 0, sizeof(*msg));
+ msg->data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
+ if (!msg->data) {
rv = ERR_PTR(-ENOMEM);
goto out;
}
- memcpy(msg.data, &bl_msg, sizeof(bl_msg));
- dataptr = (uint8_t *) msg.data;
+ memcpy(msg->data, &bl_msg, sizeof(bl_msg));
+ dataptr = (uint8_t *) msg->data;
len = dev->mincount;
offset = sizeof(bl_msg);
for (i = 0; len > 0; i++) {
@@ -142,13 +149,13 @@ nfs4_blk_decode_device(struct nfs_server *server,
len -= PAGE_CACHE_SIZE;
offset += PAGE_CACHE_SIZE;
}
- msg.len = sizeof(bl_msg) + dev->mincount;
+ msg->len = sizeof(bl_msg) + dev->mincount;
dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
- add_wait_queue(&bl_wq, &wq);
- rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+ add_wait_queue(&nn->bl_wq, &wq);
+ rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
if (rc < 0) {
- remove_wait_queue(&bl_wq, &wq);
+ remove_wait_queue(&nn->bl_wq, &wq);
rv = ERR_PTR(rc);
goto out;
}
@@ -156,7 +163,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
set_current_state(TASK_UNINTERRUPTIBLE);
schedule();
__set_current_state(TASK_RUNNING);
- remove_wait_queue(&bl_wq, &wq);
+ remove_wait_queue(&nn->bl_wq, &wq);
if (reply->status != BL_DEVICE_REQUEST_PROC) {
dprintk("%s failed to open device: %d\n",
@@ -181,13 +188,14 @@ nfs4_blk_decode_device(struct nfs_server *server,
rv->bm_mdev = bd;
memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
+ rv->net = net;
dprintk("%s Created device %s with bd_block_size %u\n",
__func__,
bd->bd_disk->disk_name,
bd->bd_block_size);
out:
- kfree(msg.data);
+ kfree(msg->data);
return rv;
}
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index d055c75..737d839 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -38,9 +38,10 @@
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-static void dev_remove(dev_t dev)
+static void dev_remove(struct net *net, dev_t dev)
{
- struct rpc_pipe_msg msg;
+ struct bl_pipe_msg bl_pipe_msg;
+ struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
struct bl_dev_msg bl_umount_request;
struct bl_msg_hdr bl_msg = {
.type = BL_DEVICE_UMOUNT,
@@ -48,36 +49,38 @@ static void dev_remove(dev_t dev)
};
uint8_t *dataptr;
DECLARE_WAITQUEUE(wq, current);
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
dprintk("Entering %s\n", __func__);
- memset(&msg, 0, sizeof(msg));
- msg.data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
- if (!msg.data)
+ bl_pipe_msg.bl_wq = &nn->bl_wq;
+ memset(msg, 0, sizeof(*msg));
+ msg->data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+ if (!msg->data)
goto out;
memset(&bl_umount_request, 0, sizeof(bl_umount_request));
bl_umount_request.major = MAJOR(dev);
bl_umount_request.minor = MINOR(dev);
- memcpy(msg.data, &bl_msg, sizeof(bl_msg));
- dataptr = (uint8_t *) msg.data;
+ memcpy(msg->data, &bl_msg, sizeof(bl_msg));
+ dataptr = (uint8_t *) msg->data;
memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
- msg.len = sizeof(bl_msg) + bl_msg.totallen;
+ msg->len = sizeof(bl_msg) + bl_msg.totallen;
- add_wait_queue(&bl_wq, &wq);
- if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
- remove_wait_queue(&bl_wq, &wq);
+ add_wait_queue(&nn->bl_wq, &wq);
+ if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
+ remove_wait_queue(&nn->bl_wq, &wq);
goto out;
}
set_current_state(TASK_UNINTERRUPTIBLE);
schedule();
__set_current_state(TASK_RUNNING);
- remove_wait_queue(&bl_wq, &wq);
+ remove_wait_queue(&nn->bl_wq, &wq);
out:
- kfree(msg.data);
+ kfree(msg->data);
}
/*
@@ -90,10 +93,10 @@ static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
dprintk("%s Releasing\n", __func__);
rv = nfs4_blkdev_put(bdev->bm_mdev);
if (rv)
- printk(KERN_ERR "%s nfs4_blkdev_put returns %d\n",
+ printk(KERN_ERR "NFS: %s nfs4_blkdev_put returns %d\n",
__func__, rv);
- dev_remove(bdev->bm_mdev->bd_dev);
+ dev_remove(bdev->net, bdev->bm_mdev->bd_dev);
}
void bl_free_block_dev(struct pnfs_block_dev *bdev)
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 1abac09..1f9a603 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -147,7 +147,7 @@ static int _preload_range(struct pnfs_inval_markings *marks,
count = (int)(end - start) / (int)tree->mtt_step_size;
/* Pre-malloc what memory we might need */
- storage = kmalloc(sizeof(*storage) * count, GFP_NOFS);
+ storage = kcalloc(count, sizeof(*storage), GFP_NOFS);
if (!storage)
return -ENOMEM;
for (i = 0; i < count; i++) {
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index c98b439..dded263 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -13,6 +13,7 @@
#include <linux/slab.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
+#include <net/net_namespace.h>
#include "cache_lib.h"
@@ -111,30 +112,54 @@ int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq)
return 0;
}
-int nfs_cache_register(struct cache_detail *cd)
+int nfs_cache_register_sb(struct super_block *sb, struct cache_detail *cd)
{
- struct vfsmount *mnt;
- struct path path;
int ret;
+ struct dentry *dir;
- mnt = rpc_get_mount();
- if (IS_ERR(mnt))
- return PTR_ERR(mnt);
- ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &path);
- if (ret)
- goto err;
- ret = sunrpc_cache_register_pipefs(path.dentry, cd->name, 0600, cd);
- path_put(&path);
- if (!ret)
- return ret;
-err:
- rpc_put_mount();
+ dir = rpc_d_lookup_sb(sb, "cache");
+ BUG_ON(dir == NULL);
+ ret = sunrpc_cache_register_pipefs(dir, cd->name, 0600, cd);
+ dput(dir);
return ret;
}
-void nfs_cache_unregister(struct cache_detail *cd)
+int nfs_cache_register_net(struct net *net, struct cache_detail *cd)
{
- sunrpc_cache_unregister_pipefs(cd);
- rpc_put_mount();
+ struct super_block *pipefs_sb;
+ int ret = 0;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (pipefs_sb) {
+ ret = nfs_cache_register_sb(pipefs_sb, cd);
+ rpc_put_sb_net(net);
+ }
+ return ret;
+}
+
+void nfs_cache_unregister_sb(struct super_block *sb, struct cache_detail *cd)
+{
+ if (cd->u.pipefs.dir)
+ sunrpc_cache_unregister_pipefs(cd);
+}
+
+void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd)
+{
+ struct super_block *pipefs_sb;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (pipefs_sb) {
+ nfs_cache_unregister_sb(pipefs_sb, cd);
+ rpc_put_sb_net(net);
+ }
+}
+
+void nfs_cache_init(struct cache_detail *cd)
+{
+ sunrpc_init_cache_detail(cd);
}
+void nfs_cache_destroy(struct cache_detail *cd)
+{
+ sunrpc_destroy_cache_detail(cd);
+}
diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h
index 7cf6caf..317db95 100644
--- a/fs/nfs/cache_lib.h
+++ b/fs/nfs/cache_lib.h
@@ -23,5 +23,11 @@ extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void);
extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq);
extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq);
-extern int nfs_cache_register(struct cache_detail *cd);
-extern void nfs_cache_unregister(struct cache_detail *cd);
+extern void nfs_cache_init(struct cache_detail *cd);
+extern void nfs_cache_destroy(struct cache_detail *cd);
+extern int nfs_cache_register_net(struct net *net, struct cache_detail *cd);
+extern void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd);
+extern int nfs_cache_register_sb(struct super_block *sb,
+ struct cache_detail *cd);
+extern void nfs_cache_unregister_sb(struct super_block *sb,
+ struct cache_detail *cd);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 516f337..eb95f50 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -85,7 +85,7 @@ nfs4_callback_svc(void *vrqstp)
}
if (err < 0) {
if (err != preverr) {
- printk(KERN_WARNING "%s: unexpected error "
+ printk(KERN_WARNING "NFS: %s: unexpected error "
"from svc_recv (%d)\n", __func__, err);
preverr = err;
}
@@ -101,12 +101,12 @@ nfs4_callback_svc(void *vrqstp)
/*
* Prepare to bring up the NFSv4 callback service
*/
-struct svc_rqst *
-nfs4_callback_up(struct svc_serv *serv)
+static struct svc_rqst *
+nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
{
int ret;
- ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
+ ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET,
nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
if (ret <= 0)
goto out_err;
@@ -114,7 +114,7 @@ nfs4_callback_up(struct svc_serv *serv)
dprintk("NFS: Callback listener port = %u (af %u)\n",
nfs_callback_tcpport, PF_INET);
- ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
+ ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET6,
nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
if (ret > 0) {
nfs_callback_tcpport6 = ret;
@@ -172,7 +172,7 @@ nfs41_callback_svc(void *vrqstp)
/*
* Bring up the NFSv4.1 callback service
*/
-struct svc_rqst *
+static struct svc_rqst *
nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
{
struct svc_rqst *rqstp;
@@ -183,7 +183,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
* fore channel connection.
* Returns the input port (0) and sets the svc_serv bc_xprt on success
*/
- ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0,
+ ret = svc_create_xprt(serv, "tcp-bc", xprt->xprt_net, PF_INET, 0,
SVC_SOCK_ANONYMOUS);
if (ret < 0) {
rqstp = ERR_PTR(ret);
@@ -269,7 +269,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
serv, xprt, &rqstp, &callback_svc);
if (!minorversion_setup) {
/* v4.0 callback setup */
- rqstp = nfs4_callback_up(serv);
+ rqstp = nfs4_callback_up(serv, xprt);
callback_svc = nfs4_callback_svc;
}
@@ -332,7 +332,6 @@ void nfs_callback_down(int minorversion)
int
check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
{
- struct rpc_clnt *r = clp->cl_rpcclient;
char *p = svc_gss_principal(rqstp);
if (rqstp->rq_authop->flavour != RPC_AUTH_GSS)
@@ -353,7 +352,7 @@ check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
if (memcmp(p, "nfs@", 4) != 0)
return 0;
p += 4;
- if (strcmp(p, r->cl_server) != 0)
+ if (strcmp(p, clp->cl_hostname) != 0)
return 0;
return 1;
}
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index c89d3b9..a5527c9 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -38,7 +38,8 @@ enum nfs4_callback_opnum {
struct cb_process_state {
__be32 drc_status;
struct nfs_client *clp;
- int slotid;
+ u32 slotid;
+ struct net *net;
};
struct cb_compound_hdr_arg {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 54cea8a..1b5d809 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -8,6 +8,7 @@
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/slab.h>
+#include <linux/rcupdate.h>
#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
@@ -33,7 +34,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
res->bitmap[0] = res->bitmap[1] = 0;
res->status = htonl(NFS4ERR_BADHANDLE);
- dprintk("NFS: GETATTR callback request from %s\n",
+ dprintk_rcu("NFS: GETATTR callback request from %s\n",
rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
inode = nfs_delegation_find_inode(cps->clp, &args->fh);
@@ -73,7 +74,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
if (!cps->clp) /* Always set for v4.0. Set in cb_sequence for v4.1 */
goto out;
- dprintk("NFS: RECALL callback request from %s\n",
+ dprintk_rcu("NFS: RECALL callback request from %s\n",
rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
res = htonl(NFS4ERR_BADHANDLE);
@@ -86,8 +87,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
res = 0;
break;
case -ENOENT:
- if (res != 0)
- res = htonl(NFS4ERR_BAD_STATEID);
+ res = htonl(NFS4ERR_BAD_STATEID);
break;
default:
res = htonl(NFS4ERR_RESOURCE);
@@ -98,52 +98,64 @@ out:
return res;
}
-int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
-{
- if (delegation == NULL || memcmp(delegation->stateid.data, stateid->data,
- sizeof(delegation->stateid.data)) != 0)
- return 0;
- return 1;
-}
-
#if defined(CONFIG_NFS_V4_1)
-static u32 initiate_file_draining(struct nfs_client *clp,
- struct cb_layoutrecallargs *args)
+/*
+ * Lookup a layout by filehandle.
+ *
+ * Note: gets a refcount on the layout hdr and on its respective inode.
+ * Caller must put the layout hdr and the inode.
+ *
+ * TODO: keep track of all layouts (and delegations) in a hash table
+ * hashed by filehandle.
+ */
+static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp, struct nfs_fh *fh)
{
struct nfs_server *server;
- struct pnfs_layout_hdr *lo;
struct inode *ino;
- bool found = false;
- u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
- LIST_HEAD(free_me_list);
+ struct pnfs_layout_hdr *lo;
- spin_lock(&clp->cl_lock);
- rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
list_for_each_entry(lo, &server->layouts, plh_layouts) {
- if (nfs_compare_fh(&args->cbl_fh,
- &NFS_I(lo->plh_inode)->fh))
+ if (nfs_compare_fh(fh, &NFS_I(lo->plh_inode)->fh))
continue;
ino = igrab(lo->plh_inode);
if (!ino)
continue;
- found = true;
- /* Without this, layout can be freed as soon
- * as we release cl_lock.
- */
get_layout_hdr(lo);
- break;
+ return lo;
}
- if (found)
- break;
}
+
+ return NULL;
+}
+
+static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, struct nfs_fh *fh)
+{
+ struct pnfs_layout_hdr *lo;
+
+ spin_lock(&clp->cl_lock);
+ rcu_read_lock();
+ lo = get_layout_by_fh_locked(clp, fh);
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
- if (!found)
+ return lo;
+}
+
+static u32 initiate_file_draining(struct nfs_client *clp,
+ struct cb_layoutrecallargs *args)
+{
+ struct inode *ino;
+ struct pnfs_layout_hdr *lo;
+ u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
+ LIST_HEAD(free_me_list);
+
+ lo = get_layout_by_fh(clp, &args->cbl_fh);
+ if (!lo)
return NFS4ERR_NOMATCHING_LAYOUT;
+ ino = lo->plh_inode;
spin_lock(&ino->i_lock);
if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
mark_matching_lsegs_invalid(lo, &free_me_list,
@@ -213,17 +225,13 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
static u32 do_callback_layoutrecall(struct nfs_client *clp,
struct cb_layoutrecallargs *args)
{
- u32 res = NFS4ERR_DELAY;
+ u32 res;
dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type);
- if (test_and_set_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state))
- goto out;
if (args->cbl_recall_type == RETURN_FILE)
res = initiate_file_draining(clp, args);
else
res = initiate_bulk_draining(clp, args);
- clear_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state);
-out:
dprintk("%s returning %i\n", __func__, res);
return res;
@@ -303,21 +311,6 @@ out:
return res;
}
-int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
-{
- if (delegation == NULL)
- return 0;
-
- if (stateid->stateid.seqid != 0)
- return 0;
- if (memcmp(&delegation->stateid.stateid.other,
- &stateid->stateid.other,
- NFS4_STATEID_OTHER_SIZE))
- return 0;
-
- return 1;
-}
-
/*
* Validate the sequenceID sent by the server.
* Return success if the sequenceID is one more than what we last saw on
@@ -441,7 +434,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
int i;
__be32 status = htonl(NFS4ERR_BADSESSION);
- clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
+ clp = nfs4_find_client_sessionid(cps->net, args->csa_addr, &args->csa_sessionid);
if (clp == NULL)
goto out;
@@ -517,7 +510,7 @@ __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy,
if (!cps->clp) /* set in cb_sequence */
goto out;
- dprintk("NFS: RECALL_ANY callback request from %s\n",
+ dprintk_rcu("NFS: RECALL_ANY callback request from %s\n",
rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
status = cpu_to_be32(NFS4ERR_INVAL);
@@ -552,7 +545,7 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
if (!cps->clp) /* set in cb_sequence */
goto out;
- dprintk("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
+ dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR),
args->crsa_target_max_slots);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index d50b274..95bfc24 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -9,6 +9,8 @@
#include <linux/sunrpc/svc.h>
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
+#include <linux/ratelimit.h>
+#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/sunrpc/bc_xprt.h>
#include "nfs4_fs.h"
@@ -73,7 +75,7 @@ static __be32 *read_buf(struct xdr_stream *xdr, int nbytes)
p = xdr_inline_decode(xdr, nbytes);
if (unlikely(p == NULL))
- printk(KERN_WARNING "NFSv4 callback reply buffer overflowed!\n");
+ printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n");
return p;
}
@@ -138,10 +140,10 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
{
__be32 *p;
- p = read_buf(xdr, 16);
+ p = read_buf(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
- memcpy(stateid->data, p, 16);
+ memcpy(stateid, p, NFS4_STATEID_SIZE);
return 0;
}
@@ -155,7 +157,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
return status;
/* We do not like overly long tags! */
if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) {
- printk("NFSv4 CALLBACK %s: client sent tag of length %u\n",
+ printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n",
__func__, hdr->taglen);
return htonl(NFS4ERR_RESOURCE);
}
@@ -167,7 +169,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
if (hdr->minorversion <= 1) {
hdr->cb_ident = ntohl(*p++); /* ignored by v4.1 */
} else {
- printk(KERN_WARNING "%s: NFSv4 server callback with "
+ pr_warn_ratelimited("NFS: %s: NFSv4 server callback with "
"illegal minor version %u!\n",
__func__, hdr->minorversion);
return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
@@ -759,14 +761,14 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
* Let the state manager know callback processing done.
* A single slot, so highest used slotid is either 0 or -1
*/
- tbl->highest_used_slotid = -1;
+ tbl->highest_used_slotid = NFS4_NO_SLOT;
nfs4_check_drain_bc_complete(session);
spin_unlock(&tbl->slot_tbl_lock);
}
static void nfs4_cb_free_slot(struct cb_process_state *cps)
{
- if (cps->slotid != -1)
+ if (cps->slotid != NFS4_NO_SLOT)
nfs4_callback_free_slot(cps->clp->cl_session);
}
@@ -860,7 +862,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
struct cb_process_state cps = {
.drc_status = 0,
.clp = NULL,
- .slotid = -1,
+ .slotid = NFS4_NO_SLOT,
+ .net = rqstp->rq_xprt->xpt_net,
};
unsigned int nops = 0;
@@ -876,7 +879,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
return rpc_garbage_args;
if (hdr_arg.minorversion == 0) {
- cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident);
+ cps.clp = nfs4_find_client_ident(rqstp->rq_xprt->xpt_net, hdr_arg.cb_ident);
if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
return rpc_drop_reply;
}
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 31778f7..4a108a0 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -36,9 +36,12 @@
#include <linux/inet.h>
#include <linux/in6.h>
#include <linux/slab.h>
+#include <linux/idr.h>
#include <net/ipv6.h>
#include <linux/nfs_xdr.h>
#include <linux/sunrpc/bc_xprt.h>
+#include <linux/nsproxy.h>
+#include <linux/pid_namespace.h>
#include <asm/system.h>
@@ -49,15 +52,12 @@
#include "internal.h"
#include "fscache.h"
#include "pnfs.h"
+#include "netns.h"
#define NFSDBG_FACILITY NFSDBG_CLIENT
-static DEFINE_SPINLOCK(nfs_client_lock);
-static LIST_HEAD(nfs_client_list);
-static LIST_HEAD(nfs_volume_list);
static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
#ifdef CONFIG_NFS_V4
-static DEFINE_IDR(cb_ident_idr); /* Protected by nfs_client_lock */
/*
* Get a unique NFSv4.0 callback identifier which will be used
@@ -66,15 +66,16 @@ static DEFINE_IDR(cb_ident_idr); /* Protected by nfs_client_lock */
static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
{
int ret = 0;
+ struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
if (clp->rpc_ops->version != 4 || minorversion != 0)
return ret;
retry:
- if (!idr_pre_get(&cb_ident_idr, GFP_KERNEL))
+ if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
return -ENOMEM;
- spin_lock(&nfs_client_lock);
- ret = idr_get_new(&cb_ident_idr, clp, &clp->cl_cb_ident);
- spin_unlock(&nfs_client_lock);
+ spin_lock(&nn->nfs_client_lock);
+ ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+ spin_unlock(&nn->nfs_client_lock);
if (ret == -EAGAIN)
goto retry;
return ret;
@@ -89,7 +90,7 @@ static bool nfs4_disable_idmapping = true;
/*
* RPC cruft for NFS
*/
-static struct rpc_version *nfs_version[5] = {
+static const struct rpc_version *nfs_version[5] = {
[2] = &nfs_version2,
#ifdef CONFIG_NFS_V3
[3] = &nfs_version3,
@@ -99,7 +100,7 @@ static struct rpc_version *nfs_version[5] = {
#endif
};
-struct rpc_program nfs_program = {
+const struct rpc_program nfs_program = {
.name = "nfs",
.number = NFS_PROGRAM,
.nrvers = ARRAY_SIZE(nfs_version),
@@ -115,11 +116,11 @@ struct rpc_stat nfs_rpcstat = {
#ifdef CONFIG_NFS_V3_ACL
static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program };
-static struct rpc_version * nfsacl_version[] = {
+static const struct rpc_version *nfsacl_version[] = {
[3] = &nfsacl_version3,
};
-struct rpc_program nfsacl_program = {
+const struct rpc_program nfsacl_program = {
.name = "nfsacl",
.number = NFS_ACL_PROGRAM,
.nrvers = ARRAY_SIZE(nfsacl_version),
@@ -135,6 +136,7 @@ struct nfs_client_initdata {
const struct nfs_rpc_ops *rpc_ops;
int proto;
u32 minorversion;
+ struct net *net;
};
/*
@@ -171,6 +173,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
clp->cl_rpcclient = ERR_PTR(-EINVAL);
clp->cl_proto = cl_init->proto;
+ clp->net = get_net(cl_init->net);
#ifdef CONFIG_NFS_V4
err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
@@ -202,8 +205,11 @@ error_0:
#ifdef CONFIG_NFS_V4_1
static void nfs4_shutdown_session(struct nfs_client *clp)
{
- if (nfs4_has_session(clp))
+ if (nfs4_has_session(clp)) {
+ nfs4_deviceid_purge_client(clp);
nfs4_destroy_session(clp->cl_session);
+ }
+
}
#else /* CONFIG_NFS_V4_1 */
static void nfs4_shutdown_session(struct nfs_client *clp)
@@ -233,16 +239,20 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
}
/* idr_remove_all is not needed as all id's are removed by nfs_put_client */
-void nfs_cleanup_cb_ident_idr(void)
+void nfs_cleanup_cb_ident_idr(struct net *net)
{
- idr_destroy(&cb_ident_idr);
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+ idr_destroy(&nn->cb_ident_idr);
}
/* nfs_client_lock held */
static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
{
+ struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
+
if (clp->cl_cb_ident)
- idr_remove(&cb_ident_idr, clp->cl_cb_ident);
+ idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident);
}
static void pnfs_init_server(struct nfs_server *server)
@@ -260,7 +270,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
{
}
-void nfs_cleanup_cb_ident_idr(void)
+void nfs_cleanup_cb_ident_idr(struct net *net)
{
}
@@ -292,10 +302,10 @@ static void nfs_free_client(struct nfs_client *clp)
if (clp->cl_machine_cred != NULL)
put_rpccred(clp->cl_machine_cred);
- nfs4_deviceid_purge_client(clp);
-
+ put_net(clp->net);
kfree(clp->cl_hostname);
kfree(clp->server_scope);
+ kfree(clp->impl_id);
kfree(clp);
dprintk("<-- nfs_free_client()\n");
@@ -306,15 +316,18 @@ static void nfs_free_client(struct nfs_client *clp)
*/
void nfs_put_client(struct nfs_client *clp)
{
+ struct nfs_net *nn;
+
if (!clp)
return;
dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
+ nn = net_generic(clp->net, nfs_net_id);
- if (atomic_dec_and_lock(&clp->cl_count, &nfs_client_lock)) {
+ if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
list_del(&clp->cl_share_link);
nfs_cb_idr_remove_locked(clp);
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
BUG_ON(!list_empty(&clp->cl_superblocks));
@@ -392,6 +405,7 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
(sin1->sin_port == sin2->sin_port);
}
+#if defined(CONFIG_NFS_V4_1)
/*
* Test if two socket addresses represent the same actual socket,
* by comparing (only) relevant fields, excluding the port number.
@@ -410,6 +424,7 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
}
return 0;
}
+#endif /* CONFIG_NFS_V4_1 */
/*
* Test if two socket addresses represent the same actual socket,
@@ -430,10 +445,10 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
return 0;
}
+#if defined(CONFIG_NFS_V4_1)
/* Common match routine for v4.0 and v4.1 callback services */
-bool
-nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
- u32 minorversion)
+static bool nfs4_cb_match_client(const struct sockaddr *addr,
+ struct nfs_client *clp, u32 minorversion)
{
struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
@@ -453,6 +468,7 @@ nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
return true;
}
+#endif /* CONFIG_NFS_V4_1 */
/*
* Find an nfs_client on the list that matches the initialisation data
@@ -462,8 +478,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
{
struct nfs_client *clp;
const struct sockaddr *sap = data->addr;
+ struct nfs_net *nn = net_generic(data->net, nfs_net_id);
- list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+ list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
/* Don't match clients that failed to initialise properly */
if (clp->cl_cons_state < 0)
@@ -501,13 +518,14 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
{
struct nfs_client *clp, *new = NULL;
int error;
+ struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
dprintk("--> nfs_get_client(%s,v%u)\n",
cl_init->hostname ?: "", cl_init->rpc_ops->version);
/* see if the client already exists */
do {
- spin_lock(&nfs_client_lock);
+ spin_lock(&nn->nfs_client_lock);
clp = nfs_match_client(cl_init);
if (clp)
@@ -515,7 +533,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
if (new)
goto install_client;
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
new = nfs_alloc_client(cl_init);
} while (!IS_ERR(new));
@@ -526,8 +544,8 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
/* install a new client and return with it unready */
install_client:
clp = new;
- list_add(&clp->cl_share_link, &nfs_client_list);
- spin_unlock(&nfs_client_lock);
+ list_add(&clp->cl_share_link, &nn->nfs_client_list);
+ spin_unlock(&nn->nfs_client_lock);
error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr,
authflavour, noresvport);
@@ -542,7 +560,7 @@ install_client:
* - make sure it's ready before returning
*/
found_client:
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
if (new)
nfs_free_client(new);
@@ -642,7 +660,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
{
struct rpc_clnt *clnt = NULL;
struct rpc_create_args args = {
- .net = &init_net,
+ .net = clp->net,
.protocol = clp->cl_proto,
.address = (struct sockaddr *)&clp->cl_addr,
.addrsize = clp->cl_addrlen,
@@ -696,6 +714,7 @@ static int nfs_start_lockd(struct nfs_server *server)
.nfs_version = clp->rpc_ops->version,
.noresvport = server->flags & NFS_MOUNT_NORESVPORT ?
1 : 0,
+ .net = clp->net,
};
if (nlm_init.nfs_version > 3)
@@ -831,6 +850,7 @@ static int nfs_init_server(struct nfs_server *server,
.addrlen = data->nfs_server.addrlen,
.rpc_ops = &nfs_v2_clientops,
.proto = data->nfs_server.protocol,
+ .net = data->net,
};
struct rpc_timeout timeparms;
struct nfs_client *clp;
@@ -1029,25 +1049,30 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
static void nfs_server_insert_lists(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
+ struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
- spin_lock(&nfs_client_lock);
+ spin_lock(&nn->nfs_client_lock);
list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
- list_add_tail(&server->master_link, &nfs_volume_list);
+ list_add_tail(&server->master_link, &nn->nfs_volume_list);
clear_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
}
static void nfs_server_remove_lists(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
+ struct nfs_net *nn;
- spin_lock(&nfs_client_lock);
+ if (clp == NULL)
+ return;
+ nn = net_generic(clp->net, nfs_net_id);
+ spin_lock(&nn->nfs_client_lock);
list_del_rcu(&server->client_link);
- if (clp && list_empty(&clp->cl_superblocks))
+ if (list_empty(&clp->cl_superblocks))
set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
list_del(&server->master_link);
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
synchronize_rcu();
}
@@ -1086,6 +1111,8 @@ static struct nfs_server *nfs_alloc_server(void)
return NULL;
}
+ ida_init(&server->openowner_id);
+ ida_init(&server->lockowner_id);
pnfs_init_server(server);
return server;
@@ -1111,6 +1138,8 @@ void nfs_free_server(struct nfs_server *server)
nfs_put_client(server->nfs_client);
+ ida_destroy(&server->lockowner_id);
+ ida_destroy(&server->openowner_id);
nfs_free_iostats(server->io_stats);
bdi_destroy(&server->backing_dev_info);
kfree(server);
@@ -1189,45 +1218,19 @@ error:
/*
* NFSv4.0 callback thread helper
*
- * Find a client by IP address, protocol version, and minorversion
- *
- * Called from the pg_authenticate method. The callback identifier
- * is not used as it has not been decoded.
- *
- * Returns NULL if no such client
- */
-struct nfs_client *
-nfs4_find_client_no_ident(const struct sockaddr *addr)
-{
- struct nfs_client *clp;
-
- spin_lock(&nfs_client_lock);
- list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
- if (nfs4_cb_match_client(addr, clp, 0) == false)
- continue;
- atomic_inc(&clp->cl_count);
- spin_unlock(&nfs_client_lock);
- return clp;
- }
- spin_unlock(&nfs_client_lock);
- return NULL;
-}
-
-/*
- * NFSv4.0 callback thread helper
- *
* Find a client by callback identifier
*/
struct nfs_client *
-nfs4_find_client_ident(int cb_ident)
+nfs4_find_client_ident(struct net *net, int cb_ident)
{
struct nfs_client *clp;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
- spin_lock(&nfs_client_lock);
- clp = idr_find(&cb_ident_idr, cb_ident);
+ spin_lock(&nn->nfs_client_lock);
+ clp = idr_find(&nn->cb_ident_idr, cb_ident);
if (clp)
atomic_inc(&clp->cl_count);
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
return clp;
}
@@ -1240,13 +1243,14 @@ nfs4_find_client_ident(int cb_ident)
* Returns NULL if no such client
*/
struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *addr,
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
struct nfs4_sessionid *sid)
{
struct nfs_client *clp;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
- spin_lock(&nfs_client_lock);
- list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+ spin_lock(&nn->nfs_client_lock);
+ list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
if (nfs4_cb_match_client(addr, clp, 1) == false)
continue;
@@ -1259,17 +1263,17 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
continue;
atomic_inc(&clp->cl_count);
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
return clp;
}
- spin_unlock(&nfs_client_lock);
+ spin_unlock(&nn->nfs_client_lock);
return NULL;
}
#else /* CONFIG_NFS_V4_1 */
struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *addr,
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
struct nfs4_sessionid *sid)
{
return NULL;
@@ -1284,16 +1288,18 @@ static int nfs4_init_callback(struct nfs_client *clp)
int error;
if (clp->rpc_ops->version == 4) {
+ struct rpc_xprt *xprt;
+
+ xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
+
if (nfs4_has_session(clp)) {
- error = xprt_setup_backchannel(
- clp->cl_rpcclient->cl_xprt,
+ error = xprt_setup_backchannel(xprt,
NFS41_BC_MIN_CALLBACKS);
if (error < 0)
return error;
}
- error = nfs_callback_up(clp->cl_mvops->minor_version,
- clp->cl_rpcclient->cl_xprt);
+ error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
if (error < 0) {
dprintk("%s: failed to start callback. Error = %d\n",
__func__, error);
@@ -1344,6 +1350,7 @@ int nfs4_init_client(struct nfs_client *clp,
rpc_authflavor_t authflavour,
int noresvport)
{
+ char buf[INET6_ADDRSTRLEN + 1];
int error;
if (clp->cl_cons_state == NFS_CS_READY) {
@@ -1359,6 +1366,20 @@ int nfs4_init_client(struct nfs_client *clp,
1, noresvport);
if (error < 0)
goto error;
+
+ /* If no clientaddr= option was specified, find a usable cb address */
+ if (ip_addr == NULL) {
+ struct sockaddr_storage cb_addr;
+ struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+ error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+ if (error < 0)
+ goto error;
+ error = rpc_ntop(sap, buf, sizeof(buf));
+ if (error < 0)
+ goto error;
+ ip_addr = (const char *)buf;
+ }
strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
error = nfs_idmap_new(clp);
@@ -1393,7 +1414,7 @@ static int nfs4_set_client(struct nfs_server *server,
const char *ip_addr,
rpc_authflavor_t authflavour,
int proto, const struct rpc_timeout *timeparms,
- u32 minorversion)
+ u32 minorversion, struct net *net)
{
struct nfs_client_initdata cl_init = {
.hostname = hostname,
@@ -1402,6 +1423,7 @@ static int nfs4_set_client(struct nfs_server *server,
.rpc_ops = &nfs_v4_clientops,
.proto = proto,
.minorversion = minorversion,
+ .net = net,
};
struct nfs_client *clp;
int error;
@@ -1453,6 +1475,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
.rpc_ops = &nfs_v4_clientops,
.proto = ds_proto,
.minorversion = mds_clp->cl_minorversion,
+ .net = mds_clp->net,
};
struct rpc_timeout ds_timeout = {
.to_initval = 15 * HZ,
@@ -1580,7 +1603,8 @@ static int nfs4_init_server(struct nfs_server *server,
data->auth_flavors[0],
data->nfs_server.protocol,
&timeparms,
- data->minorversion);
+ data->minorversion,
+ data->net);
if (error < 0)
goto error;
@@ -1675,9 +1699,10 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
data->addrlen,
parent_client->cl_ipaddr,
data->authflavor,
- parent_server->client->cl_xprt->prot,
+ rpc_protocol(parent_server->client),
parent_server->client->cl_timeout,
- parent_client->cl_mvops->minor_version);
+ parent_client->cl_mvops->minor_version,
+ parent_client->net);
if (error < 0)
goto error;
@@ -1770,6 +1795,18 @@ out_free_server:
return ERR_PTR(error);
}
+void nfs_clients_init(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+ INIT_LIST_HEAD(&nn->nfs_client_list);
+ INIT_LIST_HEAD(&nn->nfs_volume_list);
+#ifdef CONFIG_NFS_V4
+ idr_init(&nn->cb_ident_idr);
+#endif
+ spin_lock_init(&nn->nfs_client_lock);
+}
+
#ifdef CONFIG_PROC_FS
static struct proc_dir_entry *proc_fs_nfs;
@@ -1823,13 +1860,15 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
{
struct seq_file *m;
int ret;
+ struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
+ struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
ret = seq_open(file, &nfs_server_list_ops);
if (ret < 0)
return ret;
m = file->private_data;
- m->private = PDE(inode)->data;
+ m->private = net;
return 0;
}
@@ -1839,9 +1878,11 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
*/
static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
{
+ struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+
/* lock the list against modification */
- spin_lock(&nfs_client_lock);
- return seq_list_start_head(&nfs_client_list, *_pos);
+ spin_lock(&nn->nfs_client_lock);
+ return seq_list_start_head(&nn->nfs_client_list, *_pos);
}
/*
@@ -1849,7 +1890,9 @@ static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
*/
static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
{
- return seq_list_next(v, &nfs_client_list, pos);
+ struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+ return seq_list_next(v, &nn->nfs_client_list, pos);
}
/*
@@ -1857,7 +1900,9 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
*/
static void nfs_server_list_stop(struct seq_file *p, void *v)
{
- spin_unlock(&nfs_client_lock);
+ struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+ spin_unlock(&nn->nfs_client_lock);
}
/*
@@ -1866,9 +1911,10 @@ static void nfs_server_list_stop(struct seq_file *p, void *v)
static int nfs_server_list_show(struct seq_file *m, void *v)
{
struct nfs_client *clp;
+ struct nfs_net *nn = net_generic(m->private, nfs_net_id);
/* display header on line 1 */
- if (v == &nfs_client_list) {
+ if (v == &nn->nfs_client_list) {
seq_puts(m, "NV SERVER PORT USE HOSTNAME\n");
return 0;
}
@@ -1880,12 +1926,14 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
if (clp->cl_cons_state != NFS_CS_READY)
return 0;
+ rcu_read_lock();
seq_printf(m, "v%u %s %s %3d %s\n",
clp->rpc_ops->version,
rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
atomic_read(&clp->cl_count),
clp->cl_hostname);
+ rcu_read_unlock();
return 0;
}
@@ -1897,13 +1945,15 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
{
struct seq_file *m;
int ret;
+ struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
+ struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
ret = seq_open(file, &nfs_volume_list_ops);
if (ret < 0)
return ret;
m = file->private_data;
- m->private = PDE(inode)->data;
+ m->private = net;
return 0;
}
@@ -1913,9 +1963,11 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
*/
static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
{
+ struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+
/* lock the list against modification */
- spin_lock(&nfs_client_lock);
- return seq_list_start_head(&nfs_volume_list, *_pos);
+ spin_lock(&nn->nfs_client_lock);
+ return seq_list_start_head(&nn->nfs_volume_list, *_pos);
}
/*
@@ -1923,7 +1975,9 @@ static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
*/
static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
{
- return seq_list_next(v, &nfs_volume_list, pos);
+ struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+ return seq_list_next(v, &nn->nfs_volume_list, pos);
}
/*
@@ -1931,7 +1985,9 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
*/
static void nfs_volume_list_stop(struct seq_file *p, void *v)
{
- spin_unlock(&nfs_client_lock);
+ struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+ spin_unlock(&nn->nfs_client_lock);
}
/*
@@ -1942,9 +1998,10 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
struct nfs_server *server;
struct nfs_client *clp;
char dev[8], fsid[17];
+ struct nfs_net *nn = net_generic(m->private, nfs_net_id);
/* display header on line 1 */
- if (v == &nfs_volume_list) {
+ if (v == &nn->nfs_volume_list) {
seq_puts(m, "NV SERVER PORT DEV FSID FSC\n");
return 0;
}
@@ -1959,6 +2016,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
(unsigned long long) server->fsid.major,
(unsigned long long) server->fsid.minor);
+ rcu_read_lock();
seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
clp->rpc_ops->version,
rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
@@ -1966,6 +2024,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
dev,
fsid,
nfs_server_fscache_state(server));
+ rcu_read_unlock();
return 0;
}
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 7f26540..89af1d2 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -105,7 +105,7 @@ again:
continue;
if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
continue;
- if (memcmp(state->stateid.data, stateid->data, sizeof(state->stateid.data)) != 0)
+ if (!nfs4_stateid_match(&state->stateid, stateid))
continue;
get_nfs_open_context(ctx);
spin_unlock(&inode->i_lock);
@@ -139,8 +139,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
if (delegation != NULL) {
spin_lock(&delegation->lock);
if (delegation->inode != NULL) {
- memcpy(delegation->stateid.data, res->delegation.data,
- sizeof(delegation->stateid.data));
+ nfs4_stateid_copy(&delegation->stateid, &res->delegation);
delegation->type = res->delegation_type;
delegation->maxsize = res->maxsize;
oldcred = delegation->cred;
@@ -236,8 +235,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
delegation = kmalloc(sizeof(*delegation), GFP_NOFS);
if (delegation == NULL)
return -ENOMEM;
- memcpy(delegation->stateid.data, res->delegation.data,
- sizeof(delegation->stateid.data));
+ nfs4_stateid_copy(&delegation->stateid, &res->delegation);
delegation->type = res->delegation_type;
delegation->maxsize = res->maxsize;
delegation->change_attr = inode->i_version;
@@ -250,19 +248,22 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
old_delegation = rcu_dereference_protected(nfsi->delegation,
lockdep_is_held(&clp->cl_lock));
if (old_delegation != NULL) {
- if (memcmp(&delegation->stateid, &old_delegation->stateid,
- sizeof(old_delegation->stateid)) == 0 &&
+ if (nfs4_stateid_match(&delegation->stateid,
+ &old_delegation->stateid) &&
delegation->type == old_delegation->type) {
goto out;
}
/*
* Deal with broken servers that hand out two
* delegations for the same file.
+ * Allow for upgrades to a WRITE delegation, but
+ * nothing else.
*/
dfprintk(FILE, "%s: server %s handed out "
"a duplicate delegation!\n",
__func__, clp->cl_hostname);
- if (delegation->type <= old_delegation->type) {
+ if (delegation->type == old_delegation->type ||
+ !(delegation->type & FMODE_WRITE)) {
freeme = delegation;
delegation = NULL;
goto out;
@@ -455,17 +456,24 @@ static void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp,
rcu_read_unlock();
}
-static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
-{
- nfs_client_mark_return_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
-}
-
static void nfs_delegation_run_state_manager(struct nfs_client *clp)
{
if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
nfs4_schedule_state_manager(clp);
}
+void nfs_remove_bad_delegation(struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+
+ delegation = nfs_detach_delegation(NFS_I(inode), NFS_SERVER(inode));
+ if (delegation) {
+ nfs_inode_find_state_and_recover(inode, &delegation->stateid);
+ nfs_free_delegation(delegation);
+ }
+}
+EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
+
/**
* nfs_expire_all_delegation_types
* @clp: client to process
@@ -488,18 +496,6 @@ void nfs_expire_all_delegations(struct nfs_client *clp)
nfs_expire_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
}
-/**
- * nfs_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
- * @clp: client to process
- *
- */
-void nfs_handle_cb_pathdown(struct nfs_client *clp)
-{
- if (clp == NULL)
- return;
- nfs_client_mark_return_all_delegations(clp);
-}
-
static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
{
struct nfs_delegation *delegation;
@@ -531,7 +527,7 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
/**
* nfs_async_inode_return_delegation - asynchronously return a delegation
* @inode: inode to process
- * @stateid: state ID information from CB_RECALL arguments
+ * @stateid: state ID information
*
* Returns zero on success, or a negative errno value.
*/
@@ -545,7 +541,7 @@ int nfs_async_inode_return_delegation(struct inode *inode,
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
- if (!clp->cl_mvops->validate_stateid(delegation, stateid)) {
+ if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
rcu_read_unlock();
return -ENOENT;
}
@@ -684,21 +680,25 @@ int nfs_delegations_present(struct nfs_client *clp)
* nfs4_copy_delegation_stateid - Copy inode's state ID information
* @dst: stateid data structure to fill in
* @inode: inode to check
+ * @flags: delegation type requirement
*
- * Returns one and fills in "dst->data" * if inode had a delegation,
- * otherwise zero is returned.
+ * Returns "true" and fills in "dst->data" * if inode had a delegation,
+ * otherwise "false" is returned.
*/
-int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
+bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
+ fmode_t flags)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_delegation *delegation;
- int ret = 0;
+ bool ret;
+ flags &= FMODE_READ|FMODE_WRITE;
rcu_read_lock();
delegation = rcu_dereference(nfsi->delegation);
- if (delegation != NULL) {
- memcpy(dst->data, delegation->stateid.data, sizeof(dst->data));
- ret = 1;
+ ret = (delegation != NULL && (delegation->type & flags) == flags);
+ if (ret) {
+ nfs4_stateid_copy(dst, &delegation->stateid);
+ nfs_mark_delegation_referenced(delegation);
}
rcu_read_unlock();
return ret;
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index d9322e4..cd6a7a8 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -42,9 +42,9 @@ void nfs_super_return_all_delegations(struct super_block *sb);
void nfs_expire_all_delegations(struct nfs_client *clp);
void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
-void nfs_handle_cb_pathdown(struct nfs_client *clp);
int nfs_client_return_marked_delegations(struct nfs_client *clp);
int nfs_delegations_present(struct nfs_client *clp);
+void nfs_remove_bad_delegation(struct inode *inode);
void nfs_delegation_mark_reclaim(struct nfs_client *clp);
void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
@@ -53,7 +53,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
-int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
+bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
int nfs_have_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index fd9a872..4aaf031 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -207,7 +207,7 @@ struct nfs_cache_array_entry {
};
struct nfs_cache_array {
- unsigned int size;
+ int size;
int eof_index;
u64 last_cookie;
struct nfs_cache_array_entry array[0];
@@ -260,10 +260,10 @@ void nfs_readdir_clear_array(struct page *page)
struct nfs_cache_array *array;
int i;
- array = kmap_atomic(page, KM_USER0);
+ array = kmap_atomic(page);
for (i = 0; i < array->size; i++)
kfree(array->array[i].string.name);
- kunmap_atomic(array, KM_USER0);
+ kunmap_atomic(array);
}
/*
@@ -1429,6 +1429,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
}
open_flags = nd->intent.open.flags;
+ attr.ia_valid = 0;
ctx = create_nfs_open_context(dentry, open_flags);
res = ERR_CAST(ctx);
@@ -1437,11 +1438,14 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
if (nd->flags & LOOKUP_CREATE) {
attr.ia_mode = nd->intent.open.create_mode;
- attr.ia_valid = ATTR_MODE;
+ attr.ia_valid |= ATTR_MODE;
attr.ia_mode &= ~current_umask();
- } else {
+ } else
open_flags &= ~(O_EXCL | O_CREAT);
- attr.ia_valid = 0;
+
+ if (open_flags & O_TRUNC) {
+ attr.ia_valid |= ATTR_SIZE;
+ attr.ia_size = 0;
}
/* Open the file on the server */
@@ -1495,6 +1499,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
struct inode *inode;
struct inode *dir;
struct nfs_open_context *ctx;
+ struct iattr attr;
int openflags, ret = 0;
if (nd->flags & LOOKUP_RCU)
@@ -1523,19 +1528,27 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
/* We cannot do exclusive creation on a positive dentry */
if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
goto no_open_dput;
- /* We can't create new files, or truncate existing ones here */
- openflags &= ~(O_CREAT|O_EXCL|O_TRUNC);
+ /* We can't create new files here */
+ openflags &= ~(O_CREAT|O_EXCL);
ctx = create_nfs_open_context(dentry, openflags);
ret = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
+
+ attr.ia_valid = 0;
+ if (openflags & O_TRUNC) {
+ attr.ia_valid |= ATTR_SIZE;
+ attr.ia_size = 0;
+ nfs_wb_all(inode);
+ }
+
/*
* Note: we're not holding inode->i_mutex and so may be racing with
* operations that change the directory. We therefore save the
* change attribute *before* we do the RPC call.
*/
- inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL);
+ inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
switch (ret) {
@@ -1870,11 +1883,11 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
if (!page)
return -ENOMEM;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(kaddr, symname, pathlen);
if (pathlen < PAGE_SIZE)
memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
if (error != 0) {
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 1940f1a..9c7f66a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -265,9 +265,7 @@ static void nfs_direct_read_release(void *calldata)
}
static const struct rpc_call_ops nfs_read_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_direct_read_result,
.rpc_release = nfs_direct_read_release,
};
@@ -554,9 +552,7 @@ static void nfs_direct_commit_release(void *calldata)
}
static const struct rpc_call_ops nfs_commit_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_direct_commit_result,
.rpc_release = nfs_direct_commit_release,
};
@@ -696,9 +692,7 @@ out_unlock:
}
static const struct rpc_call_ops nfs_write_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_direct_write_result,
.rpc_release = nfs_direct_write_release,
};
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index a6e711a..b3924b8 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -10,8 +10,9 @@
#include <linux/sunrpc/clnt.h>
#include <linux/dns_resolver.h>
+#include "dns_resolve.h"
-ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
struct sockaddr *sa, size_t salen)
{
ssize_t ret;
@@ -20,7 +21,7 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL);
if (ip_len > 0)
- ret = rpc_pton(ip_addr, ip_len, sa, salen);
+ ret = rpc_pton(net, ip_addr, ip_len, sa, salen);
else
ret = -ESRCH;
kfree(ip_addr);
@@ -40,15 +41,15 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/svcauth.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
#include "dns_resolve.h"
#include "cache_lib.h"
+#include "netns.h"
#define NFS_DNS_HASHBITS 4
#define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS)
-static struct cache_head *nfs_dns_table[NFS_DNS_HASHTBL_SIZE];
-
struct nfs_dns_ent {
struct cache_head h;
@@ -224,7 +225,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
len = qword_get(&buf, buf1, sizeof(buf1));
if (len <= 0)
goto out;
- key.addrlen = rpc_pton(buf1, len,
+ key.addrlen = rpc_pton(cd->net, buf1, len,
(struct sockaddr *)&key.addr,
sizeof(key.addr));
@@ -259,21 +260,6 @@ out:
return ret;
}
-static struct cache_detail nfs_dns_resolve = {
- .owner = THIS_MODULE,
- .hash_size = NFS_DNS_HASHTBL_SIZE,
- .hash_table = nfs_dns_table,
- .name = "dns_resolve",
- .cache_put = nfs_dns_ent_put,
- .cache_upcall = nfs_dns_upcall,
- .cache_parse = nfs_dns_parse,
- .cache_show = nfs_dns_show,
- .match = nfs_dns_match,
- .init = nfs_dns_ent_init,
- .update = nfs_dns_ent_update,
- .alloc = nfs_dns_ent_alloc,
-};
-
static int do_cache_lookup(struct cache_detail *cd,
struct nfs_dns_ent *key,
struct nfs_dns_ent **item,
@@ -336,8 +322,8 @@ out:
return ret;
}
-ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
- struct sockaddr *sa, size_t salen)
+ssize_t nfs_dns_resolve_name(struct net *net, char *name,
+ size_t namelen, struct sockaddr *sa, size_t salen)
{
struct nfs_dns_ent key = {
.hostname = name,
@@ -345,28 +331,118 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
};
struct nfs_dns_ent *item = NULL;
ssize_t ret;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
- ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item);
+ ret = do_cache_lookup_wait(nn->nfs_dns_resolve, &key, &item);
if (ret == 0) {
if (salen >= item->addrlen) {
memcpy(sa, &item->addr, item->addrlen);
ret = item->addrlen;
} else
ret = -EOVERFLOW;
- cache_put(&item->h, &nfs_dns_resolve);
+ cache_put(&item->h, nn->nfs_dns_resolve);
} else if (ret == -ENOENT)
ret = -ESRCH;
return ret;
}
+int nfs_dns_resolver_cache_init(struct net *net)
+{
+ int err = -ENOMEM;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct cache_detail *cd;
+ struct cache_head **tbl;
+
+ cd = kzalloc(sizeof(struct cache_detail), GFP_KERNEL);
+ if (cd == NULL)
+ goto err_cd;
+
+ tbl = kzalloc(NFS_DNS_HASHTBL_SIZE * sizeof(struct cache_head *),
+ GFP_KERNEL);
+ if (tbl == NULL)
+ goto err_tbl;
+
+ cd->owner = THIS_MODULE,
+ cd->hash_size = NFS_DNS_HASHTBL_SIZE,
+ cd->hash_table = tbl,
+ cd->name = "dns_resolve",
+ cd->cache_put = nfs_dns_ent_put,
+ cd->cache_upcall = nfs_dns_upcall,
+ cd->cache_parse = nfs_dns_parse,
+ cd->cache_show = nfs_dns_show,
+ cd->match = nfs_dns_match,
+ cd->init = nfs_dns_ent_init,
+ cd->update = nfs_dns_ent_update,
+ cd->alloc = nfs_dns_ent_alloc,
+
+ nfs_cache_init(cd);
+ err = nfs_cache_register_net(net, cd);
+ if (err)
+ goto err_reg;
+ nn->nfs_dns_resolve = cd;
+ return 0;
+
+err_reg:
+ nfs_cache_destroy(cd);
+ kfree(cd->hash_table);
+err_tbl:
+ kfree(cd);
+err_cd:
+ return err;
+}
+
+void nfs_dns_resolver_cache_destroy(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct cache_detail *cd = nn->nfs_dns_resolve;
+
+ nfs_cache_unregister_net(net, cd);
+ nfs_cache_destroy(cd);
+ kfree(cd->hash_table);
+ kfree(cd);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct super_block *sb = ptr;
+ struct net *net = sb->s_fs_info;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct cache_detail *cd = nn->nfs_dns_resolve;
+ int ret = 0;
+
+ if (cd == NULL)
+ return 0;
+
+ if (!try_module_get(THIS_MODULE))
+ return 0;
+
+ switch (event) {
+ case RPC_PIPEFS_MOUNT:
+ ret = nfs_cache_register_sb(sb, cd);
+ break;
+ case RPC_PIPEFS_UMOUNT:
+ nfs_cache_unregister_sb(sb, cd);
+ break;
+ default:
+ ret = -ENOTSUPP;
+ break;
+ }
+ module_put(THIS_MODULE);
+ return ret;
+}
+
+static struct notifier_block nfs_dns_resolver_block = {
+ .notifier_call = rpc_pipefs_event,
+};
+
int nfs_dns_resolver_init(void)
{
- return nfs_cache_register(&nfs_dns_resolve);
+ return rpc_pipefs_notifier_register(&nfs_dns_resolver_block);
}
void nfs_dns_resolver_destroy(void)
{
- nfs_cache_unregister(&nfs_dns_resolve);
+ rpc_pipefs_notifier_unregister(&nfs_dns_resolver_block);
}
-
#endif
diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h
index 199bb55..2e4f596 100644
--- a/fs/nfs/dns_resolve.h
+++ b/fs/nfs/dns_resolve.h
@@ -15,12 +15,22 @@ static inline int nfs_dns_resolver_init(void)
static inline void nfs_dns_resolver_destroy(void)
{}
+
+static inline int nfs_dns_resolver_cache_init(struct net *net)
+{
+ return 0;
+}
+
+static inline void nfs_dns_resolver_cache_destroy(struct net *net)
+{}
#else
extern int nfs_dns_resolver_init(void);
extern void nfs_dns_resolver_destroy(void);
+extern int nfs_dns_resolver_cache_init(struct net *net);
+extern void nfs_dns_resolver_cache_destroy(struct net *net);
#endif
-extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
- struct sockaddr *sa, size_t salen);
+extern ssize_t nfs_dns_resolve_name(struct net *net, char *name,
+ size_t namelen, struct sockaddr *sa, size_t salen);
#endif
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index c43a452..4fdaaa6 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -530,6 +530,8 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
if (mapping != dentry->d_inode->i_mapping)
goto out_unlock;
+ wait_on_page_writeback(page);
+
pagelen = nfs_page_length(page);
if (pagelen == 0)
goto out_unlock;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 419119c..ae65c16 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -327,7 +327,7 @@ void nfs_fscache_reset_inode_cookie(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_server *nfss = NFS_SERVER(inode);
- struct fscache_cookie *old = nfsi->fscache;
+ NFS_IFDEBUG(struct fscache_cookie *old = nfsi->fscache);
nfs_fscache_inode_lock(inode);
if (nfsi->fscache) {
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index dcb6154..801d6d8 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -49,11 +49,9 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
{
/* The mntroot acts as the dummy root dentry for this superblock */
if (sb->s_root == NULL) {
- sb->s_root = d_alloc_root(inode);
- if (sb->s_root == NULL) {
- iput(inode);
+ sb->s_root = d_make_root(inode);
+ if (sb->s_root == NULL)
return -ENOMEM;
- }
ihold(inode);
/*
* Ensure that this dentry is invisible to d_find_alias().
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 2c05f19..b7f348b 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -34,11 +34,29 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/fs.h>
#include <linux/nfs_idmap.h>
+#include <net/net_namespace.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <keys/user-type.h>
+#include <linux/module.h>
+
+#include "internal.h"
+#include "netns.h"
+
+#define NFS_UINT_MAXLEN 11
+
+/* Default cache timeout is 10 minutes */
+unsigned int nfs_idmap_cache_timeout = 600;
+static const struct cred *id_resolver_cache;
+static struct key_type key_type_id_resolver_legacy;
+
/**
* nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
@@ -142,24 +160,7 @@ static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
return snprintf(buf, buflen, "%u", id);
}
-#ifdef CONFIG_NFS_USE_NEW_IDMAPPER
-
-#include <linux/cred.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_fs_sb.h>
-#include <linux/keyctl.h>
-#include <linux/key-type.h>
-#include <linux/rcupdate.h>
-#include <linux/err.h>
-
-#include <keys/user-type.h>
-
-#define NFS_UINT_MAXLEN 11
-
-const struct cred *id_resolver_cache;
-
-struct key_type key_type_id_resolver = {
+static struct key_type key_type_id_resolver = {
.name = "id_resolver",
.instantiate = user_instantiate,
.match = user_match,
@@ -169,13 +170,14 @@ struct key_type key_type_id_resolver = {
.read = user_read,
};
-int nfs_idmap_init(void)
+static int nfs_idmap_init_keyring(void)
{
struct cred *cred;
struct key *keyring;
int ret = 0;
- printk(KERN_NOTICE "Registering the %s key type\n", key_type_id_resolver.name);
+ printk(KERN_NOTICE "NFS: Registering the %s key type\n",
+ key_type_id_resolver.name);
cred = prepare_kernel_cred(NULL);
if (!cred)
@@ -198,6 +200,7 @@ int nfs_idmap_init(void)
if (ret < 0)
goto failed_put_key;
+ set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags);
cred->thread_keyring = keyring;
cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
id_resolver_cache = cred;
@@ -210,7 +213,7 @@ failed_put_cred:
return ret;
}
-void nfs_idmap_quit(void)
+static void nfs_idmap_quit_keyring(void)
{
key_revoke(id_resolver_cache->thread_keyring);
unregister_key_type(&key_type_id_resolver);
@@ -245,8 +248,10 @@ static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen,
return desclen;
}
-static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
- const char *type, void *data, size_t data_size)
+static ssize_t nfs_idmap_request_key(struct key_type *key_type,
+ const char *name, size_t namelen,
+ const char *type, void *data,
+ size_t data_size, struct idmap *idmap)
{
const struct cred *saved_cred;
struct key *rkey;
@@ -259,8 +264,12 @@ static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
goto out;
saved_cred = override_creds(id_resolver_cache);
- rkey = request_key(&key_type_id_resolver, desc, "");
+ if (idmap)
+ rkey = request_key_with_auxdata(key_type, desc, "", 0, idmap);
+ else
+ rkey = request_key(&key_type_id_resolver, desc, "");
revert_creds(saved_cred);
+
kfree(desc);
if (IS_ERR(rkey)) {
ret = PTR_ERR(rkey);
@@ -293,31 +302,46 @@ out:
return ret;
}
+static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
+ const char *type, void *data,
+ size_t data_size, struct idmap *idmap)
+{
+ ssize_t ret = nfs_idmap_request_key(&key_type_id_resolver,
+ name, namelen, type, data,
+ data_size, NULL);
+ if (ret < 0) {
+ ret = nfs_idmap_request_key(&key_type_id_resolver_legacy,
+ name, namelen, type, data,
+ data_size, idmap);
+ }
+ return ret;
+}
/* ID -> Name */
-static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen)
+static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf,
+ size_t buflen, struct idmap *idmap)
{
char id_str[NFS_UINT_MAXLEN];
int id_len;
ssize_t ret;
id_len = snprintf(id_str, sizeof(id_str), "%u", id);
- ret = nfs_idmap_request_key(id_str, id_len, type, buf, buflen);
+ ret = nfs_idmap_get_key(id_str, id_len, type, buf, buflen, idmap);
if (ret < 0)
return -EINVAL;
return ret;
}
/* Name -> ID */
-static int nfs_idmap_lookup_id(const char *name, size_t namelen,
- const char *type, __u32 *id)
+static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *type,
+ __u32 *id, struct idmap *idmap)
{
char id_str[NFS_UINT_MAXLEN];
long id_long;
ssize_t data_size;
int ret = 0;
- data_size = nfs_idmap_request_key(name, namelen, type, id_str, NFS_UINT_MAXLEN);
+ data_size = nfs_idmap_get_key(name, namelen, type, id_str, NFS_UINT_MAXLEN, idmap);
if (data_size <= 0) {
ret = -EINVAL;
} else {
@@ -327,114 +351,103 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen,
return ret;
}
-int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
-{
- if (nfs_map_string_to_numeric(name, namelen, uid))
- return 0;
- return nfs_idmap_lookup_id(name, namelen, "uid", uid);
-}
-
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
-{
- if (nfs_map_string_to_numeric(name, namelen, gid))
- return 0;
- return nfs_idmap_lookup_id(name, namelen, "gid", gid);
-}
-
-int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
-{
- int ret = -EINVAL;
-
- if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
- ret = nfs_idmap_lookup_name(uid, "user", buf, buflen);
- if (ret < 0)
- ret = nfs_map_numeric_to_string(uid, buf, buflen);
- return ret;
-}
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
-{
- int ret = -EINVAL;
+/* idmap classic begins here */
+module_param(nfs_idmap_cache_timeout, int, 0644);
- if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
- ret = nfs_idmap_lookup_name(gid, "group", buf, buflen);
- if (ret < 0)
- ret = nfs_map_numeric_to_string(gid, buf, buflen);
- return ret;
-}
-
-#else /* CONFIG_NFS_USE_NEW_IDMAPPER not defined */
-
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/init.h>
-#include <linux/socket.h>
-#include <linux/in.h>
-#include <linux/sched.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/workqueue.h>
-#include <linux/sunrpc/rpc_pipe_fs.h>
-
-#include <linux/nfs_fs.h>
-
-#include "nfs4_fs.h"
-
-#define IDMAP_HASH_SZ 128
-
-/* Default cache timeout is 10 minutes */
-unsigned int nfs_idmap_cache_timeout = 600 * HZ;
-
-static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
-{
- char *endp;
- int num = simple_strtol(val, &endp, 0);
- int jif = num * HZ;
- if (endp == val || *endp || num < 0 || jif < num)
- return -EINVAL;
- *((int *)kp->arg) = jif;
- return 0;
-}
-
-module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
- &nfs_idmap_cache_timeout, 0644);
-
-struct idmap_hashent {
- unsigned long ih_expires;
- __u32 ih_id;
- size_t ih_namelen;
- char ih_name[IDMAP_NAMESZ];
+struct idmap {
+ struct rpc_pipe *idmap_pipe;
+ struct key_construction *idmap_key_cons;
};
-struct idmap_hashtable {
- __u8 h_type;
- struct idmap_hashent h_entries[IDMAP_HASH_SZ];
+enum {
+ Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err
};
-struct idmap {
- struct dentry *idmap_dentry;
- wait_queue_head_t idmap_wq;
- struct idmap_msg idmap_im;
- struct mutex idmap_lock; /* Serializes upcalls */
- struct mutex idmap_im_lock; /* Protects the hashtable */
- struct idmap_hashtable idmap_user_hash;
- struct idmap_hashtable idmap_group_hash;
+static const match_table_t nfs_idmap_tokens = {
+ { Opt_find_uid, "uid:%s" },
+ { Opt_find_gid, "gid:%s" },
+ { Opt_find_user, "user:%s" },
+ { Opt_find_group, "group:%s" },
+ { Opt_find_err, NULL }
};
+static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
size_t);
static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
-static unsigned int fnvhash32(const void *, size_t);
-
static const struct rpc_pipe_ops idmap_upcall_ops = {
.upcall = rpc_pipe_generic_upcall,
.downcall = idmap_pipe_downcall,
.destroy_msg = idmap_pipe_destroy_msg,
};
+static struct key_type key_type_id_resolver_legacy = {
+ .name = "id_resolver",
+ .instantiate = user_instantiate,
+ .match = user_match,
+ .revoke = user_revoke,
+ .destroy = user_destroy,
+ .describe = user_describe,
+ .read = user_read,
+ .request_key = nfs_idmap_legacy_upcall,
+};
+
+static void __nfs_idmap_unregister(struct rpc_pipe *pipe)
+{
+ if (pipe->dentry)
+ rpc_unlink(pipe->dentry);
+}
+
+static int __nfs_idmap_register(struct dentry *dir,
+ struct idmap *idmap,
+ struct rpc_pipe *pipe)
+{
+ struct dentry *dentry;
+
+ dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+ pipe->dentry = dentry;
+ return 0;
+}
+
+static void nfs_idmap_unregister(struct nfs_client *clp,
+ struct rpc_pipe *pipe)
+{
+ struct net *net = clp->net;
+ struct super_block *pipefs_sb;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (pipefs_sb) {
+ __nfs_idmap_unregister(pipe);
+ rpc_put_sb_net(net);
+ }
+}
+
+static int nfs_idmap_register(struct nfs_client *clp,
+ struct idmap *idmap,
+ struct rpc_pipe *pipe)
+{
+ struct net *net = clp->net;
+ struct super_block *pipefs_sb;
+ int err = 0;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (pipefs_sb) {
+ if (clp->cl_rpcclient->cl_dentry)
+ err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
+ idmap, pipe);
+ rpc_put_sb_net(net);
+ }
+ return err;
+}
+
int
nfs_idmap_new(struct nfs_client *clp)
{
struct idmap *idmap;
+ struct rpc_pipe *pipe;
int error;
BUG_ON(clp->cl_idmap != NULL);
@@ -443,19 +456,19 @@ nfs_idmap_new(struct nfs_client *clp)
if (idmap == NULL)
return -ENOMEM;
- idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry,
- "idmap", idmap, &idmap_upcall_ops, 0);
- if (IS_ERR(idmap->idmap_dentry)) {
- error = PTR_ERR(idmap->idmap_dentry);
+ pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0);
+ if (IS_ERR(pipe)) {
+ error = PTR_ERR(pipe);
kfree(idmap);
return error;
}
-
- mutex_init(&idmap->idmap_lock);
- mutex_init(&idmap->idmap_im_lock);
- init_waitqueue_head(&idmap->idmap_wq);
- idmap->idmap_user_hash.h_type = IDMAP_TYPE_USER;
- idmap->idmap_group_hash.h_type = IDMAP_TYPE_GROUP;
+ error = nfs_idmap_register(clp, idmap, pipe);
+ if (error) {
+ rpc_destroy_pipe_data(pipe);
+ kfree(idmap);
+ return error;
+ }
+ idmap->idmap_pipe = pipe;
clp->cl_idmap = idmap;
return 0;
@@ -468,211 +481,220 @@ nfs_idmap_delete(struct nfs_client *clp)
if (!idmap)
return;
- rpc_unlink(idmap->idmap_dentry);
+ nfs_idmap_unregister(clp, idmap->idmap_pipe);
+ rpc_destroy_pipe_data(idmap->idmap_pipe);
clp->cl_idmap = NULL;
kfree(idmap);
}
-/*
- * Helper routines for manipulating the hashtable
- */
-static inline struct idmap_hashent *
-idmap_name_hash(struct idmap_hashtable* h, const char *name, size_t len)
-{
- return &h->h_entries[fnvhash32(name, len) % IDMAP_HASH_SZ];
-}
-
-static struct idmap_hashent *
-idmap_lookup_name(struct idmap_hashtable *h, const char *name, size_t len)
+static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event,
+ struct super_block *sb)
{
- struct idmap_hashent *he = idmap_name_hash(h, name, len);
+ int err = 0;
- if (he->ih_namelen != len || memcmp(he->ih_name, name, len) != 0)
- return NULL;
- if (time_after(jiffies, he->ih_expires))
- return NULL;
- return he;
+ switch (event) {
+ case RPC_PIPEFS_MOUNT:
+ BUG_ON(clp->cl_rpcclient->cl_dentry == NULL);
+ err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
+ clp->cl_idmap,
+ clp->cl_idmap->idmap_pipe);
+ break;
+ case RPC_PIPEFS_UMOUNT:
+ if (clp->cl_idmap->idmap_pipe) {
+ struct dentry *parent;
+
+ parent = clp->cl_idmap->idmap_pipe->dentry->d_parent;
+ __nfs_idmap_unregister(clp->cl_idmap->idmap_pipe);
+ /*
+ * Note: This is a dirty hack. SUNRPC hook has been
+ * called already but simple_rmdir() call for the
+ * directory returned with error because of idmap pipe
+ * inside. Thus now we have to remove this directory
+ * here.
+ */
+ if (rpc_rmdir(parent))
+ printk(KERN_ERR "NFS: %s: failed to remove "
+ "clnt dir!\n", __func__);
+ }
+ break;
+ default:
+ printk(KERN_ERR "NFS: %s: unknown event: %ld\n", __func__,
+ event);
+ return -ENOTSUPP;
+ }
+ return err;
+}
+
+static struct nfs_client *nfs_get_client_for_event(struct net *net, int event)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct dentry *cl_dentry;
+ struct nfs_client *clp;
+
+ spin_lock(&nn->nfs_client_lock);
+ list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+ if (clp->rpc_ops != &nfs_v4_clientops)
+ continue;
+ cl_dentry = clp->cl_idmap->idmap_pipe->dentry;
+ if (((event == RPC_PIPEFS_MOUNT) && cl_dentry) ||
+ ((event == RPC_PIPEFS_UMOUNT) && !cl_dentry))
+ continue;
+ atomic_inc(&clp->cl_count);
+ spin_unlock(&nn->nfs_client_lock);
+ return clp;
+ }
+ spin_unlock(&nn->nfs_client_lock);
+ return NULL;
}
-static inline struct idmap_hashent *
-idmap_id_hash(struct idmap_hashtable* h, __u32 id)
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+ void *ptr)
{
- return &h->h_entries[fnvhash32(&id, sizeof(id)) % IDMAP_HASH_SZ];
-}
+ struct super_block *sb = ptr;
+ struct nfs_client *clp;
+ int error = 0;
-static struct idmap_hashent *
-idmap_lookup_id(struct idmap_hashtable *h, __u32 id)
-{
- struct idmap_hashent *he = idmap_id_hash(h, id);
- if (he->ih_id != id || he->ih_namelen == 0)
- return NULL;
- if (time_after(jiffies, he->ih_expires))
- return NULL;
- return he;
+ while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) {
+ error = __rpc_pipefs_event(clp, event, sb);
+ nfs_put_client(clp);
+ if (error)
+ break;
+ }
+ return error;
}
-/*
- * Routines for allocating new entries in the hashtable.
- * For now, we just have 1 entry per bucket, so it's all
- * pretty trivial.
- */
-static inline struct idmap_hashent *
-idmap_alloc_name(struct idmap_hashtable *h, char *name, size_t len)
-{
- return idmap_name_hash(h, name, len);
-}
+#define PIPEFS_NFS_PRIO 1
+
+static struct notifier_block nfs_idmap_block = {
+ .notifier_call = rpc_pipefs_event,
+ .priority = SUNRPC_PIPEFS_NFS_PRIO,
+};
-static inline struct idmap_hashent *
-idmap_alloc_id(struct idmap_hashtable *h, __u32 id)
+int nfs_idmap_init(void)
{
- return idmap_id_hash(h, id);
+ int ret;
+ ret = nfs_idmap_init_keyring();
+ if (ret != 0)
+ goto out;
+ ret = rpc_pipefs_notifier_register(&nfs_idmap_block);
+ if (ret != 0)
+ nfs_idmap_quit_keyring();
+out:
+ return ret;
}
-static void
-idmap_update_entry(struct idmap_hashent *he, const char *name,
- size_t namelen, __u32 id)
+void nfs_idmap_quit(void)
{
- he->ih_id = id;
- memcpy(he->ih_name, name, namelen);
- he->ih_name[namelen] = '\0';
- he->ih_namelen = namelen;
- he->ih_expires = jiffies + nfs_idmap_cache_timeout;
+ rpc_pipefs_notifier_unregister(&nfs_idmap_block);
+ nfs_idmap_quit_keyring();
}
-/*
- * Name -> ID
- */
-static int
-nfs_idmap_id(struct idmap *idmap, struct idmap_hashtable *h,
- const char *name, size_t namelen, __u32 *id)
+static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im,
+ struct rpc_pipe_msg *msg)
{
- struct rpc_pipe_msg msg;
- struct idmap_msg *im;
- struct idmap_hashent *he;
- DECLARE_WAITQUEUE(wq, current);
- int ret = -EIO;
-
- im = &idmap->idmap_im;
-
- /*
- * String sanity checks
- * Note that the userland daemon expects NUL terminated strings
- */
- for (;;) {
- if (namelen == 0)
- return -EINVAL;
- if (name[namelen-1] != '\0')
- break;
- namelen--;
- }
- if (namelen >= IDMAP_NAMESZ)
- return -EINVAL;
+ substring_t substr;
+ int token, ret;
- mutex_lock(&idmap->idmap_lock);
- mutex_lock(&idmap->idmap_im_lock);
-
- he = idmap_lookup_name(h, name, namelen);
- if (he != NULL) {
- *id = he->ih_id;
- ret = 0;
- goto out;
- }
+ memset(im, 0, sizeof(*im));
+ memset(msg, 0, sizeof(*msg));
- memset(im, 0, sizeof(*im));
- memcpy(im->im_name, name, namelen);
+ im->im_type = IDMAP_TYPE_GROUP;
+ token = match_token(desc, nfs_idmap_tokens, &substr);
- im->im_type = h->h_type;
- im->im_conv = IDMAP_CONV_NAMETOID;
+ switch (token) {
+ case Opt_find_uid:
+ im->im_type = IDMAP_TYPE_USER;
+ case Opt_find_gid:
+ im->im_conv = IDMAP_CONV_NAMETOID;
+ ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ);
+ break;
- memset(&msg, 0, sizeof(msg));
- msg.data = im;
- msg.len = sizeof(*im);
+ case Opt_find_user:
+ im->im_type = IDMAP_TYPE_USER;
+ case Opt_find_group:
+ im->im_conv = IDMAP_CONV_IDTONAME;
+ ret = match_int(&substr, &im->im_id);
+ break;
- add_wait_queue(&idmap->idmap_wq, &wq);
- if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
- remove_wait_queue(&idmap->idmap_wq, &wq);
+ default:
+ ret = -EINVAL;
goto out;
}
- set_current_state(TASK_UNINTERRUPTIBLE);
- mutex_unlock(&idmap->idmap_im_lock);
- schedule();
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&idmap->idmap_wq, &wq);
- mutex_lock(&idmap->idmap_im_lock);
+ msg->data = im;
+ msg->len = sizeof(struct idmap_msg);
- if (im->im_status & IDMAP_STATUS_SUCCESS) {
- *id = im->im_id;
- ret = 0;
- }
-
- out:
- memset(im, 0, sizeof(*im));
- mutex_unlock(&idmap->idmap_im_lock);
- mutex_unlock(&idmap->idmap_lock);
+out:
return ret;
}
-/*
- * ID -> Name
- */
-static int
-nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
- __u32 id, char *name)
+static int nfs_idmap_legacy_upcall(struct key_construction *cons,
+ const char *op,
+ void *aux)
{
- struct rpc_pipe_msg msg;
+ struct rpc_pipe_msg *msg;
struct idmap_msg *im;
- struct idmap_hashent *he;
- DECLARE_WAITQUEUE(wq, current);
- int ret = -EIO;
- unsigned int len;
-
- im = &idmap->idmap_im;
+ struct idmap *idmap = (struct idmap *)aux;
+ struct key *key = cons->key;
+ int ret;
- mutex_lock(&idmap->idmap_lock);
- mutex_lock(&idmap->idmap_im_lock);
+ /* msg and im are freed in idmap_pipe_destroy_msg */
+ msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+ if (IS_ERR(msg)) {
+ ret = PTR_ERR(msg);
+ goto out0;
+ }
- he = idmap_lookup_id(h, id);
- if (he) {
- memcpy(name, he->ih_name, he->ih_namelen);
- ret = he->ih_namelen;
- goto out;
+ im = kmalloc(sizeof(*im), GFP_KERNEL);
+ if (IS_ERR(im)) {
+ ret = PTR_ERR(im);
+ goto out1;
}
- memset(im, 0, sizeof(*im));
- im->im_type = h->h_type;
- im->im_conv = IDMAP_CONV_IDTONAME;
- im->im_id = id;
+ ret = nfs_idmap_prepare_message(key->description, im, msg);
+ if (ret < 0)
+ goto out2;
- memset(&msg, 0, sizeof(msg));
- msg.data = im;
- msg.len = sizeof(*im);
+ idmap->idmap_key_cons = cons;
- add_wait_queue(&idmap->idmap_wq, &wq);
+ ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
+ if (ret < 0)
+ goto out2;
- if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
- remove_wait_queue(&idmap->idmap_wq, &wq);
- goto out;
- }
+ return ret;
+
+out2:
+ kfree(im);
+out1:
+ kfree(msg);
+out0:
+ key_revoke(cons->key);
+ key_revoke(cons->authkey);
+ return ret;
+}
+
+static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data)
+{
+ return key_instantiate_and_link(key, data, strlen(data) + 1,
+ id_resolver_cache->thread_keyring,
+ authkey);
+}
- set_current_state(TASK_UNINTERRUPTIBLE);
- mutex_unlock(&idmap->idmap_im_lock);
- schedule();
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&idmap->idmap_wq, &wq);
- mutex_lock(&idmap->idmap_im_lock);
-
- if (im->im_status & IDMAP_STATUS_SUCCESS) {
- if ((len = strnlen(im->im_name, IDMAP_NAMESZ)) == 0)
- goto out;
- memcpy(name, im->im_name, len);
- ret = len;
+static int nfs_idmap_read_message(struct idmap_msg *im, struct key *key, struct key *authkey)
+{
+ char id_str[NFS_UINT_MAXLEN];
+ int ret = -EINVAL;
+
+ switch (im->im_conv) {
+ case IDMAP_CONV_NAMETOID:
+ sprintf(id_str, "%d", im->im_id);
+ ret = nfs_idmap_instantiate(key, authkey, id_str);
+ break;
+ case IDMAP_CONV_IDTONAME:
+ ret = nfs_idmap_instantiate(key, authkey, im->im_name);
+ break;
}
- out:
- memset(im, 0, sizeof(*im));
- mutex_unlock(&idmap->idmap_im_lock);
- mutex_unlock(&idmap->idmap_lock);
return ret;
}
@@ -681,115 +703,51 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
{
struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
struct idmap *idmap = (struct idmap *)rpci->private;
- struct idmap_msg im_in, *im = &idmap->idmap_im;
- struct idmap_hashtable *h;
- struct idmap_hashent *he = NULL;
+ struct key_construction *cons = idmap->idmap_key_cons;
+ struct idmap_msg im;
size_t namelen_in;
int ret;
- if (mlen != sizeof(im_in))
- return -ENOSPC;
-
- if (copy_from_user(&im_in, src, mlen) != 0)
- return -EFAULT;
-
- mutex_lock(&idmap->idmap_im_lock);
-
- ret = mlen;
- im->im_status = im_in.im_status;
- /* If we got an error, terminate now, and wake up pending upcalls */
- if (!(im_in.im_status & IDMAP_STATUS_SUCCESS)) {
- wake_up(&idmap->idmap_wq);
+ if (mlen != sizeof(im)) {
+ ret = -ENOSPC;
goto out;
}
- /* Sanity checking of strings */
- ret = -EINVAL;
- namelen_in = strnlen(im_in.im_name, IDMAP_NAMESZ);
- if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ)
+ if (copy_from_user(&im, src, mlen) != 0) {
+ ret = -EFAULT;
goto out;
+ }
- switch (im_in.im_type) {
- case IDMAP_TYPE_USER:
- h = &idmap->idmap_user_hash;
- break;
- case IDMAP_TYPE_GROUP:
- h = &idmap->idmap_group_hash;
- break;
- default:
- goto out;
+ if (!(im.im_status & IDMAP_STATUS_SUCCESS)) {
+ ret = mlen;
+ complete_request_key(idmap->idmap_key_cons, -ENOKEY);
+ goto out_incomplete;
}
- switch (im_in.im_conv) {
- case IDMAP_CONV_IDTONAME:
- /* Did we match the current upcall? */
- if (im->im_conv == IDMAP_CONV_IDTONAME
- && im->im_type == im_in.im_type
- && im->im_id == im_in.im_id) {
- /* Yes: copy string, including the terminating '\0' */
- memcpy(im->im_name, im_in.im_name, namelen_in);
- im->im_name[namelen_in] = '\0';
- wake_up(&idmap->idmap_wq);
- }
- he = idmap_alloc_id(h, im_in.im_id);
- break;
- case IDMAP_CONV_NAMETOID:
- /* Did we match the current upcall? */
- if (im->im_conv == IDMAP_CONV_NAMETOID
- && im->im_type == im_in.im_type
- && strnlen(im->im_name, IDMAP_NAMESZ) == namelen_in
- && memcmp(im->im_name, im_in.im_name, namelen_in) == 0) {
- im->im_id = im_in.im_id;
- wake_up(&idmap->idmap_wq);
- }
- he = idmap_alloc_name(h, im_in.im_name, namelen_in);
- break;
- default:
+ namelen_in = strnlen(im.im_name, IDMAP_NAMESZ);
+ if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
+ ret = -EINVAL;
goto out;
}
- /* If the entry is valid, also copy it to the cache */
- if (he != NULL)
- idmap_update_entry(he, im_in.im_name, namelen_in, im_in.im_id);
- ret = mlen;
+ ret = nfs_idmap_read_message(&im, cons->key, cons->authkey);
+ if (ret >= 0) {
+ key_set_timeout(cons->key, nfs_idmap_cache_timeout);
+ ret = mlen;
+ }
+
out:
- mutex_unlock(&idmap->idmap_im_lock);
+ complete_request_key(idmap->idmap_key_cons, ret);
+out_incomplete:
return ret;
}
static void
idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
{
- struct idmap_msg *im = msg->data;
- struct idmap *idmap = container_of(im, struct idmap, idmap_im);
-
- if (msg->errno >= 0)
- return;
- mutex_lock(&idmap->idmap_im_lock);
- im->im_status = IDMAP_STATUS_LOOKUPFAIL;
- wake_up(&idmap->idmap_wq);
- mutex_unlock(&idmap->idmap_im_lock);
-}
-
-/*
- * Fowler/Noll/Vo hash
- * http://www.isthe.com/chongo/tech/comp/fnv/
- */
-
-#define FNV_P_32 ((unsigned int)0x01000193) /* 16777619 */
-#define FNV_1_32 ((unsigned int)0x811c9dc5) /* 2166136261 */
-
-static unsigned int fnvhash32(const void *buf, size_t buflen)
-{
- const unsigned char *p, *end = (const unsigned char *)buf + buflen;
- unsigned int hash = FNV_1_32;
-
- for (p = buf; p < end; p++) {
- hash *= FNV_P_32;
- hash ^= (unsigned int)*p;
- }
-
- return hash;
+ /* Free memory allocated in nfs_idmap_legacy_upcall() */
+ kfree(msg->data);
+ kfree(msg);
}
int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
@@ -798,16 +756,16 @@ int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_
if (nfs_map_string_to_numeric(name, namelen, uid))
return 0;
- return nfs_idmap_id(idmap, &idmap->idmap_user_hash, name, namelen, uid);
+ return nfs_idmap_lookup_id(name, namelen, "uid", uid, idmap);
}
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
{
struct idmap *idmap = server->nfs_client->cl_idmap;
- if (nfs_map_string_to_numeric(name, namelen, uid))
+ if (nfs_map_string_to_numeric(name, namelen, gid))
return 0;
- return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
+ return nfs_idmap_lookup_id(name, namelen, "gid", gid, idmap);
}
int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
@@ -816,21 +774,19 @@ int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, s
int ret = -EINVAL;
if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
- ret = nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
+ ret = nfs_idmap_lookup_name(uid, "user", buf, buflen, idmap);
if (ret < 0)
ret = nfs_map_numeric_to_string(uid, buf, buflen);
return ret;
}
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
+int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
{
struct idmap *idmap = server->nfs_client->cl_idmap;
int ret = -EINVAL;
if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
- ret = nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
+ ret = nfs_idmap_lookup_name(gid, "group", buf, buflen, idmap);
if (ret < 0)
- ret = nfs_map_numeric_to_string(uid, buf, buflen);
+ ret = nfs_map_numeric_to_string(gid, buf, buflen);
return ret;
}
-
-#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f649fba..7bb4d13 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -39,6 +39,7 @@
#include <linux/slab.h>
#include <linux/compat.h>
#include <linux/freezer.h>
+#include <linux/crc32.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -51,6 +52,7 @@
#include "fscache.h"
#include "dns_resolve.h"
#include "pnfs.h"
+#include "netns.h"
#define NFSDBG_FACILITY NFSDBG_VFS
@@ -388,9 +390,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
unlock_new_inode(inode);
} else
nfs_refresh_inode(inode, fattr);
- dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
+ dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode),
+ nfs_display_fhandle_hash(fh),
atomic_read(&inode->i_count));
out:
@@ -401,7 +404,7 @@ out_no_inode:
goto out;
}
-#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE)
+#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
int
nfs_setattr(struct dentry *dentry, struct iattr *attr)
@@ -423,7 +426,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
/* Optimization: if the end result is no change, don't RPC */
attr->ia_valid &= NFS_VALID_ATTRS;
- if ((attr->ia_valid & ~ATTR_FILE) == 0)
+ if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
return 0;
/* Write all dirty data */
@@ -1044,6 +1047,67 @@ struct nfs_fh *nfs_alloc_fhandle(void)
return fh;
}
+#ifdef NFS_DEBUG
+/*
+ * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle
+ * in the same way that wireshark does
+ *
+ * @fh: file handle
+ *
+ * For debugging only.
+ */
+u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
+{
+ /* wireshark uses 32-bit AUTODIN crc and does a bitwise
+ * not on the result */
+ return ~crc32(0xFFFFFFFF, &fh->data[0], fh->size);
+}
+
+/*
+ * _nfs_display_fhandle - display an NFS file handle on the console
+ *
+ * @fh: file handle to display
+ * @caption: display caption
+ *
+ * For debugging only.
+ */
+void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption)
+{
+ unsigned short i;
+
+ if (fh == NULL || fh->size == 0) {
+ printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh);
+ return;
+ }
+
+ printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n",
+ caption, fh, fh->size, _nfs_display_fhandle_hash(fh));
+ for (i = 0; i < fh->size; i += 16) {
+ __be32 *pos = (__be32 *)&fh->data[i];
+
+ switch ((fh->size - i - 1) >> 2) {
+ case 0:
+ printk(KERN_DEFAULT " %08x\n",
+ be32_to_cpup(pos));
+ break;
+ case 1:
+ printk(KERN_DEFAULT " %08x %08x\n",
+ be32_to_cpup(pos), be32_to_cpup(pos + 1));
+ break;
+ case 2:
+ printk(KERN_DEFAULT " %08x %08x %08x\n",
+ be32_to_cpup(pos), be32_to_cpup(pos + 1),
+ be32_to_cpup(pos + 2));
+ break;
+ default:
+ printk(KERN_DEFAULT " %08x %08x %08x %08x\n",
+ be32_to_cpup(pos), be32_to_cpup(pos + 1),
+ be32_to_cpup(pos + 2), be32_to_cpup(pos + 3));
+ }
+ }
+}
+#endif
+
/**
* nfs_inode_attrs_need_update - check if the inode attributes need updating
* @inode - pointer to inode
@@ -1211,8 +1275,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
unsigned long now = jiffies;
unsigned long save_cache_validity;
- dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
+ dfprintk(VFS, "NFS: %s(%s/%ld fh_crc=0x%08x ct=%d info=0x%x)\n",
__func__, inode->i_sb->s_id, inode->i_ino,
+ nfs_display_fhandle_hash(NFS_FH(inode)),
atomic_read(&inode->i_count), fattr->valid);
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
@@ -1406,7 +1471,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
/*
* Big trouble! The inode has become a different object.
*/
- printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
+ printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
__func__, inode->i_ino, inode->i_mode, fattr->mode);
out_err:
/*
@@ -1495,7 +1560,7 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&nfsi->open_files);
INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
- INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
+ INIT_LIST_HEAD(&nfsi->commit_list);
nfsi->npages = 0;
nfsi->ncommit = 0;
atomic_set(&nfsi->silly_count, 1);
@@ -1552,6 +1617,28 @@ static void nfsiod_stop(void)
destroy_workqueue(wq);
}
+int nfs_net_id;
+EXPORT_SYMBOL_GPL(nfs_net_id);
+
+static int nfs_net_init(struct net *net)
+{
+ nfs_clients_init(net);
+ return nfs_dns_resolver_cache_init(net);
+}
+
+static void nfs_net_exit(struct net *net)
+{
+ nfs_dns_resolver_cache_destroy(net);
+ nfs_cleanup_cb_ident_idr(net);
+}
+
+static struct pernet_operations nfs_net_ops = {
+ .init = nfs_net_init,
+ .exit = nfs_net_exit,
+ .id = &nfs_net_id,
+ .size = sizeof(struct nfs_net),
+};
+
/*
* Initialize NFS
*/
@@ -1561,10 +1648,14 @@ static int __init init_nfs_fs(void)
err = nfs_idmap_init();
if (err < 0)
- goto out9;
+ goto out10;
err = nfs_dns_resolver_init();
if (err < 0)
+ goto out9;
+
+ err = register_pernet_subsys(&nfs_net_ops);
+ if (err < 0)
goto out8;
err = nfs_fscache_register();
@@ -1600,14 +1691,14 @@ static int __init init_nfs_fs(void)
goto out0;
#ifdef CONFIG_PROC_FS
- rpc_proc_register(&nfs_rpcstat);
+ rpc_proc_register(&init_net, &nfs_rpcstat);
#endif
if ((err = register_nfs_fs()) != 0)
goto out;
return 0;
out:
#ifdef CONFIG_PROC_FS
- rpc_proc_unregister("nfs");
+ rpc_proc_unregister(&init_net, "nfs");
#endif
nfs_destroy_directcache();
out0:
@@ -1625,10 +1716,12 @@ out5:
out6:
nfs_fscache_unregister();
out7:
- nfs_dns_resolver_destroy();
+ unregister_pernet_subsys(&nfs_net_ops);
out8:
- nfs_idmap_quit();
+ nfs_dns_resolver_destroy();
out9:
+ nfs_idmap_quit();
+out10:
return err;
}
@@ -1640,12 +1733,12 @@ static void __exit exit_nfs_fs(void)
nfs_destroy_inodecache();
nfs_destroy_nfspagecache();
nfs_fscache_unregister();
+ unregister_pernet_subsys(&nfs_net_ops);
nfs_dns_resolver_destroy();
nfs_idmap_quit();
#ifdef CONFIG_PROC_FS
- rpc_proc_unregister("nfs");
+ rpc_proc_unregister(&init_net, "nfs");
#endif
- nfs_cleanup_cb_ident_idr();
unregister_nfs_fs();
nfs_fs_proc_exit();
nfsiod_stop();
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8102db9..2476dc6 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -123,6 +123,7 @@ struct nfs_parsed_mount_data {
} nfs_server;
struct security_mnt_opts lsm_opts;
+ struct net *net;
};
/* mount_clnt.c */
@@ -137,20 +138,22 @@ struct nfs_mount_request {
int noresvport;
unsigned int *auth_flav_len;
rpc_authflavor_t *auth_flavs;
+ struct net *net;
};
extern int nfs_mount(struct nfs_mount_request *info);
extern void nfs_umount(const struct nfs_mount_request *info);
/* client.c */
-extern struct rpc_program nfs_program;
+extern const struct rpc_program nfs_program;
+extern void nfs_clients_init(struct net *net);
-extern void nfs_cleanup_cb_ident_idr(void);
+extern void nfs_cleanup_cb_ident_idr(struct net *);
extern void nfs_put_client(struct nfs_client *);
-extern struct nfs_client *nfs4_find_client_no_ident(const struct sockaddr *);
-extern struct nfs_client *nfs4_find_client_ident(int);
+extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
extern struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *);
+nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
+ struct nfs4_sessionid *);
extern struct nfs_server *nfs_create_server(
const struct nfs_parsed_mount_data *,
struct nfs_fh *);
@@ -329,6 +332,8 @@ void nfs_retry_commit(struct list_head *page_list,
void nfs_commit_clear_lock(struct nfs_inode *nfsi);
void nfs_commitdata_release(void *data);
void nfs_commit_release_pages(struct nfs_write_data *data);
+void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head);
+void nfs_request_remove_commit_list(struct nfs_page *req);
#ifdef CONFIG_MIGRATION
extern int nfs_migrate_page(struct address_space *,
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d4c2d6b..8e65c7f 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -16,7 +16,7 @@
#include <linux/nfs_fs.h>
#include "internal.h"
-#ifdef RPC_DEBUG
+#ifdef NFS_DEBUG
# define NFSDBG_FACILITY NFSDBG_MOUNT
#endif
@@ -67,7 +67,7 @@ enum {
MOUNTPROC3_EXPORT = 5,
};
-static struct rpc_program mnt_program;
+static const struct rpc_program mnt_program;
/*
* Defined by OpenGroup XNFS Version 3W, chapter 8
@@ -153,7 +153,7 @@ int nfs_mount(struct nfs_mount_request *info)
.rpc_resp = &result,
};
struct rpc_create_args args = {
- .net = &init_net,
+ .net = info->net,
.protocol = info->protocol,
.address = info->sap,
.addrsize = info->salen,
@@ -225,7 +225,7 @@ void nfs_umount(const struct nfs_mount_request *info)
.to_retries = 2,
};
struct rpc_create_args args = {
- .net = &init_net,
+ .net = info->net,
.protocol = IPPROTO_UDP,
.address = info->sap,
.addrsize = info->salen,
@@ -488,19 +488,19 @@ static struct rpc_procinfo mnt3_procedures[] = {
};
-static struct rpc_version mnt_version1 = {
+static const struct rpc_version mnt_version1 = {
.number = 1,
.nrprocs = ARRAY_SIZE(mnt_procedures),
.procs = mnt_procedures,
};
-static struct rpc_version mnt_version3 = {
+static const struct rpc_version mnt_version3 = {
.number = 3,
.nrprocs = ARRAY_SIZE(mnt3_procedures),
.procs = mnt3_procedures,
};
-static struct rpc_version *mnt_version[] = {
+static const struct rpc_version *mnt_version[] = {
NULL,
&mnt_version1,
NULL,
@@ -509,7 +509,7 @@ static struct rpc_version *mnt_version[] = {
static struct rpc_stat mnt_stats;
-static struct rpc_program mnt_program = {
+static const struct rpc_program mnt_program = {
.name = "mount",
.number = NFS_MNT_PROGRAM,
.nrvers = ARRAY_SIZE(mnt_version),
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 8102391..1807866 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -276,7 +276,10 @@ out:
nfs_free_fattr(fattr);
nfs_free_fhandle(fh);
out_nofree:
- dprintk("<-- nfs_follow_mountpoint() = %p\n", mnt);
+ if (IS_ERR(mnt))
+ dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
+ else
+ dprintk("<-- %s() = %p\n", __func__, mnt);
return mnt;
}
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
new file mode 100644
index 0000000..aa14ec3
--- /dev/null
+++ b/fs/nfs/netns.h
@@ -0,0 +1,27 @@
+#ifndef __NFS_NETNS_H__
+#define __NFS_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct bl_dev_msg {
+ int32_t status;
+ uint32_t major, minor;
+};
+
+struct nfs_net {
+ struct cache_detail *nfs_dns_resolve;
+ struct rpc_pipe *bl_device_pipe;
+ struct bl_dev_msg bl_mount_reply;
+ wait_queue_head_t bl_wq;
+ struct list_head nfs_client_list;
+ struct list_head nfs_volume_list;
+#ifdef CONFIG_NFS_V4
+ struct idr cb_ident_idr; /* Protected by nfs_client_lock */
+#endif
+ spinlock_t nfs_client_lock;
+};
+
+extern int nfs_net_id;
+
+#endif
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 792cb13..1f56000 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -1150,7 +1150,7 @@ struct rpc_procinfo nfs_procedures[] = {
PROC(STATFS, fhandle, statfsres, 0),
};
-struct rpc_version nfs_version2 = {
+const struct rpc_version nfs_version2 = {
.number = 2,
.nrprocs = ARRAY_SIZE(nfs_procedures),
.procs = nfs_procedures
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 7ef2397..e4498dc 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -192,7 +192,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
.pages = pages,
};
struct nfs3_getaclres res = {
- 0
+ NULL,
};
struct rpc_message msg = {
.rpc_argp = &args,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 9194395..5242eae 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -428,6 +428,11 @@ nfs3_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
msg->rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE];
}
+static void nfs3_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+ rpc_call_start(task);
+}
+
static int
nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir)
{
@@ -445,6 +450,11 @@ nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME];
}
+static void nfs3_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+ rpc_call_start(task);
+}
+
static int
nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
struct inode *new_dir)
@@ -814,6 +824,11 @@ static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message
msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
}
+static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+ rpc_call_start(task);
+}
+
static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
{
if (nfs3_async_handle_jukebox(task, data->inode))
@@ -828,6 +843,11 @@ static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
}
+static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+ rpc_call_start(task);
+}
+
static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
{
if (nfs3_async_handle_jukebox(task, data->inode))
@@ -864,9 +884,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.create = nfs3_proc_create,
.remove = nfs3_proc_remove,
.unlink_setup = nfs3_proc_unlink_setup,
+ .unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
.unlink_done = nfs3_proc_unlink_done,
.rename = nfs3_proc_rename,
.rename_setup = nfs3_proc_rename_setup,
+ .rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
.rename_done = nfs3_proc_rename_done,
.link = nfs3_proc_link,
.symlink = nfs3_proc_symlink,
@@ -879,8 +901,10 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.pathconf = nfs3_proc_pathconf,
.decode_dirent = nfs3_decode_dirent,
.read_setup = nfs3_proc_read_setup,
+ .read_rpc_prepare = nfs3_proc_read_rpc_prepare,
.read_done = nfs3_read_done,
.write_setup = nfs3_proc_write_setup,
+ .write_rpc_prepare = nfs3_proc_write_rpc_prepare,
.write_done = nfs3_write_done,
.commit_setup = nfs3_proc_commit_setup,
.commit_done = nfs3_commit_done,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 183c6b1..a77cc9a 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2461,7 +2461,7 @@ struct rpc_procinfo nfs3_procedures[] = {
PROC(COMMIT, commit, commit, 5),
};
-struct rpc_version nfs_version3 = {
+const struct rpc_version nfs_version3 = {
.number = 3,
.nrprocs = ARRAY_SIZE(nfs3_procedures),
.procs = nfs3_procedures
@@ -2489,7 +2489,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = {
},
};
-struct rpc_version nfsacl_version3 = {
+const struct rpc_version nfsacl_version3 = {
.number = 3,
.nrprocs = sizeof(nfs3_acl_procedures)/
sizeof(nfs3_acl_procedures[0]),
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4d7d0ae..97ecc86 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -20,7 +20,6 @@ enum nfs4_client_state {
NFS4CLNT_RECLAIM_REBOOT,
NFS4CLNT_RECLAIM_NOGRACE,
NFS4CLNT_DELEGRETURN,
- NFS4CLNT_LAYOUTRECALL,
NFS4CLNT_SESSION_RESET,
NFS4CLNT_RECALL_SLOT,
NFS4CLNT_LEASE_CONFIRM,
@@ -44,7 +43,7 @@ struct nfs4_minor_version_ops {
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
int cache_reply);
- int (*validate_stateid)(struct nfs_delegation *,
+ bool (*match_stateid)(const nfs4_stateid *,
const nfs4_stateid *);
int (*find_root_sec)(struct nfs_server *, struct nfs_fh *,
struct nfs_fsinfo *);
@@ -53,26 +52,25 @@ struct nfs4_minor_version_ops {
const struct nfs4_state_maintenance_ops *state_renewal_ops;
};
-/*
- * struct rpc_sequence ensures that RPC calls are sent in the exact
- * order that they appear on the list.
- */
-struct rpc_sequence {
- struct rpc_wait_queue wait; /* RPC call delay queue */
- spinlock_t lock; /* Protects the list */
- struct list_head list; /* Defines sequence of RPC calls */
+struct nfs_unique_id {
+ struct rb_node rb_node;
+ __u64 id;
};
#define NFS_SEQID_CONFIRMED 1
struct nfs_seqid_counter {
- struct rpc_sequence *sequence;
+ int owner_id;
int flags;
u32 counter;
+ spinlock_t lock; /* Protects the list */
+ struct list_head list; /* Defines sequence of RPC calls */
+ struct rpc_wait_queue wait; /* RPC call delay queue */
};
struct nfs_seqid {
struct nfs_seqid_counter *sequence;
struct list_head list;
+ struct rpc_task *task;
};
static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status)
@@ -81,18 +79,12 @@ static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status
seqid->flags |= NFS_SEQID_CONFIRMED;
}
-struct nfs_unique_id {
- struct rb_node rb_node;
- __u64 id;
-};
-
/*
* NFS4 state_owners and lock_owners are simply labels for ordered
* sequences of RPC calls. Their sole purpose is to provide once-only
* semantics by allowing the server to identify replayed requests.
*/
struct nfs4_state_owner {
- struct nfs_unique_id so_owner_id;
struct nfs_server *so_server;
struct list_head so_lru;
unsigned long so_expires;
@@ -105,7 +97,6 @@ struct nfs4_state_owner {
unsigned long so_flags;
struct list_head so_states;
struct nfs_seqid_counter so_seqid;
- struct rpc_sequence so_sequence;
};
enum {
@@ -146,8 +137,6 @@ struct nfs4_lock_state {
#define NFS_LOCK_INITIALIZED 1
int ls_flags;
struct nfs_seqid_counter ls_seqid;
- struct rpc_sequence ls_sequence;
- struct nfs_unique_id ls_id;
nfs4_stateid ls_stateid;
atomic_t ls_count;
struct nfs4_lock_owner ls_owner;
@@ -193,6 +182,7 @@ struct nfs4_exception {
long timeout;
int retry;
struct nfs4_state *state;
+ struct inode *inode;
};
struct nfs4_state_recovery_ops {
@@ -224,7 +214,7 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, boo
extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
struct nfs4_fs_locations *fs_locations, struct page *page);
-extern void nfs4_release_lockowner(const struct nfs4_lock_state *);
+extern int nfs4_release_lockowner(struct nfs4_lock_state *);
extern const struct xattr_handler *nfs4_xattr_handlers[];
#if defined(CONFIG_NFS_V4_1)
@@ -233,12 +223,13 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
return server->nfs_client->cl_session;
}
+extern bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy);
extern int nfs4_setup_sequence(const struct nfs_server *server,
struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
- int cache_reply, struct rpc_task *task);
+ struct rpc_task *task);
extern int nfs41_setup_sequence(struct nfs4_session *session,
struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
- int cache_reply, struct rpc_task *task);
+ struct rpc_task *task);
extern void nfs4_destroy_session(struct nfs4_session *session);
extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
extern int nfs4_proc_create_session(struct nfs_client *);
@@ -269,7 +260,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
static inline int nfs4_setup_sequence(const struct nfs_server *server,
struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
- int cache_reply, struct rpc_task *task)
+ struct rpc_task *task)
{
return 0;
}
@@ -319,7 +310,7 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
}
#endif /* CONFIG_NFS_V4_1 */
-extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
+extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t);
extern void nfs4_put_state_owner(struct nfs4_state_owner *);
extern void nfs4_purge_state_owners(struct nfs_server *);
extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
@@ -327,6 +318,8 @@ extern void nfs4_put_open_state(struct nfs4_state *);
extern void nfs4_close_state(struct nfs4_state *, fmode_t);
extern void nfs4_close_sync(struct nfs4_state *, fmode_t);
extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
+extern void nfs_inode_find_state_and_recover(struct inode *inode,
+ const nfs4_stateid *stateid);
extern void nfs4_schedule_lease_recovery(struct nfs_client *);
extern void nfs4_schedule_state_manager(struct nfs_client *);
extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
@@ -337,7 +330,8 @@ extern void nfs41_handle_server_scope(struct nfs_client *,
struct server_scope **);
extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t, pid_t);
+extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
+ fmode_t, fl_owner_t, pid_t);
extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -346,6 +340,8 @@ extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
extern void nfs_release_seqid(struct nfs_seqid *seqid);
extern void nfs_free_seqid(struct nfs_seqid *seqid);
+extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
+
extern const nfs4_stateid zero_stateid;
/* nfs4xdr.c */
@@ -357,6 +353,16 @@ struct nfs4_mount_data;
extern struct svc_version nfs4_callback_version1;
extern struct svc_version nfs4_callback_version4;
+static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
+{
+ memcpy(dst, src, sizeof(*dst));
+}
+
+static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src)
+{
+ return memcmp(dst, src, sizeof(*dst)) == 0;
+}
+
#else
#define nfs4_close_state(a, b) do { } while (0)
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 71ec086..634c0bc 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -33,7 +33,10 @@
#include <linux/nfs_page.h>
#include <linux/module.h>
+#include <linux/sunrpc/metrics.h>
+
#include "internal.h"
+#include "delegation.h"
#include "nfs4filelayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
@@ -84,12 +87,27 @@ static int filelayout_async_handle_error(struct rpc_task *task,
struct nfs_client *clp,
int *reset)
{
+ struct nfs_server *mds_server = NFS_SERVER(state->inode);
+ struct nfs_client *mds_client = mds_server->nfs_client;
+
if (task->tk_status >= 0)
return 0;
-
*reset = 0;
switch (task->tk_status) {
+ /* MDS state errors */
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_BAD_STATEID:
+ nfs_remove_bad_delegation(state->inode);
+ case -NFS4ERR_OPENMODE:
+ nfs4_schedule_stateid_recovery(mds_server, state);
+ goto wait_on_recovery;
+ case -NFS4ERR_EXPIRED:
+ nfs4_schedule_stateid_recovery(mds_server, state);
+ nfs4_schedule_lease_recovery(mds_client);
+ goto wait_on_recovery;
+ /* DS session errors */
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
@@ -115,8 +133,14 @@ static int filelayout_async_handle_error(struct rpc_task *task,
*reset = 1;
break;
}
+out:
task->tk_status = 0;
return -EAGAIN;
+wait_on_recovery:
+ rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
+ if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
+ rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
+ goto out;
}
/* NFS_PROTO call done callback routines */
@@ -173,7 +197,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
&rdata->args.seq_args, &rdata->res.seq_res,
- 0, task))
+ task))
return;
rpc_call_start(task);
@@ -189,10 +213,18 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
rdata->mds_ops->rpc_call_done(task, data);
}
+static void filelayout_read_count_stats(struct rpc_task *task, void *data)
+{
+ struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+
+ rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics);
+}
+
static void filelayout_read_release(void *data)
{
struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+ put_lseg(rdata->lseg);
rdata->mds_ops->rpc_release(data);
}
@@ -254,7 +286,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
&wdata->args.seq_args, &wdata->res.seq_res,
- 0, task))
+ task))
return;
rpc_call_start(task);
@@ -268,10 +300,18 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
wdata->mds_ops->rpc_call_done(task, data);
}
+static void filelayout_write_count_stats(struct rpc_task *task, void *data)
+{
+ struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+
+ rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics);
+}
+
static void filelayout_write_release(void *data)
{
struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+ put_lseg(wdata->lseg);
wdata->mds_ops->rpc_release(data);
}
@@ -282,24 +322,28 @@ static void filelayout_commit_release(void *data)
nfs_commit_release_pages(wdata);
if (atomic_dec_and_test(&NFS_I(wdata->inode)->commits_outstanding))
nfs_commit_clear_lock(NFS_I(wdata->inode));
+ put_lseg(wdata->lseg);
nfs_commitdata_release(wdata);
}
-struct rpc_call_ops filelayout_read_call_ops = {
+static const struct rpc_call_ops filelayout_read_call_ops = {
.rpc_call_prepare = filelayout_read_prepare,
.rpc_call_done = filelayout_read_call_done,
+ .rpc_count_stats = filelayout_read_count_stats,
.rpc_release = filelayout_read_release,
};
-struct rpc_call_ops filelayout_write_call_ops = {
+static const struct rpc_call_ops filelayout_write_call_ops = {
.rpc_call_prepare = filelayout_write_prepare,
.rpc_call_done = filelayout_write_call_done,
+ .rpc_count_stats = filelayout_write_count_stats,
.rpc_release = filelayout_write_release,
};
-struct rpc_call_ops filelayout_commit_call_ops = {
+static const struct rpc_call_ops filelayout_commit_call_ops = {
.rpc_call_prepare = filelayout_write_prepare,
.rpc_call_done = filelayout_write_call_done,
+ .rpc_count_stats = filelayout_write_count_stats,
.rpc_release = filelayout_commit_release,
};
@@ -367,7 +411,8 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
idx = nfs4_fl_calc_ds_index(lseg, j);
ds = nfs4_fl_prepare_ds(lseg, idx);
if (!ds) {
- printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+ printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
+ __func__);
set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
return PNFS_NOT_ATTEMPTED;
@@ -575,7 +620,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
goto out_err_free;
fl->fh_array[i]->size = be32_to_cpup(p++);
if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
- printk(KERN_ERR "Too big fh %d received %d\n",
+ printk(KERN_ERR "NFS: Too big fh %d received %d\n",
i, fl->fh_array[i]->size);
goto out_err_free;
}
@@ -640,14 +685,16 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
int size = (fl->stripe_type == STRIPE_SPARSE) ?
fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
- fl->commit_buckets = kcalloc(size, sizeof(struct list_head), gfp_flags);
+ fl->commit_buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), gfp_flags);
if (!fl->commit_buckets) {
filelayout_free_lseg(&fl->generic_hdr);
return NULL;
}
fl->number_of_buckets = size;
- for (i = 0; i < size; i++)
- INIT_LIST_HEAD(&fl->commit_buckets[i]);
+ for (i = 0; i < size; i++) {
+ INIT_LIST_HEAD(&fl->commit_buckets[i].written);
+ INIT_LIST_HEAD(&fl->commit_buckets[i].committing);
+ }
}
return &fl->generic_hdr;
}
@@ -679,7 +726,7 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
return (p_stripe == r_stripe);
}
-void
+static void
filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
@@ -696,7 +743,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
nfs_pageio_reset_read_mds(pgio);
}
-void
+static void
filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
@@ -725,11 +772,6 @@ static const struct nfs_pageio_ops filelayout_pg_write_ops = {
.pg_doio = pnfs_generic_pg_writepages,
};
-static bool filelayout_mark_pnfs_commit(struct pnfs_layout_segment *lseg)
-{
- return !FILELAYOUT_LSEG(lseg)->commit_through_mds;
-}
-
static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
{
if (fl->stripe_type == STRIPE_SPARSE)
@@ -738,13 +780,49 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
return j;
}
-struct list_head *filelayout_choose_commit_list(struct nfs_page *req)
+/* The generic layer is about to remove the req from the commit list.
+ * If this will make the bucket empty, it will need to put the lseg reference.
+ */
+static void
+filelayout_clear_request_commit(struct nfs_page *req)
+{
+ struct pnfs_layout_segment *freeme = NULL;
+ struct inode *inode = req->wb_context->dentry->d_inode;
+
+ spin_lock(&inode->i_lock);
+ if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
+ goto out;
+ if (list_is_singular(&req->wb_list)) {
+ struct inode *inode = req->wb_context->dentry->d_inode;
+ struct pnfs_layout_segment *lseg;
+
+ /* From here we can find the bucket, but for the moment,
+ * since there is only one relevant lseg...
+ */
+ list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+ if (lseg->pls_range.iomode == IOMODE_RW) {
+ freeme = lseg;
+ break;
+ }
+ }
+ }
+out:
+ nfs_request_remove_commit_list(req);
+ spin_unlock(&inode->i_lock);
+ put_lseg(freeme);
+}
+
+static struct list_head *
+filelayout_choose_commit_list(struct nfs_page *req,
+ struct pnfs_layout_segment *lseg)
{
- struct pnfs_layout_segment *lseg = req->wb_commit_lseg;
struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
u32 i, j;
struct list_head *list;
+ if (fl->commit_through_mds)
+ return &NFS_I(req->wb_context->dentry->d_inode)->commit_list;
+
/* Note that we are calling nfs4_fl_calc_j_index on each page
* that ends up being committed to a data server. An attractive
* alternative is to add a field to nfs_write_data and nfs_page
@@ -754,14 +832,30 @@ struct list_head *filelayout_choose_commit_list(struct nfs_page *req)
j = nfs4_fl_calc_j_index(lseg,
(loff_t)req->wb_index << PAGE_CACHE_SHIFT);
i = select_bucket_index(fl, j);
- list = &fl->commit_buckets[i];
+ list = &fl->commit_buckets[i].written;
if (list_empty(list)) {
- /* Non-empty buckets hold a reference on the lseg */
+ /* Non-empty buckets hold a reference on the lseg. That ref
+ * is normally transferred to the COMMIT call and released
+ * there. It could also be released if the last req is pulled
+ * off due to a rewrite, in which case it will be done in
+ * filelayout_remove_commit_req
+ */
get_lseg(lseg);
}
+ set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
return list;
}
+static void
+filelayout_mark_request_commit(struct nfs_page *req,
+ struct pnfs_layout_segment *lseg)
+{
+ struct list_head *list;
+
+ list = filelayout_choose_commit_list(req, lseg);
+ nfs_request_add_commit_list(req, list);
+}
+
static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
{
struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
@@ -797,11 +891,12 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
ds = nfs4_fl_prepare_ds(lseg, idx);
if (!ds) {
- printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+ printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
+ __func__);
set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
prepare_to_resend_writes(data);
- data->mds_ops->rpc_release(data);
+ filelayout_commit_release(data);
return -EAGAIN;
}
dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how);
@@ -817,24 +912,87 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
/*
* This is only useful while we are using whole file layouts.
*/
-static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
+static struct pnfs_layout_segment *
+find_only_write_lseg_locked(struct inode *inode)
{
- struct pnfs_layout_segment *lseg, *rv = NULL;
+ struct pnfs_layout_segment *lseg;
- spin_lock(&inode->i_lock);
list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
if (lseg->pls_range.iomode == IOMODE_RW)
- rv = get_lseg(lseg);
+ return lseg;
+ return NULL;
+}
+
+static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
+{
+ struct pnfs_layout_segment *rv;
+
+ spin_lock(&inode->i_lock);
+ rv = find_only_write_lseg_locked(inode);
+ if (rv)
+ get_lseg(rv);
spin_unlock(&inode->i_lock);
return rv;
}
-static int alloc_ds_commits(struct inode *inode, struct list_head *list)
+static int
+filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max,
+ spinlock_t *lock)
+{
+ struct list_head *src = &bucket->written;
+ struct list_head *dst = &bucket->committing;
+ struct nfs_page *req, *tmp;
+ int ret = 0;
+
+ list_for_each_entry_safe(req, tmp, src, wb_list) {
+ if (!nfs_lock_request(req))
+ continue;
+ if (cond_resched_lock(lock))
+ list_safe_reset_next(req, tmp, wb_list);
+ nfs_request_remove_commit_list(req);
+ clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+ nfs_list_add_request(req, dst);
+ ret++;
+ if (ret == max)
+ break;
+ }
+ return ret;
+}
+
+/* Move reqs from written to committing lists, returning count of number moved.
+ * Note called with i_lock held.
+ */
+static int filelayout_scan_commit_lists(struct inode *inode, int max,
+ spinlock_t *lock)
+{
+ struct pnfs_layout_segment *lseg;
+ struct nfs4_filelayout_segment *fl;
+ int i, rv = 0, cnt;
+
+ lseg = find_only_write_lseg_locked(inode);
+ if (!lseg)
+ goto out_done;
+ fl = FILELAYOUT_LSEG(lseg);
+ if (fl->commit_through_mds)
+ goto out_done;
+ for (i = 0; i < fl->number_of_buckets && max != 0; i++) {
+ cnt = filelayout_scan_ds_commit_list(&fl->commit_buckets[i],
+ max, lock);
+ max -= cnt;
+ rv += cnt;
+ }
+out_done:
+ return rv;
+}
+
+static unsigned int
+alloc_ds_commits(struct inode *inode, struct list_head *list)
{
struct pnfs_layout_segment *lseg;
struct nfs4_filelayout_segment *fl;
struct nfs_write_data *data;
int i, j;
+ unsigned int nreq = 0;
/* Won't need this when non-whole file layout segments are supported
* instead we will use a pnfs_layout_hdr structure */
@@ -843,28 +1001,27 @@ static int alloc_ds_commits(struct inode *inode, struct list_head *list)
return 0;
fl = FILELAYOUT_LSEG(lseg);
for (i = 0; i < fl->number_of_buckets; i++) {
- if (list_empty(&fl->commit_buckets[i]))
+ if (list_empty(&fl->commit_buckets[i].committing))
continue;
data = nfs_commitdata_alloc();
if (!data)
- goto out_bad;
+ break;
data->ds_commit_index = i;
data->lseg = lseg;
list_add(&data->pages, list);
+ nreq++;
}
- put_lseg(lseg);
- return 0;
-out_bad:
+ /* Clean up on error */
for (j = i; j < fl->number_of_buckets; j++) {
- if (list_empty(&fl->commit_buckets[i]))
+ if (list_empty(&fl->commit_buckets[i].committing))
continue;
- nfs_retry_commit(&fl->commit_buckets[i], lseg);
+ nfs_retry_commit(&fl->commit_buckets[i].committing, lseg);
put_lseg(lseg); /* associated with emptying bucket */
}
put_lseg(lseg);
/* Caller will clean up entries put on list */
- return -ENOMEM;
+ return nreq;
}
/* This follows nfs_commit_list pretty closely */
@@ -874,40 +1031,40 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
{
struct nfs_write_data *data, *tmp;
LIST_HEAD(list);
+ unsigned int nreq = 0;
if (!list_empty(mds_pages)) {
data = nfs_commitdata_alloc();
- if (!data)
- goto out_bad;
- data->lseg = NULL;
- list_add(&data->pages, &list);
+ if (data != NULL) {
+ data->lseg = NULL;
+ list_add(&data->pages, &list);
+ nreq++;
+ } else
+ nfs_retry_commit(mds_pages, NULL);
}
- if (alloc_ds_commits(inode, &list))
- goto out_bad;
+ nreq += alloc_ds_commits(inode, &list);
+
+ if (nreq == 0) {
+ nfs_commit_clear_lock(NFS_I(inode));
+ goto out;
+ }
+
+ atomic_add(nreq, &NFS_I(inode)->commits_outstanding);
list_for_each_entry_safe(data, tmp, &list, pages) {
list_del_init(&data->pages);
- atomic_inc(&NFS_I(inode)->commits_outstanding);
if (!data->lseg) {
nfs_init_commit(data, mds_pages, NULL);
nfs_initiate_commit(data, NFS_CLIENT(inode),
data->mds_ops, how);
} else {
- nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index], data->lseg);
+ nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index].committing, data->lseg);
filelayout_initiate_commit(data, how);
}
}
- return 0;
- out_bad:
- list_for_each_entry_safe(data, tmp, &list, pages) {
- nfs_retry_commit(&data->pages, data->lseg);
- list_del_init(&data->pages);
- nfs_commit_free(data);
- }
- nfs_retry_commit(mds_pages, NULL);
- nfs_commit_clear_lock(NFS_I(inode));
- return -ENOMEM;
+out:
+ return PNFS_ATTEMPTED;
}
static void
@@ -924,8 +1081,9 @@ static struct pnfs_layoutdriver_type filelayout_type = {
.free_lseg = filelayout_free_lseg,
.pg_read_ops = &filelayout_pg_read_ops,
.pg_write_ops = &filelayout_pg_write_ops,
- .mark_pnfs_commit = filelayout_mark_pnfs_commit,
- .choose_commit_list = filelayout_choose_commit_list,
+ .mark_request_commit = filelayout_mark_request_commit,
+ .clear_request_commit = filelayout_clear_request_commit,
+ .scan_commit_lists = filelayout_scan_commit_lists,
.commit_pagelist = filelayout_commit_pagelist,
.read_pagelist = filelayout_read_pagelist,
.write_pagelist = filelayout_write_pagelist,
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 2e42284..21190bb 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -74,6 +74,11 @@ struct nfs4_file_layout_dsaddr {
struct nfs4_pnfs_ds *ds_list[1];
};
+struct nfs4_fl_commit_bucket {
+ struct list_head written;
+ struct list_head committing;
+};
+
struct nfs4_filelayout_segment {
struct pnfs_layout_segment generic_hdr;
u32 stripe_type;
@@ -84,7 +89,7 @@ struct nfs4_filelayout_segment {
struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
unsigned int num_fh;
struct nfs_fh **fh_array;
- struct list_head *commit_buckets; /* Sort commits to ds */
+ struct nfs4_fl_commit_bucket *commit_buckets; /* Sort commits to ds */
int number_of_buckets;
};
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 8ae9190..a866bbd 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -45,7 +45,7 @@
* - incremented when a device id maps a data server already in the cache.
* - decremented when deviceid is removed from the cache.
*/
-DEFINE_SPINLOCK(nfs4_ds_cache_lock);
+static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
static LIST_HEAD(nfs4_data_server_cache);
/* Debug routines */
@@ -108,58 +108,40 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
return false;
}
-/*
- * Lookup DS by addresses. The first matching address returns true.
- * nfs4_ds_cache_lock is held
- */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(struct list_head *dsaddrs)
+static bool
+_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
+ const struct list_head *dsaddrs2)
{
- struct nfs4_pnfs_ds *ds;
struct nfs4_pnfs_ds_addr *da1, *da2;
- list_for_each_entry(da1, dsaddrs, da_node) {
- list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
- list_for_each_entry(da2, &ds->ds_addrs, da_node) {
- if (same_sockaddr(
- (struct sockaddr *)&da1->da_addr,
- (struct sockaddr *)&da2->da_addr))
- return ds;
- }
- }
+ /* step through both lists, comparing as we go */
+ for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
+ da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
+ da1 != NULL && da2 != NULL;
+ da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
+ da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
+ if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
+ (struct sockaddr *)&da2->da_addr))
+ return false;
}
- return NULL;
+ if (da1 == NULL && da2 == NULL)
+ return true;
+
+ return false;
}
/*
- * Compare two lists of addresses.
+ * Lookup DS by addresses. nfs4_ds_cache_lock is held
*/
-static bool
-_data_server_match_all_addrs_locked(struct list_head *dsaddrs1,
- struct list_head *dsaddrs2)
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(const struct list_head *dsaddrs)
{
- struct nfs4_pnfs_ds_addr *da1, *da2;
- size_t count1 = 0,
- count2 = 0;
-
- list_for_each_entry(da1, dsaddrs1, da_node)
- count1++;
-
- list_for_each_entry(da2, dsaddrs2, da_node) {
- bool found = false;
- count2++;
- list_for_each_entry(da1, dsaddrs1, da_node) {
- if (same_sockaddr((struct sockaddr *)&da1->da_addr,
- (struct sockaddr *)&da2->da_addr)) {
- found = true;
- break;
- }
- }
- if (!found)
- return false;
- }
+ struct nfs4_pnfs_ds *ds;
- return (count1 == count2);
+ list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+ if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
+ return ds;
+ return NULL;
}
/*
@@ -356,11 +338,6 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
dprintk("%s add new data server %s\n", __func__,
ds->ds_remotestr);
} else {
- if (!_data_server_match_all_addrs_locked(&tmp_ds->ds_addrs,
- dsaddrs)) {
- dprintk("%s: multipath address mismatch: %s != %s",
- __func__, tmp_ds->ds_remotestr, remotestr);
- }
kfree(remotestr);
kfree(ds);
atomic_inc(&tmp_ds->ds_count);
@@ -378,7 +355,7 @@ out:
* Currently only supports ipv4, ipv6 and one multi-path address.
*/
static struct nfs4_pnfs_ds_addr *
-decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
+decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
{
struct nfs4_pnfs_ds_addr *da = NULL;
char *buf, *portstr;
@@ -457,7 +434,7 @@ decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
INIT_LIST_HEAD(&da->da_node);
- if (!rpc_pton(buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+ if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
sizeof(da->da_addr))) {
dprintk("%s: error parsing address %s\n", __func__, buf);
goto out_free_da;
@@ -554,7 +531,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
cnt = be32_to_cpup(p);
dprintk("%s stripe count %d\n", __func__, cnt);
if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
- printk(KERN_WARNING "%s: stripe count %d greater than "
+ printk(KERN_WARNING "NFS: %s: stripe count %d greater than "
"supported maximum %d\n", __func__,
cnt, NFS4_PNFS_MAX_STRIPE_CNT);
goto out_err_free_scratch;
@@ -585,7 +562,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
num = be32_to_cpup(p);
dprintk("%s ds_num %u\n", __func__, num);
if (num > NFS4_PNFS_MAX_MULTI_CNT) {
- printk(KERN_WARNING "%s: multipath count %d greater than "
+ printk(KERN_WARNING "NFS: %s: multipath count %d greater than "
"supported maximum %d\n", __func__,
num, NFS4_PNFS_MAX_MULTI_CNT);
goto out_err_free_stripe_indices;
@@ -593,7 +570,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
/* validate stripe indices are all < num */
if (max_stripe_index >= num) {
- printk(KERN_WARNING "%s: stripe index %u >= num ds %u\n",
+ printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n",
__func__, max_stripe_index, num);
goto out_err_free_stripe_indices;
}
@@ -625,7 +602,8 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
mp_count = be32_to_cpup(p); /* multipath count */
for (j = 0; j < mp_count; j++) {
- da = decode_ds_addr(&stream, gfp_flags);
+ da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net,
+ &stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
@@ -686,7 +664,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
new = decode_device(inode, dev, gfp_flags);
if (!new) {
- printk(KERN_WARNING "%s: Could not decode or add device\n",
+ printk(KERN_WARNING "NFS: %s: Could not decode or add device\n",
__func__);
return NULL;
}
@@ -835,7 +813,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
if (ds == NULL) {
- printk(KERN_ERR "%s: No data server for offset index %d\n",
+ printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
__func__, ds_idx);
return NULL;
}
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index bb80c49..9c8eca3 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -94,13 +94,14 @@ static int nfs4_validate_fspath(struct dentry *dentry,
}
static size_t nfs_parse_server_name(char *string, size_t len,
- struct sockaddr *sa, size_t salen)
+ struct sockaddr *sa, size_t salen, struct nfs_server *server)
{
+ struct net *net = rpc_net_ns(server->client);
ssize_t ret;
- ret = rpc_pton(string, len, sa, salen);
+ ret = rpc_pton(net, string, len, sa, salen);
if (ret == 0) {
- ret = nfs_dns_resolve_name(string, len, sa, salen);
+ ret = nfs_dns_resolve_name(net, string, len, sa, salen);
if (ret < 0)
ret = 0;
}
@@ -137,7 +138,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
continue;
mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
- mountdata->addr, addr_bufsize);
+ mountdata->addr, addr_bufsize,
+ NFS_SB(mountdata->sb));
if (mountdata->addrlen == 0)
continue;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f0c849c..e809d23 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -72,18 +72,21 @@
#define NFS4_MAX_LOOP_ON_RECOVER (10)
+static unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
+
struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
+static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr);
static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
struct nfs_fattr *fattr, struct iattr *sattr,
struct nfs4_state *state);
#ifdef CONFIG_NFS_V4_1
-static int nfs41_test_stateid(struct nfs_server *, struct nfs4_state *);
-static int nfs41_free_stateid(struct nfs_server *, struct nfs4_state *);
+static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *);
+static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *);
#endif
/* Prevent leaks of NFSv4 errors into userland */
static int nfs4_map_errors(int err)
@@ -193,7 +196,7 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
* when talking to the server, we always send cookie 0
* instead of 1 or 2.
*/
- start = p = kmap_atomic(*readdir->pages, KM_USER0);
+ start = p = kmap_atomic(*readdir->pages);
if (cookie == 0) {
*p++ = xdr_one; /* next */
@@ -221,7 +224,7 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
readdir->pgbase = (char *)p - (char *)start;
readdir->count -= readdir->pgbase;
- kunmap_atomic(start, KM_USER0);
+ kunmap_atomic(start);
}
static int nfs4_wait_clnt_recover(struct nfs_client *clp)
@@ -259,15 +262,28 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state *state = exception->state;
+ struct inode *inode = exception->inode;
int ret = errorcode;
exception->retry = 0;
switch(errorcode) {
case 0:
return 0;
+ case -NFS4ERR_OPENMODE:
+ if (nfs_have_delegation(inode, FMODE_READ)) {
+ nfs_inode_return_delegation(inode);
+ exception->retry = 1;
+ return 0;
+ }
+ if (state == NULL)
+ break;
+ nfs4_schedule_stateid_recovery(server, state);
+ goto wait_on_recovery;
+ case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_OPENMODE:
+ if (state != NULL)
+ nfs_remove_bad_delegation(state->inode);
if (state == NULL)
break;
nfs4_schedule_stateid_recovery(server, state);
@@ -360,16 +376,14 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
* When updating highest_used_slotid there may be "holes" in the bitmap
* so we need to scan down from highest_used_slotid to 0 looking for the now
* highest slotid in use.
- * If none found, highest_used_slotid is set to -1.
+ * If none found, highest_used_slotid is set to NFS4_NO_SLOT.
*
* Must be called while holding tbl->slot_tbl_lock
*/
static void
-nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
+nfs4_free_slot(struct nfs4_slot_table *tbl, u32 slotid)
{
- int slotid = free_slotid;
-
- BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE);
+ BUG_ON(slotid >= NFS4_MAX_SLOT_TABLE);
/* clear used bit in bitmap */
__clear_bit(slotid, tbl->used_slots);
@@ -379,10 +393,16 @@ nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
if (slotid < tbl->max_slots)
tbl->highest_used_slotid = slotid;
else
- tbl->highest_used_slotid = -1;
+ tbl->highest_used_slotid = NFS4_NO_SLOT;
}
- dprintk("%s: free_slotid %u highest_used_slotid %d\n", __func__,
- free_slotid, tbl->highest_used_slotid);
+ dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
+ slotid, tbl->highest_used_slotid);
+}
+
+bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy)
+{
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ return true;
}
/*
@@ -390,16 +410,13 @@ nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
*/
static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
{
- struct rpc_task *task;
-
if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
- task = rpc_wake_up_next(&ses->fc_slot_table.slot_tbl_waitq);
- if (task)
- rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ rpc_wake_up_first(&ses->fc_slot_table.slot_tbl_waitq,
+ nfs4_set_task_privileged, NULL);
return;
}
- if (ses->fc_slot_table.highest_used_slotid != -1)
+ if (ses->fc_slot_table.highest_used_slotid != NFS4_NO_SLOT)
return;
dprintk("%s COMPLETE: Session Fore Channel Drained\n", __func__);
@@ -412,7 +429,7 @@ static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
void nfs4_check_drain_bc_complete(struct nfs4_session *ses)
{
if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state) ||
- ses->bc_slot_table.highest_used_slotid != -1)
+ ses->bc_slot_table.highest_used_slotid != NFS4_NO_SLOT)
return;
dprintk("%s COMPLETE: Session Back Channel Drained\n", __func__);
complete(&ses->bc_slot_table.complete);
@@ -507,25 +524,25 @@ static int nfs4_sequence_done(struct rpc_task *task,
* nfs4_find_slot looks for an unset bit in the used_slots bitmap.
* If found, we mark the slot as used, update the highest_used_slotid,
* and respectively set up the sequence operation args.
- * The slot number is returned if found, or NFS4_MAX_SLOT_TABLE otherwise.
+ * The slot number is returned if found, or NFS4_NO_SLOT otherwise.
*
* Note: must be called with under the slot_tbl_lock.
*/
-static u8
+static u32
nfs4_find_slot(struct nfs4_slot_table *tbl)
{
- int slotid;
- u8 ret_id = NFS4_MAX_SLOT_TABLE;
- BUILD_BUG_ON((u8)NFS4_MAX_SLOT_TABLE != (int)NFS4_MAX_SLOT_TABLE);
+ u32 slotid;
+ u32 ret_id = NFS4_NO_SLOT;
- dprintk("--> %s used_slots=%04lx highest_used=%d max_slots=%d\n",
+ dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n",
__func__, tbl->used_slots[0], tbl->highest_used_slotid,
tbl->max_slots);
slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slots);
if (slotid >= tbl->max_slots)
goto out;
__set_bit(slotid, tbl->used_slots);
- if (slotid > tbl->highest_used_slotid)
+ if (slotid > tbl->highest_used_slotid ||
+ tbl->highest_used_slotid == NFS4_NO_SLOT)
tbl->highest_used_slotid = slotid;
ret_id = slotid;
out:
@@ -534,15 +551,25 @@ out:
return ret_id;
}
+static void nfs41_init_sequence(struct nfs4_sequence_args *args,
+ struct nfs4_sequence_res *res, int cache_reply)
+{
+ args->sa_session = NULL;
+ args->sa_cache_this = 0;
+ if (cache_reply)
+ args->sa_cache_this = 1;
+ res->sr_session = NULL;
+ res->sr_slot = NULL;
+}
+
int nfs41_setup_sequence(struct nfs4_session *session,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
- int cache_reply,
struct rpc_task *task)
{
struct nfs4_slot *slot;
struct nfs4_slot_table *tbl;
- u8 slotid;
+ u32 slotid;
dprintk("--> %s\n", __func__);
/* slot already allocated? */
@@ -570,7 +597,7 @@ int nfs41_setup_sequence(struct nfs4_session *session,
}
slotid = nfs4_find_slot(tbl);
- if (slotid == NFS4_MAX_SLOT_TABLE) {
+ if (slotid == NFS4_NO_SLOT) {
rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
spin_unlock(&tbl->slot_tbl_lock);
dprintk("<-- %s: no free slots\n", __func__);
@@ -582,7 +609,6 @@ int nfs41_setup_sequence(struct nfs4_session *session,
slot = tbl->slots + slotid;
args->sa_session = session;
args->sa_slotid = slotid;
- args->sa_cache_this = cache_reply;
dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
@@ -602,24 +628,19 @@ EXPORT_SYMBOL_GPL(nfs41_setup_sequence);
int nfs4_setup_sequence(const struct nfs_server *server,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
- int cache_reply,
struct rpc_task *task)
{
struct nfs4_session *session = nfs4_get_session(server);
int ret = 0;
- if (session == NULL) {
- args->sa_session = NULL;
- res->sr_session = NULL;
+ if (session == NULL)
goto out;
- }
dprintk("--> %s clp %p session %p sr_slot %td\n",
__func__, session->clp, session, res->sr_slot ?
res->sr_slot - session->fc_slot_table.slots : -1);
- ret = nfs41_setup_sequence(session, args, res, cache_reply,
- task);
+ ret = nfs41_setup_sequence(session, args, res, task);
out:
dprintk("<-- %s status=%d\n", __func__, ret);
return ret;
@@ -629,7 +650,6 @@ struct nfs41_call_sync_data {
const struct nfs_server *seq_server;
struct nfs4_sequence_args *seq_args;
struct nfs4_sequence_res *seq_res;
- int cache_reply;
};
static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
@@ -639,7 +659,7 @@ static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server);
if (nfs4_setup_sequence(data->seq_server, data->seq_args,
- data->seq_res, data->cache_reply, task))
+ data->seq_res, task))
return;
rpc_call_start(task);
}
@@ -657,12 +677,12 @@ static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
nfs41_sequence_done(task, data->seq_res);
}
-struct rpc_call_ops nfs41_call_sync_ops = {
+static const struct rpc_call_ops nfs41_call_sync_ops = {
.rpc_call_prepare = nfs41_call_sync_prepare,
.rpc_call_done = nfs41_call_sync_done,
};
-struct rpc_call_ops nfs41_call_priv_sync_ops = {
+static const struct rpc_call_ops nfs41_call_priv_sync_ops = {
.rpc_call_prepare = nfs41_call_priv_sync_prepare,
.rpc_call_done = nfs41_call_sync_done,
};
@@ -672,7 +692,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
struct rpc_message *msg,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
- int cache_reply,
int privileged)
{
int ret;
@@ -681,7 +700,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
.seq_server = server,
.seq_args = args,
.seq_res = res,
- .cache_reply = cache_reply,
};
struct rpc_task_setup task_setup = {
.rpc_client = clnt,
@@ -690,7 +708,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
.callback_data = &data
};
- res->sr_slot = NULL;
if (privileged)
task_setup.callback_ops = &nfs41_call_priv_sync_ops;
task = rpc_run_task(&task_setup);
@@ -710,10 +727,17 @@ int _nfs4_call_sync_session(struct rpc_clnt *clnt,
struct nfs4_sequence_res *res,
int cache_reply)
{
- return nfs4_call_sync_sequence(clnt, server, msg, args, res, cache_reply, 0);
+ nfs41_init_sequence(args, res, cache_reply);
+ return nfs4_call_sync_sequence(clnt, server, msg, args, res, 0);
}
#else
+static inline
+void nfs41_init_sequence(struct nfs4_sequence_args *args,
+ struct nfs4_sequence_res *res, int cache_reply)
+{
+}
+
static int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
@@ -728,7 +752,7 @@ int _nfs4_call_sync(struct rpc_clnt *clnt,
struct nfs4_sequence_res *res,
int cache_reply)
{
- args->sa_session = res->sr_session = NULL;
+ nfs41_init_sequence(args, res, cache_reply);
return rpc_call_sync(clnt, msg, 0);
}
@@ -815,20 +839,22 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
p->o_arg.open_flags = flags;
p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
p->o_arg.clientid = server->nfs_client->cl_clientid;
- p->o_arg.id = sp->so_owner_id.id;
+ p->o_arg.id = sp->so_seqid.owner_id;
p->o_arg.name = &dentry->d_name;
p->o_arg.server = server;
p->o_arg.bitmask = server->attr_bitmask;
p->o_arg.dir_bitmask = server->cache_consistency_bitmask;
p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
- if (flags & O_CREAT) {
- u32 *s;
+ if (attrs != NULL && attrs->ia_valid != 0) {
+ __be32 verf[2];
p->o_arg.u.attrs = &p->attrs;
memcpy(&p->attrs, attrs, sizeof(p->attrs));
- s = (u32 *) p->o_arg.u.verifier.data;
- s[0] = jiffies;
- s[1] = current->pid;
+
+ verf[0] = jiffies;
+ verf[1] = current->pid;
+ memcpy(p->o_arg.u.verifier.data, verf,
+ sizeof(p->o_arg.u.verifier.data));
}
p->c_arg.fh = &p->o_res.fh;
p->c_arg.stateid = &p->o_res.stateid;
@@ -878,7 +904,7 @@ static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode
{
int ret = 0;
- if (open_mode & O_EXCL)
+ if (open_mode & (O_EXCL|O_TRUNC))
goto out;
switch (mode & (FMODE_READ|FMODE_WRITE)) {
case FMODE_READ:
@@ -927,8 +953,8 @@ static void update_open_stateflags(struct nfs4_state *state, fmode_t fmode)
static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
{
if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
- memcpy(state->stateid.data, stateid->data, sizeof(state->stateid.data));
- memcpy(state->open_stateid.data, stateid->data, sizeof(state->open_stateid.data));
+ nfs4_stateid_copy(&state->stateid, stateid);
+ nfs4_stateid_copy(&state->open_stateid, stateid);
switch (fmode) {
case FMODE_READ:
set_bit(NFS_O_RDONLY_STATE, &state->flags);
@@ -956,7 +982,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s
*/
write_seqlock(&state->seqlock);
if (deleg_stateid != NULL) {
- memcpy(state->stateid.data, deleg_stateid->data, sizeof(state->stateid.data));
+ nfs4_stateid_copy(&state->stateid, deleg_stateid);
set_bit(NFS_DELEGATED_STATE, &state->flags);
}
if (open_stateid != NULL)
@@ -987,7 +1013,7 @@ static int update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stat
if (delegation == NULL)
delegation = &deleg_cur->stateid;
- else if (memcmp(deleg_cur->stateid.data, delegation->data, NFS4_STATEID_SIZE) != 0)
+ else if (!nfs4_stateid_match(&deleg_cur->stateid, delegation))
goto no_delegation_unlock;
nfs_mark_delegation_referenced(deleg_cur);
@@ -1026,7 +1052,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
struct nfs4_state *state = opendata->state;
struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_delegation *delegation;
- int open_mode = opendata->o_arg.open_flags & O_EXCL;
+ int open_mode = opendata->o_arg.open_flags & (O_EXCL|O_TRUNC);
fmode_t fmode = opendata->o_arg.fmode;
nfs4_stateid stateid;
int ret = -EAGAIN;
@@ -1048,7 +1074,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
break;
}
/* Save the delegation */
- memcpy(stateid.data, delegation->stateid.data, sizeof(stateid.data));
+ nfs4_stateid_copy(&stateid, &delegation->stateid);
rcu_read_unlock();
ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
if (ret != 0)
@@ -1090,6 +1116,7 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
if (state == NULL)
goto err_put_inode;
if (data->o_res.delegation_type != 0) {
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
int delegation_flags = 0;
rcu_read_lock();
@@ -1101,7 +1128,7 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
"returning a delegation for "
"OPEN(CLAIM_DELEGATE_CUR)\n",
- NFS_CLIENT(inode)->cl_server);
+ clp->cl_hostname);
} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
nfs_inode_set_delegation(state->inode,
data->owner->so_cred,
@@ -1210,10 +1237,10 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
* Check if we need to update the current stateid.
*/
if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0 &&
- memcmp(state->stateid.data, state->open_stateid.data, sizeof(state->stateid.data)) != 0) {
+ !nfs4_stateid_match(&state->stateid, &state->open_stateid)) {
write_seqlock(&state->seqlock);
if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
- memcpy(state->stateid.data, state->open_stateid.data, sizeof(state->stateid.data));
+ nfs4_stateid_copy(&state->stateid, &state->open_stateid);
write_sequnlock(&state->seqlock);
}
return 0;
@@ -1282,8 +1309,7 @@ static int _nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs
if (IS_ERR(opendata))
return PTR_ERR(opendata);
opendata->o_arg.claim = NFS4_OPEN_CLAIM_DELEGATE_CUR;
- memcpy(opendata->o_arg.u.delegation.data, stateid->data,
- sizeof(opendata->o_arg.u.delegation.data));
+ nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
ret = nfs4_open_recover(opendata, state);
nfs4_opendata_put(opendata);
return ret;
@@ -1319,8 +1345,11 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
* The show must go on: exit, but mark the
* stateid as needing recovery.
*/
+ case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
+ nfs_inode_find_state_and_recover(state->inode,
+ stateid);
nfs4_schedule_stateid_recovery(server, state);
case -EKEYEXPIRED:
/*
@@ -1345,8 +1374,7 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
data->rpc_status = task->tk_status;
if (data->rpc_status == 0) {
- memcpy(data->o_res.stateid.data, data->c_res.stateid.data,
- sizeof(data->o_res.stateid.data));
+ nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid);
nfs_confirm_seqid(&data->owner->so_seqid, 0);
renew_lease(data->o_res.server, data->timestamp);
data->rpc_done = 1;
@@ -1440,7 +1468,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
rcu_read_unlock();
}
/* Update sequence id. */
- data->o_arg.id = sp->so_owner_id.id;
+ data->o_arg.id = sp->so_seqid.owner_id;
data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
@@ -1449,7 +1477,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
data->timestamp = jiffies;
if (nfs4_setup_sequence(data->o_arg.server,
&data->o_arg.seq_args,
- &data->o_res.seq_res, 1, task))
+ &data->o_res.seq_res, task))
return;
rpc_call_start(task);
return;
@@ -1551,6 +1579,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
};
int status;
+ nfs41_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1);
kref_get(&data->kref);
data->rpc_done = 0;
data->rpc_status = 0;
@@ -1712,15 +1741,32 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
}
#if defined(CONFIG_NFS_V4_1)
-static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+static int nfs41_check_expired_stateid(struct nfs4_state *state, nfs4_stateid *stateid, unsigned int flags)
{
- int status;
+ int status = NFS_OK;
struct nfs_server *server = NFS_SERVER(state->inode);
- status = nfs41_test_stateid(server, state);
- if (status == NFS_OK)
- return 0;
- nfs41_free_stateid(server, state);
+ if (state->flags & flags) {
+ status = nfs41_test_stateid(server, stateid);
+ if (status != NFS_OK) {
+ nfs41_free_stateid(server, stateid);
+ state->flags &= ~flags;
+ }
+ }
+ return status;
+}
+
+static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+ int deleg_status, open_status;
+ int deleg_flags = 1 << NFS_DELEGATED_STATE;
+ int open_flags = (1 << NFS_O_RDONLY_STATE) | (1 << NFS_O_WRONLY_STATE) | (1 << NFS_O_RDWR_STATE);
+
+ deleg_status = nfs41_check_expired_stateid(state, &state->stateid, deleg_flags);
+ open_status = nfs41_check_expired_stateid(state, &state->open_stateid, open_flags);
+
+ if ((deleg_status == NFS_OK) && (open_status == NFS_OK))
+ return NFS_OK;
return nfs4_open_expired(sp, state);
}
#endif
@@ -1754,7 +1800,8 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode
/* Protect against reboot recovery conflicts */
status = -ENOMEM;
- if (!(sp = nfs4_get_state_owner(server, cred))) {
+ sp = nfs4_get_state_owner(server, cred, GFP_KERNEL);
+ if (sp == NULL) {
dprintk("nfs4_do_open: nfs4_get_state_owner failed!\n");
goto out_err;
}
@@ -1829,7 +1876,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry,
* the user though...
*/
if (status == -NFS4ERR_BAD_SEQID) {
- printk(KERN_WARNING "NFS: v4 server %s "
+ pr_warn_ratelimited("NFS: v4 server %s "
" returned a bad sequence-id error!\n",
NFS_SERVER(dir)->nfs_client->cl_hostname);
exception.retry = 1;
@@ -1882,12 +1929,14 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
nfs_fattr_init(fattr);
- if (nfs4_copy_delegation_stateid(&arg.stateid, inode)) {
+ if (state != NULL) {
+ nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+ current->files, current->tgid);
+ } else if (nfs4_copy_delegation_stateid(&arg.stateid, inode,
+ FMODE_WRITE)) {
/* Use that stateid */
- } else if (state != NULL) {
- nfs4_copy_stateid(&arg.stateid, state, current->files, current->tgid);
} else
- memcpy(&arg.stateid, &zero_stateid, sizeof(arg.stateid));
+ nfs4_stateid_copy(&arg.stateid, &zero_stateid);
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
if (status == 0 && state != NULL)
@@ -1900,7 +1949,10 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
struct nfs4_state *state)
{
struct nfs_server *server = NFS_SERVER(inode);
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .state = state,
+ .inode = inode,
+ };
int err;
do {
err = nfs4_handle_exception(server,
@@ -1954,6 +2006,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
struct nfs4_state *state = calldata->state;
struct nfs_server *server = NFS_SERVER(calldata->inode);
+ dprintk("%s: begin!\n", __func__);
if (!nfs4_sequence_done(task, &calldata->res.seq_res))
return;
/* hmm. we are done with the inode, and in the process of freeing
@@ -1981,6 +2034,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
}
nfs_release_seqid(calldata->arg.seqid);
nfs_refresh_inode(calldata->inode, calldata->res.fattr);
+ dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
}
static void nfs4_close_prepare(struct rpc_task *task, void *data)
@@ -1989,6 +2043,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
struct nfs4_state *state = calldata->state;
int call_close = 0;
+ dprintk("%s: begin!\n", __func__);
if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
return;
@@ -2013,7 +2068,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
if (!call_close) {
/* Note: exit _without_ calling nfs4_close_done */
task->tk_action = NULL;
- return;
+ goto out;
}
if (calldata->arg.fmode == 0) {
@@ -2022,17 +2077,20 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
pnfs_roc_drain(calldata->inode, &calldata->roc_barrier)) {
rpc_sleep_on(&NFS_SERVER(calldata->inode)->roc_rpcwaitq,
task, NULL);
- return;
+ goto out;
}
}
nfs_fattr_init(calldata->res.fattr);
calldata->timestamp = jiffies;
if (nfs4_setup_sequence(NFS_SERVER(calldata->inode),
- &calldata->arg.seq_args, &calldata->res.seq_res,
- 1, task))
- return;
+ &calldata->arg.seq_args,
+ &calldata->res.seq_res,
+ task))
+ goto out;
rpc_call_start(task);
+out:
+ dprintk("%s: done!\n", __func__);
}
static const struct rpc_call_ops nfs4_close_ops = {
@@ -2074,6 +2132,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
calldata = kzalloc(sizeof(*calldata), gfp_mask);
if (calldata == NULL)
goto out;
+ nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 1);
calldata->inode = state->inode;
calldata->state = state;
calldata->arg.fh = NFS_FH(state->inode);
@@ -2182,6 +2241,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
server->acl_bitmask = res.acl_bitmask;
+ server->fh_expire_type = res.fh_expire_type;
}
return status;
@@ -2303,7 +2363,6 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
return nfs4_map_errors(status);
}
-static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
/*
* Get locations and (maybe) other attributes of a referral.
* Note that we'll actually follow the referral later when
@@ -2420,6 +2479,10 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
}
}
+ /* Deal with open(O_TRUNC) */
+ if (sattr->ia_valid & ATTR_OPEN)
+ sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN);
+
status = nfs4_do_setattr(inode, cred, fattr, sattr, state);
if (status == 0)
nfs_setattr_update_inode(inode, sattr);
@@ -2494,7 +2557,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
struct nfs_server *server = NFS_SERVER(inode);
struct nfs4_accessargs args = {
.fh = NFS_FH(inode),
- .bitmask = server->attr_bitmask,
+ .bitmask = server->cache_consistency_bitmask,
};
struct nfs4_accessres res = {
.server = server,
@@ -2712,8 +2775,18 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
args->bitmask = server->cache_consistency_bitmask;
res->server = server;
- res->seq_res.sr_slot = NULL;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE];
+ nfs41_init_sequence(&args->seq_args, &res->seq_res, 1);
+}
+
+static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+ if (nfs4_setup_sequence(NFS_SERVER(data->dir),
+ &data->args.seq_args,
+ &data->res.seq_res,
+ task))
+ return;
+ rpc_call_start(task);
}
static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
@@ -2738,6 +2811,17 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME];
arg->bitmask = server->attr_bitmask;
res->server = server;
+ nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1);
+}
+
+static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+ if (nfs4_setup_sequence(NFS_SERVER(data->old_dir),
+ &data->args.seq_args,
+ &data->res.seq_res,
+ task))
+ return;
+ rpc_call_start(task);
}
static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
@@ -3232,6 +3316,17 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
data->timestamp = jiffies;
data->read_done_cb = nfs4_read_done_cb;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+ nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
+}
+
+static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+ if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+ &data->args.seq_args,
+ &data->res.seq_res,
+ task))
+ return;
+ rpc_call_start(task);
}
/* Reset the the nfs_read_data to send the read to the MDS. */
@@ -3305,6 +3400,17 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
data->timestamp = jiffies;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE];
+ nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
+}
+
+static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+ if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+ &data->args.seq_args,
+ &data->res.seq_res,
+ task))
+ return;
+ rpc_call_start(task);
}
static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *data)
@@ -3339,6 +3445,7 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_messa
data->write_done_cb = nfs4_commit_done_cb;
data->res.server = server;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT];
+ nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
}
struct nfs4_renewdata {
@@ -3575,8 +3682,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
}
if (npages > 1) {
/* for decoding across pages */
- args.acl_scratch = alloc_page(GFP_KERNEL);
- if (!args.acl_scratch)
+ res.acl_scratch = alloc_page(GFP_KERNEL);
+ if (!res.acl_scratch)
goto out_free;
}
args.acl_len = npages * PAGE_SIZE;
@@ -3612,8 +3719,8 @@ out_free:
for (i = 0; i < npages; i++)
if (pages[i])
__free_page(pages[i]);
- if (args.acl_scratch)
- __free_page(args.acl_scratch);
+ if (res.acl_scratch)
+ __free_page(res.acl_scratch);
return ret;
}
@@ -3714,8 +3821,11 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
if (task->tk_status >= 0)
return 0;
switch(task->tk_status) {
+ case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
+ if (state != NULL)
+ nfs_remove_bad_delegation(state->inode);
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
@@ -3764,6 +3874,16 @@ wait_on_recovery:
return -EAGAIN;
}
+static void nfs4_construct_boot_verifier(struct nfs_client *clp,
+ nfs4_verifier *bootverf)
+{
+ __be32 verf[2];
+
+ verf[0] = htonl((u32)clp->cl_boot_time.tv_sec);
+ verf[1] = htonl((u32)clp->cl_boot_time.tv_nsec);
+ memcpy(bootverf->data, verf, sizeof(bootverf->data));
+}
+
int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
unsigned short port, struct rpc_cred *cred,
struct nfs4_setclientid_res *res)
@@ -3780,15 +3900,13 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
.rpc_resp = res,
.rpc_cred = cred,
};
- __be32 *p;
int loop = 0;
int status;
- p = (__be32*)sc_verifier.data;
- *p++ = htonl((u32)clp->cl_boot_time.tv_sec);
- *p = htonl((u32)clp->cl_boot_time.tv_nsec);
+ nfs4_construct_boot_verifier(clp, &sc_verifier);
for(;;) {
+ rcu_read_lock();
setclientid.sc_name_len = scnprintf(setclientid.sc_name,
sizeof(setclientid.sc_name), "%s/%s %s %s %u",
clp->cl_ipaddr,
@@ -3805,6 +3923,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
sizeof(setclientid.sc_uaddr), "%s.%u.%u",
clp->cl_ipaddr, port >> 8, port & 255);
+ rcu_read_unlock();
status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
if (status != -NFS4ERR_CLID_INUSE)
@@ -3891,7 +4010,7 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
if (nfs4_setup_sequence(d_data->res.server,
&d_data->args.seq_args,
- &d_data->res.seq_res, 1, task))
+ &d_data->res.seq_res, task))
return;
rpc_call_start(task);
}
@@ -3925,11 +4044,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
data = kzalloc(sizeof(*data), GFP_NOFS);
if (data == NULL)
return -ENOMEM;
+ nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
data->args.fhandle = &data->fh;
data->args.stateid = &data->stateid;
data->args.bitmask = server->attr_bitmask;
nfs_copy_fh(&data->fh, NFS_FH(inode));
- memcpy(&data->stateid, stateid, sizeof(data->stateid));
+ nfs4_stateid_copy(&data->stateid, stateid);
data->res.fattr = &data->fattr;
data->res.server = server;
nfs_fattr_init(data->res.fattr);
@@ -4016,7 +4136,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
if (status != 0)
goto out;
lsp = request->fl_u.nfs4_fl.owner;
- arg.lock_owner.id = lsp->ls_id.id;
+ arg.lock_owner.id = lsp->ls_seqid.owner_id;
arg.lock_owner.s_dev = server->s_dev;
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
switch (status) {
@@ -4112,9 +4232,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
return;
switch (task->tk_status) {
case 0:
- memcpy(calldata->lsp->ls_stateid.data,
- calldata->res.stateid.data,
- sizeof(calldata->lsp->ls_stateid.data));
+ nfs4_stateid_copy(&calldata->lsp->ls_stateid,
+ &calldata->res.stateid);
renew_lease(calldata->server, calldata->timestamp);
break;
case -NFS4ERR_BAD_STATEID:
@@ -4142,7 +4261,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
calldata->timestamp = jiffies;
if (nfs4_setup_sequence(calldata->server,
&calldata->arg.seq_args,
- &calldata->res.seq_res, 1, task))
+ &calldata->res.seq_res, task))
return;
rpc_call_start(task);
}
@@ -4182,6 +4301,7 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
return ERR_PTR(-ENOMEM);
}
+ nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1);
msg.rpc_argp = &data->arg;
msg.rpc_resp = &data->res;
task_setup_data.callback_data = data;
@@ -4261,7 +4381,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
goto out_free_seqid;
p->arg.lock_stateid = &lsp->ls_stateid;
p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
- p->arg.lock_owner.id = lsp->ls_id.id;
+ p->arg.lock_owner.id = lsp->ls_seqid.owner_id;
p->arg.lock_owner.s_dev = server->s_dev;
p->res.lock_seqid = p->arg.lock_seqid;
p->lsp = lsp;
@@ -4297,7 +4417,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
data->timestamp = jiffies;
if (nfs4_setup_sequence(data->server,
&data->arg.seq_args,
- &data->res.seq_res, 1, task))
+ &data->res.seq_res, task))
return;
rpc_call_start(task);
dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
@@ -4326,8 +4446,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
goto out;
}
if (data->rpc_status == 0) {
- memcpy(data->lsp->ls_stateid.data, data->res.stateid.data,
- sizeof(data->lsp->ls_stateid.data));
+ nfs4_stateid_copy(&data->lsp->ls_stateid, &data->res.stateid);
data->lsp->ls_flags |= NFS_LOCK_INITIALIZED;
renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp);
}
@@ -4415,6 +4534,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
data->arg.reclaim = NFS_LOCK_RECLAIM;
task_setup_data.callback_ops = &nfs4_recover_lock_ops;
}
+ nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1);
msg.rpc_argp = &data->arg;
msg.rpc_resp = &data->res;
task_setup_data.callback_data = data;
@@ -4479,15 +4599,34 @@ out:
}
#if defined(CONFIG_NFS_V4_1)
-static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
+static int nfs41_check_expired_locks(struct nfs4_state *state)
{
- int status;
+ int status, ret = NFS_OK;
+ struct nfs4_lock_state *lsp;
struct nfs_server *server = NFS_SERVER(state->inode);
- status = nfs41_test_stateid(server, state);
+ list_for_each_entry(lsp, &state->lock_states, ls_locks) {
+ if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+ status = nfs41_test_stateid(server, &lsp->ls_stateid);
+ if (status != NFS_OK) {
+ nfs41_free_stateid(server, &lsp->ls_stateid);
+ lsp->ls_flags &= ~NFS_LOCK_INITIALIZED;
+ ret = status;
+ }
+ }
+ };
+
+ return ret;
+}
+
+static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
+{
+ int status = NFS_OK;
+
+ if (test_bit(LK_STATE_IN_USE, &state->flags))
+ status = nfs41_check_expired_locks(state);
if (status == NFS_OK)
- return 0;
- nfs41_free_stateid(server, state);
+ return status;
return nfs4_lock_expired(state, request);
}
#endif
@@ -4523,7 +4662,8 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
/* Note: we always want to sleep here! */
request->fl_flags = fl_flags | FL_SLEEP;
if (do_vfs_lock(request->fl_file, request) < 0)
- printk(KERN_WARNING "%s: VFS is out of sync with lock manager!\n", __func__);
+ printk(KERN_WARNING "NFS: %s: VFS is out of sync with lock "
+ "manager!\n", __func__);
out_unlock:
up_read(&nfsi->rwsem);
out:
@@ -4533,7 +4673,9 @@ out:
static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .state = state,
+ };
int err;
do {
@@ -4603,8 +4745,8 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
switch (err) {
default:
- printk(KERN_ERR "%s: unhandled error %d.\n",
- __func__, err);
+ printk(KERN_ERR "NFS: %s: unhandled error "
+ "%d.\n", __func__, err);
case 0:
case -ESTALE:
goto out;
@@ -4626,6 +4768,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
* The show must go on: exit, but mark the
* stateid as needing recovery.
*/
+ case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
case -NFS4ERR_OPENMODE:
@@ -4655,33 +4798,44 @@ out:
return err;
}
+struct nfs_release_lockowner_data {
+ struct nfs4_lock_state *lsp;
+ struct nfs_server *server;
+ struct nfs_release_lockowner_args args;
+};
+
static void nfs4_release_lockowner_release(void *calldata)
{
+ struct nfs_release_lockowner_data *data = calldata;
+ nfs4_free_lock_state(data->server, data->lsp);
kfree(calldata);
}
-const struct rpc_call_ops nfs4_release_lockowner_ops = {
+static const struct rpc_call_ops nfs4_release_lockowner_ops = {
.rpc_release = nfs4_release_lockowner_release,
};
-void nfs4_release_lockowner(const struct nfs4_lock_state *lsp)
+int nfs4_release_lockowner(struct nfs4_lock_state *lsp)
{
struct nfs_server *server = lsp->ls_state->owner->so_server;
- struct nfs_release_lockowner_args *args;
+ struct nfs_release_lockowner_data *data;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RELEASE_LOCKOWNER],
};
if (server->nfs_client->cl_mvops->minor_version != 0)
- return;
- args = kmalloc(sizeof(*args), GFP_NOFS);
- if (!args)
- return;
- args->lock_owner.clientid = server->nfs_client->cl_clientid;
- args->lock_owner.id = lsp->ls_id.id;
- args->lock_owner.s_dev = server->s_dev;
- msg.rpc_argp = args;
- rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, args);
+ return -EINVAL;
+ data = kmalloc(sizeof(*data), GFP_NOFS);
+ if (!data)
+ return -ENOMEM;
+ data->lsp = lsp;
+ data->server = server;
+ data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
+ data->args.lock_owner.id = lsp->ls_seqid.owner_id;
+ data->args.lock_owner.s_dev = server->s_dev;
+ msg.rpc_argp = &data->args;
+ rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
+ return 0;
}
#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
@@ -4727,11 +4881,11 @@ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr)
if (!(((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) ||
(fattr->valid & NFS_ATTR_FATTR_FILEID)) &&
(fattr->valid & NFS_ATTR_FATTR_FSID) &&
- (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)))
+ (fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS)))
return;
fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE |
- NFS_ATTR_FATTR_NLINK;
+ NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_V4_REFERRAL;
fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO;
fattr->nlink = 2;
}
@@ -4798,7 +4952,8 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct
return status;
}
-int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors)
+static int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
+ struct nfs4_secinfo_flavors *flavors)
{
struct nfs4_exception exception = { };
int err;
@@ -4852,6 +5007,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
{
nfs4_verifier verifier;
struct nfs41_exchange_id_args args = {
+ .verifier = &verifier,
.client = clp,
.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER,
};
@@ -4865,15 +5021,11 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
.rpc_resp = &res,
.rpc_cred = cred,
};
- __be32 *p;
dprintk("--> %s\n", __func__);
BUG_ON(clp == NULL);
- p = (u32 *)verifier.data;
- *p++ = htonl((u32)clp->cl_boot_time.tv_sec);
- *p = htonl((u32)clp->cl_boot_time.tv_nsec);
- args.verifier = &verifier;
+ nfs4_construct_boot_verifier(clp, &verifier);
args.id_len = scnprintf(args.id, sizeof(args.id),
"%s/%s.%s/%u",
@@ -4883,14 +5035,29 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
clp->cl_rpcclient->cl_auth->au_flavor);
res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL);
- if (unlikely(!res.server_scope))
- return -ENOMEM;
+ if (unlikely(!res.server_scope)) {
+ status = -ENOMEM;
+ goto out;
+ }
+
+ res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_KERNEL);
+ if (unlikely(!res.impl_id)) {
+ status = -ENOMEM;
+ goto out_server_scope;
+ }
status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
if (!status)
status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
if (!status) {
+ /* use the most recent implementation id */
+ kfree(clp->impl_id);
+ clp->impl_id = res.impl_id;
+ } else
+ kfree(res.impl_id);
+
+ if (!status) {
if (clp->server_scope &&
!nfs41_same_server_scope(clp->server_scope,
res.server_scope)) {
@@ -4901,12 +5068,21 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
clp->server_scope = NULL;
}
- if (!clp->server_scope)
+ if (!clp->server_scope) {
clp->server_scope = res.server_scope;
- else
- kfree(res.server_scope);
+ goto out;
+ }
}
+out_server_scope:
+ kfree(res.server_scope);
+out:
+ if (clp->impl_id)
+ dprintk("%s: Server Implementation ID: "
+ "domain: %s, name: %s, date: %llu,%u\n",
+ __func__, clp->impl_id->domain, clp->impl_id->name,
+ clp->impl_id->date.seconds,
+ clp->impl_id->date.nseconds);
dprintk("<-- %s status= %d\n", __func__, status);
return status;
}
@@ -4930,7 +5106,7 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
since we're invoked within one */
ret = nfs41_setup_sequence(data->clp->cl_session,
&data->args->la_seq_args,
- &data->res->lr_seq_res, 0, task);
+ &data->res->lr_seq_res, task);
BUG_ON(ret == -EAGAIN);
rpc_call_start(task);
@@ -4963,7 +5139,7 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
dprintk("<-- %s\n", __func__);
}
-struct rpc_call_ops nfs4_get_lease_time_ops = {
+static const struct rpc_call_ops nfs4_get_lease_time_ops = {
.rpc_call_prepare = nfs4_get_lease_time_prepare,
.rpc_call_done = nfs4_get_lease_time_done,
};
@@ -4994,6 +5170,7 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
};
int status;
+ nfs41_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0);
dprintk("--> %s\n", __func__);
task = rpc_run_task(&task_setup);
@@ -5008,37 +5185,53 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
return status;
}
+static struct nfs4_slot *nfs4_alloc_slots(u32 max_slots, gfp_t gfp_flags)
+{
+ return kcalloc(max_slots, sizeof(struct nfs4_slot), gfp_flags);
+}
+
+static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
+ struct nfs4_slot *new,
+ u32 max_slots,
+ u32 ivalue)
+{
+ struct nfs4_slot *old = NULL;
+ u32 i;
+
+ spin_lock(&tbl->slot_tbl_lock);
+ if (new) {
+ old = tbl->slots;
+ tbl->slots = new;
+ tbl->max_slots = max_slots;
+ }
+ tbl->highest_used_slotid = -1; /* no slot is currently used */
+ for (i = 0; i < tbl->max_slots; i++)
+ tbl->slots[i].seq_nr = ivalue;
+ spin_unlock(&tbl->slot_tbl_lock);
+ kfree(old);
+}
+
/*
- * Reset a slot table
+ * (re)Initialise a slot table
*/
-static int nfs4_reset_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
- int ivalue)
+static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
+ u32 ivalue)
{
struct nfs4_slot *new = NULL;
- int i;
- int ret = 0;
+ int ret = -ENOMEM;
dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
max_reqs, tbl->max_slots);
/* Does the newly negotiated max_reqs match the existing slot table? */
if (max_reqs != tbl->max_slots) {
- ret = -ENOMEM;
- new = kmalloc(max_reqs * sizeof(struct nfs4_slot),
- GFP_NOFS);
+ new = nfs4_alloc_slots(max_reqs, GFP_NOFS);
if (!new)
goto out;
- ret = 0;
- kfree(tbl->slots);
- }
- spin_lock(&tbl->slot_tbl_lock);
- if (new) {
- tbl->slots = new;
- tbl->max_slots = max_reqs;
}
- for (i = 0; i < tbl->max_slots; ++i)
- tbl->slots[i].seq_nr = ivalue;
- spin_unlock(&tbl->slot_tbl_lock);
+ ret = 0;
+
+ nfs4_add_and_init_slots(tbl, new, max_reqs, ivalue);
dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
tbl, tbl->slots, tbl->max_slots);
out:
@@ -5061,36 +5254,6 @@ static void nfs4_destroy_slot_tables(struct nfs4_session *session)
}
/*
- * Initialize slot table
- */
-static int nfs4_init_slot_table(struct nfs4_slot_table *tbl,
- int max_slots, int ivalue)
-{
- struct nfs4_slot *slot;
- int ret = -ENOMEM;
-
- BUG_ON(max_slots > NFS4_MAX_SLOT_TABLE);
-
- dprintk("--> %s: max_reqs=%u\n", __func__, max_slots);
-
- slot = kcalloc(max_slots, sizeof(struct nfs4_slot), GFP_NOFS);
- if (!slot)
- goto out;
- ret = 0;
-
- spin_lock(&tbl->slot_tbl_lock);
- tbl->max_slots = max_slots;
- tbl->slots = slot;
- tbl->highest_used_slotid = -1; /* no slot is currently used */
- spin_unlock(&tbl->slot_tbl_lock);
- dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
- tbl, tbl->slots, tbl->max_slots);
-out:
- dprintk("<-- %s: return %d\n", __func__, ret);
- return ret;
-}
-
-/*
* Initialize or reset the forechannel and backchannel tables
*/
static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
@@ -5101,25 +5264,16 @@ static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
dprintk("--> %s\n", __func__);
/* Fore channel */
tbl = &ses->fc_slot_table;
- if (tbl->slots == NULL) {
- status = nfs4_init_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
- if (status) /* -ENOMEM */
- return status;
- } else {
- status = nfs4_reset_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
- if (status)
- return status;
- }
+ status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
+ if (status) /* -ENOMEM */
+ return status;
/* Back channel */
tbl = &ses->bc_slot_table;
- if (tbl->slots == NULL) {
- status = nfs4_init_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
- if (status)
- /* Fore and back channel share a connection so get
- * both slot tables or neither */
- nfs4_destroy_slot_tables(ses);
- } else
- status = nfs4_reset_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
+ status = nfs4_realloc_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
+ if (status && tbl->slots == NULL)
+ /* Fore and back channel share a connection so get
+ * both slot tables or neither */
+ nfs4_destroy_slot_tables(ses);
return status;
}
@@ -5133,13 +5287,13 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
return NULL;
tbl = &session->fc_slot_table;
- tbl->highest_used_slotid = -1;
+ tbl->highest_used_slotid = NFS4_NO_SLOT;
spin_lock_init(&tbl->slot_tbl_lock);
rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
init_completion(&tbl->complete);
tbl = &session->bc_slot_table;
- tbl->highest_used_slotid = -1;
+ tbl->highest_used_slotid = NFS4_NO_SLOT;
spin_lock_init(&tbl->slot_tbl_lock);
rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
init_completion(&tbl->complete);
@@ -5152,11 +5306,16 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
void nfs4_destroy_session(struct nfs4_session *session)
{
+ struct rpc_xprt *xprt;
+
nfs4_proc_destroy_session(session);
+
+ rcu_read_lock();
+ xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt);
+ rcu_read_unlock();
dprintk("%s Destroy backchannel for xprt %p\n",
- __func__, session->clp->cl_rpcclient->cl_xprt);
- xprt_destroy_backchannel(session->clp->cl_rpcclient->cl_xprt,
- NFS41_BC_MIN_CALLBACKS);
+ __func__, xprt);
+ xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS);
nfs4_destroy_slot_tables(session);
kfree(session);
}
@@ -5184,7 +5343,7 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
args->fc_attrs.max_rqst_sz = mxrqst_sz;
args->fc_attrs.max_resp_sz = mxresp_sz;
args->fc_attrs.max_ops = NFS4_MAX_OPS;
- args->fc_attrs.max_reqs = session->clp->cl_rpcclient->cl_xprt->max_reqs;
+ args->fc_attrs.max_reqs = max_session_slots;
dprintk("%s: Fore Channel : max_rqst_sz=%u max_resp_sz=%u "
"max_ops=%u max_reqs=%u\n",
@@ -5224,6 +5383,8 @@ static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args
return -EINVAL;
if (rcvd->max_reqs == 0)
return -EINVAL;
+ if (rcvd->max_reqs > NFS4_MAX_SLOT_TABLE)
+ rcvd->max_reqs = NFS4_MAX_SLOT_TABLE;
return 0;
}
@@ -5239,9 +5400,9 @@ static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args
if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached)
return -EINVAL;
/* These would render the backchannel useless: */
- if (rcvd->max_ops == 0)
+ if (rcvd->max_ops != sent->max_ops)
return -EINVAL;
- if (rcvd->max_reqs == 0)
+ if (rcvd->max_reqs != sent->max_reqs)
return -EINVAL;
return 0;
}
@@ -5344,7 +5505,7 @@ int nfs4_proc_destroy_session(struct nfs4_session *session)
if (status)
printk(KERN_WARNING
- "Got error %d from the server on DESTROY_SESSION. "
+ "NFS: Got error %d from the server on DESTROY_SESSION. "
"Session has been destroyed regardless...\n", status);
dprintk("<-- nfs4_proc_destroy_session\n");
@@ -5467,7 +5628,7 @@ static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
args = task->tk_msg.rpc_argp;
res = task->tk_msg.rpc_resp;
- if (nfs41_setup_sequence(clp->cl_session, args, res, 0, task))
+ if (nfs41_setup_sequence(clp->cl_session, args, res, task))
return;
rpc_call_start(task);
}
@@ -5499,6 +5660,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
nfs_put_client(clp);
return ERR_PTR(-ENOMEM);
}
+ nfs41_init_sequence(&calldata->args, &calldata->res, 0);
msg.rpc_argp = &calldata->args;
msg.rpc_resp = &calldata->res;
calldata->clp = clp;
@@ -5560,7 +5722,7 @@ static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data)
rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
if (nfs41_setup_sequence(calldata->clp->cl_session,
&calldata->arg.seq_args,
- &calldata->res.seq_res, 0, task))
+ &calldata->res.seq_res, task))
return;
rpc_call_start(task);
@@ -5639,6 +5801,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
calldata->clp = clp;
calldata->arg.one_fs = 0;
+ nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0);
msg.rpc_argp = &calldata->arg;
msg.rpc_resp = &calldata->res;
task_setup_data.callback_data = calldata;
@@ -5670,7 +5833,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
* to be no way to prevent it completely.
*/
if (nfs4_setup_sequence(server, &lgp->args.seq_args,
- &lgp->res.seq_res, 0, task))
+ &lgp->res.seq_res, task))
return;
if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
NFS_I(lgp->args.inode)->layout,
@@ -5745,6 +5908,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
lgp->res.layoutp = &lgp->args.layout;
lgp->res.seq_res.sr_slot = NULL;
+ nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -5765,7 +5929,7 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
dprintk("--> %s\n", __func__);
if (nfs41_setup_sequence(lrp->clp->cl_session, &lrp->args.seq_args,
- &lrp->res.seq_res, 0, task))
+ &lrp->res.seq_res, task))
return;
rpc_call_start(task);
}
@@ -5831,6 +5995,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
int status;
dprintk("--> %s\n", __func__);
+ nfs41_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -5931,7 +6096,7 @@ static void nfs4_layoutcommit_prepare(struct rpc_task *task, void *calldata)
struct nfs_server *server = NFS_SERVER(data->args.inode);
if (nfs4_setup_sequence(server, &data->args.seq_args,
- &data->res.seq_res, 1, task))
+ &data->res.seq_res, task))
return;
rpc_call_start(task);
}
@@ -6018,6 +6183,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync)
data->args.lastbytewritten,
data->args.inode->i_ino);
+ nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -6111,11 +6277,12 @@ out_freepage:
out:
return err;
}
-static int _nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+
+static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
{
int status;
struct nfs41_test_stateid_args args = {
- .stateid = &state->stateid,
+ .stateid = stateid,
};
struct nfs41_test_stateid_res res;
struct rpc_message msg = {
@@ -6123,28 +6290,31 @@ static int _nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *sta
.rpc_argp = &args,
.rpc_resp = &res,
};
- args.seq_args.sa_session = res.seq_res.sr_session = NULL;
- status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
+
+ nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
+ status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
+
+ if (status == NFS_OK)
+ return res.status;
return status;
}
-static int nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
{
struct nfs4_exception exception = { };
int err;
do {
err = nfs4_handle_exception(server,
- _nfs41_test_stateid(server, state),
+ _nfs41_test_stateid(server, stateid),
&exception);
} while (exception.retry);
return err;
}
-static int _nfs4_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
{
- int status;
struct nfs41_free_stateid_args args = {
- .stateid = &state->stateid,
+ .stateid = stateid,
};
struct nfs41_free_stateid_res res;
struct rpc_message msg = {
@@ -6153,25 +6323,46 @@ static int _nfs4_free_stateid(struct nfs_server *server, struct nfs4_state *stat
.rpc_resp = &res,
};
- args.seq_args.sa_session = res.seq_res.sr_session = NULL;
- status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
- return status;
+ nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
+ return nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
}
-static int nfs41_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+static int nfs41_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
{
struct nfs4_exception exception = { };
int err;
do {
err = nfs4_handle_exception(server,
- _nfs4_free_stateid(server, state),
+ _nfs4_free_stateid(server, stateid),
&exception);
} while (exception.retry);
return err;
}
+
+static bool nfs41_match_stateid(const nfs4_stateid *s1,
+ const nfs4_stateid *s2)
+{
+ if (memcmp(s1->other, s2->other, sizeof(s1->other)) != 0)
+ return false;
+
+ if (s1->seqid == s2->seqid)
+ return true;
+ if (s1->seqid == 0 || s2->seqid == 0)
+ return true;
+
+ return false;
+}
+
#endif /* CONFIG_NFS_V4_1 */
-struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
+static bool nfs4_match_stateid(const nfs4_stateid *s1,
+ const nfs4_stateid *s2)
+{
+ return nfs4_stateid_match(s1, s2);
+}
+
+
+static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
.state_flag_bit = NFS_STATE_RECLAIM_REBOOT,
.recover_open = nfs4_open_reclaim,
@@ -6181,7 +6372,7 @@ struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
};
#if defined(CONFIG_NFS_V4_1)
-struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
+static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
.state_flag_bit = NFS_STATE_RECLAIM_REBOOT,
.recover_open = nfs4_open_reclaim,
@@ -6192,7 +6383,7 @@ struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
};
#endif /* CONFIG_NFS_V4_1 */
-struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
+static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
.state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
.recover_open = nfs4_open_expired,
@@ -6202,7 +6393,7 @@ struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
};
#if defined(CONFIG_NFS_V4_1)
-struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
+static const struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
.state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
.recover_open = nfs41_open_expired,
@@ -6212,14 +6403,14 @@ struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
};
#endif /* CONFIG_NFS_V4_1 */
-struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
+static const struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
.sched_state_renewal = nfs4_proc_async_renew,
.get_state_renewal_cred_locked = nfs4_get_renew_cred_locked,
.renew_lease = nfs4_proc_renew,
};
#if defined(CONFIG_NFS_V4_1)
-struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
+static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
.sched_state_renewal = nfs41_proc_async_sequence,
.get_state_renewal_cred_locked = nfs4_get_machine_cred_locked,
.renew_lease = nfs4_proc_sequence,
@@ -6229,7 +6420,7 @@ struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
.minor_version = 0,
.call_sync = _nfs4_call_sync,
- .validate_stateid = nfs4_validate_delegation_stateid,
+ .match_stateid = nfs4_match_stateid,
.find_root_sec = nfs4_find_root_sec,
.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
.nograce_recovery_ops = &nfs40_nograce_recovery_ops,
@@ -6240,7 +6431,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
.minor_version = 1,
.call_sync = _nfs4_call_sync_session,
- .validate_stateid = nfs41_validate_delegation_stateid,
+ .match_stateid = nfs41_match_stateid,
.find_root_sec = nfs41_find_root_sec,
.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
@@ -6280,9 +6471,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.create = nfs4_proc_create,
.remove = nfs4_proc_remove,
.unlink_setup = nfs4_proc_unlink_setup,
+ .unlink_rpc_prepare = nfs4_proc_unlink_rpc_prepare,
.unlink_done = nfs4_proc_unlink_done,
.rename = nfs4_proc_rename,
.rename_setup = nfs4_proc_rename_setup,
+ .rename_rpc_prepare = nfs4_proc_rename_rpc_prepare,
.rename_done = nfs4_proc_rename_done,
.link = nfs4_proc_link,
.symlink = nfs4_proc_symlink,
@@ -6296,8 +6489,10 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.set_capabilities = nfs4_server_capabilities,
.decode_dirent = nfs4_decode_dirent,
.read_setup = nfs4_proc_read_setup,
+ .read_rpc_prepare = nfs4_proc_read_rpc_prepare,
.read_done = nfs4_read_done,
.write_setup = nfs4_proc_write_setup,
+ .write_rpc_prepare = nfs4_proc_write_rpc_prepare,
.write_done = nfs4_write_done,
.commit_setup = nfs4_proc_commit_setup,
.commit_done = nfs4_commit_done,
@@ -6321,6 +6516,10 @@ const struct xattr_handler *nfs4_xattr_handlers[] = {
NULL
};
+module_param(max_session_slots, ushort, 0644);
+MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
+ "requests the client will negotiate");
+
/*
* Local variables:
* c-basic-offset: 8
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index a53f33b..0f43414 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -146,6 +146,11 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
struct rpc_cred *cred = NULL;
struct nfs_server *server;
+ /* Use machine credentials if available */
+ cred = nfs4_get_machine_cred_locked(clp);
+ if (cred != NULL)
+ goto out;
+
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
cred = nfs4_get_renew_cred_server_locked(server);
@@ -153,6 +158,8 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
break;
}
rcu_read_unlock();
+
+out:
return cred;
}
@@ -190,30 +197,29 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp)
static void nfs4_end_drain_session(struct nfs_client *clp)
{
struct nfs4_session *ses = clp->cl_session;
+ struct nfs4_slot_table *tbl;
int max_slots;
if (ses == NULL)
return;
+ tbl = &ses->fc_slot_table;
if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
- spin_lock(&ses->fc_slot_table.slot_tbl_lock);
- max_slots = ses->fc_slot_table.max_slots;
+ spin_lock(&tbl->slot_tbl_lock);
+ max_slots = tbl->max_slots;
while (max_slots--) {
- struct rpc_task *task;
-
- task = rpc_wake_up_next(&ses->fc_slot_table.
- slot_tbl_waitq);
- if (!task)
+ if (rpc_wake_up_first(&tbl->slot_tbl_waitq,
+ nfs4_set_task_privileged,
+ NULL) == NULL)
break;
- rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
}
- spin_unlock(&ses->fc_slot_table.slot_tbl_lock);
+ spin_unlock(&tbl->slot_tbl_lock);
}
}
static int nfs4_wait_on_slot_tbl(struct nfs4_slot_table *tbl)
{
spin_lock(&tbl->slot_tbl_lock);
- if (tbl->highest_used_slotid != -1) {
+ if (tbl->highest_used_slotid != NFS4_NO_SLOT) {
INIT_COMPLETION(tbl->complete);
spin_unlock(&tbl->slot_tbl_lock);
return wait_for_completion_interruptible(&tbl->complete);
@@ -317,62 +323,6 @@ out:
return cred;
}
-static void nfs_alloc_unique_id_locked(struct rb_root *root,
- struct nfs_unique_id *new,
- __u64 minval, int maxbits)
-{
- struct rb_node **p, *parent;
- struct nfs_unique_id *pos;
- __u64 mask = ~0ULL;
-
- if (maxbits < 64)
- mask = (1ULL << maxbits) - 1ULL;
-
- /* Ensure distribution is more or less flat */
- get_random_bytes(&new->id, sizeof(new->id));
- new->id &= mask;
- if (new->id < minval)
- new->id += minval;
-retry:
- p = &root->rb_node;
- parent = NULL;
-
- while (*p != NULL) {
- parent = *p;
- pos = rb_entry(parent, struct nfs_unique_id, rb_node);
-
- if (new->id < pos->id)
- p = &(*p)->rb_left;
- else if (new->id > pos->id)
- p = &(*p)->rb_right;
- else
- goto id_exists;
- }
- rb_link_node(&new->rb_node, parent, p);
- rb_insert_color(&new->rb_node, root);
- return;
-id_exists:
- for (;;) {
- new->id++;
- if (new->id < minval || (new->id & mask) != new->id) {
- new->id = minval;
- break;
- }
- parent = rb_next(parent);
- if (parent == NULL)
- break;
- pos = rb_entry(parent, struct nfs_unique_id, rb_node);
- if (new->id < pos->id)
- break;
- }
- goto retry;
-}
-
-static void nfs_free_unique_id(struct rb_root *root, struct nfs_unique_id *id)
-{
- rb_erase(&id->rb_node, root);
-}
-
static struct nfs4_state_owner *
nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
{
@@ -405,6 +355,7 @@ nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
struct rb_node **p = &server->state_owners.rb_node,
*parent = NULL;
struct nfs4_state_owner *sp;
+ int err;
while (*p != NULL) {
parent = *p;
@@ -421,8 +372,9 @@ nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
return sp;
}
}
- nfs_alloc_unique_id_locked(&server->openowner_id,
- &new->so_owner_id, 1, 64);
+ err = ida_get_new(&server->openowner_id, &new->so_seqid.owner_id);
+ if (err)
+ return ERR_PTR(err);
rb_link_node(&new->so_server_node, parent, p);
rb_insert_color(&new->so_server_node, &server->state_owners);
return new;
@@ -435,7 +387,23 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
if (!RB_EMPTY_NODE(&sp->so_server_node))
rb_erase(&sp->so_server_node, &server->state_owners);
- nfs_free_unique_id(&server->openowner_id, &sp->so_owner_id);
+ ida_remove(&server->openowner_id, sp->so_seqid.owner_id);
+}
+
+static void
+nfs4_init_seqid_counter(struct nfs_seqid_counter *sc)
+{
+ sc->flags = 0;
+ sc->counter = 0;
+ spin_lock_init(&sc->lock);
+ INIT_LIST_HEAD(&sc->list);
+ rpc_init_wait_queue(&sc->wait, "Seqid_waitqueue");
+}
+
+static void
+nfs4_destroy_seqid_counter(struct nfs_seqid_counter *sc)
+{
+ rpc_destroy_wait_queue(&sc->wait);
}
/*
@@ -444,19 +412,20 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
*
*/
static struct nfs4_state_owner *
-nfs4_alloc_state_owner(void)
+nfs4_alloc_state_owner(struct nfs_server *server,
+ struct rpc_cred *cred,
+ gfp_t gfp_flags)
{
struct nfs4_state_owner *sp;
- sp = kzalloc(sizeof(*sp),GFP_NOFS);
+ sp = kzalloc(sizeof(*sp), gfp_flags);
if (!sp)
return NULL;
+ sp->so_server = server;
+ sp->so_cred = get_rpccred(cred);
spin_lock_init(&sp->so_lock);
INIT_LIST_HEAD(&sp->so_states);
- rpc_init_wait_queue(&sp->so_sequence.wait, "Seqid_waitqueue");
- sp->so_seqid.sequence = &sp->so_sequence;
- spin_lock_init(&sp->so_sequence.lock);
- INIT_LIST_HEAD(&sp->so_sequence.list);
+ nfs4_init_seqid_counter(&sp->so_seqid);
atomic_set(&sp->so_count, 1);
INIT_LIST_HEAD(&sp->so_lru);
return sp;
@@ -478,7 +447,7 @@ nfs4_drop_state_owner(struct nfs4_state_owner *sp)
static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
{
- rpc_destroy_wait_queue(&sp->so_sequence.wait);
+ nfs4_destroy_seqid_counter(&sp->so_seqid);
put_rpccred(sp->so_cred);
kfree(sp);
}
@@ -516,7 +485,8 @@ static void nfs4_gc_state_owners(struct nfs_server *server)
* Returns a pointer to an instantiated nfs4_state_owner struct, or NULL.
*/
struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
- struct rpc_cred *cred)
+ struct rpc_cred *cred,
+ gfp_t gfp_flags)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state_owner *sp, *new;
@@ -526,20 +496,18 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
spin_unlock(&clp->cl_lock);
if (sp != NULL)
goto out;
- new = nfs4_alloc_state_owner();
+ new = nfs4_alloc_state_owner(server, cred, gfp_flags);
if (new == NULL)
goto out;
- new->so_server = server;
- new->so_cred = cred;
- spin_lock(&clp->cl_lock);
- sp = nfs4_insert_state_owner_locked(new);
- spin_unlock(&clp->cl_lock);
- if (sp == new)
- get_rpccred(cred);
- else {
- rpc_destroy_wait_queue(&new->so_sequence.wait);
- kfree(new);
- }
+ do {
+ if (ida_pre_get(&server->openowner_id, gfp_flags) == 0)
+ break;
+ spin_lock(&clp->cl_lock);
+ sp = nfs4_insert_state_owner_locked(new);
+ spin_unlock(&clp->cl_lock);
+ } while (sp == ERR_PTR(-EAGAIN));
+ if (sp != new)
+ nfs4_free_state_owner(new);
out:
nfs4_gc_state_owners(server);
return sp;
@@ -795,15 +763,11 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
{
struct nfs4_lock_state *lsp;
struct nfs_server *server = state->owner->so_server;
- struct nfs_client *clp = server->nfs_client;
lsp = kzalloc(sizeof(*lsp), GFP_NOFS);
if (lsp == NULL)
return NULL;
- rpc_init_wait_queue(&lsp->ls_sequence.wait, "lock_seqid_waitqueue");
- spin_lock_init(&lsp->ls_sequence.lock);
- INIT_LIST_HEAD(&lsp->ls_sequence.list);
- lsp->ls_seqid.sequence = &lsp->ls_sequence;
+ nfs4_init_seqid_counter(&lsp->ls_seqid);
atomic_set(&lsp->ls_count, 1);
lsp->ls_state = state;
lsp->ls_owner.lo_type = type;
@@ -815,25 +779,22 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
lsp->ls_owner.lo_u.posix_owner = fl_owner;
break;
default:
- kfree(lsp);
- return NULL;
+ goto out_free;
}
- spin_lock(&clp->cl_lock);
- nfs_alloc_unique_id_locked(&server->lockowner_id, &lsp->ls_id, 1, 64);
- spin_unlock(&clp->cl_lock);
+ lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
+ if (lsp->ls_seqid.owner_id < 0)
+ goto out_free;
INIT_LIST_HEAD(&lsp->ls_locks);
return lsp;
+out_free:
+ kfree(lsp);
+ return NULL;
}
-static void nfs4_free_lock_state(struct nfs4_lock_state *lsp)
+void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
{
- struct nfs_server *server = lsp->ls_state->owner->so_server;
- struct nfs_client *clp = server->nfs_client;
-
- spin_lock(&clp->cl_lock);
- nfs_free_unique_id(&server->lockowner_id, &lsp->ls_id);
- spin_unlock(&clp->cl_lock);
- rpc_destroy_wait_queue(&lsp->ls_sequence.wait);
+ ida_simple_remove(&server->lockowner_id, lsp->ls_seqid.owner_id);
+ nfs4_destroy_seqid_counter(&lsp->ls_seqid);
kfree(lsp);
}
@@ -865,7 +826,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_
}
spin_unlock(&state->state_lock);
if (new != NULL)
- nfs4_free_lock_state(new);
+ nfs4_free_lock_state(state->owner->so_server, new);
return lsp;
}
@@ -886,9 +847,11 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
if (list_empty(&state->lock_states))
clear_bit(LK_STATE_IN_USE, &state->flags);
spin_unlock(&state->state_lock);
- if (lsp->ls_flags & NFS_LOCK_INITIALIZED)
- nfs4_release_lockowner(lsp);
- nfs4_free_lock_state(lsp);
+ if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+ if (nfs4_release_lockowner(lsp) == 0)
+ return;
+ }
+ nfs4_free_lock_state(lsp->ls_state->owner->so_server, lsp);
}
static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
@@ -918,7 +881,8 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
if (fl->fl_flags & FL_POSIX)
lsp = nfs4_get_lock_state(state, fl->fl_owner, 0, NFS4_POSIX_LOCK_TYPE);
else if (fl->fl_flags & FL_FLOCK)
- lsp = nfs4_get_lock_state(state, 0, fl->fl_pid, NFS4_FLOCK_LOCK_TYPE);
+ lsp = nfs4_get_lock_state(state, NULL, fl->fl_pid,
+ NFS4_FLOCK_LOCK_TYPE);
else
return -EINVAL;
if (lsp == NULL)
@@ -928,28 +892,49 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
return 0;
}
-/*
- * Byte-range lock aware utility to initialize the stateid of read/write
- * requests.
- */
-void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid)
+static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state,
+ fl_owner_t fl_owner, pid_t fl_pid)
{
struct nfs4_lock_state *lsp;
- int seq;
+ bool ret = false;
- do {
- seq = read_seqbegin(&state->seqlock);
- memcpy(dst, &state->stateid, sizeof(*dst));
- } while (read_seqretry(&state->seqlock, seq));
if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
- return;
+ goto out;
spin_lock(&state->state_lock);
lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
- if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
- memcpy(dst, &lsp->ls_stateid, sizeof(*dst));
+ if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0) {
+ nfs4_stateid_copy(dst, &lsp->ls_stateid);
+ ret = true;
+ }
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
+out:
+ return ret;
+}
+
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+{
+ int seq;
+
+ do {
+ seq = read_seqbegin(&state->seqlock);
+ nfs4_stateid_copy(dst, &state->stateid);
+ } while (read_seqretry(&state->seqlock, seq));
+}
+
+/*
+ * Byte-range lock aware utility to initialize the stateid of read/write
+ * requests.
+ */
+void nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
+ fmode_t fmode, fl_owner_t fl_owner, pid_t fl_pid)
+{
+ if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+ return;
+ if (nfs4_copy_lock_stateid(dst, state, fl_owner, fl_pid))
+ return;
+ nfs4_copy_open_stateid(dst, state);
}
struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask)
@@ -960,20 +945,28 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_m
if (new != NULL) {
new->sequence = counter;
INIT_LIST_HEAD(&new->list);
+ new->task = NULL;
}
return new;
}
void nfs_release_seqid(struct nfs_seqid *seqid)
{
- if (!list_empty(&seqid->list)) {
- struct rpc_sequence *sequence = seqid->sequence->sequence;
+ struct nfs_seqid_counter *sequence;
- spin_lock(&sequence->lock);
- list_del_init(&seqid->list);
- spin_unlock(&sequence->lock);
- rpc_wake_up(&sequence->wait);
+ if (list_empty(&seqid->list))
+ return;
+ sequence = seqid->sequence;
+ spin_lock(&sequence->lock);
+ list_del_init(&seqid->list);
+ if (!list_empty(&sequence->list)) {
+ struct nfs_seqid *next;
+
+ next = list_first_entry(&sequence->list,
+ struct nfs_seqid, list);
+ rpc_wake_up_queued_task(&sequence->wait, next->task);
}
+ spin_unlock(&sequence->lock);
}
void nfs_free_seqid(struct nfs_seqid *seqid)
@@ -989,14 +982,14 @@ void nfs_free_seqid(struct nfs_seqid *seqid)
*/
static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
{
- BUG_ON(list_first_entry(&seqid->sequence->sequence->list, struct nfs_seqid, list) != seqid);
+ BUG_ON(list_first_entry(&seqid->sequence->list, struct nfs_seqid, list) != seqid);
switch (status) {
case 0:
break;
case -NFS4ERR_BAD_SEQID:
if (seqid->sequence->flags & NFS_SEQID_CONFIRMED)
return;
- printk(KERN_WARNING "NFS: v4 server returned a bad"
+ pr_warn_ratelimited("NFS: v4 server returned a bad"
" sequence-id error on an"
" unconfirmed sequence %p!\n",
seqid->sequence);
@@ -1040,10 +1033,11 @@ void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
{
- struct rpc_sequence *sequence = seqid->sequence->sequence;
+ struct nfs_seqid_counter *sequence = seqid->sequence;
int status = 0;
spin_lock(&sequence->lock);
+ seqid->task = task;
if (list_empty(&seqid->list))
list_add_tail(&seqid->list, &sequence->list);
if (list_first_entry(&sequence->list, struct nfs_seqid, list) == seqid)
@@ -1072,19 +1066,28 @@ static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
void nfs4_schedule_state_manager(struct nfs_client *clp)
{
struct task_struct *task;
+ char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
return;
__module_get(THIS_MODULE);
atomic_inc(&clp->cl_count);
- task = kthread_run(nfs4_run_state_manager, clp, "%s-manager",
- rpc_peeraddr2str(clp->cl_rpcclient,
- RPC_DISPLAY_ADDR));
- if (!IS_ERR(task))
- return;
- nfs4_clear_state_manager_bit(clp);
- nfs_put_client(clp);
- module_put(THIS_MODULE);
+
+ /* The rcu_read_lock() is not strictly necessary, as the state
+ * manager is the only thread that ever changes the rpc_xprt
+ * after it's initialized. At this point, we're single threaded. */
+ rcu_read_lock();
+ snprintf(buf, sizeof(buf), "%s-manager",
+ rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+ rcu_read_unlock();
+ task = kthread_run(nfs4_run_state_manager, clp, buf);
+ if (IS_ERR(task)) {
+ printk(KERN_ERR "%s: kthread_run: %ld\n",
+ __func__, PTR_ERR(task));
+ nfs4_clear_state_manager_bit(clp);
+ nfs_put_client(clp);
+ module_put(THIS_MODULE);
+ }
}
/*
@@ -1098,10 +1101,25 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
nfs4_schedule_state_manager(clp);
}
+EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
+
+/*
+ * nfs40_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
+ * @clp: client to process
+ *
+ * Set the NFS4CLNT_LEASE_EXPIRED state in order to force a
+ * resend of the SETCLIENTID and hence re-establish the
+ * callback channel. Then return all existing delegations.
+ */
+static void nfs40_handle_cb_pathdown(struct nfs_client *clp)
+{
+ set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+ nfs_expire_all_delegations(clp);
+}
void nfs4_schedule_path_down_recovery(struct nfs_client *clp)
{
- nfs_handle_cb_pathdown(clp);
+ nfs40_handle_cb_pathdown(clp);
nfs4_schedule_state_manager(clp);
}
@@ -1135,6 +1153,34 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4
nfs4_state_mark_reclaim_nograce(clp, state);
nfs4_schedule_state_manager(clp);
}
+EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
+
+void nfs_inode_find_state_and_recover(struct inode *inode,
+ const nfs4_stateid *stateid)
+{
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_open_context *ctx;
+ struct nfs4_state *state;
+ bool found = false;
+
+ spin_lock(&inode->i_lock);
+ list_for_each_entry(ctx, &nfsi->open_files, list) {
+ state = ctx->state;
+ if (state == NULL)
+ continue;
+ if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
+ continue;
+ if (!nfs4_stateid_match(&state->stateid, stateid))
+ continue;
+ nfs4_state_mark_reclaim_nograce(clp, state);
+ found = true;
+ }
+ spin_unlock(&inode->i_lock);
+ if (found)
+ nfs4_schedule_state_manager(clp);
+}
+
static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
{
@@ -1173,8 +1219,8 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
goto out;
default:
- printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
- __func__, status);
+ printk(KERN_ERR "NFS: %s: unhandled error %d. "
+ "Zeroing state\n", __func__, status);
case -ENOMEM:
case -NFS4ERR_DENIED:
case -NFS4ERR_RECLAIM_BAD:
@@ -1220,8 +1266,9 @@ restart:
spin_lock(&state->state_lock);
list_for_each_entry(lock, &state->lock_states, ls_locks) {
if (!(lock->ls_flags & NFS_LOCK_INITIALIZED))
- printk("%s: Lock reclaim failed!\n",
- __func__);
+ pr_warn_ratelimited("NFS: "
+ "%s: Lock reclaim "
+ "failed!\n", __func__);
}
spin_unlock(&state->state_lock);
nfs4_put_open_state(state);
@@ -1230,8 +1277,8 @@ restart:
}
switch (status) {
default:
- printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
- __func__, status);
+ printk(KERN_ERR "NFS: %s: unhandled error %d. "
+ "Zeroing state\n", __func__, status);
case -ENOENT:
case -ENOMEM:
case -ESTALE:
@@ -1239,8 +1286,8 @@ restart:
* Open state on this file cannot be recovered
* All we can do is revert to using the zero stateid.
*/
- memset(state->stateid.data, 0,
- sizeof(state->stateid.data));
+ memset(&state->stateid, 0,
+ sizeof(state->stateid));
/* Mark the file as being 'closed' */
state->state = 0;
break;
@@ -1418,7 +1465,7 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
case 0:
break;
case -NFS4ERR_CB_PATH_DOWN:
- nfs_handle_cb_pathdown(clp);
+ nfs40_handle_cb_pathdown(clp);
break;
case -NFS4ERR_NO_GRACE:
nfs4_state_end_reclaim_reboot(clp);
@@ -1799,7 +1846,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
} while (atomic_read(&clp->cl_count) > 1);
return;
out_error:
- printk(KERN_WARNING "Error: state manager failed on NFSv4 server %s"
+ pr_warn_ratelimited("NFS: state manager failed on NFSv4 server %s"
" with error %d\n", clp->cl_hostname, -status);
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 95e92e4..c74fdb1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -44,6 +44,8 @@
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/kdev_t.h>
+#include <linux/module.h>
+#include <linux/utsname.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/msg_prot.h>
#include <linux/sunrpc/gss_api.h>
@@ -271,7 +273,12 @@ static int nfs4_stat_to_errno(int);
1 /* flags */ + \
1 /* spa_how */ + \
0 /* SP4_NONE (for now) */ + \
- 1 /* zero implemetation id array */)
+ 1 /* implementation id array of size 1 */ + \
+ 1 /* nii_domain */ + \
+ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+ 1 /* nii_name */ + \
+ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+ 3 /* nii_date */)
#define decode_exchange_id_maxsz (op_decode_hdr_maxsz + \
2 /* eir_clientid */ + \
1 /* eir_sequenceid */ + \
@@ -284,7 +291,11 @@ static int nfs4_stat_to_errno(int);
/* eir_server_scope<> */ \
XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \
1 /* eir_server_impl_id array length */ + \
- 0 /* ignored eir_server_impl_id contents */)
+ 1 /* nii_domain */ + \
+ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+ 1 /* nii_name */ + \
+ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+ 3 /* nii_date */)
#define encode_channel_attrs_maxsz (6 + 1 /* ca_rdma_ird.len (0) */)
#define decode_channel_attrs_maxsz (6 + \
1 /* ca_rdma_ird.len */ + \
@@ -838,6 +849,12 @@ const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
XDR_UNIT);
#endif /* CONFIG_NFS_V4_1 */
+static unsigned short send_implementation_id = 1;
+
+module_param(send_implementation_id, ushort, 0644);
+MODULE_PARM_DESC(send_implementation_id,
+ "Send implementation ID with NFSv4.1 exchange_id");
+
static const umode_t nfs_type2fmt[] = {
[NF4BAD] = 0,
[NF4REG] = S_IFREG,
@@ -868,15 +885,44 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes)
return p;
}
+static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, len);
+ xdr_encode_opaque_fixed(p, buf, len);
+}
+
static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
{
__be32 *p;
- p = xdr_reserve_space(xdr, 4 + len);
- BUG_ON(p == NULL);
+ p = reserve_space(xdr, 4 + len);
xdr_encode_opaque(p, str, len);
}
+static void encode_uint32(struct xdr_stream *xdr, u32 n)
+{
+ __be32 *p;
+
+ p = reserve_space(xdr, 4);
+ *p = cpu_to_be32(n);
+}
+
+static void encode_uint64(struct xdr_stream *xdr, u64 n)
+{
+ __be32 *p;
+
+ p = reserve_space(xdr, 8);
+ xdr_encode_hyper(p, n);
+}
+
+static void encode_nfs4_seqid(struct xdr_stream *xdr,
+ const struct nfs_seqid *seqid)
+{
+ encode_uint32(xdr, seqid->sequence->counter);
+}
+
static void encode_compound_hdr(struct xdr_stream *xdr,
struct rpc_rqst *req,
struct compound_hdr *hdr)
@@ -889,28 +935,37 @@ static void encode_compound_hdr(struct xdr_stream *xdr,
* but this is not required as a MUST for the server to do so. */
hdr->replen = RPC_REPHDRSIZE + auth->au_rslack + 3 + hdr->taglen;
- dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag);
BUG_ON(hdr->taglen > NFS4_MAXTAGLEN);
- p = reserve_space(xdr, 4 + hdr->taglen + 8);
- p = xdr_encode_opaque(p, hdr->tag, hdr->taglen);
+ encode_string(xdr, hdr->taglen, hdr->tag);
+ p = reserve_space(xdr, 8);
*p++ = cpu_to_be32(hdr->minorversion);
hdr->nops_p = p;
*p = cpu_to_be32(hdr->nops);
}
+static void encode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 op,
+ uint32_t replen,
+ struct compound_hdr *hdr)
+{
+ encode_uint32(xdr, op);
+ hdr->nops++;
+ hdr->replen += replen;
+}
+
static void encode_nops(struct compound_hdr *hdr)
{
BUG_ON(hdr->nops > NFS4_MAX_OPS);
*hdr->nops_p = htonl(hdr->nops);
}
-static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *verf)
+static void encode_nfs4_stateid(struct xdr_stream *xdr, const nfs4_stateid *stateid)
{
- __be32 *p;
+ encode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
+}
- p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
- BUG_ON(p == NULL);
- xdr_encode_opaque_fixed(p, verf->data, NFS4_VERIFIER_SIZE);
+static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *verf)
+{
+ encode_opaque_fixed(xdr, verf->data, NFS4_VERIFIER_SIZE);
}
static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const struct nfs_server *server)
@@ -1023,7 +1078,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
* Now we backfill the bitmap and the attribute buffer length.
*/
if (len != ((char *)p - (char *)q) + 4) {
- printk(KERN_ERR "nfs: Attr length error, %u != %Zu\n",
+ printk(KERN_ERR "NFS: Attr length error, %u != %Zu\n",
len, ((char *)p - (char *)q) + 4);
BUG();
}
@@ -1037,46 +1092,33 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 8);
- *p++ = cpu_to_be32(OP_ACCESS);
- *p = cpu_to_be32(access);
- hdr->nops++;
- hdr->replen += decode_access_maxsz;
+ encode_op_hdr(xdr, OP_ACCESS, decode_access_maxsz, hdr);
+ encode_uint32(xdr, access);
}
static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 8+NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_CLOSE);
- *p++ = cpu_to_be32(arg->seqid->sequence->counter);
- xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE);
- hdr->nops++;
- hdr->replen += decode_close_maxsz;
+ encode_op_hdr(xdr, OP_CLOSE, decode_close_maxsz, hdr);
+ encode_nfs4_seqid(xdr, arg->seqid);
+ encode_nfs4_stateid(xdr, arg->stateid);
}
static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 16);
- *p++ = cpu_to_be32(OP_COMMIT);
+ encode_op_hdr(xdr, OP_COMMIT, decode_commit_maxsz, hdr);
+ p = reserve_space(xdr, 12);
p = xdr_encode_hyper(p, args->offset);
*p = cpu_to_be32(args->count);
- hdr->nops++;
- hdr->replen += decode_commit_maxsz;
}
static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *create, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 8);
- *p++ = cpu_to_be32(OP_CREATE);
- *p = cpu_to_be32(create->ftype);
+ encode_op_hdr(xdr, OP_CREATE, decode_create_maxsz, hdr);
+ encode_uint32(xdr, create->ftype);
switch (create->ftype) {
case NF4LNK:
@@ -1096,9 +1138,6 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *
}
encode_string(xdr, create->name->len, create->name->name);
- hdr->nops++;
- hdr->replen += decode_create_maxsz;
-
encode_attrs(xdr, create->attrs, create->server);
}
@@ -1106,25 +1145,21 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c
{
__be32 *p;
- p = reserve_space(xdr, 12);
- *p++ = cpu_to_be32(OP_GETATTR);
+ encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr);
+ p = reserve_space(xdr, 8);
*p++ = cpu_to_be32(1);
*p = cpu_to_be32(bitmap);
- hdr->nops++;
- hdr->replen += decode_getattr_maxsz;
}
static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm1, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 16);
- *p++ = cpu_to_be32(OP_GETATTR);
+ encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr);
+ p = reserve_space(xdr, 12);
*p++ = cpu_to_be32(2);
*p++ = cpu_to_be32(bm0);
*p = cpu_to_be32(bm1);
- hdr->nops++;
- hdr->replen += decode_getattr_maxsz;
}
static void
@@ -1134,8 +1169,7 @@ encode_getattr_three(struct xdr_stream *xdr,
{
__be32 *p;
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_GETATTR);
+ encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr);
if (bm2) {
p = reserve_space(xdr, 16);
*p++ = cpu_to_be32(3);
@@ -1152,8 +1186,6 @@ encode_getattr_three(struct xdr_stream *xdr,
*p++ = cpu_to_be32(1);
*p = cpu_to_be32(bm0);
}
- hdr->nops++;
- hdr->replen += decode_getattr_maxsz;
}
static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -1179,23 +1211,13 @@ static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, stru
static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_GETFH);
- hdr->nops++;
- hdr->replen += decode_getfh_maxsz;
+ encode_op_hdr(xdr, OP_GETFH, decode_getfh_maxsz, hdr);
}
static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 8 + name->len);
- *p++ = cpu_to_be32(OP_LINK);
- xdr_encode_opaque(p, name->name, name->len);
- hdr->nops++;
- hdr->replen += decode_link_maxsz;
+ encode_op_hdr(xdr, OP_LINK, decode_link_maxsz, hdr);
+ encode_string(xdr, name->len, name->name);
}
static inline int nfs4_lock_type(struct file_lock *fl, int block)
@@ -1232,79 +1254,60 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args
{
__be32 *p;
- p = reserve_space(xdr, 32);
- *p++ = cpu_to_be32(OP_LOCK);
+ encode_op_hdr(xdr, OP_LOCK, decode_lock_maxsz, hdr);
+ p = reserve_space(xdr, 28);
*p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block));
*p++ = cpu_to_be32(args->reclaim);
p = xdr_encode_hyper(p, args->fl->fl_start);
p = xdr_encode_hyper(p, nfs4_lock_length(args->fl));
*p = cpu_to_be32(args->new_lock_owner);
if (args->new_lock_owner){
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
- *p++ = cpu_to_be32(args->open_seqid->sequence->counter);
- p = xdr_encode_opaque_fixed(p, args->open_stateid->data, NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(args->lock_seqid->sequence->counter);
+ encode_nfs4_seqid(xdr, args->open_seqid);
+ encode_nfs4_stateid(xdr, args->open_stateid);
+ encode_nfs4_seqid(xdr, args->lock_seqid);
encode_lockowner(xdr, &args->lock_owner);
}
else {
- p = reserve_space(xdr, NFS4_STATEID_SIZE+4);
- p = xdr_encode_opaque_fixed(p, args->lock_stateid->data, NFS4_STATEID_SIZE);
- *p = cpu_to_be32(args->lock_seqid->sequence->counter);
+ encode_nfs4_stateid(xdr, args->lock_stateid);
+ encode_nfs4_seqid(xdr, args->lock_seqid);
}
- hdr->nops++;
- hdr->replen += decode_lock_maxsz;
}
static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *args, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 24);
- *p++ = cpu_to_be32(OP_LOCKT);
+ encode_op_hdr(xdr, OP_LOCKT, decode_lockt_maxsz, hdr);
+ p = reserve_space(xdr, 20);
*p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0));
p = xdr_encode_hyper(p, args->fl->fl_start);
p = xdr_encode_hyper(p, nfs4_lock_length(args->fl));
encode_lockowner(xdr, &args->lock_owner);
- hdr->nops++;
- hdr->replen += decode_lockt_maxsz;
}
static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *args, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 12+NFS4_STATEID_SIZE+16);
- *p++ = cpu_to_be32(OP_LOCKU);
- *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0));
- *p++ = cpu_to_be32(args->seqid->sequence->counter);
- p = xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
+ encode_op_hdr(xdr, OP_LOCKU, decode_locku_maxsz, hdr);
+ encode_uint32(xdr, nfs4_lock_type(args->fl, 0));
+ encode_nfs4_seqid(xdr, args->seqid);
+ encode_nfs4_stateid(xdr, args->stateid);
+ p = reserve_space(xdr, 16);
p = xdr_encode_hyper(p, args->fl->fl_start);
xdr_encode_hyper(p, nfs4_lock_length(args->fl));
- hdr->nops++;
- hdr->replen += decode_locku_maxsz;
}
static void encode_release_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_RELEASE_LOCKOWNER);
+ encode_op_hdr(xdr, OP_RELEASE_LOCKOWNER, decode_release_lockowner_maxsz, hdr);
encode_lockowner(xdr, lowner);
- hdr->nops++;
- hdr->replen += decode_release_lockowner_maxsz;
}
static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
{
- int len = name->len;
- __be32 *p;
-
- p = reserve_space(xdr, 8 + len);
- *p++ = cpu_to_be32(OP_LOOKUP);
- xdr_encode_opaque(p, name->name, len);
- hdr->nops++;
- hdr->replen += decode_lookup_maxsz;
+ encode_op_hdr(xdr, OP_LOOKUP, decode_lookup_maxsz, hdr);
+ encode_string(xdr, name->len, name->name);
}
static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode)
@@ -1335,9 +1338,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
* opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4,
* owner 4 = 32
*/
- p = reserve_space(xdr, 8);
- *p++ = cpu_to_be32(OP_OPEN);
- *p = cpu_to_be32(arg->seqid->sequence->counter);
+ encode_nfs4_seqid(xdr, arg->seqid);
encode_share_access(xdr, arg->fmode);
p = reserve_space(xdr, 32);
p = xdr_encode_hyper(p, arg->clientid);
@@ -1437,14 +1438,15 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc
{
__be32 *p;
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR);
- xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE);
+ p = reserve_space(xdr, 4);
+ *p = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR);
+ encode_nfs4_stateid(xdr, stateid);
encode_string(xdr, name->len, name->name);
}
static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg, struct compound_hdr *hdr)
{
+ encode_op_hdr(xdr, OP_OPEN, decode_open_maxsz, hdr);
encode_openhdr(xdr, arg);
encode_opentype(xdr, arg);
switch (arg->claim) {
@@ -1460,88 +1462,64 @@ static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg,
default:
BUG();
}
- hdr->nops++;
- hdr->replen += decode_open_maxsz;
}
static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_confirmargs *arg, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
- *p++ = cpu_to_be32(OP_OPEN_CONFIRM);
- p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE);
- *p = cpu_to_be32(arg->seqid->sequence->counter);
- hdr->nops++;
- hdr->replen += decode_open_confirm_maxsz;
+ encode_op_hdr(xdr, OP_OPEN_CONFIRM, decode_open_confirm_maxsz, hdr);
+ encode_nfs4_stateid(xdr, arg->stateid);
+ encode_nfs4_seqid(xdr, arg->seqid);
}
static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
- *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE);
- p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE);
- *p = cpu_to_be32(arg->seqid->sequence->counter);
+ encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr);
+ encode_nfs4_stateid(xdr, arg->stateid);
+ encode_nfs4_seqid(xdr, arg->seqid);
encode_share_access(xdr, arg->fmode);
- hdr->nops++;
- hdr->replen += decode_open_downgrade_maxsz;
}
static void
encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hdr *hdr)
{
- int len = fh->size;
- __be32 *p;
-
- p = reserve_space(xdr, 8 + len);
- *p++ = cpu_to_be32(OP_PUTFH);
- xdr_encode_opaque(p, fh->data, len);
- hdr->nops++;
- hdr->replen += decode_putfh_maxsz;
+ encode_op_hdr(xdr, OP_PUTFH, decode_putfh_maxsz, hdr);
+ encode_string(xdr, fh->size, fh->data);
}
static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_PUTROOTFH);
- hdr->nops++;
- hdr->replen += decode_putrootfh_maxsz;
+ encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr);
}
-static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, int zero_seqid)
+static void encode_open_stateid(struct xdr_stream *xdr,
+ const struct nfs_open_context *ctx,
+ const struct nfs_lock_context *l_ctx,
+ fmode_t fmode,
+ int zero_seqid)
{
nfs4_stateid stateid;
- __be32 *p;
- p = reserve_space(xdr, NFS4_STATEID_SIZE);
if (ctx->state != NULL) {
- nfs4_copy_stateid(&stateid, ctx->state, l_ctx->lockowner, l_ctx->pid);
+ nfs4_select_rw_stateid(&stateid, ctx->state,
+ fmode, l_ctx->lockowner, l_ctx->pid);
if (zero_seqid)
- stateid.stateid.seqid = 0;
- xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE);
+ stateid.seqid = 0;
+ encode_nfs4_stateid(xdr, &stateid);
} else
- xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE);
+ encode_nfs4_stateid(xdr, &zero_stateid);
}
static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_READ);
-
- encode_stateid(xdr, args->context, args->lock_context,
- hdr->minorversion);
+ encode_op_hdr(xdr, OP_READ, decode_read_maxsz, hdr);
+ encode_open_stateid(xdr, args->context, args->lock_context,
+ FMODE_READ, hdr->minorversion);
p = reserve_space(xdr, 12);
p = xdr_encode_hyper(p, args->offset);
*p = cpu_to_be32(args->count);
- hdr->nops++;
- hdr->replen += decode_read_maxsz;
}
static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr)
@@ -1551,7 +1529,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
FATTR4_WORD1_MOUNTED_ON_FILEID,
};
uint32_t dircount = readdir->count >> 1;
- __be32 *p;
+ __be32 *p, verf[2];
if (readdir->plus) {
attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
@@ -1566,80 +1544,54 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID))
attrs[0] |= FATTR4_WORD0_FILEID;
- p = reserve_space(xdr, 12+NFS4_VERIFIER_SIZE+20);
- *p++ = cpu_to_be32(OP_READDIR);
- p = xdr_encode_hyper(p, readdir->cookie);
- p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE);
+ encode_op_hdr(xdr, OP_READDIR, decode_readdir_maxsz, hdr);
+ encode_uint64(xdr, readdir->cookie);
+ encode_nfs4_verifier(xdr, &readdir->verifier);
+ p = reserve_space(xdr, 20);
*p++ = cpu_to_be32(dircount);
*p++ = cpu_to_be32(readdir->count);
*p++ = cpu_to_be32(2);
*p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]);
*p = cpu_to_be32(attrs[1] & readdir->bitmask[1]);
- hdr->nops++;
- hdr->replen += decode_readdir_maxsz;
+ memcpy(verf, readdir->verifier.data, sizeof(verf));
dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n",
__func__,
(unsigned long long)readdir->cookie,
- ((u32 *)readdir->verifier.data)[0],
- ((u32 *)readdir->verifier.data)[1],
+ verf[0], verf[1],
attrs[0] & readdir->bitmask[0],
attrs[1] & readdir->bitmask[1]);
}
static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink *readlink, struct rpc_rqst *req, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_READLINK);
- hdr->nops++;
- hdr->replen += decode_readlink_maxsz;
+ encode_op_hdr(xdr, OP_READLINK, decode_readlink_maxsz, hdr);
}
static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 8 + name->len);
- *p++ = cpu_to_be32(OP_REMOVE);
- xdr_encode_opaque(p, name->name, name->len);
- hdr->nops++;
- hdr->replen += decode_remove_maxsz;
+ encode_op_hdr(xdr, OP_REMOVE, decode_remove_maxsz, hdr);
+ encode_string(xdr, name->len, name->name);
}
static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, const struct qstr *newname, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_RENAME);
+ encode_op_hdr(xdr, OP_RENAME, decode_rename_maxsz, hdr);
encode_string(xdr, oldname->len, oldname->name);
encode_string(xdr, newname->len, newname->name);
- hdr->nops++;
- hdr->replen += decode_rename_maxsz;
}
-static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client_stateid, struct compound_hdr *hdr)
+static void encode_renew(struct xdr_stream *xdr, clientid4 clid,
+ struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 12);
- *p++ = cpu_to_be32(OP_RENEW);
- xdr_encode_hyper(p, client_stateid->cl_clientid);
- hdr->nops++;
- hdr->replen += decode_renew_maxsz;
+ encode_op_hdr(xdr, OP_RENEW, decode_renew_maxsz, hdr);
+ encode_uint64(xdr, clid);
}
static void
encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_RESTOREFH);
- hdr->nops++;
- hdr->replen += decode_restorefh_maxsz;
+ encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr);
}
static void
@@ -1647,9 +1599,8 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
{
__be32 *p;
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_SETATTR);
- xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE);
+ encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr);
+ encode_nfs4_stateid(xdr, &zero_stateid);
p = reserve_space(xdr, 2*4);
*p++ = cpu_to_be32(1);
*p = cpu_to_be32(FATTR4_WORD0_ACL);
@@ -1657,30 +1608,18 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
p = reserve_space(xdr, 4);
*p = cpu_to_be32(arg->acl_len);
xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len);
- hdr->nops++;
- hdr->replen += decode_setacl_maxsz;
}
static void
encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_SAVEFH);
- hdr->nops++;
- hdr->replen += decode_savefh_maxsz;
+ encode_op_hdr(xdr, OP_SAVEFH, decode_savefh_maxsz, hdr);
}
static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs *arg, const struct nfs_server *server, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_SETATTR);
- xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE);
- hdr->nops++;
- hdr->replen += decode_setattr_maxsz;
+ encode_op_hdr(xdr, OP_SETATTR, decode_setattr_maxsz, hdr);
+ encode_nfs4_stateid(xdr, &arg->stateid);
encode_attrs(xdr, arg->iap, server);
}
@@ -1688,9 +1627,8 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie
{
__be32 *p;
- p = reserve_space(xdr, 4 + NFS4_VERIFIER_SIZE);
- *p++ = cpu_to_be32(OP_SETCLIENTID);
- xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE);
+ encode_op_hdr(xdr, OP_SETCLIENTID, decode_setclientid_maxsz, hdr);
+ encode_nfs4_verifier(xdr, setclientid->sc_verifier);
encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name);
p = reserve_space(xdr, 4);
@@ -1699,31 +1637,23 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie
encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr);
p = reserve_space(xdr, 4);
*p = cpu_to_be32(setclientid->sc_cb_ident);
- hdr->nops++;
- hdr->replen += decode_setclientid_maxsz;
}
static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4_setclientid_res *arg, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 12 + NFS4_VERIFIER_SIZE);
- *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM);
- p = xdr_encode_hyper(p, arg->clientid);
- xdr_encode_opaque_fixed(p, arg->confirm.data, NFS4_VERIFIER_SIZE);
- hdr->nops++;
- hdr->replen += decode_setclientid_confirm_maxsz;
+ encode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM,
+ decode_setclientid_confirm_maxsz, hdr);
+ encode_uint64(xdr, arg->clientid);
+ encode_nfs4_verifier(xdr, &arg->confirm);
}
static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
{
__be32 *p;
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(OP_WRITE);
-
- encode_stateid(xdr, args->context, args->lock_context,
- hdr->minorversion);
+ encode_op_hdr(xdr, OP_WRITE, decode_write_maxsz, hdr);
+ encode_open_stateid(xdr, args->context, args->lock_context,
+ FMODE_WRITE, hdr->minorversion);
p = reserve_space(xdr, 16);
p = xdr_encode_hyper(p, args->offset);
@@ -1731,32 +1661,18 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg
*p = cpu_to_be32(args->count);
xdr_write_pages(xdr, args->pages, args->pgbase, args->count);
- hdr->nops++;
- hdr->replen += decode_write_maxsz;
}
static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *stateid, struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
-
- *p++ = cpu_to_be32(OP_DELEGRETURN);
- xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE);
- hdr->nops++;
- hdr->replen += decode_delegreturn_maxsz;
+ encode_op_hdr(xdr, OP_DELEGRETURN, decode_delegreturn_maxsz, hdr);
+ encode_nfs4_stateid(xdr, stateid);
}
static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
{
- int len = name->len;
- __be32 *p;
-
- p = reserve_space(xdr, 8 + len);
- *p++ = cpu_to_be32(OP_SECINFO);
- xdr_encode_opaque(p, name->name, len);
- hdr->nops++;
- hdr->replen += decode_secinfo_maxsz;
+ encode_op_hdr(xdr, OP_SECINFO, decode_secinfo_maxsz, hdr);
+ encode_string(xdr, name->len, name->name);
}
#if defined(CONFIG_NFS_V4_1)
@@ -1766,19 +1682,39 @@ static void encode_exchange_id(struct xdr_stream *xdr,
struct compound_hdr *hdr)
{
__be32 *p;
+ char impl_name[NFS4_OPAQUE_LIMIT];
+ int len = 0;
- p = reserve_space(xdr, 4 + sizeof(args->verifier->data));
- *p++ = cpu_to_be32(OP_EXCHANGE_ID);
- xdr_encode_opaque_fixed(p, args->verifier->data, sizeof(args->verifier->data));
+ encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr);
+ encode_nfs4_verifier(xdr, args->verifier);
encode_string(xdr, args->id_len, args->id);
p = reserve_space(xdr, 12);
*p++ = cpu_to_be32(args->flags);
*p++ = cpu_to_be32(0); /* zero length state_protect4_a */
- *p = cpu_to_be32(0); /* zero length implementation id array */
- hdr->nops++;
- hdr->replen += decode_exchange_id_maxsz;
+
+ if (send_implementation_id &&
+ sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) > 1 &&
+ sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN)
+ <= NFS4_OPAQUE_LIMIT + 1)
+ len = snprintf(impl_name, sizeof(impl_name), "%s %s %s %s",
+ utsname()->sysname, utsname()->release,
+ utsname()->version, utsname()->machine);
+
+ if (len > 0) {
+ *p = cpu_to_be32(1); /* implementation id array length=1 */
+
+ encode_string(xdr,
+ sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) - 1,
+ CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN);
+ encode_string(xdr, len, impl_name);
+ /* just send zeros for nii_date - the date is in nii_name */
+ p = reserve_space(xdr, 12);
+ p = xdr_encode_hyper(p, 0);
+ *p = cpu_to_be32(0);
+ } else
+ *p = cpu_to_be32(0); /* implementation id array length=0 */
}
static void encode_create_session(struct xdr_stream *xdr,
@@ -1801,8 +1737,8 @@ static void encode_create_session(struct xdr_stream *xdr,
len = scnprintf(machine_name, sizeof(machine_name), "%s",
clp->cl_ipaddr);
- p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12);
- *p++ = cpu_to_be32(OP_CREATE_SESSION);
+ encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr);
+ p = reserve_space(xdr, 16 + 2*28 + 20 + len + 12);
p = xdr_encode_hyper(p, clp->cl_clientid);
*p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */
*p++ = cpu_to_be32(args->flags); /*flags */
@@ -1835,33 +1771,22 @@ static void encode_create_session(struct xdr_stream *xdr,
*p++ = cpu_to_be32(0); /* UID */
*p++ = cpu_to_be32(0); /* GID */
*p = cpu_to_be32(0); /* No more gids */
- hdr->nops++;
- hdr->replen += decode_create_session_maxsz;
}
static void encode_destroy_session(struct xdr_stream *xdr,
struct nfs4_session *session,
struct compound_hdr *hdr)
{
- __be32 *p;
- p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN);
- *p++ = cpu_to_be32(OP_DESTROY_SESSION);
- xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
- hdr->nops++;
- hdr->replen += decode_destroy_session_maxsz;
+ encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr);
+ encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
}
static void encode_reclaim_complete(struct xdr_stream *xdr,
struct nfs41_reclaim_complete_args *args,
struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 8);
- *p++ = cpu_to_be32(OP_RECLAIM_COMPLETE);
- *p++ = cpu_to_be32(args->one_fs);
- hdr->nops++;
- hdr->replen += decode_reclaim_complete_maxsz;
+ encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr);
+ encode_uint32(xdr, args->one_fs);
}
#endif /* CONFIG_NFS_V4_1 */
@@ -1883,8 +1808,7 @@ static void encode_sequence(struct xdr_stream *xdr,
WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE);
slot = tp->slots + args->sa_slotid;
- p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN + 16);
- *p++ = cpu_to_be32(OP_SEQUENCE);
+ encode_op_hdr(xdr, OP_SEQUENCE, decode_sequence_maxsz, hdr);
/*
* Sessionid + seqid + slotid + max slotid + cache_this
@@ -1898,13 +1822,12 @@ static void encode_sequence(struct xdr_stream *xdr,
((u32 *)session->sess_id.data)[3],
slot->seq_nr, args->sa_slotid,
tp->highest_used_slotid, args->sa_cache_this);
+ p = reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 16);
p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
*p++ = cpu_to_be32(slot->seq_nr);
*p++ = cpu_to_be32(args->sa_slotid);
*p++ = cpu_to_be32(tp->highest_used_slotid);
*p = cpu_to_be32(args->sa_cache_this);
- hdr->nops++;
- hdr->replen += decode_sequence_maxsz;
#endif /* CONFIG_NFS_V4_1 */
}
@@ -1919,14 +1842,12 @@ encode_getdevicelist(struct xdr_stream *xdr,
.data = "dummmmmy",
};
- p = reserve_space(xdr, 20);
- *p++ = cpu_to_be32(OP_GETDEVICELIST);
+ encode_op_hdr(xdr, OP_GETDEVICELIST, decode_getdevicelist_maxsz, hdr);
+ p = reserve_space(xdr, 16);
*p++ = cpu_to_be32(args->layoutclass);
*p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
xdr_encode_hyper(p, 0ULL); /* cookie */
encode_nfs4_verifier(xdr, &dummy);
- hdr->nops++;
- hdr->replen += decode_getdevicelist_maxsz;
}
static void
@@ -1936,15 +1857,13 @@ encode_getdeviceinfo(struct xdr_stream *xdr,
{
__be32 *p;
- p = reserve_space(xdr, 16 + NFS4_DEVICEID4_SIZE);
- *p++ = cpu_to_be32(OP_GETDEVICEINFO);
+ encode_op_hdr(xdr, OP_GETDEVICEINFO, decode_getdeviceinfo_maxsz, hdr);
+ p = reserve_space(xdr, 12 + NFS4_DEVICEID4_SIZE);
p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data,
NFS4_DEVICEID4_SIZE);
*p++ = cpu_to_be32(args->pdev->layout_type);
*p++ = cpu_to_be32(args->pdev->pglen); /* gdia_maxcount */
*p++ = cpu_to_be32(0); /* bitmap length 0 */
- hdr->nops++;
- hdr->replen += decode_getdeviceinfo_maxsz;
}
static void
@@ -1954,16 +1873,16 @@ encode_layoutget(struct xdr_stream *xdr,
{
__be32 *p;
- p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_LAYOUTGET);
+ encode_op_hdr(xdr, OP_LAYOUTGET, decode_layoutget_maxsz, hdr);
+ p = reserve_space(xdr, 36);
*p++ = cpu_to_be32(0); /* Signal layout available */
*p++ = cpu_to_be32(args->type);
*p++ = cpu_to_be32(args->range.iomode);
p = xdr_encode_hyper(p, args->range.offset);
p = xdr_encode_hyper(p, args->range.length);
p = xdr_encode_hyper(p, args->minlength);
- p = xdr_encode_opaque_fixed(p, &args->stateid.data, NFS4_STATEID_SIZE);
- *p = cpu_to_be32(args->maxcount);
+ encode_nfs4_stateid(xdr, &args->stateid);
+ encode_uint32(xdr, args->maxcount);
dprintk("%s: 1st type:0x%x iomode:%d off:%lu len:%lu mc:%d\n",
__func__,
@@ -1972,8 +1891,6 @@ encode_layoutget(struct xdr_stream *xdr,
(unsigned long)args->range.offset,
(unsigned long)args->range.length,
args->maxcount);
- hdr->nops++;
- hdr->replen += decode_layoutget_maxsz;
}
static int
@@ -1987,13 +1904,14 @@ encode_layoutcommit(struct xdr_stream *xdr,
dprintk("%s: lbw: %llu type: %d\n", __func__, args->lastbytewritten,
NFS_SERVER(args->inode)->pnfs_curr_ld->id);
- p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_LAYOUTCOMMIT);
+ encode_op_hdr(xdr, OP_LAYOUTCOMMIT, decode_layoutcommit_maxsz, hdr);
+ p = reserve_space(xdr, 20);
/* Only whole file layouts */
p = xdr_encode_hyper(p, 0); /* offset */
p = xdr_encode_hyper(p, args->lastbytewritten + 1); /* length */
- *p++ = cpu_to_be32(0); /* reclaim */
- p = xdr_encode_opaque_fixed(p, args->stateid.data, NFS4_STATEID_SIZE);
+ *p = cpu_to_be32(0); /* reclaim */
+ encode_nfs4_stateid(xdr, &args->stateid);
+ p = reserve_space(xdr, 20);
*p++ = cpu_to_be32(1); /* newoffset = TRUE */
p = xdr_encode_hyper(p, args->lastbytewritten);
*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
@@ -2002,13 +1920,9 @@ encode_layoutcommit(struct xdr_stream *xdr,
if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
NFS_I(inode)->layout, xdr, args);
- else {
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(0); /* no layout-type payload */
- }
+ else
+ encode_uint32(xdr, 0); /* no layout-type payload */
- hdr->nops++;
- hdr->replen += decode_layoutcommit_maxsz;
return 0;
}
@@ -2019,27 +1933,23 @@ encode_layoutreturn(struct xdr_stream *xdr,
{
__be32 *p;
- p = reserve_space(xdr, 20);
- *p++ = cpu_to_be32(OP_LAYOUTRETURN);
+ encode_op_hdr(xdr, OP_LAYOUTRETURN, decode_layoutreturn_maxsz, hdr);
+ p = reserve_space(xdr, 16);
*p++ = cpu_to_be32(0); /* reclaim. always 0 for now */
*p++ = cpu_to_be32(args->layout_type);
*p++ = cpu_to_be32(IOMODE_ANY);
*p = cpu_to_be32(RETURN_FILE);
- p = reserve_space(xdr, 16 + NFS4_STATEID_SIZE);
+ p = reserve_space(xdr, 16);
p = xdr_encode_hyper(p, 0);
p = xdr_encode_hyper(p, NFS4_MAX_UINT64);
spin_lock(&args->inode->i_lock);
- xdr_encode_opaque_fixed(p, &args->stateid.data, NFS4_STATEID_SIZE);
+ encode_nfs4_stateid(xdr, &args->stateid);
spin_unlock(&args->inode->i_lock);
if (NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn) {
NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn(
NFS_I(args->inode)->layout, xdr, args);
- } else {
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(0);
- }
- hdr->nops++;
- hdr->replen += decode_layoutreturn_maxsz;
+ } else
+ encode_uint32(xdr, 0);
}
static int
@@ -2047,12 +1957,8 @@ encode_secinfo_no_name(struct xdr_stream *xdr,
const struct nfs41_secinfo_no_name_args *args,
struct compound_hdr *hdr)
{
- __be32 *p;
- p = reserve_space(xdr, 8);
- *p++ = cpu_to_be32(OP_SECINFO_NO_NAME);
- *p++ = cpu_to_be32(args->style);
- hdr->nops++;
- hdr->replen += decode_secinfo_no_name_maxsz;
+ encode_op_hdr(xdr, OP_SECINFO_NO_NAME, decode_secinfo_no_name_maxsz, hdr);
+ encode_uint32(xdr, args->style);
return 0;
}
@@ -2060,26 +1966,17 @@ static void encode_test_stateid(struct xdr_stream *xdr,
struct nfs41_test_stateid_args *args,
struct compound_hdr *hdr)
{
- __be32 *p;
-
- p = reserve_space(xdr, 8 + NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_TEST_STATEID);
- *p++ = cpu_to_be32(1);
- xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
- hdr->nops++;
- hdr->replen += decode_test_stateid_maxsz;
+ encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr);
+ encode_uint32(xdr, 1);
+ encode_nfs4_stateid(xdr, args->stateid);
}
static void encode_free_stateid(struct xdr_stream *xdr,
struct nfs41_free_stateid_args *args,
struct compound_hdr *hdr)
{
- __be32 *p;
- p = reserve_space(xdr, 4 + NFS4_STATEID_SIZE);
- *p++ = cpu_to_be32(OP_FREE_STATEID);
- xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
- hdr->nops++;
- hdr->replen += decode_free_stateid_maxsz;
+ encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr);
+ encode_nfs4_stateid(xdr, args->stateid);
}
#endif /* CONFIG_NFS_V4_1 */
@@ -2522,7 +2419,6 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
args->acl_pages, args->acl_pgbase, args->acl_len);
- xdr_set_scratch_buffer(xdr, page_address(args->acl_scratch), PAGE_SIZE);
encode_nops(&hdr);
}
@@ -2634,6 +2530,7 @@ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req,
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->fhandle, &hdr);
encode_getattr_one(xdr, FATTR4_WORD0_SUPPORTED_ATTRS|
+ FATTR4_WORD0_FH_EXPIRE_TYPE|
FATTR4_WORD0_LINK_SUPPORT|
FATTR4_WORD0_SYMLINK_SUPPORT|
FATTR4_WORD0_ACLSUPPORT, &hdr);
@@ -2651,7 +2548,7 @@ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr,
};
encode_compound_hdr(xdr, req, &hdr);
- encode_renew(xdr, clp, &hdr);
+ encode_renew(xdr, clp->cl_clientid, &hdr);
encode_nops(&hdr);
}
@@ -3181,6 +3078,28 @@ out_overflow:
return -EIO;
}
+static int decode_attr_fh_expire_type(struct xdr_stream *xdr,
+ uint32_t *bitmap, uint32_t *type)
+{
+ __be32 *p;
+
+ *type = 0;
+ if (unlikely(bitmap[0] & (FATTR4_WORD0_FH_EXPIRE_TYPE - 1U)))
+ return -EIO;
+ if (likely(bitmap[0] & FATTR4_WORD0_FH_EXPIRE_TYPE)) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ goto out_overflow;
+ *type = be32_to_cpup(p);
+ bitmap[0] &= ~FATTR4_WORD0_FH_EXPIRE_TYPE;
+ }
+ dprintk("%s: expire type=0x%x\n", __func__, *type);
+ return 0;
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change)
{
__be32 *p;
@@ -3514,16 +3433,17 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
n = be32_to_cpup(p);
if (n == 0)
goto root_path;
- dprintk("path ");
+ dprintk("pathname4: ");
path->ncomponents = 0;
while (path->ncomponents < n) {
struct nfs4_string *component = &path->components[path->ncomponents];
status = decode_opaque_inline(xdr, &component->len, &component->data);
if (unlikely(status != 0))
goto out_eio;
- if (path->ncomponents != n)
- dprintk("/");
- dprintk("%s", component->data);
+ ifdebug (XDR)
+ pr_cont("%s%.*s ",
+ (path->ncomponents != n ? "/ " : ""),
+ component->len, component->data);
if (path->ncomponents < NFS4_PATHNAME_MAXCOMPONENTS)
path->ncomponents++;
else {
@@ -3532,14 +3452,13 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
}
}
out:
- dprintk("\n");
return status;
root_path:
/* a root pathname is sent as a zero component4 */
path->ncomponents = 1;
path->components[0].len=0;
path->components[0].data=NULL;
- dprintk("path /\n");
+ dprintk("pathname4: /\n");
goto out;
out_eio:
dprintk(" status %d", status);
@@ -3561,7 +3480,11 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
status = 0;
if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS)))
goto out;
- dprintk("%s: fsroot ", __func__);
+ status = -EIO;
+ /* Ignore borken servers that return unrequested attrs */
+ if (unlikely(res == NULL))
+ goto out;
+ dprintk("%s: fsroot:\n", __func__);
status = decode_pathname(xdr, &res->fs_path);
if (unlikely(status != 0))
goto out;
@@ -3582,7 +3505,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
m = be32_to_cpup(p);
loc->nservers = 0;
- dprintk("%s: servers ", __func__);
+ dprintk("%s: servers:\n", __func__);
while (loc->nservers < m) {
struct nfs4_string *server = &loc->servers[loc->nservers];
status = decode_opaque_inline(xdr, &server->len, &server->data);
@@ -3614,7 +3537,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
res->nlocations++;
}
if (res->nlocations != 0)
- status = NFS_ATTR_FATTR_V4_REFERRAL;
+ status = NFS_ATTR_FATTR_V4_LOCATIONS;
out:
dprintk("%s: fs_locations done, error = %d\n", __func__, status);
return status;
@@ -4158,7 +4081,7 @@ static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
{
- return decode_opaque_fixed(xdr, stateid->data, NFS4_STATEID_SIZE);
+ return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
}
static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
@@ -4175,7 +4098,7 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
static int decode_verifier(struct xdr_stream *xdr, void *verifier)
{
- return decode_opaque_fixed(xdr, verifier, 8);
+ return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
}
static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res)
@@ -4225,6 +4148,9 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re
goto xdr_error;
if ((status = decode_attr_supported(xdr, bitmap, res->attr_bitmask)) != 0)
goto xdr_error;
+ if ((status = decode_attr_fh_expire_type(xdr, bitmap,
+ &res->fh_expire_type)) != 0)
+ goto xdr_error;
if ((status = decode_attr_link_support(xdr, bitmap, &res->has_links)) != 0)
goto xdr_error;
if ((status = decode_attr_symlink_support(xdr, bitmap, &res->has_symlinks)) != 0)
@@ -4295,6 +4221,7 @@ xdr_error:
static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
struct nfs_fattr *fattr, struct nfs_fh *fh,
+ struct nfs4_fs_locations *fs_loc,
const struct nfs_server *server)
{
int status;
@@ -4342,9 +4269,7 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
goto xdr_error;
fattr->valid |= status;
- status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr,
- struct nfs4_fs_locations,
- fattr));
+ status = decode_attr_fs_locations(xdr, bitmap, fs_loc);
if (status < 0)
goto xdr_error;
fattr->valid |= status;
@@ -4408,7 +4333,8 @@ xdr_error:
}
static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr,
- struct nfs_fh *fh, const struct nfs_server *server)
+ struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc,
+ const struct nfs_server *server)
{
__be32 *savep;
uint32_t attrlen,
@@ -4427,7 +4353,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
if (status < 0)
goto xdr_error;
- status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server);
+ status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc, server);
if (status < 0)
goto xdr_error;
@@ -4440,7 +4366,7 @@ xdr_error:
static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
const struct nfs_server *server)
{
- return decode_getfattr_generic(xdr, fattr, NULL, server);
+ return decode_getfattr_generic(xdr, fattr, NULL, NULL, server);
}
/*
@@ -4464,8 +4390,8 @@ static int decode_first_pnfs_layout_type(struct xdr_stream *xdr,
return 0;
}
if (num > 1)
- printk(KERN_INFO "%s: Warning: Multiple pNFS layout drivers "
- "per filesystem not supported\n", __func__);
+ printk(KERN_INFO "NFS: %s: Warning: Multiple pNFS layout "
+ "drivers per filesystem not supported\n", __func__);
/* Decode and set first layout type, move xdr->p past unused types */
p = xdr_inline_decode(xdr, num * 4);
@@ -4864,17 +4790,16 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
size_t hdrlen;
u32 recvd, pglen = rcvbuf->page_len;
int status;
+ __be32 verf[2];
status = decode_op_hdr(xdr, OP_READDIR);
if (!status)
status = decode_verifier(xdr, readdir->verifier.data);
if (unlikely(status))
return status;
+ memcpy(verf, readdir->verifier.data, sizeof(verf));
dprintk("%s: verifier = %08x:%08x\n",
- __func__,
- ((u32 *)readdir->verifier.data)[0],
- ((u32 *)readdir->verifier.data)[1]);
-
+ __func__, verf[0], verf[1]);
hdrlen = (char *) xdr->p - (char *) iov->iov_base;
recvd = rcvbuf->len - hdrlen;
@@ -5121,7 +5046,7 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
goto out_overflow;
res->count = be32_to_cpup(p++);
res->verf->committed = be32_to_cpup(p++);
- memcpy(res->verf->verifier, p, 8);
+ memcpy(res->verf->verifier, p, NFS4_VERIFIER_SIZE);
return 0;
out_overflow:
print_overflow_msg(__func__, xdr);
@@ -5215,6 +5140,7 @@ static int decode_exchange_id(struct xdr_stream *xdr,
char *dummy_str;
int status;
struct nfs_client *clp = res->client;
+ uint32_t impl_id_count;
status = decode_op_hdr(xdr, OP_EXCHANGE_ID);
if (status)
@@ -5256,11 +5182,38 @@ static int decode_exchange_id(struct xdr_stream *xdr,
memcpy(res->server_scope->server_scope, dummy_str, dummy);
res->server_scope->server_scope_sz = dummy;
- /* Throw away Implementation id array */
- status = decode_opaque_inline(xdr, &dummy, &dummy_str);
- if (unlikely(status))
- return status;
+ /* Implementation Id */
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ goto out_overflow;
+ impl_id_count = be32_to_cpup(p++);
+
+ if (impl_id_count) {
+ /* nii_domain */
+ status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+ if (unlikely(status))
+ return status;
+ if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+ return -EIO;
+ memcpy(res->impl_id->domain, dummy_str, dummy);
+
+ /* nii_name */
+ status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+ if (unlikely(status))
+ return status;
+ if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+ return -EIO;
+ memcpy(res->impl_id->name, dummy_str, dummy);
+ /* nii_date */
+ p = xdr_inline_decode(xdr, 12);
+ if (unlikely(!p))
+ goto out_overflow;
+ p = xdr_decode_hyper(p, &res->impl_id->date.seconds);
+ res->impl_id->date.nseconds = be32_to_cpup(p);
+
+ /* if there's more than one entry, ignore the rest */
+ }
return 0;
out_overflow:
print_overflow_msg(__func__, xdr);
@@ -5286,8 +5239,8 @@ static int decode_chan_attrs(struct xdr_stream *xdr,
attrs->max_reqs = be32_to_cpup(p++);
nr_attrs = be32_to_cpup(p);
if (unlikely(nr_attrs > 1)) {
- printk(KERN_WARNING "%s: Invalid rdma channel attrs count %u\n",
- __func__, nr_attrs);
+ printk(KERN_WARNING "NFS: %s: Invalid rdma channel attrs "
+ "count %u\n", __func__, nr_attrs);
return -EINVAL;
}
if (nr_attrs == 1) {
@@ -5437,14 +5390,14 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
p += 2;
/* Read verifier */
- p = xdr_decode_opaque_fixed(p, verftemp.verifier, 8);
+ p = xdr_decode_opaque_fixed(p, verftemp.verifier, NFS4_VERIFIER_SIZE);
res->num_devs = be32_to_cpup(p);
dprintk("%s: num_dev %d\n", __func__, res->num_devs);
if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
- printk(KERN_ERR "%s too many result dev_num %u\n",
+ printk(KERN_ERR "NFS: %s too many result dev_num %u\n",
__func__, res->num_devs);
return -EIO;
}
@@ -5538,11 +5491,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
status = decode_op_hdr(xdr, OP_LAYOUTGET);
if (status)
return status;
- p = xdr_inline_decode(xdr, 8 + NFS4_STATEID_SIZE);
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ goto out_overflow;
+ res->return_on_close = be32_to_cpup(p);
+ decode_stateid(xdr, &res->stateid);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
- res->return_on_close = be32_to_cpup(p++);
- p = xdr_decode_opaque_fixed(p, res->stateid.data, NFS4_STATEID_SIZE);
layout_count = be32_to_cpup(p);
if (!layout_count) {
dprintk("%s: server responded with empty layout array\n",
@@ -5667,7 +5623,8 @@ static int decode_test_stateid(struct xdr_stream *xdr,
if (unlikely(!p))
goto out_overflow;
res->status = be32_to_cpup(p++);
- return res->status;
+
+ return status;
out_overflow:
print_overflow_msg(__func__, xdr);
out:
@@ -6032,6 +5989,10 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
struct compound_hdr hdr;
int status;
+ if (res->acl_scratch != NULL) {
+ void *p = page_address(res->acl_scratch);
+ xdr_set_scratch_buffer(xdr, p, PAGE_SIZE);
+ }
status = decode_compound_hdr(xdr, &hdr);
if (status)
goto out;
@@ -6580,8 +6541,9 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
if (status)
goto out;
xdr_enter_page(xdr, PAGE_SIZE);
- status = decode_getfattr(xdr, &res->fs_locations->fattr,
- res->fs_locations->server);
+ status = decode_getfattr_generic(xdr, &res->fs_locations->fattr,
+ NULL, res->fs_locations,
+ res->fs_locations->server);
out:
return status;
}
@@ -6961,7 +6923,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
goto out_overflow;
if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
- entry->server) < 0)
+ NULL, entry->server) < 0)
goto out_overflow;
if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
entry->ino = entry->fattr->mounted_on_fileid;
@@ -7109,7 +7071,7 @@ struct rpc_procinfo nfs4_procedures[] = {
#endif /* CONFIG_NFS_V4_1 */
};
-struct rpc_version nfs_version4 = {
+const struct rpc_version nfs_version4 = {
.number = 4,
.nrprocs = ARRAY_SIZE(nfs4_procedures),
.procs = nfs4_procedures
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index c4744e1..cd3c910 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -104,7 +104,7 @@ static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = "";
/* server:export path string passed to super.c */
static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = "";
-#ifdef RPC_DEBUG
+#ifdef NFS_DEBUG
/*
* When the "nfsrootdebug" kernel command line option is specified,
* enable debugging messages for NFSROOT.
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 55d0128..4bff4a3 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -137,6 +137,7 @@ static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
struct objio_dev_ent *ode;
struct osd_dev *od;
struct osd_dev_info odi;
+ bool retry_flag = true;
int err;
ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
@@ -171,10 +172,18 @@ static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
goto out;
}
+retry_lookup:
od = osduld_info_lookup(&odi);
if (unlikely(IS_ERR(od))) {
err = PTR_ERR(od);
dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
+ if (err == -ENODEV && retry_flag) {
+ err = objlayout_autologin(deviceaddr);
+ if (likely(!err)) {
+ retry_flag = false;
+ goto retry_lookup;
+ }
+ }
goto out;
}
@@ -205,25 +214,36 @@ static void copy_single_comp(struct ore_components *oc, unsigned c,
int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
struct objio_segment **pseg)
{
- struct __alloc_objio_segment {
- struct objio_segment olseg;
- struct ore_dev *ods[numdevs];
- struct ore_comp comps[numdevs];
- } *aolseg;
-
- aolseg = kzalloc(sizeof(*aolseg), gfp_flags);
- if (unlikely(!aolseg)) {
+/* This is the in memory structure of the objio_segment
+ *
+ * struct __alloc_objio_segment {
+ * struct objio_segment olseg;
+ * struct ore_dev *ods[numdevs];
+ * struct ore_comp comps[numdevs];
+ * } *aolseg;
+ * NOTE: The code as above compiles and runs perfectly. It is elegant,
+ * type safe and compact. At some Past time Linus has decided he does not
+ * like variable length arrays, For the sake of this principal we uglify
+ * the code as below.
+ */
+ struct objio_segment *lseg;
+ size_t lseg_size = sizeof(*lseg) +
+ numdevs * sizeof(lseg->oc.ods[0]) +
+ numdevs * sizeof(*lseg->oc.comps);
+
+ lseg = kzalloc(lseg_size, gfp_flags);
+ if (unlikely(!lseg)) {
dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__,
- numdevs, sizeof(*aolseg));
+ numdevs, lseg_size);
return -ENOMEM;
}
- aolseg->olseg.oc.numdevs = numdevs;
- aolseg->olseg.oc.single_comp = EC_MULTPLE_COMPS;
- aolseg->olseg.oc.comps = aolseg->comps;
- aolseg->olseg.oc.ods = aolseg->ods;
+ lseg->oc.numdevs = numdevs;
+ lseg->oc.single_comp = EC_MULTPLE_COMPS;
+ lseg->oc.ods = (void *)(lseg + 1);
+ lseg->oc.comps = (void *)(lseg->oc.ods + numdevs);
- *pseg = &aolseg->olseg;
+ *pseg = lseg;
return 0;
}
@@ -582,10 +602,10 @@ objlayout_init(void)
if (ret)
printk(KERN_INFO
- "%s: Registering OSD pNFS Layout Driver failed: error=%d\n",
+ "NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n",
__func__, ret);
else
- printk(KERN_INFO "%s: Registered OSD pNFS Layout Driver\n",
+ printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n",
__func__);
return ret;
}
@@ -594,7 +614,7 @@ static void __exit
objlayout_exit(void)
{
pnfs_unregister_layoutdriver(&objlayout_type);
- printk(KERN_INFO "%s: Unregistered OSD pNFS Layout Driver\n",
+ printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n",
__func__);
}
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index b3c2903..8d45f1c 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -37,6 +37,9 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <linux/kmod.h>
+#include <linux/moduleparam.h>
+#include <linux/ratelimit.h>
#include <scsi/osd_initiator.h>
#include "objlayout.h"
@@ -156,7 +159,7 @@ last_byte_offset(u64 start, u64 len)
return end > start ? end - 1 : NFS4_MAX_UINT64;
}
-void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
+static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
struct page ***p_pages, unsigned *p_pgbase,
u64 offset, unsigned long count)
{
@@ -490,9 +493,9 @@ encode_accumulated_error(struct objlayout *objlay, __be32 *p)
if (!ioerr->oer_errno)
continue;
- printk(KERN_ERR "%s: err[%d]: errno=%d is_write=%d "
- "dev(%llx:%llx) par=0x%llx obj=0x%llx "
- "offset=0x%llx length=0x%llx\n",
+ printk(KERN_ERR "NFS: %s: err[%d]: errno=%d "
+ "is_write=%d dev(%llx:%llx) par=0x%llx "
+ "obj=0x%llx offset=0x%llx length=0x%llx\n",
__func__, i, ioerr->oer_errno,
ioerr->oer_iswrite,
_DEVID_LO(&ioerr->oer_component.oid_device_id),
@@ -651,3 +654,134 @@ void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr)
__free_page(odi->page);
kfree(odi);
}
+
+enum {
+ OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
+ OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
+ OSD_LOGIN_UPCALL_PATHLEN = 256
+};
+
+static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login";
+
+module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog),
+ 0600);
+MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program");
+
+struct __auto_login {
+ char uri[OBJLAYOUT_MAX_URI_LEN];
+ char osdname[OBJLAYOUT_MAX_OSDNAME_LEN];
+ char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN];
+};
+
+static int __objlayout_upcall(struct __auto_login *login)
+{
+ static char *envp[] = { "HOME=/",
+ "TERM=linux",
+ "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+ NULL
+ };
+ char *argv[8];
+ int ret;
+
+ if (unlikely(!osd_login_prog[0])) {
+ dprintk("%s: osd_login_prog is disabled\n", __func__);
+ return -EACCES;
+ }
+
+ dprintk("%s uri: %s\n", __func__, login->uri);
+ dprintk("%s osdname %s\n", __func__, login->osdname);
+ dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex);
+
+ argv[0] = (char *)osd_login_prog;
+ argv[1] = "-u";
+ argv[2] = login->uri;
+ argv[3] = "-o";
+ argv[4] = login->osdname;
+ argv[5] = "-s";
+ argv[6] = login->systemid_hex;
+ argv[7] = NULL;
+
+ ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+ /*
+ * Disable the upcall mechanism if we're getting an ENOENT or
+ * EACCES error. The admin can re-enable it on the fly by using
+ * sysfs to set the objlayoutdriver.osd_login_prog module parameter once
+ * the problem has been fixed.
+ */
+ if (ret == -ENOENT || ret == -EACCES) {
+ printk(KERN_ERR "PNFS-OBJ: %s was not found please set "
+ "objlayoutdriver.osd_login_prog kernel parameter!\n",
+ osd_login_prog);
+ osd_login_prog[0] = '\0';
+ }
+ dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret);
+
+ return ret;
+}
+
+/* Assume dest is all zeros */
+static void __copy_nfsS_and_zero_terminate(struct nfs4_string s,
+ char *dest, int max_len,
+ const char *var_name)
+{
+ if (!s.len)
+ return;
+
+ if (s.len >= max_len) {
+ pr_warn_ratelimited(
+ "objlayout_autologin: %s: s.len(%d) >= max_len(%d)",
+ var_name, s.len, max_len);
+ s.len = max_len - 1; /* space for null terminator */
+ }
+
+ memcpy(dest, s.data, s.len);
+}
+
+/* Assume sysid is all zeros */
+static void _sysid_2_hex(struct nfs4_string s,
+ char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN])
+{
+ int i;
+ char *cur;
+
+ if (!s.len)
+ return;
+
+ if (s.len != OSD_SYSTEMID_LEN) {
+ pr_warn_ratelimited(
+ "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN",
+ s.len);
+ if (s.len > OSD_SYSTEMID_LEN)
+ s.len = OSD_SYSTEMID_LEN;
+ }
+
+ cur = sysid;
+ for (i = 0; i < s.len; i++)
+ cur = hex_byte_pack(cur, s.data[i]);
+}
+
+int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr)
+{
+ int rc;
+ struct __auto_login login;
+
+ if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len)
+ return -ENODEV;
+
+ memset(&login, 0, sizeof(login));
+ __copy_nfsS_and_zero_terminate(
+ deviceaddr->oda_targetaddr.ota_netaddr.r_addr,
+ login.uri, sizeof(login.uri), "URI");
+
+ __copy_nfsS_and_zero_terminate(
+ deviceaddr->oda_osdname,
+ login.osdname, sizeof(login.osdname), "OSDNAME");
+
+ _sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex);
+
+ rc = __objlayout_upcall(&login);
+ if (rc > 0) /* script returns positive values */
+ rc = -ENODEV;
+
+ return rc;
+}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index 8ec3472..880ba08 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -184,4 +184,6 @@ extern void objlayout_encode_layoutreturn(
struct xdr_stream *,
const struct nfs4_layoutreturn_args *);
+extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr);
+
#endif /* _OBJLAYOUT_H */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 5668f7c..d21fcea 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -13,6 +13,7 @@
#include <linux/file.h>
#include <linux/sched.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/nfs.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
#include <linux/nfs_page.h>
@@ -106,36 +107,6 @@ void nfs_unlock_request(struct nfs_page *req)
nfs_release_request(req);
}
-/**
- * nfs_set_page_tag_locked - Tag a request as locked
- * @req:
- */
-int nfs_set_page_tag_locked(struct nfs_page *req)
-{
- if (!nfs_lock_request_dontget(req))
- return 0;
- if (test_bit(PG_MAPPED, &req->wb_flags))
- radix_tree_tag_set(&NFS_I(req->wb_context->dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
- return 1;
-}
-
-/**
- * nfs_clear_page_tag_locked - Clear request tag and wake up sleepers
- */
-void nfs_clear_page_tag_locked(struct nfs_page *req)
-{
- if (test_bit(PG_MAPPED, &req->wb_flags)) {
- struct inode *inode = req->wb_context->dentry->d_inode;
- struct nfs_inode *nfsi = NFS_I(inode);
-
- spin_lock(&inode->i_lock);
- radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
- nfs_unlock_request(req);
- spin_unlock(&inode->i_lock);
- } else
- nfs_unlock_request(req);
-}
-
/*
* nfs_clear_request - Free up all resources allocated to the request
* @req:
@@ -425,67 +396,6 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
}
}
-#define NFS_SCAN_MAXENTRIES 16
-/**
- * nfs_scan_list - Scan a list for matching requests
- * @nfsi: NFS inode
- * @dst: Destination list
- * @idx_start: lower bound of page->index to scan
- * @npages: idx_start + npages sets the upper bound to scan.
- * @tag: tag to scan for
- *
- * Moves elements from one of the inode request lists.
- * If the number of requests is set to 0, the entire address_space
- * starting at index idx_start, is scanned.
- * The requests are *not* checked to ensure that they form a contiguous set.
- * You must be holding the inode's i_lock when calling this function
- */
-int nfs_scan_list(struct nfs_inode *nfsi,
- struct list_head *dst, pgoff_t idx_start,
- unsigned int npages, int tag)
-{
- struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES];
- struct nfs_page *req;
- pgoff_t idx_end;
- int found, i;
- int res;
- struct list_head *list;
-
- res = 0;
- if (npages == 0)
- idx_end = ~0;
- else
- idx_end = idx_start + npages - 1;
-
- for (;;) {
- found = radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree,
- (void **)&pgvec[0], idx_start,
- NFS_SCAN_MAXENTRIES, tag);
- if (found <= 0)
- break;
- for (i = 0; i < found; i++) {
- req = pgvec[i];
- if (req->wb_index > idx_end)
- goto out;
- idx_start = req->wb_index + 1;
- if (nfs_set_page_tag_locked(req)) {
- kref_get(&req->wb_kref);
- radix_tree_tag_clear(&nfsi->nfs_page_tree,
- req->wb_index, tag);
- list = pnfs_choose_commit_list(req, dst);
- nfs_list_add_request(req, list);
- res++;
- if (res == INT_MAX)
- goto out;
- }
- }
- /* for latency reduction */
- cond_resched_lock(&nfsi->vfs_inode.i_lock);
- }
-out:
- return res;
-}
-
int __init nfs_init_nfspagecache(void)
{
nfs_page_cachep = kmem_cache_create("nfs_page",
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 17149a4..b5d4515 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -101,8 +101,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
goto out_no_driver;
if (!(server->nfs_client->cl_exchange_flags &
(EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
- printk(KERN_ERR "%s: id %u cl_exchange_flags 0x%x\n", __func__,
- id, server->nfs_client->cl_exchange_flags);
+ printk(KERN_ERR "NFS: %s: id %u cl_exchange_flags 0x%x\n",
+ __func__, id, server->nfs_client->cl_exchange_flags);
goto out_no_driver;
}
ld_type = find_pnfs_driver(id);
@@ -122,8 +122,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
server->pnfs_curr_ld = ld_type;
if (ld_type->set_layoutdriver
&& ld_type->set_layoutdriver(server, mntfh)) {
- printk(KERN_ERR "%s: Error initializing pNFS layout driver %u.\n",
- __func__, id);
+ printk(KERN_ERR "NFS: %s: Error initializing pNFS layout "
+ "driver %u.\n", __func__, id);
module_put(ld_type->owner);
goto out_no_driver;
}
@@ -143,11 +143,11 @@ pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
struct pnfs_layoutdriver_type *tmp;
if (ld_type->id == 0) {
- printk(KERN_ERR "%s id 0 is reserved\n", __func__);
+ printk(KERN_ERR "NFS: %s id 0 is reserved\n", __func__);
return status;
}
if (!ld_type->alloc_lseg || !ld_type->free_lseg) {
- printk(KERN_ERR "%s Layout driver must provide "
+ printk(KERN_ERR "NFS: %s Layout driver must provide "
"alloc_lseg and free_lseg.\n", __func__);
return status;
}
@@ -160,7 +160,7 @@ pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
ld_type->name);
} else {
- printk(KERN_ERR "%s Module with id %d already loaded!\n",
+ printk(KERN_ERR "NFS: %s Module with id %d already loaded!\n",
__func__, ld_type->id);
}
spin_unlock(&pnfs_spinlock);
@@ -496,12 +496,12 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
{
u32 oldseq, newseq;
- oldseq = be32_to_cpu(lo->plh_stateid.stateid.seqid);
- newseq = be32_to_cpu(new->stateid.seqid);
+ oldseq = be32_to_cpu(lo->plh_stateid.seqid);
+ newseq = be32_to_cpu(new->seqid);
if ((int)(newseq - oldseq) > 0) {
- memcpy(&lo->plh_stateid, &new->stateid, sizeof(new->stateid));
+ nfs4_stateid_copy(&lo->plh_stateid, new);
if (update_barrier) {
- u32 new_barrier = be32_to_cpu(new->stateid.seqid);
+ u32 new_barrier = be32_to_cpu(new->seqid);
if ((int)(new_barrier - lo->plh_barrier))
lo->plh_barrier = new_barrier;
@@ -525,7 +525,7 @@ pnfs_layoutgets_blocked(struct pnfs_layout_hdr *lo, nfs4_stateid *stateid,
int lget)
{
if ((stateid) &&
- (int)(lo->plh_barrier - be32_to_cpu(stateid->stateid.seqid)) >= 0)
+ (int)(lo->plh_barrier - be32_to_cpu(stateid->seqid)) >= 0)
return true;
return lo->plh_block_lgets ||
test_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags) ||
@@ -549,11 +549,10 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
do {
seq = read_seqbegin(&open_state->seqlock);
- memcpy(dst->data, open_state->stateid.data,
- sizeof(open_state->stateid.data));
+ nfs4_stateid_copy(dst, &open_state->stateid);
} while (read_seqretry(&open_state->seqlock, seq));
} else
- memcpy(dst->data, lo->plh_stateid.data, sizeof(lo->plh_stateid.data));
+ nfs4_stateid_copy(dst, &lo->plh_stateid);
spin_unlock(&lo->plh_inode->i_lock);
dprintk("<-- %s\n", __func__);
return status;
@@ -590,7 +589,7 @@ send_layoutget(struct pnfs_layout_hdr *lo,
max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
max_pages = max_resp_sz >> PAGE_SHIFT;
- pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags);
+ pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
if (!pages)
goto out_err_free;
@@ -760,7 +759,7 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
}
if (!found) {
struct pnfs_layout_hdr *lo = nfsi->layout;
- u32 current_seqid = be32_to_cpu(lo->plh_stateid.stateid.seqid);
+ u32 current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
/* Since close does not return a layout stateid for use as
* a barrier, we choose the worst-case barrier.
@@ -966,8 +965,7 @@ pnfs_update_layout(struct inode *ino,
}
/* Do we even need to bother with this? */
- if (test_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state) ||
- test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+ if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
dprintk("%s matches recall, use MDS\n", __func__);
goto out_unlock;
}
@@ -1032,7 +1030,6 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
struct nfs4_layoutget_res *res = &lgp->res;
struct pnfs_layout_segment *lseg;
struct inode *ino = lo->plh_inode;
- struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
int status = 0;
/* Inject layout blob into I/O device driver */
@@ -1048,8 +1045,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
}
spin_lock(&ino->i_lock);
- if (test_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state) ||
- test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+ if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
dprintk("%s forget reply due to recall\n", __func__);
goto out_forget_reply;
}
@@ -1214,6 +1210,7 @@ void pnfs_ld_write_done(struct nfs_write_data *data)
}
data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages);
}
+ put_lseg(data->lseg);
data->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
@@ -1227,6 +1224,7 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
nfs_list_add_request(data->req, &desc->pg_list);
nfs_pageio_reset_write_mds(desc);
desc->pg_recoalesce = 1;
+ put_lseg(data->lseg);
nfs_writedata_release(data);
}
@@ -1327,6 +1325,7 @@ void pnfs_ld_read_done(struct nfs_read_data *data)
data->mds_ops->rpc_call_done(&data->task, data);
} else
pnfs_ld_handle_read_error(data);
+ put_lseg(data->lseg);
data->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
@@ -1530,8 +1529,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
end_pos = nfsi->layout->plh_lwb;
nfsi->layout->plh_lwb = 0;
- memcpy(&data->args.stateid.data, nfsi->layout->plh_stateid.data,
- sizeof(nfsi->layout->plh_stateid.data));
+ nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid);
spin_unlock(&inode->i_lock);
data->args.inode = inode;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 53d593a..442ebf6 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -94,11 +94,10 @@ struct pnfs_layoutdriver_type {
const struct nfs_pageio_ops *pg_read_ops;
const struct nfs_pageio_ops *pg_write_ops;
- /* Returns true if layoutdriver wants to divert this request to
- * driver's commit routine.
- */
- bool (*mark_pnfs_commit)(struct pnfs_layout_segment *lseg);
- struct list_head * (*choose_commit_list) (struct nfs_page *req);
+ void (*mark_request_commit) (struct nfs_page *req,
+ struct pnfs_layout_segment *lseg);
+ void (*clear_request_commit) (struct nfs_page *req);
+ int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock);
int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how);
/*
@@ -229,7 +228,6 @@ struct nfs4_deviceid_node {
atomic_t ref;
};
-void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
@@ -262,20 +260,6 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss)
return nfss->pnfs_curr_ld != NULL;
}
-static inline void
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
-{
- if (lseg) {
- struct pnfs_layoutdriver_type *ld;
-
- ld = NFS_SERVER(req->wb_page->mapping->host)->pnfs_curr_ld;
- if (ld->mark_pnfs_commit && ld->mark_pnfs_commit(lseg)) {
- set_bit(PG_PNFS_COMMIT, &req->wb_flags);
- req->wb_commit_lseg = get_lseg(lseg);
- }
- }
-}
-
static inline int
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
{
@@ -284,27 +268,42 @@ pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how);
}
-static inline struct list_head *
-pnfs_choose_commit_list(struct nfs_page *req, struct list_head *mds)
+static inline bool
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
{
- struct list_head *rv;
+ struct inode *inode = req->wb_context->dentry->d_inode;
+ struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
- if (test_and_clear_bit(PG_PNFS_COMMIT, &req->wb_flags)) {
- struct inode *inode = req->wb_commit_lseg->pls_layout->plh_inode;
+ if (lseg == NULL || ld->mark_request_commit == NULL)
+ return false;
+ ld->mark_request_commit(req, lseg);
+ return true;
+}
- set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
- rv = NFS_SERVER(inode)->pnfs_curr_ld->choose_commit_list(req);
- /* matched by ref taken when PG_PNFS_COMMIT is set */
- put_lseg(req->wb_commit_lseg);
- } else
- rv = mds;
- return rv;
+static inline bool
+pnfs_clear_request_commit(struct nfs_page *req)
+{
+ struct inode *inode = req->wb_context->dentry->d_inode;
+ struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+ if (ld == NULL || ld->clear_request_commit == NULL)
+ return false;
+ ld->clear_request_commit(req);
+ return true;
}
-static inline void pnfs_clear_request_commit(struct nfs_page *req)
+static inline int
+pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
{
- if (test_and_clear_bit(PG_PNFS_COMMIT, &req->wb_flags))
- put_lseg(req->wb_commit_lseg);
+ struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+ int ret;
+
+ if (ld == NULL || ld->scan_commit_lists == NULL)
+ return 0;
+ ret = ld->scan_commit_lists(inode, max, lock);
+ if (ret != 0)
+ set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
+ return ret;
}
/* Should the pNFS client commit and return the layout upon a setattr */
@@ -328,6 +327,13 @@ static inline int pnfs_return_layout(struct inode *ino)
return 0;
}
+#ifdef NFS_DEBUG
+void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
+#else
+static inline void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id)
+{
+}
+#endif /* NFS_DEBUG */
#else /* CONFIG_NFS_V4_1 */
static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
@@ -400,35 +406,35 @@ static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, st
return false;
}
-static inline void
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
-{
-}
-
static inline int
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
{
return PNFS_NOT_ATTEMPTED;
}
-static inline struct list_head *
-pnfs_choose_commit_list(struct nfs_page *req, struct list_head *mds)
+static inline bool
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
{
- return mds;
+ return false;
}
-static inline void pnfs_clear_request_commit(struct nfs_page *req)
+static inline bool
+pnfs_clear_request_commit(struct nfs_page *req)
{
+ return false;
}
-static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
+static inline int
+pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
{
return 0;
}
-static inline void nfs4_deviceid_purge_client(struct nfs_client *ncl)
+static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
{
+ return 0;
}
+
#endif /* CONFIG_NFS_V4_1 */
#endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 4f359d2..73f701f 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -43,6 +43,7 @@
static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
static DEFINE_SPINLOCK(nfs4_deviceid_lock);
+#ifdef NFS_DEBUG
void
nfs4_print_deviceid(const struct nfs4_deviceid *id)
{
@@ -52,6 +53,7 @@ nfs4_print_deviceid(const struct nfs4_deviceid *id)
p[0], p[1], p[2], p[3]);
}
EXPORT_SYMBOL_GPL(nfs4_print_deviceid);
+#endif
static inline u32
nfs4_deviceid_hash(const struct nfs4_deviceid *id)
@@ -92,7 +94,7 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
* @clp nfs_client associated with deviceid
* @id deviceid to look up
*/
-struct nfs4_deviceid_node *
+static struct nfs4_deviceid_node *
_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
const struct nfs_client *clp, const struct nfs4_deviceid *id,
long hash)
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 0c672588..b63b6f4 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -358,6 +358,11 @@ nfs_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
msg->rpc_proc = &nfs_procedures[NFSPROC_REMOVE];
}
+static void nfs_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+ rpc_call_start(task);
+}
+
static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir)
{
if (nfs_async_handle_expired_key(task))
@@ -372,6 +377,11 @@ nfs_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
msg->rpc_proc = &nfs_procedures[NFSPROC_RENAME];
}
+static void nfs_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+ rpc_call_start(task);
+}
+
static int
nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
struct inode *new_dir)
@@ -651,6 +661,11 @@ static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *
msg->rpc_proc = &nfs_procedures[NFSPROC_READ];
}
+static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+ rpc_call_start(task);
+}
+
static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
{
if (nfs_async_handle_expired_key(task))
@@ -668,6 +683,11 @@ static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message
msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE];
}
+static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+ rpc_call_start(task);
+}
+
static void
nfs_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
{
@@ -721,9 +741,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.create = nfs_proc_create,
.remove = nfs_proc_remove,
.unlink_setup = nfs_proc_unlink_setup,
+ .unlink_rpc_prepare = nfs_proc_unlink_rpc_prepare,
.unlink_done = nfs_proc_unlink_done,
.rename = nfs_proc_rename,
.rename_setup = nfs_proc_rename_setup,
+ .rename_rpc_prepare = nfs_proc_rename_rpc_prepare,
.rename_done = nfs_proc_rename_done,
.link = nfs_proc_link,
.symlink = nfs_proc_symlink,
@@ -736,8 +758,10 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.pathconf = nfs_proc_pathconf,
.decode_dirent = nfs2_decode_dirent,
.read_setup = nfs_proc_read_setup,
+ .read_rpc_prepare = nfs_proc_read_rpc_prepare,
.read_done = nfs_read_done,
.write_setup = nfs_proc_write_setup,
+ .write_rpc_prepare = nfs_proc_write_rpc_prepare,
.write_done = nfs_write_done,
.commit_setup = nfs_proc_commit_setup,
.lock = nfs_proc_lock,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index cfa175c..cc1f758 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -66,7 +66,6 @@ void nfs_readdata_free(struct nfs_read_data *p)
void nfs_readdata_release(struct nfs_read_data *rdata)
{
- put_lseg(rdata->lseg);
put_nfs_open_context(rdata->args.context);
nfs_readdata_free(rdata);
}
@@ -465,23 +464,14 @@ static void nfs_readpage_release_partial(void *calldata)
nfs_readdata_release(calldata);
}
-#if defined(CONFIG_NFS_V4_1)
void nfs_read_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_read_data *data = calldata;
-
- if (nfs4_setup_sequence(NFS_SERVER(data->inode),
- &data->args.seq_args, &data->res.seq_res,
- 0, task))
- return;
- rpc_call_start(task);
+ NFS_PROTO(data->inode)->read_rpc_prepare(task, data);
}
-#endif /* CONFIG_NFS_V4_1 */
static const struct rpc_call_ops nfs_read_partial_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_readpage_result_partial,
.rpc_release = nfs_readpage_release_partial,
};
@@ -545,9 +535,7 @@ static void nfs_readpage_release_full(void *calldata)
}
static const struct rpc_call_ops nfs_read_full_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_readpage_result_full,
.rpc_release = nfs_readpage_release_full,
};
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 3dfa4f1..ccc4cdb 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -52,6 +52,8 @@
#include <linux/nfs_xdr.h>
#include <linux/magic.h>
#include <linux/parser.h>
+#include <linux/nsproxy.h>
+#include <linux/rcupdate.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -79,7 +81,6 @@ enum {
Opt_cto, Opt_nocto,
Opt_ac, Opt_noac,
Opt_lock, Opt_nolock,
- Opt_v2, Opt_v3, Opt_v4,
Opt_udp, Opt_tcp, Opt_rdma,
Opt_acl, Opt_noacl,
Opt_rdirplus, Opt_nordirplus,
@@ -97,10 +98,10 @@ enum {
Opt_namelen,
Opt_mountport,
Opt_mountvers,
- Opt_nfsvers,
Opt_minorversion,
/* Mount options that take string arguments */
+ Opt_nfsvers,
Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
Opt_addr, Opt_mountaddr, Opt_clientaddr,
Opt_lookupcache,
@@ -132,9 +133,6 @@ static const match_table_t nfs_mount_option_tokens = {
{ Opt_noac, "noac" },
{ Opt_lock, "lock" },
{ Opt_nolock, "nolock" },
- { Opt_v2, "v2" },
- { Opt_v3, "v3" },
- { Opt_v4, "v4" },
{ Opt_udp, "udp" },
{ Opt_tcp, "tcp" },
{ Opt_rdma, "rdma" },
@@ -163,9 +161,10 @@ static const match_table_t nfs_mount_option_tokens = {
{ Opt_namelen, "namlen=%s" },
{ Opt_mountport, "mountport=%s" },
{ Opt_mountvers, "mountvers=%s" },
+ { Opt_minorversion, "minorversion=%s" },
+
{ Opt_nfsvers, "nfsvers=%s" },
{ Opt_nfsvers, "vers=%s" },
- { Opt_minorversion, "minorversion=%s" },
{ Opt_sec, "sec=%s" },
{ Opt_proto, "proto=%s" },
@@ -179,6 +178,9 @@ static const match_table_t nfs_mount_option_tokens = {
{ Opt_fscache_uniq, "fsc=%s" },
{ Opt_local_lock, "local_lock=%s" },
+ /* The following needs to be listed after all other options */
+ { Opt_nfsvers, "v%s" },
+
{ Opt_err, NULL }
};
@@ -259,6 +261,22 @@ static match_table_t nfs_local_lock_tokens = {
{ Opt_local_lock_err, NULL }
};
+enum {
+ Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0,
+ Opt_vers_4_1,
+
+ Opt_vers_err
+};
+
+static match_table_t nfs_vers_tokens = {
+ { Opt_vers_2, "2" },
+ { Opt_vers_3, "3" },
+ { Opt_vers_4, "4" },
+ { Opt_vers_4_0, "4.0" },
+ { Opt_vers_4_1, "4.1" },
+
+ { Opt_vers_err, NULL }
+};
static void nfs_umount_begin(struct super_block *);
static int nfs_statfs(struct dentry *, struct kstatfs *);
@@ -620,7 +638,6 @@ static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
struct nfs_client *clp = nfss->nfs_client;
seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
- seq_printf(m, ",minorversion=%u", clp->cl_minorversion);
}
#else
static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
@@ -629,6 +646,15 @@ static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
}
#endif
+static void nfs_show_nfs_version(struct seq_file *m,
+ unsigned int version,
+ unsigned int minorversion)
+{
+ seq_printf(m, ",vers=%u", version);
+ if (version == 4)
+ seq_printf(m, ".%u", minorversion);
+}
+
/*
* Describe the mount options in force on this server representation
*/
@@ -656,7 +682,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
u32 version = clp->rpc_ops->version;
int local_flock, local_fcntl;
- seq_printf(m, ",vers=%u", version);
+ nfs_show_nfs_version(m, version, clp->cl_minorversion);
seq_printf(m, ",rsize=%u", nfss->rsize);
seq_printf(m, ",wsize=%u", nfss->wsize);
if (nfss->bsize != 0)
@@ -676,8 +702,10 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
else
seq_puts(m, nfs_infop->nostr);
}
+ rcu_read_lock();
seq_printf(m, ",proto=%s",
rpc_peeraddr2str(nfss->client, RPC_DISPLAY_NETID));
+ rcu_read_unlock();
if (version == 4) {
if (nfss->port != NFS_PORT)
seq_printf(m, ",port=%u", nfss->port);
@@ -726,9 +754,11 @@ static int nfs_show_options(struct seq_file *m, struct dentry *root)
nfs_show_mount_options(m, nfss, 0);
+ rcu_read_lock();
seq_printf(m, ",addr=%s",
rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient,
RPC_DISPLAY_ADDR));
+ rcu_read_unlock();
return 0;
}
@@ -745,7 +775,6 @@ static void show_sessions(struct seq_file *m, struct nfs_server *server) {}
#endif
#endif
-#ifdef CONFIG_NFS_V4
#ifdef CONFIG_NFS_V4_1
static void show_pnfs(struct seq_file *m, struct nfs_server *server)
{
@@ -755,9 +784,26 @@ static void show_pnfs(struct seq_file *m, struct nfs_server *server)
else
seq_printf(m, "not configured");
}
+
+static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
+{
+ if (nfss->nfs_client && nfss->nfs_client->impl_id) {
+ struct nfs41_impl_id *impl_id = nfss->nfs_client->impl_id;
+ seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s',"
+ "date='%llu,%u'",
+ impl_id->name, impl_id->domain,
+ impl_id->date.seconds, impl_id->date.nseconds);
+ }
+}
#else
-static void show_pnfs(struct seq_file *m, struct nfs_server *server) {}
+#ifdef CONFIG_NFS_V4
+static void show_pnfs(struct seq_file *m, struct nfs_server *server)
+{
+}
#endif
+static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
+{
+}
#endif
static int nfs_show_devname(struct seq_file *m, struct dentry *root)
@@ -806,6 +852,8 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ);
+ show_implementation_id(m, nfss);
+
seq_printf(m, "\n\tcaps:\t");
seq_printf(m, "caps=0x%x", nfss->caps);
seq_printf(m, ",wtmult=%u", nfss->wtmult);
@@ -908,6 +956,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve
data->auth_flavor_len = 1;
data->version = version;
data->minorversion = 0;
+ data->net = current->nsproxy->net_ns;
security_init_mnt_opts(&data->lsm_opts);
}
return data;
@@ -1052,6 +1101,40 @@ static int nfs_parse_security_flavors(char *value,
return 1;
}
+static int nfs_parse_version_string(char *string,
+ struct nfs_parsed_mount_data *mnt,
+ substring_t *args)
+{
+ mnt->flags &= ~NFS_MOUNT_VER3;
+ switch (match_token(string, nfs_vers_tokens, args)) {
+ case Opt_vers_2:
+ mnt->version = 2;
+ break;
+ case Opt_vers_3:
+ mnt->flags |= NFS_MOUNT_VER3;
+ mnt->version = 3;
+ break;
+ case Opt_vers_4:
+ /* Backward compatibility option. In future,
+ * the mount program should always supply
+ * a NFSv4 minor version number.
+ */
+ mnt->version = 4;
+ break;
+ case Opt_vers_4_0:
+ mnt->version = 4;
+ mnt->minorversion = 0;
+ break;
+ case Opt_vers_4_1:
+ mnt->version = 4;
+ mnt->minorversion = 1;
+ break;
+ default:
+ return 0;
+ }
+ return 1;
+}
+
static int nfs_get_option_str(substring_t args[], char **option)
{
kfree(*option);
@@ -1157,18 +1240,6 @@ static int nfs_parse_mount_options(char *raw,
mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
NFS_MOUNT_LOCAL_FCNTL);
break;
- case Opt_v2:
- mnt->flags &= ~NFS_MOUNT_VER3;
- mnt->version = 2;
- break;
- case Opt_v3:
- mnt->flags |= NFS_MOUNT_VER3;
- mnt->version = 3;
- break;
- case Opt_v4:
- mnt->flags &= ~NFS_MOUNT_VER3;
- mnt->version = 4;
- break;
case Opt_udp:
mnt->flags &= ~NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
@@ -1295,26 +1366,6 @@ static int nfs_parse_mount_options(char *raw,
goto out_invalid_value;
mnt->mount_server.version = option;
break;
- case Opt_nfsvers:
- if (nfs_get_option_ul(args, &option))
- goto out_invalid_value;
- switch (option) {
- case NFS2_VERSION:
- mnt->flags &= ~NFS_MOUNT_VER3;
- mnt->version = 2;
- break;
- case NFS3_VERSION:
- mnt->flags |= NFS_MOUNT_VER3;
- mnt->version = 3;
- break;
- case NFS4_VERSION:
- mnt->flags &= ~NFS_MOUNT_VER3;
- mnt->version = 4;
- break;
- default:
- goto out_invalid_value;
- }
- break;
case Opt_minorversion:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
@@ -1326,6 +1377,15 @@ static int nfs_parse_mount_options(char *raw,
/*
* options that take text values
*/
+ case Opt_nfsvers:
+ string = match_strdup(args);
+ if (string == NULL)
+ goto out_nomem;
+ rc = nfs_parse_version_string(string, mnt, args);
+ kfree(string);
+ if (!rc)
+ goto out_invalid_value;
+ break;
case Opt_sec:
string = match_strdup(args);
if (string == NULL)
@@ -1405,7 +1465,7 @@ static int nfs_parse_mount_options(char *raw,
if (string == NULL)
goto out_nomem;
mnt->nfs_server.addrlen =
- rpc_pton(string, strlen(string),
+ rpc_pton(mnt->net, string, strlen(string),
(struct sockaddr *)
&mnt->nfs_server.address,
sizeof(mnt->nfs_server.address));
@@ -1427,7 +1487,7 @@ static int nfs_parse_mount_options(char *raw,
if (string == NULL)
goto out_nomem;
mnt->mount_server.addrlen =
- rpc_pton(string, strlen(string),
+ rpc_pton(mnt->net, string, strlen(string),
(struct sockaddr *)
&mnt->mount_server.address,
sizeof(mnt->mount_server.address));
@@ -1516,6 +1576,9 @@ static int nfs_parse_mount_options(char *raw,
if (!sloppy && invalid_option)
return 0;
+ if (mnt->minorversion && mnt->version != 4)
+ goto out_minorversion_mismatch;
+
/*
* verify that any proto=/mountproto= options match the address
* familiies in the addr=/mountaddr= options.
@@ -1549,6 +1612,10 @@ out_invalid_address:
out_invalid_value:
printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p);
return 0;
+out_minorversion_mismatch:
+ printk(KERN_INFO "NFS: mount option vers=%u does not support "
+ "minorversion=%u\n", mnt->version, mnt->minorversion);
+ return 0;
out_nomem:
printk(KERN_INFO "NFS: not enough memory to parse option\n");
return 0;
@@ -1622,6 +1689,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
.noresvport = args->flags & NFS_MOUNT_NORESVPORT,
.auth_flav_len = &server_authlist_len,
.auth_flavs = server_authlist,
+ .net = args->net,
};
int status;
@@ -2047,7 +2115,7 @@ static inline void nfs_initialise_sb(struct super_block *sb)
/* We probably want something more informative here */
snprintf(sb->s_id, sizeof(sb->s_id),
- "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));
+ "%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev));
if (sb->s_blocksize == 0)
sb->s_blocksize = nfs_block_bits(server->wsize,
@@ -2499,12 +2567,6 @@ static int nfs4_validate_text_mount_data(void *options,
return -EINVAL;
}
- if (args->client_address == NULL) {
- dfprintk(MOUNT,
- "NFS4: mount program didn't pass callback address\n");
- return -EINVAL;
- }
-
return nfs_parse_devname(dev_name,
&args->nfs_server.hostname,
NFS4_MAXNAMLEN,
@@ -2663,8 +2725,7 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
if (!s->s_root) {
/* initial superblock/root creation */
nfs4_fill_super(s);
- nfs_fscache_get_super_cookie(
- s, data ? data->fscache_uniq : NULL, NULL);
+ nfs_fscache_get_super_cookie(s, data->fscache_uniq, NULL);
}
mntroot = nfs4_get_root(s, mntfh, dev_name);
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 978aaeb..ad4d2e7 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -32,7 +32,6 @@ static ctl_table nfs_cb_sysctls[] = {
.extra1 = (int *)&nfs_set_port_min,
.extra2 = (int *)&nfs_set_port_max,
},
-#ifndef CONFIG_NFS_USE_NEW_IDMAPPER
{
.procname = "idmap_cache_timeout",
.data = &nfs_idmap_cache_timeout,
@@ -40,7 +39,6 @@ static ctl_table nfs_cb_sysctls[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
-#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
#endif
{
.procname = "nfs_mountpoint_timeout",
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 4f9319a..3210a03 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -20,15 +20,6 @@
#include "iostat.h"
#include "delegation.h"
-struct nfs_unlinkdata {
- struct hlist_node list;
- struct nfs_removeargs args;
- struct nfs_removeres res;
- struct inode *dir;
- struct rpc_cred *cred;
- struct nfs_fattr dir_attr;
-};
-
/**
* nfs_free_unlinkdata - release data from a sillydelete operation.
* @data: pointer to unlink structure.
@@ -107,25 +98,16 @@ static void nfs_async_unlink_release(void *calldata)
nfs_sb_deactive(sb);
}
-#if defined(CONFIG_NFS_V4_1)
-void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
+static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- struct nfs_server *server = NFS_SERVER(data->dir);
-
- if (nfs4_setup_sequence(server, &data->args.seq_args,
- &data->res.seq_res, 1, task))
- return;
- rpc_call_start(task);
+ NFS_PROTO(data->dir)->unlink_rpc_prepare(task, data);
}
-#endif /* CONFIG_NFS_V4_1 */
static const struct rpc_call_ops nfs_unlink_ops = {
.rpc_call_done = nfs_async_unlink_done,
.rpc_release = nfs_async_unlink_release,
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_unlink_prepare,
-#endif /* CONFIG_NFS_V4_1 */
};
static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data)
@@ -341,18 +323,6 @@ nfs_cancel_async_unlink(struct dentry *dentry)
spin_unlock(&dentry->d_lock);
}
-struct nfs_renamedata {
- struct nfs_renameargs args;
- struct nfs_renameres res;
- struct rpc_cred *cred;
- struct inode *old_dir;
- struct dentry *old_dentry;
- struct nfs_fattr old_fattr;
- struct inode *new_dir;
- struct dentry *new_dentry;
- struct nfs_fattr new_fattr;
-};
-
/**
* nfs_async_rename_done - Sillyrename post-processing
* @task: rpc_task of the sillyrename
@@ -403,25 +373,16 @@ static void nfs_async_rename_release(void *calldata)
kfree(data);
}
-#if defined(CONFIG_NFS_V4_1)
static void nfs_rename_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_renamedata *data = calldata;
- struct nfs_server *server = NFS_SERVER(data->old_dir);
-
- if (nfs4_setup_sequence(server, &data->args.seq_args,
- &data->res.seq_res, 1, task))
- return;
- rpc_call_start(task);
+ NFS_PROTO(data->old_dir)->rename_rpc_prepare(task, data);
}
-#endif /* CONFIG_NFS_V4_1 */
static const struct rpc_call_ops nfs_rename_ops = {
.rpc_call_done = nfs_async_rename_done,
.rpc_release = nfs_async_rename_release,
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_rename_prepare,
-#endif /* CONFIG_NFS_V4_1 */
};
/**
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 834f0fe..2c68818 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -100,7 +100,6 @@ void nfs_writedata_free(struct nfs_write_data *p)
void nfs_writedata_release(struct nfs_write_data *wdata)
{
- put_lseg(wdata->lseg);
put_nfs_open_context(wdata->args.context);
nfs_writedata_free(wdata);
}
@@ -236,10 +235,10 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo
req = nfs_page_find_request_locked(page);
if (req == NULL)
break;
- if (nfs_set_page_tag_locked(req))
+ if (nfs_lock_request_dontget(req))
break;
/* Note: If we hold the page lock, as is the case in nfs_writepage,
- * then the call to nfs_set_page_tag_locked() will always
+ * then the call to nfs_lock_request_dontget() will always
* succeed provided that someone hasn't already marked the
* request as dirty (in which case we don't care).
*/
@@ -375,21 +374,14 @@ out_err:
/*
* Insert a write request into an inode
*/
-static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
+static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
{
struct nfs_inode *nfsi = NFS_I(inode);
- int error;
-
- error = radix_tree_preload(GFP_NOFS);
- if (error != 0)
- goto out;
/* Lock the request! */
nfs_lock_request_dontget(req);
spin_lock(&inode->i_lock);
- error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req);
- BUG_ON(error);
if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
inode->i_version++;
set_bit(PG_MAPPED, &req->wb_flags);
@@ -397,12 +389,7 @@ static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
set_page_private(req->wb_page, (unsigned long)req);
nfsi->npages++;
kref_get(&req->wb_kref);
- radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index,
- NFS_PAGE_TAG_LOCKED);
spin_unlock(&inode->i_lock);
- radix_tree_preload_end();
-out:
- return error;
}
/*
@@ -419,7 +406,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
set_page_private(req->wb_page, 0);
ClearPagePrivate(req->wb_page);
clear_bit(PG_MAPPED, &req->wb_flags);
- radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
nfsi->npages--;
spin_unlock(&inode->i_lock);
nfs_release_request(req);
@@ -432,39 +418,90 @@ nfs_mark_request_dirty(struct nfs_page *req)
}
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-/*
- * Add a request to the inode's commit list.
+/**
+ * nfs_request_add_commit_list - add request to a commit list
+ * @req: pointer to a struct nfs_page
+ * @head: commit list head
+ *
+ * This sets the PG_CLEAN bit, updates the inode global count of
+ * number of outstanding requests requiring a commit as well as
+ * the MM page stats.
+ *
+ * The caller must _not_ hold the inode->i_lock, but must be
+ * holding the nfs_page lock.
*/
-static void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+void
+nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head)
{
struct inode *inode = req->wb_context->dentry->d_inode;
- struct nfs_inode *nfsi = NFS_I(inode);
- spin_lock(&inode->i_lock);
set_bit(PG_CLEAN, &(req)->wb_flags);
- radix_tree_tag_set(&nfsi->nfs_page_tree,
- req->wb_index,
- NFS_PAGE_TAG_COMMIT);
- nfsi->ncommit++;
+ spin_lock(&inode->i_lock);
+ nfs_list_add_request(req, head);
+ NFS_I(inode)->ncommit++;
spin_unlock(&inode->i_lock);
- pnfs_mark_request_commit(req, lseg);
inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE);
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
+EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
-static int
+/**
+ * nfs_request_remove_commit_list - Remove request from a commit list
+ * @req: pointer to a nfs_page
+ *
+ * This clears the PG_CLEAN bit, and updates the inode global count of
+ * number of outstanding requests requiring a commit
+ * It does not update the MM page stats.
+ *
+ * The caller _must_ hold the inode->i_lock and the nfs_page lock.
+ */
+void
+nfs_request_remove_commit_list(struct nfs_page *req)
+{
+ struct inode *inode = req->wb_context->dentry->d_inode;
+
+ if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags))
+ return;
+ nfs_list_remove_request(req);
+ NFS_I(inode)->ncommit--;
+}
+EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list);
+
+
+/*
+ * Add a request to the inode's commit list.
+ */
+static void
+nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+{
+ struct inode *inode = req->wb_context->dentry->d_inode;
+
+ if (pnfs_mark_request_commit(req, lseg))
+ return;
+ nfs_request_add_commit_list(req, &NFS_I(inode)->commit_list);
+}
+
+static void
+nfs_clear_page_commit(struct page *page)
+{
+ dec_zone_page_state(page, NR_UNSTABLE_NFS);
+ dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+}
+
+static void
nfs_clear_request_commit(struct nfs_page *req)
{
- struct page *page = req->wb_page;
+ if (test_bit(PG_CLEAN, &req->wb_flags)) {
+ struct inode *inode = req->wb_context->dentry->d_inode;
- if (test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) {
- dec_zone_page_state(page, NR_UNSTABLE_NFS);
- dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
- return 1;
+ if (!pnfs_clear_request_commit(req)) {
+ spin_lock(&inode->i_lock);
+ nfs_request_remove_commit_list(req);
+ spin_unlock(&inode->i_lock);
+ }
+ nfs_clear_page_commit(req->wb_page);
}
- return 0;
}
static inline
@@ -491,15 +528,14 @@ int nfs_reschedule_unstable_write(struct nfs_page *req,
return 0;
}
#else
-static inline void
+static void
nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
{
}
-static inline int
+static void
nfs_clear_request_commit(struct nfs_page *req)
{
- return 0;
}
static inline
@@ -520,46 +556,65 @@ int nfs_reschedule_unstable_write(struct nfs_page *req,
static int
nfs_need_commit(struct nfs_inode *nfsi)
{
- return radix_tree_tagged(&nfsi->nfs_page_tree, NFS_PAGE_TAG_COMMIT);
+ return nfsi->ncommit > 0;
+}
+
+/* i_lock held by caller */
+static int
+nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max,
+ spinlock_t *lock)
+{
+ struct nfs_page *req, *tmp;
+ int ret = 0;
+
+ list_for_each_entry_safe(req, tmp, src, wb_list) {
+ if (!nfs_lock_request(req))
+ continue;
+ if (cond_resched_lock(lock))
+ list_safe_reset_next(req, tmp, wb_list);
+ nfs_request_remove_commit_list(req);
+ nfs_list_add_request(req, dst);
+ ret++;
+ if (ret == max)
+ break;
+ }
+ return ret;
}
/*
* nfs_scan_commit - Scan an inode for commit requests
* @inode: NFS inode to scan
* @dst: destination list
- * @idx_start: lower bound of page->index to scan.
- * @npages: idx_start + npages sets the upper bound to scan.
*
* Moves requests from the inode's 'commit' request list.
* The requests are *not* checked to ensure that they form a contiguous set.
*/
static int
-nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
+nfs_scan_commit(struct inode *inode, struct list_head *dst)
{
struct nfs_inode *nfsi = NFS_I(inode);
- int ret;
-
- if (!nfs_need_commit(nfsi))
- return 0;
+ int ret = 0;
spin_lock(&inode->i_lock);
- ret = nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT);
- if (ret > 0)
- nfsi->ncommit -= ret;
- spin_unlock(&inode->i_lock);
-
- if (nfs_need_commit(NFS_I(inode)))
- __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ if (nfsi->ncommit > 0) {
+ const int max = INT_MAX;
+ ret = nfs_scan_commit_list(&nfsi->commit_list, dst, max,
+ &inode->i_lock);
+ ret += pnfs_scan_commit_lists(inode, max - ret,
+ &inode->i_lock);
+ }
+ spin_unlock(&inode->i_lock);
return ret;
}
+
#else
static inline int nfs_need_commit(struct nfs_inode *nfsi)
{
return 0;
}
-static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
+static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst)
{
return 0;
}
@@ -604,7 +659,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
|| end < req->wb_offset)
goto out_flushme;
- if (nfs_set_page_tag_locked(req))
+ if (nfs_lock_request_dontget(req))
break;
/* The request is locked, so wait and then retry */
@@ -616,13 +671,6 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
spin_lock(&inode->i_lock);
}
- if (nfs_clear_request_commit(req) &&
- radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree,
- req->wb_index, NFS_PAGE_TAG_COMMIT) != NULL) {
- NFS_I(inode)->ncommit--;
- pnfs_clear_request_commit(req);
- }
-
/* Okay, the request matches. Update the region */
if (offset < req->wb_offset) {
req->wb_offset = offset;
@@ -634,6 +682,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
req->wb_bytes = rqend - req->wb_offset;
out_unlock:
spin_unlock(&inode->i_lock);
+ nfs_clear_request_commit(req);
return req;
out_flushme:
spin_unlock(&inode->i_lock);
@@ -655,7 +704,6 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
{
struct inode *inode = page->mapping->host;
struct nfs_page *req;
- int error;
req = nfs_try_to_update_request(inode, page, offset, bytes);
if (req != NULL)
@@ -663,11 +711,7 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
req = nfs_create_request(ctx, inode, page, offset, bytes);
if (IS_ERR(req))
goto out;
- error = nfs_inode_add_request(inode, req);
- if (error != 0) {
- nfs_release_request(req);
- req = ERR_PTR(error);
- }
+ nfs_inode_add_request(inode, req);
out:
return req;
}
@@ -684,7 +728,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
nfs_grow_file(page, offset, count);
nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
nfs_mark_request_dirty(req);
- nfs_clear_page_tag_locked(req);
+ nfs_unlock_request(req);
return 0;
}
@@ -777,7 +821,7 @@ static void nfs_writepage_release(struct nfs_page *req,
if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data))
nfs_inode_remove_request(req);
- nfs_clear_page_tag_locked(req);
+ nfs_unlock_request(req);
nfs_end_page_writeback(page);
}
@@ -925,7 +969,7 @@ static void nfs_redirty_request(struct nfs_page *req)
struct page *page = req->wb_page;
nfs_mark_request_dirty(req);
- nfs_clear_page_tag_locked(req);
+ nfs_unlock_request(req);
nfs_end_page_writeback(page);
}
@@ -1128,23 +1172,14 @@ out:
nfs_writedata_release(calldata);
}
-#if defined(CONFIG_NFS_V4_1)
void nfs_write_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_write_data *data = calldata;
-
- if (nfs4_setup_sequence(NFS_SERVER(data->inode),
- &data->args.seq_args,
- &data->res.seq_res, 1, task))
- return;
- rpc_call_start(task);
+ NFS_PROTO(data->inode)->write_rpc_prepare(task, data);
}
-#endif /* CONFIG_NFS_V4_1 */
static const struct rpc_call_ops nfs_write_partial_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_writeback_done_partial,
.rpc_release = nfs_writeback_release_partial,
};
@@ -1199,16 +1234,14 @@ static void nfs_writeback_release_full(void *calldata)
remove_request:
nfs_inode_remove_request(req);
next:
- nfs_clear_page_tag_locked(req);
+ nfs_unlock_request(req);
nfs_end_page_writeback(page);
}
nfs_writedata_release(calldata);
}
static const struct rpc_call_ops nfs_write_full_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_writeback_done_full,
.rpc_release = nfs_writeback_release_full,
};
@@ -1325,7 +1358,6 @@ void nfs_commitdata_release(void *data)
{
struct nfs_write_data *wdata = data;
- put_lseg(wdata->lseg);
put_nfs_open_context(wdata->args.context);
nfs_commit_free(wdata);
}
@@ -1411,7 +1443,7 @@ void nfs_retry_commit(struct list_head *page_list,
dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
BDI_RECLAIMABLE);
- nfs_clear_page_tag_locked(req);
+ nfs_unlock_request(req);
}
}
EXPORT_SYMBOL_GPL(nfs_retry_commit);
@@ -1460,7 +1492,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data)
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
- nfs_clear_request_commit(req);
+ nfs_clear_page_commit(req->wb_page);
dprintk("NFS: commit (%s/%lld %d@%lld)",
req->wb_context->dentry->d_sb->s_id,
@@ -1486,7 +1518,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data)
dprintk(" mismatch\n");
nfs_mark_request_dirty(req);
next:
- nfs_clear_page_tag_locked(req);
+ nfs_unlock_request(req);
}
}
EXPORT_SYMBOL_GPL(nfs_commit_release_pages);
@@ -1501,9 +1533,7 @@ static void nfs_commit_release(void *calldata)
}
static const struct rpc_call_ops nfs_commit_ops = {
-#if defined(CONFIG_NFS_V4_1)
.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
.rpc_call_done = nfs_commit_done,
.rpc_release = nfs_commit_release,
};
@@ -1517,7 +1547,7 @@ int nfs_commit_inode(struct inode *inode, int how)
res = nfs_commit_set_lock(NFS_I(inode), may_wait);
if (res <= 0)
goto out_mark_dirty;
- res = nfs_scan_commit(inode, &head, 0, 0);
+ res = nfs_scan_commit(inode, &head);
if (res) {
int error;
@@ -1635,6 +1665,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
if (req == NULL)
break;
if (nfs_lock_request_dontget(req)) {
+ nfs_clear_request_commit(req);
nfs_inode_remove_request(req);
/*
* In case nfs_inode_remove_request has marked the
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index ce7f075..9559ce4 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -72,7 +72,7 @@ int nfsd_fault_inject_init(void)
{
unsigned int i;
struct nfsd_fault_inject_op *op;
- mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
debug_dir = debugfs_create_dir("nfsd", NULL);
if (!debug_dir)
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 6f3ebb4..0e262f3 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -605,24 +605,24 @@ static struct rpc_version nfs_cb_version4 = {
.procs = nfs4_cb_procedures
};
-static struct rpc_version *nfs_cb_version[] = {
+static const struct rpc_version *nfs_cb_version[] = {
&nfs_cb_version4,
};
-static struct rpc_program cb_program;
+static const struct rpc_program cb_program;
static struct rpc_stat cb_stats = {
.program = &cb_program
};
#define NFS4_CALLBACK 0x40000000
-static struct rpc_program cb_program = {
+static const struct rpc_program cb_program = {
.name = "nfs4_cb",
.number = NFS4_CALLBACK,
.nrvers = ARRAY_SIZE(nfs_cb_version),
.version = nfs_cb_version,
.stats = &cb_stats,
- .pipe_dir_name = "/nfsd4_cb",
+ .pipe_dir_name = "nfsd4_cb",
};
static int max_cb_time(void)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e8c98f0..c5cddd6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1308,7 +1308,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r
else
goto out_err;
- conn->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
+ conn->cb_addrlen = rpc_uaddr2sockaddr(&init_net, se->se_callback_addr_val,
se->se_callback_addr_len,
(struct sockaddr *)&conn->cb_addr,
sizeof(conn->cb_addr));
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 748eda9..64c24af 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -223,7 +223,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
if (qword_get(&buf, fo_path, size) < 0)
return -EINVAL;
- if (rpc_pton(fo_path, size, sap, salen) == 0)
+ if (rpc_pton(&init_net, fo_path, size, sap, salen) == 0)
return -EINVAL;
return nlmsvc_unlock_all_by_ip(sap);
@@ -722,7 +722,7 @@ static ssize_t __write_ports_addxprt(char *buf)
nfsd_serv->sv_nrthreads--;
return 0;
out_close:
- xprt = svc_find_xprt(nfsd_serv, transport, PF_INET, port);
+ xprt = svc_find_xprt(nfsd_serv, transport, &init_net, PF_INET, port);
if (xprt != NULL) {
svc_close_xprt(xprt);
svc_xprt_put(xprt);
@@ -748,7 +748,7 @@ static ssize_t __write_ports_delxprt(char *buf)
if (port < 1 || port > USHRT_MAX || nfsd_serv == NULL)
return -EINVAL;
- xprt = svc_find_xprt(nfsd_serv, transport, AF_UNSPEC, port);
+ xprt = svc_find_xprt(nfsd_serv, transport, &init_net, AF_UNSPEC, port);
if (xprt == NULL)
return -ENOTCONN;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index eda7d7e..fce472f 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -251,13 +251,13 @@ static void nfsd_shutdown(void)
nfsd_up = false;
}
-static void nfsd_last_thread(struct svc_serv *serv)
+static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
{
/* When last nfsd thread exits we need to do some clean-up */
nfsd_serv = NULL;
nfsd_shutdown();
- svc_rpcb_cleanup(serv);
+ svc_rpcb_cleanup(serv, net);
printk(KERN_WARNING "nfsd: last server has exited, flushing export "
"cache\n");
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index a2e2402..6d4521f 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -25,6 +25,7 @@
#include <linux/module.h>
#include <linux/sunrpc/stats.h>
#include <linux/nfsd/stats.h>
+#include <net/net_namespace.h>
#include "nfsd.h"
@@ -94,11 +95,11 @@ static const struct file_operations nfsd_proc_fops = {
void
nfsd_stat_init(void)
{
- svc_proc_register(&nfsd_svcstats, &nfsd_proc_fops);
+ svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_fops);
}
void
nfsd_stat_shutdown(void)
{
- svc_proc_unregister("nfsd");
+ svc_proc_unregister(&init_net, "nfsd");
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index edf6d3e..e59f71d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1541,30 +1541,31 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32
nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
{
- struct dentry *dentry;
struct inode *inode;
mm_segment_t oldfs;
__be32 err;
int host_err;
+ struct path path;
err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP);
if (err)
goto out;
- dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
+ path.mnt = fhp->fh_export->ex_path.mnt;
+ path.dentry = fhp->fh_dentry;
+ inode = path.dentry->d_inode;
err = nfserr_inval;
if (!inode->i_op->readlink)
goto out;
- touch_atime(fhp->fh_export->ex_path.mnt, dentry);
+ touch_atime(&path);
/* N.B. Why does this call need a get_fs()??
* Remove the set_fs and watch the fireworks:-) --okir
*/
oldfs = get_fs(); set_fs(KERNEL_DS);
- host_err = inode->i_op->readlink(dentry, buf, *lenp);
+ host_err = inode->i_op->readlink(path.dentry, buf, *lenp);
set_fs(oldfs);
if (host_err < 0)
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index c9b342c..dab5c4c 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -218,11 +218,11 @@ int nilfs_cpfile_get_checkpoint(struct inode *cpfile,
kaddr, 1);
mark_buffer_dirty(cp_bh);
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh,
kaddr);
le64_add_cpu(&header->ch_ncheckpoints, 1);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(header_bh);
nilfs_mdt_mark_dirty(cpfile);
}
@@ -313,7 +313,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
continue;
}
- kaddr = kmap_atomic(cp_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(
cpfile, cno, cp_bh, kaddr);
nicps = 0;
@@ -334,7 +334,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
cpfile, cp_bh, kaddr, nicps);
if (count == 0) {
/* make hole */
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(cp_bh);
ret =
nilfs_cpfile_delete_checkpoint_block(
@@ -349,18 +349,18 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
}
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(cp_bh);
}
if (tnicps > 0) {
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh,
kaddr);
le64_add_cpu(&header->ch_ncheckpoints, -(u64)tnicps);
mark_buffer_dirty(header_bh);
nilfs_mdt_mark_dirty(cpfile);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
brelse(header_bh);
@@ -408,7 +408,7 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
continue; /* skip hole */
}
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
for (i = 0; i < ncps && n < nci; i++, cp = (void *)cp + cpsz) {
if (!nilfs_checkpoint_invalid(cp)) {
@@ -418,7 +418,7 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
n++;
}
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh);
}
@@ -451,10 +451,10 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
ret = nilfs_cpfile_get_header_block(cpfile, &bh);
if (ret < 0)
goto out;
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
curr = le64_to_cpu(header->ch_snapshot_list.ssl_next);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh);
if (curr == 0) {
ret = 0;
@@ -472,7 +472,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
ret = 0; /* No snapshots (started from a hole block) */
goto out;
}
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
while (n < nci) {
cp = nilfs_cpfile_block_get_checkpoint(cpfile, curr, bh, kaddr);
curr = ~(__u64)0; /* Terminator */
@@ -488,7 +488,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
next_blkoff = nilfs_cpfile_get_blkoff(cpfile, next);
if (curr_blkoff != next_blkoff) {
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh);
ret = nilfs_cpfile_get_checkpoint_block(cpfile, next,
0, &bh);
@@ -496,12 +496,12 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
WARN_ON(ret == -ENOENT);
goto out;
}
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
}
curr = next;
curr_blkoff = next_blkoff;
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh);
*cnop = curr;
ret = n;
@@ -592,24 +592,24 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(cp_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
if (nilfs_checkpoint_invalid(cp)) {
ret = -ENOENT;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
goto out_cp;
}
if (nilfs_checkpoint_snapshot(cp)) {
ret = 0;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
goto out_cp;
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
if (ret < 0)
goto out_cp;
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
list = &header->ch_snapshot_list;
curr_bh = header_bh;
@@ -621,13 +621,13 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
prev_blkoff = nilfs_cpfile_get_blkoff(cpfile, prev);
curr = prev;
if (curr_blkoff != prev_blkoff) {
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(curr_bh);
ret = nilfs_cpfile_get_checkpoint_block(cpfile, curr,
0, &curr_bh);
if (ret < 0)
goto out_header;
- kaddr = kmap_atomic(curr_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(curr_bh->b_page);
}
curr_blkoff = prev_blkoff;
cp = nilfs_cpfile_block_get_checkpoint(
@@ -635,7 +635,7 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
list = &cp->cp_snapshot_list;
prev = le64_to_cpu(list->ssl_prev);
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (prev != 0) {
ret = nilfs_cpfile_get_checkpoint_block(cpfile, prev, 0,
@@ -647,29 +647,29 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
get_bh(prev_bh);
}
- kaddr = kmap_atomic(curr_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(curr_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, curr, curr_bh, kaddr);
list->ssl_prev = cpu_to_le64(cno);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(cp_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
cp->cp_snapshot_list.ssl_next = cpu_to_le64(curr);
cp->cp_snapshot_list.ssl_prev = cpu_to_le64(prev);
nilfs_checkpoint_set_snapshot(cp);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(prev_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(prev_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, prev, prev_bh, kaddr);
list->ssl_next = cpu_to_le64(cno);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
le64_add_cpu(&header->ch_nsnapshots, 1);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(prev_bh);
mark_buffer_dirty(curr_bh);
@@ -710,23 +710,23 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(cp_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
if (nilfs_checkpoint_invalid(cp)) {
ret = -ENOENT;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
goto out_cp;
}
if (!nilfs_checkpoint_snapshot(cp)) {
ret = 0;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
goto out_cp;
}
list = &cp->cp_snapshot_list;
next = le64_to_cpu(list->ssl_next);
prev = le64_to_cpu(list->ssl_prev);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
if (ret < 0)
@@ -750,29 +750,29 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
get_bh(prev_bh);
}
- kaddr = kmap_atomic(next_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(next_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, next, next_bh, kaddr);
list->ssl_prev = cpu_to_le64(prev);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(prev_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(prev_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, prev, prev_bh, kaddr);
list->ssl_next = cpu_to_le64(next);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(cp_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
cp->cp_snapshot_list.ssl_next = cpu_to_le64(0);
cp->cp_snapshot_list.ssl_prev = cpu_to_le64(0);
nilfs_checkpoint_clear_snapshot(cp);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
le64_add_cpu(&header->ch_nsnapshots, -1);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(next_bh);
mark_buffer_dirty(prev_bh);
@@ -829,13 +829,13 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &bh);
if (ret < 0)
goto out;
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
if (nilfs_checkpoint_invalid(cp))
ret = -ENOENT;
else
ret = nilfs_checkpoint_snapshot(cp);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh);
out:
@@ -912,12 +912,12 @@ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat)
ret = nilfs_cpfile_get_header_block(cpfile, &bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
cpstat->cs_cno = nilfs_mdt_cno(cpfile);
cpstat->cs_ncps = le64_to_cpu(header->ch_ncheckpoints);
cpstat->cs_nsss = le64_to_cpu(header->ch_nsnapshots);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh);
out_sem:
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index fcc2f86..b5c13f3 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -85,13 +85,13 @@ void nilfs_dat_commit_alloc(struct inode *dat, struct nilfs_palloc_req *req)
struct nilfs_dat_entry *entry;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
entry->de_start = cpu_to_le64(NILFS_CNO_MIN);
entry->de_end = cpu_to_le64(NILFS_CNO_MAX);
entry->de_blocknr = cpu_to_le64(0);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nilfs_palloc_commit_alloc_entry(dat, req);
nilfs_dat_commit_entry(dat, req);
@@ -109,13 +109,13 @@ static void nilfs_dat_commit_free(struct inode *dat,
struct nilfs_dat_entry *entry;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
entry->de_start = cpu_to_le64(NILFS_CNO_MIN);
entry->de_end = cpu_to_le64(NILFS_CNO_MIN);
entry->de_blocknr = cpu_to_le64(0);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nilfs_dat_commit_entry(dat, req);
nilfs_palloc_commit_free_entry(dat, req);
@@ -136,12 +136,12 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req,
struct nilfs_dat_entry *entry;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
entry->de_start = cpu_to_le64(nilfs_mdt_cno(dat));
entry->de_blocknr = cpu_to_le64(blocknr);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nilfs_dat_commit_entry(dat, req);
}
@@ -160,12 +160,12 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req)
return ret;
}
- kaddr = kmap_atomic(req->pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
start = le64_to_cpu(entry->de_start);
blocknr = le64_to_cpu(entry->de_blocknr);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (blocknr == 0) {
ret = nilfs_palloc_prepare_free_entry(dat, req);
@@ -186,7 +186,7 @@ void nilfs_dat_commit_end(struct inode *dat, struct nilfs_palloc_req *req,
sector_t blocknr;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
end = start = le64_to_cpu(entry->de_start);
@@ -196,7 +196,7 @@ void nilfs_dat_commit_end(struct inode *dat, struct nilfs_palloc_req *req,
}
entry->de_end = cpu_to_le64(end);
blocknr = le64_to_cpu(entry->de_blocknr);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (blocknr == 0)
nilfs_dat_commit_free(dat, req);
@@ -211,12 +211,12 @@ void nilfs_dat_abort_end(struct inode *dat, struct nilfs_palloc_req *req)
sector_t blocknr;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
start = le64_to_cpu(entry->de_start);
blocknr = le64_to_cpu(entry->de_blocknr);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (start == nilfs_mdt_cno(dat) && blocknr == 0)
nilfs_palloc_abort_free_entry(dat, req);
@@ -346,20 +346,20 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
}
}
- kaddr = kmap_atomic(entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
if (unlikely(entry->de_blocknr == cpu_to_le64(0))) {
printk(KERN_CRIT "%s: vbn = %llu, [%llu, %llu)\n", __func__,
(unsigned long long)vblocknr,
(unsigned long long)le64_to_cpu(entry->de_start),
(unsigned long long)le64_to_cpu(entry->de_end));
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(entry_bh);
return -EINVAL;
}
WARN_ON(blocknr == 0);
entry->de_blocknr = cpu_to_le64(blocknr);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(entry_bh);
nilfs_mdt_mark_dirty(dat);
@@ -409,7 +409,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
}
}
- kaddr = kmap_atomic(entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
blocknr = le64_to_cpu(entry->de_blocknr);
if (blocknr == 0) {
@@ -419,7 +419,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
*blocknrp = blocknr;
out:
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(entry_bh);
return ret;
}
@@ -440,7 +440,7 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned visz,
0, &entry_bh);
if (ret < 0)
return ret;
- kaddr = kmap_atomic(entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(entry_bh->b_page);
/* last virtual block number in this block */
first = vinfo->vi_vblocknr;
do_div(first, entries_per_block);
@@ -456,7 +456,7 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned visz,
vinfo->vi_end = le64_to_cpu(entry->de_end);
vinfo->vi_blocknr = le64_to_cpu(entry->de_blocknr);
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(entry_bh);
}
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index ca35b3a..df1a7fb 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -602,7 +602,7 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent)
unlock_page(page);
goto fail;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr, 0, chunk_size);
de = (struct nilfs_dir_entry *)kaddr;
de->name_len = 1;
@@ -617,7 +617,7 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent)
de->inode = cpu_to_le64(parent->i_ino);
memcpy(de->name, "..\0", 4);
nilfs_set_de_type(de, inode);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nilfs_commit_chunk(page, mapping, 0, chunk_size);
fail:
page_cache_release(page);
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 684d763..5a48df7 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -122,11 +122,11 @@ int nilfs_ifile_delete_inode(struct inode *ifile, ino_t ino)
return ret;
}
- kaddr = kmap_atomic(req.pr_entry_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(req.pr_entry_bh->b_page);
raw_inode = nilfs_palloc_block_get_entry(ifile, req.pr_entry_nr,
req.pr_entry_bh, kaddr);
raw_inode->i_flags = 0;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(req.pr_entry_bh);
brelse(req.pr_entry_bh);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 8866496..2a70fce 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -603,6 +603,8 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
nsegs = argv[4].v_nmembs;
if (argv[4].v_size != argsz[4])
goto out;
+ if (nsegs > UINT_MAX / sizeof(__u64))
+ goto out;
/*
* argv[4] points to segment numbers this ioctl cleans. We
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 800e8d7..f9897d0 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -58,12 +58,12 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
set_buffer_mapped(bh);
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits);
if (init_block)
init_block(inode, bh, kaddr);
flush_dcache_page(bh->b_page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1cd3f62..fce2bbe 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -193,9 +193,6 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
struct nilfs_transaction_info ti;
int err;
- if (inode->i_nlink >= NILFS_LINK_MAX)
- return -EMLINK;
-
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
@@ -219,9 +216,6 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct nilfs_transaction_info ti;
int err;
- if (dir->i_nlink >= NILFS_LINK_MAX)
- return -EMLINK;
-
err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
if (err)
return err;
@@ -400,11 +394,6 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
drop_nlink(new_inode);
nilfs_mark_inode_dirty(new_inode);
} else {
- if (dir_de) {
- err = -EMLINK;
- if (new_dir->i_nlink >= NILFS_LINK_MAX)
- goto out_dir;
- }
err = nilfs_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 65221a0..3e7b2a0 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -119,11 +119,11 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
struct page *spage = sbh->b_page, *dpage = dbh->b_page;
struct buffer_head *bh;
- kaddr0 = kmap_atomic(spage, KM_USER0);
- kaddr1 = kmap_atomic(dpage, KM_USER1);
+ kaddr0 = kmap_atomic(spage);
+ kaddr1 = kmap_atomic(dpage);
memcpy(kaddr1 + bh_offset(dbh), kaddr0 + bh_offset(sbh), sbh->b_size);
- kunmap_atomic(kaddr1, KM_USER1);
- kunmap_atomic(kaddr0, KM_USER0);
+ kunmap_atomic(kaddr1);
+ kunmap_atomic(kaddr0);
dbh->b_state = sbh->b_state & NILFS_BUFFER_INHERENT_BITS;
dbh->b_blocknr = sbh->b_blocknr;
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index a604ac0..f1626f5 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -493,9 +493,9 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
if (unlikely(!bh_org))
return -EIO;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(bh_org);
return 0;
}
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 850a7c0..dc9a913 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -227,9 +227,9 @@ static void nilfs_segbuf_fill_in_data_crc(struct nilfs_segment_buffer *segbuf,
crc = crc32_le(crc, bh->b_data, bh->b_size);
}
list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
crc = crc32_le(crc, kaddr + bh_offset(bh), bh->b_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
raw_sum->ss_datasum = cpu_to_le32(crc);
}
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 0a0aba6..c5b7653 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -111,11 +111,11 @@ static void nilfs_sufile_mod_counter(struct buffer_head *header_bh,
struct nilfs_sufile_header *header;
void *kaddr;
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
le64_add_cpu(&header->sh_ncleansegs, ncleanadd);
le64_add_cpu(&header->sh_ndirtysegs, ndirtyadd);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(header_bh);
}
@@ -319,11 +319,11 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
ret = nilfs_sufile_get_header_block(sufile, &header_bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
ncleansegs = le64_to_cpu(header->sh_ncleansegs);
last_alloc = le64_to_cpu(header->sh_last_alloc);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nsegments = nilfs_sufile_get_nsegments(sufile);
maxsegnum = sui->allocmax;
@@ -356,7 +356,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
&su_bh);
if (ret < 0)
goto out_header;
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
@@ -367,14 +367,14 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
continue;
/* found a clean segment */
nilfs_segment_usage_set_dirty(su);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
le64_add_cpu(&header->sh_ncleansegs, -1);
le64_add_cpu(&header->sh_ndirtysegs, 1);
header->sh_last_alloc = cpu_to_le64(segnum);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
sui->ncleansegs--;
mark_buffer_dirty(header_bh);
@@ -385,7 +385,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
goto out_header;
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(su_bh);
}
@@ -407,16 +407,16 @@ void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
struct nilfs_segment_usage *su;
void *kaddr;
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (unlikely(!nilfs_segment_usage_clean(su))) {
printk(KERN_WARNING "%s: segment %llu must be clean\n",
__func__, (unsigned long long)segnum);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
return;
}
nilfs_segment_usage_set_dirty(su);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nilfs_sufile_mod_counter(header_bh, -1, 1);
NILFS_SUI(sufile)->ncleansegs--;
@@ -433,11 +433,11 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
void *kaddr;
int clean, dirty;
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (su->su_flags == cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY) &&
su->su_nblocks == cpu_to_le32(0)) {
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
return;
}
clean = nilfs_segment_usage_clean(su);
@@ -447,7 +447,7 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
su->su_lastmod = cpu_to_le64(0);
su->su_nblocks = cpu_to_le32(0);
su->su_flags = cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1);
NILFS_SUI(sufile)->ncleansegs -= clean;
@@ -464,12 +464,12 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
void *kaddr;
int sudirty;
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (nilfs_segment_usage_clean(su)) {
printk(KERN_WARNING "%s: segment %llu is already clean\n",
__func__, (unsigned long long)segnum);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
return;
}
WARN_ON(nilfs_segment_usage_error(su));
@@ -477,7 +477,7 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
sudirty = nilfs_segment_usage_dirty(su);
nilfs_segment_usage_set_clean(su);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(su_bh);
nilfs_sufile_mod_counter(header_bh, 1, sudirty ? (u64)-1 : 0);
@@ -525,13 +525,13 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
WARN_ON(nilfs_segment_usage_error(su));
if (modtime)
su->su_lastmod = cpu_to_le64(modtime);
su->su_nblocks = cpu_to_le32(nblocks);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(bh);
nilfs_mdt_mark_dirty(sufile);
@@ -572,7 +572,7 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
sustat->ss_nsegs = nilfs_sufile_get_nsegments(sufile);
sustat->ss_ncleansegs = le64_to_cpu(header->sh_ncleansegs);
@@ -582,7 +582,7 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
spin_lock(&nilfs->ns_last_segment_lock);
sustat->ss_prot_seq = nilfs->ns_prot_seq;
spin_unlock(&nilfs->ns_last_segment_lock);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(header_bh);
out_sem:
@@ -598,15 +598,15 @@ void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
void *kaddr;
int suclean;
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (nilfs_segment_usage_error(su)) {
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
return;
}
suclean = nilfs_segment_usage_clean(su);
nilfs_segment_usage_set_error(su);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (suclean) {
nilfs_sufile_mod_counter(header_bh, -1, 0);
@@ -675,7 +675,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
/* hole */
continue;
}
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
su2 = su;
@@ -684,7 +684,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
~(1UL << NILFS_SEGMENT_USAGE_ERROR)) ||
nilfs_segment_is_active(nilfs, segnum + j)) {
ret = -EBUSY;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(su_bh);
goto out_header;
}
@@ -696,7 +696,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
nc++;
}
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (nc > 0) {
mark_buffer_dirty(su_bh);
ncleaned += nc;
@@ -772,10 +772,10 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
sui->ncleansegs -= nsegs - newnsegs;
}
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
header->sh_ncleansegs = cpu_to_le64(sui->ncleansegs);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
mark_buffer_dirty(header_bh);
nilfs_mdt_mark_dirty(sufile);
@@ -840,7 +840,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
continue;
}
- kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
for (j = 0; j < n;
@@ -853,7 +853,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
si->sui_flags |=
(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(su_bh);
}
ret = nsegs;
@@ -902,10 +902,10 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
goto failed;
sui = NILFS_SUI(sufile);
- kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
+ kaddr = kmap_atomic(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
sui->ncleansegs = le64_to_cpu(header->sh_ncleansegs);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
brelse(header_bh);
sui->allocmax = nilfs_sufile_get_nsegments(sufile) - 1;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 08e3d4f..1099a76 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -917,9 +917,8 @@ static int nilfs_get_root_dentry(struct super_block *sb,
if (root->cno == NILFS_CPTREE_CURRENT_CNO) {
dentry = d_find_alias(inode);
if (!dentry) {
- dentry = d_alloc_root(inode);
+ dentry = d_make_root(inode);
if (!dentry) {
- iput(inode);
ret = -ENOMEM;
goto failed_dentry;
}
@@ -1059,6 +1058,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_export_op = &nilfs_export_ops;
sb->s_root = NULL;
sb->s_time_gran = 1;
+ sb->s_max_links = NILFS_LINK_MAX;
bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
sb->s_bdi = bdi ? : &default_backing_dev_info;
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index d327140..501b7f8 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -409,6 +409,12 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
nilfs->ns_first_data_block = le64_to_cpu(sbp->s_first_data_block);
nilfs->ns_r_segments_percentage =
le32_to_cpu(sbp->s_r_segments_percentage);
+ if (nilfs->ns_r_segments_percentage < 1 ||
+ nilfs->ns_r_segments_percentage > 99) {
+ printk(KERN_ERR "NILFS: invalid reserved segments percentage.\n");
+ return -EINVAL;
+ }
+
nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments));
nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed);
return 0;
@@ -515,6 +521,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
brelse(sbh[1]);
sbh[1] = NULL;
sbp[1] = NULL;
+ valid[1] = 0;
swp = 0;
}
if (!valid[swp]) {
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index ee18815..c887b13 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -447,7 +447,7 @@ struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
return event;
}
-__init int fsnotify_notification_init(void)
+static __init int fsnotify_notification_init(void)
{
fsnotify_event_cachep = KMEM_CACHE(fsnotify_event, SLAB_PANIC);
fsnotify_event_holder_cachep = KMEM_CACHE(fsnotify_event_holder, SLAB_PANIC);
@@ -461,4 +461,3 @@ __init int fsnotify_notification_init(void)
return 0;
}
subsys_initcall(fsnotify_notification_init);
-
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 0b1e885b..fa9c05f 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -94,11 +94,11 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
if (file_ofs < init_size)
ofs = init_size - file_ofs;
local_irq_save(flags);
- kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ);
+ kaddr = kmap_atomic(page);
memset(kaddr + bh_offset(bh) + ofs, 0,
bh->b_size - ofs);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
+ kunmap_atomic(kaddr);
local_irq_restore(flags);
}
} else {
@@ -147,11 +147,11 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
/* Should have been verified before we got here... */
BUG_ON(!recs);
local_irq_save(flags);
- kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ);
+ kaddr = kmap_atomic(page);
for (i = 0; i < recs; i++)
post_read_mst_fixup((NTFS_RECORD*)(kaddr +
i * rec_size), rec_size);
- kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
+ kunmap_atomic(kaddr);
local_irq_restore(flags);
flush_dcache_page(page);
if (likely(page_uptodate && !PageError(page)))
@@ -504,7 +504,7 @@ retry_readpage:
/* Race with shrinking truncate. */
attr_len = i_size;
}
- addr = kmap_atomic(page, KM_USER0);
+ addr = kmap_atomic(page);
/* Copy the data to the page. */
memcpy(addr, (u8*)ctx->attr +
le16_to_cpu(ctx->attr->data.resident.value_offset),
@@ -512,7 +512,7 @@ retry_readpage:
/* Zero the remainder of the page. */
memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
flush_dcache_page(page);
- kunmap_atomic(addr, KM_USER0);
+ kunmap_atomic(addr);
put_unm_err_out:
ntfs_attr_put_search_ctx(ctx);
unm_err_out:
@@ -746,14 +746,14 @@ lock_retry_remap:
unsigned long *bpos, *bend;
/* Check if the buffer is zero. */
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
bpos = (unsigned long *)(kaddr + bh_offset(bh));
bend = (unsigned long *)((u8*)bpos + blocksize);
do {
if (unlikely(*bpos))
break;
} while (likely(++bpos < bend));
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (bpos == bend) {
/*
* Buffer is zero and sparse, no need to write
@@ -1495,14 +1495,14 @@ retry_writepage:
/* Shrinking cannot fail. */
BUG_ON(err);
}
- addr = kmap_atomic(page, KM_USER0);
+ addr = kmap_atomic(page);
/* Copy the data from the page to the mft record. */
memcpy((u8*)ctx->attr +
le16_to_cpu(ctx->attr->data.resident.value_offset),
addr, attr_len);
/* Zero out of bounds area in the page cache page. */
memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
- kunmap_atomic(addr, KM_USER0);
+ kunmap_atomic(addr);
flush_dcache_page(page);
flush_dcache_mft_record_page(ctx->ntfs_ino);
/* We are done with the page. */
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index f14fde2..a27e3fe 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -1,7 +1,7 @@
/**
* attrib.c - NTFS attribute operations. Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2007 Anton Altaparmakov
+ * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
* Copyright (c) 2002 Richard Russon
*
* This program/include file is free software; you can redistribute it and/or
@@ -345,10 +345,10 @@ LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
unsigned long flags;
bool is_retry = false;
+ BUG_ON(!ni);
ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
ni->mft_no, (unsigned long long)vcn,
write_locked ? "write" : "read");
- BUG_ON(!ni);
BUG_ON(!NInoNonResident(ni));
BUG_ON(vcn < 0);
if (!ni->runlist.rl) {
@@ -469,9 +469,9 @@ runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
int err = 0;
bool is_retry = false;
+ BUG_ON(!ni);
ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
- BUG_ON(!ni);
BUG_ON(!NInoNonResident(ni));
BUG_ON(vcn < 0);
if (!ni->runlist.rl) {
@@ -1656,12 +1656,12 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
attr_size = le32_to_cpu(a->data.resident.value_length);
BUG_ON(attr_size != data_size);
if (page && !PageUptodate(page)) {
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(kaddr, (u8*)a +
le16_to_cpu(a->data.resident.value_offset),
attr_size);
memset(kaddr + attr_size, 0, PAGE_CACHE_SIZE - attr_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
flush_dcache_page(page);
SetPageUptodate(page);
}
@@ -1806,9 +1806,9 @@ undo_err_out:
sizeof(a->data.resident.reserved));
/* Copy the data from the page back to the attribute value. */
if (page) {
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy((u8*)a + mp_ofs, kaddr, attr_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
/* Setup the allocated size in the ntfs inode in case it changed. */
write_lock_irqsave(&ni->size_lock, flags);
@@ -2540,10 +2540,10 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
size = PAGE_CACHE_SIZE;
if (idx == end)
size = end_ofs;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr + start_ofs, val, size - start_ofs);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
set_page_dirty(page);
page_cache_release(page);
balance_dirty_pages_ratelimited(mapping);
@@ -2561,10 +2561,10 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
"page (index 0x%lx).", idx);
return -ENOMEM;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr, val, PAGE_CACHE_SIZE);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
/*
* If the page has buffers, mark them uptodate since buffer
* state and not page state is definitive in 2.6 kernels.
@@ -2598,10 +2598,10 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
"(error, index 0x%lx).", idx);
return PTR_ERR(page);
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr, val, end_ofs);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
set_page_dirty(page);
page_cache_release(page);
balance_dirty_pages_ratelimited(mapping);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index c587e2d..8639169 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -704,7 +704,7 @@ map_buffer_cached:
u8 *kaddr;
unsigned pofs;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
if (bh_pos < pos) {
pofs = bh_pos & ~PAGE_CACHE_MASK;
memset(kaddr + pofs, 0, pos - bh_pos);
@@ -713,7 +713,7 @@ map_buffer_cached:
pofs = end & ~PAGE_CACHE_MASK;
memset(kaddr + pofs, 0, bh_end - end);
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
flush_dcache_page(page);
}
continue;
@@ -1287,9 +1287,9 @@ static inline size_t ntfs_copy_from_user(struct page **pages,
len = PAGE_CACHE_SIZE - ofs;
if (len > bytes)
len = bytes;
- addr = kmap_atomic(*pages, KM_USER0);
+ addr = kmap_atomic(*pages);
left = __copy_from_user_inatomic(addr + ofs, buf, len);
- kunmap_atomic(addr, KM_USER0);
+ kunmap_atomic(addr);
if (unlikely(left)) {
/* Do it the slow way. */
addr = kmap(*pages);
@@ -1401,10 +1401,10 @@ static inline size_t ntfs_copy_from_user_iovec(struct page **pages,
len = PAGE_CACHE_SIZE - ofs;
if (len > bytes)
len = bytes;
- addr = kmap_atomic(*pages, KM_USER0);
+ addr = kmap_atomic(*pages);
copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
*iov, *iov_ofs, len);
- kunmap_atomic(addr, KM_USER0);
+ kunmap_atomic(addr);
if (unlikely(copied != len)) {
/* Do it the slow way. */
addr = kmap(*pages);
@@ -1691,7 +1691,7 @@ static int ntfs_commit_pages_after_write(struct page **pages,
BUG_ON(end > le32_to_cpu(a->length) -
le16_to_cpu(a->data.resident.value_offset));
kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
/* Copy the received data from the page to the mft record. */
memcpy(kattr + pos, kaddr + pos, bytes);
/* Update the attribute length if necessary. */
@@ -1713,7 +1713,7 @@ static int ntfs_commit_pages_after_write(struct page **pages,
flush_dcache_page(page);
SetPageUptodate(page);
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
/* Update initialized_size/i_size if necessary. */
read_lock_irqsave(&ni->size_lock, flags);
initialized_size = ni->initialized_size;
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index faece71..809c0e6 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -2008,14 +2008,14 @@ typedef struct {
*
* When a directory is small enough to fit inside the index root then this
* is the only attribute describing the directory. When the directory is too
- * large to fit in the index root, on the other hand, two aditional attributes
+ * large to fit in the index root, on the other hand, two additional attributes
* are present: an index allocation attribute, containing sub-nodes of the B+
* directory tree (see below), and a bitmap attribute, describing which virtual
* cluster numbers (vcns) in the index allocation attribute are in use by an
* index block.
*
* NOTE: The root directory (FILE_root) contains an entry for itself. Other
- * dircetories do not contain entries for themselves, though.
+ * directories do not contain entries for themselves, though.
*/
typedef struct {
ATTR_TYPE type; /* Type of the indexed attribute. Is
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 382857f..3014a36 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -1,7 +1,7 @@
/**
* mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.
+ * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
* Copyright (c) 2002 Richard Russon
*
* This program/include file is free software; you can redistribute it and/or
@@ -1367,7 +1367,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
ntfs_error(vol->sb, "Failed to merge runlists for mft "
"bitmap.");
if (ntfs_cluster_free_from_rl(vol, rl2)) {
- ntfs_error(vol->sb, "Failed to dealocate "
+ ntfs_error(vol->sb, "Failed to deallocate "
"allocated cluster.%s", es);
NVolSetErrors(vol);
}
@@ -1805,7 +1805,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
ntfs_error(vol->sb, "Failed to merge runlists for mft data "
"attribute.");
if (ntfs_cluster_free_from_rl(vol, rl2)) {
- ntfs_error(vol->sb, "Failed to dealocate clusters "
+ ntfs_error(vol->sb, "Failed to deallocate clusters "
"from the mft data attribute.%s", es);
NVolSetErrors(vol);
}
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 5a4a8af..b341492 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -1,7 +1,7 @@
/*
* super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.
+ * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
* Copyright (c) 2001,2002 Richard Russon
*
* This program/include file is free software; you can redistribute it and/or
@@ -1239,7 +1239,6 @@ static int check_windows_hibernation_status(ntfs_volume *vol)
{
MFT_REF mref;
struct inode *vi;
- ntfs_inode *ni;
struct page *page;
u32 *kaddr, *kend;
ntfs_name *name = NULL;
@@ -1290,7 +1289,6 @@ static int check_windows_hibernation_status(ntfs_volume *vol)
"is not the system volume.", i_size_read(vi));
goto iput_out;
}
- ni = NTFS_I(vi);
page = ntfs_map_page(vi->i_mapping, 0);
if (IS_ERR(page)) {
ntfs_error(vol->sb, "Failed to read from hiberfil.sys.");
@@ -2475,7 +2473,7 @@ static s64 get_nr_free_clusters(ntfs_volume *vol)
nr_free -= PAGE_CACHE_SIZE * 8;
continue;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
/*
* Subtract the number of set bits. If this
* is the last page and it is partial we don't really care as
@@ -2485,7 +2483,7 @@ static s64 get_nr_free_clusters(ntfs_volume *vol)
*/
nr_free -= bitmap_weight(kaddr,
PAGE_CACHE_SIZE * BITS_PER_BYTE);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
page_cache_release(page);
}
ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
@@ -2546,7 +2544,7 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
nr_free -= PAGE_CACHE_SIZE * 8;
continue;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
/*
* Subtract the number of set bits. If this
* is the last page and it is partial we don't really care as
@@ -2556,7 +2554,7 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
*/
nr_free -= bitmap_weight(kaddr,
PAGE_CACHE_SIZE * BITS_PER_BYTE);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
page_cache_release(page);
}
ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
@@ -2910,9 +2908,10 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
ntfs_error(sb, "Failed to load system files.");
goto unl_upcase_iput_tmp_ino_err_out_now;
}
- if ((sb->s_root = d_alloc_root(vol->root_ino))) {
- /* We grab a reference, simulating an ntfs_iget(). */
- ihold(vol->root_ino);
+
+ /* We grab a reference, simulating an ntfs_iget(). */
+ ihold(vol->root_ino);
+ if ((sb->s_root = d_make_root(vol->root_ino))) {
ntfs_debug("Exiting, status successful.");
/* Release the default upcase if it has no users. */
mutex_lock(&ntfs_lock);
@@ -3160,6 +3159,8 @@ static int __init init_ntfs_fs(void)
}
printk(KERN_CRIT "NTFS: Failed to register NTFS filesystem driver!\n");
+ /* Unregister the ntfs sysctls. */
+ ntfs_sysctl(0);
sysctl_err_out:
kmem_cache_destroy(ntfs_big_inode_cache);
big_inode_err_out:
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 78b68af..6577432 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -102,7 +102,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
* copy, the data is still good. */
if (buffer_jbd(buffer_cache_bh)
&& ocfs2_inode_is_new(inode)) {
- kaddr = kmap_atomic(bh_result->b_page, KM_USER0);
+ kaddr = kmap_atomic(bh_result->b_page);
if (!kaddr) {
mlog(ML_ERROR, "couldn't kmap!\n");
goto bail;
@@ -110,7 +110,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
memcpy(kaddr + (bh_result->b_size * iblock),
buffer_cache_bh->b_data,
bh_result->b_size);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
set_buffer_uptodate(bh_result);
}
brelse(buffer_cache_bh);
@@ -236,13 +236,13 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
return -EROFS;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
if (size)
memcpy(kaddr, di->id2.i_data.id_data, size);
/* Clear the remaining part of the page */
memset(kaddr + size, 0, PAGE_CACHE_SIZE - size);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
SetPageUptodate(page);
@@ -689,7 +689,7 @@ static void ocfs2_clear_page_regions(struct page *page,
ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end);
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
if (from || to) {
if (from > cluster_start)
@@ -700,7 +700,7 @@ static void ocfs2_clear_page_regions(struct page *page,
memset(kaddr + cluster_start, 0, cluster_end - cluster_start);
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
/*
@@ -1981,9 +1981,9 @@ static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
}
}
- kaddr = kmap_atomic(wc->w_target_page, KM_USER0);
+ kaddr = kmap_atomic(wc->w_target_page);
memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
trace_ocfs2_write_end_inline(
(unsigned long long)OCFS2_I(inode)->ip_blkno,
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index abfac0d..3b5825e 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -582,24 +582,14 @@ static int dlmfs_fill_super(struct super_block * sb,
void * data,
int silent)
{
- struct inode * inode;
- struct dentry * root;
-
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_magic = DLMFS_MAGIC;
sb->s_op = &dlmfs_ops;
- inode = dlmfs_get_root_inode(sb);
- if (!inode)
- return -ENOMEM;
-
- root = d_alloc_root(inode);
- if (!root) {
- iput(inode);
+ sb->s_root = d_make_root(dlmfs_get_root_inode(sb));
+ if (!sb->s_root)
return -ENOMEM;
- }
- sb->s_root = root;
return 0;
}
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index be24469..a9856e3 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -1053,7 +1053,7 @@ static int ocfs2_rename(struct inode *old_dir,
handle_t *handle = NULL;
struct buffer_head *old_dir_bh = NULL;
struct buffer_head *new_dir_bh = NULL;
- nlink_t old_dir_nlink = old_dir->i_nlink;
+ u32 old_dir_nlink = old_dir->i_nlink;
struct ocfs2_dinode *old_di;
struct ocfs2_dir_lookup_result old_inode_dot_dot_res = { NULL, };
struct ocfs2_dir_lookup_result target_lookup_res = { NULL, };
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 604e12c..68f4541 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1154,19 +1154,19 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
}
status = ocfs2_mount_volume(sb);
- if (osb->root_inode)
- inode = igrab(osb->root_inode);
-
if (status < 0)
goto read_super_error;
+ if (osb->root_inode)
+ inode = igrab(osb->root_inode);
+
if (!inode) {
status = -EIO;
mlog_errno(status);
goto read_super_error;
}
- root = d_alloc_root(inode);
+ root = d_make_root(inode);
if (!root) {
status = -ENOMEM;
mlog_errno(status);
@@ -1220,9 +1220,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
read_super_error:
brelse(bh);
- if (inode)
- iput(inode);
-
if (osb) {
atomic_set(&osb->vol_state, VOLUME_DISABLED);
wake_up(&osb->osb_mount_event);
@@ -1627,21 +1624,17 @@ static int __init ocfs2_init(void)
init_waitqueue_head(&ocfs2__ioend_wq[i]);
status = init_ocfs2_uptodate_cache();
- if (status < 0) {
- mlog_errno(status);
- goto leave;
- }
+ if (status < 0)
+ goto out1;
status = ocfs2_initialize_mem_caches();
- if (status < 0) {
- mlog_errno(status);
- goto leave;
- }
+ if (status < 0)
+ goto out2;
ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
if (!ocfs2_wq) {
status = -ENOMEM;
- goto leave;
+ goto out3;
}
ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
@@ -1653,17 +1646,23 @@ static int __init ocfs2_init(void)
ocfs2_set_locking_protocol();
status = register_quota_format(&ocfs2_quota_format);
-leave:
- if (status < 0) {
- ocfs2_free_mem_caches();
- exit_ocfs2_uptodate_cache();
- mlog_errno(status);
- }
+ if (status < 0)
+ goto out4;
+ status = register_filesystem(&ocfs2_fs_type);
+ if (!status)
+ return 0;
- if (status >= 0) {
- return register_filesystem(&ocfs2_fs_type);
- } else
- return -1;
+ unregister_quota_format(&ocfs2_quota_format);
+out4:
+ destroy_workqueue(ocfs2_wq);
+ debugfs_remove(ocfs2_debugfs_root);
+out3:
+ ocfs2_free_mem_caches();
+out2:
+ exit_ocfs2_uptodate_cache();
+out1:
+ mlog_errno(status);
+ return status;
}
static void __exit ocfs2_exit(void)
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 6065bb0..dbc8422 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -539,11 +539,9 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent)
goto out_brelse_bh2;
}
- sb->s_root = d_alloc_root(root);
- if (!sb->s_root) {
- iput(root);
+ sb->s_root = d_make_root(root);
+ if (!sb->s_root)
goto out_brelse_bh2;
- }
printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name);
ret = 0;
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index a88c03b..bc49c97 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -408,13 +408,12 @@ static int openprom_fill_super(struct super_block *s, void *data, int silent)
oi->type = op_inode_node;
oi->u.node = of_find_node_by_path("/");
- s->s_root = d_alloc_root(root_inode);
+ s->s_root = d_make_root(root_inode);
if (!s->s_root)
goto out_no_root_dentry;
return 0;
out_no_root_dentry:
- iput(root_inode);
ret = -ENOMEM;
out_no_root:
printk("openprom_fill_super: get root inode failed\n");
diff --git a/fs/pipe.c b/fs/pipe.c
index a932ced..25feaa3 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -13,6 +13,7 @@
#include <linux/fs.h>
#include <linux/log2.h>
#include <linux/mount.h>
+#include <linux/magic.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
@@ -230,7 +231,7 @@ void *generic_pipe_buf_map(struct pipe_inode_info *pipe,
{
if (atomic) {
buf->flags |= PIPE_BUF_FLAG_ATOMIC;
- return kmap_atomic(buf->page, KM_USER0);
+ return kmap_atomic(buf->page);
}
return kmap(buf->page);
@@ -251,7 +252,7 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *pipe,
{
if (buf->flags & PIPE_BUF_FLAG_ATOMIC) {
buf->flags &= ~PIPE_BUF_FLAG_ATOMIC;
- kunmap_atomic(map_data, KM_USER0);
+ kunmap_atomic(map_data);
} else
kunmap(buf->page);
}
@@ -565,14 +566,14 @@ redo1:
iov_fault_in_pages_read(iov, chars);
redo2:
if (atomic)
- src = kmap_atomic(page, KM_USER0);
+ src = kmap_atomic(page);
else
src = kmap(page);
error = pipe_iov_copy_from_user(src, iov, chars,
atomic);
if (atomic)
- kunmap_atomic(src, KM_USER0);
+ kunmap_atomic(src);
else
kunmap(page);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index cea4623..5e325a4 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -18,7 +18,7 @@
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/posix_acl.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/errno.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index c602b8d..fbb53c2 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -462,59 +462,56 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
/* convert nsec -> ticks */
start_time = nsec_to_clock_t(start_time);
- seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
-%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
-%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld %lu %lu %lu\n",
- pid_nr_ns(pid, ns),
- tcomm,
- state,
- ppid,
- pgid,
- sid,
- tty_nr,
- tty_pgrp,
- task->flags,
- min_flt,
- cmin_flt,
- maj_flt,
- cmaj_flt,
- cputime_to_clock_t(utime),
- cputime_to_clock_t(stime),
- cputime_to_clock_t(cutime),
- cputime_to_clock_t(cstime),
- priority,
- nice,
- num_threads,
- start_time,
- vsize,
- mm ? get_mm_rss(mm) : 0,
- rsslim,
- mm ? (permitted ? mm->start_code : 1) : 0,
- mm ? (permitted ? mm->end_code : 1) : 0,
- (permitted && mm) ? mm->start_stack : 0,
- esp,
- eip,
- /* The signal information here is obsolete.
- * It must be decimal for Linux 2.0 compatibility.
- * Use /proc/#/status for real-time signals.
- */
- task->pending.signal.sig[0] & 0x7fffffffUL,
- task->blocked.sig[0] & 0x7fffffffUL,
- sigign .sig[0] & 0x7fffffffUL,
- sigcatch .sig[0] & 0x7fffffffUL,
- wchan,
- 0UL,
- 0UL,
- task->exit_signal,
- task_cpu(task),
- task->rt_priority,
- task->policy,
- (unsigned long long)delayacct_blkio_ticks(task),
- cputime_to_clock_t(gtime),
- cputime_to_clock_t(cgtime),
- (mm && permitted) ? mm->start_data : 0,
- (mm && permitted) ? mm->end_data : 0,
- (mm && permitted) ? mm->start_brk : 0);
+ seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state);
+ seq_put_decimal_ll(m, ' ', ppid);
+ seq_put_decimal_ll(m, ' ', pgid);
+ seq_put_decimal_ll(m, ' ', sid);
+ seq_put_decimal_ll(m, ' ', tty_nr);
+ seq_put_decimal_ll(m, ' ', tty_pgrp);
+ seq_put_decimal_ull(m, ' ', task->flags);
+ seq_put_decimal_ull(m, ' ', min_flt);
+ seq_put_decimal_ull(m, ' ', cmin_flt);
+ seq_put_decimal_ull(m, ' ', maj_flt);
+ seq_put_decimal_ull(m, ' ', cmaj_flt);
+ seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime));
+ seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime));
+ seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime));
+ seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime));
+ seq_put_decimal_ll(m, ' ', priority);
+ seq_put_decimal_ll(m, ' ', nice);
+ seq_put_decimal_ll(m, ' ', num_threads);
+ seq_put_decimal_ull(m, ' ', 0);
+ seq_put_decimal_ull(m, ' ', start_time);
+ seq_put_decimal_ull(m, ' ', vsize);
+ seq_put_decimal_ll(m, ' ', mm ? get_mm_rss(mm) : 0);
+ seq_put_decimal_ull(m, ' ', rsslim);
+ seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0);
+ seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0);
+ seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0);
+ seq_put_decimal_ull(m, ' ', esp);
+ seq_put_decimal_ull(m, ' ', eip);
+ /* The signal information here is obsolete.
+ * It must be decimal for Linux 2.0 compatibility.
+ * Use /proc/#/status for real-time signals.
+ */
+ seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL);
+ seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL);
+ seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL);
+ seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL);
+ seq_put_decimal_ull(m, ' ', wchan);
+ seq_put_decimal_ull(m, ' ', 0);
+ seq_put_decimal_ull(m, ' ', 0);
+ seq_put_decimal_ll(m, ' ', task->exit_signal);
+ seq_put_decimal_ll(m, ' ', task_cpu(task));
+ seq_put_decimal_ull(m, ' ', task->rt_priority);
+ seq_put_decimal_ull(m, ' ', task->policy);
+ seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task));
+ seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime));
+ seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime));
+ seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_data : 0);
+ seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->end_data : 0);
+ seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_brk : 0);
+ seq_putc(m, '\n');
if (mm)
mmput(mm);
return 0;
@@ -542,8 +539,20 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
size = task_statm(mm, &shared, &text, &data, &resident);
mmput(mm);
}
- seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
- size, resident, shared, text, data);
+ /*
+ * For quick read, open code by putting numbers directly
+ * expected format is
+ * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
+ * size, resident, shared, text, data);
+ */
+ seq_put_decimal_ull(m, 0, size);
+ seq_put_decimal_ull(m, ' ', resident);
+ seq_put_decimal_ull(m, ' ', shared);
+ seq_put_decimal_ull(m, ' ', text);
+ seq_put_decimal_ull(m, ' ', 0);
+ seq_put_decimal_ull(m, ' ', text);
+ seq_put_decimal_ull(m, ' ', 0);
+ seq_putc(m, '\n');
return 0;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9cde9edf..3b42c14 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -198,26 +198,6 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
return result;
}
-static struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
-{
- struct mm_struct *mm;
- int err;
-
- err = mutex_lock_killable(&task->signal->cred_guard_mutex);
- if (err)
- return ERR_PTR(err);
-
- mm = get_task_mm(task);
- if (mm && mm != current->mm &&
- !ptrace_may_access(task, mode)) {
- mmput(mm);
- mm = ERR_PTR(-EACCES);
- }
- mutex_unlock(&task->signal->cred_guard_mutex);
-
- return mm;
-}
-
struct mm_struct *mm_for_maps(struct task_struct *task)
{
return mm_access(task, PTRACE_MODE_READ);
@@ -711,6 +691,13 @@ static int mem_open(struct inode* inode, struct file* file)
if (IS_ERR(mm))
return PTR_ERR(mm);
+ if (mm) {
+ /* ensure this mm_struct can't be freed */
+ atomic_inc(&mm->mm_count);
+ /* but do not pin its memory */
+ mmput(mm);
+ }
+
/* OK to pass negative loff_t, we can catch out-of-range */
file->f_mode |= FMODE_UNSIGNED_OFFSET;
file->private_data = mm;
@@ -718,57 +705,13 @@ static int mem_open(struct inode* inode, struct file* file)
return 0;
}
-static ssize_t mem_read(struct file * file, char __user * buf,
- size_t count, loff_t *ppos)
+static ssize_t mem_rw(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos, int write)
{
- int ret;
- char *page;
- unsigned long src = *ppos;
struct mm_struct *mm = file->private_data;
-
- if (!mm)
- return 0;
-
- page = (char *)__get_free_page(GFP_TEMPORARY);
- if (!page)
- return -ENOMEM;
-
- ret = 0;
-
- while (count > 0) {
- int this_len, retval;
-
- this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
- retval = access_remote_vm(mm, src, page, this_len, 0);
- if (!retval) {
- if (!ret)
- ret = -EIO;
- break;
- }
-
- if (copy_to_user(buf, page, retval)) {
- ret = -EFAULT;
- break;
- }
-
- ret += retval;
- src += retval;
- buf += retval;
- count -= retval;
- }
- *ppos = src;
-
- free_page((unsigned long) page);
- return ret;
-}
-
-static ssize_t mem_write(struct file * file, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- int copied;
+ unsigned long addr = *ppos;
+ ssize_t copied;
char *page;
- unsigned long dst = *ppos;
- struct mm_struct *mm = file->private_data;
if (!mm)
return 0;
@@ -778,31 +721,54 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
return -ENOMEM;
copied = 0;
+ if (!atomic_inc_not_zero(&mm->mm_users))
+ goto free;
+
while (count > 0) {
- int this_len, retval;
+ int this_len = min_t(int, count, PAGE_SIZE);
- this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
- if (copy_from_user(page, buf, this_len)) {
+ if (write && copy_from_user(page, buf, this_len)) {
copied = -EFAULT;
break;
}
- retval = access_remote_vm(mm, dst, page, this_len, 1);
- if (!retval) {
+
+ this_len = access_remote_vm(mm, addr, page, this_len, write);
+ if (!this_len) {
if (!copied)
copied = -EIO;
break;
}
- copied += retval;
- buf += retval;
- dst += retval;
- count -= retval;
+
+ if (!write && copy_to_user(buf, page, this_len)) {
+ copied = -EFAULT;
+ break;
+ }
+
+ buf += this_len;
+ addr += this_len;
+ copied += this_len;
+ count -= this_len;
}
- *ppos = dst;
+ *ppos = addr;
+ mmput(mm);
+free:
free_page((unsigned long) page);
return copied;
}
+static ssize_t mem_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return mem_rw(file, buf, count, ppos, 0);
+}
+
+static ssize_t mem_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return mem_rw(file, (char __user*)buf, count, ppos, 1);
+}
+
loff_t mem_lseek(struct file *file, loff_t offset, int orig)
{
switch (orig) {
@@ -822,8 +788,8 @@ loff_t mem_lseek(struct file *file, loff_t offset, int orig)
static int mem_release(struct inode *inode, struct file *file)
{
struct mm_struct *mm = file->private_data;
-
- mmput(mm);
+ if (mm)
+ mmdrop(mm);
return 0;
}
@@ -1344,8 +1310,7 @@ sched_autogroup_write(struct file *file, const char __user *buf,
if (!p)
return -ESRCH;
- err = nice;
- err = proc_sched_autogroup_set_nice(p, &err);
+ err = proc_sched_autogroup_set_nice(p, nice);
if (err)
count = err;
@@ -3024,9 +2989,9 @@ static const struct pid_entry tgid_base_stuff[] = {
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tgid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
- REG("maps", S_IRUGO, proc_maps_operations),
+ REG("maps", S_IRUGO, proc_pid_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+ REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations),
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
@@ -3037,7 +3002,7 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("mountstats", S_IRUSR, proc_mountstats_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
- REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("smaps", S_IRUGO, proc_pid_smaps_operations),
REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
@@ -3383,9 +3348,9 @@ static const struct pid_entry tid_base_stuff[] = {
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
- REG("maps", S_IRUGO, proc_maps_operations),
+ REG("maps", S_IRUGO, proc_tid_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+ REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
@@ -3395,7 +3360,7 @@ static const struct pid_entry tid_base_stuff[] = {
REG("mountinfo", S_IRUGO, proc_mountinfo_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
- REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("smaps", S_IRUGO, proc_tid_smaps_operations),
REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 84fd323..8461a7b 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -486,8 +486,6 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
int proc_fill_super(struct super_block *s)
{
- struct inode * root_inode;
-
s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
@@ -496,19 +494,11 @@ int proc_fill_super(struct super_block *s)
s->s_time_gran = 1;
pde_get(&proc_root);
- root_inode = proc_get_inode(s, &proc_root);
- if (!root_inode)
- goto out_no_root;
- root_inode->i_uid = 0;
- root_inode->i_gid = 0;
- s->s_root = d_alloc_root(root_inode);
- if (!s->s_root)
- goto out_no_root;
- return 0;
+ s->s_root = d_make_root(proc_get_inode(s, &proc_root));
+ if (s->s_root)
+ return 0;
-out_no_root:
printk("proc_read_super: get root inode failed\n");
- iput(root_inode);
pde_put(&proc_root);
return -ENOMEM;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 2925775..5f79bb8 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -10,12 +10,15 @@
*/
#include <linux/proc_fs.h>
+struct ctl_table_header;
extern struct proc_dir_entry proc_root;
#ifdef CONFIG_PROC_SYSCTL
extern int proc_sys_init(void);
+extern void sysctl_head_put(struct ctl_table_header *head);
#else
static inline void proc_sys_init(void) { }
+static inline void sysctl_head_put(struct ctl_table_header *head) { }
#endif
#ifdef CONFIG_NET
extern int proc_net_init(void);
@@ -53,9 +56,12 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task);
extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
-extern const struct file_operations proc_maps_operations;
-extern const struct file_operations proc_numa_maps_operations;
-extern const struct file_operations proc_smaps_operations;
+extern const struct file_operations proc_pid_maps_operations;
+extern const struct file_operations proc_tid_maps_operations;
+extern const struct file_operations proc_pid_numa_maps_operations;
+extern const struct file_operations proc_tid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_tid_smaps_operations;
extern const struct file_operations proc_clear_refs_operations;
extern const struct file_operations proc_pagemap_operations;
extern const struct file_operations proc_net_operations;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index d245cb2..86c67ee 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -157,7 +157,8 @@ static int kcore_update_ram(void)
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/* calculate vmemmap's address from given system ram pfn and register it */
-int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
{
unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT;
unsigned long nr_pages = ent->size >> PAGE_SHIFT;
@@ -189,7 +190,8 @@ int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
}
#else
-int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
{
return 1;
}
@@ -513,7 +515,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
n = copy_to_user(buffer, (char *)start, tsz);
/*
- * We cannot distingush between fault on source
+ * We cannot distinguish between fault on source
* and fault on destination. When this happens
* we clear too and hope it will trigger the
* EFAULT again.
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 27da860..3551f1f 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -53,7 +53,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
ei->ns_ops = ns_ops;
ei->ns = ns;
- dentry->d_op = &pid_dentry_operations;
+ d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (pid_revalidate(dentry, NULL))
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 6d8e6a9..7fcd0d6 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -115,6 +115,8 @@ u64 stable_page_flags(struct page *page)
u |= 1 << KPF_COMPOUND_TAIL;
if (PageHuge(page))
u |= 1 << KPF_HUGE;
+ else if (PageTransCompound(page))
+ u |= 1 << KPF_THP;
/*
* Caveats on high order pages: page->_count will only be set
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index a6b6217..21d836f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -6,7 +6,10 @@
#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
+#include <linux/sched.h>
#include <linux/namei.h>
+#include <linux/mm.h>
+#include <linux/module.h>
#include "internal.h"
static const struct dentry_operations proc_sys_dentry_operations;
@@ -24,6 +27,371 @@ void proc_sys_poll_notify(struct ctl_table_poll *poll)
wake_up_interruptible(&poll->wait);
}
+static struct ctl_table root_table[] = {
+ {
+ .procname = "",
+ .mode = S_IFDIR|S_IRUGO|S_IXUGO,
+ },
+ { }
+};
+static struct ctl_table_root sysctl_table_root = {
+ .default_set.dir.header = {
+ {{.count = 1,
+ .nreg = 1,
+ .ctl_table = root_table }},
+ .ctl_table_arg = root_table,
+ .root = &sysctl_table_root,
+ .set = &sysctl_table_root.default_set,
+ },
+};
+
+static DEFINE_SPINLOCK(sysctl_lock);
+
+static void drop_sysctl_table(struct ctl_table_header *header);
+static int sysctl_follow_link(struct ctl_table_header **phead,
+ struct ctl_table **pentry, struct nsproxy *namespaces);
+static int insert_links(struct ctl_table_header *head);
+static void put_links(struct ctl_table_header *header);
+
+static void sysctl_print_dir(struct ctl_dir *dir)
+{
+ if (dir->header.parent)
+ sysctl_print_dir(dir->header.parent);
+ printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
+}
+
+static int namecmp(const char *name1, int len1, const char *name2, int len2)
+{
+ int minlen;
+ int cmp;
+
+ minlen = len1;
+ if (minlen > len2)
+ minlen = len2;
+
+ cmp = memcmp(name1, name2, minlen);
+ if (cmp == 0)
+ cmp = len1 - len2;
+ return cmp;
+}
+
+/* Called under sysctl_lock */
+static struct ctl_table *find_entry(struct ctl_table_header **phead,
+ struct ctl_dir *dir, const char *name, int namelen)
+{
+ struct ctl_table_header *head;
+ struct ctl_table *entry;
+ struct rb_node *node = dir->root.rb_node;
+
+ while (node)
+ {
+ struct ctl_node *ctl_node;
+ const char *procname;
+ int cmp;
+
+ ctl_node = rb_entry(node, struct ctl_node, node);
+ head = ctl_node->header;
+ entry = &head->ctl_table[ctl_node - head->node];
+ procname = entry->procname;
+
+ cmp = namecmp(name, namelen, procname, strlen(procname));
+ if (cmp < 0)
+ node = node->rb_left;
+ else if (cmp > 0)
+ node = node->rb_right;
+ else {
+ *phead = head;
+ return entry;
+ }
+ }
+ return NULL;
+}
+
+static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+ struct rb_node *node = &head->node[entry - head->ctl_table].node;
+ struct rb_node **p = &head->parent->root.rb_node;
+ struct rb_node *parent = NULL;
+ const char *name = entry->procname;
+ int namelen = strlen(name);
+
+ while (*p) {
+ struct ctl_table_header *parent_head;
+ struct ctl_table *parent_entry;
+ struct ctl_node *parent_node;
+ const char *parent_name;
+ int cmp;
+
+ parent = *p;
+ parent_node = rb_entry(parent, struct ctl_node, node);
+ parent_head = parent_node->header;
+ parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
+ parent_name = parent_entry->procname;
+
+ cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
+ if (cmp < 0)
+ p = &(*p)->rb_left;
+ else if (cmp > 0)
+ p = &(*p)->rb_right;
+ else {
+ printk(KERN_ERR "sysctl duplicate entry: ");
+ sysctl_print_dir(head->parent);
+ printk(KERN_CONT "/%s\n", entry->procname);
+ return -EEXIST;
+ }
+ }
+
+ rb_link_node(node, parent, p);
+ return 0;
+}
+
+static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+ struct rb_node *node = &head->node[entry - head->ctl_table].node;
+
+ rb_erase(node, &head->parent->root);
+}
+
+static void init_header(struct ctl_table_header *head,
+ struct ctl_table_root *root, struct ctl_table_set *set,
+ struct ctl_node *node, struct ctl_table *table)
+{
+ head->ctl_table = table;
+ head->ctl_table_arg = table;
+ head->used = 0;
+ head->count = 1;
+ head->nreg = 1;
+ head->unregistering = NULL;
+ head->root = root;
+ head->set = set;
+ head->parent = NULL;
+ head->node = node;
+ if (node) {
+ struct ctl_table *entry;
+ for (entry = table; entry->procname; entry++, node++) {
+ rb_init_node(&node->node);
+ node->header = head;
+ }
+ }
+}
+
+static void erase_header(struct ctl_table_header *head)
+{
+ struct ctl_table *entry;
+ for (entry = head->ctl_table; entry->procname; entry++)
+ erase_entry(head, entry);
+}
+
+static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
+{
+ struct ctl_table *entry;
+ int err;
+
+ dir->header.nreg++;
+ header->parent = dir;
+ err = insert_links(header);
+ if (err)
+ goto fail_links;
+ for (entry = header->ctl_table; entry->procname; entry++) {
+ err = insert_entry(header, entry);
+ if (err)
+ goto fail;
+ }
+ return 0;
+fail:
+ erase_header(header);
+ put_links(header);
+fail_links:
+ header->parent = NULL;
+ drop_sysctl_table(&dir->header);
+ return err;
+}
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+ if (unlikely(p->unregistering))
+ return 0;
+ p->used++;
+ return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+ if (!--p->used)
+ if (unlikely(p->unregistering))
+ complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+ /*
+ * if p->used is 0, nobody will ever touch that entry again;
+ * we'll eliminate all paths to it before dropping sysctl_lock
+ */
+ if (unlikely(p->used)) {
+ struct completion wait;
+ init_completion(&wait);
+ p->unregistering = &wait;
+ spin_unlock(&sysctl_lock);
+ wait_for_completion(&wait);
+ spin_lock(&sysctl_lock);
+ } else {
+ /* anything non-NULL; we'll never dereference it */
+ p->unregistering = ERR_PTR(-EINVAL);
+ }
+ /*
+ * do not remove from the list until nobody holds it; walking the
+ * list in do_sysctl() relies on that.
+ */
+ erase_header(p);
+}
+
+static void sysctl_head_get(struct ctl_table_header *head)
+{
+ spin_lock(&sysctl_lock);
+ head->count++;
+ spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+ spin_lock(&sysctl_lock);
+ if (!--head->count)
+ kfree_rcu(head, rcu);
+ spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+ if (!head)
+ BUG();
+ spin_lock(&sysctl_lock);
+ if (!use_table(head))
+ head = ERR_PTR(-ENOENT);
+ spin_unlock(&sysctl_lock);
+ return head;
+}
+
+static void sysctl_head_finish(struct ctl_table_header *head)
+{
+ if (!head)
+ return;
+ spin_lock(&sysctl_lock);
+ unuse_table(head);
+ spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+ struct ctl_table_set *set = &root->default_set;
+ if (root->lookup)
+ set = root->lookup(root, namespaces);
+ return set;
+}
+
+static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
+ struct ctl_dir *dir,
+ const char *name, int namelen)
+{
+ struct ctl_table_header *head;
+ struct ctl_table *entry;
+
+ spin_lock(&sysctl_lock);
+ entry = find_entry(&head, dir, name, namelen);
+ if (entry && use_table(head))
+ *phead = head;
+ else
+ entry = NULL;
+ spin_unlock(&sysctl_lock);
+ return entry;
+}
+
+static struct ctl_node *first_usable_entry(struct rb_node *node)
+{
+ struct ctl_node *ctl_node;
+
+ for (;node; node = rb_next(node)) {
+ ctl_node = rb_entry(node, struct ctl_node, node);
+ if (use_table(ctl_node->header))
+ return ctl_node;
+ }
+ return NULL;
+}
+
+static void first_entry(struct ctl_dir *dir,
+ struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+ struct ctl_table_header *head = NULL;
+ struct ctl_table *entry = NULL;
+ struct ctl_node *ctl_node;
+
+ spin_lock(&sysctl_lock);
+ ctl_node = first_usable_entry(rb_first(&dir->root));
+ spin_unlock(&sysctl_lock);
+ if (ctl_node) {
+ head = ctl_node->header;
+ entry = &head->ctl_table[ctl_node - head->node];
+ }
+ *phead = head;
+ *pentry = entry;
+}
+
+static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+ struct ctl_table_header *head = *phead;
+ struct ctl_table *entry = *pentry;
+ struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
+
+ spin_lock(&sysctl_lock);
+ unuse_table(head);
+
+ ctl_node = first_usable_entry(rb_next(&ctl_node->node));
+ spin_unlock(&sysctl_lock);
+ head = NULL;
+ if (ctl_node) {
+ head = ctl_node->header;
+ entry = &head->ctl_table[ctl_node - head->node];
+ }
+ *phead = head;
+ *pentry = entry;
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+}
+
+/*
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
+ * some sysctl variables are readonly even to root.
+ */
+
+static int test_perm(int mode, int op)
+{
+ if (!current_euid())
+ mode >>= 6;
+ else if (in_egroup_p(0))
+ mode >>= 3;
+ if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
+ return 0;
+ return -EACCES;
+}
+
+static int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
+{
+ int mode;
+
+ if (root->permissions)
+ mode = root->permissions(root, current->nsproxy, table);
+ else
+ mode = table->mode;
+
+ return test_perm(mode, op);
+}
+
static struct inode *proc_sys_make_inode(struct super_block *sb,
struct ctl_table_header *head, struct ctl_table *table)
{
@@ -43,13 +411,12 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_mode = table->mode;
- if (!table->child) {
+ if (!S_ISDIR(table->mode)) {
inode->i_mode |= S_IFREG;
inode->i_op = &proc_sys_inode_operations;
inode->i_fop = &proc_sys_file_operations;
} else {
inode->i_mode |= S_IFDIR;
- clear_nlink(inode);
inode->i_op = &proc_sys_dir_operations;
inode->i_fop = &proc_sys_dir_file_operations;
}
@@ -57,70 +424,42 @@ out:
return inode;
}
-static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
-{
- int len;
- for ( ; p->procname; p++) {
-
- if (!p->procname)
- continue;
-
- len = strlen(p->procname);
- if (len != name->len)
- continue;
-
- if (memcmp(p->procname, name->name, len) != 0)
- continue;
-
- /* I have a match */
- return p;
- }
- return NULL;
-}
-
static struct ctl_table_header *grab_header(struct inode *inode)
{
- if (PROC_I(inode)->sysctl)
- return sysctl_head_grab(PROC_I(inode)->sysctl);
- else
- return sysctl_head_next(NULL);
+ struct ctl_table_header *head = PROC_I(inode)->sysctl;
+ if (!head)
+ head = &sysctl_table_root.default_set.dir.header;
+ return sysctl_head_grab(head);
}
static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct ctl_table_header *head = grab_header(dir);
- struct ctl_table *table = PROC_I(dir)->sysctl_entry;
struct ctl_table_header *h = NULL;
struct qstr *name = &dentry->d_name;
struct ctl_table *p;
struct inode *inode;
struct dentry *err = ERR_PTR(-ENOENT);
+ struct ctl_dir *ctl_dir;
+ int ret;
if (IS_ERR(head))
return ERR_CAST(head);
- if (table && !table->child) {
- WARN_ON(1);
- goto out;
- }
-
- table = table ? table->child : head->ctl_table;
-
- p = find_in_table(table, name);
- if (!p) {
- for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
- if (h->attached_to != table)
- continue;
- p = find_in_table(h->attached_by, name);
- if (p)
- break;
- }
- }
+ ctl_dir = container_of(head, struct ctl_dir, header);
+ p = lookup_entry(&h, ctl_dir, name->name, name->len);
if (!p)
goto out;
+ if (S_ISLNK(p->mode)) {
+ ret = sysctl_follow_link(&h, &p, current->nsproxy);
+ err = ERR_PTR(ret);
+ if (ret)
+ goto out;
+ }
+
err = ERR_PTR(-ENOMEM);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
if (h)
@@ -188,20 +527,32 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
static int proc_sys_open(struct inode *inode, struct file *filp)
{
+ struct ctl_table_header *head = grab_header(inode);
struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+ /* sysctl was unregistered */
+ if (IS_ERR(head))
+ return PTR_ERR(head);
+
if (table->poll)
filp->private_data = proc_sys_poll_event(table->poll);
+ sysctl_head_finish(head);
+
return 0;
}
static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
{
struct inode *inode = filp->f_path.dentry->d_inode;
+ struct ctl_table_header *head = grab_header(inode);
struct ctl_table *table = PROC_I(inode)->sysctl_entry;
- unsigned long event = (unsigned long)filp->private_data;
unsigned int ret = DEFAULT_POLLMASK;
+ unsigned long event;
+
+ /* sysctl was unregistered */
+ if (IS_ERR(head))
+ return POLLERR | POLLHUP;
if (!table->proc_handler)
goto out;
@@ -209,6 +560,7 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
if (!table->poll)
goto out;
+ event = (unsigned long)filp->private_data;
poll_wait(filp, &table->poll->wait, wait);
if (event != atomic_read(&table->poll->event)) {
@@ -217,6 +569,8 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
}
out:
+ sysctl_head_finish(head);
+
return ret;
}
@@ -258,28 +612,45 @@ static int proc_sys_fill_cache(struct file *filp, void *dirent,
return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
}
+static int proc_sys_link_fill_cache(struct file *filp, void *dirent,
+ filldir_t filldir,
+ struct ctl_table_header *head,
+ struct ctl_table *table)
+{
+ int err, ret = 0;
+ head = sysctl_head_grab(head);
+
+ if (S_ISLNK(table->mode)) {
+ /* It is not an error if we can not follow the link ignore it */
+ err = sysctl_follow_link(&head, &table, current->nsproxy);
+ if (err)
+ goto out;
+ }
+
+ ret = proc_sys_fill_cache(filp, dirent, filldir, head, table);
+out:
+ sysctl_head_finish(head);
+ return ret;
+}
+
static int scan(struct ctl_table_header *head, ctl_table *table,
unsigned long *pos, struct file *file,
void *dirent, filldir_t filldir)
{
+ int res;
- for (; table->procname; table++, (*pos)++) {
- int res;
-
- /* Can't do anything without a proc name */
- if (!table->procname)
- continue;
-
- if (*pos < file->f_pos)
- continue;
+ if ((*pos)++ < file->f_pos)
+ return 0;
+ if (unlikely(S_ISLNK(table->mode)))
+ res = proc_sys_link_fill_cache(file, dirent, filldir, head, table);
+ else
res = proc_sys_fill_cache(file, dirent, filldir, head, table);
- if (res)
- return res;
- file->f_pos = *pos + 1;
- }
- return 0;
+ if (res == 0)
+ file->f_pos = *pos;
+
+ return res;
}
static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
@@ -287,20 +658,16 @@ static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct ctl_table_header *head = grab_header(inode);
- struct ctl_table *table = PROC_I(inode)->sysctl_entry;
struct ctl_table_header *h = NULL;
+ struct ctl_table *entry;
+ struct ctl_dir *ctl_dir;
unsigned long pos;
int ret = -EINVAL;
if (IS_ERR(head))
return PTR_ERR(head);
- if (table && !table->child) {
- WARN_ON(1);
- goto out;
- }
-
- table = table ? table->child : head->ctl_table;
+ ctl_dir = container_of(head, struct ctl_dir, header);
ret = 0;
/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
@@ -318,14 +685,8 @@ static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
}
pos = 2;
- ret = scan(head, table, &pos, filp, dirent, filldir);
- if (ret)
- goto out;
-
- for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
- if (h->attached_to != table)
- continue;
- ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
+ for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
+ ret = scan(h, entry, &pos, filp, dirent, filldir);
if (ret) {
sysctl_head_finish(h);
break;
@@ -445,6 +806,21 @@ static int proc_sys_delete(const struct dentry *dentry)
return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
}
+static int sysctl_is_seen(struct ctl_table_header *p)
+{
+ struct ctl_table_set *set = p->set;
+ int res;
+ spin_lock(&sysctl_lock);
+ if (p->unregistering)
+ res = 0;
+ else if (!set->is_seen)
+ res = 1;
+ else
+ res = set->is_seen(set);
+ spin_unlock(&sysctl_lock);
+ return res;
+}
+
static int proc_sys_compare(const struct dentry *parent,
const struct inode *pinode,
const struct dentry *dentry, const struct inode *inode,
@@ -470,6 +846,753 @@ static const struct dentry_operations proc_sys_dentry_operations = {
.d_compare = proc_sys_compare,
};
+static struct ctl_dir *find_subdir(struct ctl_dir *dir,
+ const char *name, int namelen)
+{
+ struct ctl_table_header *head;
+ struct ctl_table *entry;
+
+ entry = find_entry(&head, dir, name, namelen);
+ if (!entry)
+ return ERR_PTR(-ENOENT);
+ if (!S_ISDIR(entry->mode))
+ return ERR_PTR(-ENOTDIR);
+ return container_of(head, struct ctl_dir, header);
+}
+
+static struct ctl_dir *new_dir(struct ctl_table_set *set,
+ const char *name, int namelen)
+{
+ struct ctl_table *table;
+ struct ctl_dir *new;
+ struct ctl_node *node;
+ char *new_name;
+
+ new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
+ sizeof(struct ctl_table)*2 + namelen + 1,
+ GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ node = (struct ctl_node *)(new + 1);
+ table = (struct ctl_table *)(node + 1);
+ new_name = (char *)(table + 2);
+ memcpy(new_name, name, namelen);
+ new_name[namelen] = '\0';
+ table[0].procname = new_name;
+ table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
+ init_header(&new->header, set->dir.header.root, set, node, table);
+
+ return new;
+}
+
+/**
+ * get_subdir - find or create a subdir with the specified name.
+ * @dir: Directory to create the subdirectory in
+ * @name: The name of the subdirectory to find or create
+ * @namelen: The length of name
+ *
+ * Takes a directory with an elevated reference count so we know that
+ * if we drop the lock the directory will not go away. Upon success
+ * the reference is moved from @dir to the returned subdirectory.
+ * Upon error an error code is returned and the reference on @dir is
+ * simply dropped.
+ */
+static struct ctl_dir *get_subdir(struct ctl_dir *dir,
+ const char *name, int namelen)
+{
+ struct ctl_table_set *set = dir->header.set;
+ struct ctl_dir *subdir, *new = NULL;
+ int err;
+
+ spin_lock(&sysctl_lock);
+ subdir = find_subdir(dir, name, namelen);
+ if (!IS_ERR(subdir))
+ goto found;
+ if (PTR_ERR(subdir) != -ENOENT)
+ goto failed;
+
+ spin_unlock(&sysctl_lock);
+ new = new_dir(set, name, namelen);
+ spin_lock(&sysctl_lock);
+ subdir = ERR_PTR(-ENOMEM);
+ if (!new)
+ goto failed;
+
+ /* Was the subdir added while we dropped the lock? */
+ subdir = find_subdir(dir, name, namelen);
+ if (!IS_ERR(subdir))
+ goto found;
+ if (PTR_ERR(subdir) != -ENOENT)
+ goto failed;
+
+ /* Nope. Use the our freshly made directory entry. */
+ err = insert_header(dir, &new->header);
+ subdir = ERR_PTR(err);
+ if (err)
+ goto failed;
+ subdir = new;
+found:
+ subdir->header.nreg++;
+failed:
+ if (unlikely(IS_ERR(subdir))) {
+ printk(KERN_ERR "sysctl could not get directory: ");
+ sysctl_print_dir(dir);
+ printk(KERN_CONT "/%*.*s %ld\n",
+ namelen, namelen, name, PTR_ERR(subdir));
+ }
+ drop_sysctl_table(&dir->header);
+ if (new)
+ drop_sysctl_table(&new->header);
+ spin_unlock(&sysctl_lock);
+ return subdir;
+}
+
+static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
+{
+ struct ctl_dir *parent;
+ const char *procname;
+ if (!dir->header.parent)
+ return &set->dir;
+ parent = xlate_dir(set, dir->header.parent);
+ if (IS_ERR(parent))
+ return parent;
+ procname = dir->header.ctl_table[0].procname;
+ return find_subdir(parent, procname, strlen(procname));
+}
+
+static int sysctl_follow_link(struct ctl_table_header **phead,
+ struct ctl_table **pentry, struct nsproxy *namespaces)
+{
+ struct ctl_table_header *head;
+ struct ctl_table_root *root;
+ struct ctl_table_set *set;
+ struct ctl_table *entry;
+ struct ctl_dir *dir;
+ int ret;
+
+ ret = 0;
+ spin_lock(&sysctl_lock);
+ root = (*pentry)->data;
+ set = lookup_header_set(root, namespaces);
+ dir = xlate_dir(set, (*phead)->parent);
+ if (IS_ERR(dir))
+ ret = PTR_ERR(dir);
+ else {
+ const char *procname = (*pentry)->procname;
+ head = NULL;
+ entry = find_entry(&head, dir, procname, strlen(procname));
+ ret = -ENOENT;
+ if (entry && use_table(head)) {
+ unuse_table(*phead);
+ *phead = head;
+ *pentry = entry;
+ ret = 0;
+ }
+ }
+
+ spin_unlock(&sysctl_lock);
+ return ret;
+}
+
+static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
+{
+ struct va_format vaf;
+ va_list args;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n",
+ path, table->procname, &vaf);
+
+ va_end(args);
+ return -EINVAL;
+}
+
+static int sysctl_check_table(const char *path, struct ctl_table *table)
+{
+ int err = 0;
+ for (; table->procname; table++) {
+ if (table->child)
+ err = sysctl_err(path, table, "Not a file");
+
+ if ((table->proc_handler == proc_dostring) ||
+ (table->proc_handler == proc_dointvec) ||
+ (table->proc_handler == proc_dointvec_minmax) ||
+ (table->proc_handler == proc_dointvec_jiffies) ||
+ (table->proc_handler == proc_dointvec_userhz_jiffies) ||
+ (table->proc_handler == proc_dointvec_ms_jiffies) ||
+ (table->proc_handler == proc_doulongvec_minmax) ||
+ (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
+ if (!table->data)
+ err = sysctl_err(path, table, "No data");
+ if (!table->maxlen)
+ err = sysctl_err(path, table, "No maxlen");
+ }
+ if (!table->proc_handler)
+ err = sysctl_err(path, table, "No proc_handler");
+
+ if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
+ err = sysctl_err(path, table, "bogus .mode 0%o",
+ table->mode);
+ }
+ return err;
+}
+
+static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table,
+ struct ctl_table_root *link_root)
+{
+ struct ctl_table *link_table, *entry, *link;
+ struct ctl_table_header *links;
+ struct ctl_node *node;
+ char *link_name;
+ int nr_entries, name_bytes;
+
+ name_bytes = 0;
+ nr_entries = 0;
+ for (entry = table; entry->procname; entry++) {
+ nr_entries++;
+ name_bytes += strlen(entry->procname) + 1;
+ }
+
+ links = kzalloc(sizeof(struct ctl_table_header) +
+ sizeof(struct ctl_node)*nr_entries +
+ sizeof(struct ctl_table)*(nr_entries + 1) +
+ name_bytes,
+ GFP_KERNEL);
+
+ if (!links)
+ return NULL;
+
+ node = (struct ctl_node *)(links + 1);
+ link_table = (struct ctl_table *)(node + nr_entries);
+ link_name = (char *)&link_table[nr_entries + 1];
+
+ for (link = link_table, entry = table; entry->procname; link++, entry++) {
+ int len = strlen(entry->procname) + 1;
+ memcpy(link_name, entry->procname, len);
+ link->procname = link_name;
+ link->mode = S_IFLNK|S_IRWXUGO;
+ link->data = link_root;
+ link_name += len;
+ }
+ init_header(links, dir->header.root, dir->header.set, node, link_table);
+ links->nreg = nr_entries;
+
+ return links;
+}
+
+static bool get_links(struct ctl_dir *dir,
+ struct ctl_table *table, struct ctl_table_root *link_root)
+{
+ struct ctl_table_header *head;
+ struct ctl_table *entry, *link;
+
+ /* Are there links available for every entry in table? */
+ for (entry = table; entry->procname; entry++) {
+ const char *procname = entry->procname;
+ link = find_entry(&head, dir, procname, strlen(procname));
+ if (!link)
+ return false;
+ if (S_ISDIR(link->mode) && S_ISDIR(entry->mode))
+ continue;
+ if (S_ISLNK(link->mode) && (link->data == link_root))
+ continue;
+ return false;
+ }
+
+ /* The checks passed. Increase the registration count on the links */
+ for (entry = table; entry->procname; entry++) {
+ const char *procname = entry->procname;
+ link = find_entry(&head, dir, procname, strlen(procname));
+ head->nreg++;
+ }
+ return true;
+}
+
+static int insert_links(struct ctl_table_header *head)
+{
+ struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+ struct ctl_dir *core_parent = NULL;
+ struct ctl_table_header *links;
+ int err;
+
+ if (head->set == root_set)
+ return 0;
+
+ core_parent = xlate_dir(root_set, head->parent);
+ if (IS_ERR(core_parent))
+ return 0;
+
+ if (get_links(core_parent, head->ctl_table, head->root))
+ return 0;
+
+ core_parent->header.nreg++;
+ spin_unlock(&sysctl_lock);
+
+ links = new_links(core_parent, head->ctl_table, head->root);
+
+ spin_lock(&sysctl_lock);
+ err = -ENOMEM;
+ if (!links)
+ goto out;
+
+ err = 0;
+ if (get_links(core_parent, head->ctl_table, head->root)) {
+ kfree(links);
+ goto out;
+ }
+
+ err = insert_header(core_parent, links);
+ if (err)
+ kfree(links);
+out:
+ drop_sysctl_table(&core_parent->header);
+ return err;
+}
+
+/**
+ * __register_sysctl_table - register a leaf sysctl table
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * The members of the &struct ctl_table structure are used as follows:
+ *
+ * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
+ * enter a sysctl file
+ *
+ * data - a pointer to data for use by proc_handler
+ *
+ * maxlen - the maximum size in bytes of the data
+ *
+ * mode - the file permissions for the /proc/sys file
+ *
+ * child - must be %NULL.
+ *
+ * proc_handler - the text handler routine (described below)
+ *
+ * extra1, extra2 - extra pointers usable by the proc handler routines
+ *
+ * Leaf nodes in the sysctl tree will be represented by a single file
+ * under /proc; non-leaf nodes will be represented by directories.
+ *
+ * There must be a proc_handler routine for any terminal nodes.
+ * Several default handlers are available to cover common cases -
+ *
+ * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
+ * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
+ * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
+ *
+ * It is the handler's job to read the input buffer from user memory
+ * and process it. The handler should return 0 on success.
+ *
+ * This routine returns %NULL on a failure to register, and a pointer
+ * to the table header on success.
+ */
+struct ctl_table_header *__register_sysctl_table(
+ struct ctl_table_set *set,
+ const char *path, struct ctl_table *table)
+{
+ struct ctl_table_root *root = set->dir.header.root;
+ struct ctl_table_header *header;
+ const char *name, *nextname;
+ struct ctl_dir *dir;
+ struct ctl_table *entry;
+ struct ctl_node *node;
+ int nr_entries = 0;
+
+ for (entry = table; entry->procname; entry++)
+ nr_entries++;
+
+ header = kzalloc(sizeof(struct ctl_table_header) +
+ sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
+ if (!header)
+ return NULL;
+
+ node = (struct ctl_node *)(header + 1);
+ init_header(header, root, set, node, table);
+ if (sysctl_check_table(path, table))
+ goto fail;
+
+ spin_lock(&sysctl_lock);
+ dir = &set->dir;
+ /* Reference moved down the diretory tree get_subdir */
+ dir->header.nreg++;
+ spin_unlock(&sysctl_lock);
+
+ /* Find the directory for the ctl_table */
+ for (name = path; name; name = nextname) {
+ int namelen;
+ nextname = strchr(name, '/');
+ if (nextname) {
+ namelen = nextname - name;
+ nextname++;
+ } else {
+ namelen = strlen(name);
+ }
+ if (namelen == 0)
+ continue;
+
+ dir = get_subdir(dir, name, namelen);
+ if (IS_ERR(dir))
+ goto fail;
+ }
+
+ spin_lock(&sysctl_lock);
+ if (insert_header(dir, header))
+ goto fail_put_dir_locked;
+
+ drop_sysctl_table(&dir->header);
+ spin_unlock(&sysctl_lock);
+
+ return header;
+
+fail_put_dir_locked:
+ drop_sysctl_table(&dir->header);
+ spin_unlock(&sysctl_lock);
+fail:
+ kfree(header);
+ dump_stack();
+ return NULL;
+}
+
+/**
+ * register_sysctl - register a sysctl table
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the table structure
+ *
+ * Register a sysctl table. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table)
+{
+ return __register_sysctl_table(&sysctl_table_root.default_set,
+ path, table);
+}
+EXPORT_SYMBOL(register_sysctl);
+
+static char *append_path(const char *path, char *pos, const char *name)
+{
+ int namelen;
+ namelen = strlen(name);
+ if (((pos - path) + namelen + 2) >= PATH_MAX)
+ return NULL;
+ memcpy(pos, name, namelen);
+ pos[namelen] = '/';
+ pos[namelen + 1] = '\0';
+ pos += namelen + 1;
+ return pos;
+}
+
+static int count_subheaders(struct ctl_table *table)
+{
+ int has_files = 0;
+ int nr_subheaders = 0;
+ struct ctl_table *entry;
+
+ /* special case: no directory and empty directory */
+ if (!table || !table->procname)
+ return 1;
+
+ for (entry = table; entry->procname; entry++) {
+ if (entry->child)
+ nr_subheaders += count_subheaders(entry->child);
+ else
+ has_files = 1;
+ }
+ return nr_subheaders + has_files;
+}
+
+static int register_leaf_sysctl_tables(const char *path, char *pos,
+ struct ctl_table_header ***subheader, struct ctl_table_set *set,
+ struct ctl_table *table)
+{
+ struct ctl_table *ctl_table_arg = NULL;
+ struct ctl_table *entry, *files;
+ int nr_files = 0;
+ int nr_dirs = 0;
+ int err = -ENOMEM;
+
+ for (entry = table; entry->procname; entry++) {
+ if (entry->child)
+ nr_dirs++;
+ else
+ nr_files++;
+ }
+
+ files = table;
+ /* If there are mixed files and directories we need a new table */
+ if (nr_dirs && nr_files) {
+ struct ctl_table *new;
+ files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1),
+ GFP_KERNEL);
+ if (!files)
+ goto out;
+
+ ctl_table_arg = files;
+ for (new = files, entry = table; entry->procname; entry++) {
+ if (entry->child)
+ continue;
+ *new = *entry;
+ new++;
+ }
+ }
+
+ /* Register everything except a directory full of subdirectories */
+ if (nr_files || !nr_dirs) {
+ struct ctl_table_header *header;
+ header = __register_sysctl_table(set, path, files);
+ if (!header) {
+ kfree(ctl_table_arg);
+ goto out;
+ }
+
+ /* Remember if we need to free the file table */
+ header->ctl_table_arg = ctl_table_arg;
+ **subheader = header;
+ (*subheader)++;
+ }
+
+ /* Recurse into the subdirectories. */
+ for (entry = table; entry->procname; entry++) {
+ char *child_pos;
+
+ if (!entry->child)
+ continue;
+
+ err = -ENAMETOOLONG;
+ child_pos = append_path(path, pos, entry->procname);
+ if (!child_pos)
+ goto out;
+
+ err = register_leaf_sysctl_tables(path, child_pos, subheader,
+ set, entry->child);
+ pos[0] = '\0';
+ if (err)
+ goto out;
+ }
+ err = 0;
+out:
+ /* On failure our caller will unregister all registered subheaders */
+ return err;
+}
+
+/**
+ * __register_sysctl_paths - register a sysctl table hierarchy
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *__register_sysctl_paths(
+ struct ctl_table_set *set,
+ const struct ctl_path *path, struct ctl_table *table)
+{
+ struct ctl_table *ctl_table_arg = table;
+ int nr_subheaders = count_subheaders(table);
+ struct ctl_table_header *header = NULL, **subheaders, **subheader;
+ const struct ctl_path *component;
+ char *new_path, *pos;
+
+ pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!new_path)
+ return NULL;
+
+ pos[0] = '\0';
+ for (component = path; component->procname; component++) {
+ pos = append_path(new_path, pos, component->procname);
+ if (!pos)
+ goto out;
+ }
+ while (table->procname && table->child && !table[1].procname) {
+ pos = append_path(new_path, pos, table->procname);
+ if (!pos)
+ goto out;
+ table = table->child;
+ }
+ if (nr_subheaders == 1) {
+ header = __register_sysctl_table(set, new_path, table);
+ if (header)
+ header->ctl_table_arg = ctl_table_arg;
+ } else {
+ header = kzalloc(sizeof(*header) +
+ sizeof(*subheaders)*nr_subheaders, GFP_KERNEL);
+ if (!header)
+ goto out;
+
+ subheaders = (struct ctl_table_header **) (header + 1);
+ subheader = subheaders;
+ header->ctl_table_arg = ctl_table_arg;
+
+ if (register_leaf_sysctl_tables(new_path, pos, &subheader,
+ set, table))
+ goto err_register_leaves;
+ }
+
+out:
+ kfree(new_path);
+ return header;
+
+err_register_leaves:
+ while (subheader > subheaders) {
+ struct ctl_table_header *subh = *(--subheader);
+ struct ctl_table *table = subh->ctl_table_arg;
+ unregister_sysctl_table(subh);
+ kfree(table);
+ }
+ kfree(header);
+ header = NULL;
+ goto out;
+}
+
+/**
+ * register_sysctl_table_path - register a sysctl table hierarchy
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+ struct ctl_table *table)
+{
+ return __register_sysctl_paths(&sysctl_table_root.default_set,
+ path, table);
+}
+EXPORT_SYMBOL(register_sysctl_paths);
+
+/**
+ * register_sysctl_table - register a sysctl table hierarchy
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
+{
+ static const struct ctl_path null_path[] = { {} };
+
+ return register_sysctl_paths(null_path, table);
+}
+EXPORT_SYMBOL(register_sysctl_table);
+
+static void put_links(struct ctl_table_header *header)
+{
+ struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+ struct ctl_table_root *root = header->root;
+ struct ctl_dir *parent = header->parent;
+ struct ctl_dir *core_parent;
+ struct ctl_table *entry;
+
+ if (header->set == root_set)
+ return;
+
+ core_parent = xlate_dir(root_set, parent);
+ if (IS_ERR(core_parent))
+ return;
+
+ for (entry = header->ctl_table; entry->procname; entry++) {
+ struct ctl_table_header *link_head;
+ struct ctl_table *link;
+ const char *name = entry->procname;
+
+ link = find_entry(&link_head, core_parent, name, strlen(name));
+ if (link &&
+ ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) ||
+ (S_ISLNK(link->mode) && (link->data == root)))) {
+ drop_sysctl_table(link_head);
+ }
+ else {
+ printk(KERN_ERR "sysctl link missing during unregister: ");
+ sysctl_print_dir(parent);
+ printk(KERN_CONT "/%s\n", name);
+ }
+ }
+}
+
+static void drop_sysctl_table(struct ctl_table_header *header)
+{
+ struct ctl_dir *parent = header->parent;
+
+ if (--header->nreg)
+ return;
+
+ put_links(header);
+ start_unregistering(header);
+ if (!--header->count)
+ kfree_rcu(header, rcu);
+
+ if (parent)
+ drop_sysctl_table(&parent->header);
+}
+
+/**
+ * unregister_sysctl_table - unregister a sysctl table hierarchy
+ * @header: the header returned from register_sysctl_table
+ *
+ * Unregisters the sysctl table and all children. proc entries may not
+ * actually be removed until they are no longer used by anyone.
+ */
+void unregister_sysctl_table(struct ctl_table_header * header)
+{
+ int nr_subheaders;
+ might_sleep();
+
+ if (header == NULL)
+ return;
+
+ nr_subheaders = count_subheaders(header->ctl_table_arg);
+ if (unlikely(nr_subheaders > 1)) {
+ struct ctl_table_header **subheaders;
+ int i;
+
+ subheaders = (struct ctl_table_header **)(header + 1);
+ for (i = nr_subheaders -1; i >= 0; i--) {
+ struct ctl_table_header *subh = subheaders[i];
+ struct ctl_table *table = subh->ctl_table_arg;
+ unregister_sysctl_table(subh);
+ kfree(table);
+ }
+ kfree(header);
+ return;
+ }
+
+ spin_lock(&sysctl_lock);
+ drop_sysctl_table(header);
+ spin_unlock(&sysctl_lock);
+}
+EXPORT_SYMBOL(unregister_sysctl_table);
+
+void setup_sysctl_set(struct ctl_table_set *set,
+ struct ctl_table_root *root,
+ int (*is_seen)(struct ctl_table_set *))
+{
+ memset(set, 0, sizeof(*set));
+ set->is_seen = is_seen;
+ init_header(&set->dir.header, root, set, NULL, root_table);
+}
+
+void retire_sysctl_set(struct ctl_table_set *set)
+{
+ WARN_ON(!RB_EMPTY_ROOT(&set->dir.root));
+}
+
int __init proc_sys_init(void)
{
struct proc_dir_entry *proc_sys_root;
@@ -478,5 +1601,6 @@ int __init proc_sys_init(void)
proc_sys_root->proc_iops = &proc_sys_dir_operations;
proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
proc_sys_root->nlink = 0;
- return 0;
+
+ return sysctl_init();
}
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 121f77c..6a0c62d 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -89,18 +89,19 @@ static int show_stat(struct seq_file *p, void *v)
}
sum += arch_irq_stat();
- seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu "
- "%llu\n",
- (unsigned long long)cputime64_to_clock_t(user),
- (unsigned long long)cputime64_to_clock_t(nice),
- (unsigned long long)cputime64_to_clock_t(system),
- (unsigned long long)cputime64_to_clock_t(idle),
- (unsigned long long)cputime64_to_clock_t(iowait),
- (unsigned long long)cputime64_to_clock_t(irq),
- (unsigned long long)cputime64_to_clock_t(softirq),
- (unsigned long long)cputime64_to_clock_t(steal),
- (unsigned long long)cputime64_to_clock_t(guest),
- (unsigned long long)cputime64_to_clock_t(guest_nice));
+ seq_puts(p, "cpu ");
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+ seq_putc(p, '\n');
+
for_each_online_cpu(i) {
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
@@ -113,26 +114,24 @@ static int show_stat(struct seq_file *p, void *v)
steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
- seq_printf(p,
- "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
- "%llu\n",
- i,
- (unsigned long long)cputime64_to_clock_t(user),
- (unsigned long long)cputime64_to_clock_t(nice),
- (unsigned long long)cputime64_to_clock_t(system),
- (unsigned long long)cputime64_to_clock_t(idle),
- (unsigned long long)cputime64_to_clock_t(iowait),
- (unsigned long long)cputime64_to_clock_t(irq),
- (unsigned long long)cputime64_to_clock_t(softirq),
- (unsigned long long)cputime64_to_clock_t(steal),
- (unsigned long long)cputime64_to_clock_t(guest),
- (unsigned long long)cputime64_to_clock_t(guest_nice));
+ seq_printf(p, "cpu%d", i);
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
+ seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
+ seq_putc(p, '\n');
}
seq_printf(p, "intr %llu", (unsigned long long)sum);
/* sum again ? it could be updated? */
for_each_irq_nr(j)
- seq_printf(p, " %u", kstat_irqs(j));
+ seq_put_decimal_ull(p, ' ', kstat_irqs(j));
seq_printf(p,
"\nctxt %llu\n"
@@ -149,7 +148,7 @@ static int show_stat(struct seq_file *p, void *v)
seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
for (i = 0; i < NR_SOFTIRQS; i++)
- seq_printf(p, " %u", per_softirq_sums[i]);
+ seq_put_decimal_ull(p, ' ', per_softirq_sums[i]);
seq_putc(p, '\n');
return 0;
@@ -157,11 +156,14 @@ static int show_stat(struct seq_file *p, void *v)
static int stat_open(struct inode *inode, struct file *file)
{
- unsigned size = 4096 * (1 + num_possible_cpus() / 32);
+ unsigned size = 1024 + 128 * num_possible_cpus();
char *buf;
struct seq_file *m;
int res;
+ /* minimum size to display an interrupt count : 2 bytes */
+ size += 2 * nr_irqs;
+
/* don't ask for more than the kmalloc() max size */
if (size > KMALLOC_MAX_SIZE)
size = KMALLOC_MAX_SIZE;
@@ -173,7 +175,7 @@ static int stat_open(struct inode *inode, struct file *file)
if (!res) {
m = file->private_data;
m->buf = buf;
- m->size = size;
+ m->size = ksize(buf);
} else
kfree(buf);
return res;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e418c5a..9694cc2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -209,16 +209,20 @@ static int do_maps_open(struct inode *inode, struct file *file,
return ret;
}
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
vm_flags_t flags = vma->vm_flags;
unsigned long ino = 0;
unsigned long long pgoff = 0;
unsigned long start, end;
dev_t dev = 0;
int len;
+ const char *name = NULL;
if (file) {
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
@@ -252,36 +256,57 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
if (file) {
pad_len_spaces(m, len);
seq_path(m, &file->f_path, "\n");
- } else {
- const char *name = arch_vma_name(vma);
- if (!name) {
- if (mm) {
- if (vma->vm_start <= mm->brk &&
- vma->vm_end >= mm->start_brk) {
- name = "[heap]";
- } else if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
- name = "[stack]";
- }
+ goto done;
+ }
+
+ name = arch_vma_name(vma);
+ if (!name) {
+ pid_t tid;
+
+ if (!mm) {
+ name = "[vdso]";
+ goto done;
+ }
+
+ if (vma->vm_start <= mm->brk &&
+ vma->vm_end >= mm->start_brk) {
+ name = "[heap]";
+ goto done;
+ }
+
+ tid = vm_is_stack(task, vma, is_pid);
+
+ if (tid != 0) {
+ /*
+ * Thread stack in /proc/PID/task/TID/maps or
+ * the main process stack.
+ */
+ if (!is_pid || (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack)) {
+ name = "[stack]";
} else {
- name = "[vdso]";
+ /* Thread stack in /proc/PID/maps */
+ pad_len_spaces(m, len);
+ seq_printf(m, "[stack:%d]", tid);
}
}
- if (name) {
- pad_len_spaces(m, len);
- seq_puts(m, name);
- }
+ }
+
+done:
+ if (name) {
+ pad_len_spaces(m, len);
+ seq_puts(m, name);
}
seq_putc(m, '\n');
}
-static int show_map(struct seq_file *m, void *v)
+static int show_map(struct seq_file *m, void *v, int is_pid)
{
struct vm_area_struct *vma = v;
struct proc_maps_private *priv = m->private;
struct task_struct *task = priv->task;
- show_map_vma(m, vma);
+ show_map_vma(m, vma, is_pid);
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task->mm))
@@ -289,20 +314,49 @@ static int show_map(struct seq_file *m, void *v)
return 0;
}
+static int show_pid_map(struct seq_file *m, void *v)
+{
+ return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+ return show_map(m, v, 0);
+}
+
static const struct seq_operations proc_pid_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_map
+ .show = show_pid_map
};
-static int maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_pid_maps_op);
}
-const struct file_operations proc_maps_operations = {
- .open = maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+ .open = pid_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+ .open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
@@ -394,21 +448,15 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t *pte;
spinlock_t *ptl;
- spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(vma->anon_vma, pmd);
- } else {
- smaps_pte_entry(*(pte_t *)pmd, addr,
- HPAGE_PMD_SIZE, walk);
- spin_unlock(&walk->mm->page_table_lock);
- mss->anonymous_thp += HPAGE_PMD_SIZE;
- return 0;
- }
- } else {
+ if (pmd_trans_huge_lock(pmd, vma) == 1) {
+ smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
spin_unlock(&walk->mm->page_table_lock);
+ mss->anonymous_thp += HPAGE_PMD_SIZE;
+ return 0;
}
+
+ if (pmd_trans_unstable(pmd))
+ return 0;
/*
* The mmap_sem held all the way back in m_start() is what
* keeps khugepaged out of here and from collapsing things
@@ -422,7 +470,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
return 0;
}
-static int show_smap(struct seq_file *m, void *v)
+static int show_smap(struct seq_file *m, void *v, int is_pid)
{
struct proc_maps_private *priv = m->private;
struct task_struct *task = priv->task;
@@ -440,7 +488,7 @@ static int show_smap(struct seq_file *m, void *v)
if (vma->vm_mm && !is_vm_hugetlb_page(vma))
walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
- show_map_vma(m, vma);
+ show_map_vma(m, vma, is_pid);
seq_printf(m,
"Size: %8lu kB\n"
@@ -479,20 +527,49 @@ static int show_smap(struct seq_file *m, void *v)
return 0;
}
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+ return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+ return show_smap(m, v, 0);
+}
+
static const struct seq_operations proc_pid_smaps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_smap
+ .show = show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_smap
};
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_smaps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_pid_smaps_op);
}
-const struct file_operations proc_smaps_operations = {
- .open = smaps_open,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+ .open = pid_smaps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+ .open = tid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
@@ -507,6 +584,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
struct page *page;
split_huge_page_pmd(walk->mm, pmd);
+ if (pmd_trans_unstable(pmd))
+ return 0;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -518,6 +597,9 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
if (!page)
continue;
+ if (PageReserved(page))
+ continue;
+
/* Clear accessed and referenced bits. */
ptep_test_and_clear_young(vma, addr, pte);
ClearPageReferenced(page);
@@ -595,11 +677,18 @@ const struct file_operations proc_clear_refs_operations = {
.llseek = noop_llseek,
};
+typedef struct {
+ u64 pme;
+} pagemap_entry_t;
+
struct pagemapread {
int pos, len;
- u64 *buffer;
+ pagemap_entry_t *buffer;
};
+#define PAGEMAP_WALK_SIZE (PMD_SIZE)
+#define PAGEMAP_WALK_MASK (PMD_MASK)
+
#define PM_ENTRY_BYTES sizeof(u64)
#define PM_STATUS_BITS 3
#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
@@ -617,10 +706,15 @@ struct pagemapread {
#define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT)
#define PM_END_OF_BUFFER 1
-static int add_to_pagemap(unsigned long addr, u64 pfn,
+static inline pagemap_entry_t make_pme(u64 val)
+{
+ return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
struct pagemapread *pm)
{
- pm->buffer[pm->pos++] = pfn;
+ pm->buffer[pm->pos++] = *pme;
if (pm->pos >= pm->len)
return PM_END_OF_BUFFER;
return 0;
@@ -632,8 +726,10 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
struct pagemapread *pm = walk->private;
unsigned long addr;
int err = 0;
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+
for (addr = start; addr < end; addr += PAGE_SIZE) {
- err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+ err = add_to_pagemap(addr, &pme, pm);
if (err)
break;
}
@@ -646,18 +742,36 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
}
-static u64 pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte)
{
- u64 pme = 0;
if (is_swap_pte(pte))
- pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
- | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+ *pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP);
else if (pte_present(pte))
- pme = PM_PFRAME(pte_pfn(pte))
- | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
- return pme;
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+ pmd_t pmd, int offset)
+{
+ /*
+ * Currently pmd for thp is always present because thp can not be
+ * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+ * This if-check is just to prepare for future implementation.
+ */
+ if (pmd_present(pmd))
+ *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+}
+#else
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+ pmd_t pmd, int offset)
+{
+}
+#endif
+
static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -665,13 +779,30 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct pagemapread *pm = walk->private;
pte_t *pte;
int err = 0;
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
- split_huge_page_pmd(walk->mm, pmd);
+ if (pmd_trans_unstable(pmd))
+ return 0;
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
+ spin_lock(&walk->mm->page_table_lock);
+ if (pmd_trans_huge_lock(pmd, vma) == 1) {
+ for (; addr != end; addr += PAGE_SIZE) {
+ unsigned long offset;
+
+ offset = (addr & ~PAGEMAP_WALK_MASK) >>
+ PAGE_SHIFT;
+ thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ break;
+ }
+ spin_unlock(&walk->mm->page_table_lock);
+ return err;
+ }
+
for (; addr != end; addr += PAGE_SIZE) {
- u64 pfn = PM_NOT_PRESENT;
/* check to see if we've left 'vma' behind
* and need a new, higher one */
@@ -683,11 +814,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (vma && (vma->vm_start <= addr) &&
!is_vm_hugetlb_page(vma)) {
pte = pte_offset_map(pmd, addr);
- pfn = pte_to_pagemap_entry(*pte);
+ pte_to_pagemap_entry(&pme, *pte);
/* unmap before userspace copy */
pte_unmap(pte);
}
- err = add_to_pagemap(addr, pfn, pm);
+ err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
}
@@ -698,13 +829,12 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
}
#ifdef CONFIG_HUGETLB_PAGE
-static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+ pte_t pte, int offset)
{
- u64 pme = 0;
if (pte_present(pte))
- pme = PM_PFRAME(pte_pfn(pte) + offset)
- | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
- return pme;
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
}
/* This function walks within one hugetlb entry in the single call */
@@ -714,12 +844,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
{
struct pagemapread *pm = walk->private;
int err = 0;
- u64 pfn;
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
for (; addr != end; addr += PAGE_SIZE) {
int offset = (addr & ~hmask) >> PAGE_SHIFT;
- pfn = huge_pte_to_pagemap_entry(*pte, offset);
- err = add_to_pagemap(addr, pfn, pm);
+ huge_pte_to_pagemap_entry(&pme, *pte, offset);
+ err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
}
@@ -754,8 +884,6 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
* determine which areas of memory are actually mapped and llseek to
* skip over unmapped regions.
*/
-#define PAGEMAP_WALK_SIZE (PMD_SIZE)
-#define PAGEMAP_WALK_MASK (PMD_MASK)
static ssize_t pagemap_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
@@ -938,26 +1066,21 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
pte_t *pte;
md = walk->private;
- spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(md->vma->anon_vma, pmd);
- } else {
- pte_t huge_pte = *(pte_t *)pmd;
- struct page *page;
-
- page = can_gather_numa_stats(huge_pte, md->vma, addr);
- if (page)
- gather_stats(page, md, pte_dirty(huge_pte),
- HPAGE_PMD_SIZE/PAGE_SIZE);
- spin_unlock(&walk->mm->page_table_lock);
- return 0;
- }
- } else {
+
+ if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+ pte_t huge_pte = *(pte_t *)pmd;
+ struct page *page;
+
+ page = can_gather_numa_stats(huge_pte, md->vma, addr);
+ if (page)
+ gather_stats(page, md, pte_dirty(huge_pte),
+ HPAGE_PMD_SIZE/PAGE_SIZE);
spin_unlock(&walk->mm->page_table_lock);
+ return 0;
}
+ if (pmd_trans_unstable(pmd))
+ return 0;
orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
do {
struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -999,7 +1122,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
/*
* Display pages allocated per node and memory policy via /proc.
*/
-static int show_numa_map(struct seq_file *m, void *v)
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
{
struct numa_maps_private *numa_priv = m->private;
struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
@@ -1036,9 +1159,19 @@ static int show_numa_map(struct seq_file *m, void *v)
seq_path(m, &file->f_path, "\n\t= ");
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_printf(m, " heap");
- } else if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
- seq_printf(m, " stack");
+ } else {
+ pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+ if (tid != 0) {
+ /*
+ * Thread stack in /proc/PID/task/TID/maps or
+ * the main process stack.
+ */
+ if (!is_pid || (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack))
+ seq_printf(m, " stack");
+ else
+ seq_printf(m, " stack:%d", tid);
+ }
}
if (is_vm_hugetlb_page(vma))
@@ -1081,21 +1214,39 @@ out:
return 0;
}
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+ return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+ return show_numa_map(m, v, 0);
+}
+
static const struct seq_operations proc_pid_numa_maps_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_numa_map,
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_pid_numa_map,
+};
+
+static const struct seq_operations proc_tid_numa_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_numa_map,
};
-static int numa_maps_open(struct inode *inode, struct file *file)
+static int numa_maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops)
{
struct numa_maps_private *priv;
int ret = -ENOMEM;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (priv) {
priv->proc_maps.pid = proc_pid(inode);
- ret = seq_open(file, &proc_pid_numa_maps_op);
+ ret = seq_open(file, ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = priv;
@@ -1106,8 +1257,25 @@ static int numa_maps_open(struct inode *inode, struct file *file)
return ret;
}
-const struct file_operations proc_numa_maps_operations = {
- .open = numa_maps_open,
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+ return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+ return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+ .open = pid_numa_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+ .open = tid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 980de54..74fe164 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -134,9 +134,11 @@ static void pad_len_spaces(struct seq_file *m, int len)
/*
* display a single VMA to a sequenced file
*/
-static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
+ int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
+ struct proc_maps_private *priv = m->private;
unsigned long ino = 0;
struct file *file;
dev_t dev = 0;
@@ -168,10 +170,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
pad_len_spaces(m, len);
seq_path(m, &file->f_path, "");
} else if (mm) {
- if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
+ pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+
+ if (tid != 0) {
pad_len_spaces(m, len);
- seq_puts(m, "[stack]");
+ /*
+ * Thread stack in /proc/PID/task/TID/maps or
+ * the main process stack.
+ */
+ if (!is_pid || (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack))
+ seq_printf(m, "[stack]");
+ else
+ seq_printf(m, "[stack:%d]", tid);
}
}
@@ -182,11 +193,22 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
/*
* display mapping lines for a particular process's /proc/pid/maps
*/
-static int show_map(struct seq_file *m, void *_p)
+static int show_map(struct seq_file *m, void *_p, int is_pid)
{
struct rb_node *p = _p;
- return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
+ return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb),
+ is_pid);
+}
+
+static int show_pid_map(struct seq_file *m, void *_p)
+{
+ return show_map(m, _p, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *_p)
+{
+ return show_map(m, _p, 0);
}
static void *m_start(struct seq_file *m, loff_t *pos)
@@ -240,10 +262,18 @@ static const struct seq_operations proc_pid_maps_ops = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_map
+ .show = show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_ops = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_map
};
-static int maps_open(struct inode *inode, struct file *file)
+static int maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops)
{
struct proc_maps_private *priv;
int ret = -ENOMEM;
@@ -251,7 +281,7 @@ static int maps_open(struct inode *inode, struct file *file)
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (priv) {
priv->pid = proc_pid(inode);
- ret = seq_open(file, &proc_pid_maps_ops);
+ ret = seq_open(file, ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = priv;
@@ -262,8 +292,25 @@ static int maps_open(struct inode *inode, struct file *file)
return ret;
}
-const struct file_operations proc_maps_operations = {
- .open = maps_open,
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+ return maps_open(inode, file, &proc_pid_maps_ops);
+}
+
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+ return maps_open(inode, file, &proc_tid_maps_ops);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+ .open = pid_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+ .open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index b0f450a..0d5071d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -700,3 +700,26 @@ static int __init vmcore_init(void)
return 0;
}
module_init(vmcore_init)
+
+/* Cleanup function for vmcore module. */
+void vmcore_cleanup(void)
+{
+ struct list_head *pos, *next;
+
+ if (proc_vmcore) {
+ remove_proc_entry(proc_vmcore->name, proc_vmcore->parent);
+ proc_vmcore = NULL;
+ }
+
+ /* clear the vmcore list. */
+ list_for_each_safe(pos, next, &vmcore_list) {
+ struct vmcore *m;
+
+ m = list_entry(pos, struct vmcore, list);
+ list_del(&m->list);
+ kfree(m);
+ }
+ kfree(elfcorebuf);
+ elfcorebuf = NULL;
+}
+EXPORT_SYMBOL_GPL(vmcore_cleanup);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index b3b426e..f37c32b 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -278,9 +278,7 @@ fail:
int pstore_fill_super(struct super_block *sb, void *data, int silent)
{
- struct inode *inode = NULL;
- struct dentry *root;
- int err;
+ struct inode *inode;
save_mount_options(sb, data);
@@ -296,26 +294,17 @@ int pstore_fill_super(struct super_block *sb, void *data, int silent)
parse_options(data);
inode = pstore_get_inode(sb, NULL, S_IFDIR | 0755, 0);
- if (!inode) {
- err = -ENOMEM;
- goto fail;
- }
- /* override ramfs "dir" options so we catch unlink(2) */
- inode->i_op = &pstore_dir_inode_operations;
-
- root = d_alloc_root(inode);
- sb->s_root = root;
- if (!root) {
- err = -ENOMEM;
- goto fail;
+ if (inode) {
+ /* override ramfs "dir" options so we catch unlink(2) */
+ inode->i_op = &pstore_dir_inode_operations;
}
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root)
+ return -ENOMEM;
pstore_get_records(0);
return 0;
-fail:
- iput(inode);
- return err;
}
static struct dentry *pstore_mount(struct file_system_type *fs_type,
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 9ec22d3..82c585f 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -68,9 +68,25 @@ void pstore_set_kmsg_bytes(int bytes)
/* Tag each group of saved records with a sequence number */
static int oopscount;
-static char *reason_str[] = {
- "Oops", "Panic", "Kexec", "Restart", "Halt", "Poweroff", "Emergency"
-};
+static const char *get_reason_str(enum kmsg_dump_reason reason)
+{
+ switch (reason) {
+ case KMSG_DUMP_PANIC:
+ return "Panic";
+ case KMSG_DUMP_OOPS:
+ return "Oops";
+ case KMSG_DUMP_EMERG:
+ return "Emergency";
+ case KMSG_DUMP_RESTART:
+ return "Restart";
+ case KMSG_DUMP_HALT:
+ return "Halt";
+ case KMSG_DUMP_POWEROFF:
+ return "Poweroff";
+ default:
+ return "Unknown";
+ }
+}
/*
* callback from kmsg_dump. (s2,l2) has the most recently
@@ -85,17 +101,15 @@ static void pstore_dump(struct kmsg_dumper *dumper,
unsigned long s1_start, s2_start;
unsigned long l1_cpy, l2_cpy;
unsigned long size, total = 0;
- char *dst, *why;
+ char *dst;
+ const char *why;
u64 id;
int hsize, ret;
unsigned int part = 1;
unsigned long flags = 0;
int is_locked = 0;
- if (reason < ARRAY_SIZE(reason_str))
- why = reason_str[reason];
- else
- why = "Unknown";
+ why = get_reason_str(reason);
if (in_nmi()) {
is_locked = spin_trylock(&psinfo->buf_lock);
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 6b00954..552e994 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -52,38 +52,6 @@ static int qnx4_remount(struct super_block *sb, int *flags, char *data)
return 0;
}
-static struct buffer_head *qnx4_getblk(struct inode *inode, int nr,
- int create)
-{
- struct buffer_head *result = NULL;
-
- if ( nr >= 0 )
- nr = qnx4_block_map( inode, nr );
- if (nr) {
- result = sb_getblk(inode->i_sb, nr);
- return result;
- }
- return NULL;
-}
-
-struct buffer_head *qnx4_bread(struct inode *inode, int block, int create)
-{
- struct buffer_head *bh;
-
- bh = qnx4_getblk(inode, block, create);
- if (!bh || buffer_uptodate(bh)) {
- return bh;
- }
- ll_rw_block(READ, 1, &bh);
- wait_on_buffer(bh);
- if (buffer_uptodate(bh)) {
- return bh;
- }
- brelse(bh);
-
- return NULL;
-}
-
static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_head *bh, int create )
{
unsigned long phys;
@@ -98,23 +66,31 @@ static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_h
return 0;
}
+static inline u32 try_extent(qnx4_xtnt_t *extent, u32 *offset)
+{
+ u32 size = le32_to_cpu(extent->xtnt_size);
+ if (*offset < size)
+ return le32_to_cpu(extent->xtnt_blk) + *offset - 1;
+ *offset -= size;
+ return 0;
+}
+
unsigned long qnx4_block_map( struct inode *inode, long iblock )
{
int ix;
- long offset, i_xblk;
- unsigned long block = 0;
+ long i_xblk;
struct buffer_head *bh = NULL;
struct qnx4_xblk *xblk = NULL;
struct qnx4_inode_entry *qnx4_inode = qnx4_raw_inode(inode);
u16 nxtnt = le16_to_cpu(qnx4_inode->di_num_xtnts);
+ u32 offset = iblock;
+ u32 block = try_extent(&qnx4_inode->di_first_xtnt, &offset);
- if ( iblock < le32_to_cpu(qnx4_inode->di_first_xtnt.xtnt_size) ) {
+ if (block) {
// iblock is in the first extent. This is easy.
- block = le32_to_cpu(qnx4_inode->di_first_xtnt.xtnt_blk) + iblock - 1;
} else {
// iblock is beyond first extent. We have to follow the extent chain.
i_xblk = le32_to_cpu(qnx4_inode->di_xblk);
- offset = iblock - le32_to_cpu(qnx4_inode->di_first_xtnt.xtnt_size);
ix = 0;
while ( --nxtnt > 0 ) {
if ( ix == 0 ) {
@@ -130,12 +106,11 @@ unsigned long qnx4_block_map( struct inode *inode, long iblock )
return -EIO;
}
}
- if ( offset < le32_to_cpu(xblk->xblk_xtnts[ix].xtnt_size) ) {
+ block = try_extent(&xblk->xblk_xtnts[ix], &offset);
+ if (block) {
// got it!
- block = le32_to_cpu(xblk->xblk_xtnts[ix].xtnt_blk) + offset - 1;
break;
}
- offset -= le32_to_cpu(xblk->xblk_xtnts[ix].xtnt_size);
if ( ++ix >= xblk->xblk_num_xtnts ) {
i_xblk = le32_to_cpu(xblk->xblk_next_xblk);
ix = 0;
@@ -260,15 +235,13 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent)
}
ret = -ENOMEM;
- s->s_root = d_alloc_root(root);
+ s->s_root = d_make_root(root);
if (s->s_root == NULL)
- goto outi;
+ goto outb;
brelse(bh);
return 0;
- outi:
- iput(root);
outb:
kfree(qs->BitMap);
out:
@@ -288,44 +261,17 @@ static void qnx4_put_super(struct super_block *sb)
return;
}
-static int qnx4_writepage(struct page *page, struct writeback_control *wbc)
-{
- return block_write_full_page(page,qnx4_get_block, wbc);
-}
-
static int qnx4_readpage(struct file *file, struct page *page)
{
return block_read_full_page(page,qnx4_get_block);
}
-static int qnx4_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
-{
- struct qnx4_inode_info *qnx4_inode = qnx4_i(mapping->host);
- int ret;
-
- *pagep = NULL;
- ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- qnx4_get_block,
- &qnx4_inode->mmu_private);
- if (unlikely(ret)) {
- loff_t isize = mapping->host->i_size;
- if (pos + len > isize)
- vmtruncate(mapping->host, isize);
- }
-
- return ret;
-}
static sector_t qnx4_bmap(struct address_space *mapping, sector_t block)
{
return generic_block_bmap(mapping,block,qnx4_get_block);
}
static const struct address_space_operations qnx4_aops = {
.readpage = qnx4_readpage,
- .writepage = qnx4_writepage,
- .write_begin = qnx4_write_begin,
- .write_end = generic_write_end,
.bmap = qnx4_bmap
};
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index 275327b..a512c0b 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -39,10 +39,6 @@ static int qnx4_match(int len, const char *name,
} else {
namelen = QNX4_SHORT_NAME_MAX;
}
- /* "" means "." ---> so paths like "/usr/lib//libc.a" work */
- if (!len && (de->di_fname[0] == '.') && (de->di_fname[1] == '\0')) {
- return 1;
- }
thislen = strlen( de->di_fname );
if ( thislen > namelen )
thislen = namelen;
@@ -72,7 +68,9 @@ static struct buffer_head *qnx4_find_entry(int len, struct inode *dir,
block = offset = blkofs = 0;
while (blkofs * QNX4_BLOCK_SIZE + offset < dir->i_size) {
if (!bh) {
- bh = qnx4_bread(dir, blkofs, 0);
+ block = qnx4_block_map(dir, blkofs);
+ if (block)
+ bh = sb_bread(dir->i_sb, block);
if (!bh) {
blkofs++;
continue;
@@ -80,7 +78,6 @@ static struct buffer_head *qnx4_find_entry(int len, struct inode *dir,
}
*res_dir = (struct qnx4_inode_entry *) (bh->b_data + offset);
if (qnx4_match(len, name, bh, &offset)) {
- block = qnx4_block_map( dir, blkofs );
*ino = block * QNX4_INODES_PER_BLOCK +
(offset / QNX4_DIR_ENTRY_SIZE) - 1;
return bh;
diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h
index 33a6085..244d462 100644
--- a/fs/qnx4/qnx4.h
+++ b/fs/qnx4/qnx4.h
@@ -27,8 +27,6 @@ extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, stru
extern unsigned long qnx4_count_free_blocks(struct super_block *sb);
extern unsigned long qnx4_block_map(struct inode *inode, long iblock);
-extern struct buffer_head *qnx4_bread(struct inode *, int, int);
-
extern const struct inode_operations qnx4_dir_inode_operations;
extern const struct file_operations qnx4_dir_operations;
extern int qnx4_is_free(struct super_block *sb, long block);
diff --git a/fs/qnx6/Kconfig b/fs/qnx6/Kconfig
new file mode 100644
index 0000000..edbba5c
--- /dev/null
+++ b/fs/qnx6/Kconfig
@@ -0,0 +1,26 @@
+config QNX6FS_FS
+ tristate "QNX6 file system support (read only)"
+ depends on BLOCK && CRC32
+ help
+ This is the file system used by the real-time operating systems
+ QNX 6 (also called QNX RTP).
+ Further information is available at <http://www.qnx.com/>.
+ Say Y if you intend to mount QNX hard disks or floppies formatted
+ with a mkqnx6fs.
+ However, keep in mind that this currently is a readonly driver!
+
+ To compile this file system support as a module, choose M here: the
+ module will be called qnx6.
+
+ If you don't know whether you need it, then you don't need it:
+ answer N.
+
+config QNX6FS_DEBUG
+ bool "QNX6 debugging information"
+ depends on QNX6FS_FS
+ help
+ Turns on extended debugging output.
+
+ If you are not a developer working on the QNX6FS, you probably don't
+ want this:
+ answer N.
diff --git a/fs/qnx6/Makefile b/fs/qnx6/Makefile
new file mode 100644
index 0000000..9dd0619
--- /dev/null
+++ b/fs/qnx6/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the linux qnx4-filesystem routines.
+#
+
+obj-$(CONFIG_QNX6FS_FS) += qnx6.o
+
+qnx6-objs := inode.o dir.o namei.o super_mmi.o
diff --git a/fs/qnx6/README b/fs/qnx6/README
new file mode 100644
index 0000000..116d622
--- /dev/null
+++ b/fs/qnx6/README
@@ -0,0 +1,8 @@
+
+ This is a snapshot of the QNX6 filesystem for Linux.
+ Please send diffs and remarks to <chaosman@ontika.net> .
+
+Credits :
+
+Al Viro <viro@ZenIV.linux.org.uk> (endless patience with me & support ;))
+Kai Bankett <chaosman@ontika.net> (Maintainer)
diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c
new file mode 100644
index 0000000..dc59735
--- /dev/null
+++ b/fs/qnx6/dir.c
@@ -0,0 +1,291 @@
+/*
+ * QNX6 file system, Linux implementation.
+ *
+ * Version : 1.0.0
+ *
+ * History :
+ *
+ * 01-02-2012 by Kai Bankett (chaosman@ontika.net) : first release.
+ * 16-02-2012 pagemap extension by Al Viro
+ *
+ */
+
+#include "qnx6.h"
+
+static unsigned qnx6_lfile_checksum(char *name, unsigned size)
+{
+ unsigned crc = 0;
+ char *end = name + size;
+ while (name < end) {
+ crc = ((crc >> 1) + *(name++)) ^
+ ((crc & 0x00000001) ? 0x80000000 : 0);
+ }
+ return crc;
+}
+
+static struct page *qnx6_get_page(struct inode *dir, unsigned long n)
+{
+ struct address_space *mapping = dir->i_mapping;
+ struct page *page = read_mapping_page(mapping, n, NULL);
+ if (!IS_ERR(page))
+ kmap(page);
+ return page;
+}
+
+static inline unsigned long dir_pages(struct inode *inode)
+{
+ return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
+}
+
+static unsigned last_entry(struct inode *inode, unsigned long page_nr)
+{
+ unsigned long last_byte = inode->i_size;
+ last_byte -= page_nr << PAGE_CACHE_SHIFT;
+ if (last_byte > PAGE_CACHE_SIZE)
+ last_byte = PAGE_CACHE_SIZE;
+ return last_byte / QNX6_DIR_ENTRY_SIZE;
+}
+
+static struct qnx6_long_filename *qnx6_longname(struct super_block *sb,
+ struct qnx6_long_dir_entry *de,
+ struct page **p)
+{
+ struct qnx6_sb_info *sbi = QNX6_SB(sb);
+ u32 s = fs32_to_cpu(sbi, de->de_long_inode); /* in block units */
+ u32 n = s >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits); /* in pages */
+ /* within page */
+ u32 offs = (s << sb->s_blocksize_bits) & ~PAGE_CACHE_MASK;
+ struct address_space *mapping = sbi->longfile->i_mapping;
+ struct page *page = read_mapping_page(mapping, n, NULL);
+ if (IS_ERR(page))
+ return ERR_CAST(page);
+ kmap(*p = page);
+ return (struct qnx6_long_filename *)(page_address(page) + offs);
+}
+
+static int qnx6_dir_longfilename(struct inode *inode,
+ struct qnx6_long_dir_entry *de,
+ void *dirent, loff_t pos,
+ unsigned de_inode, filldir_t filldir)
+{
+ struct qnx6_long_filename *lf;
+ struct super_block *s = inode->i_sb;
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ struct page *page;
+ int lf_size;
+
+ if (de->de_size != 0xff) {
+ /* error - long filename entries always have size 0xff
+ in direntry */
+ printk(KERN_ERR "qnx6: invalid direntry size (%i).\n",
+ de->de_size);
+ return 0;
+ }
+ lf = qnx6_longname(s, de, &page);
+ if (IS_ERR(lf)) {
+ printk(KERN_ERR "qnx6:Error reading longname\n");
+ return 0;
+ }
+
+ lf_size = fs16_to_cpu(sbi, lf->lf_size);
+
+ if (lf_size > QNX6_LONG_NAME_MAX) {
+ QNX6DEBUG((KERN_INFO "file %s\n", lf->lf_fname));
+ printk(KERN_ERR "qnx6:Filename too long (%i)\n", lf_size);
+ qnx6_put_page(page);
+ return 0;
+ }
+
+ /* calc & validate longfilename checksum
+ mmi 3g filesystem does not have that checksum */
+ if (!test_opt(s, MMI_FS) && fs32_to_cpu(sbi, de->de_checksum) !=
+ qnx6_lfile_checksum(lf->lf_fname, lf_size))
+ printk(KERN_INFO "qnx6: long filename checksum error.\n");
+
+ QNX6DEBUG((KERN_INFO "qnx6_readdir:%.*s inode:%u\n",
+ lf_size, lf->lf_fname, de_inode));
+ if (filldir(dirent, lf->lf_fname, lf_size, pos, de_inode,
+ DT_UNKNOWN) < 0) {
+ qnx6_put_page(page);
+ return 0;
+ }
+
+ qnx6_put_page(page);
+ /* success */
+ return 1;
+}
+
+static int qnx6_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *s = inode->i_sb;
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ loff_t pos = filp->f_pos & (QNX6_DIR_ENTRY_SIZE - 1);
+ unsigned long npages = dir_pages(inode);
+ unsigned long n = pos >> PAGE_CACHE_SHIFT;
+ unsigned start = (pos & ~PAGE_CACHE_MASK) / QNX6_DIR_ENTRY_SIZE;
+ bool done = false;
+
+ if (filp->f_pos >= inode->i_size)
+ return 0;
+
+ for ( ; !done && n < npages; n++, start = 0) {
+ struct page *page = qnx6_get_page(inode, n);
+ int limit = last_entry(inode, n);
+ struct qnx6_dir_entry *de;
+ int i = start;
+
+ if (IS_ERR(page)) {
+ printk(KERN_ERR "qnx6_readdir: read failed\n");
+ filp->f_pos = (n + 1) << PAGE_CACHE_SHIFT;
+ return PTR_ERR(page);
+ }
+ de = ((struct qnx6_dir_entry *)page_address(page)) + start;
+ for (; i < limit; i++, de++, pos += QNX6_DIR_ENTRY_SIZE) {
+ int size = de->de_size;
+ u32 no_inode = fs32_to_cpu(sbi, de->de_inode);
+
+ if (!no_inode || !size)
+ continue;
+
+ if (size > QNX6_SHORT_NAME_MAX) {
+ /* long filename detected
+ get the filename from long filename
+ structure / block */
+ if (!qnx6_dir_longfilename(inode,
+ (struct qnx6_long_dir_entry *)de,
+ dirent, pos, no_inode,
+ filldir)) {
+ done = true;
+ break;
+ }
+ } else {
+ QNX6DEBUG((KERN_INFO "qnx6_readdir:%.*s"
+ " inode:%u\n", size, de->de_fname,
+ no_inode));
+ if (filldir(dirent, de->de_fname, size,
+ pos, no_inode, DT_UNKNOWN)
+ < 0) {
+ done = true;
+ break;
+ }
+ }
+ }
+ qnx6_put_page(page);
+ }
+ filp->f_pos = pos;
+ return 0;
+}
+
+/*
+ * check if the long filename is correct.
+ */
+static unsigned qnx6_long_match(int len, const char *name,
+ struct qnx6_long_dir_entry *de, struct inode *dir)
+{
+ struct super_block *s = dir->i_sb;
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ struct page *page;
+ int thislen;
+ struct qnx6_long_filename *lf = qnx6_longname(s, de, &page);
+
+ if (IS_ERR(lf))
+ return 0;
+
+ thislen = fs16_to_cpu(sbi, lf->lf_size);
+ if (len != thislen) {
+ qnx6_put_page(page);
+ return 0;
+ }
+ if (memcmp(name, lf->lf_fname, len) == 0) {
+ qnx6_put_page(page);
+ return fs32_to_cpu(sbi, de->de_inode);
+ }
+ qnx6_put_page(page);
+ return 0;
+}
+
+/*
+ * check if the filename is correct.
+ */
+static unsigned qnx6_match(struct super_block *s, int len, const char *name,
+ struct qnx6_dir_entry *de)
+{
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ if (memcmp(name, de->de_fname, len) == 0)
+ return fs32_to_cpu(sbi, de->de_inode);
+ return 0;
+}
+
+
+unsigned qnx6_find_entry(int len, struct inode *dir, const char *name,
+ struct page **res_page)
+{
+ struct super_block *s = dir->i_sb;
+ struct qnx6_inode_info *ei = QNX6_I(dir);
+ struct page *page = NULL;
+ unsigned long start, n;
+ unsigned long npages = dir_pages(dir);
+ unsigned ino;
+ struct qnx6_dir_entry *de;
+ struct qnx6_long_dir_entry *lde;
+
+ *res_page = NULL;
+
+ if (npages == 0)
+ return 0;
+ start = ei->i_dir_start_lookup;
+ if (start >= npages)
+ start = 0;
+ n = start;
+
+ do {
+ page = qnx6_get_page(dir, n);
+ if (!IS_ERR(page)) {
+ int limit = last_entry(dir, n);
+ int i;
+
+ de = (struct qnx6_dir_entry *)page_address(page);
+ for (i = 0; i < limit; i++, de++) {
+ if (len <= QNX6_SHORT_NAME_MAX) {
+ /* short filename */
+ if (len != de->de_size)
+ continue;
+ ino = qnx6_match(s, len, name, de);
+ if (ino)
+ goto found;
+ } else if (de->de_size == 0xff) {
+ /* deal with long filename */
+ lde = (struct qnx6_long_dir_entry *)de;
+ ino = qnx6_long_match(len,
+ name, lde, dir);
+ if (ino)
+ goto found;
+ } else
+ printk(KERN_ERR "qnx6: undefined "
+ "filename size in inode.\n");
+ }
+ qnx6_put_page(page);
+ }
+
+ if (++n >= npages)
+ n = 0;
+ } while (n != start);
+ return 0;
+
+found:
+ *res_page = page;
+ ei->i_dir_start_lookup = n;
+ return ino;
+}
+
+const struct file_operations qnx6_dir_operations = {
+ .llseek = generic_file_llseek,
+ .read = generic_read_dir,
+ .readdir = qnx6_readdir,
+ .fsync = generic_file_fsync,
+};
+
+const struct inode_operations qnx6_dir_inode_operations = {
+ .lookup = qnx6_lookup,
+};
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
new file mode 100644
index 0000000..e44012d
--- /dev/null
+++ b/fs/qnx6/inode.c
@@ -0,0 +1,698 @@
+/*
+ * QNX6 file system, Linux implementation.
+ *
+ * Version : 1.0.0
+ *
+ * History :
+ *
+ * 01-02-2012 by Kai Bankett (chaosman@ontika.net) : first release.
+ * 16-02-2012 pagemap extension by Al Viro
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/statfs.h>
+#include <linux/parser.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/crc32.h>
+#include <linux/mpage.h>
+#include "qnx6.h"
+
+static const struct super_operations qnx6_sops;
+
+static void qnx6_put_super(struct super_block *sb);
+static struct inode *qnx6_alloc_inode(struct super_block *sb);
+static void qnx6_destroy_inode(struct inode *inode);
+static int qnx6_remount(struct super_block *sb, int *flags, char *data);
+static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf);
+static int qnx6_show_options(struct seq_file *seq, struct dentry *root);
+
+static const struct super_operations qnx6_sops = {
+ .alloc_inode = qnx6_alloc_inode,
+ .destroy_inode = qnx6_destroy_inode,
+ .put_super = qnx6_put_super,
+ .statfs = qnx6_statfs,
+ .remount_fs = qnx6_remount,
+ .show_options = qnx6_show_options,
+};
+
+static int qnx6_show_options(struct seq_file *seq, struct dentry *root)
+{
+ struct super_block *sb = root->d_sb;
+ struct qnx6_sb_info *sbi = QNX6_SB(sb);
+
+ if (sbi->s_mount_opt & QNX6_MOUNT_MMI_FS)
+ seq_puts(seq, ",mmi_fs");
+ return 0;
+}
+
+static int qnx6_remount(struct super_block *sb, int *flags, char *data)
+{
+ *flags |= MS_RDONLY;
+ return 0;
+}
+
+static unsigned qnx6_get_devblock(struct super_block *sb, __fs32 block)
+{
+ struct qnx6_sb_info *sbi = QNX6_SB(sb);
+ return fs32_to_cpu(sbi, block) + sbi->s_blks_off;
+}
+
+static unsigned qnx6_block_map(struct inode *inode, unsigned iblock);
+
+static int qnx6_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh, int create)
+{
+ unsigned phys;
+
+ QNX6DEBUG((KERN_INFO "qnx6: qnx6_get_block inode=[%ld] iblock=[%ld]\n",
+ inode->i_ino, (unsigned long)iblock));
+
+ phys = qnx6_block_map(inode, iblock);
+ if (phys) {
+ /* logical block is before EOF */
+ map_bh(bh, inode->i_sb, phys);
+ }
+ return 0;
+}
+
+static int qnx6_check_blockptr(__fs32 ptr)
+{
+ if (ptr == ~(__fs32)0) {
+ printk(KERN_ERR "qnx6: hit unused blockpointer.\n");
+ return 0;
+ }
+ return 1;
+}
+
+static int qnx6_readpage(struct file *file, struct page *page)
+{
+ return mpage_readpage(page, qnx6_get_block);
+}
+
+static int qnx6_readpages(struct file *file, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ return mpage_readpages(mapping, pages, nr_pages, qnx6_get_block);
+}
+
+/*
+ * returns the block number for the no-th element in the tree
+ * inodebits requred as there are multiple inodes in one inode block
+ */
+static unsigned qnx6_block_map(struct inode *inode, unsigned no)
+{
+ struct super_block *s = inode->i_sb;
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ struct qnx6_inode_info *ei = QNX6_I(inode);
+ unsigned block = 0;
+ struct buffer_head *bh;
+ __fs32 ptr;
+ int levelptr;
+ int ptrbits = sbi->s_ptrbits;
+ int bitdelta;
+ u32 mask = (1 << ptrbits) - 1;
+ int depth = ei->di_filelevels;
+ int i;
+
+ bitdelta = ptrbits * depth;
+ levelptr = no >> bitdelta;
+
+ if (levelptr > QNX6_NO_DIRECT_POINTERS - 1) {
+ printk(KERN_ERR "qnx6:Requested file block number (%u) too big.",
+ no);
+ return 0;
+ }
+
+ block = qnx6_get_devblock(s, ei->di_block_ptr[levelptr]);
+
+ for (i = 0; i < depth; i++) {
+ bh = sb_bread(s, block);
+ if (!bh) {
+ printk(KERN_ERR "qnx6:Error reading block (%u)\n",
+ block);
+ return 0;
+ }
+ bitdelta -= ptrbits;
+ levelptr = (no >> bitdelta) & mask;
+ ptr = ((__fs32 *)bh->b_data)[levelptr];
+
+ if (!qnx6_check_blockptr(ptr))
+ return 0;
+
+ block = qnx6_get_devblock(s, ptr);
+ brelse(bh);
+ }
+ return block;
+}
+
+static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ struct super_block *sb = dentry->d_sb;
+ struct qnx6_sb_info *sbi = QNX6_SB(sb);
+ u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+
+ buf->f_type = sb->s_magic;
+ buf->f_bsize = sb->s_blocksize;
+ buf->f_blocks = fs32_to_cpu(sbi, sbi->sb->sb_num_blocks);
+ buf->f_bfree = fs32_to_cpu(sbi, sbi->sb->sb_free_blocks);
+ buf->f_files = fs32_to_cpu(sbi, sbi->sb->sb_num_inodes);
+ buf->f_ffree = fs32_to_cpu(sbi, sbi->sb->sb_free_inodes);
+ buf->f_bavail = buf->f_bfree;
+ buf->f_namelen = QNX6_LONG_NAME_MAX;
+ buf->f_fsid.val[0] = (u32)id;
+ buf->f_fsid.val[1] = (u32)(id >> 32);
+
+ return 0;
+}
+
+/*
+ * Check the root directory of the filesystem to make sure
+ * it really _is_ a qnx6 filesystem, and to check the size
+ * of the directory entry.
+ */
+static const char *qnx6_checkroot(struct super_block *s)
+{
+ static char match_root[2][3] = {".\0\0", "..\0"};
+ int i, error = 0;
+ struct qnx6_dir_entry *dir_entry;
+ struct inode *root = s->s_root->d_inode;
+ struct address_space *mapping = root->i_mapping;
+ struct page *page = read_mapping_page(mapping, 0, NULL);
+ if (IS_ERR(page))
+ return "error reading root directory";
+ kmap(page);
+ dir_entry = page_address(page);
+ for (i = 0; i < 2; i++) {
+ /* maximum 3 bytes - due to match_root limitation */
+ if (strncmp(dir_entry[i].de_fname, match_root[i], 3))
+ error = 1;
+ }
+ qnx6_put_page(page);
+ if (error)
+ return "error reading root directory.";
+ return NULL;
+}
+
+#ifdef CONFIG_QNX6FS_DEBUG
+void qnx6_superblock_debug(struct qnx6_super_block *sb, struct super_block *s)
+{
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+
+ QNX6DEBUG((KERN_INFO "magic: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_magic)));
+ QNX6DEBUG((KERN_INFO "checksum: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_checksum)));
+ QNX6DEBUG((KERN_INFO "serial: %llx\n",
+ fs64_to_cpu(sbi, sb->sb_serial)));
+ QNX6DEBUG((KERN_INFO "flags: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_flags)));
+ QNX6DEBUG((KERN_INFO "blocksize: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_blocksize)));
+ QNX6DEBUG((KERN_INFO "num_inodes: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_num_inodes)));
+ QNX6DEBUG((KERN_INFO "free_inodes: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_free_inodes)));
+ QNX6DEBUG((KERN_INFO "num_blocks: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_num_blocks)));
+ QNX6DEBUG((KERN_INFO "free_blocks: %08x\n",
+ fs32_to_cpu(sbi, sb->sb_free_blocks)));
+ QNX6DEBUG((KERN_INFO "inode_levels: %02x\n",
+ sb->Inode.levels));
+}
+#endif
+
+enum {
+ Opt_mmifs,
+ Opt_err
+};
+
+static const match_table_t tokens = {
+ {Opt_mmifs, "mmi_fs"},
+ {Opt_err, NULL}
+};
+
+static int qnx6_parse_options(char *options, struct super_block *sb)
+{
+ char *p;
+ struct qnx6_sb_info *sbi = QNX6_SB(sb);
+ substring_t args[MAX_OPT_ARGS];
+
+ if (!options)
+ return 1;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_mmifs:
+ set_opt(sbi->s_mount_opt, MMI_FS);
+ break;
+ default:
+ return 0;
+ }
+ }
+ return 1;
+}
+
+static struct buffer_head *qnx6_check_first_superblock(struct super_block *s,
+ int offset, int silent)
+{
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ struct buffer_head *bh;
+ struct qnx6_super_block *sb;
+
+ /* Check the superblock signatures
+ start with the first superblock */
+ bh = sb_bread(s, offset);
+ if (!bh) {
+ printk(KERN_ERR "qnx6: unable to read the first superblock\n");
+ return NULL;
+ }
+ sb = (struct qnx6_super_block *)bh->b_data;
+ if (fs32_to_cpu(sbi, sb->sb_magic) != QNX6_SUPER_MAGIC) {
+ sbi->s_bytesex = BYTESEX_BE;
+ if (fs32_to_cpu(sbi, sb->sb_magic) == QNX6_SUPER_MAGIC) {
+ /* we got a big endian fs */
+ QNX6DEBUG((KERN_INFO "qnx6: fs got different"
+ " endianess.\n"));
+ return bh;
+ } else
+ sbi->s_bytesex = BYTESEX_LE;
+ if (!silent) {
+ if (offset == 0) {
+ printk(KERN_ERR "qnx6: wrong signature (magic)"
+ " in superblock #1.\n");
+ } else {
+ printk(KERN_INFO "qnx6: wrong signature (magic)"
+ " at position (0x%lx) - will try"
+ " alternative position (0x0000).\n",
+ offset * s->s_blocksize);
+ }
+ }
+ brelse(bh);
+ return NULL;
+ }
+ return bh;
+}
+
+static struct inode *qnx6_private_inode(struct super_block *s,
+ struct qnx6_root_node *p);
+
+static int qnx6_fill_super(struct super_block *s, void *data, int silent)
+{
+ struct buffer_head *bh1 = NULL, *bh2 = NULL;
+ struct qnx6_super_block *sb1 = NULL, *sb2 = NULL;
+ struct qnx6_sb_info *sbi;
+ struct inode *root;
+ const char *errmsg;
+ struct qnx6_sb_info *qs;
+ int ret = -EINVAL;
+ u64 offset;
+ int bootblock_offset = QNX6_BOOTBLOCK_SIZE;
+
+ qs = kzalloc(sizeof(struct qnx6_sb_info), GFP_KERNEL);
+ if (!qs)
+ return -ENOMEM;
+ s->s_fs_info = qs;
+
+ /* Superblock always is 512 Byte long */
+ if (!sb_set_blocksize(s, QNX6_SUPERBLOCK_SIZE)) {
+ printk(KERN_ERR "qnx6: unable to set blocksize\n");
+ goto outnobh;
+ }
+
+ /* parse the mount-options */
+ if (!qnx6_parse_options((char *) data, s)) {
+ printk(KERN_ERR "qnx6: invalid mount options.\n");
+ goto outnobh;
+ }
+ if (test_opt(s, MMI_FS)) {
+ sb1 = qnx6_mmi_fill_super(s, silent);
+ if (sb1)
+ goto mmi_success;
+ else
+ goto outnobh;
+ }
+ sbi = QNX6_SB(s);
+ sbi->s_bytesex = BYTESEX_LE;
+ /* Check the superblock signatures
+ start with the first superblock */
+ bh1 = qnx6_check_first_superblock(s,
+ bootblock_offset / QNX6_SUPERBLOCK_SIZE, silent);
+ if (!bh1) {
+ /* try again without bootblock offset */
+ bh1 = qnx6_check_first_superblock(s, 0, silent);
+ if (!bh1) {
+ printk(KERN_ERR "qnx6: unable to read the first superblock\n");
+ goto outnobh;
+ }
+ /* seems that no bootblock at partition start */
+ bootblock_offset = 0;
+ }
+ sb1 = (struct qnx6_super_block *)bh1->b_data;
+
+#ifdef CONFIG_QNX6FS_DEBUG
+ qnx6_superblock_debug(sb1, s);
+#endif
+
+ /* checksum check - start at byte 8 and end at byte 512 */
+ if (fs32_to_cpu(sbi, sb1->sb_checksum) !=
+ crc32_be(0, (char *)(bh1->b_data + 8), 504)) {
+ printk(KERN_ERR "qnx6: superblock #1 checksum error\n");
+ goto out;
+ }
+
+ /* set new blocksize */
+ if (!sb_set_blocksize(s, fs32_to_cpu(sbi, sb1->sb_blocksize))) {
+ printk(KERN_ERR "qnx6: unable to set blocksize\n");
+ goto out;
+ }
+ /* blocksize invalidates bh - pull it back in */
+ brelse(bh1);
+ bh1 = sb_bread(s, bootblock_offset >> s->s_blocksize_bits);
+ if (!bh1)
+ goto outnobh;
+ sb1 = (struct qnx6_super_block *)bh1->b_data;
+
+ /* calculate second superblock blocknumber */
+ offset = fs32_to_cpu(sbi, sb1->sb_num_blocks) +
+ (bootblock_offset >> s->s_blocksize_bits) +
+ (QNX6_SUPERBLOCK_AREA >> s->s_blocksize_bits);
+
+ /* set bootblock offset */
+ sbi->s_blks_off = (bootblock_offset >> s->s_blocksize_bits) +
+ (QNX6_SUPERBLOCK_AREA >> s->s_blocksize_bits);
+
+ /* next the second superblock */
+ bh2 = sb_bread(s, offset);
+ if (!bh2) {
+ printk(KERN_ERR "qnx6: unable to read the second superblock\n");
+ goto out;
+ }
+ sb2 = (struct qnx6_super_block *)bh2->b_data;
+ if (fs32_to_cpu(sbi, sb2->sb_magic) != QNX6_SUPER_MAGIC) {
+ if (!silent)
+ printk(KERN_ERR "qnx6: wrong signature (magic)"
+ " in superblock #2.\n");
+ goto out;
+ }
+
+ /* checksum check - start at byte 8 and end at byte 512 */
+ if (fs32_to_cpu(sbi, sb2->sb_checksum) !=
+ crc32_be(0, (char *)(bh2->b_data + 8), 504)) {
+ printk(KERN_ERR "qnx6: superblock #2 checksum error\n");
+ goto out;
+ }
+
+ if (fs64_to_cpu(sbi, sb1->sb_serial) >=
+ fs64_to_cpu(sbi, sb2->sb_serial)) {
+ /* superblock #1 active */
+ sbi->sb_buf = bh1;
+ sbi->sb = (struct qnx6_super_block *)bh1->b_data;
+ brelse(bh2);
+ printk(KERN_INFO "qnx6: superblock #1 active\n");
+ } else {
+ /* superblock #2 active */
+ sbi->sb_buf = bh2;
+ sbi->sb = (struct qnx6_super_block *)bh2->b_data;
+ brelse(bh1);
+ printk(KERN_INFO "qnx6: superblock #2 active\n");
+ }
+mmi_success:
+ /* sanity check - limit maximum indirect pointer levels */
+ if (sb1->Inode.levels > QNX6_PTR_MAX_LEVELS) {
+ printk(KERN_ERR "qnx6: too many inode levels (max %i, sb %i)\n",
+ QNX6_PTR_MAX_LEVELS, sb1->Inode.levels);
+ goto out;
+ }
+ if (sb1->Longfile.levels > QNX6_PTR_MAX_LEVELS) {
+ printk(KERN_ERR "qnx6: too many longfilename levels"
+ " (max %i, sb %i)\n",
+ QNX6_PTR_MAX_LEVELS, sb1->Longfile.levels);
+ goto out;
+ }
+ s->s_op = &qnx6_sops;
+ s->s_magic = QNX6_SUPER_MAGIC;
+ s->s_flags |= MS_RDONLY; /* Yup, read-only yet */
+
+ /* ease the later tree level calculations */
+ sbi = QNX6_SB(s);
+ sbi->s_ptrbits = ilog2(s->s_blocksize / 4);
+ sbi->inodes = qnx6_private_inode(s, &sb1->Inode);
+ if (!sbi->inodes)
+ goto out;
+ sbi->longfile = qnx6_private_inode(s, &sb1->Longfile);
+ if (!sbi->longfile)
+ goto out1;
+
+ /* prefetch root inode */
+ root = qnx6_iget(s, QNX6_ROOT_INO);
+ if (IS_ERR(root)) {
+ printk(KERN_ERR "qnx6: get inode failed\n");
+ ret = PTR_ERR(root);
+ goto out2;
+ }
+
+ ret = -ENOMEM;
+ s->s_root = d_make_root(root);
+ if (!s->s_root)
+ goto out2;
+
+ ret = -EINVAL;
+ errmsg = qnx6_checkroot(s);
+ if (errmsg != NULL) {
+ if (!silent)
+ printk(KERN_ERR "qnx6: %s\n", errmsg);
+ goto out3;
+ }
+ return 0;
+
+out3:
+ dput(s->s_root);
+ s->s_root = NULL;
+out2:
+ iput(sbi->longfile);
+out1:
+ iput(sbi->inodes);
+out:
+ if (bh1)
+ brelse(bh1);
+ if (bh2)
+ brelse(bh2);
+outnobh:
+ kfree(qs);
+ s->s_fs_info = NULL;
+ return ret;
+}
+
+static void qnx6_put_super(struct super_block *sb)
+{
+ struct qnx6_sb_info *qs = QNX6_SB(sb);
+ brelse(qs->sb_buf);
+ iput(qs->longfile);
+ iput(qs->inodes);
+ kfree(qs);
+ sb->s_fs_info = NULL;
+ return;
+}
+
+static sector_t qnx6_bmap(struct address_space *mapping, sector_t block)
+{
+ return generic_block_bmap(mapping, block, qnx6_get_block);
+}
+static const struct address_space_operations qnx6_aops = {
+ .readpage = qnx6_readpage,
+ .readpages = qnx6_readpages,
+ .bmap = qnx6_bmap
+};
+
+static struct inode *qnx6_private_inode(struct super_block *s,
+ struct qnx6_root_node *p)
+{
+ struct inode *inode = new_inode(s);
+ if (inode) {
+ struct qnx6_inode_info *ei = QNX6_I(inode);
+ struct qnx6_sb_info *sbi = QNX6_SB(s);
+ inode->i_size = fs64_to_cpu(sbi, p->size);
+ memcpy(ei->di_block_ptr, p->ptr, sizeof(p->ptr));
+ ei->di_filelevels = p->levels;
+ inode->i_mode = S_IFREG | S_IRUSR; /* probably wrong */
+ inode->i_mapping->a_ops = &qnx6_aops;
+ }
+ return inode;
+}
+
+struct inode *qnx6_iget(struct super_block *sb, unsigned ino)
+{
+ struct qnx6_sb_info *sbi = QNX6_SB(sb);
+ struct qnx6_inode_entry *raw_inode;
+ struct inode *inode;
+ struct qnx6_inode_info *ei;
+ struct address_space *mapping;
+ struct page *page;
+ u32 n, offs;
+
+ inode = iget_locked(sb, ino);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ if (!(inode->i_state & I_NEW))
+ return inode;
+
+ ei = QNX6_I(inode);
+
+ inode->i_mode = 0;
+
+ if (ino == 0) {
+ printk(KERN_ERR "qnx6: bad inode number on dev %s: %u is "
+ "out of range\n",
+ sb->s_id, ino);
+ iget_failed(inode);
+ return ERR_PTR(-EIO);
+ }
+ n = (ino - 1) >> (PAGE_CACHE_SHIFT - QNX6_INODE_SIZE_BITS);
+ offs = (ino - 1) & (~PAGE_CACHE_MASK >> QNX6_INODE_SIZE_BITS);
+ mapping = sbi->inodes->i_mapping;
+ page = read_mapping_page(mapping, n, NULL);
+ if (IS_ERR(page)) {
+ printk(KERN_ERR "qnx6: major problem: unable to read inode from "
+ "dev %s\n", sb->s_id);
+ iget_failed(inode);
+ return ERR_CAST(page);
+ }
+ kmap(page);
+ raw_inode = ((struct qnx6_inode_entry *)page_address(page)) + offs;
+
+ inode->i_mode = fs16_to_cpu(sbi, raw_inode->di_mode);
+ inode->i_uid = (uid_t)fs32_to_cpu(sbi, raw_inode->di_uid);
+ inode->i_gid = (gid_t)fs32_to_cpu(sbi, raw_inode->di_gid);
+ inode->i_size = fs64_to_cpu(sbi, raw_inode->di_size);
+ inode->i_mtime.tv_sec = fs32_to_cpu(sbi, raw_inode->di_mtime);
+ inode->i_mtime.tv_nsec = 0;
+ inode->i_atime.tv_sec = fs32_to_cpu(sbi, raw_inode->di_atime);
+ inode->i_atime.tv_nsec = 0;
+ inode->i_ctime.tv_sec = fs32_to_cpu(sbi, raw_inode->di_ctime);
+ inode->i_ctime.tv_nsec = 0;
+
+ /* calc blocks based on 512 byte blocksize */
+ inode->i_blocks = (inode->i_size + 511) >> 9;
+
+ memcpy(&ei->di_block_ptr, &raw_inode->di_block_ptr,
+ sizeof(raw_inode->di_block_ptr));
+ ei->di_filelevels = raw_inode->di_filelevels;
+
+ if (S_ISREG(inode->i_mode)) {
+ inode->i_fop = &generic_ro_fops;
+ inode->i_mapping->a_ops = &qnx6_aops;
+ } else if (S_ISDIR(inode->i_mode)) {
+ inode->i_op = &qnx6_dir_inode_operations;
+ inode->i_fop = &qnx6_dir_operations;
+ inode->i_mapping->a_ops = &qnx6_aops;
+ } else if (S_ISLNK(inode->i_mode)) {
+ inode->i_op = &page_symlink_inode_operations;
+ inode->i_mapping->a_ops = &qnx6_aops;
+ } else
+ init_special_inode(inode, inode->i_mode, 0);
+ qnx6_put_page(page);
+ unlock_new_inode(inode);
+ return inode;
+}
+
+static struct kmem_cache *qnx6_inode_cachep;
+
+static struct inode *qnx6_alloc_inode(struct super_block *sb)
+{
+ struct qnx6_inode_info *ei;
+ ei = kmem_cache_alloc(qnx6_inode_cachep, GFP_KERNEL);
+ if (!ei)
+ return NULL;
+ return &ei->vfs_inode;
+}
+
+static void qnx6_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(qnx6_inode_cachep, QNX6_I(inode));
+}
+
+static void qnx6_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, qnx6_i_callback);
+}
+
+static void init_once(void *foo)
+{
+ struct qnx6_inode_info *ei = (struct qnx6_inode_info *) foo;
+
+ inode_init_once(&ei->vfs_inode);
+}
+
+static int init_inodecache(void)
+{
+ qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache",
+ sizeof(struct qnx6_inode_info),
+ 0, (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD),
+ init_once);
+ if (!qnx6_inode_cachep)
+ return -ENOMEM;
+ return 0;
+}
+
+static void destroy_inodecache(void)
+{
+ kmem_cache_destroy(qnx6_inode_cachep);
+}
+
+static struct dentry *qnx6_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ return mount_bdev(fs_type, flags, dev_name, data, qnx6_fill_super);
+}
+
+static struct file_system_type qnx6_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "qnx6",
+ .mount = qnx6_mount,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+
+static int __init init_qnx6_fs(void)
+{
+ int err;
+
+ err = init_inodecache();
+ if (err)
+ return err;
+
+ err = register_filesystem(&qnx6_fs_type);
+ if (err) {
+ destroy_inodecache();
+ return err;
+ }
+
+ printk(KERN_INFO "QNX6 filesystem 1.0.0 registered.\n");
+ return 0;
+}
+
+static void __exit exit_qnx6_fs(void)
+{
+ unregister_filesystem(&qnx6_fs_type);
+ destroy_inodecache();
+}
+
+module_init(init_qnx6_fs)
+module_exit(exit_qnx6_fs)
+MODULE_LICENSE("GPL");
diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c
new file mode 100644
index 0000000..8a97289
--- /dev/null
+++ b/fs/qnx6/namei.c
@@ -0,0 +1,42 @@
+/*
+ * QNX6 file system, Linux implementation.
+ *
+ * Version : 1.0.0
+ *
+ * History :
+ *
+ * 01-02-2012 by Kai Bankett (chaosman@ontika.net) : first release.
+ * 16-02-2012 pagemap extension by Al Viro
+ *
+ */
+
+#include "qnx6.h"
+
+struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ unsigned ino;
+ struct page *page;
+ struct inode *foundinode = NULL;
+ const char *name = dentry->d_name.name;
+ int len = dentry->d_name.len;
+
+ if (len > QNX6_LONG_NAME_MAX)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ ino = qnx6_find_entry(len, dir, name, &page);
+ if (ino) {
+ foundinode = qnx6_iget(dir->i_sb, ino);
+ qnx6_put_page(page);
+ if (IS_ERR(foundinode)) {
+ QNX6DEBUG((KERN_ERR "qnx6: lookup->iget -> "
+ " error %ld\n", PTR_ERR(foundinode)));
+ return ERR_CAST(foundinode);
+ }
+ } else {
+ QNX6DEBUG((KERN_INFO "qnx6_lookup: not found %s\n", name));
+ return NULL;
+ }
+ d_add(dentry, foundinode);
+ return NULL;
+}
diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h
new file mode 100644
index 0000000..6c5e02a
--- /dev/null
+++ b/fs/qnx6/qnx6.h
@@ -0,0 +1,135 @@
+/*
+ * QNX6 file system, Linux implementation.
+ *
+ * Version : 1.0.0
+ *
+ * History :
+ *
+ * 01-02-2012 by Kai Bankett (chaosman@ontika.net) : first release.
+ * 16-02-2012 page map extension by Al Viro
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+
+typedef __u16 __bitwise __fs16;
+typedef __u32 __bitwise __fs32;
+typedef __u64 __bitwise __fs64;
+
+#include <linux/qnx6_fs.h>
+
+#ifdef CONFIG_QNX6FS_DEBUG
+#define QNX6DEBUG(X) printk X
+#else
+#define QNX6DEBUG(X) (void) 0
+#endif
+
+struct qnx6_sb_info {
+ struct buffer_head *sb_buf; /* superblock buffer */
+ struct qnx6_super_block *sb; /* our superblock */
+ int s_blks_off; /* blkoffset fs-startpoint */
+ int s_ptrbits; /* indirect pointer bitfield */
+ unsigned long s_mount_opt; /* all mount options */
+ int s_bytesex; /* holds endianess info */
+ struct inode * inodes;
+ struct inode * longfile;
+};
+
+struct qnx6_inode_info {
+ __fs32 di_block_ptr[QNX6_NO_DIRECT_POINTERS];
+ __u8 di_filelevels;
+ __u32 i_dir_start_lookup;
+ struct inode vfs_inode;
+};
+
+extern struct inode *qnx6_iget(struct super_block *sb, unsigned ino);
+extern struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd);
+
+#ifdef CONFIG_QNX6FS_DEBUG
+extern void qnx6_superblock_debug(struct qnx6_super_block *,
+ struct super_block *);
+#endif
+
+extern const struct inode_operations qnx6_dir_inode_operations;
+extern const struct file_operations qnx6_dir_operations;
+
+static inline struct qnx6_sb_info *QNX6_SB(struct super_block *sb)
+{
+ return sb->s_fs_info;
+}
+
+static inline struct qnx6_inode_info *QNX6_I(struct inode *inode)
+{
+ return container_of(inode, struct qnx6_inode_info, vfs_inode);
+}
+
+#define clear_opt(o, opt) (o &= ~(QNX6_MOUNT_##opt))
+#define set_opt(o, opt) (o |= (QNX6_MOUNT_##opt))
+#define test_opt(sb, opt) (QNX6_SB(sb)->s_mount_opt & \
+ QNX6_MOUNT_##opt)
+enum {
+ BYTESEX_LE,
+ BYTESEX_BE,
+};
+
+static inline __u64 fs64_to_cpu(struct qnx6_sb_info *sbi, __fs64 n)
+{
+ if (sbi->s_bytesex == BYTESEX_LE)
+ return le64_to_cpu((__force __le64)n);
+ else
+ return be64_to_cpu((__force __be64)n);
+}
+
+static inline __fs64 cpu_to_fs64(struct qnx6_sb_info *sbi, __u64 n)
+{
+ if (sbi->s_bytesex == BYTESEX_LE)
+ return (__force __fs64)cpu_to_le64(n);
+ else
+ return (__force __fs64)cpu_to_be64(n);
+}
+
+static inline __u32 fs32_to_cpu(struct qnx6_sb_info *sbi, __fs32 n)
+{
+ if (sbi->s_bytesex == BYTESEX_LE)
+ return le32_to_cpu((__force __le32)n);
+ else
+ return be32_to_cpu((__force __be32)n);
+}
+
+static inline __fs32 cpu_to_fs32(struct qnx6_sb_info *sbi, __u32 n)
+{
+ if (sbi->s_bytesex == BYTESEX_LE)
+ return (__force __fs32)cpu_to_le32(n);
+ else
+ return (__force __fs32)cpu_to_be32(n);
+}
+
+static inline __u16 fs16_to_cpu(struct qnx6_sb_info *sbi, __fs16 n)
+{
+ if (sbi->s_bytesex == BYTESEX_LE)
+ return le16_to_cpu((__force __le16)n);
+ else
+ return be16_to_cpu((__force __be16)n);
+}
+
+static inline __fs16 cpu_to_fs16(struct qnx6_sb_info *sbi, __u16 n)
+{
+ if (sbi->s_bytesex == BYTESEX_LE)
+ return (__force __fs16)cpu_to_le16(n);
+ else
+ return (__force __fs16)cpu_to_be16(n);
+}
+
+extern struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s,
+ int silent);
+
+static inline void qnx6_put_page(struct page *page)
+{
+ kunmap(page);
+ page_cache_release(page);
+}
+
+extern unsigned qnx6_find_entry(int len, struct inode *dir, const char *name,
+ struct page **res_page);
diff --git a/fs/qnx6/super_mmi.c b/fs/qnx6/super_mmi.c
new file mode 100644
index 0000000..29c32cb
--- /dev/null
+++ b/fs/qnx6/super_mmi.c
@@ -0,0 +1,150 @@
+/*
+ * QNX6 file system, Linux implementation.
+ *
+ * Version : 1.0.0
+ *
+ * History :
+ *
+ * 01-02-2012 by Kai Bankett (chaosman@ontika.net) : first release.
+ *
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/slab.h>
+#include <linux/crc32.h>
+#include "qnx6.h"
+
+static void qnx6_mmi_copy_sb(struct qnx6_super_block *qsb,
+ struct qnx6_mmi_super_block *sb)
+{
+ qsb->sb_magic = sb->sb_magic;
+ qsb->sb_checksum = sb->sb_checksum;
+ qsb->sb_serial = sb->sb_serial;
+ qsb->sb_blocksize = sb->sb_blocksize;
+ qsb->sb_num_inodes = sb->sb_num_inodes;
+ qsb->sb_free_inodes = sb->sb_free_inodes;
+ qsb->sb_num_blocks = sb->sb_num_blocks;
+ qsb->sb_free_blocks = sb->sb_free_blocks;
+
+ /* the rest of the superblock is the same */
+ memcpy(&qsb->Inode, &sb->Inode, sizeof(sb->Inode));
+ memcpy(&qsb->Bitmap, &sb->Bitmap, sizeof(sb->Bitmap));
+ memcpy(&qsb->Longfile, &sb->Longfile, sizeof(sb->Longfile));
+}
+
+struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
+{
+ struct buffer_head *bh1, *bh2 = NULL;
+ struct qnx6_mmi_super_block *sb1, *sb2;
+ struct qnx6_super_block *qsb = NULL;
+ struct qnx6_sb_info *sbi;
+ __u64 offset;
+
+ /* Check the superblock signatures
+ start with the first superblock */
+ bh1 = sb_bread(s, 0);
+ if (!bh1) {
+ printk(KERN_ERR "qnx6: Unable to read first mmi superblock\n");
+ return NULL;
+ }
+ sb1 = (struct qnx6_mmi_super_block *)bh1->b_data;
+ sbi = QNX6_SB(s);
+ if (fs32_to_cpu(sbi, sb1->sb_magic) != QNX6_SUPER_MAGIC) {
+ if (!silent) {
+ printk(KERN_ERR "qnx6: wrong signature (magic) in"
+ " superblock #1.\n");
+ goto out;
+ }
+ }
+
+ /* checksum check - start at byte 8 and end at byte 512 */
+ if (fs32_to_cpu(sbi, sb1->sb_checksum) !=
+ crc32_be(0, (char *)(bh1->b_data + 8), 504)) {
+ printk(KERN_ERR "qnx6: superblock #1 checksum error\n");
+ goto out;
+ }
+
+ /* calculate second superblock blocknumber */
+ offset = fs32_to_cpu(sbi, sb1->sb_num_blocks) + QNX6_SUPERBLOCK_AREA /
+ fs32_to_cpu(sbi, sb1->sb_blocksize);
+
+ /* set new blocksize */
+ if (!sb_set_blocksize(s, fs32_to_cpu(sbi, sb1->sb_blocksize))) {
+ printk(KERN_ERR "qnx6: unable to set blocksize\n");
+ goto out;
+ }
+ /* blocksize invalidates bh - pull it back in */
+ brelse(bh1);
+ bh1 = sb_bread(s, 0);
+ if (!bh1)
+ goto out;
+ sb1 = (struct qnx6_mmi_super_block *)bh1->b_data;
+
+ /* read second superblock */
+ bh2 = sb_bread(s, offset);
+ if (!bh2) {
+ printk(KERN_ERR "qnx6: unable to read the second superblock\n");
+ goto out;
+ }
+ sb2 = (struct qnx6_mmi_super_block *)bh2->b_data;
+ if (fs32_to_cpu(sbi, sb2->sb_magic) != QNX6_SUPER_MAGIC) {
+ if (!silent)
+ printk(KERN_ERR "qnx6: wrong signature (magic) in"
+ " superblock #2.\n");
+ goto out;
+ }
+
+ /* checksum check - start at byte 8 and end at byte 512 */
+ if (fs32_to_cpu(sbi, sb2->sb_checksum)
+ != crc32_be(0, (char *)(bh2->b_data + 8), 504)) {
+ printk(KERN_ERR "qnx6: superblock #1 checksum error\n");
+ goto out;
+ }
+
+ qsb = kmalloc(sizeof(*qsb), GFP_KERNEL);
+ if (!qsb) {
+ printk(KERN_ERR "qnx6: unable to allocate memory.\n");
+ goto out;
+ }
+
+ if (fs64_to_cpu(sbi, sb1->sb_serial) >
+ fs64_to_cpu(sbi, sb2->sb_serial)) {
+ /* superblock #1 active */
+ qnx6_mmi_copy_sb(qsb, sb1);
+#ifdef CONFIG_QNX6FS_DEBUG
+ qnx6_superblock_debug(qsb, s);
+#endif
+ memcpy(bh1->b_data, qsb, sizeof(struct qnx6_super_block));
+
+ sbi->sb_buf = bh1;
+ sbi->sb = (struct qnx6_super_block *)bh1->b_data;
+ brelse(bh2);
+ printk(KERN_INFO "qnx6: superblock #1 active\n");
+ } else {
+ /* superblock #2 active */
+ qnx6_mmi_copy_sb(qsb, sb2);
+#ifdef CONFIG_QNX6FS_DEBUG
+ qnx6_superblock_debug(qsb, s);
+#endif
+ memcpy(bh2->b_data, qsb, sizeof(struct qnx6_super_block));
+
+ sbi->sb_buf = bh2;
+ sbi->sb = (struct qnx6_super_block *)bh2->b_data;
+ brelse(bh1);
+ printk(KERN_INFO "qnx6: superblock #2 active\n");
+ }
+ kfree(qsb);
+
+ /* offset for mmi_fs is just SUPERBLOCK_AREA bytes */
+ sbi->s_blks_off = QNX6_SUPERBLOCK_AREA / s->s_blocksize;
+
+ /* success */
+ return sbi->sb;
+
+out:
+ if (bh1 != NULL)
+ brelse(bh1);
+ if (bh2 != NULL)
+ brelse(bh2);
+ return NULL;
+}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 5ec59b2..d69a1d1 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -71,6 +71,7 @@
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
+#include <linux/sched.h>
#include <linux/kmod.h>
#include <linux/namei.h>
#include <linux/capability.h>
@@ -1109,6 +1110,13 @@ static void dquot_decr_space(struct dquot *dquot, qsize_t number)
clear_bit(DQ_BLKS_B, &dquot->dq_flags);
}
+struct dquot_warn {
+ struct super_block *w_sb;
+ qid_t w_dq_id;
+ short w_dq_type;
+ short w_type;
+};
+
static int warning_issued(struct dquot *dquot, const int warntype)
{
int flag = (warntype == QUOTA_NL_BHARDWARN ||
@@ -1124,41 +1132,42 @@ static int warning_issued(struct dquot *dquot, const int warntype)
#ifdef CONFIG_PRINT_QUOTA_WARNING
static int flag_print_warnings = 1;
-static int need_print_warning(struct dquot *dquot)
+static int need_print_warning(struct dquot_warn *warn)
{
if (!flag_print_warnings)
return 0;
- switch (dquot->dq_type) {
+ switch (warn->w_dq_type) {
case USRQUOTA:
- return current_fsuid() == dquot->dq_id;
+ return current_fsuid() == warn->w_dq_id;
case GRPQUOTA:
- return in_group_p(dquot->dq_id);
+ return in_group_p(warn->w_dq_id);
}
return 0;
}
/* Print warning to user which exceeded quota */
-static void print_warning(struct dquot *dquot, const int warntype)
+static void print_warning(struct dquot_warn *warn)
{
char *msg = NULL;
struct tty_struct *tty;
+ int warntype = warn->w_type;
if (warntype == QUOTA_NL_IHARDBELOW ||
warntype == QUOTA_NL_ISOFTBELOW ||
warntype == QUOTA_NL_BHARDBELOW ||
- warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(dquot))
+ warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(warn))
return;
tty = get_current_tty();
if (!tty)
return;
- tty_write_message(tty, dquot->dq_sb->s_id);
+ tty_write_message(tty, warn->w_sb->s_id);
if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN)
tty_write_message(tty, ": warning, ");
else
tty_write_message(tty, ": write failed, ");
- tty_write_message(tty, quotatypes[dquot->dq_type]);
+ tty_write_message(tty, quotatypes[warn->w_dq_type]);
switch (warntype) {
case QUOTA_NL_IHARDWARN:
msg = " file limit reached.\r\n";
@@ -1184,26 +1193,34 @@ static void print_warning(struct dquot *dquot, const int warntype)
}
#endif
+static void prepare_warning(struct dquot_warn *warn, struct dquot *dquot,
+ int warntype)
+{
+ if (warning_issued(dquot, warntype))
+ return;
+ warn->w_type = warntype;
+ warn->w_sb = dquot->dq_sb;
+ warn->w_dq_id = dquot->dq_id;
+ warn->w_dq_type = dquot->dq_type;
+}
+
/*
* Write warnings to the console and send warning messages over netlink.
*
- * Note that this function can sleep.
+ * Note that this function can call into tty and networking code.
*/
-static void flush_warnings(struct dquot *const *dquots, char *warntype)
+static void flush_warnings(struct dquot_warn *warn)
{
- struct dquot *dq;
int i;
for (i = 0; i < MAXQUOTAS; i++) {
- dq = dquots[i];
- if (dq && warntype[i] != QUOTA_NL_NOWARN &&
- !warning_issued(dq, warntype[i])) {
+ if (warn[i].w_type == QUOTA_NL_NOWARN)
+ continue;
#ifdef CONFIG_PRINT_QUOTA_WARNING
- print_warning(dq, warntype[i]);
+ print_warning(&warn[i]);
#endif
- quota_send_warning(dq->dq_type, dq->dq_id,
- dq->dq_sb->s_dev, warntype[i]);
- }
+ quota_send_warning(warn[i].w_dq_type, warn[i].w_dq_id,
+ warn[i].w_sb->s_dev, warn[i].w_type);
}
}
@@ -1217,11 +1234,11 @@ static int ignore_hardlimit(struct dquot *dquot)
}
/* needs dq_data_lock */
-static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
+static int check_idq(struct dquot *dquot, qsize_t inodes,
+ struct dquot_warn *warn)
{
qsize_t newinodes = dquot->dq_dqb.dqb_curinodes + inodes;
- *warntype = QUOTA_NL_NOWARN;
if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type) ||
test_bit(DQ_FAKE_B, &dquot->dq_flags))
return 0;
@@ -1229,7 +1246,7 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
if (dquot->dq_dqb.dqb_ihardlimit &&
newinodes > dquot->dq_dqb.dqb_ihardlimit &&
!ignore_hardlimit(dquot)) {
- *warntype = QUOTA_NL_IHARDWARN;
+ prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN);
return -EDQUOT;
}
@@ -1238,14 +1255,14 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
dquot->dq_dqb.dqb_itime &&
get_seconds() >= dquot->dq_dqb.dqb_itime &&
!ignore_hardlimit(dquot)) {
- *warntype = QUOTA_NL_ISOFTLONGWARN;
+ prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN);
return -EDQUOT;
}
if (dquot->dq_dqb.dqb_isoftlimit &&
newinodes > dquot->dq_dqb.dqb_isoftlimit &&
dquot->dq_dqb.dqb_itime == 0) {
- *warntype = QUOTA_NL_ISOFTWARN;
+ prepare_warning(warn, dquot, QUOTA_NL_ISOFTWARN);
dquot->dq_dqb.dqb_itime = get_seconds() +
sb_dqopt(dquot->dq_sb)->info[dquot->dq_type].dqi_igrace;
}
@@ -1254,12 +1271,12 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
}
/* needs dq_data_lock */
-static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *warntype)
+static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc,
+ struct dquot_warn *warn)
{
qsize_t tspace;
struct super_block *sb = dquot->dq_sb;
- *warntype = QUOTA_NL_NOWARN;
if (!sb_has_quota_limits_enabled(sb, dquot->dq_type) ||
test_bit(DQ_FAKE_B, &dquot->dq_flags))
return 0;
@@ -1271,7 +1288,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
tspace > dquot->dq_dqb.dqb_bhardlimit &&
!ignore_hardlimit(dquot)) {
if (!prealloc)
- *warntype = QUOTA_NL_BHARDWARN;
+ prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN);
return -EDQUOT;
}
@@ -1281,7 +1298,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
get_seconds() >= dquot->dq_dqb.dqb_btime &&
!ignore_hardlimit(dquot)) {
if (!prealloc)
- *warntype = QUOTA_NL_BSOFTLONGWARN;
+ prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN);
return -EDQUOT;
}
@@ -1289,7 +1306,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
tspace > dquot->dq_dqb.dqb_bsoftlimit &&
dquot->dq_dqb.dqb_btime == 0) {
if (!prealloc) {
- *warntype = QUOTA_NL_BSOFTWARN;
+ prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN);
dquot->dq_dqb.dqb_btime = get_seconds() +
sb_dqopt(sb)->info[dquot->dq_type].dqi_bgrace;
}
@@ -1542,10 +1559,9 @@ static void inode_decr_space(struct inode *inode, qsize_t number, int reserve)
int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
{
int cnt, ret = 0;
- char warntype[MAXQUOTAS];
- int warn = flags & DQUOT_SPACE_WARN;
+ struct dquot_warn warn[MAXQUOTAS];
+ struct dquot **dquots = inode->i_dquot;
int reserve = flags & DQUOT_SPACE_RESERVE;
- int nofail = flags & DQUOT_SPACE_NOFAIL;
/*
* First test before acquiring mutex - solves deadlocks when we
@@ -1558,36 +1574,36 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- warntype[cnt] = QUOTA_NL_NOWARN;
+ warn[cnt].w_type = QUOTA_NL_NOWARN;
spin_lock(&dq_data_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!inode->i_dquot[cnt])
+ if (!dquots[cnt])
continue;
- ret = check_bdq(inode->i_dquot[cnt], number, !warn,
- warntype+cnt);
- if (ret && !nofail) {
+ ret = check_bdq(dquots[cnt], number,
+ !(flags & DQUOT_SPACE_WARN), &warn[cnt]);
+ if (ret && !(flags & DQUOT_SPACE_NOFAIL)) {
spin_unlock(&dq_data_lock);
goto out_flush_warn;
}
}
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!inode->i_dquot[cnt])
+ if (!dquots[cnt])
continue;
if (reserve)
- dquot_resv_space(inode->i_dquot[cnt], number);
+ dquot_resv_space(dquots[cnt], number);
else
- dquot_incr_space(inode->i_dquot[cnt], number);
+ dquot_incr_space(dquots[cnt], number);
}
inode_incr_space(inode, number, reserve);
spin_unlock(&dq_data_lock);
if (reserve)
goto out_flush_warn;
- mark_all_dquot_dirty(inode->i_dquot);
+ mark_all_dquot_dirty(dquots);
out_flush_warn:
- flush_warnings(inode->i_dquot, warntype);
up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ flush_warnings(warn);
out:
return ret;
}
@@ -1599,36 +1615,37 @@ EXPORT_SYMBOL(__dquot_alloc_space);
int dquot_alloc_inode(const struct inode *inode)
{
int cnt, ret = 0;
- char warntype[MAXQUOTAS];
+ struct dquot_warn warn[MAXQUOTAS];
+ struct dquot * const *dquots = inode->i_dquot;
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
if (!dquot_active(inode))
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- warntype[cnt] = QUOTA_NL_NOWARN;
+ warn[cnt].w_type = QUOTA_NL_NOWARN;
down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
spin_lock(&dq_data_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!inode->i_dquot[cnt])
+ if (!dquots[cnt])
continue;
- ret = check_idq(inode->i_dquot[cnt], 1, warntype + cnt);
+ ret = check_idq(dquots[cnt], 1, &warn[cnt]);
if (ret)
goto warn_put_all;
}
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!inode->i_dquot[cnt])
+ if (!dquots[cnt])
continue;
- dquot_incr_inodes(inode->i_dquot[cnt], 1);
+ dquot_incr_inodes(dquots[cnt], 1);
}
warn_put_all:
spin_unlock(&dq_data_lock);
if (ret == 0)
- mark_all_dquot_dirty(inode->i_dquot);
- flush_warnings(inode->i_dquot, warntype);
+ mark_all_dquot_dirty(dquots);
up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ flush_warnings(warn);
return ret;
}
EXPORT_SYMBOL(dquot_alloc_inode);
@@ -1668,7 +1685,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty);
void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
{
unsigned int cnt;
- char warntype[MAXQUOTAS];
+ struct dquot_warn warn[MAXQUOTAS];
+ struct dquot **dquots = inode->i_dquot;
int reserve = flags & DQUOT_SPACE_RESERVE;
/* First test before acquiring mutex - solves deadlocks when we
@@ -1681,23 +1699,28 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
spin_lock(&dq_data_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!inode->i_dquot[cnt])
+ int wtype;
+
+ warn[cnt].w_type = QUOTA_NL_NOWARN;
+ if (!dquots[cnt])
continue;
- warntype[cnt] = info_bdq_free(inode->i_dquot[cnt], number);
+ wtype = info_bdq_free(dquots[cnt], number);
+ if (wtype != QUOTA_NL_NOWARN)
+ prepare_warning(&warn[cnt], dquots[cnt], wtype);
if (reserve)
- dquot_free_reserved_space(inode->i_dquot[cnt], number);
+ dquot_free_reserved_space(dquots[cnt], number);
else
- dquot_decr_space(inode->i_dquot[cnt], number);
+ dquot_decr_space(dquots[cnt], number);
}
inode_decr_space(inode, number, reserve);
spin_unlock(&dq_data_lock);
if (reserve)
goto out_unlock;
- mark_all_dquot_dirty(inode->i_dquot);
+ mark_all_dquot_dirty(dquots);
out_unlock:
- flush_warnings(inode->i_dquot, warntype);
up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ flush_warnings(warn);
}
EXPORT_SYMBOL(__dquot_free_space);
@@ -1707,7 +1730,8 @@ EXPORT_SYMBOL(__dquot_free_space);
void dquot_free_inode(const struct inode *inode)
{
unsigned int cnt;
- char warntype[MAXQUOTAS];
+ struct dquot_warn warn[MAXQUOTAS];
+ struct dquot * const *dquots = inode->i_dquot;
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
@@ -1717,15 +1741,20 @@ void dquot_free_inode(const struct inode *inode)
down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
spin_lock(&dq_data_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!inode->i_dquot[cnt])
+ int wtype;
+
+ warn[cnt].w_type = QUOTA_NL_NOWARN;
+ if (!dquots[cnt])
continue;
- warntype[cnt] = info_idq_free(inode->i_dquot[cnt], 1);
- dquot_decr_inodes(inode->i_dquot[cnt], 1);
+ wtype = info_idq_free(dquots[cnt], 1);
+ if (wtype != QUOTA_NL_NOWARN)
+ prepare_warning(&warn[cnt], dquots[cnt], wtype);
+ dquot_decr_inodes(dquots[cnt], 1);
}
spin_unlock(&dq_data_lock);
- mark_all_dquot_dirty(inode->i_dquot);
- flush_warnings(inode->i_dquot, warntype);
+ mark_all_dquot_dirty(dquots);
up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ flush_warnings(warn);
}
EXPORT_SYMBOL(dquot_free_inode);
@@ -1746,16 +1775,20 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
struct dquot *transfer_from[MAXQUOTAS] = {};
int cnt, ret = 0;
char is_valid[MAXQUOTAS] = {};
- char warntype_to[MAXQUOTAS];
- char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS];
+ struct dquot_warn warn_to[MAXQUOTAS];
+ struct dquot_warn warn_from_inodes[MAXQUOTAS];
+ struct dquot_warn warn_from_space[MAXQUOTAS];
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
if (IS_NOQUOTA(inode))
return 0;
/* Initialize the arrays */
- for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- warntype_to[cnt] = QUOTA_NL_NOWARN;
+ for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+ warn_to[cnt].w_type = QUOTA_NL_NOWARN;
+ warn_from_inodes[cnt].w_type = QUOTA_NL_NOWARN;
+ warn_from_space[cnt].w_type = QUOTA_NL_NOWARN;
+ }
down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
if (IS_NOQUOTA(inode)) { /* File without quota accounting? */
up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
@@ -1777,10 +1810,10 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
continue;
is_valid[cnt] = 1;
transfer_from[cnt] = inode->i_dquot[cnt];
- ret = check_idq(transfer_to[cnt], 1, warntype_to + cnt);
+ ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]);
if (ret)
goto over_quota;
- ret = check_bdq(transfer_to[cnt], space, 0, warntype_to + cnt);
+ ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]);
if (ret)
goto over_quota;
}
@@ -1793,10 +1826,15 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
continue;
/* Due to IO error we might not have transfer_from[] structure */
if (transfer_from[cnt]) {
- warntype_from_inodes[cnt] =
- info_idq_free(transfer_from[cnt], 1);
- warntype_from_space[cnt] =
- info_bdq_free(transfer_from[cnt], space);
+ int wtype;
+ wtype = info_idq_free(transfer_from[cnt], 1);
+ if (wtype != QUOTA_NL_NOWARN)
+ prepare_warning(&warn_from_inodes[cnt],
+ transfer_from[cnt], wtype);
+ wtype = info_bdq_free(transfer_from[cnt], space);
+ if (wtype != QUOTA_NL_NOWARN)
+ prepare_warning(&warn_from_space[cnt],
+ transfer_from[cnt], wtype);
dquot_decr_inodes(transfer_from[cnt], 1);
dquot_decr_space(transfer_from[cnt], cur_space);
dquot_free_reserved_space(transfer_from[cnt],
@@ -1814,9 +1852,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
mark_all_dquot_dirty(transfer_from);
mark_all_dquot_dirty(transfer_to);
- flush_warnings(transfer_to, warntype_to);
- flush_warnings(transfer_from, warntype_from_inodes);
- flush_warnings(transfer_from, warntype_from_space);
+ flush_warnings(warn_to);
+ flush_warnings(warn_from_inodes);
+ flush_warnings(warn_from_space);
/* Pass back references to put */
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
if (is_valid[cnt])
@@ -1825,7 +1863,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
over_quota:
spin_unlock(&dq_data_lock);
up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
- flush_warnings(transfer_to, warntype_to);
+ flush_warnings(warn_to);
return ret;
}
EXPORT_SYMBOL(__dquot_transfer);
@@ -2125,6 +2163,8 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
mutex_unlock(&dqopt->dqio_mutex);
goto out_file_init;
}
+ if (dqopt->flags & DQUOT_QUOTA_SYS_FILE)
+ dqopt->info[type].dqi_flags |= DQF_SYS_FILE;
mutex_unlock(&dqopt->dqio_mutex);
spin_lock(&dq_state_lock);
dqopt->flags |= dquot_state_flag(flags, type);
@@ -2464,7 +2504,7 @@ int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
spin_lock(&dq_data_lock);
ii->dqi_bgrace = mi->dqi_bgrace;
ii->dqi_igrace = mi->dqi_igrace;
- ii->dqi_flags = mi->dqi_flags & DQF_MASK;
+ ii->dqi_flags = mi->dqi_flags & DQF_GETINFO_MASK;
ii->dqi_valid = IIF_ALL;
spin_unlock(&dq_data_lock);
mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
@@ -2490,8 +2530,8 @@ int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
if (ii->dqi_valid & IIF_IGRACE)
mi->dqi_igrace = ii->dqi_igrace;
if (ii->dqi_valid & IIF_FLAGS)
- mi->dqi_flags = (mi->dqi_flags & ~DQF_MASK) |
- (ii->dqi_flags & DQF_MASK);
+ mi->dqi_flags = (mi->dqi_flags & ~DQF_SETINFO_MASK) |
+ (ii->dqi_flags & DQF_SETINFO_MASK);
spin_unlock(&dq_data_lock);
mark_info_dirty(sb, type);
/* Force write to disk */
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 7a9bede..9a39120 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -291,11 +291,26 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
}
}
+/* Return 1 if 'cmd' will block on frozen filesystem */
+static int quotactl_cmd_write(int cmd)
+{
+ switch (cmd) {
+ case Q_GETFMT:
+ case Q_GETINFO:
+ case Q_SYNC:
+ case Q_XGETQSTAT:
+ case Q_XGETQUOTA:
+ case Q_XQUOTASYNC:
+ return 0;
+ }
+ return 1;
+}
+
/*
* look up a superblock on which quota ops will be performed
* - use the name of a block device to find the superblock thereon
*/
-static struct super_block *quotactl_block(const char __user *special)
+static struct super_block *quotactl_block(const char __user *special, int cmd)
{
#ifdef CONFIG_BLOCK
struct block_device *bdev;
@@ -308,7 +323,10 @@ static struct super_block *quotactl_block(const char __user *special)
putname(tmp);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
- sb = get_super(bdev);
+ if (quotactl_cmd_write(cmd))
+ sb = get_super_thawed(bdev);
+ else
+ sb = get_super(bdev);
bdput(bdev);
if (!sb)
return ERR_PTR(-ENODEV);
@@ -360,7 +378,7 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
pathp = &path;
}
- sb = quotactl_block(special);
+ sb = quotactl_block(special, cmds);
if (IS_ERR(sb)) {
ret = PTR_ERR(sb);
goto out;
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index aec766a..a1fdabe 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -209,22 +209,19 @@ static int ramfs_parse_options(char *data, struct ramfs_mount_opts *opts)
int ramfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct ramfs_fs_info *fsi;
- struct inode *inode = NULL;
- struct dentry *root;
+ struct inode *inode;
int err;
save_mount_options(sb, data);
fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL);
sb->s_fs_info = fsi;
- if (!fsi) {
- err = -ENOMEM;
- goto fail;
- }
+ if (!fsi)
+ return -ENOMEM;
err = ramfs_parse_options(data, &fsi->mount_opts);
if (err)
- goto fail;
+ return err;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = PAGE_CACHE_SIZE;
@@ -234,24 +231,11 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_time_gran = 1;
inode = ramfs_get_inode(sb, NULL, S_IFDIR | fsi->mount_opts.mode, 0);
- if (!inode) {
- err = -ENOMEM;
- goto fail;
- }
-
- root = d_alloc_root(inode);
- sb->s_root = root;
- if (!root) {
- err = -ENOMEM;
- goto fail;
- }
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root)
+ return -ENOMEM;
return 0;
-fail:
- kfree(fsi);
- sb->s_fs_info = NULL;
- iput(inode);
- return err;
}
struct dentry *ramfs_mount(struct file_system_type *fs_type,
diff --git a/fs/read_write.c b/fs/read_write.c
index 5ad4248..ffc99d2 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -11,7 +11,7 @@
#include <linux/uio.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
diff --git a/fs/readdir.c b/fs/readdir.c
index 356f715..cc0a822 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -6,7 +6,7 @@
#include <linux/stddef.h>
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/errno.h>
diff --git a/fs/reiserfs/acl.h b/fs/reiserfs/acl.h
new file mode 100644
index 0000000..f096b80
--- /dev/null
+++ b/fs/reiserfs/acl.h
@@ -0,0 +1,76 @@
+#include <linux/init.h>
+#include <linux/posix_acl.h>
+
+#define REISERFS_ACL_VERSION 0x0001
+
+typedef struct {
+ __le16 e_tag;
+ __le16 e_perm;
+ __le32 e_id;
+} reiserfs_acl_entry;
+
+typedef struct {
+ __le16 e_tag;
+ __le16 e_perm;
+} reiserfs_acl_entry_short;
+
+typedef struct {
+ __le32 a_version;
+} reiserfs_acl_header;
+
+static inline size_t reiserfs_acl_size(int count)
+{
+ if (count <= 4) {
+ return sizeof(reiserfs_acl_header) +
+ count * sizeof(reiserfs_acl_entry_short);
+ } else {
+ return sizeof(reiserfs_acl_header) +
+ 4 * sizeof(reiserfs_acl_entry_short) +
+ (count - 4) * sizeof(reiserfs_acl_entry);
+ }
+}
+
+static inline int reiserfs_acl_count(size_t size)
+{
+ ssize_t s;
+ size -= sizeof(reiserfs_acl_header);
+ s = size - 4 * sizeof(reiserfs_acl_entry_short);
+ if (s < 0) {
+ if (size % sizeof(reiserfs_acl_entry_short))
+ return -1;
+ return size / sizeof(reiserfs_acl_entry_short);
+ } else {
+ if (s % sizeof(reiserfs_acl_entry))
+ return -1;
+ return s / sizeof(reiserfs_acl_entry) + 4;
+ }
+}
+
+#ifdef CONFIG_REISERFS_FS_POSIX_ACL
+struct posix_acl *reiserfs_get_acl(struct inode *inode, int type);
+int reiserfs_acl_chmod(struct inode *inode);
+int reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
+ struct inode *dir, struct dentry *dentry,
+ struct inode *inode);
+int reiserfs_cache_default_acl(struct inode *dir);
+extern const struct xattr_handler reiserfs_posix_acl_default_handler;
+extern const struct xattr_handler reiserfs_posix_acl_access_handler;
+
+#else
+
+#define reiserfs_cache_default_acl(inode) 0
+#define reiserfs_get_acl NULL
+
+static inline int reiserfs_acl_chmod(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int
+reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
+ const struct inode *dir, struct dentry *dentry,
+ struct inode *inode)
+{
+ return 0;
+}
+#endif
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index 70de42f..4c0c7d1 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -4,14 +4,12 @@
/* Reiserfs block (de)allocator, bitmap-based. */
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/errno.h>
#include <linux/buffer_head.h>
#include <linux/kernel.h>
#include <linux/pagemap.h>
#include <linux/vmalloc.h>
-#include <linux/reiserfs_fs_sb.h>
-#include <linux/reiserfs_fs_i.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 133e935..66c53b6 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -5,7 +5,7 @@
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/fs.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/stat.h>
#include <linux/buffer_head.h>
#include <linux/slab.h>
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 60c0804..2b7882b 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -17,7 +17,7 @@
#include <asm/uaccess.h>
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/buffer_head.h>
#include <linux/kernel.h>
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index ace6350..8375c92 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -3,9 +3,9 @@
*/
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_acl.h>
-#include <linux/reiserfs_xattr.h>
+#include "reiserfs.h"
+#include "acl.h"
+#include "xattr.h"
#include <asm/uaccess.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c
index 1e4250b..430e065 100644
--- a/fs/reiserfs/fix_node.c
+++ b/fs/reiserfs/fix_node.c
@@ -37,7 +37,7 @@
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/string.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/buffer_head.h>
/* To make any changes in the tree we find a node, that contains item
diff --git a/fs/reiserfs/hashes.c b/fs/reiserfs/hashes.c
index 6471c67..91b0cc1 100644
--- a/fs/reiserfs/hashes.c
+++ b/fs/reiserfs/hashes.c
@@ -19,7 +19,7 @@
//
#include <linux/kernel.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <asm/types.h>
#define DELTA 0x9E3779B9
diff --git a/fs/reiserfs/ibalance.c b/fs/reiserfs/ibalance.c
index 2074fd9..e1978fd 100644
--- a/fs/reiserfs/ibalance.c
+++ b/fs/reiserfs/ibalance.c
@@ -5,7 +5,7 @@
#include <asm/uaccess.h>
#include <linux/string.h>
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/buffer_head.h>
/* this is one and only function that is used outside (do_balance.c) */
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 9e8cd5a..494c315 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -4,9 +4,9 @@
#include <linux/time.h>
#include <linux/fs.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_acl.h>
-#include <linux/reiserfs_xattr.h>
+#include "reiserfs.h"
+#include "acl.h"
+#include "xattr.h"
#include <linux/exportfs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 950e3d1..0c21850 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -5,7 +5,7 @@
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/mount.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/time.h>
#include <asm/uaccess.h>
#include <linux/pagemap.h>
diff --git a/fs/reiserfs/item_ops.c b/fs/reiserfs/item_ops.c
index 72cb1cc..ee382ef 100644
--- a/fs/reiserfs/item_ops.c
+++ b/fs/reiserfs/item_ops.c
@@ -3,7 +3,7 @@
*/
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
// this contains item handlers for old item types: sd, direct,
// indirect, directory
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index c3cf54f..cf9f4de 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -37,7 +37,7 @@
#include <linux/time.h>
#include <linux/semaphore.h>
#include <linux/vmalloc.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
diff --git a/fs/reiserfs/lbalance.c b/fs/reiserfs/lbalance.c
index 03d85cb..79e5a8b 100644
--- a/fs/reiserfs/lbalance.c
+++ b/fs/reiserfs/lbalance.c
@@ -5,7 +5,7 @@
#include <asm/uaccess.h>
#include <linux/string.h>
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/buffer_head.h>
/* these are used in do_balance.c */
@@ -975,7 +975,7 @@ static int leaf_cut_entries(struct buffer_head *bh,
remove */
RFALSE(!is_direntry_le_ih(ih), "10180: item is not directory item");
RFALSE(I_ENTRY_COUNT(ih) < from + del_count,
- "10185: item contains not enough entries: entry_cout = %d, from = %d, to delete = %d",
+ "10185: item contains not enough entries: entry_count = %d, from = %d, to delete = %d",
I_ENTRY_COUNT(ih), from, del_count);
if (del_count == 0)
diff --git a/fs/reiserfs/lock.c b/fs/reiserfs/lock.c
index 7df1ce4..d735bc8 100644
--- a/fs/reiserfs/lock.c
+++ b/fs/reiserfs/lock.c
@@ -1,4 +1,4 @@
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/mutex.h>
/*
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 1463788..84e8a69 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -14,9 +14,9 @@
#include <linux/time.h>
#include <linux/bitops.h>
#include <linux/slab.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_acl.h>
-#include <linux/reiserfs_xattr.h>
+#include "reiserfs.h"
+#include "acl.h"
+#include "xattr.h"
#include <linux/quotaops.h>
#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) set_nlink(i, 1); }
diff --git a/fs/reiserfs/objectid.c b/fs/reiserfs/objectid.c
index 3a6de81..f732d6a 100644
--- a/fs/reiserfs/objectid.c
+++ b/fs/reiserfs/objectid.c
@@ -5,8 +5,7 @@
#include <linux/string.h>
#include <linux/random.h>
#include <linux/time.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_fs_sb.h>
+#include "reiserfs.h"
// find where objectid map starts
#define objectid_map(s,rs) (old_format_only (s) ? \
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index 45de98b..c0b1112 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -4,7 +4,7 @@
#include <linux/time.h>
#include <linux/fs.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/string.h>
#include <linux/buffer_head.h>
@@ -329,7 +329,7 @@ void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...)
Numbering scheme for panic used by Vladimir and Anatoly( Hans completely ignores this scheme, and considers it
pointless complexity):
- panics in reiserfs_fs.h have numbers from 1000 to 1999
+ panics in reiserfs.h have numbers from 1000 to 1999
super.c 2000 to 2999
preserve.c (unused) 3000 to 3999
bitmap.c 4000 to 4999
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 7a99811..2c1ade6 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -12,8 +12,7 @@
#include <linux/time.h>
#include <linux/seq_file.h>
#include <asm/uaccess.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_fs_sb.h>
+#include "reiserfs.h"
#include <linux/init.h>
#include <linux/proc_fs.h>
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
new file mode 100644
index 0000000..a59d271
--- /dev/null
+++ b/fs/reiserfs/reiserfs.h
@@ -0,0 +1,2923 @@
+/*
+ * Copyright 1996, 1997, 1998 Hans Reiser, see reiserfs/README for licensing and copyright details
+ */
+
+#include <linux/reiserfs_fs.h>
+
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/bug.h>
+#include <linux/workqueue.h>
+#include <asm/unaligned.h>
+#include <linux/bitops.h>
+#include <linux/proc_fs.h>
+#include <linux/buffer_head.h>
+
+/* the 32 bit compat definitions with int argument */
+#define REISERFS_IOC32_UNPACK _IOW(0xCD, 1, int)
+#define REISERFS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
+#define REISERFS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
+#define REISERFS_IOC32_GETVERSION FS_IOC32_GETVERSION
+#define REISERFS_IOC32_SETVERSION FS_IOC32_SETVERSION
+
+struct reiserfs_journal_list;
+
+/** bitmasks for i_flags field in reiserfs-specific part of inode */
+typedef enum {
+ /** this says what format of key do all items (but stat data) of
+ an object have. If this is set, that format is 3.6 otherwise
+ - 3.5 */
+ i_item_key_version_mask = 0x0001,
+ /** If this is unset, object has 3.5 stat data, otherwise, it has
+ 3.6 stat data with 64bit size, 32bit nlink etc. */
+ i_stat_data_version_mask = 0x0002,
+ /** file might need tail packing on close */
+ i_pack_on_close_mask = 0x0004,
+ /** don't pack tail of file */
+ i_nopack_mask = 0x0008,
+ /** If those is set, "safe link" was created for this file during
+ truncate or unlink. Safe link is used to avoid leakage of disk
+ space on crash with some files open, but unlinked. */
+ i_link_saved_unlink_mask = 0x0010,
+ i_link_saved_truncate_mask = 0x0020,
+ i_has_xattr_dir = 0x0040,
+ i_data_log = 0x0080,
+} reiserfs_inode_flags;
+
+struct reiserfs_inode_info {
+ __u32 i_key[4]; /* key is still 4 32 bit integers */
+ /** transient inode flags that are never stored on disk. Bitmasks
+ for this field are defined above. */
+ __u32 i_flags;
+
+ __u32 i_first_direct_byte; // offset of first byte stored in direct item.
+
+ /* copy of persistent inode flags read from sd_attrs. */
+ __u32 i_attrs;
+
+ int i_prealloc_block; /* first unused block of a sequence of unused blocks */
+ int i_prealloc_count; /* length of that sequence */
+ struct list_head i_prealloc_list; /* per-transaction list of inodes which
+ * have preallocated blocks */
+
+ unsigned new_packing_locality:1; /* new_packig_locality is created; new blocks
+ * for the contents of this directory should be
+ * displaced */
+
+ /* we use these for fsync or O_SYNC to decide which transaction
+ ** needs to be committed in order for this inode to be properly
+ ** flushed */
+ unsigned int i_trans_id;
+ struct reiserfs_journal_list *i_jl;
+ atomic_t openers;
+ struct mutex tailpack;
+#ifdef CONFIG_REISERFS_FS_XATTR
+ struct rw_semaphore i_xattr_sem;
+#endif
+ struct inode vfs_inode;
+};
+
+typedef enum {
+ reiserfs_attrs_cleared = 0x00000001,
+} reiserfs_super_block_flags;
+
+/* struct reiserfs_super_block accessors/mutators
+ * since this is a disk structure, it will always be in
+ * little endian format. */
+#define sb_block_count(sbp) (le32_to_cpu((sbp)->s_v1.s_block_count))
+#define set_sb_block_count(sbp,v) ((sbp)->s_v1.s_block_count = cpu_to_le32(v))
+#define sb_free_blocks(sbp) (le32_to_cpu((sbp)->s_v1.s_free_blocks))
+#define set_sb_free_blocks(sbp,v) ((sbp)->s_v1.s_free_blocks = cpu_to_le32(v))
+#define sb_root_block(sbp) (le32_to_cpu((sbp)->s_v1.s_root_block))
+#define set_sb_root_block(sbp,v) ((sbp)->s_v1.s_root_block = cpu_to_le32(v))
+
+#define sb_jp_journal_1st_block(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_1st_block))
+#define set_sb_jp_journal_1st_block(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_1st_block = cpu_to_le32(v))
+#define sb_jp_journal_dev(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_dev))
+#define set_sb_jp_journal_dev(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_dev = cpu_to_le32(v))
+#define sb_jp_journal_size(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_size))
+#define set_sb_jp_journal_size(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_size = cpu_to_le32(v))
+#define sb_jp_journal_trans_max(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_trans_max))
+#define set_sb_jp_journal_trans_max(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_trans_max = cpu_to_le32(v))
+#define sb_jp_journal_magic(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_magic))
+#define set_sb_jp_journal_magic(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_magic = cpu_to_le32(v))
+#define sb_jp_journal_max_batch(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_max_batch))
+#define set_sb_jp_journal_max_batch(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_max_batch = cpu_to_le32(v))
+#define sb_jp_jourmal_max_commit_age(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_max_commit_age))
+#define set_sb_jp_journal_max_commit_age(sbp,v) \
+ ((sbp)->s_v1.s_journal.jp_journal_max_commit_age = cpu_to_le32(v))
+
+#define sb_blocksize(sbp) (le16_to_cpu((sbp)->s_v1.s_blocksize))
+#define set_sb_blocksize(sbp,v) ((sbp)->s_v1.s_blocksize = cpu_to_le16(v))
+#define sb_oid_maxsize(sbp) (le16_to_cpu((sbp)->s_v1.s_oid_maxsize))
+#define set_sb_oid_maxsize(sbp,v) ((sbp)->s_v1.s_oid_maxsize = cpu_to_le16(v))
+#define sb_oid_cursize(sbp) (le16_to_cpu((sbp)->s_v1.s_oid_cursize))
+#define set_sb_oid_cursize(sbp,v) ((sbp)->s_v1.s_oid_cursize = cpu_to_le16(v))
+#define sb_umount_state(sbp) (le16_to_cpu((sbp)->s_v1.s_umount_state))
+#define set_sb_umount_state(sbp,v) ((sbp)->s_v1.s_umount_state = cpu_to_le16(v))
+#define sb_fs_state(sbp) (le16_to_cpu((sbp)->s_v1.s_fs_state))
+#define set_sb_fs_state(sbp,v) ((sbp)->s_v1.s_fs_state = cpu_to_le16(v))
+#define sb_hash_function_code(sbp) \
+ (le32_to_cpu((sbp)->s_v1.s_hash_function_code))
+#define set_sb_hash_function_code(sbp,v) \
+ ((sbp)->s_v1.s_hash_function_code = cpu_to_le32(v))
+#define sb_tree_height(sbp) (le16_to_cpu((sbp)->s_v1.s_tree_height))
+#define set_sb_tree_height(sbp,v) ((sbp)->s_v1.s_tree_height = cpu_to_le16(v))
+#define sb_bmap_nr(sbp) (le16_to_cpu((sbp)->s_v1.s_bmap_nr))
+#define set_sb_bmap_nr(sbp,v) ((sbp)->s_v1.s_bmap_nr = cpu_to_le16(v))
+#define sb_version(sbp) (le16_to_cpu((sbp)->s_v1.s_version))
+#define set_sb_version(sbp,v) ((sbp)->s_v1.s_version = cpu_to_le16(v))
+
+#define sb_mnt_count(sbp) (le16_to_cpu((sbp)->s_mnt_count))
+#define set_sb_mnt_count(sbp, v) ((sbp)->s_mnt_count = cpu_to_le16(v))
+
+#define sb_reserved_for_journal(sbp) \
+ (le16_to_cpu((sbp)->s_v1.s_reserved_for_journal))
+#define set_sb_reserved_for_journal(sbp,v) \
+ ((sbp)->s_v1.s_reserved_for_journal = cpu_to_le16(v))
+
+/* LOGGING -- */
+
+/* These all interelate for performance.
+**
+** If the journal block count is smaller than n transactions, you lose speed.
+** I don't know what n is yet, I'm guessing 8-16.
+**
+** typical transaction size depends on the application, how often fsync is
+** called, and how many metadata blocks you dirty in a 30 second period.
+** The more small files (<16k) you use, the larger your transactions will
+** be.
+**
+** If your journal fills faster than dirty buffers get flushed to disk, it must flush them before allowing the journal
+** to wrap, which slows things down. If you need high speed meta data updates, the journal should be big enough
+** to prevent wrapping before dirty meta blocks get to disk.
+**
+** If the batch max is smaller than the transaction max, you'll waste space at the end of the journal
+** because journal_end sets the next transaction to start at 0 if the next transaction has any chance of wrapping.
+**
+** The large the batch max age, the better the speed, and the more meta data changes you'll lose after a crash.
+**
+*/
+
+/* don't mess with these for a while */
+ /* we have a node size define somewhere in reiserfs_fs.h. -Hans */
+#define JOURNAL_BLOCK_SIZE 4096 /* BUG gotta get rid of this */
+#define JOURNAL_MAX_CNODE 1500 /* max cnodes to allocate. */
+#define JOURNAL_HASH_SIZE 8192
+#define JOURNAL_NUM_BITMAPS 5 /* number of copies of the bitmaps to have floating. Must be >= 2 */
+
+/* One of these for every block in every transaction
+** Each one is in two hash tables. First, a hash of the current transaction, and after journal_end, a
+** hash of all the in memory transactions.
+** next and prev are used by the current transaction (journal_hash).
+** hnext and hprev are used by journal_list_hash. If a block is in more than one transaction, the journal_list_hash
+** links it in multiple times. This allows flush_journal_list to remove just the cnode belonging
+** to a given transaction.
+*/
+struct reiserfs_journal_cnode {
+ struct buffer_head *bh; /* real buffer head */
+ struct super_block *sb; /* dev of real buffer head */
+ __u32 blocknr; /* block number of real buffer head, == 0 when buffer on disk */
+ unsigned long state;
+ struct reiserfs_journal_list *jlist; /* journal list this cnode lives in */
+ struct reiserfs_journal_cnode *next; /* next in transaction list */
+ struct reiserfs_journal_cnode *prev; /* prev in transaction list */
+ struct reiserfs_journal_cnode *hprev; /* prev in hash list */
+ struct reiserfs_journal_cnode *hnext; /* next in hash list */
+};
+
+struct reiserfs_bitmap_node {
+ int id;
+ char *data;
+ struct list_head list;
+};
+
+struct reiserfs_list_bitmap {
+ struct reiserfs_journal_list *journal_list;
+ struct reiserfs_bitmap_node **bitmaps;
+};
+
+/*
+** one of these for each transaction. The most important part here is the j_realblock.
+** this list of cnodes is used to hash all the blocks in all the commits, to mark all the
+** real buffer heads dirty once all the commits hit the disk,
+** and to make sure every real block in a transaction is on disk before allowing the log area
+** to be overwritten */
+struct reiserfs_journal_list {
+ unsigned long j_start;
+ unsigned long j_state;
+ unsigned long j_len;
+ atomic_t j_nonzerolen;
+ atomic_t j_commit_left;
+ atomic_t j_older_commits_done; /* all commits older than this on disk */
+ struct mutex j_commit_mutex;
+ unsigned int j_trans_id;
+ time_t j_timestamp;
+ struct reiserfs_list_bitmap *j_list_bitmap;
+ struct buffer_head *j_commit_bh; /* commit buffer head */
+ struct reiserfs_journal_cnode *j_realblock;
+ struct reiserfs_journal_cnode *j_freedlist; /* list of buffers that were freed during this trans. free each of these on flush */
+ /* time ordered list of all active transactions */
+ struct list_head j_list;
+
+ /* time ordered list of all transactions we haven't tried to flush yet */
+ struct list_head j_working_list;
+
+ /* list of tail conversion targets in need of flush before commit */
+ struct list_head j_tail_bh_list;
+ /* list of data=ordered buffers in need of flush before commit */
+ struct list_head j_bh_list;
+ int j_refcount;
+};
+
+struct reiserfs_journal {
+ struct buffer_head **j_ap_blocks; /* journal blocks on disk */
+ struct reiserfs_journal_cnode *j_last; /* newest journal block */
+ struct reiserfs_journal_cnode *j_first; /* oldest journal block. start here for traverse */
+
+ struct block_device *j_dev_bd;
+ fmode_t j_dev_mode;
+ int j_1st_reserved_block; /* first block on s_dev of reserved area journal */
+
+ unsigned long j_state;
+ unsigned int j_trans_id;
+ unsigned long j_mount_id;
+ unsigned long j_start; /* start of current waiting commit (index into j_ap_blocks) */
+ unsigned long j_len; /* length of current waiting commit */
+ unsigned long j_len_alloc; /* number of buffers requested by journal_begin() */
+ atomic_t j_wcount; /* count of writers for current commit */
+ unsigned long j_bcount; /* batch count. allows turning X transactions into 1 */
+ unsigned long j_first_unflushed_offset; /* first unflushed transactions offset */
+ unsigned j_last_flush_trans_id; /* last fully flushed journal timestamp */
+ struct buffer_head *j_header_bh;
+
+ time_t j_trans_start_time; /* time this transaction started */
+ struct mutex j_mutex;
+ struct mutex j_flush_mutex;
+ wait_queue_head_t j_join_wait; /* wait for current transaction to finish before starting new one */
+ atomic_t j_jlock; /* lock for j_join_wait */
+ int j_list_bitmap_index; /* number of next list bitmap to use */
+ int j_must_wait; /* no more journal begins allowed. MUST sleep on j_join_wait */
+ int j_next_full_flush; /* next journal_end will flush all journal list */
+ int j_next_async_flush; /* next journal_end will flush all async commits */
+
+ int j_cnode_used; /* number of cnodes on the used list */
+ int j_cnode_free; /* number of cnodes on the free list */
+
+ unsigned int j_trans_max; /* max number of blocks in a transaction. */
+ unsigned int j_max_batch; /* max number of blocks to batch into a trans */
+ unsigned int j_max_commit_age; /* in seconds, how old can an async commit be */
+ unsigned int j_max_trans_age; /* in seconds, how old can a transaction be */
+ unsigned int j_default_max_commit_age; /* the default for the max commit age */
+
+ struct reiserfs_journal_cnode *j_cnode_free_list;
+ struct reiserfs_journal_cnode *j_cnode_free_orig; /* orig pointer returned from vmalloc */
+
+ struct reiserfs_journal_list *j_current_jl;
+ int j_free_bitmap_nodes;
+ int j_used_bitmap_nodes;
+
+ int j_num_lists; /* total number of active transactions */
+ int j_num_work_lists; /* number that need attention from kreiserfsd */
+
+ /* debugging to make sure things are flushed in order */
+ unsigned int j_last_flush_id;
+
+ /* debugging to make sure things are committed in order */
+ unsigned int j_last_commit_id;
+
+ struct list_head j_bitmap_nodes;
+ struct list_head j_dirty_buffers;
+ spinlock_t j_dirty_buffers_lock; /* protects j_dirty_buffers */
+
+ /* list of all active transactions */
+ struct list_head j_journal_list;
+ /* lists that haven't been touched by writeback attempts */
+ struct list_head j_working_list;
+
+ struct reiserfs_list_bitmap j_list_bitmap[JOURNAL_NUM_BITMAPS]; /* array of bitmaps to record the deleted blocks */
+ struct reiserfs_journal_cnode *j_hash_table[JOURNAL_HASH_SIZE]; /* hash table for real buffer heads in current trans */
+ struct reiserfs_journal_cnode *j_list_hash_table[JOURNAL_HASH_SIZE]; /* hash table for all the real buffer heads in all
+ the transactions */
+ struct list_head j_prealloc_list; /* list of inodes which have preallocated blocks */
+ int j_persistent_trans;
+ unsigned long j_max_trans_size;
+ unsigned long j_max_batch_size;
+
+ int j_errno;
+
+ /* when flushing ordered buffers, throttle new ordered writers */
+ struct delayed_work j_work;
+ struct super_block *j_work_sb;
+ atomic_t j_async_throttle;
+};
+
+enum journal_state_bits {
+ J_WRITERS_BLOCKED = 1, /* set when new writers not allowed */
+ J_WRITERS_QUEUED, /* set when log is full due to too many writers */
+ J_ABORTED, /* set when log is aborted */
+};
+
+#define JOURNAL_DESC_MAGIC "ReIsErLB" /* ick. magic string to find desc blocks in the journal */
+
+typedef __u32(*hashf_t) (const signed char *, int);
+
+struct reiserfs_bitmap_info {
+ __u32 free_count;
+};
+
+struct proc_dir_entry;
+
+#if defined( CONFIG_PROC_FS ) && defined( CONFIG_REISERFS_PROC_INFO )
+typedef unsigned long int stat_cnt_t;
+typedef struct reiserfs_proc_info_data {
+ spinlock_t lock;
+ int exiting;
+ int max_hash_collisions;
+
+ stat_cnt_t breads;
+ stat_cnt_t bread_miss;
+ stat_cnt_t search_by_key;
+ stat_cnt_t search_by_key_fs_changed;
+ stat_cnt_t search_by_key_restarted;
+
+ stat_cnt_t insert_item_restarted;
+ stat_cnt_t paste_into_item_restarted;
+ stat_cnt_t cut_from_item_restarted;
+ stat_cnt_t delete_solid_item_restarted;
+ stat_cnt_t delete_item_restarted;
+
+ stat_cnt_t leaked_oid;
+ stat_cnt_t leaves_removable;
+
+ /* balances per level. Use explicit 5 as MAX_HEIGHT is not visible yet. */
+ stat_cnt_t balance_at[5]; /* XXX */
+ /* sbk == search_by_key */
+ stat_cnt_t sbk_read_at[5]; /* XXX */
+ stat_cnt_t sbk_fs_changed[5];
+ stat_cnt_t sbk_restarted[5];
+ stat_cnt_t items_at[5]; /* XXX */
+ stat_cnt_t free_at[5]; /* XXX */
+ stat_cnt_t can_node_be_removed[5]; /* XXX */
+ long int lnum[5]; /* XXX */
+ long int rnum[5]; /* XXX */
+ long int lbytes[5]; /* XXX */
+ long int rbytes[5]; /* XXX */
+ stat_cnt_t get_neighbors[5];
+ stat_cnt_t get_neighbors_restart[5];
+ stat_cnt_t need_l_neighbor[5];
+ stat_cnt_t need_r_neighbor[5];
+
+ stat_cnt_t free_block;
+ struct __scan_bitmap_stats {
+ stat_cnt_t call;
+ stat_cnt_t wait;
+ stat_cnt_t bmap;
+ stat_cnt_t retry;
+ stat_cnt_t in_journal_hint;
+ stat_cnt_t in_journal_nohint;
+ stat_cnt_t stolen;
+ } scan_bitmap;
+ struct __journal_stats {
+ stat_cnt_t in_journal;
+ stat_cnt_t in_journal_bitmap;
+ stat_cnt_t in_journal_reusable;
+ stat_cnt_t lock_journal;
+ stat_cnt_t lock_journal_wait;
+ stat_cnt_t journal_being;
+ stat_cnt_t journal_relock_writers;
+ stat_cnt_t journal_relock_wcount;
+ stat_cnt_t mark_dirty;
+ stat_cnt_t mark_dirty_already;
+ stat_cnt_t mark_dirty_notjournal;
+ stat_cnt_t restore_prepared;
+ stat_cnt_t prepare;
+ stat_cnt_t prepare_retry;
+ } journal;
+} reiserfs_proc_info_data_t;
+#else
+typedef struct reiserfs_proc_info_data {
+} reiserfs_proc_info_data_t;
+#endif
+
+/* reiserfs union of in-core super block data */
+struct reiserfs_sb_info {
+ struct buffer_head *s_sbh; /* Buffer containing the super block */
+ /* both the comment and the choice of
+ name are unclear for s_rs -Hans */
+ struct reiserfs_super_block *s_rs; /* Pointer to the super block in the buffer */
+ struct reiserfs_bitmap_info *s_ap_bitmap;
+ struct reiserfs_journal *s_journal; /* pointer to journal information */
+ unsigned short s_mount_state; /* reiserfs state (valid, invalid) */
+
+ /* Serialize writers access, replace the old bkl */
+ struct mutex lock;
+ /* Owner of the lock (can be recursive) */
+ struct task_struct *lock_owner;
+ /* Depth of the lock, start from -1 like the bkl */
+ int lock_depth;
+
+ /* Comment? -Hans */
+ void (*end_io_handler) (struct buffer_head *, int);
+ hashf_t s_hash_function; /* pointer to function which is used
+ to sort names in directory. Set on
+ mount */
+ unsigned long s_mount_opt; /* reiserfs's mount options are set
+ here (currently - NOTAIL, NOLOG,
+ REPLAYONLY) */
+
+ struct { /* This is a structure that describes block allocator options */
+ unsigned long bits; /* Bitfield for enable/disable kind of options */
+ unsigned long large_file_size; /* size started from which we consider file to be a large one(in blocks) */
+ int border; /* percentage of disk, border takes */
+ int preallocmin; /* Minimal file size (in blocks) starting from which we do preallocations */
+ int preallocsize; /* Number of blocks we try to prealloc when file
+ reaches preallocmin size (in blocks) or
+ prealloc_list is empty. */
+ } s_alloc_options;
+
+ /* Comment? -Hans */
+ wait_queue_head_t s_wait;
+ /* To be obsoleted soon by per buffer seals.. -Hans */
+ atomic_t s_generation_counter; // increased by one every time the
+ // tree gets re-balanced
+ unsigned long s_properties; /* File system properties. Currently holds
+ on-disk FS format */
+
+ /* session statistics */
+ int s_disk_reads;
+ int s_disk_writes;
+ int s_fix_nodes;
+ int s_do_balance;
+ int s_unneeded_left_neighbor;
+ int s_good_search_by_key_reada;
+ int s_bmaps;
+ int s_bmaps_without_search;
+ int s_direct2indirect;
+ int s_indirect2direct;
+ /* set up when it's ok for reiserfs_read_inode2() to read from
+ disk inode with nlink==0. Currently this is only used during
+ finish_unfinished() processing at mount time */
+ int s_is_unlinked_ok;
+ reiserfs_proc_info_data_t s_proc_info_data;
+ struct proc_dir_entry *procdir;
+ int reserved_blocks; /* amount of blocks reserved for further allocations */
+ spinlock_t bitmap_lock; /* this lock on now only used to protect reserved_blocks variable */
+ struct dentry *priv_root; /* root of /.reiserfs_priv */
+ struct dentry *xattr_root; /* root of /.reiserfs_priv/xattrs */
+ int j_errno;
+#ifdef CONFIG_QUOTA
+ char *s_qf_names[MAXQUOTAS];
+ int s_jquota_fmt;
+#endif
+ char *s_jdev; /* Stored jdev for mount option showing */
+#ifdef CONFIG_REISERFS_CHECK
+
+ struct tree_balance *cur_tb; /*
+ * Detects whether more than one
+ * copy of tb exists per superblock
+ * as a means of checking whether
+ * do_balance is executing concurrently
+ * against another tree reader/writer
+ * on a same mount point.
+ */
+#endif
+};
+
+/* Definitions of reiserfs on-disk properties: */
+#define REISERFS_3_5 0
+#define REISERFS_3_6 1
+#define REISERFS_OLD_FORMAT 2
+
+enum reiserfs_mount_options {
+/* Mount options */
+ REISERFS_LARGETAIL, /* large tails will be created in a session */
+ REISERFS_SMALLTAIL, /* small (for files less than block size) tails will be created in a session */
+ REPLAYONLY, /* replay journal and return 0. Use by fsck */
+ REISERFS_CONVERT, /* -o conv: causes conversion of old
+ format super block to the new
+ format. If not specified - old
+ partition will be dealt with in a
+ manner of 3.5.x */
+
+/* -o hash={tea, rupasov, r5, detect} is meant for properly mounting
+** reiserfs disks from 3.5.19 or earlier. 99% of the time, this option
+** is not required. If the normal autodection code can't determine which
+** hash to use (because both hashes had the same value for a file)
+** use this option to force a specific hash. It won't allow you to override
+** the existing hash on the FS, so if you have a tea hash disk, and mount
+** with -o hash=rupasov, the mount will fail.
+*/
+ FORCE_TEA_HASH, /* try to force tea hash on mount */
+ FORCE_RUPASOV_HASH, /* try to force rupasov hash on mount */
+ FORCE_R5_HASH, /* try to force rupasov hash on mount */
+ FORCE_HASH_DETECT, /* try to detect hash function on mount */
+
+ REISERFS_DATA_LOG,
+ REISERFS_DATA_ORDERED,
+ REISERFS_DATA_WRITEBACK,
+
+/* used for testing experimental features, makes benchmarking new
+ features with and without more convenient, should never be used by
+ users in any code shipped to users (ideally) */
+
+ REISERFS_NO_BORDER,
+ REISERFS_NO_UNHASHED_RELOCATION,
+ REISERFS_HASHED_RELOCATION,
+ REISERFS_ATTRS,
+ REISERFS_XATTRS_USER,
+ REISERFS_POSIXACL,
+ REISERFS_EXPOSE_PRIVROOT,
+ REISERFS_BARRIER_NONE,
+ REISERFS_BARRIER_FLUSH,
+
+ /* Actions on error */
+ REISERFS_ERROR_PANIC,
+ REISERFS_ERROR_RO,
+ REISERFS_ERROR_CONTINUE,
+
+ REISERFS_USRQUOTA, /* User quota option specified */
+ REISERFS_GRPQUOTA, /* Group quota option specified */
+
+ REISERFS_TEST1,
+ REISERFS_TEST2,
+ REISERFS_TEST3,
+ REISERFS_TEST4,
+ REISERFS_UNSUPPORTED_OPT,
+};
+
+#define reiserfs_r5_hash(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_R5_HASH))
+#define reiserfs_rupasov_hash(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_RUPASOV_HASH))
+#define reiserfs_tea_hash(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_TEA_HASH))
+#define reiserfs_hash_detect(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_HASH_DETECT))
+#define reiserfs_no_border(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_NO_BORDER))
+#define reiserfs_no_unhashed_relocation(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_NO_UNHASHED_RELOCATION))
+#define reiserfs_hashed_relocation(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_HASHED_RELOCATION))
+#define reiserfs_test4(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_TEST4))
+
+#define have_large_tails(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_LARGETAIL))
+#define have_small_tails(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_SMALLTAIL))
+#define replay_only(s) (REISERFS_SB(s)->s_mount_opt & (1 << REPLAYONLY))
+#define reiserfs_attrs(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_ATTRS))
+#define old_format_only(s) (REISERFS_SB(s)->s_properties & (1 << REISERFS_3_5))
+#define convert_reiserfs(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_CONVERT))
+#define reiserfs_data_log(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_LOG))
+#define reiserfs_data_ordered(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_ORDERED))
+#define reiserfs_data_writeback(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_WRITEBACK))
+#define reiserfs_xattrs_user(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_XATTRS_USER))
+#define reiserfs_posixacl(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_POSIXACL))
+#define reiserfs_expose_privroot(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_EXPOSE_PRIVROOT))
+#define reiserfs_xattrs_optional(s) (reiserfs_xattrs_user(s) || reiserfs_posixacl(s))
+#define reiserfs_barrier_none(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_NONE))
+#define reiserfs_barrier_flush(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_FLUSH))
+
+#define reiserfs_error_panic(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_ERROR_PANIC))
+#define reiserfs_error_ro(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_ERROR_RO))
+
+void reiserfs_file_buffer(struct buffer_head *bh, int list);
+extern struct file_system_type reiserfs_fs_type;
+int reiserfs_resize(struct super_block *, unsigned long);
+
+#define CARRY_ON 0
+#define SCHEDULE_OCCURRED 1
+
+#define SB_BUFFER_WITH_SB(s) (REISERFS_SB(s)->s_sbh)
+#define SB_JOURNAL(s) (REISERFS_SB(s)->s_journal)
+#define SB_JOURNAL_1st_RESERVED_BLOCK(s) (SB_JOURNAL(s)->j_1st_reserved_block)
+#define SB_JOURNAL_LEN_FREE(s) (SB_JOURNAL(s)->j_journal_len_free)
+#define SB_AP_BITMAP(s) (REISERFS_SB(s)->s_ap_bitmap)
+
+#define SB_DISK_JOURNAL_HEAD(s) (SB_JOURNAL(s)->j_header_bh->)
+
+/* A safe version of the "bdevname", which returns the "s_id" field of
+ * a superblock or else "Null superblock" if the super block is NULL.
+ */
+static inline char *reiserfs_bdevname(struct super_block *s)
+{
+ return (s == NULL) ? "Null superblock" : s->s_id;
+}
+
+#define reiserfs_is_journal_aborted(journal) (unlikely (__reiserfs_is_journal_aborted (journal)))
+static inline int __reiserfs_is_journal_aborted(struct reiserfs_journal
+ *journal)
+{
+ return test_bit(J_ABORTED, &journal->j_state);
+}
+
+/*
+ * Locking primitives. The write lock is a per superblock
+ * special mutex that has properties close to the Big Kernel Lock
+ * which was used in the previous locking scheme.
+ */
+void reiserfs_write_lock(struct super_block *s);
+void reiserfs_write_unlock(struct super_block *s);
+int reiserfs_write_lock_once(struct super_block *s);
+void reiserfs_write_unlock_once(struct super_block *s, int lock_depth);
+
+#ifdef CONFIG_REISERFS_CHECK
+void reiserfs_lock_check_recursive(struct super_block *s);
+#else
+static inline void reiserfs_lock_check_recursive(struct super_block *s) { }
+#endif
+
+/*
+ * Several mutexes depend on the write lock.
+ * However sometimes we want to relax the write lock while we hold
+ * these mutexes, according to the release/reacquire on schedule()
+ * properties of the Bkl that were used.
+ * Reiserfs performances and locking were based on this scheme.
+ * Now that the write lock is a mutex and not the bkl anymore, doing so
+ * may result in a deadlock:
+ *
+ * A acquire write_lock
+ * A acquire j_commit_mutex
+ * A release write_lock and wait for something
+ * B acquire write_lock
+ * B can't acquire j_commit_mutex and sleep
+ * A can't acquire write lock anymore
+ * deadlock
+ *
+ * What we do here is avoiding such deadlock by playing the same game
+ * than the Bkl: if we can't acquire a mutex that depends on the write lock,
+ * we release the write lock, wait a bit and then retry.
+ *
+ * The mutexes concerned by this hack are:
+ * - The commit mutex of a journal list
+ * - The flush mutex
+ * - The journal lock
+ * - The inode mutex
+ */
+static inline void reiserfs_mutex_lock_safe(struct mutex *m,
+ struct super_block *s)
+{
+ reiserfs_lock_check_recursive(s);
+ reiserfs_write_unlock(s);
+ mutex_lock(m);
+ reiserfs_write_lock(s);
+}
+
+static inline void
+reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass,
+ struct super_block *s)
+{
+ reiserfs_lock_check_recursive(s);
+ reiserfs_write_unlock(s);
+ mutex_lock_nested(m, subclass);
+ reiserfs_write_lock(s);
+}
+
+static inline void
+reiserfs_down_read_safe(struct rw_semaphore *sem, struct super_block *s)
+{
+ reiserfs_lock_check_recursive(s);
+ reiserfs_write_unlock(s);
+ down_read(sem);
+ reiserfs_write_lock(s);
+}
+
+/*
+ * When we schedule, we usually want to also release the write lock,
+ * according to the previous bkl based locking scheme of reiserfs.
+ */
+static inline void reiserfs_cond_resched(struct super_block *s)
+{
+ if (need_resched()) {
+ reiserfs_write_unlock(s);
+ schedule();
+ reiserfs_write_lock(s);
+ }
+}
+
+struct fid;
+
+/* in reading the #defines, it may help to understand that they employ
+ the following abbreviations:
+
+ B = Buffer
+ I = Item header
+ H = Height within the tree (should be changed to LEV)
+ N = Number of the item in the node
+ STAT = stat data
+ DEH = Directory Entry Header
+ EC = Entry Count
+ E = Entry number
+ UL = Unsigned Long
+ BLKH = BLocK Header
+ UNFM = UNForMatted node
+ DC = Disk Child
+ P = Path
+
+ These #defines are named by concatenating these abbreviations,
+ where first comes the arguments, and last comes the return value,
+ of the macro.
+
+*/
+
+#define USE_INODE_GENERATION_COUNTER
+
+#define REISERFS_PREALLOCATE
+#define DISPLACE_NEW_PACKING_LOCALITIES
+#define PREALLOCATION_SIZE 9
+
+/* n must be power of 2 */
+#define _ROUND_UP(x,n) (((x)+(n)-1u) & ~((n)-1u))
+
+// to be ok for alpha and others we have to align structures to 8 byte
+// boundary.
+// FIXME: do not change 4 by anything else: there is code which relies on that
+#define ROUND_UP(x) _ROUND_UP(x,8LL)
+
+/* debug levels. Right now, CONFIG_REISERFS_CHECK means print all debug
+** messages.
+*/
+#define REISERFS_DEBUG_CODE 5 /* extra messages to help find/debug errors */
+
+void __reiserfs_warning(struct super_block *s, const char *id,
+ const char *func, const char *fmt, ...);
+#define reiserfs_warning(s, id, fmt, args...) \
+ __reiserfs_warning(s, id, __func__, fmt, ##args)
+/* assertions handling */
+
+/** always check a condition and panic if it's false. */
+#define __RASSERT(cond, scond, format, args...) \
+do { \
+ if (!(cond)) \
+ reiserfs_panic(NULL, "assertion failure", "(" #cond ") at " \
+ __FILE__ ":%i:%s: " format "\n", \
+ in_interrupt() ? -1 : task_pid_nr(current), \
+ __LINE__, __func__ , ##args); \
+} while (0)
+
+#define RASSERT(cond, format, args...) __RASSERT(cond, #cond, format, ##args)
+
+#if defined( CONFIG_REISERFS_CHECK )
+#define RFALSE(cond, format, args...) __RASSERT(!(cond), "!(" #cond ")", format, ##args)
+#else
+#define RFALSE( cond, format, args... ) do {;} while( 0 )
+#endif
+
+#define CONSTF __attribute_const__
+/*
+ * Disk Data Structures
+ */
+
+/***************************************************************************/
+/* SUPER BLOCK */
+/***************************************************************************/
+
+/*
+ * Structure of super block on disk, a version of which in RAM is often accessed as REISERFS_SB(s)->s_rs
+ * the version in RAM is part of a larger structure containing fields never written to disk.
+ */
+#define UNSET_HASH 0 // read_super will guess about, what hash names
+ // in directories were sorted with
+#define TEA_HASH 1
+#define YURA_HASH 2
+#define R5_HASH 3
+#define DEFAULT_HASH R5_HASH
+
+struct journal_params {
+ __le32 jp_journal_1st_block; /* where does journal start from on its
+ * device */
+ __le32 jp_journal_dev; /* journal device st_rdev */
+ __le32 jp_journal_size; /* size of the journal */
+ __le32 jp_journal_trans_max; /* max number of blocks in a transaction. */
+ __le32 jp_journal_magic; /* random value made on fs creation (this
+ * was sb_journal_block_count) */
+ __le32 jp_journal_max_batch; /* max number of blocks to batch into a
+ * trans */
+ __le32 jp_journal_max_commit_age; /* in seconds, how old can an async
+ * commit be */
+ __le32 jp_journal_max_trans_age; /* in seconds, how old can a transaction
+ * be */
+};
+
+/* this is the super from 3.5.X, where X >= 10 */
+struct reiserfs_super_block_v1 {
+ __le32 s_block_count; /* blocks count */
+ __le32 s_free_blocks; /* free blocks count */
+ __le32 s_root_block; /* root block number */
+ struct journal_params s_journal;
+ __le16 s_blocksize; /* block size */
+ __le16 s_oid_maxsize; /* max size of object id array, see
+ * get_objectid() commentary */
+ __le16 s_oid_cursize; /* current size of object id array */
+ __le16 s_umount_state; /* this is set to 1 when filesystem was
+ * umounted, to 2 - when not */
+ char s_magic[10]; /* reiserfs magic string indicates that
+ * file system is reiserfs:
+ * "ReIsErFs" or "ReIsEr2Fs" or "ReIsEr3Fs" */
+ __le16 s_fs_state; /* it is set to used by fsck to mark which
+ * phase of rebuilding is done */
+ __le32 s_hash_function_code; /* indicate, what hash function is being use
+ * to sort names in a directory*/
+ __le16 s_tree_height; /* height of disk tree */
+ __le16 s_bmap_nr; /* amount of bitmap blocks needed to address
+ * each block of file system */
+ __le16 s_version; /* this field is only reliable on filesystem
+ * with non-standard journal */
+ __le16 s_reserved_for_journal; /* size in blocks of journal area on main
+ * device, we need to keep after
+ * making fs with non-standard journal */
+} __attribute__ ((__packed__));
+
+#define SB_SIZE_V1 (sizeof(struct reiserfs_super_block_v1))
+
+/* this is the on disk super block */
+struct reiserfs_super_block {
+ struct reiserfs_super_block_v1 s_v1;
+ __le32 s_inode_generation;
+ __le32 s_flags; /* Right now used only by inode-attributes, if enabled */
+ unsigned char s_uuid[16]; /* filesystem unique identifier */
+ unsigned char s_label[16]; /* filesystem volume label */
+ __le16 s_mnt_count; /* Count of mounts since last fsck */
+ __le16 s_max_mnt_count; /* Maximum mounts before check */
+ __le32 s_lastcheck; /* Timestamp of last fsck */
+ __le32 s_check_interval; /* Interval between checks */
+ char s_unused[76]; /* zero filled by mkreiserfs and
+ * reiserfs_convert_objectid_map_v1()
+ * so any additions must be updated
+ * there as well. */
+} __attribute__ ((__packed__));
+
+#define SB_SIZE (sizeof(struct reiserfs_super_block))
+
+#define REISERFS_VERSION_1 0
+#define REISERFS_VERSION_2 2
+
+// on-disk super block fields converted to cpu form
+#define SB_DISK_SUPER_BLOCK(s) (REISERFS_SB(s)->s_rs)
+#define SB_V1_DISK_SUPER_BLOCK(s) (&(SB_DISK_SUPER_BLOCK(s)->s_v1))
+#define SB_BLOCKSIZE(s) \
+ le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_blocksize))
+#define SB_BLOCK_COUNT(s) \
+ le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_block_count))
+#define SB_FREE_BLOCKS(s) \
+ le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_free_blocks))
+#define SB_REISERFS_MAGIC(s) \
+ (SB_V1_DISK_SUPER_BLOCK(s)->s_magic)
+#define SB_ROOT_BLOCK(s) \
+ le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_root_block))
+#define SB_TREE_HEIGHT(s) \
+ le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_tree_height))
+#define SB_REISERFS_STATE(s) \
+ le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_umount_state))
+#define SB_VERSION(s) le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_version))
+#define SB_BMAP_NR(s) le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_bmap_nr))
+
+#define PUT_SB_BLOCK_COUNT(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_block_count = cpu_to_le32(val); } while (0)
+#define PUT_SB_FREE_BLOCKS(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_free_blocks = cpu_to_le32(val); } while (0)
+#define PUT_SB_ROOT_BLOCK(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_root_block = cpu_to_le32(val); } while (0)
+#define PUT_SB_TREE_HEIGHT(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_tree_height = cpu_to_le16(val); } while (0)
+#define PUT_SB_REISERFS_STATE(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_umount_state = cpu_to_le16(val); } while (0)
+#define PUT_SB_VERSION(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_version = cpu_to_le16(val); } while (0)
+#define PUT_SB_BMAP_NR(s, val) \
+ do { SB_V1_DISK_SUPER_BLOCK(s)->s_bmap_nr = cpu_to_le16 (val); } while (0)
+
+#define SB_ONDISK_JP(s) (&SB_V1_DISK_SUPER_BLOCK(s)->s_journal)
+#define SB_ONDISK_JOURNAL_SIZE(s) \
+ le32_to_cpu ((SB_ONDISK_JP(s)->jp_journal_size))
+#define SB_ONDISK_JOURNAL_1st_BLOCK(s) \
+ le32_to_cpu ((SB_ONDISK_JP(s)->jp_journal_1st_block))
+#define SB_ONDISK_JOURNAL_DEVICE(s) \
+ le32_to_cpu ((SB_ONDISK_JP(s)->jp_journal_dev))
+#define SB_ONDISK_RESERVED_FOR_JOURNAL(s) \
+ le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_reserved_for_journal))
+
+#define is_block_in_log_or_reserved_area(s, block) \
+ block >= SB_JOURNAL_1st_RESERVED_BLOCK(s) \
+ && block < SB_JOURNAL_1st_RESERVED_BLOCK(s) + \
+ ((!is_reiserfs_jr(SB_DISK_SUPER_BLOCK(s)) ? \
+ SB_ONDISK_JOURNAL_SIZE(s) + 1 : SB_ONDISK_RESERVED_FOR_JOURNAL(s)))
+
+int is_reiserfs_3_5(struct reiserfs_super_block *rs);
+int is_reiserfs_3_6(struct reiserfs_super_block *rs);
+int is_reiserfs_jr(struct reiserfs_super_block *rs);
+
+/* ReiserFS leaves the first 64k unused, so that partition labels have
+ enough space. If someone wants to write a fancy bootloader that
+ needs more than 64k, let us know, and this will be increased in size.
+ This number must be larger than than the largest block size on any
+ platform, or code will break. -Hans */
+#define REISERFS_DISK_OFFSET_IN_BYTES (64 * 1024)
+#define REISERFS_FIRST_BLOCK unused_define
+#define REISERFS_JOURNAL_OFFSET_IN_BYTES REISERFS_DISK_OFFSET_IN_BYTES
+
+/* the spot for the super in versions 3.5 - 3.5.10 (inclusive) */
+#define REISERFS_OLD_DISK_OFFSET_IN_BYTES (8 * 1024)
+
+/* reiserfs internal error code (used by search_by_key and fix_nodes)) */
+#define CARRY_ON 0
+#define REPEAT_SEARCH -1
+#define IO_ERROR -2
+#define NO_DISK_SPACE -3
+#define NO_BALANCING_NEEDED (-4)
+#define NO_MORE_UNUSED_CONTIGUOUS_BLOCKS (-5)
+#define QUOTA_EXCEEDED -6
+
+typedef __u32 b_blocknr_t;
+typedef __le32 unp_t;
+
+struct unfm_nodeinfo {
+ unp_t unfm_nodenum;
+ unsigned short unfm_freespace;
+};
+
+/* there are two formats of keys: 3.5 and 3.6
+ */
+#define KEY_FORMAT_3_5 0
+#define KEY_FORMAT_3_6 1
+
+/* there are two stat datas */
+#define STAT_DATA_V1 0
+#define STAT_DATA_V2 1
+
+static inline struct reiserfs_inode_info *REISERFS_I(const struct inode *inode)
+{
+ return container_of(inode, struct reiserfs_inode_info, vfs_inode);
+}
+
+static inline struct reiserfs_sb_info *REISERFS_SB(const struct super_block *sb)
+{
+ return sb->s_fs_info;
+}
+
+/* Don't trust REISERFS_SB(sb)->s_bmap_nr, it's a u16
+ * which overflows on large file systems. */
+static inline __u32 reiserfs_bmap_count(struct super_block *sb)
+{
+ return (SB_BLOCK_COUNT(sb) - 1) / (sb->s_blocksize * 8) + 1;
+}
+
+static inline int bmap_would_wrap(unsigned bmap_nr)
+{
+ return bmap_nr > ((1LL << 16) - 1);
+}
+
+/** this says about version of key of all items (but stat data) the
+ object consists of */
+#define get_inode_item_key_version( inode ) \
+ ((REISERFS_I(inode)->i_flags & i_item_key_version_mask) ? KEY_FORMAT_3_6 : KEY_FORMAT_3_5)
+
+#define set_inode_item_key_version( inode, version ) \
+ ({ if((version)==KEY_FORMAT_3_6) \
+ REISERFS_I(inode)->i_flags |= i_item_key_version_mask; \
+ else \
+ REISERFS_I(inode)->i_flags &= ~i_item_key_version_mask; })
+
+#define get_inode_sd_version(inode) \
+ ((REISERFS_I(inode)->i_flags & i_stat_data_version_mask) ? STAT_DATA_V2 : STAT_DATA_V1)
+
+#define set_inode_sd_version(inode, version) \
+ ({ if((version)==STAT_DATA_V2) \
+ REISERFS_I(inode)->i_flags |= i_stat_data_version_mask; \
+ else \
+ REISERFS_I(inode)->i_flags &= ~i_stat_data_version_mask; })
+
+/* This is an aggressive tail suppression policy, I am hoping it
+ improves our benchmarks. The principle behind it is that percentage
+ space saving is what matters, not absolute space saving. This is
+ non-intuitive, but it helps to understand it if you consider that the
+ cost to access 4 blocks is not much more than the cost to access 1
+ block, if you have to do a seek and rotate. A tail risks a
+ non-linear disk access that is significant as a percentage of total
+ time cost for a 4 block file and saves an amount of space that is
+ less significant as a percentage of space, or so goes the hypothesis.
+ -Hans */
+#define STORE_TAIL_IN_UNFM_S1(n_file_size,n_tail_size,n_block_size) \
+(\
+ (!(n_tail_size)) || \
+ (((n_tail_size) > MAX_DIRECT_ITEM_LEN(n_block_size)) || \
+ ( (n_file_size) >= (n_block_size) * 4 ) || \
+ ( ( (n_file_size) >= (n_block_size) * 3 ) && \
+ ( (n_tail_size) >= (MAX_DIRECT_ITEM_LEN(n_block_size))/4) ) || \
+ ( ( (n_file_size) >= (n_block_size) * 2 ) && \
+ ( (n_tail_size) >= (MAX_DIRECT_ITEM_LEN(n_block_size))/2) ) || \
+ ( ( (n_file_size) >= (n_block_size) ) && \
+ ( (n_tail_size) >= (MAX_DIRECT_ITEM_LEN(n_block_size) * 3)/4) ) ) \
+)
+
+/* Another strategy for tails, this one means only create a tail if all the
+ file would fit into one DIRECT item.
+ Primary intention for this one is to increase performance by decreasing
+ seeking.
+*/
+#define STORE_TAIL_IN_UNFM_S2(n_file_size,n_tail_size,n_block_size) \
+(\
+ (!(n_tail_size)) || \
+ (((n_file_size) > MAX_DIRECT_ITEM_LEN(n_block_size)) ) \
+)
+
+/*
+ * values for s_umount_state field
+ */
+#define REISERFS_VALID_FS 1
+#define REISERFS_ERROR_FS 2
+
+//
+// there are 5 item types currently
+//
+#define TYPE_STAT_DATA 0
+#define TYPE_INDIRECT 1
+#define TYPE_DIRECT 2
+#define TYPE_DIRENTRY 3
+#define TYPE_MAXTYPE 3
+#define TYPE_ANY 15 // FIXME: comment is required
+
+/***************************************************************************/
+/* KEY & ITEM HEAD */
+/***************************************************************************/
+
+//
+// directories use this key as well as old files
+//
+struct offset_v1 {
+ __le32 k_offset;
+ __le32 k_uniqueness;
+} __attribute__ ((__packed__));
+
+struct offset_v2 {
+ __le64 v;
+} __attribute__ ((__packed__));
+
+static inline __u16 offset_v2_k_type(const struct offset_v2 *v2)
+{
+ __u8 type = le64_to_cpu(v2->v) >> 60;
+ return (type <= TYPE_MAXTYPE) ? type : TYPE_ANY;
+}
+
+static inline void set_offset_v2_k_type(struct offset_v2 *v2, int type)
+{
+ v2->v =
+ (v2->v & cpu_to_le64(~0ULL >> 4)) | cpu_to_le64((__u64) type << 60);
+}
+
+static inline loff_t offset_v2_k_offset(const struct offset_v2 *v2)
+{
+ return le64_to_cpu(v2->v) & (~0ULL >> 4);
+}
+
+static inline void set_offset_v2_k_offset(struct offset_v2 *v2, loff_t offset)
+{
+ offset &= (~0ULL >> 4);
+ v2->v = (v2->v & cpu_to_le64(15ULL << 60)) | cpu_to_le64(offset);
+}
+
+/* Key of an item determines its location in the S+tree, and
+ is composed of 4 components */
+struct reiserfs_key {
+ __le32 k_dir_id; /* packing locality: by default parent
+ directory object id */
+ __le32 k_objectid; /* object identifier */
+ union {
+ struct offset_v1 k_offset_v1;
+ struct offset_v2 k_offset_v2;
+ } __attribute__ ((__packed__)) u;
+} __attribute__ ((__packed__));
+
+struct in_core_key {
+ __u32 k_dir_id; /* packing locality: by default parent
+ directory object id */
+ __u32 k_objectid; /* object identifier */
+ __u64 k_offset;
+ __u8 k_type;
+};
+
+struct cpu_key {
+ struct in_core_key on_disk_key;
+ int version;
+ int key_length; /* 3 in all cases but direct2indirect and
+ indirect2direct conversion */
+};
+
+/* Our function for comparing keys can compare keys of different
+ lengths. It takes as a parameter the length of the keys it is to
+ compare. These defines are used in determining what is to be passed
+ to it as that parameter. */
+#define REISERFS_FULL_KEY_LEN 4
+#define REISERFS_SHORT_KEY_LEN 2
+
+/* The result of the key compare */
+#define FIRST_GREATER 1
+#define SECOND_GREATER -1
+#define KEYS_IDENTICAL 0
+#define KEY_FOUND 1
+#define KEY_NOT_FOUND 0
+
+#define KEY_SIZE (sizeof(struct reiserfs_key))
+#define SHORT_KEY_SIZE (sizeof (__u32) + sizeof (__u32))
+
+/* return values for search_by_key and clones */
+#define ITEM_FOUND 1
+#define ITEM_NOT_FOUND 0
+#define ENTRY_FOUND 1
+#define ENTRY_NOT_FOUND 0
+#define DIRECTORY_NOT_FOUND -1
+#define REGULAR_FILE_FOUND -2
+#define DIRECTORY_FOUND -3
+#define BYTE_FOUND 1
+#define BYTE_NOT_FOUND 0
+#define FILE_NOT_FOUND -1
+
+#define POSITION_FOUND 1
+#define POSITION_NOT_FOUND 0
+
+// return values for reiserfs_find_entry and search_by_entry_key
+#define NAME_FOUND 1
+#define NAME_NOT_FOUND 0
+#define GOTO_PREVIOUS_ITEM 2
+#define NAME_FOUND_INVISIBLE 3
+
+/* Everything in the filesystem is stored as a set of items. The
+ item head contains the key of the item, its free space (for
+ indirect items) and specifies the location of the item itself
+ within the block. */
+
+struct item_head {
+ /* Everything in the tree is found by searching for it based on
+ * its key.*/
+ struct reiserfs_key ih_key;
+ union {
+ /* The free space in the last unformatted node of an
+ indirect item if this is an indirect item. This
+ equals 0xFFFF iff this is a direct item or stat data
+ item. Note that the key, not this field, is used to
+ determine the item type, and thus which field this
+ union contains. */
+ __le16 ih_free_space_reserved;
+ /* Iff this is a directory item, this field equals the
+ number of directory entries in the directory item. */
+ __le16 ih_entry_count;
+ } __attribute__ ((__packed__)) u;
+ __le16 ih_item_len; /* total size of the item body */
+ __le16 ih_item_location; /* an offset to the item body
+ * within the block */
+ __le16 ih_version; /* 0 for all old items, 2 for new
+ ones. Highest bit is set by fsck
+ temporary, cleaned after all
+ done */
+} __attribute__ ((__packed__));
+/* size of item header */
+#define IH_SIZE (sizeof(struct item_head))
+
+#define ih_free_space(ih) le16_to_cpu((ih)->u.ih_free_space_reserved)
+#define ih_version(ih) le16_to_cpu((ih)->ih_version)
+#define ih_entry_count(ih) le16_to_cpu((ih)->u.ih_entry_count)
+#define ih_location(ih) le16_to_cpu((ih)->ih_item_location)
+#define ih_item_len(ih) le16_to_cpu((ih)->ih_item_len)
+
+#define put_ih_free_space(ih, val) do { (ih)->u.ih_free_space_reserved = cpu_to_le16(val); } while(0)
+#define put_ih_version(ih, val) do { (ih)->ih_version = cpu_to_le16(val); } while (0)
+#define put_ih_entry_count(ih, val) do { (ih)->u.ih_entry_count = cpu_to_le16(val); } while (0)
+#define put_ih_location(ih, val) do { (ih)->ih_item_location = cpu_to_le16(val); } while (0)
+#define put_ih_item_len(ih, val) do { (ih)->ih_item_len = cpu_to_le16(val); } while (0)
+
+#define unreachable_item(ih) (ih_version(ih) & (1 << 15))
+
+#define get_ih_free_space(ih) (ih_version (ih) == KEY_FORMAT_3_6 ? 0 : ih_free_space (ih))
+#define set_ih_free_space(ih,val) put_ih_free_space((ih), ((ih_version(ih) == KEY_FORMAT_3_6) ? 0 : (val)))
+
+/* these operate on indirect items, where you've got an array of ints
+** at a possibly unaligned location. These are a noop on ia32
+**
+** p is the array of __u32, i is the index into the array, v is the value
+** to store there.
+*/
+#define get_block_num(p, i) get_unaligned_le32((p) + (i))
+#define put_block_num(p, i, v) put_unaligned_le32((v), (p) + (i))
+
+//
+// in old version uniqueness field shows key type
+//
+#define V1_SD_UNIQUENESS 0
+#define V1_INDIRECT_UNIQUENESS 0xfffffffe
+#define V1_DIRECT_UNIQUENESS 0xffffffff
+#define V1_DIRENTRY_UNIQUENESS 500
+#define V1_ANY_UNIQUENESS 555 // FIXME: comment is required
+
+//
+// here are conversion routines
+//
+static inline int uniqueness2type(__u32 uniqueness) CONSTF;
+static inline int uniqueness2type(__u32 uniqueness)
+{
+ switch ((int)uniqueness) {
+ case V1_SD_UNIQUENESS:
+ return TYPE_STAT_DATA;
+ case V1_INDIRECT_UNIQUENESS:
+ return TYPE_INDIRECT;
+ case V1_DIRECT_UNIQUENESS:
+ return TYPE_DIRECT;
+ case V1_DIRENTRY_UNIQUENESS:
+ return TYPE_DIRENTRY;
+ case V1_ANY_UNIQUENESS:
+ default:
+ return TYPE_ANY;
+ }
+}
+
+static inline __u32 type2uniqueness(int type) CONSTF;
+static inline __u32 type2uniqueness(int type)
+{
+ switch (type) {
+ case TYPE_STAT_DATA:
+ return V1_SD_UNIQUENESS;
+ case TYPE_INDIRECT:
+ return V1_INDIRECT_UNIQUENESS;
+ case TYPE_DIRECT:
+ return V1_DIRECT_UNIQUENESS;
+ case TYPE_DIRENTRY:
+ return V1_DIRENTRY_UNIQUENESS;
+ case TYPE_ANY:
+ default:
+ return V1_ANY_UNIQUENESS;
+ }
+}
+
+//
+// key is pointer to on disk key which is stored in le, result is cpu,
+// there is no way to get version of object from key, so, provide
+// version to these defines
+//
+static inline loff_t le_key_k_offset(int version,
+ const struct reiserfs_key *key)
+{
+ return (version == KEY_FORMAT_3_5) ?
+ le32_to_cpu(key->u.k_offset_v1.k_offset) :
+ offset_v2_k_offset(&(key->u.k_offset_v2));
+}
+
+static inline loff_t le_ih_k_offset(const struct item_head *ih)
+{
+ return le_key_k_offset(ih_version(ih), &(ih->ih_key));
+}
+
+static inline loff_t le_key_k_type(int version, const struct reiserfs_key *key)
+{
+ return (version == KEY_FORMAT_3_5) ?
+ uniqueness2type(le32_to_cpu(key->u.k_offset_v1.k_uniqueness)) :
+ offset_v2_k_type(&(key->u.k_offset_v2));
+}
+
+static inline loff_t le_ih_k_type(const struct item_head *ih)
+{
+ return le_key_k_type(ih_version(ih), &(ih->ih_key));
+}
+
+static inline void set_le_key_k_offset(int version, struct reiserfs_key *key,
+ loff_t offset)
+{
+ (version == KEY_FORMAT_3_5) ? (void)(key->u.k_offset_v1.k_offset = cpu_to_le32(offset)) : /* jdm check */
+ (void)(set_offset_v2_k_offset(&(key->u.k_offset_v2), offset));
+}
+
+static inline void set_le_ih_k_offset(struct item_head *ih, loff_t offset)
+{
+ set_le_key_k_offset(ih_version(ih), &(ih->ih_key), offset);
+}
+
+static inline void set_le_key_k_type(int version, struct reiserfs_key *key,
+ int type)
+{
+ (version == KEY_FORMAT_3_5) ?
+ (void)(key->u.k_offset_v1.k_uniqueness =
+ cpu_to_le32(type2uniqueness(type)))
+ : (void)(set_offset_v2_k_type(&(key->u.k_offset_v2), type));
+}
+
+static inline void set_le_ih_k_type(struct item_head *ih, int type)
+{
+ set_le_key_k_type(ih_version(ih), &(ih->ih_key), type);
+}
+
+static inline int is_direntry_le_key(int version, struct reiserfs_key *key)
+{
+ return le_key_k_type(version, key) == TYPE_DIRENTRY;
+}
+
+static inline int is_direct_le_key(int version, struct reiserfs_key *key)
+{
+ return le_key_k_type(version, key) == TYPE_DIRECT;
+}
+
+static inline int is_indirect_le_key(int version, struct reiserfs_key *key)
+{
+ return le_key_k_type(version, key) == TYPE_INDIRECT;
+}
+
+static inline int is_statdata_le_key(int version, struct reiserfs_key *key)
+{
+ return le_key_k_type(version, key) == TYPE_STAT_DATA;
+}
+
+//
+// item header has version.
+//
+static inline int is_direntry_le_ih(struct item_head *ih)
+{
+ return is_direntry_le_key(ih_version(ih), &ih->ih_key);
+}
+
+static inline int is_direct_le_ih(struct item_head *ih)
+{
+ return is_direct_le_key(ih_version(ih), &ih->ih_key);
+}
+
+static inline int is_indirect_le_ih(struct item_head *ih)
+{
+ return is_indirect_le_key(ih_version(ih), &ih->ih_key);
+}
+
+static inline int is_statdata_le_ih(struct item_head *ih)
+{
+ return is_statdata_le_key(ih_version(ih), &ih->ih_key);
+}
+
+//
+// key is pointer to cpu key, result is cpu
+//
+static inline loff_t cpu_key_k_offset(const struct cpu_key *key)
+{
+ return key->on_disk_key.k_offset;
+}
+
+static inline loff_t cpu_key_k_type(const struct cpu_key *key)
+{
+ return key->on_disk_key.k_type;
+}
+
+static inline void set_cpu_key_k_offset(struct cpu_key *key, loff_t offset)
+{
+ key->on_disk_key.k_offset = offset;
+}
+
+static inline void set_cpu_key_k_type(struct cpu_key *key, int type)
+{
+ key->on_disk_key.k_type = type;
+}
+
+static inline void cpu_key_k_offset_dec(struct cpu_key *key)
+{
+ key->on_disk_key.k_offset--;
+}
+
+#define is_direntry_cpu_key(key) (cpu_key_k_type (key) == TYPE_DIRENTRY)
+#define is_direct_cpu_key(key) (cpu_key_k_type (key) == TYPE_DIRECT)
+#define is_indirect_cpu_key(key) (cpu_key_k_type (key) == TYPE_INDIRECT)
+#define is_statdata_cpu_key(key) (cpu_key_k_type (key) == TYPE_STAT_DATA)
+
+/* are these used ? */
+#define is_direntry_cpu_ih(ih) (is_direntry_cpu_key (&((ih)->ih_key)))
+#define is_direct_cpu_ih(ih) (is_direct_cpu_key (&((ih)->ih_key)))
+#define is_indirect_cpu_ih(ih) (is_indirect_cpu_key (&((ih)->ih_key)))
+#define is_statdata_cpu_ih(ih) (is_statdata_cpu_key (&((ih)->ih_key)))
+
+#define I_K_KEY_IN_ITEM(ih, key, n_blocksize) \
+ (!COMP_SHORT_KEYS(ih, key) && \
+ I_OFF_BYTE_IN_ITEM(ih, k_offset(key), n_blocksize))
+
+/* maximal length of item */
+#define MAX_ITEM_LEN(block_size) (block_size - BLKH_SIZE - IH_SIZE)
+#define MIN_ITEM_LEN 1
+
+/* object identifier for root dir */
+#define REISERFS_ROOT_OBJECTID 2
+#define REISERFS_ROOT_PARENT_OBJECTID 1
+
+extern struct reiserfs_key root_key;
+
+/*
+ * Picture represents a leaf of the S+tree
+ * ______________________________________________________
+ * | | Array of | | |
+ * |Block | Object-Item | F r e e | Objects- |
+ * | head | Headers | S p a c e | Items |
+ * |______|_______________|___________________|___________|
+ */
+
+/* Header of a disk block. More precisely, header of a formatted leaf
+ or internal node, and not the header of an unformatted node. */
+struct block_head {
+ __le16 blk_level; /* Level of a block in the tree. */
+ __le16 blk_nr_item; /* Number of keys/items in a block. */
+ __le16 blk_free_space; /* Block free space in bytes. */
+ __le16 blk_reserved;
+ /* dump this in v4/planA */
+ struct reiserfs_key blk_right_delim_key; /* kept only for compatibility */
+};
+
+#define BLKH_SIZE (sizeof(struct block_head))
+#define blkh_level(p_blkh) (le16_to_cpu((p_blkh)->blk_level))
+#define blkh_nr_item(p_blkh) (le16_to_cpu((p_blkh)->blk_nr_item))
+#define blkh_free_space(p_blkh) (le16_to_cpu((p_blkh)->blk_free_space))
+#define blkh_reserved(p_blkh) (le16_to_cpu((p_blkh)->blk_reserved))
+#define set_blkh_level(p_blkh,val) ((p_blkh)->blk_level = cpu_to_le16(val))
+#define set_blkh_nr_item(p_blkh,val) ((p_blkh)->blk_nr_item = cpu_to_le16(val))
+#define set_blkh_free_space(p_blkh,val) ((p_blkh)->blk_free_space = cpu_to_le16(val))
+#define set_blkh_reserved(p_blkh,val) ((p_blkh)->blk_reserved = cpu_to_le16(val))
+#define blkh_right_delim_key(p_blkh) ((p_blkh)->blk_right_delim_key)
+#define set_blkh_right_delim_key(p_blkh,val) ((p_blkh)->blk_right_delim_key = val)
+
+/*
+ * values for blk_level field of the struct block_head
+ */
+
+#define FREE_LEVEL 0 /* when node gets removed from the tree its
+ blk_level is set to FREE_LEVEL. It is then
+ used to see whether the node is still in the
+ tree */
+
+#define DISK_LEAF_NODE_LEVEL 1 /* Leaf node level. */
+
+/* Given the buffer head of a formatted node, resolve to the block head of that node. */
+#define B_BLK_HEAD(bh) ((struct block_head *)((bh)->b_data))
+/* Number of items that are in buffer. */
+#define B_NR_ITEMS(bh) (blkh_nr_item(B_BLK_HEAD(bh)))
+#define B_LEVEL(bh) (blkh_level(B_BLK_HEAD(bh)))
+#define B_FREE_SPACE(bh) (blkh_free_space(B_BLK_HEAD(bh)))
+
+#define PUT_B_NR_ITEMS(bh, val) do { set_blkh_nr_item(B_BLK_HEAD(bh), val); } while (0)
+#define PUT_B_LEVEL(bh, val) do { set_blkh_level(B_BLK_HEAD(bh), val); } while (0)
+#define PUT_B_FREE_SPACE(bh, val) do { set_blkh_free_space(B_BLK_HEAD(bh), val); } while (0)
+
+/* Get right delimiting key. -- little endian */
+#define B_PRIGHT_DELIM_KEY(bh) (&(blk_right_delim_key(B_BLK_HEAD(bh))))
+
+/* Does the buffer contain a disk leaf. */
+#define B_IS_ITEMS_LEVEL(bh) (B_LEVEL(bh) == DISK_LEAF_NODE_LEVEL)
+
+/* Does the buffer contain a disk internal node */
+#define B_IS_KEYS_LEVEL(bh) (B_LEVEL(bh) > DISK_LEAF_NODE_LEVEL \
+ && B_LEVEL(bh) <= MAX_HEIGHT)
+
+/***************************************************************************/
+/* STAT DATA */
+/***************************************************************************/
+
+//
+// old stat data is 32 bytes long. We are going to distinguish new one by
+// different size
+//
+struct stat_data_v1 {
+ __le16 sd_mode; /* file type, permissions */
+ __le16 sd_nlink; /* number of hard links */
+ __le16 sd_uid; /* owner */
+ __le16 sd_gid; /* group */
+ __le32 sd_size; /* file size */
+ __le32 sd_atime; /* time of last access */
+ __le32 sd_mtime; /* time file was last modified */
+ __le32 sd_ctime; /* time inode (stat data) was last changed (except changes to sd_atime and sd_mtime) */
+ union {
+ __le32 sd_rdev;
+ __le32 sd_blocks; /* number of blocks file uses */
+ } __attribute__ ((__packed__)) u;
+ __le32 sd_first_direct_byte; /* first byte of file which is stored
+ in a direct item: except that if it
+ equals 1 it is a symlink and if it
+ equals ~(__u32)0 there is no
+ direct item. The existence of this
+ field really grates on me. Let's
+ replace it with a macro based on
+ sd_size and our tail suppression
+ policy. Someday. -Hans */
+} __attribute__ ((__packed__));
+
+#define SD_V1_SIZE (sizeof(struct stat_data_v1))
+#define stat_data_v1(ih) (ih_version (ih) == KEY_FORMAT_3_5)
+#define sd_v1_mode(sdp) (le16_to_cpu((sdp)->sd_mode))
+#define set_sd_v1_mode(sdp,v) ((sdp)->sd_mode = cpu_to_le16(v))
+#define sd_v1_nlink(sdp) (le16_to_cpu((sdp)->sd_nlink))
+#define set_sd_v1_nlink(sdp,v) ((sdp)->sd_nlink = cpu_to_le16(v))
+#define sd_v1_uid(sdp) (le16_to_cpu((sdp)->sd_uid))
+#define set_sd_v1_uid(sdp,v) ((sdp)->sd_uid = cpu_to_le16(v))
+#define sd_v1_gid(sdp) (le16_to_cpu((sdp)->sd_gid))
+#define set_sd_v1_gid(sdp,v) ((sdp)->sd_gid = cpu_to_le16(v))
+#define sd_v1_size(sdp) (le32_to_cpu((sdp)->sd_size))
+#define set_sd_v1_size(sdp,v) ((sdp)->sd_size = cpu_to_le32(v))
+#define sd_v1_atime(sdp) (le32_to_cpu((sdp)->sd_atime))
+#define set_sd_v1_atime(sdp,v) ((sdp)->sd_atime = cpu_to_le32(v))
+#define sd_v1_mtime(sdp) (le32_to_cpu((sdp)->sd_mtime))
+#define set_sd_v1_mtime(sdp,v) ((sdp)->sd_mtime = cpu_to_le32(v))
+#define sd_v1_ctime(sdp) (le32_to_cpu((sdp)->sd_ctime))
+#define set_sd_v1_ctime(sdp,v) ((sdp)->sd_ctime = cpu_to_le32(v))
+#define sd_v1_rdev(sdp) (le32_to_cpu((sdp)->u.sd_rdev))
+#define set_sd_v1_rdev(sdp,v) ((sdp)->u.sd_rdev = cpu_to_le32(v))
+#define sd_v1_blocks(sdp) (le32_to_cpu((sdp)->u.sd_blocks))
+#define set_sd_v1_blocks(sdp,v) ((sdp)->u.sd_blocks = cpu_to_le32(v))
+#define sd_v1_first_direct_byte(sdp) \
+ (le32_to_cpu((sdp)->sd_first_direct_byte))
+#define set_sd_v1_first_direct_byte(sdp,v) \
+ ((sdp)->sd_first_direct_byte = cpu_to_le32(v))
+
+/* inode flags stored in sd_attrs (nee sd_reserved) */
+
+/* we want common flags to have the same values as in ext2,
+ so chattr(1) will work without problems */
+#define REISERFS_IMMUTABLE_FL FS_IMMUTABLE_FL
+#define REISERFS_APPEND_FL FS_APPEND_FL
+#define REISERFS_SYNC_FL FS_SYNC_FL
+#define REISERFS_NOATIME_FL FS_NOATIME_FL
+#define REISERFS_NODUMP_FL FS_NODUMP_FL
+#define REISERFS_SECRM_FL FS_SECRM_FL
+#define REISERFS_UNRM_FL FS_UNRM_FL
+#define REISERFS_COMPR_FL FS_COMPR_FL
+#define REISERFS_NOTAIL_FL FS_NOTAIL_FL
+
+/* persistent flags that file inherits from the parent directory */
+#define REISERFS_INHERIT_MASK ( REISERFS_IMMUTABLE_FL | \
+ REISERFS_SYNC_FL | \
+ REISERFS_NOATIME_FL | \
+ REISERFS_NODUMP_FL | \
+ REISERFS_SECRM_FL | \
+ REISERFS_COMPR_FL | \
+ REISERFS_NOTAIL_FL )
+
+/* Stat Data on disk (reiserfs version of UFS disk inode minus the
+ address blocks) */
+struct stat_data {
+ __le16 sd_mode; /* file type, permissions */
+ __le16 sd_attrs; /* persistent inode flags */
+ __le32 sd_nlink; /* number of hard links */
+ __le64 sd_size; /* file size */
+ __le32 sd_uid; /* owner */
+ __le32 sd_gid; /* group */
+ __le32 sd_atime; /* time of last access */
+ __le32 sd_mtime; /* time file was last modified */
+ __le32 sd_ctime; /* time inode (stat data) was last changed (except changes to sd_atime and sd_mtime) */
+ __le32 sd_blocks;
+ union {
+ __le32 sd_rdev;
+ __le32 sd_generation;
+ //__le32 sd_first_direct_byte;
+ /* first byte of file which is stored in a
+ direct item: except that if it equals 1
+ it is a symlink and if it equals
+ ~(__u32)0 there is no direct item. The
+ existence of this field really grates
+ on me. Let's replace it with a macro
+ based on sd_size and our tail
+ suppression policy? */
+ } __attribute__ ((__packed__)) u;
+} __attribute__ ((__packed__));
+//
+// this is 44 bytes long
+//
+#define SD_SIZE (sizeof(struct stat_data))
+#define SD_V2_SIZE SD_SIZE
+#define stat_data_v2(ih) (ih_version (ih) == KEY_FORMAT_3_6)
+#define sd_v2_mode(sdp) (le16_to_cpu((sdp)->sd_mode))
+#define set_sd_v2_mode(sdp,v) ((sdp)->sd_mode = cpu_to_le16(v))
+/* sd_reserved */
+/* set_sd_reserved */
+#define sd_v2_nlink(sdp) (le32_to_cpu((sdp)->sd_nlink))
+#define set_sd_v2_nlink(sdp,v) ((sdp)->sd_nlink = cpu_to_le32(v))
+#define sd_v2_size(sdp) (le64_to_cpu((sdp)->sd_size))
+#define set_sd_v2_size(sdp,v) ((sdp)->sd_size = cpu_to_le64(v))
+#define sd_v2_uid(sdp) (le32_to_cpu((sdp)->sd_uid))
+#define set_sd_v2_uid(sdp,v) ((sdp)->sd_uid = cpu_to_le32(v))
+#define sd_v2_gid(sdp) (le32_to_cpu((sdp)->sd_gid))
+#define set_sd_v2_gid(sdp,v) ((sdp)->sd_gid = cpu_to_le32(v))
+#define sd_v2_atime(sdp) (le32_to_cpu((sdp)->sd_atime))
+#define set_sd_v2_atime(sdp,v) ((sdp)->sd_atime = cpu_to_le32(v))
+#define sd_v2_mtime(sdp) (le32_to_cpu((sdp)->sd_mtime))
+#define set_sd_v2_mtime(sdp,v) ((sdp)->sd_mtime = cpu_to_le32(v))
+#define sd_v2_ctime(sdp) (le32_to_cpu((sdp)->sd_ctime))
+#define set_sd_v2_ctime(sdp,v) ((sdp)->sd_ctime = cpu_to_le32(v))
+#define sd_v2_blocks(sdp) (le32_to_cpu((sdp)->sd_blocks))
+#define set_sd_v2_blocks(sdp,v) ((sdp)->sd_blocks = cpu_to_le32(v))
+#define sd_v2_rdev(sdp) (le32_to_cpu((sdp)->u.sd_rdev))
+#define set_sd_v2_rdev(sdp,v) ((sdp)->u.sd_rdev = cpu_to_le32(v))
+#define sd_v2_generation(sdp) (le32_to_cpu((sdp)->u.sd_generation))
+#define set_sd_v2_generation(sdp,v) ((sdp)->u.sd_generation = cpu_to_le32(v))
+#define sd_v2_attrs(sdp) (le16_to_cpu((sdp)->sd_attrs))
+#define set_sd_v2_attrs(sdp,v) ((sdp)->sd_attrs = cpu_to_le16(v))
+
+/***************************************************************************/
+/* DIRECTORY STRUCTURE */
+/***************************************************************************/
+/*
+ Picture represents the structure of directory items
+ ________________________________________________
+ | Array of | | | | | |
+ | directory |N-1| N-2 | .... | 1st |0th|
+ | entry headers | | | | | |
+ |_______________|___|_____|________|_______|___|
+ <---- directory entries ------>
+
+ First directory item has k_offset component 1. We store "." and ".."
+ in one item, always, we never split "." and ".." into differing
+ items. This makes, among other things, the code for removing
+ directories simpler. */
+#define SD_OFFSET 0
+#define SD_UNIQUENESS 0
+#define DOT_OFFSET 1
+#define DOT_DOT_OFFSET 2
+#define DIRENTRY_UNIQUENESS 500
+
+/* */
+#define FIRST_ITEM_OFFSET 1
+
+/*
+ Q: How to get key of object pointed to by entry from entry?
+
+ A: Each directory entry has its header. This header has deh_dir_id and deh_objectid fields, those are key
+ of object, entry points to */
+
+/* NOT IMPLEMENTED:
+ Directory will someday contain stat data of object */
+
+struct reiserfs_de_head {
+ __le32 deh_offset; /* third component of the directory entry key */
+ __le32 deh_dir_id; /* objectid of the parent directory of the object, that is referenced
+ by directory entry */
+ __le32 deh_objectid; /* objectid of the object, that is referenced by directory entry */
+ __le16 deh_location; /* offset of name in the whole item */
+ __le16 deh_state; /* whether 1) entry contains stat data (for future), and 2) whether
+ entry is hidden (unlinked) */
+} __attribute__ ((__packed__));
+#define DEH_SIZE sizeof(struct reiserfs_de_head)
+#define deh_offset(p_deh) (le32_to_cpu((p_deh)->deh_offset))
+#define deh_dir_id(p_deh) (le32_to_cpu((p_deh)->deh_dir_id))
+#define deh_objectid(p_deh) (le32_to_cpu((p_deh)->deh_objectid))
+#define deh_location(p_deh) (le16_to_cpu((p_deh)->deh_location))
+#define deh_state(p_deh) (le16_to_cpu((p_deh)->deh_state))
+
+#define put_deh_offset(p_deh,v) ((p_deh)->deh_offset = cpu_to_le32((v)))
+#define put_deh_dir_id(p_deh,v) ((p_deh)->deh_dir_id = cpu_to_le32((v)))
+#define put_deh_objectid(p_deh,v) ((p_deh)->deh_objectid = cpu_to_le32((v)))
+#define put_deh_location(p_deh,v) ((p_deh)->deh_location = cpu_to_le16((v)))
+#define put_deh_state(p_deh,v) ((p_deh)->deh_state = cpu_to_le16((v)))
+
+/* empty directory contains two entries "." and ".." and their headers */
+#define EMPTY_DIR_SIZE \
+(DEH_SIZE * 2 + ROUND_UP (strlen (".")) + ROUND_UP (strlen ("..")))
+
+/* old format directories have this size when empty */
+#define EMPTY_DIR_SIZE_V1 (DEH_SIZE * 2 + 3)
+
+#define DEH_Statdata 0 /* not used now */
+#define DEH_Visible 2
+
+/* 64 bit systems (and the S/390) need to be aligned explicitly -jdm */
+#if BITS_PER_LONG == 64 || defined(__s390__) || defined(__hppa__)
+# define ADDR_UNALIGNED_BITS (3)
+#endif
+
+/* These are only used to manipulate deh_state.
+ * Because of this, we'll use the ext2_ bit routines,
+ * since they are little endian */
+#ifdef ADDR_UNALIGNED_BITS
+
+# define aligned_address(addr) ((void *)((long)(addr) & ~((1UL << ADDR_UNALIGNED_BITS) - 1)))
+# define unaligned_offset(addr) (((int)((long)(addr) & ((1 << ADDR_UNALIGNED_BITS) - 1))) << 3)
+
+# define set_bit_unaligned(nr, addr) \
+ __test_and_set_bit_le((nr) + unaligned_offset(addr), aligned_address(addr))
+# define clear_bit_unaligned(nr, addr) \
+ __test_and_clear_bit_le((nr) + unaligned_offset(addr), aligned_address(addr))
+# define test_bit_unaligned(nr, addr) \
+ test_bit_le((nr) + unaligned_offset(addr), aligned_address(addr))
+
+#else
+
+# define set_bit_unaligned(nr, addr) __test_and_set_bit_le(nr, addr)
+# define clear_bit_unaligned(nr, addr) __test_and_clear_bit_le(nr, addr)
+# define test_bit_unaligned(nr, addr) test_bit_le(nr, addr)
+
+#endif
+
+#define mark_de_with_sd(deh) set_bit_unaligned (DEH_Statdata, &((deh)->deh_state))
+#define mark_de_without_sd(deh) clear_bit_unaligned (DEH_Statdata, &((deh)->deh_state))
+#define mark_de_visible(deh) set_bit_unaligned (DEH_Visible, &((deh)->deh_state))
+#define mark_de_hidden(deh) clear_bit_unaligned (DEH_Visible, &((deh)->deh_state))
+
+#define de_with_sd(deh) test_bit_unaligned (DEH_Statdata, &((deh)->deh_state))
+#define de_visible(deh) test_bit_unaligned (DEH_Visible, &((deh)->deh_state))
+#define de_hidden(deh) !test_bit_unaligned (DEH_Visible, &((deh)->deh_state))
+
+extern void make_empty_dir_item_v1(char *body, __le32 dirid, __le32 objid,
+ __le32 par_dirid, __le32 par_objid);
+extern void make_empty_dir_item(char *body, __le32 dirid, __le32 objid,
+ __le32 par_dirid, __le32 par_objid);
+
+/* array of the entry headers */
+ /* get item body */
+#define B_I_PITEM(bh,ih) ( (bh)->b_data + ih_location(ih) )
+#define B_I_DEH(bh,ih) ((struct reiserfs_de_head *)(B_I_PITEM(bh,ih)))
+
+/* length of the directory entry in directory item. This define
+ calculates length of i-th directory entry using directory entry
+ locations from dir entry head. When it calculates length of 0-th
+ directory entry, it uses length of whole item in place of entry
+ location of the non-existent following entry in the calculation.
+ See picture above.*/
+/*
+#define I_DEH_N_ENTRY_LENGTH(ih,deh,i) \
+((i) ? (deh_location((deh)-1) - deh_location((deh))) : (ih_item_len((ih)) - deh_location((deh))))
+*/
+static inline int entry_length(const struct buffer_head *bh,
+ const struct item_head *ih, int pos_in_item)
+{
+ struct reiserfs_de_head *deh;
+
+ deh = B_I_DEH(bh, ih) + pos_in_item;
+ if (pos_in_item)
+ return deh_location(deh - 1) - deh_location(deh);
+
+ return ih_item_len(ih) - deh_location(deh);
+}
+
+/* number of entries in the directory item, depends on ENTRY_COUNT being at the start of directory dynamic data. */
+#define I_ENTRY_COUNT(ih) (ih_entry_count((ih)))
+
+/* name by bh, ih and entry_num */
+#define B_I_E_NAME(bh,ih,entry_num) ((char *)(bh->b_data + ih_location(ih) + deh_location(B_I_DEH(bh,ih)+(entry_num))))
+
+// two entries per block (at least)
+#define REISERFS_MAX_NAME(block_size) 255
+
+/* this structure is used for operations on directory entries. It is
+ not a disk structure. */
+/* When reiserfs_find_entry or search_by_entry_key find directory
+ entry, they return filled reiserfs_dir_entry structure */
+struct reiserfs_dir_entry {
+ struct buffer_head *de_bh;
+ int de_item_num;
+ struct item_head *de_ih;
+ int de_entry_num;
+ struct reiserfs_de_head *de_deh;
+ int de_entrylen;
+ int de_namelen;
+ char *de_name;
+ unsigned long *de_gen_number_bit_string;
+
+ __u32 de_dir_id;
+ __u32 de_objectid;
+
+ struct cpu_key de_entry_key;
+};
+
+/* these defines are useful when a particular member of a reiserfs_dir_entry is needed */
+
+/* pointer to file name, stored in entry */
+#define B_I_DEH_ENTRY_FILE_NAME(bh,ih,deh) (B_I_PITEM (bh, ih) + deh_location(deh))
+
+/* length of name */
+#define I_DEH_N_ENTRY_FILE_NAME_LENGTH(ih,deh,entry_num) \
+(I_DEH_N_ENTRY_LENGTH (ih, deh, entry_num) - (de_with_sd (deh) ? SD_SIZE : 0))
+
+/* hash value occupies bits from 7 up to 30 */
+#define GET_HASH_VALUE(offset) ((offset) & 0x7fffff80LL)
+/* generation number occupies 7 bits starting from 0 up to 6 */
+#define GET_GENERATION_NUMBER(offset) ((offset) & 0x7fLL)
+#define MAX_GENERATION_NUMBER 127
+
+#define SET_GENERATION_NUMBER(offset,gen_number) (GET_HASH_VALUE(offset)|(gen_number))
+
+/*
+ * Picture represents an internal node of the reiserfs tree
+ * ______________________________________________________
+ * | | Array of | Array of | Free |
+ * |block | keys | pointers | space |
+ * | head | N | N+1 | |
+ * |______|_______________|___________________|___________|
+ */
+
+/***************************************************************************/
+/* DISK CHILD */
+/***************************************************************************/
+/* Disk child pointer: The pointer from an internal node of the tree
+ to a node that is on disk. */
+struct disk_child {
+ __le32 dc_block_number; /* Disk child's block number. */
+ __le16 dc_size; /* Disk child's used space. */
+ __le16 dc_reserved;
+};
+
+#define DC_SIZE (sizeof(struct disk_child))
+#define dc_block_number(dc_p) (le32_to_cpu((dc_p)->dc_block_number))
+#define dc_size(dc_p) (le16_to_cpu((dc_p)->dc_size))
+#define put_dc_block_number(dc_p, val) do { (dc_p)->dc_block_number = cpu_to_le32(val); } while(0)
+#define put_dc_size(dc_p, val) do { (dc_p)->dc_size = cpu_to_le16(val); } while(0)
+
+/* Get disk child by buffer header and position in the tree node. */
+#define B_N_CHILD(bh, n_pos) ((struct disk_child *)\
+((bh)->b_data + BLKH_SIZE + B_NR_ITEMS(bh) * KEY_SIZE + DC_SIZE * (n_pos)))
+
+/* Get disk child number by buffer header and position in the tree node. */
+#define B_N_CHILD_NUM(bh, n_pos) (dc_block_number(B_N_CHILD(bh, n_pos)))
+#define PUT_B_N_CHILD_NUM(bh, n_pos, val) \
+ (put_dc_block_number(B_N_CHILD(bh, n_pos), val))
+
+ /* maximal value of field child_size in structure disk_child */
+ /* child size is the combined size of all items and their headers */
+#define MAX_CHILD_SIZE(bh) ((int)( (bh)->b_size - BLKH_SIZE ))
+
+/* amount of used space in buffer (not including block head) */
+#define B_CHILD_SIZE(cur) (MAX_CHILD_SIZE(cur)-(B_FREE_SPACE(cur)))
+
+/* max and min number of keys in internal node */
+#define MAX_NR_KEY(bh) ( (MAX_CHILD_SIZE(bh)-DC_SIZE)/(KEY_SIZE+DC_SIZE) )
+#define MIN_NR_KEY(bh) (MAX_NR_KEY(bh)/2)
+
+/***************************************************************************/
+/* PATH STRUCTURES AND DEFINES */
+/***************************************************************************/
+
+/* Search_by_key fills up the path from the root to the leaf as it descends the tree looking for the
+ key. It uses reiserfs_bread to try to find buffers in the cache given their block number. If it
+ does not find them in the cache it reads them from disk. For each node search_by_key finds using
+ reiserfs_bread it then uses bin_search to look through that node. bin_search will find the
+ position of the block_number of the next node if it is looking through an internal node. If it
+ is looking through a leaf node bin_search will find the position of the item which has key either
+ equal to given key, or which is the maximal key less than the given key. */
+
+struct path_element {
+ struct buffer_head *pe_buffer; /* Pointer to the buffer at the path in the tree. */
+ int pe_position; /* Position in the tree node which is placed in the */
+ /* buffer above. */
+};
+
+#define MAX_HEIGHT 5 /* maximal height of a tree. don't change this without changing JOURNAL_PER_BALANCE_CNT */
+#define EXTENDED_MAX_HEIGHT 7 /* Must be equals MAX_HEIGHT + FIRST_PATH_ELEMENT_OFFSET */
+#define FIRST_PATH_ELEMENT_OFFSET 2 /* Must be equal to at least 2. */
+
+#define ILLEGAL_PATH_ELEMENT_OFFSET 1 /* Must be equal to FIRST_PATH_ELEMENT_OFFSET - 1 */
+#define MAX_FEB_SIZE 6 /* this MUST be MAX_HEIGHT + 1. See about FEB below */
+
+/* We need to keep track of who the ancestors of nodes are. When we
+ perform a search we record which nodes were visited while
+ descending the tree looking for the node we searched for. This list
+ of nodes is called the path. This information is used while
+ performing balancing. Note that this path information may become
+ invalid, and this means we must check it when using it to see if it
+ is still valid. You'll need to read search_by_key and the comments
+ in it, especially about decrement_counters_in_path(), to understand
+ this structure.
+
+Paths make the code so much harder to work with and debug.... An
+enormous number of bugs are due to them, and trying to write or modify
+code that uses them just makes my head hurt. They are based on an
+excessive effort to avoid disturbing the precious VFS code.:-( The
+gods only know how we are going to SMP the code that uses them.
+znodes are the way! */
+
+#define PATH_READA 0x1 /* do read ahead */
+#define PATH_READA_BACK 0x2 /* read backwards */
+
+struct treepath {
+ int path_length; /* Length of the array above. */
+ int reada;
+ struct path_element path_elements[EXTENDED_MAX_HEIGHT]; /* Array of the path elements. */
+ int pos_in_item;
+};
+
+#define pos_in_item(path) ((path)->pos_in_item)
+
+#define INITIALIZE_PATH(var) \
+struct treepath var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,}
+
+/* Get path element by path and path position. */
+#define PATH_OFFSET_PELEMENT(path, n_offset) ((path)->path_elements + (n_offset))
+
+/* Get buffer header at the path by path and path position. */
+#define PATH_OFFSET_PBUFFER(path, n_offset) (PATH_OFFSET_PELEMENT(path, n_offset)->pe_buffer)
+
+/* Get position in the element at the path by path and path position. */
+#define PATH_OFFSET_POSITION(path, n_offset) (PATH_OFFSET_PELEMENT(path, n_offset)->pe_position)
+
+#define PATH_PLAST_BUFFER(path) (PATH_OFFSET_PBUFFER((path), (path)->path_length))
+ /* you know, to the person who didn't
+ write this the macro name does not
+ at first suggest what it does.
+ Maybe POSITION_FROM_PATH_END? Or
+ maybe we should just focus on
+ dumping paths... -Hans */
+#define PATH_LAST_POSITION(path) (PATH_OFFSET_POSITION((path), (path)->path_length))
+
+#define PATH_PITEM_HEAD(path) B_N_PITEM_HEAD(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION(path))
+
+/* in do_balance leaf has h == 0 in contrast with path structure,
+ where root has level == 0. That is why we need these defines */
+#define PATH_H_PBUFFER(path, h) PATH_OFFSET_PBUFFER (path, path->path_length - (h)) /* tb->S[h] */
+#define PATH_H_PPARENT(path, h) PATH_H_PBUFFER (path, (h) + 1) /* tb->F[h] or tb->S[0]->b_parent */
+#define PATH_H_POSITION(path, h) PATH_OFFSET_POSITION (path, path->path_length - (h))
+#define PATH_H_B_ITEM_ORDER(path, h) PATH_H_POSITION(path, h + 1) /* tb->S[h]->b_item_order */
+
+#define PATH_H_PATH_OFFSET(path, n_h) ((path)->path_length - (n_h))
+
+#define get_last_bh(path) PATH_PLAST_BUFFER(path)
+#define get_ih(path) PATH_PITEM_HEAD(path)
+#define get_item_pos(path) PATH_LAST_POSITION(path)
+#define get_item(path) ((void *)B_N_PITEM(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION (path)))
+#define item_moved(ih,path) comp_items(ih, path)
+#define path_changed(ih,path) comp_items (ih, path)
+
+/***************************************************************************/
+/* MISC */
+/***************************************************************************/
+
+/* Size of pointer to the unformatted node. */
+#define UNFM_P_SIZE (sizeof(unp_t))
+#define UNFM_P_SHIFT 2
+
+// in in-core inode key is stored on le form
+#define INODE_PKEY(inode) ((struct reiserfs_key *)(REISERFS_I(inode)->i_key))
+
+#define MAX_UL_INT 0xffffffff
+#define MAX_INT 0x7ffffff
+#define MAX_US_INT 0xffff
+
+// reiserfs version 2 has max offset 60 bits. Version 1 - 32 bit offset
+#define U32_MAX (~(__u32)0)
+
+static inline loff_t max_reiserfs_offset(struct inode *inode)
+{
+ if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5)
+ return (loff_t) U32_MAX;
+
+ return (loff_t) ((~(__u64) 0) >> 4);
+}
+
+/*#define MAX_KEY_UNIQUENESS MAX_UL_INT*/
+#define MAX_KEY_OBJECTID MAX_UL_INT
+
+#define MAX_B_NUM MAX_UL_INT
+#define MAX_FC_NUM MAX_US_INT
+
+/* the purpose is to detect overflow of an unsigned short */
+#define REISERFS_LINK_MAX (MAX_US_INT - 1000)
+
+/* The following defines are used in reiserfs_insert_item and reiserfs_append_item */
+#define REISERFS_KERNEL_MEM 0 /* reiserfs kernel memory mode */
+#define REISERFS_USER_MEM 1 /* reiserfs user memory mode */
+
+#define fs_generation(s) (REISERFS_SB(s)->s_generation_counter)
+#define get_generation(s) atomic_read (&fs_generation(s))
+#define FILESYSTEM_CHANGED_TB(tb) (get_generation((tb)->tb_sb) != (tb)->fs_gen)
+#define __fs_changed(gen,s) (gen != get_generation (s))
+#define fs_changed(gen,s) \
+({ \
+ reiserfs_cond_resched(s); \
+ __fs_changed(gen, s); \
+})
+
+/***************************************************************************/
+/* FIXATE NODES */
+/***************************************************************************/
+
+#define VI_TYPE_LEFT_MERGEABLE 1
+#define VI_TYPE_RIGHT_MERGEABLE 2
+
+/* To make any changes in the tree we always first find node, that
+ contains item to be changed/deleted or place to insert a new
+ item. We call this node S. To do balancing we need to decide what
+ we will shift to left/right neighbor, or to a new node, where new
+ item will be etc. To make this analysis simpler we build virtual
+ node. Virtual node is an array of items, that will replace items of
+ node S. (For instance if we are going to delete an item, virtual
+ node does not contain it). Virtual node keeps information about
+ item sizes and types, mergeability of first and last items, sizes
+ of all entries in directory item. We use this array of items when
+ calculating what we can shift to neighbors and how many nodes we
+ have to have if we do not any shiftings, if we shift to left/right
+ neighbor or to both. */
+struct virtual_item {
+ int vi_index; // index in the array of item operations
+ unsigned short vi_type; // left/right mergeability
+ unsigned short vi_item_len; /* length of item that it will have after balancing */
+ struct item_head *vi_ih;
+ const char *vi_item; // body of item (old or new)
+ const void *vi_new_data; // 0 always but paste mode
+ void *vi_uarea; // item specific area
+};
+
+struct virtual_node {
+ char *vn_free_ptr; /* this is a pointer to the free space in the buffer */
+ unsigned short vn_nr_item; /* number of items in virtual node */
+ short vn_size; /* size of node , that node would have if it has unlimited size and no balancing is performed */
+ short vn_mode; /* mode of balancing (paste, insert, delete, cut) */
+ short vn_affected_item_num;
+ short vn_pos_in_item;
+ struct item_head *vn_ins_ih; /* item header of inserted item, 0 for other modes */
+ const void *vn_data;
+ struct virtual_item *vn_vi; /* array of items (including a new one, excluding item to be deleted) */
+};
+
+/* used by directory items when creating virtual nodes */
+struct direntry_uarea {
+ int flags;
+ __u16 entry_count;
+ __u16 entry_sizes[1];
+} __attribute__ ((__packed__));
+
+/***************************************************************************/
+/* TREE BALANCE */
+/***************************************************************************/
+
+/* This temporary structure is used in tree balance algorithms, and
+ constructed as we go to the extent that its various parts are
+ needed. It contains arrays of nodes that can potentially be
+ involved in the balancing of node S, and parameters that define how
+ each of the nodes must be balanced. Note that in these algorithms
+ for balancing the worst case is to need to balance the current node
+ S and the left and right neighbors and all of their parents plus
+ create a new node. We implement S1 balancing for the leaf nodes
+ and S0 balancing for the internal nodes (S1 and S0 are defined in
+ our papers.)*/
+
+#define MAX_FREE_BLOCK 7 /* size of the array of buffers to free at end of do_balance */
+
+/* maximum number of FEB blocknrs on a single level */
+#define MAX_AMOUNT_NEEDED 2
+
+/* someday somebody will prefix every field in this struct with tb_ */
+struct tree_balance {
+ int tb_mode;
+ int need_balance_dirty;
+ struct super_block *tb_sb;
+ struct reiserfs_transaction_handle *transaction_handle;
+ struct treepath *tb_path;
+ struct buffer_head *L[MAX_HEIGHT]; /* array of left neighbors of nodes in the path */
+ struct buffer_head *R[MAX_HEIGHT]; /* array of right neighbors of nodes in the path */
+ struct buffer_head *FL[MAX_HEIGHT]; /* array of fathers of the left neighbors */
+ struct buffer_head *FR[MAX_HEIGHT]; /* array of fathers of the right neighbors */
+ struct buffer_head *CFL[MAX_HEIGHT]; /* array of common parents of center node and its left neighbor */
+ struct buffer_head *CFR[MAX_HEIGHT]; /* array of common parents of center node and its right neighbor */
+
+ struct buffer_head *FEB[MAX_FEB_SIZE]; /* array of empty buffers. Number of buffers in array equals
+ cur_blknum. */
+ struct buffer_head *used[MAX_FEB_SIZE];
+ struct buffer_head *thrown[MAX_FEB_SIZE];
+ int lnum[MAX_HEIGHT]; /* array of number of items which must be
+ shifted to the left in order to balance the
+ current node; for leaves includes item that
+ will be partially shifted; for internal
+ nodes, it is the number of child pointers
+ rather than items. It includes the new item
+ being created. The code sometimes subtracts
+ one to get the number of wholly shifted
+ items for other purposes. */
+ int rnum[MAX_HEIGHT]; /* substitute right for left in comment above */
+ int lkey[MAX_HEIGHT]; /* array indexed by height h mapping the key delimiting L[h] and
+ S[h] to its item number within the node CFL[h] */
+ int rkey[MAX_HEIGHT]; /* substitute r for l in comment above */
+ int insert_size[MAX_HEIGHT]; /* the number of bytes by we are trying to add or remove from
+ S[h]. A negative value means removing. */
+ int blknum[MAX_HEIGHT]; /* number of nodes that will replace node S[h] after
+ balancing on the level h of the tree. If 0 then S is
+ being deleted, if 1 then S is remaining and no new nodes
+ are being created, if 2 or 3 then 1 or 2 new nodes is
+ being created */
+
+ /* fields that are used only for balancing leaves of the tree */
+ int cur_blknum; /* number of empty blocks having been already allocated */
+ int s0num; /* number of items that fall into left most node when S[0] splits */
+ int s1num; /* number of items that fall into first new node when S[0] splits */
+ int s2num; /* number of items that fall into second new node when S[0] splits */
+ int lbytes; /* number of bytes which can flow to the left neighbor from the left */
+ /* most liquid item that cannot be shifted from S[0] entirely */
+ /* if -1 then nothing will be partially shifted */
+ int rbytes; /* number of bytes which will flow to the right neighbor from the right */
+ /* most liquid item that cannot be shifted from S[0] entirely */
+ /* if -1 then nothing will be partially shifted */
+ int s1bytes; /* number of bytes which flow to the first new node when S[0] splits */
+ /* note: if S[0] splits into 3 nodes, then items do not need to be cut */
+ int s2bytes;
+ struct buffer_head *buf_to_free[MAX_FREE_BLOCK]; /* buffers which are to be freed after do_balance finishes by unfix_nodes */
+ char *vn_buf; /* kmalloced memory. Used to create
+ virtual node and keep map of
+ dirtied bitmap blocks */
+ int vn_buf_size; /* size of the vn_buf */
+ struct virtual_node *tb_vn; /* VN starts after bitmap of bitmap blocks */
+
+ int fs_gen; /* saved value of `reiserfs_generation' counter
+ see FILESYSTEM_CHANGED() macro in reiserfs_fs.h */
+#ifdef DISPLACE_NEW_PACKING_LOCALITIES
+ struct in_core_key key; /* key pointer, to pass to block allocator or
+ another low-level subsystem */
+#endif
+};
+
+/* These are modes of balancing */
+
+/* When inserting an item. */
+#define M_INSERT 'i'
+/* When inserting into (directories only) or appending onto an already
+ existent item. */
+#define M_PASTE 'p'
+/* When deleting an item. */
+#define M_DELETE 'd'
+/* When truncating an item or removing an entry from a (directory) item. */
+#define M_CUT 'c'
+
+/* used when balancing on leaf level skipped (in reiserfsck) */
+#define M_INTERNAL 'n'
+
+/* When further balancing is not needed, then do_balance does not need
+ to be called. */
+#define M_SKIP_BALANCING 's'
+#define M_CONVERT 'v'
+
+/* modes of leaf_move_items */
+#define LEAF_FROM_S_TO_L 0
+#define LEAF_FROM_S_TO_R 1
+#define LEAF_FROM_R_TO_L 2
+#define LEAF_FROM_L_TO_R 3
+#define LEAF_FROM_S_TO_SNEW 4
+
+#define FIRST_TO_LAST 0
+#define LAST_TO_FIRST 1
+
+/* used in do_balance for passing parent of node information that has
+ been gotten from tb struct */
+struct buffer_info {
+ struct tree_balance *tb;
+ struct buffer_head *bi_bh;
+ struct buffer_head *bi_parent;
+ int bi_position;
+};
+
+static inline struct super_block *sb_from_tb(struct tree_balance *tb)
+{
+ return tb ? tb->tb_sb : NULL;
+}
+
+static inline struct super_block *sb_from_bi(struct buffer_info *bi)
+{
+ return bi ? sb_from_tb(bi->tb) : NULL;
+}
+
+/* there are 4 types of items: stat data, directory item, indirect, direct.
++-------------------+------------+--------------+------------+
+| | k_offset | k_uniqueness | mergeable? |
++-------------------+------------+--------------+------------+
+| stat data | 0 | 0 | no |
++-------------------+------------+--------------+------------+
+| 1st directory item| DOT_OFFSET |DIRENTRY_UNIQUENESS| no |
+| non 1st directory | hash value | | yes |
+| item | | | |
++-------------------+------------+--------------+------------+
+| indirect item | offset + 1 |TYPE_INDIRECT | if this is not the first indirect item of the object
++-------------------+------------+--------------+------------+
+| direct item | offset + 1 |TYPE_DIRECT | if not this is not the first direct item of the object
++-------------------+------------+--------------+------------+
+*/
+
+struct item_operations {
+ int (*bytes_number) (struct item_head * ih, int block_size);
+ void (*decrement_key) (struct cpu_key *);
+ int (*is_left_mergeable) (struct reiserfs_key * ih,
+ unsigned long bsize);
+ void (*print_item) (struct item_head *, char *item);
+ void (*check_item) (struct item_head *, char *item);
+
+ int (*create_vi) (struct virtual_node * vn, struct virtual_item * vi,
+ int is_affected, int insert_size);
+ int (*check_left) (struct virtual_item * vi, int free,
+ int start_skip, int end_skip);
+ int (*check_right) (struct virtual_item * vi, int free);
+ int (*part_size) (struct virtual_item * vi, int from, int to);
+ int (*unit_num) (struct virtual_item * vi);
+ void (*print_vi) (struct virtual_item * vi);
+};
+
+extern struct item_operations *item_ops[TYPE_ANY + 1];
+
+#define op_bytes_number(ih,bsize) item_ops[le_ih_k_type (ih)]->bytes_number (ih, bsize)
+#define op_is_left_mergeable(key,bsize) item_ops[le_key_k_type (le_key_version (key), key)]->is_left_mergeable (key, bsize)
+#define op_print_item(ih,item) item_ops[le_ih_k_type (ih)]->print_item (ih, item)
+#define op_check_item(ih,item) item_ops[le_ih_k_type (ih)]->check_item (ih, item)
+#define op_create_vi(vn,vi,is_affected,insert_size) item_ops[le_ih_k_type ((vi)->vi_ih)]->create_vi (vn,vi,is_affected,insert_size)
+#define op_check_left(vi,free,start_skip,end_skip) item_ops[(vi)->vi_index]->check_left (vi, free, start_skip, end_skip)
+#define op_check_right(vi,free) item_ops[(vi)->vi_index]->check_right (vi, free)
+#define op_part_size(vi,from,to) item_ops[(vi)->vi_index]->part_size (vi, from, to)
+#define op_unit_num(vi) item_ops[(vi)->vi_index]->unit_num (vi)
+#define op_print_vi(vi) item_ops[(vi)->vi_index]->print_vi (vi)
+
+#define COMP_SHORT_KEYS comp_short_keys
+
+/* number of blocks pointed to by the indirect item */
+#define I_UNFM_NUM(ih) (ih_item_len(ih) / UNFM_P_SIZE)
+
+/* the used space within the unformatted node corresponding to pos within the item pointed to by ih */
+#define I_POS_UNFM_SIZE(ih,pos,size) (((pos) == I_UNFM_NUM(ih) - 1 ) ? (size) - ih_free_space(ih) : (size))
+
+/* number of bytes contained by the direct item or the unformatted nodes the indirect item points to */
+
+/* get the item header */
+#define B_N_PITEM_HEAD(bh,item_num) ( (struct item_head * )((bh)->b_data + BLKH_SIZE) + (item_num) )
+
+/* get key */
+#define B_N_PDELIM_KEY(bh,item_num) ( (struct reiserfs_key * )((bh)->b_data + BLKH_SIZE) + (item_num) )
+
+/* get the key */
+#define B_N_PKEY(bh,item_num) ( &(B_N_PITEM_HEAD(bh,item_num)->ih_key) )
+
+/* get item body */
+#define B_N_PITEM(bh,item_num) ( (bh)->b_data + ih_location(B_N_PITEM_HEAD((bh),(item_num))))
+
+/* get the stat data by the buffer header and the item order */
+#define B_N_STAT_DATA(bh,nr) \
+( (struct stat_data *)((bh)->b_data + ih_location(B_N_PITEM_HEAD((bh),(nr))) ) )
+
+ /* following defines use reiserfs buffer header and item header */
+
+/* get stat-data */
+#define B_I_STAT_DATA(bh, ih) ( (struct stat_data * )((bh)->b_data + ih_location(ih)) )
+
+// this is 3976 for size==4096
+#define MAX_DIRECT_ITEM_LEN(size) ((size) - BLKH_SIZE - 2*IH_SIZE - SD_SIZE - UNFM_P_SIZE)
+
+/* indirect items consist of entries which contain blocknrs, pos
+ indicates which entry, and B_I_POS_UNFM_POINTER resolves to the
+ blocknr contained by the entry pos points to */
+#define B_I_POS_UNFM_POINTER(bh,ih,pos) le32_to_cpu(*(((unp_t *)B_I_PITEM(bh,ih)) + (pos)))
+#define PUT_B_I_POS_UNFM_POINTER(bh,ih,pos, val) do {*(((unp_t *)B_I_PITEM(bh,ih)) + (pos)) = cpu_to_le32(val); } while (0)
+
+struct reiserfs_iget_args {
+ __u32 objectid;
+ __u32 dirid;
+};
+
+/***************************************************************************/
+/* FUNCTION DECLARATIONS */
+/***************************************************************************/
+
+#define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12)
+
+#define journal_trans_half(blocksize) \
+ ((blocksize - sizeof (struct reiserfs_journal_desc) + sizeof (__u32) - 12) / sizeof (__u32))
+
+/* journal.c see journal.c for all the comments here */
+
+/* first block written in a commit. */
+struct reiserfs_journal_desc {
+ __le32 j_trans_id; /* id of commit */
+ __le32 j_len; /* length of commit. len +1 is the commit block */
+ __le32 j_mount_id; /* mount id of this trans */
+ __le32 j_realblock[1]; /* real locations for each block */
+};
+
+#define get_desc_trans_id(d) le32_to_cpu((d)->j_trans_id)
+#define get_desc_trans_len(d) le32_to_cpu((d)->j_len)
+#define get_desc_mount_id(d) le32_to_cpu((d)->j_mount_id)
+
+#define set_desc_trans_id(d,val) do { (d)->j_trans_id = cpu_to_le32 (val); } while (0)
+#define set_desc_trans_len(d,val) do { (d)->j_len = cpu_to_le32 (val); } while (0)
+#define set_desc_mount_id(d,val) do { (d)->j_mount_id = cpu_to_le32 (val); } while (0)
+
+/* last block written in a commit */
+struct reiserfs_journal_commit {
+ __le32 j_trans_id; /* must match j_trans_id from the desc block */
+ __le32 j_len; /* ditto */
+ __le32 j_realblock[1]; /* real locations for each block */
+};
+
+#define get_commit_trans_id(c) le32_to_cpu((c)->j_trans_id)
+#define get_commit_trans_len(c) le32_to_cpu((c)->j_len)
+#define get_commit_mount_id(c) le32_to_cpu((c)->j_mount_id)
+
+#define set_commit_trans_id(c,val) do { (c)->j_trans_id = cpu_to_le32 (val); } while (0)
+#define set_commit_trans_len(c,val) do { (c)->j_len = cpu_to_le32 (val); } while (0)
+
+/* this header block gets written whenever a transaction is considered fully flushed, and is more recent than the
+** last fully flushed transaction. fully flushed means all the log blocks and all the real blocks are on disk,
+** and this transaction does not need to be replayed.
+*/
+struct reiserfs_journal_header {
+ __le32 j_last_flush_trans_id; /* id of last fully flushed transaction */
+ __le32 j_first_unflushed_offset; /* offset in the log of where to start replay after a crash */
+ __le32 j_mount_id;
+ /* 12 */ struct journal_params jh_journal;
+};
+
+/* biggest tunable defines are right here */
+#define JOURNAL_BLOCK_COUNT 8192 /* number of blocks in the journal */
+#define JOURNAL_TRANS_MAX_DEFAULT 1024 /* biggest possible single transaction, don't change for now (8/3/99) */
+#define JOURNAL_TRANS_MIN_DEFAULT 256
+#define JOURNAL_MAX_BATCH_DEFAULT 900 /* max blocks to batch into one transaction, don't make this any bigger than 900 */
+#define JOURNAL_MIN_RATIO 2
+#define JOURNAL_MAX_COMMIT_AGE 30
+#define JOURNAL_MAX_TRANS_AGE 30
+#define JOURNAL_PER_BALANCE_CNT (3 * (MAX_HEIGHT-2) + 9)
+#define JOURNAL_BLOCKS_PER_OBJECT(sb) (JOURNAL_PER_BALANCE_CNT * 3 + \
+ 2 * (REISERFS_QUOTA_INIT_BLOCKS(sb) + \
+ REISERFS_QUOTA_TRANS_BLOCKS(sb)))
+
+#ifdef CONFIG_QUOTA
+#define REISERFS_QUOTA_OPTS ((1 << REISERFS_USRQUOTA) | (1 << REISERFS_GRPQUOTA))
+/* We need to update data and inode (atime) */
+#define REISERFS_QUOTA_TRANS_BLOCKS(s) (REISERFS_SB(s)->s_mount_opt & REISERFS_QUOTA_OPTS ? 2 : 0)
+/* 1 balancing, 1 bitmap, 1 data per write + stat data update */
+#define REISERFS_QUOTA_INIT_BLOCKS(s) (REISERFS_SB(s)->s_mount_opt & REISERFS_QUOTA_OPTS ? \
+(DQUOT_INIT_ALLOC*(JOURNAL_PER_BALANCE_CNT+2)+DQUOT_INIT_REWRITE+1) : 0)
+/* same as with INIT */
+#define REISERFS_QUOTA_DEL_BLOCKS(s) (REISERFS_SB(s)->s_mount_opt & REISERFS_QUOTA_OPTS ? \
+(DQUOT_DEL_ALLOC*(JOURNAL_PER_BALANCE_CNT+2)+DQUOT_DEL_REWRITE+1) : 0)
+#else
+#define REISERFS_QUOTA_TRANS_BLOCKS(s) 0
+#define REISERFS_QUOTA_INIT_BLOCKS(s) 0
+#define REISERFS_QUOTA_DEL_BLOCKS(s) 0
+#endif
+
+/* both of these can be as low as 1, or as high as you want. The min is the
+** number of 4k bitmap nodes preallocated on mount. New nodes are allocated
+** as needed, and released when transactions are committed. On release, if
+** the current number of nodes is > max, the node is freed, otherwise,
+** it is put on a free list for faster use later.
+*/
+#define REISERFS_MIN_BITMAP_NODES 10
+#define REISERFS_MAX_BITMAP_NODES 100
+
+#define JBH_HASH_SHIFT 13 /* these are based on journal hash size of 8192 */
+#define JBH_HASH_MASK 8191
+
+#define _jhashfn(sb,block) \
+ (((unsigned long)sb>>L1_CACHE_SHIFT) ^ \
+ (((block)<<(JBH_HASH_SHIFT - 6)) ^ ((block) >> 13) ^ ((block) << (JBH_HASH_SHIFT - 12))))
+#define journal_hash(t,sb,block) ((t)[_jhashfn((sb),(block)) & JBH_HASH_MASK])
+
+// We need these to make journal.c code more readable
+#define journal_find_get_block(s, block) __find_get_block(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize)
+#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize)
+#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize)
+
+enum reiserfs_bh_state_bits {
+ BH_JDirty = BH_PrivateStart, /* buffer is in current transaction */
+ BH_JDirty_wait,
+ BH_JNew, /* disk block was taken off free list before
+ * being in a finished transaction, or
+ * written to disk. Can be reused immed. */
+ BH_JPrepared,
+ BH_JRestore_dirty,
+ BH_JTest, // debugging only will go away
+};
+
+BUFFER_FNS(JDirty, journaled);
+TAS_BUFFER_FNS(JDirty, journaled);
+BUFFER_FNS(JDirty_wait, journal_dirty);
+TAS_BUFFER_FNS(JDirty_wait, journal_dirty);
+BUFFER_FNS(JNew, journal_new);
+TAS_BUFFER_FNS(JNew, journal_new);
+BUFFER_FNS(JPrepared, journal_prepared);
+TAS_BUFFER_FNS(JPrepared, journal_prepared);
+BUFFER_FNS(JRestore_dirty, journal_restore_dirty);
+TAS_BUFFER_FNS(JRestore_dirty, journal_restore_dirty);
+BUFFER_FNS(JTest, journal_test);
+TAS_BUFFER_FNS(JTest, journal_test);
+
+/*
+** transaction handle which is passed around for all journal calls
+*/
+struct reiserfs_transaction_handle {
+ struct super_block *t_super; /* super for this FS when journal_begin was
+ called. saves calls to reiserfs_get_super
+ also used by nested transactions to make
+ sure they are nesting on the right FS
+ _must_ be first in the handle
+ */
+ int t_refcount;
+ int t_blocks_logged; /* number of blocks this writer has logged */
+ int t_blocks_allocated; /* number of blocks this writer allocated */
+ unsigned int t_trans_id; /* sanity check, equals the current trans id */
+ void *t_handle_save; /* save existing current->journal_info */
+ unsigned displace_new_blocks:1; /* if new block allocation occurres, that block
+ should be displaced from others */
+ struct list_head t_list;
+};
+
+/* used to keep track of ordered and tail writes, attached to the buffer
+ * head through b_journal_head.
+ */
+struct reiserfs_jh {
+ struct reiserfs_journal_list *jl;
+ struct buffer_head *bh;
+ struct list_head list;
+};
+
+void reiserfs_free_jh(struct buffer_head *bh);
+int reiserfs_add_tail_list(struct inode *inode, struct buffer_head *bh);
+int reiserfs_add_ordered_list(struct inode *inode, struct buffer_head *bh);
+int journal_mark_dirty(struct reiserfs_transaction_handle *,
+ struct super_block *, struct buffer_head *bh);
+
+static inline int reiserfs_file_data_log(struct inode *inode)
+{
+ if (reiserfs_data_log(inode->i_sb) ||
+ (REISERFS_I(inode)->i_flags & i_data_log))
+ return 1;
+ return 0;
+}
+
+static inline int reiserfs_transaction_running(struct super_block *s)
+{
+ struct reiserfs_transaction_handle *th = current->journal_info;
+ if (th && th->t_super == s)
+ return 1;
+ if (th && th->t_super == NULL)
+ BUG();
+ return 0;
+}
+
+static inline int reiserfs_transaction_free_space(struct reiserfs_transaction_handle *th)
+{
+ return th->t_blocks_allocated - th->t_blocks_logged;
+}
+
+struct reiserfs_transaction_handle *reiserfs_persistent_transaction(struct
+ super_block
+ *,
+ int count);
+int reiserfs_end_persistent_transaction(struct reiserfs_transaction_handle *);
+int reiserfs_commit_page(struct inode *inode, struct page *page,
+ unsigned from, unsigned to);
+int reiserfs_flush_old_commits(struct super_block *);
+int reiserfs_commit_for_inode(struct inode *);
+int reiserfs_inode_needs_commit(struct inode *);
+void reiserfs_update_inode_transaction(struct inode *);
+void reiserfs_wait_on_write_block(struct super_block *s);
+void reiserfs_block_writes(struct reiserfs_transaction_handle *th);
+void reiserfs_allow_writes(struct super_block *s);
+void reiserfs_check_lock_depth(struct super_block *s, char *caller);
+int reiserfs_prepare_for_journal(struct super_block *, struct buffer_head *bh,
+ int wait);
+void reiserfs_restore_prepared_buffer(struct super_block *,
+ struct buffer_head *bh);
+int journal_init(struct super_block *, const char *j_dev_name, int old_format,
+ unsigned int);
+int journal_release(struct reiserfs_transaction_handle *, struct super_block *);
+int journal_release_error(struct reiserfs_transaction_handle *,
+ struct super_block *);
+int journal_end(struct reiserfs_transaction_handle *, struct super_block *,
+ unsigned long);
+int journal_end_sync(struct reiserfs_transaction_handle *, struct super_block *,
+ unsigned long);
+int journal_mark_freed(struct reiserfs_transaction_handle *,
+ struct super_block *, b_blocknr_t blocknr);
+int journal_transaction_should_end(struct reiserfs_transaction_handle *, int);
+int reiserfs_in_journal(struct super_block *sb, unsigned int bmap_nr,
+ int bit_nr, int searchall, b_blocknr_t *next);
+int journal_begin(struct reiserfs_transaction_handle *,
+ struct super_block *sb, unsigned long);
+int journal_join_abort(struct reiserfs_transaction_handle *,
+ struct super_block *sb, unsigned long);
+void reiserfs_abort_journal(struct super_block *sb, int errno);
+void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...);
+int reiserfs_allocate_list_bitmaps(struct super_block *s,
+ struct reiserfs_list_bitmap *, unsigned int);
+
+void add_save_link(struct reiserfs_transaction_handle *th,
+ struct inode *inode, int truncate);
+int remove_save_link(struct inode *inode, int truncate);
+
+/* objectid.c */
+__u32 reiserfs_get_unused_objectid(struct reiserfs_transaction_handle *th);
+void reiserfs_release_objectid(struct reiserfs_transaction_handle *th,
+ __u32 objectid_to_release);
+int reiserfs_convert_objectid_map_v1(struct super_block *);
+
+/* stree.c */
+int B_IS_IN_TREE(const struct buffer_head *);
+extern void copy_item_head(struct item_head *to,
+ const struct item_head *from);
+
+// first key is in cpu form, second - le
+extern int comp_short_keys(const struct reiserfs_key *le_key,
+ const struct cpu_key *cpu_key);
+extern void le_key2cpu_key(struct cpu_key *to, const struct reiserfs_key *from);
+
+// both are in le form
+extern int comp_le_keys(const struct reiserfs_key *,
+ const struct reiserfs_key *);
+extern int comp_short_le_keys(const struct reiserfs_key *,
+ const struct reiserfs_key *);
+
+//
+// get key version from on disk key - kludge
+//
+static inline int le_key_version(const struct reiserfs_key *key)
+{
+ int type;
+
+ type = offset_v2_k_type(&(key->u.k_offset_v2));
+ if (type != TYPE_DIRECT && type != TYPE_INDIRECT
+ && type != TYPE_DIRENTRY)
+ return KEY_FORMAT_3_5;
+
+ return KEY_FORMAT_3_6;
+
+}
+
+static inline void copy_key(struct reiserfs_key *to,
+ const struct reiserfs_key *from)
+{
+ memcpy(to, from, KEY_SIZE);
+}
+
+int comp_items(const struct item_head *stored_ih, const struct treepath *path);
+const struct reiserfs_key *get_rkey(const struct treepath *chk_path,
+ const struct super_block *sb);
+int search_by_key(struct super_block *, const struct cpu_key *,
+ struct treepath *, int);
+#define search_item(s,key,path) search_by_key (s, key, path, DISK_LEAF_NODE_LEVEL)
+int search_for_position_by_key(struct super_block *sb,
+ const struct cpu_key *cpu_key,
+ struct treepath *search_path);
+extern void decrement_bcount(struct buffer_head *bh);
+void decrement_counters_in_path(struct treepath *search_path);
+void pathrelse(struct treepath *search_path);
+int reiserfs_check_path(struct treepath *p);
+void pathrelse_and_restore(struct super_block *s, struct treepath *search_path);
+
+int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
+ struct treepath *path,
+ const struct cpu_key *key,
+ struct item_head *ih,
+ struct inode *inode, const char *body);
+
+int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th,
+ struct treepath *path,
+ const struct cpu_key *key,
+ struct inode *inode,
+ const char *body, int paste_size);
+
+int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
+ struct treepath *path,
+ struct cpu_key *key,
+ struct inode *inode,
+ struct page *page, loff_t new_file_size);
+
+int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
+ struct treepath *path,
+ const struct cpu_key *key,
+ struct inode *inode, struct buffer_head *un_bh);
+
+void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th,
+ struct inode *inode, struct reiserfs_key *key);
+int reiserfs_delete_object(struct reiserfs_transaction_handle *th,
+ struct inode *inode);
+int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
+ struct inode *inode, struct page *,
+ int update_timestamps);
+
+#define i_block_size(inode) ((inode)->i_sb->s_blocksize)
+#define file_size(inode) ((inode)->i_size)
+#define tail_size(inode) (file_size (inode) & (i_block_size (inode) - 1))
+
+#define tail_has_to_be_packed(inode) (have_large_tails ((inode)->i_sb)?\
+!STORE_TAIL_IN_UNFM_S1(file_size (inode), tail_size(inode), inode->i_sb->s_blocksize):have_small_tails ((inode)->i_sb)?!STORE_TAIL_IN_UNFM_S2(file_size (inode), tail_size(inode), inode->i_sb->s_blocksize):0 )
+
+void padd_item(char *item, int total_length, int length);
+
+/* inode.c */
+/* args for the create parameter of reiserfs_get_block */
+#define GET_BLOCK_NO_CREATE 0 /* don't create new blocks or convert tails */
+#define GET_BLOCK_CREATE 1 /* add anything you need to find block */
+#define GET_BLOCK_NO_HOLE 2 /* return -ENOENT for file holes */
+#define GET_BLOCK_READ_DIRECT 4 /* read the tail if indirect item not found */
+#define GET_BLOCK_NO_IMUX 8 /* i_mutex is not held, don't preallocate */
+#define GET_BLOCK_NO_DANGLE 16 /* don't leave any transactions running */
+
+void reiserfs_read_locked_inode(struct inode *inode,
+ struct reiserfs_iget_args *args);
+int reiserfs_find_actor(struct inode *inode, void *p);
+int reiserfs_init_locked_inode(struct inode *inode, void *p);
+void reiserfs_evict_inode(struct inode *inode);
+int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc);
+int reiserfs_get_block(struct inode *inode, sector_t block,
+ struct buffer_head *bh_result, int create);
+struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type);
+struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type);
+int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp,
+ int connectable);
+
+int reiserfs_truncate_file(struct inode *, int update_timestamps);
+void make_cpu_key(struct cpu_key *cpu_key, struct inode *inode, loff_t offset,
+ int type, int key_length);
+void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
+ int version,
+ loff_t offset, int type, int length, int entry_count);
+struct inode *reiserfs_iget(struct super_block *s, const struct cpu_key *key);
+
+struct reiserfs_security_handle;
+int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
+ struct inode *dir, umode_t mode,
+ const char *symname, loff_t i_size,
+ struct dentry *dentry, struct inode *inode,
+ struct reiserfs_security_handle *security);
+
+void reiserfs_update_sd_size(struct reiserfs_transaction_handle *th,
+ struct inode *inode, loff_t size);
+
+static inline void reiserfs_update_sd(struct reiserfs_transaction_handle *th,
+ struct inode *inode)
+{
+ reiserfs_update_sd_size(th, inode, inode->i_size);
+}
+
+void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode);
+void i_attrs_to_sd_attrs(struct inode *inode, __u16 * sd_attrs);
+int reiserfs_setattr(struct dentry *dentry, struct iattr *attr);
+
+int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len);
+
+/* namei.c */
+void set_de_name_and_namelen(struct reiserfs_dir_entry *de);
+int search_by_entry_key(struct super_block *sb, const struct cpu_key *key,
+ struct treepath *path, struct reiserfs_dir_entry *de);
+struct dentry *reiserfs_get_parent(struct dentry *);
+
+#ifdef CONFIG_REISERFS_PROC_INFO
+int reiserfs_proc_info_init(struct super_block *sb);
+int reiserfs_proc_info_done(struct super_block *sb);
+int reiserfs_proc_info_global_init(void);
+int reiserfs_proc_info_global_done(void);
+
+#define PROC_EXP( e ) e
+
+#define __PINFO( sb ) REISERFS_SB(sb) -> s_proc_info_data
+#define PROC_INFO_MAX( sb, field, value ) \
+ __PINFO( sb ).field = \
+ max( REISERFS_SB( sb ) -> s_proc_info_data.field, value )
+#define PROC_INFO_INC( sb, field ) ( ++ ( __PINFO( sb ).field ) )
+#define PROC_INFO_ADD( sb, field, val ) ( __PINFO( sb ).field += ( val ) )
+#define PROC_INFO_BH_STAT( sb, bh, level ) \
+ PROC_INFO_INC( sb, sbk_read_at[ ( level ) ] ); \
+ PROC_INFO_ADD( sb, free_at[ ( level ) ], B_FREE_SPACE( bh ) ); \
+ PROC_INFO_ADD( sb, items_at[ ( level ) ], B_NR_ITEMS( bh ) )
+#else
+static inline int reiserfs_proc_info_init(struct super_block *sb)
+{
+ return 0;
+}
+
+static inline int reiserfs_proc_info_done(struct super_block *sb)
+{
+ return 0;
+}
+
+static inline int reiserfs_proc_info_global_init(void)
+{
+ return 0;
+}
+
+static inline int reiserfs_proc_info_global_done(void)
+{
+ return 0;
+}
+
+#define PROC_EXP( e )
+#define VOID_V ( ( void ) 0 )
+#define PROC_INFO_MAX( sb, field, value ) VOID_V
+#define PROC_INFO_INC( sb, field ) VOID_V
+#define PROC_INFO_ADD( sb, field, val ) VOID_V
+#define PROC_INFO_BH_STAT(sb, bh, n_node_level) VOID_V
+#endif
+
+/* dir.c */
+extern const struct inode_operations reiserfs_dir_inode_operations;
+extern const struct inode_operations reiserfs_symlink_inode_operations;
+extern const struct inode_operations reiserfs_special_inode_operations;
+extern const struct file_operations reiserfs_dir_operations;
+int reiserfs_readdir_dentry(struct dentry *, void *, filldir_t, loff_t *);
+
+/* tail_conversion.c */
+int direct2indirect(struct reiserfs_transaction_handle *, struct inode *,
+ struct treepath *, struct buffer_head *, loff_t);
+int indirect2direct(struct reiserfs_transaction_handle *, struct inode *,
+ struct page *, struct treepath *, const struct cpu_key *,
+ loff_t, char *);
+void reiserfs_unmap_buffer(struct buffer_head *);
+
+/* file.c */
+extern const struct inode_operations reiserfs_file_inode_operations;
+extern const struct file_operations reiserfs_file_operations;
+extern const struct address_space_operations reiserfs_address_space_operations;
+
+/* fix_nodes.c */
+
+int fix_nodes(int n_op_mode, struct tree_balance *tb,
+ struct item_head *ins_ih, const void *);
+void unfix_nodes(struct tree_balance *);
+
+/* prints.c */
+void __reiserfs_panic(struct super_block *s, const char *id,
+ const char *function, const char *fmt, ...)
+ __attribute__ ((noreturn));
+#define reiserfs_panic(s, id, fmt, args...) \
+ __reiserfs_panic(s, id, __func__, fmt, ##args)
+void __reiserfs_error(struct super_block *s, const char *id,
+ const char *function, const char *fmt, ...);
+#define reiserfs_error(s, id, fmt, args...) \
+ __reiserfs_error(s, id, __func__, fmt, ##args)
+void reiserfs_info(struct super_block *s, const char *fmt, ...);
+void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...);
+void print_indirect_item(struct buffer_head *bh, int item_num);
+void store_print_tb(struct tree_balance *tb);
+void print_cur_tb(char *mes);
+void print_de(struct reiserfs_dir_entry *de);
+void print_bi(struct buffer_info *bi, char *mes);
+#define PRINT_LEAF_ITEMS 1 /* print all items */
+#define PRINT_DIRECTORY_ITEMS 2 /* print directory items */
+#define PRINT_DIRECT_ITEMS 4 /* print contents of direct items */
+void print_block(struct buffer_head *bh, ...);
+void print_bmap(struct super_block *s, int silent);
+void print_bmap_block(int i, char *data, int size, int silent);
+/*void print_super_block (struct super_block * s, char * mes);*/
+void print_objectid_map(struct super_block *s);
+void print_block_head(struct buffer_head *bh, char *mes);
+void check_leaf(struct buffer_head *bh);
+void check_internal(struct buffer_head *bh);
+void print_statistics(struct super_block *s);
+char *reiserfs_hashname(int code);
+
+/* lbalance.c */
+int leaf_move_items(int shift_mode, struct tree_balance *tb, int mov_num,
+ int mov_bytes, struct buffer_head *Snew);
+int leaf_shift_left(struct tree_balance *tb, int shift_num, int shift_bytes);
+int leaf_shift_right(struct tree_balance *tb, int shift_num, int shift_bytes);
+void leaf_delete_items(struct buffer_info *cur_bi, int last_first, int first,
+ int del_num, int del_bytes);
+void leaf_insert_into_buf(struct buffer_info *bi, int before,
+ struct item_head *inserted_item_ih,
+ const char *inserted_item_body, int zeros_number);
+void leaf_paste_in_buffer(struct buffer_info *bi, int pasted_item_num,
+ int pos_in_item, int paste_size, const char *body,
+ int zeros_number);
+void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num,
+ int pos_in_item, int cut_size);
+void leaf_paste_entries(struct buffer_info *bi, int item_num, int before,
+ int new_entry_count, struct reiserfs_de_head *new_dehs,
+ const char *records, int paste_size);
+/* ibalance.c */
+int balance_internal(struct tree_balance *, int, int, struct item_head *,
+ struct buffer_head **);
+
+/* do_balance.c */
+void do_balance_mark_leaf_dirty(struct tree_balance *tb,
+ struct buffer_head *bh, int flag);
+#define do_balance_mark_internal_dirty do_balance_mark_leaf_dirty
+#define do_balance_mark_sb_dirty do_balance_mark_leaf_dirty
+
+void do_balance(struct tree_balance *tb, struct item_head *ih,
+ const char *body, int flag);
+void reiserfs_invalidate_buffer(struct tree_balance *tb,
+ struct buffer_head *bh);
+
+int get_left_neighbor_position(struct tree_balance *tb, int h);
+int get_right_neighbor_position(struct tree_balance *tb, int h);
+void replace_key(struct tree_balance *tb, struct buffer_head *, int,
+ struct buffer_head *, int);
+void make_empty_node(struct buffer_info *);
+struct buffer_head *get_FEB(struct tree_balance *);
+
+/* bitmap.c */
+
+/* structure contains hints for block allocator, and it is a container for
+ * arguments, such as node, search path, transaction_handle, etc. */
+struct __reiserfs_blocknr_hint {
+ struct inode *inode; /* inode passed to allocator, if we allocate unf. nodes */
+ sector_t block; /* file offset, in blocks */
+ struct in_core_key key;
+ struct treepath *path; /* search path, used by allocator to deternine search_start by
+ * various ways */
+ struct reiserfs_transaction_handle *th; /* transaction handle is needed to log super blocks and
+ * bitmap blocks changes */
+ b_blocknr_t beg, end;
+ b_blocknr_t search_start; /* a field used to transfer search start value (block number)
+ * between different block allocator procedures
+ * (determine_search_start() and others) */
+ int prealloc_size; /* is set in determine_prealloc_size() function, used by underlayed
+ * function that do actual allocation */
+
+ unsigned formatted_node:1; /* the allocator uses different polices for getting disk space for
+ * formatted/unformatted blocks with/without preallocation */
+ unsigned preallocate:1;
+};
+
+typedef struct __reiserfs_blocknr_hint reiserfs_blocknr_hint_t;
+
+int reiserfs_parse_alloc_options(struct super_block *, char *);
+void reiserfs_init_alloc_options(struct super_block *s);
+
+/*
+ * given a directory, this will tell you what packing locality
+ * to use for a new object underneat it. The locality is returned
+ * in disk byte order (le).
+ */
+__le32 reiserfs_choose_packing(struct inode *dir);
+
+int reiserfs_init_bitmap_cache(struct super_block *sb);
+void reiserfs_free_bitmap_cache(struct super_block *sb);
+void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info);
+struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, unsigned int bitmap);
+int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value);
+void reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *,
+ b_blocknr_t, int for_unformatted);
+int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t *, b_blocknr_t *, int,
+ int);
+static inline int reiserfs_new_form_blocknrs(struct tree_balance *tb,
+ b_blocknr_t * new_blocknrs,
+ int amount_needed)
+{
+ reiserfs_blocknr_hint_t hint = {
+ .th = tb->transaction_handle,
+ .path = tb->tb_path,
+ .inode = NULL,
+ .key = tb->key,
+ .block = 0,
+ .formatted_node = 1
+ };
+ return reiserfs_allocate_blocknrs(&hint, new_blocknrs, amount_needed,
+ 0);
+}
+
+static inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle
+ *th, struct inode *inode,
+ b_blocknr_t * new_blocknrs,
+ struct treepath *path,
+ sector_t block)
+{
+ reiserfs_blocknr_hint_t hint = {
+ .th = th,
+ .path = path,
+ .inode = inode,
+ .block = block,
+ .formatted_node = 0,
+ .preallocate = 0
+ };
+ return reiserfs_allocate_blocknrs(&hint, new_blocknrs, 1, 0);
+}
+
+#ifdef REISERFS_PREALLOCATE
+static inline int reiserfs_new_unf_blocknrs2(struct reiserfs_transaction_handle
+ *th, struct inode *inode,
+ b_blocknr_t * new_blocknrs,
+ struct treepath *path,
+ sector_t block)
+{
+ reiserfs_blocknr_hint_t hint = {
+ .th = th,
+ .path = path,
+ .inode = inode,
+ .block = block,
+ .formatted_node = 0,
+ .preallocate = 1
+ };
+ return reiserfs_allocate_blocknrs(&hint, new_blocknrs, 1, 0);
+}
+
+void reiserfs_discard_prealloc(struct reiserfs_transaction_handle *th,
+ struct inode *inode);
+void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th);
+#endif
+
+/* hashes.c */
+__u32 keyed_hash(const signed char *msg, int len);
+__u32 yura_hash(const signed char *msg, int len);
+__u32 r5_hash(const signed char *msg, int len);
+
+#define reiserfs_set_le_bit __set_bit_le
+#define reiserfs_test_and_set_le_bit __test_and_set_bit_le
+#define reiserfs_clear_le_bit __clear_bit_le
+#define reiserfs_test_and_clear_le_bit __test_and_clear_bit_le
+#define reiserfs_test_le_bit test_bit_le
+#define reiserfs_find_next_zero_le_bit find_next_zero_bit_le
+
+/* sometimes reiserfs_truncate may require to allocate few new blocks
+ to perform indirect2direct conversion. People probably used to
+ think, that truncate should work without problems on a filesystem
+ without free disk space. They may complain that they can not
+ truncate due to lack of free disk space. This spare space allows us
+ to not worry about it. 500 is probably too much, but it should be
+ absolutely safe */
+#define SPARE_SPACE 500
+
+/* prototypes from ioctl.c */
+long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+long reiserfs_compat_ioctl(struct file *filp,
+ unsigned int cmd, unsigned long arg);
+int reiserfs_unpack(struct inode *inode, struct file *filp);
diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c
index 7483279..9a17f63 100644
--- a/fs/reiserfs/resize.c
+++ b/fs/reiserfs/resize.c
@@ -13,8 +13,7 @@
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/errno.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_fs_sb.h>
+#include "reiserfs.h"
#include <linux/buffer_head.h>
int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 313d39d..f8afa4b 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -51,7 +51,7 @@
#include <linux/time.h>
#include <linux/string.h>
#include <linux/pagemap.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/buffer_head.h>
#include <linux/quotaops.h>
@@ -1284,12 +1284,12 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
** -clm
*/
- data = kmap_atomic(un_bh->b_page, KM_USER0);
+ data = kmap_atomic(un_bh->b_page);
off = ((le_ih_k_offset(&s_ih) - 1) & (PAGE_CACHE_SIZE - 1));
memcpy(data + off,
B_I_PITEM(PATH_PLAST_BUFFER(path), &s_ih),
ret_value);
- kunmap_atomic(data, KM_USER0);
+ kunmap_atomic(data);
}
/* Perform balancing after all resources have been collected at once. */
do_balance(&s_del_balance, NULL, NULL, M_DELETE);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index e12d8b9..8b7616e 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -16,9 +16,9 @@
#include <linux/vmalloc.h>
#include <linux/time.h>
#include <asm/uaccess.h>
-#include <linux/reiserfs_fs.h>
-#include <linux/reiserfs_acl.h>
-#include <linux/reiserfs_xattr.h>
+#include "reiserfs.h"
+#include "acl.h"
+#include "xattr.h"
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
@@ -1874,11 +1874,9 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
unlock_new_inode(root_inode);
}
- s->s_root = d_alloc_root(root_inode);
- if (!s->s_root) {
- iput(root_inode);
+ s->s_root = d_make_root(root_inode);
+ if (!s->s_root)
goto error;
- }
// define and initialize hash function
sbi->s_hash_function = hash_function(s);
if (sbi->s_hash_function == NULL) {
diff --git a/fs/reiserfs/tail_conversion.c b/fs/reiserfs/tail_conversion.c
index d7f6e51..5e2624d 100644
--- a/fs/reiserfs/tail_conversion.c
+++ b/fs/reiserfs/tail_conversion.c
@@ -5,7 +5,7 @@
#include <linux/time.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
/* access to tail : when one is going to read tail it must make sure, that is not running.
direct2indirect and indirect2direct can not run concurrently */
@@ -128,9 +128,9 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
if (up_to_date_bh) {
unsigned pgoff =
(tail_offset + total_tail - 1) & (PAGE_CACHE_SIZE - 1);
- char *kaddr = kmap_atomic(up_to_date_bh->b_page, KM_USER0);
+ char *kaddr = kmap_atomic(up_to_date_bh->b_page);
memset(kaddr + pgoff, 0, blk_size - total_tail);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
}
REISERFS_I(inode)->i_first_direct_byte = U32_MAX;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index c24deda..46fc1c2 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -33,7 +33,7 @@
* The xattrs themselves are protected by the xattr_sem.
*/
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/capability.h>
#include <linux/dcache.h>
#include <linux/namei.h>
@@ -43,8 +43,8 @@
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
-#include <linux/reiserfs_xattr.h>
-#include <linux/reiserfs_acl.h>
+#include "xattr.h"
+#include "acl.h"
#include <asm/uaccess.h>
#include <net/checksum.h>
#include <linux/stat.h>
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
new file mode 100644
index 0000000..f59626c
--- /dev/null
+++ b/fs/reiserfs/xattr.h
@@ -0,0 +1,122 @@
+#include <linux/reiserfs_xattr.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rwsem.h>
+
+struct inode;
+struct dentry;
+struct iattr;
+struct super_block;
+struct nameidata;
+
+int reiserfs_xattr_register_handlers(void) __init;
+void reiserfs_xattr_unregister_handlers(void);
+int reiserfs_xattr_init(struct super_block *sb, int mount_flags);
+int reiserfs_lookup_privroot(struct super_block *sb);
+int reiserfs_delete_xattrs(struct inode *inode);
+int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs);
+int reiserfs_permission(struct inode *inode, int mask);
+
+#ifdef CONFIG_REISERFS_FS_XATTR
+#define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir)
+ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size);
+int reiserfs_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags);
+ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
+int reiserfs_removexattr(struct dentry *dentry, const char *name);
+
+int reiserfs_xattr_get(struct inode *, const char *, void *, size_t);
+int reiserfs_xattr_set(struct inode *, const char *, const void *, size_t, int);
+int reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *,
+ struct inode *, const char *, const void *,
+ size_t, int);
+
+extern const struct xattr_handler reiserfs_xattr_user_handler;
+extern const struct xattr_handler reiserfs_xattr_trusted_handler;
+extern const struct xattr_handler reiserfs_xattr_security_handler;
+#ifdef CONFIG_REISERFS_FS_SECURITY
+int reiserfs_security_init(struct inode *dir, struct inode *inode,
+ const struct qstr *qstr,
+ struct reiserfs_security_handle *sec);
+int reiserfs_security_write(struct reiserfs_transaction_handle *th,
+ struct inode *inode,
+ struct reiserfs_security_handle *sec);
+void reiserfs_security_free(struct reiserfs_security_handle *sec);
+#endif
+
+static inline int reiserfs_xattrs_initialized(struct super_block *sb)
+{
+ return REISERFS_SB(sb)->priv_root != NULL;
+}
+
+#define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header))
+static inline loff_t reiserfs_xattr_nblocks(struct inode *inode, loff_t size)
+{
+ loff_t ret = 0;
+ if (reiserfs_file_data_log(inode)) {
+ ret = _ROUND_UP(xattr_size(size), inode->i_sb->s_blocksize);
+ ret >>= inode->i_sb->s_blocksize_bits;
+ }
+ return ret;
+}
+
+/* We may have to create up to 3 objects: xattr root, xattr dir, xattr file.
+ * Let's try to be smart about it.
+ * xattr root: We cache it. If it's not cached, we may need to create it.
+ * xattr dir: If anything has been loaded for this inode, we can set a flag
+ * saying so.
+ * xattr file: Since we don't cache xattrs, we can't tell. We always include
+ * blocks for it.
+ *
+ * However, since root and dir can be created between calls - YOU MUST SAVE
+ * THIS VALUE.
+ */
+static inline size_t reiserfs_xattr_jcreate_nblocks(struct inode *inode)
+{
+ size_t nblocks = JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb);
+
+ if ((REISERFS_I(inode)->i_flags & i_has_xattr_dir) == 0) {
+ nblocks += JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb);
+ if (!REISERFS_SB(inode->i_sb)->xattr_root->d_inode)
+ nblocks += JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb);
+ }
+
+ return nblocks;
+}
+
+static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
+{
+ init_rwsem(&REISERFS_I(inode)->i_xattr_sem);
+}
+
+#else
+
+#define reiserfs_getxattr NULL
+#define reiserfs_setxattr NULL
+#define reiserfs_listxattr NULL
+#define reiserfs_removexattr NULL
+
+static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
+{
+}
+#endif /* CONFIG_REISERFS_FS_XATTR */
+
+#ifndef CONFIG_REISERFS_FS_SECURITY
+static inline int reiserfs_security_init(struct inode *dir,
+ struct inode *inode,
+ const struct qstr *qstr,
+ struct reiserfs_security_handle *sec)
+{
+ return 0;
+}
+static inline int
+reiserfs_security_write(struct reiserfs_transaction_handle *th,
+ struct inode *inode,
+ struct reiserfs_security_handle *sec)
+{
+ return 0;
+}
+static inline void reiserfs_security_free(struct reiserfs_security_handle *sec)
+{}
+#endif
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 6da0396..44474f9 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -1,14 +1,14 @@
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/posix_acl.h>
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/errno.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
#include <linux/slab.h>
#include <linux/posix_acl_xattr.h>
-#include <linux/reiserfs_xattr.h>
-#include <linux/reiserfs_acl.h>
+#include "xattr.h"
+#include "acl.h"
#include <asm/uaccess.h>
static int reiserfs_set_acl(struct reiserfs_transaction_handle *th,
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index 534668f..800a3ce 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -1,10 +1,10 @@
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
#include <linux/slab.h>
-#include <linux/reiserfs_xattr.h>
+#include "xattr.h"
#include <linux/security.h>
#include <asm/uaccess.h>
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index 9883736..a003571 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -1,10 +1,10 @@
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
-#include <linux/reiserfs_xattr.h>
+#include "xattr.h"
#include <asm/uaccess.h>
static int
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index 45ae1a0..8667491 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -1,9 +1,9 @@
-#include <linux/reiserfs_fs.h>
+#include "reiserfs.h"
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
-#include <linux/reiserfs_xattr.h>
+#include "xattr.h"
#include <asm/uaccess.h>
static int
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index bb36ab7..e64f6b5 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -538,14 +538,12 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
if (IS_ERR(root))
goto error;
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root)
- goto error_i;
+ goto error;
return 0;
-error_i:
- iput(root);
error:
return -EINVAL;
error_rsb_inval:
diff --git a/fs/select.c b/fs/select.c
index d33418f..6fb8943 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -17,7 +17,7 @@
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
@@ -223,7 +223,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
get_file(filp);
entry->filp = filp;
entry->wait_address = wait_address;
- entry->key = p->key;
+ entry->key = p->_key;
init_waitqueue_func_entry(&entry->wait, pollwake);
entry->wait.private = pwq;
add_wait_queue(wait_address, &entry->wait);
@@ -386,13 +386,11 @@ get_max:
static inline void wait_key_set(poll_table *wait, unsigned long in,
unsigned long out, unsigned long bit)
{
- if (wait) {
- wait->key = POLLEX_SET;
- if (in & bit)
- wait->key |= POLLIN_SET;
- if (out & bit)
- wait->key |= POLLOUT_SET;
- }
+ wait->_key = POLLEX_SET;
+ if (in & bit)
+ wait->_key |= POLLIN_SET;
+ if (out & bit)
+ wait->_key |= POLLOUT_SET;
}
int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
@@ -414,7 +412,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
poll_initwait(&table);
wait = &table.pt;
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
- wait = NULL;
+ wait->_qproc = NULL;
timed_out = 1;
}
@@ -459,17 +457,17 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
retval++;
- wait = NULL;
+ wait->_qproc = NULL;
}
if ((mask & POLLOUT_SET) && (out & bit)) {
res_out |= bit;
retval++;
- wait = NULL;
+ wait->_qproc = NULL;
}
if ((mask & POLLEX_SET) && (ex & bit)) {
res_ex |= bit;
retval++;
- wait = NULL;
+ wait->_qproc = NULL;
}
}
}
@@ -481,7 +479,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
*rexp = res_ex;
cond_resched();
}
- wait = NULL;
+ wait->_qproc = NULL;
if (retval || timed_out || signal_pending(current))
break;
if (table.error) {
@@ -720,7 +718,7 @@ struct poll_list {
* interested in events matching the pollfd->events mask, and the result
* matching that mask is both recorded in pollfd->revents and returned. The
* pwait poll_table will be used by the fd-provided poll handler for waiting,
- * if non-NULL.
+ * if pwait->_qproc is non-NULL.
*/
static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
{
@@ -738,9 +736,7 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
if (file != NULL) {
mask = DEFAULT_POLLMASK;
if (file->f_op && file->f_op->poll) {
- if (pwait)
- pwait->key = pollfd->events |
- POLLERR | POLLHUP;
+ pwait->_key = pollfd->events|POLLERR|POLLHUP;
mask = file->f_op->poll(file, pwait);
}
/* Mask out unneeded events. */
@@ -763,7 +759,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
- pt = NULL;
+ pt->_qproc = NULL;
timed_out = 1;
}
@@ -781,22 +777,22 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
for (; pfd != pfd_end; pfd++) {
/*
* Fish for events. If we found one, record it
- * and kill the poll_table, so we don't
+ * and kill poll_table->_qproc, so we don't
* needlessly register any other waiters after
* this. They'll get immediately deregistered
* when we break out and return.
*/
if (do_pollfd(pfd, pt)) {
count++;
- pt = NULL;
+ pt->_qproc = NULL;
}
}
}
/*
* All waiters have already been registered, so don't provide
- * a poll_table to them on the next loop iteration.
+ * a poll_table->_qproc to them on the next loop iteration.
*/
- pt = NULL;
+ pt->_qproc = NULL;
if (!count) {
count = wait->error;
if (signal_pending(current))
@@ -912,7 +908,7 @@ static long do_restart_poll(struct restart_block *restart_block)
}
SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
- long, timeout_msecs)
+ int, timeout_msecs)
{
struct timespec end_time, *to = NULL;
int ret;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4023d6b..0cbd049 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -6,13 +6,29 @@
*/
#include <linux/fs.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/page.h>
+
+/*
+ * seq_files have a buffer which can may overflow. When this happens a larger
+ * buffer is reallocated and all the data will be printed again.
+ * The overflow state is true when m->count == m->size.
+ */
+static bool seq_overflow(struct seq_file *m)
+{
+ return m->count == m->size;
+}
+
+static void seq_set_overflow(struct seq_file *m)
+{
+ m->count = m->size;
+}
+
/**
* seq_open - initialize sequential file
* @file: file we initialize
@@ -92,7 +108,7 @@ static int traverse(struct seq_file *m, loff_t offset)
error = 0;
m->count = 0;
}
- if (m->count == m->size)
+ if (seq_overflow(m))
goto Eoverflow;
if (pos + m->count > offset) {
m->from = offset - pos;
@@ -140,9 +156,21 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
mutex_lock(&m->lock);
+ /*
+ * seq_file->op->..m_start/m_stop/m_next may do special actions
+ * or optimisations based on the file->f_version, so we want to
+ * pass the file->f_version to those methods.
+ *
+ * seq_file->version is just copy of f_version, and seq_file
+ * methods can treat it simply as file version.
+ * It is copied in first and copied out after all operations.
+ * It is convenient to have it as part of structure to avoid the
+ * need of passing another argument to all the seq_file methods.
+ */
+ m->version = file->f_version;
+
/* Don't assume *ppos is where we left it */
if (unlikely(*ppos != m->read_pos)) {
- m->read_pos = *ppos;
while ((err = traverse(m, *ppos)) == -EAGAIN)
;
if (err) {
@@ -152,21 +180,11 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
m->index = 0;
m->count = 0;
goto Done;
+ } else {
+ m->read_pos = *ppos;
}
}
- /*
- * seq_file->op->..m_start/m_stop/m_next may do special actions
- * or optimisations based on the file->f_version, so we want to
- * pass the file->f_version to those methods.
- *
- * seq_file->version is just copy of f_version, and seq_file
- * methods can treat it simply as file version.
- * It is copied in first and copied out after all operations.
- * It is convenient to have it as part of structure to avoid the
- * need of passing another argument to all the seq_file methods.
- */
- m->version = file->f_version;
/* grab buffer if we didn't have one */
if (!m->buf) {
m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
@@ -232,7 +250,7 @@ Fill:
break;
}
err = m->op->show(m, p);
- if (m->count == m->size || err) {
+ if (seq_overflow(m) || err) {
m->count = offs;
if (likely(err <= 0))
break;
@@ -359,7 +377,7 @@ int seq_escape(struct seq_file *m, const char *s, const char *esc)
*p++ = '0' + (c & 07);
continue;
}
- m->count = m->size;
+ seq_set_overflow(m);
return -1;
}
m->count = p - m->buf;
@@ -381,7 +399,7 @@ int seq_printf(struct seq_file *m, const char *f, ...)
return 0;
}
}
- m->count = m->size;
+ seq_set_overflow(m);
return -1;
}
EXPORT_SYMBOL(seq_printf);
@@ -510,7 +528,7 @@ int seq_bitmap(struct seq_file *m, const unsigned long *bits,
return 0;
}
}
- m->count = m->size;
+ seq_set_overflow(m);
return -1;
}
EXPORT_SYMBOL(seq_bitmap);
@@ -526,7 +544,7 @@ int seq_bitmap_list(struct seq_file *m, const unsigned long *bits,
return 0;
}
}
- m->count = m->size;
+ seq_set_overflow(m);
return -1;
}
EXPORT_SYMBOL(seq_bitmap_list);
@@ -637,11 +655,63 @@ int seq_puts(struct seq_file *m, const char *s)
m->count += len;
return 0;
}
- m->count = m->size;
+ seq_set_overflow(m);
return -1;
}
EXPORT_SYMBOL(seq_puts);
+/*
+ * A helper routine for putting decimal numbers without rich format of printf().
+ * only 'unsigned long long' is supported.
+ * This routine will put one byte delimiter + number into seq_file.
+ * This routine is very quick when you show lots of numbers.
+ * In usual cases, it will be better to use seq_printf(). It's easier to read.
+ */
+int seq_put_decimal_ull(struct seq_file *m, char delimiter,
+ unsigned long long num)
+{
+ int len;
+
+ if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */
+ goto overflow;
+
+ if (delimiter)
+ m->buf[m->count++] = delimiter;
+
+ if (num < 10) {
+ m->buf[m->count++] = num + '0';
+ return 0;
+ }
+
+ len = num_to_str(m->buf + m->count, m->size - m->count, num);
+ if (!len)
+ goto overflow;
+ m->count += len;
+ return 0;
+overflow:
+ seq_set_overflow(m);
+ return -1;
+}
+EXPORT_SYMBOL(seq_put_decimal_ull);
+
+int seq_put_decimal_ll(struct seq_file *m, char delimiter,
+ long long num)
+{
+ if (num < 0) {
+ if (m->count + 3 >= m->size) {
+ seq_set_overflow(m);
+ return -1;
+ }
+ if (delimiter)
+ m->buf[m->count++] = delimiter;
+ num = -num;
+ delimiter = '-';
+ }
+ return seq_put_decimal_ull(m, delimiter, num);
+
+}
+EXPORT_SYMBOL(seq_put_decimal_ll);
+
/**
* seq_write - write arbitrary data to buffer
* @seq: seq_file identifying the buffer to which data should be written
@@ -657,7 +727,7 @@ int seq_write(struct seq_file *seq, const void *data, size_t len)
seq->count += len;
return 0;
}
- seq->count = seq->size;
+ seq_set_overflow(seq);
return -1;
}
EXPORT_SYMBOL(seq_write);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 492465b..7ae2a57 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -30,6 +30,21 @@
#include <linux/signalfd.h>
#include <linux/syscalls.h>
+void signalfd_cleanup(struct sighand_struct *sighand)
+{
+ wait_queue_head_t *wqh = &sighand->signalfd_wqh;
+ /*
+ * The lockless check can race with remove_wait_queue() in progress,
+ * but in this case its caller should run under rcu_read_lock() and
+ * sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
+ */
+ if (likely(!waitqueue_active(wqh)))
+ return;
+
+ /* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */
+ wake_up_poll(wqh, POLLHUP | POLLFREE);
+}
+
struct signalfd_ctx {
sigset_t sigmask;
};
diff --git a/fs/splice.c b/fs/splice.c
index 1ec0493..5f883de 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -25,7 +25,7 @@
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/writeback.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/uio.h>
#include <linux/security.h>
@@ -737,15 +737,12 @@ int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
goto out;
if (buf->page != page) {
- /*
- * Careful, ->map() uses KM_USER0!
- */
char *src = buf->ops->map(pipe, buf, 1);
- char *dst = kmap_atomic(page, KM_USER1);
+ char *dst = kmap_atomic(page);
memcpy(dst + offset, src + buf->offset, this_len);
flush_dcache_page(page);
- kunmap_atomic(dst, KM_USER1);
+ kunmap_atomic(dst);
buf->ops->unmap(pipe, buf, src);
}
ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 38bb1c6..8ca62c2 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -464,10 +464,10 @@ static int squashfs_readpage(struct file *file, struct page *page)
if (PageUptodate(push_page))
goto skip_page;
- pageaddr = kmap_atomic(push_page, KM_USER0);
+ pageaddr = kmap_atomic(push_page);
squashfs_copy_data(pageaddr, buffer, offset, avail);
memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
- kunmap_atomic(pageaddr, KM_USER0);
+ kunmap_atomic(pageaddr);
flush_dcache_page(push_page);
SetPageUptodate(push_page);
skip_page:
@@ -484,9 +484,9 @@ skip_page:
error_out:
SetPageError(page);
out:
- pageaddr = kmap_atomic(page, KM_USER0);
+ pageaddr = kmap_atomic(page);
memset(pageaddr, 0, PAGE_CACHE_SIZE);
- kunmap_atomic(pageaddr, KM_USER0);
+ kunmap_atomic(pageaddr);
flush_dcache_page(page);
if (!PageError(page))
SetPageUptodate(page);
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index ecaa2f7..970b116 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -316,11 +316,10 @@ check_directory_table:
}
insert_inode_hash(root);
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (sb->s_root == NULL) {
ERROR("Root inode create failed\n");
err = -ENOMEM;
- iput(root);
goto failed_mount;
}
diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c
index 1191817..12806df 100644
--- a/fs/squashfs/symlink.c
+++ b/fs/squashfs/symlink.c
@@ -90,14 +90,14 @@ static int squashfs_symlink_readpage(struct file *file, struct page *page)
goto error_out;
}
- pageaddr = kmap_atomic(page, KM_USER0);
+ pageaddr = kmap_atomic(page);
copied = squashfs_copy_data(pageaddr + bytes, entry, offset,
length - bytes);
if (copied == length - bytes)
memset(pageaddr + length, 0, PAGE_CACHE_SIZE - length);
else
block = entry->next_index;
- kunmap_atomic(pageaddr, KM_USER0);
+ kunmap_atomic(pageaddr);
squashfs_cache_put(entry);
}
diff --git a/fs/stack.c b/fs/stack.c
index 9c11519..5b53882 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/fs_stack.h>
diff --git a/fs/stat.c b/fs/stat.c
index 8806b89..c733dc5 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -4,7 +4,7 @@
* Copyright (C) 1991, 1992 Linus Torvalds
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/file.h>
@@ -307,7 +307,7 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
if (inode->i_op->readlink) {
error = security_inode_readlink(path.dentry);
if (!error) {
- touch_atime(path.mnt, path.dentry);
+ touch_atime(&path);
error = inode->i_op->readlink(path.dentry,
buf, bufsiz);
}
diff --git a/fs/statfs.c b/fs/statfs.c
index 2aa6a22..43e6b6f 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -1,5 +1,5 @@
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
diff --git a/fs/super.c b/fs/super.c
index 6015c02..cf00177 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -20,7 +20,7 @@
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/acct.h>
#include <linux/blkdev.h>
@@ -32,6 +32,7 @@
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
#include <linux/cleancache.h>
+#include <linux/fsnotify.h>
#include "internal.h"
@@ -250,7 +251,7 @@ void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
- cleancache_flush_fs(s);
+ cleancache_invalidate_fs(s);
fs->kill_sb(s);
/* caches are now gone, we can safely kill the shrinker now */
@@ -634,6 +635,28 @@ rescan:
EXPORT_SYMBOL(get_super);
/**
+ * get_super_thawed - get thawed superblock of a device
+ * @bdev: device to get the superblock for
+ *
+ * Scans the superblock list and finds the superblock of the file system
+ * mounted on the device. The superblock is returned once it is thawed
+ * (or immediately if it was not frozen). %NULL is returned if no match
+ * is found.
+ */
+struct super_block *get_super_thawed(struct block_device *bdev)
+{
+ while (1) {
+ struct super_block *s = get_super(bdev);
+ if (!s || s->s_frozen == SB_UNFROZEN)
+ return s;
+ up_read(&s->s_umount);
+ vfs_check_frozen(s, SB_FREEZE_WRITE);
+ put_super(s);
+ }
+}
+EXPORT_SYMBOL(get_super_thawed);
+
+/**
* get_active_super - get an active reference to the superblock of a device
* @bdev: device to get the superblock for
*
diff --git a/fs/sync.c b/fs/sync.c
index f3501ef..0e8db93 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -6,7 +6,7 @@
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/writeback.h>
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 7fdf6a7..2a7a3f5 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -22,76 +22,103 @@
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/security.h>
+#include <linux/hash.h>
#include "sysfs.h"
DEFINE_MUTEX(sysfs_mutex);
DEFINE_SPINLOCK(sysfs_assoc_lock);
+#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb);
+
static DEFINE_SPINLOCK(sysfs_ino_lock);
static DEFINE_IDA(sysfs_ino_ida);
/**
- * sysfs_link_sibling - link sysfs_dirent into sibling list
+ * sysfs_name_hash
+ * @ns: Namespace tag to hash
+ * @name: Null terminated string to hash
+ *
+ * Returns 31 bit hash of ns + name (so it fits in an off_t )
+ */
+static unsigned int sysfs_name_hash(const void *ns, const char *name)
+{
+ unsigned long hash = init_name_hash();
+ unsigned int len = strlen(name);
+ while (len--)
+ hash = partial_name_hash(*name++, hash);
+ hash = ( end_name_hash(hash) ^ hash_ptr( (void *)ns, 31 ) );
+ hash &= 0x7fffffffU;
+ /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
+ if (hash < 1)
+ hash += 2;
+ if (hash >= INT_MAX)
+ hash = INT_MAX - 1;
+ return hash;
+}
+
+static int sysfs_name_compare(unsigned int hash, const void *ns,
+ const char *name, const struct sysfs_dirent *sd)
+{
+ if (hash != sd->s_hash)
+ return hash - sd->s_hash;
+ if (ns != sd->s_ns)
+ return ns - sd->s_ns;
+ return strcmp(name, sd->s_name);
+}
+
+static int sysfs_sd_compare(const struct sysfs_dirent *left,
+ const struct sysfs_dirent *right)
+{
+ return sysfs_name_compare(left->s_hash, left->s_ns, left->s_name,
+ right);
+}
+
+/**
+ * sysfs_link_subling - link sysfs_dirent into sibling rbtree
* @sd: sysfs_dirent of interest
*
- * Link @sd into its sibling list which starts from
+ * Link @sd into its sibling rbtree which starts from
* sd->s_parent->s_dir.children.
*
* Locking:
* mutex_lock(sysfs_mutex)
+ *
+ * RETURNS:
+ * 0 on susccess -EEXIST on failure.
*/
-static void sysfs_link_sibling(struct sysfs_dirent *sd)
+static int sysfs_link_sibling(struct sysfs_dirent *sd)
{
- struct sysfs_dirent *parent_sd = sd->s_parent;
-
- struct rb_node **p;
- struct rb_node *parent;
+ struct rb_node **node = &sd->s_parent->s_dir.children.rb_node;
+ struct rb_node *parent = NULL;
if (sysfs_type(sd) == SYSFS_DIR)
- parent_sd->s_dir.subdirs++;
-
- p = &parent_sd->s_dir.inode_tree.rb_node;
- parent = NULL;
- while (*p) {
- parent = *p;
-#define node rb_entry(parent, struct sysfs_dirent, inode_node)
- if (sd->s_ino < node->s_ino) {
- p = &node->inode_node.rb_left;
- } else if (sd->s_ino > node->s_ino) {
- p = &node->inode_node.rb_right;
- } else {
- printk(KERN_CRIT "sysfs: inserting duplicate inode '%lx'\n",
- (unsigned long) sd->s_ino);
- BUG();
- }
-#undef node
- }
- rb_link_node(&sd->inode_node, parent, p);
- rb_insert_color(&sd->inode_node, &parent_sd->s_dir.inode_tree);
-
- p = &parent_sd->s_dir.name_tree.rb_node;
- parent = NULL;
- while (*p) {
- int c;
- parent = *p;
-#define node rb_entry(parent, struct sysfs_dirent, name_node)
- c = strcmp(sd->s_name, node->s_name);
- if (c < 0) {
- p = &node->name_node.rb_left;
- } else {
- p = &node->name_node.rb_right;
- }
-#undef node
+ sd->s_parent->s_dir.subdirs++;
+
+ while (*node) {
+ struct sysfs_dirent *pos;
+ int result;
+
+ pos = to_sysfs_dirent(*node);
+ parent = *node;
+ result = sysfs_sd_compare(sd, pos);
+ if (result < 0)
+ node = &pos->s_rb.rb_left;
+ else if (result > 0)
+ node = &pos->s_rb.rb_right;
+ else
+ return -EEXIST;
}
- rb_link_node(&sd->name_node, parent, p);
- rb_insert_color(&sd->name_node, &parent_sd->s_dir.name_tree);
+ /* add new node and rebalance the tree */
+ rb_link_node(&sd->s_rb, parent, node);
+ rb_insert_color(&sd->s_rb, &sd->s_parent->s_dir.children);
+ return 0;
}
/**
- * sysfs_unlink_sibling - unlink sysfs_dirent from sibling list
+ * sysfs_unlink_sibling - unlink sysfs_dirent from sibling rbtree
* @sd: sysfs_dirent of interest
*
- * Unlink @sd from its sibling list which starts from
+ * Unlink @sd from its sibling rbtree which starts from
* sd->s_parent->s_dir.children.
*
* Locking:
@@ -102,8 +129,7 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
if (sysfs_type(sd) == SYSFS_DIR)
sd->s_parent->s_dir.subdirs--;
- rb_erase(&sd->inode_node, &sd->s_parent->s_dir.inode_tree);
- rb_erase(&sd->name_node, &sd->s_parent->s_dir.name_tree);
+ rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children);
}
/**
@@ -198,7 +224,7 @@ static void sysfs_deactivate(struct sysfs_dirent *sd)
rwsem_release(&sd->dep_map, 1, _RET_IP_);
}
-static int sysfs_alloc_ino(ino_t *pino)
+static int sysfs_alloc_ino(unsigned int *pino)
{
int ino, rc;
@@ -217,7 +243,7 @@ static int sysfs_alloc_ino(ino_t *pino)
return rc;
}
-static void sysfs_free_ino(ino_t ino)
+static void sysfs_free_ino(unsigned int ino)
{
spin_lock(&sysfs_ino_lock);
ida_remove(&sysfs_ino_ida, ino);
@@ -402,6 +428,7 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
struct sysfs_inode_attrs *ps_iattr;
+ int ret;
if (!!sysfs_ns_type(acxt->parent_sd) != !!sd->s_ns) {
WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
@@ -410,12 +437,12 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
return -EINVAL;
}
- if (sysfs_find_dirent(acxt->parent_sd, sd->s_ns, sd->s_name))
- return -EEXIST;
-
+ sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
sd->s_parent = sysfs_get(acxt->parent_sd);
- sysfs_link_sibling(sd);
+ ret = sysfs_link_sibling(sd);
+ if (ret)
+ return ret;
/* Update timestamps on the parent */
ps_iattr = acxt->parent_sd->s_iattr;
@@ -565,8 +592,8 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
const void *ns,
const unsigned char *name)
{
- struct rb_node *p = parent_sd->s_dir.name_tree.rb_node;
- struct sysfs_dirent *found = NULL;
+ struct rb_node *node = parent_sd->s_dir.children.rb_node;
+ unsigned int hash;
if (!!sysfs_ns_type(parent_sd) != !!ns) {
WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
@@ -575,33 +602,21 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
return NULL;
}
- while (p) {
- int c;
-#define node rb_entry(p, struct sysfs_dirent, name_node)
- c = strcmp(name, node->s_name);
- if (c < 0) {
- p = node->name_node.rb_left;
- } else if (c > 0) {
- p = node->name_node.rb_right;
- } else {
- found = node;
- p = node->name_node.rb_left;
- }
-#undef node
- }
-
- if (found) {
- while (found->s_ns != ns) {
- p = rb_next(&found->name_node);
- if (!p)
- return NULL;
- found = rb_entry(p, struct sysfs_dirent, name_node);
- if (strcmp(name, found->s_name))
- return NULL;
- }
+ hash = sysfs_name_hash(ns, name);
+ while (node) {
+ struct sysfs_dirent *sd;
+ int result;
+
+ sd = to_sysfs_dirent(node);
+ result = sysfs_name_compare(hash, ns, name, sd);
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return sd;
}
-
- return found;
+ return NULL;
}
/**
@@ -804,9 +819,9 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
sysfs_addrm_start(&acxt, dir_sd);
- pos = rb_first(&dir_sd->s_dir.inode_tree);
+ pos = rb_first(&dir_sd->s_dir.children);
while (pos) {
- struct sysfs_dirent *sd = rb_entry(pos, struct sysfs_dirent, inode_node);
+ struct sysfs_dirent *sd = to_sysfs_dirent(pos);
pos = rb_next(pos);
if (sysfs_type(sd) != SYSFS_DIR)
sysfs_remove_one(&acxt, sd);
@@ -863,6 +878,7 @@ int sysfs_rename(struct sysfs_dirent *sd,
dup_name = sd->s_name;
sd->s_name = new_name;
+ sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
}
/* Move to the appropriate place in the appropriate directories rbtree. */
@@ -919,38 +935,36 @@ static int sysfs_dir_release(struct inode *inode, struct file *filp)
}
static struct sysfs_dirent *sysfs_dir_pos(const void *ns,
- struct sysfs_dirent *parent_sd, ino_t ino, struct sysfs_dirent *pos)
+ struct sysfs_dirent *parent_sd, loff_t hash, struct sysfs_dirent *pos)
{
if (pos) {
int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) &&
pos->s_parent == parent_sd &&
- ino == pos->s_ino;
+ hash == pos->s_hash;
sysfs_put(pos);
if (!valid)
pos = NULL;
}
- if (!pos && (ino > 1) && (ino < INT_MAX)) {
- struct rb_node *p = parent_sd->s_dir.inode_tree.rb_node;
- while (p) {
-#define node rb_entry(p, struct sysfs_dirent, inode_node)
- if (ino < node->s_ino) {
- pos = node;
- p = node->inode_node.rb_left;
- } else if (ino > node->s_ino) {
- p = node->inode_node.rb_right;
- } else {
- pos = node;
+ if (!pos && (hash > 1) && (hash < INT_MAX)) {
+ struct rb_node *node = parent_sd->s_dir.children.rb_node;
+ while (node) {
+ pos = to_sysfs_dirent(node);
+
+ if (hash < pos->s_hash)
+ node = node->rb_left;
+ else if (hash > pos->s_hash)
+ node = node->rb_right;
+ else
break;
- }
-#undef node
}
}
+ /* Skip over entries in the wrong namespace */
while (pos && pos->s_ns != ns) {
- struct rb_node *p = rb_next(&pos->inode_node);
- if (!p)
+ struct rb_node *node = rb_next(&pos->s_rb);
+ if (!node)
pos = NULL;
else
- pos = rb_entry(p, struct sysfs_dirent, inode_node);
+ pos = to_sysfs_dirent(node);
}
return pos;
}
@@ -960,11 +974,11 @@ static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns,
{
pos = sysfs_dir_pos(ns, parent_sd, ino, pos);
if (pos) do {
- struct rb_node *p = rb_next(&pos->inode_node);
- if (!p)
+ struct rb_node *node = rb_next(&pos->s_rb);
+ if (!node)
pos = NULL;
else
- pos = rb_entry(p, struct sysfs_dirent, inode_node);
+ pos = to_sysfs_dirent(node);
} while (pos && pos->s_ns != ns);
return pos;
}
@@ -1006,7 +1020,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
len = strlen(name);
ino = pos->s_ino;
type = dt_type(pos);
- filp->f_pos = ino;
+ filp->f_pos = pos->s_hash;
filp->private_data = sysfs_get(pos);
mutex_unlock(&sysfs_mutex);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 62f4fb3..00012e3 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -493,6 +493,12 @@ int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr,
const void *ns = NULL;
int err;
+ if (!dir_sd) {
+ WARN(1, KERN_ERR "sysfs: kobject %s without dirent\n",
+ kobject_name(kobj));
+ return -ENOENT;
+ }
+
err = 0;
if (!sysfs_ns_type(dir_sd))
goto out;
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 4a802b4..feb2d69 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -136,12 +136,13 @@ static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, u32 *sec
void *old_secdata;
size_t old_secdata_len;
- iattrs = sd->s_iattr;
- if (!iattrs)
- iattrs = sysfs_init_inode_attrs(sd);
- if (!iattrs)
- return -ENOMEM;
+ if (!sd->s_iattr) {
+ sd->s_iattr = sysfs_init_inode_attrs(sd);
+ if (!sd->s_iattr)
+ return -ENOMEM;
+ }
+ iattrs = sd->s_iattr;
old_secdata = iattrs->ia_secdata;
old_secdata_len = iattrs->ia_secdata_len;
@@ -318,8 +319,11 @@ int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const cha
struct sysfs_addrm_cxt acxt;
struct sysfs_dirent *sd;
- if (!dir_sd)
+ if (!dir_sd) {
+ WARN(1, KERN_WARNING "sysfs: can not remove '%s', no directory\n",
+ name);
return -ENOENT;
+ }
sysfs_addrm_start(&acxt, dir_sd);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index e34f0d9..52c3bdb 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -36,7 +36,7 @@ struct sysfs_dirent sysfs_root = {
.s_name = "",
.s_count = ATOMIC_INIT(1),
.s_flags = SYSFS_DIR | (KOBJ_NS_TYPE_NONE << SYSFS_NS_TYPE_SHIFT),
- .s_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
+ .s_mode = S_IFDIR | S_IRUGO | S_IXUGO,
.s_ino = 1,
};
@@ -61,10 +61,9 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent)
}
/* instantiate and link root dentry */
- root = d_alloc_root(inode);
+ root = d_make_root(inode);
if (!root) {
pr_debug("%s: could not get root dentry!\n",__func__);
- iput(inode);
return -ENOMEM;
}
root->d_fsdata = &sysfs_root;
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 7484a36..661a963 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -20,9 +20,8 @@ struct sysfs_elem_dir {
struct kobject *kobj;
unsigned long subdirs;
-
- struct rb_root inode_tree;
- struct rb_root name_tree;
+ /* children rbtree starts here and goes through sd->s_rb */
+ struct rb_root children;
};
struct sysfs_elem_symlink {
@@ -62,8 +61,7 @@ struct sysfs_dirent {
struct sysfs_dirent *s_parent;
const char *s_name;
- struct rb_node inode_node;
- struct rb_node name_node;
+ struct rb_node s_rb;
union {
struct completion *completion;
@@ -71,6 +69,7 @@ struct sysfs_dirent {
} u;
const void *s_ns; /* namespace tag */
+ unsigned int s_hash; /* ns + name hash */
union {
struct sysfs_elem_dir s_dir;
struct sysfs_elem_symlink s_symlink;
@@ -78,9 +77,9 @@ struct sysfs_dirent {
struct sysfs_elem_bin_attr s_bin_attr;
};
- unsigned int s_flags;
+ unsigned short s_flags;
umode_t s_mode;
- ino_t s_ino;
+ unsigned int s_ino;
struct sysfs_inode_attrs *s_iattr;
};
@@ -95,11 +94,11 @@ struct sysfs_dirent {
#define SYSFS_ACTIVE_REF (SYSFS_KOBJ_ATTR | SYSFS_KOBJ_BIN_ATTR)
/* identify any namespace tag on sysfs_dirents */
-#define SYSFS_NS_TYPE_MASK 0xff00
+#define SYSFS_NS_TYPE_MASK 0xf00
#define SYSFS_NS_TYPE_SHIFT 8
#define SYSFS_FLAG_MASK ~(SYSFS_NS_TYPE_MASK|SYSFS_TYPE_MASK)
-#define SYSFS_FLAG_REMOVED 0x020000
+#define SYSFS_FLAG_REMOVED 0x02000
static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
{
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index b217797..d7466e2 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -121,9 +121,6 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir,
{
struct inode *inode = old_dentry->d_inode;
- if (inode->i_nlink >= SYSV_SB(inode->i_sb)->s_link_max)
- return -EMLINK;
-
inode->i_ctime = CURRENT_TIME_SEC;
inode_inc_link_count(inode);
ihold(inode);
@@ -134,10 +131,8 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir,
static int sysv_mkdir(struct inode * dir, struct dentry *dentry, umode_t mode)
{
struct inode * inode;
- int err = -EMLINK;
+ int err;
- if (dir->i_nlink >= SYSV_SB(dir->i_sb)->s_link_max)
- goto out;
inode_inc_link_count(dir);
inode = sysv_new_inode(dir, S_IFDIR|mode);
@@ -251,11 +246,6 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry,
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
- if (dir_de) {
- err = -EMLINK;
- if (new_dir->i_nlink >= SYSV_SB(new_dir->i_sb)->s_link_max)
- goto out_dir;
- }
err = sysv_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index f60c196..7491c33 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -44,7 +44,7 @@ enum {
JAN_1_1980 = (10*365 + 2) * 24 * 60 * 60
};
-static void detected_xenix(struct sysv_sb_info *sbi)
+static void detected_xenix(struct sysv_sb_info *sbi, unsigned *max_links)
{
struct buffer_head *bh1 = sbi->s_bh1;
struct buffer_head *bh2 = sbi->s_bh2;
@@ -59,7 +59,7 @@ static void detected_xenix(struct sysv_sb_info *sbi)
sbd2 = (struct xenix_super_block *) (bh2->b_data - 512);
}
- sbi->s_link_max = XENIX_LINK_MAX;
+ *max_links = XENIX_LINK_MAX;
sbi->s_fic_size = XENIX_NICINOD;
sbi->s_flc_size = XENIX_NICFREE;
sbi->s_sbd1 = (char *)sbd1;
@@ -75,7 +75,7 @@ static void detected_xenix(struct sysv_sb_info *sbi)
sbi->s_nzones = fs32_to_cpu(sbi, sbd1->s_fsize);
}
-static void detected_sysv4(struct sysv_sb_info *sbi)
+static void detected_sysv4(struct sysv_sb_info *sbi, unsigned *max_links)
{
struct sysv4_super_block * sbd;
struct buffer_head *bh1 = sbi->s_bh1;
@@ -86,7 +86,7 @@ static void detected_sysv4(struct sysv_sb_info *sbi)
else
sbd = (struct sysv4_super_block *) bh2->b_data;
- sbi->s_link_max = SYSV_LINK_MAX;
+ *max_links = SYSV_LINK_MAX;
sbi->s_fic_size = SYSV_NICINOD;
sbi->s_flc_size = SYSV_NICFREE;
sbi->s_sbd1 = (char *)sbd;
@@ -103,7 +103,7 @@ static void detected_sysv4(struct sysv_sb_info *sbi)
sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize);
}
-static void detected_sysv2(struct sysv_sb_info *sbi)
+static void detected_sysv2(struct sysv_sb_info *sbi, unsigned *max_links)
{
struct sysv2_super_block *sbd;
struct buffer_head *bh1 = sbi->s_bh1;
@@ -114,7 +114,7 @@ static void detected_sysv2(struct sysv_sb_info *sbi)
else
sbd = (struct sysv2_super_block *) bh2->b_data;
- sbi->s_link_max = SYSV_LINK_MAX;
+ *max_links = SYSV_LINK_MAX;
sbi->s_fic_size = SYSV_NICINOD;
sbi->s_flc_size = SYSV_NICFREE;
sbi->s_sbd1 = (char *)sbd;
@@ -131,14 +131,14 @@ static void detected_sysv2(struct sysv_sb_info *sbi)
sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize);
}
-static void detected_coherent(struct sysv_sb_info *sbi)
+static void detected_coherent(struct sysv_sb_info *sbi, unsigned *max_links)
{
struct coh_super_block * sbd;
struct buffer_head *bh1 = sbi->s_bh1;
sbd = (struct coh_super_block *) bh1->b_data;
- sbi->s_link_max = COH_LINK_MAX;
+ *max_links = COH_LINK_MAX;
sbi->s_fic_size = COH_NICINOD;
sbi->s_flc_size = COH_NICFREE;
sbi->s_sbd1 = (char *)sbd;
@@ -154,12 +154,12 @@ static void detected_coherent(struct sysv_sb_info *sbi)
sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize);
}
-static void detected_v7(struct sysv_sb_info *sbi)
+static void detected_v7(struct sysv_sb_info *sbi, unsigned *max_links)
{
struct buffer_head *bh2 = sbi->s_bh2;
struct v7_super_block *sbd = (struct v7_super_block *)bh2->b_data;
- sbi->s_link_max = V7_LINK_MAX;
+ *max_links = V7_LINK_MAX;
sbi->s_fic_size = V7_NICINOD;
sbi->s_flc_size = V7_NICFREE;
sbi->s_sbd1 = (char *)sbd;
@@ -290,7 +290,7 @@ static char *flavour_names[] = {
[FSTYPE_AFS] = "AFS",
};
-static void (*flavour_setup[])(struct sysv_sb_info *) = {
+static void (*flavour_setup[])(struct sysv_sb_info *, unsigned *) = {
[FSTYPE_XENIX] = detected_xenix,
[FSTYPE_SYSV4] = detected_sysv4,
[FSTYPE_SYSV2] = detected_sysv2,
@@ -310,7 +310,7 @@ static int complete_read_super(struct super_block *sb, int silent, int size)
sbi->s_firstinodezone = 2;
- flavour_setup[sbi->s_type](sbi);
+ flavour_setup[sbi->s_type](sbi, &sb->s_max_links);
sbi->s_truncate = 1;
sbi->s_ndatazones = sbi->s_nzones - sbi->s_firstdatazone;
@@ -341,9 +341,8 @@ static int complete_read_super(struct super_block *sb, int silent, int size)
printk("SysV FS: get root inode failed\n");
return 0;
}
- sb->s_root = d_alloc_root(root_inode);
+ sb->s_root = d_make_root(root_inode);
if (!sb->s_root) {
- iput(root_inode);
printk("SysV FS: get root dentry failed\n");
return 0;
}
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 0e4b821..11b0767 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -24,7 +24,6 @@ struct sysv_sb_info {
char s_bytesex; /* bytesex (le/be/pdp) */
char s_truncate; /* if 1: names > SYSV_NAMELEN chars are truncated */
/* if 0: they are disallowed (ENAMETOOLONG) */
- nlink_t s_link_max; /* max number of hard links to a file */
unsigned int s_inodes_per_block; /* number of inodes per block */
unsigned int s_inodes_per_block_1; /* inodes_per_block - 1 */
unsigned int s_inodes_per_block_bits; /* log2(inodes_per_block) */
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index f922cba..1934084 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -36,7 +36,7 @@
#ifdef CONFIG_UBIFS_FS_DEBUG
-DEFINE_SPINLOCK(dbg_lock);
+static DEFINE_SPINLOCK(dbg_lock);
static const char *get_key_fmt(int fmt)
{
@@ -221,15 +221,15 @@ const char *dbg_jhead(int jhead)
static void dump_ch(const struct ubifs_ch *ch)
{
- printk(KERN_DEBUG "\tmagic %#x\n", le32_to_cpu(ch->magic));
- printk(KERN_DEBUG "\tcrc %#x\n", le32_to_cpu(ch->crc));
- printk(KERN_DEBUG "\tnode_type %d (%s)\n", ch->node_type,
+ printk(KERN_ERR "\tmagic %#x\n", le32_to_cpu(ch->magic));
+ printk(KERN_ERR "\tcrc %#x\n", le32_to_cpu(ch->crc));
+ printk(KERN_ERR "\tnode_type %d (%s)\n", ch->node_type,
dbg_ntype(ch->node_type));
- printk(KERN_DEBUG "\tgroup_type %d (%s)\n", ch->group_type,
+ printk(KERN_ERR "\tgroup_type %d (%s)\n", ch->group_type,
dbg_gtype(ch->group_type));
- printk(KERN_DEBUG "\tsqnum %llu\n",
+ printk(KERN_ERR "\tsqnum %llu\n",
(unsigned long long)le64_to_cpu(ch->sqnum));
- printk(KERN_DEBUG "\tlen %u\n", le32_to_cpu(ch->len));
+ printk(KERN_ERR "\tlen %u\n", le32_to_cpu(ch->len));
}
void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode)
@@ -240,43 +240,43 @@ void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode)
struct ubifs_dent_node *dent, *pdent = NULL;
int count = 2;
- printk(KERN_DEBUG "Dump in-memory inode:");
- printk(KERN_DEBUG "\tinode %lu\n", inode->i_ino);
- printk(KERN_DEBUG "\tsize %llu\n",
+ printk(KERN_ERR "Dump in-memory inode:");
+ printk(KERN_ERR "\tinode %lu\n", inode->i_ino);
+ printk(KERN_ERR "\tsize %llu\n",
(unsigned long long)i_size_read(inode));
- printk(KERN_DEBUG "\tnlink %u\n", inode->i_nlink);
- printk(KERN_DEBUG "\tuid %u\n", (unsigned int)inode->i_uid);
- printk(KERN_DEBUG "\tgid %u\n", (unsigned int)inode->i_gid);
- printk(KERN_DEBUG "\tatime %u.%u\n",
+ printk(KERN_ERR "\tnlink %u\n", inode->i_nlink);
+ printk(KERN_ERR "\tuid %u\n", (unsigned int)inode->i_uid);
+ printk(KERN_ERR "\tgid %u\n", (unsigned int)inode->i_gid);
+ printk(KERN_ERR "\tatime %u.%u\n",
(unsigned int)inode->i_atime.tv_sec,
(unsigned int)inode->i_atime.tv_nsec);
- printk(KERN_DEBUG "\tmtime %u.%u\n",
+ printk(KERN_ERR "\tmtime %u.%u\n",
(unsigned int)inode->i_mtime.tv_sec,
(unsigned int)inode->i_mtime.tv_nsec);
- printk(KERN_DEBUG "\tctime %u.%u\n",
+ printk(KERN_ERR "\tctime %u.%u\n",
(unsigned int)inode->i_ctime.tv_sec,
(unsigned int)inode->i_ctime.tv_nsec);
- printk(KERN_DEBUG "\tcreat_sqnum %llu\n", ui->creat_sqnum);
- printk(KERN_DEBUG "\txattr_size %u\n", ui->xattr_size);
- printk(KERN_DEBUG "\txattr_cnt %u\n", ui->xattr_cnt);
- printk(KERN_DEBUG "\txattr_names %u\n", ui->xattr_names);
- printk(KERN_DEBUG "\tdirty %u\n", ui->dirty);
- printk(KERN_DEBUG "\txattr %u\n", ui->xattr);
- printk(KERN_DEBUG "\tbulk_read %u\n", ui->xattr);
- printk(KERN_DEBUG "\tsynced_i_size %llu\n",
+ printk(KERN_ERR "\tcreat_sqnum %llu\n", ui->creat_sqnum);
+ printk(KERN_ERR "\txattr_size %u\n", ui->xattr_size);
+ printk(KERN_ERR "\txattr_cnt %u\n", ui->xattr_cnt);
+ printk(KERN_ERR "\txattr_names %u\n", ui->xattr_names);
+ printk(KERN_ERR "\tdirty %u\n", ui->dirty);
+ printk(KERN_ERR "\txattr %u\n", ui->xattr);
+ printk(KERN_ERR "\tbulk_read %u\n", ui->xattr);
+ printk(KERN_ERR "\tsynced_i_size %llu\n",
(unsigned long long)ui->synced_i_size);
- printk(KERN_DEBUG "\tui_size %llu\n",
+ printk(KERN_ERR "\tui_size %llu\n",
(unsigned long long)ui->ui_size);
- printk(KERN_DEBUG "\tflags %d\n", ui->flags);
- printk(KERN_DEBUG "\tcompr_type %d\n", ui->compr_type);
- printk(KERN_DEBUG "\tlast_page_read %lu\n", ui->last_page_read);
- printk(KERN_DEBUG "\tread_in_a_row %lu\n", ui->read_in_a_row);
- printk(KERN_DEBUG "\tdata_len %d\n", ui->data_len);
+ printk(KERN_ERR "\tflags %d\n", ui->flags);
+ printk(KERN_ERR "\tcompr_type %d\n", ui->compr_type);
+ printk(KERN_ERR "\tlast_page_read %lu\n", ui->last_page_read);
+ printk(KERN_ERR "\tread_in_a_row %lu\n", ui->read_in_a_row);
+ printk(KERN_ERR "\tdata_len %d\n", ui->data_len);
if (!S_ISDIR(inode->i_mode))
return;
- printk(KERN_DEBUG "List of directory entries:\n");
+ printk(KERN_ERR "List of directory entries:\n");
ubifs_assert(!mutex_is_locked(&c->tnc_mutex));
lowest_dent_key(c, &key, inode->i_ino);
@@ -284,11 +284,11 @@ void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode)
dent = ubifs_tnc_next_ent(c, &key, &nm);
if (IS_ERR(dent)) {
if (PTR_ERR(dent) != -ENOENT)
- printk(KERN_DEBUG "error %ld\n", PTR_ERR(dent));
+ printk(KERN_ERR "error %ld\n", PTR_ERR(dent));
break;
}
- printk(KERN_DEBUG "\t%d: %s (%s)\n",
+ printk(KERN_ERR "\t%d: %s (%s)\n",
count++, dent->name, get_dent_type(dent->type));
nm.name = dent->name;
@@ -312,8 +312,8 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
/* If the magic is incorrect, just hexdump the first bytes */
if (le32_to_cpu(ch->magic) != UBIFS_NODE_MAGIC) {
- printk(KERN_DEBUG "Not a node, first %zu bytes:", UBIFS_CH_SZ);
- print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 32, 1,
+ printk(KERN_ERR "Not a node, first %zu bytes:", UBIFS_CH_SZ);
+ print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 32, 1,
(void *)node, UBIFS_CH_SZ, 1);
return;
}
@@ -326,7 +326,7 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
{
const struct ubifs_pad_node *pad = node;
- printk(KERN_DEBUG "\tpad_len %u\n",
+ printk(KERN_ERR "\tpad_len %u\n",
le32_to_cpu(pad->pad_len));
break;
}
@@ -335,50 +335,50 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
const struct ubifs_sb_node *sup = node;
unsigned int sup_flags = le32_to_cpu(sup->flags);
- printk(KERN_DEBUG "\tkey_hash %d (%s)\n",
+ printk(KERN_ERR "\tkey_hash %d (%s)\n",
(int)sup->key_hash, get_key_hash(sup->key_hash));
- printk(KERN_DEBUG "\tkey_fmt %d (%s)\n",
+ printk(KERN_ERR "\tkey_fmt %d (%s)\n",
(int)sup->key_fmt, get_key_fmt(sup->key_fmt));
- printk(KERN_DEBUG "\tflags %#x\n", sup_flags);
- printk(KERN_DEBUG "\t big_lpt %u\n",
+ printk(KERN_ERR "\tflags %#x\n", sup_flags);
+ printk(KERN_ERR "\t big_lpt %u\n",
!!(sup_flags & UBIFS_FLG_BIGLPT));
- printk(KERN_DEBUG "\t space_fixup %u\n",
+ printk(KERN_ERR "\t space_fixup %u\n",
!!(sup_flags & UBIFS_FLG_SPACE_FIXUP));
- printk(KERN_DEBUG "\tmin_io_size %u\n",
+ printk(KERN_ERR "\tmin_io_size %u\n",
le32_to_cpu(sup->min_io_size));
- printk(KERN_DEBUG "\tleb_size %u\n",
+ printk(KERN_ERR "\tleb_size %u\n",
le32_to_cpu(sup->leb_size));
- printk(KERN_DEBUG "\tleb_cnt %u\n",
+ printk(KERN_ERR "\tleb_cnt %u\n",
le32_to_cpu(sup->leb_cnt));
- printk(KERN_DEBUG "\tmax_leb_cnt %u\n",
+ printk(KERN_ERR "\tmax_leb_cnt %u\n",
le32_to_cpu(sup->max_leb_cnt));
- printk(KERN_DEBUG "\tmax_bud_bytes %llu\n",
+ printk(KERN_ERR "\tmax_bud_bytes %llu\n",
(unsigned long long)le64_to_cpu(sup->max_bud_bytes));
- printk(KERN_DEBUG "\tlog_lebs %u\n",
+ printk(KERN_ERR "\tlog_lebs %u\n",
le32_to_cpu(sup->log_lebs));
- printk(KERN_DEBUG "\tlpt_lebs %u\n",
+ printk(KERN_ERR "\tlpt_lebs %u\n",
le32_to_cpu(sup->lpt_lebs));
- printk(KERN_DEBUG "\torph_lebs %u\n",
+ printk(KERN_ERR "\torph_lebs %u\n",
le32_to_cpu(sup->orph_lebs));
- printk(KERN_DEBUG "\tjhead_cnt %u\n",
+ printk(KERN_ERR "\tjhead_cnt %u\n",
le32_to_cpu(sup->jhead_cnt));
- printk(KERN_DEBUG "\tfanout %u\n",
+ printk(KERN_ERR "\tfanout %u\n",
le32_to_cpu(sup->fanout));
- printk(KERN_DEBUG "\tlsave_cnt %u\n",
+ printk(KERN_ERR "\tlsave_cnt %u\n",
le32_to_cpu(sup->lsave_cnt));
- printk(KERN_DEBUG "\tdefault_compr %u\n",
+ printk(KERN_ERR "\tdefault_compr %u\n",
(int)le16_to_cpu(sup->default_compr));
- printk(KERN_DEBUG "\trp_size %llu\n",
+ printk(KERN_ERR "\trp_size %llu\n",
(unsigned long long)le64_to_cpu(sup->rp_size));
- printk(KERN_DEBUG "\trp_uid %u\n",
+ printk(KERN_ERR "\trp_uid %u\n",
le32_to_cpu(sup->rp_uid));
- printk(KERN_DEBUG "\trp_gid %u\n",
+ printk(KERN_ERR "\trp_gid %u\n",
le32_to_cpu(sup->rp_gid));
- printk(KERN_DEBUG "\tfmt_version %u\n",
+ printk(KERN_ERR "\tfmt_version %u\n",
le32_to_cpu(sup->fmt_version));
- printk(KERN_DEBUG "\ttime_gran %u\n",
+ printk(KERN_ERR "\ttime_gran %u\n",
le32_to_cpu(sup->time_gran));
- printk(KERN_DEBUG "\tUUID %pUB\n",
+ printk(KERN_ERR "\tUUID %pUB\n",
sup->uuid);
break;
}
@@ -386,61 +386,61 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
{
const struct ubifs_mst_node *mst = node;
- printk(KERN_DEBUG "\thighest_inum %llu\n",
+ printk(KERN_ERR "\thighest_inum %llu\n",
(unsigned long long)le64_to_cpu(mst->highest_inum));
- printk(KERN_DEBUG "\tcommit number %llu\n",
+ printk(KERN_ERR "\tcommit number %llu\n",
(unsigned long long)le64_to_cpu(mst->cmt_no));
- printk(KERN_DEBUG "\tflags %#x\n",
+ printk(KERN_ERR "\tflags %#x\n",
le32_to_cpu(mst->flags));
- printk(KERN_DEBUG "\tlog_lnum %u\n",
+ printk(KERN_ERR "\tlog_lnum %u\n",
le32_to_cpu(mst->log_lnum));
- printk(KERN_DEBUG "\troot_lnum %u\n",
+ printk(KERN_ERR "\troot_lnum %u\n",
le32_to_cpu(mst->root_lnum));
- printk(KERN_DEBUG "\troot_offs %u\n",
+ printk(KERN_ERR "\troot_offs %u\n",
le32_to_cpu(mst->root_offs));
- printk(KERN_DEBUG "\troot_len %u\n",
+ printk(KERN_ERR "\troot_len %u\n",
le32_to_cpu(mst->root_len));
- printk(KERN_DEBUG "\tgc_lnum %u\n",
+ printk(KERN_ERR "\tgc_lnum %u\n",
le32_to_cpu(mst->gc_lnum));
- printk(KERN_DEBUG "\tihead_lnum %u\n",
+ printk(KERN_ERR "\tihead_lnum %u\n",
le32_to_cpu(mst->ihead_lnum));
- printk(KERN_DEBUG "\tihead_offs %u\n",
+ printk(KERN_ERR "\tihead_offs %u\n",
le32_to_cpu(mst->ihead_offs));
- printk(KERN_DEBUG "\tindex_size %llu\n",
+ printk(KERN_ERR "\tindex_size %llu\n",
(unsigned long long)le64_to_cpu(mst->index_size));
- printk(KERN_DEBUG "\tlpt_lnum %u\n",
+ printk(KERN_ERR "\tlpt_lnum %u\n",
le32_to_cpu(mst->lpt_lnum));
- printk(KERN_DEBUG "\tlpt_offs %u\n",
+ printk(KERN_ERR "\tlpt_offs %u\n",
le32_to_cpu(mst->lpt_offs));
- printk(KERN_DEBUG "\tnhead_lnum %u\n",
+ printk(KERN_ERR "\tnhead_lnum %u\n",
le32_to_cpu(mst->nhead_lnum));
- printk(KERN_DEBUG "\tnhead_offs %u\n",
+ printk(KERN_ERR "\tnhead_offs %u\n",
le32_to_cpu(mst->nhead_offs));
- printk(KERN_DEBUG "\tltab_lnum %u\n",
+ printk(KERN_ERR "\tltab_lnum %u\n",
le32_to_cpu(mst->ltab_lnum));
- printk(KERN_DEBUG "\tltab_offs %u\n",
+ printk(KERN_ERR "\tltab_offs %u\n",
le32_to_cpu(mst->ltab_offs));
- printk(KERN_DEBUG "\tlsave_lnum %u\n",
+ printk(KERN_ERR "\tlsave_lnum %u\n",
le32_to_cpu(mst->lsave_lnum));
- printk(KERN_DEBUG "\tlsave_offs %u\n",
+ printk(KERN_ERR "\tlsave_offs %u\n",
le32_to_cpu(mst->lsave_offs));
- printk(KERN_DEBUG "\tlscan_lnum %u\n",
+ printk(KERN_ERR "\tlscan_lnum %u\n",
le32_to_cpu(mst->lscan_lnum));
- printk(KERN_DEBUG "\tleb_cnt %u\n",
+ printk(KERN_ERR "\tleb_cnt %u\n",
le32_to_cpu(mst->leb_cnt));
- printk(KERN_DEBUG "\tempty_lebs %u\n",
+ printk(KERN_ERR "\tempty_lebs %u\n",
le32_to_cpu(mst->empty_lebs));
- printk(KERN_DEBUG "\tidx_lebs %u\n",
+ printk(KERN_ERR "\tidx_lebs %u\n",
le32_to_cpu(mst->idx_lebs));
- printk(KERN_DEBUG "\ttotal_free %llu\n",
+ printk(KERN_ERR "\ttotal_free %llu\n",
(unsigned long long)le64_to_cpu(mst->total_free));
- printk(KERN_DEBUG "\ttotal_dirty %llu\n",
+ printk(KERN_ERR "\ttotal_dirty %llu\n",
(unsigned long long)le64_to_cpu(mst->total_dirty));
- printk(KERN_DEBUG "\ttotal_used %llu\n",
+ printk(KERN_ERR "\ttotal_used %llu\n",
(unsigned long long)le64_to_cpu(mst->total_used));
- printk(KERN_DEBUG "\ttotal_dead %llu\n",
+ printk(KERN_ERR "\ttotal_dead %llu\n",
(unsigned long long)le64_to_cpu(mst->total_dead));
- printk(KERN_DEBUG "\ttotal_dark %llu\n",
+ printk(KERN_ERR "\ttotal_dark %llu\n",
(unsigned long long)le64_to_cpu(mst->total_dark));
break;
}
@@ -448,11 +448,11 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
{
const struct ubifs_ref_node *ref = node;
- printk(KERN_DEBUG "\tlnum %u\n",
+ printk(KERN_ERR "\tlnum %u\n",
le32_to_cpu(ref->lnum));
- printk(KERN_DEBUG "\toffs %u\n",
+ printk(KERN_ERR "\toffs %u\n",
le32_to_cpu(ref->offs));
- printk(KERN_DEBUG "\tjhead %u\n",
+ printk(KERN_ERR "\tjhead %u\n",
le32_to_cpu(ref->jhead));
break;
}
@@ -461,40 +461,40 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
const struct ubifs_ino_node *ino = node;
key_read(c, &ino->key, &key);
- printk(KERN_DEBUG "\tkey %s\n",
+ printk(KERN_ERR "\tkey %s\n",
dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
- printk(KERN_DEBUG "\tcreat_sqnum %llu\n",
+ printk(KERN_ERR "\tcreat_sqnum %llu\n",
(unsigned long long)le64_to_cpu(ino->creat_sqnum));
- printk(KERN_DEBUG "\tsize %llu\n",
+ printk(KERN_ERR "\tsize %llu\n",
(unsigned long long)le64_to_cpu(ino->size));
- printk(KERN_DEBUG "\tnlink %u\n",
+ printk(KERN_ERR "\tnlink %u\n",
le32_to_cpu(ino->nlink));
- printk(KERN_DEBUG "\tatime %lld.%u\n",
+ printk(KERN_ERR "\tatime %lld.%u\n",
(long long)le64_to_cpu(ino->atime_sec),
le32_to_cpu(ino->atime_nsec));
- printk(KERN_DEBUG "\tmtime %lld.%u\n",
+ printk(KERN_ERR "\tmtime %lld.%u\n",
(long long)le64_to_cpu(ino->mtime_sec),
le32_to_cpu(ino->mtime_nsec));
- printk(KERN_DEBUG "\tctime %lld.%u\n",
+ printk(KERN_ERR "\tctime %lld.%u\n",
(long long)le64_to_cpu(ino->ctime_sec),
le32_to_cpu(ino->ctime_nsec));
- printk(KERN_DEBUG "\tuid %u\n",
+ printk(KERN_ERR "\tuid %u\n",
le32_to_cpu(ino->uid));
- printk(KERN_DEBUG "\tgid %u\n",
+ printk(KERN_ERR "\tgid %u\n",
le32_to_cpu(ino->gid));
- printk(KERN_DEBUG "\tmode %u\n",
+ printk(KERN_ERR "\tmode %u\n",
le32_to_cpu(ino->mode));
- printk(KERN_DEBUG "\tflags %#x\n",
+ printk(KERN_ERR "\tflags %#x\n",
le32_to_cpu(ino->flags));
- printk(KERN_DEBUG "\txattr_cnt %u\n",
+ printk(KERN_ERR "\txattr_cnt %u\n",
le32_to_cpu(ino->xattr_cnt));
- printk(KERN_DEBUG "\txattr_size %u\n",
+ printk(KERN_ERR "\txattr_size %u\n",
le32_to_cpu(ino->xattr_size));
- printk(KERN_DEBUG "\txattr_names %u\n",
+ printk(KERN_ERR "\txattr_names %u\n",
le32_to_cpu(ino->xattr_names));
- printk(KERN_DEBUG "\tcompr_type %#x\n",
+ printk(KERN_ERR "\tcompr_type %#x\n",
(int)le16_to_cpu(ino->compr_type));
- printk(KERN_DEBUG "\tdata len %u\n",
+ printk(KERN_ERR "\tdata len %u\n",
le32_to_cpu(ino->data_len));
break;
}
@@ -505,16 +505,16 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
int nlen = le16_to_cpu(dent->nlen);
key_read(c, &dent->key, &key);
- printk(KERN_DEBUG "\tkey %s\n",
+ printk(KERN_ERR "\tkey %s\n",
dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
- printk(KERN_DEBUG "\tinum %llu\n",
+ printk(KERN_ERR "\tinum %llu\n",
(unsigned long long)le64_to_cpu(dent->inum));
- printk(KERN_DEBUG "\ttype %d\n", (int)dent->type);
- printk(KERN_DEBUG "\tnlen %d\n", nlen);
- printk(KERN_DEBUG "\tname ");
+ printk(KERN_ERR "\ttype %d\n", (int)dent->type);
+ printk(KERN_ERR "\tnlen %d\n", nlen);
+ printk(KERN_ERR "\tname ");
if (nlen > UBIFS_MAX_NLEN)
- printk(KERN_DEBUG "(bad name length, not printing, "
+ printk(KERN_ERR "(bad name length, not printing, "
"bad or corrupted node)");
else {
for (i = 0; i < nlen && dent->name[i]; i++)
@@ -530,16 +530,16 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
int dlen = le32_to_cpu(ch->len) - UBIFS_DATA_NODE_SZ;
key_read(c, &dn->key, &key);
- printk(KERN_DEBUG "\tkey %s\n",
+ printk(KERN_ERR "\tkey %s\n",
dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
- printk(KERN_DEBUG "\tsize %u\n",
+ printk(KERN_ERR "\tsize %u\n",
le32_to_cpu(dn->size));
- printk(KERN_DEBUG "\tcompr_typ %d\n",
+ printk(KERN_ERR "\tcompr_typ %d\n",
(int)le16_to_cpu(dn->compr_type));
- printk(KERN_DEBUG "\tdata size %d\n",
+ printk(KERN_ERR "\tdata size %d\n",
dlen);
- printk(KERN_DEBUG "\tdata:\n");
- print_hex_dump(KERN_DEBUG, "\t", DUMP_PREFIX_OFFSET, 32, 1,
+ printk(KERN_ERR "\tdata:\n");
+ print_hex_dump(KERN_ERR, "\t", DUMP_PREFIX_OFFSET, 32, 1,
(void *)&dn->data, dlen, 0);
break;
}
@@ -547,11 +547,11 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
{
const struct ubifs_trun_node *trun = node;
- printk(KERN_DEBUG "\tinum %u\n",
+ printk(KERN_ERR "\tinum %u\n",
le32_to_cpu(trun->inum));
- printk(KERN_DEBUG "\told_size %llu\n",
+ printk(KERN_ERR "\told_size %llu\n",
(unsigned long long)le64_to_cpu(trun->old_size));
- printk(KERN_DEBUG "\tnew_size %llu\n",
+ printk(KERN_ERR "\tnew_size %llu\n",
(unsigned long long)le64_to_cpu(trun->new_size));
break;
}
@@ -560,17 +560,17 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
const struct ubifs_idx_node *idx = node;
n = le16_to_cpu(idx->child_cnt);
- printk(KERN_DEBUG "\tchild_cnt %d\n", n);
- printk(KERN_DEBUG "\tlevel %d\n",
+ printk(KERN_ERR "\tchild_cnt %d\n", n);
+ printk(KERN_ERR "\tlevel %d\n",
(int)le16_to_cpu(idx->level));
- printk(KERN_DEBUG "\tBranches:\n");
+ printk(KERN_ERR "\tBranches:\n");
for (i = 0; i < n && i < c->fanout - 1; i++) {
const struct ubifs_branch *br;
br = ubifs_idx_branch(c, idx, i);
key_read(c, &br->key, &key);
- printk(KERN_DEBUG "\t%d: LEB %d:%d len %d key %s\n",
+ printk(KERN_ERR "\t%d: LEB %d:%d len %d key %s\n",
i, le32_to_cpu(br->lnum), le32_to_cpu(br->offs),
le32_to_cpu(br->len),
dbg_snprintf_key(c, &key, key_buf,
@@ -584,20 +584,20 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
{
const struct ubifs_orph_node *orph = node;
- printk(KERN_DEBUG "\tcommit number %llu\n",
+ printk(KERN_ERR "\tcommit number %llu\n",
(unsigned long long)
le64_to_cpu(orph->cmt_no) & LLONG_MAX);
- printk(KERN_DEBUG "\tlast node flag %llu\n",
+ printk(KERN_ERR "\tlast node flag %llu\n",
(unsigned long long)(le64_to_cpu(orph->cmt_no)) >> 63);
n = (le32_to_cpu(ch->len) - UBIFS_ORPH_NODE_SZ) >> 3;
- printk(KERN_DEBUG "\t%d orphan inode numbers:\n", n);
+ printk(KERN_ERR "\t%d orphan inode numbers:\n", n);
for (i = 0; i < n; i++)
- printk(KERN_DEBUG "\t ino %llu\n",
+ printk(KERN_ERR "\t ino %llu\n",
(unsigned long long)le64_to_cpu(orph->inos[i]));
break;
}
default:
- printk(KERN_DEBUG "node type %d was not recognized\n",
+ printk(KERN_ERR "node type %d was not recognized\n",
(int)ch->node_type);
}
spin_unlock(&dbg_lock);
@@ -606,16 +606,16 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
void dbg_dump_budget_req(const struct ubifs_budget_req *req)
{
spin_lock(&dbg_lock);
- printk(KERN_DEBUG "Budgeting request: new_ino %d, dirtied_ino %d\n",
+ printk(KERN_ERR "Budgeting request: new_ino %d, dirtied_ino %d\n",
req->new_ino, req->dirtied_ino);
- printk(KERN_DEBUG "\tnew_ino_d %d, dirtied_ino_d %d\n",
+ printk(KERN_ERR "\tnew_ino_d %d, dirtied_ino_d %d\n",
req->new_ino_d, req->dirtied_ino_d);
- printk(KERN_DEBUG "\tnew_page %d, dirtied_page %d\n",
+ printk(KERN_ERR "\tnew_page %d, dirtied_page %d\n",
req->new_page, req->dirtied_page);
- printk(KERN_DEBUG "\tnew_dent %d, mod_dent %d\n",
+ printk(KERN_ERR "\tnew_dent %d, mod_dent %d\n",
req->new_dent, req->mod_dent);
- printk(KERN_DEBUG "\tidx_growth %d\n", req->idx_growth);
- printk(KERN_DEBUG "\tdata_growth %d dd_growth %d\n",
+ printk(KERN_ERR "\tidx_growth %d\n", req->idx_growth);
+ printk(KERN_ERR "\tdata_growth %d dd_growth %d\n",
req->data_growth, req->dd_growth);
spin_unlock(&dbg_lock);
}
@@ -623,12 +623,12 @@ void dbg_dump_budget_req(const struct ubifs_budget_req *req)
void dbg_dump_lstats(const struct ubifs_lp_stats *lst)
{
spin_lock(&dbg_lock);
- printk(KERN_DEBUG "(pid %d) Lprops statistics: empty_lebs %d, "
+ printk(KERN_ERR "(pid %d) Lprops statistics: empty_lebs %d, "
"idx_lebs %d\n", current->pid, lst->empty_lebs, lst->idx_lebs);
- printk(KERN_DEBUG "\ttaken_empty_lebs %d, total_free %lld, "
+ printk(KERN_ERR "\ttaken_empty_lebs %d, total_free %lld, "
"total_dirty %lld\n", lst->taken_empty_lebs, lst->total_free,
lst->total_dirty);
- printk(KERN_DEBUG "\ttotal_used %lld, total_dark %lld, "
+ printk(KERN_ERR "\ttotal_used %lld, total_dark %lld, "
"total_dead %lld\n", lst->total_used, lst->total_dark,
lst->total_dead);
spin_unlock(&dbg_lock);
@@ -644,21 +644,21 @@ void dbg_dump_budg(struct ubifs_info *c, const struct ubifs_budg_info *bi)
spin_lock(&c->space_lock);
spin_lock(&dbg_lock);
- printk(KERN_DEBUG "(pid %d) Budgeting info: data budget sum %lld, "
+ printk(KERN_ERR "(pid %d) Budgeting info: data budget sum %lld, "
"total budget sum %lld\n", current->pid,
bi->data_growth + bi->dd_growth,
bi->data_growth + bi->dd_growth + bi->idx_growth);
- printk(KERN_DEBUG "\tbudg_data_growth %lld, budg_dd_growth %lld, "
+ printk(KERN_ERR "\tbudg_data_growth %lld, budg_dd_growth %lld, "
"budg_idx_growth %lld\n", bi->data_growth, bi->dd_growth,
bi->idx_growth);
- printk(KERN_DEBUG "\tmin_idx_lebs %d, old_idx_sz %llu, "
+ printk(KERN_ERR "\tmin_idx_lebs %d, old_idx_sz %llu, "
"uncommitted_idx %lld\n", bi->min_idx_lebs, bi->old_idx_sz,
bi->uncommitted_idx);
- printk(KERN_DEBUG "\tpage_budget %d, inode_budget %d, dent_budget %d\n",
+ printk(KERN_ERR "\tpage_budget %d, inode_budget %d, dent_budget %d\n",
bi->page_budget, bi->inode_budget, bi->dent_budget);
- printk(KERN_DEBUG "\tnospace %u, nospace_rp %u\n",
+ printk(KERN_ERR "\tnospace %u, nospace_rp %u\n",
bi->nospace, bi->nospace_rp);
- printk(KERN_DEBUG "\tdark_wm %d, dead_wm %d, max_idx_node_sz %d\n",
+ printk(KERN_ERR "\tdark_wm %d, dead_wm %d, max_idx_node_sz %d\n",
c->dark_wm, c->dead_wm, c->max_idx_node_sz);
if (bi != &c->bi)
@@ -669,38 +669,38 @@ void dbg_dump_budg(struct ubifs_info *c, const struct ubifs_budg_info *bi)
*/
goto out_unlock;
- printk(KERN_DEBUG "\tfreeable_cnt %d, calc_idx_sz %lld, idx_gc_cnt %d\n",
+ printk(KERN_ERR "\tfreeable_cnt %d, calc_idx_sz %lld, idx_gc_cnt %d\n",
c->freeable_cnt, c->calc_idx_sz, c->idx_gc_cnt);
- printk(KERN_DEBUG "\tdirty_pg_cnt %ld, dirty_zn_cnt %ld, "
+ printk(KERN_ERR "\tdirty_pg_cnt %ld, dirty_zn_cnt %ld, "
"clean_zn_cnt %ld\n", atomic_long_read(&c->dirty_pg_cnt),
atomic_long_read(&c->dirty_zn_cnt),
atomic_long_read(&c->clean_zn_cnt));
- printk(KERN_DEBUG "\tgc_lnum %d, ihead_lnum %d\n",
+ printk(KERN_ERR "\tgc_lnum %d, ihead_lnum %d\n",
c->gc_lnum, c->ihead_lnum);
/* If we are in R/O mode, journal heads do not exist */
if (c->jheads)
for (i = 0; i < c->jhead_cnt; i++)
- printk(KERN_DEBUG "\tjhead %s\t LEB %d\n",
+ printk(KERN_ERR "\tjhead %s\t LEB %d\n",
dbg_jhead(c->jheads[i].wbuf.jhead),
c->jheads[i].wbuf.lnum);
for (rb = rb_first(&c->buds); rb; rb = rb_next(rb)) {
bud = rb_entry(rb, struct ubifs_bud, rb);
- printk(KERN_DEBUG "\tbud LEB %d\n", bud->lnum);
+ printk(KERN_ERR "\tbud LEB %d\n", bud->lnum);
}
list_for_each_entry(bud, &c->old_buds, list)
- printk(KERN_DEBUG "\told bud LEB %d\n", bud->lnum);
+ printk(KERN_ERR "\told bud LEB %d\n", bud->lnum);
list_for_each_entry(idx_gc, &c->idx_gc, list)
- printk(KERN_DEBUG "\tGC'ed idx LEB %d unmap %d\n",
+ printk(KERN_ERR "\tGC'ed idx LEB %d unmap %d\n",
idx_gc->lnum, idx_gc->unmap);
- printk(KERN_DEBUG "\tcommit state %d\n", c->cmt_state);
+ printk(KERN_ERR "\tcommit state %d\n", c->cmt_state);
/* Print budgeting predictions */
available = ubifs_calc_available(c, c->bi.min_idx_lebs);
outstanding = c->bi.data_growth + c->bi.dd_growth;
free = ubifs_get_free_space_nolock(c);
- printk(KERN_DEBUG "Budgeting predictions:\n");
- printk(KERN_DEBUG "\tavailable: %lld, outstanding %lld, free %lld\n",
+ printk(KERN_ERR "Budgeting predictions:\n");
+ printk(KERN_ERR "\tavailable: %lld, outstanding %lld, free %lld\n",
available, outstanding, free);
out_unlock:
spin_unlock(&dbg_lock);
@@ -720,11 +720,11 @@ void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp)
dark = ubifs_calc_dark(c, spc);
if (lp->flags & LPROPS_INDEX)
- printk(KERN_DEBUG "LEB %-7d free %-8d dirty %-8d used %-8d "
+ printk(KERN_ERR "LEB %-7d free %-8d dirty %-8d used %-8d "
"free + dirty %-8d flags %#x (", lp->lnum, lp->free,
lp->dirty, c->leb_size - spc, spc, lp->flags);
else
- printk(KERN_DEBUG "LEB %-7d free %-8d dirty %-8d used %-8d "
+ printk(KERN_ERR "LEB %-7d free %-8d dirty %-8d used %-8d "
"free + dirty %-8d dark %-4d dead %-4d nodes fit %-3d "
"flags %#-4x (", lp->lnum, lp->free, lp->dirty,
c->leb_size - spc, spc, dark, dead,
@@ -807,7 +807,7 @@ void dbg_dump_lprops(struct ubifs_info *c)
struct ubifs_lprops lp;
struct ubifs_lp_stats lst;
- printk(KERN_DEBUG "(pid %d) start dumping LEB properties\n",
+ printk(KERN_ERR "(pid %d) start dumping LEB properties\n",
current->pid);
ubifs_get_lp_stats(c, &lst);
dbg_dump_lstats(&lst);
@@ -819,7 +819,7 @@ void dbg_dump_lprops(struct ubifs_info *c)
dbg_dump_lprop(c, &lp);
}
- printk(KERN_DEBUG "(pid %d) finish dumping LEB properties\n",
+ printk(KERN_ERR "(pid %d) finish dumping LEB properties\n",
current->pid);
}
@@ -828,35 +828,35 @@ void dbg_dump_lpt_info(struct ubifs_info *c)
int i;
spin_lock(&dbg_lock);
- printk(KERN_DEBUG "(pid %d) dumping LPT information\n", current->pid);
- printk(KERN_DEBUG "\tlpt_sz: %lld\n", c->lpt_sz);
- printk(KERN_DEBUG "\tpnode_sz: %d\n", c->pnode_sz);
- printk(KERN_DEBUG "\tnnode_sz: %d\n", c->nnode_sz);
- printk(KERN_DEBUG "\tltab_sz: %d\n", c->ltab_sz);
- printk(KERN_DEBUG "\tlsave_sz: %d\n", c->lsave_sz);
- printk(KERN_DEBUG "\tbig_lpt: %d\n", c->big_lpt);
- printk(KERN_DEBUG "\tlpt_hght: %d\n", c->lpt_hght);
- printk(KERN_DEBUG "\tpnode_cnt: %d\n", c->pnode_cnt);
- printk(KERN_DEBUG "\tnnode_cnt: %d\n", c->nnode_cnt);
- printk(KERN_DEBUG "\tdirty_pn_cnt: %d\n", c->dirty_pn_cnt);
- printk(KERN_DEBUG "\tdirty_nn_cnt: %d\n", c->dirty_nn_cnt);
- printk(KERN_DEBUG "\tlsave_cnt: %d\n", c->lsave_cnt);
- printk(KERN_DEBUG "\tspace_bits: %d\n", c->space_bits);
- printk(KERN_DEBUG "\tlpt_lnum_bits: %d\n", c->lpt_lnum_bits);
- printk(KERN_DEBUG "\tlpt_offs_bits: %d\n", c->lpt_offs_bits);
- printk(KERN_DEBUG "\tlpt_spc_bits: %d\n", c->lpt_spc_bits);
- printk(KERN_DEBUG "\tpcnt_bits: %d\n", c->pcnt_bits);
- printk(KERN_DEBUG "\tlnum_bits: %d\n", c->lnum_bits);
- printk(KERN_DEBUG "\tLPT root is at %d:%d\n", c->lpt_lnum, c->lpt_offs);
- printk(KERN_DEBUG "\tLPT head is at %d:%d\n",
+ printk(KERN_ERR "(pid %d) dumping LPT information\n", current->pid);
+ printk(KERN_ERR "\tlpt_sz: %lld\n", c->lpt_sz);
+ printk(KERN_ERR "\tpnode_sz: %d\n", c->pnode_sz);
+ printk(KERN_ERR "\tnnode_sz: %d\n", c->nnode_sz);
+ printk(KERN_ERR "\tltab_sz: %d\n", c->ltab_sz);
+ printk(KERN_ERR "\tlsave_sz: %d\n", c->lsave_sz);
+ printk(KERN_ERR "\tbig_lpt: %d\n", c->big_lpt);
+ printk(KERN_ERR "\tlpt_hght: %d\n", c->lpt_hght);
+ printk(KERN_ERR "\tpnode_cnt: %d\n", c->pnode_cnt);
+ printk(KERN_ERR "\tnnode_cnt: %d\n", c->nnode_cnt);
+ printk(KERN_ERR "\tdirty_pn_cnt: %d\n", c->dirty_pn_cnt);
+ printk(KERN_ERR "\tdirty_nn_cnt: %d\n", c->dirty_nn_cnt);
+ printk(KERN_ERR "\tlsave_cnt: %d\n", c->lsave_cnt);
+ printk(KERN_ERR "\tspace_bits: %d\n", c->space_bits);
+ printk(KERN_ERR "\tlpt_lnum_bits: %d\n", c->lpt_lnum_bits);
+ printk(KERN_ERR "\tlpt_offs_bits: %d\n", c->lpt_offs_bits);
+ printk(KERN_ERR "\tlpt_spc_bits: %d\n", c->lpt_spc_bits);
+ printk(KERN_ERR "\tpcnt_bits: %d\n", c->pcnt_bits);
+ printk(KERN_ERR "\tlnum_bits: %d\n", c->lnum_bits);
+ printk(KERN_ERR "\tLPT root is at %d:%d\n", c->lpt_lnum, c->lpt_offs);
+ printk(KERN_ERR "\tLPT head is at %d:%d\n",
c->nhead_lnum, c->nhead_offs);
- printk(KERN_DEBUG "\tLPT ltab is at %d:%d\n",
+ printk(KERN_ERR "\tLPT ltab is at %d:%d\n",
c->ltab_lnum, c->ltab_offs);
if (c->big_lpt)
- printk(KERN_DEBUG "\tLPT lsave is at %d:%d\n",
+ printk(KERN_ERR "\tLPT lsave is at %d:%d\n",
c->lsave_lnum, c->lsave_offs);
for (i = 0; i < c->lpt_lebs; i++)
- printk(KERN_DEBUG "\tLPT LEB %d free %d dirty %d tgc %d "
+ printk(KERN_ERR "\tLPT LEB %d free %d dirty %d tgc %d "
"cmt %d\n", i + c->lpt_first, c->ltab[i].free,
c->ltab[i].dirty, c->ltab[i].tgc, c->ltab[i].cmt);
spin_unlock(&dbg_lock);
@@ -867,12 +867,12 @@ void dbg_dump_sleb(const struct ubifs_info *c,
{
struct ubifs_scan_node *snod;
- printk(KERN_DEBUG "(pid %d) start dumping scanned data from LEB %d:%d\n",
+ printk(KERN_ERR "(pid %d) start dumping scanned data from LEB %d:%d\n",
current->pid, sleb->lnum, offs);
list_for_each_entry(snod, &sleb->nodes, list) {
cond_resched();
- printk(KERN_DEBUG "Dumping node at LEB %d:%d len %d\n", sleb->lnum,
+ printk(KERN_ERR "Dumping node at LEB %d:%d len %d\n", sleb->lnum,
snod->offs, snod->len);
dbg_dump_node(c, snod->node);
}
@@ -887,7 +887,7 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum)
if (dbg_is_tst_rcvry(c))
return;
- printk(KERN_DEBUG "(pid %d) start dumping LEB %d\n",
+ printk(KERN_ERR "(pid %d) start dumping LEB %d\n",
current->pid, lnum);
buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
@@ -902,17 +902,17 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum)
goto out;
}
- printk(KERN_DEBUG "LEB %d has %d nodes ending at %d\n", lnum,
+ printk(KERN_ERR "LEB %d has %d nodes ending at %d\n", lnum,
sleb->nodes_cnt, sleb->endpt);
list_for_each_entry(snod, &sleb->nodes, list) {
cond_resched();
- printk(KERN_DEBUG "Dumping node at LEB %d:%d len %d\n", lnum,
+ printk(KERN_ERR "Dumping node at LEB %d:%d len %d\n", lnum,
snod->offs, snod->len);
dbg_dump_node(c, snod->node);
}
- printk(KERN_DEBUG "(pid %d) finish dumping LEB %d\n",
+ printk(KERN_ERR "(pid %d) finish dumping LEB %d\n",
current->pid, lnum);
ubifs_scan_destroy(sleb);
@@ -934,7 +934,7 @@ void dbg_dump_znode(const struct ubifs_info *c,
else
zbr = &c->zroot;
- printk(KERN_DEBUG "znode %p, LEB %d:%d len %d parent %p iip %d level %d"
+ printk(KERN_ERR "znode %p, LEB %d:%d len %d parent %p iip %d level %d"
" child_cnt %d flags %lx\n", znode, zbr->lnum, zbr->offs,
zbr->len, znode->parent, znode->iip, znode->level,
znode->child_cnt, znode->flags);
@@ -944,18 +944,18 @@ void dbg_dump_znode(const struct ubifs_info *c,
return;
}
- printk(KERN_DEBUG "zbranches:\n");
+ printk(KERN_ERR "zbranches:\n");
for (n = 0; n < znode->child_cnt; n++) {
zbr = &znode->zbranch[n];
if (znode->level > 0)
- printk(KERN_DEBUG "\t%d: znode %p LEB %d:%d len %d key "
+ printk(KERN_ERR "\t%d: znode %p LEB %d:%d len %d key "
"%s\n", n, zbr->znode, zbr->lnum,
zbr->offs, zbr->len,
dbg_snprintf_key(c, &zbr->key,
key_buf,
DBG_KEY_BUF_LEN));
else
- printk(KERN_DEBUG "\t%d: LNC %p LEB %d:%d len %d key "
+ printk(KERN_ERR "\t%d: LNC %p LEB %d:%d len %d key "
"%s\n", n, zbr->znode, zbr->lnum,
zbr->offs, zbr->len,
dbg_snprintf_key(c, &zbr->key,
@@ -969,16 +969,16 @@ void dbg_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat)
{
int i;
- printk(KERN_DEBUG "(pid %d) start dumping heap cat %d (%d elements)\n",
+ printk(KERN_ERR "(pid %d) start dumping heap cat %d (%d elements)\n",
current->pid, cat, heap->cnt);
for (i = 0; i < heap->cnt; i++) {
struct ubifs_lprops *lprops = heap->arr[i];
- printk(KERN_DEBUG "\t%d. LEB %d hpos %d free %d dirty %d "
+ printk(KERN_ERR "\t%d. LEB %d hpos %d free %d dirty %d "
"flags %d\n", i, lprops->lnum, lprops->hpos,
lprops->free, lprops->dirty, lprops->flags);
}
- printk(KERN_DEBUG "(pid %d) finish dumping heap\n", current->pid);
+ printk(KERN_ERR "(pid %d) finish dumping heap\n", current->pid);
}
void dbg_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode,
@@ -986,15 +986,15 @@ void dbg_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode,
{
int i;
- printk(KERN_DEBUG "(pid %d) dumping pnode:\n", current->pid);
- printk(KERN_DEBUG "\taddress %zx parent %zx cnext %zx\n",
+ printk(KERN_ERR "(pid %d) dumping pnode:\n", current->pid);
+ printk(KERN_ERR "\taddress %zx parent %zx cnext %zx\n",
(size_t)pnode, (size_t)parent, (size_t)pnode->cnext);
- printk(KERN_DEBUG "\tflags %lu iip %d level %d num %d\n",
+ printk(KERN_ERR "\tflags %lu iip %d level %d num %d\n",
pnode->flags, iip, pnode->level, pnode->num);
for (i = 0; i < UBIFS_LPT_FANOUT; i++) {
struct ubifs_lprops *lp = &pnode->lprops[i];
- printk(KERN_DEBUG "\t%d: free %d dirty %d flags %d lnum %d\n",
+ printk(KERN_ERR "\t%d: free %d dirty %d flags %d lnum %d\n",
i, lp->free, lp->dirty, lp->flags, lp->lnum);
}
}
@@ -1004,20 +1004,20 @@ void dbg_dump_tnc(struct ubifs_info *c)
struct ubifs_znode *znode;
int level;
- printk(KERN_DEBUG "\n");
- printk(KERN_DEBUG "(pid %d) start dumping TNC tree\n", current->pid);
+ printk(KERN_ERR "\n");
+ printk(KERN_ERR "(pid %d) start dumping TNC tree\n", current->pid);
znode = ubifs_tnc_levelorder_next(c->zroot.znode, NULL);
level = znode->level;
- printk(KERN_DEBUG "== Level %d ==\n", level);
+ printk(KERN_ERR "== Level %d ==\n", level);
while (znode) {
if (level != znode->level) {
level = znode->level;
- printk(KERN_DEBUG "== Level %d ==\n", level);
+ printk(KERN_ERR "== Level %d ==\n", level);
}
dbg_dump_znode(c, znode);
znode = ubifs_tnc_levelorder_next(c->zroot.znode, znode);
}
- printk(KERN_DEBUG "(pid %d) finish dumping TNC tree\n", current->pid);
+ printk(KERN_ERR "(pid %d) finish dumping TNC tree\n", current->pid);
}
static int dump_znode(struct ubifs_info *c, struct ubifs_znode *znode,
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index ad1a6fe..9f71765 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -164,9 +164,7 @@ struct ubifs_global_debug_info {
#define dbg_dump_stack() dump_stack()
#define dbg_err(fmt, ...) do { \
- spin_lock(&dbg_lock); \
ubifs_err(fmt, ##__VA_ARGS__); \
- spin_unlock(&dbg_lock); \
} while (0)
#define ubifs_dbg_msg(type, fmt, ...) \
@@ -217,7 +215,6 @@ struct ubifs_global_debug_info {
/* Additional recovery messages */
#define dbg_rcvry(fmt, ...) ubifs_dbg_msg("rcvry", fmt, ##__VA_ARGS__)
-extern spinlock_t dbg_lock;
extern struct ubifs_global_debug_info ubifs_dbg;
static inline int dbg_is_chk_gen(const struct ubifs_info *c)
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index d6fe1c7..ec9f187 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -566,6 +566,7 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry)
int sz_change = CALC_DENT_SIZE(dentry->d_name.len);
int err, budgeted = 1;
struct ubifs_budget_req req = { .mod_dent = 1, .dirtied_ino = 2 };
+ unsigned int saved_nlink = inode->i_nlink;
/*
* Budget request settings: deletion direntry, deletion inode (+1 for
@@ -613,7 +614,7 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry)
out_cancel:
dir->i_size += sz_change;
dir_ui->ui_size = dir->i_size;
- inc_nlink(inode);
+ set_nlink(inode, saved_nlink);
unlock_2_inodes(dir, inode);
if (budgeted)
ubifs_release_budget(c, &req);
@@ -704,8 +705,7 @@ out_cancel:
dir->i_size += sz_change;
dir_ui->ui_size = dir->i_size;
inc_nlink(dir);
- inc_nlink(inode);
- inc_nlink(inode);
+ set_nlink(inode, 2);
unlock_2_inodes(dir, inode);
if (budgeted)
ubifs_release_budget(c, &req);
@@ -977,6 +977,7 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct ubifs_budget_req ino_req = { .dirtied_ino = 1,
.dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
struct timespec time;
+ unsigned int saved_nlink;
/*
* Budget request settings: deletion direntry, new direntry, removing
@@ -1059,13 +1060,14 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (unlink) {
/*
* Directories cannot have hard-links, so if this is a
- * directory, decrement its @i_nlink twice because an empty
- * directory has @i_nlink 2.
+ * directory, just clear @i_nlink.
*/
+ saved_nlink = new_inode->i_nlink;
if (is_dir)
+ clear_nlink(new_inode);
+ else
drop_nlink(new_inode);
new_inode->i_ctime = time;
- drop_nlink(new_inode);
} else {
new_dir->i_size += new_sz;
ubifs_inode(new_dir)->ui_size = new_dir->i_size;
@@ -1102,9 +1104,7 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
out_cancel:
if (unlink) {
- if (is_dir)
- inc_nlink(new_inode);
- inc_nlink(new_inode);
+ set_nlink(new_inode, saved_nlink);
} else {
new_dir->i_size -= new_sz;
ubifs_inode(new_dir)->ui_size = new_dir->i_size;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index f9c234b..5c8f6dc 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1042,10 +1042,10 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc)
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memset(kaddr + len, 0, PAGE_CACHE_SIZE - len);
flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
if (i_size > synced_i_size) {
err = inode->i_sb->s_op->write_inode(inode, NULL);
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index ee4f43f..2a935b3 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -679,7 +679,8 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
ret == SCANNED_GARBAGE ||
ret == SCANNED_A_BAD_PAD_NODE ||
ret == SCANNED_A_CORRUPT_NODE) {
- dbg_rcvry("found corruption - %d", ret);
+ dbg_rcvry("found corruption (%d) at %d:%d",
+ ret, lnum, offs);
break;
} else {
dbg_err("unexpected return value %d", ret);
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 6094c5a..771f7fb 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -410,13 +410,23 @@ static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup)
}
if (c->main_lebs < UBIFS_MIN_MAIN_LEBS) {
- err = 7;
+ ubifs_err("too few main LEBs count %d, must be at least %d",
+ c->main_lebs, UBIFS_MIN_MAIN_LEBS);
goto failed;
}
- if (c->max_bud_bytes < (long long)c->leb_size * UBIFS_MIN_BUD_LEBS ||
- c->max_bud_bytes > (long long)c->leb_size * c->main_lebs) {
- err = 8;
+ max_bytes = (long long)c->leb_size * UBIFS_MIN_BUD_LEBS;
+ if (c->max_bud_bytes < max_bytes) {
+ ubifs_err("too small journal (%lld bytes), must be at least "
+ "%lld bytes", c->max_bud_bytes, max_bytes);
+ goto failed;
+ }
+
+ max_bytes = (long long)c->leb_size * c->main_lebs;
+ if (c->max_bud_bytes > max_bytes) {
+ ubifs_err("too large journal size (%lld bytes), only %lld bytes"
+ "available in the main area",
+ c->max_bud_bytes, max_bytes);
goto failed;
}
@@ -450,7 +460,6 @@ static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup)
goto failed;
}
- max_bytes = c->main_lebs * (long long)c->leb_size;
if (c->rp_size < 0 || max_bytes < c->rp_size) {
err = 14;
goto failed;
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 63765d5..76e4e05 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2076,15 +2076,13 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
goto out_umount;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root)
- goto out_iput;
+ goto out_umount;
mutex_unlock(&c->umount_mutex);
return 0;
-out_iput:
- iput(root);
out_umount:
ubifs_umount(c);
out_unlock:
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 12e9477..93d59ac 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -84,9 +84,6 @@
#define INUM_WARN_WATERMARK 0xFFF00000
#define INUM_WATERMARK 0xFFFFFF00
-/* Largest key size supported in this implementation */
-#define CUR_MAX_KEY_LEN UBIFS_SK_LEN
-
/* Maximum number of entries in each LPT (LEB category) heap */
#define LPT_HEAP_SZ 256
@@ -277,10 +274,10 @@ struct ubifs_old_idx {
/* The below union makes it easier to deal with keys */
union ubifs_key {
- uint8_t u8[CUR_MAX_KEY_LEN];
- uint32_t u32[CUR_MAX_KEY_LEN/4];
- uint64_t u64[CUR_MAX_KEY_LEN/8];
- __le32 j32[CUR_MAX_KEY_LEN/4];
+ uint8_t u8[UBIFS_SK_LEN];
+ uint32_t u32[UBIFS_SK_LEN/4];
+ uint64_t u64[UBIFS_SK_LEN/8];
+ __le32 j32[UBIFS_SK_LEN/4];
};
/**
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 987585b..1ba2baa 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -105,7 +105,6 @@ static void udf_add_free_space(struct super_block *sb, u16 partition, u32 cnt)
}
static void udf_bitmap_free_blocks(struct super_block *sb,
- struct inode *inode,
struct udf_bitmap *bitmap,
struct kernel_lb_addr *bloc,
uint32_t offset,
@@ -172,7 +171,6 @@ error_return:
}
static int udf_bitmap_prealloc_blocks(struct super_block *sb,
- struct inode *inode,
struct udf_bitmap *bitmap,
uint16_t partition, uint32_t first_block,
uint32_t block_count)
@@ -223,7 +221,6 @@ out:
}
static int udf_bitmap_new_block(struct super_block *sb,
- struct inode *inode,
struct udf_bitmap *bitmap, uint16_t partition,
uint32_t goal, int *err)
{
@@ -349,7 +346,6 @@ error_return:
}
static void udf_table_free_blocks(struct super_block *sb,
- struct inode *inode,
struct inode *table,
struct kernel_lb_addr *bloc,
uint32_t offset,
@@ -581,7 +577,6 @@ error_return:
}
static int udf_table_prealloc_blocks(struct super_block *sb,
- struct inode *inode,
struct inode *table, uint16_t partition,
uint32_t first_block, uint32_t block_count)
{
@@ -643,7 +638,6 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
}
static int udf_table_new_block(struct super_block *sb,
- struct inode *inode,
struct inode *table, uint16_t partition,
uint32_t goal, int *err)
{
@@ -743,18 +737,23 @@ void udf_free_blocks(struct super_block *sb, struct inode *inode,
struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
- udf_bitmap_free_blocks(sb, inode, map->s_uspace.s_bitmap,
+ udf_bitmap_free_blocks(sb, map->s_uspace.s_bitmap,
bloc, offset, count);
} else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE) {
- udf_table_free_blocks(sb, inode, map->s_uspace.s_table,
+ udf_table_free_blocks(sb, map->s_uspace.s_table,
bloc, offset, count);
} else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP) {
- udf_bitmap_free_blocks(sb, inode, map->s_fspace.s_bitmap,
+ udf_bitmap_free_blocks(sb, map->s_fspace.s_bitmap,
bloc, offset, count);
} else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE) {
- udf_table_free_blocks(sb, inode, map->s_fspace.s_table,
+ udf_table_free_blocks(sb, map->s_fspace.s_table,
bloc, offset, count);
}
+
+ if (inode) {
+ inode_sub_bytes(inode,
+ ((sector_t)count) << sb->s_blocksize_bits);
+ }
}
inline int udf_prealloc_blocks(struct super_block *sb,
@@ -763,29 +762,34 @@ inline int udf_prealloc_blocks(struct super_block *sb,
uint32_t block_count)
{
struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
+ sector_t allocated;
if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP)
- return udf_bitmap_prealloc_blocks(sb, inode,
- map->s_uspace.s_bitmap,
- partition, first_block,
- block_count);
+ allocated = udf_bitmap_prealloc_blocks(sb,
+ map->s_uspace.s_bitmap,
+ partition, first_block,
+ block_count);
else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE)
- return udf_table_prealloc_blocks(sb, inode,
- map->s_uspace.s_table,
- partition, first_block,
- block_count);
+ allocated = udf_table_prealloc_blocks(sb,
+ map->s_uspace.s_table,
+ partition, first_block,
+ block_count);
else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP)
- return udf_bitmap_prealloc_blocks(sb, inode,
- map->s_fspace.s_bitmap,
- partition, first_block,
- block_count);
+ allocated = udf_bitmap_prealloc_blocks(sb,
+ map->s_fspace.s_bitmap,
+ partition, first_block,
+ block_count);
else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE)
- return udf_table_prealloc_blocks(sb, inode,
- map->s_fspace.s_table,
- partition, first_block,
- block_count);
+ allocated = udf_table_prealloc_blocks(sb,
+ map->s_fspace.s_table,
+ partition, first_block,
+ block_count);
else
return 0;
+
+ if (inode && allocated > 0)
+ inode_add_bytes(inode, allocated << sb->s_blocksize_bits);
+ return allocated;
}
inline int udf_new_block(struct super_block *sb,
@@ -793,25 +797,29 @@ inline int udf_new_block(struct super_block *sb,
uint16_t partition, uint32_t goal, int *err)
{
struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
+ int block;
if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP)
- return udf_bitmap_new_block(sb, inode,
- map->s_uspace.s_bitmap,
- partition, goal, err);
+ block = udf_bitmap_new_block(sb,
+ map->s_uspace.s_bitmap,
+ partition, goal, err);
else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE)
- return udf_table_new_block(sb, inode,
- map->s_uspace.s_table,
- partition, goal, err);
- else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP)
- return udf_bitmap_new_block(sb, inode,
- map->s_fspace.s_bitmap,
+ block = udf_table_new_block(sb,
+ map->s_uspace.s_table,
partition, goal, err);
+ else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP)
+ block = udf_bitmap_new_block(sb,
+ map->s_fspace.s_bitmap,
+ partition, goal, err);
else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE)
- return udf_table_new_block(sb, inode,
- map->s_fspace.s_table,
- partition, goal, err);
+ block = udf_table_new_block(sb,
+ map->s_fspace.s_table,
+ partition, goal, err);
else {
*err = -EIO;
return 0;
}
+ if (inode && block)
+ inode_add_bytes(inode, sb->s_blocksize);
+ return block;
}
diff --git a/fs/udf/file.c b/fs/udf/file.c
index dca0c38..7f3f7ba 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -87,10 +87,10 @@ static int udf_adinicb_write_end(struct file *file,
char *kaddr;
struct udf_inode_info *iinfo = UDF_I(inode);
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr + offset,
kaddr + offset, copied);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
return simple_write_end(file, mapping, pos, len, copied, page, fsdata);
}
@@ -201,12 +201,10 @@ out:
static int udf_release_file(struct inode *inode, struct file *filp)
{
if (filp->f_mode & FMODE_WRITE) {
- mutex_lock(&inode->i_mutex);
down_write(&UDF_I(inode)->i_data_sem);
udf_discard_prealloc(inode);
udf_truncate_tail_extent(inode);
up_write(&UDF_I(inode)->i_data_sem);
- mutex_unlock(&inode->i_mutex);
}
return 0;
}
diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c
index 05ab481..7e5aae4 100644
--- a/fs/udf/ialloc.c
+++ b/fs/udf/ialloc.c
@@ -116,6 +116,7 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err)
iinfo->i_lenEAttr = 0;
iinfo->i_lenAlloc = 0;
iinfo->i_use = 0;
+ iinfo->i_checkpoint = 1;
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_AD_IN_ICB))
iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
else if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 7699df7..7d75280 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1358,6 +1358,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
iinfo->i_unique = le64_to_cpu(fe->uniqueID);
iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr);
iinfo->i_lenAlloc = le32_to_cpu(fe->lengthAllocDescs);
+ iinfo->i_checkpoint = le32_to_cpu(fe->checkpoint);
offset = sizeof(struct fileEntry) + iinfo->i_lenEAttr;
} else {
inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) <<
@@ -1379,6 +1380,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
iinfo->i_unique = le64_to_cpu(efe->uniqueID);
iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr);
iinfo->i_lenAlloc = le32_to_cpu(efe->lengthAllocDescs);
+ iinfo->i_checkpoint = le32_to_cpu(efe->checkpoint);
offset = sizeof(struct extendedFileEntry) +
iinfo->i_lenEAttr;
}
@@ -1495,6 +1497,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
struct buffer_head *bh = NULL;
struct fileEntry *fe;
struct extendedFileEntry *efe;
+ uint64_t lb_recorded;
uint32_t udfperms;
uint16_t icbflags;
uint16_t crclen;
@@ -1589,13 +1592,18 @@ static int udf_update_inode(struct inode *inode, int do_sync)
dsea->minorDeviceIdent = cpu_to_le32(iminor(inode));
}
+ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)
+ lb_recorded = 0; /* No extents => no blocks! */
+ else
+ lb_recorded =
+ (inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >>
+ (blocksize_bits - 9);
+
if (iinfo->i_efe == 0) {
memcpy(bh->b_data + sizeof(struct fileEntry),
iinfo->i_ext.i_data,
inode->i_sb->s_blocksize - sizeof(struct fileEntry));
- fe->logicalBlocksRecorded = cpu_to_le64(
- (inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >>
- (blocksize_bits - 9));
+ fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
udf_time_to_disk_stamp(&fe->accessTime, inode->i_atime);
udf_time_to_disk_stamp(&fe->modificationTime, inode->i_mtime);
@@ -1607,6 +1615,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
fe->uniqueID = cpu_to_le64(iinfo->i_unique);
fe->lengthExtendedAttr = cpu_to_le32(iinfo->i_lenEAttr);
fe->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc);
+ fe->checkpoint = cpu_to_le32(iinfo->i_checkpoint);
fe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_FE);
crclen = sizeof(struct fileEntry);
} else {
@@ -1615,9 +1624,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
inode->i_sb->s_blocksize -
sizeof(struct extendedFileEntry));
efe->objectSize = cpu_to_le64(inode->i_size);
- efe->logicalBlocksRecorded = cpu_to_le64(
- (inode->i_blocks + (1 << (blocksize_bits - 9)) - 1) >>
- (blocksize_bits - 9));
+ efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
if (iinfo->i_crtime.tv_sec > inode->i_atime.tv_sec ||
(iinfo->i_crtime.tv_sec == inode->i_atime.tv_sec &&
@@ -1646,6 +1653,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
efe->uniqueID = cpu_to_le64(iinfo->i_unique);
efe->lengthExtendedAttr = cpu_to_le32(iinfo->i_lenEAttr);
efe->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc);
+ efe->checkpoint = cpu_to_le32(iinfo->i_checkpoint);
efe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_EFE);
crclen = sizeof(struct extendedFileEntry);
}
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 08bf46e..38de8f2 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -32,8 +32,6 @@
#include <linux/crc-itu-t.h>
#include <linux/exportfs.h>
-enum { UDF_MAX_LINKS = 0xffff };
-
static inline int udf_match(int len1, const unsigned char *name1, int len2,
const unsigned char *name2)
{
@@ -649,10 +647,6 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct udf_inode_info *dinfo = UDF_I(dir);
struct udf_inode_info *iinfo;
- err = -EMLINK;
- if (dir->i_nlink >= UDF_MAX_LINKS)
- goto out;
-
err = -EIO;
inode = udf_new_inode(dir, S_IFDIR | mode, &err);
if (!inode)
@@ -1032,9 +1026,6 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir,
struct fileIdentDesc cfi, *fi;
int err;
- if (inode->i_nlink >= UDF_MAX_LINKS)
- return -EMLINK;
-
fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
if (!fi) {
return err;
@@ -1126,10 +1117,6 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) !=
old_dir->i_ino)
goto end_rename;
-
- retval = -EMLINK;
- if (!new_inode && new_dir->i_nlink >= UDF_MAX_LINKS)
- goto end_rename;
}
if (!nfi) {
nfi = udf_add_entry(new_dir, new_dentry, &nfibh, &ncfi,
diff --git a/fs/udf/super.c b/fs/udf/super.c
index c09a84da..ac8a348 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -75,6 +75,8 @@
#define UDF_DEFAULT_BLOCKSIZE 2048
+enum { UDF_MAX_LINKS = 0xffff };
+
/* These are the "meat" - everything else is stuffing */
static int udf_fill_super(struct super_block *, void *, int);
static void udf_put_super(struct super_block *);
@@ -948,11 +950,8 @@ static struct udf_bitmap *udf_sb_alloc_bitmap(struct super_block *sb, u32 index)
else
bitmap = vzalloc(size); /* TODO: get rid of vzalloc */
- if (bitmap == NULL) {
- udf_err(sb, "Unable to allocate space for bitmap and %d buffer_head pointers\n",
- nr_groups);
+ if (bitmap == NULL)
return NULL;
- }
bitmap->s_block_bitmap = (struct buffer_head **)(bitmap + 1);
bitmap->s_nr_groups = nr_groups;
@@ -2035,13 +2034,13 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
}
/* Allocate a dentry for the root inode */
- sb->s_root = d_alloc_root(inode);
+ sb->s_root = d_make_root(inode);
if (!sb->s_root) {
udf_err(sb, "Couldn't allocate root dentry\n");
- iput(inode);
goto error_out;
}
sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_max_links = UDF_MAX_LINKS;
return 0;
error_out:
diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h
index d1bd31e..bb8309d 100644
--- a/fs/udf/udf_i.h
+++ b/fs/udf/udf_i.h
@@ -23,6 +23,7 @@ struct udf_inode_info {
__u64 i_lenExtents;
__u32 i_next_alloc_block;
__u32 i_next_alloc_goal;
+ __u32 i_checkpoint;
unsigned i_alloc_type : 3;
unsigned i_efe : 1; /* extendedFileEntry */
unsigned i_use : 1; /* unallocSpaceEntry */
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 38cac19..a2281ca 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -166,10 +166,6 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir,
int error;
lock_ufs(dir->i_sb);
- if (inode->i_nlink >= UFS_LINK_MAX) {
- unlock_ufs(dir->i_sb);
- return -EMLINK;
- }
inode->i_ctime = CURRENT_TIME_SEC;
inode_inc_link_count(inode);
@@ -183,10 +179,7 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir,
static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
{
struct inode * inode;
- int err = -EMLINK;
-
- if (dir->i_nlink >= UFS_LINK_MAX)
- goto out;
+ int err;
lock_ufs(dir->i_sb);
inode_inc_link_count(dir);
@@ -305,11 +298,6 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
- if (dir_de) {
- err = -EMLINK;
- if (new_dir->i_nlink >= UFS_LINK_MAX)
- goto out_dir;
- }
err = ufs_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 5246ee3..f636f6b 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1157,16 +1157,17 @@ magic_found:
"fast symlink size (%u)\n", uspi->s_maxsymlinklen);
uspi->s_maxsymlinklen = maxsymlen;
}
+ sb->s_max_links = UFS_LINK_MAX;
inode = ufs_iget(sb, UFS_ROOTINO);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto failed;
}
- sb->s_root = d_alloc_root(inode);
+ sb->s_root = d_make_root(inode);
if (!sb->s_root) {
ret = -ENOMEM;
- goto dalloc_failed;
+ goto failed;
}
ufs_setup_cstotal(sb);
@@ -1180,8 +1181,6 @@ magic_found:
UFSD("EXIT\n");
return 0;
-dalloc_failed:
- iput(inode);
failed:
if (ubh)
ubh_brelse_uspi (uspi);
diff --git a/fs/xattr.c b/fs/xattr.c
index 82f4337..d6dfd24 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -16,7 +16,7 @@
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/fsnotify.h>
#include <linux/audit.h>
#include <asm/uaccess.h>
diff --git a/fs/xattr_acl.c b/fs/xattr_acl.c
index 8d5a506..69d06b0 100644
--- a/fs/xattr_acl.c
+++ b/fs/xattr_acl.c
@@ -5,7 +5,7 @@
* Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/posix_acl_xattr.h>
#include <linux/gfp.h>
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index 866de27..e44ef7e 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -118,17 +118,6 @@ xfs_rename(
new_parent = (src_dp != target_dp);
src_is_directory = S_ISDIR(src_ip->i_d.di_mode);
- if (src_is_directory) {
- /*
- * Check for link count overflow on target_dp
- */
- if (target_ip == NULL && new_parent &&
- target_dp->i_d.di_nlink >= XFS_MAXLINK) {
- error = XFS_ERROR(EMLINK);
- goto std_return;
- }
- }
-
xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip,
inodes, &num_inodes);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e1c623b..dab9a5f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1358,6 +1358,7 @@ xfs_fs_fill_super(
sb->s_blocksize = mp->m_sb.sb_blocksize;
sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
+ sb->s_max_links = XFS_MAXLINK;
sb->s_time_gran = 1;
set_posix_acl_flag(sb);
@@ -1378,10 +1379,10 @@ xfs_fs_fill_super(
error = EINVAL;
goto out_syncd_stop;
}
- sb->s_root = d_alloc_root(root);
+ sb->s_root = d_make_root(root);
if (!sb->s_root) {
error = ENOMEM;
- goto out_iput;
+ goto out_syncd_stop;
}
return 0;
@@ -1402,8 +1403,6 @@ out_destroy_workqueues:
out:
return -error;
- out_iput:
- iput(root);
out_syncd_stop:
xfs_syncd_stop(mp);
out_unmount:
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index 89dbb4a..79c05ac 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -296,8 +296,6 @@ xfs_bumplink(
xfs_trans_t *tp,
xfs_inode_t *ip)
{
- if (ip->i_d.di_nlink >= XFS_MAXLINK)
- return XFS_ERROR(EMLINK);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
ASSERT(ip->i_d.di_nlink > 0);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index ebdb888..64981d7 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -917,14 +917,6 @@ xfs_create(
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
unlock_dp_on_error = B_TRUE;
- /*
- * Check for directory link count overflow.
- */
- if (is_dir && dp->i_d.di_nlink >= XFS_MAXLINK) {
- error = XFS_ERROR(EMLINK);
- goto out_trans_cancel;
- }
-
xfs_bmap_init(&free_list, &first_block);
/*
@@ -1429,14 +1421,6 @@ xfs_link(
xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
/*
- * If the source has too many links, we can't make any more to it.
- */
- if (sip->i_d.di_nlink >= XFS_MAXLINK) {
- error = XFS_ERROR(EMLINK);
- goto error_return;
- }
-
- /*
* If we are using project inheritance, we only allow hard link
* creation in our tree when the project IDs are the same; else
* the tree quota mechanism could be circumvented.