summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/v9fs.c2
-rw-r--r--fs/9p/vfs_dir.c1
-rw-r--r--fs/9p/vfs_file.c7
-rw-r--r--fs/9p/vfs_inode.c8
-rw-r--r--fs/9p/vfs_inode_dotl.c7
-rw-r--r--fs/9p/xattr.c2
-rw-r--r--fs/Makefile3
-rw-r--r--fs/affs/affs.h16
-rw-r--r--fs/affs/amigaffs.c15
-rw-r--r--fs/affs/bitmap.c21
-rw-r--r--fs/affs/dir.c8
-rw-r--r--fs/affs/file.c46
-rw-r--r--fs/affs/inode.c14
-rw-r--r--fs/affs/namei.c39
-rw-r--r--fs/affs/super.c43
-rw-r--r--fs/affs/symlink.c2
-rw-r--r--fs/afs/flock.c4
-rw-r--r--fs/attr.c8
-rw-r--r--fs/autofs4/dev-ioctl.c2
-rw-r--r--fs/befs/btree.c11
-rw-r--r--fs/befs/datastream.c2
-rw-r--r--fs/befs/linuxvfs.c29
-rw-r--r--fs/binfmt_elf.c12
-rw-r--r--fs/binfmt_flat.c2
-rw-r--r--fs/bio-integrity.c657
-rw-r--r--fs/bio.c2037
-rw-r--r--fs/block_dev.c63
-rw-r--r--fs/btrfs/btrfs_inode.h2
-rw-r--r--fs/btrfs/extent_io.c13
-rw-r--r--fs/btrfs/file.c5
-rw-r--r--fs/btrfs/inode.c6
-rw-r--r--fs/btrfs/ioctl.c2
-rw-r--r--fs/buffer.c51
-rw-r--r--fs/cachefiles/bind.c17
-rw-r--r--fs/cachefiles/daemon.c31
-rw-r--r--fs/cachefiles/interface.c3
-rw-r--r--fs/cachefiles/internal.h30
-rw-r--r--fs/cachefiles/main.c9
-rw-r--r--fs/cachefiles/namei.c53
-rw-r--r--fs/cachefiles/security.c10
-rw-r--r--fs/cachefiles/xattr.c10
-rw-r--r--fs/ceph/addr.c2
-rw-r--r--fs/ceph/debugfs.c6
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/ceph/locks.c10
-rw-r--r--fs/ceph/mds_client.c6
-rw-r--r--fs/ceph/mdsmap.c2
-rw-r--r--fs/cifs/cifsfs.c94
-rw-r--r--fs/cifs/cifsfs.h22
-rw-r--r--fs/cifs/cifsglob.h8
-rw-r--r--fs/cifs/connect.c5
-rw-r--r--fs/cifs/file.c16
-rw-r--r--fs/cifs/inode.c71
-rw-r--r--fs/cifs/ioctl.c2
-rw-r--r--fs/cifs/netmisc.c9
-rw-r--r--fs/cifs/smb2ops.c2
-rw-r--r--fs/cifs/smb2pdu.c19
-rw-r--r--fs/cifs/smb2pdu.h8
-rw-r--r--fs/coda/cnode.c4
-rw-r--r--fs/coda/coda_linux.h8
-rw-r--r--fs/coda/dir.c18
-rw-r--r--fs/coda/inode.c29
-rw-r--r--fs/coda/psdev.c39
-rw-r--r--fs/coda/sysctl.c4
-rw-r--r--fs/coda/upcall.c14
-rw-r--r--fs/configfs/configfs_internal.h6
-rw-r--r--fs/configfs/dir.c8
-rw-r--r--fs/configfs/inode.c5
-rw-r--r--fs/configfs/item.c58
-rw-r--r--fs/configfs/mount.c4
-rw-r--r--fs/dcache.c2
-rw-r--r--fs/devpts/inode.c26
-rw-r--r--fs/dlm/config.c26
-rw-r--r--fs/dlm/debug_fs.c34
-rw-r--r--fs/dlm/lockspace.c21
-rw-r--r--fs/drop_caches.c2
-rw-r--r--fs/efivarfs/super.c2
-rw-r--r--fs/efs/dir.c18
-rw-r--r--fs/efs/efs.h6
-rw-r--r--fs/efs/file.c14
-rw-r--r--fs/efs/inode.c42
-rw-r--r--fs/efs/namei.c8
-rw-r--r--fs/efs/super.c42
-rw-r--r--fs/eventpoll.c2
-rw-r--r--fs/exofs/Kconfig.ore2
-rw-r--r--fs/exofs/ore.c100
-rw-r--r--fs/exofs/ore_raid.c56
-rw-r--r--fs/exofs/ore_raid.h21
-rw-r--r--fs/exportfs/expfs.c4
-rw-r--r--fs/ext4/balloc.c66
-rw-r--r--fs/ext4/dir.c3
-rw-r--r--fs/ext4/ext4.h59
-rw-r--r--fs/ext4/ext4_extents.h22
-rw-r--r--fs/ext4/ext4_jbd2.c7
-rw-r--r--fs/ext4/ext4_jbd2.h4
-rw-r--r--fs/ext4/extents.c236
-rw-r--r--fs/ext4/extents_status.c10
-rw-r--r--fs/ext4/file.c153
-rw-r--r--fs/ext4/inline.c15
-rw-r--r--fs/ext4/inode.c90
-rw-r--r--fs/ext4/mballoc.c22
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/mmp.c4
-rw-r--r--fs/ext4/move_extent.c39
-rw-r--r--fs/ext4/namei.c131
-rw-r--r--fs/ext4/page-io.c32
-rw-r--r--fs/ext4/resize.c15
-rw-r--r--fs/ext4/super.c20
-rw-r--r--fs/ext4/xattr.c9
-rw-r--r--fs/f2fs/acl.c2
-rw-r--r--fs/f2fs/checkpoint.c121
-rw-r--r--fs/f2fs/data.c63
-rw-r--r--fs/f2fs/dir.c12
-rw-r--r--fs/f2fs/f2fs.h49
-rw-r--r--fs/f2fs/file.c139
-rw-r--r--fs/f2fs/inline.c40
-rw-r--r--fs/f2fs/inode.c18
-rw-r--r--fs/f2fs/namei.c11
-rw-r--r--fs/f2fs/node.c156
-rw-r--r--fs/f2fs/node.h19
-rw-r--r--fs/f2fs/recovery.c35
-rw-r--r--fs/f2fs/segment.c134
-rw-r--r--fs/f2fs/super.c32
-rw-r--r--fs/f2fs/xattr.c110
-rw-r--r--fs/f2fs/xattr.h8
-rw-r--r--fs/fat/fat.h3
-rw-r--r--fs/fat/inode.c345
-rw-r--r--fs/file_table.c4
-rw-r--r--fs/fscache/cache.c13
-rw-r--r--fs/fscache/cookie.c2
-rw-r--r--fs/fscache/histogram.c6
-rw-r--r--fs/fscache/internal.h26
-rw-r--r--fs/fscache/main.c11
-rw-r--r--fs/fscache/netfs.c7
-rw-r--r--fs/fscache/object-list.c8
-rw-r--r--fs/fscache/operation.c3
-rw-r--r--fs/fscache/page.c6
-rw-r--r--fs/fuse/dev.c2
-rw-r--r--fs/fuse/file.c3
-rw-r--r--fs/gfs2/aops.c3
-rw-r--r--fs/gfs2/bmap.c8
-rw-r--r--fs/gfs2/file.c12
-rw-r--r--fs/gfs2/glock.c8
-rw-r--r--fs/gfs2/glops.c53
-rw-r--r--fs/gfs2/glops.h2
-rw-r--r--fs/gfs2/incore.h14
-rw-r--r--fs/gfs2/inode.c40
-rw-r--r--fs/gfs2/lock_dlm.c4
-rw-r--r--fs/gfs2/log.c93
-rw-r--r--fs/gfs2/log.h11
-rw-r--r--fs/gfs2/lops.c2
-rw-r--r--fs/gfs2/meta_io.c4
-rw-r--r--fs/gfs2/ops_fstype.c25
-rw-r--r--fs/gfs2/quota.c3
-rw-r--r--fs/gfs2/recovery.c24
-rw-r--r--fs/gfs2/rgrp.c2
-rw-r--r--fs/gfs2/super.c69
-rw-r--r--fs/gfs2/sys.c11
-rw-r--r--fs/gfs2/trans.c44
-rw-r--r--fs/hfsplus/attributes.c36
-rw-r--r--fs/hfsplus/bnode.c49
-rw-r--r--fs/hfsplus/btree.c2
-rw-r--r--fs/hfsplus/dir.c31
-rw-r--r--fs/hfsplus/extents.c17
-rw-r--r--fs/hfsplus/hfsplus_fs.h205
-rw-r--r--fs/hfsplus/hfsplus_raw.h1
-rw-r--r--fs/hfsplus/options.c9
-rw-r--r--fs/hfsplus/super.c3
-rw-r--r--fs/hfsplus/wrapper.c10
-rw-r--r--fs/hfsplus/xattr.c57
-rw-r--r--fs/hfsplus/xattr_security.c49
-rw-r--r--fs/hfsplus/xattr_trusted.c32
-rw-r--r--fs/hfsplus/xattr_user.c32
-rw-r--r--fs/hpfs/alloc.c2
-rw-r--r--fs/hpfs/buffer.c12
-rw-r--r--fs/hpfs/dir.c6
-rw-r--r--fs/hpfs/dnode.c44
-rw-r--r--fs/hpfs/ea.c6
-rw-r--r--fs/hpfs/hpfs_fn.h5
-rw-r--r--fs/hpfs/inode.c3
-rw-r--r--fs/hpfs/map.c17
-rw-r--r--fs/hpfs/name.c11
-rw-r--r--fs/hpfs/namei.c2
-rw-r--r--fs/hpfs/super.c55
-rw-r--r--fs/hugetlbfs/inode.c25
-rw-r--r--fs/inode.c12
-rw-r--r--fs/ioprio.c241
-rw-r--r--fs/jbd2/commit.c6
-rw-r--r--fs/jffs2/background.c12
-rw-r--r--fs/jfs/acl.c16
-rw-r--r--fs/jfs/jfs_dmap.c9
-rw-r--r--fs/jfs/jfs_inode.c16
-rw-r--r--fs/jfs/jfs_logmgr.c2
-rw-r--r--fs/jfs/super.c77
-rw-r--r--fs/kernfs/dir.c1
-rw-r--r--fs/kernfs/file.c41
-rw-r--r--fs/kernfs/kernfs-internal.h5
-rw-r--r--fs/kernfs/mount.c11
-rw-r--r--fs/libfs.c34
-rw-r--r--fs/lockd/clnt4xdr.c2
-rw-r--r--fs/lockd/clntxdr.c2
-rw-r--r--fs/lockd/svc.c8
-rw-r--r--fs/lockd/svcsubs.c3
-rw-r--r--fs/lockd/xdr.c2
-rw-r--r--fs/locks.c37
-rw-r--r--fs/mpage.c84
-rw-r--r--fs/namei.c11
-rw-r--r--fs/ncpfs/getopt.c13
-rw-r--r--fs/nfs/Makefile4
-rw-r--r--fs/nfs/blocklayout/blocklayout.c38
-rw-r--r--fs/nfs/dir.c12
-rw-r--r--fs/nfs/direct.c117
-rw-r--r--fs/nfs/file.c4
-rw-r--r--fs/nfs/filelayout/Makefile5
-rw-r--r--fs/nfs/filelayout/filelayout.c (renamed from fs/nfs/nfs4filelayout.c)203
-rw-r--r--fs/nfs/filelayout/filelayout.h (renamed from fs/nfs/nfs4filelayout.h)2
-rw-r--r--fs/nfs/filelayout/filelayoutdev.c (renamed from fs/nfs/nfs4filelayoutdev.c)10
-rw-r--r--fs/nfs/getroot.c3
-rw-r--r--fs/nfs/inode.c28
-rw-r--r--fs/nfs/internal.h33
-rw-r--r--fs/nfs/nfs2xdr.c14
-rw-r--r--fs/nfs/nfs3proc.c21
-rw-r--r--fs/nfs/nfs3xdr.c16
-rw-r--r--fs/nfs/nfs4_fs.h4
-rw-r--r--fs/nfs/nfs4file.c3
-rw-r--r--fs/nfs/nfs4proc.c58
-rw-r--r--fs/nfs/nfs4state.c10
-rw-r--r--fs/nfs/nfs4sysctl.c6
-rw-r--r--fs/nfs/nfs4trace.h8
-rw-r--r--fs/nfs/nfs4xdr.c19
-rw-r--r--fs/nfs/objlayout/objio_osd.c24
-rw-r--r--fs/nfs/objlayout/objlayout.c24
-rw-r--r--fs/nfs/objlayout/objlayout.h8
-rw-r--r--fs/nfs/pagelist.c639
-rw-r--r--fs/nfs/pnfs.c168
-rw-r--r--fs/nfs/pnfs.h32
-rw-r--r--fs/nfs/proc.c21
-rw-r--r--fs/nfs/read.c414
-rw-r--r--fs/nfs/super.c27
-rw-r--r--fs/nfs/sysctl.c6
-rw-r--r--fs/nfs/write.c592
-rw-r--r--fs/nfsd/acl.h2
-rw-r--r--fs/nfsd/auth.c5
-rw-r--r--fs/nfsd/export.c88
-rw-r--r--fs/nfsd/export.h110
-rw-r--r--fs/nfsd/fault_inject.c15
-rw-r--r--fs/nfsd/idmap.h4
-rw-r--r--fs/nfsd/nfs2acl.c12
-rw-r--r--fs/nfsd/nfs3acl.c6
-rw-r--r--fs/nfsd/nfs3xdr.c27
-rw-r--r--fs/nfsd/nfs4acl.c12
-rw-r--r--fs/nfsd/nfs4idmap.c42
-rw-r--r--fs/nfsd/nfs4proc.c180
-rw-r--r--fs/nfsd/nfs4state.c271
-rw-r--r--fs/nfsd/nfs4xdr.c1933
-rw-r--r--fs/nfsd/nfscache.c17
-rw-r--r--fs/nfsd/nfsctl.c1
-rw-r--r--fs/nfsd/nfsd.h17
-rw-r--r--fs/nfsd/nfsfh.c25
-rw-r--r--fs/nfsd/nfsfh.h59
-rw-r--r--fs/nfsd/nfssvc.c6
-rw-r--r--fs/nfsd/nfsxdr.c15
-rw-r--r--fs/nfsd/state.h5
-rw-r--r--fs/nfsd/stats.c1
-rw-r--r--fs/nfsd/stats.h43
-rw-r--r--fs/nfsd/vfs.c155
-rw-r--r--fs/nfsd/vfs.h10
-rw-r--r--fs/nfsd/xdr4.h23
-rw-r--r--fs/notify/fanotify/fanotify_user.c45
-rw-r--r--fs/notify/inotify/inotify_user.c2
-rw-r--r--fs/notify/mark.c2
-rw-r--r--fs/ntfs/attrib.c1
-rw-r--r--fs/ntfs/compress.c2
-rw-r--r--fs/ntfs/file.c1
-rw-r--r--fs/ntfs/super.c4
-rw-r--r--fs/ntfs/sysctl.c6
-rw-r--r--fs/ocfs2/alloc.c6
-rw-r--r--fs/ocfs2/cluster/heartbeat.c2
-rw-r--r--fs/ocfs2/cluster/tcp.c33
-rw-r--r--fs/ocfs2/dlm/dlmcommon.h1
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c2
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c14
-rw-r--r--fs/ocfs2/dlm/dlmlock.c2
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c6
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c10
-rw-r--r--fs/ocfs2/dlmglue.c5
-rw-r--r--fs/ocfs2/file.c2
-rw-r--r--fs/ocfs2/ioctl.c81
-rw-r--r--fs/ocfs2/journal.c17
-rw-r--r--fs/ocfs2/ocfs2.h1
-rw-r--r--fs/ocfs2/refcounttree.c7
-rw-r--r--fs/ocfs2/resize.c10
-rw-r--r--fs/ocfs2/stackglue.c2
-rw-r--r--fs/ocfs2/super.c8
-rw-r--r--fs/ocfs2/uptodate.c2
-rw-r--r--fs/proc/task_mmu.c28
-rw-r--r--fs/proc/vmcore.c2
-rw-r--r--fs/pstore/platform.c19
-rw-r--r--fs/pstore/ram_core.c36
-rw-r--r--fs/quota/quota.c14
-rw-r--r--fs/readdir.c2
-rw-r--r--fs/reiserfs/bitmap.c13
-rw-r--r--fs/reiserfs/stree.c8
-rw-r--r--fs/squashfs/squashfs.h2
-rw-r--r--fs/super.c16
-rw-r--r--fs/sysfs/group.c10
-rw-r--r--fs/ubifs/budget.c1
-rw-r--r--fs/ubifs/debug.c4
-rw-r--r--fs/ubifs/file.c6
-rw-r--r--fs/ubifs/io.c18
-rw-r--r--fs/ubifs/lpt_commit.c4
-rw-r--r--fs/ubifs/shrinker.c1
-rw-r--r--fs/ubifs/super.c5
-rw-r--r--fs/ubifs/tnc.c5
-rw-r--r--fs/ubifs/tnc_commit.c4
-rw-r--r--fs/ubifs/ubifs.h11
-rw-r--r--fs/ufs/balloc.c36
-rw-r--r--fs/ufs/ialloc.c17
-rw-r--r--fs/ufs/super.c28
-rw-r--r--fs/ufs/ufs.h1
-rw-r--r--fs/xfs/xfs_ag.h36
-rw-r--r--fs/xfs/xfs_alloc.c19
-rw-r--r--fs/xfs/xfs_alloc_btree.c1
-rw-r--r--fs/xfs/xfs_aops.c55
-rw-r--r--fs/xfs/xfs_attr.c343
-rw-r--r--fs/xfs/xfs_attr_leaf.c184
-rw-r--r--fs/xfs/xfs_attr_leaf.h3
-rw-r--r--fs/xfs/xfs_attr_list.c1
-rw-r--r--fs/xfs/xfs_attr_remote.c58
-rw-r--r--fs/xfs/xfs_bit.h7
-rw-r--r--fs/xfs/xfs_bmap.c211
-rw-r--r--fs/xfs/xfs_bmap.h4
-rw-r--r--fs/xfs/xfs_bmap_btree.c9
-rw-r--r--fs/xfs/xfs_bmap_btree.h2
-rw-r--r--fs/xfs/xfs_bmap_util.c18
-rw-r--r--fs/xfs/xfs_bmap_util.h13
-rw-r--r--fs/xfs/xfs_btree.c56
-rw-r--r--fs/xfs/xfs_btree.h5
-rw-r--r--fs/xfs/xfs_buf.c17
-rw-r--r--fs/xfs/xfs_buf.h9
-rw-r--r--fs/xfs/xfs_buf_item.c5
-rw-r--r--fs/xfs/xfs_da_btree.c114
-rw-r--r--fs/xfs/xfs_da_btree.h26
-rw-r--r--fs/xfs/xfs_da_format.c36
-rw-r--r--fs/xfs/xfs_da_format.h154
-rw-r--r--fs/xfs/xfs_dir2.c136
-rw-r--r--fs/xfs/xfs_dir2.h30
-rw-r--r--fs/xfs/xfs_dir2_block.c97
-rw-r--r--fs/xfs/xfs_dir2_data.c83
-rw-r--r--fs/xfs/xfs_dir2_leaf.c202
-rw-r--r--fs/xfs/xfs_dir2_node.c190
-rw-r--r--fs/xfs/xfs_dir2_priv.h142
-rw-r--r--fs/xfs/xfs_dir2_readdir.c155
-rw-r--r--fs/xfs/xfs_dir2_sf.c39
-rw-r--r--fs/xfs/xfs_dquot.c59
-rw-r--r--fs/xfs/xfs_dquot.h2
-rw-r--r--fs/xfs/xfs_dquot_buf.c5
-rw-r--r--fs/xfs/xfs_file.c2
-rw-r--r--fs/xfs/xfs_filestream.c684
-rw-r--r--fs/xfs/xfs_filestream.h34
-rw-r--r--fs/xfs/xfs_format.h14
-rw-r--r--fs/xfs/xfs_fs.h1
-rw-r--r--fs/xfs/xfs_fsops.c49
-rw-r--r--fs/xfs/xfs_ialloc.c704
-rw-r--r--fs/xfs/xfs_ialloc.h2
-rw-r--r--fs/xfs/xfs_ialloc_btree.c69
-rw-r--r--fs/xfs/xfs_ialloc_btree.h3
-rw-r--r--fs/xfs/xfs_icache.c12
-rw-r--r--fs/xfs/xfs_icache.h6
-rw-r--r--fs/xfs/xfs_inode.c178
-rw-r--r--fs/xfs/xfs_inode.h5
-rw-r--r--fs/xfs/xfs_inode_buf.c17
-rw-r--r--fs/xfs/xfs_inode_fork.c3
-rw-r--r--fs/xfs/xfs_inode_fork.h3
-rw-r--r--fs/xfs/xfs_inode_item.c32
-rw-r--r--fs/xfs/xfs_ioctl.c16
-rw-r--r--fs/xfs/xfs_ioctl32.c5
-rw-r--r--fs/xfs/xfs_iomap.c2
-rw-r--r--fs/xfs/xfs_iops.c20
-rw-r--r--fs/xfs/xfs_itable.c6
-rw-r--r--fs/xfs/xfs_log.c11
-rw-r--r--fs/xfs/xfs_log.h19
-rw-r--r--fs/xfs/xfs_log_cil.c57
-rw-r--r--fs/xfs/xfs_log_recover.c11
-rw-r--r--fs/xfs/xfs_log_rlimit.c2
-rw-r--r--fs/xfs/xfs_mount.c45
-rw-r--r--fs/xfs/xfs_mount.h12
-rw-r--r--fs/xfs/xfs_mru_cache.c151
-rw-r--r--fs/xfs/xfs_mru_cache.h31
-rw-r--r--fs/xfs/xfs_qm.c217
-rw-r--r--fs/xfs/xfs_qm_syscalls.c6
-rw-r--r--fs/xfs/xfs_quota_defs.h2
-rw-r--r--fs/xfs/xfs_quotaops.c29
-rw-r--r--fs/xfs/xfs_rtbitmap.c1
-rw-r--r--fs/xfs/xfs_sb.c12
-rw-r--r--fs/xfs/xfs_sb.h235
-rw-r--r--fs/xfs/xfs_shared.h2
-rw-r--r--fs/xfs/xfs_stats.c1
-rw-r--r--fs/xfs/xfs_stats.h18
-rw-r--r--fs/xfs/xfs_super.c22
-rw-r--r--fs/xfs/xfs_symlink.c3
-rw-r--r--fs/xfs/xfs_symlink_remote.c1
-rw-r--r--fs/xfs/xfs_trace.c1
-rw-r--r--fs/xfs/xfs_trace.h58
-rw-r--r--fs/xfs/xfs_trans.c2
-rw-r--r--fs/xfs/xfs_trans_ail.c5
-rw-r--r--fs/xfs/xfs_trans_priv.h3
-rw-r--r--fs/xfs/xfs_trans_resv.c56
-rw-r--r--fs/xfs/xfs_trans_space.h12
-rw-r--r--fs/xfs/xfs_types.h2
410 files changed, 9367 insertions, 10612 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 14da82564f4e..6894b085f0ee 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -537,7 +537,7 @@ static struct attribute_group v9fs_attr_group = {
*
*/
-static int v9fs_sysfs_init(void)
+static int __init v9fs_sysfs_init(void)
{
v9fs_kobj = kobject_create_and_add("9p", fs_kobj);
if (!v9fs_kobj)
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 4d0c2e0be7e5..0b3bfa303dda 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -42,7 +42,6 @@
/**
* struct p9_rdir - readdir accounting
- * @mutex: mutex protecting readdir
* @head: start offset of current dirread buffer
* @tail: end offset of current dirread buffer
* @buf: dirread buffer
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index d8223209d4b1..96e550760699 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -352,9 +352,6 @@ static int v9fs_file_flock_dotl(struct file *filp, int cmd,
invalidate_mapping_pages(&inode->i_data, 0, -1);
}
/* Convert flock to posix lock */
- fl->fl_owner = (fl_owner_t)filp;
- fl->fl_start = 0;
- fl->fl_end = OFFSET_MAX;
fl->fl_flags |= FL_POSIX;
fl->fl_flags ^= FL_FLOCK;
@@ -684,7 +681,7 @@ v9fs_direct_read(struct file *filp, char __user *udata, size_t count,
/**
* v9fs_cached_file_read - read from a file
* @filp: file pointer to read
- * @udata: user data buffer to read data into
+ * @data: user data buffer to read data into
* @count: size of buffer
* @offset: offset at which to read data
*
@@ -701,7 +698,7 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
/**
* v9fs_mmap_file_read - read from a file
* @filp: file pointer to read
- * @udata: user data buffer to read data into
+ * @data: user data buffer to read data into
* @count: size of buffer
* @offset: offset at which to read data
*
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 53161ec058a7..7fa4f7a7653d 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -147,7 +147,7 @@ static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses,
int major = -1, minor = -1;
strlcpy(ext, stat->extension, sizeof(ext));
- sscanf(ext, "%c %u %u", &type, &major, &minor);
+ sscanf(ext, "%c %i %i", &type, &major, &minor);
switch (type) {
case 'c':
res |= S_IFCHR;
@@ -580,7 +580,7 @@ static int v9fs_at_to_dotl_flags(int flags)
* v9fs_remove - helper function to remove files and directories
* @dir: directory inode that is being deleted
* @dentry: dentry that is being deleted
- * @rmdir: removing a directory
+ * @flags: removing a directory
*
*/
@@ -778,7 +778,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
* v9fs_vfs_lookup - VFS lookup hook to "walk" to a new inode
* @dir: inode that is being walked from
* @dentry: dentry that is being walked to?
- * @nameidata: path data
+ * @flags: lookup flags (unused)
*
*/
@@ -1324,7 +1324,7 @@ v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
* v9fs_vfs_mkspecial - create a special file
* @dir: inode to create special file in
* @dentry: dentry to create
- * @mode: mode to create special file
+ * @perm: mode to create special file
* @extension: 9p2000.u format extension string representing special file
*
*/
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 59dc8e87647f..1fa85aae24df 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -226,7 +226,7 @@ int v9fs_open_to_dotl_flags(int flags)
* v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol.
* @dir: directory inode that is being created
* @dentry: dentry that is being deleted
- * @mode: create permissions
+ * @omode: create permissions
*
*/
@@ -375,7 +375,7 @@ err_clunk_old_fid:
* v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory
* @dir: inode that is being unlinked
* @dentry: dentry that is being unlinked
- * @mode: mode for new directory
+ * @omode: mode for new directory
*
*/
@@ -607,7 +607,6 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
* v9fs_stat2inode_dotl - populate an inode structure with stat info
* @stat: stat structure
* @inode: inode to populate
- * @sb: superblock of filesystem
*
*/
@@ -808,7 +807,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
* v9fs_vfs_mknod_dotl - create a special file
* @dir: inode destination for new link
* @dentry: dentry for file
- * @mode: mode for creation
+ * @omode: mode for creation
* @rdev: device associated with special file
*
*/
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 04133a1fd9cb..f95e01e058e4 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -156,7 +156,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
offset += write_count;
value_len -= write_count;
}
- retval = offset;
+ retval = 0;
err:
p9_client_clunk(fid);
return retval;
diff --git a/fs/Makefile b/fs/Makefile
index f9cb9876e466..4030cbfbc9af 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -14,14 +14,13 @@ obj-y := open.o read_write.o file_table.o super.o \
stack.o fs_struct.o statfs.o
ifeq ($(CONFIG_BLOCK),y)
-obj-y += buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o
+obj-y += buffer.o block_dev.o direct-io.o mpage.o
else
obj-y += no-block.o
endif
obj-$(CONFIG_PROC_FS) += proc_namespace.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
obj-$(CONFIG_ANON_INODES) += anon_inodes.o
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 25b23b1e7f22..9bca88159725 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -1,3 +1,9 @@
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
@@ -206,7 +212,7 @@ affs_set_blocksize(struct super_block *sb, int size)
static inline struct buffer_head *
affs_bread(struct super_block *sb, int block)
{
- pr_debug("affs_bread: %d\n", block);
+ pr_debug("%s: %d\n", __func__, block);
if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size)
return sb_bread(sb, block);
return NULL;
@@ -214,7 +220,7 @@ affs_bread(struct super_block *sb, int block)
static inline struct buffer_head *
affs_getblk(struct super_block *sb, int block)
{
- pr_debug("affs_getblk: %d\n", block);
+ pr_debug("%s: %d\n", __func__, block);
if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size)
return sb_getblk(sb, block);
return NULL;
@@ -223,7 +229,7 @@ static inline struct buffer_head *
affs_getzeroblk(struct super_block *sb, int block)
{
struct buffer_head *bh;
- pr_debug("affs_getzeroblk: %d\n", block);
+ pr_debug("%s: %d\n", __func__, block);
if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) {
bh = sb_getblk(sb, block);
lock_buffer(bh);
@@ -238,7 +244,7 @@ static inline struct buffer_head *
affs_getemptyblk(struct super_block *sb, int block)
{
struct buffer_head *bh;
- pr_debug("affs_getemptyblk: %d\n", block);
+ pr_debug("%s: %d\n", __func__, block);
if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) {
bh = sb_getblk(sb, block);
wait_on_buffer(bh);
@@ -251,7 +257,7 @@ static inline void
affs_brelse(struct buffer_head *bh)
{
if (bh)
- pr_debug("affs_brelse: %lld\n", (long long) bh->b_blocknr);
+ pr_debug("%s: %lld\n", __func__, (long long) bh->b_blocknr);
brelse(bh);
}
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 533a322c41c0..406b29836b19 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -34,7 +34,7 @@ affs_insert_hash(struct inode *dir, struct buffer_head *bh)
ino = bh->b_blocknr;
offset = affs_hash_name(sb, AFFS_TAIL(sb, bh)->name + 1, AFFS_TAIL(sb, bh)->name[0]);
- pr_debug("AFFS: insert_hash(dir=%u, ino=%d)\n", (u32)dir->i_ino, ino);
+ pr_debug("%s(dir=%u, ino=%d)\n", __func__, (u32)dir->i_ino, ino);
dir_bh = affs_bread(sb, dir->i_ino);
if (!dir_bh)
@@ -84,7 +84,8 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh)
sb = dir->i_sb;
rem_ino = rem_bh->b_blocknr;
offset = affs_hash_name(sb, AFFS_TAIL(sb, rem_bh)->name+1, AFFS_TAIL(sb, rem_bh)->name[0]);
- pr_debug("AFFS: remove_hash(dir=%d, ino=%d, hashval=%d)\n", (u32)dir->i_ino, rem_ino, offset);
+ pr_debug("%s(dir=%d, ino=%d, hashval=%d)\n",
+ __func__, (u32)dir->i_ino, rem_ino, offset);
bh = affs_bread(sb, dir->i_ino);
if (!bh)
@@ -147,7 +148,7 @@ affs_remove_link(struct dentry *dentry)
u32 link_ino, ino;
int retval;
- pr_debug("AFFS: remove_link(key=%ld)\n", inode->i_ino);
+ pr_debug("%s(key=%ld)\n", __func__, inode->i_ino);
retval = -EIO;
bh = affs_bread(sb, inode->i_ino);
if (!bh)
@@ -279,7 +280,7 @@ affs_remove_header(struct dentry *dentry)
if (!inode)
goto done;
- pr_debug("AFFS: remove_header(key=%ld)\n", inode->i_ino);
+ pr_debug("%s(key=%ld)\n", __func__, inode->i_ino);
retval = -EIO;
bh = affs_bread(sb, (u32)(long)dentry->d_fsdata);
if (!bh)
@@ -451,10 +452,10 @@ affs_error(struct super_block *sb, const char *function, const char *fmt, ...)
vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
va_end(args);
- printk(KERN_CRIT "AFFS error (device %s): %s(): %s\n", sb->s_id,
+ pr_crit("error (device %s): %s(): %s\n", sb->s_id,
function,ErrorBuffer);
if (!(sb->s_flags & MS_RDONLY))
- printk(KERN_WARNING "AFFS: Remounting filesystem read-only\n");
+ pr_warn("Remounting filesystem read-only\n");
sb->s_flags |= MS_RDONLY;
}
@@ -467,7 +468,7 @@ affs_warning(struct super_block *sb, const char *function, const char *fmt, ...)
vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
va_end(args);
- printk(KERN_WARNING "AFFS warning (device %s): %s(): %s\n", sb->s_id,
+ pr_warn("(device %s): %s(): %s\n", sb->s_id,
function,ErrorBuffer);
}
diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c
index a32246b8359e..c8de51185c23 100644
--- a/fs/affs/bitmap.c
+++ b/fs/affs/bitmap.c
@@ -17,7 +17,7 @@ affs_count_free_blocks(struct super_block *sb)
u32 free;
int i;
- pr_debug("AFFS: count_free_blocks()\n");
+ pr_debug("%s()\n", __func__);
if (sb->s_flags & MS_RDONLY)
return 0;
@@ -43,7 +43,7 @@ affs_free_block(struct super_block *sb, u32 block)
u32 blk, bmap, bit, mask, tmp;
__be32 *data;
- pr_debug("AFFS: free_block(%u)\n", block);
+ pr_debug("%s(%u)\n", __func__, block);
if (block > sbi->s_partition_size)
goto err_range;
@@ -125,7 +125,7 @@ affs_alloc_block(struct inode *inode, u32 goal)
sb = inode->i_sb;
sbi = AFFS_SB(sb);
- pr_debug("AFFS: balloc(inode=%lu,goal=%u): ", inode->i_ino, goal);
+ pr_debug("balloc(inode=%lu,goal=%u): ", inode->i_ino, goal);
if (AFFS_I(inode)->i_pa_cnt) {
pr_debug("%d\n", AFFS_I(inode)->i_lastalloc+1);
@@ -254,8 +254,7 @@ int affs_init_bitmap(struct super_block *sb, int *flags)
return 0;
if (!AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->bm_flag) {
- printk(KERN_NOTICE "AFFS: Bitmap invalid - mounting %s read only\n",
- sb->s_id);
+ pr_notice("Bitmap invalid - mounting %s read only\n", sb->s_id);
*flags |= MS_RDONLY;
return 0;
}
@@ -268,7 +267,7 @@ int affs_init_bitmap(struct super_block *sb, int *flags)
size = sbi->s_bmap_count * sizeof(*bm);
bm = sbi->s_bitmap = kzalloc(size, GFP_KERNEL);
if (!sbi->s_bitmap) {
- printk(KERN_ERR "AFFS: Bitmap allocation failed\n");
+ pr_err("Bitmap allocation failed\n");
return -ENOMEM;
}
@@ -282,17 +281,17 @@ int affs_init_bitmap(struct super_block *sb, int *flags)
bm->bm_key = be32_to_cpu(bmap_blk[blk]);
bh = affs_bread(sb, bm->bm_key);
if (!bh) {
- printk(KERN_ERR "AFFS: Cannot read bitmap\n");
+ pr_err("Cannot read bitmap\n");
res = -EIO;
goto out;
}
if (affs_checksum_block(sb, bh)) {
- printk(KERN_WARNING "AFFS: Bitmap %u invalid - mounting %s read only.\n",
- bm->bm_key, sb->s_id);
+ pr_warn("Bitmap %u invalid - mounting %s read only.\n",
+ bm->bm_key, sb->s_id);
*flags |= MS_RDONLY;
goto out;
}
- pr_debug("AFFS: read bitmap block %d: %d\n", blk, bm->bm_key);
+ pr_debug("read bitmap block %d: %d\n", blk, bm->bm_key);
bm->bm_free = memweight(bh->b_data + 4, sb->s_blocksize - 4);
/* Don't try read the extension if this is the last block,
@@ -304,7 +303,7 @@ int affs_init_bitmap(struct super_block *sb, int *flags)
affs_brelse(bmap_bh);
bmap_bh = affs_bread(sb, be32_to_cpu(bmap_blk[blk]));
if (!bmap_bh) {
- printk(KERN_ERR "AFFS: Cannot read bitmap extension\n");
+ pr_err("Cannot read bitmap extension\n");
res = -EIO;
goto out;
}
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index cbbda476a805..59f07bec92a6 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -54,8 +54,8 @@ affs_readdir(struct file *file, struct dir_context *ctx)
u32 ino;
int error = 0;
- pr_debug("AFFS: readdir(ino=%lu,f_pos=%lx)\n",
- inode->i_ino, (unsigned long)ctx->pos);
+ pr_debug("%s(ino=%lu,f_pos=%lx)\n",
+ __func__, inode->i_ino, (unsigned long)ctx->pos);
if (ctx->pos < 2) {
file->private_data = (void *)0;
@@ -81,7 +81,7 @@ affs_readdir(struct file *file, struct dir_context *ctx)
*/
ino = (u32)(long)file->private_data;
if (ino && file->f_version == inode->i_version) {
- pr_debug("AFFS: readdir() left off=%d\n", ino);
+ pr_debug("readdir() left off=%d\n", ino);
goto inside;
}
@@ -117,7 +117,7 @@ inside:
namelen = min(AFFS_TAIL(sb, fh_bh)->name[0], (u8)30);
name = AFFS_TAIL(sb, fh_bh)->name + 1;
- pr_debug("AFFS: readdir(): dir_emit(\"%.*s\", "
+ pr_debug("readdir(): dir_emit(\"%.*s\", "
"ino=%u), hash=%d, f_pos=%x\n",
namelen, name, ino, hash_pos, (u32)ctx->pos);
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 8669b6ecddee..0270303388ee 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -45,7 +45,7 @@ const struct inode_operations affs_file_inode_operations = {
static int
affs_file_open(struct inode *inode, struct file *filp)
{
- pr_debug("AFFS: open(%lu,%d)\n",
+ pr_debug("open(%lu,%d)\n",
inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
atomic_inc(&AFFS_I(inode)->i_opencnt);
return 0;
@@ -54,7 +54,7 @@ affs_file_open(struct inode *inode, struct file *filp)
static int
affs_file_release(struct inode *inode, struct file *filp)
{
- pr_debug("AFFS: release(%lu, %d)\n",
+ pr_debug("release(%lu, %d)\n",
inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
if (atomic_dec_and_test(&AFFS_I(inode)->i_opencnt)) {
@@ -324,7 +324,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
struct buffer_head *ext_bh;
u32 ext;
- pr_debug("AFFS: get_block(%u, %lu)\n", (u32)inode->i_ino, (unsigned long)block);
+ pr_debug("%s(%u, %lu)\n",
+ __func__, (u32)inode->i_ino, (unsigned long)block);
BUG_ON(block > (sector_t)0x7fffffffUL);
@@ -498,34 +499,36 @@ affs_getemptyblk_ino(struct inode *inode, int block)
}
static int
-affs_do_readpage_ofs(struct file *file, struct page *page, unsigned from, unsigned to)
+affs_do_readpage_ofs(struct page *page, unsigned to)
{
struct inode *inode = page->mapping->host;
struct super_block *sb = inode->i_sb;
struct buffer_head *bh;
char *data;
+ unsigned pos = 0;
u32 bidx, boff, bsize;
u32 tmp;
- pr_debug("AFFS: read_page(%u, %ld, %d, %d)\n", (u32)inode->i_ino, page->index, from, to);
- BUG_ON(from > to || to > PAGE_CACHE_SIZE);
+ pr_debug("%s(%u, %ld, 0, %d)\n", __func__, (u32)inode->i_ino,
+ page->index, to);
+ BUG_ON(to > PAGE_CACHE_SIZE);
kmap(page);
data = page_address(page);
bsize = AFFS_SB(sb)->s_data_blksize;
- tmp = (page->index << PAGE_CACHE_SHIFT) + from;
+ tmp = page->index << PAGE_CACHE_SHIFT;
bidx = tmp / bsize;
boff = tmp % bsize;
- while (from < to) {
+ while (pos < to) {
bh = affs_bread_ino(inode, bidx, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
- tmp = min(bsize - boff, to - from);
- BUG_ON(from + tmp > to || tmp > bsize);
- memcpy(data + from, AFFS_DATA(bh) + boff, tmp);
+ tmp = min(bsize - boff, to - pos);
+ BUG_ON(pos + tmp > to || tmp > bsize);
+ memcpy(data + pos, AFFS_DATA(bh) + boff, tmp);
affs_brelse(bh);
bidx++;
- from += tmp;
+ pos += tmp;
boff = 0;
}
flush_dcache_page(page);
@@ -542,7 +545,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
u32 size, bsize;
u32 tmp;
- pr_debug("AFFS: extent_file(%u, %d)\n", (u32)inode->i_ino, newsize);
+ pr_debug("%s(%u, %d)\n", __func__, (u32)inode->i_ino, newsize);
bsize = AFFS_SB(sb)->s_data_blksize;
bh = NULL;
size = AFFS_I(inode)->mmu_private;
@@ -608,14 +611,14 @@ affs_readpage_ofs(struct file *file, struct page *page)
u32 to;
int err;
- pr_debug("AFFS: read_page(%u, %ld)\n", (u32)inode->i_ino, page->index);
+ pr_debug("%s(%u, %ld)\n", __func__, (u32)inode->i_ino, page->index);
to = PAGE_CACHE_SIZE;
if (((page->index + 1) << PAGE_CACHE_SHIFT) > inode->i_size) {
to = inode->i_size & ~PAGE_CACHE_MASK;
memset(page_address(page) + to, 0, PAGE_CACHE_SIZE - to);
}
- err = affs_do_readpage_ofs(file, page, 0, to);
+ err = affs_do_readpage_ofs(page, to);
if (!err)
SetPageUptodate(page);
unlock_page(page);
@@ -631,7 +634,8 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
pgoff_t index;
int err = 0;
- pr_debug("AFFS: write_begin(%u, %llu, %llu)\n", (u32)inode->i_ino, (unsigned long long)pos, (unsigned long long)pos + len);
+ pr_debug("%s(%u, %llu, %llu)\n", __func__, (u32)inode->i_ino,
+ (unsigned long long)pos, (unsigned long long)pos + len);
if (pos > AFFS_I(inode)->mmu_private) {
/* XXX: this probably leaves a too-big i_size in case of
* failure. Should really be updating i_size at write_end time
@@ -651,7 +655,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
return 0;
/* XXX: inefficient but safe in the face of short writes */
- err = affs_do_readpage_ofs(file, page, 0, PAGE_CACHE_SIZE);
+ err = affs_do_readpage_ofs(page, PAGE_CACHE_SIZE);
if (err) {
unlock_page(page);
page_cache_release(page);
@@ -680,7 +684,9 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
* due to write_begin.
*/
- pr_debug("AFFS: write_begin(%u, %llu, %llu)\n", (u32)inode->i_ino, (unsigned long long)pos, (unsigned long long)pos + len);
+ pr_debug("%s(%u, %llu, %llu)\n",
+ __func__, (u32)inode->i_ino, (unsigned long long)pos,
+ (unsigned long long)pos + len);
bsize = AFFS_SB(sb)->s_data_blksize;
data = page_address(page);
@@ -802,7 +808,7 @@ affs_free_prealloc(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
- pr_debug("AFFS: free_prealloc(ino=%lu)\n", inode->i_ino);
+ pr_debug("free_prealloc(ino=%lu)\n", inode->i_ino);
while (AFFS_I(inode)->i_pa_cnt) {
AFFS_I(inode)->i_pa_cnt--;
@@ -822,7 +828,7 @@ affs_truncate(struct inode *inode)
struct buffer_head *ext_bh;
int i;
- pr_debug("AFFS: truncate(inode=%d, oldsize=%u, newsize=%u)\n",
+ pr_debug("truncate(inode=%d, oldsize=%u, newsize=%u)\n",
(u32)inode->i_ino, (u32)AFFS_I(inode)->mmu_private, (u32)inode->i_size);
last_blk = 0;
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 96df91e8c334..bec2d1a0c91c 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -34,7 +34,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
if (!(inode->i_state & I_NEW))
return inode;
- pr_debug("AFFS: affs_iget(%lu)\n", inode->i_ino);
+ pr_debug("affs_iget(%lu)\n", inode->i_ino);
block = inode->i_ino;
bh = affs_bread(sb, block);
@@ -175,7 +175,7 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
uid_t uid;
gid_t gid;
- pr_debug("AFFS: write_inode(%lu)\n",inode->i_ino);
+ pr_debug("write_inode(%lu)\n", inode->i_ino);
if (!inode->i_nlink)
// possibly free block
@@ -220,7 +220,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr)
struct inode *inode = dentry->d_inode;
int error;
- pr_debug("AFFS: notify_change(%lu,0x%x)\n",inode->i_ino,attr->ia_valid);
+ pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid);
error = inode_change_ok(inode,attr);
if (error)
@@ -258,7 +258,8 @@ void
affs_evict_inode(struct inode *inode)
{
unsigned long cache_page;
- pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink);
+ pr_debug("evict_inode(ino=%lu, nlink=%u)\n",
+ inode->i_ino, inode->i_nlink);
truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
@@ -271,7 +272,7 @@ affs_evict_inode(struct inode *inode)
affs_free_prealloc(inode);
cache_page = (unsigned long)AFFS_I(inode)->i_lc;
if (cache_page) {
- pr_debug("AFFS: freeing ext cache\n");
+ pr_debug("freeing ext cache\n");
AFFS_I(inode)->i_lc = NULL;
AFFS_I(inode)->i_ac = NULL;
free_page(cache_page);
@@ -350,7 +351,8 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
u32 block = 0;
int retval;
- pr_debug("AFFS: add_entry(dir=%u, inode=%u, \"%*s\", type=%d)\n", (u32)dir->i_ino,
+ pr_debug("%s(dir=%u, inode=%u, \"%*s\", type=%d)\n",
+ __func__, (u32)dir->i_ino,
(u32)inode->i_ino, (int)dentry->d_name.len, dentry->d_name.name, type);
retval = -EIO;
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 6dae1ccd176d..035bd31556fc 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -190,7 +190,8 @@ affs_find_entry(struct inode *dir, struct dentry *dentry)
toupper_t toupper = affs_get_toupper(sb);
u32 key;
- pr_debug("AFFS: find_entry(\"%.*s\")\n", (int)dentry->d_name.len, dentry->d_name.name);
+ pr_debug("%s(\"%.*s\")\n",
+ __func__, (int)dentry->d_name.len, dentry->d_name.name);
bh = affs_bread(sb, dir->i_ino);
if (!bh)
@@ -218,7 +219,8 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
struct buffer_head *bh;
struct inode *inode = NULL;
- pr_debug("AFFS: lookup(\"%.*s\")\n",(int)dentry->d_name.len,dentry->d_name.name);
+ pr_debug("%s(\"%.*s\")\n",
+ __func__, (int)dentry->d_name.len, dentry->d_name.name);
affs_lock_dir(dir);
bh = affs_find_entry(dir, dentry);
@@ -248,9 +250,9 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
int
affs_unlink(struct inode *dir, struct dentry *dentry)
{
- pr_debug("AFFS: unlink(dir=%d, %lu \"%.*s\")\n", (u32)dir->i_ino,
- dentry->d_inode->i_ino,
- (int)dentry->d_name.len, dentry->d_name.name);
+ pr_debug("%s(dir=%d, %lu \"%.*s\")\n",
+ __func__, (u32)dir->i_ino, dentry->d_inode->i_ino,
+ (int)dentry->d_name.len, dentry->d_name.name);
return affs_remove_header(dentry);
}
@@ -262,7 +264,8 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
struct inode *inode;
int error;
- pr_debug("AFFS: create(%lu,\"%.*s\",0%ho)\n",dir->i_ino,(int)dentry->d_name.len,
+ pr_debug("%s(%lu,\"%.*s\",0%ho)\n",
+ __func__, dir->i_ino, (int)dentry->d_name.len,
dentry->d_name.name,mode);
inode = affs_new_inode(dir);
@@ -291,8 +294,9 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct inode *inode;
int error;
- pr_debug("AFFS: mkdir(%lu,\"%.*s\",0%ho)\n",dir->i_ino,
- (int)dentry->d_name.len,dentry->d_name.name,mode);
+ pr_debug("%s(%lu,\"%.*s\",0%ho)\n",
+ __func__, dir->i_ino, (int)dentry->d_name.len,
+ dentry->d_name.name, mode);
inode = affs_new_inode(dir);
if (!inode)
@@ -317,8 +321,8 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
int
affs_rmdir(struct inode *dir, struct dentry *dentry)
{
- pr_debug("AFFS: rmdir(dir=%u, %lu \"%.*s\")\n", (u32)dir->i_ino,
- dentry->d_inode->i_ino,
+ pr_debug("%s(dir=%u, %lu \"%.*s\")\n",
+ __func__, (u32)dir->i_ino, dentry->d_inode->i_ino,
(int)dentry->d_name.len, dentry->d_name.name);
return affs_remove_header(dentry);
@@ -334,8 +338,9 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
int i, maxlen, error;
char c, lc;
- pr_debug("AFFS: symlink(%lu,\"%.*s\" -> \"%s\")\n",dir->i_ino,
- (int)dentry->d_name.len,dentry->d_name.name,symname);
+ pr_debug("%s(%lu,\"%.*s\" -> \"%s\")\n",
+ __func__, dir->i_ino, (int)dentry->d_name.len,
+ dentry->d_name.name, symname);
maxlen = AFFS_SB(sb)->s_hashsize * sizeof(u32) - 1;
inode = affs_new_inode(dir);
@@ -404,7 +409,8 @@ affs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
- pr_debug("AFFS: link(%u, %u, \"%.*s\")\n", (u32)inode->i_ino, (u32)dir->i_ino,
+ pr_debug("%s(%u, %u, \"%.*s\")\n",
+ __func__, (u32)inode->i_ino, (u32)dir->i_ino,
(int)dentry->d_name.len,dentry->d_name.name);
return affs_add_entry(dir, inode, dentry, ST_LINKFILE);
@@ -418,9 +424,10 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct buffer_head *bh = NULL;
int retval;
- pr_debug("AFFS: rename(old=%u,\"%*s\" to new=%u,\"%*s\")\n",
- (u32)old_dir->i_ino, (int)old_dentry->d_name.len, old_dentry->d_name.name,
- (u32)new_dir->i_ino, (int)new_dentry->d_name.len, new_dentry->d_name.name);
+ pr_debug("%s(old=%u,\"%*s\" to new=%u,\"%*s\")\n",
+ __func__, (u32)old_dir->i_ino, (int)old_dentry->d_name.len,
+ old_dentry->d_name.name, (u32)new_dir->i_ino,
+ (int)new_dentry->d_name.len, new_dentry->d_name.name);
retval = affs_check_name(new_dentry->d_name.name,
new_dentry->d_name.len,
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 895ac7dc9dbf..51f1a95bff73 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -46,7 +46,7 @@ static void
affs_put_super(struct super_block *sb)
{
struct affs_sb_info *sbi = AFFS_SB(sb);
- pr_debug("AFFS: put_super()\n");
+ pr_debug("%s()\n", __func__);
cancel_delayed_work_sync(&sbi->sb_work);
}
@@ -220,7 +220,7 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
return 0;
if (n != 512 && n != 1024 && n != 2048
&& n != 4096) {
- printk ("AFFS: Invalid blocksize (512, 1024, 2048, 4096 allowed)\n");
+ pr_warn("Invalid blocksize (512, 1024, 2048, 4096 allowed)\n");
return 0;
}
*blocksize = n;
@@ -285,8 +285,8 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
/* Silently ignore the quota options */
break;
default:
- printk("AFFS: Unrecognized mount option \"%s\" "
- "or missing value\n", p);
+ pr_warn("Unrecognized mount option \"%s\" or missing value\n",
+ p);
return 0;
}
}
@@ -319,7 +319,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
save_mount_options(sb, data);
- pr_debug("AFFS: read_super(%s)\n",data ? (const char *)data : "no options");
+ pr_debug("read_super(%s)\n", data ? (const char *)data : "no options");
sb->s_magic = AFFS_SUPER_MAGIC;
sb->s_op = &affs_sops;
@@ -339,7 +339,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block,
&blocksize,&sbi->s_prefix,
sbi->s_volume, &mount_flags)) {
- printk(KERN_ERR "AFFS: Error parsing options\n");
+ pr_err("Error parsing options\n");
return -EINVAL;
}
/* N.B. after this point s_prefix must be released */
@@ -356,7 +356,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
*/
size = sb->s_bdev->bd_inode->i_size >> 9;
- pr_debug("AFFS: initial blocksize=%d, #blocks=%d\n", 512, size);
+ pr_debug("initial blocksize=%d, #blocks=%d\n", 512, size);
affs_set_blocksize(sb, PAGE_SIZE);
/* Try to find root block. Its location depends on the block size. */
@@ -371,7 +371,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_root_block = root_block;
if (root_block < 0)
sbi->s_root_block = (reserved + size - 1) / 2;
- pr_debug("AFFS: setting blocksize to %d\n", blocksize);
+ pr_debug("setting blocksize to %d\n", blocksize);
affs_set_blocksize(sb, blocksize);
sbi->s_partition_size = size;
@@ -386,7 +386,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
* block behind the calculated one. So we check this one, too.
*/
for (num_bm = 0; num_bm < 2; num_bm++) {
- pr_debug("AFFS: Dev %s, trying root=%u, bs=%d, "
+ pr_debug("Dev %s, trying root=%u, bs=%d, "
"size=%d, reserved=%d\n",
sb->s_id,
sbi->s_root_block + num_bm,
@@ -407,8 +407,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
}
}
if (!silent)
- printk(KERN_ERR "AFFS: No valid root block on device %s\n",
- sb->s_id);
+ pr_err("No valid root block on device %s\n", sb->s_id);
return -EINVAL;
/* N.B. after this point bh must be released */
@@ -420,7 +419,7 @@ got_root:
/* Find out which kind of FS we have */
boot_bh = sb_bread(sb, 0);
if (!boot_bh) {
- printk(KERN_ERR "AFFS: Cannot read boot block\n");
+ pr_err("Cannot read boot block\n");
return -EINVAL;
}
memcpy(sig, boot_bh->b_data, 4);
@@ -433,8 +432,7 @@ got_root:
*/
if ((chksum == FS_DCFFS || chksum == MUFS_DCFFS || chksum == FS_DCOFS
|| chksum == MUFS_DCOFS) && !(sb->s_flags & MS_RDONLY)) {
- printk(KERN_NOTICE "AFFS: Dircache FS - mounting %s read only\n",
- sb->s_id);
+ pr_notice("Dircache FS - mounting %s read only\n", sb->s_id);
sb->s_flags |= MS_RDONLY;
}
switch (chksum) {
@@ -468,14 +466,14 @@ got_root:
sb->s_flags |= MS_NOEXEC;
break;
default:
- printk(KERN_ERR "AFFS: Unknown filesystem on device %s: %08X\n",
- sb->s_id, chksum);
+ pr_err("Unknown filesystem on device %s: %08X\n",
+ sb->s_id, chksum);
return -EINVAL;
}
if (mount_flags & SF_VERBOSE) {
u8 len = AFFS_ROOT_TAIL(sb, root_bh)->disk_name[0];
- printk(KERN_NOTICE "AFFS: Mounting volume \"%.*s\": Type=%.3s\\%c, Blocksize=%d\n",
+ pr_notice("Mounting volume \"%.*s\": Type=%.3s\\%c, Blocksize=%d\n",
len > 31 ? 31 : len,
AFFS_ROOT_TAIL(sb, root_bh)->disk_name + 1,
sig, sig[3] + '0', blocksize);
@@ -506,11 +504,11 @@ got_root:
sb->s_root = d_make_root(root_inode);
if (!sb->s_root) {
- printk(KERN_ERR "AFFS: Get root inode failed\n");
+ pr_err("AFFS: Get root inode failed\n");
return -ENOMEM;
}
- pr_debug("AFFS: s_flags=%lX\n",sb->s_flags);
+ pr_debug("s_flags=%lX\n", sb->s_flags);
return 0;
}
@@ -530,7 +528,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
char volume[32];
char *prefix = NULL;
- pr_debug("AFFS: remount(flags=0x%x,opts=\"%s\")\n",*flags,data);
+ pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
sync_filesystem(sb);
*flags |= MS_NODIRATIME;
@@ -578,8 +576,9 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
int free;
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
- pr_debug("AFFS: statfs() partsize=%d, reserved=%d\n",AFFS_SB(sb)->s_partition_size,
- AFFS_SB(sb)->s_reserved);
+ pr_debug("%s() partsize=%d, reserved=%d\n",
+ __func__, AFFS_SB(sb)->s_partition_size,
+ AFFS_SB(sb)->s_reserved);
free = affs_count_free_blocks(sb);
buf->f_type = AFFS_SUPER_MAGIC;
diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c
index ee00f08c4f53..f39b71c3981e 100644
--- a/fs/affs/symlink.c
+++ b/fs/affs/symlink.c
@@ -21,7 +21,7 @@ static int affs_symlink_readpage(struct file *file, struct page *page)
char c;
char lc;
- pr_debug("AFFS: follow_link(ino=%lu)\n",inode->i_ino);
+ pr_debug("follow_link(ino=%lu)\n", inode->i_ino);
err = -EIO;
bh = affs_bread(inode->i_sb, inode->i_ino);
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index a8cf2cff836c..4baf1d2b39e4 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -555,10 +555,6 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
return -ENOLCK;
/* we're simulating flock() locks using posix locks on the server */
- fl->fl_owner = (fl_owner_t) file;
- fl->fl_start = 0;
- fl->fl_end = OFFSET_MAX;
-
if (fl->fl_type == F_UNLCK)
return afs_do_unlk(file, fl);
return afs_do_setlk(file, fl);
diff --git a/fs/attr.c b/fs/attr.c
index 5d4e59d56e85..6530ced19697 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
if ((ia_valid & ATTR_UID) &&
(!uid_eq(current_fsuid(), inode->i_uid) ||
!uid_eq(attr->ia_uid, inode->i_uid)) &&
- !inode_capable(inode, CAP_CHOWN))
+ !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
return -EPERM;
/* Make sure caller can chgrp. */
if ((ia_valid & ATTR_GID) &&
(!uid_eq(current_fsuid(), inode->i_uid) ||
(!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
- !inode_capable(inode, CAP_CHOWN))
+ !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
return -EPERM;
/* Make sure a caller can chmod. */
@@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
/* Also check the setgid bit! */
if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
inode->i_gid) &&
- !inode_capable(inode, CAP_FSETID))
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID))
attr->ia_mode &= ~S_ISGID;
}
@@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
umode_t mode = attr->ia_mode;
if (!in_group_p(inode->i_gid) &&
- !inode_capable(inode, CAP_FSETID))
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID))
mode &= ~S_ISGID;
inode->i_mode = mode;
}
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 232e03d4780d..5b570b6efa28 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -737,7 +737,7 @@ MODULE_ALIAS_MISCDEV(AUTOFS_MINOR);
MODULE_ALIAS("devname:autofs");
/* Register/deregister misc character device */
-int autofs_dev_ioctl_init(void)
+int __init autofs_dev_ioctl_init(void)
{
int r;
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index a2cd305a993a..9c7faa8a9288 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -318,7 +318,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
* befs_find_key - Search for a key within a node
* @sb: Filesystem superblock
* @node: Node to find the key within
- * @key: Keystring to search for
+ * @findkey: Keystring to search for
* @value: If key is found, the value stored with the key is put here
*
* finds exact match if one exists, and returns BEFS_BT_MATCH
@@ -405,7 +405,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
* Heres how it works: Key_no is the index of the key/value pair to
* return in keybuf/value.
* Bufsize is the size of keybuf (BEFS_NAME_LEN+1 is a good size). Keysize is
- * the number of charecters in the key (just a convenience).
+ * the number of characters in the key (just a convenience).
*
* Algorithm:
* Get the first leafnode of the tree. See if the requested key is in that
@@ -502,12 +502,11 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
"for key of size %d", __func__, bufsize, keylen);
brelse(this_node->bh);
goto error_alloc;
- };
+ }
- strncpy(keybuf, keystart, keylen);
+ strlcpy(keybuf, keystart, keylen + 1);
*value = fs64_to_cpu(sb, valarray[cur_key]);
*keysize = keylen;
- keybuf[keylen] = '\0';
befs_debug(sb, "Read [%llu,%d]: Key \"%.*s\", Value %llu", node_off,
cur_key, keylen, keybuf, *value);
@@ -707,7 +706,7 @@ befs_bt_get_key(struct super_block *sb, befs_btree_node * node,
* @key1: pointer to the first key to be compared
* @keylen1: length in bytes of key1
* @key2: pointer to the second key to be compared
- * @kelen2: length in bytes of key2
+ * @keylen2: length in bytes of key2
*
* Returns 0 if @key1 and @key2 are equal.
* Returns >0 if @key1 is greater.
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index c467bebd50af..1e8e0b8d8836 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -116,7 +116,7 @@ befs_fblock2brun(struct super_block *sb, befs_data_stream * data,
* befs_read_lsmylink - read long symlink from datastream.
* @sb: Filesystem superblock
* @ds: Datastrem to read from
- * @buf: Buffer in which to place long symlink data
+ * @buff: Buffer in which to place long symlink data
* @len: Length of the long symlink in bytes
*
* Returns the number of bytes read
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index d626756ff721..a16fbd4e8241 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -133,14 +133,6 @@ befs_get_block(struct inode *inode, sector_t block,
befs_debug(sb, "---> befs_get_block() for inode %lu, block %ld",
(unsigned long)inode->i_ino, (long)block);
-
- if (block < 0) {
- befs_error(sb, "befs_get_block() was asked for a block "
- "number less than zero: block %ld in inode %lu",
- (long)block, (unsigned long)inode->i_ino);
- return -EIO;
- }
-
if (create) {
befs_error(sb, "befs_get_block() was asked to write to "
"block %ld in inode %lu", (long)block,
@@ -396,9 +388,8 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
if (S_ISLNK(inode->i_mode) && !(befs_ino->i_flags & BEFS_LONG_SYMLINK)){
inode->i_size = 0;
inode->i_blocks = befs_sb->block_size / VFS_BLOCK_SIZE;
- strncpy(befs_ino->i_data.symlink, raw_inode->data.symlink,
- BEFS_SYMLINK_LEN - 1);
- befs_ino->i_data.symlink[BEFS_SYMLINK_LEN - 1] = '\0';
+ strlcpy(befs_ino->i_data.symlink, raw_inode->data.symlink,
+ BEFS_SYMLINK_LEN);
} else {
int num_blks;
@@ -591,21 +582,21 @@ befs_utf2nls(struct super_block *sb, const char *in,
/**
* befs_nls2utf - Convert NLS string to utf8 encodeing
* @sb: Superblock
- * @src: Input string buffer in NLS format
- * @srclen: Length of input string in bytes
- * @dest: The output string in UTF-8 format
- * @destlen: Length of the output buffer
+ * @in: Input string buffer in NLS format
+ * @in_len: Length of input string in bytes
+ * @out: The output string in UTF-8 format
+ * @out_len: Length of the output buffer
*
- * Converts input string @src, which is in the format of the loaded NLS map,
+ * Converts input string @in, which is in the format of the loaded NLS map,
* into a utf8 string.
*
- * The destination string @dest is allocated by this function and the caller is
+ * The destination string @out is allocated by this function and the caller is
* responsible for freeing it with kfree()
*
- * On return, *@destlen is the length of @dest in bytes.
+ * On return, *@out_len is the length of @out in bytes.
*
* On success, the return value is the number of utf8 characters written to
- * the output buffer @dest.
+ * the output buffer @out.
*
* On Failure, a negative number coresponding to the error code is returned.
*/
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index aa3cb626671e..3892c1a23241 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1108,6 +1108,14 @@ static bool always_dump_vma(struct vm_area_struct *vma)
/* Any vsyscall mappings? */
if (vma == get_gate_vma(vma->vm_mm))
return true;
+
+ /*
+ * Assume that all vmas with a .name op should always be dumped.
+ * If this changes, a new vm_ops field can easily be added.
+ */
+ if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
+ return true;
+
/*
* arch_vma_name() returns non-NULL for special architecture mappings,
* such as vDSO sections.
@@ -1686,7 +1694,7 @@ static size_t get_note_info_size(struct elf_note_info *info)
static int write_note_info(struct elf_note_info *info,
struct coredump_params *cprm)
{
- bool first = 1;
+ bool first = true;
struct elf_thread_core_info *t = info->thread;
do {
@@ -1710,7 +1718,7 @@ static int write_note_info(struct elf_note_info *info,
!writenote(&t->notes[i], cprm))
return 0;
- first = 0;
+ first = false;
t = t->next;
} while (t);
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index d50bbe59da1e..f723cd3a455c 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -380,7 +380,7 @@ failed:
/****************************************************************************/
-void old_reloc(unsigned long rl)
+static void old_reloc(unsigned long rl)
{
#ifdef DEBUG
char *segment[] = { "TEXT", "DATA", "BSS", "*UNKNOWN*" };
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
deleted file mode 100644
index 1c2ce0c87711..000000000000
--- a/fs/bio-integrity.c
+++ /dev/null
@@ -1,657 +0,0 @@
-/*
- * bio-integrity.c - bio data integrity extensions
- *
- * Copyright (C) 2007, 2008, 2009 Oracle Corporation
- * Written by: Martin K. Petersen <martin.petersen@oracle.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING. If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
- * USA.
- *
- */
-
-#include <linux/blkdev.h>
-#include <linux/mempool.h>
-#include <linux/export.h>
-#include <linux/bio.h>
-#include <linux/workqueue.h>
-#include <linux/slab.h>
-
-#define BIP_INLINE_VECS 4
-
-static struct kmem_cache *bip_slab;
-static struct workqueue_struct *kintegrityd_wq;
-
-/**
- * bio_integrity_alloc - Allocate integrity payload and attach it to bio
- * @bio: bio to attach integrity metadata to
- * @gfp_mask: Memory allocation mask
- * @nr_vecs: Number of integrity metadata scatter-gather elements
- *
- * Description: This function prepares a bio for attaching integrity
- * metadata. nr_vecs specifies the maximum number of pages containing
- * integrity metadata that can be attached.
- */
-struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
- gfp_t gfp_mask,
- unsigned int nr_vecs)
-{
- struct bio_integrity_payload *bip;
- struct bio_set *bs = bio->bi_pool;
- unsigned long idx = BIO_POOL_NONE;
- unsigned inline_vecs;
-
- if (!bs) {
- bip = kmalloc(sizeof(struct bio_integrity_payload) +
- sizeof(struct bio_vec) * nr_vecs, gfp_mask);
- inline_vecs = nr_vecs;
- } else {
- bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
- inline_vecs = BIP_INLINE_VECS;
- }
-
- if (unlikely(!bip))
- return NULL;
-
- memset(bip, 0, sizeof(*bip));
-
- if (nr_vecs > inline_vecs) {
- bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
- bs->bvec_integrity_pool);
- if (!bip->bip_vec)
- goto err;
- } else {
- bip->bip_vec = bip->bip_inline_vecs;
- }
-
- bip->bip_slab = idx;
- bip->bip_bio = bio;
- bio->bi_integrity = bip;
-
- return bip;
-err:
- mempool_free(bip, bs->bio_integrity_pool);
- return NULL;
-}
-EXPORT_SYMBOL(bio_integrity_alloc);
-
-/**
- * bio_integrity_free - Free bio integrity payload
- * @bio: bio containing bip to be freed
- *
- * Description: Used to free the integrity portion of a bio. Usually
- * called from bio_free().
- */
-void bio_integrity_free(struct bio *bio)
-{
- struct bio_integrity_payload *bip = bio->bi_integrity;
- struct bio_set *bs = bio->bi_pool;
-
- if (bip->bip_owns_buf)
- kfree(bip->bip_buf);
-
- if (bs) {
- if (bip->bip_slab != BIO_POOL_NONE)
- bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
- bip->bip_slab);
-
- mempool_free(bip, bs->bio_integrity_pool);
- } else {
- kfree(bip);
- }
-
- bio->bi_integrity = NULL;
-}
-EXPORT_SYMBOL(bio_integrity_free);
-
-static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip)
-{
- if (bip->bip_slab == BIO_POOL_NONE)
- return BIP_INLINE_VECS;
-
- return bvec_nr_vecs(bip->bip_slab);
-}
-
-/**
- * bio_integrity_add_page - Attach integrity metadata
- * @bio: bio to update
- * @page: page containing integrity metadata
- * @len: number of bytes of integrity metadata in page
- * @offset: start offset within page
- *
- * Description: Attach a page containing integrity metadata to bio.
- */
-int bio_integrity_add_page(struct bio *bio, struct page *page,
- unsigned int len, unsigned int offset)
-{
- struct bio_integrity_payload *bip = bio->bi_integrity;
- struct bio_vec *iv;
-
- if (bip->bip_vcnt >= bip_integrity_vecs(bip)) {
- printk(KERN_ERR "%s: bip_vec full\n", __func__);
- return 0;
- }
-
- iv = bip->bip_vec + bip->bip_vcnt;
-
- iv->bv_page = page;
- iv->bv_len = len;
- iv->bv_offset = offset;
- bip->bip_vcnt++;
-
- return len;
-}
-EXPORT_SYMBOL(bio_integrity_add_page);
-
-static int bdev_integrity_enabled(struct block_device *bdev, int rw)
-{
- struct blk_integrity *bi = bdev_get_integrity(bdev);
-
- if (bi == NULL)
- return 0;
-
- if (rw == READ && bi->verify_fn != NULL &&
- (bi->flags & INTEGRITY_FLAG_READ))
- return 1;
-
- if (rw == WRITE && bi->generate_fn != NULL &&
- (bi->flags & INTEGRITY_FLAG_WRITE))
- return 1;
-
- return 0;
-}
-
-/**
- * bio_integrity_enabled - Check whether integrity can be passed
- * @bio: bio to check
- *
- * Description: Determines whether bio_integrity_prep() can be called
- * on this bio or not. bio data direction and target device must be
- * set prior to calling. The functions honors the write_generate and
- * read_verify flags in sysfs.
- */
-int bio_integrity_enabled(struct bio *bio)
-{
- if (!bio_is_rw(bio))
- return 0;
-
- /* Already protected? */
- if (bio_integrity(bio))
- return 0;
-
- return bdev_integrity_enabled(bio->bi_bdev, bio_data_dir(bio));
-}
-EXPORT_SYMBOL(bio_integrity_enabled);
-
-/**
- * bio_integrity_hw_sectors - Convert 512b sectors to hardware ditto
- * @bi: blk_integrity profile for device
- * @sectors: Number of 512 sectors to convert
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the hardware
- * sector size of the storage device. Convert the block layer sectors
- * to physical sectors.
- */
-static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
- unsigned int sectors)
-{
- /* At this point there are only 512b or 4096b DIF/EPP devices */
- if (bi->sector_size == 4096)
- return sectors >>= 3;
-
- return sectors;
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
-}
-
-/**
- * bio_integrity_tag_size - Retrieve integrity tag space
- * @bio: bio to inspect
- *
- * Description: Returns the maximum number of tag bytes that can be
- * attached to this bio. Filesystems can use this to determine how
- * much metadata to attach to an I/O.
- */
-unsigned int bio_integrity_tag_size(struct bio *bio)
-{
- struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-
- BUG_ON(bio->bi_iter.bi_size == 0);
-
- return bi->tag_size * (bio->bi_iter.bi_size / bi->sector_size);
-}
-EXPORT_SYMBOL(bio_integrity_tag_size);
-
-static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
- int set)
-{
- struct bio_integrity_payload *bip = bio->bi_integrity;
- struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- unsigned int nr_sectors;
-
- BUG_ON(bip->bip_buf == NULL);
-
- if (bi->tag_size == 0)
- return -1;
-
- nr_sectors = bio_integrity_hw_sectors(bi,
- DIV_ROUND_UP(len, bi->tag_size));
-
- if (nr_sectors * bi->tuple_size > bip->bip_iter.bi_size) {
- printk(KERN_ERR "%s: tag too big for bio: %u > %u\n", __func__,
- nr_sectors * bi->tuple_size, bip->bip_iter.bi_size);
- return -1;
- }
-
- if (set)
- bi->set_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
- else
- bi->get_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-
- return 0;
-}
-
-/**
- * bio_integrity_set_tag - Attach a tag buffer to a bio
- * @bio: bio to attach buffer to
- * @tag_buf: Pointer to a buffer containing tag data
- * @len: Length of the included buffer
- *
- * Description: Use this function to tag a bio by leveraging the extra
- * space provided by devices formatted with integrity protection. The
- * size of the integrity buffer must be <= to the size reported by
- * bio_integrity_tag_size().
- */
-int bio_integrity_set_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
- BUG_ON(bio_data_dir(bio) != WRITE);
-
- return bio_integrity_tag(bio, tag_buf, len, 1);
-}
-EXPORT_SYMBOL(bio_integrity_set_tag);
-
-/**
- * bio_integrity_get_tag - Retrieve a tag buffer from a bio
- * @bio: bio to retrieve buffer from
- * @tag_buf: Pointer to a buffer for the tag data
- * @len: Length of the target buffer
- *
- * Description: Use this function to retrieve the tag buffer from a
- * completed I/O. The size of the integrity buffer must be <= to the
- * size reported by bio_integrity_tag_size().
- */
-int bio_integrity_get_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
- BUG_ON(bio_data_dir(bio) != READ);
-
- return bio_integrity_tag(bio, tag_buf, len, 0);
-}
-EXPORT_SYMBOL(bio_integrity_get_tag);
-
-/**
- * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio
- * @bio: bio to generate/verify integrity metadata for
- * @operate: operate number, 1 for generate, 0 for verify
- */
-static int bio_integrity_generate_verify(struct bio *bio, int operate)
-{
- struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- struct blk_integrity_exchg bix;
- struct bio_vec *bv;
- sector_t sector;
- unsigned int sectors, ret = 0, i;
- void *prot_buf = bio->bi_integrity->bip_buf;
-
- if (operate)
- sector = bio->bi_iter.bi_sector;
- else
- sector = bio->bi_integrity->bip_iter.bi_sector;
-
- bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
- bix.sector_size = bi->sector_size;
-
- bio_for_each_segment_all(bv, bio, i) {
- 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;
- bix.sector = sector;
-
- if (operate)
- bi->generate_fn(&bix);
- else {
- ret = bi->verify_fn(&bix);
- if (ret) {
- kunmap_atomic(kaddr);
- return ret;
- }
- }
-
- sectors = bv->bv_len / bi->sector_size;
- sector += sectors;
- prot_buf += sectors * bi->tuple_size;
-
- kunmap_atomic(kaddr);
- }
- return ret;
-}
-
-/**
- * bio_integrity_generate - Generate integrity metadata for a bio
- * @bio: bio to generate integrity metadata for
- *
- * Description: Generates integrity metadata for a bio by calling the
- * block device's generation callback function. The bio must have a
- * bip attached with enough room to accommodate the generated
- * integrity metadata.
- */
-static void bio_integrity_generate(struct bio *bio)
-{
- bio_integrity_generate_verify(bio, 1);
-}
-
-static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
-{
- if (bi)
- return bi->tuple_size;
-
- return 0;
-}
-
-/**
- * bio_integrity_prep - Prepare bio for integrity I/O
- * @bio: bio to prepare
- *
- * Description: Allocates a buffer for integrity metadata, maps the
- * pages and attaches them to a bio. The bio must have data
- * direction, target device and start sector set priot to calling. In
- * the WRITE case, integrity metadata will be generated using the
- * block device's integrity function. In the READ case, the buffer
- * will be prepared for DMA and a suitable end_io handler set up.
- */
-int bio_integrity_prep(struct bio *bio)
-{
- struct bio_integrity_payload *bip;
- struct blk_integrity *bi;
- struct request_queue *q;
- void *buf;
- unsigned long start, end;
- unsigned int len, nr_pages;
- unsigned int bytes, offset, i;
- unsigned int sectors;
-
- bi = bdev_get_integrity(bio->bi_bdev);
- q = bdev_get_queue(bio->bi_bdev);
- BUG_ON(bi == NULL);
- BUG_ON(bio_integrity(bio));
-
- sectors = bio_integrity_hw_sectors(bi, bio_sectors(bio));
-
- /* Allocate kernel buffer for protection data */
- len = sectors * blk_integrity_tuple_size(bi);
- buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
- if (unlikely(buf == NULL)) {
- printk(KERN_ERR "could not allocate integrity buffer\n");
- return -ENOMEM;
- }
-
- end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- start = ((unsigned long) buf) >> PAGE_SHIFT;
- nr_pages = end - start;
-
- /* Allocate bio integrity payload and integrity vectors */
- bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
- if (unlikely(bip == NULL)) {
- printk(KERN_ERR "could not allocate data integrity bioset\n");
- kfree(buf);
- return -EIO;
- }
-
- bip->bip_owns_buf = 1;
- bip->bip_buf = buf;
- bip->bip_iter.bi_size = len;
- bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
-
- /* Map it */
- offset = offset_in_page(buf);
- for (i = 0 ; i < nr_pages ; i++) {
- int ret;
- bytes = PAGE_SIZE - offset;
-
- if (len <= 0)
- break;
-
- if (bytes > len)
- bytes = len;
-
- ret = bio_integrity_add_page(bio, virt_to_page(buf),
- bytes, offset);
-
- if (ret == 0)
- return 0;
-
- if (ret < bytes)
- break;
-
- buf += bytes;
- len -= bytes;
- offset = 0;
- }
-
- /* Install custom I/O completion handler if read verify is enabled */
- if (bio_data_dir(bio) == READ) {
- bip->bip_end_io = bio->bi_end_io;
- bio->bi_end_io = bio_integrity_endio;
- }
-
- /* Auto-generate integrity metadata if this is a write */
- if (bio_data_dir(bio) == WRITE)
- bio_integrity_generate(bio);
-
- return 0;
-}
-EXPORT_SYMBOL(bio_integrity_prep);
-
-/**
- * bio_integrity_verify - Verify integrity metadata for a bio
- * @bio: bio to verify
- *
- * Description: This function is called to verify the integrity of a
- * bio. The data in the bio io_vec is compared to the integrity
- * metadata returned by the HBA.
- */
-static int bio_integrity_verify(struct bio *bio)
-{
- return bio_integrity_generate_verify(bio, 0);
-}
-
-/**
- * bio_integrity_verify_fn - Integrity I/O completion worker
- * @work: Work struct stored in bio to be verified
- *
- * Description: This workqueue function is called to complete a READ
- * request. The function verifies the transferred integrity metadata
- * and then calls the original bio end_io function.
- */
-static void bio_integrity_verify_fn(struct work_struct *work)
-{
- struct bio_integrity_payload *bip =
- container_of(work, struct bio_integrity_payload, bip_work);
- struct bio *bio = bip->bip_bio;
- int error;
-
- error = bio_integrity_verify(bio);
-
- /* Restore original bio completion handler */
- bio->bi_end_io = bip->bip_end_io;
- bio_endio_nodec(bio, error);
-}
-
-/**
- * bio_integrity_endio - Integrity I/O completion function
- * @bio: Protected bio
- * @error: Pointer to errno
- *
- * Description: Completion for integrity I/O
- *
- * Normally I/O completion is done in interrupt context. However,
- * verifying I/O integrity is a time-consuming task which must be run
- * in process context. This function postpones completion
- * accordingly.
- */
-void bio_integrity_endio(struct bio *bio, int error)
-{
- struct bio_integrity_payload *bip = bio->bi_integrity;
-
- BUG_ON(bip->bip_bio != bio);
-
- /* In case of an I/O error there is no point in verifying the
- * integrity metadata. Restore original bio end_io handler
- * and run it.
- */
- if (error) {
- bio->bi_end_io = bip->bip_end_io;
- bio_endio(bio, error);
-
- return;
- }
-
- INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
- queue_work(kintegrityd_wq, &bip->bip_work);
-}
-EXPORT_SYMBOL(bio_integrity_endio);
-
-/**
- * bio_integrity_advance - Advance integrity vector
- * @bio: bio whose integrity vector to update
- * @bytes_done: number of data bytes that have been completed
- *
- * Description: This function calculates how many integrity bytes the
- * number of completed data bytes correspond to and advances the
- * integrity vector accordingly.
- */
-void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
-{
- struct bio_integrity_payload *bip = bio->bi_integrity;
- struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
-
- bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes);
-}
-EXPORT_SYMBOL(bio_integrity_advance);
-
-/**
- * bio_integrity_trim - Trim integrity vector
- * @bio: bio whose integrity vector to update
- * @offset: offset to first data sector
- * @sectors: number of data sectors
- *
- * Description: Used to trim the integrity vector in a cloned bio.
- * The ivec will be advanced corresponding to 'offset' data sectors
- * and the length will be truncated corresponding to 'len' data
- * sectors.
- */
-void bio_integrity_trim(struct bio *bio, unsigned int offset,
- unsigned int sectors)
-{
- struct bio_integrity_payload *bip = bio->bi_integrity;
- struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-
- bio_integrity_advance(bio, offset << 9);
- bip->bip_iter.bi_size = bio_integrity_bytes(bi, sectors);
-}
-EXPORT_SYMBOL(bio_integrity_trim);
-
-/**
- * bio_integrity_clone - Callback for cloning bios with integrity metadata
- * @bio: New bio
- * @bio_src: Original bio
- * @gfp_mask: Memory allocation mask
- *
- * Description: Called to allocate a bip when cloning a bio
- */
-int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
- gfp_t gfp_mask)
-{
- struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
- struct bio_integrity_payload *bip;
-
- BUG_ON(bip_src == NULL);
-
- bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
-
- if (bip == NULL)
- return -EIO;
-
- memcpy(bip->bip_vec, bip_src->bip_vec,
- bip_src->bip_vcnt * sizeof(struct bio_vec));
-
- bip->bip_vcnt = bip_src->bip_vcnt;
- bip->bip_iter = bip_src->bip_iter;
-
- return 0;
-}
-EXPORT_SYMBOL(bio_integrity_clone);
-
-int bioset_integrity_create(struct bio_set *bs, int pool_size)
-{
- if (bs->bio_integrity_pool)
- return 0;
-
- bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab);
- if (!bs->bio_integrity_pool)
- return -1;
-
- bs->bvec_integrity_pool = biovec_create_pool(bs, pool_size);
- if (!bs->bvec_integrity_pool) {
- mempool_destroy(bs->bio_integrity_pool);
- return -1;
- }
-
- return 0;
-}
-EXPORT_SYMBOL(bioset_integrity_create);
-
-void bioset_integrity_free(struct bio_set *bs)
-{
- if (bs->bio_integrity_pool)
- mempool_destroy(bs->bio_integrity_pool);
-
- if (bs->bvec_integrity_pool)
- mempool_destroy(bs->bvec_integrity_pool);
-}
-EXPORT_SYMBOL(bioset_integrity_free);
-
-void __init bio_integrity_init(void)
-{
- /*
- * kintegrityd won't block much but may burn a lot of CPU cycles.
- * Make it highpri CPU intensive wq with max concurrency of 1.
- */
- kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
- if (!kintegrityd_wq)
- panic("Failed to create kintegrityd\n");
-
- bip_slab = kmem_cache_create("bio_integrity_payload",
- sizeof(struct bio_integrity_payload) +
- sizeof(struct bio_vec) * BIP_INLINE_VECS,
- 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
- if (!bip_slab)
- panic("Failed to create slab\n");
-}
diff --git a/fs/bio.c b/fs/bio.c
deleted file mode 100644
index 6f0362b77806..000000000000
--- a/fs/bio.c
+++ /dev/null
@@ -1,2037 +0,0 @@
-/*
- * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public Licens
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-
- *
- */
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/uio.h>
-#include <linux/iocontext.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/mempool.h>
-#include <linux/workqueue.h>
-#include <linux/cgroup.h>
-#include <scsi/sg.h> /* for struct sg_iovec */
-
-#include <trace/events/block.h>
-
-/*
- * Test patch to inline a certain number of bi_io_vec's inside the bio
- * itself, to shrink a bio data allocation from two mempool calls to one
- */
-#define BIO_INLINE_VECS 4
-
-/*
- * if you change this list, also change bvec_alloc or things will
- * break badly! cannot be bigger than what you can fit into an
- * unsigned short
- */
-#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
-static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
- BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
-};
-#undef BV
-
-/*
- * fs_bio_set is the bio_set containing bio and iovec memory pools used by
- * IO code that does not need private memory pools.
- */
-struct bio_set *fs_bio_set;
-EXPORT_SYMBOL(fs_bio_set);
-
-/*
- * Our slab pool management
- */
-struct bio_slab {
- struct kmem_cache *slab;
- unsigned int slab_ref;
- unsigned int slab_size;
- char name[8];
-};
-static DEFINE_MUTEX(bio_slab_lock);
-static struct bio_slab *bio_slabs;
-static unsigned int bio_slab_nr, bio_slab_max;
-
-static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
-{
- unsigned int sz = sizeof(struct bio) + extra_size;
- struct kmem_cache *slab = NULL;
- struct bio_slab *bslab, *new_bio_slabs;
- unsigned int new_bio_slab_max;
- unsigned int i, entry = -1;
-
- mutex_lock(&bio_slab_lock);
-
- i = 0;
- while (i < bio_slab_nr) {
- bslab = &bio_slabs[i];
-
- if (!bslab->slab && entry == -1)
- entry = i;
- else if (bslab->slab_size == sz) {
- slab = bslab->slab;
- bslab->slab_ref++;
- break;
- }
- i++;
- }
-
- if (slab)
- goto out_unlock;
-
- if (bio_slab_nr == bio_slab_max && entry == -1) {
- new_bio_slab_max = bio_slab_max << 1;
- new_bio_slabs = krealloc(bio_slabs,
- new_bio_slab_max * sizeof(struct bio_slab),
- GFP_KERNEL);
- if (!new_bio_slabs)
- goto out_unlock;
- bio_slab_max = new_bio_slab_max;
- bio_slabs = new_bio_slabs;
- }
- if (entry == -1)
- entry = bio_slab_nr++;
-
- bslab = &bio_slabs[entry];
-
- snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry);
- slab = kmem_cache_create(bslab->name, sz, 0, SLAB_HWCACHE_ALIGN, NULL);
- if (!slab)
- goto out_unlock;
-
- bslab->slab = slab;
- bslab->slab_ref = 1;
- bslab->slab_size = sz;
-out_unlock:
- mutex_unlock(&bio_slab_lock);
- return slab;
-}
-
-static void bio_put_slab(struct bio_set *bs)
-{
- struct bio_slab *bslab = NULL;
- unsigned int i;
-
- mutex_lock(&bio_slab_lock);
-
- for (i = 0; i < bio_slab_nr; i++) {
- if (bs->bio_slab == bio_slabs[i].slab) {
- bslab = &bio_slabs[i];
- break;
- }
- }
-
- if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n"))
- goto out;
-
- WARN_ON(!bslab->slab_ref);
-
- if (--bslab->slab_ref)
- goto out;
-
- kmem_cache_destroy(bslab->slab);
- bslab->slab = NULL;
-
-out:
- mutex_unlock(&bio_slab_lock);
-}
-
-unsigned int bvec_nr_vecs(unsigned short idx)
-{
- return bvec_slabs[idx].nr_vecs;
-}
-
-void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
-{
- BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);
-
- if (idx == BIOVEC_MAX_IDX)
- mempool_free(bv, pool);
- else {
- struct biovec_slab *bvs = bvec_slabs + idx;
-
- kmem_cache_free(bvs->slab, bv);
- }
-}
-
-struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
- mempool_t *pool)
-{
- struct bio_vec *bvl;
-
- /*
- * see comment near bvec_array define!
- */
- switch (nr) {
- case 1:
- *idx = 0;
- break;
- case 2 ... 4:
- *idx = 1;
- break;
- case 5 ... 16:
- *idx = 2;
- break;
- case 17 ... 64:
- *idx = 3;
- break;
- case 65 ... 128:
- *idx = 4;
- break;
- case 129 ... BIO_MAX_PAGES:
- *idx = 5;
- break;
- default:
- return NULL;
- }
-
- /*
- * idx now points to the pool we want to allocate from. only the
- * 1-vec entry pool is mempool backed.
- */
- if (*idx == BIOVEC_MAX_IDX) {
-fallback:
- bvl = mempool_alloc(pool, gfp_mask);
- } else {
- struct biovec_slab *bvs = bvec_slabs + *idx;
- gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
-
- /*
- * Make this allocation restricted and don't dump info on
- * allocation failures, since we'll fallback to the mempool
- * in case of failure.
- */
- __gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
-
- /*
- * Try a slab allocation. If this fails and __GFP_WAIT
- * is set, retry with the 1-entry mempool
- */
- bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
- if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) {
- *idx = BIOVEC_MAX_IDX;
- goto fallback;
- }
- }
-
- return bvl;
-}
-
-static void __bio_free(struct bio *bio)
-{
- bio_disassociate_task(bio);
-
- if (bio_integrity(bio))
- bio_integrity_free(bio);
-}
-
-static void bio_free(struct bio *bio)
-{
- struct bio_set *bs = bio->bi_pool;
- void *p;
-
- __bio_free(bio);
-
- if (bs) {
- if (bio_flagged(bio, BIO_OWNS_VEC))
- bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio));
-
- /*
- * If we have front padding, adjust the bio pointer before freeing
- */
- p = bio;
- p -= bs->front_pad;
-
- mempool_free(p, bs->bio_pool);
- } else {
- /* Bio was allocated by bio_kmalloc() */
- kfree(bio);
- }
-}
-
-void bio_init(struct bio *bio)
-{
- memset(bio, 0, sizeof(*bio));
- bio->bi_flags = 1 << BIO_UPTODATE;
- atomic_set(&bio->bi_remaining, 1);
- atomic_set(&bio->bi_cnt, 1);
-}
-EXPORT_SYMBOL(bio_init);
-
-/**
- * bio_reset - reinitialize a bio
- * @bio: bio to reset
- *
- * Description:
- * After calling bio_reset(), @bio will be in the same state as a freshly
- * allocated bio returned bio bio_alloc_bioset() - the only fields that are
- * preserved are the ones that are initialized by bio_alloc_bioset(). See
- * comment in struct bio.
- */
-void bio_reset(struct bio *bio)
-{
- unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
-
- __bio_free(bio);
-
- memset(bio, 0, BIO_RESET_BYTES);
- bio->bi_flags = flags|(1 << BIO_UPTODATE);
- atomic_set(&bio->bi_remaining, 1);
-}
-EXPORT_SYMBOL(bio_reset);
-
-static void bio_chain_endio(struct bio *bio, int error)
-{
- bio_endio(bio->bi_private, error);
- bio_put(bio);
-}
-
-/**
- * bio_chain - chain bio completions
- *
- * The caller won't have a bi_end_io called when @bio completes - instead,
- * @parent's bi_end_io won't be called until both @parent and @bio have
- * completed; the chained bio will also be freed when it completes.
- *
- * The caller must not set bi_private or bi_end_io in @bio.
- */
-void bio_chain(struct bio *bio, struct bio *parent)
-{
- BUG_ON(bio->bi_private || bio->bi_end_io);
-
- bio->bi_private = parent;
- bio->bi_end_io = bio_chain_endio;
- atomic_inc(&parent->bi_remaining);
-}
-EXPORT_SYMBOL(bio_chain);
-
-static void bio_alloc_rescue(struct work_struct *work)
-{
- struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
- struct bio *bio;
-
- while (1) {
- spin_lock(&bs->rescue_lock);
- bio = bio_list_pop(&bs->rescue_list);
- spin_unlock(&bs->rescue_lock);
-
- if (!bio)
- break;
-
- generic_make_request(bio);
- }
-}
-
-static void punt_bios_to_rescuer(struct bio_set *bs)
-{
- struct bio_list punt, nopunt;
- struct bio *bio;
-
- /*
- * In order to guarantee forward progress we must punt only bios that
- * were allocated from this bio_set; otherwise, if there was a bio on
- * there for a stacking driver higher up in the stack, processing it
- * could require allocating bios from this bio_set, and doing that from
- * our own rescuer would be bad.
- *
- * Since bio lists are singly linked, pop them all instead of trying to
- * remove from the middle of the list:
- */
-
- bio_list_init(&punt);
- bio_list_init(&nopunt);
-
- while ((bio = bio_list_pop(current->bio_list)))
- bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
-
- *current->bio_list = nopunt;
-
- spin_lock(&bs->rescue_lock);
- bio_list_merge(&bs->rescue_list, &punt);
- spin_unlock(&bs->rescue_lock);
-
- queue_work(bs->rescue_workqueue, &bs->rescue_work);
-}
-
-/**
- * bio_alloc_bioset - allocate a bio for I/O
- * @gfp_mask: the GFP_ mask given to the slab allocator
- * @nr_iovecs: number of iovecs to pre-allocate
- * @bs: the bio_set to allocate from.
- *
- * Description:
- * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
- * backed by the @bs's mempool.
- *
- * When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
- * able to allocate a bio. This is due to the mempool guarantees. To make this
- * work, callers must never allocate more than 1 bio at a time from this pool.
- * Callers that need to allocate more than 1 bio must always submit the
- * previously allocated bio for IO before attempting to allocate a new one.
- * Failure to do so can cause deadlocks under memory pressure.
- *
- * Note that when running under generic_make_request() (i.e. any block
- * driver), bios are not submitted until after you return - see the code in
- * generic_make_request() that converts recursion into iteration, to prevent
- * stack overflows.
- *
- * This would normally mean allocating multiple bios under
- * generic_make_request() would be susceptible to deadlocks, but we have
- * deadlock avoidance code that resubmits any blocked bios from a rescuer
- * thread.
- *
- * However, we do not guarantee forward progress for allocations from other
- * mempools. Doing multiple allocations from the same mempool under
- * generic_make_request() should be avoided - instead, use bio_set's front_pad
- * for per bio allocations.
- *
- * RETURNS:
- * Pointer to new bio on success, NULL on failure.
- */
-struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
-{
- gfp_t saved_gfp = gfp_mask;
- unsigned front_pad;
- unsigned inline_vecs;
- unsigned long idx = BIO_POOL_NONE;
- struct bio_vec *bvl = NULL;
- struct bio *bio;
- void *p;
-
- if (!bs) {
- if (nr_iovecs > UIO_MAXIOV)
- return NULL;
-
- p = kmalloc(sizeof(struct bio) +
- nr_iovecs * sizeof(struct bio_vec),
- gfp_mask);
- front_pad = 0;
- inline_vecs = nr_iovecs;
- } else {
- /*
- * generic_make_request() converts recursion to iteration; this
- * means if we're running beneath it, any bios we allocate and
- * submit will not be submitted (and thus freed) until after we
- * return.
- *
- * This exposes us to a potential deadlock if we allocate
- * multiple bios from the same bio_set() while running
- * underneath generic_make_request(). If we were to allocate
- * multiple bios (say a stacking block driver that was splitting
- * bios), we would deadlock if we exhausted the mempool's
- * reserve.
- *
- * We solve this, and guarantee forward progress, with a rescuer
- * workqueue per bio_set. If we go to allocate and there are
- * bios on current->bio_list, we first try the allocation
- * without __GFP_WAIT; if that fails, we punt those bios we
- * would be blocking to the rescuer workqueue before we retry
- * with the original gfp_flags.
- */
-
- if (current->bio_list && !bio_list_empty(current->bio_list))
- gfp_mask &= ~__GFP_WAIT;
-
- p = mempool_alloc(bs->bio_pool, gfp_mask);
- if (!p && gfp_mask != saved_gfp) {
- punt_bios_to_rescuer(bs);
- gfp_mask = saved_gfp;
- p = mempool_alloc(bs->bio_pool, gfp_mask);
- }
-
- front_pad = bs->front_pad;
- inline_vecs = BIO_INLINE_VECS;
- }
-
- if (unlikely(!p))
- return NULL;
-
- bio = p + front_pad;
- bio_init(bio);
-
- if (nr_iovecs > inline_vecs) {
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
- if (!bvl && gfp_mask != saved_gfp) {
- punt_bios_to_rescuer(bs);
- gfp_mask = saved_gfp;
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
- }
-
- if (unlikely(!bvl))
- goto err_free;
-
- bio->bi_flags |= 1 << BIO_OWNS_VEC;
- } else if (nr_iovecs) {
- bvl = bio->bi_inline_vecs;
- }
-
- bio->bi_pool = bs;
- bio->bi_flags |= idx << BIO_POOL_OFFSET;
- bio->bi_max_vecs = nr_iovecs;
- bio->bi_io_vec = bvl;
- return bio;
-
-err_free:
- mempool_free(p, bs->bio_pool);
- return NULL;
-}
-EXPORT_SYMBOL(bio_alloc_bioset);
-
-void zero_fill_bio(struct bio *bio)
-{
- unsigned long flags;
- struct bio_vec bv;
- struct bvec_iter iter;
-
- bio_for_each_segment(bv, bio, iter) {
- char *data = bvec_kmap_irq(&bv, &flags);
- memset(data, 0, bv.bv_len);
- flush_dcache_page(bv.bv_page);
- bvec_kunmap_irq(data, &flags);
- }
-}
-EXPORT_SYMBOL(zero_fill_bio);
-
-/**
- * bio_put - release a reference to a bio
- * @bio: bio to release reference to
- *
- * Description:
- * Put a reference to a &struct bio, either one you have gotten with
- * bio_alloc, bio_get or bio_clone. The last put of a bio will free it.
- **/
-void bio_put(struct bio *bio)
-{
- BIO_BUG_ON(!atomic_read(&bio->bi_cnt));
-
- /*
- * last put frees it
- */
- if (atomic_dec_and_test(&bio->bi_cnt))
- bio_free(bio);
-}
-EXPORT_SYMBOL(bio_put);
-
-inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
-{
- if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
- blk_recount_segments(q, bio);
-
- return bio->bi_phys_segments;
-}
-EXPORT_SYMBOL(bio_phys_segments);
-
-/**
- * __bio_clone_fast - clone a bio that shares the original bio's biovec
- * @bio: destination bio
- * @bio_src: bio to clone
- *
- * Clone a &bio. Caller will own the returned bio, but not
- * the actual data it points to. Reference count of returned
- * bio will be one.
- *
- * Caller must ensure that @bio_src is not freed before @bio.
- */
-void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
-{
- BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);
-
- /*
- * most users will be overriding ->bi_bdev with a new target,
- * so we don't set nor calculate new physical/hw segment counts here
- */
- bio->bi_bdev = bio_src->bi_bdev;
- bio->bi_flags |= 1 << BIO_CLONED;
- bio->bi_rw = bio_src->bi_rw;
- bio->bi_iter = bio_src->bi_iter;
- bio->bi_io_vec = bio_src->bi_io_vec;
-}
-EXPORT_SYMBOL(__bio_clone_fast);
-
-/**
- * bio_clone_fast - clone a bio that shares the original bio's biovec
- * @bio: bio to clone
- * @gfp_mask: allocation priority
- * @bs: bio_set to allocate from
- *
- * Like __bio_clone_fast, only also allocates the returned bio
- */
-struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
-{
- struct bio *b;
-
- b = bio_alloc_bioset(gfp_mask, 0, bs);
- if (!b)
- return NULL;
-
- __bio_clone_fast(b, bio);
-
- if (bio_integrity(bio)) {
- int ret;
-
- ret = bio_integrity_clone(b, bio, gfp_mask);
-
- if (ret < 0) {
- bio_put(b);
- return NULL;
- }
- }
-
- return b;
-}
-EXPORT_SYMBOL(bio_clone_fast);
-
-/**
- * bio_clone_bioset - clone a bio
- * @bio_src: bio to clone
- * @gfp_mask: allocation priority
- * @bs: bio_set to allocate from
- *
- * Clone bio. Caller will own the returned bio, but not the actual data it
- * points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
- struct bio_set *bs)
-{
- struct bvec_iter iter;
- struct bio_vec bv;
- struct bio *bio;
-
- /*
- * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
- * bio_src->bi_io_vec to bio->bi_io_vec.
- *
- * We can't do that anymore, because:
- *
- * - The point of cloning the biovec is to produce a bio with a biovec
- * the caller can modify: bi_idx and bi_bvec_done should be 0.
- *
- * - The original bio could've had more than BIO_MAX_PAGES biovecs; if
- * we tried to clone the whole thing bio_alloc_bioset() would fail.
- * But the clone should succeed as long as the number of biovecs we
- * actually need to allocate is fewer than BIO_MAX_PAGES.
- *
- * - Lastly, bi_vcnt should not be looked at or relied upon by code
- * that does not own the bio - reason being drivers don't use it for
- * iterating over the biovec anymore, so expecting it to be kept up
- * to date (i.e. for clones that share the parent biovec) is just
- * asking for trouble and would force extra work on
- * __bio_clone_fast() anyways.
- */
-
- bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
- if (!bio)
- return NULL;
-
- bio->bi_bdev = bio_src->bi_bdev;
- bio->bi_rw = bio_src->bi_rw;
- bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
- bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
-
- if (bio->bi_rw & REQ_DISCARD)
- goto integrity_clone;
-
- if (bio->bi_rw & REQ_WRITE_SAME) {
- bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
- goto integrity_clone;
- }
-
- bio_for_each_segment(bv, bio_src, iter)
- bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
- if (bio_integrity(bio_src)) {
- int ret;
-
- ret = bio_integrity_clone(bio, bio_src, gfp_mask);
- if (ret < 0) {
- bio_put(bio);
- return NULL;
- }
- }
-
- return bio;
-}
-EXPORT_SYMBOL(bio_clone_bioset);
-
-/**
- * bio_get_nr_vecs - return approx number of vecs
- * @bdev: I/O target
- *
- * Return the approximate number of pages we can send to this target.
- * There's no guarantee that you will be able to fit this number of pages
- * into a bio, it does not account for dynamic restrictions that vary
- * on offset.
- */
-int bio_get_nr_vecs(struct block_device *bdev)
-{
- struct request_queue *q = bdev_get_queue(bdev);
- int nr_pages;
-
- nr_pages = min_t(unsigned,
- queue_max_segments(q),
- queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
-
- return min_t(unsigned, nr_pages, BIO_MAX_PAGES);
-
-}
-EXPORT_SYMBOL(bio_get_nr_vecs);
-
-static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
- *page, unsigned int len, unsigned int offset,
- unsigned int max_sectors)
-{
- int retried_segments = 0;
- struct bio_vec *bvec;
-
- /*
- * cloned bio must not modify vec list
- */
- if (unlikely(bio_flagged(bio, BIO_CLONED)))
- return 0;
-
- if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
- return 0;
-
- /*
- * For filesystems with a blocksize smaller than the pagesize
- * we will often be called with the same page as last time and
- * a consecutive offset. Optimize this special case.
- */
- if (bio->bi_vcnt > 0) {
- struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
- if (page == prev->bv_page &&
- offset == prev->bv_offset + prev->bv_len) {
- unsigned int prev_bv_len = prev->bv_len;
- prev->bv_len += len;
-
- if (q->merge_bvec_fn) {
- struct bvec_merge_data bvm = {
- /* prev_bvec is already charged in
- bi_size, discharge it in order to
- simulate merging updated prev_bvec
- as new bvec. */
- .bi_bdev = bio->bi_bdev,
- .bi_sector = bio->bi_iter.bi_sector,
- .bi_size = bio->bi_iter.bi_size -
- prev_bv_len,
- .bi_rw = bio->bi_rw,
- };
-
- if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
- prev->bv_len -= len;
- return 0;
- }
- }
-
- goto done;
- }
- }
-
- if (bio->bi_vcnt >= bio->bi_max_vecs)
- return 0;
-
- /*
- * we might lose a segment or two here, but rather that than
- * make this too complex.
- */
-
- while (bio->bi_phys_segments >= queue_max_segments(q)) {
-
- if (retried_segments)
- return 0;
-
- retried_segments = 1;
- blk_recount_segments(q, bio);
- }
-
- /*
- * setup the new entry, we might clear it again later if we
- * cannot add the page
- */
- bvec = &bio->bi_io_vec[bio->bi_vcnt];
- bvec->bv_page = page;
- bvec->bv_len = len;
- bvec->bv_offset = offset;
-
- /*
- * if queue has other restrictions (eg varying max sector size
- * depending on offset), it can specify a merge_bvec_fn in the
- * queue to get further control
- */
- if (q->merge_bvec_fn) {
- struct bvec_merge_data bvm = {
- .bi_bdev = bio->bi_bdev,
- .bi_sector = bio->bi_iter.bi_sector,
- .bi_size = bio->bi_iter.bi_size,
- .bi_rw = bio->bi_rw,
- };
-
- /*
- * merge_bvec_fn() returns number of bytes it can accept
- * at this offset
- */
- if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
- bvec->bv_page = NULL;
- bvec->bv_len = 0;
- bvec->bv_offset = 0;
- return 0;
- }
- }
-
- /* If we may be able to merge these biovecs, force a recount */
- if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
- bio->bi_flags &= ~(1 << BIO_SEG_VALID);
-
- bio->bi_vcnt++;
- bio->bi_phys_segments++;
- done:
- bio->bi_iter.bi_size += len;
- return len;
-}
-
-/**
- * bio_add_pc_page - attempt to add page to bio
- * @q: the target queue
- * @bio: destination bio
- * @page: page to add
- * @len: vec entry length
- * @offset: vec entry offset
- *
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block device
- * limitations. The target block device must allow bio's up to PAGE_SIZE,
- * so it is always possible to add a single page to an empty bio.
- *
- * This should only be used by REQ_PC bios.
- */
-int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
- unsigned int len, unsigned int offset)
-{
- return __bio_add_page(q, bio, page, len, offset,
- queue_max_hw_sectors(q));
-}
-EXPORT_SYMBOL(bio_add_pc_page);
-
-/**
- * bio_add_page - attempt to add page to bio
- * @bio: destination bio
- * @page: page to add
- * @len: vec entry length
- * @offset: vec entry offset
- *
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block device
- * limitations. The target block device must allow bio's up to PAGE_SIZE,
- * so it is always possible to add a single page to an empty bio.
- */
-int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
- unsigned int offset)
-{
- struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
-}
-EXPORT_SYMBOL(bio_add_page);
-
-struct submit_bio_ret {
- struct completion event;
- int error;
-};
-
-static void submit_bio_wait_endio(struct bio *bio, int error)
-{
- struct submit_bio_ret *ret = bio->bi_private;
-
- ret->error = error;
- complete(&ret->event);
-}
-
-/**
- * submit_bio_wait - submit a bio, and wait until it completes
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
- * @bio: The &struct bio which describes the I/O
- *
- * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
- * bio_endio() on failure.
- */
-int submit_bio_wait(int rw, struct bio *bio)
-{
- struct submit_bio_ret ret;
-
- rw |= REQ_SYNC;
- init_completion(&ret.event);
- bio->bi_private = &ret;
- bio->bi_end_io = submit_bio_wait_endio;
- submit_bio(rw, bio);
- wait_for_completion(&ret.event);
-
- return ret.error;
-}
-EXPORT_SYMBOL(submit_bio_wait);
-
-/**
- * bio_advance - increment/complete a bio by some number of bytes
- * @bio: bio to advance
- * @bytes: number of bytes to complete
- *
- * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
- * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
- * be updated on the last bvec as well.
- *
- * @bio will then represent the remaining, uncompleted portion of the io.
- */
-void bio_advance(struct bio *bio, unsigned bytes)
-{
- if (bio_integrity(bio))
- bio_integrity_advance(bio, bytes);
-
- bio_advance_iter(bio, &bio->bi_iter, bytes);
-}
-EXPORT_SYMBOL(bio_advance);
-
-/**
- * bio_alloc_pages - allocates a single page for each bvec in a bio
- * @bio: bio to allocate pages for
- * @gfp_mask: flags for allocation
- *
- * Allocates pages up to @bio->bi_vcnt.
- *
- * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
- * freed.
- */
-int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
-{
- int i;
- struct bio_vec *bv;
-
- bio_for_each_segment_all(bv, bio, i) {
- bv->bv_page = alloc_page(gfp_mask);
- if (!bv->bv_page) {
- while (--bv >= bio->bi_io_vec)
- __free_page(bv->bv_page);
- return -ENOMEM;
- }
- }
-
- return 0;
-}
-EXPORT_SYMBOL(bio_alloc_pages);
-
-/**
- * bio_copy_data - copy contents of data buffers from one chain of bios to
- * another
- * @src: source bio list
- * @dst: destination bio list
- *
- * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
- * @src and @dst as linked lists of bios.
- *
- * Stops when it reaches the end of either @src or @dst - that is, copies
- * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
- */
-void bio_copy_data(struct bio *dst, struct bio *src)
-{
- struct bvec_iter src_iter, dst_iter;
- struct bio_vec src_bv, dst_bv;
- void *src_p, *dst_p;
- unsigned bytes;
-
- src_iter = src->bi_iter;
- dst_iter = dst->bi_iter;
-
- while (1) {
- if (!src_iter.bi_size) {
- src = src->bi_next;
- if (!src)
- break;
-
- src_iter = src->bi_iter;
- }
-
- if (!dst_iter.bi_size) {
- dst = dst->bi_next;
- if (!dst)
- break;
-
- dst_iter = dst->bi_iter;
- }
-
- src_bv = bio_iter_iovec(src, src_iter);
- dst_bv = bio_iter_iovec(dst, dst_iter);
-
- bytes = min(src_bv.bv_len, dst_bv.bv_len);
-
- src_p = kmap_atomic(src_bv.bv_page);
- dst_p = kmap_atomic(dst_bv.bv_page);
-
- memcpy(dst_p + dst_bv.bv_offset,
- src_p + src_bv.bv_offset,
- bytes);
-
- kunmap_atomic(dst_p);
- kunmap_atomic(src_p);
-
- bio_advance_iter(src, &src_iter, bytes);
- bio_advance_iter(dst, &dst_iter, bytes);
- }
-}
-EXPORT_SYMBOL(bio_copy_data);
-
-struct bio_map_data {
- int nr_sgvecs;
- int is_our_pages;
- struct sg_iovec sgvecs[];
-};
-
-static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
- const struct sg_iovec *iov, int iov_count,
- int is_our_pages)
-{
- memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
- bmd->nr_sgvecs = iov_count;
- bmd->is_our_pages = is_our_pages;
- bio->bi_private = bmd;
-}
-
-static struct bio_map_data *bio_alloc_map_data(int nr_segs,
- unsigned int iov_count,
- gfp_t gfp_mask)
-{
- if (iov_count > UIO_MAXIOV)
- return NULL;
-
- return kmalloc(sizeof(struct bio_map_data) +
- sizeof(struct sg_iovec) * iov_count, gfp_mask);
-}
-
-static int __bio_copy_iov(struct bio *bio, const struct sg_iovec *iov, int iov_count,
- int to_user, int from_user, int do_free_page)
-{
- int ret = 0, i;
- struct bio_vec *bvec;
- int iov_idx = 0;
- unsigned int iov_off = 0;
-
- bio_for_each_segment_all(bvec, bio, i) {
- char *bv_addr = page_address(bvec->bv_page);
- unsigned int bv_len = bvec->bv_len;
-
- while (bv_len && iov_idx < iov_count) {
- unsigned int bytes;
- char __user *iov_addr;
-
- bytes = min_t(unsigned int,
- iov[iov_idx].iov_len - iov_off, bv_len);
- iov_addr = iov[iov_idx].iov_base + iov_off;
-
- if (!ret) {
- if (to_user)
- ret = copy_to_user(iov_addr, bv_addr,
- bytes);
-
- if (from_user)
- ret = copy_from_user(bv_addr, iov_addr,
- bytes);
-
- if (ret)
- ret = -EFAULT;
- }
-
- bv_len -= bytes;
- bv_addr += bytes;
- iov_addr += bytes;
- iov_off += bytes;
-
- if (iov[iov_idx].iov_len == iov_off) {
- iov_idx++;
- iov_off = 0;
- }
- }
-
- if (do_free_page)
- __free_page(bvec->bv_page);
- }
-
- return ret;
-}
-
-/**
- * bio_uncopy_user - finish previously mapped bio
- * @bio: bio being terminated
- *
- * Free pages allocated from bio_copy_user() and write back data
- * to user space in case of a read.
- */
-int bio_uncopy_user(struct bio *bio)
-{
- struct bio_map_data *bmd = bio->bi_private;
- struct bio_vec *bvec;
- int ret = 0, i;
-
- if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
- /*
- * if we're in a workqueue, the request is orphaned, so
- * don't copy into a random user address space, just free.
- */
- if (current->mm)
- ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
- bio_data_dir(bio) == READ,
- 0, bmd->is_our_pages);
- else if (bmd->is_our_pages)
- bio_for_each_segment_all(bvec, bio, i)
- __free_page(bvec->bv_page);
- }
- kfree(bmd);
- bio_put(bio);
- return ret;
-}
-EXPORT_SYMBOL(bio_uncopy_user);
-
-/**
- * bio_copy_user_iov - copy user data to bio
- * @q: destination block queue
- * @map_data: pointer to the rq_map_data holding pages (if necessary)
- * @iov: the iovec.
- * @iov_count: number of elements in the iovec
- * @write_to_vm: bool indicating writing to pages or not
- * @gfp_mask: memory allocation flags
- *
- * Prepares and returns a bio for indirect user io, bouncing data
- * to/from kernel pages as necessary. Must be paired with
- * call bio_uncopy_user() on io completion.
- */
-struct bio *bio_copy_user_iov(struct request_queue *q,
- struct rq_map_data *map_data,
- const struct sg_iovec *iov, int iov_count,
- int write_to_vm, gfp_t gfp_mask)
-{
- struct bio_map_data *bmd;
- struct bio_vec *bvec;
- struct page *page;
- struct bio *bio;
- int i, ret;
- int nr_pages = 0;
- unsigned int len = 0;
- unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;
-
- for (i = 0; i < iov_count; i++) {
- unsigned long uaddr;
- unsigned long end;
- unsigned long start;
-
- uaddr = (unsigned long)iov[i].iov_base;
- end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- start = uaddr >> PAGE_SHIFT;
-
- /*
- * Overflow, abort
- */
- if (end < start)
- return ERR_PTR(-EINVAL);
-
- nr_pages += end - start;
- len += iov[i].iov_len;
- }
-
- if (offset)
- nr_pages++;
-
- bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
- if (!bmd)
- return ERR_PTR(-ENOMEM);
-
- ret = -ENOMEM;
- bio = bio_kmalloc(gfp_mask, nr_pages);
- if (!bio)
- goto out_bmd;
-
- if (!write_to_vm)
- bio->bi_rw |= REQ_WRITE;
-
- ret = 0;
-
- if (map_data) {
- nr_pages = 1 << map_data->page_order;
- i = map_data->offset / PAGE_SIZE;
- }
- while (len) {
- unsigned int bytes = PAGE_SIZE;
-
- bytes -= offset;
-
- if (bytes > len)
- bytes = len;
-
- if (map_data) {
- if (i == map_data->nr_entries * nr_pages) {
- ret = -ENOMEM;
- break;
- }
-
- page = map_data->pages[i / nr_pages];
- page += (i % nr_pages);
-
- i++;
- } else {
- page = alloc_page(q->bounce_gfp | gfp_mask);
- if (!page) {
- ret = -ENOMEM;
- break;
- }
- }
-
- if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
- break;
-
- len -= bytes;
- offset = 0;
- }
-
- if (ret)
- goto cleanup;
-
- /*
- * success
- */
- if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
- (map_data && map_data->from_user)) {
- ret = __bio_copy_iov(bio, iov, iov_count, 0, 1, 0);
- if (ret)
- goto cleanup;
- }
-
- bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
- return bio;
-cleanup:
- if (!map_data)
- bio_for_each_segment_all(bvec, bio, i)
- __free_page(bvec->bv_page);
-
- bio_put(bio);
-out_bmd:
- kfree(bmd);
- return ERR_PTR(ret);
-}
-
-/**
- * bio_copy_user - copy user data to bio
- * @q: destination block queue
- * @map_data: pointer to the rq_map_data holding pages (if necessary)
- * @uaddr: start of user address
- * @len: length in bytes
- * @write_to_vm: bool indicating writing to pages or not
- * @gfp_mask: memory allocation flags
- *
- * Prepares and returns a bio for indirect user io, bouncing data
- * to/from kernel pages as necessary. Must be paired with
- * call bio_uncopy_user() on io completion.
- */
-struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
- unsigned long uaddr, unsigned int len,
- int write_to_vm, gfp_t gfp_mask)
-{
- struct sg_iovec iov;
-
- iov.iov_base = (void __user *)uaddr;
- iov.iov_len = len;
-
- return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
-}
-EXPORT_SYMBOL(bio_copy_user);
-
-static struct bio *__bio_map_user_iov(struct request_queue *q,
- struct block_device *bdev,
- const struct sg_iovec *iov, int iov_count,
- int write_to_vm, gfp_t gfp_mask)
-{
- int i, j;
- int nr_pages = 0;
- struct page **pages;
- struct bio *bio;
- int cur_page = 0;
- int ret, offset;
-
- for (i = 0; i < iov_count; i++) {
- unsigned long uaddr = (unsigned long)iov[i].iov_base;
- unsigned long len = iov[i].iov_len;
- unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long start = uaddr >> PAGE_SHIFT;
-
- /*
- * Overflow, abort
- */
- if (end < start)
- return ERR_PTR(-EINVAL);
-
- nr_pages += end - start;
- /*
- * buffer must be aligned to at least hardsector size for now
- */
- if (uaddr & queue_dma_alignment(q))
- return ERR_PTR(-EINVAL);
- }
-
- if (!nr_pages)
- return ERR_PTR(-EINVAL);
-
- bio = bio_kmalloc(gfp_mask, nr_pages);
- if (!bio)
- return ERR_PTR(-ENOMEM);
-
- ret = -ENOMEM;
- pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
- if (!pages)
- goto out;
-
- for (i = 0; i < iov_count; i++) {
- unsigned long uaddr = (unsigned long)iov[i].iov_base;
- unsigned long len = iov[i].iov_len;
- unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long start = uaddr >> PAGE_SHIFT;
- const int local_nr_pages = end - start;
- const int page_limit = cur_page + local_nr_pages;
-
- ret = get_user_pages_fast(uaddr, local_nr_pages,
- write_to_vm, &pages[cur_page]);
- if (ret < local_nr_pages) {
- ret = -EFAULT;
- goto out_unmap;
- }
-
- offset = uaddr & ~PAGE_MASK;
- for (j = cur_page; j < page_limit; j++) {
- unsigned int bytes = PAGE_SIZE - offset;
-
- if (len <= 0)
- break;
-
- if (bytes > len)
- bytes = len;
-
- /*
- * sorry...
- */
- if (bio_add_pc_page(q, bio, pages[j], bytes, offset) <
- bytes)
- break;
-
- len -= bytes;
- offset = 0;
- }
-
- cur_page = j;
- /*
- * release the pages we didn't map into the bio, if any
- */
- while (j < page_limit)
- page_cache_release(pages[j++]);
- }
-
- kfree(pages);
-
- /*
- * set data direction, and check if mapped pages need bouncing
- */
- if (!write_to_vm)
- bio->bi_rw |= REQ_WRITE;
-
- bio->bi_bdev = bdev;
- bio->bi_flags |= (1 << BIO_USER_MAPPED);
- return bio;
-
- out_unmap:
- for (i = 0; i < nr_pages; i++) {
- if(!pages[i])
- break;
- page_cache_release(pages[i]);
- }
- out:
- kfree(pages);
- bio_put(bio);
- return ERR_PTR(ret);
-}
-
-/**
- * bio_map_user - map user address into bio
- * @q: the struct request_queue for the bio
- * @bdev: destination block device
- * @uaddr: start of user address
- * @len: length in bytes
- * @write_to_vm: bool indicating writing to pages or not
- * @gfp_mask: memory allocation flags
- *
- * Map the user space address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
- unsigned long uaddr, unsigned int len, int write_to_vm,
- gfp_t gfp_mask)
-{
- struct sg_iovec iov;
-
- iov.iov_base = (void __user *)uaddr;
- iov.iov_len = len;
-
- return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
-}
-EXPORT_SYMBOL(bio_map_user);
-
-/**
- * bio_map_user_iov - map user sg_iovec table into bio
- * @q: the struct request_queue for the bio
- * @bdev: destination block device
- * @iov: the iovec.
- * @iov_count: number of elements in the iovec
- * @write_to_vm: bool indicating writing to pages or not
- * @gfp_mask: memory allocation flags
- *
- * Map the user space address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
- const struct sg_iovec *iov, int iov_count,
- int write_to_vm, gfp_t gfp_mask)
-{
- struct bio *bio;
-
- bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
- gfp_mask);
- if (IS_ERR(bio))
- return bio;
-
- /*
- * subtle -- if __bio_map_user() ended up bouncing a bio,
- * it would normally disappear when its bi_end_io is run.
- * however, we need it for the unmap, so grab an extra
- * reference to it
- */
- bio_get(bio);
-
- return bio;
-}
-
-static void __bio_unmap_user(struct bio *bio)
-{
- struct bio_vec *bvec;
- int i;
-
- /*
- * make sure we dirty pages we wrote to
- */
- bio_for_each_segment_all(bvec, bio, i) {
- if (bio_data_dir(bio) == READ)
- set_page_dirty_lock(bvec->bv_page);
-
- page_cache_release(bvec->bv_page);
- }
-
- bio_put(bio);
-}
-
-/**
- * bio_unmap_user - unmap a bio
- * @bio: the bio being unmapped
- *
- * Unmap a bio previously mapped by bio_map_user(). Must be called with
- * a process context.
- *
- * bio_unmap_user() may sleep.
- */
-void bio_unmap_user(struct bio *bio)
-{
- __bio_unmap_user(bio);
- bio_put(bio);
-}
-EXPORT_SYMBOL(bio_unmap_user);
-
-static void bio_map_kern_endio(struct bio *bio, int err)
-{
- bio_put(bio);
-}
-
-static struct bio *__bio_map_kern(struct request_queue *q, void *data,
- unsigned int len, gfp_t gfp_mask)
-{
- unsigned long kaddr = (unsigned long)data;
- unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long start = kaddr >> PAGE_SHIFT;
- const int nr_pages = end - start;
- int offset, i;
- struct bio *bio;
-
- bio = bio_kmalloc(gfp_mask, nr_pages);
- if (!bio)
- return ERR_PTR(-ENOMEM);
-
- offset = offset_in_page(kaddr);
- for (i = 0; i < nr_pages; i++) {
- unsigned int bytes = PAGE_SIZE - offset;
-
- if (len <= 0)
- break;
-
- if (bytes > len)
- bytes = len;
-
- if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
- offset) < bytes)
- break;
-
- data += bytes;
- len -= bytes;
- offset = 0;
- }
-
- bio->bi_end_io = bio_map_kern_endio;
- return bio;
-}
-
-/**
- * bio_map_kern - map kernel address into bio
- * @q: the struct request_queue for the bio
- * @data: pointer to buffer to map
- * @len: length in bytes
- * @gfp_mask: allocation flags for bio allocation
- *
- * Map the kernel address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
- gfp_t gfp_mask)
-{
- struct bio *bio;
-
- bio = __bio_map_kern(q, data, len, gfp_mask);
- if (IS_ERR(bio))
- return bio;
-
- if (bio->bi_iter.bi_size == len)
- return bio;
-
- /*
- * Don't support partial mappings.
- */
- bio_put(bio);
- return ERR_PTR(-EINVAL);
-}
-EXPORT_SYMBOL(bio_map_kern);
-
-static void bio_copy_kern_endio(struct bio *bio, int err)
-{
- struct bio_vec *bvec;
- const int read = bio_data_dir(bio) == READ;
- struct bio_map_data *bmd = bio->bi_private;
- int i;
- char *p = bmd->sgvecs[0].iov_base;
-
- bio_for_each_segment_all(bvec, bio, i) {
- char *addr = page_address(bvec->bv_page);
-
- if (read)
- memcpy(p, addr, bvec->bv_len);
-
- __free_page(bvec->bv_page);
- p += bvec->bv_len;
- }
-
- kfree(bmd);
- bio_put(bio);
-}
-
-/**
- * bio_copy_kern - copy kernel address into bio
- * @q: the struct request_queue for the bio
- * @data: pointer to buffer to copy
- * @len: length in bytes
- * @gfp_mask: allocation flags for bio and page allocation
- * @reading: data direction is READ
- *
- * copy the kernel address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
- gfp_t gfp_mask, int reading)
-{
- struct bio *bio;
- struct bio_vec *bvec;
- int i;
-
- bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
- if (IS_ERR(bio))
- return bio;
-
- if (!reading) {
- void *p = data;
-
- bio_for_each_segment_all(bvec, bio, i) {
- char *addr = page_address(bvec->bv_page);
-
- memcpy(addr, p, bvec->bv_len);
- p += bvec->bv_len;
- }
- }
-
- bio->bi_end_io = bio_copy_kern_endio;
-
- return bio;
-}
-EXPORT_SYMBOL(bio_copy_kern);
-
-/*
- * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
- * for performing direct-IO in BIOs.
- *
- * The problem is that we cannot run set_page_dirty() from interrupt context
- * because the required locks are not interrupt-safe. So what we can do is to
- * mark the pages dirty _before_ performing IO. And in interrupt context,
- * check that the pages are still dirty. If so, fine. If not, redirty them
- * in process context.
- *
- * We special-case compound pages here: normally this means reads into hugetlb
- * pages. The logic in here doesn't really work right for compound pages
- * because the VM does not uniformly chase down the head page in all cases.
- * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
- * handle them at all. So we skip compound pages here at an early stage.
- *
- * Note that this code is very hard to test under normal circumstances because
- * direct-io pins the pages with get_user_pages(). This makes
- * is_page_cache_freeable return false, and the VM will not clean the pages.
- * But other code (eg, flusher threads) could clean the pages if they are mapped
- * pagecache.
- *
- * Simply disabling the call to bio_set_pages_dirty() is a good way to test the
- * deferred bio dirtying paths.
- */
-
-/*
- * bio_set_pages_dirty() will mark all the bio's pages as dirty.
- */
-void bio_set_pages_dirty(struct bio *bio)
-{
- struct bio_vec *bvec;
- int i;
-
- bio_for_each_segment_all(bvec, bio, i) {
- struct page *page = bvec->bv_page;
-
- if (page && !PageCompound(page))
- set_page_dirty_lock(page);
- }
-}
-
-static void bio_release_pages(struct bio *bio)
-{
- struct bio_vec *bvec;
- int i;
-
- bio_for_each_segment_all(bvec, bio, i) {
- struct page *page = bvec->bv_page;
-
- if (page)
- put_page(page);
- }
-}
-
-/*
- * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
- * If they are, then fine. If, however, some pages are clean then they must
- * have been written out during the direct-IO read. So we take another ref on
- * the BIO and the offending pages and re-dirty the pages in process context.
- *
- * It is expected that bio_check_pages_dirty() will wholly own the BIO from
- * here on. It will run one page_cache_release() against each page and will
- * run one bio_put() against the BIO.
- */
-
-static void bio_dirty_fn(struct work_struct *work);
-
-static DECLARE_WORK(bio_dirty_work, bio_dirty_fn);
-static DEFINE_SPINLOCK(bio_dirty_lock);
-static struct bio *bio_dirty_list;
-
-/*
- * This runs in process context
- */
-static void bio_dirty_fn(struct work_struct *work)
-{
- unsigned long flags;
- struct bio *bio;
-
- spin_lock_irqsave(&bio_dirty_lock, flags);
- bio = bio_dirty_list;
- bio_dirty_list = NULL;
- spin_unlock_irqrestore(&bio_dirty_lock, flags);
-
- while (bio) {
- struct bio *next = bio->bi_private;
-
- bio_set_pages_dirty(bio);
- bio_release_pages(bio);
- bio_put(bio);
- bio = next;
- }
-}
-
-void bio_check_pages_dirty(struct bio *bio)
-{
- struct bio_vec *bvec;
- int nr_clean_pages = 0;
- int i;
-
- bio_for_each_segment_all(bvec, bio, i) {
- struct page *page = bvec->bv_page;
-
- if (PageDirty(page) || PageCompound(page)) {
- page_cache_release(page);
- bvec->bv_page = NULL;
- } else {
- nr_clean_pages++;
- }
- }
-
- if (nr_clean_pages) {
- unsigned long flags;
-
- spin_lock_irqsave(&bio_dirty_lock, flags);
- bio->bi_private = bio_dirty_list;
- bio_dirty_list = bio;
- spin_unlock_irqrestore(&bio_dirty_lock, flags);
- schedule_work(&bio_dirty_work);
- } else {
- bio_put(bio);
- }
-}
-
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-void bio_flush_dcache_pages(struct bio *bi)
-{
- struct bio_vec bvec;
- struct bvec_iter iter;
-
- bio_for_each_segment(bvec, bi, iter)
- flush_dcache_page(bvec.bv_page);
-}
-EXPORT_SYMBOL(bio_flush_dcache_pages);
-#endif
-
-/**
- * bio_endio - end I/O on a bio
- * @bio: bio
- * @error: error, if any
- *
- * Description:
- * bio_endio() will end I/O on the whole bio. bio_endio() is the
- * preferred way to end I/O on a bio, it takes care of clearing
- * BIO_UPTODATE on error. @error is 0 on success, and and one of the
- * established -Exxxx (-EIO, for instance) error values in case
- * something went wrong. No one should call bi_end_io() directly on a
- * bio unless they own it and thus know that it has an end_io
- * function.
- **/
-void bio_endio(struct bio *bio, int error)
-{
- while (bio) {
- BUG_ON(atomic_read(&bio->bi_remaining) <= 0);
-
- if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
-
- if (!atomic_dec_and_test(&bio->bi_remaining))
- return;
-
- /*
- * Need to have a real endio function for chained bios,
- * otherwise various corner cases will break (like stacking
- * block devices that save/restore bi_end_io) - however, we want
- * to avoid unbounded recursion and blowing the stack. Tail call
- * optimization would handle this, but compiling with frame
- * pointers also disables gcc's sibling call optimization.
- */
- if (bio->bi_end_io == bio_chain_endio) {
- struct bio *parent = bio->bi_private;
- bio_put(bio);
- bio = parent;
- } else {
- if (bio->bi_end_io)
- bio->bi_end_io(bio, error);
- bio = NULL;
- }
- }
-}
-EXPORT_SYMBOL(bio_endio);
-
-/**
- * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining
- * @bio: bio
- * @error: error, if any
- *
- * For code that has saved and restored bi_end_io; thing hard before using this
- * function, probably you should've cloned the entire bio.
- **/
-void bio_endio_nodec(struct bio *bio, int error)
-{
- atomic_inc(&bio->bi_remaining);
- bio_endio(bio, error);
-}
-EXPORT_SYMBOL(bio_endio_nodec);
-
-/**
- * bio_split - split a bio
- * @bio: bio to split
- * @sectors: number of sectors to split from the front of @bio
- * @gfp: gfp mask
- * @bs: bio set to allocate from
- *
- * Allocates and returns a new bio which represents @sectors from the start of
- * @bio, and updates @bio to represent the remaining sectors.
- *
- * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
- * responsibility to ensure that @bio is not freed before the split.
- */
-struct bio *bio_split(struct bio *bio, int sectors,
- gfp_t gfp, struct bio_set *bs)
-{
- struct bio *split = NULL;
-
- BUG_ON(sectors <= 0);
- BUG_ON(sectors >= bio_sectors(bio));
-
- split = bio_clone_fast(bio, gfp, bs);
- if (!split)
- return NULL;
-
- split->bi_iter.bi_size = sectors << 9;
-
- if (bio_integrity(split))
- bio_integrity_trim(split, 0, sectors);
-
- bio_advance(bio, split->bi_iter.bi_size);
-
- return split;
-}
-EXPORT_SYMBOL(bio_split);
-
-/**
- * bio_trim - trim a bio
- * @bio: bio to trim
- * @offset: number of sectors to trim from the front of @bio
- * @size: size we want to trim @bio to, in sectors
- */
-void bio_trim(struct bio *bio, int offset, int size)
-{
- /* 'bio' is a cloned bio which we need to trim to match
- * the given offset and size.
- */
-
- size <<= 9;
- if (offset == 0 && size == bio->bi_iter.bi_size)
- return;
-
- clear_bit(BIO_SEG_VALID, &bio->bi_flags);
-
- bio_advance(bio, offset << 9);
-
- bio->bi_iter.bi_size = size;
-}
-EXPORT_SYMBOL_GPL(bio_trim);
-
-/*
- * create memory pools for biovec's in a bio_set.
- * use the global biovec slabs created for general use.
- */
-mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries)
-{
- struct biovec_slab *bp = bvec_slabs + BIOVEC_MAX_IDX;
-
- return mempool_create_slab_pool(pool_entries, bp->slab);
-}
-
-void bioset_free(struct bio_set *bs)
-{
- if (bs->rescue_workqueue)
- destroy_workqueue(bs->rescue_workqueue);
-
- if (bs->bio_pool)
- mempool_destroy(bs->bio_pool);
-
- if (bs->bvec_pool)
- mempool_destroy(bs->bvec_pool);
-
- bioset_integrity_free(bs);
- bio_put_slab(bs);
-
- kfree(bs);
-}
-EXPORT_SYMBOL(bioset_free);
-
-/**
- * bioset_create - Create a bio_set
- * @pool_size: Number of bio and bio_vecs to cache in the mempool
- * @front_pad: Number of bytes to allocate in front of the returned bio
- *
- * Description:
- * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- * to ask for a number of bytes to be allocated in front of the bio.
- * Front pad allocation is useful for embedding the bio inside
- * another structure, to avoid allocating extra data to go with the bio.
- * Note that the bio must be embedded at the END of that structure always,
- * or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
-{
- unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
- struct bio_set *bs;
-
- bs = kzalloc(sizeof(*bs), GFP_KERNEL);
- if (!bs)
- return NULL;
-
- bs->front_pad = front_pad;
-
- spin_lock_init(&bs->rescue_lock);
- bio_list_init(&bs->rescue_list);
- INIT_WORK(&bs->rescue_work, bio_alloc_rescue);
-
- bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad);
- if (!bs->bio_slab) {
- kfree(bs);
- return NULL;
- }
-
- bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab);
- if (!bs->bio_pool)
- goto bad;
-
- bs->bvec_pool = biovec_create_pool(bs, pool_size);
- if (!bs->bvec_pool)
- goto bad;
-
- bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
- if (!bs->rescue_workqueue)
- goto bad;
-
- return bs;
-bad:
- bioset_free(bs);
- return NULL;
-}
-EXPORT_SYMBOL(bioset_create);
-
-#ifdef CONFIG_BLK_CGROUP
-/**
- * bio_associate_current - associate a bio with %current
- * @bio: target bio
- *
- * Associate @bio with %current if it hasn't been associated yet. Block
- * layer will treat @bio as if it were issued by %current no matter which
- * task actually issues it.
- *
- * This function takes an extra reference of @task's io_context and blkcg
- * which will be put when @bio is released. The caller must own @bio,
- * ensure %current->io_context exists, and is responsible for synchronizing
- * calls to this function.
- */
-int bio_associate_current(struct bio *bio)
-{
- struct io_context *ioc;
- struct cgroup_subsys_state *css;
-
- if (bio->bi_ioc)
- return -EBUSY;
-
- ioc = current->io_context;
- if (!ioc)
- return -ENOENT;
-
- /* acquire active ref on @ioc and associate */
- get_io_context_active(ioc);
- bio->bi_ioc = ioc;
-
- /* associate blkcg if exists */
- rcu_read_lock();
- css = task_css(current, blkio_cgrp_id);
- if (css && css_tryget(css))
- bio->bi_css = css;
- rcu_read_unlock();
-
- return 0;
-}
-
-/**
- * bio_disassociate_task - undo bio_associate_current()
- * @bio: target bio
- */
-void bio_disassociate_task(struct bio *bio)
-{
- if (bio->bi_ioc) {
- put_io_context(bio->bi_ioc);
- bio->bi_ioc = NULL;
- }
- if (bio->bi_css) {
- css_put(bio->bi_css);
- bio->bi_css = NULL;
- }
-}
-
-#endif /* CONFIG_BLK_CGROUP */
-
-static void __init biovec_init_slabs(void)
-{
- int i;
-
- for (i = 0; i < BIOVEC_NR_POOLS; i++) {
- int size;
- struct biovec_slab *bvs = bvec_slabs + i;
-
- if (bvs->nr_vecs <= BIO_INLINE_VECS) {
- bvs->slab = NULL;
- continue;
- }
-
- size = bvs->nr_vecs * sizeof(struct bio_vec);
- bvs->slab = kmem_cache_create(bvs->name, size, 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
- }
-}
-
-static int __init init_bio(void)
-{
- bio_slab_max = 2;
- bio_slab_nr = 0;
- bio_slabs = kzalloc(bio_slab_max * sizeof(struct bio_slab), GFP_KERNEL);
- if (!bio_slabs)
- panic("bio: can't allocate bios\n");
-
- bio_integrity_init();
- biovec_init_slabs();
-
- fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
- if (!fs_bio_set)
- panic("bio: can't allocate bios\n");
-
- if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
- panic("bio: can't create integrity pool\n");
-
- return 0;
-}
-subsys_initcall(init_bio);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 552a8d13bc32..83fba15cc394 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -363,6 +363,69 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
}
EXPORT_SYMBOL(blkdev_fsync);
+/**
+ * bdev_read_page() - Start reading a page from a block device
+ * @bdev: The device to read the page from
+ * @sector: The offset on the device to read the page to (need not be aligned)
+ * @page: The page to read
+ *
+ * On entry, the page should be locked. It will be unlocked when the page
+ * has been read. If the block driver implements rw_page synchronously,
+ * that will be true on exit from this function, but it need not be.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to read this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_read_page(struct block_device *bdev, sector_t sector,
+ struct page *page)
+{
+ const struct block_device_operations *ops = bdev->bd_disk->fops;
+ if (!ops->rw_page)
+ return -EOPNOTSUPP;
+ return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+}
+EXPORT_SYMBOL_GPL(bdev_read_page);
+
+/**
+ * bdev_write_page() - Start writing a page to a block device
+ * @bdev: The device to write the page to
+ * @sector: The offset on the device to write the page to (need not be aligned)
+ * @page: The page to write
+ * @wbc: The writeback_control for the write
+ *
+ * On entry, the page should be locked and not currently under writeback.
+ * On exit, if the write started successfully, the page will be unlocked and
+ * under writeback. If the write failed already (eg the driver failed to
+ * queue the page to the device), the page will still be locked. If the
+ * caller is a ->writepage implementation, it will need to unlock the page.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to write this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_write_page(struct block_device *bdev, sector_t sector,
+ struct page *page, struct writeback_control *wbc)
+{
+ int result;
+ int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
+ const struct block_device_operations *ops = bdev->bd_disk->fops;
+ if (!ops->rw_page)
+ return -EOPNOTSUPP;
+ set_page_writeback(page);
+ result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
+ if (result)
+ end_page_writeback(page);
+ else
+ unlock_page(page);
+ return result;
+}
+EXPORT_SYMBOL_GPL(bdev_write_page);
+
/*
* pseudo-fs
*/
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index a0cf3e56fe20..4794923c410c 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -279,7 +279,7 @@ static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0b5fa91d9a88..f25a9092b946 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3523,7 +3523,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
static void end_extent_buffer_writeback(struct extent_buffer *eb)
{
clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
}
@@ -4576,7 +4576,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
spin_unlock(&eb->refs_lock);
}
-static void mark_extent_buffer_accessed(struct extent_buffer *eb)
+static void mark_extent_buffer_accessed(struct extent_buffer *eb,
+ struct page *accessed)
{
unsigned long num_pages, i;
@@ -4585,7 +4586,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb)
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
struct page *p = extent_buffer_page(eb, i);
- mark_page_accessed(p);
+ if (p != accessed)
+ mark_page_accessed(p);
}
}
@@ -4599,7 +4601,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
start >> PAGE_CACHE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
- mark_extent_buffer_accessed(eb);
+ mark_extent_buffer_accessed(eb, NULL);
return eb;
}
rcu_read_unlock();
@@ -4694,7 +4696,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
spin_unlock(&mapping->private_lock);
unlock_page(p);
page_cache_release(p);
- mark_extent_buffer_accessed(exists);
+ mark_extent_buffer_accessed(exists, p);
goto free_eb;
}
@@ -4709,7 +4711,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
attach_extent_buffer_page(eb, p);
spin_unlock(&mapping->private_lock);
WARN_ON(PageDirty(p));
- mark_page_accessed(p);
eb->pages[i] = p;
if (!PageUptodate(p))
uptodate = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ad7c05909a49..e472441feb5d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -471,11 +471,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
for (i = 0; i < num_pages; i++) {
/* page checked is some magic around finding pages that
* have been modified without going through btrfs_set_page_dirty
- * clear it here
+ * clear it here. There should be no need to mark the pages
+ * accessed as prepare_pages should have marked them accessed
+ * in prepare_pages via find_or_create_page()
*/
ClearPageChecked(pages[i]);
unlock_page(pages[i]);
- mark_page_accessed(pages[i]);
page_cache_release(pages[i]);
}
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 372b2cb2b297..7fa5f7fd7bc7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7180,7 +7180,7 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
* before atomic variable goto zero, we must make sure
* dip->errors is perceived to be set.
*/
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
}
/* if there are more bios still pending for this dio, just exit */
@@ -7360,7 +7360,7 @@ out_err:
* before atomic variable goto zero, we must
* make sure dip->errors is perceived to be set.
*/
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
if (atomic_dec_and_test(&dip->pending_bios))
bio_io_error(dip->orig_bio);
@@ -7503,7 +7503,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
return 0;
atomic_inc(&inode->i_dio_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
/*
* The generic stuff only does filemap_write_and_wait_range, which
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c2e796b664c1..82c18ba12e3f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -643,7 +643,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
return -EINVAL;
atomic_inc(&root->will_be_snapshoted);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
btrfs_wait_nocow_write(root);
ret = btrfs_start_delalloc_inodes(root, 0);
diff --git a/fs/buffer.c b/fs/buffer.c
index 9ddb9fc7d923..eba6e4f621ce 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -77,7 +77,7 @@ EXPORT_SYMBOL(__lock_buffer);
void unlock_buffer(struct buffer_head *bh)
{
clear_bit_unlock(BH_Lock, &bh->b_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&bh->b_state, BH_Lock);
}
EXPORT_SYMBOL(unlock_buffer);
@@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
int all_mapped = 1;
index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits);
- page = find_get_page(bd_mapping, index);
+ page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
if (!page)
goto out;
@@ -1366,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
if (bh == NULL) {
+ /* __find_get_block_slow will mark the page accessed */
bh = __find_get_block_slow(bdev, block);
if (bh)
bh_lru_install(bh);
- }
- if (bh)
+ } else
touch_buffer(bh);
+
return bh;
}
EXPORT_SYMBOL(__find_get_block);
@@ -1483,16 +1484,27 @@ EXPORT_SYMBOL(set_bh_page);
/*
* Called when truncating a buffer on a page completely.
*/
+
+/* Bits that are cleared during an invalidate */
+#define BUFFER_FLAGS_DISCARD \
+ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
+ 1 << BH_Delay | 1 << BH_Unwritten)
+
static void discard_buffer(struct buffer_head * bh)
{
+ unsigned long b_state, b_state_old;
+
lock_buffer(bh);
clear_buffer_dirty(bh);
bh->b_bdev = NULL;
- clear_buffer_mapped(bh);
- clear_buffer_req(bh);
- clear_buffer_new(bh);
- clear_buffer_delay(bh);
- clear_buffer_unwritten(bh);
+ b_state = bh->b_state;
+ for (;;) {
+ b_state_old = cmpxchg(&bh->b_state, b_state,
+ (b_state & ~BUFFER_FLAGS_DISCARD));
+ if (b_state_old == b_state)
+ break;
+ b_state = b_state_old;
+ }
unlock_buffer(bh);
}
@@ -2879,10 +2891,9 @@ EXPORT_SYMBOL(block_truncate_page);
/*
* The generic ->writepage function for buffer-backed address_spaces
- * this form passes in the end_io handler used to finish the IO.
*/
-int block_write_full_page_endio(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc, bh_end_io_t *handler)
+int block_write_full_page(struct page *page, get_block_t *get_block,
+ struct writeback_control *wbc)
{
struct inode * const inode = page->mapping->host;
loff_t i_size = i_size_read(inode);
@@ -2892,7 +2903,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
/* Is the page fully inside i_size? */
if (page->index < end_index)
return __block_write_full_page(inode, page, get_block, wbc,
- handler);
+ end_buffer_async_write);
/* Is the page fully outside i_size? (truncate in progress) */
offset = i_size & (PAGE_CACHE_SIZE-1);
@@ -2915,18 +2926,8 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
* writes to that region are not written out to the file."
*/
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
- return __block_write_full_page(inode, page, get_block, wbc, handler);
-}
-EXPORT_SYMBOL(block_write_full_page_endio);
-
-/*
- * The generic ->writepage function for buffer-backed address_spaces
- */
-int block_write_full_page(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc)
-{
- return block_write_full_page_endio(page, get_block, wbc,
- end_buffer_async_write);
+ return __block_write_full_page(inode, page, get_block, wbc,
+ end_buffer_async_write);
}
EXPORT_SYMBOL(block_write_full_page);
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index 5b99bafc31d1..d749731dc0ee 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -50,18 +50,18 @@ int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
cache->brun_percent < 100);
if (*args) {
- kerror("'bind' command doesn't take an argument");
+ pr_err("'bind' command doesn't take an argument");
return -EINVAL;
}
if (!cache->rootdirname) {
- kerror("No cache directory specified");
+ pr_err("No cache directory specified");
return -EINVAL;
}
/* don't permit already bound caches to be re-bound */
if (test_bit(CACHEFILES_READY, &cache->flags)) {
- kerror("Cache already bound");
+ pr_err("Cache already bound");
return -EBUSY;
}
@@ -228,9 +228,7 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
set_bit(CACHEFILES_READY, &cache->flags);
dput(root);
- printk(KERN_INFO "CacheFiles:"
- " File cache on %s registered\n",
- cache->cache.identifier);
+ pr_info("File cache on %s registered\n", cache->cache.identifier);
/* check how much space the cache has */
cachefiles_has_space(cache, 0, 0);
@@ -250,7 +248,7 @@ error_open_root:
kmem_cache_free(cachefiles_object_jar, fsdef);
error_root_object:
cachefiles_end_secure(cache, saved_cred);
- kerror("Failed to register: %d", ret);
+ pr_err("Failed to register: %d", ret);
return ret;
}
@@ -262,9 +260,8 @@ void cachefiles_daemon_unbind(struct cachefiles_cache *cache)
_enter("");
if (test_bit(CACHEFILES_READY, &cache->flags)) {
- printk(KERN_INFO "CacheFiles:"
- " File cache on %s unregistering\n",
- cache->cache.identifier);
+ pr_info("File cache on %s unregistering\n",
+ cache->cache.identifier);
fscache_withdraw_cache(&cache->cache);
}
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 0a1467b15516..b078d3081d6c 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -315,8 +315,7 @@ static unsigned int cachefiles_daemon_poll(struct file *file,
static int cachefiles_daemon_range_error(struct cachefiles_cache *cache,
char *args)
{
- kerror("Free space limits must be in range"
- " 0%%<=stop<cull<run<100%%");
+ pr_err("Free space limits must be in range 0%%<=stop<cull<run<100%%");
return -EINVAL;
}
@@ -476,12 +475,12 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args)
_enter(",%s", args);
if (!*args) {
- kerror("Empty directory specified");
+ pr_err("Empty directory specified");
return -EINVAL;
}
if (cache->rootdirname) {
- kerror("Second cache directory specified");
+ pr_err("Second cache directory specified");
return -EEXIST;
}
@@ -504,12 +503,12 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args)
_enter(",%s", args);
if (!*args) {
- kerror("Empty security context specified");
+ pr_err("Empty security context specified");
return -EINVAL;
}
if (cache->secctx) {
- kerror("Second security context specified");
+ pr_err("Second security context specified");
return -EINVAL;
}
@@ -532,7 +531,7 @@ static int cachefiles_daemon_tag(struct cachefiles_cache *cache, char *args)
_enter(",%s", args);
if (!*args) {
- kerror("Empty tag specified");
+ pr_err("Empty tag specified");
return -EINVAL;
}
@@ -563,12 +562,12 @@ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
goto inval;
if (!test_bit(CACHEFILES_READY, &cache->flags)) {
- kerror("cull applied to unready cache");
+ pr_err("cull applied to unready cache");
return -EIO;
}
if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
- kerror("cull applied to dead cache");
+ pr_err("cull applied to dead cache");
return -EIO;
}
@@ -588,11 +587,11 @@ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
notdir:
path_put(&path);
- kerror("cull command requires dirfd to be a directory");
+ pr_err("cull command requires dirfd to be a directory");
return -ENOTDIR;
inval:
- kerror("cull command requires dirfd and filename");
+ pr_err("cull command requires dirfd and filename");
return -EINVAL;
}
@@ -615,7 +614,7 @@ static int cachefiles_daemon_debug(struct cachefiles_cache *cache, char *args)
return 0;
inval:
- kerror("debug command requires mask");
+ pr_err("debug command requires mask");
return -EINVAL;
}
@@ -635,12 +634,12 @@ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
goto inval;
if (!test_bit(CACHEFILES_READY, &cache->flags)) {
- kerror("inuse applied to unready cache");
+ pr_err("inuse applied to unready cache");
return -EIO;
}
if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
- kerror("inuse applied to dead cache");
+ pr_err("inuse applied to dead cache");
return -EIO;
}
@@ -660,11 +659,11 @@ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
notdir:
path_put(&path);
- kerror("inuse command requires dirfd to be a directory");
+ pr_err("inuse command requires dirfd to be a directory");
return -ENOTDIR;
inval:
- kerror("inuse command requires dirfd and filename");
+ pr_err("inuse command requires dirfd and filename");
return -EINVAL;
}
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 57e17fe6121a..584743d456c3 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -146,8 +146,7 @@ static int cachefiles_lookup_object(struct fscache_object *_object)
if (ret < 0 && ret != -ETIMEDOUT) {
if (ret != -ENOBUFS)
- printk(KERN_WARNING
- "CacheFiles: Lookup failed error %d\n", ret);
+ pr_warn("Lookup failed error %d\n", ret);
fscache_object_lookup_error(&object->fscache);
}
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 5349473df1b1..3d50998abf57 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -9,6 +9,13 @@
* 2 of the Licence, or (at your option) any later version.
*/
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) "CacheFiles: " fmt
+
+
#include <linux/fscache-cache.h>
#include <linux/timer.h>
#include <linux/wait.h>
@@ -245,11 +252,10 @@ extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
/*
* error handling
*/
-#define kerror(FMT, ...) printk(KERN_ERR "CacheFiles: "FMT"\n", ##__VA_ARGS__)
#define cachefiles_io_error(___cache, FMT, ...) \
do { \
- kerror("I/O Error: " FMT, ##__VA_ARGS__); \
+ pr_err("I/O Error: " FMT, ##__VA_ARGS__); \
fscache_io_error(&(___cache)->cache); \
set_bit(CACHEFILES_DEAD, &(___cache)->flags); \
} while (0)
@@ -310,8 +316,8 @@ do { \
#define ASSERT(X) \
do { \
if (unlikely(!(X))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "CacheFiles: Assertion failed\n"); \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
BUG(); \
} \
} while (0)
@@ -319,9 +325,9 @@ do { \
#define ASSERTCMP(X, OP, Y) \
do { \
if (unlikely(!((X) OP (Y)))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "CacheFiles: Assertion failed\n"); \
- printk(KERN_ERR "%lx " #OP " %lx is false\n", \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
+ pr_err("%lx " #OP " %lx is false\n", \
(unsigned long)(X), (unsigned long)(Y)); \
BUG(); \
} \
@@ -330,8 +336,8 @@ do { \
#define ASSERTIF(C, X) \
do { \
if (unlikely((C) && !(X))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "CacheFiles: Assertion failed\n"); \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
BUG(); \
} \
} while (0)
@@ -339,9 +345,9 @@ do { \
#define ASSERTIFCMP(C, X, OP, Y) \
do { \
if (unlikely((C) && !((X) OP (Y)))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "CacheFiles: Assertion failed\n"); \
- printk(KERN_ERR "%lx " #OP " %lx is false\n", \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
+ pr_err("%lx " #OP " %lx is false\n", \
(unsigned long)(X), (unsigned long)(Y)); \
BUG(); \
} \
diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c
index 4bfa8cf43bf5..180edfb45f66 100644
--- a/fs/cachefiles/main.c
+++ b/fs/cachefiles/main.c
@@ -68,8 +68,7 @@ static int __init cachefiles_init(void)
SLAB_HWCACHE_ALIGN,
cachefiles_object_init_once);
if (!cachefiles_object_jar) {
- printk(KERN_NOTICE
- "CacheFiles: Failed to allocate an object jar\n");
+ pr_notice("Failed to allocate an object jar\n");
goto error_object_jar;
}
@@ -77,7 +76,7 @@ static int __init cachefiles_init(void)
if (ret < 0)
goto error_proc;
- printk(KERN_INFO "CacheFiles: Loaded\n");
+ pr_info("Loaded\n");
return 0;
error_proc:
@@ -85,7 +84,7 @@ error_proc:
error_object_jar:
misc_deregister(&cachefiles_dev);
error_dev:
- kerror("failed to register: %d", ret);
+ pr_err("failed to register: %d", ret);
return ret;
}
@@ -96,7 +95,7 @@ fs_initcall(cachefiles_init);
*/
static void __exit cachefiles_exit(void)
{
- printk(KERN_INFO "CacheFiles: Unloading\n");
+ pr_info("Unloading\n");
cachefiles_proc_cleanup();
kmem_cache_destroy(cachefiles_object_jar);
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index c0a681705104..5bf2b41e66d3 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -35,22 +35,21 @@ void __cachefiles_printk_object(struct cachefiles_object *object,
struct fscache_cookie *cookie;
unsigned keylen, loop;
- printk(KERN_ERR "%sobject: OBJ%x\n",
- prefix, object->fscache.debug_id);
- printk(KERN_ERR "%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n",
+ pr_err("%sobject: OBJ%x\n", prefix, object->fscache.debug_id);
+ pr_err("%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n",
prefix, object->fscache.state->name,
object->fscache.flags, work_busy(&object->fscache.work),
object->fscache.events, object->fscache.event_mask);
- printk(KERN_ERR "%sops=%u inp=%u exc=%u\n",
+ pr_err("%sops=%u inp=%u exc=%u\n",
prefix, object->fscache.n_ops, object->fscache.n_in_progress,
object->fscache.n_exclusive);
- printk(KERN_ERR "%sparent=%p\n",
+ pr_err("%sparent=%p\n",
prefix, object->fscache.parent);
spin_lock(&object->fscache.lock);
cookie = object->fscache.cookie;
if (cookie) {
- printk(KERN_ERR "%scookie=%p [pr=%p nd=%p fl=%lx]\n",
+ pr_err("%scookie=%p [pr=%p nd=%p fl=%lx]\n",
prefix,
object->fscache.cookie,
object->fscache.cookie->parent,
@@ -62,16 +61,16 @@ void __cachefiles_printk_object(struct cachefiles_object *object,
else
keylen = 0;
} else {
- printk(KERN_ERR "%scookie=NULL\n", prefix);
+ pr_err("%scookie=NULL\n", prefix);
keylen = 0;
}
spin_unlock(&object->fscache.lock);
if (keylen) {
- printk(KERN_ERR "%skey=[%u] '", prefix, keylen);
+ pr_err("%skey=[%u] '", prefix, keylen);
for (loop = 0; loop < keylen; loop++)
- printk("%02x", keybuf[loop]);
- printk("'\n");
+ pr_cont("%02x", keybuf[loop]);
+ pr_cont("'\n");
}
}
@@ -131,13 +130,11 @@ found_dentry:
dentry);
if (fscache_object_is_live(&object->fscache)) {
- printk(KERN_ERR "\n");
- printk(KERN_ERR "CacheFiles: Error:"
- " Can't preemptively bury live object\n");
+ pr_err("\n");
+ pr_err("Error: Can't preemptively bury live object\n");
cachefiles_printk_object(object, NULL);
} else if (test_and_set_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
- printk(KERN_ERR "CacheFiles: Error:"
- " Object already preemptively buried\n");
+ pr_err("Error: Object already preemptively buried\n");
}
write_unlock(&cache->active_lock);
@@ -160,7 +157,7 @@ try_again:
write_lock(&cache->active_lock);
if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
- printk(KERN_ERR "CacheFiles: Error: Object already active\n");
+ pr_err("Error: Object already active\n");
cachefiles_printk_object(object, NULL);
BUG();
}
@@ -193,9 +190,8 @@ try_again:
* need to wait for it to be destroyed */
wait_for_old_object:
if (fscache_object_is_live(&object->fscache)) {
- printk(KERN_ERR "\n");
- printk(KERN_ERR "CacheFiles: Error:"
- " Unexpected object collision\n");
+ pr_err("\n");
+ pr_err("Error: Unexpected object collision\n");
cachefiles_printk_object(object, xobject);
BUG();
}
@@ -241,9 +237,8 @@ wait_for_old_object:
}
if (timeout <= 0) {
- printk(KERN_ERR "\n");
- printk(KERN_ERR "CacheFiles: Error: Overlong"
- " wait for old active object to go away\n");
+ pr_err("\n");
+ pr_err("Error: Overlong wait for old active object to go away\n");
cachefiles_printk_object(object, xobject);
goto requeue;
}
@@ -548,7 +543,7 @@ lookup_again:
next, next->d_inode, next->d_inode->i_ino);
} else if (!S_ISDIR(next->d_inode->i_mode)) {
- kerror("inode %lu is not a directory",
+ pr_err("inode %lu is not a directory",
next->d_inode->i_ino);
ret = -ENOBUFS;
goto error;
@@ -579,7 +574,7 @@ lookup_again:
} else if (!S_ISDIR(next->d_inode->i_mode) &&
!S_ISREG(next->d_inode->i_mode)
) {
- kerror("inode %lu is not a file or directory",
+ pr_err("inode %lu is not a file or directory",
next->d_inode->i_ino);
ret = -ENOBUFS;
goto error;
@@ -773,7 +768,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
ASSERT(subdir->d_inode);
if (!S_ISDIR(subdir->d_inode->i_mode)) {
- kerror("%s is not a directory", dirname);
+ pr_err("%s is not a directory", dirname);
ret = -EIO;
goto check_error;
}
@@ -800,13 +795,13 @@ check_error:
mkdir_error:
mutex_unlock(&dir->d_inode->i_mutex);
dput(subdir);
- kerror("mkdir %s failed with error %d", dirname, ret);
+ pr_err("mkdir %s failed with error %d", dirname, ret);
return ERR_PTR(ret);
lookup_error:
mutex_unlock(&dir->d_inode->i_mutex);
ret = PTR_ERR(subdir);
- kerror("Lookup %s failed with error %d", dirname, ret);
+ pr_err("Lookup %s failed with error %d", dirname, ret);
return ERR_PTR(ret);
nomem_d_alloc:
@@ -896,7 +891,7 @@ lookup_error:
if (ret == -EIO) {
cachefiles_io_error(cache, "Lookup failed");
} else if (ret != -ENOMEM) {
- kerror("Internal error: %d", ret);
+ pr_err("Internal error: %d", ret);
ret = -EIO;
}
@@ -955,7 +950,7 @@ error:
}
if (ret != -ENOMEM) {
- kerror("Internal error: %d", ret);
+ pr_err("Internal error: %d", ret);
ret = -EIO;
}
diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c
index 039b5011d83b..396c18ea2764 100644
--- a/fs/cachefiles/security.c
+++ b/fs/cachefiles/security.c
@@ -34,9 +34,7 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache)
ret = set_security_override_from_ctx(new, cache->secctx);
if (ret < 0) {
put_cred(new);
- printk(KERN_ERR "CacheFiles:"
- " Security denies permission to nominate"
- " security context: error %d\n",
+ pr_err("Security denies permission to nominate security context: error %d\n",
ret);
goto error;
}
@@ -59,16 +57,14 @@ static int cachefiles_check_cache_dir(struct cachefiles_cache *cache,
ret = security_inode_mkdir(root->d_inode, root, 0);
if (ret < 0) {
- printk(KERN_ERR "CacheFiles:"
- " Security denies permission to make dirs: error %d",
+ pr_err("Security denies permission to make dirs: error %d",
ret);
return ret;
}
ret = security_inode_create(root->d_inode, root, 0);
if (ret < 0)
- printk(KERN_ERR "CacheFiles:"
- " Security denies permission to create files: error %d",
+ pr_err("Security denies permission to create files: error %d",
ret);
return ret;
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index 12b0eef84183..1ad51ffbb275 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -51,7 +51,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
}
if (ret != -EEXIST) {
- kerror("Can't set xattr on %*.*s [%lu] (err %d)",
+ pr_err("Can't set xattr on %*.*s [%lu] (err %d)",
dentry->d_name.len, dentry->d_name.len,
dentry->d_name.name, dentry->d_inode->i_ino,
-ret);
@@ -64,7 +64,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
if (ret == -ERANGE)
goto bad_type_length;
- kerror("Can't read xattr on %*.*s [%lu] (err %d)",
+ pr_err("Can't read xattr on %*.*s [%lu] (err %d)",
dentry->d_name.len, dentry->d_name.len,
dentry->d_name.name, dentry->d_inode->i_ino,
-ret);
@@ -85,14 +85,14 @@ error:
return ret;
bad_type_length:
- kerror("Cache object %lu type xattr length incorrect",
+ pr_err("Cache object %lu type xattr length incorrect",
dentry->d_inode->i_ino);
ret = -EIO;
goto error;
bad_type:
xtype[2] = 0;
- kerror("Cache object %*.*s [%lu] type %s not %s",
+ pr_err("Cache object %*.*s [%lu] type %s not %s",
dentry->d_name.len, dentry->d_name.len,
dentry->d_name.name, dentry->d_inode->i_ino,
xtype, type);
@@ -293,7 +293,7 @@ error:
return ret;
bad_type_length:
- kerror("Cache object %lu xattr length incorrect",
+ pr_err("Cache object %lu xattr length incorrect",
dentry->d_inode->i_ino);
ret = -EIO;
goto error;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b53278c9fd97..65a30e817dd8 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -694,7 +694,7 @@ static int ceph_writepages_start(struct address_space *mapping,
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
- pr_warning("writepage_start %p on forced umount\n", inode);
+ pr_warn("writepage_start %p on forced umount\n", inode);
return -EIO; /* we're in a forced umount, don't write! */
}
if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 16b54aa31f08..5a743ac141ab 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -71,9 +71,9 @@ static int mdsc_show(struct seq_file *s, void *p)
seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
if (req->r_got_unsafe)
- seq_printf(s, "\t(unsafe)");
+ seq_puts(s, "\t(unsafe)");
else
- seq_printf(s, "\t");
+ seq_puts(s, "\t");
if (req->r_inode) {
seq_printf(s, " #%llx", ceph_ino(req->r_inode));
@@ -119,7 +119,7 @@ static int mdsc_show(struct seq_file *s, void *p)
seq_printf(s, " %s", req->r_path2);
}
- seq_printf(s, "\n");
+ seq_puts(s, "\n");
}
mutex_unlock(&mdsc->mutex);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 233c6f96910a..e4fff9ff1c27 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -821,7 +821,7 @@ no_change:
spin_unlock(&ci->i_ceph_lock);
}
} else if (cap_fmode >= 0) {
- pr_warning("mds issued no caps on %llx.%llx\n",
+ pr_warn("mds issued no caps on %llx.%llx\n",
ceph_vinop(inode));
__ceph_get_fmode(ci, cap_fmode);
}
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 191398852a2e..fbc39c47bacd 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -53,10 +53,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
else
length = fl->fl_end - fl->fl_start + 1;
- if (lock_type == CEPH_LOCK_FCNTL)
- owner = secure_addr(fl->fl_owner);
- else
- owner = secure_addr(fl->fl_file);
+ owner = secure_addr(fl->fl_owner);
dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
"start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
@@ -314,10 +311,7 @@ int lock_to_ceph_filelock(struct file_lock *lock,
cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
cephlock->client = cpu_to_le64(0);
cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
- if (lock->fl_flags & FL_POSIX)
- cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
- else
- cephlock->owner = cpu_to_le64(secure_addr(lock->fl_file));
+ cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
switch (lock->fl_type) {
case F_RDLCK:
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 2b4d093d0563..9a33b98cb000 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2218,13 +2218,13 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
/* dup? */
if ((req->r_got_unsafe && !head->safe) ||
(req->r_got_safe && head->safe)) {
- pr_warning("got a dup %s reply on %llu from mds%d\n",
+ pr_warn("got a dup %s reply on %llu from mds%d\n",
head->safe ? "safe" : "unsafe", tid, mds);
mutex_unlock(&mdsc->mutex);
goto out;
}
if (req->r_got_safe && !head->safe) {
- pr_warning("got unsafe after safe on %llu from mds%d\n",
+ pr_warn("got unsafe after safe on %llu from mds%d\n",
tid, mds);
mutex_unlock(&mdsc->mutex);
goto out;
@@ -3525,7 +3525,7 @@ static void peer_reset(struct ceph_connection *con)
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
- pr_warning("mds%d closed our session\n", s->s_mds);
+ pr_warn("mds%d closed our session\n", s->s_mds);
send_mds_reconnect(mdsc, s);
}
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 132b64eeecd4..261531e55e9d 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -62,7 +62,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
ceph_decode_16_safe(p, end, version, bad);
if (version > 3) {
- pr_warning("got mdsmap version %d > 3, failing", version);
+ pr_warn("got mdsmap version %d > 3, failing", version);
goto bad;
}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5be1f997ecde..6aaa8112c538 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -87,10 +87,6 @@ extern mempool_t *cifs_mid_poolp;
struct workqueue_struct *cifsiod_wq;
-#ifdef CONFIG_CIFS_SMB2
-__u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
-#endif
-
/*
* Bumps refcount for cifs super block.
* Note that it should be only called if a referece to VFS super block is
@@ -251,11 +247,7 @@ cifs_alloc_inode(struct super_block *sb)
* server, can not assume caching of file data or metadata.
*/
cifs_set_oplock_level(cifs_inode, 0);
- cifs_inode->delete_pending = false;
- cifs_inode->invalid_mapping = false;
- clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cifs_inode->flags);
- clear_bit(CIFS_INODE_PENDING_WRITERS, &cifs_inode->flags);
- clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cifs_inode->flags);
+ cifs_inode->flags = 0;
spin_lock_init(&cifs_inode->writers_lock);
cifs_inode->writers = 0;
cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */
@@ -302,7 +294,7 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
- seq_printf(s, ",addr=");
+ seq_puts(s, ",addr=");
switch (server->dstaddr.ss_family) {
case AF_INET:
@@ -314,7 +306,7 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
seq_printf(s, "%%%u", sa6->sin6_scope_id);
break;
default:
- seq_printf(s, "(unknown)");
+ seq_puts(s, "(unknown)");
}
}
@@ -324,45 +316,45 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
if (ses->sectype == Unspecified)
return;
- seq_printf(s, ",sec=");
+ seq_puts(s, ",sec=");
switch (ses->sectype) {
case LANMAN:
- seq_printf(s, "lanman");
+ seq_puts(s, "lanman");
break;
case NTLMv2:
- seq_printf(s, "ntlmv2");
+ seq_puts(s, "ntlmv2");
break;
case NTLM:
- seq_printf(s, "ntlm");
+ seq_puts(s, "ntlm");
break;
case Kerberos:
- seq_printf(s, "krb5");
+ seq_puts(s, "krb5");
break;
case RawNTLMSSP:
- seq_printf(s, "ntlmssp");
+ seq_puts(s, "ntlmssp");
break;
default:
/* shouldn't ever happen */
- seq_printf(s, "unknown");
+ seq_puts(s, "unknown");
break;
}
if (ses->sign)
- seq_printf(s, "i");
+ seq_puts(s, "i");
}
static void
cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb)
{
- seq_printf(s, ",cache=");
+ seq_puts(s, ",cache=");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
- seq_printf(s, "strict");
+ seq_puts(s, "strict");
else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
- seq_printf(s, "none");
+ seq_puts(s, "none");
else
- seq_printf(s, "loose");
+ seq_puts(s, "loose");
}
static void
@@ -395,7 +387,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
cifs_show_cache_flavor(s, cifs_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)
- seq_printf(s, ",multiuser");
+ seq_puts(s, ",multiuser");
else if (tcon->ses->user_name)
seq_printf(s, ",username=%s", tcon->ses->user_name);
@@ -421,16 +413,16 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_printf(s, ",uid=%u",
from_kuid_munged(&init_user_ns, cifs_sb->mnt_uid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
- seq_printf(s, ",forceuid");
+ seq_puts(s, ",forceuid");
else
- seq_printf(s, ",noforceuid");
+ seq_puts(s, ",noforceuid");
seq_printf(s, ",gid=%u",
from_kgid_munged(&init_user_ns, cifs_sb->mnt_gid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
- seq_printf(s, ",forcegid");
+ seq_puts(s, ",forcegid");
else
- seq_printf(s, ",noforcegid");
+ seq_puts(s, ",noforcegid");
cifs_show_address(s, tcon->ses->server);
@@ -442,47 +434,47 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
cifs_show_nls(s, cifs_sb->local_nls);
if (tcon->seal)
- seq_printf(s, ",seal");
+ seq_puts(s, ",seal");
if (tcon->nocase)
- seq_printf(s, ",nocase");
+ seq_puts(s, ",nocase");
if (tcon->retry)
- seq_printf(s, ",hard");
+ seq_puts(s, ",hard");
if (tcon->unix_ext)
- seq_printf(s, ",unix");
+ seq_puts(s, ",unix");
else
- seq_printf(s, ",nounix");
+ seq_puts(s, ",nounix");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
- seq_printf(s, ",posixpaths");
+ seq_puts(s, ",posixpaths");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
- seq_printf(s, ",setuids");
+ seq_puts(s, ",setuids");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
- seq_printf(s, ",serverino");
+ seq_puts(s, ",serverino");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
- seq_printf(s, ",rwpidforward");
+ seq_puts(s, ",rwpidforward");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
- seq_printf(s, ",forcemand");
+ seq_puts(s, ",forcemand");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- seq_printf(s, ",nouser_xattr");
+ seq_puts(s, ",nouser_xattr");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
- seq_printf(s, ",mapchars");
+ seq_puts(s, ",mapchars");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
- seq_printf(s, ",sfu");
+ seq_puts(s, ",sfu");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
- seq_printf(s, ",nobrl");
+ seq_puts(s, ",nobrl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
- seq_printf(s, ",cifsacl");
+ seq_puts(s, ",cifsacl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
- seq_printf(s, ",dynperm");
+ seq_puts(s, ",dynperm");
if (root->d_sb->s_flags & MS_POSIXACL)
- seq_printf(s, ",acl");
+ seq_puts(s, ",acl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
- seq_printf(s, ",mfsymlinks");
+ seq_puts(s, ",mfsymlinks");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
- seq_printf(s, ",fsc");
+ seq_puts(s, ",fsc");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
- seq_printf(s, ",nostrictsync");
+ seq_puts(s, ",nostrictsync");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
- seq_printf(s, ",noperm");
+ seq_puts(s, ",noperm");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
seq_printf(s, ",backupuid=%u",
from_kuid_munged(&init_user_ns,
@@ -1192,10 +1184,6 @@ init_cifs(void)
spin_lock_init(&cifs_file_list_lock);
spin_lock_init(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_SMB2
- get_random_bytes(cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
-#endif
-
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 26a754f49ba1..8fe51166d6e3 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -22,20 +22,28 @@
#ifndef _CIFSFS_H
#define _CIFSFS_H
+#include <linux/hash.h>
+
#define ROOT_I 2
/*
* ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
- * so that it will fit.
+ * so that it will fit. We use hash_64 to convert the value to 31 bits, and
+ * then add 1, to ensure that we don't end up with a 0 as the value.
*/
+#if BITS_PER_LONG == 64
static inline ino_t
cifs_uniqueid_to_ino_t(u64 fileid)
{
- ino_t ino = (ino_t) fileid;
- if (sizeof(ino_t) < sizeof(u64))
- ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8;
- return ino;
+ return (ino_t)fileid;
}
+#else
+static inline ino_t
+cifs_uniqueid_to_ino_t(u64 fileid)
+{
+ return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+}
+#endif
extern struct file_system_type cifs_fs_type;
extern const struct address_space_operations cifs_addr_ops;
@@ -67,6 +75,8 @@ extern int cifs_revalidate_dentry_attr(struct dentry *);
extern int cifs_revalidate_file(struct file *filp);
extern int cifs_revalidate_dentry(struct dentry *);
extern int cifs_invalidate_mapping(struct inode *inode);
+extern int cifs_revalidate_mapping(struct inode *inode);
+extern int cifs_zap_mapping(struct inode *inode);
extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int cifs_setattr(struct dentry *, struct iattr *);
@@ -130,5 +140,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.02"
+#define CIFS_VERSION "2.03"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 30f6e9251a4a..de6aed8c78e5 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -559,6 +559,7 @@ struct TCP_Server_Info {
int echo_credits; /* echo reserved slots */
int oplock_credits; /* oplock break reserved slots */
bool echoes:1; /* enable echoes */
+ __u8 client_guid[SMB2_CLIENT_GUID_SIZE]; /* Client GUID */
#endif
u16 dialect; /* dialect index that server chose */
bool oplocks:1; /* enable oplocks */
@@ -1113,12 +1114,13 @@ struct cifsInodeInfo {
__u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */
unsigned int oplock; /* oplock/lease level we have */
unsigned int epoch; /* used to track lease state changes */
- bool delete_pending; /* DELETE_ON_CLOSE is set */
- bool invalid_mapping; /* pagecache is invalid */
- unsigned long flags;
#define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */
#define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */
#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */
+#define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */
+#define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */
+#define CIFS_INO_LOCK (5) /* lock bit for synchronization */
+ unsigned long flags;
spinlock_t writers_lock;
unsigned int writers; /* Number of writers on this inode */
unsigned long time; /* jiffies of last update of inode */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 8813ff776ba3..20d75b8ddb26 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2144,6 +2144,9 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
sizeof(tcp_ses->srcaddr));
memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
sizeof(tcp_ses->dstaddr));
+#ifdef CONFIG_CIFS_SMB2
+ get_random_bytes(tcp_ses->client_guid, SMB2_CLIENT_GUID_SIZE);
+#endif
/*
* at this point we are the only ones with the pointer
* to the struct since the kernel thread not created yet
@@ -2225,7 +2228,7 @@ static int match_session(struct cifs_ses *ses, struct smb_vol *vol)
vol->username ? vol->username : "",
CIFS_MAX_USERNAME_LEN))
return 0;
- if (strlen(vol->username) != 0 &&
+ if ((vol->username && strlen(vol->username) != 0) &&
ses->password != NULL &&
strncmp(ses->password,
vol->password ? vol->password : "",
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5ed03e0b8b40..208f56eca4bf 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -335,7 +335,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
spin_unlock(&cifs_file_list_lock);
if (fid->purge_cache)
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
file->private_data = cfile;
return cfile;
@@ -392,7 +392,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
* again and get at least level II oplock.
*/
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
- CIFS_I(inode)->invalid_mapping = true;
+ set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
cifs_set_oplock_level(cifsi, 0);
}
spin_unlock(&cifs_file_list_lock);
@@ -1529,7 +1529,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
*/
if (!CIFS_CACHE_WRITE(CIFS_I(inode)) &&
CIFS_CACHE_READ(CIFS_I(inode))) {
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p due to mand locks\n",
inode);
CIFS_I(inode)->oplock = 0;
@@ -2218,7 +2218,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
file->f_path.dentry->d_name.name, datasync);
if (!CIFS_CACHE_READ(CIFS_I(inode))) {
- rc = cifs_invalidate_mapping(inode);
+ rc = cifs_zap_mapping(inode);
if (rc) {
cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc);
rc = 0; /* don't care about it in fsync */
@@ -2562,7 +2562,7 @@ ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos);
if (written > 0) {
- CIFS_I(inode)->invalid_mapping = true;
+ set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
iocb->ki_pos = pos;
}
@@ -2649,7 +2649,7 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
* request comes - break it on the client to prevent reading
* an old data.
*/
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n",
inode);
cinode->oplock = 0;
@@ -3112,7 +3112,7 @@ int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
xid = get_xid();
if (!CIFS_CACHE_READ(CIFS_I(inode))) {
- rc = cifs_invalidate_mapping(inode);
+ rc = cifs_zap_mapping(inode);
if (rc)
return rc;
}
@@ -3670,7 +3670,7 @@ void cifs_oplock_break(struct work_struct *work)
if (!CIFS_CACHE_READ(cinode)) {
rc = filemap_fdatawait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
}
cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc);
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a22d667f1069..a174605f6afa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -22,6 +22,7 @@
#include <linux/stat.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
+#include <linux/freezer.h>
#include <asm/div64.h>
#include "cifsfs.h"
#include "cifspdu.h"
@@ -117,7 +118,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
cifs_dbg(FYI, "%s: invalidating inode %llu mapping\n",
__func__, cifs_i->uniqueid);
- cifs_i->invalid_mapping = true;
+ set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
}
/*
@@ -177,7 +178,10 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
else
cifs_i->time = jiffies;
- cifs_i->delete_pending = fattr->cf_flags & CIFS_FATTR_DELETE_PENDING;
+ if (fattr->cf_flags & CIFS_FATTR_DELETE_PENDING)
+ set_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
+ else
+ clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
cifs_i->server_eof = fattr->cf_eof;
/*
@@ -1121,7 +1125,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
}
/* try to set DELETE_ON_CLOSE */
- if (!cifsInode->delete_pending) {
+ if (!test_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags)) {
rc = CIFSSMBSetFileDisposition(xid, tcon, true, fid.netfid,
current->tgid);
/*
@@ -1138,7 +1142,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
rc = -EBUSY;
goto undo_rename;
}
- cifsInode->delete_pending = true;
+ set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags);
}
out_close:
@@ -1759,23 +1763,62 @@ int
cifs_invalidate_mapping(struct inode *inode)
{
int rc = 0;
- struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-
- cifs_i->invalid_mapping = false;
if (inode->i_mapping && inode->i_mapping->nrpages != 0) {
rc = invalidate_inode_pages2(inode->i_mapping);
- if (rc) {
+ if (rc)
cifs_dbg(VFS, "%s: could not invalidate inode %p\n",
__func__, inode);
- cifs_i->invalid_mapping = true;
- }
}
cifs_fscache_reset_inode_cookie(inode);
return rc;
}
+/**
+ * cifs_wait_bit_killable - helper for functions that are sleeping on bit locks
+ * @word: long word containing the bit lock
+ */
+static int
+cifs_wait_bit_killable(void *word)
+{
+ if (fatal_signal_pending(current))
+ return -ERESTARTSYS;
+ freezable_schedule_unsafe();
+ return 0;
+}
+
+int
+cifs_revalidate_mapping(struct inode *inode)
+{
+ int rc;
+ unsigned long *flags = &CIFS_I(inode)->flags;
+
+ rc = wait_on_bit_lock(flags, CIFS_INO_LOCK, cifs_wait_bit_killable,
+ TASK_KILLABLE);
+ if (rc)
+ return rc;
+
+ if (test_and_clear_bit(CIFS_INO_INVALID_MAPPING, flags)) {
+ rc = cifs_invalidate_mapping(inode);
+ if (rc)
+ set_bit(CIFS_INO_INVALID_MAPPING, flags);
+ }
+
+ clear_bit_unlock(CIFS_INO_LOCK, flags);
+ smp_mb__after_atomic();
+ wake_up_bit(flags, CIFS_INO_LOCK);
+
+ return rc;
+}
+
+int
+cifs_zap_mapping(struct inode *inode)
+{
+ set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
+ return cifs_revalidate_mapping(inode);
+}
+
int cifs_revalidate_file_attr(struct file *filp)
{
int rc = 0;
@@ -1842,9 +1885,7 @@ int cifs_revalidate_file(struct file *filp)
if (rc)
return rc;
- if (CIFS_I(inode)->invalid_mapping)
- rc = cifs_invalidate_mapping(inode);
- return rc;
+ return cifs_revalidate_mapping(inode);
}
/* revalidate a dentry's inode attributes */
@@ -1857,9 +1898,7 @@ int cifs_revalidate_dentry(struct dentry *dentry)
if (rc)
return rc;
- if (CIFS_I(inode)->invalid_mapping)
- rc = cifs_invalidate_mapping(inode);
- return rc;
+ return cifs_revalidate_mapping(inode);
}
int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 77492301cc2b..45cb59bcc791 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -85,7 +85,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
goto out_fput;
}
- src_inode = src_file.file->f_dentry->d_inode;
+ src_inode = file_inode(src_file.file);
/*
* Note: cifs case is easier than btrfs since server responsible for
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 049884552e76..6834b9c3bec1 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -795,8 +795,8 @@ cifs_print_status(__u32 status_code)
while (nt_errs[idx].nt_errstr != NULL) {
if (((nt_errs[idx].nt_errcode) & 0xFFFFFF) ==
(status_code & 0xFFFFFF)) {
- printk(KERN_NOTICE "Status code returned 0x%08x %s\n",
- status_code, nt_errs[idx].nt_errstr);
+ pr_notice("Status code returned 0x%08x %s\n",
+ status_code, nt_errs[idx].nt_errstr);
}
idx++;
}
@@ -941,8 +941,9 @@ cifs_UnixTimeToNT(struct timespec t)
return (u64) t.tv_sec * 10000000 + t.tv_nsec/100 + NTFS_TIME_OFFSET;
}
-static int total_days_of_prev_months[] =
-{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334};
+static const int total_days_of_prev_months[] = {
+ 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334
+};
struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
{
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 35ddc3ed119d..787844bde384 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1047,6 +1047,7 @@ smb2_create_lease_buf(u8 *lease_key, u8 oplock)
buf->ccontext.NameOffset = cpu_to_le16(offsetof
(struct create_lease, Name));
buf->ccontext.NameLength = cpu_to_le16(4);
+ /* SMB2_CREATE_REQUEST_LEASE is "RqLs" */
buf->Name[0] = 'R';
buf->Name[1] = 'q';
buf->Name[2] = 'L';
@@ -1073,6 +1074,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
buf->ccontext.NameOffset = cpu_to_le16(offsetof
(struct create_lease_v2, Name));
buf->ccontext.NameLength = cpu_to_le16(4);
+ /* SMB2_CREATE_REQUEST_LEASE is "RqLs" */
buf->Name[0] = 'R';
buf->Name[1] = 'q';
buf->Name[2] = 'L';
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 3802f8c94acc..b0b260dbb19d 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -375,7 +375,12 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
req->Capabilities = cpu_to_le32(ses->server->vals->req_capabilities);
- memcpy(req->ClientGUID, cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
+ /* ClientGUID must be zero for SMB2.02 dialect */
+ if (ses->server->vals->protocol_id == SMB20_PROT_ID)
+ memset(req->ClientGUID, 0, SMB2_CLIENT_GUID_SIZE);
+ else
+ memcpy(req->ClientGUID, server->client_guid,
+ SMB2_CLIENT_GUID_SIZE);
iov[0].iov_base = (char *)req;
/* 4 for rfc1002 length field */
@@ -478,7 +483,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
vneg_inbuf.Capabilities =
cpu_to_le32(tcon->ses->server->vals->req_capabilities);
- memcpy(vneg_inbuf.Guid, cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
+ memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
+ SMB2_CLIENT_GUID_SIZE);
if (tcon->ses->sign)
vneg_inbuf.SecurityMode =
@@ -966,6 +972,7 @@ create_durable_buf(void)
buf->ccontext.NameOffset = cpu_to_le16(offsetof
(struct create_durable, Name));
buf->ccontext.NameLength = cpu_to_le16(4);
+ /* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DHnQ" */
buf->Name[0] = 'D';
buf->Name[1] = 'H';
buf->Name[2] = 'n';
@@ -990,6 +997,7 @@ create_reconnect_durable_buf(struct cifs_fid *fid)
buf->ccontext.NameLength = cpu_to_le16(4);
buf->Data.Fid.PersistentFileId = fid->persistent_fid;
buf->Data.Fid.VolatileFileId = fid->volatile_fid;
+ /* SMB2_CREATE_DURABLE_HANDLE_RECONNECT is "DHnC" */
buf->Name[0] = 'D';
buf->Name[1] = 'H';
buf->Name[2] = 'n';
@@ -1089,6 +1097,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
int rc = 0;
unsigned int num_iovecs = 2;
__u32 file_attributes = 0;
+ char *dhc_buf = NULL, *lc_buf = NULL;
cifs_dbg(FYI, "create/open\n");
@@ -1155,6 +1164,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
kfree(copy_path);
return rc;
}
+ lc_buf = iov[num_iovecs-1].iov_base;
}
if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -1169,9 +1179,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
if (rc) {
cifs_small_buf_release(req);
kfree(copy_path);
- kfree(iov[num_iovecs-1].iov_base);
+ kfree(lc_buf);
return rc;
}
+ dhc_buf = iov[num_iovecs-1].iov_base;
}
rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
@@ -1203,6 +1214,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
*oplock = rsp->OplockLevel;
creat_exit:
kfree(copy_path);
+ kfree(lc_buf);
+ kfree(dhc_buf);
free_rsp_buf(resp_buftype, rsp);
return rc;
}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 2022c542ea3a..69f3595d3952 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -183,8 +183,6 @@ struct smb2_symlink_err_rsp {
#define SMB2_CLIENT_GUID_SIZE 16
-extern __u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
-
struct smb2_negotiate_req {
struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 36 */
@@ -437,11 +435,15 @@ struct smb2_tree_disconnect_rsp {
#define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */
#define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ"
#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE "AlSi"
+#define SMB2_CREATE_ALLOCATION_SIZE "AISi"
#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
#define SMB2_CREATE_TIMEWARP_REQUEST "TWrp"
#define SMB2_CREATE_QUERY_ON_DISK_ID "QFid"
#define SMB2_CREATE_REQUEST_LEASE "RqLs"
+#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 "DH2Q"
+#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C"
+#define SMB2_CREATE_APP_INSTANCE_ID 0x45BCA66AEFA7F74A9008FA462E144D74
+#define SVHDX_OPEN_DEVICE_CONTEXT 0x83CE6F1AD851E0986E34401CC9BCFCE9
struct smb2_create_req {
struct smb2_hdr hdr;
diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c
index 911cf30d057d..7740b1c871c1 100644
--- a/fs/coda/cnode.c
+++ b/fs/coda/cnode.c
@@ -101,7 +101,7 @@ struct inode *coda_cnode_make(struct CodaFid *fid, struct super_block *sb)
inode = coda_iget(sb, fid, &attr);
if (IS_ERR(inode))
- printk("coda_cnode_make: coda_iget failed\n");
+ pr_warn("%s: coda_iget failed\n", __func__);
return inode;
}
@@ -137,7 +137,7 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb)
unsigned long hash = coda_f2i(fid);
if ( !sb ) {
- printk("coda_fid_to_inode: no sb!\n");
+ pr_warn("%s: no sb!\n", __func__);
return NULL;
}
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index e7550cb9fb74..d42b725b1d21 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -12,6 +12,12 @@
#ifndef _LINUX_CODA_FS
#define _LINUX_CODA_FS
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/kernel.h>
#include <linux/param.h>
#include <linux/mm.h>
@@ -63,7 +69,7 @@ void coda_sysctl_clean(void);
else \
ptr = (cast)vzalloc((unsigned long) size); \
if (!ptr) \
- printk("kernel malloc returns 0 at %s:%d\n", __FILE__, __LINE__); \
+ pr_warn("kernel malloc returns 0 at %s:%d\n", __FILE__, __LINE__); \
} while (0)
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 5efbb5ee0adc..cd8a63238b11 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -102,7 +102,7 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig
int type = 0;
if (length > CODA_MAXNAMLEN) {
- printk(KERN_ERR "name too long: lookup, %s (%*s)\n",
+ pr_err("name too long: lookup, %s (%*s)\n",
coda_i2s(dir), (int)length, name);
return ERR_PTR(-ENAMETOOLONG);
}
@@ -453,23 +453,23 @@ static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx)
ret = kernel_read(host_file, ctx->pos - 2, (char *)vdir,
sizeof(*vdir));
if (ret < 0) {
- printk(KERN_ERR "coda readdir: read dir %s failed %d\n",
- coda_f2s(&cii->c_fid), ret);
+ pr_err("%s: read dir %s failed %d\n",
+ __func__, coda_f2s(&cii->c_fid), ret);
break;
}
if (ret == 0) break; /* end of directory file reached */
/* catch truncated reads */
if (ret < vdir_size || ret < vdir_size + vdir->d_namlen) {
- printk(KERN_ERR "coda readdir: short read on %s\n",
- coda_f2s(&cii->c_fid));
+ pr_err("%s: short read on %s\n",
+ __func__, coda_f2s(&cii->c_fid));
ret = -EBADF;
break;
}
/* validate whether the directory file actually makes sense */
if (vdir->d_reclen < vdir_size + vdir->d_namlen) {
- printk(KERN_ERR "coda readdir: invalid dir %s\n",
- coda_f2s(&cii->c_fid));
+ pr_err("%s: invalid dir %s\n",
+ __func__, coda_f2s(&cii->c_fid));
ret = -EBADF;
break;
}
@@ -589,8 +589,8 @@ int coda_revalidate_inode(struct inode *inode)
coda_vattr_to_iattr(inode, &attr);
if ((old_mode & S_IFMT) != (inode->i_mode & S_IFMT)) {
- printk("Coda: inode %ld, fid %s changed type!\n",
- inode->i_ino, coda_f2s(&(cii->c_fid)));
+ pr_warn("inode %ld, fid %s changed type!\n",
+ inode->i_ino, coda_f2s(&(cii->c_fid)));
}
/* the following can happen when a local fid is replaced
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index d9c7751f10ac..fe3afb2de880 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -119,12 +119,12 @@ static int get_device_index(struct coda_mount_data *data)
int idx;
if (data == NULL) {
- printk("coda_read_super: Bad mount data\n");
+ pr_warn("%s: Bad mount data\n", __func__);
return -1;
}
if (data->version != CODA_MOUNT_VERSION) {
- printk("coda_read_super: Bad mount version\n");
+ pr_warn("%s: Bad mount version\n", __func__);
return -1;
}
@@ -141,13 +141,13 @@ static int get_device_index(struct coda_mount_data *data)
fdput(f);
if (idx < 0 || idx >= MAX_CODADEVS) {
- printk("coda_read_super: Bad minor number\n");
+ pr_warn("%s: Bad minor number\n", __func__);
return -1;
}
return idx;
Ebadf:
- printk("coda_read_super: Bad file\n");
+ pr_warn("%s: Bad file\n", __func__);
return -1;
}
@@ -168,19 +168,19 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
if(idx == -1)
idx = 0;
- printk(KERN_INFO "coda_read_super: device index: %i\n", idx);
+ pr_info("%s: device index: %i\n", __func__, idx);
vc = &coda_comms[idx];
mutex_lock(&vc->vc_mutex);
if (!vc->vc_inuse) {
- printk("coda_read_super: No pseudo device\n");
+ pr_warn("%s: No pseudo device\n", __func__);
error = -EINVAL;
goto unlock_out;
}
if (vc->vc_sb) {
- printk("coda_read_super: Device already mounted\n");
+ pr_warn("%s: Device already mounted\n", __func__);
error = -EBUSY;
goto unlock_out;
}
@@ -204,22 +204,23 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
/* get root fid from Venus: this needs the root inode */
error = venus_rootfid(sb, &fid);
if ( error ) {
- printk("coda_read_super: coda_get_rootfid failed with %d\n",
- error);
+ pr_warn("%s: coda_get_rootfid failed with %d\n",
+ __func__, error);
goto error;
}
- printk("coda_read_super: rootfid is %s\n", coda_f2s(&fid));
+ pr_info("%s: rootfid is %s\n", __func__, coda_f2s(&fid));
/* make root inode */
root = coda_cnode_make(&fid, sb);
if (IS_ERR(root)) {
error = PTR_ERR(root);
- printk("Failure of coda_cnode_make for root: error %d\n", error);
+ pr_warn("Failure of coda_cnode_make for root: error %d\n",
+ error);
goto error;
}
- printk("coda_read_super: rootinode is %ld dev %s\n",
- root->i_ino, root->i_sb->s_id);
+ pr_info("%s: rootinode is %ld dev %s\n",
+ __func__, root->i_ino, root->i_sb->s_id);
sb->s_root = d_make_root(root);
if (!sb->s_root) {
error = -EINVAL;
@@ -246,7 +247,7 @@ static void coda_put_super(struct super_block *sb)
sb->s_fs_info = NULL;
mutex_unlock(&vcp->vc_mutex);
- printk("Coda: Bye bye.\n");
+ pr_info("Bye bye.\n");
}
static void coda_evict_inode(struct inode *inode)
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index ebc2bae6c289..5c1e4242368b 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -114,14 +114,14 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
int size = sizeof(*dcbuf);
if ( nbytes < sizeof(struct coda_out_hdr) ) {
- printk("coda_downcall opc %d uniq %d, not enough!\n",
- hdr.opcode, hdr.unique);
+ pr_warn("coda_downcall opc %d uniq %d, not enough!\n",
+ hdr.opcode, hdr.unique);
count = nbytes;
goto out;
}
if ( nbytes > size ) {
- printk("Coda: downcall opc %d, uniq %d, too much!",
- hdr.opcode, hdr.unique);
+ pr_warn("downcall opc %d, uniq %d, too much!",
+ hdr.opcode, hdr.unique);
nbytes = size;
}
CODA_ALLOC(dcbuf, union outputArgs *, nbytes);
@@ -136,7 +136,8 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
CODA_FREE(dcbuf, nbytes);
if (error) {
- printk("psdev_write: coda_downcall error: %d\n", error);
+ pr_warn("%s: coda_downcall error: %d\n",
+ __func__, error);
retval = error;
goto out;
}
@@ -157,16 +158,17 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
mutex_unlock(&vcp->vc_mutex);
if (!req) {
- printk("psdev_write: msg (%d, %d) not found\n",
- hdr.opcode, hdr.unique);
+ pr_warn("%s: msg (%d, %d) not found\n",
+ __func__, hdr.opcode, hdr.unique);
retval = -ESRCH;
goto out;
}
/* move data into response buffer. */
if (req->uc_outSize < nbytes) {
- printk("psdev_write: too much cnt: %d, cnt: %ld, opc: %d, uniq: %d.\n",
- req->uc_outSize, (long)nbytes, hdr.opcode, hdr.unique);
+ pr_warn("%s: too much cnt: %d, cnt: %ld, opc: %d, uniq: %d.\n",
+ __func__, req->uc_outSize, (long)nbytes,
+ hdr.opcode, hdr.unique);
nbytes = req->uc_outSize; /* don't have more space! */
}
if (copy_from_user(req->uc_data, buf, nbytes)) {
@@ -240,8 +242,8 @@ static ssize_t coda_psdev_read(struct file * file, char __user * buf,
/* Move the input args into userspace */
count = req->uc_inSize;
if (nbytes < req->uc_inSize) {
- printk ("psdev_read: Venus read %ld bytes of %d in message\n",
- (long)nbytes, req->uc_inSize);
+ pr_warn("%s: Venus read %ld bytes of %d in message\n",
+ __func__, (long)nbytes, req->uc_inSize);
count = nbytes;
}
@@ -305,7 +307,7 @@ static int coda_psdev_release(struct inode * inode, struct file * file)
struct upc_req *req, *tmp;
if (!vcp || !vcp->vc_inuse ) {
- printk("psdev_release: Not open.\n");
+ pr_warn("%s: Not open.\n", __func__);
return -1;
}
@@ -354,8 +356,8 @@ static int init_coda_psdev(void)
{
int i, err = 0;
if (register_chrdev(CODA_PSDEV_MAJOR, "coda", &coda_psdev_fops)) {
- printk(KERN_ERR "coda_psdev: unable to get major %d\n",
- CODA_PSDEV_MAJOR);
+ pr_err("%s: unable to get major %d\n",
+ __func__, CODA_PSDEV_MAJOR);
return -EIO;
}
coda_psdev_class = class_create(THIS_MODULE, "coda");
@@ -393,13 +395,13 @@ static int __init init_coda(void)
goto out2;
status = init_coda_psdev();
if ( status ) {
- printk("Problem (%d) in init_coda_psdev\n", status);
+ pr_warn("Problem (%d) in init_coda_psdev\n", status);
goto out1;
}
status = register_filesystem(&coda_fs_type);
if (status) {
- printk("coda: failed to register filesystem!\n");
+ pr_warn("failed to register filesystem!\n");
goto out;
}
return 0;
@@ -420,9 +422,8 @@ static void __exit exit_coda(void)
int err, i;
err = unregister_filesystem(&coda_fs_type);
- if ( err != 0 ) {
- printk("coda: failed to unregister filesystem\n");
- }
+ if (err != 0)
+ pr_warn("failed to unregister filesystem\n");
for (i = 0; i < MAX_CODADEVS; i++)
device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i));
class_destroy(coda_psdev_class);
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index af56ad56a89a..34218a8a28cd 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -14,7 +14,7 @@
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *fs_table_header;
-static ctl_table coda_table[] = {
+static struct ctl_table coda_table[] = {
{
.procname = "timeout",
.data = &coda_timeout,
@@ -39,7 +39,7 @@ static ctl_table coda_table[] = {
{}
};
-static ctl_table fs_table[] = {
+static struct ctl_table fs_table[] = {
{
.procname = "coda",
.mode = 0555,
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index 3a731976dc5e..21fcf8dcb9cd 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -508,8 +508,8 @@ int venus_pioctl(struct super_block *sb, struct CodaFid *fid,
inp->coda_ioctl.data = (char *)(INSIZE(ioctl));
/* get the data out of user space */
- if ( copy_from_user((char*)inp + (long)inp->coda_ioctl.data,
- data->vi.in, data->vi.in_size) ) {
+ if (copy_from_user((char *)inp + (long)inp->coda_ioctl.data,
+ data->vi.in, data->vi.in_size)) {
error = -EINVAL;
goto exit;
}
@@ -518,8 +518,8 @@ int venus_pioctl(struct super_block *sb, struct CodaFid *fid,
&outsize, inp);
if (error) {
- printk("coda_pioctl: Venus returns: %d for %s\n",
- error, coda_f2s(fid));
+ pr_warn("%s: Venus returns: %d for %s\n",
+ __func__, error, coda_f2s(fid));
goto exit;
}
@@ -675,7 +675,7 @@ static int coda_upcall(struct venus_comm *vcp,
mutex_lock(&vcp->vc_mutex);
if (!vcp->vc_inuse) {
- printk(KERN_NOTICE "coda: Venus dead, not sending upcall\n");
+ pr_notice("Venus dead, not sending upcall\n");
error = -ENXIO;
goto exit;
}
@@ -725,7 +725,7 @@ static int coda_upcall(struct venus_comm *vcp,
error = -EINTR;
if ((req->uc_flags & CODA_REQ_ABORT) || !signal_pending(current)) {
- printk(KERN_WARNING "coda: Unexpected interruption.\n");
+ pr_warn("Unexpected interruption.\n");
goto exit;
}
@@ -735,7 +735,7 @@ static int coda_upcall(struct venus_comm *vcp,
/* Venus saw the upcall, make sure we can send interrupt signal */
if (!vcp->vc_inuse) {
- printk(KERN_INFO "coda: Venus dead, not sending signal.\n");
+ pr_info("Venus dead, not sending signal.\n");
goto exit;
}
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index b5f0a3b91f18..bd4a3c167091 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -24,6 +24,12 @@
* configfs Copyright (C) 2005 Oracle. All rights reserved.
*/
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/spinlock.h>
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index e081acbac2e7..668dcabc5695 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -940,9 +940,9 @@ static void client_drop_item(struct config_item *parent_item,
#ifdef DEBUG
static void configfs_dump_one(struct configfs_dirent *sd, int level)
{
- printk(KERN_INFO "%*s\"%s\":\n", level, " ", configfs_get_name(sd));
+ pr_info("%*s\"%s\":\n", level, " ", configfs_get_name(sd));
-#define type_print(_type) if (sd->s_type & _type) printk(KERN_INFO "%*s %s\n", level, " ", #_type);
+#define type_print(_type) if (sd->s_type & _type) pr_info("%*s %s\n", level, " ", #_type);
type_print(CONFIGFS_ROOT);
type_print(CONFIGFS_DIR);
type_print(CONFIGFS_ITEM_ATTR);
@@ -1699,7 +1699,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
struct dentry *root = dentry->d_sb->s_root;
if (dentry->d_parent != root) {
- printk(KERN_ERR "configfs: Tried to unregister non-subsystem!\n");
+ pr_err("Tried to unregister non-subsystem!\n");
return;
}
@@ -1709,7 +1709,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
mutex_lock(&configfs_symlink_mutex);
spin_lock(&configfs_dirent_lock);
if (configfs_detach_prep(dentry, NULL)) {
- printk(KERN_ERR "configfs: Tried to unregister non-empty subsystem!\n");
+ pr_err("Tried to unregister non-empty subsystem!\n");
}
spin_unlock(&configfs_dirent_lock);
mutex_unlock(&configfs_symlink_mutex);
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index a9d35b0e06cf..5946ad98053f 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -168,9 +168,8 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
* In practice the maximum level of locking depth is
* already reached. Just inform about possible reasons.
*/
- printk(KERN_INFO "configfs: Too many levels of inodes"
- " for the locking correctness validator.\n");
- printk(KERN_INFO "Spurious warnings may appear.\n");
+ pr_info("Too many levels of inodes for the locking correctness validator.\n");
+ pr_info("Spurious warnings may appear.\n");
}
}
}
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 50cee7f9110b..e65f9ffbb999 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -19,7 +19,7 @@
* Boston, MA 021110-1307, USA.
*
* Based on kobject:
- * kobject is Copyright (c) 2002-2003 Patrick Mochel
+ * kobject is Copyright (c) 2002-2003 Patrick Mochel
*
* configfs Copyright (C) 2005 Oracle. All rights reserved.
*
@@ -35,9 +35,9 @@
#include <linux/configfs.h>
-static inline struct config_item * to_item(struct list_head * entry)
+static inline struct config_item *to_item(struct list_head *entry)
{
- return container_of(entry,struct config_item,ci_entry);
+ return container_of(entry, struct config_item, ci_entry);
}
/* Evil kernel */
@@ -47,34 +47,35 @@ static void config_item_release(struct kref *kref);
* config_item_init - initialize item.
* @item: item in question.
*/
-void config_item_init(struct config_item * item)
+void config_item_init(struct config_item *item)
{
kref_init(&item->ci_kref);
INIT_LIST_HEAD(&item->ci_entry);
}
+EXPORT_SYMBOL(config_item_init);
/**
* config_item_set_name - Set the name of an item
* @item: item.
- * @name: name.
+ * @fmt: The vsnprintf()'s format string.
*
* If strlen(name) >= CONFIGFS_ITEM_NAME_LEN, then use a
* dynamically allocated string that @item->ci_name points to.
* Otherwise, use the static @item->ci_namebuf array.
*/
-int config_item_set_name(struct config_item * item, const char * fmt, ...)
+int config_item_set_name(struct config_item *item, const char *fmt, ...)
{
int error = 0;
int limit = CONFIGFS_ITEM_NAME_LEN;
int need;
va_list args;
- char * name;
+ char *name;
/*
* First, try the static array
*/
- va_start(args,fmt);
- need = vsnprintf(item->ci_namebuf,limit,fmt,args);
+ va_start(args, fmt);
+ need = vsnprintf(item->ci_namebuf, limit, fmt, args);
va_end(args);
if (need < limit)
name = item->ci_namebuf;
@@ -83,13 +84,13 @@ int config_item_set_name(struct config_item * item, const char * fmt, ...)
* Need more space? Allocate it and try again
*/
limit = need + 1;
- name = kmalloc(limit,GFP_KERNEL);
+ name = kmalloc(limit, GFP_KERNEL);
if (!name) {
error = -ENOMEM;
goto Done;
}
- va_start(args,fmt);
- need = vsnprintf(name,limit,fmt,args);
+ va_start(args, fmt);
+ need = vsnprintf(name, limit, fmt, args);
va_end(args);
/* Still? Give up. */
@@ -109,7 +110,6 @@ int config_item_set_name(struct config_item * item, const char * fmt, ...)
Done:
return error;
}
-
EXPORT_SYMBOL(config_item_set_name);
void config_item_init_type_name(struct config_item *item,
@@ -131,20 +131,21 @@ void config_group_init_type_name(struct config_group *group, const char *name,
}
EXPORT_SYMBOL(config_group_init_type_name);
-struct config_item * config_item_get(struct config_item * item)
+struct config_item *config_item_get(struct config_item *item)
{
if (item)
kref_get(&item->ci_kref);
return item;
}
+EXPORT_SYMBOL(config_item_get);
-static void config_item_cleanup(struct config_item * item)
+static void config_item_cleanup(struct config_item *item)
{
- struct config_item_type * t = item->ci_type;
- struct config_group * s = item->ci_group;
- struct config_item * parent = item->ci_parent;
+ struct config_item_type *t = item->ci_type;
+ struct config_group *s = item->ci_group;
+ struct config_item *parent = item->ci_parent;
- pr_debug("config_item %s: cleaning up\n",config_item_name(item));
+ pr_debug("config_item %s: cleaning up\n", config_item_name(item));
if (item->ci_name != item->ci_namebuf)
kfree(item->ci_name);
item->ci_name = NULL;
@@ -167,21 +168,23 @@ static void config_item_release(struct kref *kref)
*
* Decrement the refcount, and if 0, call config_item_cleanup().
*/
-void config_item_put(struct config_item * item)
+void config_item_put(struct config_item *item)
{
if (item)
kref_put(&item->ci_kref, config_item_release);
}
+EXPORT_SYMBOL(config_item_put);
/**
* config_group_init - initialize a group for use
- * @k: group
+ * @group: config_group
*/
void config_group_init(struct config_group *group)
{
config_item_init(&group->cg_item);
INIT_LIST_HEAD(&group->cg_children);
}
+EXPORT_SYMBOL(config_group_init);
/**
* config_group_find_item - search for item in group.
@@ -195,11 +198,11 @@ void config_group_init(struct config_group *group)
struct config_item *config_group_find_item(struct config_group *group,
const char *name)
{
- struct list_head * entry;
- struct config_item * ret = NULL;
+ struct list_head *entry;
+ struct config_item *ret = NULL;
- list_for_each(entry,&group->cg_children) {
- struct config_item * item = to_item(entry);
+ list_for_each(entry, &group->cg_children) {
+ struct config_item *item = to_item(entry);
if (config_item_name(item) &&
!strcmp(config_item_name(item), name)) {
ret = config_item_get(item);
@@ -208,9 +211,4 @@ struct config_item *config_group_find_item(struct config_group *group,
}
return ret;
}
-
-EXPORT_SYMBOL(config_item_init);
-EXPORT_SYMBOL(config_group_init);
-EXPORT_SYMBOL(config_item_get);
-EXPORT_SYMBOL(config_item_put);
EXPORT_SYMBOL(config_group_find_item);
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 7f26c3cf75ae..f6c285833390 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -85,7 +85,7 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
} else {
- pr_debug("configfs: could not get root inode\n");
+ pr_debug("could not get root inode\n");
return -ENOMEM;
}
@@ -155,7 +155,7 @@ static int __init configfs_init(void)
return 0;
out4:
- printk(KERN_ERR "configfs: Unable to register filesystem!\n");
+ pr_err("Unable to register filesystem!\n");
configfs_inode_exit();
out3:
kobject_put(config_kobj);
diff --git a/fs/dcache.c b/fs/dcache.c
index be2bea834bf4..1792d6075b4f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -150,7 +150,7 @@ static long get_nr_dentry_unused(void)
return sum < 0 ? 0 : sum;
}
-int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
+int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index c71038079b47..cfe8466f7fef 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -10,6 +10,8 @@
*
* ------------------------------------------------------------------------- */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
@@ -148,10 +150,10 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode)
/*
* parse_mount_options():
- * Set @opts to mount options specified in @data. If an option is not
- * specified in @data, set it to its default value. The exception is
- * 'newinstance' option which can only be set/cleared on a mount (i.e.
- * cannot be changed during remount).
+ * Set @opts to mount options specified in @data. If an option is not
+ * specified in @data, set it to its default value. The exception is
+ * 'newinstance' option which can only be set/cleared on a mount (i.e.
+ * cannot be changed during remount).
*
* Note: @data may be NULL (in which case all options are set to default).
*/
@@ -225,7 +227,7 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
break;
#endif
default:
- printk(KERN_ERR "devpts: called with bogus options\n");
+ pr_err("called with bogus options\n");
return -EINVAL;
}
}
@@ -261,7 +263,7 @@ static int mknod_ptmx(struct super_block *sb)
dentry = d_alloc_name(root, "ptmx");
if (!dentry) {
- printk(KERN_NOTICE "Unable to alloc dentry for ptmx node\n");
+ pr_err("Unable to alloc dentry for ptmx node\n");
goto out;
}
@@ -270,7 +272,7 @@ static int mknod_ptmx(struct super_block *sb)
*/
inode = new_inode(sb);
if (!inode) {
- printk(KERN_ERR "Unable to alloc inode for ptmx node\n");
+ pr_err("Unable to alloc inode for ptmx node\n");
dput(dentry);
goto out;
}
@@ -303,7 +305,7 @@ static void update_ptmx_mode(struct pts_fs_info *fsi)
#else
static inline void update_ptmx_mode(struct pts_fs_info *fsi)
{
- return;
+ return;
}
#endif
@@ -333,9 +335,11 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root)
struct pts_mount_opts *opts = &fsi->mount_opts;
if (opts->setuid)
- seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, opts->uid));
+ seq_printf(seq, ",uid=%u",
+ from_kuid_munged(&init_user_ns, opts->uid));
if (opts->setgid)
- seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, opts->gid));
+ seq_printf(seq, ",gid=%u",
+ from_kgid_munged(&init_user_ns, opts->gid));
seq_printf(seq, ",mode=%03o", opts->mode);
#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
@@ -396,7 +400,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
if (s->s_root)
return 0;
- printk(KERN_ERR "devpts: get root dentry failed\n");
+ pr_err("get root dentry failed\n");
fail:
return -ENOMEM;
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 76feb4b60fa6..d521bddf876d 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -157,11 +157,13 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
const char *buf, size_t len)
{
unsigned int x;
+ int rc;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
-
- x = simple_strtoul(buf, NULL, 0);
+ rc = kstrtouint(buf, 0, &x);
+ if (rc)
+ return rc;
if (check_zero && !x)
return -EINVAL;
@@ -730,7 +732,10 @@ static ssize_t comm_nodeid_read(struct dlm_comm *cm, char *buf)
static ssize_t comm_nodeid_write(struct dlm_comm *cm, const char *buf,
size_t len)
{
- cm->nodeid = simple_strtol(buf, NULL, 0);
+ int rc = kstrtoint(buf, 0, &cm->nodeid);
+
+ if (rc)
+ return rc;
return len;
}
@@ -742,7 +747,10 @@ static ssize_t comm_local_read(struct dlm_comm *cm, char *buf)
static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf,
size_t len)
{
- cm->local= simple_strtol(buf, NULL, 0);
+ int rc = kstrtoint(buf, 0, &cm->local);
+
+ if (rc)
+ return rc;
if (cm->local && !local_comm)
local_comm = cm;
return len;
@@ -846,7 +854,10 @@ static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf,
size_t len)
{
uint32_t seq = 0;
- nd->nodeid = simple_strtol(buf, NULL, 0);
+ int rc = kstrtoint(buf, 0, &nd->nodeid);
+
+ if (rc)
+ return rc;
dlm_comm_seq(nd->nodeid, &seq);
nd->comm_seq = seq;
return len;
@@ -860,7 +871,10 @@ static ssize_t node_weight_read(struct dlm_node *nd, char *buf)
static ssize_t node_weight_write(struct dlm_node *nd, const char *buf,
size_t len)
{
- nd->weight = simple_strtol(buf, NULL, 0);
+ int rc = kstrtoint(buf, 0, &nd->weight);
+
+ if (rc)
+ return rc;
return len;
}
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index b969deef9ebb..8d77ba7b1756 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -68,7 +68,7 @@ static int print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb,
if (lkb->lkb_wait_type)
seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
- return seq_printf(s, "\n");
+ return seq_puts(s, "\n");
}
static int print_format1(struct dlm_rsb *res, struct seq_file *s)
@@ -92,31 +92,31 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s)
}
if (res->res_nodeid > 0)
- rv = seq_printf(s, "\" \nLocal Copy, Master is node %d\n",
+ rv = seq_printf(s, "\"\nLocal Copy, Master is node %d\n",
res->res_nodeid);
else if (res->res_nodeid == 0)
- rv = seq_printf(s, "\" \nMaster Copy\n");
+ rv = seq_puts(s, "\"\nMaster Copy\n");
else if (res->res_nodeid == -1)
- rv = seq_printf(s, "\" \nLooking up master (lkid %x)\n",
+ rv = seq_printf(s, "\"\nLooking up master (lkid %x)\n",
res->res_first_lkid);
else
- rv = seq_printf(s, "\" \nInvalid master %d\n",
+ rv = seq_printf(s, "\"\nInvalid master %d\n",
res->res_nodeid);
if (rv)
goto out;
/* Print the LVB: */
if (res->res_lvbptr) {
- seq_printf(s, "LVB: ");
+ seq_puts(s, "LVB: ");
for (i = 0; i < lvblen; i++) {
if (i == lvblen / 2)
- seq_printf(s, "\n ");
+ seq_puts(s, "\n ");
seq_printf(s, "%02x ",
(unsigned char) res->res_lvbptr[i]);
}
if (rsb_flag(res, RSB_VALNOTVALID))
- seq_printf(s, " (INVALID)");
- rv = seq_printf(s, "\n");
+ seq_puts(s, " (INVALID)");
+ rv = seq_puts(s, "\n");
if (rv)
goto out;
}
@@ -133,21 +133,21 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s)
}
/* Print the locks attached to this resource */
- seq_printf(s, "Granted Queue\n");
+ seq_puts(s, "Granted Queue\n");
list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue) {
rv = print_format1_lock(s, lkb, res);
if (rv)
goto out;
}
- seq_printf(s, "Conversion Queue\n");
+ seq_puts(s, "Conversion Queue\n");
list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue) {
rv = print_format1_lock(s, lkb, res);
if (rv)
goto out;
}
- seq_printf(s, "Waiting Queue\n");
+ seq_puts(s, "Waiting Queue\n");
list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue) {
rv = print_format1_lock(s, lkb, res);
if (rv)
@@ -157,13 +157,13 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s)
if (list_empty(&res->res_lookup))
goto out;
- seq_printf(s, "Lookup Queue\n");
+ seq_puts(s, "Lookup Queue\n");
list_for_each_entry(lkb, &res->res_lookup, lkb_rsb_lookup) {
rv = seq_printf(s, "%08x %s", lkb->lkb_id,
print_lockmode(lkb->lkb_rqmode));
if (lkb->lkb_wait_type)
seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
- rv = seq_printf(s, "\n");
+ rv = seq_puts(s, "\n");
}
out:
unlock_rsb(res);
@@ -300,7 +300,7 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s)
else
seq_printf(s, " %02x", (unsigned char)r->res_name[i]);
}
- rv = seq_printf(s, "\n");
+ rv = seq_puts(s, "\n");
if (rv)
goto out;
@@ -311,7 +311,7 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s)
for (i = 0; i < lvblen; i++)
seq_printf(s, " %02x", (unsigned char)r->res_lvbptr[i]);
- rv = seq_printf(s, "\n");
+ rv = seq_puts(s, "\n");
if (rv)
goto out;
@@ -377,7 +377,7 @@ static int print_format4(struct dlm_rsb *r, struct seq_file *s)
else
seq_printf(s, " %02x", (unsigned char)r->res_name[i]);
}
- rv = seq_printf(s, "\n");
+ rv = seq_puts(s, "\n");
out:
unlock_rsb(r);
return rv;
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 04d6398c1f1c..f3e72787e7f9 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -35,8 +35,11 @@ static struct task_struct * scand_task;
static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len)
{
ssize_t ret = len;
- int n = simple_strtol(buf, NULL, 0);
+ int n;
+ int rc = kstrtoint(buf, 0, &n);
+ if (rc)
+ return rc;
ls = dlm_find_lockspace_local(ls->ls_local_handle);
if (!ls)
return -EINVAL;
@@ -57,7 +60,10 @@ static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len)
static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len)
{
- ls->ls_uevent_result = simple_strtol(buf, NULL, 0);
+ int rc = kstrtoint(buf, 0, &ls->ls_uevent_result);
+
+ if (rc)
+ return rc;
set_bit(LSFL_UEVENT_WAIT, &ls->ls_flags);
wake_up(&ls->ls_uevent_wait);
return len;
@@ -70,7 +76,10 @@ static ssize_t dlm_id_show(struct dlm_ls *ls, char *buf)
static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len)
{
- ls->ls_global_id = simple_strtoul(buf, NULL, 0);
+ int rc = kstrtouint(buf, 0, &ls->ls_global_id);
+
+ if (rc)
+ return rc;
return len;
}
@@ -81,7 +90,11 @@ static ssize_t dlm_nodir_show(struct dlm_ls *ls, char *buf)
static ssize_t dlm_nodir_store(struct dlm_ls *ls, const char *buf, size_t len)
{
- int val = simple_strtoul(buf, NULL, 0);
+ int val;
+ int rc = kstrtoint(buf, 0, &val);
+
+ if (rc)
+ return rc;
if (val == 1)
set_bit(LSFL_NODIR, &ls->ls_flags);
return len;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 9280202e488c..1de7294aad20 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -50,7 +50,7 @@ static void drop_slab(void)
} while (nr_objects > 10);
}
-int drop_caches_sysctl_handler(ctl_table *table, int write,
+int drop_caches_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
int ret;
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index becc725a1953..0a48886e069c 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -83,7 +83,7 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr)
return 0;
}
-static struct dentry_operations efivarfs_d_ops = {
+static const struct dentry_operations efivarfs_d_ops = {
.d_compare = efivarfs_d_compare,
.d_hash = efivarfs_d_hash,
.d_delete = always_delete_dentry,
diff --git a/fs/efs/dir.c b/fs/efs/dir.c
index b72307ccdf7a..ce63b24f7c3e 100644
--- a/fs/efs/dir.c
+++ b/fs/efs/dir.c
@@ -26,7 +26,8 @@ static int efs_readdir(struct file *file, struct dir_context *ctx)
int slot;
if (inode->i_size & (EFS_DIRBSIZE-1))
- printk(KERN_WARNING "EFS: WARNING: readdir(): directory size not a multiple of EFS_DIRBSIZE\n");
+ pr_warn("%s(): directory size not a multiple of EFS_DIRBSIZE\n",
+ __func__);
/* work out where this entry can be found */
block = ctx->pos >> EFS_DIRBSIZE_BITS;
@@ -43,14 +44,15 @@ static int efs_readdir(struct file *file, struct dir_context *ctx)
bh = sb_bread(inode->i_sb, efs_bmap(inode, block));
if (!bh) {
- printk(KERN_ERR "EFS: readdir(): failed to read dir block %d\n", block);
+ pr_err("%s(): failed to read dir block %d\n",
+ __func__, block);
break;
}
dirblock = (struct efs_dir *) bh->b_data;
if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) {
- printk(KERN_ERR "EFS: readdir(): invalid directory block\n");
+ pr_err("%s(): invalid directory block\n", __func__);
brelse(bh);
break;
}
@@ -69,10 +71,9 @@ static int efs_readdir(struct file *file, struct dir_context *ctx)
inodenum = be32_to_cpu(dirslot->inode);
namelen = dirslot->namelen;
nameptr = dirslot->name;
-
-#ifdef DEBUG
- printk(KERN_DEBUG "EFS: readdir(): block %d slot %d/%d: inode %u, name \"%s\", namelen %u\n", block, slot, dirblock->slots-1, inodenum, nameptr, namelen);
-#endif
+ pr_debug("%s(): block %d slot %d/%d: inode %u, name \"%s\", namelen %u\n",
+ __func__, block, slot, dirblock->slots-1,
+ inodenum, nameptr, namelen);
if (!namelen)
continue;
/* found the next entry */
@@ -80,7 +81,8 @@ static int efs_readdir(struct file *file, struct dir_context *ctx)
/* sanity check */
if (nameptr - (char *) dirblock + namelen > EFS_DIRBSIZE) {
- printk(KERN_WARNING "EFS: directory entry %d exceeds directory block\n", slot);
+ pr_warn("directory entry %d exceeds directory block\n",
+ slot);
continue;
}
diff --git a/fs/efs/efs.h b/fs/efs/efs.h
index 5528926ac7f6..5bbf9612140c 100644
--- a/fs/efs/efs.h
+++ b/fs/efs/efs.h
@@ -7,6 +7,12 @@
#ifndef _EFS_EFS_H_
#define _EFS_EFS_H_
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/fs.h>
#include <asm/uaccess.h>
diff --git a/fs/efs/file.c b/fs/efs/file.c
index 1ccb364ffa63..a37dcee46866 100644
--- a/fs/efs/file.c
+++ b/fs/efs/file.c
@@ -22,10 +22,8 @@ int efs_get_block(struct inode *inode, sector_t iblock,
/*
* i have no idea why this happens as often as it does
*/
- printk(KERN_WARNING "EFS: bmap(): block %d >= %ld (filesize %ld)\n",
- block,
- inode->i_blocks,
- inode->i_size);
+ pr_warn("%s(): block %d >= %ld (filesize %ld)\n",
+ __func__, block, inode->i_blocks, inode->i_size);
#endif
return 0;
}
@@ -38,7 +36,7 @@ int efs_get_block(struct inode *inode, sector_t iblock,
int efs_bmap(struct inode *inode, efs_block_t block) {
if (block < 0) {
- printk(KERN_WARNING "EFS: bmap(): block < 0\n");
+ pr_warn("%s(): block < 0\n", __func__);
return 0;
}
@@ -48,10 +46,8 @@ int efs_bmap(struct inode *inode, efs_block_t block) {
/*
* i have no idea why this happens as often as it does
*/
- printk(KERN_WARNING "EFS: bmap(): block %d >= %ld (filesize %ld)\n",
- block,
- inode->i_blocks,
- inode->i_size);
+ pr_warn("%s(): block %d >= %ld (filesize %ld)\n",
+ __func__, block, inode->i_blocks, inode->i_size);
#endif
return 0;
}
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index d15ccf20f1b3..079d20306ee1 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -89,7 +89,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
bh = sb_bread(inode->i_sb, block);
if (!bh) {
- printk(KERN_WARNING "EFS: bread() failed at block %d\n", block);
+ pr_warn("%s() failed at block %d\n", __func__, block);
goto read_inode_error;
}
@@ -130,19 +130,16 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
for(i = 0; i < EFS_DIRECTEXTENTS; i++) {
extent_copy(&(efs_inode->di_u.di_extents[i]), &(in->extents[i]));
if (i < in->numextents && in->extents[i].cooked.ex_magic != 0) {
- printk(KERN_WARNING "EFS: extent %d has bad magic number in inode %lu\n", i, inode->i_ino);
+ pr_warn("extent %d has bad magic number in inode %lu\n",
+ i, inode->i_ino);
brelse(bh);
goto read_inode_error;
}
}
brelse(bh);
-
-#ifdef DEBUG
- printk(KERN_DEBUG "EFS: efs_iget(): inode %lu, extents %d, mode %o\n",
- inode->i_ino, in->numextents, inode->i_mode);
-#endif
-
+ pr_debug("efs_iget(): inode %lu, extents %d, mode %o\n",
+ inode->i_ino, in->numextents, inode->i_mode);
switch (inode->i_mode & S_IFMT) {
case S_IFDIR:
inode->i_op = &efs_dir_inode_operations;
@@ -162,7 +159,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
init_special_inode(inode, inode->i_mode, device);
break;
default:
- printk(KERN_WARNING "EFS: unsupported inode mode %o\n", inode->i_mode);
+ pr_warn("unsupported inode mode %o\n", inode->i_mode);
goto read_inode_error;
break;
}
@@ -171,7 +168,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
return inode;
read_inode_error:
- printk(KERN_WARNING "EFS: failed to read inode %lu\n", inode->i_ino);
+ pr_warn("failed to read inode %lu\n", inode->i_ino);
iget_failed(inode);
return ERR_PTR(-EIO);
}
@@ -216,7 +213,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
/* if we only have one extent then nothing can be found */
if (in->numextents == 1) {
- printk(KERN_ERR "EFS: map_block() failed to map (1 extent)\n");
+ pr_err("%s() failed to map (1 extent)\n", __func__);
return 0;
}
@@ -234,13 +231,12 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
}
}
- printk(KERN_ERR "EFS: map_block() failed to map block %u (dir)\n", block);
+ pr_err("%s() failed to map block %u (dir)\n", __func__, block);
return 0;
}
-#ifdef DEBUG
- printk(KERN_DEBUG "EFS: map_block(): indirect search for logical block %u\n", block);
-#endif
+ pr_debug("%s(): indirect search for logical block %u\n",
+ __func__, block);
direxts = in->extents[0].cooked.ex_offset;
indexts = in->numextents;
@@ -262,7 +258,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
if (dirext == direxts) {
/* should never happen */
- printk(KERN_ERR "EFS: couldn't find direct extent for indirect extent %d (block %u)\n", cur, block);
+ pr_err("couldn't find direct extent for indirect extent %d (block %u)\n",
+ cur, block);
if (bh) brelse(bh);
return 0;
}
@@ -279,12 +276,12 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
bh = sb_bread(inode->i_sb, iblock);
if (!bh) {
- printk(KERN_ERR "EFS: bread() failed at block %d\n", iblock);
+ pr_err("%s() failed at block %d\n",
+ __func__, iblock);
return 0;
}
-#ifdef DEBUG
- printk(KERN_DEBUG "EFS: map_block(): read indirect extent block %d\n", iblock);
-#endif
+ pr_debug("%s(): read indirect extent block %d\n",
+ __func__, iblock);
first = 0;
lastblock = iblock;
}
@@ -294,7 +291,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
extent_copy(&(exts[ioffset]), &ext);
if (ext.cooked.ex_magic != 0) {
- printk(KERN_ERR "EFS: extent %d has bad magic number in block %d\n", cur, iblock);
+ pr_err("extent %d has bad magic number in block %d\n",
+ cur, iblock);
if (bh) brelse(bh);
return 0;
}
@@ -306,7 +304,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) {
}
}
if (bh) brelse(bh);
- printk(KERN_ERR "EFS: map_block() failed to map block %u (indir)\n", block);
+ pr_err("%s() failed to map block %u (indir)\n", __func__, block);
return 0;
}
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index 96f66d213a19..356c044e2cd3 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -23,20 +23,22 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len)
efs_block_t block;
if (inode->i_size & (EFS_DIRBSIZE-1))
- printk(KERN_WARNING "EFS: WARNING: find_entry(): directory size not a multiple of EFS_DIRBSIZE\n");
+ pr_warn("%s(): directory size not a multiple of EFS_DIRBSIZE\n",
+ __func__);
for(block = 0; block < inode->i_blocks; block++) {
bh = sb_bread(inode->i_sb, efs_bmap(inode, block));
if (!bh) {
- printk(KERN_ERR "EFS: find_entry(): failed to read dir block %d\n", block);
+ pr_err("%s(): failed to read dir block %d\n",
+ __func__, block);
return 0;
}
dirblock = (struct efs_dir *) bh->b_data;
if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) {
- printk(KERN_ERR "EFS: find_entry(): invalid directory block\n");
+ pr_err("%s(): invalid directory block\n", __func__);
brelse(bh);
return(0);
}
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 3befcc9f5d63..7fca462ea4e3 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -134,7 +134,7 @@ static const struct export_operations efs_export_ops = {
static int __init init_efs_fs(void) {
int err;
- printk("EFS: "EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n");
+ pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n");
err = init_inodecache();
if (err)
goto out1;
@@ -179,12 +179,12 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) {
csum += be32_to_cpu(cs);
}
if (csum) {
- printk(KERN_INFO "EFS: SGI disklabel: checksum bad, label corrupted\n");
+ pr_warn("SGI disklabel: checksum bad, label corrupted\n");
return 0;
}
#ifdef DEBUG
- printk(KERN_DEBUG "EFS: bf: \"%16s\"\n", vh->vh_bootfile);
+ pr_debug("bf: \"%16s\"\n", vh->vh_bootfile);
for(i = 0; i < NVDIR; i++) {
int j;
@@ -196,9 +196,8 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) {
name[j] = (char) 0;
if (name[0]) {
- printk(KERN_DEBUG "EFS: vh: %8s block: 0x%08x size: 0x%08x\n",
- name,
- (int) be32_to_cpu(vh->vh_vd[i].vd_lbn),
+ pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n",
+ name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn),
(int) be32_to_cpu(vh->vh_vd[i].vd_nbytes));
}
}
@@ -211,12 +210,11 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) {
}
#ifdef DEBUG
if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) {
- printk(KERN_DEBUG "EFS: pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n",
- i,
- (int) be32_to_cpu(vh->vh_pt[i].pt_firstlbn),
- (int) be32_to_cpu(vh->vh_pt[i].pt_nblks),
- pt_type,
- (pt_entry->pt_name) ? pt_entry->pt_name : "unknown");
+ pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n",
+ i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn),
+ (int)be32_to_cpu(vh->vh_pt[i].pt_nblks),
+ pt_type, (pt_entry->pt_name) ?
+ pt_entry->pt_name : "unknown");
}
#endif
if (IS_EFS(pt_type)) {
@@ -226,11 +224,10 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) {
}
if (slice == -1) {
- printk(KERN_NOTICE "EFS: partition table contained no EFS partitions\n");
+ pr_notice("partition table contained no EFS partitions\n");
#ifdef DEBUG
} else {
- printk(KERN_INFO "EFS: using slice %d (type %s, offset 0x%x)\n",
- slice,
+ pr_info("using slice %d (type %s, offset 0x%x)\n", slice,
(pt_entry->pt_name) ? pt_entry->pt_name : "unknown",
sblock);
#endif
@@ -268,7 +265,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
s->s_magic = EFS_SUPER_MAGIC;
if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) {
- printk(KERN_ERR "EFS: device does not support %d byte blocks\n",
+ pr_err("device does not support %d byte blocks\n",
EFS_BLOCKSIZE);
return -EINVAL;
}
@@ -277,7 +274,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
bh = sb_bread(s, 0);
if (!bh) {
- printk(KERN_ERR "EFS: cannot read volume header\n");
+ pr_err("cannot read volume header\n");
return -EINVAL;
}
@@ -295,13 +292,14 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
bh = sb_bread(s, sb->fs_start + EFS_SUPER);
if (!bh) {
- printk(KERN_ERR "EFS: cannot read superblock\n");
+ pr_err("cannot read superblock\n");
return -EINVAL;
}
if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) {
#ifdef DEBUG
- printk(KERN_WARNING "EFS: invalid superblock at block %u\n", sb->fs_start + EFS_SUPER);
+ pr_warn("invalid superblock at block %u\n",
+ sb->fs_start + EFS_SUPER);
#endif
brelse(bh);
return -EINVAL;
@@ -310,7 +308,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
if (!(s->s_flags & MS_RDONLY)) {
#ifdef DEBUG
- printk(KERN_INFO "EFS: forcing read-only mode\n");
+ pr_info("forcing read-only mode\n");
#endif
s->s_flags |= MS_RDONLY;
}
@@ -318,13 +316,13 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
s->s_export_op = &efs_export_ops;
root = efs_iget(s, EFS_ROOTINODE);
if (IS_ERR(root)) {
- printk(KERN_ERR "EFS: get root inode failed\n");
+ pr_err("get root inode failed\n");
return PTR_ERR(root);
}
s->s_root = d_make_root(root);
if (!(s->s_root)) {
- printk(KERN_ERR "EFS: get root dentry failed\n");
+ pr_err("get root dentry failed\n");
return -ENOMEM;
}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index af903128891c..b73e0621ce9e 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -293,7 +293,7 @@ static LIST_HEAD(tfile_check_list);
static long zero;
static long long_max = LONG_MAX;
-ctl_table epoll_table[] = {
+struct ctl_table epoll_table[] = {
{
.procname = "max_user_watches",
.data = &max_user_watches,
diff --git a/fs/exofs/Kconfig.ore b/fs/exofs/Kconfig.ore
index 1ca7fb7b6ba8..2daf2329c28d 100644
--- a/fs/exofs/Kconfig.ore
+++ b/fs/exofs/Kconfig.ore
@@ -9,4 +9,6 @@ config ORE
tristate
depends on EXOFS_FS || PNFS_OBJLAYOUT
select ASYNC_XOR
+ select RAID6_PQ
+ select ASYNC_PQ
default SCSI_OSD_ULD
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index dae884694bd9..cfc0205d62c4 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -58,9 +58,12 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
layout->parity = 1;
break;
case PNFS_OSD_RAID_PQ:
+ layout->parity = 2;
+ break;
case PNFS_OSD_RAID_4:
default:
- ORE_ERR("Only RAID_0/5 for now\n");
+ ORE_ERR("Only RAID_0/5/6 for now received-enum=%d\n",
+ layout->raid_algorithm);
return -EINVAL;
}
if (0 != (layout->stripe_unit & ~PAGE_MASK)) {
@@ -112,6 +115,8 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
layout->max_io_length /= stripe_length;
layout->max_io_length *= stripe_length;
}
+ ORE_DBGMSG("max_io_length=0x%lx\n", layout->max_io_length);
+
return 0;
}
EXPORT_SYMBOL(ore_verify_layout);
@@ -545,21 +550,24 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
/* "H - (N * U)" is just "H % U" so it's bound to u32 */
u32 C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
+ u32 first_dev = C - C % group_width;
div_u64_rem(file_offset, stripe_unit, &si->unit_off);
si->obj_offset = si->unit_off + (N * stripe_unit) +
(M * group_depth * stripe_unit);
+ si->cur_comp = C - first_dev;
+ si->cur_pg = si->unit_off / PAGE_SIZE;
if (parity) {
u32 LCMdP = lcm(group_width, parity) / parity;
/* R = N % LCMdP; */
u32 RxP = (N % LCMdP) * parity;
- u32 first_dev = C - C % group_width;
si->par_dev = (group_width + group_width - parity - RxP) %
group_width + first_dev;
- si->dev = (group_width + C - RxP) % group_width + first_dev;
+ si->dev = (group_width + group_width + C - RxP) %
+ group_width + first_dev;
si->bytes_in_stripe = U;
si->first_stripe_start = M * S + G * T + N * U;
} else {
@@ -649,6 +657,43 @@ out: /* we fail the complete unit on an error eg don't advance
return ret;
}
+static int _add_parity_units(struct ore_io_state *ios,
+ struct ore_striping_info *si,
+ unsigned dev, unsigned first_dev,
+ unsigned mirrors_p1, unsigned devs_in_group,
+ unsigned cur_len)
+{
+ unsigned do_parity;
+ int ret = 0;
+
+ for (do_parity = ios->layout->parity; do_parity; --do_parity) {
+ struct ore_per_dev_state *per_dev;
+
+ per_dev = &ios->per_dev[dev - first_dev];
+ if (!per_dev->length && !per_dev->offset) {
+ /* Only/always the parity unit of the first
+ * stripe will be empty. So this is a chance to
+ * initialize the per_dev info.
+ */
+ per_dev->dev = dev;
+ per_dev->offset = si->obj_offset - si->unit_off;
+ }
+
+ ret = _ore_add_parity_unit(ios, si, per_dev, cur_len,
+ do_parity == 1);
+ if (unlikely(ret))
+ break;
+
+ if (do_parity != 1) {
+ dev = ((dev + mirrors_p1) % devs_in_group) + first_dev;
+ si->cur_comp = (si->cur_comp + 1) %
+ ios->layout->group_width;
+ }
+ }
+
+ return ret;
+}
+
static int _prepare_for_striping(struct ore_io_state *ios)
{
struct ore_striping_info *si = &ios->si;
@@ -658,7 +703,6 @@ static int _prepare_for_striping(struct ore_io_state *ios)
unsigned devs_in_group = group_width * mirrors_p1;
unsigned dev = si->dev;
unsigned first_dev = dev - (dev % devs_in_group);
- unsigned dev_order;
unsigned cur_pg = ios->pages_consumed;
u64 length = ios->length;
int ret = 0;
@@ -670,16 +714,13 @@ static int _prepare_for_striping(struct ore_io_state *ios)
BUG_ON(length > si->length);
- dev_order = _dev_order(devs_in_group, mirrors_p1, si->par_dev, dev);
- si->cur_comp = dev_order;
- si->cur_pg = si->unit_off / PAGE_SIZE;
-
while (length) {
- unsigned comp = dev - first_dev;
- struct ore_per_dev_state *per_dev = &ios->per_dev[comp];
+ struct ore_per_dev_state *per_dev =
+ &ios->per_dev[dev - first_dev];
unsigned cur_len, page_off = 0;
- if (!per_dev->length) {
+ if (!per_dev->length && !per_dev->offset) {
+ /* First time initialize the per_dev info. */
per_dev->dev = dev;
if (dev == si->dev) {
WARN_ON(dev == si->par_dev);
@@ -688,13 +729,7 @@ static int _prepare_for_striping(struct ore_io_state *ios)
page_off = si->unit_off & ~PAGE_MASK;
BUG_ON(page_off && (page_off != ios->pgbase));
} else {
- if (si->cur_comp > dev_order)
- per_dev->offset =
- si->obj_offset - si->unit_off;
- else /* si->cur_comp < dev_order */
- per_dev->offset =
- si->obj_offset + stripe_unit -
- si->unit_off;
+ per_dev->offset = si->obj_offset - si->unit_off;
cur_len = stripe_unit;
}
} else {
@@ -708,11 +743,9 @@ static int _prepare_for_striping(struct ore_io_state *ios)
if (unlikely(ret))
goto out;
- dev += mirrors_p1;
- dev = (dev % devs_in_group) + first_dev;
-
length -= cur_len;
+ dev = ((dev + mirrors_p1) % devs_in_group) + first_dev;
si->cur_comp = (si->cur_comp + 1) % group_width;
if (unlikely((dev == si->par_dev) || (!length && ios->sp2d))) {
if (!length && ios->sp2d) {
@@ -720,23 +753,16 @@ static int _prepare_for_striping(struct ore_io_state *ios)
* stripe. then operate on parity dev.
*/
dev = si->par_dev;
- }
- if (ios->sp2d)
- /* In writes cur_len just means if it's the
- * last one. See _ore_add_parity_unit.
- */
- cur_len = length;
- per_dev = &ios->per_dev[dev - first_dev];
- if (!per_dev->length) {
- /* Only/always the parity unit of the first
- * stripe will be empty. So this is a chance to
- * initialize the per_dev info.
- */
- per_dev->dev = dev;
- per_dev->offset = si->obj_offset - si->unit_off;
+ /* If last stripe operate on parity comp */
+ si->cur_comp = group_width - ios->layout->parity;
}
- ret = _ore_add_parity_unit(ios, si, per_dev, cur_len);
+ /* In writes cur_len just means if it's the
+ * last one. See _ore_add_parity_unit.
+ */
+ ret = _add_parity_units(ios, si, dev, first_dev,
+ mirrors_p1, devs_in_group,
+ ios->sp2d ? length : cur_len);
if (unlikely(ret))
goto out;
@@ -747,6 +773,8 @@ static int _prepare_for_striping(struct ore_io_state *ios)
/* Next stripe, start fresh */
si->cur_comp = 0;
si->cur_pg = 0;
+ si->obj_offset += cur_len;
+ si->unit_off = 0;
}
}
out:
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index 4e2c032ab8a1..7f20f25c232c 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -218,22 +218,28 @@ static unsigned _sp2d_max_pg(struct __stripe_pages_2d *sp2d)
static void _gen_xor_unit(struct __stripe_pages_2d *sp2d)
{
unsigned p;
+ unsigned tx_flags = ASYNC_TX_ACK;
+
+ if (sp2d->parity == 1)
+ tx_flags |= ASYNC_TX_XOR_ZERO_DST;
+
for (p = 0; p < sp2d->pages_in_unit; p++) {
struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
if (!_1ps->write_count)
continue;
- init_async_submit(&_1ps->submit,
- ASYNC_TX_XOR_ZERO_DST | ASYNC_TX_ACK,
- NULL,
- NULL, NULL,
- (addr_conv_t *)_1ps->scribble);
-
- /* TODO: raid6 */
- _1ps->tx = async_xor(_1ps->pages[sp2d->data_devs], _1ps->pages,
- 0, sp2d->data_devs, PAGE_SIZE,
- &_1ps->submit);
+ init_async_submit(&_1ps->submit, tx_flags,
+ NULL, NULL, NULL, (addr_conv_t *)_1ps->scribble);
+
+ if (sp2d->parity == 1)
+ _1ps->tx = async_xor(_1ps->pages[sp2d->data_devs],
+ _1ps->pages, 0, sp2d->data_devs,
+ PAGE_SIZE, &_1ps->submit);
+ else /* parity == 2 */
+ _1ps->tx = async_gen_syndrome(_1ps->pages, 0,
+ sp2d->data_devs + sp2d->parity,
+ PAGE_SIZE, &_1ps->submit);
}
for (p = 0; p < sp2d->pages_in_unit; p++) {
@@ -404,9 +410,8 @@ static int _add_to_r4w_last_page(struct ore_io_state *ios, u64 *offset)
ore_calc_stripe_info(ios->layout, *offset, 0, &si);
- p = si.unit_off / PAGE_SIZE;
- c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1,
- ios->layout->mirrors_p1, si.par_dev, si.dev);
+ p = si.cur_pg;
+ c = si.cur_comp;
page = ios->sp2d->_1p_stripes[p].pages[c];
pg_len = PAGE_SIZE - (si.unit_off % PAGE_SIZE);
@@ -534,9 +539,8 @@ static int _read_4_write_last_stripe(struct ore_io_state *ios)
goto read_it;
ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
- p = read_si.unit_off / PAGE_SIZE;
- c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1,
- ios->layout->mirrors_p1, read_si.par_dev, read_si.dev);
+ p = read_si.cur_pg;
+ c = read_si.cur_comp;
if (min_p == sp2d->pages_in_unit) {
/* Didn't do it yet */
@@ -620,7 +624,7 @@ static int _read_4_write_execute(struct ore_io_state *ios)
int _ore_add_parity_unit(struct ore_io_state *ios,
struct ore_striping_info *si,
struct ore_per_dev_state *per_dev,
- unsigned cur_len)
+ unsigned cur_len, bool do_xor)
{
if (ios->reading) {
if (per_dev->cur_sg >= ios->sgs_per_dev) {
@@ -640,17 +644,16 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
si->cur_pg = _sp2d_min_pg(sp2d);
num_pages = _sp2d_max_pg(sp2d) + 1 - si->cur_pg;
- if (!cur_len) /* If last stripe operate on parity comp */
- si->cur_comp = sp2d->data_devs;
-
if (!per_dev->length) {
per_dev->offset += si->cur_pg * PAGE_SIZE;
/* If first stripe, Read in all read4write pages
* (if needed) before we calculate the first parity.
*/
- _read_4_write_first_stripe(ios);
+ if (do_xor)
+ _read_4_write_first_stripe(ios);
}
- if (!cur_len) /* If last stripe r4w pages of last stripe */
+ if (!cur_len && do_xor)
+ /* If last stripe r4w pages of last stripe */
_read_4_write_last_stripe(ios);
_read_4_write_execute(ios);
@@ -662,7 +665,7 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
++(ios->cur_par_page);
}
- BUG_ON(si->cur_comp != sp2d->data_devs);
+ BUG_ON(si->cur_comp < sp2d->data_devs);
BUG_ON(si->cur_pg + num_pages > sp2d->pages_in_unit);
ret = _ore_add_stripe_unit(ios, &array_start, 0, pages,
@@ -670,9 +673,10 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
if (unlikely(ret))
return ret;
- /* TODO: raid6 if (last_parity_dev) */
- _gen_xor_unit(sp2d);
- _sp2d_reset(sp2d, ios->r4w, ios->private);
+ if (do_xor) {
+ _gen_xor_unit(sp2d);
+ _sp2d_reset(sp2d, ios->r4w, ios->private);
+ }
}
return 0;
}
diff --git a/fs/exofs/ore_raid.h b/fs/exofs/ore_raid.h
index 2ffd2c3c6e46..cf6375d82129 100644
--- a/fs/exofs/ore_raid.h
+++ b/fs/exofs/ore_raid.h
@@ -31,24 +31,6 @@
#define ORE_DBGMSG2(M...) do {} while (0)
/* #define ORE_DBGMSG2 ORE_DBGMSG */
-/* Calculate the component order in a stripe. eg the logical data unit
- * address within the stripe of @dev given the @par_dev of this stripe.
- */
-static inline unsigned _dev_order(unsigned devs_in_group, unsigned mirrors_p1,
- unsigned par_dev, unsigned dev)
-{
- unsigned first_dev = dev - dev % devs_in_group;
-
- dev -= first_dev;
- par_dev -= first_dev;
-
- if (devs_in_group == par_dev) /* The raid 0 case */
- return dev / mirrors_p1;
- /* raid4/5/6 case */
- return ((devs_in_group + dev - par_dev - mirrors_p1) % devs_in_group) /
- mirrors_p1;
-}
-
/* ios_raid.c stuff needed by ios.c */
int _ore_post_alloc_raid_stuff(struct ore_io_state *ios);
void _ore_free_raid_stuff(struct ore_io_state *ios);
@@ -56,7 +38,8 @@ void _ore_free_raid_stuff(struct ore_io_state *ios);
void _ore_add_sg_seg(struct ore_per_dev_state *per_dev, unsigned cur_len,
bool not_last);
int _ore_add_parity_unit(struct ore_io_state *ios, struct ore_striping_info *si,
- struct ore_per_dev_state *per_dev, unsigned cur_len);
+ struct ore_per_dev_state *per_dev, unsigned cur_len,
+ bool do_xor);
void _ore_add_stripe_page(struct __stripe_pages_2d *sp2d,
struct ore_striping_info *si, struct page *page);
static inline void _add_stripe_page(struct __stripe_pages_2d *sp2d,
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 48a359dd286e..b01fbfb51f43 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -259,7 +259,7 @@ static int filldir_one(void * __buf, const char * name, int len,
/**
* get_name - default export_operations->get_name function
- * @dentry: the directory in which to find a name
+ * @path: the directory in which to find a name
* @name: a pointer to a %NAME_MAX+1 char buffer to store the name
* @child: the dentry for the child directory.
*
@@ -337,7 +337,7 @@ out:
/**
* export_encode_fh - default export_operations->encode_fh function
* @inode: the object to encode
- * @fh: where to store the file handle fragment
+ * @fid: where to store the file handle fragment
* @max_len: maximum length to store there
* @parent: parent directory inode, if wanted
*
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 5c56785007e0..0762d143e252 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -83,9 +83,9 @@ static inline int ext4_block_in_group(struct super_block *sb,
/* Return the number of clusters used for file system metadata; this
* represents the overhead needed by the file system.
*/
-unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
unsigned num_clusters;
int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
@@ -176,9 +176,10 @@ static unsigned int num_clusters_in_group(struct super_block *sb,
}
/* Initializes an uninitialized block bitmap */
-void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static void ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
unsigned int bit, bit_max;
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -307,6 +308,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
ext4_group_t block_group,
struct buffer_head *bh)
{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
ext4_fsblk_t blk;
@@ -326,14 +328,14 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
/* check whether block bitmap block number is set */
blk = ext4_block_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(offset, bh->b_data))
+ if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode bitmap block number is set */
blk = ext4_inode_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(offset, bh->b_data))
+ if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
@@ -341,18 +343,19 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
blk = ext4_inode_table(sb, desc);
offset = blk - group_first_block;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
- offset + EXT4_SB(sb)->s_itb_per_group,
- offset);
- if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group)
+ EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group),
+ EXT4_B2C(sbi, offset));
+ if (next_zero_bit <
+ EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group))
/* bad bitmap for inode tables */
return blk;
return 0;
}
-void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- ext4_group_t block_group,
- struct buffer_head *bh)
+static void ext4_validate_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *desc,
+ ext4_group_t block_group,
+ struct buffer_head *bh)
{
ext4_fsblk_t blk;
struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
@@ -708,16 +711,6 @@ static inline int test_root(ext4_group_t a, int b)
}
}
-static int ext4_group_sparse(ext4_group_t group)
-{
- if (group <= 1)
- return 1;
- if (!(group & 1))
- return 0;
- return (test_root(group, 7) || test_root(group, 5) ||
- test_root(group, 3));
-}
-
/**
* ext4_bg_has_super - number of blocks used by the superblock in group
* @sb: superblock for filesystem
@@ -728,11 +721,26 @@ static int ext4_group_sparse(ext4_group_t group)
*/
int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
{
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
- !ext4_group_sparse(group))
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ if (group == 0)
+ return 1;
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) {
+ if (group == le32_to_cpu(es->s_backup_bgs[0]) ||
+ group == le32_to_cpu(es->s_backup_bgs[1]))
+ return 1;
return 0;
- return 1;
+ }
+ if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER))
+ return 1;
+ if (!(group & 1))
+ return 0;
+ if (test_root(group, 3) || (test_root(group, 5)) ||
+ test_root(group, 7))
+ return 1;
+
+ return 0;
}
static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index d638c57e996e..ef1bed66c14f 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -105,7 +105,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
static int ext4_readdir(struct file *file, struct dir_context *ctx)
{
unsigned int offset;
- int i, stored;
+ int i;
struct ext4_dir_entry_2 *de;
int err;
struct inode *inode = file_inode(file);
@@ -133,7 +133,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
return ret;
}
- stored = 0;
offset = ctx->pos & (sb->s_blocksize - 1);
while (ctx->pos < inode->i_size) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 66946aa62127..1479e2ae00d2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -158,7 +158,6 @@ struct ext4_allocation_request {
#define EXT4_MAP_MAPPED (1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
-#define EXT4_MAP_UNINIT (1 << BH_Uninit)
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
* ext4_map_blocks wants to know whether or not the underlying cluster has
* already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
@@ -169,7 +168,7 @@ struct ext4_allocation_request {
#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
- EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
+ EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -184,7 +183,7 @@ struct ext4_map_blocks {
#define EXT4_IO_END_UNWRITTEN 0x0001
/*
- * For converting uninitialized extents on a work queue. 'handle' is used for
+ * For converting unwritten extents on a work queue. 'handle' is used for
* buffered writeback.
*/
typedef struct ext4_io_end {
@@ -537,26 +536,26 @@ enum {
/*
* Flags used by ext4_map_blocks()
*/
- /* Allocate any needed blocks and/or convert an unitialized
+ /* Allocate any needed blocks and/or convert an unwritten
extent to be an initialized ext4 */
#define EXT4_GET_BLOCKS_CREATE 0x0001
- /* Request the creation of an unitialized extent */
-#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002
-#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
+ /* Request the creation of an unwritten extent */
+#define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
/* Caller is from the delayed allocation writeout path
* finally doing the actual allocation of delayed blocks */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* caller is from the direct IO path, request to creation of an
- unitialized extents if not allocated, split the uninitialized
+ unwritten extents if not allocated, split the unwritten
extent if blocks has been preallocated already*/
#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Eventual metadata allocation (due to growing extent tree)
* should not fail, so try to use reserved blocks for that.*/
#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020
@@ -876,6 +875,8 @@ struct ext4_inode_info {
struct inode vfs_inode;
struct jbd2_inode *jinode;
+ spinlock_t i_raw_lock; /* protects updates to the raw inode */
+
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
@@ -1159,7 +1160,8 @@ struct ext4_super_block {
__le32 s_usr_quota_inum; /* inode for tracking user quota */
__le32 s_grp_quota_inum; /* inode for tracking group quota */
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
- __le32 s_reserved[108]; /* Padding to the end of the block */
+ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */
+ __le32 s_reserved[106]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
@@ -1505,6 +1507,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
+#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
@@ -1953,10 +1956,6 @@ extern void ext4_get_group_no_and_offset(struct super_block *sb,
extern ext4_group_t ext4_get_group_number(struct super_block *sb,
ext4_fsblk_t block);
-extern void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- ext4_group_t block_group,
- struct buffer_head *bh);
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
@@ -1985,16 +1984,9 @@ extern int ext4_wait_block_bitmap(struct super_block *sb,
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,
- struct ext4_group_desc *desc);
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
-extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
@@ -2137,8 +2129,6 @@ extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
-extern int ext4_block_truncate_page(handle_t *handle,
- struct address_space *mapping, loff_t from);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -2198,8 +2188,6 @@ extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
/* super.c */
extern int ext4_calculate_overhead(struct super_block *sb);
-extern int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es);
extern void ext4_superblock_csum_set(struct super_block *sb);
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
@@ -2571,19 +2559,11 @@ extern const struct file_operations ext4_dir_operations;
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
-extern void ext4_unwritten_wait(struct inode *inode);
/* inline.c */
extern int ext4_has_inline_data(struct inode *inode);
-extern int ext4_get_inline_size(struct inode *inode);
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern void ext4_write_inline_data(struct inode *inode,
- struct ext4_iloc *iloc,
- void *buffer, loff_t pos,
- unsigned int len);
-extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
@@ -2771,23 +2751,20 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc);
+ struct writeback_control *wbc,
+ bool keep_towrite);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
-extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
-extern int ext4_mmp_csum_verify(struct super_block *sb,
- struct mmp_struct *mmp);
/*
* Note that these flags will never ever appear in a buffer_head's state flag.
* See EXT4_MAP_... to see where this is used.
*/
enum ext4_state_bits {
- BH_Uninit /* blocks are allocated but uninitialized on disk */
- = BH_JBDPrivateStart,
- BH_AllocFromCluster, /* allocated blocks were part of already
+ BH_AllocFromCluster /* allocated blocks were part of already
* allocated cluster. */
+ = BH_JBDPrivateStart
};
/*
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 5074fe23f19e..a867f5ca9991 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -137,21 +137,21 @@ struct ext4_ext_path {
* EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
* initialized extent. This is 2^15 and not (2^16 - 1), since we use the
* MSB of ee_len field in the extent datastructure to signify if this
- * particular extent is an initialized extent or an uninitialized (i.e.
+ * particular extent is an initialized extent or an unwritten (i.e.
* preallocated).
- * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
- * uninitialized extent.
+ * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
+ * unwritten extent.
* If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
- * uninitialized one. In other words, if MSB of ee_len is set, it is an
- * uninitialized extent with only one special scenario when ee_len = 0x8000.
- * In this case we can not have an uninitialized extent of zero length and
+ * unwritten one. In other words, if MSB of ee_len is set, it is an
+ * unwritten extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an unwritten extent of zero length and
* thus we make it as a special case of initialized extent with 0x8000 length.
* This way we get better extent-to-group alignment for initialized extents.
* Hence, the maximum number of blocks we can have in an *initialized*
- * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
*/
#define EXT_INIT_MAX_LEN (1UL << 15)
-#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1)
+#define EXT_UNWRITTEN_MAX_LEN (EXT_INIT_MAX_LEN - 1)
#define EXT_FIRST_EXTENT(__hdr__) \
@@ -187,14 +187,14 @@ static inline unsigned short ext_depth(struct inode *inode)
return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
}
-static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
{
- /* We can not have an uninitialized extent of zero length! */
+ /* We can not have an unwritten extent of zero length! */
BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
}
-static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
{
/* Extent with ee_len of 0x8000 is treated as an initialized extent */
return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index c3fb607413ed..0074e0d23d6e 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -122,9 +122,10 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
return handle;
}
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
- const char *err_fn, struct buffer_head *bh,
- handle_t *handle, int err)
+static void ext4_journal_abort_handle(const char *caller, unsigned int line,
+ const char *err_fn,
+ struct buffer_head *bh,
+ handle_t *handle, int err)
{
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 81cfefa9dc0c..17c00ff202f2 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -231,10 +231,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
/*
* Wrapper functions with which ext4 calls into JBD.
*/
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
- const char *err_fn,
- struct buffer_head *bh, handle_t *handle, int err);
-
int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle_t *handle, struct buffer_head *bh);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 01b0c208f625..4da228a0e6d0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -50,8 +50,8 @@
*/
#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 */
+#define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */
+#define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */
#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */
#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
@@ -143,6 +143,7 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
{
if (path->p_bh) {
/* path points to block */
+ BUFFER_TRACE(path->p_bh, "get_write_access");
return ext4_journal_get_write_access(handle, path->p_bh);
}
/* path points to leaf/index in inode body */
@@ -524,7 +525,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
lblk - prev, ~0,
EXTENT_STATUS_HOLE);
- if (ext4_ext_is_uninitialized(ex))
+ if (ext4_ext_is_unwritten(ex))
status = EXTENT_STATUS_UNWRITTEN;
ext4_es_cache_extent(inode, lblk, len,
ext4_ext_pblock(ex), status);
@@ -620,7 +621,7 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
} else if (path->p_ext) {
ext_debug(" %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
- ext4_ext_is_uninitialized(path->p_ext),
+ ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext4_ext_pblock(path->p_ext));
} else
@@ -646,7 +647,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
ext_debug("\n");
@@ -677,7 +678,7 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(ex->ee_block),
ext4_ext_pblock(ex),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
newblock);
ex++;
@@ -802,7 +803,7 @@ ext4_ext_binsearch(struct inode *inode,
ext_debug(" -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_pblock(path->p_ext),
- ext4_ext_is_uninitialized(path->p_ext),
+ ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
@@ -1686,11 +1687,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
/*
* Make sure that both extents are initialized. We don't merge
- * uninitialized extents so that we can be sure that end_io code has
+ * unwritten extents so that we can be sure that end_io code has
* the extent that was written properly split out and conversion to
* initialized is trivial.
*/
- if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
+ if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
return 0;
ext1_ee_len = ext4_ext_get_actual_len(ex1);
@@ -1707,10 +1708,10 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
*/
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
- if (ext4_ext_is_uninitialized(ex1) &&
+ if (ext4_ext_is_unwritten(ex1) &&
(ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
atomic_read(&EXT4_I(inode)->i_unwritten) ||
- (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
+ (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
@@ -1735,7 +1736,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
{
struct ext4_extent_header *eh;
unsigned int depth, len;
- int merge_done = 0, uninit;
+ int merge_done = 0, unwritten;
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
@@ -1745,11 +1746,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
break;
/* merge with next extent! */
- uninit = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(ex + 1));
- if (uninit)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
if (ex + 1 < EXT_LAST_EXTENT(eh)) {
len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1903,7 +1904,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
struct ext4_ext_path *npath = NULL;
int depth, len, err;
ext4_lblk_t next;
- int mb_flags = 0, uninit;
+ int mb_flags = 0, unwritten;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1943,21 +1944,21 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
if (ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %u:[%d]%d"
"(from %llu)\n",
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
- uninit = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninit)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@@ -1969,10 +1970,10 @@ prepend:
ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
"(from %llu)\n",
le32_to_cpu(newext->ee_block),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
@@ -1980,13 +1981,13 @@ prepend:
if (err)
return err;
- uninit = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_block = newext->ee_block;
ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninit)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@@ -2046,7 +2047,7 @@ has_space:
ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext));
nearex = EXT_FIRST_EXTENT(eh);
} else {
@@ -2057,7 +2058,7 @@ has_space:
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
nearex++;
@@ -2068,7 +2069,7 @@ has_space:
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
}
@@ -2078,7 +2079,7 @@ has_space:
"move %d extents from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
len, nearex, nearex + 1);
memmove(nearex + 1, nearex,
@@ -2200,7 +2201,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
es.es_lblk = le32_to_cpu(ex->ee_block);
es.es_len = ext4_ext_get_actual_len(ex);
es.es_pblk = ext4_ext_pblock(ex);
- if (ext4_ext_is_uninitialized(ex))
+ if (ext4_ext_is_unwritten(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN;
}
@@ -2576,7 +2577,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
- unsigned uninitialized = 0;
+ unsigned unwritten = 0;
struct ext4_extent *ex;
ext4_fsblk_t pblk;
@@ -2623,13 +2624,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
+ if (ext4_ext_is_unwritten(ex))
+ unwritten = 1;
else
- uninitialized = 0;
+ unwritten = 0;
ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
- uninitialized, ex_ee_len);
+ unwritten, ex_ee_len);
path[depth].p_ext = ex;
a = ex_ee_block > start ? ex_ee_block : start;
@@ -2701,11 +2702,11 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex->ee_len = cpu_to_le16(num);
/*
- * Do not mark uninitialized if all the blocks in the
+ * Do not mark unwritten if all the blocks in the
* extent have been removed.
*/
- if (uninitialized && num)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten && num)
+ ext4_ext_mark_unwritten(ex);
/*
* If the extent was completely released,
* we need to remove it from the leaf
@@ -2854,9 +2855,9 @@ again:
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;
+ if (ext4_ext_is_unwritten(ex))
+ split_flag = EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2;
/*
* Split the extent in two so that 'end' is the last
@@ -3113,7 +3114,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
* @path: the path to the extent
* @split: the logical block where the extent is splitted.
* @split_flags: indicates if the extent could be zeroout if split fails, and
- * the states(init or uninit) of new extents.
+ * the states(init or unwritten) of new extents.
* @flags: flags used to insert new extent to extent tree.
*
*
@@ -3155,10 +3156,10 @@ static int ext4_split_extent_at(handle_t *handle,
newblock = split - ee_block + ext4_ext_pblock(ex);
BUG_ON(split < ee_block || split >= (ee_block + ee_len));
- BUG_ON(!ext4_ext_is_uninitialized(ex) &&
+ BUG_ON(!ext4_ext_is_unwritten(ex) &&
split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2));
+ EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -3170,8 +3171,8 @@ static int ext4_split_extent_at(handle_t *handle,
* then we just change the state of the extent, and splitting
* is not needed.
*/
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- ext4_ext_mark_uninitialized(ex);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+ ext4_ext_mark_unwritten(ex);
else
ext4_ext_mark_initialized(ex);
@@ -3185,8 +3186,8 @@ static int ext4_split_extent_at(handle_t *handle,
/* case a */
memcpy(&orig_ex, ex, sizeof(orig_ex));
ex->ee_len = cpu_to_le16(split - ee_block);
- if (split_flag & EXT4_EXT_MARK_UNINIT1)
- ext4_ext_mark_uninitialized(ex);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT1)
+ ext4_ext_mark_unwritten(ex);
/*
* path may lead to new leaf, not to original leaf any more
@@ -3200,8 +3201,8 @@ static int ext4_split_extent_at(handle_t *handle,
ex2->ee_block = cpu_to_le32(split);
ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block));
ext4_ext_store_pblock(ex2, newblock);
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- ext4_ext_mark_uninitialized(ex2);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+ ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
@@ -3278,7 +3279,7 @@ static int ext4_split_extent(handle_t *handle,
struct ext4_extent *ex;
unsigned int ee_len, depth;
int err = 0;
- int uninitialized;
+ int unwritten;
int split_flag1, flags1;
int allocated = map->m_len;
@@ -3286,14 +3287,14 @@ static int ext4_split_extent(handle_t *handle,
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- uninitialized = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
- if (uninitialized)
- split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2;
+ if (unwritten)
+ split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2;
if (split_flag & EXT4_EXT_DATA_VALID2)
split_flag1 |= EXT4_EXT_DATA_VALID1;
err = ext4_split_extent_at(handle, inode, path,
@@ -3318,15 +3319,15 @@ static int ext4_split_extent(handle_t *handle,
(unsigned long) map->m_lblk);
return -EIO;
}
- uninitialized = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
- if (uninitialized) {
- split_flag1 |= EXT4_EXT_MARK_UNINIT1;
+ if (unwritten) {
+ split_flag1 |= EXT4_EXT_MARK_UNWRIT1;
split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_MARK_UNINIT2);
+ EXT4_EXT_MARK_UNWRIT2);
}
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk, split_flag1, flags);
@@ -3341,16 +3342,16 @@ out:
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
- * to an uninitialized extent. It may result in splitting the uninitialized
+ * to an unwritten extent. It may result in splitting the unwritten
* extent into multiple extents (up to three - one initialized and two
- * uninitialized).
+ * unwritten).
* There are three possibilities:
* a> There is no split required: Entire extent should be initialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
* Pre-conditions:
- * - The extent pointed to by 'path' is uninitialized.
+ * - The extent pointed to by 'path' is unwritten.
* - The extent pointed to by 'path' contains a superset
* of the logical span [map->m_lblk, map->m_lblk + map->m_len).
*
@@ -3396,12 +3397,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
/* Pre-conditions */
- BUG_ON(!ext4_ext_is_uninitialized(ex));
+ BUG_ON(!ext4_ext_is_unwritten(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
/*
* Attempt to transfer newly initialized blocks from the currently
- * uninitialized extent to its neighbor. This is much cheaper
+ * unwritten extent to its neighbor. This is much cheaper
* than an insertion followed by a merge as those involve costly
* memmove() calls. Transferring to the left is the common case in
* steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
@@ -3437,7 +3438,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
+ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((prev_lblk + prev_len) == ee_block) && /*C2*/
((prev_pblk + prev_len) == ee_pblk) && /*C3*/
(prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@@ -3452,7 +3453,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex->ee_block = cpu_to_le32(ee_block + map_len);
ext4_ext_store_pblock(ex, ee_pblk + map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
- ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+ ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
@@ -3483,7 +3484,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
+ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((map->m_lblk + map_len) == next_lblk) && /*C2*/
((ee_pblk + ee_len) == next_pblk) && /*C3*/
(next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@@ -3498,7 +3499,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
abut_ex->ee_block = cpu_to_le32(next_lblk - map_len);
ext4_ext_store_pblock(abut_ex, next_pblk - map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
- ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+ ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(next_len + map_len);
@@ -3603,26 +3604,26 @@ out:
/*
* This function is called by ext4_ext_map_blocks() from
* ext4_get_blocks_dio_write() when DIO to write
- * to an uninitialized extent.
+ * to an unwritten extent.
*
- * Writing to an uninitialized extent may result in splitting the uninitialized
- * extent into multiple initialized/uninitialized extents (up to three)
+ * Writing to an unwritten extent may result in splitting the unwritten
+ * extent into multiple initialized/unwritten extents (up to three)
* There are three possibilities:
- * a> There is no split required: Entire extent should be uninitialized
+ * a> There is no split required: Entire extent should be unwritten
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
* This works the same way in the case of initialized -> unwritten conversion.
*
* One of more index blocks maybe needed if the extent tree grow after
- * the uninitialized extent split. To prevent ENOSPC occur at the IO
- * complete, we need to split the uninitialized extent before DIO submit
- * the IO. The uninitialized extent called at this time will be split
- * into three uninitialized extent(at most). After IO complete, the part
+ * the unwritten extent split. To prevent ENOSPC occur at the IO
+ * complete, we need to split the unwritten extent before DIO submit
+ * the IO. The unwritten extent called at this time will be split
+ * into three unwritten extent(at most). After IO complete, the part
* being filled will be convert to initialized by the end_io callback function
* via ext4_convert_unwritten_extents().
*
- * Returns the size of uninitialized extent to be written on success.
+ * Returns the size of unwritten extent to be written on success.
*/
static int ext4_split_convert_extents(handle_t *handle,
struct inode *inode,
@@ -3660,7 +3661,7 @@ static int ext4_split_convert_extents(handle_t *handle,
} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
split_flag |= ee_block + ee_len <= eof_block ?
EXT4_EXT_MAY_ZEROOUT : 0;
- split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+ split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
}
flags |= EXT4_GET_BLOCKS_PRE_IO;
return ext4_split_extent(handle, inode, path, map, split_flag, flags);
@@ -3710,8 +3711,8 @@ static int ext4_convert_initialized_extents(handle_t *handle,
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
- /* first mark the extent as uninitialized */
- ext4_ext_mark_uninitialized(ex);
+ /* first mark the extent as unwritten */
+ ext4_ext_mark_unwritten(ex);
/* note: ext4_ext_correct_indexes() isn't needed here because
* borders are not changed
@@ -3971,10 +3972,10 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
/*
* Make sure that the extent is no bigger than we support with
- * uninitialized extent
+ * unwritten extent
*/
- if (map->m_len > EXT_UNINIT_MAX_LEN)
- map->m_len = EXT_UNINIT_MAX_LEN / 2;
+ if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
+ map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
ret = ext4_convert_initialized_extents(handle, inode, map,
path);
@@ -3993,7 +3994,7 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
}
static int
-ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
+ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path *path, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
@@ -4002,23 +4003,23 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
int err = 0;
ext4_io_end_t *io = ext4_inode_aio(inode);
- ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
+ ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
"block %llu, max_blocks %u, flags %x, allocated %u\n",
inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
flags, allocated);
ext4_ext_show_leaf(inode, path);
/*
- * When writing into uninitialized space, we should not fail to
+ * When writing into unwritten space, we should not fail to
* allocate metadata blocks for the new extent block if needed.
*/
flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
- trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
+ trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
allocated, newblock);
/* get_block() before submit the IO, split the extent */
- if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
+ if (flags & EXT4_GET_BLOCKS_PRE_IO) {
ret = ext4_split_convert_extents(handle, inode, map,
path, flags | EXT4_GET_BLOCKS_CONVERT);
if (ret <= 0)
@@ -4033,12 +4034,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
map->m_flags |= EXT4_MAP_UNWRITTEN;
- if (ext4_should_dioread_nolock(inode))
- map->m_flags |= EXT4_MAP_UNINIT;
goto out;
}
/* IO end_io complete, convert the filled extent to written */
- if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+ if (flags & EXT4_GET_BLOCKS_CONVERT) {
ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
path);
if (ret >= 0) {
@@ -4059,7 +4058,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* repeat fallocate creation request
* we already have an unwritten extent
*/
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
}
@@ -4310,7 +4309,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
- * Uninitialized extents are treated as holes, except that
+ * unwritten extents are treated as holes, except that
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
@@ -4329,16 +4328,16 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* If the extent is initialized check whether the
* caller wants to convert it to unwritten.
*/
- if ((!ext4_ext_is_uninitialized(ex)) &&
+ if ((!ext4_ext_is_unwritten(ex)) &&
(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
allocated = ext4_ext_convert_initialized_extent(
handle, inode, map, path, flags,
allocated, newblock);
goto out2;
- } else if (!ext4_ext_is_uninitialized(ex))
+ } else if (!ext4_ext_is_unwritten(ex))
goto out;
- ret = ext4_ext_handle_uninitialized_extents(
+ ret = ext4_ext_handle_unwritten_extents(
handle, inode, map, path, flags,
allocated, newblock);
if (ret < 0)
@@ -4410,15 +4409,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
- * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
- * EXT_UNINIT_MAX_LEN.
+ * EXT_INIT_MAX_LEN and for an unwritten extent this limit is
+ * EXT_UNWRITTEN_MAX_LEN.
*/
if (map->m_len > EXT_INIT_MAX_LEN &&
- !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
+ !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_INIT_MAX_LEN;
- else if (map->m_len > EXT_UNINIT_MAX_LEN &&
- (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
- map->m_len = EXT_UNINIT_MAX_LEN;
+ else if (map->m_len > EXT_UNWRITTEN_MAX_LEN &&
+ (flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
+ map->m_len = EXT_UNWRITTEN_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
newex.ee_len = cpu_to_le16(map->m_len);
@@ -4466,21 +4465,19 @@ got_allocated_blocks:
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
- /* Mark uninitialized */
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
- ext4_ext_mark_uninitialized(&newex);
+ /* Mark unwritten */
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
+ ext4_ext_mark_unwritten(&newex);
map->m_flags |= EXT4_MAP_UNWRITTEN;
/*
* io_end structure was created for every IO write to an
- * uninitialized extent. To avoid unnecessary conversion,
+ * unwritten extent. To avoid unnecessary conversion,
* here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
* that we need to perform conversion when IO is done.
*/
- if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+ if (flags & EXT4_GET_BLOCKS_PRE_IO)
set_unwritten = 1;
- if (ext4_should_dioread_nolock(inode))
- map->m_flags |= EXT4_MAP_UNINIT;
}
err = 0;
@@ -4607,9 +4604,9 @@ got_allocated_blocks:
/*
* Cache the extent and update transaction to commit on fdatasync only
- * when it is _not_ an uninitialized extent.
+ * when it is _not_ an unwritten extent.
*/
- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
else
ext4_update_inode_fsync_trans(handle, inode, 0);
@@ -4683,7 +4680,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
* that it doesn't get unnecessarily split into multiple
* extents.
*/
- if (len <= EXT_UNINIT_MAX_LEN)
+ if (len <= EXT_UNWRITTEN_MAX_LEN)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
/*
@@ -4744,6 +4741,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
if (!S_ISREG(inode->i_mode))
return -EINVAL;
+ /* Call ext4_force_commit to flush all data in case of data=journal. */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ if (ret)
+ return ret;
+ }
+
/*
* Write out all dirty pages to avoid race conditions
* Then release them.
@@ -4775,7 +4779,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
else
max_blocks -= lblk;
- flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@@ -4918,7 +4922,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
- lblk;
- flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 0ebc21204b51..3f5c188953a4 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -344,8 +344,14 @@ static int ext4_es_can_be_merged(struct extent_status *es1,
if (ext4_es_status(es1) != ext4_es_status(es2))
return 0;
- if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
+ if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) {
+ pr_warn("ES assertion failed when merging extents. "
+ "The sum of lengths of es1 (%d) and es2 (%d) "
+ "is bigger than allowed file size (%d)\n",
+ es1->es_len, es2->es_len, EXT_MAX_BLOCKS);
+ WARN_ON(1);
return 0;
+ }
if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
return 0;
@@ -433,7 +439,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
ee_start = ext4_ext_pblock(ex);
ee_len = ext4_ext_get_actual_len(ex);
- ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
+ ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0;
es_status = ext4_es_is_unwritten(es) ? 1 : 0;
/*
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 063fc1538355..4e8bc284ec0e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -57,7 +57,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
return 0;
}
-void ext4_unwritten_wait(struct inode *inode)
+static void ext4_unwritten_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
@@ -92,58 +92,91 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
}
static ssize_t
-ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct mutex *aio_mutex = NULL;
struct blk_plug plug;
- int unaligned_aio = 0;
- ssize_t ret;
+ int o_direct = file->f_flags & O_DIRECT;
int overwrite = 0;
size_t length = iov_length(iov, nr_segs);
+ ssize_t ret;
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
- !is_sync_kiocb(iocb))
- unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+ BUG_ON(iocb->ki_pos != pos);
- /* Unaligned direct AIO must be serialized; see comment above */
- if (unaligned_aio) {
- mutex_lock(ext4_aio_mutex(inode));
+ /*
+ * Unaligned direct AIO must be serialized; see comment above
+ * In the case of O_APPEND, assume that we must always serialize
+ */
+ if (o_direct &&
+ ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+ !is_sync_kiocb(iocb) &&
+ (file->f_flags & O_APPEND ||
+ ext4_unaligned_aio(inode, iov, nr_segs, pos))) {
+ aio_mutex = ext4_aio_mutex(inode);
+ mutex_lock(aio_mutex);
ext4_unwritten_wait(inode);
}
- BUG_ON(iocb->ki_pos != pos);
-
mutex_lock(&inode->i_mutex);
- blk_start_plug(&plug);
+ if (file->f_flags & O_APPEND)
+ iocb->ki_pos = pos = i_size_read(inode);
+
+ /*
+ * If we have encountered a bitmap-format file, the size limit
+ * is smaller than s_maxbytes, which is for extent-mapped files.
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- iocb->private = &overwrite;
+ if ((pos > sbi->s_bitmap_maxbytes) ||
+ (pos == sbi->s_bitmap_maxbytes && length > 0)) {
+ mutex_unlock(&inode->i_mutex);
+ ret = -EFBIG;
+ goto errout;
+ }
- /* check whether we do a DIO overwrite or not */
- if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
- !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
- struct ext4_map_blocks map;
- unsigned int blkbits = inode->i_blkbits;
- int err, len;
+ if (pos + length > sbi->s_bitmap_maxbytes) {
+ nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
+ sbi->s_bitmap_maxbytes - pos);
+ }
+ }
- map.m_lblk = pos >> blkbits;
- map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
- - map.m_lblk;
- len = map.m_len;
+ if (o_direct) {
+ blk_start_plug(&plug);
- err = ext4_map_blocks(NULL, inode, &map, 0);
- /*
- * 'err==len' means that all of blocks has been preallocated no
- * matter they are initialized or not. For excluding
- * uninitialized extents, we need to check m_flags. There are
- * two conditions that indicate for initialized extents.
- * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
- * 2) If we do a real lookup, non-flags are returned.
- * So we should check these two conditions.
- */
- if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
- overwrite = 1;
+ iocb->private = &overwrite;
+
+ /* check whether we do a DIO overwrite or not */
+ if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+ !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+ struct ext4_map_blocks map;
+ unsigned int blkbits = inode->i_blkbits;
+ int err, len;
+
+ map.m_lblk = pos >> blkbits;
+ map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+ - map.m_lblk;
+ len = map.m_len;
+
+ err = ext4_map_blocks(NULL, inode, &map, 0);
+ /*
+ * 'err==len' means that all of blocks has
+ * been preallocated no matter they are
+ * initialized or not. For excluding
+ * unwritten extents, we need to check
+ * m_flags. There are two conditions that
+ * indicate for initialized extents. 1) If we
+ * hit extent cache, EXT4_MAP_MAPPED flag is
+ * returned; 2) If we do a real lookup,
+ * non-flags are returned. So we should check
+ * these two conditions.
+ */
+ if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+ overwrite = 1;
+ }
}
ret = __generic_file_aio_write(iocb, iov, nr_segs);
@@ -156,45 +189,12 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
if (err < 0)
ret = err;
}
- blk_finish_plug(&plug);
-
- if (unaligned_aio)
- mutex_unlock(ext4_aio_mutex(inode));
-
- return ret;
-}
-
-static ssize_t
-ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- ssize_t ret;
-
- /*
- * If we have encountered a bitmap-format file, the size limit
- * is smaller than s_maxbytes, which is for extent-mapped files.
- */
-
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- size_t length = iov_length(iov, nr_segs);
-
- if ((pos > sbi->s_bitmap_maxbytes ||
- (pos == sbi->s_bitmap_maxbytes && length > 0)))
- return -EFBIG;
-
- if (pos + length > sbi->s_bitmap_maxbytes) {
- nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
- sbi->s_bitmap_maxbytes - pos);
- }
- }
-
- if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
- ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
- else
- ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ if (o_direct)
+ blk_finish_plug(&plug);
+errout:
+ if (aio_mutex)
+ mutex_unlock(aio_mutex);
return ret;
}
@@ -244,6 +244,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 82edf5b93352..645205d8ada6 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -22,7 +22,7 @@
#define EXT4_INLINE_DOTDOT_OFFSET 2
#define EXT4_INLINE_DOTDOT_SIZE 4
-int ext4_get_inline_size(struct inode *inode)
+static int ext4_get_inline_size(struct inode *inode)
{
if (EXT4_I(inode)->i_inline_off)
return EXT4_I(inode)->i_inline_size;
@@ -211,8 +211,8 @@ out:
* value since it is already handled by ext4_xattr_ibody_inline_set.
* That saves us one memcpy.
*/
-void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
- void *buffer, loff_t pos, unsigned int len)
+static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
+ void *buffer, loff_t pos, unsigned int len)
{
struct ext4_xattr_entry *entry;
struct ext4_xattr_ibody_header *header;
@@ -264,6 +264,7 @@ static int ext4_create_inline_data(handle_t *handle,
if (error)
return error;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -347,6 +348,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
if (error == -ENODATA)
goto out;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -373,8 +375,8 @@ out:
return error;
}
-int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len)
+static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len)
{
int ret, size;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -424,6 +426,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
if (error)
goto out;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -1007,6 +1010,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
if (err)
return err;
+ BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
@@ -1669,6 +1673,7 @@ int ext4_delete_inline_entry(handle_t *handle,
EXT4_MIN_INLINE_DATA_SIZE;
}
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d7b7462a0e13..7fcd68ee9155 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -148,6 +148,9 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
+ if (ext4_has_inline_data(inode))
+ return 0;
+
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
@@ -443,7 +446,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
* could be converted.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -489,8 +492,8 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
- * On success, it returns the number of blocks being mapped or allocate.
- * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * On success, it returns the number of blocks being mapped or allocated.
+ * if create==0 and the blocks are pre-allocated and unwritten block,
* the result buffer head is unmapped. If the create ==1, it will make sure
* the buffer head is mapped.
*
@@ -555,7 +558,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* file system block.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -622,12 +625,12 @@ found:
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
- * New blocks allocate and/or writing to uninitialized extent
+ * New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_blocks()
* with create == 1 flag.
*/
- down_write((&EXT4_I(inode)->i_data_sem));
+ down_write(&EXT4_I(inode)->i_data_sem);
/*
* if the caller is from delayed allocation writeout path
@@ -922,6 +925,7 @@ int do_journal_get_write_access(handle_t *handle,
*/
if (dirty)
clear_buffer_dirty(bh);
+ BUFFER_TRACE(bh, "get write access");
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
@@ -1540,7 +1544,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
ext4_es_lru_add(inode);
if (ext4_es_is_hole(&es)) {
retval = 0;
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed;
}
@@ -1577,7 +1581,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
* Try to see if we can get the block without requesting a new
* file system block.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode)) {
/*
* We will soon create blocks for this page, and let
@@ -1769,6 +1773,7 @@ static int __ext4_journalled_writepage(struct page *page,
BUG_ON(!ext4_handle_valid(handle));
if (inline_data) {
+ BUFFER_TRACE(inode_bh, "get write access");
ret = ext4_journal_get_write_access(handle, inode_bh);
err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
@@ -1846,6 +1851,7 @@ static int ext4_writepage(struct page *page,
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
struct ext4_io_submit io_submit;
+ bool keep_towrite = false;
trace_ext4_writepage(page);
size = i_size_read(inode);
@@ -1876,6 +1882,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return 0;
}
+ keep_towrite = true;
}
if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -1892,7 +1899,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return -ENOMEM;
}
- ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
@@ -1911,7 +1918,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
else
len = PAGE_CACHE_SIZE;
clear_page_dirty_for_io(page);
- err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
if (!err)
mpd->wbc->nr_to_write--;
mpd->first_page++;
@@ -2032,7 +2039,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
* Scan buffers corresponding to changed extent (we expect corresponding pages
* to be already locked) and update buffer state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits,
- * and mark buffers as uninit when we perform writes to uninitialized extents
+ * and mark buffers as uninit when we perform writes to unwritten extents
* and do extent conversion after IO is finished. If the last page is not fully
* mapped, we update @map to the next extent in the last page that needs
* mapping. Otherwise we submit the page for IO.
@@ -2126,12 +2133,12 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int get_blocks_flags;
- int err;
+ int err, dioread_nolock;
trace_ext4_da_write_pages_extent(inode, map);
/*
* Call ext4_map_blocks() to allocate any delayed allocation blocks, or
- * to convert an uninitialized extent to be initialized (in the case
+ * to convert an unwritten extent to be initialized (in the case
* where we have written into one or more preallocated blocks). It is
* possible that we're going to need more metadata blocks than
* previously reserved. However we must not fail because we're in
@@ -2148,7 +2155,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL;
- if (ext4_should_dioread_nolock(inode))
+ dioread_nolock = ext4_should_dioread_nolock(inode);
+ if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (map->m_flags & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
@@ -2156,7 +2164,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
if (err < 0)
return err;
- if (map->m_flags & EXT4_MAP_UNINIT) {
+ if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
if (!mpd->io_submit.io_end->handle &&
ext4_handle_valid(handle)) {
mpd->io_submit.io_end->handle = handle->h_rsv_handle;
@@ -3070,9 +3078,9 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
- * For holes, we fallocate those blocks, mark them as uninitialized
+ * For holes, we fallocate those blocks, mark them as unwritten
* If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as uninitialized.
+ * still keep the range to write as unwritten.
*
* The unwritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
@@ -3124,12 +3132,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
* We could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as
- * uninitialized to prevent parallel buffered read to expose
+ * unwritten to prevent parallel buffered read to expose
* the stale data before DIO complete the data IO.
*
* As to previously fallocated extents, ext4 get_block will
* just simply mark the buffer mapped but still keep the
- * extents uninitialized.
+ * extents unwritten.
*
* For non AIO case, we will convert those unwritten extents
* to written after return back from blockdev_direct_IO.
@@ -3440,7 +3448,7 @@ unlock:
* This required during truncate. We need to physically zero the tail end
* of that block so it doesn't yield old data if the file is later grown.
*/
-int ext4_block_truncate_page(handle_t *handle,
+static int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from)
{
unsigned offset = from & (PAGE_CACHE_SIZE-1);
@@ -4304,12 +4312,15 @@ static int ext4_do_update_inode(handle_t *handle,
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
+ struct super_block *sb = inode->i_sb;
int err = 0, rc, block;
- int need_datasync = 0;
+ int need_datasync = 0, set_large_file = 0;
uid_t i_uid;
gid_t i_gid;
- /* For fields not not tracking in the in-memory inode,
+ spin_lock(&ei->i_raw_lock);
+
+ /* For fields not tracked in the in-memory inode,
* initialise them to zero for new inodes. */
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
@@ -4347,8 +4358,10 @@ static int ext4_do_update_inode(handle_t *handle,
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
- if (ext4_inode_blocks_set(handle, raw_inode, ei))
+ if (ext4_inode_blocks_set(handle, raw_inode, ei)) {
+ spin_unlock(&ei->i_raw_lock);
goto out_brelse;
+ }
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
@@ -4360,24 +4373,11 @@ static int ext4_do_update_inode(handle_t *handle,
need_datasync = 1;
}
if (ei->i_disksize > 0x7fffffffULL) {
- struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
- cpu_to_le32(EXT4_GOOD_OLD_REV)) {
- /* If this is the first large file
- * created, add a flag to the superblock.
- */
- err = ext4_journal_get_write_access(handle,
- EXT4_SB(sb)->s_sbh);
- if (err)
- goto out_brelse;
- ext4_update_dynamic_rev(sb);
- EXT4_SET_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
- ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
- }
+ cpu_to_le32(EXT4_GOOD_OLD_REV))
+ set_large_file = 1;
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@@ -4409,12 +4409,24 @@ static int ext4_do_update_inode(handle_t *handle,
ext4_inode_csum_set(inode, raw_inode, ei);
+ spin_unlock(&ei->i_raw_lock);
+
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
-
+ if (set_large_file) {
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err)
+ goto out_brelse;
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_super(handle, sb);
+ }
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
brelse(bh);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c8238a26818c..59e31622cc6e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
* allocating. If we are looking at the buddy cache we would
* have taken a reference using ext4_mb_load_buddy and that
* would have pinned buddy page to page cache.
+ * The call to ext4_mb_get_buddy_page_lock will mark the
+ * page accessed.
*/
ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
@@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
ret = -EIO;
goto err;
}
- mark_page_accessed(page);
if (e4b.bd_buddy_page == NULL) {
/*
@@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
ret = -EIO;
goto err;
}
- mark_page_accessed(page);
err:
ext4_mb_put_buddy_page_lock(&e4b);
return ret;
@@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
/* we could use find_or_create_page(), but it locks page
* what we'd like to avoid in fast path ... */
- page = find_get_page(inode->i_mapping, pnum);
+ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
if (page == NULL || !PageUptodate(page)) {
if (page)
/*
@@ -1176,15 +1176,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
ret = -EIO;
goto err;
}
+
+ /* Pages marked accessed already */
e4b->bd_bitmap_page = page;
e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
- mark_page_accessed(page);
block++;
pnum = block / blocks_per_page;
poff = block % blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
+ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
if (page == NULL || !PageUptodate(page)) {
if (page)
page_cache_release(page);
@@ -1209,9 +1210,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
ret = -EIO;
goto err;
}
+
+ /* Pages marked accessed already */
e4b->bd_buddy_page = page;
e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
- mark_page_accessed(page);
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
@@ -2617,7 +2619,7 @@ int ext4_mb_init(struct super_block *sb)
sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
if (sbi->s_locality_groups == NULL) {
ret = -ENOMEM;
- goto out_free_groupinfo_slab;
+ goto out;
}
for_each_possible_cpu(i) {
struct ext4_locality_group *lg;
@@ -2642,8 +2644,6 @@ int ext4_mb_init(struct super_block *sb)
out_free_locality_groups:
free_percpu(sbi->s_locality_groups);
sbi->s_locality_groups = NULL;
-out_free_groupinfo_slab:
- ext4_groupinfo_destroy_slabs();
out:
kfree(sbi->s_mb_offsets);
sbi->s_mb_offsets = NULL;
@@ -2876,6 +2876,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (!bitmap_bh)
goto out_err;
+ BUFFER_TRACE(bitmap_bh, "getting write access");
err = ext4_journal_get_write_access(handle, bitmap_bh);
if (err)
goto out_err;
@@ -2888,6 +2889,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
ext4_free_group_clusters(sb, gdp));
+ BUFFER_TRACE(gdp_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdp_bh);
if (err)
goto out_err;
@@ -3145,7 +3147,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
}
BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical);
- BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+ BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 2ae73a80c19b..ec092437d3e0 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -505,7 +505,7 @@ int ext4_ext_migrate(struct inode *inode)
* with i_data_sem held to prevent racing with block
* allocation.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 04434ad3e8e0..32bce844c2e1 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -18,7 +18,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
return cpu_to_le32(csum);
}
-int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
{
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -27,7 +27,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
}
-void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
{
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 58ee7dc87669..2484c7ec6a72 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -57,8 +57,8 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock,
static void
copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
{
- if (ext4_ext_is_uninitialized(src))
- ext4_ext_mark_uninitialized(dest);
+ if (ext4_ext_is_unwritten(src))
+ ext4_ext_mark_unwritten(dest);
else
dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
}
@@ -391,6 +391,7 @@ mext_insert_extents(handle_t *handle, struct inode *orig_inode,
if (depth) {
/* Register to journal */
+ BUFFER_TRACE(orig_path->p_bh, "get_write_access");
ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
if (ret)
return ret;
@@ -593,14 +594,14 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
* @inode: inode in question
* @from: block offset of inode
* @count: block count to be checked
- * @uninit: extents expected to be uninitialized
+ * @unwritten: extents expected to be unwritten
* @err: pointer to save error value
*
* Return 1 if all extents in range has expected type, and zero otherwise.
*/
static int
mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
- int uninit, int *err)
+ int unwritten, int *err)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
@@ -611,7 +612,7 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
if (*err)
goto out;
ext = path[ext_depth(inode)].p_ext;
- if (uninit != ext4_ext_is_uninitialized(ext))
+ if (unwritten != ext4_ext_is_unwritten(ext))
goto out;
from += ext4_ext_get_actual_len(ext);
ext4_ext_drop_refs(path);
@@ -894,7 +895,7 @@ out:
* @orig_page_offset: page index on original file
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
- * @uninit: orig extent is uninitialized or not
+ * @unwritten: orig extent is unwritten or not
* @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
@@ -905,7 +906,7 @@ out:
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, int data_offset_in_page,
- int block_len_in_page, int uninit, int *err)
+ int block_len_in_page, int unwritten, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
struct page *pagep[2] = {NULL, NULL};
@@ -962,27 +963,27 @@ again:
if (unlikely(*err < 0))
goto stop_journal;
/*
- * If orig extent was uninitialized it can become initialized
+ * If orig extent was unwritten it can become initialized
* at any time after i_data_sem was dropped, in order to
* serialize with delalloc we have recheck extent while we
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
- if (uninit) {
+ if (unwritten) {
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* If any of extents in range became initialized we have to
* fallback to data copying */
- uninit = mext_check_coverage(orig_inode, orig_blk_offset,
- block_len_in_page, 1, err);
+ unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
+ block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
- uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
- block_len_in_page, 1, err);
+ unwritten &= mext_check_coverage(donor_inode, orig_blk_offset,
+ block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
- if (!uninit) {
+ if (!unwritten) {
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
@@ -1259,7 +1260,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
int data_offset_in_page;
int block_len_in_page;
- int uninit;
+ int unwritten;
if (orig_inode->i_sb != donor_inode->i_sb) {
ext4_debug("ext4 move extent: The argument files "
@@ -1391,8 +1392,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
!last_extent)
continue;
- /* Is original extent is uninitialized */
- uninit = ext4_ext_is_uninitialized(ext_prev);
+ /* Is original extent is unwritten */
+ unwritten = ext4_ext_is_unwritten(ext_prev);
data_offset_in_page = seq_start % blocks_per_page;
@@ -1432,8 +1433,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
o_filp, donor_inode,
orig_page_offset,
data_offset_in_page,
- block_len_in_page, uninit,
- &ret);
+ block_len_in_page,
+ unwritten, &ret);
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1cb84f78909e..3520ab8a6639 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -67,6 +67,7 @@ static struct buffer_head *ext4_append(handle_t *handle,
return ERR_PTR(err);
inode->i_size += inode->i_sb->s_blocksize;
EXT4_I(inode)->i_disksize = inode->i_size;
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
@@ -1778,6 +1779,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
blocksize = dir->i_sb->s_blocksize;
dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
+ BUFFER_TRACE(bh, "get_write_access");
retval = ext4_journal_get_write_access(handle, bh);
if (retval) {
ext4_std_error(dir->i_sb, retval);
@@ -2510,8 +2512,7 @@ static int empty_dir(struct inode *inode)
ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
de = ext4_next_entry(de1, sb->s_blocksize);
while (offset < inode->i_size) {
- if (!bh ||
- (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+ if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
unsigned int lblock;
err = 0;
brelse(bh);
@@ -2539,26 +2540,37 @@ static int empty_dir(struct inode *inode)
return 1;
}
-/* ext4_orphan_add() links an unlinked or truncated inode into a list of
+/*
+ * ext4_orphan_add() links an unlinked or truncated inode into a list of
* such inodes, starting at the superblock, in case we crash before the
* file is closed/deleted, or in case the inode truncate spans multiple
* transactions and the last transaction is not recovered after a crash.
*
* At filesystem recovery time, we walk this list deleting unlinked
* inodes and truncating linked inodes in ext4_orphan_cleanup().
+ *
+ * Orphan list manipulation functions must be called under i_mutex unless
+ * we are just creating the inode or deleting it.
*/
int ext4_orphan_add(handle_t *handle, struct inode *inode)
{
struct super_block *sb = inode->i_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_iloc iloc;
int err = 0, rc;
+ bool dirty = false;
- if (!EXT4_SB(sb)->s_journal)
+ if (!sbi->s_journal)
return 0;
- mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
+ WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+ !mutex_is_locked(&inode->i_mutex));
+ /*
+ * Exit early if inode already is on orphan list. This is a big speedup
+ * since we don't have to contend on the global s_orphan_lock.
+ */
if (!list_empty(&EXT4_I(inode)->i_orphan))
- goto out_unlock;
+ return 0;
/*
* Orphan handling is only valid for files with data blocks
@@ -2569,48 +2581,51 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
- BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
- err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
- goto out_unlock;
+ goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
- goto out_unlock;
+ goto out;
+
+ mutex_lock(&sbi->s_orphan_lock);
/*
* Due to previous errors inode may be already a part of on-disk
* orphan list. If so skip on-disk list modification.
*/
- if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
- goto mem_insert;
-
- /* Insert this inode at the head of the on-disk orphan list... */
- NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
- EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_handle_dirty_super(handle, sb);
- rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
- if (!err)
- err = rc;
-
- /* Only add to the head of the in-memory list if all the
- * previous operations succeeded. If the orphan_add is going to
- * fail (possibly taking the journal offline), we can't risk
- * leaving the inode on the orphan list: stray orphan-list
- * entries can cause panics at unmount time.
- *
- * This is safe: on error we're going to ignore the orphan list
- * anyway on the next recovery. */
-mem_insert:
- if (!err)
- list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
-
+ if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
+ (le32_to_cpu(sbi->s_es->s_inodes_count))) {
+ /* Insert this inode at the head of the on-disk orphan list */
+ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ dirty = true;
+ }
+ list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
+ mutex_unlock(&sbi->s_orphan_lock);
+
+ if (dirty) {
+ err = ext4_handle_dirty_super(handle, sb);
+ rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ if (!err)
+ err = rc;
+ if (err) {
+ /*
+ * We have to remove inode from in-memory list if
+ * addition to on disk orphan list failed. Stray orphan
+ * list entries can cause panics at unmount time.
+ */
+ mutex_lock(&sbi->s_orphan_lock);
+ list_del(&EXT4_I(inode)->i_orphan);
+ mutex_unlock(&sbi->s_orphan_lock);
+ }
+ }
jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
jbd_debug(4, "orphan inode %lu will point to %d\n",
inode->i_ino, NEXT_ORPHAN(inode));
-out_unlock:
- mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
- ext4_std_error(inode->i_sb, err);
+out:
+ ext4_std_error(sb, err);
return err;
}
@@ -2622,45 +2637,51 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
{
struct list_head *prev;
struct ext4_inode_info *ei = EXT4_I(inode);
- struct ext4_sb_info *sbi;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 ino_next;
struct ext4_iloc iloc;
int err = 0;
- if ((!EXT4_SB(inode->i_sb)->s_journal) &&
- !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS))
+ if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
return 0;
- mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+ WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+ !mutex_is_locked(&inode->i_mutex));
+ /* Do this quick check before taking global s_orphan_lock. */
if (list_empty(&ei->i_orphan))
- goto out;
+ return 0;
- ino_next = NEXT_ORPHAN(inode);
- prev = ei->i_orphan.prev;
- sbi = EXT4_SB(inode->i_sb);
+ if (handle) {
+ /* Grab inode buffer early before taking global s_orphan_lock */
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ }
+ mutex_lock(&sbi->s_orphan_lock);
jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
+ prev = ei->i_orphan.prev;
list_del_init(&ei->i_orphan);
/* If we're on an error path, we may not have a valid
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
- if (!handle)
- goto out;
-
- err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (err)
+ if (!handle || err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_err;
+ }
+ ino_next = NEXT_ORPHAN(inode);
if (prev == &sbi->s_orphan) {
jbd_debug(4, "superblock will point to %u\n", ino_next);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
+ }
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ mutex_unlock(&sbi->s_orphan_lock);
err = ext4_handle_dirty_super(handle, inode->i_sb);
} else {
struct ext4_iloc iloc2;
@@ -2670,20 +2691,20 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
jbd_debug(4, "orphan inode %lu will point to %u\n",
i_prev->i_ino, ino_next);
err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
+ }
NEXT_ORPHAN(i_prev) = ino_next;
err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+ mutex_unlock(&sbi->s_orphan_lock);
}
if (err)
goto out_brelse;
NEXT_ORPHAN(inode) = 0;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-
out_err:
ext4_std_error(inode->i_sb, err);
-out:
- mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
return err;
out_brelse:
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index c18d95b50540..b24a2541a9ba 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -401,7 +401,8 @@ submit_and_retry:
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ bool keep_towrite)
{
struct inode *inode = page->mapping->host;
unsigned block_start, blocksize;
@@ -414,10 +415,24 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- set_page_writeback(page);
+ if (keep_towrite)
+ set_page_writeback_keepwrite(page);
+ else
+ set_page_writeback(page);
ClearPageError(page);
/*
+ * Comments copied from block_write_full_page:
+ *
+ * The page straddles i_size. It must be zeroed out on each and every
+ * writepage invocation because it may be mmapped. "A file is mapped
+ * in multiples of the page size. For a file that is not a multiple of
+ * the page size, the remaining memory is zeroed when mapped, and
+ * writes to that region are not written out to the file."
+ */
+ if (len < PAGE_CACHE_SIZE)
+ zero_user_segment(page, len, PAGE_CACHE_SIZE);
+ /*
* In the first loop we prepare and mark buffers to submit. We have to
* mark all buffers in the page before submitting so that
* end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -428,19 +443,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
do {
block_start = bh_offset(bh);
if (block_start >= len) {
- /*
- * Comments copied from block_write_full_page_endio:
- *
- * The page straddles i_size. It must be zeroed out on
- * each and every writepage invocation because it may
- * be mmapped. "A file is mapped in multiples of the
- * page size. For a file that is not a multiple of
- * the page size, the remaining memory is zeroed when
- * mapped, and writes to that region are not written
- * out to the file."
- */
- zero_user_segment(page, block_start,
- block_start + blocksize);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f3b84cd9de56..bb0e80f03e2e 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -42,7 +42,7 @@ int ext4_resize_begin(struct super_block *sb)
void ext4_resize_end(struct super_block *sb)
{
clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,
@@ -348,6 +348,7 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
bh = sb_getblk(sb, blk);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
+ BUFFER_TRACE(bh, "get_write_access");
if ((err = ext4_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
@@ -426,6 +427,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
if (unlikely(!bh))
return -ENOMEM;
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
return err;
@@ -518,6 +520,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
goto out;
}
+ BUFFER_TRACE(gdb, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb);
if (err) {
brelse(gdb);
@@ -790,14 +793,17 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
goto exit_dind;
}
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (unlikely(err))
goto exit_dind;
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
goto exit_dind;
+ BUFFER_TRACE(dind, "get_write_access");
err = ext4_journal_get_write_access(handle, dind);
if (unlikely(err))
ext4_std_error(sb, err);
@@ -902,6 +908,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
EXT4_SB(sb)->s_group_desc = n_group_desc;
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree(o_group_desc);
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
brelse(gdb_bh);
@@ -977,6 +984,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
}
for (i = 0; i < reserved_gdb; i++) {
+ BUFFER_TRACE(primary[i], "get_write_access");
if ((err = ext4_journal_get_write_access(handle, primary[i])))
goto exit_bh;
}
@@ -1084,6 +1092,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data,
ext4_debug("update metadata backup %llu(+%llu)\n",
backup_block, backup_block -
ext4_group_first_block_no(sb, group));
+ BUFFER_TRACE(bh, "get_write_access");
if ((err = ext4_journal_get_write_access(handle, bh)))
break;
lock_buffer(bh);
@@ -1163,6 +1172,7 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
*/
if (gdb_off) {
gdb_bh = sbi->s_group_desc[gdb_num];
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
@@ -1433,6 +1443,7 @@ static int ext4_flex_group_add(struct super_block *sb,
goto exit;
}
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto exit_journal;
@@ -1645,6 +1656,7 @@ static int ext4_group_extend_no_check(struct super_block *sb,
return err;
}
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err) {
ext4_warning(sb, "error %d on journal write access", err);
@@ -1804,6 +1816,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6f9e6fadac04..b9b9aabfb4d2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -138,8 +138,8 @@ static __le32 ext4_superblock_csum(struct super_block *sb,
return cpu_to_le32(csum);
}
-int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es)
+static int ext4_superblock_csum_verify(struct super_block *sb,
+ struct ext4_super_block *es)
{
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -879,6 +879,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
return NULL;
ei->vfs_inode.i_version = 1;
+ spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
@@ -1903,7 +1904,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
- else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+ else if (sbi->s_mount_state & EXT4_ERROR_FS)
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
@@ -2404,6 +2405,16 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
if (ext4_bg_has_super(sb, bg))
has_super = 1;
+ /*
+ * If we have a meta_bg fs with 1k blocks, group 0's GDT is at
+ * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled
+ * on modern mke2fs or blksize > 1k on older mke2fs) then we must
+ * compensate.
+ */
+ if (sb->s_blocksize == 1024 && nr == 0 &&
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
+ has_super++;
+
return (has_super + ext4_group_first_block_no(sb, bg));
}
@@ -3337,7 +3348,7 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
- * uninitialized extents in delalloc path. In most cases such
+ * unwritten extents in delalloc path. In most cases such
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
@@ -5370,6 +5381,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
+ BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 4eec399ec807..e7387337060c 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -369,6 +369,9 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
{
int error;
+ if (strlen(name) > 255)
+ return -ERANGE;
+
down_read(&EXT4_I(inode)->xattr_sem);
error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
buffer_size);
@@ -513,6 +516,7 @@ static void ext4_xattr_update_super_block(handle_t *handle,
if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
return;
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
ext4_handle_dirty_super(handle, sb);
@@ -532,6 +536,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
+ BUFFER_TRACE(bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bh);
if (error)
goto out;
@@ -774,6 +779,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
if (s->base) {
ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
bs->bh->b_blocknr);
+ BUFFER_TRACE(bs->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bs->bh);
if (error)
goto cleanup;
@@ -859,6 +865,7 @@ inserted:
EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
+ BUFFER_TRACE(new_bh, "get_write_access");
error = ext4_journal_get_write_access(handle,
new_bh);
if (error)
@@ -896,7 +903,7 @@ inserted:
* take i_data_sem because we will test
* i_delalloc_reserved_flag in ext4_mb_new_blocks
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
up_read((&EXT4_I(inode)->i_data_sem));
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index e93e4ec7d165..dbe2141d10ad 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
}
}
- error = f2fs_setxattr(inode, name_index, "", value, size, ipage);
+ error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0);
kfree(value);
if (!error)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 4aa521aa9bc3..0b4710c1d370 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -33,12 +33,12 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
struct address_space *mapping = META_MAPPING(sbi);
struct page *page = NULL;
repeat:
- page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+ page = grab_cache_page(mapping, index);
if (!page) {
cond_resched();
goto repeat;
}
-
+ f2fs_wait_on_page_writeback(page, META);
SetPageUptodate(page);
return page;
}
@@ -69,11 +69,10 @@ repeat:
goto repeat;
}
out:
- mark_page_accessed(page);
return page;
}
-inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
{
switch (type) {
case META_NAT:
@@ -137,13 +136,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type)
if (!page)
continue;
if (PageUptodate(page)) {
- mark_page_accessed(page);
f2fs_put_page(page, 1);
continue;
}
f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
- mark_page_accessed(page);
f2fs_put_page(page, 0);
}
out:
@@ -157,6 +154,8 @@ static int f2fs_write_meta_page(struct page *page,
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ trace_f2fs_writepage(page, META);
+
if (unlikely(sbi->por_doing))
goto redirty_out;
if (wbc->for_reclaim)
@@ -174,10 +173,7 @@ no_write:
return 0;
redirty_out:
- dec_page_count(sbi, F2FS_DIRTY_META);
- wbc->pages_skipped++;
- account_page_redirty(page);
- set_page_dirty(page);
+ redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
@@ -187,6 +183,8 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
long diff, written;
+ trace_f2fs_writepages(mapping->host, wbc, META);
+
/* collect a number of dirty meta pages and write together */
if (wbc->for_kupdate ||
get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
@@ -370,7 +368,9 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
return;
sbi->por_doing = true;
- start_blk = __start_cp_addr(sbi) + 1;
+
+ start_blk = __start_cp_addr(sbi) + 1 +
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
orphan_blkaddr = __start_sum_addr(sbi) - 1;
ra_meta_pages(sbi, start_blk, orphan_blkaddr, META_CP);
@@ -511,8 +511,11 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
unsigned long blk_size = sbi->blocksize;
unsigned long long cp1_version = 0, cp2_version = 0;
unsigned long long cp_start_blk_no;
+ unsigned int cp_blks = 1 + le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+ block_t cp_blk_no;
+ int i;
- sbi->ckpt = kzalloc(blk_size, GFP_KERNEL);
+ sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
@@ -543,6 +546,23 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
+ if (cp_blks <= 1)
+ goto done;
+
+ cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
+ if (cur_page == cp2)
+ cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
+
+ for (i = 1; i < cp_blks; i++) {
+ void *sit_bitmap_ptr;
+ unsigned char *ckpt = (unsigned char *)sbi->ckpt;
+
+ cur_page = get_meta_page(sbi, cp_blk_no + i);
+ sit_bitmap_ptr = page_address(cur_page);
+ memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
+ f2fs_put_page(cur_page, 1);
+ }
+done:
f2fs_put_page(cp1, 1);
f2fs_put_page(cp2, 1);
return 0;
@@ -555,14 +575,13 @@ fail_no_cp:
static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct list_head *head = &sbi->dir_inode_list;
- struct dir_inode_entry *entry;
- list_for_each_entry(entry, head, list)
- if (unlikely(entry->inode == inode))
- return -EEXIST;
+ if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
+ return -EEXIST;
- list_add_tail(&new->list, head);
+ set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
+ F2FS_I(inode)->dirty_dir = new;
+ list_add_tail(&new->list, &sbi->dir_inode_list);
stat_inc_dirty_dir(sbi);
return 0;
}
@@ -611,31 +630,26 @@ void add_dirty_dir_inode(struct inode *inode)
void remove_dirty_dir_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct list_head *head;
struct dir_inode_entry *entry;
if (!S_ISDIR(inode->i_mode))
return;
spin_lock(&sbi->dir_inode_lock);
- if (get_dirty_dents(inode)) {
+ if (get_dirty_dents(inode) ||
+ !is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
spin_unlock(&sbi->dir_inode_lock);
return;
}
- head = &sbi->dir_inode_list;
- list_for_each_entry(entry, head, list) {
- if (entry->inode == inode) {
- list_del(&entry->list);
- stat_dec_dirty_dir(sbi);
- spin_unlock(&sbi->dir_inode_lock);
- kmem_cache_free(inode_entry_slab, entry);
- goto done;
- }
- }
+ entry = F2FS_I(inode)->dirty_dir;
+ list_del(&entry->list);
+ F2FS_I(inode)->dirty_dir = NULL;
+ clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
+ stat_dec_dirty_dir(sbi);
spin_unlock(&sbi->dir_inode_lock);
+ kmem_cache_free(inode_entry_slab, entry);
-done:
/* Only from the recovery routine */
if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
@@ -643,26 +657,6 @@ done:
}
}
-struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino)
-{
-
- struct list_head *head;
- struct inode *inode = NULL;
- struct dir_inode_entry *entry;
-
- spin_lock(&sbi->dir_inode_lock);
-
- head = &sbi->dir_inode_list;
- list_for_each_entry(entry, head, list) {
- if (entry->inode->i_ino == ino) {
- inode = entry->inode;
- break;
- }
- }
- spin_unlock(&sbi->dir_inode_lock);
- return inode;
-}
-
void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
{
struct list_head *head;
@@ -761,6 +755,13 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
__u32 crc32 = 0;
void *kaddr;
int i;
+ int cp_payload_blks = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+
+ /*
+ * This avoids to conduct wrong roll-forward operations and uses
+ * metapages, so should be called prior to sync_meta_pages below.
+ */
+ discard_next_dnode(sbi);
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META))
@@ -805,16 +806,19 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
/ F2FS_ORPHANS_PER_BLOCK;
- ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks);
+ ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
+ orphan_blocks);
if (is_umount) {
set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
- data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE);
+ cp_payload_blks + data_sum_blocks +
+ orphan_blocks + NR_CURSEG_NODE_TYPE);
} else {
clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
- data_sum_blocks + orphan_blocks);
+ cp_payload_blks + data_sum_blocks +
+ orphan_blocks);
}
if (sbi->n_orphans)
@@ -840,6 +844,15 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
set_page_dirty(cp_page);
f2fs_put_page(cp_page, 1);
+ for (i = 1; i < 1 + cp_payload_blks; i++) {
+ cp_page = grab_meta_page(sbi, start_blk++);
+ kaddr = page_address(cp_page);
+ memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
+ (1 << sbi->log_blocksize));
+ set_page_dirty(cp_page);
+ f2fs_put_page(cp_page, 1);
+ }
+
if (sbi->n_orphans) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 45abd60e2bff..c1fb6dd10911 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -417,7 +417,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
if (unlikely(dn.data_blkaddr == NEW_ADDR))
return ERR_PTR(-EINVAL);
- page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+ page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -455,7 +455,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
int err;
repeat:
- page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+ page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -652,8 +652,7 @@ static int get_data_block(struct inode *inode, sector_t iblock,
goto put_out;
}
- end_offset = IS_INODE(dn.node_page) ?
- ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
bh_result->b_size = (((size_t)1) << blkbits);
dn.ofs_in_node++;
pgofs++;
@@ -675,8 +674,7 @@ get_next:
if (dn.data_blkaddr == NEW_ADDR)
goto put_out;
- end_offset = IS_INODE(dn.node_page) ?
- ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
}
if (maxblocks > (bh_result->b_size >> blkbits)) {
@@ -710,11 +708,19 @@ out:
return err;
}
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len, get_data_block);
+}
+
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
int ret;
+ trace_f2fs_readpage(page, DATA);
+
/* If the file has inline data, try to read it directlly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
@@ -790,6 +796,8 @@ static int f2fs_write_data_page(struct page *page,
.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
};
+ trace_f2fs_writepage(page, DATA);
+
if (page->index < end_index)
goto write;
@@ -798,10 +806,8 @@ static int f2fs_write_data_page(struct page *page,
* this page does not have to be written to disk.
*/
offset = i_size & (PAGE_CACHE_SIZE - 1);
- if ((page->index >= end_index + 1) || !offset) {
- inode_dec_dirty_dents(inode);
+ if ((page->index >= end_index + 1) || !offset)
goto out;
- }
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
write:
@@ -810,7 +816,6 @@ write:
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
- inode_dec_dirty_dents(inode);
err = do_write_data_page(page, &fio);
goto done;
}
@@ -832,15 +837,16 @@ done:
clear_cold_data(page);
out:
+ inode_dec_dirty_dents(inode);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
return 0;
redirty_out:
- wbc->pages_skipped++;
- account_page_redirty(page);
- set_page_dirty(page);
+ redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
@@ -862,12 +868,15 @@ static int f2fs_write_data_pages(struct address_space *mapping,
int ret;
long diff;
+ trace_f2fs_writepages(mapping->host, wbc, DATA);
+
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
- get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA))
+ get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+ available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
diff = nr_pages_to_write(sbi, DATA, wbc);
@@ -903,6 +912,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
struct dnode_of_data dn;
int err = 0;
+ trace_f2fs_write_begin(inode, pos, len, flags);
+
f2fs_balance_fs(sbi);
repeat:
err = f2fs_convert_inline_data(inode, pos + len);
@@ -912,6 +923,10 @@ repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
+
+ /* to avoid latency during memory pressure */
+ unlock_page(page);
+
*pagep = page;
if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
@@ -923,10 +938,18 @@ repeat:
f2fs_unlock_op(sbi);
if (err) {
- f2fs_put_page(page, 1);
+ f2fs_put_page(page, 0);
return err;
}
inline_data:
+ lock_page(page);
+ if (unlikely(page->mapping != mapping)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+
+ f2fs_wait_on_page_writeback(page, DATA);
+
if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
return 0;
@@ -978,6 +1001,8 @@ static int f2fs_write_end(struct file *file,
{
struct inode *inode = page->mapping->host;
+ trace_f2fs_write_end(inode, pos, len, copied);
+
SetPageUptodate(page);
set_page_dirty(page);
@@ -1022,6 +1047,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
if (check_direct_IO(inode, rw, iov, offset, nr_segs))
return 0;
+ /* clear fsync mark to recover these blocks */
+ fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
+
return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
get_data_block);
}
@@ -1061,6 +1089,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
+ struct inode *inode = mapping->host;
+
+ if (f2fs_has_inline_data(inode))
+ return 0;
+
return generic_block_bmap(mapping, block, get_data_block);
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 972fd0ef230f..966acb039e3b 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -23,10 +23,10 @@ static unsigned long dir_blocks(struct inode *inode)
static unsigned int dir_buckets(unsigned int level, int dir_level)
{
- if (level < MAX_DIR_HASH_DEPTH / 2)
+ if (level + dir_level < MAX_DIR_HASH_DEPTH / 2)
return 1 << (level + dir_level);
else
- return 1 << ((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1);
+ return MAX_DIR_BUCKETS;
}
static unsigned int bucket_blocks(unsigned int level)
@@ -268,6 +268,8 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
{
struct f2fs_inode *ri;
+ f2fs_wait_on_page_writeback(ipage, NODE);
+
/* copy name info. to this inode page */
ri = F2FS_INODE(ipage);
ri->i_namelen = cpu_to_le32(name->len);
@@ -637,11 +639,17 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
struct f2fs_dentry_block *dentry_blk = NULL;
struct f2fs_dir_entry *de = NULL;
struct page *dentry_page = NULL;
+ struct file_ra_state *ra = &file->f_ra;
unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
unsigned char d_type = DT_UNKNOWN;
bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK);
+ /* readahead for multi pages of dir */
+ if (npages - n > 1 && !ra_has_index(ra, n))
+ page_cache_sync_readahead(inode->i_mapping, ra, file, n,
+ min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
+
for (; n < npages; n++) {
dentry_page = get_lock_data_page(inode, n);
if (IS_ERR(dentry_page))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2ecac8312359..e51c732b0dd9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -182,6 +182,8 @@ enum {
#define F2FS_LINK_MAX 32000 /* maximum link count per file */
+#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */
+
/* for in-memory extent cache entry */
#define F2FS_MIN_EXTENT_LEN 16 /* minimum extent length */
@@ -218,6 +220,7 @@ struct f2fs_inode_info {
nid_t i_xattr_nid; /* node id that contains xattrs */
unsigned long long xattr_ver; /* cp version of xattr modification */
struct extent_info ext; /* in-memory extent cache entry */
+ struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -243,6 +246,7 @@ static inline void set_raw_extent(struct extent_info *ext,
struct f2fs_nm_info {
block_t nat_blkaddr; /* base disk address of NAT */
nid_t max_nid; /* maximum possible node ids */
+ nid_t available_nids; /* maximum available node ids */
nid_t next_scan_nid; /* the next nid to be scanned */
unsigned int ram_thresh; /* control the memory footprint */
@@ -323,6 +327,15 @@ struct flush_cmd {
int ret;
};
+struct flush_cmd_control {
+ struct task_struct *f2fs_issue_flush; /* flush thread */
+ wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
+ struct flush_cmd *issue_list; /* list for command issue */
+ struct flush_cmd *dispatch_list; /* list for command dispatch */
+ spinlock_t issue_lock; /* for issue list lock */
+ struct flush_cmd *issue_tail; /* list tail of issue list */
+};
+
struct f2fs_sm_info {
struct sit_info *sit_info; /* whole segment information */
struct free_segmap_info *free_info; /* free segment information */
@@ -353,12 +366,8 @@ struct f2fs_sm_info {
unsigned int min_ipu_util; /* in-place-update threshold */
/* for flush command control */
- struct task_struct *f2fs_issue_flush; /* flush thread */
- wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
- struct flush_cmd *issue_list; /* list for command issue */
- struct flush_cmd *dispatch_list; /* list for command dispatch */
- spinlock_t issue_lock; /* for issue list lock */
- struct flush_cmd *issue_tail; /* list tail of issue list */
+ struct flush_cmd_control *cmd_control_info;
+
};
/*
@@ -755,9 +764,18 @@ static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- int offset = (flag == NAT_BITMAP) ?
+ int offset;
+
+ if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload) > 0) {
+ if (flag == NAT_BITMAP)
+ return &ckpt->sit_nat_version_bitmap;
+ else
+ return ((unsigned char *)ckpt + F2FS_BLKSIZE);
+ } else {
+ offset = (flag == NAT_BITMAP) ?
le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
- return &ckpt->sit_nat_version_bitmap + offset;
+ return &ckpt->sit_nat_version_bitmap + offset;
+ }
}
static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
@@ -958,6 +976,7 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr)
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
FI_DIRTY_INODE, /* indicate inode is dirty or not */
+ FI_DIRTY_DIR, /* indicate directory has dirty pages */
FI_INC_LINK, /* need to increment i_nlink */
FI_ACL_MODE, /* indicate acl mode */
FI_NO_ALLOC, /* should not allocate any blocks */
@@ -1071,6 +1090,12 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
+/* get offset of first page in next direct node */
+#define PGOFS_OF_NEXT_DNODE(pgofs, fi) \
+ ((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) : \
+ (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \
+ ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+
/*
* file.c
*/
@@ -1140,8 +1165,10 @@ f2fs_hash_t f2fs_dentry_hash(const char *, size_t);
struct dnode_of_data;
struct node_info;
+bool available_free_memory(struct f2fs_sb_info *, int);
int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
bool fsync_mark_done(struct f2fs_sb_info *, nid_t);
+void fsync_mark_clear(struct f2fs_sb_info *, nid_t);
void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
@@ -1176,9 +1203,12 @@ void destroy_node_manager_caches(void);
void f2fs_balance_fs(struct f2fs_sb_info *);
void f2fs_balance_fs_bg(struct f2fs_sb_info *);
int f2fs_issue_flush(struct f2fs_sb_info *);
+int create_flush_cmd_control(struct f2fs_sb_info *);
+void destroy_flush_cmd_control(struct f2fs_sb_info *);
void invalidate_blocks(struct f2fs_sb_info *, block_t);
void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
void clear_prefree_segments(struct f2fs_sb_info *);
+void discard_next_dnode(struct f2fs_sb_info *);
int npages_for_summary_flush(struct f2fs_sb_info *);
void allocate_new_segments(struct f2fs_sb_info *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
@@ -1221,7 +1251,6 @@ int get_valid_checkpoint(struct f2fs_sb_info *);
void set_dirty_dir_page(struct inode *, struct page *);
void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
-struct inode *check_dirty_dir_inode(struct f2fs_sb_info *, nid_t);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
void write_checkpoint(struct f2fs_sb_info *, bool);
void init_orphan_info(struct f2fs_sb_info *);
@@ -1242,6 +1271,7 @@ struct page *find_data_page(struct inode *, pgoff_t, bool);
struct page *get_lock_data_page(struct inode *, pgoff_t);
struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
int do_write_data_page(struct page *, struct f2fs_io_info *);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
/*
* gc.c
@@ -1391,5 +1421,6 @@ bool f2fs_may_inline(struct inode *);
int f2fs_read_inline_data(struct inode *, struct page *);
int f2fs_convert_inline_data(struct inode *, pgoff_t);
int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
+void truncate_inline_data(struct inode *, u64);
int recover_inline_data(struct inode *, struct page *);
#endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 60e7d5448a1d..9c49c593d8eb 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -19,6 +19,7 @@
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
+#include <linux/pagevec.h>
#include "f2fs.h"
#include "node.h"
@@ -194,6 +195,132 @@ out:
return ret;
}
+static pgoff_t __get_first_dirty_index(struct address_space *mapping,
+ pgoff_t pgofs, int whence)
+{
+ struct pagevec pvec;
+ int nr_pages;
+
+ if (whence != SEEK_DATA)
+ return 0;
+
+ /* find first dirty page index */
+ pagevec_init(&pvec, 0);
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, PAGECACHE_TAG_DIRTY, 1);
+ pgofs = nr_pages ? pvec.pages[0]->index: LONG_MAX;
+ pagevec_release(&pvec);
+ return pgofs;
+}
+
+static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
+ int whence)
+{
+ switch (whence) {
+ case SEEK_DATA:
+ if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
+ (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+ return true;
+ break;
+ case SEEK_HOLE:
+ if (blkaddr == NULL_ADDR)
+ return true;
+ break;
+ }
+ return false;
+}
+
+static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t maxbytes = inode->i_sb->s_maxbytes;
+ struct dnode_of_data dn;
+ pgoff_t pgofs, end_offset, dirty;
+ loff_t data_ofs = offset;
+ loff_t isize;
+ int err = 0;
+
+ mutex_lock(&inode->i_mutex);
+
+ isize = i_size_read(inode);
+ if (offset >= isize)
+ goto fail;
+
+ /* handle inline data case */
+ if (f2fs_has_inline_data(inode)) {
+ if (whence == SEEK_HOLE)
+ data_ofs = isize;
+ goto found;
+ }
+
+ pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+
+ dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
+
+ for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+ if (err && err != -ENOENT) {
+ goto fail;
+ } else if (err == -ENOENT) {
+ /* direct node is not exist */
+ if (whence == SEEK_DATA) {
+ pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
+ F2FS_I(inode));
+ continue;
+ } else {
+ goto found;
+ }
+ }
+
+ end_offset = IS_INODE(dn.node_page) ?
+ ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+
+ /* find data/hole in dnode block */
+ for (; dn.ofs_in_node < end_offset;
+ dn.ofs_in_node++, pgofs++,
+ data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ block_t blkaddr;
+ blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+ if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+ f2fs_put_dnode(&dn);
+ goto found;
+ }
+ }
+ f2fs_put_dnode(&dn);
+ }
+
+ if (whence == SEEK_DATA)
+ goto fail;
+found:
+ if (whence == SEEK_HOLE && data_ofs > isize)
+ data_ofs = isize;
+ mutex_unlock(&inode->i_mutex);
+ return vfs_setpos(file, data_ofs, maxbytes);
+fail:
+ mutex_unlock(&inode->i_mutex);
+ return -ENXIO;
+}
+
+static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t maxbytes = inode->i_sb->s_maxbytes;
+
+ switch (whence) {
+ case SEEK_SET:
+ case SEEK_CUR:
+ case SEEK_END:
+ return generic_file_llseek_size(file, offset, whence,
+ maxbytes, i_size_read(inode));
+ case SEEK_DATA:
+ case SEEK_HOLE:
+ return f2fs_seek_block(file, offset, whence);
+ }
+
+ return -EINVAL;
+}
+
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
@@ -242,6 +369,9 @@ static void truncate_partial_data_page(struct inode *inode, u64 from)
unsigned offset = from & (PAGE_CACHE_SIZE - 1);
struct page *page;
+ if (f2fs_has_inline_data(inode))
+ return truncate_inline_data(inode, from);
+
if (!offset)
return;
@@ -288,10 +418,7 @@ int truncate_blocks(struct inode *inode, u64 from)
return err;
}
- if (IS_INODE(dn.node_page))
- count = ADDRS_PER_INODE(F2FS_I(inode));
- else
- count = ADDRS_PER_BLOCK;
+ count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
count -= dn.ofs_in_node;
f2fs_bug_on(count < 0);
@@ -413,6 +540,7 @@ const struct inode_operations f2fs_file_inode_operations = {
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
+ .fiemap = f2fs_fiemap,
};
static void fill_zero(struct inode *inode, pgoff_t index,
@@ -555,6 +683,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
+ f2fs_write_inode(inode, NULL);
}
return ret;
@@ -678,7 +807,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
#endif
const struct file_operations f2fs_file_operations = {
- .llseek = generic_file_llseek,
+ .llseek = f2fs_llseek,
.read = do_sync_read,
.write = do_sync_write,
.aio_read = generic_file_aio_read,
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 383db1fabcf4..1bba5228c197 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -81,8 +81,10 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(ipage))
- return PTR_ERR(ipage);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto out;
+ }
/*
* i_addr[0] is not used for inline data,
@@ -90,11 +92,10 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
*/
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
- if (err) {
- f2fs_unlock_op(sbi);
- return err;
- }
+ if (err)
+ goto out;
+ f2fs_wait_on_page_writeback(page, DATA);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
@@ -118,6 +119,7 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
+out:
f2fs_unlock_op(sbi);
return err;
}
@@ -132,7 +134,7 @@ int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size)
else if (to_size <= MAX_INLINE_DATA)
return 0;
- page = grab_cache_page_write_begin(inode->i_mapping, 0, AOP_FLAG_NOFS);
+ page = grab_cache_page(inode->i_mapping, 0);
if (!page)
return -ENOMEM;
@@ -155,6 +157,7 @@ int f2fs_write_inline_data(struct inode *inode,
return err;
ipage = dn.inode_page;
+ f2fs_wait_on_page_writeback(ipage, NODE);
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
src_addr = kmap(page);
@@ -175,6 +178,26 @@ int f2fs_write_inline_data(struct inode *inode,
return 0;
}
+void truncate_inline_data(struct inode *inode, u64 from)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct page *ipage;
+
+ if (from >= MAX_INLINE_DATA)
+ return;
+
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage))
+ return;
+
+ f2fs_wait_on_page_writeback(ipage, NODE);
+
+ zero_user_segment(ipage, INLINE_DATA_OFFSET + from,
+ INLINE_DATA_OFFSET + MAX_INLINE_DATA);
+ set_page_dirty(ipage);
+ f2fs_put_page(ipage, 1);
+}
+
int recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -199,6 +222,8 @@ process_inline:
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(IS_ERR(ipage));
+ f2fs_wait_on_page_writeback(ipage, NODE);
+
src_addr = inline_data_addr(npage);
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
@@ -210,6 +235,7 @@ process_inline:
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(IS_ERR(ipage));
+ f2fs_wait_on_page_writeback(ipage, NODE);
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index ee829d360468..adc622c6bdce 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -12,6 +12,7 @@
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
+#include <linux/bitops.h>
#include "f2fs.h"
#include "node.h"
@@ -21,20 +22,20 @@
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
-
- inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE |
- S_NOATIME | S_DIRSYNC);
+ unsigned int new_fl = 0;
if (flags & FS_SYNC_FL)
- inode->i_flags |= S_SYNC;
+ new_fl |= S_SYNC;
if (flags & FS_APPEND_FL)
- inode->i_flags |= S_APPEND;
+ new_fl |= S_APPEND;
if (flags & FS_IMMUTABLE_FL)
- inode->i_flags |= S_IMMUTABLE;
+ new_fl |= S_IMMUTABLE;
if (flags & FS_NOATIME_FL)
- inode->i_flags |= S_NOATIME;
+ new_fl |= S_NOATIME;
if (flags & FS_DIRSYNC_FL)
- inode->i_flags |= S_DIRSYNC;
+ new_fl |= S_DIRSYNC;
+ set_mask_bits(&inode->i_flags,
+ S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -294,4 +295,5 @@ void f2fs_evict_inode(struct inode *inode)
sb_end_intwrite(inode->i_sb);
no_delete:
clear_inode(inode);
+ invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a9409d19dfd4..9138c32aa698 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -41,18 +41,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
}
f2fs_unlock_op(sbi);
- inode->i_uid = current_fsuid();
-
- if (dir->i_mode & S_ISGID) {
- inode->i_gid = dir->i_gid;
- if (S_ISDIR(mode))
- mode |= S_ISGID;
- } else {
- inode->i_gid = current_fsgid();
- }
+ inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
- inode->i_mode = mode;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = sbi->s_next_generation++;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index a161e955c4c8..9dfb9a042fd2 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -26,20 +26,26 @@
static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;
-static inline bool available_free_memory(struct f2fs_nm_info *nm_i, int type)
+bool available_free_memory(struct f2fs_sb_info *sbi, int type)
{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
struct sysinfo val;
unsigned long mem_size = 0;
+ bool res = false;
si_meminfo(&val);
- if (type == FREE_NIDS)
- mem_size = nm_i->fcnt * sizeof(struct free_nid);
- else if (type == NAT_ENTRIES)
- mem_size += nm_i->nat_cnt * sizeof(struct nat_entry);
- mem_size >>= 12;
-
- /* give 50:50 memory for free nids and nat caches respectively */
- return (mem_size < ((val.totalram * nm_i->ram_thresh) >> 11));
+ /* give 25%, 25%, 50% memory for each components respectively */
+ if (type == FREE_NIDS) {
+ mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12;
+ res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+ } else if (type == NAT_ENTRIES) {
+ mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
+ res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+ } else if (type == DIRTY_DENTS) {
+ mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
+ res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
+ }
+ return res;
}
static void clear_node_page_dirty(struct page *page)
@@ -147,6 +153,18 @@ bool fsync_mark_done(struct f2fs_sb_info *sbi, nid_t nid)
return fsync_done;
}
+void fsync_mark_clear(struct f2fs_sb_info *sbi, nid_t nid)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct nat_entry *e;
+
+ write_lock(&nm_i->nat_tree_lock);
+ e = __lookup_nat_cache(nm_i, nid);
+ if (e)
+ e->fsync_done = false;
+ write_unlock(&nm_i->nat_tree_lock);
+}
+
static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
{
struct nat_entry *new;
@@ -179,9 +197,7 @@ retry:
write_unlock(&nm_i->nat_tree_lock);
goto retry;
}
- nat_set_blkaddr(e, le32_to_cpu(ne->block_addr));
- nat_set_ino(e, le32_to_cpu(ne->ino));
- nat_set_version(e, ne->version);
+ node_info_from_raw_nat(&e->ni, ne);
}
write_unlock(&nm_i->nat_tree_lock);
}
@@ -243,7 +259,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
- if (available_free_memory(nm_i, NAT_ENTRIES))
+ if (available_free_memory(sbi, NAT_ENTRIES))
return 0;
write_lock(&nm_i->nat_tree_lock);
@@ -849,8 +865,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return ERR_PTR(-EPERM);
- page = grab_cache_page_write_begin(NODE_MAPPING(sbi),
- dn->nid, AOP_FLAG_NOFS);
+ page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -867,6 +882,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
new_ni.ino = dn->inode->i_ino;
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
+ f2fs_wait_on_page_writeback(page, NODE);
fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
set_cold_node(dn->inode, page);
SetPageUptodate(page);
@@ -946,8 +962,7 @@ struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
struct page *page;
int err;
repeat:
- page = grab_cache_page_write_begin(NODE_MAPPING(sbi),
- nid, AOP_FLAG_NOFS);
+ page = grab_cache_page(NODE_MAPPING(sbi), nid);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -967,7 +982,6 @@ repeat:
goto repeat;
}
got_it:
- mark_page_accessed(page);
return page;
}
@@ -1022,7 +1036,6 @@ page_hit:
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
- mark_page_accessed(page);
return page;
}
@@ -1196,6 +1209,8 @@ static int f2fs_write_node_page(struct page *page,
.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
};
+ trace_f2fs_writepage(page, NODE);
+
if (unlikely(sbi->por_doing))
goto redirty_out;
@@ -1227,10 +1242,7 @@ static int f2fs_write_node_page(struct page *page,
return 0;
redirty_out:
- dec_page_count(sbi, F2FS_DIRTY_NODES);
- wbc->pages_skipped++;
- account_page_redirty(page);
- set_page_dirty(page);
+ redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
@@ -1240,6 +1252,8 @@ static int f2fs_write_node_pages(struct address_space *mapping,
struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
long diff;
+ trace_f2fs_writepages(mapping->host, wbc, NODE);
+
/* balancing f2fs's metadata in background */
f2fs_balance_fs_bg(sbi);
@@ -1315,13 +1329,14 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
radix_tree_delete(&nm_i->free_nid_root, i->nid);
}
-static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build)
+static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
struct nat_entry *ne;
bool allocated = false;
- if (!available_free_memory(nm_i, FREE_NIDS))
+ if (!available_free_memory(sbi, FREE_NIDS))
return -1;
/* 0 nid should not be used */
@@ -1374,9 +1389,10 @@ static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
kmem_cache_free(free_nid_slab, i);
}
-static void scan_nat_page(struct f2fs_nm_info *nm_i,
+static void scan_nat_page(struct f2fs_sb_info *sbi,
struct page *nat_page, nid_t start_nid)
{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
struct f2fs_nat_block *nat_blk = page_address(nat_page);
block_t blk_addr;
int i;
@@ -1391,7 +1407,7 @@ static void scan_nat_page(struct f2fs_nm_info *nm_i,
blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
f2fs_bug_on(blk_addr == NEW_ADDR);
if (blk_addr == NULL_ADDR) {
- if (add_free_nid(nm_i, start_nid, true) < 0)
+ if (add_free_nid(sbi, start_nid, true) < 0)
break;
}
}
@@ -1415,7 +1431,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
- scan_nat_page(nm_i, page, nid);
+ scan_nat_page(sbi, page, nid);
f2fs_put_page(page, 1);
nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
@@ -1435,7 +1451,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
nid = le32_to_cpu(nid_in_journal(sum, i));
if (addr == NULL_ADDR)
- add_free_nid(nm_i, nid, true);
+ add_free_nid(sbi, nid, true);
else
remove_free_nid(nm_i, nid);
}
@@ -1452,7 +1468,7 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i = NULL;
retry:
- if (unlikely(sbi->total_valid_node_count + 1 >= nm_i->max_nid))
+ if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
return false;
spin_lock(&nm_i->free_nid_list_lock);
@@ -1512,7 +1528,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
spin_lock(&nm_i->free_nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
f2fs_bug_on(!i || i->state != NID_ALLOC);
- if (!available_free_memory(nm_i, FREE_NIDS)) {
+ if (!available_free_memory(sbi, FREE_NIDS)) {
__del_from_free_nid_list(nm_i, i);
need_free = true;
} else {
@@ -1534,7 +1550,7 @@ void recover_node_page(struct f2fs_sb_info *sbi, struct page *page,
clear_node_page_dirty(page);
}
-void recover_inline_xattr(struct inode *inode, struct page *page)
+static void recover_inline_xattr(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
void *src_addr, *dst_addr;
@@ -1559,6 +1575,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
src_addr = inline_xattr_addr(page);
inline_size = inline_xattr_size(inode);
+ f2fs_wait_on_page_writeback(ipage, NODE);
memcpy(dst_addr, src_addr, inline_size);
update_inode(inode, ipage);
@@ -1614,6 +1631,11 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
struct node_info old_ni, new_ni;
struct page *ipage;
+ get_node_info(sbi, ino, &old_ni);
+
+ if (unlikely(old_ni.blk_addr != NULL_ADDR))
+ return -EINVAL;
+
ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
if (!ipage)
return -ENOMEM;
@@ -1621,7 +1643,6 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
/* Should not use this inode from free nid list */
remove_free_nid(NM_I(sbi), ino);
- get_node_info(sbi, ino, &old_ni);
SetPageUptodate(ipage);
fill_node_footer(ipage, ino, ino, 0, true);
@@ -1647,35 +1668,29 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
/*
* ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-readed pages are linked in pages list.
+ * these pre-readed pages are alloced in bd_inode's mapping tree.
*/
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct list_head *pages,
+static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
int start, int nrpages)
{
- struct page *page;
- int page_idx = start;
+ struct inode *inode = sbi->sb->s_bdev->bd_inode;
+ struct address_space *mapping = inode->i_mapping;
+ int i, page_idx = start;
struct f2fs_io_info fio = {
.type = META,
.rw = READ_SYNC | REQ_META | REQ_PRIO
};
- for (; page_idx < start + nrpages; page_idx++) {
- /* alloc temporal page for read node summary info*/
- page = alloc_page(GFP_F2FS_ZERO);
- if (!page)
+ for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
+ /* alloc page in bd_inode for reading node summary info */
+ pages[i] = grab_cache_page(mapping, page_idx);
+ if (!pages[i])
break;
-
- lock_page(page);
- page->index = page_idx;
- list_add_tail(&page->lru, pages);
+ f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
}
- list_for_each_entry(page, pages, lru)
- f2fs_submit_page_mbio(sbi, page, page->index, &fio);
-
f2fs_submit_merged_bio(sbi, META, READ);
-
- return page_idx - start;
+ return i;
}
int restore_node_summary(struct f2fs_sb_info *sbi,
@@ -1683,11 +1698,11 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
{
struct f2fs_node *rn;
struct f2fs_summary *sum_entry;
- struct page *page, *tmp;
+ struct inode *inode = sbi->sb->s_bdev->bd_inode;
block_t addr;
int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
- int i, last_offset, nrpages, err = 0;
- LIST_HEAD(page_list);
+ struct page *pages[bio_blocks];
+ int i, idx, last_offset, nrpages, err = 0;
/* scan the node segment */
last_offset = sbi->blocks_per_seg;
@@ -1698,29 +1713,31 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
nrpages = min(last_offset - i, bio_blocks);
/* read ahead node pages */
- nrpages = ra_sum_pages(sbi, &page_list, addr, nrpages);
+ nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
if (!nrpages)
return -ENOMEM;
- list_for_each_entry_safe(page, tmp, &page_list, lru) {
+ for (idx = 0; idx < nrpages; idx++) {
if (err)
goto skip;
- lock_page(page);
- if (unlikely(!PageUptodate(page))) {
+ lock_page(pages[idx]);
+ if (unlikely(!PageUptodate(pages[idx]))) {
err = -EIO;
} else {
- rn = F2FS_NODE(page);
+ rn = F2FS_NODE(pages[idx]);
sum_entry->nid = rn->footer.nid;
sum_entry->version = 0;
sum_entry->ofs_in_node = 0;
sum_entry++;
}
- unlock_page(page);
+ unlock_page(pages[idx]);
skip:
- list_del(&page->lru);
- __free_pages(page, 0);
+ page_cache_release(pages[idx]);
}
+
+ invalidate_mapping_pages(inode->i_mapping, addr,
+ addr + nrpages);
}
return err;
}
@@ -1758,9 +1775,7 @@ retry:
write_unlock(&nm_i->nat_tree_lock);
goto retry;
}
- nat_set_blkaddr(ne, le32_to_cpu(raw_ne.block_addr));
- nat_set_ino(ne, le32_to_cpu(raw_ne.ino));
- nat_set_version(ne, raw_ne.version);
+ node_info_from_raw_nat(&ne->ni, &raw_ne);
__set_nat_cache_dirty(nm_i, ne);
write_unlock(&nm_i->nat_tree_lock);
}
@@ -1793,7 +1808,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
nid_t nid;
struct f2fs_nat_entry raw_ne;
int offset = -1;
- block_t new_blkaddr;
if (nat_get_blkaddr(ne) == NEW_ADDR)
continue;
@@ -1829,11 +1843,7 @@ to_nat_page:
f2fs_bug_on(!nat_blk);
raw_ne = nat_blk->entries[nid - start_nid];
flush_now:
- new_blkaddr = nat_get_blkaddr(ne);
-
- raw_ne.ino = cpu_to_le32(nat_get_ino(ne));
- raw_ne.block_addr = cpu_to_le32(new_blkaddr);
- raw_ne.version = nat_get_version(ne);
+ raw_nat_from_node_info(&raw_ne, &ne->ni);
if (offset < 0) {
nat_blk->entries[nid - start_nid] = raw_ne;
@@ -1843,7 +1853,7 @@ flush_now:
}
if (nat_get_blkaddr(ne) == NULL_ADDR &&
- add_free_nid(NM_I(sbi), nid, false) <= 0) {
+ add_free_nid(sbi, nid, false) <= 0) {
write_lock(&nm_i->nat_tree_lock);
__del_from_nat_cache(nm_i, ne);
write_unlock(&nm_i->nat_tree_lock);
@@ -1871,8 +1881,10 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
+ nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+
/* not used nids: 0, node, meta, (and root counted as valid node) */
- nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks - 3;
+ nm_i->available_nids = nm_i->max_nid - 3;
nm_i->fcnt = 0;
nm_i->nat_cnt = 0;
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 5decc1a375f0..7281112cd1c8 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -59,12 +59,12 @@ struct nat_entry {
do { \
ne->checkpointed = false; \
list_move_tail(&ne->list, &nm_i->dirty_nat_entries); \
- } while (0);
+ } while (0)
#define __clear_nat_cache_dirty(nm_i, ne) \
do { \
ne->checkpointed = true; \
list_move_tail(&ne->list, &nm_i->nat_entries); \
- } while (0);
+ } while (0)
#define inc_node_version(version) (++version)
static inline void node_info_from_raw_nat(struct node_info *ni,
@@ -75,9 +75,18 @@ static inline void node_info_from_raw_nat(struct node_info *ni,
ni->version = raw_ne->version;
}
-enum nid_type {
+static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
+ struct node_info *ni)
+{
+ raw_ne->ino = cpu_to_le32(ni->ino);
+ raw_ne->block_addr = cpu_to_le32(ni->blk_addr);
+ raw_ne->version = ni->version;
+}
+
+enum mem_type {
FREE_NIDS, /* indicates the free nid list */
- NAT_ENTRIES /* indicates the cached nat entry */
+ NAT_ENTRIES, /* indicates the cached nat entry */
+ DIRTY_DENTS /* indicates dirty dentry pages */
};
/*
@@ -263,7 +272,7 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
- wait_on_page_writeback(p);
+ f2fs_wait_on_page_writeback(p, NODE);
if (i)
rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index b1ae89f0f44e..a112368a4a86 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -46,15 +46,10 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
struct inode *dir, *einode;
int err = 0;
- dir = check_dirty_dir_inode(F2FS_SB(inode->i_sb), pino);
- if (!dir) {
- dir = f2fs_iget(inode->i_sb, pino);
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
- }
- set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
- add_dirty_dir_inode(dir);
+ dir = f2fs_iget(inode->i_sb, pino);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
}
name.len = le32_to_cpu(raw_inode->i_namelen);
@@ -63,7 +58,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
if (unlikely(name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
- goto out;
+ goto out_err;
}
retry:
de = f2fs_find_entry(dir, &name, &page);
@@ -73,7 +68,8 @@ retry:
einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
if (IS_ERR(einode)) {
WARN_ON(1);
- if (PTR_ERR(einode) == -ENOENT)
+ err = PTR_ERR(einode);
+ if (err == -ENOENT)
err = -EEXIST;
goto out_unmap_put;
}
@@ -87,11 +83,23 @@ retry:
goto retry;
}
err = __f2fs_add_link(dir, &name, inode);
+ if (err)
+ goto out_err;
+
+ if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
+ iput(dir);
+ } else {
+ add_dirty_dir_inode(dir);
+ set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
+ }
+
goto out;
out_unmap_put:
kunmap(page);
f2fs_put_page(page, 0);
+out_err:
+ iput(dir);
out:
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -299,10 +307,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
goto out;
start = start_bidx_of_node(ofs_of_node(page), fi);
- if (IS_INODE(page))
- end = start + ADDRS_PER_INODE(fi);
- else
- end = start + ADDRS_PER_BLOCK;
+ end = start + ADDRS_PER_PAGE(page, fi);
f2fs_lock_op(sbi);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 085f548be7a3..f25f0e07e26f 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -25,7 +25,6 @@
#define __reverse_ffz(x) __reverse_ffs(~(x))
static struct kmem_cache *discard_entry_slab;
-static struct kmem_cache *flush_cmd_slab;
/*
* __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
@@ -200,20 +199,20 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
static int issue_flush_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
- struct f2fs_sm_info *sm_i = SM_I(sbi);
- wait_queue_head_t *q = &sm_i->flush_wait_queue;
+ struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ wait_queue_head_t *q = &fcc->flush_wait_queue;
repeat:
if (kthread_should_stop())
return 0;
- spin_lock(&sm_i->issue_lock);
- if (sm_i->issue_list) {
- sm_i->dispatch_list = sm_i->issue_list;
- sm_i->issue_list = sm_i->issue_tail = NULL;
+ spin_lock(&fcc->issue_lock);
+ if (fcc->issue_list) {
+ fcc->dispatch_list = fcc->issue_list;
+ fcc->issue_list = fcc->issue_tail = NULL;
}
- spin_unlock(&sm_i->issue_lock);
+ spin_unlock(&fcc->issue_lock);
- if (sm_i->dispatch_list) {
+ if (fcc->dispatch_list) {
struct bio *bio = bio_alloc(GFP_NOIO, 0);
struct flush_cmd *cmd, *next;
int ret;
@@ -221,47 +220,79 @@ repeat:
bio->bi_bdev = sbi->sb->s_bdev;
ret = submit_bio_wait(WRITE_FLUSH, bio);
- for (cmd = sm_i->dispatch_list; cmd; cmd = next) {
+ for (cmd = fcc->dispatch_list; cmd; cmd = next) {
cmd->ret = ret;
next = cmd->next;
complete(&cmd->wait);
}
- sm_i->dispatch_list = NULL;
+ bio_put(bio);
+ fcc->dispatch_list = NULL;
}
- wait_event_interruptible(*q, kthread_should_stop() || sm_i->issue_list);
+ wait_event_interruptible(*q,
+ kthread_should_stop() || fcc->issue_list);
goto repeat;
}
int f2fs_issue_flush(struct f2fs_sb_info *sbi)
{
- struct f2fs_sm_info *sm_i = SM_I(sbi);
- struct flush_cmd *cmd;
- int ret;
+ struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd cmd;
if (!test_opt(sbi, FLUSH_MERGE))
return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL);
- cmd = f2fs_kmem_cache_alloc(flush_cmd_slab, GFP_ATOMIC);
- cmd->next = NULL;
- cmd->ret = 0;
- init_completion(&cmd->wait);
+ init_completion(&cmd.wait);
+ cmd.next = NULL;
- spin_lock(&sm_i->issue_lock);
- if (sm_i->issue_list)
- sm_i->issue_tail->next = cmd;
+ spin_lock(&fcc->issue_lock);
+ if (fcc->issue_list)
+ fcc->issue_tail->next = &cmd;
else
- sm_i->issue_list = cmd;
- sm_i->issue_tail = cmd;
- spin_unlock(&sm_i->issue_lock);
+ fcc->issue_list = &cmd;
+ fcc->issue_tail = &cmd;
+ spin_unlock(&fcc->issue_lock);
- if (!sm_i->dispatch_list)
- wake_up(&sm_i->flush_wait_queue);
+ if (!fcc->dispatch_list)
+ wake_up(&fcc->flush_wait_queue);
- wait_for_completion(&cmd->wait);
- ret = cmd->ret;
- kmem_cache_free(flush_cmd_slab, cmd);
- return ret;
+ wait_for_completion(&cmd.wait);
+
+ return cmd.ret;
+}
+
+int create_flush_cmd_control(struct f2fs_sb_info *sbi)
+{
+ dev_t dev = sbi->sb->s_bdev->bd_dev;
+ struct flush_cmd_control *fcc;
+ int err = 0;
+
+ fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
+ if (!fcc)
+ return -ENOMEM;
+ spin_lock_init(&fcc->issue_lock);
+ init_waitqueue_head(&fcc->flush_wait_queue);
+ fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
+ "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
+ if (IS_ERR(fcc->f2fs_issue_flush)) {
+ err = PTR_ERR(fcc->f2fs_issue_flush);
+ kfree(fcc);
+ return err;
+ }
+ sbi->sm_info->cmd_control_info = fcc;
+
+ return err;
+}
+
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+{
+ struct flush_cmd_control *fcc =
+ sbi->sm_info->cmd_control_info;
+
+ if (fcc && fcc->f2fs_issue_flush)
+ kthread_stop(fcc->f2fs_issue_flush);
+ kfree(fcc);
+ sbi->sm_info->cmd_control_info = NULL;
}
static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -336,13 +367,26 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
mutex_unlock(&dirty_i->seglist_lock);
}
-static void f2fs_issue_discard(struct f2fs_sb_info *sbi,
+static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
block_t blkstart, block_t blklen)
{
sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
- blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+ return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
+}
+
+void discard_next_dnode(struct f2fs_sb_info *sbi)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+ block_t blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
+ if (f2fs_issue_discard(sbi, blkaddr, 1)) {
+ struct page *page = grab_meta_page(sbi, blkaddr);
+ /* zero-filled page */
+ set_page_dirty(page);
+ f2fs_put_page(page, 1);
+ }
}
static void add_discard_addrs(struct f2fs_sb_info *sbi,
@@ -1832,7 +1876,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- dev_t dev = sbi->sb->s_bdev->bd_dev;
struct f2fs_sm_info *sm_info;
int err;
@@ -1860,14 +1903,10 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
sm_info->nr_discards = 0;
sm_info->max_discards = 0;
- if (test_opt(sbi, FLUSH_MERGE)) {
- spin_lock_init(&sm_info->issue_lock);
- init_waitqueue_head(&sm_info->flush_wait_queue);
-
- sm_info->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
- "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
- if (IS_ERR(sm_info->f2fs_issue_flush))
- return PTR_ERR(sm_info->f2fs_issue_flush);
+ if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+ err = create_flush_cmd_control(sbi);
+ if (err)
+ return err;
}
err = build_sit_info(sbi);
@@ -1976,10 +2015,10 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
void destroy_segment_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_sm_info *sm_info = SM_I(sbi);
+
if (!sm_info)
return;
- if (sm_info->f2fs_issue_flush)
- kthread_stop(sm_info->f2fs_issue_flush);
+ destroy_flush_cmd_control(sbi);
destroy_dirty_segmap(sbi);
destroy_curseg(sbi);
destroy_free_segmap(sbi);
@@ -1994,17 +2033,10 @@ int __init create_segment_manager_caches(void)
sizeof(struct discard_entry));
if (!discard_entry_slab)
return -ENOMEM;
- flush_cmd_slab = f2fs_kmem_cache_create("flush_command",
- sizeof(struct flush_cmd));
- if (!flush_cmd_slab) {
- kmem_cache_destroy(discard_entry_slab);
- return -ENOMEM;
- }
return 0;
}
void destroy_segment_manager_caches(void)
{
kmem_cache_destroy(discard_entry_slab);
- kmem_cache_destroy(flush_cmd_slab);
}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index c756923a7302..b2b18637cb9e 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -514,7 +514,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
- if (!(root->d_sb->s_flags & MS_RDONLY) && test_opt(sbi, BG_GC))
+ if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC))
seq_printf(seq, ",background_gc=%s", "on");
else
seq_printf(seq, ",background_gc=%s", "off");
@@ -542,7 +542,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",disable_ext_identify");
if (test_opt(sbi, INLINE_DATA))
seq_puts(seq, ",inline_data");
- if (test_opt(sbi, FLUSH_MERGE))
+ if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
seq_puts(seq, ",flush_merge");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
@@ -594,6 +594,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct f2fs_mount_info org_mount_opt;
int err, active_logs;
+ bool need_restart_gc = false;
+ bool need_stop_gc = false;
sync_filesystem(sb);
@@ -611,7 +613,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
/*
* Previous and new state of filesystem is RO,
- * so no point in checking GC conditions.
+ * so skip checking GC and FLUSH_MERGE conditions.
*/
if ((sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY))
goto skip;
@@ -625,18 +627,40 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
if (sbi->gc_thread) {
stop_gc_thread(sbi);
f2fs_sync_fs(sb, 1);
+ need_restart_gc = true;
}
} else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
err = start_gc_thread(sbi);
if (err)
goto restore_opts;
+ need_stop_gc = true;
+ }
+
+ /*
+ * We stop issue flush thread if FS is mounted as RO
+ * or if flush_merge is not passed in mount option.
+ */
+ if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
+ destroy_flush_cmd_control(sbi);
+ } else if (test_opt(sbi, FLUSH_MERGE) &&
+ !sbi->sm_info->cmd_control_info) {
+ err = create_flush_cmd_control(sbi);
+ if (err)
+ goto restore_gc;
}
skip:
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
return 0;
-
+restore_gc:
+ if (need_restart_gc) {
+ if (start_gc_thread(sbi))
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "background gc thread is stop");
+ } else if (need_stop_gc) {
+ stop_gc_thread(sbi);
+ }
restore_opts:
sbi->mount_opt = org_mount_opt;
sbi->active_logs = active_logs;
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 503c2451131e..8bea941ee309 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -26,7 +26,7 @@
#include "xattr.h"
static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
- size_t list_size, const char *name, size_t name_len, int type)
+ size_t list_size, const char *name, size_t len, int type)
{
struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
int total_len, prefix_len = 0;
@@ -53,11 +53,11 @@ static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
return -EINVAL;
}
- total_len = prefix_len + name_len + 1;
+ total_len = prefix_len + len + 1;
if (list && total_len <= list_size) {
memcpy(list, prefix, prefix_len);
- memcpy(list + prefix_len, name, name_len);
- list[prefix_len + name_len] = '\0';
+ memcpy(list + prefix_len, name, len);
+ list[prefix_len + len] = '\0';
}
return total_len;
}
@@ -108,11 +108,12 @@ static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
if (strcmp(name, "") == 0)
return -EINVAL;
- return f2fs_setxattr(dentry->d_inode, type, name, value, size, NULL);
+ return f2fs_setxattr(dentry->d_inode, type, name,
+ value, size, NULL, flags);
}
static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
- size_t list_size, const char *name, size_t name_len, int type)
+ size_t list_size, const char *name, size_t len, int type)
{
const char *xname = F2FS_SYSTEM_ADVISE_PREFIX;
size_t size;
@@ -155,9 +156,6 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
}
#ifdef CONFIG_F2FS_FS_SECURITY
-static int __f2fs_setxattr(struct inode *inode, int name_index,
- const char *name, const void *value, size_t value_len,
- struct page *ipage);
static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
void *page)
{
@@ -165,9 +163,9 @@ static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
int err = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
- err = __f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
+ err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
xattr->name, xattr->value,
- xattr->value_len, (struct page *)page);
+ xattr->value_len, (struct page *)page, 0);
if (err < 0)
break;
}
@@ -241,26 +239,26 @@ const struct xattr_handler *f2fs_xattr_handlers[] = {
NULL,
};
-static inline const struct xattr_handler *f2fs_xattr_handler(int name_index)
+static inline const struct xattr_handler *f2fs_xattr_handler(int index)
{
const struct xattr_handler *handler = NULL;
- if (name_index > 0 && name_index < ARRAY_SIZE(f2fs_xattr_handler_map))
- handler = f2fs_xattr_handler_map[name_index];
+ if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
+ handler = f2fs_xattr_handler_map[index];
return handler;
}
-static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index,
- size_t name_len, const char *name)
+static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
+ size_t len, const char *name)
{
struct f2fs_xattr_entry *entry;
list_for_each_xattr(entry, base_addr) {
- if (entry->e_name_index != name_index)
+ if (entry->e_name_index != index)
continue;
- if (entry->e_name_len != name_len)
+ if (entry->e_name_len != len)
continue;
- if (!memcmp(entry->e_name, name, name_len))
+ if (!memcmp(entry->e_name, name, len))
break;
}
return entry;
@@ -347,6 +345,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
if (ipage) {
inline_addr = inline_xattr_addr(ipage);
+ f2fs_wait_on_page_writeback(ipage, NODE);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
@@ -354,6 +353,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
return PTR_ERR(page);
}
inline_addr = inline_xattr_addr(page);
+ f2fs_wait_on_page_writeback(page, NODE);
}
memcpy(inline_addr, txattr_addr, inline_size);
f2fs_put_page(page, 1);
@@ -374,6 +374,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
return PTR_ERR(xpage);
}
f2fs_bug_on(new_nid);
+ f2fs_wait_on_page_writeback(xpage, NODE);
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
@@ -396,42 +397,43 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
return 0;
}
-int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
+int f2fs_getxattr(struct inode *inode, int index, const char *name,
void *buffer, size_t buffer_size)
{
struct f2fs_xattr_entry *entry;
void *base_addr;
int error = 0;
- size_t value_len, name_len;
+ size_t size, len;
if (name == NULL)
return -EINVAL;
- name_len = strlen(name);
- if (name_len > F2FS_NAME_LEN)
+
+ len = strlen(name);
+ if (len > F2FS_NAME_LEN)
return -ERANGE;
base_addr = read_all_xattrs(inode, NULL);
if (!base_addr)
return -ENOMEM;
- entry = __find_xattr(base_addr, name_index, name_len, name);
+ entry = __find_xattr(base_addr, index, len, name);
if (IS_XATTR_LAST_ENTRY(entry)) {
error = -ENODATA;
goto cleanup;
}
- value_len = le16_to_cpu(entry->e_value_size);
+ size = le16_to_cpu(entry->e_value_size);
- if (buffer && value_len > buffer_size) {
+ if (buffer && size > buffer_size) {
error = -ERANGE;
goto cleanup;
}
if (buffer) {
char *pval = entry->e_name + entry->e_name_len;
- memcpy(buffer, pval, value_len);
+ memcpy(buffer, pval, size);
}
- error = value_len;
+ error = size;
cleanup:
kzfree(base_addr);
@@ -475,15 +477,15 @@ cleanup:
return error;
}
-static int __f2fs_setxattr(struct inode *inode, int name_index,
- const char *name, const void *value, size_t value_len,
- struct page *ipage)
+static int __f2fs_setxattr(struct inode *inode, int index,
+ const char *name, const void *value, size_t size,
+ struct page *ipage, int flags)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_xattr_entry *here, *last;
void *base_addr;
int found, newsize;
- size_t name_len;
+ size_t len;
__u32 new_hsize;
int error = -ENOMEM;
@@ -491,11 +493,11 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
return -EINVAL;
if (value == NULL)
- value_len = 0;
+ size = 0;
- name_len = strlen(name);
+ len = strlen(name);
- if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode))
+ if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode))
return -ERANGE;
base_addr = read_all_xattrs(inode, ipage);
@@ -503,16 +505,23 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
goto exit;
/* find entry with wanted name. */
- here = __find_xattr(base_addr, name_index, name_len, name);
+ here = __find_xattr(base_addr, index, len, name);
found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
- last = here;
+ if ((flags & XATTR_REPLACE) && !found) {
+ error = -ENODATA;
+ goto exit;
+ } else if ((flags & XATTR_CREATE) && found) {
+ error = -EEXIST;
+ goto exit;
+ }
+
+ last = here;
while (!IS_XATTR_LAST_ENTRY(last))
last = XATTR_NEXT_ENTRY(last);
- newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) +
- name_len + value_len);
+ newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
/* 1. Check space */
if (value) {
@@ -555,12 +564,12 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
* We just write new entry.
*/
memset(last, 0, newsize);
- last->e_name_index = name_index;
- last->e_name_len = name_len;
- memcpy(last->e_name, name, name_len);
- pval = last->e_name + name_len;
- memcpy(pval, value, value_len);
- last->e_value_size = cpu_to_le16(value_len);
+ last->e_name_index = index;
+ last->e_name_len = len;
+ memcpy(last->e_name, name, len);
+ pval = last->e_name + len;
+ memcpy(pval, value, size);
+ last->e_value_size = cpu_to_le16(size);
new_hsize += newsize;
}
@@ -583,18 +592,23 @@ exit:
return error;
}
-int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
- const void *value, size_t value_len, struct page *ipage)
+int f2fs_setxattr(struct inode *inode, int index, const char *name,
+ const void *value, size_t size,
+ struct page *ipage, int flags)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
int err;
+ /* this case is only from init_inode_metadata */
+ if (ipage)
+ return __f2fs_setxattr(inode, index, name, value,
+ size, ipage, flags);
f2fs_balance_fs(sbi);
f2fs_lock_op(sbi);
/* protect xattr_ver */
down_write(&F2FS_I(inode)->i_sem);
- err = __f2fs_setxattr(inode, name_index, name, value, value_len, ipage);
+ err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
up_write(&F2FS_I(inode)->i_sem);
f2fs_unlock_op(sbi);
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index b21d9ebdeff3..34ab7dbcf5e3 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -114,18 +114,18 @@ extern const struct xattr_handler f2fs_xattr_security_handler;
extern const struct xattr_handler *f2fs_xattr_handlers[];
extern int f2fs_setxattr(struct inode *, int, const char *,
- const void *, size_t, struct page *);
+ const void *, size_t, struct page *, int);
extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t);
extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
#else
#define f2fs_xattr_handlers NULL
-static inline int f2fs_setxattr(struct inode *inode, int name_index,
- const char *name, const void *value, size_t value_len)
+static inline int f2fs_setxattr(struct inode *inode, int index,
+ const char *name, const void *value, size_t size, int flags)
{
return -EOPNOTSUPP;
}
-static inline int f2fs_getxattr(struct inode *inode, int name_index,
+static inline int f2fs_getxattr(struct inode *inode, int index,
const char *name, void *buffer, size_t buffer_size)
{
return -EOPNOTSUPP;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 7c31f4bc74a9..e0c4ba39a377 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -52,7 +52,8 @@ struct fat_mount_options {
usefree:1, /* Use free_clusters for FAT32 */
tz_set:1, /* Filesystem timestamps' offset set */
rodir:1, /* allow ATTR_RO for directory */
- discard:1; /* Issue discard requests on deletions */
+ discard:1, /* Issue discard requests on deletions */
+ dos1xfloppy:1; /* Assume default BPB for DOS 1.x floppies */
};
#define FAT_HASH_BITS 8
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index b3361fe2bcb5..9c83594d7fb5 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -35,9 +35,71 @@
#define CONFIG_FAT_DEFAULT_IOCHARSET ""
#endif
+#define KB_IN_SECTORS 2
+
+/*
+ * A deserialized copy of the on-disk structure laid out in struct
+ * fat_boot_sector.
+ */
+struct fat_bios_param_block {
+ u16 fat_sector_size;
+ u8 fat_sec_per_clus;
+ u16 fat_reserved;
+ u8 fat_fats;
+ u16 fat_dir_entries;
+ u16 fat_sectors;
+ u16 fat_fat_length;
+ u32 fat_total_sect;
+
+ u8 fat16_state;
+ u32 fat16_vol_id;
+
+ u32 fat32_length;
+ u32 fat32_root_cluster;
+ u16 fat32_info_sector;
+ u8 fat32_state;
+ u32 fat32_vol_id;
+};
+
static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE;
static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET;
+static struct fat_floppy_defaults {
+ unsigned nr_sectors;
+ unsigned sec_per_clus;
+ unsigned dir_entries;
+ unsigned media;
+ unsigned fat_length;
+} floppy_defaults[] = {
+{
+ .nr_sectors = 160 * KB_IN_SECTORS,
+ .sec_per_clus = 1,
+ .dir_entries = 64,
+ .media = 0xFE,
+ .fat_length = 1,
+},
+{
+ .nr_sectors = 180 * KB_IN_SECTORS,
+ .sec_per_clus = 1,
+ .dir_entries = 64,
+ .media = 0xFC,
+ .fat_length = 2,
+},
+{
+ .nr_sectors = 320 * KB_IN_SECTORS,
+ .sec_per_clus = 2,
+ .dir_entries = 112,
+ .media = 0xFF,
+ .fat_length = 1,
+},
+{
+ .nr_sectors = 360 * KB_IN_SECTORS,
+ .sec_per_clus = 2,
+ .dir_entries = 112,
+ .media = 0xFD,
+ .fat_length = 2,
+},
+};
static int fat_add_cluster(struct inode *inode)
{
@@ -359,7 +421,7 @@ struct inode *fat_iget(struct super_block *sb, loff_t i_pos)
static int is_exec(unsigned char *extension)
{
- unsigned char *exe_extensions = "EXECOMBAT", *walk;
+ unsigned char exe_extensions[] = "EXECOMBAT", *walk;
for (walk = exe_extensions; *walk; walk += 3)
if (!strncmp(extension, walk, 3))
@@ -853,6 +915,8 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",nfs=stale_rw");
if (opts->discard)
seq_puts(m, ",discard");
+ if (opts->dos1xfloppy)
+ seq_puts(m, ",dos1xfloppy");
return 0;
}
@@ -867,7 +931,7 @@ enum {
Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont,
Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset,
- Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err,
+ Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, Opt_dos1xfloppy,
};
static const match_table_t fat_tokens = {
@@ -900,6 +964,7 @@ static const match_table_t fat_tokens = {
{Opt_nfs_stale_rw, "nfs"},
{Opt_nfs_stale_rw, "nfs=stale_rw"},
{Opt_nfs_nostale_ro, "nfs=nostale_ro"},
+ {Opt_dos1xfloppy, "dos1xfloppy"},
{Opt_obsolete, "conv=binary"},
{Opt_obsolete, "conv=text"},
{Opt_obsolete, "conv=auto"},
@@ -1102,6 +1167,9 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
case Opt_nfs_nostale_ro:
opts->nfs = FAT_NFS_NOSTALE_RO;
break;
+ case Opt_dos1xfloppy:
+ opts->dos1xfloppy = 1;
+ break;
/* msdos specific */
case Opt_dots:
@@ -1247,6 +1315,169 @@ static unsigned long calc_fat_clusters(struct super_block *sb)
return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
}
+static bool fat_bpb_is_zero(struct fat_boot_sector *b)
+{
+ if (get_unaligned_le16(&b->sector_size))
+ return false;
+ if (b->sec_per_clus)
+ return false;
+ if (b->reserved)
+ return false;
+ if (b->fats)
+ return false;
+ if (get_unaligned_le16(&b->dir_entries))
+ return false;
+ if (get_unaligned_le16(&b->sectors))
+ return false;
+ if (b->media)
+ return false;
+ if (b->fat_length)
+ return false;
+ if (b->secs_track)
+ return false;
+ if (b->heads)
+ return false;
+ return true;
+}
+
+static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b,
+ int silent, struct fat_bios_param_block *bpb)
+{
+ int error = -EINVAL;
+
+ /* Read in BPB ... */
+ memset(bpb, 0, sizeof(*bpb));
+ bpb->fat_sector_size = get_unaligned_le16(&b->sector_size);
+ bpb->fat_sec_per_clus = b->sec_per_clus;
+ bpb->fat_reserved = le16_to_cpu(b->reserved);
+ bpb->fat_fats = b->fats;
+ bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries);
+ bpb->fat_sectors = get_unaligned_le16(&b->sectors);
+ bpb->fat_fat_length = le16_to_cpu(b->fat_length);
+ bpb->fat_total_sect = le32_to_cpu(b->total_sect);
+
+ bpb->fat16_state = b->fat16.state;
+ bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id);
+
+ bpb->fat32_length = le32_to_cpu(b->fat32.length);
+ bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster);
+ bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector);
+ bpb->fat32_state = b->fat32.state;
+ bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id);
+
+ /* Validate this looks like a FAT filesystem BPB */
+ if (!bpb->fat_reserved) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR,
+ "bogus number of reserved sectors");
+ goto out;
+ }
+ if (!bpb->fat_fats) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "bogus number of FAT structure");
+ goto out;
+ }
+
+ /*
+ * Earlier we checked here that b->secs_track and b->head are nonzero,
+ * but it turns out valid FAT filesystems can have zero there.
+ */
+
+ if (!fat_valid_media(b->media)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)",
+ (unsigned)b->media);
+ goto out;
+ }
+
+ if (!is_power_of_2(bpb->fat_sector_size)
+ || (bpb->fat_sector_size < 512)
+ || (bpb->fat_sector_size > 4096)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "bogus logical sector size %u",
+ (unsigned)bpb->fat_sector_size);
+ goto out;
+ }
+
+ if (!is_power_of_2(bpb->fat_sec_per_clus)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u",
+ (unsigned)bpb->fat_sec_per_clus);
+ goto out;
+ }
+
+ error = 0;
+
+out:
+ return error;
+}
+
+static int fat_read_static_bpb(struct super_block *sb,
+ struct fat_boot_sector *b, int silent,
+ struct fat_bios_param_block *bpb)
+{
+ static const char *notdos1x = "This doesn't look like a DOS 1.x volume";
+
+ struct fat_floppy_defaults *fdefaults = NULL;
+ int error = -EINVAL;
+ sector_t bd_sects;
+ unsigned i;
+
+ bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE;
+
+ /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */
+ if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR,
+ "%s; no bootstrapping code", notdos1x);
+ goto out;
+ }
+
+ /*
+ * If any value in this region is non-zero, it isn't archaic
+ * DOS.
+ */
+ if (!fat_bpb_is_zero(b)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR,
+ "%s; DOS 2.x BPB is non-zero", notdos1x);
+ goto out;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) {
+ if (floppy_defaults[i].nr_sectors == bd_sects) {
+ fdefaults = &floppy_defaults[i];
+ break;
+ }
+ }
+
+ if (fdefaults == NULL) {
+ if (!silent)
+ fat_msg(sb, KERN_WARNING,
+ "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)",
+ (u64)bd_sects);
+ goto out;
+ }
+
+ if (!silent)
+ fat_msg(sb, KERN_INFO,
+ "This looks like a DOS 1.x volume; assuming default BPB values");
+
+ memset(bpb, 0, sizeof(*bpb));
+ bpb->fat_sector_size = SECTOR_SIZE;
+ bpb->fat_sec_per_clus = fdefaults->sec_per_clus;
+ bpb->fat_reserved = 1;
+ bpb->fat_fats = 2;
+ bpb->fat_dir_entries = fdefaults->dir_entries;
+ bpb->fat_sectors = fdefaults->nr_sectors;
+ bpb->fat_fat_length = fdefaults->fat_length;
+
+ error = 0;
+
+out:
+ return error;
+}
+
/*
* Read the super block of an MS-DOS FS.
*/
@@ -1256,12 +1487,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
struct inode *root_inode = NULL, *fat_inode = NULL;
struct inode *fsinfo_inode = NULL;
struct buffer_head *bh;
- struct fat_boot_sector *b;
+ struct fat_bios_param_block bpb;
struct msdos_sb_info *sbi;
u16 logical_sector_size;
u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors;
int debug;
- unsigned int media;
long error;
char buf[50];
@@ -1298,100 +1528,72 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
goto out_fail;
}
- b = (struct fat_boot_sector *) bh->b_data;
- if (!b->reserved) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus number of reserved sectors");
- brelse(bh);
- goto out_invalid;
- }
- if (!b->fats) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus number of FAT structure");
- brelse(bh);
- goto out_invalid;
- }
-
- /*
- * Earlier we checked here that b->secs_track and b->head are nonzero,
- * but it turns out valid FAT filesystems can have zero there.
- */
+ error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent,
+ &bpb);
+ if (error == -EINVAL && sbi->options.dos1xfloppy)
+ error = fat_read_static_bpb(sb,
+ (struct fat_boot_sector *)bh->b_data, silent, &bpb);
+ brelse(bh);
- media = b->media;
- if (!fat_valid_media(media)) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)",
- media);
- brelse(bh);
- goto out_invalid;
- }
- logical_sector_size = get_unaligned_le16(&b->sector_size);
- if (!is_power_of_2(logical_sector_size)
- || (logical_sector_size < 512)
- || (logical_sector_size > 4096)) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus logical sector size %u",
- logical_sector_size);
- brelse(bh);
- goto out_invalid;
- }
- sbi->sec_per_clus = b->sec_per_clus;
- if (!is_power_of_2(sbi->sec_per_clus)) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u",
- sbi->sec_per_clus);
- brelse(bh);
+ if (error == -EINVAL)
goto out_invalid;
- }
+ else if (error)
+ goto out_fail;
+
+ logical_sector_size = bpb.fat_sector_size;
+ sbi->sec_per_clus = bpb.fat_sec_per_clus;
+ error = -EIO;
if (logical_sector_size < sb->s_blocksize) {
fat_msg(sb, KERN_ERR, "logical sector size too small for device"
" (logical sector size = %u)", logical_sector_size);
- brelse(bh);
goto out_fail;
}
+
if (logical_sector_size > sb->s_blocksize) {
- brelse(bh);
+ struct buffer_head *bh_resize;
if (!sb_set_blocksize(sb, logical_sector_size)) {
fat_msg(sb, KERN_ERR, "unable to set blocksize %u",
logical_sector_size);
goto out_fail;
}
- bh = sb_bread(sb, 0);
- if (bh == NULL) {
+
+ /* Verify that the larger boot sector is fully readable */
+ bh_resize = sb_bread(sb, 0);
+ if (bh_resize == NULL) {
fat_msg(sb, KERN_ERR, "unable to read boot sector"
" (logical sector size = %lu)",
sb->s_blocksize);
goto out_fail;
}
- b = (struct fat_boot_sector *) bh->b_data;
+ brelse(bh_resize);
}
mutex_init(&sbi->s_lock);
sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus;
sbi->cluster_bits = ffs(sbi->cluster_size) - 1;
- sbi->fats = b->fats;
+ sbi->fats = bpb.fat_fats;
sbi->fat_bits = 0; /* Don't know yet */
- sbi->fat_start = le16_to_cpu(b->reserved);
- sbi->fat_length = le16_to_cpu(b->fat_length);
+ sbi->fat_start = bpb.fat_reserved;
+ sbi->fat_length = bpb.fat_fat_length;
sbi->root_cluster = 0;
sbi->free_clusters = -1; /* Don't know yet */
sbi->free_clus_valid = 0;
sbi->prev_free = FAT_START_ENT;
sb->s_maxbytes = 0xffffffff;
- if (!sbi->fat_length && b->fat32.length) {
+ if (!sbi->fat_length && bpb.fat32_length) {
struct fat_boot_fsinfo *fsinfo;
struct buffer_head *fsinfo_bh;
/* Must be FAT32 */
sbi->fat_bits = 32;
- sbi->fat_length = le32_to_cpu(b->fat32.length);
- sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster);
+ sbi->fat_length = bpb.fat32_length;
+ sbi->root_cluster = bpb.fat32_root_cluster;
/* MC - if info_sector is 0, don't multiply by 0 */
- sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector);
+ sbi->fsinfo_sector = bpb.fat32_info_sector;
if (sbi->fsinfo_sector == 0)
sbi->fsinfo_sector = 1;
@@ -1399,7 +1601,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
if (fsinfo_bh == NULL) {
fat_msg(sb, KERN_ERR, "bread failed, FSINFO block"
" (sector = %lu)", sbi->fsinfo_sector);
- brelse(bh);
goto out_fail;
}
@@ -1422,35 +1623,28 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
/* interpret volume ID as a little endian 32 bit integer */
if (sbi->fat_bits == 32)
- sbi->vol_id = (((u32)b->fat32.vol_id[0]) |
- ((u32)b->fat32.vol_id[1] << 8) |
- ((u32)b->fat32.vol_id[2] << 16) |
- ((u32)b->fat32.vol_id[3] << 24));
+ sbi->vol_id = bpb.fat32_vol_id;
else /* fat 16 or 12 */
- sbi->vol_id = (((u32)b->fat16.vol_id[0]) |
- ((u32)b->fat16.vol_id[1] << 8) |
- ((u32)b->fat16.vol_id[2] << 16) |
- ((u32)b->fat16.vol_id[3] << 24));
+ sbi->vol_id = bpb.fat16_vol_id;
sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length;
- sbi->dir_entries = get_unaligned_le16(&b->dir_entries);
+ sbi->dir_entries = bpb.fat_dir_entries;
if (sbi->dir_entries & (sbi->dir_per_block - 1)) {
if (!silent)
fat_msg(sb, KERN_ERR, "bogus directory-entries per block"
" (%u)", sbi->dir_entries);
- brelse(bh);
goto out_invalid;
}
rootdir_sectors = sbi->dir_entries
* sizeof(struct msdos_dir_entry) / sb->s_blocksize;
sbi->data_start = sbi->dir_start + rootdir_sectors;
- total_sectors = get_unaligned_le16(&b->sectors);
+ total_sectors = bpb.fat_sectors;
if (total_sectors == 0)
- total_sectors = le32_to_cpu(b->total_sect);
+ total_sectors = bpb.fat_total_sect;
total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus;
@@ -1459,9 +1653,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
/* some OSes set FAT_STATE_DIRTY and clean it on unmount. */
if (sbi->fat_bits == 32)
- sbi->dirty = b->fat32.state & FAT_STATE_DIRTY;
+ sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY;
else /* fat 16 or 12 */
- sbi->dirty = b->fat16.state & FAT_STATE_DIRTY;
+ sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY;
/* check that FAT table does not overflow */
fat_clusters = calc_fat_clusters(sb);
@@ -1470,7 +1664,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
if (!silent)
fat_msg(sb, KERN_ERR, "count of clusters too big (%u)",
total_clusters);
- brelse(bh);
goto out_invalid;
}
@@ -1483,8 +1676,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
if (sbi->prev_free < FAT_START_ENT)
sbi->prev_free = FAT_START_ENT;
- brelse(bh);
-
/* set up enough so that it can read an inode */
fat_hash_init(sb);
dir_hash_init(sb);
diff --git a/fs/file_table.c b/fs/file_table.c
index a374f5033e97..40bf4660f0a3 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -76,14 +76,14 @@ EXPORT_SYMBOL_GPL(get_max_files);
* Handle nr_files sysctl
*/
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-int proc_nr_files(ctl_table *table, int write,
+int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#else
-int proc_nr_files(ctl_table *table, int write,
+int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
index f7cff367db7f..56cce7fdd39e 100644
--- a/fs/fscache/cache.c
+++ b/fs/fscache/cache.c
@@ -280,15 +280,15 @@ int fscache_add_cache(struct fscache_cache *cache,
spin_unlock(&fscache_fsdef_index.lock);
up_write(&fscache_addremove_sem);
- printk(KERN_NOTICE "FS-Cache: Cache \"%s\" added (type %s)\n",
- cache->tag->name, cache->ops->name);
+ pr_notice("Cache \"%s\" added (type %s)\n",
+ cache->tag->name, cache->ops->name);
kobject_uevent(cache->kobj, KOBJ_ADD);
_leave(" = 0 [%s]", cache->identifier);
return 0;
tag_in_use:
- printk(KERN_ERR "FS-Cache: Cache tag '%s' already in use\n", tagname);
+ pr_err("Cache tag '%s' already in use\n", tagname);
__fscache_release_cache_tag(tag);
_leave(" = -EXIST");
return -EEXIST;
@@ -317,8 +317,7 @@ EXPORT_SYMBOL(fscache_add_cache);
void fscache_io_error(struct fscache_cache *cache)
{
if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags))
- printk(KERN_ERR "FS-Cache:"
- " Cache '%s' stopped due to I/O error\n",
+ pr_err("Cache '%s' stopped due to I/O error\n",
cache->ops->name);
}
EXPORT_SYMBOL(fscache_io_error);
@@ -369,8 +368,8 @@ void fscache_withdraw_cache(struct fscache_cache *cache)
_enter("");
- printk(KERN_NOTICE "FS-Cache: Withdrawing cache \"%s\"\n",
- cache->tag->name);
+ pr_notice("Withdrawing cache \"%s\"\n",
+ cache->tag->name);
/* make the cache unavailable for cookie acquisition */
if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags))
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 29d7feb62cf7..aec01be91b0a 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -519,7 +519,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
ASSERTCMP(atomic_read(&cookie->n_active), >, 0);
if (atomic_read(&cookie->n_children) != 0) {
- printk(KERN_ERR "FS-Cache: Cookie '%s' still has children\n",
+ pr_err("Cookie '%s' still has children\n",
cookie->def->name);
BUG();
}
diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c
index bad496748a59..7d637e2335fd 100644
--- a/fs/fscache/histogram.c
+++ b/fs/fscache/histogram.c
@@ -31,12 +31,10 @@ static int fscache_histogram_show(struct seq_file *m, void *v)
switch ((unsigned long) v) {
case 1:
- seq_puts(m, "JIFS SECS OBJ INST OP RUNS OBJ RUNS "
- " RETRV DLY RETRIEVLS\n");
+ seq_puts(m, "JIFS SECS OBJ INST OP RUNS OBJ RUNS RETRV DLY RETRIEVLS\n");
return 0;
case 2:
- seq_puts(m, "===== ===== ========= ========= ========="
- " ========= =========\n");
+ seq_puts(m, "===== ===== ========= ========= ========= ========= =========\n");
return 0;
default:
index = (unsigned long) v - 3;
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 4226f6680b06..bc6c08fcfddd 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -22,6 +22,12 @@
*
*/
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) "FS-Cache: " fmt
+
#include <linux/fscache-cache.h>
#include <linux/sched.h>
@@ -413,8 +419,8 @@ do { \
#define ASSERT(X) \
do { \
if (unlikely(!(X))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "FS-Cache: Assertion failed\n"); \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
BUG(); \
} \
} while (0)
@@ -422,9 +428,9 @@ do { \
#define ASSERTCMP(X, OP, Y) \
do { \
if (unlikely(!((X) OP (Y)))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "FS-Cache: Assertion failed\n"); \
- printk(KERN_ERR "%lx " #OP " %lx is false\n", \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
+ pr_err("%lx " #OP " %lx is false\n", \
(unsigned long)(X), (unsigned long)(Y)); \
BUG(); \
} \
@@ -433,8 +439,8 @@ do { \
#define ASSERTIF(C, X) \
do { \
if (unlikely((C) && !(X))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "FS-Cache: Assertion failed\n"); \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
BUG(); \
} \
} while (0)
@@ -442,9 +448,9 @@ do { \
#define ASSERTIFCMP(C, X, OP, Y) \
do { \
if (unlikely((C) && !((X) OP (Y)))) { \
- printk(KERN_ERR "\n"); \
- printk(KERN_ERR "FS-Cache: Assertion failed\n"); \
- printk(KERN_ERR "%lx " #OP " %lx is false\n", \
+ pr_err("\n"); \
+ pr_err("Assertion failed\n"); \
+ pr_err("%lx " #OP " %lx is false\n", \
(unsigned long)(X), (unsigned long)(Y)); \
BUG(); \
} \
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
index 7c27907e650c..63f868e869b9 100644
--- a/fs/fscache/main.c
+++ b/fs/fscache/main.c
@@ -67,7 +67,7 @@ static int fscache_max_active_sysctl(struct ctl_table *table, int write,
return ret;
}
-ctl_table fscache_sysctls[] = {
+struct ctl_table fscache_sysctls[] = {
{
.procname = "object_max_active",
.data = &fscache_object_max_active,
@@ -87,7 +87,7 @@ ctl_table fscache_sysctls[] = {
{}
};
-ctl_table fscache_sysctls_root[] = {
+struct ctl_table fscache_sysctls_root[] = {
{
.procname = "fscache",
.mode = 0555,
@@ -146,8 +146,7 @@ static int __init fscache_init(void)
0,
fscache_cookie_init_once);
if (!fscache_cookie_jar) {
- printk(KERN_NOTICE
- "FS-Cache: Failed to allocate a cookie jar\n");
+ pr_notice("Failed to allocate a cookie jar\n");
ret = -ENOMEM;
goto error_cookie_jar;
}
@@ -156,7 +155,7 @@ static int __init fscache_init(void)
if (!fscache_root)
goto error_kobj;
- printk(KERN_NOTICE "FS-Cache: Loaded\n");
+ pr_notice("Loaded\n");
return 0;
error_kobj:
@@ -192,7 +191,7 @@ static void __exit fscache_exit(void)
fscache_proc_cleanup();
destroy_workqueue(fscache_op_wq);
destroy_workqueue(fscache_object_wq);
- printk(KERN_NOTICE "FS-Cache: Unloaded\n");
+ pr_notice("Unloaded\n");
}
module_exit(fscache_exit);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 989f39401547..6d941f56faf4 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -65,8 +65,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
list_add(&netfs->link, &fscache_netfs_list);
ret = 0;
- printk(KERN_NOTICE "FS-Cache: Netfs '%s' registered for caching\n",
- netfs->name);
+ pr_notice("Netfs '%s' registered for caching\n", netfs->name);
already_registered:
up_write(&fscache_addremove_sem);
@@ -97,8 +96,8 @@ void __fscache_unregister_netfs(struct fscache_netfs *netfs)
up_write(&fscache_addremove_sem);
- printk(KERN_NOTICE "FS-Cache: Netfs '%s' unregistered from caching\n",
- netfs->name);
+ pr_notice("Netfs '%s' unregistered from caching\n",
+ netfs->name);
_leave("");
}
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index b5ebc2d7d80d..b8179ca6bf9d 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -285,20 +285,20 @@ static int fscache_objlist_show(struct seq_file *m, void *v)
fscache_unuse_cookie(obj);
if (keylen > 0 || auxlen > 0) {
- seq_printf(m, " ");
+ seq_puts(m, " ");
for (p = buf; keylen > 0; keylen--)
seq_printf(m, "%02x", *p++);
if (auxlen > 0) {
if (config & FSCACHE_OBJLIST_CONFIG_KEY)
- seq_printf(m, ", ");
+ seq_puts(m, ", ");
for (; auxlen > 0; auxlen--)
seq_printf(m, "%02x", *p++);
}
}
- seq_printf(m, "\n");
+ seq_puts(m, "\n");
} else {
- seq_printf(m, "<no_netfs>\n");
+ seq_puts(m, "<no_netfs>\n");
}
return 0;
}
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 318071aca217..e7b87a0e5185 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -51,8 +51,7 @@ void fscache_enqueue_operation(struct fscache_operation *op)
_debug("queue for caller's attention");
break;
default:
- printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
- op->flags);
+ pr_err("Unexpected op type %lx", op->flags);
BUG();
break;
}
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 7f5c658af755..ed70714503fa 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -1108,10 +1108,8 @@ void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page)
static bool once_only;
if (!once_only) {
once_only = true;
- printk(KERN_WARNING "FS-Cache:"
- " Cookie type %s marked page %lx"
- " multiple times\n",
- cookie->def->name, page->index);
+ pr_warn("Cookie type %s marked page %lx multiple times\n",
+ cookie->def->name, page->index);
}
}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index aac71ce373e4..098f97bdcf1b 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1614,7 +1614,7 @@ out_finish:
static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req)
{
- release_pages(req->pages, req->num_pages, 0);
+ release_pages(req->pages, req->num_pages, false);
}
static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 96d513e01a5d..903cbc9cd6bd 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1089,8 +1089,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
flush_dcache_page(page);
- mark_page_accessed(page);
-
if (!tmp) {
unlock_page(page);
page_cache_release(page);
@@ -2304,7 +2302,6 @@ static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl)
struct fuse_file *ff = file->private_data;
/* emulate flock with POSIX locks */
- fl->fl_owner = (fl_owner_t) file;
ff->flock = true;
err = fuse_setlk(file, fl, 1);
}
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index ce62dcac90b6..492123cda64a 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -431,7 +431,7 @@ static int gfs2_jdata_writepages(struct address_space *mapping,
ret = gfs2_write_cache_jdata(mapping, wbc);
if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
- gfs2_log_flush(sdp, ip->i_gl);
+ gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
ret = gfs2_write_cache_jdata(mapping, wbc);
}
return ret;
@@ -577,7 +577,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
p = kmap_atomic(page);
memcpy(buf + copied, p + offset, amt);
kunmap_atomic(p);
- mark_page_accessed(page);
page_cache_release(page);
copied += amt;
index++;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index c62d4b9f51dc..e6ee5b6e8d99 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -707,7 +707,7 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi
* @top: The first pointer in the buffer
* @bottom: One more than the last pointer
* @height: the height this buffer is at
- * @data: a pointer to a struct strip_mine
+ * @sm: a pointer to a struct strip_mine
*
* Returns: errno
*/
@@ -992,6 +992,8 @@ unlock:
return err;
}
+#define GFS2_JTRUNC_REVOKES 8192
+
/**
* gfs2_journaled_truncate - Wrapper for truncate_pagecache for jdata files
* @inode: The inode being truncated
@@ -1003,8 +1005,6 @@ unlock:
* if the number of pages being truncated gets too large.
*/
-#define GFS2_JTRUNC_REVOKES 8192
-
static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize)
{
struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -1348,7 +1348,7 @@ void gfs2_free_journal_extents(struct gfs2_jdesc *jd)
* gfs2_add_jextent - Add or merge a new extent to extent cache
* @jd: The journal descriptor
* @lblock: The logical block at start of new extent
- * @pblock: The physical block at start of new extent
+ * @dblock: The physical block at start of new extent
* @blocks: Size of extent in fs blocks
*
* Returns: 0 on success or -ENOMEM
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 80d67253623c..6ab0cfb2e891 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -203,9 +203,9 @@ void gfs2_set_inode_flags(struct inode *inode)
GFS2_DIF_INHERIT_JDATA)
/**
- * gfs2_set_flags - set flags on an inode
- * @inode: The inode
- * @flags: The flags to set
+ * do_gfs2_set_flags - set flags on an inode
+ * @filp: file pointer
+ * @reqflags: The flags to set
* @mask: Indicates which flags are valid
*
*/
@@ -256,7 +256,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
}
if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
if (flags & GFS2_DIF_JDATA)
- gfs2_log_flush(sdp, ip->i_gl);
+ gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
error = filemap_fdatawrite(inode->i_mapping);
if (error)
goto out;
@@ -318,7 +318,7 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
/**
* gfs2_size_hint - Give a hint to the size of a write request
- * @file: The struct file
+ * @filep: The struct file
* @offset: The file offset of the write
* @size: The length of the write
*
@@ -371,7 +371,7 @@ static int gfs2_allocate_page_backing(struct page *page)
/**
* gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
* @vma: The virtual memory area
- * @page: The page which is about to become writable
+ * @vmf: The virtual memory fault containing the page to become writable
*
* When the page becomes writable, we need to ensure that we have
* blocks allocated on disk to back that page.
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index aec7f73832f0..c355f7320e44 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -277,7 +277,7 @@ static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holde
static void gfs2_holder_wake(struct gfs2_holder *gh)
{
clear_bit(HIF_WAIT, &gh->gh_iflags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&gh->gh_iflags, HIF_WAIT);
}
@@ -411,7 +411,7 @@ static void gfs2_demote_wake(struct gfs2_glock *gl)
{
gl->gl_demote_state = LM_ST_EXCLUSIVE;
clear_bit(GLF_DEMOTE, &gl->gl_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
}
@@ -620,7 +620,7 @@ out:
out_sched:
clear_bit(GLF_LOCK, &gl->gl_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
gl->gl_lockref.count++;
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
gl->gl_lockref.count--;
@@ -628,7 +628,7 @@ out_sched:
out_unlock:
clear_bit(GLF_LOCK, &gl->gl_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
return;
}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 54b66809e818..fc1100781bbc 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -89,18 +89,23 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
if (!tr.tr_revokes)
return;
- /* A shortened, inline version of gfs2_trans_begin() */
+ /* A shortened, inline version of gfs2_trans_begin()
+ * tr->alloced is not set since the transaction structure is
+ * on the stack */
tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
tr.tr_ip = (unsigned long)__builtin_return_address(0);
sb_start_intwrite(sdp->sd_vfs);
- gfs2_log_reserve(sdp, tr.tr_reserved);
+ if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) {
+ sb_end_intwrite(sdp->sd_vfs);
+ return;
+ }
WARN_ON_ONCE(current->journal_info);
current->journal_info = &tr;
__gfs2_ail_flush(gl, 0, tr.tr_revokes);
gfs2_trans_end(sdp);
- gfs2_log_flush(sdp, NULL);
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
@@ -121,7 +126,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
return;
__gfs2_ail_flush(gl, fsync, max_revokes);
gfs2_trans_end(sdp);
- gfs2_log_flush(sdp, NULL);
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
/**
@@ -144,7 +149,7 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
return;
GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
- gfs2_log_flush(sdp, gl);
+ gfs2_log_flush(sdp, gl, NORMAL_FLUSH);
filemap_fdatawrite_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
error = filemap_fdatawait_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
mapping_set_error(mapping, error);
@@ -206,7 +211,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
- gfs2_log_flush(gl->gl_sbd, gl);
+ gfs2_log_flush(gl->gl_sbd, gl, NORMAL_FLUSH);
filemap_fdatawrite(metamapping);
if (ip) {
struct address_space *mapping = ip->i_inode.i_mapping;
@@ -221,7 +226,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
* Writeback of the data mapping may cause the dirty flag to be set
* so we have to clear it again here.
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(GLF_DIRTY, &gl->gl_flags);
}
@@ -253,7 +258,7 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
}
if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) {
- gfs2_log_flush(gl->gl_sbd, NULL);
+ gfs2_log_flush(gl->gl_sbd, NULL, NORMAL_FLUSH);
gl->gl_sbd->sd_rindex_uptodate = 0;
}
if (ip && S_ISREG(ip->i_inode.i_mode))
@@ -455,31 +460,39 @@ static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
}
/**
- * trans_go_sync - promote/demote the transaction glock
+ * freeze_go_sync - promote/demote the freeze glock
* @gl: the glock
* @state: the requested state
* @flags:
*
*/
-static void trans_go_sync(struct gfs2_glock *gl)
+static void freeze_go_sync(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
+ DEFINE_WAIT(wait);
- if (gl->gl_state != LM_ST_UNLOCKED &&
+ if (gl->gl_state == LM_ST_SHARED &&
test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
- gfs2_meta_syncfs(sdp);
- gfs2_log_shutdown(sdp);
+ atomic_set(&sdp->sd_log_freeze, 1);
+ wake_up(&sdp->sd_logd_waitq);
+ do {
+ prepare_to_wait(&sdp->sd_log_frozen_wait, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (atomic_read(&sdp->sd_log_freeze))
+ io_schedule();
+ } while(atomic_read(&sdp->sd_log_freeze));
+ finish_wait(&sdp->sd_log_frozen_wait, &wait);
}
}
/**
- * trans_go_xmote_bh - After promoting/demoting the transaction glock
+ * freeze_go_xmote_bh - After promoting/demoting the freeze glock
* @gl: the glock
*
*/
-static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
+static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
@@ -512,7 +525,7 @@ static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
* Always returns 0
*/
-static int trans_go_demote_ok(const struct gfs2_glock *gl)
+static int freeze_go_demote_ok(const struct gfs2_glock *gl)
{
return 0;
}
@@ -563,10 +576,10 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
.go_flags = GLOF_LVB,
};
-const struct gfs2_glock_operations gfs2_trans_glops = {
- .go_sync = trans_go_sync,
- .go_xmote_bh = trans_go_xmote_bh,
- .go_demote_ok = trans_go_demote_ok,
+const struct gfs2_glock_operations gfs2_freeze_glops = {
+ .go_sync = freeze_go_sync,
+ .go_xmote_bh = freeze_go_xmote_bh,
+ .go_demote_ok = freeze_go_demote_ok,
.go_type = LM_TYPE_NONDISK,
};
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index bf95a2dc1662..7455d2629bcb 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -15,7 +15,7 @@
extern const struct gfs2_glock_operations gfs2_meta_glops;
extern const struct gfs2_glock_operations gfs2_inode_glops;
extern const struct gfs2_glock_operations gfs2_rgrp_glops;
-extern const struct gfs2_glock_operations gfs2_trans_glops;
+extern const struct gfs2_glock_operations gfs2_freeze_glops;
extern const struct gfs2_glock_operations gfs2_iopen_glops;
extern const struct gfs2_glock_operations gfs2_flock_glops;
extern const struct gfs2_glock_operations gfs2_nondisk_glops;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index bdf70c18610c..67d310c9ada3 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -465,9 +465,7 @@ struct gfs2_trans {
unsigned int tr_reserved;
unsigned int tr_touched:1;
unsigned int tr_attached:1;
-
- struct gfs2_holder tr_t_gh;
-
+ unsigned int tr_alloced:1;
unsigned int tr_num_buf_new;
unsigned int tr_num_databuf_new;
@@ -682,7 +680,7 @@ struct gfs2_sbd {
struct lm_lockstruct sd_lockstruct;
struct gfs2_holder sd_live_gh;
struct gfs2_glock *sd_rename_gl;
- struct gfs2_glock *sd_trans_gl;
+ struct gfs2_glock *sd_freeze_gl;
wait_queue_head_t sd_glock_wait;
atomic_t sd_glock_disposal;
struct completion sd_locking_init;
@@ -730,6 +728,8 @@ struct gfs2_sbd {
struct gfs2_holder sd_sc_gh;
struct gfs2_holder sd_qc_gh;
+ struct completion sd_journal_ready;
+
/* Daemon stuff */
struct task_struct *sd_logd_process;
@@ -794,6 +794,12 @@ struct gfs2_sbd {
/* For quiescing the filesystem */
struct gfs2_holder sd_freeze_gh;
+ struct gfs2_holder sd_freeze_root_gh;
+ struct gfs2_holder sd_thaw_gh;
+ atomic_t sd_log_freeze;
+ atomic_t sd_frozen_root;
+ wait_queue_head_t sd_frozen_root_wait;
+ wait_queue_head_t sd_log_frozen_wait;
char sd_fsname[GFS2_FSNAME_LEN];
char sd_table_name[GFS2_FSNAME_LEN];
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 28cc7bf6575a..e62e59477884 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1613,18 +1613,26 @@ int gfs2_permission(struct inode *inode, int mask)
{
struct gfs2_inode *ip;
struct gfs2_holder i_gh;
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
int error;
int unlock = 0;
+ int frozen_root = 0;
ip = GFS2_I(inode);
if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
- if (mask & MAY_NOT_BLOCK)
- return -ECHILD;
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
- if (error)
- return error;
- unlock = 1;
+ if (unlikely(gfs2_glock_is_held_excl(sdp->sd_freeze_gl) &&
+ inode == sdp->sd_root_dir->d_inode &&
+ atomic_inc_not_zero(&sdp->sd_frozen_root)))
+ frozen_root = 1;
+ else {
+ if (mask & MAY_NOT_BLOCK)
+ return -ECHILD;
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+ if (error)
+ return error;
+ unlock = 1;
+ }
}
if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
@@ -1633,6 +1641,8 @@ int gfs2_permission(struct inode *inode, int mask)
error = generic_permission(inode, mask);
if (unlock)
gfs2_glock_dq_uninit(&i_gh);
+ else if (frozen_root && atomic_dec_and_test(&sdp->sd_frozen_root))
+ wake_up(&sdp->sd_frozen_root_wait);
return error;
}
@@ -1805,19 +1815,29 @@ static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct inode *inode = dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
int error;
int unlock = 0;
+ int frozen_root = 0;
if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
- if (error)
- return error;
- unlock = 1;
+ if (unlikely(gfs2_glock_is_held_excl(sdp->sd_freeze_gl) &&
+ inode == sdp->sd_root_dir->d_inode &&
+ atomic_inc_not_zero(&sdp->sd_frozen_root)))
+ frozen_root = 1;
+ else {
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+ if (error)
+ return error;
+ unlock = 1;
+ }
}
generic_fillattr(inode, stat);
if (unlock)
gfs2_glock_dq_uninit(&gh);
+ else if (frozen_root && atomic_dec_and_test(&sdp->sd_frozen_root))
+ wake_up(&sdp->sd_frozen_root_wait);
return 0;
}
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index c1eb555dc588..91f274de1246 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1134,7 +1134,7 @@ static void gdlm_recover_done(void *arg, struct dlm_slot *slots, int num_slots,
queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
clear_bit(DFL_DLM_RECOVERY, &ls->ls_recover_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY);
spin_unlock(&ls->ls_recover_spin);
}
@@ -1271,7 +1271,7 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table)
ls->ls_first = !!test_bit(DFL_FIRST_MOUNT, &ls->ls_recover_flags);
clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
return 0;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 4a14d504ef83..3966fadbcebd 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -301,6 +301,23 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
}
/**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+ atomic_add(blks, &sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, blks);
+ gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+ sdp->sd_jdesc->jd_blocks);
+ up_read(&sdp->sd_log_flush_lock);
+}
+
+/**
* gfs2_log_reserve - Make a log reservation
* @sdp: The GFS2 superblock
* @blks: The number of blocks to reserve
@@ -358,7 +375,10 @@ retry:
wake_up(&sdp->sd_log_waitq);
down_read(&sdp->sd_log_flush_lock);
-
+ if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
+ gfs2_log_release(sdp, blks);
+ return -EROFS;
+ }
return 0;
}
@@ -671,7 +691,8 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
*
*/
-void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+ enum gfs2_flush_type type)
{
struct gfs2_trans *tr;
@@ -723,6 +744,42 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
}
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
+
+ if (atomic_read(&sdp->sd_log_freeze))
+ type = FREEZE_FLUSH;
+ if (type != NORMAL_FLUSH) {
+ if (!sdp->sd_log_idle) {
+ for (;;) {
+ gfs2_ail1_start(sdp);
+ gfs2_ail1_wait(sdp);
+ if (gfs2_ail1_empty(sdp))
+ break;
+ }
+ atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+ trace_gfs2_log_blocks(sdp, -1);
+ sdp->sd_log_flush_wrapped = 0;
+ log_write_header(sdp, 0);
+ sdp->sd_log_head = sdp->sd_log_flush_head;
+ }
+ if (type == SHUTDOWN_FLUSH || type == FREEZE_FLUSH)
+ gfs2_log_shutdown(sdp);
+ if (type == FREEZE_FLUSH) {
+ int error;
+
+ atomic_set(&sdp->sd_log_freeze, 0);
+ wake_up(&sdp->sd_log_frozen_wait);
+ error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
+ LM_ST_SHARED, 0,
+ &sdp->sd_thaw_gh);
+ if (error) {
+ printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error);
+ gfs2_assert_withdraw(sdp, 0);
+ }
+ else
+ gfs2_glock_dq_uninit(&sdp->sd_thaw_gh);
+ }
+ }
+
trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
@@ -761,7 +818,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
if (sdp->sd_log_tr) {
gfs2_merge_trans(sdp->sd_log_tr, tr);
} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
- gfs2_assert_withdraw(sdp, tr->tr_t_gh.gh_gl);
+ gfs2_assert_withdraw(sdp, tr->tr_alloced);
sdp->sd_log_tr = tr;
tr->tr_attached = 1;
}
@@ -813,8 +870,6 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
void gfs2_log_shutdown(struct gfs2_sbd *sdp)
{
- down_write(&sdp->sd_log_flush_lock);
-
gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
@@ -824,38 +879,16 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT);
- gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_tail = sdp->sd_log_head;
-
- up_write(&sdp->sd_log_flush_lock);
-}
-
-
-/**
- * gfs2_meta_syncfs - sync all the buffers in a filesystem
- * @sdp: the filesystem
- *
- */
-
-void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
-{
- gfs2_log_flush(sdp, NULL);
- for (;;) {
- gfs2_ail1_start(sdp);
- gfs2_ail1_wait(sdp);
- if (gfs2_ail1_empty(sdp))
- break;
- }
- gfs2_log_flush(sdp, NULL);
}
static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
{
- return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+ return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1) || atomic_read(&sdp->sd_log_freeze));
}
static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
@@ -882,14 +915,14 @@ int gfs2_logd(void *data)
if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
gfs2_ail1_empty(sdp);
- gfs2_log_flush(sdp, NULL);
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
if (gfs2_ail_flush_reqd(sdp)) {
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
gfs2_ail1_empty(sdp);
- gfs2_log_flush(sdp, NULL);
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
if (!gfs2_ail_flush_reqd(sdp))
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 37216634f0aa..9499a6049212 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -63,14 +63,21 @@ extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
unsigned int ssize);
+extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
-extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
+enum gfs2_flush_type {
+ NORMAL_FLUSH = 0,
+ SYNC_FLUSH,
+ SHUTDOWN_FLUSH,
+ FREEZE_FLUSH
+};
+extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+ enum gfs2_flush_type type);
extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
-extern void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
extern int gfs2_logd(void *data);
extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
extern void gfs2_write_revokes(struct gfs2_sbd *sdp);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index a294d8d8bcd4..2c1ae861dc94 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -75,7 +75,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd)
unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
struct gfs2_bitmap *bi = rgd->rd_bits + index;
- if (bi->bi_clone == 0)
+ if (bi->bi_clone == NULL)
return;
if (sdp->sd_args.ar_discard)
gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 2cf09b63a6b4..b984a6e190bc 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -136,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
yield();
}
} else {
- page = find_lock_page(mapping, index);
+ page = find_get_page_flags(mapping, index,
+ FGP_LOCK|FGP_ACCESSED);
if (!page)
return NULL;
}
@@ -153,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
map_bh(bh, sdp->sd_vfs, blkno);
unlock_page(page);
- mark_page_accessed(page);
page_cache_release(page);
return bh;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 22f954051bb8..bc564c0d6d16 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -94,6 +94,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
INIT_LIST_HEAD(&sdp->sd_jindex_list);
spin_lock_init(&sdp->sd_jindex_spin);
mutex_init(&sdp->sd_jindex_mutex);
+ init_completion(&sdp->sd_journal_ready);
INIT_LIST_HEAD(&sdp->sd_quota_list);
mutex_init(&sdp->sd_quota_mutex);
@@ -129,6 +130,10 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
init_rwsem(&sdp->sd_log_flush_lock);
atomic_set(&sdp->sd_log_in_flight, 0);
init_waitqueue_head(&sdp->sd_log_flush_wait);
+ init_waitqueue_head(&sdp->sd_log_frozen_wait);
+ atomic_set(&sdp->sd_log_freeze, 0);
+ atomic_set(&sdp->sd_frozen_root, 0);
+ init_waitqueue_head(&sdp->sd_frozen_root_wait);
return sdp;
}
@@ -419,8 +424,8 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
goto fail_live;
}
- error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
- CREATE, &sdp->sd_trans_gl);
+ error = gfs2_glock_get(sdp, GFS2_FREEZE_LOCK, &gfs2_freeze_glops,
+ CREATE, &sdp->sd_freeze_gl);
if (error) {
fs_err(sdp, "can't create transaction glock: %d\n", error);
goto fail_rename;
@@ -429,7 +434,7 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
return 0;
fail_trans:
- gfs2_glock_put(sdp->sd_trans_gl);
+ gfs2_glock_put(sdp->sd_freeze_gl);
fail_rename:
gfs2_glock_put(sdp->sd_rename_gl);
fail_live:
@@ -755,7 +760,15 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
gfs2_glock_dq_uninit(&ji_gh);
jindex = 0;
-
+ if (!sdp->sd_args.ar_spectator) {
+ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
+ &sdp->sd_thaw_gh);
+ if (error) {
+ fs_err(sdp, "can't acquire freeze glock: %d\n", error);
+ goto fail_jinode_gh;
+ }
+ }
+ gfs2_glock_dq_uninit(&sdp->sd_thaw_gh);
return 0;
fail_jinode_gh:
@@ -784,6 +797,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
goto fail_qinode;
error = init_journal(sdp, undo);
+ complete_all(&sdp->sd_journal_ready);
if (error)
goto fail;
@@ -1200,6 +1214,7 @@ fail_sb:
fail_locking:
init_locking(sdp, &mount_gh, UNDO);
fail_lm:
+ complete_all(&sdp->sd_journal_ready);
gfs2_gl_hash_clear(sdp);
gfs2_lm_unmount(sdp);
fail_debug:
@@ -1380,7 +1395,7 @@ static void gfs2_kill_sb(struct super_block *sb)
return;
}
- gfs2_meta_syncfs(sdp);
+ gfs2_log_flush(sdp, NULL, SYNC_FLUSH);
dput(sdp->sd_root_dir);
dput(sdp->sd_master_dir);
sdp->sd_root_dir = NULL;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index c4effff7cf55..64b29f7f6b4c 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -778,6 +778,7 @@ get_a_page:
i_size_write(inode, size);
inode->i_mtime = inode->i_atime = CURRENT_TIME;
mark_inode_dirty(inode);
+ set_bit(QDF_REFRESH, &qd->qd_flags);
return 0;
unlock_out:
@@ -879,7 +880,7 @@ out:
gfs2_glock_dq_uninit(&ghs[qx]);
mutex_unlock(&ip->i_inode.i_mutex);
kfree(ghs);
- gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl);
+ gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl, NORMAL_FLUSH);
return error;
}
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 7ad4094d68c0..94555d4c5698 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -454,7 +454,7 @@ void gfs2_recover_func(struct work_struct *work)
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
struct gfs2_log_header_host head;
- struct gfs2_holder j_gh, ji_gh, t_gh;
+ struct gfs2_holder j_gh, ji_gh, thaw_gh;
unsigned long t;
int ro = 0;
unsigned int pass;
@@ -508,11 +508,11 @@ void gfs2_recover_func(struct work_struct *work)
t = jiffies;
- /* Acquire a shared hold on the transaction lock */
+ /* Acquire a shared hold on the freeze lock */
- error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
- LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
- GL_NOCACHE, &t_gh);
+ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+ LM_FLAG_NOEXP | LM_FLAG_PRIORITY,
+ &thaw_gh);
if (error)
goto fail_gunlock_ji;
@@ -538,7 +538,7 @@ void gfs2_recover_func(struct work_struct *work)
fs_warn(sdp, "jid=%u: Can't replay: read-only block "
"device\n", jd->jd_jid);
error = -EROFS;
- goto fail_gunlock_tr;
+ goto fail_gunlock_thaw;
}
fs_info(sdp, "jid=%u: Replaying journal...\n", jd->jd_jid);
@@ -549,14 +549,14 @@ void gfs2_recover_func(struct work_struct *work)
head.lh_blkno, pass);
lops_after_scan(jd, error, pass);
if (error)
- goto fail_gunlock_tr;
+ goto fail_gunlock_thaw;
}
error = clean_journal(jd, &head);
if (error)
- goto fail_gunlock_tr;
+ goto fail_gunlock_thaw;
- gfs2_glock_dq_uninit(&t_gh);
+ gfs2_glock_dq_uninit(&thaw_gh);
t = DIV_ROUND_UP(jiffies - t, HZ);
fs_info(sdp, "jid=%u: Journal replayed in %lus\n",
jd->jd_jid, t);
@@ -572,8 +572,8 @@ void gfs2_recover_func(struct work_struct *work)
fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
goto done;
-fail_gunlock_tr:
- gfs2_glock_dq_uninit(&t_gh);
+fail_gunlock_thaw:
+ gfs2_glock_dq_uninit(&thaw_gh);
fail_gunlock_ji:
if (jlocked) {
gfs2_glock_dq_uninit(&ji_gh);
@@ -587,7 +587,7 @@ fail:
gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
done:
clear_bit(JDF_RECOVERY, &jd->jd_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
}
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 281a7716e3f3..db629d1bd1bd 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -2001,7 +2001,7 @@ next_rgrp:
}
/* Flushing the log may release space */
if (loops == 2)
- gfs2_log_flush(sdp, NULL);
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
return -ENOSPC;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index de8afad89e51..1319b5c4ec68 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -399,7 +399,7 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
struct gfs2_glock *j_gl = ip->i_gl;
- struct gfs2_holder t_gh;
+ struct gfs2_holder thaw_gh;
struct gfs2_log_header_host head;
int error;
@@ -407,7 +407,8 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
if (error)
return error;
- error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh);
+ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
+ &thaw_gh);
if (error)
goto fail_threads;
@@ -433,13 +434,13 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
- gfs2_glock_dq_uninit(&t_gh);
+ gfs2_glock_dq_uninit(&thaw_gh);
return 0;
fail:
- t_gh.gh_flags |= GL_NOCACHE;
- gfs2_glock_dq_uninit(&t_gh);
+ thaw_gh.gh_flags |= GL_NOCACHE;
+ gfs2_glock_dq_uninit(&thaw_gh);
fail_threads:
kthread_stop(sdp->sd_quotad_process);
kthread_stop(sdp->sd_logd_process);
@@ -635,15 +636,21 @@ struct lfcc {
*/
static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
- struct gfs2_holder *t_gh)
+ struct gfs2_holder *freeze_gh)
{
struct gfs2_inode *ip;
struct gfs2_jdesc *jd;
struct lfcc *lfcc;
LIST_HEAD(list);
struct gfs2_log_header_host lh;
+ struct gfs2_inode *dip = GFS2_I(sdp->sd_root_dir->d_inode);
int error;
+ error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0,
+ &sdp->sd_freeze_root_gh);
+ if (error)
+ return error;
+ atomic_set(&sdp->sd_frozen_root, 1);
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL);
if (!lfcc) {
@@ -659,8 +666,8 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
list_add(&lfcc->list, &list);
}
- error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
- GL_NOCACHE, t_gh);
+ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
+ GL_NOCACHE, freeze_gh);
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
error = gfs2_jdesc_check(jd);
@@ -676,7 +683,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
}
if (error)
- gfs2_glock_dq_uninit(t_gh);
+ gfs2_glock_dq_uninit(freeze_gh);
out:
while (!list_empty(&list)) {
@@ -685,6 +692,11 @@ out:
gfs2_glock_dq_uninit(&lfcc->gh);
kfree(lfcc);
}
+ if (error) {
+ atomic_dec(&sdp->sd_frozen_root);
+ wait_event(sdp->sd_frozen_root_wait, atomic_read(&sdp->sd_frozen_root) == 0);
+ gfs2_glock_dq_uninit(&sdp->sd_freeze_root_gh);
+ }
return error;
}
@@ -742,7 +754,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
int ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
- gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+ gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH);
if (bdi->dirty_exceeded)
gfs2_ail1_flush(sdp, wbc);
else
@@ -822,9 +834,18 @@ out:
static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
{
- struct gfs2_holder t_gh;
+ struct gfs2_holder thaw_gh;
int error;
+ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
+ &thaw_gh);
+ if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+ return error;
+
+ down_write(&sdp->sd_log_flush_lock);
+ clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+ up_write(&sdp->sd_log_flush_lock);
+
kthread_stop(sdp->sd_quotad_process);
kthread_stop(sdp->sd_logd_process);
@@ -832,18 +853,11 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
gfs2_quota_sync(sdp->sd_vfs, 0);
gfs2_statfs_sync(sdp->sd_vfs, 0);
- error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
- &t_gh);
- if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
- return error;
-
- gfs2_meta_syncfs(sdp);
- gfs2_log_shutdown(sdp);
-
- clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+ gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH);
+ gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
- if (t_gh.gh_gl)
- gfs2_glock_dq_uninit(&t_gh);
+ if (thaw_gh.gh_gl)
+ gfs2_glock_dq_uninit(&thaw_gh);
gfs2_quota_cleanup(sdp);
@@ -900,7 +914,7 @@ restart:
iput(sdp->sd_quota_inode);
gfs2_glock_put(sdp->sd_rename_gl);
- gfs2_glock_put(sdp->sd_trans_gl);
+ gfs2_glock_put(sdp->sd_freeze_gl);
if (!sdp->sd_args.ar_spectator) {
gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
@@ -935,8 +949,8 @@ static int gfs2_sync_fs(struct super_block *sb, int wait)
struct gfs2_sbd *sdp = sb->s_fs_info;
gfs2_quota_sync(sb, -1);
- if (wait && sdp)
- gfs2_log_flush(sdp, NULL);
+ if (wait && sdp && !atomic_read(&sdp->sd_log_freeze))
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
return 0;
}
@@ -986,6 +1000,9 @@ static int gfs2_unfreeze(struct super_block *sb)
struct gfs2_sbd *sdp = sb->s_fs_info;
gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+ atomic_dec(&sdp->sd_frozen_root);
+ wait_event(sdp->sd_frozen_root_wait, atomic_read(&sdp->sd_frozen_root) == 0);
+ gfs2_glock_dq_uninit(&sdp->sd_freeze_root_gh);
return 0;
}
@@ -1525,7 +1542,7 @@ static void gfs2_evict_inode(struct inode *inode)
goto out_unlock;
out_truncate:
- gfs2_log_flush(sdp, ip->i_gl);
+ gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
filemap_fdatawrite(metamapping);
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index de25d5577e5d..3ab566ba5696 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -240,8 +240,8 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len
if (gltype > LM_TYPE_JOURNAL)
return -EINVAL;
- if (gltype == LM_TYPE_NONDISK && glnum == GFS2_TRANS_LOCK)
- glops = &gfs2_trans_glops;
+ if (gltype == LM_TYPE_NONDISK && glnum == GFS2_FREEZE_LOCK)
+ glops = &gfs2_freeze_glops;
else
glops = gfs2_glops_list[gltype];
if (glops == NULL)
@@ -333,7 +333,7 @@ static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
set_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
else if (val == 0) {
clear_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
gfs2_glock_thaw(sdp);
} else {
ret = -EINVAL;
@@ -407,6 +407,9 @@ int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid)
struct gfs2_jdesc *jd;
int rv;
+ /* Wait for our primary journal to be initialized */
+ wait_for_completion(&sdp->sd_journal_ready);
+
spin_lock(&sdp->sd_jindex_spin);
rv = -EBUSY;
if (sdp->sd_jdesc->jd_jid == jid)
@@ -482,7 +485,7 @@ static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
rv = jid = -EINVAL;
sdp->sd_lockstruct.ls_jid = jid;
clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
out:
spin_unlock(&sdp->sd_jindex_spin);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index bead90d27bad..0546ab4e28e8 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -48,6 +48,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
tr->tr_blocks = blocks;
tr->tr_revokes = revokes;
tr->tr_reserved = 1;
+ tr->tr_alloced = 1;
if (blocks)
tr->tr_reserved += 6 + blocks;
if (revokes)
@@ -57,48 +58,22 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
INIT_LIST_HEAD(&tr->tr_buf);
sb_start_intwrite(sdp->sd_vfs);
- gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh);
-
- error = gfs2_glock_nq(&tr->tr_t_gh);
- if (error)
- goto fail_holder_uninit;
error = gfs2_log_reserve(sdp, tr->tr_reserved);
if (error)
- goto fail_gunlock;
+ goto fail;
current->journal_info = tr;
return 0;
-fail_gunlock:
- gfs2_glock_dq(&tr->tr_t_gh);
-
-fail_holder_uninit:
+fail:
sb_end_intwrite(sdp->sd_vfs);
- gfs2_holder_uninit(&tr->tr_t_gh);
kfree(tr);
return error;
}
-/**
- * gfs2_log_release - Release a given number of log blocks
- * @sdp: The GFS2 superblock
- * @blks: The number of blocks
- *
- */
-
-static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
-{
-
- atomic_add(blks, &sdp->sd_log_blks_free);
- trace_gfs2_log_blocks(sdp, blks);
- gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
- sdp->sd_jdesc->jd_blocks);
- up_read(&sdp->sd_log_flush_lock);
-}
-
static void gfs2_print_trans(const struct gfs2_trans *tr)
{
pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
@@ -119,11 +94,8 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
if (!tr->tr_touched) {
gfs2_log_release(sdp, tr->tr_reserved);
- if (tr->tr_t_gh.gh_gl) {
- gfs2_glock_dq(&tr->tr_t_gh);
- gfs2_holder_uninit(&tr->tr_t_gh);
+ if (tr->tr_alloced)
kfree(tr);
- }
sb_end_intwrite(sdp->sd_vfs);
return;
}
@@ -137,16 +109,12 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
gfs2_print_trans(tr);
gfs2_log_commit(sdp, tr);
- if (tr->tr_t_gh.gh_gl) {
- gfs2_glock_dq(&tr->tr_t_gh);
- gfs2_holder_uninit(&tr->tr_t_gh);
- if (!tr->tr_attached)
+ if (tr->tr_alloced && !tr->tr_attached)
kfree(tr);
- }
up_read(&sdp->sd_log_flush_lock);
if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
- gfs2_log_flush(sdp, NULL);
+ gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
sb_end_intwrite(sdp->sd_vfs);
}
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
index caf89a7be0a1..e5b221de7de6 100644
--- a/fs/hfsplus/attributes.c
+++ b/fs/hfsplus/attributes.c
@@ -54,14 +54,11 @@ int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key,
memset(key, 0, sizeof(struct hfsplus_attr_key));
key->attr.cnid = cpu_to_be32(cnid);
if (name) {
- len = strlen(name);
- if (len > HFSPLUS_ATTR_MAX_STRLEN) {
- pr_err("invalid xattr name's length\n");
- return -EINVAL;
- }
- hfsplus_asc2uni(sb,
+ int res = hfsplus_asc2uni(sb,
(struct hfsplus_unistr *)&key->attr.key_name,
- HFSPLUS_ATTR_MAX_STRLEN, name, len);
+ HFSPLUS_ATTR_MAX_STRLEN, name, strlen(name));
+ if (res)
+ return res;
len = be16_to_cpu(key->attr.key_name.length);
} else {
key->attr.key_name.length = 0;
@@ -82,31 +79,6 @@ int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key,
return 0;
}
-void hfsplus_attr_build_key_uni(hfsplus_btree_key *key,
- u32 cnid,
- struct hfsplus_attr_unistr *name)
-{
- int ustrlen;
-
- memset(key, 0, sizeof(struct hfsplus_attr_key));
- ustrlen = be16_to_cpu(name->length);
- key->attr.cnid = cpu_to_be32(cnid);
- key->attr.key_name.length = cpu_to_be16(ustrlen);
- ustrlen *= 2;
- memcpy(key->attr.key_name.unicode, name->unicode, ustrlen);
-
- /* The length of the key, as stored in key_len field, does not include
- * the size of the key_len field itself.
- * So, offsetof(hfsplus_attr_key, key_name) is a trick because
- * it takes into consideration key_len field (__be16) of
- * hfsplus_attr_key structure instead of length field (__be16) of
- * hfsplus_attr_unistr structure.
- */
- key->key_len =
- cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) +
- ustrlen);
-}
-
hfsplus_attr_entry *hfsplus_alloc_attr_entry(void)
{
return kmem_cache_alloc(hfsplus_attr_tree_cachep, GFP_KERNEL);
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 11c860204520..759708fd9331 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -27,13 +27,13 @@ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
pagep = node->page + (off >> PAGE_CACHE_SHIFT);
off &= ~PAGE_CACHE_MASK;
- l = min(len, (int)PAGE_CACHE_SIZE - off);
+ l = min_t(int, len, PAGE_CACHE_SIZE - off);
memcpy(buf, kmap(*pagep) + off, l);
kunmap(*pagep);
while ((len -= l) != 0) {
buf += l;
- l = min(len, (int)PAGE_CACHE_SIZE);
+ l = min_t(int, len, PAGE_CACHE_SIZE);
memcpy(buf, kmap(*++pagep), l);
kunmap(*pagep);
}
@@ -80,14 +80,14 @@ void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len)
pagep = node->page + (off >> PAGE_CACHE_SHIFT);
off &= ~PAGE_CACHE_MASK;
- l = min(len, (int)PAGE_CACHE_SIZE - off);
+ l = min_t(int, len, PAGE_CACHE_SIZE - off);
memcpy(kmap(*pagep) + off, buf, l);
set_page_dirty(*pagep);
kunmap(*pagep);
while ((len -= l) != 0) {
buf += l;
- l = min(len, (int)PAGE_CACHE_SIZE);
+ l = min_t(int, len, PAGE_CACHE_SIZE);
memcpy(kmap(*++pagep), buf, l);
set_page_dirty(*pagep);
kunmap(*pagep);
@@ -110,13 +110,13 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
pagep = node->page + (off >> PAGE_CACHE_SHIFT);
off &= ~PAGE_CACHE_MASK;
- l = min(len, (int)PAGE_CACHE_SIZE - off);
+ l = min_t(int, len, PAGE_CACHE_SIZE - off);
memset(kmap(*pagep) + off, 0, l);
set_page_dirty(*pagep);
kunmap(*pagep);
while ((len -= l) != 0) {
- l = min(len, (int)PAGE_CACHE_SIZE);
+ l = min_t(int, len, PAGE_CACHE_SIZE);
memset(kmap(*++pagep), 0, l);
set_page_dirty(*pagep);
kunmap(*pagep);
@@ -142,14 +142,14 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
dst &= ~PAGE_CACHE_MASK;
if (src == dst) {
- l = min(len, (int)PAGE_CACHE_SIZE - src);
+ l = min_t(int, len, PAGE_CACHE_SIZE - src);
memcpy(kmap(*dst_page) + src, kmap(*src_page) + src, l);
kunmap(*src_page);
set_page_dirty(*dst_page);
kunmap(*dst_page);
while ((len -= l) != 0) {
- l = min(len, (int)PAGE_CACHE_SIZE);
+ l = min_t(int, len, PAGE_CACHE_SIZE);
memcpy(kmap(*++dst_page), kmap(*++src_page), l);
kunmap(*src_page);
set_page_dirty(*dst_page);
@@ -251,7 +251,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
dst &= ~PAGE_CACHE_MASK;
if (src == dst) {
- l = min(len, (int)PAGE_CACHE_SIZE - src);
+ l = min_t(int, len, PAGE_CACHE_SIZE - src);
memmove(kmap(*dst_page) + src,
kmap(*src_page) + src, l);
kunmap(*src_page);
@@ -259,7 +259,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
kunmap(*dst_page);
while ((len -= l) != 0) {
- l = min(len, (int)PAGE_CACHE_SIZE);
+ l = min_t(int, len, PAGE_CACHE_SIZE);
memmove(kmap(*++dst_page),
kmap(*++src_page), l);
kunmap(*src_page);
@@ -386,9 +386,8 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid)
struct hfs_bnode *node;
if (cnid >= tree->node_count) {
- pr_err("request for non-existent node "
- "%d in B*Tree\n",
- cnid);
+ pr_err("request for non-existent node %d in B*Tree\n",
+ cnid);
return NULL;
}
@@ -409,9 +408,8 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
loff_t off;
if (cnid >= tree->node_count) {
- pr_err("request for non-existent node "
- "%d in B*Tree\n",
- cnid);
+ pr_err("request for non-existent node %d in B*Tree\n",
+ cnid);
return NULL;
}
@@ -602,7 +600,7 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num)
pagep = node->page;
memset(kmap(*pagep) + node->page_offset, 0,
- min((int)PAGE_CACHE_SIZE, (int)tree->node_size));
+ min_t(int, PAGE_CACHE_SIZE, tree->node_size));
set_page_dirty(*pagep);
kunmap(*pagep);
for (i = 1; i < tree->pages_per_bnode; i++) {
@@ -648,8 +646,8 @@ void hfs_bnode_put(struct hfs_bnode *node)
if (test_bit(HFS_BNODE_DELETED, &node->flags)) {
hfs_bnode_unhash(node);
spin_unlock(&tree->hash_lock);
- hfs_bnode_clear(node, 0,
- PAGE_CACHE_SIZE * tree->pages_per_bnode);
+ if (hfs_bnode_need_zeroout(tree))
+ hfs_bnode_clear(node, 0, tree->node_size);
hfs_bmap_free(node);
hfs_bnode_free(node);
return;
@@ -658,3 +656,16 @@ void hfs_bnode_put(struct hfs_bnode *node)
}
}
+/*
+ * Unused nodes have to be zeroed if this is the catalog tree and
+ * a corresponding flag in the volume header is set.
+ */
+bool hfs_bnode_need_zeroout(struct hfs_btree *tree)
+{
+ struct super_block *sb = tree->inode->i_sb;
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+ const u32 volume_attr = be32_to_cpu(sbi->s_vhdr->attributes);
+
+ return tree->cnid == HFSPLUS_CAT_CNID &&
+ volume_attr & HFSPLUS_VOL_UNUSED_NODE_FIX;
+}
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 0fcec8b2a90b..3345c7553edc 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -358,7 +358,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
u32 count;
int res;
- res = hfsplus_file_extend(inode);
+ res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree));
if (res)
return ERR_PTR(res);
hip->phys_size = inode->i_size =
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index bdec66522de3..610a3260bef1 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -12,6 +12,7 @@
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/random.h>
+#include <linux/nls.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
@@ -127,7 +128,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
int len, err;
- char strbuf[HFSPLUS_MAX_STRLEN + 1];
+ char *strbuf;
hfsplus_cat_entry entry;
struct hfs_find_data fd;
struct hfsplus_readdir_data *rd;
@@ -139,6 +140,11 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
if (err)
return err;
+ strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN + 1, GFP_KERNEL);
+ if (!strbuf) {
+ err = -ENOMEM;
+ goto out;
+ }
hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
@@ -193,7 +199,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
fd.entrylength);
type = be16_to_cpu(entry.type);
- len = HFSPLUS_MAX_STRLEN;
+ len = NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN;
err = hfsplus_uni2asc(sb, &fd.key->cat.name, strbuf, &len);
if (err)
goto out;
@@ -212,13 +218,31 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
be32_to_cpu(entry.folder.id), DT_DIR))
break;
} else if (type == HFSPLUS_FILE) {
+ u16 mode;
+ unsigned type = DT_UNKNOWN;
+
if (fd.entrylength < sizeof(struct hfsplus_cat_file)) {
pr_err("small file entry\n");
err = -EIO;
goto out;
}
+
+ mode = be16_to_cpu(entry.file.permissions.mode);
+ if (S_ISREG(mode))
+ type = DT_REG;
+ else if (S_ISLNK(mode))
+ type = DT_LNK;
+ else if (S_ISFIFO(mode))
+ type = DT_FIFO;
+ else if (S_ISCHR(mode))
+ type = DT_CHR;
+ else if (S_ISBLK(mode))
+ type = DT_BLK;
+ else if (S_ISSOCK(mode))
+ type = DT_SOCK;
+
if (!dir_emit(ctx, strbuf, len,
- be32_to_cpu(entry.file.id), DT_REG))
+ be32_to_cpu(entry.file.id), type))
break;
} else {
pr_err("bad catalog entry type\n");
@@ -246,6 +270,7 @@ next:
}
memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key));
out:
+ kfree(strbuf);
hfs_find_exit(&fd);
return err;
}
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index a7aafb35b624..feca524ce2a5 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -235,7 +235,7 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
if (iblock > hip->fs_blocks || !create)
return -EIO;
if (ablock >= hip->alloc_blocks) {
- res = hfsplus_file_extend(inode);
+ res = hfsplus_file_extend(inode, false);
if (res)
return res;
}
@@ -425,7 +425,7 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid,
return res;
}
-int hfsplus_file_extend(struct inode *inode)
+int hfsplus_file_extend(struct inode *inode, bool zeroout)
{
struct super_block *sb = inode->i_sb;
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
@@ -436,10 +436,9 @@ int hfsplus_file_extend(struct inode *inode)
if (sbi->alloc_file->i_size * 8 <
sbi->total_blocks - sbi->free_blocks + 8) {
/* extend alloc file */
- pr_err("extend alloc file! "
- "(%llu,%u,%u)\n",
- sbi->alloc_file->i_size * 8,
- sbi->total_blocks, sbi->free_blocks);
+ pr_err("extend alloc file! (%llu,%u,%u)\n",
+ sbi->alloc_file->i_size * 8,
+ sbi->total_blocks, sbi->free_blocks);
return -ENOSPC;
}
@@ -463,6 +462,12 @@ int hfsplus_file_extend(struct inode *inode)
}
}
+ if (zeroout) {
+ res = sb_issue_zeroout(sb, start, len, GFP_NOFS);
+ if (res)
+ goto out;
+ }
+
hfs_dbg(EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len);
if (hip->alloc_blocks <= hip->first_blocks) {
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 83dc29286b10..eb5e059f481a 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -369,114 +369,119 @@ typedef int (*search_strategy_t)(struct hfs_bnode *,
/* attributes.c */
int __init hfsplus_create_attr_tree_cache(void);
void hfsplus_destroy_attr_tree_cache(void);
+int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *k1,
+ const hfsplus_btree_key *k2);
+int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key,
+ u32 cnid, const char *name);
hfsplus_attr_entry *hfsplus_alloc_attr_entry(void);
-void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p);
-int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *,
- const hfsplus_btree_key *);
-int hfsplus_attr_build_key(struct super_block *, hfsplus_btree_key *,
- u32, const char *);
-void hfsplus_attr_build_key_uni(hfsplus_btree_key *key,
- u32 cnid,
- struct hfsplus_attr_unistr *name);
-int hfsplus_find_attr(struct super_block *, u32,
- const char *, struct hfs_find_data *);
+void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry);
+int hfsplus_find_attr(struct super_block *sb, u32 cnid, const char *name,
+ struct hfs_find_data *fd);
int hfsplus_attr_exists(struct inode *inode, const char *name);
-int hfsplus_create_attr(struct inode *, const char *, const void *, size_t);
-int hfsplus_delete_attr(struct inode *, const char *);
+int hfsplus_create_attr(struct inode *inode, const char *name,
+ const void *value, size_t size);
+int hfsplus_delete_attr(struct inode *inode, const char *name);
int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid);
/* bitmap.c */
-int hfsplus_block_allocate(struct super_block *, u32, u32, u32 *);
-int hfsplus_block_free(struct super_block *, u32, u32);
+int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset,
+ u32 *max);
+int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count);
/* btree.c */
-u32 hfsplus_calc_btree_clump_size(u32, u32, u64, int);
-struct hfs_btree *hfs_btree_open(struct super_block *, u32);
-void hfs_btree_close(struct hfs_btree *);
-int hfs_btree_write(struct hfs_btree *);
-struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *);
-void hfs_bmap_free(struct hfs_bnode *);
+u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size, u64 sectors,
+ int file_id);
+struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id);
+void hfs_btree_close(struct hfs_btree *tree);
+int hfs_btree_write(struct hfs_btree *tree);
+struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree);
+void hfs_bmap_free(struct hfs_bnode *node);
/* bnode.c */
-void hfs_bnode_read(struct hfs_bnode *, void *, int, int);
-u16 hfs_bnode_read_u16(struct hfs_bnode *, int);
-u8 hfs_bnode_read_u8(struct hfs_bnode *, int);
-void hfs_bnode_read_key(struct hfs_bnode *, void *, int);
-void hfs_bnode_write(struct hfs_bnode *, void *, int, int);
-void hfs_bnode_write_u16(struct hfs_bnode *, int, u16);
-void hfs_bnode_clear(struct hfs_bnode *, int, int);
-void hfs_bnode_copy(struct hfs_bnode *, int,
- struct hfs_bnode *, int, int);
-void hfs_bnode_move(struct hfs_bnode *, int, int, int);
-void hfs_bnode_dump(struct hfs_bnode *);
-void hfs_bnode_unlink(struct hfs_bnode *);
-struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *, u32);
-struct hfs_bnode *hfs_bnode_find(struct hfs_btree *, u32);
-void hfs_bnode_unhash(struct hfs_bnode *);
-void hfs_bnode_free(struct hfs_bnode *);
-struct hfs_bnode *hfs_bnode_create(struct hfs_btree *, u32);
-void hfs_bnode_get(struct hfs_bnode *);
-void hfs_bnode_put(struct hfs_bnode *);
+void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len);
+u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off);
+u8 hfs_bnode_read_u8(struct hfs_bnode *node, int off);
+void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off);
+void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len);
+void hfs_bnode_write_u16(struct hfs_bnode *node, int off, u16 data);
+void hfs_bnode_clear(struct hfs_bnode *node, int off, int len);
+void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
+ struct hfs_bnode *src_node, int src, int len);
+void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len);
+void hfs_bnode_dump(struct hfs_bnode *node);
+void hfs_bnode_unlink(struct hfs_bnode *node);
+struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid);
+void hfs_bnode_unhash(struct hfs_bnode *node);
+struct hfs_bnode *hfs_bnode_find(struct hfs_btree *tree, u32 num);
+void hfs_bnode_free(struct hfs_bnode *node);
+struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num);
+void hfs_bnode_get(struct hfs_bnode *node);
+void hfs_bnode_put(struct hfs_bnode *node);
+bool hfs_bnode_need_zeroout(struct hfs_btree *tree);
/* brec.c */
-u16 hfs_brec_lenoff(struct hfs_bnode *, u16, u16 *);
-u16 hfs_brec_keylen(struct hfs_bnode *, u16);
-int hfs_brec_insert(struct hfs_find_data *, void *, int);
-int hfs_brec_remove(struct hfs_find_data *);
+u16 hfs_brec_lenoff(struct hfs_bnode *node, u16 rec, u16 *off);
+u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec);
+int hfs_brec_insert(struct hfs_find_data *fd, void *entry, int entry_len);
+int hfs_brec_remove(struct hfs_find_data *fd);
/* bfind.c */
-int hfs_find_init(struct hfs_btree *, struct hfs_find_data *);
-void hfs_find_exit(struct hfs_find_data *);
-int hfs_find_1st_rec_by_cnid(struct hfs_bnode *,
- struct hfs_find_data *,
- int *, int *, int *);
-int hfs_find_rec_by_key(struct hfs_bnode *,
- struct hfs_find_data *,
- int *, int *, int *);
-int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *,
- search_strategy_t);
-int hfs_brec_find(struct hfs_find_data *, search_strategy_t);
-int hfs_brec_read(struct hfs_find_data *, void *, int);
-int hfs_brec_goto(struct hfs_find_data *, int);
+int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd);
+void hfs_find_exit(struct hfs_find_data *fd);
+int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, struct hfs_find_data *fd,
+ int *begin, int *end, int *cur_rec);
+int hfs_find_rec_by_key(struct hfs_bnode *bnode, struct hfs_find_data *fd,
+ int *begin, int *end, int *cur_rec);
+int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd,
+ search_strategy_t rec_found);
+int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare);
+int hfs_brec_read(struct hfs_find_data *fd, void *rec, int rec_len);
+int hfs_brec_goto(struct hfs_find_data *fd, int cnt);
/* catalog.c */
-int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *,
- const hfsplus_btree_key *);
-int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *,
- const hfsplus_btree_key *);
-void hfsplus_cat_build_key(struct super_block *sb,
- hfsplus_btree_key *, u32, struct qstr *);
-int hfsplus_find_cat(struct super_block *, u32, struct hfs_find_data *);
-int hfsplus_create_cat(u32, struct inode *, struct qstr *, struct inode *);
-int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
-int hfsplus_rename_cat(u32, struct inode *, struct qstr *,
- struct inode *, struct qstr *);
+int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1,
+ const hfsplus_btree_key *k2);
+int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
+ const hfsplus_btree_key *k2);
+void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
+ u32 parent, struct qstr *str);
void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
+int hfsplus_find_cat(struct super_block *sb, u32 cnid,
+ struct hfs_find_data *fd);
+int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str,
+ struct inode *inode);
+int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str);
+int hfsplus_rename_cat(u32 cnid, struct inode *src_dir, struct qstr *src_name,
+ struct inode *dst_dir, struct qstr *dst_name);
/* dir.c */
extern const struct inode_operations hfsplus_dir_inode_operations;
extern const struct file_operations hfsplus_dir_operations;
/* extents.c */
-int hfsplus_ext_cmp_key(const hfsplus_btree_key *, const hfsplus_btree_key *);
-int hfsplus_ext_write_extent(struct inode *);
-int hfsplus_get_block(struct inode *, sector_t, struct buffer_head *, int);
-int hfsplus_free_fork(struct super_block *, u32,
- struct hfsplus_fork_raw *, int);
-int hfsplus_file_extend(struct inode *);
-void hfsplus_file_truncate(struct inode *);
+int hfsplus_ext_cmp_key(const hfsplus_btree_key *k1,
+ const hfsplus_btree_key *k2);
+int hfsplus_ext_write_extent(struct inode *inode);
+int hfsplus_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
+int hfsplus_free_fork(struct super_block *sb, u32 cnid,
+ struct hfsplus_fork_raw *fork, int type);
+int hfsplus_file_extend(struct inode *inode, bool zeroout);
+void hfsplus_file_truncate(struct inode *inode);
/* inode.c */
extern const struct address_space_operations hfsplus_aops;
extern const struct address_space_operations hfsplus_btree_aops;
extern const struct dentry_operations hfsplus_dentry_operations;
-void hfsplus_inode_read_fork(struct inode *, struct hfsplus_fork_raw *);
-void hfsplus_inode_write_fork(struct inode *, struct hfsplus_fork_raw *);
-int hfsplus_cat_read_inode(struct inode *, struct hfs_find_data *);
-int hfsplus_cat_write_inode(struct inode *);
-struct inode *hfsplus_new_inode(struct super_block *, umode_t);
-void hfsplus_delete_inode(struct inode *);
+struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode);
+void hfsplus_delete_inode(struct inode *inode);
+void hfsplus_inode_read_fork(struct inode *inode,
+ struct hfsplus_fork_raw *fork);
+void hfsplus_inode_write_fork(struct inode *inode,
+ struct hfsplus_fork_raw *fork);
+int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd);
+int hfsplus_cat_write_inode(struct inode *inode);
int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
@@ -484,13 +489,17 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
/* options.c */
-int hfsplus_parse_options(char *, struct hfsplus_sb_info *);
+void hfsplus_fill_defaults(struct hfsplus_sb_info *opts);
int hfsplus_parse_options_remount(char *input, int *force);
-void hfsplus_fill_defaults(struct hfsplus_sb_info *);
-int hfsplus_show_options(struct seq_file *, struct dentry *);
+int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi);
+int hfsplus_show_options(struct seq_file *seq, struct dentry *root);
+
+/* part_tbl.c */
+int hfs_part_find(struct super_block *sb, sector_t *part_start,
+ sector_t *part_size);
/* super.c */
-struct inode *hfsplus_iget(struct super_block *, unsigned long);
+struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino);
void hfsplus_mark_mdb_dirty(struct super_block *sb);
/* tables.c */
@@ -499,23 +508,23 @@ extern u16 hfsplus_decompose_table[];
extern u16 hfsplus_compose_table[];
/* unicode.c */
-int hfsplus_strcasecmp(const struct hfsplus_unistr *,
- const struct hfsplus_unistr *);
-int hfsplus_strcmp(const struct hfsplus_unistr *,
- const struct hfsplus_unistr *);
-int hfsplus_uni2asc(struct super_block *,
- const struct hfsplus_unistr *, char *, int *);
-int hfsplus_asc2uni(struct super_block *,
- struct hfsplus_unistr *, int, const char *, int);
+int hfsplus_strcasecmp(const struct hfsplus_unistr *s1,
+ const struct hfsplus_unistr *s2);
+int hfsplus_strcmp(const struct hfsplus_unistr *s1,
+ const struct hfsplus_unistr *s2);
+int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr,
+ char *astr, int *len_p);
+int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
+ int max_unistr_len, const char *astr, int len);
int hfsplus_hash_dentry(const struct dentry *dentry, struct qstr *str);
-int hfsplus_compare_dentry(const struct dentry *parent, const struct dentry *dentry,
- unsigned int len, const char *str, const struct qstr *name);
+int hfsplus_compare_dentry(const struct dentry *parent,
+ const struct dentry *dentry, unsigned int len,
+ const char *str, const struct qstr *name);
/* wrapper.c */
-int hfsplus_read_wrapper(struct super_block *);
-int hfs_part_find(struct super_block *, sector_t *, sector_t *);
-int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
- void *buf, void **data, int rw);
+int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf,
+ void **data, int rw);
+int hfsplus_read_wrapper(struct super_block *sb);
/* time macros */
#define __hfsp_mt2ut(t) (be32_to_cpu(t) - 2082844800U)
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 5a126828d85e..8298d0985f81 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -144,6 +144,7 @@ struct hfsplus_vh {
#define HFSPLUS_VOL_NODEID_REUSED (1 << 12)
#define HFSPLUS_VOL_JOURNALED (1 << 13)
#define HFSPLUS_VOL_SOFTLOCK (1 << 15)
+#define HFSPLUS_VOL_UNUSED_NODE_FIX (1 << 31)
/* HFS+ BTree node descriptor */
struct hfs_bnode_desc {
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 68537e8b7a09..c90b72ee676d 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -173,9 +173,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
if (p)
sbi->nls = load_nls(p);
if (!sbi->nls) {
- pr_err("unable to load "
- "nls mapping \"%s\"\n",
- p);
+ pr_err("unable to load nls mapping \"%s\"\n",
+ p);
kfree(p);
return 0;
}
@@ -232,8 +231,8 @@ int hfsplus_show_options(struct seq_file *seq, struct dentry *root)
if (sbi->nls)
seq_printf(seq, ",nls=%s", sbi->nls->charset);
if (test_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags))
- seq_printf(seq, ",nodecompose");
+ seq_puts(seq, ",nodecompose");
if (test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
- seq_printf(seq, ",nobarrier");
+ seq_puts(seq, ",nobarrier");
return 0;
}
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index a513d2d36be9..4cf2024b87da 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -131,9 +131,10 @@ static int hfsplus_system_write_inode(struct inode *inode)
hfsplus_inode_write_fork(inode, fork);
if (tree) {
int err = hfs_btree_write(tree);
+
if (err) {
pr_err("b-tree write err: %d, ino %lu\n",
- err, inode->i_ino);
+ err, inode->i_ino);
return err;
}
}
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 3f999649587f..cc6235671437 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -24,8 +24,8 @@ struct hfsplus_wd {
u16 embed_count;
};
-/*
- * hfsplus_submit_bio - Perfrom block I/O
+/**
+ * hfsplus_submit_bio - Perform block I/O
* @sb: super block of volume for I/O
* @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
* @buf: buffer for I/O
@@ -231,10 +231,8 @@ reread:
if (blocksize < HFSPLUS_SECTOR_SIZE || ((blocksize - 1) & blocksize))
goto out_free_backup_vhdr;
sbi->alloc_blksz = blocksize;
- sbi->alloc_blksz_shift = 0;
- while ((blocksize >>= 1) != 0)
- sbi->alloc_blksz_shift++;
- blocksize = min(sbi->alloc_blksz, (u32)PAGE_SIZE);
+ sbi->alloc_blksz_shift = ilog2(blocksize);
+ blocksize = min_t(u32, sbi->alloc_blksz, PAGE_SIZE);
/*
* Align block size to block offset.
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index 4e27edc082a4..d98094a9f476 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -8,6 +8,7 @@
#include "hfsplus_fs.h"
#include <linux/posix_acl_xattr.h>
+#include <linux/nls.h>
#include "xattr.h"
#include "acl.h"
@@ -66,10 +67,10 @@ static void hfsplus_init_header_node(struct inode *attr_file,
char *bmp;
u32 used_nodes;
u32 used_bmp_bytes;
- loff_t tmp;
+ u64 tmp;
hfs_dbg(ATTR_MOD, "init_hdr_attr_file: clump %u, node_size %u\n",
- clump_size, node_size);
+ clump_size, node_size);
/* The end of the node contains list of record offsets */
rec_offsets = (__be16 *)(buf + node_size);
@@ -195,7 +196,7 @@ check_attr_tree_state_again:
}
while (hip->alloc_blocks < hip->clump_blocks) {
- err = hfsplus_file_extend(attr_file);
+ err = hfsplus_file_extend(attr_file, false);
if (unlikely(err)) {
pr_err("failed to extend attributes file\n");
goto end_attr_file_creation;
@@ -645,8 +646,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
struct hfs_find_data fd;
u16 key_len = 0;
struct hfsplus_attr_key attr_key;
- char strbuf[HFSPLUS_ATTR_MAX_STRLEN +
- XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ char *strbuf;
int xattr_name_len;
if ((!S_ISREG(inode->i_mode) &&
@@ -666,6 +666,13 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
return err;
}
+ strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
+ if (!strbuf) {
+ res = -ENOMEM;
+ goto out;
+ }
+
err = hfsplus_find_attr(inode->i_sb, inode->i_ino, NULL, &fd);
if (err) {
if (err == -ENOENT) {
@@ -692,7 +699,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
if (be32_to_cpu(attr_key.cnid) != inode->i_ino)
goto end_listxattr;
- xattr_name_len = HFSPLUS_ATTR_MAX_STRLEN;
+ xattr_name_len = NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN;
if (hfsplus_uni2asc(inode->i_sb,
(const struct hfsplus_unistr *)&fd.key->attr.key_name,
strbuf, &xattr_name_len)) {
@@ -718,6 +725,8 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
}
end_listxattr:
+ kfree(strbuf);
+out:
hfs_find_exit(&fd);
return res;
}
@@ -797,47 +806,55 @@ end_removexattr:
static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN +
- XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
/*
* Don't allow retrieving properly prefixed attributes
* by prepending them with "osx."
*/
if (is_known_namespace(name))
return -EOPNOTSUPP;
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN
+ + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
+ strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
+ strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
- return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ res = hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ kfree(xattr_name);
+ return res;
}
static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
const void *buffer, size_t size, int flags, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN +
- XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
/*
* Don't allow setting properly prefixed attributes
* by prepending them with "osx."
*/
if (is_known_namespace(name))
return -EOPNOTSUPP;
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN
+ + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
+ strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
+ strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
- return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ kfree(xattr_name);
+ return res;
}
static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list,
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
index 00722765ea79..6ec5e107691f 100644
--- a/fs/hfsplus/xattr_security.c
+++ b/fs/hfsplus/xattr_security.c
@@ -7,6 +7,8 @@
*/
#include <linux/security.h>
+#include <linux/nls.h>
+
#include "hfsplus_fs.h"
#include "xattr.h"
#include "acl.h"
@@ -14,37 +16,43 @@
static int hfsplus_security_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
strcpy(xattr_name, XATTR_SECURITY_PREFIX);
strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name);
- return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ res = hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ kfree(xattr_name);
+ return res;
}
static int hfsplus_security_setxattr(struct dentry *dentry, const char *name,
const void *buffer, size_t size, int flags, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
strcpy(xattr_name, XATTR_SECURITY_PREFIX);
strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name);
- return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ kfree(xattr_name);
+ return res;
}
static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list,
@@ -62,31 +70,30 @@ static int hfsplus_initxattrs(struct inode *inode,
void *fs_info)
{
const struct xattr *xattr;
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t xattr_name_len;
+ char *xattr_name;
int err = 0;
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
- xattr_name_len = strlen(xattr->name);
- if (xattr_name_len == 0)
+ if (!strcmp(xattr->name, ""))
continue;
- if (xattr_name_len + XATTR_SECURITY_PREFIX_LEN >
- HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
strcpy(xattr_name, XATTR_SECURITY_PREFIX);
strcpy(xattr_name +
XATTR_SECURITY_PREFIX_LEN, xattr->name);
memset(xattr_name +
- XATTR_SECURITY_PREFIX_LEN + xattr_name_len, 0, 1);
+ XATTR_SECURITY_PREFIX_LEN + strlen(xattr->name), 0, 1);
err = __hfsplus_setxattr(inode, xattr_name,
xattr->value, xattr->value_len, 0);
if (err)
break;
}
+ kfree(xattr_name);
return err;
}
diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c
index 426cee277542..3c5f27e4746a 100644
--- a/fs/hfsplus/xattr_trusted.c
+++ b/fs/hfsplus/xattr_trusted.c
@@ -6,43 +6,51 @@
* Handler for trusted extended attributes.
*/
+#include <linux/nls.h>
+
#include "hfsplus_fs.h"
#include "xattr.h"
static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
strcpy(xattr_name, XATTR_TRUSTED_PREFIX);
strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name);
- return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ res = hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ kfree(xattr_name);
+ return res;
}
static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name,
const void *buffer, size_t size, int flags, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
strcpy(xattr_name, XATTR_TRUSTED_PREFIX);
strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name);
- return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ kfree(xattr_name);
+ return res;
}
static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list,
diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c
index e34016561ae0..2b625a538b64 100644
--- a/fs/hfsplus/xattr_user.c
+++ b/fs/hfsplus/xattr_user.c
@@ -6,43 +6,51 @@
* Handler for user extended attributes.
*/
+#include <linux/nls.h>
+
#include "hfsplus_fs.h"
#include "xattr.h"
static int hfsplus_user_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
strcpy(xattr_name, XATTR_USER_PREFIX);
strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name);
- return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ res = hfsplus_getxattr(dentry, xattr_name, buffer, size);
+ kfree(xattr_name);
+ return res;
}
static int hfsplus_user_setxattr(struct dentry *dentry, const char *name,
const void *buffer, size_t size, int flags, int type)
{
- char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
- size_t len = strlen(name);
+ char *xattr_name;
+ int res;
if (!strcmp(name, ""))
return -EINVAL;
- if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
- return -EOPNOTSUPP;
-
+ xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
+ GFP_KERNEL);
+ if (!xattr_name)
+ return -ENOMEM;
strcpy(xattr_name, XATTR_USER_PREFIX);
strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name);
- return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+ kfree(xattr_name);
+ return res;
}
static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list,
diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c
index 58b5106186d0..f005046e1591 100644
--- a/fs/hpfs/alloc.c
+++ b/fs/hpfs/alloc.c
@@ -316,7 +316,7 @@ void hpfs_free_sectors(struct super_block *s, secno sec, unsigned n)
struct quad_buffer_head qbh;
__le32 *bmp;
struct hpfs_sb_info *sbi = hpfs_sb(s);
- /*printk("2 - ");*/
+ /*pr_info("2 - ");*/
if (!n) return;
if (sec < 0x12) {
hpfs_error(s, "Trying to free reserved sector %08x", sec);
diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c
index 139ef1684d07..8057fe4e6574 100644
--- a/fs/hpfs/buffer.c
+++ b/fs/hpfs/buffer.c
@@ -55,7 +55,7 @@ void *hpfs_map_sector(struct super_block *s, unsigned secno, struct buffer_head
if (bh != NULL)
return bh->b_data;
else {
- printk("HPFS: hpfs_map_sector: read error\n");
+ pr_err("%s(): read error\n", __func__);
return NULL;
}
}
@@ -76,7 +76,7 @@ void *hpfs_get_sector(struct super_block *s, unsigned secno, struct buffer_head
set_buffer_uptodate(bh);
return bh->b_data;
} else {
- printk("HPFS: hpfs_get_sector: getblk failed\n");
+ pr_err("%s(): getblk failed\n", __func__);
return NULL;
}
}
@@ -93,7 +93,7 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe
cond_resched();
if (secno & 3) {
- printk("HPFS: hpfs_map_4sectors: unaligned read\n");
+ pr_err("%s(): unaligned read\n", __func__);
return NULL;
}
@@ -112,7 +112,7 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe
qbh->data = data = kmalloc(2048, GFP_NOFS);
if (!data) {
- printk("HPFS: hpfs_map_4sectors: out of memory\n");
+ pr_err("%s(): out of memory\n", __func__);
goto bail4;
}
@@ -145,7 +145,7 @@ void *hpfs_get_4sectors(struct super_block *s, unsigned secno,
hpfs_lock_assert(s);
if (secno & 3) {
- printk("HPFS: hpfs_get_4sectors: unaligned read\n");
+ pr_err("%s(): unaligned read\n", __func__);
return NULL;
}
@@ -161,7 +161,7 @@ void *hpfs_get_4sectors(struct super_block *s, unsigned secno,
}
if (!(qbh->data = kmalloc(2048, GFP_NOFS))) {
- printk("HPFS: hpfs_get_4sectors: out of memory\n");
+ pr_err("%s(): out of memory\n", __func__);
goto bail4;
}
return qbh->data;
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 292b1acb9b81..2a8e07425de0 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -36,7 +36,7 @@ static loff_t hpfs_dir_lseek(struct file *filp, loff_t off, int whence)
mutex_lock(&i->i_mutex);
hpfs_lock(s);
- /*printk("dir lseek\n");*/
+ /*pr_info("dir lseek\n");*/
if (new_off == 0 || new_off == 1 || new_off == 11 || new_off == 12 || new_off == 13) goto ok;
pos = ((loff_t) hpfs_de_as_down_as_possible(s, hpfs_inode->i_dno) << 4) + 1;
while (pos != new_off) {
@@ -51,7 +51,7 @@ ok:
mutex_unlock(&i->i_mutex);
return new_off;
fail:
- /*printk("illegal lseek: %016llx\n", new_off);*/
+ /*pr_warn("illegal lseek: %016llx\n", new_off);*/
hpfs_unlock(s);
mutex_unlock(&i->i_mutex);
return -ESPIPE;
@@ -127,7 +127,7 @@ static int hpfs_readdir(struct file *file, struct dir_context *ctx)
if (ctx->pos == 12)
goto out;
if (ctx->pos == 3 || ctx->pos == 4 || ctx->pos == 5) {
- printk("HPFS: warning: pos==%d\n",(int)ctx->pos);
+ pr_err("pos==%d\n", (int)ctx->pos);
goto out;
}
if (ctx->pos == 0) {
diff --git a/fs/hpfs/dnode.c b/fs/hpfs/dnode.c
index 4364b2a02c5d..f36fc010fccb 100644
--- a/fs/hpfs/dnode.c
+++ b/fs/hpfs/dnode.c
@@ -17,7 +17,7 @@ static loff_t get_pos(struct dnode *d, struct hpfs_dirent *fde)
if (de == fde) return ((loff_t) le32_to_cpu(d->self) << 4) | (loff_t)i;
i++;
}
- printk("HPFS: get_pos: not_found\n");
+ pr_info("%s(): not_found\n", __func__);
return ((loff_t)le32_to_cpu(d->self) << 4) | (loff_t)1;
}
@@ -32,7 +32,7 @@ void hpfs_add_pos(struct inode *inode, loff_t *pos)
if (hpfs_inode->i_rddir_off[i] == pos) return;
if (!(i&0x0f)) {
if (!(ppos = kmalloc((i+0x11) * sizeof(loff_t*), GFP_NOFS))) {
- printk("HPFS: out of memory for position list\n");
+ pr_err("out of memory for position list\n");
return;
}
if (hpfs_inode->i_rddir_off) {
@@ -63,7 +63,8 @@ void hpfs_del_pos(struct inode *inode, loff_t *pos)
}
return;
not_f:
- /*printk("HPFS: warning: position pointer %p->%08x not found\n", pos, (int)*pos);*/
+ /*pr_warn("position pointer %p->%08x not found\n",
+ pos, (int)*pos);*/
return;
}
@@ -92,8 +93,11 @@ static void hpfs_pos_ins(loff_t *p, loff_t d, loff_t c)
{
if ((*p & ~0x3f) == (d & ~0x3f) && (*p & 0x3f) >= (d & 0x3f)) {
int n = (*p & 0x3f) + c;
- if (n > 0x3f) printk("HPFS: hpfs_pos_ins: %08x + %d\n", (int)*p, (int)c >> 8);
- else *p = (*p & ~0x3f) | n;
+ if (n > 0x3f)
+ pr_err("%s(): %08x + %d\n",
+ __func__, (int)*p, (int)c >> 8);
+ else
+ *p = (*p & ~0x3f) | n;
}
}
@@ -101,8 +105,11 @@ static void hpfs_pos_del(loff_t *p, loff_t d, loff_t c)
{
if ((*p & ~0x3f) == (d & ~0x3f) && (*p & 0x3f) >= (d & 0x3f)) {
int n = (*p & 0x3f) - c;
- if (n < 1) printk("HPFS: hpfs_pos_ins: %08x - %d\n", (int)*p, (int)c >> 8);
- else *p = (*p & ~0x3f) | n;
+ if (n < 1)
+ pr_err("%s(): %08x - %d\n",
+ __func__, (int)*p, (int)c >> 8);
+ else
+ *p = (*p & ~0x3f) | n;
}
}
@@ -239,12 +246,12 @@ static int hpfs_add_to_dnode(struct inode *i, dnode_secno dno,
struct fnode *fnode;
int c1, c2 = 0;
if (!(nname = kmalloc(256, GFP_NOFS))) {
- printk("HPFS: out of memory, can't add to dnode\n");
+ pr_err("out of memory, can't add to dnode\n");
return 1;
}
go_up:
if (namelen >= 256) {
- hpfs_error(i->i_sb, "hpfs_add_to_dnode: namelen == %d", namelen);
+ hpfs_error(i->i_sb, "%s(): namelen == %d", __func__, namelen);
kfree(nd);
kfree(nname);
return 1;
@@ -281,7 +288,7 @@ static int hpfs_add_to_dnode(struct inode *i, dnode_secno dno,
not be any error while splitting dnodes, otherwise the
whole directory, not only file we're adding, would
be lost. */
- printk("HPFS: out of memory for dnode splitting\n");
+ pr_err("out of memory for dnode splitting\n");
hpfs_brelse4(&qbh);
kfree(nname);
return 1;
@@ -597,7 +604,7 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno)
if (!de_next->down) goto endm;
ndown = de_down_pointer(de_next);
if (!(de_cp = kmalloc(le16_to_cpu(de->length), GFP_NOFS))) {
- printk("HPFS: out of memory for dtree balancing\n");
+ pr_err("out of memory for dtree balancing\n");
goto endm;
}
memcpy(de_cp, de, le16_to_cpu(de->length));
@@ -612,7 +619,8 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno)
hpfs_brelse4(&qbh1);
}
hpfs_add_to_dnode(i, ndown, de_cp->name, de_cp->namelen, de_cp, de_cp->down ? de_down_pointer(de_cp) : 0);
- /*printk("UP-TO-DNODE: %08x (ndown = %08x, down = %08x, dno = %08x)\n", up, ndown, down, dno);*/
+ /*pr_info("UP-TO-DNODE: %08x (ndown = %08x, down = %08x, dno = %08x)\n",
+ up, ndown, down, dno);*/
dno = up;
kfree(de_cp);
goto try_it_again;
@@ -637,15 +645,15 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno)
if (!dlp && down) {
if (le32_to_cpu(d1->first_free) > 2044) {
if (hpfs_sb(i->i_sb)->sb_chk >= 2) {
- printk("HPFS: warning: unbalanced dnode tree, see hpfs.txt 4 more info\n");
- printk("HPFS: warning: terminating balancing operation\n");
+ pr_err("unbalanced dnode tree, see hpfs.txt 4 more info\n");
+ pr_err("terminating balancing operation\n");
}
hpfs_brelse4(&qbh1);
goto endm;
}
if (hpfs_sb(i->i_sb)->sb_chk >= 2) {
- printk("HPFS: warning: unbalanced dnode tree, see hpfs.txt 4 more info\n");
- printk("HPFS: warning: goin'on\n");
+ pr_err("unbalanced dnode tree, see hpfs.txt 4 more info\n");
+ pr_err("goin'on\n");
}
le16_add_cpu(&del->length, 4);
del->down = 1;
@@ -659,7 +667,7 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno)
*(__le32 *) ((void *) del + le16_to_cpu(del->length) - 4) = cpu_to_le32(down);
} else goto endm;
if (!(de_cp = kmalloc(le16_to_cpu(de_prev->length), GFP_NOFS))) {
- printk("HPFS: out of memory for dtree balancing\n");
+ pr_err("out of memory for dtree balancing\n");
hpfs_brelse4(&qbh1);
goto endm;
}
@@ -1000,7 +1008,7 @@ struct hpfs_dirent *map_fnode_dirent(struct super_block *s, fnode_secno fno,
int d1, d2 = 0;
name1 = f->name;
if (!(name2 = kmalloc(256, GFP_NOFS))) {
- printk("HPFS: out of memory, can't map dirent\n");
+ pr_err("out of memory, can't map dirent\n");
return NULL;
}
if (f->len <= 15)
diff --git a/fs/hpfs/ea.c b/fs/hpfs/ea.c
index bcaafcd2666a..ce3f98ba993a 100644
--- a/fs/hpfs/ea.c
+++ b/fs/hpfs/ea.c
@@ -51,7 +51,7 @@ static char *get_indirect_ea(struct super_block *s, int ano, secno a, int size)
{
char *ret;
if (!(ret = kmalloc(size + 1, GFP_NOFS))) {
- printk("HPFS: out of memory for EA\n");
+ pr_err("out of memory for EA\n");
return NULL;
}
if (hpfs_ea_read(s, a, ano, 0, size, ret)) {
@@ -139,7 +139,7 @@ char *hpfs_get_ea(struct super_block *s, struct fnode *fnode, char *key, int *si
if (ea_indirect(ea))
return get_indirect_ea(s, ea_in_anode(ea), ea_sec(ea), *size = ea_len(ea));
if (!(ret = kmalloc((*size = ea_valuelen(ea)) + 1, GFP_NOFS))) {
- printk("HPFS: out of memory for EA\n");
+ pr_err("out of memory for EA\n");
return NULL;
}
memcpy(ret, ea_data(ea), ea_valuelen(ea));
@@ -165,7 +165,7 @@ char *hpfs_get_ea(struct super_block *s, struct fnode *fnode, char *key, int *si
if (ea_indirect(ea))
return get_indirect_ea(s, ea_in_anode(ea), ea_sec(ea), *size = ea_len(ea));
if (!(ret = kmalloc((*size = ea_valuelen(ea)) + 1, GFP_NOFS))) {
- printk("HPFS: out of memory for EA\n");
+ pr_err("out of memory for EA\n");
return NULL;
}
if (hpfs_ea_read(s, a, ano, pos + 4 + ea->namelen + 1, ea_valuelen(ea), ret)) {
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index 3ba49c080e42..b63b75fa00e7 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -8,6 +8,11 @@
//#define DBG
//#define DEBUG_LOCKS
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mutex.h>
#include <linux/pagemap.h>
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 50a427313835..7ce4b74234a1 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -183,7 +183,8 @@ void hpfs_write_inode(struct inode *i)
struct inode *parent;
if (i->i_ino == hpfs_sb(i->i_sb)->sb_root) return;
if (hpfs_inode->i_rddir_off && !atomic_read(&i->i_count)) {
- if (*hpfs_inode->i_rddir_off) printk("HPFS: write_inode: some position still there\n");
+ if (*hpfs_inode->i_rddir_off)
+ pr_err("write_inode: some position still there\n");
kfree(hpfs_inode->i_rddir_off);
hpfs_inode->i_rddir_off = NULL;
}
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index 3aa66ae1031e..442770edcdc7 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -65,12 +65,13 @@ unsigned char *hpfs_load_code_page(struct super_block *s, secno cps)
struct code_page_directory *cp = hpfs_map_sector(s, cps, &bh, 0);
if (!cp) return NULL;
if (le32_to_cpu(cp->magic) != CP_DIR_MAGIC) {
- printk("HPFS: Code page directory magic doesn't match (magic = %08x)\n", le32_to_cpu(cp->magic));
+ pr_err("Code page directory magic doesn't match (magic = %08x)\n",
+ le32_to_cpu(cp->magic));
brelse(bh);
return NULL;
}
if (!le32_to_cpu(cp->n_code_pages)) {
- printk("HPFS: n_code_pages == 0\n");
+ pr_err("n_code_pages == 0\n");
brelse(bh);
return NULL;
}
@@ -79,19 +80,19 @@ unsigned char *hpfs_load_code_page(struct super_block *s, secno cps)
brelse(bh);
if (cpi >= 3) {
- printk("HPFS: Code page index out of array\n");
+ pr_err("Code page index out of array\n");
return NULL;
}
if (!(cpd = hpfs_map_sector(s, cpds, &bh, 0))) return NULL;
if (le16_to_cpu(cpd->offs[cpi]) > 0x178) {
- printk("HPFS: Code page index out of sector\n");
+ pr_err("Code page index out of sector\n");
brelse(bh);
return NULL;
}
ptr = (unsigned char *)cpd + le16_to_cpu(cpd->offs[cpi]) + 6;
if (!(cp_table = kmalloc(256, GFP_KERNEL))) {
- printk("HPFS: out of memory for code page table\n");
+ pr_err("out of memory for code page table\n");
brelse(bh);
return NULL;
}
@@ -114,7 +115,7 @@ __le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp)
int i;
__le32 *b;
if (!(b = kmalloc(n * 512, GFP_KERNEL))) {
- printk("HPFS: can't allocate memory for bitmap directory\n");
+ pr_err("can't allocate memory for bitmap directory\n");
return NULL;
}
for (i=0;i<n;i++) {
@@ -281,7 +282,9 @@ struct dnode *hpfs_map_dnode(struct super_block *s, unsigned secno,
hpfs_error(s, "dnode %08x does not end with \\377 entry", secno);
goto bail;
}
- if (b == 3) printk("HPFS: warning: unbalanced dnode tree, dnode %08x; see hpfs.txt 4 more info\n", secno);
+ if (b == 3)
+ pr_err("unbalanced dnode tree, dnode %08x; see hpfs.txt 4 more info\n",
+ secno);
}
return dnode;
bail:
diff --git a/fs/hpfs/name.c b/fs/hpfs/name.c
index 9acdf338def0..b00d396d22c6 100644
--- a/fs/hpfs/name.c
+++ b/fs/hpfs/name.c
@@ -56,14 +56,15 @@ unsigned char *hpfs_translate_name(struct super_block *s, unsigned char *from,
unsigned char *to;
int i;
if (hpfs_sb(s)->sb_chk >= 2) if (hpfs_is_name_long(from, len) != lng) {
- printk("HPFS: Long name flag mismatch - name ");
- for (i=0; i<len; i++) printk("%c", from[i]);
- printk(" misidentified as %s.\n", lng ? "short" : "long");
- printk("HPFS: It's nothing serious. It could happen because of bug in OS/2.\nHPFS: Set checks=normal to disable this message.\n");
+ pr_err("Long name flag mismatch - name ");
+ for (i = 0; i < len; i++)
+ pr_cont("%c", from[i]);
+ pr_cont(" misidentified as %s.\n", lng ? "short" : "long");
+ pr_err("It's nothing serious. It could happen because of bug in OS/2.\nSet checks=normal to disable this message.\n");
}
if (!lc) return from;
if (!(to = kmalloc(len, GFP_KERNEL))) {
- printk("HPFS: can't allocate memory for name conversion buffer\n");
+ pr_err("can't allocate memory for name conversion buffer\n");
return from;
}
for (i = 0; i < len; i++) to[i] = locase(hpfs_sb(s)->sb_cp_table,from[i]);
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 1b39afdd86fd..bdbc2c3080a4 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -404,7 +404,7 @@ again:
d_rehash(dentry);
} else {
struct iattr newattrs;
- /*printk("HPFS: truncating file before delete.\n");*/
+ /*pr_info("truncating file before delete.\n");*/
newattrs.ia_size = 0;
newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
err = notify_change(dentry, &newattrs, NULL);
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index fe3463a43236..7cd00d3a7c9b 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -62,22 +62,26 @@ void hpfs_error(struct super_block *s, const char *fmt, ...)
vsnprintf(err_buf, sizeof(err_buf), fmt, args);
va_end(args);
- printk("HPFS: filesystem error: %s", err_buf);
+ pr_err("filesystem error: %s", err_buf);
if (!hpfs_sb(s)->sb_was_error) {
if (hpfs_sb(s)->sb_err == 2) {
- printk("; crashing the system because you wanted it\n");
+ pr_cont("; crashing the system because you wanted it\n");
mark_dirty(s, 0);
panic("HPFS panic");
} else if (hpfs_sb(s)->sb_err == 1) {
- if (s->s_flags & MS_RDONLY) printk("; already mounted read-only\n");
+ if (s->s_flags & MS_RDONLY)
+ pr_cont("; already mounted read-only\n");
else {
- printk("; remounting read-only\n");
+ pr_cont("; remounting read-only\n");
mark_dirty(s, 0);
s->s_flags |= MS_RDONLY;
}
- } else if (s->s_flags & MS_RDONLY) printk("; going on - but anything won't be destroyed because it's read-only\n");
- else printk("; corrupted filesystem mounted read/write - your computer will explode within 20 seconds ... but you wanted it so!\n");
- } else printk("\n");
+ } else if (s->s_flags & MS_RDONLY)
+ pr_cont("; going on - but anything won't be destroyed because it's read-only\n");
+ else
+ pr_cont("; corrupted filesystem mounted read/write - your computer will explode within 20 seconds ... but you wanted it so!\n");
+ } else
+ pr_cont("\n");
hpfs_sb(s)->sb_was_error = 1;
}
@@ -292,7 +296,7 @@ static int parse_opts(char *opts, kuid_t *uid, kgid_t *gid, umode_t *umask,
if (!opts)
return 1;
- /*printk("Parsing opts: '%s'\n",opts);*/
+ /*pr_info("Parsing opts: '%s'\n",opts);*/
while ((p = strsep(&opts, ",")) != NULL) {
substring_t args[MAX_OPT_ARGS];
@@ -387,7 +391,7 @@ static int parse_opts(char *opts, kuid_t *uid, kgid_t *gid, umode_t *umask,
static inline void hpfs_help(void)
{
- printk("\n\
+ pr_info("\n\
HPFS filesystem options:\n\
help do not mount and display this text\n\
uid=xxx set uid of files that don't have uid specified in eas\n\
@@ -434,7 +438,7 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
if (!(o = parse_opts(data, &uid, &gid, &umask, &lowercase,
&eas, &chk, &errs, &chkdsk, &timeshift))) {
- printk("HPFS: bad mount options.\n");
+ pr_err("bad mount options.\n");
goto out_err;
}
if (o == 2) {
@@ -442,7 +446,7 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
goto out_err;
}
if (timeshift != sbi->sb_timeshift) {
- printk("HPFS: timeshift can't be changed using remount.\n");
+ pr_err("timeshift can't be changed using remount.\n");
goto out_err;
}
@@ -523,7 +527,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
if (!(o = parse_opts(options, &uid, &gid, &umask, &lowercase,
&eas, &chk, &errs, &chkdsk, &timeshift))) {
- printk("HPFS: bad mount options.\n");
+ pr_err("bad mount options.\n");
goto bail0;
}
if (o==2) {
@@ -542,16 +546,17 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
if (/*le16_to_cpu(bootblock->magic) != BB_MAGIC
||*/ le32_to_cpu(superblock->magic) != SB_MAGIC
|| le32_to_cpu(spareblock->magic) != SP_MAGIC) {
- if (!silent) printk("HPFS: Bad magic ... probably not HPFS\n");
+ if (!silent)
+ pr_err("Bad magic ... probably not HPFS\n");
goto bail4;
}
/* Check version */
if (!(s->s_flags & MS_RDONLY) &&
superblock->funcversion != 2 && superblock->funcversion != 3) {
- printk("HPFS: Bad version %d,%d. Mount readonly to go around\n",
+ pr_err("Bad version %d,%d. Mount readonly to go around\n",
(int)superblock->version, (int)superblock->funcversion);
- printk("HPFS: please try recent version of HPFS driver at http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi and if it still can't understand this format, contact author - mikulas@artax.karlin.mff.cuni.cz\n");
+ pr_err("please try recent version of HPFS driver at http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi and if it still can't understand this format, contact author - mikulas@artax.karlin.mff.cuni.cz\n");
goto bail4;
}
@@ -597,7 +602,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
/* Check for general fs errors*/
if (spareblock->dirty && !spareblock->old_wrote) {
if (errs == 2) {
- printk("HPFS: Improperly stopped, not mounted\n");
+ pr_err("Improperly stopped, not mounted\n");
goto bail4;
}
hpfs_error(s, "improperly stopped");
@@ -611,22 +616,25 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
if (spareblock->hotfixes_used || spareblock->n_spares_used) {
if (errs >= 2) {
- printk("HPFS: Hotfixes not supported here, try chkdsk\n");
+ pr_err("Hotfixes not supported here, try chkdsk\n");
mark_dirty(s, 0);
goto bail4;
}
hpfs_error(s, "hotfixes not supported here, try chkdsk");
- if (errs == 0) printk("HPFS: Proceeding, but your filesystem will be probably corrupted by this driver...\n");
- else printk("HPFS: This driver may read bad files or crash when operating on disk with hotfixes.\n");
+ if (errs == 0)
+ pr_err("Proceeding, but your filesystem will be probably corrupted by this driver...\n");
+ else
+ pr_err("This driver may read bad files or crash when operating on disk with hotfixes.\n");
}
if (le32_to_cpu(spareblock->n_dnode_spares) != le32_to_cpu(spareblock->n_dnode_spares_free)) {
if (errs >= 2) {
- printk("HPFS: Spare dnodes used, try chkdsk\n");
+ pr_err("Spare dnodes used, try chkdsk\n");
mark_dirty(s, 0);
goto bail4;
}
hpfs_error(s, "warning: spare dnodes used, try chkdsk");
- if (errs == 0) printk("HPFS: Proceeding, but your filesystem could be corrupted if you delete files or directories\n");
+ if (errs == 0)
+ pr_err("Proceeding, but your filesystem could be corrupted if you delete files or directories\n");
}
if (chk) {
unsigned a;
@@ -645,12 +653,13 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
goto bail4;
}
sbi->sb_dirband_size = a;
- } else printk("HPFS: You really don't want any checks? You are crazy...\n");
+ } else
+ pr_err("You really don't want any checks? You are crazy...\n");
/* Load code page table */
if (le32_to_cpu(spareblock->n_code_pages))
if (!(sbi->sb_cp_table = hpfs_load_code_page(s, le32_to_cpu(spareblock->code_page_dir))))
- printk("HPFS: Warning: code page support is disabled\n");
+ pr_err("code page support is disabled\n");
brelse(bh2);
brelse(bh1);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e19d4c0cacae..1e2872b25343 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -6,6 +6,8 @@
* Copyright (C) 2002 Linus Torvalds.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/thread_info.h>
#include <asm/current.h>
@@ -475,7 +477,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
* annotation because huge_pmd_share() does an allocation under
* i_mmap_mutex.
*/
-struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+static struct lock_class_key hugetlbfs_i_mmap_mutex_key;
static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct inode *dir,
@@ -823,8 +825,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
ps = memparse(args[0].from, &rest);
pconfig->hstate = size_to_hstate(ps);
if (!pconfig->hstate) {
- printk(KERN_ERR
- "hugetlbfs: Unsupported page size %lu MB\n",
+ pr_err("Unsupported page size %lu MB\n",
ps >> 20);
return -EINVAL;
}
@@ -832,8 +833,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
}
default:
- printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
- p);
+ pr_err("Bad mount option: \"%s\"\n", p);
return -EINVAL;
break;
}
@@ -853,8 +853,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
return 0;
bad_val:
- printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
- args[0].from, p);
+ pr_err("Bad value '%s' for mount option '%s'\n", args[0].from, p);
return -EINVAL;
}
@@ -902,8 +901,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
goto out_free;
return 0;
out_free:
- if (sbinfo->spool)
- kfree(sbinfo->spool);
+ kfree(sbinfo->spool);
kfree(sbinfo);
return -ENOMEM;
}
@@ -939,7 +937,7 @@ static int get_hstate_idx(int page_size_log)
return h - hstates;
}
-static struct dentry_operations anon_ops = {
+static const struct dentry_operations anon_ops = {
.d_dname = simple_dname
};
@@ -970,8 +968,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
*user = current_user();
if (user_shm_lock(size, *user)) {
task_lock(current);
- printk_once(KERN_WARNING
- "%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+ pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
current->comm, current->pid);
task_unlock(current);
} else {
@@ -1031,7 +1028,7 @@ static int __init init_hugetlbfs_fs(void)
int i;
if (!hugepages_supported()) {
- pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n");
+ pr_info("disabling because there are no supported hugepage sizes\n");
return -ENOTSUPP;
}
@@ -1060,7 +1057,7 @@ static int __init init_hugetlbfs_fs(void)
buf);
if (IS_ERR(hugetlbfs_vfsmount[i])) {
- pr_err("hugetlb: Cannot mount internal hugetlbfs for "
+ pr_err("Cannot mount internal hugetlbfs for "
"page size %uK", ps_kb);
error = PTR_ERR(hugetlbfs_vfsmount[i]);
hugetlbfs_vfsmount[i] = NULL;
diff --git a/fs/inode.c b/fs/inode.c
index f96d2a6f88cc..6eecb7ff0b9a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -105,7 +105,7 @@ long get_nr_dirty_inodes(void)
* Handle nr_inode sysctl
*/
#ifdef CONFIG_SYSCTL
-int proc_nr_inodes(ctl_table *table, int write,
+int proc_nr_inodes(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
inodes_stat.nr_inodes = get_nr_inodes();
@@ -1839,14 +1839,18 @@ EXPORT_SYMBOL(inode_init_owner);
* inode_owner_or_capable - check current task permissions to inode
* @inode: inode being checked
*
- * Return true if current either has CAP_FOWNER to the inode, or
- * owns the file.
+ * Return true if current either has CAP_FOWNER in a namespace with the
+ * inode owner uid mapped, or owns the file.
*/
bool inode_owner_or_capable(const struct inode *inode)
{
+ struct user_namespace *ns;
+
if (uid_eq(current_fsuid(), inode->i_uid))
return true;
- if (inode_capable(inode, CAP_FOWNER))
+
+ ns = current_user_ns();
+ if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
return true;
return false;
}
diff --git a/fs/ioprio.c b/fs/ioprio.c
deleted file mode 100644
index e50170ca7c33..000000000000
--- a/fs/ioprio.c
+++ /dev/null
@@ -1,241 +0,0 @@
-/*
- * fs/ioprio.c
- *
- * Copyright (C) 2004 Jens Axboe <axboe@kernel.dk>
- *
- * Helper functions for setting/querying io priorities of processes. The
- * system calls closely mimmick getpriority/setpriority, see the man page for
- * those. The prio argument is a composite of prio class and prio data, where
- * the data argument has meaning within that class. The standard scheduling
- * classes have 8 distinct prio levels, with 0 being the highest prio and 7
- * being the lowest.
- *
- * IOW, setting BE scheduling class with prio 2 is done ala:
- *
- * unsigned int prio = (IOPRIO_CLASS_BE << IOPRIO_CLASS_SHIFT) | 2;
- *
- * ioprio_set(PRIO_PROCESS, pid, prio);
- *
- * See also Documentation/block/ioprio.txt
- *
- */
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/ioprio.h>
-#include <linux/blkdev.h>
-#include <linux/capability.h>
-#include <linux/syscalls.h>
-#include <linux/security.h>
-#include <linux/pid_namespace.h>
-
-int set_task_ioprio(struct task_struct *task, int ioprio)
-{
- int err;
- struct io_context *ioc;
- const struct cred *cred = current_cred(), *tcred;
-
- rcu_read_lock();
- tcred = __task_cred(task);
- if (!uid_eq(tcred->uid, cred->euid) &&
- !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
- rcu_read_unlock();
- return -EPERM;
- }
- rcu_read_unlock();
-
- err = security_task_setioprio(task, ioprio);
- if (err)
- return err;
-
- ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
- if (ioc) {
- ioc->ioprio = ioprio;
- put_io_context(ioc);
- }
-
- return err;
-}
-EXPORT_SYMBOL_GPL(set_task_ioprio);
-
-SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
-{
- int class = IOPRIO_PRIO_CLASS(ioprio);
- int data = IOPRIO_PRIO_DATA(ioprio);
- struct task_struct *p, *g;
- struct user_struct *user;
- struct pid *pgrp;
- kuid_t uid;
- int ret;
-
- switch (class) {
- case IOPRIO_CLASS_RT:
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- /* fall through, rt has prio field too */
- case IOPRIO_CLASS_BE:
- if (data >= IOPRIO_BE_NR || data < 0)
- return -EINVAL;
-
- break;
- case IOPRIO_CLASS_IDLE:
- break;
- case IOPRIO_CLASS_NONE:
- if (data)
- return -EINVAL;
- break;
- default:
- return -EINVAL;
- }
-
- ret = -ESRCH;
- rcu_read_lock();
- switch (which) {
- case IOPRIO_WHO_PROCESS:
- if (!who)
- p = current;
- else
- p = find_task_by_vpid(who);
- if (p)
- ret = set_task_ioprio(p, ioprio);
- break;
- case IOPRIO_WHO_PGRP:
- if (!who)
- pgrp = task_pgrp(current);
- else
- pgrp = find_vpid(who);
- do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
- ret = set_task_ioprio(p, ioprio);
- if (ret)
- break;
- } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
- break;
- case IOPRIO_WHO_USER:
- uid = make_kuid(current_user_ns(), who);
- if (!uid_valid(uid))
- break;
- if (!who)
- user = current_user();
- else
- user = find_user(uid);
-
- if (!user)
- break;
-
- do_each_thread(g, p) {
- if (!uid_eq(task_uid(p), uid))
- continue;
- ret = set_task_ioprio(p, ioprio);
- if (ret)
- goto free_uid;
- } while_each_thread(g, p);
-free_uid:
- if (who)
- free_uid(user);
- break;
- default:
- ret = -EINVAL;
- }
-
- rcu_read_unlock();
- return ret;
-}
-
-static int get_task_ioprio(struct task_struct *p)
-{
- int ret;
-
- ret = security_task_getioprio(p);
- if (ret)
- goto out;
- ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
- if (p->io_context)
- ret = p->io_context->ioprio;
-out:
- return ret;
-}
-
-int ioprio_best(unsigned short aprio, unsigned short bprio)
-{
- unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
- unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
-
- if (aclass == IOPRIO_CLASS_NONE)
- aclass = IOPRIO_CLASS_BE;
- if (bclass == IOPRIO_CLASS_NONE)
- bclass = IOPRIO_CLASS_BE;
-
- if (aclass == bclass)
- return min(aprio, bprio);
- if (aclass > bclass)
- return bprio;
- else
- return aprio;
-}
-
-SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
-{
- struct task_struct *g, *p;
- struct user_struct *user;
- struct pid *pgrp;
- kuid_t uid;
- int ret = -ESRCH;
- int tmpio;
-
- rcu_read_lock();
- switch (which) {
- case IOPRIO_WHO_PROCESS:
- if (!who)
- p = current;
- else
- p = find_task_by_vpid(who);
- if (p)
- ret = get_task_ioprio(p);
- break;
- case IOPRIO_WHO_PGRP:
- if (!who)
- pgrp = task_pgrp(current);
- else
- pgrp = find_vpid(who);
- do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
- tmpio = get_task_ioprio(p);
- if (tmpio < 0)
- continue;
- if (ret == -ESRCH)
- ret = tmpio;
- else
- ret = ioprio_best(ret, tmpio);
- } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
- break;
- case IOPRIO_WHO_USER:
- uid = make_kuid(current_user_ns(), who);
- if (!who)
- user = current_user();
- else
- user = find_user(uid);
-
- if (!user)
- break;
-
- do_each_thread(g, p) {
- if (!uid_eq(task_uid(p), user->uid))
- continue;
- tmpio = get_task_ioprio(p);
- if (tmpio < 0)
- continue;
- if (ret == -ESRCH)
- ret = tmpio;
- else
- ret = ioprio_best(ret, tmpio);
- } while_each_thread(g, p);
-
- if (who)
- free_uid(user);
- break;
- default:
- ret = -EINVAL;
- }
-
- rcu_read_unlock();
- return ret;
-}
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 5f26139a165a..6fac74349856 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -43,7 +43,7 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
clear_buffer_uptodate(bh);
if (orig_bh) {
clear_bit_unlock(BH_Shadow, &orig_bh->b_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&orig_bh->b_state, BH_Shadow);
}
unlock_buffer(bh);
@@ -239,7 +239,7 @@ static int journal_submit_data_buffers(journal_t *journal,
spin_lock(&journal->j_list_lock);
J_ASSERT(jinode->i_transaction == commit_transaction);
clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
spin_unlock(&journal->j_list_lock);
@@ -277,7 +277,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
}
spin_lock(&journal->j_list_lock);
clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index 2b60ce1996aa..bb9cebc9ca8a 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -75,10 +75,13 @@ void jffs2_stop_garbage_collect_thread(struct jffs2_sb_info *c)
static int jffs2_garbage_collect_thread(void *_c)
{
struct jffs2_sb_info *c = _c;
+ sigset_t hupmask;
+ siginitset(&hupmask, sigmask(SIGHUP));
allow_signal(SIGKILL);
allow_signal(SIGSTOP);
allow_signal(SIGCONT);
+ allow_signal(SIGHUP);
c->gc_task = current;
complete(&c->gc_thread_start);
@@ -87,7 +90,7 @@ static int jffs2_garbage_collect_thread(void *_c)
set_freezable();
for (;;) {
- allow_signal(SIGHUP);
+ sigprocmask(SIG_UNBLOCK, &hupmask, NULL);
again:
spin_lock(&c->erase_completion_lock);
if (!jffs2_thread_should_wake(c)) {
@@ -95,10 +98,9 @@ static int jffs2_garbage_collect_thread(void *_c)
spin_unlock(&c->erase_completion_lock);
jffs2_dbg(1, "%s(): sleeping...\n", __func__);
schedule();
- } else
+ } else {
spin_unlock(&c->erase_completion_lock);
-
-
+ }
/* Problem - immediately after bootup, the GCD spends a lot
* of time in places like jffs2_kill_fragtree(); so much so
* that userspace processes (like gdm and X) are starved
@@ -150,7 +152,7 @@ static int jffs2_garbage_collect_thread(void *_c)
}
}
/* We don't want SIGHUP to interrupt us. STOP and KILL are OK though. */
- disallow_signal(SIGHUP);
+ sigprocmask(SIG_BLOCK, &hupmask, NULL);
jffs2_dbg(1, "%s(): pass\n", __func__);
if (jffs2_garbage_collect_pass(c) == -ENOSPC) {
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 5a8ea16eedbc..0c8ca830b113 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -83,13 +83,15 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = POSIX_ACL_XATTR_ACCESS;
- rc = posix_acl_equiv_mode(acl, &inode->i_mode);
- if (rc < 0)
- return rc;
- inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
- if (rc == 0)
- acl = NULL;
+ if (acl) {
+ rc = posix_acl_equiv_mode(acl, &inode->i_mode);
+ if (rc < 0)
+ return rc;
+ inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
+ if (rc == 0)
+ acl = NULL;
+ }
break;
case ACL_TYPE_DEFAULT:
ea_name = POSIX_ACL_XATTR_DEFAULT;
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 370d7b6c5942..2d514c7affc2 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -1208,7 +1208,7 @@ static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno,
* by this leaf.
*/
l2size =
- min((int)leaf[word], NLSTOL2BSZ(nwords));
+ min_t(int, leaf[word], NLSTOL2BSZ(nwords));
/* determine how many words were handled.
*/
@@ -1902,7 +1902,7 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results)
/* determine how many blocks to allocate from this dmap.
*/
- nb = min(n, (s64)BPERDMAP);
+ nb = min_t(s64, n, BPERDMAP);
/* allocate the blocks from the dmap.
*/
@@ -2260,7 +2260,8 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
* of bits being allocated and the l2 number
* of bits currently described by this leaf.
*/
- size = min((int)leaf[word], NLSTOL2BSZ(nwords));
+ size = min_t(int, leaf[word],
+ NLSTOL2BSZ(nwords));
/* update the leaf to reflect the allocation.
* in addition to setting the leaf value to
@@ -3563,7 +3564,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks)
if (mp == NULL)
goto errout;
- n = min(nblocks, (s64)BPERDMAP);
+ n = min_t(s64, nblocks, BPERDMAP);
}
dp = (struct dmap *) mp->data;
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 7f464c513ba0..6b0f816201a2 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -29,20 +29,20 @@
void jfs_set_inode_flags(struct inode *inode)
{
unsigned int flags = JFS_IP(inode)->mode2;
-
- inode->i_flags &= ~(S_IMMUTABLE | S_APPEND |
- S_NOATIME | S_DIRSYNC | S_SYNC);
+ unsigned int new_fl = 0;
if (flags & JFS_IMMUTABLE_FL)
- inode->i_flags |= S_IMMUTABLE;
+ new_fl |= S_IMMUTABLE;
if (flags & JFS_APPEND_FL)
- inode->i_flags |= S_APPEND;
+ new_fl |= S_APPEND;
if (flags & JFS_NOATIME_FL)
- inode->i_flags |= S_NOATIME;
+ new_fl |= S_NOATIME;
if (flags & JFS_DIRSYNC_FL)
- inode->i_flags |= S_DIRSYNC;
+ new_fl |= S_DIRSYNC;
if (flags & JFS_SYNC_FL)
- inode->i_flags |= S_SYNC;
+ new_fl |= S_SYNC;
+ inode_set_flags(inode, new_fl, S_IMMUTABLE | S_APPEND | S_NOATIME |
+ S_DIRSYNC | S_SYNC);
}
void jfs_get_inode_flags(struct jfs_inode_info *jfs_ip)
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 8d811e02b4b9..0acddf60af55 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -167,7 +167,7 @@ do { \
* Global list of active external journals
*/
static LIST_HEAD(jfs_external_logs);
-static struct jfs_log *dummy_log = NULL;
+static struct jfs_log *dummy_log;
static DEFINE_MUTEX(jfs_log_mutex);
/*
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 97f7fda51890..adf8cb045b9e 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -50,14 +50,14 @@ MODULE_DESCRIPTION("The Journaled Filesystem (JFS)");
MODULE_AUTHOR("Steve Best/Dave Kleikamp/Barry Arndt, IBM");
MODULE_LICENSE("GPL");
-static struct kmem_cache * jfs_inode_cachep;
+static struct kmem_cache *jfs_inode_cachep;
static const struct super_operations jfs_super_operations;
static const struct export_operations jfs_export_operations;
static struct file_system_type jfs_fs_type;
#define MAX_COMMIT_THREADS 64
-static int commit_threads = 0;
+static int commit_threads;
module_param(commit_threads, int, 0);
MODULE_PARM_DESC(commit_threads, "Number of commit threads");
@@ -84,8 +84,7 @@ static void jfs_handle_error(struct super_block *sb)
panic("JFS (device %s): panic forced after error\n",
sb->s_id);
else if (sbi->flag & JFS_ERR_REMOUNT_RO) {
- jfs_err("ERROR: (device %s): remounting filesystem "
- "as read-only\n",
+ jfs_err("ERROR: (device %s): remounting filesystem as read-only\n",
sb->s_id);
sb->s_flags |= MS_RDONLY;
}
@@ -273,7 +272,10 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
case Opt_resize:
{
char *resize = args[0].from;
- *newLVSize = simple_strtoull(resize, &resize, 0);
+ int rc = kstrtoll(resize, 0, newLVSize);
+
+ if (rc)
+ goto cleanup;
break;
}
case Opt_resize_nosize:
@@ -327,7 +329,11 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
case Opt_uid:
{
char *uid = args[0].from;
- uid_t val = simple_strtoul(uid, &uid, 0);
+ uid_t val;
+ int rc = kstrtouint(uid, 0, &val);
+
+ if (rc)
+ goto cleanup;
sbi->uid = make_kuid(current_user_ns(), val);
if (!uid_valid(sbi->uid))
goto cleanup;
@@ -337,7 +343,11 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
case Opt_gid:
{
char *gid = args[0].from;
- gid_t val = simple_strtoul(gid, &gid, 0);
+ gid_t val;
+ int rc = kstrtouint(gid, 0, &val);
+
+ if (rc)
+ goto cleanup;
sbi->gid = make_kgid(current_user_ns(), val);
if (!gid_valid(sbi->gid))
goto cleanup;
@@ -347,7 +357,10 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
case Opt_umask:
{
char *umask = args[0].from;
- sbi->umask = simple_strtoul(umask, &umask, 8);
+ int rc = kstrtouint(umask, 8, &sbi->umask);
+
+ if (rc)
+ goto cleanup;
if (sbi->umask & ~0777) {
pr_err("JFS: Invalid value of umask\n");
goto cleanup;
@@ -363,12 +376,10 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
* -> user has more control over the online trimming
*/
sbi->minblks_trim = 64;
- if (blk_queue_discard(q)) {
+ if (blk_queue_discard(q))
*flag |= JFS_DISCARD;
- } else {
- pr_err("JFS: discard option " \
- "not supported on device\n");
- }
+ else
+ pr_err("JFS: discard option not supported on device\n");
break;
}
@@ -380,20 +391,21 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
char *minblks_trim = args[0].from;
+ int rc;
if (blk_queue_discard(q)) {
*flag |= JFS_DISCARD;
- sbi->minblks_trim = simple_strtoull(
- minblks_trim, &minblks_trim, 0);
- } else {
- pr_err("JFS: discard option " \
- "not supported on device\n");
- }
+ rc = kstrtouint(minblks_trim, 0,
+ &sbi->minblks_trim);
+ if (rc)
+ goto cleanup;
+ } else
+ pr_err("JFS: discard option not supported on device\n");
break;
}
default:
- printk("jfs: Unrecognized mount option \"%s\" "
- " or missing value\n", p);
+ printk("jfs: Unrecognized mount option \"%s\" or missing value\n",
+ p);
goto cleanup;
}
}
@@ -419,14 +431,12 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
int ret;
sync_filesystem(sb);
- if (!parse_options(data, sb, &newLVSize, &flag)) {
+ if (!parse_options(data, sb, &newLVSize, &flag))
return -EINVAL;
- }
if (newLVSize) {
if (sb->s_flags & MS_RDONLY) {
- pr_err("JFS: resize requires volume" \
- " to be mounted read-write\n");
+ pr_err("JFS: resize requires volume to be mounted read-write\n");
return -EROFS;
}
rc = jfs_extendfs(sb, newLVSize, 0);
@@ -452,9 +462,8 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
}
if ((!(sb->s_flags & MS_RDONLY)) && (*flags & MS_RDONLY)) {
rc = dquot_suspend(sb, -1);
- if (rc < 0) {
+ if (rc < 0)
return rc;
- }
rc = jfs_umount_rw(sb);
JFS_SBI(sb)->flag = flag;
return rc;
@@ -487,7 +496,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
if (!new_valid_dev(sb->s_bdev->bd_dev))
return -EOVERFLOW;
- sbi = kzalloc(sizeof (struct jfs_sb_info), GFP_KERNEL);
+ sbi = kzalloc(sizeof(struct jfs_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
@@ -548,9 +557,8 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
rc = jfs_mount(sb);
if (rc) {
- if (!silent) {
+ if (!silent)
jfs_err("jfs_mount failed w/return code = %d", rc);
- }
goto out_mount_failed;
}
if (sb->s_flags & MS_RDONLY)
@@ -587,7 +595,8 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
* Page cache is indexed by long.
* I would use MAX_LFS_FILESIZE, but it's only half as big
*/
- sb->s_maxbytes = min(((u64) PAGE_CACHE_SIZE << 32) - 1, (u64)sb->s_maxbytes);
+ sb->s_maxbytes = min(((u64) PAGE_CACHE_SIZE << 32) - 1,
+ (u64)sb->s_maxbytes);
#endif
sb->s_time_gran = 1;
return 0;
@@ -597,9 +606,8 @@ out_no_root:
out_no_rw:
rc = jfs_umount(sb);
- if (rc) {
+ if (rc)
jfs_err("jfs_umount failed with return code %d", rc);
- }
out_mount_failed:
filemap_write_and_wait(sbi->direct_inode->i_mapping);
truncate_inode_pages(sbi->direct_inode->i_mapping, 0);
@@ -924,7 +932,8 @@ static int __init init_jfs_fs(void)
commit_threads = MAX_COMMIT_THREADS;
for (i = 0; i < commit_threads; i++) {
- jfsCommitThread[i] = kthread_run(jfs_lazycommit, NULL, "jfsCommit");
+ jfsCommitThread[i] = kthread_run(jfs_lazycommit, NULL,
+ "jfsCommit");
if (IS_ERR(jfsCommitThread[i])) {
rc = PTR_ERR(jfsCommitThread[i]);
jfs_err("init_jfs_fs: fork failed w/rc = %d", rc);
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index ac127cd008bf..a693f5b01ae6 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -714,6 +714,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
return ERR_PTR(-ENOMEM);
ida_init(&root->ino_ida);
+ INIT_LIST_HEAD(&root->supers);
kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
KERNFS_DIR);
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 5e9a80cfc3d8..e3d37f607f97 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -14,6 +14,7 @@
#include <linux/poll.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
+#include <linux/fsnotify.h>
#include "kernfs-internal.h"
@@ -790,20 +791,48 @@ static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
*/
void kernfs_notify(struct kernfs_node *kn)
{
+ struct kernfs_root *root = kernfs_root(kn);
struct kernfs_open_node *on;
+ struct kernfs_super_info *info;
unsigned long flags;
+ if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
+ return;
+
+ /* kick poll */
spin_lock_irqsave(&kernfs_open_node_lock, flags);
- if (!WARN_ON(kernfs_type(kn) != KERNFS_FILE)) {
- on = kn->attr.open;
- if (on) {
- atomic_inc(&on->event);
- wake_up_interruptible(&on->poll);
- }
+ on = kn->attr.open;
+ if (on) {
+ atomic_inc(&on->event);
+ wake_up_interruptible(&on->poll);
}
spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
+
+ /* kick fsnotify */
+ mutex_lock(&kernfs_mutex);
+
+ list_for_each_entry(info, &root->supers, node) {
+ struct inode *inode;
+ struct dentry *dentry;
+
+ inode = ilookup(info->sb, kn->ino);
+ if (!inode)
+ continue;
+
+ dentry = d_find_any_alias(inode);
+ if (dentry) {
+ fsnotify_parent(NULL, dentry, FS_MODIFY);
+ fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
+ NULL, 0);
+ dput(dentry);
+ }
+
+ iput(inode);
+ }
+
+ mutex_unlock(&kernfs_mutex);
}
EXPORT_SYMBOL_GPL(kernfs_notify);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 8be13b2a079b..dc84a3ef9ca2 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -49,6 +49,8 @@ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
* mount.c
*/
struct kernfs_super_info {
+ struct super_block *sb;
+
/*
* The root associated with this super_block. Each super_block is
* identified by the root and ns it's associated with.
@@ -62,6 +64,9 @@ struct kernfs_super_info {
* an array and compare kernfs_node tag against every entry.
*/
const void *ns;
+
+ /* anchored at kernfs_root->supers, protected by kernfs_mutex */
+ struct list_head node;
};
#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 95dcd1d558bb..d171b98a6cdd 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -68,6 +68,7 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
struct inode *inode;
struct dentry *root;
+ info->sb = sb;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_magic = magic;
@@ -167,12 +168,18 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
*new_sb_created = !sb->s_root;
if (!sb->s_root) {
+ struct kernfs_super_info *info = kernfs_info(sb);
+
error = kernfs_fill_super(sb, magic);
if (error) {
deactivate_locked_super(sb);
return ERR_PTR(error);
}
sb->s_flags |= MS_ACTIVE;
+
+ mutex_lock(&kernfs_mutex);
+ list_add(&info->node, &root->supers);
+ mutex_unlock(&kernfs_mutex);
}
return dget(sb->s_root);
@@ -191,6 +198,10 @@ void kernfs_kill_sb(struct super_block *sb)
struct kernfs_super_info *info = kernfs_info(sb);
struct kernfs_node *root_kn = sb->s_root->d_fsdata;
+ mutex_lock(&kernfs_mutex);
+ list_del(&info->node);
+ mutex_unlock(&kernfs_mutex);
+
/*
* Remove the superblock from fs_supers/s_instances
* so we can't find it, before freeing kernfs_super_info.
diff --git a/fs/libfs.c b/fs/libfs.c
index a1844244246f..88e3e00e2eca 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -3,6 +3,7 @@
* Library for filesystems writers.
*/
+#include <linux/blkdev.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
@@ -923,16 +924,19 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
EXPORT_SYMBOL_GPL(generic_fh_to_parent);
/**
- * generic_file_fsync - generic fsync implementation for simple filesystems
+ * __generic_file_fsync - generic fsync implementation for simple filesystems
+ *
* @file: file to synchronize
+ * @start: start offset in bytes
+ * @end: end offset in bytes (inclusive)
* @datasync: only synchronize essential metadata if true
*
* This is a generic implementation of the fsync method for simple
* filesystems which track all non-inode metadata in the buffers list
* hanging off the address_space structure.
*/
-int generic_file_fsync(struct file *file, loff_t start, loff_t end,
- int datasync)
+int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
{
struct inode *inode = file->f_mapping->host;
int err;
@@ -952,10 +956,34 @@ int generic_file_fsync(struct file *file, loff_t start, loff_t end,
err = sync_inode_metadata(inode, 1);
if (ret == 0)
ret = err;
+
out:
mutex_unlock(&inode->i_mutex);
return ret;
}
+EXPORT_SYMBOL(__generic_file_fsync);
+
+/**
+ * generic_file_fsync - generic fsync implementation for simple filesystems
+ * with flush
+ * @file: file to synchronize
+ * @start: start offset in bytes
+ * @end: end offset in bytes (inclusive)
+ * @datasync: only synchronize essential metadata if true
+ *
+ */
+
+int generic_file_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ struct inode *inode = file->f_mapping->host;
+ int err;
+
+ err = __generic_file_fsync(file, start, end, datasync);
+ if (err)
+ return err;
+ return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+}
EXPORT_SYMBOL(generic_file_fsync);
/**
diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index 00ec0b9c94d1..d3e40db28930 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -14,6 +14,8 @@
#include <linux/sunrpc/stats.h>
#include <linux/lockd/lockd.h>
+#include <uapi/linux/nfs3.h>
+
#define NLMDBG_FACILITY NLMDBG_XDR
#if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ)
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 9a55797a1cd4..3e9f7874b975 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -15,6 +15,8 @@
#include <linux/sunrpc/stats.h>
#include <linux/lockd/lockd.h>
+#include <uapi/linux/nfs2.h>
+
#define NLMDBG_FACILITY NLMDBG_XDR
#if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ)
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 6bf06a07f3e0..8f27c93f8d2e 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -436,7 +436,7 @@ EXPORT_SYMBOL_GPL(lockd_down);
* Sysctl parameters (same as module parameters, different interface).
*/
-static ctl_table nlm_sysctls[] = {
+static struct ctl_table nlm_sysctls[] = {
{
.procname = "nlm_grace_period",
.data = &nlm_grace_period,
@@ -490,7 +490,7 @@ static ctl_table nlm_sysctls[] = {
{ }
};
-static ctl_table nlm_sysctl_dir[] = {
+static struct ctl_table nlm_sysctl_dir[] = {
{
.procname = "nfs",
.mode = 0555,
@@ -499,7 +499,7 @@ static ctl_table nlm_sysctl_dir[] = {
{ }
};
-static ctl_table nlm_sysctl_root[] = {
+static struct ctl_table nlm_sysctl_root[] = {
{
.procname = "fs",
.mode = 0555,
@@ -622,8 +622,8 @@ static int __init init_nlm(void)
err_pernet:
#ifdef CONFIG_SYSCTL
unregister_sysctl_table(nlm_sysctl_table);
-#endif
err_sysctl:
+#endif
return err;
}
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index dc5c75930f0f..b6f3b84b6e99 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -14,12 +14,11 @@
#include <linux/mutex.h>
#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/addr.h>
-#include <linux/nfsd/nfsfh.h>
-#include <linux/nfsd/export.h>
#include <linux/lockd/lockd.h>
#include <linux/lockd/share.h>
#include <linux/module.h>
#include <linux/mount.h>
+#include <uapi/linux/nfs2.h>
#define NLMDBG_FACILITY NLMDBG_SVCSUBS
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 964666c68a86..9340e7e10ef6 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -16,6 +16,8 @@
#include <linux/sunrpc/stats.h>
#include <linux/lockd/lockd.h>
+#include <uapi/linux/nfs2.h>
+
#define NLMDBG_FACILITY NLMDBG_XDR
diff --git a/fs/locks.c b/fs/locks.c
index e390bd9ae068..da57c9b7e844 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -130,6 +130,9 @@
#include <linux/percpu.h>
#include <linux/lglock.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/filelock.h>
+
#include <asm/uaccess.h>
#define IS_POSIX(fl) (fl->fl_flags & FL_POSIX)
@@ -322,6 +325,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock,
return -ENOMEM;
fl->fl_file = filp;
+ fl->fl_owner = (fl_owner_t)filp;
fl->fl_pid = current->tgid;
fl->fl_flags = FL_FLOCK;
fl->fl_type = type;
@@ -427,7 +431,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
if (assign_type(fl, type) != 0)
return -EINVAL;
- fl->fl_owner = current->files;
+ fl->fl_owner = (fl_owner_t)filp;
fl->fl_pid = current->tgid;
fl->fl_file = filp;
@@ -1286,6 +1290,7 @@ static void time_out_leases(struct inode *inode)
before = &inode->i_flock;
while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
+ trace_time_out_leases(inode, fl);
if (past_time(fl->fl_downgrade_time))
lease_modify(before, F_RDLCK);
if (past_time(fl->fl_break_time))
@@ -1373,6 +1378,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
}
if (i_have_this_lease || (mode & O_NONBLOCK)) {
+ trace_break_lease_noblock(inode, new_fl);
error = -EWOULDBLOCK;
goto out;
}
@@ -1384,10 +1390,12 @@ restart:
if (break_time == 0)
break_time++;
locks_insert_block(flock, new_fl);
+ trace_break_lease_block(inode, new_fl);
spin_unlock(&inode->i_lock);
error = wait_event_interruptible_timeout(new_fl->fl_wait,
!new_fl->fl_next, break_time);
spin_lock(&inode->i_lock);
+ trace_break_lease_unblock(inode, new_fl);
locks_delete_block(new_fl);
if (error >= 0) {
if (error == 0)
@@ -1509,6 +1517,8 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
int error;
lease = *flp;
+ trace_generic_add_lease(inode, lease);
+
/*
* In the delegation case we need mutual exclusion with
* a number of operations that take the i_mutex. We trylock
@@ -1598,6 +1608,8 @@ static int generic_delete_lease(struct file *filp, struct file_lock **flp)
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
+ trace_generic_delete_lease(inode, *flp);
+
for (before = &inode->i_flock;
((fl = *before) != NULL) && IS_LEASE(fl);
before = &fl->fl_next) {
@@ -2316,6 +2328,7 @@ void locks_remove_file(struct file *filp)
if (filp->f_op->flock) {
struct file_lock fl = {
+ .fl_owner = (fl_owner_t)filp,
.fl_pid = current->tgid,
.fl_file = filp,
.fl_flags = FL_FLOCK,
@@ -2423,31 +2436,31 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
seq_printf(f, "%lld:%s ", id, pfx);
if (IS_POSIX(fl)) {
if (fl->fl_flags & FL_ACCESS)
- seq_printf(f, "ACCESS");
+ seq_puts(f, "ACCESS");
else if (IS_OFDLCK(fl))
- seq_printf(f, "OFDLCK");
+ seq_puts(f, "OFDLCK");
else
- seq_printf(f, "POSIX ");
+ seq_puts(f, "POSIX ");
seq_printf(f, " %s ",
(inode == NULL) ? "*NOINODE*" :
mandatory_lock(inode) ? "MANDATORY" : "ADVISORY ");
} else if (IS_FLOCK(fl)) {
if (fl->fl_type & LOCK_MAND) {
- seq_printf(f, "FLOCK MSNFS ");
+ seq_puts(f, "FLOCK MSNFS ");
} else {
- seq_printf(f, "FLOCK ADVISORY ");
+ seq_puts(f, "FLOCK ADVISORY ");
}
} else if (IS_LEASE(fl)) {
- seq_printf(f, "LEASE ");
+ seq_puts(f, "LEASE ");
if (lease_breaking(fl))
- seq_printf(f, "BREAKING ");
+ seq_puts(f, "BREAKING ");
else if (fl->fl_file)
- seq_printf(f, "ACTIVE ");
+ seq_puts(f, "ACTIVE ");
else
- seq_printf(f, "BREAKER ");
+ seq_puts(f, "BREAKER ");
} else {
- seq_printf(f, "UNKNOWN UNKNOWN ");
+ seq_puts(f, "UNKNOWN UNKNOWN ");
}
if (fl->fl_type & LOCK_MAND) {
seq_printf(f, "%s ",
@@ -2479,7 +2492,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
else
seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end);
} else {
- seq_printf(f, "0 EOF\n");
+ seq_puts(f, "0 EOF\n");
}
}
diff --git a/fs/mpage.c b/fs/mpage.c
index 4979ffa60aaa..5f9ed622274f 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -48,23 +48,7 @@ static void mpage_end_io(struct bio *bio, int err)
bio_for_each_segment_all(bv, bio, i) {
struct page *page = bv->bv_page;
-
- if (bio_data_dir(bio) == READ) {
- if (!err) {
- SetPageUptodate(page);
- } else {
- ClearPageUptodate(page);
- SetPageError(page);
- }
- unlock_page(page);
- } else { /* bio_data_dir(bio) == WRITE */
- if (err) {
- SetPageError(page);
- if (page->mapping)
- set_bit(AS_EIO, &page->mapping->flags);
- }
- end_page_writeback(page);
- }
+ page_endio(page, bio_data_dir(bio), err);
}
bio_put(bio);
@@ -285,6 +269,11 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
alloc_new:
if (bio == NULL) {
+ if (first_hole == blocks_per_page) {
+ if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9),
+ page))
+ goto out;
+ }
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
GFP_KERNEL);
@@ -439,6 +428,35 @@ struct mpage_data {
unsigned use_writepage;
};
+/*
+ * We have our BIO, so we can now mark the buffers clean. Make
+ * sure to only clean buffers which we know we'll be writing.
+ */
+static void clean_buffers(struct page *page, unsigned first_unmapped)
+{
+ unsigned buffer_counter = 0;
+ struct buffer_head *bh, *head;
+ if (!page_has_buffers(page))
+ return;
+ head = page_buffers(page);
+ bh = head;
+
+ do {
+ if (buffer_counter++ == first_unmapped)
+ break;
+ clear_buffer_dirty(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+
+ /*
+ * we cannot drop the bh if the page is not uptodate or a concurrent
+ * readpage would fail to serialize with the bh and it would read from
+ * disk before we reach the platter.
+ */
+ if (buffer_heads_over_limit && PageUptodate(page))
+ try_to_free_buffers(page);
+}
+
static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
@@ -574,6 +592,13 @@ page_is_mapped:
alloc_new:
if (bio == NULL) {
+ if (first_unmapped == blocks_per_page) {
+ if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9),
+ page, wbc)) {
+ clean_buffers(page, first_unmapped);
+ goto out;
+ }
+ }
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
if (bio == NULL)
@@ -591,30 +616,7 @@ alloc_new:
goto alloc_new;
}
- /*
- * OK, we have our BIO, so we can now mark the buffers clean. Make
- * sure to only clean buffers which we know we'll be writing.
- */
- if (page_has_buffers(page)) {
- struct buffer_head *head = page_buffers(page);
- struct buffer_head *bh = head;
- unsigned buffer_counter = 0;
-
- do {
- if (buffer_counter++ == first_unmapped)
- break;
- clear_buffer_dirty(bh);
- bh = bh->b_this_page;
- } while (bh != head);
-
- /*
- * we cannot drop the bh if the page is not uptodate
- * or a concurrent readpage would fail to serialize with the bh
- * and it would read from disk before we reach the platter.
- */
- if (buffer_heads_over_limit && PageUptodate(page))
- try_to_free_buffers(page);
- }
+ clean_buffers(page, first_unmapped);
BUG_ON(PageWriteback(page));
set_page_writeback(page);
diff --git a/fs/namei.c b/fs/namei.c
index 80168273396b..985c6f368485 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -332,10 +332,11 @@ int generic_permission(struct inode *inode, int mask)
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
- if (inode_capable(inode, CAP_DAC_OVERRIDE))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
return 0;
if (!(mask & MAY_WRITE))
- if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+ if (capable_wrt_inode_uidgid(inode,
+ CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
}
@@ -345,7 +346,7 @@ int generic_permission(struct inode *inode, int mask)
* at least one exec bit set.
*/
if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
- if (inode_capable(inode, CAP_DAC_OVERRIDE))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
return 0;
/*
@@ -353,7 +354,7 @@ int generic_permission(struct inode *inode, int mask)
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ)
- if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
@@ -2379,7 +2380,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
return 0;
if (uid_eq(dir->i_uid, fsuid))
return 0;
- return !inode_capable(inode, CAP_FOWNER);
+ return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
}
/*
diff --git a/fs/ncpfs/getopt.c b/fs/ncpfs/getopt.c
index 03ffde1f44d6..344889cd120e 100644
--- a/fs/ncpfs/getopt.c
+++ b/fs/ncpfs/getopt.c
@@ -53,15 +53,14 @@ int ncp_getopt(const char *caller, char **options, const struct ncp_option *opts
return -EINVAL;
}
if (opts->has_arg & OPT_INT) {
- char* v;
+ int rc = kstrtoul(val, 0, value);
- *value = simple_strtoul(val, &v, 0);
- if (!*v) {
- return opts->val;
+ if (rc) {
+ pr_info("%s: invalid numeric value in %s=%s\n",
+ caller, token, val);
+ return rc;
}
- pr_info("%s: invalid numeric value in %s=%s\n",
- caller, token, val);
- return -EDOM;
+ return opts->val;
}
if (opts->has_arg & OPT_STRING) {
return opts->val;
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 03192a66c143..4782e0840dcc 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -29,8 +29,6 @@ nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o
nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o
-obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
-nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
-
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 65d849bdf77a..9b431f44fad9 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -210,7 +210,7 @@ static void bl_end_io_read(struct bio *bio, int err)
SetPageUptodate(bvec->bv_page);
if (err) {
- struct nfs_read_data *rdata = par->data;
+ struct nfs_pgio_data *rdata = par->data;
struct nfs_pgio_header *header = rdata->header;
if (!header->pnfs_error)
@@ -224,17 +224,17 @@ static void bl_end_io_read(struct bio *bio, int err)
static void bl_read_cleanup(struct work_struct *work)
{
struct rpc_task *task;
- struct nfs_read_data *rdata;
+ struct nfs_pgio_data *rdata;
dprintk("%s enter\n", __func__);
task = container_of(work, struct rpc_task, u.tk_work);
- rdata = container_of(task, struct nfs_read_data, task);
+ rdata = container_of(task, struct nfs_pgio_data, task);
pnfs_ld_read_done(rdata);
}
static void
bl_end_par_io_read(void *data, int unused)
{
- struct nfs_read_data *rdata = data;
+ struct nfs_pgio_data *rdata = data;
rdata->task.tk_status = rdata->header->pnfs_error;
INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
@@ -242,7 +242,7 @@ bl_end_par_io_read(void *data, int unused)
}
static enum pnfs_try_status
-bl_read_pagelist(struct nfs_read_data *rdata)
+bl_read_pagelist(struct nfs_pgio_data *rdata)
{
struct nfs_pgio_header *header = rdata->header;
int i, hole;
@@ -390,7 +390,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
}
if (unlikely(err)) {
- struct nfs_write_data *data = par->data;
+ struct nfs_pgio_data *data = par->data;
struct nfs_pgio_header *header = data->header;
if (!header->pnfs_error)
@@ -405,7 +405,7 @@ static void bl_end_io_write(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct nfs_write_data *data = par->data;
+ struct nfs_pgio_data *data = par->data;
struct nfs_pgio_header *header = data->header;
if (!uptodate) {
@@ -423,10 +423,10 @@ static void bl_end_io_write(struct bio *bio, int err)
static void bl_write_cleanup(struct work_struct *work)
{
struct rpc_task *task;
- struct nfs_write_data *wdata;
+ struct nfs_pgio_data *wdata;
dprintk("%s enter\n", __func__);
task = container_of(work, struct rpc_task, u.tk_work);
- wdata = container_of(task, struct nfs_write_data, task);
+ wdata = container_of(task, struct nfs_pgio_data, task);
if (likely(!wdata->header->pnfs_error)) {
/* Marks for LAYOUTCOMMIT */
mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
@@ -438,7 +438,7 @@ static void bl_write_cleanup(struct work_struct *work)
/* Called when last of bios associated with a bl_write_pagelist call finishes */
static void bl_end_par_io_write(void *data, int num_se)
{
- struct nfs_write_data *wdata = data;
+ struct nfs_pgio_data *wdata = data;
if (unlikely(wdata->header->pnfs_error)) {
bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
@@ -673,7 +673,7 @@ check_page:
}
static enum pnfs_try_status
-bl_write_pagelist(struct nfs_write_data *wdata, int sync)
+bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
{
struct nfs_pgio_header *header = wdata->header;
int i, ret, npg_zero, pg_index, last = 0;
@@ -1189,13 +1189,17 @@ bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
pnfs_generic_pg_init_read(pgio, req);
}
-static bool
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t
bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
if (pgio->pg_dreq != NULL &&
!is_aligned_req(req, SECTOR_SIZE))
- return false;
+ return 0;
return pnfs_generic_pg_test(pgio, prev, req);
}
@@ -1241,13 +1245,17 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
}
}
-static bool
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t
bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
if (pgio->pg_dreq != NULL &&
!is_aligned_req(req, PAGE_CACHE_SIZE))
- return false;
+ return 0;
return pnfs_generic_pg_test(pgio, prev, req);
}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index d9f3d067cd15..4a3d4ef76127 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2032,9 +2032,9 @@ static void nfs_access_free_entry(struct nfs_access_entry *entry)
{
put_rpccred(entry->cred);
kfree(entry);
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_long_dec(&nfs_access_nr_entries);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
static void nfs_access_free_list(struct list_head *head)
@@ -2082,9 +2082,9 @@ nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
else {
remove_lru_entry:
list_del_init(&nfsi->access_cache_inode_lru);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
spin_unlock(&inode->i_lock);
}
@@ -2232,9 +2232,9 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
nfs_access_add_rbtree(inode, cache);
/* Update accounting */
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_long_inc(&nfs_access_nr_entries);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
/* Add inode to global LRU list */
if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b8797ae6831f..4ad7bc388679 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -108,6 +108,97 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
return atomic_dec_and_test(&dreq->io_count);
}
+/*
+ * nfs_direct_select_verf - select the right verifier
+ * @dreq - direct request possibly spanning multiple servers
+ * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
+ * @ds_idx - index of data server in data server list, only valid if ds_clp set
+ *
+ * returns the correct verifier to use given the role of the server
+ */
+static struct nfs_writeverf *
+nfs_direct_select_verf(struct nfs_direct_req *dreq,
+ struct nfs_client *ds_clp,
+ int ds_idx)
+{
+ struct nfs_writeverf *verfp = &dreq->verf;
+
+#ifdef CONFIG_NFS_V4_1
+ if (ds_clp) {
+ /* pNFS is in use, use the DS verf */
+ if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
+ verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+ else
+ WARN_ON_ONCE(1);
+ }
+#endif
+ return verfp;
+}
+
+
+/*
+ * nfs_direct_set_hdr_verf - set the write/commit verifier
+ * @dreq - direct request possibly spanning multiple servers
+ * @hdr - pageio header to validate against previously seen verfs
+ *
+ * Set the server's (MDS or DS) "seen" verifier
+ */
+static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
+ struct nfs_pgio_header *hdr)
+{
+ struct nfs_writeverf *verfp;
+
+ verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
+ hdr->data->ds_idx);
+ WARN_ON_ONCE(verfp->committed >= 0);
+ memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+ WARN_ON_ONCE(verfp->committed < 0);
+}
+
+/*
+ * nfs_direct_cmp_hdr_verf - compare verifier for pgio header
+ * @dreq - direct request possibly spanning multiple servers
+ * @hdr - pageio header to validate against previously seen verf
+ *
+ * set the server's "seen" verf if not initialized.
+ * returns result of comparison between @hdr->verf and the "seen"
+ * verf of the server used by @hdr (DS or MDS)
+ */
+static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
+ struct nfs_pgio_header *hdr)
+{
+ struct nfs_writeverf *verfp;
+
+ verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
+ hdr->data->ds_idx);
+ if (verfp->committed < 0) {
+ nfs_direct_set_hdr_verf(dreq, hdr);
+ return 0;
+ }
+ return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+}
+
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
+/*
+ * nfs_direct_cmp_commit_data_verf - compare verifier for commit data
+ * @dreq - direct request possibly spanning multiple servers
+ * @data - commit data to validate against previously seen verf
+ *
+ * returns result of comparison between @data->verf and the verf of
+ * the server used by @data (DS or MDS)
+ */
+static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
+ struct nfs_commit_data *data)
+{
+ struct nfs_writeverf *verfp;
+
+ verfp = nfs_direct_select_verf(dreq, data->ds_clp,
+ data->ds_commit_index);
+ WARN_ON_ONCE(verfp->committed < 0);
+ return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
+}
+#endif
+
/**
* nfs_direct_IO - NFS address space operation for direct I/O
* @rw: direction (read or write)
@@ -168,6 +259,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
kref_get(&dreq->kref);
init_completion(&dreq->completion);
INIT_LIST_HEAD(&dreq->mds_cinfo.list);
+ dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */
INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
spin_lock_init(&dreq->lock);
@@ -380,8 +472,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
/* XXX do we need to do the eof zeroing found in async_filler? */
- req = nfs_create_request(dreq->ctx, dreq->inode,
- pagevec[i],
+ req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
pgbase, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
@@ -424,7 +515,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
size_t requested_bytes = 0;
unsigned long seg;
- NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode,
+ nfs_pageio_init_read(&desc, dreq->inode, false,
&nfs_direct_read_completion_ops);
get_dreq(dreq);
desc.pg_dreq = dreq;
@@ -564,7 +655,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
dreq->count = 0;
get_dreq(dreq);
- NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE,
+ nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
@@ -603,7 +694,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
dprintk("NFS: %5u commit failed with error %d.\n",
data->task.tk_pid, status);
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
- } else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) {
+ } else if (nfs_direct_cmp_commit_data_verf(dreq, data)) {
dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
}
@@ -750,8 +841,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
- req = nfs_create_request(dreq->ctx, dreq->inode,
- pagevec[i],
+ req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
pgbase, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
@@ -813,13 +903,13 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
bit = NFS_IOHDR_NEED_RESCHED;
else if (dreq->flags == 0) {
- memcpy(&dreq->verf, hdr->verf,
- sizeof(dreq->verf));
+ nfs_direct_set_hdr_verf(dreq, hdr);
bit = NFS_IOHDR_NEED_COMMIT;
dreq->flags = NFS_ODIRECT_DO_COMMIT;
} else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) {
- if (memcmp(&dreq->verf, hdr->verf, sizeof(dreq->verf))) {
- dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+ if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr)) {
+ dreq->flags =
+ NFS_ODIRECT_RESCHED_WRITES;
bit = NFS_IOHDR_NEED_RESCHED;
} else
bit = NFS_IOHDR_NEED_COMMIT;
@@ -829,6 +919,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
spin_unlock(&dreq->lock);
while (!list_empty(&hdr->pages)) {
+ bool do_destroy = true;
+
req = nfs_list_entry(hdr->pages.next);
nfs_list_remove_request(req);
switch (bit) {
@@ -836,6 +928,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
case NFS_IOHDR_NEED_COMMIT:
kref_get(&req->wb_kref);
nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+ do_destroy = false;
}
nfs_unlock_and_release_request(req);
}
@@ -874,7 +967,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
size_t requested_bytes = 0;
unsigned long seg;
- NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE,
+ nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
get_dreq(dreq);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 284ca901fe16..c1edf7336315 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -916,10 +916,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
is_local = 1;
/* We're simulating flock() locks using posix locks on the server */
- fl->fl_owner = (fl_owner_t)filp;
- fl->fl_start = 0;
- fl->fl_end = OFFSET_MAX;
-
if (fl->fl_type == F_UNLCK)
return do_unlk(filp, cmd, fl, is_local);
return do_setlk(filp, cmd, fl, is_local);
diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile
new file mode 100644
index 000000000000..8516cdffb9e9
--- /dev/null
+++ b/fs/nfs/filelayout/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Files Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
+nfs_layout_nfsv41_files-y := filelayout.o filelayoutdev.o
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/filelayout/filelayout.c
index b9a35c05b60f..d2eba1c13b7e 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -35,11 +35,11 @@
#include <linux/sunrpc/metrics.h>
-#include "nfs4session.h"
-#include "internal.h"
-#include "delegation.h"
-#include "nfs4filelayout.h"
-#include "nfs4trace.h"
+#include "../nfs4session.h"
+#include "../internal.h"
+#include "../delegation.h"
+#include "filelayout.h"
+#include "../nfs4trace.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
@@ -84,7 +84,7 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
BUG();
}
-static void filelayout_reset_write(struct nfs_write_data *data)
+static void filelayout_reset_write(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
struct rpc_task *task = &data->task;
@@ -105,7 +105,7 @@ static void filelayout_reset_write(struct nfs_write_data *data)
}
}
-static void filelayout_reset_read(struct nfs_read_data *data)
+static void filelayout_reset_read(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
struct rpc_task *task = &data->task;
@@ -243,7 +243,7 @@ wait_on_recovery:
/* NFS_PROTO call done callback routines */
static int filelayout_read_done_cb(struct rpc_task *task,
- struct nfs_read_data *data)
+ struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
int err;
@@ -270,7 +270,7 @@ static int filelayout_read_done_cb(struct rpc_task *task,
* rfc5661 is not clear about which credential should be used.
*/
static void
-filelayout_set_layoutcommit(struct nfs_write_data *wdata)
+filelayout_set_layoutcommit(struct nfs_pgio_data *wdata)
{
struct nfs_pgio_header *hdr = wdata->header;
@@ -279,7 +279,7 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
return;
pnfs_set_layoutcommit(wdata);
- dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+ dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
}
@@ -305,7 +305,7 @@ filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
*/
static void filelayout_read_prepare(struct rpc_task *task, void *data)
{
- struct nfs_read_data *rdata = data;
+ struct nfs_pgio_data *rdata = data;
if (unlikely(test_bit(NFS_CONTEXT_BAD, &rdata->args.context->flags))) {
rpc_exit(task, -EIO);
@@ -317,7 +317,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
rpc_exit(task, 0);
return;
}
- rdata->read_done_cb = filelayout_read_done_cb;
+ rdata->pgio_done_cb = filelayout_read_done_cb;
if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
&rdata->args.seq_args,
@@ -331,7 +331,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
static void filelayout_read_call_done(struct rpc_task *task, void *data)
{
- struct nfs_read_data *rdata = data;
+ struct nfs_pgio_data *rdata = data;
dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
@@ -347,14 +347,14 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
static void filelayout_read_count_stats(struct rpc_task *task, void *data)
{
- struct nfs_read_data *rdata = data;
+ struct nfs_pgio_data *rdata = data;
rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics);
}
static void filelayout_read_release(void *data)
{
- struct nfs_read_data *rdata = data;
+ struct nfs_pgio_data *rdata = data;
struct pnfs_layout_hdr *lo = rdata->header->lseg->pls_layout;
filelayout_fenceme(lo->plh_inode, lo);
@@ -363,7 +363,7 @@ static void filelayout_read_release(void *data)
}
static int filelayout_write_done_cb(struct rpc_task *task,
- struct nfs_write_data *data)
+ struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
int err;
@@ -419,7 +419,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
static void filelayout_write_prepare(struct rpc_task *task, void *data)
{
- struct nfs_write_data *wdata = data;
+ struct nfs_pgio_data *wdata = data;
if (unlikely(test_bit(NFS_CONTEXT_BAD, &wdata->args.context->flags))) {
rpc_exit(task, -EIO);
@@ -443,7 +443,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
static void filelayout_write_call_done(struct rpc_task *task, void *data)
{
- struct nfs_write_data *wdata = data;
+ struct nfs_pgio_data *wdata = data;
if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
task->tk_status == 0) {
@@ -457,14 +457,14 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
static void filelayout_write_count_stats(struct rpc_task *task, void *data)
{
- struct nfs_write_data *wdata = data;
+ struct nfs_pgio_data *wdata = data;
rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics);
}
static void filelayout_write_release(void *data)
{
- struct nfs_write_data *wdata = data;
+ struct nfs_pgio_data *wdata = data;
struct pnfs_layout_hdr *lo = wdata->header->lseg->pls_layout;
filelayout_fenceme(lo->plh_inode, lo);
@@ -529,7 +529,7 @@ static const struct rpc_call_ops filelayout_commit_call_ops = {
};
static enum pnfs_try_status
-filelayout_read_pagelist(struct nfs_read_data *data)
+filelayout_read_pagelist(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
struct pnfs_layout_segment *lseg = hdr->lseg;
@@ -560,6 +560,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
/* No multipath support. Use first DS */
atomic_inc(&ds->ds_clp->cl_count);
data->ds_clp = ds->ds_clp;
+ data->ds_idx = idx;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
data->args.fh = fh;
@@ -568,14 +569,14 @@ filelayout_read_pagelist(struct nfs_read_data *data)
data->mds_offset = offset;
/* Perform an asynchronous read to ds */
- nfs_initiate_read(ds_clnt, data,
- &filelayout_read_call_ops, RPC_TASK_SOFTCONN);
+ nfs_initiate_pgio(ds_clnt, data,
+ &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
}
/* Perform async writes. */
static enum pnfs_try_status
-filelayout_write_pagelist(struct nfs_write_data *data, int sync)
+filelayout_write_pagelist(struct nfs_pgio_data *data, int sync)
{
struct nfs_pgio_header *hdr = data->header;
struct pnfs_layout_segment *lseg = hdr->lseg;
@@ -600,20 +601,18 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
__func__, hdr->inode->i_ino, sync, (size_t) data->args.count,
offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
- data->write_done_cb = filelayout_write_done_cb;
+ data->pgio_done_cb = filelayout_write_done_cb;
atomic_inc(&ds->ds_clp->cl_count);
data->ds_clp = ds->ds_clp;
+ data->ds_idx = idx;
fh = nfs4_fl_select_ds_fh(lseg, j);
if (fh)
data->args.fh = fh;
- /*
- * Get the file offset on the dserver. Set the write offset to
- * this offset and save the original offset.
- */
+
data->args.offset = filelayout_get_dserver_offset(lseg, offset);
/* Perform an asynchronous write */
- nfs_initiate_write(ds_clnt, data,
+ nfs_initiate_pgio(ds_clnt, data,
&filelayout_write_call_ops, sync,
RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
@@ -637,7 +636,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
struct nfs4_deviceid_node *d;
struct nfs4_file_layout_dsaddr *dsaddr;
int status = -EINVAL;
- struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);
dprintk("--> %s\n", __func__);
@@ -655,7 +653,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
goto out;
}
- if (!fl->stripe_unit || fl->stripe_unit % PAGE_SIZE) {
+ if (!fl->stripe_unit) {
dprintk("%s Invalid stripe unit (%u)\n",
__func__, fl->stripe_unit);
goto out;
@@ -692,12 +690,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
goto out_put;
}
- if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) {
- dprintk("%s Stripe unit (%u) not aligned with rsize %u "
- "wsize %u\n", __func__, fl->stripe_unit, nfss->rsize,
- nfss->wsize);
- }
-
status = 0;
out:
dprintk("--> %s returns %d\n", __func__, status);
@@ -850,11 +842,15 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
{
struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
struct pnfs_commit_bucket *buckets;
- int size;
+ int size, i;
if (fl->commit_through_mds)
return 0;
- if (cinfo->ds->nbuckets != 0) {
+
+ size = (fl->stripe_type == STRIPE_SPARSE) ?
+ fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
+
+ if (cinfo->ds->nbuckets >= size) {
/* This assumes there is only one IOMODE_RW lseg. What
* we really want to do is have a layout_hdr level
* dictionary of <multipath_list4, fh> keys, each
@@ -864,30 +860,36 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
return 0;
}
- size = (fl->stripe_type == STRIPE_SPARSE) ?
- fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
-
buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
gfp_flags);
if (!buckets)
return -ENOMEM;
- else {
- int i;
+ for (i = 0; i < size; i++) {
+ INIT_LIST_HEAD(&buckets[i].written);
+ INIT_LIST_HEAD(&buckets[i].committing);
+ /* mark direct verifier as unset */
+ buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW;
+ }
- spin_lock(cinfo->lock);
- if (cinfo->ds->nbuckets != 0)
- kfree(buckets);
- else {
- cinfo->ds->buckets = buckets;
- cinfo->ds->nbuckets = size;
- for (i = 0; i < size; i++) {
- INIT_LIST_HEAD(&buckets[i].written);
- INIT_LIST_HEAD(&buckets[i].committing);
- }
- }
- spin_unlock(cinfo->lock);
- return 0;
+ spin_lock(cinfo->lock);
+ if (cinfo->ds->nbuckets >= size)
+ goto out;
+ for (i = 0; i < cinfo->ds->nbuckets; i++) {
+ list_splice(&cinfo->ds->buckets[i].written,
+ &buckets[i].written);
+ list_splice(&cinfo->ds->buckets[i].committing,
+ &buckets[i].committing);
+ buckets[i].direct_verf.committed =
+ cinfo->ds->buckets[i].direct_verf.committed;
+ buckets[i].wlseg = cinfo->ds->buckets[i].wlseg;
+ buckets[i].clseg = cinfo->ds->buckets[i].clseg;
}
+ swap(cinfo->ds->buckets, buckets);
+ cinfo->ds->nbuckets = size;
+out:
+ spin_unlock(cinfo->lock);
+ kfree(buckets);
+ return 0;
}
static struct pnfs_layout_segment *
@@ -915,47 +917,51 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
/*
* filelayout_pg_test(). Called by nfs_can_coalesce_requests()
*
- * return true : coalesce page
- * return false : don't coalesce page
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
*/
-static bool
+static size_t
filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
+ unsigned int size;
u64 p_stripe, r_stripe;
- u32 stripe_unit;
+ u32 stripe_offset;
+ u64 segment_offset = pgio->pg_lseg->pls_range.offset;
+ u32 stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
- if (!pnfs_generic_pg_test(pgio, prev, req) ||
- !nfs_generic_pg_test(pgio, prev, req))
- return false;
+ /* calls nfs_generic_pg_test */
+ size = pnfs_generic_pg_test(pgio, prev, req);
+ if (!size)
+ return 0;
- p_stripe = (u64)req_offset(prev);
- r_stripe = (u64)req_offset(req);
- stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
+ /* see if req and prev are in the same stripe */
+ if (prev) {
+ p_stripe = (u64)req_offset(prev) - segment_offset;
+ r_stripe = (u64)req_offset(req) - segment_offset;
+ do_div(p_stripe, stripe_unit);
+ do_div(r_stripe, stripe_unit);
- do_div(p_stripe, stripe_unit);
- do_div(r_stripe, stripe_unit);
+ if (p_stripe != r_stripe)
+ return 0;
+ }
- return (p_stripe == r_stripe);
+ /* calculate remaining bytes in the current stripe */
+ div_u64_rem((u64)req_offset(req) - segment_offset,
+ stripe_unit,
+ &stripe_offset);
+ WARN_ON_ONCE(stripe_offset > stripe_unit);
+ if (stripe_offset >= stripe_unit)
+ return 0;
+ return min(stripe_unit - (unsigned int)stripe_offset, size);
}
static void
filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
- WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
- if (req->wb_offset != req->wb_pgbase) {
- /*
- * Handling unaligned pages is difficult, because have to
- * somehow split a req in two in certain cases in the
- * pg.test code. Avoid this by just not using pnfs
- * in this case.
- */
- nfs_pageio_reset_read_mds(pgio);
- return;
- }
- pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+ if (!pgio->pg_lseg)
+ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
0,
NFS4_MAX_UINT64,
@@ -973,11 +979,8 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs_commit_info cinfo;
int status;
- WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
- if (req->wb_offset != req->wb_pgbase)
- goto out_mds;
- pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+ if (!pgio->pg_lseg)
+ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
0,
NFS4_MAX_UINT64,
@@ -1067,6 +1070,7 @@ filelayout_choose_commit_list(struct nfs_page *req,
*/
j = nfs4_fl_calc_j_index(lseg, req_offset(req));
i = select_bucket_index(fl, j);
+ spin_lock(cinfo->lock);
buckets = cinfo->ds->buckets;
list = &buckets[i].written;
if (list_empty(list)) {
@@ -1080,6 +1084,7 @@ filelayout_choose_commit_list(struct nfs_page *req,
}
set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
cinfo->ds->nwritten++;
+ spin_unlock(cinfo->lock);
return list;
}
@@ -1176,6 +1181,7 @@ transfer_commit_list(struct list_head *src, struct list_head *dst,
return ret;
}
+/* Note called with cinfo->lock held. */
static int
filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo,
@@ -1220,15 +1226,18 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
struct nfs_commit_info *cinfo)
{
struct pnfs_commit_bucket *b;
+ struct pnfs_layout_segment *freeme;
int i;
+restart:
spin_lock(cinfo->lock);
for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
- spin_unlock(cinfo->lock);
- pnfs_put_lseg(b->wlseg);
+ freeme = b->wlseg;
b->wlseg = NULL;
- spin_lock(cinfo->lock);
+ spin_unlock(cinfo->lock);
+ pnfs_put_lseg(freeme);
+ goto restart;
}
}
cinfo->ds->nwritten = 0;
@@ -1243,6 +1252,7 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
struct nfs_commit_data *data;
int i, j;
unsigned int nreq = 0;
+ struct pnfs_layout_segment *freeme;
fl_cinfo = cinfo->ds;
bucket = fl_cinfo->buckets;
@@ -1253,8 +1263,10 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
if (!data)
break;
data->ds_commit_index = i;
+ spin_lock(cinfo->lock);
data->lseg = bucket->clseg;
bucket->clseg = NULL;
+ spin_unlock(cinfo->lock);
list_add(&data->pages, list);
nreq++;
}
@@ -1264,8 +1276,11 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
if (list_empty(&bucket->committing))
continue;
nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
- pnfs_put_lseg(bucket->clseg);
+ spin_lock(cinfo->lock);
+ freeme = bucket->clseg;
bucket->clseg = NULL;
+ spin_unlock(cinfo->lock);
+ pnfs_put_lseg(freeme);
}
/* Caller will clean up entries put on list */
return nreq;
@@ -1330,7 +1345,7 @@ filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
struct nfs4_filelayout *flo;
flo = kzalloc(sizeof(*flo), gfp_flags);
- return &flo->generic_hdr;
+ return flo != NULL ? &flo->generic_hdr : NULL;
}
static void
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/filelayout/filelayout.h
index cebd20e7e923..ffbddf2219ea 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -30,7 +30,7 @@
#ifndef FS_NFS_NFS4FILELAYOUT_H
#define FS_NFS_NFS4FILELAYOUT_H
-#include "pnfs.h"
+#include "../pnfs.h"
/*
* Default data server connection timeout and retrans vaules.
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index efac602edb37..44bf0140a4c7 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -33,9 +33,9 @@
#include <linux/module.h>
#include <linux/sunrpc/addr.h>
-#include "internal.h"
-#include "nfs4session.h"
-#include "nfs4filelayout.h"
+#include "../internal.h"
+#include "../nfs4session.h"
+#include "filelayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
@@ -789,9 +789,9 @@ static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
}
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 66984a9aafaa..b94f80420a58 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -120,7 +120,8 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh,
security_d_instantiate(ret, inode);
spin_lock(&ret->d_lock);
- if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
+ if (IS_ROOT(ret) && !ret->d_fsdata &&
+ !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
ret->d_fsdata = name;
name = NULL;
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 0c438973f3c8..c496f8a74639 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1085,7 +1085,7 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
trace_nfs_invalidate_mapping_exit(inode, ret);
clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_INVALIDATING);
out:
return ret;
@@ -1575,18 +1575,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_version = fattr->change_attr;
}
} else if (server->caps & NFS_CAP_CHANGE_ATTR)
- invalid |= save_cache_validity;
+ nfsi->cache_validity |= save_cache_validity;
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
} else if (server->caps & NFS_CAP_MTIME)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
} else if (server->caps & NFS_CAP_CTIME)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
/* Check if our cached file size is stale */
@@ -1608,7 +1610,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
(long long)new_isize);
}
} else
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_PAGECACHE
| NFS_INO_REVAL_FORCED);
@@ -1616,7 +1619,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
else if (server->caps & NFS_CAP_ATIME)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_MODE) {
@@ -1627,7 +1631,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
}
} else if (server->caps & NFS_CAP_MODE)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
@@ -1638,7 +1643,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_uid = fattr->uid;
}
} else if (server->caps & NFS_CAP_OWNER)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
@@ -1649,7 +1655,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_gid = fattr->gid;
}
} else if (server->caps & NFS_CAP_OWNER_GROUP)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
@@ -1662,7 +1669,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
set_nlink(inode, fattr->nlink);
}
} else if (server->caps & NFS_CAP_NLINK)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index dd8bfc2e2464..8b69cba1bb04 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -231,13 +231,20 @@ extern void nfs_destroy_writepagecache(void);
extern int __init nfs_init_directcache(void);
extern void nfs_destroy_directcache(void);
-extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount);
extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr,
void (*release)(struct nfs_pgio_header *hdr));
void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
int nfs_iocounter_wait(struct nfs_io_counter *c);
+extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
+struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *);
+void nfs_rw_header_free(struct nfs_pgio_header *);
+void nfs_pgio_data_release(struct nfs_pgio_data *);
+int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
+int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *,
+ const struct rpc_call_ops *, int, int);
+
static inline void nfs_iocounter_init(struct nfs_io_counter *c)
{
c->flags = 0;
@@ -395,19 +402,11 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool
struct nfs_pgio_completion_ops;
/* read.c */
-extern struct nfs_read_header *nfs_readhdr_alloc(void);
-extern void nfs_readhdr_free(struct nfs_pgio_header *hdr);
extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
- struct inode *inode,
+ struct inode *inode, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops);
-extern int nfs_initiate_read(struct rpc_clnt *clnt,
- struct nfs_read_data *data,
- const struct rpc_call_ops *call_ops, int flags);
extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
-extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
-extern void nfs_readdata_release(struct nfs_read_data *rdata);
/* super.c */
void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
@@ -422,19 +421,10 @@ int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
/* write.c */
extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
- struct inode *inode, int ioflags,
+ struct inode *inode, int ioflags, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops);
-extern struct nfs_write_header *nfs_writehdr_alloc(void);
-extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
-extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr);
extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
-extern void nfs_writedata_release(struct nfs_write_data *wdata);
extern void nfs_commit_free(struct nfs_commit_data *p);
-extern int nfs_initiate_write(struct rpc_clnt *clnt,
- struct nfs_write_data *data,
- const struct rpc_call_ops *call_ops,
- int how, int flags);
extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
extern int nfs_initiate_commit(struct rpc_clnt *clnt,
@@ -447,6 +437,7 @@ extern void nfs_init_commit(struct nfs_commit_data *data,
struct nfs_commit_info *cinfo);
int nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_commit_info *cinfo, int max);
+unsigned long nfs_reqs_to_commit(struct nfs_commit_info *);
int nfs_scan_commit(struct inode *inode, struct list_head *dst,
struct nfs_commit_info *cinfo);
void nfs_mark_request_commit(struct nfs_page *req,
@@ -492,7 +483,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
/* nfs4proc.c */
-extern void __nfs4_read_done_cb(struct nfs_read_data *);
+extern void __nfs4_read_done_cb(struct nfs_pgio_data *);
extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 62db136339ea..5f61b83f4a1c 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -103,7 +103,7 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
/*
* typedef opaque nfsdata<>;
*/
-static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result)
+static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_pgio_res *result)
{
u32 recvd, count;
__be32 *p;
@@ -613,7 +613,7 @@ static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req,
* };
*/
static void encode_readargs(struct xdr_stream *xdr,
- const struct nfs_readargs *args)
+ const struct nfs_pgio_args *args)
{
u32 offset = args->offset;
u32 count = args->count;
@@ -629,7 +629,7 @@ static void encode_readargs(struct xdr_stream *xdr,
static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
struct xdr_stream *xdr,
- const struct nfs_readargs *args)
+ const struct nfs_pgio_args *args)
{
encode_readargs(xdr, args);
prepare_reply_buffer(req, args->pages, args->pgbase,
@@ -649,7 +649,7 @@ static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
* };
*/
static void encode_writeargs(struct xdr_stream *xdr,
- const struct nfs_writeargs *args)
+ const struct nfs_pgio_args *args)
{
u32 offset = args->offset;
u32 count = args->count;
@@ -669,7 +669,7 @@ static void encode_writeargs(struct xdr_stream *xdr,
static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req,
struct xdr_stream *xdr,
- const struct nfs_writeargs *args)
+ const struct nfs_pgio_args *args)
{
encode_writeargs(xdr, args);
xdr->buf->flags |= XDRBUF_WRITE;
@@ -857,7 +857,7 @@ out_default:
* };
*/
static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
- struct nfs_readres *result)
+ struct nfs_pgio_res *result)
{
enum nfs_stat status;
int error;
@@ -878,7 +878,7 @@ out_default:
}
static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
- struct nfs_writeres *result)
+ struct nfs_pgio_res *result)
{
/* All NFSv2 writes are "file sync" writes */
result->verf->committed = NFS_FILE_SYNC;
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index db60149c4579..e7daa42bbc86 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -795,7 +795,7 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
return status;
}
-static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
{
struct inode *inode = data->header->inode;
@@ -807,18 +807,18 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
return 0;
}
-static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
+static void nfs3_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
}
-static int nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
{
rpc_call_start(task);
return 0;
}
-static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
{
struct inode *inode = data->header->inode;
@@ -829,17 +829,11 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
return 0;
}
-static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs3_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
}
-static int nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
-{
- rpc_call_start(task);
- return 0;
-}
-
static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
{
rpc_call_start(task);
@@ -946,13 +940,10 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.fsinfo = nfs3_proc_fsinfo,
.pathconf = nfs3_proc_pathconf,
.decode_dirent = nfs3_decode_dirent,
+ .pgio_rpc_prepare = nfs3_proc_pgio_rpc_prepare,
.read_setup = nfs3_proc_read_setup,
- .read_pageio_init = nfs_pageio_init_read,
- .read_rpc_prepare = nfs3_proc_read_rpc_prepare,
.read_done = nfs3_read_done,
.write_setup = nfs3_proc_write_setup,
- .write_pageio_init = nfs_pageio_init_write,
- .write_rpc_prepare = nfs3_proc_write_rpc_prepare,
.write_done = nfs3_write_done,
.commit_setup = nfs3_proc_commit_setup,
.commit_rpc_prepare = nfs3_proc_commit_rpc_prepare,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index fa6d72131c19..8f4cbe7f4aa8 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -953,7 +953,7 @@ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req,
* };
*/
static void encode_read3args(struct xdr_stream *xdr,
- const struct nfs_readargs *args)
+ const struct nfs_pgio_args *args)
{
__be32 *p;
@@ -966,7 +966,7 @@ static void encode_read3args(struct xdr_stream *xdr,
static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
struct xdr_stream *xdr,
- const struct nfs_readargs *args)
+ const struct nfs_pgio_args *args)
{
encode_read3args(xdr, args);
prepare_reply_buffer(req, args->pages, args->pgbase,
@@ -992,7 +992,7 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
* };
*/
static void encode_write3args(struct xdr_stream *xdr,
- const struct nfs_writeargs *args)
+ const struct nfs_pgio_args *args)
{
__be32 *p;
@@ -1008,7 +1008,7 @@ static void encode_write3args(struct xdr_stream *xdr,
static void nfs3_xdr_enc_write3args(struct rpc_rqst *req,
struct xdr_stream *xdr,
- const struct nfs_writeargs *args)
+ const struct nfs_pgio_args *args)
{
encode_write3args(xdr, args);
xdr->buf->flags |= XDRBUF_WRITE;
@@ -1589,7 +1589,7 @@ out_default:
* };
*/
static int decode_read3resok(struct xdr_stream *xdr,
- struct nfs_readres *result)
+ struct nfs_pgio_res *result)
{
u32 eof, count, ocount, recvd;
__be32 *p;
@@ -1625,7 +1625,7 @@ out_overflow:
}
static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
- struct nfs_readres *result)
+ struct nfs_pgio_res *result)
{
enum nfs_stat status;
int error;
@@ -1673,7 +1673,7 @@ out_status:
* };
*/
static int decode_write3resok(struct xdr_stream *xdr,
- struct nfs_writeres *result)
+ struct nfs_pgio_res *result)
{
__be32 *p;
@@ -1697,7 +1697,7 @@ out_eio:
}
static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
- struct nfs_writeres *result)
+ struct nfs_pgio_res *result)
{
enum nfs_stat status;
int error;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index e1d1badbe53c..f63cb87cd730 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -337,7 +337,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
*/
static inline void
nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
- struct rpc_message *msg, struct nfs_write_data *wdata)
+ struct rpc_message *msg, struct nfs_pgio_data *wdata)
{
if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) &&
!test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags))
@@ -369,7 +369,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags,
static inline void
nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
- struct rpc_message *msg, struct nfs_write_data *wdata)
+ struct rpc_message *msg, struct nfs_pgio_data *wdata)
{
}
#endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 8de3407e0360..464db9dd6318 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -100,8 +100,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
break;
mutex_lock(&inode->i_mutex);
ret = nfs_file_fsync_commit(file, start, end, datasync);
- if (!ret && !datasync)
- /* application has asked for meta-data sync */
+ if (!ret)
ret = pnfs_layoutcommit_inode(inode, true);
mutex_unlock(&inode->i_mutex);
/*
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 397be39c6dc8..285ad5334018 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2027,7 +2027,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
return status;
}
if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
- _nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
+ nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
return 0;
}
@@ -2750,7 +2750,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
-#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_CHANGE_SECURITY_LABEL - 1UL)
+#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_SECURITY_LABEL - 1UL)
static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
{
@@ -4033,12 +4033,12 @@ static bool nfs4_error_stateid_expired(int err)
return false;
}
-void __nfs4_read_done_cb(struct nfs_read_data *data)
+void __nfs4_read_done_cb(struct nfs_pgio_data *data)
{
nfs_invalidate_atime(data->header->inode);
}
-static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_data *data)
{
struct nfs_server *server = NFS_SERVER(data->header->inode);
@@ -4055,7 +4055,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
}
static bool nfs4_read_stateid_changed(struct rpc_task *task,
- struct nfs_readargs *args)
+ struct nfs_pgio_args *args)
{
if (!nfs4_error_stateid_expired(task->tk_status) ||
@@ -4068,7 +4068,7 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task,
return true;
}
-static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
{
dprintk("--> %s\n", __func__);
@@ -4077,19 +4077,19 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
return -EAGAIN;
if (nfs4_read_stateid_changed(task, &data->args))
return -EAGAIN;
- return data->read_done_cb ? data->read_done_cb(task, data) :
+ return data->pgio_done_cb ? data->pgio_done_cb(task, data) :
nfs4_read_done_cb(task, data);
}
-static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
+static void nfs4_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
{
data->timestamp = jiffies;
- data->read_done_cb = nfs4_read_done_cb;
+ data->pgio_done_cb = nfs4_read_done_cb;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
}
-static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
{
if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
&data->args.seq_args,
@@ -4097,14 +4097,14 @@ static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat
task))
return 0;
if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
- data->args.lock_context, FMODE_READ) == -EIO)
+ data->args.lock_context, data->header->rw_ops->rw_mode) == -EIO)
return -EIO;
if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
return -EIO;
return 0;
}
-static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_pgio_data *data)
{
struct inode *inode = data->header->inode;
@@ -4121,7 +4121,7 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data
}
static bool nfs4_write_stateid_changed(struct rpc_task *task,
- struct nfs_writeargs *args)
+ struct nfs_pgio_args *args)
{
if (!nfs4_error_stateid_expired(task->tk_status) ||
@@ -4134,18 +4134,18 @@ static bool nfs4_write_stateid_changed(struct rpc_task *task,
return true;
}
-static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
{
if (!nfs4_sequence_done(task, &data->res.seq_res))
return -EAGAIN;
if (nfs4_write_stateid_changed(task, &data->args))
return -EAGAIN;
- return data->write_done_cb ? data->write_done_cb(task, data) :
+ return data->pgio_done_cb ? data->pgio_done_cb(task, data) :
nfs4_write_done_cb(task, data);
}
static
-bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
+bool nfs4_write_need_cache_consistency_data(const struct nfs_pgio_data *data)
{
const struct nfs_pgio_header *hdr = data->header;
@@ -4158,7 +4158,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
}
-static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs4_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
{
struct nfs_server *server = NFS_SERVER(data->header->inode);
@@ -4168,8 +4168,8 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
} else
data->args.bitmask = server->cache_consistency_bitmask;
- if (!data->write_done_cb)
- data->write_done_cb = nfs4_write_done_cb;
+ if (!data->pgio_done_cb)
+ data->pgio_done_cb = nfs4_write_done_cb;
data->res.server = server;
data->timestamp = jiffies;
@@ -4177,21 +4177,6 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
}
-static int nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
-{
- if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
- &data->args.seq_args,
- &data->res.seq_res,
- task))
- return 0;
- if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
- data->args.lock_context, FMODE_WRITE) == -EIO)
- return -EIO;
- if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
- return -EIO;
- return 0;
-}
-
static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
{
nfs4_setup_sequence(NFS_SERVER(data->inode),
@@ -8432,13 +8417,10 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.pathconf = nfs4_proc_pathconf,
.set_capabilities = nfs4_server_capabilities,
.decode_dirent = nfs4_decode_dirent,
+ .pgio_rpc_prepare = nfs4_proc_pgio_rpc_prepare,
.read_setup = nfs4_proc_read_setup,
- .read_pageio_init = pnfs_pageio_init_read,
- .read_rpc_prepare = nfs4_proc_read_rpc_prepare,
.read_done = nfs4_read_done,
.write_setup = nfs4_proc_write_setup,
- .write_pageio_init = pnfs_pageio_init_write,
- .write_rpc_prepare = nfs4_proc_write_rpc_prepare,
.write_done = nfs4_write_done,
.commit_setup = nfs4_proc_commit_setup,
.commit_rpc_prepare = nfs4_proc_commit_rpc_prepare,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2349518eef2c..848f6853c59e 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1140,9 +1140,9 @@ static int nfs4_run_state_manager(void *);
static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING);
rpc_wake_up(&clp->cl_rpcwaitq);
}
@@ -1456,7 +1456,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
* server that doesn't support a grace period.
*/
spin_lock(&sp->so_lock);
- write_seqcount_begin(&sp->so_reclaim_seqcount);
+ raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
restart:
list_for_each_entry(state, &sp->so_states, open_states) {
if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1519,13 +1519,13 @@ restart:
spin_lock(&sp->so_lock);
goto restart;
}
- write_seqcount_end(&sp->so_reclaim_seqcount);
+ raw_write_seqcount_end(&sp->so_reclaim_seqcount);
spin_unlock(&sp->so_lock);
return 0;
out_err:
nfs4_put_open_state(state);
spin_lock(&sp->so_lock);
- write_seqcount_end(&sp->so_reclaim_seqcount);
+ raw_write_seqcount_end(&sp->so_reclaim_seqcount);
spin_unlock(&sp->so_lock);
return status;
}
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 2628d921b7e3..b6ebe7e445f6 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -16,7 +16,7 @@ static const int nfs_set_port_min = 0;
static const int nfs_set_port_max = 65535;
static struct ctl_table_header *nfs4_callback_sysctl_table;
-static ctl_table nfs4_cb_sysctls[] = {
+static struct ctl_table nfs4_cb_sysctls[] = {
{
.procname = "nfs_callback_tcpport",
.data = &nfs_callback_set_tcpport,
@@ -36,7 +36,7 @@ static ctl_table nfs4_cb_sysctls[] = {
{ }
};
-static ctl_table nfs4_cb_sysctl_dir[] = {
+static struct ctl_table nfs4_cb_sysctl_dir[] = {
{
.procname = "nfs",
.mode = 0555,
@@ -45,7 +45,7 @@ static ctl_table nfs4_cb_sysctl_dir[] = {
{ }
};
-static ctl_table nfs4_cb_sysctl_root[] = {
+static struct ctl_table nfs4_cb_sysctl_root[] = {
{
.procname = "fs",
.mode = 0555,
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 849cf146db30..0a744f3a86f6 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -932,7 +932,7 @@ DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group);
DECLARE_EVENT_CLASS(nfs4_read_event,
TP_PROTO(
- const struct nfs_read_data *data,
+ const struct nfs_pgio_data *data,
int error
),
@@ -972,7 +972,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
#define DEFINE_NFS4_READ_EVENT(name) \
DEFINE_EVENT(nfs4_read_event, name, \
TP_PROTO( \
- const struct nfs_read_data *data, \
+ const struct nfs_pgio_data *data, \
int error \
), \
TP_ARGS(data, error))
@@ -983,7 +983,7 @@ DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read);
DECLARE_EVENT_CLASS(nfs4_write_event,
TP_PROTO(
- const struct nfs_write_data *data,
+ const struct nfs_pgio_data *data,
int error
),
@@ -1024,7 +1024,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
#define DEFINE_NFS4_WRITE_EVENT(name) \
DEFINE_EVENT(nfs4_write_event, name, \
TP_PROTO( \
- const struct nfs_write_data *data, \
+ const struct nfs_pgio_data *data, \
int error \
), \
TP_ARGS(data, error))
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 73ce8d4fe2c8..939ae606cfa4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1556,7 +1556,8 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr);
}
-static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr)
+static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args,
+ struct compound_hdr *hdr)
{
__be32 *p;
@@ -1701,7 +1702,8 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4
encode_nfs4_verifier(xdr, &arg->confirm);
}
-static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
+static void encode_write(struct xdr_stream *xdr, const struct nfs_pgio_args *args,
+ struct compound_hdr *hdr)
{
__be32 *p;
@@ -2451,7 +2453,7 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr,
* Encode a READ request
*/
static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
- struct nfs_readargs *args)
+ struct nfs_pgio_args *args)
{
struct compound_hdr hdr = {
.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@@ -2513,7 +2515,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
* Encode a WRITE request
*/
static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
- struct nfs_writeargs *args)
+ struct nfs_pgio_args *args)
{
struct compound_hdr hdr = {
.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@@ -5085,7 +5087,8 @@ static int decode_putrootfh(struct xdr_stream *xdr)
return decode_op_hdr(xdr, OP_PUTROOTFH);
}
-static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res)
+static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req,
+ struct nfs_pgio_res *res)
{
__be32 *p;
uint32_t count, eof, recvd;
@@ -5339,7 +5342,7 @@ static int decode_setclientid_confirm(struct xdr_stream *xdr)
return decode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM);
}
-static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
+static int decode_write(struct xdr_stream *xdr, struct nfs_pgio_res *res)
{
__be32 *p;
int status;
@@ -6636,7 +6639,7 @@ out:
* Decode Read response
*/
static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
- struct nfs_readres *res)
+ struct nfs_pgio_res *res)
{
struct compound_hdr hdr;
int status;
@@ -6661,7 +6664,7 @@ out:
* Decode WRITE response
*/
static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
- struct nfs_writeres *res)
+ struct nfs_pgio_res *res)
{
struct compound_hdr hdr;
int status;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 5457745dd4f1..611320753db2 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -439,7 +439,7 @@ static void _read_done(struct ore_io_state *ios, void *private)
objlayout_read_done(&objios->oir, status, objios->sync);
}
-int objio_read_pagelist(struct nfs_read_data *rdata)
+int objio_read_pagelist(struct nfs_pgio_data *rdata)
{
struct nfs_pgio_header *hdr = rdata->header;
struct objio_state *objios;
@@ -487,7 +487,7 @@ static void _write_done(struct ore_io_state *ios, void *private)
static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
{
struct objio_state *objios = priv;
- struct nfs_write_data *wdata = objios->oir.rpcdata;
+ struct nfs_pgio_data *wdata = objios->oir.rpcdata;
struct address_space *mapping = wdata->header->inode->i_mapping;
pgoff_t index = offset / PAGE_SIZE;
struct page *page;
@@ -531,7 +531,7 @@ static const struct _ore_r4w_op _r4w_op = {
.put_page = &__r4w_put_page,
};
-int objio_write_pagelist(struct nfs_write_data *wdata, int how)
+int objio_write_pagelist(struct nfs_pgio_data *wdata, int how)
{
struct nfs_pgio_header *hdr = wdata->header;
struct objio_state *objios;
@@ -564,14 +564,22 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how)
return 0;
}
-static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
struct nfs_page *prev, struct nfs_page *req)
{
- if (!pnfs_generic_pg_test(pgio, prev, req))
- return false;
+ unsigned int size;
+
+ size = pnfs_generic_pg_test(pgio, prev, req);
+
+ if (!size || pgio->pg_count + req->wb_bytes >
+ (unsigned long)pgio->pg_layout_private)
+ return 0;
- return pgio->pg_count + req->wb_bytes <=
- (unsigned long)pgio->pg_layout_private;
+ return min(size, req->wb_bytes);
}
static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index e4f9cbfec67b..765d3f54e986 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -53,10 +53,10 @@ objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
struct objlayout *objlay;
objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
- if (objlay) {
- spin_lock_init(&objlay->lock);
- INIT_LIST_HEAD(&objlay->err_list);
- }
+ if (!objlay)
+ return NULL;
+ spin_lock_init(&objlay->lock);
+ INIT_LIST_HEAD(&objlay->err_list);
dprintk("%s: Return %p\n", __func__, objlay);
return &objlay->pnfs_layout;
}
@@ -229,11 +229,11 @@ objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
static void _rpc_read_complete(struct work_struct *work)
{
struct rpc_task *task;
- struct nfs_read_data *rdata;
+ struct nfs_pgio_data *rdata;
dprintk("%s enter\n", __func__);
task = container_of(work, struct rpc_task, u.tk_work);
- rdata = container_of(task, struct nfs_read_data, task);
+ rdata = container_of(task, struct nfs_pgio_data, task);
pnfs_ld_read_done(rdata);
}
@@ -241,7 +241,7 @@ static void _rpc_read_complete(struct work_struct *work)
void
objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
{
- struct nfs_read_data *rdata = oir->rpcdata;
+ struct nfs_pgio_data *rdata = oir->rpcdata;
oir->status = rdata->task.tk_status = status;
if (status >= 0)
@@ -266,7 +266,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
* Perform sync or async reads.
*/
enum pnfs_try_status
-objlayout_read_pagelist(struct nfs_read_data *rdata)
+objlayout_read_pagelist(struct nfs_pgio_data *rdata)
{
struct nfs_pgio_header *hdr = rdata->header;
struct inode *inode = hdr->inode;
@@ -312,11 +312,11 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
static void _rpc_write_complete(struct work_struct *work)
{
struct rpc_task *task;
- struct nfs_write_data *wdata;
+ struct nfs_pgio_data *wdata;
dprintk("%s enter\n", __func__);
task = container_of(work, struct rpc_task, u.tk_work);
- wdata = container_of(task, struct nfs_write_data, task);
+ wdata = container_of(task, struct nfs_pgio_data, task);
pnfs_ld_write_done(wdata);
}
@@ -324,7 +324,7 @@ static void _rpc_write_complete(struct work_struct *work)
void
objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
{
- struct nfs_write_data *wdata = oir->rpcdata;
+ struct nfs_pgio_data *wdata = oir->rpcdata;
oir->status = wdata->task.tk_status = status;
if (status >= 0) {
@@ -351,7 +351,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
* Perform sync or async writes.
*/
enum pnfs_try_status
-objlayout_write_pagelist(struct nfs_write_data *wdata,
+objlayout_write_pagelist(struct nfs_pgio_data *wdata,
int how)
{
struct nfs_pgio_header *hdr = wdata->header;
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index 87aa1dec6120..01e041029a6c 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -119,8 +119,8 @@ extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
*/
extern void objio_free_result(struct objlayout_io_res *oir);
-extern int objio_read_pagelist(struct nfs_read_data *rdata);
-extern int objio_write_pagelist(struct nfs_write_data *wdata, int how);
+extern int objio_read_pagelist(struct nfs_pgio_data *rdata);
+extern int objio_write_pagelist(struct nfs_pgio_data *wdata, int how);
/*
* callback API
@@ -168,10 +168,10 @@ extern struct pnfs_layout_segment *objlayout_alloc_lseg(
extern void objlayout_free_lseg(struct pnfs_layout_segment *);
extern enum pnfs_try_status objlayout_read_pagelist(
- struct nfs_read_data *);
+ struct nfs_pgio_data *);
extern enum pnfs_try_status objlayout_write_pagelist(
- struct nfs_write_data *,
+ struct nfs_pgio_data *,
int how);
extern void objlayout_encode_layoutcommit(
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 2ffebf2081ce..b6ee3a6ee96d 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -24,9 +24,14 @@
#include "internal.h"
#include "pnfs.h"
+#define NFSDBG_FACILITY NFSDBG_PAGECACHE
+
static struct kmem_cache *nfs_page_cachep;
+static const struct rpc_call_ops nfs_pgio_common_ops;
+
+static void nfs_free_request(struct nfs_page *);
-bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
+static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
{
p->npages = pagecount;
if (pagecount <= ARRAY_SIZE(p->page_array))
@@ -95,7 +100,7 @@ nfs_iocounter_dec(struct nfs_io_counter *c)
{
if (atomic_dec_and_test(&c->io_count)) {
clear_bit(NFS_IO_INPROGRESS, &c->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
}
}
@@ -133,11 +138,156 @@ nfs_iocounter_wait(struct nfs_io_counter *c)
return __nfs_iocounter_wait(c);
}
+static int nfs_wait_bit_uninterruptible(void *word)
+{
+ io_schedule();
+ return 0;
+}
+
+/*
+ * nfs_page_group_lock - lock the head of the page group
+ * @req - request in group that is to be locked
+ *
+ * this lock must be held if modifying the page group list
+ */
+void
+nfs_page_group_lock(struct nfs_page *req)
+{
+ struct nfs_page *head = req->wb_head;
+
+ WARN_ON_ONCE(head != head->wb_head);
+
+ wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
+ nfs_wait_bit_uninterruptible,
+ TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * nfs_page_group_unlock - unlock the head of the page group
+ * @req - request in group that is to be unlocked
+ */
+void
+nfs_page_group_unlock(struct nfs_page *req)
+{
+ struct nfs_page *head = req->wb_head;
+
+ WARN_ON_ONCE(head != head->wb_head);
+
+ smp_mb__before_atomic();
+ clear_bit(PG_HEADLOCK, &head->wb_flags);
+ smp_mb__after_atomic();
+ wake_up_bit(&head->wb_flags, PG_HEADLOCK);
+}
+
+/*
+ * nfs_page_group_sync_on_bit_locked
+ *
+ * must be called with page group lock held
+ */
+static bool
+nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit)
+{
+ struct nfs_page *head = req->wb_head;
+ struct nfs_page *tmp;
+
+ WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_flags));
+ WARN_ON_ONCE(test_and_set_bit(bit, &req->wb_flags));
+
+ tmp = req->wb_this_page;
+ while (tmp != req) {
+ if (!test_bit(bit, &tmp->wb_flags))
+ return false;
+ tmp = tmp->wb_this_page;
+ }
+
+ /* true! reset all bits */
+ tmp = req;
+ do {
+ clear_bit(bit, &tmp->wb_flags);
+ tmp = tmp->wb_this_page;
+ } while (tmp != req);
+
+ return true;
+}
+
+/*
+ * nfs_page_group_sync_on_bit - set bit on current request, but only
+ * return true if the bit is set for all requests in page group
+ * @req - request in page group
+ * @bit - PG_* bit that is used to sync page group
+ */
+bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit)
+{
+ bool ret;
+
+ nfs_page_group_lock(req);
+ ret = nfs_page_group_sync_on_bit_locked(req, bit);
+ nfs_page_group_unlock(req);
+
+ return ret;
+}
+
+/*
+ * nfs_page_group_init - Initialize the page group linkage for @req
+ * @req - a new nfs request
+ * @prev - the previous request in page group, or NULL if @req is the first
+ * or only request in the group (the head).
+ */
+static inline void
+nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
+{
+ WARN_ON_ONCE(prev == req);
+
+ if (!prev) {
+ req->wb_head = req;
+ req->wb_this_page = req;
+ } else {
+ WARN_ON_ONCE(prev->wb_this_page != prev->wb_head);
+ WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags));
+ req->wb_head = prev->wb_head;
+ req->wb_this_page = prev->wb_this_page;
+ prev->wb_this_page = req;
+
+ /* grab extra ref if head request has extra ref from
+ * the write/commit path to handle handoff between write
+ * and commit lists */
+ if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags))
+ kref_get(&req->wb_kref);
+ }
+}
+
+/*
+ * nfs_page_group_destroy - sync the destruction of page groups
+ * @req - request that no longer needs the page group
+ *
+ * releases the page group reference from each member once all
+ * members have called this function.
+ */
+static void
+nfs_page_group_destroy(struct kref *kref)
+{
+ struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
+ struct nfs_page *tmp, *next;
+
+ if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN))
+ return;
+
+ tmp = req;
+ do {
+ next = tmp->wb_this_page;
+ /* unlink and free */
+ tmp->wb_this_page = tmp;
+ tmp->wb_head = tmp;
+ nfs_free_request(tmp);
+ tmp = next;
+ } while (tmp != req);
+}
+
/**
* nfs_create_request - Create an NFS read/write request.
* @ctx: open context to use
- * @inode: inode to which the request is attached
* @page: page to write
+ * @last: last nfs request created for this page group or NULL if head
* @offset: starting offset within the page for the write
* @count: number of bytes to read/write
*
@@ -146,9 +296,9 @@ nfs_iocounter_wait(struct nfs_io_counter *c)
* User should ensure it is safe to sleep in this function.
*/
struct nfs_page *
-nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
- struct page *page,
- unsigned int offset, unsigned int count)
+nfs_create_request(struct nfs_open_context *ctx, struct page *page,
+ struct nfs_page *last, unsigned int offset,
+ unsigned int count)
{
struct nfs_page *req;
struct nfs_lock_context *l_ctx;
@@ -180,6 +330,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
req->wb_bytes = count;
req->wb_context = get_nfs_open_context(ctx);
kref_init(&req->wb_kref);
+ nfs_page_group_init(req, last);
return req;
}
@@ -193,9 +344,9 @@ void nfs_unlock_request(struct nfs_page *req)
printk(KERN_ERR "NFS: Invalid unlock attempted\n");
BUG();
}
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(PG_BUSY, &req->wb_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&req->wb_flags, PG_BUSY);
}
@@ -237,16 +388,22 @@ static void nfs_clear_request(struct nfs_page *req)
}
}
-
/**
* nfs_release_request - Release the count on an NFS read/write request
* @req: request to release
*
* Note: Should never be called with the spinlock held!
*/
-static void nfs_free_request(struct kref *kref)
+static void nfs_free_request(struct nfs_page *req)
{
- struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
+ WARN_ON_ONCE(req->wb_this_page != req);
+
+ /* extra debug: make sure no sync bits are still set */
+ WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags));
+ WARN_ON_ONCE(test_bit(PG_UNLOCKPAGE, &req->wb_flags));
+ WARN_ON_ONCE(test_bit(PG_UPTODATE, &req->wb_flags));
+ WARN_ON_ONCE(test_bit(PG_WB_END, &req->wb_flags));
+ WARN_ON_ONCE(test_bit(PG_REMOVE, &req->wb_flags));
/* Release struct file and open context */
nfs_clear_request(req);
@@ -255,13 +412,7 @@ static void nfs_free_request(struct kref *kref)
void nfs_release_request(struct nfs_page *req)
{
- kref_put(&req->wb_kref, nfs_free_request);
-}
-
-static int nfs_wait_bit_uninterruptible(void *word)
-{
- io_schedule();
- return 0;
+ kref_put(&req->wb_kref, nfs_page_group_destroy);
}
/**
@@ -279,22 +430,249 @@ nfs_wait_on_request(struct nfs_page *req)
TASK_UNINTERRUPTIBLE);
}
-bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req)
+/*
+ * nfs_generic_pg_test - determine if requests can be coalesced
+ * @desc: pointer to descriptor
+ * @prev: previous request in desc, or NULL
+ * @req: this request
+ *
+ * Returns zero if @req can be coalesced into @desc, otherwise it returns
+ * the size of the request.
+ */
+size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
+ struct nfs_page *prev, struct nfs_page *req)
{
- /*
- * FIXME: ideally we should be able to coalesce all requests
- * that are not block boundary aligned, but currently this
- * is problematic for the case of bsize < PAGE_CACHE_SIZE,
- * since nfs_flush_multi and nfs_pagein_multi assume you
- * can have only one struct nfs_page.
- */
- if (desc->pg_bsize < PAGE_SIZE)
+ if (desc->pg_count > desc->pg_bsize) {
+ /* should never happen */
+ WARN_ON_ONCE(1);
return 0;
+ }
- return desc->pg_count + req->wb_bytes <= desc->pg_bsize;
+ return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
}
EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
+static inline struct nfs_rw_header *NFS_RW_HEADER(struct nfs_pgio_header *hdr)
+{
+ return container_of(hdr, struct nfs_rw_header, header);
+}
+
+/**
+ * nfs_rw_header_alloc - Allocate a header for a read or write
+ * @ops: Read or write function vector
+ */
+struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *ops)
+{
+ struct nfs_rw_header *header = ops->rw_alloc_header();
+
+ if (header) {
+ struct nfs_pgio_header *hdr = &header->header;
+
+ INIT_LIST_HEAD(&hdr->pages);
+ spin_lock_init(&hdr->lock);
+ atomic_set(&hdr->refcnt, 0);
+ hdr->rw_ops = ops;
+ }
+ return header;
+}
+EXPORT_SYMBOL_GPL(nfs_rw_header_alloc);
+
+/*
+ * nfs_rw_header_free - Free a read or write header
+ * @hdr: The header to free
+ */
+void nfs_rw_header_free(struct nfs_pgio_header *hdr)
+{
+ hdr->rw_ops->rw_free_header(NFS_RW_HEADER(hdr));
+}
+EXPORT_SYMBOL_GPL(nfs_rw_header_free);
+
+/**
+ * nfs_pgio_data_alloc - Allocate pageio data
+ * @hdr: The header making a request
+ * @pagecount: Number of pages to create
+ */
+static struct nfs_pgio_data *nfs_pgio_data_alloc(struct nfs_pgio_header *hdr,
+ unsigned int pagecount)
+{
+ struct nfs_pgio_data *data, *prealloc;
+
+ prealloc = &NFS_RW_HEADER(hdr)->rpc_data;
+ if (prealloc->header == NULL)
+ data = prealloc;
+ else
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out;
+
+ if (nfs_pgarray_set(&data->pages, pagecount)) {
+ data->header = hdr;
+ atomic_inc(&hdr->refcnt);
+ } else {
+ if (data != prealloc)
+ kfree(data);
+ data = NULL;
+ }
+out:
+ return data;
+}
+
+/**
+ * nfs_pgio_data_release - Properly free pageio data
+ * @data: The data to release
+ */
+void nfs_pgio_data_release(struct nfs_pgio_data *data)
+{
+ struct nfs_pgio_header *hdr = data->header;
+ struct nfs_rw_header *pageio_header = NFS_RW_HEADER(hdr);
+
+ put_nfs_open_context(data->args.context);
+ if (data->pages.pagevec != data->pages.page_array)
+ kfree(data->pages.pagevec);
+ if (data == &pageio_header->rpc_data) {
+ data->header = NULL;
+ data = NULL;
+ }
+ if (atomic_dec_and_test(&hdr->refcnt))
+ hdr->completion_ops->completion(hdr);
+ /* Note: we only free the rpc_task after callbacks are done.
+ * See the comment in rpc_free_task() for why
+ */
+ kfree(data);
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_data_release);
+
+/**
+ * nfs_pgio_rpcsetup - Set up arguments for a pageio call
+ * @data: The pageio data
+ * @count: Number of bytes to read
+ * @offset: Initial offset
+ * @how: How to commit data (writes only)
+ * @cinfo: Commit information for the call (writes only)
+ */
+static void nfs_pgio_rpcsetup(struct nfs_pgio_data *data,
+ unsigned int count, unsigned int offset,
+ int how, struct nfs_commit_info *cinfo)
+{
+ struct nfs_page *req = data->header->req;
+
+ /* Set up the RPC argument and reply structs
+ * NB: take care not to mess about with data->commit et al. */
+
+ data->args.fh = NFS_FH(data->header->inode);
+ data->args.offset = req_offset(req) + offset;
+ /* pnfs_set_layoutcommit needs this */
+ data->mds_offset = data->args.offset;
+ data->args.pgbase = req->wb_pgbase + offset;
+ data->args.pages = data->pages.pagevec;
+ data->args.count = count;
+ data->args.context = get_nfs_open_context(req->wb_context);
+ data->args.lock_context = req->wb_lock_context;
+ data->args.stable = NFS_UNSTABLE;
+ switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
+ case 0:
+ break;
+ case FLUSH_COND_STABLE:
+ if (nfs_reqs_to_commit(cinfo))
+ break;
+ default:
+ data->args.stable = NFS_FILE_SYNC;
+ }
+
+ data->res.fattr = &data->fattr;
+ data->res.count = count;
+ data->res.eof = 0;
+ data->res.verf = &data->verf;
+ nfs_fattr_init(&data->fattr);
+}
+
+/**
+ * nfs_pgio_prepare - Prepare pageio data to go over the wire
+ * @task: The current task
+ * @calldata: pageio data to prepare
+ */
+static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
+{
+ struct nfs_pgio_data *data = calldata;
+ int err;
+ err = NFS_PROTO(data->header->inode)->pgio_rpc_prepare(task, data);
+ if (err)
+ rpc_exit(task, err);
+}
+
+int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_data *data,
+ const struct rpc_call_ops *call_ops, int how, int flags)
+{
+ struct rpc_task *task;
+ struct rpc_message msg = {
+ .rpc_argp = &data->args,
+ .rpc_resp = &data->res,
+ .rpc_cred = data->header->cred,
+ };
+ struct rpc_task_setup task_setup_data = {
+ .rpc_client = clnt,
+ .task = &data->task,
+ .rpc_message = &msg,
+ .callback_ops = call_ops,
+ .callback_data = data,
+ .workqueue = nfsiod_workqueue,
+ .flags = RPC_TASK_ASYNC | flags,
+ };
+ int ret = 0;
+
+ data->header->rw_ops->rw_initiate(data, &msg, &task_setup_data, how);
+
+ dprintk("NFS: %5u initiated pgio call "
+ "(req %s/%llu, %u bytes @ offset %llu)\n",
+ data->task.tk_pid,
+ data->header->inode->i_sb->s_id,
+ (unsigned long long)NFS_FILEID(data->header->inode),
+ data->args.count,
+ (unsigned long long)data->args.offset);
+
+ task = rpc_run_task(&task_setup_data);
+ if (IS_ERR(task)) {
+ ret = PTR_ERR(task);
+ goto out;
+ }
+ if (how & FLUSH_SYNC) {
+ ret = rpc_wait_for_completion_task(task);
+ if (ret == 0)
+ ret = task->tk_status;
+ }
+ rpc_put_task(task);
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_initiate_pgio);
+
+/**
+ * nfs_pgio_error - Clean up from a pageio error
+ * @desc: IO descriptor
+ * @hdr: pageio header
+ */
+static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr)
+{
+ set_bit(NFS_IOHDR_REDO, &hdr->flags);
+ nfs_pgio_data_release(hdr->data);
+ hdr->data = NULL;
+ desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+ return -ENOMEM;
+}
+
+/**
+ * nfs_pgio_release - Release pageio data
+ * @calldata: The pageio data to release
+ */
+static void nfs_pgio_release(void *calldata)
+{
+ struct nfs_pgio_data *data = calldata;
+ if (data->header->rw_ops->rw_release)
+ data->header->rw_ops->rw_release(data);
+ nfs_pgio_data_release(data);
+}
+
/**
* nfs_pageio_init - initialise a page io descriptor
* @desc: pointer to descriptor
@@ -307,6 +685,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
struct inode *inode,
const struct nfs_pageio_ops *pg_ops,
const struct nfs_pgio_completion_ops *compl_ops,
+ const struct nfs_rw_ops *rw_ops,
size_t bsize,
int io_flags)
{
@@ -320,6 +699,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
desc->pg_inode = inode;
desc->pg_ops = pg_ops;
desc->pg_completion_ops = compl_ops;
+ desc->pg_rw_ops = rw_ops;
desc->pg_ioflags = io_flags;
desc->pg_error = 0;
desc->pg_lseg = NULL;
@@ -328,6 +708,94 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
}
EXPORT_SYMBOL_GPL(nfs_pageio_init);
+/**
+ * nfs_pgio_result - Basic pageio error handling
+ * @task: The task that ran
+ * @calldata: Pageio data to check
+ */
+static void nfs_pgio_result(struct rpc_task *task, void *calldata)
+{
+ struct nfs_pgio_data *data = calldata;
+ struct inode *inode = data->header->inode;
+
+ dprintk("NFS: %s: %5u, (status %d)\n", __func__,
+ task->tk_pid, task->tk_status);
+
+ if (data->header->rw_ops->rw_done(task, data, inode) != 0)
+ return;
+ if (task->tk_status < 0)
+ nfs_set_pgio_error(data->header, task->tk_status, data->args.offset);
+ else
+ data->header->rw_ops->rw_result(task, data);
+}
+
+/*
+ * Create an RPC task for the given read or write request and kick it.
+ * The page must have been locked by the caller.
+ *
+ * It may happen that the page we're passed is not marked dirty.
+ * This is the case if nfs_updatepage detects a conflicting request
+ * that has been written but not committed.
+ */
+int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr)
+{
+ struct nfs_page *req;
+ struct page **pages;
+ struct nfs_pgio_data *data;
+ struct list_head *head = &desc->pg_list;
+ struct nfs_commit_info cinfo;
+
+ data = nfs_pgio_data_alloc(hdr, nfs_page_array_len(desc->pg_base,
+ desc->pg_count));
+ if (!data)
+ return nfs_pgio_error(desc, hdr);
+
+ nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
+ pages = data->pages.pagevec;
+ while (!list_empty(head)) {
+ req = nfs_list_entry(head->next);
+ nfs_list_remove_request(req);
+ nfs_list_add_request(req, &hdr->pages);
+ *pages++ = req->wb_page;
+ }
+
+ if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
+ (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
+ desc->pg_ioflags &= ~FLUSH_COND_STABLE;
+
+ /* Set up the argument struct */
+ nfs_pgio_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
+ hdr->data = data;
+ desc->pg_rpc_callops = &nfs_pgio_common_ops;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nfs_generic_pgio);
+
+static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
+{
+ struct nfs_rw_header *rw_hdr;
+ struct nfs_pgio_header *hdr;
+ int ret;
+
+ rw_hdr = nfs_rw_header_alloc(desc->pg_rw_ops);
+ if (!rw_hdr) {
+ desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+ return -ENOMEM;
+ }
+ hdr = &rw_hdr->header;
+ nfs_pgheader_init(desc, hdr, nfs_rw_header_free);
+ atomic_inc(&hdr->refcnt);
+ ret = nfs_generic_pgio(desc, hdr);
+ if (ret == 0)
+ ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
+ hdr->data, desc->pg_rpc_callops,
+ desc->pg_ioflags, 0);
+ if (atomic_dec_and_test(&hdr->refcnt))
+ hdr->completion_ops->completion(hdr);
+ return ret;
+}
+
static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
const struct nfs_open_context *ctx2)
{
@@ -356,18 +824,23 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
struct nfs_page *req,
struct nfs_pageio_descriptor *pgio)
{
- if (!nfs_match_open_context(req->wb_context, prev->wb_context))
- return false;
- if (req->wb_context->dentry->d_inode->i_flock != NULL &&
- !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context))
- return false;
- if (req->wb_pgbase != 0)
- return false;
- if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
- return false;
- if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
- return false;
- return pgio->pg_ops->pg_test(pgio, prev, req);
+ size_t size;
+
+ if (prev) {
+ if (!nfs_match_open_context(req->wb_context, prev->wb_context))
+ return false;
+ if (req->wb_context->dentry->d_inode->i_flock != NULL &&
+ !nfs_match_lock_context(req->wb_lock_context,
+ prev->wb_lock_context))
+ return false;
+ if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
+ return false;
+ }
+ size = pgio->pg_ops->pg_test(pgio, prev, req);
+ WARN_ON_ONCE(size > req->wb_bytes);
+ if (size && size < req->wb_bytes)
+ req->wb_bytes = size;
+ return size > 0;
}
/**
@@ -381,17 +854,16 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
struct nfs_page *req)
{
+ struct nfs_page *prev = NULL;
if (desc->pg_count != 0) {
- struct nfs_page *prev;
-
prev = nfs_list_entry(desc->pg_list.prev);
- if (!nfs_can_coalesce_requests(prev, req, desc))
- return 0;
} else {
if (desc->pg_ops->pg_init)
desc->pg_ops->pg_init(desc, req);
desc->pg_base = req->wb_pgbase;
}
+ if (!nfs_can_coalesce_requests(prev, req, desc))
+ return 0;
nfs_list_remove_request(req);
nfs_list_add_request(req, &desc->pg_list);
desc->pg_count += req->wb_bytes;
@@ -421,22 +893,73 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
* @desc: destination io descriptor
* @req: request
*
+ * This may split a request into subrequests which are all part of the
+ * same page group.
+ *
* Returns true if the request 'req' was successfully coalesced into the
* existing list of pages 'desc'.
*/
static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
struct nfs_page *req)
{
- while (!nfs_pageio_do_add_request(desc, req)) {
- desc->pg_moreio = 1;
- nfs_pageio_doio(desc);
- if (desc->pg_error < 0)
- return 0;
- desc->pg_moreio = 0;
- if (desc->pg_recoalesce)
- return 0;
- }
+ struct nfs_page *subreq;
+ unsigned int bytes_left = 0;
+ unsigned int offset, pgbase;
+
+ nfs_page_group_lock(req);
+
+ subreq = req;
+ bytes_left = subreq->wb_bytes;
+ offset = subreq->wb_offset;
+ pgbase = subreq->wb_pgbase;
+
+ do {
+ if (!nfs_pageio_do_add_request(desc, subreq)) {
+ /* make sure pg_test call(s) did nothing */
+ WARN_ON_ONCE(subreq->wb_bytes != bytes_left);
+ WARN_ON_ONCE(subreq->wb_offset != offset);
+ WARN_ON_ONCE(subreq->wb_pgbase != pgbase);
+
+ nfs_page_group_unlock(req);
+ desc->pg_moreio = 1;
+ nfs_pageio_doio(desc);
+ if (desc->pg_error < 0)
+ return 0;
+ desc->pg_moreio = 0;
+ if (desc->pg_recoalesce)
+ return 0;
+ /* retry add_request for this subreq */
+ nfs_page_group_lock(req);
+ continue;
+ }
+
+ /* check for buggy pg_test call(s) */
+ WARN_ON_ONCE(subreq->wb_bytes + subreq->wb_pgbase > PAGE_SIZE);
+ WARN_ON_ONCE(subreq->wb_bytes > bytes_left);
+ WARN_ON_ONCE(subreq->wb_bytes == 0);
+
+ bytes_left -= subreq->wb_bytes;
+ offset += subreq->wb_bytes;
+ pgbase += subreq->wb_bytes;
+
+ if (bytes_left) {
+ subreq = nfs_create_request(req->wb_context,
+ req->wb_page,
+ subreq, pgbase, bytes_left);
+ if (IS_ERR(subreq))
+ goto err_ptr;
+ nfs_lock_request(subreq);
+ subreq->wb_offset = offset;
+ subreq->wb_index = req->wb_index;
+ }
+ } while (bytes_left > 0);
+
+ nfs_page_group_unlock(req);
return 1;
+err_ptr:
+ desc->pg_error = PTR_ERR(subreq);
+ nfs_page_group_unlock(req);
+ return 0;
}
static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
@@ -535,3 +1058,13 @@ void nfs_destroy_nfspagecache(void)
kmem_cache_destroy(nfs_page_cachep);
}
+static const struct rpc_call_ops nfs_pgio_common_ops = {
+ .rpc_call_prepare = nfs_pgio_prepare,
+ .rpc_call_done = nfs_pgio_result,
+ .rpc_release = nfs_pgio_release,
+};
+
+const struct nfs_pageio_ops nfs_pgio_rw_ops = {
+ .pg_test = nfs_generic_pg_test,
+ .pg_doio = nfs_generic_pg_pgios,
+};
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index cb53d450ae32..6fdcd233d6f7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1388,11 +1388,6 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
WARN_ON_ONCE(pgio->pg_lseg != NULL);
- if (req->wb_offset != req->wb_pgbase) {
- nfs_pageio_reset_read_mds(pgio);
- return;
- }
-
if (pgio->pg_dreq == NULL)
rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
else
@@ -1417,11 +1412,6 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
{
WARN_ON_ONCE(pgio->pg_lseg != NULL);
- if (req->wb_offset != req->wb_pgbase) {
- nfs_pageio_reset_write_mds(pgio);
- return;
- }
-
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
req_offset(req),
@@ -1434,56 +1424,49 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
-void
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
- const struct nfs_pgio_completion_ops *compl_ops)
-{
- struct nfs_server *server = NFS_SERVER(inode);
- struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
-
- if (ld == NULL)
- nfs_pageio_init_read(pgio, inode, compl_ops);
- else
- nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0);
-}
-
-void
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
- int ioflags,
- const struct nfs_pgio_completion_ops *compl_ops)
-{
- struct nfs_server *server = NFS_SERVER(inode);
- struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
-
- if (ld == NULL)
- nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
- else
- nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags);
-}
-
-bool
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+size_t
pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
- if (pgio->pg_lseg == NULL)
- return nfs_generic_pg_test(pgio, prev, req);
+ unsigned int size;
+ u64 seg_end, req_start, seg_left;
+
+ size = nfs_generic_pg_test(pgio, prev, req);
+ if (!size)
+ return 0;
/*
- * Test if a nfs_page is fully contained in the pnfs_layout_range.
- * Note that this test makes several assumptions:
- * - that the previous nfs_page in the struct nfs_pageio_descriptor
- * is known to lie within the range.
- * - that the nfs_page being tested is known to be contiguous with the
- * previous nfs_page.
- * - Layout ranges are page aligned, so we only have to test the
- * start offset of the request.
+ * 'size' contains the number of bytes left in the current page (up
+ * to the original size asked for in @req->wb_bytes).
+ *
+ * Calculate how many bytes are left in the layout segment
+ * and if there are less bytes than 'size', return that instead.
*
* Please also note that 'end_offset' is actually the offset of the
* first byte that lies outside the pnfs_layout_range. FIXME?
*
*/
- return req_offset(req) < end_offset(pgio->pg_lseg->pls_range.offset,
- pgio->pg_lseg->pls_range.length);
+ if (pgio->pg_lseg) {
+ seg_end = end_offset(pgio->pg_lseg->pls_range.offset,
+ pgio->pg_lseg->pls_range.length);
+ req_start = req_offset(req);
+ WARN_ON_ONCE(req_start > seg_end);
+ /* start of request is past the last byte of this segment */
+ if (req_start >= seg_end)
+ return 0;
+
+ /* adjust 'size' iff there are fewer bytes left in the
+ * segment than what nfs_generic_pg_test returned */
+ seg_left = seg_end - req_start;
+ if (seg_left < size)
+ size = (unsigned int)seg_left;
+ }
+
+ return size;
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
@@ -1496,7 +1479,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
LIST_HEAD(failed);
/* Resend all requests through the MDS */
- nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
+ nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, true, compl_ops);
pgio.pg_dreq = dreq;
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
@@ -1519,7 +1502,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
}
EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
-static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
+static void pnfs_ld_handle_write_error(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
@@ -1538,7 +1521,7 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
/*
* Called by non rpc-based layout drivers
*/
-void pnfs_ld_write_done(struct nfs_write_data *data)
+void pnfs_ld_write_done(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
@@ -1554,7 +1537,7 @@ EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
static void
pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
- struct nfs_write_data *data)
+ struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
@@ -1563,11 +1546,11 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
nfs_pageio_reset_write_mds(desc);
desc->pg_recoalesce = 1;
}
- nfs_writedata_release(data);
+ nfs_pgio_data_release(data);
}
static enum pnfs_try_status
-pnfs_try_to_write_data(struct nfs_write_data *wdata,
+pnfs_try_to_write_data(struct nfs_pgio_data *wdata,
const struct rpc_call_ops *call_ops,
struct pnfs_layout_segment *lseg,
int how)
@@ -1589,41 +1572,36 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
}
static void
-pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *head, int how)
+pnfs_do_write(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr, int how)
{
- struct nfs_write_data *data;
+ struct nfs_pgio_data *data = hdr->data;
const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
+ enum pnfs_try_status trypnfs;
desc->pg_lseg = NULL;
- while (!list_empty(head)) {
- enum pnfs_try_status trypnfs;
-
- data = list_first_entry(head, struct nfs_write_data, list);
- list_del_init(&data->list);
-
- trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
- if (trypnfs == PNFS_NOT_ATTEMPTED)
- pnfs_write_through_mds(desc, data);
- }
+ trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
+ if (trypnfs == PNFS_NOT_ATTEMPTED)
+ pnfs_write_through_mds(desc, data);
pnfs_put_lseg(lseg);
}
static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
{
pnfs_put_lseg(hdr->lseg);
- nfs_writehdr_free(hdr);
+ nfs_rw_header_free(hdr);
}
EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
int
pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
{
- struct nfs_write_header *whdr;
+ struct nfs_rw_header *whdr;
struct nfs_pgio_header *hdr;
int ret;
- whdr = nfs_writehdr_alloc();
+ whdr = nfs_rw_header_alloc(desc->pg_rw_ops);
if (!whdr) {
desc->pg_completion_ops->error_cleanup(&desc->pg_list);
pnfs_put_lseg(desc->pg_lseg);
@@ -1634,12 +1612,12 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
atomic_inc(&hdr->refcnt);
- ret = nfs_generic_flush(desc, hdr);
+ ret = nfs_generic_pgio(desc, hdr);
if (ret != 0) {
pnfs_put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
} else
- pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags);
+ pnfs_do_write(desc, hdr, desc->pg_ioflags);
if (atomic_dec_and_test(&hdr->refcnt))
hdr->completion_ops->completion(hdr);
return ret;
@@ -1655,7 +1633,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
LIST_HEAD(failed);
/* Resend all requests through the MDS */
- nfs_pageio_init_read(&pgio, inode, compl_ops);
+ nfs_pageio_init_read(&pgio, inode, true, compl_ops);
pgio.pg_dreq = dreq;
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
@@ -1674,7 +1652,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
}
EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds);
-static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+static void pnfs_ld_handle_read_error(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
@@ -1693,7 +1671,7 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
/*
* Called by non rpc-based layout drivers
*/
-void pnfs_ld_read_done(struct nfs_read_data *data)
+void pnfs_ld_read_done(struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
@@ -1709,7 +1687,7 @@ EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
static void
pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
- struct nfs_read_data *data)
+ struct nfs_pgio_data *data)
{
struct nfs_pgio_header *hdr = data->header;
@@ -1718,14 +1696,14 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
nfs_pageio_reset_read_mds(desc);
desc->pg_recoalesce = 1;
}
- nfs_readdata_release(data);
+ nfs_pgio_data_release(data);
}
/*
* Call the appropriate parallel I/O subsystem read function.
*/
static enum pnfs_try_status
-pnfs_try_to_read_data(struct nfs_read_data *rdata,
+pnfs_try_to_read_data(struct nfs_pgio_data *rdata,
const struct rpc_call_ops *call_ops,
struct pnfs_layout_segment *lseg)
{
@@ -1747,41 +1725,35 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata,
}
static void
-pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *head)
+pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
{
- struct nfs_read_data *data;
+ struct nfs_pgio_data *data = hdr->data;
const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
+ enum pnfs_try_status trypnfs;
desc->pg_lseg = NULL;
- while (!list_empty(head)) {
- enum pnfs_try_status trypnfs;
-
- data = list_first_entry(head, struct nfs_read_data, list);
- list_del_init(&data->list);
-
- trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
- if (trypnfs == PNFS_NOT_ATTEMPTED)
- pnfs_read_through_mds(desc, data);
- }
+ trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
+ if (trypnfs == PNFS_NOT_ATTEMPTED)
+ pnfs_read_through_mds(desc, data);
pnfs_put_lseg(lseg);
}
static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
{
pnfs_put_lseg(hdr->lseg);
- nfs_readhdr_free(hdr);
+ nfs_rw_header_free(hdr);
}
EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
int
pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
{
- struct nfs_read_header *rhdr;
+ struct nfs_rw_header *rhdr;
struct nfs_pgio_header *hdr;
int ret;
- rhdr = nfs_readhdr_alloc();
+ rhdr = nfs_rw_header_alloc(desc->pg_rw_ops);
if (!rhdr) {
desc->pg_completion_ops->error_cleanup(&desc->pg_list);
ret = -ENOMEM;
@@ -1793,12 +1765,12 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
atomic_inc(&hdr->refcnt);
- ret = nfs_generic_pagein(desc, hdr);
+ ret = nfs_generic_pgio(desc, hdr);
if (ret != 0) {
pnfs_put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
} else
- pnfs_do_multiple_reads(desc, &hdr->rpc_list);
+ pnfs_do_read(desc, hdr);
if (atomic_dec_and_test(&hdr->refcnt))
hdr->completion_ops->completion(hdr);
return ret;
@@ -1810,7 +1782,7 @@ static void pnfs_clear_layoutcommitting(struct inode *inode)
unsigned long *bitlock = &NFS_I(inode)->flags;
clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
}
@@ -1848,7 +1820,7 @@ void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
void
-pnfs_set_layoutcommit(struct nfs_write_data *wdata)
+pnfs_set_layoutcommit(struct nfs_pgio_data *wdata)
{
struct nfs_pgio_header *hdr = wdata->header;
struct inode *inode = hdr->inode;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 023793909778..4fb309a2b4c4 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -113,8 +113,8 @@ struct pnfs_layoutdriver_type {
* Return PNFS_ATTEMPTED to indicate the layout code has attempted
* I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
*/
- enum pnfs_try_status (*read_pagelist) (struct nfs_read_data *nfs_data);
- enum pnfs_try_status (*write_pagelist) (struct nfs_write_data *nfs_data, int how);
+ enum pnfs_try_status (*read_pagelist) (struct nfs_pgio_data *nfs_data);
+ enum pnfs_try_status (*write_pagelist) (struct nfs_pgio_data *nfs_data, int how);
void (*free_deviceid_node) (struct nfs4_deviceid_node *);
@@ -180,11 +180,6 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
-void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
- const struct nfs_pgio_completion_ops *);
-void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
- int, const struct nfs_pgio_completion_ops *);
-
void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
void unset_pnfs_layoutdriver(struct nfs_server *);
void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
@@ -192,7 +187,8 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req, u64 wb_size);
int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
-bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
+size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
+ struct nfs_page *prev, struct nfs_page *req);
void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp);
void pnfs_free_lseg_list(struct list_head *tmp_list);
@@ -217,13 +213,13 @@ bool pnfs_roc(struct inode *ino);
void pnfs_roc_release(struct inode *ino);
void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
-void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
+void pnfs_set_layoutcommit(struct nfs_pgio_data *wdata);
void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
int _pnfs_return_layout(struct inode *);
int pnfs_commit_and_return_layout(struct inode *);
-void pnfs_ld_write_done(struct nfs_write_data *);
-void pnfs_ld_read_done(struct nfs_read_data *);
+void pnfs_ld_write_done(struct nfs_pgio_data *);
+void pnfs_ld_read_done(struct nfs_pgio_data *);
struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
struct nfs_open_context *ctx,
loff_t pos,
@@ -275,7 +271,7 @@ pnfs_get_lseg(struct pnfs_layout_segment *lseg)
{
if (lseg) {
atomic_inc(&lseg->pls_refcount);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}
return lseg;
}
@@ -461,18 +457,6 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
{
}
-static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
- const struct nfs_pgio_completion_ops *compl_ops)
-{
- nfs_pageio_init_read(pgio, inode, compl_ops);
-}
-
-static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
- const struct nfs_pgio_completion_ops *compl_ops)
-{
- nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
-}
-
static inline int
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
struct nfs_commit_info *cinfo)
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index e55ce9e8b034..c171ce1a8a30 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -578,7 +578,7 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
return 0;
}
-static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
{
struct inode *inode = data->header->inode;
@@ -594,18 +594,18 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
return 0;
}
-static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
+static void nfs_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
{
msg->rpc_proc = &nfs_procedures[NFSPROC_READ];
}
-static int nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
{
rpc_call_start(task);
return 0;
}
-static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
{
struct inode *inode = data->header->inode;
@@ -614,19 +614,13 @@ static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
return 0;
}
-static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
{
/* Note: NFSv2 ignores @stable and always uses NFS_FILE_SYNC */
data->args.stable = NFS_FILE_SYNC;
msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE];
}
-static int nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
-{
- rpc_call_start(task);
- return 0;
-}
-
static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
{
BUG();
@@ -734,13 +728,10 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.fsinfo = nfs_proc_fsinfo,
.pathconf = nfs_proc_pathconf,
.decode_dirent = nfs2_decode_dirent,
+ .pgio_rpc_prepare = nfs_proc_pgio_rpc_prepare,
.read_setup = nfs_proc_read_setup,
- .read_pageio_init = nfs_pageio_init_read,
- .read_rpc_prepare = nfs_proc_read_rpc_prepare,
.read_done = nfs_read_done,
.write_setup = nfs_proc_write_setup,
- .write_pageio_init = nfs_pageio_init_write,
- .write_rpc_prepare = nfs_proc_write_rpc_prepare,
.write_done = nfs_write_done,
.commit_setup = nfs_proc_commit_setup,
.commit_rpc_prepare = nfs_proc_commit_rpc_prepare,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 411aedda14bb..e818a475ca64 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -24,85 +24,24 @@
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
+#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
-static const struct nfs_pageio_ops nfs_pageio_read_ops;
-static const struct rpc_call_ops nfs_read_common_ops;
static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
+static const struct nfs_rw_ops nfs_rw_read_ops;
static struct kmem_cache *nfs_rdata_cachep;
-struct nfs_read_header *nfs_readhdr_alloc(void)
+static struct nfs_rw_header *nfs_readhdr_alloc(void)
{
- struct nfs_read_header *rhdr;
-
- rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
- if (rhdr) {
- struct nfs_pgio_header *hdr = &rhdr->header;
-
- INIT_LIST_HEAD(&hdr->pages);
- INIT_LIST_HEAD(&hdr->rpc_list);
- spin_lock_init(&hdr->lock);
- atomic_set(&hdr->refcnt, 0);
- }
- return rhdr;
+ return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
}
-EXPORT_SYMBOL_GPL(nfs_readhdr_alloc);
-static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr,
- unsigned int pagecount)
+static void nfs_readhdr_free(struct nfs_rw_header *rhdr)
{
- struct nfs_read_data *data, *prealloc;
-
- prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data;
- if (prealloc->header == NULL)
- data = prealloc;
- else
- data = kzalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- goto out;
-
- if (nfs_pgarray_set(&data->pages, pagecount)) {
- data->header = hdr;
- atomic_inc(&hdr->refcnt);
- } else {
- if (data != prealloc)
- kfree(data);
- data = NULL;
- }
-out:
- return data;
-}
-
-void nfs_readhdr_free(struct nfs_pgio_header *hdr)
-{
- struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header);
-
kmem_cache_free(nfs_rdata_cachep, rhdr);
}
-EXPORT_SYMBOL_GPL(nfs_readhdr_free);
-
-void nfs_readdata_release(struct nfs_read_data *rdata)
-{
- struct nfs_pgio_header *hdr = rdata->header;
- struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header);
-
- put_nfs_open_context(rdata->args.context);
- if (rdata->pages.pagevec != rdata->pages.page_array)
- kfree(rdata->pages.pagevec);
- if (rdata == &read_header->rpc_data) {
- rdata->header = NULL;
- rdata = NULL;
- }
- if (atomic_dec_and_test(&hdr->refcnt))
- hdr->completion_ops->completion(hdr);
- /* Note: we only free the rpc_task after callbacks are done.
- * See the comment in rpc_free_task() for why
- */
- kfree(rdata);
-}
-EXPORT_SYMBOL_GPL(nfs_readdata_release);
static
int nfs_return_empty_page(struct page *page)
@@ -114,17 +53,24 @@ int nfs_return_empty_page(struct page *page)
}
void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
- struct inode *inode,
+ struct inode *inode, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops)
{
- nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops,
- NFS_SERVER(inode)->rsize, 0);
+ struct nfs_server *server = NFS_SERVER(inode);
+ const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;
+
+#ifdef CONFIG_NFS_V4_1
+ if (server->pnfs_curr_ld && !force_mds)
+ pg_ops = server->pnfs_curr_ld->pg_read_ops;
+#endif
+ nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops,
+ server->rsize, 0);
}
EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
{
- pgio->pg_ops = &nfs_pageio_read_ops;
+ pgio->pg_ops = &nfs_pgio_rw_ops;
pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
@@ -139,7 +85,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
len = nfs_page_length(page);
if (len == 0)
return nfs_return_empty_page(page);
- new = nfs_create_request(ctx, inode, page, 0, len);
+ new = nfs_create_request(ctx, page, NULL, 0, len);
if (IS_ERR(new)) {
unlock_page(page);
return PTR_ERR(new);
@@ -147,7 +93,8 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
if (len < PAGE_CACHE_SIZE)
zero_user_segment(page, len, PAGE_CACHE_SIZE);
- NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
+ nfs_pageio_init_read(&pgio, inode, false,
+ &nfs_async_read_completion_ops);
nfs_pageio_add_request(&pgio, new);
nfs_pageio_complete(&pgio);
NFS_I(inode)->read_io += pgio.pg_bytes_written;
@@ -158,10 +105,16 @@ static void nfs_readpage_release(struct nfs_page *req)
{
struct inode *d_inode = req->wb_context->dentry->d_inode;
- if (PageUptodate(req->wb_page))
- nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+ dprintk("NFS: read done (%s/%llu %d@%lld)\n", d_inode->i_sb->s_id,
+ (unsigned long long)NFS_FILEID(d_inode), req->wb_bytes,
+ (long long)req_offset(req));
- unlock_page(req->wb_page);
+ if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
+ if (PageUptodate(req->wb_page))
+ nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+
+ unlock_page(req->wb_page);
+ }
dprintk("NFS: read done (%s/%Lu %d@%Ld)\n",
req->wb_context->dentry->d_inode->i_sb->s_id,
@@ -171,7 +124,12 @@ static void nfs_readpage_release(struct nfs_page *req)
nfs_release_request(req);
}
-/* Note io was page aligned */
+static void nfs_page_group_set_uptodate(struct nfs_page *req)
+{
+ if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
+ SetPageUptodate(req->wb_page);
+}
+
static void nfs_read_completion(struct nfs_pgio_header *hdr)
{
unsigned long bytes = 0;
@@ -181,21 +139,32 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
while (!list_empty(&hdr->pages)) {
struct nfs_page *req = nfs_list_entry(hdr->pages.next);
struct page *page = req->wb_page;
+ unsigned long start = req->wb_pgbase;
+ unsigned long end = req->wb_pgbase + req->wb_bytes;
if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
- if (bytes > hdr->good_bytes)
- zero_user(page, 0, PAGE_SIZE);
- else if (hdr->good_bytes - bytes < PAGE_SIZE)
- zero_user_segment(page,
- hdr->good_bytes & ~PAGE_MASK,
- PAGE_SIZE);
+ /* note: regions of the page not covered by a
+ * request are zeroed in nfs_readpage_async /
+ * readpage_async_filler */
+ if (bytes > hdr->good_bytes) {
+ /* nothing in this request was good, so zero
+ * the full extent of the request */
+ zero_user_segment(page, start, end);
+
+ } else if (hdr->good_bytes - bytes < req->wb_bytes) {
+ /* part of this request has good bytes, but
+ * not all. zero the bad bytes */
+ start += hdr->good_bytes - bytes;
+ WARN_ON(start < req->wb_pgbase);
+ zero_user_segment(page, start, end);
+ }
}
bytes += req->wb_bytes;
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
if (bytes <= hdr->good_bytes)
- SetPageUptodate(page);
+ nfs_page_group_set_uptodate(req);
} else
- SetPageUptodate(page);
+ nfs_page_group_set_uptodate(req);
nfs_list_remove_request(req);
nfs_readpage_release(req);
}
@@ -203,95 +172,14 @@ out:
hdr->release(hdr);
}
-int nfs_initiate_read(struct rpc_clnt *clnt,
- struct nfs_read_data *data,
- const struct rpc_call_ops *call_ops, int flags)
+static void nfs_initiate_read(struct nfs_pgio_data *data, struct rpc_message *msg,
+ struct rpc_task_setup *task_setup_data, int how)
{
struct inode *inode = data->header->inode;
int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
- struct rpc_task *task;
- struct rpc_message msg = {
- .rpc_argp = &data->args,
- .rpc_resp = &data->res,
- .rpc_cred = data->header->cred,
- };
- struct rpc_task_setup task_setup_data = {
- .task = &data->task,
- .rpc_client = clnt,
- .rpc_message = &msg,
- .callback_ops = call_ops,
- .callback_data = data,
- .workqueue = nfsiod_workqueue,
- .flags = RPC_TASK_ASYNC | swap_flags | flags,
- };
- /* Set up the initial task struct. */
- NFS_PROTO(inode)->read_setup(data, &msg);
-
- dprintk("NFS: %5u initiated read call (req %s/%llu, %u bytes @ "
- "offset %llu)\n",
- data->task.tk_pid,
- inode->i_sb->s_id,
- (unsigned long long)NFS_FILEID(inode),
- data->args.count,
- (unsigned long long)data->args.offset);
-
- task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task))
- return PTR_ERR(task);
- rpc_put_task(task);
- return 0;
-}
-EXPORT_SYMBOL_GPL(nfs_initiate_read);
-
-/*
- * Set up the NFS read request struct
- */
-static void nfs_read_rpcsetup(struct nfs_read_data *data,
- unsigned int count, unsigned int offset)
-{
- struct nfs_page *req = data->header->req;
-
- data->args.fh = NFS_FH(data->header->inode);
- data->args.offset = req_offset(req) + offset;
- data->args.pgbase = req->wb_pgbase + offset;
- data->args.pages = data->pages.pagevec;
- data->args.count = count;
- data->args.context = get_nfs_open_context(req->wb_context);
- data->args.lock_context = req->wb_lock_context;
-
- data->res.fattr = &data->fattr;
- data->res.count = count;
- data->res.eof = 0;
- nfs_fattr_init(&data->fattr);
-}
-
-static int nfs_do_read(struct nfs_read_data *data,
- const struct rpc_call_ops *call_ops)
-{
- struct inode *inode = data->header->inode;
-
- return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops, 0);
-}
-
-static int
-nfs_do_multiple_reads(struct list_head *head,
- const struct rpc_call_ops *call_ops)
-{
- struct nfs_read_data *data;
- int ret = 0;
-
- while (!list_empty(head)) {
- int ret2;
-
- data = list_first_entry(head, struct nfs_read_data, list);
- list_del_init(&data->list);
-
- ret2 = nfs_do_read(data, call_ops);
- if (ret == 0)
- ret = ret2;
- }
- return ret;
+ task_setup_data->flags |= swap_flags;
+ NFS_PROTO(inode)->read_setup(data, msg);
}
static void
@@ -311,143 +199,14 @@ static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
.completion = nfs_read_completion,
};
-static void nfs_pagein_error(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- set_bit(NFS_IOHDR_REDO, &hdr->flags);
- while (!list_empty(&hdr->rpc_list)) {
- struct nfs_read_data *data = list_first_entry(&hdr->rpc_list,
- struct nfs_read_data, list);
- list_del(&data->list);
- nfs_readdata_release(data);
- }
- desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-}
-
-/*
- * Generate multiple requests to fill a single page.
- *
- * We optimize to reduce the number of read operations on the wire. If we
- * detect that we're reading a page, or an area of a page, that is past the
- * end of file, we do not generate NFS read operations but just clear the
- * parts of the page that would have come back zero from the server anyway.
- *
- * We rely on the cached value of i_size to make this determination; another
- * client can fill pages on the server past our cached end-of-file, but we
- * won't see the new data until our attribute cache is updated. This is more
- * or less conventional NFS client behavior.
- */
-static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- struct nfs_page *req = hdr->req;
- struct page *page = req->wb_page;
- struct nfs_read_data *data;
- size_t rsize = desc->pg_bsize, nbytes;
- unsigned int offset;
-
- offset = 0;
- nbytes = desc->pg_count;
- do {
- size_t len = min(nbytes,rsize);
-
- data = nfs_readdata_alloc(hdr, 1);
- if (!data) {
- nfs_pagein_error(desc, hdr);
- return -ENOMEM;
- }
- data->pages.pagevec[0] = page;
- nfs_read_rpcsetup(data, len, offset);
- list_add(&data->list, &hdr->rpc_list);
- nbytes -= len;
- offset += len;
- } while (nbytes != 0);
-
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &hdr->pages);
- desc->pg_rpc_callops = &nfs_read_common_ops;
- return 0;
-}
-
-static int nfs_pagein_one(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- struct nfs_page *req;
- struct page **pages;
- struct nfs_read_data *data;
- struct list_head *head = &desc->pg_list;
-
- data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base,
- desc->pg_count));
- if (!data) {
- nfs_pagein_error(desc, hdr);
- return -ENOMEM;
- }
-
- pages = data->pages.pagevec;
- while (!list_empty(head)) {
- req = nfs_list_entry(head->next);
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &hdr->pages);
- *pages++ = req->wb_page;
- }
-
- nfs_read_rpcsetup(data, desc->pg_count, 0);
- list_add(&data->list, &hdr->rpc_list);
- desc->pg_rpc_callops = &nfs_read_common_ops;
- return 0;
-}
-
-int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- if (desc->pg_bsize < PAGE_CACHE_SIZE)
- return nfs_pagein_multi(desc, hdr);
- return nfs_pagein_one(desc, hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_generic_pagein);
-
-static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
-{
- struct nfs_read_header *rhdr;
- struct nfs_pgio_header *hdr;
- int ret;
-
- rhdr = nfs_readhdr_alloc();
- if (!rhdr) {
- desc->pg_completion_ops->error_cleanup(&desc->pg_list);
- return -ENOMEM;
- }
- hdr = &rhdr->header;
- nfs_pgheader_init(desc, hdr, nfs_readhdr_free);
- atomic_inc(&hdr->refcnt);
- ret = nfs_generic_pagein(desc, hdr);
- if (ret == 0)
- ret = nfs_do_multiple_reads(&hdr->rpc_list,
- desc->pg_rpc_callops);
- if (atomic_dec_and_test(&hdr->refcnt))
- hdr->completion_ops->completion(hdr);
- return ret;
-}
-
-static const struct nfs_pageio_ops nfs_pageio_read_ops = {
- .pg_test = nfs_generic_pg_test,
- .pg_doio = nfs_generic_pg_readpages,
-};
-
/*
* This is the callback from RPC telling us whether a reply was
* received or some error occurred (timeout or socket shutdown).
*/
-int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_readpage_done(struct rpc_task *task, struct nfs_pgio_data *data,
+ struct inode *inode)
{
- struct inode *inode = data->header->inode;
- int status;
-
- dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid,
- task->tk_status);
-
- status = NFS_PROTO(inode)->read_done(task, data);
+ int status = NFS_PROTO(inode)->read_done(task, data);
if (status != 0)
return status;
@@ -460,10 +219,10 @@ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
return 0;
}
-static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data)
+static void nfs_readpage_retry(struct rpc_task *task, struct nfs_pgio_data *data)
{
- struct nfs_readargs *argp = &data->args;
- struct nfs_readres *resp = &data->res;
+ struct nfs_pgio_args *argp = &data->args;
+ struct nfs_pgio_res *resp = &data->res;
/* This is a short read! */
nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD);
@@ -480,17 +239,11 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
rpc_restart_call_prepare(task);
}
-static void nfs_readpage_result_common(struct rpc_task *task, void *calldata)
+static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_data *data)
{
- struct nfs_read_data *data = calldata;
struct nfs_pgio_header *hdr = data->header;
- /* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */
- if (nfs_readpage_result(task, data) != 0)
- return;
- if (task->tk_status < 0)
- nfs_set_pgio_error(hdr, task->tk_status, data->args.offset);
- else if (data->res.eof) {
+ if (data->res.eof) {
loff_t bound;
bound = data->args.offset + data->res.count;
@@ -505,26 +258,6 @@ static void nfs_readpage_result_common(struct rpc_task *task, void *calldata)
nfs_readpage_retry(task, data);
}
-static void nfs_readpage_release_common(void *calldata)
-{
- nfs_readdata_release(calldata);
-}
-
-void nfs_read_prepare(struct rpc_task *task, void *calldata)
-{
- struct nfs_read_data *data = calldata;
- int err;
- err = NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
- if (err)
- rpc_exit(task, err);
-}
-
-static const struct rpc_call_ops nfs_read_common_ops = {
- .rpc_call_prepare = nfs_read_prepare,
- .rpc_call_done = nfs_readpage_result_common,
- .rpc_release = nfs_readpage_release_common,
-};
-
/*
* Read a page over NFS.
* We read the page synchronously in the following case:
@@ -592,7 +325,6 @@ static int
readpage_async_filler(void *data, struct page *page)
{
struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
- struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *new;
unsigned int len;
int error;
@@ -601,7 +333,7 @@ readpage_async_filler(void *data, struct page *page)
if (len == 0)
return nfs_return_empty_page(page);
- new = nfs_create_request(desc->ctx, inode, page, 0, len);
+ new = nfs_create_request(desc->ctx, page, NULL, 0, len);
if (IS_ERR(new))
goto out_error;
@@ -654,7 +386,8 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
if (ret == 0)
goto read_complete; /* all pages were read */
- NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
+ nfs_pageio_init_read(&pgio, inode, false,
+ &nfs_async_read_completion_ops);
ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
@@ -671,7 +404,7 @@ out:
int __init nfs_init_readpagecache(void)
{
nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
- sizeof(struct nfs_read_header),
+ sizeof(struct nfs_rw_header),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_rdata_cachep == NULL)
@@ -684,3 +417,12 @@ void nfs_destroy_readpagecache(void)
{
kmem_cache_destroy(nfs_rdata_cachep);
}
+
+static const struct nfs_rw_ops nfs_rw_read_ops = {
+ .rw_mode = FMODE_READ,
+ .rw_alloc_header = nfs_readhdr_alloc,
+ .rw_free_header = nfs_readhdr_free,
+ .rw_done = nfs_readpage_done,
+ .rw_result = nfs_readpage_result,
+ .rw_initiate = nfs_initiate_read,
+};
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2cb56943e232..084af1060d79 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2180,11 +2180,23 @@ out_no_address:
return -EINVAL;
}
+#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
+ | NFS_MOUNT_SECURE \
+ | NFS_MOUNT_TCP \
+ | NFS_MOUNT_VER3 \
+ | NFS_MOUNT_KERBEROS \
+ | NFS_MOUNT_NONLM \
+ | NFS_MOUNT_BROKEN_SUID \
+ | NFS_MOUNT_STRICTLOCK \
+ | NFS_MOUNT_UNSHARED \
+ | NFS_MOUNT_NORESVPORT \
+ | NFS_MOUNT_LEGACY_INTERFACE)
+
static int
nfs_compare_remount_data(struct nfs_server *nfss,
struct nfs_parsed_mount_data *data)
{
- if (data->flags != nfss->flags ||
+ if ((data->flags ^ nfss->flags) & NFS_MOUNT_CMP_FLAGMASK ||
data->rsize != nfss->rsize ||
data->wsize != nfss->wsize ||
data->version != nfss->nfs_client->rpc_ops->version ||
@@ -2248,6 +2260,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
data->version = nfsvers;
data->minorversion = nfss->nfs_client->cl_minorversion;
+ data->net = current->nsproxy->net_ns;
memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
data->nfs_server.addrlen);
@@ -2347,18 +2360,6 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
nfs_initialise_sb(sb);
}
-#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
- | NFS_MOUNT_SECURE \
- | NFS_MOUNT_TCP \
- | NFS_MOUNT_VER3 \
- | NFS_MOUNT_KERBEROS \
- | NFS_MOUNT_NONLM \
- | NFS_MOUNT_BROKEN_SUID \
- | NFS_MOUNT_STRICTLOCK \
- | NFS_MOUNT_UNSHARED \
- | NFS_MOUNT_NORESVPORT \
- | NFS_MOUNT_LEGACY_INTERFACE)
-
static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
{
const struct nfs_server *a = s->s_fs_info;
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 6b3f2535a3ec..bb6ed810fa6f 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -13,7 +13,7 @@
static struct ctl_table_header *nfs_callback_sysctl_table;
-static ctl_table nfs_cb_sysctls[] = {
+static struct ctl_table nfs_cb_sysctls[] = {
{
.procname = "nfs_mountpoint_timeout",
.data = &nfs_mountpoint_expiry_timeout,
@@ -31,7 +31,7 @@ static ctl_table nfs_cb_sysctls[] = {
{ }
};
-static ctl_table nfs_cb_sysctl_dir[] = {
+static struct ctl_table nfs_cb_sysctl_dir[] = {
{
.procname = "nfs",
.mode = 0555,
@@ -40,7 +40,7 @@ static ctl_table nfs_cb_sysctl_dir[] = {
{ }
};
-static ctl_table nfs_cb_sysctl_root[] = {
+static struct ctl_table nfs_cb_sysctl_root[] = {
{
.procname = "fs",
.mode = 0555,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 9a3b6a4cd6b9..3ee5af4e738e 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -42,10 +42,10 @@
* Local function declarations
*/
static void nfs_redirty_request(struct nfs_page *req);
-static const struct rpc_call_ops nfs_write_common_ops;
static const struct rpc_call_ops nfs_commit_ops;
static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
+static const struct nfs_rw_ops nfs_rw_write_ops;
static struct kmem_cache *nfs_wdata_cachep;
static mempool_t *nfs_wdata_mempool;
@@ -70,76 +70,19 @@ void nfs_commit_free(struct nfs_commit_data *p)
}
EXPORT_SYMBOL_GPL(nfs_commit_free);
-struct nfs_write_header *nfs_writehdr_alloc(void)
+static struct nfs_rw_header *nfs_writehdr_alloc(void)
{
- struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
-
- if (p) {
- struct nfs_pgio_header *hdr = &p->header;
+ struct nfs_rw_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
+ if (p)
memset(p, 0, sizeof(*p));
- INIT_LIST_HEAD(&hdr->pages);
- INIT_LIST_HEAD(&hdr->rpc_list);
- spin_lock_init(&hdr->lock);
- atomic_set(&hdr->refcnt, 0);
- hdr->verf = &p->verf;
- }
return p;
}
-EXPORT_SYMBOL_GPL(nfs_writehdr_alloc);
-
-static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr,
- unsigned int pagecount)
-{
- struct nfs_write_data *data, *prealloc;
-
- prealloc = &container_of(hdr, struct nfs_write_header, header)->rpc_data;
- if (prealloc->header == NULL)
- data = prealloc;
- else
- data = kzalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- goto out;
-
- if (nfs_pgarray_set(&data->pages, pagecount)) {
- data->header = hdr;
- atomic_inc(&hdr->refcnt);
- } else {
- if (data != prealloc)
- kfree(data);
- data = NULL;
- }
-out:
- return data;
-}
-void nfs_writehdr_free(struct nfs_pgio_header *hdr)
+static void nfs_writehdr_free(struct nfs_rw_header *whdr)
{
- struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header);
mempool_free(whdr, nfs_wdata_mempool);
}
-EXPORT_SYMBOL_GPL(nfs_writehdr_free);
-
-void nfs_writedata_release(struct nfs_write_data *wdata)
-{
- struct nfs_pgio_header *hdr = wdata->header;
- struct nfs_write_header *write_header = container_of(hdr, struct nfs_write_header, header);
-
- put_nfs_open_context(wdata->args.context);
- if (wdata->pages.pagevec != wdata->pages.page_array)
- kfree(wdata->pages.pagevec);
- if (wdata == &write_header->rpc_data) {
- wdata->header = NULL;
- wdata = NULL;
- }
- if (atomic_dec_and_test(&hdr->refcnt))
- hdr->completion_ops->completion(hdr);
- /* Note: we only free the rpc_task after callbacks are done.
- * See the comment in rpc_free_task() for why
- */
- kfree(wdata);
-}
-EXPORT_SYMBOL_GPL(nfs_writedata_release);
static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
{
@@ -211,18 +154,78 @@ static void nfs_set_pageerror(struct page *page)
nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
}
+/*
+ * nfs_page_group_search_locked
+ * @head - head request of page group
+ * @page_offset - offset into page
+ *
+ * Search page group with head @head to find a request that contains the
+ * page offset @page_offset.
+ *
+ * Returns a pointer to the first matching nfs request, or NULL if no
+ * match is found.
+ *
+ * Must be called with the page group lock held
+ */
+static struct nfs_page *
+nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
+{
+ struct nfs_page *req;
+
+ WARN_ON_ONCE(head != head->wb_head);
+ WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_head->wb_flags));
+
+ req = head;
+ do {
+ if (page_offset >= req->wb_pgbase &&
+ page_offset < (req->wb_pgbase + req->wb_bytes))
+ return req;
+
+ req = req->wb_this_page;
+ } while (req != head);
+
+ return NULL;
+}
+
+/*
+ * nfs_page_group_covers_page
+ * @head - head request of page group
+ *
+ * Return true if the page group with head @head covers the whole page,
+ * returns false otherwise
+ */
+static bool nfs_page_group_covers_page(struct nfs_page *req)
+{
+ struct nfs_page *tmp;
+ unsigned int pos = 0;
+ unsigned int len = nfs_page_length(req->wb_page);
+
+ nfs_page_group_lock(req);
+
+ do {
+ tmp = nfs_page_group_search_locked(req->wb_head, pos);
+ if (tmp) {
+ /* no way this should happen */
+ WARN_ON_ONCE(tmp->wb_pgbase != pos);
+ pos += tmp->wb_bytes - (pos - tmp->wb_pgbase);
+ }
+ } while (tmp && pos < len);
+
+ nfs_page_group_unlock(req);
+ WARN_ON_ONCE(pos > len);
+ return pos == len;
+}
+
/* We can set the PG_uptodate flag if we see that a write request
* covers the full page.
*/
-static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int count)
+static void nfs_mark_uptodate(struct nfs_page *req)
{
- if (PageUptodate(page))
- return;
- if (base != 0)
+ if (PageUptodate(req->wb_page))
return;
- if (count != nfs_page_length(page))
+ if (!nfs_page_group_covers_page(req))
return;
- SetPageUptodate(page);
+ SetPageUptodate(req->wb_page);
}
static int wb_priority(struct writeback_control *wbc)
@@ -258,12 +261,15 @@ static void nfs_set_page_writeback(struct page *page)
}
}
-static void nfs_end_page_writeback(struct page *page)
+static void nfs_end_page_writeback(struct nfs_page *req)
{
- struct inode *inode = page_file_mapping(page)->host;
+ struct inode *inode = page_file_mapping(req->wb_page)->host;
struct nfs_server *nfss = NFS_SERVER(inode);
- end_page_writeback(page);
+ if (!nfs_page_group_sync_on_bit(req, PG_WB_END))
+ return;
+
+ end_page_writeback(req->wb_page);
if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
}
@@ -354,10 +360,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
struct nfs_pageio_descriptor pgio;
int err;
- NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio,
- page->mapping->host,
- wb_priority(wbc),
- &nfs_async_write_completion_ops);
+ nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
+ false, &nfs_async_write_completion_ops);
err = nfs_do_writepage(page, wbc, &pgio);
nfs_pageio_complete(&pgio);
if (err < 0)
@@ -400,12 +404,13 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
- NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops);
+ nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
+ &nfs_async_write_completion_ops);
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
nfs_pageio_complete(&pgio);
clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_FLUSHING);
if (err < 0)
@@ -425,6 +430,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ WARN_ON_ONCE(req->wb_this_page != req);
+
/* Lock the request! */
nfs_lock_request(req);
@@ -441,6 +448,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
set_page_private(req->wb_page, (unsigned long)req);
}
nfsi->npages++;
+ set_bit(PG_INODE_REF, &req->wb_flags);
kref_get(&req->wb_kref);
spin_unlock(&inode->i_lock);
}
@@ -452,15 +460,20 @@ static void nfs_inode_remove_request(struct nfs_page *req)
{
struct inode *inode = req->wb_context->dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_page *head;
- spin_lock(&inode->i_lock);
- if (likely(!PageSwapCache(req->wb_page))) {
- set_page_private(req->wb_page, 0);
- ClearPagePrivate(req->wb_page);
- clear_bit(PG_MAPPED, &req->wb_flags);
+ if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
+ head = req->wb_head;
+
+ spin_lock(&inode->i_lock);
+ if (likely(!PageSwapCache(head->wb_page))) {
+ set_page_private(head->wb_page, 0);
+ ClearPagePrivate(head->wb_page);
+ clear_bit(PG_MAPPED, &head->wb_flags);
+ }
+ nfsi->npages--;
+ spin_unlock(&inode->i_lock);
}
- nfsi->npages--;
- spin_unlock(&inode->i_lock);
nfs_release_request(req);
}
@@ -583,7 +596,7 @@ nfs_clear_request_commit(struct nfs_page *req)
}
static inline
-int nfs_write_need_commit(struct nfs_write_data *data)
+int nfs_write_need_commit(struct nfs_pgio_data *data)
{
if (data->verf.committed == NFS_DATA_SYNC)
return data->header->lseg == NULL;
@@ -614,7 +627,7 @@ nfs_clear_request_commit(struct nfs_page *req)
}
static inline
-int nfs_write_need_commit(struct nfs_write_data *data)
+int nfs_write_need_commit(struct nfs_pgio_data *data)
{
return 0;
}
@@ -625,6 +638,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_commit_info cinfo;
unsigned long bytes = 0;
+ bool do_destroy;
if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
goto out;
@@ -645,7 +659,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
goto next;
}
if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
- memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf));
+ memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
nfs_mark_request_commit(req, hdr->lseg, &cinfo);
goto next;
}
@@ -653,7 +667,8 @@ remove_req:
nfs_inode_remove_request(req);
next:
nfs_unlock_request(req);
- nfs_end_page_writeback(req->wb_page);
+ nfs_end_page_writeback(req);
+ do_destroy = !test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags);
nfs_release_request(req);
}
out:
@@ -661,7 +676,7 @@ out:
}
#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
-static unsigned long
+unsigned long
nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
{
return cinfo->mds->ncommit;
@@ -718,7 +733,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
}
#else
-static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
+unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
{
return 0;
}
@@ -758,6 +773,10 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
if (req == NULL)
goto out_unlock;
+ /* should be handled by nfs_flush_incompatible */
+ WARN_ON_ONCE(req->wb_head != req);
+ WARN_ON_ONCE(req->wb_this_page != req);
+
rqend = req->wb_offset + req->wb_bytes;
/*
* Tell the caller to flush out the request if
@@ -819,7 +838,7 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
req = nfs_try_to_update_request(inode, page, offset, bytes);
if (req != NULL)
goto out;
- req = nfs_create_request(ctx, inode, page, offset, bytes);
+ req = nfs_create_request(ctx, page, NULL, offset, bytes);
if (IS_ERR(req))
goto out;
nfs_inode_add_request(inode, req);
@@ -837,7 +856,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
return PTR_ERR(req);
/* Update file length */
nfs_grow_file(page, offset, count);
- nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
+ nfs_mark_uptodate(req);
nfs_mark_request_dirty(req);
nfs_unlock_and_release_request(req);
return 0;
@@ -863,6 +882,8 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
return 0;
l_ctx = req->wb_lock_context;
do_flush = req->wb_page != page || req->wb_context != ctx;
+ /* for now, flush if more than 1 request in page_group */
+ do_flush |= req->wb_this_page != req;
if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) {
do_flush |= l_ctx->lockowner.l_owner != current->files
|| l_ctx->lockowner.l_pid != current->tgid;
@@ -990,126 +1011,17 @@ static int flush_task_priority(int how)
return RPC_PRIORITY_NORMAL;
}
-int nfs_initiate_write(struct rpc_clnt *clnt,
- struct nfs_write_data *data,
- const struct rpc_call_ops *call_ops,
- int how, int flags)
+static void nfs_initiate_write(struct nfs_pgio_data *data, struct rpc_message *msg,
+ struct rpc_task_setup *task_setup_data, int how)
{
struct inode *inode = data->header->inode;
int priority = flush_task_priority(how);
- struct rpc_task *task;
- struct rpc_message msg = {
- .rpc_argp = &data->args,
- .rpc_resp = &data->res,
- .rpc_cred = data->header->cred,
- };
- struct rpc_task_setup task_setup_data = {
- .rpc_client = clnt,
- .task = &data->task,
- .rpc_message = &msg,
- .callback_ops = call_ops,
- .callback_data = data,
- .workqueue = nfsiod_workqueue,
- .flags = RPC_TASK_ASYNC | flags,
- .priority = priority,
- };
- int ret = 0;
-
- /* Set up the initial task struct. */
- NFS_PROTO(inode)->write_setup(data, &msg);
- dprintk("NFS: %5u initiated write call "
- "(req %s/%llu, %u bytes @ offset %llu)\n",
- data->task.tk_pid,
- inode->i_sb->s_id,
- (unsigned long long)NFS_FILEID(inode),
- data->args.count,
- (unsigned long long)data->args.offset);
+ task_setup_data->priority = priority;
+ NFS_PROTO(inode)->write_setup(data, msg);
nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client,
- &task_setup_data.rpc_client, &msg, data);
-
- task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task)) {
- ret = PTR_ERR(task);
- goto out;
- }
- if (how & FLUSH_SYNC) {
- ret = rpc_wait_for_completion_task(task);
- if (ret == 0)
- ret = task->tk_status;
- }
- rpc_put_task(task);
-out:
- return ret;
-}
-EXPORT_SYMBOL_GPL(nfs_initiate_write);
-
-/*
- * Set up the argument/result storage required for the RPC call.
- */
-static void nfs_write_rpcsetup(struct nfs_write_data *data,
- unsigned int count, unsigned int offset,
- int how, struct nfs_commit_info *cinfo)
-{
- struct nfs_page *req = data->header->req;
-
- /* Set up the RPC argument and reply structs
- * NB: take care not to mess about with data->commit et al. */
-
- data->args.fh = NFS_FH(data->header->inode);
- data->args.offset = req_offset(req) + offset;
- /* pnfs_set_layoutcommit needs this */
- data->mds_offset = data->args.offset;
- data->args.pgbase = req->wb_pgbase + offset;
- data->args.pages = data->pages.pagevec;
- data->args.count = count;
- data->args.context = get_nfs_open_context(req->wb_context);
- data->args.lock_context = req->wb_lock_context;
- data->args.stable = NFS_UNSTABLE;
- switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
- case 0:
- break;
- case FLUSH_COND_STABLE:
- if (nfs_reqs_to_commit(cinfo))
- break;
- default:
- data->args.stable = NFS_FILE_SYNC;
- }
-
- data->res.fattr = &data->fattr;
- data->res.count = count;
- data->res.verf = &data->verf;
- nfs_fattr_init(&data->fattr);
-}
-
-static int nfs_do_write(struct nfs_write_data *data,
- const struct rpc_call_ops *call_ops,
- int how)
-{
- struct inode *inode = data->header->inode;
-
- return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how, 0);
-}
-
-static int nfs_do_multiple_writes(struct list_head *head,
- const struct rpc_call_ops *call_ops,
- int how)
-{
- struct nfs_write_data *data;
- int ret = 0;
-
- while (!list_empty(head)) {
- int ret2;
-
- data = list_first_entry(head, struct nfs_write_data, list);
- list_del_init(&data->list);
-
- ret2 = nfs_do_write(data, call_ops, how);
- if (ret == 0)
- ret = ret2;
- }
- return ret;
+ &task_setup_data->rpc_client, msg, data);
}
/* If a nfs_flush_* function fails, it should remove reqs from @head and
@@ -1120,7 +1032,7 @@ static void nfs_redirty_request(struct nfs_page *req)
{
nfs_mark_request_dirty(req);
nfs_unlock_request(req);
- nfs_end_page_writeback(req->wb_page);
+ nfs_end_page_writeback(req);
nfs_release_request(req);
}
@@ -1140,173 +1052,30 @@ static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
.completion = nfs_write_completion,
};
-static void nfs_flush_error(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- set_bit(NFS_IOHDR_REDO, &hdr->flags);
- while (!list_empty(&hdr->rpc_list)) {
- struct nfs_write_data *data = list_first_entry(&hdr->rpc_list,
- struct nfs_write_data, list);
- list_del(&data->list);
- nfs_writedata_release(data);
- }
- desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-}
-
-/*
- * Generate multiple small requests to write out a single
- * contiguous dirty area on one page.
- */
-static int nfs_flush_multi(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- struct nfs_page *req = hdr->req;
- struct page *page = req->wb_page;
- struct nfs_write_data *data;
- size_t wsize = desc->pg_bsize, nbytes;
- unsigned int offset;
- int requests = 0;
- struct nfs_commit_info cinfo;
-
- nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
-
- if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
- (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) ||
- desc->pg_count > wsize))
- desc->pg_ioflags &= ~FLUSH_COND_STABLE;
-
-
- offset = 0;
- nbytes = desc->pg_count;
- do {
- size_t len = min(nbytes, wsize);
-
- data = nfs_writedata_alloc(hdr, 1);
- if (!data) {
- nfs_flush_error(desc, hdr);
- return -ENOMEM;
- }
- data->pages.pagevec[0] = page;
- nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo);
- list_add(&data->list, &hdr->rpc_list);
- requests++;
- nbytes -= len;
- offset += len;
- } while (nbytes != 0);
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &hdr->pages);
- desc->pg_rpc_callops = &nfs_write_common_ops;
- return 0;
-}
-
-/*
- * Create an RPC task for the given write request and kick it.
- * The page must have been locked by the caller.
- *
- * It may happen that the page we're passed is not marked dirty.
- * This is the case if nfs_updatepage detects a conflicting request
- * that has been written but not committed.
- */
-static int nfs_flush_one(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- struct nfs_page *req;
- struct page **pages;
- struct nfs_write_data *data;
- struct list_head *head = &desc->pg_list;
- struct nfs_commit_info cinfo;
-
- data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base,
- desc->pg_count));
- if (!data) {
- nfs_flush_error(desc, hdr);
- return -ENOMEM;
- }
-
- nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
- pages = data->pages.pagevec;
- while (!list_empty(head)) {
- req = nfs_list_entry(head->next);
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &hdr->pages);
- *pages++ = req->wb_page;
- }
-
- if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
- (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
- desc->pg_ioflags &= ~FLUSH_COND_STABLE;
-
- /* Set up the argument struct */
- nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
- list_add(&data->list, &hdr->rpc_list);
- desc->pg_rpc_callops = &nfs_write_common_ops;
- return 0;
-}
-
-int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr)
-{
- if (desc->pg_bsize < PAGE_CACHE_SIZE)
- return nfs_flush_multi(desc, hdr);
- return nfs_flush_one(desc, hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_generic_flush);
-
-static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
-{
- struct nfs_write_header *whdr;
- struct nfs_pgio_header *hdr;
- int ret;
-
- whdr = nfs_writehdr_alloc();
- if (!whdr) {
- desc->pg_completion_ops->error_cleanup(&desc->pg_list);
- return -ENOMEM;
- }
- hdr = &whdr->header;
- nfs_pgheader_init(desc, hdr, nfs_writehdr_free);
- atomic_inc(&hdr->refcnt);
- ret = nfs_generic_flush(desc, hdr);
- if (ret == 0)
- ret = nfs_do_multiple_writes(&hdr->rpc_list,
- desc->pg_rpc_callops,
- desc->pg_ioflags);
- if (atomic_dec_and_test(&hdr->refcnt))
- hdr->completion_ops->completion(hdr);
- return ret;
-}
-
-static const struct nfs_pageio_ops nfs_pageio_write_ops = {
- .pg_test = nfs_generic_pg_test,
- .pg_doio = nfs_generic_pg_writepages,
-};
-
void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
- struct inode *inode, int ioflags,
+ struct inode *inode, int ioflags, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops)
{
- nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops,
- NFS_SERVER(inode)->wsize, ioflags);
+ struct nfs_server *server = NFS_SERVER(inode);
+ const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;
+
+#ifdef CONFIG_NFS_V4_1
+ if (server->pnfs_curr_ld && !force_mds)
+ pg_ops = server->pnfs_curr_ld->pg_write_ops;
+#endif
+ nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops,
+ server->wsize, ioflags);
}
EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
{
- pgio->pg_ops = &nfs_pageio_write_ops;
+ pgio->pg_ops = &nfs_pgio_rw_ops;
pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
-void nfs_write_prepare(struct rpc_task *task, void *calldata)
-{
- struct nfs_write_data *data = calldata;
- int err;
- err = NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data);
- if (err)
- rpc_exit(task, err);
-}
-
void nfs_commit_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_commit_data *data = calldata;
@@ -1314,23 +1083,8 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata)
NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
}
-/*
- * Handle a write reply that flushes a whole page.
- *
- * FIXME: There is an inherent race with invalidate_inode_pages and
- * writebacks since the page->count is kept > 1 for as long
- * as the page has a write request pending.
- */
-static void nfs_writeback_done_common(struct rpc_task *task, void *calldata)
-{
- struct nfs_write_data *data = calldata;
-
- nfs_writeback_done(task, data);
-}
-
-static void nfs_writeback_release_common(void *calldata)
+static void nfs_writeback_release_common(struct nfs_pgio_data *data)
{
- struct nfs_write_data *data = calldata;
struct nfs_pgio_header *hdr = data->header;
int status = data->task.tk_status;
@@ -1339,34 +1093,46 @@ static void nfs_writeback_release_common(void *calldata)
if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags))
; /* Do nothing */
else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags))
- memcpy(hdr->verf, &data->verf, sizeof(*hdr->verf));
- else if (memcmp(hdr->verf, &data->verf, sizeof(*hdr->verf)))
+ memcpy(&hdr->verf, &data->verf, sizeof(hdr->verf));
+ else if (memcmp(&hdr->verf, &data->verf, sizeof(hdr->verf)))
set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags);
spin_unlock(&hdr->lock);
}
- nfs_writedata_release(data);
}
-static const struct rpc_call_ops nfs_write_common_ops = {
- .rpc_call_prepare = nfs_write_prepare,
- .rpc_call_done = nfs_writeback_done_common,
- .rpc_release = nfs_writeback_release_common,
-};
+/*
+ * Special version of should_remove_suid() that ignores capabilities.
+ */
+static int nfs_should_remove_suid(const struct inode *inode)
+{
+ umode_t mode = inode->i_mode;
+ int kill = 0;
+
+ /* suid always must be killed */
+ if (unlikely(mode & S_ISUID))
+ kill = ATTR_KILL_SUID;
+ /*
+ * sgid without any exec bits is just a mandatory locking mark; leave
+ * it alone. If some exec bits are set, it's a real sgid; kill it.
+ */
+ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
+ kill |= ATTR_KILL_SGID;
+
+ if (unlikely(kill && S_ISREG(mode)))
+ return kill;
+
+ return 0;
+}
/*
* This function is called when the WRITE call is complete.
*/
-void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs_writeback_done(struct rpc_task *task, struct nfs_pgio_data *data,
+ struct inode *inode)
{
- struct nfs_writeargs *argp = &data->args;
- struct nfs_writeres *resp = &data->res;
- struct inode *inode = data->header->inode;
int status;
- dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
- task->tk_pid, task->tk_status);
-
/*
* ->write_done will attempt to use post-op attributes to detect
* conflicting writes by other clients. A strict interpretation
@@ -1376,11 +1142,11 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
*/
status = NFS_PROTO(inode)->write_done(task, data);
if (status != 0)
- return;
- nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count);
+ return status;
+ nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, data->res.count);
#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
- if (resp->verf->committed < argp->stable && task->tk_status >= 0) {
+ if (data->res.verf->committed < data->args.stable && task->tk_status >= 0) {
/* We tried a write call, but the server did not
* commit data to stable storage even though we
* requested it.
@@ -1396,18 +1162,31 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
dprintk("NFS: faulty NFS server %s:"
" (committed = %d) != (stable = %d)\n",
NFS_SERVER(inode)->nfs_client->cl_hostname,
- resp->verf->committed, argp->stable);
+ data->res.verf->committed, data->args.stable);
complain = jiffies + 300 * HZ;
}
}
#endif
- if (task->tk_status < 0)
- nfs_set_pgio_error(data->header, task->tk_status, argp->offset);
- else if (resp->count < argp->count) {
+
+ /* Deal with the suid/sgid bit corner case */
+ if (nfs_should_remove_suid(inode))
+ nfs_mark_for_revalidate(inode);
+ return 0;
+}
+
+/*
+ * This function is called when the WRITE call is complete.
+ */
+static void nfs_writeback_result(struct rpc_task *task, struct nfs_pgio_data *data)
+{
+ struct nfs_pgio_args *argp = &data->args;
+ struct nfs_pgio_res *resp = &data->res;
+
+ if (resp->count < argp->count) {
static unsigned long complain;
/* This a short write! */
- nfs_inc_stats(inode, NFSIOS_SHORTWRITE);
+ nfs_inc_stats(data->header->inode, NFSIOS_SHORTWRITE);
/* Has the server at least made some progress? */
if (resp->count == 0) {
@@ -1458,7 +1237,7 @@ static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
static void nfs_commit_clear_lock(struct nfs_inode *nfsi)
{
clear_bit(NFS_INO_COMMIT, &nfsi->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&nfsi->flags, NFS_INO_COMMIT);
}
@@ -1874,7 +1653,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
int __init nfs_init_writepagecache(void)
{
nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
- sizeof(struct nfs_write_header),
+ sizeof(struct nfs_rw_header),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_wdata_cachep == NULL)
@@ -1936,3 +1715,12 @@ void nfs_destroy_writepagecache(void)
kmem_cache_destroy(nfs_wdata_cachep);
}
+static const struct nfs_rw_ops nfs_rw_write_ops = {
+ .rw_mode = FMODE_WRITE,
+ .rw_alloc_header = nfs_writehdr_alloc,
+ .rw_free_header = nfs_writehdr_free,
+ .rw_release = nfs_writeback_release_common,
+ .rw_done = nfs_writeback_done,
+ .rw_result = nfs_writeback_result,
+ .rw_initiate = nfs_initiate_write,
+};
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
index b481e1f5eecc..a986ceb6fd0d 100644
--- a/fs/nfsd/acl.h
+++ b/fs/nfsd/acl.h
@@ -49,7 +49,7 @@ struct svc_rqst;
struct nfs4_acl *nfs4_acl_new(int);
int nfs4_acl_get_whotype(char *, u32);
-__be32 nfs4_acl_write_who(int who, __be32 **p, int *len);
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who);
int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
struct nfs4_acl **acl);
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 2645be435e75..72f44823adbb 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -1,7 +1,6 @@
/* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
#include <linux/sched.h>
-#include <linux/user_namespace.h>
#include "nfsd.h"
#include "auth.h"
@@ -25,7 +24,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
struct cred *new;
int i;
int flags = nfsexp_flags(rqstp, exp);
- int ret;
validate_process_creds();
@@ -86,8 +84,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
return 0;
oom:
- ret = -ENOMEM;
abort_creds(new);
- return ret;
+ return -ENOMEM;
}
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 8513c598fabf..13b85f94d9e2 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -17,17 +17,12 @@
#include <linux/exportfs.h>
#include <linux/sunrpc/svc_xprt.h>
-#include <net/ipv6.h>
-
#include "nfsd.h"
#include "nfsfh.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_EXPORT
-typedef struct auth_domain svc_client;
-typedef struct svc_export svc_export;
-
/*
* We have two caches.
* One maps client+vfsmnt+dentry to export options - the export map
@@ -73,7 +68,7 @@ static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_
static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
{
- /* client fsidtype fsid [path] */
+ /* client fsidtype fsid expiry [path] */
char *buf;
int len;
struct auth_domain *dom = NULL;
@@ -295,13 +290,19 @@ svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new,
static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc)
{
+ struct nfsd4_fs_location *locations = fsloc->locations;
int i;
+ if (!locations)
+ return;
+
for (i = 0; i < fsloc->locations_count; i++) {
- kfree(fsloc->locations[i].path);
- kfree(fsloc->locations[i].hosts);
+ kfree(locations[i].path);
+ kfree(locations[i].hosts);
}
- kfree(fsloc->locations);
+
+ kfree(locations);
+ fsloc->locations = NULL;
}
static void svc_export_put(struct kref *ref)
@@ -388,6 +389,10 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc)
int len;
int migrated, i, err;
+ /* more than one fsloc */
+ if (fsloc->locations)
+ return -EINVAL;
+
/* listsize */
err = get_uint(mesg, &fsloc->locations_count);
if (err)
@@ -437,13 +442,18 @@ out_free_all:
static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
{
- int listsize, err;
struct exp_flavor_info *f;
+ u32 listsize;
+ int err;
+
+ /* more than one secinfo */
+ if (exp->ex_nflavors)
+ return -EINVAL;
- err = get_int(mesg, &listsize);
+ err = get_uint(mesg, &listsize);
if (err)
return err;
- if (listsize < 0 || listsize > MAX_SECINFO_LIST)
+ if (listsize > MAX_SECINFO_LIST)
return -EINVAL;
for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) {
@@ -474,6 +484,27 @@ static inline int
secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; }
#endif
+static inline int
+uuid_parse(char **mesg, char *buf, unsigned char **puuid)
+{
+ int len;
+
+ /* more than one uuid */
+ if (*puuid)
+ return -EINVAL;
+
+ /* expect a 16 byte uuid encoded as \xXXXX... */
+ len = qword_get(mesg, buf, PAGE_SIZE);
+ if (len != EX_UUID_LEN)
+ return -EINVAL;
+
+ *puuid = kmemdup(buf, EX_UUID_LEN, GFP_KERNEL);
+ if (*puuid == NULL)
+ return -ENOMEM;
+
+ return 0;
+}
+
static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
{
/* client path expiry [flags anonuid anongid fsid] */
@@ -552,18 +583,9 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) {
if (strcmp(buf, "fsloc") == 0)
err = fsloc_parse(&mesg, buf, &exp.ex_fslocs);
- else if (strcmp(buf, "uuid") == 0) {
- /* expect a 16 byte uuid encoded as \xXXXX... */
- len = qword_get(&mesg, buf, PAGE_SIZE);
- if (len != 16)
- err = -EINVAL;
- else {
- exp.ex_uuid =
- kmemdup(buf, 16, GFP_KERNEL);
- if (exp.ex_uuid == NULL)
- err = -ENOMEM;
- }
- } else if (strcmp(buf, "secinfo") == 0)
+ else if (strcmp(buf, "uuid") == 0)
+ err = uuid_parse(&mesg, buf, &exp.ex_uuid);
+ else if (strcmp(buf, "secinfo") == 0)
err = secinfo_parse(&mesg, buf, &exp);
else
/* quietly ignore unknown words and anything
@@ -649,7 +671,7 @@ static int svc_export_show(struct seq_file *m,
if (exp->ex_uuid) {
int i;
seq_puts(m, ",uuid=");
- for (i=0; i<16; i++) {
+ for (i = 0; i < EX_UUID_LEN; i++) {
if ((i&3) == 0 && i)
seq_putc(m, ':');
seq_printf(m, "%02x", exp->ex_uuid[i]);
@@ -771,7 +793,7 @@ svc_export_update(struct svc_export *new, struct svc_export *old)
static struct svc_expkey *
-exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type,
+exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type,
u32 *fsidv, struct cache_req *reqp)
{
struct svc_expkey key, *ek;
@@ -793,9 +815,9 @@ exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type,
return ek;
}
-
-static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp,
- const struct path *path, struct cache_req *reqp)
+static struct svc_export *
+exp_get_by_name(struct cache_detail *cd, struct auth_domain *clp,
+ const struct path *path, struct cache_req *reqp)
{
struct svc_export *exp, key;
int err;
@@ -819,11 +841,11 @@ static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp,
/*
* Find the export entry for a given dentry.
*/
-static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp,
- struct path *path)
+static struct svc_export *
+exp_parent(struct cache_detail *cd, struct auth_domain *clp, struct path *path)
{
struct dentry *saved = dget(path->dentry);
- svc_export *exp = exp_get_by_name(cd, clp, path, NULL);
+ struct svc_export *exp = exp_get_by_name(cd, clp, path, NULL);
while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) {
struct dentry *parent = dget_parent(path->dentry);
@@ -844,7 +866,7 @@ static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp,
* since its harder to fool a kernel module than a user space program.
*/
int
-exp_rootfh(struct net *net, svc_client *clp, char *name,
+exp_rootfh(struct net *net, struct auth_domain *clp, char *name,
struct knfsd_fh *f, int maxsize)
{
struct svc_export *exp;
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
new file mode 100644
index 000000000000..cfeea85c5bed
--- /dev/null
+++ b/fs/nfsd/export.h
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef NFSD_EXPORT_H
+#define NFSD_EXPORT_H
+
+#include <linux/sunrpc/cache.h>
+#include <uapi/linux/nfsd/export.h>
+
+struct knfsd_fh;
+struct svc_fh;
+struct svc_rqst;
+
+/*
+ * FS Locations
+ */
+
+#define MAX_FS_LOCATIONS 128
+
+struct nfsd4_fs_location {
+ char *hosts; /* colon separated list of hosts */
+ char *path; /* slash separated list of path components */
+};
+
+struct nfsd4_fs_locations {
+ uint32_t locations_count;
+ struct nfsd4_fs_location *locations;
+/* If we're not actually serving this data ourselves (only providing a
+ * list of replicas that do serve it) then we set "migrated": */
+ int migrated;
+};
+
+/*
+ * We keep an array of pseudoflavors with the export, in order from most
+ * to least preferred. For the foreseeable future, we don't expect more
+ * than the eight pseudoflavors null, unix, krb5, krb5i, krb5p, skpm3,
+ * spkm3i, and spkm3p (and using all 8 at once should be rare).
+ */
+#define MAX_SECINFO_LIST 8
+#define EX_UUID_LEN 16
+
+struct exp_flavor_info {
+ u32 pseudoflavor;
+ u32 flags;
+};
+
+struct svc_export {
+ struct cache_head h;
+ struct auth_domain * ex_client;
+ int ex_flags;
+ struct path ex_path;
+ kuid_t ex_anon_uid;
+ kgid_t ex_anon_gid;
+ int ex_fsid;
+ unsigned char * ex_uuid; /* 16 byte fsid */
+ struct nfsd4_fs_locations ex_fslocs;
+ uint32_t ex_nflavors;
+ struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST];
+ struct cache_detail *cd;
+};
+
+/* an "export key" (expkey) maps a filehandlefragement to an
+ * svc_export for a given client. There can be several per export,
+ * for the different fsid types.
+ */
+struct svc_expkey {
+ struct cache_head h;
+
+ struct auth_domain * ek_client;
+ int ek_fsidtype;
+ u32 ek_fsid[6];
+
+ struct path ek_path;
+};
+
+#define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC))
+#define EX_NOHIDE(exp) ((exp)->ex_flags & NFSEXP_NOHIDE)
+#define EX_WGATHER(exp) ((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
+
+int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp);
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp);
+
+/*
+ * Function declarations
+ */
+int nfsd_export_init(struct net *);
+void nfsd_export_shutdown(struct net *);
+void nfsd_export_flush(struct net *);
+struct svc_export * rqst_exp_get_by_name(struct svc_rqst *,
+ struct path *);
+struct svc_export * rqst_exp_parent(struct svc_rqst *,
+ struct path *);
+struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *);
+int exp_rootfh(struct net *, struct auth_domain *,
+ char *path, struct knfsd_fh *, int maxsize);
+__be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
+__be32 nfserrno(int errno);
+
+static inline void exp_put(struct svc_export *exp)
+{
+ cache_put(&exp->h, exp->cd);
+}
+
+static inline void exp_get(struct svc_export *exp)
+{
+ cache_get(&exp->h);
+}
+struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *);
+
+#endif /* NFSD_EXPORT_H */
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index d620e7f81429..2ed05c3cd43d 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -97,25 +97,14 @@ static ssize_t fault_inject_read(struct file *file, char __user *buf,
{
static u64 val;
char read_buf[25];
- size_t size, ret;
+ size_t size;
loff_t pos = *ppos;
if (!pos)
nfsd_inject_get(file_inode(file)->i_private, &val);
size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
- if (pos < 0)
- return -EINVAL;
- if (pos >= size || !len)
- return 0;
- if (len > size - pos)
- len = size - pos;
- ret = copy_to_user(buf, read_buf + pos, len);
- if (ret == len)
- return -EFAULT;
- len -= ret;
- *ppos = pos + len;
- return len;
+ return simple_read_from_buffer(buf, len, ppos, read_buf, size);
}
static ssize_t fault_inject_write(struct file *file, const char __user *buf,
diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h
index 66e58db01936..a3f34900091f 100644
--- a/fs/nfsd/idmap.h
+++ b/fs/nfsd/idmap.h
@@ -56,7 +56,7 @@ static inline void nfsd_idmap_shutdown(struct net *net)
__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
-__be32 nfsd4_encode_user(struct svc_rqst *, kuid_t, __be32 **, int *);
-__be32 nfsd4_encode_group(struct svc_rqst *, kgid_t, __be32 **, int *);
+__be32 nfsd4_encode_user(struct xdr_stream *, struct svc_rqst *, kuid_t);
+__be32 nfsd4_encode_group(struct xdr_stream *, struct svc_rqst *, kgid_t);
#endif /* LINUX_NFSD_IDMAP_H */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 11c1fba29312..12b023a7ab7d 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -182,7 +182,8 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg
static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_getaclargs *argp)
{
- if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+ p = nfs2svc_decode_fh(p, &argp->fh);
+ if (!p)
return 0;
argp->mask = ntohl(*p); p++;
@@ -197,7 +198,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
unsigned int base;
int n;
- if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+ p = nfs2svc_decode_fh(p, &argp->fh);
+ if (!p)
return 0;
argp->mask = ntohl(*p++);
if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
@@ -218,7 +220,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_fhandle *argp)
{
- if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+ p = nfs2svc_decode_fh(p, &argp->fh);
+ if (!p)
return 0;
return xdr_argsize_check(rqstp, p);
}
@@ -226,7 +229,8 @@ static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_accessargs *argp)
{
- if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+ p = nfs2svc_decode_fh(p, &argp->fh);
+ if (!p)
return 0;
argp->access = ntohl(*p++);
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index adc5f1b1dc26..2a514e21dc74 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -128,7 +128,8 @@ out:
static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_getaclargs *args)
{
- if (!(p = nfs3svc_decode_fh(p, &args->fh)))
+ p = nfs3svc_decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->mask = ntohl(*p); p++;
@@ -143,7 +144,8 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
unsigned int base;
int n;
- if (!(p = nfs3svc_decode_fh(p, &args->fh)))
+ p = nfs3svc_decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->mask = ntohl(*p++);
if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index de6e39e12cb3..e6c01e80325e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -278,7 +278,8 @@ void fill_post_wcc(struct svc_fh *fhp)
int
nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
return xdr_argsize_check(rqstp, p);
}
@@ -287,7 +288,8 @@ int
nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_sattrargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p = decode_sattr3(p, &args->attrs);
@@ -315,7 +317,8 @@ int
nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_accessargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->access = ntohl(*p++);
@@ -330,7 +333,8 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
int v;
u32 max_blocksize = svc_max_payload(rqstp);
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p = xdr_decode_hyper(p, &args->offset);
@@ -360,7 +364,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
unsigned int len, v, hdr, dlen;
u32 max_blocksize = svc_max_payload(rqstp);
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p = xdr_decode_hyper(p, &args->offset);
@@ -535,7 +540,8 @@ int
nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_readlinkargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
@@ -558,7 +564,8 @@ int
nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_readdirargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p = xdr_decode_hyper(p, &args->cookie);
args->verf = p; p += 2;
@@ -580,7 +587,8 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
int len;
u32 max_blocksize = svc_max_payload(rqstp);
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p = xdr_decode_hyper(p, &args->cookie);
args->verf = p; p += 2;
@@ -605,7 +613,8 @@ int
nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_commitargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p = xdr_decode_hyper(p, &args->offset);
args->count = ntohl(*p++);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index f66c66b9f182..d714156a19fd 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -36,7 +36,6 @@
#include <linux/slab.h>
#include <linux/nfs_fs.h>
-#include <linux/export.h>
#include "nfsfh.h"
#include "nfsd.h"
#include "acl.h"
@@ -920,20 +919,19 @@ nfs4_acl_get_whotype(char *p, u32 len)
return NFS4_ACL_WHO_NAMED;
}
-__be32 nfs4_acl_write_who(int who, __be32 **p, int *len)
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who)
{
+ __be32 *p;
int i;
- int bytes;
for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
if (s2t_map[i].type != who)
continue;
- bytes = 4 + (XDR_QUADLEN(s2t_map[i].stringlen) << 2);
- if (bytes > *len)
+ p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4);
+ if (!p)
return nfserr_resource;
- *p = xdr_encode_opaque(*p, s2t_map[i].string,
+ p = xdr_encode_opaque(p, s2t_map[i].string,
s2t_map[i].stringlen);
- *len -= bytes;
return 0;
}
WARN_ON_ONCE(1);
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index c0dfde68742e..a0ab0a847d69 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -551,44 +551,43 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
return 0;
}
-static __be32 encode_ascii_id(u32 id, __be32 **p, int *buflen)
+static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id)
{
char buf[11];
int len;
- int bytes;
+ __be32 *p;
len = sprintf(buf, "%u", id);
- bytes = 4 + (XDR_QUADLEN(len) << 2);
- if (bytes > *buflen)
+ p = xdr_reserve_space(xdr, len + 4);
+ if (!p)
return nfserr_resource;
- *p = xdr_encode_opaque(*p, buf, len);
- *buflen -= bytes;
+ p = xdr_encode_opaque(p, buf, len);
return 0;
}
-static __be32 idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen)
+static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+ struct svc_rqst *rqstp, int type, u32 id)
{
struct ent *item, key = {
.id = id,
.type = type,
};
+ __be32 *p;
int ret;
- int bytes;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
if (ret == -ENOENT)
- return encode_ascii_id(id, p, buflen);
+ return encode_ascii_id(xdr, id);
if (ret)
return nfserrno(ret);
ret = strlen(item->name);
WARN_ON_ONCE(ret > IDMAP_NAMESZ);
- bytes = 4 + (XDR_QUADLEN(ret) << 2);
- if (bytes > *buflen)
+ p = xdr_reserve_space(xdr, ret + 4);
+ if (!p)
return nfserr_resource;
- *p = xdr_encode_opaque(*p, item->name, ret);
- *buflen -= bytes;
+ p = xdr_encode_opaque(p, item->name, ret);
cache_put(&item->h, nn->idtoname_cache);
return 0;
}
@@ -622,11 +621,12 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u
return idmap_name_to_id(rqstp, type, name, namelen, id);
}
-static __be32 encode_name_from_id(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen)
+static __be32 encode_name_from_id(struct xdr_stream *xdr,
+ struct svc_rqst *rqstp, int type, u32 id)
{
if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
- return encode_ascii_id(id, p, buflen);
- return idmap_id_to_name(rqstp, type, id, p, buflen);
+ return encode_ascii_id(xdr, id);
+ return idmap_id_to_name(xdr, rqstp, type, id);
}
__be32
@@ -655,14 +655,16 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
return status;
}
-__be32 nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t uid, __be32 **p, int *buflen)
+__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+ kuid_t uid)
{
u32 id = from_kuid(&init_user_ns, uid);
- return encode_name_from_id(rqstp, IDMAP_TYPE_USER, id, p, buflen);
+ return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id);
}
-__be32 nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t gid, __be32 **p, int *buflen)
+__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+ kgid_t gid)
{
u32 id = from_kgid(&init_user_ns, gid);
- return encode_name_from_id(rqstp, IDMAP_TYPE_GROUP, id, p, buflen);
+ return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d543222babf3..6851b003f2a4 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -430,12 +430,12 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
- open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
status = nfs4_check_open_reclaim(&open->op_clientid,
cstate->minorversion,
nn);
if (status)
goto out;
+ open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
case NFS4_OPEN_CLAIM_FH:
case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
status = do_open_fhandle(rqstp, cstate, open);
@@ -445,7 +445,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
break;
case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
case NFS4_OPEN_CLAIM_DELEGATE_PREV:
- open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
dprintk("NFSD: unsupported OPEN claim type %d\n",
open->op_claim_type);
status = nfserr_notsupp;
@@ -786,7 +785,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!nfsd4_last_compound_op(rqstp))
rqstp->rq_splice_ok = false;
- nfs4_lock_state();
/* check stateid */
if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
cstate, &read->rd_stateid,
@@ -794,11 +792,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
goto out;
}
- if (read->rd_filp)
- get_file(read->rd_filp);
status = nfs_ok;
out:
- nfs4_unlock_state();
read->rd_rqstp = rqstp;
read->rd_fhp = &cstate->current_fh;
return status;
@@ -937,10 +932,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
int err;
if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
- nfs4_lock_state();
status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
&setattr->sa_stateid, WR_STATE, NULL);
- nfs4_unlock_state();
if (status) {
dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
return status;
@@ -1006,17 +999,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (write->wr_offset >= OFFSET_MAX)
return nfserr_inval;
- nfs4_lock_state();
status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
cstate, stateid, WR_STATE, &filp);
if (status) {
- nfs4_unlock_state();
dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
return status;
}
- if (filp)
- get_file(filp);
- nfs4_unlock_state();
cnt = write->wr_buflen;
write->wr_how_written = write->wr_stable_how;
@@ -1072,10 +1060,10 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_jukebox;
p = buf;
- status = nfsd4_encode_fattr(&cstate->current_fh,
+ status = nfsd4_encode_fattr_to_buf(&p, count, &cstate->current_fh,
cstate->current_fh.fh_export,
- cstate->current_fh.fh_dentry, &p,
- count, verify->ve_bmval,
+ cstate->current_fh.fh_dentry,
+ verify->ve_bmval,
rqstp, 0);
/*
* If nfsd4_encode_fattr() ran out of space, assume that's because
@@ -1182,9 +1170,7 @@ struct nfsd4_operation {
static struct nfsd4_operation nfsd4_ops[];
-#ifdef NFSD_DEBUG
static const char *nfsd4_op_name(unsigned opnum);
-#endif
/*
* Enforce NFSv4.1 COMPOUND ordering rules:
@@ -1226,6 +1212,8 @@ static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
bool nfsd4_cache_this_op(struct nfsd4_op *op)
{
+ if (op->opnum == OP_ILLEGAL)
+ return false;
return OPDESC(op)->op_flags & OP_CACHEME;
}
@@ -1262,6 +1250,25 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
}
+static void svcxdr_init_encode(struct svc_rqst *rqstp,
+ struct nfsd4_compoundres *resp)
+{
+ struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_buf *buf = &rqstp->rq_res;
+ struct kvec *head = buf->head;
+
+ xdr->buf = buf;
+ xdr->iov = head;
+ xdr->p = head->iov_base + head->iov_len;
+ xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
+ /* Tail and page_len should be zero at this point: */
+ buf->len = buf->head[0].iov_len;
+ xdr->scratch.iov_len = 0;
+ xdr->page_ptr = buf->pages - 1;
+ buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages)
+ - rqstp->rq_auth_slack;
+}
+
/*
* COMPOUND call.
*/
@@ -1275,24 +1282,16 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate = &resp->cstate;
struct svc_fh *current_fh = &cstate->current_fh;
struct svc_fh *save_fh = &cstate->save_fh;
- int slack_bytes;
- u32 plen = 0;
__be32 status;
- resp->xbuf = &rqstp->rq_res;
- resp->p = rqstp->rq_res.head[0].iov_base +
- rqstp->rq_res.head[0].iov_len;
- resp->tagp = resp->p;
+ svcxdr_init_encode(rqstp, resp);
+ resp->tagp = resp->xdr.p;
/* reserve space for: taglen, tag, and opcnt */
- resp->p += 2 + XDR_QUADLEN(args->taglen);
- resp->end = rqstp->rq_res.head[0].iov_base + PAGE_SIZE;
+ xdr_reserve_space(&resp->xdr, 8 + args->taglen);
resp->taglen = args->taglen;
resp->tag = args->tag;
- resp->opcnt = 0;
resp->rqstp = rqstp;
cstate->minorversion = args->minorversion;
- cstate->replay_owner = NULL;
- cstate->session = NULL;
fh_init(current_fh, NFS4_FHSIZE);
fh_init(save_fh, NFS4_FHSIZE);
/*
@@ -1332,19 +1331,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
goto encode_op;
}
- /* We must be able to encode a successful response to
- * this operation, with enough room left over to encode a
- * failed response to the next operation. If we don't
- * have enough room, fail with ERR_RESOURCE.
- */
- slack_bytes = (char *)resp->end - (char *)resp->p;
- if (slack_bytes < COMPOUND_SLACK_SPACE
- + COMPOUND_ERR_SLACK_SPACE) {
- BUG_ON(slack_bytes < COMPOUND_ERR_SLACK_SPACE);
- op->status = nfserr_resource;
- goto encode_op;
- }
-
opdesc = OPDESC(op);
if (!current_fh->fh_dentry) {
@@ -1362,9 +1348,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
/* If op is non-idempotent */
if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
- plen = opdesc->op_rsize_bop(rqstp, op);
/*
- * If there's still another operation, make sure
+ * Don't execute this op if we couldn't encode a
+ * succesful reply:
+ */
+ u32 plen = opdesc->op_rsize_bop(rqstp, op);
+ /*
+ * Plus if there's another operation, make sure
* we'll have space to at least encode an error:
*/
if (resp->opcnt < args->opcnt)
@@ -1399,7 +1389,7 @@ encode_op:
}
if (op->status == nfserr_replay_me) {
op->replay = &cstate->replay_owner->so_replay;
- nfsd4_encode_replay(resp, op);
+ nfsd4_encode_replay(&resp->xdr, op);
status = op->status = op->replay->rp_status;
} else {
nfsd4_encode_operation(resp, op);
@@ -1438,7 +1428,8 @@ out:
#define op_encode_change_info_maxsz (5)
#define nfs4_fattr_bitmap_maxsz (4)
-#define op_encode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
+/* We'll fall back on returning no lockowner if run out of space: */
+#define op_encode_lockowner_maxsz (0)
#define op_encode_lock_denied_maxsz (8 + op_encode_lockowner_maxsz)
#define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
@@ -1470,6 +1461,49 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op
+ nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
}
+/*
+ * Note since this is an idempotent operation we won't insist on failing
+ * the op prematurely if the estimate is too large. We may turn off splice
+ * reads unnecessarily.
+ */
+static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp,
+ struct nfsd4_op *op)
+{
+ u32 *bmap = op->u.getattr.ga_bmval;
+ u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2];
+ u32 ret = 0;
+
+ if (bmap0 & FATTR4_WORD0_ACL)
+ return svc_max_payload(rqstp);
+ if (bmap0 & FATTR4_WORD0_FS_LOCATIONS)
+ return svc_max_payload(rqstp);
+
+ if (bmap1 & FATTR4_WORD1_OWNER) {
+ ret += IDMAP_NAMESZ + 4;
+ bmap1 &= ~FATTR4_WORD1_OWNER;
+ }
+ if (bmap1 & FATTR4_WORD1_OWNER_GROUP) {
+ ret += IDMAP_NAMESZ + 4;
+ bmap1 &= ~FATTR4_WORD1_OWNER_GROUP;
+ }
+ if (bmap0 & FATTR4_WORD0_FILEHANDLE) {
+ ret += NFS4_FHSIZE + 4;
+ bmap0 &= ~FATTR4_WORD0_FILEHANDLE;
+ }
+ if (bmap2 & FATTR4_WORD2_SECURITY_LABEL) {
+ ret += NFSD4_MAX_SEC_LABEL_LEN + 12;
+ bmap2 &= ~FATTR4_WORD2_SECURITY_LABEL;
+ }
+ /*
+ * Largest of remaining attributes are 16 bytes (e.g.,
+ * supported_attributes)
+ */
+ ret += 16 * (hweight32(bmap0) + hweight32(bmap1) + hweight32(bmap2));
+ /* bitmask, length */
+ ret += 20;
+ return ret;
+}
+
static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
return (op_encode_hdr_size + op_encode_change_info_maxsz)
@@ -1500,18 +1534,19 @@ static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
if (rlen > maxcount)
rlen = maxcount;
- return (op_encode_hdr_size + 2) * sizeof(__be32) + rlen;
+ return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32);
}
static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
+ u32 maxcount = svc_max_payload(rqstp);
u32 rlen = op->u.readdir.rd_maxcount;
- if (rlen > PAGE_SIZE)
- rlen = PAGE_SIZE;
+ if (rlen > maxcount)
+ rlen = maxcount;
- return (op_encode_hdr_size + op_encode_verifier_maxsz)
- * sizeof(__be32) + rlen;
+ return (op_encode_hdr_size + op_encode_verifier_maxsz +
+ XDR_QUADLEN(rlen)) * sizeof(__be32);
}
static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
@@ -1526,6 +1561,12 @@ static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op
+ op_encode_change_info_maxsz) * sizeof(__be32);
}
+static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp,
+ struct nfsd4_op *op)
+{
+ return NFS4_MAX_SESSIONID_LEN + 20;
+}
+
static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
@@ -1539,7 +1580,7 @@ static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_o
static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
- return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32);
+ return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32);
}
static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
@@ -1607,6 +1648,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
[OP_GETATTR] = {
.op_func = (nfsd4op_func)nfsd4_getattr,
.op_flags = ALLOWED_ON_ABSENT_FS,
+ .op_rsize_bop = nfsd4_getattr_rsize,
.op_name = "OP_GETATTR",
},
[OP_GETFH] = {
@@ -1676,37 +1718,32 @@ static struct nfsd4_operation nfsd4_ops[] = {
[OP_PUTFH] = {
.op_func = (nfsd4op_func)nfsd4_putfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
- | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
- | OP_CLEAR_STATEID,
+ | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
.op_name = "OP_PUTFH",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
[OP_PUTPUBFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
- | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
- | OP_CLEAR_STATEID,
+ | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
.op_name = "OP_PUTPUBFH",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
[OP_PUTROOTFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
- | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
- | OP_CLEAR_STATEID,
+ | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
.op_name = "OP_PUTROOTFH",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
[OP_READ] = {
.op_func = (nfsd4op_func)nfsd4_read,
- .op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_READ",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize,
.op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid,
},
[OP_READDIR] = {
.op_func = (nfsd4op_func)nfsd4_readdir,
- .op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_READDIR",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize,
},
@@ -1864,14 +1901,33 @@ static struct nfsd4_operation nfsd4_ops[] = {
},
};
-#ifdef NFSD_DEBUG
+int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+ struct nfsd4_operation *opdesc;
+ nfsd4op_rsize estimator;
+
+ if (op->opnum == OP_ILLEGAL)
+ return op_encode_hdr_size * sizeof(__be32);
+ opdesc = OPDESC(op);
+ estimator = opdesc->op_rsize_bop;
+ return estimator ? estimator(rqstp, op) : PAGE_SIZE;
+}
+
+void warn_on_nonidempotent_op(struct nfsd4_op *op)
+{
+ if (OPDESC(op)->op_flags & OP_MODIFIES_SOMETHING) {
+ pr_err("unable to encode reply to nonidempotent op %d (%s)\n",
+ op->opnum, nfsd4_op_name(op->opnum));
+ WARN_ON_ONCE(1);
+ }
+}
+
static const char *nfsd4_op_name(unsigned opnum)
{
if (opnum < ARRAY_SIZE(nfsd4_ops))
return nfsd4_ops[opnum].op_name;
return "unknown_operation";
}
-#endif
#define nfsd4_voidres nfsd4_voidargs
struct nfsd4_voidargs { int dummy; };
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9a77a5a21557..c0d45cec9958 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -81,13 +81,13 @@ static DEFINE_MUTEX(client_mutex);
* effort to decrease the scope of the client_mutex, this spinlock may
* eventually cover more:
*/
-static DEFINE_SPINLOCK(recall_lock);
+static DEFINE_SPINLOCK(state_lock);
-static struct kmem_cache *openowner_slab = NULL;
-static struct kmem_cache *lockowner_slab = NULL;
-static struct kmem_cache *file_slab = NULL;
-static struct kmem_cache *stateid_slab = NULL;
-static struct kmem_cache *deleg_slab = NULL;
+static struct kmem_cache *openowner_slab;
+static struct kmem_cache *lockowner_slab;
+static struct kmem_cache *file_slab;
+static struct kmem_cache *stateid_slab;
+static struct kmem_cache *deleg_slab;
void
nfs4_lock_state(void)
@@ -235,9 +235,9 @@ static void nfsd4_free_file(struct nfs4_file *f)
static inline void
put_nfs4_file(struct nfs4_file *fi)
{
- if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) {
+ if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) {
hlist_del(&fi->fi_hash);
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
iput(fi->fi_inode);
nfsd4_free_file(fi);
}
@@ -375,7 +375,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
return dp;
- dp->dl_stid.sc_type = NFS4_DELEG_STID;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -418,6 +417,8 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
static void nfs4_put_deleg_lease(struct nfs4_file *fp)
{
+ if (!fp->fi_lease)
+ return;
if (atomic_dec_and_test(&fp->fi_delegees)) {
vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
fp->fi_lease = NULL;
@@ -431,18 +432,30 @@ static void unhash_stid(struct nfs4_stid *s)
s->sc_type = 0;
}
+static void
+hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
+{
+ lockdep_assert_held(&state_lock);
+
+ dp->dl_stid.sc_type = NFS4_DELEG_STID;
+ list_add(&dp->dl_perfile, &fp->fi_delegations);
+ list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
+}
+
/* Called under the state lock. */
static void
unhash_delegation(struct nfs4_delegation *dp)
{
+ spin_lock(&state_lock);
list_del_init(&dp->dl_perclnt);
- spin_lock(&recall_lock);
list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_recall_lru);
- spin_unlock(&recall_lock);
- nfs4_put_deleg_lease(dp->dl_file);
- put_nfs4_file(dp->dl_file);
- dp->dl_file = NULL;
+ spin_unlock(&state_lock);
+ if (dp->dl_file) {
+ nfs4_put_deleg_lease(dp->dl_file);
+ put_nfs4_file(dp->dl_file);
+ dp->dl_file = NULL;
+ }
}
@@ -645,6 +658,12 @@ static void unhash_lockowner(struct nfs4_lockowner *lo)
}
}
+static void nfs4_free_lockowner(struct nfs4_lockowner *lo)
+{
+ kfree(lo->lo_owner.so_owner.data);
+ kmem_cache_free(lockowner_slab, lo);
+}
+
static void release_lockowner(struct nfs4_lockowner *lo)
{
unhash_lockowner(lo);
@@ -699,6 +718,12 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
}
}
+static void nfs4_free_openowner(struct nfs4_openowner *oo)
+{
+ kfree(oo->oo_owner.so_owner.data);
+ kmem_cache_free(openowner_slab, oo);
+}
+
static void release_openowner(struct nfs4_openowner *oo)
{
unhash_openowner(oo);
@@ -1093,7 +1118,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
return clp;
}
-static inline void
+static void
free_client(struct nfs4_client *clp)
{
struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id);
@@ -1136,13 +1161,13 @@ destroy_client(struct nfs4_client *clp)
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
INIT_LIST_HEAD(&reaplist);
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
while (!list_empty(&clp->cl_delegations)) {
dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
list_del_init(&dp->dl_perclnt);
list_move(&dp->dl_recall_lru, &reaplist);
}
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
while (!list_empty(&reaplist)) {
dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
destroy_delegation(dp);
@@ -1544,6 +1569,7 @@ out_err:
void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
+ struct xdr_buf *buf = resp->xdr.buf;
struct nfsd4_slot *slot = resp->cstate.slot;
unsigned int base;
@@ -1557,11 +1583,9 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
slot->sl_datalen = 0;
return;
}
- slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap;
- base = (char *)resp->cstate.datap -
- (char *)resp->xbuf->head[0].iov_base;
- if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data,
- slot->sl_datalen))
+ base = resp->cstate.data_offset;
+ slot->sl_datalen = buf->len - base;
+ if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
WARN("%s: sessions DRC could not cache compound\n", __func__);
return;
}
@@ -1602,6 +1626,8 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
struct nfsd4_sequence *seq)
{
struct nfsd4_slot *slot = resp->cstate.slot;
+ struct xdr_stream *xdr = &resp->xdr;
+ __be32 *p;
__be32 status;
dprintk("--> %s slot %p\n", __func__, slot);
@@ -1610,14 +1636,16 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
if (status)
return status;
- /* The sequence operation has been encoded, cstate->datap set. */
- memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen);
+ p = xdr_reserve_space(xdr, slot->sl_datalen);
+ if (!p) {
+ WARN_ON_ONCE(1);
+ return nfserr_serverfault;
+ }
+ xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen);
+ xdr_commit_encode(xdr);
resp->opcnt = slot->sl_opcnt;
- resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen);
- status = slot->sl_status;
-
- return status;
+ return slot->sl_status;
}
/*
@@ -2189,11 +2217,13 @@ nfsd4_sequence(struct svc_rqst *rqstp,
struct nfsd4_sequence *seq)
{
struct nfsd4_compoundres *resp = rqstp->rq_resp;
+ struct xdr_stream *xdr = &resp->xdr;
struct nfsd4_session *session;
struct nfs4_client *clp;
struct nfsd4_slot *slot;
struct nfsd4_conn *conn;
__be32 status;
+ int buflen;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
if (resp->opcnt != 1)
@@ -2262,6 +2292,16 @@ nfsd4_sequence(struct svc_rqst *rqstp,
if (status)
goto out_put_session;
+ buflen = (seq->cachethis) ?
+ session->se_fchannel.maxresp_cached :
+ session->se_fchannel.maxresp_sz;
+ status = (seq->cachethis) ? nfserr_rep_too_big_to_cache :
+ nfserr_rep_too_big;
+ if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack))
+ goto out_put_session;
+ svc_reserve(rqstp, buflen);
+
+ status = nfs_ok;
/* Success! bump slot seqid */
slot->sl_seqid = seq->seqid;
slot->sl_flags |= NFSD4_SLOT_INUSE;
@@ -2499,28 +2539,19 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
fp->fi_lease = NULL;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access));
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]);
- spin_unlock(&recall_lock);
-}
-
-static void
-nfsd4_free_slab(struct kmem_cache **slab)
-{
- if (*slab == NULL)
- return;
- kmem_cache_destroy(*slab);
- *slab = NULL;
+ spin_unlock(&state_lock);
}
void
nfsd4_free_slabs(void)
{
- nfsd4_free_slab(&openowner_slab);
- nfsd4_free_slab(&lockowner_slab);
- nfsd4_free_slab(&file_slab);
- nfsd4_free_slab(&stateid_slab);
- nfsd4_free_slab(&deleg_slab);
+ kmem_cache_destroy(openowner_slab);
+ kmem_cache_destroy(lockowner_slab);
+ kmem_cache_destroy(file_slab);
+ kmem_cache_destroy(stateid_slab);
+ kmem_cache_destroy(deleg_slab);
}
int
@@ -2529,42 +2560,38 @@ nfsd4_init_slabs(void)
openowner_slab = kmem_cache_create("nfsd4_openowners",
sizeof(struct nfs4_openowner), 0, 0, NULL);
if (openowner_slab == NULL)
- goto out_nomem;
+ goto out;
lockowner_slab = kmem_cache_create("nfsd4_lockowners",
sizeof(struct nfs4_lockowner), 0, 0, NULL);
if (lockowner_slab == NULL)
- goto out_nomem;
+ goto out_free_openowner_slab;
file_slab = kmem_cache_create("nfsd4_files",
sizeof(struct nfs4_file), 0, 0, NULL);
if (file_slab == NULL)
- goto out_nomem;
+ goto out_free_lockowner_slab;
stateid_slab = kmem_cache_create("nfsd4_stateids",
sizeof(struct nfs4_ol_stateid), 0, 0, NULL);
if (stateid_slab == NULL)
- goto out_nomem;
+ goto out_free_file_slab;
deleg_slab = kmem_cache_create("nfsd4_delegations",
sizeof(struct nfs4_delegation), 0, 0, NULL);
if (deleg_slab == NULL)
- goto out_nomem;
+ goto out_free_stateid_slab;
return 0;
-out_nomem:
- nfsd4_free_slabs();
+
+out_free_stateid_slab:
+ kmem_cache_destroy(stateid_slab);
+out_free_file_slab:
+ kmem_cache_destroy(file_slab);
+out_free_lockowner_slab:
+ kmem_cache_destroy(lockowner_slab);
+out_free_openowner_slab:
+ kmem_cache_destroy(openowner_slab);
+out:
dprintk("nfsd4: out of memory while initializing nfsv4\n");
return -ENOMEM;
}
-void nfs4_free_openowner(struct nfs4_openowner *oo)
-{
- kfree(oo->oo_owner.so_owner.data);
- kmem_cache_free(openowner_slab, oo);
-}
-
-void nfs4_free_lockowner(struct nfs4_lockowner *lo)
-{
- kfree(lo->lo_owner.so_owner.data);
- kmem_cache_free(lockowner_slab, lo);
-}
-
static void init_nfs4_replay(struct nfs4_replay *rp)
{
rp->rp_status = nfserr_serverfault;
@@ -2685,15 +2712,15 @@ find_file(struct inode *ino)
unsigned int hashval = file_hashval(ino);
struct nfs4_file *fp;
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) {
if (fp->fi_inode == ino) {
get_nfs4_file(fp);
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
return fp;
}
}
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
return NULL;
}
@@ -2730,6 +2757,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
struct nfs4_client *clp = dp->dl_stid.sc_client;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ lockdep_assert_held(&state_lock);
/* We're assuming the state code never drops its reference
* without first removing the lease. Since we're in this lease
* callback (and since the lease code is serialized by the kernel
@@ -2766,11 +2794,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
*/
fl->fl_break_time = 0;
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
fp->fi_had_conflict = true;
list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
nfsd_break_one_deleg(dp);
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
}
static
@@ -3047,11 +3075,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
if (status)
goto out_free;
- list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
fp->fi_lease = fl;
fp->fi_deleg_file = get_file(fl->fl_file);
atomic_set(&fp->fi_delegees, 1);
- list_add(&dp->dl_perfile, &fp->fi_delegations);
+ spin_lock(&state_lock);
+ hash_delegation_locked(dp, fp);
+ spin_unlock(&state_lock);
return 0;
out_free:
locks_free_lock(fl);
@@ -3060,33 +3089,21 @@ out_free:
static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp)
{
- int status;
-
if (fp->fi_had_conflict)
return -EAGAIN;
get_nfs4_file(fp);
dp->dl_file = fp;
- if (!fp->fi_lease) {
- status = nfs4_setlease(dp);
- if (status)
- goto out_free;
- return 0;
- }
- spin_lock(&recall_lock);
+ if (!fp->fi_lease)
+ return nfs4_setlease(dp);
+ spin_lock(&state_lock);
+ atomic_inc(&fp->fi_delegees);
if (fp->fi_had_conflict) {
- spin_unlock(&recall_lock);
- status = -EAGAIN;
- goto out_free;
+ spin_unlock(&state_lock);
+ return -EAGAIN;
}
- atomic_inc(&fp->fi_delegees);
- list_add(&dp->dl_perfile, &fp->fi_delegations);
- spin_unlock(&recall_lock);
- list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
+ hash_delegation_locked(dp, fp);
+ spin_unlock(&state_lock);
return 0;
-out_free:
- put_nfs4_file(fp);
- dp->dl_file = fp;
- return status;
}
static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
@@ -3173,8 +3190,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
return;
out_free:
- remove_stid(&dp->dl_stid);
- nfs4_put_delegation(dp);
+ destroy_delegation(dp);
out_no_deleg:
open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE;
if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
@@ -3391,8 +3407,7 @@ nfs4_laundromat(struct nfsd_net *nn)
struct nfs4_delegation *dp;
struct list_head *pos, *next, reaplist;
time_t cutoff = get_seconds() - nn->nfsd4_lease;
- time_t t, clientid_val = nn->nfsd4_lease;
- time_t u, test_val = nn->nfsd4_lease;
+ time_t t, new_timeo = nn->nfsd4_lease;
nfs4_lock_state();
@@ -3404,8 +3419,7 @@ nfs4_laundromat(struct nfsd_net *nn)
clp = list_entry(pos, struct nfs4_client, cl_lru);
if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
t = clp->cl_time - cutoff;
- if (clientid_val > t)
- clientid_val = t;
+ new_timeo = min(new_timeo, t);
break;
}
if (mark_client_expired_locked(clp)) {
@@ -3422,39 +3436,35 @@ nfs4_laundromat(struct nfsd_net *nn)
clp->cl_clientid.cl_id);
expire_client(clp);
}
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn)
continue;
if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) {
- u = dp->dl_time - cutoff;
- if (test_val > u)
- test_val = u;
+ t = dp->dl_time - cutoff;
+ new_timeo = min(new_timeo, t);
break;
}
list_move(&dp->dl_recall_lru, &reaplist);
}
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
list_for_each_safe(pos, next, &reaplist) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
revoke_delegation(dp);
}
- test_val = nn->nfsd4_lease;
list_for_each_safe(pos, next, &nn->close_lru) {
oo = container_of(pos, struct nfs4_openowner, oo_close_lru);
if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) {
- u = oo->oo_time - cutoff;
- if (test_val > u)
- test_val = u;
+ t = oo->oo_time - cutoff;
+ new_timeo = min(new_timeo, t);
break;
}
release_openowner(oo);
}
- if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT)
- clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT;
+ new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
nfs4_unlock_state();
- return clientid_val;
+ return new_timeo;
}
static struct workqueue_struct *laundry_wq;
@@ -3654,6 +3664,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
struct svc_fh *current_fh = &cstate->current_fh;
struct inode *ino = current_fh->fh_dentry->d_inode;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct file *file = NULL;
__be32 status;
if (filpp)
@@ -3665,10 +3676,12 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return check_special_stateids(net, current_fh, stateid, flags);
+ nfs4_lock_state();
+
status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
&s, cstate->minorversion, nn);
if (status)
- return status;
+ goto out;
status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
if (status)
goto out;
@@ -3679,8 +3692,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (status)
goto out;
if (filpp) {
- *filpp = dp->dl_file->fi_deleg_file;
- if (!*filpp) {
+ file = dp->dl_file->fi_deleg_file;
+ if (!file) {
WARN_ON_ONCE(1);
status = nfserr_serverfault;
goto out;
@@ -3701,16 +3714,20 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
goto out;
if (filpp) {
if (flags & RD_STATE)
- *filpp = find_readable_file(stp->st_file);
+ file = find_readable_file(stp->st_file);
else
- *filpp = find_writeable_file(stp->st_file);
+ file = find_writeable_file(stp->st_file);
}
break;
default:
- return nfserr_bad_stateid;
+ status = nfserr_bad_stateid;
+ goto out;
}
status = nfs_ok;
+ if (file)
+ *filpp = get_file(file);
out:
+ nfs4_unlock_state();
return status;
}
@@ -3726,7 +3743,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
* correspondance, and we have to delete the lockowner when we
* delete the lock stateid:
*/
- unhash_lockowner(lo);
+ release_lockowner(lo);
return nfs_ok;
}
@@ -4896,6 +4913,7 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max,
struct nfs4_delegation *dp, *next;
u64 count = 0;
+ lockdep_assert_held(&state_lock);
list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) {
if (victims)
list_move(&dp->dl_recall_lru, victims);
@@ -4911,9 +4929,9 @@ u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max)
LIST_HEAD(victims);
u64 count;
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
count = nfsd_find_all_delegations(clp, max, &victims);
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
revoke_delegation(dp);
@@ -4927,11 +4945,11 @@ u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max)
LIST_HEAD(victims);
u64 count;
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
count = nfsd_find_all_delegations(clp, max, &victims);
list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
nfsd_break_one_deleg(dp);
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
return count;
}
@@ -4940,9 +4958,9 @@ u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max)
{
u64 count = 0;
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
count = nfsd_find_all_delegations(clp, max, NULL);
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
nfsd_print_count(clp, count, "delegations");
return count;
@@ -4983,13 +5001,6 @@ struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_
#endif /* CONFIG_NFSD_FAULT_INJECTION */
-/* initialization to perform at module load time: */
-
-void
-nfs4_state_init(void)
-{
-}
-
/*
* Since the lifetime of a delegation isn't limited to that of an open, a
* client may quite reasonably hang on to a delegation as long as it has
@@ -5160,12 +5171,12 @@ nfs4_state_shutdown_net(struct net *net)
nfs4_lock_state();
INIT_LIST_HEAD(&reaplist);
- spin_lock(&recall_lock);
+ spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
list_move(&dp->dl_recall_lru, &reaplist);
}
- spin_unlock(&recall_lock);
+ spin_unlock(&state_lock);
list_for_each_safe(pos, next, &reaplist) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
destroy_delegation(dp);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 18881f34737a..2d305a121f37 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -98,11 +98,6 @@ xdr_error: \
status = nfserr_bad_xdr; \
goto out
-#define READ32(x) (x) = ntohl(*p++)
-#define READ64(x) do { \
- (x) = (u64)ntohl(*p++) << 32; \
- (x) |= ntohl(*p++); \
-} while (0)
#define READMEM(x,nbytes) do { \
x = (char *)p; \
p += XDR_QUADLEN(nbytes); \
@@ -248,17 +243,17 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
bmval[2] = 0;
READ_BUF(4);
- READ32(bmlen);
+ bmlen = be32_to_cpup(p++);
if (bmlen > 1000)
goto xdr_error;
READ_BUF(bmlen << 2);
if (bmlen > 0)
- READ32(bmval[0]);
+ bmval[0] = be32_to_cpup(p++);
if (bmlen > 1)
- READ32(bmval[1]);
+ bmval[1] = be32_to_cpup(p++);
if (bmlen > 2)
- READ32(bmval[2]);
+ bmval[2] = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -270,6 +265,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
{
int expected_len, len = 0;
u32 dummy32;
+ u64 sec;
char *buf;
DECODE_HEAD;
@@ -278,12 +274,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
return status;
READ_BUF(4);
- READ32(expected_len);
+ expected_len = be32_to_cpup(p++);
if (bmval[0] & FATTR4_WORD0_SIZE) {
READ_BUF(8);
len += 8;
- READ64(iattr->ia_size);
+ p = xdr_decode_hyper(p, &iattr->ia_size);
iattr->ia_valid |= ATTR_SIZE;
}
if (bmval[0] & FATTR4_WORD0_ACL) {
@@ -291,7 +287,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
struct nfs4_ace *ace;
READ_BUF(4); len += 4;
- READ32(nace);
+ nace = be32_to_cpup(p++);
if (nace > NFS4_ACL_MAX)
return nfserr_fbig;
@@ -305,10 +301,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
(*acl)->naces = nace;
for (ace = (*acl)->aces; ace < (*acl)->aces + nace; ace++) {
READ_BUF(16); len += 16;
- READ32(ace->type);
- READ32(ace->flag);
- READ32(ace->access_mask);
- READ32(dummy32);
+ ace->type = be32_to_cpup(p++);
+ ace->flag = be32_to_cpup(p++);
+ ace->access_mask = be32_to_cpup(p++);
+ dummy32 = be32_to_cpup(p++);
READ_BUF(dummy32);
len += XDR_QUADLEN(dummy32) << 2;
READMEM(buf, dummy32);
@@ -330,14 +326,14 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
if (bmval[1] & FATTR4_WORD1_MODE) {
READ_BUF(4);
len += 4;
- READ32(iattr->ia_mode);
+ iattr->ia_mode = be32_to_cpup(p++);
iattr->ia_mode &= (S_IFMT | S_IALLUGO);
iattr->ia_valid |= ATTR_MODE;
}
if (bmval[1] & FATTR4_WORD1_OWNER) {
READ_BUF(4);
len += 4;
- READ32(dummy32);
+ dummy32 = be32_to_cpup(p++);
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
@@ -348,7 +344,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) {
READ_BUF(4);
len += 4;
- READ32(dummy32);
+ dummy32 = be32_to_cpup(p++);
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
@@ -359,15 +355,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
READ_BUF(4);
len += 4;
- READ32(dummy32);
+ dummy32 = be32_to_cpup(p++);
switch (dummy32) {
case NFS4_SET_TO_CLIENT_TIME:
/* We require the high 32 bits of 'seconds' to be 0, and we ignore
all 32 bits of 'nseconds'. */
READ_BUF(12);
len += 12;
- READ64(iattr->ia_atime.tv_sec);
- READ32(iattr->ia_atime.tv_nsec);
+ p = xdr_decode_hyper(p, &sec);
+ iattr->ia_atime.tv_sec = (time_t)sec;
+ iattr->ia_atime.tv_nsec = be32_to_cpup(p++);
if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
return nfserr_inval;
iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
@@ -382,15 +379,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
READ_BUF(4);
len += 4;
- READ32(dummy32);
+ dummy32 = be32_to_cpup(p++);
switch (dummy32) {
case NFS4_SET_TO_CLIENT_TIME:
/* We require the high 32 bits of 'seconds' to be 0, and we ignore
all 32 bits of 'nseconds'. */
READ_BUF(12);
len += 12;
- READ64(iattr->ia_mtime.tv_sec);
- READ32(iattr->ia_mtime.tv_nsec);
+ p = xdr_decode_hyper(p, &sec);
+ iattr->ia_mtime.tv_sec = sec;
+ iattr->ia_mtime.tv_nsec = be32_to_cpup(p++);
if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
return nfserr_inval;
iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
@@ -408,13 +406,13 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
READ_BUF(4);
len += 4;
- READ32(dummy32); /* lfs: we don't use it */
+ dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */
READ_BUF(4);
len += 4;
- READ32(dummy32); /* pi: we don't use it either */
+ dummy32 = be32_to_cpup(p++); /* pi: we don't use it either */
READ_BUF(4);
len += 4;
- READ32(dummy32);
+ dummy32 = be32_to_cpup(p++);
READ_BUF(dummy32);
if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN)
return nfserr_badlabel;
@@ -445,7 +443,7 @@ nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid)
DECODE_HEAD;
READ_BUF(sizeof(stateid_t));
- READ32(sid->si_generation);
+ sid->si_generation = be32_to_cpup(p++);
COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t));
DECODE_TAIL;
@@ -457,7 +455,7 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
DECODE_HEAD;
READ_BUF(4);
- READ32(access->ac_req_access);
+ access->ac_req_access = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -472,7 +470,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
/* callback_sec_params4 */
READ_BUF(4);
- READ32(nr_secflavs);
+ nr_secflavs = be32_to_cpup(p++);
if (nr_secflavs)
cbs->flavor = (u32)(-1);
else
@@ -480,7 +478,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
cbs->flavor = 0;
for (i = 0; i < nr_secflavs; ++i) {
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
switch (dummy) {
case RPC_AUTH_NULL:
/* Nothing to read */
@@ -490,21 +488,21 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
case RPC_AUTH_UNIX:
READ_BUF(8);
/* stamp */
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
/* machine name */
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
SAVEMEM(machine_name, dummy);
/* uid, gid */
READ_BUF(8);
- READ32(uid);
- READ32(gid);
+ uid = be32_to_cpup(p++);
+ gid = be32_to_cpup(p++);
/* more gids */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy * 4);
if (cbs->flavor == (u32)(-1)) {
kuid_t kuid = make_kuid(&init_user_ns, uid);
@@ -524,14 +522,14 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
"not supported!\n");
READ_BUF(8);
/* gcbp_service */
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
/* gcbp_handle_from_server */
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
/* gcbp_handle_from_client */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
break;
default:
@@ -547,7 +545,7 @@ static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, stru
DECODE_HEAD;
READ_BUF(4);
- READ32(bc->bc_cb_program);
+ bc->bc_cb_program = be32_to_cpup(p++);
nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec);
DECODE_TAIL;
@@ -559,7 +557,7 @@ static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp,
READ_BUF(NFS4_MAX_SESSIONID_LEN + 8);
COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
- READ32(bcts->dir);
+ bcts->dir = be32_to_cpup(p++);
/* XXX: skipping ctsa_use_conn_in_rdma_mode. Perhaps Tom Tucker
* could help us figure out we should be using it. */
DECODE_TAIL;
@@ -571,7 +569,7 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
DECODE_HEAD;
READ_BUF(4);
- READ32(close->cl_seqid);
+ close->cl_seqid = be32_to_cpup(p++);
return nfsd4_decode_stateid(argp, &close->cl_stateid);
DECODE_TAIL;
@@ -584,8 +582,8 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit
DECODE_HEAD;
READ_BUF(12);
- READ64(commit->co_offset);
- READ32(commit->co_count);
+ p = xdr_decode_hyper(p, &commit->co_offset);
+ commit->co_count = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -596,19 +594,19 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
DECODE_HEAD;
READ_BUF(4);
- READ32(create->cr_type);
+ create->cr_type = be32_to_cpup(p++);
switch (create->cr_type) {
case NF4LNK:
READ_BUF(4);
- READ32(create->cr_linklen);
+ create->cr_linklen = be32_to_cpup(p++);
READ_BUF(create->cr_linklen);
SAVEMEM(create->cr_linkname, create->cr_linklen);
break;
case NF4BLK:
case NF4CHR:
READ_BUF(8);
- READ32(create->cr_specdata1);
- READ32(create->cr_specdata2);
+ create->cr_specdata1 = be32_to_cpup(p++);
+ create->cr_specdata2 = be32_to_cpup(p++);
break;
case NF4SOCK:
case NF4FIFO:
@@ -618,7 +616,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
}
READ_BUF(4);
- READ32(create->cr_namelen);
+ create->cr_namelen = be32_to_cpup(p++);
READ_BUF(create->cr_namelen);
SAVEMEM(create->cr_name, create->cr_namelen);
if ((status = check_filename(create->cr_name, create->cr_namelen)))
@@ -650,7 +648,7 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
DECODE_HEAD;
READ_BUF(4);
- READ32(link->li_namelen);
+ link->li_namelen = be32_to_cpup(p++);
READ_BUF(link->li_namelen);
SAVEMEM(link->li_name, link->li_namelen);
if ((status = check_filename(link->li_name, link->li_namelen)))
@@ -668,24 +666,24 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
* type, reclaim(boolean), offset, length, new_lock_owner(boolean)
*/
READ_BUF(28);
- READ32(lock->lk_type);
+ lock->lk_type = be32_to_cpup(p++);
if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT))
goto xdr_error;
- READ32(lock->lk_reclaim);
- READ64(lock->lk_offset);
- READ64(lock->lk_length);
- READ32(lock->lk_is_new);
+ lock->lk_reclaim = be32_to_cpup(p++);
+ p = xdr_decode_hyper(p, &lock->lk_offset);
+ p = xdr_decode_hyper(p, &lock->lk_length);
+ lock->lk_is_new = be32_to_cpup(p++);
if (lock->lk_is_new) {
READ_BUF(4);
- READ32(lock->lk_new_open_seqid);
+ lock->lk_new_open_seqid = be32_to_cpup(p++);
status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid);
if (status)
return status;
READ_BUF(8 + sizeof(clientid_t));
- READ32(lock->lk_new_lock_seqid);
+ lock->lk_new_lock_seqid = be32_to_cpup(p++);
COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t));
- READ32(lock->lk_new_owner.len);
+ lock->lk_new_owner.len = be32_to_cpup(p++);
READ_BUF(lock->lk_new_owner.len);
READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len);
} else {
@@ -693,7 +691,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
if (status)
return status;
READ_BUF(4);
- READ32(lock->lk_old_lock_seqid);
+ lock->lk_old_lock_seqid = be32_to_cpup(p++);
}
DECODE_TAIL;
@@ -705,13 +703,13 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
DECODE_HEAD;
READ_BUF(32);
- READ32(lockt->lt_type);
+ lockt->lt_type = be32_to_cpup(p++);
if((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT))
goto xdr_error;
- READ64(lockt->lt_offset);
- READ64(lockt->lt_length);
+ p = xdr_decode_hyper(p, &lockt->lt_offset);
+ p = xdr_decode_hyper(p, &lockt->lt_length);
COPYMEM(&lockt->lt_clientid, 8);
- READ32(lockt->lt_owner.len);
+ lockt->lt_owner.len = be32_to_cpup(p++);
READ_BUF(lockt->lt_owner.len);
READMEM(lockt->lt_owner.data, lockt->lt_owner.len);
@@ -724,16 +722,16 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku)
DECODE_HEAD;
READ_BUF(8);
- READ32(locku->lu_type);
+ locku->lu_type = be32_to_cpup(p++);
if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT))
goto xdr_error;
- READ32(locku->lu_seqid);
+ locku->lu_seqid = be32_to_cpup(p++);
status = nfsd4_decode_stateid(argp, &locku->lu_stateid);
if (status)
return status;
READ_BUF(16);
- READ64(locku->lu_offset);
- READ64(locku->lu_length);
+ p = xdr_decode_hyper(p, &locku->lu_offset);
+ p = xdr_decode_hyper(p, &locku->lu_length);
DECODE_TAIL;
}
@@ -744,7 +742,7 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup
DECODE_HEAD;
READ_BUF(4);
- READ32(lookup->lo_len);
+ lookup->lo_len = be32_to_cpup(p++);
READ_BUF(lookup->lo_len);
SAVEMEM(lookup->lo_name, lookup->lo_len);
if ((status = check_filename(lookup->lo_name, lookup->lo_len)))
@@ -759,7 +757,7 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh
u32 w;
READ_BUF(4);
- READ32(w);
+ w = be32_to_cpup(p++);
*share_access = w & NFS4_SHARE_ACCESS_MASK;
*deleg_want = w & NFS4_SHARE_WANT_MASK;
if (deleg_when)
@@ -811,7 +809,7 @@ static __be32 nfsd4_decode_share_deny(struct nfsd4_compoundargs *argp, u32 *x)
__be32 *p;
READ_BUF(4);
- READ32(*x);
+ *x = be32_to_cpup(p++);
/* Note: unlinke access bits, deny bits may be zero. */
if (*x & ~NFS4_SHARE_DENY_BOTH)
return nfserr_bad_xdr;
@@ -825,7 +823,7 @@ static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_ne
__be32 *p;
READ_BUF(4);
- READ32(o->len);
+ o->len = be32_to_cpup(p++);
if (o->len == 0 || o->len > NFS4_OPAQUE_LIMIT)
return nfserr_bad_xdr;
@@ -850,7 +848,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
open->op_xdr_error = 0;
/* seqid, share_access, share_deny, clientid, ownerlen */
READ_BUF(4);
- READ32(open->op_seqid);
+ open->op_seqid = be32_to_cpup(p++);
/* decode, yet ignore deleg_when until supported */
status = nfsd4_decode_share_access(argp, &open->op_share_access,
&open->op_deleg_want, &dummy);
@@ -865,13 +863,13 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
if (status)
goto xdr_error;
READ_BUF(4);
- READ32(open->op_create);
+ open->op_create = be32_to_cpup(p++);
switch (open->op_create) {
case NFS4_OPEN_NOCREATE:
break;
case NFS4_OPEN_CREATE:
READ_BUF(4);
- READ32(open->op_createmode);
+ open->op_createmode = be32_to_cpup(p++);
switch (open->op_createmode) {
case NFS4_CREATE_UNCHECKED:
case NFS4_CREATE_GUARDED:
@@ -904,12 +902,12 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
/* open_claim */
READ_BUF(4);
- READ32(open->op_claim_type);
+ open->op_claim_type = be32_to_cpup(p++);
switch (open->op_claim_type) {
case NFS4_OPEN_CLAIM_NULL:
case NFS4_OPEN_CLAIM_DELEGATE_PREV:
READ_BUF(4);
- READ32(open->op_fname.len);
+ open->op_fname.len = be32_to_cpup(p++);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
@@ -917,14 +915,14 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
READ_BUF(4);
- READ32(open->op_delegate_type);
+ open->op_delegate_type = be32_to_cpup(p++);
break;
case NFS4_OPEN_CLAIM_DELEGATE_CUR:
status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid);
if (status)
return status;
READ_BUF(4);
- READ32(open->op_fname.len);
+ open->op_fname.len = be32_to_cpup(p++);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
@@ -962,7 +960,7 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con
if (status)
return status;
READ_BUF(4);
- READ32(open_conf->oc_seqid);
+ open_conf->oc_seqid = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -976,7 +974,7 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d
if (status)
return status;
READ_BUF(4);
- READ32(open_down->od_seqid);
+ open_down->od_seqid = be32_to_cpup(p++);
status = nfsd4_decode_share_access(argp, &open_down->od_share_access,
&open_down->od_deleg_want, NULL);
if (status)
@@ -993,7 +991,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh)
DECODE_HEAD;
READ_BUF(4);
- READ32(putfh->pf_fhlen);
+ putfh->pf_fhlen = be32_to_cpup(p++);
if (putfh->pf_fhlen > NFS4_FHSIZE)
goto xdr_error;
READ_BUF(putfh->pf_fhlen);
@@ -1019,8 +1017,8 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read)
if (status)
return status;
READ_BUF(12);
- READ64(read->rd_offset);
- READ32(read->rd_length);
+ p = xdr_decode_hyper(p, &read->rd_offset);
+ read->rd_length = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -1031,10 +1029,10 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read
DECODE_HEAD;
READ_BUF(24);
- READ64(readdir->rd_cookie);
+ p = xdr_decode_hyper(p, &readdir->rd_cookie);
COPYMEM(readdir->rd_verf.data, sizeof(readdir->rd_verf.data));
- READ32(readdir->rd_dircount); /* just in case you needed a useless field... */
- READ32(readdir->rd_maxcount);
+ readdir->rd_dircount = be32_to_cpup(p++);
+ readdir->rd_maxcount = be32_to_cpup(p++);
if ((status = nfsd4_decode_bitmap(argp, readdir->rd_bmval)))
goto out;
@@ -1047,7 +1045,7 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove
DECODE_HEAD;
READ_BUF(4);
- READ32(remove->rm_namelen);
+ remove->rm_namelen = be32_to_cpup(p++);
READ_BUF(remove->rm_namelen);
SAVEMEM(remove->rm_name, remove->rm_namelen);
if ((status = check_filename(remove->rm_name, remove->rm_namelen)))
@@ -1062,10 +1060,10 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
DECODE_HEAD;
READ_BUF(4);
- READ32(rename->rn_snamelen);
+ rename->rn_snamelen = be32_to_cpup(p++);
READ_BUF(rename->rn_snamelen + 4);
SAVEMEM(rename->rn_sname, rename->rn_snamelen);
- READ32(rename->rn_tnamelen);
+ rename->rn_tnamelen = be32_to_cpup(p++);
READ_BUF(rename->rn_tnamelen);
SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
if ((status = check_filename(rename->rn_sname, rename->rn_snamelen)))
@@ -1097,7 +1095,7 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
DECODE_HEAD;
READ_BUF(4);
- READ32(secinfo->si_namelen);
+ secinfo->si_namelen = be32_to_cpup(p++);
READ_BUF(secinfo->si_namelen);
SAVEMEM(secinfo->si_name, secinfo->si_namelen);
status = check_filename(secinfo->si_name, secinfo->si_namelen);
@@ -1113,7 +1111,7 @@ nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,
DECODE_HEAD;
READ_BUF(4);
- READ32(sin->sin_style);
+ sin->sin_style = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -1144,16 +1142,16 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
if (status)
return nfserr_bad_xdr;
READ_BUF(8);
- READ32(setclientid->se_callback_prog);
- READ32(setclientid->se_callback_netid_len);
+ setclientid->se_callback_prog = be32_to_cpup(p++);
+ setclientid->se_callback_netid_len = be32_to_cpup(p++);
READ_BUF(setclientid->se_callback_netid_len + 4);
SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
- READ32(setclientid->se_callback_addr_len);
+ setclientid->se_callback_addr_len = be32_to_cpup(p++);
READ_BUF(setclientid->se_callback_addr_len + 4);
SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
- READ32(setclientid->se_callback_ident);
+ setclientid->se_callback_ident = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -1186,7 +1184,7 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify
* nfsd4_proc_verify */
READ_BUF(4);
- READ32(verify->ve_attrlen);
+ verify->ve_attrlen = be32_to_cpup(p++);
READ_BUF(verify->ve_attrlen);
SAVEMEM(verify->ve_attrval, verify->ve_attrlen);
@@ -1204,11 +1202,11 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
if (status)
return status;
READ_BUF(16);
- READ64(write->wr_offset);
- READ32(write->wr_stable_how);
+ p = xdr_decode_hyper(p, &write->wr_offset);
+ write->wr_stable_how = be32_to_cpup(p++);
if (write->wr_stable_how > 2)
goto xdr_error;
- READ32(write->wr_buflen);
+ write->wr_buflen = be32_to_cpup(p++);
/* Sorry .. no magic macros for this.. *
* READ_BUF(write->wr_buflen);
@@ -1254,7 +1252,7 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel
READ_BUF(12);
COPYMEM(&rlockowner->rl_clientid, sizeof(clientid_t));
- READ32(rlockowner->rl_owner.len);
+ rlockowner->rl_owner.len = be32_to_cpup(p++);
READ_BUF(rlockowner->rl_owner.len);
READMEM(rlockowner->rl_owner.data, rlockowner->rl_owner.len);
@@ -1278,63 +1276,63 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
return nfserr_bad_xdr;
READ_BUF(4);
- READ32(exid->flags);
+ exid->flags = be32_to_cpup(p++);
/* Ignore state_protect4_a */
READ_BUF(4);
- READ32(exid->spa_how);
+ exid->spa_how = be32_to_cpup(p++);
switch (exid->spa_how) {
case SP4_NONE:
break;
case SP4_MACH_CRED:
/* spo_must_enforce */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy * 4);
p += dummy;
/* spo_must_allow */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy * 4);
p += dummy;
break;
case SP4_SSV:
/* ssp_ops */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy * 4);
p += dummy;
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy * 4);
p += dummy;
/* ssp_hash_algs<> */
READ_BUF(4);
- READ32(tmp);
+ tmp = be32_to_cpup(p++);
while (tmp--) {
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
}
/* ssp_encr_algs<> */
READ_BUF(4);
- READ32(tmp);
+ tmp = be32_to_cpup(p++);
while (tmp--) {
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
}
/* ssp_window and ssp_num_gss_handles */
READ_BUF(8);
- READ32(dummy);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
+ dummy = be32_to_cpup(p++);
break;
default:
goto xdr_error;
@@ -1342,7 +1340,7 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
/* Ignore Implementation ID */
READ_BUF(4); /* nfs_impl_id4 array length */
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
if (dummy > 1)
goto xdr_error;
@@ -1350,13 +1348,13 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
if (dummy == 1) {
/* nii_domain */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
/* nii_name */
READ_BUF(4);
- READ32(dummy);
+ dummy = be32_to_cpup(p++);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
@@ -1376,21 +1374,21 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
READ_BUF(16);
COPYMEM(&sess->clientid, 8);
- READ32(sess->seqid);
- READ32(sess->flags);
+ sess->seqid = be32_to_cpup(p++);
+ sess->flags = be32_to_cpup(p++);
/* Fore channel attrs */
READ_BUF(28);
- READ32(dummy); /* headerpadsz is always 0 */
- READ32(sess->fore_channel.maxreq_sz);
- READ32(sess->fore_channel.maxresp_sz);
- READ32(sess->fore_channel.maxresp_cached);
- READ32(sess->fore_channel.maxops);
- READ32(sess->fore_channel.maxreqs);
- READ32(sess->fore_channel.nr_rdma_attrs);
+ dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */
+ sess->fore_channel.maxreq_sz = be32_to_cpup(p++);
+ sess->fore_channel.maxresp_sz = be32_to_cpup(p++);
+ sess->fore_channel.maxresp_cached = be32_to_cpup(p++);
+ sess->fore_channel.maxops = be32_to_cpup(p++);
+ sess->fore_channel.maxreqs = be32_to_cpup(p++);
+ sess->fore_channel.nr_rdma_attrs = be32_to_cpup(p++);
if (sess->fore_channel.nr_rdma_attrs == 1) {
READ_BUF(4);
- READ32(sess->fore_channel.rdma_attrs);
+ sess->fore_channel.rdma_attrs = be32_to_cpup(p++);
} else if (sess->fore_channel.nr_rdma_attrs > 1) {
dprintk("Too many fore channel attr bitmaps!\n");
goto xdr_error;
@@ -1398,23 +1396,23 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
/* Back channel attrs */
READ_BUF(28);
- READ32(dummy); /* headerpadsz is always 0 */
- READ32(sess->back_channel.maxreq_sz);
- READ32(sess->back_channel.maxresp_sz);
- READ32(sess->back_channel.maxresp_cached);
- READ32(sess->back_channel.maxops);
- READ32(sess->back_channel.maxreqs);
- READ32(sess->back_channel.nr_rdma_attrs);
+ dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */
+ sess->back_channel.maxreq_sz = be32_to_cpup(p++);
+ sess->back_channel.maxresp_sz = be32_to_cpup(p++);
+ sess->back_channel.maxresp_cached = be32_to_cpup(p++);
+ sess->back_channel.maxops = be32_to_cpup(p++);
+ sess->back_channel.maxreqs = be32_to_cpup(p++);
+ sess->back_channel.nr_rdma_attrs = be32_to_cpup(p++);
if (sess->back_channel.nr_rdma_attrs == 1) {
READ_BUF(4);
- READ32(sess->back_channel.rdma_attrs);
+ sess->back_channel.rdma_attrs = be32_to_cpup(p++);
} else if (sess->back_channel.nr_rdma_attrs > 1) {
dprintk("Too many back channel attr bitmaps!\n");
goto xdr_error;
}
READ_BUF(4);
- READ32(sess->callback_prog);
+ sess->callback_prog = be32_to_cpup(p++);
nfsd4_decode_cb_sec(argp, &sess->cb_sec);
DECODE_TAIL;
}
@@ -1437,7 +1435,7 @@ nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp,
DECODE_HEAD;
READ_BUF(sizeof(stateid_t));
- READ32(free_stateid->fr_stateid.si_generation);
+ free_stateid->fr_stateid.si_generation = be32_to_cpup(p++);
COPYMEM(&free_stateid->fr_stateid.si_opaque, sizeof(stateid_opaque_t));
DECODE_TAIL;
@@ -1451,10 +1449,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp,
READ_BUF(NFS4_MAX_SESSIONID_LEN + 16);
COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN);
- READ32(seq->seqid);
- READ32(seq->slotid);
- READ32(seq->maxslots);
- READ32(seq->cachethis);
+ seq->seqid = be32_to_cpup(p++);
+ seq->slotid = be32_to_cpup(p++);
+ seq->maxslots = be32_to_cpup(p++);
+ seq->cachethis = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -1511,7 +1509,7 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
DECODE_HEAD;
READ_BUF(4);
- READ32(rc->rca_one_fs);
+ rc->rca_one_fs = be32_to_cpup(p++);
DECODE_TAIL;
}
@@ -1605,47 +1603,25 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op)
return true;
}
-/*
- * Return a rough estimate of the maximum possible reply size. Note the
- * estimate includes rpc headers so is meant to be passed to
- * svc_reserve, not svc_reserve_auth.
- *
- * Also note the current compound encoding permits only one operation to
- * use pages beyond the first one, so the maximum possible length is the
- * maximum over these values, not the sum.
- */
-static int nfsd4_max_reply(u32 opnum)
-{
- switch (opnum) {
- case OP_READLINK:
- case OP_READDIR:
- /*
- * Both of these ops take a single page for data and put
- * the head and tail in another page:
- */
- return 2 * PAGE_SIZE;
- case OP_READ:
- return INT_MAX;
- default:
- return PAGE_SIZE;
- }
-}
-
static __be32
nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
{
DECODE_HEAD;
struct nfsd4_op *op;
bool cachethis = false;
- int max_reply = PAGE_SIZE;
+ int auth_slack= argp->rqstp->rq_auth_slack;
+ int max_reply = auth_slack + 8; /* opcnt, status */
+ int readcount = 0;
+ int readbytes = 0;
int i;
READ_BUF(4);
- READ32(argp->taglen);
+ argp->taglen = be32_to_cpup(p++);
READ_BUF(argp->taglen + 8);
SAVEMEM(argp->tag, argp->taglen);
- READ32(argp->minorversion);
- READ32(argp->opcnt);
+ argp->minorversion = be32_to_cpup(p++);
+ argp->opcnt = be32_to_cpup(p++);
+ max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2);
if (argp->taglen > NFSD4_MAX_TAGLEN)
goto xdr_error;
@@ -1669,7 +1645,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
op->replay = NULL;
READ_BUF(4);
- READ32(op->opnum);
+ op->opnum = be32_to_cpup(p++);
if (nfsd4_opnum_in_range(argp, op))
op->status = nfsd4_dec_ops[op->opnum](argp, &op->u);
@@ -1677,97 +1653,82 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
op->opnum = OP_ILLEGAL;
op->status = nfserr_op_illegal;
}
-
- if (op->status) {
- argp->opcnt = i+1;
- break;
- }
/*
* We'll try to cache the result in the DRC if any one
* op in the compound wants to be cached:
*/
cachethis |= nfsd4_cache_this_op(op);
- max_reply = max(max_reply, nfsd4_max_reply(op->opnum));
+ if (op->opnum == OP_READ) {
+ readcount++;
+ readbytes += nfsd4_max_reply(argp->rqstp, op);
+ } else
+ max_reply += nfsd4_max_reply(argp->rqstp, op);
+
+ if (op->status) {
+ argp->opcnt = i+1;
+ break;
+ }
}
/* Sessions make the DRC unnecessary: */
if (argp->minorversion)
cachethis = false;
- if (max_reply != INT_MAX)
- svc_reserve(argp->rqstp, max_reply);
+ svc_reserve(argp->rqstp, max_reply + readbytes);
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
- DECODE_TAIL;
-}
-
-#define WRITE32(n) *p++ = htonl(n)
-#define WRITE64(n) do { \
- *p++ = htonl((u32)((n) >> 32)); \
- *p++ = htonl((u32)(n)); \
-} while (0)
-#define WRITEMEM(ptr,nbytes) do { if (nbytes > 0) { \
- *(p + XDR_QUADLEN(nbytes) -1) = 0; \
- memcpy(p, ptr, nbytes); \
- p += XDR_QUADLEN(nbytes); \
-}} while (0)
-
-static void write32(__be32 **p, u32 n)
-{
- *(*p)++ = htonl(n);
-}
+ if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
+ argp->rqstp->rq_splice_ok = false;
-static void write64(__be32 **p, u64 n)
-{
- write32(p, (n >> 32));
- write32(p, (u32)n);
+ DECODE_TAIL;
}
-static void write_change(__be32 **p, struct kstat *stat, struct inode *inode)
+static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode)
{
if (IS_I_VERSION(inode)) {
- write64(p, inode->i_version);
+ p = xdr_encode_hyper(p, inode->i_version);
} else {
- write32(p, stat->ctime.tv_sec);
- write32(p, stat->ctime.tv_nsec);
+ *p++ = cpu_to_be32(stat->ctime.tv_sec);
+ *p++ = cpu_to_be32(stat->ctime.tv_nsec);
}
+ return p;
}
-static void write_cinfo(__be32 **p, struct nfsd4_change_info *c)
+static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c)
{
- write32(p, c->atomic);
+ *p++ = cpu_to_be32(c->atomic);
if (c->change_supported) {
- write64(p, c->before_change);
- write64(p, c->after_change);
+ p = xdr_encode_hyper(p, c->before_change);
+ p = xdr_encode_hyper(p, c->after_change);
} else {
- write32(p, c->before_ctime_sec);
- write32(p, c->before_ctime_nsec);
- write32(p, c->after_ctime_sec);
- write32(p, c->after_ctime_nsec);
+ *p++ = cpu_to_be32(c->before_ctime_sec);
+ *p++ = cpu_to_be32(c->before_ctime_nsec);
+ *p++ = cpu_to_be32(c->after_ctime_sec);
+ *p++ = cpu_to_be32(c->after_ctime_nsec);
}
+ return p;
}
-#define RESERVE_SPACE(nbytes) do { \
- p = resp->p; \
- BUG_ON(p + XDR_QUADLEN(nbytes) > resp->end); \
-} while (0)
-#define ADJUST_ARGS() resp->p = p
-
/* Encode as an array of strings the string given with components
* separated @sep, escaped with esc_enter and esc_exit.
*/
-static __be32 nfsd4_encode_components_esc(char sep, char *components,
- __be32 **pp, int *buflen,
- char esc_enter, char esc_exit)
+static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep,
+ char *components, char esc_enter,
+ char esc_exit)
{
- __be32 *p = *pp;
- __be32 *countp = p;
+ __be32 *p;
+ __be32 pathlen;
+ int pathlen_offset;
int strlen, count=0;
char *str, *end, *next;
dprintk("nfsd4_encode_components(%s)\n", components);
- if ((*buflen -= 4) < 0)
+
+ pathlen_offset = xdr->buf->len;
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
return nfserr_resource;
- WRITE32(0); /* We will fill this in with @count later */
+ p++; /* We will fill this in with @count later */
+
end = str = components;
while (*end) {
bool found_esc = false;
@@ -1789,59 +1750,57 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components,
strlen = end - str;
if (strlen) {
- if ((*buflen -= ((XDR_QUADLEN(strlen) << 2) + 4)) < 0)
+ p = xdr_reserve_space(xdr, strlen + 4);
+ if (!p)
return nfserr_resource;
- WRITE32(strlen);
- WRITEMEM(str, strlen);
+ p = xdr_encode_opaque(p, str, strlen);
count++;
}
else
end++;
str = end;
}
- *pp = p;
- p = countp;
- WRITE32(count);
+ pathlen = htonl(xdr->buf->len - pathlen_offset);
+ write_bytes_to_xdr_buf(xdr->buf, pathlen_offset, &pathlen, 4);
return 0;
}
/* Encode as an array of strings the string given with components
* separated @sep.
*/
-static __be32 nfsd4_encode_components(char sep, char *components,
- __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep,
+ char *components)
{
- return nfsd4_encode_components_esc(sep, components, pp, buflen, 0, 0);
+ return nfsd4_encode_components_esc(xdr, sep, components, 0, 0);
}
/*
* encode a location element of a fs_locations structure
*/
-static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
- __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr,
+ struct nfsd4_fs_location *location)
{
__be32 status;
- __be32 *p = *pp;
- status = nfsd4_encode_components_esc(':', location->hosts, &p, buflen,
+ status = nfsd4_encode_components_esc(xdr, ':', location->hosts,
'[', ']');
if (status)
return status;
- status = nfsd4_encode_components('/', location->path, &p, buflen);
+ status = nfsd4_encode_components(xdr, '/', location->path);
if (status)
return status;
- *pp = p;
return 0;
}
/*
* Encode a path in RFC3530 'pathname4' format
*/
-static __be32 nfsd4_encode_path(const struct path *root,
- const struct path *path, __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_path(struct xdr_stream *xdr,
+ const struct path *root,
+ const struct path *path)
{
struct path cur = *path;
- __be32 *p = *pp;
+ __be32 *p;
struct dentry **components = NULL;
unsigned int ncomponents = 0;
__be32 err = nfserr_jukebox;
@@ -1872,11 +1831,11 @@ static __be32 nfsd4_encode_path(const struct path *root,
components[ncomponents++] = cur.dentry;
cur.dentry = dget_parent(cur.dentry);
}
-
- *buflen -= 4;
- if (*buflen < 0)
+ err = nfserr_resource;
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_free;
- WRITE32(ncomponents);
+ *p++ = cpu_to_be32(ncomponents);
while (ncomponents) {
struct dentry *dentry = components[ncomponents - 1];
@@ -1884,20 +1843,18 @@ static __be32 nfsd4_encode_path(const struct path *root,
spin_lock(&dentry->d_lock);
len = dentry->d_name.len;
- *buflen -= 4 + (XDR_QUADLEN(len) << 2);
- if (*buflen < 0) {
+ p = xdr_reserve_space(xdr, len + 4);
+ if (!p) {
spin_unlock(&dentry->d_lock);
goto out_free;
}
- WRITE32(len);
- WRITEMEM(dentry->d_name.name, len);
+ p = xdr_encode_opaque(p, dentry->d_name.name, len);
dprintk("/%s", dentry->d_name.name);
spin_unlock(&dentry->d_lock);
dput(dentry);
ncomponents--;
}
- *pp = p;
err = 0;
out_free:
dprintk(")\n");
@@ -1908,8 +1865,8 @@ out_free:
return err;
}
-static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp,
- const struct path *path, __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_fsloc_fsroot(struct xdr_stream *xdr,
+ struct svc_rqst *rqstp, const struct path *path)
{
struct svc_export *exp_ps;
__be32 res;
@@ -1917,7 +1874,7 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp,
exp_ps = rqst_find_fsidzero_export(rqstp);
if (IS_ERR(exp_ps))
return nfserrno(PTR_ERR(exp_ps));
- res = nfsd4_encode_path(&exp_ps->ex_path, path, pp, buflen);
+ res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path);
exp_put(exp_ps);
return res;
}
@@ -1925,28 +1882,26 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp,
/*
* encode a fs_locations structure
*/
-static __be32 nfsd4_encode_fs_locations(struct svc_rqst *rqstp,
- struct svc_export *exp,
- __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_fs_locations(struct xdr_stream *xdr,
+ struct svc_rqst *rqstp, struct svc_export *exp)
{
__be32 status;
int i;
- __be32 *p = *pp;
+ __be32 *p;
struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs;
- status = nfsd4_encode_fsloc_fsroot(rqstp, &exp->ex_path, &p, buflen);
+ status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path);
if (status)
return status;
- if ((*buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
return nfserr_resource;
- WRITE32(fslocs->locations_count);
+ *p++ = cpu_to_be32(fslocs->locations_count);
for (i=0; i<fslocs->locations_count; i++) {
- status = nfsd4_encode_fs_location4(&fslocs->locations[i],
- &p, buflen);
+ status = nfsd4_encode_fs_location4(xdr, &fslocs->locations[i]);
if (status)
return status;
}
- *pp = p;
return 0;
}
@@ -1965,15 +1920,15 @@ static u32 nfs4_file_type(umode_t mode)
}
static inline __be32
-nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
- __be32 **p, int *buflen)
+nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+ struct nfs4_ace *ace)
{
if (ace->whotype != NFS4_ACL_WHO_NAMED)
- return nfs4_acl_write_who(ace->whotype, p, buflen);
+ return nfs4_acl_write_who(xdr, ace->whotype);
else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
- return nfsd4_encode_group(rqstp, ace->who_gid, p, buflen);
+ return nfsd4_encode_group(xdr, rqstp, ace->who_gid);
else
- return nfsd4_encode_user(rqstp, ace->who_uid, p, buflen);
+ return nfsd4_encode_user(xdr, rqstp, ace->who_uid);
}
#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
@@ -1982,31 +1937,28 @@ nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
static inline __be32
-nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen)
+nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+ void *context, int len)
{
- __be32 *p = *pp;
+ __be32 *p;
- if (*buflen < ((XDR_QUADLEN(len) << 2) + 4 + 4 + 4))
+ p = xdr_reserve_space(xdr, len + 4 + 4 + 4);
+ if (!p)
return nfserr_resource;
/*
* For now we use a 0 here to indicate the null translation; in
* the future we may place a call to translation code here.
*/
- if ((*buflen -= 8) < 0)
- return nfserr_resource;
-
- WRITE32(0); /* lfs */
- WRITE32(0); /* pi */
+ *p++ = cpu_to_be32(0); /* lfs */
+ *p++ = cpu_to_be32(0); /* pi */
p = xdr_encode_opaque(p, context, len);
- *buflen -= (XDR_QUADLEN(len) << 2) + 4;
-
- *pp = p;
return 0;
}
#else
static inline __be32
-nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen)
+nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+ void *context, int len)
{ return 0; }
#endif
@@ -2045,12 +1997,11 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
/*
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
- *
- * countp is the buffer size in _words_
*/
-__be32
-nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 **buffer, int count, u32 *bmval,
+static __be32
+nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
+ struct svc_export *exp,
+ struct dentry *dentry, u32 *bmval,
struct svc_rqst *rqstp, int ignore_crossmnt)
{
u32 bmval0 = bmval[0];
@@ -2059,12 +2010,13 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
struct kstat stat;
struct svc_fh *tempfh = NULL;
struct kstatfs statfs;
- int buflen = count << 2;
- __be32 *attrlenp;
+ __be32 *p;
+ int starting_len = xdr->buf->len;
+ int attrlen_offset;
+ __be32 attrlen;
u32 dummy;
u64 dummy64;
u32 rdattr_err = 0;
- __be32 *p = *buffer;
__be32 status;
int err;
int aclsupport = 0;
@@ -2095,8 +2047,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
err = vfs_getattr(&path, &stat);
if (err)
goto out_nfserr;
- if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
- FATTR4_WORD0_MAXNAME)) ||
+ if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+ FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
(bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
FATTR4_WORD1_SPACE_TOTAL))) {
err = vfs_statfs(&path, &statfs);
@@ -2145,25 +2097,33 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
if (bmval2) {
- if ((buflen -= 16) < 0)
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
goto out_resource;
- WRITE32(3);
- WRITE32(bmval0);
- WRITE32(bmval1);
- WRITE32(bmval2);
+ *p++ = cpu_to_be32(3);
+ *p++ = cpu_to_be32(bmval0);
+ *p++ = cpu_to_be32(bmval1);
+ *p++ = cpu_to_be32(bmval2);
} else if (bmval1) {
- if ((buflen -= 12) < 0)
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
goto out_resource;
- WRITE32(2);
- WRITE32(bmval0);
- WRITE32(bmval1);
+ *p++ = cpu_to_be32(2);
+ *p++ = cpu_to_be32(bmval0);
+ *p++ = cpu_to_be32(bmval1);
} else {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE32(1);
- WRITE32(bmval0);
+ *p++ = cpu_to_be32(1);
+ *p++ = cpu_to_be32(bmval0);
}
- attrlenp = p++; /* to be backfilled later */
+
+ attrlen_offset = xdr->buf->len;
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ goto out_resource;
+ p++; /* to be backfilled later */
if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
u32 word0 = nfsd_suppattrs0(minorversion);
@@ -2175,296 +2135,343 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
if (!contextsupport)
word2 &= ~FATTR4_WORD2_SECURITY_LABEL;
if (!word2) {
- if ((buflen -= 12) < 0)
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
goto out_resource;
- WRITE32(2);
- WRITE32(word0);
- WRITE32(word1);
+ *p++ = cpu_to_be32(2);
+ *p++ = cpu_to_be32(word0);
+ *p++ = cpu_to_be32(word1);
} else {
- if ((buflen -= 16) < 0)
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
goto out_resource;
- WRITE32(3);
- WRITE32(word0);
- WRITE32(word1);
- WRITE32(word2);
+ *p++ = cpu_to_be32(3);
+ *p++ = cpu_to_be32(word0);
+ *p++ = cpu_to_be32(word1);
+ *p++ = cpu_to_be32(word2);
}
}
if (bmval0 & FATTR4_WORD0_TYPE) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
dummy = nfs4_file_type(stat.mode);
if (dummy == NF4BAD) {
status = nfserr_serverfault;
goto out;
}
- WRITE32(dummy);
+ *p++ = cpu_to_be32(dummy);
}
if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
if (exp->ex_flags & NFSEXP_NOSUBTREECHECK)
- WRITE32(NFS4_FH_PERSISTENT);
+ *p++ = cpu_to_be32(NFS4_FH_PERSISTENT);
else
- WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME);
+ *p++ = cpu_to_be32(NFS4_FH_PERSISTENT|
+ NFS4_FH_VOL_RENAME);
}
if (bmval0 & FATTR4_WORD0_CHANGE) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- write_change(&p, &stat, dentry->d_inode);
+ p = encode_change(p, &stat, dentry->d_inode);
}
if (bmval0 & FATTR4_WORD0_SIZE) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64(stat.size);
+ p = xdr_encode_hyper(p, stat.size);
}
if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval0 & FATTR4_WORD0_NAMED_ATTR) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(0);
+ *p++ = cpu_to_be32(0);
}
if (bmval0 & FATTR4_WORD0_FSID) {
- if ((buflen -= 16) < 0)
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
goto out_resource;
if (exp->ex_fslocs.migrated) {
- WRITE64(NFS4_REFERRAL_FSID_MAJOR);
- WRITE64(NFS4_REFERRAL_FSID_MINOR);
+ p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR);
+ p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR);
} else switch(fsid_source(fhp)) {
case FSIDSOURCE_FSID:
- WRITE64((u64)exp->ex_fsid);
- WRITE64((u64)0);
+ p = xdr_encode_hyper(p, (u64)exp->ex_fsid);
+ p = xdr_encode_hyper(p, (u64)0);
break;
case FSIDSOURCE_DEV:
- WRITE32(0);
- WRITE32(MAJOR(stat.dev));
- WRITE32(0);
- WRITE32(MINOR(stat.dev));
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(MAJOR(stat.dev));
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(MINOR(stat.dev));
break;
case FSIDSOURCE_UUID:
- WRITEMEM(exp->ex_uuid, 16);
+ p = xdr_encode_opaque_fixed(p, exp->ex_uuid,
+ EX_UUID_LEN);
break;
}
}
if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(0);
+ *p++ = cpu_to_be32(0);
}
if (bmval0 & FATTR4_WORD0_LEASE_TIME) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(nn->nfsd4_lease);
+ *p++ = cpu_to_be32(nn->nfsd4_lease);
}
if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(rdattr_err);
+ *p++ = cpu_to_be32(rdattr_err);
}
if (bmval0 & FATTR4_WORD0_ACL) {
struct nfs4_ace *ace;
if (acl == NULL) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(0);
+ *p++ = cpu_to_be32(0);
goto out_acl;
}
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(acl->naces);
+ *p++ = cpu_to_be32(acl->naces);
for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
- if ((buflen -= 4*3) < 0)
+ p = xdr_reserve_space(xdr, 4*3);
+ if (!p)
goto out_resource;
- WRITE32(ace->type);
- WRITE32(ace->flag);
- WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL);
- status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen);
+ *p++ = cpu_to_be32(ace->type);
+ *p++ = cpu_to_be32(ace->flag);
+ *p++ = cpu_to_be32(ace->access_mask &
+ NFS4_ACE_MASK_ALL);
+ status = nfsd4_encode_aclname(xdr, rqstp, ace);
if (status)
goto out;
}
}
out_acl:
if (bmval0 & FATTR4_WORD0_ACLSUPPORT) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(aclsupport ?
+ *p++ = cpu_to_be32(aclsupport ?
ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0);
}
if (bmval0 & FATTR4_WORD0_CANSETTIME) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(0);
+ *p++ = cpu_to_be32(0);
}
if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval0 & FATTR4_WORD0_FILEHANDLE) {
- buflen -= (XDR_QUADLEN(fhp->fh_handle.fh_size) << 2) + 4;
- if (buflen < 0)
+ p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4);
+ if (!p)
goto out_resource;
- WRITE32(fhp->fh_handle.fh_size);
- WRITEMEM(&fhp->fh_handle.fh_base, fhp->fh_handle.fh_size);
+ p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base,
+ fhp->fh_handle.fh_size);
}
if (bmval0 & FATTR4_WORD0_FILEID) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64(stat.ino);
+ p = xdr_encode_hyper(p, stat.ino);
}
if (bmval0 & FATTR4_WORD0_FILES_AVAIL) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64((u64) statfs.f_ffree);
+ p = xdr_encode_hyper(p, (u64) statfs.f_ffree);
}
if (bmval0 & FATTR4_WORD0_FILES_FREE) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64((u64) statfs.f_ffree);
+ p = xdr_encode_hyper(p, (u64) statfs.f_ffree);
}
if (bmval0 & FATTR4_WORD0_FILES_TOTAL) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64((u64) statfs.f_files);
+ p = xdr_encode_hyper(p, (u64) statfs.f_files);
}
if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
- status = nfsd4_encode_fs_locations(rqstp, exp, &p, &buflen);
+ status = nfsd4_encode_fs_locations(xdr, rqstp, exp);
if (status)
goto out;
}
if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval0 & FATTR4_WORD0_MAXFILESIZE) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64(exp->ex_path.mnt->mnt_sb->s_maxbytes);
+ p = xdr_encode_hyper(p, exp->ex_path.mnt->mnt_sb->s_maxbytes);
}
if (bmval0 & FATTR4_WORD0_MAXLINK) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(255);
+ *p++ = cpu_to_be32(255);
}
if (bmval0 & FATTR4_WORD0_MAXNAME) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(statfs.f_namelen);
+ *p++ = cpu_to_be32(statfs.f_namelen);
}
if (bmval0 & FATTR4_WORD0_MAXREAD) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64((u64) svc_max_payload(rqstp));
+ p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp));
}
if (bmval0 & FATTR4_WORD0_MAXWRITE) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE64((u64) svc_max_payload(rqstp));
+ p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp));
}
if (bmval1 & FATTR4_WORD1_MODE) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(stat.mode & S_IALLUGO);
+ *p++ = cpu_to_be32(stat.mode & S_IALLUGO);
}
if (bmval1 & FATTR4_WORD1_NO_TRUNC) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(1);
+ *p++ = cpu_to_be32(1);
}
if (bmval1 & FATTR4_WORD1_NUMLINKS) {
- if ((buflen -= 4) < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto out_resource;
- WRITE32(stat.nlink);
+ *p++ = cpu_to_be32(stat.nlink);
}
if (bmval1 & FATTR4_WORD1_OWNER) {
- status = nfsd4_encode_user(rqstp, stat.uid, &p, &buflen);
+ status = nfsd4_encode_user(xdr, rqstp, stat.uid);
if (status)
goto out;
}
if (bmval1 & FATTR4_WORD1_OWNER_GROUP) {
- status = nfsd4_encode_group(rqstp, stat.gid, &p, &buflen);
+ status = nfsd4_encode_group(xdr, rqstp, stat.gid);
if (status)
goto out;
}
if (bmval1 & FATTR4_WORD1_RAWDEV) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
- WRITE32((u32) MAJOR(stat.rdev));
- WRITE32((u32) MINOR(stat.rdev));
+ *p++ = cpu_to_be32((u32) MAJOR(stat.rdev));
+ *p++ = cpu_to_be32((u32) MINOR(stat.rdev));
}
if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize;
- WRITE64(dummy64);
+ p = xdr_encode_hyper(p, dummy64);
}
if (bmval1 & FATTR4_WORD1_SPACE_FREE) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize;
- WRITE64(dummy64);
+ p = xdr_encode_hyper(p, dummy64);
}
if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize;
- WRITE64(dummy64);
+ p = xdr_encode_hyper(p, dummy64);
}
if (bmval1 & FATTR4_WORD1_SPACE_USED) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
dummy64 = (u64)stat.blocks << 9;
- WRITE64(dummy64);
+ p = xdr_encode_hyper(p, dummy64);
}
if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
- if ((buflen -= 12) < 0)
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
goto out_resource;
- WRITE64((s64)stat.atime.tv_sec);
- WRITE32(stat.atime.tv_nsec);
+ p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec);
+ *p++ = cpu_to_be32(stat.atime.tv_nsec);
}
if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
- if ((buflen -= 12) < 0)
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
goto out_resource;
- WRITE32(0);
- WRITE32(1);
- WRITE32(0);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(1);
+ *p++ = cpu_to_be32(0);
}
if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
- if ((buflen -= 12) < 0)
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
goto out_resource;
- WRITE64((s64)stat.ctime.tv_sec);
- WRITE32(stat.ctime.tv_nsec);
+ p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec);
+ *p++ = cpu_to_be32(stat.ctime.tv_nsec);
}
if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
- if ((buflen -= 12) < 0)
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
goto out_resource;
- WRITE64((s64)stat.mtime.tv_sec);
- WRITE32(stat.mtime.tv_nsec);
+ p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec);
+ *p++ = cpu_to_be32(stat.mtime.tv_nsec);
}
if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
- if ((buflen -= 8) < 0)
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
goto out_resource;
/*
* Get parent's attributes if not ignoring crossmount
@@ -2473,25 +2480,26 @@ out_acl:
if (ignore_crossmnt == 0 &&
dentry == exp->ex_path.mnt->mnt_root)
get_parent_attributes(exp, &stat);
- WRITE64(stat.ino);
+ p = xdr_encode_hyper(p, stat.ino);
}
if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
- status = nfsd4_encode_security_label(rqstp, context,
- contextlen, &p, &buflen);
+ status = nfsd4_encode_security_label(xdr, rqstp, context,
+ contextlen);
if (status)
goto out;
}
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
- if ((buflen -= 16) < 0)
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
goto out_resource;
- WRITE32(3);
- WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
- WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
- WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD2);
+ *p++ = cpu_to_be32(3);
+ *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
+ *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
+ *p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD2);
}
- *attrlenp = htonl((char *)p - (char *)attrlenp - 4);
- *buffer = p;
+ attrlen = htonl(xdr->buf->len - attrlen_offset - 4);
+ write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4);
status = nfs_ok;
out:
@@ -2504,6 +2512,8 @@ out:
fh_put(tempfh);
kfree(tempfh);
}
+ if (status)
+ xdr_truncate_encode(xdr, starting_len);
return status;
out_nfserr:
status = nfserrno(err);
@@ -2513,6 +2523,37 @@ out_resource:
goto out;
}
+static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr,
+ struct xdr_buf *buf, __be32 *p, int bytes)
+{
+ xdr->scratch.iov_len = 0;
+ memset(buf, 0, sizeof(struct xdr_buf));
+ buf->head[0].iov_base = p;
+ buf->head[0].iov_len = 0;
+ buf->len = 0;
+ xdr->buf = buf;
+ xdr->iov = buf->head;
+ xdr->p = p;
+ xdr->end = (void *)p + bytes;
+ buf->buflen = bytes;
+}
+
+__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
+ struct svc_fh *fhp, struct svc_export *exp,
+ struct dentry *dentry, u32 *bmval,
+ struct svc_rqst *rqstp, int ignore_crossmnt)
+{
+ struct xdr_buf dummy;
+ struct xdr_stream xdr;
+ __be32 ret;
+
+ svcxdr_init_encode_from_buffer(&xdr, &dummy, *p, words << 2);
+ ret = nfsd4_encode_fattr(&xdr, fhp, exp, dentry, bmval, rqstp,
+ ignore_crossmnt);
+ *p = xdr.p;
+ return ret;
+}
+
static inline int attributes_need_mount(u32 *bmval)
{
if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME))
@@ -2523,8 +2564,8 @@ static inline int attributes_need_mount(u32 *bmval)
}
static __be32
-nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
- const char *name, int namlen, __be32 **p, int buflen)
+nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd,
+ const char *name, int namlen)
{
struct svc_export *exp = cd->rd_fhp->fh_export;
struct dentry *dentry;
@@ -2576,7 +2617,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
}
out_encode:
- nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval,
+ nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval,
cd->rd_rqstp, ignore_crossmnt);
out_put:
dput(dentry);
@@ -2585,9 +2626,12 @@ out_put:
}
static __be32 *
-nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr)
+nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr)
{
- if (buflen < 6)
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, 6);
+ if (!p)
return NULL;
*p++ = htonl(2);
*p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */
@@ -2604,10 +2648,13 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
{
struct readdir_cd *ccd = ccdv;
struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common);
- int buflen;
- __be32 *p = cd->buffer;
- __be32 *cookiep;
+ struct xdr_stream *xdr = cd->xdr;
+ int start_offset = xdr->buf->len;
+ int cookie_offset;
+ int entry_bytes;
__be32 nfserr = nfserr_toosmall;
+ __be64 wire_offset;
+ __be32 *p;
/* In nfsv4, "." and ".." never make it onto the wire.. */
if (name && isdotent(name, namlen)) {
@@ -2615,19 +2662,24 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
return 0;
}
- if (cd->offset)
- xdr_encode_hyper(cd->offset, (u64) offset);
+ if (cd->cookie_offset) {
+ wire_offset = cpu_to_be64(offset);
+ write_bytes_to_xdr_buf(xdr->buf, cd->cookie_offset,
+ &wire_offset, 8);
+ }
- buflen = cd->buflen - 4 - XDR_QUADLEN(namlen);
- if (buflen < 0)
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
goto fail;
-
*p++ = xdr_one; /* mark entry present */
- cookiep = p;
+ cookie_offset = xdr->buf->len;
+ p = xdr_reserve_space(xdr, 3*4 + namlen);
+ if (!p)
+ goto fail;
p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */
p = xdr_encode_array(p, name, namlen); /* name length & name */
- nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, &p, buflen);
+ nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen);
switch (nfserr) {
case nfs_ok:
break;
@@ -2646,59 +2698,74 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
*/
if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR))
goto fail;
- p = nfsd4_encode_rdattr_error(p, buflen, nfserr);
+ p = nfsd4_encode_rdattr_error(xdr, nfserr);
if (p == NULL) {
nfserr = nfserr_toosmall;
goto fail;
}
}
- cd->buflen -= (p - cd->buffer);
- cd->buffer = p;
- cd->offset = cookiep;
+ nfserr = nfserr_toosmall;
+ entry_bytes = xdr->buf->len - start_offset;
+ if (entry_bytes > cd->rd_maxcount)
+ goto fail;
+ cd->rd_maxcount -= entry_bytes;
+ if (!cd->rd_dircount)
+ goto fail;
+ cd->rd_dircount--;
+ cd->cookie_offset = cookie_offset;
skip_entry:
cd->common.err = nfs_ok;
return 0;
fail:
+ xdr_truncate_encode(xdr, start_offset);
cd->common.err = nfserr;
return -EINVAL;
}
-static void
-nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid)
+static __be32
+nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid)
{
__be32 *p;
- RESERVE_SPACE(sizeof(stateid_t));
- WRITE32(sid->si_generation);
- WRITEMEM(&sid->si_opaque, sizeof(stateid_opaque_t));
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, sizeof(stateid_t));
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(sid->si_generation);
+ p = xdr_encode_opaque_fixed(p, &sid->si_opaque,
+ sizeof(stateid_opaque_t));
+ return 0;
}
static __be32
nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(8);
- WRITE32(access->ac_supported);
- WRITE32(access->ac_resp_access);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(access->ac_supported);
+ *p++ = cpu_to_be32(access->ac_resp_access);
}
return nfserr;
}
static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8);
- WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
- WRITE32(bcts->dir);
+ p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8);
+ if (!p)
+ return nfserr_resource;
+ p = xdr_encode_opaque_fixed(p, bcts->sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+ *p++ = cpu_to_be32(bcts->dir);
/* Sorry, we do not yet support RDMA over 4.1: */
- WRITE32(0);
- ADJUST_ARGS();
+ *p++ = cpu_to_be32(0);
}
return nfserr;
}
@@ -2706,8 +2773,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
static __be32
nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
{
+ struct xdr_stream *xdr = &resp->xdr;
+
if (!nfserr)
- nfsd4_encode_stateid(resp, &close->cl_stateid);
+ nfserr = nfsd4_encode_stateid(xdr, &close->cl_stateid);
return nfserr;
}
@@ -2716,12 +2785,15 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
static __be32
nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(NFS4_VERIFIER_SIZE);
- WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
+ if (!p)
+ return nfserr_resource;
+ p = xdr_encode_opaque_fixed(p, commit->co_verf.data,
+ NFS4_VERIFIER_SIZE);
}
return nfserr;
}
@@ -2729,15 +2801,17 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(32);
- write_cinfo(&p, &create->cr_cinfo);
- WRITE32(2);
- WRITE32(create->cr_bmval[0]);
- WRITE32(create->cr_bmval[1]);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 32);
+ if (!p)
+ return nfserr_resource;
+ p = encode_cinfo(p, &create->cr_cinfo);
+ *p++ = cpu_to_be32(2);
+ *p++ = cpu_to_be32(create->cr_bmval[0]);
+ *p++ = cpu_to_be32(create->cr_bmval[1]);
}
return nfserr;
}
@@ -2746,14 +2820,13 @@ static __be32
nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr)
{
struct svc_fh *fhp = getattr->ga_fhp;
- int buflen;
+ struct xdr_stream *xdr = &resp->xdr;
if (nfserr)
return nfserr;
- buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2);
- nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry,
- &resp->p, buflen, getattr->ga_bmval,
+ nfserr = nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry,
+ getattr->ga_bmval,
resp->rqstp, 0);
return nfserr;
}
@@ -2761,16 +2834,17 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
static __be32
nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp)
{
+ struct xdr_stream *xdr = &resp->xdr;
struct svc_fh *fhp = *fhpp;
unsigned int len;
__be32 *p;
if (!nfserr) {
len = fhp->fh_handle.fh_size;
- RESERVE_SPACE(len + 4);
- WRITE32(len);
- WRITEMEM(&fhp->fh_handle.fh_base, len);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, len + 4);
+ if (!p)
+ return nfserr_resource;
+ p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len);
}
return nfserr;
}
@@ -2779,52 +2853,69 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
* Including all fields other than the name, a LOCK4denied structure requires
* 8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes.
*/
-static void
-nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denied *ld)
+static __be32
+nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld)
{
struct xdr_netobj *conf = &ld->ld_owner;
__be32 *p;
- RESERVE_SPACE(32 + XDR_LEN(conf->len));
- WRITE64(ld->ld_start);
- WRITE64(ld->ld_length);
- WRITE32(ld->ld_type);
+again:
+ p = xdr_reserve_space(xdr, 32 + XDR_LEN(conf->len));
+ if (!p) {
+ /*
+ * Don't fail to return the result just because we can't
+ * return the conflicting open:
+ */
+ if (conf->len) {
+ conf->len = 0;
+ conf->data = NULL;
+ goto again;
+ }
+ return nfserr_resource;
+ }
+ p = xdr_encode_hyper(p, ld->ld_start);
+ p = xdr_encode_hyper(p, ld->ld_length);
+ *p++ = cpu_to_be32(ld->ld_type);
if (conf->len) {
- WRITEMEM(&ld->ld_clientid, 8);
- WRITE32(conf->len);
- WRITEMEM(conf->data, conf->len);
- kfree(conf->data);
+ p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8);
+ p = xdr_encode_opaque(p, conf->data, conf->len);
} else { /* non - nfsv4 lock in conflict, no clientid nor owner */
- WRITE64((u64)0); /* clientid */
- WRITE32(0); /* length of owner name */
+ p = xdr_encode_hyper(p, (u64)0); /* clientid */
+ *p++ = cpu_to_be32(0); /* length of owner name */
}
- ADJUST_ARGS();
+ return nfserr_denied;
}
static __be32
nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock)
{
+ struct xdr_stream *xdr = &resp->xdr;
+
if (!nfserr)
- nfsd4_encode_stateid(resp, &lock->lk_resp_stateid);
+ nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid);
else if (nfserr == nfserr_denied)
- nfsd4_encode_lock_denied(resp, &lock->lk_denied);
-
+ nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied);
+ kfree(lock->lk_denied.ld_owner.data);
return nfserr;
}
static __be32
nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt)
{
+ struct xdr_stream *xdr = &resp->xdr;
+
if (nfserr == nfserr_denied)
- nfsd4_encode_lock_denied(resp, &lockt->lt_denied);
+ nfsd4_encode_lock_denied(xdr, &lockt->lt_denied);
return nfserr;
}
static __be32
nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku)
{
+ struct xdr_stream *xdr = &resp->xdr;
+
if (!nfserr)
- nfsd4_encode_stateid(resp, &locku->lu_stateid);
+ nfserr = nfsd4_encode_stateid(xdr, &locku->lu_stateid);
return nfserr;
}
@@ -2833,12 +2924,14 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
static __be32
nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(20);
- write_cinfo(&p, &link->li_cinfo);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 20);
+ if (!p)
+ return nfserr_resource;
+ p = encode_cinfo(p, &link->li_cinfo);
}
return nfserr;
}
@@ -2847,72 +2940,86 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
static __be32
nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (nfserr)
goto out;
- nfsd4_encode_stateid(resp, &open->op_stateid);
- RESERVE_SPACE(40);
- write_cinfo(&p, &open->op_cinfo);
- WRITE32(open->op_rflags);
- WRITE32(2);
- WRITE32(open->op_bmval[0]);
- WRITE32(open->op_bmval[1]);
- WRITE32(open->op_delegate_type);
- ADJUST_ARGS();
+ nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid);
+ if (nfserr)
+ goto out;
+ p = xdr_reserve_space(xdr, 40);
+ if (!p)
+ return nfserr_resource;
+ p = encode_cinfo(p, &open->op_cinfo);
+ *p++ = cpu_to_be32(open->op_rflags);
+ *p++ = cpu_to_be32(2);
+ *p++ = cpu_to_be32(open->op_bmval[0]);
+ *p++ = cpu_to_be32(open->op_bmval[1]);
+ *p++ = cpu_to_be32(open->op_delegate_type);
switch (open->op_delegate_type) {
case NFS4_OPEN_DELEGATE_NONE:
break;
case NFS4_OPEN_DELEGATE_READ:
- nfsd4_encode_stateid(resp, &open->op_delegate_stateid);
- RESERVE_SPACE(20);
- WRITE32(open->op_recall);
+ nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid);
+ if (nfserr)
+ return nfserr;
+ p = xdr_reserve_space(xdr, 20);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(open->op_recall);
/*
* TODO: ACE's in delegations
*/
- WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
- WRITE32(0);
- WRITE32(0);
- WRITE32(0); /* XXX: is NULL principal ok? */
- ADJUST_ARGS();
+ *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */
break;
case NFS4_OPEN_DELEGATE_WRITE:
- nfsd4_encode_stateid(resp, &open->op_delegate_stateid);
- RESERVE_SPACE(32);
- WRITE32(0);
+ nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid);
+ if (nfserr)
+ return nfserr;
+ p = xdr_reserve_space(xdr, 32);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(0);
/*
* TODO: space_limit's in delegations
*/
- WRITE32(NFS4_LIMIT_SIZE);
- WRITE32(~(u32)0);
- WRITE32(~(u32)0);
+ *p++ = cpu_to_be32(NFS4_LIMIT_SIZE);
+ *p++ = cpu_to_be32(~(u32)0);
+ *p++ = cpu_to_be32(~(u32)0);
/*
* TODO: ACE's in delegations
*/
- WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
- WRITE32(0);
- WRITE32(0);
- WRITE32(0); /* XXX: is NULL principal ok? */
- ADJUST_ARGS();
+ *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */
break;
case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */
switch (open->op_why_no_deleg) {
case WND4_CONTENTION:
case WND4_RESOURCE:
- RESERVE_SPACE(8);
- WRITE32(open->op_why_no_deleg);
- WRITE32(0); /* deleg signaling not supported yet */
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(open->op_why_no_deleg);
+ /* deleg signaling not supported yet: */
+ *p++ = cpu_to_be32(0);
break;
default:
- RESERVE_SPACE(4);
- WRITE32(open->op_why_no_deleg);
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(open->op_why_no_deleg);
}
- ADJUST_ARGS();
break;
default:
BUG();
@@ -2925,8 +3032,10 @@ out:
static __be32
nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
{
+ struct xdr_stream *xdr = &resp->xdr;
+
if (!nfserr)
- nfsd4_encode_stateid(resp, &oc->oc_resp_stateid);
+ nfserr = nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid);
return nfserr;
}
@@ -2934,127 +3043,233 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct
static __be32
nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
{
+ struct xdr_stream *xdr = &resp->xdr;
+
if (!nfserr)
- nfsd4_encode_stateid(resp, &od->od_stateid);
+ nfserr = nfsd4_encode_stateid(xdr, &od->od_stateid);
return nfserr;
}
-static __be32
-nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
- struct nfsd4_read *read)
+static __be32 nfsd4_encode_splice_read(
+ struct nfsd4_compoundres *resp,
+ struct nfsd4_read *read,
+ struct file *file, unsigned long maxcount)
{
+ struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_buf *buf = xdr->buf;
u32 eof;
- int v;
- struct page *page;
- unsigned long maxcount;
- long len;
- __be32 *p;
+ int space_left;
+ __be32 nfserr;
+ __be32 *p = xdr->p - 2;
- if (nfserr)
- return nfserr;
- if (resp->xbuf->page_len)
+ /*
+ * Don't inline pages unless we know there's room for eof,
+ * count, and possible padding:
+ */
+ if (xdr->end - xdr->p < 3)
return nfserr_resource;
- RESERVE_SPACE(8); /* eof flag and byte count */
+ nfserr = nfsd_splice_read(read->rd_rqstp, file,
+ read->rd_offset, &maxcount);
+ if (nfserr) {
+ /*
+ * nfsd_splice_actor may have already messed with the
+ * page length; reset it so as not to confuse
+ * xdr_truncate_encode:
+ */
+ buf->page_len = 0;
+ return nfserr;
+ }
- maxcount = svc_max_payload(resp->rqstp);
- if (maxcount > read->rd_length)
- maxcount = read->rd_length;
+ eof = (read->rd_offset + maxcount >=
+ read->rd_fhp->fh_dentry->d_inode->i_size);
+
+ *(p++) = htonl(eof);
+ *(p++) = htonl(maxcount);
+
+ buf->page_len = maxcount;
+ buf->len += maxcount;
+ xdr->page_ptr += (maxcount + PAGE_SIZE - 1) / PAGE_SIZE;
+
+ /* Use rest of head for padding and remaining ops: */
+ buf->tail[0].iov_base = xdr->p;
+ buf->tail[0].iov_len = 0;
+ xdr->iov = buf->tail;
+ if (maxcount&3) {
+ int pad = 4 - (maxcount&3);
+
+ *(xdr->p++) = 0;
+
+ buf->tail[0].iov_base += maxcount&3;
+ buf->tail[0].iov_len = pad;
+ buf->len += pad;
+ }
+
+ space_left = min_t(int, (void *)xdr->end - (void *)xdr->p,
+ buf->buflen - buf->len);
+ buf->buflen = buf->len + space_left;
+ xdr->end = (__be32 *)((void *)xdr->end + space_left);
+
+ return 0;
+}
+
+static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
+ struct nfsd4_read *read,
+ struct file *file, unsigned long maxcount)
+{
+ struct xdr_stream *xdr = &resp->xdr;
+ u32 eof;
+ int v;
+ int starting_len = xdr->buf->len - 8;
+ long len;
+ int thislen;
+ __be32 nfserr;
+ __be32 tmp;
+ __be32 *p;
+ u32 zzz = 0;
+ int pad;
len = maxcount;
v = 0;
- while (len > 0) {
- page = *(resp->rqstp->rq_next_page);
- if (!page) { /* ran out of pages */
- maxcount -= len;
- break;
- }
- resp->rqstp->rq_vec[v].iov_base = page_address(page);
- resp->rqstp->rq_vec[v].iov_len =
- len < PAGE_SIZE ? len : PAGE_SIZE;
- resp->rqstp->rq_next_page++;
+
+ thislen = (void *)xdr->end - (void *)xdr->p;
+ if (len < thislen)
+ thislen = len;
+ p = xdr_reserve_space(xdr, (thislen+3)&~3);
+ WARN_ON_ONCE(!p);
+ resp->rqstp->rq_vec[v].iov_base = p;
+ resp->rqstp->rq_vec[v].iov_len = thislen;
+ v++;
+ len -= thislen;
+
+ while (len) {
+ thislen = min_t(long, len, PAGE_SIZE);
+ p = xdr_reserve_space(xdr, (thislen+3)&~3);
+ WARN_ON_ONCE(!p);
+ resp->rqstp->rq_vec[v].iov_base = p;
+ resp->rqstp->rq_vec[v].iov_len = thislen;
v++;
- len -= PAGE_SIZE;
+ len -= thislen;
}
read->rd_vlen = v;
- nfserr = nfsd_read_file(read->rd_rqstp, read->rd_fhp, read->rd_filp,
- read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen,
- &maxcount);
-
+ nfserr = nfsd_readv(file, read->rd_offset, resp->rqstp->rq_vec,
+ read->rd_vlen, &maxcount);
if (nfserr)
return nfserr;
+ xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
+
eof = (read->rd_offset + maxcount >=
read->rd_fhp->fh_dentry->d_inode->i_size);
- WRITE32(eof);
- WRITE32(maxcount);
- ADJUST_ARGS();
- resp->xbuf->head[0].iov_len = (char*)p
- - (char*)resp->xbuf->head[0].iov_base;
- resp->xbuf->page_len = maxcount;
+ tmp = htonl(eof);
+ write_bytes_to_xdr_buf(xdr->buf, starting_len , &tmp, 4);
+ tmp = htonl(maxcount);
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
- /* Use rest of head for padding and remaining ops: */
- resp->xbuf->tail[0].iov_base = p;
- resp->xbuf->tail[0].iov_len = 0;
- if (maxcount&3) {
- RESERVE_SPACE(4);
- WRITE32(0);
- resp->xbuf->tail[0].iov_base += maxcount&3;
- resp->xbuf->tail[0].iov_len = 4 - (maxcount&3);
- ADJUST_ARGS();
- }
+ pad = (maxcount&3) ? 4 - (maxcount&3) : 0;
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount,
+ &zzz, pad);
return 0;
+
}
static __be32
-nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink)
+nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
+ struct nfsd4_read *read)
{
- int maxcount;
- char *page;
+ unsigned long maxcount;
+ struct xdr_stream *xdr = &resp->xdr;
+ struct file *file = read->rd_filp;
+ int starting_len = xdr->buf->len;
+ struct raparms *ra;
__be32 *p;
+ __be32 err;
if (nfserr)
return nfserr;
- if (resp->xbuf->page_len)
+
+ p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
+ if (!p) {
+ WARN_ON_ONCE(resp->rqstp->rq_splice_ok);
return nfserr_resource;
- if (!*resp->rqstp->rq_next_page)
+ }
+ if (resp->xdr.buf->page_len && resp->rqstp->rq_splice_ok) {
+ WARN_ON_ONCE(1);
return nfserr_resource;
+ }
+ xdr_commit_encode(xdr);
+
+ maxcount = svc_max_payload(resp->rqstp);
+ if (maxcount > xdr->buf->buflen - xdr->buf->len)
+ maxcount = xdr->buf->buflen - xdr->buf->len;
+ if (maxcount > read->rd_length)
+ maxcount = read->rd_length;
+
+ if (!read->rd_filp) {
+ err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp,
+ &file, &ra);
+ if (err)
+ goto err_truncate;
+ }
+
+ if (file->f_op->splice_read && resp->rqstp->rq_splice_ok)
+ err = nfsd4_encode_splice_read(resp, read, file, maxcount);
+ else
+ err = nfsd4_encode_readv(resp, read, file, maxcount);
+
+ if (!read->rd_filp)
+ nfsd_put_tmp_read_open(file, ra);
+
+err_truncate:
+ if (err)
+ xdr_truncate_encode(xdr, starting_len);
+ return err;
+}
+
+static __be32
+nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink)
+{
+ int maxcount;
+ __be32 wire_count;
+ int zero = 0;
+ struct xdr_stream *xdr = &resp->xdr;
+ int length_offset = xdr->buf->len;
+ __be32 *p;
- page = page_address(*(resp->rqstp->rq_next_page++));
+ if (nfserr)
+ return nfserr;
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ return nfserr_resource;
maxcount = PAGE_SIZE;
- RESERVE_SPACE(4);
+ p = xdr_reserve_space(xdr, maxcount);
+ if (!p)
+ return nfserr_resource;
/*
* XXX: By default, the ->readlink() VFS op will truncate symlinks
* if they would overflow the buffer. Is this kosher in NFSv4? If
* not, one easy fix is: if ->readlink() precisely fills the buffer,
* assume that truncation occurred, and return NFS4ERR_RESOURCE.
*/
- nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, page, &maxcount);
+ nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp,
+ (char *)p, &maxcount);
if (nfserr == nfserr_isdir)
- return nfserr_inval;
- if (nfserr)
+ nfserr = nfserr_inval;
+ if (nfserr) {
+ xdr_truncate_encode(xdr, length_offset);
return nfserr;
-
- WRITE32(maxcount);
- ADJUST_ARGS();
- resp->xbuf->head[0].iov_len = (char*)p
- - (char*)resp->xbuf->head[0].iov_base;
- resp->xbuf->page_len = maxcount;
-
- /* Use rest of head for padding and remaining ops: */
- resp->xbuf->tail[0].iov_base = p;
- resp->xbuf->tail[0].iov_len = 0;
- if (maxcount&3) {
- RESERVE_SPACE(4);
- WRITE32(0);
- resp->xbuf->tail[0].iov_base += maxcount&3;
- resp->xbuf->tail[0].iov_len = 4 - (maxcount&3);
- ADJUST_ARGS();
}
+
+ wire_count = htonl(maxcount);
+ write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4);
+ xdr_truncate_encode(xdr, length_offset + 4 + maxcount);
+ if (maxcount & 3)
+ write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount,
+ &zero, 4 - (maxcount&3));
return 0;
}
@@ -3062,47 +3277,52 @@ static __be32
nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir)
{
int maxcount;
+ int bytes_left;
loff_t offset;
- __be32 *page, *savep, *tailbase;
+ __be64 wire_offset;
+ struct xdr_stream *xdr = &resp->xdr;
+ int starting_len = xdr->buf->len;
__be32 *p;
if (nfserr)
return nfserr;
- if (resp->xbuf->page_len)
- return nfserr_resource;
- if (!*resp->rqstp->rq_next_page)
- return nfserr_resource;
- RESERVE_SPACE(NFS4_VERIFIER_SIZE);
- savep = p;
+ p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
+ if (!p)
+ return nfserr_resource;
/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
- WRITE32(0);
- WRITE32(0);
- ADJUST_ARGS();
- resp->xbuf->head[0].iov_len = ((char*)resp->p) - (char*)resp->xbuf->head[0].iov_base;
- tailbase = p;
-
- maxcount = PAGE_SIZE;
- if (maxcount > readdir->rd_maxcount)
- maxcount = readdir->rd_maxcount;
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0);
+ resp->xdr.buf->head[0].iov_len = ((char *)resp->xdr.p)
+ - (char *)resp->xdr.buf->head[0].iov_base;
/*
- * Convert from bytes to words, account for the two words already
- * written, make sure to leave two words at the end for the next
- * pointer and eof field.
+ * Number of bytes left for directory entries allowing for the
+ * final 8 bytes of the readdir and a following failed op:
+ */
+ bytes_left = xdr->buf->buflen - xdr->buf->len
+ - COMPOUND_ERR_SLACK_SPACE - 8;
+ if (bytes_left < 0) {
+ nfserr = nfserr_resource;
+ goto err_no_verf;
+ }
+ maxcount = min_t(u32, readdir->rd_maxcount, INT_MAX);
+ /*
+ * Note the rfc defines rd_maxcount as the size of the
+ * READDIR4resok structure, which includes the verifier above
+ * and the 8 bytes encoded at the end of this function:
*/
- maxcount = (maxcount >> 2) - 4;
- if (maxcount < 0) {
- nfserr = nfserr_toosmall;
+ if (maxcount < 16) {
+ nfserr = nfserr_toosmall;
goto err_no_verf;
}
+ maxcount = min_t(int, maxcount-16, bytes_left);
- page = page_address(*(resp->rqstp->rq_next_page++));
+ readdir->xdr = xdr;
+ readdir->rd_maxcount = maxcount;
readdir->common.err = 0;
- readdir->buflen = maxcount;
- readdir->buffer = page;
- readdir->offset = NULL;
+ readdir->cookie_offset = 0;
offset = readdir->rd_cookie;
nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp,
@@ -3110,42 +3330,49 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
&readdir->common, nfsd4_encode_dirent);
if (nfserr == nfs_ok &&
readdir->common.err == nfserr_toosmall &&
- readdir->buffer == page)
- nfserr = nfserr_toosmall;
+ xdr->buf->len == starting_len + 8) {
+ /* nothing encoded; which limit did we hit?: */
+ if (maxcount - 16 < bytes_left)
+ /* It was the fault of rd_maxcount: */
+ nfserr = nfserr_toosmall;
+ else
+ /* We ran out of buffer space: */
+ nfserr = nfserr_resource;
+ }
if (nfserr)
goto err_no_verf;
- if (readdir->offset)
- xdr_encode_hyper(readdir->offset, offset);
+ if (readdir->cookie_offset) {
+ wire_offset = cpu_to_be64(offset);
+ write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset,
+ &wire_offset, 8);
+ }
- p = readdir->buffer;
+ p = xdr_reserve_space(xdr, 8);
+ if (!p) {
+ WARN_ON_ONCE(1);
+ goto err_no_verf;
+ }
*p++ = 0; /* no more entries */
*p++ = htonl(readdir->common.err == nfserr_eof);
- resp->xbuf->page_len = ((char*)p) -
- (char*)page_address(*(resp->rqstp->rq_next_page-1));
-
- /* Use rest of head for padding and remaining ops: */
- resp->xbuf->tail[0].iov_base = tailbase;
- resp->xbuf->tail[0].iov_len = 0;
- resp->p = resp->xbuf->tail[0].iov_base;
- resp->end = resp->p + (PAGE_SIZE - resp->xbuf->head[0].iov_len)/4;
return 0;
err_no_verf:
- p = savep;
- ADJUST_ARGS();
+ xdr_truncate_encode(xdr, starting_len);
return nfserr;
}
static __be32
nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(20);
- write_cinfo(&p, &remove->rm_cinfo);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 20);
+ if (!p)
+ return nfserr_resource;
+ p = encode_cinfo(p, &remove->rm_cinfo);
}
return nfserr;
}
@@ -3153,19 +3380,21 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(40);
- write_cinfo(&p, &rename->rn_sinfo);
- write_cinfo(&p, &rename->rn_tinfo);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 40);
+ if (!p)
+ return nfserr_resource;
+ p = encode_cinfo(p, &rename->rn_sinfo);
+ p = encode_cinfo(p, &rename->rn_tinfo);
}
return nfserr;
}
static __be32
-nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
+nfsd4_do_encode_secinfo(struct xdr_stream *xdr,
__be32 nfserr, struct svc_export *exp)
{
u32 i, nflavs, supported;
@@ -3176,6 +3405,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
if (nfserr)
goto out;
+ nfserr = nfserr_resource;
if (exp->ex_nflavors) {
flavs = exp->ex_flavors;
nflavs = exp->ex_nflavors;
@@ -3197,9 +3427,10 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
}
supported = 0;
- RESERVE_SPACE(4);
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ goto out;
flavorsp = p++; /* to be backfilled later */
- ADJUST_ARGS();
for (i = 0; i < nflavs; i++) {
rpc_authflavor_t pf = flavs[i].pseudoflavor;
@@ -3207,18 +3438,20 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
if (rpcauth_get_gssinfo(pf, &info) == 0) {
supported++;
- RESERVE_SPACE(4 + 4 + XDR_LEN(info.oid.len) + 4 + 4);
- WRITE32(RPC_AUTH_GSS);
- WRITE32(info.oid.len);
- WRITEMEM(info.oid.data, info.oid.len);
- WRITE32(info.qop);
- WRITE32(info.service);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 4 + 4 +
+ XDR_LEN(info.oid.len) + 4 + 4);
+ if (!p)
+ goto out;
+ *p++ = cpu_to_be32(RPC_AUTH_GSS);
+ p = xdr_encode_opaque(p, info.oid.data, info.oid.len);
+ *p++ = cpu_to_be32(info.qop);
+ *p++ = cpu_to_be32(info.service);
} else if (pf < RPC_AUTH_MAXFLAVOR) {
supported++;
- RESERVE_SPACE(4);
- WRITE32(pf);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ goto out;
+ *p++ = cpu_to_be32(pf);
} else {
if (report)
pr_warn("NFS: SECINFO: security flavor %u "
@@ -3229,7 +3462,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
if (nflavs != supported)
report = false;
*flavorsp = htonl(supported);
-
+ nfserr = 0;
out:
if (exp)
exp_put(exp);
@@ -3240,14 +3473,18 @@ static __be32
nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo *secinfo)
{
- return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->si_exp);
+ struct xdr_stream *xdr = &resp->xdr;
+
+ return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->si_exp);
}
static __be32
nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo_no_name *secinfo)
{
- return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->sin_exp);
+ struct xdr_stream *xdr = &resp->xdr;
+
+ return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->sin_exp);
}
/*
@@ -3257,41 +3494,47 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
static __be32
nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
- RESERVE_SPACE(16);
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
+ return nfserr_resource;
if (nfserr) {
- WRITE32(3);
- WRITE32(0);
- WRITE32(0);
- WRITE32(0);
+ *p++ = cpu_to_be32(3);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0);
}
else {
- WRITE32(3);
- WRITE32(setattr->sa_bmval[0]);
- WRITE32(setattr->sa_bmval[1]);
- WRITE32(setattr->sa_bmval[2]);
+ *p++ = cpu_to_be32(3);
+ *p++ = cpu_to_be32(setattr->sa_bmval[0]);
+ *p++ = cpu_to_be32(setattr->sa_bmval[1]);
+ *p++ = cpu_to_be32(setattr->sa_bmval[2]);
}
- ADJUST_ARGS();
return nfserr;
}
static __be32
nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE);
- WRITEMEM(&scd->se_clientid, 8);
- WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 8 + NFS4_VERIFIER_SIZE);
+ if (!p)
+ return nfserr_resource;
+ p = xdr_encode_opaque_fixed(p, &scd->se_clientid, 8);
+ p = xdr_encode_opaque_fixed(p, &scd->se_confirm,
+ NFS4_VERIFIER_SIZE);
}
else if (nfserr == nfserr_clid_inuse) {
- RESERVE_SPACE(8);
- WRITE32(0);
- WRITE32(0);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 8);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(0);
+ *p++ = cpu_to_be32(0);
}
return nfserr;
}
@@ -3299,14 +3542,17 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
static __be32
nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(16);
- WRITE32(write->wr_bytes_written);
- WRITE32(write->wr_how_written);
- WRITEMEM(write->wr_verifier.data, NFS4_VERIFIER_SIZE);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(write->wr_bytes_written);
+ *p++ = cpu_to_be32(write->wr_how_written);
+ p = xdr_encode_opaque_fixed(p, write->wr_verifier.data,
+ NFS4_VERIFIER_SIZE);
}
return nfserr;
}
@@ -3323,6 +3569,7 @@ static __be32
nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_exchange_id *exid)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
char *major_id;
char *server_scope;
@@ -3338,60 +3585,61 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
server_scope = utsname()->nodename;
server_scope_sz = strlen(server_scope);
- RESERVE_SPACE(
+ p = xdr_reserve_space(xdr,
8 /* eir_clientid */ +
4 /* eir_sequenceid */ +
4 /* eir_flags */ +
4 /* spr_how */);
+ if (!p)
+ return nfserr_resource;
- WRITEMEM(&exid->clientid, 8);
- WRITE32(exid->seqid);
- WRITE32(exid->flags);
+ p = xdr_encode_opaque_fixed(p, &exid->clientid, 8);
+ *p++ = cpu_to_be32(exid->seqid);
+ *p++ = cpu_to_be32(exid->flags);
- WRITE32(exid->spa_how);
- ADJUST_ARGS();
+ *p++ = cpu_to_be32(exid->spa_how);
switch (exid->spa_how) {
case SP4_NONE:
break;
case SP4_MACH_CRED:
/* spo_must_enforce, spo_must_allow */
- RESERVE_SPACE(16);
+ p = xdr_reserve_space(xdr, 16);
+ if (!p)
+ return nfserr_resource;
/* spo_must_enforce bitmap: */
- WRITE32(2);
- WRITE32(nfs4_minimal_spo_must_enforce[0]);
- WRITE32(nfs4_minimal_spo_must_enforce[1]);
+ *p++ = cpu_to_be32(2);
+ *p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[0]);
+ *p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[1]);
/* empty spo_must_allow bitmap: */
- WRITE32(0);
+ *p++ = cpu_to_be32(0);
- ADJUST_ARGS();
break;
default:
WARN_ON_ONCE(1);
}
- RESERVE_SPACE(
+ p = xdr_reserve_space(xdr,
8 /* so_minor_id */ +
4 /* so_major_id.len */ +
(XDR_QUADLEN(major_id_sz) * 4) +
4 /* eir_server_scope.len */ +
(XDR_QUADLEN(server_scope_sz) * 4) +
4 /* eir_server_impl_id.count (0) */);
+ if (!p)
+ return nfserr_resource;
/* The server_owner struct */
- WRITE64(minor_id); /* Minor id */
+ p = xdr_encode_hyper(p, minor_id); /* Minor id */
/* major id */
- WRITE32(major_id_sz);
- WRITEMEM(major_id, major_id_sz);
+ p = xdr_encode_opaque(p, major_id, major_id_sz);
/* Server scope */
- WRITE32(server_scope_sz);
- WRITEMEM(server_scope, server_scope_sz);
+ p = xdr_encode_opaque(p, server_scope, server_scope_sz);
/* Implementation id */
- WRITE32(0); /* zero length nfs_impl_id4 array */
- ADJUST_ARGS();
+ *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */
return 0;
}
@@ -3399,47 +3647,54 @@ static __be32
nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_create_session *sess)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (nfserr)
return nfserr;
- RESERVE_SPACE(24);
- WRITEMEM(sess->sessionid.data, NFS4_MAX_SESSIONID_LEN);
- WRITE32(sess->seqid);
- WRITE32(sess->flags);
- ADJUST_ARGS();
-
- RESERVE_SPACE(28);
- WRITE32(0); /* headerpadsz */
- WRITE32(sess->fore_channel.maxreq_sz);
- WRITE32(sess->fore_channel.maxresp_sz);
- WRITE32(sess->fore_channel.maxresp_cached);
- WRITE32(sess->fore_channel.maxops);
- WRITE32(sess->fore_channel.maxreqs);
- WRITE32(sess->fore_channel.nr_rdma_attrs);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 24);
+ if (!p)
+ return nfserr_resource;
+ p = xdr_encode_opaque_fixed(p, sess->sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+ *p++ = cpu_to_be32(sess->seqid);
+ *p++ = cpu_to_be32(sess->flags);
+
+ p = xdr_reserve_space(xdr, 28);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(0); /* headerpadsz */
+ *p++ = cpu_to_be32(sess->fore_channel.maxreq_sz);
+ *p++ = cpu_to_be32(sess->fore_channel.maxresp_sz);
+ *p++ = cpu_to_be32(sess->fore_channel.maxresp_cached);
+ *p++ = cpu_to_be32(sess->fore_channel.maxops);
+ *p++ = cpu_to_be32(sess->fore_channel.maxreqs);
+ *p++ = cpu_to_be32(sess->fore_channel.nr_rdma_attrs);
if (sess->fore_channel.nr_rdma_attrs) {
- RESERVE_SPACE(4);
- WRITE32(sess->fore_channel.rdma_attrs);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(sess->fore_channel.rdma_attrs);
}
- RESERVE_SPACE(28);
- WRITE32(0); /* headerpadsz */
- WRITE32(sess->back_channel.maxreq_sz);
- WRITE32(sess->back_channel.maxresp_sz);
- WRITE32(sess->back_channel.maxresp_cached);
- WRITE32(sess->back_channel.maxops);
- WRITE32(sess->back_channel.maxreqs);
- WRITE32(sess->back_channel.nr_rdma_attrs);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 28);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(0); /* headerpadsz */
+ *p++ = cpu_to_be32(sess->back_channel.maxreq_sz);
+ *p++ = cpu_to_be32(sess->back_channel.maxresp_sz);
+ *p++ = cpu_to_be32(sess->back_channel.maxresp_cached);
+ *p++ = cpu_to_be32(sess->back_channel.maxops);
+ *p++ = cpu_to_be32(sess->back_channel.maxreqs);
+ *p++ = cpu_to_be32(sess->back_channel.nr_rdma_attrs);
if (sess->back_channel.nr_rdma_attrs) {
- RESERVE_SPACE(4);
- WRITE32(sess->back_channel.rdma_attrs);
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ return nfserr_resource;
+ *p++ = cpu_to_be32(sess->back_channel.rdma_attrs);
}
return 0;
}
@@ -3448,22 +3703,25 @@ static __be32
nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_sequence *seq)
{
+ struct xdr_stream *xdr = &resp->xdr;
__be32 *p;
if (nfserr)
return nfserr;
- RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 20);
- WRITEMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN);
- WRITE32(seq->seqid);
- WRITE32(seq->slotid);
+ p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20);
+ if (!p)
+ return nfserr_resource;
+ p = xdr_encode_opaque_fixed(p, seq->sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+ *p++ = cpu_to_be32(seq->seqid);
+ *p++ = cpu_to_be32(seq->slotid);
/* Note slotid's are numbered from zero: */
- WRITE32(seq->maxslots - 1); /* sr_highest_slotid */
- WRITE32(seq->maxslots - 1); /* sr_target_highest_slotid */
- WRITE32(seq->status_flags);
+ *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_highest_slotid */
+ *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_target_highest_slotid */
+ *p++ = cpu_to_be32(seq->status_flags);
- ADJUST_ARGS();
- resp->cstate.datap = p; /* DRC cache data pointer */
+ resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */
return 0;
}
@@ -3471,20 +3729,22 @@ static __be32
nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_test_stateid *test_stateid)
{
+ struct xdr_stream *xdr = &resp->xdr;
struct nfsd4_test_stateid_id *stateid, *next;
__be32 *p;
if (nfserr)
return nfserr;
- RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
+ p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids));
+ if (!p)
+ return nfserr_resource;
*p++ = htonl(test_stateid->ts_num_ids);
list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) {
*p++ = stateid->ts_id_status;
}
- ADJUST_ARGS();
return nfserr;
}
@@ -3563,81 +3823,99 @@ static nfsd4_enc nfsd4_enc_ops[] = {
};
/*
- * Calculate the total amount of memory that the compound response has taken
- * after encoding the current operation with pad.
- *
- * pad: if operation is non-idempotent, pad was calculate by op_rsize_bop()
- * which was specified at nfsd4_operation, else pad is zero.
- *
- * Compare this length to the session se_fmaxresp_sz and se_fmaxresp_cached.
+ * Calculate whether we still have space to encode repsize bytes.
+ * There are two considerations:
+ * - For NFS versions >=4.1, the size of the reply must stay within
+ * session limits
+ * - For all NFS versions, we must stay within limited preallocated
+ * buffer space.
*
- * Our se_fmaxresp_cached will always be a multiple of PAGE_SIZE, and so
- * will be at least a page and will therefore hold the xdr_buf head.
+ * This is called before the operation is processed, so can only provide
+ * an upper estimate. For some nonidempotent operations (such as
+ * getattr), it's not necessarily a problem if that estimate is wrong,
+ * as we can fail it after processing without significant side effects.
*/
-__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 pad)
+__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize)
{
- struct xdr_buf *xb = &resp->rqstp->rq_res;
- struct nfsd4_session *session = NULL;
+ struct xdr_buf *buf = &resp->rqstp->rq_res;
struct nfsd4_slot *slot = resp->cstate.slot;
- u32 length, tlen = 0;
+ if (buf->len + respsize <= buf->buflen)
+ return nfs_ok;
if (!nfsd4_has_session(&resp->cstate))
- return 0;
-
- session = resp->cstate.session;
-
- if (xb->page_len == 0) {
- length = (char *)resp->p - (char *)xb->head[0].iov_base + pad;
- } else {
- if (xb->tail[0].iov_base && xb->tail[0].iov_len > 0)
- tlen = (char *)resp->p - (char *)xb->tail[0].iov_base;
-
- length = xb->head[0].iov_len + xb->page_len + tlen + pad;
- }
- dprintk("%s length %u, xb->page_len %u tlen %u pad %u\n", __func__,
- length, xb->page_len, tlen, pad);
-
- if (length > session->se_fchannel.maxresp_sz)
- return nfserr_rep_too_big;
-
- if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) &&
- length > session->se_fchannel.maxresp_cached)
+ return nfserr_resource;
+ if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) {
+ WARN_ON_ONCE(1);
return nfserr_rep_too_big_to_cache;
-
- return 0;
+ }
+ return nfserr_rep_too_big;
}
void
nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
+ struct xdr_stream *xdr = &resp->xdr;
struct nfs4_stateowner *so = resp->cstate.replay_owner;
- __be32 *statp;
+ struct svc_rqst *rqstp = resp->rqstp;
+ int post_err_offset;
+ nfsd4_enc encoder;
__be32 *p;
- RESERVE_SPACE(8);
- WRITE32(op->opnum);
- statp = p++; /* to be backfilled at the end */
- ADJUST_ARGS();
+ p = xdr_reserve_space(xdr, 8);
+ if (!p) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ *p++ = cpu_to_be32(op->opnum);
+ post_err_offset = xdr->buf->len;
if (op->opnum == OP_ILLEGAL)
goto status;
BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) ||
!nfsd4_enc_ops[op->opnum]);
- op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u);
+ encoder = nfsd4_enc_ops[op->opnum];
+ op->status = encoder(resp, op->status, &op->u);
+ xdr_commit_encode(xdr);
+
/* nfsd4_check_resp_size guarantees enough room for error status */
- if (!op->status)
- op->status = nfsd4_check_resp_size(resp, 0);
+ if (!op->status) {
+ int space_needed = 0;
+ if (!nfsd4_last_compound_op(rqstp))
+ space_needed = COMPOUND_ERR_SLACK_SPACE;
+ op->status = nfsd4_check_resp_size(resp, space_needed);
+ }
+ if (op->status == nfserr_resource && nfsd4_has_session(&resp->cstate)) {
+ struct nfsd4_slot *slot = resp->cstate.slot;
+
+ if (slot->sl_flags & NFSD4_SLOT_CACHETHIS)
+ op->status = nfserr_rep_too_big_to_cache;
+ else
+ op->status = nfserr_rep_too_big;
+ }
+ if (op->status == nfserr_resource ||
+ op->status == nfserr_rep_too_big ||
+ op->status == nfserr_rep_too_big_to_cache) {
+ /*
+ * The operation may have already been encoded or
+ * partially encoded. No op returns anything additional
+ * in the case of one of these three errors, so we can
+ * just truncate back to after the status. But it's a
+ * bug if we had to do this on a non-idempotent op:
+ */
+ warn_on_nonidempotent_op(op);
+ xdr_truncate_encode(xdr, post_err_offset);
+ }
if (so) {
+ int len = xdr->buf->len - post_err_offset;
+
so->so_replay.rp_status = op->status;
- so->so_replay.rp_buflen = (char *)resp->p - (char *)(statp+1);
- memcpy(so->so_replay.rp_buf, statp+1, so->so_replay.rp_buflen);
+ so->so_replay.rp_buflen = len;
+ read_bytes_from_xdr_buf(xdr->buf, post_err_offset,
+ so->so_replay.rp_buf, len);
}
status:
- /*
- * Note: We write the status directly, instead of using WRITE32(),
- * since it is already in network byte order.
- */
- *statp = op->status;
+ /* Note that op->status is already in network byte order: */
+ write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4);
}
/*
@@ -3649,21 +3927,22 @@ status:
* called with nfs4_lock_state() held
*/
void
-nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
+nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
{
__be32 *p;
struct nfs4_replay *rp = op->replay;
BUG_ON(!rp);
- RESERVE_SPACE(8);
- WRITE32(op->opnum);
+ p = xdr_reserve_space(xdr, 8 + rp->rp_buflen);
+ if (!p) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ *p++ = cpu_to_be32(op->opnum);
*p++ = rp->rp_status; /* already xdr'ed */
- ADJUST_ARGS();
- RESERVE_SPACE(rp->rp_buflen);
- WRITEMEM(rp->rp_buf, rp->rp_buflen);
- ADJUST_ARGS();
+ p = xdr_encode_opaque_fixed(p, rp->rp_buf, rp->rp_buflen);
}
int
@@ -3720,19 +3999,19 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
* All that remains is to write the tag and operation count...
*/
struct nfsd4_compound_state *cs = &resp->cstate;
- struct kvec *iov;
+ struct xdr_buf *buf = resp->xdr.buf;
+
+ WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
+ buf->tail[0].iov_len);
+
+ rqstp->rq_next_page = resp->xdr.page_ptr + 1;
+
p = resp->tagp;
*p++ = htonl(resp->taglen);
memcpy(p, resp->tag, resp->taglen);
p += XDR_QUADLEN(resp->taglen);
*p++ = htonl(resp->opcnt);
- if (rqstp->rq_res.page_len)
- iov = &rqstp->rq_res.tail[0];
- else
- iov = &rqstp->rq_res.head[0];
- iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
- BUG_ON(iov->iov_len > PAGE_SIZE);
if (nfsd4_has_session(cs)) {
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
struct nfs4_client *clp = cs->session->se_client;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index f8f060ffbf4f..6040da8830ff 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp)
hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits));
}
-static inline bool
-nfsd_cache_entry_expired(struct svc_cacherep *rp)
-{
- return rp->c_state != RC_INPROG &&
- time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
-}
-
/*
* Walk the LRU list and prune off entries that are older than RC_EXPIRE.
* Also prune the oldest ones when the total exceeds the max number of entries.
@@ -242,8 +235,14 @@ prune_cache_entries(void)
long freed = 0;
list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
- if (!nfsd_cache_entry_expired(rp) &&
- num_drc_entries <= max_drc_entries)
+ /*
+ * Don't free entries attached to calls that are still
+ * in-progress, but do keep scanning the list.
+ */
+ if (rp->c_state == RC_INPROG)
+ continue;
+ if (num_drc_entries <= max_drc_entries &&
+ time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
break;
nfsd_reply_cache_free_locked(rp);
freed++;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index f34d9de802ab..51844048937f 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1179,7 +1179,6 @@ static int __init init_nfsd(void)
retval = nfsd4_init_slabs();
if (retval)
goto out_unregister_pernet;
- nfs4_state_init();
retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
if (retval)
goto out_free_slabs;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 479eb681c27c..847daf37e566 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -15,11 +15,20 @@
#include <linux/nfs2.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
+#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/msg_prot.h>
-#include <linux/nfsd/debug.h>
-#include <linux/nfsd/export.h>
-#include <linux/nfsd/stats.h>
+#include <uapi/linux/nfsd/debug.h>
+
+#include "stats.h"
+#include "export.h"
+
+#undef ifdebug
+#ifdef NFSD_DEBUG
+# define ifdebug(flag) if (nfsd_debug & NFSDDBG_##flag)
+#else
+# define ifdebug(flag) if (0)
+#endif
/*
* nfsd version
@@ -106,7 +115,6 @@ static inline int nfsd_v4client(struct svc_rqst *rq)
*/
#ifdef CONFIG_NFSD_V4
extern unsigned long max_delegations;
-void nfs4_state_init(void);
int nfsd4_init_slabs(void);
void nfsd4_free_slabs(void);
int nfs4_state_start(void);
@@ -117,7 +125,6 @@ void nfs4_reset_lease(time_t leasetime);
int nfs4_reset_recoverydir(char *recdir);
char * nfs4_recoverydir(void);
#else
-static inline void nfs4_state_init(void) { }
static inline int nfsd4_init_slabs(void) { return 0; }
static inline void nfsd4_free_slabs(void) { }
static inline int nfs4_state_start(void) { return 0; }
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 3c37b160dcad..ec8393418154 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -88,9 +88,8 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
/* Check if the request originated from a secure port. */
if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) {
RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
- dprintk(KERN_WARNING
- "nfsd: request from insecure port %s!\n",
- svc_print_addr(rqstp, buf, sizeof(buf)));
+ dprintk("nfsd: request from insecure port %s!\n",
+ svc_print_addr(rqstp, buf, sizeof(buf)));
return nfserr_perm;
}
@@ -169,8 +168,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
data_left -= len;
if (data_left < 0)
return error;
- exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_auth);
- fid = (struct fid *)(fh->fh_auth + len);
+ exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
+ fid = (struct fid *)(fh->fh_fsid + len);
} else {
__u32 tfh[2];
dev_t xdev;
@@ -385,7 +384,7 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
{
if (dentry != exp->ex_path.dentry) {
struct fid *fid = (struct fid *)
- (fhp->fh_handle.fh_auth + fhp->fh_handle.fh_size/4 - 1);
+ (fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1);
int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK);
@@ -513,7 +512,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
*/
struct inode * inode = dentry->d_inode;
- __u32 *datap;
dev_t ex_dev = exp_sb(exp)->s_dev;
dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %pd2, ino=%ld)\n",
@@ -557,17 +555,16 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
if (inode)
_fh_update_old(dentry, exp, &fhp->fh_handle);
} else {
- int len;
+ fhp->fh_handle.fh_size =
+ key_len(fhp->fh_handle.fh_fsid_type) + 4;
fhp->fh_handle.fh_auth_type = 0;
- datap = fhp->fh_handle.fh_auth+0;
- mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev,
+
+ mk_fsid(fhp->fh_handle.fh_fsid_type,
+ fhp->fh_handle.fh_fsid,
+ ex_dev,
exp->ex_path.dentry->d_inode->i_ino,
exp->ex_fsid, exp->ex_uuid);
- len = key_len(fhp->fh_handle.fh_fsid_type);
- datap += len/4;
- fhp->fh_handle.fh_size = 4 + len;
-
if (inode)
_fh_update(fhp, exp, dentry);
if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index ad67964d0bb1..2e89e70ac15c 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -1,9 +1,58 @@
-/* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */
+/*
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ *
+ * This file describes the layout of the file handles as passed
+ * over the wire.
+ */
+#ifndef _LINUX_NFSD_NFSFH_H
+#define _LINUX_NFSD_NFSFH_H
+
+#include <linux/sunrpc/svc.h>
+#include <uapi/linux/nfsd/nfsfh.h>
+
+static inline __u32 ino_t_to_u32(ino_t ino)
+{
+ return (__u32) ino;
+}
+
+static inline ino_t u32_to_ino_t(__u32 uino)
+{
+ return (ino_t) uino;
+}
-#ifndef _LINUX_NFSD_FH_INT_H
-#define _LINUX_NFSD_FH_INT_H
+/*
+ * This is the internal representation of an NFS handle used in knfsd.
+ * pre_mtime/post_version will be used to support wcc_attr's in NFSv3.
+ */
+typedef struct svc_fh {
+ struct knfsd_fh fh_handle; /* FH data */
+ struct dentry * fh_dentry; /* validated dentry */
+ struct svc_export * fh_export; /* export pointer */
+ int fh_maxsize; /* max size for fh_handle */
+
+ unsigned char fh_locked; /* inode locked by us */
+ unsigned char fh_want_write; /* remount protection taken */
+
+#ifdef CONFIG_NFSD_V3
+ unsigned char fh_post_saved; /* post-op attrs saved */
+ unsigned char fh_pre_saved; /* pre-op attrs saved */
+
+ /* Pre-op attributes saved during fh_lock */
+ __u64 fh_pre_size; /* size before operation */
+ struct timespec fh_pre_mtime; /* mtime before oper */
+ struct timespec fh_pre_ctime; /* ctime before oper */
+ /*
+ * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
+ * to find out if it is valid.
+ */
+ u64 fh_pre_change;
+
+ /* Post-op attributes saved in fh_unlock */
+ struct kstat fh_post_attr; /* full attrs after operation */
+ u64 fh_post_change; /* nfsv4 change; see above */
+#endif /* CONFIG_NFSD_V3 */
-#include <linux/nfsd/nfsfh.h>
+} svc_fh;
enum nfsd_fsid {
FSID_DEV = 0,
@@ -215,4 +264,4 @@ fh_unlock(struct svc_fh *fhp)
}
}
-#endif /* _LINUX_NFSD_FH_INT_H */
+#endif /* _LINUX_NFSD_NFSFH_H */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9a4a5f9e7468..1879e43f2868 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -591,12 +591,6 @@ nfsd(void *vrqstp)
nfsdstats.th_cnt++;
mutex_unlock(&nfsd_mutex);
- /*
- * We want less throttling in balance_dirty_pages() so that nfs to
- * localhost doesn't cause nfsd to lock up due to all the client's
- * dirty pages.
- */
- current->flags |= PF_LESS_THROTTLE;
set_freezable();
/*
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 9c769a47ac5a..1ac306b769df 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -214,7 +214,8 @@ nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
int
nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
return xdr_argsize_check(rqstp, p);
}
@@ -248,7 +249,8 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
{
unsigned int len;
int v;
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->offset = ntohl(*p++);
@@ -281,7 +283,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
unsigned int len, hdr, dlen;
int v;
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
p++; /* beginoffset */
@@ -355,7 +358,8 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
int
nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
@@ -391,7 +395,8 @@ int
nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_readdirargs *args)
{
- if (!(p = decode_fh(p, &args->fh)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
args->cookie = ntohl(*p++);
args->count = ntohl(*p++);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 424d8f5f2317..374c66283ac5 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -37,7 +37,6 @@
#include <linux/idr.h>
#include <linux/sunrpc/svc_xprt.h>
-#include <linux/nfsd/nfsfh.h>
#include "nfsfh.h"
typedef struct {
@@ -123,7 +122,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
/* Maximum number of operations per session compound */
#define NFSD_MAX_OPS_PER_COMPOUND 16
/* Maximum session per slot cache size */
-#define NFSD_SLOT_CACHE_SIZE 1024
+#define NFSD_SLOT_CACHE_SIZE 2048
/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION 32
#define NFSD_MAX_MEM_PER_SESSION \
@@ -464,8 +463,6 @@ extern void nfs4_release_reclaim(struct nfsd_net *);
extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
struct nfsd_net *nn);
extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn);
-extern void nfs4_free_openowner(struct nfs4_openowner *);
-extern void nfs4_free_lockowner(struct nfs4_lockowner *);
extern int set_callback_cred(void);
extern void nfsd4_init_callback(struct nfsd4_callback *);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 6d4521feb6e3..cd90878a76aa 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -24,7 +24,6 @@
#include <linux/seq_file.h>
#include <linux/module.h>
#include <linux/sunrpc/stats.h>
-#include <linux/nfsd/stats.h>
#include <net/net_namespace.h>
#include "nfsd.h"
diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h
new file mode 100644
index 000000000000..a5c944b771c6
--- /dev/null
+++ b/fs/nfsd/stats.h
@@ -0,0 +1,43 @@
+/*
+ * Statistics for NFS server.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef _NFSD_STATS_H
+#define _NFSD_STATS_H
+
+#include <uapi/linux/nfsd/stats.h>
+
+
+struct nfsd_stats {
+ unsigned int rchits; /* repcache hits */
+ unsigned int rcmisses; /* repcache hits */
+ unsigned int rcnocache; /* uncached reqs */
+ unsigned int fh_stale; /* FH stale error */
+ unsigned int fh_lookup; /* dentry cached */
+ unsigned int fh_anon; /* anon file dentry returned */
+ unsigned int fh_nocache_dir; /* filehandle not found in dcache */
+ unsigned int fh_nocache_nondir; /* filehandle not found in dcache */
+ unsigned int io_read; /* bytes returned to read requests */
+ unsigned int io_write; /* bytes passed in write requests */
+ unsigned int th_cnt; /* number of available threads */
+ unsigned int th_usage[10]; /* number of ticks during which n perdeciles
+ * of available threads were in use */
+ unsigned int th_fullcnt; /* number of times last free thread was used */
+ unsigned int ra_size; /* size of ra cache */
+ unsigned int ra_depth[11]; /* number of times ra entry was found that deep
+ * in the cache (10percentiles). [10] = not found */
+#ifdef CONFIG_NFSD_V4
+ unsigned int nfs4_opcount[LAST_NFS4_OP + 1]; /* count of individual nfsv4 operations */
+#endif
+
+};
+
+
+extern struct nfsd_stats nfsdstats;
+extern struct svc_stat nfsd_svcstats;
+
+void nfsd_stat_init(void);
+void nfsd_stat_shutdown(void);
+
+#endif /* _NFSD_STATS_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 16f0673a423c..140c496f612c 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -820,55 +820,54 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
}
-static __be32
-nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
- loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+__be32 nfsd_finish_read(struct file *file, unsigned long *count, int host_err)
{
- mm_segment_t oldfs;
- __be32 err;
- int host_err;
-
- err = nfserr_perm;
-
- if (file->f_op->splice_read && rqstp->rq_splice_ok) {
- struct splice_desc sd = {
- .len = 0,
- .total_len = *count,
- .pos = offset,
- .u.data = rqstp,
- };
-
- rqstp->rq_next_page = rqstp->rq_respages + 1;
- host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
- } else {
- oldfs = get_fs();
- set_fs(KERNEL_DS);
- host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
- set_fs(oldfs);
- }
-
if (host_err >= 0) {
nfsdstats.io_read += host_err;
*count = host_err;
- err = 0;
fsnotify_access(file);
+ return 0;
} else
- err = nfserrno(host_err);
- return err;
+ return nfserrno(host_err);
+}
+
+int nfsd_splice_read(struct svc_rqst *rqstp,
+ struct file *file, loff_t offset, unsigned long *count)
+{
+ struct splice_desc sd = {
+ .len = 0,
+ .total_len = *count,
+ .pos = offset,
+ .u.data = rqstp,
+ };
+ int host_err;
+
+ rqstp->rq_next_page = rqstp->rq_respages + 1;
+ host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+ return nfsd_finish_read(file, count, host_err);
}
-static void kill_suid(struct dentry *dentry)
+int nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
+ unsigned long *count)
{
- struct iattr ia;
- ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+ mm_segment_t oldfs;
+ int host_err;
- mutex_lock(&dentry->d_inode->i_mutex);
- /*
- * Note we call this on write, so notify_change will not
- * encounter any conflicting delegations:
- */
- notify_change(dentry, &ia, NULL);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+ set_fs(oldfs);
+ return nfsd_finish_read(file, count, host_err);
+}
+
+static __be32
+nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
+ loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+{
+ if (file->f_op->splice_read && rqstp->rq_splice_ok)
+ return nfsd_splice_read(rqstp, file, offset, count);
+ else
+ return nfsd_readv(file, offset, vec, vlen, count);
}
/*
@@ -922,6 +921,16 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
int stable = *stablep;
int use_wgather;
loff_t pos = offset;
+ unsigned int pflags = current->flags;
+
+ if (rqstp->rq_local)
+ /*
+ * We want less throttling in balance_dirty_pages()
+ * and shrink_inactive_list() so that nfs to
+ * localhost doesn't cause nfsd to lock up due to all
+ * the client's dirty pages or its congested queue.
+ */
+ current->flags |= PF_LESS_THROTTLE;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
@@ -942,10 +951,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
nfsdstats.io_write += host_err;
fsnotify_modify(file);
- /* clear setuid/setgid flag after write */
- if (inode->i_mode & (S_ISUID | S_ISGID))
- kill_suid(dentry);
-
if (stable) {
if (use_wgather)
host_err = wait_for_concurrent_writes(file);
@@ -959,36 +964,33 @@ out_nfserr:
err = 0;
else
err = nfserrno(host_err);
+ if (rqstp->rq_local)
+ tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
return err;
}
-/*
- * Read data from a file. count must contain the requested read count
- * on entry. On return, *count contains the number of bytes actually read.
- * N.B. After this call fhp needs an fh_put
- */
-__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
- loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct file **file, struct raparms **ra)
{
- struct file *file;
struct inode *inode;
- struct raparms *ra;
__be32 err;
- err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file);
if (err)
return err;
- inode = file_inode(file);
+ inode = file_inode(*file);
/* Get readahead parameters */
- ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
+ *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
- if (ra && ra->p_set)
- file->f_ra = ra->p_ra;
-
- err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
+ if (*ra && (*ra)->p_set)
+ (*file)->f_ra = (*ra)->p_ra;
+ return nfs_ok;
+}
+void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra)
+{
/* Write back readahead params */
if (ra) {
struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
@@ -998,28 +1000,29 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
ra->p_count--;
spin_unlock(&rab->pb_lock);
}
-
nfsd_close(file);
- return err;
}
-/* As above, but use the provided file descriptor. */
-__be32
-nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
- loff_t offset, struct kvec *vec, int vlen,
- unsigned long *count)
+/*
+ * Read data from a file. count must contain the requested read count
+ * on entry. On return, *count contains the number of bytes actually read.
+ * N.B. After this call fhp needs an fh_put
+ */
+__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
{
- __be32 err;
+ struct file *file;
+ struct raparms *ra;
+ __be32 err;
+
+ err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra);
+ if (err)
+ return err;
+
+ err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+
+ nfsd_put_tmp_read_open(file, ra);
- if (file) {
- err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
- NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE);
- if (err)
- goto out;
- err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
- } else /* Note file may still be NULL in NFSv4 special stateid case: */
- err = nfsd_read(rqstp, fhp, offset, vec, vlen, count);
-out:
return err;
}
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index fbe90bdb2214..91b6ae3f658b 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -70,10 +70,16 @@ __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *,
__be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
int, struct file **);
void nfsd_close(struct file *);
+struct raparms;
+__be32 nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *,
+ struct file **, struct raparms **);
+void nfsd_put_tmp_read_open(struct file *, struct raparms *);
+int nfsd_splice_read(struct svc_rqst *,
+ struct file *, loff_t, unsigned long *);
+int nfsd_readv(struct file *, loff_t, struct kvec *, int,
+ unsigned long *);
__be32 nfsd_read(struct svc_rqst *, struct svc_fh *,
loff_t, struct kvec *, int, unsigned long *);
-__be32 nfsd_read_file(struct svc_rqst *, struct svc_fh *, struct file *,
- loff_t, struct kvec *, int, unsigned long *);
__be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
loff_t, struct kvec *,int, unsigned long *, int *);
__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 5ea7df305083..18cbb6d9c8a9 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -58,7 +58,7 @@ struct nfsd4_compound_state {
/* For sessions DRC */
struct nfsd4_session *session;
struct nfsd4_slot *slot;
- __be32 *datap;
+ int data_offset;
size_t iovlen;
u32 minorversion;
__be32 status;
@@ -287,9 +287,8 @@ struct nfsd4_readdir {
struct svc_fh * rd_fhp; /* response */
struct readdir_cd common;
- __be32 * buffer;
- int buflen;
- __be32 * offset;
+ struct xdr_stream *xdr;
+ int cookie_offset;
};
struct nfsd4_release_lockowner {
@@ -506,9 +505,7 @@ struct nfsd4_compoundargs {
struct nfsd4_compoundres {
/* scratch variables for XDR encode */
- __be32 * p;
- __be32 * end;
- struct xdr_buf * xbuf;
+ struct xdr_stream xdr;
struct svc_rqst * rqstp;
u32 taglen;
@@ -538,6 +535,9 @@ static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
return argp->opcnt == resp->opcnt;
}
+int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op);
+void warn_on_nonidempotent_op(struct nfsd4_op *op);
+
#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs)
static inline void
@@ -563,10 +563,11 @@ int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
struct nfsd4_compoundres *);
__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
-void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op);
-__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 **buffer, int countp,
- u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
+void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
+__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
+ struct svc_fh *fhp, struct svc_export *exp,
+ struct dentry *dentry,
+ u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *,
struct nfsd4_setclientid *setclid);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 732648b270dc..3fdc8a3e1134 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -25,6 +25,19 @@
#define FANOTIFY_DEFAULT_MAX_MARKS 8192
#define FANOTIFY_DEFAULT_MAX_LISTENERS 128
+/*
+ * All flags that may be specified in parameter event_f_flags of fanotify_init.
+ *
+ * Internal and external open flags are stored together in field f_flags of
+ * struct file. Only external open flags shall be allowed in event_f_flags.
+ * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
+ * excluded.
+ */
+#define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \
+ O_ACCMODE | O_APPEND | O_NONBLOCK | \
+ __O_SYNC | O_DSYNC | O_CLOEXEC | \
+ O_LARGEFILE | O_NOATIME )
+
extern const struct fsnotify_ops fanotify_fsnotify_ops;
static struct kmem_cache *fanotify_mark_cache __read_mostly;
@@ -669,6 +682,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
if (flags & ~FAN_ALL_INIT_FLAGS)
return -EINVAL;
+ if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
+ return -EINVAL;
+
+ switch (event_f_flags & O_ACCMODE) {
+ case O_RDONLY:
+ case O_RDWR:
+ case O_WRONLY:
+ break;
+ default:
+ return -EINVAL;
+ }
+
user = get_current_user();
if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
free_uid(user);
@@ -776,7 +801,10 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
case FAN_MARK_REMOVE:
if (!mask)
return -EINVAL;
+ break;
case FAN_MARK_FLUSH:
+ if (flags & ~(FAN_MARK_MOUNT | FAN_MARK_FLUSH))
+ return -EINVAL;
break;
default:
return -EINVAL;
@@ -813,6 +841,15 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
group->priority == FS_PRIO_0)
goto fput_and_out;
+ if (flags & FAN_MARK_FLUSH) {
+ ret = 0;
+ if (flags & FAN_MARK_MOUNT)
+ fsnotify_clear_vfsmount_marks_by_group(group);
+ else
+ fsnotify_clear_inode_marks_by_group(group);
+ goto fput_and_out;
+ }
+
ret = fanotify_find_path(dfd, pathname, &path, flags);
if (ret)
goto fput_and_out;
@@ -824,7 +861,7 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
mnt = path.mnt;
/* create/update an inode mark */
- switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
+ switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
case FAN_MARK_ADD:
if (flags & FAN_MARK_MOUNT)
ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags);
@@ -837,12 +874,6 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
else
ret = fanotify_remove_inode_mark(group, inode, mask, flags);
break;
- case FAN_MARK_FLUSH:
- if (flags & FAN_MARK_MOUNT)
- fsnotify_clear_vfsmount_marks_by_group(group);
- else
- fsnotify_clear_inode_marks_by_group(group);
- break;
default:
ret = -EINVAL;
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 78a2ca3966c3..cc423a30a0c8 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -57,7 +57,7 @@ static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
static int zero;
-ctl_table inotify_table[] = {
+struct ctl_table inotify_table[] = {
{
.procname = "max_user_instances",
.data = &inotify_max_user_instances,
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 923fe4a5f503..d90deaa08e78 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -340,7 +340,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
static int fsnotify_mark_destroy(void *ignored)
{
struct fsnotify_mark *mark, *next;
- LIST_HEAD(private_destroy_list);
+ struct list_head private_destroy_list;
for (;;) {
spin_lock(&destroy_lock);
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index a27e3fecefaf..250ed5b20c8f 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
if (page) {
set_page_dirty(page);
unlock_page(page);
- mark_page_accessed(page);
page_cache_release(page);
}
ntfs_debug("Done.");
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index ee4144ce5d7c..f82498c35e78 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -58,7 +58,7 @@ typedef enum {
/**
* ntfs_compression_buffer - one buffer for the decompression engine
*/
-static u8 *ntfs_compression_buffer = NULL;
+static u8 *ntfs_compression_buffer;
/**
* ntfs_cb_lock - spinlock which protects ntfs_compression_buffer
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index db9bd8a31725..86ddab916b66 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
}
do {
unlock_page(pages[--do_pages]);
- mark_page_accessed(pages[do_pages]);
page_cache_release(pages[do_pages]);
} while (do_pages);
if (unlikely(status))
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 9de2491f2926..6c3296e546c3 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -50,8 +50,8 @@
static unsigned long ntfs_nr_compression_users;
/* A global default upcase table and a corresponding reference count. */
-static ntfschar *default_upcase = NULL;
-static unsigned long ntfs_nr_upcase_users = 0;
+static ntfschar *default_upcase;
+static unsigned long ntfs_nr_upcase_users;
/* Error constants/strings used in inode.c::ntfs_show_options(). */
typedef enum {
diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c
index 79a89184cb5e..a503156ec15f 100644
--- a/fs/ntfs/sysctl.c
+++ b/fs/ntfs/sysctl.c
@@ -34,7 +34,7 @@
#include "debug.h"
/* Definition of the ntfs sysctl. */
-static ctl_table ntfs_sysctls[] = {
+static struct ctl_table ntfs_sysctls[] = {
{
.procname = "ntfs-debug",
.data = &debug_msgs, /* Data pointer and size. */
@@ -46,7 +46,7 @@ static ctl_table ntfs_sysctls[] = {
};
/* Define the parent directory /proc/sys/fs. */
-static ctl_table sysctls_root[] = {
+static struct ctl_table sysctls_root[] = {
{
.procname = "fs",
.mode = 0555,
@@ -56,7 +56,7 @@ static ctl_table sysctls_root[] = {
};
/* Storage for the sysctls header. */
-static struct ctl_table_header *sysctls_root_table = NULL;
+static struct ctl_table_header *sysctls_root_table;
/**
* ntfs_sysctl - add or remove the debug sysctl
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b4deb5f750d9..9d8fcf2f3b94 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6046,7 +6046,8 @@ static void ocfs2_truncate_log_worker(struct work_struct *work)
void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
int cancel)
{
- if (osb->osb_tl_inode) {
+ if (osb->osb_tl_inode &&
+ atomic_read(&osb->osb_tl_disable) == 0) {
/* We want to push off log flushes while truncates are
* still running. */
if (cancel)
@@ -6223,6 +6224,8 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb)
int status;
struct inode *tl_inode = osb->osb_tl_inode;
+ atomic_set(&osb->osb_tl_disable, 1);
+
if (tl_inode) {
cancel_delayed_work(&osb->osb_truncate_log_wq);
flush_workqueue(ocfs2_wq);
@@ -6254,6 +6257,7 @@ int ocfs2_truncate_log_init(struct ocfs2_super *osb)
* until we're sure all is well. */
INIT_DELAYED_WORK(&osb->osb_truncate_log_wq,
ocfs2_truncate_log_worker);
+ atomic_set(&osb->osb_tl_disable, 0);
osb->osb_tl_bh = tl_bh;
osb->osb_tl_inode = tl_inode;
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index bf482dfed14f..73039295d0d1 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1107,7 +1107,7 @@ static int o2hb_thread(void *data)
mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread running\n");
- set_user_nice(current, -20);
+ set_user_nice(current, MIN_NICE);
/* Pin node */
o2nm_depend_this_node();
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index c6b90e670389..681691bc233a 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -108,7 +108,7 @@ static struct rb_root o2net_handler_tree = RB_ROOT;
static struct o2net_node o2net_nodes[O2NM_MAX_NODES];
/* XXX someday we'll need better accounting */
-static struct socket *o2net_listen_sock = NULL;
+static struct socket *o2net_listen_sock;
/*
* listen work is only queued by the listening socket callbacks on the
@@ -1799,7 +1799,7 @@ int o2net_register_hb_callbacks(void)
/* ------------------------------------------------------------ */
-static int o2net_accept_one(struct socket *sock)
+static int o2net_accept_one(struct socket *sock, int *more)
{
int ret, slen;
struct sockaddr_in sin;
@@ -1810,6 +1810,7 @@ static int o2net_accept_one(struct socket *sock)
struct o2net_node *nn;
BUG_ON(sock == NULL);
+ *more = 0;
ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type,
sock->sk->sk_protocol, &new_sock);
if (ret)
@@ -1821,6 +1822,7 @@ static int o2net_accept_one(struct socket *sock)
if (ret < 0)
goto out;
+ *more = 1;
new_sock->sk->sk_allocation = GFP_ATOMIC;
ret = o2net_set_nodelay(new_sock);
@@ -1919,11 +1921,36 @@ out:
return ret;
}
+/*
+ * This function is invoked in response to one or more
+ * pending accepts at softIRQ level. We must drain the
+ * entire que before returning.
+ */
+
static void o2net_accept_many(struct work_struct *work)
{
struct socket *sock = o2net_listen_sock;
- while (o2net_accept_one(sock) == 0)
+ int more;
+ int err;
+
+ /*
+ * It is critical to note that due to interrupt moderation
+ * at the network driver level, we can't assume to get a
+ * softIRQ for every single conn since tcp SYN packets
+ * can arrive back-to-back, and therefore many pending
+ * accepts may result in just 1 softIRQ. If we terminate
+ * the o2net_accept_one() loop upon seeing an err, what happens
+ * to the rest of the conns in the queue? If no new SYN
+ * arrives for hours, no softIRQ will be delivered,
+ * and the connections will just sit in the queue.
+ */
+
+ for (;;) {
+ err = o2net_accept_one(sock, &more);
+ if (!more)
+ break;
cond_resched();
+ }
}
static void o2net_listen_data_ready(struct sock *sk)
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e0517762fcc0..a106b3f2b22a 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -108,7 +108,6 @@ static inline int dlm_is_recovery_lock(const char *lock_name, int name_len)
struct dlm_recovery_ctxt
{
struct list_head resources;
- struct list_head received;
struct list_head node_data;
u8 new_master;
u8 dead_node;
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index e33cd7a3c582..18f13c2e4a10 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -338,7 +338,7 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle)
#ifdef CONFIG_DEBUG_FS
-static struct dentry *dlm_debugfs_root = NULL;
+static struct dentry *dlm_debugfs_root;
#define DLM_DEBUGFS_DIR "o2dlm"
#define DLM_DEBUGFS_DLM_STATE "dlm_state"
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index c973690dc0bc..39efc5057a36 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -959,6 +959,14 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data,
* domain. Set him in the map and clean up our
* leftover join state. */
BUG_ON(dlm->joining_node != assert->node_idx);
+
+ if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+ mlog(0, "dlm recovery is ongoing, disallow join\n");
+ spin_unlock(&dlm->spinlock);
+ spin_unlock(&dlm_domain_lock);
+ return -EAGAIN;
+ }
+
set_bit(assert->node_idx, dlm->domain_map);
clear_bit(assert->node_idx, dlm->exit_domain_map);
__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
@@ -1517,6 +1525,7 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm,
unsigned int node)
{
int status;
+ int ret;
struct dlm_assert_joined assert_msg;
mlog(0, "Sending join assert to node %u\n", node);
@@ -1528,11 +1537,13 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm,
status = o2net_send_message(DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY,
&assert_msg, sizeof(assert_msg), node,
- NULL);
+ &ret);
if (status < 0)
mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
"node %u\n", status, DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY,
node);
+ else
+ status = ret;
return status;
}
@@ -2023,7 +2034,6 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
INIT_LIST_HEAD(&dlm->list);
INIT_LIST_HEAD(&dlm->dirty_list);
INIT_LIST_HEAD(&dlm->reco.resources);
- INIT_LIST_HEAD(&dlm->reco.received);
INIT_LIST_HEAD(&dlm->reco.node_data);
INIT_LIST_HEAD(&dlm->purge_list);
INIT_LIST_HEAD(&dlm->dlm_domain_handlers);
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 5d32f7511f74..66c2a491f68d 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -52,7 +52,7 @@
#define MLOG_MASK_PREFIX ML_DLM
#include "cluster/masklog.h"
-static struct kmem_cache *dlm_lock_cache = NULL;
+static struct kmem_cache *dlm_lock_cache;
static DEFINE_SPINLOCK(dlm_cookie_lock);
static u64 dlm_next_cookie = 1;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index ee1f88419cb0..3087a21d32f9 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -82,9 +82,9 @@ static inline int dlm_mle_equal(struct dlm_ctxt *dlm,
return 1;
}
-static struct kmem_cache *dlm_lockres_cache = NULL;
-static struct kmem_cache *dlm_lockname_cache = NULL;
-static struct kmem_cache *dlm_mle_cache = NULL;
+static struct kmem_cache *dlm_lockres_cache;
+static struct kmem_cache *dlm_lockname_cache;
+static struct kmem_cache *dlm_mle_cache;
static void dlm_mle_release(struct kref *kref);
static void dlm_init_mle(struct dlm_master_list_entry *mle,
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index fe29f7978f81..5de019437ea5 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1986,7 +1986,15 @@ skip_lvb:
}
if (!bad) {
dlm_lock_get(newlock);
- list_add_tail(&newlock->list, queue);
+ if (mres->flags & DLM_MRES_RECOVERY &&
+ ml->list == DLM_CONVERTING_LIST &&
+ newlock->ml.type >
+ newlock->ml.convert_type) {
+ /* newlock is doing downconvert, add it to the
+ * head of converting list */
+ list_add(&newlock->list, queue);
+ } else
+ list_add_tail(&newlock->list, queue);
mlog(0, "%s:%.*s: added lock for node %u, "
"setting refmap bit\n", dlm->name,
res->lockname.len, res->lockname.name, ml->node);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6bd690b5a061..52cfe99ae056 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2544,11 +2544,6 @@ int ocfs2_super_lock(struct ocfs2_super *osb,
* refreshed, so we do it here. Of course, making sense of
* everything is up to the caller :) */
status = ocfs2_should_refresh_lock_res(lockres);
- if (status < 0) {
- ocfs2_cluster_unlock(osb, lockres, level);
- mlog_errno(status);
- goto bail;
- }
if (status) {
status = ocfs2_refresh_slot_info(osb);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8970dcf74de5..8eb6e5732d3b 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -828,7 +828,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
/*
* fs-writeback will release the dirty pages without page lock
* whose offset are over inode size, the release happens at
- * block_write_full_page_endio().
+ * block_write_full_page().
*/
i_size_write(inode, abs_to);
inode->i_blocks = ocfs2_inode_sector_count(inode);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 490229f43731..6f66b3751ace 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -143,8 +143,8 @@ bail:
return status;
}
-int ocfs2_info_handle_blocksize(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_blocksize(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_blocksize oib;
@@ -167,8 +167,8 @@ bail:
return status;
}
-int ocfs2_info_handle_clustersize(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_clustersize(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_clustersize oic;
@@ -192,8 +192,8 @@ bail:
return status;
}
-int ocfs2_info_handle_maxslots(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_maxslots(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_maxslots oim;
@@ -217,8 +217,8 @@ bail:
return status;
}
-int ocfs2_info_handle_label(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_label(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_label oil;
@@ -242,8 +242,8 @@ bail:
return status;
}
-int ocfs2_info_handle_uuid(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_uuid(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_uuid oiu;
@@ -267,8 +267,8 @@ bail:
return status;
}
-int ocfs2_info_handle_fs_features(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_fs_features(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_fs_features oif;
@@ -294,8 +294,8 @@ bail:
return status;
}
-int ocfs2_info_handle_journal_size(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_journal_size(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_journal_size oij;
@@ -319,9 +319,10 @@ bail:
return status;
}
-int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
- struct inode *inode_alloc, u64 blkno,
- struct ocfs2_info_freeinode *fi, u32 slot)
+static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
+ struct inode *inode_alloc, u64 blkno,
+ struct ocfs2_info_freeinode *fi,
+ u32 slot)
{
int status = 0, unlock = 0;
@@ -366,8 +367,8 @@ bail:
return status;
}
-int ocfs2_info_handle_freeinode(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_freeinode(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
u32 i;
u64 blkno = -1;
@@ -462,19 +463,19 @@ static void o2ffg_update_stats(struct ocfs2_info_freefrag_stats *stats,
stats->ffs_free_chunks_real++;
}
-void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg,
- unsigned int chunksize)
+static void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg,
+ unsigned int chunksize)
{
o2ffg_update_histogram(&(ffg->iff_ffs.ffs_fc_hist), chunksize);
o2ffg_update_stats(&(ffg->iff_ffs), chunksize);
}
-int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb,
- struct inode *gb_inode,
- struct ocfs2_dinode *gb_dinode,
- struct ocfs2_chain_rec *rec,
- struct ocfs2_info_freefrag *ffg,
- u32 chunks_in_group)
+static int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb,
+ struct inode *gb_inode,
+ struct ocfs2_dinode *gb_dinode,
+ struct ocfs2_chain_rec *rec,
+ struct ocfs2_info_freefrag *ffg,
+ u32 chunks_in_group)
{
int status = 0, used;
u64 blkno;
@@ -572,9 +573,9 @@ bail:
return status;
}
-int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb,
- struct inode *gb_inode, u64 blkno,
- struct ocfs2_info_freefrag *ffg)
+static int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb,
+ struct inode *gb_inode, u64 blkno,
+ struct ocfs2_info_freefrag *ffg)
{
u32 chunks_in_group;
int status = 0, unlock = 0, i;
@@ -652,8 +653,8 @@ bail:
return status;
}
-int ocfs2_info_handle_freefrag(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_freefrag(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
u64 blkno = -1;
char namebuf[40];
@@ -723,8 +724,8 @@ out_err:
return status;
}
-int ocfs2_info_handle_unknown(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_unknown(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_request oir;
@@ -752,8 +753,8 @@ bail:
* - distinguish different requests.
* - validate size of different requests.
*/
-int ocfs2_info_handle_request(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_request(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_request oir;
@@ -811,8 +812,8 @@ bail:
return status;
}
-int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx,
- u64 *req_addr, int compat_flag)
+static int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx,
+ u64 *req_addr, int compat_flag)
{
int status = -EFAULT;
u64 __user *bp = NULL;
@@ -849,8 +850,8 @@ bail:
* a better backward&forward compatibility, since a small piece of
* request will be less likely to be broken if disk layout get changed.
*/
-int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info,
- int compat_flag)
+static int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info,
+ int compat_flag)
{
int i, status = 0;
u64 req_addr;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 03ea9314fecd..4b0c68849b36 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -30,6 +30,7 @@
#include <linux/kthread.h>
#include <linux/time.h>
#include <linux/random.h>
+#include <linux/delay.h>
#include <cluster/masklog.h>
@@ -2185,8 +2186,20 @@ static int ocfs2_commit_thread(void *arg)
|| kthread_should_stop());
status = ocfs2_commit_cache(osb);
- if (status < 0)
- mlog_errno(status);
+ if (status < 0) {
+ static unsigned long abort_warn_time;
+
+ /* Warn about this once per minute */
+ if (printk_timed_ratelimit(&abort_warn_time, 60*HZ))
+ mlog(ML_ERROR, "status = %d, journal is "
+ "already aborted.\n", status);
+ /*
+ * After ocfs2_commit_cache() fails, j_num_trans has a
+ * non-zero value. Sleep here to avoid a busy-wait
+ * loop.
+ */
+ msleep_interruptible(1000);
+ }
if (kthread_should_stop() && atomic_read(&journal->j_num_trans)){
mlog(ML_KTHREAD,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 8d64a97a9d5e..bbec539230fd 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -422,6 +422,7 @@ struct ocfs2_super
struct inode *osb_tl_inode;
struct buffer_head *osb_tl_bh;
struct delayed_work osb_truncate_log_wq;
+ atomic_t osb_tl_disable;
/*
* How many clusters in our truncate log.
* It must be protected by osb_tl_inode->i_mutex.
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 6ba4bcbc4796..714e53b9cc66 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -1408,10 +1408,9 @@ static void swap_refcount_rec(void *a, void *b, int size)
{
struct ocfs2_refcount_rec *l = a, *r = b, tmp;
- tmp = *(struct ocfs2_refcount_rec *)l;
- *(struct ocfs2_refcount_rec *)l =
- *(struct ocfs2_refcount_rec *)r;
- *(struct ocfs2_refcount_rec *)r = tmp;
+ tmp = *l;
+ *l = *r;
+ *r = tmp;
}
/*
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index 822ebc10f281..d5da6f624142 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -53,8 +53,6 @@
*/
static u16 ocfs2_calc_new_backup_super(struct inode *inode,
struct ocfs2_group_desc *gd,
- int new_clusters,
- u32 first_new_cluster,
u16 cl_cpg,
int set)
{
@@ -127,8 +125,6 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
OCFS2_FEATURE_COMPAT_BACKUP_SB)) {
backups = ocfs2_calc_new_backup_super(bm_inode,
group,
- new_clusters,
- first_new_cluster,
cl_cpg, 1);
le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
}
@@ -157,7 +153,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
spin_lock(&OCFS2_I(bm_inode)->ip_lock);
OCFS2_I(bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
- le64_add_cpu(&fe->i_size, new_clusters << osb->s_clustersize_bits);
+ le64_add_cpu(&fe->i_size, (u64)new_clusters << osb->s_clustersize_bits);
spin_unlock(&OCFS2_I(bm_inode)->ip_lock);
i_size_write(bm_inode, le64_to_cpu(fe->i_size));
@@ -167,8 +163,6 @@ out_rollback:
if (ret < 0) {
ocfs2_calc_new_backup_super(bm_inode,
group,
- new_clusters,
- first_new_cluster,
cl_cpg, 0);
le16_add_cpu(&group->bg_free_bits_count, backups);
le16_add_cpu(&group->bg_bits, -1 * num_bits);
@@ -569,7 +563,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input)
spin_lock(&OCFS2_I(main_bm_inode)->ip_lock);
OCFS2_I(main_bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
- le64_add_cpu(&fe->i_size, input->clusters << osb->s_clustersize_bits);
+ le64_add_cpu(&fe->i_size, (u64)input->clusters << osb->s_clustersize_bits);
spin_unlock(&OCFS2_I(main_bm_inode)->ip_lock);
i_size_write(main_bm_inode, le64_to_cpu(fe->i_size));
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 83f1a665ae97..5d965e83bd43 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -709,7 +709,7 @@ static struct ctl_table ocfs2_root_table[] = {
{ }
};
-static struct ctl_table_header *ocfs2_table_header = NULL;
+static struct ctl_table_header *ocfs2_table_header;
/*
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a7cdd56f4c79..c7a89cea5c5d 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -75,7 +75,7 @@
#include "buffer_head_io.h"
-static struct kmem_cache *ocfs2_inode_cachep = NULL;
+static struct kmem_cache *ocfs2_inode_cachep;
struct kmem_cache *ocfs2_dquot_cachep;
struct kmem_cache *ocfs2_qf_chunk_cachep;
@@ -85,7 +85,7 @@ struct kmem_cache *ocfs2_qf_chunk_cachep;
* workqueue and schedule on our own. */
struct workqueue_struct *ocfs2_wq = NULL;
-static struct dentry *ocfs2_debugfs_root = NULL;
+static struct dentry *ocfs2_debugfs_root;
MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");
@@ -2292,8 +2292,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
- osb->vol_label[63] = '\0';
+ strlcpy(osb->vol_label, di->id2.i_super.s_label,
+ OCFS2_MAX_VOL_LABEL_LEN);
osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno);
osb->system_dir_blkno = le64_to_cpu(di->id2.i_super.s_system_dir_blkno);
osb->first_cluster_group_blkno =
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 52eaf33d346f..82e17b076ce7 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -67,7 +67,7 @@ struct ocfs2_meta_cache_item {
sector_t c_block;
};
-static struct kmem_cache *ocfs2_uptodate_cachep = NULL;
+static struct kmem_cache *ocfs2_uptodate_cachep;
u64 ocfs2_metadata_cache_owner(struct ocfs2_caching_info *ci)
{
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c4b2646b6d7c..cfa63ee92c96 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -300,6 +300,12 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
goto done;
}
+ if (vma->vm_ops && vma->vm_ops->name) {
+ name = vma->vm_ops->name(vma);
+ if (name)
+ goto done;
+ }
+
name = arch_vma_name(vma);
if (!name) {
pid_t tid;
@@ -737,9 +743,6 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
ptent = pte_file_clear_soft_dirty(ptent);
}
- if (vma->vm_flags & VM_SOFTDIRTY)
- vma->vm_flags &= ~VM_SOFTDIRTY;
-
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
@@ -807,8 +810,9 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
if (type == CLEAR_REFS_SOFT_DIRTY) {
soft_dirty_cleared = true;
- pr_warn_once("The pagemap bits 55-60 has changed their meaning! "
- "See the linux/Documentation/vm/pagemap.txt for details.\n");
+ pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
+ " See the linux/Documentation/vm/pagemap.txt for "
+ "details.\n");
}
task = get_proc_task(file_inode(file));
@@ -839,11 +843,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
*
* Writing 3 to /proc/pid/clear_refs only affects file
* mapped pages.
+ *
+ * Writing 4 to /proc/pid/clear_refs affects all pages.
*/
if (type == CLEAR_REFS_ANON && vma->vm_file)
continue;
if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
continue;
+ if (type == CLEAR_REFS_SOFT_DIRTY) {
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ }
walk_page_range(vma->vm_start, vma->vm_end,
&clear_refs_walk);
}
@@ -1408,10 +1418,10 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
if (file) {
- seq_printf(m, " file=");
+ seq_puts(m, " file=");
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");
+ seq_puts(m, " heap");
} else {
pid_t tid = vm_is_stack(task, vma, is_pid);
if (tid != 0) {
@@ -1421,14 +1431,14 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
*/
if (!is_pid || (vma->vm_start <= mm->start_stack &&
vma->vm_end >= mm->start_stack))
- seq_printf(m, " stack");
+ seq_puts(m, " stack");
else
seq_printf(m, " stack:%d", tid);
}
}
if (is_vm_hugetlb_page(vma))
- seq_printf(m, " huge");
+ seq_puts(m, " huge");
walk_page_range(vma->vm_start, vma->vm_end, &walk);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 6a8e785b29da..382aa890e228 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -42,7 +42,7 @@ static size_t elfnotes_sz;
/* Total size of vmcore file. */
static u64 vmcore_size;
-static struct proc_dir_entry *proc_vmcore = NULL;
+static struct proc_dir_entry *proc_vmcore;
/*
* Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 46d269e38706..0a9b72cdfeca 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -18,6 +18,8 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#define pr_fmt(fmt) "pstore: " fmt
+
#include <linux/atomic.h>
#include <linux/types.h>
#include <linux/errno.h>
@@ -224,14 +226,12 @@ static void allocate_buf_for_compression(void)
zlib_inflate_workspacesize());
stream.workspace = kmalloc(size, GFP_KERNEL);
if (!stream.workspace) {
- pr_err("pstore: No memory for compression workspace; "
- "skipping compression\n");
+ pr_err("No memory for compression workspace; skipping compression\n");
kfree(big_oops_buf);
big_oops_buf = NULL;
}
} else {
- pr_err("No memory for uncompressed data; "
- "skipping compression\n");
+ pr_err("No memory for uncompressed data; skipping compression\n");
stream.workspace = NULL;
}
@@ -455,8 +455,7 @@ int pstore_register(struct pstore_info *psi)
add_timer(&pstore_timer);
}
- pr_info("pstore: Registered %s as persistent store backend\n",
- psi->name);
+ pr_info("Registered %s as persistent store backend\n", psi->name);
return 0;
}
@@ -502,8 +501,8 @@ void pstore_get_records(int quiet)
size = unzipped_len;
compressed = false;
} else {
- pr_err("pstore: decompression failed;"
- "returned %d\n", unzipped_len);
+ pr_err("decompression failed;returned %d\n",
+ unzipped_len);
compressed = true;
}
}
@@ -524,8 +523,8 @@ out:
mutex_unlock(&psi->read_mutex);
if (failed)
- printk(KERN_WARNING "pstore: failed to load %d record(s) from '%s'\n",
- failed, psi->name);
+ pr_warn("failed to load %d record(s) from '%s'\n",
+ failed, psi->name);
}
static void pstore_dowork(struct work_struct *work)
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index ff7e3d4df5a1..34a1e5aa848c 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -12,6 +12,8 @@
*
*/
+#define pr_fmt(fmt) "persistent_ram: " fmt
+
#include <linux/device.h>
#include <linux/err.h>
#include <linux/errno.h>
@@ -205,12 +207,10 @@ static void persistent_ram_ecc_old(struct persistent_ram_zone *prz)
size = buffer->data + prz->buffer_size - block;
numerr = persistent_ram_decode_rs8(prz, block, size, par);
if (numerr > 0) {
- pr_devel("persistent_ram: error in block %p, %d\n",
- block, numerr);
+ pr_devel("error in block %p, %d\n", block, numerr);
prz->corrected_bytes += numerr;
} else if (numerr < 0) {
- pr_devel("persistent_ram: uncorrectable error in block %p\n",
- block);
+ pr_devel("uncorrectable error in block %p\n", block);
prz->bad_blocks++;
}
block += prz->ecc_info.block_size;
@@ -257,7 +257,7 @@ static int persistent_ram_init_ecc(struct persistent_ram_zone *prz,
prz->rs_decoder = init_rs(prz->ecc_info.symsize, prz->ecc_info.poly,
0, 1, prz->ecc_info.ecc_size);
if (prz->rs_decoder == NULL) {
- pr_info("persistent_ram: init_rs failed\n");
+ pr_info("init_rs failed\n");
return -EINVAL;
}
@@ -267,10 +267,10 @@ static int persistent_ram_init_ecc(struct persistent_ram_zone *prz,
numerr = persistent_ram_decode_rs8(prz, buffer, sizeof(*buffer),
prz->par_header);
if (numerr > 0) {
- pr_info("persistent_ram: error in header, %d\n", numerr);
+ pr_info("error in header, %d\n", numerr);
prz->corrected_bytes += numerr;
} else if (numerr < 0) {
- pr_info("persistent_ram: uncorrectable error in header\n");
+ pr_info("uncorrectable error in header\n");
prz->bad_blocks++;
}
@@ -317,7 +317,7 @@ void persistent_ram_save_old(struct persistent_ram_zone *prz)
prz->old_log = kmalloc(size, GFP_KERNEL);
}
if (!prz->old_log) {
- pr_err("persistent_ram: failed to allocate buffer\n");
+ pr_err("failed to allocate buffer\n");
return;
}
@@ -396,8 +396,8 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL);
if (!pages) {
- pr_err("%s: Failed to allocate array for %u pages\n", __func__,
- page_count);
+ pr_err("%s: Failed to allocate array for %u pages\n",
+ __func__, page_count);
return NULL;
}
@@ -462,19 +462,17 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
if (prz->buffer->sig == sig) {
if (buffer_size(prz) > prz->buffer_size ||
buffer_start(prz) > buffer_size(prz))
- pr_info("persistent_ram: found existing invalid buffer,"
- " size %zu, start %zu\n",
- buffer_size(prz), buffer_start(prz));
+ pr_info("found existing invalid buffer, size %zu, start %zu\n",
+ buffer_size(prz), buffer_start(prz));
else {
- pr_debug("persistent_ram: found existing buffer,"
- " size %zu, start %zu\n",
- buffer_size(prz), buffer_start(prz));
+ pr_debug("found existing buffer, size %zu, start %zu\n",
+ buffer_size(prz), buffer_start(prz));
persistent_ram_save_old(prz);
return 0;
}
} else {
- pr_debug("persistent_ram: no valid data in buffer"
- " (sig = 0x%08x)\n", prz->buffer->sig);
+ pr_debug("no valid data in buffer (sig = 0x%08x)\n",
+ prz->buffer->sig);
}
prz->buffer->sig = sig;
@@ -509,7 +507,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
prz = kzalloc(sizeof(struct persistent_ram_zone), GFP_KERNEL);
if (!prz) {
- pr_err("persistent_ram: failed to allocate persistent ram zone\n");
+ pr_err("failed to allocate persistent ram zone\n");
goto err;
}
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 2b363e23f36e..ff3f0b3cfdb3 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -278,6 +278,17 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
return ret;
}
+static int quota_rmxquota(struct super_block *sb, void __user *addr)
+{
+ __u32 flags;
+
+ if (copy_from_user(&flags, addr, sizeof(flags)))
+ return -EFAULT;
+ if (!sb->s_qcop->rm_xquota)
+ return -ENOSYS;
+ return sb->s_qcop->rm_xquota(sb, flags);
+}
+
/* Copy parameters and call proper function */
static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
void __user *addr, struct path *path)
@@ -316,8 +327,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
return sb->s_qcop->quota_sync(sb, type);
case Q_XQUOTAON:
case Q_XQUOTAOFF:
- case Q_XQUOTARM:
return quota_setxstate(sb, cmd, addr);
+ case Q_XQUOTARM:
+ return quota_rmxquota(sb, addr);
case Q_XGETQSTAT:
return quota_getxstate(sb, addr);
case Q_XGETQSTATV:
diff --git a/fs/readdir.c b/fs/readdir.c
index 5b53d995cae6..33fd92208cb7 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -13,6 +13,7 @@
#include <linux/stat.h>
#include <linux/file.h>
#include <linux/fs.h>
+#include <linux/fsnotify.h>
#include <linux/dirent.h>
#include <linux/security.h>
#include <linux/syscalls.h>
@@ -40,6 +41,7 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
ctx->pos = file->f_pos;
res = file->f_op->iterate(file, ctx);
file->f_pos = ctx->pos;
+ fsnotify_access(file);
file_accessed(file);
}
mutex_unlock(&inode->i_mutex);
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index dc9a6829f7c6..1bcffeab713c 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -142,7 +142,6 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th,
int org = *beg;
BUG_ON(!th->t_trans_id);
-
RFALSE(bmap_n >= reiserfs_bmap_count(s), "Bitmap %u is out of "
"range (0..%u)", bmap_n, reiserfs_bmap_count(s) - 1);
PROC_INFO_INC(s, scan_bitmap.bmap);
@@ -321,7 +320,6 @@ static int scan_bitmap(struct reiserfs_transaction_handle *th,
unsigned int off_max = s->s_blocksize << 3;
BUG_ON(!th->t_trans_id);
-
PROC_INFO_INC(s, scan_bitmap.call);
if (SB_FREE_BLOCKS(s) <= 0)
return 0; // No point in looking for more free blocks
@@ -388,9 +386,7 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th,
unsigned int nr, offset;
BUG_ON(!th->t_trans_id);
-
PROC_INFO_INC(s, free_block);
-
rs = SB_DISK_SUPER_BLOCK(s);
sbh = SB_BUFFER_WITH_SB(s);
apbi = SB_AP_BITMAP(s);
@@ -435,8 +431,8 @@ void reiserfs_free_block(struct reiserfs_transaction_handle *th,
int for_unformatted)
{
struct super_block *s = th->t_super;
- BUG_ON(!th->t_trans_id);
+ BUG_ON(!th->t_trans_id);
RFALSE(!s, "vs-4061: trying to free block on nonexistent device");
if (!is_reusable(s, block, 1))
return;
@@ -471,6 +467,7 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th,
unsigned long save = ei->i_prealloc_block;
int dirty = 0;
struct inode *inode = &ei->vfs_inode;
+
BUG_ON(!th->t_trans_id);
#ifdef CONFIG_REISERFS_CHECK
if (ei->i_prealloc_count < 0)
@@ -494,6 +491,7 @@ void reiserfs_discard_prealloc(struct reiserfs_transaction_handle *th,
struct inode *inode)
{
struct reiserfs_inode_info *ei = REISERFS_I(inode);
+
BUG_ON(!th->t_trans_id);
if (ei->i_prealloc_count)
__discard_prealloc(th, ei);
@@ -504,7 +502,6 @@ void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th)
struct list_head *plist = &SB_JOURNAL(th->t_super)->j_prealloc_list;
BUG_ON(!th->t_trans_id);
-
while (!list_empty(plist)) {
struct reiserfs_inode_info *ei;
ei = list_entry(plist->next, struct reiserfs_inode_info,
@@ -562,7 +559,7 @@ int reiserfs_parse_alloc_options(struct super_block *s, char *options)
if (!strcmp(this_char, "displacing_new_packing_localities")) {
SET_OPTION(displacing_new_packing_localities);
continue;
- };
+ }
if (!strcmp(this_char, "old_hashed_relocation")) {
SET_OPTION(old_hashed_relocation);
@@ -729,6 +726,7 @@ void show_alloc_options(struct seq_file *seq, struct super_block *s)
static inline void new_hashed_relocation(reiserfs_blocknr_hint_t * hint)
{
char *hash_in;
+
if (hint->formatted_node) {
hash_in = (char *)&hint->key.k_dir_id;
} else {
@@ -757,6 +755,7 @@ static void dirid_groups(reiserfs_blocknr_hint_t * hint)
__u32 dirid = 0;
int bm = 0;
struct super_block *sb = hint->th->t_super;
+
if (hint->inode)
dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id);
else if (hint->formatted_node)
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index b14706a05d52..615cd9ab7940 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -228,10 +228,10 @@ const struct reiserfs_key MIN_KEY = { 0, 0, {{0, 0},} };
/* Maximal possible key. It is never in the tree. */
static const struct reiserfs_key MAX_KEY = {
- __constant_cpu_to_le32(0xffffffff),
- __constant_cpu_to_le32(0xffffffff),
- {{__constant_cpu_to_le32(0xffffffff),
- __constant_cpu_to_le32(0xffffffff)},}
+ cpu_to_le32(0xffffffff),
+ cpu_to_le32(0xffffffff),
+ {{cpu_to_le32(0xffffffff),
+ cpu_to_le32(0xffffffff)},}
};
/* Get delimiting key of the buffer by looking for it in the buffers in the path, starting from the bottom
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 9e1bb79f7e6f..887d6d270080 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -25,7 +25,7 @@
#define ERROR(s, args...) pr_err("SQUASHFS error: "s, ## args)
-#define WARNING(s, args...) pr_warning("SQUASHFS: "s, ## args)
+#define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args)
/* block.c */
extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
diff --git a/fs/super.c b/fs/super.c
index 48377f7463c0..d20d5b11dedf 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -112,9 +112,14 @@ static unsigned long super_cache_count(struct shrinker *shrink,
sb = container_of(shrink, struct super_block, s_shrink);
- if (!grab_super_passive(sb))
- return 0;
-
+ /*
+ * Don't call grab_super_passive as it is a potential
+ * scalability bottleneck. The counts could get updated
+ * between super_cache_count and super_cache_scan anyway.
+ * Call to super_cache_count with shrinker_rwsem held
+ * ensures the safety of call to list_lru_count_node() and
+ * s_op->nr_cached_objects().
+ */
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb,
sc->nid);
@@ -125,7 +130,6 @@ static unsigned long super_cache_count(struct shrinker *shrink,
sc->nid);
total_objects = vfs_pressure_ratio(total_objects);
- drop_super(sb);
return total_objects;
}
@@ -276,10 +280,8 @@ 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_invalidate_fs(s);
- fs->kill_sb(s);
-
- /* caches are now gone, we can safely kill the shrinker now */
unregister_shrinker(&s->s_shrink);
+ fs->kill_sb(s);
put_filesystem(fs);
put_super(s);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index aa0406895b53..7d2a860ba788 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -18,7 +18,7 @@
#include "sysfs.h"
-static void remove_files(struct kernfs_node *parent, struct kobject *kobj,
+static void remove_files(struct kernfs_node *parent,
const struct attribute_group *grp)
{
struct attribute *const *attr;
@@ -29,7 +29,7 @@ static void remove_files(struct kernfs_node *parent, struct kobject *kobj,
kernfs_remove_by_name(parent, (*attr)->name);
if (grp->bin_attrs)
for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++)
- sysfs_remove_bin_file(kobj, *bin_attr);
+ kernfs_remove_by_name(parent, (*bin_attr)->attr.name);
}
static int create_files(struct kernfs_node *parent, struct kobject *kobj,
@@ -62,7 +62,7 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
break;
}
if (error) {
- remove_files(parent, kobj, grp);
+ remove_files(parent, grp);
goto exit;
}
}
@@ -79,7 +79,7 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
break;
}
if (error)
- remove_files(parent, kobj, grp);
+ remove_files(parent, grp);
}
exit:
return error;
@@ -224,7 +224,7 @@ void sysfs_remove_group(struct kobject *kobj,
kernfs_get(kn);
}
- remove_files(kn, kobj, grp);
+ remove_files(kn, grp);
if (grp->name)
kernfs_remove(kn);
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index e8e01d74dc05..eb997e9c4ab0 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -437,7 +437,6 @@ static int calc_dd_growth(const struct ubifs_info *c,
*/
int ubifs_budget_space(struct ubifs_info *c, struct ubifs_budget_req *req)
{
- int uninitialized_var(cmt_retries), uninitialized_var(wb_retries);
int err, idx_growth, data_growth, dd_growth, retried = 0;
ubifs_assert(req->new_page <= 1);
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 5157b866a853..177b0152fef4 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -745,8 +745,10 @@ void ubifs_dump_lprops(struct ubifs_info *c)
for (lnum = c->main_first; lnum < c->leb_cnt; lnum++) {
err = ubifs_read_one_lp(c, lnum, &lp);
- if (err)
+ if (err) {
ubifs_err("cannot read lprops for LEB %d", lnum);
+ continue;
+ }
ubifs_dump_lprop(c, &lp);
}
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 4f34dbae823d..0ab7f7dfb98b 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -903,8 +903,9 @@ static int do_writepage(struct page *page, int len)
struct ubifs_info *c = inode->i_sb->s_fs_info;
#ifdef UBIFS_DEBUG
+ struct ubifs_inode *ui = ubifs_inode(inode);
spin_lock(&ui->ui_lock);
- ubifs_assert(page->index <= ui->synced_i_size << PAGE_CACHE_SIZE);
+ ubifs_assert(page->index <= ui->synced_i_size >> PAGE_CACHE_SHIFT);
spin_unlock(&ui->ui_lock);
#endif
@@ -1525,8 +1526,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
}
wait_for_stable_page(page);
- unlock_page(page);
- return 0;
+ return VM_FAULT_LOCKED;
out_unlock:
unlock_page(page);
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index e18b9889a51b..2290d5866725 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -988,30 +988,32 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len,
return err;
if (type != ch->node_type) {
- ubifs_err("bad node type (%d but expected %d)",
- ch->node_type, type);
+ ubifs_errc(c, "bad node type (%d but expected %d)",
+ ch->node_type, type);
goto out;
}
err = ubifs_check_node(c, buf, lnum, offs, 0, 0);
if (err) {
- ubifs_err("expected node type %d", type);
+ ubifs_errc(c, "expected node type %d", type);
return err;
}
l = le32_to_cpu(ch->len);
if (l != len) {
- ubifs_err("bad node length %d, expected %d", l, len);
+ ubifs_errc(c, "bad node length %d, expected %d", l, len);
goto out;
}
return 0;
out:
- ubifs_err("bad node at LEB %d:%d, LEB mapping status %d", lnum, offs,
- ubi_is_mapped(c->ubi, lnum));
- ubifs_dump_node(c, buf);
- dump_stack();
+ ubifs_errc(c, "bad node at LEB %d:%d, LEB mapping status %d", lnum,
+ offs, ubi_is_mapped(c->ubi, lnum));
+ if (!c->probing) {
+ ubifs_dump_node(c, buf);
+ dump_stack();
+ }
return -EINVAL;
}
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index 4b826abb1528..45d4e96a6bac 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -460,9 +460,9 @@ static int write_cnodes(struct ubifs_info *c)
* important.
*/
clear_bit(DIRTY_CNODE, &cnode->flags);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(COW_CNODE, &cnode->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
offs += len;
dbg_chk_lpt_sz(c, 1, len);
cnode = cnode->cnext;
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index f35135e28e96..9a9fb94a41c6 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -128,7 +128,6 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention)
freed = ubifs_destroy_tnc_subtree(znode);
atomic_long_sub(freed, &ubifs_clean_zn_cnt);
atomic_long_sub(freed, &c->clean_zn_cnt);
- ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0);
total_freed += freed;
znode = zprev;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index a81c7b556896..3904c8574ef9 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1149,6 +1149,9 @@ static int mount_ubifs(struct ubifs_info *c)
size_t sz;
c->ro_mount = !!(c->vfs_sb->s_flags & MS_RDONLY);
+ /* Suppress error messages while probing if MS_SILENT is set */
+ c->probing = !!(c->vfs_sb->s_flags & MS_SILENT);
+
err = init_constants_early(c);
if (err)
return err;
@@ -1214,6 +1217,8 @@ static int mount_ubifs(struct ubifs_info *c)
if (err)
goto out_free;
+ c->probing = 0;
+
/*
* Make sure the compressor which is set as default in the superblock
* or overridden by mount options is actually compiled in.
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 9083bc7ed4ae..8a40cf9c02d7 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2859,10 +2859,11 @@ void ubifs_tnc_close(struct ubifs_info *c)
{
tnc_destroy_cnext(c);
if (c->zroot.znode) {
- long n;
+ long n, freed;
- ubifs_destroy_tnc_subtree(c->zroot.znode);
n = atomic_long_read(&c->clean_zn_cnt);
+ freed = ubifs_destroy_tnc_subtree(c->zroot.znode);
+ ubifs_assert(freed == n);
atomic_long_sub(n, &ubifs_clean_zn_cnt);
}
kfree(c->gap_lebs);
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index 52a6559275c4..3600994f8411 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -895,9 +895,9 @@ static int write_index(struct ubifs_info *c)
* the reason for the second barrier.
*/
clear_bit(DIRTY_ZNODE, &znode->flags);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(COW_ZNODE, &znode->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
/*
* We have marked the znode as clean but have not updated the
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index e8c8cfe1435c..c1f71fe17cc0 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -51,6 +51,15 @@
#define ubifs_warn(fmt, ...) \
pr_warn("UBIFS warning (pid %d): %s: " fmt "\n", \
current->pid, __func__, ##__VA_ARGS__)
+/*
+ * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description
+ * object as an argument.
+ */
+#define ubifs_errc(c, fmt, ...) \
+ do { \
+ if (!(c)->probing) \
+ ubifs_err(fmt, ##__VA_ARGS__); \
+ } while (0)
/* UBIFS file system VFS magic number */
#define UBIFS_SUPER_MAGIC 0x24051905
@@ -1209,6 +1218,7 @@ struct ubifs_debug_info;
* @need_recovery: %1 if the file-system needs recovery
* @replaying: %1 during journal replay
* @mounting: %1 while mounting
+ * @probing: %1 while attempting to mount if MS_SILENT mount flag is set
* @remounting_rw: %1 while re-mounting from R/O mode to R/W mode
* @replay_list: temporary list used during journal replay
* @replay_buds: list of buds to replay
@@ -1441,6 +1451,7 @@ struct ubifs_info {
unsigned int replaying:1;
unsigned int mounting:1;
unsigned int remounting_rw:1;
+ unsigned int probing:1;
struct list_head replay_list;
struct list_head replay_buds;
unsigned long long cs_sqnum;
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 0ab1de4b39a5..7bc20809c99e 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -24,7 +24,7 @@
#define INVBLOCK ((u64)-1L)
-static u64 ufs_add_fragments(struct inode *, u64, unsigned, unsigned, int *);
+static u64 ufs_add_fragments(struct inode *, u64, unsigned, unsigned);
static u64 ufs_alloc_fragments(struct inode *, unsigned, u64, unsigned, int *);
static u64 ufs_alloccg_block(struct inode *, struct ufs_cg_private_info *, u64, int *);
static u64 ufs_bitmap_search (struct super_block *, struct ufs_cg_private_info *, u64, unsigned);
@@ -52,7 +52,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
if (ufs_fragnum(fragment) + count > uspi->s_fpg)
ufs_error (sb, "ufs_free_fragments", "internal error");
- mutex_lock(&UFS_SB(sb)->s_lock);
+ lock_ufs(sb);
cgno = ufs_dtog(uspi, fragment);
bit = ufs_dtogd(uspi, fragment);
@@ -116,12 +116,12 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT\n");
return;
failed:
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT (FAILED)\n");
return;
}
@@ -151,7 +151,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count)
goto failed;
}
- mutex_lock(&UFS_SB(sb)->s_lock);
+ lock_ufs(sb);
do_more:
overflow = 0;
@@ -211,12 +211,12 @@ do_more:
}
ufs_mark_sb_dirty(sb);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT\n");
return;
failed_unlock:
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
failed:
UFSD("EXIT (FAILED)\n");
return;
@@ -357,7 +357,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
usb1 = ubh_get_usb_first(uspi);
*err = -ENOSPC;
- mutex_lock(&UFS_SB(sb)->s_lock);
+ lock_ufs(sb);
tmp = ufs_data_ptr_to_cpu(sb, p);
if (count + ufs_fragnum(fragment) > uspi->s_fpb) {
@@ -378,19 +378,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
"fragment %llu, tmp %llu\n",
(unsigned long long)fragment,
(unsigned long long)tmp);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
return INVBLOCK;
}
if (fragment < UFS_I(inode)->i_lastfrag) {
UFSD("EXIT (ALREADY ALLOCATED)\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
return 0;
}
}
else {
if (tmp) {
UFSD("EXIT (ALREADY ALLOCATED)\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
return 0;
}
}
@@ -399,7 +399,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
* There is not enough space for user on the device
*/
if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) {
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT (FAILED)\n");
return 0;
}
@@ -424,7 +424,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
ufs_clear_frags(inode, result + oldcount,
newcount - oldcount, locked_page != NULL);
}
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT, result %llu\n", (unsigned long long)result);
return result;
}
@@ -432,14 +432,14 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
/*
* resize block
*/
- result = ufs_add_fragments (inode, tmp, oldcount, newcount, err);
+ result = ufs_add_fragments(inode, tmp, oldcount, newcount);
if (result) {
*err = 0;
UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
fragment + count);
ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
locked_page != NULL);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT, result %llu\n", (unsigned long long)result);
return result;
}
@@ -477,7 +477,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
*err = 0;
UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
fragment + count);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
if (newcount < request)
ufs_free_fragments (inode, result + newcount, request - newcount);
ufs_free_fragments (inode, tmp, oldcount);
@@ -485,13 +485,13 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
return result;
}
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT (FAILED)\n");
return 0;
}
static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
- unsigned oldcount, unsigned newcount, int *err)
+ unsigned oldcount, unsigned newcount)
{
struct super_block * sb;
struct ufs_sb_private_info * uspi;
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index 98f7211599ff..a9cc75ffa925 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -69,11 +69,11 @@ void ufs_free_inode (struct inode * inode)
ino = inode->i_ino;
- mutex_lock(&UFS_SB(sb)->s_lock);
+ lock_ufs(sb);
if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) {
ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
return;
}
@@ -81,7 +81,7 @@ void ufs_free_inode (struct inode * inode)
bit = ufs_inotocgoff (ino);
ucpi = ufs_load_cylinder (sb, cg);
if (!ucpi) {
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
return;
}
ucg = ubh_get_ucg(UCPI_UBH(ucpi));
@@ -115,7 +115,7 @@ void ufs_free_inode (struct inode * inode)
ubh_sync_block(UCPI_UBH(ucpi));
ufs_mark_sb_dirty(sb);
- mutex_unlock(&UFS_SB(sb)->s_lock);
+ unlock_ufs(sb);
UFSD("EXIT\n");
}
@@ -193,7 +193,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode)
sbi = UFS_SB(sb);
uspi = sbi->s_uspi;
- mutex_lock(&sbi->s_lock);
+ lock_ufs(sb);
/*
* Try to place the inode in its parent directory
@@ -328,21 +328,20 @@ cg_found:
sync_dirty_buffer(bh);
brelse(bh);
}
-
- mutex_unlock(&sbi->s_lock);
+ unlock_ufs(sb);
UFSD("allocating inode %lu\n", inode->i_ino);
UFSD("EXIT\n");
return inode;
fail_remove_inode:
- mutex_unlock(&sbi->s_lock);
+ unlock_ufs(sb);
clear_nlink(inode);
iput(inode);
UFSD("EXIT (FAILED): err %d\n", err);
return ERR_PTR(err);
failed:
- mutex_unlock(&sbi->s_lock);
+ unlock_ufs(sb);
make_bad_inode(inode);
iput (inode);
UFSD("EXIT (FAILED): err %d\n", err);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index c1183f9f69dc..b879f1ba3439 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -697,7 +697,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
unsigned flags;
lock_ufs(sb);
- mutex_lock(&UFS_SB(sb)->s_lock);
UFSD("ENTER\n");
@@ -715,7 +714,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
ufs_put_cstotal(sb);
UFSD("EXIT\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return 0;
@@ -760,6 +758,7 @@ static void ufs_put_super(struct super_block *sb)
ubh_brelse_uspi (sbi->s_uspi);
kfree (sbi->s_uspi);
+ mutex_destroy(&sbi->mutex);
kfree (sbi);
sb->s_fs_info = NULL;
UFSD("EXIT\n");
@@ -786,6 +785,14 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
flags = 0;
UFSD("ENTER\n");
+
+#ifndef CONFIG_UFS_FS_WRITE
+ if (!(sb->s_flags & MS_RDONLY)) {
+ printk("ufs was compiled with read-only support, "
+ "can't be mounted as read-write\n");
+ return -EROFS;
+ }
+#endif
sbi = kzalloc(sizeof(struct ufs_sb_info), GFP_KERNEL);
if (!sbi)
@@ -795,15 +802,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
-#ifndef CONFIG_UFS_FS_WRITE
- if (!(sb->s_flags & MS_RDONLY)) {
- printk("ufs was compiled with read-only support, "
- "can't be mounted as read-write\n");
- goto failed;
- }
-#endif
mutex_init(&sbi->mutex);
- mutex_init(&sbi->s_lock);
spin_lock_init(&sbi->work_lock);
INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
/*
@@ -1257,6 +1256,7 @@ magic_found:
return 0;
failed:
+ mutex_destroy(&sbi->mutex);
if (ubh)
ubh_brelse_uspi (uspi);
kfree (uspi);
@@ -1280,7 +1280,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
sync_filesystem(sb);
lock_ufs(sb);
- mutex_lock(&UFS_SB(sb)->s_lock);
uspi = UFS_SB(sb)->s_uspi;
flags = UFS_SB(sb)->s_flags;
usb1 = ubh_get_usb_first(uspi);
@@ -1294,7 +1293,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
new_mount_opt = 0;
ufs_set_opt (new_mount_opt, ONERROR_LOCK);
if (!ufs_parse_options (data, &new_mount_opt)) {
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
}
@@ -1302,14 +1300,12 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
new_mount_opt |= ufstype;
} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
printk("ufstype can't be changed during remount\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
}
if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
UFS_SB(sb)->s_mount_opt = new_mount_opt;
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return 0;
}
@@ -1334,7 +1330,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
#ifndef CONFIG_UFS_FS_WRITE
printk("ufs was compiled with read-only support, "
"can't be mounted as read-write\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
#else
@@ -1344,13 +1339,11 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
printk("this ufstype is read-only supported\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
}
if (!ufs_read_cylinder_structures(sb)) {
printk("failed during remounting\n");
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EPERM;
}
@@ -1358,7 +1351,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
#endif
}
UFS_SB(sb)->s_mount_opt = new_mount_opt;
- mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return 0;
}
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index ff2c15ab81aa..343e6fc571e5 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -24,7 +24,6 @@ struct ufs_sb_info {
int work_queued; /* non-zero if the delayed work is queued */
struct delayed_work sync_work; /* FS sync delayed work */
spinlock_t work_lock; /* protects sync_work and work_queued */
- struct mutex s_lock;
};
struct ufs_inode_info {
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 0fdd4109c624..6e247a99f5db 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -160,30 +160,38 @@ typedef struct xfs_agi {
* still being referenced.
*/
__be32 agi_unlinked[XFS_AGI_UNLINKED_BUCKETS];
-
+ /*
+ * This marks the end of logging region 1 and start of logging region 2.
+ */
uuid_t agi_uuid; /* uuid of filesystem */
__be32 agi_crc; /* crc of agi sector */
__be32 agi_pad32;
__be64 agi_lsn; /* last write sequence */
+ __be32 agi_free_root; /* root of the free inode btree */
+ __be32 agi_free_level;/* levels in free inode btree */
+
/* structure must be padded to 64 bit alignment */
} xfs_agi_t;
#define XFS_AGI_CRC_OFF offsetof(struct xfs_agi, agi_crc)
-#define XFS_AGI_MAGICNUM 0x00000001
-#define XFS_AGI_VERSIONNUM 0x00000002
-#define XFS_AGI_SEQNO 0x00000004
-#define XFS_AGI_LENGTH 0x00000008
-#define XFS_AGI_COUNT 0x00000010
-#define XFS_AGI_ROOT 0x00000020
-#define XFS_AGI_LEVEL 0x00000040
-#define XFS_AGI_FREECOUNT 0x00000080
-#define XFS_AGI_NEWINO 0x00000100
-#define XFS_AGI_DIRINO 0x00000200
-#define XFS_AGI_UNLINKED 0x00000400
-#define XFS_AGI_NUM_BITS 11
-#define XFS_AGI_ALL_BITS ((1 << XFS_AGI_NUM_BITS) - 1)
+#define XFS_AGI_MAGICNUM (1 << 0)
+#define XFS_AGI_VERSIONNUM (1 << 1)
+#define XFS_AGI_SEQNO (1 << 2)
+#define XFS_AGI_LENGTH (1 << 3)
+#define XFS_AGI_COUNT (1 << 4)
+#define XFS_AGI_ROOT (1 << 5)
+#define XFS_AGI_LEVEL (1 << 6)
+#define XFS_AGI_FREECOUNT (1 << 7)
+#define XFS_AGI_NEWINO (1 << 8)
+#define XFS_AGI_DIRINO (1 << 9)
+#define XFS_AGI_UNLINKED (1 << 10)
+#define XFS_AGI_NUM_BITS_R1 11 /* end of the 1st agi logging region */
+#define XFS_AGI_ALL_BITS_R1 ((1 << XFS_AGI_NUM_BITS_R1) - 1)
+#define XFS_AGI_FREE_ROOT (1 << 11)
+#define XFS_AGI_FREE_LEVEL (1 << 12)
+#define XFS_AGI_NUM_BITS_R2 13
/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGI_DADDR(mp) ((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index c1cf6a336a72..d43813267a80 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -257,16 +257,14 @@ xfs_alloc_fix_len(
k = rlen % args->prod;
if (k == args->mod)
return;
- if (k > args->mod) {
- if ((int)(rlen = rlen - k - args->mod) < (int)args->minlen)
- return;
- } else {
- if ((int)(rlen = rlen - args->prod - (args->mod - k)) <
- (int)args->minlen)
- return;
- }
- ASSERT(rlen >= args->minlen);
- ASSERT(rlen <= args->maxlen);
+ if (k > args->mod)
+ rlen = rlen - (k - args->mod);
+ else
+ rlen = rlen - args->prod + (args->mod - k);
+ if ((int)rlen < (int)args->minlen)
+ return;
+ ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
+ ASSERT(rlen % args->prod == args->mod);
args->len = rlen;
}
@@ -541,7 +539,6 @@ xfs_alloc_read_agfl(
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
if (error)
return error;
- ASSERT(!xfs_buf_geterror(bp));
xfs_buf_set_ref(bp, XFS_AGFL_REF);
*bpp = bp;
return 0;
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index cc1eadcbb049..8358f1ded94d 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -70,7 +70,6 @@ xfs_allocbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
- int length,
int *stat)
{
int error;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0479c32c5eb1..e32640eedea6 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -975,14 +975,39 @@ xfs_vm_writepage(
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
- if (WARN_ON(current->flags & PF_FSTRANS))
+ if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
goto redirty;
/* Is this page beyond the end of the file? */
offset = i_size_read(inode);
end_index = offset >> PAGE_CACHE_SHIFT;
last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
- if (page->index >= end_index) {
+
+ /*
+ * The page index is less than the end_index, adjust the end_offset
+ * to the highest offset that this page should represent.
+ * -----------------------------------------------------
+ * | file mapping | <EOF> |
+ * -----------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | |
+ * ^--------------------------------^----------|--------
+ * | desired writeback range | see else |
+ * ---------------------------------^------------------|
+ */
+ if (page->index < end_index)
+ end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+ else {
+ /*
+ * Check whether the page to write out is beyond or straddles
+ * i_size or not.
+ * -------------------------------------------------------
+ * | file mapping | <EOF> |
+ * -------------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | Beyond |
+ * ^--------------------------------^-----------|---------
+ * | | Straddles |
+ * ---------------------------------^-----------|--------|
+ */
unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
/*
@@ -990,24 +1015,36 @@ xfs_vm_writepage(
* truncate operation that is in progress. We must redirty the
* page so that reclaim stops reclaiming it. Otherwise
* xfs_vm_releasepage() is called on it and gets confused.
+ *
+ * Note that the end_index is unsigned long, it would overflow
+ * if the given offset is greater than 16TB on 32-bit system
+ * and if we do check the page is fully outside i_size or not
+ * via "if (page->index >= end_index + 1)" as "end_index + 1"
+ * will be evaluated to 0. Hence this page will be redirtied
+ * and be written out repeatedly which would result in an
+ * infinite loop, the user program that perform this operation
+ * will hang. Instead, we can verify this situation by checking
+ * if the page to write is totally beyond the i_size or if it's
+ * offset is just equal to the EOF.
*/
- if (page->index >= end_index + 1 || offset_into_page == 0)
+ if (page->index > end_index ||
+ (page->index == end_index && offset_into_page == 0))
goto redirty;
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
* "A file is mapped in multiples of the page size. For a file
- * that is not a multiple of the page size, the remaining
+ * that is not a multiple of the page size, the remaining
* memory is zeroed when mapped, and writes to that region are
* not written out to the file."
*/
zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+
+ /* Adjust the end_offset to the end of file */
+ end_offset = offset;
}
- end_offset = min_t(unsigned long long,
- (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
- offset);
len = 1 << inode->i_blkbits;
bh = head = page_buffers(page);
@@ -1188,9 +1225,9 @@ xfs_vm_releasepage(
xfs_count_page_state(page, &delalloc, &unwritten);
- if (WARN_ON(delalloc))
+ if (WARN_ON_ONCE(delalloc))
return 0;
- if (WARN_ON(unwritten))
+ if (WARN_ON_ONCE(unwritten))
return 0;
return try_to_free_buffers(page);
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index abda1124a70f..bfe36fc2cdc2 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -77,17 +77,27 @@ STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
STATIC int
-xfs_attr_name_to_xname(
- struct xfs_name *xname,
- const unsigned char *aname)
+xfs_attr_args_init(
+ struct xfs_da_args *args,
+ struct xfs_inode *dp,
+ const unsigned char *name,
+ int flags)
{
- if (!aname)
+
+ if (!name)
return EINVAL;
- xname->name = aname;
- xname->len = strlen((char *)aname);
- if (xname->len >= MAXNAMELEN)
+
+ memset(args, 0, sizeof(*args));
+ args->geo = dp->i_mount->m_attr_geo;
+ args->whichfork = XFS_ATTR_FORK;
+ args->dp = dp;
+ args->flags = flags;
+ args->name = name;
+ args->namelen = strlen((const char *)name);
+ if (args->namelen >= MAXNAMELEN)
return EFAULT; /* match IRIX behaviour */
+ args->hashval = xfs_da_hashname(args->name, args->namelen);
return 0;
}
@@ -106,79 +116,46 @@ xfs_inode_hasattr(
* Overall external interface routines.
*========================================================================*/
-STATIC int
-xfs_attr_get_int(
+int
+xfs_attr_get(
struct xfs_inode *ip,
- struct xfs_name *name,
+ const unsigned char *name,
unsigned char *value,
int *valuelenp,
int flags)
{
- xfs_da_args_t args;
- int error;
+ struct xfs_da_args args;
+ uint lock_mode;
+ int error;
+
+ XFS_STATS_INC(xs_attr_get);
+
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ return EIO;
if (!xfs_inode_hasattr(ip))
return ENOATTR;
- /*
- * Fill in the arg structure for this request.
- */
- memset((char *)&args, 0, sizeof(args));
- args.name = name->name;
- args.namelen = name->len;
+ error = xfs_attr_args_init(&args, ip, name, flags);
+ if (error)
+ return error;
+
args.value = value;
args.valuelen = *valuelenp;
- args.flags = flags;
- args.hashval = xfs_da_hashname(args.name, args.namelen);
- args.dp = ip;
- args.whichfork = XFS_ATTR_FORK;
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ lock_mode = xfs_ilock_attr_map_shared(ip);
+ if (!xfs_inode_hasattr(ip))
+ error = ENOATTR;
+ else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
error = xfs_attr_shortform_getvalue(&args);
- } else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) {
+ else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
error = xfs_attr_leaf_get(&args);
- } else {
+ else
error = xfs_attr_node_get(&args);
- }
+ xfs_iunlock(ip, lock_mode);
- /*
- * Return the number of bytes in the value to the caller.
- */
*valuelenp = args.valuelen;
-
- if (error == EEXIST)
- error = 0;
- return(error);
-}
-
-int
-xfs_attr_get(
- xfs_inode_t *ip,
- const unsigned char *name,
- unsigned char *value,
- int *valuelenp,
- int flags)
-{
- int error;
- struct xfs_name xname;
- uint lock_mode;
-
- XFS_STATS_INC(xs_attr_get);
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- return(EIO);
-
- error = xfs_attr_name_to_xname(&xname, name);
- if (error)
- return error;
-
- lock_mode = xfs_ilock_attr_map_shared(ip);
- error = xfs_attr_get_int(ip, &xname, value, valuelenp, flags);
- xfs_iunlock(ip, lock_mode);
- return(error);
+ return error == EEXIST ? 0 : error;
}
/*
@@ -186,12 +163,10 @@ xfs_attr_get(
*/
STATIC int
xfs_attr_calc_size(
- struct xfs_inode *ip,
- int namelen,
- int valuelen,
+ struct xfs_da_args *args,
int *local)
{
- struct xfs_mount *mp = ip->i_mount;
+ struct xfs_mount *mp = args->dp->i_mount;
int size;
int nblks;
@@ -199,12 +174,10 @@ xfs_attr_calc_size(
* Determine space new attribute will use, and if it would be
* "local" or "remote" (note: local != inline).
*/
- size = xfs_attr_leaf_newentsize(namelen, valuelen,
- mp->m_sb.sb_blocksize, local);
-
+ size = xfs_attr_leaf_newentsize(args, local);
nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
if (*local) {
- if (size > (mp->m_sb.sb_blocksize >> 1)) {
+ if (size > (args->geo->blksize / 2)) {
/* Double split possible */
nblks *= 2;
}
@@ -213,7 +186,7 @@ xfs_attr_calc_size(
* Out of line attribute, cannot double split, but
* make room for the attribute value itself.
*/
- uint dblocks = xfs_attr3_rmt_blocks(mp, valuelen);
+ uint dblocks = xfs_attr3_rmt_blocks(mp, args->valuelen);
nblks += dblocks;
nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK);
}
@@ -221,26 +194,38 @@ xfs_attr_calc_size(
return nblks;
}
-STATIC int
-xfs_attr_set_int(
- struct xfs_inode *dp,
- struct xfs_name *name,
- unsigned char *value,
- int valuelen,
- int flags)
+int
+xfs_attr_set(
+ struct xfs_inode *dp,
+ const unsigned char *name,
+ unsigned char *value,
+ int valuelen,
+ int flags)
{
- xfs_da_args_t args;
- xfs_fsblock_t firstblock;
- xfs_bmap_free_t flist;
- int error, err2, committed;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_da_args args;
+ struct xfs_bmap_free flist;
struct xfs_trans_res tres;
+ xfs_fsblock_t firstblock;
int rsvd = (flags & ATTR_ROOT) != 0;
- int local;
+ int error, err2, committed, local;
+
+ XFS_STATS_INC(xs_attr_set);
+
+ if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+ return EIO;
+
+ error = xfs_attr_args_init(&args, dp, name, flags);
+ if (error)
+ return error;
+
+ args.value = value;
+ args.valuelen = valuelen;
+ args.firstblock = &firstblock;
+ args.flist = &flist;
+ args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+ args.total = xfs_attr_calc_size(&args, &local);
- /*
- * Attach the dquots to the inode.
- */
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
@@ -251,32 +236,14 @@ xfs_attr_set_int(
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
- XFS_ATTR_SF_ENTSIZE_BYNAME(name->len, valuelen);
+ XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
- if ((error = xfs_bmap_add_attrfork(dp, sf_size, rsvd)))
- return(error);
+ error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
+ if (error)
+ return error;
}
/*
- * Fill in the arg structure for this request.
- */
- memset((char *)&args, 0, sizeof(args));
- args.name = name->name;
- args.namelen = name->len;
- args.value = value;
- args.valuelen = valuelen;
- args.flags = flags;
- args.hashval = xfs_da_hashname(args.name, args.namelen);
- args.dp = dp;
- args.firstblock = &firstblock;
- args.flist = &flist;
- args.whichfork = XFS_ATTR_FORK;
- args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
-
- /* Size is now blocks for attribute data */
- args.total = xfs_attr_calc_size(dp, name->len, valuelen, &local);
-
- /*
* Start our first transaction of the day.
*
* All future transactions during this code must be "chained" off
@@ -303,7 +270,7 @@ xfs_attr_set_int(
error = xfs_trans_reserve(args.trans, &tres, args.total, 0);
if (error) {
xfs_trans_cancel(args.trans, 0);
- return(error);
+ return error;
}
xfs_ilock(dp, XFS_ILOCK_EXCL);
@@ -313,7 +280,7 @@ xfs_attr_set_int(
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans, XFS_TRANS_RELEASE_LOG_RES);
- return (error);
+ return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
@@ -322,9 +289,9 @@ xfs_attr_set_int(
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
- if ((dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) ||
- ((dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) &&
- (dp->i_d.di_anextents == 0))) {
+ if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
+ (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+ dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
@@ -349,9 +316,8 @@ xfs_attr_set_int(
* the transaction goes to disk before returning
* to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
- }
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
@@ -361,7 +327,7 @@ xfs_attr_set_int(
XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error == 0 ? err2 : error);
+ return error ? error : err2;
}
/*
@@ -399,22 +365,19 @@ xfs_attr_set_int(
}
- if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+ if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
- } else {
+ else
error = xfs_attr_node_addname(&args);
- }
- if (error) {
+ if (error)
goto out;
- }
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
- }
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
@@ -426,65 +389,47 @@ xfs_attr_set_int(
error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
out:
- if (args.trans)
+ if (args.trans) {
xfs_trans_cancel(args.trans,
XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
+ }
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
}
+/*
+ * Generic handler routine to remove a name from an attribute list.
+ * Transitions attribute list from Btree to shortform as necessary.
+ */
int
-xfs_attr_set(
- xfs_inode_t *dp,
- const unsigned char *name,
- unsigned char *value,
- int valuelen,
- int flags)
+xfs_attr_remove(
+ struct xfs_inode *dp,
+ const unsigned char *name,
+ int flags)
{
- int error;
- struct xfs_name xname;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_da_args args;
+ struct xfs_bmap_free flist;
+ xfs_fsblock_t firstblock;
+ int error;
- XFS_STATS_INC(xs_attr_set);
+ XFS_STATS_INC(xs_attr_remove);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return (EIO);
+ return EIO;
+
+ if (!xfs_inode_hasattr(dp))
+ return ENOATTR;
- error = xfs_attr_name_to_xname(&xname, name);
+ error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
- return xfs_attr_set_int(dp, &xname, value, valuelen, flags);
-}
-
-/*
- * Generic handler routine to remove a name from an attribute list.
- * Transitions attribute list from Btree to shortform as necessary.
- */
-STATIC int
-xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
-{
- xfs_da_args_t args;
- xfs_fsblock_t firstblock;
- xfs_bmap_free_t flist;
- int error;
- xfs_mount_t *mp = dp->i_mount;
-
- /*
- * Fill in the arg structure for this request.
- */
- memset((char *)&args, 0, sizeof(args));
- args.name = name->name;
- args.namelen = name->len;
- args.flags = flags;
- args.hashval = xfs_da_hashname(args.name, args.namelen);
- args.dp = dp;
args.firstblock = &firstblock;
args.flist = &flist;
- args.total = 0;
- args.whichfork = XFS_ATTR_FORK;
/*
* we have no control over the attribute names that userspace passes us
@@ -493,9 +438,6 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
*/
args.op_flags = XFS_DA_OP_OKNOENT;
- /*
- * Attach the dquots to the inode.
- */
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
@@ -524,7 +466,7 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
XFS_ATTRRM_SPACE_RES(mp), 0);
if (error) {
xfs_trans_cancel(args.trans, 0);
- return(error);
+ return error;
}
xfs_ilock(dp, XFS_ILOCK_EXCL);
@@ -534,35 +476,26 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
*/
xfs_trans_ijoin(args.trans, dp, 0);
- /*
- * Decide on what work routines to call based on the inode size.
- */
if (!xfs_inode_hasattr(dp)) {
error = XFS_ERROR(ENOATTR);
- goto out;
- }
- if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
error = xfs_attr_shortform_remove(&args);
- if (error) {
- goto out;
- }
} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
error = xfs_attr_leaf_removename(&args);
} else {
error = xfs_attr_node_removename(&args);
}
- if (error) {
+
+ if (error)
goto out;
- }
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
- }
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
@@ -574,45 +507,17 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
out:
- if (args.trans)
+ if (args.trans) {
xfs_trans_cancel(args.trans,
XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
-}
-
-int
-xfs_attr_remove(
- xfs_inode_t *dp,
- const unsigned char *name,
- int flags)
-{
- int error;
- struct xfs_name xname;
-
- XFS_STATS_INC(xs_attr_remove);
-
- if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return (EIO);
-
- error = xfs_attr_name_to_xname(&xname, name);
- if (error)
- return error;
-
- xfs_ilock(dp, XFS_ILOCK_SHARED);
- if (!xfs_inode_hasattr(dp)) {
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
- return XFS_ERROR(ENOATTR);
}
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
-
- return xfs_attr_remove_int(dp, &xname, flags);
+ xfs_iunlock(dp, XFS_ILOCK_EXCL);
+ return error;
}
-
/*========================================================================
* External routines when attribute list is inside the inode
*========================================================================*/
@@ -958,7 +863,7 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
}
/*========================================================================
- * External routines when attribute list size > XFS_LBSIZE(mp).
+ * External routines when attribute list size > geo->blksize
*========================================================================*/
/*
@@ -991,8 +896,6 @@ restart:
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
/*
* Search to see if name already exists, and get back a pointer
@@ -1170,8 +1073,6 @@ restart:
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
state->inleaf = 0;
error = xfs_da3_node_lookup_int(state, &retval);
if (error)
@@ -1262,8 +1163,6 @@ xfs_attr_node_removename(xfs_da_args_t *args)
state = xfs_da_state_alloc();
state->args = args;
state->mp = dp->i_mount;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
/*
* Search to see if name exists, and get back a pointer to it.
@@ -1525,8 +1424,6 @@ xfs_attr_node_get(xfs_da_args_t *args)
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
/*
* Search to see if name exists, and get back a pointer to it.
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 511c283459b1..28712d29e43c 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -80,11 +80,12 @@ STATIC int xfs_attr3_leaf_figure_balance(xfs_da_state_t *state,
/*
* Utility routines.
*/
-STATIC void xfs_attr3_leaf_moveents(struct xfs_attr_leafblock *src_leaf,
+STATIC void xfs_attr3_leaf_moveents(struct xfs_da_args *args,
+ struct xfs_attr_leafblock *src_leaf,
struct xfs_attr3_icleaf_hdr *src_ichdr, int src_start,
struct xfs_attr_leafblock *dst_leaf,
struct xfs_attr3_icleaf_hdr *dst_ichdr, int dst_start,
- int move_count, struct xfs_mount *mp);
+ int move_count);
STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index);
void
@@ -711,6 +712,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
memset((char *)&nargs, 0, sizeof(nargs));
nargs.dp = dp;
+ nargs.geo = args->geo;
nargs.firstblock = args->firstblock;
nargs.flist = args->flist;
nargs.total = args->total;
@@ -805,18 +807,18 @@ xfs_attr3_leaf_to_shortform(
trace_xfs_attr_leaf_to_sf(args);
- tmpbuffer = kmem_alloc(XFS_LBSIZE(dp->i_mount), KM_SLEEP);
+ tmpbuffer = kmem_alloc(args->geo->blksize, KM_SLEEP);
if (!tmpbuffer)
return ENOMEM;
- memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(dp->i_mount));
+ memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
leaf = (xfs_attr_leafblock_t *)tmpbuffer;
xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
entry = xfs_attr3_leaf_entryp(leaf);
/* XXX (dgc): buffer is about to be marked stale - why zero it? */
- memset(bp->b_addr, 0, XFS_LBSIZE(dp->i_mount));
+ memset(bp->b_addr, 0, args->geo->blksize);
/*
* Clean out the prior contents of the attribute list.
@@ -838,6 +840,7 @@ xfs_attr3_leaf_to_shortform(
* Copy the attributes
*/
memset((char *)&nargs, 0, sizeof(nargs));
+ nargs.geo = args->geo;
nargs.dp = dp;
nargs.firstblock = args->firstblock;
nargs.flist = args->flist;
@@ -904,12 +907,12 @@ xfs_attr3_leaf_to_node(
/* copy leaf to new buffer, update identifiers */
xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF);
bp2->b_ops = bp1->b_ops;
- memcpy(bp2->b_addr, bp1->b_addr, XFS_LBSIZE(mp));
+ memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize);
if (xfs_sb_version_hascrc(&mp->m_sb)) {
struct xfs_da3_blkinfo *hdr3 = bp2->b_addr;
hdr3->blkno = cpu_to_be64(bp2->b_bn);
}
- xfs_trans_log_buf(args->trans, bp2, 0, XFS_LBSIZE(mp) - 1);
+ xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1);
/*
* Set up the new root node.
@@ -930,7 +933,7 @@ xfs_attr3_leaf_to_node(
btree[0].before = cpu_to_be32(blkno);
icnodehdr.count = 1;
dp->d_ops->node_hdr_to_disk(node, &icnodehdr);
- xfs_trans_log_buf(args->trans, bp1, 0, XFS_LBSIZE(mp) - 1);
+ xfs_trans_log_buf(args->trans, bp1, 0, args->geo->blksize - 1);
error = 0;
out:
return error;
@@ -966,10 +969,10 @@ xfs_attr3_leaf_create(
bp->b_ops = &xfs_attr3_leaf_buf_ops;
xfs_trans_buf_set_type(args->trans, bp, XFS_BLFT_ATTR_LEAF_BUF);
leaf = bp->b_addr;
- memset(leaf, 0, XFS_LBSIZE(mp));
+ memset(leaf, 0, args->geo->blksize);
memset(&ichdr, 0, sizeof(ichdr));
- ichdr.firstused = XFS_LBSIZE(mp);
+ ichdr.firstused = args->geo->blksize;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
struct xfs_da3_blkinfo *hdr3 = bp->b_addr;
@@ -988,7 +991,7 @@ xfs_attr3_leaf_create(
ichdr.freemap[0].size = ichdr.firstused - ichdr.freemap[0].base;
xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr);
- xfs_trans_log_buf(args->trans, bp, 0, XFS_LBSIZE(mp) - 1);
+ xfs_trans_log_buf(args->trans, bp, 0, args->geo->blksize - 1);
*bpp = bp;
return 0;
@@ -1074,8 +1077,7 @@ xfs_attr3_leaf_add(
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
ASSERT(args->index >= 0 && args->index <= ichdr.count);
- entsize = xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
- args->trans->t_mountp->m_sb.sb_blocksize, NULL);
+ entsize = xfs_attr_leaf_newentsize(args, NULL);
/*
* Search through freemap for first-fit on new name length.
@@ -1174,17 +1176,14 @@ xfs_attr3_leaf_add_work(
* Allocate space for the new string (at the end of the run).
*/
mp = args->trans->t_mountp;
- ASSERT(ichdr->freemap[mapindex].base < XFS_LBSIZE(mp));
+ ASSERT(ichdr->freemap[mapindex].base < args->geo->blksize);
ASSERT((ichdr->freemap[mapindex].base & 0x3) == 0);
ASSERT(ichdr->freemap[mapindex].size >=
- xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
- mp->m_sb.sb_blocksize, NULL));
- ASSERT(ichdr->freemap[mapindex].size < XFS_LBSIZE(mp));
+ xfs_attr_leaf_newentsize(args, NULL));
+ ASSERT(ichdr->freemap[mapindex].size < args->geo->blksize);
ASSERT((ichdr->freemap[mapindex].size & 0x3) == 0);
- ichdr->freemap[mapindex].size -=
- xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
- mp->m_sb.sb_blocksize, &tmp);
+ ichdr->freemap[mapindex].size -= xfs_attr_leaf_newentsize(args, &tmp);
entry->nameidx = cpu_to_be16(ichdr->freemap[mapindex].base +
ichdr->freemap[mapindex].size);
@@ -1269,14 +1268,13 @@ xfs_attr3_leaf_compact(
struct xfs_attr_leafblock *leaf_dst;
struct xfs_attr3_icleaf_hdr ichdr_src;
struct xfs_trans *trans = args->trans;
- struct xfs_mount *mp = trans->t_mountp;
char *tmpbuffer;
trace_xfs_attr_leaf_compact(args);
- tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
- memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp));
- memset(bp->b_addr, 0, XFS_LBSIZE(mp));
+ tmpbuffer = kmem_alloc(args->geo->blksize, KM_SLEEP);
+ memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
+ memset(bp->b_addr, 0, args->geo->blksize);
leaf_src = (xfs_attr_leafblock_t *)tmpbuffer;
leaf_dst = bp->b_addr;
@@ -1289,7 +1287,7 @@ xfs_attr3_leaf_compact(
/* Initialise the incore headers */
ichdr_src = *ichdr_dst; /* struct copy */
- ichdr_dst->firstused = XFS_LBSIZE(mp);
+ ichdr_dst->firstused = args->geo->blksize;
ichdr_dst->usedbytes = 0;
ichdr_dst->count = 0;
ichdr_dst->holes = 0;
@@ -1304,13 +1302,13 @@ xfs_attr3_leaf_compact(
* Copy all entry's in the same (sorted) order,
* but allocate name/value pairs packed and in sequence.
*/
- xfs_attr3_leaf_moveents(leaf_src, &ichdr_src, 0, leaf_dst, ichdr_dst, 0,
- ichdr_src.count, mp);
+ xfs_attr3_leaf_moveents(args, leaf_src, &ichdr_src, 0,
+ leaf_dst, ichdr_dst, 0, ichdr_src.count);
/*
* this logs the entire buffer, but the caller must write the header
* back to the buffer when it is finished modifying it.
*/
- xfs_trans_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
+ xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1);
kmem_free(tmpbuffer);
}
@@ -1461,8 +1459,8 @@ xfs_attr3_leaf_rebalance(
/*
* Move high entries from leaf1 to low end of leaf2.
*/
- xfs_attr3_leaf_moveents(leaf1, &ichdr1, ichdr1.count - count,
- leaf2, &ichdr2, 0, count, state->mp);
+ xfs_attr3_leaf_moveents(args, leaf1, &ichdr1,
+ ichdr1.count - count, leaf2, &ichdr2, 0, count);
} else if (count > ichdr1.count) {
/*
@@ -1490,14 +1488,14 @@ xfs_attr3_leaf_rebalance(
/*
* Move low entries from leaf2 to high end of leaf1.
*/
- xfs_attr3_leaf_moveents(leaf2, &ichdr2, 0, leaf1, &ichdr1,
- ichdr1.count, count, state->mp);
+ xfs_attr3_leaf_moveents(args, leaf2, &ichdr2, 0, leaf1, &ichdr1,
+ ichdr1.count, count);
}
xfs_attr3_leaf_hdr_to_disk(leaf1, &ichdr1);
xfs_attr3_leaf_hdr_to_disk(leaf2, &ichdr2);
- xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
- xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+ xfs_trans_log_buf(args->trans, blk1->bp, 0, args->geo->blksize - 1);
+ xfs_trans_log_buf(args->trans, blk2->bp, 0, args->geo->blksize - 1);
/*
* Copy out last hashval in each block for B-tree code.
@@ -1592,11 +1590,9 @@ xfs_attr3_leaf_figure_balance(
max = ichdr1->count + ichdr2->count;
half = (max + 1) * sizeof(*entry);
half += ichdr1->usedbytes + ichdr2->usedbytes +
- xfs_attr_leaf_newentsize(state->args->namelen,
- state->args->valuelen,
- state->blocksize, NULL);
+ xfs_attr_leaf_newentsize(state->args, NULL);
half /= 2;
- lastdelta = state->blocksize;
+ lastdelta = state->args->geo->blksize;
entry = xfs_attr3_leaf_entryp(leaf1);
for (count = index = 0; count < max; entry++, index++, count++) {
@@ -1606,10 +1602,7 @@ xfs_attr3_leaf_figure_balance(
*/
if (count == blk1->index) {
tmp = totallen + sizeof(*entry) +
- xfs_attr_leaf_newentsize(
- state->args->namelen,
- state->args->valuelen,
- state->blocksize, NULL);
+ xfs_attr_leaf_newentsize(state->args, NULL);
if (XFS_ATTR_ABS(half - tmp) > lastdelta)
break;
lastdelta = XFS_ATTR_ABS(half - tmp);
@@ -1645,10 +1638,7 @@ xfs_attr3_leaf_figure_balance(
totallen -= count * sizeof(*entry);
if (foundit) {
totallen -= sizeof(*entry) +
- xfs_attr_leaf_newentsize(
- state->args->namelen,
- state->args->valuelen,
- state->blocksize, NULL);
+ xfs_attr_leaf_newentsize(state->args, NULL);
}
*countarg = count;
@@ -1700,7 +1690,7 @@ xfs_attr3_leaf_toosmall(
bytes = xfs_attr3_leaf_hdr_size(leaf) +
ichdr.count * sizeof(xfs_attr_leaf_entry_t) +
ichdr.usedbytes;
- if (bytes > (state->blocksize >> 1)) {
+ if (bytes > (state->args->geo->blksize >> 1)) {
*action = 0; /* blk over 50%, don't try to join */
return(0);
}
@@ -1754,7 +1744,8 @@ xfs_attr3_leaf_toosmall(
xfs_attr3_leaf_hdr_from_disk(&ichdr2, bp->b_addr);
- bytes = state->blocksize - (state->blocksize >> 2) -
+ bytes = state->args->geo->blksize -
+ (state->args->geo->blksize >> 2) -
ichdr.usedbytes - ichdr2.usedbytes -
((ichdr.count + ichdr2.count) *
sizeof(xfs_attr_leaf_entry_t)) -
@@ -1805,7 +1796,6 @@ xfs_attr3_leaf_remove(
struct xfs_attr_leafblock *leaf;
struct xfs_attr3_icleaf_hdr ichdr;
struct xfs_attr_leaf_entry *entry;
- struct xfs_mount *mp = args->trans->t_mountp;
int before;
int after;
int smallest;
@@ -1819,7 +1809,7 @@ xfs_attr3_leaf_remove(
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
- ASSERT(ichdr.count > 0 && ichdr.count < XFS_LBSIZE(mp) / 8);
+ ASSERT(ichdr.count > 0 && ichdr.count < args->geo->blksize / 8);
ASSERT(args->index >= 0 && args->index < ichdr.count);
ASSERT(ichdr.firstused >= ichdr.count * sizeof(*entry) +
xfs_attr3_leaf_hdr_size(leaf));
@@ -1827,7 +1817,7 @@ xfs_attr3_leaf_remove(
entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused);
- ASSERT(be16_to_cpu(entry->nameidx) < XFS_LBSIZE(mp));
+ ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize);
/*
* Scan through free region table:
@@ -1842,8 +1832,8 @@ xfs_attr3_leaf_remove(
smallest = XFS_ATTR_LEAF_MAPSIZE - 1;
entsize = xfs_attr_leaf_entsize(leaf, args->index);
for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
- ASSERT(ichdr.freemap[i].base < XFS_LBSIZE(mp));
- ASSERT(ichdr.freemap[i].size < XFS_LBSIZE(mp));
+ ASSERT(ichdr.freemap[i].base < args->geo->blksize);
+ ASSERT(ichdr.freemap[i].size < args->geo->blksize);
if (ichdr.freemap[i].base == tablesize) {
ichdr.freemap[i].base -= sizeof(xfs_attr_leaf_entry_t);
ichdr.freemap[i].size += sizeof(xfs_attr_leaf_entry_t);
@@ -1920,11 +1910,11 @@ xfs_attr3_leaf_remove(
* removing the name.
*/
if (smallest) {
- tmp = XFS_LBSIZE(mp);
+ tmp = args->geo->blksize;
entry = xfs_attr3_leaf_entryp(leaf);
for (i = ichdr.count - 1; i >= 0; entry++, i--) {
ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused);
- ASSERT(be16_to_cpu(entry->nameidx) < XFS_LBSIZE(mp));
+ ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize);
if (be16_to_cpu(entry->nameidx) < tmp)
tmp = be16_to_cpu(entry->nameidx);
@@ -1947,7 +1937,7 @@ xfs_attr3_leaf_remove(
tmp = ichdr.usedbytes + xfs_attr3_leaf_hdr_size(leaf) +
ichdr.count * sizeof(xfs_attr_leaf_entry_t);
- return tmp < mp->m_attr_magicpct; /* leaf is < 37% full */
+ return tmp < args->geo->magicpct; /* leaf is < 37% full */
}
/*
@@ -1964,7 +1954,6 @@ xfs_attr3_leaf_unbalance(
struct xfs_attr3_icleaf_hdr drophdr;
struct xfs_attr3_icleaf_hdr savehdr;
struct xfs_attr_leaf_entry *entry;
- struct xfs_mount *mp = state->mp;
trace_xfs_attr_leaf_unbalance(state->args);
@@ -1991,13 +1980,15 @@ xfs_attr3_leaf_unbalance(
*/
if (xfs_attr3_leaf_order(save_blk->bp, &savehdr,
drop_blk->bp, &drophdr)) {
- xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
save_leaf, &savehdr, 0,
- drophdr.count, mp);
+ drophdr.count);
} else {
- xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
save_leaf, &savehdr,
- savehdr.count, drophdr.count, mp);
+ savehdr.count, drophdr.count);
}
} else {
/*
@@ -2007,7 +1998,7 @@ xfs_attr3_leaf_unbalance(
struct xfs_attr_leafblock *tmp_leaf;
struct xfs_attr3_icleaf_hdr tmphdr;
- tmp_leaf = kmem_zalloc(state->blocksize, KM_SLEEP);
+ tmp_leaf = kmem_zalloc(state->args->geo->blksize, KM_SLEEP);
/*
* Copy the header into the temp leaf so that all the stuff
@@ -2020,35 +2011,39 @@ xfs_attr3_leaf_unbalance(
tmphdr.magic = savehdr.magic;
tmphdr.forw = savehdr.forw;
tmphdr.back = savehdr.back;
- tmphdr.firstused = state->blocksize;
+ tmphdr.firstused = state->args->geo->blksize;
/* write the header to the temp buffer to initialise it */
xfs_attr3_leaf_hdr_to_disk(tmp_leaf, &tmphdr);
if (xfs_attr3_leaf_order(save_blk->bp, &savehdr,
drop_blk->bp, &drophdr)) {
- xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
tmp_leaf, &tmphdr, 0,
- drophdr.count, mp);
- xfs_attr3_leaf_moveents(save_leaf, &savehdr, 0,
+ drophdr.count);
+ xfs_attr3_leaf_moveents(state->args,
+ save_leaf, &savehdr, 0,
tmp_leaf, &tmphdr, tmphdr.count,
- savehdr.count, mp);
+ savehdr.count);
} else {
- xfs_attr3_leaf_moveents(save_leaf, &savehdr, 0,
+ xfs_attr3_leaf_moveents(state->args,
+ save_leaf, &savehdr, 0,
tmp_leaf, &tmphdr, 0,
- savehdr.count, mp);
- xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+ savehdr.count);
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
tmp_leaf, &tmphdr, tmphdr.count,
- drophdr.count, mp);
+ drophdr.count);
}
- memcpy(save_leaf, tmp_leaf, state->blocksize);
+ memcpy(save_leaf, tmp_leaf, state->args->geo->blksize);
savehdr = tmphdr; /* struct copy */
kmem_free(tmp_leaf);
}
xfs_attr3_leaf_hdr_to_disk(save_leaf, &savehdr);
xfs_trans_log_buf(state->args->trans, save_blk->bp, 0,
- state->blocksize - 1);
+ state->args->geo->blksize - 1);
/*
* Copy out last hashval in each block for B-tree code.
@@ -2094,7 +2089,7 @@ xfs_attr3_leaf_lookup_int(
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
entries = xfs_attr3_leaf_entryp(leaf);
- ASSERT(ichdr.count < XFS_LBSIZE(args->dp->i_mount) / 8);
+ ASSERT(ichdr.count < args->geo->blksize / 8);
/*
* Binary search. (note: small blocks will skip this loop)
@@ -2198,7 +2193,7 @@ xfs_attr3_leaf_getvalue(
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
- ASSERT(ichdr.count < XFS_LBSIZE(args->dp->i_mount) / 8);
+ ASSERT(ichdr.count < args->geo->blksize / 8);
ASSERT(args->index < ichdr.count);
entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
@@ -2249,14 +2244,14 @@ xfs_attr3_leaf_getvalue(
/*ARGSUSED*/
STATIC void
xfs_attr3_leaf_moveents(
+ struct xfs_da_args *args,
struct xfs_attr_leafblock *leaf_s,
struct xfs_attr3_icleaf_hdr *ichdr_s,
int start_s,
struct xfs_attr_leafblock *leaf_d,
struct xfs_attr3_icleaf_hdr *ichdr_d,
int start_d,
- int count,
- struct xfs_mount *mp)
+ int count)
{
struct xfs_attr_leaf_entry *entry_s;
struct xfs_attr_leaf_entry *entry_d;
@@ -2276,10 +2271,10 @@ xfs_attr3_leaf_moveents(
ASSERT(ichdr_s->magic == XFS_ATTR_LEAF_MAGIC ||
ichdr_s->magic == XFS_ATTR3_LEAF_MAGIC);
ASSERT(ichdr_s->magic == ichdr_d->magic);
- ASSERT(ichdr_s->count > 0 && ichdr_s->count < XFS_LBSIZE(mp) / 8);
+ ASSERT(ichdr_s->count > 0 && ichdr_s->count < args->geo->blksize / 8);
ASSERT(ichdr_s->firstused >= (ichdr_s->count * sizeof(*entry_s))
+ xfs_attr3_leaf_hdr_size(leaf_s));
- ASSERT(ichdr_d->count < XFS_LBSIZE(mp) / 8);
+ ASSERT(ichdr_d->count < args->geo->blksize / 8);
ASSERT(ichdr_d->firstused >= (ichdr_d->count * sizeof(*entry_d))
+ xfs_attr3_leaf_hdr_size(leaf_d));
@@ -2331,11 +2326,11 @@ xfs_attr3_leaf_moveents(
entry_d->nameidx = cpu_to_be16(ichdr_d->firstused);
entry_d->flags = entry_s->flags;
ASSERT(be16_to_cpu(entry_d->nameidx) + tmp
- <= XFS_LBSIZE(mp));
+ <= args->geo->blksize);
memmove(xfs_attr3_leaf_name(leaf_d, desti),
xfs_attr3_leaf_name(leaf_s, start_s + i), tmp);
ASSERT(be16_to_cpu(entry_s->nameidx) + tmp
- <= XFS_LBSIZE(mp));
+ <= args->geo->blksize);
memset(xfs_attr3_leaf_name(leaf_s, start_s + i), 0, tmp);
ichdr_s->usedbytes -= tmp;
ichdr_d->usedbytes += tmp;
@@ -2356,7 +2351,7 @@ xfs_attr3_leaf_moveents(
tmp = count * sizeof(xfs_attr_leaf_entry_t);
entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s];
ASSERT(((char *)entry_s + tmp) <=
- ((char *)leaf_s + XFS_LBSIZE(mp)));
+ ((char *)leaf_s + args->geo->blksize));
memset(entry_s, 0, tmp);
} else {
/*
@@ -2371,7 +2366,7 @@ xfs_attr3_leaf_moveents(
tmp = count * sizeof(xfs_attr_leaf_entry_t);
entry_s = &xfs_attr3_leaf_entryp(leaf_s)[ichdr_s->count];
ASSERT(((char *)entry_s + tmp) <=
- ((char *)leaf_s + XFS_LBSIZE(mp)));
+ ((char *)leaf_s + args->geo->blksize));
memset(entry_s, 0, tmp);
}
@@ -2439,22 +2434,21 @@ xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index)
* a "local" or a "remote" attribute.
*/
int
-xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local)
+xfs_attr_leaf_newentsize(
+ struct xfs_da_args *args,
+ int *local)
{
- int size;
+ int size;
- size = xfs_attr_leaf_entsize_local(namelen, valuelen);
- if (size < xfs_attr_leaf_entsize_local_max(blocksize)) {
- if (local) {
+ size = xfs_attr_leaf_entsize_local(args->namelen, args->valuelen);
+ if (size < xfs_attr_leaf_entsize_local_max(args->geo->blksize)) {
+ if (local)
*local = 1;
- }
- } else {
- size = xfs_attr_leaf_entsize_remote(namelen);
- if (local) {
- *local = 0;
- }
+ return size;
}
- return size;
+ if (local)
+ *local = 0;
+ return xfs_attr_leaf_entsize_remote(args->namelen);
}
diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h
index 3ec5ec0b8678..e2929da7c3ba 100644
--- a/fs/xfs/xfs_attr_leaf.h
+++ b/fs/xfs/xfs_attr_leaf.h
@@ -96,8 +96,7 @@ int xfs_attr3_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
xfs_dahash_t xfs_attr_leaf_lasthash(struct xfs_buf *bp, int *count);
int xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
struct xfs_buf *leaf2_bp);
-int xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize,
- int *local);
+int xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local);
int xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mappedbno,
struct xfs_buf **bpp);
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 833fe5d98d80..90e2eeb21207 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -444,6 +444,7 @@ xfs_attr3_leaf_list_int(
xfs_da_args_t args;
memset((char *)&args, 0, sizeof(args));
+ args.geo = context->dp->i_mount->m_attr_geo;
args.dp = context->dp;
args.whichfork = XFS_ATTR_FORK;
args.valuelen = valuelen;
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index d2e6e948cec7..b5adfecbb8ee 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -68,7 +68,6 @@ xfs_attr3_rmt_blocks(
*/
static bool
xfs_attr3_rmt_hdr_ok(
- struct xfs_mount *mp,
void *ptr,
xfs_ino_t ino,
uint32_t offset,
@@ -126,6 +125,7 @@ xfs_attr3_rmt_read_verify(
char *ptr;
int len;
xfs_daddr_t bno;
+ int blksize = mp->m_attr_geo->blksize;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -134,21 +134,20 @@ xfs_attr3_rmt_read_verify(
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
- ASSERT(len >= XFS_LBSIZE(mp));
+ ASSERT(len >= blksize);
while (len > 0) {
- if (!xfs_verify_cksum(ptr, XFS_LBSIZE(mp),
- XFS_ATTR3_RMT_CRC_OFF)) {
+ if (!xfs_verify_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF)) {
xfs_buf_ioerror(bp, EFSBADCRC);
break;
}
- if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
+ if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, EFSCORRUPTED);
break;
}
- len -= XFS_LBSIZE(mp);
- ptr += XFS_LBSIZE(mp);
- bno += mp->m_bsize;
+ len -= blksize;
+ ptr += blksize;
+ bno += BTOBB(blksize);
}
if (bp->b_error)
@@ -166,6 +165,7 @@ xfs_attr3_rmt_write_verify(
char *ptr;
int len;
xfs_daddr_t bno;
+ int blksize = mp->m_attr_geo->blksize;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -174,10 +174,10 @@ xfs_attr3_rmt_write_verify(
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
- ASSERT(len >= XFS_LBSIZE(mp));
+ ASSERT(len >= blksize);
while (len > 0) {
- if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
+ if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, EFSCORRUPTED);
xfs_verifier_error(bp);
return;
@@ -188,11 +188,11 @@ xfs_attr3_rmt_write_verify(
rmt = (struct xfs_attr3_rmt_hdr *)ptr;
rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
}
- xfs_update_cksum(ptr, XFS_LBSIZE(mp), XFS_ATTR3_RMT_CRC_OFF);
+ xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
- len -= XFS_LBSIZE(mp);
- ptr += XFS_LBSIZE(mp);
- bno += mp->m_bsize;
+ len -= blksize;
+ ptr += blksize;
+ bno += BTOBB(blksize);
}
ASSERT(len == 0);
}
@@ -241,17 +241,18 @@ xfs_attr_rmtval_copyout(
char *src = bp->b_addr;
xfs_daddr_t bno = bp->b_bn;
int len = BBTOB(bp->b_length);
+ int blksize = mp->m_attr_geo->blksize;
- ASSERT(len >= XFS_LBSIZE(mp));
+ ASSERT(len >= blksize);
while (len > 0 && *valuelen > 0) {
int hdr_size = 0;
- int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp));
+ int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
byte_cnt = min(*valuelen, byte_cnt);
if (xfs_sb_version_hascrc(&mp->m_sb)) {
- if (!xfs_attr3_rmt_hdr_ok(mp, src, ino, *offset,
+ if (!xfs_attr3_rmt_hdr_ok(src, ino, *offset,
byte_cnt, bno)) {
xfs_alert(mp,
"remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
@@ -264,9 +265,9 @@ xfs_attr_rmtval_copyout(
memcpy(*dst, src + hdr_size, byte_cnt);
/* roll buffer forwards */
- len -= XFS_LBSIZE(mp);
- src += XFS_LBSIZE(mp);
- bno += mp->m_bsize;
+ len -= blksize;
+ src += blksize;
+ bno += BTOBB(blksize);
/* roll attribute data forwards */
*valuelen -= byte_cnt;
@@ -288,12 +289,13 @@ xfs_attr_rmtval_copyin(
char *dst = bp->b_addr;
xfs_daddr_t bno = bp->b_bn;
int len = BBTOB(bp->b_length);
+ int blksize = mp->m_attr_geo->blksize;
- ASSERT(len >= XFS_LBSIZE(mp));
+ ASSERT(len >= blksize);
while (len > 0 && *valuelen > 0) {
int hdr_size;
- int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp));
+ int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
byte_cnt = min(*valuelen, byte_cnt);
hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset,
@@ -305,17 +307,17 @@ xfs_attr_rmtval_copyin(
* If this is the last block, zero the remainder of it.
* Check that we are actually the last block, too.
*/
- if (byte_cnt + hdr_size < XFS_LBSIZE(mp)) {
+ if (byte_cnt + hdr_size < blksize) {
ASSERT(*valuelen - byte_cnt == 0);
- ASSERT(len == XFS_LBSIZE(mp));
+ ASSERT(len == blksize);
memset(dst + hdr_size + byte_cnt, 0,
- XFS_LBSIZE(mp) - hdr_size - byte_cnt);
+ blksize - hdr_size - byte_cnt);
}
/* roll buffer forwards */
- len -= XFS_LBSIZE(mp);
- dst += XFS_LBSIZE(mp);
- bno += mp->m_bsize;
+ len -= blksize;
+ dst += blksize;
+ bno += BTOBB(blksize);
/* roll attribute data forwards */
*valuelen -= byte_cnt;
diff --git a/fs/xfs/xfs_bit.h b/fs/xfs/xfs_bit.h
index f1e3c907044d..e1649c0d3e02 100644
--- a/fs/xfs/xfs_bit.h
+++ b/fs/xfs/xfs_bit.h
@@ -66,8 +66,11 @@ static inline int xfs_lowbit64(__uint64_t v)
n = ffs(w);
} else { /* upper bits */
w = (__uint32_t)(v >> 32);
- if (w && (n = ffs(w)))
- n += 32;
+ if (w) {
+ n = ffs(w);
+ if (n)
+ n += 32;
+ }
}
return n - 1;
}
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index f0efc7e970ef..96175df211b1 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -94,7 +94,7 @@ xfs_bmap_compute_maxlevels(
maxleafents = MAXAEXTNUM;
sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
}
- maxrootrecs = xfs_bmdr_maxrecs(mp, sz, 0);
+ maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
minleafrecs = mp->m_bmap_dmnr[0];
minnoderecs = mp->m_bmap_dmnr[1];
maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
@@ -233,7 +233,6 @@ xfs_default_attroffset(
*/
STATIC void
xfs_bmap_forkoff_reset(
- xfs_mount_t *mp,
xfs_inode_t *ip,
int whichfork)
{
@@ -905,7 +904,7 @@ xfs_bmap_local_to_extents_empty(
ASSERT(ifp->if_bytes == 0);
ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0);
- xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork);
+ xfs_bmap_forkoff_reset(ip, whichfork);
ifp->if_flags &= ~XFS_IFINLINE;
ifp->if_flags |= XFS_IFEXTENTS;
XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
@@ -1099,10 +1098,11 @@ xfs_bmap_add_attrfork_local(
if (S_ISDIR(ip->i_d.di_mode)) {
memset(&dargs, 0, sizeof(dargs));
+ dargs.geo = ip->i_mount->m_dir_geo;
dargs.dp = ip;
dargs.firstblock = firstblock;
dargs.flist = flist;
- dargs.total = ip->i_mount->m_dirblkfsbs;
+ dargs.total = dargs.geo->fsbcount;
dargs.whichfork = XFS_DATA_FORK;
dargs.trans = tp;
return xfs_dir2_sf_to_block(&dargs);
@@ -1675,7 +1675,6 @@ xfs_bmap_isaeof(
*/
int
xfs_bmap_last_offset(
- struct xfs_trans *tp,
struct xfs_inode *ip,
xfs_fileoff_t *last_block,
int whichfork)
@@ -3517,6 +3516,67 @@ xfs_bmap_adjacent(
#undef ISVALID
}
+static int
+xfs_bmap_longest_free_extent(
+ struct xfs_trans *tp,
+ xfs_agnumber_t ag,
+ xfs_extlen_t *blen,
+ int *notinit)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_perag *pag;
+ xfs_extlen_t longest;
+ int error = 0;
+
+ pag = xfs_perag_get(mp, ag);
+ if (!pag->pagf_init) {
+ error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK);
+ if (error)
+ goto out;
+
+ if (!pag->pagf_init) {
+ *notinit = 1;
+ goto out;
+ }
+ }
+
+ longest = xfs_alloc_longest_free_extent(mp, pag);
+ if (*blen < longest)
+ *blen = longest;
+
+out:
+ xfs_perag_put(pag);
+ return error;
+}
+
+static void
+xfs_bmap_select_minlen(
+ struct xfs_bmalloca *ap,
+ struct xfs_alloc_arg *args,
+ xfs_extlen_t *blen,
+ int notinit)
+{
+ if (notinit || *blen < ap->minlen) {
+ /*
+ * Since we did a BUF_TRYLOCK above, it is possible that
+ * there is space for this request.
+ */
+ args->minlen = ap->minlen;
+ } else if (*blen < args->maxlen) {
+ /*
+ * If the best seen length is less than the request length,
+ * use the best as the minimum.
+ */
+ args->minlen = *blen;
+ } else {
+ /*
+ * Otherwise we've seen an extent as big as maxlen, use that
+ * as the minimum.
+ */
+ args->minlen = args->maxlen;
+ }
+}
+
STATIC int
xfs_bmap_btalloc_nullfb(
struct xfs_bmalloca *ap,
@@ -3524,111 +3584,74 @@ xfs_bmap_btalloc_nullfb(
xfs_extlen_t *blen)
{
struct xfs_mount *mp = ap->ip->i_mount;
- struct xfs_perag *pag;
xfs_agnumber_t ag, startag;
int notinit = 0;
int error;
- if (ap->userdata && xfs_inode_is_filestream(ap->ip))
- args->type = XFS_ALLOCTYPE_NEAR_BNO;
- else
- args->type = XFS_ALLOCTYPE_START_BNO;
+ args->type = XFS_ALLOCTYPE_START_BNO;
args->total = ap->total;
- /*
- * Search for an allocation group with a single extent large enough
- * for the request. If one isn't found, then adjust the minimum
- * allocation size to the largest space found.
- */
startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
if (startag == NULLAGNUMBER)
startag = ag = 0;
- pag = xfs_perag_get(mp, ag);
while (*blen < args->maxlen) {
- if (!pag->pagf_init) {
- error = xfs_alloc_pagf_init(mp, args->tp, ag,
- XFS_ALLOC_FLAG_TRYLOCK);
- if (error) {
- xfs_perag_put(pag);
- return error;
- }
- }
-
- /*
- * See xfs_alloc_fix_freelist...
- */
- if (pag->pagf_init) {
- xfs_extlen_t longest;
- longest = xfs_alloc_longest_free_extent(mp, pag);
- if (*blen < longest)
- *blen = longest;
- } else
- notinit = 1;
-
- if (xfs_inode_is_filestream(ap->ip)) {
- if (*blen >= args->maxlen)
- break;
-
- if (ap->userdata) {
- /*
- * If startag is an invalid AG, we've
- * come here once before and
- * xfs_filestream_new_ag picked the
- * best currently available.
- *
- * Don't continue looping, since we
- * could loop forever.
- */
- if (startag == NULLAGNUMBER)
- break;
-
- error = xfs_filestream_new_ag(ap, &ag);
- xfs_perag_put(pag);
- if (error)
- return error;
+ error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
+ &notinit);
+ if (error)
+ return error;
- /* loop again to set 'blen'*/
- startag = NULLAGNUMBER;
- pag = xfs_perag_get(mp, ag);
- continue;
- }
- }
if (++ag == mp->m_sb.sb_agcount)
ag = 0;
if (ag == startag)
break;
- xfs_perag_put(pag);
- pag = xfs_perag_get(mp, ag);
}
- xfs_perag_put(pag);
- /*
- * Since the above loop did a BUF_TRYLOCK, it is
- * possible that there is space for this request.
- */
- if (notinit || *blen < ap->minlen)
- args->minlen = ap->minlen;
- /*
- * If the best seen length is less than the request
- * length, use the best as the minimum.
- */
- else if (*blen < args->maxlen)
- args->minlen = *blen;
- /*
- * Otherwise we've seen an extent as big as maxlen,
- * use that as the minimum.
- */
- else
- args->minlen = args->maxlen;
+ xfs_bmap_select_minlen(ap, args, blen, notinit);
+ return 0;
+}
+
+STATIC int
+xfs_bmap_btalloc_filestreams(
+ struct xfs_bmalloca *ap,
+ struct xfs_alloc_arg *args,
+ xfs_extlen_t *blen)
+{
+ struct xfs_mount *mp = ap->ip->i_mount;
+ xfs_agnumber_t ag;
+ int notinit = 0;
+ int error;
+
+ args->type = XFS_ALLOCTYPE_NEAR_BNO;
+ args->total = ap->total;
+
+ ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
+ if (ag == NULLAGNUMBER)
+ ag = 0;
+
+ error = xfs_bmap_longest_free_extent(args->tp, ag, blen, &notinit);
+ if (error)
+ return error;
+
+ if (*blen < args->maxlen) {
+ error = xfs_filestream_new_ag(ap, &ag);
+ if (error)
+ return error;
+
+ error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
+ &notinit);
+ if (error)
+ return error;
+
+ }
+
+ xfs_bmap_select_minlen(ap, args, blen, notinit);
/*
- * set the failure fallback case to look in the selected
- * AG as the stream may have moved.
+ * Set the failure fallback case to look in the selected AG as stream
+ * may have moved.
*/
- if (xfs_inode_is_filestream(ap->ip))
- ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
-
+ ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
return 0;
}
@@ -3708,7 +3731,15 @@ xfs_bmap_btalloc(
args.firstblock = *ap->firstblock;
blen = 0;
if (nullfb) {
- error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
+ /*
+ * Search for an allocation group with a single extent large
+ * enough for the request. If one isn't found, then adjust
+ * the minimum allocation size to the largest space found.
+ */
+ if (ap->userdata && xfs_inode_is_filestream(ap->ip))
+ error = xfs_bmap_btalloc_filestreams(ap, &args, &blen);
+ else
+ error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
if (error)
return error;
} else if (ap->flist->xbf_low) {
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index f84bd7af43be..38ba36e9b2f0 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -156,8 +156,8 @@ int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
int xfs_bmap_last_before(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *last_block, int whichfork);
-int xfs_bmap_last_offset(struct xfs_trans *tp, struct xfs_inode *ip,
- xfs_fileoff_t *unused, int whichfork);
+int xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
+ int whichfork);
int xfs_bmap_one_block(struct xfs_inode *ip, int whichfork);
int xfs_bmap_read_extents(struct xfs_trans *tp, struct xfs_inode *ip,
int whichfork);
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index 818d546664e7..948836c4fd90 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -84,7 +84,7 @@ xfs_bmdr_to_bmbt(
rblock->bb_level = dblock->bb_level;
ASSERT(be16_to_cpu(rblock->bb_level) > 0);
rblock->bb_numrecs = dblock->bb_numrecs;
- dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+ dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
@@ -443,7 +443,7 @@ xfs_bmbt_to_bmdr(
ASSERT(rblock->bb_level != 0);
dblock->bb_level = rblock->bb_level;
dblock->bb_numrecs = rblock->bb_numrecs;
- dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+ dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
@@ -519,7 +519,6 @@ xfs_bmbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
- int length,
int *stat)
{
xfs_alloc_arg_t args; /* block allocation args */
@@ -672,8 +671,7 @@ xfs_bmbt_get_dmaxrecs(
{
if (level != cur->bc_nlevels - 1)
return cur->bc_mp->m_bmap_dmxr[level != 0];
- return xfs_bmdr_maxrecs(cur->bc_mp, cur->bc_private.b.forksize,
- level == 0);
+ return xfs_bmdr_maxrecs(cur->bc_private.b.forksize, level == 0);
}
STATIC void
@@ -914,7 +912,6 @@ xfs_bmbt_maxrecs(
*/
int
xfs_bmdr_maxrecs(
- struct xfs_mount *mp,
int blocklen,
int leaf)
{
diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h
index 6e42e1e50b89..819a8a4dee95 100644
--- a/fs/xfs/xfs_bmap_btree.h
+++ b/fs/xfs/xfs_bmap_btree.h
@@ -130,7 +130,7 @@ extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int,
xfs_bmdr_block_t *, int);
extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level);
-extern int xfs_bmdr_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+extern int xfs_bmdr_maxrecs(int blocklen, int leaf);
extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 296160b8e78c..703b3ec1796c 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -258,14 +258,23 @@ xfs_bmapi_allocate_worker(
struct xfs_bmalloca *args = container_of(work,
struct xfs_bmalloca, work);
unsigned long pflags;
+ unsigned long new_pflags = PF_FSTRANS;
- /* we are in a transaction context here */
- current_set_flags_nested(&pflags, PF_FSTRANS);
+ /*
+ * we are in a transaction context here, but may also be doing work
+ * in kswapd context, and hence we may need to inherit that state
+ * temporarily to ensure that we don't block waiting for memory reclaim
+ * in any way.
+ */
+ if (args->kswapd)
+ new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+ current_set_flags_nested(&pflags, new_pflags);
args->result = __xfs_bmapi_allocate(args);
complete(args->done);
- current_restore_flags_nested(&pflags, PF_FSTRANS);
+ current_restore_flags_nested(&pflags, new_pflags);
}
/*
@@ -284,6 +293,7 @@ xfs_bmapi_allocate(
args->done = &done;
+ args->kswapd = current_is_kswapd();
INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
queue_work(xfs_alloc_wq, &args->work);
wait_for_completion(&done);
@@ -1519,7 +1529,6 @@ xfs_collapse_file_space(
while (!error && !done) {
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
- tp->t_flags |= XFS_TRANS_RESERVE;
/*
* We would need to reserve permanent block for transaction.
* This will come into picture when after shifting extent into
@@ -1529,7 +1538,6 @@ xfs_collapse_file_space(
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
if (error) {
- ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 935ed2b24edf..075f72232a64 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -50,12 +50,13 @@ struct xfs_bmalloca {
xfs_extlen_t total; /* total blocks needed for xaction */
xfs_extlen_t minlen; /* minimum allocation size (blocks) */
xfs_extlen_t minleft; /* amount must be left after alloc */
- char eof; /* set if allocating past last extent */
- char wasdel; /* replacing a delayed allocation */
- char userdata;/* set if is user data */
- char aeof; /* allocated space at eof */
- char conv; /* overwriting unwritten extents */
- char stack_switch;
+ bool eof; /* set if allocating past last extent */
+ bool wasdel; /* replacing a delayed allocation */
+ bool userdata;/* set if is user data */
+ bool aeof; /* allocated space at eof */
+ bool conv; /* overwriting unwritten extents */
+ bool stack_switch;
+ bool kswapd; /* allocation in kswapd context */
int flags;
struct completion *done;
struct work_struct work;
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e80d59fdf89a..bf810c6baf2b 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -43,9 +43,10 @@ kmem_zone_t *xfs_btree_cur_zone;
* Btree magic numbers.
*/
static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
- { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC },
+ { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
+ XFS_FIBT_MAGIC },
{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC,
- XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC }
+ XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC }
};
#define xfs_btree_magic(cur) \
xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
@@ -552,14 +553,11 @@ xfs_btree_get_bufl(
xfs_fsblock_t fsbno, /* file system block number */
uint lock) /* lock flags for get_buf */
{
- xfs_buf_t *bp; /* buffer pointer (return value) */
xfs_daddr_t d; /* real disk block address */
ASSERT(fsbno != NULLFSBLOCK);
d = XFS_FSB_TO_DADDR(mp, fsbno);
- bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
- ASSERT(!xfs_buf_geterror(bp));
- return bp;
+ return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
}
/*
@@ -574,15 +572,12 @@ xfs_btree_get_bufs(
xfs_agblock_t agbno, /* allocation group block number */
uint lock) /* lock flags for get_buf */
{
- xfs_buf_t *bp; /* buffer pointer (return value) */
xfs_daddr_t d; /* real disk block address */
ASSERT(agno != NULLAGNUMBER);
ASSERT(agbno != NULLAGBLOCK);
d = XFS_AGB_TO_DADDR(mp, agno, agbno);
- bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
- ASSERT(!xfs_buf_geterror(bp));
- return bp;
+ return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
}
/*
@@ -722,7 +717,6 @@ xfs_btree_read_bufl(
mp->m_bsize, lock, &bp, ops);
if (error)
return error;
- ASSERT(!xfs_buf_geterror(bp));
if (bp)
xfs_buf_set_ref(bp, refval);
*bpp = bp;
@@ -1115,6 +1109,7 @@ xfs_btree_set_refs(
xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
break;
case XFS_BTNUM_INO:
+ case XFS_BTNUM_FINO:
xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
break;
case XFS_BTNUM_BMAP:
@@ -1159,7 +1154,6 @@ STATIC int
xfs_btree_read_buf_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr,
- int level,
int flags,
struct xfs_btree_block **block,
struct xfs_buf **bpp)
@@ -1178,7 +1172,6 @@ xfs_btree_read_buf_block(
if (error)
return error;
- ASSERT(!xfs_buf_geterror(*bpp));
xfs_btree_set_refs(cur, *bpp);
*block = XFS_BUF_TO_BLOCK(*bpp);
return 0;
@@ -1517,8 +1510,8 @@ xfs_btree_increment(
union xfs_btree_ptr *ptrp;
ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
- error = xfs_btree_read_buf_block(cur, ptrp, --lev,
- 0, &block, &bp);
+ --lev;
+ error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
@@ -1616,8 +1609,8 @@ xfs_btree_decrement(
union xfs_btree_ptr *ptrp;
ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
- error = xfs_btree_read_buf_block(cur, ptrp, --lev,
- 0, &block, &bp);
+ --lev;
+ error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
xfs_btree_setbuf(cur, lev, bp);
@@ -1667,7 +1660,7 @@ xfs_btree_lookup_get_block(
return 0;
}
- error = xfs_btree_read_buf_block(cur, pp, level, 0, blkp, &bp);
+ error = xfs_btree_read_buf_block(cur, pp, 0, blkp, &bp);
if (error)
return error;
@@ -2018,7 +2011,7 @@ xfs_btree_lshift(
goto out0;
/* Set up the left neighbor as "left". */
- error = xfs_btree_read_buf_block(cur, &lptr, level, 0, &left, &lbp);
+ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
if (error)
goto error0;
@@ -2202,7 +2195,7 @@ xfs_btree_rshift(
goto out0;
/* Set up the right neighbor as "right". */
- error = xfs_btree_read_buf_block(cur, &rptr, level, 0, &right, &rbp);
+ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
if (error)
goto error0;
@@ -2372,7 +2365,7 @@ xfs_btree_split(
xfs_btree_buf_to_ptr(cur, lbp, &lptr);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, 1, stat);
+ error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -2470,7 +2463,7 @@ xfs_btree_split(
* point back to right instead of to left.
*/
if (!xfs_btree_ptr_is_null(cur, &rrptr)) {
- error = xfs_btree_read_buf_block(cur, &rrptr, level,
+ error = xfs_btree_read_buf_block(cur, &rrptr,
0, &rrblock, &rrbp);
if (error)
goto error0;
@@ -2545,7 +2538,7 @@ xfs_btree_new_iroot(
pp = xfs_btree_ptr_addr(cur, 1, block);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, pp, &nptr, 1, stat);
+ error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
if (error)
goto error0;
if (*stat == 0) {
@@ -2649,7 +2642,7 @@ xfs_btree_new_root(
cur->bc_ops->init_ptr_from_cur(cur, &rptr);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, 1, stat);
+ error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -2684,8 +2677,7 @@ xfs_btree_new_root(
lbp = bp;
xfs_btree_buf_to_ptr(cur, lbp, &lptr);
left = block;
- error = xfs_btree_read_buf_block(cur, &rptr,
- cur->bc_nlevels - 1, 0, &right, &rbp);
+ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
if (error)
goto error0;
bp = rbp;
@@ -2696,8 +2688,7 @@ xfs_btree_new_root(
xfs_btree_buf_to_ptr(cur, rbp, &rptr);
right = block;
xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
- error = xfs_btree_read_buf_block(cur, &lptr,
- cur->bc_nlevels - 1, 0, &left, &lbp);
+ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
if (error)
goto error0;
bp = lbp;
@@ -3649,8 +3640,7 @@ xfs_btree_delrec(
rptr = cptr;
right = block;
rbp = bp;
- error = xfs_btree_read_buf_block(cur, &lptr, level,
- 0, &left, &lbp);
+ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
if (error)
goto error0;
@@ -3667,8 +3657,7 @@ xfs_btree_delrec(
lptr = cptr;
left = block;
lbp = bp;
- error = xfs_btree_read_buf_block(cur, &rptr, level,
- 0, &right, &rbp);
+ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
if (error)
goto error0;
@@ -3740,8 +3729,7 @@ xfs_btree_delrec(
/* If there is a right sibling, point it to the remaining block. */
xfs_btree_get_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
if (!xfs_btree_ptr_is_null(cur, &cptr)) {
- error = xfs_btree_read_buf_block(cur, &cptr, level,
- 0, &rrblock, &rrbp);
+ error = xfs_btree_read_buf_block(cur, &cptr, 0, &rrblock, &rrbp);
if (error)
goto error0;
xfs_btree_set_sibling(cur, rrblock, &lptr, XFS_BB_LEFTSIB);
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 91e34f21bace..a04b69422f67 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -62,6 +62,7 @@ union xfs_btree_rec {
#define XFS_BTNUM_CNT ((xfs_btnum_t)XFS_BTNUM_CNTi)
#define XFS_BTNUM_BMAP ((xfs_btnum_t)XFS_BTNUM_BMAPi)
#define XFS_BTNUM_INO ((xfs_btnum_t)XFS_BTNUM_INOi)
+#define XFS_BTNUM_FINO ((xfs_btnum_t)XFS_BTNUM_FINOi)
/*
* For logging record fields.
@@ -92,6 +93,7 @@ do { \
case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break; \
case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break; \
case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break; \
+ case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break; \
case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
} \
} while (0)
@@ -105,6 +107,7 @@ do { \
case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
+ case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \
case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
} \
} while (0)
@@ -129,7 +132,7 @@ struct xfs_btree_ops {
int (*alloc_block)(struct xfs_btree_cur *cur,
union xfs_btree_ptr *start_bno,
union xfs_btree_ptr *new_bno,
- int length, int *stat);
+ int *stat);
int (*free_block)(struct xfs_btree_cur *cur, struct xfs_buf *bp);
/* update last record information */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index cb10a0aaab3a..7a34a1ae6552 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -216,8 +216,7 @@ _xfs_buf_alloc(
STATIC int
_xfs_buf_get_pages(
xfs_buf_t *bp,
- int page_count,
- xfs_buf_flags_t flags)
+ int page_count)
{
/* Make sure that we have a page list */
if (bp->b_pages == NULL) {
@@ -330,7 +329,7 @@ use_alloc_page:
end = (BBTOB(bp->b_maps[0].bm_bn + bp->b_length) + PAGE_SIZE - 1)
>> PAGE_SHIFT;
page_count = end - start;
- error = _xfs_buf_get_pages(bp, page_count, flags);
+ error = _xfs_buf_get_pages(bp, page_count);
if (unlikely(error))
return error;
@@ -778,7 +777,7 @@ xfs_buf_associate_memory(
bp->b_pages = NULL;
bp->b_addr = mem;
- rval = _xfs_buf_get_pages(bp, page_count, 0);
+ rval = _xfs_buf_get_pages(bp, page_count);
if (rval)
return rval;
@@ -811,7 +810,7 @@ xfs_buf_get_uncached(
goto fail;
page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT;
- error = _xfs_buf_get_pages(bp, page_count, 0);
+ error = _xfs_buf_get_pages(bp, page_count);
if (error)
goto fail_free_buf;
@@ -1615,7 +1614,6 @@ xfs_free_buftarg(
int
xfs_setsize_buftarg(
xfs_buftarg_t *btp,
- unsigned int blocksize,
unsigned int sectorsize)
{
/* Set up metadata sector size info */
@@ -1650,16 +1648,13 @@ xfs_setsize_buftarg_early(
xfs_buftarg_t *btp,
struct block_device *bdev)
{
- return xfs_setsize_buftarg(btp, PAGE_SIZE,
- bdev_logical_block_size(bdev));
+ return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev));
}
xfs_buftarg_t *
xfs_alloc_buftarg(
struct xfs_mount *mp,
- struct block_device *bdev,
- int external,
- const char *fsname)
+ struct block_device *bdev)
{
xfs_buftarg_t *btp;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b8a3abf6cf47..3a7a5523d3dc 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -298,11 +298,6 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
extern int xfs_bioerror_relse(struct xfs_buf *);
-static inline int xfs_buf_geterror(xfs_buf_t *bp)
-{
- return bp ? bp->b_error : ENOMEM;
-}
-
/* Buffer Utility Routines */
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
@@ -387,10 +382,10 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
* Handling of buftargs.
*/
extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
- struct block_device *, int, const char *);
+ struct block_device *);
extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
-extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
+extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);
#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 8752821443be..4654338b03fc 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -812,7 +812,6 @@ xfs_buf_item_init(
*/
static void
xfs_buf_item_log_segment(
- struct xfs_buf_log_item *bip,
uint first,
uint last,
uint *map)
@@ -920,7 +919,7 @@ xfs_buf_item_log(
if (end > last)
end = last;
- xfs_buf_item_log_segment(bip, first, end,
+ xfs_buf_item_log_segment(first, end,
&bip->bli_formats[i].blf_data_map[0]);
start += bp->b_maps[i].bm_len;
@@ -1053,7 +1052,7 @@ xfs_buf_iodone_callbacks(
static ulong lasttime;
static xfs_buftarg_t *lasttarg;
- if (likely(!xfs_buf_geterror(bp)))
+ if (likely(!bp->b_error))
goto do_callbacks;
/*
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 6cc5f6785a77..a514ab616650 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -167,8 +167,8 @@ xfs_da3_node_verify(
* we don't know if the node is for and attribute or directory tree,
* so only fail if the count is outside both bounds
*/
- if (ichdr.count > mp->m_dir_node_ents &&
- ichdr.count > mp->m_attr_node_ents)
+ if (ichdr.count > mp->m_dir_geo->node_ents &&
+ ichdr.count > mp->m_attr_geo->node_ents)
return false;
/* XXX: hash order check? */
@@ -598,7 +598,7 @@ xfs_da3_root_split(
* Set up the new root node.
*/
error = xfs_da3_node_create(args,
- (args->whichfork == XFS_DATA_FORK) ? mp->m_dirleafblk : 0,
+ (args->whichfork == XFS_DATA_FORK) ? args->geo->leafblk : 0,
level + 1, &bp, args->whichfork);
if (error)
return error;
@@ -616,10 +616,10 @@ xfs_da3_root_split(
#ifdef DEBUG
if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
- ASSERT(blk1->blkno >= mp->m_dirleafblk &&
- blk1->blkno < mp->m_dirfreeblk);
- ASSERT(blk2->blkno >= mp->m_dirleafblk &&
- blk2->blkno < mp->m_dirfreeblk);
+ ASSERT(blk1->blkno >= args->geo->leafblk &&
+ blk1->blkno < args->geo->freeblk);
+ ASSERT(blk2->blkno >= args->geo->leafblk &&
+ blk2->blkno < args->geo->freeblk);
}
#endif
@@ -663,7 +663,7 @@ xfs_da3_node_split(
/*
* Do we have to split the node?
*/
- if (nodehdr.count + newcount > state->node_ents) {
+ if (nodehdr.count + newcount > state->args->geo->node_ents) {
/*
* Allocate a new node, add to the doubly linked chain of
* nodes, then move some of our excess entries into it.
@@ -894,8 +894,8 @@ xfs_da3_node_add(
ASSERT(oldblk->index >= 0 && oldblk->index <= nodehdr.count);
ASSERT(newblk->blkno != 0);
if (state->args->whichfork == XFS_DATA_FORK)
- ASSERT(newblk->blkno >= state->mp->m_dirleafblk &&
- newblk->blkno < state->mp->m_dirfreeblk);
+ ASSERT(newblk->blkno >= state->args->geo->leafblk &&
+ newblk->blkno < state->args->geo->freeblk);
/*
* We may need to make some room before we insert the new node.
@@ -1089,14 +1089,15 @@ xfs_da3_root_join(
* that could occur. For dir3 blocks we also need to update the block
* number in the buffer header.
*/
- memcpy(root_blk->bp->b_addr, bp->b_addr, state->blocksize);
+ memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize);
root_blk->bp->b_ops = bp->b_ops;
xfs_trans_buf_copy_type(root_blk->bp, bp);
if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) {
struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr;
da3->blkno = cpu_to_be64(root_blk->bp->b_bn);
}
- xfs_trans_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
+ xfs_trans_log_buf(args->trans, root_blk->bp, 0,
+ args->geo->blksize - 1);
error = xfs_da_shrink_inode(args, child, bp);
return(error);
}
@@ -1139,7 +1140,7 @@ xfs_da3_node_toosmall(
info = blk->bp->b_addr;
node = (xfs_da_intnode_t *)info;
dp->d_ops->node_hdr_from_disk(&nodehdr, node);
- if (nodehdr.count > (state->node_ents >> 1)) {
+ if (nodehdr.count > (state->args->geo->node_ents >> 1)) {
*action = 0; /* blk over 50%, don't try to join */
return(0); /* blk over 50%, don't try to join */
}
@@ -1176,8 +1177,8 @@ xfs_da3_node_toosmall(
* We prefer coalescing with the lower numbered sibling so as
* to shrink a directory over time.
*/
- count = state->node_ents;
- count -= state->node_ents >> 2;
+ count = state->args->geo->node_ents;
+ count -= state->args->geo->node_ents >> 2;
count -= nodehdr.count;
/* start with smaller blk num */
@@ -1472,7 +1473,7 @@ xfs_da3_node_lookup_int(
* Descend thru the B-tree searching each level for the right
* node to use, until the right hashval is found.
*/
- blkno = (args->whichfork == XFS_DATA_FORK)? state->mp->m_dirleafblk : 0;
+ blkno = (args->whichfork == XFS_DATA_FORK)? args->geo->leafblk : 0;
for (blk = &state->path.blk[0], state->path.active = 1;
state->path.active <= XFS_DA_NODE_MAXDEPTH;
blk++, state->path.active++) {
@@ -2090,20 +2091,12 @@ xfs_da_grow_inode(
xfs_dablk_t *new_blkno)
{
xfs_fileoff_t bno;
- int count;
int error;
trace_xfs_da_grow_inode(args);
- if (args->whichfork == XFS_DATA_FORK) {
- bno = args->dp->i_mount->m_dirleafblk;
- count = args->dp->i_mount->m_dirblkfsbs;
- } else {
- bno = 0;
- count = 1;
- }
-
- error = xfs_da_grow_inode_int(args, &bno, count);
+ bno = args->geo->leafblk;
+ error = xfs_da_grow_inode_int(args, &bno, args->geo->fsbcount);
if (!error)
*new_blkno = (xfs_dablk_t)bno;
return error;
@@ -2158,7 +2151,7 @@ xfs_da3_swap_lastblock(
w = args->whichfork;
ASSERT(w == XFS_DATA_FORK);
mp = dp->i_mount;
- lastoff = mp->m_dirfreeblk;
+ lastoff = args->geo->freeblk;
error = xfs_bmap_last_before(tp, dp, &lastoff, w);
if (error)
return error;
@@ -2170,15 +2163,15 @@ xfs_da3_swap_lastblock(
/*
* Read the last block in the btree space.
*/
- last_blkno = (xfs_dablk_t)lastoff - mp->m_dirblkfsbs;
+ last_blkno = (xfs_dablk_t)lastoff - args->geo->fsbcount;
error = xfs_da3_node_read(tp, dp, last_blkno, -1, &last_buf, w);
if (error)
return error;
/*
* Copy the last block into the dead buffer and log it.
*/
- memcpy(dead_buf->b_addr, last_buf->b_addr, mp->m_dirblksize);
- xfs_trans_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
+ memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
+ xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
dead_info = dead_buf->b_addr;
/*
* Get values from the moved block.
@@ -2247,7 +2240,7 @@ xfs_da3_swap_lastblock(
sizeof(sib_info->back)));
sib_buf = NULL;
}
- par_blkno = mp->m_dirleafblk;
+ par_blkno = args->geo->leafblk;
level = -1;
/*
* Walk down the tree looking for the parent of the moved block.
@@ -2357,10 +2350,7 @@ xfs_da_shrink_inode(
w = args->whichfork;
tp = args->trans;
mp = dp->i_mount;
- if (w == XFS_DATA_FORK)
- count = mp->m_dirblkfsbs;
- else
- count = 1;
+ count = args->geo->fsbcount;
for (;;) {
/*
* Remove extents. If we get ENOSPC for a dir we have to move
@@ -2462,7 +2452,6 @@ xfs_buf_map_from_irec(
*/
static int
xfs_dabuf_map(
- struct xfs_trans *trans,
struct xfs_inode *dp,
xfs_dablk_t bno,
xfs_daddr_t mappedbno,
@@ -2480,7 +2469,10 @@ xfs_dabuf_map(
ASSERT(map && *map);
ASSERT(*nmaps == 1);
- nfsb = (whichfork == XFS_DATA_FORK) ? mp->m_dirblkfsbs : 1;
+ if (whichfork == XFS_DATA_FORK)
+ nfsb = mp->m_dir_geo->fsbcount;
+ else
+ nfsb = mp->m_attr_geo->fsbcount;
/*
* Caller doesn't have a mapping. -2 means don't complain
@@ -2558,7 +2550,7 @@ xfs_da_get_buf(
*bpp = NULL;
mapp = &map;
nmap = 1;
- error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+ error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
&mapp, &nmap);
if (error) {
/* mapping a hole is not an error, but we don't continue */
@@ -2606,7 +2598,7 @@ xfs_da_read_buf(
*bpp = NULL;
mapp = &map;
nmap = 1;
- error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+ error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
&mapp, &nmap);
if (error) {
/* mapping a hole is not an error, but we don't continue */
@@ -2625,47 +2617,6 @@ xfs_da_read_buf(
xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
else
xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
-
- /*
- * This verification code will be moved to a CRC verification callback
- * function so just leave it here unchanged until then.
- */
- {
- xfs_dir2_data_hdr_t *hdr = bp->b_addr;
- xfs_dir2_free_t *free = bp->b_addr;
- xfs_da_blkinfo_t *info = bp->b_addr;
- uint magic, magic1;
- struct xfs_mount *mp = dp->i_mount;
-
- magic = be16_to_cpu(info->magic);
- magic1 = be32_to_cpu(hdr->magic);
- if (unlikely(
- XFS_TEST_ERROR((magic != XFS_DA_NODE_MAGIC) &&
- (magic != XFS_DA3_NODE_MAGIC) &&
- (magic != XFS_ATTR_LEAF_MAGIC) &&
- (magic != XFS_ATTR3_LEAF_MAGIC) &&
- (magic != XFS_DIR2_LEAF1_MAGIC) &&
- (magic != XFS_DIR3_LEAF1_MAGIC) &&
- (magic != XFS_DIR2_LEAFN_MAGIC) &&
- (magic != XFS_DIR3_LEAFN_MAGIC) &&
- (magic1 != XFS_DIR2_BLOCK_MAGIC) &&
- (magic1 != XFS_DIR3_BLOCK_MAGIC) &&
- (magic1 != XFS_DIR2_DATA_MAGIC) &&
- (magic1 != XFS_DIR3_DATA_MAGIC) &&
- (free->hdr.magic !=
- cpu_to_be32(XFS_DIR2_FREE_MAGIC)) &&
- (free->hdr.magic !=
- cpu_to_be32(XFS_DIR3_FREE_MAGIC)),
- mp, XFS_ERRTAG_DA_READ_BUF,
- XFS_RANDOM_DA_READ_BUF))) {
- trace_xfs_da_btree_corrupt(bp, _RET_IP_);
- XFS_CORRUPTION_ERROR("xfs_da_do_buf(2)",
- XFS_ERRLEVEL_LOW, mp, info);
- error = XFS_ERROR(EFSCORRUPTED);
- xfs_trans_brelse(trans, bp);
- goto out_free;
- }
- }
*bpp = bp;
out_free:
if (mapp != &map)
@@ -2679,7 +2630,6 @@ out_free:
*/
xfs_daddr_t
xfs_da_reada_buf(
- struct xfs_trans *trans,
struct xfs_inode *dp,
xfs_dablk_t bno,
xfs_daddr_t mappedbno,
@@ -2693,7 +2643,7 @@ xfs_da_reada_buf(
mapp = &map;
nmap = 1;
- error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+ error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
&mapp, &nmap);
if (error) {
/* mapping a hole is not an error, but we don't continue */
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 201c6091d26a..6e153e399a77 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -25,6 +25,23 @@ struct xfs_trans;
struct zone;
struct xfs_dir_ops;
+/*
+ * Directory/attribute geometry information. There will be one of these for each
+ * data fork type, and it will be passed around via the xfs_da_args. Global
+ * structures will be attached to the xfs_mount.
+ */
+struct xfs_da_geometry {
+ int blksize; /* da block size in bytes */
+ int fsbcount; /* da block size in filesystem blocks */
+ uint8_t fsblog; /* log2 of _filesystem_ block size */
+ uint8_t blklog; /* log2 of da block size */
+ uint node_ents; /* # of entries in a danode */
+ int magicpct; /* 37% of block size in bytes */
+ xfs_dablk_t datablk; /* blockno of dir data v2 */
+ xfs_dablk_t leafblk; /* blockno of leaf data v2 */
+ xfs_dablk_t freeblk; /* blockno of free data v2 */
+};
+
/*========================================================================
* Btree searching and modification structure definitions.
*========================================================================*/
@@ -42,6 +59,7 @@ enum xfs_dacmp {
* Structure to ease passing around component names.
*/
typedef struct xfs_da_args {
+ struct xfs_da_geometry *geo; /* da block geometry */
const __uint8_t *name; /* string (maybe not NULL terminated) */
int namelen; /* length of string (maybe no NULL) */
__uint8_t filetype; /* filetype of inode for directories */
@@ -110,8 +128,6 @@ typedef struct xfs_da_state_path {
typedef struct xfs_da_state {
xfs_da_args_t *args; /* filename arguments */
struct xfs_mount *mp; /* filesystem mount point */
- unsigned int blocksize; /* logical block size */
- unsigned int node_ents; /* how many entries in danode */
xfs_da_state_path_t path; /* search/split paths */
xfs_da_state_path_t altpath; /* alternate path for join */
unsigned char inleaf; /* insert into 1->lf, 0->splf */
@@ -185,9 +201,9 @@ int xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mappedbno,
struct xfs_buf **bpp, int whichfork,
const struct xfs_buf_ops *ops);
-xfs_daddr_t xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
- xfs_dablk_t bno, xfs_daddr_t mapped_bno,
- int whichfork, const struct xfs_buf_ops *ops);
+xfs_daddr_t xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
+ xfs_daddr_t mapped_bno, int whichfork,
+ const struct xfs_buf_ops *ops);
int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
struct xfs_buf *dead_buf);
diff --git a/fs/xfs/xfs_da_format.c b/fs/xfs/xfs_da_format.c
index e6c83e1fbc8a..c9aee52a37e2 100644
--- a/fs/xfs/xfs_da_format.c
+++ b/fs/xfs/xfs_da_format.c
@@ -26,8 +26,10 @@
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
/*
* Shortform directory ops
@@ -425,9 +427,9 @@ xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
* Directory Leaf block operations
*/
static int
-xfs_dir2_max_leaf_ents(struct xfs_mount *mp)
+xfs_dir2_max_leaf_ents(struct xfs_da_geometry *geo)
{
- return (mp->m_dirblksize - sizeof(struct xfs_dir2_leaf_hdr)) /
+ return (geo->blksize - sizeof(struct xfs_dir2_leaf_hdr)) /
(uint)sizeof(struct xfs_dir2_leaf_entry);
}
@@ -438,9 +440,9 @@ xfs_dir2_leaf_ents_p(struct xfs_dir2_leaf *lp)
}
static int
-xfs_dir3_max_leaf_ents(struct xfs_mount *mp)
+xfs_dir3_max_leaf_ents(struct xfs_da_geometry *geo)
{
- return (mp->m_dirblksize - sizeof(struct xfs_dir3_leaf_hdr)) /
+ return (geo->blksize - sizeof(struct xfs_dir3_leaf_hdr)) /
(uint)sizeof(struct xfs_dir2_leaf_entry);
}
@@ -591,9 +593,9 @@ xfs_da3_node_hdr_to_disk(
* Directory free space block operations
*/
static int
-xfs_dir2_free_max_bests(struct xfs_mount *mp)
+xfs_dir2_free_max_bests(struct xfs_da_geometry *geo)
{
- return (mp->m_dirblksize - sizeof(struct xfs_dir2_free_hdr)) /
+ return (geo->blksize - sizeof(struct xfs_dir2_free_hdr)) /
sizeof(xfs_dir2_data_off_t);
}
@@ -607,24 +609,25 @@ xfs_dir2_free_bests_p(struct xfs_dir2_free *free)
* Convert data space db to the corresponding free db.
*/
static xfs_dir2_db_t
-xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir2_db_to_fdb(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
{
- return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir2_free_max_bests(mp);
+ return xfs_dir2_byte_to_db(geo, XFS_DIR2_FREE_OFFSET) +
+ (db / xfs_dir2_free_max_bests(geo));
}
/*
* Convert data space db to the corresponding index in a free db.
*/
static int
-xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir2_db_to_fdindex(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
{
- return db % xfs_dir2_free_max_bests(mp);
+ return db % xfs_dir2_free_max_bests(geo);
}
static int
-xfs_dir3_free_max_bests(struct xfs_mount *mp)
+xfs_dir3_free_max_bests(struct xfs_da_geometry *geo)
{
- return (mp->m_dirblksize - sizeof(struct xfs_dir3_free_hdr)) /
+ return (geo->blksize - sizeof(struct xfs_dir3_free_hdr)) /
sizeof(xfs_dir2_data_off_t);
}
@@ -638,18 +641,19 @@ xfs_dir3_free_bests_p(struct xfs_dir2_free *free)
* Convert data space db to the corresponding free db.
*/
static xfs_dir2_db_t
-xfs_dir3_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir3_db_to_fdb(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
{
- return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir3_free_max_bests(mp);
+ return xfs_dir2_byte_to_db(geo, XFS_DIR2_FREE_OFFSET) +
+ (db / xfs_dir3_free_max_bests(geo));
}
/*
* Convert data space db to the corresponding index in a free db.
*/
static int
-xfs_dir3_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir3_db_to_fdindex(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
{
- return db % xfs_dir3_free_max_bests(mp);
+ return db % xfs_dir3_free_max_bests(geo);
}
static void
diff --git a/fs/xfs/xfs_da_format.h b/fs/xfs/xfs_da_format.h
index a19d3f8f639c..0a49b0286372 100644
--- a/fs/xfs/xfs_da_format.h
+++ b/fs/xfs/xfs_da_format.h
@@ -19,10 +19,6 @@
#ifndef __XFS_DA_FORMAT_H__
#define __XFS_DA_FORMAT_H__
-/*========================================================================
- * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
/*
* This structure is common to both leaf nodes and non-leaf nodes in the Btree.
*
@@ -122,8 +118,6 @@ struct xfs_da3_icnode_hdr {
__uint16_t level;
};
-#define XFS_LBSIZE(mp) (mp)->m_sb.sb_blocksize
-
/*
* Directory version 2.
*
@@ -330,8 +324,6 @@ xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
#define XFS_DIR2_SPACE_SIZE (1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
#define XFS_DIR2_DATA_SPACE 0
#define XFS_DIR2_DATA_OFFSET (XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
-#define XFS_DIR2_DATA_FIRSTDB(mp) \
- xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET)
/*
* Describe a free area in the data block.
@@ -456,8 +448,6 @@ xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
*/
#define XFS_DIR2_LEAF_SPACE 1
#define XFS_DIR2_LEAF_OFFSET (XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE)
-#define XFS_DIR2_LEAF_FIRSTDB(mp) \
- xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET)
/*
* Leaf block header.
@@ -514,17 +504,6 @@ struct xfs_dir3_leaf {
#define XFS_DIR3_LEAF_CRC_OFF offsetof(struct xfs_dir3_leaf_hdr, info.crc)
/*
- * Get address of the bestcount field in the single-leaf block.
- */
-static inline struct xfs_dir2_leaf_tail *
-xfs_dir2_leaf_tail_p(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
-{
- return (struct xfs_dir2_leaf_tail *)
- ((char *)lp + mp->m_dirblksize -
- sizeof(struct xfs_dir2_leaf_tail));
-}
-
-/*
* Get address of the bests array in the single-leaf block.
*/
static inline __be16 *
@@ -534,123 +513,6 @@ xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp)
}
/*
- * DB blocks here are logical directory block numbers, not filesystem blocks.
- */
-
-/*
- * Convert dataptr to byte in file space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
- return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
-}
-
-/*
- * Convert byte in file space to dataptr. It had better be aligned.
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
-}
-
-/*
- * Convert byte in space to (DB) block
- */
-static inline xfs_dir2_db_t
-xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return (xfs_dir2_db_t)
- (by >> (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog));
-}
-
-/*
- * Convert dataptr to a block number
- */
-static inline xfs_dir2_db_t
-xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
- return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert byte in space to offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return (xfs_dir2_data_aoff_t)(by &
- ((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) - 1));
-}
-
-/*
- * Convert dataptr to a byte offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
- return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert block and offset to byte in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db,
- xfs_dir2_data_aoff_t o)
-{
- return ((xfs_dir2_off_t)db <<
- (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) + o;
-}
-
-/*
- * Convert block (DB) to block (dablk)
- */
-static inline xfs_dablk_t
-xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
- return (xfs_dablk_t)(db << mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert byte in space to (DA) block
- */
-static inline xfs_dablk_t
-xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by));
-}
-
-/*
- * Convert block and offset to dataptr
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db,
- xfs_dir2_data_aoff_t o)
-{
- return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o));
-}
-
-/*
- * Convert block (dablk) to block (DB)
- */
-static inline xfs_dir2_db_t
-xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da)
-{
- return (xfs_dir2_db_t)(da >> mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert block (dablk) to byte offset in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
-{
- return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0);
-}
-
-/*
* Free space block defintions for the node format.
*/
@@ -659,8 +521,6 @@ xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
*/
#define XFS_DIR2_FREE_SPACE 2
#define XFS_DIR2_FREE_OFFSET (XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE)
-#define XFS_DIR2_FREE_FIRSTDB(mp) \
- xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET)
typedef struct xfs_dir2_free_hdr {
__be32 magic; /* XFS_DIR2_FREE_MAGIC */
@@ -736,16 +596,6 @@ typedef struct xfs_dir2_block_tail {
} xfs_dir2_block_tail_t;
/*
- * Pointer to the leaf header embedded in a data block (1-block format)
- */
-static inline struct xfs_dir2_block_tail *
-xfs_dir2_block_tail_p(struct xfs_mount *mp, struct xfs_dir2_data_hdr *hdr)
-{
- return ((struct xfs_dir2_block_tail *)
- ((char *)hdr + mp->m_dirblksize)) - 1;
-}
-
-/*
* Pointer to the leaf entries embedded in a data block (1-block format)
*/
static inline struct xfs_dir2_leaf_entry *
@@ -764,10 +614,6 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
* of an attribute name may not be unique, we may have duplicate keys. The
* internal links in the Btree are logical block offsets into the file.
*
- *========================================================================
- * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
- *========================================================================
- *
* Struct leaf_entry's are packed from the top. Name/values grow from the
* bottom but are not packed. The freemap contains run-length-encoded entries
* for the free bytes after the leaf_entry's, but only the N largest such,
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index fda46253966a..79670cda48ae 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -85,38 +85,74 @@ static struct xfs_nameops xfs_ascii_ci_nameops = {
.compname = xfs_ascii_ci_compname,
};
-void
-xfs_dir_mount(
- xfs_mount_t *mp)
+int
+xfs_da_mount(
+ struct xfs_mount *mp)
{
- int nodehdr_size;
+ struct xfs_da_geometry *dageo;
+ int nodehdr_size;
- ASSERT(xfs_sb_version_hasdirv2(&mp->m_sb));
+ ASSERT(mp->m_sb.sb_versionnum & XFS_SB_VERSION_DIRV2BIT);
ASSERT((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) <=
XFS_MAX_BLOCKSIZE);
mp->m_dir_inode_ops = xfs_dir_get_ops(mp, NULL);
mp->m_nondir_inode_ops = xfs_nondir_get_ops(mp, NULL);
- mp->m_dirblksize = 1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog);
- mp->m_dirblkfsbs = 1 << mp->m_sb.sb_dirblklog;
- mp->m_dirdatablk = xfs_dir2_db_to_da(mp, XFS_DIR2_DATA_FIRSTDB(mp));
- mp->m_dirleafblk = xfs_dir2_db_to_da(mp, XFS_DIR2_LEAF_FIRSTDB(mp));
- mp->m_dirfreeblk = xfs_dir2_db_to_da(mp, XFS_DIR2_FREE_FIRSTDB(mp));
-
nodehdr_size = mp->m_dir_inode_ops->node_hdr_size;
- mp->m_attr_node_ents = (mp->m_sb.sb_blocksize - nodehdr_size) /
+ mp->m_dir_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
+ KM_SLEEP | KM_MAYFAIL);
+ mp->m_attr_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
+ KM_SLEEP | KM_MAYFAIL);
+ if (!mp->m_dir_geo || !mp->m_attr_geo) {
+ kmem_free(mp->m_dir_geo);
+ kmem_free(mp->m_attr_geo);
+ return ENOMEM;
+ }
+
+ /* set up directory geometry */
+ dageo = mp->m_dir_geo;
+ dageo->blklog = mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog;
+ dageo->fsblog = mp->m_sb.sb_blocklog;
+ dageo->blksize = 1 << dageo->blklog;
+ dageo->fsbcount = 1 << mp->m_sb.sb_dirblklog;
+
+ /*
+ * Now we've set up the block conversion variables, we can calculate the
+ * segment block constants using the geometry structure.
+ */
+ dageo->datablk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_DATA_OFFSET);
+ dageo->leafblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_LEAF_OFFSET);
+ dageo->freeblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_FREE_OFFSET);
+ dageo->node_ents = (dageo->blksize - nodehdr_size) /
(uint)sizeof(xfs_da_node_entry_t);
- mp->m_dir_node_ents = (mp->m_dirblksize - nodehdr_size) /
+ dageo->magicpct = (dageo->blksize * 37) / 100;
+
+ /* set up attribute geometry - single fsb only */
+ dageo = mp->m_attr_geo;
+ dageo->blklog = mp->m_sb.sb_blocklog;
+ dageo->fsblog = mp->m_sb.sb_blocklog;
+ dageo->blksize = 1 << dageo->blklog;
+ dageo->fsbcount = 1;
+ dageo->node_ents = (dageo->blksize - nodehdr_size) /
(uint)sizeof(xfs_da_node_entry_t);
+ dageo->magicpct = (dageo->blksize * 37) / 100;
- mp->m_dir_magicpct = (mp->m_dirblksize * 37) / 100;
if (xfs_sb_version_hasasciici(&mp->m_sb))
mp->m_dirnameops = &xfs_ascii_ci_nameops;
else
mp->m_dirnameops = &xfs_default_nameops;
+ return 0;
+}
+
+void
+xfs_da_unmount(
+ struct xfs_mount *mp)
+{
+ kmem_free(mp->m_dir_geo);
+ kmem_free(mp->m_attr_geo);
}
/*
@@ -192,6 +228,7 @@ xfs_dir_init(
if (!args)
return ENOMEM;
+ args->geo = dp->i_mount->m_dir_geo;
args->dp = dp;
args->trans = tp;
error = xfs_dir2_sf_create(args, pdp->i_ino);
@@ -226,6 +263,7 @@ xfs_dir_createname(
if (!args)
return ENOMEM;
+ args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
args->filetype = name->type;
@@ -244,7 +282,7 @@ xfs_dir_createname(
goto out_free;
}
- rval = xfs_dir2_isblock(tp, dp, &v);
+ rval = xfs_dir2_isblock(args, &v);
if (rval)
goto out_free;
if (v) {
@@ -252,7 +290,7 @@ xfs_dir_createname(
goto out_free;
}
- rval = xfs_dir2_isleaf(tp, dp, &v);
+ rval = xfs_dir2_isleaf(args, &v);
if (rval)
goto out_free;
if (v)
@@ -320,6 +358,7 @@ xfs_dir_lookup(
* annotations into the reclaim path for the ilock.
*/
args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
args->filetype = name->type;
@@ -336,7 +375,7 @@ xfs_dir_lookup(
goto out_check_rval;
}
- rval = xfs_dir2_isblock(tp, dp, &v);
+ rval = xfs_dir2_isblock(args, &v);
if (rval)
goto out_free;
if (v) {
@@ -344,7 +383,7 @@ xfs_dir_lookup(
goto out_check_rval;
}
- rval = xfs_dir2_isleaf(tp, dp, &v);
+ rval = xfs_dir2_isleaf(args, &v);
if (rval)
goto out_free;
if (v)
@@ -391,6 +430,7 @@ xfs_dir_removename(
if (!args)
return ENOMEM;
+ args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
args->filetype = name->type;
@@ -408,7 +448,7 @@ xfs_dir_removename(
goto out_free;
}
- rval = xfs_dir2_isblock(tp, dp, &v);
+ rval = xfs_dir2_isblock(args, &v);
if (rval)
goto out_free;
if (v) {
@@ -416,7 +456,7 @@ xfs_dir_removename(
goto out_free;
}
- rval = xfs_dir2_isleaf(tp, dp, &v);
+ rval = xfs_dir2_isleaf(args, &v);
if (rval)
goto out_free;
if (v)
@@ -455,6 +495,7 @@ xfs_dir_replace(
if (!args)
return ENOMEM;
+ args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
args->filetype = name->type;
@@ -472,7 +513,7 @@ xfs_dir_replace(
goto out_free;
}
- rval = xfs_dir2_isblock(tp, dp, &v);
+ rval = xfs_dir2_isblock(args, &v);
if (rval)
goto out_free;
if (v) {
@@ -480,7 +521,7 @@ xfs_dir_replace(
goto out_free;
}
- rval = xfs_dir2_isleaf(tp, dp, &v);
+ rval = xfs_dir2_isleaf(args, &v);
if (rval)
goto out_free;
if (v)
@@ -516,6 +557,7 @@ xfs_dir_canenter(
if (!args)
return ENOMEM;
+ args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
args->filetype = name->type;
@@ -531,7 +573,7 @@ xfs_dir_canenter(
goto out_free;
}
- rval = xfs_dir2_isblock(tp, dp, &v);
+ rval = xfs_dir2_isblock(args, &v);
if (rval)
goto out_free;
if (v) {
@@ -539,7 +581,7 @@ xfs_dir_canenter(
goto out_free;
}
- rval = xfs_dir2_isleaf(tp, dp, &v);
+ rval = xfs_dir2_isleaf(args, &v);
if (rval)
goto out_free;
if (v)
@@ -579,13 +621,13 @@ xfs_dir2_grow_inode(
* Set lowest possible block in the space requested.
*/
bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE);
- count = mp->m_dirblkfsbs;
+ count = args->geo->fsbcount;
error = xfs_da_grow_inode_int(args, &bno, count);
if (error)
return error;
- *dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno);
+ *dbp = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)bno);
/*
* Update file's size if this is the data space and it grew.
@@ -607,19 +649,16 @@ xfs_dir2_grow_inode(
*/
int
xfs_dir2_isblock(
- xfs_trans_t *tp,
- xfs_inode_t *dp,
- int *vp) /* out: 1 is block, 0 is not block */
+ struct xfs_da_args *args,
+ int *vp) /* out: 1 is block, 0 is not block */
{
- xfs_fileoff_t last; /* last file offset */
- xfs_mount_t *mp;
- int rval;
+ xfs_fileoff_t last; /* last file offset */
+ int rval;
- mp = dp->i_mount;
- if ((rval = xfs_bmap_last_offset(tp, dp, &last, XFS_DATA_FORK)))
+ if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
return rval;
- rval = XFS_FSB_TO_B(mp, last) == mp->m_dirblksize;
- ASSERT(rval == 0 || dp->i_d.di_size == mp->m_dirblksize);
+ rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
+ ASSERT(rval == 0 || args->dp->i_d.di_size == args->geo->blksize);
*vp = rval;
return 0;
}
@@ -629,18 +668,15 @@ xfs_dir2_isblock(
*/
int
xfs_dir2_isleaf(
- xfs_trans_t *tp,
- xfs_inode_t *dp,
- int *vp) /* out: 1 is leaf, 0 is not leaf */
+ struct xfs_da_args *args,
+ int *vp) /* out: 1 is block, 0 is not block */
{
- xfs_fileoff_t last; /* last file offset */
- xfs_mount_t *mp;
- int rval;
+ xfs_fileoff_t last; /* last file offset */
+ int rval;
- mp = dp->i_mount;
- if ((rval = xfs_bmap_last_offset(tp, dp, &last, XFS_DATA_FORK)))
+ if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
return rval;
- *vp = last == mp->m_dirleafblk + (1 << mp->m_sb.sb_dirblklog);
+ *vp = last == args->geo->leafblk + args->geo->fsbcount;
return 0;
}
@@ -668,11 +704,11 @@ xfs_dir2_shrink_inode(
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
- da = xfs_dir2_db_to_da(mp, db);
+ da = xfs_dir2_db_to_da(args->geo, db);
/*
* Unmap the fsblock(s).
*/
- if ((error = xfs_bunmapi(tp, dp, da, mp->m_dirblkfsbs,
+ if ((error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount,
XFS_BMAPI_METADATA, 0, args->firstblock, args->flist,
&done))) {
/*
@@ -699,12 +735,12 @@ xfs_dir2_shrink_inode(
/*
* If it's not a data block, we're done.
*/
- if (db >= XFS_DIR2_LEAF_FIRSTDB(mp))
+ if (db >= xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET))
return 0;
/*
* If the block isn't the last one in the directory, we're done.
*/
- if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(mp, db + 1, 0))
+ if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
return 0;
bno = da;
if ((error = xfs_bmap_last_before(tp, dp, &bno, XFS_DATA_FORK))) {
@@ -713,7 +749,7 @@ xfs_dir2_shrink_inode(
*/
return error;
}
- if (db == mp->m_dirdatablk)
+ if (db == args->geo->datablk)
ASSERT(bno == 0);
else
ASSERT(bno > 0);
diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h
index cec70e0781ab..c8e86b0b5e99 100644
--- a/fs/xfs/xfs_dir2.h
+++ b/fs/xfs/xfs_dir2.h
@@ -80,7 +80,7 @@ struct xfs_dir_ops {
struct xfs_dir3_icleaf_hdr *from);
void (*leaf_hdr_from_disk)(struct xfs_dir3_icleaf_hdr *to,
struct xfs_dir2_leaf *from);
- int (*leaf_max_ents)(struct xfs_mount *mp);
+ int (*leaf_max_ents)(struct xfs_da_geometry *geo);
struct xfs_dir2_leaf_entry *
(*leaf_ents_p)(struct xfs_dir2_leaf *lp);
@@ -97,10 +97,12 @@ struct xfs_dir_ops {
struct xfs_dir3_icfree_hdr *from);
void (*free_hdr_from_disk)(struct xfs_dir3_icfree_hdr *to,
struct xfs_dir2_free *from);
- int (*free_max_bests)(struct xfs_mount *mp);
+ int (*free_max_bests)(struct xfs_da_geometry *geo);
__be16 * (*free_bests_p)(struct xfs_dir2_free *free);
- xfs_dir2_db_t (*db_to_fdb)(struct xfs_mount *mp, xfs_dir2_db_t db);
- int (*db_to_fdindex)(struct xfs_mount *mp, xfs_dir2_db_t db);
+ xfs_dir2_db_t (*db_to_fdb)(struct xfs_da_geometry *geo,
+ xfs_dir2_db_t db);
+ int (*db_to_fdindex)(struct xfs_da_geometry *geo,
+ xfs_dir2_db_t db);
};
extern const struct xfs_dir_ops *
@@ -112,7 +114,9 @@ extern const struct xfs_dir_ops *
* Generic directory interface routines
*/
extern void xfs_dir_startup(void);
-extern void xfs_dir_mount(struct xfs_mount *mp);
+extern int xfs_da_mount(struct xfs_mount *mp);
+extern void xfs_da_unmount(struct xfs_mount *mp);
+
extern int xfs_dir_isempty(struct xfs_inode *dp);
extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_inode *pdp);
@@ -142,23 +146,23 @@ extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
/*
* Interface routines used by userspace utilities
*/
-extern int xfs_dir2_isblock(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
-extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
+extern int xfs_dir2_isblock(struct xfs_da_args *args, int *r);
+extern int xfs_dir2_isleaf(struct xfs_da_args *args, int *r);
extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
struct xfs_buf *bp);
extern void xfs_dir2_data_freescan(struct xfs_inode *dp,
struct xfs_dir2_data_hdr *hdr, int *loghead);
-extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_log_entry(struct xfs_da_args *args,
struct xfs_buf *bp, struct xfs_dir2_data_entry *dep);
-extern void xfs_dir2_data_log_header(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_log_header(struct xfs_da_args *args,
struct xfs_buf *bp);
-extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_buf *bp,
- struct xfs_dir2_data_unused *dup);
-extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_log_unused(struct xfs_da_args *args,
+ struct xfs_buf *bp, struct xfs_dir2_data_unused *dup);
+extern void xfs_dir2_data_make_free(struct xfs_da_args *args,
struct xfs_buf *bp, xfs_dir2_data_aoff_t offset,
xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
-extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_use_free(struct xfs_da_args *args,
struct xfs_buf *bp, struct xfs_dir2_data_unused *dup,
xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
int *needlogp, int *needscanp);
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 4f6a38cb83a4..c7cd3154026a 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -136,7 +136,7 @@ xfs_dir3_block_read(
struct xfs_mount *mp = dp->i_mount;
int err;
- err = xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, bpp,
+ err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
if (!err && tp)
xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
@@ -281,8 +281,7 @@ out:
*/
static void
xfs_dir2_block_compact(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
struct xfs_dir2_data_hdr *hdr,
struct xfs_dir2_block_tail *btp,
@@ -315,18 +314,17 @@ xfs_dir2_block_compact(
*lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
*lfloghigh -= be32_to_cpu(btp->stale) - 1;
be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
- xfs_dir2_data_make_free(tp, dp, bp,
+ xfs_dir2_data_make_free(args, bp,
(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
(xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
needlog, &needscan);
- blp += be32_to_cpu(btp->stale) - 1;
btp->stale = cpu_to_be32(1);
/*
* If we now need to rebuild the bestfree map, do so.
* This needs to happen before the next call to use_free.
*/
if (needscan)
- xfs_dir2_data_freescan(dp, hdr, needlog);
+ xfs_dir2_data_freescan(args->dp, hdr, needlog);
}
/*
@@ -378,7 +376,7 @@ xfs_dir2_block_addname(
* Set up pointers to parts of the block.
*/
hdr = bp->b_addr;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
@@ -421,7 +419,7 @@ xfs_dir2_block_addname(
* If need to compact the leaf entries, do it now.
*/
if (compact) {
- xfs_dir2_block_compact(tp, dp, bp, hdr, btp, blp, &needlog,
+ xfs_dir2_block_compact(args, bp, hdr, btp, blp, &needlog,
&lfloghigh, &lfloglow);
/* recalculate blp post-compaction */
blp = xfs_dir2_block_leaf_p(btp);
@@ -456,7 +454,7 @@ xfs_dir2_block_addname(
/*
* Mark the space needed for the new leaf entry, now in use.
*/
- xfs_dir2_data_use_free(tp, dp, bp, enddup,
+ xfs_dir2_data_use_free(args, bp, enddup,
(xfs_dir2_data_aoff_t)
((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
sizeof(*blp)),
@@ -537,13 +535,13 @@ xfs_dir2_block_addname(
* Fill in the leaf entry.
*/
blp[mid].hashval = cpu_to_be32(args->hashval);
- blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh);
/*
* Mark space for the data entry used.
*/
- xfs_dir2_data_use_free(tp, dp, bp, dup,
+ xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
(xfs_dir2_data_aoff_t)len, &needlog, &needscan);
/*
@@ -561,9 +559,9 @@ xfs_dir2_block_addname(
if (needscan)
xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dp, bp);
+ xfs_dir2_data_log_header(args, bp);
xfs_dir2_block_log_tail(tp, bp);
- xfs_dir2_data_log_entry(tp, dp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
xfs_dir3_data_check(dp, bp);
return 0;
}
@@ -582,7 +580,7 @@ xfs_dir2_block_log_leaf(
xfs_dir2_leaf_entry_t *blp;
xfs_dir2_block_tail_t *btp;
- btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
+ btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
@@ -599,7 +597,7 @@ xfs_dir2_block_log_tail(
xfs_dir2_data_hdr_t *hdr = bp->b_addr;
xfs_dir2_block_tail_t *btp;
- btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
+ btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr);
xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
(uint)((char *)(btp + 1) - (char *)hdr - 1));
}
@@ -634,13 +632,14 @@ xfs_dir2_block_lookup(
mp = dp->i_mount;
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Get the offset from the leaf entry, to point to the data.
*/
dep = (xfs_dir2_data_entry_t *)((char *)hdr +
- xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(blp[ent].address)));
/*
* Fill in inode number, CI name if appropriate, release the block.
*/
@@ -686,7 +685,7 @@ xfs_dir2_block_lookup_int(
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Loop doing a binary search for our hash value.
@@ -724,7 +723,7 @@ xfs_dir2_block_lookup_int(
* Get pointer to the entry from the leaf.
*/
dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr));
+ ((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, addr));
/*
* Compare name and if it's an exact match, return the index
* and buffer. If it's the first case-insensitive match, store
@@ -791,18 +790,19 @@ xfs_dir2_block_removename(
tp = args->trans;
mp = dp->i_mount;
hdr = bp->b_addr;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Point to the data entry using the leaf entry.
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(blp[ent].address)));
/*
* Mark the data entry's space free.
*/
needlog = needscan = 0;
- xfs_dir2_data_make_free(tp, dp, bp,
+ xfs_dir2_data_make_free(args, bp,
(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
/*
@@ -821,7 +821,7 @@ xfs_dir2_block_removename(
if (needscan)
xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dp, bp);
+ xfs_dir2_data_log_header(args, bp);
xfs_dir3_data_check(dp, bp);
/*
* See if the size as a shortform is good enough.
@@ -866,20 +866,21 @@ xfs_dir2_block_replace(
dp = args->dp;
mp = dp->i_mount;
hdr = bp->b_addr;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Point to the data entry we need to change.
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(blp[ent].address)));
ASSERT(be64_to_cpu(dep->inumber) != args->inumber);
/*
* Change the inode number to the new value.
*/
dep->inumber = cpu_to_be64(args->inumber);
dp->d_ops->data_put_ftype(dep, args->filetype);
- xfs_dir2_data_log_entry(args->trans, dp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
xfs_dir3_data_check(dp, bp);
return 0;
}
@@ -939,7 +940,7 @@ xfs_dir2_leaf_to_block(
leaf = lbp->b_addr;
dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
ents = dp->d_ops->leaf_ents_p(leaf);
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
ASSERT(leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
leafhdr.magic == XFS_DIR3_LEAF1_MAGIC);
@@ -949,13 +950,13 @@ xfs_dir2_leaf_to_block(
* been left behind during no-space-reservation operations.
* These will show up in the leaf bests table.
*/
- while (dp->i_d.di_size > mp->m_dirblksize) {
+ while (dp->i_d.di_size > args->geo->blksize) {
int hdrsz;
hdrsz = dp->d_ops->data_entry_offset;
bestsp = xfs_dir2_leaf_bests_p(ltp);
if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) ==
- mp->m_dirblksize - hdrsz) {
+ args->geo->blksize - hdrsz) {
if ((error =
xfs_dir2_leaf_trim_data(args, lbp,
(xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
@@ -967,7 +968,7 @@ xfs_dir2_leaf_to_block(
* Read the data block if we don't already have it, give up if it fails.
*/
if (!dbp) {
- error = xfs_dir3_data_read(tp, dp, mp->m_dirdatablk, -1, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->geo->datablk, -1, &dbp);
if (error)
return error;
}
@@ -983,7 +984,7 @@ xfs_dir2_leaf_to_block(
/*
* Look at the last data entry.
*/
- tagp = (__be16 *)((char *)hdr + mp->m_dirblksize) - 1;
+ tagp = (__be16 *)((char *)hdr + args->geo->blksize) - 1;
dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
/*
* If it's not free or is too short we can't do it.
@@ -1002,12 +1003,12 @@ xfs_dir2_leaf_to_block(
/*
* Use up the space at the end of the block (blp/btp).
*/
- xfs_dir2_data_use_free(tp, dp, dbp, dup, mp->m_dirblksize - size, size,
+ xfs_dir2_data_use_free(args, dbp, dup, args->geo->blksize - size, size,
&needlog, &needscan);
/*
* Initialize the block tail.
*/
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
btp->count = cpu_to_be32(leafhdr.count - leafhdr.stale);
btp->stale = 0;
xfs_dir2_block_log_tail(tp, dbp);
@@ -1028,11 +1029,11 @@ xfs_dir2_leaf_to_block(
if (needscan)
xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
/*
* Pitch the old leaf block.
*/
- error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
+ error = xfs_da_shrink_inode(args, args->geo->leafblk, lbp);
if (error)
return error;
@@ -1141,13 +1142,13 @@ xfs_dir2_sf_to_block(
*/
dup = dp->d_ops->data_unused_p(hdr);
needlog = needscan = 0;
- xfs_dir2_data_use_free(tp, dp, bp, dup, mp->m_dirblksize - i, i, &needlog,
- &needscan);
+ xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
+ i, &needlog, &needscan);
ASSERT(needscan == 0);
/*
* Fill in the tail.
*/
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
btp->count = cpu_to_be32(sfp->count + 2); /* ., .. */
btp->stale = 0;
blp = xfs_dir2_block_leaf_p(btp);
@@ -1155,7 +1156,7 @@ xfs_dir2_sf_to_block(
/*
* Remove the freespace, we'll manage it.
*/
- xfs_dir2_data_use_free(tp, dp, bp, dup,
+ xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
be16_to_cpu(dup->length), &needlog, &needscan);
/*
@@ -1168,9 +1169,9 @@ xfs_dir2_sf_to_block(
dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, dp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
- blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
/*
* Create entry for ..
@@ -1182,9 +1183,9 @@ xfs_dir2_sf_to_block(
dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, dp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
- blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = dp->d_ops->data_first_offset;
/*
@@ -1216,7 +1217,7 @@ xfs_dir2_sf_to_block(
dup->length = cpu_to_be16(newoffset - offset);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
((char *)dup - (char *)hdr));
- xfs_dir2_data_log_unused(tp, bp, dup);
+ xfs_dir2_data_log_unused(args, bp, dup);
xfs_dir2_data_freeinsert(hdr,
dp->d_ops->data_bestfree_p(hdr),
dup, &dummy);
@@ -1233,12 +1234,12 @@ xfs_dir2_sf_to_block(
memcpy(dep->name, sfep->name, dep->namelen);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, dp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
name.name = sfep->name;
name.len = sfep->namelen;
blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
hashname(&name));
- blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = (int)((char *)(tagp + 1) - (char *)hdr);
if (++i == sfp->count)
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index afa4ad523f3f..8c2f6422648e 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -63,8 +63,10 @@ __xfs_dir3_data_check(
int stale; /* count of stale leaves */
struct xfs_name name;
const struct xfs_dir_ops *ops;
+ struct xfs_da_geometry *geo;
mp = bp->b_target->bt_mount;
+ geo = mp->m_dir_geo;
/*
* We can be passed a null dp here from a verifier, so we need to go the
@@ -78,7 +80,7 @@ __xfs_dir3_data_check(
switch (hdr->magic) {
case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(geo, hdr);
lep = xfs_dir2_block_leaf_p(btp);
endp = (char *)lep;
@@ -94,7 +96,7 @@ __xfs_dir3_data_check(
break;
case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
- endp = (char *)hdr + mp->m_dirblksize;
+ endp = (char *)hdr + geo->blksize;
break;
default:
XFS_ERROR_REPORT("Bad Magic", XFS_ERRLEVEL_LOW, mp);
@@ -172,9 +174,9 @@ __xfs_dir3_data_check(
lastfree = 0;
if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
- addr = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
- (xfs_dir2_data_aoff_t)
- ((char *)dep - (char *)hdr));
+ addr = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
+ (xfs_dir2_data_aoff_t)
+ ((char *)dep - (char *)hdr));
name.name = dep->name;
name.len = dep->namelen;
hash = mp->m_dirnameops->hashname(&name);
@@ -329,12 +331,11 @@ xfs_dir3_data_read(
int
xfs_dir3_data_readahead(
- struct xfs_trans *tp,
struct xfs_inode *dp,
xfs_dablk_t bno,
xfs_daddr_t mapped_bno)
{
- return xfs_da_reada_buf(tp, dp, bno, mapped_bno,
+ return xfs_da_reada_buf(dp, bno, mapped_bno,
XFS_DATA_FORK, &xfs_dir3_data_reada_buf_ops);
}
@@ -510,6 +511,7 @@ xfs_dir2_data_freescan(
struct xfs_dir2_data_free *bf;
char *endp; /* end of block's data */
char *p; /* current entry pointer */
+ struct xfs_da_geometry *geo = dp->i_mount->m_dir_geo;
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
@@ -528,10 +530,10 @@ xfs_dir2_data_freescan(
p = (char *)dp->d_ops->data_entry_p(hdr);
if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
- btp = xfs_dir2_block_tail_p(dp->i_mount, hdr);
+ btp = xfs_dir2_block_tail_p(geo, hdr);
endp = (char *)xfs_dir2_block_leaf_p(btp);
} else
- endp = (char *)hdr + dp->i_mount->m_dirblksize;
+ endp = (char *)hdr + geo->blksize;
/*
* Loop over the block's entries.
*/
@@ -585,8 +587,8 @@ xfs_dir3_data_init(
/*
* Get the buffer set up for the block.
*/
- error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, blkno), -1, &bp,
- XFS_DATA_FORK);
+ error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, blkno),
+ -1, &bp, XFS_DATA_FORK);
if (error)
return error;
bp->b_ops = &xfs_dir3_data_buf_ops;
@@ -621,15 +623,15 @@ xfs_dir3_data_init(
dup = dp->d_ops->data_unused_p(hdr);
dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
- t = mp->m_dirblksize - (uint)dp->d_ops->data_entry_offset;
+ t = args->geo->blksize - (uint)dp->d_ops->data_entry_offset;
bf[0].length = cpu_to_be16(t);
dup->length = cpu_to_be16(t);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)hdr);
/*
* Log it and return it.
*/
- xfs_dir2_data_log_header(tp, dp, bp);
- xfs_dir2_data_log_unused(tp, bp, dup);
+ xfs_dir2_data_log_header(args, bp);
+ xfs_dir2_data_log_unused(args, bp, dup);
*bpp = bp;
return 0;
}
@@ -639,8 +641,7 @@ xfs_dir3_data_init(
*/
void
xfs_dir2_data_log_entry(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
xfs_dir2_data_entry_t *dep) /* data entry pointer */
{
@@ -651,8 +652,8 @@ xfs_dir2_data_log_entry(
hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
- xfs_trans_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
- (uint)((char *)(dp->d_ops->data_entry_tag_p(dep) + 1) -
+ xfs_trans_log_buf(args->trans, bp, (uint)((char *)dep - (char *)hdr),
+ (uint)((char *)(args->dp->d_ops->data_entry_tag_p(dep) + 1) -
(char *)hdr - 1));
}
@@ -661,8 +662,7 @@ xfs_dir2_data_log_entry(
*/
void
xfs_dir2_data_log_header(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp)
{
#ifdef DEBUG
@@ -674,7 +674,8 @@ xfs_dir2_data_log_header(
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
#endif
- xfs_trans_log_buf(tp, bp, 0, dp->d_ops->data_entry_offset - 1);
+ xfs_trans_log_buf(args->trans, bp, 0,
+ args->dp->d_ops->data_entry_offset - 1);
}
/*
@@ -682,7 +683,7 @@ xfs_dir2_data_log_header(
*/
void
xfs_dir2_data_log_unused(
- struct xfs_trans *tp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
xfs_dir2_data_unused_t *dup) /* data unused pointer */
{
@@ -696,13 +697,13 @@ xfs_dir2_data_log_unused(
/*
* Log the first part of the unused entry.
*/
- xfs_trans_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
+ xfs_trans_log_buf(args->trans, bp, (uint)((char *)dup - (char *)hdr),
(uint)((char *)&dup->length + sizeof(dup->length) -
1 - (char *)hdr));
/*
* Log the end (tag) of the unused entry.
*/
- xfs_trans_log_buf(tp, bp,
+ xfs_trans_log_buf(args->trans, bp,
(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
sizeof(xfs_dir2_data_off_t) - 1));
@@ -714,8 +715,7 @@ xfs_dir2_data_log_unused(
*/
void
xfs_dir2_data_make_free(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
xfs_dir2_data_aoff_t offset, /* starting byte offset */
xfs_dir2_data_aoff_t len, /* length in bytes */
@@ -725,14 +725,12 @@ xfs_dir2_data_make_free(
xfs_dir2_data_hdr_t *hdr; /* data block pointer */
xfs_dir2_data_free_t *dfp; /* bestfree pointer */
char *endptr; /* end of data area */
- xfs_mount_t *mp; /* filesystem mount point */
int needscan; /* need to regen bestfree */
xfs_dir2_data_unused_t *newdup; /* new unused entry */
xfs_dir2_data_unused_t *postdup; /* unused entry after us */
xfs_dir2_data_unused_t *prevdup; /* unused entry before us */
struct xfs_dir2_data_free *bf;
- mp = tp->t_mountp;
hdr = bp->b_addr;
/*
@@ -740,20 +738,20 @@ xfs_dir2_data_make_free(
*/
if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC))
- endptr = (char *)hdr + mp->m_dirblksize;
+ endptr = (char *)hdr + args->geo->blksize;
else {
xfs_dir2_block_tail_t *btp; /* block tail */
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
endptr = (char *)xfs_dir2_block_leaf_p(btp);
}
/*
* If this isn't the start of the block, then back up to
* the previous entry and see if it's free.
*/
- if (offset > dp->d_ops->data_entry_offset) {
+ if (offset > args->dp->d_ops->data_entry_offset) {
__be16 *tagp; /* tag just before us */
tagp = (__be16 *)((char *)hdr + offset) - 1;
@@ -779,7 +777,7 @@ xfs_dir2_data_make_free(
* Previous and following entries are both free,
* merge everything into a single free entry.
*/
- bf = dp->d_ops->data_bestfree_p(hdr);
+ bf = args->dp->d_ops->data_bestfree_p(hdr);
if (prevdup && postdup) {
xfs_dir2_data_free_t *dfp2; /* another bestfree pointer */
@@ -801,7 +799,7 @@ xfs_dir2_data_make_free(
be16_add_cpu(&prevdup->length, len + be16_to_cpu(postdup->length));
*xfs_dir2_data_unused_tag_p(prevdup) =
cpu_to_be16((char *)prevdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, prevdup);
+ xfs_dir2_data_log_unused(args, bp, prevdup);
if (!needscan) {
/*
* Has to be the case that entries 0 and 1 are
@@ -836,7 +834,7 @@ xfs_dir2_data_make_free(
be16_add_cpu(&prevdup->length, len);
*xfs_dir2_data_unused_tag_p(prevdup) =
cpu_to_be16((char *)prevdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, prevdup);
+ xfs_dir2_data_log_unused(args, bp, prevdup);
/*
* If the previous entry was in the table, the new entry
* is longer, so it will be in the table too. Remove
@@ -864,7 +862,7 @@ xfs_dir2_data_make_free(
newdup->length = cpu_to_be16(len + be16_to_cpu(postdup->length));
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
/*
* If the following entry was in the table, the new entry
* is longer, so it will be in the table too. Remove
@@ -891,7 +889,7 @@ xfs_dir2_data_make_free(
newdup->length = cpu_to_be16(len);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
}
*needscanp = needscan;
@@ -902,8 +900,7 @@ xfs_dir2_data_make_free(
*/
void
xfs_dir2_data_use_free(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
xfs_dir2_data_unused_t *dup, /* unused entry */
xfs_dir2_data_aoff_t offset, /* starting offset to use */
@@ -934,7 +931,7 @@ xfs_dir2_data_use_free(
* Look up the entry in the bestfree table.
*/
oldlen = be16_to_cpu(dup->length);
- bf = dp->d_ops->data_bestfree_p(hdr);
+ bf = args->dp->d_ops->data_bestfree_p(hdr);
dfp = xfs_dir2_data_freefind(hdr, bf, dup);
ASSERT(dfp || oldlen <= be16_to_cpu(bf[2].length));
/*
@@ -966,7 +963,7 @@ xfs_dir2_data_use_free(
newdup->length = cpu_to_be16(oldlen - len);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
/*
* If it was in the table, remove it and add the new one.
*/
@@ -994,7 +991,7 @@ xfs_dir2_data_use_free(
newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
/*
* If it was in the table, remove it and add the new one.
*/
@@ -1022,13 +1019,13 @@ xfs_dir2_data_use_free(
newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
newdup2 = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len);
newdup2->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
newdup2->length = cpu_to_be16(oldlen - len - be16_to_cpu(newdup->length));
*xfs_dir2_data_unused_tag_p(newdup2) =
cpu_to_be16((char *)newdup2 - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup2);
+ xfs_dir2_data_log_unused(args, bp, newdup2);
/*
* If the old entry was in the table, we need to scan
* if the 3rd entry was valid, since these entries
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index d36e97df1187..fb0aad4440c1 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -41,9 +41,10 @@
*/
static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, struct xfs_buf **lbpp,
int *indexp, struct xfs_buf **dbpp);
-static void xfs_dir3_leaf_log_bests(struct xfs_trans *tp, struct xfs_buf *bp,
- int first, int last);
-static void xfs_dir3_leaf_log_tail(struct xfs_trans *tp, struct xfs_buf *bp);
+static void xfs_dir3_leaf_log_bests(struct xfs_da_args *args,
+ struct xfs_buf *bp, int first, int last);
+static void xfs_dir3_leaf_log_tail(struct xfs_da_args *args,
+ struct xfs_buf *bp);
/*
* Check the internal consistency of a leaf1 block.
@@ -92,6 +93,7 @@ xfs_dir3_leaf_check_int(
int i;
const struct xfs_dir_ops *ops;
struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_da_geometry *geo = mp->m_dir_geo;
/*
* we can be passed a null dp here from a verifier, so we need to go the
@@ -105,14 +107,14 @@ xfs_dir3_leaf_check_int(
}
ents = ops->leaf_ents_p(leaf);
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(geo, leaf);
/*
* XXX (dgc): This value is not restrictive enough.
* Should factor in the size of the bests table as well.
* We can deduce a value for that from di_size.
*/
- if (hdr->count > ops->leaf_max_ents(mp))
+ if (hdr->count > ops->leaf_max_ents(geo))
return false;
/* Leaves and bests don't overlap in leaf format. */
@@ -323,7 +325,7 @@ xfs_dir3_leaf_init(
if (type == XFS_DIR2_LEAF1_MAGIC) {
struct xfs_dir2_leaf_tail *ltp;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(mp->m_dir_geo, leaf);
ltp->bestcount = 0;
bp->b_ops = &xfs_dir3_leaf1_buf_ops;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAF1_BUF);
@@ -347,18 +349,18 @@ xfs_dir3_leaf_get_buf(
int error;
ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
- ASSERT(bno >= XFS_DIR2_LEAF_FIRSTDB(mp) &&
- bno < XFS_DIR2_FREE_FIRSTDB(mp));
+ ASSERT(bno >= xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET) &&
+ bno < xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET));
- error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, bno), -1, &bp,
- XFS_DATA_FORK);
+ error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, bno),
+ -1, &bp, XFS_DATA_FORK);
if (error)
return error;
xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
- xfs_dir3_leaf_log_header(tp, dp, bp);
+ xfs_dir3_leaf_log_header(args, bp);
if (magic == XFS_DIR2_LEAF1_MAGIC)
- xfs_dir3_leaf_log_tail(tp, bp);
+ xfs_dir3_leaf_log_tail(args, bp);
*bpp = bp;
return 0;
}
@@ -403,8 +405,8 @@ xfs_dir2_block_to_leaf(
if ((error = xfs_da_grow_inode(args, &blkno))) {
return error;
}
- ldb = xfs_dir2_da_to_db(mp, blkno);
- ASSERT(ldb == XFS_DIR2_LEAF_FIRSTDB(mp));
+ ldb = xfs_dir2_da_to_db(args->geo, blkno);
+ ASSERT(ldb == xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET));
/*
* Initialize the leaf block, get a buffer for it.
*/
@@ -415,7 +417,7 @@ xfs_dir2_block_to_leaf(
leaf = lbp->b_addr;
hdr = dbp->b_addr;
xfs_dir3_data_check(dp, dbp);
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
bf = dp->d_ops->data_bestfree_p(hdr);
ents = dp->d_ops->leaf_ents_p(leaf);
@@ -427,23 +429,23 @@ xfs_dir2_block_to_leaf(
leafhdr.count = be32_to_cpu(btp->count);
leafhdr.stale = be32_to_cpu(btp->stale);
dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
- xfs_dir3_leaf_log_header(tp, dp, lbp);
+ xfs_dir3_leaf_log_header(args, lbp);
/*
* Could compact these but I think we always do the conversion
* after squeezing out stale entries.
*/
memcpy(ents, blp, be32_to_cpu(btp->count) * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir3_leaf_log_ents(tp, dp, lbp, 0, leafhdr.count - 1);
+ xfs_dir3_leaf_log_ents(args, lbp, 0, leafhdr.count - 1);
needscan = 0;
needlog = 1;
/*
* Make the space formerly occupied by the leaf entries and block
* tail be free.
*/
- xfs_dir2_data_make_free(tp, dp, dbp,
+ xfs_dir2_data_make_free(args, dbp,
(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
- (xfs_dir2_data_aoff_t)((char *)hdr + mp->m_dirblksize -
+ (xfs_dir2_data_aoff_t)((char *)hdr + args->geo->blksize -
(char *)blp),
&needlog, &needscan);
/*
@@ -461,7 +463,7 @@ xfs_dir2_block_to_leaf(
/*
* Set up leaf tail and bests table.
*/
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
ltp->bestcount = cpu_to_be32(1);
bestsp = xfs_dir2_leaf_bests_p(ltp);
bestsp[0] = bf[0].length;
@@ -469,10 +471,10 @@ xfs_dir2_block_to_leaf(
* Log the data header and leaf bests table.
*/
if (needlog)
- xfs_dir2_data_log_header(tp, dp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
xfs_dir3_leaf_check(dp, lbp);
xfs_dir3_data_check(dp, dbp);
- xfs_dir3_leaf_log_bests(tp, lbp, 0, 0);
+ xfs_dir3_leaf_log_bests(args, lbp, 0, 0);
return 0;
}
@@ -641,7 +643,7 @@ xfs_dir2_leaf_addname(
tp = args->trans;
mp = dp->i_mount;
- error = xfs_dir3_leaf_read(tp, dp, mp->m_dirleafblk, -1, &lbp);
+ error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp);
if (error)
return error;
@@ -653,7 +655,7 @@ xfs_dir2_leaf_addname(
*/
index = xfs_dir2_leaf_search_hash(args, lbp);
leaf = lbp->b_addr;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
ents = dp->d_ops->leaf_ents_p(leaf);
dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
bestsp = xfs_dir2_leaf_bests_p(ltp);
@@ -670,7 +672,7 @@ xfs_dir2_leaf_addname(
index++, lep++) {
if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR)
continue;
- i = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ i = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
ASSERT(i < be32_to_cpu(ltp->bestcount));
ASSERT(bestsp[i] != cpu_to_be16(NULLDATAOFF));
if (be16_to_cpu(bestsp[i]) >= length) {
@@ -810,14 +812,15 @@ xfs_dir2_leaf_addname(
memmove(&bestsp[0], &bestsp[1],
be32_to_cpu(ltp->bestcount) * sizeof(bestsp[0]));
be32_add_cpu(&ltp->bestcount, 1);
- xfs_dir3_leaf_log_tail(tp, lbp);
- xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0,
+ be32_to_cpu(ltp->bestcount) - 1);
}
/*
* If we're filling in a previously empty block just log it.
*/
else
- xfs_dir3_leaf_log_bests(tp, lbp, use_block, use_block);
+ xfs_dir3_leaf_log_bests(args, lbp, use_block, use_block);
hdr = dbp->b_addr;
bf = dp->d_ops->data_bestfree_p(hdr);
bestsp[use_block] = bf[0].length;
@@ -828,8 +831,8 @@ xfs_dir2_leaf_addname(
* Just read that one in.
*/
error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(mp, use_block),
- -1, &dbp);
+ xfs_dir2_db_to_da(args->geo, use_block),
+ -1, &dbp);
if (error) {
xfs_trans_brelse(tp, lbp);
return error;
@@ -848,7 +851,7 @@ xfs_dir2_leaf_addname(
/*
* Mark the initial part of our freespace in use for the new entry.
*/
- xfs_dir2_data_use_free(tp, dp, dbp, dup,
+ xfs_dir2_data_use_free(args, dbp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
&needlog, &needscan);
/*
@@ -870,8 +873,8 @@ xfs_dir2_leaf_addname(
* Need to log the data block's header.
*/
if (needlog)
- xfs_dir2_data_log_header(tp, dp, dbp);
- xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+ xfs_dir2_data_log_header(args, dbp);
+ xfs_dir2_data_log_entry(args, dbp, dep);
/*
* If the bests table needs to be changed, do it.
* Log the change unless we've already done that.
@@ -879,7 +882,7 @@ xfs_dir2_leaf_addname(
if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(bf[0].length)) {
bestsp[use_block] = bf[0].length;
if (!grown)
- xfs_dir3_leaf_log_bests(tp, lbp, use_block, use_block);
+ xfs_dir3_leaf_log_bests(args, lbp, use_block, use_block);
}
lep = xfs_dir3_leaf_find_entry(&leafhdr, ents, index, compact, lowstale,
@@ -889,14 +892,15 @@ xfs_dir2_leaf_addname(
* Fill in the new leaf entry.
*/
lep->hashval = cpu_to_be32(args->hashval);
- lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp, use_block,
+ lep->address = cpu_to_be32(
+ xfs_dir2_db_off_to_dataptr(args->geo, use_block,
be16_to_cpu(*tagp)));
/*
* Log the leaf fields and give up the buffers.
*/
dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
- xfs_dir3_leaf_log_header(tp, dp, lbp);
- xfs_dir3_leaf_log_ents(tp, dp, lbp, lfloglow, lfloghigh);
+ xfs_dir3_leaf_log_header(args, lbp);
+ xfs_dir3_leaf_log_ents(args, lbp, lfloglow, lfloghigh);
xfs_dir3_leaf_check(dp, lbp);
xfs_dir3_data_check(dp, dbp);
return 0;
@@ -948,9 +952,9 @@ xfs_dir3_leaf_compact(
leafhdr->stale = 0;
dp->d_ops->leaf_hdr_to_disk(leaf, leafhdr);
- xfs_dir3_leaf_log_header(args->trans, dp, bp);
+ xfs_dir3_leaf_log_header(args, bp);
if (loglow != -1)
- xfs_dir3_leaf_log_ents(args->trans, dp, bp, loglow, to - 1);
+ xfs_dir3_leaf_log_ents(args, bp, loglow, to - 1);
}
/*
@@ -1052,7 +1056,7 @@ xfs_dir3_leaf_compact_x1(
*/
static void
xfs_dir3_leaf_log_bests(
- xfs_trans_t *tp, /* transaction pointer */
+ struct xfs_da_args *args,
struct xfs_buf *bp, /* leaf buffer */
int first, /* first entry to log */
int last) /* last entry to log */
@@ -1065,10 +1069,11 @@ xfs_dir3_leaf_log_bests(
ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC));
- ltp = xfs_dir2_leaf_tail_p(tp->t_mountp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
firstb = xfs_dir2_leaf_bests_p(ltp) + first;
lastb = xfs_dir2_leaf_bests_p(ltp) + last;
- xfs_trans_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)firstb - (char *)leaf),
(uint)((char *)lastb - (char *)leaf + sizeof(*lastb) - 1));
}
@@ -1077,8 +1082,7 @@ xfs_dir3_leaf_log_bests(
*/
void
xfs_dir3_leaf_log_ents(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
int first,
int last)
@@ -1093,10 +1097,11 @@ xfs_dir3_leaf_log_ents(
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
- ents = dp->d_ops->leaf_ents_p(leaf);
+ ents = args->dp->d_ops->leaf_ents_p(leaf);
firstlep = &ents[first];
lastlep = &ents[last];
- xfs_trans_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)firstlep - (char *)leaf),
(uint)((char *)lastlep - (char *)leaf + sizeof(*lastlep) - 1));
}
@@ -1105,8 +1110,7 @@ xfs_dir3_leaf_log_ents(
*/
void
xfs_dir3_leaf_log_header(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp)
{
struct xfs_dir2_leaf *leaf = bp->b_addr;
@@ -1116,8 +1120,9 @@ xfs_dir3_leaf_log_header(
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
- xfs_trans_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
- dp->d_ops->leaf_hdr_size - 1);
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)&leaf->hdr - (char *)leaf),
+ args->dp->d_ops->leaf_hdr_size - 1);
}
/*
@@ -1125,21 +1130,20 @@ xfs_dir3_leaf_log_header(
*/
STATIC void
xfs_dir3_leaf_log_tail(
- struct xfs_trans *tp,
+ struct xfs_da_args *args,
struct xfs_buf *bp)
{
struct xfs_dir2_leaf *leaf = bp->b_addr;
xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */
- struct xfs_mount *mp = tp->t_mountp;
ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
- xfs_trans_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
- (uint)(mp->m_dirblksize - 1));
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+ xfs_trans_log_buf(args->trans, bp, (uint)((char *)ltp - (char *)leaf),
+ (uint)(args->geo->blksize - 1));
}
/*
@@ -1185,7 +1189,7 @@ xfs_dir2_leaf_lookup(
*/
dep = (xfs_dir2_data_entry_t *)
((char *)dbp->b_addr +
- xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
+ xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
/*
* Return the found inode number & CI name if appropriate
*/
@@ -1231,7 +1235,7 @@ xfs_dir2_leaf_lookup_int(
tp = args->trans;
mp = dp->i_mount;
- error = xfs_dir3_leaf_read(tp, dp, mp->m_dirleafblk, -1, &lbp);
+ error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp);
if (error)
return error;
@@ -1260,7 +1264,8 @@ xfs_dir2_leaf_lookup_int(
/*
* Get the new data block number.
*/
- newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ newdb = xfs_dir2_dataptr_to_db(args->geo,
+ be32_to_cpu(lep->address));
/*
* If it's not the same as the old data block number,
* need to pitch the old one and read the new one.
@@ -1269,8 +1274,8 @@ xfs_dir2_leaf_lookup_int(
if (dbp)
xfs_trans_brelse(tp, dbp);
error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(mp, newdb),
- -1, &dbp);
+ xfs_dir2_db_to_da(args->geo, newdb),
+ -1, &dbp);
if (error) {
xfs_trans_brelse(tp, lbp);
return error;
@@ -1281,7 +1286,8 @@ xfs_dir2_leaf_lookup_int(
* Point to the data entry.
*/
dep = (xfs_dir2_data_entry_t *)((char *)dbp->b_addr +
- xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(lep->address)));
/*
* Compare name and if it's an exact match, return the index
* and buffer. If it's the first case-insensitive match, store
@@ -1310,8 +1316,8 @@ xfs_dir2_leaf_lookup_int(
if (cidb != curdb) {
xfs_trans_brelse(tp, dbp);
error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(mp, cidb),
- -1, &dbp);
+ xfs_dir2_db_to_da(args->geo, cidb),
+ -1, &dbp);
if (error) {
xfs_trans_brelse(tp, lbp);
return error;
@@ -1380,18 +1386,18 @@ xfs_dir2_leaf_removename(
* Point to the leaf entry, use that to point to the data entry.
*/
lep = &ents[index];
- db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+ db = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
needscan = needlog = 0;
oldbest = be16_to_cpu(bf[0].length);
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
bestsp = xfs_dir2_leaf_bests_p(ltp);
ASSERT(be16_to_cpu(bestsp[db]) == oldbest);
/*
* Mark the former data entry unused.
*/
- xfs_dir2_data_make_free(tp, dp, dbp,
+ xfs_dir2_data_make_free(args, dbp,
(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
/*
@@ -1399,10 +1405,10 @@ xfs_dir2_leaf_removename(
*/
leafhdr.stale++;
dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
- xfs_dir3_leaf_log_header(tp, dp, lbp);
+ xfs_dir3_leaf_log_header(args, lbp);
lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
- xfs_dir3_leaf_log_ents(tp, dp, lbp, index, index);
+ xfs_dir3_leaf_log_ents(args, lbp, index, index);
/*
* Scan the freespace in the data block again if necessary,
@@ -1411,22 +1417,22 @@ xfs_dir2_leaf_removename(
if (needscan)
xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
/*
* If the longest freespace in the data block has changed,
* put the new value in the bests table and log that.
*/
if (be16_to_cpu(bf[0].length) != oldbest) {
bestsp[db] = bf[0].length;
- xfs_dir3_leaf_log_bests(tp, lbp, db, db);
+ xfs_dir3_leaf_log_bests(args, lbp, db, db);
}
xfs_dir3_data_check(dp, dbp);
/*
* If the data block is now empty then get rid of the data block.
*/
if (be16_to_cpu(bf[0].length) ==
- mp->m_dirblksize - dp->d_ops->data_entry_offset) {
- ASSERT(db != mp->m_dirdatablk);
+ args->geo->blksize - dp->d_ops->data_entry_offset) {
+ ASSERT(db != args->geo->datablk);
if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
/*
* Nope, can't get rid of it because it caused
@@ -1459,15 +1465,16 @@ xfs_dir2_leaf_removename(
memmove(&bestsp[db - i], bestsp,
(be32_to_cpu(ltp->bestcount) - (db - i)) * sizeof(*bestsp));
be32_add_cpu(&ltp->bestcount, -(db - i));
- xfs_dir3_leaf_log_tail(tp, lbp);
- xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0,
+ be32_to_cpu(ltp->bestcount) - 1);
} else
bestsp[db] = cpu_to_be16(NULLDATAOFF);
}
/*
* If the data block was not the first one, drop it.
*/
- else if (db != mp->m_dirdatablk)
+ else if (db != args->geo->datablk)
dbp = NULL;
xfs_dir3_leaf_check(dp, lbp);
@@ -1515,7 +1522,7 @@ xfs_dir2_leaf_replace(
*/
dep = (xfs_dir2_data_entry_t *)
((char *)dbp->b_addr +
- xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
+ xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
ASSERT(args->inumber != be64_to_cpu(dep->inumber));
/*
* Put the new inode number in, log it.
@@ -1523,7 +1530,7 @@ xfs_dir2_leaf_replace(
dep->inumber = cpu_to_be64(args->inumber);
dp->d_ops->data_put_ftype(dep, args->filetype);
tp = args->trans;
- xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+ xfs_dir2_data_log_entry(args, dbp, dep);
xfs_dir3_leaf_check(dp, lbp);
xfs_trans_brelse(tp, lbp);
return 0;
@@ -1609,12 +1616,13 @@ xfs_dir2_leaf_trim_data(
/*
* Read the offending data block. We need its buffer.
*/
- error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(mp, db), -1, &dbp);
+ error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(args->geo, db),
+ -1, &dbp);
if (error)
return error;
leaf = lbp->b_addr;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
#ifdef DEBUG
{
@@ -1624,7 +1632,7 @@ xfs_dir2_leaf_trim_data(
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
ASSERT(be16_to_cpu(bf[0].length) ==
- mp->m_dirblksize - dp->d_ops->data_entry_offset);
+ args->geo->blksize - dp->d_ops->data_entry_offset);
ASSERT(db == be32_to_cpu(ltp->bestcount) - 1);
}
#endif
@@ -1643,8 +1651,8 @@ xfs_dir2_leaf_trim_data(
bestsp = xfs_dir2_leaf_bests_p(ltp);
be32_add_cpu(&ltp->bestcount, -1);
memmove(&bestsp[1], &bestsp[0], be32_to_cpu(ltp->bestcount) * sizeof(*bestsp));
- xfs_dir3_leaf_log_tail(tp, lbp);
- xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
return 0;
}
@@ -1708,22 +1716,22 @@ xfs_dir2_node_to_leaf(
/*
* Get the last offset in the file.
*/
- if ((error = xfs_bmap_last_offset(tp, dp, &fo, XFS_DATA_FORK))) {
+ if ((error = xfs_bmap_last_offset(dp, &fo, XFS_DATA_FORK))) {
return error;
}
- fo -= mp->m_dirblkfsbs;
+ fo -= args->geo->fsbcount;
/*
* If there are freespace blocks other than the first one,
* take this opportunity to remove trailing empty freespace blocks
* that may have been left behind during no-space-reservation
* operations.
*/
- while (fo > mp->m_dirfreeblk) {
+ while (fo > args->geo->freeblk) {
if ((error = xfs_dir2_node_trim_free(args, fo, &rval))) {
return error;
}
if (rval)
- fo -= mp->m_dirblkfsbs;
+ fo -= args->geo->fsbcount;
else
return 0;
}
@@ -1736,7 +1744,7 @@ xfs_dir2_node_to_leaf(
/*
* If it's not the single leaf block, give up.
*/
- if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + mp->m_dirblksize)
+ if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + args->geo->blksize)
return 0;
lbp = state->path.blk[0].bp;
leaf = lbp->b_addr;
@@ -1748,7 +1756,7 @@ xfs_dir2_node_to_leaf(
/*
* Read the freespace block.
*/
- error = xfs_dir2_free_read(tp, dp, mp->m_dirfreeblk, &fbp);
+ error = xfs_dir2_free_read(tp, dp, args->geo->freeblk, &fbp);
if (error)
return error;
free = fbp->b_addr;
@@ -1760,7 +1768,7 @@ xfs_dir2_node_to_leaf(
* Now see if the leafn and free data will fit in a leaf1.
* If not, release the buffer and give up.
*/
- if (xfs_dir3_leaf_size(&leafhdr, freehdr.nvalid) > mp->m_dirblksize) {
+ if (xfs_dir3_leaf_size(&leafhdr, freehdr.nvalid) > args->geo->blksize) {
xfs_trans_brelse(tp, fbp);
return 0;
}
@@ -1780,7 +1788,7 @@ xfs_dir2_node_to_leaf(
/*
* Set up the leaf tail from the freespace block.
*/
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
ltp->bestcount = cpu_to_be32(freehdr.nvalid);
/*
@@ -1790,15 +1798,17 @@ xfs_dir2_node_to_leaf(
freehdr.nvalid * sizeof(xfs_dir2_data_off_t));
dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
- xfs_dir3_leaf_log_header(tp, dp, lbp);
- xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
- xfs_dir3_leaf_log_tail(tp, lbp);
+ xfs_dir3_leaf_log_header(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
xfs_dir3_leaf_check(dp, lbp);
/*
* Get rid of the freespace block.
*/
- error = xfs_dir2_shrink_inode(args, XFS_DIR2_FREE_FIRSTDB(mp), fbp);
+ error = xfs_dir2_shrink_inode(args,
+ xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET),
+ fbp);
if (error) {
/*
* This can't fail here because it can only happen when
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index cb434d732681..da43d304fca2 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -195,17 +195,18 @@ xfs_dir2_free_try_read(
static int
xfs_dir3_free_get_buf(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ xfs_da_args_t *args,
xfs_dir2_db_t fbno,
struct xfs_buf **bpp)
{
+ struct xfs_trans *tp = args->trans;
+ struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_buf *bp;
int error;
struct xfs_dir3_icfree_hdr hdr;
- error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, fbno),
+ error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, fbno),
-1, &bp, XFS_DATA_FORK);
if (error)
return error;
@@ -240,8 +241,7 @@ xfs_dir3_free_get_buf(
*/
STATIC void
xfs_dir2_free_log_bests(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
int first, /* first entry to log */
int last) /* last entry to log */
@@ -250,10 +250,10 @@ xfs_dir2_free_log_bests(
__be16 *bests;
free = bp->b_addr;
- bests = dp->d_ops->free_bests_p(free);
+ bests = args->dp->d_ops->free_bests_p(free);
ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
- xfs_trans_log_buf(tp, bp,
+ xfs_trans_log_buf(args->trans, bp,
(uint)((char *)&bests[first] - (char *)free),
(uint)((char *)&bests[last] - (char *)free +
sizeof(bests[0]) - 1));
@@ -264,8 +264,7 @@ xfs_dir2_free_log_bests(
*/
static void
xfs_dir2_free_log_header(
- struct xfs_trans *tp,
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
struct xfs_buf *bp)
{
#ifdef DEBUG
@@ -275,7 +274,8 @@ xfs_dir2_free_log_header(
ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
#endif
- xfs_trans_log_buf(tp, bp, 0, dp->d_ops->free_hdr_size - 1);
+ xfs_trans_log_buf(args->trans, bp, 0,
+ args->dp->d_ops->free_hdr_size - 1);
}
/*
@@ -315,20 +315,20 @@ xfs_dir2_leaf_to_node(
if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_FREE_SPACE, &fdb))) {
return error;
}
- ASSERT(fdb == XFS_DIR2_FREE_FIRSTDB(mp));
+ ASSERT(fdb == xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET));
/*
* Get the buffer for the new freespace block.
*/
- error = xfs_dir3_free_get_buf(tp, dp, fdb, &fbp);
+ error = xfs_dir3_free_get_buf(args, fdb, &fbp);
if (error)
return error;
free = fbp->b_addr;
dp->d_ops->free_hdr_from_disk(&freehdr, free);
leaf = lbp->b_addr;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
ASSERT(be32_to_cpu(ltp->bestcount) <=
- (uint)dp->i_d.di_size / mp->m_dirblksize);
+ (uint)dp->i_d.di_size / args->geo->blksize);
/*
* Copy freespace entries from the leaf block to the new block.
@@ -349,8 +349,8 @@ xfs_dir2_leaf_to_node(
freehdr.nvalid = be32_to_cpu(ltp->bestcount);
dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
- xfs_dir2_free_log_bests(tp, dp, fbp, 0, freehdr.nvalid - 1);
- xfs_dir2_free_log_header(tp, dp, fbp);
+ xfs_dir2_free_log_bests(args, fbp, 0, freehdr.nvalid - 1);
+ xfs_dir2_free_log_header(args, fbp);
/*
* Converting the leaf to a leafnode is just a matter of changing the
@@ -364,7 +364,7 @@ xfs_dir2_leaf_to_node(
leaf->hdr.info.magic = cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
lbp->b_ops = &xfs_dir3_leafn_buf_ops;
xfs_trans_buf_set_type(tp, lbp, XFS_BLFT_DIR_LEAFN_BUF);
- xfs_dir3_leaf_log_header(tp, dp, lbp);
+ xfs_dir3_leaf_log_header(args, lbp);
xfs_dir3_leaf_check(dp, lbp);
return 0;
}
@@ -415,7 +415,7 @@ xfs_dir2_leafn_add(
* a compact.
*/
- if (leafhdr.count == dp->d_ops->leaf_max_ents(mp)) {
+ if (leafhdr.count == dp->d_ops->leaf_max_ents(args->geo)) {
if (!leafhdr.stale)
return XFS_ERROR(ENOSPC);
compact = leafhdr.stale > 1;
@@ -450,12 +450,12 @@ xfs_dir2_leafn_add(
highstale, &lfloglow, &lfloghigh);
lep->hashval = cpu_to_be32(args->hashval);
- lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp,
+ lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(args->geo,
args->blkno, args->index));
dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
- xfs_dir3_leaf_log_header(tp, dp, bp);
- xfs_dir3_leaf_log_ents(tp, dp, bp, lfloglow, lfloghigh);
+ xfs_dir3_leaf_log_header(args, bp);
+ xfs_dir3_leaf_log_ents(args, bp, lfloglow, lfloghigh);
xfs_dir3_leaf_check(dp, bp);
return 0;
}
@@ -471,7 +471,8 @@ xfs_dir2_free_hdr_check(
dp->d_ops->free_hdr_from_disk(&hdr, bp->b_addr);
- ASSERT((hdr.firstdb % dp->d_ops->free_max_bests(dp->i_mount)) == 0);
+ ASSERT((hdr.firstdb %
+ dp->d_ops->free_max_bests(dp->i_mount->m_dir_geo)) == 0);
ASSERT(hdr.firstdb <= db);
ASSERT(db < hdr.firstdb + hdr.nvalid);
}
@@ -576,7 +577,8 @@ xfs_dir2_leafn_lookup_for_addname(
/*
* Pull the data block number from the entry.
*/
- newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ newdb = xfs_dir2_dataptr_to_db(args->geo,
+ be32_to_cpu(lep->address));
/*
* For addname, we're looking for a place to put the new entry.
* We want to use a data block with an entry of equal
@@ -593,7 +595,7 @@ xfs_dir2_leafn_lookup_for_addname(
* Convert the data block to the free block
* holding its freespace information.
*/
- newfdb = dp->d_ops->db_to_fdb(mp, newdb);
+ newfdb = dp->d_ops->db_to_fdb(args->geo, newdb);
/*
* If it's not the one we have in hand, read it in.
*/
@@ -605,7 +607,8 @@ xfs_dir2_leafn_lookup_for_addname(
xfs_trans_brelse(tp, curbp);
error = xfs_dir2_free_read(tp, dp,
- xfs_dir2_db_to_da(mp, newfdb),
+ xfs_dir2_db_to_da(args->geo,
+ newfdb),
&curbp);
if (error)
return error;
@@ -616,7 +619,7 @@ xfs_dir2_leafn_lookup_for_addname(
/*
* Get the index for our entry.
*/
- fi = dp->d_ops->db_to_fdindex(mp, curdb);
+ fi = dp->d_ops->db_to_fdindex(args->geo, curdb);
/*
* If it has room, return it.
*/
@@ -721,7 +724,8 @@ xfs_dir2_leafn_lookup_for_entry(
/*
* Pull the data block number from the entry.
*/
- newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ newdb = xfs_dir2_dataptr_to_db(args->geo,
+ be32_to_cpu(lep->address));
/*
* Not adding a new entry, so we really want to find
* the name given to us.
@@ -746,7 +750,8 @@ xfs_dir2_leafn_lookup_for_entry(
curbp = state->extrablk.bp;
} else {
error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(mp, newdb),
+ xfs_dir2_db_to_da(args->geo,
+ newdb),
-1, &curbp);
if (error)
return error;
@@ -758,7 +763,8 @@ xfs_dir2_leafn_lookup_for_entry(
* Point to the data entry.
*/
dep = (xfs_dir2_data_entry_t *)((char *)curbp->b_addr +
- xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(lep->address)));
/*
* Compare the entry and if it's an exact match, return
* EEXIST immediately. If it's the first case-insensitive
@@ -844,7 +850,6 @@ xfs_dir3_leafn_moveents(
int start_d,/* destination leaf index */
int count) /* count of leaves to copy */
{
- struct xfs_trans *tp = args->trans;
int stale; /* count stale leaves copied */
trace_xfs_dir2_leafn_moveents(args, start_s, start_d, count);
@@ -863,7 +868,7 @@ xfs_dir3_leafn_moveents(
if (start_d < dhdr->count) {
memmove(&dents[start_d + count], &dents[start_d],
(dhdr->count - start_d) * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir3_leaf_log_ents(tp, args->dp, bp_d, start_d + count,
+ xfs_dir3_leaf_log_ents(args, bp_d, start_d + count,
count + dhdr->count - 1);
}
/*
@@ -885,8 +890,7 @@ xfs_dir3_leafn_moveents(
*/
memcpy(&dents[start_d], &sents[start_s],
count * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir3_leaf_log_ents(tp, args->dp, bp_d,
- start_d, start_d + count - 1);
+ xfs_dir3_leaf_log_ents(args, bp_d, start_d, start_d + count - 1);
/*
* If there are source entries after the ones we copied,
@@ -895,8 +899,7 @@ xfs_dir3_leafn_moveents(
if (start_s + count < shdr->count) {
memmove(&sents[start_s], &sents[start_s + count],
count * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir3_leaf_log_ents(tp, args->dp, bp_s,
- start_s, start_s + count - 1);
+ xfs_dir3_leaf_log_ents(args, bp_s, start_s, start_s + count - 1);
}
/*
@@ -1032,8 +1035,8 @@ xfs_dir2_leafn_rebalance(
/* log the changes made when moving the entries */
dp->d_ops->leaf_hdr_to_disk(leaf1, &hdr1);
dp->d_ops->leaf_hdr_to_disk(leaf2, &hdr2);
- xfs_dir3_leaf_log_header(args->trans, dp, blk1->bp);
- xfs_dir3_leaf_log_header(args->trans, dp, blk2->bp);
+ xfs_dir3_leaf_log_header(args, blk1->bp);
+ xfs_dir3_leaf_log_header(args, blk2->bp);
xfs_dir3_leaf_check(dp, blk1->bp);
xfs_dir3_leaf_check(dp, blk2->bp);
@@ -1076,7 +1079,6 @@ xfs_dir3_data_block_free(
struct xfs_buf *fbp,
int longest)
{
- struct xfs_trans *tp = args->trans;
int logfree = 0;
__be16 *bests;
struct xfs_dir3_icfree_hdr freehdr;
@@ -1090,7 +1092,7 @@ xfs_dir3_data_block_free(
* value.
*/
bests[findex] = cpu_to_be16(longest);
- xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
+ xfs_dir2_free_log_bests(args, fbp, findex, findex);
return 0;
}
@@ -1118,7 +1120,7 @@ xfs_dir3_data_block_free(
}
dp->d_ops->free_hdr_to_disk(free, &freehdr);
- xfs_dir2_free_log_header(tp, dp, fbp);
+ xfs_dir2_free_log_header(args, fbp);
/*
* If there are no useful entries left in the block, get rid of the
@@ -1142,7 +1144,7 @@ xfs_dir3_data_block_free(
/* Log the free entry that changed, unless we got rid of it. */
if (logfree)
- xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
+ xfs_dir2_free_log_bests(args, fbp, findex, findex);
return 0;
}
@@ -1193,9 +1195,9 @@ xfs_dir2_leafn_remove(
/*
* Extract the data block and offset from the entry.
*/
- db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ db = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
ASSERT(dblk->blkno == db);
- off = xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address));
+ off = xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address));
ASSERT(dblk->index == off);
/*
@@ -1204,10 +1206,10 @@ xfs_dir2_leafn_remove(
*/
leafhdr.stale++;
dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
- xfs_dir3_leaf_log_header(tp, dp, bp);
+ xfs_dir3_leaf_log_header(args, bp);
lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
- xfs_dir3_leaf_log_ents(tp, dp, bp, index, index);
+ xfs_dir3_leaf_log_ents(args, bp, index, index);
/*
* Make the data entry free. Keep track of the longest freespace
@@ -1219,7 +1221,7 @@ xfs_dir2_leafn_remove(
bf = dp->d_ops->data_bestfree_p(hdr);
longest = be16_to_cpu(bf[0].length);
needlog = needscan = 0;
- xfs_dir2_data_make_free(tp, dp, dbp, off,
+ xfs_dir2_data_make_free(args, dbp, off,
dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
/*
* Rescan the data block freespaces for bestfree.
@@ -1228,7 +1230,7 @@ xfs_dir2_leafn_remove(
if (needscan)
xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
xfs_dir3_data_check(dp, dbp);
/*
* If the longest data block freespace changes, need to update
@@ -1245,8 +1247,9 @@ xfs_dir2_leafn_remove(
* Convert the data block number to a free block,
* read in the free block.
*/
- fdb = dp->d_ops->db_to_fdb(mp, db);
- error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(mp, fdb),
+ fdb = dp->d_ops->db_to_fdb(args->geo, db);
+ error = xfs_dir2_free_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, fdb),
&fbp);
if (error)
return error;
@@ -1255,20 +1258,21 @@ xfs_dir2_leafn_remove(
{
struct xfs_dir3_icfree_hdr freehdr;
dp->d_ops->free_hdr_from_disk(&freehdr, free);
- ASSERT(freehdr.firstdb == dp->d_ops->free_max_bests(mp) *
- (fdb - XFS_DIR2_FREE_FIRSTDB(mp)));
+ ASSERT(freehdr.firstdb == dp->d_ops->free_max_bests(args->geo) *
+ (fdb - xfs_dir2_byte_to_db(args->geo,
+ XFS_DIR2_FREE_OFFSET)));
}
#endif
/*
* Calculate which entry we need to fix.
*/
- findex = dp->d_ops->db_to_fdindex(mp, db);
+ findex = dp->d_ops->db_to_fdindex(args->geo, db);
longest = be16_to_cpu(bf[0].length);
/*
* If the data block is now empty we can get rid of it
* (usually).
*/
- if (longest == mp->m_dirblksize -
+ if (longest == args->geo->blksize -
dp->d_ops->data_entry_offset) {
/*
* Try to punch out the data block.
@@ -1303,7 +1307,7 @@ xfs_dir2_leafn_remove(
*/
*rval = (dp->d_ops->leaf_hdr_size +
(uint)sizeof(ents[0]) * (leafhdr.count - leafhdr.stale)) <
- mp->m_dir_magicpct;
+ args->geo->magicpct;
return 0;
}
@@ -1336,7 +1340,7 @@ xfs_dir2_leafn_split(
/*
* Initialize the new leaf block.
*/
- error = xfs_dir3_leaf_get_buf(args, xfs_dir2_da_to_db(mp, blkno),
+ error = xfs_dir3_leaf_get_buf(args, xfs_dir2_da_to_db(args->geo, blkno),
&newblk->bp, XFS_DIR2_LEAFN_MAGIC);
if (error)
return error;
@@ -1410,7 +1414,7 @@ xfs_dir2_leafn_toosmall(
count = leafhdr.count - leafhdr.stale;
bytes = dp->d_ops->leaf_hdr_size + count * sizeof(ents[0]);
- if (bytes > (state->blocksize >> 1)) {
+ if (bytes > (state->args->geo->blksize >> 1)) {
/*
* Blk over 50%, don't try to join.
*/
@@ -1463,7 +1467,8 @@ xfs_dir2_leafn_toosmall(
* Count bytes in the two blocks combined.
*/
count = leafhdr.count - leafhdr.stale;
- bytes = state->blocksize - (state->blocksize >> 2);
+ bytes = state->args->geo->blksize -
+ (state->args->geo->blksize >> 2);
leaf = bp->b_addr;
dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf);
@@ -1560,8 +1565,8 @@ xfs_dir2_leafn_unbalance(
/* log the changes made when moving the entries */
dp->d_ops->leaf_hdr_to_disk(save_leaf, &savehdr);
dp->d_ops->leaf_hdr_to_disk(drop_leaf, &drophdr);
- xfs_dir3_leaf_log_header(args->trans, dp, save_blk->bp);
- xfs_dir3_leaf_log_header(args->trans, dp, drop_blk->bp);
+ xfs_dir3_leaf_log_header(args, save_blk->bp);
+ xfs_dir3_leaf_log_header(args, drop_blk->bp);
xfs_dir3_leaf_check(dp, save_blk->bp);
xfs_dir3_leaf_check(dp, drop_blk->bp);
@@ -1587,8 +1592,6 @@ xfs_dir2_node_addname(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
/*
* Look up the name. We're not supposed to find it, but
* this gives us the insertion point.
@@ -1727,9 +1730,9 @@ xfs_dir2_node_addname_int(
if (dbno == -1) {
xfs_fileoff_t fo; /* freespace block number */
- if ((error = xfs_bmap_last_offset(tp, dp, &fo, XFS_DATA_FORK)))
+ if ((error = xfs_bmap_last_offset(dp, &fo, XFS_DATA_FORK)))
return error;
- lastfbno = xfs_dir2_da_to_db(mp, (xfs_dablk_t)fo);
+ lastfbno = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)fo);
fbno = ifbno;
}
/*
@@ -1747,7 +1750,8 @@ xfs_dir2_node_addname_int(
* us a freespace block to start with.
*/
if (++fbno == 0)
- fbno = XFS_DIR2_FREE_FIRSTDB(mp);
+ fbno = xfs_dir2_byte_to_db(args->geo,
+ XFS_DIR2_FREE_OFFSET);
/*
* If it's ifbno we already looked at it.
*/
@@ -1765,8 +1769,8 @@ xfs_dir2_node_addname_int(
* to avoid it.
*/
error = xfs_dir2_free_try_read(tp, dp,
- xfs_dir2_db_to_da(mp, fbno),
- &fbp);
+ xfs_dir2_db_to_da(args->geo, fbno),
+ &fbp);
if (error)
return error;
if (!fbp)
@@ -1834,10 +1838,10 @@ xfs_dir2_node_addname_int(
* Get the freespace block corresponding to the data block
* that was just allocated.
*/
- fbno = dp->d_ops->db_to_fdb(mp, dbno);
+ fbno = dp->d_ops->db_to_fdb(args->geo, dbno);
error = xfs_dir2_free_try_read(tp, dp,
- xfs_dir2_db_to_da(mp, fbno),
- &fbp);
+ xfs_dir2_db_to_da(args->geo, fbno),
+ &fbp);
if (error)
return error;
@@ -1851,12 +1855,13 @@ xfs_dir2_node_addname_int(
if (error)
return error;
- if (unlikely(dp->d_ops->db_to_fdb(mp, dbno) != fbno)) {
+ if (dp->d_ops->db_to_fdb(args->geo, dbno) != fbno) {
xfs_alert(mp,
"%s: dir ino %llu needed freesp block %lld for\n"
" data block %lld, got %lld ifbno %llu lastfbno %d",
__func__, (unsigned long long)dp->i_ino,
- (long long)dp->d_ops->db_to_fdb(mp, dbno),
+ (long long)dp->d_ops->db_to_fdb(
+ args->geo, dbno),
(long long)dbno, (long long)fbno,
(unsigned long long)ifbno, lastfbno);
if (fblk) {
@@ -1877,7 +1882,7 @@ xfs_dir2_node_addname_int(
/*
* Get a buffer for the new block.
*/
- error = xfs_dir3_free_get_buf(tp, dp, fbno, &fbp);
+ error = xfs_dir3_free_get_buf(args, fbno, &fbp);
if (error)
return error;
free = fbp->b_addr;
@@ -1887,8 +1892,10 @@ xfs_dir2_node_addname_int(
/*
* Remember the first slot as our empty slot.
*/
- freehdr.firstdb = (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
- dp->d_ops->free_max_bests(mp);
+ freehdr.firstdb =
+ (fbno - xfs_dir2_byte_to_db(args->geo,
+ XFS_DIR2_FREE_OFFSET)) *
+ dp->d_ops->free_max_bests(args->geo);
} else {
free = fbp->b_addr;
bests = dp->d_ops->free_bests_p(free);
@@ -1898,13 +1905,13 @@ xfs_dir2_node_addname_int(
/*
* Set the freespace block index from the data block number.
*/
- findex = dp->d_ops->db_to_fdindex(mp, dbno);
+ findex = dp->d_ops->db_to_fdindex(args->geo, dbno);
/*
* If it's after the end of the current entries in the
* freespace block, extend that table.
*/
if (findex >= freehdr.nvalid) {
- ASSERT(findex < dp->d_ops->free_max_bests(mp));
+ ASSERT(findex < dp->d_ops->free_max_bests(args->geo));
freehdr.nvalid = findex + 1;
/*
* Tag new entry so nused will go up.
@@ -1918,7 +1925,7 @@ xfs_dir2_node_addname_int(
if (bests[findex] == cpu_to_be16(NULLDATAOFF)) {
freehdr.nused++;
dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
- xfs_dir2_free_log_header(tp, dp, fbp);
+ xfs_dir2_free_log_header(args, fbp);
}
/*
* Update the real value in the table.
@@ -1943,7 +1950,8 @@ xfs_dir2_node_addname_int(
/*
* Read the data block in.
*/
- error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(mp, dbno),
+ error = xfs_dir3_data_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, dbno),
-1, &dbp);
if (error)
return error;
@@ -1961,7 +1969,7 @@ xfs_dir2_node_addname_int(
/*
* Mark the first part of the unused space, inuse for us.
*/
- xfs_dir2_data_use_free(tp, dp, dbp, dup,
+ xfs_dir2_data_use_free(args, dbp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
&needlog, &needscan);
/*
@@ -1974,7 +1982,7 @@ xfs_dir2_node_addname_int(
dp->d_ops->data_put_ftype(dep, args->filetype);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+ xfs_dir2_data_log_entry(args, dbp, dep);
/*
* Rescan the block for bestfree if needed.
*/
@@ -1984,7 +1992,7 @@ xfs_dir2_node_addname_int(
* Log the data block header if needed.
*/
if (needlog)
- xfs_dir2_data_log_header(tp, dp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
/*
* If the freespace entry is now wrong, update it.
*/
@@ -1997,7 +2005,7 @@ xfs_dir2_node_addname_int(
* Log the freespace entry if needed.
*/
if (logfree)
- xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
+ xfs_dir2_free_log_bests(args, fbp, findex, findex);
/*
* Return the data block and offset in args, then drop the data block.
*/
@@ -2028,8 +2036,6 @@ xfs_dir2_node_lookup(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
/*
* Fill in the path to the entry in the cursor.
*/
@@ -2083,8 +2089,6 @@ xfs_dir2_node_removename(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
/* Look up the entry we're deleting, set up the cursor. */
error = xfs_da3_node_lookup_int(state, &rval);
@@ -2153,8 +2157,6 @@ xfs_dir2_node_replace(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
inum = args->inumber;
/*
* Lookup the entry to change in the btree.
@@ -2186,15 +2188,15 @@ xfs_dir2_node_replace(
hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
dep = (xfs_dir2_data_entry_t *)
((char *)hdr +
- xfs_dir2_dataptr_to_off(state->mp, be32_to_cpu(lep->address)));
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(lep->address)));
ASSERT(inum != be64_to_cpu(dep->inumber));
/*
* Fill in the new inode number and log the entry.
*/
dep->inumber = cpu_to_be64(inum);
args->dp->d_ops->data_put_ftype(dep, args->filetype);
- xfs_dir2_data_log_entry(args->trans, args->dp,
- state->extrablk.bp, dep);
+ xfs_dir2_data_log_entry(args, state->extrablk.bp, dep);
rval = 0;
}
/*
@@ -2262,9 +2264,9 @@ xfs_dir2_node_trim_free(
/*
* Blow the block away.
*/
- if ((error =
- xfs_dir2_shrink_inode(args, xfs_dir2_da_to_db(mp, (xfs_dablk_t)fo),
- bp))) {
+ error = xfs_dir2_shrink_inode(args,
+ xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)fo), bp);
+ if (error) {
/*
* Can't fail with ENOSPC since that only happens with no
* space reservation, when breaking up an extent into two
diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h
index 8b9d2281f85b..27ce0794d196 100644
--- a/fs/xfs/xfs_dir2_priv.h
+++ b/fs/xfs/xfs_dir2_priv.h
@@ -20,6 +20,140 @@
struct dir_context;
+/*
+ * Directory offset/block conversion functions.
+ *
+ * DB blocks here are logical directory block numbers, not filesystem blocks.
+ */
+
+/*
+ * Convert dataptr to byte in file space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_dataptr_to_byte(xfs_dir2_dataptr_t dp)
+{
+ return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
+}
+
+/*
+ * Convert byte in file space to dataptr. It had better be aligned.
+ */
+static inline xfs_dir2_dataptr_t
+xfs_dir2_byte_to_dataptr(xfs_dir2_off_t by)
+{
+ return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
+}
+
+/*
+ * Convert byte in space to (DB) block
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_byte_to_db(struct xfs_da_geometry *geo, xfs_dir2_off_t by)
+{
+ return (xfs_dir2_db_t)(by >> geo->blklog);
+}
+
+/*
+ * Convert dataptr to a block number
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_dataptr_to_db(struct xfs_da_geometry *geo, xfs_dir2_dataptr_t dp)
+{
+ return xfs_dir2_byte_to_db(geo, xfs_dir2_dataptr_to_byte(dp));
+}
+
+/*
+ * Convert byte in space to offset in a block
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_byte_to_off(struct xfs_da_geometry *geo, xfs_dir2_off_t by)
+{
+ return (xfs_dir2_data_aoff_t)(by & (geo->blksize - 1));
+}
+
+/*
+ * Convert dataptr to a byte offset in a block
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_dataptr_to_off(struct xfs_da_geometry *geo, xfs_dir2_dataptr_t dp)
+{
+ return xfs_dir2_byte_to_off(geo, xfs_dir2_dataptr_to_byte(dp));
+}
+
+/*
+ * Convert block and offset to byte in space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_db_off_to_byte(struct xfs_da_geometry *geo, xfs_dir2_db_t db,
+ xfs_dir2_data_aoff_t o)
+{
+ return ((xfs_dir2_off_t)db << geo->blklog) + o;
+}
+
+/*
+ * Convert block (DB) to block (dablk)
+ */
+static inline xfs_dablk_t
+xfs_dir2_db_to_da(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
+{
+ return (xfs_dablk_t)(db << (geo->blklog - geo->fsblog));
+}
+
+/*
+ * Convert byte in space to (DA) block
+ */
+static inline xfs_dablk_t
+xfs_dir2_byte_to_da(struct xfs_da_geometry *geo, xfs_dir2_off_t by)
+{
+ return xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, by));
+}
+
+/*
+ * Convert block and offset to dataptr
+ */
+static inline xfs_dir2_dataptr_t
+xfs_dir2_db_off_to_dataptr(struct xfs_da_geometry *geo, xfs_dir2_db_t db,
+ xfs_dir2_data_aoff_t o)
+{
+ return xfs_dir2_byte_to_dataptr(xfs_dir2_db_off_to_byte(geo, db, o));
+}
+
+/*
+ * Convert block (dablk) to block (DB)
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_da_to_db(struct xfs_da_geometry *geo, xfs_dablk_t da)
+{
+ return (xfs_dir2_db_t)(da >> (geo->blklog - geo->fsblog));
+}
+
+/*
+ * Convert block (dablk) to byte offset in space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_da_to_byte(struct xfs_da_geometry *geo, xfs_dablk_t da)
+{
+ return xfs_dir2_db_off_to_byte(geo, xfs_dir2_da_to_db(geo, da), 0);
+}
+
+/*
+ * Directory tail pointer accessor functions. Based on block geometry.
+ */
+static inline struct xfs_dir2_block_tail *
+xfs_dir2_block_tail_p(struct xfs_da_geometry *geo, struct xfs_dir2_data_hdr *hdr)
+{
+ return ((struct xfs_dir2_block_tail *)
+ ((char *)hdr + geo->blksize)) - 1;
+}
+
+static inline struct xfs_dir2_leaf_tail *
+xfs_dir2_leaf_tail_p(struct xfs_da_geometry *geo, struct xfs_dir2_leaf *lp)
+{
+ return (struct xfs_dir2_leaf_tail *)
+ ((char *)lp + geo->blksize -
+ sizeof(struct xfs_dir2_leaf_tail));
+}
+
/* xfs_dir2.c */
extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space,
@@ -54,8 +188,8 @@ extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args,
extern int __xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
extern int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mapped_bno, struct xfs_buf **bpp);
-extern int xfs_dir3_data_readahead(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t bno, xfs_daddr_t mapped_bno);
+extern int xfs_dir3_data_readahead(struct xfs_inode *dp, xfs_dablk_t bno,
+ xfs_daddr_t mapped_bno);
extern struct xfs_dir2_data_free *
xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
@@ -77,9 +211,9 @@ extern void xfs_dir3_leaf_compact_x1(struct xfs_dir3_icleaf_hdr *leafhdr,
int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
extern int xfs_dir3_leaf_get_buf(struct xfs_da_args *args, xfs_dir2_db_t bno,
struct xfs_buf **bpp, __uint16_t magic);
-extern void xfs_dir3_leaf_log_ents(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir3_leaf_log_ents(struct xfs_da_args *args,
struct xfs_buf *bp, int first, int last);
-extern void xfs_dir3_leaf_log_header(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir3_leaf_log_header(struct xfs_da_args *args,
struct xfs_buf *bp);
extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_leaf_removename(struct xfs_da_args *args);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index aead369e1c30..48e99afb9cb0 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -76,26 +76,25 @@ const unsigned char xfs_mode_to_ftype[S_IFMT >> S_SHIFT] = {
STATIC int
xfs_dir2_sf_getdents(
- xfs_inode_t *dp, /* incore directory inode */
+ struct xfs_da_args *args,
struct dir_context *ctx)
{
int i; /* shortform entry number */
- xfs_mount_t *mp; /* filesystem mount point */
+ struct xfs_inode *dp = args->dp; /* incore directory inode */
xfs_dir2_dataptr_t off; /* current entry's offset */
xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */
xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
xfs_dir2_dataptr_t dot_offset;
xfs_dir2_dataptr_t dotdot_offset;
xfs_ino_t ino;
-
- mp = dp->i_mount;
+ struct xfs_da_geometry *geo = args->geo;
ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
/*
* Give up if the directory is way too short.
*/
if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount));
return XFS_ERROR(EIO);
}
@@ -109,18 +108,18 @@ xfs_dir2_sf_getdents(
/*
* If the block number in the offset is out of range, we're done.
*/
- if (xfs_dir2_dataptr_to_db(mp, ctx->pos) > mp->m_dirdatablk)
+ if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
return 0;
/*
* Precalculate offsets for . and .. as we will always need them.
*
* XXX(hch): the second argument is sometimes 0 and sometimes
- * mp->m_dirdatablk.
+ * geo->datablk
*/
- dot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+ dot_offset = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
dp->d_ops->data_dot_offset);
- dotdot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+ dotdot_offset = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
dp->d_ops->data_dotdot_offset);
/*
@@ -149,7 +148,7 @@ xfs_dir2_sf_getdents(
for (i = 0; i < sfp->count; i++) {
__uint8_t filetype;
- off = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+ off = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
xfs_dir2_sf_get_offset(sfep));
if (ctx->pos > off) {
@@ -161,13 +160,13 @@ xfs_dir2_sf_getdents(
filetype = dp->d_ops->sf_get_ftype(sfep);
ctx->pos = off & 0x7fffffff;
if (!dir_emit(ctx, (char *)sfep->name, sfep->namelen, ino,
- xfs_dir3_get_dtype(mp, filetype)))
+ xfs_dir3_get_dtype(dp->i_mount, filetype)))
return 0;
sfep = dp->d_ops->sf_nextentry(sfp, sfep);
}
- ctx->pos = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
- 0x7fffffff;
+ ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
+ 0x7fffffff;
return 0;
}
@@ -176,9 +175,10 @@ xfs_dir2_sf_getdents(
*/
STATIC int
xfs_dir2_block_getdents(
- xfs_inode_t *dp, /* incore inode */
+ struct xfs_da_args *args,
struct dir_context *ctx)
{
+ struct xfs_inode *dp = args->dp; /* incore directory inode */
xfs_dir2_data_hdr_t *hdr; /* block header */
struct xfs_buf *bp; /* buffer for block */
xfs_dir2_block_tail_t *btp; /* block tail */
@@ -186,16 +186,15 @@ xfs_dir2_block_getdents(
xfs_dir2_data_unused_t *dup; /* block unused entry */
char *endptr; /* end of the data entries */
int error; /* error return value */
- xfs_mount_t *mp; /* filesystem mount point */
char *ptr; /* current data entry */
int wantoff; /* starting block offset */
xfs_off_t cook;
+ struct xfs_da_geometry *geo = args->geo;
- mp = dp->i_mount;
/*
* If the block number in the offset is out of range, we're done.
*/
- if (xfs_dir2_dataptr_to_db(mp, ctx->pos) > mp->m_dirdatablk)
+ if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
return 0;
error = xfs_dir3_block_read(NULL, dp, &bp);
@@ -206,13 +205,13 @@ xfs_dir2_block_getdents(
* Extract the byte offset we start at from the seek pointer.
* We'll skip entries before this.
*/
- wantoff = xfs_dir2_dataptr_to_off(mp, ctx->pos);
+ wantoff = xfs_dir2_dataptr_to_off(geo, ctx->pos);
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
/*
* Set up values for the loop.
*/
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(geo, hdr);
ptr = (char *)dp->d_ops->data_entry_p(hdr);
endptr = (char *)xfs_dir2_block_leaf_p(btp);
@@ -244,7 +243,7 @@ xfs_dir2_block_getdents(
if ((char *)dep - (char *)hdr < wantoff)
continue;
- cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+ cook = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
(char *)dep - (char *)hdr);
ctx->pos = cook & 0x7fffffff;
@@ -254,7 +253,7 @@ xfs_dir2_block_getdents(
*/
if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
be64_to_cpu(dep->inumber),
- xfs_dir3_get_dtype(mp, filetype))) {
+ xfs_dir3_get_dtype(dp->i_mount, filetype))) {
xfs_trans_brelse(NULL, bp);
return 0;
}
@@ -264,8 +263,8 @@ xfs_dir2_block_getdents(
* Reached the end of the block.
* Set the offset to a non-existent block 1 and return.
*/
- ctx->pos = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
- 0x7fffffff;
+ ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
+ 0x7fffffff;
xfs_trans_brelse(NULL, bp);
return 0;
}
@@ -286,13 +285,13 @@ struct xfs_dir2_leaf_map_info {
STATIC int
xfs_dir2_leaf_readbuf(
- struct xfs_inode *dp,
+ struct xfs_da_args *args,
size_t bufsize,
struct xfs_dir2_leaf_map_info *mip,
xfs_dir2_off_t *curoff,
struct xfs_buf **bpp)
{
- struct xfs_mount *mp = dp->i_mount;
+ struct xfs_inode *dp = args->dp;
struct xfs_buf *bp = *bpp;
struct xfs_bmbt_irec *map = mip->map;
struct blk_plug plug;
@@ -300,6 +299,7 @@ xfs_dir2_leaf_readbuf(
int length;
int i;
int j;
+ struct xfs_da_geometry *geo = args->geo;
/*
* If we have a buffer, we need to release it and
@@ -309,12 +309,12 @@ xfs_dir2_leaf_readbuf(
if (bp) {
xfs_trans_brelse(NULL, bp);
bp = NULL;
- mip->map_blocks -= mp->m_dirblkfsbs;
+ mip->map_blocks -= geo->fsbcount;
/*
* Loop to get rid of the extents for the
* directory block.
*/
- for (i = mp->m_dirblkfsbs; i > 0; ) {
+ for (i = geo->fsbcount; i > 0; ) {
j = min_t(int, map->br_blockcount, i);
map->br_blockcount -= j;
map->br_startblock += j;
@@ -333,8 +333,7 @@ xfs_dir2_leaf_readbuf(
/*
* Recalculate the readahead blocks wanted.
*/
- mip->ra_want = howmany(bufsize + mp->m_dirblksize,
- mp->m_sb.sb_blocksize) - 1;
+ mip->ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)) - 1;
ASSERT(mip->ra_want >= 0);
/*
@@ -342,14 +341,14 @@ xfs_dir2_leaf_readbuf(
* run out of data blocks, get some more mappings.
*/
if (1 + mip->ra_want > mip->map_blocks &&
- mip->map_off < xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
+ mip->map_off < xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET)) {
/*
* Get more bmaps, fill in after the ones
* we already have in the table.
*/
mip->nmap = mip->map_size - mip->map_valid;
error = xfs_bmapi_read(dp, mip->map_off,
- xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET) -
+ xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET) -
mip->map_off,
&map[mip->map_valid], &mip->nmap, 0);
@@ -370,7 +369,7 @@ xfs_dir2_leaf_readbuf(
i = mip->map_valid + mip->nmap - 1;
mip->map_off = map[i].br_startoff + map[i].br_blockcount;
} else
- mip->map_off = xfs_dir2_byte_to_da(mp,
+ mip->map_off = xfs_dir2_byte_to_da(geo,
XFS_DIR2_LEAF_OFFSET);
/*
@@ -396,18 +395,18 @@ xfs_dir2_leaf_readbuf(
* No valid mappings, so no more data blocks.
*/
if (!mip->map_valid) {
- *curoff = xfs_dir2_da_to_byte(mp, mip->map_off);
+ *curoff = xfs_dir2_da_to_byte(geo, mip->map_off);
goto out;
}
/*
* Read the directory block starting at the first mapping.
*/
- mip->curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
+ mip->curdb = xfs_dir2_da_to_db(geo, map->br_startoff);
error = xfs_dir3_data_read(NULL, dp, map->br_startoff,
- map->br_blockcount >= mp->m_dirblkfsbs ?
- XFS_FSB_TO_DADDR(mp, map->br_startblock) : -1, &bp);
-
+ map->br_blockcount >= geo->fsbcount ?
+ XFS_FSB_TO_DADDR(dp->i_mount, map->br_startblock) :
+ -1, &bp);
/*
* Should just skip over the data block instead of giving up.
*/
@@ -419,7 +418,7 @@ xfs_dir2_leaf_readbuf(
* was previously ra.
*/
if (mip->ra_current)
- mip->ra_current -= mp->m_dirblkfsbs;
+ mip->ra_current -= geo->fsbcount;
/*
* Do we need more readahead?
@@ -427,16 +426,16 @@ xfs_dir2_leaf_readbuf(
blk_start_plug(&plug);
for (mip->ra_index = mip->ra_offset = i = 0;
mip->ra_want > mip->ra_current && i < mip->map_blocks;
- i += mp->m_dirblkfsbs) {
+ i += geo->fsbcount) {
ASSERT(mip->ra_index < mip->map_valid);
/*
* Read-ahead a contiguous directory block.
*/
if (i > mip->ra_current &&
- map[mip->ra_index].br_blockcount >= mp->m_dirblkfsbs) {
- xfs_dir3_data_readahead(NULL, dp,
+ map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+ xfs_dir3_data_readahead(dp,
map[mip->ra_index].br_startoff + mip->ra_offset,
- XFS_FSB_TO_DADDR(mp,
+ XFS_FSB_TO_DADDR(dp->i_mount,
map[mip->ra_index].br_startblock +
mip->ra_offset));
mip->ra_current = i;
@@ -447,7 +446,7 @@ xfs_dir2_leaf_readbuf(
* use our mapping, but this is a very rare case.
*/
else if (i > mip->ra_current) {
- xfs_dir3_data_readahead(NULL, dp,
+ xfs_dir3_data_readahead(dp,
map[mip->ra_index].br_startoff +
mip->ra_offset, -1);
mip->ra_current = i;
@@ -456,15 +455,14 @@ xfs_dir2_leaf_readbuf(
/*
* Advance offset through the mapping table.
*/
- for (j = 0; j < mp->m_dirblkfsbs; j++) {
+ for (j = 0; j < geo->fsbcount; j += length ) {
/*
* The rest of this extent but not more than a dir
* block.
*/
- length = min_t(int, mp->m_dirblkfsbs,
+ length = min_t(int, geo->fsbcount,
map[mip->ra_index].br_blockcount -
mip->ra_offset);
- j += length;
mip->ra_offset += length;
/*
@@ -489,22 +487,23 @@ out:
*/
STATIC int
xfs_dir2_leaf_getdents(
- xfs_inode_t *dp, /* incore directory inode */
+ struct xfs_da_args *args,
struct dir_context *ctx,
size_t bufsize)
{
+ struct xfs_inode *dp = args->dp;
struct xfs_buf *bp = NULL; /* data block buffer */
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_dir2_data_entry_t *dep; /* data entry */
xfs_dir2_data_unused_t *dup; /* unused entry */
int error = 0; /* error return value */
int length; /* temporary length value */
- xfs_mount_t *mp; /* filesystem mount point */
int byteoff; /* offset in current block */
xfs_dir2_off_t curoff; /* current overall offset */
xfs_dir2_off_t newoff; /* new curoff after new blk */
char *ptr = NULL; /* pointer to current data */
struct xfs_dir2_leaf_map_info *map_info;
+ struct xfs_da_geometry *geo = args->geo;
/*
* If the offset is at or past the largest allowed value,
@@ -513,15 +512,12 @@ xfs_dir2_leaf_getdents(
if (ctx->pos >= XFS_DIR2_MAX_DATAPTR)
return 0;
- mp = dp->i_mount;
-
/*
* Set up to bmap a number of blocks based on the caller's
* buffer size, the directory block size, and the filesystem
* block size.
*/
- length = howmany(bufsize + mp->m_dirblksize,
- mp->m_sb.sb_blocksize);
+ length = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
(length * sizeof(struct xfs_bmbt_irec)),
KM_SLEEP | KM_NOFS);
@@ -531,14 +527,14 @@ xfs_dir2_leaf_getdents(
* Inside the loop we keep the main offset value as a byte offset
* in the directory file.
*/
- curoff = xfs_dir2_dataptr_to_byte(mp, ctx->pos);
+ curoff = xfs_dir2_dataptr_to_byte(ctx->pos);
/*
* Force this conversion through db so we truncate the offset
* down to get the start of the data block.
*/
- map_info->map_off = xfs_dir2_db_to_da(mp,
- xfs_dir2_byte_to_db(mp, curoff));
+ map_info->map_off = xfs_dir2_db_to_da(geo,
+ xfs_dir2_byte_to_db(geo, curoff));
/*
* Loop over directory entries until we reach the end offset.
@@ -551,9 +547,9 @@ xfs_dir2_leaf_getdents(
* If we have no buffer, or we're off the end of the
* current buffer, need to get another one.
*/
- if (!bp || ptr >= (char *)bp->b_addr + mp->m_dirblksize) {
+ if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) {
- error = xfs_dir2_leaf_readbuf(dp, bufsize, map_info,
+ error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
&curoff, &bp);
if (error || !map_info->map_valid)
break;
@@ -561,7 +557,8 @@ xfs_dir2_leaf_getdents(
/*
* Having done a read, we need to set a new offset.
*/
- newoff = xfs_dir2_db_off_to_byte(mp, map_info->curdb, 0);
+ newoff = xfs_dir2_db_off_to_byte(geo,
+ map_info->curdb, 0);
/*
* Start of the current block.
*/
@@ -571,7 +568,7 @@ xfs_dir2_leaf_getdents(
* Make sure we're in the right block.
*/
else if (curoff > newoff)
- ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
+ ASSERT(xfs_dir2_byte_to_db(geo, curoff) ==
map_info->curdb);
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
@@ -579,7 +576,7 @@ xfs_dir2_leaf_getdents(
* Find our position in the block.
*/
ptr = (char *)dp->d_ops->data_entry_p(hdr);
- byteoff = xfs_dir2_byte_to_off(mp, curoff);
+ byteoff = xfs_dir2_byte_to_off(geo, curoff);
/*
* Skip past the header.
*/
@@ -608,10 +605,10 @@ xfs_dir2_leaf_getdents(
* Now set our real offset.
*/
curoff =
- xfs_dir2_db_off_to_byte(mp,
- xfs_dir2_byte_to_db(mp, curoff),
+ xfs_dir2_db_off_to_byte(geo,
+ xfs_dir2_byte_to_db(geo, curoff),
(char *)ptr - (char *)hdr);
- if (ptr >= (char *)hdr + mp->m_dirblksize) {
+ if (ptr >= (char *)hdr + geo->blksize) {
continue;
}
}
@@ -635,10 +632,10 @@ xfs_dir2_leaf_getdents(
length = dp->d_ops->data_entsize(dep->namelen);
filetype = dp->d_ops->data_get_ftype(dep);
- ctx->pos = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
+ ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
be64_to_cpu(dep->inumber),
- xfs_dir3_get_dtype(mp, filetype)))
+ xfs_dir3_get_dtype(dp->i_mount, filetype)))
break;
/*
@@ -653,10 +650,10 @@ xfs_dir2_leaf_getdents(
/*
* All done. Set output offset value to current offset.
*/
- if (curoff > xfs_dir2_dataptr_to_byte(mp, XFS_DIR2_MAX_DATAPTR))
+ if (curoff > xfs_dir2_dataptr_to_byte(XFS_DIR2_MAX_DATAPTR))
ctx->pos = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
else
- ctx->pos = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
+ ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
kmem_free(map_info);
if (bp)
xfs_trans_brelse(NULL, bp);
@@ -668,13 +665,14 @@ xfs_dir2_leaf_getdents(
*/
int
xfs_readdir(
- xfs_inode_t *dp,
- struct dir_context *ctx,
- size_t bufsize)
+ struct xfs_inode *dp,
+ struct dir_context *ctx,
+ size_t bufsize)
{
- int rval; /* return value */
- int v; /* type-checking value */
- uint lock_mode;
+ struct xfs_da_args args = { NULL };
+ int rval;
+ int v;
+ uint lock_mode;
trace_xfs_readdir(dp);
@@ -684,15 +682,18 @@ xfs_readdir(
ASSERT(S_ISDIR(dp->i_d.di_mode));
XFS_STATS_INC(xs_dir_getdents);
+ args.dp = dp;
+ args.geo = dp->i_mount->m_dir_geo;
+
lock_mode = xfs_ilock_data_map_shared(dp);
if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_getdents(dp, ctx);
- else if ((rval = xfs_dir2_isblock(NULL, dp, &v)))
+ rval = xfs_dir2_sf_getdents(&args, ctx);
+ else if ((rval = xfs_dir2_isblock(&args, &v)))
;
else if (v)
- rval = xfs_dir2_block_getdents(dp, ctx);
+ rval = xfs_dir2_block_getdents(&args, ctx);
else
- rval = xfs_dir2_leaf_getdents(dp, ctx, bufsize);
+ rval = xfs_dir2_leaf_getdents(&args, ctx, bufsize);
xfs_iunlock(dp, lock_mode);
return rval;
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index 3725fb1b902b..53c3be619db5 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -82,8 +82,10 @@ xfs_dir2_block_sfsize(
xfs_ino_t parent = 0; /* parent inode number */
int size=0; /* total computed size */
int has_ftype;
+ struct xfs_da_geometry *geo;
mp = dp->i_mount;
+ geo = mp->m_dir_geo;
/*
* if there is a filetype field, add the extra byte to the namelen
@@ -92,7 +94,7 @@ xfs_dir2_block_sfsize(
has_ftype = xfs_sb_version_hasftype(&mp->m_sb) ? 1 : 0;
count = i8count = namelen = 0;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
@@ -104,8 +106,8 @@ xfs_dir2_block_sfsize(
/*
* Calculate the pointer to the entry at hand.
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(geo, addr));
/*
* Detect . and .., so we can special-case them.
* . is not included in sf directories.
@@ -195,7 +197,7 @@ xfs_dir2_block_to_sf(
/*
* Set up to loop over the block's entries.
*/
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
ptr = (char *)dp->d_ops->data_entry_p(hdr);
endptr = (char *)xfs_dir2_block_leaf_p(btp);
sfep = xfs_dir2_sf_firstentry(sfp);
@@ -247,7 +249,7 @@ xfs_dir2_block_to_sf(
/* now we are done with the block, we can shrink the inode */
logflags = XFS_ILOG_CORE;
- error = xfs_dir2_shrink_inode(args, mp->m_dirdatablk, bp);
+ error = xfs_dir2_shrink_inode(args, args->geo->datablk, bp);
if (error) {
ASSERT(error != ENOSPC);
goto out;
@@ -285,14 +287,12 @@ int /* error */
xfs_dir2_sf_addname(
xfs_da_args_t *args) /* operation arguments */
{
- int add_entsize; /* size of the new entry */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return value */
int incr_isize; /* total change in size */
int new_isize; /* di_size after adding name */
int objchange; /* changing to 8-byte inodes */
xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */
- int old_isize; /* di_size before adding name */
int pick; /* which algorithm to use */
xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
xfs_dir2_sf_entry_t *sfep = NULL; /* shortform entry */
@@ -316,8 +316,7 @@ xfs_dir2_sf_addname(
/*
* Compute entry (and change in) size.
*/
- add_entsize = dp->d_ops->sf_entsize(sfp, args->namelen);
- incr_isize = add_entsize;
+ incr_isize = dp->d_ops->sf_entsize(sfp, args->namelen);
objchange = 0;
#if XFS_BIG_INUMS
/*
@@ -325,11 +324,8 @@ xfs_dir2_sf_addname(
*/
if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) {
/*
- * Yes, adjust the entry size and the total size.
+ * Yes, adjust the inode size. old count + (parent + new)
*/
- add_entsize +=
- (uint)sizeof(xfs_dir2_ino8_t) -
- (uint)sizeof(xfs_dir2_ino4_t);
incr_isize +=
(sfp->count + 2) *
((uint)sizeof(xfs_dir2_ino8_t) -
@@ -337,8 +333,7 @@ xfs_dir2_sf_addname(
objchange = 1;
}
#endif
- old_isize = (int)dp->i_d.di_size;
- new_isize = old_isize + incr_isize;
+ new_isize = (int)dp->i_d.di_size + incr_isize;
/*
* Won't fit as shortform any more (due to size),
* or the pick routine says it won't (due to offset values).
@@ -593,7 +588,7 @@ xfs_dir2_sf_addname_pick(
* we'll go back, convert to block, then try the insert and convert
* to leaf.
*/
- if (used + (holefit ? 0 : size) > mp->m_dirblksize)
+ if (used + (holefit ? 0 : size) > args->geo->blksize)
return 0;
/*
* If changing the inode number size, do it the hard way.
@@ -608,7 +603,7 @@ xfs_dir2_sf_addname_pick(
/*
* If it won't fit at the end then do it the hard way (use the hole).
*/
- if (used + size > mp->m_dirblksize)
+ if (used + size > args->geo->blksize)
return 2;
/*
* Do it the easy way.
@@ -659,7 +654,7 @@ xfs_dir2_sf_check(
ASSERT((char *)sfep - (char *)sfp == dp->i_d.di_size);
ASSERT(offset +
(sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
- (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dirblksize);
+ (uint)sizeof(xfs_dir2_block_tail_t) <= args->geo->blksize);
}
#endif /* DEBUG */
@@ -1110,9 +1105,9 @@ xfs_dir2_sf_toino4(
}
/*
- * Convert from 4-byte inode numbers to 8-byte inode numbers.
- * The new 8-byte inode number is not there yet, we leave with the
- * count 1 but no corresponding entry.
+ * Convert existing entries from 4-byte inode numbers to 8-byte inode numbers.
+ * The new entry w/ an 8-byte inode number is not there yet; we leave with
+ * i8count set to 1, but no corresponding 8-byte entry.
*/
static void
xfs_dir2_sf_toino8(
@@ -1145,7 +1140,7 @@ xfs_dir2_sf_toino8(
ASSERT(oldsfp->i8count == 0);
memcpy(buf, oldsfp, oldsize);
/*
- * Compute the new inode size.
+ * Compute the new inode size (nb: entry count + 1 for parent)
*/
newsize =
oldsize +
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 868b19f096bf..3ee0cd43edc0 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -353,10 +353,10 @@ xfs_qm_dqalloc(
dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen,
0);
-
- error = xfs_buf_geterror(bp);
- if (error)
+ if (!bp) {
+ error = ENOMEM;
goto error1;
+ }
bp->b_ops = &xfs_dquot_buf_ops;
/*
@@ -832,47 +832,6 @@ restart:
return (0);
}
-
-STATIC void
-xfs_qm_dqput_final(
- struct xfs_dquot *dqp)
-{
- struct xfs_quotainfo *qi = dqp->q_mount->m_quotainfo;
- struct xfs_dquot *gdqp;
- struct xfs_dquot *pdqp;
-
- trace_xfs_dqput_free(dqp);
-
- if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
- XFS_STATS_INC(xs_qm_dquot_unused);
-
- /*
- * If we just added a udquot to the freelist, then we want to release
- * the gdquot/pdquot reference that it (probably) has. Otherwise it'll
- * keep the gdquot/pdquot from getting reclaimed.
- */
- gdqp = dqp->q_gdquot;
- if (gdqp) {
- xfs_dqlock(gdqp);
- dqp->q_gdquot = NULL;
- }
-
- pdqp = dqp->q_pdquot;
- if (pdqp) {
- xfs_dqlock(pdqp);
- dqp->q_pdquot = NULL;
- }
- xfs_dqunlock(dqp);
-
- /*
- * If we had a group/project quota hint, release it now.
- */
- if (gdqp)
- xfs_qm_dqput(gdqp);
- if (pdqp)
- xfs_qm_dqput(pdqp);
-}
-
/*
* Release a reference to the dquot (decrement ref-count) and unlock it.
*
@@ -888,10 +847,14 @@ xfs_qm_dqput(
trace_xfs_dqput(dqp);
- if (--dqp->q_nrefs > 0)
- xfs_dqunlock(dqp);
- else
- xfs_qm_dqput_final(dqp);
+ if (--dqp->q_nrefs == 0) {
+ struct xfs_quotainfo *qi = dqp->q_mount->m_quotainfo;
+ trace_xfs_dqput_free(dqp);
+
+ if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
+ XFS_STATS_INC(xs_qm_dquot_unused);
+ }
+ xfs_dqunlock(dqp);
}
/*
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index d22ed0053c32..68a68f704837 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -52,8 +52,6 @@ typedef struct xfs_dquot {
int q_bufoffset; /* off of dq in buffer (# dquots) */
xfs_fileoff_t q_fileoffset; /* offset in quotas file */
- struct xfs_dquot*q_gdquot; /* group dquot, hint only */
- struct xfs_dquot*q_pdquot; /* project dquot, hint only */
xfs_disk_dquot_t q_core; /* actual usage & quotas */
xfs_dq_logitem_t q_logitem; /* dquot log item */
xfs_qcnt_t q_res_bcount; /* total regular nblks used+reserved */
diff --git a/fs/xfs/xfs_dquot_buf.c b/fs/xfs/xfs_dquot_buf.c
index 610da8177737..c2ac0c611ad8 100644
--- a/fs/xfs/xfs_dquot_buf.c
+++ b/fs/xfs/xfs_dquot_buf.c
@@ -35,7 +35,6 @@
int
xfs_calc_dquots_per_chunk(
- struct xfs_mount *mp,
unsigned int nbblks) /* basic block units */
{
unsigned int ndquots;
@@ -194,7 +193,7 @@ xfs_dquot_buf_verify_crc(
if (mp->m_quotainfo)
ndquots = mp->m_quotainfo->qi_dqperchunk;
else
- ndquots = xfs_calc_dquots_per_chunk(mp,
+ ndquots = xfs_calc_dquots_per_chunk(
XFS_BB_TO_FSB(mp, bp->b_length));
for (i = 0; i < ndquots; i++, d++) {
@@ -225,7 +224,7 @@ xfs_dquot_buf_verify(
if (mp->m_quotainfo)
ndquots = mp->m_quotainfo->qi_dqperchunk;
else
- ndquots = xfs_calc_dquots_per_chunk(mp, bp->b_length);
+ ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
/*
* On the first read of the buffer, verify that each dquot is valid.
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 830c1c937b88..1b8160dc04d1 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -944,7 +944,7 @@ xfs_dir_open(
*/
mode = xfs_ilock_data_map_shared(ip);
if (ip->i_d.di_nextents > 0)
- xfs_dir3_data_readahead(NULL, ip, 0, -1);
+ xfs_dir3_data_readahead(ip, 0, -1);
xfs_iunlock(ip, mode);
return 0;
}
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 12b6e7701985..8ec81bed7992 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2006-2007 Silicon Graphics, Inc.
+ * Copyright (c) 2014 Christoph Hellwig.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -32,100 +33,20 @@
#include "xfs_filestream.h"
#include "xfs_trace.h"
-#ifdef XFS_FILESTREAMS_TRACE
-
-ktrace_t *xfs_filestreams_trace_buf;
-
-STATIC void
-xfs_filestreams_trace(
- xfs_mount_t *mp, /* mount point */
- int type, /* type of trace */
- const char *func, /* source function */
- int line, /* source line number */
- __psunsigned_t arg0,
- __psunsigned_t arg1,
- __psunsigned_t arg2,
- __psunsigned_t arg3,
- __psunsigned_t arg4,
- __psunsigned_t arg5)
-{
- ktrace_enter(xfs_filestreams_trace_buf,
- (void *)(__psint_t)(type | (line << 16)),
- (void *)func,
- (void *)(__psunsigned_t)current_pid(),
- (void *)mp,
- (void *)(__psunsigned_t)arg0,
- (void *)(__psunsigned_t)arg1,
- (void *)(__psunsigned_t)arg2,
- (void *)(__psunsigned_t)arg3,
- (void *)(__psunsigned_t)arg4,
- (void *)(__psunsigned_t)arg5,
- NULL, NULL, NULL, NULL, NULL, NULL);
-}
-
-#define TRACE0(mp,t) TRACE6(mp,t,0,0,0,0,0,0)
-#define TRACE1(mp,t,a0) TRACE6(mp,t,a0,0,0,0,0,0)
-#define TRACE2(mp,t,a0,a1) TRACE6(mp,t,a0,a1,0,0,0,0)
-#define TRACE3(mp,t,a0,a1,a2) TRACE6(mp,t,a0,a1,a2,0,0,0)
-#define TRACE4(mp,t,a0,a1,a2,a3) TRACE6(mp,t,a0,a1,a2,a3,0,0)
-#define TRACE5(mp,t,a0,a1,a2,a3,a4) TRACE6(mp,t,a0,a1,a2,a3,a4,0)
-#define TRACE6(mp,t,a0,a1,a2,a3,a4,a5) \
- xfs_filestreams_trace(mp, t, __func__, __LINE__, \
- (__psunsigned_t)a0, (__psunsigned_t)a1, \
- (__psunsigned_t)a2, (__psunsigned_t)a3, \
- (__psunsigned_t)a4, (__psunsigned_t)a5)
-
-#define TRACE_AG_SCAN(mp, ag, ag2) \
- TRACE2(mp, XFS_FSTRM_KTRACE_AGSCAN, ag, ag2);
-#define TRACE_AG_PICK1(mp, max_ag, maxfree) \
- TRACE2(mp, XFS_FSTRM_KTRACE_AGPICK1, max_ag, maxfree);
-#define TRACE_AG_PICK2(mp, ag, ag2, cnt, free, scan, flag) \
- TRACE6(mp, XFS_FSTRM_KTRACE_AGPICK2, ag, ag2, \
- cnt, free, scan, flag)
-#define TRACE_UPDATE(mp, ip, ag, cnt, ag2, cnt2) \
- TRACE5(mp, XFS_FSTRM_KTRACE_UPDATE, ip, ag, cnt, ag2, cnt2)
-#define TRACE_FREE(mp, ip, pip, ag, cnt) \
- TRACE4(mp, XFS_FSTRM_KTRACE_FREE, ip, pip, ag, cnt)
-#define TRACE_LOOKUP(mp, ip, pip, ag, cnt) \
- TRACE4(mp, XFS_FSTRM_KTRACE_ITEM_LOOKUP, ip, pip, ag, cnt)
-#define TRACE_ASSOCIATE(mp, ip, pip, ag, cnt) \
- TRACE4(mp, XFS_FSTRM_KTRACE_ASSOCIATE, ip, pip, ag, cnt)
-#define TRACE_MOVEAG(mp, ip, pip, oag, ocnt, nag, ncnt) \
- TRACE6(mp, XFS_FSTRM_KTRACE_MOVEAG, ip, pip, oag, ocnt, nag, ncnt)
-#define TRACE_ORPHAN(mp, ip, ag) \
- TRACE2(mp, XFS_FSTRM_KTRACE_ORPHAN, ip, ag);
-
-
-#else
-#define TRACE_AG_SCAN(mp, ag, ag2)
-#define TRACE_AG_PICK1(mp, max_ag, maxfree)
-#define TRACE_AG_PICK2(mp, ag, ag2, cnt, free, scan, flag)
-#define TRACE_UPDATE(mp, ip, ag, cnt, ag2, cnt2)
-#define TRACE_FREE(mp, ip, pip, ag, cnt)
-#define TRACE_LOOKUP(mp, ip, pip, ag, cnt)
-#define TRACE_ASSOCIATE(mp, ip, pip, ag, cnt)
-#define TRACE_MOVEAG(mp, ip, pip, oag, ocnt, nag, ncnt)
-#define TRACE_ORPHAN(mp, ip, ag)
-#endif
-
-static kmem_zone_t *item_zone;
+struct xfs_fstrm_item {
+ struct xfs_mru_cache_elem mru;
+ struct xfs_inode *ip;
+ xfs_agnumber_t ag; /* AG in use for this directory */
+};
-/*
- * Structure for associating a file or a directory with an allocation group.
- * The parent directory pointer is only needed for files, but since there will
- * generally be vastly more files than directories in the cache, using the same
- * data structure simplifies the code with very little memory overhead.
- */
-typedef struct fstrm_item
-{
- xfs_agnumber_t ag; /* AG currently in use for the file/directory. */
- xfs_inode_t *ip; /* inode self-pointer. */
- xfs_inode_t *pip; /* Parent directory inode pointer. */
-} fstrm_item_t;
+enum xfs_fstrm_alloc {
+ XFS_PICK_USERDATA = 1,
+ XFS_PICK_LOWSPACE = 2,
+};
/*
* Allocation group filestream associations are tracked with per-ag atomic
- * counters. These counters allow _xfs_filestream_pick_ag() to tell whether a
+ * counters. These counters allow xfs_filestream_pick_ag() to tell whether a
* particular AG already has active filestreams associated with it. The mount
* point's m_peraglock is used to protect these counters from per-ag array
* re-allocation during a growfs operation. When xfs_growfs_data_private() is
@@ -160,7 +81,7 @@ typedef struct fstrm_item
* the cache that reference per-ag array elements that have since been
* reallocated.
*/
-static int
+int
xfs_filestream_peek_ag(
xfs_mount_t *mp,
xfs_agnumber_t agno)
@@ -200,23 +121,40 @@ xfs_filestream_put_ag(
xfs_perag_put(pag);
}
+static void
+xfs_fstrm_free_func(
+ struct xfs_mru_cache_elem *mru)
+{
+ struct xfs_fstrm_item *item =
+ container_of(mru, struct xfs_fstrm_item, mru);
+
+ xfs_filestream_put_ag(item->ip->i_mount, item->ag);
+
+ trace_xfs_filestream_free(item->ip, item->ag);
+
+ kmem_free(item);
+}
+
/*
* Scan the AGs starting at startag looking for an AG that isn't in use and has
* at least minlen blocks free.
*/
static int
-_xfs_filestream_pick_ag(
- xfs_mount_t *mp,
- xfs_agnumber_t startag,
- xfs_agnumber_t *agp,
- int flags,
- xfs_extlen_t minlen)
+xfs_filestream_pick_ag(
+ struct xfs_inode *ip,
+ xfs_agnumber_t startag,
+ xfs_agnumber_t *agp,
+ int flags,
+ xfs_extlen_t minlen)
{
- int streams, max_streams;
- int err, trylock, nscan;
- xfs_extlen_t longest, free, minfree, maxfree = 0;
- xfs_agnumber_t ag, max_ag = NULLAGNUMBER;
- struct xfs_perag *pag;
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_fstrm_item *item;
+ struct xfs_perag *pag;
+ xfs_extlen_t longest, free = 0, minfree, maxfree = 0;
+ xfs_agnumber_t ag, max_ag = NULLAGNUMBER;
+ int err, trylock, nscan;
+
+ ASSERT(S_ISDIR(ip->i_d.di_mode));
/* 2% of an AG's blocks must be free for it to be chosen. */
minfree = mp->m_sb.sb_agblocks / 50;
@@ -228,8 +166,9 @@ _xfs_filestream_pick_ag(
trylock = XFS_ALLOC_FLAG_TRYLOCK;
for (nscan = 0; 1; nscan++) {
+ trace_xfs_filestream_scan(ip, ag);
+
pag = xfs_perag_get(mp, ag);
- TRACE_AG_SCAN(mp, ag, atomic_read(&pag->pagf_fstrms));
if (!pag->pagf_init) {
err = xfs_alloc_pagf_init(mp, NULL, ag, trylock);
@@ -246,7 +185,6 @@ _xfs_filestream_pick_ag(
/* Keep track of the AG with the most free blocks. */
if (pag->pagf_freeblks > maxfree) {
maxfree = pag->pagf_freeblks;
- max_streams = atomic_read(&pag->pagf_fstrms);
max_ag = ag;
}
@@ -269,7 +207,6 @@ _xfs_filestream_pick_ag(
/* Break out, retaining the reference on the AG. */
free = pag->pagf_freeblks;
- streams = atomic_read(&pag->pagf_fstrms);
xfs_perag_put(pag);
*agp = ag;
break;
@@ -305,317 +242,98 @@ next_ag:
*/
if (max_ag != NULLAGNUMBER) {
xfs_filestream_get_ag(mp, max_ag);
- TRACE_AG_PICK1(mp, max_ag, maxfree);
- streams = max_streams;
free = maxfree;
*agp = max_ag;
break;
}
/* take AG 0 if none matched */
- TRACE_AG_PICK1(mp, max_ag, maxfree);
+ trace_xfs_filestream_pick(ip, *agp, free, nscan);
*agp = 0;
return 0;
}
- TRACE_AG_PICK2(mp, startag, *agp, streams, free, nscan, flags);
-
- return 0;
-}
+ trace_xfs_filestream_pick(ip, *agp, free, nscan);
-/*
- * Set the allocation group number for a file or a directory, updating inode
- * references and per-AG references as appropriate.
- */
-static int
-_xfs_filestream_update_ag(
- xfs_inode_t *ip,
- xfs_inode_t *pip,
- xfs_agnumber_t ag)
-{
- int err = 0;
- xfs_mount_t *mp;
- xfs_mru_cache_t *cache;
- fstrm_item_t *item;
- xfs_agnumber_t old_ag;
- xfs_inode_t *old_pip;
-
- /*
- * Either ip is a regular file and pip is a directory, or ip is a
- * directory and pip is NULL.
- */
- ASSERT(ip && ((S_ISREG(ip->i_d.di_mode) && pip &&
- S_ISDIR(pip->i_d.di_mode)) ||
- (S_ISDIR(ip->i_d.di_mode) && !pip)));
-
- mp = ip->i_mount;
- cache = mp->m_filestream;
-
- item = xfs_mru_cache_lookup(cache, ip->i_ino);
- if (item) {
- ASSERT(item->ip == ip);
- old_ag = item->ag;
- item->ag = ag;
- old_pip = item->pip;
- item->pip = pip;
- xfs_mru_cache_done(cache);
-
- /*
- * If the AG has changed, drop the old ref and take a new one,
- * effectively transferring the reference from old to new AG.
- */
- if (ag != old_ag) {
- xfs_filestream_put_ag(mp, old_ag);
- xfs_filestream_get_ag(mp, ag);
- }
-
- /*
- * If ip is a file and its pip has changed, drop the old ref and
- * take a new one.
- */
- if (pip && pip != old_pip) {
- IRELE(old_pip);
- IHOLD(pip);
- }
-
- TRACE_UPDATE(mp, ip, old_ag, xfs_filestream_peek_ag(mp, old_ag),
- ag, xfs_filestream_peek_ag(mp, ag));
+ if (*agp == NULLAGNUMBER)
return 0;
- }
- item = kmem_zone_zalloc(item_zone, KM_MAYFAIL);
+ err = ENOMEM;
+ item = kmem_alloc(sizeof(*item), KM_MAYFAIL);
if (!item)
- return ENOMEM;
+ goto out_put_ag;
- item->ag = ag;
+ item->ag = *agp;
item->ip = ip;
- item->pip = pip;
- err = xfs_mru_cache_insert(cache, ip->i_ino, item);
+ err = xfs_mru_cache_insert(mp->m_filestream, ip->i_ino, &item->mru);
if (err) {
- kmem_zone_free(item_zone, item);
- return err;
+ if (err == EEXIST)
+ err = 0;
+ goto out_free_item;
}
- /* Take a reference on the AG. */
- xfs_filestream_get_ag(mp, ag);
-
- /*
- * Take a reference on the inode itself regardless of whether it's a
- * regular file or a directory.
- */
- IHOLD(ip);
-
- /*
- * In the case of a regular file, take a reference on the parent inode
- * as well to ensure it remains in-core.
- */
- if (pip)
- IHOLD(pip);
-
- TRACE_UPDATE(mp, ip, ag, xfs_filestream_peek_ag(mp, ag),
- ag, xfs_filestream_peek_ag(mp, ag));
-
return 0;
-}
-
-/* xfs_fstrm_free_func(): callback for freeing cached stream items. */
-STATIC void
-xfs_fstrm_free_func(
- unsigned long ino,
- void *data)
-{
- fstrm_item_t *item = (fstrm_item_t *)data;
- xfs_inode_t *ip = item->ip;
-
- ASSERT(ip->i_ino == ino);
-
- xfs_iflags_clear(ip, XFS_IFILESTREAM);
-
- /* Drop the reference taken on the AG when the item was added. */
- xfs_filestream_put_ag(ip->i_mount, item->ag);
-
- TRACE_FREE(ip->i_mount, ip, item->pip, item->ag,
- xfs_filestream_peek_ag(ip->i_mount, item->ag));
-
- /*
- * _xfs_filestream_update_ag() always takes a reference on the inode
- * itself, whether it's a file or a directory. Release it here.
- * This can result in the inode being freed and so we must
- * not hold any inode locks when freeing filesstreams objects
- * otherwise we can deadlock here.
- */
- IRELE(ip);
-
- /*
- * In the case of a regular file, _xfs_filestream_update_ag() also
- * takes a ref on the parent inode to keep it in-core. Release that
- * too.
- */
- if (item->pip)
- IRELE(item->pip);
-
- /* Finally, free the memory allocated for the item. */
- kmem_zone_free(item_zone, item);
-}
-
-/*
- * xfs_filestream_init() is called at xfs initialisation time to set up the
- * memory zone that will be used for filestream data structure allocation.
- */
-int
-xfs_filestream_init(void)
-{
- item_zone = kmem_zone_init(sizeof(fstrm_item_t), "fstrm_item");
- if (!item_zone)
- return -ENOMEM;
-
- return 0;
-}
-
-/*
- * xfs_filestream_uninit() is called at xfs termination time to destroy the
- * memory zone that was used for filestream data structure allocation.
- */
-void
-xfs_filestream_uninit(void)
-{
- kmem_zone_destroy(item_zone);
-}
-
-/*
- * xfs_filestream_mount() is called when a file system is mounted with the
- * filestream option. It is responsible for allocating the data structures
- * needed to track the new file system's file streams.
- */
-int
-xfs_filestream_mount(
- xfs_mount_t *mp)
-{
- int err;
- unsigned int lifetime, grp_count;
-
- /*
- * The filestream timer tunable is currently fixed within the range of
- * one second to four minutes, with five seconds being the default. The
- * group count is somewhat arbitrary, but it'd be nice to adhere to the
- * timer tunable to within about 10 percent. This requires at least 10
- * groups.
- */
- lifetime = xfs_fstrm_centisecs * 10;
- grp_count = 10;
-
- err = xfs_mru_cache_create(&mp->m_filestream, lifetime, grp_count,
- xfs_fstrm_free_func);
+out_free_item:
+ kmem_free(item);
+out_put_ag:
+ xfs_filestream_put_ag(mp, *agp);
return err;
}
-/*
- * xfs_filestream_unmount() is called when a file system that was mounted with
- * the filestream option is unmounted. It drains the data structures created
- * to track the file system's file streams and frees all the memory that was
- * allocated.
- */
-void
-xfs_filestream_unmount(
- xfs_mount_t *mp)
+static struct xfs_inode *
+xfs_filestream_get_parent(
+ struct xfs_inode *ip)
{
- xfs_mru_cache_destroy(mp->m_filestream);
-}
+ struct inode *inode = VFS_I(ip), *dir = NULL;
+ struct dentry *dentry, *parent;
-/*
- * Return the AG of the filestream the file or directory belongs to, or
- * NULLAGNUMBER otherwise.
- */
-xfs_agnumber_t
-xfs_filestream_lookup_ag(
- xfs_inode_t *ip)
-{
- xfs_mru_cache_t *cache;
- fstrm_item_t *item;
- xfs_agnumber_t ag;
- int ref;
-
- if (!S_ISREG(ip->i_d.di_mode) && !S_ISDIR(ip->i_d.di_mode)) {
- ASSERT(0);
- return NULLAGNUMBER;
- }
+ dentry = d_find_alias(inode);
+ if (!dentry)
+ goto out;
- cache = ip->i_mount->m_filestream;
- item = xfs_mru_cache_lookup(cache, ip->i_ino);
- if (!item) {
- TRACE_LOOKUP(ip->i_mount, ip, NULL, NULLAGNUMBER, 0);
- return NULLAGNUMBER;
- }
+ parent = dget_parent(dentry);
+ if (!parent)
+ goto out_dput;
- ASSERT(ip == item->ip);
- ag = item->ag;
- ref = xfs_filestream_peek_ag(ip->i_mount, ag);
- xfs_mru_cache_done(cache);
+ dir = igrab(parent->d_inode);
+ dput(parent);
- TRACE_LOOKUP(ip->i_mount, ip, item->pip, ag, ref);
- return ag;
+out_dput:
+ dput(dentry);
+out:
+ return dir ? XFS_I(dir) : NULL;
}
/*
- * xfs_filestream_associate() should only be called to associate a regular file
- * with its parent directory. Calling it with a child directory isn't
- * appropriate because filestreams don't apply to entire directory hierarchies.
- * Creating a file in a child directory of an existing filestream directory
- * starts a new filestream with its own allocation group association.
+ * Find the right allocation group for a file, either by finding an
+ * existing file stream or creating a new one.
*
- * Returns < 0 on error, 0 if successful association occurred, > 0 if
- * we failed to get an association because of locking issues.
+ * Returns NULLAGNUMBER in case of an error.
*/
-int
-xfs_filestream_associate(
- xfs_inode_t *pip,
- xfs_inode_t *ip)
+xfs_agnumber_t
+xfs_filestream_lookup_ag(
+ struct xfs_inode *ip)
{
- xfs_mount_t *mp;
- xfs_mru_cache_t *cache;
- fstrm_item_t *item;
- xfs_agnumber_t ag, rotorstep, startag;
- int err = 0;
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_inode *pip = NULL;
+ xfs_agnumber_t startag, ag = NULLAGNUMBER;
+ struct xfs_mru_cache_elem *mru;
- ASSERT(S_ISDIR(pip->i_d.di_mode));
ASSERT(S_ISREG(ip->i_d.di_mode));
- if (!S_ISDIR(pip->i_d.di_mode) || !S_ISREG(ip->i_d.di_mode))
- return -EINVAL;
- mp = pip->i_mount;
- cache = mp->m_filestream;
+ pip = xfs_filestream_get_parent(ip);
+ if (!pip)
+ goto out;
- /*
- * We have a problem, Houston.
- *
- * Taking the iolock here violates inode locking order - we already
- * hold the ilock. Hence if we block getting this lock we may never
- * wake. Unfortunately, that means if we can't get the lock, we're
- * screwed in terms of getting a stream association - we can't spin
- * waiting for the lock because someone else is waiting on the lock we
- * hold and we cannot drop that as we are in a transaction here.
- *
- * Lucky for us, this inversion is not a problem because it's a
- * directory inode that we are trying to lock here.
- *
- * So, if we can't get the iolock without sleeping then just give up
- */
- if (!xfs_ilock_nowait(pip, XFS_IOLOCK_EXCL))
- return 1;
-
- /* If the parent directory is already in the cache, use its AG. */
- item = xfs_mru_cache_lookup(cache, pip->i_ino);
- if (item) {
- ASSERT(item->ip == pip);
- ag = item->ag;
- xfs_mru_cache_done(cache);
-
- TRACE_LOOKUP(mp, pip, pip, ag, xfs_filestream_peek_ag(mp, ag));
- err = _xfs_filestream_update_ag(ip, pip, ag);
+ mru = xfs_mru_cache_lookup(mp->m_filestream, pip->i_ino);
+ if (mru) {
+ ag = container_of(mru, struct xfs_fstrm_item, mru)->ag;
+ xfs_mru_cache_done(mp->m_filestream);
- goto exit;
+ trace_xfs_filestream_lookup(ip, ag);
+ goto out;
}
/*
@@ -623,202 +341,94 @@ xfs_filestream_associate(
* use the directory inode's AG.
*/
if (mp->m_flags & XFS_MOUNT_32BITINODES) {
- rotorstep = xfs_rotorstep;
+ xfs_agnumber_t rotorstep = xfs_rotorstep;
startag = (mp->m_agfrotor / rotorstep) % mp->m_sb.sb_agcount;
mp->m_agfrotor = (mp->m_agfrotor + 1) %
(mp->m_sb.sb_agcount * rotorstep);
} else
startag = XFS_INO_TO_AGNO(mp, pip->i_ino);
- /* Pick a new AG for the parent inode starting at startag. */
- err = _xfs_filestream_pick_ag(mp, startag, &ag, 0, 0);
- if (err || ag == NULLAGNUMBER)
- goto exit_did_pick;
-
- /* Associate the parent inode with the AG. */
- err = _xfs_filestream_update_ag(pip, NULL, ag);
- if (err)
- goto exit_did_pick;
-
- /* Associate the file inode with the AG. */
- err = _xfs_filestream_update_ag(ip, pip, ag);
- if (err)
- goto exit_did_pick;
-
- TRACE_ASSOCIATE(mp, ip, pip, ag, xfs_filestream_peek_ag(mp, ag));
-
-exit_did_pick:
- /*
- * If _xfs_filestream_pick_ag() returned a valid AG, remove the
- * reference it took on it, since the file and directory will have taken
- * their own now if they were successfully cached.
- */
- if (ag != NULLAGNUMBER)
- xfs_filestream_put_ag(mp, ag);
-
-exit:
- xfs_iunlock(pip, XFS_IOLOCK_EXCL);
- return -err;
+ if (xfs_filestream_pick_ag(pip, startag, &ag, 0, 0))
+ ag = NULLAGNUMBER;
+out:
+ IRELE(pip);
+ return ag;
}
/*
- * Pick a new allocation group for the current file and its file stream. This
- * function is called by xfs_bmap_filestreams() with the mount point's per-ag
- * lock held.
+ * Pick a new allocation group for the current file and its file stream.
+ *
+ * This is called when the allocator can't find a suitable extent in the
+ * current AG, and we have to move the stream into a new AG with more space.
*/
int
xfs_filestream_new_ag(
struct xfs_bmalloca *ap,
xfs_agnumber_t *agp)
{
- int flags, err;
- xfs_inode_t *ip, *pip = NULL;
- xfs_mount_t *mp;
- xfs_mru_cache_t *cache;
- xfs_extlen_t minlen;
- fstrm_item_t *dir, *file;
- xfs_agnumber_t ag = NULLAGNUMBER;
-
- ip = ap->ip;
- mp = ip->i_mount;
- cache = mp->m_filestream;
- minlen = ap->length;
- *agp = NULLAGNUMBER;
+ struct xfs_inode *ip = ap->ip, *pip;
+ struct xfs_mount *mp = ip->i_mount;
+ xfs_extlen_t minlen = ap->length;
+ xfs_agnumber_t startag = 0;
+ int flags, err = 0;
+ struct xfs_mru_cache_elem *mru;
- /*
- * Look for the file in the cache, removing it if it's found. Doing
- * this allows it to be held across the dir lookup that follows.
- */
- file = xfs_mru_cache_remove(cache, ip->i_ino);
- if (file) {
- ASSERT(ip == file->ip);
-
- /* Save the file's parent inode and old AG number for later. */
- pip = file->pip;
- ag = file->ag;
-
- /* Look for the file's directory in the cache. */
- dir = xfs_mru_cache_lookup(cache, pip->i_ino);
- if (dir) {
- ASSERT(pip == dir->ip);
-
- /*
- * If the directory has already moved on to a new AG,
- * use that AG as the new AG for the file. Don't
- * forget to twiddle the AG refcounts to match the
- * movement.
- */
- if (dir->ag != file->ag) {
- xfs_filestream_put_ag(mp, file->ag);
- xfs_filestream_get_ag(mp, dir->ag);
- *agp = file->ag = dir->ag;
- }
-
- xfs_mru_cache_done(cache);
- }
+ *agp = NULLAGNUMBER;
- /*
- * Put the file back in the cache. If this fails, the free
- * function needs to be called to tidy up in the same way as if
- * the item had simply expired from the cache.
- */
- err = xfs_mru_cache_insert(cache, ip->i_ino, file);
- if (err) {
- xfs_fstrm_free_func(ip->i_ino, file);
- return err;
- }
+ pip = xfs_filestream_get_parent(ip);
+ if (!pip)
+ goto exit;
- /*
- * If the file's AG was moved to the directory's new AG, there's
- * nothing more to be done.
- */
- if (*agp != NULLAGNUMBER) {
- TRACE_MOVEAG(mp, ip, pip,
- ag, xfs_filestream_peek_ag(mp, ag),
- *agp, xfs_filestream_peek_ag(mp, *agp));
- return 0;
- }
+ mru = xfs_mru_cache_remove(mp->m_filestream, pip->i_ino);
+ if (mru) {
+ struct xfs_fstrm_item *item =
+ container_of(mru, struct xfs_fstrm_item, mru);
+ startag = (item->ag + 1) % mp->m_sb.sb_agcount;
}
- /*
- * If the file's parent directory is known, take its iolock in exclusive
- * mode to prevent two sibling files from racing each other to migrate
- * themselves and their parent to different AGs.
- *
- * Note that we lock the parent directory iolock inside the child
- * iolock here. That's fine as we never hold both parent and child
- * iolock in any other place. This is different from the ilock,
- * which requires locking of the child after the parent for namespace
- * operations.
- */
- if (pip)
- xfs_ilock(pip, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT);
-
- /*
- * A new AG needs to be found for the file. If the file's parent
- * directory is also known, it will be moved to the new AG as well to
- * ensure that files created inside it in future use the new AG.
- */
- ag = (ag == NULLAGNUMBER) ? 0 : (ag + 1) % mp->m_sb.sb_agcount;
flags = (ap->userdata ? XFS_PICK_USERDATA : 0) |
(ap->flist->xbf_low ? XFS_PICK_LOWSPACE : 0);
- err = _xfs_filestream_pick_ag(mp, ag, agp, flags, minlen);
- if (err || *agp == NULLAGNUMBER)
- goto exit;
+ err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
/*
- * If the file wasn't found in the file cache, then its parent directory
- * inode isn't known. For this to have happened, the file must either
- * be pre-existing, or it was created long enough ago that its cache
- * entry has expired. This isn't the sort of usage that the filestreams
- * allocator is trying to optimise, so there's no point trying to track
- * its new AG somehow in the filestream data structures.
+ * Only free the item here so we skip over the old AG earlier.
*/
- if (!pip) {
- TRACE_ORPHAN(mp, ip, *agp);
- goto exit;
- }
-
- /* Associate the parent inode with the AG. */
- err = _xfs_filestream_update_ag(pip, NULL, *agp);
- if (err)
- goto exit;
-
- /* Associate the file inode with the AG. */
- err = _xfs_filestream_update_ag(ip, pip, *agp);
- if (err)
- goto exit;
-
- TRACE_MOVEAG(mp, ip, pip, NULLAGNUMBER, 0,
- *agp, xfs_filestream_peek_ag(mp, *agp));
+ if (mru)
+ xfs_fstrm_free_func(mru);
+ IRELE(pip);
exit:
- /*
- * If _xfs_filestream_pick_ag() returned a valid AG, remove the
- * reference it took on it, since the file and directory will have taken
- * their own now if they were successfully cached.
- */
- if (*agp != NULLAGNUMBER)
- xfs_filestream_put_ag(mp, *agp);
- else
+ if (*agp == NULLAGNUMBER)
*agp = 0;
-
- if (pip)
- xfs_iunlock(pip, XFS_IOLOCK_EXCL);
-
return err;
}
-/*
- * Remove an association between an inode and a filestream object.
- * Typically this is done on last close of an unlinked file.
- */
void
xfs_filestream_deassociate(
- xfs_inode_t *ip)
+ struct xfs_inode *ip)
{
- xfs_mru_cache_t *cache = ip->i_mount->m_filestream;
+ xfs_mru_cache_delete(ip->i_mount->m_filestream, ip->i_ino);
+}
+
+int
+xfs_filestream_mount(
+ xfs_mount_t *mp)
+{
+ /*
+ * The filestream timer tunable is currently fixed within the range of
+ * one second to four minutes, with five seconds being the default. The
+ * group count is somewhat arbitrary, but it'd be nice to adhere to the
+ * timer tunable to within about 10 percent. This requires at least 10
+ * groups.
+ */
+ return xfs_mru_cache_create(&mp->m_filestream, xfs_fstrm_centisecs * 10,
+ 10, xfs_fstrm_free_func);
+}
- xfs_mru_cache_delete(cache, ip->i_ino);
+void
+xfs_filestream_unmount(
+ xfs_mount_t *mp)
+{
+ xfs_mru_cache_destroy(mp->m_filestream);
}
diff --git a/fs/xfs/xfs_filestream.h b/fs/xfs/xfs_filestream.h
index 6d61dbee8564..2ef43406e53b 100644
--- a/fs/xfs/xfs_filestream.h
+++ b/fs/xfs/xfs_filestream.h
@@ -20,50 +20,20 @@
struct xfs_mount;
struct xfs_inode;
-struct xfs_perag;
struct xfs_bmalloca;
-#ifdef XFS_FILESTREAMS_TRACE
-#define XFS_FSTRM_KTRACE_INFO 1
-#define XFS_FSTRM_KTRACE_AGSCAN 2
-#define XFS_FSTRM_KTRACE_AGPICK1 3
-#define XFS_FSTRM_KTRACE_AGPICK2 4
-#define XFS_FSTRM_KTRACE_UPDATE 5
-#define XFS_FSTRM_KTRACE_FREE 6
-#define XFS_FSTRM_KTRACE_ITEM_LOOKUP 7
-#define XFS_FSTRM_KTRACE_ASSOCIATE 8
-#define XFS_FSTRM_KTRACE_MOVEAG 9
-#define XFS_FSTRM_KTRACE_ORPHAN 10
-
-#define XFS_FSTRM_KTRACE_SIZE 16384
-extern ktrace_t *xfs_filestreams_trace_buf;
-
-#endif
-
-/* allocation selection flags */
-typedef enum xfs_fstrm_alloc {
- XFS_PICK_USERDATA = 1,
- XFS_PICK_LOWSPACE = 2,
-} xfs_fstrm_alloc_t;
-
-/* prototypes for filestream.c */
-int xfs_filestream_init(void);
-void xfs_filestream_uninit(void);
int xfs_filestream_mount(struct xfs_mount *mp);
void xfs_filestream_unmount(struct xfs_mount *mp);
-xfs_agnumber_t xfs_filestream_lookup_ag(struct xfs_inode *ip);
-int xfs_filestream_associate(struct xfs_inode *dip, struct xfs_inode *ip);
void xfs_filestream_deassociate(struct xfs_inode *ip);
+xfs_agnumber_t xfs_filestream_lookup_ag(struct xfs_inode *ip);
int xfs_filestream_new_ag(struct xfs_bmalloca *ap, xfs_agnumber_t *agp);
+int xfs_filestream_peek_ag(struct xfs_mount *mp, xfs_agnumber_t agno);
-
-/* filestreams for the inode? */
static inline int
xfs_inode_is_filestream(
struct xfs_inode *ip)
{
return (ip->i_mount->m_flags & XFS_MOUNT_FILESTREAMS) ||
- xfs_iflags_test(ip, XFS_IFILESTREAM) ||
(ip->i_d.di_flags & XFS_DIFLAG_FILESTREAM);
}
diff --git a/fs/xfs/xfs_format.h b/fs/xfs/xfs_format.h
index 9898f31d05d8..34d85aca3058 100644
--- a/fs/xfs/xfs_format.h
+++ b/fs/xfs/xfs_format.h
@@ -202,6 +202,8 @@ typedef __be32 xfs_alloc_ptr_t;
*/
#define XFS_IBT_MAGIC 0x49414254 /* 'IABT' */
#define XFS_IBT_CRC_MAGIC 0x49414233 /* 'IAB3' */
+#define XFS_FIBT_MAGIC 0x46494254 /* 'FIBT' */
+#define XFS_FIBT_CRC_MAGIC 0x46494233 /* 'FIB3' */
typedef __uint64_t xfs_inofree_t;
#define XFS_INODES_PER_CHUNK (NBBY * sizeof(xfs_inofree_t))
@@ -244,7 +246,17 @@ typedef __be32 xfs_inobt_ptr_t;
* block numbers in the AG.
*/
#define XFS_IBT_BLOCK(mp) ((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
-#define XFS_PREALLOC_BLOCKS(mp) ((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+#define XFS_FIBT_BLOCK(mp) ((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+
+/*
+ * The first data block of an AG depends on whether the filesystem was formatted
+ * with the finobt feature. If so, account for the finobt reserved root btree
+ * block.
+ */
+#define XFS_PREALLOC_BLOCKS(mp) \
+ (xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
+ XFS_FIBT_BLOCK(mp) + 1 : \
+ XFS_IBT_BLOCK(mp) + 1)
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index c5fc116dfaa3..d34703dbcb42 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -238,6 +238,7 @@ typedef struct xfs_fsop_resblks {
#define XFS_FSOP_GEOM_FLAGS_LAZYSB 0x4000 /* lazy superblock counters */
#define XFS_FSOP_GEOM_FLAGS_V5SB 0x8000 /* version 5 superblock */
#define XFS_FSOP_GEOM_FLAGS_FTYPE 0x10000 /* inode directory types */
+#define XFS_FSOP_GEOM_FLAGS_FINOBT 0x20000 /* free inode btree */
/*
* Minimum and maximum sizes need for growth checks.
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 02fb943cbf22..d2295561570a 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -24,6 +24,8 @@
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
@@ -74,23 +76,18 @@ xfs_fs_geometry(
}
if (new_version >= 3) {
geo->version = XFS_FSOP_GEOM_VERSION;
- geo->flags =
+ geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK |
+ XFS_FSOP_GEOM_FLAGS_DIRV2 |
(xfs_sb_version_hasattr(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_ATTR : 0) |
- (xfs_sb_version_hasnlink(&mp->m_sb) ?
- XFS_FSOP_GEOM_FLAGS_NLINK : 0) |
(xfs_sb_version_hasquota(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_QUOTA : 0) |
(xfs_sb_version_hasalign(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_IALIGN : 0) |
(xfs_sb_version_hasdalign(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_DALIGN : 0) |
- (xfs_sb_version_hasshared(&mp->m_sb) ?
- XFS_FSOP_GEOM_FLAGS_SHARED : 0) |
(xfs_sb_version_hasextflgbit(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_EXTFLG : 0) |
- (xfs_sb_version_hasdirv2(&mp->m_sb) ?
- XFS_FSOP_GEOM_FLAGS_DIRV2 : 0) |
(xfs_sb_version_hassector(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_SECTOR : 0) |
(xfs_sb_version_hasasciici(&mp->m_sb) ?
@@ -104,11 +101,13 @@ xfs_fs_geometry(
(xfs_sb_version_hascrc(&mp->m_sb) ?
XFS_FSOP_GEOM_FLAGS_V5SB : 0) |
(xfs_sb_version_hasftype(&mp->m_sb) ?
- XFS_FSOP_GEOM_FLAGS_FTYPE : 0);
+ XFS_FSOP_GEOM_FLAGS_FTYPE : 0) |
+ (xfs_sb_version_hasfinobt(&mp->m_sb) ?
+ XFS_FSOP_GEOM_FLAGS_FINOBT : 0);
geo->logsectsize = xfs_sb_version_hassector(&mp->m_sb) ?
mp->m_sb.sb_logsectsize : BBSIZE;
geo->rtsectsize = mp->m_sb.sb_blocksize;
- geo->dirblocksize = mp->m_dirblksize;
+ geo->dirblocksize = mp->m_dir_geo->blksize;
}
if (new_version >= 4) {
geo->flags |=
@@ -316,6 +315,10 @@ xfs_growfs_data_private(
agi->agi_dirino = cpu_to_be32(NULLAGINO);
if (xfs_sb_version_hascrc(&mp->m_sb))
uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_uuid);
+ if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+ agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
+ agi->agi_free_level = cpu_to_be32(1);
+ }
for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
@@ -407,6 +410,34 @@ xfs_growfs_data_private(
xfs_buf_relse(bp);
if (error)
goto error0;
+
+ /*
+ * FINO btree root block
+ */
+ if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+ bp = xfs_growfs_get_hdr_buf(mp,
+ XFS_AGB_TO_DADDR(mp, agno, XFS_FIBT_BLOCK(mp)),
+ BTOBB(mp->m_sb.sb_blocksize), 0,
+ &xfs_inobt_buf_ops);
+ if (!bp) {
+ error = ENOMEM;
+ goto error0;
+ }
+
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ xfs_btree_init_block(mp, bp, XFS_FIBT_CRC_MAGIC,
+ 0, 0, agno,
+ XFS_BTREE_CRC_BLOCKS);
+ else
+ xfs_btree_init_block(mp, bp, XFS_FIBT_MAGIC, 0,
+ 0, agno, 0);
+
+ error = xfs_bwrite(bp);
+ xfs_buf_relse(bp);
+ if (error)
+ goto error0;
+ }
+
}
xfs_trans_agblocks_delta(tp, nfree);
/*
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 8f711db61a0c..5960e5593fe0 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -112,6 +112,66 @@ xfs_inobt_get_rec(
}
/*
+ * Insert a single inobt record. Cursor must already point to desired location.
+ */
+STATIC int
+xfs_inobt_insert_rec(
+ struct xfs_btree_cur *cur,
+ __int32_t freecount,
+ xfs_inofree_t free,
+ int *stat)
+{
+ cur->bc_rec.i.ir_freecount = freecount;
+ cur->bc_rec.i.ir_free = free;
+ return xfs_btree_insert(cur, stat);
+}
+
+/*
+ * Insert records describing a newly allocated inode chunk into the inobt.
+ */
+STATIC int
+xfs_inobt_insert(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ xfs_agino_t newino,
+ xfs_agino_t newlen,
+ xfs_btnum_t btnum)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+ xfs_agnumber_t agno = be32_to_cpu(agi->agi_seqno);
+ xfs_agino_t thisino;
+ int i;
+ int error;
+
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum);
+
+ for (thisino = newino;
+ thisino < newino + newlen;
+ thisino += XFS_INODES_PER_CHUNK) {
+ error = xfs_inobt_lookup(cur, thisino, XFS_LOOKUP_EQ, &i);
+ if (error) {
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ return error;
+ }
+ ASSERT(i == 0);
+
+ error = xfs_inobt_insert_rec(cur, XFS_INODES_PER_CHUNK,
+ XFS_INOBT_ALL_FREE, &i);
+ if (error) {
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ return error;
+ }
+ ASSERT(i == 1);
+ }
+
+ xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+
+ return 0;
+}
+
+/*
* Verify that the number of free inodes in the AGI is correct.
*/
#ifdef DEBUG
@@ -220,10 +280,8 @@ xfs_ialloc_inode_init(
if (tp)
xfs_icreate_log(tp, agno, agbno, mp->m_ialloc_inos,
mp->m_sb.sb_inodesize, length, gen);
- } else if (xfs_sb_version_hasnlink(&mp->m_sb))
+ } else
version = 2;
- else
- version = 1;
for (j = 0; j < nbufs; j++) {
/*
@@ -303,13 +361,10 @@ xfs_ialloc_ag_alloc(
{
xfs_agi_t *agi; /* allocation group header */
xfs_alloc_arg_t args; /* allocation argument structure */
- xfs_btree_cur_t *cur; /* inode btree cursor */
xfs_agnumber_t agno;
int error;
- int i;
xfs_agino_t newino; /* new first inode's number */
xfs_agino_t newlen; /* new number of inodes */
- xfs_agino_t thisino; /* current inode number, for loop */
int isaligned = 0; /* inode allocation at stripe unit */
/* boundary */
struct xfs_perag *pag;
@@ -459,29 +514,19 @@ xfs_ialloc_ag_alloc(
agi->agi_newino = cpu_to_be32(newino);
/*
- * Insert records describing the new inode chunk into the btree.
+ * Insert records describing the new inode chunk into the btrees.
*/
- cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
- for (thisino = newino;
- thisino < newino + newlen;
- thisino += XFS_INODES_PER_CHUNK) {
- cur->bc_rec.i.ir_startino = thisino;
- cur->bc_rec.i.ir_freecount = XFS_INODES_PER_CHUNK;
- cur->bc_rec.i.ir_free = XFS_INOBT_ALL_FREE;
- error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, &i);
- if (error) {
- xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
- return error;
- }
- ASSERT(i == 0);
- error = xfs_btree_insert(cur, &i);
- if (error) {
- xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ error = xfs_inobt_insert(args.mp, tp, agbp, newino, newlen,
+ XFS_BTNUM_INO);
+ if (error)
+ return error;
+
+ if (xfs_sb_version_hasfinobt(&args.mp->m_sb)) {
+ error = xfs_inobt_insert(args.mp, tp, agbp, newino, newlen,
+ XFS_BTNUM_FINO);
+ if (error)
return error;
- }
- ASSERT(i == 1);
}
- xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
/*
* Log allocation group header fields
*/
@@ -675,13 +720,10 @@ xfs_ialloc_get_rec(
}
/*
- * Allocate an inode.
- *
- * The caller selected an AG for us, and made sure that free inodes are
- * available.
+ * Allocate an inode using the inobt-only algorithm.
*/
STATIC int
-xfs_dialloc_ag(
+xfs_dialloc_ag_inobt(
struct xfs_trans *tp,
struct xfs_buf *agbp,
xfs_ino_t parent,
@@ -707,7 +749,7 @@ xfs_dialloc_ag(
ASSERT(pag->pagi_freecount > 0);
restart_pagno:
- cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
@@ -940,6 +982,294 @@ error0:
}
/*
+ * Use the free inode btree to allocate an inode based on distance from the
+ * parent. Note that the provided cursor may be deleted and replaced.
+ */
+STATIC int
+xfs_dialloc_ag_finobt_near(
+ xfs_agino_t pagino,
+ struct xfs_btree_cur **ocur,
+ struct xfs_inobt_rec_incore *rec)
+{
+ struct xfs_btree_cur *lcur = *ocur; /* left search cursor */
+ struct xfs_btree_cur *rcur; /* right search cursor */
+ struct xfs_inobt_rec_incore rrec;
+ int error;
+ int i, j;
+
+ error = xfs_inobt_lookup(lcur, pagino, XFS_LOOKUP_LE, &i);
+ if (error)
+ return error;
+
+ if (i == 1) {
+ error = xfs_inobt_get_rec(lcur, rec, &i);
+ if (error)
+ return error;
+ XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+ /*
+ * See if we've landed in the parent inode record. The finobt
+ * only tracks chunks with at least one free inode, so record
+ * existence is enough.
+ */
+ if (pagino >= rec->ir_startino &&
+ pagino < (rec->ir_startino + XFS_INODES_PER_CHUNK))
+ return 0;
+ }
+
+ error = xfs_btree_dup_cursor(lcur, &rcur);
+ if (error)
+ return error;
+
+ error = xfs_inobt_lookup(rcur, pagino, XFS_LOOKUP_GE, &j);
+ if (error)
+ goto error_rcur;
+ if (j == 1) {
+ error = xfs_inobt_get_rec(rcur, &rrec, &j);
+ if (error)
+ goto error_rcur;
+ XFS_WANT_CORRUPTED_GOTO(j == 1, error_rcur);
+ }
+
+ XFS_WANT_CORRUPTED_GOTO(i == 1 || j == 1, error_rcur);
+ if (i == 1 && j == 1) {
+ /*
+ * Both the left and right records are valid. Choose the closer
+ * inode chunk to the target.
+ */
+ if ((pagino - rec->ir_startino + XFS_INODES_PER_CHUNK - 1) >
+ (rrec.ir_startino - pagino)) {
+ *rec = rrec;
+ xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
+ *ocur = rcur;
+ } else {
+ xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
+ }
+ } else if (j == 1) {
+ /* only the right record is valid */
+ *rec = rrec;
+ xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
+ *ocur = rcur;
+ } else if (i == 1) {
+ /* only the left record is valid */
+ xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
+ }
+
+ return 0;
+
+error_rcur:
+ xfs_btree_del_cursor(rcur, XFS_BTREE_ERROR);
+ return error;
+}
+
+/*
+ * Use the free inode btree to find a free inode based on a newino hint. If
+ * the hint is NULL, find the first free inode in the AG.
+ */
+STATIC int
+xfs_dialloc_ag_finobt_newino(
+ struct xfs_agi *agi,
+ struct xfs_btree_cur *cur,
+ struct xfs_inobt_rec_incore *rec)
+{
+ int error;
+ int i;
+
+ if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
+ error = xfs_inobt_lookup(cur, agi->agi_newino, XFS_LOOKUP_EQ,
+ &i);
+ if (error)
+ return error;
+ if (i == 1) {
+ error = xfs_inobt_get_rec(cur, rec, &i);
+ if (error)
+ return error;
+ XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+ return 0;
+ }
+ }
+
+ /*
+ * Find the first inode available in the AG.
+ */
+ error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
+ if (error)
+ return error;
+ XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+ error = xfs_inobt_get_rec(cur, rec, &i);
+ if (error)
+ return error;
+ XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+ return 0;
+}
+
+/*
+ * Update the inobt based on a modification made to the finobt. Also ensure that
+ * the records from both trees are equivalent post-modification.
+ */
+STATIC int
+xfs_dialloc_ag_update_inobt(
+ struct xfs_btree_cur *cur, /* inobt cursor */
+ struct xfs_inobt_rec_incore *frec, /* finobt record */
+ int offset) /* inode offset */
+{
+ struct xfs_inobt_rec_incore rec;
+ int error;
+ int i;
+
+ error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
+ if (error)
+ return error;
+ XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+ error = xfs_inobt_get_rec(cur, &rec, &i);
+ if (error)
+ return error;
+ XFS_WANT_CORRUPTED_RETURN(i == 1);
+ ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
+ XFS_INODES_PER_CHUNK) == 0);
+
+ rec.ir_free &= ~XFS_INOBT_MASK(offset);
+ rec.ir_freecount--;
+
+ XFS_WANT_CORRUPTED_RETURN((rec.ir_free == frec->ir_free) &&
+ (rec.ir_freecount == frec->ir_freecount));
+
+ error = xfs_inobt_update(cur, &rec);
+ if (error)
+ return error;
+
+ return 0;
+}
+
+/*
+ * Allocate an inode using the free inode btree, if available. Otherwise, fall
+ * back to the inobt search algorithm.
+ *
+ * The caller selected an AG for us, and made sure that free inodes are
+ * available.
+ */
+STATIC int
+xfs_dialloc_ag(
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ xfs_ino_t parent,
+ xfs_ino_t *inop)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+ xfs_agnumber_t agno = be32_to_cpu(agi->agi_seqno);
+ xfs_agnumber_t pagno = XFS_INO_TO_AGNO(mp, parent);
+ xfs_agino_t pagino = XFS_INO_TO_AGINO(mp, parent);
+ struct xfs_perag *pag;
+ struct xfs_btree_cur *cur; /* finobt cursor */
+ struct xfs_btree_cur *icur; /* inobt cursor */
+ struct xfs_inobt_rec_incore rec;
+ xfs_ino_t ino;
+ int error;
+ int offset;
+ int i;
+
+ if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+ return xfs_dialloc_ag_inobt(tp, agbp, parent, inop);
+
+ pag = xfs_perag_get(mp, agno);
+
+ /*
+ * If pagino is 0 (this is the root inode allocation) use newino.
+ * This must work because we've just allocated some.
+ */
+ if (!pagino)
+ pagino = be32_to_cpu(agi->agi_newino);
+
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+ error = xfs_check_agi_freecount(cur, agi);
+ if (error)
+ goto error_cur;
+
+ /*
+ * The search algorithm depends on whether we're in the same AG as the
+ * parent. If so, find the closest available inode to the parent. If
+ * not, consider the agi hint or find the first free inode in the AG.
+ */
+ if (agno == pagno)
+ error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec);
+ else
+ error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec);
+ if (error)
+ goto error_cur;
+
+ offset = xfs_lowbit64(rec.ir_free);
+ ASSERT(offset >= 0);
+ ASSERT(offset < XFS_INODES_PER_CHUNK);
+ ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
+ XFS_INODES_PER_CHUNK) == 0);
+ ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
+
+ /*
+ * Modify or remove the finobt record.
+ */
+ rec.ir_free &= ~XFS_INOBT_MASK(offset);
+ rec.ir_freecount--;
+ if (rec.ir_freecount)
+ error = xfs_inobt_update(cur, &rec);
+ else
+ error = xfs_btree_delete(cur, &i);
+ if (error)
+ goto error_cur;
+
+ /*
+ * The finobt has now been updated appropriately. We haven't updated the
+ * agi and superblock yet, so we can create an inobt cursor and validate
+ * the original freecount. If all is well, make the equivalent update to
+ * the inobt using the finobt record and offset information.
+ */
+ icur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
+
+ error = xfs_check_agi_freecount(icur, agi);
+ if (error)
+ goto error_icur;
+
+ error = xfs_dialloc_ag_update_inobt(icur, &rec, offset);
+ if (error)
+ goto error_icur;
+
+ /*
+ * Both trees have now been updated. We must update the perag and
+ * superblock before we can check the freecount for each btree.
+ */
+ be32_add_cpu(&agi->agi_freecount, -1);
+ xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
+ pag->pagi_freecount--;
+
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
+
+ error = xfs_check_agi_freecount(icur, agi);
+ if (error)
+ goto error_icur;
+ error = xfs_check_agi_freecount(cur, agi);
+ if (error)
+ goto error_icur;
+
+ xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR);
+ xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+ xfs_perag_put(pag);
+ *inop = ino;
+ return 0;
+
+error_icur:
+ xfs_btree_del_cursor(icur, XFS_BTREE_ERROR);
+error_cur:
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ xfs_perag_put(pag);
+ return error;
+}
+
+/*
* Allocate an inode on disk.
*
* Mode is used to tell whether the new inode will need space, and whether it
@@ -1098,78 +1428,34 @@ out_error:
return XFS_ERROR(error);
}
-/*
- * Free disk inode. Carefully avoids touching the incore inode, all
- * manipulations incore are the caller's responsibility.
- * The on-disk inode is not changed by this operation, only the
- * btree (free inode mask) is changed.
- */
-int
-xfs_difree(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_ino_t inode, /* inode to be freed */
- xfs_bmap_free_t *flist, /* extents to free */
- int *delete, /* set if inode cluster was deleted */
- xfs_ino_t *first_ino) /* first inode in deleted cluster */
+STATIC int
+xfs_difree_inobt(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ xfs_agino_t agino,
+ struct xfs_bmap_free *flist,
+ int *deleted,
+ xfs_ino_t *first_ino,
+ struct xfs_inobt_rec_incore *orec)
{
- /* REFERENCED */
- xfs_agblock_t agbno; /* block number containing inode */
- xfs_buf_t *agbp; /* buffer containing allocation group header */
- xfs_agino_t agino; /* inode number relative to allocation group */
- xfs_agnumber_t agno; /* allocation group number */
- xfs_agi_t *agi; /* allocation group header */
- xfs_btree_cur_t *cur; /* inode btree cursor */
- int error; /* error return value */
- int i; /* result code */
- int ilen; /* inodes in an inode cluster */
- xfs_mount_t *mp; /* mount structure for filesystem */
- int off; /* offset of inode in inode chunk */
- xfs_inobt_rec_incore_t rec; /* btree record */
- struct xfs_perag *pag;
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+ xfs_agnumber_t agno = be32_to_cpu(agi->agi_seqno);
+ struct xfs_perag *pag;
+ struct xfs_btree_cur *cur;
+ struct xfs_inobt_rec_incore rec;
+ int ilen;
+ int error;
+ int i;
+ int off;
- mp = tp->t_mountp;
-
- /*
- * Break up inode number into its components.
- */
- agno = XFS_INO_TO_AGNO(mp, inode);
- if (agno >= mp->m_sb.sb_agcount) {
- xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
- __func__, agno, mp->m_sb.sb_agcount);
- ASSERT(0);
- return XFS_ERROR(EINVAL);
- }
- agino = XFS_INO_TO_AGINO(mp, inode);
- if (inode != XFS_AGINO_TO_INO(mp, agno, agino)) {
- xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
- __func__, (unsigned long long)inode,
- (unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
- ASSERT(0);
- return XFS_ERROR(EINVAL);
- }
- agbno = XFS_AGINO_TO_AGBNO(mp, agino);
- if (agbno >= mp->m_sb.sb_agblocks) {
- xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
- __func__, agbno, mp->m_sb.sb_agblocks);
- ASSERT(0);
- return XFS_ERROR(EINVAL);
- }
- /*
- * Get the allocation group header.
- */
- error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
- if (error) {
- xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
- __func__, error);
- return error;
- }
- agi = XFS_BUF_TO_AGI(agbp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
- ASSERT(agbno < be32_to_cpu(agi->agi_length));
+ ASSERT(XFS_AGINO_TO_AGBNO(mp, agino) < be32_to_cpu(agi->agi_length));
+
/*
* Initialize the cursor.
*/
- cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
error = xfs_check_agi_freecount(cur, agi);
if (error)
@@ -1209,7 +1495,7 @@ xfs_difree(
if (!(mp->m_flags & XFS_MOUNT_IKEEP) &&
(rec.ir_freecount == mp->m_ialloc_inos)) {
- *delete = 1;
+ *deleted = 1;
*first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino);
/*
@@ -1237,7 +1523,7 @@ xfs_difree(
XFS_AGINO_TO_AGBNO(mp, rec.ir_startino)),
mp->m_ialloc_blks, flist, mp);
} else {
- *delete = 0;
+ *deleted = 0;
error = xfs_inobt_update(cur, &rec);
if (error) {
@@ -1261,6 +1547,7 @@ xfs_difree(
if (error)
goto error0;
+ *orec = rec;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
return 0;
@@ -1269,6 +1556,182 @@ error0:
return error;
}
+/*
+ * Free an inode in the free inode btree.
+ */
+STATIC int
+xfs_difree_finobt(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ xfs_agino_t agino,
+ struct xfs_inobt_rec_incore *ibtrec) /* inobt record */
+{
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+ xfs_agnumber_t agno = be32_to_cpu(agi->agi_seqno);
+ struct xfs_btree_cur *cur;
+ struct xfs_inobt_rec_incore rec;
+ int offset = agino - ibtrec->ir_startino;
+ int error;
+ int i;
+
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+ error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
+ if (error)
+ goto error;
+ if (i == 0) {
+ /*
+ * If the record does not exist in the finobt, we must have just
+ * freed an inode in a previously fully allocated chunk. If not,
+ * something is out of sync.
+ */
+ XFS_WANT_CORRUPTED_GOTO(ibtrec->ir_freecount == 1, error);
+
+ error = xfs_inobt_insert_rec(cur, ibtrec->ir_freecount,
+ ibtrec->ir_free, &i);
+ if (error)
+ goto error;
+ ASSERT(i == 1);
+
+ goto out;
+ }
+
+ /*
+ * Read and update the existing record. We could just copy the ibtrec
+ * across here, but that would defeat the purpose of having redundant
+ * metadata. By making the modifications independently, we can catch
+ * corruptions that we wouldn't see if we just copied from one record
+ * to another.
+ */
+ error = xfs_inobt_get_rec(cur, &rec, &i);
+ if (error)
+ goto error;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+
+ rec.ir_free |= XFS_INOBT_MASK(offset);
+ rec.ir_freecount++;
+
+ XFS_WANT_CORRUPTED_GOTO((rec.ir_free == ibtrec->ir_free) &&
+ (rec.ir_freecount == ibtrec->ir_freecount),
+ error);
+
+ /*
+ * The content of inobt records should always match between the inobt
+ * and finobt. The lifecycle of records in the finobt is different from
+ * the inobt in that the finobt only tracks records with at least one
+ * free inode. Hence, if all of the inodes are free and we aren't
+ * keeping inode chunks permanently on disk, remove the record.
+ * Otherwise, update the record with the new information.
+ */
+ if (rec.ir_freecount == mp->m_ialloc_inos &&
+ !(mp->m_flags & XFS_MOUNT_IKEEP)) {
+ error = xfs_btree_delete(cur, &i);
+ if (error)
+ goto error;
+ ASSERT(i == 1);
+ } else {
+ error = xfs_inobt_update(cur, &rec);
+ if (error)
+ goto error;
+ }
+
+out:
+ error = xfs_check_agi_freecount(cur, agi);
+ if (error)
+ goto error;
+
+ xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+ return 0;
+
+error:
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ return error;
+}
+
+/*
+ * Free disk inode. Carefully avoids touching the incore inode, all
+ * manipulations incore are the caller's responsibility.
+ * The on-disk inode is not changed by this operation, only the
+ * btree (free inode mask) is changed.
+ */
+int
+xfs_difree(
+ struct xfs_trans *tp, /* transaction pointer */
+ xfs_ino_t inode, /* inode to be freed */
+ struct xfs_bmap_free *flist, /* extents to free */
+ int *deleted,/* set if inode cluster was deleted */
+ xfs_ino_t *first_ino)/* first inode in deleted cluster */
+{
+ /* REFERENCED */
+ xfs_agblock_t agbno; /* block number containing inode */
+ struct xfs_buf *agbp; /* buffer for allocation group header */
+ xfs_agino_t agino; /* allocation group inode number */
+ xfs_agnumber_t agno; /* allocation group number */
+ int error; /* error return value */
+ struct xfs_mount *mp; /* mount structure for filesystem */
+ struct xfs_inobt_rec_incore rec;/* btree record */
+
+ mp = tp->t_mountp;
+
+ /*
+ * Break up inode number into its components.
+ */
+ agno = XFS_INO_TO_AGNO(mp, inode);
+ if (agno >= mp->m_sb.sb_agcount) {
+ xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
+ __func__, agno, mp->m_sb.sb_agcount);
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+ agino = XFS_INO_TO_AGINO(mp, inode);
+ if (inode != XFS_AGINO_TO_INO(mp, agno, agino)) {
+ xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
+ __func__, (unsigned long long)inode,
+ (unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+ agbno = XFS_AGINO_TO_AGBNO(mp, agino);
+ if (agbno >= mp->m_sb.sb_agblocks) {
+ xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
+ __func__, agbno, mp->m_sb.sb_agblocks);
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+ /*
+ * Get the allocation group header.
+ */
+ error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+ if (error) {
+ xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
+ __func__, error);
+ return error;
+ }
+
+ /*
+ * Fix up the inode allocation btree.
+ */
+ error = xfs_difree_inobt(mp, tp, agbp, agino, flist, deleted, first_ino,
+ &rec);
+ if (error)
+ goto error0;
+
+ /*
+ * Fix up the free inode btree.
+ */
+ if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+ error = xfs_difree_finobt(mp, tp, agbp, agino, &rec);
+ if (error)
+ goto error0;
+ }
+
+ return 0;
+
+error0:
+ return error;
+}
+
STATIC int
xfs_imap_lookup(
struct xfs_mount *mp,
@@ -1300,7 +1763,7 @@ xfs_imap_lookup(
* we have a record, we need to ensure it contains the inode number
* we are looking up.
*/
- cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+ cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
if (!error) {
if (i)
@@ -1488,7 +1951,16 @@ xfs_ialloc_compute_maxlevels(
}
/*
- * Log specified fields for the ag hdr (inode section)
+ * Log specified fields for the ag hdr (inode section). The growth of the agi
+ * structure over time requires that we interpret the buffer as two logical
+ * regions delineated by the end of the unlinked list. This is due to the size
+ * of the hash table and its location in the middle of the agi.
+ *
+ * For example, a request to log a field before agi_unlinked and a field after
+ * agi_unlinked could cause us to log the entire hash table and use an excessive
+ * amount of log space. To avoid this behavior, log the region up through
+ * agi_unlinked in one call and the region after agi_unlinked through the end of
+ * the structure in another.
*/
void
xfs_ialloc_log_agi(
@@ -1511,6 +1983,8 @@ xfs_ialloc_log_agi(
offsetof(xfs_agi_t, agi_newino),
offsetof(xfs_agi_t, agi_dirino),
offsetof(xfs_agi_t, agi_unlinked),
+ offsetof(xfs_agi_t, agi_free_root),
+ offsetof(xfs_agi_t, agi_free_level),
sizeof(xfs_agi_t)
};
#ifdef DEBUG
@@ -1519,15 +1993,30 @@ xfs_ialloc_log_agi(
agi = XFS_BUF_TO_AGI(bp);
ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
#endif
+
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
+
/*
- * Compute byte offsets for the first and last fields.
+ * Compute byte offsets for the first and last fields in the first
+ * region and log the agi buffer. This only logs up through
+ * agi_unlinked.
*/
- xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS, &first, &last);
+ if (fields & XFS_AGI_ALL_BITS_R1) {
+ xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R1,
+ &first, &last);
+ xfs_trans_log_buf(tp, bp, first, last);
+ }
+
/*
- * Log the allocation group inode header buffer.
+ * Mask off the bits in the first region and calculate the first and
+ * last field offsets for any bits in the second region.
*/
- xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
- xfs_trans_log_buf(tp, bp, first, last);
+ fields &= ~XFS_AGI_ALL_BITS_R1;
+ if (fields) {
+ xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R2,
+ &first, &last);
+ xfs_trans_log_buf(tp, bp, first, last);
+ }
}
#ifdef DEBUG
@@ -1640,7 +2129,6 @@ xfs_read_agi(
if (error)
return error;
- ASSERT(!xfs_buf_geterror(*bpp));
xfs_buf_set_ref(*bpp, XFS_AGI_REF);
return 0;
}
diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h
index 812365d17e67..95ad1c002d60 100644
--- a/fs/xfs/xfs_ialloc.h
+++ b/fs/xfs/xfs_ialloc.h
@@ -90,7 +90,7 @@ xfs_difree(
struct xfs_trans *tp, /* transaction pointer */
xfs_ino_t inode, /* inode to be freed */
struct xfs_bmap_free *flist, /* extents to free */
- int *delete, /* set if inode cluster was deleted */
+ int *deleted, /* set if inode cluster was deleted */
xfs_ino_t *first_ino); /* first inode in deleted cluster */
/*
diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c
index 7e309b11e87d..726f83a681a5 100644
--- a/fs/xfs/xfs_ialloc_btree.c
+++ b/fs/xfs/xfs_ialloc_btree.c
@@ -49,7 +49,8 @@ xfs_inobt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp,
- cur->bc_private.a.agbp, cur->bc_private.a.agno);
+ cur->bc_private.a.agbp, cur->bc_private.a.agno,
+ cur->bc_btnum);
}
STATIC void
@@ -66,12 +67,26 @@ xfs_inobt_set_root(
xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
}
+STATIC void
+xfs_finobt_set_root(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *nptr,
+ int inc) /* level change */
+{
+ struct xfs_buf *agbp = cur->bc_private.a.agbp;
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
+
+ agi->agi_free_root = nptr->s;
+ be32_add_cpu(&agi->agi_free_level, inc);
+ xfs_ialloc_log_agi(cur->bc_tp, agbp,
+ XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL);
+}
+
STATIC int
xfs_inobt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
- int length,
int *stat)
{
xfs_alloc_arg_t args; /* block allocation args */
@@ -173,6 +188,17 @@ xfs_inobt_init_ptr_from_cur(
ptr->s = agi->agi_root;
}
+STATIC void
+xfs_finobt_init_ptr_from_cur(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr)
+{
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
+
+ ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));
+ ptr->s = agi->agi_free_root;
+}
+
STATIC __int64_t
xfs_inobt_key_diff(
struct xfs_btree_cur *cur,
@@ -203,6 +229,7 @@ xfs_inobt_verify(
*/
switch (block->bb_magic) {
case cpu_to_be32(XFS_IBT_CRC_MAGIC):
+ case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
if (!xfs_sb_version_hascrc(&mp->m_sb))
return false;
if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
@@ -214,6 +241,7 @@ xfs_inobt_verify(
return false;
/* fall through */
case cpu_to_be32(XFS_IBT_MAGIC):
+ case cpu_to_be32(XFS_FIBT_MAGIC):
break;
default:
return 0;
@@ -317,6 +345,28 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
#endif
};
+static const struct xfs_btree_ops xfs_finobt_ops = {
+ .rec_len = sizeof(xfs_inobt_rec_t),
+ .key_len = sizeof(xfs_inobt_key_t),
+
+ .dup_cursor = xfs_inobt_dup_cursor,
+ .set_root = xfs_finobt_set_root,
+ .alloc_block = xfs_inobt_alloc_block,
+ .free_block = xfs_inobt_free_block,
+ .get_minrecs = xfs_inobt_get_minrecs,
+ .get_maxrecs = xfs_inobt_get_maxrecs,
+ .init_key_from_rec = xfs_inobt_init_key_from_rec,
+ .init_rec_from_key = xfs_inobt_init_rec_from_key,
+ .init_rec_from_cur = xfs_inobt_init_rec_from_cur,
+ .init_ptr_from_cur = xfs_finobt_init_ptr_from_cur,
+ .key_diff = xfs_inobt_key_diff,
+ .buf_ops = &xfs_inobt_buf_ops,
+#if defined(DEBUG) || defined(XFS_WARN)
+ .keys_inorder = xfs_inobt_keys_inorder,
+ .recs_inorder = xfs_inobt_recs_inorder,
+#endif
+};
+
/*
* Allocate a new inode btree cursor.
*/
@@ -325,7 +375,8 @@ xfs_inobt_init_cursor(
struct xfs_mount *mp, /* file system mount point */
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *agbp, /* buffer for agi structure */
- xfs_agnumber_t agno) /* allocation group number */
+ xfs_agnumber_t agno, /* allocation group number */
+ xfs_btnum_t btnum) /* ialloc or free ino btree */
{
struct xfs_agi *agi = XFS_BUF_TO_AGI(agbp);
struct xfs_btree_cur *cur;
@@ -334,11 +385,17 @@ xfs_inobt_init_cursor(
cur->bc_tp = tp;
cur->bc_mp = mp;
- cur->bc_nlevels = be32_to_cpu(agi->agi_level);
- cur->bc_btnum = XFS_BTNUM_INO;
+ cur->bc_btnum = btnum;
+ if (btnum == XFS_BTNUM_INO) {
+ cur->bc_nlevels = be32_to_cpu(agi->agi_level);
+ cur->bc_ops = &xfs_inobt_ops;
+ } else {
+ cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
+ cur->bc_ops = &xfs_finobt_ops;
+ }
+
cur->bc_blocklog = mp->m_sb.sb_blocklog;
- cur->bc_ops = &xfs_inobt_ops;
if (xfs_sb_version_hascrc(&mp->m_sb))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
diff --git a/fs/xfs/xfs_ialloc_btree.h b/fs/xfs/xfs_ialloc_btree.h
index f38b22011c4e..d7ebea72c2d0 100644
--- a/fs/xfs/xfs_ialloc_btree.h
+++ b/fs/xfs/xfs_ialloc_btree.h
@@ -58,7 +58,8 @@ struct xfs_mount;
((index) - 1) * sizeof(xfs_inobt_ptr_t)))
extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
- struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
+ struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t,
+ xfs_btnum_t);
extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
#endif /* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 98d35244eecc..c48df5f25b9f 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -507,8 +507,7 @@ STATIC int
xfs_inode_ag_walk(
struct xfs_mount *mp,
struct xfs_perag *pag,
- int (*execute)(struct xfs_inode *ip,
- struct xfs_perag *pag, int flags,
+ int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
void *args,
@@ -582,7 +581,7 @@ restart:
for (i = 0; i < nr_found; i++) {
if (!batch[i])
continue;
- error = execute(batch[i], pag, flags, args);
+ error = execute(batch[i], flags, args);
IRELE(batch[i]);
if (error == EAGAIN) {
skipped++;
@@ -636,8 +635,7 @@ xfs_eofblocks_worker(
int
xfs_inode_ag_iterator(
struct xfs_mount *mp,
- int (*execute)(struct xfs_inode *ip,
- struct xfs_perag *pag, int flags,
+ int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
void *args)
@@ -664,8 +662,7 @@ xfs_inode_ag_iterator(
int
xfs_inode_ag_iterator_tag(
struct xfs_mount *mp,
- int (*execute)(struct xfs_inode *ip,
- struct xfs_perag *pag, int flags,
+ int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
void *args,
@@ -1209,7 +1206,6 @@ xfs_inode_match_id(
STATIC int
xfs_inode_free_eofblocks(
struct xfs_inode *ip,
- struct xfs_perag *pag,
int flags,
void *args)
{
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 9ed68bb750f5..9cf017b899be 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -60,12 +60,10 @@ int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *);
void xfs_eofblocks_worker(struct work_struct *);
int xfs_inode_ag_iterator(struct xfs_mount *mp,
- int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag,
- int flags, void *args),
+ int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args);
int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
- int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag,
- int flags, void *args),
+ int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args, int tag);
static inline int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 768087bedbac..a6115fe1ac94 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -655,7 +655,6 @@ xfs_ialloc(
uint flags;
int error;
timespec_t tv;
- int filestreams = 0;
/*
* Call the space management code to pick
@@ -682,6 +681,14 @@ xfs_ialloc(
return error;
ASSERT(ip != NULL);
+ /*
+ * We always convert v1 inodes to v2 now - we only support filesystems
+ * with >= v2 inode capability, so there is no reason for ever leaving
+ * an inode in v1 format.
+ */
+ if (ip->i_d.di_version == 1)
+ ip->i_d.di_version = 2;
+
ip->i_d.di_mode = mode;
ip->i_d.di_onlink = 0;
ip->i_d.di_nlink = nlink;
@@ -691,27 +698,6 @@ xfs_ialloc(
xfs_set_projid(ip, prid);
memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
- /*
- * If the superblock version is up to where we support new format
- * inodes and this is currently an old format inode, then change
- * the inode version number now. This way we only do the conversion
- * here rather than here and in the flush/logging code.
- */
- if (xfs_sb_version_hasnlink(&mp->m_sb) &&
- ip->i_d.di_version == 1) {
- ip->i_d.di_version = 2;
- /*
- * We've already zeroed the old link count, the projid field,
- * and the pad field.
- */
- }
-
- /*
- * Project ids won't be stored on disk if we are using a version 1 inode.
- */
- if ((prid != 0) && (ip->i_d.di_version == 1))
- xfs_bump_ino_vers2(tp, ip);
-
if (pip && XFS_INHERIT_GID(pip)) {
ip->i_d.di_gid = pip->i_d.di_gid;
if ((pip->i_d.di_mode & S_ISGID) && S_ISDIR(mode)) {
@@ -772,13 +758,6 @@ xfs_ialloc(
flags |= XFS_ILOG_DEV;
break;
case S_IFREG:
- /*
- * we can't set up filestreams until after the VFS inode
- * is set up properly.
- */
- if (pip && xfs_inode_is_filestream(pip))
- filestreams = 1;
- /* fall through */
case S_IFDIR:
if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
uint di_flags = 0;
@@ -844,15 +823,6 @@ xfs_ialloc(
/* now that we have an i_mode we can setup inode ops and unlock */
xfs_setup_inode(ip);
- /* now we have set up the vfs inode we can associate the filestream */
- if (filestreams) {
- error = xfs_filestream_associate(pip, ip);
- if (error < 0)
- return -error;
- if (!error)
- xfs_iflags_set(ip, XFS_IFILESTREAM);
- }
-
*ipp = ip;
return 0;
}
@@ -1073,40 +1043,6 @@ xfs_droplink(
}
/*
- * This gets called when the inode's version needs to be changed from 1 to 2.
- * Currently this happens when the nlink field overflows the old 16-bit value
- * or when chproj is called to change the project for the first time.
- * As a side effect the superblock version will also get rev'd
- * to contain the NLINK bit.
- */
-void
-xfs_bump_ino_vers2(
- xfs_trans_t *tp,
- xfs_inode_t *ip)
-{
- xfs_mount_t *mp;
-
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- ASSERT(ip->i_d.di_version == 1);
-
- ip->i_d.di_version = 2;
- ip->i_d.di_onlink = 0;
- memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
- mp = tp->t_mountp;
- if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
- spin_lock(&mp->m_sb_lock);
- if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
- xfs_sb_version_addnlink(&mp->m_sb);
- spin_unlock(&mp->m_sb_lock);
- xfs_mod_sb(tp, XFS_SB_VERSIONNUM);
- } else {
- spin_unlock(&mp->m_sb_lock);
- }
- }
- /* Caller must log the inode */
-}
-
-/*
* Increment the link count on an inode & log the change.
*/
int
@@ -1116,22 +1052,10 @@ xfs_bumplink(
{
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+ ASSERT(ip->i_d.di_version > 1);
ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
ip->i_d.di_nlink++;
inc_nlink(VFS_I(ip));
- if ((ip->i_d.di_version == 1) &&
- (ip->i_d.di_nlink > XFS_MAXLINK_1)) {
- /*
- * The inode has increased its number of links beyond
- * what can fit in an old format inode. It now needs
- * to be converted to a version 2 inode with a 32 bit
- * link count. If this is the first inode in the file
- * system to do this, then we need to bump the superblock
- * version number as well.
- */
- xfs_bump_ino_vers2(tp, ip);
- }
-
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return 0;
}
@@ -1699,16 +1623,6 @@ xfs_release(
int truncated;
/*
- * If we are using filestreams, and we have an unlinked
- * file that we are processing the last close on, then nothing
- * will be able to reopen and write to this file. Purge this
- * inode from the filestreams cache so that it doesn't delay
- * teardown of the inode.
- */
- if ((ip->i_d.di_nlink == 0) && xfs_inode_is_filestream(ip))
- xfs_filestream_deassociate(ip);
-
- /*
* If we previously truncated this file and removed old data
* in the process, we want to initiate "early" writeout on
* the last close. This is an attempt to combat the notorious
@@ -1838,9 +1752,33 @@ xfs_inactive_ifree(
int error;
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
- error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree, 0, 0);
+
+ /*
+ * The ifree transaction might need to allocate blocks for record
+ * insertion to the finobt. We don't want to fail here at ENOSPC, so
+ * allow ifree to dip into the reserved block pool if necessary.
+ *
+ * Freeing large sets of inodes generally means freeing inode chunks,
+ * directory and file data blocks, so this should be relatively safe.
+ * Only under severe circumstances should it be possible to free enough
+ * inodes to exhaust the reserve block pool via finobt expansion while
+ * at the same time not creating free space in the filesystem.
+ *
+ * Send a warning if the reservation does happen to fail, as the inode
+ * now remains allocated and sits on the unlinked list until the fs is
+ * repaired.
+ */
+ tp->t_flags |= XFS_TRANS_RESERVE;
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree,
+ XFS_IFREE_SPACE_RES(mp), 0);
if (error) {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ if (error == ENOSPC) {
+ xfs_warn_ratelimited(mp,
+ "Failed to remove inode(s) from unlinked list. "
+ "Please free space, unmount and run xfs_repair.");
+ } else {
+ ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ }
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
return error;
}
@@ -2664,13 +2602,7 @@ xfs_remove(
if (error)
goto std_return;
- /*
- * If we are using filestreams, kill the stream association.
- * If the file is still open it may get a new one but that
- * will get killed on last close in xfs_close() so we don't
- * have to worry about that.
- */
- if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
+ if (is_dir && xfs_inode_is_filestream(ip))
xfs_filestream_deassociate(ip);
return 0;
@@ -3258,6 +3190,7 @@ xfs_iflush_int(
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
ASSERT(iip != NULL && iip->ili_fields != 0);
+ ASSERT(ip->i_d.di_version > 1);
/* set *dip = inode's place in the buffer */
dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -3318,7 +3251,7 @@ xfs_iflush_int(
}
/*
- * Inode item log recovery for v1/v2 inodes are dependent on the
+ * Inode item log recovery for v2 inodes are dependent on the
* di_flushiter count for correct sequencing. We bump the flush
* iteration count so we can detect flushes which postdate a log record
* during recovery. This is redundant as we now log every change and
@@ -3341,40 +3274,9 @@ xfs_iflush_int(
if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
ip->i_d.di_flushiter = 0;
- /*
- * If this is really an old format inode and the superblock version
- * has not been updated to support only new format inodes, then
- * convert back to the old inode format. If the superblock version
- * has been updated, then make the conversion permanent.
- */
- ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb));
- if (ip->i_d.di_version == 1) {
- if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
- /*
- * Convert it back.
- */
- ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
- dip->di_onlink = cpu_to_be16(ip->i_d.di_nlink);
- } else {
- /*
- * The superblock version has already been bumped,
- * so just make the conversion to the new inode
- * format permanent.
- */
- ip->i_d.di_version = 2;
- dip->di_version = 2;
- ip->i_d.di_onlink = 0;
- dip->di_onlink = 0;
- memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
- memset(&(dip->di_pad[0]), 0,
- sizeof(dip->di_pad));
- ASSERT(xfs_get_projid(ip) == 0);
- }
- }
-
- xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp);
+ xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
if (XFS_IFORK_Q(ip))
- xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
+ xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
xfs_inobp_check(mp, bp);
/*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index f2fcde52b66d..f72bffa67266 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -209,7 +209,6 @@ xfs_get_initial_prid(struct xfs_inode *dp)
#define XFS_ISTALE (1 << 1) /* inode has been staled */
#define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */
#define XFS_INEW (1 << 3) /* inode has just been allocated */
-#define XFS_IFILESTREAM (1 << 4) /* inode is in a filestream dir. */
#define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */
#define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */
#define __XFS_IFLOCK_BIT 7 /* inode is being flushed right now */
@@ -225,8 +224,7 @@ xfs_get_initial_prid(struct xfs_inode *dp)
*/
#define XFS_IRECLAIM_RESET_FLAGS \
(XFS_IRECLAIMABLE | XFS_IRECLAIM | \
- XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \
- XFS_IFILESTREAM);
+ XFS_IDIRTY_RELEASE | XFS_ITRUNCATED)
/*
* Synchronize processes attempting to flush the in-core inode back to disk.
@@ -379,7 +377,6 @@ int xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t,
struct xfs_inode **, int *);
int xfs_droplink(struct xfs_trans *, struct xfs_inode *);
int xfs_bumplink(struct xfs_trans *, struct xfs_inode *);
-void xfs_bump_ino_vers2(struct xfs_trans *, struct xfs_inode *);
/* from xfs_file.c */
int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
diff --git a/fs/xfs/xfs_inode_buf.c b/fs/xfs/xfs_inode_buf.c
index 24e993996bdc..cb35ae41d4a1 100644
--- a/fs/xfs/xfs_inode_buf.c
+++ b/fs/xfs/xfs_inode_buf.c
@@ -437,17 +437,16 @@ xfs_iread(
}
/*
- * The inode format changed when we moved the link count and
- * made it 32 bits long. If this is an old format inode,
- * convert it in memory to look like a new one. If it gets
- * flushed to disk we will convert back before flushing or
- * logging it. We zero out the new projid field and the old link
- * count field. We'll handle clearing the pad field (the remains
- * of the old uuid field) when we actually convert the inode to
- * the new format. We don't change the version number so that we
- * can distinguish this from a real new format inode.
+ * Automatically convert version 1 inode formats in memory to version 2
+ * inode format. If the inode is modified, it will get logged and
+ * rewritten as a version 2 inode. We can do this because we set the
+ * superblock feature bit for v2 inodes unconditionally during mount
+ * and it means the reast of the code can assume the inode version is 2
+ * or higher.
*/
if (ip->i_d.di_version == 1) {
+ ip->i_d.di_version = 2;
+ memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
ip->i_d.di_nlink = ip->i_d.di_onlink;
ip->i_d.di_onlink = 0;
xfs_set_projid(ip, 0);
diff --git a/fs/xfs/xfs_inode_fork.c b/fs/xfs/xfs_inode_fork.c
index 73514c0486b7..b031e8d0d928 100644
--- a/fs/xfs/xfs_inode_fork.c
+++ b/fs/xfs/xfs_inode_fork.c
@@ -798,8 +798,7 @@ xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
xfs_inode_log_item_t *iip,
- int whichfork,
- xfs_buf_t *bp)
+ int whichfork)
{
char *cp;
xfs_ifork_t *ifp;
diff --git a/fs/xfs/xfs_inode_fork.h b/fs/xfs/xfs_inode_fork.h
index eb329a1ea888..7d3b1ed6dcbe 100644
--- a/fs/xfs/xfs_inode_fork.h
+++ b/fs/xfs/xfs_inode_fork.h
@@ -127,8 +127,7 @@ typedef struct xfs_ifork {
int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
- struct xfs_inode_log_item *, int,
- struct xfs_buf *);
+ struct xfs_inode_log_item *, int);
void xfs_idestroy_fork(struct xfs_inode *, int);
void xfs_idata_realloc(struct xfs_inode *, int, int);
void xfs_iroot_realloc(struct xfs_inode *, int, int);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 686889b4a1e5..a640137b3573 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -145,34 +145,6 @@ xfs_inode_item_size(
xfs_inode_item_attr_fork_size(iip, nvecs, nbytes);
}
-/*
- * If this is a v1 format inode, then we need to log it as such. This means
- * that we have to copy the link count from the new field to the old. We
- * don't have to worry about the new fields, because nothing trusts them as
- * long as the old inode version number is there.
- */
-STATIC void
-xfs_inode_item_format_v1_inode(
- struct xfs_inode *ip)
-{
- if (!xfs_sb_version_hasnlink(&ip->i_mount->m_sb)) {
- /*
- * Convert it back.
- */
- ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
- ip->i_d.di_onlink = ip->i_d.di_nlink;
- } else {
- /*
- * The superblock version has already been bumped,
- * so just make the conversion to the new inode
- * format permanent.
- */
- ip->i_d.di_version = 2;
- ip->i_d.di_onlink = 0;
- memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
- }
-}
-
STATIC void
xfs_inode_item_format_data_fork(
struct xfs_inode_log_item *iip,
@@ -370,6 +342,8 @@ xfs_inode_item_format(
struct xfs_inode_log_format *ilf;
struct xfs_log_iovec *vecp = NULL;
+ ASSERT(ip->i_d.di_version > 1);
+
ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT);
ilf->ilf_type = XFS_LI_INODE;
ilf->ilf_ino = ip->i_ino;
@@ -380,8 +354,6 @@ xfs_inode_item_format(
ilf->ilf_size = 2; /* format + core */
xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
- if (ip->i_d.di_version == 1)
- xfs_inode_item_format_v1_inode(ip);
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
&ip->i_d,
xfs_icdinode_size(ip->i_d.di_version));
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 0b18776b075e..8bc1bbce7451 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -543,10 +543,11 @@ xfs_attrmulti_by_handle(
ops = memdup_user(am_hreq.ops, size);
if (IS_ERR(ops)) {
- error = PTR_ERR(ops);
+ error = -PTR_ERR(ops);
goto out_dput;
}
+ error = ENOMEM;
attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
if (!attr_name)
goto out_kfree_ops;
@@ -556,7 +557,7 @@ xfs_attrmulti_by_handle(
ops[i].am_error = strncpy_from_user((char *)attr_name,
ops[i].am_attrname, MAXNAMELEN);
if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
- error = -ERANGE;
+ error = ERANGE;
if (ops[i].am_error < 0)
break;
@@ -1215,7 +1216,7 @@ xfs_ioctl_setattr(
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
- !inode_capable(VFS_I(ip), CAP_FSETID))
+ !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
/*
@@ -1227,15 +1228,8 @@ xfs_ioctl_setattr(
olddquot = xfs_qm_vop_chown(tp, ip,
&ip->i_pdquot, pdqp);
}
+ ASSERT(ip->i_d.di_version > 1);
xfs_set_projid(ip, fa->fsx_projid);
-
- /*
- * We may have to rev the inode as well as
- * the superblock version number since projids didn't
- * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
- */
- if (ip->i_d.di_version == 1)
- xfs_bump_ino_vers2(tp, ip);
}
}
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index a7992f8de9d3..944d5baa710a 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -424,10 +424,11 @@ xfs_compat_attrmulti_by_handle(
ops = memdup_user(compat_ptr(am_hreq.ops), size);
if (IS_ERR(ops)) {
- error = PTR_ERR(ops);
+ error = -PTR_ERR(ops);
goto out_dput;
}
+ error = ENOMEM;
attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
if (!attr_name)
goto out_kfree_ops;
@@ -438,7 +439,7 @@ xfs_compat_attrmulti_by_handle(
compat_ptr(ops[i].am_attrname),
MAXNAMELEN);
if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
- error = -ERANGE;
+ error = ERANGE;
if (ops[i].am_error < 0)
break;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 3b80ebae05f5..6c5eb4c551e3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -730,7 +730,7 @@ xfs_iomap_write_allocate(
*/
nimaps = 1;
end_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
- error = xfs_bmap_last_offset(NULL, ip, &last_block,
+ error = xfs_bmap_last_offset(ip, &last_block,
XFS_DATA_FORK);
if (error)
goto trans_cancel;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 36d630319a27..205613a06068 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -829,22 +829,34 @@ xfs_setattr_size(
*/
inode_dio_wait(inode);
+ /*
+ * Do all the page cache truncate work outside the transaction context
+ * as the "lock" order is page lock->log space reservation. i.e.
+ * locking pages inside the transaction can ABBA deadlock with
+ * writeback. We have to do the VFS inode size update before we truncate
+ * the pagecache, however, to avoid racing with page faults beyond the
+ * new EOF they are not serialised against truncate operations except by
+ * page locks and size updates.
+ *
+ * Hence we are in a situation where a truncate can fail with ENOMEM
+ * from xfs_trans_reserve(), but having already truncated the in-memory
+ * version of the file (i.e. made user visible changes). There's not
+ * much we can do about this, except to hope that the caller sees ENOMEM
+ * and retries the truncate operation.
+ */
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
return error;
+ truncate_setsize(inode, newsize);
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error)
goto out_trans_cancel;
- truncate_setsize(inode, newsize);
-
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
-
xfs_ilock(ip, XFS_ILOCK_EXCL);
-
xfs_trans_ijoin(tp, ip, 0);
/*
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index f46338285152..cb64f222d607 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -270,7 +270,8 @@ xfs_bulkstat(
/*
* Allocate and initialize a btree cursor for ialloc btree.
*/
- cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
+ cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
+ XFS_BTNUM_INO);
irbp = irbuf;
irbufend = irbuf + nirbuf;
end_of_ag = 0;
@@ -621,7 +622,8 @@ xfs_inumbers(
agino = 0;
continue;
}
- cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
+ cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
+ XFS_BTNUM_INO);
error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_GE,
&tmp);
if (error) {
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a5f8bd9899d3..292308dede6d 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1165,7 +1165,7 @@ xlog_iodone(xfs_buf_t *bp)
/*
* Race to shutdown the filesystem if we see an error.
*/
- if (XFS_TEST_ERROR((xfs_buf_geterror(bp)), l->l_mp,
+ if (XFS_TEST_ERROR(bp->b_error, l->l_mp,
XFS_ERRTAG_IODONE_IOERR, XFS_RANDOM_IODONE_IOERR)) {
xfs_buf_ioerror_alert(bp, __func__);
xfs_buf_stale(bp);
@@ -3952,11 +3952,14 @@ xfs_log_force_umount(
retval = xlog_state_ioerror(log);
spin_unlock(&log->l_icloglock);
}
+
/*
- * Wake up everybody waiting on xfs_log_force.
- * Callback all log item committed functions as if the
- * log writes were completed.
+ * Wake up everybody waiting on xfs_log_force. Wake the CIL push first
+ * as if the log writes were completed. The abort handling in the log
+ * item committed callback functions will do this again under lock to
+ * avoid races.
*/
+ wake_up_all(&log->l_cilp->xc_commit_wait);
xlog_state_do_callback(log, XFS_LI_ABORTED, NULL);
#ifdef XFSERRORDEBUG
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 2c4004475e71..84e0deb95abd 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -24,7 +24,8 @@ struct xfs_log_vec {
struct xfs_log_iovec *lv_iovecp; /* iovec array */
struct xfs_log_item *lv_item; /* owner */
char *lv_buf; /* formatted buffer */
- int lv_buf_len; /* size of formatted buffer */
+ int lv_bytes; /* accounted space in buffer */
+ int lv_buf_len; /* aligned size of buffer */
int lv_size; /* size of allocated lv */
};
@@ -52,15 +53,21 @@ xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
return vec->i_addr;
}
+/*
+ * We need to make sure the next buffer is naturally aligned for the biggest
+ * basic data type we put into it. We already accounted for this padding when
+ * sizing the buffer.
+ *
+ * However, this padding does not get written into the log, and hence we have to
+ * track the space used by the log vectors separately to prevent log space hangs
+ * due to inaccurate accounting (i.e. a leak) of the used log space through the
+ * CIL context ticket.
+ */
static inline void
xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
{
- /*
- * We need to make sure the next buffer is naturally aligned for the
- * biggest basic data type we put into it. We already accounted for
- * this when sizing the buffer.
- */
lv->lv_buf_len += round_up(len, sizeof(uint64_t));
+ lv->lv_bytes += len;
vec->i_len = len;
}
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 7e5455391176..b3425b34e3d5 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -97,7 +97,7 @@ xfs_cil_prepare_item(
{
/* Account for the new LV being passed in */
if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
- *diff_len += lv->lv_buf_len;
+ *diff_len += lv->lv_bytes;
*diff_iovecs += lv->lv_niovecs;
}
@@ -111,7 +111,7 @@ xfs_cil_prepare_item(
else if (old_lv != lv) {
ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
- *diff_len -= old_lv->lv_buf_len;
+ *diff_len -= old_lv->lv_bytes;
*diff_iovecs -= old_lv->lv_niovecs;
kmem_free(old_lv);
}
@@ -239,7 +239,7 @@ xlog_cil_insert_format_items(
* that the space reservation accounting is correct.
*/
*diff_iovecs -= lv->lv_niovecs;
- *diff_len -= lv->lv_buf_len;
+ *diff_len -= lv->lv_bytes;
} else {
/* allocate new data chunk */
lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS);
@@ -259,6 +259,7 @@ xlog_cil_insert_format_items(
/* The allocated data region lies beyond the iovec region */
lv->lv_buf_len = 0;
+ lv->lv_bytes = 0;
lv->lv_buf = (char *)lv + buf_size - nbytes;
ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
@@ -385,7 +386,15 @@ xlog_cil_committed(
xfs_extent_busy_clear(mp, &ctx->busy_extents,
(mp->m_flags & XFS_MOUNT_DISCARD) && !abort);
+ /*
+ * If we are aborting the commit, wake up anyone waiting on the
+ * committing list. If we don't, then a shutdown we can leave processes
+ * waiting in xlog_cil_force_lsn() waiting on a sequence commit that
+ * will never happen because we aborted it.
+ */
spin_lock(&ctx->cil->xc_push_lock);
+ if (abort)
+ wake_up_all(&ctx->cil->xc_commit_wait);
list_del(&ctx->committing);
spin_unlock(&ctx->cil->xc_push_lock);
@@ -564,8 +573,18 @@ restart:
spin_lock(&cil->xc_push_lock);
list_for_each_entry(new_ctx, &cil->xc_committing, committing) {
/*
+ * Avoid getting stuck in this loop because we were woken by the
+ * shutdown, but then went back to sleep once already in the
+ * shutdown state.
+ */
+ if (XLOG_FORCED_SHUTDOWN(log)) {
+ spin_unlock(&cil->xc_push_lock);
+ goto out_abort_free_ticket;
+ }
+
+ /*
* Higher sequences will wait for this one so skip them.
- * Don't wait for own own sequence, either.
+ * Don't wait for our own sequence, either.
*/
if (new_ctx->sequence >= ctx->sequence)
continue;
@@ -810,6 +829,13 @@ restart:
*/
spin_lock(&cil->xc_push_lock);
list_for_each_entry(ctx, &cil->xc_committing, committing) {
+ /*
+ * Avoid getting stuck in this loop because we were woken by the
+ * shutdown, but then went back to sleep once already in the
+ * shutdown state.
+ */
+ if (XLOG_FORCED_SHUTDOWN(log))
+ goto out_shutdown;
if (ctx->sequence > sequence)
continue;
if (!ctx->commit_lsn) {
@@ -833,14 +859,12 @@ restart:
* push sequence after the above wait loop and the CIL still contains
* dirty objects.
*
- * When the push occurs, it will empty the CIL and
- * atomically increment the currect sequence past the push sequence and
- * move it into the committing list. Of course, if the CIL is clean at
- * the time of the push, it won't have pushed the CIL at all, so in that
- * case we should try the push for this sequence again from the start
- * just in case.
+ * When the push occurs, it will empty the CIL and atomically increment
+ * the currect sequence past the push sequence and move it into the
+ * committing list. Of course, if the CIL is clean at the time of the
+ * push, it won't have pushed the CIL at all, so in that case we should
+ * try the push for this sequence again from the start just in case.
*/
-
if (sequence == cil->xc_current_sequence &&
!list_empty(&cil->xc_cil)) {
spin_unlock(&cil->xc_push_lock);
@@ -849,6 +873,17 @@ restart:
spin_unlock(&cil->xc_push_lock);
return commit_lsn;
+
+ /*
+ * We detected a shutdown in progress. We need to trigger the log force
+ * to pass through it's iclog state machine error handling, even though
+ * we are already in a shutdown state. Hence we can't return
+ * NULLCOMMITLSN here as that has special meaning to log forces (i.e.
+ * LSN is already stable), so we return a zero LSN instead.
+ */
+out_shutdown:
+ spin_unlock(&cil->xc_push_lock);
+ return 0;
}
/*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index bce53ac81096..981af0f6504b 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2138,7 +2138,9 @@ xlog_recover_validate_buf_type(
bp->b_ops = &xfs_allocbt_buf_ops;
break;
case XFS_IBT_CRC_MAGIC:
+ case XFS_FIBT_CRC_MAGIC:
case XFS_IBT_MAGIC:
+ case XFS_FIBT_MAGIC:
bp->b_ops = &xfs_inobt_buf_ops;
break;
case XFS_BMAP_CRC_MAGIC:
@@ -3145,7 +3147,7 @@ xlog_recover_efd_pass2(
}
lip = xfs_trans_ail_cursor_next(ailp, &cur);
}
- xfs_trans_ail_cursor_done(ailp, &cur);
+ xfs_trans_ail_cursor_done(&cur);
spin_unlock(&ailp->xa_lock);
return 0;
@@ -3520,8 +3522,7 @@ out:
STATIC int
xlog_recover_unmount_trans(
- struct xlog *log,
- struct xlog_recover *trans)
+ struct xlog *log)
{
/* Do nothing now */
xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
@@ -3595,7 +3596,7 @@ xlog_recover_process_data(
trans, pass);
break;
case XLOG_UNMOUNT_TRANS:
- error = xlog_recover_unmount_trans(log, trans);
+ error = xlog_recover_unmount_trans(log);
break;
case XLOG_WAS_CONT_TRANS:
error = xlog_recover_add_to_cont_trans(log,
@@ -3757,7 +3758,7 @@ xlog_recover_process_efis(
lip = xfs_trans_ail_cursor_next(ailp, &cur);
}
out:
- xfs_trans_ail_cursor_done(ailp, &cur);
+ xfs_trans_ail_cursor_done(&cur);
spin_unlock(&ailp->xa_lock);
return error;
}
diff --git a/fs/xfs/xfs_log_rlimit.c b/fs/xfs/xfs_log_rlimit.c
index 2af1a0a4d0f1..ee7e0e80246b 100644
--- a/fs/xfs/xfs_log_rlimit.c
+++ b/fs/xfs/xfs_log_rlimit.c
@@ -42,7 +42,7 @@ xfs_log_calc_max_attrsetm_res(
int size;
int nblks;
- size = xfs_attr_leaf_entsize_local_max(mp->m_sb.sb_blocksize) -
+ size = xfs_attr_leaf_entsize_local_max(mp->m_attr_geo->blksize) -
MAXNAMELEN - 1;
nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
nblks += XFS_B_TO_FSB(mp, size);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 944f3d9456a8..3507cd0ec400 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -323,8 +323,19 @@ reread:
/*
* Initialize the mount structure from the superblock.
*/
- xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
- xfs_sb_quota_from_disk(&mp->m_sb);
+ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
+ xfs_sb_quota_from_disk(sbp);
+
+ /*
+ * If we haven't validated the superblock, do so now before we try
+ * to check the sector size and reread the superblock appropriately.
+ */
+ if (sbp->sb_magicnum != XFS_SB_MAGIC) {
+ if (loud)
+ xfs_warn(mp, "Invalid superblock magic number");
+ error = EINVAL;
+ goto release_buf;
+ }
/*
* We must be able to do sector-sized and sector-aligned IO.
@@ -337,11 +348,11 @@ reread:
goto release_buf;
}
- /*
- * Re-read the superblock so the buffer is correctly sized,
- * and properly verified.
- */
if (buf_ops == NULL) {
+ /*
+ * Re-read the superblock so the buffer is correctly sized,
+ * and properly verified.
+ */
xfs_buf_relse(bp);
sector_size = sbp->sb_sectsize;
buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
@@ -697,6 +708,12 @@ xfs_mountfs(
mp->m_update_flags |= XFS_SB_VERSIONNUM;
}
+ /* always use v2 inodes by default now */
+ if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
+ mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
+ mp->m_update_flags |= XFS_SB_VERSIONNUM;
+ }
+
/*
* Check if sb_agblocks is aligned at stripe boundary
* If sb_agblocks is NOT aligned turn off m_dalign since
@@ -774,12 +791,11 @@ xfs_mountfs(
mp->m_dmevmask = 0; /* not persistent; set after each mount */
- xfs_dir_mount(mp);
-
- /*
- * Initialize the attribute manager's entries.
- */
- mp->m_attr_magicpct = (mp->m_sb.sb_blocksize * 37) / 100;
+ error = xfs_da_mount(mp);
+ if (error) {
+ xfs_warn(mp, "Failed dir/attr init: %d", error);
+ goto out_remove_uuid;
+ }
/*
* Initialize the precomputed transaction reservations values.
@@ -794,7 +810,7 @@ xfs_mountfs(
error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
if (error) {
xfs_warn(mp, "Failed per-ag init: %d", error);
- goto out_remove_uuid;
+ goto out_free_dir;
}
if (!sbp->sb_logblocks) {
@@ -969,6 +985,8 @@ xfs_mountfs(
xfs_wait_buftarg(mp->m_ddev_targp);
out_free_perag:
xfs_free_perag(mp);
+ out_free_dir:
+ xfs_da_unmount(mp);
out_remove_uuid:
xfs_uuid_unmount(mp);
out:
@@ -1046,6 +1064,7 @@ xfs_unmountfs(
"Freespace may not be correct on next mount.");
xfs_log_unmount(mp);
+ xfs_da_unmount(mp);
xfs_uuid_unmount(mp);
#if defined(DEBUG)
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index a466c5e5826e..7295a0b7c343 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -27,6 +27,7 @@ struct xfs_nameops;
struct xfs_ail;
struct xfs_quotainfo;
struct xfs_dir_ops;
+struct xfs_da_geometry;
#ifdef HAVE_PERCPU_SB
@@ -96,6 +97,8 @@ typedef struct xfs_mount {
uint m_readio_blocks; /* min read size blocks */
uint m_writeio_log; /* min write size log bytes */
uint m_writeio_blocks; /* min write size blocks */
+ struct xfs_da_geometry *m_dir_geo; /* directory block geometry */
+ struct xfs_da_geometry *m_attr_geo; /* attribute block geometry */
struct xlog *m_log; /* log specific stuff */
int m_logbufs; /* number of log buffers */
int m_logbsize; /* size of each log buffer */
@@ -131,8 +134,6 @@ typedef struct xfs_mount {
int m_fixedfsid[2]; /* unchanged for life of FS */
uint m_dmevmask; /* DMI events for this FS */
__uint64_t m_flags; /* global mount flags */
- uint m_dir_node_ents; /* #entries in a dir danode */
- uint m_attr_node_ents; /* #entries in attr danode */
int m_ialloc_inos; /* inodes in inode allocation */
int m_ialloc_blks; /* blocks in inode allocation */
int m_inoalign_mask;/* mask sb_inoalignmt if used */
@@ -145,17 +146,10 @@ typedef struct xfs_mount {
int m_dalign; /* stripe unit */
int m_swidth; /* stripe width */
int m_sinoalign; /* stripe unit inode alignment */
- int m_attr_magicpct;/* 37% of the blocksize */
- int m_dir_magicpct; /* 37% of the dir blocksize */
__uint8_t m_sectbb_log; /* sectlog - BBSHIFT */
const struct xfs_nameops *m_dirnameops; /* vector of dir name ops */
const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */
const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */
- int m_dirblksize; /* directory block sz--bytes */
- int m_dirblkfsbs; /* directory block sz--fsbs */
- xfs_dablk_t m_dirdatablk; /* blockno of dir data v2 */
- xfs_dablk_t m_dirleafblk; /* blockno of dir non-data v2 */
- xfs_dablk_t m_dirfreeblk; /* blockno of dirfreeindex v2 */
uint m_chsize; /* size of next field */
atomic_t m_active_trans; /* number trans frozen */
#ifdef HAVE_PERCPU_SB
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 4aff56395732..f99b4933dc22 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -100,14 +100,20 @@
* likely result in a loop in one of the lists. That's a sure-fire recipe for
* an infinite loop in the code.
*/
-typedef struct xfs_mru_cache_elem
-{
- struct list_head list_node;
- unsigned long key;
- void *value;
-} xfs_mru_cache_elem_t;
+struct xfs_mru_cache {
+ struct radix_tree_root store; /* Core storage data structure. */
+ struct list_head *lists; /* Array of lists, one per grp. */
+ struct list_head reap_list; /* Elements overdue for reaping. */
+ spinlock_t lock; /* Lock to protect this struct. */
+ unsigned int grp_count; /* Number of discrete groups. */
+ unsigned int grp_time; /* Time period spanned by grps. */
+ unsigned int lru_grp; /* Group containing time zero. */
+ unsigned long time_zero; /* Time first element was added. */
+ xfs_mru_cache_free_func_t free_func; /* Function pointer for freeing. */
+ struct delayed_work work; /* Workqueue data for reaping. */
+ unsigned int queued; /* work has been queued */
+};
-static kmem_zone_t *xfs_mru_elem_zone;
static struct workqueue_struct *xfs_mru_reap_wq;
/*
@@ -129,12 +135,12 @@ static struct workqueue_struct *xfs_mru_reap_wq;
*/
STATIC unsigned long
_xfs_mru_cache_migrate(
- xfs_mru_cache_t *mru,
- unsigned long now)
+ struct xfs_mru_cache *mru,
+ unsigned long now)
{
- unsigned int grp;
- unsigned int migrated = 0;
- struct list_head *lru_list;
+ unsigned int grp;
+ unsigned int migrated = 0;
+ struct list_head *lru_list;
/* Nothing to do if the data store is empty. */
if (!mru->time_zero)
@@ -193,11 +199,11 @@ _xfs_mru_cache_migrate(
*/
STATIC void
_xfs_mru_cache_list_insert(
- xfs_mru_cache_t *mru,
- xfs_mru_cache_elem_t *elem)
+ struct xfs_mru_cache *mru,
+ struct xfs_mru_cache_elem *elem)
{
- unsigned int grp = 0;
- unsigned long now = jiffies;
+ unsigned int grp = 0;
+ unsigned long now = jiffies;
/*
* If the data store is empty, initialise time zero, leave grp set to
@@ -231,10 +237,10 @@ _xfs_mru_cache_list_insert(
*/
STATIC void
_xfs_mru_cache_clear_reap_list(
- xfs_mru_cache_t *mru) __releases(mru->lock) __acquires(mru->lock)
-
+ struct xfs_mru_cache *mru)
+ __releases(mru->lock) __acquires(mru->lock)
{
- xfs_mru_cache_elem_t *elem, *next;
+ struct xfs_mru_cache_elem *elem, *next;
struct list_head tmp;
INIT_LIST_HEAD(&tmp);
@@ -252,15 +258,8 @@ _xfs_mru_cache_clear_reap_list(
spin_unlock(&mru->lock);
list_for_each_entry_safe(elem, next, &tmp, list_node) {
-
- /* Remove the element from the reap list. */
list_del_init(&elem->list_node);
-
- /* Call the client's free function with the key and value pointer. */
- mru->free_func(elem->key, elem->value);
-
- /* Free the element structure. */
- kmem_zone_free(xfs_mru_elem_zone, elem);
+ mru->free_func(elem);
}
spin_lock(&mru->lock);
@@ -277,7 +276,8 @@ STATIC void
_xfs_mru_cache_reap(
struct work_struct *work)
{
- xfs_mru_cache_t *mru = container_of(work, xfs_mru_cache_t, work.work);
+ struct xfs_mru_cache *mru =
+ container_of(work, struct xfs_mru_cache, work.work);
unsigned long now, next;
ASSERT(mru && mru->lists);
@@ -304,28 +304,16 @@ _xfs_mru_cache_reap(
int
xfs_mru_cache_init(void)
{
- xfs_mru_elem_zone = kmem_zone_init(sizeof(xfs_mru_cache_elem_t),
- "xfs_mru_cache_elem");
- if (!xfs_mru_elem_zone)
- goto out;
-
xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache", WQ_MEM_RECLAIM, 1);
if (!xfs_mru_reap_wq)
- goto out_destroy_mru_elem_zone;
-
+ return -ENOMEM;
return 0;
-
- out_destroy_mru_elem_zone:
- kmem_zone_destroy(xfs_mru_elem_zone);
- out:
- return -ENOMEM;
}
void
xfs_mru_cache_uninit(void)
{
destroy_workqueue(xfs_mru_reap_wq);
- kmem_zone_destroy(xfs_mru_elem_zone);
}
/*
@@ -336,14 +324,14 @@ xfs_mru_cache_uninit(void)
*/
int
xfs_mru_cache_create(
- xfs_mru_cache_t **mrup,
+ struct xfs_mru_cache **mrup,
unsigned int lifetime_ms,
unsigned int grp_count,
xfs_mru_cache_free_func_t free_func)
{
- xfs_mru_cache_t *mru = NULL;
- int err = 0, grp;
- unsigned int grp_time;
+ struct xfs_mru_cache *mru = NULL;
+ int err = 0, grp;
+ unsigned int grp_time;
if (mrup)
*mrup = NULL;
@@ -400,7 +388,7 @@ exit:
*/
static void
xfs_mru_cache_flush(
- xfs_mru_cache_t *mru)
+ struct xfs_mru_cache *mru)
{
if (!mru || !mru->lists)
return;
@@ -420,7 +408,7 @@ xfs_mru_cache_flush(
void
xfs_mru_cache_destroy(
- xfs_mru_cache_t *mru)
+ struct xfs_mru_cache *mru)
{
if (!mru || !mru->lists)
return;
@@ -438,38 +426,30 @@ xfs_mru_cache_destroy(
*/
int
xfs_mru_cache_insert(
- xfs_mru_cache_t *mru,
- unsigned long key,
- void *value)
+ struct xfs_mru_cache *mru,
+ unsigned long key,
+ struct xfs_mru_cache_elem *elem)
{
- xfs_mru_cache_elem_t *elem;
+ int error;
ASSERT(mru && mru->lists);
if (!mru || !mru->lists)
return EINVAL;
- elem = kmem_zone_zalloc(xfs_mru_elem_zone, KM_SLEEP);
- if (!elem)
+ if (radix_tree_preload(GFP_KERNEL))
return ENOMEM;
- if (radix_tree_preload(GFP_KERNEL)) {
- kmem_zone_free(xfs_mru_elem_zone, elem);
- return ENOMEM;
- }
-
INIT_LIST_HEAD(&elem->list_node);
elem->key = key;
- elem->value = value;
spin_lock(&mru->lock);
-
- radix_tree_insert(&mru->store, key, elem);
+ error = -radix_tree_insert(&mru->store, key, elem);
radix_tree_preload_end();
- _xfs_mru_cache_list_insert(mru, elem);
-
+ if (!error)
+ _xfs_mru_cache_list_insert(mru, elem);
spin_unlock(&mru->lock);
- return 0;
+ return error;
}
/*
@@ -478,13 +458,12 @@ xfs_mru_cache_insert(
* the client data pointer for the removed element is returned, otherwise this
* function will return a NULL pointer.
*/
-void *
+struct xfs_mru_cache_elem *
xfs_mru_cache_remove(
- xfs_mru_cache_t *mru,
- unsigned long key)
+ struct xfs_mru_cache *mru,
+ unsigned long key)
{
- xfs_mru_cache_elem_t *elem;
- void *value = NULL;
+ struct xfs_mru_cache_elem *elem;
ASSERT(mru && mru->lists);
if (!mru || !mru->lists)
@@ -492,17 +471,11 @@ xfs_mru_cache_remove(
spin_lock(&mru->lock);
elem = radix_tree_delete(&mru->store, key);
- if (elem) {
- value = elem->value;
+ if (elem)
list_del(&elem->list_node);
- }
-
spin_unlock(&mru->lock);
- if (elem)
- kmem_zone_free(xfs_mru_elem_zone, elem);
-
- return value;
+ return elem;
}
/*
@@ -511,13 +484,14 @@ xfs_mru_cache_remove(
*/
void
xfs_mru_cache_delete(
- xfs_mru_cache_t *mru,
- unsigned long key)
+ struct xfs_mru_cache *mru,
+ unsigned long key)
{
- void *value = xfs_mru_cache_remove(mru, key);
+ struct xfs_mru_cache_elem *elem;
- if (value)
- mru->free_func(key, value);
+ elem = xfs_mru_cache_remove(mru, key);
+ if (elem)
+ mru->free_func(elem);
}
/*
@@ -540,12 +514,12 @@ xfs_mru_cache_delete(
* status, we need to help it get it right by annotating the path that does
* not release the lock.
*/
-void *
+struct xfs_mru_cache_elem *
xfs_mru_cache_lookup(
- xfs_mru_cache_t *mru,
- unsigned long key)
+ struct xfs_mru_cache *mru,
+ unsigned long key)
{
- xfs_mru_cache_elem_t *elem;
+ struct xfs_mru_cache_elem *elem;
ASSERT(mru && mru->lists);
if (!mru || !mru->lists)
@@ -560,7 +534,7 @@ xfs_mru_cache_lookup(
} else
spin_unlock(&mru->lock);
- return elem ? elem->value : NULL;
+ return elem;
}
/*
@@ -570,7 +544,8 @@ xfs_mru_cache_lookup(
*/
void
xfs_mru_cache_done(
- xfs_mru_cache_t *mru) __releases(mru->lock)
+ struct xfs_mru_cache *mru)
+ __releases(mru->lock)
{
spin_unlock(&mru->lock);
}
diff --git a/fs/xfs/xfs_mru_cache.h b/fs/xfs/xfs_mru_cache.h
index 36dd3ec8b4eb..fb5245ba5ff7 100644
--- a/fs/xfs/xfs_mru_cache.h
+++ b/fs/xfs/xfs_mru_cache.h
@@ -18,24 +18,15 @@
#ifndef __XFS_MRU_CACHE_H__
#define __XFS_MRU_CACHE_H__
+struct xfs_mru_cache;
-/* Function pointer type for callback to free a client's data pointer. */
-typedef void (*xfs_mru_cache_free_func_t)(unsigned long, void*);
+struct xfs_mru_cache_elem {
+ struct list_head list_node;
+ unsigned long key;
+};
-typedef struct xfs_mru_cache
-{
- struct radix_tree_root store; /* Core storage data structure. */
- struct list_head *lists; /* Array of lists, one per grp. */
- struct list_head reap_list; /* Elements overdue for reaping. */
- spinlock_t lock; /* Lock to protect this struct. */
- unsigned int grp_count; /* Number of discrete groups. */
- unsigned int grp_time; /* Time period spanned by grps. */
- unsigned int lru_grp; /* Group containing time zero. */
- unsigned long time_zero; /* Time first element was added. */
- xfs_mru_cache_free_func_t free_func; /* Function pointer for freeing. */
- struct delayed_work work; /* Workqueue data for reaping. */
- unsigned int queued; /* work has been queued */
-} xfs_mru_cache_t;
+/* Function pointer type for callback to free a client's data pointer. */
+typedef void (*xfs_mru_cache_free_func_t)(struct xfs_mru_cache_elem *elem);
int xfs_mru_cache_init(void);
void xfs_mru_cache_uninit(void);
@@ -44,10 +35,12 @@ int xfs_mru_cache_create(struct xfs_mru_cache **mrup, unsigned int lifetime_ms,
xfs_mru_cache_free_func_t free_func);
void xfs_mru_cache_destroy(struct xfs_mru_cache *mru);
int xfs_mru_cache_insert(struct xfs_mru_cache *mru, unsigned long key,
- void *value);
-void * xfs_mru_cache_remove(struct xfs_mru_cache *mru, unsigned long key);
+ struct xfs_mru_cache_elem *elem);
+struct xfs_mru_cache_elem *
+xfs_mru_cache_remove(struct xfs_mru_cache *mru, unsigned long key);
void xfs_mru_cache_delete(struct xfs_mru_cache *mru, unsigned long key);
-void *xfs_mru_cache_lookup(struct xfs_mru_cache *mru, unsigned long key);
+struct xfs_mru_cache_elem *
+xfs_mru_cache_lookup(struct xfs_mru_cache *mru, unsigned long key);
void xfs_mru_cache_done(struct xfs_mru_cache *mru);
#endif /* __XFS_MRU_CACHE_H__ */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index dc977b6e6a36..6d26759c779a 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -193,47 +193,6 @@ xfs_qm_dqpurge(
}
/*
- * Release the group or project dquot pointers the user dquots maybe carrying
- * around as a hint, and proceed to purge the user dquot cache if requested.
-*/
-STATIC int
-xfs_qm_dqpurge_hints(
- struct xfs_dquot *dqp,
- void *data)
-{
- struct xfs_dquot *gdqp = NULL;
- struct xfs_dquot *pdqp = NULL;
- uint flags = *((uint *)data);
-
- xfs_dqlock(dqp);
- if (dqp->dq_flags & XFS_DQ_FREEING) {
- xfs_dqunlock(dqp);
- return EAGAIN;
- }
-
- /* If this quota has a hint attached, prepare for releasing it now */
- gdqp = dqp->q_gdquot;
- if (gdqp)
- dqp->q_gdquot = NULL;
-
- pdqp = dqp->q_pdquot;
- if (pdqp)
- dqp->q_pdquot = NULL;
-
- xfs_dqunlock(dqp);
-
- if (gdqp)
- xfs_qm_dqrele(gdqp);
- if (pdqp)
- xfs_qm_dqrele(pdqp);
-
- if (flags & XFS_QMOPT_UQUOTA)
- return xfs_qm_dqpurge(dqp, NULL);
-
- return 0;
-}
-
-/*
* Purge the dquot cache.
*/
void
@@ -241,18 +200,8 @@ xfs_qm_dqpurge_all(
struct xfs_mount *mp,
uint flags)
{
- /*
- * We have to release group/project dquot hint(s) from the user dquot
- * at first if they are there, otherwise we would run into an infinite
- * loop while walking through radix tree to purge other type of dquots
- * since their refcount is not zero if the user dquot refers to them
- * as hint.
- *
- * Call the special xfs_qm_dqpurge_hints() will end up go through the
- * general xfs_qm_dqpurge() against user dquot cache if requested.
- */
- xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags);
-
+ if (flags & XFS_QMOPT_UQUOTA)
+ xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_GQUOTA)
xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_PQUOTA)
@@ -409,7 +358,6 @@ xfs_qm_dqattach_one(
xfs_dqid_t id,
uint type,
uint doalloc,
- xfs_dquot_t *udqhint, /* hint */
xfs_dquot_t **IO_idqpp)
{
xfs_dquot_t *dqp;
@@ -419,9 +367,9 @@ xfs_qm_dqattach_one(
error = 0;
/*
- * See if we already have it in the inode itself. IO_idqpp is
- * &i_udquot or &i_gdquot. This made the code look weird, but
- * made the logic a lot simpler.
+ * See if we already have it in the inode itself. IO_idqpp is &i_udquot
+ * or &i_gdquot. This made the code look weird, but made the logic a lot
+ * simpler.
*/
dqp = *IO_idqpp;
if (dqp) {
@@ -430,49 +378,10 @@ xfs_qm_dqattach_one(
}
/*
- * udqhint is the i_udquot field in inode, and is non-NULL only
- * when the type arg is group/project. Its purpose is to save a
- * lookup by dqid (xfs_qm_dqget) by caching a group dquot inside
- * the user dquot.
- */
- if (udqhint) {
- ASSERT(type == XFS_DQ_GROUP || type == XFS_DQ_PROJ);
- xfs_dqlock(udqhint);
-
- /*
- * No need to take dqlock to look at the id.
- *
- * The ID can't change until it gets reclaimed, and it won't
- * be reclaimed as long as we have a ref from inode and we
- * hold the ilock.
- */
- if (type == XFS_DQ_GROUP)
- dqp = udqhint->q_gdquot;
- else
- dqp = udqhint->q_pdquot;
- if (dqp && be32_to_cpu(dqp->q_core.d_id) == id) {
- ASSERT(*IO_idqpp == NULL);
-
- *IO_idqpp = xfs_qm_dqhold(dqp);
- xfs_dqunlock(udqhint);
- return 0;
- }
-
- /*
- * We can't hold a dquot lock when we call the dqget code.
- * We'll deadlock in no time, because of (not conforming to)
- * lock ordering - the inodelock comes before any dquot lock,
- * and we may drop and reacquire the ilock in xfs_qm_dqget().
- */
- xfs_dqunlock(udqhint);
- }
-
- /*
- * Find the dquot from somewhere. This bumps the
- * reference count of dquot and returns it locked.
- * This can return ENOENT if dquot didn't exist on
- * disk and we didn't ask it to allocate;
- * ESRCH if quotas got turned off suddenly.
+ * Find the dquot from somewhere. This bumps the reference count of
+ * dquot and returns it locked. This can return ENOENT if dquot didn't
+ * exist on disk and we didn't ask it to allocate; ESRCH if quotas got
+ * turned off suddenly.
*/
error = xfs_qm_dqget(ip->i_mount, ip, id, type,
doalloc | XFS_QMOPT_DOWARN, &dqp);
@@ -490,48 +399,6 @@ xfs_qm_dqattach_one(
return 0;
}
-
-/*
- * Given a udquot and group/project type, attach the group/project
- * dquot pointer to the udquot as a hint for future lookups.
- */
-STATIC void
-xfs_qm_dqattach_hint(
- struct xfs_inode *ip,
- int type)
-{
- struct xfs_dquot **dqhintp;
- struct xfs_dquot *dqp;
- struct xfs_dquot *udq = ip->i_udquot;
-
- ASSERT(type == XFS_DQ_GROUP || type == XFS_DQ_PROJ);
-
- xfs_dqlock(udq);
-
- if (type == XFS_DQ_GROUP) {
- dqp = ip->i_gdquot;
- dqhintp = &udq->q_gdquot;
- } else {
- dqp = ip->i_pdquot;
- dqhintp = &udq->q_pdquot;
- }
-
- if (*dqhintp) {
- struct xfs_dquot *tmp;
-
- if (*dqhintp == dqp)
- goto done;
-
- tmp = *dqhintp;
- *dqhintp = NULL;
- xfs_qm_dqrele(tmp);
- }
-
- *dqhintp = xfs_qm_dqhold(dqp);
-done:
- xfs_dqunlock(udq);
-}
-
static bool
xfs_qm_need_dqattach(
struct xfs_inode *ip)
@@ -562,7 +429,6 @@ xfs_qm_dqattach_locked(
uint flags)
{
xfs_mount_t *mp = ip->i_mount;
- uint nquotas = 0;
int error = 0;
if (!xfs_qm_need_dqattach(ip))
@@ -570,77 +436,39 @@ xfs_qm_dqattach_locked(
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- if (XFS_IS_UQUOTA_ON(mp)) {
+ if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
flags & XFS_QMOPT_DQALLOC,
- NULL, &ip->i_udquot);
+ &ip->i_udquot);
if (error)
goto done;
- nquotas++;
+ ASSERT(ip->i_udquot);
}
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- if (XFS_IS_GQUOTA_ON(mp)) {
+ if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
flags & XFS_QMOPT_DQALLOC,
- ip->i_udquot, &ip->i_gdquot);
- /*
- * Don't worry about the udquot that we may have
- * attached above. It'll get detached, if not already.
- */
+ &ip->i_gdquot);
if (error)
goto done;
- nquotas++;
+ ASSERT(ip->i_gdquot);
}
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- if (XFS_IS_PQUOTA_ON(mp)) {
+ if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
flags & XFS_QMOPT_DQALLOC,
- ip->i_udquot, &ip->i_pdquot);
- /*
- * Don't worry about the udquot that we may have
- * attached above. It'll get detached, if not already.
- */
+ &ip->i_pdquot);
if (error)
goto done;
- nquotas++;
+ ASSERT(ip->i_pdquot);
}
+done:
/*
- * Attach this group/project quota to the user quota as a hint.
- * This WON'T, in general, result in a thrash.
+ * Don't worry about the dquots that we may have attached before any
+ * error - they'll get detached later if it has not already been done.
*/
- if (nquotas > 1 && ip->i_udquot) {
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- ASSERT(ip->i_gdquot || !XFS_IS_GQUOTA_ON(mp));
- ASSERT(ip->i_pdquot || !XFS_IS_PQUOTA_ON(mp));
-
- /*
- * We do not have i_udquot locked at this point, but this check
- * is OK since we don't depend on the i_gdquot to be accurate
- * 100% all the time. It is just a hint, and this will
- * succeed in general.
- */
- if (ip->i_udquot->q_gdquot != ip->i_gdquot)
- xfs_qm_dqattach_hint(ip, XFS_DQ_GROUP);
-
- if (ip->i_udquot->q_pdquot != ip->i_pdquot)
- xfs_qm_dqattach_hint(ip, XFS_DQ_PROJ);
- }
-
- done:
-#ifdef DEBUG
- if (!error) {
- if (XFS_IS_UQUOTA_ON(mp))
- ASSERT(ip->i_udquot);
- if (XFS_IS_GQUOTA_ON(mp))
- ASSERT(ip->i_gdquot);
- if (XFS_IS_PQUOTA_ON(mp))
- ASSERT(ip->i_pdquot);
- }
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-#endif
return error;
}
@@ -865,8 +693,7 @@ xfs_qm_init_quotainfo(
/* Precalc some constants */
qinf->qi_dqchunklen = XFS_FSB_TO_BB(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
- qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(mp,
- qinf->qi_dqchunklen);
+ qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(qinf->qi_dqchunklen);
mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 3daf5ea1eb8d..bbc813caba4c 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -278,9 +278,10 @@ xfs_qm_scall_trunc_qfiles(
xfs_mount_t *mp,
uint flags)
{
- int error;
+ int error = EINVAL;
- if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
+ if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0 ||
+ (flags & ~XFS_DQ_ALLTYPES)) {
xfs_debug(mp, "%s: flags=%x m_qflags=%x",
__func__, flags, mp->m_qflags);
return XFS_ERROR(EINVAL);
@@ -959,7 +960,6 @@ xfs_qm_export_flags(
STATIC int
xfs_dqrele_inode(
struct xfs_inode *ip,
- struct xfs_perag *pag,
int flags,
void *args)
{
diff --git a/fs/xfs/xfs_quota_defs.h b/fs/xfs/xfs_quota_defs.h
index b3b2b1065c0f..137e20937077 100644
--- a/fs/xfs/xfs_quota_defs.h
+++ b/fs/xfs/xfs_quota_defs.h
@@ -156,6 +156,6 @@ typedef __uint16_t xfs_qwarncnt_t;
extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
xfs_dqid_t id, uint type, uint flags, char *str);
-extern int xfs_calc_dquots_per_chunk(struct xfs_mount *mp, unsigned int nbblks);
+extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
#endif /* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index af33cafe69b6..2ad1b9822e92 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -100,16 +100,36 @@ xfs_fs_set_xstate(
if (!XFS_IS_QUOTA_ON(mp))
return -EINVAL;
return -xfs_qm_scall_quotaoff(mp, flags);
- case Q_XQUOTARM:
- if (XFS_IS_QUOTA_ON(mp))
- return -EINVAL;
- return -xfs_qm_scall_trunc_qfiles(mp, flags);
}
return -EINVAL;
}
STATIC int
+xfs_fs_rm_xquota(
+ struct super_block *sb,
+ unsigned int uflags)
+{
+ struct xfs_mount *mp = XFS_M(sb);
+ unsigned int flags = 0;
+
+ if (sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
+ if (XFS_IS_QUOTA_ON(mp))
+ return -EINVAL;
+
+ if (uflags & FS_USER_QUOTA)
+ flags |= XFS_DQ_USER;
+ if (uflags & FS_GROUP_QUOTA)
+ flags |= XFS_DQ_GROUP;
+ if (uflags & FS_USER_QUOTA)
+ flags |= XFS_DQ_PROJ;
+
+ return -xfs_qm_scall_trunc_qfiles(mp, flags);
+}
+
+STATIC int
xfs_fs_get_dqblk(
struct super_block *sb,
struct kqid qid,
@@ -149,6 +169,7 @@ const struct quotactl_ops xfs_quotactl_operations = {
.get_xstatev = xfs_fs_get_xstatev,
.get_xstate = xfs_fs_get_xstate,
.set_xstate = xfs_fs_set_xstate,
+ .rm_xquota = xfs_fs_rm_xquota,
.get_dqblk = xfs_fs_get_dqblk,
.set_dqblk = xfs_fs_set_dqblk,
};
diff --git a/fs/xfs/xfs_rtbitmap.c b/fs/xfs/xfs_rtbitmap.c
index b1f2fe8af4a8..f4dd697cac08 100644
--- a/fs/xfs/xfs_rtbitmap.c
+++ b/fs/xfs/xfs_rtbitmap.c
@@ -74,7 +74,6 @@ xfs_rtbuf_get(
mp->m_bsize, 0, &bp, NULL);
if (error)
return error;
- ASSERT(!xfs_buf_geterror(bp));
*bpp = bp;
return 0;
}
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index 8baf61afae1d..c3453b11f563 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -291,7 +291,8 @@ xfs_mount_validate_sb(
(sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */) ||
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) ||
- sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
+ sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp) ||
+ sbp->sb_shared_vn != 0)) {
xfs_notice(mp, "SB sanity check failed");
return XFS_ERROR(EFSCORRUPTED);
}
@@ -333,15 +334,6 @@ xfs_mount_validate_sb(
xfs_warn(mp, "Offline file system operation in progress!");
return XFS_ERROR(EFSCORRUPTED);
}
-
- /*
- * Version 1 directory format has never worked on Linux.
- */
- if (unlikely(!xfs_sb_version_hasdirv2(sbp))) {
- xfs_warn(mp, "file system using version 1 directory format");
- return XFS_ERROR(ENOSYS);
- }
-
return 0;
}
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index f7b2fe77c5a5..c43c2d609a24 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -36,8 +36,6 @@ struct xfs_trans;
#define XFS_SB_VERSION_5 5 /* CRC enabled filesystem */
#define XFS_SB_VERSION_NUMBITS 0x000f
#define XFS_SB_VERSION_ALLFBITS 0xfff0
-#define XFS_SB_VERSION_SASHFBITS 0xf000
-#define XFS_SB_VERSION_REALFBITS 0x0ff0
#define XFS_SB_VERSION_ATTRBIT 0x0010
#define XFS_SB_VERSION_NLINKBIT 0x0020
#define XFS_SB_VERSION_QUOTABIT 0x0040
@@ -50,24 +48,15 @@ struct xfs_trans;
#define XFS_SB_VERSION_DIRV2BIT 0x2000
#define XFS_SB_VERSION_BORGBIT 0x4000 /* ASCII only case-insens. */
#define XFS_SB_VERSION_MOREBITSBIT 0x8000
-#define XFS_SB_VERSION_OKSASHFBITS \
- (XFS_SB_VERSION_EXTFLGBIT | \
- XFS_SB_VERSION_DIRV2BIT | \
- XFS_SB_VERSION_BORGBIT)
-#define XFS_SB_VERSION_OKREALFBITS \
- (XFS_SB_VERSION_ATTRBIT | \
- XFS_SB_VERSION_NLINKBIT | \
- XFS_SB_VERSION_QUOTABIT | \
- XFS_SB_VERSION_ALIGNBIT | \
- XFS_SB_VERSION_DALIGNBIT | \
- XFS_SB_VERSION_SHAREDBIT | \
- XFS_SB_VERSION_LOGV2BIT | \
- XFS_SB_VERSION_SECTORBIT | \
- XFS_SB_VERSION_MOREBITSBIT)
-#define XFS_SB_VERSION_OKREALBITS \
- (XFS_SB_VERSION_NUMBITS | \
- XFS_SB_VERSION_OKREALFBITS | \
- XFS_SB_VERSION_OKSASHFBITS)
+
+/*
+ * Supported feature bit list is just all bits in the versionnum field because
+ * we've used them all up and understand them all. Except, of course, for the
+ * shared superblock bit, which nobody knows what it does and so is unsupported.
+ */
+#define XFS_SB_VERSION_OKBITS \
+ ((XFS_SB_VERSION_NUMBITS | XFS_SB_VERSION_ALLFBITS) & \
+ ~XFS_SB_VERSION_SHAREDBIT)
/*
* There are two words to hold XFS "feature" bits: the original
@@ -76,7 +65,6 @@ struct xfs_trans;
*
* These defines represent bits in sb_features2.
*/
-#define XFS_SB_VERSION2_REALFBITS 0x00ffffff /* Mask: features */
#define XFS_SB_VERSION2_RESERVED1BIT 0x00000001
#define XFS_SB_VERSION2_LAZYSBCOUNTBIT 0x00000002 /* Superblk counters */
#define XFS_SB_VERSION2_RESERVED4BIT 0x00000004
@@ -86,16 +74,11 @@ struct xfs_trans;
#define XFS_SB_VERSION2_CRCBIT 0x00000100 /* metadata CRCs */
#define XFS_SB_VERSION2_FTYPE 0x00000200 /* inode type in dir */
-#define XFS_SB_VERSION2_OKREALFBITS \
+#define XFS_SB_VERSION2_OKBITS \
(XFS_SB_VERSION2_LAZYSBCOUNTBIT | \
XFS_SB_VERSION2_ATTR2BIT | \
XFS_SB_VERSION2_PROJID32BIT | \
XFS_SB_VERSION2_FTYPE)
-#define XFS_SB_VERSION2_OKSASHFBITS \
- (0)
-#define XFS_SB_VERSION2_OKREALBITS \
- (XFS_SB_VERSION2_OKREALFBITS | \
- XFS_SB_VERSION2_OKSASHFBITS )
/*
* Superblock - in core version. Must match the ondisk version below.
@@ -345,214 +328,140 @@ typedef enum {
#define XFS_SB_VERSION_NUM(sbp) ((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS)
-static inline int xfs_sb_good_version(xfs_sb_t *sbp)
-{
- /* We always support version 1-3 */
- if (sbp->sb_versionnum >= XFS_SB_VERSION_1 &&
- sbp->sb_versionnum <= XFS_SB_VERSION_3)
- return 1;
-
- /* We support version 4 if all feature bits are supported */
- if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) {
- if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKREALBITS) ||
- ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
- (sbp->sb_features2 & ~XFS_SB_VERSION2_OKREALBITS)))
- return 0;
-
- if (sbp->sb_shared_vn > XFS_SB_MAX_SHARED_VN)
- return 0;
- return 1;
- }
- if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5)
- return 1;
-
- return 0;
-}
-
/*
- * Detect a mismatched features2 field. Older kernels read/wrote
- * this into the wrong slot, so to be safe we keep them in sync.
+ * The first XFS version we support is a v4 superblock with V2 directories.
*/
-static inline int xfs_sb_has_mismatched_features2(xfs_sb_t *sbp)
+static inline bool xfs_sb_good_v4_features(struct xfs_sb *sbp)
{
- return (sbp->sb_bad_features2 != sbp->sb_features2);
-}
-
-static inline unsigned xfs_sb_version_tonew(unsigned v)
-{
- if (v == XFS_SB_VERSION_1)
- return XFS_SB_VERSION_4;
+ if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT))
+ return false;
- if (v == XFS_SB_VERSION_2)
- return XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT;
+ /* check for unknown features in the fs */
+ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
+ ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
+ (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
+ return false;
- return XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT |
- XFS_SB_VERSION_NLINKBIT;
+ return true;
}
-static inline unsigned xfs_sb_version_toold(unsigned v)
+static inline bool xfs_sb_good_version(struct xfs_sb *sbp)
{
- if (v & (XFS_SB_VERSION_QUOTABIT | XFS_SB_VERSION_ALIGNBIT))
- return 0;
- if (v & XFS_SB_VERSION_NLINKBIT)
- return XFS_SB_VERSION_3;
- if (v & XFS_SB_VERSION_ATTRBIT)
- return XFS_SB_VERSION_2;
- return XFS_SB_VERSION_1;
-}
-
-static inline int xfs_sb_version_hasattr(xfs_sb_t *sbp)
-{
- return sbp->sb_versionnum == XFS_SB_VERSION_2 ||
- sbp->sb_versionnum == XFS_SB_VERSION_3 ||
- (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT));
+ if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5)
+ return true;
+ if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4)
+ return xfs_sb_good_v4_features(sbp);
+ return false;
}
-static inline void xfs_sb_version_addattr(xfs_sb_t *sbp)
+/*
+ * Detect a mismatched features2 field. Older kernels read/wrote
+ * this into the wrong slot, so to be safe we keep them in sync.
+ */
+static inline bool xfs_sb_has_mismatched_features2(struct xfs_sb *sbp)
{
- if (sbp->sb_versionnum == XFS_SB_VERSION_1)
- sbp->sb_versionnum = XFS_SB_VERSION_2;
- else if (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4)
- sbp->sb_versionnum |= XFS_SB_VERSION_ATTRBIT;
- else
- sbp->sb_versionnum = XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT;
+ return sbp->sb_bad_features2 != sbp->sb_features2;
}
-static inline int xfs_sb_version_hasnlink(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasattr(struct xfs_sb *sbp)
{
- return sbp->sb_versionnum == XFS_SB_VERSION_3 ||
- (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT));
+ return (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT);
}
-static inline void xfs_sb_version_addnlink(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addattr(struct xfs_sb *sbp)
{
- if (sbp->sb_versionnum <= XFS_SB_VERSION_2)
- sbp->sb_versionnum = XFS_SB_VERSION_3;
- else
- sbp->sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
+ sbp->sb_versionnum |= XFS_SB_VERSION_ATTRBIT;
}
-static inline int xfs_sb_version_hasquota(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasquota(struct xfs_sb *sbp)
{
- return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
+ return (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
}
-static inline void xfs_sb_version_addquota(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addquota(struct xfs_sb *sbp)
{
- if (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4)
- sbp->sb_versionnum |= XFS_SB_VERSION_QUOTABIT;
- else
- sbp->sb_versionnum = xfs_sb_version_tonew(sbp->sb_versionnum) |
- XFS_SB_VERSION_QUOTABIT;
+ sbp->sb_versionnum |= XFS_SB_VERSION_QUOTABIT;
}
-static inline int xfs_sb_version_hasalign(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasalign(struct xfs_sb *sbp)
{
- return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
- (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
+ return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
(sbp->sb_versionnum & XFS_SB_VERSION_ALIGNBIT));
}
-static inline int xfs_sb_version_hasdalign(xfs_sb_t *sbp)
-{
- return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
-}
-
-static inline int xfs_sb_version_hasshared(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasdalign(struct xfs_sb *sbp)
{
- return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_SHAREDBIT);
+ return (sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
}
-static inline int xfs_sb_version_hasdirv2(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_haslogv2(struct xfs_sb *sbp)
{
- return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
- (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT));
+ return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
+ (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT);
}
-static inline int xfs_sb_version_haslogv2(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasextflgbit(struct xfs_sb *sbp)
{
- return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
- (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT));
+ return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
+ (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT);
}
-static inline int xfs_sb_version_hasextflgbit(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hassector(struct xfs_sb *sbp)
{
- return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
- (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT));
+ return (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
}
-static inline int xfs_sb_version_hassector(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasasciici(struct xfs_sb *sbp)
{
- return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
+ return (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
}
-static inline int xfs_sb_version_hasasciici(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasmorebits(struct xfs_sb *sbp)
{
- return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
-}
-
-static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp)
-{
- return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
- (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
- (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT));
+ return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
+ (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
}
/*
* sb_features2 bit version macros.
- *
- * For example, for a bit defined as XFS_SB_VERSION2_FUNBIT, has a macro:
- *
- * SB_VERSION_HASFUNBIT(xfs_sb_t *sbp)
- * ((xfs_sb_version_hasmorebits(sbp) &&
- * ((sbp)->sb_features2 & XFS_SB_VERSION2_FUNBIT)
*/
-
-static inline int xfs_sb_version_haslazysbcount(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_haslazysbcount(struct xfs_sb *sbp)
{
return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
(xfs_sb_version_hasmorebits(sbp) &&
(sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT));
}
-static inline int xfs_sb_version_hasattr2(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasattr2(struct xfs_sb *sbp)
{
return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
(xfs_sb_version_hasmorebits(sbp) &&
(sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT));
}
-static inline void xfs_sb_version_addattr2(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addattr2(struct xfs_sb *sbp)
{
sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT;
+ sbp->sb_bad_features2 |= XFS_SB_VERSION2_ATTR2BIT;
}
-static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp)
+static inline void xfs_sb_version_removeattr2(struct xfs_sb *sbp)
{
sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
+ sbp->sb_bad_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
if (!sbp->sb_features2)
sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT;
}
-static inline int xfs_sb_version_hasprojid32bit(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasprojid32bit(struct xfs_sb *sbp)
{
return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
(xfs_sb_version_hasmorebits(sbp) &&
(sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT));
}
-static inline void xfs_sb_version_addprojid32bit(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp)
{
sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
sbp->sb_features2 |= XFS_SB_VERSION2_PROJID32BIT;
@@ -587,7 +496,9 @@ xfs_sb_has_compat_feature(
return (sbp->sb_features_compat & feature) != 0;
}
-#define XFS_SB_FEAT_RO_COMPAT_ALL 0
+#define XFS_SB_FEAT_RO_COMPAT_FINOBT (1 << 0) /* free inode btree */
+#define XFS_SB_FEAT_RO_COMPAT_ALL \
+ (XFS_SB_FEAT_RO_COMPAT_FINOBT)
#define XFS_SB_FEAT_RO_COMPAT_UNKNOWN ~XFS_SB_FEAT_RO_COMPAT_ALL
static inline bool
xfs_sb_has_ro_compat_feature(
@@ -623,12 +534,12 @@ xfs_sb_has_incompat_log_feature(
/*
* V5 superblock specific feature checks
*/
-static inline int xfs_sb_version_hascrc(xfs_sb_t *sbp)
+static inline int xfs_sb_version_hascrc(struct xfs_sb *sbp)
{
return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
}
-static inline int xfs_sb_version_has_pquotino(xfs_sb_t *sbp)
+static inline int xfs_sb_version_has_pquotino(struct xfs_sb *sbp)
{
return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
}
@@ -641,6 +552,12 @@ static inline int xfs_sb_version_hasftype(struct xfs_sb *sbp)
(sbp->sb_features2 & XFS_SB_VERSION2_FTYPE));
}
+static inline int xfs_sb_version_hasfinobt(xfs_sb_t *sbp)
+{
+ return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
+ (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT);
+}
+
/*
* end of superblock version macros
*/
diff --git a/fs/xfs/xfs_shared.h b/fs/xfs/xfs_shared.h
index 4484e5151395..82404da2ca67 100644
--- a/fs/xfs/xfs_shared.h
+++ b/fs/xfs/xfs_shared.h
@@ -238,7 +238,7 @@ int xfs_log_calc_minimum_size(struct xfs_mount *);
int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
uint32_t size, struct xfs_buf *bp);
void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
struct xfs_inode *ip, struct xfs_ifork *ifp);
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index ce372b7d5644..f2240383d4bb 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -59,6 +59,7 @@ static int xfs_stat_proc_show(struct seq_file *m, void *v)
{ "abtc2", XFSSTAT_END_ABTC_V2 },
{ "bmbt2", XFSSTAT_END_BMBT_V2 },
{ "ibt2", XFSSTAT_END_IBT_V2 },
+ { "fibt2", XFSSTAT_END_FIBT_V2 },
/* we print both series of quota information together */
{ "qm", XFSSTAT_END_QM },
};
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index c03ad38ceaeb..c8f238b8299a 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -183,7 +183,23 @@ struct xfsstats {
__uint32_t xs_ibt_2_alloc;
__uint32_t xs_ibt_2_free;
__uint32_t xs_ibt_2_moves;
-#define XFSSTAT_END_XQMSTAT (XFSSTAT_END_IBT_V2+6)
+#define XFSSTAT_END_FIBT_V2 (XFSSTAT_END_IBT_V2+15)
+ __uint32_t xs_fibt_2_lookup;
+ __uint32_t xs_fibt_2_compare;
+ __uint32_t xs_fibt_2_insrec;
+ __uint32_t xs_fibt_2_delrec;
+ __uint32_t xs_fibt_2_newroot;
+ __uint32_t xs_fibt_2_killroot;
+ __uint32_t xs_fibt_2_increment;
+ __uint32_t xs_fibt_2_decrement;
+ __uint32_t xs_fibt_2_lshift;
+ __uint32_t xs_fibt_2_rshift;
+ __uint32_t xs_fibt_2_split;
+ __uint32_t xs_fibt_2_join;
+ __uint32_t xs_fibt_2_alloc;
+ __uint32_t xs_fibt_2_free;
+ __uint32_t xs_fibt_2_moves;
+#define XFSSTAT_END_XQMSTAT (XFSSTAT_END_FIBT_V2+6)
__uint32_t xs_qm_dqreclaims;
__uint32_t xs_qm_dqreclaim_misses;
__uint32_t xs_qm_dquot_dups;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 3494eff8e4eb..8f0333b3f7a0 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -765,20 +765,18 @@ xfs_open_devices(
* Setup xfs_mount buffer target pointers
*/
error = ENOMEM;
- mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, 0, mp->m_fsname);
+ mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
if (!mp->m_ddev_targp)
goto out_close_rtdev;
if (rtdev) {
- mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, 1,
- mp->m_fsname);
+ mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
if (!mp->m_rtdev_targp)
goto out_free_ddev_targ;
}
if (logdev && logdev != ddev) {
- mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, 1,
- mp->m_fsname);
+ mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
if (!mp->m_logdev_targp)
goto out_free_rtdev_targ;
} else {
@@ -811,8 +809,7 @@ xfs_setup_devices(
{
int error;
- error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize,
- mp->m_sb.sb_sectsize);
+ error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize);
if (error)
return error;
@@ -822,14 +819,12 @@ xfs_setup_devices(
if (xfs_sb_version_hassector(&mp->m_sb))
log_sector_size = mp->m_sb.sb_logsectsize;
error = xfs_setsize_buftarg(mp->m_logdev_targp,
- mp->m_sb.sb_blocksize,
log_sector_size);
if (error)
return error;
}
if (mp->m_rtdev_targp) {
error = xfs_setsize_buftarg(mp->m_rtdev_targp,
- mp->m_sb.sb_blocksize,
mp->m_sb.sb_sectsize);
if (error)
return error;
@@ -1754,13 +1749,9 @@ init_xfs_fs(void)
if (error)
goto out_destroy_wq;
- error = xfs_filestream_init();
- if (error)
- goto out_mru_cache_uninit;
-
error = xfs_buf_init();
if (error)
- goto out_filestream_uninit;
+ goto out_mru_cache_uninit;
error = xfs_init_procfs();
if (error)
@@ -1787,8 +1778,6 @@ init_xfs_fs(void)
xfs_cleanup_procfs();
out_buf_terminate:
xfs_buf_terminate();
- out_filestream_uninit:
- xfs_filestream_uninit();
out_mru_cache_uninit:
xfs_mru_cache_uninit();
out_destroy_wq:
@@ -1807,7 +1796,6 @@ exit_xfs_fs(void)
xfs_sysctl_unregister();
xfs_cleanup_procfs();
xfs_buf_terminate();
- xfs_filestream_uninit();
xfs_mru_cache_uninit();
xfs_destroy_workqueues();
xfs_destroy_zones();
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 52979aa90986..d69363c833e1 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -27,6 +27,7 @@
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_inode.h"
#include "xfs_ialloc.h"
@@ -92,7 +93,7 @@ xfs_readlink_bmap(
cur_chunk = bp->b_addr;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
- if (!xfs_symlink_hdr_ok(mp, ip->i_ino, offset,
+ if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
byte_cnt, bp)) {
error = EFSCORRUPTED;
xfs_alert(mp,
diff --git a/fs/xfs/xfs_symlink_remote.c b/fs/xfs/xfs_symlink_remote.c
index 9b32052ff65e..23c2f2577c8d 100644
--- a/fs/xfs/xfs_symlink_remote.c
+++ b/fs/xfs/xfs_symlink_remote.c
@@ -80,7 +80,6 @@ xfs_symlink_hdr_set(
*/
bool
xfs_symlink_hdr_ok(
- struct xfs_mount *mp,
xfs_ino_t ino,
uint32_t offset,
uint32_t size,
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index dee3279c095e..1e85bcd0e418 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -46,6 +46,7 @@
#include "xfs_log_recover.h"
#include "xfs_inode_item.h"
#include "xfs_bmap_btree.h"
+#include "xfs_filestream.h"
/*
* We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 65d8c793a25c..6910458915cf 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -538,6 +538,64 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
DEFINE_BUF_ITEM_EVENT(xfs_trans_buf_ordered);
+DECLARE_EVENT_CLASS(xfs_filestream_class,
+ TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno),
+ TP_ARGS(ip, agno),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_agnumber_t, agno)
+ __field(int, streams)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->agno = agno;
+ __entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx agno %u streams %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->agno,
+ __entry->streams)
+)
+#define DEFINE_FILESTREAM_EVENT(name) \
+DEFINE_EVENT(xfs_filestream_class, name, \
+ TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno), \
+ TP_ARGS(ip, agno))
+DEFINE_FILESTREAM_EVENT(xfs_filestream_free);
+DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup);
+DEFINE_FILESTREAM_EVENT(xfs_filestream_scan);
+
+TRACE_EVENT(xfs_filestream_pick,
+ TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno,
+ xfs_extlen_t free, int nscan),
+ TP_ARGS(ip, agno, free, nscan),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_agnumber_t, agno)
+ __field(int, streams)
+ __field(xfs_extlen_t, free)
+ __field(int, nscan)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->agno = agno;
+ __entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+ __entry->free = free;
+ __entry->nscan = nscan;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx agno %u streams %d free %d nscan %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->agno,
+ __entry->streams,
+ __entry->free,
+ __entry->nscan)
+);
+
DECLARE_EVENT_CLASS(xfs_lock_class,
TP_PROTO(struct xfs_inode *ip, unsigned lock_flags,
unsigned long caller_ip),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 54a57326d85b..d03932564ccb 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -827,7 +827,7 @@ xfs_trans_committed_bulk(
xfs_log_item_batch_insert(ailp, &cur, log_items, i, commit_lsn);
spin_lock(&ailp->xa_lock);
- xfs_trans_ail_cursor_done(ailp, &cur);
+ xfs_trans_ail_cursor_done(&cur);
spin_unlock(&ailp->xa_lock);
}
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index a7287354e535..cb0f3a84cc68 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -173,7 +173,6 @@ xfs_trans_ail_cursor_next(
*/
void
xfs_trans_ail_cursor_done(
- struct xfs_ail *ailp,
struct xfs_ail_cursor *cur)
{
cur->item = NULL;
@@ -368,7 +367,7 @@ xfsaild_push(
* If the AIL is empty or our push has reached the end we are
* done now.
*/
- xfs_trans_ail_cursor_done(ailp, &cur);
+ xfs_trans_ail_cursor_done(&cur);
spin_unlock(&ailp->xa_lock);
goto out_done;
}
@@ -453,7 +452,7 @@ xfsaild_push(
break;
lsn = lip->li_lsn;
}
- xfs_trans_ail_cursor_done(ailp, &cur);
+ xfs_trans_ail_cursor_done(&cur);
spin_unlock(&ailp->xa_lock);
if (xfs_buf_delwri_submit_nowait(&ailp->xa_buf_list))
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 12e86af9d9b9..bd1281862ad7 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -133,8 +133,7 @@ struct xfs_log_item * xfs_trans_ail_cursor_last(struct xfs_ail *ailp,
xfs_lsn_t lsn);
struct xfs_log_item * xfs_trans_ail_cursor_next(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur);
-void xfs_trans_ail_cursor_done(struct xfs_ail *ailp,
- struct xfs_ail_cursor *cur);
+void xfs_trans_ail_cursor_done(struct xfs_ail_cursor *cur);
#if BITS_PER_LONG != 64
static inline void
diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c
index ae368165244d..f2bda7c76b8a 100644
--- a/fs/xfs/xfs_trans_resv.c
+++ b/fs/xfs/xfs_trans_resv.c
@@ -26,6 +26,7 @@
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc.h"
@@ -106,6 +107,47 @@ xfs_calc_inode_res(
}
/*
+ * The free inode btree is a conditional feature and the log reservation
+ * requirements differ slightly from that of the traditional inode allocation
+ * btree. The finobt tracks records for inode chunks with at least one free
+ * inode. A record can be removed from the tree for an inode allocation
+ * or free and thus the finobt reservation is unconditional across:
+ *
+ * - inode allocation
+ * - inode free
+ * - inode chunk allocation
+ *
+ * The 'modify' param indicates to include the record modification scenario. The
+ * 'alloc' param indicates to include the reservation for free space btree
+ * modifications on behalf of finobt modifications. This is required only for
+ * transactions that do not already account for free space btree modifications.
+ *
+ * the free inode btree: max depth * block size
+ * the allocation btrees: 2 trees * (max depth - 1) * block size
+ * the free inode btree entry: block size
+ */
+STATIC uint
+xfs_calc_finobt_res(
+ struct xfs_mount *mp,
+ int alloc,
+ int modify)
+{
+ uint res;
+
+ if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+ return 0;
+
+ res = xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1));
+ if (alloc)
+ res += xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1));
+ if (modify)
+ res += (uint)XFS_FSB_TO_B(mp, 1);
+
+ return res;
+}
+
+/*
* Various log reservation values.
*
* These are based on the size of the file system block because that is what
@@ -302,6 +344,7 @@ xfs_calc_remove_reservation(
* the superblock for the nlink flag: sector size
* the directory btree: (max depth + v2) * dir block size
* the directory inode's bmap btree: (max depth + v2) * block size
+ * the finobt (record modification and allocation btrees)
*/
STATIC uint
xfs_calc_create_resv_modify(
@@ -310,7 +353,8 @@ xfs_calc_create_resv_modify(
return xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
(uint)XFS_FSB_TO_B(mp, 1) +
- xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_finobt_res(mp, 1, 1);
}
/*
@@ -348,6 +392,7 @@ __xfs_calc_create_reservation(
* the superblock for the nlink flag: sector size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
+ * the finobt (record insertion)
*/
STATIC uint
xfs_calc_icreate_resv_alloc(
@@ -357,7 +402,8 @@ xfs_calc_icreate_resv_alloc(
mp->m_sb.sb_sectsize +
xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
- XFS_FSB_TO_B(mp, 1));
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_finobt_res(mp, 0, 0);
}
STATIC uint
@@ -425,6 +471,7 @@ xfs_calc_symlink_reservation(
* the on disk inode before ours in the agi hash list: inode cluster size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
+ * the finobt (record insertion, removal or modification)
*/
STATIC uint
xfs_calc_ifree_reservation(
@@ -439,7 +486,8 @@ xfs_calc_ifree_reservation(
xfs_calc_buf_res(2 + mp->m_ialloc_blks +
mp->m_in_maxlevels, 0) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
- XFS_FSB_TO_B(mp, 1));
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_finobt_res(mp, 0, 1);
}
/*
@@ -562,7 +610,7 @@ xfs_calc_addafork_reservation(
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(1, mp->m_dirblksize) +
+ xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
diff --git a/fs/xfs/xfs_trans_space.h b/fs/xfs/xfs_trans_space.h
index af5dbe06cb65..bf9c4579334d 100644
--- a/fs/xfs/xfs_trans_space.h
+++ b/fs/xfs/xfs_trans_space.h
@@ -28,7 +28,8 @@
(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
XFS_EXTENTADD_SPACE_RES(mp,w))
-#define XFS_DAENTER_1B(mp,w) ((w) == XFS_DATA_FORK ? (mp)->m_dirblkfsbs : 1)
+#define XFS_DAENTER_1B(mp,w) \
+ ((w) == XFS_DATA_FORK ? (mp)->m_dir_geo->fsbcount : 1)
#define XFS_DAENTER_DBS(mp,w) \
(XFS_DA_NODE_MAXDEPTH + (((w) == XFS_DATA_FORK) ? 2 : 0))
#define XFS_DAENTER_BLOCKS(mp,w) \
@@ -47,13 +48,15 @@
#define XFS_DIRREMOVE_SPACE_RES(mp) \
XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
#define XFS_IALLOC_SPACE_RES(mp) \
- ((mp)->m_ialloc_blks + (mp)->m_in_maxlevels - 1)
+ ((mp)->m_ialloc_blks + \
+ (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \
+ ((mp)->m_in_maxlevels - 1)))
/*
* Space reservation values for various transactions.
*/
#define XFS_ADDAFORK_SPACE_RES(mp) \
- ((mp)->m_dirblkfsbs + XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK))
+ ((mp)->m_dir_geo->fsbcount + XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK))
#define XFS_ATTRRM_SPACE_RES(mp) \
XFS_DAREMOVE_SPACE_RES(mp, XFS_ATTR_FORK)
/* This macro is not used - see inline code in xfs_attr_set */
@@ -82,5 +85,8 @@
(XFS_DIRREMOVE_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
#define XFS_SYMLINK_SPACE_RES(mp,nl,b) \
(XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b))
+#define XFS_IFREE_SPACE_RES(mp) \
+ (xfs_sb_version_hasfinobt(&mp->m_sb) ? (mp)->m_in_maxlevels : 0)
+
#endif /* __XFS_TRANS_SPACE_H__ */
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index 82bbc34d54a3..65c6e6650b1a 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -134,7 +134,7 @@ typedef enum {
typedef enum {
XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_BMAPi, XFS_BTNUM_INOi,
- XFS_BTNUM_MAX
+ XFS_BTNUM_FINOi, XFS_BTNUM_MAX
} xfs_btnum_t;
struct xfs_name {