aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_inode.c2
-rw-r--r--fs/9p/vfs_inode_dotl.c4
-rw-r--r--fs/Kconfig.binfmt3
-rw-r--r--fs/Makefile4
-rw-r--r--fs/affs/affs.h2
-rw-r--r--fs/affs/amigaffs.c30
-rw-r--r--fs/affs/file.c76
-rw-r--r--fs/affs/inode.c4
-rw-r--r--fs/affs/namei.c40
-rw-r--r--fs/afs/dir.c80
-rw-r--r--fs/afs/inode.c4
-rw-r--r--fs/afs/mntpt.c22
-rw-r--r--fs/afs/rxrpc.c14
-rw-r--r--fs/afs/write.c9
-rw-r--r--fs/aio.c54
-rw-r--r--fs/autofs4/expire.c42
-rw-r--r--fs/autofs4/root.c25
-rw-r--r--fs/befs/linuxvfs.c20
-rw-r--r--fs/binfmt_aout.c8
-rw-r--r--fs/binfmt_elf.c278
-rw-r--r--fs/binfmt_em86.c4
-rw-r--r--fs/binfmt_misc.c398
-rw-r--r--fs/binfmt_script.c10
-rw-r--r--fs/block_dev.c10
-rw-r--r--fs/btrfs/check-integrity.c163
-rw-r--r--fs/btrfs/compression.c51
-rw-r--r--fs/btrfs/compression.h4
-rw-r--r--fs/btrfs/ctree.c16
-rw-r--r--fs/btrfs/ctree.h89
-rw-r--r--fs/btrfs/dev-replace.c32
-rw-r--r--fs/btrfs/dir-item.c10
-rw-r--r--fs/btrfs/disk-io.c55
-rw-r--r--fs/btrfs/extent-tree.c234
-rw-r--r--fs/btrfs/extent_io.c41
-rw-r--r--fs/btrfs/extent_io.h1
-rw-r--r--fs/btrfs/extent_map.c2
-rw-r--r--fs/btrfs/file-item.c2
-rw-r--r--fs/btrfs/file.c51
-rw-r--r--fs/btrfs/free-space-cache.c123
-rw-r--r--fs/btrfs/free-space-cache.h2
-rw-r--r--fs/btrfs/inode-map.c4
-rw-r--r--fs/btrfs/inode.c154
-rw-r--r--fs/btrfs/ioctl.c38
-rw-r--r--fs/btrfs/locking.c24
-rw-r--r--fs/btrfs/locking.h2
-rw-r--r--fs/btrfs/lzo.c15
-rw-r--r--fs/btrfs/ordered-data.c49
-rw-r--r--fs/btrfs/ordered-data.h12
-rw-r--r--fs/btrfs/raid56.c763
-rw-r--r--fs/btrfs/raid56.h16
-rw-r--r--fs/btrfs/scrub.c893
-rw-r--r--fs/btrfs/send.c49
-rw-r--r--fs/btrfs/super.c94
-rw-r--r--fs/btrfs/sysfs.c34
-rw-r--r--fs/btrfs/transaction.c166
-rw-r--r--fs/btrfs/transaction.h6
-rw-r--r--fs/btrfs/tree-log.c50
-rw-r--r--fs/btrfs/volumes.c92
-rw-r--r--fs/btrfs/volumes.h32
-rw-r--r--fs/btrfs/xattr.c150
-rw-r--r--fs/btrfs/zlib.c20
-rw-r--r--fs/cachefiles/namei.c21
-rw-r--r--fs/cachefiles/xattr.c15
-rw-r--r--fs/ceph/addr.c273
-rw-r--r--fs/ceph/caps.c134
-rw-r--r--fs/ceph/debugfs.c14
-rw-r--r--fs/ceph/dir.c83
-rw-r--r--fs/ceph/file.c103
-rw-r--r--fs/ceph/inode.c77
-rw-r--r--fs/ceph/locks.c64
-rw-r--r--fs/ceph/mds_client.c41
-rw-r--r--fs/ceph/mds_client.h10
-rw-r--r--fs/ceph/snap.c37
-rw-r--r--fs/ceph/super.c16
-rw-r--r--fs/ceph/super.h55
-rw-r--r--fs/ceph/xattr.c7
-rw-r--r--fs/char_dev.c1
-rw-r--r--fs/cifs/cifs_debug.c77
-rw-r--r--fs/cifs/cifs_debug.h7
-rw-r--r--fs/cifs/cifsacl.c2
-rw-r--r--fs/cifs/cifsfs.c3
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h12
-rw-r--r--fs/cifs/cifssmb.c20
-rw-r--r--fs/cifs/connect.c51
-rw-r--r--fs/cifs/file.c16
-rw-r--r--fs/cifs/inode.c2
-rw-r--r--fs/cifs/misc.c32
-rw-r--r--fs/cifs/netmisc.c12
-rw-r--r--fs/cifs/readdir.c24
-rw-r--r--fs/cifs/sess.c7
-rw-r--r--fs/cifs/smb2file.c4
-rw-r--r--fs/cifs/smb2misc.c50
-rw-r--r--fs/cifs/smb2ops.c68
-rw-r--r--fs/cifs/smb2pdu.c5
-rw-r--r--fs/cifs/smb2pdu.h49
-rw-r--r--fs/cifs/smb2transport.c2
-rw-r--r--fs/cifs/transport.c4
-rw-r--r--fs/coda/cache.c2
-rw-r--r--fs/coda/coda_linux.c6
-rw-r--r--fs/coda/coda_linux.h1
-rw-r--r--fs/coda/dir.c16
-rw-r--r--fs/compat.c21
-rw-r--r--fs/configfs/dir.c2
-rw-r--r--fs/dcache.c272
-rw-r--r--fs/debugfs/file.c69
-rw-r--r--fs/debugfs/inode.c2
-rw-r--r--fs/dlm/debug_fs.c263
-rw-r--r--fs/dlm/lock.c76
-rw-r--r--fs/dlm/lock.h3
-rw-r--r--fs/dlm/user.c13
-rw-r--r--fs/drop_caches.c11
-rw-r--r--fs/ecryptfs/crypto.c3
-rw-r--r--fs/ecryptfs/file.c18
-rw-r--r--fs/ecryptfs/keystore.c6
-rw-r--r--fs/ecryptfs/main.c16
-rw-r--r--fs/ecryptfs/mmap.c2
-rw-r--r--fs/efivarfs/file.c4
-rw-r--r--fs/efivarfs/super.c11
-rw-r--r--fs/eventfd.c9
-rw-r--r--fs/eventpoll.c13
-rw-r--r--fs/exec.c114
-rw-r--r--fs/exportfs/expfs.c7
-rw-r--r--fs/ext2/ext2.h3
-rw-r--r--fs/ext2/super.c10
-rw-r--r--fs/ext3/ext3.h4
-rw-r--r--fs/ext3/super.c10
-rw-r--r--fs/ext4/ext4.h4
-rw-r--r--fs/ext4/move_extent.c4
-rw-r--r--fs/ext4/super.c8
-rw-r--r--fs/f2fs/acl.c148
-rw-r--r--fs/f2fs/acl.h5
-rw-r--r--fs/f2fs/checkpoint.c186
-rw-r--r--fs/f2fs/data.c166
-rw-r--r--fs/f2fs/debug.c15
-rw-r--r--fs/f2fs/dir.c308
-rw-r--r--fs/f2fs/f2fs.h176
-rw-r--r--fs/f2fs/file.c212
-rw-r--r--fs/f2fs/gc.c89
-rw-r--r--fs/f2fs/gc.h5
-rw-r--r--fs/f2fs/inline.c482
-rw-r--r--fs/f2fs/inode.c44
-rw-r--r--fs/f2fs/namei.c58
-rw-r--r--fs/f2fs/node.c163
-rw-r--r--fs/f2fs/node.h8
-rw-r--r--fs/f2fs/recovery.c14
-rw-r--r--fs/f2fs/segment.c122
-rw-r--r--fs/f2fs/segment.h8
-rw-r--r--fs/f2fs/super.c29
-rw-r--r--fs/f2fs/xattr.c6
-rw-r--r--fs/f2fs/xattr.h6
-rw-r--r--fs/fat/dir.c5
-rw-r--r--fs/fat/fat.h1
-rw-r--r--fs/fat/file.c3
-rw-r--r--fs/fat/inode.c12
-rw-r--r--fs/fat/namei_vfat.c20
-rw-r--r--fs/file.c2
-rw-r--r--fs/fs-writeback.c29
-rw-r--r--fs/fuse/cuse.c2
-rw-r--r--fs/fuse/dev.c29
-rw-r--r--fs/fuse/dir.c542
-rw-r--r--fs/fuse/file.c232
-rw-r--r--fs/fuse/fuse_i.h45
-rw-r--r--fs/fuse/inode.c39
-rw-r--r--fs/gfs2/dir.c39
-rw-r--r--fs/gfs2/export.c8
-rw-r--r--fs/gfs2/file.c83
-rw-r--r--fs/gfs2/glock.c3
-rw-r--r--fs/gfs2/glops.c26
-rw-r--r--fs/gfs2/glops.h2
-rw-r--r--fs/gfs2/incore.h19
-rw-r--r--fs/gfs2/inode.c72
-rw-r--r--fs/gfs2/log.c42
-rw-r--r--fs/gfs2/main.c11
-rw-r--r--fs/gfs2/ops_fstype.c19
-rw-r--r--fs/gfs2/quota.c9
-rw-r--r--fs/gfs2/rgrp.c69
-rw-r--r--fs/gfs2/rgrp.h1
-rw-r--r--fs/gfs2/super.c112
-rw-r--r--fs/gfs2/super.h1
-rw-r--r--fs/gfs2/trans.c17
-rw-r--r--fs/hfs/catalog.c14
-rw-r--r--fs/hfsplus/catalog.c89
-rw-r--r--fs/hfsplus/dir.c11
-rw-r--r--fs/hfsplus/hfsplus_fs.h4
-rw-r--r--fs/hfsplus/super.c4
-rw-r--r--fs/hppfs/hppfs.c5
-rw-r--r--fs/hugetlbfs/inode.c14
-rw-r--r--fs/inode.c16
-rw-r--r--fs/internal.h5
-rw-r--r--fs/ioctl.c8
-rw-r--r--fs/isofs/inode.c42
-rw-r--r--fs/isofs/rock.c9
-rw-r--r--fs/jbd/journal.c3
-rw-r--r--fs/jbd2/journal.c5
-rw-r--r--fs/jffs2/readinode.c2
-rw-r--r--fs/jffs2/summary.c1
-rw-r--r--fs/jfs/jfs_incore.h3
-rw-r--r--fs/jfs/namei.c18
-rw-r--r--fs/jfs/super.c9
-rw-r--r--fs/kernfs/dir.c2
-rw-r--r--fs/kernfs/file.c95
-rw-r--r--fs/libfs.c12
-rw-r--r--fs/lockd/mon.c2
-rw-r--r--fs/lockd/svc.c2
-rw-r--r--fs/lockd/svclock.c2
-rw-r--r--fs/lockd/svcsubs.c2
-rw-r--r--fs/mount.h3
-rw-r--r--fs/namei.c100
-rw-r--r--fs/namespace.c71
-rw-r--r--fs/ncpfs/dir.c12
-rw-r--r--fs/ncpfs/file.c14
-rw-r--r--fs/ncpfs/ioctl.c1
-rw-r--r--fs/ncpfs/mmap.c4
-rw-r--r--fs/ncpfs/ncplib_kernel.h4
-rw-r--r--fs/nfs/blocklayout/blocklayout.c4
-rw-r--r--fs/nfs/blocklayout/rpc_pipefs.c16
-rw-r--r--fs/nfs/callback_proc.c2
-rw-r--r--fs/nfs/delegation.c25
-rw-r--r--fs/nfs/delegation.h1
-rw-r--r--fs/nfs/dir.c7
-rw-r--r--fs/nfs/direct.c1
-rw-r--r--fs/nfs/filelayout/filelayout.c3
-rw-r--r--fs/nfs/filelayout/filelayoutdev.c3
-rw-r--r--fs/nfs/fscache.c24
-rw-r--r--fs/nfs/getroot.c4
-rw-r--r--fs/nfs/inode.c11
-rw-r--r--fs/nfs/iostat.h5
-rw-r--r--fs/nfs/netns.h1
-rw-r--r--fs/nfs/nfs42.h2
-rw-r--r--fs/nfs/nfs42proc.c77
-rw-r--r--fs/nfs/nfs42xdr.c139
-rw-r--r--fs/nfs/nfs4_fs.h1
-rw-r--r--fs/nfs/nfs4client.c46
-rw-r--r--fs/nfs/nfs4file.c31
-rw-r--r--fs/nfs/nfs4proc.c107
-rw-r--r--fs/nfs/nfs4xdr.c12
-rw-r--r--fs/nfs/pagelist.c11
-rw-r--r--fs/nfs/read.c2
-rw-r--r--fs/nfs/write.c21
-rw-r--r--fs/nfsd/nfs4callback.c8
-rw-r--r--fs/nfsd/nfs4proc.c57
-rw-r--r--fs/nfsd/nfs4recover.c7
-rw-r--r--fs/nfsd/nfs4state.c74
-rw-r--r--fs/nfsd/nfs4xdr.c36
-rw-r--r--fs/nfsd/nfscache.c4
-rw-r--r--fs/nfsd/nfsctl.c43
-rw-r--r--fs/nfsd/nfsd.h9
-rw-r--r--fs/nfsd/nfsfh.c2
-rw-r--r--fs/nfsd/nfssvc.c2
-rw-r--r--fs/nfsd/state.h19
-rw-r--r--fs/nfsd/vfs.c53
-rw-r--r--fs/nfsd/vfs.h6
-rw-r--r--fs/nfsd/xdr4.h9
-rw-r--r--fs/nilfs2/file.c10
-rw-r--r--fs/nilfs2/inode.c32
-rw-r--r--fs/nilfs2/namei.c15
-rw-r--r--fs/nilfs2/the_nilfs.c3
-rw-r--r--fs/notify/dnotify/dnotify.c4
-rw-r--r--fs/notify/fdinfo.c84
-rw-r--r--fs/notify/fdinfo.h4
-rw-r--r--fs/notify/fsnotify.c44
-rw-r--r--fs/notify/fsnotify.h16
-rw-r--r--fs/notify/inode_mark.c115
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c2
-rw-r--r--fs/notify/inotify/inotify_user.c19
-rw-r--r--fs/notify/mark.c133
-rw-r--r--fs/notify/vfsmount_mark.c111
-rw-r--r--fs/nsfs.c161
-rw-r--r--fs/ntfs/namei.c4
-rw-r--r--fs/ocfs2/alloc.c28
-rw-r--r--fs/ocfs2/alloc.h2
-rw-r--r--fs/ocfs2/aops.c18
-rw-r--r--fs/ocfs2/cluster/heartbeat.c4
-rw-r--r--fs/ocfs2/cluster/tcp.c4
-rw-r--r--fs/ocfs2/dcache.c20
-rw-r--r--fs/ocfs2/dir.c12
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c2
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c24
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c18
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c4
-rw-r--r--fs/ocfs2/dlmglue.c40
-rw-r--r--fs/ocfs2/file.c6
-rw-r--r--fs/ocfs2/inode.c3
-rw-r--r--fs/ocfs2/inode.h2
-rw-r--r--fs/ocfs2/journal.c8
-rw-r--r--fs/ocfs2/move_extents.c3
-rw-r--r--fs/ocfs2/ocfs2.h6
-rw-r--r--fs/ocfs2/slot_map.c2
-rw-r--r--fs/ocfs2/super.c11
-rw-r--r--fs/ocfs2/xattr.c2
-rw-r--r--fs/open.c20
-rw-r--r--fs/overlayfs/Kconfig2
-rw-r--r--fs/overlayfs/Makefile4
-rw-r--r--fs/overlayfs/dir.c31
-rw-r--r--fs/overlayfs/inode.c27
-rw-r--r--fs/overlayfs/readdir.c49
-rw-r--r--fs/overlayfs/super.c61
-rw-r--r--fs/pnode.c1
-rw-r--r--fs/proc/array.c47
-rw-r--r--fs/proc/base.c60
-rw-r--r--fs/proc/fd.c3
-rw-r--r--fs/proc/generic.c163
-rw-r--r--fs/proc/inode.c10
-rw-r--r--fs/proc/internal.h13
-rw-r--r--fs/proc/meminfo.c15
-rw-r--r--fs/proc/namespaces.c153
-rw-r--r--fs/proc/proc_net.c1
-rw-r--r--fs/proc/root.c1
-rw-r--r--fs/proc/stat.c2
-rw-r--r--fs/proc/task_mmu.c107
-rw-r--r--fs/proc_namespace.c16
-rw-r--r--fs/pstore/inode.c22
-rw-r--r--fs/pstore/ram.c36
-rw-r--r--fs/pstore/ram_core.c31
-rw-r--r--fs/quota/dquot.c59
-rw-r--r--fs/quota/quota.c13
-rw-r--r--fs/read_write.c24
-rw-r--r--fs/readdir.c21
-rw-r--r--fs/reiserfs/journal.c2
-rw-r--r--fs/reiserfs/reiserfs.h4
-rw-r--r--fs/reiserfs/super.c14
-rw-r--r--fs/reiserfs/xattr.c21
-rw-r--r--fs/seq_file.c21
-rw-r--r--fs/signalfd.c4
-rw-r--r--fs/squashfs/Kconfig15
-rw-r--r--fs/squashfs/Makefile1
-rw-r--r--fs/squashfs/decompressor.c7
-rw-r--r--fs/squashfs/decompressor.h4
-rw-r--r--fs/squashfs/lz4_wrapper.c142
-rw-r--r--fs/squashfs/squashfs_fs.h1
-rw-r--r--fs/sync.c2
-rw-r--r--fs/sysfs/file.c59
-rw-r--r--fs/timerfd.c27
-rw-r--r--fs/ubifs/file.c1
-rw-r--r--fs/ubifs/journal.c7
-rw-r--r--fs/udf/dir.c31
-rw-r--r--fs/udf/inode.c14
-rw-r--r--fs/udf/namei.c17
-rw-r--r--fs/udf/super.c11
-rw-r--r--fs/udf/symlink.c57
-rw-r--r--fs/udf/udfdecl.h3
-rw-r--r--fs/udf/unicode.c28
-rw-r--r--fs/xattr.c16
-rw-r--r--fs/xfs/libxfs/xfs_ag.h281
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c1
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h3
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c1
-rw-r--r--fs/xfs/libxfs/xfs_attr.c3
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c2
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c77
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c3
-rw-r--r--fs/xfs/libxfs/xfs_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c6
-rw-r--r--fs/xfs/libxfs/xfs_da_format.c2
-rw-r--r--fs/xfs/libxfs/xfs_dinode.h243
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c20
-rw-r--r--fs/xfs/libxfs/xfs_dir2.h140
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c11
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c2
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c12
-rw-r--r--fs/xfs/libxfs/xfs_dir2_node.c14
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h140
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c13
-rw-r--r--fs/xfs/libxfs/xfs_dquot_buf.c2
-rw-r--r--fs/xfs/libxfs/xfs_format.h1107
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c43
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.h4
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c3
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c4
-rw-r--r--fs/xfs/libxfs/xfs_inum.h60
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h2
-rw-r--r--fs/xfs/libxfs/xfs_log_rlimit.c2
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c3
-rw-r--r--fs/xfs/libxfs/xfs_sb.c2
-rw-r--r--fs/xfs/libxfs/xfs_sb.h584
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c2
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c2
-rw-r--r--fs/xfs/xfs_acl.c2
-rw-r--r--fs/xfs/xfs_acl.h36
-rw-r--r--fs/xfs/xfs_aops.c3
-rw-r--r--fs/xfs/xfs_attr_inactive.c3
-rw-r--r--fs/xfs/xfs_attr_list.c3
-rw-r--r--fs/xfs/xfs_bmap_util.c75
-rw-r--r--fs/xfs/xfs_buf.c27
-rw-r--r--fs/xfs/xfs_buf.h3
-rw-r--r--fs/xfs/xfs_buf_item.c2
-rw-r--r--fs/xfs/xfs_dir2_readdir.c21
-rw-r--r--fs/xfs/xfs_discard.c1
-rw-r--r--fs/xfs/xfs_dquot.c2
-rw-r--r--fs/xfs/xfs_dquot_item.c2
-rw-r--r--fs/xfs/xfs_error.c2
-rw-r--r--fs/xfs/xfs_export.c3
-rw-r--r--fs/xfs/xfs_extent_busy.c1
-rw-r--r--fs/xfs/xfs_extfree_item.c3
-rw-r--r--fs/xfs/xfs_file.c9
-rw-r--r--fs/xfs/xfs_filestream.c3
-rw-r--r--fs/xfs/xfs_fsops.c2
-rw-r--r--fs/xfs/xfs_icache.c4
-rw-r--r--fs/xfs/xfs_icache.h8
-rw-r--r--fs/xfs/xfs_icreate_item.c3
-rw-r--r--fs/xfs/xfs_inode.c29
-rw-r--r--fs/xfs/xfs_inode.h2
-rw-r--r--fs/xfs/xfs_inode_item.c3
-rw-r--r--fs/xfs/xfs_ioctl.c3
-rw-r--r--fs/xfs/xfs_ioctl32.c2
-rw-r--r--fs/xfs/xfs_iomap.c18
-rw-r--r--fs/xfs/xfs_iops.c5
-rw-r--r--fs/xfs/xfs_itable.c256
-rw-r--r--fs/xfs/xfs_itable.h16
-rw-r--r--fs/xfs/xfs_linux.h6
-rw-r--r--fs/xfs/xfs_log.c8
-rw-r--r--fs/xfs/xfs_log_cil.c3
-rw-r--r--fs/xfs/xfs_log_recover.c4
-rw-r--r--fs/xfs/xfs_message.c3
-rw-r--r--fs/xfs/xfs_mount.c33
-rw-r--r--fs/xfs/xfs_mount.h8
-rw-r--r--fs/xfs/xfs_qm.c14
-rw-r--r--fs/xfs/xfs_qm_bhv.c2
-rw-r--r--fs/xfs/xfs_qm_syscalls.c27
-rw-r--r--fs/xfs/xfs_quotaops.c2
-rw-r--r--fs/xfs/xfs_rtalloc.c3
-rw-r--r--fs/xfs/xfs_super.c20
-rw-r--r--fs/xfs/xfs_symlink.c3
-rw-r--r--fs/xfs/xfs_trace.c2
-rw-r--r--fs/xfs/xfs_trans.c2
-rw-r--r--fs/xfs/xfs_trans_ail.c3
-rw-r--r--fs/xfs/xfs_trans_buf.c137
-rw-r--r--fs/xfs/xfs_trans_dquot.c2
-rw-r--r--fs/xfs/xfs_trans_extfree.c3
-rw-r--r--fs/xfs/xfs_trans_inode.c2
-rw-r--r--fs/xfs/xfs_xattr.c2
434 files changed, 11562 insertions, 6858 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 296482fc77a9..9ee5343d4884 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -832,7 +832,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
* moved b under k and client parallely did a lookup for
* k/b.
*/
- res = d_materialise_unique(dentry, inode);
+ res = d_splice_alias(inode, dentry);
if (!res)
v9fs_fid_add(dentry, fid);
else if (!IS_ERR(res))
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 02b64f4e576a..6054c16b8fae 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -826,8 +826,8 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
struct dentry *dir_dentry;
struct posix_acl *dacl = NULL, *pacl = NULL;
- p9_debug(P9_DEBUG_VFS, " %lu,%s mode: %hx MAJOR: %u MINOR: %u\n",
- dir->i_ino, dentry->d_name.name, omode,
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+ dir->i_ino, dentry, omode,
MAJOR(rdev), MINOR(rdev));
if (!new_valid_dev(rdev))
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 370b24cee4d8..c055d56ec63d 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -30,6 +30,9 @@ config COMPAT_BINFMT_ELF
config ARCH_BINFMT_ELF_RANDOMIZE_PIE
bool
+config ARCH_BINFMT_ELF_STATE
+ bool
+
config BINFMT_ELF_FDPIC
bool "Kernel support for FDPIC ELF binaries"
default y
diff --git a/fs/Makefile b/fs/Makefile
index 34a1b9dea6dd..bedff48e8fdc 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -11,7 +11,7 @@ obj-y := open.o read_write.o file_table.o super.o \
attr.o bad_inode.o file.o filesystems.o namespace.o \
seq_file.o xattr.o libfs.o fs-writeback.o \
pnode.o splice.o sync.o utimes.o \
- stack.o fs_struct.o statfs.o fs_pin.o
+ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o
ifeq ($(CONFIG_BLOCK),y)
obj-y += buffer.o block_dev.o direct-io.o mpage.o
@@ -104,7 +104,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/
obj-$(CONFIG_AUTOFS4_FS) += autofs4/
obj-$(CONFIG_ADFS_FS) += adfs/
obj-$(CONFIG_FUSE_FS) += fuse/
-obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/
+obj-$(CONFIG_OVERLAY_FS) += overlayfs/
obj-$(CONFIG_UDF_FS) += udf/
obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/
obj-$(CONFIG_OMFS_FS) += omfs/
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 9bca88159725..ff44ff3ff015 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -135,8 +135,10 @@ extern void affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
extern void secs_to_datestamp(time_t secs, struct affs_date *ds);
extern umode_t prot_to_mode(u32 prot);
extern void mode_to_prot(struct inode *inode);
+__printf(3, 4)
extern void affs_error(struct super_block *sb, const char *function,
const char *fmt, ...);
+__printf(3, 4)
extern void affs_warning(struct super_block *sb, const char *function,
const char *fmt, ...);
extern bool affs_nofilenametruncate(const struct dentry *dentry);
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index abc853968fed..c852f2fa1710 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -10,8 +10,6 @@
#include "affs.h"
-static char ErrorBuffer[256];
-
/*
* Functions for accessing Amiga-FFS structures.
*/
@@ -125,7 +123,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino)
{
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
if (entry_ino == (u32)(long)dentry->d_fsdata) {
dentry->d_fsdata = (void *)inode->i_ino;
break;
@@ -444,30 +442,30 @@ mode_to_prot(struct inode *inode)
void
affs_error(struct super_block *sb, const char *function, const char *fmt, ...)
{
- va_list args;
-
- va_start(args,fmt);
- vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
- va_end(args);
+ struct va_format vaf;
+ va_list args;
- pr_crit("error (device %s): %s(): %s\n", sb->s_id,
- function,ErrorBuffer);
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ pr_crit("error (device %s): %s(): %pV\n", sb->s_id, function, &vaf);
if (!(sb->s_flags & MS_RDONLY))
pr_warn("Remounting filesystem read-only\n");
sb->s_flags |= MS_RDONLY;
+ va_end(args);
}
void
affs_warning(struct super_block *sb, const char *function, const char *fmt, ...)
{
- va_list args;
+ struct va_format vaf;
+ va_list args;
- va_start(args,fmt);
- vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ pr_warn("(device %s): %s(): %pV\n", sb->s_id, function, &vaf);
va_end(args);
-
- pr_warn("(device %s): %s(): %s\n", sb->s_id,
- function,ErrorBuffer);
}
bool
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 1ed590aafecf..8faa6593ca6d 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -12,35 +12,10 @@
* affs regular file handling primitives
*/
+#include <linux/aio.h>
#include "affs.h"
-#if PAGE_SIZE < 4096
-#error PAGE_SIZE must be at least 4096
-#endif
-
-static int affs_grow_extcache(struct inode *inode, u32 lc_idx);
-static struct buffer_head *affs_alloc_extblock(struct inode *inode, struct buffer_head *bh, u32 ext);
-static inline struct buffer_head *affs_get_extblock(struct inode *inode, u32 ext);
static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
-static int affs_file_open(struct inode *inode, struct file *filp);
-static int affs_file_release(struct inode *inode, struct file *filp);
-
-const struct file_operations affs_file_operations = {
- .llseek = generic_file_llseek,
- .read = new_sync_read,
- .read_iter = generic_file_read_iter,
- .write = new_sync_write,
- .write_iter = generic_file_write_iter,
- .mmap = generic_file_mmap,
- .open = affs_file_open,
- .release = affs_file_release,
- .fsync = affs_file_fsync,
- .splice_read = generic_file_splice_read,
-};
-
-const struct inode_operations affs_file_inode_operations = {
- .setattr = affs_notify_change,
-};
static int
affs_file_open(struct inode *inode, struct file *filp)
@@ -355,7 +330,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
/* store new block */
if (bh_result->b_blocknr)
- affs_warning(sb, "get_block", "block already set (%x)", bh_result->b_blocknr);
+ affs_warning(sb, "get_block", "block already set (%lx)",
+ (unsigned long)bh_result->b_blocknr);
AFFS_BLOCK(sb, ext_bh, block) = cpu_to_be32(blocknr);
AFFS_HEAD(ext_bh)->block_count = cpu_to_be32(block + 1);
affs_adjust_checksum(ext_bh, blocknr - bh_result->b_blocknr + 1);
@@ -377,7 +353,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
return 0;
err_big:
- affs_error(inode->i_sb,"get_block","strange block request %d", block);
+ affs_error(inode->i_sb, "get_block", "strange block request %d",
+ (int)block);
return -EIO;
err_ext:
// unlock cache
@@ -412,6 +389,22 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
}
}
+static ssize_t
+affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ size_t count = iov_iter_count(iter);
+ ssize_t ret;
+
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, affs_get_block);
+ if (ret < 0 && (rw & WRITE))
+ affs_write_failed(mapping, offset + count);
+ return ret;
+}
+
static int affs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -438,6 +431,7 @@ const struct address_space_operations affs_aops = {
.writepage = affs_writepage,
.write_begin = affs_write_begin,
.write_end = generic_write_end,
+ .direct_IO = affs_direct_IO,
.bmap = _affs_bmap
};
@@ -867,8 +861,9 @@ affs_truncate(struct inode *inode)
// lock cache
ext_bh = affs_get_extblock(inode, ext);
if (IS_ERR(ext_bh)) {
- affs_warning(sb, "truncate", "unexpected read error for ext block %u (%d)",
- ext, PTR_ERR(ext_bh));
+ affs_warning(sb, "truncate",
+ "unexpected read error for ext block %u (%ld)",
+ (unsigned int)ext, PTR_ERR(ext_bh));
return;
}
if (AFFS_I(inode)->i_lc) {
@@ -914,8 +909,9 @@ affs_truncate(struct inode *inode)
struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0);
u32 tmp;
if (IS_ERR(bh)) {
- affs_warning(sb, "truncate", "unexpected read error for last block %u (%d)",
- ext, PTR_ERR(bh));
+ affs_warning(sb, "truncate",
+ "unexpected read error for last block %u (%ld)",
+ (unsigned int)ext, PTR_ERR(bh));
return;
}
tmp = be32_to_cpu(AFFS_DATA_HEAD(bh)->next);
@@ -961,3 +957,19 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
mutex_unlock(&inode->i_mutex);
return ret;
}
+const struct file_operations affs_file_operations = {
+ .llseek = generic_file_llseek,
+ .read = new_sync_read,
+ .read_iter = generic_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = generic_file_write_iter,
+ .mmap = generic_file_mmap,
+ .open = affs_file_open,
+ .release = affs_file_release,
+ .fsync = affs_file_fsync,
+ .splice_read = generic_file_splice_read,
+};
+
+const struct inode_operations affs_file_inode_operations = {
+ .setattr = affs_notify_change,
+};
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index e217c511459b..d0609a282e1d 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -348,9 +348,9 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
u32 block = 0;
int retval;
- pr_debug("%s(dir=%u, inode=%u, \"%*s\", type=%d)\n",
+ pr_debug("%s(dir=%u, inode=%u, \"%pd\", type=%d)\n",
__func__, (u32)dir->i_ino,
- (u32)inode->i_ino, (int)dentry->d_name.len, dentry->d_name.name, type);
+ (u32)inode->i_ino, dentry, type);
retval = -EIO;
bh = affs_bread(sb, inode->i_ino);
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 035bd31556fc..bbc38530e924 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -190,8 +190,7 @@ affs_find_entry(struct inode *dir, struct dentry *dentry)
toupper_t toupper = affs_get_toupper(sb);
u32 key;
- pr_debug("%s(\"%.*s\")\n",
- __func__, (int)dentry->d_name.len, dentry->d_name.name);
+ pr_debug("%s(\"%pd\")\n", __func__, dentry);
bh = affs_bread(sb, dir->i_ino);
if (!bh)
@@ -219,8 +218,7 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
struct buffer_head *bh;
struct inode *inode = NULL;
- pr_debug("%s(\"%.*s\")\n",
- __func__, (int)dentry->d_name.len, dentry->d_name.name);
+ pr_debug("%s(\"%pd\")\n", __func__, dentry);
affs_lock_dir(dir);
bh = affs_find_entry(dir, dentry);
@@ -250,9 +248,9 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
int
affs_unlink(struct inode *dir, struct dentry *dentry)
{
- pr_debug("%s(dir=%d, %lu \"%.*s\")\n",
+ pr_debug("%s(dir=%d, %lu \"%pd\")\n",
__func__, (u32)dir->i_ino, dentry->d_inode->i_ino,
- (int)dentry->d_name.len, dentry->d_name.name);
+ dentry);
return affs_remove_header(dentry);
}
@@ -264,9 +262,8 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
struct inode *inode;
int error;
- pr_debug("%s(%lu,\"%.*s\",0%ho)\n",
- __func__, dir->i_ino, (int)dentry->d_name.len,
- dentry->d_name.name,mode);
+ pr_debug("%s(%lu,\"%pd\",0%ho)\n",
+ __func__, dir->i_ino, dentry, mode);
inode = affs_new_inode(dir);
if (!inode)
@@ -294,9 +291,8 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct inode *inode;
int error;
- pr_debug("%s(%lu,\"%.*s\",0%ho)\n",
- __func__, dir->i_ino, (int)dentry->d_name.len,
- dentry->d_name.name, mode);
+ pr_debug("%s(%lu,\"%pd\",0%ho)\n",
+ __func__, dir->i_ino, dentry, mode);
inode = affs_new_inode(dir);
if (!inode)
@@ -321,9 +317,9 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
int
affs_rmdir(struct inode *dir, struct dentry *dentry)
{
- pr_debug("%s(dir=%u, %lu \"%.*s\")\n",
+ pr_debug("%s(dir=%u, %lu \"%pd\")\n",
__func__, (u32)dir->i_ino, dentry->d_inode->i_ino,
- (int)dentry->d_name.len, dentry->d_name.name);
+ dentry);
return affs_remove_header(dentry);
}
@@ -338,9 +334,8 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
int i, maxlen, error;
char c, lc;
- pr_debug("%s(%lu,\"%.*s\" -> \"%s\")\n",
- __func__, dir->i_ino, (int)dentry->d_name.len,
- dentry->d_name.name, symname);
+ pr_debug("%s(%lu,\"%pd\" -> \"%s\")\n",
+ __func__, dir->i_ino, dentry, symname);
maxlen = AFFS_SB(sb)->s_hashsize * sizeof(u32) - 1;
inode = affs_new_inode(dir);
@@ -409,9 +404,9 @@ affs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
- pr_debug("%s(%u, %u, \"%.*s\")\n",
+ pr_debug("%s(%u, %u, \"%pd\")\n",
__func__, (u32)inode->i_ino, (u32)dir->i_ino,
- (int)dentry->d_name.len,dentry->d_name.name);
+ dentry);
return affs_add_entry(dir, inode, dentry, ST_LINKFILE);
}
@@ -424,10 +419,9 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct buffer_head *bh = NULL;
int retval;
- 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);
+ pr_debug("%s(old=%u,\"%pd\" to new=%u,\"%pd\")\n",
+ __func__, (u32)old_dir->i_ino, old_dentry,
+ (u32)new_dir->i_ino, new_dentry);
retval = affs_check_name(new_dentry->d_name.name,
new_dentry->d_name.len,
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index a1645b88fe8a..4ec35e9130e1 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -26,7 +26,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx);
static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
static int afs_d_delete(const struct dentry *dentry);
static void afs_d_release(struct dentry *dentry);
-static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
+static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen,
loff_t fpos, u64 ino, unsigned dtype);
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool excl);
@@ -391,10 +391,11 @@ static int afs_readdir(struct file *file, struct dir_context *ctx)
* - if afs_dir_iterate_block() spots this function, it'll pass the FID
* uniquifier through dtype
*/
-static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
- loff_t fpos, u64 ino, unsigned dtype)
+static int afs_lookup_filldir(struct dir_context *ctx, const char *name,
+ int nlen, loff_t fpos, u64 ino, unsigned dtype)
{
- struct afs_lookup_cookie *cookie = _cookie;
+ struct afs_lookup_cookie *cookie =
+ container_of(ctx, struct afs_lookup_cookie, ctx);
_enter("{%s,%u},%s,%u,,%llu,%u",
cookie->name.name, cookie->name.len, name, nlen,
@@ -433,7 +434,7 @@ static int afs_do_lookup(struct inode *dir, struct dentry *dentry,
};
int ret;
- _enter("{%lu},%p{%s},", dir->i_ino, dentry, dentry->d_name.name);
+ _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);
/* search the directory */
ret = afs_dir_iterate(dir, &cookie.ctx, key);
@@ -465,8 +466,8 @@ static struct inode *afs_try_auto_mntpt(
struct afs_vnode *vnode = AFS_FS_I(dir);
struct inode *inode;
- _enter("%d, %p{%s}, {%x:%u}, %p",
- ret, dentry, devname, vnode->fid.vid, vnode->fid.vnode, key);
+ _enter("%d, %p{%pd}, {%x:%u}, %p",
+ ret, dentry, dentry, vnode->fid.vid, vnode->fid.vnode, key);
if (ret != -ENOENT ||
!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))
@@ -501,8 +502,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
vnode = AFS_FS_I(dir);
- _enter("{%x:%u},%p{%s},",
- vnode->fid.vid, vnode->fid.vnode, dentry, dentry->d_name.name);
+ _enter("{%x:%u},%p{%pd},",
+ vnode->fid.vid, vnode->fid.vnode, dentry, dentry);
ASSERTCMP(dentry->d_inode, ==, NULL);
@@ -588,11 +589,11 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
vnode = AFS_FS_I(dentry->d_inode);
if (dentry->d_inode)
- _enter("{v={%x:%u} n=%s fl=%lx},",
- vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
+ _enter("{v={%x:%u} n=%pd fl=%lx},",
+ vnode->fid.vid, vnode->fid.vnode, dentry,
vnode->flags);
else
- _enter("{neg n=%s}", dentry->d_name.name);
+ _enter("{neg n=%pd}", dentry);
key = afs_request_key(AFS_FS_S(dentry->d_sb)->volume->cell);
if (IS_ERR(key))
@@ -607,7 +608,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
afs_validate(dir, key);
if (test_bit(AFS_VNODE_DELETED, &dir->flags)) {
- _debug("%s: parent dir deleted", dentry->d_name.name);
+ _debug("%pd: parent dir deleted", dentry);
goto out_bad;
}
@@ -625,16 +626,16 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
if (!dentry->d_inode)
goto out_bad;
if (is_bad_inode(dentry->d_inode)) {
- printk("kAFS: afs_d_revalidate: %s/%s has bad inode\n",
- parent->d_name.name, dentry->d_name.name);
+ printk("kAFS: afs_d_revalidate: %pd2 has bad inode\n",
+ dentry);
goto out_bad;
}
/* if the vnode ID has changed, then the dirent points to a
* different file */
if (fid.vnode != vnode->fid.vnode) {
- _debug("%s: dirent changed [%u != %u]",
- dentry->d_name.name, fid.vnode,
+ _debug("%pd: dirent changed [%u != %u]",
+ dentry, fid.vnode,
vnode->fid.vnode);
goto not_found;
}
@@ -643,8 +644,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
* been deleted and replaced, and the original vnode ID has
* been reused */
if (fid.unique != vnode->fid.unique) {
- _debug("%s: file deleted (uq %u -> %u I:%u)",
- dentry->d_name.name, fid.unique,
+ _debug("%pd: file deleted (uq %u -> %u I:%u)",
+ dentry, fid.unique,
vnode->fid.unique,
dentry->d_inode->i_generation);
spin_lock(&vnode->lock);
@@ -656,14 +657,14 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
case -ENOENT:
/* the filename is unknown */
- _debug("%s: dirent not found", dentry->d_name.name);
+ _debug("%pd: dirent not found", dentry);
if (dentry->d_inode)
goto not_found;
goto out_valid;
default:
- _debug("failed to iterate dir %s: %d",
- parent->d_name.name, ret);
+ _debug("failed to iterate dir %pd: %d",
+ parent, ret);
goto out_bad;
}
@@ -681,8 +682,7 @@ not_found:
spin_unlock(&dentry->d_lock);
out_bad:
- _debug("dropping dentry %s/%s",
- parent->d_name.name, dentry->d_name.name);
+ _debug("dropping dentry %pd2", dentry);
dput(parent);
key_put(key);
@@ -698,7 +698,7 @@ out_bad:
*/
static int afs_d_delete(const struct dentry *dentry)
{
- _enter("%s", dentry->d_name.name);
+ _enter("%pd", dentry);
if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
goto zap;
@@ -721,7 +721,7 @@ zap:
*/
static void afs_d_release(struct dentry *dentry)
{
- _enter("%s", dentry->d_name.name);
+ _enter("%pd", dentry);
}
/*
@@ -740,8 +740,8 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
dvnode = AFS_FS_I(dir);
- _enter("{%x:%u},{%s},%ho",
- dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode);
+ _enter("{%x:%u},{%pd},%ho",
+ dvnode->fid.vid, dvnode->fid.vnode, dentry, mode);
key = afs_request_key(dvnode->volume->cell);
if (IS_ERR(key)) {
@@ -801,8 +801,8 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
dvnode = AFS_FS_I(dir);
- _enter("{%x:%u},{%s}",
- dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
+ _enter("{%x:%u},{%pd}",
+ dvnode->fid.vid, dvnode->fid.vnode, dentry);
key = afs_request_key(dvnode->volume->cell);
if (IS_ERR(key)) {
@@ -843,8 +843,8 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
dvnode = AFS_FS_I(dir);
- _enter("{%x:%u},{%s}",
- dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
+ _enter("{%x:%u},{%pd}",
+ dvnode->fid.vid, dvnode->fid.vnode, dentry);
ret = -ENAMETOOLONG;
if (dentry->d_name.len >= AFSNAMEMAX)
@@ -917,8 +917,8 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
dvnode = AFS_FS_I(dir);
- _enter("{%x:%u},{%s},%ho,",
- dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode);
+ _enter("{%x:%u},{%pd},%ho,",
+ dvnode->fid.vid, dvnode->fid.vnode, dentry, mode);
key = afs_request_key(dvnode->volume->cell);
if (IS_ERR(key)) {
@@ -980,10 +980,10 @@ static int afs_link(struct dentry *from, struct inode *dir,
vnode = AFS_FS_I(from->d_inode);
dvnode = AFS_FS_I(dir);
- _enter("{%x:%u},{%x:%u},{%s}",
+ _enter("{%x:%u},{%x:%u},{%pd}",
vnode->fid.vid, vnode->fid.vnode,
dvnode->fid.vid, dvnode->fid.vnode,
- dentry->d_name.name);
+ dentry);
key = afs_request_key(dvnode->volume->cell);
if (IS_ERR(key)) {
@@ -1025,8 +1025,8 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
dvnode = AFS_FS_I(dir);
- _enter("{%x:%u},{%s},%s",
- dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name,
+ _enter("{%x:%u},{%pd},%s",
+ dvnode->fid.vid, dvnode->fid.vnode, dentry,
content);
ret = -EINVAL;
@@ -1093,11 +1093,11 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
orig_dvnode = AFS_FS_I(old_dir);
new_dvnode = AFS_FS_I(new_dir);
- _enter("{%x:%u},{%x:%u},{%x:%u},{%s}",
+ _enter("{%x:%u},{%x:%u},{%x:%u},{%pd}",
orig_dvnode->fid.vid, orig_dvnode->fid.vnode,
vnode->fid.vid, vnode->fid.vnode,
new_dvnode->fid.vid, new_dvnode->fid.vnode,
- new_dentry->d_name.name);
+ new_dentry);
key = afs_request_key(orig_dvnode->volume->cell);
if (IS_ERR(key)) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 294671288449..8a1d38ef0fc2 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -462,8 +462,8 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
struct key *key;
int ret;
- _enter("{%x:%u},{n=%s},%x",
- vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
+ _enter("{%x:%u},{n=%pd},%x",
+ vnode->fid.vid, vnode->fid.vnode, dentry,
attr->ia_valid);
if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 9682c33d5daf..938c5ab06d5a 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -106,14 +106,7 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
- _enter("%p,%p{%p{%s},%s}",
- dir,
- dentry,
- dentry->d_parent,
- dentry->d_parent ?
- dentry->d_parent->d_name.name : (const unsigned char *) "",
- dentry->d_name.name);
-
+ _enter("%p,%p{%pd2}", dir, dentry, dentry);
return ERR_PTR(-EREMOTE);
}
@@ -122,14 +115,7 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir,
*/
static int afs_mntpt_open(struct inode *inode, struct file *file)
{
- _enter("%p,%p{%p{%s},%s}",
- inode, file,
- file->f_path.dentry->d_parent,
- file->f_path.dentry->d_parent ?
- file->f_path.dentry->d_parent->d_name.name :
- (const unsigned char *) "",
- file->f_path.dentry->d_name.name);
-
+ _enter("%p,%p{%pD2}", inode, file, file);
return -EREMOTE;
}
@@ -146,7 +132,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
bool rwpath = false;
int ret;
- _enter("{%s}", mntpt->d_name.name);
+ _enter("{%pd}", mntpt);
BUG_ON(!mntpt->d_inode);
@@ -242,7 +228,7 @@ struct vfsmount *afs_d_automount(struct path *path)
{
struct vfsmount *newmnt;
- _enter("{%s}", path->dentry->d_name.name);
+ _enter("{%pd}", path->dentry);
newmnt = afs_mntpt_do_automount(path->dentry);
if (IS_ERR(newmnt))
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 03a3beb17004..06e14bfb3496 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
_debug("- range %u-%u%s",
offset, to, msg->msg_flags ? " [more]" : "");
- msg->msg_iov = (struct iovec *) iov;
- msg->msg_iovlen = 1;
+ iov_iter_init(&msg->msg_iter, WRITE,
+ (struct iovec *) iov, 1, to - offset);
/* have to change the state *before* sending the last
* packet as RxRPC might give us the reply before it
@@ -384,8 +384,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
msg.msg_name = NULL;
msg.msg_namelen = 0;
- msg.msg_iov = (struct iovec *) iov;
- msg.msg_iovlen = 1;
+ iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1,
+ call->request_size);
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = (call->send_pages ? MSG_MORE : 0);
@@ -778,8 +778,7 @@ void afs_send_empty_reply(struct afs_call *call)
iov[0].iov_len = 0;
msg.msg_name = NULL;
msg.msg_namelen = 0;
- msg.msg_iov = iov;
- msg.msg_iovlen = 0;
+ iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0); /* WTF? */
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
@@ -815,8 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
iov[0].iov_len = len;
msg.msg_name = NULL;
msg.msg_namelen = 0;
- msg.msg_iov = iov;
- msg.msg_iovlen = 1;
+ iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len);
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index ab6adfd52516..c13cb08964ed 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -682,14 +682,13 @@ int afs_writeback_all(struct afs_vnode *vnode)
*/
int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
- struct dentry *dentry = file->f_path.dentry;
- struct inode *inode = file->f_mapping->host;
+ struct inode *inode = file_inode(file);
struct afs_writeback *wb, *xwb;
- struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(inode);
int ret;
- _enter("{%x:%u},{n=%s},%d",
- vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
+ _enter("{%x:%u},{n=%pD},%d",
+ vnode->fid.vid, vnode->fid.vnode, file,
datasync);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
diff --git a/fs/aio.c b/fs/aio.c
index 84a751005f5b..1b7893ecc296 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -165,6 +165,15 @@ static struct vfsmount *aio_mnt;
static const struct file_operations aio_ring_fops;
static const struct address_space_operations aio_ctx_aops;
+/* Backing dev info for aio fs.
+ * -no dirty page accounting or writeback happens
+ */
+static struct backing_dev_info aio_fs_backing_dev_info = {
+ .name = "aiofs",
+ .state = 0,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
+};
+
static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
{
struct qstr this = QSTR_INIT("[aio]", 5);
@@ -176,6 +185,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
inode->i_mapping->a_ops = &aio_ctx_aops;
inode->i_mapping->private_data = ctx;
+ inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
inode->i_size = PAGE_SIZE * nr_pages;
path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -220,6 +230,9 @@ static int __init aio_setup(void)
if (IS_ERR(aio_mnt))
panic("Failed to create aio fs mount.");
+ if (bdi_init(&aio_fs_backing_dev_info))
+ panic("Failed to init aio fs backing dev info.");
+
kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
@@ -273,19 +286,39 @@ static void aio_free_ring(struct kioctx *ctx)
static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
{
+ vma->vm_flags |= VM_DONTEXPAND;
vma->vm_ops = &generic_file_vm_ops;
return 0;
}
+static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ struct kioctx_table *table;
+ int i;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+ for (i = 0; i < table->nr; i++) {
+ struct kioctx *ctx;
+
+ ctx = table->table[i];
+ if (ctx && ctx->aio_ring_file == file) {
+ ctx->user_id = ctx->mmap_base = vma->vm_start;
+ break;
+ }
+ }
+
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+}
+
static const struct file_operations aio_ring_fops = {
.mmap = aio_ring_mmap,
+ .mremap = aio_ring_remap,
};
-static int aio_set_page_dirty(struct page *page)
-{
- return 0;
-}
-
#if IS_ENABLED(CONFIG_MIGRATION)
static int aio_migratepage(struct address_space *mapping, struct page *new,
struct page *old, enum migrate_mode mode)
@@ -357,7 +390,7 @@ out:
#endif
static const struct address_space_operations aio_ctx_aops = {
- .set_page_dirty = aio_set_page_dirty,
+ .set_page_dirty = __set_page_dirty_no_writeback,
#if IS_ENABLED(CONFIG_MIGRATION)
.migratepage = aio_migratepage,
#endif
@@ -412,7 +445,6 @@ static int aio_setup_ring(struct kioctx *ctx)
pr_debug("pid(%d) page[%d]->count=%d\n",
current->pid, i, page_count(page));
SetPageUptodate(page);
- SetPageDirty(page);
unlock_page(page);
ctx->ring_pages[i] = page;
@@ -1221,8 +1253,12 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
* the ringbuffer empty. So in practice we should be ok, but it's
* something to be aware of when touching this code.
*/
- wait_event_interruptible_hrtimeout(ctx->wait,
- aio_read_events(ctx, min_nr, nr, event, &ret), until);
+ if (until.tv64 == 0)
+ aio_read_events(ctx, min_nr, nr, event, &ret);
+ else
+ wait_event_interruptible_hrtimeout(ctx->wait,
+ aio_read_events(ctx, min_nr, nr, event, &ret),
+ until);
if (!ret && signal_pending(current))
ret = -EINTR;
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 683a5b9ce22a..bfdbaba9c2ba 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -41,8 +41,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
struct path path = {.mnt = mnt, .dentry = dentry};
int status = 1;
- DPRINTK("dentry %p %.*s",
- dentry, (int)dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("dentry %p %pd", dentry, dentry);
path_get(&path);
@@ -85,7 +84,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev,
spin_lock(&root->d_lock);
if (prev)
- next = prev->d_u.d_child.next;
+ next = prev->d_child.next;
else {
prev = dget_dlock(root);
next = prev->d_subdirs.next;
@@ -99,13 +98,13 @@ cont:
return NULL;
}
- q = list_entry(next, struct dentry, d_u.d_child);
+ q = list_entry(next, struct dentry, d_child);
spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
/* Already gone or negative dentry (under construction) - try next */
if (!d_count(q) || !simple_positive(q)) {
spin_unlock(&q->d_lock);
- next = q->d_u.d_child.next;
+ next = q->d_child.next;
goto cont;
}
dget_dlock(q);
@@ -155,13 +154,13 @@ again:
goto relock;
}
spin_unlock(&p->d_lock);
- next = p->d_u.d_child.next;
+ next = p->d_child.next;
p = parent;
if (next != &parent->d_subdirs)
break;
}
}
- ret = list_entry(next, struct dentry, d_u.d_child);
+ ret = list_entry(next, struct dentry, d_child);
spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED);
/* Negative dentry - try next */
@@ -192,8 +191,7 @@ static int autofs4_direct_busy(struct vfsmount *mnt,
unsigned long timeout,
int do_now)
{
- DPRINTK("top %p %.*s",
- top, (int) top->d_name.len, top->d_name.name);
+ DPRINTK("top %p %pd", top, top);
/* If it's busy update the expiry counters */
if (!may_umount_tree(mnt)) {
@@ -221,8 +219,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
struct autofs_info *top_ino = autofs4_dentry_ino(top);
struct dentry *p;
- DPRINTK("top %p %.*s",
- top, (int)top->d_name.len, top->d_name.name);
+ DPRINTK("top %p %pd", top, top);
/* Negative dentry - give up */
if (!simple_positive(top))
@@ -230,8 +227,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
p = NULL;
while ((p = get_next_positive_dentry(p, top))) {
- DPRINTK("dentry %p %.*s",
- p, (int) p->d_name.len, p->d_name.name);
+ DPRINTK("dentry %p %pd", p, p);
/*
* Is someone visiting anywhere in the subtree ?
@@ -277,13 +273,11 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt,
{
struct dentry *p;
- DPRINTK("parent %p %.*s",
- parent, (int)parent->d_name.len, parent->d_name.name);
+ DPRINTK("parent %p %pd", parent, parent);
p = NULL;
while ((p = get_next_positive_dentry(p, parent))) {
- DPRINTK("dentry %p %.*s",
- p, (int) p->d_name.len, p->d_name.name);
+ DPRINTK("dentry %p %pd", p, p);
if (d_mountpoint(p)) {
/* Can we umount this guy */
@@ -368,8 +362,7 @@ static struct dentry *should_expire(struct dentry *dentry,
* offset (autofs-5.0+).
*/
if (d_mountpoint(dentry)) {
- DPRINTK("checking mountpoint %p %.*s",
- dentry, (int)dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("checking mountpoint %p %pd", dentry, dentry);
/* Can we umount this guy */
if (autofs4_mount_busy(mnt, dentry))
@@ -382,8 +375,7 @@ static struct dentry *should_expire(struct dentry *dentry,
}
if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) {
- DPRINTK("checking symlink %p %.*s",
- dentry, (int)dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("checking symlink %p %pd", dentry, dentry);
/*
* A symlink can't be "busy" in the usual sense so
* just check last used for expire timeout.
@@ -479,8 +471,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
return NULL;
found:
- DPRINTK("returning %p %.*s",
- expired, (int)expired->d_name.len, expired->d_name.name);
+ DPRINTK("returning %p %pd", expired, expired);
ino->flags |= AUTOFS_INF_EXPIRING;
smp_mb();
ino->flags &= ~AUTOFS_INF_NO_RCU;
@@ -489,7 +480,7 @@ found:
spin_lock(&sbi->lookup_lock);
spin_lock(&expired->d_parent->d_lock);
spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
+ list_move(&expired->d_parent->d_subdirs, &expired->d_child);
spin_unlock(&expired->d_lock);
spin_unlock(&expired->d_parent->d_lock);
spin_unlock(&sbi->lookup_lock);
@@ -512,8 +503,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
if (ino->flags & AUTOFS_INF_EXPIRING) {
spin_unlock(&sbi->fs_lock);
- DPRINTK("waiting for expire %p name=%.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("waiting for expire %p name=%pd", dentry, dentry);
status = autofs4_wait(sbi, dentry, NFY_NONE);
wait_for_completion(&ino->expire_complete);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index d76d083f2f06..dbb5b7212ce1 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -108,8 +108,7 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
struct dentry *dentry = file->f_path.dentry;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
- DPRINTK("file=%p dentry=%p %.*s",
- file, dentry, dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("file=%p dentry=%p %pD", file, dentry, dentry);
if (autofs4_oz_mode(sbi))
goto out;
@@ -279,8 +278,7 @@ static int autofs4_mount_wait(struct dentry *dentry, bool rcu_walk)
if (ino->flags & AUTOFS_INF_PENDING) {
if (rcu_walk)
return -ECHILD;
- DPRINTK("waiting for mount name=%.*s",
- dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("waiting for mount name=%pd", dentry);
status = autofs4_wait(sbi, dentry, NFY_MOUNT);
DPRINTK("mount wait done status=%d", status);
}
@@ -340,8 +338,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status;
- DPRINTK("dentry=%p %.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("dentry=%p %pd", dentry, dentry);
/* The daemon never triggers a mount. */
if (autofs4_oz_mode(sbi))
@@ -428,8 +425,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status;
- DPRINTK("dentry=%p %.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("dentry=%p %pd", dentry, dentry);
/* The daemon never waits. */
if (autofs4_oz_mode(sbi)) {
@@ -504,7 +500,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
struct autofs_info *ino;
struct dentry *active;
- DPRINTK("name = %.*s", dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("name = %pd", dentry);
/* File name too long to exist */
if (dentry->d_name.len > NAME_MAX)
@@ -558,8 +554,7 @@ static int autofs4_dir_symlink(struct inode *dir,
size_t size = strlen(symname);
char *cp;
- DPRINTK("%s <- %.*s", symname,
- dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("%s <- %pd", symname, dentry);
if (!autofs4_oz_mode(sbi))
return -EACCES;
@@ -687,7 +682,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
/* only consider parents below dentrys in the root */
if (IS_ROOT(parent->d_parent))
return;
- d_child = &dentry->d_u.d_child;
+ d_child = &dentry->d_child;
/* Set parent managed if it's becoming empty */
if (d_child->next == &parent->d_subdirs &&
d_child->prev == &parent->d_subdirs)
@@ -701,8 +696,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
struct autofs_info *ino = autofs4_dentry_ino(dentry);
struct autofs_info *p_ino;
- DPRINTK("dentry %p, removing %.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("dentry %p, removing %pd", dentry, dentry);
if (!autofs4_oz_mode(sbi))
return -EACCES;
@@ -744,8 +738,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
if (!autofs4_oz_mode(sbi))
return -EACCES;
- DPRINTK("dentry %p, creating %.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
+ DPRINTK("dentry %p, creating %pd", dentry, dentry);
BUG_ON(!ino);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 4cf61ec6b7a8..edf47774b03d 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -172,8 +172,8 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
char *utfname;
const char *name = dentry->d_name.name;
- befs_debug(sb, "---> %s name %s inode %ld", __func__,
- dentry->d_name.name, dir->i_ino);
+ befs_debug(sb, "---> %s name %pd inode %ld", __func__,
+ dentry, dir->i_ino);
/* Convert to UTF-8 */
if (BEFS_SB(sb)->nls) {
@@ -191,8 +191,7 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
}
if (ret == BEFS_BT_NOT_FOUND) {
- befs_debug(sb, "<--- %s %s not found", __func__,
- dentry->d_name.name);
+ befs_debug(sb, "<--- %s %pd not found", __func__, dentry);
return ERR_PTR(-ENOENT);
} else if (ret != BEFS_OK || offset == 0) {
@@ -222,10 +221,9 @@ befs_readdir(struct file *file, struct dir_context *ctx)
size_t keysize;
unsigned char d_type;
char keybuf[BEFS_NAME_LEN + 1];
- const char *dirname = file->f_path.dentry->d_name.name;
- befs_debug(sb, "---> %s name %s, inode %ld, ctx->pos %lld",
- __func__, dirname, inode->i_ino, ctx->pos);
+ befs_debug(sb, "---> %s name %pD, inode %ld, ctx->pos %lld",
+ __func__, file, inode->i_ino, ctx->pos);
more:
result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1,
@@ -233,8 +231,8 @@ more:
if (result == BEFS_ERR) {
befs_debug(sb, "<--- %s ERROR", __func__);
- befs_error(sb, "IO error reading %s (inode %lu)",
- dirname, inode->i_ino);
+ befs_error(sb, "IO error reading %pD (inode %lu)",
+ file, inode->i_ino);
return -EIO;
} else if (result == BEFS_BT_END) {
@@ -271,10 +269,6 @@ more:
}
ctx->pos++;
goto more;
-
- befs_debug(sb, "<--- %s pos %lld", __func__, ctx->pos);
-
- return 0;
}
static struct inode *
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 929dec08c348..4c556680fa74 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -292,8 +292,8 @@ static int load_aout_binary(struct linux_binprm * bprm)
if ((fd_offset & ~PAGE_MASK) != 0 && printk_ratelimit())
{
printk(KERN_WARNING
- "fd_offset is not page aligned. Please convert program: %s\n",
- bprm->file->f_path.dentry->d_name.name);
+ "fd_offset is not page aligned. Please convert program: %pD\n",
+ bprm->file);
}
if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
@@ -375,8 +375,8 @@ static int load_aout_library(struct file *file)
if (printk_ratelimit())
{
printk(KERN_WARNING
- "N_TXTOFF is not page aligned. Please convert library: %s\n",
- file->f_path.dentry->d_name.name);
+ "N_TXTOFF is not page aligned. Please convert library: %pD\n",
+ file);
}
vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d8fc0605b9d2..02b16910f4c9 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -386,6 +386,127 @@ static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
ELF_PAGESTART(cmds[first_idx].p_vaddr);
}
+/**
+ * load_elf_phdrs() - load ELF program headers
+ * @elf_ex: ELF header of the binary whose program headers should be loaded
+ * @elf_file: the opened ELF binary file
+ *
+ * Loads ELF program headers from the binary file elf_file, which has the ELF
+ * header pointed to by elf_ex, into a newly allocated array. The caller is
+ * responsible for freeing the allocated data. Returns an ERR_PTR upon failure.
+ */
+static struct elf_phdr *load_elf_phdrs(struct elfhdr *elf_ex,
+ struct file *elf_file)
+{
+ struct elf_phdr *elf_phdata = NULL;
+ int retval, size, err = -1;
+
+ /*
+ * If the size of this structure has changed, then punt, since
+ * we will be doing the wrong thing.
+ */
+ if (elf_ex->e_phentsize != sizeof(struct elf_phdr))
+ goto out;
+
+ /* Sanity check the number of program headers... */
+ if (elf_ex->e_phnum < 1 ||
+ elf_ex->e_phnum > 65536U / sizeof(struct elf_phdr))
+ goto out;
+
+ /* ...and their total size. */
+ size = sizeof(struct elf_phdr) * elf_ex->e_phnum;
+ if (size > ELF_MIN_ALIGN)
+ goto out;
+
+ elf_phdata = kmalloc(size, GFP_KERNEL);
+ if (!elf_phdata)
+ goto out;
+
+ /* Read in the program headers */
+ retval = kernel_read(elf_file, elf_ex->e_phoff,
+ (char *)elf_phdata, size);
+ if (retval != size) {
+ err = (retval < 0) ? retval : -EIO;
+ goto out;
+ }
+
+ /* Success! */
+ err = 0;
+out:
+ if (err) {
+ kfree(elf_phdata);
+ elf_phdata = NULL;
+ }
+ return elf_phdata;
+}
+
+#ifndef CONFIG_ARCH_BINFMT_ELF_STATE
+
+/**
+ * struct arch_elf_state - arch-specific ELF loading state
+ *
+ * This structure is used to preserve architecture specific data during
+ * the loading of an ELF file, throughout the checking of architecture
+ * specific ELF headers & through to the point where the ELF load is
+ * known to be proceeding (ie. SET_PERSONALITY).
+ *
+ * This implementation is a dummy for architectures which require no
+ * specific state.
+ */
+struct arch_elf_state {
+};
+
+#define INIT_ARCH_ELF_STATE {}
+
+/**
+ * arch_elf_pt_proc() - check a PT_LOPROC..PT_HIPROC ELF program header
+ * @ehdr: The main ELF header
+ * @phdr: The program header to check
+ * @elf: The open ELF file
+ * @is_interp: True if the phdr is from the interpreter of the ELF being
+ * loaded, else false.
+ * @state: Architecture-specific state preserved throughout the process
+ * of loading the ELF.
+ *
+ * Inspects the program header phdr to validate its correctness and/or
+ * suitability for the system. Called once per ELF program header in the
+ * range PT_LOPROC to PT_HIPROC, for both the ELF being loaded and its
+ * interpreter.
+ *
+ * Return: Zero to proceed with the ELF load, non-zero to fail the ELF load
+ * with that return code.
+ */
+static inline int arch_elf_pt_proc(struct elfhdr *ehdr,
+ struct elf_phdr *phdr,
+ struct file *elf, bool is_interp,
+ struct arch_elf_state *state)
+{
+ /* Dummy implementation, always proceed */
+ return 0;
+}
+
+/**
+ * arch_check_elf() - check a PT_LOPROC..PT_HIPROC ELF program header
+ * @ehdr: The main ELF header
+ * @has_interp: True if the ELF has an interpreter, else false.
+ * @state: Architecture-specific state preserved throughout the process
+ * of loading the ELF.
+ *
+ * Provides a final opportunity for architecture code to reject the loading
+ * of the ELF & cause an exec syscall to return an error. This is called after
+ * all program headers to be checked by arch_elf_pt_proc have been.
+ *
+ * Return: Zero to proceed with the ELF load, non-zero to fail the ELF load
+ * with that return code.
+ */
+static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp,
+ struct arch_elf_state *state)
+{
+ /* Dummy implementation, always proceed */
+ return 0;
+}
+
+#endif /* !CONFIG_ARCH_BINFMT_ELF_STATE */
/* This is much more generalized than the library routine read function,
so we keep this separate. Technically the library read function
@@ -394,16 +515,15 @@ static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
struct file *interpreter, unsigned long *interp_map_addr,
- unsigned long no_base)
+ unsigned long no_base, struct elf_phdr *interp_elf_phdata)
{
- struct elf_phdr *elf_phdata;
struct elf_phdr *eppnt;
unsigned long load_addr = 0;
int load_addr_set = 0;
unsigned long last_bss = 0, elf_bss = 0;
unsigned long error = ~0UL;
unsigned long total_size;
- int retval, i, size;
+ int i;
/* First of all, some simple consistency checks */
if (interp_elf_ex->e_type != ET_EXEC &&
@@ -414,40 +534,14 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
if (!interpreter->f_op->mmap)
goto out;
- /*
- * If the size of this structure has changed, then punt, since
- * we will be doing the wrong thing.
- */
- if (interp_elf_ex->e_phentsize != sizeof(struct elf_phdr))
- goto out;
- if (interp_elf_ex->e_phnum < 1 ||
- interp_elf_ex->e_phnum > 65536U / sizeof(struct elf_phdr))
- goto out;
-
- /* Now read in all of the header information */
- size = sizeof(struct elf_phdr) * interp_elf_ex->e_phnum;
- if (size > ELF_MIN_ALIGN)
- goto out;
- elf_phdata = kmalloc(size, GFP_KERNEL);
- if (!elf_phdata)
- goto out;
-
- retval = kernel_read(interpreter, interp_elf_ex->e_phoff,
- (char *)elf_phdata, size);
- error = -EIO;
- if (retval != size) {
- if (retval < 0)
- error = retval;
- goto out_close;
- }
-
- total_size = total_mapping_size(elf_phdata, interp_elf_ex->e_phnum);
+ total_size = total_mapping_size(interp_elf_phdata,
+ interp_elf_ex->e_phnum);
if (!total_size) {
error = -EINVAL;
- goto out_close;
+ goto out;
}
- eppnt = elf_phdata;
+ eppnt = interp_elf_phdata;
for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
if (eppnt->p_type == PT_LOAD) {
int elf_type = MAP_PRIVATE | MAP_DENYWRITE;
@@ -474,7 +568,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
*interp_map_addr = map_addr;
error = map_addr;
if (BAD_ADDR(map_addr))
- goto out_close;
+ goto out;
if (!load_addr_set &&
interp_elf_ex->e_type == ET_DYN) {
@@ -493,7 +587,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
eppnt->p_memsz > TASK_SIZE ||
TASK_SIZE - eppnt->p_memsz < k) {
error = -ENOMEM;
- goto out_close;
+ goto out;
}
/*
@@ -523,7 +617,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
*/
if (padzero(elf_bss)) {
error = -EFAULT;
- goto out_close;
+ goto out;
}
/* What we have mapped so far */
@@ -532,13 +626,10 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
/* Map the last of the bss segment */
error = vm_brk(elf_bss, last_bss - elf_bss);
if (BAD_ADDR(error))
- goto out_close;
+ goto out;
}
error = load_addr;
-
-out_close:
- kfree(elf_phdata);
out:
return error;
}
@@ -575,10 +666,9 @@ static int load_elf_binary(struct linux_binprm *bprm)
int load_addr_set = 0;
char * elf_interpreter = NULL;
unsigned long error;
- struct elf_phdr *elf_ppnt, *elf_phdata;
+ struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
unsigned long elf_bss, elf_brk;
int retval, i;
- unsigned int size;
unsigned long elf_entry;
unsigned long interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
@@ -589,6 +679,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
} *loc;
+ struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE;
loc = kmalloc(sizeof(*loc), GFP_KERNEL);
if (!loc) {
@@ -611,26 +702,10 @@ static int load_elf_binary(struct linux_binprm *bprm)
if (!bprm->file->f_op->mmap)
goto out;
- /* Now read in all of the header information */
- if (loc->elf_ex.e_phentsize != sizeof(struct elf_phdr))
- goto out;
- if (loc->elf_ex.e_phnum < 1 ||
- loc->elf_ex.e_phnum > 65536U / sizeof(struct elf_phdr))
- goto out;
- size = loc->elf_ex.e_phnum * sizeof(struct elf_phdr);
- retval = -ENOMEM;
- elf_phdata = kmalloc(size, GFP_KERNEL);
+ elf_phdata = load_elf_phdrs(&loc->elf_ex, bprm->file);
if (!elf_phdata)
goto out;
- retval = kernel_read(bprm->file, loc->elf_ex.e_phoff,
- (char *)elf_phdata, size);
- if (retval != size) {
- if (retval >= 0)
- retval = -EIO;
- goto out_free_ph;
- }
-
elf_ppnt = elf_phdata;
elf_bss = 0;
elf_brk = 0;
@@ -699,12 +774,21 @@ static int load_elf_binary(struct linux_binprm *bprm)
elf_ppnt = elf_phdata;
for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
- if (elf_ppnt->p_type == PT_GNU_STACK) {
+ switch (elf_ppnt->p_type) {
+ case PT_GNU_STACK:
if (elf_ppnt->p_flags & PF_X)
executable_stack = EXSTACK_ENABLE_X;
else
executable_stack = EXSTACK_DISABLE_X;
break;
+
+ case PT_LOPROC ... PT_HIPROC:
+ retval = arch_elf_pt_proc(&loc->elf_ex, elf_ppnt,
+ bprm->file, false,
+ &arch_state);
+ if (retval)
+ goto out_free_dentry;
+ break;
}
/* Some simple consistency checks for the interpreter */
@@ -716,8 +800,36 @@ static int load_elf_binary(struct linux_binprm *bprm)
/* Verify the interpreter has a valid arch */
if (!elf_check_arch(&loc->interp_elf_ex))
goto out_free_dentry;
+
+ /* Load the interpreter program headers */
+ interp_elf_phdata = load_elf_phdrs(&loc->interp_elf_ex,
+ interpreter);
+ if (!interp_elf_phdata)
+ goto out_free_dentry;
+
+ /* Pass PT_LOPROC..PT_HIPROC headers to arch code */
+ elf_ppnt = interp_elf_phdata;
+ for (i = 0; i < loc->interp_elf_ex.e_phnum; i++, elf_ppnt++)
+ switch (elf_ppnt->p_type) {
+ case PT_LOPROC ... PT_HIPROC:
+ retval = arch_elf_pt_proc(&loc->interp_elf_ex,
+ elf_ppnt, interpreter,
+ true, &arch_state);
+ if (retval)
+ goto out_free_dentry;
+ break;
+ }
}
+ /*
+ * Allow arch code to reject the ELF at this point, whilst it's
+ * still possible to return an error to the code that invoked
+ * the exec syscall.
+ */
+ retval = arch_check_elf(&loc->elf_ex, !!interpreter, &arch_state);
+ if (retval)
+ goto out_free_dentry;
+
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
@@ -725,7 +837,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
- SET_PERSONALITY(loc->elf_ex);
+ SET_PERSONALITY2(loc->elf_ex, &arch_state);
if (elf_read_implies_exec(loc->elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
@@ -890,7 +1002,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
elf_entry = load_elf_interp(&loc->interp_elf_ex,
interpreter,
&interp_map_addr,
- load_bias);
+ load_bias, interp_elf_phdata);
if (!IS_ERR((void *)elf_entry)) {
/*
* load_elf_interp() returns relocation
@@ -917,6 +1029,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
}
}
+ kfree(interp_elf_phdata);
kfree(elf_phdata);
set_binfmt(&elf_format);
@@ -981,6 +1094,7 @@ out_ret:
/* error cleanup */
out_free_dentry:
+ kfree(interp_elf_phdata);
allow_write_access(interpreter);
if (interpreter)
fput(interpreter);
@@ -1994,18 +2108,6 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
shdr4extnum->sh_info = segs;
}
-static size_t elf_core_vma_data_size(struct vm_area_struct *gate_vma,
- unsigned long mm_flags)
-{
- struct vm_area_struct *vma;
- size_t size = 0;
-
- for (vma = first_vma(current, gate_vma); vma != NULL;
- vma = next_vma(vma, gate_vma))
- size += vma_dump_size(vma, mm_flags);
- return size;
-}
-
/*
* Actual dumper
*
@@ -2017,7 +2119,8 @@ static int elf_core_dump(struct coredump_params *cprm)
{
int has_dumped = 0;
mm_segment_t fs;
- int segs;
+ int segs, i;
+ size_t vma_data_size = 0;
struct vm_area_struct *vma, *gate_vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff;
@@ -2026,6 +2129,7 @@ static int elf_core_dump(struct coredump_params *cprm)
struct elf_shdr *shdr4extnum = NULL;
Elf_Half e_phnum;
elf_addr_t e_shoff;
+ elf_addr_t *vma_filesz = NULL;
/*
* We no longer stop all VM operations.
@@ -2093,7 +2197,20 @@ static int elf_core_dump(struct coredump_params *cprm)
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
- offset += elf_core_vma_data_size(gate_vma, cprm->mm_flags);
+ vma_filesz = kmalloc_array(segs - 1, sizeof(*vma_filesz), GFP_KERNEL);
+ if (!vma_filesz)
+ goto end_coredump;
+
+ for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
+ vma = next_vma(vma, gate_vma)) {
+ unsigned long dump_size;
+
+ dump_size = vma_dump_size(vma, cprm->mm_flags);
+ vma_filesz[i++] = dump_size;
+ vma_data_size += dump_size;
+ }
+
+ offset += vma_data_size;
offset += elf_core_extra_data_size();
e_shoff = offset;
@@ -2113,7 +2230,7 @@ static int elf_core_dump(struct coredump_params *cprm)
goto end_coredump;
/* Write program headers for segments dump */
- for (vma = first_vma(current, gate_vma); vma != NULL;
+ for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
struct elf_phdr phdr;
@@ -2121,7 +2238,7 @@ static int elf_core_dump(struct coredump_params *cprm)
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
- phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
+ phdr.p_filesz = vma_filesz[i++];
phdr.p_memsz = vma->vm_end - vma->vm_start;
offset += phdr.p_filesz;
phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
@@ -2149,12 +2266,12 @@ static int elf_core_dump(struct coredump_params *cprm)
if (!dump_skip(cprm, dataoff - cprm->written))
goto end_coredump;
- for (vma = first_vma(current, gate_vma); vma != NULL;
+ for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
unsigned long addr;
unsigned long end;
- end = vma->vm_start + vma_dump_size(vma, cprm->mm_flags);
+ end = vma->vm_start + vma_filesz[i++];
for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
struct page *page;
@@ -2187,6 +2304,7 @@ end_coredump:
cleanup:
free_note_info(&info);
kfree(shdr4extnum);
+ kfree(vma_filesz);
kfree(phdr4note);
kfree(elf);
out:
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index f37b08cea1f7..490538536cb4 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -42,6 +42,10 @@ static int load_em86(struct linux_binprm *bprm)
return -ENOEXEC;
}
+ /* Need to be able to load the file after exec */
+ if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+ return -ENOENT;
+
allow_write_access(bprm->file);
fput(bprm->file);
bprm->file = NULL;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index fd8beb9657a2..97aff2879cda 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -1,21 +1,14 @@
/*
- * binfmt_misc.c
+ * binfmt_misc.c
*
- * Copyright (C) 1997 Richard Günther
+ * Copyright (C) 1997 Richard Günther
*
- * binfmt_misc detects binaries via a magic or filename extension and invokes
- * a specified wrapper. This should obsolete binfmt_java, binfmt_em86 and
- * binfmt_mz.
- *
- * 1997-04-25 first version
- * [...]
- * 1997-05-19 cleanup
- * 1997-06-26 hpa: pass the real filename rather than argv[0]
- * 1997-06-30 minor cleanup
- * 1997-08-09 removed extension stripping, locking cleanup
- * 2001-02-28 AV: rewritten into something that resembles C. Original didn't.
+ * binfmt_misc detects binaries via a magic or filename extension and invokes
+ * a specified wrapper. See Documentation/binfmt_misc.txt for more details.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
@@ -30,8 +23,13 @@
#include <linux/mount.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
+#include <linux/uaccess.h>
-#include <asm/uaccess.h>
+#ifdef DEBUG
+# define USE_DEBUG 1
+#else
+# define USE_DEBUG 0
+#endif
enum {
VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */
@@ -41,9 +39,9 @@ static LIST_HEAD(entries);
static int enabled = 1;
enum {Enabled, Magic};
-#define MISC_FMT_PRESERVE_ARGV0 (1<<31)
-#define MISC_FMT_OPEN_BINARY (1<<30)
-#define MISC_FMT_CREDENTIALS (1<<29)
+#define MISC_FMT_PRESERVE_ARGV0 (1 << 31)
+#define MISC_FMT_OPEN_BINARY (1 << 30)
+#define MISC_FMT_CREDENTIALS (1 << 29)
typedef struct {
struct list_head list;
@@ -87,20 +85,24 @@ static Node *check_file(struct linux_binprm *bprm)
char *p = strrchr(bprm->interp, '.');
struct list_head *l;
+ /* Walk all the registered handlers. */
list_for_each(l, &entries) {
Node *e = list_entry(l, Node, list);
char *s;
int j;
+ /* Make sure this one is currently enabled. */
if (!test_bit(Enabled, &e->flags))
continue;
+ /* Do matching based on extension if applicable. */
if (!test_bit(Magic, &e->flags)) {
if (p && !strcmp(e->magic, p + 1))
return e;
continue;
}
+ /* Do matching based on magic & mask. */
s = bprm->buf + e->offset;
if (e->mask) {
for (j = 0; j < e->size; j++)
@@ -123,7 +125,7 @@ static Node *check_file(struct linux_binprm *bprm)
static int load_misc_binary(struct linux_binprm *bprm)
{
Node *fmt;
- struct file * interp_file = NULL;
+ struct file *interp_file = NULL;
char iname[BINPRM_BUF_SIZE];
const char *iname_addr = iname;
int retval;
@@ -131,7 +133,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
retval = -ENOEXEC;
if (!enabled)
- goto _ret;
+ goto ret;
/* to keep locking time low, we copy the interpreter string */
read_lock(&entries_lock);
@@ -140,25 +142,30 @@ static int load_misc_binary(struct linux_binprm *bprm)
strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
read_unlock(&entries_lock);
if (!fmt)
- goto _ret;
+ goto ret;
+
+ /* Need to be able to load the file after exec */
+ if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+ return -ENOENT;
if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
retval = remove_arg_zero(bprm);
if (retval)
- goto _ret;
+ goto ret;
}
if (fmt->flags & MISC_FMT_OPEN_BINARY) {
/* if the binary should be opened on behalf of the
* interpreter than keep it open and assign descriptor
- * to it */
- fd_binary = get_unused_fd();
- if (fd_binary < 0) {
- retval = fd_binary;
- goto _ret;
- }
- fd_install(fd_binary, bprm->file);
+ * to it
+ */
+ fd_binary = get_unused_fd_flags(0);
+ if (fd_binary < 0) {
+ retval = fd_binary;
+ goto ret;
+ }
+ fd_install(fd_binary, bprm->file);
/* if the binary is not readable than enforce mm->dumpable=0
regardless of the interpreter's permissions */
@@ -171,32 +178,32 @@ static int load_misc_binary(struct linux_binprm *bprm)
bprm->interp_flags |= BINPRM_FLAGS_EXECFD;
bprm->interp_data = fd_binary;
- } else {
- allow_write_access(bprm->file);
- fput(bprm->file);
- bprm->file = NULL;
- }
+ } else {
+ allow_write_access(bprm->file);
+ fput(bprm->file);
+ bprm->file = NULL;
+ }
/* make argv[1] be the path to the binary */
- retval = copy_strings_kernel (1, &bprm->interp, bprm);
+ retval = copy_strings_kernel(1, &bprm->interp, bprm);
if (retval < 0)
- goto _error;
+ goto error;
bprm->argc++;
/* add the interp as argv[0] */
- retval = copy_strings_kernel (1, &iname_addr, bprm);
+ retval = copy_strings_kernel(1, &iname_addr, bprm);
if (retval < 0)
- goto _error;
- bprm->argc ++;
+ goto error;
+ bprm->argc++;
/* Update interp in case binfmt_script needs it. */
retval = bprm_change_interp(iname, bprm);
if (retval < 0)
- goto _error;
+ goto error;
- interp_file = open_exec (iname);
- retval = PTR_ERR (interp_file);
- if (IS_ERR (interp_file))
- goto _error;
+ interp_file = open_exec(iname);
+ retval = PTR_ERR(interp_file);
+ if (IS_ERR(interp_file))
+ goto error;
bprm->file = interp_file;
if (fmt->flags & MISC_FMT_CREDENTIALS) {
@@ -207,23 +214,23 @@ static int load_misc_binary(struct linux_binprm *bprm)
memset(bprm->buf, 0, BINPRM_BUF_SIZE);
retval = kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
} else
- retval = prepare_binprm (bprm);
+ retval = prepare_binprm(bprm);
if (retval < 0)
- goto _error;
+ goto error;
retval = search_binary_handler(bprm);
if (retval < 0)
- goto _error;
+ goto error;
-_ret:
+ret:
return retval;
-_error:
+error:
if (fd_binary > 0)
sys_close(fd_binary);
bprm->interp_flags = 0;
bprm->interp_data = 0;
- goto _ret;
+ goto ret;
}
/* Command parsers */
@@ -247,39 +254,44 @@ static char *scanarg(char *s, char del)
return NULL;
}
}
+ s[-1] ='\0';
return s;
}
-static char * check_special_flags (char * sfs, Node * e)
+static char *check_special_flags(char *sfs, Node *e)
{
- char * p = sfs;
+ char *p = sfs;
int cont = 1;
/* special flags */
while (cont) {
switch (*p) {
- case 'P':
- p++;
- e->flags |= MISC_FMT_PRESERVE_ARGV0;
- break;
- case 'O':
- p++;
- e->flags |= MISC_FMT_OPEN_BINARY;
- break;
- case 'C':
- p++;
- /* this flags also implies the
- open-binary flag */
- e->flags |= (MISC_FMT_CREDENTIALS |
- MISC_FMT_OPEN_BINARY);
- break;
- default:
- cont = 0;
+ case 'P':
+ pr_debug("register: flag: P (preserve argv0)\n");
+ p++;
+ e->flags |= MISC_FMT_PRESERVE_ARGV0;
+ break;
+ case 'O':
+ pr_debug("register: flag: O (open binary)\n");
+ p++;
+ e->flags |= MISC_FMT_OPEN_BINARY;
+ break;
+ case 'C':
+ pr_debug("register: flag: C (preserve creds)\n");
+ p++;
+ /* this flags also implies the
+ open-binary flag */
+ e->flags |= (MISC_FMT_CREDENTIALS |
+ MISC_FMT_OPEN_BINARY);
+ break;
+ default:
+ cont = 0;
}
}
return p;
}
+
/*
* This registers a new binary format, it recognises the syntax
* ':name:type:offset:magic:mask:interpreter:flags'
@@ -292,6 +304,8 @@ static Node *create_entry(const char __user *buffer, size_t count)
char *buf, *p;
char del;
+ pr_debug("register: received %zu bytes\n", count);
+
/* some sanity checks */
err = -EINVAL;
if ((count < 11) || (count > MAX_REGISTER_LENGTH))
@@ -299,7 +313,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
err = -ENOMEM;
memsize = sizeof(Node) + count + 8;
- e = kmalloc(memsize, GFP_USER);
+ e = kmalloc(memsize, GFP_KERNEL);
if (!e)
goto out;
@@ -307,98 +321,173 @@ static Node *create_entry(const char __user *buffer, size_t count)
memset(e, 0, sizeof(Node));
if (copy_from_user(buf, buffer, count))
- goto Efault;
+ goto efault;
del = *p++; /* delimeter */
- memset(buf+count, del, 8);
+ pr_debug("register: delim: %#x {%c}\n", del, del);
+
+ /* Pad the buffer with the delim to simplify parsing below. */
+ memset(buf + count, del, 8);
+ /* Parse the 'name' field. */
e->name = p;
p = strchr(p, del);
if (!p)
- goto Einval;
+ goto einval;
*p++ = '\0';
if (!e->name[0] ||
!strcmp(e->name, ".") ||
!strcmp(e->name, "..") ||
strchr(e->name, '/'))
- goto Einval;
+ goto einval;
+
+ pr_debug("register: name: {%s}\n", e->name);
+
+ /* Parse the 'type' field. */
switch (*p++) {
- case 'E': e->flags = 1<<Enabled; break;
- case 'M': e->flags = (1<<Enabled) | (1<<Magic); break;
- default: goto Einval;
+ case 'E':
+ pr_debug("register: type: E (extension)\n");
+ e->flags = 1 << Enabled;
+ break;
+ case 'M':
+ pr_debug("register: type: M (magic)\n");
+ e->flags = (1 << Enabled) | (1 << Magic);
+ break;
+ default:
+ goto einval;
}
if (*p++ != del)
- goto Einval;
+ goto einval;
+
if (test_bit(Magic, &e->flags)) {
- char *s = strchr(p, del);
+ /* Handle the 'M' (magic) format. */
+ char *s;
+
+ /* Parse the 'offset' field. */
+ s = strchr(p, del);
if (!s)
- goto Einval;
+ goto einval;
*s++ = '\0';
e->offset = simple_strtoul(p, &p, 10);
if (*p++)
- goto Einval;
+ goto einval;
+ pr_debug("register: offset: %#x\n", e->offset);
+
+ /* Parse the 'magic' field. */
e->magic = p;
p = scanarg(p, del);
if (!p)
- goto Einval;
- p[-1] = '\0';
+ goto einval;
if (!e->magic[0])
- goto Einval;
+ goto einval;
+ if (USE_DEBUG)
+ print_hex_dump_bytes(
+ KBUILD_MODNAME ": register: magic[raw]: ",
+ DUMP_PREFIX_NONE, e->magic, p - e->magic);
+
+ /* Parse the 'mask' field. */
e->mask = p;
p = scanarg(p, del);
if (!p)
- goto Einval;
- p[-1] = '\0';
- if (!e->mask[0])
+ goto einval;
+ if (!e->mask[0]) {
e->mask = NULL;
+ pr_debug("register: mask[raw]: none\n");
+ } else if (USE_DEBUG)
+ print_hex_dump_bytes(
+ KBUILD_MODNAME ": register: mask[raw]: ",
+ DUMP_PREFIX_NONE, e->mask, p - e->mask);
+
+ /*
+ * Decode the magic & mask fields.
+ * Note: while we might have accepted embedded NUL bytes from
+ * above, the unescape helpers here will stop at the first one
+ * it encounters.
+ */
e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX);
if (e->mask &&
string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
- goto Einval;
+ goto einval;
if (e->size + e->offset > BINPRM_BUF_SIZE)
- goto Einval;
+ goto einval;
+ pr_debug("register: magic/mask length: %i\n", e->size);
+ if (USE_DEBUG) {
+ print_hex_dump_bytes(
+ KBUILD_MODNAME ": register: magic[decoded]: ",
+ DUMP_PREFIX_NONE, e->magic, e->size);
+
+ if (e->mask) {
+ int i;
+ char *masked = kmalloc(e->size, GFP_KERNEL);
+
+ print_hex_dump_bytes(
+ KBUILD_MODNAME ": register: mask[decoded]: ",
+ DUMP_PREFIX_NONE, e->mask, e->size);
+
+ if (masked) {
+ for (i = 0; i < e->size; ++i)
+ masked[i] = e->magic[i] & e->mask[i];
+ print_hex_dump_bytes(
+ KBUILD_MODNAME ": register: magic[masked]: ",
+ DUMP_PREFIX_NONE, masked, e->size);
+
+ kfree(masked);
+ }
+ }
+ }
} else {
+ /* Handle the 'E' (extension) format. */
+
+ /* Skip the 'offset' field. */
p = strchr(p, del);
if (!p)
- goto Einval;
+ goto einval;
*p++ = '\0';
+
+ /* Parse the 'magic' field. */
e->magic = p;
p = strchr(p, del);
if (!p)
- goto Einval;
+ goto einval;
*p++ = '\0';
if (!e->magic[0] || strchr(e->magic, '/'))
- goto Einval;
+ goto einval;
+ pr_debug("register: extension: {%s}\n", e->magic);
+
+ /* Skip the 'mask' field. */
p = strchr(p, del);
if (!p)
- goto Einval;
+ goto einval;
*p++ = '\0';
}
+
+ /* Parse the 'interpreter' field. */
e->interpreter = p;
p = strchr(p, del);
if (!p)
- goto Einval;
+ goto einval;
*p++ = '\0';
if (!e->interpreter[0])
- goto Einval;
-
-
- p = check_special_flags (p, e);
+ goto einval;
+ pr_debug("register: interpreter: {%s}\n", e->interpreter);
+ /* Parse the 'flags' field. */
+ p = check_special_flags(p, e);
if (*p == '\n')
p++;
if (p != buf + count)
- goto Einval;
+ goto einval;
+
return e;
out:
return ERR_PTR(err);
-Efault:
+efault:
kfree(e);
return ERR_PTR(-EFAULT);
-Einval:
+einval:
kfree(e);
return ERR_PTR(-EINVAL);
}
@@ -417,7 +506,7 @@ static int parse_command(const char __user *buffer, size_t count)
return -EFAULT;
if (!count)
return 0;
- if (s[count-1] == '\n')
+ if (s[count - 1] == '\n')
count--;
if (count == 1 && s[0] == '0')
return 1;
@@ -434,7 +523,7 @@ static void entry_status(Node *e, char *page)
{
char *dp;
char *status = "disabled";
- const char * flags = "flags: ";
+ const char *flags = "flags: ";
if (test_bit(Enabled, &e->flags))
status = "enabled";
@@ -448,19 +537,15 @@ static void entry_status(Node *e, char *page)
dp = page + strlen(page);
/* print the special flags */
- sprintf (dp, "%s", flags);
- dp += strlen (flags);
- if (e->flags & MISC_FMT_PRESERVE_ARGV0) {
- *dp ++ = 'P';
- }
- if (e->flags & MISC_FMT_OPEN_BINARY) {
- *dp ++ = 'O';
- }
- if (e->flags & MISC_FMT_CREDENTIALS) {
- *dp ++ = 'C';
- }
- *dp ++ = '\n';
-
+ sprintf(dp, "%s", flags);
+ dp += strlen(flags);
+ if (e->flags & MISC_FMT_PRESERVE_ARGV0)
+ *dp++ = 'P';
+ if (e->flags & MISC_FMT_OPEN_BINARY)
+ *dp++ = 'O';
+ if (e->flags & MISC_FMT_CREDENTIALS)
+ *dp++ = 'C';
+ *dp++ = '\n';
if (!test_bit(Magic, &e->flags)) {
sprintf(dp, "extension .%s\n", e->magic);
@@ -488,7 +573,7 @@ static void entry_status(Node *e, char *page)
static struct inode *bm_get_inode(struct super_block *sb, int mode)
{
- struct inode * inode = new_inode(sb);
+ struct inode *inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
@@ -528,13 +613,14 @@ static void kill_node(Node *e)
/* /<entry> */
static ssize_t
-bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
+bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
Node *e = file_inode(file)->i_private;
ssize_t res;
char *page;
- if (!(page = (char*) __get_free_page(GFP_KERNEL)))
+ page = (char *) __get_free_page(GFP_KERNEL);
+ if (!page)
return -ENOMEM;
entry_status(e, page);
@@ -553,20 +639,28 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
int res = parse_command(buffer, count);
switch (res) {
- case 1: clear_bit(Enabled, &e->flags);
- break;
- case 2: set_bit(Enabled, &e->flags);
- break;
- case 3: root = dget(file->f_path.dentry->d_sb->s_root);
- mutex_lock(&root->d_inode->i_mutex);
-
- kill_node(e);
-
- mutex_unlock(&root->d_inode->i_mutex);
- dput(root);
- break;
- default: return res;
+ case 1:
+ /* Disable this handler. */
+ clear_bit(Enabled, &e->flags);
+ break;
+ case 2:
+ /* Enable this handler. */
+ set_bit(Enabled, &e->flags);
+ break;
+ case 3:
+ /* Delete this handler. */
+ root = dget(file->f_path.dentry->d_sb->s_root);
+ mutex_lock(&root->d_inode->i_mutex);
+
+ kill_node(e);
+
+ mutex_unlock(&root->d_inode->i_mutex);
+ dput(root);
+ break;
+ default:
+ return res;
}
+
return count;
}
@@ -654,26 +748,36 @@ bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
}
-static ssize_t bm_status_write(struct file * file, const char __user * buffer,
+static ssize_t bm_status_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
int res = parse_command(buffer, count);
struct dentry *root;
switch (res) {
- case 1: enabled = 0; break;
- case 2: enabled = 1; break;
- case 3: root = dget(file->f_path.dentry->d_sb->s_root);
- mutex_lock(&root->d_inode->i_mutex);
-
- while (!list_empty(&entries))
- kill_node(list_entry(entries.next, Node, list));
-
- mutex_unlock(&root->d_inode->i_mutex);
- dput(root);
- break;
- default: return res;
+ case 1:
+ /* Disable all handlers. */
+ enabled = 0;
+ break;
+ case 2:
+ /* Enable all handlers. */
+ enabled = 1;
+ break;
+ case 3:
+ /* Delete all handlers. */
+ root = dget(file->f_path.dentry->d_sb->s_root);
+ mutex_lock(&root->d_inode->i_mutex);
+
+ while (!list_empty(&entries))
+ kill_node(list_entry(entries.next, Node, list));
+
+ mutex_unlock(&root->d_inode->i_mutex);
+ dput(root);
+ break;
+ default:
+ return res;
}
+
return count;
}
@@ -690,14 +794,16 @@ static const struct super_operations s_ops = {
.evict_inode = bm_evict_inode,
};
-static int bm_fill_super(struct super_block * sb, void * data, int silent)
+static int bm_fill_super(struct super_block *sb, void *data, int silent)
{
+ int err;
static struct tree_descr bm_files[] = {
[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
[3] = {"register", &bm_register_operations, S_IWUSR},
/* last one */ {""}
};
- int err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
+
+ err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
if (!err)
sb->s_op = &s_ops;
return err;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 5027a3e14922..afdf4e3cafc2 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -24,6 +24,16 @@ static int load_script(struct linux_binprm *bprm)
if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
return -ENOEXEC;
+
+ /*
+ * If the script filename will be inaccessible after exec, typically
+ * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
+ * up now (on the assumption that the interpreter will want to load
+ * this file).
+ */
+ if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+ return -ENOENT;
+
/*
* This section does the #! interpretation.
* Sorta complicated, but hopefully it will work. -TYT
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1d9c9f3754f8..b48c41bf0f86 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -235,7 +235,10 @@ struct super_block *freeze_bdev(struct block_device *bdev)
sb = get_active_super(bdev);
if (!sb)
goto out;
- error = freeze_super(sb);
+ if (sb->s_op->freeze_super)
+ error = sb->s_op->freeze_super(sb);
+ else
+ error = freeze_super(sb);
if (error) {
deactivate_super(sb);
bdev->bd_fsfreeze_count--;
@@ -272,7 +275,10 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb)
if (!sb)
goto out;
- error = thaw_super(sb);
+ if (sb->s_op->thaw_super)
+ error = sb->s_op->thaw_super(sb);
+ else
+ error = thaw_super(sb);
if (error) {
bdev->bd_fsfreeze_count++;
mutex_unlock(&bdev->bd_fsfreeze_mutex);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index cb7f3fe9c9f6..d897ef803b3b 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -94,6 +94,7 @@
#include <linux/mutex.h>
#include <linux/genhd.h>
#include <linux/blkdev.h>
+#include <linux/vmalloc.h>
#include "ctree.h"
#include "disk-io.h"
#include "hash.h"
@@ -326,9 +327,6 @@ static int btrfsic_handle_extent_data(struct btrfsic_state *state,
static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
struct btrfsic_block_data_ctx *block_ctx_out,
int mirror_num);
-static int btrfsic_map_superblock(struct btrfsic_state *state, u64 bytenr,
- u32 len, struct block_device *bdev,
- struct btrfsic_block_data_ctx *block_ctx_out);
static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx);
static int btrfsic_read_block(struct btrfsic_state *state,
struct btrfsic_block_data_ctx *block_ctx);
@@ -1326,24 +1324,25 @@ static int btrfsic_create_link_to_next_block(
l = NULL;
next_block->generation = BTRFSIC_GENERATION_UNKNOWN;
} else {
- if (next_block->logical_bytenr != next_bytenr &&
- !(!next_block->is_metadata &&
- 0 == next_block->logical_bytenr)) {
- printk(KERN_INFO
- "Referenced block @%llu (%s/%llu/%d)"
- " found in hash table, %c,"
- " bytenr mismatch (!= stored %llu).\n",
- next_bytenr, next_block_ctx->dev->name,
- next_block_ctx->dev_bytenr, *mirror_nump,
- btrfsic_get_block_type(state, next_block),
- next_block->logical_bytenr);
- } else if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
- printk(KERN_INFO
- "Referenced block @%llu (%s/%llu/%d)"
- " found in hash table, %c.\n",
- next_bytenr, next_block_ctx->dev->name,
- next_block_ctx->dev_bytenr, *mirror_nump,
- btrfsic_get_block_type(state, next_block));
+ if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) {
+ if (next_block->logical_bytenr != next_bytenr &&
+ !(!next_block->is_metadata &&
+ 0 == next_block->logical_bytenr))
+ printk(KERN_INFO
+ "Referenced block @%llu (%s/%llu/%d) found in hash table, %c, bytenr mismatch (!= stored %llu).\n",
+ next_bytenr, next_block_ctx->dev->name,
+ next_block_ctx->dev_bytenr, *mirror_nump,
+ btrfsic_get_block_type(state,
+ next_block),
+ next_block->logical_bytenr);
+ else
+ printk(KERN_INFO
+ "Referenced block @%llu (%s/%llu/%d) found in hash table, %c.\n",
+ next_bytenr, next_block_ctx->dev->name,
+ next_block_ctx->dev_bytenr, *mirror_nump,
+ btrfsic_get_block_type(state,
+ next_block));
+ }
next_block->logical_bytenr = next_bytenr;
next_block->mirror_num = *mirror_nump;
@@ -1529,7 +1528,9 @@ static int btrfsic_handle_extent_data(
return -1;
}
if (!block_was_created) {
- if (next_block->logical_bytenr != next_bytenr &&
+ if ((state->print_mask &
+ BTRFSIC_PRINT_MASK_VERBOSE) &&
+ next_block->logical_bytenr != next_bytenr &&
!(!next_block->is_metadata &&
0 == next_block->logical_bytenr)) {
printk(KERN_INFO
@@ -1607,25 +1608,6 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
return ret;
}
-static int btrfsic_map_superblock(struct btrfsic_state *state, u64 bytenr,
- u32 len, struct block_device *bdev,
- struct btrfsic_block_data_ctx *block_ctx_out)
-{
- block_ctx_out->dev = btrfsic_dev_state_lookup(bdev);
- block_ctx_out->dev_bytenr = bytenr;
- block_ctx_out->start = bytenr;
- block_ctx_out->len = len;
- block_ctx_out->datav = NULL;
- block_ctx_out->pagev = NULL;
- block_ctx_out->mem_to_free = NULL;
- if (NULL != block_ctx_out->dev) {
- return 0;
- } else {
- printk(KERN_INFO "btrfsic: error, cannot lookup dev (#2)!\n");
- return -ENXIO;
- }
-}
-
static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx)
{
if (block_ctx->mem_to_free) {
@@ -1901,25 +1883,26 @@ again:
dev_state,
dev_bytenr);
}
- if (block->logical_bytenr != bytenr &&
- !(!block->is_metadata &&
- block->logical_bytenr == 0))
- printk(KERN_INFO
- "Written block @%llu (%s/%llu/%d)"
- " found in hash table, %c,"
- " bytenr mismatch"
- " (!= stored %llu).\n",
- bytenr, dev_state->name, dev_bytenr,
- block->mirror_num,
- btrfsic_get_block_type(state, block),
- block->logical_bytenr);
- else if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
- printk(KERN_INFO
- "Written block @%llu (%s/%llu/%d)"
- " found in hash table, %c.\n",
- bytenr, dev_state->name, dev_bytenr,
- block->mirror_num,
- btrfsic_get_block_type(state, block));
+ if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) {
+ if (block->logical_bytenr != bytenr &&
+ !(!block->is_metadata &&
+ block->logical_bytenr == 0))
+ printk(KERN_INFO
+ "Written block @%llu (%s/%llu/%d) found in hash table, %c, bytenr mismatch (!= stored %llu).\n",
+ bytenr, dev_state->name,
+ dev_bytenr,
+ block->mirror_num,
+ btrfsic_get_block_type(state,
+ block),
+ block->logical_bytenr);
+ else
+ printk(KERN_INFO
+ "Written block @%llu (%s/%llu/%d) found in hash table, %c.\n",
+ bytenr, dev_state->name,
+ dev_bytenr, block->mirror_num,
+ btrfsic_get_block_type(state,
+ block));
+ }
block->logical_bytenr = bytenr;
} else {
if (num_pages * PAGE_CACHE_SIZE <
@@ -2002,24 +1985,13 @@ again:
}
}
- if (block->is_superblock)
- ret = btrfsic_map_superblock(state, bytenr,
- processed_len,
- bdev, &block_ctx);
- else
- ret = btrfsic_map_block(state, bytenr, processed_len,
- &block_ctx, 0);
- if (ret) {
- printk(KERN_INFO
- "btrfsic: btrfsic_map_block(root @%llu)"
- " failed!\n", bytenr);
- goto continue_loop;
- }
- block_ctx.datav = mapped_datav;
- /* the following is required in case of writes to mirrors,
- * use the same that was used for the lookup */
block_ctx.dev = dev_state;
block_ctx.dev_bytenr = dev_bytenr;
+ block_ctx.start = bytenr;
+ block_ctx.len = processed_len;
+ block_ctx.pagev = NULL;
+ block_ctx.mem_to_free = NULL;
+ block_ctx.datav = mapped_datav;
if (is_metadata || state->include_extent_data) {
block->never_written = 0;
@@ -2133,10 +2105,6 @@ again:
/* this is getting ugly for the
* include_extent_data case... */
bytenr = 0; /* unknown */
- block_ctx.start = bytenr;
- block_ctx.len = processed_len;
- block_ctx.mem_to_free = NULL;
- block_ctx.pagev = NULL;
} else {
processed_len = state->metablock_size;
bytenr = btrfs_stack_header_bytenr(
@@ -2149,22 +2117,15 @@ again:
"Written block @%llu (%s/%llu/?)"
" !found in hash table, M.\n",
bytenr, dev_state->name, dev_bytenr);
-
- ret = btrfsic_map_block(state, bytenr, processed_len,
- &block_ctx, 0);
- if (ret) {
- printk(KERN_INFO
- "btrfsic: btrfsic_map_block(root @%llu)"
- " failed!\n",
- dev_bytenr);
- goto continue_loop;
- }
}
- block_ctx.datav = mapped_datav;
- /* the following is required in case of writes to mirrors,
- * use the same that was used for the lookup */
+
block_ctx.dev = dev_state;
block_ctx.dev_bytenr = dev_bytenr;
+ block_ctx.start = bytenr;
+ block_ctx.len = processed_len;
+ block_ctx.pagev = NULL;
+ block_ctx.mem_to_free = NULL;
+ block_ctx.datav = mapped_datav;
block = btrfsic_block_alloc();
if (NULL == block) {
@@ -3130,10 +3091,13 @@ int btrfsic_mount(struct btrfs_root *root,
root->sectorsize, PAGE_CACHE_SIZE);
return -1;
}
- state = kzalloc(sizeof(*state), GFP_NOFS);
- if (NULL == state) {
- printk(KERN_INFO "btrfs check-integrity: kmalloc() failed!\n");
- return -1;
+ state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!state) {
+ state = vzalloc(sizeof(*state));
+ if (!state) {
+ printk(KERN_INFO "btrfs check-integrity: vzalloc() failed!\n");
+ return -1;
+ }
}
if (!btrfsic_is_initialized) {
@@ -3277,5 +3241,8 @@ void btrfsic_unmount(struct btrfs_root *root,
mutex_unlock(&btrfsic_mutex);
- kfree(state);
+ if (is_vmalloc_addr(state))
+ vfree(state);
+ else
+ kfree(state);
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d3220d31d3cb..e9df8862012c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -224,16 +224,19 @@ out:
* Clear the writeback bits on all of the file
* pages for a compressed write
*/
-static noinline void end_compressed_writeback(struct inode *inode, u64 start,
- unsigned long ram_size)
+static noinline void end_compressed_writeback(struct inode *inode,
+ const struct compressed_bio *cb)
{
- unsigned long index = start >> PAGE_CACHE_SHIFT;
- unsigned long end_index = (start + ram_size - 1) >> PAGE_CACHE_SHIFT;
+ unsigned long index = cb->start >> PAGE_CACHE_SHIFT;
+ unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_CACHE_SHIFT;
struct page *pages[16];
unsigned long nr_pages = end_index - index + 1;
int i;
int ret;
+ if (cb->errors)
+ mapping_set_error(inode->i_mapping, -EIO);
+
while (nr_pages > 0) {
ret = find_get_pages_contig(inode->i_mapping, index,
min_t(unsigned long,
@@ -244,6 +247,8 @@ static noinline void end_compressed_writeback(struct inode *inode, u64 start,
continue;
}
for (i = 0; i < ret; i++) {
+ if (cb->errors)
+ SetPageError(pages[i]);
end_page_writeback(pages[i]);
page_cache_release(pages[i]);
}
@@ -287,10 +292,11 @@ static void end_compressed_bio_write(struct bio *bio, int err)
tree->ops->writepage_end_io_hook(cb->compressed_pages[0],
cb->start,
cb->start + cb->len - 1,
- NULL, 1);
+ NULL,
+ err ? 0 : 1);
cb->compressed_pages[0]->mapping = NULL;
- end_compressed_writeback(inode, cb->start, cb->len);
+ end_compressed_writeback(inode, cb);
/* note, our inode could be gone now */
/*
@@ -1011,8 +1017,6 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(page_out);
memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
- if (*pg_index == (vcnt - 1) && *pg_offset == 0)
- memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
kunmap_atomic(kaddr);
flush_dcache_page(page_out);
@@ -1054,3 +1058,34 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
return 1;
}
+
+/*
+ * When uncompressing data, we need to make sure and zero any parts of
+ * the biovec that were not filled in by the decompression code. pg_index
+ * and pg_offset indicate the last page and the last offset of that page
+ * that have been filled in. This will zero everything remaining in the
+ * biovec.
+ */
+void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
+ unsigned long pg_index,
+ unsigned long pg_offset)
+{
+ while (pg_index < vcnt) {
+ struct page *page = bvec[pg_index].bv_page;
+ unsigned long off = bvec[pg_index].bv_offset;
+ unsigned long len = bvec[pg_index].bv_len;
+
+ if (pg_offset < off)
+ pg_offset = off;
+ if (pg_offset < off + len) {
+ unsigned long bytes = off + len - pg_offset;
+ char *kaddr;
+
+ kaddr = kmap_atomic(page);
+ memset(kaddr + pg_offset, 0, bytes);
+ kunmap_atomic(kaddr);
+ }
+ pg_index++;
+ pg_offset = 0;
+ }
+}
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 0c803b4fbf93..d181f70caae0 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -45,7 +45,9 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long nr_pages);
int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
-
+void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
+ unsigned long pg_index,
+ unsigned long pg_offset);
struct btrfs_compress_op {
struct list_head *(*alloc_workspace)(void);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 19bc6162fb8e..14a72ed14ef7 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -80,13 +80,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
{
int i;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- /* lockdep really cares that we take all of these spinlocks
- * in the right order. If any of the locks in the path are not
- * currently blocking, it is going to complain. So, make really
- * really sure by forcing the path to blocking before we clear
- * the path blocking.
- */
if (held) {
btrfs_set_lock_blocking_rw(held, held_rw);
if (held_rw == BTRFS_WRITE_LOCK)
@@ -95,7 +88,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
held_rw = BTRFS_READ_LOCK_BLOCKING;
}
btrfs_set_path_blocking(p);
-#endif
for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
if (p->nodes[i] && p->locks[i]) {
@@ -107,10 +99,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
}
}
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (held)
btrfs_clear_lock_blocking_rw(held, held_rw);
-#endif
}
/* this also releases the path */
@@ -2893,7 +2883,7 @@ cow_done:
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
- err = btrfs_try_tree_read_lock(b);
+ err = btrfs_tree_read_lock_atomic(b);
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
@@ -2939,7 +2929,7 @@ done:
*/
if (!p->leave_spinning)
btrfs_set_path_blocking(p);
- if (ret < 0)
+ if (ret < 0 && !p->skip_release_on_error)
btrfs_release_path(p);
return ret;
}
@@ -3025,7 +3015,7 @@ again:
}
level = btrfs_header_level(b);
- err = btrfs_try_tree_read_lock(b);
+ err = btrfs_tree_read_lock_atomic(b);
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index fe69edda11fb..7e607416755a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -607,6 +607,7 @@ struct btrfs_path {
unsigned int leave_spinning:1;
unsigned int search_commit_root:1;
unsigned int need_commit_sem:1;
+ unsigned int skip_release_on_error:1;
};
/*
@@ -1170,6 +1171,7 @@ struct btrfs_space_info {
struct percpu_counter total_bytes_pinned;
struct list_head list;
+ struct list_head ro_bgs;
struct rw_semaphore groups_sem;
/* for block groups in our same type */
@@ -1276,6 +1278,8 @@ struct btrfs_block_group_cache {
unsigned int ro:1;
unsigned int dirty:1;
unsigned int iref:1;
+ unsigned int has_caching_ctl:1;
+ unsigned int removed:1;
int disk_cache_state;
@@ -1305,6 +1309,11 @@ struct btrfs_block_group_cache {
/* For delayed block group creation or deletion of empty block groups */
struct list_head bg_list;
+
+ /* For read-only block groups */
+ struct list_head ro_list;
+
+ atomic_t trimming;
};
/* delayed seq elem */
@@ -1402,6 +1411,11 @@ struct btrfs_fs_info {
*/
u64 last_trans_log_full_commit;
unsigned long mount_opt;
+ /*
+ * Track requests for actions that need to be done during transaction
+ * commit (like for some mount options).
+ */
+ unsigned long pending_changes;
unsigned long compress_type:4;
int commit_interval;
/*
@@ -1729,6 +1743,12 @@ struct btrfs_fs_info {
/* For btrfs to record security options */
struct security_mnt_opts security_opts;
+
+ /*
+ * Chunks that can't be freed yet (under a trim/discard operation)
+ * and will be latter freed. Protected by fs_info->chunk_mutex.
+ */
+ struct list_head pinned_chunks;
};
struct btrfs_subvolume_writers {
@@ -2093,7 +2113,6 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23)
-#define BTRFS_MOUNT_CHANGE_INODE_CACHE (1 << 24)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
#define BTRFS_DEFAULT_MAX_INLINE (8192)
@@ -2103,6 +2122,7 @@ struct btrfs_ioctl_defrag_range_args {
#define btrfs_raw_test_opt(o, opt) ((o) & BTRFS_MOUNT_##opt)
#define btrfs_test_opt(root, opt) ((root)->fs_info->mount_opt & \
BTRFS_MOUNT_##opt)
+
#define btrfs_set_and_info(root, opt, fmt, args...) \
{ \
if (!btrfs_test_opt(root, opt)) \
@@ -2118,6 +2138,49 @@ struct btrfs_ioctl_defrag_range_args {
}
/*
+ * Requests for changes that need to be done during transaction commit.
+ *
+ * Internal mount options that are used for special handling of the real
+ * mount options (eg. cannot be set during remount and have to be set during
+ * transaction commit)
+ */
+
+#define BTRFS_PENDING_SET_INODE_MAP_CACHE (0)
+#define BTRFS_PENDING_CLEAR_INODE_MAP_CACHE (1)
+#define BTRFS_PENDING_COMMIT (2)
+
+#define btrfs_test_pending(info, opt) \
+ test_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
+#define btrfs_set_pending(info, opt) \
+ set_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
+#define btrfs_clear_pending(info, opt) \
+ clear_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
+
+/*
+ * Helpers for setting pending mount option changes.
+ *
+ * Expects corresponding macros
+ * BTRFS_PENDING_SET_ and CLEAR_ + short mount option name
+ */
+#define btrfs_set_pending_and_info(info, opt, fmt, args...) \
+do { \
+ if (!btrfs_raw_test_opt((info)->mount_opt, opt)) { \
+ btrfs_info((info), fmt, ##args); \
+ btrfs_set_pending((info), SET_##opt); \
+ btrfs_clear_pending((info), CLEAR_##opt); \
+ } \
+} while(0)
+
+#define btrfs_clear_pending_and_info(info, opt, fmt, args...) \
+do { \
+ if (btrfs_raw_test_opt((info)->mount_opt, opt)) { \
+ btrfs_info((info), fmt, ##args); \
+ btrfs_set_pending((info), CLEAR_##opt); \
+ btrfs_clear_pending((info), SET_##opt); \
+ } \
+} while(0)
+
+/*
* Inode flags
*/
#define BTRFS_INODE_NODATASUM (1 << 0)
@@ -3351,7 +3414,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
u64 type, u64 chunk_objectid, u64 chunk_offset,
u64 size);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, u64 group_start);
+ struct btrfs_root *root, u64 group_start,
+ struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
@@ -3417,8 +3481,8 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
int btrfs_error_unpin_extent_range(struct btrfs_root *root,
u64 start, u64 end);
-int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
- u64 num_bytes, u64 *actual_bytes);
+int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
+ u64 num_bytes, u64 *actual_bytes);
int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 type);
int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range);
@@ -3427,8 +3491,8 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int __get_raid_index(u64 flags);
-int btrfs_start_nocow_write(struct btrfs_root *root);
-void btrfs_end_nocow_write(struct btrfs_root *root);
+int btrfs_start_write_no_snapshoting(struct btrfs_root *root);
+void btrfs_end_write_no_snapshoting(struct btrfs_root *root);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
int level, int *slot);
@@ -3686,6 +3750,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
int verify_dir_item(struct btrfs_root *root,
struct extent_buffer *leaf,
struct btrfs_dir_item *dir_item);
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+ struct btrfs_path *path,
+ const char *name,
+ int name_len);
/* orphan.c */
int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
@@ -3857,6 +3925,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
struct btrfs_trans_handle *trans, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
+int btrfs_inode_check_errors(struct inode *inode);
extern const struct dentry_operations btrfs_dentry_operations;
/* ioctl.c */
@@ -3901,6 +3970,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
struct page **pages, size_t num_pages,
loff_t pos, size_t write_bytes,
struct extent_state **cached);
+int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
@@ -4097,7 +4167,12 @@ int btrfs_scrub_progress(struct btrfs_root *root, u64 devid,
/* dev-replace.c */
void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info);
-void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info);
+void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount);
+
+static inline void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
+{
+ btrfs_bio_counter_sub(fs_info, 1);
+}
/* reada.c */
struct reada_control {
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 6f662b34ba0e..ca6a3a3b6b6c 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -316,11 +316,6 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
struct btrfs_device *tgt_device = NULL;
struct btrfs_device *src_device = NULL;
- if (btrfs_fs_incompat(fs_info, RAID56)) {
- btrfs_warn(fs_info, "dev_replace cannot yet handle RAID5/RAID6");
- return -EOPNOTSUPP;
- }
-
switch (args->start.cont_reading_from_srcdev_mode) {
case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
@@ -422,9 +417,15 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(root->fs_info, ret);
- WARN_ON(ret);
+ /* don't warn if EINPROGRESS, someone else might be running scrub */
+ if (ret == -EINPROGRESS) {
+ args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
+ ret = 0;
+ } else {
+ WARN_ON(ret);
+ }
- return 0;
+ return ret;
leave:
dev_replace->srcdev = NULL;
@@ -542,7 +543,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
- return 0;
+ return scrub_ret;
}
printk_in_rcu(KERN_INFO
@@ -571,15 +572,11 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
fs_info->fs_devices->rw_devices++;
- /* replace the sysfs entry */
- btrfs_kobj_rm_device(fs_info, src_device);
- btrfs_kobj_add_device(fs_info, tgt_device);
-
btrfs_dev_replace_unlock(dev_replace);
btrfs_rm_dev_replace_blocked(fs_info);
- btrfs_rm_dev_replace_srcdev(fs_info, src_device);
+ btrfs_rm_dev_replace_remove_srcdev(fs_info, src_device);
btrfs_rm_dev_replace_unblocked(fs_info);
@@ -594,6 +591,11 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
mutex_unlock(&uuid_mutex);
+ /* replace the sysfs entry */
+ btrfs_kobj_rm_device(fs_info, src_device);
+ btrfs_kobj_add_device(fs_info, tgt_device);
+ btrfs_rm_dev_replace_free_srcdev(fs_info, src_device);
+
/* write back the superblocks */
trans = btrfs_start_transaction(root, 0);
if (!IS_ERR(trans))
@@ -920,9 +922,9 @@ void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
percpu_counter_inc(&fs_info->bio_counter);
}
-void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
+void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount)
{
- percpu_counter_dec(&fs_info->bio_counter);
+ percpu_counter_sub(&fs_info->bio_counter, amount);
if (waitqueue_active(&fs_info->replace_wait))
wake_up(&fs_info->replace_wait);
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index fc8df866e919..1752625fb4dd 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -21,10 +21,6 @@
#include "hash.h"
#include "transaction.h"
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
- struct btrfs_path *path,
- const char *name, int name_len);
-
/*
* insert a name into a directory, doing overflow properly if there is a hash
* collision. data_size indicates how big the item inserted should be. On
@@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
* this walks through all the entries in a dir item and finds one
* for a specific name.
*/
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
- struct btrfs_path *path,
- const char *name, int name_len)
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+ struct btrfs_path *path,
+ const char *name, int name_len)
{
struct btrfs_dir_item *dir_item;
unsigned long name_ptr;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1bf9f897065d..8c63419a7f70 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2384,6 +2384,8 @@ int open_ctree(struct super_block *sb,
init_waitqueue_head(&fs_info->transaction_blocked_wait);
init_waitqueue_head(&fs_info->async_submit_wait);
+ INIT_LIST_HEAD(&fs_info->pinned_chunks);
+
ret = btrfs_alloc_stripe_hash_table(fs_info);
if (ret) {
err = ret;
@@ -2830,9 +2832,11 @@ retry_root_backup:
btrfs_set_opt(fs_info->mount_opt, SSD);
}
- /* Set the real inode map cache flag */
- if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE))
- btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE);
+ /*
+ * Mount does not set all options immediatelly, we can do it now and do
+ * not have to wait for transaction commit
+ */
+ btrfs_apply_pending_changes(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
@@ -3713,6 +3717,17 @@ void close_ctree(struct btrfs_root *root)
btrfs_free_block_rsv(root, root->orphan_block_rsv);
root->orphan_block_rsv = NULL;
+
+ lock_chunks(root);
+ while (!list_empty(&fs_info->pinned_chunks)) {
+ struct extent_map *em;
+
+ em = list_first_entry(&fs_info->pinned_chunks,
+ struct extent_map, list);
+ list_del_init(&em->list);
+ free_extent_map(em);
+ }
+ unlock_chunks(root);
}
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
@@ -3839,12 +3854,12 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
*/
if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
- sb->root);
+ btrfs_super_root(sb));
if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
- printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
- sb->chunk_root);
+ printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
+ btrfs_super_chunk_root(sb));
if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
- printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+ printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
btrfs_super_log_root(sb));
if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
@@ -4106,12 +4121,6 @@ again:
if (ret)
break;
- /* opt_discard */
- if (btrfs_test_opt(root, DISCARD))
- ret = btrfs_error_discard_extent(root, start,
- end + 1 - start,
- NULL);
-
clear_extent_dirty(unpin, start, end, GFP_NOFS);
btrfs_error_unpin_extent_range(root, start, end);
cond_resched();
@@ -4129,6 +4138,25 @@ again:
return 0;
}
+static void btrfs_free_pending_ordered(struct btrfs_transaction *cur_trans,
+ struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_ordered_extent *ordered;
+
+ spin_lock(&fs_info->trans_lock);
+ while (!list_empty(&cur_trans->pending_ordered)) {
+ ordered = list_first_entry(&cur_trans->pending_ordered,
+ struct btrfs_ordered_extent,
+ trans_list);
+ list_del_init(&ordered->trans_list);
+ spin_unlock(&fs_info->trans_lock);
+
+ btrfs_put_ordered_extent(ordered);
+ spin_lock(&fs_info->trans_lock);
+ }
+ spin_unlock(&fs_info->trans_lock);
+}
+
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_root *root)
{
@@ -4140,6 +4168,7 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
cur_trans->state = TRANS_STATE_UNBLOCKED;
wake_up(&root->fs_info->transaction_wait);
+ btrfs_free_pending_ordered(cur_trans, root->fs_info);
btrfs_destroy_delayed_inodes(root);
btrfs_assert_delayed_root_empty(root);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 47c1ba141082..a80b97100d90 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -315,12 +315,6 @@ get_caching_control(struct btrfs_block_group_cache *cache)
struct btrfs_caching_control *ctl;
spin_lock(&cache->lock);
- if (cache->cached != BTRFS_CACHE_STARTED) {
- spin_unlock(&cache->lock);
- return NULL;
- }
-
- /* We're loading it the fast way, so we don't have a caching_ctl. */
if (!cache->caching_ctl) {
spin_unlock(&cache->lock);
return NULL;
@@ -594,6 +588,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
spin_unlock(&cache->lock);
if (fs_info->mount_opt & BTRFS_MOUNT_SPACE_CACHE) {
+ mutex_lock(&caching_ctl->mutex);
ret = load_free_space_cache(fs_info, cache);
spin_lock(&cache->lock);
@@ -601,15 +596,19 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
cache->caching_ctl = NULL;
cache->cached = BTRFS_CACHE_FINISHED;
cache->last_byte_to_unpin = (u64)-1;
+ caching_ctl->progress = (u64)-1;
} else {
if (load_cache_only) {
cache->caching_ctl = NULL;
cache->cached = BTRFS_CACHE_NO;
} else {
cache->cached = BTRFS_CACHE_STARTED;
+ cache->has_caching_ctl = 1;
}
}
spin_unlock(&cache->lock);
+ mutex_unlock(&caching_ctl->mutex);
+
wake_up(&caching_ctl->wait);
if (ret == 1) {
put_caching_control(caching_ctl);
@@ -627,6 +626,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
cache->cached = BTRFS_CACHE_NO;
} else {
cache->cached = BTRFS_CACHE_STARTED;
+ cache->has_caching_ctl = 1;
}
spin_unlock(&cache->lock);
wake_up(&caching_ctl->wait);
@@ -1889,8 +1889,8 @@ static int btrfs_issue_discard(struct block_device *bdev,
return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0);
}
-static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
- u64 num_bytes, u64 *actual_bytes)
+int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
+ u64 num_bytes, u64 *actual_bytes)
{
int ret;
u64 discarded_bytes = 0;
@@ -3162,7 +3162,19 @@ next_block_group(struct btrfs_root *root,
struct btrfs_block_group_cache *cache)
{
struct rb_node *node;
+
spin_lock(&root->fs_info->block_group_cache_lock);
+
+ /* If our block group was removed, we need a full search. */
+ if (RB_EMPTY_NODE(&cache->cache_node)) {
+ const u64 next_bytenr = cache->key.objectid + cache->key.offset;
+
+ spin_unlock(&root->fs_info->block_group_cache_lock);
+ btrfs_put_block_group(cache);
+ cache = btrfs_lookup_first_block_group(root->fs_info,
+ next_bytenr);
+ return cache;
+ }
node = rb_next(&cache->cache_node);
btrfs_put_block_group(cache);
if (node) {
@@ -3504,6 +3516,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
found->chunk_alloc = 0;
found->flush = 0;
init_waitqueue_head(&found->wait);
+ INIT_LIST_HEAD(&found->ro_bgs);
ret = kobject_init_and_add(&found->kobj, &space_info_ktype,
info->space_info_kobj, "%s",
@@ -5425,7 +5438,17 @@ static int update_block_group(struct btrfs_root *root,
spin_unlock(&cache->space_info->lock);
} else {
old_val -= num_bytes;
+ btrfs_set_block_group_used(&cache->item, old_val);
+ cache->pinned += num_bytes;
+ cache->space_info->bytes_pinned += num_bytes;
+ cache->space_info->bytes_used -= num_bytes;
+ cache->space_info->disk_used -= num_bytes * factor;
+ spin_unlock(&cache->lock);
+ spin_unlock(&cache->space_info->lock);
+ set_extent_dirty(info->pinned_extents,
+ bytenr, bytenr + num_bytes - 1,
+ GFP_NOFS | __GFP_NOFAIL);
/*
* No longer have used bytes in this block group, queue
* it for deletion.
@@ -5439,17 +5462,6 @@ static int update_block_group(struct btrfs_root *root,
}
spin_unlock(&info->unused_bgs_lock);
}
- btrfs_set_block_group_used(&cache->item, old_val);
- cache->pinned += num_bytes;
- cache->space_info->bytes_pinned += num_bytes;
- cache->space_info->bytes_used -= num_bytes;
- cache->space_info->disk_used -= num_bytes * factor;
- spin_unlock(&cache->lock);
- spin_unlock(&cache->space_info->lock);
-
- set_extent_dirty(info->pinned_extents,
- bytenr, bytenr + num_bytes - 1,
- GFP_NOFS | __GFP_NOFAIL);
}
btrfs_put_block_group(cache);
total -= num_bytes;
@@ -5715,7 +5727,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
update_global_block_rsv(fs_info);
}
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+ const bool return_free_space)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_group_cache *cache = NULL;
@@ -5739,7 +5752,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
if (start < cache->last_byte_to_unpin) {
len = min(len, cache->last_byte_to_unpin - start);
- btrfs_add_free_space(cache, start, len);
+ if (return_free_space)
+ btrfs_add_free_space(cache, start, len);
}
start += len;
@@ -5803,7 +5817,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
end + 1 - start, NULL);
clear_extent_dirty(unpin, start, end, GFP_NOFS);
- unpin_extent_range(root, start, end);
+ unpin_extent_range(root, start, end, true);
cond_resched();
}
@@ -8511,6 +8525,7 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache, int force)
min_allocable_bytes <= sinfo->total_bytes) {
sinfo->bytes_readonly += num_bytes;
cache->ro = 1;
+ list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
ret = 0;
}
out:
@@ -8565,15 +8580,20 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
/*
* helper to account the unused space of all the readonly block group in the
- * list. takes mirrors into account.
+ * space_info. takes mirrors into account.
*/
-static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list)
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
{
struct btrfs_block_group_cache *block_group;
u64 free_bytes = 0;
int factor;
- list_for_each_entry(block_group, groups_list, list) {
+ /* It's df, we don't care if it's racey */
+ if (list_empty(&sinfo->ro_bgs))
+ return 0;
+
+ spin_lock(&sinfo->lock);
+ list_for_each_entry(block_group, &sinfo->ro_bgs, ro_list) {
spin_lock(&block_group->lock);
if (!block_group->ro) {
@@ -8594,26 +8614,6 @@ static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list)
spin_unlock(&block_group->lock);
}
-
- return free_bytes;
-}
-
-/*
- * helper to account the unused space of all the readonly block group in the
- * space_info. takes mirrors into account.
- */
-u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
-{
- int i;
- u64 free_bytes = 0;
-
- spin_lock(&sinfo->lock);
-
- for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
- if (!list_empty(&sinfo->block_groups[i]))
- free_bytes += __btrfs_get_ro_block_group_free_space(
- &sinfo->block_groups[i]);
-
spin_unlock(&sinfo->lock);
return free_bytes;
@@ -8633,6 +8633,7 @@ void btrfs_set_block_group_rw(struct btrfs_root *root,
cache->bytes_super - btrfs_block_group_used(&cache->item);
sinfo->bytes_readonly -= num_bytes;
cache->ro = 0;
+ list_del_init(&cache->ro_list);
spin_unlock(&cache->lock);
spin_unlock(&sinfo->lock);
}
@@ -8873,6 +8874,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
cache_node);
rb_erase(&block_group->cache_node,
&info->block_group_cache_tree);
+ RB_CLEAR_NODE(&block_group->cache_node);
spin_unlock(&info->block_group_cache_lock);
down_write(&block_group->space_info->groups_sem);
@@ -9002,7 +9004,9 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
INIT_LIST_HEAD(&cache->list);
INIT_LIST_HEAD(&cache->cluster_list);
INIT_LIST_HEAD(&cache->bg_list);
+ INIT_LIST_HEAD(&cache->ro_list);
btrfs_init_free_space_ctl(cache);
+ atomic_set(&cache->trimming, 0);
return cache;
}
@@ -9129,6 +9133,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
spin_lock(&info->block_group_cache_lock);
rb_erase(&cache->cache_node,
&info->block_group_cache_tree);
+ RB_CLEAR_NODE(&cache->cache_node);
spin_unlock(&info->block_group_cache_lock);
btrfs_put_block_group(cache);
goto error;
@@ -9195,9 +9200,8 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
int ret = 0;
list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
- list_del_init(&block_group->bg_list);
if (ret)
- continue;
+ goto next;
spin_lock(&block_group->lock);
memcpy(&item, &block_group->item, sizeof(item));
@@ -9212,6 +9216,8 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
key.objectid, key.offset);
if (ret)
btrfs_abort_transaction(trans, extent_root, ret);
+next:
+ list_del_init(&block_group->bg_list);
}
}
@@ -9269,6 +9275,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
spin_lock(&root->fs_info->block_group_cache_lock);
rb_erase(&cache->cache_node,
&root->fs_info->block_group_cache_tree);
+ RB_CLEAR_NODE(&cache->cache_node);
spin_unlock(&root->fs_info->block_group_cache_lock);
btrfs_put_block_group(cache);
return ret;
@@ -9304,7 +9311,8 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
}
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, u64 group_start)
+ struct btrfs_root *root, u64 group_start,
+ struct extent_map *em)
{
struct btrfs_path *path;
struct btrfs_block_group_cache *block_group;
@@ -9316,6 +9324,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
int ret;
int index;
int factor;
+ struct btrfs_caching_control *caching_ctl = NULL;
+ bool remove_em;
root = root->fs_info->extent_root;
@@ -9400,6 +9410,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
spin_lock(&root->fs_info->block_group_cache_lock);
rb_erase(&block_group->cache_node,
&root->fs_info->block_group_cache_tree);
+ RB_CLEAR_NODE(&block_group->cache_node);
if (root->fs_info->first_logical_byte == block_group->key.objectid)
root->fs_info->first_logical_byte = (u64)-1;
@@ -9411,6 +9422,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
* are still on the list after taking the semaphore
*/
list_del_init(&block_group->list);
+ list_del_init(&block_group->ro_list);
if (list_empty(&block_group->space_info->block_groups[index])) {
kobj = block_group->space_info->block_group_kobjs[index];
block_group->space_info->block_group_kobjs[index] = NULL;
@@ -9422,8 +9434,32 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
kobject_put(kobj);
}
+ if (block_group->has_caching_ctl)
+ caching_ctl = get_caching_control(block_group);
if (block_group->cached == BTRFS_CACHE_STARTED)
wait_block_group_cache_done(block_group);
+ if (block_group->has_caching_ctl) {
+ down_write(&root->fs_info->commit_root_sem);
+ if (!caching_ctl) {
+ struct btrfs_caching_control *ctl;
+
+ list_for_each_entry(ctl,
+ &root->fs_info->caching_block_groups, list)
+ if (ctl->block_group == block_group) {
+ caching_ctl = ctl;
+ atomic_inc(&caching_ctl->count);
+ break;
+ }
+ }
+ if (caching_ctl)
+ list_del_init(&caching_ctl->list);
+ up_write(&root->fs_info->commit_root_sem);
+ if (caching_ctl) {
+ /* Once for the caching bgs list and once for us. */
+ put_caching_control(caching_ctl);
+ put_caching_control(caching_ctl);
+ }
+ }
btrfs_remove_free_space_cache(block_group);
@@ -9435,6 +9471,71 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
memcpy(&key, &block_group->key, sizeof(key));
+ lock_chunks(root);
+ if (!list_empty(&em->list)) {
+ /* We're in the transaction->pending_chunks list. */
+ free_extent_map(em);
+ }
+ spin_lock(&block_group->lock);
+ block_group->removed = 1;
+ /*
+ * At this point trimming can't start on this block group, because we
+ * removed the block group from the tree fs_info->block_group_cache_tree
+ * so no one can't find it anymore and even if someone already got this
+ * block group before we removed it from the rbtree, they have already
+ * incremented block_group->trimming - if they didn't, they won't find
+ * any free space entries because we already removed them all when we
+ * called btrfs_remove_free_space_cache().
+ *
+ * And we must not remove the extent map from the fs_info->mapping_tree
+ * to prevent the same logical address range and physical device space
+ * ranges from being reused for a new block group. This is because our
+ * fs trim operation (btrfs_trim_fs() / btrfs_ioctl_fitrim()) is
+ * completely transactionless, so while it is trimming a range the
+ * currently running transaction might finish and a new one start,
+ * allowing for new block groups to be created that can reuse the same
+ * physical device locations unless we take this special care.
+ */
+ remove_em = (atomic_read(&block_group->trimming) == 0);
+ /*
+ * Make sure a trimmer task always sees the em in the pinned_chunks list
+ * if it sees block_group->removed == 1 (needs to lock block_group->lock
+ * before checking block_group->removed).
+ */
+ if (!remove_em) {
+ /*
+ * Our em might be in trans->transaction->pending_chunks which
+ * is protected by fs_info->chunk_mutex ([lock|unlock]_chunks),
+ * and so is the fs_info->pinned_chunks list.
+ *
+ * So at this point we must be holding the chunk_mutex to avoid
+ * any races with chunk allocation (more specifically at
+ * volumes.c:contains_pending_extent()), to ensure it always
+ * sees the em, either in the pending_chunks list or in the
+ * pinned_chunks list.
+ */
+ list_move_tail(&em->list, &root->fs_info->pinned_chunks);
+ }
+ spin_unlock(&block_group->lock);
+
+ if (remove_em) {
+ struct extent_map_tree *em_tree;
+
+ em_tree = &root->fs_info->mapping_tree.map_tree;
+ write_lock(&em_tree->lock);
+ /*
+ * The em might be in the pending_chunks list, so make sure the
+ * chunk mutex is locked, since remove_extent_mapping() will
+ * delete us from that list.
+ */
+ remove_extent_mapping(em_tree, em);
+ write_unlock(&em_tree->lock);
+ /* once for the tree */
+ free_extent_map(em);
+ }
+
+ unlock_chunks(root);
+
btrfs_put_block_group(block_group);
btrfs_put_block_group(block_group);
@@ -9523,10 +9624,18 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
*/
start = block_group->key.objectid;
end = start + block_group->key.offset - 1;
- clear_extent_bits(&fs_info->freed_extents[0], start, end,
+ ret = clear_extent_bits(&fs_info->freed_extents[0], start, end,
EXTENT_DIRTY, GFP_NOFS);
- clear_extent_bits(&fs_info->freed_extents[1], start, end,
+ if (ret) {
+ btrfs_set_block_group_rw(root, block_group);
+ goto end_trans;
+ }
+ ret = clear_extent_bits(&fs_info->freed_extents[1], start, end,
EXTENT_DIRTY, GFP_NOFS);
+ if (ret) {
+ btrfs_set_block_group_rw(root, block_group);
+ goto end_trans;
+ }
/* Reset pinned so btrfs_put_block_group doesn't complain */
block_group->pinned = 0;
@@ -9537,6 +9646,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
*/
ret = btrfs_remove_chunk(trans, root,
block_group->key.objectid);
+end_trans:
btrfs_end_transaction(trans, root);
next:
btrfs_put_block_group(block_group);
@@ -9585,13 +9695,7 @@ out:
int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
{
- return unpin_extent_range(root, start, end);
-}
-
-int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
- u64 num_bytes, u64 *actual_bytes)
-{
- return btrfs_discard_extent(root, bytenr, num_bytes, actual_bytes);
+ return unpin_extent_range(root, start, end, false);
}
int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
@@ -9657,12 +9761,14 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
}
/*
- * btrfs_{start,end}_write() is similar to mnt_{want, drop}_write(),
- * they are used to prevent the some tasks writing data into the page cache
- * by nocow before the subvolume is snapshoted, but flush the data into
- * the disk after the snapshot creation.
+ * btrfs_{start,end}_write_no_snapshoting() are similar to
+ * mnt_{want,drop}_write(), they are used to prevent some tasks from writing
+ * data into the page cache through nocow before the subvolume is snapshoted,
+ * but flush the data into disk after the snapshot creation, or to prevent
+ * operations while snapshoting is ongoing and that cause the snapshot to be
+ * inconsistent (writes followed by expanding truncates for example).
*/
-void btrfs_end_nocow_write(struct btrfs_root *root)
+void btrfs_end_write_no_snapshoting(struct btrfs_root *root)
{
percpu_counter_dec(&root->subv_writers->counter);
/*
@@ -9674,7 +9780,7 @@ void btrfs_end_nocow_write(struct btrfs_root *root)
wake_up(&root->subv_writers->wait);
}
-int btrfs_start_nocow_write(struct btrfs_root *root)
+int btrfs_start_write_no_snapshoting(struct btrfs_root *root)
{
if (atomic_read(&root->will_be_snapshoted))
return 0;
@@ -9685,7 +9791,7 @@ int btrfs_start_nocow_write(struct btrfs_root *root)
*/
smp_mb();
if (atomic_read(&root->will_be_snapshoted)) {
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
return 0;
}
return 1;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index bf3f424e0013..4ebabd237153 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -595,9 +595,14 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
clear = 1;
again:
if (!prealloc && (mask & __GFP_WAIT)) {
+ /*
+ * Don't care for allocation failure here because we might end
+ * up not needing the pre-allocated extent state at all, which
+ * is the case if we only have in the tree extent states that
+ * cover our input range and don't cover too any other range.
+ * If we end up needing a new extent state we allocate it later.
+ */
prealloc = alloc_extent_state(mask);
- if (!prealloc)
- return -ENOMEM;
}
spin_lock(&tree->lock);
@@ -796,17 +801,25 @@ static void set_state_bits(struct extent_io_tree *tree,
state->state |= bits_to_set;
}
-static void cache_state(struct extent_state *state,
- struct extent_state **cached_ptr)
+static void cache_state_if_flags(struct extent_state *state,
+ struct extent_state **cached_ptr,
+ const u64 flags)
{
if (cached_ptr && !(*cached_ptr)) {
- if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY)) {
+ if (!flags || (state->state & flags)) {
*cached_ptr = state;
atomic_inc(&state->refs);
}
}
}
+static void cache_state(struct extent_state *state,
+ struct extent_state **cached_ptr)
+{
+ return cache_state_if_flags(state, cached_ptr,
+ EXTENT_IOBITS | EXTENT_BOUNDARY);
+}
+
/*
* set some bits on a range in the tree. This may require allocations or
* sleeping, so the gfp mask is used to indicate what is allowed.
@@ -1058,13 +1071,21 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
int err = 0;
u64 last_start;
u64 last_end;
+ bool first_iteration = true;
btrfs_debug_check_extent_io_range(tree, start, end);
again:
if (!prealloc && (mask & __GFP_WAIT)) {
+ /*
+ * Best effort, don't worry if extent state allocation fails
+ * here for the first iteration. We might have a cached state
+ * that matches exactly the target range, in which case no
+ * extent state allocations are needed. We'll only know this
+ * after locking the tree.
+ */
prealloc = alloc_extent_state(mask);
- if (!prealloc)
+ if (!prealloc && !first_iteration)
return -ENOMEM;
}
@@ -1234,6 +1255,7 @@ search_again:
spin_unlock(&tree->lock);
if (mask & __GFP_WAIT)
cond_resched();
+ first_iteration = false;
goto again;
}
@@ -1482,7 +1504,7 @@ int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
state = find_first_extent_bit_state(tree, start, bits);
got_it:
if (state) {
- cache_state(state, cached_state);
+ cache_state_if_flags(state, cached_state, 0);
*start_ret = state->start;
*end_ret = state->end;
ret = 0;
@@ -1746,6 +1768,9 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
if (page_ops == 0)
return 0;
+ if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
+ mapping_set_error(inode->i_mapping, -EIO);
+
while (nr_pages > 0) {
ret = find_get_pages_contig(inode->i_mapping, index,
min_t(unsigned long,
@@ -1763,6 +1788,8 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
clear_page_dirty_for_io(pages[i]);
if (page_ops & PAGE_SET_WRITEBACK)
set_page_writeback(pages[i]);
+ if (page_ops & PAGE_SET_ERROR)
+ SetPageError(pages[i]);
if (page_ops & PAGE_END_WRITEBACK)
end_page_writeback(pages[i]);
if (page_ops & PAGE_UNLOCK)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 6d4b938be986..ece9ce87edff 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -49,6 +49,7 @@
#define PAGE_SET_WRITEBACK (1 << 2)
#define PAGE_END_WRITEBACK (1 << 3)
#define PAGE_SET_PRIVATE2 (1 << 4)
+#define PAGE_SET_ERROR (1 << 5)
/*
* page->private values. Every page that is controlled by the extent
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 225302b39afb..6a98bddd8f33 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -287,8 +287,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
if (!em)
goto out;
- if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
- list_move(&em->list, &tree->modified_extents);
em->generation = gen;
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
em->mod_start = em->start;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 783a94355efd..84a2d1868271 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -413,7 +413,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
ret = 0;
fail:
while (ret < 0 && !list_empty(&tmplist)) {
- sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+ sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
list_del(&sums->list);
kfree(sums);
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a18ceabd99a8..e4090259569b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1428,7 +1428,7 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
u64 num_bytes;
int ret;
- ret = btrfs_start_nocow_write(root);
+ ret = btrfs_start_write_no_snapshoting(root);
if (!ret)
return -ENOSPC;
@@ -1451,7 +1451,7 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
if (ret <= 0) {
ret = 0;
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
} else {
*write_bytes = min_t(size_t, *write_bytes ,
num_bytes - pos + lockstart);
@@ -1543,7 +1543,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
btrfs_free_reserved_data_space(inode,
reserve_bytes);
else
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
break;
}
@@ -1632,7 +1632,7 @@ again:
release_bytes = 0;
if (only_release_metadata)
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
if (only_release_metadata && copied > 0) {
u64 lockstart = round_down(pos, root->sectorsize);
@@ -1661,7 +1661,7 @@ again:
if (release_bytes) {
if (only_release_metadata) {
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
btrfs_delalloc_release_metadata(inode, release_bytes);
} else {
btrfs_delalloc_release_space(inode, release_bytes);
@@ -1676,6 +1676,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
loff_t pos)
{
struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
ssize_t written;
ssize_t written_buffered;
loff_t endbyte;
@@ -1692,8 +1693,15 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
err = written_buffered;
goto out;
}
+ /*
+ * Ensure all data is persisted. We want the next direct IO read to be
+ * able to read what was just written.
+ */
endbyte = pos + written_buffered - 1;
- err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
+ err = btrfs_fdatawrite_range(inode, pos, endbyte);
+ if (err)
+ goto out;
+ err = filemap_fdatawait_range(inode->i_mapping, pos, endbyte);
if (err)
goto out;
written += written_buffered;
@@ -1854,10 +1862,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
int ret;
atomic_inc(&BTRFS_I(inode)->sync_writers);
- ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
- if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
- &BTRFS_I(inode)->runtime_flags))
- ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+ ret = btrfs_fdatawrite_range(inode, start, end);
atomic_dec(&BTRFS_I(inode)->sync_writers);
return ret;
@@ -2810,3 +2815,29 @@ int btrfs_auto_defrag_init(void)
return 0;
}
+
+int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end)
+{
+ int ret;
+
+ /*
+ * So with compression we will find and lock a dirty page and clear the
+ * first one as dirty, setup an async extent, and immediately return
+ * with the entire range locked but with nobody actually marked with
+ * writeback. So we can't just filemap_write_and_wait_range() and
+ * expect it to work since it will just kick off a thread to do the
+ * actual work. So we need to call filemap_fdatawrite_range _again_
+ * since it will wait on the page lock, which won't be unlocked until
+ * after the pages have been marked as writeback and so we're good to go
+ * from there. We have to do this otherwise we'll miss the ordered
+ * extents and that results in badness. Please Josef, do not think you
+ * know better and pull this out at some point in the future, it is
+ * right and you are wrong.
+ */
+ ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+ if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+
+ return ret;
+}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 33848196550e..d6c03f7f136b 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -27,10 +27,17 @@
#include "disk-io.h"
#include "extent_io.h"
#include "inode-map.h"
+#include "volumes.h"
#define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8)
#define MAX_CACHE_BYTES_PER_GIG (32 * 1024)
+struct btrfs_trim_range {
+ u64 start;
+ u64 bytes;
+ struct list_head list;
+};
+
static int link_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info);
static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
@@ -881,6 +888,7 @@ int write_cache_extent_entries(struct io_ctl *io_ctl,
int ret;
struct btrfs_free_cluster *cluster = NULL;
struct rb_node *node = rb_first(&ctl->free_space_offset);
+ struct btrfs_trim_range *trim_entry;
/* Get the cluster for this block_group if it exists */
if (block_group && !list_empty(&block_group->cluster_list)) {
@@ -916,6 +924,21 @@ int write_cache_extent_entries(struct io_ctl *io_ctl,
cluster = NULL;
}
}
+
+ /*
+ * Make sure we don't miss any range that was removed from our rbtree
+ * because trimming is running. Otherwise after a umount+mount (or crash
+ * after committing the transaction) we would leak free space and get
+ * an inconsistent free space cache report from fsck.
+ */
+ list_for_each_entry(trim_entry, &ctl->trimming_ranges, list) {
+ ret = io_ctl_add_entry(io_ctl, trim_entry->start,
+ trim_entry->bytes, NULL);
+ if (ret)
+ goto fail;
+ *entries += 1;
+ }
+
return 0;
fail:
return -ENOSPC;
@@ -1135,12 +1158,15 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
io_ctl_set_generation(&io_ctl, trans->transid);
+ mutex_lock(&ctl->cache_writeout_mutex);
/* Write out the extent entries in the free space cache */
ret = write_cache_extent_entries(&io_ctl, ctl,
block_group, &entries, &bitmaps,
&bitmap_list);
- if (ret)
+ if (ret) {
+ mutex_unlock(&ctl->cache_writeout_mutex);
goto out_nospc;
+ }
/*
* Some spaces that are freed in the current transaction are pinned,
@@ -1148,11 +1174,18 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
* committed, we shouldn't lose them.
*/
ret = write_pinned_extent_entries(root, block_group, &io_ctl, &entries);
- if (ret)
+ if (ret) {
+ mutex_unlock(&ctl->cache_writeout_mutex);
goto out_nospc;
+ }
- /* At last, we write out all the bitmaps. */
+ /*
+ * At last, we write out all the bitmaps and keep cache_writeout_mutex
+ * locked while doing it because a concurrent trim can be manipulating
+ * or freeing the bitmap.
+ */
ret = write_bitmap_entries(&io_ctl, &bitmap_list);
+ mutex_unlock(&ctl->cache_writeout_mutex);
if (ret)
goto out_nospc;
@@ -2295,6 +2328,8 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
ctl->start = block_group->key.objectid;
ctl->private = block_group;
ctl->op = &free_space_op;
+ INIT_LIST_HEAD(&ctl->trimming_ranges);
+ mutex_init(&ctl->cache_writeout_mutex);
/*
* we only want to have 32k of ram per block group for keeping
@@ -2911,10 +2946,12 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
static int do_trimming(struct btrfs_block_group_cache *block_group,
u64 *total_trimmed, u64 start, u64 bytes,
- u64 reserved_start, u64 reserved_bytes)
+ u64 reserved_start, u64 reserved_bytes,
+ struct btrfs_trim_range *trim_entry)
{
struct btrfs_space_info *space_info = block_group->space_info;
struct btrfs_fs_info *fs_info = block_group->fs_info;
+ struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
int ret;
int update = 0;
u64 trimmed = 0;
@@ -2929,12 +2966,15 @@ static int do_trimming(struct btrfs_block_group_cache *block_group,
spin_unlock(&block_group->lock);
spin_unlock(&space_info->lock);
- ret = btrfs_error_discard_extent(fs_info->extent_root,
- start, bytes, &trimmed);
+ ret = btrfs_discard_extent(fs_info->extent_root,
+ start, bytes, &trimmed);
if (!ret)
*total_trimmed += trimmed;
+ mutex_lock(&ctl->cache_writeout_mutex);
btrfs_add_free_space(block_group, reserved_start, reserved_bytes);
+ list_del(&trim_entry->list);
+ mutex_unlock(&ctl->cache_writeout_mutex);
if (update) {
spin_lock(&space_info->lock);
@@ -2962,16 +3002,21 @@ static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
u64 bytes;
while (start < end) {
+ struct btrfs_trim_range trim_entry;
+
+ mutex_lock(&ctl->cache_writeout_mutex);
spin_lock(&ctl->tree_lock);
if (ctl->free_space < minlen) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
break;
}
entry = tree_search_offset(ctl, start, 0, 1);
if (!entry) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
break;
}
@@ -2980,6 +3025,7 @@ static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
node = rb_next(&entry->offset_index);
if (!node) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
goto out;
}
entry = rb_entry(node, struct btrfs_free_space,
@@ -2988,6 +3034,7 @@ static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
if (entry->offset >= end) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
break;
}
@@ -2997,6 +3044,7 @@ static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
bytes = min(extent_start + extent_bytes, end) - start;
if (bytes < minlen) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
goto next;
}
@@ -3004,9 +3052,13 @@ static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
kmem_cache_free(btrfs_free_space_cachep, entry);
spin_unlock(&ctl->tree_lock);
+ trim_entry.start = extent_start;
+ trim_entry.bytes = extent_bytes;
+ list_add_tail(&trim_entry.list, &ctl->trimming_ranges);
+ mutex_unlock(&ctl->cache_writeout_mutex);
ret = do_trimming(block_group, total_trimmed, start, bytes,
- extent_start, extent_bytes);
+ extent_start, extent_bytes, &trim_entry);
if (ret)
break;
next:
@@ -3035,17 +3087,21 @@ static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
while (offset < end) {
bool next_bitmap = false;
+ struct btrfs_trim_range trim_entry;
+ mutex_lock(&ctl->cache_writeout_mutex);
spin_lock(&ctl->tree_lock);
if (ctl->free_space < minlen) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
break;
}
entry = tree_search_offset(ctl, offset, 1, 0);
if (!entry) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
next_bitmap = true;
goto next;
}
@@ -3054,6 +3110,7 @@ static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
ret2 = search_bitmap(ctl, entry, &start, &bytes);
if (ret2 || start >= end) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
next_bitmap = true;
goto next;
}
@@ -3061,6 +3118,7 @@ static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
bytes = min(bytes, end - start);
if (bytes < minlen) {
spin_unlock(&ctl->tree_lock);
+ mutex_unlock(&ctl->cache_writeout_mutex);
goto next;
}
@@ -3069,9 +3127,13 @@ static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
free_bitmap(ctl, entry);
spin_unlock(&ctl->tree_lock);
+ trim_entry.start = start;
+ trim_entry.bytes = bytes;
+ list_add_tail(&trim_entry.list, &ctl->trimming_ranges);
+ mutex_unlock(&ctl->cache_writeout_mutex);
ret = do_trimming(block_group, total_trimmed, start, bytes,
- start, bytes);
+ start, bytes, &trim_entry);
if (ret)
break;
next:
@@ -3101,11 +3163,54 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
*trimmed = 0;
+ spin_lock(&block_group->lock);
+ if (block_group->removed) {
+ spin_unlock(&block_group->lock);
+ return 0;
+ }
+ atomic_inc(&block_group->trimming);
+ spin_unlock(&block_group->lock);
+
ret = trim_no_bitmap(block_group, trimmed, start, end, minlen);
if (ret)
- return ret;
+ goto out;
ret = trim_bitmaps(block_group, trimmed, start, end, minlen);
+out:
+ spin_lock(&block_group->lock);
+ if (atomic_dec_and_test(&block_group->trimming) &&
+ block_group->removed) {
+ struct extent_map_tree *em_tree;
+ struct extent_map *em;
+
+ spin_unlock(&block_group->lock);
+
+ lock_chunks(block_group->fs_info->chunk_root);
+ em_tree = &block_group->fs_info->mapping_tree.map_tree;
+ write_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, block_group->key.objectid,
+ 1);
+ BUG_ON(!em); /* logic error, can't happen */
+ /*
+ * remove_extent_mapping() will delete us from the pinned_chunks
+ * list, which is protected by the chunk mutex.
+ */
+ remove_extent_mapping(em_tree, em);
+ write_unlock(&em_tree->lock);
+ unlock_chunks(block_group->fs_info->chunk_root);
+
+ /* once for us and once for the tree */
+ free_extent_map(em);
+ free_extent_map(em);
+
+ /*
+ * We've left one free space entry and other tasks trimming
+ * this block group have left 1 entry each one. Free them.
+ */
+ __btrfs_remove_free_space_cache(block_group->free_space_ctl);
+ } else {
+ spin_unlock(&block_group->lock);
+ }
return ret;
}
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 0cf4977ef70d..88b2238a0aed 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -38,6 +38,8 @@ struct btrfs_free_space_ctl {
u64 start;
struct btrfs_free_space_op *op;
void *private;
+ struct mutex cache_writeout_mutex;
+ struct list_head trimming_ranges;
};
struct btrfs_free_space_op {
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 83d646bd2e4b..74faea3a516e 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -178,7 +178,7 @@ static void start_caching(struct btrfs_root *root)
root->root_key.objectid);
if (IS_ERR(tsk)) {
btrfs_warn(root->fs_info, "failed to start inode caching task");
- btrfs_clear_and_info(root, CHANGE_INODE_CACHE,
+ btrfs_clear_pending_and_info(root->fs_info, INODE_MAP_CACHE,
"disabling inode map caching");
}
}
@@ -364,6 +364,8 @@ void btrfs_init_free_ino_ctl(struct btrfs_root *root)
ctl->start = 0;
ctl->private = NULL;
ctl->op = &free_ino_op;
+ INIT_LIST_HEAD(&ctl->trimming_ranges);
+ mutex_init(&ctl->cache_writeout_mutex);
/*
* Initially we allow to use 16K of ram to cache chunks of
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d23362f4464e..e687bb0dc73a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -382,7 +382,7 @@ static inline int inode_need_compress(struct inode *inode)
* are written in the same order that the flusher thread sent them
* down.
*/
-static noinline int compress_file_range(struct inode *inode,
+static noinline void compress_file_range(struct inode *inode,
struct page *locked_page,
u64 start, u64 end,
struct async_cow *async_cow,
@@ -411,14 +411,6 @@ static noinline int compress_file_range(struct inode *inode,
(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
btrfs_add_inode_defrag(NULL, inode);
- /*
- * skip compression for a small file range(<=blocksize) that
- * isn't an inline extent, since it dosen't save disk space at all.
- */
- if ((end - start + 1) <= blocksize &&
- (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
- goto cleanup_and_bail_uncompressed;
-
actual_end = min_t(u64, isize, end + 1);
again:
will_compress = 0;
@@ -440,6 +432,14 @@ again:
total_compressed = actual_end - start;
+ /*
+ * skip compression for a small file range(<=blocksize) that
+ * isn't an inline extent, since it dosen't save disk space at all.
+ */
+ if (total_compressed <= blocksize &&
+ (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
+ goto cleanup_and_bail_uncompressed;
+
/* we want to make sure that amount of ram required to uncompress
* an extent is reasonable, so we limit the total size in ram
* of a compressed extent to 128k. This is a crucial number
@@ -527,7 +527,10 @@ cont:
if (ret <= 0) {
unsigned long clear_flags = EXTENT_DELALLOC |
EXTENT_DEFRAG;
+ unsigned long page_error_op;
+
clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0;
+ page_error_op = ret < 0 ? PAGE_SET_ERROR : 0;
/*
* inline extent creation worked or returned error,
@@ -538,6 +541,7 @@ cont:
clear_flags, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK |
+ page_error_op |
PAGE_END_WRITEBACK);
goto free_pages_out;
}
@@ -620,8 +624,7 @@ cleanup_and_bail_uncompressed:
*num_added += 1;
}
-out:
- return ret;
+ return;
free_pages_out:
for (i = 0; i < nr_pages_ret; i++) {
@@ -629,8 +632,22 @@ free_pages_out:
page_cache_release(pages[i]);
}
kfree(pages);
+}
- goto out;
+static void free_async_extent_pages(struct async_extent *async_extent)
+{
+ int i;
+
+ if (!async_extent->pages)
+ return;
+
+ for (i = 0; i < async_extent->nr_pages; i++) {
+ WARN_ON(async_extent->pages[i]->mapping);
+ page_cache_release(async_extent->pages[i]);
+ }
+ kfree(async_extent->pages);
+ async_extent->nr_pages = 0;
+ async_extent->pages = NULL;
}
/*
@@ -639,7 +656,7 @@ free_pages_out:
* queued. We walk all the async extents created by compress_file_range
* and send them down to the disk.
*/
-static noinline int submit_compressed_extents(struct inode *inode,
+static noinline void submit_compressed_extents(struct inode *inode,
struct async_cow *async_cow)
{
struct async_extent *async_extent;
@@ -651,9 +668,6 @@ static noinline int submit_compressed_extents(struct inode *inode,
struct extent_io_tree *io_tree;
int ret = 0;
- if (list_empty(&async_cow->extents))
- return 0;
-
again:
while (!list_empty(&async_cow->extents)) {
async_extent = list_entry(async_cow->extents.next,
@@ -709,15 +723,7 @@ retry:
async_extent->compressed_size,
0, alloc_hint, &ins, 1, 1);
if (ret) {
- int i;
-
- for (i = 0; i < async_extent->nr_pages; i++) {
- WARN_ON(async_extent->pages[i]->mapping);
- page_cache_release(async_extent->pages[i]);
- }
- kfree(async_extent->pages);
- async_extent->nr_pages = 0;
- async_extent->pages = NULL;
+ free_async_extent_pages(async_extent);
if (ret == -ENOSPC) {
unlock_extent(io_tree, async_extent->start,
@@ -814,15 +820,26 @@ retry:
ins.objectid,
ins.offset, async_extent->pages,
async_extent->nr_pages);
+ if (ret) {
+ struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+ struct page *p = async_extent->pages[0];
+ const u64 start = async_extent->start;
+ const u64 end = start + async_extent->ram_size - 1;
+
+ p->mapping = inode->i_mapping;
+ tree->ops->writepage_end_io_hook(p, start, end,
+ NULL, 0);
+ p->mapping = NULL;
+ extent_clear_unlock_delalloc(inode, start, end, NULL, 0,
+ PAGE_END_WRITEBACK |
+ PAGE_SET_ERROR);
+ free_async_extent_pages(async_extent);
+ }
alloc_hint = ins.objectid + ins.offset;
kfree(async_extent);
- if (ret)
- goto out;
cond_resched();
}
- ret = 0;
-out:
- return ret;
+ return;
out_free_reserve:
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_free:
@@ -832,7 +849,9 @@ out_free:
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
- PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
+ PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
+ PAGE_SET_ERROR);
+ free_async_extent_pages(async_extent);
kfree(async_extent);
goto again;
}
@@ -1318,7 +1337,7 @@ next_slot:
* we fall into common COW way.
*/
if (!nolock) {
- err = btrfs_start_nocow_write(root);
+ err = btrfs_start_write_no_snapshoting(root);
if (!err)
goto out_check;
}
@@ -1342,7 +1361,7 @@ out_check:
if (extent_end <= start) {
path->slots[0]++;
if (!nolock && nocow)
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
goto next_slot;
}
if (!nocow) {
@@ -1362,7 +1381,7 @@ out_check:
page_started, nr_written, 1);
if (ret) {
if (!nolock && nocow)
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
goto error;
}
cow_start = (u64)-1;
@@ -1413,7 +1432,7 @@ out_check:
num_bytes);
if (ret) {
if (!nolock && nocow)
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
goto error;
}
}
@@ -1424,7 +1443,7 @@ out_check:
EXTENT_DELALLOC, PAGE_UNLOCK |
PAGE_SET_PRIVATE2);
if (!nolock && nocow)
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
if (cur_offset > end)
break;
@@ -4580,6 +4599,26 @@ next:
return err;
}
+static int wait_snapshoting_atomic_t(atomic_t *a)
+{
+ schedule();
+ return 0;
+}
+
+static void wait_for_snapshot_creation(struct btrfs_root *root)
+{
+ while (true) {
+ int ret;
+
+ ret = btrfs_start_write_no_snapshoting(root);
+ if (ret)
+ break;
+ wait_on_atomic_t(&root->will_be_snapshoted,
+ wait_snapshoting_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+ }
+}
+
static int btrfs_setsize(struct inode *inode, struct iattr *attr)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -4604,17 +4643,30 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
if (newsize > oldsize) {
truncate_pagecache(inode, newsize);
+ /*
+ * Don't do an expanding truncate while snapshoting is ongoing.
+ * This is to ensure the snapshot captures a fully consistent
+ * state of this file - if the snapshot captures this expanding
+ * truncation, it must capture all writes that happened before
+ * this truncation.
+ */
+ wait_for_snapshot_creation(root);
ret = btrfs_cont_expand(inode, oldsize, newsize);
- if (ret)
+ if (ret) {
+ btrfs_end_write_no_snapshoting(root);
return ret;
+ }
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
+ btrfs_end_write_no_snapshoting(root);
return PTR_ERR(trans);
+ }
i_size_write(inode, newsize);
btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
ret = btrfs_update_inode(trans, root, inode);
+ btrfs_end_write_no_snapshoting(root);
btrfs_end_transaction(trans, root);
} else {
@@ -5303,7 +5355,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
return ERR_CAST(inode);
}
- return d_materialise_unique(dentry, inode);
+ return d_splice_alias(inode, dentry);
}
unsigned char btrfs_filetype_table[] = {
@@ -7000,9 +7052,12 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
btrfs_put_ordered_extent(ordered);
} else {
/* Screw you mmap */
- ret = filemap_write_and_wait_range(inode->i_mapping,
- lockstart,
- lockend);
+ ret = btrfs_fdatawrite_range(inode, lockstart, lockend);
+ if (ret)
+ break;
+ ret = filemap_fdatawait_range(inode->i_mapping,
+ lockstart,
+ lockend);
if (ret)
break;
@@ -9442,6 +9497,21 @@ out_inode:
}
+/* Inspired by filemap_check_errors() */
+int btrfs_inode_check_errors(struct inode *inode)
+{
+ int ret = 0;
+
+ if (test_bit(AS_ENOSPC, &inode->i_mapping->flags) &&
+ test_and_clear_bit(AS_ENOSPC, &inode->i_mapping->flags))
+ ret = -ENOSPC;
+ if (test_bit(AS_EIO, &inode->i_mapping->flags) &&
+ test_and_clear_bit(AS_EIO, &inode->i_mapping->flags))
+ ret = -EIO;
+
+ return ret;
+}
+
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4399f0c3a4ce..d49fe8a0f6b5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -617,7 +617,7 @@ fail:
return ret;
}
-static void btrfs_wait_nocow_write(struct btrfs_root *root)
+static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
{
s64 writers;
DEFINE_WAIT(wait);
@@ -649,7 +649,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
atomic_inc(&root->will_be_snapshoted);
smp_mb__after_atomic();
- btrfs_wait_nocow_write(root);
+ btrfs_wait_for_no_snapshoting_writes(root);
ret = btrfs_start_delalloc_inodes(root, 0);
if (ret)
@@ -717,35 +717,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (ret)
goto fail;
- /*
- * If orphan cleanup did remove any orphans, it means the tree was
- * modified and therefore the commit root is not the same as the
- * current root anymore. This is a problem, because send uses the
- * commit root and therefore can see inode items that don't exist
- * in the current root anymore, and for example make calls to
- * btrfs_iget, which will do tree lookups based on the current root
- * and not on the commit root. Those lookups will fail, returning a
- * -ESTALE error, and making send fail with that error. So make sure
- * a send does not see any orphans we have just removed, and that it
- * will see the same inodes regardless of whether a transaction
- * commit happened before it started (meaning that the commit root
- * will be the same as the current root) or not.
- */
- if (readonly && pending_snapshot->snap->node !=
- pending_snapshot->snap->commit_root) {
- trans = btrfs_join_transaction(pending_snapshot->snap);
- if (IS_ERR(trans) && PTR_ERR(trans) != -ENOENT) {
- ret = PTR_ERR(trans);
- goto fail;
- }
- if (!IS_ERR(trans)) {
- ret = btrfs_commit_transaction(trans,
- pending_snapshot->snap);
- if (ret)
- goto fail;
- }
- }
-
inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
@@ -761,7 +732,8 @@ fail:
free:
kfree(pending_snapshot);
out:
- atomic_dec(&root->will_be_snapshoted);
+ if (atomic_dec_and_test(&root->will_be_snapshoted))
+ wake_up_atomic_t(&root->will_be_snapshoted);
return ret;
}
@@ -5296,7 +5268,7 @@ long btrfs_ioctl(struct file *file, unsigned int
ret = btrfs_start_delalloc_roots(root->fs_info, 0, -1);
if (ret)
return ret;
- ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
+ ret = btrfs_sync_fs(file_inode(file)->i_sb, 1);
/*
* The transaction thread may want to do more work,
* namely it pokes the cleaner ktread that will start
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 5665d2149249..f8229ef1b46d 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -128,6 +128,26 @@ again:
}
/*
+ * take a spinning read lock.
+ * returns 1 if we get the read lock and 0 if we don't
+ * this won't wait for blocking writers
+ */
+int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
+{
+ if (atomic_read(&eb->blocking_writers))
+ return 0;
+
+ read_lock(&eb->lock);
+ if (atomic_read(&eb->blocking_writers)) {
+ read_unlock(&eb->lock);
+ return 0;
+ }
+ atomic_inc(&eb->read_locks);
+ atomic_inc(&eb->spinning_readers);
+ return 1;
+}
+
+/*
* returns 1 if we get the read lock and 0 if we don't
* this won't wait for blocking writers
*/
@@ -158,9 +178,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
atomic_read(&eb->blocking_readers))
return 0;
- if (!write_trylock(&eb->lock))
- return 0;
-
+ write_lock(&eb->lock);
if (atomic_read(&eb->blocking_writers) ||
atomic_read(&eb->blocking_readers)) {
write_unlock(&eb->lock);
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index b81e0e9a4894..c44a9d5f5362 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -35,6 +35,8 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw);
void btrfs_assert_tree_locked(struct extent_buffer *eb);
int btrfs_try_tree_read_lock(struct extent_buffer *eb);
int btrfs_try_tree_write_lock(struct extent_buffer *eb);
+int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
+
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
{
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 78285f30909e..617553cdb7d3 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -373,6 +373,8 @@ cont:
}
done:
kunmap(pages_in[page_in_index]);
+ if (!ret)
+ btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
return ret;
}
@@ -410,10 +412,23 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
goto out;
}
+ /*
+ * the caller is already checking against PAGE_SIZE, but lets
+ * move this check closer to the memcpy/memset
+ */
+ destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
kaddr = kmap_atomic(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
+
+ /*
+ * btrfs_getblock is doing a zero on the tail of the page too,
+ * but this will cover anything missing from the decompressed
+ * data.
+ */
+ if (bytes < destlen)
+ memset(kaddr+bytes, 0, destlen-bytes);
kunmap_atomic(kaddr);
out:
return ret;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index ac734ec4cc20..534544e08f76 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -220,6 +220,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
INIT_LIST_HEAD(&entry->work_list);
init_completion(&entry->completion);
INIT_LIST_HEAD(&entry->log_list);
+ INIT_LIST_HEAD(&entry->trans_list);
trace_btrfs_ordered_extent_add(inode, entry);
@@ -431,19 +432,31 @@ out:
/* Needs to either be called under a log transaction or the log_mutex */
void btrfs_get_logged_extents(struct inode *inode,
- struct list_head *logged_list)
+ struct list_head *logged_list,
+ const loff_t start,
+ const loff_t end)
{
struct btrfs_ordered_inode_tree *tree;
struct btrfs_ordered_extent *ordered;
struct rb_node *n;
+ struct rb_node *prev;
tree = &BTRFS_I(inode)->ordered_tree;
spin_lock_irq(&tree->lock);
- for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
+ n = __tree_search(&tree->tree, end, &prev);
+ if (!n)
+ n = prev;
+ for (; n; n = rb_prev(n)) {
ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
+ if (ordered->file_offset > end)
+ continue;
+ if (entry_end(ordered) <= start)
+ break;
if (!list_empty(&ordered->log_list))
continue;
- list_add_tail(&ordered->log_list, logged_list);
+ if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+ continue;
+ list_add(&ordered->log_list, logged_list);
atomic_inc(&ordered->refs);
}
spin_unlock_irq(&tree->lock);
@@ -472,7 +485,8 @@ void btrfs_submit_logged_extents(struct list_head *logged_list,
spin_unlock_irq(&log->log_extents_lock[index]);
}
-void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
+void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
+ struct btrfs_root *log, u64 transid)
{
struct btrfs_ordered_extent *ordered;
int index = transid % 2;
@@ -497,7 +511,8 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
&ordered->flags));
- btrfs_put_ordered_extent(ordered);
+ if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+ list_add_tail(&ordered->trans_list, &trans->ordered);
spin_lock_irq(&log->log_extents_lock[index]);
}
spin_unlock_irq(&log->log_extents_lock[index]);
@@ -725,30 +740,10 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
/* start IO across the range first to instantiate any delalloc
* extents
*/
- ret = filemap_fdatawrite_range(inode->i_mapping, start, orig_end);
+ ret = btrfs_fdatawrite_range(inode, start, orig_end);
if (ret)
return ret;
- /*
- * So with compression we will find and lock a dirty page and clear the
- * first one as dirty, setup an async extent, and immediately return
- * with the entire range locked but with nobody actually marked with
- * writeback. So we can't just filemap_write_and_wait_range() and
- * expect it to work since it will just kick off a thread to do the
- * actual work. So we need to call filemap_fdatawrite_range _again_
- * since it will wait on the page lock, which won't be unlocked until
- * after the pages have been marked as writeback and so we're good to go
- * from there. We have to do this otherwise we'll miss the ordered
- * extents and that results in badness. Please Josef, do not think you
- * know better and pull this out at some point in the future, it is
- * right and you are wrong.
- */
- if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
- &BTRFS_I(inode)->runtime_flags)) {
- ret = filemap_fdatawrite_range(inode->i_mapping, start,
- orig_end);
- if (ret)
- return ret;
- }
+
ret = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
if (ret)
return ret;
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index d81a274d621e..e96cd4ccd805 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -71,6 +71,8 @@ struct btrfs_ordered_sum {
ordered extent */
#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
+#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent
+ * in the logging code. */
struct btrfs_ordered_extent {
/* logical offset in the file */
u64 file_offset;
@@ -121,6 +123,9 @@ struct btrfs_ordered_extent {
/* If we need to wait on this to be done */
struct list_head log_list;
+ /* If the transaction needs to wait on this ordered extent */
+ struct list_head trans_list;
+
/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
wait_queue_head_t wait;
@@ -193,11 +198,14 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr);
void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr);
void btrfs_get_logged_extents(struct inode *inode,
- struct list_head *logged_list);
+ struct list_head *logged_list,
+ const loff_t start,
+ const loff_t end);
void btrfs_put_logged_extents(struct list_head *logged_list);
void btrfs_submit_logged_extents(struct list_head *logged_list,
struct btrfs_root *log);
-void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid);
+void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
+ struct btrfs_root *log, u64 transid);
void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
int __init ordered_data_init(void);
void ordered_data_exit(void);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 6a41631cb959..8ab2a17bbba8 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -58,9 +58,23 @@
*/
#define RBIO_CACHE_READY_BIT 3
+/*
+ * bbio and raid_map is managed by the caller, so we shouldn't free
+ * them here. And besides that, all rbios with this flag should not
+ * be cached, because we need raid_map to check the rbios' stripe
+ * is the same or not, but it is very likely that the caller has
+ * free raid_map, so don't cache those rbios.
+ */
+#define RBIO_HOLD_BBIO_MAP_BIT 4
#define RBIO_CACHE_SIZE 1024
+enum btrfs_rbio_ops {
+ BTRFS_RBIO_WRITE = 0,
+ BTRFS_RBIO_READ_REBUILD = 1,
+ BTRFS_RBIO_PARITY_SCRUB = 2,
+};
+
struct btrfs_raid_bio {
struct btrfs_fs_info *fs_info;
struct btrfs_bio *bbio;
@@ -117,13 +131,16 @@ struct btrfs_raid_bio {
/* number of data stripes (no p/q) */
int nr_data;
+ int real_stripes;
+
+ int stripe_npages;
/*
* set if we're doing a parity rebuild
* for a read from higher up, which is handled
* differently from a parity rebuild as part of
* rmw
*/
- int read_rebuild;
+ enum btrfs_rbio_ops operation;
/* first bad stripe */
int faila;
@@ -131,6 +148,7 @@ struct btrfs_raid_bio {
/* second bad stripe (for raid6 use) */
int failb;
+ int scrubp;
/*
* number of pages needed to represent the full
* stripe
@@ -144,8 +162,13 @@ struct btrfs_raid_bio {
*/
int bio_list_bytes;
+ int generic_bio_cnt;
+
atomic_t refs;
+ atomic_t stripes_pending;
+
+ atomic_t error;
/*
* these are two arrays of pointers. We allocate the
* rbio big enough to hold them both and setup their
@@ -162,6 +185,11 @@ struct btrfs_raid_bio {
* here for faster lookup
*/
struct page **bio_pages;
+
+ /*
+ * bitmap to record which horizontal stripe has data
+ */
+ unsigned long *dbitmap;
};
static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
@@ -176,6 +204,10 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio);
static void index_rbio_pages(struct btrfs_raid_bio *rbio);
static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);
+static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
+ int need_check);
+static void async_scrub_parity(struct btrfs_raid_bio *rbio);
+
/*
* the stripe hash table is used for locking, and to collect
* bios in hopes of making a full stripe
@@ -324,6 +356,7 @@ static void merge_rbio(struct btrfs_raid_bio *dest,
{
bio_list_merge(&dest->bio_list, &victim->bio_list);
dest->bio_list_bytes += victim->bio_list_bytes;
+ dest->generic_bio_cnt += victim->generic_bio_cnt;
bio_list_init(&victim->bio_list);
}
@@ -577,11 +610,20 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
cur->raid_map[0])
return 0;
- /* reads can't merge with writes */
- if (last->read_rebuild !=
- cur->read_rebuild) {
+ /* we can't merge with different operations */
+ if (last->operation != cur->operation)
+ return 0;
+ /*
+ * We've need read the full stripe from the drive.
+ * check and repair the parity and write the new results.
+ *
+ * We're not allowed to add any new bios to the
+ * bio list here, anyone else that wants to
+ * change this stripe needs to do their own rmw.
+ */
+ if (last->operation == BTRFS_RBIO_PARITY_SCRUB ||
+ cur->operation == BTRFS_RBIO_PARITY_SCRUB)
return 0;
- }
return 1;
}
@@ -601,7 +643,7 @@ static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
*/
static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
{
- if (rbio->nr_data + 1 == rbio->bbio->num_stripes)
+ if (rbio->nr_data + 1 == rbio->real_stripes)
return NULL;
index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
@@ -772,11 +814,14 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
spin_unlock(&rbio->bio_list_lock);
spin_unlock_irqrestore(&h->lock, flags);
- if (next->read_rebuild)
+ if (next->operation == BTRFS_RBIO_READ_REBUILD)
async_read_rebuild(next);
- else {
+ else if (next->operation == BTRFS_RBIO_WRITE) {
steal_rbio(rbio, next);
async_rmw_stripe(next);
+ } else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
+ steal_rbio(rbio, next);
+ async_scrub_parity(next);
}
goto done_nolock;
@@ -796,6 +841,21 @@ done_nolock:
remove_rbio_from_cache(rbio);
}
+static inline void
+__free_bbio_and_raid_map(struct btrfs_bio *bbio, u64 *raid_map, int need)
+{
+ if (need) {
+ kfree(raid_map);
+ kfree(bbio);
+ }
+}
+
+static inline void free_bbio_and_raid_map(struct btrfs_raid_bio *rbio)
+{
+ __free_bbio_and_raid_map(rbio->bbio, rbio->raid_map,
+ !test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags));
+}
+
static void __free_raid_bio(struct btrfs_raid_bio *rbio)
{
int i;
@@ -814,8 +874,9 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio)
rbio->stripe_pages[i] = NULL;
}
}
- kfree(rbio->raid_map);
- kfree(rbio->bbio);
+
+ free_bbio_and_raid_map(rbio);
+
kfree(rbio);
}
@@ -833,6 +894,10 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate)
{
struct bio *cur = bio_list_get(&rbio->bio_list);
struct bio *next;
+
+ if (rbio->generic_bio_cnt)
+ btrfs_bio_counter_sub(rbio->fs_info, rbio->generic_bio_cnt);
+
free_raid_bio(rbio);
while (cur) {
@@ -858,13 +923,13 @@ static void raid_write_end_io(struct bio *bio, int err)
bio_put(bio);
- if (!atomic_dec_and_test(&rbio->bbio->stripes_pending))
+ if (!atomic_dec_and_test(&rbio->stripes_pending))
return;
err = 0;
/* OK, we have read all the stripes we need to. */
- if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
+ if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
err = -EIO;
rbio_orig_end_io(rbio, err, 0);
@@ -925,16 +990,16 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
{
struct btrfs_raid_bio *rbio;
int nr_data = 0;
- int num_pages = rbio_nr_pages(stripe_len, bbio->num_stripes);
+ int real_stripes = bbio->num_stripes - bbio->num_tgtdevs;
+ int num_pages = rbio_nr_pages(stripe_len, real_stripes);
+ int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE);
void *p;
- rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2,
+ rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
+ DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8),
GFP_NOFS);
- if (!rbio) {
- kfree(raid_map);
- kfree(bbio);
+ if (!rbio)
return ERR_PTR(-ENOMEM);
- }
bio_list_init(&rbio->bio_list);
INIT_LIST_HEAD(&rbio->plug_list);
@@ -946,9 +1011,13 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
rbio->fs_info = root->fs_info;
rbio->stripe_len = stripe_len;
rbio->nr_pages = num_pages;
+ rbio->real_stripes = real_stripes;
+ rbio->stripe_npages = stripe_npages;
rbio->faila = -1;
rbio->failb = -1;
atomic_set(&rbio->refs, 1);
+ atomic_set(&rbio->error, 0);
+ atomic_set(&rbio->stripes_pending, 0);
/*
* the stripe_pages and bio_pages array point to the extra
@@ -957,11 +1026,12 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
p = rbio + 1;
rbio->stripe_pages = p;
rbio->bio_pages = p + sizeof(struct page *) * num_pages;
+ rbio->dbitmap = p + sizeof(struct page *) * num_pages * 2;
- if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE)
- nr_data = bbio->num_stripes - 2;
+ if (raid_map[real_stripes - 1] == RAID6_Q_STRIPE)
+ nr_data = real_stripes - 2;
else
- nr_data = bbio->num_stripes - 1;
+ nr_data = real_stripes - 1;
rbio->nr_data = nr_data;
return rbio;
@@ -1073,7 +1143,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
{
if (rbio->faila >= 0 || rbio->failb >= 0) {
- BUG_ON(rbio->faila == rbio->bbio->num_stripes - 1);
+ BUG_ON(rbio->faila == rbio->real_stripes - 1);
__raid56_parity_recover(rbio);
} else {
finish_rmw(rbio);
@@ -1134,7 +1204,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
{
struct btrfs_bio *bbio = rbio->bbio;
- void *pointers[bbio->num_stripes];
+ void *pointers[rbio->real_stripes];
int stripe_len = rbio->stripe_len;
int nr_data = rbio->nr_data;
int stripe;
@@ -1148,11 +1218,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
bio_list_init(&bio_list);
- if (bbio->num_stripes - rbio->nr_data == 1) {
- p_stripe = bbio->num_stripes - 1;
- } else if (bbio->num_stripes - rbio->nr_data == 2) {
- p_stripe = bbio->num_stripes - 2;
- q_stripe = bbio->num_stripes - 1;
+ if (rbio->real_stripes - rbio->nr_data == 1) {
+ p_stripe = rbio->real_stripes - 1;
+ } else if (rbio->real_stripes - rbio->nr_data == 2) {
+ p_stripe = rbio->real_stripes - 2;
+ q_stripe = rbio->real_stripes - 1;
} else {
BUG();
}
@@ -1169,7 +1239,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
spin_unlock_irq(&rbio->bio_list_lock);
- atomic_set(&rbio->bbio->error, 0);
+ atomic_set(&rbio->error, 0);
/*
* now that we've set rmw_locked, run through the
@@ -1209,7 +1279,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
SetPageUptodate(p);
pointers[stripe++] = kmap(p);
- raid6_call.gen_syndrome(bbio->num_stripes, PAGE_SIZE,
+ raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE,
pointers);
} else {
/* raid5 */
@@ -1218,7 +1288,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
}
- for (stripe = 0; stripe < bbio->num_stripes; stripe++)
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++)
kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
}
@@ -1227,7 +1297,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
* higher layers (the bio_list in our rbio) and our p/q. Ignore
* everything else.
*/
- for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
struct page *page;
if (stripe < rbio->nr_data) {
@@ -1245,8 +1315,34 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
}
}
- atomic_set(&bbio->stripes_pending, bio_list_size(&bio_list));
- BUG_ON(atomic_read(&bbio->stripes_pending) == 0);
+ if (likely(!bbio->num_tgtdevs))
+ goto write_data;
+
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
+ if (!bbio->tgtdev_map[stripe])
+ continue;
+
+ for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ struct page *page;
+ if (stripe < rbio->nr_data) {
+ page = page_in_rbio(rbio, stripe, pagenr, 1);
+ if (!page)
+ continue;
+ } else {
+ page = rbio_stripe_page(rbio, stripe, pagenr);
+ }
+
+ ret = rbio_add_io_page(rbio, &bio_list, page,
+ rbio->bbio->tgtdev_map[stripe],
+ pagenr, rbio->stripe_len);
+ if (ret)
+ goto cleanup;
+ }
+ }
+
+write_data:
+ atomic_set(&rbio->stripes_pending, bio_list_size(&bio_list));
+ BUG_ON(atomic_read(&rbio->stripes_pending) == 0);
while (1) {
bio = bio_list_pop(&bio_list);
@@ -1283,7 +1379,8 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
stripe = &rbio->bbio->stripes[i];
stripe_start = stripe->physical;
if (physical >= stripe_start &&
- physical < stripe_start + rbio->stripe_len) {
+ physical < stripe_start + rbio->stripe_len &&
+ bio->bi_bdev == stripe->dev->bdev) {
return i;
}
}
@@ -1331,11 +1428,11 @@ static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed)
if (rbio->faila == -1) {
/* first failure on this rbio */
rbio->faila = failed;
- atomic_inc(&rbio->bbio->error);
+ atomic_inc(&rbio->error);
} else if (rbio->failb == -1) {
/* second failure on this rbio */
rbio->failb = failed;
- atomic_inc(&rbio->bbio->error);
+ atomic_inc(&rbio->error);
} else {
ret = -EIO;
}
@@ -1394,11 +1491,11 @@ static void raid_rmw_end_io(struct bio *bio, int err)
bio_put(bio);
- if (!atomic_dec_and_test(&rbio->bbio->stripes_pending))
+ if (!atomic_dec_and_test(&rbio->stripes_pending))
return;
err = 0;
- if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
+ if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
goto cleanup;
/*
@@ -1439,7 +1536,6 @@ static void async_read_rebuild(struct btrfs_raid_bio *rbio)
static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
{
int bios_to_read = 0;
- struct btrfs_bio *bbio = rbio->bbio;
struct bio_list bio_list;
int ret;
int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
@@ -1455,7 +1551,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
index_rbio_pages(rbio);
- atomic_set(&rbio->bbio->error, 0);
+ atomic_set(&rbio->error, 0);
/*
* build a list of bios to read all the missing parts of this
* stripe
@@ -1503,7 +1599,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
* the bbio may be freed once we submit the last bio. Make sure
* not to touch it after that
*/
- atomic_set(&bbio->stripes_pending, bios_to_read);
+ atomic_set(&rbio->stripes_pending, bios_to_read);
while (1) {
bio = bio_list_pop(&bio_list);
if (!bio)
@@ -1686,19 +1782,30 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
struct btrfs_raid_bio *rbio;
struct btrfs_plug_cb *plug = NULL;
struct blk_plug_cb *cb;
+ int ret;
rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
- if (IS_ERR(rbio))
+ if (IS_ERR(rbio)) {
+ __free_bbio_and_raid_map(bbio, raid_map, 1);
return PTR_ERR(rbio);
+ }
bio_list_add(&rbio->bio_list, bio);
rbio->bio_list_bytes = bio->bi_iter.bi_size;
+ rbio->operation = BTRFS_RBIO_WRITE;
+
+ btrfs_bio_counter_inc_noblocked(root->fs_info);
+ rbio->generic_bio_cnt = 1;
/*
* don't plug on full rbios, just get them out the door
* as quickly as we can
*/
- if (rbio_is_full(rbio))
- return full_stripe_write(rbio);
+ if (rbio_is_full(rbio)) {
+ ret = full_stripe_write(rbio);
+ if (ret)
+ btrfs_bio_counter_dec(root->fs_info);
+ return ret;
+ }
cb = blk_check_plugged(btrfs_raid_unplug, root->fs_info,
sizeof(*plug));
@@ -1709,10 +1816,13 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
INIT_LIST_HEAD(&plug->rbio_list);
}
list_add_tail(&rbio->plug_list, &plug->rbio_list);
+ ret = 0;
} else {
- return __raid56_parity_write(rbio);
+ ret = __raid56_parity_write(rbio);
+ if (ret)
+ btrfs_bio_counter_dec(root->fs_info);
}
- return 0;
+ return ret;
}
/*
@@ -1730,7 +1840,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
int err;
int i;
- pointers = kzalloc(rbio->bbio->num_stripes * sizeof(void *),
+ pointers = kzalloc(rbio->real_stripes * sizeof(void *),
GFP_NOFS);
if (!pointers) {
err = -ENOMEM;
@@ -1740,7 +1850,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
faila = rbio->faila;
failb = rbio->failb;
- if (rbio->read_rebuild) {
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD) {
spin_lock_irq(&rbio->bio_list_lock);
set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
spin_unlock_irq(&rbio->bio_list_lock);
@@ -1749,15 +1859,23 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
index_rbio_pages(rbio);
for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ /*
+ * Now we just use bitmap to mark the horizontal stripes in
+ * which we have data when doing parity scrub.
+ */
+ if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB &&
+ !test_bit(pagenr, rbio->dbitmap))
+ continue;
+
/* setup our array of pointers with pages
* from each stripe
*/
- for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
/*
* if we're rebuilding a read, we have to use
* pages from the bio list
*/
- if (rbio->read_rebuild &&
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD &&
(stripe == faila || stripe == failb)) {
page = page_in_rbio(rbio, stripe, pagenr, 0);
} else {
@@ -1767,7 +1885,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
}
/* all raid6 handling here */
- if (rbio->raid_map[rbio->bbio->num_stripes - 1] ==
+ if (rbio->raid_map[rbio->real_stripes - 1] ==
RAID6_Q_STRIPE) {
/*
@@ -1817,10 +1935,10 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
}
if (rbio->raid_map[failb] == RAID5_P_STRIPE) {
- raid6_datap_recov(rbio->bbio->num_stripes,
+ raid6_datap_recov(rbio->real_stripes,
PAGE_SIZE, faila, pointers);
} else {
- raid6_2data_recov(rbio->bbio->num_stripes,
+ raid6_2data_recov(rbio->real_stripes,
PAGE_SIZE, faila, failb,
pointers);
}
@@ -1850,7 +1968,7 @@ pstripe:
* know they can be trusted. If this was a read reconstruction,
* other endio functions will fiddle the uptodate bits
*/
- if (!rbio->read_rebuild) {
+ if (rbio->operation == BTRFS_RBIO_WRITE) {
for (i = 0; i < nr_pages; i++) {
if (faila != -1) {
page = rbio_stripe_page(rbio, faila, i);
@@ -1862,12 +1980,12 @@ pstripe:
}
}
}
- for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
/*
* if we're rebuilding a read, we have to use
* pages from the bio list
*/
- if (rbio->read_rebuild &&
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD &&
(stripe == faila || stripe == failb)) {
page = page_in_rbio(rbio, stripe, pagenr, 0);
} else {
@@ -1882,9 +2000,9 @@ cleanup:
kfree(pointers);
cleanup_io:
-
- if (rbio->read_rebuild) {
- if (err == 0)
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD) {
+ if (err == 0 &&
+ !test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags))
cache_rbio_pages(rbio);
else
clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
@@ -1893,7 +2011,13 @@ cleanup_io:
} else if (err == 0) {
rbio->faila = -1;
rbio->failb = -1;
- finish_rmw(rbio);
+
+ if (rbio->operation == BTRFS_RBIO_WRITE)
+ finish_rmw(rbio);
+ else if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB)
+ finish_parity_scrub(rbio, 0);
+ else
+ BUG();
} else {
rbio_orig_end_io(rbio, err, 0);
}
@@ -1917,10 +2041,10 @@ static void raid_recover_end_io(struct bio *bio, int err)
set_bio_pages_uptodate(bio);
bio_put(bio);
- if (!atomic_dec_and_test(&rbio->bbio->stripes_pending))
+ if (!atomic_dec_and_test(&rbio->stripes_pending))
return;
- if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
+ if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
rbio_orig_end_io(rbio, -EIO, 0);
else
__raid_recover_end_io(rbio);
@@ -1937,7 +2061,6 @@ static void raid_recover_end_io(struct bio *bio, int err)
static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
{
int bios_to_read = 0;
- struct btrfs_bio *bbio = rbio->bbio;
struct bio_list bio_list;
int ret;
int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
@@ -1951,16 +2074,16 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
if (ret)
goto cleanup;
- atomic_set(&rbio->bbio->error, 0);
+ atomic_set(&rbio->error, 0);
/*
* read everything that hasn't failed. Thanks to the
* stripe cache, it is possible that some or all of these
* pages are going to be uptodate.
*/
- for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
if (rbio->faila == stripe || rbio->failb == stripe) {
- atomic_inc(&rbio->bbio->error);
+ atomic_inc(&rbio->error);
continue;
}
@@ -1990,7 +2113,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
* were up to date, or we might have no bios to read because
* the devices were gone.
*/
- if (atomic_read(&rbio->bbio->error) <= rbio->bbio->max_errors) {
+ if (atomic_read(&rbio->error) <= rbio->bbio->max_errors) {
__raid_recover_end_io(rbio);
goto out;
} else {
@@ -2002,7 +2125,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
* the bbio may be freed once we submit the last bio. Make sure
* not to touch it after that
*/
- atomic_set(&bbio->stripes_pending, bios_to_read);
+ atomic_set(&rbio->stripes_pending, bios_to_read);
while (1) {
bio = bio_list_pop(&bio_list);
if (!bio)
@@ -2021,7 +2144,7 @@ out:
return 0;
cleanup:
- if (rbio->read_rebuild)
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD)
rbio_orig_end_io(rbio, -EIO, 0);
return -EIO;
}
@@ -2034,34 +2157,42 @@ cleanup:
*/
int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
struct btrfs_bio *bbio, u64 *raid_map,
- u64 stripe_len, int mirror_num)
+ u64 stripe_len, int mirror_num, int generic_io)
{
struct btrfs_raid_bio *rbio;
int ret;
rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
- if (IS_ERR(rbio))
+ if (IS_ERR(rbio)) {
+ __free_bbio_and_raid_map(bbio, raid_map, generic_io);
return PTR_ERR(rbio);
+ }
- rbio->read_rebuild = 1;
+ rbio->operation = BTRFS_RBIO_READ_REBUILD;
bio_list_add(&rbio->bio_list, bio);
rbio->bio_list_bytes = bio->bi_iter.bi_size;
rbio->faila = find_logical_bio_stripe(rbio, bio);
if (rbio->faila == -1) {
BUG();
- kfree(raid_map);
- kfree(bbio);
+ __free_bbio_and_raid_map(bbio, raid_map, generic_io);
kfree(rbio);
return -EIO;
}
+ if (generic_io) {
+ btrfs_bio_counter_inc_noblocked(root->fs_info);
+ rbio->generic_bio_cnt = 1;
+ } else {
+ set_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags);
+ }
+
/*
* reconstruct from the q stripe if they are
* asking for mirror 3
*/
if (mirror_num == 3)
- rbio->failb = bbio->num_stripes - 2;
+ rbio->failb = rbio->real_stripes - 2;
ret = lock_stripe_add(rbio);
@@ -2098,3 +2229,483 @@ static void read_rebuild_work(struct btrfs_work *work)
rbio = container_of(work, struct btrfs_raid_bio, work);
__raid56_parity_recover(rbio);
}
+
+/*
+ * The following code is used to scrub/replace the parity stripe
+ *
+ * Note: We need make sure all the pages that add into the scrub/replace
+ * raid bio are correct and not be changed during the scrub/replace. That
+ * is those pages just hold metadata or file data with checksum.
+ */
+
+struct btrfs_raid_bio *
+raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len, struct btrfs_device *scrub_dev,
+ unsigned long *dbitmap, int stripe_nsectors)
+{
+ struct btrfs_raid_bio *rbio;
+ int i;
+
+ rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
+ if (IS_ERR(rbio))
+ return NULL;
+ bio_list_add(&rbio->bio_list, bio);
+ /*
+ * This is a special bio which is used to hold the completion handler
+ * and make the scrub rbio is similar to the other types
+ */
+ ASSERT(!bio->bi_iter.bi_size);
+ rbio->operation = BTRFS_RBIO_PARITY_SCRUB;
+
+ for (i = 0; i < rbio->real_stripes; i++) {
+ if (bbio->stripes[i].dev == scrub_dev) {
+ rbio->scrubp = i;
+ break;
+ }
+ }
+
+ /* Now we just support the sectorsize equals to page size */
+ ASSERT(root->sectorsize == PAGE_SIZE);
+ ASSERT(rbio->stripe_npages == stripe_nsectors);
+ bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors);
+
+ return rbio;
+}
+
+void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio,
+ struct page *page, u64 logical)
+{
+ int stripe_offset;
+ int index;
+
+ ASSERT(logical >= rbio->raid_map[0]);
+ ASSERT(logical + PAGE_SIZE <= rbio->raid_map[0] +
+ rbio->stripe_len * rbio->nr_data);
+ stripe_offset = (int)(logical - rbio->raid_map[0]);
+ index = stripe_offset >> PAGE_CACHE_SHIFT;
+ rbio->bio_pages[index] = page;
+}
+
+/*
+ * We just scrub the parity that we have correct data on the same horizontal,
+ * so we needn't allocate all pages for all the stripes.
+ */
+static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
+{
+ int i;
+ int bit;
+ int index;
+ struct page *page;
+
+ for_each_set_bit(bit, rbio->dbitmap, rbio->stripe_npages) {
+ for (i = 0; i < rbio->real_stripes; i++) {
+ index = i * rbio->stripe_npages + bit;
+ if (rbio->stripe_pages[index])
+ continue;
+
+ page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (!page)
+ return -ENOMEM;
+ rbio->stripe_pages[index] = page;
+ ClearPageUptodate(page);
+ }
+ }
+ return 0;
+}
+
+/*
+ * end io function used by finish_rmw. When we finally
+ * get here, we've written a full stripe
+ */
+static void raid_write_parity_end_io(struct bio *bio, int err)
+{
+ struct btrfs_raid_bio *rbio = bio->bi_private;
+
+ if (err)
+ fail_bio_stripe(rbio, bio);
+
+ bio_put(bio);
+
+ if (!atomic_dec_and_test(&rbio->stripes_pending))
+ return;
+
+ err = 0;
+
+ if (atomic_read(&rbio->error))
+ err = -EIO;
+
+ rbio_orig_end_io(rbio, err, 0);
+}
+
+static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
+ int need_check)
+{
+ struct btrfs_bio *bbio = rbio->bbio;
+ void *pointers[rbio->real_stripes];
+ DECLARE_BITMAP(pbitmap, rbio->stripe_npages);
+ int nr_data = rbio->nr_data;
+ int stripe;
+ int pagenr;
+ int p_stripe = -1;
+ int q_stripe = -1;
+ struct page *p_page = NULL;
+ struct page *q_page = NULL;
+ struct bio_list bio_list;
+ struct bio *bio;
+ int is_replace = 0;
+ int ret;
+
+ bio_list_init(&bio_list);
+
+ if (rbio->real_stripes - rbio->nr_data == 1) {
+ p_stripe = rbio->real_stripes - 1;
+ } else if (rbio->real_stripes - rbio->nr_data == 2) {
+ p_stripe = rbio->real_stripes - 2;
+ q_stripe = rbio->real_stripes - 1;
+ } else {
+ BUG();
+ }
+
+ if (bbio->num_tgtdevs && bbio->tgtdev_map[rbio->scrubp]) {
+ is_replace = 1;
+ bitmap_copy(pbitmap, rbio->dbitmap, rbio->stripe_npages);
+ }
+
+ /*
+ * Because the higher layers(scrubber) are unlikely to
+ * use this area of the disk again soon, so don't cache
+ * it.
+ */
+ clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
+
+ if (!need_check)
+ goto writeback;
+
+ p_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (!p_page)
+ goto cleanup;
+ SetPageUptodate(p_page);
+
+ if (q_stripe != -1) {
+ q_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (!q_page) {
+ __free_page(p_page);
+ goto cleanup;
+ }
+ SetPageUptodate(q_page);
+ }
+
+ atomic_set(&rbio->error, 0);
+
+ for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
+ struct page *p;
+ void *parity;
+ /* first collect one page from each data stripe */
+ for (stripe = 0; stripe < nr_data; stripe++) {
+ p = page_in_rbio(rbio, stripe, pagenr, 0);
+ pointers[stripe] = kmap(p);
+ }
+
+ /* then add the parity stripe */
+ pointers[stripe++] = kmap(p_page);
+
+ if (q_stripe != -1) {
+
+ /*
+ * raid6, add the qstripe and call the
+ * library function to fill in our p/q
+ */
+ pointers[stripe++] = kmap(q_page);
+
+ raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE,
+ pointers);
+ } else {
+ /* raid5 */
+ memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+ run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE);
+ }
+
+ /* Check scrubbing pairty and repair it */
+ p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
+ parity = kmap(p);
+ if (memcmp(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE))
+ memcpy(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE);
+ else
+ /* Parity is right, needn't writeback */
+ bitmap_clear(rbio->dbitmap, pagenr, 1);
+ kunmap(p);
+
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++)
+ kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+ }
+
+ __free_page(p_page);
+ if (q_page)
+ __free_page(q_page);
+
+writeback:
+ /*
+ * time to start writing. Make bios for everything from the
+ * higher layers (the bio_list in our rbio) and our p/q. Ignore
+ * everything else.
+ */
+ for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
+ struct page *page;
+
+ page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
+ ret = rbio_add_io_page(rbio, &bio_list,
+ page, rbio->scrubp, pagenr, rbio->stripe_len);
+ if (ret)
+ goto cleanup;
+ }
+
+ if (!is_replace)
+ goto submit_write;
+
+ for_each_set_bit(pagenr, pbitmap, rbio->stripe_npages) {
+ struct page *page;
+
+ page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
+ ret = rbio_add_io_page(rbio, &bio_list, page,
+ bbio->tgtdev_map[rbio->scrubp],
+ pagenr, rbio->stripe_len);
+ if (ret)
+ goto cleanup;
+ }
+
+submit_write:
+ nr_data = bio_list_size(&bio_list);
+ if (!nr_data) {
+ /* Every parity is right */
+ rbio_orig_end_io(rbio, 0, 0);
+ return;
+ }
+
+ atomic_set(&rbio->stripes_pending, nr_data);
+
+ while (1) {
+ bio = bio_list_pop(&bio_list);
+ if (!bio)
+ break;
+
+ bio->bi_private = rbio;
+ bio->bi_end_io = raid_write_parity_end_io;
+ BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
+ submit_bio(WRITE, bio);
+ }
+ return;
+
+cleanup:
+ rbio_orig_end_io(rbio, -EIO, 0);
+}
+
+static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe)
+{
+ if (stripe >= 0 && stripe < rbio->nr_data)
+ return 1;
+ return 0;
+}
+
+/*
+ * While we're doing the parity check and repair, we could have errors
+ * in reading pages off the disk. This checks for errors and if we're
+ * not able to read the page it'll trigger parity reconstruction. The
+ * parity scrub will be finished after we've reconstructed the failed
+ * stripes
+ */
+static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
+{
+ if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+ goto cleanup;
+
+ if (rbio->faila >= 0 || rbio->failb >= 0) {
+ int dfail = 0, failp = -1;
+
+ if (is_data_stripe(rbio, rbio->faila))
+ dfail++;
+ else if (is_parity_stripe(rbio->faila))
+ failp = rbio->faila;
+
+ if (is_data_stripe(rbio, rbio->failb))
+ dfail++;
+ else if (is_parity_stripe(rbio->failb))
+ failp = rbio->failb;
+
+ /*
+ * Because we can not use a scrubbing parity to repair
+ * the data, so the capability of the repair is declined.
+ * (In the case of RAID5, we can not repair anything)
+ */
+ if (dfail > rbio->bbio->max_errors - 1)
+ goto cleanup;
+
+ /*
+ * If all data is good, only parity is correctly, just
+ * repair the parity.
+ */
+ if (dfail == 0) {
+ finish_parity_scrub(rbio, 0);
+ return;
+ }
+
+ /*
+ * Here means we got one corrupted data stripe and one
+ * corrupted parity on RAID6, if the corrupted parity
+ * is scrubbing parity, luckly, use the other one to repair
+ * the data, or we can not repair the data stripe.
+ */
+ if (failp != rbio->scrubp)
+ goto cleanup;
+
+ __raid_recover_end_io(rbio);
+ } else {
+ finish_parity_scrub(rbio, 1);
+ }
+ return;
+
+cleanup:
+ rbio_orig_end_io(rbio, -EIO, 0);
+}
+
+/*
+ * end io for the read phase of the rmw cycle. All the bios here are physical
+ * stripe bios we've read from the disk so we can recalculate the parity of the
+ * stripe.
+ *
+ * This will usually kick off finish_rmw once all the bios are read in, but it
+ * may trigger parity reconstruction if we had any errors along the way
+ */
+static void raid56_parity_scrub_end_io(struct bio *bio, int err)
+{
+ struct btrfs_raid_bio *rbio = bio->bi_private;
+
+ if (err)
+ fail_bio_stripe(rbio, bio);
+ else
+ set_bio_pages_uptodate(bio);
+
+ bio_put(bio);
+
+ if (!atomic_dec_and_test(&rbio->stripes_pending))
+ return;
+
+ /*
+ * this will normally call finish_rmw to start our write
+ * but if there are any failed stripes we'll reconstruct
+ * from parity first
+ */
+ validate_rbio_for_parity_scrub(rbio);
+}
+
+static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
+{
+ int bios_to_read = 0;
+ struct bio_list bio_list;
+ int ret;
+ int pagenr;
+ int stripe;
+ struct bio *bio;
+
+ ret = alloc_rbio_essential_pages(rbio);
+ if (ret)
+ goto cleanup;
+
+ bio_list_init(&bio_list);
+
+ atomic_set(&rbio->error, 0);
+ /*
+ * build a list of bios to read all the missing parts of this
+ * stripe
+ */
+ for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
+ for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
+ struct page *page;
+ /*
+ * we want to find all the pages missing from
+ * the rbio and read them from the disk. If
+ * page_in_rbio finds a page in the bio list
+ * we don't need to read it off the stripe.
+ */
+ page = page_in_rbio(rbio, stripe, pagenr, 1);
+ if (page)
+ continue;
+
+ page = rbio_stripe_page(rbio, stripe, pagenr);
+ /*
+ * the bio cache may have handed us an uptodate
+ * page. If so, be happy and use it
+ */
+ if (PageUptodate(page))
+ continue;
+
+ ret = rbio_add_io_page(rbio, &bio_list, page,
+ stripe, pagenr, rbio->stripe_len);
+ if (ret)
+ goto cleanup;
+ }
+ }
+
+ bios_to_read = bio_list_size(&bio_list);
+ if (!bios_to_read) {
+ /*
+ * this can happen if others have merged with
+ * us, it means there is nothing left to read.
+ * But if there are missing devices it may not be
+ * safe to do the full stripe write yet.
+ */
+ goto finish;
+ }
+
+ /*
+ * the bbio may be freed once we submit the last bio. Make sure
+ * not to touch it after that
+ */
+ atomic_set(&rbio->stripes_pending, bios_to_read);
+ while (1) {
+ bio = bio_list_pop(&bio_list);
+ if (!bio)
+ break;
+
+ bio->bi_private = rbio;
+ bio->bi_end_io = raid56_parity_scrub_end_io;
+
+ btrfs_bio_wq_end_io(rbio->fs_info, bio,
+ BTRFS_WQ_ENDIO_RAID56);
+
+ BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
+ submit_bio(READ, bio);
+ }
+ /* the actual write will happen once the reads are done */
+ return;
+
+cleanup:
+ rbio_orig_end_io(rbio, -EIO, 0);
+ return;
+
+finish:
+ validate_rbio_for_parity_scrub(rbio);
+}
+
+static void scrub_parity_work(struct btrfs_work *work)
+{
+ struct btrfs_raid_bio *rbio;
+
+ rbio = container_of(work, struct btrfs_raid_bio, work);
+ raid56_parity_scrub_stripe(rbio);
+}
+
+static void async_scrub_parity(struct btrfs_raid_bio *rbio)
+{
+ btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+ scrub_parity_work, NULL, NULL);
+
+ btrfs_queue_work(rbio->fs_info->rmw_workers,
+ &rbio->work);
+}
+
+void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
+{
+ if (!lock_stripe_add(rbio))
+ async_scrub_parity(rbio);
+}
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index ea5d73bfdfbe..31d4a157b5e3 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -39,13 +39,25 @@ static inline int nr_data_stripes(struct map_lookup *map)
#define is_parity_stripe(x) (((x) == RAID5_P_STRIPE) || \
((x) == RAID6_Q_STRIPE))
+struct btrfs_raid_bio;
+struct btrfs_device;
+
int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
- struct btrfs_bio *bbio, u64 *raid_map,
- u64 stripe_len, int mirror_num);
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len, int mirror_num, int generic_io);
int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
struct btrfs_bio *bbio, u64 *raid_map,
u64 stripe_len);
+struct btrfs_raid_bio *
+raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len, struct btrfs_device *scrub_dev,
+ unsigned long *dbitmap, int stripe_nsectors);
+void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio,
+ struct page *page, u64 logical);
+void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio);
+
int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info);
void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info);
#endif
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index efa083113827..f2bb13a23f86 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -63,10 +63,18 @@ struct scrub_ctx;
*/
#define SCRUB_MAX_PAGES_PER_BLOCK 16 /* 64k per node/leaf/sector */
+struct scrub_recover {
+ atomic_t refs;
+ struct btrfs_bio *bbio;
+ u64 *raid_map;
+ u64 map_length;
+};
+
struct scrub_page {
struct scrub_block *sblock;
struct page *page;
struct btrfs_device *dev;
+ struct list_head list;
u64 flags; /* extent flags */
u64 generation;
u64 logical;
@@ -79,6 +87,8 @@ struct scrub_page {
unsigned int io_error:1;
};
u8 csum[BTRFS_CSUM_SIZE];
+
+ struct scrub_recover *recover;
};
struct scrub_bio {
@@ -105,14 +115,52 @@ struct scrub_block {
atomic_t outstanding_pages;
atomic_t ref_count; /* free mem on transition to zero */
struct scrub_ctx *sctx;
+ struct scrub_parity *sparity;
struct {
unsigned int header_error:1;
unsigned int checksum_error:1;
unsigned int no_io_error_seen:1;
unsigned int generation_error:1; /* also sets header_error */
+
+ /* The following is for the data used to check parity */
+ /* It is for the data with checksum */
+ unsigned int data_corrected:1;
};
};
+/* Used for the chunks with parity stripe such RAID5/6 */
+struct scrub_parity {
+ struct scrub_ctx *sctx;
+
+ struct btrfs_device *scrub_dev;
+
+ u64 logic_start;
+
+ u64 logic_end;
+
+ int nsectors;
+
+ int stripe_len;
+
+ atomic_t ref_count;
+
+ struct list_head spages;
+
+ /* Work of parity check and repair */
+ struct btrfs_work work;
+
+ /* Mark the parity blocks which have data */
+ unsigned long *dbitmap;
+
+ /*
+ * Mark the parity blocks which have data, but errors happen when
+ * read data or check data
+ */
+ unsigned long *ebitmap;
+
+ unsigned long bitmap[0];
+};
+
struct scrub_wr_ctx {
struct scrub_bio *wr_curr_bio;
struct btrfs_device *tgtdev;
@@ -196,7 +244,7 @@ static int scrub_setup_recheck_block(struct scrub_ctx *sctx,
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
struct scrub_block *sblock, int is_metadata,
int have_csum, u8 *csum, u64 generation,
- u16 csum_size);
+ u16 csum_size, int retry_failed_mirror);
static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
struct scrub_block *sblock,
int is_metadata, int have_csum,
@@ -218,6 +266,8 @@ static void scrub_block_get(struct scrub_block *sblock);
static void scrub_block_put(struct scrub_block *sblock);
static void scrub_page_get(struct scrub_page *spage);
static void scrub_page_put(struct scrub_page *spage);
+static void scrub_parity_get(struct scrub_parity *sparity);
+static void scrub_parity_put(struct scrub_parity *sparity);
static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx,
struct scrub_page *spage);
static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
@@ -790,6 +840,20 @@ out:
scrub_pending_trans_workers_dec(sctx);
}
+static inline void scrub_get_recover(struct scrub_recover *recover)
+{
+ atomic_inc(&recover->refs);
+}
+
+static inline void scrub_put_recover(struct scrub_recover *recover)
+{
+ if (atomic_dec_and_test(&recover->refs)) {
+ kfree(recover->bbio);
+ kfree(recover->raid_map);
+ kfree(recover);
+ }
+}
+
/*
* scrub_handle_errored_block gets called when either verification of the
* pages failed or the bio failed to read, e.g. with EIO. In the latter
@@ -906,7 +970,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
/* build and submit the bios for the failed mirror, check checksums */
scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum,
- csum, generation, sctx->csum_size);
+ csum, generation, sctx->csum_size, 1);
if (!sblock_bad->header_error && !sblock_bad->checksum_error &&
sblock_bad->no_io_error_seen) {
@@ -920,6 +984,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
*/
spin_lock(&sctx->stat_lock);
sctx->stat.unverified_errors++;
+ sblock_to_check->data_corrected = 1;
spin_unlock(&sctx->stat_lock);
if (sctx->is_dev_replace)
@@ -1019,7 +1084,7 @@ nodatasum_case:
/* build and submit the bios, check checksums */
scrub_recheck_block(fs_info, sblock_other, is_metadata,
have_csum, csum, generation,
- sctx->csum_size);
+ sctx->csum_size, 0);
if (!sblock_other->header_error &&
!sblock_other->checksum_error &&
@@ -1169,7 +1234,7 @@ nodatasum_case:
*/
scrub_recheck_block(fs_info, sblock_bad,
is_metadata, have_csum, csum,
- generation, sctx->csum_size);
+ generation, sctx->csum_size, 1);
if (!sblock_bad->header_error &&
!sblock_bad->checksum_error &&
sblock_bad->no_io_error_seen)
@@ -1180,6 +1245,7 @@ nodatasum_case:
corrected_error:
spin_lock(&sctx->stat_lock);
sctx->stat.corrected_errors++;
+ sblock_to_check->data_corrected = 1;
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
"BTRFS: fixed up error at logical %llu on dev %s\n",
@@ -1201,11 +1267,18 @@ out:
mirror_index++) {
struct scrub_block *sblock = sblocks_for_recheck +
mirror_index;
+ struct scrub_recover *recover;
int page_index;
for (page_index = 0; page_index < sblock->page_count;
page_index++) {
sblock->pagev[page_index]->sblock = NULL;
+ recover = sblock->pagev[page_index]->recover;
+ if (recover) {
+ scrub_put_recover(recover);
+ sblock->pagev[page_index]->recover =
+ NULL;
+ }
scrub_page_put(sblock->pagev[page_index]);
}
}
@@ -1215,14 +1288,63 @@ out:
return 0;
}
+static inline int scrub_nr_raid_mirrors(struct btrfs_bio *bbio, u64 *raid_map)
+{
+ if (raid_map) {
+ if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE)
+ return 3;
+ else
+ return 2;
+ } else {
+ return (int)bbio->num_stripes;
+ }
+}
+
+static inline void scrub_stripe_index_and_offset(u64 logical, u64 *raid_map,
+ u64 mapped_length,
+ int nstripes, int mirror,
+ int *stripe_index,
+ u64 *stripe_offset)
+{
+ int i;
+
+ if (raid_map) {
+ /* RAID5/6 */
+ for (i = 0; i < nstripes; i++) {
+ if (raid_map[i] == RAID6_Q_STRIPE ||
+ raid_map[i] == RAID5_P_STRIPE)
+ continue;
+
+ if (logical >= raid_map[i] &&
+ logical < raid_map[i] + mapped_length)
+ break;
+ }
+
+ *stripe_index = i;
+ *stripe_offset = logical - raid_map[i];
+ } else {
+ /* The other RAID type */
+ *stripe_index = mirror;
+ *stripe_offset = 0;
+ }
+}
+
static int scrub_setup_recheck_block(struct scrub_ctx *sctx,
struct btrfs_fs_info *fs_info,
struct scrub_block *original_sblock,
u64 length, u64 logical,
struct scrub_block *sblocks_for_recheck)
{
+ struct scrub_recover *recover;
+ struct btrfs_bio *bbio;
+ u64 *raid_map;
+ u64 sublen;
+ u64 mapped_length;
+ u64 stripe_offset;
+ int stripe_index;
int page_index;
int mirror_index;
+ int nmirrors;
int ret;
/*
@@ -1233,23 +1355,39 @@ static int scrub_setup_recheck_block(struct scrub_ctx *sctx,
page_index = 0;
while (length > 0) {
- u64 sublen = min_t(u64, length, PAGE_SIZE);
- u64 mapped_length = sublen;
- struct btrfs_bio *bbio = NULL;
+ sublen = min_t(u64, length, PAGE_SIZE);
+ mapped_length = sublen;
+ bbio = NULL;
+ raid_map = NULL;
/*
* with a length of PAGE_SIZE, each returned stripe
* represents one mirror
*/
- ret = btrfs_map_block(fs_info, REQ_GET_READ_MIRRORS, logical,
- &mapped_length, &bbio, 0);
+ ret = btrfs_map_sblock(fs_info, REQ_GET_READ_MIRRORS, logical,
+ &mapped_length, &bbio, 0, &raid_map);
if (ret || !bbio || mapped_length < sublen) {
kfree(bbio);
+ kfree(raid_map);
return -EIO;
}
+ recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS);
+ if (!recover) {
+ kfree(bbio);
+ kfree(raid_map);
+ return -ENOMEM;
+ }
+
+ atomic_set(&recover->refs, 1);
+ recover->bbio = bbio;
+ recover->raid_map = raid_map;
+ recover->map_length = mapped_length;
+
BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO);
- for (mirror_index = 0; mirror_index < (int)bbio->num_stripes;
+
+ nmirrors = scrub_nr_raid_mirrors(bbio, raid_map);
+ for (mirror_index = 0; mirror_index < nmirrors;
mirror_index++) {
struct scrub_block *sblock;
struct scrub_page *page;
@@ -1265,26 +1403,38 @@ leave_nomem:
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
- kfree(bbio);
+ scrub_put_recover(recover);
return -ENOMEM;
}
scrub_page_get(page);
sblock->pagev[page_index] = page;
page->logical = logical;
- page->physical = bbio->stripes[mirror_index].physical;
+
+ scrub_stripe_index_and_offset(logical, raid_map,
+ mapped_length,
+ bbio->num_stripes,
+ mirror_index,
+ &stripe_index,
+ &stripe_offset);
+ page->physical = bbio->stripes[stripe_index].physical +
+ stripe_offset;
+ page->dev = bbio->stripes[stripe_index].dev;
+
BUG_ON(page_index >= original_sblock->page_count);
page->physical_for_dev_replace =
original_sblock->pagev[page_index]->
physical_for_dev_replace;
/* for missing devices, dev->bdev is NULL */
- page->dev = bbio->stripes[mirror_index].dev;
page->mirror_num = mirror_index + 1;
sblock->page_count++;
page->page = alloc_page(GFP_NOFS);
if (!page->page)
goto leave_nomem;
+
+ scrub_get_recover(recover);
+ page->recover = recover;
}
- kfree(bbio);
+ scrub_put_recover(recover);
length -= sublen;
logical += sublen;
page_index++;
@@ -1293,6 +1443,51 @@ leave_nomem:
return 0;
}
+struct scrub_bio_ret {
+ struct completion event;
+ int error;
+};
+
+static void scrub_bio_wait_endio(struct bio *bio, int error)
+{
+ struct scrub_bio_ret *ret = bio->bi_private;
+
+ ret->error = error;
+ complete(&ret->event);
+}
+
+static inline int scrub_is_page_on_raid56(struct scrub_page *page)
+{
+ return page->recover && page->recover->raid_map;
+}
+
+static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
+ struct bio *bio,
+ struct scrub_page *page)
+{
+ struct scrub_bio_ret done;
+ int ret;
+
+ init_completion(&done.event);
+ done.error = 0;
+ bio->bi_iter.bi_sector = page->logical >> 9;
+ bio->bi_private = &done;
+ bio->bi_end_io = scrub_bio_wait_endio;
+
+ ret = raid56_parity_recover(fs_info->fs_root, bio, page->recover->bbio,
+ page->recover->raid_map,
+ page->recover->map_length,
+ page->mirror_num, 0);
+ if (ret)
+ return ret;
+
+ wait_for_completion(&done.event);
+ if (done.error)
+ return -EIO;
+
+ return 0;
+}
+
/*
* this function will check the on disk data for checksum errors, header
* errors and read I/O errors. If any I/O errors happen, the exact pages
@@ -1303,7 +1498,7 @@ leave_nomem:
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
struct scrub_block *sblock, int is_metadata,
int have_csum, u8 *csum, u64 generation,
- u16 csum_size)
+ u16 csum_size, int retry_failed_mirror)
{
int page_num;
@@ -1329,11 +1524,17 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
continue;
}
bio->bi_bdev = page->dev->bdev;
- bio->bi_iter.bi_sector = page->physical >> 9;
bio_add_page(bio, page->page, PAGE_SIZE, 0);
- if (btrfsic_submit_bio_wait(READ, bio))
- sblock->no_io_error_seen = 0;
+ if (!retry_failed_mirror && scrub_is_page_on_raid56(page)) {
+ if (scrub_submit_raid56_bio_wait(fs_info, bio, page))
+ sblock->no_io_error_seen = 0;
+ } else {
+ bio->bi_iter.bi_sector = page->physical >> 9;
+
+ if (btrfsic_submit_bio_wait(READ, bio))
+ sblock->no_io_error_seen = 0;
+ }
bio_put(bio);
}
@@ -1486,6 +1687,13 @@ static void scrub_write_block_to_dev_replace(struct scrub_block *sblock)
{
int page_num;
+ /*
+ * This block is used for the check of the parity on the source device,
+ * so the data needn't be written into the destination device.
+ */
+ if (sblock->sparity)
+ return;
+
for (page_num = 0; page_num < sblock->page_count; page_num++) {
int ret;
@@ -1867,6 +2075,9 @@ static void scrub_block_put(struct scrub_block *sblock)
if (atomic_dec_and_test(&sblock->ref_count)) {
int i;
+ if (sblock->sparity)
+ scrub_parity_put(sblock->sparity);
+
for (i = 0; i < sblock->page_count; i++)
scrub_page_put(sblock->pagev[i]);
kfree(sblock);
@@ -2124,9 +2335,51 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work)
scrub_pending_bio_dec(sctx);
}
+static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
+ unsigned long *bitmap,
+ u64 start, u64 len)
+{
+ int offset;
+ int nsectors;
+ int sectorsize = sparity->sctx->dev_root->sectorsize;
+
+ if (len >= sparity->stripe_len) {
+ bitmap_set(bitmap, 0, sparity->nsectors);
+ return;
+ }
+
+ start -= sparity->logic_start;
+ offset = (int)do_div(start, sparity->stripe_len);
+ offset /= sectorsize;
+ nsectors = (int)len / sectorsize;
+
+ if (offset + nsectors <= sparity->nsectors) {
+ bitmap_set(bitmap, offset, nsectors);
+ return;
+ }
+
+ bitmap_set(bitmap, offset, sparity->nsectors - offset);
+ bitmap_set(bitmap, 0, nsectors - (sparity->nsectors - offset));
+}
+
+static inline void scrub_parity_mark_sectors_error(struct scrub_parity *sparity,
+ u64 start, u64 len)
+{
+ __scrub_mark_bitmap(sparity, sparity->ebitmap, start, len);
+}
+
+static inline void scrub_parity_mark_sectors_data(struct scrub_parity *sparity,
+ u64 start, u64 len)
+{
+ __scrub_mark_bitmap(sparity, sparity->dbitmap, start, len);
+}
+
static void scrub_block_complete(struct scrub_block *sblock)
{
+ int corrupted = 0;
+
if (!sblock->no_io_error_seen) {
+ corrupted = 1;
scrub_handle_errored_block(sblock);
} else {
/*
@@ -2134,9 +2387,19 @@ static void scrub_block_complete(struct scrub_block *sblock)
* dev replace case, otherwise write here in dev replace
* case.
*/
- if (!scrub_checksum(sblock) && sblock->sctx->is_dev_replace)
+ corrupted = scrub_checksum(sblock);
+ if (!corrupted && sblock->sctx->is_dev_replace)
scrub_write_block_to_dev_replace(sblock);
}
+
+ if (sblock->sparity && corrupted && !sblock->data_corrected) {
+ u64 start = sblock->pagev[0]->logical;
+ u64 end = sblock->pagev[sblock->page_count - 1]->logical +
+ PAGE_SIZE;
+
+ scrub_parity_mark_sectors_error(sblock->sparity,
+ start, end - start);
+ }
}
static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u64 len,
@@ -2228,6 +2491,132 @@ behind_scrub_pages:
return 0;
}
+static int scrub_pages_for_parity(struct scrub_parity *sparity,
+ u64 logical, u64 len,
+ u64 physical, struct btrfs_device *dev,
+ u64 flags, u64 gen, int mirror_num, u8 *csum)
+{
+ struct scrub_ctx *sctx = sparity->sctx;
+ struct scrub_block *sblock;
+ int index;
+
+ sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+ if (!sblock) {
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.malloc_errors++;
+ spin_unlock(&sctx->stat_lock);
+ return -ENOMEM;
+ }
+
+ /* one ref inside this function, plus one for each page added to
+ * a bio later on */
+ atomic_set(&sblock->ref_count, 1);
+ sblock->sctx = sctx;
+ sblock->no_io_error_seen = 1;
+ sblock->sparity = sparity;
+ scrub_parity_get(sparity);
+
+ for (index = 0; len > 0; index++) {
+ struct scrub_page *spage;
+ u64 l = min_t(u64, len, PAGE_SIZE);
+
+ spage = kzalloc(sizeof(*spage), GFP_NOFS);
+ if (!spage) {
+leave_nomem:
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.malloc_errors++;
+ spin_unlock(&sctx->stat_lock);
+ scrub_block_put(sblock);
+ return -ENOMEM;
+ }
+ BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK);
+ /* For scrub block */
+ scrub_page_get(spage);
+ sblock->pagev[index] = spage;
+ /* For scrub parity */
+ scrub_page_get(spage);
+ list_add_tail(&spage->list, &sparity->spages);
+ spage->sblock = sblock;
+ spage->dev = dev;
+ spage->flags = flags;
+ spage->generation = gen;
+ spage->logical = logical;
+ spage->physical = physical;
+ spage->mirror_num = mirror_num;
+ if (csum) {
+ spage->have_csum = 1;
+ memcpy(spage->csum, csum, sctx->csum_size);
+ } else {
+ spage->have_csum = 0;
+ }
+ sblock->page_count++;
+ spage->page = alloc_page(GFP_NOFS);
+ if (!spage->page)
+ goto leave_nomem;
+ len -= l;
+ logical += l;
+ physical += l;
+ }
+
+ WARN_ON(sblock->page_count == 0);
+ for (index = 0; index < sblock->page_count; index++) {
+ struct scrub_page *spage = sblock->pagev[index];
+ int ret;
+
+ ret = scrub_add_page_to_rd_bio(sctx, spage);
+ if (ret) {
+ scrub_block_put(sblock);
+ return ret;
+ }
+ }
+
+ /* last one frees, either here or in bio completion for last page */
+ scrub_block_put(sblock);
+ return 0;
+}
+
+static int scrub_extent_for_parity(struct scrub_parity *sparity,
+ u64 logical, u64 len,
+ u64 physical, struct btrfs_device *dev,
+ u64 flags, u64 gen, int mirror_num)
+{
+ struct scrub_ctx *sctx = sparity->sctx;
+ int ret;
+ u8 csum[BTRFS_CSUM_SIZE];
+ u32 blocksize;
+
+ if (flags & BTRFS_EXTENT_FLAG_DATA) {
+ blocksize = sctx->sectorsize;
+ } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+ blocksize = sctx->nodesize;
+ } else {
+ blocksize = sctx->sectorsize;
+ WARN_ON(1);
+ }
+
+ while (len) {
+ u64 l = min_t(u64, len, blocksize);
+ int have_csum = 0;
+
+ if (flags & BTRFS_EXTENT_FLAG_DATA) {
+ /* push csums to sbio */
+ have_csum = scrub_find_csum(sctx, logical, l, csum);
+ if (have_csum == 0)
+ goto skip;
+ }
+ ret = scrub_pages_for_parity(sparity, logical, l, physical, dev,
+ flags, gen, mirror_num,
+ have_csum ? csum : NULL);
+skip:
+ if (ret)
+ return ret;
+ len -= l;
+ logical += l;
+ physical += l;
+ }
+ return 0;
+}
+
/*
* Given a physical address, this will calculate it's
* logical offset. if this is a parity stripe, it will return
@@ -2236,7 +2625,8 @@ behind_scrub_pages:
* return 0 if it is a data stripe, 1 means parity stripe.
*/
static int get_raid56_logic_offset(u64 physical, int num,
- struct map_lookup *map, u64 *offset)
+ struct map_lookup *map, u64 *offset,
+ u64 *stripe_start)
{
int i;
int j = 0;
@@ -2247,6 +2637,9 @@ static int get_raid56_logic_offset(u64 physical, int num,
last_offset = (physical - map->stripes[num].physical) *
nr_data_stripes(map);
+ if (stripe_start)
+ *stripe_start = last_offset;
+
*offset = last_offset;
for (i = 0; i < nr_data_stripes(map); i++) {
*offset = last_offset + i * map->stripe_len;
@@ -2269,13 +2662,330 @@ static int get_raid56_logic_offset(u64 physical, int num,
return 1;
}
+static void scrub_free_parity(struct scrub_parity *sparity)
+{
+ struct scrub_ctx *sctx = sparity->sctx;
+ struct scrub_page *curr, *next;
+ int nbits;
+
+ nbits = bitmap_weight(sparity->ebitmap, sparity->nsectors);
+ if (nbits) {
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.read_errors += nbits;
+ sctx->stat.uncorrectable_errors += nbits;
+ spin_unlock(&sctx->stat_lock);
+ }
+
+ list_for_each_entry_safe(curr, next, &sparity->spages, list) {
+ list_del_init(&curr->list);
+ scrub_page_put(curr);
+ }
+
+ kfree(sparity);
+}
+
+static void scrub_parity_bio_endio(struct bio *bio, int error)
+{
+ struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private;
+ struct scrub_ctx *sctx = sparity->sctx;
+
+ if (error)
+ bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
+ sparity->nsectors);
+
+ scrub_free_parity(sparity);
+ scrub_pending_bio_dec(sctx);
+ bio_put(bio);
+}
+
+static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
+{
+ struct scrub_ctx *sctx = sparity->sctx;
+ struct bio *bio;
+ struct btrfs_raid_bio *rbio;
+ struct scrub_page *spage;
+ struct btrfs_bio *bbio = NULL;
+ u64 *raid_map = NULL;
+ u64 length;
+ int ret;
+
+ if (!bitmap_andnot(sparity->dbitmap, sparity->dbitmap, sparity->ebitmap,
+ sparity->nsectors))
+ goto out;
+
+ length = sparity->logic_end - sparity->logic_start + 1;
+ ret = btrfs_map_sblock(sctx->dev_root->fs_info, WRITE,
+ sparity->logic_start,
+ &length, &bbio, 0, &raid_map);
+ if (ret || !bbio || !raid_map)
+ goto bbio_out;
+
+ bio = btrfs_io_bio_alloc(GFP_NOFS, 0);
+ if (!bio)
+ goto bbio_out;
+
+ bio->bi_iter.bi_sector = sparity->logic_start >> 9;
+ bio->bi_private = sparity;
+ bio->bi_end_io = scrub_parity_bio_endio;
+
+ rbio = raid56_parity_alloc_scrub_rbio(sctx->dev_root, bio, bbio,
+ raid_map, length,
+ sparity->scrub_dev,
+ sparity->dbitmap,
+ sparity->nsectors);
+ if (!rbio)
+ goto rbio_out;
+
+ list_for_each_entry(spage, &sparity->spages, list)
+ raid56_parity_add_scrub_pages(rbio, spage->page,
+ spage->logical);
+
+ scrub_pending_bio_inc(sctx);
+ raid56_parity_submit_scrub_rbio(rbio);
+ return;
+
+rbio_out:
+ bio_put(bio);
+bbio_out:
+ kfree(bbio);
+ kfree(raid_map);
+ bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
+ sparity->nsectors);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.malloc_errors++;
+ spin_unlock(&sctx->stat_lock);
+out:
+ scrub_free_parity(sparity);
+}
+
+static inline int scrub_calc_parity_bitmap_len(int nsectors)
+{
+ return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8);
+}
+
+static void scrub_parity_get(struct scrub_parity *sparity)
+{
+ atomic_inc(&sparity->ref_count);
+}
+
+static void scrub_parity_put(struct scrub_parity *sparity)
+{
+ if (!atomic_dec_and_test(&sparity->ref_count))
+ return;
+
+ scrub_parity_check_and_repair(sparity);
+}
+
+static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
+ struct map_lookup *map,
+ struct btrfs_device *sdev,
+ struct btrfs_path *path,
+ u64 logic_start,
+ u64 logic_end)
+{
+ struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
+ struct btrfs_root *root = fs_info->extent_root;
+ struct btrfs_root *csum_root = fs_info->csum_root;
+ struct btrfs_extent_item *extent;
+ u64 flags;
+ int ret;
+ int slot;
+ struct extent_buffer *l;
+ struct btrfs_key key;
+ u64 generation;
+ u64 extent_logical;
+ u64 extent_physical;
+ u64 extent_len;
+ struct btrfs_device *extent_dev;
+ struct scrub_parity *sparity;
+ int nsectors;
+ int bitmap_len;
+ int extent_mirror_num;
+ int stop_loop = 0;
+
+ nsectors = map->stripe_len / root->sectorsize;
+ bitmap_len = scrub_calc_parity_bitmap_len(nsectors);
+ sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len,
+ GFP_NOFS);
+ if (!sparity) {
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.malloc_errors++;
+ spin_unlock(&sctx->stat_lock);
+ return -ENOMEM;
+ }
+
+ sparity->stripe_len = map->stripe_len;
+ sparity->nsectors = nsectors;
+ sparity->sctx = sctx;
+ sparity->scrub_dev = sdev;
+ sparity->logic_start = logic_start;
+ sparity->logic_end = logic_end;
+ atomic_set(&sparity->ref_count, 1);
+ INIT_LIST_HEAD(&sparity->spages);
+ sparity->dbitmap = sparity->bitmap;
+ sparity->ebitmap = (void *)sparity->bitmap + bitmap_len;
+
+ ret = 0;
+ while (logic_start < logic_end) {
+ if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.objectid = logic_start;
+ key.offset = (u64)-1;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ if (ret > 0) {
+ ret = btrfs_previous_extent_item(root, path, 0);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, &key,
+ path, 0, 0);
+ if (ret < 0)
+ goto out;
+ }
+ }
+
+ stop_loop = 0;
+ while (1) {
+ u64 bytes;
+
+ l = path->nodes[0];
+ slot = path->slots[0];
+ if (slot >= btrfs_header_nritems(l)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret == 0)
+ continue;
+ if (ret < 0)
+ goto out;
+
+ stop_loop = 1;
+ break;
+ }
+ btrfs_item_key_to_cpu(l, &key, slot);
+
+ if (key.type == BTRFS_METADATA_ITEM_KEY)
+ bytes = root->nodesize;
+ else
+ bytes = key.offset;
+
+ if (key.objectid + bytes <= logic_start)
+ goto next;
+
+ if (key.type != BTRFS_EXTENT_ITEM_KEY &&
+ key.type != BTRFS_METADATA_ITEM_KEY)
+ goto next;
+
+ if (key.objectid > logic_end) {
+ stop_loop = 1;
+ break;
+ }
+
+ while (key.objectid >= logic_start + map->stripe_len)
+ logic_start += map->stripe_len;
+
+ extent = btrfs_item_ptr(l, slot,
+ struct btrfs_extent_item);
+ flags = btrfs_extent_flags(l, extent);
+ generation = btrfs_extent_generation(l, extent);
+
+ if (key.objectid < logic_start &&
+ (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
+ btrfs_err(fs_info,
+ "scrub: tree block %llu spanning stripes, ignored. logical=%llu",
+ key.objectid, logic_start);
+ goto next;
+ }
+again:
+ extent_logical = key.objectid;
+ extent_len = bytes;
+
+ if (extent_logical < logic_start) {
+ extent_len -= logic_start - extent_logical;
+ extent_logical = logic_start;
+ }
+
+ if (extent_logical + extent_len >
+ logic_start + map->stripe_len)
+ extent_len = logic_start + map->stripe_len -
+ extent_logical;
+
+ scrub_parity_mark_sectors_data(sparity, extent_logical,
+ extent_len);
+
+ scrub_remap_extent(fs_info, extent_logical,
+ extent_len, &extent_physical,
+ &extent_dev,
+ &extent_mirror_num);
+
+ ret = btrfs_lookup_csums_range(csum_root,
+ extent_logical,
+ extent_logical + extent_len - 1,
+ &sctx->csum_list, 1);
+ if (ret)
+ goto out;
+
+ ret = scrub_extent_for_parity(sparity, extent_logical,
+ extent_len,
+ extent_physical,
+ extent_dev, flags,
+ generation,
+ extent_mirror_num);
+ if (ret)
+ goto out;
+
+ scrub_free_csums(sctx);
+ if (extent_logical + extent_len <
+ key.objectid + bytes) {
+ logic_start += map->stripe_len;
+
+ if (logic_start >= logic_end) {
+ stop_loop = 1;
+ break;
+ }
+
+ if (logic_start < key.objectid + bytes) {
+ cond_resched();
+ goto again;
+ }
+ }
+next:
+ path->slots[0]++;
+ }
+
+ btrfs_release_path(path);
+
+ if (stop_loop)
+ break;
+
+ logic_start += map->stripe_len;
+ }
+out:
+ if (ret < 0)
+ scrub_parity_mark_sectors_error(sparity, logic_start,
+ logic_end - logic_start + 1);
+ scrub_parity_put(sparity);
+ scrub_submit(sctx);
+ mutex_lock(&sctx->wr_ctx.wr_lock);
+ scrub_wr_submit(sctx);
+ mutex_unlock(&sctx->wr_ctx.wr_lock);
+
+ btrfs_release_path(path);
+ return ret < 0 ? ret : 0;
+}
+
static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
struct map_lookup *map,
struct btrfs_device *scrub_dev,
int num, u64 base, u64 length,
int is_dev_replace)
{
- struct btrfs_path *path;
+ struct btrfs_path *path, *ppath;
struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
struct btrfs_root *root = fs_info->extent_root;
struct btrfs_root *csum_root = fs_info->csum_root;
@@ -2302,6 +3012,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
u64 extent_logical;
u64 extent_physical;
u64 extent_len;
+ u64 stripe_logical;
+ u64 stripe_end;
struct btrfs_device *extent_dev;
int extent_mirror_num;
int stop_loop = 0;
@@ -2327,7 +3039,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
mirror_num = num % map->num_stripes + 1;
} else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
BTRFS_BLOCK_GROUP_RAID6)) {
- get_raid56_logic_offset(physical, num, map, &offset);
+ get_raid56_logic_offset(physical, num, map, &offset, NULL);
increment = map->stripe_len * nr_data_stripes(map);
mirror_num = 1;
} else {
@@ -2339,6 +3051,12 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
if (!path)
return -ENOMEM;
+ ppath = btrfs_alloc_path();
+ if (!ppath) {
+ btrfs_free_path(ppath);
+ return -ENOMEM;
+ }
+
/*
* work on commit root. The related disk blocks are static as
* long as COW is applied. This means, it is save to rewrite
@@ -2357,7 +3075,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
BTRFS_BLOCK_GROUP_RAID6)) {
get_raid56_logic_offset(physical_end, num,
- map, &logic_end);
+ map, &logic_end, NULL);
logic_end += base;
} else {
logic_end = logical + increment * nstripes;
@@ -2404,10 +3122,18 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
BTRFS_BLOCK_GROUP_RAID6)) {
ret = get_raid56_logic_offset(physical, num,
- map, &logical);
+ map, &logical, &stripe_logical);
logical += base;
- if (ret)
+ if (ret) {
+ stripe_logical += base;
+ stripe_end = stripe_logical + increment - 1;
+ ret = scrub_raid56_parity(sctx, map, scrub_dev,
+ ppath, stripe_logical,
+ stripe_end);
+ if (ret)
+ goto out;
goto skip;
+ }
}
/*
* canceled?
@@ -2558,13 +3284,25 @@ again:
* loop until we find next data stripe
* or we have finished all stripes.
*/
- do {
- physical += map->stripe_len;
- ret = get_raid56_logic_offset(
- physical, num,
- map, &logical);
- logical += base;
- } while (physical < physical_end && ret);
+loop:
+ physical += map->stripe_len;
+ ret = get_raid56_logic_offset(physical,
+ num, map, &logical,
+ &stripe_logical);
+ logical += base;
+
+ if (ret && physical < physical_end) {
+ stripe_logical += base;
+ stripe_end = stripe_logical +
+ increment - 1;
+ ret = scrub_raid56_parity(sctx,
+ map, scrub_dev, ppath,
+ stripe_logical,
+ stripe_end);
+ if (ret)
+ goto out;
+ goto loop;
+ }
} else {
physical += map->stripe_len;
logical += increment;
@@ -2605,6 +3343,7 @@ out:
blk_finish_plug(&plug);
btrfs_free_path(path);
+ btrfs_free_path(ppath);
return ret < 0 ? ret : 0;
}
@@ -3310,6 +4049,50 @@ out:
scrub_pending_trans_workers_dec(sctx);
}
+static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
+ u64 logical)
+{
+ struct extent_state *cached_state = NULL;
+ struct btrfs_ordered_extent *ordered;
+ struct extent_io_tree *io_tree;
+ struct extent_map *em;
+ u64 lockstart = start, lockend = start + len - 1;
+ int ret = 0;
+
+ io_tree = &BTRFS_I(inode)->io_tree;
+
+ lock_extent_bits(io_tree, lockstart, lockend, 0, &cached_state);
+ ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
+ if (ordered) {
+ btrfs_put_ordered_extent(ordered);
+ ret = 1;
+ goto out_unlock;
+ }
+
+ em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out_unlock;
+ }
+
+ /*
+ * This extent does not actually cover the logical extent anymore,
+ * move on to the next inode.
+ */
+ if (em->block_start > logical ||
+ em->block_start + em->block_len < logical + len) {
+ free_extent_map(em);
+ ret = 1;
+ goto out_unlock;
+ }
+ free_extent_map(em);
+
+out_unlock:
+ unlock_extent_cached(io_tree, lockstart, lockend, &cached_state,
+ GFP_NOFS);
+ return ret;
+}
+
static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
struct scrub_copy_nocow_ctx *nocow_ctx)
{
@@ -3318,13 +4101,10 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
struct inode *inode;
struct page *page;
struct btrfs_root *local_root;
- struct btrfs_ordered_extent *ordered;
- struct extent_map *em;
- struct extent_state *cached_state = NULL;
struct extent_io_tree *io_tree;
u64 physical_for_dev_replace;
+ u64 nocow_ctx_logical;
u64 len = nocow_ctx->len;
- u64 lockstart = offset, lockend = offset + len - 1;
unsigned long index;
int srcu_index;
int ret = 0;
@@ -3356,30 +4136,13 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
io_tree = &BTRFS_I(inode)->io_tree;
+ nocow_ctx_logical = nocow_ctx->logical;
- lock_extent_bits(io_tree, lockstart, lockend, 0, &cached_state);
- ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
- if (ordered) {
- btrfs_put_ordered_extent(ordered);
- goto out_unlock;
- }
-
- em = btrfs_get_extent(inode, NULL, 0, lockstart, len, 0);
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto out_unlock;
- }
-
- /*
- * This extent does not actually cover the logical extent anymore,
- * move on to the next inode.
- */
- if (em->block_start > nocow_ctx->logical ||
- em->block_start + em->block_len < nocow_ctx->logical + len) {
- free_extent_map(em);
- goto out_unlock;
+ ret = check_extent_to_block(inode, offset, len, nocow_ctx_logical);
+ if (ret) {
+ ret = ret > 0 ? 0 : ret;
+ goto out;
}
- free_extent_map(em);
while (len >= PAGE_CACHE_SIZE) {
index = offset >> PAGE_CACHE_SHIFT;
@@ -3396,7 +4159,7 @@ again:
goto next_page;
} else {
ClearPageError(page);
- err = extent_read_full_page_nolock(io_tree, page,
+ err = extent_read_full_page(io_tree, page,
btrfs_get_extent,
nocow_ctx->mirror_num);
if (err) {
@@ -3421,6 +4184,14 @@ again:
goto next_page;
}
}
+
+ ret = check_extent_to_block(inode, offset, len,
+ nocow_ctx_logical);
+ if (ret) {
+ ret = ret > 0 ? 0 : ret;
+ goto next_page;
+ }
+
err = write_page_nocow(nocow_ctx->sctx,
physical_for_dev_replace, page);
if (err)
@@ -3434,12 +4205,10 @@ next_page:
offset += PAGE_CACHE_SIZE;
physical_for_dev_replace += PAGE_CACHE_SIZE;
+ nocow_ctx_logical += PAGE_CACHE_SIZE;
len -= PAGE_CACHE_SIZE;
}
ret = COPY_COMPLETE;
-out_unlock:
- unlock_extent_cached(io_tree, lockstart, lockend, &cached_state,
- GFP_NOFS);
out:
mutex_unlock(&inode->i_mutex);
iput(inode);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 874828dd0a86..804432dbc351 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5507,6 +5507,51 @@ out:
return ret;
}
+/*
+ * If orphan cleanup did remove any orphans from a root, it means the tree
+ * was modified and therefore the commit root is not the same as the current
+ * root anymore. This is a problem, because send uses the commit root and
+ * therefore can see inode items that don't exist in the current root anymore,
+ * and for example make calls to btrfs_iget, which will do tree lookups based
+ * on the current root and not on the commit root. Those lookups will fail,
+ * returning a -ESTALE error, and making send fail with that error. So make
+ * sure a send does not see any orphans we have just removed, and that it will
+ * see the same inodes regardless of whether a transaction commit happened
+ * before it started (meaning that the commit root will be the same as the
+ * current root) or not.
+ */
+static int ensure_commit_roots_uptodate(struct send_ctx *sctx)
+{
+ int i;
+ struct btrfs_trans_handle *trans = NULL;
+
+again:
+ if (sctx->parent_root &&
+ sctx->parent_root->node != sctx->parent_root->commit_root)
+ goto commit_trans;
+
+ for (i = 0; i < sctx->clone_roots_cnt; i++)
+ if (sctx->clone_roots[i].root->node !=
+ sctx->clone_roots[i].root->commit_root)
+ goto commit_trans;
+
+ if (trans)
+ return btrfs_end_transaction(trans, sctx->send_root);
+
+ return 0;
+
+commit_trans:
+ /* Use any root, all fs roots will get their commit roots updated. */
+ if (!trans) {
+ trans = btrfs_join_transaction(sctx->send_root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ goto again;
+ }
+
+ return btrfs_commit_transaction(trans, sctx->send_root);
+}
+
static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
{
spin_lock(&root->root_item_lock);
@@ -5728,6 +5773,10 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
NULL);
sort_clone_roots = 1;
+ ret = ensure_commit_roots_uptodate(sctx);
+ if (ret)
+ goto out;
+
current->journal_info = BTRFS_SEND_TRANS_STUB;
ret = send_subvol(sctx);
current->journal_info = NULL;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 54bd91ece35b..60f7cbe815e9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -262,7 +262,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
trans->aborted = errno;
/* Nothing used. The other threads that have joined this
* transaction may be able to continue. */
- if (!trans->blocks_used) {
+ if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
const char *errstr;
errstr = btrfs_decode_error(errno);
@@ -642,11 +642,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
"disabling disk space caching");
break;
case Opt_inode_cache:
- btrfs_set_and_info(root, CHANGE_INODE_CACHE,
+ btrfs_set_pending_and_info(info, INODE_MAP_CACHE,
"enabling inode map caching");
break;
case Opt_noinode_cache:
- btrfs_clear_and_info(root, CHANGE_INODE_CACHE,
+ btrfs_clear_pending_and_info(info, INODE_MAP_CACHE,
"disabling inode map caching");
break;
case Opt_clear_cache:
@@ -993,9 +993,17 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
- if (PTR_ERR(trans) == -ENOENT)
- return 0;
- return PTR_ERR(trans);
+ if (PTR_ERR(trans) == -ENOENT) {
+ /*
+ * Exit unless we have some pending changes
+ * that need to go through commit
+ */
+ if (fs_info->pending_changes == 0)
+ return 0;
+ trans = btrfs_start_transaction(root, 0);
+ } else {
+ return PTR_ERR(trans);
+ }
}
return btrfs_commit_transaction(trans, root);
}
@@ -1644,8 +1652,20 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
int i = 0, nr_devices;
int ret;
+ /*
+ * We aren't under the device list lock, so this is racey-ish, but good
+ * enough for our purposes.
+ */
nr_devices = fs_info->fs_devices->open_devices;
- BUG_ON(!nr_devices);
+ if (!nr_devices) {
+ smp_mb();
+ nr_devices = fs_info->fs_devices->open_devices;
+ ASSERT(nr_devices);
+ if (!nr_devices) {
+ *free_bytes = 0;
+ return 0;
+ }
+ }
devices_info = kmalloc_array(nr_devices, sizeof(*devices_info),
GFP_NOFS);
@@ -1670,11 +1690,17 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
else
min_stripe_size = BTRFS_STRIPE_LEN;
- list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ if (fs_info->alloc_start)
+ mutex_lock(&fs_devices->device_list_mutex);
+ rcu_read_lock();
+ list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
if (!device->in_fs_metadata || !device->bdev ||
device->is_tgtdev_for_dev_replace)
continue;
+ if (i >= nr_devices)
+ break;
+
avail_space = device->total_bytes - device->bytes_used;
/* align with stripe_len */
@@ -1689,24 +1715,32 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
skip_space = 1024 * 1024;
/* user can set the offset in fs_info->alloc_start. */
- if (fs_info->alloc_start + BTRFS_STRIPE_LEN <=
- device->total_bytes)
+ if (fs_info->alloc_start &&
+ fs_info->alloc_start + BTRFS_STRIPE_LEN <=
+ device->total_bytes) {
+ rcu_read_unlock();
skip_space = max(fs_info->alloc_start, skip_space);
- /*
- * btrfs can not use the free space in [0, skip_space - 1],
- * we must subtract it from the total. In order to implement
- * it, we account the used space in this range first.
- */
- ret = btrfs_account_dev_extents_size(device, 0, skip_space - 1,
- &used_space);
- if (ret) {
- kfree(devices_info);
- return ret;
- }
+ /*
+ * btrfs can not use the free space in
+ * [0, skip_space - 1], we must subtract it from the
+ * total. In order to implement it, we account the used
+ * space in this range first.
+ */
+ ret = btrfs_account_dev_extents_size(device, 0,
+ skip_space - 1,
+ &used_space);
+ if (ret) {
+ kfree(devices_info);
+ mutex_unlock(&fs_devices->device_list_mutex);
+ return ret;
+ }
- /* calc the free space in [0, skip_space - 1] */
- skip_space -= used_space;
+ rcu_read_lock();
+
+ /* calc the free space in [0, skip_space - 1] */
+ skip_space -= used_space;
+ }
/*
* we can use the free space in [0, skip_space - 1], subtract
@@ -1725,6 +1759,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
i++;
}
+ rcu_read_unlock();
+ if (fs_info->alloc_start)
+ mutex_unlock(&fs_devices->device_list_mutex);
nr_devices = i;
@@ -1787,8 +1824,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
* holding chunk_muext to avoid allocating new chunks, holding
* device_list_mutex to avoid the device being removed
*/
- mutex_lock(&fs_info->fs_devices->device_list_mutex);
- mutex_lock(&fs_info->chunk_mutex);
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
@@ -1824,17 +1859,12 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_bfree -= block_rsv->size >> bits;
spin_unlock(&block_rsv->lock);
- buf->f_bavail = total_free_data;
+ buf->f_bavail = div_u64(total_free_data, factor);
ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data);
- if (ret) {
- mutex_unlock(&fs_info->chunk_mutex);
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ if (ret)
return ret;
- }
buf->f_bavail += div_u64(total_free_data, factor);
buf->f_bavail = buf->f_bavail >> bits;
- mutex_unlock(&fs_info->chunk_mutex);
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
buf->f_type = BTRFS_SUPER_MAGIC;
buf->f_bsize = dentry->d_sb->s_blocksize;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index b2e7bb4393f6..92db3f648df4 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -111,7 +111,6 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info;
struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a);
- struct btrfs_trans_handle *trans;
u64 features, set, clear;
unsigned long val;
int ret;
@@ -153,10 +152,6 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
btrfs_info(fs_info, "%s %s feature flag",
val ? "Setting" : "Clearing", fa->kobj_attr.attr.name);
- trans = btrfs_start_transaction(fs_info->fs_root, 0);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
-
spin_lock(&fs_info->super_lock);
features = get_features(fs_info, fa->feature_set);
if (val)
@@ -166,9 +161,11 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
set_features(fs_info, fa->feature_set, features);
spin_unlock(&fs_info->super_lock);
- ret = btrfs_commit_transaction(trans, fs_info->fs_root);
- if (ret)
- return ret;
+ /*
+ * We don't want to do full transaction commit from inside sysfs
+ */
+ btrfs_set_pending(fs_info, COMMIT);
+ wake_up_process(fs_info->transaction_kthread);
return count;
}
@@ -372,9 +369,6 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
const char *buf, size_t len)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- struct btrfs_trans_handle *trans;
- struct btrfs_root *root = fs_info->fs_root;
- int ret;
size_t p_len;
if (fs_info->sb->s_flags & MS_RDONLY)
@@ -389,20 +383,18 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
if (p_len >= BTRFS_LABEL_SIZE)
return -EINVAL;
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
-
- spin_lock(&root->fs_info->super_lock);
+ spin_lock(&fs_info->super_lock);
memset(fs_info->super_copy->label, 0, BTRFS_LABEL_SIZE);
memcpy(fs_info->super_copy->label, buf, p_len);
- spin_unlock(&root->fs_info->super_lock);
- ret = btrfs_commit_transaction(trans, root);
+ spin_unlock(&fs_info->super_lock);
- if (!ret)
- return len;
+ /*
+ * We don't want to do full transaction commit from inside sysfs
+ */
+ btrfs_set_pending(fs_info, COMMIT);
+ wake_up_process(fs_info->transaction_kthread);
- return ret;
+ return len;
}
BTRFS_ATTR_RW(label, btrfs_label_show, btrfs_label_store);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index dcaae3616728..a605d4e2f2bc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -76,6 +76,32 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
}
}
+static void clear_btree_io_tree(struct extent_io_tree *tree)
+{
+ spin_lock(&tree->lock);
+ while (!RB_EMPTY_ROOT(&tree->state)) {
+ struct rb_node *node;
+ struct extent_state *state;
+
+ node = rb_first(&tree->state);
+ state = rb_entry(node, struct extent_state, rb_node);
+ rb_erase(&state->rb_node, &tree->state);
+ RB_CLEAR_NODE(&state->rb_node);
+ /*
+ * btree io trees aren't supposed to have tasks waiting for
+ * changes in the flags of extent states ever.
+ */
+ ASSERT(!waitqueue_active(&state->wq));
+ free_extent_state(state);
+ if (need_resched()) {
+ spin_unlock(&tree->lock);
+ cond_resched();
+ spin_lock(&tree->lock);
+ }
+ }
+ spin_unlock(&tree->lock);
+}
+
static noinline void switch_commit_roots(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info)
{
@@ -89,6 +115,7 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans,
root->commit_root = btrfs_root_node(root);
if (is_fstree(root->objectid))
btrfs_unpin_free_ino(root);
+ clear_btree_io_tree(&root->dirty_log_pages);
}
up_write(&fs_info->commit_root_sem);
}
@@ -220,6 +247,7 @@ loop:
INIT_LIST_HEAD(&cur_trans->pending_snapshots);
INIT_LIST_HEAD(&cur_trans->pending_chunks);
INIT_LIST_HEAD(&cur_trans->switch_commits);
+ INIT_LIST_HEAD(&cur_trans->pending_ordered);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(&cur_trans->dirty_pages,
fs_info->btree_inode->i_mapping);
@@ -488,6 +516,7 @@ again:
h->sync = false;
INIT_LIST_HEAD(&h->qgroup_ref_list);
INIT_LIST_HEAD(&h->new_bgs);
+ INIT_LIST_HEAD(&h->ordered);
smp_mb();
if (cur_trans->state >= TRANS_STATE_BLOCKED &&
@@ -719,6 +748,12 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
if (!list_empty(&trans->new_bgs))
btrfs_create_pending_block_groups(trans, root);
+ if (!list_empty(&trans->ordered)) {
+ spin_lock(&info->trans_lock);
+ list_splice(&trans->ordered, &cur_trans->pending_ordered);
+ spin_unlock(&info->trans_lock);
+ }
+
trans->delayed_ref_updates = 0;
if (!trans->sync) {
must_run_delayed_refs =
@@ -828,17 +863,39 @@ int btrfs_write_marked_extents(struct btrfs_root *root,
while (!find_first_extent_bit(dirty_pages, start, &start, &end,
mark, &cached_state)) {
- convert_extent_bit(dirty_pages, start, end, EXTENT_NEED_WAIT,
- mark, &cached_state, GFP_NOFS);
- cached_state = NULL;
- err = filemap_fdatawrite_range(mapping, start, end);
+ bool wait_writeback = false;
+
+ err = convert_extent_bit(dirty_pages, start, end,
+ EXTENT_NEED_WAIT,
+ mark, &cached_state, GFP_NOFS);
+ /*
+ * convert_extent_bit can return -ENOMEM, which is most of the
+ * time a temporary error. So when it happens, ignore the error
+ * and wait for writeback of this range to finish - because we
+ * failed to set the bit EXTENT_NEED_WAIT for the range, a call
+ * to btrfs_wait_marked_extents() would not know that writeback
+ * for this range started and therefore wouldn't wait for it to
+ * finish - we don't want to commit a superblock that points to
+ * btree nodes/leafs for which writeback hasn't finished yet
+ * (and without errors).
+ * We cleanup any entries left in the io tree when committing
+ * the transaction (through clear_btree_io_tree()).
+ */
+ if (err == -ENOMEM) {
+ err = 0;
+ wait_writeback = true;
+ }
+ if (!err)
+ err = filemap_fdatawrite_range(mapping, start, end);
if (err)
werr = err;
+ else if (wait_writeback)
+ werr = filemap_fdatawait_range(mapping, start, end);
+ free_extent_state(cached_state);
+ cached_state = NULL;
cond_resched();
start = end + 1;
}
- if (err)
- werr = err;
return werr;
}
@@ -862,11 +919,25 @@ int btrfs_wait_marked_extents(struct btrfs_root *root,
while (!find_first_extent_bit(dirty_pages, start, &start, &end,
EXTENT_NEED_WAIT, &cached_state)) {
- clear_extent_bit(dirty_pages, start, end, EXTENT_NEED_WAIT,
- 0, 0, &cached_state, GFP_NOFS);
- err = filemap_fdatawait_range(mapping, start, end);
+ /*
+ * Ignore -ENOMEM errors returned by clear_extent_bit().
+ * When committing the transaction, we'll remove any entries
+ * left in the io tree. For a log commit, we don't remove them
+ * after committing the log because the tree can be accessed
+ * concurrently - we do it only at transaction commit time when
+ * it's safe to do it (through clear_btree_io_tree()).
+ */
+ err = clear_extent_bit(dirty_pages, start, end,
+ EXTENT_NEED_WAIT,
+ 0, 0, &cached_state, GFP_NOFS);
+ if (err == -ENOMEM)
+ err = 0;
+ if (!err)
+ err = filemap_fdatawait_range(mapping, start, end);
if (err)
werr = err;
+ free_extent_state(cached_state);
+ cached_state = NULL;
cond_resched();
start = end + 1;
}
@@ -919,17 +990,17 @@ static int btrfs_write_and_wait_marked_extents(struct btrfs_root *root,
return 0;
}
-int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
+static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
- if (!trans || !trans->transaction) {
- struct inode *btree_inode;
- btree_inode = root->fs_info->btree_inode;
- return filemap_write_and_wait(btree_inode->i_mapping);
- }
- return btrfs_write_and_wait_marked_extents(root,
+ int ret;
+
+ ret = btrfs_write_and_wait_marked_extents(root,
&trans->transaction->dirty_pages,
EXTENT_DIRTY);
+ clear_btree_io_tree(&trans->transaction->dirty_pages);
+
+ return ret;
}
/*
@@ -1652,6 +1723,28 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
btrfs_wait_ordered_roots(fs_info, -1);
}
+static inline void
+btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans,
+ struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_ordered_extent *ordered;
+
+ spin_lock(&fs_info->trans_lock);
+ while (!list_empty(&cur_trans->pending_ordered)) {
+ ordered = list_first_entry(&cur_trans->pending_ordered,
+ struct btrfs_ordered_extent,
+ trans_list);
+ list_del_init(&ordered->trans_list);
+ spin_unlock(&fs_info->trans_lock);
+
+ wait_event(ordered->wait, test_bit(BTRFS_ORDERED_COMPLETE,
+ &ordered->flags));
+ btrfs_put_ordered_extent(ordered);
+ spin_lock(&fs_info->trans_lock);
+ }
+ spin_unlock(&fs_info->trans_lock);
+}
+
int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
@@ -1702,6 +1795,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
}
spin_lock(&root->fs_info->trans_lock);
+ list_splice(&trans->ordered, &cur_trans->pending_ordered);
if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
spin_unlock(&root->fs_info->trans_lock);
atomic_inc(&cur_trans->use_count);
@@ -1754,6 +1848,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
btrfs_wait_delalloc_flush(root->fs_info);
+ btrfs_wait_pending_ordered(cur_trans, root->fs_info);
+
btrfs_scrub_pause(root);
/*
* Ok now we need to make sure to block out any other joins while we
@@ -1842,13 +1938,10 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
}
/*
- * Since the transaction is done, we should set the inode map cache flag
- * before any other comming transaction.
+ * Since the transaction is done, we can apply the pending changes
+ * before the next transaction.
*/
- if (btrfs_test_opt(root, CHANGE_INODE_CACHE))
- btrfs_set_opt(root->fs_info->mount_opt, INODE_MAP_CACHE);
- else
- btrfs_clear_opt(root->fs_info->mount_opt, INODE_MAP_CACHE);
+ btrfs_apply_pending_changes(root->fs_info);
/* commit_fs_roots gets rid of all the tree log roots, it is now
* safe to free the root of tree log roots
@@ -2019,3 +2112,32 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
return (ret < 0) ? 0 : 1;
}
+
+void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info)
+{
+ unsigned long prev;
+ unsigned long bit;
+
+ prev = cmpxchg(&fs_info->pending_changes, 0, 0);
+ if (!prev)
+ return;
+
+ bit = 1 << BTRFS_PENDING_SET_INODE_MAP_CACHE;
+ if (prev & bit)
+ btrfs_set_opt(fs_info->mount_opt, INODE_MAP_CACHE);
+ prev &= ~bit;
+
+ bit = 1 << BTRFS_PENDING_CLEAR_INODE_MAP_CACHE;
+ if (prev & bit)
+ btrfs_clear_opt(fs_info->mount_opt, INODE_MAP_CACHE);
+ prev &= ~bit;
+
+ bit = 1 << BTRFS_PENDING_COMMIT;
+ if (prev & bit)
+ btrfs_debug(fs_info, "pending commit done");
+ prev &= ~bit;
+
+ if (prev)
+ btrfs_warn(fs_info,
+ "unknown pending changes left 0x%lx, ignoring", prev);
+}
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index d8f40e1a5d2d..00ed29c4b3f9 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -56,6 +56,7 @@ struct btrfs_transaction {
wait_queue_head_t commit_wait;
struct list_head pending_snapshots;
struct list_head pending_chunks;
+ struct list_head pending_ordered;
struct list_head switch_commits;
struct btrfs_delayed_ref_root delayed_refs;
int aborted;
@@ -105,6 +106,7 @@ struct btrfs_trans_handle {
*/
struct btrfs_root *root;
struct seq_list delayed_ref_elem;
+ struct list_head ordered;
struct list_head qgroup_ref_list;
struct list_head new_bgs;
};
@@ -145,8 +147,6 @@ struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root);
int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
-int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
- struct btrfs_root *root);
void btrfs_add_dead_root(struct btrfs_root *root);
int btrfs_defrag_root(struct btrfs_root *root);
@@ -170,4 +170,6 @@ int btrfs_wait_marked_extents(struct btrfs_root *root,
int btrfs_transaction_blocked(struct btrfs_fs_info *info);
int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
void btrfs_put_transaction(struct btrfs_transaction *transaction);
+void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info);
+
#endif
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 286213cec861..9a02da16f2be 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2599,12 +2599,14 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
index2 = root_log_ctx.log_transid % 2;
if (atomic_read(&log_root_tree->log_commit[index2])) {
blk_finish_plug(&plug);
- btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
+ ret = btrfs_wait_marked_extents(log, &log->dirty_log_pages,
+ mark);
+ btrfs_wait_logged_extents(trans, log, log_transid);
wait_log_commit(trans, log_root_tree,
root_log_ctx.log_transid);
- btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&log_root_tree->log_mutex);
- ret = root_log_ctx.log_ret;
+ if (!ret)
+ ret = root_log_ctx.log_ret;
goto out;
}
ASSERT(root_log_ctx.log_transid == log_root_tree->log_transid);
@@ -2641,11 +2643,18 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
- btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
- btrfs_wait_marked_extents(log_root_tree,
- &log_root_tree->dirty_log_pages,
- EXTENT_NEW | EXTENT_DIRTY);
- btrfs_wait_logged_extents(log, log_transid);
+ ret = btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
+ if (!ret)
+ ret = btrfs_wait_marked_extents(log_root_tree,
+ &log_root_tree->dirty_log_pages,
+ EXTENT_NEW | EXTENT_DIRTY);
+ if (ret) {
+ btrfs_set_log_full_commit(root->fs_info, trans);
+ btrfs_free_logged_extents(log, log_transid);
+ mutex_unlock(&log_root_tree->log_mutex);
+ goto out_wake_log_root;
+ }
+ btrfs_wait_logged_extents(trans, log, log_transid);
btrfs_set_super_log_root(root->fs_info->super_for_commit,
log_root_tree->node->start);
@@ -3626,6 +3635,12 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans,
test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
+ /*
+ * Clear the AS_EIO/AS_ENOSPC flags from the inode's
+ * i_mapping flags, so that the next fsync won't get
+ * an outdated io error too.
+ */
+ btrfs_inode_check_errors(inode);
*ordered_io_error = true;
break;
}
@@ -3766,7 +3781,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
- btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
+ btrfs_set_token_file_extent_generation(leaf, fi, trans->transid,
&token);
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
btrfs_set_token_file_extent_type(leaf, fi,
@@ -3963,7 +3978,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
mutex_lock(&BTRFS_I(inode)->log_mutex);
- btrfs_get_logged_extents(inode, &logged_list);
+ btrfs_get_logged_extents(inode, &logged_list, start, end);
/*
* a brute force approach to making sure we get the most uptodate
@@ -4089,6 +4104,21 @@ log_extents:
btrfs_release_path(path);
btrfs_release_path(dst_path);
if (fast_search) {
+ /*
+ * Some ordered extents started by fsync might have completed
+ * before we collected the ordered extents in logged_list, which
+ * means they're gone, not in our logged_list nor in the inode's
+ * ordered tree. We want the application/user space to know an
+ * error happened while attempting to persist file data so that
+ * it can take proper action. If such error happened, we leave
+ * without writing to the log tree and the fsync must report the
+ * file data write error and not commit the current transaction.
+ */
+ err = btrfs_inode_check_errors(inode);
+ if (err) {
+ ctx->io_err = err;
+ goto out_unlock;
+ }
ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
&logged_list, ctx);
if (ret) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d47289c715c8..50c5a8762aed 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -53,16 +53,6 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);
-static void lock_chunks(struct btrfs_root *root)
-{
- mutex_lock(&root->fs_info->chunk_mutex);
-}
-
-static void unlock_chunks(struct btrfs_root *root)
-{
- mutex_unlock(&root->fs_info->chunk_mutex);
-}
-
static struct btrfs_fs_devices *__alloc_fs_devices(void)
{
struct btrfs_fs_devices *fs_devs;
@@ -1068,9 +1058,11 @@ static int contains_pending_extent(struct btrfs_trans_handle *trans,
u64 *start, u64 len)
{
struct extent_map *em;
+ struct list_head *search_list = &trans->transaction->pending_chunks;
int ret = 0;
- list_for_each_entry(em, &trans->transaction->pending_chunks, list) {
+again:
+ list_for_each_entry(em, search_list, list) {
struct map_lookup *map;
int i;
@@ -1087,6 +1079,10 @@ static int contains_pending_extent(struct btrfs_trans_handle *trans,
ret = 1;
}
}
+ if (search_list == &trans->transaction->pending_chunks) {
+ search_list = &trans->root->fs_info->pinned_chunks;
+ goto again;
+ }
return ret;
}
@@ -1489,7 +1485,7 @@ static void update_dev_time(char *path_name)
struct file *filp;
filp = filp_open(path_name, O_RDWR, 0);
- if (!filp)
+ if (IS_ERR(filp))
return;
file_update_time(filp);
filp_close(filp, NULL);
@@ -1800,8 +1796,8 @@ error_undo:
goto error_brelse;
}
-void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
- struct btrfs_device *srcdev)
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *srcdev)
{
struct btrfs_fs_devices *fs_devices;
@@ -1829,6 +1825,12 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
if (srcdev->bdev)
fs_devices->open_devices--;
+}
+
+void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *srcdev)
+{
+ struct btrfs_fs_devices *fs_devices = srcdev->fs_devices;
call_rcu(&srcdev->rcu, free_device);
@@ -2647,18 +2649,12 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
}
}
- ret = btrfs_remove_block_group(trans, extent_root, chunk_offset);
+ ret = btrfs_remove_block_group(trans, extent_root, chunk_offset, em);
if (ret) {
btrfs_abort_transaction(trans, extent_root, ret);
goto out;
}
- write_lock(&em_tree->lock);
- remove_extent_mapping(em_tree, em);
- write_unlock(&em_tree->lock);
-
- /* once for the tree */
- free_extent_map(em);
out:
/* once for us */
free_extent_map(em);
@@ -4505,6 +4501,8 @@ error_del_extent:
free_extent_map(em);
/* One for the tree reference */
free_extent_map(em);
+ /* One for the pending_chunks list reference */
+ free_extent_map(em);
error:
kfree(devices_info);
return ret;
@@ -4881,13 +4879,15 @@ static inline int parity_smaller(u64 a, u64 b)
static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map)
{
struct btrfs_bio_stripe s;
+ int real_stripes = bbio->num_stripes - bbio->num_tgtdevs;
int i;
u64 l;
int again = 1;
+ int m;
while (again) {
again = 0;
- for (i = 0; i < bbio->num_stripes - 1; i++) {
+ for (i = 0; i < real_stripes - 1; i++) {
if (parity_smaller(raid_map[i], raid_map[i+1])) {
s = bbio->stripes[i];
l = raid_map[i];
@@ -4895,6 +4895,14 @@ static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map)
raid_map[i] = raid_map[i+1];
bbio->stripes[i+1] = s;
raid_map[i+1] = l;
+
+ if (bbio->tgtdev_map) {
+ m = bbio->tgtdev_map[i];
+ bbio->tgtdev_map[i] =
+ bbio->tgtdev_map[i + 1];
+ bbio->tgtdev_map[i + 1] = m;
+ }
+
again = 1;
}
}
@@ -4923,6 +4931,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
int ret = 0;
int num_stripes;
int max_errors = 0;
+ int tgtdev_indexes = 0;
struct btrfs_bio *bbio = NULL;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
int dev_replace_is_ongoing = 0;
@@ -5161,15 +5170,14 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
BTRFS_BLOCK_GROUP_RAID6)) {
u64 tmp;
- if (bbio_ret && ((rw & REQ_WRITE) || mirror_num > 1)
- && raid_map_ret) {
+ if (raid_map_ret &&
+ ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) ||
+ mirror_num > 1)) {
int i, rot;
/* push stripe_nr back to the start of the full stripe */
stripe_nr = raid56_full_stripe_start;
- do_div(stripe_nr, stripe_len);
-
- stripe_index = do_div(stripe_nr, nr_data_stripes(map));
+ do_div(stripe_nr, stripe_len * nr_data_stripes(map));
/* RAID[56] write or recovery. Return all stripes */
num_stripes = map->num_stripes;
@@ -5235,14 +5243,19 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
num_alloc_stripes <<= 1;
if (rw & REQ_GET_READ_MIRRORS)
num_alloc_stripes++;
+ tgtdev_indexes = num_stripes;
}
- bbio = kzalloc(btrfs_bio_size(num_alloc_stripes), GFP_NOFS);
+
+ bbio = kzalloc(btrfs_bio_size(num_alloc_stripes, tgtdev_indexes),
+ GFP_NOFS);
if (!bbio) {
kfree(raid_map);
ret = -ENOMEM;
goto out;
}
atomic_set(&bbio->error, 0);
+ if (dev_replace_is_ongoing)
+ bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes);
if (rw & REQ_DISCARD) {
int factor = 0;
@@ -5327,6 +5340,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
max_errors = btrfs_chunk_max_errors(map);
+ tgtdev_indexes = 0;
if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) &&
dev_replace->tgtdev != NULL) {
int index_where_to_add;
@@ -5355,8 +5369,10 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
new->physical = old->physical;
new->length = old->length;
new->dev = dev_replace->tgtdev;
+ bbio->tgtdev_map[i] = index_where_to_add;
index_where_to_add++;
max_errors++;
+ tgtdev_indexes++;
}
}
num_stripes = index_where_to_add;
@@ -5402,7 +5418,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
tgtdev_stripe->length =
bbio->stripes[index_srcdev].length;
tgtdev_stripe->dev = dev_replace->tgtdev;
+ bbio->tgtdev_map[index_srcdev] = num_stripes;
+ tgtdev_indexes++;
num_stripes++;
}
}
@@ -5412,6 +5430,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
bbio->num_stripes = num_stripes;
bbio->max_errors = max_errors;
bbio->mirror_num = mirror_num;
+ bbio->num_tgtdevs = tgtdev_indexes;
/*
* this is the case that REQ_READ && dev_replace_is_ongoing &&
@@ -5443,6 +5462,16 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
mirror_num, NULL);
}
+/* For Scrub/replace */
+int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw,
+ u64 logical, u64 *length,
+ struct btrfs_bio **bbio_ret, int mirror_num,
+ u64 **raid_map_ret)
+{
+ return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
+ mirror_num, raid_map_ret);
+}
+
int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
u64 chunk_start, u64 physical, u64 devid,
u64 **logical, int *naddrs, int *stripe_len)
@@ -5812,12 +5841,9 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
} else {
ret = raid56_parity_recover(root, bio, bbio,
raid_map, map_length,
- mirror_num);
+ mirror_num, 1);
}
- /*
- * FIXME, replace dosen't support raid56 yet, please fix
- * it in the future.
- */
+
btrfs_bio_counter_dec(root->fs_info);
return ret;
}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 08980fa23039..d6fe73c0f4a2 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -292,7 +292,7 @@ struct btrfs_bio_stripe {
struct btrfs_bio;
typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
-#define BTRFS_BIO_ORIG_BIO_SUBMITTED 0x1
+#define BTRFS_BIO_ORIG_BIO_SUBMITTED (1 << 0)
struct btrfs_bio {
atomic_t stripes_pending;
@@ -305,6 +305,8 @@ struct btrfs_bio {
int max_errors;
int num_stripes;
int mirror_num;
+ int num_tgtdevs;
+ int *tgtdev_map;
struct btrfs_bio_stripe stripes[];
};
@@ -387,12 +389,18 @@ struct btrfs_balance_control {
int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
u64 end, u64 *length);
-#define btrfs_bio_size(n) (sizeof(struct btrfs_bio) + \
- (sizeof(struct btrfs_bio_stripe) * (n)))
+#define btrfs_bio_size(total_stripes, real_stripes) \
+ (sizeof(struct btrfs_bio) + \
+ (sizeof(struct btrfs_bio_stripe) * (total_stripes)) + \
+ (sizeof(int) * (real_stripes)))
int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret, int mirror_num);
+int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw,
+ u64 logical, u64 *length,
+ struct btrfs_bio **bbio_ret, int mirror_num,
+ u64 **raid_map_ret);
int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
u64 chunk_start, u64 physical, u64 devid,
u64 **logical, int *naddrs, int *stripe_len);
@@ -448,8 +456,10 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info);
int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info);
int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
-void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
- struct btrfs_device *srcdev);
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *srcdev);
+void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *srcdev);
void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
struct btrfs_device *tgtdev);
void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
@@ -513,4 +523,16 @@ static inline void btrfs_dev_stat_reset(struct btrfs_device *dev,
void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info);
void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
struct btrfs_transaction *transaction);
+
+static inline void lock_chunks(struct btrfs_root *root)
+{
+ mutex_lock(&root->fs_info->chunk_mutex);
+}
+
+static inline void unlock_chunks(struct btrfs_root *root)
+{
+ mutex_unlock(&root->fs_info->chunk_mutex);
+}
+
+
#endif
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index dcf20131fbe4..47b19465f0dc 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -29,6 +29,7 @@
#include "xattr.h"
#include "disk-io.h"
#include "props.h"
+#include "locking.h"
ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
@@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
- struct btrfs_dir_item *di;
+ struct btrfs_dir_item *di = NULL;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
size_t name_len = strlen(name);
@@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
+ path->skip_release_on_error = 1;
+
+ if (!value) {
+ di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
+ name, name_len, -1);
+ if (!di && (flags & XATTR_REPLACE))
+ ret = -ENODATA;
+ else if (di)
+ ret = btrfs_delete_one_dir_name(trans, root, path, di);
+ goto out;
+ }
+ /*
+ * For a replace we can't just do the insert blindly.
+ * Do a lookup first (read-only btrfs_search_slot), and return if xattr
+ * doesn't exist. If it exists, fall down below to the insert/replace
+ * path - we can't race with a concurrent xattr delete, because the VFS
+ * locks the inode's i_mutex before calling setxattr or removexattr.
+ */
if (flags & XATTR_REPLACE) {
- di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name,
- name_len, -1);
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
- goto out;
- } else if (!di) {
+ ASSERT(mutex_is_locked(&inode->i_mutex));
+ di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
+ name, name_len, 0);
+ if (!di) {
ret = -ENODATA;
goto out;
}
- ret = btrfs_delete_one_dir_name(trans, root, path, di);
- if (ret)
- goto out;
btrfs_release_path(path);
+ di = NULL;
+ }
+ ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
+ name, name_len, value, size);
+ if (ret == -EOVERFLOW) {
/*
- * remove the attribute
+ * We have an existing item in a leaf, split_leaf couldn't
+ * expand it. That item might have or not a dir_item that
+ * matches our target xattr, so lets check.
*/
- if (!value)
- goto out;
- } else {
- di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
- name, name_len, 0);
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
+ ret = 0;
+ btrfs_assert_tree_locked(path->nodes[0]);
+ di = btrfs_match_dir_item_name(root, path, name, name_len);
+ if (!di && !(flags & XATTR_REPLACE)) {
+ ret = -ENOSPC;
goto out;
}
- if (!di && !value)
- goto out;
- btrfs_release_path(path);
+ } else if (ret == -EEXIST) {
+ ret = 0;
+ di = btrfs_match_dir_item_name(root, path, name, name_len);
+ ASSERT(di); /* logic error */
+ } else if (ret) {
+ goto out;
}
-again:
- ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
- name, name_len, value, size);
- /*
- * If we're setting an xattr to a new value but the new value is say
- * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting
- * back from split_leaf. This is because it thinks we'll be extending
- * the existing item size, but we're asking for enough space to add the
- * item itself. So if we get EOVERFLOW just set ret to EEXIST and let
- * the rest of the function figure it out.
- */
- if (ret == -EOVERFLOW)
+ if (di && (flags & XATTR_CREATE)) {
ret = -EEXIST;
+ goto out;
+ }
- if (ret == -EEXIST) {
- if (flags & XATTR_CREATE)
- goto out;
+ if (di) {
/*
- * We can't use the path we already have since we won't have the
- * proper locking for a delete, so release the path and
- * re-lookup to delete the thing.
+ * We're doing a replace, and it must be atomic, that is, at
+ * any point in time we have either the old or the new xattr
+ * value in the tree. We don't want readers (getxattr and
+ * listxattrs) to miss a value, this is specially important
+ * for ACLs.
*/
- btrfs_release_path(path);
- di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
- name, name_len, -1);
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
- goto out;
- } else if (!di) {
- /* Shouldn't happen but just in case... */
- btrfs_release_path(path);
- goto again;
+ const int slot = path->slots[0];
+ struct extent_buffer *leaf = path->nodes[0];
+ const u16 old_data_len = btrfs_dir_data_len(leaf, di);
+ const u32 item_size = btrfs_item_size_nr(leaf, slot);
+ const u32 data_size = sizeof(*di) + name_len + size;
+ struct btrfs_item *item;
+ unsigned long data_ptr;
+ char *ptr;
+
+ if (size > old_data_len) {
+ if (btrfs_leaf_free_space(root, leaf) <
+ (size - old_data_len)) {
+ ret = -ENOSPC;
+ goto out;
+ }
}
- ret = btrfs_delete_one_dir_name(trans, root, path, di);
- if (ret)
- goto out;
+ if (old_data_len + name_len + sizeof(*di) == item_size) {
+ /* No other xattrs packed in the same leaf item. */
+ if (size > old_data_len)
+ btrfs_extend_item(root, path,
+ size - old_data_len);
+ else if (size < old_data_len)
+ btrfs_truncate_item(root, path, data_size, 1);
+ } else {
+ /* There are other xattrs packed in the same item. */
+ ret = btrfs_delete_one_dir_name(trans, root, path, di);
+ if (ret)
+ goto out;
+ btrfs_extend_item(root, path, data_size);
+ }
+ item = btrfs_item_nr(slot);
+ ptr = btrfs_item_ptr(leaf, slot, char);
+ ptr += btrfs_item_size(leaf, item) - data_size;
+ di = (struct btrfs_dir_item *)ptr;
+ btrfs_set_dir_data_len(leaf, di, size);
+ data_ptr = ((unsigned long)(di + 1)) + name_len;
+ write_extent_buffer(leaf, value, data_ptr, size);
+ btrfs_mark_buffer_dirty(leaf);
+ } else {
/*
- * We have a value to set, so go back and try to insert it now.
+ * Insert, and we had space for the xattr, so path->slots[0] is
+ * where our xattr dir_item is and btrfs_insert_xattr_item()
+ * filled it.
*/
- if (value) {
- btrfs_release_path(path);
- goto again;
- }
}
out:
btrfs_free_path(path);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 759fa4e2de8f..fb22fd8d8fb8 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -299,6 +299,8 @@ done:
zlib_inflateEnd(&workspace->strm);
if (data_in)
kunmap(pages_in[page_in_index]);
+ if (!ret)
+ btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
return ret;
}
@@ -310,10 +312,14 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
int wbits = MAX_WBITS;
- unsigned long bytes_left = destlen;
+ unsigned long bytes_left;
unsigned long total_out = 0;
+ unsigned long pg_offset = 0;
char *kaddr;
+ destlen = min_t(unsigned long, destlen, PAGE_SIZE);
+ bytes_left = destlen;
+
workspace->strm.next_in = data_in;
workspace->strm.avail_in = srclen;
workspace->strm.total_in = 0;
@@ -341,7 +347,6 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
unsigned long buf_start;
unsigned long buf_offset;
unsigned long bytes;
- unsigned long pg_offset = 0;
ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
if (ret != Z_OK && ret != Z_STREAM_END)
@@ -384,6 +389,17 @@ next:
ret = 0;
zlib_inflateEnd(&workspace->strm);
+
+ /*
+ * this should only happen if zlib returned fewer bytes than we
+ * expected. btrfs_get_block is responsible for zeroing from the
+ * end of the inline extent (destlen) to the end of the page
+ */
+ if (pg_offset < destlen) {
+ kaddr = kmap_atomic(dest_page);
+ memset(kaddr + pg_offset, 0, destlen - pg_offset);
+ kunmap_atomic(kaddr);
+ }
return ret;
}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index e12f189d539b..7f8e83f9d74e 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -102,8 +102,7 @@ static void cachefiles_mark_object_buried(struct cachefiles_cache *cache,
struct cachefiles_object *object;
struct rb_node *p;
- _enter(",'%*.*s'",
- dentry->d_name.len, dentry->d_name.len, dentry->d_name.name);
+ _enter(",'%pd'", dentry);
write_lock(&cache->active_lock);
@@ -273,9 +272,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
char nbuffer[8 + 8 + 1];
int ret;
- _enter(",'%*.*s','%*.*s'",
- dir->d_name.len, dir->d_name.len, dir->d_name.name,
- rep->d_name.len, rep->d_name.len, rep->d_name.name);
+ _enter(",'%pd','%pd'", dir, rep);
_debug("remove %p from %p", rep, dir);
@@ -597,8 +594,7 @@ lookup_again:
/* if we've found that the terminal object exists, then we need to
* check its attributes and delete it if it's out of date */
if (!object->new) {
- _debug("validate '%*.*s'",
- next->d_name.len, next->d_name.len, next->d_name.name);
+ _debug("validate '%pd'", next);
ret = cachefiles_check_object_xattr(object, auxdata);
if (ret == -ESTALE) {
@@ -827,8 +823,8 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
unsigned long start;
int ret;
- //_enter(",%*.*s/,%s",
- // dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+ //_enter(",%pd/,%s",
+ // dir, filename);
/* look up the victim */
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
@@ -910,8 +906,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
struct dentry *victim;
int ret;
- _enter(",%*.*s/,%s",
- dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+ _enter(",%pd/,%s", dir, filename);
victim = cachefiles_check_active(cache, dir, filename);
if (IS_ERR(victim))
@@ -969,8 +964,8 @@ int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
{
struct dentry *victim;
- //_enter(",%*.*s/,%s",
- // dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+ //_enter(",%pd/,%s",
+ // dir, filename);
victim = cachefiles_check_active(cache, dir, filename);
if (IS_ERR(victim))
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index acbc1f094fb1..a8a68745e11d 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -51,9 +51,8 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
}
if (ret != -EEXIST) {
- pr_err("Can't set xattr on %*.*s [%lu] (err %d)\n",
- dentry->d_name.len, dentry->d_name.len,
- dentry->d_name.name, dentry->d_inode->i_ino,
+ pr_err("Can't set xattr on %pd [%lu] (err %d)\n",
+ dentry, dentry->d_inode->i_ino,
-ret);
goto error;
}
@@ -64,9 +63,8 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
if (ret == -ERANGE)
goto bad_type_length;
- pr_err("Can't read xattr on %*.*s [%lu] (err %d)\n",
- dentry->d_name.len, dentry->d_name.len,
- dentry->d_name.name, dentry->d_inode->i_ino,
+ pr_err("Can't read xattr on %pd [%lu] (err %d)\n",
+ dentry, dentry->d_inode->i_ino,
-ret);
goto error;
}
@@ -92,9 +90,8 @@ bad_type_length:
bad_type:
xtype[2] = 0;
- pr_err("Cache object %*.*s [%lu] type %s not %s\n",
- dentry->d_name.len, dentry->d_name.len,
- dentry->d_name.name, dentry->d_inode->i_ino,
+ pr_err("Cache object %pd [%lu] type %s not %s\n",
+ dentry, dentry->d_inode->i_ino,
xtype, type);
ret = -EIO;
goto error;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 18c06bbaf136..f5013d92a7e6 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -192,17 +192,30 @@ static int readpage_nounlock(struct file *filp, struct page *page)
struct ceph_osd_client *osdc =
&ceph_inode_to_client(inode)->client->osdc;
int err = 0;
+ u64 off = page_offset(page);
u64 len = PAGE_CACHE_SIZE;
- err = ceph_readpage_from_fscache(inode, page);
+ if (off >= i_size_read(inode)) {
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ SetPageUptodate(page);
+ return 0;
+ }
+ /*
+ * Uptodate inline data should have been added into page cache
+ * while getting Fcr caps.
+ */
+ if (ci->i_inline_version != CEPH_INLINE_NONE)
+ return -EINVAL;
+
+ err = ceph_readpage_from_fscache(inode, page);
if (err == 0)
goto out;
dout("readpage inode %p file %p page %p index %lu\n",
inode, filp, page, page->index);
err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
- (u64) page_offset(page), &len,
+ off, &len,
ci->i_truncate_seq, ci->i_truncate_size,
&page, 1, 0);
if (err == -ENOENT)
@@ -319,7 +332,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
off, len);
vino = ceph_vino(inode);
req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
- 1, CEPH_OSD_OP_READ,
+ 0, 1, CEPH_OSD_OP_READ,
CEPH_OSD_FLAG_READ, NULL,
ci->i_truncate_seq, ci->i_truncate_size,
false);
@@ -384,6 +397,9 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
int rc = 0;
int max = 0;
+ if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE)
+ return -EINVAL;
+
rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
&nr_pages);
@@ -673,7 +689,7 @@ static int ceph_writepages_start(struct address_space *mapping,
int rc = 0;
unsigned wsize = 1 << inode->i_blkbits;
struct ceph_osd_request *req = NULL;
- int do_sync;
+ int do_sync = 0;
u64 truncate_size, snap_size;
u32 truncate_seq;
@@ -750,7 +766,6 @@ retry:
last_snapc = snapc;
while (!done && index <= end) {
- int num_ops = do_sync ? 2 : 1;
unsigned i;
int first;
pgoff_t next;
@@ -850,7 +865,8 @@ get_more_pages:
len = wsize;
req = ceph_osdc_new_request(&fsc->client->osdc,
&ci->i_layout, vino,
- offset, &len, num_ops,
+ offset, &len, 0,
+ do_sync ? 2 : 1,
CEPH_OSD_OP_WRITE,
CEPH_OSD_FLAG_WRITE |
CEPH_OSD_FLAG_ONDISK,
@@ -862,6 +878,9 @@ get_more_pages:
break;
}
+ if (do_sync)
+ osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+
req->r_callback = writepages_finish;
req->r_inode = inode;
@@ -1204,6 +1223,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
struct inode *inode = file_inode(vma->vm_file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = vma->vm_file->private_data;
+ struct page *pinned_page = NULL;
loff_t off = vmf->pgoff << PAGE_CACHE_SHIFT;
int want, got, ret;
@@ -1215,7 +1235,8 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
want = CEPH_CAP_FILE_CACHE;
while (1) {
got = 0;
- ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, &got, -1);
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want,
+ -1, &got, &pinned_page);
if (ret == 0)
break;
if (ret != -ERESTARTSYS) {
@@ -1226,12 +1247,54 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
dout("filemap_fault %p %llu~%zd got cap refs on %s\n",
inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got));
- ret = filemap_fault(vma, vmf);
+ if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
+ ci->i_inline_version == CEPH_INLINE_NONE)
+ ret = filemap_fault(vma, vmf);
+ else
+ ret = -EAGAIN;
dout("filemap_fault %p %llu~%zd dropping cap refs on %s ret %d\n",
inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got), ret);
+ if (pinned_page)
+ page_cache_release(pinned_page);
ceph_put_cap_refs(ci, got);
+ if (ret != -EAGAIN)
+ return ret;
+
+ /* read inline data */
+ if (off >= PAGE_CACHE_SIZE) {
+ /* does not support inline data > PAGE_SIZE */
+ ret = VM_FAULT_SIGBUS;
+ } else {
+ int ret1;
+ struct address_space *mapping = inode->i_mapping;
+ struct page *page = find_or_create_page(mapping, 0,
+ mapping_gfp_mask(mapping) &
+ ~__GFP_FS);
+ if (!page) {
+ ret = VM_FAULT_OOM;
+ goto out;
+ }
+ ret1 = __ceph_do_getattr(inode, page,
+ CEPH_STAT_CAP_INLINE_DATA, true);
+ if (ret1 < 0 || off >= i_size_read(inode)) {
+ unlock_page(page);
+ page_cache_release(page);
+ ret = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if (ret1 < PAGE_CACHE_SIZE)
+ zero_user_segment(page, ret1, PAGE_CACHE_SIZE);
+ else
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ vmf->page = page;
+ ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
+ }
+out:
+ dout("filemap_fault %p %llu~%zd read inline data ret %d\n",
+ inode, off, (size_t)PAGE_CACHE_SIZE, ret);
return ret;
}
@@ -1250,6 +1313,19 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
size_t len;
int want, got, ret;
+ if (ci->i_inline_version != CEPH_INLINE_NONE) {
+ struct page *locked_page = NULL;
+ if (off == 0) {
+ lock_page(page);
+ locked_page = page;
+ }
+ ret = ceph_uninline_data(vma->vm_file, locked_page);
+ if (locked_page)
+ unlock_page(locked_page);
+ if (ret < 0)
+ return VM_FAULT_SIGBUS;
+ }
+
if (off + PAGE_CACHE_SIZE <= size)
len = PAGE_CACHE_SIZE;
else
@@ -1263,7 +1339,8 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
want = CEPH_CAP_FILE_BUFFER;
while (1) {
got = 0;
- ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, off + len);
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, off + len,
+ &got, NULL);
if (ret == 0)
break;
if (ret != -ERESTARTSYS) {
@@ -1297,11 +1374,13 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
ret = VM_FAULT_SIGBUS;
}
out:
- if (ret != VM_FAULT_LOCKED) {
+ if (ret != VM_FAULT_LOCKED)
unlock_page(page);
- } else {
+ if (ret == VM_FAULT_LOCKED ||
+ ci->i_inline_version != CEPH_INLINE_NONE) {
int dirty;
spin_lock(&ci->i_ceph_lock);
+ ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
@@ -1315,6 +1394,178 @@ out:
return ret;
}
+void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+ char *data, size_t len)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct page *page;
+
+ if (locked_page) {
+ page = locked_page;
+ } else {
+ if (i_size_read(inode) == 0)
+ return;
+ page = find_or_create_page(mapping, 0,
+ mapping_gfp_mask(mapping) & ~__GFP_FS);
+ if (!page)
+ return;
+ if (PageUptodate(page)) {
+ unlock_page(page);
+ page_cache_release(page);
+ return;
+ }
+ }
+
+ dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+ inode, ceph_vinop(inode), len, locked_page);
+
+ if (len > 0) {
+ void *kaddr = kmap_atomic(page);
+ memcpy(kaddr, data, len);
+ kunmap_atomic(kaddr);
+ }
+
+ if (page != locked_page) {
+ if (len < PAGE_CACHE_SIZE)
+ zero_user_segment(page, len, PAGE_CACHE_SIZE);
+ else
+ flush_dcache_page(page);
+
+ SetPageUptodate(page);
+ unlock_page(page);
+ page_cache_release(page);
+ }
+}
+
+int ceph_uninline_data(struct file *filp, struct page *locked_page)
+{
+ struct inode *inode = file_inode(filp);
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+ struct ceph_osd_request *req;
+ struct page *page = NULL;
+ u64 len, inline_version;
+ int err = 0;
+ bool from_pagecache = false;
+
+ spin_lock(&ci->i_ceph_lock);
+ inline_version = ci->i_inline_version;
+ spin_unlock(&ci->i_ceph_lock);
+
+ dout("uninline_data %p %llx.%llx inline_version %llu\n",
+ inode, ceph_vinop(inode), inline_version);
+
+ if (inline_version == 1 || /* initial version, no data */
+ inline_version == CEPH_INLINE_NONE)
+ goto out;
+
+ if (locked_page) {
+ page = locked_page;
+ WARN_ON(!PageUptodate(page));
+ } else if (ceph_caps_issued(ci) &
+ (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) {
+ page = find_get_page(inode->i_mapping, 0);
+ if (page) {
+ if (PageUptodate(page)) {
+ from_pagecache = true;
+ lock_page(page);
+ } else {
+ page_cache_release(page);
+ page = NULL;
+ }
+ }
+ }
+
+ if (page) {
+ len = i_size_read(inode);
+ if (len > PAGE_CACHE_SIZE)
+ len = PAGE_CACHE_SIZE;
+ } else {
+ page = __page_cache_alloc(GFP_NOFS);
+ if (!page) {
+ err = -ENOMEM;
+ goto out;
+ }
+ err = __ceph_do_getattr(inode, page,
+ CEPH_STAT_CAP_INLINE_DATA, true);
+ if (err < 0) {
+ /* no inline data */
+ if (err == -ENODATA)
+ err = 0;
+ goto out;
+ }
+ len = err;
+ }
+
+ req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
+ ceph_vino(inode), 0, &len, 0, 1,
+ CEPH_OSD_OP_CREATE,
+ CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
+ ci->i_snap_realm->cached_context,
+ 0, 0, false);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ goto out;
+ }
+
+ ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
+ err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
+ if (!err)
+ err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_put_request(req);
+ if (err < 0)
+ goto out;
+
+ req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
+ ceph_vino(inode), 0, &len, 1, 3,
+ CEPH_OSD_OP_WRITE,
+ CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
+ ci->i_snap_realm->cached_context,
+ ci->i_truncate_seq, ci->i_truncate_size,
+ false);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ goto out;
+ }
+
+ osd_req_op_extent_osd_data_pages(req, 1, &page, len, 0, false, false);
+
+ err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR,
+ "inline_version", &inline_version,
+ sizeof(inline_version),
+ CEPH_OSD_CMPXATTR_OP_GT,
+ CEPH_OSD_CMPXATTR_MODE_U64);
+ if (err)
+ goto out_put;
+
+ err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR,
+ "inline_version", &inline_version,
+ sizeof(inline_version), 0, 0);
+ if (err)
+ goto out_put;
+
+ ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
+ err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
+ if (!err)
+ err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+out_put:
+ ceph_osdc_put_request(req);
+ if (err == -ECANCELED)
+ err = 0;
+out:
+ if (page && page != locked_page) {
+ if (from_pagecache) {
+ unlock_page(page);
+ page_cache_release(page);
+ } else
+ __free_pages(page, 0);
+ }
+
+ dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
+ inode, ceph_vinop(inode), inline_version, err);
+ return err;
+}
+
static struct vm_operations_struct ceph_vmops = {
.fault = ceph_filemap_fault,
.page_mkwrite = ceph_page_mkwrite,
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 659f2ea9e6f7..b93c631c6c87 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -975,10 +975,12 @@ static int send_cap_msg(struct ceph_mds_session *session,
kuid_t uid, kgid_t gid, umode_t mode,
u64 xattr_version,
struct ceph_buffer *xattrs_buf,
- u64 follows)
+ u64 follows, bool inline_data)
{
struct ceph_mds_caps *fc;
struct ceph_msg *msg;
+ void *p;
+ size_t extra_len;
dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
" seq %u/%u mseq %u follows %lld size %llu/%llu"
@@ -988,7 +990,10 @@ static int send_cap_msg(struct ceph_mds_session *session,
seq, issue_seq, mseq, follows, size, max_size,
xattr_version, xattrs_buf ? (int)xattrs_buf->vec.iov_len : 0);
- msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc), GFP_NOFS, false);
+ /* flock buffer size + inline version + inline data size */
+ extra_len = 4 + 8 + 4;
+ msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc) + extra_len,
+ GFP_NOFS, false);
if (!msg)
return -ENOMEM;
@@ -1020,6 +1025,14 @@ static int send_cap_msg(struct ceph_mds_session *session,
fc->gid = cpu_to_le32(from_kgid(&init_user_ns, gid));
fc->mode = cpu_to_le32(mode);
+ p = fc + 1;
+ /* flock buffer size */
+ ceph_encode_32(&p, 0);
+ /* inline version */
+ ceph_encode_64(&p, inline_data ? 0 : CEPH_INLINE_NONE);
+ /* inline data size */
+ ceph_encode_32(&p, 0);
+
fc->xattr_version = cpu_to_le64(xattr_version);
if (xattrs_buf) {
msg->middle = ceph_buffer_get(xattrs_buf);
@@ -1126,6 +1139,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
u64 flush_tid = 0;
int i;
int ret;
+ bool inline_data;
held = cap->issued | cap->implemented;
revoking = cap->implemented & ~cap->issued;
@@ -1209,13 +1223,15 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
xattr_version = ci->i_xattrs.version;
}
+ inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
+
spin_unlock(&ci->i_ceph_lock);
ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
op, keep, want, flushing, seq, flush_tid, issue_seq, mseq,
size, max_size, &mtime, &atime, time_warp_seq,
uid, gid, mode, xattr_version, xattr_blob,
- follows);
+ follows, inline_data);
if (ret < 0) {
dout("error sending cap msg, must requeue %p\n", inode);
delayed = 1;
@@ -1336,7 +1352,7 @@ retry:
capsnap->time_warp_seq,
capsnap->uid, capsnap->gid, capsnap->mode,
capsnap->xattr_version, capsnap->xattr_blob,
- capsnap->follows);
+ capsnap->follows, capsnap->inline_data);
next_follows = capsnap->follows + 1;
ceph_put_cap_snap(capsnap);
@@ -2057,15 +2073,17 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got)
* requested from the MDS.
*/
static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
- int *got, loff_t endoff, int *check_max, int *err)
+ loff_t endoff, int *got, struct page **pinned_page,
+ int *check_max, int *err)
{
struct inode *inode = &ci->vfs_inode;
int ret = 0;
- int have, implemented;
+ int have, implemented, _got = 0;
int file_wanted;
dout("get_cap_refs %p need %s want %s\n", inode,
ceph_cap_string(need), ceph_cap_string(want));
+again:
spin_lock(&ci->i_ceph_lock);
/* make sure file is actually open */
@@ -2075,7 +2093,7 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
ceph_cap_string(need), ceph_cap_string(file_wanted));
*err = -EBADF;
ret = 1;
- goto out;
+ goto out_unlock;
}
/* finish pending truncate */
@@ -2095,7 +2113,7 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
*check_max = 1;
ret = 1;
}
- goto out;
+ goto out_unlock;
}
/*
* If a sync write is in progress, we must wait, so that we
@@ -2103,7 +2121,7 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
*/
if (__ceph_have_pending_cap_snap(ci)) {
dout("get_cap_refs %p cap_snap_pending\n", inode);
- goto out;
+ goto out_unlock;
}
}
@@ -2120,18 +2138,50 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
inode, ceph_cap_string(have), ceph_cap_string(not),
ceph_cap_string(revoking));
if ((revoking & not) == 0) {
- *got = need | (have & want);
- __take_cap_refs(ci, *got);
+ _got = need | (have & want);
+ __take_cap_refs(ci, _got);
ret = 1;
}
} else {
dout("get_cap_refs %p have %s needed %s\n", inode,
ceph_cap_string(have), ceph_cap_string(need));
}
-out:
+out_unlock:
spin_unlock(&ci->i_ceph_lock);
+
+ if (ci->i_inline_version != CEPH_INLINE_NONE &&
+ (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
+ i_size_read(inode) > 0) {
+ int ret1;
+ struct page *page = find_get_page(inode->i_mapping, 0);
+ if (page) {
+ if (PageUptodate(page)) {
+ *pinned_page = page;
+ goto out;
+ }
+ page_cache_release(page);
+ }
+ /*
+ * drop cap refs first because getattr while holding
+ * caps refs can cause deadlock.
+ */
+ ceph_put_cap_refs(ci, _got);
+ _got = 0;
+
+ /* getattr request will bring inline data into page cache */
+ ret1 = __ceph_do_getattr(inode, NULL,
+ CEPH_STAT_CAP_INLINE_DATA, true);
+ if (ret1 >= 0) {
+ ret = 0;
+ goto again;
+ }
+ *err = ret1;
+ ret = 1;
+ }
+out:
dout("get_cap_refs %p ret %d got %s\n", inode,
- ret, ceph_cap_string(*got));
+ ret, ceph_cap_string(_got));
+ *got = _got;
return ret;
}
@@ -2168,8 +2218,8 @@ static void check_max_size(struct inode *inode, loff_t endoff)
* due to a small max_size, make sure we check_max_size (and possibly
* ask the mds) so we don't get hung up indefinitely.
*/
-int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, int *got,
- loff_t endoff)
+int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
+ loff_t endoff, int *got, struct page **pinned_page)
{
int check_max, ret, err;
@@ -2179,8 +2229,8 @@ retry:
check_max = 0;
err = 0;
ret = wait_event_interruptible(ci->i_cap_wq,
- try_get_cap_refs(ci, need, want,
- got, endoff,
+ try_get_cap_refs(ci, need, want, endoff,
+ got, pinned_page,
&check_max, &err));
if (err)
ret = err;
@@ -2383,6 +2433,8 @@ static void invalidate_aliases(struct inode *inode)
static void handle_cap_grant(struct ceph_mds_client *mdsc,
struct inode *inode, struct ceph_mds_caps *grant,
void *snaptrace, int snaptrace_len,
+ u64 inline_version,
+ void *inline_data, int inline_len,
struct ceph_buffer *xattr_buf,
struct ceph_mds_session *session,
struct ceph_cap *cap, int issued)
@@ -2403,6 +2455,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
bool queue_invalidate = false;
bool queue_revalidate = false;
bool deleted_inode = false;
+ bool fill_inline = false;
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2576,6 +2629,13 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
}
BUG_ON(cap->issued & ~cap->implemented);
+ if (inline_version > 0 && inline_version >= ci->i_inline_version) {
+ ci->i_inline_version = inline_version;
+ if (ci->i_inline_version != CEPH_INLINE_NONE &&
+ (newcaps & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)))
+ fill_inline = true;
+ }
+
spin_unlock(&ci->i_ceph_lock);
if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
@@ -2589,6 +2649,9 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
wake = true;
}
+ if (fill_inline)
+ ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
+
if (queue_trunc) {
ceph_queue_vmtruncate(inode);
ceph_queue_revalidate(inode);
@@ -2638,7 +2701,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
for (i = 0; i < CEPH_CAP_BITS; i++)
if ((dirty & (1 << i)) &&
- flush_tid == ci->i_cap_flush_tid[i])
+ (u16)flush_tid == ci->i_cap_flush_tid[i])
cleaned |= 1 << i;
dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s,"
@@ -2996,11 +3059,12 @@ void ceph_handle_caps(struct ceph_mds_session *session,
u64 cap_id;
u64 size, max_size;
u64 tid;
+ u64 inline_version = 0;
+ void *inline_data = NULL;
+ u32 inline_len = 0;
void *snaptrace;
size_t snaptrace_len;
- void *flock;
- void *end;
- u32 flock_len;
+ void *p, *end;
dout("handle_caps from mds%d\n", mds);
@@ -3021,30 +3085,37 @@ void ceph_handle_caps(struct ceph_mds_session *session,
snaptrace = h + 1;
snaptrace_len = le32_to_cpu(h->snap_trace_len);
+ p = snaptrace + snaptrace_len;
if (le16_to_cpu(msg->hdr.version) >= 2) {
- void *p = snaptrace + snaptrace_len;
+ u32 flock_len;
ceph_decode_32_safe(&p, end, flock_len, bad);
if (p + flock_len > end)
goto bad;
- flock = p;
- } else {
- flock = NULL;
- flock_len = 0;
+ p += flock_len;
}
if (le16_to_cpu(msg->hdr.version) >= 3) {
if (op == CEPH_CAP_OP_IMPORT) {
- void *p = flock + flock_len;
if (p + sizeof(*peer) > end)
goto bad;
peer = p;
+ p += sizeof(*peer);
} else if (op == CEPH_CAP_OP_EXPORT) {
/* recorded in unused fields */
peer = (void *)&h->size;
}
}
+ if (le16_to_cpu(msg->hdr.version) >= 4) {
+ ceph_decode_64_safe(&p, end, inline_version, bad);
+ ceph_decode_32_safe(&p, end, inline_len, bad);
+ if (p + inline_len > end)
+ goto bad;
+ inline_data = p;
+ p += inline_len;
+ }
+
/* lookup ino */
inode = ceph_find_inode(sb, vino);
ci = ceph_inode(inode);
@@ -3085,6 +3156,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
handle_cap_import(mdsc, inode, h, peer, session,
&cap, &issued);
handle_cap_grant(mdsc, inode, h, snaptrace, snaptrace_len,
+ inline_version, inline_data, inline_len,
msg->middle, session, cap, issued);
goto done_unlocked;
}
@@ -3105,8 +3177,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
case CEPH_CAP_OP_GRANT:
__ceph_caps_issued(ci, &issued);
issued |= __ceph_caps_dirty(ci);
- handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle,
- session, cap, issued);
+ handle_cap_grant(mdsc, inode, h, NULL, 0,
+ inline_version, inline_data, inline_len,
+ msg->middle, session, cap, issued);
goto done_unlocked;
case CEPH_CAP_OP_FLUSH_ACK:
@@ -3137,8 +3210,7 @@ flush_cap_releases:
done:
mutex_unlock(&session->s_mutex);
done_unlocked:
- if (inode)
- iput(inode);
+ iput(inode);
return;
bad:
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 5d5a4c8c8496..1b2355109b9f 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -83,10 +83,9 @@ static int mdsc_show(struct seq_file *s, void *p)
if (IS_ERR(path))
path = NULL;
spin_lock(&req->r_dentry->d_lock);
- seq_printf(s, " #%llx/%.*s (%s)",
+ seq_printf(s, " #%llx/%pd (%s)",
ceph_ino(req->r_dentry->d_parent->d_inode),
- req->r_dentry->d_name.len,
- req->r_dentry->d_name.name,
+ req->r_dentry,
path ? path : "");
spin_unlock(&req->r_dentry->d_lock);
kfree(path);
@@ -103,11 +102,10 @@ static int mdsc_show(struct seq_file *s, void *p)
if (IS_ERR(path))
path = NULL;
spin_lock(&req->r_old_dentry->d_lock);
- seq_printf(s, " #%llx/%.*s (%s)",
+ seq_printf(s, " #%llx/%pd (%s)",
req->r_old_dentry_dir ?
ceph_ino(req->r_old_dentry_dir) : 0,
- req->r_old_dentry->d_name.len,
- req->r_old_dentry->d_name.name,
+ req->r_old_dentry,
path ? path : "");
spin_unlock(&req->r_old_dentry->d_lock);
kfree(path);
@@ -150,8 +148,8 @@ static int dentry_lru_show(struct seq_file *s, void *ptr)
spin_lock(&mdsc->dentry_lru_lock);
list_for_each_entry(di, &mdsc->dentry_lru, lru) {
struct dentry *dentry = di->dentry;
- seq_printf(s, "%p %p\t%.*s\n",
- di, dentry, dentry->d_name.len, dentry->d_name.name);
+ seq_printf(s, "%p %p\t%pd\n",
+ di, dentry, dentry);
}
spin_unlock(&mdsc->dentry_lru_lock);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index e6d63f8f98c0..c241603764fd 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -111,7 +111,7 @@ static int fpos_cmp(loff_t l, loff_t r)
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
- * d_u.d_child when we initially get results back from the MDS, and
+ * d_child when we initially get results back from the MDS, and
* falling back to a "normal" sync readdir if any dentries in the dir
* are dropped.
*
@@ -123,7 +123,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
u32 shared_gen)
{
struct ceph_file_info *fi = file->private_data;
- struct dentry *parent = file->f_dentry;
+ struct dentry *parent = file->f_path.dentry;
struct inode *dir = parent->d_inode;
struct list_head *p;
struct dentry *dentry, *last;
@@ -147,11 +147,11 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
p = parent->d_subdirs.prev;
dout(" initial p %p/%p\n", p->prev, p->next);
} else {
- p = last->d_u.d_child.prev;
+ p = last->d_child.prev;
}
more:
- dentry = list_entry(p, struct dentry, d_u.d_child);
+ dentry = list_entry(p, struct dentry, d_child);
di = ceph_dentry(dentry);
while (1) {
dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
@@ -168,13 +168,13 @@ more:
ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
fpos_cmp(ctx->pos, di->offset) <= 0)
break;
- dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
- dentry->d_name.len, dentry->d_name.name, di->offset,
+ dout(" skipping %p %pd at %llu (%llu)%s%s\n", dentry,
+ dentry, di->offset,
ctx->pos, d_unhashed(dentry) ? " unhashed" : "",
!dentry->d_inode ? " null" : "");
spin_unlock(&dentry->d_lock);
p = p->prev;
- dentry = list_entry(p, struct dentry, d_u.d_child);
+ dentry = list_entry(p, struct dentry, d_child);
di = ceph_dentry(dentry);
}
@@ -183,15 +183,15 @@ more:
spin_unlock(&parent->d_lock);
/* make sure a dentry wasn't dropped while we didn't have parent lock */
- if (!ceph_dir_is_complete(dir)) {
+ if (!ceph_dir_is_complete_ordered(dir)) {
dout(" lost dir complete on %p; falling back to mds\n", dir);
dput(dentry);
err = -EAGAIN;
goto out;
}
- dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, ctx->pos,
- dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
+ dout(" %llu (%llu) dentry %p %pd %p\n", di->offset, ctx->pos,
+ dentry, dentry, dentry->d_inode);
if (!dir_emit(ctx, dentry->d_name.name,
dentry->d_name.len,
ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino),
@@ -261,10 +261,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
/* always start with . and .. */
if (ctx->pos == 0) {
- /* note dir version at start of readdir so we can tell
- * if any dentries get dropped */
- fi->dir_release_count = atomic_read(&ci->i_release_count);
-
dout("readdir off 0 -> '.'\n");
if (!dir_emit(ctx, ".", 1,
ceph_translate_ino(inode->i_sb, inode->i_ino),
@@ -274,7 +270,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
off = 1;
}
if (ctx->pos == 1) {
- ino_t ino = parent_ino(file->f_dentry);
+ ino_t ino = parent_ino(file->f_path.dentry);
dout("readdir off 1 -> '..'\n");
if (!dir_emit(ctx, "..", 2,
ceph_translate_ino(inode->i_sb, ino),
@@ -289,7 +285,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
if ((ctx->pos == 2 || fi->dentry) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
- __ceph_dir_is_complete(ci) &&
+ __ceph_dir_is_complete_ordered(ci) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
u32 shared_gen = ci->i_shared_gen;
spin_unlock(&ci->i_ceph_lock);
@@ -312,6 +308,13 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
/* proceed with a normal readdir */
+ if (ctx->pos == 2) {
+ /* note dir version at start of readdir so we can tell
+ * if any dentries get dropped */
+ fi->dir_release_count = atomic_read(&ci->i_release_count);
+ fi->dir_ordered_count = ci->i_ordered_count;
+ }
+
more:
/* do we have the correct frag content buffered? */
if (fi->frag != frag || fi->last_readdir == NULL) {
@@ -337,7 +340,7 @@ more:
}
req->r_inode = inode;
ihold(inode);
- req->r_dentry = dget(file->f_dentry);
+ req->r_dentry = dget(file->f_path.dentry);
/* hints to request -> mds selection code */
req->r_direct_mode = USE_AUTH_MDS;
req->r_direct_hash = ceph_frag_value(frag);
@@ -446,8 +449,12 @@ more:
*/
spin_lock(&ci->i_ceph_lock);
if (atomic_read(&ci->i_release_count) == fi->dir_release_count) {
- dout(" marking %p complete\n", inode);
- __ceph_dir_set_complete(ci, fi->dir_release_count);
+ if (ci->i_ordered_count == fi->dir_ordered_count)
+ dout(" marking %p complete and ordered\n", inode);
+ else
+ dout(" marking %p complete\n", inode);
+ __ceph_dir_set_complete(ci, fi->dir_release_count,
+ fi->dir_ordered_count);
}
spin_unlock(&ci->i_ceph_lock);
@@ -538,8 +545,8 @@ int ceph_handle_snapdir(struct ceph_mds_request *req,
strcmp(dentry->d_name.name,
fsc->mount_options->snapdir_name) == 0) {
struct inode *inode = ceph_get_snapdir(parent);
- dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
- dentry, dentry->d_name.len, dentry->d_name.name, inode);
+ dout("ENOENT on snapdir %p '%pd', linking to snapdir %p\n",
+ dentry, dentry, inode);
BUG_ON(!d_unhashed(dentry));
d_add(dentry, inode);
err = 0;
@@ -603,8 +610,8 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
int op;
int err;
- dout("lookup %p dentry %p '%.*s'\n",
- dir, dentry, dentry->d_name.len, dentry->d_name.name);
+ dout("lookup %p dentry %p '%pd'\n",
+ dir, dentry, dentry);
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
@@ -774,8 +781,8 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* mkdir .snap/foo is a MKSNAP */
op = CEPH_MDS_OP_MKSNAP;
- dout("mksnap dir %p snap '%.*s' dn %p\n", dir,
- dentry->d_name.len, dentry->d_name.name, dentry);
+ dout("mksnap dir %p snap '%pd' dn %p\n", dir,
+ dentry, dentry);
} else if (ceph_snap(dir) == CEPH_NOSNAP) {
dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode);
op = CEPH_MDS_OP_MKDIR;
@@ -805,7 +812,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
acls.pagelist = NULL;
}
err = ceph_mdsc_do_request(mdsc, dir, req);
- if (!err && !req->r_reply_info.head->is_dentry)
+ if (!err &&
+ !req->r_reply_info.head->is_target &&
+ !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
out:
@@ -888,8 +897,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* rmdir .snap/foo is RMSNAP */
- dout("rmsnap dir %p '%.*s' dn %p\n", dir, dentry->d_name.len,
- dentry->d_name.name, dentry);
+ dout("rmsnap dir %p '%pd' dn %p\n", dir, dentry, dentry);
op = CEPH_MDS_OP_RMSNAP;
} else if (ceph_snap(dir) == CEPH_NOSNAP) {
dout("unlink/rmdir dir %p dn %p inode %p\n",
@@ -1063,16 +1071,15 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
if (flags & LOOKUP_RCU)
return -ECHILD;
- dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
- dentry->d_name.len, dentry->d_name.name, dentry->d_inode,
- ceph_dentry(dentry)->offset);
+ dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
+ dentry, dentry->d_inode, ceph_dentry(dentry)->offset);
dir = ceph_get_dentry_parent_inode(dentry);
/* always trust cached snapped dentries, snapdir dentry */
if (ceph_snap(dir) != CEPH_NOSNAP) {
- dout("d_revalidate %p '%.*s' inode %p is SNAPPED\n", dentry,
- dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
+ dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
+ dentry, dentry->d_inode);
valid = 1;
} else if (dentry->d_inode &&
ceph_snap(dentry->d_inode) == CEPH_SNAPDIR) {
@@ -1265,8 +1272,7 @@ void ceph_dentry_lru_add(struct dentry *dn)
struct ceph_dentry_info *di = ceph_dentry(dn);
struct ceph_mds_client *mdsc;
- dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
- dn->d_name.len, dn->d_name.name);
+ dout("dentry_lru_add %p %p '%pd'\n", di, dn, dn);
mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
spin_lock(&mdsc->dentry_lru_lock);
list_add_tail(&di->lru, &mdsc->dentry_lru);
@@ -1279,8 +1285,8 @@ void ceph_dentry_lru_touch(struct dentry *dn)
struct ceph_dentry_info *di = ceph_dentry(dn);
struct ceph_mds_client *mdsc;
- dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn,
- dn->d_name.len, dn->d_name.name, di->offset);
+ dout("dentry_lru_touch %p %p '%pd' (offset %lld)\n", di, dn, dn,
+ di->offset);
mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
spin_lock(&mdsc->dentry_lru_lock);
list_move_tail(&di->lru, &mdsc->dentry_lru);
@@ -1292,8 +1298,7 @@ void ceph_dentry_lru_del(struct dentry *dn)
struct ceph_dentry_info *di = ceph_dentry(dn);
struct ceph_mds_client *mdsc;
- dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
- dn->d_name.len, dn->d_name.name);
+ dout("dentry_lru_del %p %p '%pd'\n", di, dn, dn);
mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
spin_lock(&mdsc->dentry_lru_lock);
list_del_init(&di->lru);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d7e0da8366e6..ce74b394b49d 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -211,7 +211,7 @@ int ceph_open(struct inode *inode, struct file *file)
req->r_num_caps = 1;
if (flags & O_CREAT)
- parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
+ parent_inode = ceph_get_dentry_parent_inode(file->f_path.dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
iput(parent_inode);
if (!err)
@@ -238,8 +238,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct ceph_acls_info acls = {};
int err;
- dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n",
- dir, dentry, dentry->d_name.len, dentry->d_name.name,
+ dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
+ dir, dentry, dentry,
d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
if (dentry->d_name.len > NAME_MAX)
@@ -333,6 +333,11 @@ int ceph_release(struct inode *inode, struct file *file)
return 0;
}
+enum {
+ CHECK_EOF = 1,
+ READ_INLINE = 2,
+};
+
/*
* Read a range of bytes striped over one or more objects. Iterate over
* objects we stripe over. (That's not atomic, but good enough for now.)
@@ -412,7 +417,7 @@ more:
ret = read;
/* did we bounce off eof? */
if (pos + left > inode->i_size)
- *checkeof = 1;
+ *checkeof = CHECK_EOF;
}
dout("striped_read returns %d\n", ret);
@@ -598,7 +603,7 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
snapc = ci->i_snap_realm->cached_context;
vino = ceph_vino(inode);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
- vino, pos, &len,
+ vino, pos, &len, 0,
2,/*include a 'startsync' command*/
CEPH_OSD_OP_WRITE, flags, snapc,
ci->i_truncate_seq,
@@ -609,6 +614,8 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
break;
}
+ osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+
n = iov_iter_get_pages_alloc(from, &pages, len, &start);
if (unlikely(n < 0)) {
ret = n;
@@ -713,7 +720,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
snapc = ci->i_snap_realm->cached_context;
vino = ceph_vino(inode);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
- vino, pos, &len, 1,
+ vino, pos, &len, 0, 1,
CEPH_OSD_OP_WRITE, flags, snapc,
ci->i_truncate_seq,
ci->i_truncate_size,
@@ -803,9 +810,10 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
size_t len = iocb->ki_nbytes;
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
+ struct page *pinned_page = NULL;
ssize_t ret;
int want, got = 0;
- int checkeof = 0, read = 0;
+ int retry_op = 0, read = 0;
again:
dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
@@ -815,7 +823,7 @@ again:
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_CACHE;
- ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, &got, -1);
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, -1, &got, &pinned_page);
if (ret < 0)
return ret;
@@ -827,8 +835,12 @@ again:
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- /* hmm, this isn't really async... */
- ret = ceph_sync_read(iocb, to, &checkeof);
+ if (ci->i_inline_version == CEPH_INLINE_NONE) {
+ /* hmm, this isn't really async... */
+ ret = ceph_sync_read(iocb, to, &retry_op);
+ } else {
+ retry_op = READ_INLINE;
+ }
} else {
dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
@@ -838,13 +850,55 @@ again:
}
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
+ if (pinned_page) {
+ page_cache_release(pinned_page);
+ pinned_page = NULL;
+ }
ceph_put_cap_refs(ci, got);
+ if (retry_op && ret >= 0) {
+ int statret;
+ struct page *page = NULL;
+ loff_t i_size;
+ if (retry_op == READ_INLINE) {
+ page = __page_cache_alloc(GFP_NOFS);
+ if (!page)
+ return -ENOMEM;
+ }
- if (checkeof && ret >= 0) {
- int statret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
+ statret = __ceph_do_getattr(inode, page,
+ CEPH_STAT_CAP_INLINE_DATA, !!page);
+ if (statret < 0) {
+ __free_page(page);
+ if (statret == -ENODATA) {
+ BUG_ON(retry_op != READ_INLINE);
+ goto again;
+ }
+ return statret;
+ }
+
+ i_size = i_size_read(inode);
+ if (retry_op == READ_INLINE) {
+ /* does not support inline data > PAGE_SIZE */
+ if (i_size > PAGE_CACHE_SIZE) {
+ ret = -EIO;
+ } else if (iocb->ki_pos < i_size) {
+ loff_t end = min_t(loff_t, i_size,
+ iocb->ki_pos + len);
+ if (statret < end)
+ zero_user_segment(page, statret, end);
+ ret = copy_page_to_iter(page,
+ iocb->ki_pos & ~PAGE_MASK,
+ end - iocb->ki_pos, to);
+ iocb->ki_pos += ret;
+ } else {
+ ret = 0;
+ }
+ __free_pages(page, 0);
+ return ret;
+ }
/* hit EOF or hole? */
- if (statret == 0 && iocb->ki_pos < inode->i_size &&
+ if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
ret < len) {
dout("sync_read hit hole, ppos %lld < size %lld"
", reading more\n", iocb->ki_pos,
@@ -852,7 +906,7 @@ again:
read += ret;
len -= ret;
- checkeof = 0;
+ retry_op = 0;
goto again;
}
}
@@ -909,6 +963,12 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (err)
goto out;
+ if (ci->i_inline_version != CEPH_INLINE_NONE) {
+ err = ceph_uninline_data(file, NULL);
+ if (err < 0)
+ goto out;
+ }
+
retry_snap:
if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
err = -ENOSPC;
@@ -922,7 +982,8 @@ retry_snap:
else
want = CEPH_CAP_FILE_BUFFER;
got = 0;
- err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos + count);
+ err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, pos + count,
+ &got, NULL);
if (err < 0)
goto out;
@@ -969,6 +1030,7 @@ retry_snap:
if (written >= 0) {
int dirty;
spin_lock(&ci->i_ceph_lock);
+ ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
@@ -1111,7 +1173,7 @@ static int ceph_zero_partial_object(struct inode *inode,
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
ceph_vino(inode),
offset, length,
- 1, op,
+ 0, 1, op,
CEPH_OSD_FLAG_WRITE |
CEPH_OSD_FLAG_ONDISK,
NULL, 0, 0, false);
@@ -1214,6 +1276,12 @@ static long ceph_fallocate(struct file *file, int mode,
goto unlock;
}
+ if (ci->i_inline_version != CEPH_INLINE_NONE) {
+ ret = ceph_uninline_data(file, NULL);
+ if (ret < 0)
+ goto unlock;
+ }
+
size = i_size_read(inode);
if (!(mode & FALLOC_FL_KEEP_SIZE))
endoff = offset + length;
@@ -1223,7 +1291,7 @@ static long ceph_fallocate(struct file *file, int mode,
else
want = CEPH_CAP_FILE_BUFFER;
- ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
+ ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, endoff, &got, NULL);
if (ret < 0)
goto unlock;
@@ -1240,6 +1308,7 @@ static long ceph_fallocate(struct file *file, int mode,
if (!ret) {
spin_lock(&ci->i_ceph_lock);
+ ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 7b6139004401..f61a74115beb 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -387,8 +387,10 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
spin_lock_init(&ci->i_ceph_lock);
ci->i_version = 0;
+ ci->i_inline_version = 0;
ci->i_time_warp_seq = 0;
ci->i_ceph_flags = 0;
+ ci->i_ordered_count = 0;
atomic_set(&ci->i_release_count, 1);
atomic_set(&ci->i_complete_count, 0);
ci->i_symlink = NULL;
@@ -657,7 +659,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
* Populate an inode based on info from mds. May be called on new or
* existing inodes.
*/
-static int fill_inode(struct inode *inode,
+static int fill_inode(struct inode *inode, struct page *locked_page,
struct ceph_mds_reply_info_in *iinfo,
struct ceph_mds_reply_dirfrag *dirinfo,
struct ceph_mds_session *session,
@@ -675,6 +677,7 @@ static int fill_inode(struct inode *inode,
bool wake = false;
bool queue_trunc = false;
bool new_version = false;
+ bool fill_inline = false;
dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
inode, ceph_vinop(inode), le64_to_cpu(info->version),
@@ -845,7 +848,8 @@ static int fill_inode(struct inode *inode,
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
!__ceph_dir_is_complete(ci)) {
dout(" marking %p complete (empty)\n", inode);
- __ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
+ __ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count),
+ ci->i_ordered_count);
}
/* were we issued a capability? */
@@ -873,8 +877,23 @@ static int fill_inode(struct inode *inode,
ceph_vinop(inode));
__ceph_get_fmode(ci, cap_fmode);
}
+
+ if (iinfo->inline_version > 0 &&
+ iinfo->inline_version >= ci->i_inline_version) {
+ int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
+ ci->i_inline_version = iinfo->inline_version;
+ if (ci->i_inline_version != CEPH_INLINE_NONE &&
+ (locked_page ||
+ (le32_to_cpu(info->cap.caps) & cache_caps)))
+ fill_inline = true;
+ }
+
spin_unlock(&ci->i_ceph_lock);
+ if (fill_inline)
+ ceph_fill_inline_data(inode, locked_page,
+ iinfo->inline_data, iinfo->inline_len);
+
if (wake)
wake_up_all(&ci->i_cap_wq);
@@ -967,7 +986,7 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
/* dn must be unhashed */
if (!d_unhashed(dn))
d_drop(dn);
- realdn = d_materialise_unique(dn, in);
+ realdn = d_splice_alias(in, dn);
if (IS_ERR(realdn)) {
pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
PTR_ERR(realdn), dn, in, ceph_vinop(in));
@@ -1062,7 +1081,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
struct inode *dir = req->r_locked_dir;
if (dir) {
- err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
+ err = fill_inode(dir, NULL,
+ &rinfo->diri, rinfo->dirfrag,
session, req->r_request_started, -1,
&req->r_caps_reservation);
if (err < 0)
@@ -1132,7 +1152,7 @@ retry_lookup:
}
req->r_target_inode = in;
- err = fill_inode(in, &rinfo->targeti, NULL,
+ err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
session, req->r_request_started,
(!req->r_aborted && rinfo->head->result == 0) ?
req->r_fmode : -1,
@@ -1186,28 +1206,26 @@ retry_lookup:
struct inode *olddir = req->r_old_dentry_dir;
BUG_ON(!olddir);
- dout(" src %p '%.*s' dst %p '%.*s'\n",
+ dout(" src %p '%pd' dst %p '%pd'\n",
+ req->r_old_dentry,
req->r_old_dentry,
- req->r_old_dentry->d_name.len,
- req->r_old_dentry->d_name.name,
- dn, dn->d_name.len, dn->d_name.name);
+ dn, dn);
dout("fill_trace doing d_move %p -> %p\n",
req->r_old_dentry, dn);
d_move(req->r_old_dentry, dn);
- dout(" src %p '%.*s' dst %p '%.*s'\n",
+ dout(" src %p '%pd' dst %p '%pd'\n",
req->r_old_dentry,
- req->r_old_dentry->d_name.len,
- req->r_old_dentry->d_name.name,
- dn, dn->d_name.len, dn->d_name.name);
+ req->r_old_dentry,
+ dn, dn);
/* ensure target dentry is invalidated, despite
rehashing bug in vfs_rename_dir */
ceph_invalidate_dentry_lease(dn);
/* d_move screws up sibling dentries' offsets */
- ceph_dir_clear_complete(dir);
- ceph_dir_clear_complete(olddir);
+ ceph_dir_clear_ordered(dir);
+ ceph_dir_clear_ordered(olddir);
dout("dn %p gets new offset %lld\n", req->r_old_dentry,
ceph_dentry(req->r_old_dentry)->offset);
@@ -1219,6 +1237,7 @@ retry_lookup:
if (!rinfo->head->is_target) {
dout("fill_trace null dentry\n");
if (dn->d_inode) {
+ ceph_dir_clear_ordered(dir);
dout("d_delete %p\n", dn);
d_delete(dn);
} else {
@@ -1235,7 +1254,7 @@ retry_lookup:
/* attach proper inode */
if (!dn->d_inode) {
- ceph_dir_clear_complete(dir);
+ ceph_dir_clear_ordered(dir);
ihold(in);
dn = splice_dentry(dn, in, &have_lease);
if (IS_ERR(dn)) {
@@ -1265,7 +1284,7 @@ retry_lookup:
BUG_ON(!dir);
BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR);
dout(" linking snapped dir %p to dn %p\n", in, dn);
- ceph_dir_clear_complete(dir);
+ ceph_dir_clear_ordered(dir);
ihold(in);
dn = splice_dentry(dn, in, NULL);
if (IS_ERR(dn)) {
@@ -1302,7 +1321,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
dout("new_inode badness got %d\n", err);
continue;
}
- rc = fill_inode(in, &rinfo->dir_in[i], NULL, session,
+ rc = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
req->r_request_started, -1,
&req->r_caps_reservation);
if (rc < 0) {
@@ -1399,7 +1418,7 @@ retry_lookup:
/* reorder parent's d_subdirs */
spin_lock(&parent->d_lock);
spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&dn->d_u.d_child, &parent->d_subdirs);
+ list_move(&dn->d_child, &parent->d_subdirs);
spin_unlock(&dn->d_lock);
spin_unlock(&parent->d_lock);
}
@@ -1418,7 +1437,7 @@ retry_lookup:
}
}
- if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
+ if (fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
req->r_request_started, -1,
&req->r_caps_reservation) < 0) {
pr_err("fill_inode badness on %p\n", in);
@@ -1901,7 +1920,8 @@ out_put:
* Verify that we have a lease on the given mask. If not,
* do a getattr against an mds.
*/
-int ceph_do_getattr(struct inode *inode, int mask, bool force)
+int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+ int mask, bool force)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1913,7 +1933,8 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
return 0;
}
- dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
+ dout("do_getattr inode %p mask %s mode 0%o\n",
+ inode, ceph_cap_string(mask), inode->i_mode);
if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
return 0;
@@ -1924,7 +1945,19 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
ihold(inode);
req->r_num_caps = 1;
req->r_args.getattr.mask = cpu_to_le32(mask);
+ req->r_locked_page = locked_page;
err = ceph_mdsc_do_request(mdsc, NULL, req);
+ if (locked_page && err == 0) {
+ u64 inline_version = req->r_reply_info.targeti.inline_version;
+ if (inline_version == 0) {
+ /* the reply is supposed to contain inline data */
+ err = -EINVAL;
+ } else if (inline_version == CEPH_INLINE_NONE) {
+ err = -ENODATA;
+ } else {
+ err = req->r_reply_info.targeti.inline_len;
+ }
+ }
ceph_mdsc_put_request(req);
dout("do_getattr result=%d\n", err);
return err;
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index fbc39c47bacd..c35c5c614e38 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -9,6 +9,8 @@
#include <linux/ceph/pagelist.h>
static u64 lock_secret;
+static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
+ struct ceph_mds_request *req);
static inline u64 secure_addr(void *addr)
{
@@ -40,6 +42,9 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
u64 length = 0;
u64 owner;
+ if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK)
+ wait = 0;
+
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -68,6 +73,9 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
req->r_args.filelock_change.length = cpu_to_le64(length);
req->r_args.filelock_change.wait = wait;
+ if (wait)
+ req->r_wait_for_completion = ceph_lock_wait_for_completion;
+
err = ceph_mdsc_do_request(mdsc, inode, req);
if (operation == CEPH_MDS_OP_GETFILELOCK) {
@@ -96,6 +104,52 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
return err;
}
+static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
+ struct ceph_mds_request *req)
+{
+ struct ceph_mds_request *intr_req;
+ struct inode *inode = req->r_inode;
+ int err, lock_type;
+
+ BUG_ON(req->r_op != CEPH_MDS_OP_SETFILELOCK);
+ if (req->r_args.filelock_change.rule == CEPH_LOCK_FCNTL)
+ lock_type = CEPH_LOCK_FCNTL_INTR;
+ else if (req->r_args.filelock_change.rule == CEPH_LOCK_FLOCK)
+ lock_type = CEPH_LOCK_FLOCK_INTR;
+ else
+ BUG_ON(1);
+ BUG_ON(req->r_args.filelock_change.type == CEPH_LOCK_UNLOCK);
+
+ err = wait_for_completion_interruptible(&req->r_completion);
+ if (!err)
+ return 0;
+
+ dout("ceph_lock_wait_for_completion: request %llu was interrupted\n",
+ req->r_tid);
+
+ intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK,
+ USE_AUTH_MDS);
+ if (IS_ERR(intr_req))
+ return PTR_ERR(intr_req);
+
+ intr_req->r_inode = inode;
+ ihold(inode);
+ intr_req->r_num_caps = 1;
+
+ intr_req->r_args.filelock_change = req->r_args.filelock_change;
+ intr_req->r_args.filelock_change.rule = lock_type;
+ intr_req->r_args.filelock_change.type = CEPH_LOCK_UNLOCK;
+
+ err = ceph_mdsc_do_request(mdsc, inode, intr_req);
+ ceph_mdsc_put_request(intr_req);
+
+ if (err && err != -ERESTARTSYS)
+ return err;
+
+ wait_for_completion(&req->r_completion);
+ return 0;
+}
+
/**
* Attempt to set an fcntl lock.
* For now, this just goes away to the server. Later it may be more awesome.
@@ -143,11 +197,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
err);
}
}
-
- } else if (err == -ERESTARTSYS) {
- dout("undoing lock\n");
- ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
- CEPH_LOCK_UNLOCK, 0, fl);
}
return err;
}
@@ -186,11 +235,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
file, CEPH_LOCK_UNLOCK, 0, fl);
dout("got %d on flock_lock_file_wait, undid lock", err);
}
- } else if (err == -ERESTARTSYS) {
- dout("undoing lock\n");
- ceph_lock_message(CEPH_LOCK_FLOCK,
- CEPH_MDS_OP_SETFILELOCK,
- file, CEPH_LOCK_UNLOCK, 0, fl);
}
return err;
}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a92d3f5c6c12..d2171f4a6980 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -89,6 +89,16 @@ static int parse_reply_info_in(void **p, void *end,
ceph_decode_need(p, end, info->xattr_len, bad);
info->xattr_data = *p;
*p += info->xattr_len;
+
+ if (features & CEPH_FEATURE_MDS_INLINE_DATA) {
+ ceph_decode_64_safe(p, end, info->inline_version, bad);
+ ceph_decode_32_safe(p, end, info->inline_len, bad);
+ ceph_decode_need(p, end, info->inline_len, bad);
+ info->inline_data = *p;
+ *p += info->inline_len;
+ } else
+ info->inline_version = CEPH_INLINE_NONE;
+
return 0;
bad:
return err;
@@ -524,8 +534,7 @@ void ceph_mdsc_release_request(struct kref *kref)
}
if (req->r_locked_dir)
ceph_put_cap_refs(ceph_inode(req->r_locked_dir), CEPH_CAP_PIN);
- if (req->r_target_inode)
- iput(req->r_target_inode);
+ iput(req->r_target_inode);
if (req->r_dentry)
dput(req->r_dentry);
if (req->r_old_dentry)
@@ -861,8 +870,11 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
/*
* Serialize client metadata into waiting buffer space, using
* the format that userspace expects for map<string, string>
+ *
+ * ClientSession messages with metadata are v2
*/
- msg->hdr.version = 2; /* ClientSession messages with metadata are v2 */
+ msg->hdr.version = cpu_to_le16(2);
+ msg->hdr.compat_version = cpu_to_le16(1);
/* The write pointer, following the session_head structure */
p = msg->front.iov_base + sizeof(*h);
@@ -1066,8 +1078,7 @@ out:
session->s_cap_iterator = NULL;
spin_unlock(&session->s_cap_lock);
- if (last_inode)
- iput(last_inode);
+ iput(last_inode);
if (old_cap)
ceph_put_cap(session->s_mdsc, old_cap);
@@ -1874,7 +1885,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
goto out_free2;
}
- msg->hdr.version = 2;
+ msg->hdr.version = cpu_to_le16(2);
msg->hdr.tid = cpu_to_le64(req->r_tid);
head = msg->front.iov_base;
@@ -2208,6 +2219,8 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
&req->r_completion, req->r_timeout);
if (err == 0)
err = -EIO;
+ } else if (req->r_wait_for_completion) {
+ err = req->r_wait_for_completion(mdsc, req);
} else {
err = wait_for_completion_killable(&req->r_completion);
}
@@ -3744,6 +3757,20 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con,
return msg;
}
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+ struct ceph_mds_session *s = con->private;
+ struct ceph_auth_handshake *auth = &s->s_auth;
+ return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+ struct ceph_mds_session *s = con->private;
+ struct ceph_auth_handshake *auth = &s->s_auth;
+ return ceph_auth_check_message_signature(auth, msg);
+}
+
static const struct ceph_connection_operations mds_con_ops = {
.get = con_get,
.put = con_put,
@@ -3753,6 +3780,8 @@ static const struct ceph_connection_operations mds_con_ops = {
.invalidate_authorizer = invalidate_authorizer,
.peer_reset = peer_reset,
.alloc_msg = mds_alloc_msg,
+ .sign_message = sign_message,
+ .check_message_signature = check_message_signature,
};
/* eof */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3288359353e9..e2817d00f7d9 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -41,6 +41,9 @@ struct ceph_mds_reply_info_in {
char *symlink;
u32 xattr_len;
char *xattr_data;
+ u64 inline_version;
+ u32 inline_len;
+ char *inline_data;
};
/*
@@ -166,6 +169,11 @@ struct ceph_mds_client;
*/
typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
struct ceph_mds_request *req);
+/*
+ * wait for request completion callback
+ */
+typedef int (*ceph_mds_request_wait_callback_t) (struct ceph_mds_client *mdsc,
+ struct ceph_mds_request *req);
/*
* an in-flight mds request
@@ -215,6 +223,7 @@ struct ceph_mds_request {
int r_request_release_offset;
struct ceph_msg *r_reply;
struct ceph_mds_reply_info_parsed r_reply_info;
+ struct page *r_locked_page;
int r_err;
bool r_aborted;
@@ -239,6 +248,7 @@ struct ceph_mds_request {
struct completion r_completion;
struct completion r_safe_completion;
ceph_mds_request_callback_t r_callback;
+ ceph_mds_request_wait_callback_t r_wait_for_completion;
struct list_head r_unsafe_item; /* per-session unsafe list item */
bool r_got_unsafe, r_got_safe, r_got_result;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index f01645a27752..ce35fbd4ba5d 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -288,6 +288,9 @@ static int cmpu64_rev(const void *a, const void *b)
return 0;
}
+
+static struct ceph_snap_context *empty_snapc;
+
/*
* build the snap context for a given realm.
*/
@@ -328,6 +331,12 @@ static int build_snap_context(struct ceph_snap_realm *realm)
return 0;
}
+ if (num == 0 && realm->seq == empty_snapc->seq) {
+ ceph_get_snap_context(empty_snapc);
+ snapc = empty_snapc;
+ goto done;
+ }
+
/* alloc new snap context */
err = -ENOMEM;
if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
@@ -365,8 +374,8 @@ static int build_snap_context(struct ceph_snap_realm *realm)
realm->ino, realm, snapc, snapc->seq,
(unsigned int) snapc->num_snaps);
- if (realm->cached_context)
- ceph_put_snap_context(realm->cached_context);
+done:
+ ceph_put_snap_context(realm->cached_context);
realm->cached_context = snapc;
return 0;
@@ -466,6 +475,9 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
cap_snap. lucky us. */
dout("queue_cap_snap %p already pending\n", inode);
kfree(capsnap);
+ } else if (ci->i_snap_realm->cached_context == empty_snapc) {
+ dout("queue_cap_snap %p empty snapc\n", inode);
+ kfree(capsnap);
} else if (dirty & (CEPH_CAP_AUTH_EXCL|CEPH_CAP_XATTR_EXCL|
CEPH_CAP_FILE_EXCL|CEPH_CAP_FILE_WR)) {
struct ceph_snap_context *snapc = ci->i_head_snapc;
@@ -504,6 +516,8 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
capsnap->xattr_version = 0;
}
+ capsnap->inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
+
/* dirty page count moved from _head to this cap_snap;
all subsequent writes page dirties occur _after_ this
snapshot. */
@@ -590,15 +604,13 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
if (!inode)
continue;
spin_unlock(&realm->inodes_with_caps_lock);
- if (lastinode)
- iput(lastinode);
+ iput(lastinode);
lastinode = inode;
ceph_queue_cap_snap(ci);
spin_lock(&realm->inodes_with_caps_lock);
}
spin_unlock(&realm->inodes_with_caps_lock);
- if (lastinode)
- iput(lastinode);
+ iput(lastinode);
list_for_each_entry(child, &realm->children, child_item) {
dout("queue_realm_cap_snaps %p %llx queue child %p %llx\n",
@@ -928,5 +940,16 @@ out:
return;
}
+int __init ceph_snap_init(void)
+{
+ empty_snapc = ceph_create_snap_context(0, GFP_NOFS);
+ if (!empty_snapc)
+ return -ENOMEM;
+ empty_snapc->seq = 1;
+ return 0;
+}
-
+void ceph_snap_exit(void)
+{
+ ceph_put_snap_context(empty_snapc);
+}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index f6e12377335c..50f06cddc94b 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -515,7 +515,8 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
struct ceph_fs_client *fsc;
const u64 supported_features =
CEPH_FEATURE_FLOCK |
- CEPH_FEATURE_DIRLAYOUTHASH;
+ CEPH_FEATURE_DIRLAYOUTHASH |
+ CEPH_FEATURE_MDS_INLINE_DATA;
const u64 required_features = 0;
int page_count;
size_t size;
@@ -1017,9 +1018,6 @@ static struct file_system_type ceph_fs_type = {
};
MODULE_ALIAS_FS("ceph");
-#define _STRINGIFY(x) #x
-#define STRINGIFY(x) _STRINGIFY(x)
-
static int __init init_ceph(void)
{
int ret = init_caches();
@@ -1028,15 +1026,20 @@ static int __init init_ceph(void)
ceph_flock_init();
ceph_xattr_init();
+ ret = ceph_snap_init();
+ if (ret)
+ goto out_xattr;
ret = register_filesystem(&ceph_fs_type);
if (ret)
- goto out_icache;
+ goto out_snap;
pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
return 0;
-out_icache:
+out_snap:
+ ceph_snap_exit();
+out_xattr:
ceph_xattr_exit();
destroy_caches();
out:
@@ -1047,6 +1050,7 @@ static void __exit exit_ceph(void)
{
dout("exit_ceph\n");
unregister_filesystem(&ceph_fs_type);
+ ceph_snap_exit();
ceph_xattr_exit();
destroy_caches();
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b82f507979b8..e1aa32d0759d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -161,6 +161,7 @@ struct ceph_cap_snap {
u64 time_warp_seq;
int writing; /* a sync write is still in progress */
int dirty_pages; /* dirty pages awaiting writeback */
+ bool inline_data;
};
static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
@@ -253,9 +254,11 @@ struct ceph_inode_info {
spinlock_t i_ceph_lock;
u64 i_version;
+ u64 i_inline_version;
u32 i_time_warp_seq;
unsigned i_ceph_flags;
+ int i_ordered_count;
atomic_t i_release_count;
atomic_t i_complete_count;
@@ -434,14 +437,19 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
/*
* Ceph inode.
*/
-#define CEPH_I_NODELAY 4 /* do not delay cap release */
-#define CEPH_I_FLUSH 8 /* do not delay flush of dirty metadata */
-#define CEPH_I_NOFLUSH 16 /* do not flush dirty caps */
+#define CEPH_I_DIR_ORDERED 1 /* dentries in dir are ordered */
+#define CEPH_I_NODELAY 4 /* do not delay cap release */
+#define CEPH_I_FLUSH 8 /* do not delay flush of dirty metadata */
+#define CEPH_I_NOFLUSH 16 /* do not flush dirty caps */
static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
- int release_count)
+ int release_count, int ordered_count)
{
atomic_set(&ci->i_complete_count, release_count);
+ if (ci->i_ordered_count == ordered_count)
+ ci->i_ceph_flags |= CEPH_I_DIR_ORDERED;
+ else
+ ci->i_ceph_flags &= ~CEPH_I_DIR_ORDERED;
}
static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
@@ -455,16 +463,35 @@ static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
atomic_read(&ci->i_release_count);
}
+static inline bool __ceph_dir_is_complete_ordered(struct ceph_inode_info *ci)
+{
+ return __ceph_dir_is_complete(ci) &&
+ (ci->i_ceph_flags & CEPH_I_DIR_ORDERED);
+}
+
static inline void ceph_dir_clear_complete(struct inode *inode)
{
__ceph_dir_clear_complete(ceph_inode(inode));
}
-static inline bool ceph_dir_is_complete(struct inode *inode)
+static inline void ceph_dir_clear_ordered(struct inode *inode)
{
- return __ceph_dir_is_complete(ceph_inode(inode));
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ spin_lock(&ci->i_ceph_lock);
+ ci->i_ordered_count++;
+ ci->i_ceph_flags &= ~CEPH_I_DIR_ORDERED;
+ spin_unlock(&ci->i_ceph_lock);
}
+static inline bool ceph_dir_is_complete_ordered(struct inode *inode)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ bool ret;
+ spin_lock(&ci->i_ceph_lock);
+ ret = __ceph_dir_is_complete_ordered(ci);
+ spin_unlock(&ci->i_ceph_lock);
+ return ret;
+}
/* find a specific frag @f */
extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci,
@@ -580,6 +607,7 @@ struct ceph_file_info {
char *last_name; /* last entry in previous chunk */
struct dentry *dentry; /* next dentry (for dcache readdir) */
int dir_release_count;
+ int dir_ordered_count;
/* used for -o dirstat read() on directory thing */
char *dir_info;
@@ -673,6 +701,8 @@ extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
struct ceph_cap_snap *capsnap);
extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
+extern int ceph_snap_init(void);
+extern void ceph_snap_exit(void);
/*
* a cap_snap is "pending" if it is still awaiting an in-progress
@@ -715,7 +745,12 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
extern void ceph_queue_invalidate(struct inode *inode);
extern void ceph_queue_writeback(struct inode *inode);
-extern int ceph_do_getattr(struct inode *inode, int mask, bool force);
+extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+ int mask, bool force);
+static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
+{
+ return __ceph_do_getattr(inode, NULL, mask, force);
+}
extern int ceph_permission(struct inode *inode, int mask);
extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -830,7 +865,7 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
int mds, int drop, int unless);
extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
- int *got, loff_t endoff);
+ loff_t endoff, int *got, struct page **pinned_page);
/* for counting open files by mode */
static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode)
@@ -852,7 +887,9 @@ extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode,
int *opened);
extern int ceph_release(struct inode *inode, struct file *filp);
-
+extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+ char *data, size_t len);
+int ceph_uninline_data(struct file *filp, struct page *locked_page);
/* dir.c */
extern const struct file_operations ceph_dir_fops;
extern const struct inode_operations ceph_dir_iops;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 678b0d2bbbc4..5a492caf34cb 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -854,7 +854,7 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
struct ceph_pagelist *pagelist = NULL;
int err;
- if (value) {
+ if (size > 0) {
/* copy value into pagelist */
pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
if (!pagelist)
@@ -864,7 +864,7 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
err = ceph_pagelist_append(pagelist, value, size);
if (err)
goto out;
- } else {
+ } else if (!value) {
flags |= CEPH_XATTR_REMOVE;
}
@@ -1001,6 +1001,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_setxattr(dentry, name, value, size, flags);
+ if (size == 0)
+ value = ""; /* empty EA, do not remove */
+
return __ceph_setxattr(dentry, name, value, size, flags);
}
diff --git a/fs/char_dev.c b/fs/char_dev.c
index f77f7702fabe..67b2007f10fe 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -117,7 +117,6 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor,
goto out;
}
major = i;
- ret = major;
}
cd->major = major;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 44ec72684df5..9c56ef776407 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -34,27 +34,9 @@
void
cifs_dump_mem(char *label, void *data, int length)
{
- int i, j;
- int *intptr = data;
- char *charptr = data;
- char buf[10], line[80];
-
- printk(KERN_DEBUG "%s: dump of %d bytes of data at 0x%p\n",
- label, length, data);
- for (i = 0; i < length; i += 16) {
- line[0] = 0;
- for (j = 0; (j < 4) && (i + j * 4 < length); j++) {
- sprintf(buf, " %08x", intptr[i / 4 + j]);
- strcat(line, buf);
- }
- buf[0] = ' ';
- buf[2] = 0;
- for (j = 0; (j < 16) && (i + j < length); j++) {
- buf[1] = isprint(charptr[i + j]) ? charptr[i + j] : '.';
- strcat(line, buf);
- }
- printk(KERN_DEBUG "%s\n", line);
- }
+ pr_debug("%s: dump of %d bytes of data at 0x%p\n", label, length, data);
+ print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 16, 4,
+ data, length, true);
}
#ifdef CONFIG_CIFS_DEBUG
@@ -68,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...)
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_ERR "CIFS VFS: %pV", &vaf);
+ pr_err("CIFS VFS: %pV", &vaf);
va_end(args);
}
@@ -274,6 +256,7 @@ static ssize_t cifs_stats_proc_write(struct file *file,
const char __user *buffer, size_t count, loff_t *ppos)
{
char c;
+ bool bv;
int rc;
struct list_head *tmp1, *tmp2, *tmp3;
struct TCP_Server_Info *server;
@@ -284,7 +267,7 @@ static ssize_t cifs_stats_proc_write(struct file *file,
if (rc)
return rc;
- if (c == '1' || c == 'y' || c == 'Y' || c == '0') {
+ if (strtobool(&c, &bv) == 0) {
#ifdef CONFIG_CIFS_STATS2
atomic_set(&totBufAllocCount, 0);
atomic_set(&totSmBufAllocCount, 0);
@@ -451,15 +434,14 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
char c;
+ bool bv;
int rc;
rc = get_user(c, buffer);
if (rc)
return rc;
- if (c == '0' || c == 'n' || c == 'N')
- cifsFYI = 0;
- else if (c == '1' || c == 'y' || c == 'Y')
- cifsFYI = 1;
+ if (strtobool(&c, &bv) == 0)
+ cifsFYI = bv;
else if ((c > '1') && (c <= '9'))
cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */
@@ -490,15 +472,18 @@ static ssize_t cifs_linux_ext_proc_write(struct file *file,
const char __user *buffer, size_t count, loff_t *ppos)
{
char c;
+ bool bv;
int rc;
rc = get_user(c, buffer);
if (rc)
return rc;
- if (c == '0' || c == 'n' || c == 'N')
- linuxExtEnabled = 0;
- else if (c == '1' || c == 'y' || c == 'Y')
- linuxExtEnabled = 1;
+
+ rc = strtobool(&c, &bv);
+ if (rc)
+ return rc;
+
+ linuxExtEnabled = bv;
return count;
}
@@ -527,15 +512,18 @@ static ssize_t cifs_lookup_cache_proc_write(struct file *file,
const char __user *buffer, size_t count, loff_t *ppos)
{
char c;
+ bool bv;
int rc;
rc = get_user(c, buffer);
if (rc)
return rc;
- if (c == '0' || c == 'n' || c == 'N')
- lookupCacheEnabled = 0;
- else if (c == '1' || c == 'y' || c == 'Y')
- lookupCacheEnabled = 1;
+
+ rc = strtobool(&c, &bv);
+ if (rc)
+ return rc;
+
+ lookupCacheEnabled = bv;
return count;
}
@@ -564,15 +552,18 @@ static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
char c;
+ bool bv;
int rc;
rc = get_user(c, buffer);
if (rc)
return rc;
- if (c == '0' || c == 'n' || c == 'N')
- traceSMB = 0;
- else if (c == '1' || c == 'y' || c == 'Y')
- traceSMB = 1;
+
+ rc = strtobool(&c, &bv);
+ if (rc)
+ return rc;
+
+ traceSMB = bv;
return count;
}
@@ -630,6 +621,7 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
unsigned int flags;
char flags_string[12];
char c;
+ bool bv;
if ((count < 1) || (count > 11))
return -EINVAL;
@@ -642,11 +634,8 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
if (count < 3) {
/* single char or single char followed by null */
c = flags_string[0];
- if (c == '0' || c == 'n' || c == 'N') {
- global_secflags = CIFSSEC_DEF; /* default */
- return count;
- } else if (c == '1' || c == 'y' || c == 'Y') {
- global_secflags = CIFSSEC_MAX;
+ if (strtobool(&c, &bv) == 0) {
+ global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF;
return count;
} else if (!isdigit(c)) {
cifs_dbg(VFS, "Invalid SecurityFlags: %s\n",
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index c99b40fb609b..f40fbaca1b2a 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -53,13 +53,12 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...);
do { \
if (type == FYI) { \
if (cifsFYI & CIFS_INFO) { \
- printk(KERN_DEBUG "%s: " fmt, \
- __FILE__, ##__VA_ARGS__); \
+ pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__); \
} \
} else if (type == VFS) { \
cifs_vfs_err(fmt, ##__VA_ARGS__); \
} else if (type == NOISY && type != 0) { \
- printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
+ pr_debug(fmt, ##__VA_ARGS__); \
} \
} while (0)
@@ -71,7 +70,7 @@ do { \
#define cifs_dbg(type, fmt, ...) \
do { \
if (0) \
- printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
+ pr_debug(fmt, ##__VA_ARGS__); \
} while (0)
#endif
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 6d00c419cbae..1ea780bc6376 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -38,7 +38,7 @@ static const struct cifs_sid sid_everyone = {
1, 1, {0, 0, 0, 0, 0, 1}, {0} };
/* security id for Authenticated Users system group */
static const struct cifs_sid sid_authusers = {
- 1, 1, {0, 0, 0, 0, 0, 5}, {__constant_cpu_to_le32(11)} };
+ 1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(11)} };
/* group users */
static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 9d7996e8e793..d72fe37f5420 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -209,8 +209,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
{
- struct super_block *sb = file->f_path.dentry->d_sb;
- struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct TCP_Server_Info *server = tcon->ses->server;
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 002e0c173939..252f5c15806b 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -136,5 +136,5 @@ 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 "2.05"
+#define CIFS_VERSION "2.06"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 02a33e529904..22b289a3b1c4 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -661,16 +661,16 @@ set_credits(struct TCP_Server_Info *server, const int val)
server->ops->set_credits(server, val);
}
-static inline __u64
+static inline __le64
get_next_mid64(struct TCP_Server_Info *server)
{
- return server->ops->get_next_mid(server);
+ return cpu_to_le64(server->ops->get_next_mid(server));
}
static inline __le16
get_next_mid(struct TCP_Server_Info *server)
{
- __u16 mid = get_next_mid64(server);
+ __u16 mid = server->ops->get_next_mid(server);
/*
* The value in the SMB header should be little endian for easy
* on-the-wire decoding.
@@ -1168,6 +1168,12 @@ CIFS_SB(struct super_block *sb)
return sb->s_fs_info;
}
+static inline struct cifs_sb_info *
+CIFS_FILE_SB(struct file *file)
+{
+ return CIFS_SB(file_inode(file)->i_sb);
+}
+
static inline char CIFS_DIR_SEP(const struct cifs_sb_info *cifs_sb)
{
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 61d00a6e398f..fa13d5e79f64 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2477,14 +2477,14 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
}
parm_data = (struct cifs_posix_lock *)
((char *)&pSMBr->hdr.Protocol + data_offset);
- if (parm_data->lock_type == __constant_cpu_to_le16(CIFS_UNLCK))
+ if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
pLockData->fl_type = F_UNLCK;
else {
if (parm_data->lock_type ==
- __constant_cpu_to_le16(CIFS_RDLCK))
+ cpu_to_le16(CIFS_RDLCK))
pLockData->fl_type = F_RDLCK;
else if (parm_data->lock_type ==
- __constant_cpu_to_le16(CIFS_WRLCK))
+ cpu_to_le16(CIFS_WRLCK))
pLockData->fl_type = F_WRLCK;
pLockData->fl_start = le64_to_cpu(parm_data->start);
@@ -3276,25 +3276,25 @@ CIFSSMB_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
pSMB->compression_state = cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
pSMB->TotalParameterCount = 0;
- pSMB->TotalDataCount = __constant_cpu_to_le32(2);
+ pSMB->TotalDataCount = cpu_to_le32(2);
pSMB->MaxParameterCount = 0;
pSMB->MaxDataCount = 0;
pSMB->MaxSetupCount = 4;
pSMB->Reserved = 0;
pSMB->ParameterOffset = 0;
- pSMB->DataCount = __constant_cpu_to_le32(2);
+ pSMB->DataCount = cpu_to_le32(2);
pSMB->DataOffset =
cpu_to_le32(offsetof(struct smb_com_transaction_compr_ioctl_req,
compression_state) - 4); /* 84 */
pSMB->SetupCount = 4;
- pSMB->SubCommand = __constant_cpu_to_le16(NT_TRANSACT_IOCTL);
+ pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
pSMB->ParameterCount = 0;
- pSMB->FunctionCode = __constant_cpu_to_le32(FSCTL_SET_COMPRESSION);
+ pSMB->FunctionCode = cpu_to_le32(FSCTL_SET_COMPRESSION);
pSMB->IsFsctl = 1; /* FSCTL */
pSMB->IsRootFlag = 0;
pSMB->Fid = fid; /* file handle always le */
/* 3 byte pad, followed by 2 byte compress state */
- pSMB->ByteCount = __constant_cpu_to_le16(5);
+ pSMB->ByteCount = cpu_to_le16(5);
inc_rfc1001_len(pSMB, 5);
rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
@@ -3430,10 +3430,10 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL,
cifs_acl->version = cpu_to_le16(1);
if (acl_type == ACL_TYPE_ACCESS) {
cifs_acl->access_entry_count = cpu_to_le16(count);
- cifs_acl->default_entry_count = __constant_cpu_to_le16(0xFFFF);
+ cifs_acl->default_entry_count = cpu_to_le16(0xFFFF);
} else if (acl_type == ACL_TYPE_DEFAULT) {
cifs_acl->default_entry_count = cpu_to_le16(count);
- cifs_acl->access_entry_count = __constant_cpu_to_le16(0xFFFF);
+ cifs_acl->access_entry_count = cpu_to_le16(0xFFFF);
} else {
cifs_dbg(FYI, "unknown ACL type %d\n", acl_type);
return 0;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 24fa08d261fb..2a772da16b83 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1466,9 +1466,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
vol->seal = 1;
break;
case Opt_noac:
- printk(KERN_WARNING "CIFS: Mount option noac not "
- "supported. Instead set "
- "/proc/fs/cifs/LookupCacheEnabled to 0\n");
+ pr_warn("CIFS: Mount option noac not supported. Instead set /proc/fs/cifs/LookupCacheEnabled to 0\n");
break;
case Opt_fsc:
#ifndef CONFIG_CIFS_FSCACHE
@@ -1598,7 +1596,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
if (strnlen(string, CIFS_MAX_USERNAME_LEN) >
CIFS_MAX_USERNAME_LEN) {
- printk(KERN_WARNING "CIFS: username too long\n");
+ pr_warn("CIFS: username too long\n");
goto cifs_parse_mount_err;
}
vol->username = kstrdup(string, GFP_KERNEL);
@@ -1662,8 +1660,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
temp_len = strlen(value);
vol->password = kzalloc(temp_len+1, GFP_KERNEL);
if (vol->password == NULL) {
- printk(KERN_WARNING "CIFS: no memory "
- "for password\n");
+ pr_warn("CIFS: no memory for password\n");
goto cifs_parse_mount_err;
}
@@ -1687,8 +1684,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
if (!cifs_convert_address(dstaddr, string,
strlen(string))) {
- printk(KERN_ERR "CIFS: bad ip= option (%s).\n",
- string);
+ pr_err("CIFS: bad ip= option (%s).\n", string);
goto cifs_parse_mount_err;
}
got_ip = true;
@@ -1700,15 +1696,13 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN)
== CIFS_MAX_DOMAINNAME_LEN) {
- printk(KERN_WARNING "CIFS: domain name too"
- " long\n");
+ pr_warn("CIFS: domain name too long\n");
goto cifs_parse_mount_err;
}
vol->domainname = kstrdup(string, GFP_KERNEL);
if (!vol->domainname) {
- printk(KERN_WARNING "CIFS: no memory "
- "for domainname\n");
+ pr_warn("CIFS: no memory for domainname\n");
goto cifs_parse_mount_err;
}
cifs_dbg(FYI, "Domain name set\n");
@@ -1721,8 +1715,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
if (!cifs_convert_address(
(struct sockaddr *)&vol->srcaddr,
string, strlen(string))) {
- printk(KERN_WARNING "CIFS: Could not parse"
- " srcaddr: %s\n", string);
+ pr_warn("CIFS: Could not parse srcaddr: %s\n",
+ string);
goto cifs_parse_mount_err;
}
break;
@@ -1732,8 +1726,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
goto out_nomem;
if (strnlen(string, 1024) >= 65) {
- printk(KERN_WARNING "CIFS: iocharset name "
- "too long.\n");
+ pr_warn("CIFS: iocharset name too long.\n");
goto cifs_parse_mount_err;
}
@@ -1741,8 +1734,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
vol->iocharset = kstrdup(string,
GFP_KERNEL);
if (!vol->iocharset) {
- printk(KERN_WARNING "CIFS: no memory"
- "for charset\n");
+ pr_warn("CIFS: no memory for charset\n");
goto cifs_parse_mount_err;
}
}
@@ -1773,9 +1765,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
* set at top of the function
*/
if (i == RFC1001_NAME_LEN && string[i] != 0)
- printk(KERN_WARNING "CIFS: netbiosname"
- " longer than 15 truncated.\n");
-
+ pr_warn("CIFS: netbiosname longer than 15 truncated.\n");
break;
case Opt_servern:
/* servernetbiosname specified override *SMBSERVER */
@@ -1801,8 +1791,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
/* The string has 16th byte zero still from
set at top of the function */
if (i == RFC1001_NAME_LEN && string[i] != 0)
- printk(KERN_WARNING "CIFS: server net"
- "biosname longer than 15 truncated.\n");
+ pr_warn("CIFS: server netbiosname longer than 15 truncated.\n");
break;
case Opt_ver:
string = match_strdup(args);
@@ -1814,8 +1803,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
break;
}
/* For all other value, error */
- printk(KERN_WARNING "CIFS: Invalid version"
- " specified\n");
+ pr_warn("CIFS: Invalid version specified\n");
goto cifs_parse_mount_err;
case Opt_vers:
string = match_strdup(args);
@@ -1856,7 +1844,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
if (!sloppy && invalid) {
- printk(KERN_ERR "CIFS: Unknown mount option \"%s\"\n", invalid);
+ pr_err("CIFS: Unknown mount option \"%s\"\n", invalid);
goto cifs_parse_mount_err;
}
@@ -1882,8 +1870,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
/* No ip= option specified? Try to get it from UNC */
if (!cifs_convert_address(dstaddr, &vol->UNC[2],
strlen(&vol->UNC[2]))) {
- printk(KERN_ERR "Unable to determine destination "
- "address.\n");
+ pr_err("Unable to determine destination address.\n");
goto cifs_parse_mount_err;
}
}
@@ -1894,20 +1881,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
if (uid_specified)
vol->override_uid = override_uid;
else if (override_uid == 1)
- printk(KERN_NOTICE "CIFS: ignoring forceuid mount option "
- "specified with no uid= option.\n");
+ pr_notice("CIFS: ignoring forceuid mount option specified with no uid= option.\n");
if (gid_specified)
vol->override_gid = override_gid;
else if (override_gid == 1)
- printk(KERN_NOTICE "CIFS: ignoring forcegid mount option "
- "specified with no gid= option.\n");
+ pr_notice("CIFS: ignoring forcegid mount option specified with no gid= option.\n");
kfree(mountdata_copy);
return 0;
out_nomem:
- printk(KERN_WARNING "Could not allocate temporary buffer\n");
+ pr_warn("Could not allocate temporary buffer\n");
cifs_parse_mount_err:
kfree(string);
kfree(mountdata_copy);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3e4d00a06c44..96b7e9b7706d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1066,7 +1066,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
max_num = (max_buf - sizeof(struct smb_hdr)) /
sizeof(LOCKING_ANDX_RANGE);
- buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+ buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf) {
free_xid(xid);
return -ENOMEM;
@@ -1401,7 +1401,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
max_num = (max_buf - sizeof(struct smb_hdr)) /
sizeof(LOCKING_ANDX_RANGE);
- buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+ buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -1586,7 +1586,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag,
tcon->ses->server);
- cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ cifs_sb = CIFS_FILE_SB(file);
netfid = cfile->fid.netfid;
cinode = CIFS_I(file_inode(file));
@@ -2305,7 +2305,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifsFileInfo *smbfile = file->private_data;
- struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
struct inode *inode = file->f_mapping->host;
rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
@@ -2585,7 +2585,7 @@ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset)
iov_iter_truncate(from, len);
INIT_LIST_HEAD(&wdata_list);
- cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ cifs_sb = CIFS_FILE_SB(file);
open_file = file->private_data;
tcon = tlink_tcon(open_file->tlink);
@@ -3010,7 +3010,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
return 0;
INIT_LIST_HEAD(&rdata_list);
- cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ cifs_sb = CIFS_FILE_SB(file);
open_file = file->private_data;
tcon = tlink_tcon(open_file->tlink);
@@ -3155,7 +3155,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
__u32 pid;
xid = get_xid();
- cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ cifs_sb = CIFS_FILE_SB(file);
/* FIXME: set up handlers for larger reads and/or convert to async */
rsize = min_t(unsigned int, cifs_sb->rsize, CIFSMaxBufSize);
@@ -3462,7 +3462,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
int rc;
struct list_head tmplist;
struct cifsFileInfo *open_file = file->private_data;
- struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
struct TCP_Server_Info *server;
pid_t pid;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 197cb503d528..0c3ce464cae4 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -895,7 +895,7 @@ inode_has_hashed_dentries(struct inode *inode)
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
spin_unlock(&inode->i_lock);
return true;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index b7415d596dbd..337946355b29 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -513,39 +513,11 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
void
dump_smb(void *buf, int smb_buf_length)
{
- int i, j;
- char debug_line[17];
- unsigned char *buffer = buf;
-
if (traceSMB == 0)
return;
- for (i = 0, j = 0; i < smb_buf_length; i++, j++) {
- if (i % 8 == 0) {
- /* have reached the beginning of line */
- printk(KERN_DEBUG "| ");
- j = 0;
- }
- printk("%0#4x ", buffer[i]);
- debug_line[2 * j] = ' ';
- if (isprint(buffer[i]))
- debug_line[1 + (2 * j)] = buffer[i];
- else
- debug_line[1 + (2 * j)] = '_';
-
- if (i % 8 == 7) {
- /* reached end of line, time to print ascii */
- debug_line[16] = 0;
- printk(" | %s\n", debug_line);
- }
- }
- for (; j < 8; j++) {
- printk(" ");
- debug_line[2 * j] = ' ';
- debug_line[1 + (2 * j)] = ' ';
- }
- printk(" | %s\n", debug_line);
- return;
+ print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 8, 2, buf,
+ smb_buf_length, true);
}
void
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index b333ff60781d..abae6dd2c6b9 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -926,6 +926,7 @@ cifs_NTtimeToUnix(__le64 ntutc)
/* Subtract the NTFS time offset, then convert to 1s intervals. */
s64 t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET;
+ u64 abs_t;
/*
* Unfortunately can not use normal 64 bit division on 32 bit arch, but
@@ -933,13 +934,14 @@ cifs_NTtimeToUnix(__le64 ntutc)
* to special case them
*/
if (t < 0) {
- t = -t;
- ts.tv_nsec = (long)(do_div(t, 10000000) * 100);
+ abs_t = -t;
+ ts.tv_nsec = (long)(do_div(abs_t, 10000000) * 100);
ts.tv_nsec = -ts.tv_nsec;
- ts.tv_sec = -t;
+ ts.tv_sec = -abs_t;
} else {
- ts.tv_nsec = (long)do_div(t, 10000000) * 100;
- ts.tv_sec = t;
+ abs_t = t;
+ ts.tv_nsec = (long)do_div(abs_t, 10000000) * 100;
+ ts.tv_sec = abs_t;
}
return ts;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 8fd2a95860ba..c295338e0a98 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -69,7 +69,8 @@ static inline void dump_cifs_file_struct(struct file *file, char *label)
* Attempt to preload the dcache with the results from the FIND_FIRST/NEXT
*
* Find the dentry that matches "name". If there isn't one, create one. If it's
- * a negative dentry or the uniqueid changed, then drop it and recreate it.
+ * a negative dentry or the uniqueid or filetype(mode) changed,
+ * then drop it and recreate it.
*/
static void
cifs_prime_dcache(struct dentry *parent, struct qstr *name,
@@ -97,8 +98,11 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM))
fattr->cf_uniqueid = CIFS_I(inode)->uniqueid;
- /* update inode in place if i_ino didn't change */
- if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) {
+ /* update inode in place
+ * if both i_ino and i_mode didn't change */
+ if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid &&
+ (inode->i_mode & S_IFMT) ==
+ (fattr->cf_mode & S_IFMT)) {
cifs_fattr_to_inode(inode, fattr);
goto out;
}
@@ -123,7 +127,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
if (!inode)
goto out;
- alias = d_materialise_unique(dentry, inode);
+ alias = d_splice_alias(inode, dentry);
if (alias && !IS_ERR(alias))
dput(alias);
out:
@@ -261,7 +265,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file)
int rc = 0;
char *full_path = NULL;
struct cifsFileInfo *cifsFile;
- struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
struct tcon_link *tlink = NULL;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
@@ -561,7 +565,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
loff_t first_entry_in_buffer;
loff_t index_to_find = pos;
struct cifsFileInfo *cfile = file->private_data;
- struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
struct TCP_Server_Info *server = tcon->ses->server;
/* check if index in the buffer */
@@ -679,7 +683,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
char *scratch_buf, unsigned int max_len)
{
struct cifsFileInfo *file_info = file->private_data;
- struct super_block *sb = file->f_path.dentry->d_sb;
+ struct super_block *sb = file_inode(file)->i_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifs_dirent de = { NULL, };
struct cifs_fattr fattr;
@@ -753,7 +757,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
*/
fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
- cifs_prime_dcache(file->f_dentry, &name, &fattr);
+ cifs_prime_dcache(file->f_path.dentry, &name, &fattr);
ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid);
return !dir_emit(ctx, name.name, name.len, ino, fattr.cf_dtype);
@@ -794,10 +798,6 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
if it before then restart search
if after then keep searching till find it */
- if (file->private_data == NULL) {
- rc = -EINVAL;
- goto rddir2_exit;
- }
cifsFile = file->private_data;
if (cifsFile->srch_inf.endOfSearch) {
if (cifsFile->srch_inf.emptyDir) {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 57db63ff88da..bce6fdcd5d48 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -46,7 +46,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4,
USHRT_MAX));
pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq);
- pSMB->req.VcNumber = __constant_cpu_to_le16(1);
+ pSMB->req.VcNumber = cpu_to_le16(1);
/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
@@ -1303,6 +1303,11 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
if (le16_to_cpu(pSMB->resp.Action) & GUEST_LOGIN)
cifs_dbg(FYI, "Guest login\n"); /* BB mark SesInfo struct? */
+ if (ses->Suid != smb_buf->Uid) {
+ ses->Suid = smb_buf->Uid;
+ cifs_dbg(FYI, "UID changed! new UID = %llu\n", ses->Suid);
+ }
+
bytes_remaining = get_bcc(smb_buf);
bcc_ptr = pByteArea(smb_buf);
blob_len = le16_to_cpu(pSMB->resp.SecurityBlobLength);
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 45992944e238..7198eac5dddd 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -111,7 +111,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
return -EINVAL;
max_num = max_buf / sizeof(struct smb2_lock_element);
- buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+ buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -247,7 +247,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
}
max_num = max_buf / sizeof(struct smb2_lock_element);
- buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+ buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
if (!buf) {
free_xid(xid);
return -ENOMEM;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 1a08a34838fc..689f035915cf 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -32,12 +32,14 @@
static int
check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
{
+ __u64 wire_mid = le64_to_cpu(hdr->MessageId);
+
/*
* Make sure that this really is an SMB, that it is a response,
* and that the message ids match.
*/
if ((*(__le32 *)hdr->ProtocolId == SMB2_PROTO_NUMBER) &&
- (mid == hdr->MessageId)) {
+ (mid == wire_mid)) {
if (hdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
return 0;
else {
@@ -51,11 +53,11 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
if (*(__le32 *)hdr->ProtocolId != SMB2_PROTO_NUMBER)
cifs_dbg(VFS, "Bad protocol string signature header %x\n",
*(unsigned int *) hdr->ProtocolId);
- if (mid != hdr->MessageId)
+ if (mid != wire_mid)
cifs_dbg(VFS, "Mids do not match: %llu and %llu\n",
- mid, hdr->MessageId);
+ mid, wire_mid);
}
- cifs_dbg(VFS, "Bad SMB detected. The Mid=%llu\n", hdr->MessageId);
+ cifs_dbg(VFS, "Bad SMB detected. The Mid=%llu\n", wire_mid);
return 1;
}
@@ -67,27 +69,27 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
* indexed by command in host byte order
*/
static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
- /* SMB2_NEGOTIATE */ __constant_cpu_to_le16(65),
- /* SMB2_SESSION_SETUP */ __constant_cpu_to_le16(9),
- /* SMB2_LOGOFF */ __constant_cpu_to_le16(4),
- /* SMB2_TREE_CONNECT */ __constant_cpu_to_le16(16),
- /* SMB2_TREE_DISCONNECT */ __constant_cpu_to_le16(4),
- /* SMB2_CREATE */ __constant_cpu_to_le16(89),
- /* SMB2_CLOSE */ __constant_cpu_to_le16(60),
- /* SMB2_FLUSH */ __constant_cpu_to_le16(4),
- /* SMB2_READ */ __constant_cpu_to_le16(17),
- /* SMB2_WRITE */ __constant_cpu_to_le16(17),
- /* SMB2_LOCK */ __constant_cpu_to_le16(4),
- /* SMB2_IOCTL */ __constant_cpu_to_le16(49),
+ /* SMB2_NEGOTIATE */ cpu_to_le16(65),
+ /* SMB2_SESSION_SETUP */ cpu_to_le16(9),
+ /* SMB2_LOGOFF */ cpu_to_le16(4),
+ /* SMB2_TREE_CONNECT */ cpu_to_le16(16),
+ /* SMB2_TREE_DISCONNECT */ cpu_to_le16(4),
+ /* SMB2_CREATE */ cpu_to_le16(89),
+ /* SMB2_CLOSE */ cpu_to_le16(60),
+ /* SMB2_FLUSH */ cpu_to_le16(4),
+ /* SMB2_READ */ cpu_to_le16(17),
+ /* SMB2_WRITE */ cpu_to_le16(17),
+ /* SMB2_LOCK */ cpu_to_le16(4),
+ /* SMB2_IOCTL */ cpu_to_le16(49),
/* BB CHECK this ... not listed in documentation */
- /* SMB2_CANCEL */ __constant_cpu_to_le16(0),
- /* SMB2_ECHO */ __constant_cpu_to_le16(4),
- /* SMB2_QUERY_DIRECTORY */ __constant_cpu_to_le16(9),
- /* SMB2_CHANGE_NOTIFY */ __constant_cpu_to_le16(9),
- /* SMB2_QUERY_INFO */ __constant_cpu_to_le16(9),
- /* SMB2_SET_INFO */ __constant_cpu_to_le16(2),
+ /* SMB2_CANCEL */ cpu_to_le16(0),
+ /* SMB2_ECHO */ cpu_to_le16(4),
+ /* SMB2_QUERY_DIRECTORY */ cpu_to_le16(9),
+ /* SMB2_CHANGE_NOTIFY */ cpu_to_le16(9),
+ /* SMB2_QUERY_INFO */ cpu_to_le16(9),
+ /* SMB2_SET_INFO */ cpu_to_le16(2),
/* BB FIXME can also be 44 for lease break */
- /* SMB2_OPLOCK_BREAK */ __constant_cpu_to_le16(24)
+ /* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
};
int
@@ -95,7 +97,7 @@ smb2_check_message(char *buf, unsigned int length)
{
struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
- __u64 mid = hdr->MessageId;
+ __u64 mid = le64_to_cpu(hdr->MessageId);
__u32 len = get_rfc1002_length(buf);
__u32 clc_len; /* calculated length */
int command;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index c5f521bcdee2..96b5d40a2ece 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -176,10 +176,11 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
{
struct mid_q_entry *mid;
struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
+ __u64 wire_mid = le64_to_cpu(hdr->MessageId);
spin_lock(&GlobalMid_Lock);
list_for_each_entry(mid, &server->pending_mid_q, qhead) {
- if ((mid->mid == hdr->MessageId) &&
+ if ((mid->mid == wire_mid) &&
(mid->mid_state == MID_REQUEST_SUBMITTED) &&
(mid->command == hdr->Command)) {
spin_unlock(&GlobalMid_Lock);
@@ -600,7 +601,7 @@ smb2_clone_range(const unsigned int xid,
goto cchunk_out;
/* For now array only one chunk long, will make more flexible later */
- pcchunk->ChunkCount = __constant_cpu_to_le32(1);
+ pcchunk->ChunkCount = cpu_to_le32(1);
pcchunk->Reserved = 0;
pcchunk->Reserved2 = 0;
@@ -1102,6 +1103,64 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
return rc;
}
+static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
+ loff_t off, loff_t len, bool keep_size)
+{
+ struct inode *inode;
+ struct cifsInodeInfo *cifsi;
+ struct cifsFileInfo *cfile = file->private_data;
+ long rc = -EOPNOTSUPP;
+ unsigned int xid;
+
+ xid = get_xid();
+
+ inode = cfile->dentry->d_inode;
+ cifsi = CIFS_I(inode);
+
+ /* if file not oplocked can't be sure whether asking to extend size */
+ if (!CIFS_CACHE_READ(cifsi))
+ if (keep_size == false)
+ return -EOPNOTSUPP;
+
+ /*
+ * Files are non-sparse by default so falloc may be a no-op
+ * Must check if file sparse. If not sparse, and not extending
+ * then no need to do anything since file already allocated
+ */
+ if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) == 0) {
+ if (keep_size == true)
+ return 0;
+ /* check if extending file */
+ else if (i_size_read(inode) >= off + len)
+ /* not extending file and already not sparse */
+ return 0;
+ /* BB: in future add else clause to extend file */
+ else
+ return -EOPNOTSUPP;
+ }
+
+ if ((keep_size == true) || (i_size_read(inode) >= off + len)) {
+ /*
+ * Check if falloc starts within first few pages of file
+ * and ends within a few pages of the end of file to
+ * ensure that most of file is being forced to be
+ * fallocated now. If so then setting whole file sparse
+ * ie potentially making a few extra pages at the beginning
+ * or end of the file non-sparse via set_sparse is harmless.
+ */
+ if ((off > 8192) || (off + len + 8192 < i_size_read(inode)))
+ return -EOPNOTSUPP;
+
+ rc = smb2_set_sparse(xid, tcon, cfile, inode, false);
+ }
+ /* BB: else ... in future add code to extend file and set sparse */
+
+
+ free_xid(xid);
+ return rc;
+}
+
+
static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
loff_t off, loff_t len)
{
@@ -1112,7 +1171,10 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
if (mode & FALLOC_FL_KEEP_SIZE)
return smb3_zero_range(file, tcon, off, len, true);
return smb3_zero_range(file, tcon, off, len, false);
- }
+ } else if (mode == FALLOC_FL_KEEP_SIZE)
+ return smb3_simple_falloc(file, tcon, off, len, true);
+ else if (mode == 0)
+ return smb3_simple_falloc(file, tcon, off, len, false);
return -EOPNOTSUPP;
}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 8f1672bb82d5..3417340bf89e 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -431,8 +431,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
if (rc)
goto neg_exit;
if (blob_length)
- rc = decode_neg_token_init(security_blob, blob_length,
- &server->sec_type);
+ rc = decode_negTokenInit(security_blob, blob_length, server);
if (rc == 1)
rc = 0;
else if (rc == 0) {
@@ -1359,7 +1358,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
char *ret_data = NULL;
fsctl_input.CompressionState =
- __constant_cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
+ cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
FSCTL_SET_COMPRESSION, true /* is_fsctl */,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index e3188abdafd0..70867d54fb8b 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -85,7 +85,7 @@
/* BB FIXME - analyze following length BB */
#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
-#define SMB2_PROTO_NUMBER __constant_cpu_to_le32(0x424d53fe)
+#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
/*
* SMB2 Header Definition
@@ -96,7 +96,7 @@
*
*/
-#define SMB2_HEADER_STRUCTURE_SIZE __constant_cpu_to_le16(64)
+#define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
struct smb2_hdr {
__be32 smb2_buf_length; /* big endian on wire */
@@ -110,7 +110,7 @@ struct smb2_hdr {
__le16 CreditRequest; /* CreditResponse */
__le32 Flags;
__le32 NextCommand;
- __u64 MessageId; /* opaque - so can stay little endian */
+ __le64 MessageId;
__le32 ProcessId;
__u32 TreeId; /* opaque - so do not make little endian */
__u64 SessionId; /* opaque - so do not make little endian */
@@ -137,16 +137,16 @@ struct smb2_transform_hdr {
} __packed;
/* Encryption Algorithms */
-#define SMB2_ENCRYPTION_AES128_CCM __constant_cpu_to_le16(0x0001)
+#define SMB2_ENCRYPTION_AES128_CCM cpu_to_le16(0x0001)
/*
* SMB2 flag definitions
*/
-#define SMB2_FLAGS_SERVER_TO_REDIR __constant_cpu_to_le32(0x00000001)
-#define SMB2_FLAGS_ASYNC_COMMAND __constant_cpu_to_le32(0x00000002)
-#define SMB2_FLAGS_RELATED_OPERATIONS __constant_cpu_to_le32(0x00000004)
-#define SMB2_FLAGS_SIGNED __constant_cpu_to_le32(0x00000008)
-#define SMB2_FLAGS_DFS_OPERATIONS __constant_cpu_to_le32(0x10000000)
+#define SMB2_FLAGS_SERVER_TO_REDIR cpu_to_le32(0x00000001)
+#define SMB2_FLAGS_ASYNC_COMMAND cpu_to_le32(0x00000002)
+#define SMB2_FLAGS_RELATED_OPERATIONS cpu_to_le32(0x00000004)
+#define SMB2_FLAGS_SIGNED cpu_to_le32(0x00000008)
+#define SMB2_FLAGS_DFS_OPERATIONS cpu_to_le32(0x10000000)
/*
* Definitions for SMB2 Protocol Data Units (network frames)
@@ -157,7 +157,7 @@ struct smb2_transform_hdr {
*
*/
-#define SMB2_ERROR_STRUCTURE_SIZE2 __constant_cpu_to_le16(9)
+#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
struct smb2_err_rsp {
struct smb2_hdr hdr;
@@ -502,12 +502,12 @@ struct create_context {
#define SMB2_LEASE_HANDLE_CACHING_HE 0x02
#define SMB2_LEASE_WRITE_CACHING_HE 0x04
-#define SMB2_LEASE_NONE __constant_cpu_to_le32(0x00)
-#define SMB2_LEASE_READ_CACHING __constant_cpu_to_le32(0x01)
-#define SMB2_LEASE_HANDLE_CACHING __constant_cpu_to_le32(0x02)
-#define SMB2_LEASE_WRITE_CACHING __constant_cpu_to_le32(0x04)
+#define SMB2_LEASE_NONE cpu_to_le32(0x00)
+#define SMB2_LEASE_READ_CACHING cpu_to_le32(0x01)
+#define SMB2_LEASE_HANDLE_CACHING cpu_to_le32(0x02)
+#define SMB2_LEASE_WRITE_CACHING cpu_to_le32(0x04)
-#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS __constant_cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x02)
#define SMB2_LEASE_KEY_SIZE 16
@@ -836,6 +836,25 @@ struct smb2_query_directory_rsp {
#define SMB2_O_INFO_SECURITY 0x03
#define SMB2_O_INFO_QUOTA 0x04
+/* Security info type additionalinfo flags. See MS-SMB2 (2.2.37) or MS-DTYP */
+#define OWNER_SECINFO 0x00000001
+#define GROUP_SECINFO 0x00000002
+#define DACL_SECINFO 0x00000004
+#define SACL_SECINFO 0x00000008
+#define LABEL_SECINFO 0x00000010
+#define ATTRIBUTE_SECINFO 0x00000020
+#define SCOPE_SECINFO 0x00000040
+#define BACKUP_SECINFO 0x00010000
+#define UNPROTECTED_SACL_SECINFO 0x10000000
+#define UNPROTECTED_DACL_SECINFO 0x20000000
+#define PROTECTED_SACL_SECINFO 0x40000000
+#define PROTECTED_DACL_SECINFO 0x80000000
+
+/* Flags used for FileFullEAinfo */
+#define SL_RESTART_SCAN 0x00000001
+#define SL_RETURN_SINGLE_ENTRY 0x00000002
+#define SL_INDEX_SPECIFIED 0x00000004
+
struct smb2_query_info_req {
struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 41 */
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 5111e7272db6..d4c5b6f109a7 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -490,7 +490,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
return temp;
else {
memset(temp, 0, sizeof(struct mid_q_entry));
- temp->mid = smb_buffer->MessageId; /* always LE */
+ temp->mid = le64_to_cpu(smb_buffer->MessageId);
temp->pid = current->pid;
temp->command = smb_buffer->Command; /* Always LE */
temp->when_alloc = jiffies;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 9d087f4e7d4e..126f46b887cc 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -99,9 +99,9 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
something is wrong, unless it is quite a slow link or server */
if ((now - midEntry->when_alloc) > HZ) {
if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
- printk(KERN_DEBUG " CIFS slow rsp: cmd %d mid %llu",
+ pr_debug(" CIFS slow rsp: cmd %d mid %llu",
midEntry->command, midEntry->mid);
- printk(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
+ pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
now - midEntry->when_alloc,
now - midEntry->when_sent,
now - midEntry->when_received);
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 278f8fdeb9ef..46ee6f238985 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag)
struct dentry *de;
spin_lock(&parent->d_lock);
- list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) {
+ list_for_each_entry(de, &parent->d_subdirs, d_child) {
/* don't know what to do with negative dentries */
if (de->d_inode )
coda_flag_inode(de->d_inode, flag);
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 1326d38960db..f1714cfb589c 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -40,12 +40,6 @@ int coda_iscontrol(const char *name, size_t length)
(strncmp(name, CODA_CONTROL, CODA_CONTROLLEN) == 0));
}
-/* recognize /coda inode */
-int coda_isroot(struct inode *i)
-{
- return ( i->i_sb->s_root->d_inode == i );
-}
-
unsigned short coda_flags_to_cflags(unsigned short flags)
{
unsigned short coda_flags = 0;
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index d42b725b1d21..d6f7a76a1f5b 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -52,7 +52,6 @@ int coda_setattr(struct dentry *, struct iattr *);
/* this file: heloers */
char *coda_f2s(struct CodaFid *f);
-int coda_isroot(struct inode *i);
int coda_iscontrol(const char *name, size_t length);
void coda_vattr_to_iattr(struct inode *, struct coda_vattr *);
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 9c3dedc000d1..86c893884eb9 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -107,7 +107,7 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig
}
/* control object, create inode on the fly */
- if (coda_isroot(dir) && coda_iscontrol(name, length)) {
+ if (is_root_inode(dir) && coda_iscontrol(name, length)) {
inode = coda_cnode_makectl(sb);
type = CODA_NOCACHE;
} else {
@@ -195,7 +195,7 @@ static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool
struct CodaFid newfid;
struct coda_vattr attrs;
- if (coda_isroot(dir) && coda_iscontrol(name, length))
+ if (is_root_inode(dir) && coda_iscontrol(name, length))
return -EPERM;
error = venus_create(dir->i_sb, coda_i2f(dir), name, length,
@@ -227,7 +227,7 @@ static int coda_mkdir(struct inode *dir, struct dentry *de, umode_t mode)
int error;
struct CodaFid newfid;
- if (coda_isroot(dir) && coda_iscontrol(name, len))
+ if (is_root_inode(dir) && coda_iscontrol(name, len))
return -EPERM;
attrs.va_mode = mode;
@@ -261,7 +261,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode,
int len = de->d_name.len;
int error;
- if (coda_isroot(dir_inode) && coda_iscontrol(name, len))
+ if (is_root_inode(dir_inode) && coda_iscontrol(name, len))
return -EPERM;
error = venus_link(dir_inode->i_sb, coda_i2f(inode),
@@ -287,7 +287,7 @@ static int coda_symlink(struct inode *dir_inode, struct dentry *de,
int symlen;
int error;
- if (coda_isroot(dir_inode) && coda_iscontrol(name, len))
+ if (is_root_inode(dir_inode) && coda_iscontrol(name, len))
return -EPERM;
symlen = strlen(symname);
@@ -426,7 +426,6 @@ static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx)
struct coda_file_info *cfi;
struct coda_inode_info *cii;
struct file *host_file;
- struct dentry *de;
struct venus_dirent *vdir;
unsigned long vdir_size = offsetof(struct venus_dirent, d_name);
unsigned int type;
@@ -438,8 +437,7 @@ static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx)
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
- de = coda_file->f_path.dentry;
- cii = ITOC(de->d_inode);
+ cii = ITOC(file_inode(coda_file));
vdir = kmalloc(sizeof(*vdir), GFP_KERNEL);
if (!vdir) return -ENOMEM;
@@ -507,7 +505,7 @@ static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
return -ECHILD;
inode = de->d_inode;
- if (!inode || coda_isroot(inode))
+ if (!inode || is_root_inode(inode))
goto out;
if (is_bad_inode(inode))
goto bad;
diff --git a/fs/compat.c b/fs/compat.c
index b13df99f3534..6fd272d455e4 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -847,10 +847,12 @@ struct compat_readdir_callback {
int result;
};
-static int compat_fillonedir(void *__buf, const char *name, int namlen,
- loff_t offset, u64 ino, unsigned int d_type)
+static int compat_fillonedir(struct dir_context *ctx, const char *name,
+ int namlen, loff_t offset, u64 ino,
+ unsigned int d_type)
{
- struct compat_readdir_callback *buf = __buf;
+ struct compat_readdir_callback *buf =
+ container_of(ctx, struct compat_readdir_callback, ctx);
struct compat_old_linux_dirent __user *dirent;
compat_ulong_t d_ino;
@@ -915,11 +917,12 @@ struct compat_getdents_callback {
int error;
};
-static int compat_filldir(void *__buf, const char *name, int namlen,
+static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct compat_linux_dirent __user * dirent;
- struct compat_getdents_callback *buf = __buf;
+ struct compat_getdents_callback *buf =
+ container_of(ctx, struct compat_getdents_callback, ctx);
compat_ulong_t d_ino;
int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
namlen + 2, sizeof(compat_long_t));
@@ -1001,11 +1004,13 @@ struct compat_getdents_callback64 {
int error;
};
-static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset,
- u64 ino, unsigned int d_type)
+static int compat_filldir64(struct dir_context *ctx, const char *name,
+ int namlen, loff_t offset, u64 ino,
+ unsigned int d_type)
{
struct linux_dirent64 __user *dirent;
- struct compat_getdents_callback64 *buf = __buf;
+ struct compat_getdents_callback64 *buf =
+ container_of(ctx, struct compat_getdents_callback64, ctx);
int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
sizeof(u64));
u64 off;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 668dcabc5695..c9c298bd3058 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -386,7 +386,7 @@ static void remove_dir(struct dentry * d)
if (d->d_inode)
simple_rmdir(parent->d_inode,d);
- pr_debug(" o %s removing done (%d)\n",d->d_name.name, d_count(d));
+ pr_debug(" o %pd removing done (%d)\n", d, d_count(d));
dput(parent);
}
diff --git a/fs/dcache.c b/fs/dcache.c
index 3ffef7f4e5cd..e368d4f412f9 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -44,7 +44,7 @@
/*
* Usage:
* dcache->d_inode->i_lock protects:
- * - i_dentry, d_alias, d_inode of aliases
+ * - i_dentry, d_u.d_alias, d_inode of aliases
* dcache_hash_bucket lock protects:
* - the dcache hash table
* s_anon bl list spinlock protects:
@@ -59,7 +59,7 @@
* - d_unhashed()
* - d_parent and d_subdirs
* - childrens' d_child and d_parent
- * - d_alias, d_inode
+ * - d_u.d_alias, d_inode
*
* Ordering:
* dentry->d_inode->i_lock
@@ -252,14 +252,12 @@ static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- WARN_ON(!hlist_unhashed(&dentry->d_alias));
kmem_cache_free(dentry_cache, dentry);
}
static void __d_free_external(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- WARN_ON(!hlist_unhashed(&dentry->d_alias));
kfree(external_name(dentry));
kmem_cache_free(dentry_cache, dentry);
}
@@ -271,6 +269,7 @@ static inline int dname_external(const struct dentry *dentry)
static void dentry_free(struct dentry *dentry)
{
+ WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
if (unlikely(dname_external(dentry))) {
struct external_name *p = external_name(dentry);
if (likely(atomic_dec_and_test(&p->u.count))) {
@@ -311,7 +310,7 @@ static void dentry_iput(struct dentry * dentry)
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- hlist_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
@@ -336,7 +335,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
struct inode *inode = dentry->d_inode;
__d_clear_type(dentry);
dentry->d_inode = NULL;
- hlist_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
@@ -496,7 +495,7 @@ static void __dentry_kill(struct dentry *dentry)
}
/* if it was on the hash then remove it */
__d_drop(dentry);
- list_del(&dentry->d_u.d_child);
+ __list_del_entry(&dentry->d_child);
/*
* Inform d_walk() that we are no longer attached to the
* dentry tree
@@ -722,7 +721,7 @@ static struct dentry *__d_find_alias(struct inode *inode)
again:
discon_alias = NULL;
- hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
@@ -772,12 +771,13 @@ void d_prune_aliases(struct inode *inode)
struct dentry *dentry;
restart:
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_lockref.count) {
struct dentry *parent = lock_parent(dentry);
if (likely(!dentry->d_lockref.count)) {
__dentry_kill(dentry);
+ dput(parent);
goto restart;
}
if (parent)
@@ -1050,7 +1050,7 @@ repeat:
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
@@ -1082,33 +1082,31 @@ resume:
/*
* All done at this level ... ascend and resume the search.
*/
+ rcu_read_lock();
+ascend:
if (this_parent != parent) {
struct dentry *child = this_parent;
this_parent = child->d_parent;
- rcu_read_lock();
spin_unlock(&child->d_lock);
spin_lock(&this_parent->d_lock);
- /*
- * might go back up the wrong parent if we have had a rename
- * or deletion
- */
- if (this_parent != child->d_parent ||
- (child->d_flags & DCACHE_DENTRY_KILLED) ||
- need_seqretry(&rename_lock, seq)) {
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
+ /* might go back up the wrong parent if we have had a rename. */
+ if (need_seqretry(&rename_lock, seq))
goto rename_retry;
+ next = child->d_child.next;
+ while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ next = next->next;
}
rcu_read_unlock();
- next = child->d_u.d_child.next;
goto resume;
}
- if (need_seqretry(&rename_lock, seq)) {
- spin_unlock(&this_parent->d_lock);
+ if (need_seqretry(&rename_lock, seq))
goto rename_retry;
- }
+ rcu_read_unlock();
if (finish)
finish(data);
@@ -1118,6 +1116,9 @@ out_unlock:
return;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
+ BUG_ON(seq & 1);
if (!retry)
return;
seq = 1;
@@ -1454,8 +1455,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
- INIT_HLIST_NODE(&dentry->d_alias);
- INIT_LIST_HEAD(&dentry->d_u.d_child);
+ INIT_HLIST_NODE(&dentry->d_u.d_alias);
+ INIT_LIST_HEAD(&dentry->d_child);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
this_cpu_inc(nr_dentry);
@@ -1485,7 +1486,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
*/
__dget_dlock(parent);
dentry->d_parent = parent;
- list_add(&dentry->d_u.d_child, &parent->d_subdirs);
+ list_add(&dentry->d_child, &parent->d_subdirs);
spin_unlock(&parent->d_lock);
return dentry;
@@ -1578,7 +1579,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
spin_lock(&dentry->d_lock);
__d_set_type(dentry, add_flags);
if (inode)
- hlist_add_head(&dentry->d_alias, &inode->i_dentry);
+ hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
dentry->d_inode = inode;
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
@@ -1602,7 +1603,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
void d_instantiate(struct dentry *entry, struct inode * inode)
{
- BUG_ON(!hlist_unhashed(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode)
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
@@ -1641,7 +1642,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
return NULL;
}
- hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
@@ -1667,7 +1668,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
{
struct dentry *result;
- BUG_ON(!hlist_unhashed(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode)
spin_lock(&inode->i_lock);
@@ -1698,7 +1699,7 @@ EXPORT_SYMBOL(d_instantiate_unique);
*/
int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
{
- BUG_ON(!hlist_unhashed(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
@@ -1737,7 +1738,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode)
if (hlist_empty(&inode->i_dentry))
return NULL;
- alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
__dget(alias);
return alias;
}
@@ -1799,7 +1800,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
spin_lock(&tmp->d_lock);
tmp->d_inode = inode;
tmp->d_flags |= add_flags;
- hlist_add_head(&tmp->d_alias, &inode->i_dentry);
+ hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
hlist_bl_lock(&tmp->d_sb->s_anon);
hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
hlist_bl_unlock(&tmp->d_sb->s_anon);
@@ -1888,51 +1889,19 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
- if (unlikely(IS_ERR(found)))
- goto err_out;
if (!found) {
new = d_alloc(dentry->d_parent, name);
if (!new) {
found = ERR_PTR(-ENOMEM);
- goto err_out;
- }
-
- found = d_splice_alias(inode, new);
- if (found) {
- dput(new);
- return found;
- }
- return new;
- }
-
- /*
- * If a matching dentry exists, and it's not negative use it.
- *
- * Decrement the reference count to balance the iget() done
- * earlier on.
- */
- if (found->d_inode) {
- if (unlikely(found->d_inode != inode)) {
- /* This can't happen because bad inodes are unhashed. */
- BUG_ON(!is_bad_inode(inode));
- BUG_ON(!is_bad_inode(found->d_inode));
+ } else {
+ found = d_splice_alias(inode, new);
+ if (found) {
+ dput(new);
+ return found;
+ }
+ return new;
}
- iput(inode);
- return found;
}
-
- /*
- * Negative dentry: instantiate it unless the inode is a directory and
- * already has a dentry.
- */
- new = d_splice_alias(inode, found);
- if (new) {
- dput(found);
- found = new;
- }
- return found;
-
-err_out:
iput(inode);
return found;
}
@@ -2234,7 +2203,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent)
struct dentry *child;
spin_lock(&dparent->d_lock);
- list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &dparent->d_subdirs, d_child) {
if (dentry == child) {
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
__dget_dlock(dentry);
@@ -2392,6 +2361,8 @@ static void swap_names(struct dentry *dentry, struct dentry *target)
*/
unsigned int i;
BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+ kmemcheck_mark_initialized(dentry->d_iname, DNAME_INLINE_LEN);
+ kmemcheck_mark_initialized(target->d_iname, DNAME_INLINE_LEN);
for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
swap(((long *) &dentry->d_iname)[i],
((long *) &target->d_iname)[i]);
@@ -2525,13 +2496,13 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
/* splicing a tree */
dentry->d_parent = target->d_parent;
target->d_parent = target;
- list_del_init(&target->d_u.d_child);
- list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+ list_del_init(&target->d_child);
+ list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
} else {
/* swapping two dentries */
swap(dentry->d_parent, target->d_parent);
- list_move(&target->d_u.d_child, &target->d_parent->d_subdirs);
- list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+ list_move(&target->d_child, &target->d_parent->d_subdirs);
+ list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
if (exchange)
fsnotify_d_move(target);
fsnotify_d_move(dentry);
@@ -2607,11 +2578,11 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
*/
-static struct dentry *__d_unalias(struct inode *inode,
+static int __d_unalias(struct inode *inode,
struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
- struct dentry *ret = ERR_PTR(-EBUSY);
+ int ret = -EBUSY;
/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
@@ -2626,7 +2597,7 @@ static struct dentry *__d_unalias(struct inode *inode,
m2 = &alias->d_parent->d_inode->i_mutex;
out_unalias:
__d_move(alias, dentry, false);
- ret = alias;
+ ret = 0;
out_err:
spin_unlock(&inode->i_lock);
if (m2)
@@ -2661,130 +2632,57 @@ out_err:
*/
struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
{
- struct dentry *new = NULL;
-
if (IS_ERR(inode))
return ERR_CAST(inode);
- if (inode && S_ISDIR(inode->i_mode)) {
- spin_lock(&inode->i_lock);
- new = __d_find_any_alias(inode);
- if (new) {
- if (!IS_ROOT(new)) {
- spin_unlock(&inode->i_lock);
- dput(new);
- iput(inode);
- return ERR_PTR(-EIO);
- }
- if (d_ancestor(new, dentry)) {
- spin_unlock(&inode->i_lock);
- dput(new);
- iput(inode);
- return ERR_PTR(-EIO);
- }
- write_seqlock(&rename_lock);
- __d_move(new, dentry, false);
- write_sequnlock(&rename_lock);
- spin_unlock(&inode->i_lock);
- security_d_instantiate(new, inode);
- iput(inode);
- } else {
- /* already taking inode->i_lock, so d_add() by hand */
- __d_instantiate(dentry, inode);
- spin_unlock(&inode->i_lock);
- security_d_instantiate(dentry, inode);
- d_rehash(dentry);
- }
- } else {
- d_instantiate(dentry, inode);
- if (d_unhashed(dentry))
- d_rehash(dentry);
- }
- return new;
-}
-EXPORT_SYMBOL(d_splice_alias);
-
-/**
- * d_materialise_unique - introduce an inode into the tree
- * @dentry: candidate dentry
- * @inode: inode to bind to the dentry, to which aliases may be attached
- *
- * Introduces an dentry into the tree, substituting an extant disconnected
- * root directory alias in its place if there is one. Caller must hold the
- * i_mutex of the parent directory.
- */
-struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
-{
- struct dentry *actual;
-
BUG_ON(!d_unhashed(dentry));
if (!inode) {
- actual = dentry;
__d_instantiate(dentry, NULL);
- d_rehash(actual);
- goto out_nolock;
+ goto out;
}
-
spin_lock(&inode->i_lock);
-
if (S_ISDIR(inode->i_mode)) {
- struct dentry *alias;
-
- /* Does an aliased dentry already exist? */
- alias = __d_find_alias(inode);
- if (alias) {
- actual = alias;
+ struct dentry *new = __d_find_any_alias(inode);
+ if (unlikely(new)) {
write_seqlock(&rename_lock);
-
- if (d_ancestor(alias, dentry)) {
- /* Check for loops */
- actual = ERR_PTR(-ELOOP);
+ if (unlikely(d_ancestor(new, dentry))) {
+ write_sequnlock(&rename_lock);
spin_unlock(&inode->i_lock);
- } else if (IS_ROOT(alias)) {
- /* Is this an anonymous mountpoint that we
- * could splice into our tree? */
- __d_move(alias, dentry, false);
+ dput(new);
+ new = ERR_PTR(-ELOOP);
+ pr_warn_ratelimited(
+ "VFS: Lookup of '%s' in %s %s"
+ " would have caused loop\n",
+ dentry->d_name.name,
+ inode->i_sb->s_type->name,
+ inode->i_sb->s_id);
+ } else if (!IS_ROOT(new)) {
+ int err = __d_unalias(inode, dentry, new);
write_sequnlock(&rename_lock);
- goto found;
+ if (err) {
+ dput(new);
+ new = ERR_PTR(err);
+ }
} else {
- /* Nope, but we must(!) avoid directory
- * aliasing. This drops inode->i_lock */
- actual = __d_unalias(inode, dentry, alias);
- }
- write_sequnlock(&rename_lock);
- if (IS_ERR(actual)) {
- if (PTR_ERR(actual) == -ELOOP)
- pr_warn_ratelimited(
- "VFS: Lookup of '%s' in %s %s"
- " would have caused loop\n",
- dentry->d_name.name,
- inode->i_sb->s_type->name,
- inode->i_sb->s_id);
- dput(alias);
+ __d_move(new, dentry, false);
+ write_sequnlock(&rename_lock);
+ spin_unlock(&inode->i_lock);
+ security_d_instantiate(new, inode);
}
- goto out_nolock;
+ iput(inode);
+ return new;
}
}
-
- /* Add a unique reference */
- actual = __d_instantiate_unique(dentry, inode);
- if (!actual)
- actual = dentry;
-
- d_rehash(actual);
-found:
+ /* already taking inode->i_lock, so d_add() by hand */
+ __d_instantiate(dentry, inode);
spin_unlock(&inode->i_lock);
-out_nolock:
- if (actual == dentry) {
- security_d_instantiate(dentry, inode);
- return NULL;
- }
-
- iput(inode);
- return actual;
+out:
+ security_d_instantiate(dentry, inode);
+ d_rehash(dentry);
+ return NULL;
}
-EXPORT_SYMBOL_GPL(d_materialise_unique);
+EXPORT_SYMBOL(d_splice_alias);
static int prepend(char **buffer, int *buflen, const char *str, int namelen)
{
@@ -3320,7 +3218,7 @@ void d_tmpfile(struct dentry *dentry, struct inode *inode)
{
inode_dec_link_count(inode);
BUG_ON(dentry->d_name.name != dentry->d_iname ||
- !hlist_unhashed(&dentry->d_alias) ||
+ !hlist_unhashed(&dentry->d_u.d_alias) ||
!d_unlinked(dentry));
spin_lock(&dentry->d_parent->d_lock);
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 76c08c2beb2f..517e64938438 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -22,6 +22,7 @@
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/atomic.h>
+#include <linux/device.h>
static ssize_t default_read_file(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
@@ -692,18 +693,19 @@ EXPORT_SYMBOL_GPL(debugfs_create_u32_array);
* because some peripherals have several blocks of identical registers,
* for example configuration of dma channels
*/
-int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
- int nregs, void __iomem *base, char *prefix)
+void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
+ int nregs, void __iomem *base, char *prefix)
{
- int i, ret = 0;
+ int i;
for (i = 0; i < nregs; i++, regs++) {
if (prefix)
- ret += seq_printf(s, "%s", prefix);
- ret += seq_printf(s, "%s = 0x%08x\n", regs->name,
- readl(base + regs->offset));
+ seq_printf(s, "%s", prefix);
+ seq_printf(s, "%s = 0x%08x\n", regs->name,
+ readl(base + regs->offset));
+ if (seq_has_overflowed(s))
+ break;
}
- return ret;
}
EXPORT_SYMBOL_GPL(debugfs_print_regs32);
@@ -761,3 +763,56 @@ struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
EXPORT_SYMBOL_GPL(debugfs_create_regset32);
#endif /* CONFIG_HAS_IOMEM */
+
+struct debugfs_devm_entry {
+ int (*read)(struct seq_file *seq, void *data);
+ struct device *dev;
+};
+
+static int debugfs_devm_entry_open(struct inode *inode, struct file *f)
+{
+ struct debugfs_devm_entry *entry = inode->i_private;
+
+ return single_open(f, entry->read, entry->dev);
+}
+
+static const struct file_operations debugfs_devm_entry_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_devm_entry_open,
+ .release = single_release,
+ .read = seq_read,
+ .llseek = seq_lseek
+};
+
+/**
+ * debugfs_create_devm_seqfile - create a debugfs file that is bound to device.
+ *
+ * @dev: device related to this debugfs file.
+ * @name: name of the debugfs file.
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is %NULL, then the
+ * file will be created in the root of the debugfs filesystem.
+ * @read_fn: function pointer called to print the seq_file content.
+ */
+struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s,
+ void *data))
+{
+ struct debugfs_devm_entry *entry;
+
+ if (IS_ERR(parent))
+ return ERR_PTR(-ENOENT);
+
+ entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return ERR_PTR(-ENOMEM);
+
+ entry->read = read_fn;
+ entry->dev = dev;
+
+ return debugfs_create_file(name, S_IRUGO, parent, entry,
+ &debugfs_devm_entry_ops);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile);
+
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 1e3b99d3db0d..05f2960ed7c3 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -553,7 +553,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
* use the d_u.d_child as the rcu head and corrupt this list.
*/
spin_lock(&parent->d_lock);
- list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &parent->d_subdirs, d_child) {
if (!debugfs_positive(child))
continue;
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 1323c568e362..eea64912c9c0 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -48,8 +48,8 @@ static char *print_lockmode(int mode)
}
}
-static int print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb,
- struct dlm_rsb *res)
+static void print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb,
+ struct dlm_rsb *res)
{
seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode));
@@ -68,21 +68,17 @@ 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_puts(s, "\n");
+ seq_puts(s, "\n");
}
-static int print_format1(struct dlm_rsb *res, struct seq_file *s)
+static void print_format1(struct dlm_rsb *res, struct seq_file *s)
{
struct dlm_lkb *lkb;
int i, lvblen = res->res_ls->ls_lvblen, recover_list, root_list;
- int rv;
lock_rsb(res);
- rv = seq_printf(s, "\nResource %p Name (len=%d) \"",
- res, res->res_length);
- if (rv)
- goto out;
+ seq_printf(s, "\nResource %p Name (len=%d) \"", res, res->res_length);
for (i = 0; i < res->res_length; i++) {
if (isprint(res->res_name[i]))
@@ -92,17 +88,16 @@ 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",
- res->res_nodeid);
+ seq_printf(s, "\"\nLocal Copy, Master is node %d\n",
+ res->res_nodeid);
else if (res->res_nodeid == 0)
- rv = seq_puts(s, "\"\nMaster Copy\n");
+ seq_puts(s, "\"\nMaster Copy\n");
else if (res->res_nodeid == -1)
- rv = seq_printf(s, "\"\nLooking up master (lkid %x)\n",
- res->res_first_lkid);
+ seq_printf(s, "\"\nLooking up master (lkid %x)\n",
+ res->res_first_lkid);
else
- rv = seq_printf(s, "\"\nInvalid master %d\n",
- res->res_nodeid);
- if (rv)
+ seq_printf(s, "\"\nInvalid master %d\n", res->res_nodeid);
+ if (seq_has_overflowed(s))
goto out;
/* Print the LVB: */
@@ -116,8 +111,8 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s)
}
if (rsb_flag(res, RSB_VALNOTVALID))
seq_puts(s, " (INVALID)");
- rv = seq_puts(s, "\n");
- if (rv)
+ seq_puts(s, "\n");
+ if (seq_has_overflowed(s))
goto out;
}
@@ -125,32 +120,30 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s)
recover_list = !list_empty(&res->res_recover_list);
if (root_list || recover_list) {
- rv = seq_printf(s, "Recovery: root %d recover %d flags %lx "
- "count %d\n", root_list, recover_list,
- res->res_flags, res->res_recover_locks_count);
- if (rv)
- goto out;
+ seq_printf(s, "Recovery: root %d recover %d flags %lx count %d\n",
+ root_list, recover_list,
+ res->res_flags, res->res_recover_locks_count);
}
/* Print the locks attached to this resource */
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)
+ print_format1_lock(s, lkb, res);
+ if (seq_has_overflowed(s))
goto out;
}
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)
+ print_format1_lock(s, lkb, res);
+ if (seq_has_overflowed(s))
goto out;
}
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)
+ print_format1_lock(s, lkb, res);
+ if (seq_has_overflowed(s))
goto out;
}
@@ -159,23 +152,23 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s)
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));
+ 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_puts(s, "\n");
+ seq_puts(s, "\n");
+ if (seq_has_overflowed(s))
+ goto out;
}
out:
unlock_rsb(res);
- return rv;
}
-static int print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb,
- struct dlm_rsb *r)
+static void print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb,
+ struct dlm_rsb *r)
{
u64 xid = 0;
u64 us;
- int rv;
if (lkb->lkb_flags & DLM_IFL_USER) {
if (lkb->lkb_ua)
@@ -188,103 +181,97 @@ static int print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb,
/* id nodeid remid pid xid exflags flags sts grmode rqmode time_us
r_nodeid r_len r_name */
- rv = seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n",
- lkb->lkb_id,
- lkb->lkb_nodeid,
- lkb->lkb_remid,
- lkb->lkb_ownpid,
- (unsigned long long)xid,
- lkb->lkb_exflags,
- lkb->lkb_flags,
- lkb->lkb_status,
- lkb->lkb_grmode,
- lkb->lkb_rqmode,
- (unsigned long long)us,
- r->res_nodeid,
- r->res_length,
- r->res_name);
- return rv;
+ seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n",
+ lkb->lkb_id,
+ lkb->lkb_nodeid,
+ lkb->lkb_remid,
+ lkb->lkb_ownpid,
+ (unsigned long long)xid,
+ lkb->lkb_exflags,
+ lkb->lkb_flags,
+ lkb->lkb_status,
+ lkb->lkb_grmode,
+ lkb->lkb_rqmode,
+ (unsigned long long)us,
+ r->res_nodeid,
+ r->res_length,
+ r->res_name);
}
-static int print_format2(struct dlm_rsb *r, struct seq_file *s)
+static void print_format2(struct dlm_rsb *r, struct seq_file *s)
{
struct dlm_lkb *lkb;
- int rv = 0;
lock_rsb(r);
list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
- rv = print_format2_lock(s, lkb, r);
- if (rv)
+ print_format2_lock(s, lkb, r);
+ if (seq_has_overflowed(s))
goto out;
}
list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
- rv = print_format2_lock(s, lkb, r);
- if (rv)
+ print_format2_lock(s, lkb, r);
+ if (seq_has_overflowed(s))
goto out;
}
list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) {
- rv = print_format2_lock(s, lkb, r);
- if (rv)
+ print_format2_lock(s, lkb, r);
+ if (seq_has_overflowed(s))
goto out;
}
out:
unlock_rsb(r);
- return rv;
}
-static int print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb,
+static void print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb,
int rsb_lookup)
{
u64 xid = 0;
- int rv;
if (lkb->lkb_flags & DLM_IFL_USER) {
if (lkb->lkb_ua)
xid = lkb->lkb_ua->xid;
}
- rv = seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n",
- lkb->lkb_id,
- lkb->lkb_nodeid,
- lkb->lkb_remid,
- lkb->lkb_ownpid,
- (unsigned long long)xid,
- lkb->lkb_exflags,
- lkb->lkb_flags,
- lkb->lkb_status,
- lkb->lkb_grmode,
- lkb->lkb_rqmode,
- lkb->lkb_last_bast.mode,
- rsb_lookup,
- lkb->lkb_wait_type,
- lkb->lkb_lvbseq,
- (unsigned long long)ktime_to_ns(lkb->lkb_timestamp),
- (unsigned long long)ktime_to_ns(lkb->lkb_last_bast_time));
- return rv;
+ seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n",
+ lkb->lkb_id,
+ lkb->lkb_nodeid,
+ lkb->lkb_remid,
+ lkb->lkb_ownpid,
+ (unsigned long long)xid,
+ lkb->lkb_exflags,
+ lkb->lkb_flags,
+ lkb->lkb_status,
+ lkb->lkb_grmode,
+ lkb->lkb_rqmode,
+ lkb->lkb_last_bast.mode,
+ rsb_lookup,
+ lkb->lkb_wait_type,
+ lkb->lkb_lvbseq,
+ (unsigned long long)ktime_to_ns(lkb->lkb_timestamp),
+ (unsigned long long)ktime_to_ns(lkb->lkb_last_bast_time));
}
-static int print_format3(struct dlm_rsb *r, struct seq_file *s)
+static void print_format3(struct dlm_rsb *r, struct seq_file *s)
{
struct dlm_lkb *lkb;
int i, lvblen = r->res_ls->ls_lvblen;
int print_name = 1;
- int rv;
lock_rsb(r);
- rv = seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ",
- r,
- r->res_nodeid,
- r->res_first_lkid,
- r->res_flags,
- !list_empty(&r->res_root_list),
- !list_empty(&r->res_recover_list),
- r->res_recover_locks_count,
- r->res_length);
- if (rv)
+ seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ",
+ r,
+ r->res_nodeid,
+ r->res_first_lkid,
+ r->res_flags,
+ !list_empty(&r->res_root_list),
+ !list_empty(&r->res_recover_list),
+ r->res_recover_locks_count,
+ r->res_length);
+ if (seq_has_overflowed(s))
goto out;
for (i = 0; i < r->res_length; i++) {
@@ -292,7 +279,7 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s)
print_name = 0;
}
- seq_printf(s, "%s", print_name ? "str " : "hex");
+ seq_puts(s, print_name ? "str " : "hex");
for (i = 0; i < r->res_length; i++) {
if (print_name)
@@ -300,8 +287,8 @@ 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_puts(s, "\n");
- if (rv)
+ seq_puts(s, "\n");
+ if (seq_has_overflowed(s))
goto out;
if (!r->res_lvbptr)
@@ -311,65 +298,62 @@ 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_puts(s, "\n");
- if (rv)
+ seq_puts(s, "\n");
+ if (seq_has_overflowed(s))
goto out;
do_locks:
list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
- rv = print_format3_lock(s, lkb, 0);
- if (rv)
+ print_format3_lock(s, lkb, 0);
+ if (seq_has_overflowed(s))
goto out;
}
list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
- rv = print_format3_lock(s, lkb, 0);
- if (rv)
+ print_format3_lock(s, lkb, 0);
+ if (seq_has_overflowed(s))
goto out;
}
list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) {
- rv = print_format3_lock(s, lkb, 0);
- if (rv)
+ print_format3_lock(s, lkb, 0);
+ if (seq_has_overflowed(s))
goto out;
}
list_for_each_entry(lkb, &r->res_lookup, lkb_rsb_lookup) {
- rv = print_format3_lock(s, lkb, 1);
- if (rv)
+ print_format3_lock(s, lkb, 1);
+ if (seq_has_overflowed(s))
goto out;
}
out:
unlock_rsb(r);
- return rv;
}
-static int print_format4(struct dlm_rsb *r, struct seq_file *s)
+static void print_format4(struct dlm_rsb *r, struct seq_file *s)
{
int our_nodeid = dlm_our_nodeid();
int print_name = 1;
- int i, rv;
+ int i;
lock_rsb(r);
- rv = seq_printf(s, "rsb %p %d %d %d %d %lu %lx %d ",
- r,
- r->res_nodeid,
- r->res_master_nodeid,
- r->res_dir_nodeid,
- our_nodeid,
- r->res_toss_time,
- r->res_flags,
- r->res_length);
- if (rv)
- goto out;
+ seq_printf(s, "rsb %p %d %d %d %d %lu %lx %d ",
+ r,
+ r->res_nodeid,
+ r->res_master_nodeid,
+ r->res_dir_nodeid,
+ our_nodeid,
+ r->res_toss_time,
+ r->res_flags,
+ r->res_length);
for (i = 0; i < r->res_length; i++) {
if (!isascii(r->res_name[i]) || !isprint(r->res_name[i]))
print_name = 0;
}
- seq_printf(s, "%s", print_name ? "str " : "hex");
+ seq_puts(s, print_name ? "str " : "hex");
for (i = 0; i < r->res_length; i++) {
if (print_name)
@@ -377,10 +361,9 @@ 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_puts(s, "\n");
- out:
+ seq_puts(s, "\n");
+
unlock_rsb(r);
- return rv;
}
struct rsbtbl_iter {
@@ -390,47 +373,45 @@ struct rsbtbl_iter {
int header;
};
-/* seq_printf returns -1 if the buffer is full, and 0 otherwise.
- If the buffer is full, seq_printf can be called again, but it
- does nothing and just returns -1. So, the these printing routines
- periodically check the return value to avoid wasting too much time
- trying to print to a full buffer. */
+/*
+ * If the buffer is full, seq_printf can be called again, but it
+ * does nothing. So, the these printing routines periodically check
+ * seq_has_overflowed to avoid wasting too much time trying to print to
+ * a full buffer.
+ */
static int table_seq_show(struct seq_file *seq, void *iter_ptr)
{
struct rsbtbl_iter *ri = iter_ptr;
- int rv = 0;
switch (ri->format) {
case 1:
- rv = print_format1(ri->rsb, seq);
+ print_format1(ri->rsb, seq);
break;
case 2:
if (ri->header) {
- seq_printf(seq, "id nodeid remid pid xid exflags "
- "flags sts grmode rqmode time_ms "
- "r_nodeid r_len r_name\n");
+ seq_puts(seq, "id nodeid remid pid xid exflags flags sts grmode rqmode time_ms r_nodeid r_len r_name\n");
ri->header = 0;
}
- rv = print_format2(ri->rsb, seq);
+ print_format2(ri->rsb, seq);
break;
case 3:
if (ri->header) {
- seq_printf(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n");
+ seq_puts(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n");
ri->header = 0;
}
- rv = print_format3(ri->rsb, seq);
+ print_format3(ri->rsb, seq);
break;
case 4:
if (ri->header) {
- seq_printf(seq, "version 4 rsb 2\n");
+ seq_puts(seq, "version 4 rsb 2\n");
ri->header = 0;
}
- rv = print_format4(ri->rsb, seq);
+ print_format4(ri->rsb, seq);
break;
}
- return rv;
+ return 0;
}
static const struct seq_operations format1_seq_ops;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 83f3d5520307..35502d4046f5 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -5886,6 +5886,78 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
return error;
}
+/*
+ * The caller asks for an orphan lock on a given resource with a given mode.
+ * If a matching lock exists, it's moved to the owner's list of locks and
+ * the lkid is returned.
+ */
+
+int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+ int mode, uint32_t flags, void *name, unsigned int namelen,
+ unsigned long timeout_cs, uint32_t *lkid)
+{
+ struct dlm_lkb *lkb;
+ struct dlm_user_args *ua;
+ int found_other_mode = 0;
+ int found = 0;
+ int rv = 0;
+
+ mutex_lock(&ls->ls_orphans_mutex);
+ list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) {
+ if (lkb->lkb_resource->res_length != namelen)
+ continue;
+ if (memcmp(lkb->lkb_resource->res_name, name, namelen))
+ continue;
+ if (lkb->lkb_grmode != mode) {
+ found_other_mode = 1;
+ continue;
+ }
+
+ found = 1;
+ list_del_init(&lkb->lkb_ownqueue);
+ lkb->lkb_flags &= ~DLM_IFL_ORPHAN;
+ *lkid = lkb->lkb_id;
+ break;
+ }
+ mutex_unlock(&ls->ls_orphans_mutex);
+
+ if (!found && found_other_mode) {
+ rv = -EAGAIN;
+ goto out;
+ }
+
+ if (!found) {
+ rv = -ENOENT;
+ goto out;
+ }
+
+ lkb->lkb_exflags = flags;
+ lkb->lkb_ownpid = (int) current->pid;
+
+ ua = lkb->lkb_ua;
+
+ ua->proc = ua_tmp->proc;
+ ua->xid = ua_tmp->xid;
+ ua->castparam = ua_tmp->castparam;
+ ua->castaddr = ua_tmp->castaddr;
+ ua->bastparam = ua_tmp->bastparam;
+ ua->bastaddr = ua_tmp->bastaddr;
+ ua->user_lksb = ua_tmp->user_lksb;
+
+ /*
+ * The lkb reference from the ls_orphans list was not
+ * removed above, and is now considered the reference
+ * for the proc locks list.
+ */
+
+ spin_lock(&ua->proc->locks_spin);
+ list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
+ spin_unlock(&ua->proc->locks_spin);
+ out:
+ kfree(ua_tmp);
+ return rv;
+}
+
int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
uint32_t flags, uint32_t lkid, char *lvb_in)
{
@@ -6029,7 +6101,7 @@ static int orphan_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb)
struct dlm_args args;
int error;
- hold_lkb(lkb);
+ hold_lkb(lkb); /* reference for the ls_orphans list */
mutex_lock(&ls->ls_orphans_mutex);
list_add_tail(&lkb->lkb_ownqueue, &ls->ls_orphans);
mutex_unlock(&ls->ls_orphans_mutex);
@@ -6217,7 +6289,7 @@ int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
{
int error = 0;
- if (nodeid != dlm_our_nodeid()) {
+ if (nodeid && (nodeid != dlm_our_nodeid())) {
error = send_purge(ls, nodeid, pid);
} else {
dlm_lock_recovery(ls);
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index 5e0c72e36a9b..ed8ebd3a8593 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -49,6 +49,9 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
unsigned long timeout_cs);
+int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+ int mode, uint32_t flags, void *name, unsigned int namelen,
+ unsigned long timeout_cs, uint32_t *lkid);
int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
uint32_t flags, uint32_t lkid, char *lvb_in);
int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 142e21655eed..fb85f32e9eca 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -238,6 +238,7 @@ static int device_user_lock(struct dlm_user_proc *proc,
{
struct dlm_ls *ls;
struct dlm_user_args *ua;
+ uint32_t lkid;
int error = -ENOMEM;
ls = dlm_find_lockspace_local(proc->lockspace);
@@ -260,12 +261,20 @@ static int device_user_lock(struct dlm_user_proc *proc,
ua->bastaddr = params->bastaddr;
ua->xid = params->xid;
- if (params->flags & DLM_LKF_CONVERT)
+ if (params->flags & DLM_LKF_CONVERT) {
error = dlm_user_convert(ls, ua,
params->mode, params->flags,
params->lkid, params->lvb,
(unsigned long) params->timeout);
- else {
+ } else if (params->flags & DLM_LKF_ORPHAN) {
+ error = dlm_user_adopt_orphan(ls, ua,
+ params->mode, params->flags,
+ params->name, params->namelen,
+ (unsigned long) params->timeout,
+ &lkid);
+ if (!error)
+ error = lkid;
+ } else {
error = dlm_user_request(ls, ua,
params->mode, params->flags,
params->name, params->namelen,
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 1de7294aad20..2bc2c87f35e7 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -40,13 +40,14 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
static void drop_slab(void)
{
int nr_objects;
- struct shrink_control shrink = {
- .gfp_mask = GFP_KERNEL,
- };
- nodes_setall(shrink.nodes_to_scan);
do {
- nr_objects = shrink_slab(&shrink, 1000, 1000);
+ int nid;
+
+ nr_objects = 0;
+ for_each_online_node(nid)
+ nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
+ 1000, 1000);
} while (nr_objects > 10);
}
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 2f6735dbf1a9..719e1ce1c609 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1373,7 +1373,7 @@ out:
int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode)
{
struct dentry *lower_dentry =
- ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry;
+ ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry;
ssize_t size;
int rc = 0;
@@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
break;
case 2:
dst[dst_byte_offset++] |= (src_byte);
- dst[dst_byte_offset] = 0;
current_bit_offset = 0;
break;
}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index f5bce9096555..6f4e659f508f 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -75,11 +75,11 @@ struct ecryptfs_getdents_callback {
/* Inspired by generic filldir in fs/readdir.c */
static int
-ecryptfs_filldir(void *dirent, const char *lower_name, int lower_namelen,
- loff_t offset, u64 ino, unsigned int d_type)
+ecryptfs_filldir(struct dir_context *ctx, const char *lower_name,
+ int lower_namelen, loff_t offset, u64 ino, unsigned int d_type)
{
struct ecryptfs_getdents_callback *buf =
- (struct ecryptfs_getdents_callback *)dirent;
+ container_of(ctx, struct ecryptfs_getdents_callback, ctx);
size_t name_size;
char *name;
int rc;
@@ -190,23 +190,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
{
int rc = 0;
struct ecryptfs_crypt_stat *crypt_stat = NULL;
- struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct dentry *ecryptfs_dentry = file->f_path.dentry;
/* Private value of ecryptfs_dentry allocated in
* ecryptfs_lookup() */
struct ecryptfs_file_info *file_info;
- mount_crypt_stat = &ecryptfs_superblock_to_private(
- ecryptfs_dentry->d_sb)->mount_crypt_stat;
- if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
- && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
- || (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
- || (file->f_flags & O_APPEND))) {
- printk(KERN_WARNING "Mount has encrypted view enabled; "
- "files may only be read\n");
- rc = -EPERM;
- goto out;
- }
/* Released in ecryptfs_release or end of function if failure */
file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
ecryptfs_set_file_private(file, file_info);
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 635e8e16a5b7..917bd5c9776a 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -100,12 +100,12 @@ int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
(*size) = 0;
if (data[0] < 192) {
/* One-byte length */
- (*size) = (unsigned char)data[0];
+ (*size) = data[0];
(*length_size) = 1;
} else if (data[0] < 224) {
/* Two-byte length */
- (*size) = (((unsigned char)(data[0]) - 192) * 256);
- (*size) += ((unsigned char)(data[1]) + 192);
+ (*size) = (data[0] - 192) * 256;
+ (*size) += data[1] + 192;
(*length_size) = 2;
} else if (data[0] == 255) {
/* If support is added, adjust ECRYPTFS_MAX_PKT_LEN_SIZE */
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index c4cd1fd86cc2..d9eb84bda559 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
{
struct super_block *s;
struct ecryptfs_sb_info *sbi;
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct ecryptfs_dentry_info *root_info;
const char *err = "Getting sb failed";
struct inode *inode;
@@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
err = "Error parsing options";
goto out;
}
+ mount_crypt_stat = &sbi->mount_crypt_stat;
s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s)) {
@@ -557,11 +559,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
/**
* Set the POSIX ACL flag based on whether they're enabled in the lower
- * mount. Force a read-only eCryptfs mount if the lower mount is ro.
- * Allow a ro eCryptfs mount even when the lower mount is rw.
+ * mount.
*/
s->s_flags = flags & ~MS_POSIXACL;
- s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+ s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+
+ /**
+ * Force a read-only eCryptfs mount when:
+ * 1) The lower mount is ro
+ * 2) The ecryptfs_encrypted_view mount option is specified
+ */
+ if (path.dentry->d_sb->s_flags & MS_RDONLY ||
+ mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+ s->s_flags |= MS_RDONLY;
s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 564a1fa34b99..4626976794e7 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -419,7 +419,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
ssize_t size;
void *xattr_virt;
struct dentry *lower_dentry =
- ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry;
+ ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry;
struct inode *lower_inode = lower_dentry->d_inode;
int rc;
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index cdb2971192a5..90001da9abfd 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -47,8 +47,8 @@ static ssize_t efivarfs_file_write(struct file *file,
if (bytes == -ENOENT) {
drop_nlink(inode);
- d_delete(file->f_dentry);
- dput(file->f_dentry);
+ d_delete(file->f_path.dentry);
+ dput(file->f_path.dentry);
} else {
mutex_lock(&inode->i_mutex);
i_size_write(inode, datasize + sizeof(attributes));
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 0a48886e069c..6dad1176ec52 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -236,6 +236,7 @@ static void efivarfs_kill_sb(struct super_block *sb)
}
static struct file_system_type efivarfs_type = {
+ .owner = THIS_MODULE,
.name = "efivarfs",
.mount = efivarfs_mount,
.kill_sb = efivarfs_kill_sb,
@@ -244,17 +245,23 @@ static struct file_system_type efivarfs_type = {
static __init int efivarfs_init(void)
{
if (!efi_enabled(EFI_RUNTIME_SERVICES))
- return 0;
+ return -ENODEV;
if (!efivars_kobject())
- return 0;
+ return -ENODEV;
return register_filesystem(&efivarfs_type);
}
+static __exit void efivarfs_exit(void)
+{
+ unregister_filesystem(&efivarfs_type);
+}
+
MODULE_AUTHOR("Matthew Garrett, Jeremy Kerr");
MODULE_DESCRIPTION("EFI Variable Filesystem");
MODULE_LICENSE("GPL");
MODULE_ALIAS_FS("efivarfs");
module_init(efivarfs_init);
+module_exit(efivarfs_exit);
diff --git a/fs/eventfd.c b/fs/eventfd.c
index d6a88e7812f3..4b0a226024fa 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -287,17 +287,14 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
}
#ifdef CONFIG_PROC_FS
-static int eventfd_show_fdinfo(struct seq_file *m, struct file *f)
+static void eventfd_show_fdinfo(struct seq_file *m, struct file *f)
{
struct eventfd_ctx *ctx = f->private_data;
- int ret;
spin_lock_irq(&ctx->wqh.lock);
- ret = seq_printf(m, "eventfd-count: %16llx\n",
- (unsigned long long)ctx->count);
+ seq_printf(m, "eventfd-count: %16llx\n",
+ (unsigned long long)ctx->count);
spin_unlock_irq(&ctx->wqh.lock);
-
- return ret;
}
#endif
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7bcfff900f05..d77f94491352 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -870,25 +870,22 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
}
#ifdef CONFIG_PROC_FS
-static int ep_show_fdinfo(struct seq_file *m, struct file *f)
+static void ep_show_fdinfo(struct seq_file *m, struct file *f)
{
struct eventpoll *ep = f->private_data;
struct rb_node *rbp;
- int ret = 0;
mutex_lock(&ep->mtx);
for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
- ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
- epi->ffd.fd, epi->event.events,
- (long long)epi->event.data);
- if (ret)
+ seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+ epi->ffd.fd, epi->event.events,
+ (long long)epi->event.data);
+ if (seq_has_overflowed(m))
break;
}
mutex_unlock(&ep->mtx);
-
- return ret;
}
#endif
diff --git a/fs/exec.c b/fs/exec.c
index 7302b75a9820..ad8798e26be9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -277,6 +277,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
goto err;
mm->stack_vm = mm->total_vm = 1;
+ arch_bprm_mm_init(mm, vma);
up_write(&mm->mmap_sem);
bprm->p = vma->vm_end - sizeof(void *);
return 0;
@@ -747,18 +748,25 @@ EXPORT_SYMBOL(setup_arg_pages);
#endif /* CONFIG_MMU */
-static struct file *do_open_exec(struct filename *name)
+static struct file *do_open_execat(int fd, struct filename *name, int flags)
{
struct file *file;
int err;
- static const struct open_flags open_exec_flags = {
+ struct open_flags open_exec_flags = {
.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
.acc_mode = MAY_EXEC | MAY_OPEN,
.intent = LOOKUP_OPEN,
.lookup_flags = LOOKUP_FOLLOW,
};
- file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
+ if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+ return ERR_PTR(-EINVAL);
+ if (flags & AT_SYMLINK_NOFOLLOW)
+ open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW;
+ if (flags & AT_EMPTY_PATH)
+ open_exec_flags.lookup_flags |= LOOKUP_EMPTY;
+
+ file = do_filp_open(fd, name, &open_exec_flags);
if (IS_ERR(file))
goto out;
@@ -769,12 +777,13 @@ static struct file *do_open_exec(struct filename *name)
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
goto exit;
- fsnotify_open(file);
-
err = deny_write_access(file);
if (err)
goto exit;
+ if (name->name[0] != '\0')
+ fsnotify_open(file);
+
out:
return file;
@@ -786,7 +795,7 @@ exit:
struct file *open_exec(const char *name)
{
struct filename tmp = { .name = name };
- return do_open_exec(&tmp);
+ return do_open_execat(AT_FDCWD, &tmp, 0);
}
EXPORT_SYMBOL(open_exec);
@@ -1427,10 +1436,12 @@ static int exec_binprm(struct linux_binprm *bprm)
/*
* sys_execve() executes a new program.
*/
-static int do_execve_common(struct filename *filename,
- struct user_arg_ptr argv,
- struct user_arg_ptr envp)
+static int do_execveat_common(int fd, struct filename *filename,
+ struct user_arg_ptr argv,
+ struct user_arg_ptr envp,
+ int flags)
{
+ char *pathbuf = NULL;
struct linux_binprm *bprm;
struct file *file;
struct files_struct *displaced;
@@ -1471,7 +1482,7 @@ static int do_execve_common(struct filename *filename,
check_unsafe_exec(bprm);
current->in_execve = 1;
- file = do_open_exec(filename);
+ file = do_open_execat(fd, filename, flags);
retval = PTR_ERR(file);
if (IS_ERR(file))
goto out_unmark;
@@ -1479,7 +1490,28 @@ static int do_execve_common(struct filename *filename,
sched_exec();
bprm->file = file;
- bprm->filename = bprm->interp = filename->name;
+ if (fd == AT_FDCWD || filename->name[0] == '/') {
+ bprm->filename = filename->name;
+ } else {
+ if (filename->name[0] == '\0')
+ pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d", fd);
+ else
+ pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d/%s",
+ fd, filename->name);
+ if (!pathbuf) {
+ retval = -ENOMEM;
+ goto out_unmark;
+ }
+ /*
+ * Record that a name derived from an O_CLOEXEC fd will be
+ * inaccessible after exec. Relies on having exclusive access to
+ * current->files (due to unshare_files above).
+ */
+ if (close_on_exec(fd, rcu_dereference_raw(current->files->fdt)))
+ bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+ bprm->filename = pathbuf;
+ }
+ bprm->interp = bprm->filename;
retval = bprm_mm_init(bprm);
if (retval)
@@ -1520,6 +1552,7 @@ static int do_execve_common(struct filename *filename,
acct_update_integrals(current);
task_numa_free(current);
free_bprm(bprm);
+ kfree(pathbuf);
putname(filename);
if (displaced)
put_files_struct(displaced);
@@ -1537,6 +1570,7 @@ out_unmark:
out_free:
free_bprm(bprm);
+ kfree(pathbuf);
out_files:
if (displaced)
@@ -1552,7 +1586,18 @@ int do_execve(struct filename *filename,
{
struct user_arg_ptr argv = { .ptr.native = __argv };
struct user_arg_ptr envp = { .ptr.native = __envp };
- return do_execve_common(filename, argv, envp);
+ return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
+}
+
+int do_execveat(int fd, struct filename *filename,
+ const char __user *const __user *__argv,
+ const char __user *const __user *__envp,
+ int flags)
+{
+ struct user_arg_ptr argv = { .ptr.native = __argv };
+ struct user_arg_ptr envp = { .ptr.native = __envp };
+
+ return do_execveat_common(fd, filename, argv, envp, flags);
}
#ifdef CONFIG_COMPAT
@@ -1568,7 +1613,23 @@ static int compat_do_execve(struct filename *filename,
.is_compat = true,
.ptr.compat = __envp,
};
- return do_execve_common(filename, argv, envp);
+ return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
+}
+
+static int compat_do_execveat(int fd, struct filename *filename,
+ const compat_uptr_t __user *__argv,
+ const compat_uptr_t __user *__envp,
+ int flags)
+{
+ struct user_arg_ptr argv = {
+ .is_compat = true,
+ .ptr.compat = __argv,
+ };
+ struct user_arg_ptr envp = {
+ .is_compat = true,
+ .ptr.compat = __envp,
+ };
+ return do_execveat_common(fd, filename, argv, envp, flags);
}
#endif
@@ -1608,6 +1669,20 @@ SYSCALL_DEFINE3(execve,
{
return do_execve(getname(filename), argv, envp);
}
+
+SYSCALL_DEFINE5(execveat,
+ int, fd, const char __user *, filename,
+ const char __user *const __user *, argv,
+ const char __user *const __user *, envp,
+ int, flags)
+{
+ int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+ return do_execveat(fd,
+ getname_flags(filename, lookup_flags, NULL),
+ argv, envp, flags);
+}
+
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
const compat_uptr_t __user *, argv,
@@ -1615,4 +1690,17 @@ COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
{
return compat_do_execve(getname(filename), argv, envp);
}
+
+COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
+ const char __user *, filename,
+ const compat_uptr_t __user *, argv,
+ const compat_uptr_t __user *, envp,
+ int, flags)
+{
+ int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+ return compat_do_execveat(fd,
+ getname_flags(filename, lookup_flags, NULL),
+ argv, envp, flags);
+}
#endif
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index b01fbfb51f43..fdfd206c737a 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result,
inode = result->d_inode;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
dget(dentry);
spin_unlock(&inode->i_lock);
if (toput)
@@ -241,10 +241,11 @@ struct getdents_callback {
* A rather strange filldir function to capture
* the name matching the specified inode number.
*/
-static int filldir_one(void * __buf, const char * name, int len,
+static int filldir_one(struct dir_context *ctx, const char *name, int len,
loff_t pos, u64 ino, unsigned int d_type)
{
- struct getdents_callback *buf = __buf;
+ struct getdents_callback *buf =
+ container_of(ctx, struct getdents_callback, ctx);
int result = 0;
buf->sequence++;
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index d9a17d0b124d..e4279ead4a05 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -689,6 +689,9 @@ struct ext2_inode_info {
struct mutex truncate_mutex;
struct inode vfs_inode;
struct list_head i_orphan; /* unlinked but open inodes */
+#ifdef CONFIG_QUOTA
+ struct dquot *i_dquot[MAXQUOTAS];
+#endif
};
/*
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 170dc41e8bf4..ae55fddc26a9 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -166,6 +166,10 @@ static struct inode *ext2_alloc_inode(struct super_block *sb)
return NULL;
ei->i_block_alloc_info = NULL;
ei->vfs_inode.i_version = 1;
+#ifdef CONFIG_QUOTA
+ memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
+#endif
+
return &ei->vfs_inode;
}
@@ -303,6 +307,10 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
#ifdef CONFIG_QUOTA
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
+static struct dquot **ext2_get_dquots(struct inode *inode)
+{
+ return EXT2_I(inode)->i_dquot;
+}
#endif
static const struct super_operations ext2_sops = {
@@ -320,6 +328,7 @@ static const struct super_operations ext2_sops = {
#ifdef CONFIG_QUOTA
.quota_read = ext2_quota_read,
.quota_write = ext2_quota_write,
+ .get_dquots = ext2_get_dquots,
#endif
};
@@ -1090,6 +1099,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
#ifdef CONFIG_QUOTA
sb->dq_op = &dquot_operations;
sb->s_qcop = &dquot_quotactl_ops;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
#endif
root = ext2_iget(sb, EXT2_ROOT_INO);
diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h
index fc3cdcf24aed..f483a80b3fe7 100644
--- a/fs/ext3/ext3.h
+++ b/fs/ext3/ext3.h
@@ -615,6 +615,10 @@ struct ext3_inode_info {
atomic_t i_sync_tid;
atomic_t i_datasync_tid;
+#ifdef CONFIG_QUOTA
+ struct dquot *i_dquot[MAXQUOTAS];
+#endif
+
struct inode vfs_inode;
};
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index eb742d0e67ff..9b4e7d750d4f 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -485,6 +485,10 @@ static struct inode *ext3_alloc_inode(struct super_block *sb)
ei->vfs_inode.i_version = 1;
atomic_set(&ei->i_datasync_tid, 0);
atomic_set(&ei->i_sync_tid, 0);
+#ifdef CONFIG_QUOTA
+ memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
+#endif
+
return &ei->vfs_inode;
}
@@ -764,6 +768,10 @@ static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
static ssize_t ext3_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off);
+static struct dquot **ext3_get_dquots(struct inode *inode)
+{
+ return EXT3_I(inode)->i_dquot;
+}
static const struct dquot_operations ext3_quota_operations = {
.write_dquot = ext3_write_dquot,
@@ -803,6 +811,7 @@ static const struct super_operations ext3_sops = {
#ifdef CONFIG_QUOTA
.quota_read = ext3_quota_read,
.quota_write = ext3_quota_write,
+ .get_dquots = ext3_get_dquots,
#endif
.bdev_try_to_free_page = bdev_try_to_free_page,
};
@@ -2001,6 +2010,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
#ifdef CONFIG_QUOTA
sb->s_qcop = &ext3_qctl_operations;
sb->dq_op = &ext3_quota_operations;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
#endif
memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c24665ead8d1..a75fba67bb1f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -932,6 +932,10 @@ struct ext4_inode_info {
tid_t i_sync_tid;
tid_t i_datasync_tid;
+#ifdef CONFIG_QUOTA
+ struct dquot *i_dquot[MAXQUOTAS];
+#endif
+
/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
__u32 i_csum_seed;
};
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 503ea15dc5db..370420bfae8d 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -267,7 +267,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
handle_t *handle;
ext4_lblk_t orig_blk_offset, donor_blk_offset;
unsigned long blocksize = orig_inode->i_sb->s_blocksize;
- unsigned int w_flags = 0;
unsigned int tmp_data_size, data_size, replaced_size;
int err2, jblocks, retries = 0;
int replaced_count = 0;
@@ -288,9 +287,6 @@ again:
return 0;
}
- if (segment_eq(get_fs(), KERNEL_DS))
- w_flags |= AOP_FLAG_UNINTERRUPTIBLE;
-
orig_blk_offset = orig_page_offset * blocks_per_page +
data_offset_in_page;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 65b9c9eaad18..74c5f53595fb 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -883,6 +883,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
+ memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
#endif
ei->jinode = NULL;
INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
@@ -1058,6 +1059,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
unsigned int flags);
static int ext4_enable_quotas(struct super_block *sb);
+static struct dquot **ext4_get_dquots(struct inode *inode)
+{
+ return EXT4_I(inode)->i_dquot;
+}
+
static const struct dquot_operations ext4_quota_operations = {
.get_reserved_space = ext4_get_reserved_space,
.write_dquot = ext4_write_dquot,
@@ -1107,6 +1113,7 @@ static const struct super_operations ext4_sops = {
#ifdef CONFIG_QUOTA
.quota_read = ext4_quota_read,
.quota_write = ext4_quota_write,
+ .get_dquots = ext4_get_dquots,
#endif
.bdev_try_to_free_page = bdev_try_to_free_page,
};
@@ -3931,6 +3938,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sb->s_qcop = &ext4_qctl_sysfile_operations;
else
sb->s_qcop = &ext4_qctl_operations;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
#endif
memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 83b9b5a8d112..1ccb26bc2a0b 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -162,7 +162,8 @@ fail:
return ERR_PTR(-EINVAL);
}
-struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
+static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
+ struct page *dpage)
{
int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
void *value = NULL;
@@ -172,12 +173,13 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
if (type == ACL_TYPE_ACCESS)
name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
- retval = f2fs_getxattr(inode, name_index, "", NULL, 0);
+ retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
if (retval > 0) {
value = kmalloc(retval, GFP_F2FS_ZERO);
if (!value)
return ERR_PTR(-ENOMEM);
- retval = f2fs_getxattr(inode, name_index, "", value, retval);
+ retval = f2fs_getxattr(inode, name_index, "", value,
+ retval, dpage);
}
if (retval > 0)
@@ -194,6 +196,11 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
return acl;
}
+struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
+{
+ return __f2fs_get_acl(inode, type, NULL);
+}
+
static int __f2fs_set_acl(struct inode *inode, int type,
struct posix_acl *acl, struct page *ipage)
{
@@ -229,7 +236,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
if (acl) {
value = f2fs_acl_to_disk(acl, &size);
if (IS_ERR(value)) {
- cond_clear_inode_flag(fi, FI_ACL_MODE);
+ clear_inode_flag(fi, FI_ACL_MODE);
return (int)PTR_ERR(value);
}
}
@@ -240,7 +247,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
if (!error)
set_cached_acl(inode, type, acl);
- cond_clear_inode_flag(fi, FI_ACL_MODE);
+ clear_inode_flag(fi, FI_ACL_MODE);
return error;
}
@@ -249,12 +256,137 @@ int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
return __f2fs_set_acl(inode, type, acl, NULL);
}
-int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage)
+/*
+ * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create
+ * are copied from posix_acl.c
+ */
+static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
+ gfp_t flags)
+{
+ struct posix_acl *clone = NULL;
+
+ if (acl) {
+ int size = sizeof(struct posix_acl) + acl->a_count *
+ sizeof(struct posix_acl_entry);
+ clone = kmemdup(acl, size, flags);
+ if (clone)
+ atomic_set(&clone->a_refcount, 1);
+ }
+ return clone;
+}
+
+static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
+{
+ struct posix_acl_entry *pa, *pe;
+ struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
+ umode_t mode = *mode_p;
+ int not_equiv = 0;
+
+ /* assert(atomic_read(acl->a_refcount) == 1); */
+
+ FOREACH_ACL_ENTRY(pa, acl, pe) {
+ switch(pa->e_tag) {
+ case ACL_USER_OBJ:
+ pa->e_perm &= (mode >> 6) | ~S_IRWXO;
+ mode &= (pa->e_perm << 6) | ~S_IRWXU;
+ break;
+
+ case ACL_USER:
+ case ACL_GROUP:
+ not_equiv = 1;
+ break;
+
+ case ACL_GROUP_OBJ:
+ group_obj = pa;
+ break;
+
+ case ACL_OTHER:
+ pa->e_perm &= mode | ~S_IRWXO;
+ mode &= pa->e_perm | ~S_IRWXO;
+ break;
+
+ case ACL_MASK:
+ mask_obj = pa;
+ not_equiv = 1;
+ break;
+
+ default:
+ return -EIO;
+ }
+ }
+
+ if (mask_obj) {
+ mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
+ mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
+ } else {
+ if (!group_obj)
+ return -EIO;
+ group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
+ mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
+ }
+
+ *mode_p = (*mode_p & ~S_IRWXUGO) | mode;
+ return not_equiv;
+}
+
+static int f2fs_acl_create(struct inode *dir, umode_t *mode,
+ struct posix_acl **default_acl, struct posix_acl **acl,
+ struct page *dpage)
+{
+ struct posix_acl *p;
+ int ret;
+
+ if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
+ goto no_acl;
+
+ p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage);
+ if (IS_ERR(p)) {
+ if (p == ERR_PTR(-EOPNOTSUPP))
+ goto apply_umask;
+ return PTR_ERR(p);
+ }
+
+ if (!p)
+ goto apply_umask;
+
+ *acl = f2fs_acl_clone(p, GFP_NOFS);
+ if (!*acl)
+ return -ENOMEM;
+
+ ret = f2fs_acl_create_masq(*acl, mode);
+ if (ret < 0) {
+ posix_acl_release(*acl);
+ return -ENOMEM;
+ }
+
+ if (ret == 0) {
+ posix_acl_release(*acl);
+ *acl = NULL;
+ }
+
+ if (!S_ISDIR(*mode)) {
+ posix_acl_release(p);
+ *default_acl = NULL;
+ } else {
+ *default_acl = p;
+ }
+ return 0;
+
+apply_umask:
+ *mode &= ~current_umask();
+no_acl:
+ *default_acl = NULL;
+ *acl = NULL;
+ return 0;
+}
+
+int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
+ struct page *dpage)
{
- struct posix_acl *default_acl, *acl;
+ struct posix_acl *default_acl = NULL, *acl = NULL;
int error = 0;
- error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+ error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage);
if (error)
return error;
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index e0864651cdc1..997ca8edb6cb 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -38,14 +38,15 @@ struct f2fs_acl_header {
extern struct posix_acl *f2fs_get_acl(struct inode *, int);
extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-extern int f2fs_init_acl(struct inode *, struct inode *, struct page *);
+extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,
+ struct page *);
#else
#define f2fs_check_acl NULL
#define f2fs_get_acl NULL
#define f2fs_set_acl NULL
static inline int f2fs_init_acl(struct inode *inode, struct inode *dir,
- struct page *page)
+ struct page *ipage, struct page *dpage)
{
return 0;
}
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index dd10a031c052..e6c271fefaca 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -72,36 +72,36 @@ out:
return page;
}
-struct page *get_meta_page_ra(struct f2fs_sb_info *sbi, pgoff_t index)
-{
- bool readahead = false;
- struct page *page;
-
- page = find_get_page(META_MAPPING(sbi), index);
- if (!page || (page && !PageUptodate(page)))
- readahead = true;
- f2fs_put_page(page, 0);
-
- if (readahead)
- ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
- return get_meta_page(sbi, index);
-}
-
-static inline block_t get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
{
switch (type) {
case META_NAT:
- return NM_I(sbi)->max_nid / NAT_ENTRY_PER_BLOCK;
+ break;
case META_SIT:
- return SIT_BLK_CNT(sbi);
+ if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
+ return false;
+ break;
case META_SSA:
+ if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
+ blkaddr < SM_I(sbi)->ssa_blkaddr))
+ return false;
+ break;
case META_CP:
- return 0;
+ if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
+ blkaddr < __start_cp_addr(sbi)))
+ return false;
+ break;
case META_POR:
- return MAX_BLKADDR(sbi);
+ if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
+ blkaddr < MAIN_BLKADDR(sbi)))
+ return false;
+ break;
default:
BUG();
}
+
+ return true;
}
/*
@@ -112,7 +112,6 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
block_t prev_blk_addr = 0;
struct page *page;
block_t blkno = start;
- block_t max_blks = get_max_meta_blks(sbi, type);
struct f2fs_io_info fio = {
.type = META,
@@ -122,18 +121,20 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
for (; nrpages-- > 0; blkno++) {
block_t blk_addr;
+ if (!is_valid_blkaddr(sbi, blkno, type))
+ goto out;
+
switch (type) {
case META_NAT:
- /* get nat block addr */
- if (unlikely(blkno >= max_blks))
+ if (unlikely(blkno >=
+ NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
blkno = 0;
+ /* get nat block addr */
blk_addr = current_nat_addr(sbi,
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
/* get sit block addr */
- if (unlikely(blkno >= max_blks))
- goto out;
blk_addr = current_sit_addr(sbi,
blkno * SIT_ENTRY_PER_BLOCK);
if (blkno != start && prev_blk_addr + 1 != blk_addr)
@@ -143,10 +144,6 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
case META_SSA:
case META_CP:
case META_POR:
- if (unlikely(blkno >= max_blks))
- goto out;
- if (unlikely(blkno < SEG0_BLKADDR(sbi)))
- goto out;
blk_addr = blkno;
break;
default:
@@ -169,6 +166,20 @@ out:
return blkno - start;
}
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ struct page *page;
+ bool readahead = false;
+
+ page = find_get_page(META_MAPPING(sbi), index);
+ if (!page || (page && !PageUptodate(page)))
+ readahead = true;
+ f2fs_put_page(page, 0);
+
+ if (readahead)
+ ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
+}
+
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
@@ -178,7 +189,7 @@ static int f2fs_write_meta_page(struct page *page,
if (unlikely(sbi->por_doing))
goto redirty_out;
- if (wbc->for_reclaim)
+ if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
@@ -187,6 +198,9 @@ static int f2fs_write_meta_page(struct page *page,
write_meta_page(sbi, page);
dec_page_count(sbi, F2FS_DIRTY_META);
unlock_page(page);
+
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio(sbi, META, WRITE);
return 0;
redirty_out:
@@ -298,46 +312,57 @@ const struct address_space_operations f2fs_meta_aops = {
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
+ struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
retry:
- spin_lock(&sbi->ino_lock[type]);
+ if (radix_tree_preload(GFP_NOFS)) {
+ cond_resched();
+ goto retry;
+ }
+
+ spin_lock(&im->ino_lock);
- e = radix_tree_lookup(&sbi->ino_root[type], ino);
+ e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC);
if (!e) {
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
+ radix_tree_preload_end();
goto retry;
}
- if (radix_tree_insert(&sbi->ino_root[type], ino, e)) {
- spin_unlock(&sbi->ino_lock[type]);
+ if (radix_tree_insert(&im->ino_root, ino, e)) {
+ spin_unlock(&im->ino_lock);
kmem_cache_free(ino_entry_slab, e);
+ radix_tree_preload_end();
goto retry;
}
memset(e, 0, sizeof(struct ino_entry));
e->ino = ino;
- list_add_tail(&e->list, &sbi->ino_list[type]);
+ list_add_tail(&e->list, &im->ino_list);
+ if (type != ORPHAN_INO)
+ im->ino_num++;
}
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
+ radix_tree_preload_end();
}
static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
+ struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
- spin_lock(&sbi->ino_lock[type]);
- e = radix_tree_lookup(&sbi->ino_root[type], ino);
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
if (e) {
list_del(&e->list);
- radix_tree_delete(&sbi->ino_root[type], ino);
- if (type == ORPHAN_INO)
- sbi->n_orphans--;
- spin_unlock(&sbi->ino_lock[type]);
+ radix_tree_delete(&im->ino_root, ino);
+ im->ino_num--;
+ spin_unlock(&im->ino_lock);
kmem_cache_free(ino_entry_slab, e);
return;
}
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
}
void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -355,10 +380,12 @@ void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
/* mode should be APPEND_INO or UPDATE_INO */
bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
+ struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
- spin_lock(&sbi->ino_lock[mode]);
- e = radix_tree_lookup(&sbi->ino_root[mode], ino);
- spin_unlock(&sbi->ino_lock[mode]);
+
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
+ spin_unlock(&im->ino_lock);
return e ? true : false;
}
@@ -368,36 +395,42 @@ void release_dirty_inode(struct f2fs_sb_info *sbi)
int i;
for (i = APPEND_INO; i <= UPDATE_INO; i++) {
- spin_lock(&sbi->ino_lock[i]);
- list_for_each_entry_safe(e, tmp, &sbi->ino_list[i], list) {
+ struct inode_management *im = &sbi->im[i];
+
+ spin_lock(&im->ino_lock);
+ list_for_each_entry_safe(e, tmp, &im->ino_list, list) {
list_del(&e->list);
- radix_tree_delete(&sbi->ino_root[i], e->ino);
+ radix_tree_delete(&im->ino_root, e->ino);
kmem_cache_free(ino_entry_slab, e);
+ im->ino_num--;
}
- spin_unlock(&sbi->ino_lock[i]);
+ spin_unlock(&im->ino_lock);
}
}
int acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- if (unlikely(sbi->n_orphans >= sbi->max_orphans))
+ spin_lock(&im->ino_lock);
+ if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
- sbi->n_orphans++;
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ im->ino_num++;
+ spin_unlock(&im->ino_lock);
return err;
}
void release_orphan_inode(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- f2fs_bug_on(sbi, sbi->n_orphans == 0);
- sbi->n_orphans--;
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
+
+ spin_lock(&im->ino_lock);
+ f2fs_bug_on(sbi, im->ino_num == 0);
+ im->ino_num--;
+ spin_unlock(&im->ino_lock);
}
void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
@@ -460,17 +493,19 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
struct f2fs_orphan_block *orphan_blk = NULL;
unsigned int nentries = 0;
unsigned short index;
- unsigned short orphan_blocks =
- (unsigned short)GET_ORPHAN_BLOCKS(sbi->n_orphans);
+ unsigned short orphan_blocks;
struct page *page = NULL;
struct ino_entry *orphan = NULL;
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
+
+ orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num);
for (index = 0; index < orphan_blocks; index++)
grab_meta_page(sbi, start_blk + index);
index = 1;
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- head = &sbi->ino_list[ORPHAN_INO];
+ spin_lock(&im->ino_lock);
+ head = &im->ino_list;
/* loop for each orphan inode entry and write them in Jornal block */
list_for_each_entry(orphan, head, list) {
@@ -510,7 +545,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
f2fs_put_page(page, 1);
}
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ spin_unlock(&im->ino_lock);
}
static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
@@ -731,6 +766,9 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
struct dir_inode_entry *entry;
struct inode *inode;
retry:
+ if (unlikely(f2fs_cp_error(sbi)))
+ return;
+
spin_lock(&sbi->dir_inode_lock);
head = &sbi->dir_inode_list;
@@ -830,6 +868,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
nid_t last_nid = nm_i->next_scan_nid;
block_t start_blk;
struct page *cp_page;
@@ -889,7 +928,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
else
clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
- orphan_blocks = GET_ORPHAN_BLOCKS(sbi->n_orphans);
+ orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
@@ -905,7 +944,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
orphan_blocks);
}
- if (sbi->n_orphans)
+ if (orphan_num)
set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
else
clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
@@ -940,7 +979,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_put_page(cp_page, 1);
}
- if (sbi->n_orphans) {
+ if (orphan_num) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
}
@@ -975,6 +1014,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* Here, we only have one bio having CP pack */
sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+ /* wait for previous submitted meta pages writeback */
+ wait_on_all_pages_writeback(sbi);
+
release_dirty_inode(sbi);
if (unlikely(f2fs_cp_error(sbi)))
@@ -1036,9 +1078,12 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi)
int i;
for (i = 0; i < MAX_INO_ENTRY; i++) {
- INIT_RADIX_TREE(&sbi->ino_root[i], GFP_ATOMIC);
- spin_lock_init(&sbi->ino_lock[i]);
- INIT_LIST_HEAD(&sbi->ino_list[i]);
+ struct inode_management *im = &sbi->im[i];
+
+ INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC);
+ spin_lock_init(&im->ino_lock);
+ INIT_LIST_HEAD(&im->ino_list);
+ im->ino_num = 0;
}
/*
@@ -1047,7 +1092,6 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi)
* orphan entries with the limitation one reserved segment
* for cp pack we can have max 1020*504 orphan entries
*/
- sbi->n_orphans = 0;
sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
NR_CURSEG_TYPE) * F2FS_ORPHANS_PER_BLOCK;
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8e58c4cc2cb9..7ec697b37f19 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -61,11 +61,6 @@ static void f2fs_write_end_io(struct bio *bio, int err)
dec_page_count(sbi, F2FS_WRITEBACK);
}
- if (sbi->wait_io) {
- complete(sbi->wait_io);
- sbi->wait_io = NULL;
- }
-
if (!get_pages(sbi, F2FS_WRITEBACK) &&
!list_empty(&sbi->cp_wait.task_list))
wake_up(&sbi->cp_wait);
@@ -95,34 +90,18 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
- int rw;
if (!io->bio)
return;
- rw = fio->rw;
-
- if (is_read_io(rw)) {
- trace_f2fs_submit_read_bio(io->sbi->sb, rw,
- fio->type, io->bio);
- submit_bio(rw, io->bio);
- } else {
- trace_f2fs_submit_write_bio(io->sbi->sb, rw,
- fio->type, io->bio);
- /*
- * META_FLUSH is only from the checkpoint procedure, and we
- * should wait this metadata bio for FS consistency.
- */
- if (fio->type == META_FLUSH) {
- DECLARE_COMPLETION_ONSTACK(wait);
- io->sbi->wait_io = &wait;
- submit_bio(rw, io->bio);
- wait_for_completion(&wait);
- } else {
- submit_bio(rw, io->bio);
- }
- }
+ if (is_read_io(fio->rw))
+ trace_f2fs_submit_read_bio(io->sbi->sb, fio->rw,
+ fio->type, io->bio);
+ else
+ trace_f2fs_submit_write_bio(io->sbi->sb, fio->rw,
+ fio->type, io->bio);
+ submit_bio(fio->rw, io->bio);
io->bio = NULL;
}
@@ -257,9 +236,6 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
bool need_put = dn->inode_page ? false : true;
int err;
- /* if inode_page exists, index should be zero */
- f2fs_bug_on(F2FS_I_SB(dn->inode), !need_put && index);
-
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
@@ -740,14 +716,14 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
- int ret;
+ int ret = -EAGAIN;
trace_f2fs_readpage(page, DATA);
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
- else
+ if (ret == -EAGAIN)
ret = mpage_readpage(page, get_data_block);
return ret;
@@ -859,10 +835,11 @@ write:
else if (has_not_enough_free_secs(sbi, 0))
goto redirty_out;
+ err = -EAGAIN;
f2fs_lock_op(sbi);
- if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode))
- err = f2fs_write_inline_data(inode, page, offset);
- else
+ if (f2fs_has_inline_data(inode))
+ err = f2fs_write_inline_data(inode, page);
+ if (err == -EAGAIN)
err = do_write_data_page(page, &fio);
f2fs_unlock_op(sbi);
done:
@@ -951,7 +928,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct page *page;
+ struct page *page, *ipage;
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
int err = 0;
@@ -959,45 +936,60 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
trace_f2fs_write_begin(inode, pos, len, flags);
f2fs_balance_fs(sbi);
-repeat:
- err = f2fs_convert_inline_data(inode, pos + len, NULL);
- if (err)
- goto fail;
+ /*
+ * We should check this at this moment to avoid deadlock on inode page
+ * and #0 page. The locking rule for inline_data conversion should be:
+ * lock_page(page #0) -> lock_page(inode_page)
+ */
+ if (index != 0) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ goto fail;
+ }
+repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
err = -ENOMEM;
goto fail;
}
- /* to avoid latency during memory pressure */
- unlock_page(page);
-
*pagep = page;
- if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
- goto inline_data;
-
f2fs_lock_op(sbi);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_reserve_block(&dn, index);
- f2fs_unlock_op(sbi);
- if (err) {
- f2fs_put_page(page, 0);
- goto fail;
- }
-inline_data:
- lock_page(page);
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
- goto repeat;
+
+ /* check inline_data */
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto unlock_fail;
}
- f2fs_wait_on_page_writeback(page, DATA);
+ set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+ if (f2fs_has_inline_data(inode)) {
+ if (pos + len <= MAX_INLINE_DATA) {
+ read_inline_data(page, ipage);
+ set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+ sync_inode_page(&dn);
+ goto put_next;
+ }
+ err = f2fs_convert_inline_page(&dn, page);
+ if (err)
+ goto put_fail;
+ }
+ err = f2fs_reserve_block(&dn, index);
+ if (err)
+ goto put_fail;
+put_next:
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
return 0;
+ f2fs_wait_on_page_writeback(page, DATA);
+
if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
unsigned start = pos & (PAGE_CACHE_SIZE - 1);
unsigned end = start + len;
@@ -1010,18 +1002,10 @@ inline_data:
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
- if (f2fs_has_inline_data(inode)) {
- err = f2fs_read_inline_data(inode, page);
- if (err) {
- page_cache_release(page);
- goto fail;
- }
- } else